4043 files changed, 104040 insertions, 59675 deletions

diff --git a/.mailmap b/.mailmap
index 29ddeb1bf015..d96147eb1a68 100644
--- a/.mailmap
+++ b/.mailmap
@@ -81,6 +81,9 @@ Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
 Jean Tourrilhes <jt@hpl.hp.com>
 Jeff Garzik <jgarzik@pretzel.yyz.us>
+Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
+Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net>
+Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com>
 Jens Axboe <axboe@suse.de>
 Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 Johan Hovold <johan@kernel.org> <jhovold@gmail.com>
diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats
index f91a973a37fe..abac31d216de 100644
--- a/Documentation/ABI/testing/procfs-diskstats
+++ b/Documentation/ABI/testing/procfs-diskstats
@@ -5,6 +5,7 @@ Description:
 		The /proc/diskstats file displays the I/O statistics
 		of block devices. Each line contains the following 14
 		fields:
+
 		 1 - major number
 		 2 - minor mumber
 		 3 - device name
@@ -19,4 +20,13 @@ Description:
 		12 - I/Os currently in progress
 		13 - time spent doing I/Os (ms)
 		14 - weighted time spent doing I/Os (ms)
+
+		Kernel 4.18+ appends four more fields for discard
+		tracking putting the total at 18:
+
+		15 - discards completed successfully
+		16 - discards merged
+		17 - sectors discarded
+		18 - time spent discarding
+
 		For more details refer to Documentation/iostats.txt
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 9c5e7732d249..73318225a368 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -476,6 +476,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
+		/sys/devices/system/cpu/vulnerabilities/l1tf
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
@@ -487,3 +488,26 @@ Description:	Information about CPU vulnerabilities
 		"Not affected"	  CPU is not affected by the vulnerability
 		"Vulnerable"	  CPU is affected and no mitigation in effect
 		"Mitigation: $M"  CPU is affected and mitigation $M is in effect
+
+		Details about the l1tf file can be found in
+		Documentation/admin-guide/l1tf.rst
+
+What:		/sys/devices/system/cpu/smt
+		/sys/devices/system/cpu/smt/active
+		/sys/devices/system/cpu/smt/control
+Date:		June 2018
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Control Symetric Multi Threading (SMT)
+
+		active:  Tells whether SMT is active (enabled and siblings online)
+
+		control: Read/write interface to control SMT. Possible
+			 values:
+
+			 "on"		SMT is enabled
+			 "off"		SMT is disabled
+			 "forceoff"	SMT is force disabled. Cannot be changed.
+			 "notsupported" SMT is not supported by the CPU
+
+			 If control status is "forceoff" or "notsupported" writes
+			 are rejected.
diff --git a/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator b/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator
new file mode 100644
index 000000000000..4d63a7904b94
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator
@@ -0,0 +1,27 @@
+What:		/sys/bus/i2c/devices/.../bd9571mwv-regulator.*.auto/backup_mode
+Date:		Jul 2018
+KernelVersion:	4.19
+Contact:	Geert Uytterhoeven <geert+renesas@glider.be>
+Description:	Read/write the current state of DDR Backup Mode, which controls
+		if DDR power rails will be kept powered during system suspend.
+		("on"/"1" = enabled, "off"/"0" = disabled).
+		Two types of power switches (or control signals) can be used:
+		  A. With a momentary power switch (or pulse signal), DDR
+		     Backup Mode is enabled by default when available, as the
+		     PMIC will be configured only during system suspend.
+		  B. With a toggle power switch (or level signal), the
+		     following steps must be followed exactly:
+		       1. Configure PMIC for backup mode, to change the role of
+			  the accessory power switch from a power switch to a
+			  wake-up switch,
+		       2. Switch accessory power switch off, to prepare for
+			  system suspend, which is a manual step not controlled
+			  by software,
+		       3. Suspend system,
+		       4. Switch accessory power switch on, to resume the
+			  system.
+		     DDR Backup Mode must be explicitly enabled by the user,
+		     to invoke step 1.
+		See also Documentation/devicetree/bindings/mfd/bd9571mwv.txt.
+Users:		User space applications for embedded boards equipped with a
+		BD9571MWV PMIC.
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
index 6c06e10bd04b..f5120a00f511 100644
--- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html
+++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
@@ -380,31 +380,26 @@ and therefore need no protection.
 as follows:
 
 <pre>
-  1   unsigned long gpnum;
-  2   unsigned long completed;
+  1   unsigned long gp_seq;
 </pre>
 
 <p>RCU grace periods are numbered, and
-the <tt>-&gt;gpnum</tt> field contains the number of the grace
-period that started most recently.
-The <tt>-&gt;completed</tt> field contains the number of the
-grace period that completed most recently.
-If the two fields are equal, the RCU grace period that most recently
-started has already completed, and therefore the corresponding
-flavor of RCU is idle.
-If <tt>-&gt;gpnum</tt> is one greater than <tt>-&gt;completed</tt>,
-then <tt>-&gt;gpnum</tt> gives the number of the current RCU
-grace period, which has not yet completed.
-Any other combination of values indicates that something is broken.
-These two fields are protected by the root <tt>rcu_node</tt>'s
+the <tt>-&gt;gp_seq</tt> field contains the current grace-period
+sequence number.
+The bottom two bits are the state of the current grace period,
+which can be zero for not yet started or one for in progress.
+In other words, if the bottom two bits of <tt>-&gt;gp_seq</tt> are
+zero, the corresponding flavor of RCU is idle.
+Any other value in the bottom two bits indicates that something is broken.
+This field is protected by the root <tt>rcu_node</tt> structure's
 <tt>-&gt;lock</tt> field.
 
-</p><p>There are <tt>-&gt;gpnum</tt> and <tt>-&gt;completed</tt> fields
+</p><p>There are <tt>-&gt;gp_seq</tt> fields
 in the <tt>rcu_node</tt> and <tt>rcu_data</tt> structures
 as well.
 The fields in the <tt>rcu_state</tt> structure represent the
-most current values, and those of the other structures are compared
-in order to detect the start of a new grace period in a distributed
+most current value, and those of the other structures are compared
+in order to detect the beginnings and ends of grace periods in a distributed
 fashion.
 The values flow from <tt>rcu_state</tt> to <tt>rcu_node</tt>
 (down the tree from the root to the leaves) to <tt>rcu_data</tt>.
@@ -512,27 +507,47 @@ than to be heisenbugged out of existence.
 as follows:
 
 <pre>
-  1   unsigned long gpnum;
-  2   unsigned long completed;
+  1   unsigned long gp_seq;
+  2   unsigned long gp_seq_needed;
 </pre>
 
-<p>These fields are the counterparts of the fields of the same name in
-the <tt>rcu_state</tt> structure.
-They each may lag up to one behind their <tt>rcu_state</tt>
-counterparts.
-If a given <tt>rcu_node</tt> structure's <tt>-&gt;gpnum</tt> and
-<tt>-&gt;complete</tt> fields are equal, then this <tt>rcu_node</tt>
+<p>The <tt>rcu_node</tt> structures' <tt>-&gt;gp_seq</tt> fields are
+the counterparts of the field of the same name in the <tt>rcu_state</tt>
+structure.
+They each may lag up to one step behind their <tt>rcu_state</tt>
+counterpart.
+If the bottom two bits of a given <tt>rcu_node</tt> structure's
+<tt>-&gt;gp_seq</tt> field is zero, then this <tt>rcu_node</tt>
 structure believes that RCU is idle.
-Otherwise, as with the <tt>rcu_state</tt> structure,
-the <tt>-&gt;gpnum</tt> field will be one greater than the
-<tt>-&gt;complete</tt> fields, with <tt>-&gt;gpnum</tt>
-indicating which grace period this <tt>rcu_node</tt> believes
-is still being waited for.
+</p><p>The <tt>&gt;gp_seq</tt> field of each <tt>rcu_node</tt>
+structure is updated at the beginning and the end
+of each grace period.
+
+<p>The <tt>-&gt;gp_seq_needed</tt> fields record the
+furthest-in-the-future grace period request seen by the corresponding
+<tt>rcu_node</tt> structure.  The request is considered fulfilled when
+the value of the <tt>-&gt;gp_seq</tt> field equals or exceeds that of
+the <tt>-&gt;gp_seq_needed</tt> field.
 
-</p><p>The <tt>&gt;gpnum</tt> field of each <tt>rcu_node</tt>
-structure is updated at the beginning
-of each grace period, and the <tt>-&gt;completed</tt> fields are
-updated at the end of each grace period.
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	Suppose that this <tt>rcu_node</tt> structure doesn't see
+	a request for a very long time.
+	Won't wrapping of the <tt>-&gt;gp_seq</tt> field cause
+	problems?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	No, because if the <tt>-&gt;gp_seq_needed</tt> field lags behind the
+	<tt>-&gt;gp_seq</tt> field, the <tt>-&gt;gp_seq_needed</tt> field
+	will be updated at the end of the grace period.
+	Modulo-arithmetic comparisons therefore will always get the
+	correct answer, even with wrapping.
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
 
 <h5>Quiescent-State Tracking</h5>
 
@@ -626,9 +641,8 @@ normal and expedited grace periods, respectively.
 	</ol>
 
 	<p><font color="ffffff">So the locking is absolutely required in
-	order to coordinate
-	clearing of the bits with the grace-period numbers in
-	<tt>-&gt;gpnum</tt> and <tt>-&gt;completed</tt>.
+	order to coordinate clearing of the bits with updating of the
+	grace-period sequence number in <tt>-&gt;gp_seq</tt>.
 </font></td></tr>
 <tr><td>&nbsp;</td></tr>
 </table>
@@ -1038,15 +1052,15 @@ out any <tt>rcu_data</tt> structure for which this flag is not set.
 as follows:
 
 <pre>
-  1   unsigned long completed;
-  2   unsigned long gpnum;
+  1   unsigned long gp_seq;
+  2   unsigned long gp_seq_needed;
   3   bool cpu_no_qs;
   4   bool core_needs_qs;
   5   bool gpwrap;
   6   unsigned long rcu_qs_ctr_snap;
 </pre>
 
-<p>The <tt>completed</tt> and <tt>gpnum</tt>
+<p>The <tt>-&gt;gp_seq</tt> and <tt>-&gt;gp_seq_needed</tt>
 fields are the counterparts of the fields of the same name
 in the <tt>rcu_state</tt> and <tt>rcu_node</tt> structures.
 They may each lag up to one behind their <tt>rcu_node</tt>
@@ -1054,15 +1068,9 @@ counterparts, but in <tt>CONFIG_NO_HZ_IDLE</tt> and
 <tt>CONFIG_NO_HZ_FULL</tt> kernels can lag
 arbitrarily far behind for CPUs in dyntick-idle mode (but these counters
 will catch up upon exit from dyntick-idle mode).
-If a given <tt>rcu_data</tt> structure's <tt>-&gt;gpnum</tt> and
-<tt>-&gt;complete</tt> fields are equal, then this <tt>rcu_data</tt>
+If the lower two bits of a given <tt>rcu_data</tt> structure's
+<tt>-&gt;gp_seq</tt> are zero, then this <tt>rcu_data</tt>
 structure believes that RCU is idle.
-Otherwise, as with the <tt>rcu_state</tt> and <tt>rcu_node</tt>
-structure,
-the <tt>-&gt;gpnum</tt> field will be one greater than the
-<tt>-&gt;complete</tt> fields, with <tt>-&gt;gpnum</tt>
-indicating which grace period this <tt>rcu_data</tt> believes
-is still being waited for.
 
 <table>
 <tr><th>&nbsp;</th></tr>
@@ -1070,13 +1078,13 @@ is still being waited for.
 <tr><td>
 	All this replication of the grace period numbers can only cause
 	massive confusion.
-	Why not just keep a global pair of counters and be done with it???
+	Why not just keep a global sequence number and be done with it???
 </td></tr>
 <tr><th align="left">Answer:</th></tr>
 <tr><td bgcolor="#ffffff"><font color="ffffff">
-	Because if there was only a single global pair of grace-period
+	Because if there was only a single global sequence
 	numbers, there would need to be a single global lock to allow
-	safely accessing and updating them.
+	safely accessing and updating it.
 	And if we are not going to have a single global lock, we need
 	to carefully manage the numbers on a per-node basis.
 	Recall from the answer to a previous Quick Quiz that the consequences
@@ -1091,8 +1099,8 @@ CPU has not yet passed through a quiescent state,
 while the <tt>-&gt;core_needs_qs</tt> flag indicates that the
 RCU core needs a quiescent state from the corresponding CPU.
 The <tt>-&gt;gpwrap</tt> field indicates that the corresponding
-CPU has remained idle for so long that the <tt>completed</tt>
-and <tt>gpnum</tt> counters are in danger of overflow, which
+CPU has remained idle for so long that the
+<tt>gp_seq</tt> counter is in danger of overflow, which
 will cause the CPU to disregard the values of its counters on
 its next exit from idle.
 Finally, the <tt>rcu_qs_ctr_snap</tt> field is used to detect
@@ -1130,10 +1138,10 @@ The CPU advances the callbacks in its <tt>rcu_data</tt> structure
 whenever it notices that another RCU grace period has completed.
 The CPU detects the completion of an RCU grace period by noticing
 that the value of its <tt>rcu_data</tt> structure's
-<tt>-&gt;completed</tt> field differs from that of its leaf
+<tt>-&gt;gp_seq</tt> field differs from that of its leaf
 <tt>rcu_node</tt> structure.
 Recall that each <tt>rcu_node</tt> structure's
-<tt>-&gt;completed</tt> field is updated at the end of each
+<tt>-&gt;gp_seq</tt> field is updated at the beginnings and ends of each
 grace period.
 
 <p>
diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
index 8651b0b4fd79..a346ce0116eb 100644
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
+++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
@@ -357,7 +357,7 @@ parts, starting in this section with the various phases of
 grace-period initialization.
 
 <p>The first ordering-related grace-period initialization action is to
-increment the <tt>rcu_state</tt> structure's <tt>-&gt;gpnum</tt>
+advance the <tt>rcu_state</tt> structure's <tt>-&gt;gp_seq</tt>
 grace-period-number counter, as shown below:
 
 </p><p><img src="TreeRCU-gp-init-1.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
@@ -388,7 +388,7 @@ its last CPU and if the next <tt>rcu_node</tt> structure has no online CPUs).
 
 <p>The final <tt>rcu_gp_init()</tt> pass through the <tt>rcu_node</tt>
 tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's
-<tt>-&gt;gpnum</tt> field to the newly incremented value from the
+<tt>-&gt;gp_seq</tt> field to the newly advanced value from the
 <tt>rcu_state</tt> structure, as shown in the following diagram.
 
 </p><p><img src="TreeRCU-gp-init-3.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
@@ -398,9 +398,9 @@ tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's
 to notice that a new grace period has started, as described in the next
 section.
 But because the grace-period kthread started the grace period at the
-root (with the increment of the <tt>rcu_state</tt> structure's
-<tt>-&gt;gpnum</tt> field) before setting each leaf <tt>rcu_node</tt>
-structure's <tt>-&gt;gpnum</tt> field, each CPU's observation of
+root (with the advancing of the <tt>rcu_state</tt> structure's
+<tt>-&gt;gp_seq</tt> field) before setting each leaf <tt>rcu_node</tt>
+structure's <tt>-&gt;gp_seq</tt> field, each CPU's observation of
 the start of the grace period will happen after the actual start
 of the grace period.
 
@@ -466,7 +466,7 @@ section that the grace period must wait on.
 <tr><td>
 	But a RCU read-side critical section might have started
 	after the beginning of the grace period
-	(the <tt>-&gt;gpnum++</tt> from earlier), so why should
+	(the advancing of <tt>-&gt;gp_seq</tt> from earlier), so why should
 	the grace period wait on such a critical section?
 </td></tr>
 <tr><th align="left">Answer:</th></tr>
@@ -609,10 +609,8 @@ states outstanding from other CPUs.
 <h4><a name="Grace-Period Cleanup">Grace-Period Cleanup</a></h4>
 
 <p>Grace-period cleanup first scans the <tt>rcu_node</tt> tree
-breadth-first setting all the <tt>-&gt;completed</tt> fields equal
-to the number of the newly completed grace period, then it sets
-the <tt>rcu_state</tt> structure's <tt>-&gt;completed</tt> field,
-again to the number of the newly completed grace period.
+breadth-first advancing all the <tt>-&gt;gp_seq</tt> fields, then it
+advances the <tt>rcu_state</tt> structure's <tt>-&gt;gp_seq</tt> field.
 The ordering effects are shown below:
 
 </p><p><img src="TreeRCU-gp-cleanup.svg" alt="TreeRCU-gp-cleanup.svg" width="75%">
@@ -634,7 +632,7 @@ grace-period cleanup is complete, the next grace period can begin.
 	CPU has reported its quiescent state, but it may be some
 	milliseconds before RCU becomes aware of this.
 	The latest reasonable candidate is once the <tt>rcu_state</tt>
-	structure's <tt>-&gt;completed</tt> field has been updated,
+	structure's <tt>-&gt;gp_seq</tt> field has been updated,
 	but it is quite possible that some CPUs have already completed
 	phase two of their updates by that time.
 	In short, if you are going to work with RCU, you need to
@@ -647,7 +645,7 @@ grace-period cleanup is complete, the next grace period can begin.
 <h4><a name="Callback Invocation">Callback Invocation</a></h4>
 
 <p>Once a given CPU's leaf <tt>rcu_node</tt> structure's
-<tt>-&gt;completed</tt> field has been updated, that CPU can begin
+<tt>-&gt;gp_seq</tt> field has been updated, that CPU can begin
 invoking its RCU callbacks that were waiting for this grace period
 to end.
 These callbacks are identified by <tt>rcu_advance_cbs()</tt>,
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg
index 754f426b297a..bf84fbab27ee 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg
@@ -384,11 +384,11 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.70710678"
-     inkscape:cx="617.89017"
-     inkscape:cy="542.52419"
-     inkscape:window-x="86"
-     inkscape:window-y="28"
+     inkscape:zoom="0.78716603"
+     inkscape:cx="513.06403"
+     inkscape:cy="623.1214"
+     inkscape:window-x="102"
+     inkscape:window-y="38"
      inkscape:window-maximized="0"
      inkscape:current-layer="g3188-3"
      fit-margin-top="5"
@@ -417,13 +417,15 @@
      id="g3188">
     <text
        xml:space="preserve"
-       x="3199.1516"
+       x="3145.9592"
        y="13255.592"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3143">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     <g
        id="g3107"
        transform="translate(947.90548,11584.029)">
@@ -502,13 +504,15 @@
     </g>
     <text
        xml:space="preserve"
-       x="5324.5371"
-       y="15414.598"
+       x="5264.4731"
+       y="15428.84"
        font-style="normal"
        font-weight="bold"
        font-size="192"
-       id="text202-753"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       id="text202-36-7"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-5">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      style="fill:none;stroke-width:0.025in"
@@ -547,15 +551,6 @@
        sodipodi:linespacing="125%"><tspan
          style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
          id="tspan3104-6-5-6-0">Leaf</tspan></text>
-    <text
-       xml:space="preserve"
-       x="7479.5796"
-       y="17699.943"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-9"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
     <path
        sodipodi:nodetypes="cc"
        inkscape:connector-curvature="0"
@@ -566,15 +561,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(-737.93887,7732.6672)"
        id="g3188-3">
-      <text
-         xml:space="preserve"
-         x="3225.7478"
-         y="13175.802"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-60"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp-&gt;completed =</text>
       <g
          id="g3107-62"
          transform="translate(947.90548,11584.029)">
@@ -607,15 +593,6 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-7">Root</tspan></text>
-      <text
-         xml:space="preserve"
-         x="3225.7478"
-         y="13390.038"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-60-3"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">       rnp-&gt;completed</text>
       <flowRoot
          xml:space="preserve"
          id="flowRoot3356"
@@ -627,7 +604,18 @@
              height="63.63961"
              x="332.34018"
              y="681.87292" /></flowRegion><flowPara
-           id="flowPara3362" /></flowRoot>    </g>
+           id="flowPara3362" /></flowRoot>      <text
+         xml:space="preserve"
+         x="3156.6121"
+         y="13317.754"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-36-6"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-0">rcu_seq_end(&amp;rsp-&gt;gp_seq)</tspan></text>
+    </g>
     <g
        style="fill:none;stroke-width:0.025in"
        transform="translate(-858.40227,7769.0342)"
@@ -859,6 +847,17 @@
        id="path3414-8-3-6-6"
        inkscape:connector-curvature="0"
        sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       x="7418.769"
+       y="17646.104"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-70"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-93">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      transform="translate(-1642.5377,-11611.245)"
@@ -887,13 +886,15 @@
     </g>
     <text
        xml:space="preserve"
-       x="5327.3057"
+       x="5274.1133"
        y="15428.84"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-36"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      transform="translate(-151.71746,-11647.612)"
@@ -972,13 +973,15 @@
          id="tspan3104-6-5-6-0-92">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7486.4907"
-       y="17670.119"
+       x="7408.5918"
+       y="17619.504"
        font-style="normal"
        font-weight="bold"
        font-size="192"
-       id="text202-6"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       id="text202-36-2"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-9">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      transform="translate(-6817.1997,-11647.612)"
@@ -1019,13 +1022,15 @@
          id="tspan3104-6-5-6-0-1">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7474.1382"
-       y="17688.926"
+       x="7416.8003"
+       y="17619.504"
        font-style="normal"
        font-weight="bold"
        font-size="192"
-       id="text202-5"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       id="text202-36-3"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-56">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <path
      style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -1059,15 +1064,6 @@
      id="path3414-8-3-6"
      inkscape:connector-curvature="0"
      sodipodi:nodetypes="cc" />
-  <text
-     xml:space="preserve"
-     x="7318.9653"
-     y="6031.6353"
-     font-style="normal"
-     font-weight="bold"
-     font-size="192"
-     id="text202-2"
-     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
   <g
      style="fill:none;stroke-width:0.025in"
      id="g4504-3-9"
@@ -1123,4 +1119,15 @@
      id="path3134-9-0-3-5"
      d="m 6875.6003,15833.906 1595.7755,0"
      style="fill:none;stroke:#969696;stroke-width:53.19251633;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send-36)" />
+  <text
+     xml:space="preserve"
+     x="7275.2612"
+     y="5971.8916"
+     font-style="normal"
+     font-weight="bold"
+     font-size="192"
+     id="text202-36-1"
+     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+       style="font-size:172.87567139px"
+       id="tspan3166-2">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
 </svg>
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg
index 0161262904ec..8c207550818f 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg
@@ -272,13 +272,13 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.70710678"
-     inkscape:cx="617.89019"
-     inkscape:cy="636.57143"
-     inkscape:window-x="697"
+     inkscape:zoom="2.6330492"
+     inkscape:cx="524.82797"
+     inkscape:cy="519.31194"
+     inkscape:window-x="79"
      inkscape:window-y="28"
      inkscape:window-maximized="0"
-     inkscape:current-layer="svg2"
+     inkscape:current-layer="g3188"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
@@ -305,13 +305,15 @@
      id="g3188">
     <text
        xml:space="preserve"
-       x="3305.5364"
+       x="3119.363"
        y="13255.592"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp-&gt;gpnum++</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3071">rcu_seq_start(rsp-&gt;gp_seq)</tspan></text>
     <g
        id="g3107"
        transform="translate(947.90548,11584.029)">
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg
index de6ecc51b00e..d24d7d555dbc 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg
@@ -19,7 +19,7 @@
    id="svg2"
    version="1.1"
    inkscape:version="0.48.4 r9939"
-   sodipodi:docname="TreeRCU-gp-init-2.svg">
+   sodipodi:docname="TreeRCU-gp-init-3.svg">
   <metadata
      id="metadata212">
     <rdf:RDF>
@@ -257,18 +257,22 @@
      inkscape:window-width="1087"
      inkscape:window-height="1144"
      id="namedview208"
-     showgrid="false"
-     inkscape:zoom="0.70710678"
+     showgrid="true"
+     inkscape:zoom="0.68224756"
      inkscape:cx="617.89019"
      inkscape:cy="625.84293"
-     inkscape:window-x="697"
+     inkscape:window-x="54"
      inkscape:window-y="28"
      inkscape:window-maximized="0"
-     inkscape:current-layer="svg2"
+     inkscape:current-layer="g3153"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
-     fit-margin-bottom="5" />
+     fit-margin-bottom="5">
+    <inkscape:grid
+       type="xygrid"
+       id="grid3090" />
+  </sodipodi:namedview>
   <path
      sodipodi:nodetypes="cccccccccccccccccccccccc"
      inkscape:connector-curvature="0"
@@ -281,13 +285,13 @@
      id="g3188">
     <text
        xml:space="preserve"
-       x="3305.5364"
+       x="3145.9592"
        y="13255.592"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     <g
        id="g3107"
        transform="translate(947.90548,11584.029)">
@@ -366,13 +370,13 @@
     </g>
     <text
        xml:space="preserve"
-       x="5392.3345"
-       y="15407.104"
+       x="5253.6904"
+       y="15407.032"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-6"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      style="fill:none;stroke-width:0.025in"
@@ -413,13 +417,13 @@
          id="tspan3104-6-5-6-0">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7536.4883"
-       y="17640.934"
+       x="7415.4365"
+       y="17670.572"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-9"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      transform="translate(-1642.5375,-11610.962)"
@@ -448,13 +452,13 @@
     </g>
     <text
        xml:space="preserve"
-       x="5378.4146"
-       y="15436.927"
+       x="5258.0688"
+       y="15412.313"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-3"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      transform="translate(-151.71726,-11647.329)"
@@ -533,13 +537,13 @@
          id="tspan3104-6-5-6-0-92">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7520.1294"
-       y="17673.639"
+       x="7405.2607"
+       y="17670.572"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-35"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      transform="translate(-6817.1998,-11647.329)"
@@ -580,13 +584,13 @@
          id="tspan3104-6-5-6-0-1">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7521.4663"
-       y="17666.062"
+       x="7413.4688"
+       y="17670.566"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-75"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <path
      style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -622,11 +626,11 @@
      sodipodi:nodetypes="cc" />
   <text
      xml:space="preserve"
-     x="7370.856"
-     y="5997.5972"
+     x="7271.9297"
+     y="6023.2412"
      font-style="normal"
      font-weight="bold"
      font-size="192"
      id="text202-62"
-     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
 </svg>
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
index b13b7b01bb3a..acd73c7ad0f4 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
@@ -1070,13 +1070,13 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.6004608"
-     inkscape:cx="826.65969"
-     inkscape:cy="483.3047"
-     inkscape:window-x="66"
-     inkscape:window-y="28"
+     inkscape:zoom="0.81932583"
+     inkscape:cx="840.45848"
+     inkscape:cy="5052.4242"
+     inkscape:window-x="787"
+     inkscape:window-y="24"
      inkscape:window-maximized="0"
-     inkscape:current-layer="svg2"
+     inkscape:current-layer="g4"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
@@ -1543,15 +1543,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(1749.0282,658.72243)"
        id="g3188">
-      <text
-         xml:space="preserve"
-         x="3305.5364"
-         y="13255.592"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-5"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp-&gt;gpnum++</text>
       <g
          id="g3107-62"
          transform="translate(947.90548,11584.029)">
@@ -1584,6 +1575,17 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-7">Root</tspan></text>
+      <text
+         xml:space="preserve"
+         x="3137.9988"
+         y="13271.316"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-626"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3071">rcu_seq_start(rsp-&gt;gp_seq)</tspan></text>
     </g>
     <rect
        ry="0"
@@ -2318,15 +2320,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(1739.0986,17188.625)"
        id="g3188-6">
-      <text
-         xml:space="preserve"
-         x="3305.5364"
-         y="13255.592"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-1"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
       <g
          id="g3107-5"
          transform="translate(947.90548,11584.029)">
@@ -2359,6 +2352,15 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-1">Root</tspan></text>
+      <text
+         xml:space="preserve"
+         x="3147.9268"
+         y="13240.524"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-1"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        style="fill:none;stroke-width:0.025in"
@@ -2387,13 +2389,13 @@
       </g>
       <text
          xml:space="preserve"
-         x="5392.3345"
-         y="15407.104"
+         x="5263.1094"
+         y="15411.646"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-6-7"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-92"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        style="fill:none;stroke-width:0.025in"
@@ -2434,13 +2436,13 @@
            id="tspan3104-6-5-6-0-94">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7536.4883"
-         y="17640.934"
+         x="7417.4053"
+         y="17655.502"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-9"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-759"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        transform="translate(-2353.8462,17224.992)"
@@ -2469,13 +2471,13 @@
       </g>
       <text
          xml:space="preserve"
-         x="5378.4146"
-         y="15436.927"
+         x="5246.1548"
+         y="15411.648"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-3"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-87"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        transform="translate(-863.02613,17188.625)"
@@ -2554,13 +2556,13 @@
            id="tspan3104-6-5-6-0-92-6">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7520.1294"
-         y="17673.639"
+         x="7433.8257"
+         y="17682.098"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-35"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-2"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        transform="translate(-7528.5085,17188.625)"
@@ -2601,13 +2603,13 @@
            id="tspan3104-6-5-6-0-1-8">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7521.4663"
-         y="17666.062"
+         x="7415.4404"
+         y="17682.098"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-75-1"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-0"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <path
        style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -2641,15 +2643,6 @@
        id="path3414-8-3-6-4"
        inkscape:connector-curvature="0"
        sodipodi:nodetypes="cc" />
-    <text
-       xml:space="preserve"
-       x="6659.5469"
-       y="34833.551"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-62"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
     <path
        sodipodi:nodetypes="ccc"
        inkscape:connector-curvature="0"
@@ -3844,7 +3837,7 @@
          font-weight="bold"
          font-size="192"
          id="text202-6-6-5"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gpnum</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gp_seq</text>
       <text
          xml:space="preserve"
          x="5035.4155"
@@ -4284,15 +4277,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(1874.038,53203.538)"
        id="g3188-7">
-      <text
-         xml:space="preserve"
-         x="3199.1516"
-         y="13255.592"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-82"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
       <g
          id="g3107-53"
          transform="translate(947.90548,11584.029)">
@@ -4325,6 +4309,17 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-19">Root</tspan></text>
+      <text
+         xml:space="preserve"
+         x="3175.896"
+         y="13240.11"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-36-3"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <rect
        ry="0"
@@ -4371,13 +4366,15 @@
       </g>
       <text
          xml:space="preserve"
-         x="5324.5371"
-         y="15414.598"
+         x="5264.4829"
+         y="15411.231"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-753"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         id="text202-36-7"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-5">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <g
        style="fill:none;stroke-width:0.025in"
@@ -4412,30 +4409,12 @@
        sodipodi:linespacing="125%"><tspan
          style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
          id="tspan3104-6-5-6-0-4">Leaf</tspan></text>
-    <text
-       xml:space="preserve"
-       x="10084.225"
-       y="70903.312"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-9-0"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
     <path
        sodipodi:nodetypes="ccc"
        inkscape:connector-curvature="0"
        id="path3134-9-0-3-9"
        d="m 6315.6122,72629.054 -20.9533,8108.684 1648.968,0"
        style="fill:none;stroke:#969696;stroke-width:53.19251251;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send)" />
-    <text
-       xml:space="preserve"
-       x="5092.4683"
-       y="74111.672"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-60"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rsp-&gt;completed =</text>
     <g
        style="fill:none;stroke-width:0.025in"
        id="g3107-62-6"
@@ -4469,15 +4448,6 @@
        sodipodi:linespacing="125%"><tspan
          style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
          id="tspan3104-6-5-7-7">Root</tspan></text>
-    <text
-       xml:space="preserve"
-       x="5092.4683"
-       y="74325.906"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-60-3"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">       rnp-&gt;completed</text>
     <g
        style="fill:none;stroke-width:0.025in"
        transform="translate(1746.2528,60972.572)"
@@ -4736,13 +4706,15 @@
       </g>
       <text
          xml:space="preserve"
-         x="5327.3057"
-         y="15428.84"
+         x="5274.1216"
+         y="15411.231"
          font-style="normal"
          font-weight="bold"
          font-size="192"
          id="text202-36"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-6">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <g
        transform="translate(-728.08545,53203.538)"
@@ -4821,13 +4793,15 @@
            id="tspan3104-6-5-6-0-92-5">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7486.4907"
-         y="17670.119"
+         x="7435.1987"
+         y="17708.281"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-6-2"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         id="text202-36-9"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-1">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <g
        transform="translate(-7393.5687,53203.538)"
@@ -4868,13 +4842,15 @@
            id="tspan3104-6-5-6-0-1-5">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7474.1382"
-         y="17688.926"
+         x="7416.8125"
+         y="17708.281"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-5-1"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         id="text202-36-35"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-62">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <path
        style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -4908,15 +4884,6 @@
        id="path3414-8-3-6-67"
        inkscape:connector-curvature="0"
        sodipodi:nodetypes="cc" />
-    <text
-       xml:space="preserve"
-       x="6742.6001"
-       y="70882.617"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-2"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
     <g
        style="fill:none;stroke-width:0.025in"
        id="g4504-3-9-6"
@@ -5131,5 +5098,47 @@
        font-size="192"
        id="text202-7-9-6-6-7"
        style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_do_batch()</text>
+    <text
+       xml:space="preserve"
+       x="6698.9019"
+       y="70885.211"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-2"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-7">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
+    <text
+       xml:space="preserve"
+       x="10023.457"
+       y="70885.234"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-0"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-9">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
+    <text
+       xml:space="preserve"
+       x="5023.3389"
+       y="74209.773"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-36"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-0">rcu_seq_end(&amp;rsp-&gt;gp_seq)</tspan></text>
+    <text
+       xml:space="preserve"
+       x="6562.5884"
+       y="34870.727"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-3"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
 </svg>
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
index de3992f4cbe1..149bec2a4493 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
@@ -300,13 +300,13 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.70710678"
-     inkscape:cx="616.47598"
-     inkscape:cy="595.41964"
-     inkscape:window-x="813"
+     inkscape:zoom="0.96484375"
+     inkscape:cx="507.0191"
+     inkscape:cy="885.62207"
+     inkscape:window-x="47"
      inkscape:window-y="28"
      inkscape:window-maximized="0"
-     inkscape:current-layer="g4405"
+     inkscape:current-layer="g3115"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
@@ -710,7 +710,7 @@
          font-weight="bold"
          font-size="192"
          id="text202-6-6"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gpnum</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gp_seq</text>
       <text
          xml:space="preserve"
          x="5035.4155"
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 4259f95c3261..f99cf11b314b 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -172,7 +172,7 @@ it will print a message similar to the following:
 	INFO: rcu_sched detected stalls on CPUs/tasks:
 	2-...: (3 GPs behind) idle=06c/0/0 softirq=1453/1455 fqs=0
 	16-...: (0 ticks this GP) idle=81c/0/0 softirq=764/764 fqs=0
-	(detected by 32, t=2603 jiffies, g=7073, c=7072, q=625)
+	(detected by 32, t=2603 jiffies, g=7075, q=625)
 
 This message indicates that CPU 32 detected that CPUs 2 and 16 were both
 causing stalls, and that the stall was affecting RCU-sched.  This message
@@ -215,11 +215,10 @@ CPU since the last time that this CPU noted the beginning of a grace
 period.
 
 The "detected by" line indicates which CPU detected the stall (in this
-case, CPU 32), how many jiffies have elapsed since the start of the
-grace period (in this case 2603), the number of the last grace period
-to start and to complete (7073 and 7072, respectively), and an estimate
-of the total number of RCU callbacks queued across all CPUs (625 in
-this case).
+case, CPU 32), how many jiffies have elapsed since the start of the grace
+period (in this case 2603), the grace-period sequence number (7075), and
+an estimate of the total number of RCU callbacks queued across all CPUs
+(625 in this case).
 
 In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed
 for each CPU:
@@ -266,15 +265,16 @@ If the relevant grace-period kthread has been unable to run prior to
 the stall warning, as was the case in the "All QSes seen" line above,
 the following additional line is printed:
 
-	kthread starved for 23807 jiffies! g7073 c7072 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1
+	kthread starved for 23807 jiffies! g7075 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1 ->cpu=5
 
 Starving the grace-period kthreads of CPU time can of course result
 in RCU CPU stall warnings even when all CPUs and tasks have passed
-through the required quiescent states.  The "g" and "c" numbers flag the
-number of the last grace period started and completed, respectively,
-the "f" precedes the ->gp_flags command to the grace-period kthread,
-the "RCU_GP_WAIT_FQS" indicates that the kthread is waiting for a short
-timeout, and the "state" precedes value of the task_struct ->state field.
+through the required quiescent states.  The "g" number shows the current
+grace-period sequence number, the "f" precedes the ->gp_flags command
+to the grace-period kthread, the "RCU_GP_WAIT_FQS" indicates that the
+kthread is waiting for a short timeout, the "state" precedes value of the
+task_struct ->state field, and the "cpu" indicates that the grace-period
+kthread last ran on CPU 5.
 
 
 Multiple Warnings From One Stall
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 65eb856526b7..c2a7facf7ff9 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -588,6 +588,7 @@ It is extremely simple:
 	void synchronize_rcu(void)
 	{
 		write_lock(&rcu_gp_mutex);
+		smp_mb__after_spinlock();
 		write_unlock(&rcu_gp_mutex);
 	}
 
@@ -609,12 +610,15 @@ don't forget about them when submitting patches making use of RCU!]
 
 The rcu_read_lock() and rcu_read_unlock() primitive read-acquire
 and release a global reader-writer lock.  The synchronize_rcu()
-primitive write-acquires this same lock, then immediately releases
-it.  This means that once synchronize_rcu() exits, all RCU read-side
-critical sections that were in progress before synchronize_rcu() was
-called are guaranteed to have completed -- there is no way that
-synchronize_rcu() would have been able to write-acquire the lock
-otherwise.
+primitive write-acquires this same lock, then releases it.  This means
+that once synchronize_rcu() exits, all RCU read-side critical sections
+that were in progress before synchronize_rcu() was called are guaranteed
+to have completed -- there is no way that synchronize_rcu() would have
+been able to write-acquire the lock otherwise.  The smp_mb__after_spinlock()
+promotes synchronize_rcu() to a full memory barrier in compliance with
+the "Memory-Barrier Guarantees" listed in:
+
+	Documentation/RCU/Design/Requirements/Requirements.html.
 
 It is possible to nest rcu_read_lock(), since reader-writer locks may
 be recursively acquired.  Note also that rcu_read_lock() is immune
@@ -816,11 +820,13 @@ RCU list traversal:
 	list_next_rcu
 	list_for_each_entry_rcu
 	list_for_each_entry_continue_rcu
+	list_for_each_entry_from_rcu
 	hlist_first_rcu
 	hlist_next_rcu
 	hlist_pprev_rcu
 	hlist_for_each_entry_rcu
 	hlist_for_each_entry_rcu_bh
+	hlist_for_each_entry_from_rcu
 	hlist_for_each_entry_continue_rcu
 	hlist_for_each_entry_continue_rcu_bh
 	hlist_nulls_first_rcu
diff --git a/Documentation/acpi/dsd/data-node-references.txt b/Documentation/acpi/dsd/data-node-references.txt
new file mode 100644
index 000000000000..c3871565c8cf
--- /dev/null
+++ b/Documentation/acpi/dsd/data-node-references.txt
@@ -0,0 +1,89 @@
+Copyright (C) 2018 Intel Corporation
+Author: Sakari Ailus <sakari.ailus@linux.intel.com>
+
+
+Referencing hierarchical data nodes
+-----------------------------------
+
+ACPI in general allows referring to device objects in the tree only.
+Hierarchical data extension nodes may not be referred to directly, hence this
+document defines a scheme to implement such references.
+
+A reference consist of the device object name followed by one or more
+hierarchical data extension [1] keys. Specifically, the hierarchical data
+extension node which is referred to by the key shall lie directly under the
+parent object i.e. either the device object or another hierarchical data
+extension node.
+
+The keys in the hierarchical data nodes shall consist of the name of the node,
+"@" character and the number of the node in hexadecimal notation (without pre-
+or postfixes). The same ACPI object shall include the _DSD property extension
+with a property "reg" that shall have the same numerical value as the number of
+the node.
+
+In case a hierarchical data extensions node has no numerical value, then the
+"reg" property shall be omitted from the ACPI object's _DSD properties and the
+"@" character and the number shall be omitted from the hierarchical data
+extension key.
+
+
+Example
+-------
+
+	In the ASL snippet below, the "reference" _DSD property [2] contains a
+	device object reference to DEV0 and under that device object, a
+	hierarchical data extension key "node@1" referring to the NOD1 object
+	and lastly, a hierarchical data extension key "anothernode" referring to
+	the ANOD object which is also the final target node of the reference.
+
+	Device (DEV0)
+	{
+	    Name (_DSD, Package () {
+		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+		Package () {
+		    Package () { "node@0", NOD0 },
+		    Package () { "node@1", NOD1 },
+		}
+	    })
+	    Name (NOD0, Package() {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "random-property", 3 },
+		}
+	    })
+	    Name (NOD1, Package() {
+		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+		Package () {
+		    Package () { "anothernode", ANOD },
+		}
+	    })
+	    Name (ANOD, Package() {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "random-property", 0 },
+		}
+	    })
+	}
+
+	Device (DEV1)
+	{
+	    Name (_DSD, Package () {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "reference", ^DEV0, "node@1", "anothernode" },
+		}
+	    })
+	}
+
+Please also see a graph example in graph.txt .
+
+References
+----------
+
+[1] Hierarchical Data Extension UUID For _DSD.
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
+    referenced 2018-07-17.
+
+[2] Device Properties UUID For _DSD.
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
+    referenced 2016-10-04.
diff --git a/Documentation/acpi/dsd/graph.txt b/Documentation/acpi/dsd/graph.txt
index ac09e3138b79..b9ce910781dc 100644
--- a/Documentation/acpi/dsd/graph.txt
+++ b/Documentation/acpi/dsd/graph.txt
@@ -36,29 +36,41 @@ The port and endpoint concepts are very similar to those in Devicetree
 [3]. A port represents an interface in a device, and an endpoint
 represents a connection to that interface.
 
-All port nodes are located under the device's "_DSD" node in the
-hierarchical data extension tree. The property extension related to
-each port node must contain the key "port" and an integer value which
-is the number of the port. The object it refers to should be called "PRTX",
-where "X" is the number of the port.
-
-Further on, endpoints are located under the individual port nodes. The
-first hierarchical data extension package list entry of the endpoint
-nodes must begin with "endpoint" and must be followed by the number
-of the endpoint. The object it refers to should be called "EPXY", where
-"X" is the number of the port and "Y" is the number of the endpoint.
-
-Each port node contains a property extension key "port", the value of
-which is the number of the port node. The each endpoint is similarly numbered
-with a property extension key "endpoint". Port numbers must be unique within a
-device and endpoint numbers must be unique within a port.
+All port nodes are located under the device's "_DSD" node in the hierarchical
+data extension tree. The data extension related to each port node must begin
+with "port" and must be followed by the "@" character and the number of the port
+as its key. The target object it refers to should be called "PRTX", where "X" is
+the number of the port. An example of such a package would be:
+
+    Package() { "port@4", PRT4 }
+
+Further on, endpoints are located under the port nodes. The hierarchical
+data extension key of the endpoint nodes must begin with
+"endpoint" and must be followed by the "@" character and the number of the
+endpoint. The object it refers to should be called "EPXY", where "X" is the
+number of the port and "Y" is the number of the endpoint. An example of such a
+package would be:
+
+    Package() { "endpoint@0", EP40 }
+
+Each port node contains a property extension key "port", the value of which is
+the number of the port. Each endpoint is similarly numbered with a property
+extension key "reg", the value of which is the number of the endpoint. Port
+numbers must be unique within a device and endpoint numbers must be unique
+within a port. If a device object may only has a single port, then the number
+of that port shall be zero. Similarly, if a port may only have a single
+endpoint, the number of that endpoint shall be zero.
 
 The endpoint reference uses property extension with "remote-endpoint" property
 name followed by a reference in the same package. Such references consist of the
-the remote device reference, number of the port in the device and finally the
-number of the endpoint in that port. Individual references thus appear as:
+the remote device reference, the first package entry of the port data extension
+reference under the device and finally the first package entry of the endpoint
+data extension reference under the port. Individual references thus appear as:
 
-    Package() { device, port_number, endpoint_number }
+    Package() { device, "port@X", "endpoint@Y" }
+
+In the above example, "X" is the number of the port and "Y" is the number of the
+endpoint.
 
 The references to endpoints must be always done both ways, to the
 remote endpoint and back from the referred remote endpoint node.
@@ -76,24 +88,24 @@ A simple example of this is show below:
 		},
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "port0", "PRT0" },
+		    Package () { "port@0", PRT0 },
 		}
 	    })
 	    Name (PRT0, Package() {
 		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
 		Package () {
-		    Package () { "port", 0 },
+		    Package () { "reg", 0 },
 		},
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "endpoint0", "EP00" },
+		    Package () { "endpoint@0", EP00 },
 		}
 	    })
 	    Name (EP00, Package() {
 		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
 		Package () {
-		    Package () { "endpoint", 0 },
-		    Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, 4, 0 } },
+		    Package () { "reg", 0 },
+		    Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, "port@4", "endpoint@0" } },
 		}
 	    })
 	}
@@ -106,26 +118,26 @@ A simple example of this is show below:
 	    Name (_DSD, Package () {
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "port4", "PRT4" },
+		    Package () { "port@4", PRT4 },
 		}
 	    })
 
 	    Name (PRT4, Package() {
 		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
 		Package () {
-		    Package () { "port", 4 }, /* CSI-2 port number */
+		    Package () { "reg", 4 }, /* CSI-2 port number */
 		},
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "endpoint0", "EP40" },
+		    Package () { "endpoint@0", EP40 },
 		}
 	    })
 
 	    Name (EP40, Package() {
 		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
 		Package () {
-		    Package () { "endpoint", 0 },
-		    Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, 0, 0 } },
+		    Package () { "reg", 0 },
+		    Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, "port@0", "endpoint@0" } },
 		}
 	    })
 	}
@@ -151,7 +163,7 @@ References
     referenced 2016-10-04.
 
 [5] Hierarchical Data Extension UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.pdf>,
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
     referenced 2016-10-04.
 
 [6] Advanced Configuration and Power Interface Specification.
diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst
index 02caa7efd5ef..15ea785b2dfa 100644
--- a/Documentation/admin-guide/README.rst
+++ b/Documentation/admin-guide/README.rst
@@ -1,3 +1,5 @@
+.. _readme:
+
 Linux kernel release 4.x <http://kernel.org/>
 =============================================
 
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 8a2c52d5c53b..1746131bc9cb 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -51,6 +51,9 @@ v1 is available under Documentation/cgroup-v1/.
      5-3. IO
        5-3-1. IO Interface Files
        5-3-2. Writeback
+       5-3-3. IO Latency
+         5-3-3-1. How IO Latency Throttling Works
+         5-3-3-2. IO Latency Interface Files
      5-4. PID
        5-4-1. PID Interface Files
      5-5. Device
@@ -1314,17 +1317,19 @@ IO Interface Files
 	Lines are keyed by $MAJ:$MIN device numbers and not ordered.
 	The following nested keys are defined.
 
-	  ======	===================
+	  ======	=====================
 	  rbytes	Bytes read
 	  wbytes	Bytes written
 	  rios		Number of read IOs
 	  wios		Number of write IOs
-	  ======	===================
+	  dbytes	Bytes discarded
+	  dios		Number of discard IOs
+	  ======	=====================
 
 	An example read output follows:
 
-	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353
-	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252
+	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 dbytes=0 dios=0
+	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 dbytes=50331648 dios=3021
 
   io.weight
 	A read-write flat-keyed file which exists on non-root cgroups.
@@ -1446,6 +1451,85 @@ writeback as follows.
 	vm.dirty[_background]_ratio.
 
 
+IO Latency
+~~~~~~~~~~
+
+This is a cgroup v2 controller for IO workload protection.  You provide a group
+with a latency target, and if the average latency exceeds that target the
+controller will throttle any peers that have a lower latency target than the
+protected workload.
+
+The limits are only applied at the peer level in the hierarchy.  This means that
+in the diagram below, only groups A, B, and C will influence each other, and
+groups D and F will influence each other.  Group G will influence nobody.
+
+			[root]
+		/	   |		\
+		A	   B		C
+	       /  \        |
+	      D    F	   G
+
+
+So the ideal way to configure this is to set io.latency in groups A, B, and C.
+Generally you do not want to set a value lower than the latency your device
+supports.  Experiment to find the value that works best for your workload.
+Start at higher than the expected latency for your device and watch the
+avg_lat value in io.stat for your workload group to get an idea of the
+latency you see during normal operation.  Use the avg_lat value as a basis for
+your real setting, setting at 10-15% higher than the value in io.stat.
+
+How IO Latency Throttling Works
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+io.latency is work conserving; so as long as everybody is meeting their latency
+target the controller doesn't do anything.  Once a group starts missing its
+target it begins throttling any peer group that has a higher target than itself.
+This throttling takes 2 forms:
+
+- Queue depth throttling.  This is the number of outstanding IO's a group is
+  allowed to have.  We will clamp down relatively quickly, starting at no limit
+  and going all the way down to 1 IO at a time.
+
+- Artificial delay induction.  There are certain types of IO that cannot be
+  throttled without possibly adversely affecting higher priority groups.  This
+  includes swapping and metadata IO.  These types of IO are allowed to occur
+  normally, however they are "charged" to the originating group.  If the
+  originating group is being throttled you will see the use_delay and delay
+  fields in io.stat increase.  The delay value is how many microseconds that are
+  being added to any process that runs in this group.  Because this number can
+  grow quite large if there is a lot of swapping or metadata IO occurring we
+  limit the individual delay events to 1 second at a time.
+
+Once the victimized group starts meeting its latency target again it will start
+unthrottling any peer groups that were throttled previously.  If the victimized
+group simply stops doing IO the global counter will unthrottle appropriately.
+
+IO Latency Interface Files
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+  io.latency
+	This takes a similar format as the other controllers.
+
+		"MAJOR:MINOR target=<target time in microseconds"
+
+  io.stat
+	If the controller is enabled you will see extra stats in io.stat in
+	addition to the normal ones.
+
+	  depth
+		This is the current queue depth for the group.
+
+	  avg_lat
+		This is an exponential moving average with a decay rate of 1/exp
+		bound by the sampling interval.  The decay rate interval can be
+		calculated by multiplying the win value in io.stat by the
+		corresponding number of samples based on the win value.
+
+	  win
+		The sampling window size in milliseconds.  This is the minimum
+		duration of time between evaluation events.  Windows only elapse
+		with IO activity.  Idle periods extend the most recent window.
+
 PID
 ---
 
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index 48d70af11652..0873685bab0f 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -17,6 +17,15 @@ etc.
    kernel-parameters
    devices
 
+This section describes CPU vulnerabilities and provides an overview of the
+possible mitigations along with guidance for selecting mitigations if they
+are configurable at compile, boot or run time.
+
+.. toctree::
+   :maxdepth: 1
+
+   l1tf
+
 Here is a set of documents aimed at users who are trying to track down
 problems and bugs in particular.
 
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..a32f2a126791 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -816,6 +816,17 @@
 	disable=	[IPV6]
 			See Documentation/networking/ipv6.txt.
 
+	hardened_usercopy=
+                        [KNL] Under CONFIG_HARDENED_USERCOPY, whether
+                        hardening is enabled for this boot. Hardened
+                        usercopy checking is used to protect the kernel
+                        from reading or writing beyond known memory
+                        allocation boundaries as a proactive defense
+                        against bounds-checking flaws in the kernel's
+                        copy_to_user()/copy_from_user() interface.
+                on      Perform hardened usercopy checks (default).
+                off     Disable hardened usercopy checks.
+
 	disable_radix	[PPC]
 			Disable RADIX MMU mode on POWER9
 
@@ -1967,10 +1978,84 @@
 			(virtualized real and unpaged mode) on capable
 			Intel chips. Default is 1 (enabled)
 
+	kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
+			CVE-2018-3620.
+
+			Valid arguments: never, cond, always
+
+			always: L1D cache flush on every VMENTER.
+			cond:	Flush L1D on VMENTER only when the code between
+				VMEXIT and VMENTER can leak host memory.
+			never:	Disables the mitigation
+
+			Default is cond (do L1 cache flush in specific instances)
+
 	kvm-intel.vpid=	[KVM,Intel] Disable Virtual Processor Identification
 			feature (tagged TLBs) on capable Intel chips.
 			Default is 1 (enabled)
 
+	l1tf=           [X86] Control mitigation of the L1TF vulnerability on
+			      affected CPUs
+
+			The kernel PTE inversion protection is unconditionally
+			enabled and cannot be disabled.
+
+			full
+				Provides all available mitigations for the
+				L1TF vulnerability. Disables SMT and
+				enables all mitigations in the
+				hypervisors, i.e. unconditional L1D flush.
+
+				SMT control and L1D flush control via the
+				sysfs interface is still possible after
+				boot.  Hypervisors will issue a warning
+				when the first VM is started in a
+				potentially insecure configuration,
+				i.e. SMT enabled or L1D flush disabled.
+
+			full,force
+				Same as 'full', but disables SMT and L1D
+				flush runtime control. Implies the
+				'nosmt=force' command line option.
+				(i.e. sysfs control of SMT is disabled.)
+
+			flush
+				Leaves SMT enabled and enables the default
+				hypervisor mitigation, i.e. conditional
+				L1D flush.
+
+				SMT control and L1D flush control via the
+				sysfs interface is still possible after
+				boot.  Hypervisors will issue a warning
+				when the first VM is started in a
+				potentially insecure configuration,
+				i.e. SMT enabled or L1D flush disabled.
+
+			flush,nosmt
+
+				Disables SMT and enables the default
+				hypervisor mitigation.
+
+				SMT control and L1D flush control via the
+				sysfs interface is still possible after
+				boot.  Hypervisors will issue a warning
+				when the first VM is started in a
+				potentially insecure configuration,
+				i.e. SMT enabled or L1D flush disabled.
+
+			flush,nowarn
+				Same as 'flush', but hypervisors will not
+				warn when a VM is started in a potentially
+				insecure configuration.
+
+			off
+				Disables hypervisor mitigations and doesn't
+				emit any warnings.
+
+			Default is 'flush'.
+
+			For details see: Documentation/admin-guide/l1tf.rst
+
 	l2cr=		[PPC]
 
 	l3cr=		[PPC]
@@ -2687,6 +2772,10 @@
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
+			[KNL,x86] Disable symmetric multithreading (SMT).
+			nosmt=force: Force disable SMT, cannot be undone
+				     via the sysfs control file.
+
 	nospectre_v2	[X86] Disable all mitigations for the Spectre variant 2
 			(indirect branch prediction) vulnerability. System may
 			allow data leaks with this option, which is equivalent
@@ -2835,8 +2924,6 @@
 
 	nosync		[HW,M68K] Disables sync negotiation for all devices.
 
-	notsc		[BUGS=X86-32] Disable Time Stamp Counter
-
 	nowatchdog	[KNL] Disable both lockup detectors, i.e.
 			soft-lockup and NMI watchdog (hard-lockup).
 
@@ -3632,8 +3719,8 @@
 			Set time (s) after boot for CPU-hotplug testing.
 
 	rcutorture.onoff_interval= [KNL]
-			Set time (s) between CPU-hotplug operations, or
-			zero to disable CPU-hotplug testing.
+			Set time (jiffies) between CPU-hotplug operations,
+			or zero to disable CPU-hotplug testing.
 
 	rcutorture.shuffle_interval= [KNL]
 			Set task-shuffle interval (s).  Shuffling tasks
@@ -4060,6 +4147,8 @@
 			This parameter controls whether the Speculative Store
 			Bypass optimization is used.
 
+			On x86 the options are:
+
 			on      - Unconditionally disable Speculative Store Bypass
 			off     - Unconditionally enable Speculative Store Bypass
 			auto    - Kernel detects whether the CPU model contains an
@@ -4075,12 +4164,20 @@
 			seccomp - Same as "prctl" above, but all seccomp threads
 				  will disable SSB unless they explicitly opt out.
 
-			Not specifying this option is equivalent to
-			spec_store_bypass_disable=auto.
-
 			Default mitigations:
 			X86:	If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
 
+			On powerpc the options are:
+
+			on,auto - On Power8 and Power9 insert a store-forwarding
+				  barrier on kernel entry and exit. On Power7
+				  perform a software flush on kernel entry and
+				  exit.
+			off	- No action.
+
+			Not specifying this option is equivalent to
+			spec_store_bypass_disable=auto.
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=
@@ -4846,3 +4943,8 @@
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
+
+	xhci-hcd.quirks		[USB,KNL]
+			A hex value specifying bitmask with supplemental xhci
+			host controller quirks. Meaning of each bit can be
+			consulted in header drivers/usb/host/xhci.h.
diff --git a/Documentation/admin-guide/l1tf.rst b/Documentation/admin-guide/l1tf.rst
new file mode 100644
index 000000000000..bae52b845de0
--- /dev/null
+++ b/Documentation/admin-guide/l1tf.rst
@@ -0,0 +1,610 @@
+L1TF - L1 Terminal Fault
+========================
+
+L1 Terminal Fault is a hardware vulnerability which allows unprivileged
+speculative access to data which is available in the Level 1 Data Cache
+when the page table entry controlling the virtual address, which is used
+for the access, has the Present bit cleared or other reserved bits set.
+
+Affected processors
+-------------------
+
+This vulnerability affects a wide range of Intel processors. The
+vulnerability is not present on:
+
+   - Processors from AMD, Centaur and other non Intel vendors
+
+   - Older processor models, where the CPU family is < 6
+
+   - A range of Intel ATOM processors (Cedarview, Cloverview, Lincroft,
+     Penwell, Pineview, Silvermont, Airmont, Merrifield)
+
+   - The Intel XEON PHI family
+
+   - Intel processors which have the ARCH_CAP_RDCL_NO bit set in the
+     IA32_ARCH_CAPABILITIES MSR. If the bit is set the CPU is not affected
+     by the Meltdown vulnerability either. These CPUs should become
+     available by end of 2018.
+
+Whether a processor is affected or not can be read out from the L1TF
+vulnerability file in sysfs. See :ref:`l1tf_sys_info`.
+
+Related CVEs
+------------
+
+The following CVE entries are related to the L1TF vulnerability:
+
+   =============  =================  ==============================
+   CVE-2018-3615  L1 Terminal Fault  SGX related aspects
+   CVE-2018-3620  L1 Terminal Fault  OS, SMM related aspects
+   CVE-2018-3646  L1 Terminal Fault  Virtualization related aspects
+   =============  =================  ==============================
+
+Problem
+-------
+
+If an instruction accesses a virtual address for which the relevant page
+table entry (PTE) has the Present bit cleared or other reserved bits set,
+then speculative execution ignores the invalid PTE and loads the referenced
+data if it is present in the Level 1 Data Cache, as if the page referenced
+by the address bits in the PTE was still present and accessible.
+
+While this is a purely speculative mechanism and the instruction will raise
+a page fault when it is retired eventually, the pure act of loading the
+data and making it available to other speculative instructions opens up the
+opportunity for side channel attacks to unprivileged malicious code,
+similar to the Meltdown attack.
+
+While Meltdown breaks the user space to kernel space protection, L1TF
+allows to attack any physical memory address in the system and the attack
+works across all protection domains. It allows an attack of SGX and also
+works from inside virtual machines because the speculation bypasses the
+extended page table (EPT) protection mechanism.
+
+
+Attack scenarios
+----------------
+
+1. Malicious user space
+^^^^^^^^^^^^^^^^^^^^^^^
+
+   Operating Systems store arbitrary information in the address bits of a
+   PTE which is marked non present. This allows a malicious user space
+   application to attack the physical memory to which these PTEs resolve.
+   In some cases user-space can maliciously influence the information
+   encoded in the address bits of the PTE, thus making attacks more
+   deterministic and more practical.
+
+   The Linux kernel contains a mitigation for this attack vector, PTE
+   inversion, which is permanently enabled and has no performance
+   impact. The kernel ensures that the address bits of PTEs, which are not
+   marked present, never point to cacheable physical memory space.
+
+   A system with an up to date kernel is protected against attacks from
+   malicious user space applications.
+
+2. Malicious guest in a virtual machine
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The fact that L1TF breaks all domain protections allows malicious guest
+   OSes, which can control the PTEs directly, and malicious guest user
+   space applications, which run on an unprotected guest kernel lacking the
+   PTE inversion mitigation for L1TF, to attack physical host memory.
+
+   A special aspect of L1TF in the context of virtualization is symmetric
+   multi threading (SMT). The Intel implementation of SMT is called
+   HyperThreading. The fact that Hyperthreads on the affected processors
+   share the L1 Data Cache (L1D) is important for this. As the flaw allows
+   only to attack data which is present in L1D, a malicious guest running
+   on one Hyperthread can attack the data which is brought into the L1D by
+   the context which runs on the sibling Hyperthread of the same physical
+   core. This context can be host OS, host user space or a different guest.
+
+   If the processor does not support Extended Page Tables, the attack is
+   only possible, when the hypervisor does not sanitize the content of the
+   effective (shadow) page tables.
+
+   While solutions exist to mitigate these attack vectors fully, these
+   mitigations are not enabled by default in the Linux kernel because they
+   can affect performance significantly. The kernel provides several
+   mechanisms which can be utilized to address the problem depending on the
+   deployment scenario. The mitigations, their protection scope and impact
+   are described in the next sections.
+
+   The default mitigations and the rationale for choosing them are explained
+   at the end of this document. See :ref:`default_mitigations`.
+
+.. _l1tf_sys_info:
+
+L1TF system information
+-----------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current L1TF
+status of the system: whether the system is vulnerable, and which
+mitigations are active. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/l1tf
+
+The possible values in this file are:
+
+  ===========================   ===============================
+  'Not affected'		The processor is not vulnerable
+  'Mitigation: PTE Inversion'	The host protection is active
+  ===========================   ===============================
+
+If KVM/VMX is enabled and the processor is vulnerable then the following
+information is appended to the 'Mitigation: PTE Inversion' part:
+
+  - SMT status:
+
+    =====================  ================
+    'VMX: SMT vulnerable'  SMT is enabled
+    'VMX: SMT disabled'    SMT is disabled
+    =====================  ================
+
+  - L1D Flush mode:
+
+    ================================  ====================================
+    'L1D vulnerable'		      L1D flushing is disabled
+
+    'L1D conditional cache flushes'   L1D flush is conditionally enabled
+
+    'L1D cache flushes'		      L1D flush is unconditionally enabled
+    ================================  ====================================
+
+The resulting grade of protection is discussed in the following sections.
+
+
+Host mitigation mechanism
+-------------------------
+
+The kernel is unconditionally protected against L1TF attacks from malicious
+user space running on the host.
+
+
+Guest mitigation mechanisms
+---------------------------
+
+.. _l1d_flush:
+
+1. L1D flush on VMENTER
+^^^^^^^^^^^^^^^^^^^^^^^
+
+   To make sure that a guest cannot attack data which is present in the L1D
+   the hypervisor flushes the L1D before entering the guest.
+
+   Flushing the L1D evicts not only the data which should not be accessed
+   by a potentially malicious guest, it also flushes the guest
+   data. Flushing the L1D has a performance impact as the processor has to
+   bring the flushed guest data back into the L1D. Depending on the
+   frequency of VMEXIT/VMENTER and the type of computations in the guest
+   performance degradation in the range of 1% to 50% has been observed. For
+   scenarios where guest VMEXIT/VMENTER are rare the performance impact is
+   minimal. Virtio and mechanisms like posted interrupts are designed to
+   confine the VMEXITs to a bare minimum, but specific configurations and
+   application scenarios might still suffer from a high VMEXIT rate.
+
+   The kernel provides two L1D flush modes:
+    - conditional ('cond')
+    - unconditional ('always')
+
+   The conditional mode avoids L1D flushing after VMEXITs which execute
+   only audited code paths before the corresponding VMENTER. These code
+   paths have been verified that they cannot expose secrets or other
+   interesting data to an attacker, but they can leak information about the
+   address space layout of the hypervisor.
+
+   Unconditional mode flushes L1D on all VMENTER invocations and provides
+   maximum protection. It has a higher overhead than the conditional
+   mode. The overhead cannot be quantified correctly as it depends on the
+   workload scenario and the resulting number of VMEXITs.
+
+   The general recommendation is to enable L1D flush on VMENTER. The kernel
+   defaults to conditional mode on affected processors.
+
+   **Note**, that L1D flush does not prevent the SMT problem because the
+   sibling thread will also bring back its data into the L1D which makes it
+   attackable again.
+
+   L1D flush can be controlled by the administrator via the kernel command
+   line and sysfs control files. See :ref:`mitigation_control_command_line`
+   and :ref:`mitigation_control_kvm`.
+
+.. _guest_confinement:
+
+2. Guest VCPU confinement to dedicated physical cores
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   To address the SMT problem, it is possible to make a guest or a group of
+   guests affine to one or more physical cores. The proper mechanism for
+   that is to utilize exclusive cpusets to ensure that no other guest or
+   host tasks can run on these cores.
+
+   If only a single guest or related guests run on sibling SMT threads on
+   the same physical core then they can only attack their own memory and
+   restricted parts of the host memory.
+
+   Host memory is attackable, when one of the sibling SMT threads runs in
+   host OS (hypervisor) context and the other in guest context. The amount
+   of valuable information from the host OS context depends on the context
+   which the host OS executes, i.e. interrupts, soft interrupts and kernel
+   threads. The amount of valuable data from these contexts cannot be
+   declared as non-interesting for an attacker without deep inspection of
+   the code.
+
+   **Note**, that assigning guests to a fixed set of physical cores affects
+   the ability of the scheduler to do load balancing and might have
+   negative effects on CPU utilization depending on the hosting
+   scenario. Disabling SMT might be a viable alternative for particular
+   scenarios.
+
+   For further information about confining guests to a single or to a group
+   of cores consult the cpusets documentation:
+
+   https://www.kernel.org/doc/Documentation/cgroup-v1/cpusets.txt
+
+.. _interrupt_isolation:
+
+3. Interrupt affinity
+^^^^^^^^^^^^^^^^^^^^^
+
+   Interrupts can be made affine to logical CPUs. This is not universally
+   true because there are types of interrupts which are truly per CPU
+   interrupts, e.g. the local timer interrupt. Aside of that multi queue
+   devices affine their interrupts to single CPUs or groups of CPUs per
+   queue without allowing the administrator to control the affinities.
+
+   Moving the interrupts, which can be affinity controlled, away from CPUs
+   which run untrusted guests, reduces the attack vector space.
+
+   Whether the interrupts with are affine to CPUs, which run untrusted
+   guests, provide interesting data for an attacker depends on the system
+   configuration and the scenarios which run on the system. While for some
+   of the interrupts it can be assumed that they won't expose interesting
+   information beyond exposing hints about the host OS memory layout, there
+   is no way to make general assumptions.
+
+   Interrupt affinity can be controlled by the administrator via the
+   /proc/irq/$NR/smp_affinity[_list] files. Limited documentation is
+   available at:
+
+   https://www.kernel.org/doc/Documentation/IRQ-affinity.txt
+
+.. _smt_control:
+
+4. SMT control
+^^^^^^^^^^^^^^
+
+   To prevent the SMT issues of L1TF it might be necessary to disable SMT
+   completely. Disabling SMT can have a significant performance impact, but
+   the impact depends on the hosting scenario and the type of workloads.
+   The impact of disabling SMT needs also to be weighted against the impact
+   of other mitigation solutions like confining guests to dedicated cores.
+
+   The kernel provides a sysfs interface to retrieve the status of SMT and
+   to control it. It also provides a kernel command line interface to
+   control SMT.
+
+   The kernel command line interface consists of the following options:
+
+     =========== ==========================================================
+     nosmt	 Affects the bring up of the secondary CPUs during boot. The
+		 kernel tries to bring all present CPUs online during the
+		 boot process. "nosmt" makes sure that from each physical
+		 core only one - the so called primary (hyper) thread is
+		 activated. Due to a design flaw of Intel processors related
+		 to Machine Check Exceptions the non primary siblings have
+		 to be brought up at least partially and are then shut down
+		 again.  "nosmt" can be undone via the sysfs interface.
+
+     nosmt=force Has the same effect as "nosmt" but it does not allow to
+		 undo the SMT disable via the sysfs interface.
+     =========== ==========================================================
+
+   The sysfs interface provides two files:
+
+   - /sys/devices/system/cpu/smt/control
+   - /sys/devices/system/cpu/smt/active
+
+   /sys/devices/system/cpu/smt/control:
+
+     This file allows to read out the SMT control state and provides the
+     ability to disable or (re)enable SMT. The possible states are:
+
+	==============  ===================================================
+	on		SMT is supported by the CPU and enabled. All
+			logical CPUs can be onlined and offlined without
+			restrictions.
+
+	off		SMT is supported by the CPU and disabled. Only
+			the so called primary SMT threads can be onlined
+			and offlined without restrictions. An attempt to
+			online a non-primary sibling is rejected
+
+	forceoff	Same as 'off' but the state cannot be controlled.
+			Attempts to write to the control file are rejected.
+
+	notsupported	The processor does not support SMT. It's therefore
+			not affected by the SMT implications of L1TF.
+			Attempts to write to the control file are rejected.
+	==============  ===================================================
+
+     The possible states which can be written into this file to control SMT
+     state are:
+
+     - on
+     - off
+     - forceoff
+
+   /sys/devices/system/cpu/smt/active:
+
+     This file reports whether SMT is enabled and active, i.e. if on any
+     physical core two or more sibling threads are online.
+
+   SMT control is also possible at boot time via the l1tf kernel command
+   line parameter in combination with L1D flush control. See
+   :ref:`mitigation_control_command_line`.
+
+5. Disabling EPT
+^^^^^^^^^^^^^^^^
+
+  Disabling EPT for virtual machines provides full mitigation for L1TF even
+  with SMT enabled, because the effective page tables for guests are
+  managed and sanitized by the hypervisor. Though disabling EPT has a
+  significant performance impact especially when the Meltdown mitigation
+  KPTI is enabled.
+
+  EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter.
+
+There is ongoing research and development for new mitigation mechanisms to
+address the performance impact of disabling SMT or EPT.
+
+.. _mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the L1TF mitigations at boot
+time with the option "l1tf=". The valid arguments for this option are:
+
+  ============  =============================================================
+  full		Provides all available mitigations for the L1TF
+		vulnerability. Disables SMT and enables all mitigations in
+		the hypervisors, i.e. unconditional L1D flushing
+
+		SMT control and L1D flush control via the sysfs interface
+		is still possible after boot.  Hypervisors will issue a
+		warning when the first VM is started in a potentially
+		insecure configuration, i.e. SMT enabled or L1D flush
+		disabled.
+
+  full,force	Same as 'full', but disables SMT and L1D flush runtime
+		control. Implies the 'nosmt=force' command line option.
+		(i.e. sysfs control of SMT is disabled.)
+
+  flush		Leaves SMT enabled and enables the default hypervisor
+		mitigation, i.e. conditional L1D flushing
+
+		SMT control and L1D flush control via the sysfs interface
+		is still possible after boot.  Hypervisors will issue a
+		warning when the first VM is started in a potentially
+		insecure configuration, i.e. SMT enabled or L1D flush
+		disabled.
+
+  flush,nosmt	Disables SMT and enables the default hypervisor mitigation,
+		i.e. conditional L1D flushing.
+
+		SMT control and L1D flush control via the sysfs interface
+		is still possible after boot.  Hypervisors will issue a
+		warning when the first VM is started in a potentially
+		insecure configuration, i.e. SMT enabled or L1D flush
+		disabled.
+
+  flush,nowarn	Same as 'flush', but hypervisors will not warn when a VM is
+		started in a potentially insecure configuration.
+
+  off		Disables hypervisor mitigations and doesn't emit any
+		warnings.
+  ============  =============================================================
+
+The default is 'flush'. For details about L1D flushing see :ref:`l1d_flush`.
+
+
+.. _mitigation_control_kvm:
+
+Mitigation control for KVM - module parameter
+-------------------------------------------------------------
+
+The KVM hypervisor mitigation mechanism, flushing the L1D cache when
+entering a guest, can be controlled with a module parameter.
+
+The option/parameter is "kvm-intel.vmentry_l1d_flush=". It takes the
+following arguments:
+
+  ============  ==============================================================
+  always	L1D cache flush on every VMENTER.
+
+  cond		Flush L1D on VMENTER only when the code between VMEXIT and
+		VMENTER can leak host memory which is considered
+		interesting for an attacker. This still can leak host memory
+		which allows e.g. to determine the hosts address space layout.
+
+  never		Disables the mitigation
+  ============  ==============================================================
+
+The parameter can be provided on the kernel command line, as a module
+parameter when loading the modules and at runtime modified via the sysfs
+file:
+
+/sys/module/kvm_intel/parameters/vmentry_l1d_flush
+
+The default is 'cond'. If 'l1tf=full,force' is given on the kernel command
+line, then 'always' is enforced and the kvm-intel.vmentry_l1d_flush
+module parameter is ignored and writes to the sysfs file are rejected.
+
+
+Mitigation selection guide
+--------------------------
+
+1. No virtualization in use
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The system is protected by the kernel unconditionally and no further
+   action is required.
+
+2. Virtualization with trusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   If the guest comes from a trusted source and the guest OS kernel is
+   guaranteed to have the L1TF mitigations in place the system is fully
+   protected against L1TF and no further action is required.
+
+   To avoid the overhead of the default L1D flushing on VMENTER the
+   administrator can disable the flushing via the kernel command line and
+   sysfs control files. See :ref:`mitigation_control_command_line` and
+   :ref:`mitigation_control_kvm`.
+
+
+3. Virtualization with untrusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+3.1. SMT not supported or disabled
+""""""""""""""""""""""""""""""""""
+
+  If SMT is not supported by the processor or disabled in the BIOS or by
+  the kernel, it's only required to enforce L1D flushing on VMENTER.
+
+  Conditional L1D flushing is the default behaviour and can be tuned. See
+  :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`.
+
+3.2. EPT not supported or disabled
+""""""""""""""""""""""""""""""""""
+
+  If EPT is not supported by the processor or disabled in the hypervisor,
+  the system is fully protected. SMT can stay enabled and L1D flushing on
+  VMENTER is not required.
+
+  EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter.
+
+3.3. SMT and EPT supported and active
+"""""""""""""""""""""""""""""""""""""
+
+  If SMT and EPT are supported and active then various degrees of
+  mitigations can be employed:
+
+  - L1D flushing on VMENTER:
+
+    L1D flushing on VMENTER is the minimal protection requirement, but it
+    is only potent in combination with other mitigation methods.
+
+    Conditional L1D flushing is the default behaviour and can be tuned. See
+    :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`.
+
+  - Guest confinement:
+
+    Confinement of guests to a single or a group of physical cores which
+    are not running any other processes, can reduce the attack surface
+    significantly, but interrupts, soft interrupts and kernel threads can
+    still expose valuable data to a potential attacker. See
+    :ref:`guest_confinement`.
+
+  - Interrupt isolation:
+
+    Isolating the guest CPUs from interrupts can reduce the attack surface
+    further, but still allows a malicious guest to explore a limited amount
+    of host physical memory. This can at least be used to gain knowledge
+    about the host address space layout. The interrupts which have a fixed
+    affinity to the CPUs which run the untrusted guests can depending on
+    the scenario still trigger soft interrupts and schedule kernel threads
+    which might expose valuable information. See
+    :ref:`interrupt_isolation`.
+
+The above three mitigation methods combined can provide protection to a
+certain degree, but the risk of the remaining attack surface has to be
+carefully analyzed. For full protection the following methods are
+available:
+
+  - Disabling SMT:
+
+    Disabling SMT and enforcing the L1D flushing provides the maximum
+    amount of protection. This mitigation is not depending on any of the
+    above mitigation methods.
+
+    SMT control and L1D flushing can be tuned by the command line
+    parameters 'nosmt', 'l1tf', 'kvm-intel.vmentry_l1d_flush' and at run
+    time with the matching sysfs control files. See :ref:`smt_control`,
+    :ref:`mitigation_control_command_line` and
+    :ref:`mitigation_control_kvm`.
+
+  - Disabling EPT:
+
+    Disabling EPT provides the maximum amount of protection as well. It is
+    not depending on any of the above mitigation methods. SMT can stay
+    enabled and L1D flushing is not required, but the performance impact is
+    significant.
+
+    EPT can be disabled in the hypervisor via the 'kvm-intel.ept'
+    parameter.
+
+3.4. Nested virtual machines
+""""""""""""""""""""""""""""
+
+When nested virtualization is in use, three operating systems are involved:
+the bare metal hypervisor, the nested hypervisor and the nested virtual
+machine.  VMENTER operations from the nested hypervisor into the nested
+guest will always be processed by the bare metal hypervisor. If KVM is the
+bare metal hypervisor it wiil:
+
+ - Flush the L1D cache on every switch from the nested hypervisor to the
+   nested virtual machine, so that the nested hypervisor's secrets are not
+   exposed to the nested virtual machine;
+
+ - Flush the L1D cache on every switch from the nested virtual machine to
+   the nested hypervisor; this is a complex operation, and flushing the L1D
+   cache avoids that the bare metal hypervisor's secrets are exposed to the
+   nested virtual machine;
+
+ - Instruct the nested hypervisor to not perform any L1D cache flush. This
+   is an optimization to avoid double L1D flushing.
+
+
+.. _default_mitigations:
+
+Default mitigations
+-------------------
+
+  The kernel default mitigations for vulnerable processors are:
+
+  - PTE inversion to protect against malicious user space. This is done
+    unconditionally and cannot be controlled.
+
+  - L1D conditional flushing on VMENTER when EPT is enabled for
+    a guest.
+
+  The kernel does not by default enforce the disabling of SMT, which leaves
+  SMT systems vulnerable when running untrusted guests with EPT enabled.
+
+  The rationale for this choice is:
+
+  - Force disabling SMT can break existing setups, especially with
+    unattended updates.
+
+  - If regular users run untrusted guests on their machine, then L1TF is
+    just an add on to other malware which might be embedded in an untrusted
+    guest, e.g. spam-bots or attacks on the local network.
+
+    There is no technical way to prevent a user from running untrusted code
+    on their machines blindly.
+
+  - It's technically extremely unlikely and from today's knowledge even
+    impossible that L1TF can be exploited via the most popular attack
+    mechanisms like JavaScript because these mechanisms have no way to
+    control PTEs. If this would be possible and not other mitigation would
+    be possible, then the default might be different.
+
+  - The administrators of cloud and hosting setups have to carefully
+    analyze the risk for their scenarios and make the appropriate
+    mitigation choices, which might even vary across their deployed
+    machines and also result in other changes of their overall setup.
+    There is no way for the kernel to provide a sensible default for this
+    kind of scenarios.
diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst
index 8b9164990956..8f1d3de449b5 100644
--- a/Documentation/admin-guide/pm/intel_pstate.rst
+++ b/Documentation/admin-guide/pm/intel_pstate.rst
@@ -324,8 +324,7 @@ Global Attributes
 
 ``intel_pstate`` exposes several global attributes (files) in ``sysfs`` to
 control its functionality at the system level.  They are located in the
-``/sys/devices/system/cpu/cpufreq/intel_pstate/`` directory and affect all
-CPUs.
+``/sys/devices/system/cpu/intel_pstate/`` directory and affect all CPUs.
 
 Some of them are not present if the ``intel_pstate=per_cpu_perf_limits``
 argument is passed to the kernel in the command line.
@@ -379,6 +378,17 @@ argument is passed to the kernel in the command line.
 	but it affects the maximum possible value of per-policy P-state	limits
 	(see `Interpretation of Policy Attributes`_ below for details).
 
+``hwp_dynamic_boost``
+	This attribute is only present if ``intel_pstate`` works in the
+	`active mode with the HWP feature enabled <Active Mode With HWP_>`_ in
+	the processor.  If set (equal to 1), it causes the minimum P-state limit
+	to be increased dynamically for a short time whenever a task previously
+	waiting on I/O is selected to run on a given logical CPU (the purpose
+	of this mechanism is to improve performance).
+
+	This setting has no effect on logical CPUs whose minimum P-state limit
+	is directly set to the highest non-turbo P-state or above it.
+
 .. _status_attr:
 
 ``status``
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt
index 07f147381f32..ea2dafe49ae8 100644
--- a/Documentation/block/null_blk.txt
+++ b/Documentation/block/null_blk.txt
@@ -85,3 +85,10 @@ shared_tags=[0/1]: Default: 0
   0: Tag set is not shared.
   1: Tag set shared between devices for blk-mq. Only makes sense with
      nr_devices > 1, otherwise there's no tag set to share.
+
+zoned=[0/1]: Default: 0
+  0: Block device is exposed as a random-access block device.
+  1: Block device is exposed as a host-managed zoned block device.
+
+zone_size=[MB]: Default: 256
+  Per zone size when exposed as a zoned block device. Must be a power of two.
diff --git a/Documentation/block/stat.txt b/Documentation/block/stat.txt
index 0dbc946de2ea..0aace9cc536c 100644
--- a/Documentation/block/stat.txt
+++ b/Documentation/block/stat.txt
@@ -31,28 +31,32 @@ write ticks     milliseconds  total wait time for write requests
 in_flight       requests      number of I/Os currently in flight
 io_ticks        milliseconds  total time this block device has been active
 time_in_queue   milliseconds  total wait time for all requests
+discard I/Os    requests      number of discard I/Os processed
+discard merges  requests      number of discard I/Os merged with in-queue I/O
+discard sectors sectors       number of sectors discarded
+discard ticks   milliseconds  total wait time for discard requests
 
-read I/Os, write I/Os
-=====================
+read I/Os, write I/Os, discard I/0s
+===================================
 
 These values increment when an I/O request completes.
 
-read merges, write merges
-=========================
+read merges, write merges, discard merges
+=========================================
 
 These values increment when an I/O request is merged with an
 already-queued I/O request.
 
-read sectors, write sectors
-===========================
+read sectors, write sectors, discard_sectors
+============================================
 
-These values count the number of sectors read from or written to this
-block device.  The "sectors" in question are the standard UNIX 512-byte
-sectors, not any device- or filesystem-specific block size.  The
-counters are incremented when the I/O completes.
+These values count the number of sectors read from, written to, or
+discarded from this block device.  The "sectors" in question are the
+standard UNIX 512-byte sectors, not any device- or filesystem-specific
+block size.  The counters are incremented when the I/O completes.
 
-read ticks, write ticks
-=======================
+read ticks, write ticks, discard ticks
+======================================
 
 These values count the number of milliseconds that I/O requests have
 waited on this block device.  If there are multiple I/O requests waiting,
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 62ac5a9f3a9f..b691af4831fa 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -34,7 +34,7 @@ needs_sphinx = '1.3'
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain', 'kfigure']
+extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain', 'kfigure', 'sphinx.ext.ifconfig']
 
 # The name of the math extension changed on Sphinx 1.4
 if major == 1 and minor > 3:
diff --git a/Documentation/console/console.txt b/Documentation/console/console.txt
index f93810d599ad..d73c2ab4beda 100644
--- a/Documentation/console/console.txt
+++ b/Documentation/console/console.txt
@@ -1,7 +1,7 @@
 Console Drivers
 ===============
 
-The linux kernel has 2 general types of console drivers.  The first type is
+The Linux kernel has 2 general types of console drivers.  The first type is
 assigned by the kernel to all the virtual consoles during the boot process.
 This type will be called 'system driver', and only one system driver is allowed
 to exist. The system driver is persistent and it can never be unloaded, though
@@ -17,10 +17,11 @@ of driver occupying the consoles.) They can only take over the console that is
 occupied by the system driver. In the same token, if the modular driver is
 released by the console, the system driver will take over.
 
-Modular drivers, from the programmer's point of view, has to call:
+Modular drivers, from the programmer's point of view, have to call:
 
 	 do_take_over_console() - load and bind driver to console layer
-	 give_up_console() - unload driver, it will only work if driver is fully unbond
+	 give_up_console() - unload driver; it will only work if driver
+			     is fully unbound
 
 In newer kernels, the following are also available:
 
@@ -56,7 +57,7 @@ What do these files signify?
 	cat /sys/class/vtconsole/vtcon0/name
 	(S) VGA+
 
-	    '(S)' stands for a (S)ystem driver, ie, it cannot be directly
+	    '(S)' stands for a (S)ystem driver, i.e., it cannot be directly
 	    commanded to bind or unbind
 
 	    'VGA+' is the name of the driver
@@ -89,7 +90,7 @@ driver, make changes, recompile, reload and rebind the driver without any need
 for rebooting the kernel. For regular users who may want to switch from
 framebuffer console to VGA console and vice versa, this feature also makes
 this possible. (NOTE NOTE NOTE: Please read fbcon.txt under Documentation/fb
-for more details).
+for more details.)
 
 Notes for developers:
 =====================
@@ -110,8 +111,8 @@ In order for binding to and unbinding from the console to properly work,
 console drivers must follow these guidelines:
 
 1. All drivers, except system drivers, must call either do_register_con_driver()
-   or do_take_over_console(). do_register_con_driver() will just add the driver to
-   the console's internal list. It won't take over the
+   or do_take_over_console(). do_register_con_driver() will just add the driver
+   to the console's internal list. It won't take over the
    console. do_take_over_console(), as it name implies, will also take over (or
    bind to) the console.
 
diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst
index 2e7165f86f55..724583453e1f 100644
--- a/Documentation/core-api/atomic_ops.rst
+++ b/Documentation/core-api/atomic_ops.rst
@@ -29,7 +29,7 @@ updated by one CPU, local_t is probably more appropriate. Please see
 local_t.
 
 The first operations to implement for atomic_t's are the initializers and
-plain reads. ::
+plain writes. ::
 
 	#define ATOMIC_INIT(i)		{ (i) }
 	#define atomic_set(v, i)	((v)->counter = (i))
diff --git a/Documentation/core-api/boot-time-mm.rst b/Documentation/core-api/boot-time-mm.rst
new file mode 100644
index 000000000000..03cb1643f46f
--- /dev/null
+++ b/Documentation/core-api/boot-time-mm.rst
@@ -0,0 +1,92 @@
+===========================
+Boot time memory management
+===========================
+
+Early system initialization cannot use "normal" memory management
+simply because it is not set up yet. But there is still need to
+allocate memory for various data structures, for instance for the
+physical page allocator. To address this, a specialized allocator
+called the :ref:`Boot Memory Allocator <bootmem>`, or bootmem, was
+introduced. Several years later PowerPC developers added a "Logical
+Memory Blocks" allocator, which was later adopted by other
+architectures and renamed to :ref:`memblock <memblock>`. There is also
+a compatibility layer called `nobootmem` that translates bootmem
+allocation interfaces to memblock calls.
+
+The selection of the early allocator is done using
+``CONFIG_NO_BOOTMEM`` and ``CONFIG_HAVE_MEMBLOCK`` kernel
+configuration options. These options are enabled or disabled
+statically by the architectures' Kconfig files.
+
+* Architectures that rely only on bootmem select
+  ``CONFIG_NO_BOOTMEM=n && CONFIG_HAVE_MEMBLOCK=n``.
+* The users of memblock with the nobootmem compatibility layer set
+  ``CONFIG_NO_BOOTMEM=y && CONFIG_HAVE_MEMBLOCK=y``.
+* And for those that use both memblock and bootmem the configuration
+  includes ``CONFIG_NO_BOOTMEM=n && CONFIG_HAVE_MEMBLOCK=y``.
+
+Whichever allocator is used, it is the responsibility of the
+architecture specific initialization to set it up in
+:c:func:`setup_arch` and tear it down in :c:func:`mem_init` functions.
+
+Once the early memory management is available it offers a variety of
+functions and macros for memory allocations. The allocation request
+may be directed to the first (and probably the only) node or to a
+particular node in a NUMA system. There are API variants that panic
+when an allocation fails and those that don't. And more recent and
+advanced memblock even allows controlling its own behaviour.
+
+.. _bootmem:
+
+Bootmem
+=======
+
+(mostly stolen from Mel Gorman's "Understanding the Linux Virtual
+Memory Manager" `book`_)
+
+.. _book: https://www.kernel.org/doc/gorman/
+
+.. kernel-doc:: mm/bootmem.c
+   :doc: bootmem overview
+
+.. _memblock:
+
+Memblock
+========
+
+.. kernel-doc:: mm/memblock.c
+   :doc: memblock overview
+
+
+Functions and structures
+========================
+
+Common API
+----------
+
+The functions that are described in this section are available
+regardless of what early memory manager is enabled.
+
+.. kernel-doc:: mm/nobootmem.c
+
+Bootmem specific API
+--------------------
+
+These interfaces available only with bootmem, i.e when ``CONFIG_NO_BOOTMEM=n``
+
+.. kernel-doc:: include/linux/bootmem.h
+.. kernel-doc:: mm/bootmem.c
+   :nodocs:
+
+Memblock specific API
+---------------------
+
+Here is the description of memblock data structures, functions and
+macros. Some of them are actually internal, but since they are
+documented it would be silly to omit them. Besides, reading the
+descriptions for the internal functions can help to understand what
+really happens under the hood.
+
+.. kernel-doc:: include/linux/memblock.h
+.. kernel-doc:: mm/memblock.c
+   :nodocs:
diff --git a/Documentation/core-api/idr.rst b/Documentation/core-api/idr.rst
index 9078a5c3ac95..d351e880a2f6 100644
--- a/Documentation/core-api/idr.rst
+++ b/Documentation/core-api/idr.rst
@@ -76,4 +76,6 @@ Functions and structures
 ========================
 
 .. kernel-doc:: include/linux/idr.h
+   :functions:
 .. kernel-doc:: lib/idr.c
+   :functions:
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index f5a66b72f984..b5379fb740a5 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -28,6 +28,8 @@ Core utilities
    printk-formats
    circular-buffers
    gfp_mask-from-fs-io
+   timekeeping
+   boot-time-mm
 
 Interfaces for kernel debugging
 ===============================
diff --git a/Documentation/core-api/timekeeping.rst b/Documentation/core-api/timekeeping.rst
new file mode 100644
index 000000000000..93cbeb9daec0
--- /dev/null
+++ b/Documentation/core-api/timekeeping.rst
@@ -0,0 +1,185 @@
+ktime accessors
+===============
+
+Device drivers can read the current time using ktime_get() and the many
+related functions declared in linux/timekeeping.h. As a rule of thumb,
+using an accessor with a shorter name is preferred over one with a longer
+name if both are equally fit for a particular use case.
+
+Basic ktime_t based interfaces
+------------------------------
+
+The recommended simplest form returns an opaque ktime_t, with variants
+that return time for different clock references:
+
+
+.. c:function:: ktime_t ktime_get( void )
+
+	CLOCK_MONOTONIC
+
+	Useful for reliable timestamps and measuring short time intervals
+	accurately. Starts at system boot time but stops during suspend.
+
+.. c:function:: ktime_t ktime_get_boottime( void )
+
+	CLOCK_BOOTTIME
+
+	Like ktime_get(), but does not stop when suspended. This can be
+	used e.g. for key expiration times that need to be synchronized
+	with other machines across a suspend operation.
+
+.. c:function:: ktime_t ktime_get_real( void )
+
+	CLOCK_REALTIME
+
+	Returns the time in relative to the UNIX epoch starting in 1970
+	using the Coordinated Universal Time (UTC), same as gettimeofday()
+	user space. This is used for all timestamps that need to
+	persist across a reboot, like inode times, but should be avoided
+	for internal uses, since it can jump backwards due to a leap
+	second update, NTP adjustment settimeofday() operation from user
+	space.
+
+.. c:function:: ktime_t ktime_get_clocktai( void )
+
+	 CLOCK_TAI
+
+	Like ktime_get_real(), but uses the International Atomic Time (TAI)
+	reference instead of UTC to avoid jumping on leap second updates.
+	This is rarely useful in the kernel.
+
+.. c:function:: ktime_t ktime_get_raw( void )
+
+	CLOCK_MONOTONIC_RAW
+
+	Like ktime_get(), but runs at the same rate as the hardware
+	clocksource without (NTP) adjustments for clock drift. This is
+	also rarely needed in the kernel.
+
+nanosecond, timespec64, and second output
+-----------------------------------------
+
+For all of the above, there are variants that return the time in a
+different format depending on what is required by the user:
+
+.. c:function:: u64 ktime_get_ns( void )
+		u64 ktime_get_boottime_ns( void )
+		u64 ktime_get_real_ns( void )
+		u64 ktime_get_tai_ns( void )
+		u64 ktime_get_raw_ns( void )
+
+	Same as the plain ktime_get functions, but returning a u64 number
+	of nanoseconds in the respective time reference, which may be
+	more convenient for some callers.
+
+.. c:function:: void ktime_get_ts64( struct timespec64 * )
+		void ktime_get_boottime_ts64( struct timespec64 * )
+		void ktime_get_real_ts64( struct timespec64 * )
+		void ktime_get_clocktai_ts64( struct timespec64 * )
+		void ktime_get_raw_ts64( struct timespec64 * )
+
+	Same above, but returns the time in a 'struct timespec64', split
+	into seconds and nanoseconds. This can avoid an extra division
+	when printing the time, or when passing it into an external
+	interface that expects a 'timespec' or 'timeval' structure.
+
+.. c:function:: time64_t ktime_get_seconds( void )
+		time64_t ktime_get_boottime_seconds( void )
+		time64_t ktime_get_real_seconds( void )
+		time64_t ktime_get_clocktai_seconds( void )
+		time64_t ktime_get_raw_seconds( void )
+
+	Return a coarse-grained version of the time as a scalar
+	time64_t. This avoids accessing the clock hardware and rounds
+	down the seconds to the full seconds of the last timer tick
+	using the respective reference.
+
+Coarse and fast_ns access
+-------------------------
+
+Some additional variants exist for more specialized cases:
+
+.. c:function:: ktime_t ktime_get_coarse_boottime( void )
+		ktime_t ktime_get_coarse_real( void )
+		ktime_t ktime_get_coarse_clocktai( void )
+		ktime_t ktime_get_coarse_raw( void )
+
+.. c:function:: void ktime_get_coarse_ts64( struct timespec64 * )
+		void ktime_get_coarse_boottime_ts64( struct timespec64 * )
+		void ktime_get_coarse_real_ts64( struct timespec64 * )
+		void ktime_get_coarse_clocktai_ts64( struct timespec64 * )
+		void ktime_get_coarse_raw_ts64( struct timespec64 * )
+
+	These are quicker than the non-coarse versions, but less accurate,
+	corresponding to CLOCK_MONONOTNIC_COARSE and CLOCK_REALTIME_COARSE
+	in user space, along with the equivalent boottime/tai/raw
+	timebase not available in user space.
+
+	The time returned here corresponds to the last timer tick, which
+	may be as much as 10ms in the past (for CONFIG_HZ=100), same as
+	reading the 'jiffies' variable.  These are only useful when called
+	in a fast path and one still expects better than second accuracy,
+	but can't easily use 'jiffies', e.g. for inode timestamps.
+	Skipping the hardware clock access saves around 100 CPU cycles
+	on most modern machines with a reliable cycle counter, but
+	up to several microseconds on older hardware with an external
+	clocksource.
+
+.. c:function:: u64 ktime_get_mono_fast_ns( void )
+		u64 ktime_get_raw_fast_ns( void )
+		u64 ktime_get_boot_fast_ns( void )
+		u64 ktime_get_real_fast_ns( void )
+
+	These variants are safe to call from any context, including from
+	a non-maskable interrupt (NMI) during a timekeeper update, and
+	while we are entering suspend with the clocksource powered down.
+	This is useful in some tracing or debugging code as well as
+	machine check reporting, but most drivers should never call them,
+	since the time is allowed to jump under certain conditions.
+
+Deprecated time interfaces
+--------------------------
+
+Older kernels used some other interfaces that are now being phased out
+but may appear in third-party drivers being ported here. In particular,
+all interfaces returning a 'struct timeval' or 'struct timespec' have
+been replaced because the tv_sec member overflows in year 2038 on 32-bit
+architectures. These are the recommended replacements:
+
+.. c:function:: void ktime_get_ts( struct timespec * )
+
+	Use ktime_get() or ktime_get_ts64() instead.
+
+.. c:function:: struct timeval do_gettimeofday( void )
+		struct timespec getnstimeofday( void )
+		struct timespec64 getnstimeofday64( void )
+		void ktime_get_real_ts( struct timespec * )
+
+	ktime_get_real_ts64() is a direct replacement, but consider using
+	monotonic time (ktime_get_ts64()) and/or a ktime_t based interface
+	(ktime_get()/ktime_get_real()).
+
+.. c:function:: struct timespec current_kernel_time( void )
+		struct timespec64 current_kernel_time64( void )
+		struct timespec get_monotonic_coarse( void )
+		struct timespec64 get_monotonic_coarse64( void )
+
+	These are replaced by ktime_get_coarse_real_ts64() and
+	ktime_get_coarse_ts64(). However, A lot of code that wants
+	coarse-grained times can use the simple 'jiffies' instead, while
+	some drivers may actually want the higher resolution accessors
+	these days.
+
+.. c:function:: struct timespec getrawmonotonic( void )
+		struct timespec64 getrawmonotonic64( void )
+		struct timespec timekeeping_clocktai( void )
+		struct timespec64 timekeeping_clocktai64( void )
+		struct timespec get_monotonic_boottime( void )
+		struct timespec64 get_monotonic_boottime64( void )
+
+	These are replaced by ktime_get_raw()/ktime_get_raw_ts64(),
+	ktime_get_clocktai()/ktime_get_clocktai_ts64() as well
+	as ktime_get_boottime()/ktime_get_boottime_ts64().
+	However, if the particular choice of clock source is not
+	important for the user, consider converting to
+	ktime_get()/ktime_get_ts64() instead for consistency.
diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst
index 3bf371a938d0..6f653acea248 100644
--- a/Documentation/dev-tools/kselftest.rst
+++ b/Documentation/dev-tools/kselftest.rst
@@ -156,6 +156,11 @@ Contributing new tests (details)
    installed by the distro on the system should be the primary focus to be able
    to find regressions.
 
+ * If a test needs specific kernel config options enabled, add a config file in
+   the test directory to enable them.
+
+   e.g: tools/testing/selftests/android/ion/config
+
 Test Harness
 ============
 
diff --git a/Documentation/device-mapper/writecache.txt b/Documentation/device-mapper/writecache.txt
index 4424fa2c67d7..01532b3008ae 100644
--- a/Documentation/device-mapper/writecache.txt
+++ b/Documentation/device-mapper/writecache.txt
@@ -15,6 +15,8 @@ Constructor parameters:
    size)
 5. the number of optional parameters (the parameters with an argument
    count as two)
+	start_sector n		(default: 0)
+		offset from the start of cache device in 512-byte sectors
 	high_watermark n	(default: 50)
 		start writeback when the number of used blocks reach this
 		watermark
diff --git a/Documentation/devicetree/bindings/arm/freescale/fsl,vf610-mscm-ir.txt b/Documentation/devicetree/bindings/arm/freescale/fsl,vf610-mscm-ir.txt
index 669808b2af49..6dd6f399236d 100644
--- a/Documentation/devicetree/bindings/arm/freescale/fsl,vf610-mscm-ir.txt
+++ b/Documentation/devicetree/bindings/arm/freescale/fsl,vf610-mscm-ir.txt
@@ -18,9 +18,6 @@ Required properties:
 			assignment of the interrupt router is required.
 			Flags get passed only when using GIC as parent. Flags
 			encoding as documented by the GIC bindings.
-- interrupt-parent:	Should be the phandle for the interrupt controller of
-			the CPU the device tree is intended to be used on. This
-			is either the node of the GIC or NVIC controller.
 
 Example:
 	mscm_ir: interrupt-controller@40001800 {
diff --git a/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt b/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt
index 35c3c3460d17..eddde4faef01 100644
--- a/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt
@@ -33,3 +33,18 @@ nb_pm: syscon@14000 {
 	compatible = "marvell,armada-3700-nb-pm", "syscon";
 	reg = <0x14000 0x60>;
 }
+
+AVS
+---
+
+For AVS an other component is needed:
+
+Required properties:
+- compatible     : should contain "marvell,armada-3700-avs", "syscon";
+- reg            : the register start and length for the AVS
+
+Example:
+avs: avs@11500 {
+	compatible = "marvell,armada-3700-avs", "syscon";
+	reg = <0x11500 0x40>;
+}
diff --git a/Documentation/devicetree/bindings/arm/msm/qcom,llcc.txt b/Documentation/devicetree/bindings/arm/msm/qcom,llcc.txt
new file mode 100644
index 000000000000..5e85749262ae
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/msm/qcom,llcc.txt
@@ -0,0 +1,26 @@
+== Introduction==
+
+LLCC (Last Level Cache Controller) provides last level of cache memory in SOC,
+that can be shared by multiple clients. Clients here are different cores in the
+SOC, the idea is to minimize the local caches at the clients and migrate to
+common pool of memory. Cache memory is divided into partitions called slices
+which are assigned to clients. Clients can query the slice details, activate
+and deactivate them.
+
+Properties:
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be "qcom,sdm845-llcc"
+
+- reg:
+	Usage: required
+	Value Type: <prop-encoded-array>
+	Definition: Start address and the the size of the register region.
+
+Example:
+
+	cache-controller@1100000 {
+		compatible = "qcom,sdm845-llcc";
+		reg = <0x1100000 0x250000>;
+	};
diff --git a/Documentation/devicetree/bindings/arm/omap/crossbar.txt b/Documentation/devicetree/bindings/arm/omap/crossbar.txt
index ecb360ed0e33..4cd5d873fc3a 100644
--- a/Documentation/devicetree/bindings/arm/omap/crossbar.txt
+++ b/Documentation/devicetree/bindings/arm/omap/crossbar.txt
@@ -10,7 +10,6 @@ Required properties:
 - compatible : Should be "ti,irq-crossbar"
 - reg: Base address and the size of the crossbar registers.
 - interrupt-controller: indicates that this block is an interrupt controller.
-- interrupt-parent: the interrupt controller this block is connected to.
 - ti,max-irqs: Total number of irqs available at the parent interrupt controller.
 - ti,max-crossbar-sources: Maximum number of crossbar sources that can be routed.
 - ti,reg-size: Size of a individual register in bytes. Every individual
diff --git a/Documentation/devicetree/bindings/arm/samsung/pmu.txt b/Documentation/devicetree/bindings/arm/samsung/pmu.txt
index 16685787d2bd..433bfd7593ac 100644
--- a/Documentation/devicetree/bindings/arm/samsung/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/pmu.txt
@@ -40,9 +40,6 @@ following properties:
 - #interrupt-cells: must be identical to the that of the parent interrupt
   controller.
 
-- interrupt-parent: a phandle indicating which interrupt controller
-  this PMU signals interrupts to.
-
 
 Optional nodes:
 
diff --git a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
index bdadc3da9556..6970f30a3770 100644
--- a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
@@ -66,7 +66,7 @@ Required root node properties:
 	- "insignal,arndale-octa" - for Exynos5420-based Insignal Arndale
 				    Octa board.
 	- "insignal,origen"       - for Exynos4210-based Insignal Origen board.
-	- "insignal,origen4412    - for Exynos4412-based Insignal Origen board.
+	- "insignal,origen4412"   - for Exynos4412-based Insignal Origen board.
 
 
 Optional nodes:
diff --git a/Documentation/devicetree/bindings/ata/fsl-sata.txt b/Documentation/devicetree/bindings/ata/fsl-sata.txt
index b46bcf46c3d8..fd63bb3becc9 100644
--- a/Documentation/devicetree/bindings/ata/fsl-sata.txt
+++ b/Documentation/devicetree/bindings/ata/fsl-sata.txt
@@ -16,7 +16,6 @@ Required properties:
                           4 for controller @ 0x1b000
 
 Optional properties:
-- interrupt-parent  : optional, if needed for interrupt mapping
 - reg               : <registers mapping>
 
 Example:
diff --git a/Documentation/devicetree/bindings/ata/pata-arasan.txt b/Documentation/devicetree/bindings/ata/pata-arasan.txt
index 2aff154be84e..872edc105680 100644
--- a/Documentation/devicetree/bindings/ata/pata-arasan.txt
+++ b/Documentation/devicetree/bindings/ata/pata-arasan.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: "arasan,cf-spear1340"
 - reg: Address range of the CF registers
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupt: Should contain the CF interrupt number
 - clock-frequency: Interface clock rate, in Hz, one of
        25000000
diff --git a/Documentation/devicetree/bindings/board/fsl-board.txt b/Documentation/devicetree/bindings/board/fsl-board.txt
index fb7b03ec2071..eb52f6b35159 100644
--- a/Documentation/devicetree/bindings/board/fsl-board.txt
+++ b/Documentation/devicetree/bindings/board/fsl-board.txt
@@ -29,7 +29,6 @@ Required properties:
 - reg: should contain the address and the length of the FPGA register set.
 
 Optional properties:
-- interrupt-parent: should specify phandle for the interrupt controller.
 - interrupts: should specify event (wakeup) IRQ.
 
 Example (P1022DS):
diff --git a/Documentation/devicetree/bindings/bus/brcm,gisb-arb.txt b/Documentation/devicetree/bindings/bus/brcm,gisb-arb.txt
index 8a6c3c2e58fe..729def62f0c5 100644
--- a/Documentation/devicetree/bindings/bus/brcm,gisb-arb.txt
+++ b/Documentation/devicetree/bindings/bus/brcm,gisb-arb.txt
@@ -9,8 +9,6 @@ Required properties:
     "brcm,bcm7400-gisb-arb" for older 40nm chips and all 65nm chips
     "brcm,bcm7038-gisb-arb" for 130nm chips
 - reg: specifies the base physical address and size of the registers
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this arbiter gets interrupt line from
 - interrupts: specifies the two interrupts (timeout and TEA) to be used from
   the parent interrupt controller
 
diff --git a/Documentation/devicetree/bindings/clock/at91-clock.txt b/Documentation/devicetree/bindings/clock/at91-clock.txt
index 51c259a92d02..33fe9591e904 100644
--- a/Documentation/devicetree/bindings/clock/at91-clock.txt
+++ b/Documentation/devicetree/bindings/clock/at91-clock.txt
@@ -180,7 +180,6 @@ For example:
 	};
 
 Required properties for main clock internal RC oscillator:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<0>".
 - clock-frequency : define the internal RC oscillator frequency.
 
@@ -197,7 +196,6 @@ For example:
 	};
 
 Required properties for main clock oscillator:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<0>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall encode the main osc source clk sources (see atmel datasheet).
@@ -218,7 +216,6 @@ For example:
 	};
 
 Required properties for main clock:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<0>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall encode the main clk sources (see atmel datasheet).
@@ -233,7 +230,6 @@ For example:
 	};
 
 Required properties for master clock:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<3>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall be the master clock sources (see atmel datasheet) phandles.
@@ -292,7 +288,6 @@ For example:
 
 
 Required properties for pll clocks:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<1>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall be the main clock phandle.
@@ -348,7 +343,6 @@ For example:
 	};
 
 Required properties for programmable clocks:
-- interrupt-parent : must reference the PMC node.
 - #size-cells : shall be 0 (reg is used to encode clk id).
 - #address-cells : shall be 1 (reg is used to encode clk id).
 - clocks : shall be the programmable clock source phandles.
@@ -451,7 +445,6 @@ For example:
 
 
 Required properties for utmi clock:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<AT91_PMC_LOCKU IRQ_TYPE_LEVEL_HIGH>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall be the main clock source phandle.
diff --git a/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt
index af2385795d78..73470ecd1f12 100644
--- a/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt
+++ b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt
@@ -29,8 +29,6 @@ Required properties:
 - reg: Specifies base physical address and size of the registers.
 - interrupts: The interrupt that the AVS CPU will use to interrupt the host
               when a command completed.
-- interrupt-parent: The interrupt controller the above interrupt is routed
-                    through.
 - interrupt-names: The name of the interrupt used to interrupt the host.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/crypto/amd-ccp.txt b/Documentation/devicetree/bindings/crypto/amd-ccp.txt
index 8c61183b41e0..d87579d63da6 100644
--- a/Documentation/devicetree/bindings/crypto/amd-ccp.txt
+++ b/Documentation/devicetree/bindings/crypto/amd-ccp.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: Should be "amd,ccp-seattle-v1a"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the CCP interrupt
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt b/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
index c2598ab27f2e..999fb2a810f6 100644
--- a/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
+++ b/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
@@ -7,8 +7,6 @@ Required properties:
 - interrupts: Interrupt number for the device.
 
 Optional properties:
-- interrupt-parent: The phandle for the interrupt controller that services
-  interrupts for this device.
 - clocks: Reference to the crypto engine clock.
 - dma-coherent: Present if dma operations are coherent.
 
diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec2.txt b/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
index f0d926bf9f36..125f155d00d0 100644
--- a/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
@@ -50,11 +50,6 @@ remaining bits are reserved for future SEC EUs.
 
   ..and so on and so forth.
 
-Optional properties:
-
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
-
 Example:
 
 	/* MPC8548E */
diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
index 3c1f3a229eab..2fe245ca816a 100644
--- a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
@@ -99,13 +99,6 @@ PROPERTIES
            of the specifier is defined by the binding document
            describing the node's interrupt parent.
 
-   - interrupt-parent
-      Usage: (required if interrupt property is defined)
-      Value type: <phandle>
-      Definition: A single <phandle> value that points
-          to the interrupt parent to which the child domain
-          is being mapped.
-
    - clocks
       Usage: required if SEC 4.0 requires explicit enablement of clocks
       Value type: <prop_encoded-array>
@@ -199,13 +192,6 @@ Job Ring (JR) Node
            of the specifier is defined by the binding document
            describing the node's interrupt parent.
 
-   - interrupt-parent
-      Usage: (required if interrupt property is defined)
-      Value type: <phandle>
-      Definition: A single <phandle> value that points
-          to the interrupt parent to which the child domain
-          is being mapped.
-
 EXAMPLE
 	jr@1000 {
 		compatible = "fsl,sec-v4.0-job-ring";
@@ -370,13 +356,6 @@ Secure Non-Volatile Storage (SNVS) Node
            of the specifier is defined by the binding document
            describing the node's interrupt parent.
 
-   - interrupt-parent
-      Usage: (required if interrupt property is defined)
-      Value type: <phandle>
-      Definition: A single <phandle> value that points
-          to the interrupt parent to which the child domain
-          is being mapped.
-
 EXAMPLE
 	sec_mon@314000 {
 		compatible = "fsl,sec-v4.0-mon", "syscon";
diff --git a/Documentation/devicetree/bindings/crypto/picochip-spacc.txt b/Documentation/devicetree/bindings/crypto/picochip-spacc.txt
index d8609ece1f4c..df1151f87745 100644
--- a/Documentation/devicetree/bindings/crypto/picochip-spacc.txt
+++ b/Documentation/devicetree/bindings/crypto/picochip-spacc.txt
@@ -7,8 +7,6 @@ Required properties:
   - compatible : "picochip,spacc-ipsec" for the IPSEC offload engine
     "picochip,spacc-l2" for the femtocell layer 2 ciphering engine.
   - reg : Offset and length of the register set for this device
-  - interrupt-parent : The interrupt controller that controls the SPAcc
-    interrupt.
   - interrupts : The interrupt line from the SPAcc.
   - ref-clock : The input clock that drives the SPAcc.
 
diff --git a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
index fc2bcbe26b1e..0ec68141f85a 100644
--- a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
+++ b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
@@ -1,14 +1,10 @@
-* Rockchip rk3399 DMC(Dynamic Memory Controller) device
+* Rockchip rk3399 DMC (Dynamic Memory Controller) device
 
 Required properties:
 - compatible:		 Must be "rockchip,rk3399-dmc".
 - devfreq-events:	 Node to get DDR loading, Refer to
-			 Documentation/devicetree/bindings/devfreq/
+			 Documentation/devicetree/bindings/devfreq/event/
 			 rockchip-dfi.txt
-- interrupts:		 The interrupt number to the CPU. The interrupt
-			 specifier format depends on the interrupt controller.
-			 It should be DCF interrupts, when DDR dvfs finish,
-			 it will happen.
 - clocks:		 Phandles for clock specified in "clock-names" property
 - clock-names :		 The name of clock used by the DFI, must be
 			 "pclk_ddr_mon";
@@ -17,139 +13,148 @@ Required properties:
 - center-supply:	 DMC supply node.
 - status:		 Marks the node enabled/disabled.
 
-Following properties are ddr timing:
-
-- rockchip,dram_speed_bin :	  Value reference include/dt-bindings/clock/ddr.h,
-				  it select ddr3 cl-trp-trcd type, default value
-				  "DDR3_DEFAULT".it must selected according to
-				  "Speed Bin" in ddr3 datasheet, DO NOT use
-				  smaller "Speed Bin" than ddr3 exactly is.
-
-- rockchip,pd_idle :		  Config the PD_IDLE value, defined the power-down
-				  idle period, memories are places into power-down
-				  mode if bus is idle for PD_IDLE DFI clocks.
-
-- rockchip,sr_idle :		  Configure the SR_IDLE value, defined the
-				  selfrefresh idle period, memories are places
-				  into self-refresh mode if bus is idle for
-				  SR_IDLE*1024 DFI clocks (DFI clocks freq is
-				  half of dram's clocks), defaule value is "0".
-
-- rockchip,sr_mc_gate_idle :	  Defined the self-refresh with memory and
-				  controller clock gating idle period, memories
-				  are places into self-refresh mode and memory
-				  controller clock arg gating if bus is idle for
-				  sr_mc_gate_idle*1024 DFI clocks.
-
-- rockchip,srpd_lite_idle :	  Defined the self-refresh power down idle
-				  period, memories are places into self-refresh
-				  power down mode if bus is idle for
-				  srpd_lite_idle*1024 DFI clocks. This parameter
-				  is for LPDDR4 only.
-
-- rockchip,standby_idle :	  Defined the standby idle period, memories are
-				  places into self-refresh than controller, pi,
-				  phy and dram clock will gating if bus is idle
-				  for standby_idle * DFI clocks.
-
-- rockchip,dram_dll_disb_freq :  It's defined the DDR3 dll bypass frequency in
-				  MHz, when ddr freq less than DRAM_DLL_DISB_FREQ,
-				  ddr3 dll will bypssed note: if dll was bypassed,
-				  the odt also stop working.
-
-- rockchip,phy_dll_disb_freq :	  Defined the PHY dll bypass frequency in
-				  MHz (Mega Hz), when ddr freq less than
-				  DRAM_DLL_DISB_FREQ, phy dll will bypssed.
-				  note: phy dll and phy odt are independent.
-
-- rockchip,ddr3_odt_disb_freq :  When dram type is DDR3, this parameter defined
-				  the odt disable frequency in MHz (Mega Hz),
-				  when ddr frequency less then ddr3_odt_disb_freq,
-				  the odt on dram side and controller side are
+Optional properties:
+- interrupts:		 The CPU interrupt number. The interrupt specifier
+			 format depends on the interrupt controller.
+			 It should be a DCF interrupt. When DDR DVFS finishes
+			 a DCF interrupt is triggered.
+
+Following properties relate to DDR timing:
+
+- rockchip,dram_speed_bin :	  Value reference include/dt-bindings/clock/rk3399-ddr.h,
+				  it selects the DDR3 cl-trp-trcd type. It must be
+				  set according to "Speed Bin" in DDR3 datasheet,
+				  DO NOT use a smaller "Speed Bin" than specified
+				  for the DDR3 being used.
+
+- rockchip,pd_idle :		  Configure the PD_IDLE value. Defines the
+				  power-down idle period in which memories are
+				  placed into power-down mode if bus is idle
+				  for PD_IDLE DFI clock cycles.
+
+- rockchip,sr_idle :		  Configure the SR_IDLE value. Defines the
+				  self-refresh idle period in which memories are
+				  placed into self-refresh mode if bus is idle
+				  for SR_IDLE * 1024 DFI clock cycles (DFI
+				  clocks freq is half of DRAM clock), default
+				  value is "0".
+
+- rockchip,sr_mc_gate_idle :	  Defines the memory self-refresh and controller
+				  clock gating idle period. Memories are placed
+				  into self-refresh mode and memory controller
+				  clock arg gating started if bus is idle for
+				  sr_mc_gate_idle*1024 DFI clock cycles.
+
+- rockchip,srpd_lite_idle :	  Defines the self-refresh power down idle
+				  period in which memories are placed into
+				  self-refresh power down mode if bus is idle
+				  for srpd_lite_idle * 1024 DFI clock cycles.
+				  This parameter is for LPDDR4 only.
+
+- rockchip,standby_idle :	  Defines the standby idle period in which
+				  memories are placed into self-refresh mode.
+				  The controller, pi, PHY and DRAM clock will
+				  be gated if bus is idle for standby_idle * DFI
+				  clock cycles.
+
+- rockchip,dram_dll_dis_freq :	  Defines the DDR3 DLL bypass frequency in MHz.
+				  When DDR frequency is less than DRAM_DLL_DISB_FREQ,
+				  DDR3 DLL will be bypassed. Note: if DLL was bypassed,
+				  the odt will also stop working.
+
+- rockchip,phy_dll_dis_freq :	  Defines the PHY dll bypass frequency in
+				  MHz (Mega Hz). When DDR frequency is less than
+				  DRAM_DLL_DISB_FREQ, PHY DLL will be bypassed.
+				  Note: PHY DLL and PHY ODT are independent.
+
+- rockchip,ddr3_odt_dis_freq :	  When the DRAM type is DDR3, this parameter defines
+				  the ODT disable frequency in MHz (Mega Hz).
+				  when the DDR frequency is  less then ddr3_odt_dis_freq,
+				  the ODT on the DRAM side and controller side are
 				  both disabled.
 
-- rockchip,ddr3_drv :		  When dram type is DDR3, this parameter define
-				  the dram side driver stength in ohm, default
+- rockchip,ddr3_drv :		  When the DRAM type is DDR3, this parameter defines
+				  the DRAM side driver strength in ohms. Default
 				  value is DDR3_DS_40ohm.
 
-- rockchip,ddr3_odt :		  When dram type is DDR3, this parameter define
-				  the dram side ODT stength in ohm, default value
+- rockchip,ddr3_odt :		  When the DRAM type is DDR3, this parameter defines
+				  the DRAM side ODT strength in ohms. Default value
 				  is DDR3_ODT_120ohm.
 
-- rockchip,phy_ddr3_ca_drv :	  When dram type is DDR3, this parameter define
-				  the phy side CA line(incluing command line,
+- rockchip,phy_ddr3_ca_drv :	  When the DRAM type is DDR3, this parameter defines
+				  the phy side CA line (incluing command line,
 				  address line and clock line) driver strength.
 				  Default value is PHY_DRV_ODT_40.
 
-- rockchip,phy_ddr3_dq_drv :	  When dram type is DDR3, this parameter define
-				  the phy side DQ line(incluing DQS/DQ/DM line)
-				  driver strength. default value is PHY_DRV_ODT_40.
+- rockchip,phy_ddr3_dq_drv :	  When the DRAM type is DDR3, this parameter defines
+				  the PHY side DQ line (including DQS/DQ/DM line)
+				  driver strength. Default value is PHY_DRV_ODT_40.
 
-- rockchip,phy_ddr3_odt : 	  When dram type is DDR3, this parameter define the
-				  phy side odt strength, default value is
+- rockchip,phy_ddr3_odt : 	  When the DRAM type is DDR3, this parameter defines
+				  the PHY side ODT strength. Default value is
 				  PHY_DRV_ODT_240.
 
-- rockchip,lpddr3_odt_disb_freq : When dram type is LPDDR3, this parameter defined
-				  then odt disable frequency in MHz (Mega Hz),
-				  when ddr frequency less then ddr3_odt_disb_freq,
-				  the odt on dram side and controller side are
+- rockchip,lpddr3_odt_dis_freq : When the DRAM type is LPDDR3, this parameter defines
+				  then ODT disable frequency in MHz (Mega Hz).
+				  When DDR frequency is less then ddr3_odt_dis_freq,
+				  the ODT on the DRAM side and controller side are
 				  both disabled.
 
-- rockchip,lpddr3_drv :	  When dram type is LPDDR3, this parameter define
-				  the dram side driver stength in ohm, default
+- rockchip,lpddr3_drv :		  When the DRAM type is LPDDR3, this parameter defines
+				  the DRAM side driver strength in ohms. Default
 				  value is LP3_DS_34ohm.
 
-- rockchip,lpddr3_odt :	  When dram type is LPDDR3, this parameter define
-				  the dram side ODT stength in ohm, default value
+- rockchip,lpddr3_odt :		  When the DRAM type is LPDDR3, this parameter defines
+				  the DRAM side ODT strength in ohms. Default value
 				  is LP3_ODT_240ohm.
 
-- rockchip,phy_lpddr3_ca_drv :	  When dram type is LPDDR3, this parameter define
-				  the phy side CA line(incluing command line,
+- rockchip,phy_lpddr3_ca_drv :	  When the DRAM type is LPDDR3, this parameter defines
+				  the PHY side CA line (including command line,
 				  address line and clock line) driver strength.
-				  default value is PHY_DRV_ODT_40.
+				  Default value is PHY_DRV_ODT_40.
 
-- rockchip,phy_lpddr3_dq_drv :	  When dram type is LPDDR3, this parameter define
-				  the phy side DQ line(incluing DQS/DQ/DM line)
-				  driver strength. default value is
+- rockchip,phy_lpddr3_dq_drv :	  When the DRAM type is LPDDR3, this parameter defines
+				  the PHY side DQ line (including DQS/DQ/DM line)
+				  driver strength. Default value is
 				  PHY_DRV_ODT_40.
 
 - rockchip,phy_lpddr3_odt : 	  When dram type is LPDDR3, this parameter define
 				  the phy side odt strength, default value is
 				  PHY_DRV_ODT_240.
 
-- rockchip,lpddr4_odt_disb_freq : When dram type is LPDDR4, this parameter
-				  defined the odt disable frequency in
-				  MHz (Mega Hz), when ddr frequency less then
-				  ddr3_odt_disb_freq, the odt on dram side and
+- rockchip,lpddr4_odt_dis_freq : When the DRAM type is LPDDR4, this parameter
+				  defines the ODT disable frequency in
+				  MHz (Mega Hz). When the DDR frequency is less then
+				  ddr3_odt_dis_freq, the ODT on the DRAM side and
 				  controller side are both disabled.
 
-- rockchip,lpddr4_drv :	  When dram type is LPDDR4, this parameter define
-				  the dram side driver stength in ohm, default
+- rockchip,lpddr4_drv :		  When the DRAM type is LPDDR4, this parameter defines
+				  the DRAM side driver strength in ohms. Default
 				  value is LP4_PDDS_60ohm.
 
-- rockchip,lpddr4_dq_odt : 	  When dram type is LPDDR4, this parameter define
-				  the dram side ODT on dqs/dq line stength in ohm,
-				  default value is LP4_DQ_ODT_40ohm.
+- rockchip,lpddr4_dq_odt : 	  When the DRAM type is LPDDR4, this parameter defines
+				  the DRAM side ODT on DQS/DQ line strength in ohms.
+				  Default value is LP4_DQ_ODT_40ohm.
 
-- rockchip,lpddr4_ca_odt :	  When dram type is LPDDR4, this parameter define
-				  the dram side ODT on ca line stength in ohm,
-				  default value is LP4_CA_ODT_40ohm.
+- rockchip,lpddr4_ca_odt :	  When the DRAM type is LPDDR4, this parameter defines
+				  the DRAM side ODT on CA line strength in ohms.
+				  Default value is LP4_CA_ODT_40ohm.
 
-- rockchip,phy_lpddr4_ca_drv :	  When dram type is LPDDR4, this parameter define
-				  the phy side  CA line(incluing command address
-				  line) driver strength. default value is
+- rockchip,phy_lpddr4_ca_drv :	  When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side CA line (including command address
+				  line) driver strength. Default value is
 				  PHY_DRV_ODT_40.
 
-- rockchip,phy_lpddr4_ck_cs_drv : When dram type is LPDDR4, this parameter define
-				  the phy side clock line and cs line driver
-				  strength. default value is PHY_DRV_ODT_80.
+- rockchip,phy_lpddr4_ck_cs_drv : When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side clock line and CS line driver
+				  strength. Default value is PHY_DRV_ODT_80.
 
-- rockchip,phy_lpddr4_dq_drv :	  When dram type is LPDDR4, this parameter define
-				  the phy side DQ line(incluing DQS/DQ/DM line)
-				  driver strength. default value is PHY_DRV_ODT_80.
+- rockchip,phy_lpddr4_dq_drv :	  When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side DQ line (including DQS/DQ/DM line)
+				  driver strength. Default value is PHY_DRV_ODT_80.
 
-- rockchip,phy_lpddr4_odt :	  When dram type is LPDDR4, this parameter define
-				  the phy side odt strength, default value is
+- rockchip,phy_lpddr4_odt :	  When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side ODT strength. Default value is
 				  PHY_DRV_ODT_60.
 
 Example:
diff --git a/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt b/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt
index 0c7473dd0e51..027d76c27a41 100644
--- a/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt
+++ b/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt
@@ -15,8 +15,6 @@ Required properties for dp-controller:
 		from common clock binding: handle to dp clock.
 	-clock-names:
 		from common clock binding: Shall be "dp".
-	-interrupt-parent:
-		phandle to Interrupt combiner node.
 	-phys:
 		from general PHY binding: the phandle for the PHY device.
 	-phy-names:
diff --git a/Documentation/devicetree/bindings/display/bridge/anx7814.txt b/Documentation/devicetree/bindings/display/bridge/anx7814.txt
index b2a22c28c9b3..dbd7c84ee584 100644
--- a/Documentation/devicetree/bindings/display/bridge/anx7814.txt
+++ b/Documentation/devicetree/bindings/display/bridge/anx7814.txt
@@ -8,8 +8,6 @@ Required properties:
 
  - compatible		: "analogix,anx7814"
  - reg			: I2C address of the device
- - interrupt-parent	: Should be the phandle of the interrupt controller
-			  that services interrupts for this device
  - interrupts		: Should contain the INTP interrupt
  - hpd-gpios		: Which GPIO to use for hpd
  - pd-gpios		: Which GPIO to use for power down
diff --git a/Documentation/devicetree/bindings/display/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt b/Documentation/devicetree/bindings/display/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt
index aacc8b92968c..09e0a21f705e 100644
--- a/Documentation/devicetree/bindings/display/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt
+++ b/Documentation/devicetree/bindings/display/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt
@@ -19,8 +19,6 @@ hardware are EDID, HPD, and interrupts.
 stdp4028-ge-b850v3-fw required properties:
   - compatible : "megachips,stdp4028-ge-b850v3-fw"
   - reg : I2C bus address
-  - interrupt-parent : phandle of the interrupt controller that services
-    interrupts to the device
   - interrupts : one interrupt should be described here, as in
     <0 IRQ_TYPE_LEVEL_HIGH>
   - ports : One input port(reg = <0>) and one output port(reg = <1>)
diff --git a/Documentation/devicetree/bindings/display/bridge/sii902x.txt b/Documentation/devicetree/bindings/display/bridge/sii902x.txt
index 56a3e68ccb80..72d2dc6c3e6b 100644
--- a/Documentation/devicetree/bindings/display/bridge/sii902x.txt
+++ b/Documentation/devicetree/bindings/display/bridge/sii902x.txt
@@ -5,8 +5,8 @@ Required properties:
 	- reg: i2c address of the bridge
 
 Optional properties:
-	- interrupts-extended or interrupt-parent + interrupts: describe
-	  the interrupt line used to inform the host about hotplug events.
+	- interrupts: describe the interrupt line used to inform the host 
+	  about hotplug events.
 	- reset-gpios: OF device-tree gpio specification for RST_N pin.
 
 Optional subnodes:
diff --git a/Documentation/devicetree/bindings/display/bridge/sii9234.txt b/Documentation/devicetree/bindings/display/bridge/sii9234.txt
index 88041ba23d56..a55bf77bd960 100644
--- a/Documentation/devicetree/bindings/display/bridge/sii9234.txt
+++ b/Documentation/devicetree/bindings/display/bridge/sii9234.txt
@@ -7,7 +7,7 @@ Required properties:
 	- iovcc18-supply : I/O Supply Voltage (1.8V)
 	- avcc12-supply : TMDS Analog Supply Voltage (1.2V)
 	- cvcc12-supply : Digital Core Supply Voltage (1.2V)
-	- interrupts, interrupt-parent: interrupt specifier of INT pin
+	- interrupts: interrupt specifier of INT pin
 	- reset-gpios: gpio specifier of RESET pin (active low)
 	- video interfaces: Device node can contain two video interface port
 			    nodes for HDMI encoder and connector according to [1].
diff --git a/Documentation/devicetree/bindings/display/bridge/sil-sii8620.txt b/Documentation/devicetree/bindings/display/bridge/sil-sii8620.txt
index 9409d9c6a260..b05052f7d62f 100644
--- a/Documentation/devicetree/bindings/display/bridge/sil-sii8620.txt
+++ b/Documentation/devicetree/bindings/display/bridge/sil-sii8620.txt
@@ -5,7 +5,7 @@ Required properties:
 	- reg: i2c address of the bridge
 	- cvcc10-supply: Digital Core Supply Voltage (1.0V)
 	- iovcc18-supply: I/O Supply Voltage (1.8V)
-	- interrupts, interrupt-parent: interrupt specifier of INT pin
+	- interrupts: interrupt specifier of INT pin
 	- reset-gpios: gpio specifier of RESET pin
 	- clocks, clock-names: specification and name of "xtal" clock
 	- video interfaces: Device node can contain video interface port
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos7-decon.txt b/Documentation/devicetree/bindings/display/exynos/exynos7-decon.txt
index 9e2e7f6f7609..53912c99ec38 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos7-decon.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos7-decon.txt
@@ -9,9 +9,6 @@ Required properties:
 
 - reg: physical base address and length of the DECON registers set.
 
-- interrupt-parent: should be the phandle of the decon controller's
-		parent interrupt controller.
-
 - interrupts: should contain a list of all DECON IP block interrupts in the
 		 order: FIFO Level, VSYNC, LCD_SYSTEM. The interrupt specifier
 		 format depends on the interrupt controller used.
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt b/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt
index ade5d8eebf85..9b6cba3f82af 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt
@@ -25,8 +25,6 @@ Required properties for dp-controller:
 		from common clock binding: handle to dp clock.
 	-clock-names:
 		from common clock binding: Shall be "dp".
-	-interrupt-parent:
-		phandle to Interrupt combiner node.
 	-phys:
 		from general PHY binding: the phandle for the PHY device.
 	-phy-names:
diff --git a/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt b/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
index 5837402c3ade..b3096421d42b 100644
--- a/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
+++ b/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
@@ -16,9 +16,6 @@ Required properties:
 
 - reg: physical base address and length of the FIMD registers set.
 
-- interrupt-parent: should be the phandle of the fimd controller's
-		parent interrupt controller.
-
 - interrupts: should contain a list of all FIMD IP block interrupts in the
 		 order: FIFO Level, VSYNC, LCD_SYSTEM. The interrupt specifier
 		 format depends on the interrupt controller used.
diff --git a/Documentation/devicetree/bindings/display/ht16k33.txt b/Documentation/devicetree/bindings/display/ht16k33.txt
index 8e5b30b87754..d5a8b070b467 100644
--- a/Documentation/devicetree/bindings/display/ht16k33.txt
+++ b/Documentation/devicetree/bindings/display/ht16k33.txt
@@ -4,8 +4,6 @@ Holtek ht16k33 RAM mapping 16*8 LED controller driver with keyscan
 Required properties:
 - compatible:		"holtek,ht16k33"
 - reg:			I2C slave address of the chip.
-- interrupt-parent:	A phandle pointing to the interrupt controller
-			serving the interrupt for this chip.
 - interrupts:		Interrupt specification for the key pressed interrupt.
 - refresh-rate-hz:	Display update interval in HZ.
 - debounce-delay-ms:	Debouncing interval time in milliseconds.
diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt
index 518e9cdf0d4b..5eaffca2e28c 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi.txt
+++ b/Documentation/devicetree/bindings/display/msm/dsi.txt
@@ -43,8 +43,6 @@ Optional properties:
   the master link of the 2-DSI panel.
 - qcom,sync-dual-dsi: Boolean value indicating if the DSI controller is
   driving a 2-DSI panel whose 2 links need receive command simultaneously.
-- interrupt-parent: phandle to the MDP block if the interrupt signal is routed
-  through MDP block
 - pinctrl-names: the pin control state names; should contain "default"
 - pinctrl-0: the default pinctrl state (active)
 - pinctrl-n: the "sleep" pinctrl state
diff --git a/Documentation/devicetree/bindings/display/msm/edp.txt b/Documentation/devicetree/bindings/display/msm/edp.txt
index 95ce19ca7bc5..eff9daff418c 100644
--- a/Documentation/devicetree/bindings/display/msm/edp.txt
+++ b/Documentation/devicetree/bindings/display/msm/edp.txt
@@ -25,10 +25,6 @@ Required properties:
 - panel-hpd-gpios: GPIO pin used for eDP hpd.
 
 
-Optional properties:
-- interrupt-parent: phandle to the MDP block if the interrupt signal is routed
-  through MDP block
-
 Example:
 	mdss_edp: qcom,mdss_edp@fd923400 {
 			compatible = "qcom,mdss-edp";
diff --git a/Documentation/devicetree/bindings/display/msm/mdp5.txt b/Documentation/devicetree/bindings/display/msm/mdp5.txt
index 1b31977a68ba..4e11338548aa 100644
--- a/Documentation/devicetree/bindings/display/msm/mdp5.txt
+++ b/Documentation/devicetree/bindings/display/msm/mdp5.txt
@@ -41,8 +41,6 @@ Required properties:
 - reg-names: The names of register regions. The following regions are required:
   * "mdp_phys"
 - interrupts: Interrupt line from MDP5 to MDSS interrupt controller.
-- interrupt-parent: phandle to the MDSS block
-  through MDP block
 - clocks: device clocks. See ../clocks/clock-bindings.txt for details.
 - clock-names: the following clocks are required.
 -   * "bus"
diff --git a/Documentation/devicetree/bindings/display/renesas,du.txt b/Documentation/devicetree/bindings/display/renesas,du.txt
index 7c6854bd0a04..ec9d34be2ff7 100644
--- a/Documentation/devicetree/bindings/display/renesas,du.txt
+++ b/Documentation/devicetree/bindings/display/renesas,du.txt
@@ -19,7 +19,6 @@ Required Properties:
 
   - reg: the memory-mapped I/O registers base address and length
 
-  - interrupt-parent: phandle of the parent interrupt controller.
   - interrupts: Interrupt specifiers for the DU interrupts.
 
   - clocks: A list of phandles + clock-specifier pairs, one for each entry in
diff --git a/Documentation/devicetree/bindings/display/sm501fb.txt b/Documentation/devicetree/bindings/display/sm501fb.txt
index 9d9f0098092b..1c79c267a57f 100644
--- a/Documentation/devicetree/bindings/display/sm501fb.txt
+++ b/Documentation/devicetree/bindings/display/sm501fb.txt
@@ -9,8 +9,6 @@ Required properties:
     - First entry: System Configuration register
     - Second entry: IO space (Display Controller register)
 - interrupts : SMI interrupt to the cpu should be described here.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 
 Optional properties:
 - mode : select a video mode:
diff --git a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
index 6fddb4f4f71a..7bf1bb444812 100644
--- a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
+++ b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
@@ -8,8 +8,6 @@ Required properties:
  - reg: base address and size of the LCDC device
 
 Recommended properties:
- - interrupt-parent: the phandle for the interrupt controller that
-   services interrupts for this device.
  - ti,hwmods: Name of the hwmod associated to the LCDC
 
 Optional properties:
@@ -36,7 +34,7 @@ Optional nodes:
 
  - port/ports: to describe a connection to an external encoder. The
    binding follows Documentation/devicetree/bindings/graph.txt and
-   suppors a single port with a single endpoint.
+   supports a single port with a single endpoint.
 
  - See also Documentation/devicetree/bindings/display/tilcdc/panel.txt and
    Documentation/devicetree/bindings/display/tilcdc/tfp410.txt for connecting
diff --git a/Documentation/devicetree/bindings/dma/jz4780-dma.txt b/Documentation/devicetree/bindings/dma/jz4780-dma.txt
index f25feee62b15..03e9cf7b42e0 100644
--- a/Documentation/devicetree/bindings/dma/jz4780-dma.txt
+++ b/Documentation/devicetree/bindings/dma/jz4780-dma.txt
@@ -5,7 +5,6 @@ Required properties:
 - compatible: Should be "ingenic,jz4780-dma"
 - reg: Should contain the DMA controller registers location and length.
 - interrupts: Should contain the interrupt specifier of the DMA controller.
-- interrupt-parent: Should be the phandle of the interrupt controller that
 - clocks: Should contain a clock specifier for the JZ4780 PDMA clock.
 - #dma-cells: Must be <2>. Number of integer cells in the dmas property of
   DMA clients (see below).
diff --git a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.txt b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.txt
index 1e1dc8f972e4..2f35b047f772 100644
--- a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.txt
+++ b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.txt
@@ -8,7 +8,6 @@ Required properties:
 - reg: Should contain DMA registers location and length. This should be
   a single entry that includes all of the per-channel registers in one
   contiguous bank.
-- interrupt-parent: Phandle to the interrupt parent controller.
 - interrupts: Should contain all of the per-channel DMA interrupts in
   ascending order with respect to the DMA channel index.
 - clocks: Must contain one entry for the ADMA module clock
diff --git a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.txt b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.txt
index f237b7928283..dbe160400adc 100644
--- a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.txt
@@ -5,8 +5,6 @@ Required properties:
 - reg: Address range of the DMAC registers. This should include
   all of the per-channel registers.
 - interrupt: Should contain the DMAC interrupt number.
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device.
 - dma-channels: Number of channels supported by hardware.
 - snps,dma-masters: Number of AXI masters supported by the hardware.
 - snps,data-width: Maximum AXI data width supported by hardware.
diff --git a/Documentation/devicetree/bindings/dma/snps-dma.txt b/Documentation/devicetree/bindings/dma/snps-dma.txt
index 99acc712f83a..39e2b26be344 100644
--- a/Documentation/devicetree/bindings/dma/snps-dma.txt
+++ b/Documentation/devicetree/bindings/dma/snps-dma.txt
@@ -23,8 +23,6 @@ Deprecated properties:
 
 
 Optional properties:
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - is_private: The device channels should be marked as private and not for by the
   general purpose DMA channel allocator. False if not passed.
 - multi-block: Multi block transfers supported by hardware. Array property with
diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt
index 3f15f6644527..4bbc94d829c8 100644
--- a/Documentation/devicetree/bindings/dma/ti-edma.txt
+++ b/Documentation/devicetree/bindings/dma/ti-edma.txt
@@ -201,7 +201,6 @@ Required properties:
 - #dma-cells: Should be set to <1>
               Clients should use a single channel number per DMA request.
 - reg: Memory map for accessing module
-- interrupt-parent: Interrupt controller the interrupt is routed through
 - interrupts: Exactly 3 interrupts need to be specified in the order:
               1. Transfer completion interrupt.
               2. Memory protection interrupt.
diff --git a/Documentation/devicetree/bindings/dma/xilinx/zynqmp_dma.txt b/Documentation/devicetree/bindings/dma/xilinx/zynqmp_dma.txt
index a784cdd94790..07a5a7aa9ea0 100644
--- a/Documentation/devicetree/bindings/dma/xilinx/zynqmp_dma.txt
+++ b/Documentation/devicetree/bindings/dma/xilinx/zynqmp_dma.txt
@@ -5,7 +5,6 @@ control and rate control support for slave/peripheral dma access.
 Required properties:
 - compatible		: Should be "xlnx,zynqmp-dma-1.0"
 - reg			: Memory map for gdma/adma module access.
-- interrupt-parent	: Interrupt controller the interrupt is routed through
 - interrupts		: Should contain DMA channel interrupt.
 - xlnx,bus-width	: Axi buswidth in bits. Should contain 128 or 64
 - clock-names		: List of input clocks "clk_main", "clk_apb"
diff --git a/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt b/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt
index 6dede7d11532..cfcf455ad4de 100644
--- a/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt
+++ b/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt
@@ -11,8 +11,6 @@ for USB D-/D+ switching.
 Required properties:
 - compatible: Should be "richtek,rt8973a-muic"
 - reg: Specifies the I2C slave address of the MUIC block. It should be 0x14
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from rt8973a are delivered to.
 - interrupts: Interrupt specifiers for detection interrupt sources.
 
 Example:
diff --git a/Documentation/devicetree/bindings/extcon/extcon-sm5502.txt b/Documentation/devicetree/bindings/extcon/extcon-sm5502.txt
index 4ecda224955f..fc3888e09549 100644
--- a/Documentation/devicetree/bindings/extcon/extcon-sm5502.txt
+++ b/Documentation/devicetree/bindings/extcon/extcon-sm5502.txt
@@ -9,8 +9,6 @@ the host controller using an I2C interface.
 Required properties:
 - compatible: Should be "siliconmitus,sm5502-muic"
 - reg: Specifies the I2C slave address of the MUIC block. It should be 0x25
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from sm5502 are delivered to.
 - interrupts: Interrupt specifiers for detection interrupt sources.
 
 Example:
diff --git a/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt b/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt
index 798cfc9d3839..973362eb3f1e 100644
--- a/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt
@@ -25,8 +25,6 @@ Required properties:
 - #gpio-cells:		Should be two. The first cell is the pin number
 			and the second cell is used to specify optional
 			parameters (currently unused).
-- interrupt-parent:	Phandle for the interrupt controller that
-			services interrupts for this device.
 - interrupts:		Interrupt mapping for GPIO IRQ.
 - gpio-controller:	Marks the port as GPIO controller.
 
diff --git a/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt b/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt
index a25c87b650e5..ce19c5660aca 100644
--- a/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt
@@ -14,7 +14,6 @@ Optional Properties:
 - #interrupt-cells: Should be <1>. Interrupts are triggered on both edges.
 - interrupts: Defines the interrupt line connecting this GPIO controller to
   its parent interrupt controller.
-- interrupt-parent: Defines the parent interrupt controller.
 
 GPIO ranges are specified as described in
 Documentation/devicetree/bindings/gpio/gpio.txt
diff --git a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
index b405b4410bfb..5d468ecd1809 100644
--- a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
@@ -30,9 +30,6 @@ Optional properties:
 - interrupts:
     The interrupt shared by all GPIO lines for this controller.
 
-- interrupt-parent:
-    phandle of the parent interrupt controller
-
 - interrupts-extended:
     Alternate form of specifying interrupts and parents that allows for
     multiple parents.  This takes precedence over 'interrupts' and
diff --git a/Documentation/devicetree/bindings/gpio/gpio-adnp.txt b/Documentation/devicetree/bindings/gpio/gpio-adnp.txt
index af66b2724837..a28902a65a62 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-adnp.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-adnp.txt
@@ -3,7 +3,6 @@ Avionic Design N-bit GPIO expander bindings
 Required properties:
 - compatible: should be "ad,gpio-adnp"
 - reg: The I2C slave address for this device.
-- interrupt-parent: phandle of the parent interrupt controller.
 - interrupts: Interrupt specifier for the controllers interrupt.
 - #gpio-cells: Should be 2. The first cell is the GPIO number and the
   second cell is used to specify optional parameters:
diff --git a/Documentation/devicetree/bindings/gpio/gpio-aspeed.txt b/Documentation/devicetree/bindings/gpio/gpio-aspeed.txt
index fc6378c778c5..7e9b586770b0 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-aspeed.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-aspeed.txt
@@ -17,7 +17,6 @@ Required properties:
 
 Optional properties:
 
-- interrupt-parent      : The parent interrupt controller, optional if inherited
 - clocks                : A phandle to the clock to use for debounce timings
 
 The gpio and interrupt properties are further described in their respective
diff --git a/Documentation/devicetree/bindings/gpio/gpio-ath79.txt b/Documentation/devicetree/bindings/gpio/gpio-ath79.txt
index c522851017ae..cf71f3ec969d 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-ath79.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-ath79.txt
@@ -12,7 +12,6 @@ Required properties:
 - ngpios: Should be set to the number of GPIOs available on the SoC.
 
 Optional properties:
-- interrupt-parent: phandle of the parent interrupt controller.
 - interrupts: Interrupt specifier for the controllers interrupt.
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode interrupt
diff --git a/Documentation/devicetree/bindings/gpio/gpio-davinci.txt b/Documentation/devicetree/bindings/gpio/gpio-davinci.txt
index 8beb0539b6d8..553b92a7e87b 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-davinci.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-davinci.txt
@@ -15,8 +15,6 @@ Required Properties:
   - first cell is the pin number
   - second cell is used to specify optional parameters (unused)
 
-- interrupt-parent: phandle of the parent interrupt controller.
-
 - interrupts: Array of GPIO interrupt number. Only banked or unbanked IRQs are
 	      supported at a time.
 
diff --git a/Documentation/devicetree/bindings/gpio/gpio-max732x.txt b/Documentation/devicetree/bindings/gpio/gpio-max732x.txt
index 5fdc843b4542..b3a9c0c32823 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-max732x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-max732x.txt
@@ -30,7 +30,6 @@ Optional properties:
   - #interrupt-cells: Number of cells to encode an interrupt source, shall be 2.
     - first cell is the pin number
     - second cell is used to specify flags
-  - interrupt-parent: phandle of the parent interrupt controller.
   - interrupts: Interrupt specifier for the controllers interrupt.
 
 Please refer to gpio.txt in this directory for details of the common GPIO
diff --git a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
index 88f228665507..4e3c550e319a 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
@@ -37,6 +37,7 @@ Required properties:
  - #interrupt-cells: if to be used as interrupt expander.
 
 Optional properties:
+ - interrupts: interrupt specifier for the device's interrupt output.
  - reset-gpios: GPIO specification for the RESET input. This is an
 		active low signal to the PCA953x.
  - vcc-supply:	power supply regulator.
@@ -49,6 +50,8 @@ Example:
 		reg = <0x20>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_pca9505>;
+		gpio-controller;
+		#gpio-cells = <2>;
 		interrupt-parent = <&gpio3>;
 		interrupts = <23 IRQ_TYPE_LEVEL_LOW>;
 	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-pcf857x.txt b/Documentation/devicetree/bindings/gpio/gpio-pcf857x.txt
index 7d3bd631d011..a482455a205b 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-pcf857x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-pcf857x.txt
@@ -49,7 +49,6 @@ Optional Properties:
 
   - interrupt-controller: Identifies the node as an interrupt controller.
   - #interrupt-cells: Number of cells to encode an interrupt source, shall be 2.
-  - interrupt-parent: phandle of the parent interrupt controller.
   - interrupts: Interrupt specifier for the controllers interrupt.
 
 
diff --git a/Documentation/devicetree/bindings/gpio/gpio-uniphier.txt b/Documentation/devicetree/bindings/gpio/gpio-uniphier.txt
index fed9158dd913..f281f12dac18 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-uniphier.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-uniphier.txt
@@ -6,7 +6,6 @@ Required properties:
 - gpio-controller: Marks the device node as a GPIO controller.
 - #gpio-cells: Should be 2.  The first cell is the pin number and the second
   cell is used to specify optional parameters.
-- interrupt-parent: Specifies the parent interrupt controller.
 - interrupt-controller: Marks the device node as an interrupt controller.
 - #interrupt-cells: Should be 2.  The first cell defines the interrupt number.
   The second cell bits[3:0] is used to specify trigger type as follows:
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xgene-sb.txt b/Documentation/devicetree/bindings/gpio/gpio-xgene-sb.txt
index 5490c1d68981..e90fb987e25f 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-xgene-sb.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-xgene-sb.txt
@@ -26,7 +26,6 @@ Required properties:
 		1 = active low
 - gpio-controller: Marks the device node as a GPIO controller.
 - interrupts: The EXT_INT_0 parent interrupt resource must be listed first.
-- interrupt-parent: Phandle of the parent interrupt controller.
 - interrupt-cells: Should be two.
        - first cell is 0-N coresponding for EXT_INT_0 to EXT_INT_N.
        - second cell is used to specify flags.
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xilinx.txt b/Documentation/devicetree/bindings/gpio/gpio-xilinx.txt
index 63bf4becd5f0..08eed2335db0 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-xilinx.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-xilinx.txt
@@ -14,8 +14,6 @@ Required properties:
 
 Optional properties:
 - interrupts : Interrupt mapping for GPIO IRQ.
-- interrupt-parent : Phandle for the interrupt controller that
-  services interrupts for this device.
 - xlnx,all-inputs : if n-th bit is setup, GPIO-n is input
 - xlnx,dout-default : if n-th bit is 1, GPIO-n default value is 1
 - xlnx,gpio-width : gpio width
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xlp.txt b/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
index 28662d83a43e..47fc64922fe0 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
@@ -30,7 +30,6 @@ Required properties:
 	4 = active high level-sensitive.
 	8 = active low level-sensitive.
 - interrupts: Interrupt number for this device.
-- interrupt-parent: phandle of the parent interrupt controller.
 - interrupt-controller: Identifies the node as an interrupt controller.
 
 Example:
diff --git a/Documentation/devicetree/bindings/gpio/gpio-zynq.txt b/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
index 7b542657f259..4fa4eb5507cd 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
@@ -11,7 +11,6 @@ Required properties:
 - gpio-controller	: Marks the device node as a GPIO controller.
 - interrupts		: Interrupt specifier (see interrupt bindings for
 			  details)
-- interrupt-parent	: Must be core interrupt controller
 - interrupt-controller	: Marks the device node as an interrupt controller.
 - #interrupt-cells 	: Should be 2.  The first cell is the GPIO number.
 			  The second cell bits[3:0] is used to specify trigger type and level flags:
diff --git a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt
index 20fc72d9e61e..df63da46309c 100644
--- a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt
@@ -1,7 +1,7 @@
 Nintendo Wii (Hollywood) GPIO controller
 
 Required properties:
-- compatible: "nintendo,hollywood-gpio
+- compatible: "nintendo,hollywood-gpio"
 - reg: Physical base address and length of the controller's registers.
 - gpio-controller: Marks the device node as a GPIO controller.
 - #gpio-cells: Should be <2>. The first cell is the pin number and the
@@ -14,7 +14,6 @@ Optional properties:
 - #interrupt-cells: Should be two.
 - interrupts: Interrupt specifier for the controller's Broadway (PowerPC)
   interrupt.
-- interrupt-parent: phandle of the parent interrupt controller.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
index 378f1322211e..fe1bf24104d3 100644
--- a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
+++ b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
@@ -31,7 +31,6 @@ Required Properties:
   - reg: Base address and length of each memory resource used by the GPIO
     controller hardware module.
 
-  - interrupt-parent: phandle of the parent interrupt controller.
   - interrupts: Interrupt specifier for the controllers interrupt.
 
   - gpio-controller: Marks the device node as a gpio controller.
diff --git a/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt b/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
index 3c1118bc67f5..7276b50c3506 100644
--- a/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
@@ -25,7 +25,6 @@ controller.
   interrupt.  Shall be set to 2.  The first cell defines the interrupt number,
   the second encodes the triger flags encoded as described in
   Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
-- interrupt-parent : The parent interrupt controller.
 - interrupts : The interrupts to the parent controller raised when GPIOs
   generate the interrupts. If the controller provides one combined interrupt
   for all GPIOs, specify a single interrupt. If the controller provides one
diff --git a/Documentation/devicetree/bindings/hsi/omap-ssi.txt b/Documentation/devicetree/bindings/hsi/omap-ssi.txt
index 955e335e7e56..77a0c3c3036e 100644
--- a/Documentation/devicetree/bindings/hsi/omap-ssi.txt
+++ b/Documentation/devicetree/bindings/hsi/omap-ssi.txt
@@ -33,7 +33,6 @@ Required Port sub-node properties:
 - reg-names:		Contains the values "tx" and "rx" (in this order).
 - reg:			Contains a matching register specifier for each entry
 			in reg-names.
-- interrupt-parent	Should be a phandle for the interrupt controller
 - interrupts:		Should contain interrupt specifiers for mpu interrupts
 			0 and 1 (in this order).
 - ti,ssi-cawake-gpio:	Defines which GPIO pin is used to signify CAWAKE
diff --git a/Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt b/Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt
new file mode 100644
index 000000000000..28f43e929f6d
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt
@@ -0,0 +1,84 @@
+Nuvoton NPCM7xx PWM and Fan Tacho controller device
+
+The Nuvoton BMC NPCM7XX supports 8 Pulse-width modulation (PWM)
+controller outputs and 16 Fan tachometer controller inputs.
+
+Required properties for pwm-fan node
+- #address-cells : should be 1.
+- #size-cells	: should be 0.
+- compatible	: "nuvoton,npcm750-pwm-fan" for Poleg NPCM7XX.
+- reg			: specifies physical base address and size of the registers.
+- reg-names	: must contain:
+					* "pwm" for the PWM registers.
+					* "fan" for the Fan registers.
+- clocks		: phandle of reference clocks.
+- clock-names	: must contain
+					* "pwm" for PWM controller operating clock.
+					* "fan" for Fan controller operating clock.
+- interrupts	: contain the Fan interrupts with flags for falling edge.
+- pinctrl-names	: a pinctrl state named "default" must be defined.
+- pinctrl-0	: phandle referencing pin configuration of the PWM and Fan
+					controller ports.
+
+fan subnode format:
+===================
+Under fan subnode can be upto 8 child nodes, each child node representing a fan.
+Each fan subnode must have one PWM channel and atleast one Fan tach channel.
+
+For PWM channel can be configured cooling-levels to create cooling device.
+Cooling device could be bound to a thermal zone for the thermal control.
+
+Required properties for each child node:
+- reg : specify the PWM output channel.
+	integer value in the range 0 through 7, that represent
+	the PWM channel number that used.
+
+- fan-tach-ch : specify the Fan tach input channel.
+		integer value in the range 0 through 15, that represent
+		the fan tach channel number that used.
+
+		At least one Fan tach input channel is required
+
+Optional property for each child node:
+- cooling-levels: PWM duty cycle values in a range from 0 to 255
+                  which correspond to thermal cooling states.
+
+Examples:
+
+pwm_fan:pwm-fan-controller@103000 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "nuvoton,npcm750-pwm-fan";
+	reg = <0x103000 0x2000>,
+		<0x180000 0x8000>;
+	reg-names = "pwm", "fan";
+	clocks = <&clk NPCM7XX_CLK_APB3>,
+		<&clk NPCM7XX_CLK_APB4>;
+	clock-names = "pwm","fan";
+	interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pwm0_pins &pwm1_pins &pwm2_pins
+			&fanin0_pins &fanin1_pins &fanin2_pins
+			&fanin3_pins &fanin4_pins>;
+	fan@0 {
+		reg = <0x00>;
+		fan-tach-ch = /bits/ 8 <0x00 0x01>;
+		cooling-levels = <127 255>;
+	};
+	fan@1 {
+		reg = <0x01>;
+		fan-tach-ch = /bits/ 8 <0x02 0x03>;
+	};
+	fan@2 {
+		reg = <0x02>;
+		fan-tach-ch = /bits/ 8 <0x04>;
+	};
+
+};
diff --git a/Documentation/devicetree/bindings/i2c/i2c-aspeed.txt b/Documentation/devicetree/bindings/i2c/i2c-aspeed.txt
index e7106bfc1f13..8fbd8633a387 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-aspeed.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-aspeed.txt
@@ -11,9 +11,6 @@ Required Properties:
 - resets		: phandle to reset controller with the reset number in
 			  the second cell
 - interrupts		: interrupt number
-- interrupt-parent	: interrupt controller for bus, should reference a
-			  aspeed,ast2400-i2c-ic or aspeed,ast2500-i2c-ic
-			  interrupt controller
 
 Optional Properties:
 - bus-frequency	: frequency of the bus clock in Hz defaults to 100 kHz when not
diff --git a/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt b/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt
index aeceaceba3c5..0380609b177a 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt
@@ -10,8 +10,6 @@ Required properties:
 
 Optional properties :
 
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this one is cascaded from
 - interrupts: specifies the interrupt number, the irq line to be used
 - interrupt-names: Interrupt name string
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
index 60fe90d69f4e..00e4365d7206 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
@@ -5,7 +5,6 @@ Required properties:
   - "fsl,imx7ulp-lpi2c" for LPI2C compatible with the one integrated on i.MX7ULP soc
   - "fsl,imx8dv-lpi2c" for LPI2C compatible with the one integrated on i.MX8DV soc
 - reg : address and length of the lpi2c master registers
-- interrupt-parent : core interrupt controller
 - interrupts : lpi2c interrupt
 - clocks : lpi2c clock specifier
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt b/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt
index d4a082acf92f..3738cfbf863f 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt
@@ -11,10 +11,6 @@ Recommended properties:
 - pinctrl-names: should be "default";
 - pinctrl-0: phandle to pinctrl function
 
-Optional properties:
-- interrupt-parent: Should be the phandle of the interrupt controller that
-  delivers interrupts to the I2C block.
-
 Example
 
 / {
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mpc.txt b/Documentation/devicetree/bindings/i2c/i2c-mpc.txt
index 1eacd6b20ed5..42a390526957 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mpc.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mpc.txt
@@ -15,8 +15,6 @@ Recommended properties :
    information for the interrupt.  This should be encoded based on
    the information in section 2) depending on the type of interrupt
    controller you have.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
  - fsl,preserve-clocking : boolean; if defined, the clock settings
    from the bootloader are preserved (not touched).
  - clock-frequency : desired I2C bus clock frequency in Hz.
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt
index 34d91501342e..ccf6c86ed076 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt
@@ -28,8 +28,6 @@ Optional Properties:
   - i2c-mux-idle-disconnect: Boolean; if defined, forces mux to disconnect all
     children in idle state. This is necessary for example, if there are several
     multiplexers on the bus and the devices behind them use same I2C addresses.
-  - interrupt-parent: Phandle for the interrupt controller that services
-    interrupts for this device.
   - interrupts: Interrupt mapping for IRQ.
   - interrupt-controller: Marks the device node as an interrupt controller.
   - #interrupt-cells : Should be two.
diff --git a/Documentation/devicetree/bindings/i2c/i2c-pca-platform.txt b/Documentation/devicetree/bindings/i2c/i2c-pca-platform.txt
index f1f3876bb8e8..73a693d66ef7 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-pca-platform.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-pca-platform.txt
@@ -12,8 +12,6 @@ Required properties :
 
 Optional properties
  - interrupts : the interrupt number
- - interrupt-parent : the phandle for the interrupt controller.
-   If an interrupt is not specified polling will be used.
  - reset-gpios : gpio specifier for gpio connected to RESET_N pin. As the line
    is active low, it should be marked GPIO_ACTIVE_LOW.
  - clock-frequency : I2C bus frequency.
diff --git a/Documentation/devicetree/bindings/i2c/i2c-pnx.txt b/Documentation/devicetree/bindings/i2c/i2c-pnx.txt
index fe98ada33ee4..2a59006cf79e 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-pnx.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-pnx.txt
@@ -7,8 +7,6 @@ Required properties:
  - interrupts: configure one interrupt line
  - #address-cells: always 1 (for i2c addresses)
  - #size-cells: always 0
- - interrupt-parent: the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Optional properties:
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-pxa.txt b/Documentation/devicetree/bindings/i2c/i2c-pxa.txt
index d30f0b11d853..c30783c0eca0 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-pxa.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-pxa.txt
@@ -12,9 +12,6 @@ Required properties :
 Recommended properties :
 
  - interrupts : the interrupt number
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device. If the parent is the default
-   interrupt controller in device tree, it could be ignored.
  - mrvl,i2c-polling : Disable interrupt of i2c controller. Polling
    status register of i2c controller instead.
  - mrvl,i2c-fast-mode : Enable fast mode of i2c controller.
diff --git a/Documentation/devicetree/bindings/iio/accel/adxl345.txt b/Documentation/devicetree/bindings/iio/accel/adxl345.txt
index e7111b02c02c..ae09a046bc72 100644
--- a/Documentation/devicetree/bindings/iio/accel/adxl345.txt
+++ b/Documentation/devicetree/bindings/iio/accel/adxl345.txt
@@ -11,8 +11,6 @@ Required properties for SPI bus usage:
  - spi-cpol and spi-cpha : must be defined for adxl345 to enable SPI mode 3
 
 Optional properties:
- - interrupt-parent : phandle to the parent interrupt controller as documented
-   in Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
  - interrupts: interrupt mapping for IRQ as documented in
    Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
diff --git a/Documentation/devicetree/bindings/iio/accel/bma180.txt b/Documentation/devicetree/bindings/iio/accel/bma180.txt
index 4a3679d54457..3b25b4c4d446 100644
--- a/Documentation/devicetree/bindings/iio/accel/bma180.txt
+++ b/Documentation/devicetree/bindings/iio/accel/bma180.txt
@@ -10,8 +10,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent : should be the phandle for the interrupt controller
-
   - interrupts : interrupt mapping for GPIO IRQ, it should by configured with
 		flags IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_EDGE_RISING
 		For the bma250 the first interrupt listed must be the one
diff --git a/Documentation/devicetree/bindings/iio/accel/mma8452.txt b/Documentation/devicetree/bindings/iio/accel/mma8452.txt
index 45f5c5c5929c..2100e9af379c 100644
--- a/Documentation/devicetree/bindings/iio/accel/mma8452.txt
+++ b/Documentation/devicetree/bindings/iio/accel/mma8452.txt
@@ -15,8 +15,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent: should be the phandle for the interrupt controller
-
   - interrupts: interrupt mapping for GPIO IRQ
 
   - interrupt-names: should contain "INT1" and/or "INT2", the accelerometer's
diff --git a/Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt b/Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt
index 487ea966858e..ec04008e8f4f 100644
--- a/Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt
@@ -2,7 +2,6 @@ Motorola CPCAP PMIC ADC binding
 
 Required properties:
 - compatible: Should be "motorola,cpcap-adc" or "motorola,mapphone-cpcap-adc"
-- interrupt-parent: The interrupt controller
 - interrupts: The interrupt number for the ADC device
 - interrupt-names: Should be "adcdone"
 - #io-channel-cells: Number of cells in an IIO specifier
diff --git a/Documentation/devicetree/bindings/iio/adc/fsl,imx25-gcq.txt b/Documentation/devicetree/bindings/iio/adc/fsl,imx25-gcq.txt
index b0866d36a307..eebdcec3dab5 100644
--- a/Documentation/devicetree/bindings/iio/adc/fsl,imx25-gcq.txt
+++ b/Documentation/devicetree/bindings/iio/adc/fsl,imx25-gcq.txt
@@ -8,7 +8,6 @@ Required properties:
  - reg: Should be the register range of the module.
  - interrupts: Should be the interrupt number of the module.
    Typically this is <1>.
- - interrupt-parent: phandle to the tsadc module of the i.MX25.
  - #address-cells: Should be <1> (setting for the subnodes)
  - #size-cells: Should be <0> (setting for the subnodes)
 
diff --git a/Documentation/devicetree/bindings/iio/adc/max1027-adc.txt b/Documentation/devicetree/bindings/iio/adc/max1027-adc.txt
index a8770cc6bcad..e680c61dfb84 100644
--- a/Documentation/devicetree/bindings/iio/adc/max1027-adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/max1027-adc.txt
@@ -3,8 +3,6 @@
 Required properties:
   - compatible: Should be "maxim,max1027" or "maxim,max1029" or "maxim,max1031"
   - reg: SPI chip select number for the device
-  - interrupt-parent: phandle to the parent interrupt controller
-  see: Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
   - interrupts: IRQ line for the ADC
   see: Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt
index f1ead43a1a95..8346bcb04ad7 100644
--- a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt
@@ -60,7 +60,6 @@ Required properties:
 - reg: Offset of ADC instance in ADC block (e.g. may be 0x0, 0x100, 0x200).
 - clocks: Input clock private to this ADC instance. It's required only on
   stm32f4, that has per instance clock input for registers access.
-- interrupt-parent: Phandle to the parent interrupt controller.
 - interrupts: IRQ Line for the ADC (e.g. may be 0 for adc@0, 1 for adc@100 or
   2 for adc@200).
 - st,adc-channels: List of single-ended channels muxed for this ADC.
diff --git a/Documentation/devicetree/bindings/iio/adc/xilinx-xadc.txt b/Documentation/devicetree/bindings/iio/adc/xilinx-xadc.txt
index d71258e2d456..e0e0755cabd8 100644
--- a/Documentation/devicetree/bindings/iio/adc/xilinx-xadc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/xilinx-xadc.txt
@@ -22,7 +22,6 @@ Required properties:
 	  clock to the AXI bus interface of the core.
 
 Optional properties:
-	- interrupt-parent: phandle to the parent interrupt controller
 	- xlnx,external-mux:
 		* "none": No external multiplexer is used, this is the default
 		  if the property is omitted.
diff --git a/Documentation/devicetree/bindings/iio/chemical/atlas,ec-sm.txt b/Documentation/devicetree/bindings/iio/chemical/atlas,ec-sm.txt
index 2962bd9a2b3d..f4320595b851 100644
--- a/Documentation/devicetree/bindings/iio/chemical/atlas,ec-sm.txt
+++ b/Documentation/devicetree/bindings/iio/chemical/atlas,ec-sm.txt
@@ -6,7 +6,6 @@ Required properties:
 
   - compatible: must be "atlas,ec-sm"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/chemical/atlas,orp-sm.txt b/Documentation/devicetree/bindings/iio/chemical/atlas,orp-sm.txt
index 5d8b687d5edc..af1f5a9aa4da 100644
--- a/Documentation/devicetree/bindings/iio/chemical/atlas,orp-sm.txt
+++ b/Documentation/devicetree/bindings/iio/chemical/atlas,orp-sm.txt
@@ -6,7 +6,6 @@ Required properties:
 
   - compatible: must be "atlas,orp-sm"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/chemical/atlas,ph-sm.txt b/Documentation/devicetree/bindings/iio/chemical/atlas,ph-sm.txt
index cffa1907463a..79d90f060327 100644
--- a/Documentation/devicetree/bindings/iio/chemical/atlas,ph-sm.txt
+++ b/Documentation/devicetree/bindings/iio/chemical/atlas,ph-sm.txt
@@ -6,7 +6,6 @@ Required properties:
 
   - compatible: must be "atlas,ph-sm"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt b/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt
index b0d3b59966bc..233fe207aded 100644
--- a/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt
+++ b/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt
@@ -5,7 +5,6 @@ Required properties:
   - reg : the I2C address of the sensor
 
 Optional properties:
-  - interrupt-parent : should be the phandle for the interrupt controller
   - interrupts : interrupt mapping for the trigger interrupt from the
     internal oscillator. The following IRQ modes are supported:
     IRQ_TYPE_EDGE_RISING, IRQ_TYPE_EDGE_FALLING, IRQ_TYPE_LEVEL_HIGH and
diff --git a/Documentation/devicetree/bindings/iio/health/afe4403.txt b/Documentation/devicetree/bindings/iio/health/afe4403.txt
index 2fffd70336ba..8e412054d6d5 100644
--- a/Documentation/devicetree/bindings/iio/health/afe4403.txt
+++ b/Documentation/devicetree/bindings/iio/health/afe4403.txt
@@ -4,7 +4,6 @@ Required properties:
  - compatible		: Should be "ti,afe4403".
  - reg			: SPI chip select address of device.
  - tx-supply		: Regulator supply to transmitting LEDs.
- - interrupt-parent	: Phandle to he parent interrupt controller.
  - interrupts		: The interrupt line the device ADC_RDY pin is
 			  connected to. For details refer to,
 			  ../../interrupt-controller/interrupts.txt.
diff --git a/Documentation/devicetree/bindings/iio/health/afe4404.txt b/Documentation/devicetree/bindings/iio/health/afe4404.txt
index de69f203edfa..0b52830a0d9c 100644
--- a/Documentation/devicetree/bindings/iio/health/afe4404.txt
+++ b/Documentation/devicetree/bindings/iio/health/afe4404.txt
@@ -4,7 +4,6 @@ Required properties:
  - compatible		: Should be "ti,afe4404".
  - reg			: I2C address of the device.
  - tx-supply		: Regulator supply to transmitting LEDs.
- - interrupt-parent	: Phandle to he parent interrupt controller.
  - interrupts		: The interrupt line the device ADC_RDY pin is
 			  connected to. For details refer to,
 			  ../interrupt-controller/interrupts.txt.
diff --git a/Documentation/devicetree/bindings/iio/health/max30100.txt b/Documentation/devicetree/bindings/iio/health/max30100.txt
index 8d8176459d09..0054908a6e74 100644
--- a/Documentation/devicetree/bindings/iio/health/max30100.txt
+++ b/Documentation/devicetree/bindings/iio/health/max30100.txt
@@ -5,7 +5,6 @@ Maxim MAX30100 heart rate and pulse oximeter sensor
 Required properties:
   - compatible: must be "maxim,max30100"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic
diff --git a/Documentation/devicetree/bindings/iio/health/max30102.txt b/Documentation/devicetree/bindings/iio/health/max30102.txt
index ef2ca0a0306f..7ef7ae40ae4f 100644
--- a/Documentation/devicetree/bindings/iio/health/max30102.txt
+++ b/Documentation/devicetree/bindings/iio/health/max30102.txt
@@ -7,7 +7,6 @@ Maxim MAX30105 optical particle-sensing module
 Required properties:
   - compatible: must be "maxim,max30102" or "maxim,max30105"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic
diff --git a/Documentation/devicetree/bindings/iio/humidity/hts221.txt b/Documentation/devicetree/bindings/iio/humidity/hts221.txt
index 10adeb0d703d..84d029372260 100644
--- a/Documentation/devicetree/bindings/iio/humidity/hts221.txt
+++ b/Documentation/devicetree/bindings/iio/humidity/hts221.txt
@@ -13,7 +13,6 @@ Optional properties:
   when it is not active, whereas a pull-up one is needed when interrupt
   line is configured as IRQ_TYPE_LEVEL_LOW or IRQ_TYPE_EDGE_FALLING.
   Refer to pinctrl/pinctrl-bindings.txt for the property description.
-- interrupt-parent: should be the phandle for the interrupt controller
 - interrupts: interrupt mapping for IRQ. It should be configured with
   flags IRQ_TYPE_LEVEL_HIGH, IRQ_TYPE_EDGE_RISING, IRQ_TYPE_LEVEL_LOW or
   IRQ_TYPE_EDGE_FALLING.
diff --git a/Documentation/devicetree/bindings/iio/imu/bmi160.txt b/Documentation/devicetree/bindings/iio/imu/bmi160.txt
index ae0112c7debc..0c1c105fb503 100644
--- a/Documentation/devicetree/bindings/iio/imu/bmi160.txt
+++ b/Documentation/devicetree/bindings/iio/imu/bmi160.txt
@@ -9,7 +9,6 @@ Required properties:
  - spi-max-frequency : set maximum clock frequency (only for SPI)
 
 Optional properties:
- - interrupt-parent : should be the phandle of the interrupt controller
  - interrupts : interrupt mapping for IRQ, must be IRQ_TYPE_LEVEL_LOW
  - interrupt-names : set to "INT1" if INT1 pin should be used as interrupt
    input, set to "INT2" if INT2 pin should be used instead
diff --git a/Documentation/devicetree/bindings/iio/imu/inv_mpu6050.txt b/Documentation/devicetree/bindings/iio/imu/inv_mpu6050.txt
index 5f4777e8cc9e..d33c19d68de3 100644
--- a/Documentation/devicetree/bindings/iio/imu/inv_mpu6050.txt
+++ b/Documentation/devicetree/bindings/iio/imu/inv_mpu6050.txt
@@ -11,7 +11,6 @@ Required properties:
 		"invensense,mpu9255"
 		"invensense,icm20608"
  - reg : the I2C address of the sensor
- - interrupt-parent : should be the phandle for the interrupt controller
  - interrupts: interrupt mapping for IRQ. It should be configured with flags
    IRQ_TYPE_LEVEL_HIGH, IRQ_TYPE_EDGE_RISING, IRQ_TYPE_LEVEL_LOW or
    IRQ_TYPE_EDGE_FALLING.
diff --git a/Documentation/devicetree/bindings/iio/imu/st_lsm6dsx.txt b/Documentation/devicetree/bindings/iio/imu/st_lsm6dsx.txt
index ef8a8566c63f..ea2d6e0ae4c5 100644
--- a/Documentation/devicetree/bindings/iio/imu/st_lsm6dsx.txt
+++ b/Documentation/devicetree/bindings/iio/imu/st_lsm6dsx.txt
@@ -20,7 +20,6 @@ Optional properties:
   IRQ_TYPE_EDGE_RISING a pull-down resistor is needed to drive the line
   when it is not active, whereas a pull-up one is needed when interrupt
   line is configured as IRQ_TYPE_LEVEL_LOW or IRQ_TYPE_EDGE_FALLING.
-- interrupt-parent: should be the phandle for the interrupt controller
 - interrupts: interrupt mapping for IRQ. It should be configured with
   flags IRQ_TYPE_LEVEL_HIGH, IRQ_TYPE_EDGE_RISING, IRQ_TYPE_LEVEL_LOW or
   IRQ_TYPE_EDGE_FALLING.
diff --git a/Documentation/devicetree/bindings/iio/light/apds9300.txt b/Documentation/devicetree/bindings/iio/light/apds9300.txt
index d6f66c73ddbf..aa199e09a493 100644
--- a/Documentation/devicetree/bindings/iio/light/apds9300.txt
+++ b/Documentation/devicetree/bindings/iio/light/apds9300.txt
@@ -9,7 +9,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent : should be the phandle for the interrupt controller
   - interrupts : interrupt mapping for GPIO IRQ
 
 Example:
diff --git a/Documentation/devicetree/bindings/iio/light/apds9960.txt b/Documentation/devicetree/bindings/iio/light/apds9960.txt
index 174b709f16db..3af325ad194b 100644
--- a/Documentation/devicetree/bindings/iio/light/apds9960.txt
+++ b/Documentation/devicetree/bindings/iio/light/apds9960.txt
@@ -6,7 +6,6 @@ Required properties:
 
   - compatible: must be "avago,apds9960"
   - reg: the I2c address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts : the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/light/isl29018.txt b/Documentation/devicetree/bindings/iio/light/isl29018.txt
index 425ab459e209..b9bbde3e13ed 100644
--- a/Documentation/devicetree/bindings/iio/light/isl29018.txt
+++ b/Documentation/devicetree/bindings/iio/light/isl29018.txt
@@ -10,7 +10,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/light/opt3001.txt b/Documentation/devicetree/bindings/iio/light/opt3001.txt
index eac30d508849..47b13eb8f4ec 100644
--- a/Documentation/devicetree/bindings/iio/light/opt3001.txt
+++ b/Documentation/devicetree/bindings/iio/light/opt3001.txt
@@ -13,7 +13,6 @@ Required properties:
   - reg: the I2C address of the sensor
 
 Optional properties:
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: interrupt mapping for GPIO IRQ (configure for falling edge)
 
 Example:
diff --git a/Documentation/devicetree/bindings/iio/light/tsl2583.txt b/Documentation/devicetree/bindings/iio/light/tsl2583.txt
index 8e2066c83f70..059dffa1829a 100644
--- a/Documentation/devicetree/bindings/iio/light/tsl2583.txt
+++ b/Documentation/devicetree/bindings/iio/light/tsl2583.txt
@@ -10,7 +10,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/light/uvis25.txt b/Documentation/devicetree/bindings/iio/light/uvis25.txt
index 3041207e3f3c..043c139d91e6 100644
--- a/Documentation/devicetree/bindings/iio/light/uvis25.txt
+++ b/Documentation/devicetree/bindings/iio/light/uvis25.txt
@@ -5,7 +5,6 @@ Required properties:
 - reg: i2c address of the sensor / spi cs line
 
 Optional properties:
-- interrupt-parent: should be the phandle for the interrupt controller
 - interrupts: interrupt mapping for IRQ. It should be configured with
   flags IRQ_TYPE_LEVEL_HIGH, IRQ_TYPE_EDGE_RISING, IRQ_TYPE_LEVEL_LOW or
   IRQ_TYPE_EDGE_FALLING.
diff --git a/Documentation/devicetree/bindings/iio/magnetometer/bmc150_magn.txt b/Documentation/devicetree/bindings/iio/magnetometer/bmc150_magn.txt
index 9f263b7df162..fd5fca90fb39 100644
--- a/Documentation/devicetree/bindings/iio/magnetometer/bmc150_magn.txt
+++ b/Documentation/devicetree/bindings/iio/magnetometer/bmc150_magn.txt
@@ -9,7 +9,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent : phandle to the parent interrupt controller
   - interrupts : interrupt mapping for GPIO IRQ
 
 Example:
diff --git a/Documentation/devicetree/bindings/iio/pressure/bmp085.txt b/Documentation/devicetree/bindings/iio/pressure/bmp085.txt
index c7198a03c906..5498b0688b6f 100644
--- a/Documentation/devicetree/bindings/iio/pressure/bmp085.txt
+++ b/Documentation/devicetree/bindings/iio/pressure/bmp085.txt
@@ -12,7 +12,6 @@ Optional properties:
 - temp-measurement-period: temperature measurement period (milliseconds)
 - default-oversampling: default oversampling value to be used at startup,
   value range is 0-3 with rising sensitivity.
-- interrupt-parent: should be the phandle for the interrupt controller
 - interrupts: interrupt mapping for IRQ
 - reset-gpios: a GPIO line handling reset of the sensor: as the line is
   active low, it should be marked GPIO_ACTIVE_LOW (see gpio/gpio.txt)
diff --git a/Documentation/devicetree/bindings/iio/pressure/zpa2326.txt b/Documentation/devicetree/bindings/iio/pressure/zpa2326.txt
index fb85de676e03..a36ab3e0c3f7 100644
--- a/Documentation/devicetree/bindings/iio/pressure/zpa2326.txt
+++ b/Documentation/devicetree/bindings/iio/pressure/zpa2326.txt
@@ -15,8 +15,6 @@ Optional properties:
   power to the sensor
 - vdd-supply: an optional regulator that needs to be on to provide VDD
   power to the sensor
-- interrupt-parent: phandle to the parent interrupt controller as documented in
-  Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 - interrupts: interrupt mapping for IRQ as documented in
   Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
diff --git a/Documentation/devicetree/bindings/iio/proximity/as3935.txt b/Documentation/devicetree/bindings/iio/proximity/as3935.txt
index b6c1afa6f02d..849115585d55 100644
--- a/Documentation/devicetree/bindings/iio/proximity/as3935.txt
+++ b/Documentation/devicetree/bindings/iio/proximity/as3935.txt
@@ -6,7 +6,6 @@ Required properties:
 	- spi-max-frequency: specifies maximum SPI clock frequency
 	- spi-cpha: SPI Mode 1. Refer to spi/spi-bus.txt for generic SPI
 	slave node bindings.
-	- interrupt-parent : should be the phandle for the interrupt controller
 	- interrupts : the sole interrupt generated by the device
 
 	Refer to interrupt-controller/interrupts.txt for generic
diff --git a/Documentation/devicetree/bindings/iio/proximity/sx9500.txt b/Documentation/devicetree/bindings/iio/proximity/sx9500.txt
index b301dd2b35da..c54455db3bec 100644
--- a/Documentation/devicetree/bindings/iio/proximity/sx9500.txt
+++ b/Documentation/devicetree/bindings/iio/proximity/sx9500.txt
@@ -3,7 +3,6 @@ Semtech's SX9500 capacitive proximity button device driver
 Required properties:
 	- compatible: must be "semtech,sx9500"
 	- reg: i2c address where to find the device
-	- interrupt-parent : should be the phandle for the interrupt controller
 	- interrupts : the sole interrupt generated by the device
 
 	Refer to interrupt-controller/interrupts.txt for generic
diff --git a/Documentation/devicetree/bindings/iio/sensorhub.txt b/Documentation/devicetree/bindings/iio/sensorhub.txt
index 8d57571d5c0b..b6ac0457d4ea 100644
--- a/Documentation/devicetree/bindings/iio/sensorhub.txt
+++ b/Documentation/devicetree/bindings/iio/sensorhub.txt
@@ -6,7 +6,6 @@ of a virtual sensor device.
 Required properties:
 - compatible: "samsung,sensorhub-rinato" or "samsung,sensorhub-thermostat"
 - spi-max-frequency: max SPI clock frequency
-- interrupt-parent: interrupt parent
 - interrupts: communication interrupt
 - ap-mcu-gpios: [out] ap to sensorhub line - used during communication
 - mcu-ap-gpios: [in] sensorhub to ap - used during communication
diff --git a/Documentation/devicetree/bindings/iio/temperature/tmp007.txt b/Documentation/devicetree/bindings/iio/temperature/tmp007.txt
index b63aba91ef03..da0af234a357 100644
--- a/Documentation/devicetree/bindings/iio/temperature/tmp007.txt
+++ b/Documentation/devicetree/bindings/iio/temperature/tmp007.txt
@@ -20,8 +20,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent: should be the phandle for the interrupt controller
-
   - interrupts: interrupt mapping for GPIO IRQ (level active low)
 
 Example:
diff --git a/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt b/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
index d3b273e4336a..84f1a1b505d2 100644
--- a/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
+++ b/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
@@ -19,7 +19,6 @@ representing a dsaf device.
 - #size-cells: must be 2
 Optional properties:
 - dma-coherent: Present if DMA operations are coherent.
-- interrupt-parent: the interrupt parent of this device.
 - interrupts: should contain 32 completion event irq,1 async event irq
 and 1 event overflow irq.
 - interrupt-names:should be one of 34 irqs for roce device
diff --git a/Documentation/devicetree/bindings/input/cypress,cyapa.txt b/Documentation/devicetree/bindings/input/cypress,cyapa.txt
index 8d91ba9ff2fd..d3db65916a36 100644
--- a/Documentation/devicetree/bindings/input/cypress,cyapa.txt
+++ b/Documentation/devicetree/bindings/input/cypress,cyapa.txt
@@ -3,8 +3,6 @@ Cypress I2C Touchpad
 Required properties:
 - compatible: must be "cypress,cyapa".
 - reg: I2C address of the chip.
-- interrupt-parent: a phandle for the interrupt controller (see interrupt
-	binding[0]).
 - interrupts: interrupt to which the chip is connected (see interrupt
 	binding[0]).
 
diff --git a/Documentation/devicetree/bindings/input/cypress,tm2-touchkey.txt b/Documentation/devicetree/bindings/input/cypress,tm2-touchkey.txt
index 635f62c756ee..0c252d9306da 100644
--- a/Documentation/devicetree/bindings/input/cypress,tm2-touchkey.txt
+++ b/Documentation/devicetree/bindings/input/cypress,tm2-touchkey.txt
@@ -3,8 +3,6 @@ Samsung tm2-touchkey
 Required properties:
 - compatible: must be "cypress,tm2-touchkey"
 - reg: I2C address of the chip.
-- interrupt-parent: a phandle for the interrupt controller (see interrupt
-	binding[0]).
 - interrupts: interrupt to which the chip is connected (see interrupt
 	binding[0]).
 - vcc-supply : internal regulator output. 1.8V
diff --git a/Documentation/devicetree/bindings/input/e3x0-button.txt b/Documentation/devicetree/bindings/input/e3x0-button.txt
index 751665e8e47a..907b195f2eaa 100644
--- a/Documentation/devicetree/bindings/input/e3x0-button.txt
+++ b/Documentation/devicetree/bindings/input/e3x0-button.txt
@@ -7,8 +7,6 @@ This module provides a simple power button event via two interrupts.
 Required properties:
 - compatible: should be one of the following
   - "ettus,e3x0-button": For devices such as the NI Ettus Research USRP E3x0
-- interrupt-parent:
-  - a phandle to the interrupt controller that it is attached to.
 - interrupts: should be one of the following
   - <0 30 1>, <0 31 1>: For devices such as the NI Ettus Research USRP E3x0
 - interrupt-names: should be one of the following
diff --git a/Documentation/devicetree/bindings/input/elan_i2c.txt b/Documentation/devicetree/bindings/input/elan_i2c.txt
index d80a83583238..797607460735 100644
--- a/Documentation/devicetree/bindings/input/elan_i2c.txt
+++ b/Documentation/devicetree/bindings/input/elan_i2c.txt
@@ -3,8 +3,6 @@ Elantech I2C Touchpad
 Required properties:
 - compatible: must be "elan,ekth3000".
 - reg: I2C address of the chip.
-- interrupt-parent: a phandle for the interrupt controller (see interrupt
-  binding[0]).
 - interrupts: interrupt to which the chip is connected (see interrupt
   binding[0]).
 
diff --git a/Documentation/devicetree/bindings/input/elants_i2c.txt b/Documentation/devicetree/bindings/input/elants_i2c.txt
index 8a71038f3489..5edac8be0802 100644
--- a/Documentation/devicetree/bindings/input/elants_i2c.txt
+++ b/Documentation/devicetree/bindings/input/elants_i2c.txt
@@ -3,8 +3,6 @@ Elantech I2C Touchscreen
 Required properties:
 - compatible: must be "elan,ekth3500".
 - reg: I2C address of the chip.
-- interrupt-parent: a phandle for the interrupt controller (see interrupt
-  binding[0]).
 - interrupts: interrupt to which the chip is connected (see interrupt
   binding[0]).
 
diff --git a/Documentation/devicetree/bindings/input/hid-over-i2c.txt b/Documentation/devicetree/bindings/input/hid-over-i2c.txt
index 4d3da9d91de4..f1cb9f8d7692 100644
--- a/Documentation/devicetree/bindings/input/hid-over-i2c.txt
+++ b/Documentation/devicetree/bindings/input/hid-over-i2c.txt
@@ -14,7 +14,6 @@ Required properties:
 - compatible: must be "hid-over-i2c"
 - reg: i2c slave address
 - hid-descr-addr: HID descriptor address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: interrupt line
 
 Additional optional properties:
diff --git a/Documentation/devicetree/bindings/input/raydium_i2c_ts.txt b/Documentation/devicetree/bindings/input/raydium_i2c_ts.txt
index 5b6232db7c61..99a4f2ab5557 100644
--- a/Documentation/devicetree/bindings/input/raydium_i2c_ts.txt
+++ b/Documentation/devicetree/bindings/input/raydium_i2c_ts.txt
@@ -3,7 +3,6 @@ Raydium I2C touchscreen
 Required properties:
 - compatible: must be "raydium,rm32380"
 - reg: The I2C address of the device
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: interrupt to which the chip is connected
     See ../interrupt-controller/interrupts.txt
 Optional properties:
diff --git a/Documentation/devicetree/bindings/input/rmi4/rmi_i2c.txt b/Documentation/devicetree/bindings/input/rmi4/rmi_i2c.txt
index ec908b91fd90..dcb012f5b3ee 100644
--- a/Documentation/devicetree/bindings/input/rmi4/rmi_i2c.txt
+++ b/Documentation/devicetree/bindings/input/rmi4/rmi_i2c.txt
@@ -16,7 +16,6 @@ Required Properties:
 
 Optional Properties:
 - interrupts: interrupt which the rmi device is connected to.
-- interrupt-parent: The interrupt controller.
 See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
 - syna,reset-delay-ms: The number of milliseconds to wait after resetting the
diff --git a/Documentation/devicetree/bindings/input/rmi4/rmi_spi.txt b/Documentation/devicetree/bindings/input/rmi4/rmi_spi.txt
index a4ca7828f21d..632f473db65b 100644
--- a/Documentation/devicetree/bindings/input/rmi4/rmi_spi.txt
+++ b/Documentation/devicetree/bindings/input/rmi4/rmi_spi.txt
@@ -16,7 +16,6 @@ Required Properties:
 
 Optional Properties:
 - interrupts: interrupt which the rmi device is connected to.
-- interrupt-parent: The interrupt controller.
 See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
 - spi-rx-delay-us: microsecond delay after a read transfer.
diff --git a/Documentation/devicetree/bindings/input/sprd,sc27xx-vibra.txt b/Documentation/devicetree/bindings/input/sprd,sc27xx-vibra.txt
new file mode 100644
index 000000000000..f2ec0d4f2dff
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/sprd,sc27xx-vibra.txt
@@ -0,0 +1,23 @@
+Spreadtrum SC27xx PMIC Vibrator
+
+Required properties:
+- compatible: should be "sprd,sc2731-vibrator".
+- reg: address of vibrator control register.
+
+Example :
+
+	sc2731_pmic: pmic@0 {
+		compatible = "sprd,sc2731";
+		reg = <0>;
+		spi-max-frequency = <26000000>;
+		interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vibrator@eb4 {
+			compatible = "sprd,sc2731-vibrator";
+			reg = <0xeb4>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/input/ti,palmas-pwrbutton.txt b/Documentation/devicetree/bindings/input/ti,palmas-pwrbutton.txt
index a3dde8c30e67..c829e18e1a05 100644
--- a/Documentation/devicetree/bindings/input/ti,palmas-pwrbutton.txt
+++ b/Documentation/devicetree/bindings/input/ti,palmas-pwrbutton.txt
@@ -9,7 +9,6 @@ This module provides a simple power button event via an Interrupt.
 Required properties:
 - compatible: should be one of the following
    - "ti,palmas-pwrbutton": For Palmas compatible power on button
-- interrupt-parent: Parent interrupt device, must be handle of palmas node.
 - interrupts: Interrupt number of power button submodule on device.
 
 Optional Properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ad7879.txt b/Documentation/devicetree/bindings/input/touchscreen/ad7879.txt
index 3c8614c451f2..cdd743a1f2d5 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/ad7879.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/ad7879.txt
@@ -5,7 +5,6 @@ Required properties:
 				  for I2C slave, use "adi,ad7879-1"
 - reg				: SPI chipselect/I2C slave address
 				  See spi-bus.txt for more SPI slave properties
-- interrupt-parent		: the phandle for the interrupt controller
 - interrupts			: touch controller interrupt
 - touchscreen-max-pressure	: maximum reported pressure
 - adi,resistance-plate-x	: total resistance of X-plate (for pressure
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ads7846.txt b/Documentation/devicetree/bindings/input/touchscreen/ads7846.txt
index 9fc47b006fd1..04413da51391 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/ads7846.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/ads7846.txt
@@ -18,7 +18,6 @@ Additional required properties:
 					"ti,ads7846"
 					"ti,ads7873"
 
-	interrupt-parent
 	interrupts		An interrupt node describing the IRQ line the chip's
 				!PENIRQ pin is connected to.
 	vcc-supply		A regulator node for the supply voltage.
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ar1021.txt b/Documentation/devicetree/bindings/input/touchscreen/ar1021.txt
index e459e8546f34..82019bd6094e 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/ar1021.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/ar1021.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible		: "microchip,ar1021-i2c"
 - reg			: I2C slave address
-- interrupt-parent	: the phandle for the interrupt controller
 - interrupts		: touch controller interrupt
 
 Example:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt b/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt
index d11f8d615b5d..38b0603f65f3 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt
@@ -3,8 +3,6 @@
 Required properties:
  - compatible		  : "chipone,icn8318"
  - reg			  : I2C slave address of the chip (0x40)
- - interrupt-parent	  : a phandle pointing to the interrupt controller
-			    serving the interrupt for this chip
  - interrupts		  : interrupt specification for the icn8318 interrupt
  - wake-gpios		  : GPIO specification for the WAKE input
  - touchscreen-size-x	  : horizontal resolution of touchscreen (in pixels)
diff --git a/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt
index df531b5b6a0d..2e1490a8fe74 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt
@@ -7,7 +7,6 @@ Required Properties:
 - xm-gpios: FET gate driver for input of X-
 - yp-gpios: FET gate driver for input of Y+
 - ym-gpios: FET gate driver for input of Y-
-- interrupt-parent: phandle for the interrupt controller
 - interrupts: pen irq interrupt for touch detection
 - pinctrl-names: "idle", "default", "gpios"
 - pinctrl-0: pinctrl node for pen/touch detection state pinmux
diff --git a/Documentation/devicetree/bindings/input/touchscreen/cyttsp.txt b/Documentation/devicetree/bindings/input/touchscreen/cyttsp.txt
index b75d4cfd2c36..6ee274aa8b03 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/cyttsp.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/cyttsp.txt
@@ -4,8 +4,6 @@ Required properties:
  - compatible		: must be "cypress,cyttsp-i2c" or "cypress,cyttsp-spi"
  - reg			: Device I2C address or SPI chip select number
  - spi-max-frequency	: Maximum SPI clocking speed of the device (for cyttsp-spi)
- - interrupt-parent	: the phandle for the gpio controller
-			  (see interrupt binding[0]).
  - interrupts		: (gpio) interrupt to which the chip is connected
 			  (see interrupt binding[0]).
  - bootloader-key	: the 8-byte bootloader key that is required to switch
diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt
index 025cf8c9324a..da2dc5d6c98b 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt
@@ -22,8 +22,6 @@ Required properties:
            or:  "focaltech,ft6236"
 
  - reg:         I2C slave address of the chip (0x38)
- - interrupt-parent: a phandle pointing to the interrupt controller
-                     serving the interrupt for this chip
  - interrupts:       interrupt specification for the touchdetect
                      interrupt
 
diff --git a/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt
index 298e3442f143..92fb2620f5e2 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "eeti,egalax_ts"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: touch controller interrupt
 - wakeup-gpios: the gpio pin to be used for waking up the controller
   and also used as irq pin
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ektf2127.txt b/Documentation/devicetree/bindings/input/touchscreen/ektf2127.txt
index 5a19f4c3e9d7..94c4fc644940 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/ektf2127.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/ektf2127.txt
@@ -3,8 +3,6 @@
 Required properties:
  - compatible		  : "elan,ektf2127"
  - reg			  : I2C slave address of the chip (0x40)
- - interrupt-parent	  : a phandle pointing to the interrupt controller
-			    serving the interrupt for this chip
  - interrupts		  : interrupt specification for the ektf2127 interrupt
  - power-gpios		  : GPIO specification for the pin connected to the
 			    ektf2127's wake input. This needs to be driven high
diff --git a/Documentation/devicetree/bindings/input/touchscreen/exc3000.txt b/Documentation/devicetree/bindings/input/touchscreen/exc3000.txt
index 1dcff4a43eaa..68291b94fec2 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/exc3000.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/exc3000.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "eeti,exc3000"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: touch controller interrupt
 - touchscreen-size-x: See touchscreen.txt
 - touchscreen-size-y: See touchscreen.txt
diff --git a/Documentation/devicetree/bindings/input/touchscreen/fsl-mx25-tcq.txt b/Documentation/devicetree/bindings/input/touchscreen/fsl-mx25-tcq.txt
index abfcab3edc66..99d6f9d25335 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/fsl-mx25-tcq.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/fsl-mx25-tcq.txt
@@ -8,7 +8,6 @@ Required properties:
  - reg: Memory range of the device.
  - interrupts: Should be the interrupt number associated with this module within
    the tscadc unit (<0>).
- - interrupt-parent: Should be a phandle to the tscadc unit.
  - fsl,wires: Should be '<4>' or '<5>'
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/goodix.txt b/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
index 0c369d8ebcab..f7e95c52f3c7 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
@@ -11,7 +11,6 @@ Required properties:
 				 or "goodix,gt928"
 				 or "goodix,gt967"
  - reg			: I2C address of the chip. Should be 0x5d or 0x14
- - interrupt-parent	: Interrupt controller to which the chip is connected
  - interrupts		: Interrupt to which the chip is connected
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt
index 121d9b7c79a2..a47c36190b01 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible		: must be "hideep,hideep-ts"
 - reg			: I2C slave address, (e.g. 0x6C).
-- interrupt-parent : Interrupt controller to which the chip is connected.
 - interrupts : Interrupt to which the chip is connected.
 
 Optional properties:
@@ -32,7 +31,7 @@ i2c@00000000 {
 		reg = <0x6c>;
 		interrupt-parent = <&gpx1>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
-		vdd-supply = <&ldo15_reg>";
+		vdd-supply = <&ldo15_reg>;
 		vid-supply = <&ldo18_reg>;
 		reset-gpios = <&gpx1 5 0>;
 		touchscreen-size-x = <1080>;
diff --git a/Documentation/devicetree/bindings/input/touchscreen/max11801-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/max11801-ts.txt
index 40ac0fe94df6..05e982c3454e 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/max11801-ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/max11801-ts.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "maxim,max11801"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: touch controller interrupt
 
 Example:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt b/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
index 7b8944c2cb31..b2ab5498e519 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "melfas,mip4_ts"
 - reg: I2C slave address of the chip (0x48 or 0x34)
-- interrupt-parent: interrupt controller to which the chip is connected
 - interrupts: interrupt to which the chip is connected
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
index d9b7c2ff611e..6805d10d226d 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible		: must be "samsung,s6sy761"
 - reg			: I2C slave address, (e.g. 0x48)
-- interrupt-parent	: the phandle to the interrupt controller which provides
-			  the interrupt
 - interrupts		: interrupt specification
 - avdd-supply		: analogic power supply
 - vdd-supply		: power supply
diff --git a/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt b/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt
index 84752de12412..d67e558e5ab5 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt
@@ -8,8 +8,6 @@ Required properties:
 			    "silead,gsl3675"
 			    "silead,gsl3692"
 - reg			  : I2C slave address of the chip (0x40)
-- interrupt-parent	  : a phandle pointing to the interrupt controller
-			    serving the interrupt for this chip
 - interrupts		  : interrupt specification for the gsl1680 interrupt
 - power-gpios		  : Specification for the pin connected to the gsl1680's
 			    shutdown input. This needs to be driven high to take the
diff --git a/Documentation/devicetree/bindings/input/touchscreen/sis_i2c.txt b/Documentation/devicetree/bindings/input/touchscreen/sis_i2c.txt
index d87ad14f1efe..8f5322e01024 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/sis_i2c.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/sis_i2c.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: must be "sis,9200-ts"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
-  (see interrupt binding [0])
 - interrupts: touch controller interrupt (see interrupt
   binding [0])
 
diff --git a/Documentation/devicetree/bindings/input/touchscreen/st,stmfts.txt b/Documentation/devicetree/bindings/input/touchscreen/st,stmfts.txt
index 9683595cd0f5..0a5d0cb4a280 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/st,stmfts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/st,stmfts.txt
@@ -10,8 +10,6 @@ coordinates.
 Required properties:
 - compatible		: must be "st,stmfts"
 - reg			: I2C slave address, (e.g. 0x49)
-- interrupt-parent	: the phandle to the interrupt controller which provides
-			  the interrupt
 - interrupts		: interrupt specification
 - avdd-supply		: analogic power supply
 - vdd-supply		: power supply
diff --git a/Documentation/devicetree/bindings/input/touchscreen/sx8654.txt b/Documentation/devicetree/bindings/input/touchscreen/sx8654.txt
index 5aaa6b3aa90c..4886c4aa2906 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/sx8654.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/sx8654.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "semtech,sx8654"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: touch controller interrupt
 
 Example:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/tsc2007.txt b/Documentation/devicetree/bindings/input/touchscreen/tsc2007.txt
index ec365e172236..ed00f61b8c08 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/tsc2007.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/tsc2007.txt
@@ -9,8 +9,6 @@ Optional properties:
 - gpios: the interrupt gpio the chip is connected to (trough the penirq pin).
   The penirq pin goes to low when the panel is touched.
   (see GPIO binding[1] for more details).
-- interrupt-parent: the phandle for the gpio controller
-  (see interrupt binding[0]).
 - interrupts: (gpio) interrupt to which the chip is connected
   (see interrupt binding[0]).
 - ti,max-rt: maximum pressure.
diff --git a/Documentation/devicetree/bindings/input/touchscreen/zet6223.txt b/Documentation/devicetree/bindings/input/touchscreen/zet6223.txt
index fe6a1feef703..27d55a506f18 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/zet6223.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/zet6223.txt
@@ -3,8 +3,6 @@ Zeitec ZET6223 I2C touchscreen controller
 Required properties:
 - compatible		  : "zeitec,zet6223"
 - reg			  : I2C slave address of the chip (0x76)
-- interrupt-parent	  : a phandle pointing to the interrupt controller
-			    serving the interrupt for this chip
 - interrupts		  : interrupt specification for the zet6223 interrupt
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/abilis,tb10x-ictl.txt b/Documentation/devicetree/bindings/interrupt-controller/abilis,tb10x-ictl.txt
index 9d52d5afe3e9..5a4dd263fc12 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/abilis,tb10x-ictl.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/abilis,tb10x-ictl.txt
@@ -13,7 +13,6 @@ Required properties
 - interrupt-congroller: Identifies the node as an interrupt controller.
 - #interrupt cells: Specifies the number of cells used to encode an interrupt
   source connected to this controller. The value shall be 2.
-- interrupt-parent: Specifies the parent interrupt controller.
 - interrupts: Specifies the list of interrupt lines which are handled by
   the interrupt controller in the parent controller's notation. Interrupts
   are mapped one-to-one to parent interrupts.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt b/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt
index f6f1c14bf99b..5669764f9cc9 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt
@@ -6,7 +6,6 @@ Required properties:
 
 - compatible: should be "al,alpine-msix"
 - reg: physical base address and size of the registers
-- interrupt-parent: specifies the parent interrupt controller.
 - interrupt-controller: identifies the node as an interrupt controller
 - msi-controller: identifies the node as an PCI Message Signaled Interrupt
 		  controller
diff --git a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
index 4903fb72d883..24beadf7ba83 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
@@ -13,7 +13,6 @@ Required properties:
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value shall be 2. The first cell is the IRQ number, the
   second cell the trigger type as defined in interrupt.txt in this directory.
-- interrupt-parent: Specifies the parent interrupt controller.
 - interrupts: Specifies the interrupt line (NMI) which is handled by
   the interrupt controller in the parent controller's notation. This value
   shall be the NMI.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
index 89674ad8a097..1502a51548bb 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
@@ -15,9 +15,6 @@ Required properties:
     "amlogic,meson-gxbb-gpio-intc" for GXBB SoCs (S905) or
     "amlogic,meson-gxl-gpio-intc" for GXL SoCs (S905X, S912)
     "amlogic,meson-axg-gpio-intc" for AXG SoCs (A113D, A113X)
-- interrupt-parent : a phandle to the GIC the interrupts are routed to.
-   Usually this is provided at the root level of the device tree as it is
-   common to most of the SoC.
 - reg : Specifies base physical address and size of the registers.
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Specifies the number of cells needed to encode an
diff --git a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
index 0e9f09a6a2fe..f4c5d34c4111 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "atmel,<chip>-aic"
   <chip> can be "at91rm9200", "sama5d2", "sama5d3" or "sama5d4"
 - interrupt-controller: Identifies the node as an interrupt controller.
-- interrupt-parent: For single AIC system, it is an empty property.
 - #interrupt-cells: The number of cells to define the interrupts. It should be 3.
   The first cell is the IRQ number (aka "Peripheral IDentifier" on datasheet).
   The second cell is used to specify flags:
@@ -27,7 +26,6 @@ Examples:
 	aic: interrupt-controller@fffff000 {
 		compatible = "atmel,at91rm9200-aic";
 		interrupt-controller;
-		interrupt-parent;
 		#interrupt-cells = <3>;
 		reg = <0xfffff000 0x200>;
 	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
index 6428a6ba9f4a..0f1af5a1c12e 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
@@ -26,8 +26,6 @@ Required properties:
   are 0..7 for bank 0, and 0..31 for bank 1.
 
 Additional required properties for brcm,bcm2836-armctrl-ic:
-- interrupt-parent : Specifies the parent interrupt controller when this
-  controller is the second level.
 - interrupts : Specifies the interrupt on the parent for this interrupt
   controller to handle.
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm3380-l2-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm3380-l2-intc.txt
index 8f48aad50868..37aea40d5430 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm3380-l2-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm3380-l2-intc.txt
@@ -18,8 +18,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this one is cascaded from
 - interrupts: specifies the interrupt line in the interrupt-parent controller
   node, valid values depend on the type of parent interrupt controller
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm6345-l1-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm6345-l1-intc.txt
index 4040905388d9..2bc19b1ac877 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm6345-l1-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm6345-l1-intc.txt
@@ -29,8 +29,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller(s)
-  this one is cascaded from
 - interrupts: specifies the interrupt line(s) in the interrupt-parent controller
   node; valid values depend on the type of parent interrupt controller
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7038-l1-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7038-l1-intc.txt
index cc217b22dccd..2117d4ac1ae5 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7038-l1-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7038-l1-intc.txt
@@ -28,8 +28,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller(s)
-  this one is cascaded from
 - interrupts: specifies the interrupt line(s) in the interrupt-parent controller
   node; valid values depend on the type of parent interrupt controller
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt
index 44a9bb15dd56..addd86b6ca2f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt
@@ -56,8 +56,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this one is cascaded from
 - interrupts: specifies the interrupt line(s) in the interrupt-parent controller
   node, valid values depend on the type of parent interrupt controller
 - brcm,int-map-mask: 32-bits bit mask describing how many and which interrupts
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt
index 36df06c5c567..d514ec060a4a 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt
@@ -8,8 +8,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an
   interrupt source. Should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this controller is cacaded from
 - interrupts: specifies the interrupt line in the interrupt-parent irq space
   to be used for cascading
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/fsl,ls-scfg-msi.txt b/Documentation/devicetree/bindings/interrupt-controller/fsl,ls-scfg-msi.txt
index a4ff93d6b7f3..454ce04d6787 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/fsl,ls-scfg-msi.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/fsl,ls-scfg-msi.txt
@@ -13,9 +13,6 @@ Required properties:
 - reg: physical base address of the controller and length of memory mapped.
 - interrupts: an interrupt to the parent interrupt controller.
 
-Optional properties:
-- interrupt-parent: the phandle to the parent interrupt controller.
-
 This interrupt controller hardware is a second level interrupt controller that
 is hooked to a parent interrupt controller: e.g: ARM GIC for ARM-based
 platforms. If interrupt-parent is not provided, the default parent interrupt
diff --git a/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt b/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
index 3b2f4c43ad8d..a6813a071f15 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
@@ -68,8 +68,6 @@ Examples:
 
 Devices connect to mbigen required properties:
 ----------------------------------------------------
--interrupt-parent: Specifies the mbigen device node which device connected.
-
 -interrupts:Specifies the interrupt source.
  For the specific information of each cell in this property,please refer to
  the "interrupt-cells" description mentioned above.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
index 5f89fb635a1b..d4373d0f7121 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
@@ -4,6 +4,7 @@ Required properties:
 
 - compatible : should be "ingenic,<socname>-intc". Valid strings are:
     ingenic,jz4740-intc
+    ingenic,jz4725b-intc
     ingenic,jz4770-intc
     ingenic,jz4775-intc
     ingenic,jz4780-intc
@@ -11,7 +12,6 @@ Required properties:
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value shall be 1.
-- interrupt-parent : phandle of the CPU interrupt controller.
 - interrupts : Specifies the CPU interrupt the controller is connected to.
 
 Example:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt b/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt
index 3f6442c7f867..930fb462fd9f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt
@@ -26,8 +26,6 @@ Required properties:
                          See Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
                          for details about the GIC Device Tree binding.
 
-- interrupt-parent     : Reference to the parent interrupt controller.
-
 Example:
 
 	odmi: odmi@300000 {
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt b/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt
index a7efdbc3de5b..5865f4f2c69d 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt
@@ -16,8 +16,6 @@ Required properties:
   and "mediatek,cirq" as a fallback.
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Use the same format as specified by GIC in arm,gic.txt.
-- interrupt-parent: phandle of irq parent for cirq. The parent must
-  use the same interrupt-cells format as GIC.
 - reg: Physical base address of the cirq registers and length of memory
   mapped region.
 - mediatek,ext-irq-range: Identifies external irq number range in different
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
index 07bf0b9a5139..6a32922a55b8 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
@@ -21,8 +21,6 @@ Required properties:
 	"mediatek,mt2701-sysirq", "mediatek,mt6577-sysirq": for MT2701
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Use the same format as specified by GIC in arm,gic.txt.
-- interrupt-parent: phandle of irq parent for sysirq. The parent must
-  use the same interrupt-cells format as GIC.
 - reg: Physical base address of the intpol registers and length of memory
   mapped region. Could be multiple bases here. Ex: mt6797 needs 2 reg, others
   need 1.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mscc,ocelot-icpu-intr.txt b/Documentation/devicetree/bindings/interrupt-controller/mscc,ocelot-icpu-intr.txt
index b47a8a02b17b..f5baeccb689f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mscc,ocelot-icpu-intr.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mscc,ocelot-icpu-intr.txt
@@ -7,7 +7,6 @@ Required properties:
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value shall be 1.
-- interrupt-parent : phandle of the CPU interrupt controller.
 - interrupts : Specifies the CPU interrupt the controller is connected to.
 
 Example:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt
index 1099fe0788fa..2ff356640100 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt
@@ -15,12 +15,10 @@ Required properties:
   include "nvidia,tegra30-ictlr".	
 - reg : Specifies base physical address and size of the registers.
   Each controller must be described separately (Tegra20 has 4 of them,
-  whereas Tegra30 and later have 5"  
+  whereas Tegra30 and later have 5).
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value must be 3.
-- interrupt-parent : a phandle to the GIC these interrupts are routed
-  to.
 
 Notes:
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/nxp,lpc3220-mic.txt b/Documentation/devicetree/bindings/interrupt-controller/nxp,lpc3220-mic.txt
index 38211f344dc8..0bfb3ba55f4c 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/nxp,lpc3220-mic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/nxp,lpc3220-mic.txt
@@ -14,8 +14,6 @@ Required properties:
   Reset value is IRQ_TYPE_LEVEL_LOW.
 
 Optional properties:
-- interrupt-parent: empty for MIC interrupt controller, link to parent
-  MIC interrupt controller for SIC1 and SIC2
 - interrupts: empty for MIC interrupt controller, cascaded MIC
   hardware interrupts for SIC1 and SIC2
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
index 475ae9bd562b..ad70006c1848 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
@@ -7,7 +7,6 @@ Required Properties:
 - compatible: has to be "qca,<soctype>-cpu-intc", "qca,ar7100-misc-intc" or
   "qca,<soctype>-cpu-intc", "qca,ar7240-misc-intc"
 - reg: Base address and size of the controllers memory area
-- interrupt-parent: phandle of the parent interrupt controller.
 - interrupts: Interrupt specifier for the controllers interrupt.
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode interrupt
diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt
index 0b2c97ddb520..8e0797cb1487 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt
@@ -35,12 +35,6 @@ Properties:
 		    interrupt.
 		    The second element is the trigger type.
 
-- interrupt-parent:
-	Usage: required
-	Value type: <phandle>
-	Definition: Specifies the interrupt parent necessary for hierarchical
-		    domain to operate.
-
 - interrupt-controller:
 	Usage: required
 	Value type: <bool>
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
index 20f121daa910..697ca2f26d1b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
@@ -7,6 +7,7 @@ Required properties:
     - "renesas,irqc-r8a73a4" (R-Mobile APE6)
     - "renesas,irqc-r8a7743" (RZ/G1M)
     - "renesas,irqc-r8a7745" (RZ/G1E)
+    - "renesas,irqc-r8a77470" (RZ/G1C)
     - "renesas,irqc-r8a7790" (R-Car H2)
     - "renesas,irqc-r8a7791" (R-Car M2-W)
     - "renesas,irqc-r8a7792" (R-Car V2H)
@@ -16,6 +17,7 @@ Required properties:
     - "renesas,intc-ex-r8a7796" (R-Car M3-W)
     - "renesas,intc-ex-r8a77965" (R-Car M3-N)
     - "renesas,intc-ex-r8a77970" (R-Car V3M)
+    - "renesas,intc-ex-r8a77980" (R-Car V3H)
     - "renesas,intc-ex-r8a77995" (R-Car D3)
 - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
   interrupts.txt in this directory
diff --git a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.txt b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.txt
index 9e5f73412cd7..19af687858a1 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.txt
@@ -32,8 +32,6 @@ Optional properties:
 - samsung,combiner-nr: The number of interrupt combiners supported. If this
   property is not specified, the default number of combiners is assumed
   to be 16.
-- interrupt-parent: pHandle of the parent interrupt controller, if not
-  inherited from the parent node.
 
 
 Example:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt
index 1f441fa0ad40..355c18a3a4d3 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: should be "sigma,smp8642-intc"
 - reg: physical address of MMIO region
 - ranges: address space mapping of child nodes
-- interrupt-parent: phandle of parent interrupt controller
 - interrupt-controller: boolean
 - #address-cells: should be <1>
 - #size-cells: should be <1>
diff --git a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
index 8b46a34e05f1..09fc02b99845 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
@@ -7,7 +7,6 @@ Properties:
 
 - compatible: "snps,archs-idu-intc"
 - interrupt-controller: This is an interrupt controller.
-- interrupt-parent: <reference to parent core intc>
 - #interrupt-cells: Must be <1>.
 
   Value of the cell specifies the "common" IRQ from peripheral to IDU. Number N
diff --git a/Documentation/devicetree/bindings/interrupt-controller/snps,dw-apb-ictl.txt b/Documentation/devicetree/bindings/interrupt-controller/snps,dw-apb-ictl.txt
index 492911744ca3..086ff08322db 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/snps,dw-apb-ictl.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/snps,dw-apb-ictl.txt
@@ -11,7 +11,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: number of cells to encode an interrupt-specifier, shall be 1
 - interrupts: interrupt reference to primary interrupt controller
-- interrupt-parent: (optional) reference specific primary interrupt controller
 
 The interrupt sources map to the corresponding bits in the interrupt
 registers, i.e.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/socionext,synquacer-exiu.txt b/Documentation/devicetree/bindings/interrupt-controller/socionext,synquacer-exiu.txt
index 8b2faefe29ca..dac0846fe789 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/socionext,synquacer-exiu.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/socionext,synquacer-exiu.txt
@@ -12,7 +12,6 @@ Required properties:
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells     : Specifies the number of cells needed to encode an
                          interrupt source. The value must be 3.
-- interrupt-parent     : phandle of the GIC these interrupts are routed to.
 - socionext,spi-base   : The SPI number of the first SPI of the 32 adjacent
                          ones the EXIU forwards its interrups to.
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt b/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt
index 2ab0ea39867b..a407c499b3cc 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt
@@ -31,10 +31,6 @@ Required properties:
     parent) is equal to number of groups. The format of the interrupt
     specifier depends in the interrupt parent controller.
 
-  Optional properties:
-  - interrupt-parent: pHandle of the parent interrupt controller, if not
-    inherited from the parent node.
-
 Example:
 
 The following is an example from the SPEAr320 SoC dtsi file.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
index 136bd612bd83..6a36bf66d932 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
@@ -12,7 +12,7 @@ Required properties:
   specifier, shall be 2
 - interrupts: interrupts references to primary interrupt controller
   (only needed for exti controller with multiple exti under
-  same parent interrupt: st,stm32-exti and st,stm32h7-exti")
+  same parent interrupt: st,stm32-exti and st,stm32h7-exti)
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt b/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
index 7f15f1b0325b..341ae5909333 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
@@ -11,6 +11,4 @@ Required properties:
   region
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: phandle to the parent interrupt controller this one is
-  cascaded from
 - interrupts: specifies the interrupt line in the interrupt-parent controller
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,c64x+megamod-pic.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,c64x+megamod-pic.txt
index 42bb796cc4ad..ee3f9c351501 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,c64x+megamod-pic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,c64x+megamod-pic.txt
@@ -46,7 +46,6 @@ C6X Interrupt Chips
   - interrupt-controller
   - #interrupt-cells: <1>
   - reg: base address and size of register area
-  - interrupt-parent: must be core interrupt controller
   - interrupts: This should have four cells; one for each interrupt combiner.
                 The cells contain the core priority interrupt to which the
                 corresponding combiner output is wired.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu b/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu
index 18d4f407bf0e..422d6908f8b2 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu
@@ -12,8 +12,6 @@ Required properties:
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value must be 3.
-- interrupt-parent : a phandle to the GIC these interrupts are routed
-  to.
 
 Notes:
 
diff --git a/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt b/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt
index b1682c80b490..525ec82615a6 100644
--- a/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt
+++ b/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt
@@ -31,7 +31,6 @@ Required properties:
 - compatible: Should be "samsung,exynos-sysmmu"
 - reg: A tuple of base address and size of System MMU registers.
 - #iommu-cells: Should be <0>.
-- interrupt-parent: The phandle of the interrupt controller of System MMU
 - interrupts: An interrupt specifier for interrupt signal of System MMU,
 	      according to the format defined by a particular interrupt
 	      controller.
diff --git a/Documentation/devicetree/bindings/leds/common.txt b/Documentation/devicetree/bindings/leds/common.txt
index 1d4afe9644b6..aa1399814a2a 100644
--- a/Documentation/devicetree/bindings/leds/common.txt
+++ b/Documentation/devicetree/bindings/leds/common.txt
@@ -31,7 +31,7 @@ Optional properties for child nodes:
      "backlight" - LED will act as a back-light, controlled by the framebuffer
 		   system
      "default-on" - LED will turn on (but for leds-gpio see "default-state"
-		    property in Documentation/devicetree/bindings/gpio/led.txt)
+		    property in Documentation/devicetree/bindings/leds/leds-gpio.txt)
      "heartbeat" - LED "double" flashes at a load average based rate
      "disk-activity" - LED indicates disk activity
      "ide-disk" - LED indicates IDE disk activity (deprecated),
diff --git a/Documentation/devicetree/bindings/leds/leds-lm3692x.txt b/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
index 6c9074f84a51..08b352840bd7 100644
--- a/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
+++ b/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
@@ -20,7 +20,10 @@ Optional properties:
 	- vled-supply : LED supply
 
 Required child properties:
-	- reg : 0
+	- reg : 0 - Will enable all LED sync paths
+		1 - Will enable the LED1 sync
+		2 - Will enable the LED2 sync
+		3 - Will enable the LED3 sync (LM36923 only)
 
 Optional child properties:
 	- label : see Documentation/devicetree/bindings/leds/common.txt
diff --git a/Documentation/devicetree/bindings/leds/leds-lt3593.txt b/Documentation/devicetree/bindings/leds/leds-lt3593.txt
new file mode 100644
index 000000000000..6b2cabc36c0c
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-lt3593.txt
@@ -0,0 +1,32 @@
+Bindings for Linear Technologies LT3593 LED controller
+
+Required properties:
+- compatible:		Should be "lltc,lt3593".
+- lltc,ctrl-gpios:	A handle to the GPIO that is connected to the 'CTRL'
+			pin of the chip.
+
+The hardware supports only one LED. The properties of this LED are
+configured in a sub-node in the device node.
+
+Optional sub-node properties:
+- label:	A label for the LED. If none is given, the LED will be
+		named "lt3595::".
+- linux,default-trigger: The default trigger for the LED.
+			See Documentation/devicetree/bindings/leds/common.txt
+- default-state:	The initial state of the LED.
+			See Documentation/devicetree/bindings/leds/common.txt
+
+If multiple chips of this type are found in a design, each one needs to
+be handled by its own device node.
+
+Example:
+
+led-controller {
+	compatible = "lltc,lt3593";
+	lltc,ctrl-gpios = <&gpio 0 GPIO_ACTIVE_HIGH>;
+
+	led {
+		label = "white:backlight";
+		default-state = "on";
+	};
+};
diff --git a/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt b/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt
index 49cfc8c337c4..c4dd93f1fed2 100644
--- a/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt
+++ b/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt
@@ -9,7 +9,6 @@ Required properties:
 		of cells required for the mailbox specifier. Should be 1.
 
 Optional properties:
-- interrupt-parent :	interrupt source phandle.
 - interrupts :		interrupt number. The interrupt specifier format
 			depends on the interrupt controller parent.
 
diff --git a/Documentation/devicetree/bindings/media/i2c/tc358743.txt b/Documentation/devicetree/bindings/media/i2c/tc358743.txt
index 49f8bcc2ea4d..59102edcf01e 100644
--- a/Documentation/devicetree/bindings/media/i2c/tc358743.txt
+++ b/Documentation/devicetree/bindings/media/i2c/tc358743.txt
@@ -12,7 +12,7 @@ Required Properties:
 Optional Properties:
 
 - reset-gpios: gpio phandle GPIO connected to the reset pin
-- interrupts, interrupt-parent: GPIO connected to the interrupt pin
+- interrupts: GPIO connected to the interrupt pin
 - data-lanes: should be <1 2 3 4> for four-lane operation,
 	      or <1 2> for two-lane operation
 - clock-lanes: should be <0>
diff --git a/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt b/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
index 17a8e81ca0cc..cfa4ffada8ae 100644
--- a/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
+++ b/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
@@ -2,7 +2,6 @@ Bindings, specific for the sh_mobile_ceu_camera.c driver:
  - compatible: Should be "renesas,sh-mobile-ceu"
  - reg: register base and size
  - interrupts: the interrupt number
- - interrupt-parent: the interrupt controller
  - renesas,max-width: maximum image width, supported on this SoC
  - renesas,max-height: maximum image height, supported on this SoC
 
diff --git a/Documentation/devicetree/bindings/mfd/ac100.txt b/Documentation/devicetree/bindings/mfd/ac100.txt
index b8ef00667599..dff219f07493 100644
--- a/Documentation/devicetree/bindings/mfd/ac100.txt
+++ b/Documentation/devicetree/bindings/mfd/ac100.txt
@@ -10,7 +10,6 @@ Required properties:
 - sub-nodes:
   - codec
     - compatible:		"x-powers,ac100-codec"
-    - interrupt-parent:		The parent interrupt controller
     - interrupts:		SoC NMI / GPIO interrupt connected to the
     				IRQ_AUDIO pin
     - #clock-cells:		Shall be 0
@@ -20,9 +19,6 @@ Required properties:
 
   - rtc
     - compatible:		"x-powers,ac100-rtc"
-    - interrupt-parent:		The parent interrupt controller
-    - interrupts:		SoC NMI / GPIO interrupt connected to the
-    				IRQ_RTC pin
     - clocks:			A phandle to the codec's "4M_adda" clock
     - #clock-cells:		Shall be 1
     - clock-output-names:	"cko1_rtc", "cko2_rtc", "cko3_rtc"
diff --git a/Documentation/devicetree/bindings/mfd/altera-a10sr.txt b/Documentation/devicetree/bindings/mfd/altera-a10sr.txt
index c8a736554b4b..a688520dd87d 100644
--- a/Documentation/devicetree/bindings/mfd/altera-a10sr.txt
+++ b/Documentation/devicetree/bindings/mfd/altera-a10sr.txt
@@ -5,7 +5,6 @@ Required parent device properties:
 - spi-max-frequency	: Maximum SPI frequency.
 - reg			: The SPI Chip Select address for the Arria10
 			  System Resource chip
-- interrupt-parent	: The parent interrupt controller.
 - interrupts		: The interrupt line the device is connected to.
 - interrupt-controller	: Marks the device node as an interrupt controller.
 - #interrupt-cells	: The number of cells to describe an IRQ, should be 2.
diff --git a/Documentation/devicetree/bindings/mfd/arizona.txt b/Documentation/devicetree/bindings/mfd/arizona.txt
index a014afb07902..9b62831fdf3e 100644
--- a/Documentation/devicetree/bindings/mfd/arizona.txt
+++ b/Documentation/devicetree/bindings/mfd/arizona.txt
@@ -22,7 +22,6 @@ Required properties:
     connected to.
   - interrupt-controller : Arizona class devices contain interrupt controllers
     and may provide interrupt services to other devices.
-  - interrupt-parent : The parent interrupt controller.
   - #interrupt-cells: the number of cells to describe an IRQ, this should be 2.
     The first cell is the IRQ number.
     The second cell is the flags, encoded as the trigger masks from
diff --git a/Documentation/devicetree/bindings/mfd/axp20x.txt b/Documentation/devicetree/bindings/mfd/axp20x.txt
index d1762f3b30af..62091f6b025e 100644
--- a/Documentation/devicetree/bindings/mfd/axp20x.txt
+++ b/Documentation/devicetree/bindings/mfd/axp20x.txt
@@ -28,7 +28,6 @@ Required properties:
     * "x-powers,axp809"
     * "x-powers,axp813"
 - reg: The I2C slave address or RSB hardware address for the AXP chip
-- interrupt-parent: The parent interrupt controller
 - interrupts: SoC NMI / GPIO interrupt connected to the PMIC's IRQ pin
 - interrupt-controller: The PMIC has its own internal IRQs
 - #interrupt-cells: Should be set to 1
diff --git a/Documentation/devicetree/bindings/mfd/bd9571mwv.txt b/Documentation/devicetree/bindings/mfd/bd9571mwv.txt
index 25d1f697eb25..8c4678650d1a 100644
--- a/Documentation/devicetree/bindings/mfd/bd9571mwv.txt
+++ b/Documentation/devicetree/bindings/mfd/bd9571mwv.txt
@@ -3,7 +3,6 @@
 Required properties:
  - compatible		: Should be "rohm,bd9571mwv".
  - reg			: I2C slave address.
- - interrupt-parent	: Phandle to the parent interrupt controller.
  - interrupts		: The interrupt line the device is connected to.
  - interrupt-controller	: Marks the device node as an interrupt controller.
  - #interrupt-cells	: The number of cells to describe an IRQ, should be 2.
diff --git a/Documentation/devicetree/bindings/mfd/bfticu.txt b/Documentation/devicetree/bindings/mfd/bfticu.txt
index 65c90776c620..538192fda9ae 100644
--- a/Documentation/devicetree/bindings/mfd/bfticu.txt
+++ b/Documentation/devicetree/bindings/mfd/bfticu.txt
@@ -10,7 +10,6 @@ Required properties:
 - interrupts: the main IRQ line to signal the collected IRQs
 - #interrupt-cells : is 2 and their usage is compliant to the 2 cells variant
   of Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
-- interrupt-parent: the parent IRQ ctrl the main IRQ is connected to
 - reg: access on the parent local bus (chip select, offset in chip select, size)
 
 Example:
diff --git a/Documentation/devicetree/bindings/mfd/da9055.txt b/Documentation/devicetree/bindings/mfd/da9055.txt
index 6dab34d34fce..131a53283e17 100644
--- a/Documentation/devicetree/bindings/mfd/da9055.txt
+++ b/Documentation/devicetree/bindings/mfd/da9055.txt
@@ -22,8 +22,6 @@ Documentation/devicetree/bindings/sound/da9055.txt
 Required properties:
 - compatible : Should be "dlg,da9055-pmic"
 - reg: Specifies the I2C slave address (defaults to 0x5a but can be modified)
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the IRQs from da9055 are delivered to.
 - interrupts: IRQ line info for da9055 chip.
 - interrupt-controller: da9055 has internal IRQs (has own IRQ domain).
 - #interrupt-cells: Should be 1, is the local IRQ number for da9055.
diff --git a/Documentation/devicetree/bindings/mfd/da9062.txt b/Documentation/devicetree/bindings/mfd/da9062.txt
index c0a418c27e9d..edca653a5777 100644
--- a/Documentation/devicetree/bindings/mfd/da9062.txt
+++ b/Documentation/devicetree/bindings/mfd/da9062.txt
@@ -32,8 +32,6 @@ Required properties:
     "dlg,da9061" for DA9061
 - reg : Specifies the I2C slave address (this defaults to 0x58 but it can be
   modified to match the chip's OTP settings).
-- interrupt-parent : Specifies the reference to the interrupt controller for
-  the DA9062 or DA9061.
 - interrupts : IRQ line information.
 - interrupt-controller
 
diff --git a/Documentation/devicetree/bindings/mfd/da9063.txt b/Documentation/devicetree/bindings/mfd/da9063.txt
index 443e68286957..8da879935c59 100644
--- a/Documentation/devicetree/bindings/mfd/da9063.txt
+++ b/Documentation/devicetree/bindings/mfd/da9063.txt
@@ -16,8 +16,6 @@ Required properties:
 - compatible : Should be "dlg,da9063" or "dlg,da9063l"
 - reg : Specifies the I2C slave address (this defaults to 0x58 but it can be
   modified to match the chip's OTP settings).
-- interrupt-parent : Specifies the reference to the interrupt controller for
-  the DA9063.
 - interrupts : IRQ line information.
 - interrupt-controller
 
diff --git a/Documentation/devicetree/bindings/mfd/da9150.txt b/Documentation/devicetree/bindings/mfd/da9150.txt
index fd4dca7f4aba..f09b41fbdf47 100644
--- a/Documentation/devicetree/bindings/mfd/da9150.txt
+++ b/Documentation/devicetree/bindings/mfd/da9150.txt
@@ -13,8 +13,6 @@ da9150-fg		: Battery Fuel-Gauge
 Required properties:
 - compatible : Should be "dlg,da9150"
 - reg: Specifies the I2C slave address
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the IRQs from da9150 are delivered to.
 - interrupts: IRQ line info for da9150 chip.
 - interrupt-controller: da9150 has internal IRQs (own IRQ domain).
   (See ../interrupt-controller/interrupts.txt for
diff --git a/Documentation/devicetree/bindings/mfd/max14577.txt b/Documentation/devicetree/bindings/mfd/max14577.txt
index 236264c10b92..fc6f0f4e8beb 100644
--- a/Documentation/devicetree/bindings/mfd/max14577.txt
+++ b/Documentation/devicetree/bindings/mfd/max14577.txt
@@ -11,7 +11,6 @@ Required properties:
 - compatible : Must be "maxim,max14577" or "maxim,max77836".
 - reg : I2C slave address for the max14577 chip (0x25 for max14577/max77836)
 - interrupts : IRQ line for the chip.
-- interrupt-parent :  The parent interrupt controller.
 
 
 Required nodes:
diff --git a/Documentation/devicetree/bindings/mfd/max77686.txt b/Documentation/devicetree/bindings/mfd/max77686.txt
index 0f2587fa42cb..42968b7144e0 100644
--- a/Documentation/devicetree/bindings/mfd/max77686.txt
+++ b/Documentation/devicetree/bindings/mfd/max77686.txt
@@ -15,7 +15,6 @@ Required properties:
 - compatible : Must be "maxim,max77686";
 - reg : Specifies the i2c slave address of PMIC block.
 - interrupts : This i2c device has an IRQ line connected to the main SoC.
-- interrupt-parent : The parent interrupt controller.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mfd/max77693.txt b/Documentation/devicetree/bindings/mfd/max77693.txt
index e6754974a745..a3c60a7a3be1 100644
--- a/Documentation/devicetree/bindings/mfd/max77693.txt
+++ b/Documentation/devicetree/bindings/mfd/max77693.txt
@@ -14,7 +14,6 @@ Required properties:
 - compatible : Must be "maxim,max77693".
 - reg : Specifies the i2c slave address of PMIC block.
 - interrupts : This i2c device has an IRQ line connected to the main SoC.
-- interrupt-parent :  The parent interrupt controller.
 
 Optional properties:
 - regulators : The regulators of max77693 have to be instantiated under subnode
diff --git a/Documentation/devicetree/bindings/mfd/max77802.txt b/Documentation/devicetree/bindings/mfd/max77802.txt
index f2f3fe75901c..09decac20d91 100644
--- a/Documentation/devicetree/bindings/mfd/max77802.txt
+++ b/Documentation/devicetree/bindings/mfd/max77802.txt
@@ -14,7 +14,6 @@ Required properties:
 - compatible		: Must be "maxim,max77802"
 - reg			: Specifies the I2C slave address of PMIC block.
 - interrupts		: I2C device IRQ line connected to the main SoC.
-- interrupt-parent	: The parent interrupt controller.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mfd/max8998.txt b/Documentation/devicetree/bindings/mfd/max8998.txt
index 23a3650ff2a2..5f2f07c09c90 100644
--- a/Documentation/devicetree/bindings/mfd/max8998.txt
+++ b/Documentation/devicetree/bindings/mfd/max8998.txt
@@ -20,8 +20,6 @@ Required properties:
 - reg: Specifies the i2c slave address of the pmic block. It should be 0x66.
 
 Optional properties:
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from MAX8998 are routed to.
 - interrupts: Interrupt specifiers for two interrupt sources.
   - First interrupt specifier is for main interrupt.
   - Second interrupt specifier is for power-on/-off interrupt.
diff --git a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
index c639705a98ef..5ddcc8f4febc 100644
--- a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
+++ b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
@@ -3,7 +3,6 @@ Motorola CPCAP PMIC device tree binding
 Required properties:
 - compatible		: One or both of "motorola,cpcap" or "ste,6556002"
 - reg			: SPI chip select
-- interrupt-parent	: The parent interrupt controller
 - interrupts		: The interrupt line the device is connected to
 - interrupt-controller	: Marks the device node as an interrupt controller
 - #interrupt-cells	: The number of cells to describe an IRQ, should be 2
diff --git a/Documentation/devicetree/bindings/mfd/palmas.txt b/Documentation/devicetree/bindings/mfd/palmas.txt
index 8ae1a32bfb7e..e736ab3012a6 100644
--- a/Documentation/devicetree/bindings/mfd/palmas.txt
+++ b/Documentation/devicetree/bindings/mfd/palmas.txt
@@ -25,7 +25,6 @@ and also the generic series names
   The first cell is the IRQ number.
   The second cell is the flags, encoded as the trigger masks from
   Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
-- interrupt-parent : The parent interrupt controller.
 
 Optional properties:
   ti,mux-padX : set the pad register X (1-2) to the correct muxing for the
diff --git a/Documentation/devicetree/bindings/mfd/retu.txt b/Documentation/devicetree/bindings/mfd/retu.txt
index 876242394a16..df3005dd3e3c 100644
--- a/Documentation/devicetree/bindings/mfd/retu.txt
+++ b/Documentation/devicetree/bindings/mfd/retu.txt
@@ -9,7 +9,6 @@ Required properties:
 - compatible:		"nokia,retu" or "nokia,tahvo"
 - reg:			Specifies the CBUS slave address of the ASIC chip
 - interrupts: 		The interrupt line the device is connected to
-- interrupt-parent:	The parent interrupt controller
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mfd/rk808.txt b/Documentation/devicetree/bindings/mfd/rk808.txt
index 91b65227afeb..1683ec3245bc 100644
--- a/Documentation/devicetree/bindings/mfd/rk808.txt
+++ b/Documentation/devicetree/bindings/mfd/rk808.txt
@@ -10,7 +10,6 @@ Required properties:
 - compatible: "rockchip,rk808"
 - compatible: "rockchip,rk818"
 - reg: I2C slave address
-- interrupt-parent: The parent interrupt controller.
 - interrupts: the interrupt outputs of the controller.
 - #clock-cells: from common clock binding; shall be set to 1 (multiple clock
   outputs). See <dt-bindings/clock/rockchip,rk808.h> for clock IDs.
diff --git a/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt b/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt
index cdd079bfc287..c68cdd365153 100644
--- a/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt
+++ b/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt
@@ -31,8 +31,6 @@ Required properties:
  - reg: Specifies the I2C slave address of the pmic block. It should be 0x66.
 
 Optional properties:
- - interrupt-parent: Specifies the phandle of the interrupt controller to which
-   the interrupts from s2mps11 are delivered to.
  - interrupts: Interrupt specifiers for interrupt sources.
  - samsung,s2mps11-wrstbi-ground: Indicates that WRSTBI pin of PMIC is pulled
    down. When the system is suspended it will always go down thus triggerring
diff --git a/Documentation/devicetree/bindings/mfd/stmpe.txt b/Documentation/devicetree/bindings/mfd/stmpe.txt
index f9065a5781a2..c797c05cd3c2 100644
--- a/Documentation/devicetree/bindings/mfd/stmpe.txt
+++ b/Documentation/devicetree/bindings/mfd/stmpe.txt
@@ -10,7 +10,6 @@ Required properties:
 Optional properties:
  - interrupts                   : The interrupt outputs from the controller
  - interrupt-controller         : Marks the device node as an interrupt controller
- - interrupt-parent             : Specifies which IRQ controller we're connected to
  - wakeup-source                : Marks the input device as wakable
  - st,autosleep-timeout         : Valid entries (ms); 4, 16, 32, 64, 128, 256, 512 and 1024
  - irq-gpio                     : If present, which GPIO to use for event IRQ
diff --git a/Documentation/devicetree/bindings/mfd/tc3589x.txt b/Documentation/devicetree/bindings/mfd/tc3589x.txt
index 23fc2f21f5a4..4f22b2b07dc5 100644
--- a/Documentation/devicetree/bindings/mfd/tc3589x.txt
+++ b/Documentation/devicetree/bindings/mfd/tc3589x.txt
@@ -15,7 +15,6 @@ Required properties:
  - compatible : must be "toshiba,tc35890", "toshiba,tc35892", "toshiba,tc35893",
    "toshiba,tc35894", "toshiba,tc35895" or "toshiba,tc35896"
  - reg : I2C address of the device
- - interrupt-parent : specifies which IRQ controller we're connected to
  - interrupts : the interrupt on the parent the controller is connected to
  - interrupt-controller : marks the device node as an interrupt controller
  - #interrupt-cells : should be <1>, the first cell is the IRQ offset on this
diff --git a/Documentation/devicetree/bindings/mfd/tps65086.txt b/Documentation/devicetree/bindings/mfd/tps65086.txt
index 9cfa886fe99f..67eac0ed32df 100644
--- a/Documentation/devicetree/bindings/mfd/tps65086.txt
+++ b/Documentation/devicetree/bindings/mfd/tps65086.txt
@@ -3,7 +3,6 @@
 Required properties:
  - compatible		: Should be "ti,tps65086".
  - reg			: I2C slave address.
- - interrupt-parent	: Phandle to the parent interrupt controller.
  - interrupts		: The interrupt line the device is connected to.
  - interrupt-controller	: Marks the device node as an interrupt controller.
  - #interrupt-cells	: The number of cells to describe an IRQ, should be 2.
diff --git a/Documentation/devicetree/bindings/mfd/tps65912.txt b/Documentation/devicetree/bindings/mfd/tps65912.txt
index 717e66d23142..8becb183a48e 100644
--- a/Documentation/devicetree/bindings/mfd/tps65912.txt
+++ b/Documentation/devicetree/bindings/mfd/tps65912.txt
@@ -3,7 +3,6 @@
 Required properties:
  - compatible		: Should be "ti,tps65912".
  - reg			: Slave address or chip select number (I2C / SPI).
- - interrupt-parent	: The parent interrupt controller.
  - interrupts		: The interrupt line the device is connected to.
  - interrupt-controller	: Marks the device node as an interrupt controller.
  - #interrupt-cells	: The number of cells to describe an IRQ, should be 2.
diff --git a/Documentation/devicetree/bindings/mfd/twl-familly.txt b/Documentation/devicetree/bindings/mfd/twl-familly.txt
index a66fcf946759..56f244b5d8a4 100644
--- a/Documentation/devicetree/bindings/mfd/twl-familly.txt
+++ b/Documentation/devicetree/bindings/mfd/twl-familly.txt
@@ -16,7 +16,6 @@ Required properties:
 - interrupt-controller : Since the twl support several interrupts internally,
   it is considered as an interrupt controller cascaded to the SoC one.
 - #interrupt-cells = <1>;
-- interrupt-parent : The parent interrupt controller.
 
 Optional node:
 - Child nodes contain in the twl. The twl family is made of several variants
diff --git a/Documentation/devicetree/bindings/mfd/twl6040.txt b/Documentation/devicetree/bindings/mfd/twl6040.txt
index 9a98ee7c323d..06e9dd7a0d96 100644
--- a/Documentation/devicetree/bindings/mfd/twl6040.txt
+++ b/Documentation/devicetree/bindings/mfd/twl6040.txt
@@ -9,7 +9,6 @@ Required properties:
 - compatible : "ti,twl6040" for twl6040, "ti,twl6041" for twl6041
 - reg: must be 0x4b for i2c address
 - interrupts: twl6040 has one interrupt line connecteded to the main SoC
-- interrupt-parent: The parent interrupt controller
 - gpio-controller:
 - #gpio-cells = <1>: twl6040 provides GPO lines.
 - #clock-cells = <0>; twl6040 is a provider of pdmclk which is used by McPDM
diff --git a/Documentation/devicetree/bindings/mfd/wm831x.txt b/Documentation/devicetree/bindings/mfd/wm831x.txt
index 505709403d3f..6b84b1b0d018 100644
--- a/Documentation/devicetree/bindings/mfd/wm831x.txt
+++ b/Documentation/devicetree/bindings/mfd/wm831x.txt
@@ -22,7 +22,6 @@ Required properties:
 
   - interrupts : The interrupt line the IRQ signal for the device is
     connected to.
-  - interrupt-parent : The parent interrupt controller.
 
   - interrupt-controller : wm831x devices contain interrupt controllers and
     may provide interrupt services to other devices.
diff --git a/Documentation/devicetree/bindings/mips/brcm/soc.txt b/Documentation/devicetree/bindings/mips/brcm/soc.txt
index 356c29789cf5..3a66d3c483e1 100644
--- a/Documentation/devicetree/bindings/mips/brcm/soc.txt
+++ b/Documentation/devicetree/bindings/mips/brcm/soc.txt
@@ -152,7 +152,7 @@ Required properties:
 - compatible	: should contain one of:
 		  "brcm,bcm7425-timers"
 		  "brcm,bcm7429-timers"
-		  "brcm,bcm7435-timers and
+		  "brcm,bcm7435-timers" and
 		  "brcm,brcmstb-timers"
 - reg		: the timers register range
 - interrupts	: the interrupt line for this timer block
diff --git a/Documentation/devicetree/bindings/mips/cavium/cib.txt b/Documentation/devicetree/bindings/mips/cavium/cib.txt
index f39a1aa2852b..410efa322254 100644
--- a/Documentation/devicetree/bindings/mips/cavium/cib.txt
+++ b/Documentation/devicetree/bindings/mips/cavium/cib.txt
@@ -13,8 +13,6 @@ Properties:
 - cavium,max-bits: The index (zero based) of the highest numbered bit
   in the CIB block.
 
-- interrupt-parent:  Always the CIU on the SoC.
-
 - interrupts: The CIU line to which the CIB block is connected.
 
 - #interrupt-cells: Must be <2>.  The first cell is the bit within the
diff --git a/Documentation/devicetree/bindings/misc/aspeed,cvic.txt b/Documentation/devicetree/bindings/misc/aspeed,cvic.txt
new file mode 100644
index 000000000000..d62c783d1d5e
--- /dev/null
+++ b/Documentation/devicetree/bindings/misc/aspeed,cvic.txt
@@ -0,0 +1,35 @@
+* ASPEED AST2400 and AST2500 coprocessor interrupt controller
+
+This file describes the bindings for the interrupt controller present
+in the AST2400 and AST2500 BMC SoCs which provides interrupt to the
+ColdFire coprocessor.
+
+It is not a normal interrupt controller and it would be rather
+inconvenient to create an interrupt tree for it as it somewhat shares
+some of the same sources as the main ARM interrupt controller but with
+different numbers.
+
+The AST2500 supports a SW generated interrupt
+
+Required properties:
+- reg: address and length of the register for the device.
+- compatible: "aspeed,cvic" and one of:
+		"aspeed,ast2400-cvic"
+	      or
+		"aspeed,ast2500-cvic"
+
+- valid-sources: One cell, bitmap of supported sources for the implementation
+
+Optional properties;
+- copro-sw-interrupts: List of interrupt numbers that can be used as
+		       SW interrupts from the ARM to the coprocessor.
+		       (AST2500 only)
+
+Example:
+
+	cvic: copro-interrupt-controller@1e6c2000 {
+		compatible = "aspeed,ast2500-cvic";
+		valid-sources = <0xffffffff>;
+		copro-sw-interrupts = <1>;
+		reg = <0x1e6c2000 0x80>;
+	};
diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
index 60481bfc3d31..5f3c02522c17 100644
--- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
@@ -19,8 +19,6 @@ Required Properties:
   - clocks: From clock bindings: Handles to clock inputs.
   - clock-names: From clock bindings: Tuple including "clk_xin" and "clk_ahb"
   - interrupts: Interrupt specifier
-  - interrupt-parent: Phandle for the interrupt controller that services
-		      interrupts for this device.
 
 Required Properties for "arasan,sdhci-5.1":
   - phys: From PHY bindings: Phandle for the Generic PHY for arasan.
diff --git a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
index a2cf5e1c87d8..99c5cf8507e8 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
@@ -21,7 +21,6 @@ Required properties:
 	"fsl,ls1043a-esdhc"
 	"fsl,ls1046a-esdhc"
 	"fsl,ls2080a-esdhc"
-  - interrupt-parent : interrupt source phandle.
   - clock-frequency : specifies eSDHC base clock frequency.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt b/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt
index 0e5e2ec4001d..75486cca8054 100644
--- a/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt
@@ -13,8 +13,6 @@ Optional properties:
 - gpios : may specify GPIOs in this order: Card-Detect GPIO,
   Write-Protect GPIO. Note that this does not follow the
   binding from mmc.txt, for historical reasons.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
index b40f3a492800..bcda1dfc4bac 100644
--- a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
+++ b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
@@ -42,7 +42,6 @@ Required properties:
                      May be "nand", if the SoC has the individual NAND
                      interrupts multiplexed behind another custom piece of
                      hardware
-- interrupt-parent : See standard interrupt bindings
 - #address-cells   : <1> - subnodes give the chip-select number
 - #size-cells      : <0>
 
diff --git a/Documentation/devicetree/bindings/mtd/denali-nand.txt b/Documentation/devicetree/bindings/mtd/denali-nand.txt
index 0ee8edb60efc..f33da8782741 100644
--- a/Documentation/devicetree/bindings/mtd/denali-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/denali-nand.txt
@@ -8,6 +8,9 @@ Required properties:
   - reg : should contain registers location and length for data and reg.
   - reg-names: Should contain the reg names "nand_data" and "denali_reg"
   - interrupts : The interrupt number.
+  - clocks: should contain phandle of the controller core clock, the bus
+    interface clock, and the ECC circuit clock.
+  - clock-names: should contain "nand", "nand_x", "ecc"
 
 Optional properties:
   - nand-ecc-step-size: see nand.txt for details.  If present, the value must be
@@ -31,5 +34,7 @@ nand: nand@ff900000 {
 	compatible = "altr,socfpga-denali-nand";
 	reg = <0xff900000 0x20>, <0xffb80000 0x1000>;
 	reg-names = "nand_data", "denali_reg";
+	clocks = <&nand_clk>, <&nand_x_clk>, <&nand_ecc_clk>;
+	clock-names = "nand", "nand_x", "ecc";
 	interrupts = <0 144 4>;
 };
diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
index dd559045593d..c059ab74ed88 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
@@ -16,7 +16,6 @@ Required properties:
  - compatible:	"ti,omap2-nand"
  - reg:		range id (CS number), base offset and length of the
 		NAND I/O space
- - interrupt-parent: must point to gpmc node
  - interrupts:	Two interrupt specifiers, one for fifoevent, one for termcount.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
index 956bb046e599..f03be904d3c2 100644
--- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
+++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
@@ -69,6 +69,15 @@ Optional properties:
                    all chips and support for it can not be detected at runtime.
                    Refer to your chips' datasheet to check if this is supported
                    by your chip.
+- broken-flash-reset : Some flash devices utilize stateful addressing modes
+		   (e.g., for 32-bit addressing) which need to be managed
+		   carefully by a system. Because these sorts of flash don't
+		   have a standardized software reset command, and because some
+		   systems don't toggle the flash RESET# pin upon system reset
+		   (if the pin even exists at all), there are systems which
+		   cannot reboot properly if the flash is left in the "wrong"
+		   state. This boolean flag can be used on such systems, to
+		   denote the absence of a reliable reset mechanism.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt
index 8bb11d809429..e949c778e983 100644
--- a/Documentation/devicetree/bindings/mtd/nand.txt
+++ b/Documentation/devicetree/bindings/mtd/nand.txt
@@ -25,7 +25,7 @@ Optional NAND chip properties:
 		  Deprecated values:
 		  "soft_bch": use "soft" and nand-ecc-algo instead
 - nand-ecc-algo: string, algorithm of NAND ECC.
-		 Supported values are: "hamming", "bch".
+		 Valid values are: "hamming", "bch", "rs".
 - nand-bus-width : 8 or 16 bus width if not present 8
 - nand-on-flash-bbt: boolean to enable on flash bbt option if not present false
 
@@ -43,6 +43,10 @@ Optional NAND chip properties:
 		     This is particularly useful when only the in-band area is
 		     used by the upper layers, and you want to make your NAND
 		     as reliable as possible.
+- nand-is-boot-medium: Whether the NAND chip is a boot medium. Drivers might use
+		       this information to select ECC algorithms supported by
+		       the boot ROM or similar restrictions.
+
 - nand-rb: shall contain the native Ready/Busy ids.
 
 The ECC strength and ECC step size properties define the correction capability
diff --git a/Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt b/Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt
new file mode 100644
index 000000000000..b2f2ca12f9e6
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt
@@ -0,0 +1,64 @@
+NVIDIA Tegra NAND Flash controller
+
+Required properties:
+- compatible: Must be one of:
+  - "nvidia,tegra20-nand"
+- reg: MMIO address range
+- interrupts: interrupt output of the NFC controller
+- clocks: Must contain an entry for each entry in clock-names.
+  See ../clocks/clock-bindings.txt for details.
+- clock-names: Must include the following entries:
+  - nand
+- resets: Must contain an entry for each entry in reset-names.
+  See ../reset/reset.txt for details.
+- reset-names: Must include the following entries:
+  - nand
+
+Optional children nodes:
+Individual NAND chips are children of the NAND controller node. Currently
+only one NAND chip supported.
+
+Required children node properties:
+- reg: An integer ranging from 1 to 6 representing the CS line to use.
+
+Optional children node properties:
+- nand-ecc-mode: String, operation mode of the NAND ecc mode. Currently only
+		 "hw" is supported.
+- nand-ecc-algo: string, algorithm of NAND ECC.
+		 Supported values with "hw" ECC mode are: "rs", "bch".
+- nand-bus-width : See nand.txt
+- nand-on-flash-bbt: See nand.txt
+- nand-ecc-strength: integer representing the number of bits to correct
+		     per ECC step (always 512). Supported strength using HW ECC
+		     modes are:
+		     - RS: 4, 6, 8
+		     - BCH: 4, 8, 14, 16
+- nand-ecc-maximize: See nand.txt
+- nand-is-boot-medium: Makes sure only ECC strengths supported by the boot ROM
+		       are chosen.
+- wp-gpios: GPIO specifier for the write protect pin.
+
+Optional child node of NAND chip nodes:
+Partitions: see partition.txt
+
+  Example:
+	nand-controller@70008000 {
+		compatible = "nvidia,tegra20-nand";
+		reg = <0x70008000 0x100>;
+		interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&tegra_car TEGRA20_CLK_NDFLASH>;
+		clock-names = "nand";
+		resets = <&tegra_car 13>;
+		reset-names = "nand";
+
+		nand@0 {
+			reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			nand-bus-width = <8>;
+			nand-on-flash-bbt;
+			nand-ecc-algo = "bch";
+			nand-ecc-strength = <8>;
+			wp-gpios = <&gpio TEGRA_GPIO(S, 0) GPIO_ACTIVE_LOW>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mtd/partition.txt b/Documentation/devicetree/bindings/mtd/partition.txt
index a8f382642ba9..afbbd870496d 100644
--- a/Documentation/devicetree/bindings/mtd/partition.txt
+++ b/Documentation/devicetree/bindings/mtd/partition.txt
@@ -14,6 +14,13 @@ method is used for a given flash device. To describe the method there should be
 a subnode of the flash device that is named 'partitions'. It must have a
 'compatible' property, which is used to identify the method to use.
 
+When a single partition is represented with a DT node (it depends on a used
+format) it may also be described using above rules ('compatible' and optionally
+some extra properties / subnodes). It allows describing more complex,
+hierarchical (multi-level) layouts and should be used if there is some
+significant relation between partitions or some partition internally uses
+another partitioning method.
+
 Available bindings are listed in the "partitions" subdirectory.
 
 
@@ -109,3 +116,42 @@ flash@2 {
 		};
 	};
 };
+
+flash@3 {
+	partitions {
+		compatible = "fixed-partitions";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partition@0 {
+			label = "bootloader";
+			reg = <0x000000 0x100000>;
+			read-only;
+		};
+
+		firmware@100000 {
+			label = "firmware";
+			reg = <0x100000 0xe00000>;
+			compatible = "brcm,trx";
+		};
+
+		calibration@f00000 {
+			label = "calibration";
+			reg = <0xf00000 0x100000>;
+			compatible = "fixed-partitions";
+			ranges = <0 0xf00000 0x100000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "wifi0";
+				reg = <0x000000 0x080000>;
+			};
+
+			partition@80000 {
+				label = "wifi1";
+				reg = <0x080000 0x080000>;
+			};
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt b/Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt
new file mode 100644
index 000000000000..b677147ca4e1
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt
@@ -0,0 +1,37 @@
+Broadcom TRX Container Partition
+================================
+
+TRX is Broadcom's official firmware format for the BCM947xx boards. It's used by
+most of the vendors building devices based on Broadcom's BCM47xx SoCs and is
+supported by the CFE bootloader.
+
+Design of the TRX format is very minimalistic. Its header contains
+identification fields, CRC32 checksum and the locations of embedded partitions.
+Its purpose is to store a few partitions in a format that can be distributed as
+a standalone file and written in a flash memory.
+
+Container can hold up to 4 partitions. The first partition has to contain a
+device executable binary (e.g. a kernel) as it's what the CFE bootloader starts
+executing. Other partitions can be used for operating system purposes. This is
+useful for systems that keep kernel and rootfs separated.
+
+TRX doesn't enforce any strict partition boundaries or size limits. All
+partitions have to be less than the 4GiB max size limit.
+
+There are two existing/known TRX variants:
+1) v1 which contains 3 partitions
+2) v2 which contains 4 partitions
+
+There aren't separated compatible bindings for them as version can be trivialy
+detected by a software parsing TRX header.
+
+Required properties:
+- compatible : (required) must be "brcm,trx"
+
+Example:
+
+flash@0 {
+	partitions {
+		compatible = "brcm,trx";
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/qcom_nandc.txt b/Documentation/devicetree/bindings/mtd/qcom_nandc.txt
index 73d336befa08..1123cc6d56ef 100644
--- a/Documentation/devicetree/bindings/mtd/qcom_nandc.txt
+++ b/Documentation/devicetree/bindings/mtd/qcom_nandc.txt
@@ -45,11 +45,12 @@ Required properties:
 			number (e.g., 0, 1, 2, etc.)
 - #address-cells:	see partition.txt
 - #size-cells:		see partition.txt
-- nand-ecc-strength:	see nand.txt
-- nand-ecc-step-size:	must be 512. see nand.txt for more details.
 
 Optional properties:
 - nand-bus-width:	see nand.txt
+- nand-ecc-strength:	see nand.txt. If not specified, then ECC strength will
+			be used according to chip requirement and available
+			OOB size.
 
 Each nandcs device node may optionally contain a 'partitions' sub-node, which
 further contains sub-nodes describing the flash partition mapping. See
@@ -77,7 +78,6 @@ nand-controller@1ac00000 {
 		reg = <0>;
 
 		nand-ecc-strength = <4>;
-		nand-ecc-step-size = <512>;
 		nand-bus-width = <8>;
 
 		partitions {
@@ -117,7 +117,6 @@ nand-controller@79b0000 {
 	nand@0 {
 		reg = <0>;
 		nand-ecc-strength = <4>;
-		nand-ecc-step-size = <512>;
 		nand-bus-width = <8>;
 
 		partitions {
diff --git a/Documentation/devicetree/bindings/mtd/spear_smi.txt b/Documentation/devicetree/bindings/mtd/spear_smi.txt
index 7248aadd89e4..c41873e92d26 100644
--- a/Documentation/devicetree/bindings/mtd/spear_smi.txt
+++ b/Documentation/devicetree/bindings/mtd/spear_smi.txt
@@ -5,8 +5,6 @@ Required properties:
 - reg : Address range of the mtd chip
 - #address-cells, #size-cells : Must be present if the device has sub-nodes
   representing partitions.
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the STMMAC interrupts
 - clock-rate : Functional clock rate of SMI in Hz
 
diff --git a/Documentation/devicetree/bindings/mtd/spi-nand.txt b/Documentation/devicetree/bindings/mtd/spi-nand.txt
new file mode 100644
index 000000000000..8b51f3b6d55c
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/spi-nand.txt
@@ -0,0 +1,5 @@
+SPI NAND flash
+
+Required properties:
+- compatible: should be "spi-nand"
+- reg: should encode the chip-select line used to access the NAND chip
diff --git a/Documentation/devicetree/bindings/net/amd-xgbe.txt b/Documentation/devicetree/bindings/net/amd-xgbe.txt
index 4bb624a73b54..93dcb79a5f16 100644
--- a/Documentation/devicetree/bindings/net/amd-xgbe.txt
+++ b/Documentation/devicetree/bindings/net/amd-xgbe.txt
@@ -8,8 +8,6 @@ Required properties:
    - SerDes Rx/Tx registers
    - SerDes integration registers (1/2)
    - SerDes integration registers (2/2)
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the amd-xgbe interrupt(s). The first interrupt
   listed is required and is the general device interrupt. If the optional
   amd,per-channel-interrupt property is specified, then one additional
diff --git a/Documentation/devicetree/bindings/net/btusb.txt b/Documentation/devicetree/bindings/net/btusb.txt
index 9c5e663fa1af..37d67926dd6d 100644
--- a/Documentation/devicetree/bindings/net/btusb.txt
+++ b/Documentation/devicetree/bindings/net/btusb.txt
@@ -15,7 +15,6 @@ Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
 
 Optional properties:
 
-  - interrupt-parent: phandle of the parent interrupt controller
   - interrupt-names: (see below)
   - interrupts : The interrupt specified by the name "wakeup" is the interrupt
 		 that shall be used for out-of-band wake-on-bt. Driver will
diff --git a/Documentation/devicetree/bindings/net/can/holt_hi311x.txt b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
index 23aa94eab207..903a78da65be 100644
--- a/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
+++ b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
@@ -5,7 +5,6 @@ Required properties:
    - "holt,hi3110" for HI-3110
  - reg: SPI chip select.
  - clocks: The clock feeding the CAN controller.
- - interrupt-parent: The parent interrupt controller.
  - interrupts: Should contain IRQ line for the CAN controller.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt b/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
index ee3723beb701..188c8bd4eb67 100644
--- a/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
+++ b/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
@@ -6,7 +6,6 @@ Required properties:
    - "microchip,mcp2515" for MCP2515.
  - reg: SPI chip select.
  - clocks: The clock feeding the CAN controller.
- - interrupt-parent: The parent interrupt controller.
  - interrupts: Should contain IRQ line for the CAN controller.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/net/can/xilinx_can.txt b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
index fe38847d8e26..9264d2f6a89d 100644
--- a/Documentation/devicetree/bindings/net/can/xilinx_can.txt
+++ b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
@@ -9,7 +9,6 @@ Required properties:
 			  CANPS registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
-- interrupt-parent	: Must be core interrupt controller
 - clock-names		: List of input clock names - "can_clk", "pclk"
 			  (For CANPS), "can_clk" , "s_axi_aclk"(For AXI CAN)
 			  (See clock bindings for details).
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 4cb4925a28ab..41089369f891 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -11,7 +11,6 @@ Required properties:
 			  registers map
 - interrupts		: property with a value describing the interrupt
 			  number
-- interrupt-parent	: The parent interrupt controller
 - cpdma_channels 	: Specifies number of channels in CPDMA
 - ale_entries		: Specifies No of entries ALE can hold
 - bd_ram_size		: Specifies internal descriptor RAM size
diff --git a/Documentation/devicetree/bindings/net/davicom-dm9000.txt b/Documentation/devicetree/bindings/net/davicom-dm9000.txt
index 5224bf05f6f8..64c159e9cbf7 100644
--- a/Documentation/devicetree/bindings/net/davicom-dm9000.txt
+++ b/Documentation/devicetree/bindings/net/davicom-dm9000.txt
@@ -5,7 +5,6 @@ Required properties:
 - reg : physical addresses and sizes of registers, must contain 2 entries:
     first entry : address register,
     second entry : data register.
-- interrupt-parent : interrupt controller to which the device is connected
 - interrupts : interrupt specifier specific to interrupt controller
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt
index 60d50a2b0323..feb007af13cb 100644
--- a/Documentation/devicetree/bindings/net/dsa/marvell.txt
+++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt
@@ -30,7 +30,6 @@ Required properties:
 Optional properties:
 
 - reset-gpios		: Should be a gpio specifier for a reset line
-- interrupt-parent	: Parent interrupt controller
 - interrupts		: Interrupt from the switch
 - interrupt-controller	: Indicates the switch is itself an interrupt
 			  controller. This is used for the PHY interrupts.
diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt
index df873d1f3b7c..f8c33890bc29 100644
--- a/Documentation/devicetree/bindings/net/fsl-fman.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fman.txt
@@ -238,7 +238,7 @@ PROPERTIES
 		Must include one of the following:
 		- "fsl,fman-dtsec" for dTSEC MAC
 		- "fsl,fman-xgec" for XGEC MAC
-		- "fsl,fman-memac for mEMAC MAC
+		- "fsl,fman-memac" for mEMAC MAC
 
 - cell-index
 		Usage: required
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
index abfbeecbcf39..8ee4b1cedae8 100644
--- a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
+++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
@@ -9,7 +9,6 @@ Required properties:
 		"6port-16rss",
 		"6port-16vf",
 		"single-port".
-- interrupt-parent: the interrupt parent of this device.
 - interrupts: should contain the DSA Fabric and rcb interrupt.
 - reg: specifies base physical address(es) and size of the device registers.
   The first region is external interface control register base and size(optional,
diff --git a/Documentation/devicetree/bindings/net/ibm,emac.txt b/Documentation/devicetree/bindings/net/ibm,emac.txt
index 44b842b6ca15..c0c14aa3f97c 100644
--- a/Documentation/devicetree/bindings/net/ibm,emac.txt
+++ b/Documentation/devicetree/bindings/net/ibm,emac.txt
@@ -18,7 +18,6 @@
 			  "ibm,emac4".  For Axon, thus, we have: "ibm,emac-axon",
 			  "ibm,emac4"
     - interrupts        : <interrupt mapping for EMAC IRQ and WOL IRQ>
-    - interrupt-parent  : optional, if needed for interrupt mapping
     - reg               : <registers mapping>
     - local-mac-address : 6 bytes, MAC address
     - mal-device        : phandle of the associated McMAL node
diff --git a/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt b/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
index 3d27c68613a6..957e5e5c2927 100644
--- a/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
+++ b/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
@@ -22,7 +22,6 @@ Optional properties:
   - marvell,wakeup-gap-ms: wakeup gap represents wakeup latency of the host
 		      platform. The value will be configured to firmware. This
 		      is needed to work chip's sleep feature as expected (u16).
-  - interrupt-parent: phandle of the parent interrupt controller
   - interrupt-names: Used only for USB based devices (See below)
   - interrupts : specifies the interrupt pin number to the cpu. For SDIO, the
 		 driver will use the first interrupt specified in the interrupt
diff --git a/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt b/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt
index aa6313024176..358fed2fab43 100644
--- a/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt
+++ b/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt
@@ -6,8 +6,6 @@ The mediatek gigabit switch can be found on Mediatek SoCs (mt7620, mt7621).
 Required properties:
 - compatible: Should be "mediatek,mt7620-gsw" or "mediatek,mt7621-gsw"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the gigabit switches interrupt
 - resets: Should contain the gigabit switches resets
 - reset-names: Should contain the reset names "gsw"
diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt
index 53c13ee384a4..503f2b9194e2 100644
--- a/Documentation/devicetree/bindings/net/mediatek-net.txt
+++ b/Documentation/devicetree/bindings/net/mediatek-net.txt
@@ -30,9 +30,6 @@ Required properties:
 - mediatek,pctl: phandle to the syscon node that handles the ports slew rate
 	and driver current: only for MT2701 and MT7623 SoC
 
-Optional properties:
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 * Ethernet MAC node
 
 Required properties:
diff --git a/Documentation/devicetree/bindings/net/microchip,enc28j60.txt b/Documentation/devicetree/bindings/net/microchip,enc28j60.txt
index 44dff53d4dda..24626e082b83 100644
--- a/Documentation/devicetree/bindings/net/microchip,enc28j60.txt
+++ b/Documentation/devicetree/bindings/net/microchip,enc28j60.txt
@@ -8,9 +8,6 @@ the SPI master node.
 Required properties:
 - compatible: Should be "microchip,enc28j60"
 - reg: Specify the SPI chip select the ENC28J60 is wired to
-- interrupt-parent: Specify the phandle of the source interrupt, see interrupt
-                    binding documentation for details. Usually this is the GPIO bank
-                    the interrupt line is wired to.
 - interrupts: Specify the interrupt index within the interrupt controller (referred
               to above in interrupt-parent) and interrupt type. The ENC28J60 natively
               generates falling edge interrupts, however, additional board logic
diff --git a/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt b/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt
index 92486733df71..cfaf88998918 100644
--- a/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt
+++ b/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "nxp,nxp-nci-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - enable-gpios: Output GPIO pin used for enabling/disabling the chip
 - firmware-gpios: Output GPIO pin used to enter firmware download mode
diff --git a/Documentation/devicetree/bindings/net/nfc/pn533-i2c.txt b/Documentation/devicetree/bindings/net/nfc/pn533-i2c.txt
index 122460e42e3c..2efe3886b95b 100644
--- a/Documentation/devicetree/bindings/net/nfc/pn533-i2c.txt
+++ b/Documentation/devicetree/bindings/net/nfc/pn533-i2c.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "nxp,pn532-i2c" or "nxp,pn533-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 
 Optional SoC Specific Properties:
diff --git a/Documentation/devicetree/bindings/net/nfc/pn544.txt b/Documentation/devicetree/bindings/net/nfc/pn544.txt
index 538a86f7b2b0..5b937403fed6 100644
--- a/Documentation/devicetree/bindings/net/nfc/pn544.txt
+++ b/Documentation/devicetree/bindings/net/nfc/pn544.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "nxp,pn544-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - enable-gpios: Output GPIO pin used for enabling/disabling the PN544
 - firmware-gpios: Output GPIO pin used to enter firmware download mode
diff --git a/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt b/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt
index ed5b3eaadb39..f02f6fb7f81c 100644
--- a/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt
+++ b/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: Should be "samsung,s3fwrn5-i2c".
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - s3fwrn5,en-gpios: Output GPIO pin used for enabling/disabling the chip
 - s3fwrn5,fw-gpios: Output GPIO pin used to enter firmware mode and
diff --git a/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt b/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt
index b46d473be425..baa8f8133d19 100644
--- a/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "st,st21nfcb-i2c" or "st,st21nfcc-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - reset-gpios: Output GPIO pin used to reset the ST21NFCB
 
diff --git a/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt b/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt
index 54ce8e7ac681..d33343330b94 100644
--- a/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: Should be "st,st21nfcb-spi"
 - spi-max-frequency: Maximum SPI frequency (<= 4000000).
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - reset-gpios: Output GPIO pin used to reset the ST21NFCB
 
diff --git a/Documentation/devicetree/bindings/net/nfc/st21nfca.txt b/Documentation/devicetree/bindings/net/nfc/st21nfca.txt
index 5ee9440fa9ad..b8bd90f80e12 100644
--- a/Documentation/devicetree/bindings/net/nfc/st21nfca.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st21nfca.txt
@@ -4,8 +4,6 @@ Required properties:
 - compatible: Should be "st,st21nfca-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
-- interrupts: GPIO interrupt to which the chip is connected
 - enable-gpios: Output GPIO pin used for enabling/disabling the ST21NFCA
 
 Optional SoC Specific Properties:
diff --git a/Documentation/devicetree/bindings/net/nfc/st95hf.txt b/Documentation/devicetree/bindings/net/nfc/st95hf.txt
index 08a202e00d47..3f373a1e20ff 100644
--- a/Documentation/devicetree/bindings/net/nfc/st95hf.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st95hf.txt
@@ -17,9 +17,6 @@ Required properties:
 
 - enable-gpio: GPIO line to enable ST95HF transceiver.
 
-- interrupt-parent : Standard way to specify the controller to which
-	ST95HF transceiver's interrupt is routed.
-
 - interrupts : Standard way to define ST95HF transceiver's out
 	interrupt.
 
diff --git a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
index 5ca9362ef127..ba1934b950e5 100644
--- a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
+++ b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: Should be "ti,trf7970a".
 - spi-max-frequency: Maximum SPI frequency (<= 2000000).
-- interrupt-parent: phandle of parent interrupt handler.
 - interrupts: A single interrupt specifier.
 - ti,enable-gpios: One or two GPIO entries used for 'EN' and 'EN2' pins on the
   TRF7970A. EN2 is optional.
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index d2169a56f5e3..17c1d2bd00f6 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -3,8 +3,6 @@ PHY nodes
 Required properties:
 
  - interrupts : interrupt specifier for the sole interrupt.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
  - reg : The ID number for the phy, usually a small integer
 
 Optional Properties:
diff --git a/Documentation/devicetree/bindings/net/qca,qca7000.txt b/Documentation/devicetree/bindings/net/qca,qca7000.txt
index 3987846b3fd3..e4a8a51086df 100644
--- a/Documentation/devicetree/bindings/net/qca,qca7000.txt
+++ b/Documentation/devicetree/bindings/net/qca,qca7000.txt
@@ -19,7 +19,6 @@ Required properties:
 - spi-cpol	    : Must be set
 
 Optional properties:
-- interrupt-parent  : Specify the pHandle of the source interrupt
 - spi-max-frequency : Maximum frequency of the SPI bus the chip can operate at.
 		      Numbers smaller than 1000000 or greater than 16000000
 		      are invalid. Missing the property will set the SPI
diff --git a/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt b/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt
index 88b095d1f13b..9fe1a0a22e44 100644
--- a/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt
+++ b/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt
@@ -14,8 +14,6 @@ Required properties:
   "ralink,rt3050-eth", "ralink,rt3883-eth", "ralink,rt5350-eth",
   "mediatek,mt7620-eth", "mediatek,mt7621-eth"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the frame engines interrupt
 - resets: Should contain the frame engines resets
 - reset-names: Should contain the reset names "fe". If a switch is present
diff --git a/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt b/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt
index 2e79bd376c56..87e315856efa 100644
--- a/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt
+++ b/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt
@@ -7,8 +7,6 @@ SoCs (RT3x5x, RT5350, MT76x8).
 Required properties:
 - compatible: Should be "ralink,rt3050-esw"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the embedded switches interrupt
 - resets: Should contain the embedded switches resets
 - reset-names: Should contain the reset names "esw"
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index fac897d54423..19740d01cab0 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -47,8 +47,6 @@ Required properties:
 - pinctrl-0: phandle, referring to a default pin configuration node.
 
 Optional properties:
-- interrupt-parent: the phandle for the interrupt controller that services
-		    interrupts for this device.
 - interrupt-names: A list of interrupt names.
 		   For the R-Car Gen 3 SoCs this property is mandatory;
 		   it should include one entry per channel, named "ch%u",
diff --git a/Documentation/devicetree/bindings/net/samsung-sxgbe.txt b/Documentation/devicetree/bindings/net/samsung-sxgbe.txt
index 888c250197fe..46e591178911 100644
--- a/Documentation/devicetree/bindings/net/samsung-sxgbe.txt
+++ b/Documentation/devicetree/bindings/net/samsung-sxgbe.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: Should be "samsung,sxgbe-v2.0a"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the SXGBE interrupts
   These interrupts are ordered by fixed and follows variable
   trasmit DMA interrupts, receive DMA interrupts and lpi interrupt.
diff --git a/Documentation/devicetree/bindings/net/sh_eth.txt b/Documentation/devicetree/bindings/net/sh_eth.txt
index 82a4cf2c145d..76db9f13ad96 100644
--- a/Documentation/devicetree/bindings/net/sh_eth.txt
+++ b/Documentation/devicetree/bindings/net/sh_eth.txt
@@ -35,8 +35,6 @@ Required properties:
 - pinctrl-0: phandle, referring to a default pin configuration node.
 
 Optional properties:
-- interrupt-parent: the phandle for the interrupt controller that services
-		    interrupts for this device.
 - pinctrl-names: pin configuration state name ("default").
 - renesas,no-ether-link: boolean, specify when a board does not provide a proper
 			 Ether LINK signal.
diff --git a/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt b/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
index 21d27aa4c68c..36f1aef585f0 100644
--- a/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
+++ b/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
@@ -83,8 +83,6 @@ Required properties:
   - "snps,dwc-qos-ethernet-4.10" (deprecated):
     - "phy_ref_clk"
     - "apb_clk"
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the core's combined interrupt signal
 - phy-mode: See ethernet.txt file in the same directory
 - resets: Phandle and reset specifiers for each entry in reset-names, in the
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 3a28a5d8857d..8bdb1c231d08 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -4,8 +4,6 @@ Required properties:
 - compatible: Should be "snps,dwmac-<ip_version>", "snps,dwmac"
 	For backwards compatibility: "st,spear600-gmac" is also supported.
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the STMMAC interrupts
 - interrupt-names: Should contain a list of interrupt names corresponding to
 	the interrupts in the interrupts property, if available.
diff --git a/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt b/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt
index 86602f264dce..cffb2d6876e3 100644
--- a/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt
+++ b/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt
@@ -11,8 +11,6 @@ Required properties:
 Optional properties:
  - brcm,drive-strength : drive strength used for SDIO pins on device in mA
 	(default = 6).
- - interrupt-parent : the phandle for the interrupt controller to which the
-	device interrupts are connected.
  - interrupts : specifies attributes for the out-of-band interrupt (host-wake).
 	When not specified the device will use in-band SDIO interrupts.
  - interrupt-names : name of the out-of-band interrupt, which must be set
diff --git a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt b/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
index 59de8646862d..9bf9bbac16e2 100644
--- a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
+++ b/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
@@ -29,7 +29,6 @@ Optional properties:
   - marvell,wakeup-pin : a wakeup pin number of wifi chip which will be configured
 		      to firmware. Firmware will wakeup the host using this pin
 		      during suspend/resume.
-  - interrupt-parent: phandle of the parent interrupt controller
   - interrupts : interrupt pin number to the cpu. driver will request an irq based on
 		 this interrupt number. during system suspend, the irq will be enabled
 		 so that the wifi chip can wakeup host platform under certain condition.
diff --git a/Documentation/devicetree/bindings/net/wireless/ti,wl1251.txt b/Documentation/devicetree/bindings/net/wireless/ti,wl1251.txt
index 189ae5cad8f7..bb2fcde6f7ff 100644
--- a/Documentation/devicetree/bindings/net/wireless/ti,wl1251.txt
+++ b/Documentation/devicetree/bindings/net/wireless/ti,wl1251.txt
@@ -8,8 +8,6 @@ Required properties:
 - reg :               Chip select address of device
 - spi-max-frequency : Maximum SPI clocking speed of device in Hz
 - interrupts :        Should contain interrupt line
-- interrupt-parent :  Should be the phandle for the interrupt controller
-                      that services interrupts for this device
 - vio-supply :        phandle to regulator providing VIO
 - ti,power-gpio :     GPIO connected to chip's PMEN pin
 
diff --git a/Documentation/devicetree/bindings/net/wireless/ti,wlcore,spi.txt b/Documentation/devicetree/bindings/net/wireless/ti,wlcore,spi.txt
index 8f9ced076fe1..cb5c9e1569ca 100644
--- a/Documentation/devicetree/bindings/net/wireless/ti,wlcore,spi.txt
+++ b/Documentation/devicetree/bindings/net/wireless/ti,wlcore,spi.txt
@@ -17,9 +17,7 @@ Required properties:
     * "ti,wl1837"
 - reg :                 Chip select address of device
 - spi-max-frequency :   Maximum SPI clocking speed of device in Hz
-- interrupt-parent, interrupts :
-                        Should contain parameters for 1 interrupt line.
-                        Interrupt parameters: parent, line number, type.
+- interrupts :          Should contain parameters for 1 interrupt line.
 - vwlan-supply :        Point the node of the regulator that powers/enable the
                         wl12xx/wl18xx chip
 
diff --git a/Documentation/devicetree/bindings/net/wireless/ti,wlcore.txt b/Documentation/devicetree/bindings/net/wireless/ti,wlcore.txt
index f42f6b0f1bc7..9306c4dadd46 100644
--- a/Documentation/devicetree/bindings/net/wireless/ti,wlcore.txt
+++ b/Documentation/devicetree/bindings/net/wireless/ti,wlcore.txt
@@ -20,8 +20,6 @@ Required properties:
  - interrupts : specifies attributes for the out-of-band interrupt.
 
 Optional properties:
- - interrupt-parent : the phandle for the interrupt controller to which the
-	device interrupts are connected.
  - ref-clock-frequency : ref clock frequency in Hz
  - tcxo-clock-frequency : tcxo clock frequency in Hz
 
diff --git a/Documentation/devicetree/bindings/pci/altera-pcie-msi.txt b/Documentation/devicetree/bindings/pci/altera-pcie-msi.txt
index 09cd3bc4d038..9514c327d31b 100644
--- a/Documentation/devicetree/bindings/pci/altera-pcie-msi.txt
+++ b/Documentation/devicetree/bindings/pci/altera-pcie-msi.txt
@@ -7,7 +7,6 @@ Required properties:
 - reg-names:	must include the following entries:
 		"csr": CSR registers
 		"vector_slave": vectors slave port region
-- interrupt-parent:	interrupt source phandle.
 - interrupts:	specifies the interrupt source of the parent interrupt
 		controller. The format of the interrupt specifier depends on the
 		parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/pci/altera-pcie.txt b/Documentation/devicetree/bindings/pci/altera-pcie.txt
index a1dc9366a8fc..6c396f17c91a 100644
--- a/Documentation/devicetree/bindings/pci/altera-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/altera-pcie.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg-names:	must include the following entries:
 		"Txs": TX slave port region
 		"Cra": Control register access region
-- interrupt-parent:	interrupt source phandle.
 - interrupts:	specifies the interrupt source of the parent interrupt
 		controller.  The format of the interrupt specifier depends
 		on the parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt b/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt
index b8e48b4762b2..df065aa53a83 100644
--- a/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt
@@ -65,7 +65,6 @@ When the iProc event queue based MSI is used, one needs to define the
 following properties in the MSI device node:
 - compatible: Must be "brcm,iproc-msi"
 - msi-controller: claims itself as an MSI controller
-- interrupt-parent: Link to its parent interrupt device
 - interrupts: List of interrupt IDs from its parent interrupt device
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/pci/faraday,ftpci100.txt b/Documentation/devicetree/bindings/pci/faraday,ftpci100.txt
index 89a84f8aa621..5f8cb4962f8d 100644
--- a/Documentation/devicetree/bindings/pci/faraday,ftpci100.txt
+++ b/Documentation/devicetree/bindings/pci/faraday,ftpci100.txt
@@ -41,7 +41,6 @@ Mandatory subnodes:
 - For "faraday,ftpci100" a node representing the interrupt-controller inside the
   host bridge is mandatory. It has the following mandatory properties:
   - interrupt: see interrupt-controller/interrupts.txt
-  - interrupt-parent: see interrupt-controller/interrupts.txt
   - interrupt-controller: see interrupt-controller/interrupts.txt
   - #address-cells: set to <0>
   - #interrupt-cells: set to <1>
diff --git a/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt b/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
index 65038aa642e5..a618d4787dd7 100644
--- a/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
@@ -26,9 +26,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an
 	interrupt source. The value must be 1.
-- interrupt-parent : phandle to the interrupt controller that
-		it is attached to, it should be set to gic to point to
-		ARM's Generic Interrupt Controller node in system DT.
 - interrupts: The interrupt line of the PCIe controller
 		last cell of this field is set to 4 to
 		denote it as IRQ_TYPE_LEVEL_HIGH type interrupt.
diff --git a/Documentation/devicetree/bindings/pci/pci-keystone.txt b/Documentation/devicetree/bindings/pci/pci-keystone.txt
index 3d4a209b0fd0..4dd17de549a7 100644
--- a/Documentation/devicetree/bindings/pci/pci-keystone.txt
+++ b/Documentation/devicetree/bindings/pci/pci-keystone.txt
@@ -17,7 +17,6 @@ reg:	index 1 is the base address and length of DW application registers.
 
 pcie_msi_intc : Interrupt controller device node for MSI IRQ chip
 	interrupt-cells: should be set to 1
-	interrupt-parent: Parent interrupt controller phandle
 	interrupts: GIC interrupt lines connected to PCI MSI interrupt lines
 
  Example:
@@ -37,8 +36,6 @@ pcie_msi_intc : Interrupt controller device node for MSI IRQ chip
 
 pcie_intc: Interrupt controller device node for Legacy IRQ chip
 	interrupt-cells: should be set to 1
-	interrupt-parent: Parent interrupt controller phandle
-	interrupts: GIC interrupt lines connected to PCI Legacy interrupt lines
 
  Example:
 	pcie_intc: legacy-interrupt-controller {
diff --git a/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt b/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
index a04ab1b76211..ffba4f63d71f 100644
--- a/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
+++ b/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
@@ -41,9 +41,6 @@
    - #interrupt-cells: specifies the number of cells needed to encode an
      interrupt source. The value must be 1.
 
-   - interrupt-parent: the phandle for the interrupt controller that
-     services interrupts for this device.
-
    - interrupts: specifies the interrupt source of the parent interrupt
      controller. The format of the interrupt specifier depends on the
      parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt b/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
index cafe2197dad9..c3a29c5feea3 100644
--- a/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
+++ b/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
@@ -3,7 +3,7 @@
 Required properties:
 - compatible: "qca,ar7100-usb-phy"
 - #phys-cells: should be 0
-- reset-names: "usb-phy"[, "usb-suspend-override"]
+- reset-names: "phy"[, "suspend-override"]
 - resets: references to the reset controllers
 
 Example:
@@ -11,7 +11,7 @@ Example:
 	usb-phy {
 		compatible = "qca,ar7100-usb-phy";
 
-		reset-names = "usb-phy", "usb-suspend-override";
+		reset-names = "phy", "suspend-override";
 		resets = <&rst 4>, <&rst 3>;
 
 		#phy-cells = <0>;
diff --git a/Documentation/devicetree/bindings/pinctrl/actions,s900-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/actions,s900-pinctrl.txt
index 8fb5a53775e8..81b58dddd3ed 100644
--- a/Documentation/devicetree/bindings/pinctrl/actions,s900-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/actions,s900-pinctrl.txt
@@ -19,6 +19,10 @@ Required Properties:
                     defines the interrupt number, the second encodes
                     the trigger flags described in
                     bindings/interrupt-controller/interrupts.txt
+- interrupts: The interrupt outputs from the controller. There is one GPIO
+              interrupt per GPIO bank. The number of interrupts listed depends
+              on the number of GPIO banks on the SoC. The interrupts must be
+              ordered by bank, starting with bank 0.
 
 Please refer to pinctrl-bindings.txt in this directory for details of the
 common pinctrl bindings used by client devices, including the meaning of the
@@ -180,6 +184,12 @@ Example:
                   #gpio-cells = <2>;
                   interrupt-controller;
                   #interrupt-cells = <2>;
+                  interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
 
                   uart2-default: uart2-default {
                           pinmux {
diff --git a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt
index 61ac75706cc9..04d16fb69eb7 100644
--- a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt
@@ -36,6 +36,8 @@ Optional properties:
 - GENERIC_PINCONFIG: generic pinconfig options to use, bias-disable,
 bias-pull-down, bias-pull-up, drive-open-drain, input-schmitt-enable,
 input-debounce, output-low, output-high.
+- atmel,drive-strength: 0 or 1 for low drive, 2 for medium drive and 3 for
+high drive. The default value is low drive.
 
 Example:
 
@@ -66,6 +68,7 @@ Example:
 			pinmux = <PIN_PB0>,
 				 <PIN_PB5>;
 			bias-pull-up;
+			atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>;
 		};
 
 		pinctrl_sdmmc1_default: sdmmc1_default {
diff --git a/Documentation/devicetree/bindings/pinctrl/berlin,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/berlin,pinctrl.txt
index f8fa28ce163e..0a2d5516e1f3 100644
--- a/Documentation/devicetree/bindings/pinctrl/berlin,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/berlin,pinctrl.txt
@@ -23,7 +23,8 @@ Required properties:
 	"marvell,berlin2q-system-pinctrl",
 	"marvell,berlin4ct-avio-pinctrl",
 	"marvell,berlin4ct-soc-pinctrl",
-	"marvell,berlin4ct-system-pinctrl"
+	"marvell,berlin4ct-system-pinctrl",
+	"syna,as370-soc-pinctrl"
 
 Required subnode-properties:
 - groups: a list of strings describing the group names.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx8mq-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx8mq-pinctrl.txt
new file mode 100644
index 000000000000..66de75090458
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx8mq-pinctrl.txt
@@ -0,0 +1,36 @@
+* Freescale IMX8MQ IOMUX Controller
+
+Please refer to fsl,imx-pinctrl.txt and pinctrl-bindings.txt in this directory
+for common binding part and usage.
+
+Required properties:
+- compatible: "fsl,imx8mq-iomuxc"
+- reg: should contain the base physical address and size of the iomuxc
+  registers.
+
+Required properties in sub-nodes:
+- fsl,pins: each entry consists of 6 integers and represents the mux and config
+  setting for one pin.  The first 5 integers <mux_reg conf_reg input_reg mux_val
+  input_val> are specified using a PIN_FUNC_ID macro, which can be found in
+  imx8mq-pinfunc.h under device tree source folder.  The last integer CONFIG is
+  the pad setting value like pull-up on this pin.  Please refer to i.MX8M Quad
+  Reference Manual for detailed CONFIG settings.
+
+Examples:
+
+&uart1 {
+       pinctrl-names = "default";
+       pinctrl-0 = <&pinctrl_uart1>;
+};
+
+iomuxc: pinctrl@30330000 {
+        compatible = "fsl,imx8mq-iomuxc";
+        reg = <0x0 0x30330000 0x0 0x10000>;
+
+        pinctrl_uart1: uart1grp {
+                fsl,pins = <
+                        MX8MQ_IOMUXC_UART1_RXD_UART1_DCE_RX             0x49
+                        MX8MQ_IOMUXC_UART1_TXD_UART1_DCE_TX             0x49
+                >;
+        };
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt
index ecb5c0d25218..f4d06bb0b55a 100644
--- a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt
+++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt
@@ -17,7 +17,7 @@ Tegra124 adds the following optional properties for pin configuration subnodes.
 The macros for options are defined in the
 	include/dt-binding/pinctrl/pinctrl-tegra.h.
 - nvidia,enable-input: Integer. Enable the pin's input path.
-		enable :TEGRA_PIN_ENABLE0 and
+		enable :TEGRA_PIN_ENABLE and
 		disable or output only: TEGRA_PIN_DISABLE.
 - nvidia,open-drain: Integer.
 		enable: TEGRA_PIN_ENABLE.
diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra210-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra210-pinmux.txt
index a62d82d5fbe9..85f211436b8e 100644
--- a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra210-pinmux.txt
+++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra210-pinmux.txt
@@ -44,7 +44,7 @@ Optional subnode-properties:
 - nvidia,tristate: Integer.
     0: drive, 1: tristate.
 - nvidia,enable-input: Integer. Enable the pin's input path.
-    enable :TEGRA_PIN_ENABLE0 and
+    enable :TEGRA_PIN_ENABLE and
     disable or output only: TEGRA_PIN_DISABLE.
 - nvidia,open-drain: Integer.
     enable: TEGRA_PIN_ENABLE.
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt7622.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt7622.txt
index def8fcad8941..3b695131c51b 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt7622.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt7622.txt
@@ -16,8 +16,6 @@ If the property interrupt-controller is defined, following property is required
 - reg-names: A string describing the "reg" entries. Must contain "eint".
 - interrupts : The interrupt output from the controller.
 - #interrupt-cells: Should be two.
-- interrupt-parent: Phandle of the interrupt parent to which the external
-  GPIO interrupts are forwarded to.
 
 Please refer to pinctrl-bindings.txt in this directory for details of the
 common pinctrl bindings used by client devices, including the meaning of the
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-sx150x.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-sx150x.txt
index bf76867168e9..4023bad2fe39 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-sx150x.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-sx150x.txt
@@ -25,8 +25,6 @@ Required properties:
 - gpio-controller: Marks the device as a GPIO controller.
 
 Optional properties :
-- interrupt-parent: phandle of the parent interrupt controller.
-
 - interrupts: Interrupt specifier for the controllers interrupt.
 
 - interrupt-controller: Marks the device as a interrupt controller.
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
index a752a4716486..c2dbb3e8d840 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
@@ -10,6 +10,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -67,6 +72,7 @@ Example:
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&gsbi5_uart_default>;
+		gpio-ranges = <&msmgpio 0 0 90>;
 
 		gsbi5_uart_default: gsbi5_uart_default {
 			mux {
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,apq8084-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,apq8084-pinctrl.txt
index c4ea61ac56f2..68e93d5b7ede 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,apq8084-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,apq8084-pinctrl.txt
@@ -40,6 +40,14 @@ MSM8960 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -154,6 +162,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&tlmm 0 0 147>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 208 0>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt
index 93374f478b9e..991be0cd0948 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt
@@ -13,6 +13,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -64,6 +69,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&tlmm 0 0 100>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 208 0>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8064-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8064-pinctrl.txt
index 6e88e91feb11..7ed56a1b70fc 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8064-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8064-pinctrl.txt
@@ -10,6 +10,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -67,6 +72,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&pinmux 0 0 69>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 32 0x4>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.txt
index 407b9443629d..6dd72f8599e9 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.txt
@@ -40,6 +40,14 @@ IPQ8074 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -148,6 +156,7 @@ Example:
 		interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&tlmm 0 0 70>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.txt
index 1b52f01ddcb7..86ecdcfc4fb8 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.txt
@@ -40,6 +40,14 @@ MDM9615 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -127,6 +135,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 88>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 16 0x4>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt
index df9a838ec5f9..cdc4787e59d2 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt
@@ -10,6 +10,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -62,6 +67,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 173>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 16 0x4>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.txt
index 498caff6029e..195a7a0ef0cc 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.txt
@@ -40,6 +40,14 @@ MSM8916 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -162,6 +170,7 @@ Example:
 		interrupts = <0 208 0>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&tlmm 0 0 122>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.txt
index eb8d8aa41f20..5034eb6653c7 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.txt
@@ -40,6 +40,14 @@ MSM8960 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -156,6 +164,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 152>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 16 0x4>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt
index 453bd7c76d6b..c22e6c425d0b 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt
@@ -10,6 +10,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -87,6 +92,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 146>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 208 0>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.txt
index 13cd629f896e..f15443f6e78e 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.txt
@@ -42,6 +42,14 @@ MSM8994 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -160,6 +168,7 @@ Example:
 		interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 146>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
index aaf01e929eea..fa97f609fe45 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
@@ -40,6 +40,14 @@ MSM8996 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -180,6 +188,7 @@ Example:
 		reg = <0x01010000 0x300000>;
 		interrupts = <0 208 0>;
 		gpio-controller;
+		gpio-ranges = <&tlmm 0 0 150>;
 		#gpio-cells = <2>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
index 5c25fcb29fb5..ffd4345415f3 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
@@ -7,6 +7,7 @@ PMIC's from Qualcomm.
 	Usage: required
 	Value type: <string>
 	Definition: must be one of:
+		    "qcom,pm8005-gpio"
 		    "qcom,pm8018-gpio"
 		    "qcom,pm8038-gpio"
 		    "qcom,pm8058-gpio"
@@ -15,7 +16,7 @@ PMIC's from Qualcomm.
 		    "qcom,pm8921-gpio"
 		    "qcom,pm8941-gpio"
 		    "qcom,pm8994-gpio"
-		    "qcom,pmi8994-gpio"
+		    "qcom,pm8998-gpio"
 		    "qcom,pma8084-gpio"
 		    "qcom,pmi8994-gpio"
 
@@ -78,6 +79,7 @@ to specify in a pin configuration subnode:
 	Value type: <string-array>
 	Definition: List of gpio pins affected by the properties specified in
 		    this subnode.  Valid pins are:
+		    gpio1-gpio4 for pm8005
 		    gpio1-gpio6 for pm8018
 		    gpio1-gpio12 for pm8038
 		    gpio1-gpio40 for pm8058
@@ -86,7 +88,7 @@ to specify in a pin configuration subnode:
 		    gpio1-gpio44 for pm8921
 		    gpio1-gpio36 for pm8941
 		    gpio1-gpio22 for pm8994
-		    gpio1-gpio10 for pmi8994
+		    gpio1-gpio26 for pm8998
 		    gpio1-gpio22 for pma8084
 		    gpio1-gpio10 for pmi8994
 
diff --git a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
index 5e00a21de2bf..70659c917bdc 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
@@ -124,8 +124,6 @@ used as system wakeup events.
 A. External GPIO Interrupts: For supporting external gpio interrupts, the
    following properties should be specified in the pin-controller device node.
 
-   - interrupt-parent: phandle of the interrupt parent to which the external
-     GPIO interrupts are forwarded to.
    - interrupts: interrupt specifier for the controller. The format and value of
      the interrupt specifier depends on the interrupt parent for the controller.
 
@@ -145,8 +143,13 @@ A. External GPIO Interrupts: For supporting external gpio interrupts, the
 
 B. External Wakeup Interrupts: For supporting external wakeup interrupts, a
    child node representing the external wakeup interrupt controller should be
-   included in the pin-controller device node. This child node should include
-   the following properties.
+   included in the pin-controller device node.
+
+   Only one pin-controller device node can include external wakeup interrupts
+   child node (in other words, only one External Wakeup Interrupts
+   pin-controller is supported).
+
+   This child node should include following properties:
 
    - compatible: identifies the type of the external wakeup interrupt controller
      The possible values are:
@@ -156,12 +159,12 @@ B. External Wakeup Interrupts: For supporting external wakeup interrupts, a
        found on Samsung S3C2412 and S3C2413 SoCs,
      - samsung,s3c64xx-wakeup-eint: represents wakeup interrupt controller
        found on Samsung S3C64xx SoCs,
+     - samsung,s5pv210-wakeup-eint: represents wakeup interrupt controller
+       found on Samsung S5Pv210 SoCs,
      - samsung,exynos4210-wakeup-eint: represents wakeup interrupt controller
        found on Samsung Exynos4210 and S5PC110/S5PV210 SoCs.
      - samsung,exynos7-wakeup-eint: represents wakeup interrupt controller
        found on Samsung Exynos7 SoC.
-   - interrupt-parent: phandle of the interrupt parent to which the external
-     wakeup interrupts are forwarded to.
    - interrupts: interrupt used by multiplexed wakeup interrupts.
 
    In addition, following properties must be present in node of every bank
@@ -181,8 +184,6 @@ B. External Wakeup Interrupts: For supporting external wakeup interrupts, a
    Node of every bank of pins supporting direct wake-up interrupts (without
    multiplexing) must contain following properties:
 
-   - interrupt-parent: phandle of the interrupt parent to which the external
-     wakeup interrupts are forwarded to.
    - interrupts: interrupts of the interrupt parent which are used for external
      wakeup interrupts from pins of the bank, must contain interrupts for all
      pins of the bank.
diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
index 9a06e1fdbc42..ef4f2ff4a1aa 100644
--- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
@@ -37,11 +37,10 @@ Required properties:
 
 Optional properties:
  - reset:	  : Reference to the reset controller
- - interrupt-parent: phandle of the interrupt parent to which the external
-   GPIO interrupts are forwarded to.
- - st,syscfg: Should be phandle/offset pair. The phandle to the syscon node
-   which includes IRQ mux selection register, and the offset of the IRQ mux
-   selection register.
+ - st,syscfg: Should be phandle/offset/mask.
+	-The phandle to the syscon node which includes IRQ mux selection register.
+	-The offset of the IRQ mux selection register
+	-The field mask of IRQ mux, needed if different of 0xf.
  - gpio-ranges: Define a dedicated mapping between a pin-controller and
    a gpio controller. Format is <&phandle a b c> with:
 	-(phandle): phandle of pin-controller.
@@ -55,6 +54,8 @@ Optional properties:
    NOTE: If "gpio-ranges" is used for a gpio controller, all gpio-controller
    have to use a "gpio-ranges" entry.
    More details in Documentation/devicetree/bindings/gpio/gpio.txt.
+ - st,bank-ioport: should correspond to the EXTI IOport selection (EXTI line
+   used to select GPIOs as interrupts).
 
 Example 1:
 #include <dt-bindings/pinctrl/stm32f429-pinfunc.h>
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index 9b387f861aed..8f8b25a24b8f 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -114,18 +114,26 @@ Required properties:
  - power-domains : A list of PM domain specifiers, as defined by bindings of
 		the power controller that is the PM domain provider.
 
+Optional properties:
+ - power-domain-names : A list of power domain name strings sorted in the same
+		order as the power-domains property. Consumers drivers will use
+		power-domain-names to match power domains with power-domains
+		specifiers.
+
 Example:
 
 	leaky-device@12350000 {
 		compatible = "foo,i-leak-current";
 		reg = <0x12350000 0x1000>;
 		power-domains = <&power 0>;
+		power-domain-names = "io";
 	};
 
 	leaky-device@12351000 {
 		compatible = "foo,i-leak-current";
 		reg = <0x12351000 0x1000>;
 		power-domains = <&power 0>, <&power 1> ;
+		power-domain-names = "io", "clk";
 	};
 
 The first example above defines a typical PM domain consumer device, which is
@@ -133,7 +141,7 @@ located inside a PM domain with index 0 of a power controller represented by a
 node with the label "power".
 In the second example the consumer device are partitioned across two PM domains,
 the first with index 0 and the second with index 1, of a power controller that
-is represented by a node with the label "power.
+is represented by a node with the label "power".
 
 Optional properties:
 - required-opps: This contains phandle to an OPP node in another device's OPP
diff --git a/Documentation/devicetree/bindings/power/supply/act8945a-charger.txt b/Documentation/devicetree/bindings/power/supply/act8945a-charger.txt
index b86ecada4f84..c7dfb7cecf40 100644
--- a/Documentation/devicetree/bindings/power/supply/act8945a-charger.txt
+++ b/Documentation/devicetree/bindings/power/supply/act8945a-charger.txt
@@ -9,8 +9,6 @@ Required properties:
  - interrupts: <a b> where a is the interrupt number and b is a
    field that represents an encoding of the sense and level
    information for the interrupt.
- - interrupt-parent: the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Optional properties:
  - active-semi,input-voltage-threshold-microvolt: unit: mV;
diff --git a/Documentation/devicetree/bindings/power/supply/bq24257.txt b/Documentation/devicetree/bindings/power/supply/bq24257.txt
index d693702c9c1e..f8f5a1685bb9 100644
--- a/Documentation/devicetree/bindings/power/supply/bq24257.txt
+++ b/Documentation/devicetree/bindings/power/supply/bq24257.txt
@@ -6,8 +6,6 @@ Required properties:
  * "ti,bq24251"
  * "ti,bq24257"
 - reg: integer, i2c address of the device.
-- interrupt-parent: Should be the phandle for the interrupt controller. Use in
-    conjunction with "interrupts".
 - interrupts: Interrupt mapping for GPIO IRQ (configure for both edges). Use in
     conjunction with "interrupt-parent".
 - ti,battery-regulation-voltage: integer, maximum charging voltage in uV.
diff --git a/Documentation/devicetree/bindings/power/supply/lp8727_charger.txt b/Documentation/devicetree/bindings/power/supply/lp8727_charger.txt
index 2246bc5c874b..0355a4b68f79 100644
--- a/Documentation/devicetree/bindings/power/supply/lp8727_charger.txt
+++ b/Documentation/devicetree/bindings/power/supply/lp8727_charger.txt
@@ -5,7 +5,6 @@ Required properties:
 - reg: I2C slave address 27h
 
 Optional properties:
-- interrupt-parent: interrupt controller node (see interrupt binding[0])
 - interrupts: interrupt specifier (see interrupt binding[0])
 - debounce-ms: interrupt debounce time. (u32)
 
diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max14656.txt b/Documentation/devicetree/bindings/power/supply/maxim,max14656.txt
index d6e8dfd0a581..f956247d493e 100644
--- a/Documentation/devicetree/bindings/power/supply/maxim,max14656.txt
+++ b/Documentation/devicetree/bindings/power/supply/maxim,max14656.txt
@@ -3,7 +3,6 @@ Maxim MAX14656 / AL32 USB Charger Detector
 Required properties :
 - compatible : "maxim,max14656";
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: interrupt line
 
 Example:
diff --git a/Documentation/devicetree/bindings/power/supply/rt9455_charger.txt b/Documentation/devicetree/bindings/power/supply/rt9455_charger.txt
index 5d9ad5cf2c5a..1e6107c7578e 100644
--- a/Documentation/devicetree/bindings/power/supply/rt9455_charger.txt
+++ b/Documentation/devicetree/bindings/power/supply/rt9455_charger.txt
@@ -4,8 +4,6 @@ Required properties:
 - compatible:				it should contain one of the following:
 					"richtek,rt9455".
 - reg:					integer, i2c address of the device.
-- interrupt-parent:			the phandle for the interrupt controller that
-					services interrupts for this device.
 - interrupts:				interrupt mapping for GPIO IRQ, it should be
 					configured with IRQ_TYPE_LEVEL_LOW flag.
 - richtek,output-charge-current:	integer, output current from the charger to the
diff --git a/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
index a3719623a94f..84e74151eef2 100644
--- a/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
+++ b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
@@ -7,8 +7,6 @@ Required properties:
      specific registers.
 
 Optional properties:
-- interrupt-parent: Should be the phandle for the interrupt controller. Use in
-    conjunction with "interrupts".
 - interrupts: Interrupt mapping for GPIO IRQ. Use in conjunction with
     "interrupt-parent". If an interrupt is not provided the driver will switch
     automatically to polling.
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt b/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt
index db939210e29d..940fd78e3363 100644
--- a/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt
+++ b/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt
@@ -19,7 +19,6 @@ The IBM Akebono board is a development board for the PPC476GTR SoC.
 
    - compatible : should be "ibm,476gtr-sdhci","generic-sdhci".
    - reg : should contain the SDHCI registers location and length.
-   - interrupt-parent : a phandle for the interrupt controller.
    - interrupts : should contain the SDHCI interrupt.
 
 1.b) The Advanced Host Controller Interface (AHCI) SATA node
@@ -30,7 +29,6 @@ The IBM Akebono board is a development board for the PPC476GTR SoC.
 
    - compatible : should be "ibm,476gtr-ahci".
    - reg : should contain the AHCI registers location and length.
-   - interrupt-parent : a phandle for the interrupt controller.
    - interrupts : should contain the AHCI interrupt.
 
 1.c) The FPGA node
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt b/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt
index c737c8338705..66dbd9ff56f7 100644
--- a/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt
+++ b/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt
@@ -13,7 +13,6 @@ device tree entries:
 Require properties:
 - compatible		: "ibm,476gtr-hsta-msi", "ibm,hsta-msi"
 - reg			: register mapping for the HSTA MSI space
-- interrupt-parent	: parent controller for mapping interrupts
 - interrupts		: ordered interrupt mapping for each MSI in the register
 			  space. The first interrupt should be associated with a
 			  register offset of 0x00, the second to 0x10, etc.
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt b/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt
index 515ebcf1b97d..de6a5f7d4aa4 100644
--- a/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt
+++ b/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt
@@ -38,7 +38,6 @@ DMA devices.
 			   2 sources: DMAx CS FIFO Needs Service IRQ (on UIC0)
 			   and DMA Error IRQ (on UIC1). The latter is common
 			   for both DMA engines>.
- - interrupt-parent	: needed for interrupt mapping
 
  Example:
 
@@ -65,7 +64,6 @@ DMA devices.
  - compatible		: "amcc,xor-accelerator";
  - reg			: <registers mapping>
  - interrupts		: <interrupt mapping for XOR interrupt source>
- - interrupt-parent	: for interrupt mapping
 
  Example:
 
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/dcsr.txt b/Documentation/devicetree/bindings/powerpc/fsl/dcsr.txt
index 18a88100af94..4b01e1afafda 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/dcsr.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/dcsr.txt
@@ -84,13 +84,6 @@ PROPERTIES
 
 	Interrupt numbers are listed in order (perfmon, event0, event1).
 
-	- interrupt-parent
-	Usage: required
-	Value type: <phandle>
-	Definition: A single <phandle> value that points
-	to the interrupt parent to which the child domain
-	is being mapped. Value must be "&mpic"
-
 	- reg
 	Usage: required
 	Value type: <prop-encoded-array>
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/diu.txt b/Documentation/devicetree/bindings/powerpc/fsl/diu.txt
index b66cb6d31d69..eb45db1ecee5 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/diu.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/diu.txt
@@ -8,8 +8,6 @@ Required properties:
 - reg : should contain at least address and length of the DIU register
   set.
 - interrupts : one DIU interrupt should be described here.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 
 Optional properties:
 - edid : verbatim EDID data block describing attached display.
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/dma.txt b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
index 7fc1b010fa75..c11ad5c6db21 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
@@ -13,7 +13,6 @@ Required properties:
                       DMA channels and the address space of the DMA controller
 - cell-index        : controller index.  0 for controller @ 0x8100
 - interrupts        : interrupt specifier for DMA IRQ
-- interrupt-parent  : optional, if needed for interrupt mapping
 
 - DMA channel nodes:
         - compatible        : must include "fsl,elo-dma-channel"
@@ -25,7 +24,6 @@ Optional properties:
         - interrupts        : interrupt specifier for DMA channel IRQ
                               (on 83xx this is expected to be identical to
                               the interrupts property of the parent node)
-        - interrupt-parent  : optional, if needed for interrupt mapping
 
 Example:
 	dma@82a8 {
@@ -88,7 +86,6 @@ Required properties:
         - cell-index        : DMA channel index starts at 0.
         - reg               : DMA channel specific registers
         - interrupts        : interrupt specifier for DMA channel IRQ
-        - interrupt-parent  : optional, if needed for interrupt mapping
 
 Example:
 	dma@21300 {
@@ -146,7 +143,6 @@ Required properties:
         - compatible        : must include "fsl,eloplus-dma-channel"
         - reg               : DMA channel specific registers
         - interrupts        : interrupt specifier for DMA channel IRQ
-        - interrupt-parent  : optional, if needed for interrupt mapping
 
 Example:
 dma@100300 {
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt b/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt
index f514f29c67d6..76dc547bc492 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt
@@ -57,8 +57,4 @@ PROPERTIES
       Usage: required
       Value type: <prop-encoded-array>
 
-   - interrupt-parent
-      Usage: required
-      Value type: <phandle>
-
 =====================================================================
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt b/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt
index 4ceda9b3b413..a5dae6b1f545 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt
@@ -57,8 +57,4 @@ PROPERTIES
       Usage: required
       Value type: <prop-encoded-array>
 
-   - interrupt-parent
-      Usage: required
-      Value type: <phandle>
-
 =====================================================================
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
index 647817527c88..5dfd68f1a423 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
@@ -18,8 +18,6 @@ Required properties :
  - interrupts : <a b> where a is the interrupt number of the
    PSC FIFO Controller and b is a field that represents an
    encoding of the sense and level information for the interrupt.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Recommended properties :
  - fsl,rx-fifo-size : the size of the RX fifo slice (a multiple of 4)
@@ -45,8 +43,6 @@ Required properties :
  - interrupts : <a b> where a is the interrupt number of the
    PSC FIFO Controller and b is a field that represents an
    encoding of the sense and level information for the interrupt.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Recommended properties :
  - clocks : specifies the clock needed to operate the fifo controller
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt b/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt
index 82dd5b65cf48..f8d2b7fe06d6 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt
@@ -21,11 +21,6 @@ Required properties:
   be set as edge sensitive.  If msi-available-ranges is present, only
   the interrupts that correspond to available ranges shall be present.
 
-- interrupt-parent: the phandle for the interrupt controller
-  that services interrupts for this device. for 83xx cpu, the interrupts
-  are routed to IPIC, and for 85xx/86xx cpu the interrupts are routed
-  to MPIC.
-
 Optional properties:
 - msi-available-ranges: use <start count> style section to define which
   msi interrupt can be used in the 256 msi interrupts. This property is
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt b/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt
index c2b2899885f2..b21ab85de6e7 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt
@@ -32,8 +32,6 @@ Optional properties:
 		  A standard property.   It represents the CCSR registers of
 		  all child PAMUs combined.  Include it to provide support
 		  for legacy drivers.
-- interrupt-parent : <phandle>
-		  Phandle to interrupt controller
 - fsl,portid-mapping : <u32>
 		  The Coherency Subdomain ID Port Mapping Registers and
 		  Snoop ID Port Mapping registers, which are part of the
diff --git a/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt b/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt
index a3dc4b9fa11a..c4d78f28d23c 100644
--- a/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt
+++ b/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt
@@ -148,7 +148,6 @@ Nintendo Wii device tree
   - reg : should contain the controller registers location and length
   - interrupt-controller
   - interrupts : should contain the cascade interrupt of the "flipper" pic
-  - interrupt-parent: should contain the phandle of the "flipper" pic
 
 1.l) The General Purpose I/O (GPIO) controller node
 
diff --git a/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt b/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
index 675f4437ce92..36f5e2f5cc0f 100644
--- a/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
@@ -5,6 +5,7 @@ Requires node properties:
 - "compatible" value one of:
     "motorola,cpcap-regulator"
     "motorola,mapphone-cpcap-regulator"
+    "motorola,xoom-cpcap-regulator"
 
 Required regulator properties:
 - "regulator-name"
diff --git a/Documentation/devicetree/bindings/regulator/max8997-regulator.txt b/Documentation/devicetree/bindings/regulator/max8997-regulator.txt
index 5c186a7a77ba..6fe825b8ac1b 100644
--- a/Documentation/devicetree/bindings/regulator/max8997-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/max8997-regulator.txt
@@ -32,8 +32,6 @@ Required properties:
     'max8997,pmic-buck[1/2/5]-dvs-voltage' should be specified.
 
 Optional properties:
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from max8997 are delivered to.
 - interrupts: Interrupt specifiers for two interrupt sources.
   - First interrupt specifier is for 'irq1' interrupt.
   - Second interrupt specifier is for 'alert' interrupt.
diff --git a/Documentation/devicetree/bindings/regulator/palmas-pmic.txt b/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
index 99872819604f..84bc76a7c39e 100644
--- a/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
+++ b/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
@@ -18,7 +18,6 @@ Required properties:
   ti,tps659038-pmic
 and also the generic series names
   ti,palmas-pmic
-- interrupt-parent : The parent interrupt controller which is palmas.
 - interrupts : The interrupt number and the type which can be looked up here:
 	       arch/arm/boot/dts/include/dt-bindings/interrupt-controller/irq.h
 - interrupts-name: The names of the individual interrupts.
diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt
index f0ada3b14d70..c7610718adff 100644
--- a/Documentation/devicetree/bindings/regulator/pfuze100.txt
+++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt
@@ -1,9 +1,18 @@
 PFUZE100 family of regulators
 
 Required properties:
-- compatible: "fsl,pfuze100", "fsl,pfuze200", "fsl,pfuze3000"
+- compatible: "fsl,pfuze100", "fsl,pfuze200", "fsl,pfuze3000", "fsl,pfuze3001"
 - reg: I2C slave address
 
+Optional properties:
+- fsl,pfuze-support-disable-sw: Boolean, if present disable all unused switch
+  regulators to save power consumption. Attention, ensure that all important
+  regulators (e.g. DDR ref, DDR supply) has set the "regulator-always-on"
+  property. If not present, the switched regualtors are always on and can't be
+  disabled. This binding is a workaround to keep backward compatibility with
+  old dtb's which rely on the fact that the switched regulators are always on
+  and don't mark them explicit as "regulator-always-on".
+
 Required child node:
 - regulators: This is the list of child nodes that specify the regulator
   initialization data for defined regulators. Please refer to below doc
@@ -16,6 +25,8 @@ Required child node:
   sw1ab,sw2,sw3a,sw3b,swbst,vsnvs,vrefddr,vgen1~vgen6,coin
   --PFUZE3000
   sw1a,sw1b,sw2,sw3,swbst,vsnvs,vrefddr,vldo1,vldo2,vccsd,v33,vldo3,vldo4
+  --PFUZE3001
+  sw1,sw2,sw3,vsnvs,vldo1,vldo2,vccsd,v33,vldo3,vldo4
 
 Each regulator is defined using the standard binding for regulators.
 
@@ -303,3 +314,76 @@ Example 3: PFUZE3000
 			};
 		};
 	};
+
+Example 4: PFUZE 3001
+
+	pfuze3001: pmic@8 {
+		compatible = "fsl,pfuze3001";
+		reg = <0x08>;
+
+		regulators {
+			sw1_reg: sw1 {
+				regulator-min-microvolt = <700000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw2_reg: sw2 {
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3_reg: sw3 {
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <1650000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			snvs_reg: vsnvs {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vgen1_reg: vldo1 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen2_reg: vldo2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1550000>;
+				regulator-always-on;
+			};
+
+			vgen3_reg: vccsd {
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen4_reg: v33 {
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen5_reg: vldo3 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen6_reg: vldo4 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
new file mode 100644
index 000000000000..7ef2dbe48e8a
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
@@ -0,0 +1,160 @@
+Qualcomm Technologies, Inc. RPMh Regulators
+
+rpmh-regulator devices support PMIC regulator management via the Voltage
+Regulator Manager (VRM) and Oscillator Buffer (XOB) RPMh accelerators.  The APPS
+processor communicates with these hardware blocks via a Resource State
+Coordinator (RSC) using command packets.  The VRM allows changing three
+parameters for a given regulator: enable state, output voltage, and operating
+mode.  The XOB allows changing only a single parameter for a given regulator:
+its enable state.  Despite its name, the XOB is capable of controlling the
+enable state of any PMIC peripheral.  It is used for clock buffers, low-voltage
+switches, and LDO/SMPS regulators which have a fixed voltage and mode.
+
+=======================
+Required Node Structure
+=======================
+
+RPMh regulators must be described in two levels of device nodes.  The first
+level describes the PMIC containing the regulators and must reside within an
+RPMh device node.  The second level describes each regulator within the PMIC
+which is to be used on the board.  Each of these regulators maps to a single
+RPMh resource.
+
+The names used for regulator nodes must match those supported by a given PMIC.
+Supported regulator node names:
+	PM8998:		smps1 - smps13, ldo1 - ldo28, lvs1 - lvs2
+	PMI8998:	bob
+	PM8005:		smps1 - smps4
+
+========================
+First Level Nodes - PMIC
+========================
+
+- compatible
+	Usage:      required
+	Value type: <string>
+	Definition: Must be one of: "qcom,pm8998-rpmh-regulators",
+		    "qcom,pmi8998-rpmh-regulators" or
+		    "qcom,pm8005-rpmh-regulators".
+
+- qcom,pmic-id
+	Usage:      required
+	Value type: <string>
+	Definition: RPMh resource name suffix used for the regulators found on
+		    this PMIC.  Typical values: "a", "b", "c", "d", "e", "f".
+
+- vdd-s1-supply
+- vdd-s2-supply
+- vdd-s3-supply
+- vdd-s4-supply
+	Usage:      optional (PM8998 and PM8005 only)
+	Value type: <phandle>
+	Definition: phandle of the parent supply regulator of one or more of the
+		    regulators for this PMIC.
+
+- vdd-s5-supply
+- vdd-s6-supply
+- vdd-s7-supply
+- vdd-s8-supply
+- vdd-s9-supply
+- vdd-s10-supply
+- vdd-s11-supply
+- vdd-s12-supply
+- vdd-s13-supply
+- vdd-l1-l27-supply
+- vdd-l2-l8-l17-supply
+- vdd-l3-l11-supply
+- vdd-l4-l5-supply
+- vdd-l6-supply
+- vdd-l7-l12-l14-l15-supply
+- vdd-l9-supply
+- vdd-l10-l23-l25-supply
+- vdd-l13-l19-l21-supply
+- vdd-l16-l28-supply
+- vdd-l18-l22-supply
+- vdd-l20-l24-supply
+- vdd-l26-supply
+- vin-lvs-1-2-supply
+	Usage:      optional (PM8998 only)
+	Value type: <phandle>
+	Definition: phandle of the parent supply regulator of one or more of the
+		    regulators for this PMIC.
+
+- vdd-bob-supply
+	Usage:      optional (PMI8998 only)
+	Value type: <phandle>
+	Definition: BOB regulator parent supply phandle
+
+===============================
+Second Level Nodes - Regulators
+===============================
+
+- qcom,always-wait-for-ack
+	Usage:      optional
+	Value type: <empty>
+	Definition: Boolean flag which indicates that the application processor
+		    must wait for an ACK or a NACK from RPMh for every request
+		    sent for this regulator including those which are for a
+		    strictly lower power state.
+
+Other properties defined in Documentation/devicetree/bindings/regulator.txt
+may also be used.  regulator-initial-mode and regulator-allowed-modes may be
+specified for VRM regulators using mode values from
+include/dt-bindings/regulator/qcom,rpmh-regulator.h.  regulator-allow-bypass
+may be specified for BOB type regulators managed via VRM.
+regulator-allow-set-load may be specified for LDO type regulators managed via
+VRM.
+
+========
+Examples
+========
+
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+
+&apps_rsc {
+	pm8998-rpmh-regulators {
+		compatible = "qcom,pm8998-rpmh-regulators";
+		qcom,pmic-id = "a";
+
+		vdd-l7-l12-l14-l15-supply = <&pm8998_s5>;
+
+		smps2 {
+			regulator-min-microvolt = <1100000>;
+			regulator-max-microvolt = <1100000>;
+		};
+
+		pm8998_s5: smps5 {
+			regulator-min-microvolt = <1904000>;
+			regulator-max-microvolt = <2040000>;
+		};
+
+		ldo7 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allowed-modes =
+				<RPMH_REGULATOR_MODE_LPM
+				 RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+		};
+
+		lvs1 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+	};
+
+	pmi8998-rpmh-regulators {
+		compatible = "qcom,pmi8998-rpmh-regulators";
+		qcom,pmic-id = "b";
+
+		bob {
+			regulator-min-microvolt = <3312000>;
+			regulator-max-microvolt = <3600000>;
+			regulator-allowed-modes =
+				<RPMH_REGULATOR_MODE_AUTO
+				 RPMH_REGULATOR_MODE_HPM>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_AUTO>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.txt b/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.txt
index 4edf3137d9f7..76ead07072b1 100644
--- a/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.txt
@@ -1,13 +1,5 @@
 ROHM BD71837 Power Management Integrated Circuit (PMIC) regulator bindings
 
-BD71837MWV is a programmable Power Management
-IC (PMIC) for powering single-core, dual-core, and
-quad-core SoC’s such as NXP-i.MX 8M. It is optimized
-for low BOM cost and compact solution footprint. It
-integrates 8 Buck regulators and 7 LDO’s to provide all
-the power rails required by the SoC and the commonly
-used peripherals.
-
 Required properties:
  - regulator-name: should be "buck1", ..., "buck8" and "ldo1", ..., "ldo7"
 
diff --git a/Documentation/devicetree/bindings/regulator/tps65090.txt b/Documentation/devicetree/bindings/regulator/tps65090.txt
index ca69f5e3040c..ae326f263597 100644
--- a/Documentation/devicetree/bindings/regulator/tps65090.txt
+++ b/Documentation/devicetree/bindings/regulator/tps65090.txt
@@ -16,7 +16,7 @@ Required properties:
 Optional properties:
 - ti,enable-ext-control: This is applicable for DCDC1, DCDC2 and DCDC3.
   If DCDCs are externally controlled then this property should be there.
-- "dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3.
+- dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3.
   If DCDCs are externally controlled and if it is from GPIO then GPIO
   number should be provided. If it is externally controlled and no GPIO
   entry then driver will just configure this rails as external control
diff --git a/Documentation/devicetree/bindings/regulator/uniphier-regulator.txt b/Documentation/devicetree/bindings/regulator/uniphier-regulator.txt
new file mode 100644
index 000000000000..c9919f4b92d2
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/uniphier-regulator.txt
@@ -0,0 +1,57 @@
+Socionext UniPhier Regulator Controller
+
+This describes the devicetree bindings for regulator controller implemented
+on Socionext UniPhier SoCs.
+
+USB3 Controller
+---------------
+
+This regulator controls VBUS and belongs to USB3 glue layer. Before using
+the regulator, it is necessary to control the clocks and resets to enable
+this layer. These clocks and resets should be described in each property.
+
+Required properties:
+- compatible: Should be
+    "socionext,uniphier-pro4-usb3-regulator" - for Pro4 SoC
+    "socionext,uniphier-pxs2-usb3-regulator" - for PXs2 SoC
+    "socionext,uniphier-ld20-usb3-regulator" - for LD20 SoC
+    "socionext,uniphier-pxs3-usb3-regulator" - for PXs3 SoC
+- reg: Specifies offset and length of the register set for the device.
+- clocks: A list of phandles to the clock gate for USB3 glue layer.
+	According to the clock-names, appropriate clocks are required.
+- clock-names: Should contain
+    "gio", "link" - for Pro4 SoC
+    "link"        - for others
+- resets: A list of phandles to the reset control for USB3 glue layer.
+	According to the reset-names, appropriate resets are required.
+- reset-names: Should contain
+    "gio", "link" - for Pro4 SoC
+    "link"        - for others
+
+See Documentation/devicetree/bindings/regulator/regulator.txt
+for more details about the regulator properties.
+
+Example:
+
+	usb-glue@65b00000 {
+		compatible = "socionext,uniphier-ld20-dwc3-glue",
+			     "simple-mfd";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x65b00000 0x400>;
+
+		usb_vbus0: regulators@100 {
+			compatible = "socionext,uniphier-ld20-usb3-regulator";
+			reg = <0x100 0x10>;
+			clock-names = "link";
+			clocks = <&sys_clk 14>;
+			reset-names = "link";
+			resets = <&sys_rst 14>;
+		};
+
+		phy {
+			...
+			phy-supply = <&usb_vbus0>;
+		};
+		...
+	};
diff --git a/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt b/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt
index e44a97e21164..25f8658e216f 100644
--- a/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt
+++ b/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt
@@ -45,12 +45,6 @@ The following are the mandatory properties:
 			per the bindings in
 			Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
 
-Optional properties:
---------------------
-- interrupt-parent:	phandle to the interrupt controller node. This property
-			is needed if the device node hierarchy doesn't have an
-			interrupt controller.
-
 
 Example:
 --------
diff --git a/Documentation/devicetree/bindings/remoteproc/ti,keystone-rproc.txt b/Documentation/devicetree/bindings/remoteproc/ti,keystone-rproc.txt
index 1eb72874130b..461dc1d8d570 100644
--- a/Documentation/devicetree/bindings/remoteproc/ti,keystone-rproc.txt
+++ b/Documentation/devicetree/bindings/remoteproc/ti,keystone-rproc.txt
@@ -51,12 +51,6 @@ The following are the mandatory properties:
 			Documentation/devicetree/bindings/reset/ti,sci-reset.txt
 			    for 66AK2G SoCs
 
-- interrupt-parent:	Should contain a phandle to the Keystone 2 IRQ controller
-			IP node that is used by the ARM CorePac processor to
-			receive interrupts from the DSP remote processors. See
-			Documentation/devicetree/bindings/interrupt-controller/ti,keystone-irq.txt
-			for details.
-
 - interrupts: 		Should contain an entry for each value in 'interrupt-names'.
 			Each entry should have the interrupt source number used by
 			the remote processor to the host processor. The values should
diff --git a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt
index a21658f18fe6..3661e6153a92 100644
--- a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt
+++ b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt
@@ -15,7 +15,7 @@ Please refer to reset.txt in this directory for common reset
 controller binding usage.
 
 Required properties:
-- compatible: Should be st,stih407-softreset";
+- compatible: Should be "st,stih407-softreset";
 - #reset-cells: 1, see below
 
 example:
diff --git a/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt b/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt
index 1d990bcc0baf..d946f28502b3 100644
--- a/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt
+++ b/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt
@@ -7,8 +7,6 @@ Required properties:
 - compatible     : should contain "brcm,brcmstb-waketimer"
 - reg            : the register start and length for the WKTMR block
 - interrupts     : The TIMER interrupt
-- interrupt-parent: The phandle to the Always-On (AON) Power Management (PM) L2
-                    interrupt controller node
 - clocks	 : The phandle to the UPG fixed clock (27Mhz domain)
 
 Example:
diff --git a/Documentation/devicetree/bindings/rtc/isil,isl12057.txt b/Documentation/devicetree/bindings/rtc/isil,isl12057.txt
index fbbdd92e5af9..ff7c43555199 100644
--- a/Documentation/devicetree/bindings/rtc/isil,isl12057.txt
+++ b/Documentation/devicetree/bindings/rtc/isil,isl12057.txt
@@ -25,9 +25,6 @@ Optional properties:
  - "wakeup-source": mark the chip as a wakeup source, independently of
     the availability of an IRQ line connected to the SoC.
 
- - "interrupt-parent", "interrupts": for passing the interrupt line
-   of the SoC connected to IRQ#2 of the RTC chip.
-
 
 Example isl12057 node without IRQ#2 pin connected (no alarm support):
 
diff --git a/Documentation/devicetree/bindings/rtc/rtc-cmos.txt b/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
index 7382989b3052..b94b35f3600b 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
@@ -7,7 +7,6 @@ Required properties:
 
 Optional properties:
   - interrupts : should contain interrupt.
-  - interrupt-parent : interrupt source phandle.
   - ctrl-reg : Contains the initial value of the control register also
     called "Register B".
   - freq-reg : Contains the initial value of the frequency register also
diff --git a/Documentation/devicetree/bindings/rtc/rtc-ds1307.txt b/Documentation/devicetree/bindings/rtc/rtc-ds1307.txt
index d28d6e7f6ae8..226cc93df875 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-ds1307.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-ds1307.txt
@@ -21,7 +21,6 @@ Required properties:
 - reg: I2C bus address of the device
 
 Optional properties:
-- interrupt-parent: phandle for the interrupt controller.
 - interrupts: rtc alarm interrupt.
 - clock-output-names: From common clock binding to override the default output
                       clock name
diff --git a/Documentation/devicetree/bindings/rtc/rtc-m41t80.txt b/Documentation/devicetree/bindings/rtc/rtc-m41t80.txt
index 717d93860af1..c746cb221210 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-m41t80.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-m41t80.txt
@@ -16,7 +16,6 @@ Required properties:
 - reg: I2C bus address of the device
 
 Optional properties:
-- interrupt-parent: phandle for the interrupt controller.
 - interrupts: rtc alarm interrupt.
 - clock-output-names: From common clock binding to override the default output
                       clock name
diff --git a/Documentation/devicetree/bindings/rtc/rtc-omap.txt b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
index bee41f97044e..062ebb14cecf 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-omap.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
@@ -11,7 +11,6 @@ Required properties:
 	- "ti,am4372-rtc" - for RTC IP used similar to that on AM437X SoC family.
 - reg: Address range of rtc register set
 - interrupts: rtc timer, alarm interrupts in order
-- interrupt-parent: phandle for the interrupt controller
 
 Optional properties:
 - system-power-controller: whether the rtc is controlling the system power
diff --git a/Documentation/devicetree/bindings/rtc/rtc-palmas.txt b/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
index eb1c7fdeb413..c6cf37758a77 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
@@ -3,7 +3,6 @@ Palmas RTC controller bindings
 Required properties:
 - compatible:
   - "ti,palmas-rtc" for palma series of the RTC controller
-- interrupt-parent: Parent interrupt device, must be handle of palmas node.
 - interrupts: Interrupt number of RTC submodule on device.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/rtc/spear-rtc.txt b/Documentation/devicetree/bindings/rtc/spear-rtc.txt
index ca67ac62108e..fecf8e4ad4b4 100644
--- a/Documentation/devicetree/bindings/rtc/spear-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/spear-rtc.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible : "st,spear600-rtc"
 - reg : Address range of the rtc registers
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupt: Should contain the rtc interrupt number
 
 Example:
diff --git a/Documentation/devicetree/bindings/rtc/sprd,sc27xx-rtc.txt b/Documentation/devicetree/bindings/rtc/sprd,sc27xx-rtc.txt
index 7c170da0d4b7..1f5754299d31 100644
--- a/Documentation/devicetree/bindings/rtc/sprd,sc27xx-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/sprd,sc27xx-rtc.txt
@@ -3,7 +3,6 @@ Spreadtrum SC27xx Real Time Clock
 Required properties:
 - compatible: should be "sprd,sc2731-rtc".
 - reg: address offset of rtc register.
-- interrupt-parent: phandle for the interrupt controller.
 - interrupts: rtc alarm interrupt.
 
 Example:
diff --git a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt
index c920e2736991..130ca5b98253 100644
--- a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt
@@ -13,8 +13,6 @@ Required properties:
     It is required on stm32(h7/mp1).
 - clock-names: must be "rtc_ck" and "pclk".
     It is required on stm32(h7/mp1).
-- interrupt-parent: phandle for the interrupt controller.
-    It is required on stm32(f4/f7/h7).
 - interrupts: rtc alarm interrupt. On stm32mp1, a second interrupt is required
   for rtc alarm wakeup interrupt.
 - st,syscfg: phandle/offset/mask triplet. The phandle to pwrcfg used to
diff --git a/Documentation/devicetree/bindings/rtc/stericsson,coh901331.txt b/Documentation/devicetree/bindings/rtc/stericsson,coh901331.txt
index 3ebeb311335f..e615a897b20e 100644
--- a/Documentation/devicetree/bindings/rtc/stericsson,coh901331.txt
+++ b/Documentation/devicetree/bindings/rtc/stericsson,coh901331.txt
@@ -3,7 +3,6 @@ ST-Ericsson COH 901 331 Real Time Clock
 Required properties:
 - compatible: must be "stericsson,coh901331"
 - reg: address range of rtc register set.
-- interrupt-parent: phandle for the interrupt controller.
 - interrupts: rtc alarm interrupt.
 - clocks: phandle to the rtc clock source
 
diff --git a/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt b/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt
index 6a4e0d30d8c4..0dc121b6eace 100644
--- a/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt
+++ b/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg: address on the bus
 
 Optional ST33ZP24 Properties:
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - lpcpd-gpios: Output GPIO pin used for ST33ZP24 power management D1/D2 state.
 If set, power must be present when the platform is going into sleep/hibernate mode.
diff --git a/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt b/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt
index 604dce901b60..37198971f17b 100644
--- a/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt
+++ b/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt
@@ -5,7 +5,6 @@ Required properties:
 - spi-max-frequency: Maximum SPI frequency (<= 10000000).
 
 Optional ST33ZP24 Properties:
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - lpcpd-gpios: Output GPIO pin used for ST33ZP24 power management D1/D2 state.
 If set, power must be present when the platform is going into sleep/hibernate mode.
diff --git a/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt b/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt
index 41d740545189..7c6304426da1 100644
--- a/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt
+++ b/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt
@@ -13,7 +13,7 @@ Required properties:
               "tcg,tpm-tis-mmio". Valid chip strings are:
 	          * "atmel,at97sc3204"
 - reg: The location of the MMIO registers, should be at least 0x5000 bytes
-- interrupt-parent/interrupts: An optional interrupt indicating command completion.
+- interrupts: An optional interrupt indicating command completion.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/serial/maxim,max310x.txt b/Documentation/devicetree/bindings/serial/maxim,max310x.txt
index 823f77dd7978..79e10a05a96a 100644
--- a/Documentation/devicetree/bindings/serial/maxim,max310x.txt
+++ b/Documentation/devicetree/bindings/serial/maxim,max310x.txt
@@ -7,8 +7,6 @@ Required properties:
   - "maxim,max3109" for Maxim MAX3109,
   - "maxim,max14830" for Maxim MAX14830.
 - reg: SPI chip select number.
-- interrupt-parent: The phandle for the interrupt controller that
-  services interrupts for this IC.
 - interrupts: Specifies the interrupt source of the parent interrupt
   controller. The format of the interrupt specifier depends on the
   parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt
index fbfe53635a3a..e7921a8e276b 100644
--- a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt
+++ b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt
@@ -10,8 +10,6 @@ Required properties:
   - "nxp,sc16is760" for NXP SC16IS760,
   - "nxp,sc16is762" for NXP SC16IS762.
 - reg: I2C address of the SC16IS7xx device.
-- interrupt-parent: The phandle for the interrupt controller that
-  services interrupts for this IC.
 - interrupts: Should contain the UART interrupt
 - clocks: Reference to the IC source clock.
 
@@ -44,8 +42,6 @@ Required properties:
   - "nxp,sc16is760" for NXP SC16IS760,
   - "nxp,sc16is762" for NXP SC16IS762.
 - reg: SPI chip select number.
-- interrupt-parent: The phandle for the interrupt controller that
-  services interrupts for this IC.
 - interrupts: Specifies the interrupt source of the parent interrupt
   controller. The format of the interrupt specifier depends on the
   parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
index c5e032c85bf9..7d65126bd1d7 100644
--- a/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
+++ b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
@@ -7,9 +7,6 @@ Required properties:
 - reg: Specifies the physical base address of the controller and
   the length of the memory mapped region.
 
-- interrupt-parent: The phandle for the interrupt controller that
-  services interrupts for this device.
-
 - interrupts: Specifies the interrupt source of the parent interrupt
   controller. The format of the interrupt specifier depends on the
   parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt
index 626e1afa64a6..cce3cd71e85a 100644
--- a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt
@@ -21,7 +21,6 @@ Optional properties:
   one as described by the fsl,cpm1-gpio-irq-mask property. There should be as
   many interrupts as number of ones in the mask property. The first interrupt in
   the list corresponds to the most significant bit of the mask.
-- interrupt-parent : Parent for the above interrupt property.
 
 Example of four SOC GPIO banks defined as gpio-controller nodes:
 
diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt
index e47734bee3f0..5efb7ac94c79 100644
--- a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt
@@ -11,8 +11,6 @@ Required properties:
   information for the interrupt.  This should be encoded based on
   the information in section 2) depending on the type of interrupt
   controller you have.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 - pio-handle : The phandle for the Parallel I/O port configuration.
 - port-number : for UART drivers, the port number to use, between 0 and 3.
   This usually corresponds to the /dev/ttyQE device, e.g. <0> = /dev/ttyQE0.
diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt
index 9ccd5f30405b..da13999337a4 100644
--- a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt
@@ -6,7 +6,6 @@ Required properties:
   length, the next two two cells should contain PRAM location and
   length.
 - interrupts : should contain USB interrupt.
-- interrupt-parent : interrupt source phandle.
 - fsl,fullspeed-clock : specifies the full speed USB clock source:
   "none": clock source is disabled
   "brg1" through "brg16": clock source is BRG1-BRG16, respectively
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt
index d330c73de9a2..68b7d6207e3d 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt
@@ -39,7 +39,7 @@ Required properties:
 
 Optional property:
 - clock-frequency:	Desired I2C bus clock frequency in Hz.
-			When missing default to 400000Hz.
+			When missing default to 100000Hz.
 
 Child nodes should conform to I2C bus binding as described in i2c.txt.
 
diff --git a/Documentation/devicetree/bindings/soc/qcom/rpmh-rsc.txt b/Documentation/devicetree/bindings/soc/qcom/rpmh-rsc.txt
new file mode 100644
index 000000000000..9b86d1eff219
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom/rpmh-rsc.txt
@@ -0,0 +1,137 @@
+RPMH RSC:
+------------
+
+Resource Power Manager Hardened (RPMH) is the mechanism for communicating with
+the hardened resource accelerators on Qualcomm SoCs. Requests to the resources
+can be written to the Trigger Command Set (TCS)  registers and using a (addr,
+val) pair and triggered. Messages in the TCS are then sent in sequence over an
+internal bus.
+
+The hardware block (Direct Resource Voter or DRV) is a part of the h/w entity
+(Resource State Coordinator a.k.a RSC) that can handle multiple sleep and
+active/wake resource requests. Multiple such DRVs can exist in a SoC and can
+be written to from Linux. The structure of each DRV follows the same template
+with a few variations that are captured by the properties here.
+
+A TCS may be triggered from Linux or triggered by the F/W after all the CPUs
+have powered off to facilitate idle power saving. TCS could be classified as -
+
+	ACTIVE  /* Triggered by Linux */
+	SLEEP   /* Triggered by F/W */
+	WAKE    /* Triggered by F/W */
+	CONTROL /* Triggered by F/W */
+
+The order in which they are described in the DT, should match the hardware
+configuration.
+
+Requests can be made for the state of a resource, when the subsystem is active
+or idle. When all subsystems like Modem, GPU, CPU are idle, the resource state
+will be an aggregate of the sleep votes from each of those subsystems. Clients
+may request a sleep value for their shared resources in addition to the active
+mode requests.
+
+Properties:
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: Should be "qcom,rpmh-rsc".
+
+- reg:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: The first register specifies the base address of the
+		    DRV(s). The number of DRVs in the dependent on the RSC.
+	            The tcs-offset specifies the start address of the
+	            TCS in the DRVs.
+
+- reg-names:
+	Usage: required
+	Value type: <string>
+	Definition: Maps the register specified in the reg property. Must be
+	            "drv-0", "drv-1", "drv-2" etc and "tcs-offset". The
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-interrupt>
+	Definition: The interrupt that trips when a message complete/response
+	           is received for this DRV from the accelerators.
+
+- qcom,drv-id:
+	Usage: required
+	Value type: <u32>
+	Definition: The id of the DRV in the RSC block that will be used by
+		    this controller.
+
+- qcom,tcs-config:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: The tuple defining the configuration of TCS.
+	            Must have 2 cells which describe each TCS type.
+	            <type number_of_tcs>.
+	            The order of the TCS must match the hardware
+	            configuration.
+	- Cell #1 (TCS Type): TCS types to be specified -
+	            ACTIVE_TCS
+	            SLEEP_TCS
+	            WAKE_TCS
+	            CONTROL_TCS
+	- Cell #2 (Number of TCS): <u32>
+
+- label:
+	Usage: optional
+	Value type: <string>
+	Definition: Name for the RSC. The name would be used in trace logs.
+
+Drivers that want to use the RSC to communicate with RPMH must specify their
+bindings as child nodes of the RSC controllers they wish to communicate with.
+
+Example 1:
+
+For a TCS whose RSC base address is is 0x179C0000 and is at a DRV id of 2, the
+register offsets for DRV2 start at 0D00, the register calculations are like
+this -
+DRV0: 0x179C0000
+DRV2: 0x179C0000 + 0x10000 = 0x179D0000
+DRV2: 0x179C0000 + 0x10000 * 2 = 0x179E0000
+TCS-OFFSET: 0xD00
+
+	apps_rsc: rsc@179c0000 {
+		label = "apps_rsc";
+		compatible = "qcom,rpmh-rsc";
+		reg = <0x179c0000 0x10000>,
+		      <0x179d0000 0x10000>,
+		      <0x179e0000 0x10000>;
+		reg-names = "drv-0", "drv-1", "drv-2";
+		interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+		qcom,tcs-offset = <0xd00>;
+		qcom,drv-id = <2>;
+		qcom,tcs-config = <ACTIVE_TCS  2>,
+				  <SLEEP_TCS   3>,
+				  <WAKE_TCS    3>,
+				  <CONTROL_TCS 1>;
+	};
+
+Example 2:
+
+For a TCS whose RSC base address is 0xAF20000 and is at DRV id of 0, the
+register offsets for DRV0 start at 01C00, the register calculations are like
+this -
+DRV0: 0xAF20000
+TCS-OFFSET: 0x1C00
+
+	disp_rsc: rsc@af20000 {
+		label = "disp_rsc";
+		compatible = "qcom,rpmh-rsc";
+		reg = <0xaf20000 0x10000>;
+		reg-names = "drv-0";
+		interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>;
+		qcom,tcs-offset = <0x1c00>;
+		qcom,drv-id = <0>;
+		qcom,tcs-config = <ACTIVE_TCS  0>,
+				  <SLEEP_TCS   1>,
+				  <WAKE_TCS    1>,
+				  <CONTROL_TCS 0>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/ac97-bus.txt b/Documentation/devicetree/bindings/sound/ac97-bus.txt
new file mode 100644
index 000000000000..103c428f2595
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/ac97-bus.txt
@@ -0,0 +1,32 @@
+Generic AC97 Device Properties
+
+This documents describes the devicetree bindings for an ac97 controller child
+node describing ac97 codecs.
+
+Required properties:
+-compatible : Must be "ac97,vendor_id1,vendor_id2
+	      The ids shall be the 4 characters hexadecimal encoding, such as
+	      given by "%04x" formatting of printf
+-reg	    : Must be the ac97 codec number, between 0 and 3
+
+Example:
+ac97: sound@40500000 {
+	compatible = "marvell,pxa270-ac97";
+	reg = < 0x40500000 0x1000 >;
+	interrupts = <14>;
+	reset-gpios = <&gpio 95 GPIO_ACTIVE_HIGH>;
+	#sound-dai-cells = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = < &pinctrl_ac97_default >;
+	clocks = <&clks CLK_AC97>, <&clks CLK_AC97CONF>;
+	clock-names = "AC97CLK", "AC97CONFCLK";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+	audio-codec@0 {
+		reg = <0>;
+		compatible = "ac97,574d,4c13";
+		clocks = <&fixed_wm9713_clock>;
+		clock-names = "ac97_clk";
+	}
+};
diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-fifo.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-fifo.txt
new file mode 100644
index 000000000000..3dfc2515e5c6
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-fifo.txt
@@ -0,0 +1,23 @@
+* Amlogic Audio FIFO controllers
+
+Required properties:
+- compatible: 'amlogic,axg-toddr' or
+	      'amlogic,axg-frddr'
+- reg: physical base address of the controller and length of memory
+       mapped region.
+- interrupts: interrupt specifier for the fifo.
+- clocks: phandle to the fifo peripheral clock provided by the audio
+	  clock controller.
+- resets: phandle to memory ARB line provided by the arb reset controller.
+- #sound-dai-cells: must be 0.
+
+Example of FRDDR A on the A113 SoC:
+
+frddr_a: audio-controller@1c0 {
+	compatible = "amlogic,axg-frddr";
+	reg = <0x0 0x1c0 0x0 0x1c>;
+	#sound-dai-cells = <0>;
+	interrupts = <GIC_SPI 88 IRQ_TYPE_EDGE_RISING>;
+	clocks = <&clkc_audio AUD_CLKID_FRDDR_A>;
+	resets = <&arb AXG_ARB_FRDDR_A>;
+};
diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt
new file mode 100644
index 000000000000..80b411296480
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt
@@ -0,0 +1,124 @@
+Amlogic AXG sound card:
+
+Required properties:
+
+- compatible: "amlogic,axg-sound-card"
+- model : User specified audio sound card name, one string
+
+Optional properties:
+
+- audio-aux-devs : List of phandles pointing to auxiliary devices
+- audio-widgets : Please refer to widgets.txt.
+- audio-routing : A list of the connections between audio components.
+
+Subnodes:
+
+- dai-link: Container for dai-link level properties and the CODEC
+	    sub-nodes. There should be at least one (and probably more)
+	    subnode of this type.
+
+Required dai-link properties:
+
+- sound-dai: phandle and port of the CPU DAI.
+
+Required TDM Backend dai-link properties:
+- dai-format : CPU/CODEC common audio format
+
+Optional TDM Backend dai-link properties:
+- dai-tdm-slot-rx-mask-{0,1,2,3}: Receive direction slot masks
+- dai-tdm-slot-tx-mask-{0,1,2,3}: Transmit direction slot masks
+				  When omitted, mask is assumed to have to no
+				  slots. A valid must have at one slot, so at
+				  least one these mask should be provided with
+				  an enabled slot.
+- dai-tdm-slot-num : Please refer to tdm-slot.txt.
+		     If omitted, slot number is set to accommodate the largest
+		     mask provided.
+- dai-tdm-slot-width : Please refer to tdm-slot.txt. default to 32 if omitted.
+- mclk-fs : Multiplication factor between stream rate and mclk
+
+Backend dai-link subnodes:
+
+- codec: dai-link representing backend links should have at least one subnode.
+	 One subnode for each codec of the dai-link.
+	 dai-link representing frontend links have no codec, therefore have no
+	 subnodes
+
+Required codec subnodes properties:
+
+- sound-dai: phandle and port of the CODEC DAI.
+
+Optional codec subnodes properties:
+
+- dai-tdm-slot-tx-mask : Please refer to tdm-slot.txt.
+- dai-tdm-slot-rx-mask : Please refer to tdm-slot.txt.
+
+Example:
+
+sound {
+	compatible = "amlogic,axg-sound-card";
+	model = "AXG-S420";
+	audio-aux-devs = <&tdmin_a>, <&tdmout_c>;
+	audio-widgets = "Line", "Lineout",
+			"Line", "Linein",
+			"Speaker", "Speaker1 Left",
+			"Speaker", "Speaker1 Right";
+			"Speaker", "Speaker2 Left",
+			"Speaker", "Speaker2 Right";
+	audio-routing = "TDMOUT_C IN 0", "FRDDR_A OUT 2",
+			"SPDIFOUT IN 0", "FRDDR_A OUT 3",
+			"TDM_C Playback", "TDMOUT_C OUT",
+			"TDMIN_A IN 2", "TDM_C Capture",
+			"TDMIN_A IN 5", "TDM_C Loopback",
+			"TODDR_A IN 0", "TDMIN_A OUT",
+			"Lineout", "Lineout AOUTL",
+			"Lineout", "Lineout AOUTR",
+			"Speaker1 Left", "SPK1 OUT_A",
+			"Speaker2 Left", "SPK2 OUT_A",
+			"Speaker1 Right", "SPK1 OUT_B",
+			"Speaker2 Right", "SPK2 OUT_B",
+			"Linein AINL", "Linein",
+			"Linein AINR", "Linein";
+
+	dai-link@0 {
+		sound-dai = <&frddr_a>;
+	};
+
+	dai-link@1 {
+		sound-dai = <&toddr_a>;
+	};
+
+	dai-link@2 {
+		sound-dai = <&tdmif_c>;
+		dai-format = "i2s";
+		dai-tdm-slot-tx-mask-2 = <1 1>;
+		dai-tdm-slot-tx-mask-3 = <1 1>;
+		dai-tdm-slot-rx-mask-1 = <1 1>;
+		mclk-fs = <256>;
+
+		codec@0 {
+			sound-dai = <&lineout>;
+		};
+
+		codec@1 {
+			sound-dai = <&speaker_amp1>;
+		};
+
+		codec@2 {
+			sound-dai = <&speaker_amp2>;
+		};
+
+		codec@3 {
+			sound-dai = <&linein>;
+		};
+
+	};
+
+	dai-link@3 {
+		sound-dai = <&spdifout>;
+
+		codec {
+			sound-dai = <&spdif_dit>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-spdifout.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-spdifout.txt
new file mode 100644
index 000000000000..521c38ad89e7
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-spdifout.txt
@@ -0,0 +1,20 @@
+* Amlogic Audio SPDIF Output
+
+Required properties:
+- compatible: 'amlogic,axg-spdifout'
+- clocks: list of clock phandle, one for each entry clock-names.
+- clock-names: should contain the following:
+  * "pclk" : peripheral clock.
+  * "mclk" : master clock
+- #sound-dai-cells: must be 0.
+
+Example on the A113 SoC:
+
+spdifout: audio-controller@480 {
+	compatible = "amlogic,axg-spdifout";
+	reg = <0x0 0x480 0x0 0x50>;
+	#sound-dai-cells = <0>;
+	clocks = <&clkc_audio AUD_CLKID_SPDIFOUT>,
+		 <&clkc_audio AUD_CLKID_SPDIFOUT_CLK>;
+	clock-names = "pclk", "mclk";
+};
diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-formatters.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-formatters.txt
new file mode 100644
index 000000000000..1c1b7490554e
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-formatters.txt
@@ -0,0 +1,28 @@
+* Amlogic Audio TDM formatters
+
+Required properties:
+- compatible: 'amlogic,axg-tdmin' or
+	      'amlogic,axg-tdmout'
+- reg: physical base address of the controller and length of memory
+       mapped region.
+- clocks: list of clock phandle, one for each entry clock-names.
+- clock-names: should contain the following:
+  * "pclk"     : peripheral clock.
+  * "sclk"     : bit clock.
+  * "sclk_sel" : bit clock input multiplexer.
+  * "lrclk"    : sample clock
+  * "lrclk_sel": sample clock input multiplexer
+
+Example of TDMOUT_A on the A113 SoC:
+
+tdmout_a: audio-controller@500 {
+	compatible = "amlogic,axg-tdmout";
+	reg = <0x0 0x500 0x0 0x40>;
+	clocks = <&clkc_audio AUD_CLKID_TDMOUT_A>,
+		 <&clkc_audio AUD_CLKID_TDMOUT_A_SCLK>,
+		 <&clkc_audio AUD_CLKID_TDMOUT_A_SCLK_SEL>,
+		 <&clkc_audio AUD_CLKID_TDMOUT_A_LRCLK>,
+		 <&clkc_audio AUD_CLKID_TDMOUT_A_LRCLK>;
+	clock-names = "pclk", "sclk", "sclk_sel",
+		      "lrclk", "lrclk_sel";
+};
diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-iface.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-iface.txt
new file mode 100644
index 000000000000..cabfb26a5f22
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-iface.txt
@@ -0,0 +1,22 @@
+* Amlogic Audio TDM Interfaces
+
+Required properties:
+- compatible: 'amlogic,axg-tdm-iface'
+- clocks: list of clock phandle, one for each entry clock-names.
+- clock-names: should contain the following:
+  * "sclk" : bit clock.
+  * "lrclk": sample clock
+  * "mclk" : master clock
+	     -> optional if the interface is in clock slave mode.
+- #sound-dai-cells: must be 0.
+
+Example of TDM_A on the A113 SoC:
+
+tdmif_a: audio-controller@0 {
+	compatible = "amlogic,axg-tdm-iface";
+	#sound-dai-cells = <0>;
+	clocks = <&clkc_audio AUD_CLKID_MST_A_MCLK>,
+		 <&clkc_audio AUD_CLKID_MST_A_SCLK>,
+		 <&clkc_audio AUD_CLKID_MST_A_LRCLK>;
+	clock-names = "mclk", "sclk", "lrclk";
+};
diff --git a/Documentation/devicetree/bindings/sound/atmel-i2s.txt b/Documentation/devicetree/bindings/sound/atmel-i2s.txt
index 735368b8a73f..40549f496a81 100644
--- a/Documentation/devicetree/bindings/sound/atmel-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/atmel-i2s.txt
@@ -15,7 +15,6 @@ Required properties:
 - clock-names:    Should be one of each entry matching the clocks phandles list:
                   - "pclk" (peripheral clock) Required.
                   - "gclk" (generated clock) Optional (1).
-                  - "aclk" (Audio PLL clock) Optional (1).
                   - "muxclk" (I2S mux clock) Optional (1).
 
 Optional properties:
@@ -23,9 +22,9 @@ Optional properties:
 - princtrl-names: Should contain only one value - "default".
 
 
-(1) : Only the peripheral clock is required. The generated clock, the Audio
-      PLL clock adn the I2S mux clock are optional and should only be set
-      together, when Master Mode is required.
+(1) : Only the peripheral clock is required. The generated clock and the I2S
+      mux clock are optional and should only be set together, when Master Mode
+      is required.
 
 Example:
 
@@ -40,8 +39,8 @@ Example:
 			(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
 			 AT91_XDMAC_DT_PERID(32))>;
 		dma-names = "tx", "rx";
-		clocks = <&i2s0_clk>, <&i2s0_gclk>, <&audio_pll_pmc>, <&i2s0muxck>;
-		clock-names = "pclk", "gclk", "aclk", "muxclk";
+		clocks = <&i2s0_clk>, <&i2s0_gclk>, <&i2s0muxck>;
+		clock-names = "pclk", "gclk", "muxclk";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_i2s0_default>;
 	};
diff --git a/Documentation/devicetree/bindings/sound/audio-graph-card.txt b/Documentation/devicetree/bindings/sound/audio-graph-card.txt
index d04ea3b1a1dd..7e63e53a901c 100644
--- a/Documentation/devicetree/bindings/sound/audio-graph-card.txt
+++ b/Documentation/devicetree/bindings/sound/audio-graph-card.txt
@@ -18,6 +18,8 @@ Below are same as Simple-Card.
 - bitclock-inversion
 - frame-inversion
 - mclk-fs
+- hp-det-gpio
+- mic-det-gpio
 - dai-tdm-slot-num
 - dai-tdm-slot-width
 - clocks / system-clock-frequency
diff --git a/Documentation/devicetree/bindings/sound/cs35l33.txt b/Documentation/devicetree/bindings/sound/cs35l33.txt
index acfb47525b49..dc5a355d1a19 100644
--- a/Documentation/devicetree/bindings/sound/cs35l33.txt
+++ b/Documentation/devicetree/bindings/sound/cs35l33.txt
@@ -14,8 +14,6 @@ Optional properties:
 
   - reset-gpios : gpio used to reset the amplifier
 
-  - interrupt-parent : Specifies the phandle of the interrupt controller to
-    which the IRQs from CS35L33 are delivered to.
  -  interrupts : IRQ line info CS35L33.
     (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
     for further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/cs35l34.txt b/Documentation/devicetree/bindings/sound/cs35l34.txt
index b218ead2e68e..2f7606b7d542 100644
--- a/Documentation/devicetree/bindings/sound/cs35l34.txt
+++ b/Documentation/devicetree/bindings/sound/cs35l34.txt
@@ -21,8 +21,6 @@ Optional properties:
 
   - reset-gpios: GPIO used to reset the amplifier.
 
-  - interrupt-parent : Specifies the phandle of the interrupt controller to
-    which the IRQs from CS35L34 are delivered to.
   - interrupts : IRQ line info CS35L34.
     (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
     for further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/cs35l35.txt b/Documentation/devicetree/bindings/sound/cs35l35.txt
index 77ee75c39233..7915897f8a81 100644
--- a/Documentation/devicetree/bindings/sound/cs35l35.txt
+++ b/Documentation/devicetree/bindings/sound/cs35l35.txt
@@ -10,8 +10,6 @@ Required properties:
     as covered in
     Documentation/devicetree/bindings/regulator/regulator.txt.
 
-  - interrupt-parent : Specifies the phandle of the interrupt controller to
-    which the IRQs from CS35L35 are delivered to.
   - interrupts : IRQ line info CS35L35.
     (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
     for further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/cs42l42.txt b/Documentation/devicetree/bindings/sound/cs42l42.txt
index 9a2c5e2423d5..7dfaa2ab906f 100644
--- a/Documentation/devicetree/bindings/sound/cs42l42.txt
+++ b/Documentation/devicetree/bindings/sound/cs42l42.txt
@@ -15,9 +15,6 @@ Optional properties:
   - reset-gpios : a GPIO spec for the reset pin. If specified, it will be
   deasserted before communication to the codec starts.
 
-  - interrupt-parent : Specifies the phandle of the interrupt controller to
-  which the IRQs from CS42L42 are delivered to.
-
   - interrupts : IRQ line info CS42L42.
   (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
   for further information relating to interrupt properties)
@@ -107,4 +104,4 @@ cs42l42: cs42l42@48 {
 	cirrus,btn-det-event-dbnce = <10>;
 	cirrus,bias-lvls = <0x0F 0x08 0x04 0x01>;
 	cirrus,hs-bias-ramp-rate = <0x02>;
-};
\ No newline at end of file
+};
diff --git a/Documentation/devicetree/bindings/sound/da7218.txt b/Documentation/devicetree/bindings/sound/da7218.txt
index 3ab9dfef38d1..2cf30899bd0d 100644
--- a/Documentation/devicetree/bindings/sound/da7218.txt
+++ b/Documentation/devicetree/bindings/sound/da7218.txt
@@ -15,8 +15,6 @@ Required properties:
    information relating to regulators)
 
 Optional properties:
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the IRQs from DA7218 are delivered to.
 - interrupts: IRQ line info for DA7218 chip.
   (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt for
    further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/da7219.txt b/Documentation/devicetree/bindings/sound/da7219.txt
index c3df92d31c4b..e9d0baeb94e2 100644
--- a/Documentation/devicetree/bindings/sound/da7219.txt
+++ b/Documentation/devicetree/bindings/sound/da7219.txt
@@ -8,8 +8,6 @@ Required properties:
 - compatible : Should be "dlg,da7219"
 - reg: Specifies the I2C slave address
 
-- interrupt-parent : Specifies the phandle of the interrupt controller to which
-  the IRQs from DA7219 are delivered to.
 - interrupts : IRQ line info for DA7219.
   (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt for
    further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/dioo,dio2125.txt b/Documentation/devicetree/bindings/sound/dioo,dio2125.txt
deleted file mode 100644
index 63dbfe0f11d0..000000000000
--- a/Documentation/devicetree/bindings/sound/dioo,dio2125.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-DIO2125 Audio Driver
-
-Required properties:
-- compatible : "dioo,dio2125"
-- enable-gpios : the gpio connected to the enable pin of the dio2125
-
-Example:
-
-amp: analog-amplifier {
-	compatible = "dioo,dio2125";
-	enable-gpios = <&gpio GPIOH_3 0>;
-};
diff --git a/Documentation/devicetree/bindings/sound/everest,es7134.txt b/Documentation/devicetree/bindings/sound/everest,es7134.txt
index 5495a3cb8b7b..091666069bde 100644
--- a/Documentation/devicetree/bindings/sound/everest,es7134.txt
+++ b/Documentation/devicetree/bindings/sound/everest,es7134.txt
@@ -1,10 +1,15 @@
 ES7134 i2s DA converter
 
 Required properties:
-- compatible : "everest,es7134" or "everest,es7144"
+- compatible : "everest,es7134" or
+               "everest,es7144" or
+	       "everest,es7154"
+- VDD-supply : regulator phandle for the VDD supply
+- PVDD-supply: regulator phandle for the PVDD supply for the es7154
 
 Example:
 
 i2s_codec: external-codec {
 	compatible = "everest,es7134";
+	VDD-supply = <&vcc_5v>;
 };
diff --git a/Documentation/devicetree/bindings/sound/everest,es7241.txt b/Documentation/devicetree/bindings/sound/everest,es7241.txt
new file mode 100644
index 000000000000..28f82cf4959f
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/everest,es7241.txt
@@ -0,0 +1,28 @@
+ES7241 i2s AD converter
+
+Required properties:
+- compatible : "everest,es7241"
+- VDDP-supply: regulator phandle for the VDDA supply
+- VDDA-supply: regulator phandle for the VDDP supply
+- VDDD-supply: regulator phandle for the VDDD supply
+
+Optional properties:
+- reset-gpios: gpio connected to the reset pin
+- m0-gpios   : gpio connected to the m0 pin
+- m1-gpios   : gpio connected to the m1 pin
+- everest,sdout-pull-down:
+   Format used by the serial interface is controlled by pulling
+   the sdout. If the sdout is pulled down, leftj format is used.
+   If this property is not provided, sdout is assumed to pulled
+   up and i2s format is used
+
+Example:
+
+linein: audio-codec@2 {
+	#sound-dai-cells = <0>;
+	compatible = "everest,es7241";
+	VDDA-supply = <&vcc_3v3>;
+	VDDP-supply = <&vcc_3v3>;
+	VDDD-supply = <&vcc_3v3>;
+	reset-gpios = <&gpio GPIOH_42>;
+};
diff --git a/Documentation/devicetree/bindings/sound/fsl,ssi.txt b/Documentation/devicetree/bindings/sound/fsl,ssi.txt
index d415888e1316..7e15a85cecd2 100644
--- a/Documentation/devicetree/bindings/sound/fsl,ssi.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,ssi.txt
@@ -18,8 +18,6 @@ Required properties:
                     encoded based on the information in section 2)
                     depending on the type of interrupt controller you
                     have.
-- interrupt-parent: The phandle for the interrupt controller that
-                    services interrupts for this device.
 - fsl,fifo-depth:   The number of elements in the transmit and receive FIFOs.
                     This number is the maximum allowed value for SFCSR[TFWM0].
  - clocks:          "ipg" - Required clock for the SSI unit
diff --git a/Documentation/devicetree/bindings/sound/marvell,pxa2xx-ac97.txt b/Documentation/devicetree/bindings/sound/marvell,pxa2xx-ac97.txt
new file mode 100644
index 000000000000..2ea85d5be6a4
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/marvell,pxa2xx-ac97.txt
@@ -0,0 +1,27 @@
+Marvell PXA2xx audio complex
+
+This descriptions matches the AC97 controller found in pxa2xx and pxa3xx series.
+
+Required properties:
+  - compatible: should be one of the following:
+    "marvell,pxa250-ac97"
+    "marvell,pxa270-ac97"
+    "marvell,pxa300-ac97"
+  - reg: device MMIO address space
+  - interrupts: single interrupt generated by AC97 IP
+  - clocks: input clock of the AC97 IP, refer to clock-bindings.txt
+
+Optional properties:
+  - pinctrl-names, pinctrl-0: refer to pinctrl-bindings.txt
+  - reset-gpios: gpio used for AC97 reset, refer to gpio.txt
+
+Example:
+	ac97: sound@40500000 {
+		compatible = "marvell,pxa250-ac97";
+		reg = < 0x40500000 0x1000 >;
+		interrupts = <14>;
+		reset-gpios = <&gpio 113 GPIO_ACTIVE_HIGH>;
+		#sound-dai-cells = <1>;
+		pinctrl-names = "default";
+		pinctrl-0 = < &pmux_ac97_default >;
+	};
diff --git a/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt b/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt
index 74c9ba6c2823..93b982e9419f 100644
--- a/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt
+++ b/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt
@@ -5,6 +5,14 @@ Required properties:
 	compatible	Must be "mrvl,pxa-ssp-dai"
 	port		A phandle reference to a PXA ssp upstream device
 
+Optional properties:
+
+	clock-names
+	clocks		Through "clock-names" and "clocks", external clocks
+			can be configured. If a clock names "extclk" exists,
+			it will be set to the mclk rate of the audio stream
+			and be used as clock provider of the DAI.
+
 Example:
 
 	/* upstream device */
diff --git a/Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt b/Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt
deleted file mode 100644
index 551fbb8348c2..000000000000
--- a/Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-DT bindings for ARM PXA2xx PCM platform driver
-
-This is just a dummy driver that registers the PXA ASoC platform driver.
-It does not have any resources assigned.
-
-Required properties:
-
-	- compatible		'mrvl,pxa-pcm-audio'
-
-Example:
-
-	pxa_pcm_audio: snd_soc_pxa_audio {
-		compatible = "mrvl,pxa-pcm-audio";
-	};
-
diff --git a/Documentation/devicetree/bindings/sound/name-prefix.txt b/Documentation/devicetree/bindings/sound/name-prefix.txt
new file mode 100644
index 000000000000..645775908657
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/name-prefix.txt
@@ -0,0 +1,24 @@
+Name prefix:
+
+Card implementing the routing property define the connection between
+audio components as list of string pair. Component using the same
+sink/source names may use the name prefix property to prepend the
+name of their sinks/sources with the provided string.
+
+Optional name prefix property:
+- sound-name-prefix : string using as prefix for the sink/source names of
+		      the component.
+
+Example: Two instances of the same component.
+
+amp0: analog-amplifier@0 {
+	compatible = "simple-audio-amplifier";
+	enable-gpios = <&gpio GPIOH_3 0>;
+	sound-name-prefix = "FRONT";
+};
+
+amp1: analog-amplifier@1 {
+	compatible = "simple-audio-amplifier";
+	enable-gpios = <&gpio GPIOH_4 0>;
+	sound-name-prefix = "BACK";
+};
diff --git a/Documentation/devicetree/bindings/sound/omap-dmic.txt b/Documentation/devicetree/bindings/sound/omap-dmic.txt
index fd8105f18978..418e30e72e89 100644
--- a/Documentation/devicetree/bindings/sound/omap-dmic.txt
+++ b/Documentation/devicetree/bindings/sound/omap-dmic.txt
@@ -6,7 +6,6 @@ Required properties:
        <MPU access base address, size>,
        <L3 interconnect address, size>;
 - interrupts: Interrupt number for DMIC
-- interrupt-parent: The parent interrupt controller
 - ti,hwmods: Name of the hwmod associated with OMAP dmic IP
 
 Example:
diff --git a/Documentation/devicetree/bindings/sound/omap-mcbsp.txt b/Documentation/devicetree/bindings/sound/omap-mcbsp.txt
index 17cce4490456..ae8bf703ce7a 100644
--- a/Documentation/devicetree/bindings/sound/omap-mcbsp.txt
+++ b/Documentation/devicetree/bindings/sound/omap-mcbsp.txt
@@ -15,7 +15,6 @@ Required properties:
 	<TX irq>,
 	<RX irq>;
 - interrupt-names: Array of strings associated with the interrupt numbers
-- interrupt-parent: The parent interrupt controller
 - ti,buffer-size: Size of the FIFO on the port (OMAP2430 and newer SoC)
 - ti,hwmods: Name of the hwmod associated to the McBSP port
 
diff --git a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
index 0741dff048dd..5f4e68ca228c 100644
--- a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
+++ b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
@@ -6,7 +6,6 @@ Required properties:
        <MPU access base address, size>,
        <L3 interconnect address, size>;
 - interrupts: Interrupt number for McPDM
-- interrupt-parent: The parent interrupt controller
 - ti,hwmods: Name of the hwmod associated to the McPDM
 
 Example:
diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt b/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt
index 6a4aadc4ce06..84b28dbe9f15 100644
--- a/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt
@@ -30,7 +30,7 @@ Required properties:
 
 			  Board connectors:
 			  * Headset Mic
-			  * Secondary Mic",
+			  * Secondary Mic
 			  * DMIC
 			  * Ext Spk
 
diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
index aa54e49fc8a2..c814e867850f 100644
--- a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
@@ -7,7 +7,7 @@ This binding describes the APQ8096 sound card, which uses qdsp for audio.
 	Value type: <stringlist>
 	Definition: must be "qcom,apq8096-sndcard"
 
-- qcom,audio-routing:
+- audio-routing:
 	Usage: Optional
 	Value type: <stringlist>
 	Definition:  A list of the connections between audio components.
@@ -35,7 +35,7 @@ This binding describes the APQ8096 sound card, which uses qdsp for audio.
 			"Digital Mic3"
 
 		Audio pins and MicBias on WCD9335 Codec:
-			"MIC_BIAS1
+			"MIC_BIAS1"
 			"MIC_BIAS2"
 			"MIC_BIAS3"
 			"MIC_BIAS4"
@@ -49,6 +49,12 @@ This binding describes the APQ8096 sound card, which uses qdsp for audio.
 			"DMIC1"
 			"DMIC2"
 			"DMIC3"
+
+- model:
+	Usage: required
+	Value type: <stringlist>
+	Definition: The user-visible name of this sound card.
+
 = dailinks
 Each subnode of sndcard represents either a dailink, and subnodes of each
 dailinks would be cpu/codec/platform dais.
@@ -79,11 +85,16 @@ dailinks would be cpu/codec/platform dais.
 	Value type: <phandle with arguments>
 	Definition: dai phandle/s and port of CPU/CODEC/PLATFORM node.
 
+Obsolete:
+	qcom,model: String for soundcard name (Use model instead)
+	qcom,audio-routing: A list of the connections between audio components.
+			    (Use audio-routing instead)
+
 Example:
 
 audio {
 	compatible = "qcom,apq8096-sndcard";
-	qcom,model = "DB820c";
+	model = "DB820c";
 
 	mm1-dai-link {
 		link-name = "MultiMedia1";
diff --git a/Documentation/devicetree/bindings/sound/qcom,msm8916-wcd-analog.txt b/Documentation/devicetree/bindings/sound/qcom,msm8916-wcd-analog.txt
index 551ecab67efe..fdcea3d12ee5 100644
--- a/Documentation/devicetree/bindings/sound/qcom,msm8916-wcd-analog.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,msm8916-wcd-analog.txt
@@ -7,7 +7,6 @@ Bindings for codec Analog IP which is integrated in pmic pm8916,
 Required properties
  - compatible = "qcom,pm8916-wcd-analog-codec";
  - reg: represents the slave base address provided to the peripheral.
- - interrupt-parent : The parent interrupt controller.
  - interrupts: List of interrupts in given SPMI peripheral.
  - interrupt-names: Names specified to above list of interrupts in same
 		    order. List of supported interrupt names are:
diff --git a/Documentation/devicetree/bindings/sound/qcom,q6adm.txt b/Documentation/devicetree/bindings/sound/qcom,q6adm.txt
index cb709e5dbc44..bbae426cdfb1 100644
--- a/Documentation/devicetree/bindings/sound/qcom,q6adm.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,q6adm.txt
@@ -18,6 +18,11 @@ used by the apr service device.
 = ADM routing
 "routing" subnode of the ADM node represents adm routing specific configuration
 
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6adm-routing".
+
 - #sound-dai-cells
 	Usage: required
 	Value type: <u32>
@@ -28,6 +33,7 @@ q6adm@8 {
 	compatible = "qcom,q6adm";
 	reg = <APR_SVC_ADM>;
 	q6routing: routing {
+		compatible = "qcom,q6adm-routing";
 		#sound-dai-cells = <0>;
 	};
 };
diff --git a/Documentation/devicetree/bindings/sound/qcom,q6afe.txt b/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
index bdbf87df8c0b..a8179409c194 100644
--- a/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
@@ -17,6 +17,11 @@ used by all apr services. Must contain the following properties.
 subnode of "dais" representing board specific dai setup.
 "dais" node should have following properties followed by dai children.
 
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6afe-dais"
+
 - #sound-dai-cells
 	Usage: required
 	Value type: <u32>
@@ -100,6 +105,7 @@ q6afe@4 {
 	reg = <APR_SVC_AFE>;
 
 	dais {
+		compatible = "qcom,q6afe-dais";
 		#sound-dai-cells = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/Documentation/devicetree/bindings/sound/qcom,q6asm.txt b/Documentation/devicetree/bindings/sound/qcom,q6asm.txt
index 2178eb91146f..f9c7bd8c1bc0 100644
--- a/Documentation/devicetree/bindings/sound/qcom,q6asm.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,q6asm.txt
@@ -17,6 +17,11 @@ used by the apr service device.
 = ASM DAIs (Digial Audio Interface)
 "dais" subnode of the ASM node represents dai specific configuration
 
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6asm-dais".
+
 - #sound-dai-cells
 	Usage: required
 	Value type: <u32>
@@ -28,6 +33,7 @@ q6asm@7 {
 	compatible = "qcom,q6asm";
 	reg = <APR_SVC_ASM>;
 	q6asmdai: dais {
+		compatible = "qcom,q6asm-dais";
 		#sound-dai-cells = <1>;
 	};
 };
diff --git a/Documentation/devicetree/bindings/sound/qcom,sdm845.txt b/Documentation/devicetree/bindings/sound/qcom,sdm845.txt
new file mode 100644
index 000000000000..408c4837e6d5
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/qcom,sdm845.txt
@@ -0,0 +1,80 @@
+* Qualcomm Technologies Inc. SDM845 ASoC sound card driver
+
+This binding describes the SDM845 sound card, which uses qdsp for audio.
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,sdm845-sndcard"
+
+- audio-routing:
+	Usage: Optional
+	Value type: <stringlist>
+	Definition:  A list of the connections between audio components.
+		  Each entry is a pair of strings, the first being the
+		  connection's sink, the second being the connection's
+		  source. Valid names could be power supplies, MicBias
+		  of codec and the jacks on the board.
+
+- model:
+	Usage: required
+	Value type: <stringlist>
+	Definition: The user-visible name of this sound card.
+
+= dailinks
+Each subnode of sndcard represents either a dailink, and subnodes of each
+dailinks would be cpu/codec/platform dais.
+
+- link-name:
+	Usage: required
+	Value type: <string>
+	Definition: User friendly name for dai link
+
+= CPU, PLATFORM, CODEC dais subnodes
+- cpu:
+	Usage: required
+	Value type: <subnode>
+	Definition: cpu dai sub-node
+
+- codec:
+	Usage: required
+	Value type: <subnode>
+	Definition: codec dai sub-node
+
+- platform:
+	Usage: Optional
+	Value type: <subnode>
+	Definition: platform dai sub-node
+
+- sound-dai:
+	Usage: required
+	Value type: <phandle>
+	Definition: dai phandle/s and port of CPU/CODEC/PLATFORM node.
+
+Example:
+
+audio {
+	compatible = "qcom,sdm845-sndcard";
+	model = "sdm845-snd-card";
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&pri_mi2s_active &pri_mi2s_ws_active>;
+	pinctrl-1 = <&pri_mi2s_sleep &pri_mi2s_ws_sleep>;
+
+	mm1-dai-link {
+		link-name = "MultiMedia1";
+		cpu {
+			sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA1>;
+		};
+	};
+
+	pri-mi2s-dai-link {
+		link-name = "PRI MI2S Playback";
+		cpu {
+			sound-dai = <&q6afedai PRIMARY_MI2S_RX>;
+		};
+
+		platform {
+			sound-dai = <&q6routing>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt b/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt
new file mode 100644
index 000000000000..1d8d49e30af7
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt
@@ -0,0 +1,123 @@
+QCOM WCD9335 Codec
+
+Qualcomm WCD9335 Codec is a standalone Hi-Fi audio codec IC, supports
+Qualcomm Technologies, Inc. (QTI) multimedia solutions, including
+the MSM8996, MSM8976, and MSM8956 chipsets. It has in-built
+Soundwire controller, interrupt mux. It supports both I2S/I2C and
+SLIMbus audio interfaces.
+
+Required properties with SLIMbus Interface:
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: For SLIMbus interface it should be "slimMID,PID",
+		    textual representation of Manufacturer ID, Product Code,
+		    shall be in lower case hexadecimal with leading zeroes
+		    suppressed.  Refer to slimbus/bus.txt for details.
+		    Should be:
+		    "slim217,1a0" for MSM8996 and APQ8096 SoCs with SLIMbus.
+
+- reg
+	Usage: required
+	Value type: <u32 u32>
+	Definition: Should be ('Device index', 'Instance ID')
+
+- interrupts
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: Interrupts via WCD INTR1 and INTR2 pins
+
+- interrupt-names:
+	Usage: required
+	Value type: <String array>
+	Definition: Interrupt names of WCD INTR1 and INTR2
+	Should be: "intr1", "intr2"
+
+- reset-gpio:
+	Usage: required
+	Value type: <String Array>
+	Definition: Reset gpio line
+
+- qcom,ifd:
+	Usage: required
+	Value type: <phandle>
+	Definition: SLIM interface device
+
+- clocks:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: See clock-bindings.txt section "consumers". List of
+                three clock specifiers for mclk, mclk2 and slimbus clock.
+
+- clock-names:
+	Usage: required
+	Value type: <string>
+	Definition: Must contain "mclk", "mclk2" and "slimbus" strings.
+
+- vdd-buck-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V buck supply
+
+- vdd-buck-sido-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V SIDO buck supply
+
+- vdd-rx-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V rx supply
+
+- vdd-tx-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V tx supply
+
+- vdd-vbat-supply:
+	Usage: Optional
+	Value type: <phandle>
+	Definition: Should contain a reference to the vbat supply
+
+- vdd-micbias-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the micbias supply
+
+- vdd-io-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V io supply
+
+- interrupt-controller:
+	Usage: required
+	Definition: Indicating that this is a interrupt controller
+
+- #interrupt-cells:
+	Usage: required
+	Value type: <int>
+	Definition: should be 1
+
+#sound-dai-cells
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 1
+
+codec@1{
+	compatible = "slim217,1a0";
+	reg  = <1 0>;
+	interrupts = <&msmgpio 54 IRQ_TYPE_LEVEL_HIGH>;
+	interrupt-names = "intr2"
+	reset-gpio = <&msmgpio 64 0>;
+	qcom,ifd  = <&wc9335_ifd>;
+	clock-names = "mclk", "native";
+	clocks = <&rpmcc RPM_SMD_DIV_CLK1>,
+		 <&rpmcc RPM_SMD_BB_CLK1>;
+	vdd-buck-supply = <&pm8994_s4>;
+	vdd-rx-supply = <&pm8994_s4>;
+	vdd-buck-sido-supply = <&pm8994_s4>;
+	vdd-tx-supply = <&pm8994_s4>;
+	vdd-io-supply = <&pm8994_s4>;
+	#sound-dai-cells = <1>;
+}
diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
index b86d790f630f..9e764270c36b 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
@@ -352,6 +352,7 @@ Required properties:
 				    - "renesas,rcar_sound-r8a7794" (R-Car E2)
 				    - "renesas,rcar_sound-r8a7795" (R-Car H3)
 				    - "renesas,rcar_sound-r8a7796" (R-Car M3-W)
+				    - "renesas,rcar_sound-r8a77965" (R-Car M3-N)
 - reg				: Should contain the register physical address.
 				  required register is
 				   SRU/ADG/SSI      if generation1
diff --git a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
index b208a752576c..54aefab71f2c 100644
--- a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
@@ -7,6 +7,7 @@ Required properties:
 
 - compatible: should be one of the following:
    - "rockchip,rk3066-i2s": for rk3066
+   - "rockchip,px30-i2s", "rockchip,rk3066-i2s": for px30
    - "rockchip,rk3036-i2s", "rockchip,rk3066-i2s": for rk3036
    - "rockchip,rk3188-i2s", "rockchip,rk3066-i2s": for rk3188
    - "rockchip,rk3228-i2s", "rockchip,rk3066-i2s": for rk3228
diff --git a/Documentation/devicetree/bindings/sound/rt5514.txt b/Documentation/devicetree/bindings/sound/rt5514.txt
index b25ed08c7a5a..d2cc171f22f2 100644
--- a/Documentation/devicetree/bindings/sound/rt5514.txt
+++ b/Documentation/devicetree/bindings/sound/rt5514.txt
@@ -14,7 +14,6 @@ Optional properties:
 - clocks: The phandle of the master clock to the CODEC
 - clock-names: Should be "mclk"
 
-- interrupt-parent: The phandle for the interrupt controller.
 - interrupts: The interrupt number to the cpu. The interrupt specifier format
 	      depends on the interrupt controller.
 
diff --git a/Documentation/devicetree/bindings/sound/rt5682.txt b/Documentation/devicetree/bindings/sound/rt5682.txt
new file mode 100644
index 000000000000..312e9a129530
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rt5682.txt
@@ -0,0 +1,50 @@
+RT5682 audio CODEC
+
+This device supports I2C only.
+
+Required properties:
+
+- compatible : "realtek,rt5682" or "realtek,rt5682i"
+
+- reg : The I2C address of the device.
+
+Optional properties:
+
+- interrupts : The CODEC's interrupt output.
+
+- realtek,dmic1-data-pin
+  0: dmic1 is not used
+  1: using GPIO2 pin as dmic1 data pin
+  2: using GPIO5 pin as dmic1 data pin
+
+- realtek,dmic1-clk-pin
+  0: using GPIO1 pin as dmic1 clock pin
+  1: using GPIO3 pin as dmic1 clock pin
+
+- realtek,jd-src
+  0: No JD is used
+  1: using JD1 as JD source
+
+- realtek,ldo1-en-gpios : The GPIO that controls the CODEC's LDO1_EN pin.
+
+Pins on the device (for linking into audio routes) for RT5682:
+
+  * DMIC L1
+  * DMIC R1
+  * IN1P
+  * HPOL
+  * HPOR
+
+Example:
+
+rt5682 {
+	compatible = "realtek,rt5682i";
+	reg = <0x1a>;
+	interrupt-parent = <&gpio>;
+	interrupts = <TEGRA_GPIO(U, 6) GPIO_ACTIVE_HIGH>;
+	realtek,ldo1-en-gpios =
+		<&gpio TEGRA_GPIO(R, 2) GPIO_ACTIVE_HIGH>;
+	realtek,dmic1-data-pin = <1>;
+	realtek,dmic1-clk-pin = <1>;
+	realtek,jd-src = <1>;
+};
diff --git a/Documentation/devicetree/bindings/sound/sgtl5000.txt b/Documentation/devicetree/bindings/sound/sgtl5000.txt
index 0f214457476f..9c58f724396a 100644
--- a/Documentation/devicetree/bindings/sound/sgtl5000.txt
+++ b/Documentation/devicetree/bindings/sound/sgtl5000.txt
@@ -17,7 +17,7 @@ Optional properties:
 
 - VDDD-supply : the regulator provider of VDDD
 
-- micbias-resistor-k-ohms : the bias resistor to be used in kOmhs
+- micbias-resistor-k-ohms : the bias resistor to be used in kOhms
 	The resistor can take values of 2k, 4k or 8k.
 	If set to 0 it will be off.
 	If this node is not mentioned or if the value is unknown, then
diff --git a/Documentation/devicetree/bindings/sound/simple-amplifier.txt b/Documentation/devicetree/bindings/sound/simple-amplifier.txt
new file mode 100644
index 000000000000..8647edae7af0
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/simple-amplifier.txt
@@ -0,0 +1,12 @@
+Simple Amplifier Audio Driver
+
+Required properties:
+- compatible : "dioo,dio2125" or "simple-audio-amplifier"
+- enable-gpios : the gpio connected to the enable pin of the simple amplifier
+
+Example:
+
+amp: analog-amplifier {
+	compatible = "simple-audio-amplifier";
+	enable-gpios = <&gpio GPIOH_3 0>;
+};
diff --git a/Documentation/devicetree/bindings/sound/tas571x.txt b/Documentation/devicetree/bindings/sound/tas571x.txt
index b4959f10b74b..7c8fd37c2f9e 100644
--- a/Documentation/devicetree/bindings/sound/tas571x.txt
+++ b/Documentation/devicetree/bindings/sound/tas571x.txt
@@ -7,6 +7,7 @@ powerdown (optional).
 Required properties:
 
 - compatible: should be one of the following:
+  - "ti,tas5707"
   - "ti,tas5711",
   - "ti,tas5717",
   - "ti,tas5719",
diff --git a/Documentation/devicetree/bindings/sound/ts3a227e.txt b/Documentation/devicetree/bindings/sound/ts3a227e.txt
index a836881d9608..3ed8359144d3 100644
--- a/Documentation/devicetree/bindings/sound/ts3a227e.txt
+++ b/Documentation/devicetree/bindings/sound/ts3a227e.txt
@@ -10,7 +10,6 @@ Required properties:
 
  - compatible:		Should contain "ti,ts3a227e".
  - reg:			The i2c address. Should contain <0x3b>.
- - interrupt-parent:	The parent interrupt controller
  - interrupts:		Interrupt number for /INT pin from the 227e
 
 Optional properies:
diff --git a/Documentation/devicetree/bindings/sound/ux500-msp.txt b/Documentation/devicetree/bindings/sound/ux500-msp.txt
index 99acd9c774e1..7dd1b96160f5 100644
--- a/Documentation/devicetree/bindings/sound/ux500-msp.txt
+++ b/Documentation/devicetree/bindings/sound/ux500-msp.txt
@@ -6,7 +6,6 @@ Required properties:
 
 Optional properties:
  - interrupts       : The interrupt output from the device.
- - interrupt-parent : The parent interrupt controller.
  - <name>-supply    : Phandle to the regulator <name> supply
 
 Example:
diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt
index 4a9dead1b7d3..68cccc4653ba 100644
--- a/Documentation/devicetree/bindings/sound/wm8994.txt
+++ b/Documentation/devicetree/bindings/sound/wm8994.txt
@@ -26,7 +26,6 @@ Optional properties:
   - interrupt-controller : These devices contain interrupt controllers
     and may provide interrupt services to other devices if they have an
     interrupt line connected.
-  - interrupt-parent : The parent interrupt controller.
   - #interrupt-cells: the number of cells to describe an IRQ, this should be 2.
     The first cell is the IRQ number.
     The second cell is the flags, encoded as the trigger masks from
@@ -57,6 +56,12 @@ Optional properties:
 
   - wlf,ldoena-always-driven : If present LDOENA is always driven.
 
+  - wlf,spkmode-pu : If present enable the internal pull-up resistor on
+    the SPKMODE pin.
+
+  - wlf,csnaddr-pd : If present enable the internal pull-down resistor on
+    the CS/ADDR pin.
+
 Example:
 
 wm8994: codec@1a {
diff --git a/Documentation/devicetree/bindings/spi/fsl-spi.txt b/Documentation/devicetree/bindings/spi/fsl-spi.txt
index a2331372068c..8854004a1d3a 100644
--- a/Documentation/devicetree/bindings/spi/fsl-spi.txt
+++ b/Documentation/devicetree/bindings/spi/fsl-spi.txt
@@ -12,8 +12,6 @@ Required properties:
   information for the interrupt.  This should be encoded based on
   the information in section 2) depending on the type of interrupt
   controller you have.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 - clock-frequency : input clock frequency to non FSL_SOC cores
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/spi/sh-hspi.txt b/Documentation/devicetree/bindings/spi/sh-hspi.txt
index 585fed90376e..b9d1e4d11a77 100644
--- a/Documentation/devicetree/bindings/spi/sh-hspi.txt
+++ b/Documentation/devicetree/bindings/spi/sh-hspi.txt
@@ -6,8 +6,6 @@ Required properties:
 		       - "renesas,hspi-r8a7778" (R-Car M1)
 		       - "renesas,hspi-r8a7779" (R-Car H1)
 - reg              : Offset and length of the register set for the device
-- interrupt-parent : The phandle for the interrupt controller that
-		     services interrupts for this device
 - interrupts       : Interrupt specifier
 - #address-cells   : Must be <1>
 - #size-cells      : Must be <0>
diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt
index 39806329c193..bfbc2035fb6b 100644
--- a/Documentation/devicetree/bindings/spi/sh-msiof.txt
+++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt
@@ -29,8 +29,6 @@ Required properties:
 			 If two register sets are present, the first is to be
 			 used by the CPU, and the second is to be used by the
 			 DMA engine.
-- interrupt-parent     : The phandle for the interrupt controller that
-			 services interrupts for this device
 - interrupts           : Interrupt specifier
 - #address-cells       : Must be <1>
 - #size-cells          : Must be <0>
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
index 204b311e0400..642d3fb1ef85 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
@@ -1,8 +1,10 @@
 Synopsys DesignWare AMBA 2.0 Synchronous Serial Interface.
 
 Required properties:
-- compatible : "snps,dw-apb-ssi"
-- reg : The register base for the controller.
+- compatible : "snps,dw-apb-ssi" or "mscc,<soc>-spi", where soc is "ocelot" or
+  "jaguar2"
+- reg : The register base for the controller. For "mscc,<soc>-spi", a second
+  register set is required (named ICPU_CFG:SPI_MST)
 - interrupts : One interrupt, used by the controller.
 - #address-cells : <1>, as required by generic SPI binding.
 - #size-cells : <0>, also as required by generic SPI binding.
diff --git a/Documentation/devicetree/bindings/spi/spi-cadence.txt b/Documentation/devicetree/bindings/spi/spi-cadence.txt
index 94f09141a4f0..05a2ef945664 100644
--- a/Documentation/devicetree/bindings/spi/spi-cadence.txt
+++ b/Documentation/devicetree/bindings/spi/spi-cadence.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg			: Physical base address and size of SPI registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
-- interrupt-parent	: Must be core interrupt controller
 - clock-names		: List of input clock names - "ref_clk", "pclk"
 			  (See clock bindings for details).
 - clocks		: Clock phandles (see clock bindings for details).
diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt
index 225ace1d0c65..4af132606b37 100644
--- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible :
   - "fsl,imx7ulp-spi" for LPSPI compatible with the one integrated on i.MX7ULP soc
 - reg : address and length of the lpspi master registers
-- interrupt-parent : core interrupt controller
 - interrupts : lpspi interrupt
 - clocks : lpspi clock specifier
 
diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.txt b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
index 6e3ffacbba32..a0edac12d8df 100644
--- a/Documentation/devicetree/bindings/spi/spi-rockchip.txt
+++ b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
@@ -7,6 +7,7 @@ Required Properties:
 
 - compatible: should be one of the following.
     "rockchip,rv1108-spi" for rv1108 SoCs.
+    "rockchip,px30-spi", "rockchip,rk3066-spi" for px30 SoCs.
     "rockchip,rk3036-spi" for rk3036 SoCS.
     "rockchip,rk3066-spi" for rk3066 SoCs.
     "rockchip,rk3188-spi" for rk3188 SoCs.
diff --git a/Documentation/devicetree/bindings/spi/spi-rspi.txt b/Documentation/devicetree/bindings/spi/spi-rspi.txt
index 3b02b3a7cfb2..96fd58548f69 100644
--- a/Documentation/devicetree/bindings/spi/spi-rspi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-rspi.txt
@@ -28,8 +28,6 @@ Required properties:
 		       - "rx" for SPRI,
 		       - "tx" to SPTI,
 		       - "mux" for a single muxed interrupt.
-- interrupt-parent : The phandle for the interrupt controller that
-		     services interrupts for this device.
 - num-cs	   : Number of chip selects. Some RSPI cores have more than 1.
 - #address-cells   : Must be <1>
 - #size-cells      : Must be <0>
diff --git a/Documentation/devicetree/bindings/spi/spi-uniphier.txt b/Documentation/devicetree/bindings/spi/spi-uniphier.txt
new file mode 100644
index 000000000000..504a4ecfc7b1
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-uniphier.txt
@@ -0,0 +1,22 @@
+Socionext UniPhier SPI controller driver
+
+UniPhier SoCs have SCSSI which supports SPI single channel.
+
+Required properties:
+ - compatible: should be "socionext,uniphier-scssi"
+ - reg: address and length of the spi master registers
+ - #address-cells: must be <1>, see spi-bus.txt
+ - #size-cells: must be <0>, see spi-bus.txt
+ - clocks: A phandle to the clock for the device.
+ - resets: A phandle to the reset control for the device.
+
+Example:
+
+spi0: spi@54006000 {
+	compatible = "socionext,uniphier-scssi";
+	reg = <0x54006000 0x100>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	clocks = <&peri_clk 11>;
+	resets = <&peri_rst 11>;
+};
diff --git a/Documentation/devicetree/bindings/spi/spi-xilinx.txt b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
index 7bf61efc66c8..dc924a5f71db 100644
--- a/Documentation/devicetree/bindings/spi/spi-xilinx.txt
+++ b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg			: Physical base address and size of SPI registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
-- interrupt-parent	: Must be core interrupt controller
 
 Optional properties:
 - xlnx,num-ss-bits	: Number of chip selects used.
diff --git a/Documentation/devicetree/bindings/spi/spi-xlp.txt b/Documentation/devicetree/bindings/spi/spi-xlp.txt
index 40e82d51efec..f4925ec0ed33 100644
--- a/Documentation/devicetree/bindings/spi/spi-xlp.txt
+++ b/Documentation/devicetree/bindings/spi/spi-xlp.txt
@@ -13,7 +13,6 @@ Required properties:
 - reg			: Should contain register location and length.
 - clocks		: Phandle of the spi clock
 - interrupts		: Interrupt number used by this controller.
-- interrupt-parent	: Phandle of the parent interrupt controller.
 
 SPI slave nodes must be children of the SPI master node and can contain
 properties described in Documentation/devicetree/bindings/spi/spi-bus.txt.
diff --git a/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt
index c8f50e5cf70b..0f6d37ff541c 100644
--- a/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg			: Physical base address and size of GQSPI registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
-- interrupt-parent	: Must be core interrupt controller.
 - clock-names		: List of input clock names - "ref_clk", "pclk"
 			  (See clock bindings for details).
 - clocks		: Clock phandles (see clock bindings for details).
diff --git a/Documentation/devicetree/bindings/sram/sram.txt b/Documentation/devicetree/bindings/sram/sram.txt
index 267da4410aef..e98908bd4227 100644
--- a/Documentation/devicetree/bindings/sram/sram.txt
+++ b/Documentation/devicetree/bindings/sram/sram.txt
@@ -50,6 +50,8 @@ Optional properties in the area nodes:
 		 manipulation of the page attributes.
 - label : the name for the reserved partition, if omitted, the label
           is taken from the node name excluding the unit address.
+- clocks : a list of phandle and clock specifier pair that controls the
+	   single SRAM clock.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/staging/iio/adc/spear-adc.txt b/Documentation/devicetree/bindings/staging/iio/adc/spear-adc.txt
index 02ea23a63f20..88bc94fe1f6d 100644
--- a/Documentation/devicetree/bindings/staging/iio/adc/spear-adc.txt
+++ b/Documentation/devicetree/bindings/staging/iio/adc/spear-adc.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: Should be "st,spear600-adc"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the ADC interrupt
 - sampling-frequency: Default sampling frequency
 
diff --git a/Documentation/devicetree/bindings/thermal/brcm,avs-tmon.txt b/Documentation/devicetree/bindings/thermal/brcm,avs-tmon.txt
index 9d43553a8d39..43a9ed545944 100644
--- a/Documentation/devicetree/bindings/thermal/brcm,avs-tmon.txt
+++ b/Documentation/devicetree/bindings/thermal/brcm,avs-tmon.txt
@@ -7,7 +7,6 @@ Required properties:
 - reg: address range for the AVS TMON registers
 - interrupts: temperature monitor interrupt, for high/low threshold triggers
 - interrupt-names: should be "tmon"
-- interrupt-parent: the parent interrupt controller
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
index ad648d93d961..33004ce7e5df 100644
--- a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
@@ -13,7 +13,6 @@
 			Exynos5420 (Must pass triminfo base and triminfo clock)
                "samsung,exynos5433-tmu"
 	       "samsung,exynos7-tmu"
-- interrupt-parent : The phandle for the interrupt controller
 - reg : Address range of the thermal registers. For soc's which has multiple
 	instances of TMU and some registers are shared across all TMU's like
 	interrupt related then 2 set of register has to supplied. First set
diff --git a/Documentation/devicetree/bindings/timer/altr,timer-1.0.txt b/Documentation/devicetree/bindings/timer/altr,timer-1.0.txt
index 904a5846d7ac..e698e3488735 100644
--- a/Documentation/devicetree/bindings/timer/altr,timer-1.0.txt
+++ b/Documentation/devicetree/bindings/timer/altr,timer-1.0.txt
@@ -4,7 +4,6 @@ Required properties:
 
 - compatible : should be "altr,timer-1.0"
 - reg : Specifies base physical address and size of the registers.
-- interrupt-parent: phandle of the interrupt controller
 - interrupts : Should contain the timer interrupt number
 - clock-frequency : The frequency of the clock that drives the counter, in Hz.
 
diff --git a/Documentation/devicetree/bindings/timer/fsl,gtm.txt b/Documentation/devicetree/bindings/timer/fsl,gtm.txt
index 9a33efded4bc..fc1c571f7412 100644
--- a/Documentation/devicetree/bindings/timer/fsl,gtm.txt
+++ b/Documentation/devicetree/bindings/timer/fsl,gtm.txt
@@ -7,7 +7,6 @@ Required properties:
     "fsl,<chip>-cpm2-gtm", "fsl,cpm2-gtm", "fsl,gtm" for CPM2 GTMs
   - reg : should contain gtm registers location and length (0x40).
   - interrupts : should contain four interrupts.
-  - interrupt-parent : interrupt source phandle.
   - clock-frequency : specifies the frequency driving the timer.
 
 Example:
diff --git a/Documentation/devicetree/bindings/timer/marvell,orion-timer.txt b/Documentation/devicetree/bindings/timer/marvell,orion-timer.txt
index 62bb8260cf6a..cd1a0c256f94 100644
--- a/Documentation/devicetree/bindings/timer/marvell,orion-timer.txt
+++ b/Documentation/devicetree/bindings/timer/marvell,orion-timer.txt
@@ -3,7 +3,6 @@ Marvell Orion SoC timer
 Required properties:
 - compatible: shall be "marvell,orion-timer"
 - reg: base address of the timer register starting with TIMERS CONTROL register
-- interrupt-parent: phandle of the bridge interrupt controller
 - interrupts: should contain the interrupts for Timer0 and Timer1
 - clocks: phandle of timer reference clock (tclk)
 
diff --git a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
index b1fe7e9de1b4..18d4d0166c76 100644
--- a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
+++ b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
@@ -1,19 +1,25 @@
-Mediatek MT6577, MT6572 and MT6589 Timers
----------------------------------------
+Mediatek Timers
+---------------
+
+Mediatek SoCs have two different timers on different platforms,
+- GPT (General Purpose Timer)
+- SYST (System Timer)
+
+The proper timer will be selected automatically by driver.
 
 Required properties:
 - compatible should contain:
-	* "mediatek,mt2701-timer" for MT2701 compatible timers
-	* "mediatek,mt6580-timer" for MT6580 compatible timers
-	* "mediatek,mt6589-timer" for MT6589 compatible timers
-	* "mediatek,mt7623-timer" for MT7623 compatible timers
-	* "mediatek,mt8127-timer" for MT8127 compatible timers
-	* "mediatek,mt8135-timer" for MT8135 compatible timers
-	* "mediatek,mt8173-timer" for MT8173 compatible timers
-	* "mediatek,mt6577-timer" for MT6577 and all above compatible timers
-- reg: Should contain location and length for timers register.
-- clocks: Clocks driving the timer hardware. This list should include two
-	clocks. The order is system clock and as second clock the RTC clock.
+	* "mediatek,mt2701-timer" for MT2701 compatible timers (GPT)
+	* "mediatek,mt6580-timer" for MT6580 compatible timers (GPT)
+	* "mediatek,mt6589-timer" for MT6589 compatible timers (GPT)
+	* "mediatek,mt7623-timer" for MT7623 compatible timers (GPT)
+	* "mediatek,mt8127-timer" for MT8127 compatible timers (GPT)
+	* "mediatek,mt8135-timer" for MT8135 compatible timers (GPT)
+	* "mediatek,mt8173-timer" for MT8173 compatible timers (GPT)
+	* "mediatek,mt6577-timer" for MT6577 and all above compatible timers (GPT)
+	* "mediatek,mt6765-timer" for MT6765 compatible timers (SYST)
+- reg: Should contain location and length for timer register.
+- clocks: Should contain system clock.
 
 Examples:
 
@@ -21,5 +27,5 @@ Examples:
 		compatible = "mediatek,mt6577-timer";
 		reg = <0x10008000 0x80>;
 		interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_LOW>;
-		clocks = <&system_clk>, <&rtc_clk>;
+		clocks = <&system_clk>;
 	};
diff --git a/Documentation/devicetree/bindings/timer/snps,arc-timer.txt b/Documentation/devicetree/bindings/timer/snps,arc-timer.txt
index 4ef024630d61..147ef3e74452 100644
--- a/Documentation/devicetree/bindings/timer/snps,arc-timer.txt
+++ b/Documentation/devicetree/bindings/timer/snps,arc-timer.txt
@@ -12,10 +12,6 @@ Required properties:
 	       (16 for ARCHS cores, 3 for ARC700 cores)
 - clocks     : phandle to the source clock
 
-Optional properties:
-
-- interrupt-parent : phandle to parent intc
-
 Example:
 
 	timer0 {
diff --git a/Documentation/devicetree/bindings/timer/st,spear-timer.txt b/Documentation/devicetree/bindings/timer/st,spear-timer.txt
index c0017221cf55..b5238a07da17 100644
--- a/Documentation/devicetree/bindings/timer/st,spear-timer.txt
+++ b/Documentation/devicetree/bindings/timer/st,spear-timer.txt
@@ -5,8 +5,6 @@
 - compatible : Should be:
 	"st,spear-timer"
 - reg: Address range of the timer registers
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupt: Should contain the timer interrupt number
 
 Example:
diff --git a/Documentation/devicetree/bindings/timer/ti,c64x+timer64.txt b/Documentation/devicetree/bindings/timer/ti,c64x+timer64.txt
index 95911fe70224..d96c1e283e73 100644
--- a/Documentation/devicetree/bindings/timer/ti,c64x+timer64.txt
+++ b/Documentation/devicetree/bindings/timer/ti,c64x+timer64.txt
@@ -7,7 +7,6 @@ Required properties:
 
 - compatible: must be "ti,c64x+timer64"
 - reg: base address and size of register region
-- interrupt-parent: interrupt controller
 - interrupts: interrupt id
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/usb/fsl-usb.txt b/Documentation/devicetree/bindings/usb/fsl-usb.txt
index 4779c029b675..0b08b006c5ea 100644
--- a/Documentation/devicetree/bindings/usb/fsl-usb.txt
+++ b/Documentation/devicetree/bindings/usb/fsl-usb.txt
@@ -33,8 +33,6 @@ Recommended properties :
    information for the interrupt.  This should be encoded based on
    the information in section 2) depending on the type of interrupt
    controller you have.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Optional properties :
  - fsl,invert-drvvbus : boolean; for MPC5121 USB0 only. Indicates the
diff --git a/Documentation/devicetree/bindings/usb/maxim,max3421.txt b/Documentation/devicetree/bindings/usb/maxim,max3421.txt
index 8cdbe0c85188..90495b1aeec2 100644
--- a/Documentation/devicetree/bindings/usb/maxim,max3421.txt
+++ b/Documentation/devicetree/bindings/usb/maxim,max3421.txt
@@ -11,9 +11,6 @@ Required properties:
    The driver configures MAX3421E for active low level triggered interrupts,
    configure your interrupt line accordingly.
 
-Optional property:
- - interrupt-parent: the phandle to the associated interrupt controller.
-
 Example:
 
 	usb@0 {
diff --git a/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt b/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt
index 09e847e92e5e..d4cf53c071d9 100644
--- a/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt
+++ b/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt
@@ -3,8 +3,6 @@ Richtek RT1711H TypeC PD Controller.
 Required properties:
  - compatible : Must be "richtek,rt1711h".
  - reg : Must be 0x4e, it's slave address of RT1711H.
- - interrupt-parent : the phandle for the interrupt controller that
-   provides interrupts for this device.
  - interrupts : <a b> where a is the interrupt number and b represents an
    encoding of the sense and level information for the interrupt.
 
diff --git a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt
index 252a05c5d976..c8c4b00ecb94 100644
--- a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt
@@ -16,7 +16,8 @@ A child node must exist to represent the core DWC3 IP block. The name of
 the node is not important. The content of the node is defined in dwc3.txt.
 
 Phy documentation is provided in the following places:
-Documentation/devicetree/bindings/phy/qcom-dwc3-usb-phy.txt
+Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY
+Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt     - Type-C PHY
 
 Example device nodes:
 
diff --git a/Documentation/devicetree/bindings/usb/samsung-hsotg.txt b/Documentation/devicetree/bindings/usb/samsung-hsotg.txt
index b83d428a265e..0388634598ce 100644
--- a/Documentation/devicetree/bindings/usb/samsung-hsotg.txt
+++ b/Documentation/devicetree/bindings/usb/samsung-hsotg.txt
@@ -14,8 +14,6 @@ Binding details
 Required properties:
 - compatible: "samsung,s3c6400-hsotg" should be used for all currently
     supported SoC,
-- interrupt-parent: phandle for the interrupt controller to which the
-    interrupt signal of the HSOTG block is routed,
 - interrupts: specifier of interrupt signal of interrupt controller,
     according to bindings of interrupt controller,
 - clocks: contains an array of clock specifiers:
diff --git a/Documentation/devicetree/bindings/usb/spear-usb.txt b/Documentation/devicetree/bindings/usb/spear-usb.txt
index f8a464a25653..1dc91cc459c0 100644
--- a/Documentation/devicetree/bindings/usb/spear-usb.txt
+++ b/Documentation/devicetree/bindings/usb/spear-usb.txt
@@ -6,8 +6,6 @@ EHCI:
 
 Required properties:
 - compatible: "st,spear600-ehci"
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the EHCI interrupt
 
 Example:
@@ -25,8 +23,6 @@ OHCI:
 
 Required properties:
 - compatible: "st,spear600-ohci"
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the OHCI interrupt
 
 Example:
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 7cad066191ee..c401d10335bc 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -41,6 +41,7 @@ arrow	Arrow Electronics
 artesyn	Artesyn Embedded Technologies Inc.
 asahi-kasei	Asahi Kasei Corp.
 aspeed	ASPEED Technology Inc.
+asus	AsusTek Computer Inc.
 atlas	Atlas Scientific LLC
 atmel	Atmel Corporation
 auo	AU Optronics Corporation
@@ -53,6 +54,7 @@ axentia	Axentia Technologies AB
 axis	Axis Communications AB
 bananapi BIPAI KEJI LIMITED
 bhf	Beckhoff Automation GmbH & Co. KG
+bitmain	Bitmain Technologies
 boe	BOE Technology Group Co., Ltd.
 bosch	Bosch Sensortec GmbH
 boundary	Boundary Devices Inc.
@@ -412,6 +414,7 @@ xes	Extreme Engineering Solutions (X-ES)
 xillybus	Xillybus Ltd.
 xlnx	Xilinx
 xunlong	Shenzhen Xunlong Software CO.,Limited
+ysoft	Y Soft Corporation a.s.
 zarlink	Zarlink Semiconductor
 zeitec	ZEITEC Semiconductor Co., LTD.
 zidoo	Shenzhen Zidoo Technology Co., Ltd.
diff --git a/Documentation/devicetree/bindings/w1/w1-gpio.txt b/Documentation/devicetree/bindings/w1/w1-gpio.txt
index 6e09c35d9f1a..37091902a021 100644
--- a/Documentation/devicetree/bindings/w1/w1-gpio.txt
+++ b/Documentation/devicetree/bindings/w1/w1-gpio.txt
@@ -15,7 +15,7 @@ Optional properties:
 
 Examples:
 
-	onewire@0 {
+	onewire {
 		compatible = "w1-gpio";
 		gpios = <&gpio 126 0>, <&gpio 105 0>;
 	};
diff --git a/Documentation/devicetree/bindings/watchdog/cadence-wdt.txt b/Documentation/devicetree/bindings/watchdog/cadence-wdt.txt
index c3a36ee45552..750a87657448 100644
--- a/Documentation/devicetree/bindings/watchdog/cadence-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/cadence-wdt.txt
@@ -5,7 +5,6 @@ Required properties:
 - compatible		: Should be "cdns,wdt-r1p2".
 - clocks		: This is pclk (APB clock).
 - interrupts		: This is wd_irq - watchdog timeout interrupt.
-- interrupt-parent	: Must be core interrupt controller.
 
 Optional properties
 - reset-on-timeout	: If this property exists, then a reset is done
diff --git a/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt b/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt
index d7bab3db9d1f..05b95bfa2a89 100644
--- a/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt
@@ -5,7 +5,6 @@ Required properties:
 - reg: physical base address of the controller and length of the register range
 
 Optional properties:
-- interrupt-parent: phandle to the INTC device node
 - interrupts: Specify the INTC interrupt number
 
 Example:
diff --git a/Documentation/devicetree/bindings/xilinx.txt b/Documentation/devicetree/bindings/xilinx.txt
index 1d11b9002ef8..d058ace29345 100644
--- a/Documentation/devicetree/bindings/xilinx.txt
+++ b/Documentation/devicetree/bindings/xilinx.txt
@@ -49,7 +49,7 @@
    followed by an older IP core version which implements the same
    interface or any other device with the same interface.
 
-   'reg', 'interrupt-parent' and 'interrupts' are all optional properties.
+   'reg' and 'interrupts' are all optional properties.
 
    For example, the following block from system.mhs:
 
diff --git a/Documentation/devicetree/bindings/xillybus/xillybus.txt b/Documentation/devicetree/bindings/xillybus/xillybus.txt
index 9e316dc2e40f..e65d1f94b49c 100644
--- a/Documentation/devicetree/bindings/xillybus/xillybus.txt
+++ b/Documentation/devicetree/bindings/xillybus/xillybus.txt
@@ -4,8 +4,6 @@ Required properties:
 - compatible: Should be "xillybus,xillybus-1.00.a"
 - reg: Address and length of the register set for the device
 - interrupts: Contains one interrupt node, typically consisting of three cells.
-- interrupt-parent: the phandle for the interrupt controller that
-                    services interrupts for this device.
 
 Optional properties:
 - dma-coherent: Present if DMA operations are coherent
diff --git a/Documentation/devicetree/dynamic-resolution-notes.txt b/Documentation/devicetree/dynamic-resolution-notes.txt
index 083d23262abe..c24ec366c5dc 100644
--- a/Documentation/devicetree/dynamic-resolution-notes.txt
+++ b/Documentation/devicetree/dynamic-resolution-notes.txt
@@ -2,15 +2,14 @@ Device Tree Dynamic Resolver Notes
 ----------------------------------
 
 This document describes the implementation of the in-kernel
-Device Tree resolver, residing in drivers/of/resolver.c and is a
-companion document to Documentation/devicetree/dt-object-internal.txt[1]
+Device Tree resolver, residing in drivers/of/resolver.c
 
 How the resolver works
 ----------------------
 
 The resolver is given as an input an arbitrary tree compiled with the
 proper dtc option and having a /plugin/ tag. This generates the
-appropriate __fixups__ & __local_fixups__ nodes as described in [1].
+appropriate __fixups__ & __local_fixups__ nodes.
 
 In sequence the resolver works by the following steps:
 
diff --git a/Documentation/doc-guide/kernel-doc.rst b/Documentation/doc-guide/kernel-doc.rst
index 80383b1a574a..8db53cdc225f 100644
--- a/Documentation/doc-guide/kernel-doc.rst
+++ b/Documentation/doc-guide/kernel-doc.rst
@@ -488,14 +488,19 @@ doc: *title*
     .. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
        :doc: High Definition Audio over HDMI and Display Port
 
-functions: *function* *[...]*
+functions: *[ function ...]*
   Include documentation for each *function* in *source*.
+  If no *function* if specified, the documentaion for all functions
+  and types in the *source* will be included.
 
-  Example::
+  Examples::
 
     .. kernel-doc:: lib/bitmap.c
        :functions: bitmap_parselist bitmap_parselist_user
 
+    .. kernel-doc:: lib/idr.c
+       :functions:
+
 Without options, the kernel-doc directive includes all documentation comments
 from the source file.
 
diff --git a/Documentation/doc-guide/parse-headers.rst b/Documentation/doc-guide/parse-headers.rst
index 82a3e43b6864..24cfaa15dd81 100644
--- a/Documentation/doc-guide/parse-headers.rst
+++ b/Documentation/doc-guide/parse-headers.rst
@@ -32,7 +32,7 @@ SYNOPSIS
 
 \ **parse_headers.pl**\  [<options>] <C_FILE> <OUT_FILE> [<EXCEPTIONS_FILE>]
 
-Where <options> can be: --debug, --help or --man.
+Where <options> can be: --debug, --help or --usage.
 
 
 OPTIONS
@@ -133,7 +133,7 @@ For both statements, \ **type**\  can be either one of the following:
 
 \ **symbol**\
 
- The ignore or replace statement will apply to the name of enum statements
+ The ignore or replace statement will apply to the name of enum value
  at C_FILE.
 
  For replace statements, \ **new_value**\  will automatically use :c:type:
diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst
index a2417633fdd8..f0796daa95b4 100644
--- a/Documentation/doc-guide/sphinx.rst
+++ b/Documentation/doc-guide/sphinx.rst
@@ -28,7 +28,7 @@ The ReST markups currently used by the Documentation/ files are meant to be
 built with ``Sphinx`` version 1.3 or upper. If you're desiring to build
 PDF outputs, it is recommended to use version 1.4.6 or upper.
 
-There's a script that checks for the Spinx requirements. Please see
+There's a script that checks for the Sphinx requirements. Please see
 :ref:`sphinx-pre-install` for further details.
 
 Most distributions are shipped with Sphinx, but its toolchain is fragile,
diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst
index 70e328e16aad..d6763272e747 100644
--- a/Documentation/driver-api/device_link.rst
+++ b/Documentation/driver-api/device_link.rst
@@ -81,10 +81,14 @@ integration is desired.
 Two other flags are specifically targeted at use cases where the device
 link is added from the consumer's ``->probe`` callback:  ``DL_FLAG_RPM_ACTIVE``
 can be specified to runtime resume the supplier upon addition of the
-device link.  ``DL_FLAG_AUTOREMOVE`` causes the device link to be automatically
-purged when the consumer fails to probe or later unbinds.  This obviates
-the need to explicitly delete the link in the ``->remove`` callback or in
-the error path of the ``->probe`` callback.
+device link.  ``DL_FLAG_AUTOREMOVE_CONSUMER`` causes the device link to be
+automatically purged when the consumer fails to probe or later unbinds.
+This obviates the need to explicitly delete the link in the ``->remove``
+callback or in the error path of the ``->probe`` callback.
+
+Similarly, when the device link is added from supplier's ``->probe`` callback,
+``DL_FLAG_AUTOREMOVE_SUPPLIER`` causes the device link to be automatically
+purged when the supplier fails to probe or later unbinds.
 
 Limitations
 ===========
diff --git a/Documentation/driver-api/mtdnand.rst b/Documentation/driver-api/mtdnand.rst
index dcd63599f700..c55a6034c397 100644
--- a/Documentation/driver-api/mtdnand.rst
+++ b/Documentation/driver-api/mtdnand.rst
@@ -374,7 +374,7 @@ The nand driver supports three different types of hardware ECC.
 
 -  NAND_ECC_HW8_512
 
-   Hardware ECC generator providing 6 bytes ECC per 512 byte.
+   Hardware ECC generator providing 8 bytes ECC per 512 byte.
 
 If your hardware generator has a different functionality add it at the
 appropriate place in nand_base.c
@@ -889,7 +889,7 @@ Use these constants to select the ECC algorithm::
     #define NAND_ECC_HW3_512    3
     /* Hardware ECC 6 byte ECC per 512 Byte data */
     #define NAND_ECC_HW6_512    4
-    /* Hardware ECC 6 byte ECC per 512 Byte data */
+    /* Hardware ECC 8 byte ECC per 512 Byte data */
     #define NAND_ECC_HW8_512    6
 
 
diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
index dbdf62907703..c7858dd1ea8f 100644
--- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt
+++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
@@ -5,10 +5,10 @@
 #
 # Architecture requirements
 #
-# * arm64
+# * arm/arm64
 #
-# Rely on eret context synchronization when returning from IPI handler, and
-# when returning to user-space.
+# Rely on implicit context synchronization as a result of exception return
+# when returning from IPI handler, and when returning to user-space.
 #
 # * x86
 #
@@ -31,7 +31,7 @@
     -----------------------
     |       alpha: | TODO |
     |         arc: | TODO |
-    |         arm: | TODO |
+    |         arm: |  ok  |
     |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 2c391338c675..9e6f19eaef89 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -64,7 +64,7 @@ prototypes:
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *,
 				struct file *, unsigned open_flag,
-				umode_t create_mode, int *opened);
+				umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 
 locking rules:
@@ -441,8 +441,6 @@ prototypes:
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
-	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
-	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -473,7 +471,7 @@ prototypes:
 };
 
 locking rules:
-	All except for ->poll_mask may block.
+	All may block.
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you
@@ -505,9 +503,6 @@ in sys_read() and friends.
 the lease within the individual filesystem to record the result of the
 operation
 
-->poll_mask can be called with or without the waitqueue lock for the waitqueue
-returned from ->get_poll_head.
-
 --------------------------- dquot_operations -------------------------------
 prototypes:
 	int (*write_dquot) (struct dquot *);
@@ -537,9 +532,9 @@ More details about quota locking can be found in fs/dquot.c.
 prototypes:
 	void (*open)(struct vm_area_struct*);
 	void (*close)(struct vm_area_struct*);
-	int (*fault)(struct vm_area_struct*, struct vm_fault *);
-	int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
-	int (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
+	vm_fault_t (*fault)(struct vm_area_struct*, struct vm_fault *);
+	vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
+	vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
 	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 
 locking rules:
diff --git a/Documentation/filesystems/cifs/CHANGES b/Documentation/filesystems/cifs/CHANGES
index 455e1cc494a9..1df7f4910eb2 100644
--- a/Documentation/filesystems/cifs/CHANGES
+++ b/Documentation/filesystems/cifs/CHANGES
@@ -1,1068 +1,4 @@
-See https://wiki.samba.org/index.php/LinuxCIFSKernel for
-more current information.
-
-Version 1.62
-------------
-Add sockopt=TCP_NODELAY mount option. EA (xattr) routines hardened
-to more strictly handle corrupt frames.
-
-Version 1.61
-------------
-Fix append problem to Samba servers (files opened with O_APPEND could
-have duplicated data). Fix oops in cifs_lookup. Workaround problem
-mounting to OS/400 Netserve. Fix oops in cifs_get_tcp_session.
-Disable use of server inode numbers when server only
-partially supports them (e.g. for one server querying inode numbers on
-FindFirst fails but QPathInfo queries works). Fix oops with dfs in 
-cifs_put_smb_ses. Fix mmap to work on directio mounts (needed
-for OpenOffice when on forcedirectio mount e.g.)
-
-Version 1.60
--------------
-Fix memory leak in reconnect.  Fix oops in DFS mount error path.
-Set s_maxbytes to smaller (the max that vfs can handle) so that
-sendfile will now work over cifs mounts again.  Add noforcegid
-and noforceuid mount parameters. Fix small mem leak when using
-ntlmv2. Fix 2nd mount to same server but with different port to
-be allowed (rather than reusing the 1st port) - only when the
-user explicitly overrides the port on the 2nd mount.
-
-Version 1.59
-------------
-Client uses server inode numbers (which are persistent) rather than
-client generated ones by default (mount option "serverino" turned
-on by default if server supports it).  Add forceuid and forcegid
-mount options (so that when negotiating unix extensions specifying
-which uid mounted does not immediately force the server's reported
-uids to be overridden).  Add support for scope mount parm. Improve
-hard link detection to use same inode for both.  Do not set
-read-only dos attribute on directories (for chmod) since Windows
-explorer special cases this attribute bit for directories for
-a different purpose.
-
-Version 1.58
-------------
-Guard against buffer overruns in various UCS-2 to UTF-8 string conversions
-when the UTF-8 string is composed of unusually long (more than 4 byte) converted
-characters. Add support for mounting root of a share which redirects immediately
-to DFS target. Convert string conversion functions from Unicode to more
-accurately mark string length before allocating memory (which may help the
-rare cases where a UTF-8 string is much larger than the UCS2 string that
-we converted from).  Fix endianness of the vcnum field used during
-session setup to distinguish multiple mounts to same server from different
-userids. Raw NTLMSSP fixed (it requires /proc/fs/cifs/experimental
-flag to be set to 2, and mount must enable krb5 to turn on extended security).
-Performance of file create to Samba improved (posix create on lookup
-removes 1 of 2 network requests sent on file create)
- 
-Version 1.57
-------------
-Improve support for multiple security contexts to the same server. We
-used to use the same "vcnumber" for all connections which could cause
-the server to treat subsequent connections, especially those that
-are authenticated as guest, as reconnections, invalidating the earlier
-user's smb session.  This fix allows cifs to mount multiple times to the
-same server with different userids without risking invalidating earlier
-established security contexts.  fsync now sends SMB Flush operation
-to better ensure that we wait for server to write all of the data to
-server disk (not just write it over the network).  Add new mount
-parameter to allow user to disable sending the (slow) SMB flush on
-fsync if desired (fsync still flushes all cached write data to the server).
-Posix file open support added (turned off after one attempt if server
-fails to support it properly, as with Samba server versions prior to 3.3.2)
-Fix "redzone overwritten" bug in cifs_put_tcon (CIFSTcon may allocate too
-little memory for the "nativeFileSystem" field returned by the server
-during mount).  Endian convert inode numbers if necessary (makes it easier
-to compare inode numbers on network files from big endian systems). 
-
-Version 1.56
-------------
-Add "forcemandatorylock" mount option to allow user to use mandatory
-rather than posix (advisory) byte range locks, even though server would
-support posix byte range locks.  Fix query of root inode when prefixpath
-specified and user does not have access to query information about the
-top of the share.  Fix problem in 2.6.28 resolving DFS paths to
-Samba servers (worked to Windows).  Fix rmdir so that pending search
-(readdir) requests do not get invalid results which include the now
-removed directory.  Fix oops in cifs_dfs_ref.c when prefixpath is not reachable
-when using DFS.  Add better file create support to servers which support
-the CIFS POSIX protocol extensions (this adds support for new flags
-on create, and improves semantics for write of locked ranges).
-
-Version 1.55
-------------
-Various fixes to make delete of open files behavior more predictable
-(when delete of an open file fails we mark the file as "delete-on-close"
-in a way that more servers accept, but only if we can first rename the
-file to a temporary name).  Add experimental support for more safely
-handling fcntl(F_SETLEASE).  Convert cifs to using blocking tcp
-sends, and also let tcp autotune the socket send and receive buffers.
-This reduces the number of EAGAIN errors returned by TCP/IP in
-high stress workloads (and the number of retries on socket writes
-when sending large SMBWriteX requests).  Fix case in which a portion of
-data can in some cases not get written to the file on the server before the
-file is closed.  Fix DFS parsing to properly handle path consumed field,
-and to handle certain codepage conversions better.  Fix mount and
-umount race that can cause oops in mount or umount or reconnect.
-
-Version 1.54
-------------
-Fix premature write failure on congested networks (we would give up
-on EAGAIN from the socket too quickly on large writes).
-Cifs_mkdir and cifs_create now respect the setgid bit on parent dir.
-Fix endian problems in acl (mode from/to cifs acl) on bigendian
-architectures.  Fix problems with preserving timestamps on copying open
-files (e.g. "cp -a") to Windows servers.  For mkdir and create honor setgid bit
-on parent directory when server supports Unix Extensions but not POSIX
-create. Update cifs.upcall version to handle new Kerberos sec flags
-(this requires update of cifs.upcall program from Samba).  Fix memory leak
-on dns_upcall (resolving DFS referralls).  Fix plain text password
-authentication (requires setting SecurityFlags to 0x30030 to enable
-lanman and plain text though).  Fix writes to be at correct offset when
-file is open with O_APPEND and file is on a directio (forcediretio) mount.
-Fix bug in rewinding readdir directory searches.  Add nodfs mount option.
-
-Version 1.53
-------------
-DFS support added (Microsoft Distributed File System client support needed
-for referrals which enable a hierarchical name space among servers).
-Disable temporary caching of mode bits to servers which do not support
-storing of mode (e.g. Windows servers, when client mounts without cifsacl
-mount option) and add new "dynperm" mount option to enable temporary caching
-of mode (enable old behavior).  Fix hang on mount caused when server crashes
-tcp session during negotiate protocol.
-
-Version 1.52
-------------
-Fix oops on second mount to server when null auth is used.
-Enable experimental Kerberos support.  Return writebehind errors on flush
-and sync so that events like out of disk space get reported properly on
-cached files. Fix setxattr failure to certain Samba versions. Fix mount
-of second share to disconnected server session (autoreconnect on this).
-Add ability to modify cifs acls for handling chmod (when mounted with
-cifsacl flag). Fix prefixpath path separator so we can handle mounts
-with prefixpaths longer than one directory (one path component) when
-mounted to Windows servers.  Fix slow file open when cifsacl
-enabled. Fix memory leak in FindNext when the SMB call returns -EBADF.
-
-
-Version 1.51
-------------
-Fix memory leak in statfs when mounted to very old servers (e.g.
-Windows 9x).  Add new feature "POSIX open" which allows servers
-which support the current POSIX Extensions to provide better semantics
-(e.g. delete for open files opened with posix open).  Take into
-account umask on posix mkdir not just older style mkdir.  Add
-ability to mount to IPC$ share (which allows CIFS named pipes to be
-opened, read and written as if they were files).  When 1st tree
-connect fails (e.g. due to signing negotiation failure) fix
-leak that causes cifsd not to stop and rmmod to fail to cleanup
-cifs_request_buffers pool. Fix problem with POSIX Open/Mkdir on
-bigendian architectures. Fix possible memory corruption when
-EAGAIN returned on kern_recvmsg. Return better error if server
-requires packet signing but client has disabled it. When mounted
-with cifsacl mount option - mode bits are approximated based
-on the contents of the ACL of the file or directory. When cifs
-mount helper is missing convert make sure that UNC name 
-has backslash (not forward slash) between ip address of server
-and the share name.
-
-Version 1.50
-------------
-Fix NTLMv2 signing. NFS server mounted over cifs works (if cifs mount is
-done with "serverino" mount option).  Add support for POSIX Unlink
-(helps with certain sharing violation cases when server such as
-Samba supports newer POSIX CIFS Protocol Extensions). Add "nounix"
-mount option to allow disabling the CIFS Unix Extensions for just
-that mount. Fix hang on spinlock in find_writable_file (race when
-reopening file after session crash).  Byte range unlock request to
-windows server could unlock more bytes (on server copy of file)
-than intended if start of unlock request is well before start of
-a previous byte range lock that we issued.
-
-Version 1.49
-------------
-IPv6 support.  Enable ipv6 addresses to be passed on mount (put the ipv6
-address after the "ip=" mount option, at least until mount.cifs is fixed to
-handle DNS host to ipv6 name translation).  Accept override of uid or gid
-on mount even when Unix Extensions are negotiated (it used to be ignored
-when Unix Extensions were ignored).  This allows users to override the
-default uid and gid for files when they are certain that the uids or
-gids on the server do not match those of the client.  Make "sec=none"
-mount override username (so that null user connection is attempted)
-to match what documentation said. Support for very large reads, over 127K,
-available to some newer servers (such as Samba 3.0.26 and later but
-note that it also requires setting CIFSMaxBufSize at module install
-time to a larger value which may hurt performance in some cases).
-Make sign option force signing (or fail if server does not support it).
-
-Version 1.48
-------------
-Fix mtime bouncing around from local idea of last write times to remote time.
-Fix hang (in i_size_read) when simultaneous size update of same remote file
-on smp system corrupts sequence number. Do not reread unnecessarily partial page
-(which we are about to overwrite anyway) when writing out file opened rw.
-When DOS attribute of file on non-Unix server's file changes on the server side
-from read-only back to read-write, reflect this change in default file mode
-(we had been leaving a file's mode read-only until the inode were reloaded).
-Allow setting of attribute back to ATTR_NORMAL (removing readonly dos attribute
-when archive dos attribute not set and we are changing mode back to writeable
-on server which does not support the Unix Extensions).  Remove read only dos
-attribute on chmod when adding any write permission (ie on any of
-user/group/other (not all of user/group/other ie  0222) when
-mounted to windows.  Add support for POSIX MkDir (slight performance
-enhancement and eliminates the network race between the mkdir and set 
-path info of the mode).
-
-
-Version 1.47
-------------
-Fix oops in list_del during mount caused by unaligned string.
-Fix file corruption which could occur on some large file
-copies caused by writepages page i/o completion bug.
-Seek to SEEK_END forces check for update of file size for non-cached
-files. Allow file size to be updated on remote extend of locally open,
-non-cached file.  Fix reconnect to newer Samba servers (or other servers
-which support the CIFS Unix/POSIX extensions) so that we again tell the
-server the Unix/POSIX cifs capabilities which we support (SetFSInfo).
-Add experimental support for new POSIX Open/Mkdir (which returns
-stat information on the open, and allows setting the mode).
-
-Version 1.46
-------------
-Support deep tree mounts.  Better support OS/2, Win9x (DOS) time stamps.
-Allow null user to be specified on mount ("username="). Do not return
-EINVAL on readdir when filldir fails due to overwritten blocksize
-(fixes FC problem).  Return error in rename 2nd attempt retry (ie report
-if rename by handle also fails, after rename by path fails, we were
-not reporting whether the retry worked or not). Fix NTLMv2 to
-work to Windows servers (mount with option "sec=ntlmv2").
-
-Version 1.45
-------------
-Do not time out lockw calls when using posix extensions. Do not
-time out requests if server still responding reasonably fast
-on requests on other threads.  Improve POSIX locking emulation,
-(lock cancel now works, and unlock of merged range works even
-to Windows servers now).  Fix oops on mount to lanman servers
-(win9x, os/2 etc.) when null password.  Do not send listxattr
-(SMB to query all EAs) if nouser_xattr specified.  Fix SE Linux
-problem (instantiate inodes/dentries in right order for readdir).
-
-Version 1.44
-------------
-Rewritten sessionsetup support, including support for legacy SMB
-session setup needed for OS/2 and older servers such as Windows 95 and 98.
-Fix oops on ls to OS/2 servers.  Add support for level 1 FindFirst
-so we can do search (ls etc.) to OS/2.  Do not send NTCreateX
-or recent levels of FindFirst unless server says it supports NT SMBs
-(instead use legacy equivalents from LANMAN dialect). Fix to allow
-NTLMv2 authentication support (now can use stronger password hashing
-on mount if corresponding /proc/fs/cifs/SecurityFlags is set (0x4004).
-Allow override of global cifs security flags on mount via "sec=" option(s).
-
-Version 1.43
-------------
-POSIX locking to servers which support CIFS POSIX Extensions
-(disabled by default controlled by proc/fs/cifs/Experimental).
-Handle conversion of long share names (especially Asian languages)
-to Unicode during mount. Fix memory leak in sess struct on reconnect.
-Fix rare oops after acpi suspend.  Fix O_TRUNC opens to overwrite on
-cifs open which helps rare case when setpathinfo fails or server does
-not support it. 
-
-Version 1.42
-------------
-Fix slow oplock break when mounted to different servers at the same time and
-the tids match and we try to find matching fid on wrong server. Fix read
-looping when signing required by server (2.6.16 kernel only). Fix readdir
-vs. rename race which could cause each to hang. Return . and .. even
-if server does not.  Allow searches to skip first three entries and
-begin at any location. Fix oops in find_writeable_file.
-
-Version 1.41
-------------
-Fix NTLMv2 security (can be enabled in /proc/fs/cifs) so customers can
-configure stronger authentication.  Fix sfu symlinks so they can
-be followed (not just recognized).  Fix wraparound of bcc on
-read responses when buffer size over 64K and also fix wrap of
-max smb buffer size when CIFSMaxBufSize over 64K.  Fix oops in
-cifs_user_read and cifs_readpages (when EAGAIN on send of smb
-on socket is returned over and over).  Add POSIX (advisory) byte range
-locking support (requires server with newest CIFS UNIX Extensions
-to the protocol implemented). Slow down negprot slightly in port 139
-RFC1001 case to give session_init time on buggy servers.
-
-Version 1.40
-------------
-Use fsuid (fsgid) more consistently instead of uid (gid). Improve performance
-of readpages by eliminating one extra memcpy. Allow update of file size
-from remote server even if file is open for write as long as mount is
-directio.  Recognize share mode security and send NTLM encrypted password
-on tree connect if share mode negotiated.
-
-Version 1.39
-------------
-Defer close of a file handle slightly if pending writes depend on that handle
-(this reduces the EBADF bad file handle errors that can be logged under heavy
-stress on writes). Modify cifs Kconfig options to expose CONFIG_CIFS_STATS2 
-Fix SFU style symlinks and mknod needed for servers which do not support the
-CIFS Unix Extensions.  Fix setfacl/getfacl on bigendian. Timeout negative
-dentries so files that the client sees as deleted but that later get created
-on the server will be recognized.  Add client side permission check on setattr.
-Timeout stuck requests better (where server has never responded or sent corrupt
-responses)
-
-Version 1.38
-------------
-Fix tcp socket retransmission timeouts (e.g. on ENOSPACE from the socket)
-to be smaller at first (but increasing) so large write performance performance
-over GigE is better.  Do not hang thread on illegal byte range lock response
-from Windows (Windows can send an RFC1001 size which does not match smb size) by
-allowing an SMBs TCP length to be up to a few bytes longer than it should be.
-wsize and rsize can now be larger than negotiated buffer size if server
-supports large readx/writex, even when directio mount flag not specified.
-Write size will in many cases now be 16K instead of 4K which greatly helps
-file copy performance on lightly loaded networks.  Fix oops in dnotify
-when experimental config flag enabled. Make cifsFYI more granular.
-
-Version 1.37
-------------
-Fix readdir caching when unlink removes file in current search buffer,
-and this is followed by a rewind search to just before the deleted entry.
-Do not attempt to set ctime unless atime and/or mtime change requested
-(most servers throw it away anyway). Fix length check of received smbs
-to be more accurate. Fix big endian problem with mapchars mount option,
-and with a field returned by statfs.
-
-Version 1.36
-------------
-Add support for mounting to older pre-CIFS servers such as Windows9x and ME.
-For these older servers, add option for passing netbios name of server in
-on mount (servernetbiosname).  Add suspend support for power management, to
-avoid cifsd thread preventing software suspend from working.
-Add mount option for disabling the default behavior of sending byte range lock
-requests to the server (necessary for certain applications which break with
-mandatory lock behavior such as Evolution), and also mount option for
-requesting case insensitive matching for path based requests (requesting
-case sensitive is the default).
-
-Version 1.35
-------------
-Add writepage performance improvements.  Fix path name conversions
-for long filenames on mounts which were done with "mapchars" mount option
-specified.  Ensure multiplex ids do not collide.  Fix case in which 
-rmmod can oops if done soon after last unmount.  Fix truncated
-search (readdir) output when resume filename was a long filename.
-Fix filename conversion when mapchars mount option was specified and
-filename was a long filename.
-
-Version 1.34
-------------
-Fix error mapping of the TOO_MANY_LINKS (hardlinks) case.
-Do not oops if root user kills cifs oplock kernel thread or
-kills the cifsd thread (NB: killing the cifs kernel threads is not
-recommended, unmount and rmmod cifs will kill them when they are
-no longer needed).  Fix readdir to ASCII servers (ie older servers
-which do not support Unicode) and also require asterisk.
-Fix out of memory case in which data could be written one page
-off in the page cache.
-
-Version 1.33
-------------
-Fix caching problem, in which readdir of directory containing a file
-which was cached could cause the file's time stamp to be updated
-without invalidating the readahead data (so we could get stale
-file data on the client for that file even as the server copy changed).
-Cleanup response processing so cifsd can not loop when abnormally
-terminated.
-
-
-Version 1.32
-------------
-Fix oops in ls when Transact2 FindFirst (or FindNext) returns more than one
-transact response for an SMB request and search entry split across two frames.
-Add support for lsattr (getting ext2/ext3/reiserfs attr flags from the server)
-as new protocol extensions. Do not send Get/Set calls for POSIX ACLs
-unless server explicitly claims to support them in CIFS Unix extensions
-POSIX ACL capability bit. Fix packet signing when multiuser mounting with
-different users from the same client to the same server. Fix oops in
-cifs_close. Add mount option for remapping reserved characters in
-filenames (also allow recognizing files with created by SFU which have any
-of these seven reserved characters, except backslash, to be recognized).
-Fix invalid transact2 message (we were sometimes trying to interpret
-oplock breaks as SMB responses). Add ioctl for checking that the
-current uid matches the uid of the mounter (needed by umount.cifs).
-Reduce the number of large buffer allocations in cifs response processing
-(significantly reduces memory pressure under heavy stress with multiple
-processes accessing the same server at the same time).
-
-Version 1.31
-------------
-Fix updates of DOS attributes and time fields so that files on NT4 servers
-do not get marked delete on close. Display sizes of cifs buffer pools in
-cifs stats. Fix oops in unmount when cifsd thread being killed by 
-shutdown. Add generic readv/writev and aio support. Report inode numbers 
-consistently in readdir and lookup (when serverino mount option is
-specified use the inode number that the server reports - for both lookup
-and readdir, otherwise by default the locally generated inode number is used
-for inodes created in either path since servers are not always able to 
-provide unique inode numbers when exporting multiple volumes from under one
-sharename).
-
-Version 1.30
-------------
-Allow new nouser_xattr mount parm to disable xattr support for user namespace.
-Do not flag user_xattr mount parm in dmesg.  Retry failures setting file time  
-(mostly affects NT4 servers) by retry with handle based network operation. 
-Add new POSIX Query FS Info for returning statfs info more accurately.
-Handle passwords with multiple commas in them.
-
-Version 1.29
-------------
-Fix default mode in sysfs of cifs module parms.  Remove old readdir routine.
-Fix capabilities flags for large readx so as to allow reads larger than 64K.
-
-Version 1.28
-------------
-Add module init parm for large SMB buffer size (to allow it to be changed
-from its default of 16K) which is especially useful for large file copy
-when mounting with the directio mount option. Fix oops after 
-returning from mount when experimental ExtendedSecurity enabled and
-SpnegoNegotiated returning invalid error. Fix case to retry better when 
-peek returns from 1 to 3 bytes on socket which should have more data.
-Fixed path based calls (such as cifs lookup) to handle path names
-longer than 530 (now can handle PATH_MAX). Fix pass through authentication
-from Samba server to DC (Samba required dummy LM password).
-
-Version 1.27
-------------
-Turn off DNOTIFY (directory change notification support) by default
-(unless built with the experimental flag) to fix hang with KDE
-file browser. Fix DNOTIFY flag mappings.  Fix hang (in wait_event
-waiting on an SMB response) in SendReceive when session dies but
-reconnects quickly from another task.  Add module init  parms for
-minimum number of large and small network buffers in the buffer pools,
-and for the maximum number of simultaneous requests.
-
-Version 1.26
-------------
-Add setfacl support to allow setting of ACLs remotely to Samba 3.10 and later
-and other POSIX CIFS compliant servers.  Fix error mapping for getfacl 
-to EOPNOTSUPP when server does not support posix acls on the wire. Fix 
-improperly zeroed buffer in CIFS Unix extensions set times call. 
-
-Version 1.25
-------------
-Fix internationalization problem in cifs readdir with filenames that map to 
-longer UTF-8 strings than the string on the wire was in Unicode.  Add workaround
-for readdir to netapp servers. Fix search rewind (seek into readdir to return 
-non-consecutive entries).  Do not do readdir when server negotiates 
-buffer size to small to fit filename. Add support for reading POSIX ACLs from
-the server (add also acl and noacl mount options).
-
-Version 1.24
-------------
-Optionally allow using server side inode numbers, rather than client generated
-ones by specifying mount option "serverino" - this is required for some apps
-to work which double check hardlinked files and have persistent inode numbers.
-
-Version 1.23
-------------
-Multiple bigendian fixes. On little endian systems (for reconnect after
-network failure) fix tcp session reconnect code so we do not try first
-to reconnect on reverse of port 445. Treat reparse points (NTFS junctions)
-as directories rather than symlinks because we can do follow link on them.
-
-Version 1.22
-------------
-Add config option to enable XATTR (extended attribute) support, mapping
-xattr names in the "user." namespace space to SMB/CIFS EAs. Lots of
-minor fixes pointed out by the Stanford SWAT checker (mostly missing
-or out of order NULL pointer checks in little used error paths).
-
-Version 1.21
-------------
-Add new mount parm to control whether mode check (generic_permission) is done
-on the client.  If Unix extensions are enabled and the uids on the client
-and server do not match, client permission checks are meaningless on
-server uids that do not exist on the client (this does not affect the
-normal ACL check which occurs on the server).  Fix default uid
-on mknod to match create and mkdir. Add optional mount parm to allow
-override of the default uid behavior (in which the server sets the uid
-and gid of newly created files). Normally for network filesystem mounts
-user want the server to set the uid/gid on newly created files (rather than 
-using uid of the client processes you would in a local filesystem).
-
-Version 1.20
-------------
-Make transaction counts more consistent. Merge /proc/fs/cifs/SimultaneousOps
-info into /proc/fs/cifs/DebugData.  Fix oops in rare oops in readdir 
-(in build_wildcard_path_from_dentry).  Fix mknod to pass type field
-(block/char/fifo) properly.  Remove spurious mount warning log entry when
-credentials passed as mount argument. Set major/minor device number in
-inode for block and char devices when unix extensions enabled.
-
-Version 1.19
-------------
-Fix /proc/fs/cifs/Stats and DebugData display to handle larger
-amounts of return data. Properly limit requests to MAX_REQ (50
-is the usual maximum active multiplex SMB/CIFS requests per server).
-Do not kill cifsd (and thus hurt the other SMB session) when more than one
-session to the same server (but with different userids) exists and one
-of the two user's smb sessions is being removed while leaving the other.
-Do not loop reconnecting in cifsd demultiplex thread when admin
-kills the thread without going through unmount.
-
-Version 1.18
-------------
-Do not rename hardlinked files (since that should be a noop). Flush
-cached write behind data when reopening a file after session abend,
-except when already in write. Grab per socket sem during reconnect 
-to avoid oops in sendmsg if overlapping with reconnect. Do not
-reset cached inode file size on readdir for files open for write on 
-client.
-
-
-Version 1.17
-------------
-Update number of blocks in file so du command is happier (in Linux a fake
-blocksize of 512 is required for calculating number of blocks in inode).
-Fix prepare write of partial pages to read in data from server if possible.
-Fix race on tcpStatus field between unmount and reconnection code, causing
-cifsd process sometimes to hang around forever. Improve out of memory
-checks in cifs_filldir
-
-Version 1.16
-------------
-Fix incorrect file size in file handle based setattr on big endian hardware.
-Fix oops in build_path_from_dentry when out of memory.  Add checks for invalid
-and closing file structs in writepage/partialpagewrite.  Add statistics
-for each mounted share (new menuconfig option). Fix endianness problem in
-volume information displayed in /proc/fs/cifs/DebugData (only affects
-affects big endian architectures). Prevent renames while constructing
-path names for open, mkdir and rmdir.
-
-Version 1.15
-------------
-Change to mempools for alloc smb request buffers and multiplex structs
-to better handle low memory problems (and potential deadlocks).
-
-Version 1.14
-------------
-Fix incomplete listings of large directories on Samba servers when Unix
-extensions enabled.  Fix oops when smb_buffer can not be allocated. Fix
-rename deadlock when writing out dirty pages at same time.
-
-Version 1.13
-------------
-Fix open of files in which O_CREATE can cause the mode to change in
-some cases. Fix case in which retry of write overlaps file close.
-Fix PPC64 build error.  Reduce excessive stack usage in smb password
-hashing. Fix overwrite of Linux user's view of file mode to Windows servers.
-
-Version 1.12
-------------
-Fixes for large file copy, signal handling, socket retry, buffer
-allocation and low memory situations.
-
-Version 1.11
-------------
-Better port 139 support to Windows servers (RFC1001/RFC1002 Session_Initialize)
-also now allowing support for specifying client netbiosname.  NT4 support added.
-
-Version 1.10
-------------
-Fix reconnection (and certain failed mounts) to properly wake up the
-blocked users thread so it does not seem hung (in some cases was blocked
-until the cifs receive timeout expired). Fix spurious error logging
-to kernel log when application with open network files killed. 
-
-Version 1.09
-------------
-Fix /proc/fs module unload warning message (that could be logged
-to the kernel log). Fix intermittent failure in connectathon
-test7 (hardlink count not immediately refreshed in case in which
-inode metadata can be incorrectly kept cached when time near zero)
-
-Version 1.08
-------------
-Allow file_mode and dir_mode (specified at mount time) to be enforced
-locally (the server already enforced its own ACLs too) for servers
-that do not report the correct mode (do not support the 
-CIFS Unix Extensions).
-
-Version 1.07
-------------
-Fix some small memory leaks in some unmount error paths. Fix major leak
-of cache pages in readpages causing multiple read oriented stress
-testcases (including fsx, and even large file copy) to fail over time. 
-
-Version 1.06
-------------
-Send NTCreateX with ATTR_POSIX if Linux/Unix extensions negotiated with server.
-This allows files that differ only in case and improves performance of file
-creation and file open to such servers.  Fix semaphore conflict which causes 
-slow delete of open file to Samba (which unfortunately can cause an oplock
-break to self while vfs_unlink held i_sem) which can hang for 20 seconds.
-
-Version 1.05
-------------
-fixes to cifs_readpages for fsx test case
-
-Version 1.04
-------------
-Fix caching data integrity bug when extending file size especially when no
-oplock on file.  Fix spurious logging of valid already parsed mount options
-that are parsed outside of the cifs vfs such as nosuid.
-
-
-Version 1.03
-------------
-Connect to server when port number override not specified, and tcp port
-unitialized.  Reset search to restart at correct file when kernel routine
-filldir returns error during large directory searches (readdir). 
-
-Version 1.02
-------------
-Fix caching problem when files opened by multiple clients in which 
-page cache could contain stale data, and write through did
-not occur often enough while file was still open when read ahead
-(read oplock) not allowed.  Treat "sep=" when first mount option
-as an override of comma as the default separator between mount
-options. 
-
-Version 1.01
-------------
-Allow passwords longer than 16 bytes. Allow null password string.
-
-Version 1.00
-------------
-Gracefully clean up failed mounts when attempting to mount to servers such as
-Windows 98 that terminate tcp sessions during protocol negotiation.  Handle
-embedded commas in mount parsing of passwords.
-
-Version 0.99
-------------
-Invalidate local inode cached pages on oplock break and when last file
-instance is closed so that the client does not continue using stale local
-copy rather than later modified server copy of file.  Do not reconnect
-when server drops the tcp session prematurely before negotiate
-protocol response.  Fix oops in reopen_file when dentry freed.  Allow
-the support for CIFS Unix Extensions to be disabled via proc interface.
-
-Version 0.98
-------------
-Fix hang in commit_write during reconnection of open files under heavy load.
-Fix unload_nls oops in a mount failure path. Serialize writes to same socket
-which also fixes any possible races when cifs signatures are enabled in SMBs
-being sent out of signature sequence number order.    
-
-Version 0.97
-------------
-Fix byte range locking bug (endian problem) causing bad offset and
-length.
-
-Version 0.96
-------------
-Fix oops (in send_sig) caused by CIFS unmount code trying to
-wake up the demultiplex thread after it had exited. Do not log
-error on harmless oplock release of closed handle.
-
-Version 0.95
-------------
-Fix unsafe global variable usage and password hash failure on gcc 3.3.1
-Fix problem reconnecting secondary mounts to same server after session 
-failure.  Fix invalid dentry - race in mkdir when directory gets created
-by another client between the lookup and mkdir.
- 
-Version 0.94
-------------
-Fix to list processing in reopen_files. Fix reconnection when server hung
-but tcpip session still alive.  Set proper timeout on socket read.
-
-Version 0.93
-------------
-Add missing mount options including iocharset.  SMP fixes in write and open. 
-Fix errors in reconnecting after TCP session failure.  Fix module unloading
-of default nls codepage
-
-Version 0.92
-------------
-Active smb transactions should never go negative (fix double FreeXid). Fix
-list processing in file routines. Check return code on kmalloc in open.
-Fix spinlock usage for SMP.
-
-Version 0.91
-------------
-Fix oops in reopen_files when invalid dentry. drop dentry on server rename 
-and on revalidate errors. Fix cases where pid is now tgid.  Fix return code
-on create hard link when server does not support them. 
-
-Version 0.90
-------------
-Fix scheduling while atomic error in getting inode info on newly created file. 
-Fix truncate of existing files opened with O_CREAT but not O_TRUNC set.
-
-Version 0.89
-------------
-Fix oops on write to dead tcp session. Remove error log write for case when file open
-O_CREAT but not O_EXCL
-
-Version 0.88
-------------
-Fix non-POSIX behavior on rename of open file and delete of open file by taking 
-advantage of trans2 SetFileInfo rename facility if available on target server.
-Retry on ENOSPC and EAGAIN socket errors.
-
-Version 0.87
-------------
-Fix oops on big endian readdir.  Set blksize to be even power of two (2**blkbits) to fix
-allocation size miscalculation. After oplock token lost do not read through
-cache. 
-
-Version 0.86
-------------
-Fix oops on empty file readahead.  Fix for file size handling for locally cached files.
-
-Version 0.85
-------------
-Fix oops in mkdir when server fails to return inode info. Fix oops in reopen_files
-during auto reconnection to server after server recovered from failure.
-
-Version 0.84
-------------
-Finish support for Linux 2.5 open/create changes, which removes the
-redundant NTCreate/QPathInfo/close that was sent during file create.
-Enable oplock by default. Enable packet signing by default (needed to 
-access many recent Windows servers)
-
-Version 0.83
-------------
-Fix oops when mounting to long server names caused by inverted parms to kmalloc.
-Fix MultiuserMount (/proc/fs/cifs configuration setting) so that when enabled
-we will choose a cifs user session (smb uid) that better matches the local
-uid if a) the mount uid does not match the current uid and b) we have another
-session to the same server (ip address) for a different mount which
-matches the current local uid.
-
-Version 0.82
-------------
-Add support for mknod of block or character devices.  Fix oplock
-code (distributed caching) to properly send response to oplock
-break from server.
-
-Version 0.81
-------------
-Finish up CIFS packet digital signing for the default
-NTLM security case. This should help Windows 2003
-network interoperability since it is common for
-packet signing to be required now. Fix statfs (stat -f)
-which recently started returning errors due to 
-invalid value (-1 instead of 0) being set in the
-struct kstatfs f_ffiles field.
-
-Version 0.80
------------
-Fix oops on stopping oplock thread when removing cifs when
-built as module.
-
-Version 0.79
-------------
-Fix mount options for ro (readonly), uid, gid and file and directory mode. 
-
-Version 0.78
-------------
-Fix errors displayed on failed mounts to be more understandable.
-Fixed various incorrect or misleading smb to posix error code mappings.
-
-Version 0.77
-------------
-Fix display of NTFS DFS junctions to display as symlinks.
-They are the network equivalent.  Fix oops in 
-cifs_partialpagewrite caused by missing spinlock protection
-of openfile linked list.  Allow writebehind caching errors to 
-be returned to the application at file close.
-
-Version 0.76
-------------
-Clean up options displayed in /proc/mounts by show_options to
-be more consistent with other filesystems.
-
-Version 0.75
-------------
-Fix delete of readonly file to Windows servers.  Reflect
-presence or absence of read only dos attribute in mode
-bits for servers that do not support CIFS Unix extensions.
-Fix shortened results on readdir of large directories to
-servers supporting CIFS Unix extensions (caused by
-incorrect resume key).
-
-Version 0.74
-------------
-Fix truncate bug (set file size) that could cause hangs e.g. running fsx
-
-Version 0.73
-------------
-unload nls if mount fails.
-
-Version 0.72
-------------
-Add resume key support to search (readdir) code to workaround
-Windows bug.  Add /proc/fs/cifs/LookupCacheEnable which
-allows disabling caching of attribute information for
-lookups.
-
-Version 0.71
-------------
-Add more oplock handling (distributed caching code).  Remove
-dead code.  Remove excessive stack space utilization from
-symlink routines.
-
-Version 0.70
-------------
-Fix oops in get dfs referral (triggered when null path sent in to
-mount).  Add support for overriding rsize at mount time.
-
-Version 0.69
-------------
-Fix buffer overrun in readdir which caused intermittent kernel oopses.
-Fix writepage code to release kmap on write data.  Allow "-ip=" new 
-mount option to be passed in on parameter distinct from the first part
-(server name portion of) the UNC name.  Allow override of the
-tcp port of the target server via new mount option "-port="  
-
-Version 0.68
-------------
-Fix search handle leak on rewind.  Fix setuid and gid so that they are 
-reflected in the local inode immediately.  Cleanup of whitespace
-to make 2.4 and 2.5 versions more consistent.
-
-
-Version 0.67
-------------
-Fix signal sending so that captive thread (cifsd) exits on umount 
-(which was causing the warning in kmem_cache_free of the request buffers
-at rmmod time).  This had broken as a sideeffect of the recent global
-kernel change to daemonize.  Fix memory leak in readdir code which
-showed up in "ls -R" (and applications that did search rewinding).
-
-Version 0.66
-------------
-Reconnect tids and fids after session reconnection (still do not
-reconnect byte range locks though).  Fix problem caching
-lookup information for directory inodes, improving performance,
-especially in deep directory trees.  Fix various build warnings.
-
-Version 0.65
-------------
-Finish fixes to commit write for caching/readahead consistency.  fsx 
-now works to Samba servers.  Fix oops caused when readahead
-was interrupted by a signal.
-
-Version 0.64
-------------
-Fix data corruption (in partial page after truncate) that caused fsx to
-fail to Windows servers.  Cleaned up some extraneous error logging in
-common error paths.  Add generic sendfile support.
-
-Version 0.63
-------------
-Fix memory leak in AllocMidQEntry.
-Finish reconnection logic, so connection with server can be dropped
-(or server rebooted) and the cifs client will reconnect.  
-
-Version 0.62
-------------
-Fix temporary socket leak when bad userid or password specified 
-(or other SMBSessSetup failure).  Increase maximum buffer size to slightly
-over 16K to allow negotiation of up to Samba and Windows server default read 
-sizes.  Add support for readpages
-
-Version 0.61
-------------
-Fix oops when username not passed in on mount.  Extensive fixes and improvements
-to error logging (strip redundant newlines, change debug macros to ensure newline
-passed in and to be more consistent).  Fix writepage wrong file handle problem,
-a readonly file handle could be incorrectly used to attempt to write out
-file updates through the page cache to multiply open files.  This could cause
-the iozone benchmark to fail on the fwrite test. Fix bug mounting two different
-shares to the same Windows server when using different usernames
-(doing this to Samba servers worked but Windows was rejecting it) - now it is
-possible to use different userids when connecting to the same server from a
-Linux client. Fix oops when treeDisconnect called during unmount on
-previously freed socket.
-
-Version 0.60
-------------
-Fix oops in readpages caused by not setting address space operations in inode in 
-rare code path. 
-
-Version 0.59
-------------
-Includes support for deleting of open files and renaming over existing files (per POSIX
-requirement).  Add readlink support for Windows junction points (directory symlinks).
-
-Version 0.58
-------------
-Changed read and write to go through pagecache. Added additional address space operations.
-Memory mapped operations now working.
-
-Version 0.57
-------------
-Added writepage code for additional memory mapping support.  Fixed leak in xids causing
-the simultaneous operations counter (/proc/fs/cifs/SimultaneousOps) to increase on 
-every stat call.  Additional formatting cleanup. 
-
-Version 0.56
-------------
-Fix bigendian bug in order of time conversion. Merge 2.5 to 2.4 version.  Formatting cleanup.   
-
-Version 0.55
-------------
-Fixes from Zwane Mwaikambo for adding missing return code checking in a few places.
-Also included a modified version of his fix to protect global list manipulation of
-the smb session and tree connection and mid related global variables.
-
-Version 0.54
-------------
-Fix problem with captive thread hanging around at unmount time.  Adjust to 2.5.42-pre
-changes to superblock layout.   Remove wasteful allocation of smb buffers (now the send 
-buffer is reused for responses).  Add more oplock handling. Additional minor cleanup.
-
-Version 0.53
-------------
-More stylistic updates to better match kernel style.  Add additional statistics
-for filesystem which can be viewed via /proc/fs/cifs.  Add more pieces of NTLMv2
-and CIFS Packet Signing enablement.
-
-Version 0.52
-------------
-Replace call to sleep_on with safer wait_on_event.
-Make stylistic changes to better match kernel style recommendations.
-Remove most typedef usage (except for the PDUs themselves).
-
-Version 0.51
-------------
-Update mount so the -unc mount option is no longer required (the ip address can be specified
-in a UNC style device name.   Implementation of readpage/writepage started.
-
-Version 0.50
-------------
-Fix intermittent problem with incorrect smb header checking on badly 
-fragmented tcp responses
-
-Version 0.49
-------------
-Fixes to setting of allocation size and file size.
-
-Version 0.48
-------------
-Various 2.5.38 fixes.  Now works on 2.5.38
-
-Version 0.47
-------------
-Prepare for 2.5 kernel merge.  Remove ifdefs.
-
-Version 0.46
-------------
-Socket buffer management fixes.  Fix dual free.
-
-Version 0.45
-------------
-Various big endian fixes for hardlinks and symlinks and also for dfs.
-
-Version 0.44
-------------
-Various big endian fixes for servers with Unix extensions such as Samba
-
-Version 0.43
-------------
-Various FindNext fixes for incorrect filenames on large directory searches on big endian
-clients.  basic posix file i/o tests now work on big endian machines, not just le
-
-Version 0.42
-------------
-SessionSetup and NegotiateProtocol now work from Big Endian machines.
-Various Big Endian fixes found during testing on the Linux on 390.  Various fixes for compatibility with older
-versions of 2.4 kernel (now builds and works again on kernels at least as early as 2.4.7).
-
-Version 0.41
-------------
-Various minor fixes for Connectathon Posix "basic" file i/o test suite.  Directory caching fixed so hardlinked
-files now return the correct number of links on fstat as they are repeatedly linked and unlinked.
-
-Version 0.40
-------------
-Implemented "Raw" (i.e. not encapsulated in SPNEGO) NTLMSSP (i.e. the Security Provider Interface used to negotiate
-session advanced session authentication).  Raw NTLMSSP is preferred by Windows 2000 Professional and Windows XP.
-Began implementing support for SPNEGO encapsulation of NTLMSSP based session authentication blobs
-(which is the mechanism preferred by Windows 2000 server in the absence of Kerberos).
-
-Version 0.38
-------------
-Introduced optional mount helper utility mount.cifs and made coreq changes to cifs vfs to enable
-it. Fixed a few bugs in the DFS code (e.g. bcc two bytes too short and incorrect uid in PDU).
-
-Version 0.37
-------------
-Rewrote much of connection and mount/unmount logic to handle bugs with
-multiple uses to same share, multiple users to same server etc.
-
-Version 0.36
-------------
-Fixed major problem with dentry corruption (missing call to dput)
-
-Version 0.35
-------------
-Rewrite of readdir code to fix bug. Various fixes for bigendian machines.
-Begin adding oplock support.  Multiusermount and oplockEnabled flags added to /proc/fs/cifs
-although corresponding function not fully implemented in the vfs yet
-
-Version 0.34
-------------
-Fixed dentry caching bug, misc. cleanup 
-
-Version 0.33
-------------
-Fixed 2.5 support to handle build and configure changes as well as misc. 2.5 changes.  Now can build
-on current 2.5 beta version (2.5.24) of the Linux kernel as well as on 2.4 Linux kernels.
-Support for STATUS codes (newer 32 bit NT error codes) added.  DFS support begun to be added.
-
-Version 0.32
-------------
-Unix extensions (symlink, readlink, hardlink, chmod and some chgrp and chown) implemented
-and tested against Samba 2.2.5
-
-
-Version 0.31
-------------
-1) Fixed lockrange to be correct (it was one byte too short)
-
-2) Fixed GETLK (i.e. the fcntl call to test a range of bytes in a file to see if locked) to correctly 
-show range as locked when there is a conflict with an existing lock.
-
-3) default file perms are now 2767 (indicating support for mandatory locks) instead of 777 for directories
-in most cases.  Eventually will offer optional ability to query server for the correct perms.
-
-3) Fixed eventual trap when mounting twice to different shares on the same server when the first succeeded 
-but the second one was invalid and failed (the second one was incorrectly disconnecting the tcp and smb
-session) 
-
-4) Fixed error logging of valid mount options
-
-5) Removed logging of password field.
-
-6) Moved negotiate, treeDisconnect and uloggoffX (only tConx and SessSetup remain in connect.c) to cifssmb.c
-and cleaned them up and made them more consistent with other cifs functions. 
-
-7) Server support for Unix extensions is now fully detected and FindFirst is implemented both ways 
-(with or without Unix extensions) but FindNext and QueryPathInfo with the Unix extensions are not completed,
-nor is the symlink support using the Unix extensions
-
-8) Started adding the readlink and follow_link code 
-
-Version 0.3 
------------
-Initial drop
-
+See https://wiki.samba.org/index.php/LinuxCIFSKernel for summary
+information (that may be easier to read than parsing the output of
+"git log fs/cifs") about fixes/improvements to CIFS/SMB2/SMB3 support (changes
+to cifs.ko module) by kernel version (and cifs internal module version).
diff --git a/Documentation/filesystems/cifs/README b/Documentation/filesystems/cifs/README
index 99ce3d25003d..4a804619cff2 100644
--- a/Documentation/filesystems/cifs/README
+++ b/Documentation/filesystems/cifs/README
@@ -603,8 +603,7 @@ DebugData		Displays information about active CIFS sessions and
 			shares, features enabled as well as the cifs.ko
 			version.
 Stats			Lists summary resource usage information as well as per
-			share statistics, if CONFIG_CIFS_STATS in enabled
-			in the kernel configuration.
+			share statistics.
 
 Configuration pseudo-files:
 SecurityFlags		Flags which control security negotiation and
@@ -687,23 +686,22 @@ cifsFYI functions as a bit mask. Setting it to 1 enables additional kernel
 logging of various informational messages.  2 enables logging of non-zero
 SMB return codes while 4 enables logging of requests that take longer
 than one second to complete (except for byte range lock requests). 
-Setting it to 4 requires defining CONFIG_CIFS_STATS2 manually in the
-source code (typically by setting it in the beginning of cifsglob.h),
-and setting it to seven enables all three.  Finally, tracing
+Setting it to 4 requires CONFIG_CIFS_STATS2 to be set in kernel configuration
+(.config). Setting it to seven enables all three.  Finally, tracing
 the start of smb requests and responses can be enabled via:
 
 	echo 1 > /proc/fs/cifs/traceSMB
 
-Per share (per client mount) statistics are available in /proc/fs/cifs/Stats
-if the kernel was configured with cifs statistics enabled.  The statistics
-represent the number of successful (ie non-zero return code from the server) 
-SMB responses to some of the more common commands (open, delete, mkdir etc.).
+Per share (per client mount) statistics are available in /proc/fs/cifs/Stats.
+Additional information is available if CONFIG_CIFS_STATS2 is enabled in the
+kernel configuration (.config).  The statistics returned include counters which
+represent the number of attempted and failed (ie non-zero return code from the
+server) SMB3 (or cifs) requests grouped by request type (read, write, close etc.).
 Also recorded is the total bytes read and bytes written to the server for
 that share.  Note that due to client caching effects this can be less than the
 number of bytes read and written by the application running on the client.
-The statistics for the number of total SMBs and oplock breaks are different in
-that they represent all for that share, not just those for which the server
-returned success.
+Statistics can be reset to zero by "echo 0 > /proc/fs/cifs/Stats" which may be
+useful if comparing performance of two different scenarios.
 	
 Also note that "cat /proc/fs/cifs/DebugData" will display information about
 the active sessions and the shares that are mounted.
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4/ext4.rst
index 7f628b9f7c4b..9d4368d591fa 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4/ext4.rst
@@ -1,6 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
 
-Ext4 Filesystem
-===============
+========================
+General Information
+========================
 
 Ext4 is an advanced level of the ext3 filesystem which incorporates
 scalability and reliability enhancements for supporting large filesystems
@@ -11,37 +13,30 @@ Mailing list:	linux-ext4@vger.kernel.org
 Web site:	http://ext4.wiki.kernel.org
 
 
-1. Quick usage instructions:
-===========================
+Quick usage instructions
+========================
 
 Note: More extensive information for getting started with ext4 can be
-      found at the ext4 wiki site at the URL:
-      http://ext4.wiki.kernel.org/index.php/Ext4_Howto
+found at the ext4 wiki site at the URL:
+http://ext4.wiki.kernel.org/index.php/Ext4_Howto
 
-  - Compile and install the latest version of e2fsprogs (as of this
-    writing version 1.41.3) from:
+  - The latest version of e2fsprogs can be found at:
+
+    https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
 
-    http://sourceforge.net/project/showfiles.php?group_id=2406
-	
 	or
 
-    https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
+    http://sourceforge.net/project/showfiles.php?group_id=2406
 
 	or grab the latest git repository from:
 
-    git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
-
-  - Note that it is highly important to install the mke2fs.conf file
-    that comes with the e2fsprogs 1.41.x sources in /etc/mke2fs.conf. If
-    you have edited the /etc/mke2fs.conf file installed on your system,
-    you will need to merge your changes with the version from e2fsprogs
-    1.41.x.
+   https://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
 
   - Create a new filesystem using the ext4 filesystem type:
 
-    	# mke2fs -t ext4 /dev/hda1
+        # mke2fs -t ext4 /dev/hda1
 
-    Or to configure an existing ext3 filesystem to support extents: 
+    Or to configure an existing ext3 filesystem to support extents:
 
 	# tune2fs -O extents /dev/hda1
 
@@ -50,10 +45,6 @@ Note: More extensive information for getting started with ext4 can be
 
         # tune2fs -I 256 /dev/hda1
 
-    (Note: we currently do not have tools to convert an ext4
-    filesystem back to ext3; so please do not do try this on production
-    filesystems.)
-
   - Mounting:
 
 	# mount -t ext4 /dev/hda1 /wherever
@@ -75,10 +66,11 @@ Note: More extensive information for getting started with ext4 can be
     the filesystem with a large journal can also be helpful for
     metadata-intensive workloads.
 
-2. Features
-===========
+Features
+========
 
-2.1 Currently available
+Currently Available
+-------------------
 
 * ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
@@ -103,31 +95,15 @@ Note: More extensive information for getting started with ext4 can be
 [1] Filesystems with a block size of 1k may see a limit imposed by the
 directory hash tree having a maximum depth of two.
 
-2.2 Candidate features for future inclusion
-
-* online defrag (patches available but not well tested)
-* reduced mke2fs time via lazy itable initialization in conjunction with
-  the uninit_bg feature (capability to do this is available in e2fsprogs
-  but a kernel thread to do lazy zeroing of unused inode table blocks
-  after filesystem is first mounted is required for safety)
-
-There are several others under discussion, whether they all make it in is
-partly a function of how much time everyone has to work on them. Features like
-metadata checksumming have been discussed and planned for a bit but no patches
-exist yet so I'm not sure they're in the near-term roadmap.
-
-The big performance win will come with mballoc, delalloc and flex_bg
-grouping of bitmaps and inode tables.  Some test results available here:
-
- - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-write-2.6.27-rc1.html
- - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-readwrite-2.6.27-rc1.html
-
-3. Options
-==========
+Options
+=======
 
 When mounting an ext4 filesystem, the following option are accepted:
 (*) == default
 
+======================= =======================================================
+Mount Option            Description
+======================= =======================================================
 ro                   	Mount filesystem read only. Note that ext4 will
                      	replay the journal (and thus write to the
                      	partition) even when mounted "read only". The
@@ -387,33 +363,38 @@ i_version		Enable 64-bit inode version support. This option is
 dax			Use direct access (no page cache).  See
 			Documentation/filesystems/dax.txt.  Note that
 			this option is incompatible with data=journal.
+======================= =======================================================
 
 Data Mode
 =========
 There are 3 different data modes:
 
 * writeback mode
-In data=writeback mode, ext4 does not journal data at all.  This mode provides
-a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
-mode - metadata journaling.  A crash+recovery can cause incorrect data to
-appear in files which were written shortly before the crash.  This mode will
-typically provide the best ext4 performance.
+
+  In data=writeback mode, ext4 does not journal data at all.  This mode provides
+  a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
+  mode - metadata journaling.  A crash+recovery can cause incorrect data to
+  appear in files which were written shortly before the crash.  This mode will
+  typically provide the best ext4 performance.
 
 * ordered mode
-In data=ordered mode, ext4 only officially journals metadata, but it logically
-groups metadata information related to data changes with the data blocks into a
-single unit called a transaction.  When it's time to write the new metadata
-out to disk, the associated data blocks are written first.  In general,
-this mode performs slightly slower than writeback but significantly faster than journal mode.
+
+  In data=ordered mode, ext4 only officially journals metadata, but it logically
+  groups metadata information related to data changes with the data blocks into
+  a single unit called a transaction.  When it's time to write the new metadata
+  out to disk, the associated data blocks are written first.  In general, this
+  mode performs slightly slower than writeback but significantly faster than
+  journal mode.
 
 * journal mode
-data=journal mode provides full data and metadata journaling.  All new data is
-written to the journal first, and then to its final location.
-In the event of a crash, the journal can be replayed, bringing both data and
-metadata into a consistent state.  This mode is the slowest except when data
-needs to be read from and written to disk at the same time where it
-outperforms all others modes.  Enabling this mode will disable delayed
-allocation and O_DIRECT support.
+
+  data=journal mode provides full data and metadata journaling.  All new data is
+  written to the journal first, and then to its final location.  In the event of
+  a crash, the journal can be replayed, bringing both data and metadata into a
+  consistent state.  This mode is the slowest except when data needs to be read
+  from and written to disk at the same time where it outperforms all others
+  modes.  Enabling this mode will disable delayed allocation and O_DIRECT
+  support.
 
 /proc entries
 =============
@@ -425,10 +406,12 @@ Information about mounted ext4 file systems can be found in
 in table below.
 
 Files in /proc/fs/ext4/<devname>
-..............................................................................
+
+================ =======
  File            Content
+================ =======
  mb_groups       details of multiblock allocator buddy cache of free blocks
-..............................................................................
+================ =======
 
 /sys entries
 ============
@@ -439,28 +422,30 @@ Information about mounted ext4 file systems can be found in
 /sys/fs/ext4/dm-0).   The files in each per-device directory are shown
 in table below.
 
-Files in /sys/fs/ext4/<devname>
+Files in /sys/fs/ext4/<devname>:
+
 (see also Documentation/ABI/testing/sysfs-fs-ext4)
-..............................................................................
- File                         Content
 
+============================= =================================================
+File                          Content
+============================= =================================================
  delayed_allocation_blocks    This file is read-only and shows the number of
                               blocks that are dirty in the page cache, but
                               which do not have their location in the
                               filesystem allocated yet.
 
- inode_goal                   Tuning parameter which (if non-zero) controls
+inode_goal                    Tuning parameter which (if non-zero) controls
                               the goal inode used by the inode allocator in
                               preference to all other allocation heuristics.
                               This is intended for debugging use only, and
                               should be 0 on production systems.
 
- inode_readahead_blks         Tuning parameter which controls the maximum
+inode_readahead_blks          Tuning parameter which controls the maximum
                               number of inode table blocks that ext4's inode
                               table readahead algorithm will pre-read into
                               the buffer cache
 
- lifetime_write_kbytes        This file is read-only and shows the number of
+lifetime_write_kbytes         This file is read-only and shows the number of
                               kilobytes of data that have been written to this
                               filesystem since it was created.
 
@@ -508,7 +493,7 @@ Files in /sys/fs/ext4/<devname>
                               in the file system. If there is not enough space
                               for the reserved space when mounting the file
                               mount will _not_ fail.
-..............................................................................
+============================= =================================================
 
 Ioctls
 ======
@@ -518,8 +503,10 @@ through the system call interfaces. The list of all Ext4 specific ioctls are
 shown in the table below.
 
 Table of Ext4 specific ioctls
-..............................................................................
- Ioctl			      Description
+
+============================= =================================================
+Ioctl			      Description
+============================= =================================================
  EXT4_IOC_GETFLAGS	      Get additional attributes associated with inode.
 			      The ioctl argument is an integer bitfield, with
 			      bit values described in ext4.h. This ioctl is an
@@ -610,8 +597,7 @@ Table of Ext4 specific ioctls
 			      normal user by accident.
 			      The data blocks of the previous boot loader
 			      will be associated with the given inode.
-
-..............................................................................
+============================= =================================================
 
 References
 ==========
diff --git a/Documentation/filesystems/ext4/index.rst b/Documentation/filesystems/ext4/index.rst
new file mode 100644
index 000000000000..71121605558c
--- /dev/null
+++ b/Documentation/filesystems/ext4/index.rst
@@ -0,0 +1,17 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+ext4 Filesystem
+===============
+
+General usage and on-disk artifacts writen by ext4.  More documentation may
+be ported from the wiki as time permits.  This should be considered the
+canonical source of information as the details here have been reviewed by
+the ext4 community.
+
+.. toctree::
+   :maxdepth: 5
+   :numbered:
+
+   ext4
+   ondisk/index
diff --git a/Documentation/filesystems/ext4/ondisk/about.rst b/Documentation/filesystems/ext4/ondisk/about.rst
new file mode 100644
index 000000000000..0aadba052264
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/about.rst
@@ -0,0 +1,44 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+About this Book
+===============
+
+This document attempts to describe the on-disk format for ext4
+filesystems. The same general ideas should apply to ext2/3 filesystems
+as well, though they do not support all the features that ext4 supports,
+and the fields will be shorter.
+
+**NOTE**: This is a work in progress, based on notes that the author
+(djwong) made while picking apart a filesystem by hand. The data
+structure definitions should be current as of Linux 4.18 and
+e2fsprogs-1.44. All comments and corrections are welcome, since there is
+undoubtedly plenty of lore that might not be reflected in freshly
+created demonstration filesystems.
+
+License
+-------
+This book is licensed under the terms of the GNU Public License, v2.
+
+Terminology
+-----------
+
+ext4 divides a storage device into an array of logical blocks both to
+reduce bookkeeping overhead and to increase throughput by forcing larger
+transfer sizes. Generally, the block size will be 4KiB (the same size as
+pages on x86 and the block layer's default block size), though the
+actual size is calculated as 2 ^ (10 + ``sb.s_log_block_size``) bytes.
+Throughout this document, disk locations are given in terms of these
+logical blocks, not raw LBAs, and not 1024-byte blocks. For the sake of
+convenience, the logical block size will be referred to as
+``$block_size`` throughout the rest of the document.
+
+When referenced in ``preformatted text`` blocks, ``sb`` refers to fields
+in the super block, and ``inode`` refers to fields in an inode table
+entry.
+
+Other References
+----------------
+
+Also see http://www.nongnu.org/ext2-doc/ for quite a collection of
+information about ext2/3. Here's another old reference:
+http://wiki.osdev.org/Ext2
diff --git a/Documentation/filesystems/ext4/ondisk/allocators.rst b/Documentation/filesystems/ext4/ondisk/allocators.rst
new file mode 100644
index 000000000000..7aa85152ace3
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/allocators.rst
@@ -0,0 +1,56 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Block and Inode Allocation Policy
+---------------------------------
+
+ext4 recognizes (better than ext3, anyway) that data locality is
+generally a desirably quality of a filesystem. On a spinning disk,
+keeping related blocks near each other reduces the amount of movement
+that the head actuator and disk must perform to access a data block,
+thus speeding up disk IO. On an SSD there of course are no moving parts,
+but locality can increase the size of each transfer request while
+reducing the total number of requests. This locality may also have the
+effect of concentrating writes on a single erase block, which can speed
+up file rewrites significantly. Therefore, it is useful to reduce
+fragmentation whenever possible.
+
+The first tool that ext4 uses to combat fragmentation is the multi-block
+allocator. When a file is first created, the block allocator
+speculatively allocates 8KiB of disk space to the file on the assumption
+that the space will get written soon. When the file is closed, the
+unused speculative allocations are of course freed, but if the
+speculation is correct (typically the case for full writes of small
+files) then the file data gets written out in a single multi-block
+extent. A second related trick that ext4 uses is delayed allocation.
+Under this scheme, when a file needs more blocks to absorb file writes,
+the filesystem defers deciding the exact placement on the disk until all
+the dirty buffers are being written out to disk. By not committing to a
+particular placement until it's absolutely necessary (the commit timeout
+is hit, or sync() is called, or the kernel runs out of memory), the hope
+is that the filesystem can make better location decisions.
+
+The third trick that ext4 (and ext3) uses is that it tries to keep a
+file's data blocks in the same block group as its inode. This cuts down
+on the seek penalty when the filesystem first has to read a file's inode
+to learn where the file's data blocks live and then seek over to the
+file's data blocks to begin I/O operations.
+
+The fourth trick is that all the inodes in a directory are placed in the
+same block group as the directory, when feasible. The working assumption
+here is that all the files in a directory might be related, therefore it
+is useful to try to keep them all together.
+
+The fifth trick is that the disk volume is cut up into 128MB block
+groups; these mini-containers are used as outlined above to try to
+maintain data locality. However, there is a deliberate quirk -- when a
+directory is created in the root directory, the inode allocator scans
+the block groups and puts that directory into the least heavily loaded
+block group that it can find. This encourages directories to spread out
+over a disk; as the top-level directory/file blobs fill up one block
+group, the allocators simply move on to the next block group. Allegedly
+this scheme evens out the loading on the block groups, though the author
+suspects that the directories which are so unlucky as to land towards
+the end of a spinning drive get a raw deal performance-wise.
+
+Of course if all of these mechanisms fail, one can always use e4defrag
+to defragment files.
diff --git a/Documentation/filesystems/ext4/ondisk/attributes.rst b/Documentation/filesystems/ext4/ondisk/attributes.rst
new file mode 100644
index 000000000000..0b01b67b81fe
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/attributes.rst
@@ -0,0 +1,191 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Extended Attributes
+-------------------
+
+Extended attributes (xattrs) are typically stored in a separate data
+block on the disk and referenced from inodes via ``inode.i_file_acl*``.
+The first use of extended attributes seems to have been for storing file
+ACLs and other security data (selinux). With the ``user_xattr`` mount
+option it is possible for users to store extended attributes so long as
+all attribute names begin with “user�; this restriction seems to have
+disappeared as of Linux 3.0.
+
+There are two places where extended attributes can be found. The first
+place is between the end of each inode entry and the beginning of the
+next inode entry. For example, if inode.i\_extra\_isize = 28 and
+sb.inode\_size = 256, then there are 256 - (128 + 28) = 100 bytes
+available for in-inode extended attribute storage. The second place
+where extended attributes can be found is in the block pointed to by
+``inode.i_file_acl``. As of Linux 3.11, it is not possible for this
+block to contain a pointer to a second extended attribute block (or even
+the remaining blocks of a cluster). In theory it is possible for each
+attribute's value to be stored in a separate data block, though as of
+Linux 3.11 the code does not permit this.
+
+Keys are generally assumed to be ASCIIZ strings, whereas values can be
+strings or binary data.
+
+Extended attributes, when stored after the inode, have a header
+``ext4_xattr_ibody_header`` that is 4 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - h\_magic
+     - Magic number for identification, 0xEA020000. This value is set by the
+       Linux driver, though e2fsprogs doesn't seem to check it(?)
+
+The beginning of an extended attribute block is in
+``struct ext4_xattr_header``, which is 32 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - h\_magic
+     - Magic number for identification, 0xEA020000.
+   * - 0x4
+     - \_\_le32
+     - h\_refcount
+     - Reference count.
+   * - 0x8
+     - \_\_le32
+     - h\_blocks
+     - Number of disk blocks used.
+   * - 0xC
+     - \_\_le32
+     - h\_hash
+     - Hash value of all attributes.
+   * - 0x10
+     - \_\_le32
+     - h\_checksum
+     - Checksum of the extended attribute block.
+   * - 0x14
+     - \_\_u32
+     - h\_reserved[2]
+     - Zero.
+
+The checksum is calculated against the FS UUID, the 64-bit block number
+of the extended attribute block, and the entire block (header +
+entries).
+
+Following the ``struct ext4_xattr_header`` or
+``struct ext4_xattr_ibody_header`` is an array of
+``struct ext4_xattr_entry``; each of these entries is at least 16 bytes
+long. When stored in an external block, the ``struct ext4_xattr_entry``
+entries must be stored in sorted order. The sort order is
+``e_name_index``, then ``e_name_len``, and finally ``e_name``.
+Attributes stored inside an inode do not need be stored in sorted order.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_u8
+     - e\_name\_len
+     - Length of name.
+   * - 0x1
+     - \_\_u8
+     - e\_name\_index
+     - Attribute name index. There is a discussion of this below.
+   * - 0x2
+     - \_\_le16
+     - e\_value\_offs
+     - Location of this attribute's value on the disk block where it is stored.
+       Multiple attributes can share the same value. For an inode attribute
+       this value is relative to the start of the first entry; for a block this
+       value is relative to the start of the block (i.e. the header).
+   * - 0x4
+     - \_\_le32
+     - e\_value\_inum
+     - The inode where the value is stored. Zero indicates the value is in the
+       same block as this entry. This field is only used if the
+       INCOMPAT\_EA\_INODE feature is enabled.
+   * - 0x8
+     - \_\_le32
+     - e\_value\_size
+     - Length of attribute value.
+   * - 0xC
+     - \_\_le32
+     - e\_hash
+     - Hash value of attribute name and attribute value. The kernel doesn't
+       update the hash for in-inode attributes, so for that case this value
+       must be zero, because e2fsck validates any non-zero hash regardless of
+       where the xattr lives.
+   * - 0x10
+     - char
+     - e\_name[e\_name\_len]
+     - Attribute name. Does not include trailing NULL.
+
+Attribute values can follow the end of the entry table. There appears to
+be a requirement that they be aligned to 4-byte boundaries. The values
+are stored starting at the end of the block and grow towards the
+xattr\_header/xattr\_entry table. When the two collide, the overflow is
+put into a separate disk block. If the disk block fills up, the
+filesystem returns -ENOSPC.
+
+The first four fields of the ``ext4_xattr_entry`` are set to zero to
+mark the end of the key list.
+
+Attribute Name Indices
+~~~~~~~~~~~~~~~~~~~~~~
+
+Logically speaking, extended attributes are a series of key=value pairs.
+The keys are assumed to be NULL-terminated strings. To reduce the amount
+of on-disk space that the keys consume, the beginning of the key string
+is matched against the attribute name index. If a match is found, the
+attribute name index field is set, and matching string is removed from
+the key name. Here is a map of name index values to key prefixes:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Name Index
+     - Key Prefix
+   * - 0
+     - (no prefix)
+   * - 1
+     - “user.�
+   * - 2
+     - “system.posix\_acl\_access�
+   * - 3
+     - “system.posix\_acl\_default�
+   * - 4
+     - “trusted.�
+   * - 6
+     - “security.�
+   * - 7
+     - “system.� (inline\_data only?)
+   * - 8
+     - “system.richacl� (SuSE kernels only?)
+
+For example, if the attribute key is “user.fubar�, the attribute name
+index is set to 1 and the “fubar� name is recorded on disk.
+
+POSIX ACLs
+~~~~~~~~~~
+
+POSIX ACLs are stored in a reduced version of the Linux kernel (and
+libacl's) internal ACL format. The key difference is that the version
+number is different (1) and the ``e_id`` field is only stored for named
+user and group ACLs.
diff --git a/Documentation/filesystems/ext4/ondisk/bigalloc.rst b/Documentation/filesystems/ext4/ondisk/bigalloc.rst
new file mode 100644
index 000000000000..c6d88557553c
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/bigalloc.rst
@@ -0,0 +1,22 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Bigalloc
+--------
+
+At the moment, the default size of a block is 4KiB, which is a commonly
+supported page size on most MMU-capable hardware. This is fortunate, as
+ext4 code is not prepared to handle the case where the block size
+exceeds the page size. However, for a filesystem of mostly huge files,
+it is desirable to be able to allocate disk blocks in units of multiple
+blocks to reduce both fragmentation and metadata overhead. The
+`bigalloc <Bigalloc>`__ feature provides exactly this ability. The
+administrator can set a block cluster size at mkfs time (which is stored
+in the s\_log\_cluster\_size field in the superblock); from then on, the
+block bitmaps track clusters, not individual blocks. This means that
+block groups can be several gigabytes in size (instead of just 128MiB);
+however, the minimum allocation unit becomes a cluster, not a block,
+even for directories. TaoBao had a patchset to extend the “use units of
+clusters instead of blocks� to the extent tree, though it is not clear
+where those patches went-- they eventually morphed into “extent tree v2�
+but that code has not landed as of May 2015.
+
diff --git a/Documentation/filesystems/ext4/ondisk/bitmaps.rst b/Documentation/filesystems/ext4/ondisk/bitmaps.rst
new file mode 100644
index 000000000000..c7546dbc197a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/bitmaps.rst
@@ -0,0 +1,28 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Block and inode Bitmaps
+-----------------------
+
+The data block bitmap tracks the usage of data blocks within the block
+group.
+
+The inode bitmap records which entries in the inode table are in use.
+
+As with most bitmaps, one bit represents the usage status of one data
+block or inode table entry. This implies a block group size of 8 \*
+number\_of\_bytes\_in\_a\_logical\_block.
+
+NOTE: If ``BLOCK_UNINIT`` is set for a given block group, various parts
+of the kernel and e2fsprogs code pretends that the block bitmap contains
+zeros (i.e. all blocks in the group are free). However, it is not
+necessarily the case that no blocks are in use -- if ``meta_bg`` is set,
+the bitmaps and group descriptor live inside the group. Unfortunately,
+ext2fs\_test\_block\_bitmap2() will return '0' for those locations,
+which produces confusing debugfs output.
+
+Inode Table
+-----------
+Inode tables are statically allocated at mkfs time.  Each block group
+descriptor points to the start of the table, and the superblock records
+the number of inodes per group.  See the section on inodes for more
+information.
diff --git a/Documentation/filesystems/ext4/ondisk/blockgroup.rst b/Documentation/filesystems/ext4/ondisk/blockgroup.rst
new file mode 100644
index 000000000000..baf888e4c06a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/blockgroup.rst
@@ -0,0 +1,135 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Layout
+------
+
+The layout of a standard block group is approximately as follows (each
+of these fields is discussed in a separate section below):
+
+.. list-table::
+   :widths: 1 1 1 1 1 1 1 1
+   :header-rows: 1
+
+   * - Group 0 Padding
+     - ext4 Super Block
+     - Group Descriptors
+     - Reserved GDT Blocks
+     - Data Block Bitmap
+     - inode Bitmap
+     - inode Table
+     - Data Blocks
+   * - 1024 bytes
+     - 1 block
+     - many blocks
+     - many blocks
+     - 1 block
+     - 1 block
+     - many blocks
+     - many more blocks
+
+For the special case of block group 0, the first 1024 bytes are unused,
+to allow for the installation of x86 boot sectors and other oddities.
+The superblock will start at offset 1024 bytes, whichever block that
+happens to be (usually 0). However, if for some reason the block size =
+1024, then block 0 is marked in use and the superblock goes in block 1.
+For all other block groups, there is no padding.
+
+The ext4 driver primarily works with the superblock and the group
+descriptors that are found in block group 0. Redundant copies of the
+superblock and group descriptors are written to some of the block groups
+across the disk in case the beginning of the disk gets trashed, though
+not all block groups necessarily host a redundant copy (see following
+paragraph for more details). If the group does not have a redundant
+copy, the block group begins with the data block bitmap. Note also that
+when the filesystem is freshly formatted, mkfs will allocate “reserve
+GDT block� space after the block group descriptors and before the start
+of the block bitmaps to allow for future expansion of the filesystem. By
+default, a filesystem is allowed to increase in size by a factor of
+1024x over the original filesystem size.
+
+The location of the inode table is given by ``grp.bg_inode_table_*``. It
+is continuous range of blocks large enough to contain
+``sb.s_inodes_per_group * sb.s_inode_size`` bytes.
+
+As for the ordering of items in a block group, it is generally
+established that the super block and the group descriptor table, if
+present, will be at the beginning of the block group. The bitmaps and
+the inode table can be anywhere, and it is quite possible for the
+bitmaps to come after the inode table, or for both to be in different
+groups (flex\_bg). Leftover space is used for file data blocks, indirect
+block maps, extent tree blocks, and extended attributes.
+
+Flexible Block Groups
+---------------------
+
+Starting in ext4, there is a new feature called flexible block groups
+(flex\_bg). In a flex\_bg, several block groups are tied together as one
+logical block group; the bitmap spaces and the inode table space in the
+first block group of the flex\_bg are expanded to include the bitmaps
+and inode tables of all other block groups in the flex\_bg. For example,
+if the flex\_bg size is 4, then group 0 will contain (in order) the
+superblock, group descriptors, data block bitmaps for groups 0-3, inode
+bitmaps for groups 0-3, inode tables for groups 0-3, and the remaining
+space in group 0 is for file data. The effect of this is to group the
+block metadata close together for faster loading, and to enable large
+files to be continuous on disk. Backup copies of the superblock and
+group descriptors are always at the beginning of block groups, even if
+flex\_bg is enabled. The number of block groups that make up a flex\_bg
+is given by 2 ^ ``sb.s_log_groups_per_flex``.
+
+Meta Block Groups
+-----------------
+
+Without the option META\_BG, for safety concerns, all block group
+descriptors copies are kept in the first block group. Given the default
+128MiB(2^27 bytes) block group size and 64-byte group descriptors, ext4
+can have at most 2^27/64 = 2^21 block groups. This limits the entire
+filesystem size to 2^21 ∗ 2^27 = 2^48bytes or 256TiB.
+
+The solution to this problem is to use the metablock group feature
+(META\_BG), which is already in ext3 for all 2.6 releases. With the
+META\_BG feature, ext4 filesystems are partitioned into many metablock
+groups. Each metablock group is a cluster of block groups whose group
+descriptor structures can be stored in a single disk block. For ext4
+filesystems with 4 KB block size, a single metablock group partition
+includes 64 block groups, or 8 GiB of disk space. The metablock group
+feature moves the location of the group descriptors from the congested
+first block group of the whole filesystem into the first group of each
+metablock group itself. The backups are in the second and last group of
+each metablock group. This increases the 2^21 maximum block groups limit
+to the hard limit 2^32, allowing support for a 512PiB filesystem.
+
+The change in the filesystem format replaces the current scheme where
+the superblock is followed by a variable-length set of block group
+descriptors. Instead, the superblock and a single block group descriptor
+block is placed at the beginning of the first, second, and last block
+groups in a meta-block group. A meta-block group is a collection of
+block groups which can be described by a single block group descriptor
+block. Since the size of the block group descriptor structure is 32
+bytes, a meta-block group contains 32 block groups for filesystems with
+a 1KB block size, and 128 block groups for filesystems with a 4KB
+blocksize. Filesystems can either be created using this new block group
+descriptor layout, or existing filesystems can be resized on-line, and
+the field s\_first\_meta\_bg in the superblock will indicate the first
+block group using this new layout.
+
+Please see an important note about ``BLOCK_UNINIT`` in the section about
+block and inode bitmaps.
+
+Lazy Block Group Initialization
+-------------------------------
+
+A new feature for ext4 are three block group descriptor flags that
+enable mkfs to skip initializing other parts of the block group
+metadata. Specifically, the INODE\_UNINIT and BLOCK\_UNINIT flags mean
+that the inode and block bitmaps for that group can be calculated and
+therefore the on-disk bitmap blocks are not initialized. This is
+generally the case for an empty block group or a block group containing
+only fixed-location block group metadata. The INODE\_ZEROED flag means
+that the inode table has been initialized; mkfs will unset this flag and
+rely on the kernel to initialize the inode tables in the background.
+
+By not writing zeroes to the bitmaps and inode table, mkfs time is
+reduced considerably. Note the feature flag is RO\_COMPAT\_GDT\_CSUM,
+but the dumpe2fs output prints this as “uninit\_bg�. They are the same
+thing.
diff --git a/Documentation/filesystems/ext4/ondisk/blockmap.rst b/Documentation/filesystems/ext4/ondisk/blockmap.rst
new file mode 100644
index 000000000000..30e25750d88a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/blockmap.rst
@@ -0,0 +1,49 @@
+.. SPDX-License-Identifier: GPL-2.0
+
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| i.i\_block Offset   | Where It Points                                                                                                                                                                                                              |
++=====================+==============================================================================================================================================================================================================================+
+| 0 to 11             | Direct map to file blocks 0 to 11.                                                                                                                                                                                           |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| 12                  | Indirect block: (file blocks 12 to (``$block_size`` / 4) + 11, or 12 to 1035 if 4KiB blocks)                                                                                                                                 |
+|                     |                                                                                                                                                                                                                              |
+|                     | +------------------------------+--------------------------------------------------------------------+                                                                                                                        |
+|                     | | Indirect Block Offset        | Where It Points                                                    |                                                                                                                        |
+|                     | +==============================+====================================================================+                                                                                                                        |
+|                     | | 0 to (``$block_size`` / 4)   | Direct map to (``$block_size`` / 4) blocks (1024 if 4KiB blocks)   |                                                                                                                        |
+|                     | +------------------------------+--------------------------------------------------------------------+                                                                                                                        |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| 13                  | Double-indirect block: (file blocks ``$block_size``/4 + 12 to (``$block_size`` / 4) ^ 2 + (``$block_size`` / 4) + 11, or 1036 to 1049611 if 4KiB blocks)                                                                     |
+|                     |                                                                                                                                                                                                                              |
+|                     | +--------------------------------+---------------------------------------------------------------------------------------------------------+                                                                                 |
+|                     | | Double Indirect Block Offset   | Where It Points                                                                                         |                                                                                 |
+|                     | +================================+=========================================================================================================+                                                                                 |
+|                     | | 0 to (``$block_size`` / 4)     | Map to (``$block_size`` / 4) indirect blocks (1024 if 4KiB blocks)                                      |                                                                                 |
+|                     | |                                |                                                                                                         |                                                                                 |
+|                     | |                                | +------------------------------+--------------------------------------------------------------------+   |                                                                                 |
+|                     | |                                | | Indirect Block Offset        | Where It Points                                                    |   |                                                                                 |
+|                     | |                                | +==============================+====================================================================+   |                                                                                 |
+|                     | |                                | | 0 to (``$block_size`` / 4)   | Direct map to (``$block_size`` / 4) blocks (1024 if 4KiB blocks)   |   |                                                                                 |
+|                     | |                                | +------------------------------+--------------------------------------------------------------------+   |                                                                                 |
+|                     | +--------------------------------+---------------------------------------------------------------------------------------------------------+                                                                                 |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| 14                  | Triple-indirect block: (file blocks (``$block_size`` / 4) ^ 2 + (``$block_size`` / 4) + 12 to (``$block_size`` / 4) ^ 3 + (``$block_size`` / 4) ^ 2 + (``$block_size`` / 4) + 12, or 1049612 to 1074791436 if 4KiB blocks)   |
+|                     |                                                                                                                                                                                                                              |
+|                     | +--------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------+                                          |
+|                     | | Triple Indirect Block Offset   | Where It Points                                                                                                                                |                                          |
+|                     | +================================+================================================================================================================================================+                                          |
+|                     | | 0 to (``$block_size`` / 4)     | Map to (``$block_size`` / 4) double indirect blocks (1024 if 4KiB blocks)                                                                      |                                          |
+|                     | |                                |                                                                                                                                                |                                          |
+|                     | |                                | +--------------------------------+---------------------------------------------------------------------------------------------------------+   |                                          |
+|                     | |                                | | Double Indirect Block Offset   | Where It Points                                                                                         |   |                                          |
+|                     | |                                | +================================+=========================================================================================================+   |                                          |
+|                     | |                                | | 0 to (``$block_size`` / 4)     | Map to (``$block_size`` / 4) indirect blocks (1024 if 4KiB blocks)                                      |   |                                          |
+|                     | |                                | |                                |                                                                                                         |   |                                          |
+|                     | |                                | |                                | +------------------------------+--------------------------------------------------------------------+   |   |                                          |
+|                     | |                                | |                                | | Indirect Block Offset        | Where It Points                                                    |   |   |                                          |
+|                     | |                                | |                                | +==============================+====================================================================+   |   |                                          |
+|                     | |                                | |                                | | 0 to (``$block_size`` / 4)   | Direct map to (``$block_size`` / 4) blocks (1024 if 4KiB blocks)   |   |   |                                          |
+|                     | |                                | |                                | +------------------------------+--------------------------------------------------------------------+   |   |                                          |
+|                     | |                                | +--------------------------------+---------------------------------------------------------------------------------------------------------+   |                                          |
+|                     | +--------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------+                                          |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
diff --git a/Documentation/filesystems/ext4/ondisk/blocks.rst b/Documentation/filesystems/ext4/ondisk/blocks.rst
new file mode 100644
index 000000000000..73d4dc0f7bda
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/blocks.rst
@@ -0,0 +1,142 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Blocks
+------
+
+ext4 allocates storage space in units of “blocks�. A block is a group of
+sectors between 1KiB and 64KiB, and the number of sectors must be an
+integral power of 2. Blocks are in turn grouped into larger units called
+block groups. Block size is specified at mkfs time and typically is
+4KiB. You may experience mounting problems if block size is greater than
+page size (i.e. 64KiB blocks on a i386 which only has 4KiB memory
+pages). By default a filesystem can contain 2^32 blocks; if the '64bit'
+feature is enabled, then a filesystem can have 2^64 blocks.
+
+For 32-bit filesystems, limits are as follows:
+
+.. list-table::
+   :widths: 1 1 1 1 1
+   :header-rows: 1
+
+   * - Item
+     - 1KiB
+     - 2KiB
+     - 4KiB
+     - 64KiB
+   * - Blocks
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - Inodes
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - File System Size
+     - 4TiB
+     - 8TiB
+     - 16TiB
+     - 256PiB
+   * - Blocks Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Inodes Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Block Group Size
+     - 8MiB
+     - 32MiB
+     - 128MiB
+     - 32GiB
+   * - Blocks Per File, Extents
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - Blocks Per File, Block Maps
+     - 16,843,020
+     - 134,480,396
+     - 1,074,791,436
+     - 4,398,314,962,956 (really 2^32 due to field size limitations)
+   * - File Size, Extents
+     - 4TiB
+     - 8TiB
+     - 16TiB
+     - 256TiB
+   * - File Size, Block Maps
+     - 16GiB
+     - 256GiB
+     - 4TiB
+     - 256TiB
+
+For 64-bit filesystems, limits are as follows:
+
+.. list-table::
+   :widths: 1 1 1 1 1
+   :header-rows: 1
+
+   * - Item
+     - 1KiB
+     - 2KiB
+     - 4KiB
+     - 64KiB
+   * - Blocks
+     - 2^64
+     - 2^64
+     - 2^64
+     - 2^64
+   * - Inodes
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - File System Size
+     - 16ZiB
+     - 32ZiB
+     - 64ZiB
+     - 1YiB
+   * - Blocks Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Inodes Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Block Group Size
+     - 8MiB
+     - 32MiB
+     - 128MiB
+     - 32GiB
+   * - Blocks Per File, Extents
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - Blocks Per File, Block Maps
+     - 16,843,020
+     - 134,480,396
+     - 1,074,791,436
+     - 4,398,314,962,956 (really 2^32 due to field size limitations)
+   * - File Size, Extents
+     - 4TiB
+     - 8TiB
+     - 16TiB
+     - 256TiB
+   * - File Size, Block Maps
+     - 16GiB
+     - 256GiB
+     - 4TiB
+     - 256TiB
+
+Note: Files not using extents (i.e. files using block maps) must be
+placed within the first 2^32 blocks of a filesystem. Files with extents
+must be placed within the first 2^48 blocks of a filesystem. It's not
+clear what happens with larger filesystems.
diff --git a/Documentation/filesystems/ext4/ondisk/checksums.rst b/Documentation/filesystems/ext4/ondisk/checksums.rst
new file mode 100644
index 000000000000..9d6a793b2e03
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/checksums.rst
@@ -0,0 +1,73 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Checksums
+---------
+
+Starting in early 2012, metadata checksums were added to all major ext4
+and jbd2 data structures. The associated feature flag is metadata\_csum.
+The desired checksum algorithm is indicated in the superblock, though as
+of October 2012 the only supported algorithm is crc32c. Some data
+structures did not have space to fit a full 32-bit checksum, so only the
+lower 16 bits are stored. Enabling the 64bit feature increases the data
+structure size so that full 32-bit checksums can be stored for many data
+structures. However, existing 32-bit filesystems cannot be extended to
+enable 64bit mode, at least not without the experimental resize2fs
+patches to do so.
+
+Existing filesystems can have checksumming added by running
+``tune2fs -O metadata_csum`` against the underlying device. If tune2fs
+encounters directory blocks that lack sufficient empty space to add a
+checksum, it will request that you run ``e2fsck -D`` to have the
+directories rebuilt with checksums. This has the added benefit of
+removing slack space from the directory files and rebalancing the htree
+indexes. If you \_ignore\_ this step, your directories will not be
+protected by a checksum!
+
+The following table describes the data elements that go into each type
+of checksum. The checksum function is whatever the superblock describes
+(crc32c as of October 2013) unless noted otherwise.
+
+.. list-table::
+   :widths: 1 1 4
+   :header-rows: 1
+
+   * - Metadata
+     - Length
+     - Ingredients
+   * - Superblock
+     - \_\_le32
+     - The entire superblock up to the checksum field. The UUID lives inside
+       the superblock.
+   * - MMP
+     - \_\_le32
+     - UUID + the entire MMP block up to the checksum field.
+   * - Extended Attributes
+     - \_\_le32
+     - UUID + the entire extended attribute block. The checksum field is set to
+       zero.
+   * - Directory Entries
+     - \_\_le32
+     - UUID + inode number + inode generation + the directory block up to the
+       fake entry enclosing the checksum field.
+   * - HTREE Nodes
+     - \_\_le32
+     - UUID + inode number + inode generation + all valid extents + HTREE tail.
+       The checksum field is set to zero.
+   * - Extents
+     - \_\_le32
+     - UUID + inode number + inode generation + the entire extent block up to
+       the checksum field.
+   * - Bitmaps
+     - \_\_le32 or \_\_le16
+     - UUID + the entire bitmap. Checksums are stored in the group descriptor,
+       and truncated if the group descriptor size is 32 bytes (i.e. ^64bit)
+   * - Inodes
+     - \_\_le32
+     - UUID + inode number + inode generation + the entire inode. The checksum
+       field is set to zero. Each inode has its own checksum.
+   * - Group Descriptors
+     - \_\_le16
+     - If metadata\_csum, then UUID + group number + the entire descriptor;
+       else if gdt\_csum, then crc16(UUID + group number + the entire
+       descriptor). In all cases, only the lower 16 bits are stored.
+
diff --git a/Documentation/filesystems/ext4/ondisk/directory.rst b/Documentation/filesystems/ext4/ondisk/directory.rst
new file mode 100644
index 000000000000..8fcba68c2884
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/directory.rst
@@ -0,0 +1,426 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Directory Entries
+-----------------
+
+In an ext4 filesystem, a directory is more or less a flat file that maps
+an arbitrary byte string (usually ASCII) to an inode number on the
+filesystem. There can be many directory entries across the filesystem
+that reference the same inode number--these are known as hard links, and
+that is why hard links cannot reference files on other filesystems. As
+such, directory entries are found by reading the data block(s)
+associated with a directory file for the particular directory entry that
+is desired.
+
+Linear (Classic) Directories
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+By default, each directory lists its entries in an “almost-linear�
+array. I write “almost� because it's not a linear array in the memory
+sense because directory entries are not split across filesystem blocks.
+Therefore, it is more accurate to say that a directory is a series of
+data blocks and that each block contains a linear array of directory
+entries. The end of each per-block array is signified by reaching the
+end of the block; the last entry in the block has a record length that
+takes it all the way to the end of the block. The end of the entire
+directory is of course signified by reaching the end of the file. Unused
+directory entries are signified by inode = 0. By default the filesystem
+uses ``struct ext4_dir_entry_2`` for directory entries unless the
+“filetype� feature flag is not set, in which case it uses
+``struct ext4_dir_entry``.
+
+The original directory entry format is ``struct ext4_dir_entry``, which
+is at most 263 bytes long, though on disk you'll need to reference
+``dirent.rec_len`` to know for sure.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - inode
+     - Number of the inode that this directory entry points to.
+   * - 0x4
+     - \_\_le16
+     - rec\_len
+     - Length of this directory entry. Must be a multiple of 4.
+   * - 0x6
+     - \_\_le16
+     - name\_len
+     - Length of the file name.
+   * - 0x8
+     - char
+     - name[EXT4\_NAME\_LEN]
+     - File name.
+
+Since file names cannot be longer than 255 bytes, the new directory
+entry format shortens the rec\_len field and uses the space for a file
+type flag, probably to avoid having to load every inode during directory
+tree traversal. This format is ``ext4_dir_entry_2``, which is at most
+263 bytes long, though on disk you'll need to reference
+``dirent.rec_len`` to know for sure.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - inode
+     - Number of the inode that this directory entry points to.
+   * - 0x4
+     - \_\_le16
+     - rec\_len
+     - Length of this directory entry.
+   * - 0x6
+     - \_\_u8
+     - name\_len
+     - Length of the file name.
+   * - 0x7
+     - \_\_u8
+     - file\_type
+     - File type code, see ftype_ table below.
+   * - 0x8
+     - char
+     - name[EXT4\_NAME\_LEN]
+     - File name.
+
+.. _ftype:
+
+The directory file type is one of the following values:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0
+     - Unknown.
+   * - 0x1
+     - Regular file.
+   * - 0x2
+     - Directory.
+   * - 0x3
+     - Character device file.
+   * - 0x4
+     - Block device file.
+   * - 0x5
+     - FIFO.
+   * - 0x6
+     - Socket.
+   * - 0x7
+     - Symbolic link.
+
+In order to add checksums to these classic directory blocks, a phony
+``struct ext4_dir_entry`` is placed at the end of each leaf block to
+hold the checksum. The directory entry is 12 bytes long. The inode
+number and name\_len fields are set to zero to fool old software into
+ignoring an apparently empty directory entry, and the checksum is stored
+in the place where the name normally goes. The structure is
+``struct ext4_dir_entry_tail``:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - det\_reserved\_zero1
+     - Inode number, which must be zero.
+   * - 0x4
+     - \_\_le16
+     - det\_rec\_len
+     - Length of this directory entry, which must be 12.
+   * - 0x6
+     - \_\_u8
+     - det\_reserved\_zero2
+     - Length of the file name, which must be zero.
+   * - 0x7
+     - \_\_u8
+     - det\_reserved\_ft
+     - File type, which must be 0xDE.
+   * - 0x8
+     - \_\_le32
+     - det\_checksum
+     - Directory leaf block checksum.
+
+The leaf directory block checksum is calculated against the FS UUID, the
+directory's inode number, the directory's inode generation number, and
+the entire directory entry block up to (but not including) the fake
+directory entry.
+
+Hash Tree Directories
+~~~~~~~~~~~~~~~~~~~~~
+
+A linear array of directory entries isn't great for performance, so a
+new feature was added to ext3 to provide a faster (but peculiar)
+balanced tree keyed off a hash of the directory entry name. If the
+EXT4\_INDEX\_FL (0x1000) flag is set in the inode, this directory uses a
+hashed btree (htree) to organize and find directory entries. For
+backwards read-only compatibility with ext2, this tree is actually
+hidden inside the directory file, masquerading as “empty� directory data
+blocks! It was stated previously that the end of the linear directory
+entry table was signified with an entry pointing to inode 0; this is
+(ab)used to fool the old linear-scan algorithm into thinking that the
+rest of the directory block is empty so that it moves on.
+
+The root of the tree always lives in the first data block of the
+directory. By ext2 custom, the '.' and '..' entries must appear at the
+beginning of this first block, so they are put here as two
+``struct ext4_dir_entry_2``\ s and not stored in the tree. The rest of
+the root node contains metadata about the tree and finally a hash->block
+map to find nodes that are lower in the htree. If
+``dx_root.info.indirect_levels`` is non-zero then the htree has two
+levels; the data block pointed to by the root node's map is an interior
+node, which is indexed by a minor hash. Interior nodes in this tree
+contains a zeroed out ``struct ext4_dir_entry_2`` followed by a
+minor\_hash->block map to find leafe nodes. Leaf nodes contain a linear
+array of all ``struct ext4_dir_entry_2``; all of these entries
+(presumably) hash to the same value. If there is an overflow, the
+entries simply overflow into the next leaf node, and the
+least-significant bit of the hash (in the interior node map) that gets
+us to this next leaf node is set.
+
+To traverse the directory as a htree, the code calculates the hash of
+the desired file name and uses it to find the corresponding block
+number. If the tree is flat, the block is a linear array of directory
+entries that can be searched; otherwise, the minor hash of the file name
+is computed and used against this second block to find the corresponding
+third block number. That third block number will be a linear array of
+directory entries.
+
+To traverse the directory as a linear array (such as the old code does),
+the code simply reads every data block in the directory. The blocks used
+for the htree will appear to have no entries (aside from '.' and '..')
+and so only the leaf nodes will appear to have any interesting content.
+
+The root of the htree is in ``struct dx_root``, which is the full length
+of a data block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - dot.inode
+     - inode number of this directory.
+   * - 0x4
+     - \_\_le16
+     - dot.rec\_len
+     - Length of this record, 12.
+   * - 0x6
+     - u8
+     - dot.name\_len
+     - Length of the name, 1.
+   * - 0x7
+     - u8
+     - dot.file\_type
+     - File type of this entry, 0x2 (directory) (if the feature flag is set).
+   * - 0x8
+     - char
+     - dot.name[4]
+     - “.\\0\\0\\0�
+   * - 0xC
+     - \_\_le32
+     - dotdot.inode
+     - inode number of parent directory.
+   * - 0x10
+     - \_\_le16
+     - dotdot.rec\_len
+     - block\_size - 12. The record length is long enough to cover all htree
+       data.
+   * - 0x12
+     - u8
+     - dotdot.name\_len
+     - Length of the name, 2.
+   * - 0x13
+     - u8
+     - dotdot.file\_type
+     - File type of this entry, 0x2 (directory) (if the feature flag is set).
+   * - 0x14
+     - char
+     - dotdot\_name[4]
+     - “..\\0\\0�
+   * - 0x18
+     - \_\_le32
+     - struct dx\_root\_info.reserved\_zero
+     - Zero.
+   * - 0x1C
+     - u8
+     - struct dx\_root\_info.hash\_version
+     - Hash type, see dirhash_ table below.
+   * - 0x1D
+     - u8
+     - struct dx\_root\_info.info\_length
+     - Length of the tree information, 0x8.
+   * - 0x1E
+     - u8
+     - struct dx\_root\_info.indirect\_levels
+     - Depth of the htree. Cannot be larger than 3 if the INCOMPAT\_LARGEDIR
+       feature is set; cannot be larger than 2 otherwise.
+   * - 0x1F
+     - u8
+     - struct dx\_root\_info.unused\_flags
+     -
+   * - 0x20
+     - \_\_le16
+     - limit
+     - Maximum number of dx\_entries that can follow this header, plus 1 for
+       the header itself.
+   * - 0x22
+     - \_\_le16
+     - count
+     - Actual number of dx\_entries that follow this header, plus 1 for the
+       header itself.
+   * - 0x24
+     - \_\_le32
+     - block
+     - The block number (within the directory file) that goes with hash=0.
+   * - 0x28
+     - struct dx\_entry
+     - entries[0]
+     - As many 8-byte ``struct dx_entry`` as fits in the rest of the data block.
+
+.. _dirhash:
+
+The directory hash is one of the following values:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0
+     - Legacy.
+   * - 0x1
+     - Half MD4.
+   * - 0x2
+     - Tea.
+   * - 0x3
+     - Legacy, unsigned.
+   * - 0x4
+     - Half MD4, unsigned.
+   * - 0x5
+     - Tea, unsigned.
+
+Interior nodes of an htree are recorded as ``struct dx_node``, which is
+also the full length of a data block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - fake.inode
+     - Zero, to make it look like this entry is not in use.
+   * - 0x4
+     - \_\_le16
+     - fake.rec\_len
+     - The size of the block, in order to hide all of the dx\_node data.
+   * - 0x6
+     - u8
+     - name\_len
+     - Zero. There is no name for this “unused� directory entry.
+   * - 0x7
+     - u8
+     - file\_type
+     - Zero. There is no file type for this “unused� directory entry.
+   * - 0x8
+     - \_\_le16
+     - limit
+     - Maximum number of dx\_entries that can follow this header, plus 1 for
+       the header itself.
+   * - 0xA
+     - \_\_le16
+     - count
+     - Actual number of dx\_entries that follow this header, plus 1 for the
+       header itself.
+   * - 0xE
+     - \_\_le32
+     - block
+     - The block number (within the directory file) that goes with the lowest
+       hash value of this block. This value is stored in the parent block.
+   * - 0x12
+     - struct dx\_entry
+     - entries[0]
+     - As many 8-byte ``struct dx_entry`` as fits in the rest of the data block.
+
+The hash maps that exist in both ``struct dx_root`` and
+``struct dx_node`` are recorded as ``struct dx_entry``, which is 8 bytes
+long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - hash
+     - Hash code.
+   * - 0x4
+     - \_\_le32
+     - block
+     - Block number (within the directory file, not filesystem blocks) of the
+       next node in the htree.
+
+(If you think this is all quite clever and peculiar, so does the
+author.)
+
+If metadata checksums are enabled, the last 8 bytes of the directory
+block (precisely the length of one dx\_entry) are used to store a
+``struct dx_tail``, which contains the checksum. The ``limit`` and
+``count`` entries in the dx\_root/dx\_node structures are adjusted as
+necessary to fit the dx\_tail into the block. If there is no space for
+the dx\_tail, the user is notified to run e2fsck -D to rebuild the
+directory index (which will ensure that there's space for the checksum.
+The dx\_tail structure is 8 bytes long and looks like this:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - u32
+     - dt\_reserved
+     - Zero.
+   * - 0x4
+     - \_\_le32
+     - dt\_checksum
+     - Checksum of the htree directory block.
+
+The checksum is calculated against the FS UUID, the htree index header
+(dx\_root or dx\_node), all of the htree indices (dx\_entry) that are in
+use, and the tail block (dx\_tail).
diff --git a/Documentation/filesystems/ext4/ondisk/dynamic.rst b/Documentation/filesystems/ext4/ondisk/dynamic.rst
new file mode 100644
index 000000000000..bb0c84333341
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/dynamic.rst
@@ -0,0 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Dynamic Structures
+==================
+
+Dynamic metadata are created on the fly when files and blocks are
+allocated to files.
+
+.. include:: inodes.rst
+.. include:: ifork.rst
+.. include:: directory.rst
+.. include:: attributes.rst
diff --git a/Documentation/filesystems/ext4/ondisk/eainode.rst b/Documentation/filesystems/ext4/ondisk/eainode.rst
new file mode 100644
index 000000000000..ecc0d01a0a72
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/eainode.rst
@@ -0,0 +1,18 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Large Extended Attribute Values
+-------------------------------
+
+To enable ext4 to store extended attribute values that do not fit in the
+inode or in the single extended attribute block attached to an inode,
+the EA\_INODE feature allows us to store the value in the data blocks of
+a regular file inode. This “EA inode� is linked only from the extended
+attribute name index and must not appear in a directory entry. The
+inode's i\_atime field is used to store a checksum of the xattr value;
+and i\_ctime/i\_version store a 64-bit reference count, which enables
+sharing of large xattr values between multiple owning inodes. For
+backward compatibility with older versions of this feature, the
+i\_mtime/i\_generation *may* store a back-reference to the inode number
+and i\_generation of the **one** owning inode (in cases where the EA
+inode is not referenced by multiple inodes) to verify that the EA inode
+is the correct one being accessed.
diff --git a/Documentation/filesystems/ext4/ondisk/globals.rst b/Documentation/filesystems/ext4/ondisk/globals.rst
new file mode 100644
index 000000000000..368bf7662b96
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/globals.rst
@@ -0,0 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Global Structures
+=================
+
+The filesystem is sharded into a number of block groups, each of which
+have static metadata at fixed locations.
+
+.. include:: super.rst
+.. include:: group_descr.rst
+.. include:: bitmaps.rst
+.. include:: mmp.rst
+.. include:: journal.rst
diff --git a/Documentation/filesystems/ext4/ondisk/group_descr.rst b/Documentation/filesystems/ext4/ondisk/group_descr.rst
new file mode 100644
index 000000000000..759827e5d2cf
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/group_descr.rst
@@ -0,0 +1,170 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Block Group Descriptors
+-----------------------
+
+Each block group on the filesystem has one of these descriptors
+associated with it. As noted in the Layout section above, the group
+descriptors (if present) are the second item in the block group. The
+standard configuration is for each block group to contain a full copy of
+the block group descriptor table unless the sparse\_super feature flag
+is set.
+
+Notice how the group descriptor records the location of both bitmaps and
+the inode table (i.e. they can float). This means that within a block
+group, the only data structures with fixed locations are the superblock
+and the group descriptor table. The flex\_bg mechanism uses this
+property to group several block groups into a flex group and lay out all
+of the groups' bitmaps and inode tables into one long run in the first
+group of the flex group.
+
+If the meta\_bg feature flag is set, then several block groups are
+grouped together into a meta group. Note that in the meta\_bg case,
+however, the first and last two block groups within the larger meta
+group contain only group descriptors for the groups inside the meta
+group.
+
+flex\_bg and meta\_bg do not appear to be mutually exclusive features.
+
+In ext2, ext3, and ext4 (when the 64bit feature is not enabled), the
+block group descriptor was only 32 bytes long and therefore ends at
+bg\_checksum. On an ext4 filesystem with the 64bit feature enabled, the
+block group descriptor expands to at least the 64 bytes described below;
+the size is stored in the superblock.
+
+If gdt\_csum is set and metadata\_csum is not set, the block group
+checksum is the crc16 of the FS UUID, the group number, and the group
+descriptor structure. If metadata\_csum is set, then the block group
+checksum is the lower 16 bits of the checksum of the FS UUID, the group
+number, and the group descriptor structure. Both block and inode bitmap
+checksums are calculated against the FS UUID, the group number, and the
+entire bitmap.
+
+The block group descriptor is laid out in ``struct ext4_group_desc``.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - bg\_block\_bitmap\_lo
+     - Lower 32-bits of location of block bitmap.
+   * - 0x4
+     - \_\_le32
+     - bg\_inode\_bitmap\_lo
+     - Lower 32-bits of location of inode bitmap.
+   * - 0x8
+     - \_\_le32
+     - bg\_inode\_table\_lo
+     - Lower 32-bits of location of inode table.
+   * - 0xC
+     - \_\_le16
+     - bg\_free\_blocks\_count\_lo
+     - Lower 16-bits of free block count.
+   * - 0xE
+     - \_\_le16
+     - bg\_free\_inodes\_count\_lo
+     - Lower 16-bits of free inode count.
+   * - 0x10
+     - \_\_le16
+     - bg\_used\_dirs\_count\_lo
+     - Lower 16-bits of directory count.
+   * - 0x12
+     - \_\_le16
+     - bg\_flags
+     - Block group flags. See the bgflags_ table below.
+   * - 0x14
+     - \_\_le32
+     - bg\_exclude\_bitmap\_lo
+     - Lower 32-bits of location of snapshot exclusion bitmap.
+   * - 0x18
+     - \_\_le16
+     - bg\_block\_bitmap\_csum\_lo
+     - Lower 16-bits of the block bitmap checksum.
+   * - 0x1A
+     - \_\_le16
+     - bg\_inode\_bitmap\_csum\_lo
+     - Lower 16-bits of the inode bitmap checksum.
+   * - 0x1C
+     - \_\_le16
+     - bg\_itable\_unused\_lo
+     - Lower 16-bits of unused inode count. If set, we needn't scan past the
+       ``(sb.s_inodes_per_group - gdt.bg_itable_unused)``\ th entry in the
+       inode table for this group.
+   * - 0x1E
+     - \_\_le16
+     - bg\_checksum
+     - Group descriptor checksum; crc16(sb\_uuid+group+desc) if the
+       RO\_COMPAT\_GDT\_CSUM feature is set, or crc32c(sb\_uuid+group\_desc) &
+       0xFFFF if the RO\_COMPAT\_METADATA\_CSUM feature is set.
+   * -
+     -
+     -
+     - These fields only exist if the 64bit feature is enabled and s_desc_size
+       > 32.
+   * - 0x20
+     - \_\_le32
+     - bg\_block\_bitmap\_hi
+     - Upper 32-bits of location of block bitmap.
+   * - 0x24
+     - \_\_le32
+     - bg\_inode\_bitmap\_hi
+     - Upper 32-bits of location of inodes bitmap.
+   * - 0x28
+     - \_\_le32
+     - bg\_inode\_table\_hi
+     - Upper 32-bits of location of inodes table.
+   * - 0x2C
+     - \_\_le16
+     - bg\_free\_blocks\_count\_hi
+     - Upper 16-bits of free block count.
+   * - 0x2E
+     - \_\_le16
+     - bg\_free\_inodes\_count\_hi
+     - Upper 16-bits of free inode count.
+   * - 0x30
+     - \_\_le16
+     - bg\_used\_dirs\_count\_hi
+     - Upper 16-bits of directory count.
+   * - 0x32
+     - \_\_le16
+     - bg\_itable\_unused\_hi
+     - Upper 16-bits of unused inode count.
+   * - 0x34
+     - \_\_le32
+     - bg\_exclude\_bitmap\_hi
+     - Upper 32-bits of location of snapshot exclusion bitmap.
+   * - 0x38
+     - \_\_le16
+     - bg\_block\_bitmap\_csum\_hi
+     - Upper 16-bits of the block bitmap checksum.
+   * - 0x3A
+     - \_\_le16
+     - bg\_inode\_bitmap\_csum\_hi
+     - Upper 16-bits of the inode bitmap checksum.
+   * - 0x3C
+     - \_\_u32
+     - bg\_reserved
+     - Padding to 64 bytes.
+
+.. _bgflags:
+
+Block group flags can be any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - inode table and bitmap are not initialized (EXT4\_BG\_INODE\_UNINIT).
+   * - 0x2
+     - block bitmap is not initialized (EXT4\_BG\_BLOCK\_UNINIT).
+   * - 0x4
+     - inode table is zeroed (EXT4\_BG\_INODE\_ZEROED).
diff --git a/Documentation/filesystems/ext4/ondisk/ifork.rst b/Documentation/filesystems/ext4/ondisk/ifork.rst
new file mode 100644
index 000000000000..5dbe3b2b121a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/ifork.rst
@@ -0,0 +1,194 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+The Contents of inode.i\_block
+------------------------------
+
+Depending on the type of file an inode describes, the 60 bytes of
+storage in ``inode.i_block`` can be used in different ways. In general,
+regular files and directories will use it for file block indexing
+information, and special files will use it for special purposes.
+
+Symbolic Links
+~~~~~~~~~~~~~~
+
+The target of a symbolic link will be stored in this field if the target
+string is less than 60 bytes long. Otherwise, either extents or block
+maps will be used to allocate data blocks to store the link target.
+
+Direct/Indirect Block Addressing
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In ext2/3, file block numbers were mapped to logical block numbers by
+means of an (up to) three level 1-1 block map. To find the logical block
+that stores a particular file block, the code would navigate through
+this increasingly complicated structure. Notice that there is neither a
+magic number nor a checksum to provide any level of confidence that the
+block isn't full of garbage.
+
+.. ifconfig:: builder != 'latex'
+
+   .. include:: blockmap.rst
+
+.. ifconfig:: builder == 'latex'
+
+   [Table omitted because LaTeX doesn't support nested tables.]
+
+Note that with this block mapping scheme, it is necessary to fill out a
+lot of mapping data even for a large contiguous file! This inefficiency
+led to the creation of the extent mapping scheme, discussed below.
+
+Notice also that a file using this mapping scheme cannot be placed
+higher than 2^32 blocks.
+
+Extent Tree
+~~~~~~~~~~~
+
+In ext4, the file to logical block map has been replaced with an extent
+tree. Under the old scheme, allocating a contiguous run of 1,000 blocks
+requires an indirect block to map all 1,000 entries; with extents, the
+mapping is reduced to a single ``struct ext4_extent`` with
+``ee_len = 1000``. If flex\_bg is enabled, it is possible to allocate
+very large files with a single extent, at a considerable reduction in
+metadata block use, and some improvement in disk efficiency. The inode
+must have the extents flag (0x80000) flag set for this feature to be in
+use.
+
+Extents are arranged as a tree. Each node of the tree begins with a
+``struct ext4_extent_header``. If the node is an interior node
+(``eh.eh_depth`` > 0), the header is followed by ``eh.eh_entries``
+instances of ``struct ext4_extent_idx``; each of these index entries
+points to a block containing more nodes in the extent tree. If the node
+is a leaf node (``eh.eh_depth == 0``), then the header is followed by
+``eh.eh_entries`` instances of ``struct ext4_extent``; these instances
+point to the file's data blocks. The root node of the extent tree is
+stored in ``inode.i_block``, which allows for the first four extents to
+be recorded without the use of extra metadata blocks.
+
+The extent tree header is recorded in ``struct ext4_extent_header``,
+which is 12 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - eh\_magic
+     - Magic number, 0xF30A.
+   * - 0x2
+     - \_\_le16
+     - eh\_entries
+     - Number of valid entries following the header.
+   * - 0x4
+     - \_\_le16
+     - eh\_max
+     - Maximum number of entries that could follow the header.
+   * - 0x6
+     - \_\_le16
+     - eh\_depth
+     - Depth of this extent node in the extent tree. 0 = this extent node
+       points to data blocks; otherwise, this extent node points to other
+       extent nodes. The extent tree can be at most 5 levels deep: a logical
+       block number can be at most ``2^32``, and the smallest ``n`` that
+       satisfies ``4*(((blocksize - 12)/12)^n) >= 2^32`` is 5.
+   * - 0x8
+     - \_\_le32
+     - eh\_generation
+     - Generation of the tree. (Used by Lustre, but not standard ext4).
+
+Internal nodes of the extent tree, also known as index nodes, are
+recorded as ``struct ext4_extent_idx``, and are 12 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - ei\_block
+     - This index node covers file blocks from 'block' onward.
+   * - 0x4
+     - \_\_le32
+     - ei\_leaf\_lo
+     - Lower 32-bits of the block number of the extent node that is the next
+       level lower in the tree. The tree node pointed to can be either another
+       internal node or a leaf node, described below.
+   * - 0x8
+     - \_\_le16
+     - ei\_leaf\_hi
+     - Upper 16-bits of the previous field.
+   * - 0xA
+     - \_\_u16
+     - ei\_unused
+     -
+
+Leaf nodes of the extent tree are recorded as ``struct ext4_extent``,
+and are also 12 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - ee\_block
+     - First file block number that this extent covers.
+   * - 0x4
+     - \_\_le16
+     - ee\_len
+     - Number of blocks covered by extent. If the value of this field is <=
+       32768, the extent is initialized. If the value of the field is > 32768,
+       the extent is uninitialized and the actual extent length is ``ee_len`` -
+       32768. Therefore, the maximum length of a initialized extent is 32768
+       blocks, and the maximum length of an uninitialized extent is 32767.
+   * - 0x6
+     - \_\_le16
+     - ee\_start\_hi
+     - Upper 16-bits of the block number to which this extent points.
+   * - 0x8
+     - \_\_le32
+     - ee\_start\_lo
+     - Lower 32-bits of the block number to which this extent points.
+
+Prior to the introduction of metadata checksums, the extent header +
+extent entries always left at least 4 bytes of unallocated space at the
+end of each extent tree data block (because (2^x % 12) >= 4). Therefore,
+the 32-bit checksum is inserted into this space. The 4 extents in the
+inode do not need checksumming, since the inode is already checksummed.
+The checksum is calculated against the FS UUID, the inode number, the
+inode generation, and the entire extent block leading up to (but not
+including) the checksum itself.
+
+``struct ext4_extent_tail`` is 4 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - eb\_checksum
+     - Checksum of the extent block, crc32c(uuid+inum+igeneration+extentblock)
+
+Inline Data
+~~~~~~~~~~~
+
+If the inline data feature is enabled for the filesystem and the flag is
+set for the inode, it is possible that the first 60 bytes of the file
+data are stored here.
diff --git a/Documentation/filesystems/ext4/ondisk/index.rst b/Documentation/filesystems/ext4/ondisk/index.rst
new file mode 100644
index 000000000000..f7d082c3a435
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/index.rst
@@ -0,0 +1,9 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================
+Data Structures and Algorithms
+==============================
+.. include:: about.rst
+.. include:: overview.rst
+.. include:: globals.rst
+.. include:: dynamic.rst
diff --git a/Documentation/filesystems/ext4/ondisk/inlinedata.rst b/Documentation/filesystems/ext4/ondisk/inlinedata.rst
new file mode 100644
index 000000000000..d1075178ce0b
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/inlinedata.rst
@@ -0,0 +1,37 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Inline Data
+-----------
+
+The inline data feature was designed to handle the case that a file's
+data is so tiny that it readily fits inside the inode, which
+(theoretically) reduces disk block consumption and reduces seeks. If the
+file is smaller than 60 bytes, then the data are stored inline in
+``inode.i_block``. If the rest of the file would fit inside the extended
+attribute space, then it might be found as an extended attribute
+“system.data� within the inode body (“ibody EA�). This of course
+constrains the amount of extended attributes one can attach to an inode.
+If the data size increases beyond i\_block + ibody EA, a regular block
+is allocated and the contents moved to that block.
+
+Pending a change to compact the extended attribute key used to store
+inline data, one ought to be able to store 160 bytes of data in a
+256-byte inode (as of June 2015, when i\_extra\_isize is 28). Prior to
+that, the limit was 156 bytes due to inefficient use of inode space.
+
+The inline data feature requires the presence of an extended attribute
+for “system.data�, even if the attribute value is zero length.
+
+Inline Directories
+~~~~~~~~~~~~~~~~~~
+
+The first four bytes of i\_block are the inode number of the parent
+directory. Following that is a 56-byte space for an array of directory
+entries; see ``struct ext4_dir_entry``. If there is a “system.data�
+attribute in the inode body, the EA value is an array of
+``struct ext4_dir_entry`` as well. Note that for inline directories, the
+i\_block and EA space are treated as separate dirent blocks; directory
+entries cannot span the two.
+
+Inline directory entries are not checksummed, as the inode checksum
+should protect all inline data contents.
diff --git a/Documentation/filesystems/ext4/ondisk/inodes.rst b/Documentation/filesystems/ext4/ondisk/inodes.rst
new file mode 100644
index 000000000000..655ce898f3f5
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/inodes.rst
@@ -0,0 +1,575 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Index Nodes
+-----------
+
+In a regular UNIX filesystem, the inode stores all the metadata
+pertaining to the file (time stamps, block maps, extended attributes,
+etc), not the directory entry. To find the information associated with a
+file, one must traverse the directory files to find the directory entry
+associated with a file, then load the inode to find the metadata for
+that file. ext4 appears to cheat (for performance reasons) a little bit
+by storing a copy of the file type (normally stored in the inode) in the
+directory entry. (Compare all this to FAT, which stores all the file
+information directly in the directory entry, but does not support hard
+links and is in general more seek-happy than ext4 due to its simpler
+block allocator and extensive use of linked lists.)
+
+The inode table is a linear array of ``struct ext4_inode``. The table is
+sized to have enough blocks to store at least
+``sb.s_inode_size * sb.s_inodes_per_group`` bytes. The number of the
+block group containing an inode can be calculated as
+``(inode_number - 1) / sb.s_inodes_per_group``, and the offset into the
+group's table is ``(inode_number - 1) % sb.s_inodes_per_group``. There
+is no inode 0.
+
+The inode checksum is calculated against the FS UUID, the inode number,
+and the inode structure itself.
+
+The inode table entry is laid out in ``struct ext4_inode``.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - i\_mode
+     - File mode. See the table i_mode_ below.
+   * - 0x2
+     - \_\_le16
+     - i\_uid
+     - Lower 16-bits of Owner UID.
+   * - 0x4
+     - \_\_le32
+     - i\_size\_lo
+     - Lower 32-bits of size in bytes.
+   * - 0x8
+     - \_\_le32
+     - i\_atime
+     - Last access time, in seconds since the epoch. However, if the EA\_INODE
+       inode flag is set, this inode stores an extended attribute value and
+       this field contains the checksum of the value.
+   * - 0xC
+     - \_\_le32
+     - i\_ctime
+     - Last inode change time, in seconds since the epoch. However, if the
+       EA\_INODE inode flag is set, this inode stores an extended attribute
+       value and this field contains the lower 32 bits of the attribute value's
+       reference count.
+   * - 0x10
+     - \_\_le32
+     - i\_mtime
+     - Last data modification time, in seconds since the epoch. However, if the
+       EA\_INODE inode flag is set, this inode stores an extended attribute
+       value and this field contains the number of the inode that owns the
+       extended attribute.
+   * - 0x14
+     - \_\_le32
+     - i\_dtime
+     - Deletion Time, in seconds since the epoch.
+   * - 0x18
+     - \_\_le16
+     - i\_gid
+     - Lower 16-bits of GID.
+   * - 0x1A
+     - \_\_le16
+     - i\_links\_count
+     - Hard link count. Normally, ext4 does not permit an inode to have more
+       than 65,000 hard links. This applies to files as well as directories,
+       which means that there cannot be more than 64,998 subdirectories in a
+       directory (each subdirectory's '..' entry counts as a hard link, as does
+       the '.' entry in the directory itself). With the DIR\_NLINK feature
+       enabled, ext4 supports more than 64,998 subdirectories by setting this
+       field to 1 to indicate that the number of hard links is not known.
+   * - 0x1C
+     - \_\_le32
+     - i\_blocks\_lo
+     - Lower 32-bits of “block� count. If the huge\_file feature flag is not
+       set on the filesystem, the file consumes ``i_blocks_lo`` 512-byte blocks
+       on disk. If huge\_file is set and EXT4\_HUGE\_FILE\_FL is NOT set in
+       ``inode.i_flags``, then the file consumes ``i_blocks_lo + (i_blocks_hi
+       << 32)`` 512-byte blocks on disk. If huge\_file is set and
+       EXT4\_HUGE\_FILE\_FL IS set in ``inode.i_flags``, then this file
+       consumes (``i_blocks_lo + i_blocks_hi`` << 32) filesystem blocks on
+       disk.
+   * - 0x20
+     - \_\_le32
+     - i\_flags
+     - Inode flags. See the table i_flags_ below.
+   * - 0x24
+     - 4 bytes
+     - i\_osd1
+     - See the table i_osd1_ for more details.
+   * - 0x28
+     - 60 bytes
+     - i\_block[EXT4\_N\_BLOCKS=15]
+     - Block map or extent tree. See the section “The Contents of inode.i\_block�.
+   * - 0x64
+     - \_\_le32
+     - i\_generation
+     - File version (for NFS).
+   * - 0x68
+     - \_\_le32
+     - i\_file\_acl\_lo
+     - Lower 32-bits of extended attribute block. ACLs are of course one of
+       many possible extended attributes; I think the name of this field is a
+       result of the first use of extended attributes being for ACLs.
+   * - 0x6C
+     - \_\_le32
+     - i\_size\_high / i\_dir\_acl
+     - Upper 32-bits of file/directory size. In ext2/3 this field was named
+       i\_dir\_acl, though it was usually set to zero and never used.
+   * - 0x70
+     - \_\_le32
+     - i\_obso\_faddr
+     - (Obsolete) fragment address.
+   * - 0x74
+     - 12 bytes
+     - i\_osd2
+     - See the table i_osd2_ for more details.
+   * - 0x80
+     - \_\_le16
+     - i\_extra\_isize
+     - Size of this inode - 128. Alternately, the size of the extended inode
+       fields beyond the original ext2 inode, including this field.
+   * - 0x82
+     - \_\_le16
+     - i\_checksum\_hi
+     - Upper 16-bits of the inode checksum.
+   * - 0x84
+     - \_\_le32
+     - i\_ctime\_extra
+     - Extra change time bits. This provides sub-second precision. See Inode
+       Timestamps section.
+   * - 0x88
+     - \_\_le32
+     - i\_mtime\_extra
+     - Extra modification time bits. This provides sub-second precision.
+   * - 0x8C
+     - \_\_le32
+     - i\_atime\_extra
+     - Extra access time bits. This provides sub-second precision.
+   * - 0x90
+     - \_\_le32
+     - i\_crtime
+     - File creation time, in seconds since the epoch.
+   * - 0x94
+     - \_\_le32
+     - i\_crtime\_extra
+     - Extra file creation time bits. This provides sub-second precision.
+   * - 0x98
+     - \_\_le32
+     - i\_version\_hi
+     - Upper 32-bits for version number.
+   * - 0x9C
+     - \_\_le32
+     - i\_projid
+     - Project ID.
+
+.. _i_mode:
+
+The ``i_mode`` value is a combination of the following flags:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - S\_IXOTH (Others may execute)
+   * - 0x2
+     - S\_IWOTH (Others may write)
+   * - 0x4
+     - S\_IROTH (Others may read)
+   * - 0x8
+     - S\_IXGRP (Group members may execute)
+   * - 0x10
+     - S\_IWGRP (Group members may write)
+   * - 0x20
+     - S\_IRGRP (Group members may read)
+   * - 0x40
+     - S\_IXUSR (Owner may execute)
+   * - 0x80
+     - S\_IWUSR (Owner may write)
+   * - 0x100
+     - S\_IRUSR (Owner may read)
+   * - 0x200
+     - S\_ISVTX (Sticky bit)
+   * - 0x400
+     - S\_ISGID (Set GID)
+   * - 0x800
+     - S\_ISUID (Set UID)
+   * -
+     - These are mutually-exclusive file types:
+   * - 0x1000
+     - S\_IFIFO (FIFO)
+   * - 0x2000
+     - S\_IFCHR (Character device)
+   * - 0x4000
+     - S\_IFDIR (Directory)
+   * - 0x6000
+     - S\_IFBLK (Block device)
+   * - 0x8000
+     - S\_IFREG (Regular file)
+   * - 0xA000
+     - S\_IFLNK (Symbolic link)
+   * - 0xC000
+     - S\_IFSOCK (Socket)
+
+.. _i_flags:
+
+The ``i_flags`` field is a combination of these values:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - This file requires secure deletion (EXT4\_SECRM\_FL). (not implemented)
+   * - 0x2
+     - This file should be preserved, should undeletion be desired
+       (EXT4\_UNRM\_FL). (not implemented)
+   * - 0x4
+     - File is compressed (EXT4\_COMPR\_FL). (not really implemented)
+   * - 0x8
+     - All writes to the file must be synchronous (EXT4\_SYNC\_FL).
+   * - 0x10
+     - File is immutable (EXT4\_IMMUTABLE\_FL).
+   * - 0x20
+     - File can only be appended (EXT4\_APPEND\_FL).
+   * - 0x40
+     - The dump(1) utility should not dump this file (EXT4\_NODUMP\_FL).
+   * - 0x80
+     - Do not update access time (EXT4\_NOATIME\_FL).
+   * - 0x100
+     - Dirty compressed file (EXT4\_DIRTY\_FL). (not used)
+   * - 0x200
+     - File has one or more compressed clusters (EXT4\_COMPRBLK\_FL). (not used)
+   * - 0x400
+     - Do not compress file (EXT4\_NOCOMPR\_FL). (not used)
+   * - 0x800
+     - Encrypted inode (EXT4\_ENCRYPT\_FL). This bit value previously was
+       EXT4\_ECOMPR\_FL (compression error), which was never used.
+   * - 0x1000
+     - Directory has hashed indexes (EXT4\_INDEX\_FL).
+   * - 0x2000
+     - AFS magic directory (EXT4\_IMAGIC\_FL).
+   * - 0x4000
+     - File data must always be written through the journal
+       (EXT4\_JOURNAL\_DATA\_FL).
+   * - 0x8000
+     - File tail should not be merged (EXT4\_NOTAIL\_FL). (not used by ext4)
+   * - 0x10000
+     - All directory entry data should be written synchronously (see
+       ``dirsync``) (EXT4\_DIRSYNC\_FL).
+   * - 0x20000
+     - Top of directory hierarchy (EXT4\_TOPDIR\_FL).
+   * - 0x40000
+     - This is a huge file (EXT4\_HUGE\_FILE\_FL).
+   * - 0x80000
+     - Inode uses extents (EXT4\_EXTENTS\_FL).
+   * - 0x200000
+     - Inode stores a large extended attribute value in its data blocks
+       (EXT4\_EA\_INODE\_FL).
+   * - 0x400000
+     - This file has blocks allocated past EOF (EXT4\_EOFBLOCKS\_FL).
+       (deprecated)
+   * - 0x01000000
+     - Inode is a snapshot (``EXT4_SNAPFILE_FL``). (not in mainline)
+   * - 0x04000000
+     - Snapshot is being deleted (``EXT4_SNAPFILE_DELETED_FL``). (not in
+       mainline)
+   * - 0x08000000
+     - Snapshot shrink has completed (``EXT4_SNAPFILE_SHRUNK_FL``). (not in
+       mainline)
+   * - 0x10000000
+     - Inode has inline data (EXT4\_INLINE\_DATA\_FL).
+   * - 0x20000000
+     - Create children with the same project ID (EXT4\_PROJINHERIT\_FL).
+   * - 0x80000000
+     - Reserved for ext4 library (EXT4\_RESERVED\_FL).
+   * -
+     - Aggregate flags:
+   * - 0x4BDFFF
+     - User-visible flags.
+   * - 0x4B80FF
+     - User-modifiable flags. Note that while EXT4\_JOURNAL\_DATA\_FL and
+       EXT4\_EXTENTS\_FL can be set with setattr, they are not in the kernel's
+       EXT4\_FL\_USER\_MODIFIABLE mask, since it needs to handle the setting of
+       these flags in a special manner and they are masked out of the set of
+       flags that are saved directly to i\_flags.
+
+.. _i_osd1:
+
+The ``osd1`` field has multiple meanings depending on the creator:
+
+Linux:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - l\_i\_version
+     - Inode version. However, if the EA\_INODE inode flag is set, this inode
+       stores an extended attribute value and this field contains the upper 32
+       bits of the attribute value's reference count.
+
+Hurd:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - h\_i\_translator
+     - ??
+
+Masix:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - m\_i\_reserved
+     - ??
+
+.. _i_osd2:
+
+The ``osd2`` field has multiple meanings depending on the filesystem creator:
+
+Linux:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - l\_i\_blocks\_high
+     - Upper 16-bits of the block count. Please see the note attached to
+       i\_blocks\_lo.
+   * - 0x2
+     - \_\_le16
+     - l\_i\_file\_acl\_high
+     - Upper 16-bits of the extended attribute block (historically, the file
+       ACL location). See the Extended Attributes section below.
+   * - 0x4
+     - \_\_le16
+     - l\_i\_uid\_high
+     - Upper 16-bits of the Owner UID.
+   * - 0x6
+     - \_\_le16
+     - l\_i\_gid\_high
+     - Upper 16-bits of the GID.
+   * - 0x8
+     - \_\_le16
+     - l\_i\_checksum\_lo
+     - Lower 16-bits of the inode checksum.
+   * - 0xA
+     - \_\_le16
+     - l\_i\_reserved
+     - Unused.
+
+Hurd:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - h\_i\_reserved1
+     - ??
+   * - 0x2
+     - \_\_u16
+     - h\_i\_mode\_high
+     - Upper 16-bits of the file mode.
+   * - 0x4
+     - \_\_le16
+     - h\_i\_uid\_high
+     - Upper 16-bits of the Owner UID.
+   * - 0x6
+     - \_\_le16
+     - h\_i\_gid\_high
+     - Upper 16-bits of the GID.
+   * - 0x8
+     - \_\_u32
+     - h\_i\_author
+     - Author code?
+
+Masix:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - h\_i\_reserved1
+     - ??
+   * - 0x2
+     - \_\_u16
+     - m\_i\_file\_acl\_high
+     - Upper 16-bits of the extended attribute block (historically, the file
+       ACL location).
+   * - 0x4
+     - \_\_u32
+     - m\_i\_reserved2[2]
+     - ??
+
+Inode Size
+~~~~~~~~~~
+
+In ext2 and ext3, the inode structure size was fixed at 128 bytes
+(``EXT2_GOOD_OLD_INODE_SIZE``) and each inode had a disk record size of
+128 bytes. Starting with ext4, it is possible to allocate a larger
+on-disk inode at format time for all inodes in the filesystem to provide
+space beyond the end of the original ext2 inode. The on-disk inode
+record size is recorded in the superblock as ``s_inode_size``. The
+number of bytes actually used by struct ext4\_inode beyond the original
+128-byte ext2 inode is recorded in the ``i_extra_isize`` field for each
+inode, which allows struct ext4\_inode to grow for a new kernel without
+having to upgrade all of the on-disk inodes. Access to fields beyond
+EXT2\_GOOD\_OLD\_INODE\_SIZE should be verified to be within
+``i_extra_isize``. By default, ext4 inode records are 256 bytes, and (as
+of October 2013) the inode structure is 156 bytes
+(``i_extra_isize = 28``). The extra space between the end of the inode
+structure and the end of the inode record can be used to store extended
+attributes. Each inode record can be as large as the filesystem block
+size, though this is not terribly efficient.
+
+Finding an Inode
+~~~~~~~~~~~~~~~~
+
+Each block group contains ``sb->s_inodes_per_group`` inodes. Because
+inode 0 is defined not to exist, this formula can be used to find the
+block group that an inode lives in:
+``bg = (inode_num - 1) / sb->s_inodes_per_group``. The particular inode
+can be found within the block group's inode table at
+``index = (inode_num - 1) % sb->s_inodes_per_group``. To get the byte
+address within the inode table, use
+``offset = index * sb->s_inode_size``.
+
+Inode Timestamps
+~~~~~~~~~~~~~~~~
+
+Four timestamps are recorded in the lower 128 bytes of the inode
+structure -- inode change time (ctime), access time (atime), data
+modification time (mtime), and deletion time (dtime). The four fields
+are 32-bit signed integers that represent seconds since the Unix epoch
+(1970-01-01 00:00:00 GMT), which means that the fields will overflow in
+January 2038. For inodes that are not linked from any directory but are
+still open (orphan inodes), the dtime field is overloaded for use with
+the orphan list. The superblock field ``s_last_orphan`` points to the
+first inode in the orphan list; dtime is then the number of the next
+orphaned inode, or zero if there are no more orphans.
+
+If the inode structure size ``sb->s_inode_size`` is larger than 128
+bytes and the ``i_inode_extra`` field is large enough to encompass the
+respective ``i_[cma]time_extra`` field, the ctime, atime, and mtime
+inode fields are widened to 64 bits. Within this “extra� 32-bit field,
+the lower two bits are used to extend the 32-bit seconds field to be 34
+bit wide; the upper 30 bits are used to provide nanosecond timestamp
+accuracy. Therefore, timestamps should not overflow until May 2446.
+dtime was not widened. There is also a fifth timestamp to record inode
+creation time (crtime); this field is 64-bits wide and decoded in the
+same manner as 64-bit [cma]time. Neither crtime nor dtime are accessible
+through the regular stat() interface, though debugfs will report them.
+
+We use the 32-bit signed time value plus (2^32 \* (extra epoch bits)).
+In other words:
+
+.. list-table::
+   :widths: 20 20 20 20 20
+   :header-rows: 1
+
+   * - Extra epoch bits
+     - MSB of 32-bit time
+     - Adjustment for signed 32-bit to 64-bit tv\_sec
+     - Decoded 64-bit tv\_sec
+     - valid time range
+   * - 0 0
+     - 1
+     - 0
+     - ``-0x80000000 - -0x00000001``
+     - 1901-12-13 to 1969-12-31
+   * - 0 0
+     - 0
+     - 0
+     - ``0x000000000 - 0x07fffffff``
+     - 1970-01-01 to 2038-01-19
+   * - 0 1
+     - 1
+     - 0x100000000
+     - ``0x080000000 - 0x0ffffffff``
+     - 2038-01-19 to 2106-02-07
+   * - 0 1
+     - 0
+     - 0x100000000
+     - ``0x100000000 - 0x17fffffff``
+     - 2106-02-07 to 2174-02-25
+   * - 1 0
+     - 1
+     - 0x200000000
+     - ``0x180000000 - 0x1ffffffff``
+     - 2174-02-25 to 2242-03-16
+   * - 1 0
+     - 0
+     - 0x200000000
+     - ``0x200000000 - 0x27fffffff``
+     - 2242-03-16 to 2310-04-04
+   * - 1 1
+     - 1
+     - 0x300000000
+     - ``0x280000000 - 0x2ffffffff``
+     - 2310-04-04 to 2378-04-22
+   * - 1 1
+     - 0
+     - 0x300000000
+     - ``0x300000000 - 0x37fffffff``
+     - 2378-04-22 to 2446-05-10
+
+This is a somewhat odd encoding since there are effectively seven times
+as many positive values as negative values. There have also been
+long-standing bugs decoding and encoding dates beyond 2038, which don't
+seem to be fixed as of kernel 3.12 and e2fsprogs 1.42.8. 64-bit kernels
+incorrectly use the extra epoch bits 1,1 for dates between 1901 and
+1970. At some point the kernel will be fixed and e2fsck will fix this
+situation, assuming that it is run before 2310.
diff --git a/Documentation/filesystems/ext4/ondisk/journal.rst b/Documentation/filesystems/ext4/ondisk/journal.rst
new file mode 100644
index 000000000000..e7031af86876
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/journal.rst
@@ -0,0 +1,611 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Journal (jbd2)
+--------------
+
+Introduced in ext3, the ext4 filesystem employs a journal to protect the
+filesystem against corruption in the case of a system crash. A small
+continuous region of disk (default 128MiB) is reserved inside the
+filesystem as a place to land “important� data writes on-disk as quickly
+as possible. Once the important data transaction is fully written to the
+disk and flushed from the disk write cache, a record of the data being
+committed is also written to the journal. At some later point in time,
+the journal code writes the transactions to their final locations on
+disk (this could involve a lot of seeking or a lot of small
+read-write-erases) before erasing the commit record. Should the system
+crash during the second slow write, the journal can be replayed all the
+way to the latest commit record, guaranteeing the atomicity of whatever
+gets written through the journal to the disk. The effect of this is to
+guarantee that the filesystem does not become stuck midway through a
+metadata update.
+
+For performance reasons, ext4 by default only writes filesystem metadata
+through the journal. This means that file data blocks are /not/
+guaranteed to be in any consistent state after a crash. If this default
+guarantee level (``data=ordered``) is not satisfactory, there is a mount
+option to control journal behavior. If ``data=journal``, all data and
+metadata are written to disk through the journal. This is slower but
+safest. If ``data=writeback``, dirty data blocks are not flushed to the
+disk before the metadata are written to disk through the journal.
+
+The journal inode is typically inode 8. The first 68 bytes of the
+journal inode are replicated in the ext4 superblock. The journal itself
+is normal (but hidden) file within the filesystem. The file usually
+consumes an entire block group, though mke2fs tries to put it in the
+middle of the disk.
+
+All fields in jbd2 are written to disk in big-endian order. This is the
+opposite of ext4.
+
+NOTE: Both ext4 and ocfs2 use jbd2.
+
+The maximum size of a journal embedded in an ext4 filesystem is 2^32
+blocks. jbd2 itself does not seem to care.
+
+Layout
+~~~~~~
+
+Generally speaking, the journal has this format:
+
+.. list-table::
+   :widths: 1 1 78
+   :header-rows: 1
+
+   * - Superblock
+     - descriptor\_block (data\_blocks or revocation\_block) [more data or
+       revocations] commmit\_block
+     - [more transactions...]
+   * - 
+     - One transaction
+     -
+
+Notice that a transaction begins with either a descriptor and some data,
+or a block revocation list. A finished transaction always ends with a
+commit. If there is no commit record (or the checksums don't match), the
+transaction will be discarded during replay.
+
+External Journal
+~~~~~~~~~~~~~~~~
+
+Optionally, an ext4 filesystem can be created with an external journal
+device (as opposed to an internal journal, which uses a reserved inode).
+In this case, on the filesystem device, ``s_journal_inum`` should be
+zero and ``s_journal_uuid`` should be set. On the journal device there
+will be an ext4 super block in the usual place, with a matching UUID.
+The journal superblock will be in the next full block after the
+superblock.
+
+.. list-table::
+   :widths: 1 1 1 1 76
+   :header-rows: 1
+
+   * - 1024 bytes of padding
+     - ext4 Superblock
+     - Journal Superblock
+     - descriptor\_block (data\_blocks or revocation\_block) [more data or
+       revocations] commmit\_block
+     - [more transactions...]
+   * - 
+     -
+     -
+     - One transaction
+     -
+
+Block Header
+~~~~~~~~~~~~
+
+Every block in the journal starts with a common 12-byte header
+``struct journal_header_s``:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_be32
+     - h\_magic
+     - jbd2 magic number, 0xC03B3998.
+   * - 0x4
+     - \_\_be32
+     - h\_blocktype
+     - Description of what this block contains. See the jbd2_blocktype_ table
+       below.
+   * - 0x8
+     - \_\_be32
+     - h\_sequence
+     - The transaction ID that goes with this block.
+
+.. _jbd2_blocktype:
+
+The journal block type can be any one of:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 1
+     - Descriptor. This block precedes a series of data blocks that were
+       written through the journal during a transaction.
+   * - 2
+     - Block commit record. This block signifies the completion of a
+       transaction.
+   * - 3
+     - Journal superblock, v1.
+   * - 4
+     - Journal superblock, v2.
+   * - 5
+     - Block revocation records. This speeds up recovery by enabling the
+       journal to skip writing blocks that were subsequently rewritten.
+
+Super Block
+~~~~~~~~~~~
+
+The super block for the journal is much simpler as compared to ext4's.
+The key data kept within are size of the journal, and where to find the
+start of the log of transactions.
+
+The journal superblock is recorded as ``struct journal_superblock_s``,
+which is 1024 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * -
+     -
+     -
+     - Static information describing the journal.
+   * - 0x0
+     - journal\_header\_t (12 bytes)
+     - s\_header
+     - Common header identifying this as a superblock.
+   * - 0xC
+     - \_\_be32
+     - s\_blocksize
+     - Journal device block size.
+   * - 0x10
+     - \_\_be32
+     - s\_maxlen
+     - Total number of blocks in this journal.
+   * - 0x14
+     - \_\_be32
+     - s\_first
+     - First block of log information.
+   * -
+     -
+     -
+     - Dynamic information describing the current state of the log.
+   * - 0x18
+     - \_\_be32
+     - s\_sequence
+     - First commit ID expected in log.
+   * - 0x1C
+     - \_\_be32
+     - s\_start
+     - Block number of the start of log. Contrary to the comments, this field
+       being zero does not imply that the journal is clean!
+   * - 0x20
+     - \_\_be32
+     - s\_errno
+     - Error value, as set by jbd2\_journal\_abort().
+   * -
+     -
+     -
+     - The remaining fields are only valid in a v2 superblock.
+   * - 0x24
+     - \_\_be32
+     - s\_feature\_compat;
+     - Compatible feature set. See the table jbd2_compat_ below.
+   * - 0x28
+     - \_\_be32
+     - s\_feature\_incompat
+     - Incompatible feature set. See the table jbd2_incompat_ below.
+   * - 0x2C
+     - \_\_be32
+     - s\_feature\_ro\_compat
+     - Read-only compatible feature set. There aren't any of these currently.
+   * - 0x30
+     - \_\_u8
+     - s\_uuid[16]
+     - 128-bit uuid for journal. This is compared against the copy in the ext4
+       super block at mount time.
+   * - 0x40
+     - \_\_be32
+     - s\_nr\_users
+     - Number of file systems sharing this journal.
+   * - 0x44
+     - \_\_be32
+     - s\_dynsuper
+     - Location of dynamic super block copy. (Not used?)
+   * - 0x48
+     - \_\_be32
+     - s\_max\_transaction
+     - Limit of journal blocks per transaction. (Not used?)
+   * - 0x4C
+     - \_\_be32
+     - s\_max\_trans\_data
+     - Limit of data blocks per transaction. (Not used?)
+   * - 0x50
+     - \_\_u8
+     - s\_checksum\_type
+     - Checksum algorithm used for the journal.  See jbd2_checksum_type_ for
+       more info.
+   * - 0x51
+     - \_\_u8[3]
+     - s\_padding2
+     -
+   * - 0x54
+     - \_\_u32
+     - s\_padding[42]
+     -
+   * - 0xFC
+     - \_\_be32
+     - s\_checksum
+     - Checksum of the entire superblock, with this field set to zero.
+   * - 0x100
+     - \_\_u8
+     - s\_users[16\*48]
+     - ids of all file systems sharing the log. e2fsprogs/Linux don't allow
+       shared external journals, but I imagine Lustre (or ocfs2?), which use
+       the jbd2 code, might.
+
+.. _jbd2_compat:
+
+The journal compat features are any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Journal maintains checksums on the data blocks.
+       (JBD2\_FEATURE\_COMPAT\_CHECKSUM)
+
+.. _jbd2_incompat:
+
+The journal incompat features are any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Journal has block revocation records. (JBD2\_FEATURE\_INCOMPAT\_REVOKE)
+   * - 0x2
+     - Journal can deal with 64-bit block numbers.
+       (JBD2\_FEATURE\_INCOMPAT\_64BIT)
+   * - 0x4
+     - Journal commits asynchronously. (JBD2\_FEATURE\_INCOMPAT\_ASYNC\_COMMIT)
+   * - 0x8
+     - This journal uses v2 of the checksum on-disk format. Each journal
+       metadata block gets its own checksum, and the block tags in the
+       descriptor table contain checksums for each of the data blocks in the
+       journal. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2)
+   * - 0x10
+     - This journal uses v3 of the checksum on-disk format. This is the same as
+       v2, but the journal block tag size is fixed regardless of the size of
+       block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3)
+
+.. _jbd2_checksum_type:
+
+Journal checksum type codes are one of the following.  crc32 or crc32c are the
+most likely choices.
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 1
+     - CRC32
+   * - 2
+     - MD5
+   * - 3
+     - SHA1
+   * - 4
+     - CRC32C
+
+Descriptor Block
+~~~~~~~~~~~~~~~~
+
+The descriptor block contains an array of journal block tags that
+describe the final locations of the data blocks that follow in the
+journal. Descriptor blocks are open-coded instead of being completely
+described by a data structure, but here is the block structure anyway.
+Descriptor blocks consume at least 36 bytes, but use a full block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - journal\_header\_t
+     - (open coded)
+     - Common block header.
+   * - 0xC
+     - struct journal\_block\_tag\_s
+     - open coded array[]
+     - Enough tags either to fill up the block or to describe all the data
+       blocks that follow this descriptor block.
+
+Journal block tags have any of the following formats, depending on which
+journal feature and block tag flags are set.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is set, the journal block tag is
+defined as ``struct journal_block_tag3_s``, which looks like the
+following. The size is 16 or 32 bytes.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - \_\_be32
+     - t\_blocknr
+     - Lower 32-bits of the location of where the corresponding data block
+       should end up on disk.
+   * - 0x4
+     - \_\_be32
+     - t\_flags
+     - Flags that go with the descriptor. See the table jbd2_tag_flags_ for
+       more info.
+   * - 0x8
+     - \_\_be32
+     - t\_blocknr\_high
+     - Upper 32-bits of the location of where the corresponding data block
+       should end up on disk. This is zero if JBD2\_FEATURE\_INCOMPAT\_64BIT is
+       not enabled.
+   * - 0xC
+     - \_\_be32
+     - t\_checksum
+     - Checksum of the journal UUID, the sequence number, and the data block.
+   * -
+     -
+     -
+     - This field appears to be open coded. It always comes at the end of the
+       tag, after t_checksum. This field is not present if the "same UUID" flag
+       is set.
+   * - 0x8 or 0xC
+     - char
+     - uuid[16]
+     - A UUID to go with this tag. This field appears to be copied from the
+       ``j_uuid`` field in ``struct journal_s``, but only tune2fs touches that
+       field.
+
+.. _jbd2_tag_flags:
+
+The journal tag flags are any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - On-disk block is escaped. The first four bytes of the data block just
+       happened to match the jbd2 magic number.
+   * - 0x2
+     - This block has the same UUID as previous, therefore the UUID field is
+       omitted.
+   * - 0x4
+     - The data block was deleted by the transaction. (Not used?)
+   * - 0x8
+     - This is the last tag in this descriptor block.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is NOT set, the journal block tag
+is defined as ``struct journal_block_tag_s``, which looks like the
+following. The size is 8, 12, 24, or 28 bytes:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - \_\_be32
+     - t\_blocknr
+     - Lower 32-bits of the location of where the corresponding data block
+       should end up on disk.
+   * - 0x4
+     - \_\_be16
+     - t\_checksum
+     - Checksum of the journal UUID, the sequence number, and the data block.
+       Note that only the lower 16 bits are stored.
+   * - 0x6
+     - \_\_be16
+     - t\_flags
+     - Flags that go with the descriptor. See the table jbd2_tag_flags_ for
+       more info.
+   * -
+     -
+     -
+     - This next field is only present if the super block indicates support for
+       64-bit block numbers.
+   * - 0x8
+     - \_\_be32
+     - t\_blocknr\_high
+     - Upper 32-bits of the location of where the corresponding data block
+       should end up on disk.
+   * -
+     -
+     -
+     - This field appears to be open coded. It always comes at the end of the
+       tag, after t_flags or t_blocknr_high. This field is not present if the
+       "same UUID" flag is set.
+   * - 0x8 or 0xC
+     - char
+     - uuid[16]
+     - A UUID to go with this tag. This field appears to be copied from the
+       ``j_uuid`` field in ``struct journal_s``, but only tune2fs touches that
+       field.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or
+JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the block is a
+``struct jbd2_journal_block_tail``, which looks like this:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - \_\_be32
+     - t\_checksum
+     - Checksum of the journal UUID + the descriptor block, with this field set
+       to zero.
+
+Data Block
+~~~~~~~~~~
+
+In general, the data blocks being written to disk through the journal
+are written verbatim into the journal file after the descriptor block.
+However, if the first four bytes of the block match the jbd2 magic
+number then those four bytes are replaced with zeroes and the “escaped�
+flag is set in the descriptor block tag.
+
+Revocation Block
+~~~~~~~~~~~~~~~~
+
+A revocation block is used to prevent replay of a block in an earlier
+transaction. This is used to mark blocks that were journalled at one
+time but are no longer journalled. Typically this happens if a metadata
+block is freed and re-allocated as a file data block; in this case, a
+journal replay after the file block was written to disk will cause
+corruption.
+
+**NOTE**: This mechanism is NOT used to express “this journal block is
+superseded by this other journal block�, as the author (djwong)
+mistakenly thought. Any block being added to a transaction will cause
+the removal of all existing revocation records for that block.
+
+Revocation blocks are described in
+``struct jbd2_journal_revoke_header_s``, are at least 16 bytes in
+length, but use a full block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - journal\_header\_t
+     - r\_header
+     - Common block header.
+   * - 0xC
+     - \_\_be32
+     - r\_count
+     - Number of bytes used in this block.
+   * - 0x10
+     - \_\_be32 or \_\_be64
+     - blocks[0]
+     - Blocks to revoke.
+
+After r\_count is a linear array of block numbers that are effectively
+revoked by this transaction. The size of each block number is 8 bytes if
+the superblock advertises 64-bit block number support, or 4 bytes
+otherwise.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or
+JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the revocation
+block is a ``struct jbd2_journal_revoke_tail``, which has this format:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_be32
+     - r\_checksum
+     - Checksum of the journal UUID + revocation block
+
+Commit Block
+~~~~~~~~~~~~
+
+The commit block is a sentry that indicates that a transaction has been
+completely written to the journal. Once this commit block reaches the
+journal, the data stored with this transaction can be written to their
+final locations on disk.
+
+The commit block is described by ``struct commit_header``, which is 32
+bytes long (but uses a full block):
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - journal\_header\_s
+     - (open coded)
+     - Common block header.
+   * - 0xC
+     - unsigned char
+     - h\_chksum\_type
+     - The type of checksum to use to verify the integrity of the data blocks
+       in the transaction. See jbd2_checksum_type_ for more info.
+   * - 0xD
+     - unsigned char
+     - h\_chksum\_size
+     - The number of bytes used by the checksum. Most likely 4.
+   * - 0xE
+     - unsigned char
+     - h\_padding[2]
+     -
+   * - 0x10
+     - \_\_be32
+     - h\_chksum[JBD2\_CHECKSUM\_BYTES]
+     - 32 bytes of space to store checksums. If
+       JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3
+       are set, the first ``__be32`` is the checksum of the journal UUID and
+       the entire commit block, with this field zeroed. If
+       JBD2\_FEATURE\_COMPAT\_CHECKSUM is set, the first ``__be32`` is the
+       crc32 of all the blocks already written to the transaction.
+   * - 0x30
+     - \_\_be64
+     - h\_commit\_sec
+     - The time that the transaction was committed, in seconds since the epoch.
+   * - 0x38
+     - \_\_be32
+     - h\_commit\_nsec
+     - Nanoseconds component of the above timestamp.
+
diff --git a/Documentation/filesystems/ext4/ondisk/mmp.rst b/Documentation/filesystems/ext4/ondisk/mmp.rst
new file mode 100644
index 000000000000..b7d7a3137f80
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/mmp.rst
@@ -0,0 +1,77 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Multiple Mount Protection
+-------------------------
+
+Multiple mount protection (MMP) is a feature that protects the
+filesystem against multiple hosts trying to use the filesystem
+simultaneously. When a filesystem is opened (for mounting, or fsck,
+etc.), the MMP code running on the node (call it node A) checks a
+sequence number. If the sequence number is EXT4\_MMP\_SEQ\_CLEAN, the
+open continues. If the sequence number is EXT4\_MMP\_SEQ\_FSCK, then
+fsck is (hopefully) running, and open fails immediately. Otherwise, the
+open code will wait for twice the specified MMP check interval and check
+the sequence number again. If the sequence number has changed, then the
+filesystem is active on another machine and the open fails. If the MMP
+code passes all of those checks, a new MMP sequence number is generated
+and written to the MMP block, and the mount proceeds.
+
+While the filesystem is live, the kernel sets up a timer to re-check the
+MMP block at the specified MMP check interval. To perform the re-check,
+the MMP sequence number is re-read; if it does not match the in-memory
+MMP sequence number, then another node (node B) has mounted the
+filesystem, and node A remounts the filesystem read-only. If the
+sequence numbers match, the sequence number is incremented both in
+memory and on disk, and the re-check is complete.
+
+The hostname and device filename are written into the MMP block whenever
+an open operation succeeds. The MMP code does not use these values; they
+are provided purely for informational purposes.
+
+The checksum is calculated against the FS UUID and the MMP structure.
+The MMP structure (``struct mmp_struct``) is as follows:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - mmp\_magic
+     - Magic number for MMP, 0x004D4D50 (“MMP�).
+   * - 0x4
+     - \_\_le32
+     - mmp\_seq
+     - Sequence number, updated periodically.
+   * - 0x8
+     - \_\_le64
+     - mmp\_time
+     - Time that the MMP block was last updated.
+   * - 0x10
+     - char[64]
+     - mmp\_nodename
+     - Hostname of the node that opened the filesystem.
+   * - 0x50
+     - char[32]
+     - mmp\_bdevname
+     - Block device name of the filesystem.
+   * - 0x70
+     - \_\_le16
+     - mmp\_check\_interval
+     - The MMP re-check interval, in seconds.
+   * - 0x72
+     - \_\_le16
+     - mmp\_pad1
+     - Zero.
+   * - 0x74
+     - \_\_le32[226]
+     - mmp\_pad2
+     - Zero.
+   * - 0x3FC
+     - \_\_le32
+     - mmp\_checksum
+     - Checksum of the MMP block.
diff --git a/Documentation/filesystems/ext4/ondisk/overview.rst b/Documentation/filesystems/ext4/ondisk/overview.rst
new file mode 100644
index 000000000000..cbab18baba12
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/overview.rst
@@ -0,0 +1,26 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+High Level Design
+=================
+
+An ext4 file system is split into a series of block groups. To reduce
+performance difficulties due to fragmentation, the block allocator tries
+very hard to keep each file's blocks within the same group, thereby
+reducing seek times. The size of a block group is specified in
+``sb.s_blocks_per_group`` blocks, though it can also calculated as 8 \*
+``block_size_in_bytes``. With the default block size of 4KiB, each group
+will contain 32,768 blocks, for a length of 128MiB. The number of block
+groups is the size of the device divided by the size of a block group.
+
+All fields in ext4 are written to disk in little-endian order. HOWEVER,
+all fields in jbd2 (the journal) are written to disk in big-endian
+order.
+
+.. include:: blocks.rst
+.. include:: blockgroup.rst
+.. include:: special_inodes.rst
+.. include:: allocators.rst
+.. include:: checksums.rst
+.. include:: bigalloc.rst
+.. include:: inlinedata.rst
+.. include:: eainode.rst
diff --git a/Documentation/filesystems/ext4/ondisk/special_inodes.rst b/Documentation/filesystems/ext4/ondisk/special_inodes.rst
new file mode 100644
index 000000000000..a82f70c9baeb
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/special_inodes.rst
@@ -0,0 +1,38 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Special inodes
+--------------
+
+ext4 reserves some inode for special features, as follows:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - inode Number
+     - Purpose
+   * - 0
+     - Doesn't exist; there is no inode 0.
+   * - 1
+     - List of defective blocks.
+   * - 2
+     - Root directory.
+   * - 3
+     - User quota.
+   * - 4
+     - Group quota.
+   * - 5
+     - Boot loader.
+   * - 6
+     - Undelete directory.
+   * - 7
+     - Reserved group descriptors inode. (“resize inode�)
+   * - 8
+     - Journal inode.
+   * - 9
+     - The “exclude� inode, for snapshots(?)
+   * - 10
+     - Replica inode, used for some non-upstream feature?
+   * - 11
+     - Traditional first non-reserved inode. Usually this is the lost+found directory. See s\_first\_ino in the superblock.
+
diff --git a/Documentation/filesystems/ext4/ondisk/super.rst b/Documentation/filesystems/ext4/ondisk/super.rst
new file mode 100644
index 000000000000..5f81dd87e0b9
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/super.rst
@@ -0,0 +1,801 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Super Block
+-----------
+
+The superblock records various information about the enclosing
+filesystem, such as block counts, inode counts, supported features,
+maintenance information, and more.
+
+If the sparse\_super feature flag is set, redundant copies of the
+superblock and group descriptors are kept only in the groups whose group
+number is either 0 or a power of 3, 5, or 7. If the flag is not set,
+redundant copies are kept in all groups.
+
+The superblock checksum is calculated against the superblock structure,
+which includes the FS UUID.
+
+The ext4 superblock is laid out as follows in
+``struct ext4_super_block``:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - s\_inodes\_count
+     - Total inode count.
+   * - 0x4
+     - \_\_le32
+     - s\_blocks\_count\_lo
+     - Total block count.
+   * - 0x8
+     - \_\_le32
+     - s\_r\_blocks\_count\_lo
+     - This number of blocks can only be allocated by the super-user.
+   * - 0xC
+     - \_\_le32
+     - s\_free\_blocks\_count\_lo
+     - Free block count.
+   * - 0x10
+     - \_\_le32
+     - s\_free\_inodes\_count
+     - Free inode count.
+   * - 0x14
+     - \_\_le32
+     - s\_first\_data\_block
+     - First data block. This must be at least 1 for 1k-block filesystems and
+       is typically 0 for all other block sizes.
+   * - 0x18
+     - \_\_le32
+     - s\_log\_block\_size
+     - Block size is 2 ^ (10 + s\_log\_block\_size).
+   * - 0x1C
+     - \_\_le32
+     - s\_log\_cluster\_size
+     - Cluster size is (2 ^ s\_log\_cluster\_size) blocks if bigalloc is
+       enabled. Otherwise s\_log\_cluster\_size must equal s\_log\_block\_size.
+   * - 0x20
+     - \_\_le32
+     - s\_blocks\_per\_group
+     - Blocks per group.
+   * - 0x24
+     - \_\_le32
+     - s\_clusters\_per\_group
+     - Clusters per group, if bigalloc is enabled. Otherwise
+       s\_clusters\_per\_group must equal s\_blocks\_per\_group.
+   * - 0x28
+     - \_\_le32
+     - s\_inodes\_per\_group
+     - Inodes per group.
+   * - 0x2C
+     - \_\_le32
+     - s\_mtime
+     - Mount time, in seconds since the epoch.
+   * - 0x30
+     - \_\_le32
+     - s\_wtime
+     - Write time, in seconds since the epoch.
+   * - 0x34
+     - \_\_le16
+     - s\_mnt\_count
+     - Number of mounts since the last fsck.
+   * - 0x36
+     - \_\_le16
+     - s\_max\_mnt\_count
+     - Number of mounts beyond which a fsck is needed.
+   * - 0x38
+     - \_\_le16
+     - s\_magic
+     - Magic signature, 0xEF53
+   * - 0x3A
+     - \_\_le16
+     - s\_state
+     - File system state. See super_state_ for more info.
+   * - 0x3C
+     - \_\_le16
+     - s\_errors
+     - Behaviour when detecting errors. See super_errors_ for more info.
+   * - 0x3E
+     - \_\_le16
+     - s\_minor\_rev\_level
+     - Minor revision level.
+   * - 0x40
+     - \_\_le32
+     - s\_lastcheck
+     - Time of last check, in seconds since the epoch.
+   * - 0x44
+     - \_\_le32
+     - s\_checkinterval
+     - Maximum time between checks, in seconds.
+   * - 0x48
+     - \_\_le32
+     - s\_creator\_os
+     - Creator OS. See the table super_creator_ for more info.
+   * - 0x4C
+     - \_\_le32
+     - s\_rev\_level
+     - Revision level. See the table super_revision_ for more info.
+   * - 0x50
+     - \_\_le16
+     - s\_def\_resuid
+     - Default uid for reserved blocks.
+   * - 0x52
+     - \_\_le16
+     - s\_def\_resgid
+     - Default gid for reserved blocks.
+   * -
+     -
+     -
+     - These fields are for EXT4_DYNAMIC_REV superblocks only.
+       
+       Note: the difference between the compatible feature set and the
+       incompatible feature set is that if there is a bit set in the
+       incompatible feature set that the kernel doesn't know about, it should
+       refuse to mount the filesystem.
+       
+       e2fsck's requirements are more strict; if it doesn't know
+       about a feature in either the compatible or incompatible feature set, it
+       must abort and not try to meddle with things it doesn't understand...
+   * - 0x54
+     - \_\_le32
+     - s\_first\_ino
+     - First non-reserved inode.
+   * - 0x58
+     - \_\_le16
+     - s\_inode\_size
+     - Size of inode structure, in bytes.
+   * - 0x5A
+     - \_\_le16
+     - s\_block\_group\_nr
+     - Block group # of this superblock.
+   * - 0x5C
+     - \_\_le32
+     - s\_feature\_compat
+     - Compatible feature set flags. Kernel can still read/write this fs even
+       if it doesn't understand a flag; fsck should not do that. See the
+       super_compat_ table for more info.
+   * - 0x60
+     - \_\_le32
+     - s\_feature\_incompat
+     - Incompatible feature set. If the kernel or fsck doesn't understand one
+       of these bits, it should stop. See the super_incompat_ table for more
+       info.
+   * - 0x64
+     - \_\_le32
+     - s\_feature\_ro\_compat
+     - Readonly-compatible feature set. If the kernel doesn't understand one of
+       these bits, it can still mount read-only. See the super_rocompat_ table
+       for more info.
+   * - 0x68
+     - \_\_u8
+     - s\_uuid[16]
+     - 128-bit UUID for volume.
+   * - 0x78
+     - char
+     - s\_volume\_name[16]
+     - Volume label.
+   * - 0x88
+     - char
+     - s\_last\_mounted[64]
+     - Directory where filesystem was last mounted.
+   * - 0xC8
+     - \_\_le32
+     - s\_algorithm\_usage\_bitmap
+     - For compression (Not used in e2fsprogs/Linux)
+   * -
+     -
+     -
+     - Performance hints.  Directory preallocation should only happen if the
+       EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
+   * - 0xCC
+     - \_\_u8
+     - s\_prealloc\_blocks
+     - #. of blocks to try to preallocate for ... files? (Not used in
+       e2fsprogs/Linux)
+   * - 0xCD
+     - \_\_u8
+     - s\_prealloc\_dir\_blocks
+     - #. of blocks to preallocate for directories. (Not used in
+       e2fsprogs/Linux)
+   * - 0xCE
+     - \_\_le16
+     - s\_reserved\_gdt\_blocks
+     - Number of reserved GDT entries for future filesystem expansion.
+   * -
+     -
+     -
+     - Journalling support is valid only if EXT4_FEATURE_COMPAT_HAS_JOURNAL is
+       set.
+   * - 0xD0
+     - \_\_u8
+     - s\_journal\_uuid[16]
+     - UUID of journal superblock
+   * - 0xE0
+     - \_\_le32
+     - s\_journal\_inum
+     - inode number of journal file.
+   * - 0xE4
+     - \_\_le32
+     - s\_journal\_dev
+     - Device number of journal file, if the external journal feature flag is
+       set.
+   * - 0xE8
+     - \_\_le32
+     - s\_last\_orphan
+     - Start of list of orphaned inodes to delete.
+   * - 0xEC
+     - \_\_le32
+     - s\_hash\_seed[4]
+     - HTREE hash seed.
+   * - 0xFC
+     - \_\_u8
+     - s\_def\_hash\_version
+     - Default hash algorithm to use for directory hashes. See super_def_hash_
+       for more info.
+   * - 0xFD
+     - \_\_u8
+     - s\_jnl\_backup\_type
+     - If this value is 0 or EXT3\_JNL\_BACKUP\_BLOCKS (1), then the
+       ``s_jnl_blocks`` field contains a duplicate copy of the inode's
+       ``i_block[]`` array and ``i_size``.
+   * - 0xFE
+     - \_\_le16
+     - s\_desc\_size
+     - Size of group descriptors, in bytes, if the 64bit incompat feature flag
+       is set.
+   * - 0x100
+     - \_\_le32
+     - s\_default\_mount\_opts
+     - Default mount options. See the super_mountopts_ table for more info.
+   * - 0x104
+     - \_\_le32
+     - s\_first\_meta\_bg
+     - First metablock block group, if the meta\_bg feature is enabled.
+   * - 0x108
+     - \_\_le32
+     - s\_mkfs\_time
+     - When the filesystem was created, in seconds since the epoch.
+   * - 0x10C
+     - \_\_le32
+     - s\_jnl\_blocks[17]
+     - Backup copy of the journal inode's ``i_block[]`` array in the first 15
+       elements and i\_size\_high and i\_size in the 16th and 17th elements,
+       respectively.
+   * -
+     -
+     -
+     - 64bit support is valid only if EXT4_FEATURE_COMPAT_64BIT is set.
+   * - 0x150
+     - \_\_le32
+     - s\_blocks\_count\_hi
+     - High 32-bits of the block count.
+   * - 0x154
+     - \_\_le32
+     - s\_r\_blocks\_count\_hi
+     - High 32-bits of the reserved block count.
+   * - 0x158
+     - \_\_le32
+     - s\_free\_blocks\_count\_hi
+     - High 32-bits of the free block count.
+   * - 0x15C
+     - \_\_le16
+     - s\_min\_extra\_isize
+     - All inodes have at least # bytes.
+   * - 0x15E
+     - \_\_le16
+     - s\_want\_extra\_isize
+     - New inodes should reserve # bytes.
+   * - 0x160
+     - \_\_le32
+     - s\_flags
+     - Miscellaneous flags. See the super_flags_ table for more info.
+   * - 0x164
+     - \_\_le16
+     - s\_raid\_stride
+     - RAID stride. This is the number of logical blocks read from or written
+       to the disk before moving to the next disk. This affects the placement
+       of filesystem metadata, which will hopefully make RAID storage faster.
+   * - 0x166
+     - \_\_le16
+     - s\_mmp\_interval
+     - #. seconds to wait in multi-mount prevention (MMP) checking. In theory,
+       MMP is a mechanism to record in the superblock which host and device
+       have mounted the filesystem, in order to prevent multiple mounts. This
+       feature does not seem to be implemented...
+   * - 0x168
+     - \_\_le64
+     - s\_mmp\_block
+     - Block # for multi-mount protection data.
+   * - 0x170
+     - \_\_le32
+     - s\_raid\_stripe\_width
+     - RAID stripe width. This is the number of logical blocks read from or
+       written to the disk before coming back to the current disk. This is used
+       by the block allocator to try to reduce the number of read-modify-write
+       operations in a RAID5/6.
+   * - 0x174
+     - \_\_u8
+     - s\_log\_groups\_per\_flex
+     - Size of a flexible block group is 2 ^ ``s_log_groups_per_flex``.
+   * - 0x175
+     - \_\_u8
+     - s\_checksum\_type
+     - Metadata checksum algorithm type. The only valid value is 1 (crc32c).
+   * - 0x176
+     - \_\_le16
+     - s\_reserved\_pad
+     -
+   * - 0x178
+     - \_\_le64
+     - s\_kbytes\_written
+     - Number of KiB written to this filesystem over its lifetime.
+   * - 0x180
+     - \_\_le32
+     - s\_snapshot\_inum
+     - inode number of active snapshot. (Not used in e2fsprogs/Linux.)
+   * - 0x184
+     - \_\_le32
+     - s\_snapshot\_id
+     - Sequential ID of active snapshot. (Not used in e2fsprogs/Linux.)
+   * - 0x188
+     - \_\_le64
+     - s\_snapshot\_r\_blocks\_count
+     - Number of blocks reserved for active snapshot's future use. (Not used in
+       e2fsprogs/Linux.)
+   * - 0x190
+     - \_\_le32
+     - s\_snapshot\_list
+     - inode number of the head of the on-disk snapshot list. (Not used in
+       e2fsprogs/Linux.)
+   * - 0x194
+     - \_\_le32
+     - s\_error\_count
+     - Number of errors seen.
+   * - 0x198
+     - \_\_le32
+     - s\_first\_error\_time
+     - First time an error happened, in seconds since the epoch.
+   * - 0x19C
+     - \_\_le32
+     - s\_first\_error\_ino
+     - inode involved in first error.
+   * - 0x1A0
+     - \_\_le64
+     - s\_first\_error\_block
+     - Number of block involved of first error.
+   * - 0x1A8
+     - \_\_u8
+     - s\_first\_error\_func[32]
+     - Name of function where the error happened.
+   * - 0x1C8
+     - \_\_le32
+     - s\_first\_error\_line
+     - Line number where error happened.
+   * - 0x1CC
+     - \_\_le32
+     - s\_last\_error\_time
+     - Time of most recent error, in seconds since the epoch.
+   * - 0x1D0
+     - \_\_le32
+     - s\_last\_error\_ino
+     - inode involved in most recent error.
+   * - 0x1D4
+     - \_\_le32
+     - s\_last\_error\_line
+     - Line number where most recent error happened.
+   * - 0x1D8
+     - \_\_le64
+     - s\_last\_error\_block
+     - Number of block involved in most recent error.
+   * - 0x1E0
+     - \_\_u8
+     - s\_last\_error\_func[32]
+     - Name of function where the most recent error happened.
+   * - 0x200
+     - \_\_u8
+     - s\_mount\_opts[64]
+     - ASCIIZ string of mount options.
+   * - 0x240
+     - \_\_le32
+     - s\_usr\_quota\_inum
+     - Inode number of user `quota <quota>`__ file.
+   * - 0x244
+     - \_\_le32
+     - s\_grp\_quota\_inum
+     - Inode number of group `quota <quota>`__ file.
+   * - 0x248
+     - \_\_le32
+     - s\_overhead\_blocks
+     - Overhead blocks/clusters in fs. (Huh? This field is always zero, which
+       means that the kernel calculates it dynamically.)
+   * - 0x24C
+     - \_\_le32
+     - s\_backup\_bgs[2]
+     - Block groups containing superblock backups (if sparse\_super2)
+   * - 0x254
+     - \_\_u8
+     - s\_encrypt\_algos[4]
+     - Encryption algorithms in use. There can be up to four algorithms in use
+       at any time; valid algorithm codes are given in the super_encrypt_ table
+       below.
+   * - 0x258
+     - \_\_u8
+     - s\_encrypt\_pw\_salt[16]
+     - Salt for the string2key algorithm for encryption.
+   * - 0x268
+     - \_\_le32
+     - s\_lpf\_ino
+     - Inode number of lost+found
+   * - 0x26C
+     - \_\_le32
+     - s\_prj\_quota\_inum
+     - Inode that tracks project quotas.
+   * - 0x270
+     - \_\_le32
+     - s\_checksum\_seed
+     - Checksum seed used for metadata\_csum calculations. This value is
+       crc32c(~0, $orig\_fs\_uuid).
+   * - 0x274
+     - \_\_u8
+     - s\_wtime_hi
+     - Upper 8 bits of the s_wtime field.
+   * - 0x275
+     - \_\_u8
+     - s\_wtime_hi
+     - Upper 8 bits of the s_mtime field.
+   * - 0x276
+     - \_\_u8
+     - s\_mkfs_time_hi
+     - Upper 8 bits of the s_mkfs_time field.
+   * - 0x277
+     - \_\_u8
+     - s\_lastcheck_hi
+     - Upper 8 bits of the s_lastcheck_hi field.
+   * - 0x278
+     - \_\_u8
+     - s\_first_error_time_hi
+     - Upper 8 bits of the s_first_error_time_hi field.
+   * - 0x279
+     - \_\_u8
+     - s\_last_error_time_hi
+     - Upper 8 bits of the s_last_error_time_hi field.
+   * - 0x27A
+     - \_\_u8[2]
+     - s\_pad
+     - Zero padding.
+   * - 0x27C
+     - \_\_le32
+     - s\_reserved[96]
+     - Padding to the end of the block.
+   * - 0x3FC
+     - \_\_le32
+     - s\_checksum
+     - Superblock checksum.
+
+.. _super_state:
+
+The superblock state is some combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0001
+     - Cleanly umounted
+   * - 0x0002
+     - Errors detected
+   * - 0x0004
+     - Orphans being recovered
+
+.. _super_errors:
+
+The superblock error policy is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 1
+     - Continue
+   * - 2
+     - Remount read-only
+   * - 3
+     - Panic
+
+.. _super_creator:
+
+The filesystem creator is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0
+     - Linux
+   * - 1
+     - Hurd
+   * - 2
+     - Masix
+   * - 3
+     - FreeBSD
+   * - 4
+     - Lites
+
+.. _super_revision:
+
+The superblock revision is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0
+     - Original format
+   * - 1
+     - v2 format w/ dynamic inode sizes
+
+Note that ``EXT4_DYNAMIC_REV`` refers to a revision 1 or newer filesystem.
+
+.. _super_compat:
+
+The superblock compatible features field is a combination of any of the
+following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Directory preallocation (COMPAT\_DIR\_PREALLOC).
+   * - 0x2
+     - “imagic inodes�. Not clear from the code what this does
+       (COMPAT\_IMAGIC\_INODES).
+   * - 0x4
+     - Has a journal (COMPAT\_HAS\_JOURNAL).
+   * - 0x8
+     - Supports extended attributes (COMPAT\_EXT\_ATTR).
+   * - 0x10
+     - Has reserved GDT blocks for filesystem expansion
+       (COMPAT\_RESIZE\_INODE). Requires RO\_COMPAT\_SPARSE\_SUPER.
+   * - 0x20
+     - Has directory indices (COMPAT\_DIR\_INDEX).
+   * - 0x40
+     - “Lazy BG�. Not in Linux kernel, seems to have been for uninitialized
+       block groups? (COMPAT\_LAZY\_BG)
+   * - 0x80
+     - “Exclude inode�. Not used. (COMPAT\_EXCLUDE\_INODE).
+   * - 0x100
+     - “Exclude bitmap�. Seems to be used to indicate the presence of
+       snapshot-related exclude bitmaps? Not defined in kernel or used in
+       e2fsprogs (COMPAT\_EXCLUDE\_BITMAP).
+   * - 0x200
+     - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs
+       points to the two block groups that contain backup superblocks
+       (COMPAT\_SPARSE\_SUPER2).
+
+.. _super_incompat:
+
+The superblock incompatible features field is a combination of any of the
+following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Compression (INCOMPAT\_COMPRESSION).
+   * - 0x2
+     - Directory entries record the file type. See ext4\_dir\_entry\_2 below
+       (INCOMPAT\_FILETYPE).
+   * - 0x4
+     - Filesystem needs recovery (INCOMPAT\_RECOVER).
+   * - 0x8
+     - Filesystem has a separate journal device (INCOMPAT\_JOURNAL\_DEV).
+   * - 0x10
+     - Meta block groups. See the earlier discussion of this feature
+       (INCOMPAT\_META\_BG).
+   * - 0x40
+     - Files in this filesystem use extents (INCOMPAT\_EXTENTS).
+   * - 0x80
+     - Enable a filesystem size of 2^64 blocks (INCOMPAT\_64BIT).
+   * - 0x100
+     - Multiple mount protection. Not implemented (INCOMPAT\_MMP).
+   * - 0x200
+     - Flexible block groups. See the earlier discussion of this feature
+       (INCOMPAT\_FLEX\_BG).
+   * - 0x400
+     - Inodes can be used to store large extended attribute values
+       (INCOMPAT\_EA\_INODE).
+   * - 0x1000
+     - Data in directory entry (INCOMPAT\_DIRDATA). (Not implemented?)
+   * - 0x2000
+     - Metadata checksum seed is stored in the superblock. This feature enables
+       the administrator to change the UUID of a metadata\_csum filesystem
+       while the filesystem is mounted; without it, the checksum definition
+       requires all metadata blocks to be rewritten (INCOMPAT\_CSUM\_SEED).
+   * - 0x4000
+     - Large directory >2GB or 3-level htree (INCOMPAT\_LARGEDIR). Prior to
+       this feature, directories could not be larger than 4GiB and could not
+       have an htree more than 2 levels deep. If this feature is enabled,
+       directories can be larger than 4GiB and have a maximum htree depth of 3.
+   * - 0x8000
+     - Data in inode (INCOMPAT\_INLINE\_DATA).
+   * - 0x10000
+     - Encrypted inodes are present on the filesystem. (INCOMPAT\_ENCRYPT).
+
+.. _super_rocompat:
+
+The superblock read-only compatible features field is a combination of any of
+the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Sparse superblocks. See the earlier discussion of this feature
+       (RO\_COMPAT\_SPARSE\_SUPER).
+   * - 0x2
+     - This filesystem has been used to store a file greater than 2GiB
+       (RO\_COMPAT\_LARGE\_FILE).
+   * - 0x4
+     - Not used in kernel or e2fsprogs (RO\_COMPAT\_BTREE\_DIR).
+   * - 0x8
+     - This filesystem has files whose sizes are represented in units of
+       logical blocks, not 512-byte sectors. This implies a very large file
+       indeed! (RO\_COMPAT\_HUGE\_FILE)
+   * - 0x10
+     - Group descriptors have checksums. In addition to detecting corruption,
+       this is useful for lazy formatting with uninitialized groups
+       (RO\_COMPAT\_GDT\_CSUM).
+   * - 0x20
+     - Indicates that the old ext3 32,000 subdirectory limit no longer applies
+       (RO\_COMPAT\_DIR\_NLINK). A directory's i\_links\_count will be set to 1
+       if it is incremented past 64,999.
+   * - 0x40
+     - Indicates that large inodes exist on this filesystem
+       (RO\_COMPAT\_EXTRA\_ISIZE).
+   * - 0x80
+     - This filesystem has a snapshot (RO\_COMPAT\_HAS\_SNAPSHOT).
+   * - 0x100
+     - `Quota <Quota>`__ (RO\_COMPAT\_QUOTA).
+   * - 0x200
+     - This filesystem supports “bigalloc�, which means that file extents are
+       tracked in units of clusters (of blocks) instead of blocks
+       (RO\_COMPAT\_BIGALLOC).
+   * - 0x400
+     - This filesystem supports metadata checksumming.
+       (RO\_COMPAT\_METADATA\_CSUM; implies RO\_COMPAT\_GDT\_CSUM, though
+       GDT\_CSUM must not be set)
+   * - 0x800
+     - Filesystem supports replicas. This feature is neither in the kernel nor
+       e2fsprogs. (RO\_COMPAT\_REPLICA)
+   * - 0x1000
+     - Read-only filesystem image; the kernel will not mount this image
+       read-write and most tools will refuse to write to the image.
+       (RO\_COMPAT\_READONLY)
+   * - 0x2000
+     - Filesystem tracks project quotas. (RO\_COMPAT\_PROJECT)
+
+.. _super_def_hash:
+
+The ``s_def_hash_version`` field is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0
+     - Legacy.
+   * - 0x1
+     - Half MD4.
+   * - 0x2
+     - Tea.
+   * - 0x3
+     - Legacy, unsigned.
+   * - 0x4
+     - Half MD4, unsigned.
+   * - 0x5
+     - Tea, unsigned.
+
+.. _super_mountopts:
+
+The ``s_default_mount_opts`` field is any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0001
+     - Print debugging info upon (re)mount. (EXT4\_DEFM\_DEBUG)
+   * - 0x0002
+     - New files take the gid of the containing directory (instead of the fsgid
+       of the current process). (EXT4\_DEFM\_BSDGROUPS)
+   * - 0x0004
+     - Support userspace-provided extended attributes. (EXT4\_DEFM\_XATTR\_USER)
+   * - 0x0008
+     - Support POSIX access control lists (ACLs). (EXT4\_DEFM\_ACL)
+   * - 0x0010
+     - Do not support 32-bit UIDs. (EXT4\_DEFM\_UID16)
+   * - 0x0020
+     - All data and metadata are commited to the journal.
+       (EXT4\_DEFM\_JMODE\_DATA)
+   * - 0x0040
+     - All data are flushed to the disk before metadata are committed to the
+       journal. (EXT4\_DEFM\_JMODE\_ORDERED)
+   * - 0x0060
+     - Data ordering is not preserved; data may be written after the metadata
+       has been written. (EXT4\_DEFM\_JMODE\_WBACK)
+   * - 0x0100
+     - Disable write flushes. (EXT4\_DEFM\_NOBARRIER)
+   * - 0x0200
+     - Track which blocks in a filesystem are metadata and therefore should not
+       be used as data blocks. This option will be enabled by default on 3.18,
+       hopefully. (EXT4\_DEFM\_BLOCK\_VALIDITY)
+   * - 0x0400
+     - Enable DISCARD support, where the storage device is told about blocks
+       becoming unused. (EXT4\_DEFM\_DISCARD)
+   * - 0x0800
+     - Disable delayed allocation. (EXT4\_DEFM\_NODELALLOC)
+
+.. _super_flags:
+
+The ``s_flags`` field is any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0001
+     - Signed directory hash in use.
+   * - 0x0002
+     - Unsigned directory hash in use.
+   * - 0x0004
+     - To test development code.
+
+.. _super_encrypt:
+
+The ``s_encrypt_algos`` list can contain any of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0
+     - Invalid algorithm (ENCRYPTION\_MODE\_INVALID).
+   * - 1
+     - 256-bit AES in XTS mode (ENCRYPTION\_MODE\_AES\_256\_XTS).
+   * - 2
+     - 256-bit AES in GCM mode (ENCRYPTION\_MODE\_AES\_256\_GCM).
+   * - 3
+     - 256-bit AES in CBC mode (ENCRYPTION\_MODE\_AES\_256\_CBC).
+
+Total size of the superblock is 1024 bytes.
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 53b89d0edc15..46d1b1be3a51 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -71,6 +71,39 @@ Other Functions
 .. kernel-doc:: fs/block_dev.c
    :export:
 
+.. kernel-doc:: fs/anon_inodes.c
+   :export:
+
+.. kernel-doc:: fs/attr.c
+   :export:
+
+.. kernel-doc:: fs/d_path.c
+   :export:
+
+.. kernel-doc:: fs/dax.c
+   :export:
+
+.. kernel-doc:: fs/direct-io.c
+   :export:
+
+.. kernel-doc:: fs/file_table.c
+   :export:
+
+.. kernel-doc:: fs/libfs.c
+   :export:
+
+.. kernel-doc:: fs/posix_acl.c
+   :export:
+
+.. kernel-doc:: fs/stat.c
+   :export:
+
+.. kernel-doc:: fs/sync.c
+   :export:
+
+.. kernel-doc:: fs/xattr.c
+   :export:
+
 The proc filesystem
 ===================
 
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 17bb4dc28fae..7b7b845c490a 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -602,3 +602,23 @@ in your dentry operations instead.
 	dentry separately, and it now has request_mask and query_flags arguments
 	to specify the fields and sync type requested by statx.  Filesystems not
 	supporting any statx-specific features may ignore the new arguments.
+--
+[mandatory]
+	->atomic_open() calling conventions have changed.  Gone is int *opened,
+	along with FILE_OPENED/FILE_CREATED.  In place of those we have
+	FMODE_OPENED/FMODE_CREATED, set in file->f_mode.  Additionally, return
+	value for 'called finish_no_open(), open it yourself' case has become
+	0, not 1.  Since finish_no_open() itself is returning 0 now, that part
+	does not need any changes in ->atomic_open() instances.
+--
+[mandatory]
+	alloc_file() has become static now; two wrappers are to be used instead.
+	alloc_file_pseudo(inode, vfsmount, name, flags, ops) is for the cases
+	when dentry needs to be created; that's the majority of old alloc_file()
+	users.  Calling conventions: on success a reference to new struct file
+	is returned and callers reference to inode is subsumed by that.  On
+	failure, ERR_PTR() is returned and no caller's references are affected,
+	so the caller needs to drop the inode reference it held.
+	alloc_file_clone(file, flags, ops) does not affect any caller's references.
+	On success you get a new struct file sharing the mount/dentry with the
+	original, on failure - ERR_PTR().
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 520f6a84cf50..1605acbb23b6 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -870,6 +870,7 @@ Committed_AS:   100056 kB
 VmallocTotal:   112216 kB
 VmallocUsed:       428 kB
 VmallocChunk:   111088 kB
+HardwareCorrupted:   0 kB
 AnonHugePages:   49152 kB
 ShmemHugePages:      0 kB
 ShmemPmdMapped:      0 kB
@@ -915,6 +916,8 @@ MemAvailable: An estimate of how much memory is available for starting new
        Dirty: Memory which is waiting to get written back to the disk
    Writeback: Memory which is actively being written back to the disk
    AnonPages: Non-file backed pages mapped into userspace page tables
+HardwareCorrupted: The amount of RAM/memory in KB, the kernel identifies as
+	      corrupted.
 AnonHugePages: Non-file backed huge pages mapped into userspace page tables
       Mapped: files which have been mmaped, such as libraries
        Shmem: Total memory used by shared memory (shmem) and tmpfs
diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.txt
index 33e2f3694733..cd709a94d054 100644
--- a/Documentation/filesystems/relay.txt
+++ b/Documentation/filesystems/relay.txt
@@ -222,7 +222,7 @@ using debugfs:
  */
 static struct dentry *create_buf_file_handler(const char *filename,
                                               struct dentry *parent,
-                                              int mode,
+                                              umode_t mode,
                                               struct rchan_buf *buf,
                                               int *is_global)
 {
@@ -375,7 +375,7 @@ would be very similar:
 static int subbuf_start(struct rchan_buf *buf,
                         void *subbuf,
 			void *prev_subbuf,
-			unsigned int prev_padding)
+			size_t prev_padding)
 {
 	if (prev_subbuf)
 		*((unsigned *)prev_subbuf) = prev_padding;
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 829a7b7857a4..85907d5b9c2c 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -386,7 +386,7 @@ struct inode_operations {
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *, struct file *,
-			unsigned open_flag, umode_t create_mode, int *opened);
+			unsigned open_flag, umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 };
 
@@ -496,13 +496,15 @@ otherwise noted.
 
   atomic_open: called on the last component of an open.  Using this optional
   	method the filesystem can look up, possibly create and open the file in
-  	one atomic operation.  If it cannot perform this (e.g. the file type
-  	turned out to be wrong) it may signal this by returning 1 instead of
-	usual 0 or -ve .  This method is only called if the last component is
-	negative or needs lookup.  Cached positive dentries are still handled by
-	f_op->open().  If the file was created, the FILE_CREATED flag should be
-	set in "opened".  In case of O_EXCL the method must only succeed if the
-	file didn't exist and hence FILE_CREATED shall always be set on success.
+	one atomic operation.  If it wants to leave actual opening to the
+	caller (e.g. if the file turned out to be a symlink, device, or just
+	something filesystem won't do atomic open for), it may signal this by
+	returning finish_no_open(file, dentry).  This method is only called if
+	the last component is negative or needs lookup.  Cached positive dentries
+	are still handled by f_op->open().  If the file was created,
+	FMODE_CREATED flag should be set in file->f_mode.  In case of O_EXCL
+	the method must only succeed if the file didn't exist and hence FMODE_CREATED
+	shall always be set on success.
 
   tmpfile: called in the end of O_TMPFILE open().  Optional, equivalent to
 	atomically creating, opening and unlinking a file in given directory.
@@ -857,8 +859,6 @@ struct file_operations {
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
-	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
-	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -903,17 +903,6 @@ otherwise noted.
 	activity on this file and (optionally) go to sleep until there
 	is activity. Called by the select(2) and poll(2) system calls
 
-  get_poll_head: Returns the struct wait_queue_head that callers can
-  wait on.  Callers need to check the returned events using ->poll_mask
-  once woken.  Can return NULL to indicate polling is not supported,
-  or any error code using the ERR_PTR convention to indicate that a
-  grave error occured and ->poll_mask shall not be called.
-
-  poll_mask: return the mask of EPOLL* values describing the file descriptor
-  state.  Called either before going to sleep on the waitqueue returned by
-  get_poll_head, or after it has been woken.  If ->get_poll_head and
-  ->poll_mask are implemented ->poll does not need to be implement.
-
   unlocked_ioctl: called by the ioctl(2) system call.
 
   compat_ioctl: called by the ioctl(2) system call when 32 bit system calls
diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt
index 4d9ff0a7f8e1..a9ae82fb9d13 100644
--- a/Documentation/filesystems/xfs.txt
+++ b/Documentation/filesystems/xfs.txt
@@ -223,8 +223,6 @@ Deprecated Mount Options
 
   Name				Removal Schedule
   ----				----------------
-  barrier			no earlier than v4.15
-  nobarrier			no earlier than v4.15
 
 
 Removed Mount Options
@@ -236,6 +234,8 @@ Removed Mount Options
   ihashsize			v4.0
   irixsgid			v4.0
   osyncisdsync/osyncisosync	v4.0
+  barrier			v4.19
+  nobarrier			v4.19
 
 
 sysctls
diff --git a/Documentation/hwmon/max34440 b/Documentation/hwmon/max34440
index 9ba6587b7657..b2de8fa49273 100644
--- a/Documentation/hwmon/max34440
+++ b/Documentation/hwmon/max34440
@@ -16,6 +16,11 @@ Supported chips:
     Prefixes: 'max34446'
     Addresses scanned: -
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34446.pdf
+  * Maxim MAX34451
+    PMBus 16-Channel V/I Monitor and 12-Channel Sequencer/Marginer
+    Prefixes: 'max34451'
+    Addresses scanned: -
+    Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34451.pdf
   * Maxim MAX34460
     PMBus 12-Channel Voltage Monitor & Sequencer
     Prefix: 'max34460'
@@ -36,9 +41,10 @@ Description
 This driver supports hardware monitoring for Maxim MAX34440 PMBus 6-Channel
 Power-Supply Manager, MAX34441 PMBus 5-Channel Power-Supply Manager
 and Intelligent Fan Controller, and MAX34446 PMBus Power-Supply Data Logger.
-It also supports the MAX34460 and MAX34461 PMBus Voltage Monitor & Sequencers.
-The MAX34460 supports 12 voltage channels, and the MAX34461 supports 16 voltage
-channels.
+It also supports the MAX34451, MAX34460, and MAX34461 PMBus Voltage Monitor &
+Sequencers. The MAX34451 supports monitoring voltage or current of 12 channels
+based on GIN pins. The MAX34460 supports 12 voltage channels, and the MAX34461
+supports 16 voltage channels.
 
 The driver is a client driver to the core PMBus driver. Please see
 Documentation/hwmon/pmbus for details on PMBus client drivers.
@@ -93,7 +99,7 @@ curr[1-6]_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
 curr[1-6]_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT register.
 curr[1-6]_max_alarm	Current high alarm. From IOUT_OC_WARNING status.
 curr[1-6]_crit_alarm	Current critical high alarm. From IOUT_OC_FAULT status.
-curr[1-4]_average	Historical average current (MAX34446 only).
+curr[1-4]_average	Historical average current (MAX34446/34451 only).
 curr[1-6]_highest	Historical maximum current.
 curr[1-6]_reset_history	Write any value to reset history.
 
@@ -123,5 +129,7 @@ temp[1-8]_reset_history	Write any value to reset history.
 			temp7 and temp8 attributes only exist for MAX34440.
 			MAX34446 only supports temp[1-3].
 
+MAX34451 supports attribute groups in[1-16] (or curr[1-16] based on input pins)
+and temp[1-5].
 MAX34460 supports attribute groups in[1-12] and temp[1-5].
 MAX34461 supports attribute groups in[1-16] and temp[1-5].
diff --git a/Documentation/hwmon/mlxreg-fan b/Documentation/hwmon/mlxreg-fan
new file mode 100644
index 000000000000..fc531c6978d4
--- /dev/null
+++ b/Documentation/hwmon/mlxreg-fan
@@ -0,0 +1,60 @@
+Kernel driver mlxreg-fan
+========================
+
+Provides FAN control for the next Mellanox systems:
+QMB700, equipped with 40x200GbE InfiniBand ports;
+MSN3700, equipped with 32x200GbE or 16x400GbE Ethernet ports;
+MSN3410, equipped with 6x400GbE plus 48x50GbE Ethernet ports;
+MSN3800, equipped with 64x1000GbE Ethernet ports;
+These are the Top of the Rack systems, equipped with Mellanox switch
+board with Mellanox Quantum or Spectrume-2 devices.
+FAN controller is implemented by the programmable device logic.
+
+The default registers offsets set within the programmable device is as
+following:
+- pwm1			0xe3
+- fan1 (tacho1)		0xe4
+- fan2 (tacho2)		0xe5
+- fan3 (tacho3)		0xe6
+- fan4 (tacho4)		0xe7
+- fan5 (tacho5)		0xe8
+- fan6 (tacho6)		0xe9
+- fan7 (tacho7)		0xea
+- fan8 (tacho8)		0xeb
+- fan9 (tacho9)		0xec
+- fan10 (tacho10)	0xed
+- fan11 (tacho11)	0xee
+- fan12 (tacho12)	0xef
+This setup can be re-programmed with other registers.
+
+Author: Vadim Pasternak <vadimp@mellanox.com>
+
+Description
+-----------
+
+The driver implements a simple interface for driving a fan connected to
+a PWM output and tachometer inputs.
+This driver obtains PWM and tachometers registers location according to
+the system configuration and creates FAN/PWM hwmon objects and a cooling
+device. PWM and tachometers are sensed through the on-board programmable
+device, which exports its register map. This device could be attached to
+any bus type, for which register mapping is supported.
+Single instance is created with one PWM control, up to 12 tachometers and
+one cooling device. It could be as many instances as programmable device
+supports.
+The driver exposes the fan to the user space through the hwmon's and
+thermal's sysfs interfaces.
+
+/sys files in hwmon subsystem
+-----------------------------
+
+fan[1-12]_fault - RO files for tachometers TACH1-TACH12 fault indication
+fan[1-12]_input - RO files for tachometers TACH1-TACH12 input (in RPM)
+pwm1		- RW file for fan[1-12] target duty cycle (0..255)
+
+/sys files in thermal subsystem
+-------------------------------
+
+cur_state	- RW file for current cooling state of the cooling device
+		  (0..max_state)
+max_state	- RO file for maximum cooling state of the cooling device
diff --git a/Documentation/hwmon/npcm750-pwm-fan b/Documentation/hwmon/npcm750-pwm-fan
new file mode 100644
index 000000000000..6156ef7398e6
--- /dev/null
+++ b/Documentation/hwmon/npcm750-pwm-fan
@@ -0,0 +1,22 @@
+Kernel driver npcm750-pwm-fan
+=============================
+
+Supported chips:
+	NUVOTON NPCM750/730/715/705
+
+Authors:
+	<tomer.maimon@nuvoton.com>
+
+Description:
+------------
+This driver implements support for NUVOTON NPCM7XX PWM and Fan Tacho
+controller. The PWM controller supports up to 8 PWM outputs. The Fan tacho
+controller supports up to 16 tachometer inputs.
+
+The driver provides the following sensor accesses in sysfs:
+
+fanX_input	ro	provide current fan rotation value in RPM as reported
+			by the fan to the device.
+
+pwmX		rw	get or set PWM fan control value. This is an integer
+			value between 0(off) and 255(full speed).
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index fc337c317c67..2b9e1005d88b 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -171,6 +171,13 @@ in[0-*]_label	Suggested voltage channel label.
 		user-space.
 		RO
 
+in[0-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 cpu[0-*]_vid	CPU core reference voltage.
 		Unit: millivolt
 		RO
@@ -236,6 +243,13 @@ fan[1-*]_label	Suggested fan channel label.
 		In all other cases, the label is provided by user-space.
 		RO
 
+fan[1-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 Also see the Alarms section for status flags associated with fans.
 
 
@@ -409,6 +423,13 @@ temp_reset_history
 		Reset temp_lowest and temp_highest for all sensors
 		WO
 
+temp[1-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 Some chips measure temperature using external thermistors and an ADC, and
 report the temperature measurement as a voltage. Converting this voltage
 back to a temperature (or the other way around for limits) requires
@@ -468,6 +489,13 @@ curr_reset_history
 		Reset currX_lowest and currX_highest for all sensors
 		WO
 
+curr[1-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 Also see the Alarms section for status flags associated with currents.
 
 *********
@@ -566,6 +594,13 @@ power[1-*]_crit			Critical maximum power.
 				Unit: microWatt
 				RW
 
+power[1-*]_enable		Enable or disable the sensors.
+				When disabled the sensor read will return
+				-ENODATA.
+				1: Enable
+				0: Disable
+				RW
+
 Also see the Alarms section for status flags associated with power readings.
 
 **********
@@ -576,6 +611,12 @@ energy[1-*]_input		Cumulative energy use
 				Unit: microJoule
 				RO
 
+energy[1-*]_enable		Enable or disable the sensors.
+				When disabled the sensor read will return
+				-ENODATA.
+				1: Enable
+				0: Disable
+				RW
 
 ************
 * Humidity *
@@ -586,6 +627,13 @@ humidity[1-*]_input		Humidity
 				RO
 
 
+humidity[1-*]_enable		Enable or disable the sensors
+				When disabled the sensor read will return
+				-ENODATA.
+				1: Enable
+				0: Disable
+				RW
+
 **********
 * Alarms *
 **********
diff --git a/Documentation/index.rst b/Documentation/index.rst
index fdc585703498..d43fcd25c1da 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -3,6 +3,8 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
+.. _linux_doc:
+
 The Linux Kernel documentation
 ==============================
 
@@ -102,29 +104,24 @@ implementation.
 
    sh/index
 
-Korean translations
--------------------
-
-.. toctree::
-   :maxdepth: 1
-
-   translations/ko_KR/index
+Filesystem Documentation
+------------------------
 
-Chinese translations
---------------------
+The documentation in this section are provided by specific filesystem
+subprojects.
 
 .. toctree::
-   :maxdepth: 1
+   :maxdepth: 2
 
-   translations/zh_CN/index
+   filesystems/ext4/index
 
-Japanese translations
----------------------
+Translations
+------------
 
 .. toctree::
-   :maxdepth: 1
+   :maxdepth: 2
 
-   translations/ja_JP/index
+   translations/index
 
 Indices and tables
 ==================
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 480c8609dc58..9aeb5f0ea701 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -274,6 +274,7 @@ Code  Seq#(hex)	Include File		Comments
 'v'	00-1F	linux/ext2_fs.h		conflict!
 'v'	00-1F	linux/fs.h		conflict!
 'v'	00-0F	linux/sonypi.h		conflict!
+'v'	00-0F	media/v4l2-subdev.h	conflict!
 'v'	C0-FF	linux/meye.h		conflict!
 'w'	all				CERN SCI driver
 'y'	00-1F				packet based user level communications
diff --git a/Documentation/iostats.txt b/Documentation/iostats.txt
index 04d394a2e06c..49df45f90e8a 100644
--- a/Documentation/iostats.txt
+++ b/Documentation/iostats.txt
@@ -31,6 +31,9 @@ Here are examples of these different formats::
       3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
       3    1   hda1 35486 38030 38030 38030
 
+   4.18+ diskstats:
+      3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160 0 0 0 0
+
 On 2.4 you might execute ``grep 'hda ' /proc/partitions``. On 2.6+, you have
 a choice of ``cat /sys/block/hda/stat`` or ``grep 'hda ' /proc/diskstats``.
 
@@ -101,6 +104,18 @@ Field 11 -- weighted # of milliseconds spent doing I/Os
     last update of this field.  This can provide an easy measure of both
     I/O completion time and the backlog that may be accumulating.
 
+Field 12 -- # of discards completed
+    This is the total number of discards completed successfully.
+
+Field 13 -- # of discards merged
+    See the description of field 2
+
+Field 14 -- # of sectors discarded
+    This is the total number of sectors discarded successfully.
+
+Field 15 -- # of milliseconds spent discarding
+    This is the total number of milliseconds spent by all discards (as
+    measured from __make_request() to end_that_request_last()).
 
 To avoid introducing performance bottlenecks, no locks are held while
 modifying these counters.  This implies that minor inaccuracies may be
diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt
index 6c9c69ec3986..114c7ce7b58d 100644
--- a/Documentation/kbuild/kbuild.txt
+++ b/Documentation/kbuild/kbuild.txt
@@ -50,6 +50,11 @@ LDFLAGS_MODULE
 --------------------------------------------------
 Additional options used for $(LD) when linking modules.
 
+KBUILD_KCONFIG
+--------------------------------------------------
+Set the top-level Kconfig file to the value of this environment
+variable.  The default name is "Kconfig".
+
 KBUILD_VERBOSE
 --------------------------------------------------
 Set the kbuild verbosity. Can be assigned same values as "V=...".
@@ -88,7 +93,8 @@ In most cases the name of the architecture is the same as the
 directory name found in the arch/ directory.
 But some architectures such as x86 and sparc have aliases.
 x86: i386 for 32 bit, x86_64 for 64 bit
-sparc: sparc for 32 bit, sparc64 for 64 bit
+sh: sh for 32 bit, sh64 for 64 bit
+sparc: sparc32 for 32 bit, sparc64 for 64 bit
 
 CROSS_COMPILE
 --------------------------------------------------
@@ -148,15 +154,6 @@ stripped after they are installed.  If INSTALL_MOD_STRIP is '1', then
 the default option --strip-debug will be used.  Otherwise,
 INSTALL_MOD_STRIP value will be used as the options to the strip command.
 
-INSTALL_FW_PATH
---------------------------------------------------
-INSTALL_FW_PATH specifies where to install the firmware blobs.
-The default value is:
-
-    $(INSTALL_MOD_PATH)/lib/firmware
-
-The value can be overridden in which case the default value is ignored.
-
 INSTALL_HDR_PATH
 --------------------------------------------------
 INSTALL_HDR_PATH specifies where to install user space headers when
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index 3534a84d206c..64e0775a62d4 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -430,6 +430,12 @@ This sets the config program's title bar if the config program chooses
 to use it. It should be placed at the top of the configuration, before any
 other statement.
 
+'#' Kconfig source file comment:
+
+An unquoted '#' character anywhere in a source file line indicates
+the beginning of a source file comment.  The remainder of that line
+is a comment.
+
 
 Kconfig hints
 -------------
diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt
index 7233118f3a05..68c82914c0f3 100644
--- a/Documentation/kbuild/kconfig.txt
+++ b/Documentation/kbuild/kconfig.txt
@@ -2,9 +2,9 @@ This file contains some assistance for using "make *config".
 
 Use "make help" to list all of the possible configuration targets.
 
-The xconfig ('qconf') and menuconfig ('mconf') programs also
-have embedded help text.  Be sure to check it for navigation,
-search, and other general help text.
+The xconfig ('qconf'), menuconfig ('mconf'), and nconfig ('nconf')
+programs also have embedded help text.  Be sure to check that for
+navigation, search, and other general help text.
 
 ======================================================================
 General
@@ -17,13 +17,16 @@ this happens, using a previously working .config file and running
 for you, so you may find that you need to see what NEW kernel
 symbols have been introduced.
 
-To see a list of new config symbols when using "make oldconfig", use
+To see a list of new config symbols, use
 
 	cp user/some/old.config .config
 	make listnewconfig
 
 and the config program will list any new symbols, one per line.
 
+Alternatively, you can use the brute force method:
+
+	make oldconfig
 	scripts/diffconfig .config.old .config | less
 
 ______________________________________________________________________
@@ -160,7 +163,7 @@ Searching in menuconfig:
 		This lists all config symbols that contain "hotplug",
 		e.g., HOTPLUG_CPU, MEMORY_HOTPLUG.
 
-	For search help, enter / followed TAB-TAB-TAB (to highlight
+	For search help, enter / followed by TAB-TAB (to highlight
 	<Help>) and Enter.  This will tell you that you can also use
 	regular expressions (regexes) in the search string, so if you
 	are not interested in MEMORY_HOTPLUG, you could try
@@ -203,6 +206,39 @@ Example:
 
 
 ======================================================================
+nconfig
+--------------------------------------------------
+
+nconfig is an alternate text-based configurator.  It lists function
+keys across the bottom of the terminal (window) that execute commands.
+You can also just use the corresponding numeric key to execute the
+commands unless you are in a data entry window.  E.g., instead of F6
+for Save, you can just press 6.
+
+Use F1 for Global help or F3 for the Short help menu.
+
+Searching in nconfig:
+
+	You can search either in the menu entry "prompt" strings
+	or in the configuration symbols.
+
+	Use / to begin a search through the menu entries.  This does
+	not support regular expressions.  Use <Down> or <Up> for
+	Next hit and Previous hit, respectively.  Use <Esc> to
+	terminate the search mode.
+
+	F8 (SymSearch) searches the configuration symbols for the
+	given string or regular expression (regex).
+
+NCONFIG_MODE
+--------------------------------------------------
+This mode shows all sub-menus in one large tree.
+
+Example:
+	make NCONFIG_MODE=single_menu nconfig
+
+
+======================================================================
 xconfig
 --------------------------------------------------
 
@@ -230,8 +266,7 @@ gconfig
 
 Searching in gconfig:
 
-	None (gconfig isn't maintained as well as xconfig or menuconfig);
-	however, gconfig does have a few more viewing choices than
-	xconfig does.
+	There is no search command in gconfig.  However, gconfig does
+	have several different viewing choices, modes, and options.
 
 ###
diff --git a/Documentation/kernel-hacking/hacking.rst b/Documentation/kernel-hacking/hacking.rst
index 9999c8468293..d824e4feaff3 100644
--- a/Documentation/kernel-hacking/hacking.rst
+++ b/Documentation/kernel-hacking/hacking.rst
@@ -1,3 +1,5 @@
+.. _kernel_hacking_hack:
+
 ============================================
 Unreliable Guide To Hacking The Linux Kernel
 ============================================
diff --git a/Documentation/kernel-hacking/index.rst b/Documentation/kernel-hacking/index.rst
index fcb0eda3cca3..f53027652290 100644
--- a/Documentation/kernel-hacking/index.rst
+++ b/Documentation/kernel-hacking/index.rst
@@ -1,3 +1,5 @@
+.. _kernel_hacking:
+
 =====================
 Kernel Hacking Guides
 =====================
diff --git a/Documentation/kernel-hacking/locking.rst b/Documentation/kernel-hacking/locking.rst
index f937c0fd11aa..519673df0e82 100644
--- a/Documentation/kernel-hacking/locking.rst
+++ b/Documentation/kernel-hacking/locking.rst
@@ -1,3 +1,5 @@
+.. _kernel_hacking_lock:
+
 ===========================
 Unreliable Guide To Locking
 ===========================
@@ -177,7 +179,7 @@ perfect world).
 
 Note that you can also use :c:func:`spin_lock_irq()` or
 :c:func:`spin_lock_irqsave()` here, which stop hardware interrupts
-as well: see `Hard IRQ Context <#hardirq-context>`__.
+as well: see `Hard IRQ Context <#hard-irq-context>`__.
 
 This works perfectly for UP as well: the spin lock vanishes, and this
 macro simply becomes :c:func:`local_bh_disable()`
@@ -228,7 +230,7 @@ The Same Softirq
 ~~~~~~~~~~~~~~~~
 
 The same softirq can run on the other CPUs: you can use a per-CPU array
-(see `Per-CPU Data <#per-cpu>`__) for better performance. If you're
+(see `Per-CPU Data <#per-cpu-data>`__) for better performance. If you're
 going so far as to use a softirq, you probably care about scalable
 performance enough to justify the extra complexity.
 
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index cb3b0de83fc6..10f4499e677c 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -80,6 +80,26 @@ After the instruction is single-stepped, Kprobes executes the
 "post_handler," if any, that is associated with the kprobe.
 Execution then continues with the instruction following the probepoint.
 
+Changing Execution Path
+-----------------------
+
+Since kprobes can probe into a running kernel code, it can change the
+register set, including instruction pointer. This operation requires
+maximum care, such as keeping the stack frame, recovering the execution
+path etc. Since it operates on a running kernel and needs deep knowledge
+of computer architecture and concurrent computing, you can easily shoot
+your foot.
+
+If you change the instruction pointer (and set up other related
+registers) in pre_handler, you must return !0 so that kprobes stops
+single stepping and just returns to the given address.
+This also means post_handler should not be called anymore.
+
+Note that this operation may be harder on some architectures which use
+TOC (Table of Contents) for function call, since you have to setup a new
+TOC for your function in your module, and recover the old one after
+returning from it.
+
 Return Probes
 -------------
 
@@ -262,7 +282,7 @@ is optimized, that modification is ignored.  Thus, if you want to
 tweak the kernel's execution path, you need to suppress optimization,
 using one of the following techniques:
 
-- Specify an empty function for the kprobe's post_handler or break_handler.
+- Specify an empty function for the kprobe's post_handler.
 
 or
 
@@ -474,7 +494,7 @@ error occurs during registration, all probes in the array, up to
 the bad probe, are safely unregistered before the register_*probes
 function returns.
 
-- kps/rps/jps: an array of pointers to ``*probe`` data structures
+- kps/rps: an array of pointers to ``*probe`` data structures
 - num: the number of the array entries.
 
 .. note::
@@ -566,12 +586,11 @@ the same handler) may run concurrently on different CPUs.
 Kprobes does not use mutexes or allocate memory except during
 registration and unregistration.
 
-Probe handlers are run with preemption disabled.  Depending on the
-architecture and optimization state, handlers may also run with
-interrupts disabled (e.g., kretprobe handlers and optimized kprobe
-handlers run without interrupt disabled on x86/x86-64).  In any case,
-your handler should not yield the CPU (e.g., by attempting to acquire
-a semaphore).
+Probe handlers are run with preemption disabled or interrupt disabled,
+which depends on the architecture and optimization state.  (e.g.,
+kretprobe handlers and optimized kprobe handlers run without interrupt
+disabled on x86/x86-64).  In any case, your handler should not yield
+the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O).
 
 Since a return probe is implemented by replacing the return
 address with the trampoline's address, stack backtraces and calls
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index a02d6bbfc9d0..0d8d7ef131e9 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -2179,32 +2179,41 @@ or:
 	event_indicated = 1;
 	wake_up_process(event_daemon);
 
-A write memory barrier is implied by wake_up() and co.  if and only if they
-wake something up.  The barrier occurs before the task state is cleared, and so
-sits between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+A general memory barrier is executed by wake_up() if it wakes something up.
+If it doesn't wake anything up then a memory barrier may or may not be
+executed; you must not rely on it.  The barrier occurs before the task state
+is accessed, in particular, it sits between the STORE to indicate the event
+and the STORE to set TASK_RUNNING:
 
-	CPU 1				CPU 2
+	CPU 1 (Sleeper)			CPU 2 (Waker)
 	===============================	===============================
 	set_current_state();		STORE event_indicated
 	  smp_store_mb();		wake_up();
-	    STORE current->state	  <write barrier>
-	    <general barrier>		  STORE current->state
-	LOAD event_indicated
+	    STORE current->state	  ...
+	    <general barrier>		  <general barrier>
+	LOAD event_indicated		  if ((LOAD task->state) & TASK_NORMAL)
+					    STORE task->state
 
-To repeat, this write memory barrier is present if and only if something
-is actually awakened.  To see this, consider the following sequence of
-events, where X and Y are both initially zero:
+where "task" is the thread being woken up and it equals CPU 1's "current".
+
+To repeat, a general memory barrier is guaranteed to be executed by wake_up()
+if something is actually awakened, but otherwise there is no such guarantee.
+To see this, consider the following sequence of events, where X and Y are both
+initially zero:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	X = 1;				STORE event_indicated
+	X = 1;				Y = 1;
 	smp_mb();			wake_up();
-	Y = 1;				wait_event(wq, Y == 1);
-	wake_up();			  load from Y sees 1, no memory barrier
-					load from X might see 0
+	LOAD Y				LOAD X
+
+If a wakeup does occur, one (at least) of the two loads must see 1.  If, on
+the other hand, a wakeup does not occur, both loads might see 0.
 
-In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed
-to see 1.
+wake_up_process() always executes a general memory barrier.  The barrier again
+occurs before the task state is accessed.  In particular, if the wake_up() in
+the previous snippet were replaced by a call to wake_up_process() then one of
+the two loads would be guaranteed to see 1.
 
 The available waker functions include:
 
@@ -2224,6 +2233,8 @@ The available waker functions include:
 	wake_up_poll();
 	wake_up_process();
 
+In terms of memory ordering, these functions all provide the same guarantees of
+a wake_up() (or stronger).
 
 [!] Note that the memory barriers implied by the sleeper and the waker do _not_
 order multiple stores before the wake-up with respect to loads of those stored
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index c13214d073a4..d3e5dd26db12 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -1490,7 +1490,7 @@ To remove an ARP target:
 
 To configure the interval between learning packet transmits:
 # echo 12 > /sys/class/net/bond0/bonding/lp_interval
-	NOTE: the lp_inteval is the number of seconds between instances where
+	NOTE: the lp_interval is the number of seconds between instances where
 the bonding driver sends learning packets to each slaves peer switch.  The
 default interval is 1 second.
 
diff --git a/Documentation/networking/dpaa2/overview.rst b/Documentation/networking/dpaa2/overview.rst
index 79fede4447d6..d638b5a8aadd 100644
--- a/Documentation/networking/dpaa2/overview.rst
+++ b/Documentation/networking/dpaa2/overview.rst
@@ -1,5 +1,6 @@
 .. include:: <isonum.txt>
 
+=========================================================
 DPAA2 (Data Path Acceleration Architecture Gen2) Overview
 =========================================================
 
diff --git a/Documentation/networking/e100.rst b/Documentation/networking/e100.rst
index d4d837027925..f81111eba9c5 100644
--- a/Documentation/networking/e100.rst
+++ b/Documentation/networking/e100.rst
@@ -1,3 +1,4 @@
+==============================================================
 Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
 ==============================================================
 
@@ -46,123 +47,131 @@ Driver Configuration Parameters
 The default value for each parameter is generally the recommended setting,
 unless otherwise noted.
 
-Rx Descriptors: Number of receive descriptors. A receive descriptor is a data
+Rx Descriptors:
+   Number of receive descriptors. A receive descriptor is a data
    structure that describes a receive buffer and its attributes to the network
    controller. The data in the descriptor is used by the controller to write
    data from the controller to host memory. In the 3.x.x driver the valid range
    for this parameter is 64-256. The default value is 256. This parameter can be
    changed using the command::
 
-   ethtool -G eth? rx n
+     ethtool -G eth? rx n
 
    Where n is the number of desired Rx descriptors.
 
-Tx Descriptors: Number of transmit descriptors. A transmit descriptor is a data
+Tx Descriptors:
+   Number of transmit descriptors. A transmit descriptor is a data
    structure that describes a transmit buffer and its attributes to the network
    controller. The data in the descriptor is used by the controller to read
    data from the host memory to the controller. In the 3.x.x driver the valid
    range for this parameter is 64-256. The default value is 128. This parameter
    can be changed using the command::
 
-   ethtool -G eth? tx n
+     ethtool -G eth? tx n
 
    Where n is the number of desired Tx descriptors.
 
-Speed/Duplex: The driver auto-negotiates the link speed and duplex settings by
+Speed/Duplex:
+   The driver auto-negotiates the link speed and duplex settings by
    default. The ethtool utility can be used as follows to force speed/duplex.::
 
-   ethtool -s eth?  autoneg off speed {10|100} duplex {full|half}
+     ethtool -s eth?  autoneg off speed {10|100} duplex {full|half}
 
    NOTE: setting the speed/duplex to incorrect values will cause the link to
    fail.
 
-Event Log Message Level:  The driver uses the message level flag to log events
+Event Log Message Level:
+   The driver uses the message level flag to log events
    to syslog. The message level can be set at driver load time. It can also be
    set using the command::
 
-   ethtool -s eth? msglvl n
+     ethtool -s eth? msglvl n
 
 
 Additional Configurations
 =========================
 
-  Configuring the Driver on Different Distributions
-  -------------------------------------------------
+Configuring the Driver on Different Distributions
+-------------------------------------------------
 
-  Configuring a network driver to load properly when the system is started is
-  distribution dependent. Typically, the configuration process involves adding
-  an alias line to /etc/modprobe.d/*.conf as well as editing other system
-  startup scripts and/or configuration files.  Many popular Linux
-  distributions ship with tools to make these changes for you. To learn the
-  proper way to configure a network device for your system, refer to your
-  distribution documentation.  If during this process you are asked for the
-  driver or module name, the name for the Linux Base Driver for the Intel
-  PRO/100 Family of Adapters is e100.
+Configuring a network driver to load properly when the system is started
+is distribution dependent.  Typically, the configuration process involves
+adding an alias line to `/etc/modprobe.d/*.conf` as well as editing other
+system startup scripts and/or configuration files.  Many popular Linux
+distributions ship with tools to make these changes for you.  To learn
+the proper way to configure a network device for your system, refer to
+your distribution documentation.  If during this process you are asked
+for the driver or module name, the name for the Linux Base Driver for
+the Intel PRO/100 Family of Adapters is e100.
 
-  As an example, if you install the e100 driver for two PRO/100 adapters
-  (eth0 and eth1), add the following to a configuration file in /etc/modprobe.d/
+As an example, if you install the e100 driver for two PRO/100 adapters
+(eth0 and eth1), add the following to a configuration file in
+/etc/modprobe.d/::
 
        alias eth0 e100
        alias eth1 e100
 
-  Viewing Link Messages
-  ---------------------
-  In order to see link messages and other Intel driver information on your
-  console, you must set the dmesg level up to six. This can be done by
-  entering the following on the command line before loading the e100 driver::
+Viewing Link Messages
+---------------------
+
+In order to see link messages and other Intel driver information on your
+console, you must set the dmesg level up to six.  This can be done by
+entering the following on the command line before loading the e100
+driver::
 
        dmesg -n 6
 
-  If you wish to see all messages issued by the driver, including debug
-  messages, set the dmesg level to eight.
+If you wish to see all messages issued by the driver, including debug
+messages, set the dmesg level to eight.
 
-  NOTE: This setting is not saved across reboots.
+NOTE: This setting is not saved across reboots.
 
+ethtool
+-------
 
-  ethtool
-  -------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information.  The ethtool
+version 1.6 or later is required for this functionality.
 
-  The driver utilizes the ethtool interface for driver configuration and
-  diagnostics, as well as displaying statistical information.  The ethtool
-  version 1.6 or later is required for this functionality.
+The latest release of ethtool can be found from
+https://www.kernel.org/pub/software/network/ethtool/
 
-  The latest release of ethtool can be found from
-  https://www.kernel.org/pub/software/network/ethtool/
+Enabling Wake on LAN* (WoL)
+---------------------------
+WoL is provided through the ethtool* utility.  For instructions on
+enabling WoL with ethtool, refer to the ethtool man page.  WoL will be
+enabled on the system during the next shut down or reboot.  For this
+driver version, in order to enable WoL, the e100 driver must be loaded
+when shutting down or rebooting the system.
 
-  Enabling Wake on LAN* (WoL)
-  ---------------------------
-  WoL is provided through the ethtool* utility.  For instructions on enabling
-  WoL with ethtool, refer to the ethtool man page.
+NAPI
+----
 
-  WoL will be enabled on the system during the next shut down or reboot. For
-  this driver version, in order to enable WoL, the e100 driver must be
-  loaded when shutting down or rebooting the system.
+NAPI (Rx polling mode) is supported in the e100 driver.
 
-  NAPI
-  ----
+See https://wiki.linuxfoundation.org/networking/napi for more
+information on NAPI.
 
-  NAPI (Rx polling mode) is supported in the e100 driver.
+Multiple Interfaces on Same Ethernet Broadcast Network
+------------------------------------------------------
 
-  See https://wiki.linuxfoundation.org/networking/napi for more information
-  on NAPI.
+Due to the default ARP behavior on Linux, it is not possible to have one
+system on two IP networks in the same Ethernet broadcast domain
+(non-partitioned switch) behave as expected.  All Ethernet interfaces
+will respond to IP traffic for any IP address assigned to the system.
+This results in unbalanced receive traffic.
 
-  Multiple Interfaces on Same Ethernet Broadcast Network
-  ------------------------------------------------------
+If you have multiple interfaces in a server, either turn on ARP
+filtering by
 
-  Due to the default ARP behavior on Linux, it is not possible to have
-  one system on two IP networks in the same Ethernet broadcast domain
-  (non-partitioned switch) behave as expected. All Ethernet interfaces
-  will respond to IP traffic for any IP address assigned to the system.
-  This results in unbalanced receive traffic.
+(1) entering::
 
-  If you have multiple interfaces in a server, either turn on ARP
-  filtering by
+	echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
 
-  (1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
-      (this only works if your kernel's version is higher than 2.4.5), or
+    (this only works if your kernel's version is higher than 2.4.5), or
 
-  (2) installing the interfaces in separate broadcast domains (either
-      in different switches or in a switch partitioned to VLANs).
+(2) installing the interfaces in separate broadcast domains (either
+    in different switches or in a switch partitioned to VLANs).
 
 
 Support
diff --git a/Documentation/networking/e1000.rst b/Documentation/networking/e1000.rst
index 616848940e63..f10dd4086921 100644
--- a/Documentation/networking/e1000.rst
+++ b/Documentation/networking/e1000.rst
@@ -1,3 +1,4 @@
+===========================================================
 Linux* Base Driver for Intel(R) Ethernet Network Connection
 ===========================================================
 
@@ -33,7 +34,8 @@ Command Line Parameters
 The default value for each parameter is generally the recommended setting,
 unless otherwise noted.
 
-NOTES:  For more information about the AutoNeg, Duplex, and Speed
+NOTES:
+	For more information about the AutoNeg, Duplex, and Speed
         parameters, see the "Speed and Duplex Configuration" section in
         this document.
 
@@ -44,22 +46,27 @@ NOTES:  For more information about the AutoNeg, Duplex, and Speed
 
 AutoNeg
 -------
+
 (Supported only on adapters with copper connections)
-Valid Range:   0x01-0x0F, 0x20-0x2F
-Default Value: 0x2F
+
+:Valid Range:   0x01-0x0F, 0x20-0x2F
+:Default Value: 0x2F
 
 This parameter is a bit-mask that specifies the speed and duplex settings
 advertised by the adapter.  When this parameter is used, the Speed and
 Duplex parameters must not be specified.
 
-NOTE:  Refer to the Speed and Duplex section of this readme for more
+NOTE:
+       Refer to the Speed and Duplex section of this readme for more
        information on the AutoNeg parameter.
 
 Duplex
 ------
+
 (Supported only on adapters with copper connections)
-Valid Range:   0-2 (0=auto-negotiate, 1=half, 2=full)
-Default Value: 0
+
+:Valid Range:   0-2 (0=auto-negotiate, 1=half, 2=full)
+:Default Value: 0
 
 This defines the direction in which data is allowed to flow.  Can be
 either one or two-directional.  If both Duplex and the link partner are
@@ -69,18 +76,22 @@ duplex.
 
 FlowControl
 -----------
-Valid Range:   0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
-Default Value: Reads flow control settings from the EEPROM
+
+:Valid Range:   0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
+:Default Value: Reads flow control settings from the EEPROM
 
 This parameter controls the automatic generation(Tx) and response(Rx)
 to Ethernet PAUSE frames.
 
 InterruptThrottleRate
 ---------------------
+
 (not supported on Intel(R) 82542, 82543 or 82544-based adapters)
-Valid Range:   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
-                                 4=simplified balancing)
-Default Value: 3
+
+:Valid Range:
+   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+   4=simplified balancing)
+:Default Value: 3
 
 The driver can limit the amount of interrupts per second that the adapter
 will generate for incoming packets. It does this by writing a value to the
@@ -134,13 +145,15 @@ Setting InterruptThrottleRate to 0 turns off any interrupt moderation
 and may improve small packet latency, but is generally not suitable
 for bulk throughput traffic.
 
-NOTE:  InterruptThrottleRate takes precedence over the TxAbsIntDelay and
+NOTE:
+       InterruptThrottleRate takes precedence over the TxAbsIntDelay and
        RxAbsIntDelay parameters.  In other words, minimizing the receive
        and/or transmit absolute delays does not force the controller to
        generate more interrupts than what the Interrupt Throttle Rate
        allows.
 
-CAUTION:  If you are using the Intel(R) PRO/1000 CT Network Connection
+CAUTION:
+          If you are using the Intel(R) PRO/1000 CT Network Connection
           (controller 82547), setting InterruptThrottleRate to a value
           greater than 75,000, may hang (stop transmitting) adapters
           under certain network conditions.  If this occurs a NETDEV
@@ -150,7 +163,8 @@ CAUTION:  If you are using the Intel(R) PRO/1000 CT Network Connection
           hang, ensure that InterruptThrottleRate is set no greater
           than 75,000 and is not set to 0.
 
-NOTE:  When e1000 is loaded with default settings and multiple adapters
+NOTE:
+       When e1000 is loaded with default settings and multiple adapters
        are in use simultaneously, the CPU utilization may increase non-
        linearly.  In order to limit the CPU utilization without impacting
        the overall throughput, we recommend that you load the driver as
@@ -167,9 +181,11 @@ NOTE:  When e1000 is loaded with default settings and multiple adapters
 
 RxDescriptors
 -------------
-Valid Range:   48-256 for 82542 and 82543-based adapters
-               48-4096 for all other supported adapters
-Default Value: 256
+
+:Valid Range:
+ - 48-256 for 82542 and 82543-based adapters
+ - 48-4096 for all other supported adapters
+:Default Value: 256
 
 This value specifies the number of receive buffer descriptors allocated
 by the driver.  Increasing this value allows the driver to buffer more
@@ -179,15 +195,17 @@ Each descriptor is 16 bytes.  A receive buffer is also allocated for each
 descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending
 on the MTU setting. The maximum MTU size is 16110.
 
-NOTE:  MTU designates the frame size.  It only needs to be set for Jumbo
+NOTE:
+       MTU designates the frame size.  It only needs to be set for Jumbo
        Frames.  Depending on the available system resources, the request
        for a higher number of receive descriptors may be denied.  In this
        case, use a lower number.
 
 RxIntDelay
 ----------
-Valid Range:   0-65535 (0=off)
-Default Value: 0
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 0
 
 This value delays the generation of receive interrupts in units of 1.024
 microseconds.  Receive interrupt reduction can improve CPU efficiency if
@@ -197,7 +215,8 @@ of TCP traffic.  If the system is reporting dropped receives, this value
 may be set too high, causing the driver to run out of available receive
 descriptors.
 
-CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
+CAUTION:
+          When setting RxIntDelay to a value other than 0, adapters may
           hang (stop transmitting) under certain network conditions.  If
           this occurs a NETDEV WATCHDOG message is logged in the system
           event log.  In addition, the controller is automatically reset,
@@ -206,9 +225,11 @@ CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
 
 RxAbsIntDelay
 -------------
+
 (This parameter is supported only on 82540, 82545 and later adapters.)
-Valid Range:   0-65535 (0=off)
-Default Value: 128
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 128
 
 This value, in units of 1.024 microseconds, limits the delay in which a
 receive interrupt is generated.  Useful only if RxIntDelay is non-zero,
@@ -219,9 +240,11 @@ conditions.
 
 Speed
 -----
+
 (This parameter is supported only on adapters with copper connections.)
-Valid Settings: 0, 10, 100, 1000
-Default Value:  0 (auto-negotiate at all supported speeds)
+
+:Valid Settings: 0, 10, 100, 1000
+:Default Value:  0 (auto-negotiate at all supported speeds)
 
 Speed forces the line speed to the specified value in megabits per second
 (Mbps).  If this parameter is not specified or is set to 0 and the link
@@ -230,22 +253,26 @@ speed.  Duplex should also be set when Speed is set to either 10 or 100.
 
 TxDescriptors
 -------------
-Valid Range:   48-256 for 82542 and 82543-based adapters
-               48-4096 for all other supported adapters
-Default Value: 256
+
+:Valid Range:
+  - 48-256 for 82542 and 82543-based adapters
+  - 48-4096 for all other supported adapters
+:Default Value: 256
 
 This value is the number of transmit descriptors allocated by the driver.
 Increasing this value allows the driver to queue more transmits.  Each
 descriptor is 16 bytes.
 
-NOTE:  Depending on the available system resources, the request for a
+NOTE:
+       Depending on the available system resources, the request for a
        higher number of transmit descriptors may be denied.  In this case,
        use a lower number.
 
 TxIntDelay
 ----------
-Valid Range:   0-65535 (0=off)
-Default Value: 8
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 8
 
 This value delays the generation of transmit interrupts in units of
 1.024 microseconds.  Transmit interrupt reduction can improve CPU
@@ -255,9 +282,11 @@ causing the driver to run out of available transmit descriptors.
 
 TxAbsIntDelay
 -------------
+
 (This parameter is supported only on 82540, 82545 and later adapters.)
-Valid Range:   0-65535 (0=off)
-Default Value: 32
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 32
 
 This value, in units of 1.024 microseconds, limits the delay in which a
 transmit interrupt is generated.  Useful only if TxIntDelay is non-zero,
@@ -268,18 +297,21 @@ network conditions.
 
 XsumRX
 ------
+
 (This parameter is NOT supported on the 82542-based adapter.)
-Valid Range:   0-1
-Default Value: 1
+
+:Valid Range:   0-1
+:Default Value: 1
 
 A value of '1' indicates that the driver should enable IP checksum
 offload for received packets (both UDP and TCP) to the adapter hardware.
 
 Copybreak
 ---------
-Valid Range:   0-xxxxxxx (0=off)
-Default Value: 256
-Usage: modprobe e1000.ko copybreak=128
+
+:Valid Range:   0-xxxxxxx (0=off)
+:Default Value: 256
+:Usage: modprobe e1000.ko copybreak=128
 
 Driver copies all packets below or equaling this size to a fresh RX
 buffer before handing it up the stack.
@@ -291,8 +323,9 @@ it is also available during runtime at
 
 SmartPowerDownEnable
 --------------------
-Valid Range: 0-1
-Default Value:  0 (disabled)
+
+:Valid Range: 0-1
+:Default Value:  0 (disabled)
 
 Allows PHY to turn off in lower power states. The user can turn off
 this parameter in supported chipsets.
@@ -308,14 +341,14 @@ fiber interface board only links at 1000 Mbps full-duplex.
 
 For copper-based boards, the keywords interact as follows:
 
-  The default operation is auto-negotiate.  The board advertises all
+- The default operation is auto-negotiate.  The board advertises all
   supported speed and duplex combinations, and it links at the highest
   common speed and duplex mode IF the link partner is set to auto-negotiate.
 
-  If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps
+- If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps
   is advertised (The 1000BaseT spec requires auto-negotiation.)
 
-  If Speed = 10 or 100, then both Speed and Duplex should be set.  Auto-
+- If Speed = 10 or 100, then both Speed and Duplex should be set.  Auto-
   negotiation is disabled, and the AutoNeg parameter is ignored.  Partner
   SHOULD also be forced.
 
@@ -327,13 +360,15 @@ process.
 The parameter may be specified as either a decimal or hexadecimal value as
 determined by the bitmap below.
 
+============== ====== ====== ======= ======= ====== ====== ======= ======
 Bit position   7      6      5       4       3      2      1       0
 Decimal Value  128    64     32      16      8      4      2       1
 Hex value      80     40     20      10      8      4      2       1
 Speed (Mbps)   N/A    N/A    1000    N/A     100    100    10      10
 Duplex                       Full            Full   Half   Full    Half
+============== ====== ====== ======= ======= ====== ====== ======= ======
 
-Some examples of using AutoNeg:
+Some examples of using AutoNeg::
 
   modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half)
   modprobe e1000 AutoNeg=1 (Same as above)
@@ -354,8 +389,9 @@ previously mentioned to force the adapter to the same speed and duplex.
 Additional Configurations
 =========================
 
-  Jumbo Frames
-  ------------
+Jumbo Frames
+------------
+
   Jumbo Frames support is enabled by changing the MTU to a value larger than
   the default of 1500.  Use the ifconfig command to increase the MTU size.
   For example::
@@ -367,11 +403,11 @@ Additional Configurations
 
        MTU=9000
 
-   to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>.  This example
-   applies to the Red Hat distributions; other distributions may store this
-   setting in a different location.
+  to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>.  This example
+  applies to the Red Hat distributions; other distributions may store this
+  setting in a different location.
 
-  Notes:
+Notes:
   Degradation in throughput performance may be observed in some Jumbo frames
   environments. If this is observed, increasing the application's socket buffer
   size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
@@ -385,12 +421,14 @@ Additional Configurations
     poor performance or loss of link.
 
   - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
-    support Jumbo Frames. These correspond to the following product names:
+    support Jumbo Frames. These correspond to the following product names::
+
      Intel(R) PRO/1000 Gigabit Server Adapter
      Intel(R) PRO/1000 PM Network Connection
 
-  ethtool
-  -------
+ethtool
+-------
+
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information.  The ethtool
   version 1.6 or later is required for this functionality.
@@ -398,8 +436,9 @@ Additional Configurations
   The latest release of ethtool can be found from
   https://www.kernel.org/pub/software/network/ethtool/
 
-  Enabling Wake on LAN* (WoL)
-  ---------------------------
+Enabling Wake on LAN* (WoL)
+---------------------------
+
   WoL is configured through the ethtool* utility.
 
   WoL will be enabled on the system during the next shut down or reboot.
diff --git a/Documentation/networking/strparser.txt b/Documentation/networking/strparser.txt
index 13081b3decef..a7d354ddda7b 100644
--- a/Documentation/networking/strparser.txt
+++ b/Documentation/networking/strparser.txt
@@ -48,7 +48,7 @@ void strp_pause(struct strparser *strp)
      Temporarily pause a stream parser. Message parsing is suspended
      and no new messages are delivered to the upper layer.
 
-void strp_pause(struct strparser *strp)
+void strp_unpause(struct strparser *strp)
 
      Unpause a paused stream parser.
 
diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt
index 69556f0d494b..530fed08de2c 100644
--- a/Documentation/nommu-mmap.txt
+++ b/Documentation/nommu-mmap.txt
@@ -47,7 +47,7 @@ and it's also much more restricted in the latter case:
            appropriate mapping protection capabilities. Ramfs, romfs, cramfs
            and mtd might all permit this.
 
-	 - If the backing device device can't or won't permit direct sharing,
+	 - If the backing device can't or won't permit direct sharing,
            but does have the NOMMU_MAP_COPY capability, then a copy of the
            appropriate bit of the file will be read into a contiguous bit of
            memory and any extraneous space beyond the EOF will be cleared
diff --git a/Documentation/power/freezing-of-tasks.txt b/Documentation/power/freezing-of-tasks.txt
index af005770e767..cd283190855a 100644
--- a/Documentation/power/freezing-of-tasks.txt
+++ b/Documentation/power/freezing-of-tasks.txt
@@ -204,26 +204,26 @@ VI. Are there any precautions to be taken to prevent freezing failures?
 
 Yes, there are.
 
-First of all, grabbing the 'pm_mutex' lock to mutually exclude a piece of code
+First of all, grabbing the 'system_transition_mutex' lock to mutually exclude a piece of code
 from system-wide sleep such as suspend/hibernation is not encouraged.
 If possible, that piece of code must instead hook onto the suspend/hibernation
 notifiers to achieve mutual exclusion. Look at the CPU-Hotplug code
 (kernel/cpu.c) for an example.
 
-However, if that is not feasible, and grabbing 'pm_mutex' is deemed necessary,
-it is strongly discouraged to directly call mutex_[un]lock(&pm_mutex) since
+However, if that is not feasible, and grabbing 'system_transition_mutex' is deemed necessary,
+it is strongly discouraged to directly call mutex_[un]lock(&system_transition_mutex) since
 that could lead to freezing failures, because if the suspend/hibernate code
-successfully acquired the 'pm_mutex' lock, and hence that other entity failed
+successfully acquired the 'system_transition_mutex' lock, and hence that other entity failed
 to acquire the lock, then that task would get blocked in TASK_UNINTERRUPTIBLE
 state. As a consequence, the freezer would not be able to freeze that task,
 leading to freezing failure.
 
 However, the [un]lock_system_sleep() APIs are safe to use in this scenario,
 since they ask the freezer to skip freezing this task, since it is anyway
-"frozen enough" as it is blocked on 'pm_mutex', which will be released
+"frozen enough" as it is blocked on 'system_transition_mutex', which will be released
 only after the entire suspend/hibernation sequence is complete.
 So, to summarize, use [un]lock_system_sleep() instead of directly using
-mutex_[un]lock(&pm_mutex). That would prevent freezing failures.
+mutex_[un]lock(&system_transition_mutex). That would prevent freezing failures.
 
 V. Miscellaneous
 /sys/power/pm_freeze_timeout controls how long it will cost at most to freeze
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
index 6f55eb960a6d..a8751b8df10e 100644
--- a/Documentation/power/suspend-and-cpuhotplug.txt
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -32,7 +32,7 @@ More details follow:
                                     sysfs file
                                         |
                                         v
-                               Acquire pm_mutex lock
+                               Acquire system_transition_mutex lock
                                         |
                                         v
                              Send PM_SUSPEND_PREPARE
@@ -96,10 +96,10 @@ execution during resume):
 
 * thaw tasks
 * send PM_POST_SUSPEND notifications
-* Release pm_mutex lock.
+* Release system_transition_mutex lock.
 
 
-It is to be noted here that the pm_mutex lock is acquired at the very
+It is to be noted here that the system_transition_mutex lock is acquired at the very
 beginning, when we are just starting out to suspend, and then released only
 after the entire cycle is complete (i.e., suspend + resume).
 
diff --git a/Documentation/process/2.Process.rst b/Documentation/process/2.Process.rst
index a9c46dd0706b..51d0349c7809 100644
--- a/Documentation/process/2.Process.rst
+++ b/Documentation/process/2.Process.rst
@@ -134,7 +134,7 @@ and their maintainers are:
 	4.4	Greg Kroah-Hartman	(very long-term stable kernel)
 	4.9	Greg Kroah-Hartman
 	4.14	Greg Kroah-Hartman
-	======  ======================  ===========================
+	======  ======================  ==============================
 
 The selection of a kernel for long-term support is purely a matter of a
 maintainer having the need and the time to maintain that release.  There
diff --git a/Documentation/process/howto.rst b/Documentation/process/howto.rst
index 3df55811b916..130bf0f48875 100644
--- a/Documentation/process/howto.rst
+++ b/Documentation/process/howto.rst
@@ -85,7 +85,7 @@ linux-api@vger.kernel.org.
 Here is a list of files that are in the kernel source tree that are
 required reading:
 
-  README
+  :ref:`Documentation/admin-guide/README.rst <readme>`
     This file gives a short background on the Linux kernel and describes
     what is necessary to do to configure and build the kernel.  People
     who are new to the kernel should start here.
diff --git a/Documentation/process/management-style.rst b/Documentation/process/management-style.rst
index 45595fd8a66b..85ef8ca8f639 100644
--- a/Documentation/process/management-style.rst
+++ b/Documentation/process/management-style.rst
@@ -105,7 +105,7 @@ to admit that you are stupid when you haven't **yet** done the really
 stupid thing.
 
 Then, when it really does turn out to be stupid, people just roll their
-eyes and say "Oops, he did it again".
+eyes and say "Oops, not again".
 
 This preemptive admission of incompetence might also make the people who
 actually do the work also think twice about whether it's worth doing or
@@ -172,10 +172,10 @@ To solve this problem, you really only have two options:
    might even be amused.
 
 The option of being unfailingly polite really doesn't exist. Nobody will
-trust somebody who is so clearly hiding his true character.
+trust somebody who is so clearly hiding their true character.
 
 .. [#f2] Paul Simon sang "Fifty Ways to Leave Your Lover", because quite
-  frankly, "A Million Ways to Tell a Developer He Is a D*ckhead" doesn't
+  frankly, "A Million Ways to Tell a Developer They're a D*ckhead" doesn't
   scan nearly as well.  But I'm sure he thought about it.
 
 
@@ -219,15 +219,16 @@ Things will go wrong, and people want somebody to blame. Tag, you're it.
 
 It's not actually that hard to accept the blame, especially if people
 kind of realize that it wasn't **all** your fault.  Which brings us to the
-best way of taking the blame: do it for another guy. You'll feel good
-for taking the fall, he'll feel good about not getting blamed, and the
-guy who lost his whole 36GB porn-collection because of your incompetence
-will grudgingly admit that you at least didn't try to weasel out of it.
-
-Then make the developer who really screwed up (if you can find him) know
-**in_private** that he screwed up.  Not just so he can avoid it in the
-future, but so that he knows he owes you one.  And, perhaps even more
-importantly, he's also likely the person who can fix it.  Because, let's
+best way of taking the blame: do it for someone else. You'll feel good
+for taking the fall, they'll feel good about not getting blamed, and the
+person who lost their whole 36GB porn-collection because of your
+incompetence will grudgingly admit that you at least didn't try to weasel
+out of it.
+
+Then make the developer who really screwed up (if you can find them) know
+**in_private** that they screwed up.  Not just so they can avoid it in the
+future, but so that they know they owe you one.  And, perhaps even more
+importantly, they're also likely the person who can fix it.  Because, let's
 face it, it sure ain't you.
 
 Taking the blame is also why you get to be manager in the first place.
diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst
index 4d83c1c0ca04..4a3cecc8ad38 100644
--- a/Documentation/sound/alsa-configuration.rst
+++ b/Documentation/sound/alsa-configuration.rst
@@ -1568,7 +1568,7 @@ joystick_io
 The driver requires firmware files ``turtlebeach/msndinit.bin`` and
 ``turtlebeach/msndperm.bin`` in the proper firmware directory.
 
-See Documentation/sound/oss/MultiSound for important information
+See Documentation/sound/cards/multisound.sh for important information
 about this driver.  Note that it has been discontinued, but the 
 Voyetra Turtle Beach knowledge base entry for it is still available
 at
diff --git a/Documentation/sound/cards/multisound.sh b/Documentation/sound/cards/multisound.sh
new file mode 100755
index 000000000000..a915a1affcde
--- /dev/null
+++ b/Documentation/sound/cards/multisound.sh
@@ -0,0 +1,1139 @@
+#! /bin/sh
+#
+#  Turtle Beach MultiSound Driver Notes
+#  -- Andrew Veliath <andrewtv@usa.net>
+#
+#  Last update:                      September 10, 1998
+#  Corresponding msnd driver:        0.8.3
+#
+# ** This file is a README (top part) and shell archive (bottom part).
+#    The corresponding archived utility sources can be unpacked by
+#    running `sh MultiSound' (the utilities are only needed for the
+#    Pinnacle and Fiji cards). **
+#
+#
+#  -=-=- Getting Firmware -=-=-
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  See the section `Obtaining and Creating Firmware Files' in this
+#  document for instructions on obtaining the necessary firmware
+#  files.
+#
+#
+#  Supported Features
+#  ~~~~~~~~~~~~~~~~~~
+#
+#  Currently, full-duplex digital audio (/dev/dsp only, /dev/audio is
+#  not currently available) and mixer functionality (/dev/mixer) are
+#  supported (memory mapped digital audio is not yet supported).
+#  Digital transfers and monitoring can be done as well if you have
+#  the digital daughterboard (see the section on using the S/PDIF port
+#  for more information).
+#
+#  Support for the Turtle Beach MultiSound Hurricane architecture is
+#  composed of the following modules (these can also operate compiled
+#  into the kernel):
+#
+#  snd-msnd-lib           - MultiSound base (requires snd)
+#
+#  snd-msnd-classic       - Base audio/mixer support for Classic, Monetery and
+#                           Tahiti cards
+#
+#  snd-msnd-pinnacle      - Base audio/mixer support for Pinnacle and Fiji cards
+#
+#
+#  Important Notes - Read Before Using
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  The firmware files are not included (may change in future).  You
+#  must obtain these images from Turtle Beach (they are included in
+#  the MultiSound Development Kits), and place them in /etc/sound for
+#  example, and give the full paths in the Linux configuration.  If
+#  you are compiling in support for the MultiSound driver rather than
+#  using it as a module, these firmware files must be accessible
+#  during kernel compilation.
+#
+#  Please note these files must be binary files, not assembler.  See
+#  the section later in this document for instructions to obtain these
+#  files.
+#
+#
+#  Configuring Card Resources
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  ** This section is very important, as your card may not work at all
+#     or your machine may crash if you do not do this correctly. **
+#
+#  * Classic/Monterey/Tahiti
+#
+#  These cards are configured through the driver snd-msnd-classic.  You must
+#  know the io port, then the driver will select the irq and memory resources
+#  on the card.  It is up to you to know if these are free locations or now,
+#  a conflict can lock the machine up.
+#
+#  * Pinnacle/Fiji
+#
+#  The Pinnacle and Fiji cards have an extra config port, either
+#  0x250, 0x260 or 0x270.  This port can be disabled to have the card
+#  configured strictly through PnP, however you lose the ability to
+#  access the IDE controller and joystick devices on this card when
+#  using PnP.  The included pinnaclecfg program in this shell archive
+#  can be used to configure the card in non-PnP mode, and in PnP mode
+#  you can use isapnptools.  These are described briefly here.
+#
+#  pinnaclecfg is not required; you can use the snd-msnd-pinnacle module
+#  to fully configure the card as well.  However, pinnaclecfg can be
+#  used to change the resource values of a particular device after the
+#  snd-msnd-pinnacle module has been loaded.  If you are compiling the
+#  driver into the kernel, you must set these values during compile
+#  time, however other peripheral resource values can be changed with
+#  the pinnaclecfg program after the kernel is loaded.
+#
+#
+#  *** PnP mode
+#
+#  Use pnpdump to obtain a sample configuration if you can; I was able
+#  to obtain one with the command `pnpdump 1 0x203' -- this may vary
+#  for you (running pnpdump by itself did not work for me).  Then,
+#  edit this file and use isapnp to uncomment and set the card values.
+#  Use these values when inserting the snd-msnd-pinnacle module.  Using
+#  this method, you can set the resources for the DSP and the Kurzweil
+#  synth (Pinnacle).  Since Linux does not directly support PnP
+#  devices, you may have difficulty when using the card in PnP mode
+#  when it the driver is compiled into the kernel.  Using non-PnP mode
+#  is preferable in this case.
+#
+#  Here is an example mypinnacle.conf for isapnp that sets the card to
+#  io base 0x210, irq 5 and mem 0xd8000, and also sets the Kurzweil
+#  synth to 0x330 and irq 9 (may need editing for your system):
+#
+#  (READPORT 0x0203)
+#  (CSN 2)
+#  (IDENTIFY *)
+#
+#  # DSP
+#  (CONFIGURE BVJ0440/-1 (LD 0
+#          (INT 0 (IRQ 5 (MODE +E))) (IO 0 (BASE 0x0210)) (MEM 0 (BASE 0x0d8000))
+#          (ACT Y)))
+#
+#  # Kurzweil Synth (Pinnacle Only)
+#  (CONFIGURE BVJ0440/-1 (LD 1
+#          (IO 0 (BASE 0x0330)) (INT 0 (IRQ 9 (MODE +E)))
+#          (ACT Y)))
+#
+#  (WAITFORKEY)
+#
+#
+#  *** Non-PnP mode
+#
+#  The second way is by running the card in non-PnP mode.  This
+#  actually has some advantages in that you can access some other
+#  devices on the card, such as the joystick and IDE controller.  To
+#  configure the card, unpack this shell archive and build the
+#  pinnaclecfg program.  Using this program, you can assign the
+#  resource values to the card's devices, or disable the devices.  As
+#  an alternative to using pinnaclecfg, you can specify many of the
+#  configuration values when loading the snd-msnd-pinnacle module (or
+#  during kernel configuration when compiling the driver into the
+#  kernel).
+#
+#  If you specify cfg=0x250 for the snd-msnd-pinnacle module, it
+#  automatically configure the card to the given io, irq and memory
+#  values using that config port (the config port is jumper selectable
+#  on the card to 0x250, 0x260 or 0x270).
+#
+#  See the `snd-msnd-pinnacle Additional Options' section below for more
+#  information on these parameters (also, if you compile the driver
+#  directly into the kernel, these extra parameters can be useful
+#  here).
+#
+#
+# ** It is very easy to cause problems in your machine if you choose a
+#    resource value which is incorrect. **
+#
+#
+#  Examples
+#  ~~~~~~~~
+#
+#  * MultiSound Classic/Monterey/Tahiti:
+#
+#  modprobe snd
+#  insmod snd-msnd-lib
+#  insmod snd-msnd-classic io=0x290 irq=7 mem=0xd0000
+#
+#  * MultiSound Pinnacle in PnP mode:
+#
+#  modprobe snd
+#  insmod snd-msnd-lib
+#  isapnp mypinnacle.conf
+#  insmod snd-msnd-pinnacle io=0x210 irq=5 mem=0xd8000 <-- match mypinnacle.conf values
+#
+#  * MultiSound Pinnacle in non-PnP mode (replace 0x250 with your configuration port,
+#    one of 0x250, 0x260 or 0x270):
+#
+#  modprobe snd
+#  insmod snd-msnd-lib
+#  insmod snd-msnd-pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000
+#
+# * To use the MPU-compatible Kurzweil synth on the Pinnacle in PnP
+#   mode, add the following (assumes you did `isapnp mypinnacle.conf'):
+#
+#  insmod snd
+#  insmod mpu401 io=0x330 irq=9                    <-- match mypinnacle.conf values
+#
+# * To use the MPU-compatible Kurzweil synth on the Pinnacle in non-PnP
+#   mode, add the following.  Note how we first configure the peripheral's
+#   resources, _then_ install a Linux driver for it:
+#
+#  insmod snd
+#  pinnaclecfg 0x250 mpu 0x330 9
+#  insmod mpu401 io=0x330 irq=9
+#
+#  -- OR you can use the following sequence without pinnaclecfg in non-PnP mode:
+#
+#  modprobe snd
+#  insmod snd-msnd-lib
+#  insmod snd-msnd-pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000 mpu_io=0x330 mpu_irq=9
+#  insmod snd
+#  insmod mpu401 io=0x330 irq=9
+#
+# * To setup the joystick port on the Pinnacle in non-PnP mode (though
+#   you have to find the actual Linux joystick driver elsewhere), you
+#   can use pinnaclecfg:
+#
+#   pinnaclecfg 0x250 joystick 0x200
+#
+#  -- OR you can configure this using snd-msnd-pinnacle with the following:
+#
+#  modprobe snd
+#  insmod snd-msnd-lib
+#  insmod snd-msnd-pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000 joystick_io=0x200
+#
+#
+#  snd-msnd-classic, snd-msnd-pinnacle Required Options
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  If the following options are not given, the module will not load.
+#  Examine the kernel message log for informative error messages.
+#  WARNING--probing isn't supported so try to make sure you have the
+#  correct shared memory area, otherwise you may experience problems.
+#
+#  io                   I/O base of DSP, e.g. io=0x210
+#  irq                  IRQ number, e.g. irq=5
+#  mem                  Shared memory area, e.g. mem=0xd8000
+#
+#
+#  snd-msnd-classic, snd-msnd-pinnacle Additional Options
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  fifosize             The digital audio FIFOs, in kilobytes.  If not
+#                       specified, the default will be used.  Increasing
+#                       this value will reduce the chance of a FIFO
+#                       underflow at the expense of increasing overall
+#                       latency.  For example, fifosize=512 will
+#                       allocate 512kB read and write FIFOs (1MB total).
+#                       While this may reduce dropouts, a heavy machine
+#                       load will undoubtedly starve the FIFO of data
+#                       and you will eventually get dropouts.  One
+#                       option is to alter the scheduling priority of
+#                       the playback process, using `nice' or some form
+#                       of POSIX soft real-time scheduling.
+#
+#  calibrate_signal     Setting this to one calibrates the ADCs to the
+#                       signal, zero calibrates to the card (defaults
+#                       to zero).
+#
+#
+#  snd-msnd-pinnacle Additional Options
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  digital              Specify digital=1 to enable the S/PDIF input
+#                       if you have the digital daughterboard
+#                       adapter. This will enable access to the
+#                       DIGITAL1 input for the soundcard in the mixer.
+#                       Some mixer programs might have trouble setting
+#                       the DIGITAL1 source as an input.  If you have
+#                       trouble, you can try the setdigital.c program
+#                       at the bottom of this document.
+#
+#  cfg                  Non-PnP configuration port for the Pinnacle
+#                       and Fiji (typically 0x250, 0x260 or 0x270,
+#                       depending on the jumper configuration).  If
+#                       this option is omitted, then it is assumed
+#                       that the card is in PnP mode, and that the
+#                       specified DSP resource values are already
+#                       configured with PnP (i.e. it won't attempt to
+#                       do any sort of configuration).
+#
+#  When the Pinnacle is in non-PnP mode, you can use the following
+#  options to configure particular devices.  If a full specification
+#  for a device is not given, then the device is not configured.  Note
+#  that you still must use a Linux driver for any of these devices
+#  once their resources are setup (such as the Linux joystick driver,
+#  or the MPU401 driver from OSS for the Kurzweil synth).
+#
+#  mpu_io               I/O port of MPU (on-board Kurzweil synth)
+#  mpu_irq              IRQ of MPU (on-board Kurzweil synth)
+#  ide_io0		First I/O port of IDE controller
+#  ide_io1		Second I/O port of IDE controller
+#  ide_irq		IRQ IDE controller
+#  joystick_io          I/O port of joystick
+#
+#
+#  Obtaining and Creating Firmware Files
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#       For the Classic/Tahiti/Monterey
+#       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  Download to /tmp and unzip the following file from Turtle Beach:
+#
+#       ftp://ftp.voyetra.com/pub/tbs/msndcl/msndvkit.zip
+#
+#  When unzipped, unzip the file named MsndFiles.zip.  Then copy the
+#  following firmware files to /etc/sound (note the file renaming):
+#
+#    cp DSPCODE/MSNDINIT.BIN /etc/sound/msndinit.bin
+#    cp DSPCODE/MSNDPERM.REB /etc/sound/msndperm.bin
+#
+#  When configuring the Linux kernel, specify /etc/sound/msndinit.bin and
+#  /etc/sound/msndperm.bin for the two firmware files (Linux kernel
+#  versions older than 2.2 do not ask for firmware paths, and are
+#  hardcoded to /etc/sound).
+#
+#  If you are compiling the driver into the kernel, these files must
+#  be accessible during compilation, but will not be needed later.
+#  The files must remain, however, if the driver is used as a module.
+#
+#
+#       For the Pinnacle/Fiji
+#       ~~~~~~~~~~~~~~~~~~~~~
+#
+#  Download to /tmp and unzip the following file from Turtle Beach (be
+#  sure to use the entire URL; some have had trouble navigating to the
+#  URL):
+#
+#       ftp://ftp.voyetra.com/pub/tbs/pinn/pnddk100.zip
+#
+#  Unpack this shell archive, and run make in the created directory
+#  (you need a C compiler and flex to build the utilities).  This
+#  should give you the executables conv, pinnaclecfg and setdigital.
+#  conv is only used temporarily here to create the firmware files,
+#  while pinnaclecfg is used to configure the Pinnacle or Fiji card in
+#  non-PnP mode, and setdigital can be used to set the S/PDIF input on
+#  the mixer (pinnaclecfg and setdigital should be copied to a
+#  convenient place, possibly run during system initialization).
+#
+#  To generating the firmware files with the `conv' program, we create
+#  the binary firmware files by doing the following conversion
+#  (assuming the archive unpacked into a directory named PINNDDK):
+#
+#    ./conv < PINNDDK/dspcode/pndspini.asm > /etc/sound/pndspini.bin
+#    ./conv < PINNDDK/dspcode/pndsperm.asm > /etc/sound/pndsperm.bin
+#
+#  The conv (and conv.l) program is not needed after conversion and can
+#  be safely deleted.  Then, when configuring the Linux kernel, specify
+#  /etc/sound/pndspini.bin and /etc/sound/pndsperm.bin for the two
+#  firmware files (Linux kernel versions older than 2.2 do not ask for
+#  firmware paths, and are hardcoded to /etc/sound).
+#
+#  If you are compiling the driver into the kernel, these files must
+#  be accessible during compilation, but will not be needed later.
+#  The files must remain, however, if the driver is used as a module.
+#
+#
+#  Using Digital I/O with the S/PDIF Port
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  If you have a Pinnacle or Fiji with the digital daughterboard and
+#  want to set it as the input source, you can use this program if you
+#  have trouble trying to do it with a mixer program (be sure to
+#  insert the module with the digital=1 option, or say Y to the option
+#  during compiled-in kernel operation).  Upon selection of the S/PDIF
+#  port, you should be able monitor and record from it.
+#
+#  There is something to note about using the S/PDIF port.  Digital
+#  timing is taken from the digital signal, so if a signal is not
+#  connected to the port and it is selected as recording input, you
+#  will find PCM playback to be distorted in playback rate.  Also,
+#  attempting to record at a sampling rate other than the DAT rate may
+#  be problematic (i.e. trying to record at 8000Hz when the DAT signal
+#  is 44100Hz).  If you have a problem with this, set the recording
+#  input to analog if you need to record at a rate other than that of
+#  the DAT rate.
+#
+#
+#  -- Shell archive attached below, just run `sh MultiSound' to extract.
+#     Contains Pinnacle/Fiji utilities to convert firmware, configure
+#     in non-PnP mode, and select the DIGITAL1 input for the mixer.
+#
+#
+#!/bin/sh
+# This is a shell archive (produced by GNU sharutils 4.2).
+# To extract the files from this archive, save it to some FILE, remove
+# everything before the `!/bin/sh' line above, then type `sh FILE'.
+#
+# Made on 1998-12-04 10:07 EST by <andrewtv@ztransform.velsoft.com>.
+# Source directory was `/home/andrewtv/programming/pinnacle/pinnacle'.
+#
+# Existing files will *not* be overwritten unless `-c' is specified.
+#
+# This shar contains:
+# length mode       name
+# ------ ---------- ------------------------------------------
+#   2064 -rw-rw-r-- MultiSound.d/setdigital.c
+#  10224 -rw-rw-r-- MultiSound.d/pinnaclecfg.c
+#    106 -rw-rw-r-- MultiSound.d/Makefile
+#    146 -rw-rw-r-- MultiSound.d/conv.l
+#   1491 -rw-rw-r-- MultiSound.d/msndreset.c
+#
+save_IFS="${IFS}"
+IFS="${IFS}:"
+gettext_dir=FAILED
+locale_dir=FAILED
+first_param="$1"
+for dir in $PATH
+do
+  if test "$gettext_dir" = FAILED && test -f $dir/gettext \
+     && ($dir/gettext --version >/dev/null 2>&1)
+  then
+    set `$dir/gettext --version 2>&1`
+    if test "$3" = GNU
+    then
+      gettext_dir=$dir
+    fi
+  fi
+  if test "$locale_dir" = FAILED && test -f $dir/shar \
+     && ($dir/shar --print-text-domain-dir >/dev/null 2>&1)
+  then
+    locale_dir=`$dir/shar --print-text-domain-dir`
+  fi
+done
+IFS="$save_IFS"
+if test "$locale_dir" = FAILED || test "$gettext_dir" = FAILED
+then
+  echo=echo
+else
+  TEXTDOMAINDIR=$locale_dir
+  export TEXTDOMAINDIR
+  TEXTDOMAIN=sharutils
+  export TEXTDOMAIN
+  echo="$gettext_dir/gettext -s"
+fi
+touch -am 1231235999 $$.touch >/dev/null 2>&1
+if test ! -f 1231235999 && test -f $$.touch; then
+  shar_touch=touch
+else
+  shar_touch=:
+  echo
+  $echo 'WARNING: not restoring timestamps.  Consider getting and'
+  $echo "installing GNU \`touch', distributed in GNU File Utilities..."
+  echo
+fi
+rm -f 1231235999 $$.touch
+#
+if mkdir _sh01426; then
+  $echo 'x -' 'creating lock directory'
+else
+  $echo 'failed to create lock directory'
+  exit 1
+fi
+# ============= MultiSound.d/setdigital.c ==============
+if test ! -d 'MultiSound.d'; then
+  $echo 'x -' 'creating directory' 'MultiSound.d'
+  mkdir 'MultiSound.d'
+fi
+if test -f 'MultiSound.d/setdigital.c' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/setdigital.c' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/setdigital.c' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/setdigital.c' &&
+/*********************************************************************
+X *
+X * setdigital.c - sets the DIGITAL1 input for a mixer
+X *
+X * Copyright (C) 1998 Andrew Veliath
+X *
+X * This program is free software; you can redistribute it and/or modify
+X * it under the terms of the GNU General Public License as published by
+X * the Free Software Foundation; either version 2 of the License, or
+X * (at your option) any later version.
+X *
+X * This program is distributed in the hope that it will be useful,
+X * but WITHOUT ANY WARRANTY; without even the implied warranty of
+X * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+X * GNU General Public License for more details.
+X *
+X * You should have received a copy of the GNU General Public License
+X * along with this program; if not, write to the Free Software
+X * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+X *
+X ********************************************************************/
+X
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <sys/soundcard.h>
+X
+int main(int argc, char *argv[])
+{
+X	int fd;
+X	unsigned long recmask, recsrc;
+X
+X	if (argc != 2) {
+X		fprintf(stderr, "usage: setdigital <mixer device>\n");
+X		exit(1);
+X	}
+X
+X	if ((fd = open(argv[1], O_RDWR)) < 0) {
+X		perror(argv[1]);
+X		exit(1);
+X	}
+X
+X	if (ioctl(fd, SOUND_MIXER_READ_RECMASK, &recmask) < 0) {
+X		fprintf(stderr, "error: ioctl read recording mask failed\n");
+X		perror("ioctl");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	if (!(recmask & SOUND_MASK_DIGITAL1)) {
+X		fprintf(stderr, "error: cannot find DIGITAL1 device in mixer\n");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	if (ioctl(fd, SOUND_MIXER_READ_RECSRC, &recsrc) < 0) {
+X		fprintf(stderr, "error: ioctl read recording source failed\n");
+X		perror("ioctl");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	recsrc |= SOUND_MASK_DIGITAL1;
+X
+X	if (ioctl(fd, SOUND_MIXER_WRITE_RECSRC, &recsrc) < 0) {
+X		fprintf(stderr, "error: ioctl write recording source failed\n");
+X		perror("ioctl");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	close(fd);
+X
+X	return 0;
+}
+SHAR_EOF
+  $shar_touch -am 1204092598 'MultiSound.d/setdigital.c' &&
+  chmod 0664 'MultiSound.d/setdigital.c' ||
+  $echo 'restore of' 'MultiSound.d/setdigital.c' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/setdigital.c:' 'MD5 check failed'
+e87217fc3e71288102ba41fd81f71ec4  MultiSound.d/setdigital.c
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/setdigital.c'`"
+    test 2064 -eq "$shar_count" ||
+    $echo 'MultiSound.d/setdigital.c:' 'original size' '2064,' 'current size' "$shar_count!"
+  fi
+fi
+# ============= MultiSound.d/pinnaclecfg.c ==============
+if test -f 'MultiSound.d/pinnaclecfg.c' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/pinnaclecfg.c' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/pinnaclecfg.c' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/pinnaclecfg.c' &&
+/*********************************************************************
+X *
+X * pinnaclecfg.c - Pinnacle/Fiji Device Configuration Program
+X *
+X * This is for NON-PnP mode only.  For PnP mode, use isapnptools.
+X *
+X * This is Linux-specific, and must be run with root permissions.
+X *
+X * Part of the Turtle Beach MultiSound Sound Card Driver for Linux
+X *
+X * Copyright (C) 1998 Andrew Veliath
+X *
+X * This program is free software; you can redistribute it and/or modify
+X * it under the terms of the GNU General Public License as published by
+X * the Free Software Foundation; either version 2 of the License, or
+X * (at your option) any later version.
+X *
+X * This program is distributed in the hope that it will be useful,
+X * but WITHOUT ANY WARRANTY; without even the implied warranty of
+X * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+X * GNU General Public License for more details.
+X *
+X * You should have received a copy of the GNU General Public License
+X * along with this program; if not, write to the Free Software
+X * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+X *
+X ********************************************************************/
+X
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <asm/types.h>
+#include <sys/io.h>
+X
+#define IREG_LOGDEVICE		0x07
+#define IREG_ACTIVATE		0x30
+#define LD_ACTIVATE		0x01
+#define LD_DISACTIVATE		0x00
+#define IREG_EECONTROL		0x3F
+#define IREG_MEMBASEHI		0x40
+#define IREG_MEMBASELO		0x41
+#define IREG_MEMCONTROL		0x42
+#define IREG_MEMRANGEHI		0x43
+#define IREG_MEMRANGELO		0x44
+#define MEMTYPE_8BIT		0x00
+#define MEMTYPE_16BIT		0x02
+#define MEMTYPE_RANGE		0x00
+#define MEMTYPE_HIADDR		0x01
+#define IREG_IO0_BASEHI		0x60
+#define IREG_IO0_BASELO		0x61
+#define IREG_IO1_BASEHI		0x62
+#define IREG_IO1_BASELO		0x63
+#define IREG_IRQ_NUMBER		0x70
+#define IREG_IRQ_TYPE		0x71
+#define IRQTYPE_HIGH		0x02
+#define IRQTYPE_LOW		0x00
+#define IRQTYPE_LEVEL		0x01
+#define IRQTYPE_EDGE		0x00
+X
+#define HIBYTE(w)		((BYTE)(((WORD)(w) >> 8) & 0xFF))
+#define LOBYTE(w)		((BYTE)(w))
+#define MAKEWORD(low,hi)	((WORD)(((BYTE)(low))|(((WORD)((BYTE)(hi)))<<8)))
+X
+typedef __u8			BYTE;
+typedef __u16			USHORT;
+typedef __u16			WORD;
+X
+static int config_port = -1;
+X
+static int msnd_write_cfg(int cfg, int reg, int value)
+{
+X	outb(reg, cfg);
+X	outb(value, cfg + 1);
+X	if (value != inb(cfg + 1)) {
+X		fprintf(stderr, "error: msnd_write_cfg: I/O error\n");
+X		return -EIO;
+X	}
+X	return 0;
+}
+X
+static int msnd_read_cfg(int cfg, int reg)
+{
+X	outb(reg, cfg);
+X	return inb(cfg + 1);
+}
+X
+static int msnd_write_cfg_io0(int cfg, int num, WORD io)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IO0_BASEHI, HIBYTE(io)))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IO0_BASELO, LOBYTE(io)))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_io0(int cfg, int num, WORD *io)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X
+X	*io = MAKEWORD(msnd_read_cfg(cfg, IREG_IO0_BASELO),
+X		       msnd_read_cfg(cfg, IREG_IO0_BASEHI));
+X
+X	return 0;
+}
+X
+static int msnd_write_cfg_io1(int cfg, int num, WORD io)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IO1_BASEHI, HIBYTE(io)))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IO1_BASELO, LOBYTE(io)))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_io1(int cfg, int num, WORD *io)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X
+X	*io = MAKEWORD(msnd_read_cfg(cfg, IREG_IO1_BASELO),
+X		       msnd_read_cfg(cfg, IREG_IO1_BASEHI));
+X
+X	return 0;
+}
+X
+static int msnd_write_cfg_irq(int cfg, int num, WORD irq)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IRQ_NUMBER, LOBYTE(irq)))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IRQ_TYPE, IRQTYPE_EDGE))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_irq(int cfg, int num, WORD *irq)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X
+X	*irq = msnd_read_cfg(cfg, IREG_IRQ_NUMBER);
+X
+X	return 0;
+}
+X
+static int msnd_write_cfg_mem(int cfg, int num, int mem)
+{
+X	WORD wmem;
+X
+X	mem >>= 8;
+X	mem &= 0xfff;
+X	wmem = (WORD)mem;
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_MEMBASEHI, HIBYTE(wmem)))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_MEMBASELO, LOBYTE(wmem)))
+X		return -EIO;
+X	if (wmem && msnd_write_cfg(cfg, IREG_MEMCONTROL, (MEMTYPE_HIADDR | MEMTYPE_16BIT)))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_mem(int cfg, int num, int *mem)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X
+X	*mem = MAKEWORD(msnd_read_cfg(cfg, IREG_MEMBASELO),
+X			msnd_read_cfg(cfg, IREG_MEMBASEHI));
+X	*mem <<= 8;
+X
+X	return 0;
+}
+X
+static int msnd_activate_logical(int cfg, int num)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_ACTIVATE, LD_ACTIVATE))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_write_cfg_logical(int cfg, int num, WORD io0, WORD io1, WORD irq, int mem)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg_io0(cfg, num, io0))
+X		return -EIO;
+X	if (msnd_write_cfg_io1(cfg, num, io1))
+X		return -EIO;
+X	if (msnd_write_cfg_irq(cfg, num, irq))
+X		return -EIO;
+X	if (msnd_write_cfg_mem(cfg, num, mem))
+X		return -EIO;
+X	if (msnd_activate_logical(cfg, num))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_logical(int cfg, int num, WORD *io0, WORD *io1, WORD *irq, int *mem)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_read_cfg_io0(cfg, num, io0))
+X		return -EIO;
+X	if (msnd_read_cfg_io1(cfg, num, io1))
+X		return -EIO;
+X	if (msnd_read_cfg_irq(cfg, num, irq))
+X		return -EIO;
+X	if (msnd_read_cfg_mem(cfg, num, mem))
+X		return -EIO;
+X	return 0;
+}
+X
+static void usage(void)
+{
+X	fprintf(stderr,
+X		"\n"
+X		"pinnaclecfg 1.0\n"
+X		"\n"
+X		"usage: pinnaclecfg <config port> [device config]\n"
+X		"\n"
+X		"This is for use with the card in NON-PnP mode only.\n"
+X		"\n"
+X		"Available devices (not all available for Fiji):\n"
+X		"\n"
+X		"        Device                       Description\n"
+X		"        -------------------------------------------------------------------\n"
+X		"        reset                        Reset all devices (i.e. disable)\n"
+X		"        show                         Display current device configurations\n"
+X		"\n"
+X		"        dsp <io> <irq> <mem>         Audio device\n"
+X		"        mpu <io> <irq>               Internal Kurzweil synth\n"
+X		"        ide <io0> <io1> <irq>        On-board IDE controller\n"
+X		"        joystick <io>                Joystick port\n"
+X		"\n");
+X	exit(1);
+}
+X
+static int cfg_reset(void)
+{
+X	int i;
+X
+X	for (i = 0; i < 4; ++i)
+X		msnd_write_cfg_logical(config_port, i, 0, 0, 0, 0);
+X
+X	return 0;
+}
+X
+static int cfg_show(void)
+{
+X	int i;
+X	int count = 0;
+X
+X	for (i = 0; i < 4; ++i) {
+X		WORD io0, io1, irq;
+X		int mem;
+X		msnd_read_cfg_logical(config_port, i, &io0, &io1, &irq, &mem);
+X		switch (i) {
+X		case 0:
+X			if (io0 || irq || mem) {
+X				printf("dsp 0x%x %d 0x%x\n", io0, irq, mem);
+X				++count;
+X			}
+X			break;
+X		case 1:
+X			if (io0 || irq) {
+X				printf("mpu 0x%x %d\n", io0, irq);
+X				++count;
+X			}
+X			break;
+X		case 2:
+X			if (io0 || io1 || irq) {
+X				printf("ide 0x%x 0x%x %d\n", io0, io1, irq);
+X				++count;
+X			}
+X			break;
+X		case 3:
+X			if (io0) {
+X				printf("joystick 0x%x\n", io0);
+X				++count;
+X			}
+X			break;
+X		}
+X	}
+X
+X	if (count == 0)
+X		fprintf(stderr, "no devices configured\n");
+X
+X	return 0;
+}
+X
+static int cfg_dsp(int argc, char *argv[])
+{
+X	int io, irq, mem;
+X
+X	if (argc < 3 ||
+X	    sscanf(argv[0], "0x%x", &io) != 1 ||
+X	    sscanf(argv[1], "%d", &irq) != 1 ||
+X	    sscanf(argv[2], "0x%x", &mem) != 1)
+X		usage();
+X
+X	if (!(io == 0x290 ||
+X	      io == 0x260 ||
+X	      io == 0x250 ||
+X	      io == 0x240 ||
+X	      io == 0x230 ||
+X	      io == 0x220 ||
+X	      io == 0x210 ||
+X	      io == 0x3e0)) {
+X		fprintf(stderr, "error: io must be one of "
+X			"210, 220, 230, 240, 250, 260, 290, or 3E0\n");
+X		usage();
+X	}
+X
+X	if (!(irq == 5 ||
+X	      irq == 7 ||
+X	      irq == 9 ||
+X	      irq == 10 ||
+X	      irq == 11 ||
+X	      irq == 12)) {
+X		fprintf(stderr, "error: irq must be one of "
+X			"5, 7, 9, 10, 11 or 12\n");
+X		usage();
+X	}
+X
+X	if (!(mem == 0xb0000 ||
+X	      mem == 0xc8000 ||
+X	      mem == 0xd0000 ||
+X	      mem == 0xd8000 ||
+X	      mem == 0xe0000 ||
+X	      mem == 0xe8000)) {
+X		fprintf(stderr, "error: mem must be one of "
+X			"0xb0000, 0xc8000, 0xd0000, 0xd8000, 0xe0000 or 0xe8000\n");
+X		usage();
+X	}
+X
+X	return msnd_write_cfg_logical(config_port, 0, io, 0, irq, mem);
+}
+X
+static int cfg_mpu(int argc, char *argv[])
+{
+X	int io, irq;
+X
+X	if (argc < 2 ||
+X	    sscanf(argv[0], "0x%x", &io) != 1 ||
+X	    sscanf(argv[1], "%d", &irq) != 1)
+X		usage();
+X
+X	return msnd_write_cfg_logical(config_port, 1, io, 0, irq, 0);
+}
+X
+static int cfg_ide(int argc, char *argv[])
+{
+X	int io0, io1, irq;
+X
+X	if (argc < 3 ||
+X	    sscanf(argv[0], "0x%x", &io0) != 1 ||
+X	    sscanf(argv[0], "0x%x", &io1) != 1 ||
+X	    sscanf(argv[1], "%d", &irq) != 1)
+X		usage();
+X
+X	return msnd_write_cfg_logical(config_port, 2, io0, io1, irq, 0);
+}
+X
+static int cfg_joystick(int argc, char *argv[])
+{
+X	int io;
+X
+X	if (argc < 1 ||
+X	    sscanf(argv[0], "0x%x", &io) != 1)
+X		usage();
+X
+X	return msnd_write_cfg_logical(config_port, 3, io, 0, 0, 0);
+}
+X
+int main(int argc, char *argv[])
+{
+X	char *device;
+X	int rv = 0;
+X
+X	--argc; ++argv;
+X
+X	if (argc < 2)
+X		usage();
+X
+X	sscanf(argv[0], "0x%x", &config_port);
+X	if (config_port != 0x250 && config_port != 0x260 && config_port != 0x270) {
+X		fprintf(stderr, "error: <config port> must be 0x250, 0x260 or 0x270\n");
+X		exit(1);
+X	}
+X	if (ioperm(config_port, 2, 1)) {
+X		perror("ioperm");
+X		fprintf(stderr, "note: pinnaclecfg must be run as root\n");
+X		exit(1);
+X	}
+X	device = argv[1];
+X
+X	argc -= 2; argv += 2;
+X
+X	if (strcmp(device, "reset") == 0)
+X		rv = cfg_reset();
+X	else if (strcmp(device, "show") == 0)
+X		rv = cfg_show();
+X	else if (strcmp(device, "dsp") == 0)
+X		rv = cfg_dsp(argc, argv);
+X	else if (strcmp(device, "mpu") == 0)
+X		rv = cfg_mpu(argc, argv);
+X	else if (strcmp(device, "ide") == 0)
+X		rv = cfg_ide(argc, argv);
+X	else if (strcmp(device, "joystick") == 0)
+X		rv = cfg_joystick(argc, argv);
+X	else {
+X		fprintf(stderr, "error: unknown device %s\n", device);
+X		usage();
+X	}
+X
+X	if (rv)
+X		fprintf(stderr, "error: device configuration failed\n");
+X
+X	return 0;
+}
+SHAR_EOF
+  $shar_touch -am 1204092598 'MultiSound.d/pinnaclecfg.c' &&
+  chmod 0664 'MultiSound.d/pinnaclecfg.c' ||
+  $echo 'restore of' 'MultiSound.d/pinnaclecfg.c' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/pinnaclecfg.c:' 'MD5 check failed'
+366bdf27f0db767a3c7921d0a6db20fe  MultiSound.d/pinnaclecfg.c
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/pinnaclecfg.c'`"
+    test 10224 -eq "$shar_count" ||
+    $echo 'MultiSound.d/pinnaclecfg.c:' 'original size' '10224,' 'current size' "$shar_count!"
+  fi
+fi
+# ============= MultiSound.d/Makefile ==============
+if test -f 'MultiSound.d/Makefile' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/Makefile' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/Makefile' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/Makefile' &&
+CC	= gcc
+CFLAGS	= -O
+PROGS	= setdigital msndreset pinnaclecfg conv
+X
+all: $(PROGS)
+X
+clean:
+X	rm -f $(PROGS)
+SHAR_EOF
+  $shar_touch -am 1204092398 'MultiSound.d/Makefile' &&
+  chmod 0664 'MultiSound.d/Makefile' ||
+  $echo 'restore of' 'MultiSound.d/Makefile' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/Makefile:' 'MD5 check failed'
+76ca8bb44e3882edcf79c97df6c81845  MultiSound.d/Makefile
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/Makefile'`"
+    test 106 -eq "$shar_count" ||
+    $echo 'MultiSound.d/Makefile:' 'original size' '106,' 'current size' "$shar_count!"
+  fi
+fi
+# ============= MultiSound.d/conv.l ==============
+if test -f 'MultiSound.d/conv.l' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/conv.l' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/conv.l' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/conv.l' &&
+%%
+[ \n\t,\r]
+\;.*
+DB
+[0-9A-Fa-f]+H	{ int n; sscanf(yytext, "%xH", &n); printf("%c", n); }
+%%
+int yywrap() { return 1; }
+void main() { yylex(); }
+SHAR_EOF
+  $shar_touch -am 0828231798 'MultiSound.d/conv.l' &&
+  chmod 0664 'MultiSound.d/conv.l' ||
+  $echo 'restore of' 'MultiSound.d/conv.l' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/conv.l:' 'MD5 check failed'
+d2411fc32cd71a00dcdc1f009e858dd2  MultiSound.d/conv.l
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/conv.l'`"
+    test 146 -eq "$shar_count" ||
+    $echo 'MultiSound.d/conv.l:' 'original size' '146,' 'current size' "$shar_count!"
+  fi
+fi
+# ============= MultiSound.d/msndreset.c ==============
+if test -f 'MultiSound.d/msndreset.c' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/msndreset.c' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/msndreset.c' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/msndreset.c' &&
+/*********************************************************************
+X *
+X * msndreset.c - resets the MultiSound card
+X *
+X * Copyright (C) 1998 Andrew Veliath
+X *
+X * This program is free software; you can redistribute it and/or modify
+X * it under the terms of the GNU General Public License as published by
+X * the Free Software Foundation; either version 2 of the License, or
+X * (at your option) any later version.
+X *
+X * This program is distributed in the hope that it will be useful,
+X * but WITHOUT ANY WARRANTY; without even the implied warranty of
+X * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+X * GNU General Public License for more details.
+X *
+X * You should have received a copy of the GNU General Public License
+X * along with this program; if not, write to the Free Software
+X * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+X *
+X ********************************************************************/
+X
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <sys/soundcard.h>
+X
+int main(int argc, char *argv[])
+{
+X	int fd;
+X
+X	if (argc != 2) {
+X		fprintf(stderr, "usage: msndreset <mixer device>\n");
+X		exit(1);
+X	}
+X
+X	if ((fd = open(argv[1], O_RDWR)) < 0) {
+X		perror(argv[1]);
+X		exit(1);
+X	}
+X
+X	if (ioctl(fd, SOUND_MIXER_PRIVATE1, 0) < 0) {
+X		fprintf(stderr, "error: msnd ioctl reset failed\n");
+X		perror("ioctl");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	close(fd);
+X
+X	return 0;
+}
+SHAR_EOF
+  $shar_touch -am 1204100698 'MultiSound.d/msndreset.c' &&
+  chmod 0664 'MultiSound.d/msndreset.c' ||
+  $echo 'restore of' 'MultiSound.d/msndreset.c' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/msndreset.c:' 'MD5 check failed'
+c52f876521084e8eb25e12e01dcccb8a  MultiSound.d/msndreset.c
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/msndreset.c'`"
+    test 1491 -eq "$shar_count" ||
+    $echo 'MultiSound.d/msndreset.c:' 'original size' '1491,' 'current size' "$shar_count!"
+  fi
+fi
+rm -fr _sh01426
+exit 0
diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst
index 7c2d37571af0..e06238131f77 100644
--- a/Documentation/sound/hd-audio/models.rst
+++ b/Documentation/sound/hd-audio/models.rst
@@ -34,6 +34,22 @@ ALC262
 ======
 inv-dmic
     Inverted internal mic workaround
+fsc-h270
+    Fixups for Fujitsu-Siemens Celsius H270
+fsc-s7110
+    Fixups for Fujitsu-Siemens Lifebook S7110
+hp-z200
+    Fixups for HP Z200
+tyan
+    Fixups for Tyan Thunder n6650W
+lenovo-3000
+    Fixups for Lenovo 3000
+benq
+    Fixups for Benq ED8
+benq-t31
+    Fixups for Benq T31
+bayleybay
+    Fixups for Intel BayleyBay
 
 ALC267/268
 ==========
@@ -41,6 +57,8 @@ inv-dmic
     Inverted internal mic workaround
 hp-eapd
     Disable HP EAPD on NID 0x15
+spdif
+    Enable SPDIF output on NID 0x1e
 
 ALC22x/23x/25x/269/27x/28x/29x (and vendor-specific ALC3xxx models)
 ===================================================================
@@ -70,6 +88,10 @@ dell-headset-multi
     Headset jack, which can also be used as mic-in
 dell-headset-dock
     Headset jack (without mic-in), and also dock I/O
+dell-headset3
+    Headset jack (without mic-in), and also dock I/O, variant 3
+dell-headset4
+    Headset jack (without mic-in), and also dock I/O, variant 4
 alc283-dac-wcaps
     Fixups for Chromebook with ALC283
 alc283-sense-combo
@@ -80,15 +102,173 @@ tpt440
     Lenovo Thinkpad T440s setup
 tpt460
     Lenovo Thinkpad T460/560 setup
+tpt470-dock
+    Lenovo Thinkpad T470 dock setup
 dual-codecs
     Lenovo laptops with dual codecs
 alc700-ref
     Intel reference board with ALC700 codec
+vaio
+    Pin fixups for Sony VAIO laptops
+dell-m101z
+    COEF setup for Dell M101z
+asus-g73jw
+    Subwoofer pin fixup for ASUS G73JW
+lenovo-eapd
+    Inversed EAPD setup for Lenovo laptops
+sony-hweq
+    H/W EQ COEF setup for Sony laptops
+pcm44k
+    Fixed PCM 44kHz constraints (for buggy devices)
+lifebook
+    Dock pin fixups for Fujitsu Lifebook
+lifebook-extmic
+    Headset mic fixup for Fujitsu Lifebook
+lifebook-hp-pin
+    Headphone pin fixup for Fujitsu Lifebook
+lifebook-u7x7
+    Lifebook U7x7 fixups
+alc269vb-amic
+    ALC269VB analog mic pin fixups
+alc269vb-dmic
+    ALC269VB digital mic pin fixups
+hp-mute-led-mic1
+    Mute LED via Mic1 pin on HP
+hp-mute-led-mic2
+    Mute LED via Mic2 pin on HP
+hp-mute-led-mic3
+    Mute LED via Mic3 pin on HP
+hp-gpio-mic1
+    GPIO + Mic1 pin LED on HP
+hp-line1-mic1
+    Mute LED via Line1 + Mic1 pins on HP
+noshutup
+    Skip shutup callback
+sony-nomic
+    Headset mic fixup for Sony laptops
+aspire-headset-mic
+    Headset pin fixup for Acer Aspire
+asus-x101
+    ASUS X101 fixups
+acer-ao7xx
+    Acer AO7xx fixups
+acer-aspire-e1
+    Acer Aspire E1 fixups
+acer-ac700
+    Acer AC700 fixups
+limit-mic-boost
+    Limit internal mic boost on Lenovo machines
+asus-zenbook
+    ASUS Zenbook fixups
+asus-zenbook-ux31a
+    ASUS Zenbook UX31A fixups
+ordissimo
+    Ordissimo EVE2 (or Malata PC-B1303) fixups
+asus-tx300
+    ASUS TX300 fixups
+alc283-int-mic
+    ALC283 COEF setup for Lenovo machines
+mono-speakers
+    Subwoofer and headset fixupes for Dell Inspiron
+alc290-subwoofer
+    Subwoofer fixups for Dell Vostro
+thinkpad
+    Binding with thinkpad_acpi driver for Lenovo machines
+dmic-thinkpad
+    thinkpad_acpi binding + digital mic support
+alc255-acer
+    ALC255 fixups on Acer machines
+alc255-asus
+    ALC255 fixups on ASUS machines
+alc255-dell1
+    ALC255 fixups on Dell machines
+alc255-dell2
+    ALC255 fixups on Dell machines, variant 2
+alc293-dell1
+    ALC293 fixups on Dell machines
+alc283-headset
+    Headset pin fixups on ALC283
+aspire-v5
+    Acer Aspire V5 fixups
+hp-gpio4
+    GPIO and Mic1 pin mute LED fixups for HP
+hp-gpio-led
+    GPIO mute LEDs on HP
+hp-gpio2-hotkey
+    GPIO mute LED with hot key handling on HP
+hp-dock-pins
+    GPIO mute LEDs and dock support on HP
+hp-dock-gpio-mic
+    GPIO, Mic mute LED and dock support on HP
+hp-9480m
+    HP 9480m fixups
+alc288-dell1
+    ALC288 fixups on Dell machines
+alc288-dell-xps13
+    ALC288 fixups on Dell XPS13
+dell-e7x
+    Dell E7x fixups
+alc293-dell
+    ALC293 fixups on Dell machines
+alc298-dell1
+    ALC298 fixups on Dell machines
+alc298-dell-aio
+    ALC298 fixups on Dell AIO machines
+alc275-dell-xps
+    ALC275 fixups on Dell XPS models
+alc256-dell-xps13
+    ALC256 fixups on Dell XPS13
+lenovo-spk-noise
+    Workaround for speaker noise on Lenovo machines
+lenovo-hotkey
+    Hot-key support via Mic2 pin on Lenovo machines
+dell-spk-noise
+    Workaround for speaker noise on Dell machines
+alc255-dell1
+    ALC255 fixups on Dell machines
+alc295-disable-dac3
+    Disable DAC3 routing on ALC295
+alc280-hp-headset
+    HP Elitebook fixups
+alc221-hp-mic
+    Front mic pin fixup on HP machines
+alc298-spk-volume
+    Speaker pin routing workaround on ALC298
+dell-inspiron-7559
+    Dell Inspiron 7559 fixups
+ativ-book
+    Samsung Ativ book 8 fixups
+alc221-hp-mic
+    ALC221 headset fixups on HP machines
+alc256-asus-mic
+    ALC256 fixups on ASUS machines
+alc256-asus-aio
+    ALC256 fixups on ASUS AIO machines
+alc233-eapd
+    ALC233 fixups on ASUS machines
+alc294-lenovo-mic
+    ALC294 Mic pin fixup for Lenovo AIO machines
+alc225-wyse
+    Dell Wyse fixups
+alc274-dell-aio
+    ALC274 fixups on Dell AIO machines
+alc255-dummy-lineout
+    Dell Precision 3930 fixups
+alc255-dell-headset"},
+    Dell Precision 3630 fixups
+alc295-hp-x360
+    HP Spectre X360 fixups
 
 ALC66x/67x/892
 ==============
+aspire
+    Subwoofer pin fixup for Aspire laptops
+ideapad
+    Subwoofer pin fixup for Ideapad laptops
 mario
     Chromebook mario model fixup
+hp-rp5800
+    Headphone pin fixup for HP RP5800
 asus-mode1
     ASUS
 asus-mode2
@@ -105,10 +285,40 @@ asus-mode7
     ASUS
 asus-mode8
     ASUS
+zotac-z68
+    Front HP fixup for Zotac Z68
 inv-dmic
     Inverted internal mic workaround
+alc662-headset-multi
+    Dell headset jack, which can also be used as mic-in (ALC662)
 dell-headset-multi
     Headset jack, which can also be used as mic-in
+alc662-headset
+    Headset mode support on ALC662
+alc668-headset
+    Headset mode support on ALC668
+bass16
+    Bass speaker fixup on pin 0x16
+bass1a
+    Bass speaker fixup on pin 0x1a
+automute
+    Auto-mute fixups for ALC668
+dell-xps13
+    Dell XPS13 fixups
+asus-nx50
+    ASUS Nx50 fixups
+asus-nx51
+    ASUS Nx51 fixups
+alc891-headset
+    Headset mode support on ALC891
+alc891-headset-multi
+    Dell headset jack, which can also be used as mic-in (ALC891)
+acer-veriton
+    Acer Veriton speaker pin fixup
+asrock-mobo
+    Fix invalid 0x15 / 0x16 pins
+usi-headset
+    Headset support on USI machines
 dual-codecs
     Lenovo laptops with dual codecs
 
@@ -116,20 +326,70 @@ ALC680
 ======
 N/A
 
-ALC88x/898/1150
-======================
+ALC88x/898/1150/1220
+====================
+abit-aw9d
+    Pin fixups for Abit AW9D-MAX
+lenovo-y530
+    Pin fixups for Lenovo Y530
+acer-aspire-7736
+    Fixup for Acer Aspire 7736
+asus-w90v
+    Pin fixup for ASUS W90V
+cd
+    Enable audio CD pin NID 0x1c
+no-front-hp
+    Disable front HP pin NID 0x1b
+vaio-tt
+    Pin fixup for VAIO TT
+eee1601
+    COEF setups for ASUS Eee 1601
+alc882-eapd
+    Change EAPD COEF mode on ALC882
+alc883-eapd
+    Change EAPD COEF mode on ALC883
+gpio1
+    Enable GPIO1
+gpio2
+    Enable GPIO2
+gpio3
+    Enable GPIO3
+alc889-coef
+    Setup ALC889 COEF
+asus-w2jc
+    Fixups for ASUS W2JC
 acer-aspire-4930g
     Acer Aspire 4930G/5930G/6530G/6930G/7730G
 acer-aspire-8930g
     Acer Aspire 8330G/6935G
 acer-aspire
     Acer Aspire others
+macpro-gpio
+    GPIO setup for Mac Pro
+dac-route
+    Workaround for DAC routing on Acer Aspire
+mbp-vref
+    Vref setup for Macbook Pro
+imac91-vref
+    Vref setup for iMac 9,1
+mba11-vref
+    Vref setup for MacBook Air 1,1
+mba21-vref
+    Vref setup for MacBook Air 2,1
+mp11-vref
+    Vref setup for Mac Pro 1,1
+mp41-vref
+    Vref setup for Mac Pro 4,1
 inv-dmic
     Inverted internal mic workaround
 no-primary-hp
     VAIO Z/VGC-LN51JGB workaround (for fixed speaker DAC)
+asus-bass
+    Bass speaker setup for ASUS ET2700
 dual-codecs
     ALC1220 dual codecs for Gaming mobos
+clevo-p950
+    Fixups for Clevo P950
 
 ALC861/660
 ==========
diff --git a/Documentation/sound/soc/dpcm.rst b/Documentation/sound/soc/dpcm.rst
index 395e5a516282..fe61e02277f8 100644
--- a/Documentation/sound/soc/dpcm.rst
+++ b/Documentation/sound/soc/dpcm.rst
@@ -254,9 +254,7 @@ configuration.
 	channels->min = channels->max = 2;
 
 	/* set DAI0 to 16 bit */
-	snd_mask_set(&params->masks[SNDRV_PCM_HW_PARAM_FORMAT -
-				    SNDRV_PCM_HW_PARAM_FIRST_MASK],
-				    SNDRV_PCM_FORMAT_S16_LE);
+	params_set_format(params, SNDRV_PCM_FORMAT_S16_LE);
 	return 0;
   }
 
diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py
index fbedcc39460b..9d0a7f08f93b 100644
--- a/Documentation/sphinx/kerneldoc.py
+++ b/Documentation/sphinx/kerneldoc.py
@@ -47,7 +47,7 @@ class KernelDocDirective(Directive):
     optional_arguments = 4
     option_spec = {
         'doc': directives.unchanged_required,
-        'functions': directives.unchanged_required,
+        'functions': directives.unchanged,
         'export': directives.unchanged,
         'internal': directives.unchanged,
     }
@@ -75,8 +75,12 @@ class KernelDocDirective(Directive):
         elif 'doc' in self.options:
             cmd += ['-function', str(self.options.get('doc'))]
         elif 'functions' in self.options:
-            for f in str(self.options.get('functions')).split():
-                cmd += ['-function', f]
+            functions = self.options.get('functions').split()
+            if functions:
+                for f in functions:
+                    cmd += ['-function', f]
+            else:
+                cmd += ['-no-doc-sections']
 
         for pattern in export_file_patterns:
             for f in glob.glob(env.config.kerneldoc_srctree + '/' + pattern):
diff --git a/Documentation/sphinx/parse-headers.pl b/Documentation/sphinx/parse-headers.pl
index d410f47567e9..c518050ffc3f 100755
--- a/Documentation/sphinx/parse-headers.pl
+++ b/Documentation/sphinx/parse-headers.pl
@@ -344,7 +344,7 @@ enums and defines and create cross-references to a Sphinx book.
 
 B<parse_headers.pl> [<options>] <C_FILE> <OUT_FILE> [<EXCEPTIONS_FILE>]
 
-Where <options> can be: --debug, --help or --man.
+Where <options> can be: --debug, --help or --usage.
 
 =head1 OPTIONS
 
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 697ef8c225df..e72853b6d725 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -27,6 +27,7 @@ Currently, these files are in /proc/sys/vm:
 - dirty_bytes
 - dirty_expire_centisecs
 - dirty_ratio
+- dirtytime_expire_seconds
 - dirty_writeback_centisecs
 - drop_caches
 - extfrag_threshold
@@ -44,6 +45,7 @@ Currently, these files are in /proc/sys/vm:
 - mmap_rnd_bits
 - mmap_rnd_compat_bits
 - nr_hugepages
+- nr_hugepages_mempolicy
 - nr_overcommit_hugepages
 - nr_trim_pages         (only if CONFIG_MMU=n)
 - numa_zonelist_order
@@ -178,6 +180,18 @@ The total available memory is not equal to total system memory.
 
 ==============================================================
 
+dirtytime_expire_seconds
+
+When a lazytime inode is constantly having its pages dirtied, the inode with
+an updated timestamp will never get chance to be written out.  And, if the
+only thing that has happened on the file system is a dirtytime inode caused
+by an atime update, a worker will be scheduled to make sure that inode
+eventually gets pushed out to disk.  This tunable is used to define when dirty
+inode is old enough to be eligible for writeback by the kernel flusher threads.
+And, it is also used as the interval to wakeup dirtytime_writeback thread.
+
+==============================================================
+
 dirty_writeback_centisecs
 
 The kernel flusher threads will periodically wake up and write `old' data
@@ -519,6 +533,15 @@ See Documentation/admin-guide/mm/hugetlbpage.rst
 
 ==============================================================
 
+nr_hugepages_mempolicy
+
+Change the size of the hugepage pool at run-time on a specific
+set of NUMA nodes.
+
+See Documentation/admin-guide/mm/hugetlbpage.rst
+
+==============================================================
+
 nr_overcommit_hugepages
 
 Change the maximum size of the hugepage pool. The maximum is
diff --git a/Documentation/timers/timekeeping.txt b/Documentation/timers/timekeeping.txt
index f3a8cf28f802..2d1732b0a868 100644
--- a/Documentation/timers/timekeeping.txt
+++ b/Documentation/timers/timekeeping.txt
@@ -27,7 +27,7 @@ a Linux system will eventually read the clock source to determine exactly
 what time it is.
 
 Typically the clock source is a monotonic, atomic counter which will provide
-n bits which count from 0 to 2^(n-1) and then wraps around to 0 and start over.
+n bits which count from 0 to (2^n)-1 and then wraps around to 0 and start over.
 It will ideally NEVER stop ticking as long as the system is running. It
 may stop during system suspend.
 
diff --git a/Documentation/trace/events-power.rst b/Documentation/trace/events-power.rst
index a77daca75e30..2ef318962e29 100644
--- a/Documentation/trace/events-power.rst
+++ b/Documentation/trace/events-power.rst
@@ -27,6 +27,7 @@ cpufreq.
 
   cpu_idle		"state=%lu cpu_id=%lu"
   cpu_frequency		"state=%lu cpu_id=%lu"
+  cpu_frequency_limits	"min=%lu max=%lu cpu_id=%lu"
 
 A suspend event is used to indicate the system going in and out of the
 suspend mode:
diff --git a/Documentation/trace/events.rst b/Documentation/trace/events.rst
index 696dc69b8158..f7e1fcc0953c 100644
--- a/Documentation/trace/events.rst
+++ b/Documentation/trace/events.rst
@@ -524,4 +524,4 @@ The following commands are supported:
   totals derived from one or more trace event format fields and/or
   event counts (hitcount).
 
-  See Documentation/trace/histogram.txt for details and examples.
+  See Documentation/trace/histogram.rst for details and examples.
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index a20d34955333..7ea16a0ceffc 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -329,9 +329,9 @@ of ftrace. Here is a list of some of the key files:
 	track of the time spent in those functions. The histogram
 	content can be displayed in the files:
 
-	trace_stats/function<cpu> ( function0, function1, etc).
+	trace_stat/function<cpu> ( function0, function1, etc).
 
-  trace_stats:
+  trace_stat:
 
 	A directory that holds different tracing stats.
 
diff --git a/Documentation/trace/histogram.txt b/Documentation/trace/histogram.rst
index 7ffea6aa22e3..5ac724baea7d 100644
--- a/Documentation/trace/histogram.txt
+++ b/Documentation/trace/histogram.rst
@@ -1,6 +1,8 @@
-			     Event Histograms
+================
+Event Histograms
+================
 
-		    Documentation written by Tom Zanussi
+Documentation written by Tom Zanussi
 
 1. Introduction
 ===============
@@ -19,7 +21,7 @@
   derived from one or more trace event format fields and/or event
   counts (hitcount).
 
-  The format of a hist trigger is as follows:
+  The format of a hist trigger is as follows::
 
         hist:keys=<field1[,field2,...]>[:values=<field1[,field2,...]>]
           [:sort=<field1[,field2,...]>][:size=#entries][:pause][:continue]
@@ -68,6 +70,7 @@
   modified by appending any of the following modifiers to the field
   name:
 
+	=========== ==========================================
         .hex        display a number as a hex value
 	.sym        display an address as a symbol
 	.sym-offset display an address as a symbol and offset
@@ -75,6 +78,7 @@
 	.execname   display a common_pid as a program name
 	.log2       display log2 value rather than raw number
 	.usecs      display a common_timestamp in microseconds
+	=========== ==========================================
 
   Note that in general the semantics of a given field aren't
   interpreted when applying a modifier to it, but there are some
@@ -92,15 +96,15 @@
       pid-specific comm fields in the event itself.
 
   A typical usage scenario would be the following to enable a hist
-  trigger, read its current contents, and then turn it off:
+  trigger, read its current contents, and then turn it off::
 
-  # echo 'hist:keys=skbaddr.hex:vals=len' > \
-    /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+    # echo 'hist:keys=skbaddr.hex:vals=len' > \
+      /sys/kernel/debug/tracing/events/net/netif_rx/trigger
 
-  # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+    # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
 
-  # echo '!hist:keys=skbaddr.hex:vals=len' > \
-    /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+    # echo '!hist:keys=skbaddr.hex:vals=len' > \
+      /sys/kernel/debug/tracing/events/net/netif_rx/trigger
 
   The trigger file itself can be read to show the details of the
   currently attached hist trigger.  This information is also displayed
@@ -140,7 +144,7 @@
   can be attached to a given event, allowing that event to kick off
   and stop aggregations on a host of other events.
 
-  The format is very similar to the enable/disable_event triggers:
+  The format is very similar to the enable/disable_event triggers::
 
       enable_hist:<system>:<event>[:count]
       disable_hist:<system>:<event>[:count]
@@ -153,16 +157,16 @@
   A typical usage scenario for the enable_hist/disable_hist triggers
   would be to first set up a paused hist trigger on some event,
   followed by an enable_hist/disable_hist pair that turns the hist
-  aggregation on and off when conditions of interest are hit:
+  aggregation on and off when conditions of interest are hit::
 
-  # echo 'hist:keys=skbaddr.hex:vals=len:pause' > \
-    /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+   # echo 'hist:keys=skbaddr.hex:vals=len:pause' > \
+      /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
 
-  # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
-    /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+    # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
+      /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
 
-  # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
-    /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+    # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
+      /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
 
   The above sets up an initially paused hist trigger which is unpaused
   and starts aggregating events when a given program is executed, and
@@ -172,8 +176,8 @@
   The examples below provide a more concrete illustration of the
   concepts and typical usage patterns discussed above.
 
-  'special' event fields
-  ------------------------
+'special' event fields
+------------------------
 
   There are a number of 'special event fields' available for use as
   keys or values in a hist trigger.  These look like and behave as if
@@ -182,14 +186,16 @@
   event, and can be used anywhere an actual event field could be.
   They are:
 
-    common_timestamp       u64 - timestamp (from ring buffer) associated
-                                 with the event, in nanoseconds.  May be
-				 modified by .usecs to have timestamps
-				 interpreted as microseconds.
-    cpu                    int - the cpu on which the event occurred.
+    ====================== ==== =======================================
+    common_timestamp       u64  timestamp (from ring buffer) associated
+                                with the event, in nanoseconds.  May be
+			        modified by .usecs to have timestamps
+			        interpreted as microseconds.
+    cpu                    int  the cpu on which the event occurred.
+    ====================== ==== =======================================
 
-  Extended error information
-  --------------------------
+Extended error information
+--------------------------
 
   For some error conditions encountered when invoking a hist trigger
   command, extended error information is available via the
@@ -199,7 +205,7 @@
   be available until the next hist trigger command for that event.
 
   If available for a given error condition, the extended error
-  information and usage takes the following form:
+  information and usage takes the following form::
 
     # echo xxx > /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger
     echo: write error: Invalid argument
@@ -213,7 +219,7 @@
 
   The first set of examples creates aggregations using the kmalloc
   event.  The fields that can be used for the hist trigger are listed
-  in the kmalloc event's format file:
+  in the kmalloc event's format file::
 
     # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/format
     name: kmalloc
@@ -232,7 +238,7 @@
 
   We'll start by creating a hist trigger that generates a simple table
   that lists the total number of bytes requested for each function in
-  the kernel that made one or more calls to kmalloc:
+  the kernel that made one or more calls to kmalloc::
 
     # echo 'hist:key=call_site:val=bytes_req' > \
             /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
@@ -247,7 +253,7 @@
 
   We'll let it run for awhile and then dump the contents of the 'hist'
   file in the kmalloc event's subdirectory (for readability, a number
-  of entries have been omitted):
+  of entries have been omitted)::
 
     # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
     # trigger info: hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
@@ -287,7 +293,7 @@
   specified in the trigger, followed by the value(s) also specified in
   the trigger.  At the beginning of the output is a line that displays
   the trigger info, which can also be displayed by reading the
-  'trigger' file:
+  'trigger' file::
 
     # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
     hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
@@ -317,7 +323,7 @@
   frequencies.
 
   To turn the hist trigger off, simply call up the trigger in the
-  command history and re-execute it with a '!' prepended:
+  command history and re-execute it with a '!' prepended::
 
     # echo '!hist:key=call_site:val=bytes_req' > \
            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
@@ -325,7 +331,7 @@
   Finally, notice that the call_site as displayed in the output above
   isn't really very useful.  It's an address, but normally addresses
   are displayed in hex.  To have a numeric field displayed as a hex
-  value, simply append '.hex' to the field name in the trigger:
+  value, simply append '.hex' to the field name in the trigger::
 
     # echo 'hist:key=call_site.hex:val=bytes_req' > \
            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
@@ -370,7 +376,7 @@
   when looking at text addresses are the corresponding symbols
   instead.  To have an address displayed as symbolic value instead,
   simply append '.sym' or '.sym-offset' to the field name in the
-  trigger:
+  trigger::
 
     # echo 'hist:key=call_site.sym:val=bytes_req' > \
            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
@@ -420,7 +426,7 @@
   run.  If instead we we wanted to see the top kmalloc callers in
   terms of the number of bytes requested rather than the number of
   calls, and we wanted the top caller to appear at the top, we can use
-  the 'sort' parameter, along with the 'descending' modifier:
+  the 'sort' parameter, along with the 'descending' modifier::
 
     # echo 'hist:key=call_site.sym:val=bytes_req:sort=bytes_req.descending' > \
            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
@@ -461,7 +467,7 @@
         Dropped: 0
 
   To display the offset and size information in addition to the symbol
-  name, just use 'sym-offset' instead:
+  name, just use 'sym-offset' instead::
 
     # echo 'hist:key=call_site.sym-offset:val=bytes_req:sort=bytes_req.descending' > \
            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
@@ -500,7 +506,7 @@
   We can also add multiple fields to the 'values' parameter.  For
   example, we might want to see the total number of bytes allocated
   alongside bytes requested, and display the result sorted by bytes
-  allocated in a descending order:
+  allocated in a descending order::
 
     # echo 'hist:keys=call_site.sym:values=bytes_req,bytes_alloc:sort=bytes_alloc.descending' > \
            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
@@ -543,7 +549,7 @@
   the hist trigger display symbolic call_sites, we can have the hist
   trigger additionally display the complete set of kernel stack traces
   that led to each call_site.  To do that, we simply use the special
-  value 'stacktrace' for the key parameter:
+  value 'stacktrace' for the key parameter::
 
     # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \
            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
@@ -554,7 +560,7 @@
   event, along with a running total of any of the event fields for
   that event.  Here we tally bytes requested and bytes allocated for
   every callpath in the system that led up to a kmalloc (in this case
-  every callpath to a kmalloc for a kernel compile):
+  every callpath to a kmalloc for a kernel compile)::
 
     # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
     # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active]
@@ -652,7 +658,7 @@
   gather and display sorted totals for each process, you can use the
   special .execname modifier to display the executable names for the
   processes in the table rather than raw pids.  The example below
-  keeps a per-process sum of total bytes read:
+  keeps a per-process sum of total bytes read::
 
     # echo 'hist:key=common_pid.execname:val=count:sort=count.descending' > \
            /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger
@@ -693,7 +699,7 @@
   gather and display a list of systemwide syscall hits, you can use
   the special .syscall modifier to display the syscall names rather
   than raw ids.  The example below keeps a running total of syscall
-  counts for the system during the run:
+  counts for the system during the run::
 
     # echo 'hist:key=id.syscall:val=hitcount' > \
            /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
@@ -735,19 +741,19 @@
         Entries: 72
         Dropped: 0
 
-    The syscall counts above provide a rough overall picture of system
-    call activity on the system; we can see for example that the most
-    popular system call on this system was the 'sys_ioctl' system call.
+  The syscall counts above provide a rough overall picture of system
+  call activity on the system; we can see for example that the most
+  popular system call on this system was the 'sys_ioctl' system call.
 
-    We can use 'compound' keys to refine that number and provide some
-    further insight as to which processes exactly contribute to the
-    overall ioctl count.
+  We can use 'compound' keys to refine that number and provide some
+  further insight as to which processes exactly contribute to the
+  overall ioctl count.
 
-    The command below keeps a hitcount for every unique combination of
-    system call id and pid - the end result is essentially a table
-    that keeps a per-pid sum of system call hits.  The results are
-    sorted using the system call id as the primary key, and the
-    hitcount sum as the secondary key:
+  The command below keeps a hitcount for every unique combination of
+  system call id and pid - the end result is essentially a table
+  that keeps a per-pid sum of system call hits.  The results are
+  sorted using the system call id as the primary key, and the
+  hitcount sum as the secondary key::
 
     # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount' > \
            /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
@@ -793,11 +799,11 @@
         Entries: 323
         Dropped: 0
 
-    The above list does give us a breakdown of the ioctl syscall by
-    pid, but it also gives us quite a bit more than that, which we
-    don't really care about at the moment.  Since we know the syscall
-    id for sys_ioctl (16, displayed next to the sys_ioctl name), we
-    can use that to filter out all the other syscalls:
+  The above list does give us a breakdown of the ioctl syscall by
+  pid, but it also gives us quite a bit more than that, which we
+  don't really care about at the moment.  Since we know the syscall
+  id for sys_ioctl (16, displayed next to the sys_ioctl name), we
+  can use that to filter out all the other syscalls::
 
     # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount if id == 16' > \
            /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
@@ -829,18 +835,18 @@
         Entries: 103
         Dropped: 0
 
-    The above output shows that 'compiz' and 'Xorg' are far and away
-    the heaviest ioctl callers (which might lead to questions about
-    whether they really need to be making all those calls and to
-    possible avenues for further investigation.)
+  The above output shows that 'compiz' and 'Xorg' are far and away
+  the heaviest ioctl callers (which might lead to questions about
+  whether they really need to be making all those calls and to
+  possible avenues for further investigation.)
 
-    The compound key examples used a key and a sum value (hitcount) to
-    sort the output, but we can just as easily use two keys instead.
-    Here's an example where we use a compound key composed of the the
-    common_pid and size event fields.  Sorting with pid as the primary
-    key and 'size' as the secondary key allows us to display an
-    ordered summary of the recvfrom sizes, with counts, received by
-    each process:
+  The compound key examples used a key and a sum value (hitcount) to
+  sort the output, but we can just as easily use two keys instead.
+  Here's an example where we use a compound key composed of the the
+  common_pid and size event fields.  Sorting with pid as the primary
+  key and 'size' as the secondary key allows us to display an
+  ordered summary of the recvfrom sizes, with counts, received by
+  each process::
 
     # echo 'hist:key=common_pid.execname,size:val=hitcount:sort=common_pid,size' > \
            /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/trigger
@@ -893,7 +899,7 @@
   demonstrates how you can manually pause and continue a hist trigger.
   In this example, we'll aggregate fork counts and don't expect a
   large number of entries in the hash table, so we'll drop it to a
-  much smaller number, say 256:
+  much smaller number, say 256::
 
     # echo 'hist:key=child_comm:val=hitcount:size=256' > \
            /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
@@ -929,7 +935,7 @@
 
   If we want to pause the hist trigger, we can simply append :pause to
   the command that started the trigger.  Notice that the trigger info
-  displays as [paused]:
+  displays as [paused]::
 
     # echo 'hist:key=child_comm:val=hitcount:size=256:pause' >> \
            /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
@@ -966,7 +972,7 @@
 
   To manually continue having the trigger aggregate events, append
   :cont instead.  Notice that the trigger info displays as [active]
-  again, and the data has changed:
+  again, and the data has changed::
 
     # echo 'hist:key=child_comm:val=hitcount:size=256:cont' >> \
            /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
@@ -1020,7 +1026,7 @@
   wget.
 
   First we set up an initially paused stacktrace trigger on the
-  netif_receive_skb event:
+  netif_receive_skb event::
 
     # echo 'hist:key=stacktrace:vals=len:pause' > \
            /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
@@ -1031,7 +1037,7 @@
   set up on netif_receive_skb if and only if it sees a
   sched_process_exec event with a filename of '/usr/bin/wget'.  When
   that happens, all netif_receive_skb events are aggregated into a
-  hash table keyed on stacktrace:
+  hash table keyed on stacktrace::
 
     # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
            /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
@@ -1039,7 +1045,7 @@
   The aggregation continues until the netif_receive_skb is paused
   again, which is what the following disable_hist event does by
   creating a similar setup on the sched_process_exit event, using the
-  filter 'comm==wget':
+  filter 'comm==wget'::
 
     # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
            /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
@@ -1051,7 +1057,7 @@
   The overall effect is that netif_receive_skb events are aggregated
   into the hash table for only the duration of the wget.  Executing a
   wget command and then listing the 'hist' file will display the
-  output generated by the wget command:
+  output generated by the wget command::
 
     $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
 
@@ -1136,13 +1142,13 @@
   Suppose we wanted to try another run of the previous example but
   this time also wanted to see the complete list of events that went
   into the histogram.  In order to avoid having to set everything up
-  again, we can just clear the histogram first:
+  again, we can just clear the histogram first::
 
     # echo 'hist:key=stacktrace:vals=len:clear' >> \
            /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
 
   Just to verify that it is in fact cleared, here's what we now see in
-  the hist file:
+  the hist file::
 
     # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
     # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
@@ -1156,7 +1162,7 @@
   event occurring during the new run, which are in fact the same
   events being aggregated into the hash table, we add some additional
   'enable_event' events to the triggering sched_process_exec and
-  sched_process_exit events as such:
+  sched_process_exit events as such::
 
     # echo 'enable_event:net:netif_receive_skb if filename==/usr/bin/wget' > \
            /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
@@ -1167,7 +1173,7 @@
   If you read the trigger files for the sched_process_exec and
   sched_process_exit triggers, you should see two triggers for each:
   one enabling/disabling the hist aggregation and the other
-  enabling/disabling the logging of events:
+  enabling/disabling the logging of events::
 
     # cat /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
     enable_event:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
@@ -1181,13 +1187,13 @@
   sched_process_exit events is hit and matches 'wget', it enables or
   disables both the histogram and the event log, and what you end up
   with is a hash table and set of events just covering the specified
-  duration.  Run the wget command again:
+  duration.  Run the wget command again::
 
     $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
 
   Displaying the 'hist' file should show something similar to what you
   saw in the last run, but this time you should also see the
-  individual events in the trace file:
+  individual events in the trace file::
 
     # cat /sys/kernel/debug/tracing/trace
 
@@ -1220,7 +1226,7 @@
   attached to a given event.  This capability can be useful for
   creating a set of different summaries derived from the same set of
   events, or for comparing the effects of different filters, among
-  other things.
+  other things::
 
     # echo 'hist:keys=skbaddr.hex:vals=len if len < 0' >> \
            /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
@@ -1241,7 +1247,7 @@
   any existing hist triggers beforehand).
 
   Displaying the contents of the 'hist' file for the event shows the
-  contents of all five histograms:
+  contents of all five histograms::
 
     # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
 
@@ -1361,7 +1367,7 @@
   output of events generated by tracepoints contained inside inline
   functions, but names can be used in a hist trigger on any event.
   For example, these two triggers when hit will update the same 'len'
-  field in the shared 'foo' histogram data:
+  field in the shared 'foo' histogram data::
 
     # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
            /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
@@ -1369,7 +1375,7 @@
            /sys/kernel/debug/tracing/events/net/netif_rx/trigger
 
   You can see that they're updating common histogram data by reading
-  each event's hist files at the same time:
+  each event's hist files at the same time::
 
     # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist;
       cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
@@ -1482,7 +1488,7 @@
   And here's an example that shows how to combine histogram data from
   any two events even if they don't share any 'compatible' fields
   other than 'hitcount' and 'stacktrace'.  These commands create a
-  couple of triggers named 'bar' using those fields:
+  couple of triggers named 'bar' using those fields::
 
     # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
            /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
@@ -1490,7 +1496,7 @@
           /sys/kernel/debug/tracing/events/net/netif_rx/trigger
 
   And displaying the output of either shows some interesting if
-  somewhat confusing output:
+  somewhat confusing output::
 
     # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
     # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
@@ -1705,7 +1711,7 @@ to any event field.
 
 Either keys or values can be saved and retrieved in this way.  This
 creates a variable named 'ts0' for a histogram entry with the key
-'next_pid':
+'next_pid'::
 
   # echo 'hist:keys=next_pid:vals=$ts0:ts0=common_timestamp ... >> \
 	event/trigger
@@ -1721,40 +1727,40 @@ Because 'vals=' is used, the common_timestamp variable value above
 will also be summed as a normal histogram value would (though for a
 timestamp it makes little sense).
 
-The below shows that a key value can also be saved in the same way:
+The below shows that a key value can also be saved in the same way::
 
   # echo 'hist:timer_pid=common_pid:key=timer_pid ...' >> event/trigger
 
 If a variable isn't a key variable or prefixed with 'vals=', the
 associated event field will be saved in a variable but won't be summed
-as a value:
+as a value::
 
   # echo 'hist:keys=next_pid:ts1=common_timestamp ...' >> event/trigger
 
 Multiple variables can be assigned at the same time.  The below would
 result in both ts0 and b being created as variables, with both
-common_timestamp and field1 additionally being summed as values:
+common_timestamp and field1 additionally being summed as values::
 
   # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ...' >> \
 	event/trigger
 
 Note that variable assignments can appear either preceding or
 following their use.  The command below behaves identically to the
-command above:
+command above::
 
   # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ...' >> \
 	event/trigger
 
 Any number of variables not bound to a 'vals=' prefix can also be
 assigned by simply separating them with colons.  Below is the same
-thing but without the values being summed in the histogram:
+thing but without the values being summed in the histogram::
 
   # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ...' >> event/trigger
 
 Variables set as above can be referenced and used in expressions on
 another event.
 
-For example, here's how a latency can be calculated:
+For example, here's how a latency can be calculated::
 
   # echo 'hist:keys=pid,prio:ts0=common_timestamp ...' >> event1/trigger
   # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ...' >> event2/trigger
@@ -1764,7 +1770,7 @@ variable ts0.  In the next line, ts0 is subtracted from the second
 event's timestamp to produce the latency, which is then assigned into
 yet another variable, 'wakeup_lat'.  The hist trigger below in turn
 makes use of the wakeup_lat variable to compute a combined latency
-using the same key and variable from yet another event:
+using the same key and variable from yet another event::
 
   # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ...' >> event3/trigger
 
@@ -1784,7 +1790,7 @@ separated by semicolons, to the tracing/synthetic_events file.
 
 For instance, the following creates a new event named 'wakeup_latency'
 with 3 fields: lat, pid, and prio.  Each of those fields is simply a
-variable reference to a variable on another event:
+variable reference to a variable on another event::
 
   # echo 'wakeup_latency \
           u64 lat; \
@@ -1793,13 +1799,13 @@ variable reference to a variable on another event:
 	  /sys/kernel/debug/tracing/synthetic_events
 
 Reading the tracing/synthetic_events file lists all the currently
-defined synthetic events, in this case the event defined above:
+defined synthetic events, in this case the event defined above::
 
   # cat /sys/kernel/debug/tracing/synthetic_events
     wakeup_latency u64 lat; pid_t pid; int prio
 
 An existing synthetic event definition can be removed by prepending
-the command that defined it with a '!':
+the command that defined it with a '!'::
 
   # echo '!wakeup_latency u64 lat pid_t pid int prio' >> \
     /sys/kernel/debug/tracing/synthetic_events
@@ -1811,13 +1817,13 @@ and variables defined on other events (see Section 2.2.3 below on
 how that is done using hist trigger 'onmatch' action). Once that is
 done, the 'wakeup_latency' synthetic event instance is created.
 
-A histogram can now be defined for the new synthetic event:
+A histogram can now be defined for the new synthetic event::
 
   # echo 'hist:keys=pid,prio,lat.log2:sort=pid,lat' >> \
         /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
 
 The new event is created under the tracing/events/synthetic/ directory
-and looks and behaves just like any other event:
+and looks and behaves just like any other event::
 
   # ls /sys/kernel/debug/tracing/events/synthetic/wakeup_latency
         enable  filter  format  hist  id  trigger
@@ -1872,74 +1878,74 @@ hist trigger specification.
     As an example the below defines a simple synthetic event and uses
     a variable defined on the sched_wakeup_new event as a parameter
     when invoking the synthetic event.  Here we define the synthetic
-    event:
+    event::
 
-    # echo 'wakeup_new_test pid_t pid' >> \
-           /sys/kernel/debug/tracing/synthetic_events
+      # echo 'wakeup_new_test pid_t pid' >> \
+             /sys/kernel/debug/tracing/synthetic_events
 
-    # cat /sys/kernel/debug/tracing/synthetic_events
-          wakeup_new_test pid_t pid
+      # cat /sys/kernel/debug/tracing/synthetic_events
+            wakeup_new_test pid_t pid
 
     The following hist trigger both defines the missing testpid
     variable and specifies an onmatch() action that generates a
     wakeup_new_test synthetic event whenever a sched_wakeup_new event
     occurs, which because of the 'if comm == "cyclictest"' filter only
-    happens when the executable is cyclictest:
+    happens when the executable is cyclictest::
 
-    # echo 'hist:keys=$testpid:testpid=pid:onmatch(sched.sched_wakeup_new).\
-            wakeup_new_test($testpid) if comm=="cyclictest"' >> \
-            /sys/kernel/debug/tracing/events/sched/sched_wakeup_new/trigger
+      # echo 'hist:keys=$testpid:testpid=pid:onmatch(sched.sched_wakeup_new).\
+              wakeup_new_test($testpid) if comm=="cyclictest"' >> \
+              /sys/kernel/debug/tracing/events/sched/sched_wakeup_new/trigger
 
     Creating and displaying a histogram based on those events is now
     just a matter of using the fields and new synthetic event in the
-    tracing/events/synthetic directory, as usual:
+    tracing/events/synthetic directory, as usual::
 
-    # echo 'hist:keys=pid:sort=pid' >> \
-           /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/trigger
+      # echo 'hist:keys=pid:sort=pid' >> \
+             /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/trigger
 
     Running 'cyclictest' should cause wakeup_new events to generate
     wakeup_new_test synthetic events which should result in histogram
-    output in the wakeup_new_test event's hist file:
+    output in the wakeup_new_test event's hist file::
 
-    # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/hist
+      # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/hist
 
     A more typical usage would be to use two events to calculate a
     latency.  The following example uses a set of hist triggers to
-    produce a 'wakeup_latency' histogram:
+    produce a 'wakeup_latency' histogram.
 
-    First, we define a 'wakeup_latency' synthetic event:
+    First, we define a 'wakeup_latency' synthetic event::
 
-    # echo 'wakeup_latency u64 lat; pid_t pid; int prio' >> \
-            /sys/kernel/debug/tracing/synthetic_events
+      # echo 'wakeup_latency u64 lat; pid_t pid; int prio' >> \
+              /sys/kernel/debug/tracing/synthetic_events
 
     Next, we specify that whenever we see a sched_waking event for a
-    cyclictest thread, save the timestamp in a 'ts0' variable:
+    cyclictest thread, save the timestamp in a 'ts0' variable::
 
-    # echo 'hist:keys=$saved_pid:saved_pid=pid:ts0=common_timestamp.usecs \
-            if comm=="cyclictest"' >> \
-	    /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+      # echo 'hist:keys=$saved_pid:saved_pid=pid:ts0=common_timestamp.usecs \
+              if comm=="cyclictest"' >> \
+	      /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
 
     Then, when the corresponding thread is actually scheduled onto the
     CPU by a sched_switch event, calculate the latency and use that
     along with another variable and an event field to generate a
-    wakeup_latency synthetic event:
+    wakeup_latency synthetic event::
 
-    # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:\
-            onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,\
-	            $saved_pid,next_prio) if next_comm=="cyclictest"' >> \
-	    /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
+      # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:\
+              onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,\
+	              $saved_pid,next_prio) if next_comm=="cyclictest"' >> \
+	      /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
 
     We also need to create a histogram on the wakeup_latency synthetic
-    event in order to aggregate the generated synthetic event data:
+    event in order to aggregate the generated synthetic event data::
 
-    # echo 'hist:keys=pid,prio,lat:sort=pid,lat' >> \
-            /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
+      # echo 'hist:keys=pid,prio,lat:sort=pid,lat' >> \
+              /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
 
     Finally, once we've run cyclictest to actually generate some
     events, we can see the output by looking at the wakeup_latency
-    synthetic event's hist file:
+    synthetic event's hist file::
 
-    # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/hist
+      # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/hist
 
   - onmax(var).save(field,..	.)
 
@@ -1961,38 +1967,38 @@ hist trigger specification.
     back to that pid, the timestamp difference is calculated.  If the
     resulting latency, stored in wakeup_lat, exceeds the current
     maximum latency, the values specified in the save() fields are
-    recorded:
+    recorded::
 
-    # echo 'hist:keys=pid:ts0=common_timestamp.usecs \
-            if comm=="cyclictest"' >> \
-            /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+      # echo 'hist:keys=pid:ts0=common_timestamp.usecs \
+              if comm=="cyclictest"' >> \
+              /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
 
-    # echo 'hist:keys=next_pid:\
-            wakeup_lat=common_timestamp.usecs-$ts0:\
-            onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) \
-            if next_comm=="cyclictest"' >> \
-            /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
+      # echo 'hist:keys=next_pid:\
+              wakeup_lat=common_timestamp.usecs-$ts0:\
+              onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) \
+              if next_comm=="cyclictest"' >> \
+              /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
 
     When the histogram is displayed, the max value and the saved
     values corresponding to the max are displayed following the rest
-    of the fields:
+    of the fields::
 
-    # cat /sys/kernel/debug/tracing/events/sched/sched_switch/hist
-      { next_pid:       2255 } hitcount:        239
-        common_timestamp-ts0:          0
-        max:         27
-	next_comm: cyclictest
-        prev_pid:          0  prev_prio:        120  prev_comm: swapper/1
+      # cat /sys/kernel/debug/tracing/events/sched/sched_switch/hist
+        { next_pid:       2255 } hitcount:        239
+          common_timestamp-ts0:          0
+          max:         27
+	  next_comm: cyclictest
+          prev_pid:          0  prev_prio:        120  prev_comm: swapper/1
 
-      { next_pid:       2256 } hitcount:       2355
-        common_timestamp-ts0: 0
-        max:         49  next_comm: cyclictest
-        prev_pid:          0  prev_prio:        120  prev_comm: swapper/0
+        { next_pid:       2256 } hitcount:       2355
+          common_timestamp-ts0: 0
+          max:         49  next_comm: cyclictest
+          prev_pid:          0  prev_prio:        120  prev_comm: swapper/0
 
-      Totals:
-          Hits: 12970
-          Entries: 2
-          Dropped: 0
+        Totals:
+            Hits: 12970
+            Entries: 2
+            Dropped: 0
 
 3. User space creating a trigger
 --------------------------------
@@ -2002,24 +2008,24 @@ ring buffer. This can also act like an event, by writing into the trigger
 file located in /sys/kernel/tracing/events/ftrace/print/
 
 Modifying cyclictest to write into the trace_marker file before it sleeps
-and after it wakes up, something like this:
+and after it wakes up, something like this::
 
-static void traceputs(char *str)
-{
+  static void traceputs(char *str)
+  {
 	/* tracemark_fd is the trace_marker file descriptor */
 	if (tracemark_fd < 0)
 		return;
 	/* write the tracemark message */
 	write(tracemark_fd, str, strlen(str));
-}
+  }
 
-And later add something like:
+And later add something like::
 
 	traceputs("start");
 	clock_nanosleep(...);
 	traceputs("end");
 
-We can make a histogram from this:
+We can make a histogram from this::
 
  # cd /sys/kernel/tracing
  # echo 'latency u64 lat' > synthetic_events
@@ -2034,7 +2040,7 @@ it will call the "latency" synthetic event with the calculated latency as its
 parameter. Finally, a histogram is added to the latency synthetic event to
 record the calculated latency along with the pid.
 
-Now running cyclictest with:
+Now running cyclictest with::
 
  # ./cyclictest -p80 -d0 -i250 -n -a -t --tracemark -b 1000
 
@@ -2049,297 +2055,297 @@ Now running cyclictest with:
 
 Note, the -b 1000 is used just to make --tracemark available.
 
-Then we can see the histogram created by this with:
+Then we can see the histogram created by this with::
 
  # cat events/synthetic/latency/hist
-# event histogram
-#
-# trigger info: hist:keys=lat,common_pid:vals=hitcount:sort=lat:size=2048 [active]
-#
-
-{ lat:        107, common_pid:       2039 } hitcount:          1
-{ lat:        122, common_pid:       2041 } hitcount:          1
-{ lat:        166, common_pid:       2039 } hitcount:          1
-{ lat:        174, common_pid:       2039 } hitcount:          1
-{ lat:        194, common_pid:       2041 } hitcount:          1
-{ lat:        196, common_pid:       2036 } hitcount:          1
-{ lat:        197, common_pid:       2038 } hitcount:          1
-{ lat:        198, common_pid:       2039 } hitcount:          1
-{ lat:        199, common_pid:       2039 } hitcount:          1
-{ lat:        200, common_pid:       2041 } hitcount:          1
-{ lat:        201, common_pid:       2039 } hitcount:          2
-{ lat:        202, common_pid:       2038 } hitcount:          1
-{ lat:        202, common_pid:       2043 } hitcount:          1
-{ lat:        203, common_pid:       2039 } hitcount:          1
-{ lat:        203, common_pid:       2036 } hitcount:          1
-{ lat:        203, common_pid:       2041 } hitcount:          1
-{ lat:        206, common_pid:       2038 } hitcount:          2
-{ lat:        207, common_pid:       2039 } hitcount:          1
-{ lat:        207, common_pid:       2036 } hitcount:          1
-{ lat:        208, common_pid:       2040 } hitcount:          1
-{ lat:        209, common_pid:       2043 } hitcount:          1
-{ lat:        210, common_pid:       2039 } hitcount:          1
-{ lat:        211, common_pid:       2039 } hitcount:          4
-{ lat:        212, common_pid:       2043 } hitcount:          1
-{ lat:        212, common_pid:       2039 } hitcount:          2
-{ lat:        213, common_pid:       2039 } hitcount:          1
-{ lat:        214, common_pid:       2038 } hitcount:          1
-{ lat:        214, common_pid:       2039 } hitcount:          2
-{ lat:        214, common_pid:       2042 } hitcount:          1
-{ lat:        215, common_pid:       2039 } hitcount:          1
-{ lat:        217, common_pid:       2036 } hitcount:          1
-{ lat:        217, common_pid:       2040 } hitcount:          1
-{ lat:        217, common_pid:       2039 } hitcount:          1
-{ lat:        218, common_pid:       2039 } hitcount:          6
-{ lat:        219, common_pid:       2039 } hitcount:          9
-{ lat:        220, common_pid:       2039 } hitcount:         11
-{ lat:        221, common_pid:       2039 } hitcount:          5
-{ lat:        221, common_pid:       2042 } hitcount:          1
-{ lat:        222, common_pid:       2039 } hitcount:          7
-{ lat:        223, common_pid:       2036 } hitcount:          1
-{ lat:        223, common_pid:       2039 } hitcount:          3
-{ lat:        224, common_pid:       2039 } hitcount:          4
-{ lat:        224, common_pid:       2037 } hitcount:          1
-{ lat:        224, common_pid:       2036 } hitcount:          2
-{ lat:        225, common_pid:       2039 } hitcount:          5
-{ lat:        225, common_pid:       2042 } hitcount:          1
-{ lat:        226, common_pid:       2039 } hitcount:          7
-{ lat:        226, common_pid:       2036 } hitcount:          4
-{ lat:        227, common_pid:       2039 } hitcount:          6
-{ lat:        227, common_pid:       2036 } hitcount:         12
-{ lat:        227, common_pid:       2043 } hitcount:          1
-{ lat:        228, common_pid:       2039 } hitcount:          7
-{ lat:        228, common_pid:       2036 } hitcount:         14
-{ lat:        229, common_pid:       2039 } hitcount:          9
-{ lat:        229, common_pid:       2036 } hitcount:          8
-{ lat:        229, common_pid:       2038 } hitcount:          1
-{ lat:        230, common_pid:       2039 } hitcount:         11
-{ lat:        230, common_pid:       2036 } hitcount:          6
-{ lat:        230, common_pid:       2043 } hitcount:          1
-{ lat:        230, common_pid:       2042 } hitcount:          2
-{ lat:        231, common_pid:       2041 } hitcount:          1
-{ lat:        231, common_pid:       2036 } hitcount:          6
-{ lat:        231, common_pid:       2043 } hitcount:          1
-{ lat:        231, common_pid:       2039 } hitcount:          8
-{ lat:        232, common_pid:       2037 } hitcount:          1
-{ lat:        232, common_pid:       2039 } hitcount:          6
-{ lat:        232, common_pid:       2040 } hitcount:          2
-{ lat:        232, common_pid:       2036 } hitcount:          5
-{ lat:        232, common_pid:       2043 } hitcount:          1
-{ lat:        233, common_pid:       2036 } hitcount:          5
-{ lat:        233, common_pid:       2039 } hitcount:         11
-{ lat:        234, common_pid:       2039 } hitcount:          4
-{ lat:        234, common_pid:       2038 } hitcount:          2
-{ lat:        234, common_pid:       2043 } hitcount:          2
-{ lat:        234, common_pid:       2036 } hitcount:         11
-{ lat:        234, common_pid:       2040 } hitcount:          1
-{ lat:        235, common_pid:       2037 } hitcount:          2
-{ lat:        235, common_pid:       2036 } hitcount:          8
-{ lat:        235, common_pid:       2043 } hitcount:          2
-{ lat:        235, common_pid:       2039 } hitcount:          5
-{ lat:        235, common_pid:       2042 } hitcount:          2
-{ lat:        235, common_pid:       2040 } hitcount:          4
-{ lat:        235, common_pid:       2041 } hitcount:          1
-{ lat:        236, common_pid:       2036 } hitcount:          7
-{ lat:        236, common_pid:       2037 } hitcount:          1
-{ lat:        236, common_pid:       2041 } hitcount:          5
-{ lat:        236, common_pid:       2039 } hitcount:          3
-{ lat:        236, common_pid:       2043 } hitcount:          9
-{ lat:        236, common_pid:       2040 } hitcount:          7
-{ lat:        237, common_pid:       2037 } hitcount:          1
-{ lat:        237, common_pid:       2040 } hitcount:          1
-{ lat:        237, common_pid:       2036 } hitcount:          9
-{ lat:        237, common_pid:       2039 } hitcount:          3
-{ lat:        237, common_pid:       2043 } hitcount:          8
-{ lat:        237, common_pid:       2042 } hitcount:          2
-{ lat:        237, common_pid:       2041 } hitcount:          2
-{ lat:        238, common_pid:       2043 } hitcount:         10
-{ lat:        238, common_pid:       2040 } hitcount:          1
-{ lat:        238, common_pid:       2037 } hitcount:          9
-{ lat:        238, common_pid:       2038 } hitcount:          1
-{ lat:        238, common_pid:       2039 } hitcount:          1
-{ lat:        238, common_pid:       2042 } hitcount:          3
-{ lat:        238, common_pid:       2036 } hitcount:          7
-{ lat:        239, common_pid:       2041 } hitcount:          1
-{ lat:        239, common_pid:       2043 } hitcount:         11
-{ lat:        239, common_pid:       2037 } hitcount:         11
-{ lat:        239, common_pid:       2038 } hitcount:          6
-{ lat:        239, common_pid:       2036 } hitcount:          7
-{ lat:        239, common_pid:       2040 } hitcount:          1
-{ lat:        239, common_pid:       2042 } hitcount:          9
-{ lat:        240, common_pid:       2037 } hitcount:         29
-{ lat:        240, common_pid:       2043 } hitcount:         15
-{ lat:        240, common_pid:       2040 } hitcount:         44
-{ lat:        240, common_pid:       2039 } hitcount:          1
-{ lat:        240, common_pid:       2041 } hitcount:          2
-{ lat:        240, common_pid:       2038 } hitcount:          1
-{ lat:        240, common_pid:       2036 } hitcount:         10
-{ lat:        240, common_pid:       2042 } hitcount:         13
-{ lat:        241, common_pid:       2036 } hitcount:         21
-{ lat:        241, common_pid:       2041 } hitcount:         36
-{ lat:        241, common_pid:       2037 } hitcount:         34
-{ lat:        241, common_pid:       2042 } hitcount:         14
-{ lat:        241, common_pid:       2040 } hitcount:         94
-{ lat:        241, common_pid:       2039 } hitcount:         12
-{ lat:        241, common_pid:       2038 } hitcount:          2
-{ lat:        241, common_pid:       2043 } hitcount:         28
-{ lat:        242, common_pid:       2040 } hitcount:        109
-{ lat:        242, common_pid:       2041 } hitcount:        506
-{ lat:        242, common_pid:       2039 } hitcount:        155
-{ lat:        242, common_pid:       2042 } hitcount:         21
-{ lat:        242, common_pid:       2037 } hitcount:         52
-{ lat:        242, common_pid:       2043 } hitcount:         21
-{ lat:        242, common_pid:       2036 } hitcount:         16
-{ lat:        242, common_pid:       2038 } hitcount:        156
-{ lat:        243, common_pid:       2037 } hitcount:         46
-{ lat:        243, common_pid:       2039 } hitcount:         40
-{ lat:        243, common_pid:       2042 } hitcount:        119
-{ lat:        243, common_pid:       2041 } hitcount:        611
-{ lat:        243, common_pid:       2036 } hitcount:         69
-{ lat:        243, common_pid:       2038 } hitcount:        784
-{ lat:        243, common_pid:       2040 } hitcount:        323
-{ lat:        243, common_pid:       2043 } hitcount:         14
-{ lat:        244, common_pid:       2043 } hitcount:         35
-{ lat:        244, common_pid:       2042 } hitcount:        305
-{ lat:        244, common_pid:       2039 } hitcount:          8
-{ lat:        244, common_pid:       2040 } hitcount:       4515
-{ lat:        244, common_pid:       2038 } hitcount:        371
-{ lat:        244, common_pid:       2037 } hitcount:         31
-{ lat:        244, common_pid:       2036 } hitcount:        114
-{ lat:        244, common_pid:       2041 } hitcount:       3396
-{ lat:        245, common_pid:       2036 } hitcount:        700
-{ lat:        245, common_pid:       2041 } hitcount:       2772
-{ lat:        245, common_pid:       2037 } hitcount:        268
-{ lat:        245, common_pid:       2039 } hitcount:        472
-{ lat:        245, common_pid:       2038 } hitcount:       2758
-{ lat:        245, common_pid:       2042 } hitcount:       3833
-{ lat:        245, common_pid:       2040 } hitcount:       3105
-{ lat:        245, common_pid:       2043 } hitcount:        645
-{ lat:        246, common_pid:       2038 } hitcount:       3451
-{ lat:        246, common_pid:       2041 } hitcount:        142
-{ lat:        246, common_pid:       2037 } hitcount:       5101
-{ lat:        246, common_pid:       2040 } hitcount:         68
-{ lat:        246, common_pid:       2043 } hitcount:       5099
-{ lat:        246, common_pid:       2039 } hitcount:       5608
-{ lat:        246, common_pid:       2042 } hitcount:       3723
-{ lat:        246, common_pid:       2036 } hitcount:       4738
-{ lat:        247, common_pid:       2042 } hitcount:        312
-{ lat:        247, common_pid:       2043 } hitcount:       2385
-{ lat:        247, common_pid:       2041 } hitcount:        452
-{ lat:        247, common_pid:       2038 } hitcount:        792
-{ lat:        247, common_pid:       2040 } hitcount:         78
-{ lat:        247, common_pid:       2036 } hitcount:       2375
-{ lat:        247, common_pid:       2039 } hitcount:       1834
-{ lat:        247, common_pid:       2037 } hitcount:       2655
-{ lat:        248, common_pid:       2037 } hitcount:         36
-{ lat:        248, common_pid:       2042 } hitcount:         11
-{ lat:        248, common_pid:       2038 } hitcount:        122
-{ lat:        248, common_pid:       2036 } hitcount:        135
-{ lat:        248, common_pid:       2039 } hitcount:         26
-{ lat:        248, common_pid:       2041 } hitcount:        503
-{ lat:        248, common_pid:       2043 } hitcount:         66
-{ lat:        248, common_pid:       2040 } hitcount:         46
-{ lat:        249, common_pid:       2037 } hitcount:         29
-{ lat:        249, common_pid:       2038 } hitcount:          1
-{ lat:        249, common_pid:       2043 } hitcount:         29
-{ lat:        249, common_pid:       2039 } hitcount:          8
-{ lat:        249, common_pid:       2042 } hitcount:         56
-{ lat:        249, common_pid:       2040 } hitcount:         27
-{ lat:        249, common_pid:       2041 } hitcount:         11
-{ lat:        249, common_pid:       2036 } hitcount:         27
-{ lat:        250, common_pid:       2038 } hitcount:          1
-{ lat:        250, common_pid:       2036 } hitcount:         30
-{ lat:        250, common_pid:       2040 } hitcount:         19
-{ lat:        250, common_pid:       2043 } hitcount:         22
-{ lat:        250, common_pid:       2042 } hitcount:         20
-{ lat:        250, common_pid:       2041 } hitcount:          1
-{ lat:        250, common_pid:       2039 } hitcount:          6
-{ lat:        250, common_pid:       2037 } hitcount:         48
-{ lat:        251, common_pid:       2037 } hitcount:         43
-{ lat:        251, common_pid:       2039 } hitcount:          1
-{ lat:        251, common_pid:       2036 } hitcount:         12
-{ lat:        251, common_pid:       2042 } hitcount:          2
-{ lat:        251, common_pid:       2041 } hitcount:          1
-{ lat:        251, common_pid:       2043 } hitcount:         15
-{ lat:        251, common_pid:       2040 } hitcount:          3
-{ lat:        252, common_pid:       2040 } hitcount:          1
-{ lat:        252, common_pid:       2036 } hitcount:         12
-{ lat:        252, common_pid:       2037 } hitcount:         21
-{ lat:        252, common_pid:       2043 } hitcount:         14
-{ lat:        253, common_pid:       2037 } hitcount:         21
-{ lat:        253, common_pid:       2039 } hitcount:          2
-{ lat:        253, common_pid:       2036 } hitcount:          9
-{ lat:        253, common_pid:       2043 } hitcount:          6
-{ lat:        253, common_pid:       2040 } hitcount:          1
-{ lat:        254, common_pid:       2036 } hitcount:          8
-{ lat:        254, common_pid:       2043 } hitcount:          3
-{ lat:        254, common_pid:       2041 } hitcount:          1
-{ lat:        254, common_pid:       2042 } hitcount:          1
-{ lat:        254, common_pid:       2039 } hitcount:          1
-{ lat:        254, common_pid:       2037 } hitcount:         12
-{ lat:        255, common_pid:       2043 } hitcount:          1
-{ lat:        255, common_pid:       2037 } hitcount:          2
-{ lat:        255, common_pid:       2036 } hitcount:          2
-{ lat:        255, common_pid:       2039 } hitcount:          8
-{ lat:        256, common_pid:       2043 } hitcount:          1
-{ lat:        256, common_pid:       2036 } hitcount:          4
-{ lat:        256, common_pid:       2039 } hitcount:          6
-{ lat:        257, common_pid:       2039 } hitcount:          5
-{ lat:        257, common_pid:       2036 } hitcount:          4
-{ lat:        258, common_pid:       2039 } hitcount:          5
-{ lat:        258, common_pid:       2036 } hitcount:          2
-{ lat:        259, common_pid:       2036 } hitcount:          7
-{ lat:        259, common_pid:       2039 } hitcount:          7
-{ lat:        260, common_pid:       2036 } hitcount:          8
-{ lat:        260, common_pid:       2039 } hitcount:          6
-{ lat:        261, common_pid:       2036 } hitcount:          5
-{ lat:        261, common_pid:       2039 } hitcount:          7
-{ lat:        262, common_pid:       2039 } hitcount:          5
-{ lat:        262, common_pid:       2036 } hitcount:          5
-{ lat:        263, common_pid:       2039 } hitcount:          7
-{ lat:        263, common_pid:       2036 } hitcount:          7
-{ lat:        264, common_pid:       2039 } hitcount:          9
-{ lat:        264, common_pid:       2036 } hitcount:          9
-{ lat:        265, common_pid:       2036 } hitcount:          5
-{ lat:        265, common_pid:       2039 } hitcount:          1
-{ lat:        266, common_pid:       2036 } hitcount:          1
-{ lat:        266, common_pid:       2039 } hitcount:          3
-{ lat:        267, common_pid:       2036 } hitcount:          1
-{ lat:        267, common_pid:       2039 } hitcount:          3
-{ lat:        268, common_pid:       2036 } hitcount:          1
-{ lat:        268, common_pid:       2039 } hitcount:          6
-{ lat:        269, common_pid:       2036 } hitcount:          1
-{ lat:        269, common_pid:       2043 } hitcount:          1
-{ lat:        269, common_pid:       2039 } hitcount:          2
-{ lat:        270, common_pid:       2040 } hitcount:          1
-{ lat:        270, common_pid:       2039 } hitcount:          6
-{ lat:        271, common_pid:       2041 } hitcount:          1
-{ lat:        271, common_pid:       2039 } hitcount:          5
-{ lat:        272, common_pid:       2039 } hitcount:         10
-{ lat:        273, common_pid:       2039 } hitcount:          8
-{ lat:        274, common_pid:       2039 } hitcount:          2
-{ lat:        275, common_pid:       2039 } hitcount:          1
-{ lat:        276, common_pid:       2039 } hitcount:          2
-{ lat:        276, common_pid:       2037 } hitcount:          1
-{ lat:        276, common_pid:       2038 } hitcount:          1
-{ lat:        277, common_pid:       2039 } hitcount:          1
-{ lat:        277, common_pid:       2042 } hitcount:          1
-{ lat:        278, common_pid:       2039 } hitcount:          1
-{ lat:        279, common_pid:       2039 } hitcount:          4
-{ lat:        279, common_pid:       2043 } hitcount:          1
-{ lat:        280, common_pid:       2039 } hitcount:          3
-{ lat:        283, common_pid:       2036 } hitcount:          2
-{ lat:        284, common_pid:       2039 } hitcount:          1
-{ lat:        284, common_pid:       2043 } hitcount:          1
-{ lat:        288, common_pid:       2039 } hitcount:          1
-{ lat:        289, common_pid:       2039 } hitcount:          1
-{ lat:        300, common_pid:       2039 } hitcount:          1
-{ lat:        384, common_pid:       2039 } hitcount:          1
-
-Totals:
-    Hits: 67625
-    Entries: 278
-    Dropped: 0
+ # event histogram
+ #
+ # trigger info: hist:keys=lat,common_pid:vals=hitcount:sort=lat:size=2048 [active]
+ #
+
+ { lat:        107, common_pid:       2039 } hitcount:          1
+ { lat:        122, common_pid:       2041 } hitcount:          1
+ { lat:        166, common_pid:       2039 } hitcount:          1
+ { lat:        174, common_pid:       2039 } hitcount:          1
+ { lat:        194, common_pid:       2041 } hitcount:          1
+ { lat:        196, common_pid:       2036 } hitcount:          1
+ { lat:        197, common_pid:       2038 } hitcount:          1
+ { lat:        198, common_pid:       2039 } hitcount:          1
+ { lat:        199, common_pid:       2039 } hitcount:          1
+ { lat:        200, common_pid:       2041 } hitcount:          1
+ { lat:        201, common_pid:       2039 } hitcount:          2
+ { lat:        202, common_pid:       2038 } hitcount:          1
+ { lat:        202, common_pid:       2043 } hitcount:          1
+ { lat:        203, common_pid:       2039 } hitcount:          1
+ { lat:        203, common_pid:       2036 } hitcount:          1
+ { lat:        203, common_pid:       2041 } hitcount:          1
+ { lat:        206, common_pid:       2038 } hitcount:          2
+ { lat:        207, common_pid:       2039 } hitcount:          1
+ { lat:        207, common_pid:       2036 } hitcount:          1
+ { lat:        208, common_pid:       2040 } hitcount:          1
+ { lat:        209, common_pid:       2043 } hitcount:          1
+ { lat:        210, common_pid:       2039 } hitcount:          1
+ { lat:        211, common_pid:       2039 } hitcount:          4
+ { lat:        212, common_pid:       2043 } hitcount:          1
+ { lat:        212, common_pid:       2039 } hitcount:          2
+ { lat:        213, common_pid:       2039 } hitcount:          1
+ { lat:        214, common_pid:       2038 } hitcount:          1
+ { lat:        214, common_pid:       2039 } hitcount:          2
+ { lat:        214, common_pid:       2042 } hitcount:          1
+ { lat:        215, common_pid:       2039 } hitcount:          1
+ { lat:        217, common_pid:       2036 } hitcount:          1
+ { lat:        217, common_pid:       2040 } hitcount:          1
+ { lat:        217, common_pid:       2039 } hitcount:          1
+ { lat:        218, common_pid:       2039 } hitcount:          6
+ { lat:        219, common_pid:       2039 } hitcount:          9
+ { lat:        220, common_pid:       2039 } hitcount:         11
+ { lat:        221, common_pid:       2039 } hitcount:          5
+ { lat:        221, common_pid:       2042 } hitcount:          1
+ { lat:        222, common_pid:       2039 } hitcount:          7
+ { lat:        223, common_pid:       2036 } hitcount:          1
+ { lat:        223, common_pid:       2039 } hitcount:          3
+ { lat:        224, common_pid:       2039 } hitcount:          4
+ { lat:        224, common_pid:       2037 } hitcount:          1
+ { lat:        224, common_pid:       2036 } hitcount:          2
+ { lat:        225, common_pid:       2039 } hitcount:          5
+ { lat:        225, common_pid:       2042 } hitcount:          1
+ { lat:        226, common_pid:       2039 } hitcount:          7
+ { lat:        226, common_pid:       2036 } hitcount:          4
+ { lat:        227, common_pid:       2039 } hitcount:          6
+ { lat:        227, common_pid:       2036 } hitcount:         12
+ { lat:        227, common_pid:       2043 } hitcount:          1
+ { lat:        228, common_pid:       2039 } hitcount:          7
+ { lat:        228, common_pid:       2036 } hitcount:         14
+ { lat:        229, common_pid:       2039 } hitcount:          9
+ { lat:        229, common_pid:       2036 } hitcount:          8
+ { lat:        229, common_pid:       2038 } hitcount:          1
+ { lat:        230, common_pid:       2039 } hitcount:         11
+ { lat:        230, common_pid:       2036 } hitcount:          6
+ { lat:        230, common_pid:       2043 } hitcount:          1
+ { lat:        230, common_pid:       2042 } hitcount:          2
+ { lat:        231, common_pid:       2041 } hitcount:          1
+ { lat:        231, common_pid:       2036 } hitcount:          6
+ { lat:        231, common_pid:       2043 } hitcount:          1
+ { lat:        231, common_pid:       2039 } hitcount:          8
+ { lat:        232, common_pid:       2037 } hitcount:          1
+ { lat:        232, common_pid:       2039 } hitcount:          6
+ { lat:        232, common_pid:       2040 } hitcount:          2
+ { lat:        232, common_pid:       2036 } hitcount:          5
+ { lat:        232, common_pid:       2043 } hitcount:          1
+ { lat:        233, common_pid:       2036 } hitcount:          5
+ { lat:        233, common_pid:       2039 } hitcount:         11
+ { lat:        234, common_pid:       2039 } hitcount:          4
+ { lat:        234, common_pid:       2038 } hitcount:          2
+ { lat:        234, common_pid:       2043 } hitcount:          2
+ { lat:        234, common_pid:       2036 } hitcount:         11
+ { lat:        234, common_pid:       2040 } hitcount:          1
+ { lat:        235, common_pid:       2037 } hitcount:          2
+ { lat:        235, common_pid:       2036 } hitcount:          8
+ { lat:        235, common_pid:       2043 } hitcount:          2
+ { lat:        235, common_pid:       2039 } hitcount:          5
+ { lat:        235, common_pid:       2042 } hitcount:          2
+ { lat:        235, common_pid:       2040 } hitcount:          4
+ { lat:        235, common_pid:       2041 } hitcount:          1
+ { lat:        236, common_pid:       2036 } hitcount:          7
+ { lat:        236, common_pid:       2037 } hitcount:          1
+ { lat:        236, common_pid:       2041 } hitcount:          5
+ { lat:        236, common_pid:       2039 } hitcount:          3
+ { lat:        236, common_pid:       2043 } hitcount:          9
+ { lat:        236, common_pid:       2040 } hitcount:          7
+ { lat:        237, common_pid:       2037 } hitcount:          1
+ { lat:        237, common_pid:       2040 } hitcount:          1
+ { lat:        237, common_pid:       2036 } hitcount:          9
+ { lat:        237, common_pid:       2039 } hitcount:          3
+ { lat:        237, common_pid:       2043 } hitcount:          8
+ { lat:        237, common_pid:       2042 } hitcount:          2
+ { lat:        237, common_pid:       2041 } hitcount:          2
+ { lat:        238, common_pid:       2043 } hitcount:         10
+ { lat:        238, common_pid:       2040 } hitcount:          1
+ { lat:        238, common_pid:       2037 } hitcount:          9
+ { lat:        238, common_pid:       2038 } hitcount:          1
+ { lat:        238, common_pid:       2039 } hitcount:          1
+ { lat:        238, common_pid:       2042 } hitcount:          3
+ { lat:        238, common_pid:       2036 } hitcount:          7
+ { lat:        239, common_pid:       2041 } hitcount:          1
+ { lat:        239, common_pid:       2043 } hitcount:         11
+ { lat:        239, common_pid:       2037 } hitcount:         11
+ { lat:        239, common_pid:       2038 } hitcount:          6
+ { lat:        239, common_pid:       2036 } hitcount:          7
+ { lat:        239, common_pid:       2040 } hitcount:          1
+ { lat:        239, common_pid:       2042 } hitcount:          9
+ { lat:        240, common_pid:       2037 } hitcount:         29
+ { lat:        240, common_pid:       2043 } hitcount:         15
+ { lat:        240, common_pid:       2040 } hitcount:         44
+ { lat:        240, common_pid:       2039 } hitcount:          1
+ { lat:        240, common_pid:       2041 } hitcount:          2
+ { lat:        240, common_pid:       2038 } hitcount:          1
+ { lat:        240, common_pid:       2036 } hitcount:         10
+ { lat:        240, common_pid:       2042 } hitcount:         13
+ { lat:        241, common_pid:       2036 } hitcount:         21
+ { lat:        241, common_pid:       2041 } hitcount:         36
+ { lat:        241, common_pid:       2037 } hitcount:         34
+ { lat:        241, common_pid:       2042 } hitcount:         14
+ { lat:        241, common_pid:       2040 } hitcount:         94
+ { lat:        241, common_pid:       2039 } hitcount:         12
+ { lat:        241, common_pid:       2038 } hitcount:          2
+ { lat:        241, common_pid:       2043 } hitcount:         28
+ { lat:        242, common_pid:       2040 } hitcount:        109
+ { lat:        242, common_pid:       2041 } hitcount:        506
+ { lat:        242, common_pid:       2039 } hitcount:        155
+ { lat:        242, common_pid:       2042 } hitcount:         21
+ { lat:        242, common_pid:       2037 } hitcount:         52
+ { lat:        242, common_pid:       2043 } hitcount:         21
+ { lat:        242, common_pid:       2036 } hitcount:         16
+ { lat:        242, common_pid:       2038 } hitcount:        156
+ { lat:        243, common_pid:       2037 } hitcount:         46
+ { lat:        243, common_pid:       2039 } hitcount:         40
+ { lat:        243, common_pid:       2042 } hitcount:        119
+ { lat:        243, common_pid:       2041 } hitcount:        611
+ { lat:        243, common_pid:       2036 } hitcount:         69
+ { lat:        243, common_pid:       2038 } hitcount:        784
+ { lat:        243, common_pid:       2040 } hitcount:        323
+ { lat:        243, common_pid:       2043 } hitcount:         14
+ { lat:        244, common_pid:       2043 } hitcount:         35
+ { lat:        244, common_pid:       2042 } hitcount:        305
+ { lat:        244, common_pid:       2039 } hitcount:          8
+ { lat:        244, common_pid:       2040 } hitcount:       4515
+ { lat:        244, common_pid:       2038 } hitcount:        371
+ { lat:        244, common_pid:       2037 } hitcount:         31
+ { lat:        244, common_pid:       2036 } hitcount:        114
+ { lat:        244, common_pid:       2041 } hitcount:       3396
+ { lat:        245, common_pid:       2036 } hitcount:        700
+ { lat:        245, common_pid:       2041 } hitcount:       2772
+ { lat:        245, common_pid:       2037 } hitcount:        268
+ { lat:        245, common_pid:       2039 } hitcount:        472
+ { lat:        245, common_pid:       2038 } hitcount:       2758
+ { lat:        245, common_pid:       2042 } hitcount:       3833
+ { lat:        245, common_pid:       2040 } hitcount:       3105
+ { lat:        245, common_pid:       2043 } hitcount:        645
+ { lat:        246, common_pid:       2038 } hitcount:       3451
+ { lat:        246, common_pid:       2041 } hitcount:        142
+ { lat:        246, common_pid:       2037 } hitcount:       5101
+ { lat:        246, common_pid:       2040 } hitcount:         68
+ { lat:        246, common_pid:       2043 } hitcount:       5099
+ { lat:        246, common_pid:       2039 } hitcount:       5608
+ { lat:        246, common_pid:       2042 } hitcount:       3723
+ { lat:        246, common_pid:       2036 } hitcount:       4738
+ { lat:        247, common_pid:       2042 } hitcount:        312
+ { lat:        247, common_pid:       2043 } hitcount:       2385
+ { lat:        247, common_pid:       2041 } hitcount:        452
+ { lat:        247, common_pid:       2038 } hitcount:        792
+ { lat:        247, common_pid:       2040 } hitcount:         78
+ { lat:        247, common_pid:       2036 } hitcount:       2375
+ { lat:        247, common_pid:       2039 } hitcount:       1834
+ { lat:        247, common_pid:       2037 } hitcount:       2655
+ { lat:        248, common_pid:       2037 } hitcount:         36
+ { lat:        248, common_pid:       2042 } hitcount:         11
+ { lat:        248, common_pid:       2038 } hitcount:        122
+ { lat:        248, common_pid:       2036 } hitcount:        135
+ { lat:        248, common_pid:       2039 } hitcount:         26
+ { lat:        248, common_pid:       2041 } hitcount:        503
+ { lat:        248, common_pid:       2043 } hitcount:         66
+ { lat:        248, common_pid:       2040 } hitcount:         46
+ { lat:        249, common_pid:       2037 } hitcount:         29
+ { lat:        249, common_pid:       2038 } hitcount:          1
+ { lat:        249, common_pid:       2043 } hitcount:         29
+ { lat:        249, common_pid:       2039 } hitcount:          8
+ { lat:        249, common_pid:       2042 } hitcount:         56
+ { lat:        249, common_pid:       2040 } hitcount:         27
+ { lat:        249, common_pid:       2041 } hitcount:         11
+ { lat:        249, common_pid:       2036 } hitcount:         27
+ { lat:        250, common_pid:       2038 } hitcount:          1
+ { lat:        250, common_pid:       2036 } hitcount:         30
+ { lat:        250, common_pid:       2040 } hitcount:         19
+ { lat:        250, common_pid:       2043 } hitcount:         22
+ { lat:        250, common_pid:       2042 } hitcount:         20
+ { lat:        250, common_pid:       2041 } hitcount:          1
+ { lat:        250, common_pid:       2039 } hitcount:          6
+ { lat:        250, common_pid:       2037 } hitcount:         48
+ { lat:        251, common_pid:       2037 } hitcount:         43
+ { lat:        251, common_pid:       2039 } hitcount:          1
+ { lat:        251, common_pid:       2036 } hitcount:         12
+ { lat:        251, common_pid:       2042 } hitcount:          2
+ { lat:        251, common_pid:       2041 } hitcount:          1
+ { lat:        251, common_pid:       2043 } hitcount:         15
+ { lat:        251, common_pid:       2040 } hitcount:          3
+ { lat:        252, common_pid:       2040 } hitcount:          1
+ { lat:        252, common_pid:       2036 } hitcount:         12
+ { lat:        252, common_pid:       2037 } hitcount:         21
+ { lat:        252, common_pid:       2043 } hitcount:         14
+ { lat:        253, common_pid:       2037 } hitcount:         21
+ { lat:        253, common_pid:       2039 } hitcount:          2
+ { lat:        253, common_pid:       2036 } hitcount:          9
+ { lat:        253, common_pid:       2043 } hitcount:          6
+ { lat:        253, common_pid:       2040 } hitcount:          1
+ { lat:        254, common_pid:       2036 } hitcount:          8
+ { lat:        254, common_pid:       2043 } hitcount:          3
+ { lat:        254, common_pid:       2041 } hitcount:          1
+ { lat:        254, common_pid:       2042 } hitcount:          1
+ { lat:        254, common_pid:       2039 } hitcount:          1
+ { lat:        254, common_pid:       2037 } hitcount:         12
+ { lat:        255, common_pid:       2043 } hitcount:          1
+ { lat:        255, common_pid:       2037 } hitcount:          2
+ { lat:        255, common_pid:       2036 } hitcount:          2
+ { lat:        255, common_pid:       2039 } hitcount:          8
+ { lat:        256, common_pid:       2043 } hitcount:          1
+ { lat:        256, common_pid:       2036 } hitcount:          4
+ { lat:        256, common_pid:       2039 } hitcount:          6
+ { lat:        257, common_pid:       2039 } hitcount:          5
+ { lat:        257, common_pid:       2036 } hitcount:          4
+ { lat:        258, common_pid:       2039 } hitcount:          5
+ { lat:        258, common_pid:       2036 } hitcount:          2
+ { lat:        259, common_pid:       2036 } hitcount:          7
+ { lat:        259, common_pid:       2039 } hitcount:          7
+ { lat:        260, common_pid:       2036 } hitcount:          8
+ { lat:        260, common_pid:       2039 } hitcount:          6
+ { lat:        261, common_pid:       2036 } hitcount:          5
+ { lat:        261, common_pid:       2039 } hitcount:          7
+ { lat:        262, common_pid:       2039 } hitcount:          5
+ { lat:        262, common_pid:       2036 } hitcount:          5
+ { lat:        263, common_pid:       2039 } hitcount:          7
+ { lat:        263, common_pid:       2036 } hitcount:          7
+ { lat:        264, common_pid:       2039 } hitcount:          9
+ { lat:        264, common_pid:       2036 } hitcount:          9
+ { lat:        265, common_pid:       2036 } hitcount:          5
+ { lat:        265, common_pid:       2039 } hitcount:          1
+ { lat:        266, common_pid:       2036 } hitcount:          1
+ { lat:        266, common_pid:       2039 } hitcount:          3
+ { lat:        267, common_pid:       2036 } hitcount:          1
+ { lat:        267, common_pid:       2039 } hitcount:          3
+ { lat:        268, common_pid:       2036 } hitcount:          1
+ { lat:        268, common_pid:       2039 } hitcount:          6
+ { lat:        269, common_pid:       2036 } hitcount:          1
+ { lat:        269, common_pid:       2043 } hitcount:          1
+ { lat:        269, common_pid:       2039 } hitcount:          2
+ { lat:        270, common_pid:       2040 } hitcount:          1
+ { lat:        270, common_pid:       2039 } hitcount:          6
+ { lat:        271, common_pid:       2041 } hitcount:          1
+ { lat:        271, common_pid:       2039 } hitcount:          5
+ { lat:        272, common_pid:       2039 } hitcount:         10
+ { lat:        273, common_pid:       2039 } hitcount:          8
+ { lat:        274, common_pid:       2039 } hitcount:          2
+ { lat:        275, common_pid:       2039 } hitcount:          1
+ { lat:        276, common_pid:       2039 } hitcount:          2
+ { lat:        276, common_pid:       2037 } hitcount:          1
+ { lat:        276, common_pid:       2038 } hitcount:          1
+ { lat:        277, common_pid:       2039 } hitcount:          1
+ { lat:        277, common_pid:       2042 } hitcount:          1
+ { lat:        278, common_pid:       2039 } hitcount:          1
+ { lat:        279, common_pid:       2039 } hitcount:          4
+ { lat:        279, common_pid:       2043 } hitcount:          1
+ { lat:        280, common_pid:       2039 } hitcount:          3
+ { lat:        283, common_pid:       2036 } hitcount:          2
+ { lat:        284, common_pid:       2039 } hitcount:          1
+ { lat:        284, common_pid:       2043 } hitcount:          1
+ { lat:        288, common_pid:       2039 } hitcount:          1
+ { lat:        289, common_pid:       2039 } hitcount:          1
+ { lat:        300, common_pid:       2039 } hitcount:          1
+ { lat:        384, common_pid:       2039 } hitcount:          1
+
+ Totals:
+     Hits: 67625
+     Entries: 278
+     Dropped: 0
 
 Note, the writes are around the sleep, so ideally they will all be of 250
 microseconds. If you are wondering how there are several that are under
@@ -2350,7 +2356,7 @@ will be at 200 microseconds.
 
 But this could easily be done in userspace. To make this even more
 interesting, we can mix the histogram between events that happened in the
-kernel with trace_marker.
+kernel with trace_marker::
 
  # cd /sys/kernel/tracing
  # echo 'latency u64 lat' > synthetic_events
@@ -2362,177 +2368,177 @@ The difference this time is that instead of using the trace_marker to start
 the latency, the sched_waking event is used, matching the common_pid for the
 trace_marker write with the pid that is being woken by sched_waking.
 
-After running cyclictest again with the same parameters, we now have:
+After running cyclictest again with the same parameters, we now have::
 
  # cat events/synthetic/latency/hist
-# event histogram
-#
-# trigger info: hist:keys=lat,common_pid:vals=hitcount:sort=lat:size=2048 [active]
-#
-
-{ lat:          7, common_pid:       2302 } hitcount:        640
-{ lat:          7, common_pid:       2299 } hitcount:         42
-{ lat:          7, common_pid:       2303 } hitcount:         18
-{ lat:          7, common_pid:       2305 } hitcount:        166
-{ lat:          7, common_pid:       2306 } hitcount:          1
-{ lat:          7, common_pid:       2301 } hitcount:         91
-{ lat:          7, common_pid:       2300 } hitcount:         17
-{ lat:          8, common_pid:       2303 } hitcount:       8296
-{ lat:          8, common_pid:       2304 } hitcount:       6864
-{ lat:          8, common_pid:       2305 } hitcount:       9464
-{ lat:          8, common_pid:       2301 } hitcount:       9213
-{ lat:          8, common_pid:       2306 } hitcount:       6246
-{ lat:          8, common_pid:       2302 } hitcount:       8797
-{ lat:          8, common_pid:       2299 } hitcount:       8771
-{ lat:          8, common_pid:       2300 } hitcount:       8119
-{ lat:          9, common_pid:       2305 } hitcount:       1519
-{ lat:          9, common_pid:       2299 } hitcount:       2346
-{ lat:          9, common_pid:       2303 } hitcount:       2841
-{ lat:          9, common_pid:       2301 } hitcount:       1846
-{ lat:          9, common_pid:       2304 } hitcount:       3861
-{ lat:          9, common_pid:       2302 } hitcount:       1210
-{ lat:          9, common_pid:       2300 } hitcount:       2762
-{ lat:          9, common_pid:       2306 } hitcount:       4247
-{ lat:         10, common_pid:       2299 } hitcount:         16
-{ lat:         10, common_pid:       2306 } hitcount:        333
-{ lat:         10, common_pid:       2303 } hitcount:         16
-{ lat:         10, common_pid:       2304 } hitcount:        168
-{ lat:         10, common_pid:       2302 } hitcount:        240
-{ lat:         10, common_pid:       2301 } hitcount:         28
-{ lat:         10, common_pid:       2300 } hitcount:         95
-{ lat:         10, common_pid:       2305 } hitcount:         18
-{ lat:         11, common_pid:       2303 } hitcount:          5
-{ lat:         11, common_pid:       2305 } hitcount:          8
-{ lat:         11, common_pid:       2306 } hitcount:        221
-{ lat:         11, common_pid:       2302 } hitcount:         76
-{ lat:         11, common_pid:       2304 } hitcount:         26
-{ lat:         11, common_pid:       2300 } hitcount:        125
-{ lat:         11, common_pid:       2299 } hitcount:          2
-{ lat:         12, common_pid:       2305 } hitcount:          3
-{ lat:         12, common_pid:       2300 } hitcount:          6
-{ lat:         12, common_pid:       2306 } hitcount:         90
-{ lat:         12, common_pid:       2302 } hitcount:          4
-{ lat:         12, common_pid:       2303 } hitcount:          1
-{ lat:         12, common_pid:       2304 } hitcount:        122
-{ lat:         13, common_pid:       2300 } hitcount:         12
-{ lat:         13, common_pid:       2301 } hitcount:          1
-{ lat:         13, common_pid:       2306 } hitcount:         32
-{ lat:         13, common_pid:       2302 } hitcount:          5
-{ lat:         13, common_pid:       2305 } hitcount:          1
-{ lat:         13, common_pid:       2303 } hitcount:          1
-{ lat:         13, common_pid:       2304 } hitcount:         61
-{ lat:         14, common_pid:       2303 } hitcount:          4
-{ lat:         14, common_pid:       2306 } hitcount:          5
-{ lat:         14, common_pid:       2305 } hitcount:          4
-{ lat:         14, common_pid:       2304 } hitcount:         62
-{ lat:         14, common_pid:       2302 } hitcount:         19
-{ lat:         14, common_pid:       2300 } hitcount:         33
-{ lat:         14, common_pid:       2299 } hitcount:          1
-{ lat:         14, common_pid:       2301 } hitcount:          4
-{ lat:         15, common_pid:       2305 } hitcount:          1
-{ lat:         15, common_pid:       2302 } hitcount:         25
-{ lat:         15, common_pid:       2300 } hitcount:         11
-{ lat:         15, common_pid:       2299 } hitcount:          5
-{ lat:         15, common_pid:       2301 } hitcount:          1
-{ lat:         15, common_pid:       2304 } hitcount:          8
-{ lat:         15, common_pid:       2303 } hitcount:          1
-{ lat:         15, common_pid:       2306 } hitcount:          6
-{ lat:         16, common_pid:       2302 } hitcount:         31
-{ lat:         16, common_pid:       2306 } hitcount:          3
-{ lat:         16, common_pid:       2300 } hitcount:          5
-{ lat:         17, common_pid:       2302 } hitcount:          6
-{ lat:         17, common_pid:       2303 } hitcount:          1
-{ lat:         18, common_pid:       2304 } hitcount:          1
-{ lat:         18, common_pid:       2302 } hitcount:          8
-{ lat:         18, common_pid:       2299 } hitcount:          1
-{ lat:         18, common_pid:       2301 } hitcount:          1
-{ lat:         19, common_pid:       2303 } hitcount:          4
-{ lat:         19, common_pid:       2304 } hitcount:          5
-{ lat:         19, common_pid:       2302 } hitcount:          4
-{ lat:         19, common_pid:       2299 } hitcount:          3
-{ lat:         19, common_pid:       2306 } hitcount:          1
-{ lat:         19, common_pid:       2300 } hitcount:          4
-{ lat:         19, common_pid:       2305 } hitcount:          5
-{ lat:         20, common_pid:       2299 } hitcount:          2
-{ lat:         20, common_pid:       2302 } hitcount:          3
-{ lat:         20, common_pid:       2305 } hitcount:          1
-{ lat:         20, common_pid:       2300 } hitcount:          2
-{ lat:         20, common_pid:       2301 } hitcount:          2
-{ lat:         20, common_pid:       2303 } hitcount:          3
-{ lat:         21, common_pid:       2305 } hitcount:          1
-{ lat:         21, common_pid:       2299 } hitcount:          5
-{ lat:         21, common_pid:       2303 } hitcount:          4
-{ lat:         21, common_pid:       2302 } hitcount:          7
-{ lat:         21, common_pid:       2300 } hitcount:          1
-{ lat:         21, common_pid:       2301 } hitcount:          5
-{ lat:         21, common_pid:       2304 } hitcount:          2
-{ lat:         22, common_pid:       2302 } hitcount:          5
-{ lat:         22, common_pid:       2303 } hitcount:          1
-{ lat:         22, common_pid:       2306 } hitcount:          3
-{ lat:         22, common_pid:       2301 } hitcount:          2
-{ lat:         22, common_pid:       2300 } hitcount:          1
-{ lat:         22, common_pid:       2299 } hitcount:          1
-{ lat:         22, common_pid:       2305 } hitcount:          1
-{ lat:         22, common_pid:       2304 } hitcount:          1
-{ lat:         23, common_pid:       2299 } hitcount:          1
-{ lat:         23, common_pid:       2306 } hitcount:          2
-{ lat:         23, common_pid:       2302 } hitcount:          6
-{ lat:         24, common_pid:       2302 } hitcount:          3
-{ lat:         24, common_pid:       2300 } hitcount:          1
-{ lat:         24, common_pid:       2306 } hitcount:          2
-{ lat:         24, common_pid:       2305 } hitcount:          1
-{ lat:         24, common_pid:       2299 } hitcount:          1
-{ lat:         25, common_pid:       2300 } hitcount:          1
-{ lat:         25, common_pid:       2302 } hitcount:          4
-{ lat:         26, common_pid:       2302 } hitcount:          2
-{ lat:         27, common_pid:       2305 } hitcount:          1
-{ lat:         27, common_pid:       2300 } hitcount:          1
-{ lat:         27, common_pid:       2302 } hitcount:          3
-{ lat:         28, common_pid:       2306 } hitcount:          1
-{ lat:         28, common_pid:       2302 } hitcount:          4
-{ lat:         29, common_pid:       2302 } hitcount:          1
-{ lat:         29, common_pid:       2300 } hitcount:          2
-{ lat:         29, common_pid:       2306 } hitcount:          1
-{ lat:         29, common_pid:       2304 } hitcount:          1
-{ lat:         30, common_pid:       2302 } hitcount:          4
-{ lat:         31, common_pid:       2302 } hitcount:          6
-{ lat:         32, common_pid:       2302 } hitcount:          1
-{ lat:         33, common_pid:       2299 } hitcount:          1
-{ lat:         33, common_pid:       2302 } hitcount:          3
-{ lat:         34, common_pid:       2302 } hitcount:          2
-{ lat:         35, common_pid:       2302 } hitcount:          1
-{ lat:         35, common_pid:       2304 } hitcount:          1
-{ lat:         36, common_pid:       2302 } hitcount:          4
-{ lat:         37, common_pid:       2302 } hitcount:          6
-{ lat:         38, common_pid:       2302 } hitcount:          2
-{ lat:         39, common_pid:       2302 } hitcount:          2
-{ lat:         39, common_pid:       2304 } hitcount:          1
-{ lat:         40, common_pid:       2304 } hitcount:          2
-{ lat:         40, common_pid:       2302 } hitcount:          5
-{ lat:         41, common_pid:       2304 } hitcount:          1
-{ lat:         41, common_pid:       2302 } hitcount:          8
-{ lat:         42, common_pid:       2302 } hitcount:          6
-{ lat:         42, common_pid:       2304 } hitcount:          1
-{ lat:         43, common_pid:       2302 } hitcount:          3
-{ lat:         43, common_pid:       2304 } hitcount:          4
-{ lat:         44, common_pid:       2302 } hitcount:          6
-{ lat:         45, common_pid:       2302 } hitcount:          5
-{ lat:         46, common_pid:       2302 } hitcount:          5
-{ lat:         47, common_pid:       2302 } hitcount:          7
-{ lat:         48, common_pid:       2301 } hitcount:          1
-{ lat:         48, common_pid:       2302 } hitcount:          9
-{ lat:         49, common_pid:       2302 } hitcount:          3
-{ lat:         50, common_pid:       2302 } hitcount:          1
-{ lat:         50, common_pid:       2301 } hitcount:          1
-{ lat:         51, common_pid:       2302 } hitcount:          2
-{ lat:         51, common_pid:       2301 } hitcount:          1
-{ lat:         61, common_pid:       2302 } hitcount:          1
-{ lat:        110, common_pid:       2302 } hitcount:          1
-
-Totals:
-    Hits: 89565
-    Entries: 158
-    Dropped: 0
+ # event histogram
+ #
+ # trigger info: hist:keys=lat,common_pid:vals=hitcount:sort=lat:size=2048 [active]
+ #
+
+ { lat:          7, common_pid:       2302 } hitcount:        640
+ { lat:          7, common_pid:       2299 } hitcount:         42
+ { lat:          7, common_pid:       2303 } hitcount:         18
+ { lat:          7, common_pid:       2305 } hitcount:        166
+ { lat:          7, common_pid:       2306 } hitcount:          1
+ { lat:          7, common_pid:       2301 } hitcount:         91
+ { lat:          7, common_pid:       2300 } hitcount:         17
+ { lat:          8, common_pid:       2303 } hitcount:       8296
+ { lat:          8, common_pid:       2304 } hitcount:       6864
+ { lat:          8, common_pid:       2305 } hitcount:       9464
+ { lat:          8, common_pid:       2301 } hitcount:       9213
+ { lat:          8, common_pid:       2306 } hitcount:       6246
+ { lat:          8, common_pid:       2302 } hitcount:       8797
+ { lat:          8, common_pid:       2299 } hitcount:       8771
+ { lat:          8, common_pid:       2300 } hitcount:       8119
+ { lat:          9, common_pid:       2305 } hitcount:       1519
+ { lat:          9, common_pid:       2299 } hitcount:       2346
+ { lat:          9, common_pid:       2303 } hitcount:       2841
+ { lat:          9, common_pid:       2301 } hitcount:       1846
+ { lat:          9, common_pid:       2304 } hitcount:       3861
+ { lat:          9, common_pid:       2302 } hitcount:       1210
+ { lat:          9, common_pid:       2300 } hitcount:       2762
+ { lat:          9, common_pid:       2306 } hitcount:       4247
+ { lat:         10, common_pid:       2299 } hitcount:         16
+ { lat:         10, common_pid:       2306 } hitcount:        333
+ { lat:         10, common_pid:       2303 } hitcount:         16
+ { lat:         10, common_pid:       2304 } hitcount:        168
+ { lat:         10, common_pid:       2302 } hitcount:        240
+ { lat:         10, common_pid:       2301 } hitcount:         28
+ { lat:         10, common_pid:       2300 } hitcount:         95
+ { lat:         10, common_pid:       2305 } hitcount:         18
+ { lat:         11, common_pid:       2303 } hitcount:          5
+ { lat:         11, common_pid:       2305 } hitcount:          8
+ { lat:         11, common_pid:       2306 } hitcount:        221
+ { lat:         11, common_pid:       2302 } hitcount:         76
+ { lat:         11, common_pid:       2304 } hitcount:         26
+ { lat:         11, common_pid:       2300 } hitcount:        125
+ { lat:         11, common_pid:       2299 } hitcount:          2
+ { lat:         12, common_pid:       2305 } hitcount:          3
+ { lat:         12, common_pid:       2300 } hitcount:          6
+ { lat:         12, common_pid:       2306 } hitcount:         90
+ { lat:         12, common_pid:       2302 } hitcount:          4
+ { lat:         12, common_pid:       2303 } hitcount:          1
+ { lat:         12, common_pid:       2304 } hitcount:        122
+ { lat:         13, common_pid:       2300 } hitcount:         12
+ { lat:         13, common_pid:       2301 } hitcount:          1
+ { lat:         13, common_pid:       2306 } hitcount:         32
+ { lat:         13, common_pid:       2302 } hitcount:          5
+ { lat:         13, common_pid:       2305 } hitcount:          1
+ { lat:         13, common_pid:       2303 } hitcount:          1
+ { lat:         13, common_pid:       2304 } hitcount:         61
+ { lat:         14, common_pid:       2303 } hitcount:          4
+ { lat:         14, common_pid:       2306 } hitcount:          5
+ { lat:         14, common_pid:       2305 } hitcount:          4
+ { lat:         14, common_pid:       2304 } hitcount:         62
+ { lat:         14, common_pid:       2302 } hitcount:         19
+ { lat:         14, common_pid:       2300 } hitcount:         33
+ { lat:         14, common_pid:       2299 } hitcount:          1
+ { lat:         14, common_pid:       2301 } hitcount:          4
+ { lat:         15, common_pid:       2305 } hitcount:          1
+ { lat:         15, common_pid:       2302 } hitcount:         25
+ { lat:         15, common_pid:       2300 } hitcount:         11
+ { lat:         15, common_pid:       2299 } hitcount:          5
+ { lat:         15, common_pid:       2301 } hitcount:          1
+ { lat:         15, common_pid:       2304 } hitcount:          8
+ { lat:         15, common_pid:       2303 } hitcount:          1
+ { lat:         15, common_pid:       2306 } hitcount:          6
+ { lat:         16, common_pid:       2302 } hitcount:         31
+ { lat:         16, common_pid:       2306 } hitcount:          3
+ { lat:         16, common_pid:       2300 } hitcount:          5
+ { lat:         17, common_pid:       2302 } hitcount:          6
+ { lat:         17, common_pid:       2303 } hitcount:          1
+ { lat:         18, common_pid:       2304 } hitcount:          1
+ { lat:         18, common_pid:       2302 } hitcount:          8
+ { lat:         18, common_pid:       2299 } hitcount:          1
+ { lat:         18, common_pid:       2301 } hitcount:          1
+ { lat:         19, common_pid:       2303 } hitcount:          4
+ { lat:         19, common_pid:       2304 } hitcount:          5
+ { lat:         19, common_pid:       2302 } hitcount:          4
+ { lat:         19, common_pid:       2299 } hitcount:          3
+ { lat:         19, common_pid:       2306 } hitcount:          1
+ { lat:         19, common_pid:       2300 } hitcount:          4
+ { lat:         19, common_pid:       2305 } hitcount:          5
+ { lat:         20, common_pid:       2299 } hitcount:          2
+ { lat:         20, common_pid:       2302 } hitcount:          3
+ { lat:         20, common_pid:       2305 } hitcount:          1
+ { lat:         20, common_pid:       2300 } hitcount:          2
+ { lat:         20, common_pid:       2301 } hitcount:          2
+ { lat:         20, common_pid:       2303 } hitcount:          3
+ { lat:         21, common_pid:       2305 } hitcount:          1
+ { lat:         21, common_pid:       2299 } hitcount:          5
+ { lat:         21, common_pid:       2303 } hitcount:          4
+ { lat:         21, common_pid:       2302 } hitcount:          7
+ { lat:         21, common_pid:       2300 } hitcount:          1
+ { lat:         21, common_pid:       2301 } hitcount:          5
+ { lat:         21, common_pid:       2304 } hitcount:          2
+ { lat:         22, common_pid:       2302 } hitcount:          5
+ { lat:         22, common_pid:       2303 } hitcount:          1
+ { lat:         22, common_pid:       2306 } hitcount:          3
+ { lat:         22, common_pid:       2301 } hitcount:          2
+ { lat:         22, common_pid:       2300 } hitcount:          1
+ { lat:         22, common_pid:       2299 } hitcount:          1
+ { lat:         22, common_pid:       2305 } hitcount:          1
+ { lat:         22, common_pid:       2304 } hitcount:          1
+ { lat:         23, common_pid:       2299 } hitcount:          1
+ { lat:         23, common_pid:       2306 } hitcount:          2
+ { lat:         23, common_pid:       2302 } hitcount:          6
+ { lat:         24, common_pid:       2302 } hitcount:          3
+ { lat:         24, common_pid:       2300 } hitcount:          1
+ { lat:         24, common_pid:       2306 } hitcount:          2
+ { lat:         24, common_pid:       2305 } hitcount:          1
+ { lat:         24, common_pid:       2299 } hitcount:          1
+ { lat:         25, common_pid:       2300 } hitcount:          1
+ { lat:         25, common_pid:       2302 } hitcount:          4
+ { lat:         26, common_pid:       2302 } hitcount:          2
+ { lat:         27, common_pid:       2305 } hitcount:          1
+ { lat:         27, common_pid:       2300 } hitcount:          1
+ { lat:         27, common_pid:       2302 } hitcount:          3
+ { lat:         28, common_pid:       2306 } hitcount:          1
+ { lat:         28, common_pid:       2302 } hitcount:          4
+ { lat:         29, common_pid:       2302 } hitcount:          1
+ { lat:         29, common_pid:       2300 } hitcount:          2
+ { lat:         29, common_pid:       2306 } hitcount:          1
+ { lat:         29, common_pid:       2304 } hitcount:          1
+ { lat:         30, common_pid:       2302 } hitcount:          4
+ { lat:         31, common_pid:       2302 } hitcount:          6
+ { lat:         32, common_pid:       2302 } hitcount:          1
+ { lat:         33, common_pid:       2299 } hitcount:          1
+ { lat:         33, common_pid:       2302 } hitcount:          3
+ { lat:         34, common_pid:       2302 } hitcount:          2
+ { lat:         35, common_pid:       2302 } hitcount:          1
+ { lat:         35, common_pid:       2304 } hitcount:          1
+ { lat:         36, common_pid:       2302 } hitcount:          4
+ { lat:         37, common_pid:       2302 } hitcount:          6
+ { lat:         38, common_pid:       2302 } hitcount:          2
+ { lat:         39, common_pid:       2302 } hitcount:          2
+ { lat:         39, common_pid:       2304 } hitcount:          1
+ { lat:         40, common_pid:       2304 } hitcount:          2
+ { lat:         40, common_pid:       2302 } hitcount:          5
+ { lat:         41, common_pid:       2304 } hitcount:          1
+ { lat:         41, common_pid:       2302 } hitcount:          8
+ { lat:         42, common_pid:       2302 } hitcount:          6
+ { lat:         42, common_pid:       2304 } hitcount:          1
+ { lat:         43, common_pid:       2302 } hitcount:          3
+ { lat:         43, common_pid:       2304 } hitcount:          4
+ { lat:         44, common_pid:       2302 } hitcount:          6
+ { lat:         45, common_pid:       2302 } hitcount:          5
+ { lat:         46, common_pid:       2302 } hitcount:          5
+ { lat:         47, common_pid:       2302 } hitcount:          7
+ { lat:         48, common_pid:       2301 } hitcount:          1
+ { lat:         48, common_pid:       2302 } hitcount:          9
+ { lat:         49, common_pid:       2302 } hitcount:          3
+ { lat:         50, common_pid:       2302 } hitcount:          1
+ { lat:         50, common_pid:       2301 } hitcount:          1
+ { lat:         51, common_pid:       2302 } hitcount:          2
+ { lat:         51, common_pid:       2301 } hitcount:          1
+ { lat:         61, common_pid:       2302 } hitcount:          1
+ { lat:        110, common_pid:       2302 } hitcount:          1
+
+ Totals:
+     Hits: 89565
+     Entries: 158
+     Dropped: 0
 
 This doesn't tell us any information about how late cyclictest may have
 woken up, but it does show us a nice histogram of how long it took from
diff --git a/Documentation/trace/index.rst b/Documentation/trace/index.rst
index b58c10b04e27..306997941ba1 100644
--- a/Documentation/trace/index.rst
+++ b/Documentation/trace/index.rst
@@ -18,6 +18,7 @@ Linux Tracing Technologies
    events-nmi
    events-msr
    mmiotrace
+   histogram
    hwlat_detector
    intel_th
    stm
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index 3e0f971b12de..8bfc75c90806 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -18,7 +18,7 @@ To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
 Similar to the events tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
 /sys/kernel/debug/tracing/kprobe_events, and enable it via
-/sys/kernel/debug/tracing/events/kprobes/<EVENT>/enabled.
+/sys/kernel/debug/tracing/events/kprobes/<EVENT>/enable.
 
 
 Synopsis of kprobe_events
@@ -81,9 +81,9 @@ Per-probe event filtering feature allows you to set different filter on each
 probe and gives you what arguments will be shown in trace buffer. If an event
 name is specified right after 'p:' or 'r:' in kprobe_events, it adds an event
 under tracing/events/kprobes/<EVENT>, at the directory you can see 'id',
-'enabled', 'format' and 'filter'.
+'enable', 'format', 'filter' and 'trigger'.
 
-enabled:
+enable:
   You can enable/disable the probe by writing 1 or 0 on it.
 
 format:
@@ -95,6 +95,9 @@ filter:
 id:
   This shows the id of this probe event.
 
+trigger:
+  This allows to install trigger commands which are executed when the event is
+  hit (for details, see Documentation/trace/events.rst, section 6).
 
 Event Profiling
 ---------------
diff --git a/Documentation/trace/uprobetracer.rst b/Documentation/trace/uprobetracer.rst
index 98d3f692957a..d0822811527a 100644
--- a/Documentation/trace/uprobetracer.rst
+++ b/Documentation/trace/uprobetracer.rst
@@ -13,7 +13,7 @@ To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
 Similar to the kprobe-event tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
 /sys/kernel/debug/tracing/uprobe_events, and enable it via
-/sys/kernel/debug/tracing/events/uprobes/<EVENT>/enabled.
+/sys/kernel/debug/tracing/events/uprobes/<EVENT>/enable.
 
 However unlike kprobe-event tracer, the uprobe event interface expects the
 user to calculate the offset of the probepoint in the object.
diff --git a/Documentation/translations/index.rst b/Documentation/translations/index.rst
new file mode 100644
index 000000000000..7f77c52d33aa
--- /dev/null
+++ b/Documentation/translations/index.rst
@@ -0,0 +1,13 @@
+.. _translations:
+
+============
+Translations
+============
+
+.. toctree::
+   :maxdepth: 1
+
+   zh_CN/index
+   it_IT/index
+   ko_KR/index
+   ja_JP/index
diff --git a/Documentation/translations/it_IT/disclaimer-ita.rst b/Documentation/translations/it_IT/disclaimer-ita.rst
new file mode 100644
index 000000000000..d68e52de6a5d
--- /dev/null
+++ b/Documentation/translations/it_IT/disclaimer-ita.rst
@@ -0,0 +1,13 @@
+:orphan:
+
+.. note::
+   This document is maintained by Federico Vaga <federico.vaga@vaga.pv.it>.
+   If you find any difference between this document and the original file or a
+   problem with the translation, please contact the maintainer of this file.
+   Following people helped to translate or review:
+   Alessia Mantegazza <amantegazza@vaga.pv.it>
+
+.. warning::
+   The purpose of this file is to be easier to read and understand for Italian
+   speakers and is not intended as a fork. So, if you have any comments or
+   updates for this file please try to update the original English file first.
diff --git a/Documentation/translations/it_IT/doc-guide/index.rst b/Documentation/translations/it_IT/doc-guide/index.rst
new file mode 100644
index 000000000000..7a6562b547ee
--- /dev/null
+++ b/Documentation/translations/it_IT/doc-guide/index.rst
@@ -0,0 +1,24 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/doc-guide/index.rst <doc_guide>`
+
+.. _it_doc_guide:
+
+==========================================
+Come scrivere la documentazione del kernel
+==========================================
+
+.. toctree::
+   :maxdepth: 1
+
+   sphinx.rst
+   kernel-doc.rst
+   parse-headers.rst
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/translations/it_IT/doc-guide/kernel-doc.rst b/Documentation/translations/it_IT/doc-guide/kernel-doc.rst
new file mode 100644
index 000000000000..2bf1c1e2f394
--- /dev/null
+++ b/Documentation/translations/it_IT/doc-guide/kernel-doc.rst
@@ -0,0 +1,554 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/doc-guide/index.rst <doc_guide>`
+
+.. _it_kernel_doc:
+
+Scrivere i commenti in kernel-doc
+=================================
+
+Nei file sorgenti del kernel Linux potrete trovare commenti di documentazione
+strutturanti secondo il formato kernel-doc. Essi possono descrivere funzioni,
+tipi di dati, e l'architettura del codice.
+
+.. note:: Il formato kernel-doc può sembrare simile a gtk-doc o Doxygen ma
+   in realtà è molto differente per ragioni storiche. I sorgenti del kernel
+   contengono decine di migliaia di commenti kernel-doc. Siete pregati
+   d'attenervi allo stile qui descritto.
+
+La struttura kernel-doc è estratta a partire dai commenti; da questi viene
+generato il `dominio Sphinx per il C`_ con un'adeguata descrizione per le
+funzioni ed i tipi di dato con i loro relativi collegamenti. Le descrizioni
+vengono filtrare per cercare i riferimenti ed i marcatori.
+
+Vedere di seguito per maggiori dettagli.
+
+.. _`dominio Sphinx per il C`: http://www.sphinx-doc.org/en/stable/domains.html
+
+Tutte le funzioni esportate verso i moduli esterni utilizzando
+``EXPORT_SYMBOL`` o ``EXPORT_SYMBOL_GPL`` dovrebbero avere un commento
+kernel-doc. Quando l'intenzione è di utilizzarle nei moduli, anche le funzioni
+e le strutture dati nei file d'intestazione dovrebbero avere dei commenti
+kernel-doc.
+
+È considerata una buona pratica quella di fornire una documentazione formattata
+secondo kernel-doc per le funzioni che sono visibili da altri file del kernel
+(ovvero, che non siano dichiarate utilizzando ``static``). Raccomandiamo,
+inoltre, di fornire una documentazione kernel-doc anche per procedure private
+(ovvero, dichiarate "static") al fine di fornire una struttura più coerente
+dei sorgenti. Quest'ultima raccomandazione ha una priorità più bassa ed è a
+discrezione dal manutentore (MAINTAINER) del file sorgente.
+
+
+
+Sicuramente la documentazione formattata con kernel-doc è necessaria per
+le funzioni che sono esportate verso i moduli esterni utilizzando
+``EXPORT_SYMBOL`` o ``EXPORT_SYMBOL_GPL``.
+
+Cerchiamo anche di fornire una documentazione formattata secondo kernel-doc
+per le funzioni che sono visibili da altri file del kernel (ovvero, che non
+siano dichiarate utilizzando "static")
+
+Raccomandiamo, inoltre, di fornire una documentazione formattata con kernel-doc
+anche per procedure private (ovvero, dichiarate "static") al fine di fornire
+una struttura più coerente dei sorgenti. Questa raccomandazione ha una priorità
+più bassa ed è a discrezione dal manutentore (MAINTAINER) del file sorgente.
+
+Le strutture dati visibili nei file di intestazione dovrebbero essere anch'esse
+documentate utilizzando commenti formattati con kernel-doc.
+
+Come formattare i commenti kernel-doc
+-------------------------------------
+
+I commenti kernel-doc iniziano con il marcatore ``/**``. Il programma
+``kernel-doc`` estrarrà i commenti marchiati in questo modo. Il resto
+del commento è formattato come un normale commento multilinea, ovvero
+con un asterisco all'inizio d'ogni riga e che si conclude con ``*/``
+su una riga separata.
+
+I commenti kernel-doc di funzioni e tipi dovrebbero essere posizionati
+appena sopra la funzione od il tipo che descrivono. Questo allo scopo di
+aumentare la probabilità che chi cambia il codice si ricordi di aggiornare
+anche la documentazione. I commenti kernel-doc di tipo più generale possono
+essere posizionati ovunque nel file.
+
+Al fine di verificare che i commenti siano formattati correttamente, potete
+eseguire il programma ``kernel-doc`` con un livello di verbosità alto e senza
+che questo produca alcuna documentazione. Per esempio::
+
+	scripts/kernel-doc -v -none drivers/foo/bar.c
+
+Il formato della documentazione è verificato della procedura di generazione
+del kernel quando viene richiesto di effettuare dei controlli extra con GCC::
+
+	make W=n
+
+Documentare le funzioni
+------------------------
+
+Generalmente il formato di un commento kernel-doc per funzioni e
+macro simil-funzioni è il seguente::
+
+  /**
+   * function_name() - Brief description of function.
+   * @arg1: Describe the first argument.
+   * @arg2: Describe the second argument.
+   *        One can provide multiple line descriptions
+   *        for arguments.
+   *
+   * A longer description, with more discussion of the function function_name()
+   * that might be useful to those using or modifying it. Begins with an
+   * empty comment line, and may include additional embedded empty
+   * comment lines.
+   *
+   * The longer description may have multiple paragraphs.
+   *
+   * Context: Describes whether the function can sleep, what locks it takes,
+   *          releases, or expects to be held. It can extend over multiple
+   *          lines.
+   * Return: Describe the return value of foobar.
+   *
+   * The return value description can also have multiple paragraphs, and should
+   * be placed at the end of the comment block.
+   */
+
+La descrizione introduttiva (*brief description*) che segue il nome della
+funzione può continuare su righe successive e termina con la descrizione di
+un argomento, una linea di commento vuota, oppure la fine del commento.
+
+Parametri delle funzioni
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Ogni argomento di una funzione dovrebbe essere descritto in ordine, subito
+dopo la descrizione introduttiva.  Non lasciare righe vuote né fra la
+descrizione introduttiva e quella degli argomenti, né fra gli argomenti.
+
+Ogni ``@argument:`` può estendersi su più righe.
+
+.. note::
+
+   Se la descrizione di ``@argument:`` si estende su più righe,
+   la continuazione dovrebbe iniziare alla stessa colonna della riga
+   precedente::
+
+      * @argument: some long description
+      *            that continues on next lines
+
+   or::
+
+      * @argument:
+      *		some long description
+      *		that continues on next lines
+
+Se una funzione ha un numero variabile di argomento, la sua descrizione
+dovrebbe essere scritta con la notazione kernel-doc::
+
+      * @...: description
+
+Contesto delle funzioni
+~~~~~~~~~~~~~~~~~~~~~~~
+
+Il contesto in cui le funzioni vengono chiamate viene descritto in una
+sezione chiamata ``Context``. Questo dovrebbe informare sulla possibilità
+che una funzione dorma (*sleep*) o che possa essere chiamata in un contesto
+d'interruzione, così come i *lock* che prende, rilascia e che si aspetta che
+vengano presi dal chiamante.
+
+Esempi::
+
+  * Context: Any context.
+  * Context: Any context. Takes and releases the RCU lock.
+  * Context: Any context. Expects <lock> to be held by caller.
+  * Context: Process context. May sleep if @gfp flags permit.
+  * Context: Process context. Takes and releases <mutex>.
+  * Context: Softirq or process context. Takes and releases <lock>, BH-safe.
+  * Context: Interrupt context.
+
+Valore di ritorno
+~~~~~~~~~~~~~~~~~
+
+Il valore di ritorno, se c'è, viene descritto in una sezione dedicata di nome
+``Return``.
+
+.. note::
+
+  #) La descrizione multiriga non riconosce il termine d'una riga, per cui
+     se provate a formattare bene il vostro testo come nel seguente esempio::
+
+	* Return:
+	* 0 - OK
+	* -EINVAL - invalid argument
+	* -ENOMEM - out of memory
+
+     le righe verranno unite e il risultato sarà::
+
+	Return: 0 - OK -EINVAL - invalid argument -ENOMEM - out of memory
+
+     Quindi, se volete che le righe vengano effettivamente generate, dovete
+     utilizzare una lista ReST, ad esempio::
+
+      * Return:
+      * * 0		- OK to runtime suspend the device
+      * * -EBUSY	- Device should not be runtime suspended
+
+  #) Se il vostro testo ha delle righe che iniziano con una frase seguita dai
+     due punti, allora ognuna di queste frasi verrà considerata come il nome
+     di una nuova sezione, e probabilmente non produrrà gli effetti desiderati.
+
+Documentare strutture, unioni ed enumerazioni
+---------------------------------------------
+
+Generalmente il formato di un commento kernel-doc per struct, union ed enum è::
+
+  /**
+   * struct struct_name - Brief description.
+   * @member1: Description of member1.
+   * @member2: Description of member2.
+   *           One can provide multiple line descriptions
+   *           for members.
+   *
+   * Description of the structure.
+   */
+
+Nell'esempio qui sopra, potete sostituire ``struct`` con ``union`` o ``enum``
+per descrivere unioni ed enumerati. ``member`` viene usato per indicare i
+membri di strutture ed unioni, ma anche i valori di un tipo enumerato.
+
+La descrizione introduttiva (*brief description*) che segue il nome della
+funzione può continuare su righe successive e termina con la descrizione di
+un argomento, una linea di commento vuota, oppure la fine del commento.
+
+Membri
+~~~~~~
+
+I membri di strutture, unioni ed enumerati devo essere documentati come i
+parametri delle funzioni; seguono la descrizione introduttiva e possono
+estendersi su più righe.
+
+All'interno d'una struttura o d'un unione, potete utilizzare le etichette
+``private:`` e ``public:``. I campi che sono nell'area ``private:`` non
+verranno inclusi nella documentazione finale.
+
+Le etichette ``private:`` e ``public:`` devono essere messe subito dopo
+il marcatore di un commento ``/*``. Opzionalmente, possono includere commenti
+fra ``:`` e il marcatore di fine commento ``*/``.
+
+Esempio::
+
+  /**
+   * struct my_struct - short description
+   * @a: first member
+   * @b: second member
+   * @d: fourth member
+   *
+   * Longer description
+   */
+  struct my_struct {
+      int a;
+      int b;
+  /* private: internal use only */
+      int c;
+  /* public: the next one is public */
+      int d;
+  };
+
+Strutture ed unioni annidate
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+È possibile documentare strutture ed unioni annidate, ad esempio::
+
+      /**
+       * struct nested_foobar - a struct with nested unions and structs
+       * @memb1: first member of anonymous union/anonymous struct
+       * @memb2: second member of anonymous union/anonymous struct
+       * @memb3: third member of anonymous union/anonymous struct
+       * @memb4: fourth member of anonymous union/anonymous struct
+       * @bar: non-anonymous union
+       * @bar.st1: struct st1 inside @bar
+       * @bar.st2: struct st2 inside @bar
+       * @bar.st1.memb1: first member of struct st1 on union bar
+       * @bar.st1.memb2: second member of struct st1 on union bar
+       * @bar.st2.memb1: first member of struct st2 on union bar
+       * @bar.st2.memb2: second member of struct st2 on union bar
+       */
+      struct nested_foobar {
+        /* Anonymous union/struct*/
+        union {
+          struct {
+            int memb1;
+            int memb2;
+        }
+          struct {
+            void *memb3;
+            int memb4;
+          }
+        }
+        union {
+          struct {
+            int memb1;
+            int memb2;
+          } st1;
+          struct {
+            void *memb1;
+            int memb2;
+          } st2;
+        } bar;
+      };
+
+.. note::
+
+   #) Quando documentate una struttura od unione annidata, ad esempio
+      di nome ``foo``, il suo campo ``bar`` dev'essere documentato
+      usando ``@foo.bar:``
+   #) Quando la struttura od unione annidata è anonima, il suo campo
+      ``bar`` dev'essere documentato usando ``@bar:``
+
+Commenti in linea per la documentazione dei membri
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+I membri d'una struttura possono essere documentati in linea all'interno
+della definizione stessa. Ci sono due stili: una singola riga di commento
+che inizia con ``/**`` e finisce con ``*/``; commenti multi riga come
+qualsiasi altro commento kernel-doc::
+
+  /**
+   * struct foo - Brief description.
+   * @foo: The Foo member.
+   */
+  struct foo {
+        int foo;
+        /**
+         * @bar: The Bar member.
+         */
+        int bar;
+        /**
+         * @baz: The Baz member.
+         *
+         * Here, the member description may contain several paragraphs.
+         */
+        int baz;
+        union {
+                /** @foobar: Single line description. */
+                int foobar;
+        };
+        /** @bar2: Description for struct @bar2 inside @foo */
+        struct {
+                /**
+                 * @bar2.barbar: Description for @barbar inside @foo.bar2
+                 */
+                int barbar;
+        } bar2;
+  };
+
+
+Documentazione dei tipi di dato
+-------------------------------
+Generalmente il formato di un commento kernel-doc per typedef è
+il seguente::
+
+  /**
+   * typedef type_name - Brief description.
+   *
+   * Description of the type.
+   */
+
+Anche i tipi di dato per prototipi di funzione possono essere documentati::
+
+  /**
+   * typedef type_name - Brief description.
+   * @arg1: description of arg1
+   * @arg2: description of arg2
+   *
+   * Description of the type.
+   *
+   * Context: Locking context.
+   * Return: Meaning of the return value.
+   */
+   typedef void (*type_name)(struct v4l2_ctrl *arg1, void *arg2);
+
+Marcatori e riferimenti
+-----------------------
+
+All'interno dei commenti di tipo kernel-doc vengono riconosciuti i seguenti
+*pattern* che vengono convertiti in marcatori reStructuredText ed in riferimenti
+del `dominio Sphinx per il C`_.
+
+.. attention:: Questi sono riconosciuti **solo** all'interno di commenti
+               kernel-doc, e **non** all'interno di documenti reStructuredText.
+
+``funcname()``
+  Riferimento ad una funzione.
+
+``@parameter``
+  Nome di un parametro di una funzione (nessun riferimento, solo formattazione).
+
+``%CONST``
+  Il nome di una costante (nessun riferimento, solo formattazione)
+
+````literal````
+  Un blocco di testo che deve essere riportato così com'è. La rappresentazione
+  finale utilizzerà caratteri a ``spaziatura fissa``.
+
+  Questo è utile se dovete utilizzare caratteri speciali che altrimenti
+  potrebbero assumere un significato diverso in kernel-doc o in reStructuredText
+
+  Questo è particolarmente utile se dovete scrivere qualcosa come ``%ph``
+  all'interno della descrizione di una funzione.
+
+``$ENVVAR``
+  Il nome di una variabile d'ambiente (nessun riferimento, solo formattazione).
+
+``&struct name``
+  Riferimento ad una struttura.
+
+``&enum name``
+  Riferimento ad un'enumerazione.
+
+``&typedef name``
+  Riferimento ad un tipo di dato.
+
+``&struct_name->member`` or ``&struct_name.member``
+  Riferimento ad un membro di una struttura o di un'unione. Il riferimento sarà
+  la struttura o l'unione, non il memembro.
+
+``&name``
+  Un generico riferimento ad un tipo. Usate, preferibilmente, il riferimento
+  completo come descritto sopra. Questo è dedicato ai commenti obsoleti.
+
+Riferimenti usando reStructuredText
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Per fare riferimento a funzioni e tipi di dato definiti nei commenti kernel-doc
+all'interno dei documenti reStructuredText, utilizzate i riferimenti dal
+`dominio Sphinx per il C`_. Per esempio::
+
+  See function :c:func:`foo` and struct/union/enum/typedef :c:type:`bar`.
+
+Nonostante il riferimento ai tipi di dato funzioni col solo nome,
+ovvero senza specificare struct/union/enum/typedef, potreste preferire il
+seguente::
+
+  See :c:type:`struct foo <foo>`.
+  See :c:type:`union bar <bar>`.
+  See :c:type:`enum baz <baz>`.
+  See :c:type:`typedef meh <meh>`.
+
+Questo produce dei collegamenti migliori, ed è in linea con il modo in cui
+kernel-doc gestisce i riferimenti.
+
+Per maggiori informazioni, siete pregati di consultare la documentazione
+del `dominio Sphinx per il C`_.
+
+Commenti per una documentazione generale
+----------------------------------------
+
+Al fine d'avere il codice ed i commenti nello stesso file, potete includere
+dei blocchi di documentazione kernel-doc con un formato libero invece
+che nel formato specifico per funzioni, strutture, unioni, enumerati o tipi
+di dato. Per esempio, questo tipo di commento potrebbe essere usato per la
+spiegazione delle operazioni di un driver o di una libreria
+
+Questo s'ottiene utilizzando la parola chiave ``DOC:`` a cui viene associato
+un titolo.
+
+Generalmente il formato di un commento generico o di visione d'insieme è
+il seguente::
+
+  /**
+   * DOC: Theory of Operation
+   *
+   * The whizbang foobar is a dilly of a gizmo. It can do whatever you
+   * want it to do, at any time. It reads your mind. Here's how it works.
+   *
+   * foo bar splat
+   *
+   * The only drawback to this gizmo is that is can sometimes damage
+   * hardware, software, or its subject(s).
+   */
+
+Il titolo che segue ``DOC:`` funziona da intestazione all'interno del file
+sorgente, ma anche come identificatore per l'estrazione di questi commenti di
+documentazione. Quindi, il titolo dev'essere unico all'interno del file.
+
+Includere i commenti di tipo kernel-doc
+=======================================
+
+I commenti di documentazione possono essere inclusi in un qualsiasi documento
+di tipo reStructuredText mediante l'apposita direttiva nell'estensione
+kernel-doc per Sphinx.
+
+Le direttive kernel-doc sono nel formato::
+
+  .. kernel-doc:: source
+     :option:
+
+Il campo *source* è il percorso ad un file sorgente, relativo alla cartella
+principale dei sorgenti del kernel. La direttiva supporta le seguenti opzioni:
+
+export: *[source-pattern ...]*
+  Include la documentazione per tutte le funzioni presenti nel file sorgente
+  (*source*) che sono state esportate utilizzando ``EXPORT_SYMBOL`` o
+  ``EXPORT_SYMBOL_GPL`` in *source* o in qualsiasi altro *source-pattern*
+  specificato.
+
+  Il campo *source-patter* è utile quando i commenti kernel-doc sono stati
+  scritti nei file d'intestazione, mentre ``EXPORT_SYMBOL`` e
+  ``EXPORT_SYMBOL_GPL`` si trovano vicino alla definizione delle funzioni.
+
+  Esempi::
+
+    .. kernel-doc:: lib/bitmap.c
+       :export:
+
+    .. kernel-doc:: include/net/mac80211.h
+       :export: net/mac80211/*.c
+
+internal: *[source-pattern ...]*
+  Include la documentazione per tutte le funzioni ed i tipi presenti nel file
+  sorgente (*source*) che **non** sono stati esportati utilizzando
+  ``EXPORT_SYMBOL`` o ``EXPORT_SYMBOL_GPL`` né in *source* né in qualsiasi
+  altro *source-pattern* specificato.
+
+  Esempio::
+
+    .. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
+       :internal:
+
+doc: *title*
+  Include la documentazione del paragrafo ``DOC:`` identificato dal titolo
+  (*title*) all'interno del file sorgente (*source*). Gli spazi in *title* sono
+  permessi; non virgolettate *title*. Il campo *title* è utilizzato per
+  identificare un paragrafo e per questo non viene incluso nella documentazione
+  finale. Verificate d'avere l'intestazione appropriata nei documenti
+  reStructuredText.
+
+  Esempio::
+
+    .. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
+       :doc: High Definition Audio over HDMI and Display Port
+
+functions: *function* *[...]*
+  Dal file sorgente (*source*) include la documentazione per le funzioni
+  elencate (*function*).
+
+  Esempio::
+
+    .. kernel-doc:: lib/bitmap.c
+       :functions: bitmap_parselist bitmap_parselist_user
+
+Senza alcuna opzione, la direttiva kernel-doc include tutti i commenti di
+documentazione presenti nel file sorgente (*source*).
+
+L'estensione kernel-doc fa parte dei sorgenti del kernel, la si può trovare
+in ``Documentation/sphinx/kerneldoc.py``. Internamente, viene utilizzato
+lo script ``scripts/kernel-doc`` per estrarre i commenti di documentazione
+dai file sorgenti.
+
+Come utilizzare kernel-doc per generare pagine man
+--------------------------------------------------
+
+Se volete utilizzare kernel-doc solo per generare delle pagine man, potete
+farlo direttamente dai sorgenti del kernel::
+
+  $ scripts/kernel-doc -man $(git grep -l '/\*\*' -- :^Documentation :^tools) | scripts/split-man.pl /tmp/man
diff --git a/Documentation/translations/it_IT/doc-guide/parse-headers.rst b/Documentation/translations/it_IT/doc-guide/parse-headers.rst
new file mode 100644
index 000000000000..b38918ca637e
--- /dev/null
+++ b/Documentation/translations/it_IT/doc-guide/parse-headers.rst
@@ -0,0 +1,196 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/doc-guide/index.rst <doc_guide>`
+
+=========================================
+Includere gli i file di intestazione uAPI
+=========================================
+
+Qualche volta è utile includere dei file di intestazione e degli esempi di codice C
+al fine di descrivere l'API per lo spazio utente e per generare dei riferimenti
+fra il codice e la documentazione. Aggiungere i riferimenti ai file dell'API
+dello spazio utente ha ulteriori vantaggi: Sphinx genererà dei messaggi
+d'avviso se un simbolo non viene trovato nella documentazione. Questo permette
+di mantenere allineate la documentazione della uAPI (API spazio utente)
+con le modifiche del kernel.
+Il programma :ref:`parse_headers.pl <it_parse_headers>` genera questi riferimenti.
+Esso dev'essere invocato attraverso un Makefile, mentre si genera la
+documentazione. Per avere un esempio su come utilizzarlo all'interno del kernel
+consultate ``Documentation/media/Makefile``.
+
+.. _it_parse_headers:
+
+parse_headers.pl
+^^^^^^^^^^^^^^^^
+
+NOME
+****
+
+
+parse_headers.pl - analizza i file C al fine di identificare funzioni,
+strutture, enumerati e definizioni, e creare riferimenti per Sphinx
+
+SINTASSI
+********
+
+
+\ **parse_headers.pl**\  [<options>] <C_FILE> <OUT_FILE> [<EXCEPTIONS_FILE>]
+
+Dove <options> può essere: --debug, --usage o --help.
+
+
+OPZIONI
+*******
+
+
+
+\ **--debug**\
+
+ Lo script viene messo in modalità verbosa, utile per il debugging.
+
+
+\ **--usage**\
+
+ Mostra un messaggio d'aiuto breve e termina.
+
+
+\ **--help**\
+
+ Mostra un messaggio d'aiuto dettagliato e termina.
+
+
+DESCRIZIONE
+***********
+
+Converte un file d'intestazione o un file sorgente C (C_FILE) in un testo
+ReStructuredText incluso mediante il blocco ..parsed-literal
+con riferimenti alla documentazione che descrive l'API. Opzionalmente,
+il programma accetta anche un altro file (EXCEPTIONS_FILE) che
+descrive quali elementi debbano essere ignorati o il cui riferimento
+deve puntare ad elemento diverso dal predefinito.
+
+Il file generato sarà disponibile in (OUT_FILE).
+
+Il programma è capace di identificare *define*, funzioni, strutture,
+tipi di dato, enumerati e valori di enumerati, e di creare i riferimenti
+per ognuno di loro. Inoltre, esso è capace di distinguere le #define
+utilizzate per specificare i comandi ioctl di Linux.
+
+Il file EXCEPTIONS_FILE contiene due tipi di dichiarazioni:
+\ **ignore**\  o \ **replace**\ .
+
+La sintassi per ignore è:
+
+ignore \ **tipo**\  \ **nome**\
+
+La dichiarazione \ **ignore**\  significa che non verrà generato alcun
+riferimento per il simbolo \ **name**\  di tipo \ **tipo**\ .
+
+
+La sintassi per replace è:
+
+replace \ **tipo**\  \ **nome**\  \ **nuovo_valore**\
+
+La dichiarazione \ **replace**\  significa che verrà generato un
+riferimento per il simbolo \ **name**\ di tipo \ **tipo**\ , ma, invece
+di utilizzare il valore predefinito, verrà utilizzato il valore
+\ **nuovo_valore**\ .
+
+Per entrambe le dichiarazioni, il \ **tipo**\  può essere uno dei seguenti:
+
+
+\ **ioctl**\
+
+ La dichiarazione ignore o replace verrà applicata su definizioni di ioctl
+ come la seguente:
+
+ #define	VIDIOC_DBG_S_REGISTER 	 _IOW('V', 79, struct v4l2_dbg_register)
+
+
+
+\ **define**\
+
+ La dichiarazione ignore o replace verrà applicata su una qualsiasi #define
+ trovata in C_FILE.
+
+
+
+\ **typedef**\
+
+ La dichiarazione ignore o replace verrà applicata ad una dichiarazione typedef
+ in C_FILE.
+
+
+
+\ **struct**\
+
+ La dichiarazione ignore o replace verrà applicata ai nomi di strutture
+ in C_FILE.
+
+
+
+\ **enum**\
+
+ La dichiarazione ignore o replace verrà applicata ai nomi di enumerati
+ in C_FILE.
+
+
+
+\ **symbol**\
+
+ La dichiarazione ignore o replace verrà applicata ai nomi di valori di
+ enumerati in C_FILE.
+
+ Per le dichiarazioni di tipo replace, il campo \ **new_value**\  utilizzerà
+ automaticamente i riferimenti :c:type: per \ **typedef**\ , \ **enum**\  e
+ \ **struct**\. Invece, utilizzerà :ref: per \ **ioctl**\ , \ **define**\  e
+ \ **symbol**\. Il tipo di riferimento può essere definito esplicitamente
+ nella dichiarazione stessa.
+
+
+ESEMPI
+******
+
+
+ignore define _VIDEODEV2_H
+
+
+Ignora una definizione #define _VIDEODEV2_H nel file C_FILE.
+
+ignore symbol PRIVATE
+
+
+In un enumerato come il seguente:
+
+enum foo { BAR1, BAR2, PRIVATE };
+
+Non genererà alcun riferimento per \ **PRIVATE**\ .
+
+replace symbol BAR1 :c:type:\`foo\`
+replace symbol BAR2 :c:type:\`foo\`
+
+
+In un enumerato come il seguente:
+
+enum foo { BAR1, BAR2, PRIVATE };
+
+Genererà un riferimento ai valori BAR1 e BAR2 dal simbolo foo nel dominio C.
+
+
+BUGS
+****
+
+Riferire ogni malfunzionamento a Mauro Carvalho Chehab <mchehab@s-opensource.com>
+
+
+COPYRIGHT
+*********
+
+
+Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab@s-opensource.com>.
+
+Licenza GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>.
+
+Questo è software libero: siete liberi di cambiarlo e ridistribuirlo.
+Non c'è alcuna garanzia, nei limiti permessi dalla legge.
diff --git a/Documentation/translations/it_IT/doc-guide/sphinx.rst b/Documentation/translations/it_IT/doc-guide/sphinx.rst
new file mode 100644
index 000000000000..474b7e127893
--- /dev/null
+++ b/Documentation/translations/it_IT/doc-guide/sphinx.rst
@@ -0,0 +1,457 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/doc-guide/index.rst <doc_guide>`
+
+Introduzione
+============
+
+Il kernel Linux usa `Sphinx`_ per la generazione della documentazione a partire
+dai file `reStructuredText`_ che si trovano nella cartella ``Documentation``.
+Per generare la documentazione in HTML o PDF, usate comandi ``make htmldocs`` o
+``make pdfdocs``. La documentazione così generata sarà disponibile nella
+cartella ``Documentation/output``.
+
+.. _Sphinx: http://www.sphinx-doc.org/
+.. _reStructuredText: http://docutils.sourceforge.net/rst.html
+
+I file reStructuredText possono contenere delle direttive che permettono di
+includere i commenti di documentazione, o di tipo kernel-doc, dai file
+sorgenti.
+Solitamente questi commenti sono utilizzati per descrivere le funzioni, i tipi
+e l'architettura del codice. I commenti di tipo kernel-doc hanno una struttura
+e formato speciale, ma a parte questo vengono processati come reStructuredText.
+
+Inoltre, ci sono migliaia di altri documenti in formato testo sparsi nella
+cartella ``Documentation``. Alcuni di questi verranno probabilmente convertiti,
+nel tempo, in formato reStructuredText, ma la maggior parte di questi rimarranno
+in formato testo.
+
+.. _it_sphinx_install:
+
+Installazione Sphinx
+====================
+
+I marcatori ReST utilizzati nei file in Documentation/ sono pensati per essere
+processati da ``Sphinx`` nella versione 1.3 o superiore. Se desiderate produrre
+un documento PDF è raccomandato l'utilizzo di una versione superiore alle 1.4.6.
+
+Esiste uno script che verifica i requisiti Sphinx. Per ulteriori dettagli
+consultate :ref:`it_sphinx-pre-install`.
+
+La maggior parte delle distribuzioni Linux forniscono Sphinx, ma l'insieme dei
+programmi e librerie è fragile e non è raro che dopo un aggiornamento di
+Sphinx, o qualche altro pacchetto Python, la documentazione non venga più
+generata correttamente.
+
+Un modo per evitare questo genere di problemi è quello di utilizzare una
+versione diversa da quella fornita dalla vostra distribuzione. Per fare questo,
+vi raccomandiamo di installare Sphinx dentro ad un ambiente virtuale usando
+``virtualenv-3`` o ``virtualenv`` a seconda di come Python 3 è stato
+pacchettizzato dalla vostra distribuzione.
+
+.. note::
+
+   #) Le versioni di Sphinx inferiori alla 1.5 non funzionano bene
+      con il pacchetto Python docutils versione 0.13.1 o superiore.
+      Se volete usare queste versioni, allora dovere eseguire
+      ``pip install 'docutils==0.12'``.
+
+   #) Viene raccomandato l'uso del tema RTD per la documentazione in HTML.
+      A seconda della versione di Sphinx, potrebbe essere necessaria
+      l'installazione tramite il comando ``pip install sphinx_rtd_theme``.
+
+   #) Alcune pagine ReST contengono delle formule matematiche. A causa del
+      modo in cui Sphinx funziona, queste espressioni sono scritte
+      utilizzando LaTeX. Per una corretta interpretazione, è necessario aver
+      installato texlive con i pacchetti amdfonts e amsmath.
+
+Riassumendo, se volete installare la versione 1.4.9 di Sphinx dovete eseguire::
+
+       $ virtualenv sphinx_1.4
+       $ . sphinx_1.4/bin/activate
+       (sphinx_1.4) $ pip install -r Documentation/sphinx/requirements.txt
+
+Dopo aver eseguito ``. sphinx_1.4/bin/activate``, il prompt cambierà per
+indicare che state usando il nuovo ambiente. Se aprite un nuova sessione,
+prima di generare la documentazione, dovrete rieseguire questo comando per
+rientrare nell'ambiente virtuale.
+
+Generazione d'immagini
+----------------------
+
+Il meccanismo che genera la documentazione del kernel contiene un'estensione
+capace di gestire immagini in formato Graphviz e SVG (per maggior informazioni
+vedere :ref:`it_sphinx_kfigure`).
+
+Per far si che questo funzioni, dovete installare entrambe i pacchetti
+Graphviz e ImageMagick. Il sistema di generazione della documentazione è in
+grado di procedere anche se questi pacchetti non sono installati, ma il
+risultato, ovviamente, non includerà le immagini.
+
+Generazione in PDF e LaTeX
+--------------------------
+
+Al momento, la generazione di questi documenti è supportata solo dalle
+versioni di Sphinx superiori alla 1.4.
+
+Per la generazione di PDF e LaTeX, avrete bisogno anche del pacchetto
+``XeLaTeX`` nella versione 3.14159265
+
+Per alcune distribuzioni Linux potrebbe essere necessario installare
+anche una serie di pacchetti ``texlive`` in modo da fornire il supporto
+minimo per il funzionamento di ``XeLaTeX``.
+
+.. _it_sphinx-pre-install:
+
+Verificare le dipendenze Sphinx
+-------------------------------
+
+Esiste uno script che permette di verificare automaticamente le dipendenze di
+Sphinx. Se lo script riesce a riconoscere la vostra distribuzione, allora
+sarà in grado di darvi dei suggerimenti su come procedere per completare
+l'installazione::
+
+	$ ./scripts/sphinx-pre-install
+	Checking if the needed tools for Fedora release 26 (Twenty Six) are available
+	Warning: better to also install "texlive-luatex85".
+	You should run:
+
+		sudo dnf install -y texlive-luatex85
+		/usr/bin/virtualenv sphinx_1.4
+		. sphinx_1.4/bin/activate
+		pip install -r Documentation/sphinx/requirements.txt
+
+	Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468.
+
+L'impostazione predefinita prevede il controllo dei requisiti per la generazione
+di documenti html e PDF, includendo anche il supporto per le immagini, le
+espressioni matematiche e LaTeX; inoltre, presume che venga utilizzato un
+ambiente virtuale per Python. I requisiti per generare i documenti html
+sono considerati obbligatori, gli altri sono opzionali.
+
+Questo script ha i seguenti parametri:
+
+``--no-pdf``
+	Disabilita i controlli per la generazione di PDF;
+
+``--no-virtualenv``
+	Utilizza l'ambiente predefinito dal sistema operativo invece che
+	l'ambiente virtuale per Python;
+
+
+Generazione della documentazione Sphinx
+=======================================
+
+Per generare la documentazione in formato HTML o PDF si eseguono i rispettivi
+comandi ``make htmldocs`` o ``make pdfdocs``. Esistono anche altri formati
+in cui è possibile generare la documentazione; per maggiori informazioni
+potere eseguire il comando ``make help``.
+La documentazione così generata sarà disponibile nella sottocartella
+``Documentation/output``.
+
+Ovviamente, per generare la documentazione, Sphinx (``sphinx-build``)
+dev'essere installato. Se disponibile, il tema *Read the Docs* per Sphinx
+verrà utilizzato per ottenere una documentazione HTML più gradevole.
+Per la documentazione in formato PDF, invece, avrete bisogno di ``XeLaTeX`
+e di ``convert(1)`` disponibile in ImageMagick (https://www.imagemagick.org).
+Tipicamente, tutti questi pacchetti sono disponibili e pacchettizzati nelle
+distribuzioni Linux.
+
+Per poter passare ulteriori opzioni a Sphinx potete utilizzare la variabile
+make ``SPHINXOPTS``. Per esempio, se volete che Sphinx sia più verboso durante
+la generazione potete usare il seguente comando ``make SPHINXOPTS=-v htmldocs``.
+
+Potete eliminare la documentazione generata tramite il comando
+``make cleandocs``.
+
+Scrivere la documentazione
+==========================
+
+Aggiungere nuova documentazione è semplice:
+
+1. aggiungete un file ``.rst`` nella sottocartella ``Documentation``
+2. aggiungete un riferimento ad esso nell'indice (`TOC tree`_) in
+   ``Documentation/index.rst``.
+
+.. _TOC tree: http://www.sphinx-doc.org/en/stable/markup/toctree.html
+
+Questo, di solito, è sufficiente per la documentazione più semplice (come
+quella che state leggendo ora), ma per una documentazione più elaborata è
+consigliato creare una sottocartella dedicata (o, quando possibile, utilizzarne
+una già esistente). Per esempio, il sottosistema grafico è documentato nella
+sottocartella ``Documentation/gpu``; questa documentazione è divisa in
+diversi file ``.rst`` ed un indice ``index.rst`` (con un ``toctree``
+dedicato) a cui si fa riferimento nell'indice principale.
+
+Consultate la documentazione di `Sphinx`_ e `reStructuredText`_ per maggiori
+informazione circa le loro potenzialità. In particolare, il
+`manuale introduttivo a reStructuredText`_ di Sphinx è un buon punto da
+cui cominciare. Esistono, inoltre, anche alcuni
+`costruttori specifici per Sphinx`_.
+
+.. _`manuale introduttivo a reStructuredText`: http://www.sphinx-doc.org/en/stable/rest.html
+.. _`costruttori specifici per Sphinx`: http://www.sphinx-doc.org/en/stable/markup/index.html
+
+Guide linea per la documentazione del kernel
+--------------------------------------------
+
+In questa sezione troverete alcune linee guida specifiche per la documentazione
+del kernel:
+
+* Non esagerate con i costrutti di reStructuredText. Mantenete la
+  documentazione semplice. La maggior parte della documentazione dovrebbe
+  essere testo semplice con una strutturazione minima che permetta la
+  conversione in diversi formati.
+
+* Mantenete la strutturazione il più fedele possibile all'originale quando
+  convertite un documento in formato reStructuredText.
+
+* Aggiornate i contenuti quando convertite della documentazione, non limitatevi
+  solo alla formattazione.
+
+* Mantenete la decorazione dei livelli di intestazione come segue:
+
+  1. ``=`` con una linea superiore per il titolo del documento::
+
+       ======
+       Titolo
+       ======
+
+  2. ``=`` per i capitoli::
+
+       Capitoli
+       ========
+
+  3. ``-`` per le sezioni::
+
+       Sezioni
+       -------
+
+  4. ``~`` per le sottosezioni::
+
+       Sottosezioni
+       ~~~~~~~~~~~~
+
+  Sebbene RST non forzi alcun ordine specifico (*Piuttosto che imporre
+  un numero ed un ordine fisso di decorazioni, l'ordine utilizzato sarà
+  quello incontrato*), avere uniformità dei livelli principali rende più
+  semplice la lettura dei documenti.
+
+* Per inserire blocchi di testo con caratteri a dimensione fissa (codici di
+  esempio, casi d'uso, eccetera): utilizzate ``::`` quando non è necessario
+  evidenziare la sintassi, specialmente per piccoli frammenti; invece,
+  utilizzate ``.. code-block:: <language>`` per blocchi di più lunghi che
+  potranno beneficiare dell'avere la sintassi evidenziata.
+
+
+Il dominio C
+------------
+
+Il **Dominio Sphinx C** (denominato c) è adatto alla documentazione delle API C.
+Per esempio, un prototipo di una funzione:
+
+.. code-block:: rst
+
+    .. c:function:: int ioctl( int fd, int request )
+
+Il dominio C per kernel-doc ha delle funzionalità aggiuntive. Per esempio,
+potete assegnare un nuovo nome di riferimento ad una funzione con un nome
+molto comune come ``open`` o ``ioctl``:
+
+.. code-block:: rst
+
+     .. c:function:: int ioctl( int fd, int request )
+        :name: VIDIOC_LOG_STATUS
+
+Il nome della funzione (per esempio ioctl) rimane nel testo ma il nome del suo
+riferimento cambia da ``ioctl`` a ``VIDIOC_LOG_STATUS``. Anche la voce
+nell'indice cambia in ``VIDIOC_LOG_STATUS`` e si potrà quindi fare riferimento
+a questa funzione scrivendo:
+
+.. code-block:: rst
+
+     :c:func:`VIDIOC_LOG_STATUS`
+
+
+Tabelle a liste
+---------------
+
+Raccomandiamo l'uso delle tabelle in formato lista (*list table*). Le tabelle
+in formato lista sono liste di liste. In confronto all'ASCII-art potrebbero
+non apparire di facile lettura nei file in formato testo. Il loro vantaggio è
+che sono facili da creare o modificare e che la differenza di una modifica è
+molto più significativa perché limitata alle modifiche del contenuto.
+
+La ``flat-table`` è anch'essa una lista di liste simile alle ``list-table``
+ma con delle funzionalità aggiuntive:
+
+* column-span: col ruolo ``cspan`` una cella può essere estesa attraverso
+  colonne successive
+
+* raw-span: col ruolo ``rspan`` una cella può essere estesa attraverso
+  righe successive
+
+* auto-span: la cella più a destra viene estesa verso destra per compensare
+  la mancanza di celle. Con l'opzione ``:fill-cells:`` questo comportamento
+  può essere cambiato da *auto-span* ad *auto-fill*, il quale inserisce
+  automaticamente celle (vuote) invece che estendere l'ultima.
+
+opzioni:
+
+* ``:header-rows:``   [int] conta le righe di intestazione
+* ``:stub-columns:``  [int] conta le colonne di stub
+* ``:widths:``        [[int] [int] ... ] larghezza delle colonne
+* ``:fill-cells:``    invece di estendere automaticamente una cella su quelle
+  mancanti, ne crea di vuote.
+
+ruoli:
+
+* ``:cspan:`` [int] colonne successive (*morecols*)
+* ``:rspan:`` [int] righe successive (*morerows*)
+
+L'esempio successivo mostra come usare questo marcatore. Il primo livello della
+nostra lista di liste è la *riga*. In una *riga* è possibile inserire solamente
+la lista di celle che compongono la *riga* stessa. Fanno eccezione i *commenti*
+( ``..`` ) ed i *collegamenti* (per esempio, un riferimento a
+``:ref:`last row <last row>``` / :ref:`last row <it last row>`)
+
+.. code-block:: rst
+
+   .. flat-table:: table title
+      :widths: 2 1 1 3
+
+      * - head col 1
+        - head col 2
+        - head col 3
+        - head col 4
+
+      * - column 1
+        - field 1.1
+        - field 1.2 with autospan
+
+      * - column 2
+        - field 2.1
+        - :rspan:`1` :cspan:`1` field 2.2 - 3.3
+
+      * .. _`it last row`:
+
+        - column 3
+
+Che verrà rappresentata nel seguente modo:
+
+   .. flat-table:: table title
+      :widths: 2 1 1 3
+
+      * - head col 1
+        - head col 2
+        - head col 3
+        - head col 4
+
+      * - column 1
+        - field 1.1
+        - field 1.2 with autospan
+
+      * - column 2
+        - field 2.1
+        - :rspan:`1` :cspan:`1` field 2.2 - 3.3
+
+      * .. _`it last row`:
+
+        - column 3
+
+.. _it_sphinx_kfigure:
+
+Figure ed immagini
+==================
+
+Se volete aggiungere un'immagine, utilizzate le direttive ``kernel-figure``
+e ``kernel-image``. Per esempio, per inserire una figura di un'immagine in
+formato SVG::
+
+    .. kernel-figure::  ../../../doc-guide/svg_image.svg
+       :alt:    una semplice immagine SVG
+
+       Una semplice immagine SVG
+
+.. _it_svg_image_example:
+
+.. kernel-figure::  ../../../doc-guide/svg_image.svg
+   :alt:    una semplice immagine SVG
+
+   Una semplice immagine SVG
+
+Le direttive del kernel per figure ed immagini supportano il formato **DOT**,
+per maggiori informazioni
+
+* DOT: http://graphviz.org/pdf/dotguide.pdf
+* Graphviz: http://www.graphviz.org/content/dot-language
+
+Un piccolo esempio (:ref:`it_hello_dot_file`)::
+
+  .. kernel-figure::  ../../../doc-guide/hello.dot
+     :alt:    ciao mondo
+
+     Esempio DOT
+
+.. _it_hello_dot_file:
+
+.. kernel-figure::  ../../../doc-guide/hello.dot
+   :alt:    ciao mondo
+
+   Esempio DOT
+
+Tramite la direttiva ``kernel-render`` è possibile aggiungere codice specifico;
+ad esempio nel formato **DOT** di Graphviz.::
+
+  .. kernel-render:: DOT
+     :alt: foobar digraph
+     :caption: Codice **DOT** (Graphviz) integrato
+
+     digraph foo {
+      "bar" -> "baz";
+     }
+
+La rappresentazione dipenderà dei programmi installati. Se avete Graphviz
+installato, vedrete un'immagine vettoriale. In caso contrario, il codice grezzo
+verrà rappresentato come *blocco testuale* (:ref:`it_hello_dot_render`).
+
+.. _it_hello_dot_render:
+
+.. kernel-render:: DOT
+   :alt: foobar digraph
+   :caption: Codice **DOT** (Graphviz) integrato
+
+   digraph foo {
+      "bar" -> "baz";
+   }
+
+La direttiva *render* ha tutte le opzioni della direttiva *figure*, con
+l'aggiunta dell'opzione ``caption``. Se ``caption`` ha un valore allora
+un nodo *figure* viene aggiunto. Altrimenti verrà aggiunto un nodo *image*.
+L'opzione ``caption`` è necessaria in caso si vogliano aggiungere dei
+riferimenti (:ref:`it_hello_svg_render`).
+
+Per la scrittura di codice **SVG**::
+
+  .. kernel-render:: SVG
+     :caption: Integrare codice **SVG**
+     :alt: so-nw-arrow
+
+     <?xml version="1.0" encoding="UTF-8"?>
+     <svg xmlns="http://www.w3.org/2000/svg" version="1.1" ...>
+        ...
+     </svg>
+
+.. _it_hello_svg_render:
+
+.. kernel-render:: SVG
+   :caption: Integrare codice **SVG**
+   :alt: so-nw-arrow
+
+   <?xml version="1.0" encoding="UTF-8"?>
+   <svg xmlns="http://www.w3.org/2000/svg"
+     version="1.1" baseProfile="full" width="70px" height="40px" viewBox="0 0 700 400">
+   <line x1="180" y1="370" x2="500" y2="50" stroke="black" stroke-width="15px"/>
+   <polygon points="585 0 525 25 585 50" transform="rotate(135 525 25)"/>
+   </svg>
diff --git a/Documentation/translations/it_IT/index.rst b/Documentation/translations/it_IT/index.rst
new file mode 100644
index 000000000000..898a7823a6f4
--- /dev/null
+++ b/Documentation/translations/it_IT/index.rst
@@ -0,0 +1,118 @@
+.. _it_linux_doc:
+
+===================
+Traduzione italiana
+===================
+
+L'obiettivo di questa traduzione è di rendere più facile la lettura e
+la comprensione per chi preferisce leggere in lingua italiana.
+Tenete presente che la documentazione di riferimento rimane comunque
+quella in lingua inglese: :ref:`linux_doc`
+
+Questa traduzione cerca di essere il più fedele possibile all'originale ma
+è ovvio che alcune frasi vadano trasformate: non aspettatevi una traduzione
+letterale. Quando possibile, si eviteranno gli inglesismi ed al loro posto
+verranno utilizzate le corrispettive parole italiane.
+
+Se notate che la traduzione non è più aggiornata potete contattare
+direttamente il manutentore della traduzione italiana.
+
+Se notate che la documentazione contiene errori o dimenticanze, allora
+verificate la documentazione di riferimento in lingua inglese. Se il problema
+è presente anche nella documentazione di riferimento, contattate il suo
+manutentore. Se avete problemi a scrivere in inglese, potete comunque
+riportare il problema al manutentore della traduzione italiana.
+
+Manutentore della traduzione italiana: Federico Vaga <federico.vaga@vaga.pv.it>
+
+La documentazione del kernel Linux
+==================================
+
+Questo è il livello principale della documentazione del kernel in
+lingua italiana. La traduzione è incompleta, noterete degli avvisi
+che vi segnaleranno la mancanza di una traduzione o di un gruppo di
+traduzioni.
+
+Più in generale, la documentazione, come il kernel stesso, sono in
+costante sviluppo; particolarmente vero in quanto stiamo lavorando
+alla riorganizzazione della documentazione in modo più coerente.
+I miglioramenti alla documentazione sono sempre i benvenuti; per cui,
+se vuoi aiutare, iscriviti alla lista di discussione linux-doc presso
+vger.kernel.org.
+
+Documentazione sulla licenza dei sorgenti
+-----------------------------------------
+
+I seguenti documenti descrivono la licenza usata nei sorgenti del kernel Linux
+(GPLv2), come licenziare i singoli file; inoltre troverete i riferimenti al
+testo integrale della licenza.
+
+.. warning::
+
+    TODO ancora da tradurre
+
+Documentazione per gli utenti
+-----------------------------
+
+I seguenti manuali sono scritti per gli *utenti* del kernel - ovvero,
+coloro che cercano di farlo funzionare in modo ottimale su un dato sistema
+
+.. warning::
+
+    TODO ancora da tradurre
+
+Documentazione per gli sviluppatori di applicazioni
+---------------------------------------------------
+
+Il manuale delle API verso lo spazio utente è una collezione di documenti
+che descrivono le interfacce del kernel viste dagli sviluppatori
+di applicazioni.
+
+.. warning::
+
+    TODO ancora da tradurre
+
+
+Introduzione allo sviluppo del kernel
+-------------------------------------
+
+Questi manuali contengono informazioni su come contribuire allo sviluppo
+del kernel.
+Attorno al kernel Linux gira una comunità molto grande con migliaia di
+sviluppatori che contribuiscono ogni anno. Come in ogni grande comunità,
+sapere come le cose vengono fatte renderà il processo di integrazione delle
+vostre modifiche molto più semplice
+
+.. toctree::
+   :maxdepth: 2
+
+   doc-guide/index
+   kernel-hacking/index
+
+.. warning::
+
+    TODO ancora da tradurre
+
+Documentazione della API del kernel
+-----------------------------------
+
+Questi manuali forniscono dettagli su come funzionano i sottosistemi del
+kernel dal punto di vista degli sviluppatori del kernel. Molte delle
+informazioni contenute in questi manuali sono prese direttamente dai
+file sorgenti, informazioni aggiuntive vengono aggiunte solo se necessarie
+(o almeno ci proviamo — probabilmente *non* tutto quello che è davvero
+necessario).
+
+.. warning::
+
+    TODO ancora da tradurre
+
+Documentazione specifica per architettura
+-----------------------------------------
+
+Questi manuali forniscono dettagli di programmazione per le diverse
+implementazioni d'architettura.
+
+.. warning::
+
+    TODO ancora da tradurre
diff --git a/Documentation/translations/it_IT/kernel-hacking/hacking.rst b/Documentation/translations/it_IT/kernel-hacking/hacking.rst
new file mode 100644
index 000000000000..7178e517af0a
--- /dev/null
+++ b/Documentation/translations/it_IT/kernel-hacking/hacking.rst
@@ -0,0 +1,855 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/kernel-hacking/hacking.rst <kernel_hacking_hack>`
+
+:Original: :ref:`Documentation/kernel-hacking/hacking.rst <kernel_hacking_hack>`
+:Translator: Federico Vaga <federico.vaga@vaga.pv.it>
+
+.. _it_kernel_hacking_hack:
+
+=================================================
+L'inaffidabile guida all'hacking del kernel Linux
+=================================================
+
+:Author: Rusty Russell
+
+Introduzione
+============
+
+Benvenuto, gentile lettore, alla notevole ed inaffidabile guida all'hacking
+del kernel Linux ad opera di Rusty. Questo documento descrive le procedure
+più usate ed i concetti necessari per scrivere codice per il kernel: lo scopo
+è di fornire ai programmatori C più esperti un manuale di base per sviluppo.
+Eviterò dettagli implementativi: per questo abbiamo il codice,
+ed ignorerò intere parti di alcune procedure.
+
+Prima di leggere questa guida, sappiate che non ho mai voluto scriverla,
+essendo esageratamente sotto qualificato, ma ho sempre voluto leggere
+qualcosa di simile, e quindi questa era l'unica via. Spero che possa
+crescere e diventare un compendio di buone pratiche, punti di partenza
+e generiche informazioni.
+
+Gli attori
+==========
+
+In qualsiasi momento ognuna delle CPU di un sistema può essere:
+
+-  non associata ad alcun processo, servendo un'interruzione hardware;
+
+-  non associata ad alcun processo, servendo un softirq o tasklet;
+
+-  in esecuzione nello spazio kernel, associata ad un processo
+   (contesto utente);
+
+-  in esecuzione di un processo nello spazio utente;
+
+Esiste un ordine fra questi casi. Gli ultimi due possono avvicendarsi (preempt)
+l'un l'altro, ma a parte questo esiste una gerarchia rigida: ognuno di questi
+può avvicendarsi solo ad uno di quelli sottostanti. Per esempio, mentre un
+softirq è in esecuzione su d'una CPU, nessun altro softirq può avvicendarsi
+nell'esecuzione, ma un'interruzione hardware può. Ciò nonostante, le altre CPU
+del sistema operano indipendentemente.
+
+Più avanti vedremo alcuni modi in cui dal contesto utente è possibile bloccare
+le interruzioni, così da impedirne davvero il diritto di prelazione.
+
+Contesto utente
+---------------
+
+Ci si trova nel contesto utente quando si arriva da una chiamata di sistema
+od altre eccezioni: come nello spazio utente, altre procedure più importanti,
+o le interruzioni, possono far valere il proprio diritto di prelazione sul
+vostro processo. Potete sospendere l'esecuzione chiamando :c:func:`schedule()`.
+
+.. note::
+
+    Si è sempre in contesto utente quando un modulo viene caricato o rimosso,
+    e durante le operazioni nello strato dei dispositivi a blocchi
+    (*block layer*).
+
+Nel contesto utente, il puntatore ``current`` (il quale indica il processo al
+momento in esecuzione) è valido, e :c:func:`in_interrupt()`
+(``include/linux/preempt.h``) è falsa.
+
+.. warning::
+
+    Attenzione che se avete la prelazione o i softirq disabilitati (vedere
+    di seguito), :c:func:`in_interrupt()` ritornerà un falso positivo.
+
+Interruzioni hardware (Hard IRQs)
+---------------------------------
+
+Temporizzatori, schede di rete e tastiere sono esempi di vero hardware
+che possono produrre interruzioni in un qualsiasi momento. Il kernel esegue
+i gestori d'interruzione che prestano un servizio all'hardware. Il kernel
+garantisce che questi gestori non vengano mai interrotti: se una stessa
+interruzione arriva, questa verrà accodata (o scartata).
+Dato che durante la loro esecuzione le interruzioni vengono disabilitate,
+i gestori d'interruzioni devono essere veloci: spesso si limitano
+esclusivamente a notificare la presa in carico dell'interruzione,
+programmare una 'interruzione software' per l'esecuzione e quindi terminare.
+
+Potete dire d'essere in una interruzione hardware perché :c:func:`in_irq()`
+ritorna vero.
+
+.. warning::
+
+    Attenzione, questa ritornerà un falso positivo se le interruzioni
+    sono disabilitate (vedere di seguito).
+
+Contesto d'interruzione software: softirq e tasklet
+---------------------------------------------------
+
+Quando una chiamata di sistema sta per tornare allo spazio utente,
+oppure un gestore d'interruzioni termina, qualsiasi 'interruzione software'
+marcata come pendente (solitamente da un'interruzione hardware) viene
+eseguita (``kernel/softirq.c``).
+
+La maggior parte del lavoro utile alla gestione di un'interruzione avviene qui.
+All'inizio della transizione ai sistemi multiprocessore, c'erano solo i
+cosiddetti 'bottom half' (BH), i quali non traevano alcun vantaggio da questi
+sistemi. Non appena abbandonammo i computer raffazzonati con fiammiferi e
+cicche, abbandonammo anche questa limitazione e migrammo alle interruzioni
+software 'softirqs'.
+
+Il file ``include/linux/interrupt.h`` elenca i differenti tipi di 'softirq'.
+Un tipo di softirq molto importante è il timer (``include/linux/timer.h``):
+potete programmarlo per far si che esegua funzioni dopo un determinato
+periodo di tempo.
+
+Dato che i softirq possono essere eseguiti simultaneamente su più di un
+processore, spesso diventa estenuante l'averci a che fare. Per questa ragione,
+i tasklet (``include/linux/interrupt.h``) vengo usati più di frequente:
+possono essere registrati dinamicamente (il che significa che potete averne
+quanti ne volete), e garantiscono che un qualsiasi tasklet verrà eseguito
+solo su un processore alla volta, sebbene diversi tasklet possono essere
+eseguiti simultaneamente.
+
+.. warning::
+
+    Il nome 'tasklet' è ingannevole: non hanno niente a che fare
+    con i 'processi' ('tasks'), e probabilmente hanno più a che vedere
+    con qualche pessima vodka che Alexey Kuznetsov si fece a quel tempo.
+
+Potete determinate se siete in un softirq (o tasklet) utilizzando la
+macro :c:func:`in_softirq()` (``include/linux/preempt.h``).
+
+.. warning::
+
+    State attenti che questa macro ritornerà un falso positivo
+    se :ref:`botton half lock <it_local_bh_disable>` è bloccato.
+
+Alcune regole basilari
+======================
+
+Nessuna protezione della memoria
+    Se corrompete la memoria, che sia in contesto utente o d'interruzione,
+    la macchina si pianterà. Siete sicuri che quello che volete fare
+    non possa essere fatto nello spazio utente?
+
+Nessun numero in virgola mobile o MMX
+    Il contesto della FPU non è salvato; anche se siete in contesto utente
+    lo stato dell'FPU probabilmente non corrisponde a quello del processo
+    corrente: vi incasinerete con lo stato di qualche altro processo. Se
+    volete davvero usare la virgola mobile, allora dovrete salvare e recuperare
+    lo stato dell'FPU (ed evitare cambi di contesto). Generalmente è una
+    cattiva idea; usate l'aritmetica a virgola fissa.
+
+Un limite rigido dello stack
+    A seconda della configurazione del kernel lo stack è fra 3K e 6K per la
+    maggior parte delle architetture a 32-bit; è di 14K per la maggior
+    parte di quelle a 64-bit; e spesso è condiviso con le interruzioni,
+    per cui non si può usare.
+    Evitare profonde ricorsioni ad enormi array locali nello stack
+    (allocateli dinamicamente).
+
+Il kernel Linux è portabile
+    Quindi mantenetelo tale. Il vostro codice dovrebbe essere a 64-bit ed
+    indipendente dall'ordine dei byte (endianess) di un processore. Inoltre,
+    dovreste minimizzare il codice specifico per un processore; per esempio
+    il codice assembly dovrebbe essere incapsulato in modo pulito e minimizzato
+    per facilitarne la migrazione. Generalmente questo codice dovrebbe essere
+    limitato alla parte di kernel specifica per un'architettura.
+
+ioctl: non scrivere nuove chiamate di sistema
+=============================================
+
+Una chiamata di sistema, generalmente, è scritta così::
+
+    asmlinkage long sys_mycall(int arg)
+    {
+            return 0;
+    }
+
+Primo, nella maggior parte dei casi non volete creare nuove chiamate di
+sistema.
+Create un dispositivo a caratteri ed implementate l'appropriata chiamata ioctl.
+Questo meccanismo è molto più flessibile delle chiamate di sistema: esso non
+dev'essere dichiarato in tutte le architetture nei file
+``include/asm/unistd.h`` e ``arch/kernel/entry.S``; inoltre, è improbabile
+che questo venga accettato da Linus.
+
+Se tutto quello che il vostro codice fa è leggere o scrivere alcuni parametri,
+considerate l'implementazione di un'interfaccia :c:func:`sysfs()`.
+
+All'interno di una ioctl vi trovate nel contesto utente di un processo. Quando
+avviene un errore dovete ritornare un valore negativo di errno (consultate
+``include/uapi/asm-generic/errno-base.h``,
+``include/uapi/asm-generic/errno.h`` e ``include/linux/errno.h``), altrimenti
+ritornate 0.
+
+Dopo aver dormito dovreste verificare se ci sono stati dei segnali: il modo
+Unix/Linux di gestire un segnale è di uscire temporaneamente dalla chiamata
+di sistema con l'errore ``-ERESTARTSYS``. La chiamata di sistema ritornerà
+al contesto utente, eseguirà il gestore del segnale e poi la vostra chiamata
+di sistema riprenderà (a meno che l'utente non l'abbia disabilitata). Quindi,
+dovreste essere pronti per continuare l'esecuzione, per esempio nel mezzo
+della manipolazione di una struttura dati.
+
+::
+
+    if (signal_pending(current))
+            return -ERESTARTSYS;
+
+Se dovete eseguire dei calcoli molto lunghi: pensate allo spazio utente.
+Se **davvero** volete farlo nel kernel ricordatevi di verificare periodicamente
+se dovete *lasciare* il processore (ricordatevi che, per ogni processore, c'è
+un sistema multi-processo senza diritto di prelazione).
+Esempio::
+
+    cond_resched(); /* Will sleep */
+
+Una breve nota sulla progettazione delle interfacce: il motto dei sistemi
+UNIX è "fornite meccanismi e non politiche"
+
+La ricetta per uno stallo
+=========================
+
+Non è permesso invocare una procedura che potrebbe dormire, fanno eccezione
+i seguenti casi:
+
+-  Siete in un contesto utente.
+
+-  Non trattenete alcun spinlock.
+
+-  Avete abilitato le interruzioni (in realtà, Andy Kleen dice che
+   lo schedulatore le abiliterà per voi, ma probabilmente questo non è quello
+   che volete).
+
+Da tener presente che alcune funzioni potrebbero dormire implicitamente:
+le più comuni sono quelle per l'accesso allo spazio utente (\*_user) e
+quelle per l'allocazione della memoria senza l'opzione ``GFP_ATOMIC``
+
+Dovreste sempre compilare il kernel con l'opzione ``CONFIG_DEBUG_ATOMIC_SLEEP``
+attiva, questa vi avviserà se infrangete una di queste regole.
+Se **infrangete** le regole, allora potreste bloccare il vostro scatolotto.
+
+Veramente.
+
+Alcune delle procedure più comuni
+=================================
+
+:c:func:`printk()`
+------------------
+
+Definita in ``include/linux/printk.h``
+
+:c:func:`printk()` fornisce messaggi alla console, dmesg, e al demone syslog.
+Essa è utile per il debugging o per la notifica di errori; può essere
+utilizzata anche all'interno del contesto d'interruzione, ma usatela con
+cautela: una macchina che ha la propria console inondata da messaggi diventa
+inutilizzabile. La funzione utilizza un formato stringa quasi compatibile con
+la printf ANSI C, e la concatenazione di una stringa C come primo argomento
+per indicare la "priorità"::
+
+    printk(KERN_INFO "i = %u\n", i);
+
+Consultate ``include/linux/kern_levels.h`` per gli altri valori ``KERN_``;
+questi sono interpretati da syslog come livelli. Un caso speciale:
+per stampare un indirizzo IP usate::
+
+    __be32 ipaddress;
+    printk(KERN_INFO "my ip: %pI4\n", &ipaddress);
+
+
+:c:func:`printk()` utilizza un buffer interno di 1K e non s'accorge di
+eventuali sforamenti. Accertatevi che vi basti.
+
+.. note::
+
+    Saprete di essere un vero hacker del kernel quando inizierete a digitare
+    nei vostri programmi utenti le printf come se fossero printk :)
+
+.. note::
+
+    Un'altra nota a parte: la versione originale di Unix 6 aveva un commento
+    sopra alla funzione printf: "Printf non dovrebbe essere usata per il
+    chiacchiericcio". Dovreste seguire questo consiglio.
+
+:c:func:`copy_to_user()` / :c:func:`copy_from_user()` / :c:func:`get_user()` / :c:func:`put_user()`
+---------------------------------------------------------------------------------------------------
+
+Definite in ``include/linux/uaccess.h`` / ``asm/uaccess.h``
+
+**[DORMONO]**
+
+:c:func:`put_user()` e :c:func:`get_user()` sono usate per ricevere ed
+impostare singoli valori (come int, char, o long) da e verso lo spazio utente.
+Un puntatore nello spazio utente non dovrebbe mai essere dereferenziato: i dati
+dovrebbero essere copiati usando suddette procedure. Entrambe ritornano
+``-EFAULT`` oppure 0.
+
+:c:func:`copy_to_user()` e :c:func:`copy_from_user()` sono più generiche:
+esse copiano una quantità arbitraria di dati da e verso lo spazio utente.
+
+.. warning::
+
+    Al contrario di:c:func:`put_user()` e :c:func:`get_user()`, queste
+    funzioni ritornano la quantità di dati copiati (0 è comunque un successo).
+
+[Sì, questa stupida interfaccia mi imbarazza. La battaglia torna in auge anno
+dopo anno. --RR]
+
+Le funzioni potrebbero dormire implicitamente. Queste non dovrebbero mai essere
+invocate fuori dal contesto utente (non ha senso), con le interruzioni
+disabilitate, o con uno spinlock trattenuto.
+
+:c:func:`kmalloc()`/:c:func:`kfree()`
+-------------------------------------
+
+Definite in ``include/linux/slab.h``
+
+**[POTREBBERO DORMIRE: LEGGI SOTTO]**
+
+Queste procedure sono utilizzate per la richiesta dinamica di un puntatore ad
+un pezzo di memoria allineato, esattamente come malloc e free nello spazio
+utente, ma :c:func:`kmalloc()` ha un argomento aggiuntivo per indicare alcune
+opzioni. Le opzioni più importanti sono:
+
+``GFP_KERNEL``
+    Potrebbe dormire per librarare della memoria. L'opzione fornisce il modo
+    più affidabile per allocare memoria, ma il suo uso è strettamente limitato
+    allo spazio utente.
+
+``GFP_ATOMIC``
+    Non dorme. Meno affidabile di ``GFP_KERNEL``, ma può essere usata in un
+    contesto d'interruzione. Dovreste avere **davvero** una buona strategia
+    per la gestione degli errori in caso di mancanza di memoria.
+
+``GFP_DMA``
+    Alloca memoria per il DMA sul bus ISA nello spazio d'indirizzamento
+    inferiore ai 16MB. Se non sapete cos'è allora non vi serve.
+    Molto inaffidabile.
+
+Se vedete un messaggio d'avviso per una funzione dormiente che viene chiamata
+da un contesto errato, allora probabilmente avete usato una funzione
+d'allocazione dormiente da un contesto d'interruzione senza ``GFP_ATOMIC``.
+Dovreste correggerlo. Sbrigatevi, non cincischiate.
+
+Se allocate almeno ``PAGE_SIZE``(``asm/page.h`` o ``asm/page_types.h``) byte,
+considerate l'uso di :c:func:`__get_free_pages()` (``include/linux/gfp.h``).
+Accetta un argomento che definisce l'ordine (0 per per la dimensione di una
+pagine, 1 per una doppia pagina, 2 per quattro pagine, eccetra) e le stesse
+opzioni d'allocazione viste precedentemente.
+
+Se state allocando un numero di byte notevolemnte superiore ad una pagina
+potete usare :c:func:`vmalloc()`. Essa allocherà memoria virtuale all'interno
+dello spazio kernel. Questo è un blocco di memoria fisica non contiguo, ma
+la MMU vi darà l'impressione che lo sia (quindi, sarà contiguo solo dal punto
+di vista dei processori, non dal punto di vista dei driver dei dispositivi
+esterni).
+Se per qualche strana ragione avete davvero bisogno di una grossa quantità di
+memoria fisica contigua, avete un problema: Linux non ha un buon supporto per
+questo caso d'uso perché, dopo un po' di tempo, la frammentazione della memoria
+rende l'operazione difficile. Il modo migliore per allocare un simile blocco
+all'inizio dell'avvio del sistema è attraverso la procedura
+:c:func:`alloc_bootmem()`.
+
+Prima di inventare la vostra cache per gli oggetti più usati, considerate
+l'uso di una cache slab disponibile in ``include/linux/slab.h``.
+
+:c:func:`current()`
+-------------------
+
+Definita in ``include/asm/current.h``
+
+Questa variabile globale (in realtà una macro) contiene un puntatore alla
+struttura del processo corrente, quindi è valido solo dal contesto utente.
+Per esempio, quando un processo esegue una chiamata di sistema, questo
+punterà alla struttura dati del processo chiamate.
+Nel contesto d'interruzione in suo valore **non è NULL**.
+
+:c:func:`mdelay()`/:c:func:`udelay()`
+-------------------------------------
+
+Definite in ``include/asm/delay.h`` / ``include/linux/delay.h``
+
+Le funzioni :c:func:`udelay()` e :c:func:`ndelay()` possono essere utilizzate
+per brevi pause. Non usate grandi valori perché rischiate d'avere un
+overflow - in questo contesto la funzione :c:func:`mdelay()` è utile,
+oppure considerate :c:func:`msleep()`.
+
+:c:func:`cpu_to_be32()`/:c:func:`be32_to_cpu()`/:c:func:`cpu_to_le32()`/:c:func:`le32_to_cpu()`
+-----------------------------------------------------------------------------------------------
+
+Definite in ``include/asm/byteorder.h``
+
+La famiglia di funzioni :c:func:`cpu_to_be32()` (dove "32" può essere
+sostituito da 64 o 16, e "be" con "le") forniscono un modo generico
+per fare conversioni sull'ordine dei byte (endianess): esse ritornano
+il valore convertito. Tutte le varianti supportano anche il processo inverso:
+:c:func:`be32_to_cpu()`, eccetera.
+
+Queste funzioni hanno principalmente due varianti: la variante per
+puntatori, come :c:func:`cpu_to_be32p(), che prende un puntatore
+ad un tipo, e ritorna il valore convertito. L'altra variante per
+la famiglia di conversioni "in-situ", come :c:func:`cpu_to_be32s()`,
+che convertono il valore puntato da un puntatore, e ritornano void.
+
+:c:func:`local_irq_save()`/:c:func:`local_irq_restore()`
+--------------------------------------------------------
+
+Definite in ``include/linux/irqflags.h``
+
+Queste funzioni abilitano e disabilitano le interruzioni hardware
+sul processore locale. Entrambe sono rientranti; esse salvano lo stato
+precedente nel proprio argomento ``unsigned long flags``. Se sapete
+che le interruzioni sono abilite, potete semplicemente utilizzare
+:c:func:`local_irq_disable()` e :c:func:`local_irq_enable()`.
+
+.. _it_local_bh_disable:
+
+:c:func:`local_bh_disable()`/:c:func:`local_bh_enable()`
+--------------------------------------------------------
+
+Definite in ``include/linux/bottom_half.h``
+
+
+Queste funzioni abilitano e disabilitano le interruzioni software
+sul processore locale. Entrambe sono rientranti; se le interruzioni
+software erano già state disabilitate in precedenza, rimarranno
+disabilitate anche dopo aver invocato questa coppia di funzioni.
+Lo scopo è di prevenire l'esecuzione di softirq e tasklet sul processore
+attuale.
+
+:c:func:`smp_processor_id()`
+----------------------------
+
+Definita in ``include/linux/smp.h``
+
+:c:func:`get_cpu()` nega il diritto di prelazione (quindi non potete essere
+spostati su un altro processore all'improvviso) e ritorna il numero
+del processore attuale, fra 0 e ``NR_CPUS``. Da notare che non è detto
+che la numerazione dei processori sia continua. Quando avete terminato,
+ritornate allo stato precedente con :c:func:`put_cpu()`.
+
+Se sapete che non dovete essere interrotti da altri processi (per esempio,
+se siete in un contesto d'interruzione, o il diritto di prelazione
+è disabilitato) potete utilizzare smp_processor_id().
+
+
+``__init``/``__exit``/``__initdata``
+------------------------------------
+
+Definite in  ``include/linux/init.h``
+
+Dopo l'avvio, il kernel libera una sezione speciale; le funzioni marcate
+con ``__init`` e le strutture dati marcate con ``__initdata`` vengono
+eliminate dopo il completamento dell'avvio: in modo simile i moduli eliminano
+questa memoria dopo l'inizializzazione. ``__exit`` viene utilizzato per
+dichiarare che una funzione verrà utilizzata solo in fase di rimozione:
+la detta funzione verrà eliminata quando il file che la contiene non è
+compilato come modulo. Guardate l'header file per informazioni. Da notare che
+non ha senso avere una funzione marcata come ``__init`` e al tempo stesso
+esportata ai moduli utilizzando :c:func:`EXPORT_SYMBOL()` o
+:c:func:`EXPORT_SYMBOL_GPL()` - non funzionerà.
+
+
+:c:func:`__initcall()`/:c:func:`module_init()`
+----------------------------------------------
+
+Definite in  ``include/linux/init.h`` / ``include/linux/module.h``
+
+Molte parti del kernel funzionano bene come moduli (componenti del kernel
+caricabili dinamicamente). L'utilizzo delle macro :c:func:`module_init()`
+e :c:func:`module_exit()` semplifica la scrittura di codice che può funzionare
+sia come modulo, sia come parte del kernel, senza l'ausilio di #ifdef.
+
+La macro :c:func:`module_init()` definisce quale funzione dev'essere
+chiamata quando il modulo viene inserito (se il file è stato compilato come
+tale), o in fase di avvio : se il file non è stato compilato come modulo la
+macro :c:func:`module_init()` diventa equivalente a :c:func:`__initcall()`,
+la quale, tramite qualche magia del linker, s'assicura che la funzione venga
+chiamata durante l'avvio.
+
+La funzione può ritornare un numero d'errore negativo per scatenare un
+fallimento del caricamento (sfortunatamente, questo non ha effetto se il
+modulo è compilato come parte integrante del kernel). Questa funzione è chiamata
+in contesto utente con le interruzioni abilitate, quindi potrebbe dormire.
+
+
+:c:func:`module_exit()`
+-----------------------
+
+
+Definita in  ``include/linux/module.h``
+
+Questa macro definisce la funzione che dev'essere chiamata al momento della
+rimozione (o mai, nel caso in cui il file sia parte integrante del kernel).
+Essa verrà chiamata solo quando il contatore d'uso del modulo raggiunge lo
+zero. Questa funzione può anche dormire, ma non può fallire: tutto dev'essere
+ripulito prima che la funzione ritorni.
+
+Da notare che questa macro è opzionale: se non presente, il modulo non sarà
+removibile (a meno che non usiate 'rmmod -f' ).
+
+
+:c:func:`try_module_get()`/:c:func:`module_put()`
+-------------------------------------------------
+
+Definite in ``include/linux/module.h``
+
+Queste funzioni maneggiano il contatore d'uso del modulo per proteggerlo dalla
+rimozione (in aggiunta, un modulo non può essere rimosso se un altro modulo
+utilizzo uno dei sui simboli esportati: vedere di seguito). Prima di eseguire
+codice del modulo, dovreste chiamare :c:func:`try_module_get()` su quel modulo:
+se fallisce significa che il modulo è stato rimosso e dovete agire come se
+non fosse presente. Altrimenti, potete accedere al modulo in sicurezza, e
+chiamare :c:func:`module_put()` quando avete finito.
+
+La maggior parte delle strutture registrabili hanno un campo owner
+(proprietario), come nella struttura
+:c:type:`struct file_operations <file_operations>`.
+Impostate questo campo al valore della macro ``THIS_MODULE``.
+
+
+Code d'attesa ``include/linux/wait.h``
+======================================
+
+**[DORMONO]**
+
+Una coda d'attesa è usata per aspettare che qualcuno vi attivi quando una
+certa condizione s'avvera. Per evitare corse critiche, devono essere usate
+con cautela. Dichiarate una :c:type:`wait_queue_head_t`, e poi i processi
+che vogliono attendere il verificarsi di quella condizione dichiareranno
+una :c:type:`wait_queue_entry_t` facendo riferimento a loro stessi, poi
+metteranno questa in coda.
+
+Dichiarazione
+-------------
+
+Potere dichiarare una ``wait_queue_head_t`` utilizzando la macro
+:c:func:`DECLARE_WAIT_QUEUE_HEAD()` oppure utilizzando la procedura
+:c:func:`init_waitqueue_head()` nel vostro codice d'inizializzazione.
+
+Accodamento
+-----------
+
+Mettersi in una coda d'attesa è piuttosto complesso, perché dovete
+mettervi in coda prima di verificare la condizione. Esiste una macro
+a questo scopo: :c:func:`wait_event_interruptible()` (``include/linux/wait.h``).
+Il primo argomento è la testa della coda d'attesa, e il secondo è
+un'espressione che dev'essere valutata; la macro ritorna 0 quando questa
+espressione è vera, altrimenti ``-ERESTARTSYS`` se è stato ricevuto un segnale.
+La versione :c:func:`wait_event()` ignora i segnali.
+
+Svegliare una procedura in coda
+-------------------------------
+
+Chiamate :c:func:`wake_up()` (``include/linux/wait.h``); questa attiverà tutti
+i processi in coda. Ad eccezione se uno di questi è impostato come
+``TASK_EXCLUSIVE``, in questo caso i rimanenti non verranno svegliati.
+Nello stesso header file esistono altre varianti di questa funzione.
+
+Operazioni atomiche
+===================
+
+Certe operazioni sono garantite come atomiche su tutte le piattaforme.
+Il primo gruppo di operazioni utilizza :c:type:`atomic_t`
+(``include/asm/atomic.h``); questo contiene un intero con segno (minimo 32bit),
+e dovete utilizzare queste funzione per modificare o leggere variabili di tipo
+:c:type:`atomic_t`. :c:func:`atomic_read()` e :c:func:`atomic_set()` leggono ed
+impostano il contatore, :c:func:`atomic_add()`, :c:func:`atomic_sub()`,
+:c:func:`atomic_inc()`, :c:func:`atomic_dec()`, e
+:c:func:`atomic_dec_and_test()` (ritorna vero se raggiunge zero dopo essere
+stata decrementata).
+
+Sì. Ritorna vero (ovvero != 0) se la variabile atomica è zero.
+
+Da notare che queste funzioni sono più lente rispetto alla normale aritmetica,
+e quindi non dovrebbero essere usate a sproposito.
+
+Il secondo gruppo di operazioni atomiche sono definite in
+``include/linux/bitops.h`` ed agiscono sui bit d'una variabile di tipo
+``unsigned long``. Queste operazioni prendono come argomento un puntatore
+alla variabile, e un numero di bit dove 0 è quello meno significativo.
+:c:func:`set_bit()`, :c:func:`clear_bit()` e :c:func:`change_bit()`
+impostano, cancellano, ed invertono il bit indicato.
+:c:func:`test_and_set_bit()`, :c:func:`test_and_clear_bit()` e
+:c:func:`test_and_change_bit()` fanno la stessa cosa, ad eccezione che
+ritornano vero se il bit era impostato; queste sono particolarmente
+utili quando si vuole impostare atomicamente dei flag.
+
+Con queste operazioni è possibile utilizzare indici di bit che eccedono
+il valore ``BITS_PER_LONG``. Il comportamento è strano sulle piattaforme
+big-endian quindi è meglio evitarlo.
+
+Simboli
+=======
+
+All'interno del kernel, si seguono le normali regole del linker (ovvero,
+a meno che un simbolo non venga dichiarato con visibilita limitata ad un
+file con la parola chiave ``static``, esso può essere utilizzato in qualsiasi
+parte del kernel). Nonostante ciò, per i moduli, esiste una tabella dei
+simboli esportati che limita i punti di accesso al kernel. Anche i moduli
+possono esportare simboli.
+
+:c:func:`EXPORT_SYMBOL()`
+-------------------------
+
+Definita in ``include/linux/export.h``
+
+Questo è il classico metodo per esportare un simbolo: i moduli caricati
+dinamicamente potranno utilizzare normalmente il simbolo.
+
+:c:func:`EXPORT_SYMBOL_GPL()`
+-----------------------------
+
+Definita in ``include/linux/export.h``
+
+Essa è simile a :c:func:`EXPORT_SYMBOL()` ad eccezione del fatto che i
+simboli esportati con :c:func:`EXPORT_SYMBOL_GPL()` possono essere
+utilizzati solo dai moduli che hanno dichiarato una licenza compatibile
+con la GPL attraverso :c:func:`MODULE_LICENSE()`. Questo implica che la
+funzione esportata è considerata interna, e non una vera e propria interfaccia.
+Alcuni manutentori e sviluppatori potrebbero comunque richiedere
+:c:func:`EXPORT_SYMBOL_GPL()` quando si aggiungono nuove funzionalità o
+interfacce.
+
+Procedure e convenzioni
+=======================
+
+Liste doppiamente concatenate ``include/linux/list.h``
+------------------------------------------------------
+
+Un tempo negli header del kernel c'erano tre gruppi di funzioni per
+le liste concatenate, ma questa è stata la vincente. Se non avete particolari
+necessità per una semplice lista concatenata, allora questa è una buona scelta.
+
+In particolare, :c:func:`list_for_each_entry()` è utile.
+
+Convenzione dei valori di ritorno
+---------------------------------
+
+Per codice chiamato in contesto utente, è molto comune sfidare le convenzioni
+C e ritornare 0 in caso di successo, ed un codice di errore negativo
+(eg. ``-EFAULT``) nei casi fallimentari. Questo potrebbe essere controintuitivo
+a prima vista, ma è abbastanza diffuso nel kernel.
+
+Utilizzate :c:func:`ERR_PTR()` (``include/linux/err.h``) per codificare
+un numero d'errore negativo in un puntatore, e :c:func:`IS_ERR()` e
+:c:func:`PTR_ERR()` per recuperarlo di nuovo: così si evita d'avere un
+puntatore dedicato per il numero d'errore. Da brividi, ma in senso positivo.
+
+Rompere la compilazione
+-----------------------
+
+Linus e gli altri sviluppatori a volte cambiano i nomi delle funzioni e
+delle strutture nei kernel in sviluppo; questo non è solo per tenere
+tutti sulle spine: questo riflette cambiamenti fondamentati (eg. la funzione
+non può più essere chiamata con le funzioni attive, o fa controlli aggiuntivi,
+o non fa più controlli che venivano fatti in precedenza). Solitamente a questo
+s'accompagna un'adeguata e completa nota sulla lista di discussone
+linux-kernel; cercate negli archivi.
+Solitamente eseguire una semplice sostituzione su tutto un file rendere
+le cose **peggiori**.
+
+Inizializzazione dei campi d'una struttura
+------------------------------------------
+
+Il metodo preferito per l'inizializzazione delle strutture è quello
+di utilizzare gli inizializzatori designati, come definiti nello
+standard ISO C99, eg::
+
+    static struct block_device_operations opt_fops = {
+            .open               = opt_open,
+            .release            = opt_release,
+            .ioctl              = opt_ioctl,
+            .check_media_change = opt_media_change,
+    };
+
+Questo rende più facile la ricerca con grep, e rende più chiaro quale campo
+viene impostato. Dovreste fare così perché si mostra meglio.
+
+Estensioni GNU
+--------------
+
+Le estensioni GNU sono esplicitamente permesse nel kernel Linux. Da notare
+che alcune delle più complesse non sono ben supportate, per via dello scarso
+sviluppo, ma le seguenti sono da considerarsi la norma (per maggiori dettagli,
+leggete la sezione "C Extensions" nella pagina info di GCC - Sì, davvero
+la pagina info, la pagina man è solo un breve riassunto delle cose nella
+pagina info).
+
+-  Funzioni inline
+
+-  Istruzioni in espressioni (ie. il costrutto ({ and }) ).
+
+-  Dichiarate attributi di una funzione / variabile / tipo
+   (__attribute__)
+
+-  typeof
+
+-  Array con lunghezza zero
+
+-  Macro varargs
+
+-  Aritmentica sui puntatori void
+
+-  Inizializzatori non costanti
+
+-  Istruzioni assembler (non al di fuori di 'arch/' e 'include/asm/')
+
+-  Nomi delle funzioni come stringhe (__func__).
+
+-  __builtin_constant_p()
+
+Siate sospettosi quando utilizzate long long nel kernel, il codice generato
+da gcc è orribile ed anche peggio: le divisioni e le moltiplicazioni non
+funzionano sulle piattaforme i386 perché le rispettive funzioni di runtime
+di GCC non sono incluse nell'ambiente del kernel.
+
+C++
+---
+
+Solitamente utilizzare il C++ nel kernel è una cattiva idea perché
+il kernel non fornisce il necessario ambiente di runtime e gli header file
+non sono stati verificati. Rimane comunque possibile, ma non consigliato.
+Se davvero volete usarlo, almeno evitate le eccezioni.
+
+NUMif
+-----
+
+Viene generalmente considerato più pulito l'uso delle macro negli header file
+(o all'inizio dei file .c) per astrarre funzioni piuttosto che utlizzare
+l'istruzione di pre-processore \`#if' all'interno del codice sorgente.
+
+Mettere le vostre cose nel kernel
+=================================
+
+Al fine d'avere le vostre cose in ordine per l'inclusione ufficiale, o
+anche per avere patch pulite, c'è del lavoro amministrativo da fare:
+
+-  Trovare di chi è lo stagno in cui state pisciando. Guardare in cima
+   ai file sorgenti, all'interno del file ``MAINTAINERS``, ed alla fine
+   di tutti nel file ``CREDITS``. Dovreste coordinarvi con queste persone
+   per evitare di duplicare gli sforzi, o provare qualcosa che è già stato
+   rigettato.
+
+   Assicuratevi di mettere il vostro nome ed indirizzo email in cima a
+   tutti i file che create o che mangeggiate significativamente. Questo è
+   il primo posto dove le persone guarderanno quando troveranno un baco,
+   o quando **loro** vorranno fare una modifica.
+
+-  Solitamente vorrete un'opzione di configurazione per la vostra modifica
+   al kernel. Modificate ``Kconfig`` nella cartella giusta. Il linguaggio
+   Config è facile con copia ed incolla, e c'è una completa documentazione
+   nel file ``Documentation/kbuild/kconfig-language.txt``.
+
+   Nella descrizione della vostra opzione, assicuratevi di parlare sia agli
+   utenti esperti sia agli utente che non sanno nulla del vostro lavoro.
+   Menzionate qui le incompatibilità ed i problemi. Chiaramente la
+   descrizione deve terminare con “if in doubt, say N� (se siete in dubbio,
+   dite N) (oppure, occasionalmente, \`Y'); questo è per le persone che non
+   hanno idea di che cosa voi stiate parlando.
+
+-  Modificate il file ``Makefile``: le variabili CONFIG sono esportate qui,
+   quindi potete solitamente aggiungere una riga come la seguete
+   "obj-$(CONFIG_xxx) += xxx.o". La sintassi è documentata nel file
+   ``Documentation/kbuild/makefiles.txt``.
+
+-  Aggiungete voi stessi in ``CREDITS`` se avete fatto qualcosa di notevole,
+   solitamente qualcosa che supera il singolo file (comunque il vostro nome
+   dovrebbe essere all'inizio dei file sorgenti). ``MAINTAINERS`` significa
+   che volete essere consultati quando vengono fatte delle modifiche ad un
+   sottosistema, e quando ci sono dei bachi; questo implica molto di più
+   di un semplice impegno su una parte del codice.
+
+-  Infine, non dimenticatevi di leggere
+   ``Documentation/process/submitting-patches.rst`` e possibilmente anche
+   ``Documentation/process/submitting-drivers.rst``.
+
+Trucchetti del kernel
+=====================
+
+Dopo una rapida occhiata al codice, questi sono i preferiti. Sentitevi liberi
+di aggiungerne altri.
+
+``arch/x86/include/asm/delay.h``::
+
+    #define ndelay(n) (__builtin_constant_p(n) ? \
+            ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
+            __ndelay(n))
+
+
+``include/linux/fs.h``::
+
+    /*
+     * Kernel pointers have redundant information, so we can use a
+     * scheme where we can return either an error code or a dentry
+     * pointer with the same return value.
+     *
+     * This should be a per-architecture thing, to allow different
+     * error and pointer decisions.
+     */
+     #define ERR_PTR(err)    ((void *)((long)(err)))
+     #define PTR_ERR(ptr)    ((long)(ptr))
+     #define IS_ERR(ptr)     ((unsigned long)(ptr) > (unsigned long)(-1000))
+
+``arch/x86/include/asm/uaccess_32.h:``::
+
+    #define copy_to_user(to,from,n)                         \
+            (__builtin_constant_p(n) ?                      \
+             __constant_copy_to_user((to),(from),(n)) :     \
+             __generic_copy_to_user((to),(from),(n)))
+
+
+``arch/sparc/kernel/head.S:``::
+
+    /*
+     * Sun people can't spell worth damn. "compatability" indeed.
+     * At least we *know* we can't spell, and use a spell-checker.
+     */
+
+    /* Uh, actually Linus it is I who cannot spell. Too much murky
+     * Sparc assembly will do this to ya.
+     */
+    C_LABEL(cputypvar):
+            .asciz "compatibility"
+
+    /* Tested on SS-5, SS-10. Probably someone at Sun applied a spell-checker. */
+            .align 4
+    C_LABEL(cputypvar_sun4m):
+            .asciz "compatible"
+
+
+``arch/sparc/lib/checksum.S:``::
+
+            /* Sun, you just can't beat me, you just can't.  Stop trying,
+             * give up.  I'm serious, I am going to kick the living shit
+             * out of you, game over, lights out.
+             */
+
+
+Ringraziamenti
+==============
+
+Ringrazio Andi Kleen per le sue idee, le risposte alle mie domande,
+le correzioni dei miei errori, l'aggiunta di contenuti, eccetera.
+Philipp Rumpf per l'ortografia e per aver reso più chiaro il testo, e
+per alcuni eccellenti punti tutt'altro che ovvi. Werner Almesberger
+per avermi fornito un ottimo riassunto di :c:func:`disable_irq()`,
+e Jes Sorensen e Andrea Arcangeli per le precisazioni. Michael Elizabeth
+Chastain per aver verificato ed aggiunto la sezione configurazione.
+Telsa Gwynne per avermi insegnato DocBook.
diff --git a/Documentation/translations/it_IT/kernel-hacking/index.rst b/Documentation/translations/it_IT/kernel-hacking/index.rst
new file mode 100644
index 000000000000..50228380bd50
--- /dev/null
+++ b/Documentation/translations/it_IT/kernel-hacking/index.rst
@@ -0,0 +1,16 @@
+.. include:: ../disclaimer-ita.rst
+
+:Original: :ref:`Documentation/kernel-hacking/index.rst <kernel_hacking>`
+:Translator: Federico Vaga <federico.vaga@vaga.pv.it>
+
+.. _it_kernel_hacking:
+
+============================
+Guida all'hacking del kernel
+============================
+
+.. toctree::
+   :maxdepth: 2
+
+   hacking
+   locking
diff --git a/Documentation/translations/it_IT/kernel-hacking/locking.rst b/Documentation/translations/it_IT/kernel-hacking/locking.rst
new file mode 100644
index 000000000000..753643622c23
--- /dev/null
+++ b/Documentation/translations/it_IT/kernel-hacking/locking.rst
@@ -0,0 +1,1493 @@
+.. include:: ../disclaimer-ita.rst
+
+:Original: :ref:`Documentation/kernel-hacking/locking.rst <kernel_hacking_lock>`
+:Translator: Federico Vaga <federico.vaga@vaga.pv.it>
+
+.. _it_kernel_hacking_lock:
+
+==========================================
+L'inaffidabile guida alla sincronizzazione
+==========================================
+
+:Author: Rusty Russell
+
+Introduzione
+============
+
+Benvenuto, alla notevole ed inaffidabile guida ai problemi di sincronizzazione
+(locking) nel kernel. Questo documento descrive il sistema di sincronizzazione
+nel kernel Linux 2.6.
+
+Dato il largo utilizzo del multi-threading e della prelazione nel kernel
+Linux, chiunque voglia dilettarsi col kernel deve conoscere i concetti
+fondamentali della concorrenza e della sincronizzazione nei sistemi
+multi-processore.
+
+Il problema con la concorrenza
+==============================
+
+(Saltatelo se sapete già cos'è una corsa critica).
+
+In un normale programma, potete incrementare un contatore nel seguente modo:
+
+::
+
+          contatore++;
+
+Questo è quello che vi aspettereste che accada sempre:
+
+
+.. table:: Risultati attesi
+
+  +------------------------------------+------------------------------------+
+  | Istanza 1                          | Istanza 2                          |
+  +====================================+====================================+
+  | leggi contatore (5)                |                                    |
+  +------------------------------------+------------------------------------+
+  | aggiungi 1 (6)                     |                                    |
+  +------------------------------------+------------------------------------+
+  | scrivi contatore (6)               |                                    |
+  +------------------------------------+------------------------------------+
+  |                                    | leggi contatore (6)                |
+  +------------------------------------+------------------------------------+
+  |                                    | aggiungi 1 (7)                     |
+  +------------------------------------+------------------------------------+
+  |                                    | scrivi contatore (7)               |
+  +------------------------------------+------------------------------------+
+
+Questo è quello che potrebbe succedere in realtà:
+
+.. table:: Possibile risultato
+
+  +------------------------------------+------------------------------------+
+  | Istanza 1                          | Istanza 2                          |
+  +====================================+====================================+
+  | leggi contatore (5)                |                                    |
+  +------------------------------------+------------------------------------+
+  |                                    | leggi contatore (5)                |
+  +------------------------------------+------------------------------------+
+  | aggiungi 1 (6)                     |                                    |
+  +------------------------------------+------------------------------------+
+  |                                    | aggiungi 1 (6)                     |
+  +------------------------------------+------------------------------------+
+  | scrivi contatore (6)               |                                    |
+  +------------------------------------+------------------------------------+
+  |                                    | scrivi contatore (6)               |
+  +------------------------------------+------------------------------------+
+
+
+Corse critiche e sezioni critiche
+---------------------------------
+
+Questa sovrapposizione, ovvero quando un risultato dipende dal tempo che
+intercorre fra processi diversi, è chiamata corsa critica. La porzione
+di codice che contiene questo problema è chiamata sezione critica.
+In particolar modo da quando Linux ha incominciato a girare su
+macchine multi-processore, le sezioni critiche sono diventate uno dei
+maggiori problemi di progettazione ed implementazione del kernel.
+
+La prelazione può sortire gli stessi effetti, anche se c'è una sola CPU:
+interrompendo un processo nella sua sezione critica otterremo comunque
+la stessa corsa critica. In questo caso, il thread che si avvicenda
+nell'esecuzione potrebbe eseguire anch'esso la sezione critica.
+
+La soluzione è quella di riconoscere quando avvengono questi accessi
+simultanei, ed utilizzare i *lock* per accertarsi che solo un'istanza
+per volta possa entrare nella sezione critica. Il kernel offre delle buone
+funzioni a questo scopo. E poi ci sono quelle meno buone, ma farò finta
+che non esistano.
+
+Sincronizzazione nel kernel Linux
+=================================
+
+Se posso darvi un suggerimento: non dormite mai con qualcuno più pazzo di
+voi. Ma se dovessi darvi un suggerimento sulla sincronizzazione:
+**mantenetela semplice**.
+
+Siate riluttanti nell'introduzione di nuovi *lock*.
+
+Abbastanza strano, quest'ultimo è l'esatto opposto del mio suggerimento
+su quando **avete** dormito con qualcuno più pazzo di voi. E dovreste
+pensare a prendervi un cane bello grande.
+
+I due principali tipi di *lock* nel kernel: spinlock e mutex
+------------------------------------------------------------
+
+Ci sono due tipi principali di *lock* nel kernel. Il tipo fondamentale è lo
+spinlock (``include/asm/spinlock.h``), un semplice *lock* che può essere
+trattenuto solo da un processo: se non si può trattenere lo spinlock, allora
+rimane in attesa attiva (in inglese *spinning*) finché non ci riesce.
+Gli spinlock sono molto piccoli e rapidi, possono essere utilizzati ovunque.
+
+Il secondo tipo è il mutex (``include/linux/mutex.h``): è come uno spinlock,
+ma potreste bloccarvi trattenendolo. Se non potete trattenere un mutex
+il vostro processo si auto-sospenderà; verrà riattivato quando il mutex
+verrà rilasciato. Questo significa che il processore potrà occuparsi d'altro
+mentre il vostro processo è in attesa. Esistono molti casi in cui non potete
+permettervi di sospendere un processo (vedere
+:ref:`Quali funzioni possono essere chiamate in modo sicuro dalle interruzioni? <it_sleeping-things>`)
+e quindi dovrete utilizzare gli spinlock.
+
+Nessuno di questi *lock* è ricorsivo: vedere
+:ref:`Stallo: semplice ed avanzato <it_deadlock>`
+
+I *lock* e i kernel per sistemi monoprocessore
+----------------------------------------------
+
+Per i kernel compilati senza ``CONFIG_SMP`` e senza ``CONFIG_PREEMPT``
+gli spinlock non esistono. Questa è un'ottima scelta di progettazione:
+quando nessun altro processo può essere eseguito in simultanea, allora
+non c'è la necessità di avere un *lock*.
+
+Se il kernel è compilato senza ``CONFIG_SMP`` ma con ``CONFIG_PREEMPT``,
+allora gli spinlock disabilitano la prelazione; questo è sufficiente a
+prevenire le corse critiche. Nella maggior parte dei casi, possiamo considerare
+la prelazione equivalente ad un sistema multi-processore senza preoccuparci
+di trattarla indipendentemente.
+
+Dovreste verificare sempre la sincronizzazione con le opzioni ``CONFIG_SMP`` e
+``CONFIG_PREEMPT`` abilitate, anche quando non avete un sistema
+multi-processore, questo vi permetterà di identificare alcuni problemi
+di sincronizzazione.
+
+Come vedremo di seguito, i mutex continuano ad esistere perché sono necessari
+per la sincronizzazione fra processi in contesto utente.
+
+Sincronizzazione in contesto utente
+-----------------------------------
+
+Se avete una struttura dati che verrà utilizzata solo dal contesto utente,
+allora, per proteggerla, potete utilizzare un semplice mutex
+(``include/linux/mutex.h``). Questo è il caso più semplice: inizializzate il
+mutex; invocate :c:func:`mutex_lock_interruptible()` per trattenerlo e
+:c:func:`mutex_unlock()` per rilasciarlo. C'è anche :c:func:`mutex_lock()`
+ma questa dovrebbe essere evitata perché non ritorna in caso di segnali.
+
+Per esempio: ``net/netfilter/nf_sockopt.c`` permette la registrazione
+di nuove chiamate per :c:func:`setsockopt()` e :c:func:`getsockopt()`
+usando la funzione :c:func:`nf_register_sockopt()`. La registrazione e
+la rimozione vengono eseguite solamente quando il modulo viene caricato
+o scaricato (e durante l'avvio del sistema, qui non abbiamo concorrenza),
+e la lista delle funzioni registrate viene consultata solamente quando
+:c:func:`setsockopt()` o :c:func:`getsockopt()` sono sconosciute al sistema.
+In questo caso ``nf_sockopt_mutex`` è perfetto allo scopo, in particolar modo
+visto che setsockopt e getsockopt potrebbero dormire.
+
+Sincronizzazione fra il contesto utente e i softirq
+---------------------------------------------------
+
+Se un softirq condivide dati col contesto utente, avete due problemi.
+Primo, il contesto utente corrente potrebbe essere interroto da un softirq,
+e secondo, la sezione critica potrebbe essere eseguita da un altro
+processore. Questo è quando :c:func:`spin_lock_bh()`
+(``include/linux/spinlock.h``) viene utilizzato. Questo disabilita i softirq
+sul processore e trattiene il *lock*. Invece, :c:func:`spin_unlock_bh()` fa
+l'opposto. (Il suffisso '_bh' è un residuo storico che fa riferimento al
+"Bottom Halves", il vecchio nome delle interruzioni software. In un mondo
+perfetto questa funzione si chiamerebbe 'spin_lock_softirq()').
+
+Da notare che in questo caso potete utilizzare anche :c:func:`spin_lock_irq()`
+o :c:func:`spin_lock_irqsave()`, queste fermano anche le interruzioni hardware:
+vedere :ref:`Contesto di interruzione hardware <it_hardirq-context>`.
+
+Questo funziona alla perfezione anche sui sistemi monoprocessore: gli spinlock
+svaniscono e questa macro diventa semplicemente :c:func:`local_bh_disable()`
+(``include/linux/interrupt.h``), la quale impedisce ai softirq d'essere
+eseguiti.
+
+Sincronizzazione fra contesto utente e i tasklet
+------------------------------------------------
+
+Questo caso è uguale al precedente, un tasklet viene eseguito da un softirq.
+
+Sincronizzazione fra contesto utente e i timer
+----------------------------------------------
+
+Anche questo caso è uguale al precedente, un timer viene eseguito da un
+softirq.
+Dal punto di vista della sincronizzazione, tasklet e timer sono identici.
+
+Sincronizzazione fra tasklet e timer
+------------------------------------
+
+Qualche volta un tasklet od un timer potrebbero condividere i dati con
+un altro tasklet o timer
+
+Lo stesso tasklet/timer
+~~~~~~~~~~~~~~~~~~~~~~~
+
+Dato che un tasklet non viene mai eseguito contemporaneamente su due
+processori, non dovete preoccuparvi che sia rientrante (ovvero eseguito
+più volte in contemporanea), perfino su sistemi multi-processore.
+
+Differenti tasklet/timer
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Se un altro tasklet/timer vuole condividere dati col vostro tasklet o timer,
+allora avrete bisogno entrambe di :c:func:`spin_lock()` e
+:c:func:`spin_unlock()`. Qui :c:func:`spin_lock_bh()` è inutile, siete già
+in un tasklet ed avete la garanzia che nessun altro verrà eseguito sullo
+stesso processore.
+
+Sincronizzazione fra softirq
+----------------------------
+
+Spesso un softirq potrebbe condividere dati con se stesso o un tasklet/timer.
+
+Lo stesso softirq
+~~~~~~~~~~~~~~~~~
+
+Lo stesso softirq può essere eseguito su un diverso processore: allo scopo
+di migliorare le prestazioni potete utilizzare dati riservati ad ogni
+processore (vedere :ref:`Dati per processore <it_per-cpu>`). Se siete arrivati
+fino a questo punto nell'uso dei softirq, probabilmente tenete alla scalabilità
+delle prestazioni abbastanza da giustificarne la complessità aggiuntiva.
+
+Dovete utilizzare :c:func:`spin_lock()` e :c:func:`spin_unlock()` per
+proteggere i dati condivisi.
+
+Diversi Softirqs
+~~~~~~~~~~~~~~~~
+
+Dovete utilizzare :c:func:`spin_lock()` e :c:func:`spin_unlock()` per
+proteggere i dati condivisi, che siano timer, tasklet, diversi softirq o
+lo stesso o altri softirq: uno qualsiasi di essi potrebbe essere in esecuzione
+su un diverso processore.
+
+.. _`it_hardirq-context`:
+
+Contesto di interruzione hardware
+=================================
+
+Solitamente le interruzioni hardware comunicano con un tasklet o un softirq.
+Spesso questo si traduce nel mettere in coda qualcosa da fare che verrà
+preso in carico da un softirq.
+
+Sincronizzazione fra interruzioni hardware e softirq/tasklet
+------------------------------------------------------------
+
+Se un gestore di interruzioni hardware condivide dati con un softirq, allora
+avrete due preoccupazioni. Primo, il softirq può essere interrotto da
+un'interruzione hardware, e secondo, la sezione critica potrebbe essere
+eseguita da un'interruzione hardware su un processore diverso. Questo è il caso
+dove :c:func:`spin_lock_irq()` viene utilizzato. Disabilita le interruzioni
+sul processore che l'esegue, poi trattiene il lock. :c:func:`spin_unlock_irq()`
+fa l'opposto.
+
+Il gestore d'interruzione hardware non usa :c:func:`spin_lock_irq()` perché
+i softirq non possono essere eseguiti quando il gestore d'interruzione hardware
+è in esecuzione: per questo si può usare :c:func:`spin_lock()`, che è un po'
+più veloce. L'unica eccezione è quando un altro gestore d'interruzioni
+hardware utilizza lo stesso *lock*: :c:func:`spin_lock_irq()` impedirà a questo
+secondo gestore di interrompere quello in esecuzione.
+
+Questo funziona alla perfezione anche sui sistemi monoprocessore: gli spinlock
+svaniscono e questa macro diventa semplicemente :c:func:`local_irq_disable()`
+(``include/asm/smp.h``), la quale impedisce a softirq/tasklet/BH d'essere
+eseguiti.
+
+:c:func:`spin_lock_irqsave()` (``include/linux/spinlock.h``) è una variante che
+salva lo stato delle interruzioni in una variabile, questa verrà poi passata
+a :c:func:`spin_unlock_irqrestore()`. Questo significa che lo stesso codice
+potrà essere utilizzato in un'interruzione hardware (dove le interruzioni sono
+già disabilitate) e in un softirq (dove la disabilitazione delle interruzioni
+è richiesta).
+
+Da notare che i softirq (e quindi tasklet e timer) sono eseguiti al ritorno
+da un'interruzione hardware, quindi :c:func:`spin_lock_irq()` interrompe
+anche questi. Tenuto conto di questo si può dire che
+:c:func:`spin_lock_irqsave()` è la funzione di sincronizzazione più generica
+e potente.
+
+Sincronizzazione fra due gestori d'interruzioni hardware
+--------------------------------------------------------
+
+Condividere dati fra due gestori di interruzione hardware è molto raro, ma se
+succede, dovreste usare :c:func:`spin_lock_irqsave()`: è una specificità
+dell'architettura il fatto che tutte le interruzioni vengano interrotte
+quando si eseguono di gestori di interruzioni.
+
+Bigino della sincronizzazione
+=============================
+
+Pete Zaitcev ci offre il seguente riassunto:
+
+-  Se siete in un contesto utente (una qualsiasi chiamata di sistema)
+   e volete sincronizzarvi con altri processi, usate i mutex. Potete trattenere
+   il mutex e dormire (``copy_from_user*(`` o ``kmalloc(x,GFP_KERNEL)``).
+
+-  Altrimenti (== i dati possono essere manipolati da un'interruzione) usate
+   :c:func:`spin_lock_irqsave()` e :c:func:`spin_unlock_irqrestore()`.
+
+-  Evitate di trattenere uno spinlock per più di 5 righe di codice incluse
+   le chiamate a funzione (ad eccezione di quell per l'accesso come
+   :c:func:`readb()`).
+
+Tabella dei requisiti minimi
+----------------------------
+
+La tabella seguente illustra i requisiti **minimi** per la sincronizzazione fra
+diversi contesti. In alcuni casi, lo stesso contesto può essere eseguito solo
+da un processore per volta, quindi non ci sono requisiti per la
+sincronizzazione (per esempio, un thread può essere eseguito solo su un
+processore alla volta, ma se deve condividere dati con un altro thread, allora
+la sincronizzazione è necessaria).
+
+Ricordatevi il suggerimento qui sopra: potete sempre usare
+:c:func:`spin_lock_irqsave()`, che è un sovrainsieme di tutte le altre funzioni
+per spinlock.
+
+============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ==============
+.              IRQ Handler A IRQ Handler B Softirq A Softirq B Tasklet A Tasklet B Timer A Timer B User Context A User Context B
+============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ==============
+IRQ Handler A  None
+IRQ Handler B  SLIS          None
+Softirq A      SLI           SLI           SL
+Softirq B      SLI           SLI           SL        SL
+Tasklet A      SLI           SLI           SL        SL        None
+Tasklet B      SLI           SLI           SL        SL        SL        None
+Timer A        SLI           SLI           SL        SL        SL        SL        None
+Timer B        SLI           SLI           SL        SL        SL        SL        SL      None
+User Context A SLI           SLI           SLBH      SLBH      SLBH      SLBH      SLBH    SLBH    None
+User Context B SLI           SLI           SLBH      SLBH      SLBH      SLBH      SLBH    SLBH    MLI            None
+============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ==============
+
+Table: Tabella dei requisiti per la sincronizzazione
+
++--------+----------------------------+
+| SLIS   | spin_lock_irqsave          |
++--------+----------------------------+
+| SLI    | spin_lock_irq              |
++--------+----------------------------+
+| SL     | spin_lock                  |
++--------+----------------------------+
+| SLBH   | spin_lock_bh               |
++--------+----------------------------+
+| MLI    | mutex_lock_interruptible   |
++--------+----------------------------+
+
+Table: Legenda per la tabella dei requisiti per la sincronizzazione
+
+Le funzioni *trylock*
+=====================
+
+Ci sono funzioni che provano a trattenere un *lock* solo una volta e
+ritornano immediatamente comunicato il successo od il fallimento
+dell'operazione. Posso essere usate quando non serve accedere ai dati
+protetti dal *lock* quando qualche altro thread lo sta già facendo
+trattenendo il *lock*. Potrete acquisire il *lock* più tardi se vi
+serve accedere ai dati protetti da questo *lock*.
+
+La funzione :c:func:`spin_trylock()` non ritenta di acquisire il *lock*,
+se ci riesce al primo colpo ritorna un valore diverso da zero, altrimenti
+se fallisce ritorna 0. Questa funzione può essere utilizzata in un qualunque
+contesto, ma come :c:func:`spin_lock()`: dovete disabilitare i contesti che
+potrebbero interrompervi e quindi trattenere lo spinlock.
+
+La funzione :c:func:`mutex_trylock()` invece di sospendere il vostro processo
+ritorna un valore diverso da zero se è possibile trattenere il lock al primo
+colpo, altrimenti se fallisce ritorna 0. Nonostante non dorma, questa funzione
+non può essere usata in modo sicuro in contesti di interruzione hardware o
+software.
+
+Esempi più comuni
+=================
+
+Guardiamo un semplice esempio: una memoria che associa nomi a numeri.
+La memoria tiene traccia di quanto spesso viene utilizzato ogni oggetto;
+quando è piena, l'oggetto meno usato viene eliminato.
+
+Tutto in contesto utente
+------------------------
+
+Nel primo esempio, supponiamo che tutte le operazioni avvengano in contesto
+utente (in soldoni, da una chiamata di sistema), quindi possiamo dormire.
+Questo significa che possiamo usare i mutex per proteggere la nostra memoria
+e tutti gli oggetti che contiene. Ecco il codice::
+
+    #include <linux/list.h>
+    #include <linux/slab.h>
+    #include <linux/string.h>
+    #include <linux/mutex.h>
+    #include <asm/errno.h>
+
+    struct object
+    {
+            struct list_head list;
+            int id;
+            char name[32];
+            int popularity;
+    };
+
+    /* Protects the cache, cache_num, and the objects within it */
+    static DEFINE_MUTEX(cache_lock);
+    static LIST_HEAD(cache);
+    static unsigned int cache_num = 0;
+    #define MAX_CACHE_SIZE 10
+
+    /* Must be holding cache_lock */
+    static struct object *__cache_find(int id)
+    {
+            struct object *i;
+
+            list_for_each_entry(i, &cache, list)
+                    if (i->id == id) {
+                            i->popularity++;
+                            return i;
+                    }
+            return NULL;
+    }
+
+    /* Must be holding cache_lock */
+    static void __cache_delete(struct object *obj)
+    {
+            BUG_ON(!obj);
+            list_del(&obj->list);
+            kfree(obj);
+            cache_num--;
+    }
+
+    /* Must be holding cache_lock */
+    static void __cache_add(struct object *obj)
+    {
+            list_add(&obj->list, &cache);
+            if (++cache_num > MAX_CACHE_SIZE) {
+                    struct object *i, *outcast = NULL;
+                    list_for_each_entry(i, &cache, list) {
+                            if (!outcast || i->popularity < outcast->popularity)
+                                    outcast = i;
+                    }
+                    __cache_delete(outcast);
+            }
+    }
+
+    int cache_add(int id, const char *name)
+    {
+            struct object *obj;
+
+            if ((obj = kmalloc(sizeof(*obj), GFP_KERNEL)) == NULL)
+                    return -ENOMEM;
+
+            strlcpy(obj->name, name, sizeof(obj->name));
+            obj->id = id;
+            obj->popularity = 0;
+
+            mutex_lock(&cache_lock);
+            __cache_add(obj);
+            mutex_unlock(&cache_lock);
+            return 0;
+    }
+
+    void cache_delete(int id)
+    {
+            mutex_lock(&cache_lock);
+            __cache_delete(__cache_find(id));
+            mutex_unlock(&cache_lock);
+    }
+
+    int cache_find(int id, char *name)
+    {
+            struct object *obj;
+            int ret = -ENOENT;
+
+            mutex_lock(&cache_lock);
+            obj = __cache_find(id);
+            if (obj) {
+                    ret = 0;
+                    strcpy(name, obj->name);
+            }
+            mutex_unlock(&cache_lock);
+            return ret;
+    }
+
+Da notare che ci assicuriamo sempre di trattenere cache_lock quando
+aggiungiamo, rimuoviamo od ispezioniamo la memoria: sia la struttura
+della memoria che il suo contenuto sono protetti dal *lock*. Questo
+caso è semplice dato che copiamo i dati dall'utente e non permettiamo
+mai loro di accedere direttamente agli oggetti.
+
+C'è una piccola ottimizzazione qui: nella funzione :c:func:`cache_add()`
+impostiamo i campi dell'oggetto prima di acquisire il *lock*. Questo è
+sicuro perché nessun altro potrà accedervi finché non lo inseriremo
+nella memoria.
+
+Accesso dal contesto utente
+---------------------------
+
+Ora consideriamo il caso in cui :c:func:`cache_find()` può essere invocata
+dal contesto d'interruzione: sia hardware che software. Un esempio potrebbe
+essere un timer che elimina oggetti dalla memoria.
+
+Qui di seguito troverete la modifica nel formato *patch*: le righe ``-``
+sono quelle rimosse, mentre quelle ``+`` sono quelle aggiunte.
+
+::
+
+    --- cache.c.usercontext 2003-12-09 13:58:54.000000000 +1100
+    +++ cache.c.interrupt   2003-12-09 14:07:49.000000000 +1100
+    @@ -12,7 +12,7 @@
+             int popularity;
+     };
+
+    -static DEFINE_MUTEX(cache_lock);
+    +static DEFINE_SPINLOCK(cache_lock);
+     static LIST_HEAD(cache);
+     static unsigned int cache_num = 0;
+     #define MAX_CACHE_SIZE 10
+    @@ -55,6 +55,7 @@
+     int cache_add(int id, const char *name)
+     {
+             struct object *obj;
+    +        unsigned long flags;
+
+             if ((obj = kmalloc(sizeof(*obj), GFP_KERNEL)) == NULL)
+                     return -ENOMEM;
+    @@ -63,30 +64,33 @@
+             obj->id = id;
+             obj->popularity = 0;
+
+    -        mutex_lock(&cache_lock);
+    +        spin_lock_irqsave(&cache_lock, flags);
+             __cache_add(obj);
+    -        mutex_unlock(&cache_lock);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+             return 0;
+     }
+
+     void cache_delete(int id)
+     {
+    -        mutex_lock(&cache_lock);
+    +        unsigned long flags;
+    +
+    +        spin_lock_irqsave(&cache_lock, flags);
+             __cache_delete(__cache_find(id));
+    -        mutex_unlock(&cache_lock);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+     }
+
+     int cache_find(int id, char *name)
+     {
+             struct object *obj;
+             int ret = -ENOENT;
+    +        unsigned long flags;
+
+    -        mutex_lock(&cache_lock);
+    +        spin_lock_irqsave(&cache_lock, flags);
+             obj = __cache_find(id);
+             if (obj) {
+                     ret = 0;
+                     strcpy(name, obj->name);
+             }
+    -        mutex_unlock(&cache_lock);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+             return ret;
+     }
+
+Da notare che :c:func:`spin_lock_irqsave()` disabiliterà le interruzioni
+se erano attive, altrimenti non farà niente (quando siamo già in un contesto
+d'interruzione); dunque queste funzioni possono essere chiamante in
+sicurezza da qualsiasi contesto.
+
+Sfortunatamente, :c:func:`cache_add()` invoca :c:func:`kmalloc()` con
+l'opzione ``GFP_KERNEL`` che è permessa solo in contesto utente. Ho supposto
+che :c:func:`cache_add()` venga chiamata dal contesto utente, altrimenti
+questa opzione deve diventare un parametro di :c:func:`cache_add()`.
+
+Exposing Objects Outside This File
+----------------------------------
+
+Se i vostri oggetti contengono più informazioni, potrebbe non essere
+sufficiente copiare i dati avanti e indietro: per esempio, altre parti del
+codice potrebbero avere un puntatore a questi oggetti piuttosto che cercarli
+ogni volta. Questo introduce due problemi.
+
+Il primo problema è che utilizziamo ``cache_lock`` per proteggere gli oggetti:
+dobbiamo renderlo dinamico così che il resto del codice possa usarlo. Questo
+rende la sincronizzazione più complicata dato che non avviene più in un unico
+posto.
+
+Il secondo problema è il problema del ciclo di vita: se un'altra struttura
+mantiene un puntatore ad un oggetto, presumibilmente si aspetta che questo
+puntatore rimanga valido. Sfortunatamente, questo è garantito solo mentre
+si trattiene il *lock*, altrimenti qualcuno potrebbe chiamare
+:c:func:`cache_delete()` o peggio, aggiungere un oggetto che riutilizza lo
+stesso indirizzo.
+
+Dato che c'è un solo *lock*, non potete trattenerlo a vita: altrimenti
+nessun altro potrà eseguire il proprio lavoro.
+
+La soluzione a questo problema è l'uso di un contatore di riferimenti:
+chiunque punti ad un oggetto deve incrementare il contatore, e decrementarlo
+quando il puntatore non viene più usato. Quando il contatore raggiunge lo zero
+significa che non è più usato e l'oggetto può essere rimosso.
+
+Ecco il codice::
+
+    --- cache.c.interrupt   2003-12-09 14:25:43.000000000 +1100
+    +++ cache.c.refcnt  2003-12-09 14:33:05.000000000 +1100
+    @@ -7,6 +7,7 @@
+     struct object
+     {
+             struct list_head list;
+    +        unsigned int refcnt;
+             int id;
+             char name[32];
+             int popularity;
+    @@ -17,6 +18,35 @@
+     static unsigned int cache_num = 0;
+     #define MAX_CACHE_SIZE 10
+
+    +static void __object_put(struct object *obj)
+    +{
+    +        if (--obj->refcnt == 0)
+    +                kfree(obj);
+    +}
+    +
+    +static void __object_get(struct object *obj)
+    +{
+    +        obj->refcnt++;
+    +}
+    +
+    +void object_put(struct object *obj)
+    +{
+    +        unsigned long flags;
+    +
+    +        spin_lock_irqsave(&cache_lock, flags);
+    +        __object_put(obj);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+    +}
+    +
+    +void object_get(struct object *obj)
+    +{
+    +        unsigned long flags;
+    +
+    +        spin_lock_irqsave(&cache_lock, flags);
+    +        __object_get(obj);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+    +}
+    +
+     /* Must be holding cache_lock */
+     static struct object *__cache_find(int id)
+     {
+    @@ -35,6 +65,7 @@
+     {
+             BUG_ON(!obj);
+             list_del(&obj->list);
+    +        __object_put(obj);
+             cache_num--;
+     }
+
+    @@ -63,6 +94,7 @@
+             strlcpy(obj->name, name, sizeof(obj->name));
+             obj->id = id;
+             obj->popularity = 0;
+    +        obj->refcnt = 1; /* The cache holds a reference */
+
+             spin_lock_irqsave(&cache_lock, flags);
+             __cache_add(obj);
+    @@ -79,18 +111,15 @@
+             spin_unlock_irqrestore(&cache_lock, flags);
+     }
+
+    -int cache_find(int id, char *name)
+    +struct object *cache_find(int id)
+     {
+             struct object *obj;
+    -        int ret = -ENOENT;
+             unsigned long flags;
+
+             spin_lock_irqsave(&cache_lock, flags);
+             obj = __cache_find(id);
+    -        if (obj) {
+    -                ret = 0;
+    -                strcpy(name, obj->name);
+    -        }
+    +        if (obj)
+    +                __object_get(obj);
+             spin_unlock_irqrestore(&cache_lock, flags);
+    -        return ret;
+    +        return obj;
+     }
+
+Abbiamo incapsulato il contatore di riferimenti nelle tipiche funzioni
+di 'get' e 'put'. Ora possiamo ritornare l'oggetto da :c:func:`cache_find()`
+col vantaggio che l'utente può dormire trattenendo l'oggetto (per esempio,
+:c:func:`copy_to_user()` per copiare il nome verso lo spazio utente).
+
+Un altro punto da notare è che ho detto che il contatore dovrebbe incrementarsi
+per ogni puntatore ad un oggetto: quindi il contatore di riferimenti è 1
+quando l'oggetto viene inserito nella memoria. In altre versione il framework
+non trattiene un riferimento per se, ma diventa più complicato.
+
+Usare operazioni atomiche per il contatore di riferimenti
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In sostanza, :c:type:`atomic_t` viene usato come contatore di riferimenti.
+Ci sono un certo numbero di operazioni atomiche definite
+in ``include/asm/atomic.h``: queste sono garantite come atomiche su qualsiasi
+processore del sistema, quindi non sono necessari i *lock*. In questo caso è
+più semplice rispetto all'uso degli spinlock, benché l'uso degli spinlock
+sia più elegante per casi non banali. Le funzioni :c:func:`atomic_inc()` e
+:c:func:`atomic_dec_and_test()` vengono usate al posto dei tipici operatori di
+incremento e decremento, e i *lock* non sono più necessari per proteggere il
+contatore stesso.
+
+::
+
+    --- cache.c.refcnt  2003-12-09 15:00:35.000000000 +1100
+    +++ cache.c.refcnt-atomic   2003-12-11 15:49:42.000000000 +1100
+    @@ -7,7 +7,7 @@
+     struct object
+     {
+             struct list_head list;
+    -        unsigned int refcnt;
+    +        atomic_t refcnt;
+             int id;
+             char name[32];
+             int popularity;
+    @@ -18,33 +18,15 @@
+     static unsigned int cache_num = 0;
+     #define MAX_CACHE_SIZE 10
+
+    -static void __object_put(struct object *obj)
+    -{
+    -        if (--obj->refcnt == 0)
+    -                kfree(obj);
+    -}
+    -
+    -static void __object_get(struct object *obj)
+    -{
+    -        obj->refcnt++;
+    -}
+    -
+     void object_put(struct object *obj)
+     {
+    -        unsigned long flags;
+    -
+    -        spin_lock_irqsave(&cache_lock, flags);
+    -        __object_put(obj);
+    -        spin_unlock_irqrestore(&cache_lock, flags);
+    +        if (atomic_dec_and_test(&obj->refcnt))
+    +                kfree(obj);
+     }
+
+     void object_get(struct object *obj)
+     {
+    -        unsigned long flags;
+    -
+    -        spin_lock_irqsave(&cache_lock, flags);
+    -        __object_get(obj);
+    -        spin_unlock_irqrestore(&cache_lock, flags);
+    +        atomic_inc(&obj->refcnt);
+     }
+
+     /* Must be holding cache_lock */
+    @@ -65,7 +47,7 @@
+     {
+             BUG_ON(!obj);
+             list_del(&obj->list);
+    -        __object_put(obj);
+    +        object_put(obj);
+             cache_num--;
+     }
+
+    @@ -94,7 +76,7 @@
+             strlcpy(obj->name, name, sizeof(obj->name));
+             obj->id = id;
+             obj->popularity = 0;
+    -        obj->refcnt = 1; /* The cache holds a reference */
+    +        atomic_set(&obj->refcnt, 1); /* The cache holds a reference */
+
+             spin_lock_irqsave(&cache_lock, flags);
+             __cache_add(obj);
+    @@ -119,7 +101,7 @@
+             spin_lock_irqsave(&cache_lock, flags);
+             obj = __cache_find(id);
+             if (obj)
+    -                __object_get(obj);
+    +                object_get(obj);
+             spin_unlock_irqrestore(&cache_lock, flags);
+             return obj;
+     }
+
+Proteggere l'oggetto stesso
+---------------------------
+
+In questo esempio, assumiamo che gli oggetti (ad eccezione del contatore
+di riferimenti) non cambino mai dopo la loro creazione. Se vogliamo permettere
+al nome di cambiare abbiamo tre possibilità:
+
+-  Si può togliere static da ``cache_lock`` e dire agli utenti che devono
+   trattenere il *lock* prima di modificare il nome di un oggetto.
+
+-  Si può fornire una funzione :c:func:`cache_obj_rename()` che prende il
+   *lock* e cambia il nome per conto del chiamante; si dirà poi agli utenti
+   di usare questa funzione.
+
+-  Si può decidere che ``cache_lock`` protegge solo la memoria stessa, ed
+   un altro *lock* è necessario per la protezione del nome.
+
+Teoricamente, possiamo avere un *lock* per ogni campo e per ogni oggetto.
+In pratica, le varianti più comuni sono:
+
+-  un *lock* che protegge l'infrastruttura (la lista ``cache`` di questo
+   esempio) e gli oggetti. Questo è quello che abbiamo fatto finora.
+
+-  un *lock* che protegge l'infrastruttura (inclusi i puntatori alla lista
+   negli oggetti), e un *lock* nell'oggetto per proteggere il resto
+   dell'oggetto stesso.
+
+-  *lock* multipli per proteggere l'infrastruttura (per esempio un *lock*
+   per ogni lista), possibilmente con un *lock* per oggetto.
+
+Qui di seguito un'implementazione con "un lock per oggetto":
+
+::
+
+    --- cache.c.refcnt-atomic   2003-12-11 15:50:54.000000000 +1100
+    +++ cache.c.perobjectlock   2003-12-11 17:15:03.000000000 +1100
+    @@ -6,11 +6,17 @@
+
+     struct object
+     {
+    +        /* These two protected by cache_lock. */
+             struct list_head list;
+    +        int popularity;
+    +
+             atomic_t refcnt;
+    +
+    +        /* Doesn't change once created. */
+             int id;
+    +
+    +        spinlock_t lock; /* Protects the name */
+             char name[32];
+    -        int popularity;
+     };
+
+     static DEFINE_SPINLOCK(cache_lock);
+    @@ -77,6 +84,7 @@
+             obj->id = id;
+             obj->popularity = 0;
+             atomic_set(&obj->refcnt, 1); /* The cache holds a reference */
+    +        spin_lock_init(&obj->lock);
+
+             spin_lock_irqsave(&cache_lock, flags);
+             __cache_add(obj);
+
+Da notare che ho deciso che il contatore di popolarità dovesse essere
+protetto da ``cache_lock`` piuttosto che dal *lock* dell'oggetto; questo
+perché è logicamente parte dell'infrastruttura (come
+:c:type:`struct list_head <list_head>` nell'oggetto). In questo modo,
+in :c:func:`__cache_add()`, non ho bisogno di trattenere il *lock* di ogni
+oggetto mentre si cerca il meno popolare.
+
+Ho anche deciso che il campo id è immutabile, quindi non ho bisogno di
+trattenere il lock dell'oggetto quando si usa :c:func:`__cache_find()`
+per leggere questo campo; il *lock* dell'oggetto è usato solo dal chiamante
+che vuole leggere o scrivere il campo name.
+
+Inoltre, da notare che ho aggiunto un commento che descrive i dati che sono
+protetti dal *lock*. Questo è estremamente importante in quanto descrive il
+comportamento del codice, che altrimenti sarebbe di difficile comprensione
+leggendo solamente il codice. E come dice Alan Cox: “Lock data, not code�.
+
+Problemi comuni
+===============
+
+.. _`it_deadlock`:
+
+Stallo: semplice ed avanzato
+----------------------------
+
+Esiste un tipo di  baco dove un pezzo di codice tenta di trattenere uno
+spinlock due volte: questo rimarrà in attesa attiva per sempre aspettando che
+il *lock* venga rilasciato (in Linux spinlocks, rwlocks e mutex non sono
+ricorsivi).
+Questo è facile da diagnosticare: non è uno di quei problemi che ti tengono
+sveglio 5 notti a parlare da solo.
+
+Un caso un pochino più complesso; immaginate d'avere una spazio condiviso
+fra un softirq ed il contesto utente. Se usate :c:func:`spin_lock()` per
+proteggerlo, il contesto utente potrebbe essere interrotto da un softirq
+mentre trattiene il lock, da qui il softirq rimarrà in attesa attiva provando
+ad acquisire il *lock* già trattenuto nel contesto utente.
+
+Questi casi sono chiamati stalli (*deadlock*), e come mostrato qui sopra,
+può succedere anche con un solo processore (Ma non sui sistemi
+monoprocessore perché gli spinlock spariscano quando il kernel è compilato
+con ``CONFIG_SMP``\ =n. Nonostante ciò, nel secondo caso avrete comunque
+una corruzione dei dati).
+
+Questi casi sono facili da diagnosticare; sui sistemi multi-processore
+il supervisione (*watchdog*) o l'opzione di compilazione ``DEBUG_SPINLOCK``
+(``include/linux/spinlock.h``) permettono di scovare immediatamente quando
+succedono.
+
+Esiste un caso più complesso che è conosciuto come l'abbraccio della morte;
+questo coinvolge due o più *lock*. Diciamo che avete un vettore di hash in cui
+ogni elemento è uno spinlock a cui è associata una lista di elementi con lo
+stesso hash. In un gestore di interruzioni software, dovete modificare un
+oggetto e spostarlo su un altro hash; quindi dovrete trattenete lo spinlock
+del vecchio hash e di quello nuovo, quindi rimuovere l'oggetto dal vecchio ed
+inserirlo nel nuovo.
+
+Qui abbiamo due problemi. Primo, se il vostro codice prova a spostare un
+oggetto all'interno della stessa lista, otterrete uno stallo visto che
+tenterà di trattenere lo stesso *lock* due volte. Secondo, se la stessa
+interruzione software su un altro processore sta tentando di spostare
+un altro oggetto nella direzione opposta, potrebbe accadere quanto segue:
+
++---------------------------------+---------------------------------+
+| CPU 1                           | CPU 2                           |
++=================================+=================================+
+| Trattiene *lock* A -> OK        | Trattiene *lock* B -> OK        |
++---------------------------------+---------------------------------+
+| Trattiene *lock* B -> attesa    | Trattiene *lock* A -> attesa    |
++---------------------------------+---------------------------------+
+
+Table: Conseguenze
+
+Entrambe i processori rimarranno in attesa attiva sul *lock* per sempre,
+aspettando che l'altro lo rilasci. Sembra e puzza come un blocco totale.
+
+Prevenire gli stalli
+--------------------
+
+I libri di testo vi diranno che se trattenete i *lock* sempre nello stesso
+ordine non avrete mai un simile stallo. La pratica vi dirà che questo
+approccio non funziona all'ingrandirsi del sistema: quando creo un nuovo
+*lock* non ne capisco abbastanza del kernel per dire in quale dei 5000 *lock*
+si incastrerà.
+
+I *lock* migliori sono quelli incapsulati: non vengono esposti nei file di
+intestazione, e non vengono mai trattenuti fuori dallo stesso file. Potete
+rileggere questo codice e vedere che non ci sarà mai uno stallo perché
+non tenterà mai di trattenere un altro *lock* quando lo ha già.
+Le persone che usano il vostro codice non devono nemmeno sapere che voi
+state usando dei *lock*.
+
+Un classico problema deriva dall'uso di *callback* e di *hook*: se li
+chiamate mentre trattenete un *lock*, rischiate uno stallo o un abbraccio
+della morte (chi lo sa cosa farà una *callback*?).
+
+Ossessiva prevenzione degli stalli
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Gli stalli sono un problema, ma non così terribile come la corruzione dei dati.
+Un pezzo di codice trattiene un *lock* di lettura, cerca in una lista,
+fallisce nel trovare quello che vuole, quindi rilascia il *lock* di lettura,
+trattiene un *lock* di scrittura ed inserisce un oggetto; questo genere di
+codice presenta una corsa critica.
+
+Se non riuscite a capire il perché, per favore state alla larga dal mio
+codice.
+
+corsa fra temporizzatori: un passatempo del kernel
+--------------------------------------------------
+
+I temporizzatori potrebbero avere dei problemi con le corse critiche.
+Considerate una collezione di oggetti (liste, hash, eccetera) dove ogni oggetto
+ha un temporizzatore che sta per distruggerlo.
+
+Se volete eliminare l'intera collezione (diciamo quando rimuovete un modulo),
+potreste fare come segue::
+
+            /* THIS CODE BAD BAD BAD BAD: IF IT WAS ANY WORSE IT WOULD USE
+               HUNGARIAN NOTATION */
+            spin_lock_bh(&list_lock);
+
+            while (list) {
+                    struct foo *next = list->next;
+                    del_timer(&list->timer);
+                    kfree(list);
+                    list = next;
+            }
+
+            spin_unlock_bh(&list_lock);
+
+Primo o poi, questo esploderà su un sistema multiprocessore perché un
+temporizzatore potrebbe essere già partiro prima di :c:func:`spin_lock_bh()`,
+e prenderà il *lock* solo dopo :c:func:`spin_unlock_bh()`, e cercherà
+di eliminare il suo oggetto (che però è già stato eliminato).
+
+Questo può essere evitato controllando il valore di ritorno di
+:c:func:`del_timer()`: se ritorna 1, il temporizzatore è stato già
+rimosso. Se 0, significa (in questo caso) che il temporizzatore è in
+esecuzione, quindi possiamo fare come segue::
+
+            retry:
+                    spin_lock_bh(&list_lock);
+
+                    while (list) {
+                            struct foo *next = list->next;
+                            if (!del_timer(&list->timer)) {
+                                    /* Give timer a chance to delete this */
+                                    spin_unlock_bh(&list_lock);
+                                    goto retry;
+                            }
+                            kfree(list);
+                            list = next;
+                    }
+
+                    spin_unlock_bh(&list_lock);
+
+Un altro problema è l'eliminazione dei temporizzatori che si riavviano
+da soli (chiamando :c:func:`add_timer()` alla fine della loro esecuzione).
+Dato che questo è un problema abbastanza comune con una propensione
+alle corse critiche, dovreste usare :c:func:`del_timer_sync()`
+(``include/linux/timer.h``) per gestire questo caso. Questa ritorna il
+numero di volte che il temporizzatore è stato interrotto prima che
+fosse in grado di fermarlo senza che si riavviasse.
+
+Velocità della sincronizzazione
+===============================
+
+Ci sono tre cose importanti da tenere in considerazione quando si valuta
+la velocità d'esecuzione di un pezzo di codice che necessita di
+sincronizzazione. La prima è la concorrenza: quante cose rimangono in attesa
+mentre qualcuno trattiene un *lock*. La seconda è il tempo necessario per
+acquisire (senza contese) e rilasciare un *lock*. La terza è di usare meno
+*lock* o di più furbi. Immagino che i *lock* vengano usati regolarmente,
+altrimenti, non sareste interessati all'efficienza.
+
+La concorrenza dipende da quanto a lungo un *lock* è trattenuto: dovreste
+trattenere un *lock* solo il tempo minimo necessario ma non un istante in più.
+Nella memoria dell'esempio precedente, creiamo gli oggetti senza trattenere
+il *lock*, poi acquisiamo il *lock* quando siamo pronti per inserirlo nella
+lista.
+
+Il tempo di acquisizione di un *lock* dipende da quanto danno fa
+l'operazione sulla *pipeline* (ovvero stalli della *pipeline*) e quant'è
+probabile che il processore corrente sia stato anche l'ultimo ad acquisire
+il *lock* (in pratica, il *lock* è nella memoria cache del processore
+corrente?): su sistemi multi-processore questa probabilità precipita
+rapidamente. Consideriamo un processore Intel Pentium III a 700Mhz: questo
+esegue un'istruzione in 0.7ns, un incremento atomico richiede 58ns, acquisire
+un *lock* che è nella memoria cache del processore richiede 160ns, e un
+trasferimento dalla memoria cache di un altro processore richiede altri
+170/360ns (Leggetevi l'articolo di Paul McKenney's `Linux Journal RCU
+article <http://www.linuxjournal.com/article.php?sid=6993>`__).
+
+Questi due obiettivi sono in conflitto: trattenere un *lock* per il minor
+tempo possibile potrebbe richiedere la divisione in più *lock* per diverse
+parti (come nel nostro ultimo esempio con un *lock* per ogni oggetto),
+ma questo aumenta il numero di acquisizioni di *lock*, ed il risultato
+spesso è che tutto è più lento che con un singolo *lock*. Questo è un altro
+argomento in favore della semplicità quando si parla di sincronizzazione.
+
+Il terzo punto è discusso di seguito: ci sono alcune tecniche per ridurre
+il numero di sincronizzazioni che devono essere fatte.
+
+Read/Write Lock Variants
+------------------------
+
+Sia gli spinlock che i mutex hanno una variante per la lettura/scrittura
+(read/write): ``rwlock_t`` e :c:type:`struct rw_semaphore <rw_semaphore>`.
+Queste dividono gli utenti in due categorie: i lettori e gli scrittori.
+Se state solo leggendo i dati, potete acquisire il *lock* di lettura, ma
+per scrivere avrete bisogno del *lock* di scrittura. Molti possono trattenere
+il *lock* di lettura, ma solo uno scrittore alla volta può trattenere
+quello di scrittura.
+
+Se il vostro codice si divide chiaramente in codice per lettori e codice
+per scrittori (come nel nostro esempio), e il *lock* dei lettori viene
+trattenuto per molto tempo, allora l'uso di questo tipo di *lock* può aiutare.
+Questi sono leggermente più lenti rispetto alla loro versione normale, quindi
+nella pratica l'uso di ``rwlock_t`` non ne vale la pena.
+
+Evitare i *lock*: Read Copy Update
+--------------------------------------------
+
+Esiste un metodo di sincronizzazione per letture e scritture detto
+Read Copy Update. Con l'uso della tecnica RCU, i lettori possono scordarsi
+completamente di trattenere i *lock*; dato che nel nostro esempio ci
+aspettiamo d'avere più lettore che scrittori (altrimenti questa memoria
+sarebbe uno spreco) possiamo dire che questo meccanismo permette
+un'ottimizzazione.
+
+Come facciamo a sbarazzarci dei *lock* di lettura? Sbarazzarsi dei *lock* di
+lettura significa che uno scrittore potrebbe cambiare la lista sotto al naso
+dei lettori. Questo è abbastanza semplice: possiamo leggere una lista
+concatenata se lo scrittore aggiunge elementi alla fine e con certe
+precauzioni. Per esempio, aggiungendo ``new`` ad una lista concatenata
+chiamata ``list``::
+
+            new->next = list->next;
+            wmb();
+            list->next = new;
+
+La funzione :c:func:`wmb()` è una barriera di sincronizzazione delle
+scritture. Questa garantisce che la prima operazione (impostare l'elemento
+``next`` del nuovo elemento) venga completata e vista da tutti i processori
+prima che venga eseguita la seconda operazione (che sarebbe quella di mettere
+il nuovo elemento nella lista). Questo è importante perché i moderni
+compilatori ed i moderni processori possono, entrambe, riordinare le istruzioni
+se non vengono istruiti altrimenti: vogliamo che i lettori non vedano
+completamente il nuovo elemento; oppure che lo vedano correttamente e quindi
+il puntatore ``next`` deve puntare al resto della lista.
+
+Fortunatamente, c'è una funzione che fa questa operazione sulle liste
+:c:type:`struct list_head <list_head>`: :c:func:`list_add_rcu()`
+(``include/linux/list.h``).
+
+Rimuovere un elemento dalla lista è anche più facile: sostituiamo il puntatore
+al vecchio elemento con quello del suo successore, e i lettori vedranno
+l'elemento o lo salteranno.
+
+::
+
+            list->next = old->next;
+
+La funzione :c:func:`list_del_rcu()` (``include/linux/list.h``) fa esattamente
+questo (la versione normale corrompe il vecchio oggetto, e non vogliamo che
+accada).
+
+Anche i lettori devono stare attenti: alcuni processori potrebbero leggere
+attraverso il puntatore ``next`` il contenuto dell'elemento successivo
+troppo presto, ma non accorgersi che il contenuto caricato è sbagliato quando
+il puntatore ``next`` viene modificato alla loro spalle. Ancora una volta
+c'è una funzione che viene in vostro aiuto :c:func:`list_for_each_entry_rcu()`
+(``include/linux/list.h``). Ovviamente, gli scrittori possono usare
+:c:func:`list_for_each_entry()` dato che non ci possono essere due scrittori
+in contemporanea.
+
+Il nostro ultimo dilemma è il seguente: quando possiamo realmente distruggere
+l'elemento rimosso? Ricordate, un lettore potrebbe aver avuto accesso a questo
+elemento proprio ora: se eliminiamo questo elemento ed il puntatore ``next``
+cambia, il lettore salterà direttamente nella spazzatura e scoppierà. Dobbiamo
+aspettare finché tutti i lettori che stanno attraversando la lista abbiano
+finito. Utilizziamo :c:func:`call_rcu()` per registrare una funzione di
+richiamo che distrugga l'oggetto quando tutti i lettori correnti hanno
+terminato. In alternative, potrebbe essere usata la funzione
+:c:func:`synchronize_rcu()` che blocca l'esecuzione finché tutti i lettori
+non terminano di ispezionare la lista.
+
+Ma come fa l'RCU a sapere quando i lettori sono finiti? Il meccanismo è
+il seguente: innanzi tutto i lettori accedono alla lista solo fra la coppia
+:c:func:`rcu_read_lock()`/:c:func:`rcu_read_unlock()` che disabilita la
+prelazione così che i lettori non vengano sospesi mentre stanno leggendo
+la lista.
+
+Poi, l'RCU aspetta finché tutti i processori non abbiano dormito almeno
+una volta; a questo punto, dato che i lettori non possono dormire, possiamo
+dedurre che un qualsiasi lettore che abbia consultato la lista durante la
+rimozione abbia già terminato, quindi la *callback* viene eseguita. Il vero
+codice RCU è un po' più ottimizzato di così, ma questa è l'idea di fondo.
+
+::
+
+    --- cache.c.perobjectlock   2003-12-11 17:15:03.000000000 +1100
+    +++ cache.c.rcupdate    2003-12-11 17:55:14.000000000 +1100
+    @@ -1,15 +1,18 @@
+     #include <linux/list.h>
+     #include <linux/slab.h>
+     #include <linux/string.h>
+    +#include <linux/rcupdate.h>
+     #include <linux/mutex.h>
+     #include <asm/errno.h>
+
+     struct object
+     {
+    -        /* These two protected by cache_lock. */
+    +        /* This is protected by RCU */
+             struct list_head list;
+             int popularity;
+
+    +        struct rcu_head rcu;
+    +
+             atomic_t refcnt;
+
+             /* Doesn't change once created. */
+    @@ -40,7 +43,7 @@
+     {
+             struct object *i;
+
+    -        list_for_each_entry(i, &cache, list) {
+    +        list_for_each_entry_rcu(i, &cache, list) {
+                     if (i->id == id) {
+                             i->popularity++;
+                             return i;
+    @@ -49,19 +52,25 @@
+             return NULL;
+     }
+
+    +/* Final discard done once we know no readers are looking. */
+    +static void cache_delete_rcu(void *arg)
+    +{
+    +        object_put(arg);
+    +}
+    +
+     /* Must be holding cache_lock */
+     static void __cache_delete(struct object *obj)
+     {
+             BUG_ON(!obj);
+    -        list_del(&obj->list);
+    -        object_put(obj);
+    +        list_del_rcu(&obj->list);
+             cache_num--;
+    +        call_rcu(&obj->rcu, cache_delete_rcu);
+     }
+
+     /* Must be holding cache_lock */
+     static void __cache_add(struct object *obj)
+     {
+    -        list_add(&obj->list, &cache);
+    +        list_add_rcu(&obj->list, &cache);
+             if (++cache_num > MAX_CACHE_SIZE) {
+                     struct object *i, *outcast = NULL;
+                     list_for_each_entry(i, &cache, list) {
+    @@ -104,12 +114,11 @@
+     struct object *cache_find(int id)
+     {
+             struct object *obj;
+    -        unsigned long flags;
+
+    -        spin_lock_irqsave(&cache_lock, flags);
+    +        rcu_read_lock();
+             obj = __cache_find(id);
+             if (obj)
+                     object_get(obj);
+    -        spin_unlock_irqrestore(&cache_lock, flags);
+    +        rcu_read_unlock();
+             return obj;
+     }
+
+Da notare che i lettori modificano il campo popularity nella funzione
+:c:func:`__cache_find()`, e ora non trattiene alcun *lock*. Una soluzione
+potrebbe essere quella di rendere la variabile ``atomic_t``, ma per l'uso
+che ne abbiamo fatto qui, non ci interessano queste corse critiche perché un
+risultato approssimativo è comunque accettabile, quindi non l'ho cambiato.
+
+Il risultato è che la funzione :c:func:`cache_find()` non ha bisogno di alcuna
+sincronizzazione con le altre funzioni, quindi è veloce su un sistema
+multi-processore tanto quanto lo sarebbe su un sistema mono-processore.
+
+Esiste un'ulteriore ottimizzazione possibile: vi ricordate il codice originale
+della nostra memoria dove non c'erano contatori di riferimenti e il chiamante
+semplicemente tratteneva il *lock* prima di accedere ad un oggetto? Questo è
+ancora possibile: se trattenete un *lock* nessuno potrà cancellare l'oggetto,
+quindi non avete bisogno di incrementare e decrementare il contatore di
+riferimenti.
+
+Ora, dato che il '*lock* di lettura' di un RCU non fa altro che disabilitare
+la prelazione, un chiamante che ha sempre la prelazione disabilitata fra le
+chiamate :c:func:`cache_find()` e :c:func:`object_put()` non necessita
+di incrementare e decrementare il contatore di riferimenti. Potremmo
+esporre la funzione :c:func:`__cache_find()` dichiarandola non-static,
+e quel chiamante potrebbe usare direttamente questa funzione.
+
+Il beneficio qui sta nel fatto che il contatore di riferimenti no
+viene scritto: l'oggetto non viene alterato in alcun modo e quindi diventa
+molto più veloce su sistemi molti-processore grazie alla loro memoria cache.
+
+.. _`it_per-cpu`:
+
+Dati per processore
+-------------------
+
+Un'altra tecnica comunemente usata per evitare la sincronizzazione è quella
+di duplicare le informazioni per ogni processore. Per esempio, se volete
+avere un contatore di qualcosa, potreste utilizzare uno spinlock ed un
+singolo contatore. Facile e pulito.
+
+Se questo dovesse essere troppo lento (solitamente non lo è, ma se avete
+dimostrato che lo è devvero), potreste usare un contatore per ogni processore
+e quindi non sarebbe più necessaria la mutua esclusione. Vedere
+:c:func:`DEFINE_PER_CPU()`, :c:func:`get_cpu_var()` e :c:func:`put_cpu_var()`
+(``include/linux/percpu.h``).
+
+Il tipo di dato ``local_t``, la funzione :c:func:`cpu_local_inc()` e tutte
+le altre funzioni associate, sono di particolare utilità per semplici contatori
+per-processore; su alcune architetture sono anche più efficienti
+(``include/asm/local.h``).
+
+Da notare che non esiste un modo facile ed affidabile per ottenere il valore
+di un simile contatore senza introdurre altri *lock*. In alcuni casi questo
+non è un problema.
+
+Dati che sono usati prevalentemente dai gestori d'interruzioni
+--------------------------------------------------------------
+
+Se i dati vengono utilizzati sempre dallo stesso gestore d'interruzioni,
+allora i *lock* non vi servono per niente: il kernel già vi garantisce che
+il gestore d'interruzione non verrà eseguito in contemporanea su diversi
+processori.
+
+Manfred Spraul fa notare che potreste comunque comportarvi così anche
+se i dati vengono occasionalmente utilizzati da un contesto utente o
+da un'interruzione software. Il gestore d'interruzione non utilizza alcun
+*lock*, e tutti gli altri accessi verranno fatti così::
+
+        spin_lock(&lock);
+        disable_irq(irq);
+        ...
+        enable_irq(irq);
+        spin_unlock(&lock);
+
+La funzione :c:func:`disable_irq()` impedisce al gestore d'interruzioni
+d'essere eseguito (e aspetta che finisca nel caso fosse in esecuzione su
+un altro processore). Lo spinlock, invece, previene accessi simultanei.
+Naturalmente, questo è più lento della semplice chiamata
+:c:func:`spin_lock_irq()`, quindi ha senso solo se questo genere di accesso
+è estremamente raro.
+
+.. _`it_sleeping-things`:
+
+Quali funzioni possono essere chiamate in modo sicuro dalle interruzioni?
+=========================================================================
+
+Molte funzioni del kernel dormono (in sostanza, chiamano ``schedule()``)
+direttamente od indirettamente: non potete chiamarle se trattenere uno
+spinlock o avete la prelazione disabilitata, mai. Questo significa che
+dovete necessariamente essere nel contesto utente: chiamarle da un
+contesto d'interruzione è illegale.
+
+Alcune funzioni che dormono
+---------------------------
+
+Le più comuni sono elencate qui di seguito, ma solitamente dovete leggere
+il codice per scoprire se altre chiamate sono sicure. Se chiunque altro
+le chiami dorme, allora dovreste poter dormire anche voi. In particolar
+modo, le funzioni di registrazione e deregistrazione solitamente si
+aspettano d'essere chiamante da un contesto utente e quindi che possono
+dormire.
+
+-  Accessi allo spazio utente:
+
+   -  :c:func:`copy_from_user()`
+
+   -  :c:func:`copy_to_user()`
+
+   -  :c:func:`get_user()`
+
+   -  :c:func:`put_user()`
+
+-  :c:func:`kmalloc(GFP_KERNEL) <kmalloc>`
+
+-  :c:func:`mutex_lock_interruptible()` and
+   :c:func:`mutex_lock()`
+
+   C'è anche :c:func:`mutex_trylock()` che però non dorme.
+   Comunque, non deve essere usata in un contesto d'interruzione dato
+   che la sua implementazione non è sicura in quel contesto.
+   Anche :c:func:`mutex_unlock()` non dorme mai. Non può comunque essere
+   usata in un contesto d'interruzione perché un mutex deve essere rilasciato
+   dallo stesso processo che l'ha acquisito.
+
+Alcune funzioni che non dormono
+-------------------------------
+
+Alcune funzioni possono essere chiamate tranquillamente da qualsiasi
+contesto, o trattenendo un qualsiasi *lock*.
+
+-  :c:func:`printk()`
+
+-  :c:func:`kfree()`
+
+-  :c:func:`add_timer()` e :c:func:`del_timer()`
+
+Riferimento per l'API dei Mutex
+===============================
+
+.. kernel-doc:: include/linux/mutex.h
+   :internal:
+
+.. kernel-doc:: kernel/locking/mutex.c
+   :export:
+
+Riferimento per l'API dei Futex
+===============================
+
+.. kernel-doc:: kernel/futex.c
+   :internal:
+
+Approfondimenti
+===============
+
+-  ``Documentation/locking/spinlocks.txt``: la guida di Linus Torvalds agli
+   spinlock del kernel.
+
+-  Unix Systems for Modern Architectures: Symmetric Multiprocessing and
+   Caching for Kernel Programmers.
+
+   L'introduzione alla sincronizzazione a livello di kernel di Curt Schimmel
+   è davvero ottima (non è scritta per Linux, ma approssimativamente si adatta
+   a tutte le situazioni). Il libro è costoso, ma vale ogni singolo spicciolo
+   per capire la sincronizzazione nei sistemi multi-processore.
+   [ISBN: 0201633388]
+
+Ringraziamenti
+==============
+
+Grazie a Telsa Gwynne per aver formattato questa guida in DocBook, averla
+pulita e aggiunto un po' di stile.
+
+Grazie a Martin Pool, Philipp Rumpf, Stephen Rothwell, Paul Mackerras,
+Ruedi Aschwanden, Alan Cox, Manfred Spraul, Tim Waugh, Pete Zaitcev,
+James Morris, Robert Love, Paul McKenney, John Ashby per aver revisionato,
+corretto, maledetto e commentato.
+
+Grazie alla congrega per non aver avuto alcuna influenza su questo documento.
+
+Glossario
+=========
+
+prelazione
+  Prima del kernel 2.5, o quando ``CONFIG_PREEMPT`` non è impostato, i processi
+  in contesto utente non si avvicendano nell'esecuzione (in pratica, il
+  processo userà il processore fino al proprio termine, a meno che non ci siano
+  delle interruzioni). Con l'aggiunta di ``CONFIG_PREEMPT`` nella versione
+  2.5.4 questo è cambiato: quando si è in contesto utente, processi con una
+  priorità maggiore possono subentrare nell'esecuzione: gli spinlock furono
+  cambiati per disabilitare la prelazioni, anche su sistemi monoprocessore.
+
+bh
+  Bottom Half: per ragioni storiche, le funzioni che contengono '_bh' nel
+  loro nome ora si riferiscono a qualsiasi interruzione software; per esempio,
+  :c:func:`spin_lock_bh()` blocca qualsiasi interuzione software sul processore
+  corrente. I *Bottom Halves* sono deprecati, e probabilmente verranno
+  sostituiti dai tasklet. In un dato momento potrà esserci solo un
+  *bottom half* in esecuzione.
+
+contesto d'interruzione
+  Non è il contesto utente: qui si processano le interruzioni hardware e
+  software. La macro :c:func:`in_interrupt()` ritorna vero.
+
+contesto utente
+  Il kernel che esegue qualcosa per conto di un particolare processo (per
+  esempio una chiamata di sistema) o di un thread del kernel. Potete
+  identificare il processo con la macro ``current``. Da non confondere
+  con lo spazio utente. Può essere interrotto sia da interruzioni software
+  che hardware.
+
+interruzione hardware
+  Richiesta di interruzione hardware. :c:func:`in_irq()` ritorna vero in un
+  gestore d'interruzioni hardware.
+
+interruzione software / softirq
+  Gestore di interruzioni software: :c:func:`in_irq()` ritorna falso;
+  :c:func:`in_softirq()` ritorna vero. I tasklet e le softirq sono entrambi
+  considerati 'interruzioni software'.
+
+  In soldoni, un softirq è uno delle 32 interruzioni software che possono
+  essere eseguite su più processori in contemporanea. A volte si usa per
+  riferirsi anche ai tasklet (in pratica tutte le interruzioni software).
+
+monoprocessore / UP
+  (Uni-Processor) un solo processore, ovvero non è SMP. (``CONFIG_SMP=n``).
+
+multi-processore / SMP
+  (Symmetric Multi-Processor) kernel compilati per sistemi multi-processore
+  (``CONFIG_SMP=y``).
+
+spazio utente
+  Un processo che esegue il proprio codice fuori dal kernel.
+
+tasklet
+  Un'interruzione software registrabile dinamicamente che ha la garanzia
+  d'essere eseguita solo su un processore alla volta.
+
+timer
+  Un'interruzione software registrabile dinamicamente che viene eseguita
+  (circa) in un determinato momento. Quando è in esecuzione è come un tasklet
+  (infatti, sono chiamati da ``TIMER_SOFTIRQ``).
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index 921739d00f69..7f01fb1c1084 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -1891,22 +1891,22 @@ Mandatory 배리어들ì�€ SMP 시스템ì—�ì„œë�„ UP 시스템ì—�ì„œë�„ SMP 효ê³
 		/* 소유권� 수정 */
 		desc->status = DEVICE_OWN;
 
-		/* MMIO 를 통해 디바�스� 공지를 하기 전� 메모리를 �기화 */
-		wmb();
-
 		/* 업��트� 디스�립터� 디바�스� 공지 */
 		writel(DESC_NOTIFY, doorbell);
 	}
 
      dma_rmb() 는 디스�립터로부터 ��터를 �어오기 전� 디바�스가 소유권�
-     내놓았�� 보장하게 하고, dma_wmb() 는 디바�스가 �신� 소유권� 다시
-     가졌�� 보기 전� 디스�립터� ��터가 쓰였�� 보장합니다.  wmb() 는
-     �시 �관성� 없는 (cache incoherent) MMIO �역� 쓰기를 시�하기 전�
-     �시 �관성� 있는 메모리 (cache coherent memory) 쓰기가 완료�었��
-     보장해주기 위해 필요합니다.
-
-     consistent memory � 대한 �세한 내용� 위해선 Documentation/DMA-API.txt
-     문서를 참고하세요.
+     내려놓았� 것� 보장하고, dma_wmb() 는 디바�스가 �신� 소유권� 다시
+     가졌�� 보기 전� 디스�립터� ��터가 쓰였� 것� 보장합니다.  참고로,
+     writel() � 사용하면 �시 �관성� 있는 메모리 (cache coherent memory)
+     쓰기가 MMIO �역�� 쓰기 전� 완료�었� 것� 보장하므로 writel() 앞�
+     wmb() 를 실행할 필요가 없�� 알아�시기 바�니다.  writel() 보다 비용�
+     저렴한 writel_relaxed() 는 �런 보장� 제공하지 않으므로 여기선 사용�지
+     않아야 합니다.
+
+     writel_relaxed() 와 같� 완화� I/O 접근�들� 대한 �세한 내용� 위해서는
+     "커� I/O 배리어� 효과" 섹션�, consistent memory � 대한 �세한 내용�
+     위해선 Documentation/DMA-API.txt 문서를 참고하세요.
 
 
 MMIO 쓰기 배리어
diff --git a/Documentation/translations/zh_CN/oops-tracing.txt b/Documentation/translations/zh_CN/oops-tracing.txt
index 41ab53cc0e83..a893f04dfd5d 100644
--- a/Documentation/translations/zh_CN/oops-tracing.txt
+++ b/Documentation/translations/zh_CN/oops-tracing.txt
@@ -1,4 +1,4 @@
-Chinese translated version of Documentation/admin-guide/oops-tracing.rst
+Chinese translated version of Documentation/admin-guide/bug-hunting.rst
 
 If you have any comment or update to the content, please contact the
 original document maintainer directly.  However, if you have a problem
@@ -8,7 +8,7 @@ or if there is a problem with the translation.
 
 Chinese maintainer: Dave Young <hidave.darkstar@gmail.com>
 ---------------------------------------------------------------------
-Documentation/admin-guide/oops-tracing.rst 的中文翻译
+Documentation/admin-guide/bug-hunting.rst 的中文翻译
 
 如果想评论或更新本文的内容，请直接�系原文档的维护者。如果你使用英文
 交�有困难的�，也�以�中文版维护者求助。如果本翻译更新��时或者翻
diff --git a/Documentation/usb/gadget_configfs.txt b/Documentation/usb/gadget_configfs.txt
index 635e57493709..b8cb38a98c19 100644
--- a/Documentation/usb/gadget_configfs.txt
+++ b/Documentation/usb/gadget_configfs.txt
@@ -226,7 +226,7 @@ $ rm configs/<config name>.<number>/<function>
 where <config name>.<number> specify the configuration and <function> is
 a symlink to a function being removed from the configuration, e.g.:
 
-$ rm configfs/c.1/ncm.usb0
+$ rm configs/c.1/ncm.usb0
 
 ...
 ...
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index d10944e619d3..cb8db4f9d097 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4391,6 +4391,22 @@ all such vmexits.
 
 Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
 
+7.14 KVM_CAP_S390_HPAGE_1M
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success, -EINVAL if hpage module parameter was not set
+	 or cmma is enabled
+
+With this capability the KVM support for memory backing with 1m pages
+through hugetlbfs can be enabled for a VM. After the capability is
+enabled, cmma can't be enabled anymore and pfmfi and the storage key
+interpretation are disabled. If cmma has already been enabled or the
+hpage module parameter is not set to 1, -EINVAL is returned.
+
+While it is generally possible to create a huge page backed VM without
+this capability, the VM will not be able to run.
+
 8. Other capabilities.
 ----------------------
 
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index a16aa2113840..f662d3c530e5 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -29,7 +29,11 @@ mount options are:
 L2 and L3 CDP are controlled seperately.
 
 RDT features are orthogonal. A particular system may support only
-monitoring, only control, or both monitoring and control.
+monitoring, only control, or both monitoring and control.  Cache
+pseudo-locking is a unique way of using cache control to "pin" or
+"lock" data in the cache. Details can be found in
+"Cache Pseudo-Locking".
+
 
 The mount succeeds if either of allocation or monitoring is present, but
 only those files and directories supported by the system will be created.
@@ -65,6 +69,29 @@ related to allocation:
 			some platforms support devices that have their
 			own settings for cache use which can over-ride
 			these bits.
+"bit_usage":		Annotated capacity bitmasks showing how all
+			instances of the resource are used. The legend is:
+			"0" - Corresponding region is unused. When the system's
+			      resources have been allocated and a "0" is found
+			      in "bit_usage" it is a sign that resources are
+			      wasted.
+			"H" - Corresponding region is used by hardware only
+			      but available for software use. If a resource
+			      has bits set in "shareable_bits" but not all
+			      of these bits appear in the resource groups'
+			      schematas then the bits appearing in
+			      "shareable_bits" but no resource group will
+			      be marked as "H".
+			"X" - Corresponding region is available for sharing and
+			      used by hardware and software. These are the
+			      bits that appear in "shareable_bits" as
+			      well as a resource group's allocation.
+			"S" - Corresponding region is used by software
+			      and available for sharing.
+			"E" - Corresponding region is used exclusively by
+			      one resource group. No sharing allowed.
+			"P" - Corresponding region is pseudo-locked. No
+			      sharing allowed.
 
 Memory bandwitdh(MB) subdirectory contains the following files
 with respect to allocation:
@@ -151,6 +178,9 @@ All groups contain the following files:
 	CPUs to/from this group. As with the tasks file a hierarchy is
 	maintained where MON groups may only include CPUs owned by the
 	parent CTRL_MON group.
+	When the resouce group is in pseudo-locked mode this file will
+	only be readable, reflecting the CPUs associated with the
+	pseudo-locked region.
 
 
 "cpus_list":
@@ -163,6 +193,21 @@ When control is enabled all CTRL_MON groups will also contain:
 	A list of all the resources available to this group.
 	Each resource has its own line and format - see below for details.
 
+"size":
+	Mirrors the display of the "schemata" file to display the size in
+	bytes of each allocation instead of the bits representing the
+	allocation.
+
+"mode":
+	The "mode" of the resource group dictates the sharing of its
+	allocations. A "shareable" resource group allows sharing of its
+	allocations while an "exclusive" resource group does not. A
+	cache pseudo-locked region is created by first writing
+	"pseudo-locksetup" to the "mode" file before writing the cache
+	pseudo-locked region's schemata to the resource group's "schemata"
+	file. On successful pseudo-locked region creation the mode will
+	automatically change to "pseudo-locked".
+
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
@@ -379,6 +424,170 @@ L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
 L3DATA:0=fffff;1=fffff;2=3c0;3=fffff
 L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
 
+Cache Pseudo-Locking
+--------------------
+CAT enables a user to specify the amount of cache space that an
+application can fill. Cache pseudo-locking builds on the fact that a
+CPU can still read and write data pre-allocated outside its current
+allocated area on a cache hit. With cache pseudo-locking, data can be
+preloaded into a reserved portion of cache that no application can
+fill, and from that point on will only serve cache hits. The cache
+pseudo-locked memory is made accessible to user space where an
+application can map it into its virtual address space and thus have
+a region of memory with reduced average read latency.
+
+The creation of a cache pseudo-locked region is triggered by a request
+from the user to do so that is accompanied by a schemata of the region
+to be pseudo-locked. The cache pseudo-locked region is created as follows:
+- Create a CAT allocation CLOSNEW with a CBM matching the schemata
+  from the user of the cache region that will contain the pseudo-locked
+  memory. This region must not overlap with any current CAT allocation/CLOS
+  on the system and no future overlap with this cache region is allowed
+  while the pseudo-locked region exists.
+- Create a contiguous region of memory of the same size as the cache
+  region.
+- Flush the cache, disable hardware prefetchers, disable preemption.
+- Make CLOSNEW the active CLOS and touch the allocated memory to load
+  it into the cache.
+- Set the previous CLOS as active.
+- At this point the closid CLOSNEW can be released - the cache
+  pseudo-locked region is protected as long as its CBM does not appear in
+  any CAT allocation. Even though the cache pseudo-locked region will from
+  this point on not appear in any CBM of any CLOS an application running with
+  any CLOS will be able to access the memory in the pseudo-locked region since
+  the region continues to serve cache hits.
+- The contiguous region of memory loaded into the cache is exposed to
+  user-space as a character device.
+
+Cache pseudo-locking increases the probability that data will remain
+in the cache via carefully configuring the CAT feature and controlling
+application behavior. There is no guarantee that data is placed in
+cache. Instructions like INVD, WBINVD, CLFLUSH, etc. can still evict
+“locked� data from cache. Power management C-states may shrink or
+power off cache. Deeper C-states will automatically be restricted on
+pseudo-locked region creation.
+
+It is required that an application using a pseudo-locked region runs
+with affinity to the cores (or a subset of the cores) associated
+with the cache on which the pseudo-locked region resides. A sanity check
+within the code will not allow an application to map pseudo-locked memory
+unless it runs with affinity to cores associated with the cache on which the
+pseudo-locked region resides. The sanity check is only done during the
+initial mmap() handling, there is no enforcement afterwards and the
+application self needs to ensure it remains affine to the correct cores.
+
+Pseudo-locking is accomplished in two stages:
+1) During the first stage the system administrator allocates a portion
+   of cache that should be dedicated to pseudo-locking. At this time an
+   equivalent portion of memory is allocated, loaded into allocated
+   cache portion, and exposed as a character device.
+2) During the second stage a user-space application maps (mmap()) the
+   pseudo-locked memory into its address space.
+
+Cache Pseudo-Locking Interface
+------------------------------
+A pseudo-locked region is created using the resctrl interface as follows:
+
+1) Create a new resource group by creating a new directory in /sys/fs/resctrl.
+2) Change the new resource group's mode to "pseudo-locksetup" by writing
+   "pseudo-locksetup" to the "mode" file.
+3) Write the schemata of the pseudo-locked region to the "schemata" file. All
+   bits within the schemata should be "unused" according to the "bit_usage"
+   file.
+
+On successful pseudo-locked region creation the "mode" file will contain
+"pseudo-locked" and a new character device with the same name as the resource
+group will exist in /dev/pseudo_lock. This character device can be mmap()'ed
+by user space in order to obtain access to the pseudo-locked memory region.
+
+An example of cache pseudo-locked region creation and usage can be found below.
+
+Cache Pseudo-Locking Debugging Interface
+---------------------------------------
+The pseudo-locking debugging interface is enabled by default (if
+CONFIG_DEBUG_FS is enabled) and can be found in /sys/kernel/debug/resctrl.
+
+There is no explicit way for the kernel to test if a provided memory
+location is present in the cache. The pseudo-locking debugging interface uses
+the tracing infrastructure to provide two ways to measure cache residency of
+the pseudo-locked region:
+1) Memory access latency using the pseudo_lock_mem_latency tracepoint. Data
+   from these measurements are best visualized using a hist trigger (see
+   example below). In this test the pseudo-locked region is traversed at
+   a stride of 32 bytes while hardware prefetchers and preemption
+   are disabled. This also provides a substitute visualization of cache
+   hits and misses.
+2) Cache hit and miss measurements using model specific precision counters if
+   available. Depending on the levels of cache on the system the pseudo_lock_l2
+   and pseudo_lock_l3 tracepoints are available.
+   WARNING: triggering this  measurement uses from two (for just L2
+   measurements) to four (for L2 and L3 measurements) precision counters on
+   the system, if any other measurements are in progress the counters and
+   their corresponding event registers will be clobbered.
+
+When a pseudo-locked region is created a new debugfs directory is created for
+it in debugfs as /sys/kernel/debug/resctrl/<newdir>. A single
+write-only file, pseudo_lock_measure, is present in this directory. The
+measurement on the pseudo-locked region depends on the number, 1 or 2,
+written to this debugfs file. Since the measurements are recorded with the
+tracing infrastructure the relevant tracepoints need to be enabled before the
+measurement is triggered.
+
+Example of latency debugging interface:
+In this example a pseudo-locked region named "newlock" was created. Here is
+how we can measure the latency in cycles of reading from this region and
+visualize this data with a histogram that is available if CONFIG_HIST_TRIGGERS
+is set:
+# :> /sys/kernel/debug/tracing/trace
+# echo 'hist:keys=latency' > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/trigger
+# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
+# echo 1 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure
+# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
+# cat /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/hist
+
+# event histogram
+#
+# trigger info: hist:keys=latency:vals=hitcount:sort=hitcount:size=2048 [active]
+#
+
+{ latency:        456 } hitcount:          1
+{ latency:         50 } hitcount:         83
+{ latency:         36 } hitcount:         96
+{ latency:         44 } hitcount:        174
+{ latency:         48 } hitcount:        195
+{ latency:         46 } hitcount:        262
+{ latency:         42 } hitcount:        693
+{ latency:         40 } hitcount:       3204
+{ latency:         38 } hitcount:       3484
+
+Totals:
+    Hits: 8192
+    Entries: 9
+   Dropped: 0
+
+Example of cache hits/misses debugging:
+In this example a pseudo-locked region named "newlock" was created on the L2
+cache of a platform. Here is how we can obtain details of the cache hits
+and misses using the platform's precision counters.
+
+# :> /sys/kernel/debug/tracing/trace
+# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable
+# echo 2 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure
+# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable
+# cat /sys/kernel/debug/tracing/trace
+
+# tracer: nop
+#
+#                              _-----=> irqs-off
+#                             / _----=> need-resched
+#                            | / _---=> hardirq/softirq
+#                            || / _--=> preempt-depth
+#                            ||| /     delay
+#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+#              | |       |   ||||       |         |
+ pseudo_lock_mea-1672  [002] ....  3132.860500: pseudo_lock_l2: hits=4097 miss=0
+
+
 Examples for RDT allocation usage:
 
 Example 1
@@ -502,7 +711,172 @@ siblings and only the real time threads are scheduled on the cores 4-7.
 
 # echo F0 > p0/cpus
 
-4) Locking between applications
+Example 4
+---------
+
+The resource groups in previous examples were all in the default "shareable"
+mode allowing sharing of their cache allocations. If one resource group
+configures a cache allocation then nothing prevents another resource group
+to overlap with that allocation.
+
+In this example a new exclusive resource group will be created on a L2 CAT
+system with two L2 cache instances that can be configured with an 8-bit
+capacity bitmask. The new exclusive resource group will be configured to use
+25% of each cache instance.
+
+# mount -t resctrl resctrl /sys/fs/resctrl/
+# cd /sys/fs/resctrl
+
+First, we observe that the default group is configured to allocate to all L2
+cache:
+
+# cat schemata
+L2:0=ff;1=ff
+
+We could attempt to create the new resource group at this point, but it will
+fail because of the overlap with the schemata of the default group:
+# mkdir p0
+# echo 'L2:0=0x3;1=0x3' > p0/schemata
+# cat p0/mode
+shareable
+# echo exclusive > p0/mode
+-sh: echo: write error: Invalid argument
+# cat info/last_cmd_status
+schemata overlaps
+
+To ensure that there is no overlap with another resource group the default
+resource group's schemata has to change, making it possible for the new
+resource group to become exclusive.
+# echo 'L2:0=0xfc;1=0xfc' > schemata
+# echo exclusive > p0/mode
+# grep . p0/*
+p0/cpus:0
+p0/mode:exclusive
+p0/schemata:L2:0=03;1=03
+p0/size:L2:0=262144;1=262144
+
+A new resource group will on creation not overlap with an exclusive resource
+group:
+# mkdir p1
+# grep . p1/*
+p1/cpus:0
+p1/mode:shareable
+p1/schemata:L2:0=fc;1=fc
+p1/size:L2:0=786432;1=786432
+
+The bit_usage will reflect how the cache is used:
+# cat info/L2/bit_usage
+0=SSSSSSEE;1=SSSSSSEE
+
+A resource group cannot be forced to overlap with an exclusive resource group:
+# echo 'L2:0=0x1;1=0x1' > p1/schemata
+-sh: echo: write error: Invalid argument
+# cat info/last_cmd_status
+overlaps with exclusive group
+
+Example of Cache Pseudo-Locking
+-------------------------------
+Lock portion of L2 cache from cache id 1 using CBM 0x3. Pseudo-locked
+region is exposed at /dev/pseudo_lock/newlock that can be provided to
+application for argument to mmap().
+
+# mount -t resctrl resctrl /sys/fs/resctrl/
+# cd /sys/fs/resctrl
+
+Ensure that there are bits available that can be pseudo-locked, since only
+unused bits can be pseudo-locked the bits to be pseudo-locked needs to be
+removed from the default resource group's schemata:
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSSSS
+# echo 'L2:1=0xfc' > schemata
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSS00
+
+Create a new resource group that will be associated with the pseudo-locked
+region, indicate that it will be used for a pseudo-locked region, and
+configure the requested pseudo-locked region capacity bitmask:
+
+# mkdir newlock
+# echo pseudo-locksetup > newlock/mode
+# echo 'L2:1=0x3' > newlock/schemata
+
+On success the resource group's mode will change to pseudo-locked, the
+bit_usage will reflect the pseudo-locked region, and the character device
+exposing the pseudo-locked region will exist:
+
+# cat newlock/mode
+pseudo-locked
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSSPP
+# ls -l /dev/pseudo_lock/newlock
+crw------- 1 root root 243, 0 Apr  3 05:01 /dev/pseudo_lock/newlock
+
+/*
+ * Example code to access one page of pseudo-locked cache region
+ * from user space.
+ */
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/mman.h>
+
+/*
+ * It is required that the application runs with affinity to only
+ * cores associated with the pseudo-locked region. Here the cpu
+ * is hardcoded for convenience of example.
+ */
+static int cpuid = 2;
+
+int main(int argc, char *argv[])
+{
+	cpu_set_t cpuset;
+	long page_size;
+	void *mapping;
+	int dev_fd;
+	int ret;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpuid, &cpuset);
+	ret = sched_setaffinity(0, sizeof(cpuset), &cpuset);
+	if (ret < 0) {
+		perror("sched_setaffinity");
+		exit(EXIT_FAILURE);
+	}
+
+	dev_fd = open("/dev/pseudo_lock/newlock", O_RDWR);
+	if (dev_fd < 0) {
+		perror("open");
+		exit(EXIT_FAILURE);
+	}
+
+	mapping = mmap(0, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		       dev_fd, 0);
+	if (mapping == MAP_FAILED) {
+		perror("mmap");
+		close(dev_fd);
+		exit(EXIT_FAILURE);
+	}
+
+	/* Application interacts with pseudo-locked memory @mapping */
+
+	ret = munmap(mapping, page_size);
+	if (ret < 0) {
+		perror("munmap");
+		close(dev_fd);
+		exit(EXIT_FAILURE);
+	}
+
+	close(dev_fd);
+	exit(EXIT_SUCCESS);
+}
+
+Locking between applications
+----------------------------
 
 Certain operations on the resctrl filesystem, composed of read/writes
 to/from multiple files, must be atomic.
@@ -510,7 +884,7 @@ to/from multiple files, must be atomic.
 As an example, the allocation of an exclusive reservation of L3 cache
 involves:
 
-  1. Read the cbmmasks from each directory
+  1. Read the cbmmasks from each directory or the per-resource "bit_usage"
   2. Find a contiguous set of bits in the global CBM bitmask that is clear
      in any of the directory cbmmasks
   3. Create a new directory
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 8d109ef67ab6..ad6d2a80cf05 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -92,9 +92,7 @@ APICs
 Timing
 
   notsc
-  Don't use the CPU time stamp counter to read the wall time.
-  This can be used to work around timing problems on multiprocessor systems
-  with not properly synchronized CPUs.
+  Deprecated, use tsc=unstable instead.
 
   nohpet
   Don't use the HPET timer.
@@ -156,6 +154,10 @@ NUMA
 		If given as an integer, fills all system RAM with N fake nodes
 		interleaved over physical nodes.
 
+  numa=fake=<N>U
+		If given as an integer followed by 'U', it will divide each
+		physical node into N emulated nodes.
+
 ACPI
 
   acpi=off	Don't enable ACPI
diff --git a/MAINTAINERS b/MAINTAINERS
index 3119bba7971c..a95a7e63ae55 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -367,6 +367,12 @@ L:	linux-acpi@vger.kernel.org
 S:	Maintained
 F:	drivers/acpi/arm64
 
+ACPI I2C MULTI INSTANTIATE DRIVER
+M:	Hans de Goede <hdegoede@redhat.com>
+L:	platform-driver-x86@vger.kernel.org
+S:	Maintained
+F:	drivers/platform/x86/i2c-multi-instantiate.c
+
 ACPI PMIC DRIVERS
 M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
 M:	Len Brown <lenb@kernel.org>
@@ -581,7 +587,7 @@ W:	https://www.infradead.org/~dhowells/kafs/
 
 AGPGART DRIVER
 M:	David Airlie <airlied@linux.ie>
-T:	git git://people.freedesktop.org/~airlied/linux (part of drm maint)
+T:	git git://anongit.freedesktop.org/drm/drm
 S:	Maintained
 F:	drivers/char/agp/
 F:	include/linux/agp*
@@ -2264,6 +2270,7 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git
 S:	Maintained
 F:	arch/arm64/
+X:	arch/arm64/boot/dts/
 F:	Documentation/arm64/
 
 AS3645A LED FLASH CONTROLLER DRIVER
@@ -2523,7 +2530,7 @@ S:	Supported
 F:	drivers/scsi/esas2r
 
 ATUSB IEEE 802.15.4 RADIO DRIVER
-M:	Stefan Schmidt <stefan@osg.samsung.com>
+M:	Stefan Schmidt <stefan@datenfreihafen.org>
 L:	linux-wpan@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ieee802154/atusb.c
@@ -2971,9 +2978,13 @@ N:	bcm585*
 N:	bcm586*
 N:	bcm88312
 N:	hr2
-F:	arch/arm64/boot/dts/broadcom/ns2*
+N:	stingray
+F:	arch/arm64/boot/dts/broadcom/northstar2/*
+F:	arch/arm64/boot/dts/broadcom/stingray/*
 F:	drivers/clk/bcm/clk-ns*
+F:	drivers/clk/bcm/clk-sr*
 F:	drivers/pinctrl/bcm/pinctrl-ns*
+F:	include/dt-bindings/clock/bcm-sr*
 
 BROADCOM KONA GPIO DRIVER
 M:	Ray Jui <rjui@broadcom.com>
@@ -4396,6 +4407,12 @@ X:	Documentation/spi
 X:	Documentation/media
 T:	git git://git.lwn.net/linux.git docs-next
 
+DOCUMENTATION/ITALIAN
+M:	Federico Vaga <federico.vaga@vaga.pv.it>
+L:	linux-doc@vger.kernel.org
+S:	Maintained
+F:	Documentation/translations/it_IT
+
 DONGWOON DW9714 LENS VOICE COIL DRIVER
 M:	Sakari Ailus <sakari.ailus@linux.intel.com>
 L:	linux-media@vger.kernel.org
@@ -4456,6 +4473,7 @@ F:	Documentation/blockdev/drbd/
 
 DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+R:	"Rafael J. Wysocki" <rafael@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
 S:	Supported
 F:	Documentation/kobject.txt
@@ -4626,7 +4644,7 @@ F:	include/uapi/drm/vmwgfx_drm.h
 DRM DRIVERS
 M:	David Airlie <airlied@linux.ie>
 L:	dri-devel@lists.freedesktop.org
-T:	git git://people.freedesktop.org/~airlied/linux
+T:	git git://anongit.freedesktop.org/drm/drm
 B:	https://bugs.freedesktop.org/
 C:	irc://chat.freenode.net/dri-devel
 S:	Maintained
@@ -5439,6 +5457,7 @@ F:	drivers/iommu/exynos-iommu.c
 
 EZchip NPS platform support
 M:	Vineet Gupta <vgupta@synopsys.com>
+M:	Ofer Levi <oferle@mellanox.com>
 S:	Supported
 F:	arch/arc/plat-eznps
 F:	arch/arc/boot/dts/eznps.dts
@@ -5669,7 +5688,7 @@ F:	drivers/crypto/caam/
 F:	Documentation/devicetree/bindings/crypto/fsl-sec4.txt
 
 FREESCALE DIU FRAMEBUFFER DRIVER
-M:	Timur Tabi <timur@tabi.org>
+M:	Timur Tabi <timur@kernel.org>
 L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/fbdev/fsl-diu-fb.*
@@ -5769,7 +5788,7 @@ S:	Maintained
 F:	drivers/net/wan/fsl_ucc_hdlc*
 
 FREESCALE QUICC ENGINE UCC UART DRIVER
-M:	Timur Tabi <timur@tabi.org>
+M:	Timur Tabi <timur@kernel.org>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/tty/serial/ucc_uart.c
@@ -5785,7 +5804,6 @@ F:	include/linux/fsl/
 
 FREESCALE SOC FS_ENET DRIVER
 M:	Pantelis Antoniou <pantelis.antoniou@gmail.com>
-M:	Vitaly Bordug <vbordug@ru.mvista.com>
 L:	linuxppc-dev@lists.ozlabs.org
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -5793,7 +5811,7 @@ F:	drivers/net/ethernet/freescale/fs_enet/
 F:	include/linux/fs_enet_pd.h
 
 FREESCALE SOC SOUND DRIVERS
-M:	Timur Tabi <timur@tabi.org>
+M:	Timur Tabi <timur@kernel.org>
 M:	Nicolin Chen <nicoleotsuka@gmail.com>
 M:	Xiubo Li <Xiubo.Lee@gmail.com>
 R:	Fabio Estevam <fabio.estevam@nxp.com>
@@ -5925,7 +5943,7 @@ F:	Documentation/dev-tools/gcov.rst
 
 GDB KERNEL DEBUGGING HELPER SCRIPTS
 M:	Jan Kiszka <jan.kiszka@siemens.com>
-M:	Kieran Bingham <kieran@bingham.xyz>
+M:	Kieran Bingham <kbingham@kernel.org>
 S:	Supported
 F:	scripts/gdb/
 
@@ -6904,7 +6922,7 @@ F:	drivers/clk/clk-versaclock5.c
 
 IEEE 802.15.4 SUBSYSTEM
 M:	Alexander Aring <alex.aring@gmail.com>
-M:	Stefan Schmidt <stefan@osg.samsung.com>
+M:	Stefan Schmidt <stefan@datenfreihafen.org>
 L:	linux-wpan@vger.kernel.org
 W:	http://wpan.cakelab.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git
@@ -7023,7 +7041,7 @@ M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/ina209
-F:	Documentation/devicetree/bindings/i2c/ina209.txt
+F:	Documentation/devicetree/bindings/hwmon/ina2xx.txt
 F:	drivers/hwmon/ina209.c
 
 INA2XX HARDWARE MONITOR DRIVER
@@ -7091,6 +7109,7 @@ F:	include/uapi/linux/input.h
 F:	include/uapi/linux/input-event-codes.h
 F:	include/linux/input/
 F:	Documentation/devicetree/bindings/input/
+F:	Documentation/devicetree/bindings/serio/
 F:	Documentation/input/
 
 INPUT MULTITOUCH (MT) PROTOCOL
@@ -7980,7 +7999,7 @@ F:	lib/test_kmod.c
 F:	tools/testing/selftests/kmod/
 
 KPROBES
-M:	Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
+M:	Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
 M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
@@ -8311,10 +8330,16 @@ M:	Jade Alglave <j.alglave@ucl.ac.uk>
 M:	Luc Maranget <luc.maranget@inria.fr>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 R:	Akira Yokosawa <akiyks@gmail.com>
+R:	Daniel Lustig <dlustig@nvidia.com>
 L:	linux-kernel@vger.kernel.org
+L:	linux-arch@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	tools/memory-model/
+F:	Documentation/atomic_bitops.txt
+F:	Documentation/atomic_t.txt
+F:	Documentation/core-api/atomic_ops.rst
+F:	Documentation/core-api/refcount-vs-atomic.rst
 F:	Documentation/memory-barriers.txt
 
 LIS3LV02D ACCELEROMETER DRIVER
@@ -8619,7 +8644,7 @@ MARVELL MWIFIEX WIRELESS DRIVER
 M:	Amitkumar Karwar <amitkarwar@gmail.com>
 M:	Nishant Sarmukadam <nishants@marvell.com>
 M:	Ganapathi Bhat <gbhat@marvell.com>
-M:	Xinming Hu <huxm@marvell.com>
+M:	Xinming Hu <huxinming820@gmail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
 F:	drivers/net/wireless/marvell/mwifiex/
@@ -9065,7 +9090,7 @@ S:	Maintained
 F:	drivers/usb/mtu3/
 
 MEGACHIPS STDPXXXX-GE-B850V3-FW LVDS/DP++ BRIDGES
-M:	Peter Senna Tschudin <peter.senna@collabora.com>
+M:	Peter Senna Tschudin <peter.senna@gmail.com>
 M:	Martin Donnelly <martin.donnelly@ge.com>
 M:	Martyn Welch <martyn.welch@collabora.co.uk>
 S:	Maintained
@@ -9336,7 +9361,6 @@ F:	drivers/media/platform/atmel/atmel-isc-regs.h
 F:	devicetree/bindings/media/atmel-isc.txt
 
 MICROCHIP / ATMEL NAND DRIVER
-M:	Wenyou Yang <wenyou.yang@microchip.com>
 M:	Josh Wu <rainyfeeling@outlook.com>
 L:	linux-mtd@lists.infradead.org
 S:	Supported
@@ -9877,6 +9901,7 @@ M:	Andrew Lunn <andrew@lunn.ch>
 M:	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 S:	Maintained
+F:	Documentation/devicetree/bindings/net/dsa/
 F:	net/dsa/
 F:	include/net/dsa.h
 F:	include/linux/dsa/
@@ -10203,11 +10228,13 @@ F:	sound/soc/codecs/sgtl5000*
 
 NXP TDA998X DRM DRIVER
 M:	Russell King <linux@armlinux.org.uk>
-S:	Supported
+S:	Maintained
 T:	git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-devel
 T:	git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-fixes
 F:	drivers/gpu/drm/i2c/tda998x_drv.c
 F:	include/drm/i2c/tda998x.h
+F:	include/dt-bindings/display/tda998x.h
+K:	"nxp,tda998x"
 
 NXP TFA9879 DRIVER
 M:	Peter Rosin <peda@axentia.se>
@@ -11244,7 +11271,7 @@ F:	Documentation/devicetree/bindings/pinctrl/fsl,*
 
 PIN CONTROLLER - INTEL
 M:	Mika Westerberg <mika.westerberg@linux.intel.com>
-M:	Heikki Krogerus <heikki.krogerus@linux.intel.com>
+M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 S:	Maintained
 F:	drivers/pinctrl/intel/
 
@@ -11471,6 +11498,15 @@ W:	http://wireless.kernel.org/en/users/Drivers/p54
 S:	Obsolete
 F:	drivers/net/wireless/intersil/prism54/
 
+PROC FILESYSTEM
+R:	Alexey Dobriyan <adobriyan@gmail.com>
+L:	linux-kernel@vger.kernel.org
+L:	linux-fsdevel@vger.kernel.org
+S:	Maintained
+F:	fs/proc/
+F:	include/linux/proc_fs.h
+F:	tools/testing/selftests/proc/
+
 PROC SYSCTL
 M:	"Luis R. Rodriguez" <mcgrof@kernel.org>
 M:	Kees Cook <keescook@chromium.org>
@@ -11803,9 +11839,9 @@ F:  Documentation/devicetree/bindings/opp/kryo-cpufreq.txt
 F:  drivers/cpufreq/qcom-cpufreq-kryo.c
 
 QUALCOMM EMAC GIGABIT ETHERNET DRIVER
-M:	Timur Tabi <timur@codeaurora.org>
+M:	Timur Tabi <timur@kernel.org>
 L:	netdev@vger.kernel.org
-S:	Supported
+S:	Maintained
 F:	drivers/net/ethernet/qualcomm/emac/
 
 QUALCOMM HEXAGON ARCHITECTURE
@@ -11816,7 +11852,7 @@ S:	Supported
 F:	arch/hexagon/
 
 QUALCOMM HIDMA DRIVER
-M:	Sinan Kaya <okaya@codeaurora.org>
+M:	Sinan Kaya <okaya@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org
 L:	linux-arm-msm@vger.kernel.org
 L:	dmaengine@vger.kernel.org
@@ -12016,9 +12052,9 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/
 X:	Documentation/RCU/torture.txt
 F:	include/linux/rcu*
-X:	include/linux/srcu.h
+X:	include/linux/srcu*.h
 F:	kernel/rcu/
-X:	kernel/torture.c
+X:	kernel/rcu/srcu*.c
 
 REAL TIME CLOCK (RTC) SUBSYSTEM
 M:	Alessandro Zummo <a.zummo@towertech.it>
@@ -12379,7 +12415,6 @@ F:	drivers/pci/hotplug/s390_pci_hpc.c
 
 S390 VFIO-CCW DRIVER
 M:	Cornelia Huck <cohuck@redhat.com>
-M:	Dong Jia Shi <bjsdjshi@linux.ibm.com>
 M:	Halil Pasic <pasic@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	kvm@vger.kernel.org
@@ -13055,8 +13090,8 @@ L:	linux-kernel@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
-F:	include/linux/srcu.h
-F:	kernel/rcu/srcu.c
+F:	include/linux/srcu*.h
+F:	kernel/rcu/srcu*.c
 
 SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus)
 M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
@@ -13552,6 +13587,13 @@ L:	linux-block@vger.kernel.org
 S:	Maintained
 F:	drivers/block/skd*[ch]
 
+STI AUDIO (ASoC) DRIVERS
+M:	Arnaud Pouliquen <arnaud.pouliquen@st.com>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
+F:	sound/soc/sti/
+
 STI CEC DRIVER
 M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
 S:	Maintained
@@ -13565,6 +13607,14 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/usb/stk1160/
 
+STM32 AUDIO (ASoC) DRIVERS
+M:	Olivier Moysan <olivier.moysan@st.com>
+M:	Arnaud Pouliquen <arnaud.pouliquen@st.com>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/sound/st,stm32-*.txt
+F:	sound/soc/stm/
+
 STM32 TIMER/LPTIMER DRIVERS
 M:	Fabrice Gasnier <fabrice.gasnier@st.com>
 S:	Maintained
@@ -14035,6 +14085,13 @@ M:	Laxman Dewangan <ldewangan@nvidia.com>
 S:	Supported
 F:	drivers/input/keyboard/tegra-kbc.c
 
+TEGRA NAND DRIVER
+M:	Stefan Agner <stefan@agner.ch>
+M:	Lucas Stach <dev@lynxeye.de>
+S:	Maintained
+F:	Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt
+F:	drivers/mtd/nand/raw/tegra_nand.c
+
 TEGRA PWM DRIVER
 M:	Thierry Reding <thierry.reding@gmail.com>
 S:	Supported
@@ -14415,6 +14472,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/torture.txt
 F:	kernel/torture.c
 F:	kernel/rcu/rcutorture.c
+F:	kernel/rcu/rcuperf.c
 F:	kernel/locking/locktorture.c
 
 TOSHIBA ACPI EXTRAS DRIVER
diff --git a/Makefile b/Makefile
index c9132594860b..863f58503bee 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 18
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION =
 NAME = Merciless Moray
 
 # *DOCUMENTATION*
@@ -353,9 +353,9 @@ CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \
 	  else if [ -x /bin/bash ]; then echo /bin/bash; \
 	  else echo sh; fi ; fi)
 
-HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS)
-HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS)
-HOST_LFS_LIBS := $(shell getconf LFS_LIBS)
+HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS 2>/dev/null)
+HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS 2>/dev/null)
+HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null)
 
 HOSTCC       = gcc
 HOSTCXX      = g++
@@ -507,11 +507,6 @@ ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLA
   KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
 endif
 
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/cc-can-link.sh $(CC)), y)
-  CC_CAN_LINK := y
-  export CC_CAN_LINK
-endif
-
 # The expansion should be delayed until arch/$(SRCARCH)/Makefile is included.
 # Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile.
 # CC_VERSION_TEXT is referenced from Kconfig (so it needs export),
@@ -1717,6 +1712,6 @@ endif	# skip-makefile
 PHONY += FORCE
 FORCE:
 
-# Declare the contents of the .PHONY variable as phony.  We keep that
+# Declare the contents of the PHONY variable as phony.  We keep that
 # information in a variable so we can use it in if_changed and friends.
 .PHONY: $(PHONY)
diff --git a/arch/Kconfig b/arch/Kconfig
index 1aa59063f1fd..d1f2ed462ac8 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -13,6 +13,9 @@ config KEXEC_CORE
 config HAVE_IMA_KEXEC
 	bool
 
+config HOTPLUG_SMT
+	bool
+
 config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 767bfdd42992..150a1c5d6a2c 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -18,11 +18,11 @@
  * To ensure dependency ordering is preserved for the _relaxed and
  * _release atomics, an smp_read_barrier_depends() is unconditionally
  * inserted into the _relaxed variants, which are used to build the
- * barriered versions. To avoid redundant back-to-back fences, we can
- * define the _acquire and _fence versions explicitly.
+ * barriered versions. Avoid redundant back-to-back fences in the
+ * _acquire and _fence versions.
  */
-#define __atomic_op_acquire(op, args...)	op##_relaxed(args)
-#define __atomic_op_fence			__atomic_op_release
+#define __atomic_acquire_fence()
+#define __atomic_post_full_fence()
 
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -206,7 +206,7 @@ ATOMIC_OPS(xor, xor)
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -214,7 +214,7 @@ ATOMIC_OPS(xor, xor)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, new, old;
 	smp_mb();
@@ -235,38 +235,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	smp_mb();
 	return old;
 }
-
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
  * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
+ * Returns the old value of @v.
  */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
-	long c, tmp;
+	long c, new, old;
 	smp_mb();
 	__asm__ __volatile__(
-	"1:	ldq_l	%[tmp],%[mem]\n"
-	"	cmpeq	%[tmp],%[u],%[c]\n"
-	"	addq	%[tmp],%[a],%[tmp]\n"
+	"1:	ldq_l	%[old],%[mem]\n"
+	"	cmpeq	%[old],%[u],%[c]\n"
+	"	addq	%[old],%[a],%[new]\n"
 	"	bne	%[c],2f\n"
-	"	stq_c	%[tmp],%[mem]\n"
-	"	beq	%[tmp],3f\n"
+	"	stq_c	%[new],%[mem]\n"
+	"	beq	%[new],3f\n"
 	"2:\n"
 	".subsection 2\n"
 	"3:	br	1b\n"
 	".previous"
-	: [tmp] "=&r"(tmp), [c] "=&r"(c)
+	: [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c)
 	: [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u)
 	: "memory");
 	smp_mb();
-	return !c;
+	return old;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
@@ -295,31 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	smp_mb();
 	return old - 1;
 }
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-#define atomic64_dec_return(v) atomic64_sub_return(1,(v))
-
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-#define atomic64_inc_return(v) atomic64_add_return(1,(v))
-
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0)
-#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0)
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
-#define atomic_inc(v) atomic_add(1,(v))
-#define atomic64_inc(v) atomic64_add(1,(v))
-
-#define atomic_dec(v) atomic_sub(1,(v))
-#define atomic64_dec(v) atomic64_sub(1,(v))
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #endif /* _ALPHA_ATOMIC_H */
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 6e921754c8fc..c210a25dd6da 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1180,13 +1180,10 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 		struct rusage32 __user *, ur)
 {
-	unsigned int status = 0;
 	struct rusage r;
-	long err = kernel_wait4(pid, &status, options, &r);
+	long err = kernel_wait4(pid, ustatus, options, &r);
 	if (err <= 0)
 		return err;
-	if (put_user(status, ustatus))
-		return -EFAULT;
 	if (!ur)
 		return err;
 	if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime))
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index e81bcd271be7..5151d81476a1 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -50,6 +50,9 @@ config ARC
 	select HAVE_KERNEL_LZMA
 	select ARCH_HAS_PTE_SPECIAL
 
+config ARCH_HAS_CACHE_LINE_SIZE
+	def_bool y
+
 config MIGHT_HAVE_PCI
 	bool
 
@@ -413,7 +416,7 @@ config ARC_HAS_DIV_REM
 
 config ARC_HAS_ACCL_REGS
 	bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6)"
-	default n
+	default y
 	help
 	  Depending on the configuration, CPU can contain accumulator reg-pair
 	  (also referred to as r58:r59). These can also be used by gcc as GPR so
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index d37f49d6a27f..6c1b20dd76ad 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -16,7 +16,7 @@ endif
 
 KBUILD_DEFCONFIG := nsim_700_defconfig
 
-cflags-y	+= -fno-common -pipe -fno-builtin -D__linux__
+cflags-y	+= -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__
 cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
 cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=archs
 
@@ -140,16 +140,3 @@ dtbs: scripts
 
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
-
-# Hacks to enable final link due to absence of link-time branch relexation
-# and gcc choosing optimal(shorter) branches at -O3
-#
-# vineetg Feb 2010: -mlong-calls switched off for overall kernel build
-# However lib/decompress_inflate.o (.init.text) calls
-# zlib_inflate_workspacesize (.text) causing relocation errors.
-# Thus forcing all exten calls in this file to be long calls
-export CFLAGS_decompress_inflate.o = -mmedium-calls
-export CFLAGS_initramfs.o = -mmedium-calls
-ifdef CONFIG_SMP
-export CFLAGS_core.o = -mmedium-calls
-endif
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 09f85154c5a4..a635ea972304 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 09fed3ef22b6..aa507e423075 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index ea2f6d817d1a..eba07f468654 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig
index ab231c040efe..098b19fbaa51 100644
--- a/arch/arc/configs/haps_hs_defconfig
+++ b/arch/arc/configs/haps_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EXPERT=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig
index cf449cbf440d..0104c404d897 100644
--- a/arch/arc/configs/haps_hs_smp_defconfig
+++ b/arch/arc/configs/haps_hs_smp_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 1b54c72f4296..6491be0ddbc9 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index 31c2c70b34a1..99e05cf63fca 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index a578c721d50f..0dc4f9b737e7 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index 37d7395f3272..be3c30a15e54 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 1e1470e2a7f0..3a74b9b21772 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index 084a6e42685b..ea2834b4dc1d 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index f36d47990415..80a5a1b4924b 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -9,7 +9,6 @@ CONFIG_IKCONFIG_PROC=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 1aca2e8fd1ba..2cc87f909747 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -56,7 +56,6 @@ CONFIG_STMMAC_ETH=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
-CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 11859287c52a..4e0072730241 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -187,7 +187,8 @@ static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
-#define atomic_andnot atomic_andnot
+#define atomic_andnot		atomic_andnot
+#define atomic_fetch_andnot	atomic_fetch_andnot
 
 #undef ATOMIC_OPS
 #define ATOMIC_OPS(op, c_op, asm_op)					\
@@ -296,8 +297,6 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
 	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
-#define atomic_andnot(mask, v) atomic_and(~(mask), (v))
-#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v))
 ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
 ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 
@@ -308,48 +307,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v
- */
-#define __atomic_add_unless(v, a, u)					\
-({									\
-	int c, old;							\
-									\
-	/*								\
-	 * Explicit full memory barrier needed before/after as		\
-	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
-	 */								\
-	smp_mb();							\
-									\
-	c = atomic_read(v);						\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
-		c = old;						\
-									\
-	smp_mb();							\
-									\
-	c;								\
-})
-
-#define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
-
-#define atomic_inc(v)			atomic_add(1, v)
-#define atomic_dec(v)			atomic_sub(1, v)
-
-#define atomic_inc_and_test(v)		(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i, v)	(atomic_add_return(i, v) < 0)
-
-
 #ifdef CONFIG_GENERIC_ATOMIC64
 
 #include <asm-generic/atomic64.h>
@@ -472,7 +429,8 @@ static inline long long atomic64_fetch_##op(long long a, atomic64_t *v)	\
 	ATOMIC64_OP_RETURN(op, op1, op2)				\
 	ATOMIC64_FETCH_OP(op, op1, op2)
 
-#define atomic64_andnot atomic64_andnot
+#define atomic64_andnot		atomic64_andnot
+#define atomic64_fetch_andnot	atomic64_fetch_andnot
 
 ATOMIC64_OPS(add, add.f, adc)
 ATOMIC64_OPS(sub, sub.f, sbc)
@@ -559,53 +517,43 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 
 	return val;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
- * if (v != u) { v += a; ret = 1} else {ret = 0}
- * Returns 1 iff @v was not @u (i.e. if add actually happened)
+ * Atomically adds @a to @v, if it was not @u.
+ * Returns the old value of @v
  */
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	long long val;
-	int op_done;
+	long long old, temp;
 
 	smp_mb();
 
 	__asm__ __volatile__(
 	"1:	llockd  %0, [%2]	\n"
-	"	mov	%1, 1		\n"
 	"	brne	%L0, %L4, 2f	# continue to add since v != u \n"
 	"	breq.d	%H0, %H4, 3f	# return since v == u \n"
-	"	mov	%1, 0		\n"
 	"2:				\n"
-	"	add.f   %L0, %L0, %L3	\n"
-	"	adc     %H0, %H0, %H3	\n"
-	"	scondd  %0, [%2]	\n"
+	"	add.f   %L1, %L0, %L3	\n"
+	"	adc     %H1, %H0, %H3	\n"
+	"	scondd  %1, [%2]	\n"
 	"	bnz     1b		\n"
 	"3:				\n"
-	: "=&r"(val), "=&r" (op_done)
+	: "=&r"(old), "=&r" (temp)
 	: "r"(&v->counter), "r"(a), "r"(u)
 	: "cc");	/* memory clobber comes from smp_mb() */
 
 	smp_mb();
 
-	return op_done;
+	return old;
 }
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif	/* !CONFIG_GENERIC_ATOMIC64 */
 
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 8486f328cc5d..ff7d3232764a 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -48,7 +48,9 @@
 })
 
 /* Largest line length for either L1 or L2 is 128 bytes */
-#define ARCH_DMA_MINALIGN      128
+#define SMP_CACHE_BYTES		128
+#define cache_line_size()	SMP_CACHE_BYTES
+#define ARCH_DMA_MINALIGN	SMP_CACHE_BYTES
 
 extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index d5da2115d78a..03d6bb0f4e13 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -17,8 +17,11 @@
 #ifndef __ASM_ARC_UDELAY_H
 #define __ASM_ARC_UDELAY_H
 
+#include <asm-generic/types.h>
 #include <asm/param.h>		/* HZ */
 
+extern unsigned long loops_per_jiffy;
+
 static inline void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index ec36d5b6d435..29f3988c9424 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -234,6 +234,9 @@
 	POP	gp
 	RESTORE_R12_TO_R0
 
+#ifdef CONFIG_ARC_CURR_IN_REG
+	ld	r25, [sp, 12]
+#endif
 	ld  sp, [sp] /* restore original sp */
 	/* orig_r0, ECR, user_r25 skipped automatically */
 .endm
@@ -315,6 +318,9 @@
 	POP	gp
 	RESTORE_R12_TO_R0
 
+#ifdef CONFIG_ARC_CURR_IN_REG
+	ld	r25, [sp, 12]
+#endif
 	ld  sp, [sp] /* restore original sp */
 	/* orig_r0, ECR, user_r25 skipped automatically */
 .endm
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 51597f344a62..302b0db8ea2b 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -86,9 +86,6 @@
 	POP	r1
 	POP	r0
 
-#ifdef CONFIG_ARC_CURR_IN_REG
-	ld	r25, [sp, 12]
-#endif
 .endm
 
 /*--------------------------------------------------------------
diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h
index 2e52d18e6bc7..2c1b479d5aea 100644
--- a/arch/arc/include/asm/kprobes.h
+++ b/arch/arc/include/asm/kprobes.h
@@ -45,8 +45,6 @@ struct prev_kprobe {
 
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
index c28e6c347b49..871f3cb16af9 100644
--- a/arch/arc/include/asm/mach_desc.h
+++ b/arch/arc/include/asm/mach_desc.h
@@ -34,9 +34,7 @@ struct machine_desc {
 	const char		*name;
 	const char		**dt_compat;
 	void			(*init_early)(void);
-#ifdef CONFIG_SMP
 	void			(*init_per_cpu)(unsigned int);
-#endif
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
 
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 109baa06831c..09ddddf71cc5 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -105,7 +105,7 @@ typedef pte_t * pgtable_t;
 #define virt_addr_valid(kaddr)  pfn_valid(virt_to_pfn(kaddr))
 
 /* Default Permissions for stack/heaps pages (Non Executable) */
-#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE)
+#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
 #define WANT_PAGE_VIRTUAL   1
 
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 8ec5599a0957..cf4be70d5892 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -377,7 +377,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 
 /* Decode a PTE containing swap "identifier "into constituents */
 #define __swp_type(pte_lookalike)	(((pte_lookalike).val) & 0x1f)
-#define __swp_offset(pte_lookalike)	((pte_lookalike).val << 13)
+#define __swp_offset(pte_lookalike)	((pte_lookalike).val >> 13)
 
 /* NOPs, to keep generic kernel happy */
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 538b36afe89e..62b185057c04 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -31,10 +31,10 @@ void __init init_IRQ(void)
 	/* a SMP H/w block could do IPI IRQ request here */
 	if (plat_smp_ops.init_per_cpu)
 		plat_smp_ops.init_per_cpu(smp_processor_id());
+#endif
 
 	if (machine_desc->init_per_cpu)
 		machine_desc->init_per_cpu(smp_processor_id());
-#endif
 }
 
 /*
diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 42b05046fad9..df35d4c0b0b8 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -225,24 +225,18 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
 
 		/* If we have no pre-handler or it returned 0, we continue with
 		 * normal processing. If we have a pre-handler and it returned
-		 * non-zero - which is expected from setjmp_pre_handler for
-		 * jprobe, we return without single stepping and leave that to
-		 * the break-handler which is invoked by a kprobe from
-		 * jprobe_return
+		 * non-zero - which means user handler setup registers to exit
+		 * to another instruction, we must skip the single stepping.
 		 */
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			setup_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_HIT_SS;
+		} else {
+			reset_current_kprobe();
+			preempt_enable_no_resched();
 		}
 
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			setup_singlestep(p, regs);
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			return 1;
-		}
 	}
 
 	/* no_kprobe: */
@@ -386,38 +380,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long sp_addr = regs->sp;
-
-	kcb->jprobe_saved_regs = *regs;
-	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
-	regs->ret = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	__asm__ __volatile__("unimp_s");
-	return;
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long sp_addr;
-
-	*regs = kcb->jprobe_saved_regs;
-	sp_addr = regs->sp;
-	memcpy((void *)sp_addr, kcb->jprobes_stack, MIN_STACK_SIZE(sp_addr));
-	preempt_enable_no_resched();
-
-	return 1;
-}
-
 static void __used kretprobe_trampoline_holder(void)
 {
 	__asm__ __volatile__(".global kretprobe_trampoline\n"
@@ -483,9 +445,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	regs->ret = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 5ac3b547453f..4674541eba3f 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -47,7 +47,8 @@ SYSCALL_DEFINE0(arc_gettls)
 SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 {
 	struct pt_regs *regs = current_pt_regs();
-	int uval = -EFAULT;
+	u32 uval;
+	int ret;
 
 	/*
 	 * This is only for old cores lacking LLOCK/SCOND, which by defintion
@@ -60,23 +61,47 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 	/* Z indicates to userspace if operation succeded */
 	regs->status32 &= ~STATUS_Z_MASK;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
+	ret = access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr));
+	if (!ret)
+		 goto fail;
 
+again:
 	preempt_disable();
 
-	if (__get_user(uval, uaddr))
-		goto done;
+	ret = __get_user(uval, uaddr);
+	if (ret)
+		 goto fault;
 
-	if (uval == expected) {
-		if (!__put_user(new, uaddr))
-			regs->status32 |= STATUS_Z_MASK;
-	}
+	if (uval != expected)
+		 goto out;
 
-done:
-	preempt_enable();
+	ret = __put_user(new, uaddr);
+	if (ret)
+		 goto fault;
+
+	regs->status32 |= STATUS_Z_MASK;
 
+out:
+	preempt_enable();
 	return uval;
+
+fault:
+	preempt_enable();
+
+	if (unlikely(ret != -EFAULT))
+		 goto fail;
+
+	down_read(&current->mm->mmap_sem);
+	ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr,
+			       FAULT_FLAG_WRITE, NULL);
+	up_read(&current->mm->mmap_sem);
+
+	if (likely(!ret))
+		 goto again;
+
+fail:
+	force_sig(SIGSEGV, current);
+	return ret;
 }
 
 #ifdef CONFIG_ISA_ARCV2
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 9dbe645ee127..25c631942500 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -1038,7 +1038,7 @@ void flush_cache_mm(struct mm_struct *mm)
 void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr,
 		      unsigned long pfn)
 {
-	unsigned int paddr = pfn << PAGE_SHIFT;
+	phys_addr_t paddr = pfn << PAGE_SHIFT;
 
 	u_vaddr &= PAGE_MASK;
 
@@ -1058,8 +1058,9 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page,
 		     unsigned long u_vaddr)
 {
 	/* TBD: do we really need to clear the kernel mapping */
-	__flush_dcache_page(page_address(page), u_vaddr);
-	__flush_dcache_page(page_address(page), page_address(page));
+	__flush_dcache_page((phys_addr_t)page_address(page), u_vaddr);
+	__flush_dcache_page((phys_addr_t)page_address(page),
+			    (phys_addr_t)page_address(page));
 
 }
 
@@ -1246,6 +1247,16 @@ void __init arc_cache_init_master(void)
 		}
 	}
 
+	/*
+	 * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger
+	 * or equal to any cache line length.
+	 */
+	BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES,
+			 "SMP_CACHE_BYTES must be >= any cache line length");
+	if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES))
+		panic("L2 Cache line [%d] > kernel Config [%d]\n",
+		      l2_line_sz, SMP_CACHE_BYTES);
+
 	/* Note that SLC disable not formally supported till HS 3.0 */
 	if (is_isa_arcv2() && l2_line_sz && !slc_enable)
 		arc_slc_disable();
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 8c1071840979..ec47e6079f5d 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -129,14 +129,59 @@ int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 
+/*
+ * Cache operations depending on function and direction argument, inspired by
+ * https://lkml.org/lkml/2018/5/18/979
+ * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20]
+ * dma-mapping: provide a generic dma-noncoherent implementation)"
+ *
+ *          |   map          ==  for_device     |   unmap     ==  for_cpu
+ *          |----------------------------------------------------------------
+ * TO_DEV   |   writeback        writeback      |   none          none
+ * FROM_DEV |   invalidate       invalidate     |   invalidate*   invalidate*
+ * BIDIR    |   writeback+inv    writeback+inv  |   invalidate    invalidate
+ *
+ *     [*] needed for CPU speculative prefetches
+ *
+ * NOTE: we don't check the validity of direction argument as it is done in
+ * upper layer functions (in include/linux/dma-mapping.h)
+ */
+
 void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_wback(paddr, size);
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_wback(paddr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		dma_cache_inv(paddr, size);
+		break;
+
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
 }
 
 void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_inv(paddr, size);
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+
+	/* FROM_DEVICE invalidate needed if speculative CPU prefetch only */
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		dma_cache_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
 }
diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h
index 0c7d11022d0f..4f6a1673b3a6 100644
--- a/arch/arc/plat-eznps/include/plat/ctop.h
+++ b/arch/arc/plat-eznps/include/plat/ctop.h
@@ -21,6 +21,7 @@
 #error "Incorrect ctop.h include"
 #endif
 
+#include <linux/types.h>
 #include <soc/nps/common.h>
 
 /* core auxiliary registers */
@@ -143,6 +144,15 @@ struct nps_host_reg_gim_p_int_dst {
 };
 
 /* AUX registers definition */
+struct nps_host_reg_aux_dpc {
+	union {
+		struct {
+			u32 ien:1, men:1, hen:1, reserved:29;
+		};
+		u32 value;
+	};
+};
+
 struct nps_host_reg_aux_udmc {
 	union {
 		struct {
diff --git a/arch/arc/plat-eznps/mtm.c b/arch/arc/plat-eznps/mtm.c
index 2388de3d09ef..ed0077ef666e 100644
--- a/arch/arc/plat-eznps/mtm.c
+++ b/arch/arc/plat-eznps/mtm.c
@@ -15,6 +15,8 @@
  */
 
 #include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/log2.h>
 #include <asm/arcregs.h>
@@ -157,10 +159,10 @@ void mtm_enable_core(unsigned int cpu)
 /* Verify and set the value of the mtm hs counter */
 static int __init set_mtm_hs_ctr(char *ctr_str)
 {
-	long hs_ctr;
+	int hs_ctr;
 	int ret;
 
-	ret = kstrtol(ctr_str, 0, &hs_ctr);
+	ret = kstrtoint(ctr_str, 0, &hs_ctr);
 
 	if (ret || hs_ctr > MT_HS_CNT_MAX || hs_ctr < MT_HS_CNT_MIN) {
 		pr_err("** Invalid @nps_mtm_hs_ctr [%d] needs to be [%d:%d] (incl)\n",
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig
index 19ab3cf98f0f..9356753c2ed8 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -7,5 +7,8 @@
 
 menuconfig ARC_SOC_HSDK
 	bool "ARC HS Development Kit SOC"
+	depends on ISA_ARCV2
+	select ARC_HAS_ACCL_REGS
 	select CLK_HSDK
 	select RESET_HSDK
+	select MIGHT_HAVE_PCI
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index 2958aedb649a..2588b842407c 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -42,6 +42,66 @@ static void __init hsdk_init_per_cpu(unsigned int cpu)
 #define SDIO_UHS_REG_EXT	(SDIO_BASE + 0x108)
 #define SDIO_UHS_REG_EXT_DIV_2	(2 << 30)
 
+#define HSDK_GPIO_INTC          (ARC_PERIPHERAL_BASE + 0x3000)
+
+static void __init hsdk_enable_gpio_intc_wire(void)
+{
+	/*
+	 * Peripherals on CPU Card are wired to cpu intc via intermediate
+	 * DW APB GPIO blocks (mainly for debouncing)
+	 *
+	 *         ---------------------
+	 *        |  snps,archs-intc  |
+	 *        ---------------------
+	 *                  |
+	 *        ----------------------
+	 *        | snps,archs-idu-intc |
+	 *        ----------------------
+	 *         |   |     |   |    |
+	 *         | [eth] [USB]    [... other peripherals]
+	 *         |
+	 * -------------------
+	 * | snps,dw-apb-intc |
+	 * -------------------
+	 *  |      |   |   |
+	 * [Bt] [HAPS]   [... other peripherals]
+	 *
+	 * Current implementation of "irq-dw-apb-ictl" driver doesn't work well
+	 * with stacked INTCs. In particular problem happens if its master INTC
+	 * not yet instantiated. See discussion here -
+	 * https://lkml.org/lkml/2015/3/4/755
+	 *
+	 * So setup the first gpio block as a passive pass thru and hide it from
+	 * DT hardware topology - connect intc directly to cpu intc
+	 * The GPIO "wire" needs to be init nevertheless (here)
+	 *
+	 * One side adv is that peripheral interrupt handling avoids one nested
+	 * intc ISR hop
+	 *
+	 * According to HSDK User's Manual [1], "Table 2 Interrupt Mapping"
+	 * we have the following GPIO input lines used as sources of interrupt:
+	 * - GPIO[0] - Bluetooth interrupt of RS9113 module
+	 * - GPIO[2] - HAPS interrupt (on HapsTrak 3 connector)
+	 * - GPIO[3] - Audio codec (MAX9880A) interrupt
+	 * - GPIO[8-23] - Available on Arduino and PMOD_x headers
+	 * For now there's no use of Arduino and PMOD_x headers in Linux
+	 * use-case so we only enable lines 0, 2 and 3.
+	 *
+	 * [1] https://github.com/foss-for-synopsys-dwc-arc-processors/ARC-Development-Systems-Forum/wiki/docs/ARC_HSDK_User_Guide.pdf
+	 */
+#define GPIO_INTEN              (HSDK_GPIO_INTC + 0x30)
+#define GPIO_INTMASK            (HSDK_GPIO_INTC + 0x34)
+#define GPIO_INTTYPE_LEVEL      (HSDK_GPIO_INTC + 0x38)
+#define GPIO_INT_POLARITY       (HSDK_GPIO_INTC + 0x3c)
+#define GPIO_INT_CONNECTED_MASK	0x0d
+
+	iowrite32(0xffffffff, (void __iomem *) GPIO_INTMASK);
+	iowrite32(~GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTMASK);
+	iowrite32(0x00000000, (void __iomem *) GPIO_INTTYPE_LEVEL);
+	iowrite32(0xffffffff, (void __iomem *) GPIO_INT_POLARITY);
+	iowrite32(GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTEN);
+}
+
 static void __init hsdk_init_early(void)
 {
 	/*
@@ -62,6 +122,8 @@ static void __init hsdk_init_early(void)
 	 * minimum possible div-by-2.
 	 */
 	iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
+
+	hsdk_enable_gpio_intc_wire();
 }
 
 static const char *hsdk_compat[] __initconst = {
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 54eeb8d00bc6..0f328d639d51 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -9,6 +9,7 @@ config ARM
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_SET_MEMORY
@@ -337,8 +338,8 @@ config ARCH_MULTIPLATFORM
 	select TIMER_OF
 	select COMMON_CLK
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select MIGHT_HAVE_PCI
-	select MULTI_IRQ_HANDLER
 	select PCI_DOMAINS if PCI
 	select SPARSE_IRQ
 	select USE_OF
@@ -465,9 +466,9 @@ config ARCH_DOVE
 	bool "Marvell Dove"
 	select CPU_PJ4
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select MIGHT_HAVE_PCI
-	select MULTI_IRQ_HANDLER
 	select MVEBU_MBUS
 	select PINCTRL
 	select PINCTRL_DOVE
@@ -512,8 +513,8 @@ config ARCH_LPC32XX
 	select COMMON_CLK
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
-	select MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 	select USE_OF
 	help
@@ -532,11 +533,11 @@ config ARCH_PXA
 	select TIMER_OF
 	select CPU_XSCALE if !CPU_XSC3
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIO_PXA
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
 	select PLAT_PXA
 	select SPARSE_IRQ
 	help
@@ -572,11 +573,11 @@ config ARCH_SA1100
 	select CPU_FREQ
 	select CPU_SA1100
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
 	select ISA
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_MEMORY_H
 	select SPARSE_IRQ
 	help
@@ -590,10 +591,10 @@ config ARCH_S3C24XX
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
 	select GPIOLIB
+	select GENERIC_IRQ_MULTI_HANDLER
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_S3C_RTC if RTC_CLASS
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_IO_H
 	select SAMSUNG_ATAGS
 	select USE_OF
@@ -627,10 +628,10 @@ config ARCH_OMAP1
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_IO_H if PCCARD
 	select NEED_MACH_MEMORY_H
 	select SPARSE_IRQ
@@ -921,11 +922,6 @@ config IWMMXT
 	  Enable support for iWMMXt context switching at run time if
 	  running on a CPU that supports it.
 
-config MULTI_IRQ_HANDLER
-	bool
-	help
-	  Allow each machine to specify it's own IRQ handler at run time.
-
 if !MMU
 source "arch/arm/Kconfig-nommu"
 endif
@@ -1245,8 +1241,14 @@ config PCI
 	  VESA. If you have PCI, say Y, otherwise N.
 
 config PCI_DOMAINS
-	bool
+	bool "Support for multiple PCI domains"
 	depends on PCI
+	help
+	  Enable PCI domains kernel management. Say Y if your machine
+	  has a PCI bus hierarchy that requires more than one PCI
+	  domain (aka segment) to be correctly managed. Say N otherwise.
+
+	  If you don't know what to do here, say N.
 
 config PCI_DOMAINS_GENERIC
 	def_bool PCI_DOMAINS
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index fc26c3d7b9b6..62ebeae9f837 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -46,12 +46,12 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN),y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__ARMEB__
 AS		+= -EB
-LD		+= -EB
+LDFLAGS		+= -EB
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 CHECKFLAGS	+= -D__ARMEL__
 AS		+= -EL
-LD		+= -EL
+LDFLAGS		+= -EL
 endif
 
 #
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index f9e8667f5886..73b514dddf65 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -168,7 +168,6 @@
 			AM33XX_IOPAD(0x8f0, PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_dat3.mmc0_dat3 */
 			AM33XX_IOPAD(0x904, PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_cmd.mmc0_cmd */
 			AM33XX_IOPAD(0x900, PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_clk.mmc0_clk */
-			AM33XX_IOPAD(0x9a0, PIN_INPUT | MUX_MODE4)		/* mcasp0_aclkr.mmc0_sdwp */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/am3517.dtsi b/arch/arm/boot/dts/am3517.dtsi
index ca294914bbb1..23ea381d363f 100644
--- a/arch/arm/boot/dts/am3517.dtsi
+++ b/arch/arm/boot/dts/am3517.dtsi
@@ -39,6 +39,8 @@
 			ti,davinci-ctrl-ram-size = <0x2000>;
 			ti,davinci-rmii-en = /bits/ 8 <1>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
+			clocks = <&emac_ick>;
+			clock-names = "ick";
 		};
 
 		davinci_mdio: ethernet@5c030000 {
@@ -49,6 +51,8 @@
 			bus_freq = <1000000>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+			clocks = <&emac_fck>;
+			clock-names = "fck";
 		};
 
 		uart4: serial@4809e000 {
@@ -87,6 +91,11 @@
 	};
 };
 
+/* Table Table 5-79 of the TRM shows 480ab000 is reserved */
+&usb_otg_hs {
+	status = "disabled";
+};
+
 &iva {
 	status = "disabled";
 };
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index 440351ad0b80..d4be3fd0b6f4 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -610,6 +610,8 @@
 
 		touchscreen-size-x = <480>;
 		touchscreen-size-y = <272>;
+
+		wakeup-source;
 	};
 
 	tlv320aic3106: tlv320aic3106@1b {
diff --git a/arch/arm/boot/dts/armada-385-synology-ds116.dts b/arch/arm/boot/dts/armada-385-synology-ds116.dts
index 6782ce481ac9..d8769956cbfc 100644
--- a/arch/arm/boot/dts/armada-385-synology-ds116.dts
+++ b/arch/arm/boot/dts/armada-385-synology-ds116.dts
@@ -139,7 +139,7 @@
 					      3700 5
 					      3900 6
 					      4000 7>;
-			cooling-cells = <2>;
+			#cooling-cells = <2>;
 		};
 
 		gpio-leds {
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 18edc9bc7927..929459c42760 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -547,7 +547,7 @@
 
 			thermal: thermal@e8078 {
 				compatible = "marvell,armada380-thermal";
-				reg = <0xe4078 0x4>, <0xe4074 0x4>;
+				reg = <0xe4078 0x4>, <0xe4070 0x8>;
 				status = "okay";
 			};
 
diff --git a/arch/arm/boot/dts/bcm-cygnus.dtsi b/arch/arm/boot/dts/bcm-cygnus.dtsi
index 9fe4f5a6379e..2c4df2d2d4a6 100644
--- a/arch/arm/boot/dts/bcm-cygnus.dtsi
+++ b/arch/arm/boot/dts/bcm-cygnus.dtsi
@@ -216,7 +216,7 @@
 			reg = <0x18008000 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 85 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
@@ -245,7 +245,7 @@
 			reg = <0x1800b000 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 86 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
@@ -256,7 +256,7 @@
 
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &gic GIC_SPI 100 IRQ_TYPE_NONE>;
+			interrupt-map = <0 0 0 0 &gic GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
 
 			linux,pci-domain = <0>;
 
@@ -278,10 +278,10 @@
 				compatible = "brcm,iproc-msi";
 				msi-controller;
 				interrupt-parent = <&gic>;
-				interrupts = <GIC_SPI 96 IRQ_TYPE_NONE>,
-					     <GIC_SPI 97 IRQ_TYPE_NONE>,
-					     <GIC_SPI 98 IRQ_TYPE_NONE>,
-					     <GIC_SPI 99 IRQ_TYPE_NONE>;
+				interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
 
@@ -291,7 +291,7 @@
 
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &gic GIC_SPI 106 IRQ_TYPE_NONE>;
+			interrupt-map = <0 0 0 0 &gic GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
 
 			linux,pci-domain = <1>;
 
@@ -313,10 +313,10 @@
 				compatible = "brcm,iproc-msi";
 				msi-controller;
 				interrupt-parent = <&gic>;
-				interrupts = <GIC_SPI 102 IRQ_TYPE_NONE>,
-					     <GIC_SPI 103 IRQ_TYPE_NONE>,
-					     <GIC_SPI 104 IRQ_TYPE_NONE>,
-					     <GIC_SPI 105 IRQ_TYPE_NONE>;
+				interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/bcm-hr2.dtsi b/arch/arm/boot/dts/bcm-hr2.dtsi
index 3f9cedd8011f..3084a7c95733 100644
--- a/arch/arm/boot/dts/bcm-hr2.dtsi
+++ b/arch/arm/boot/dts/bcm-hr2.dtsi
@@ -264,7 +264,7 @@
 			reg = <0x38000 0x50>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 95 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 		};
 
@@ -279,7 +279,7 @@
 			reg = <0x3b000 0x50>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 96 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 		};
 	};
@@ -300,7 +300,7 @@
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &gic GIC_SPI 186 IRQ_TYPE_NONE>;
+		interrupt-map = <0 0 0 0 &gic GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
 
 		linux,pci-domain = <0>;
 
@@ -322,10 +322,10 @@
 			compatible = "brcm,iproc-msi";
 			msi-controller;
 			interrupt-parent = <&gic>;
-			interrupts = <GIC_SPI 182 IRQ_TYPE_NONE>,
-				     <GIC_SPI 183 IRQ_TYPE_NONE>,
-				     <GIC_SPI 184 IRQ_TYPE_NONE>,
-				     <GIC_SPI 185 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 185 IRQ_TYPE_LEVEL_HIGH>;
 			brcm,pcie-msi-inten;
 		};
 	};
@@ -336,7 +336,7 @@
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &gic GIC_SPI 192 IRQ_TYPE_NONE>;
+		interrupt-map = <0 0 0 0 &gic GIC_SPI 192 IRQ_TYPE_LEVEL_HIGH>;
 
 		linux,pci-domain = <1>;
 
@@ -358,10 +358,10 @@
 			compatible = "brcm,iproc-msi";
 			msi-controller;
 			interrupt-parent = <&gic>;
-			interrupts = <GIC_SPI 188 IRQ_TYPE_NONE>,
-				     <GIC_SPI 189 IRQ_TYPE_NONE>,
-				     <GIC_SPI 190 IRQ_TYPE_NONE>,
-				     <GIC_SPI 191 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>;
 			brcm,pcie-msi-inten;
 		};
 	};
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index dcc55aa84583..09ba85046322 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -391,7 +391,7 @@
 			reg = <0x38000 0x50>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 89 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 			dma-coherent;
 			status = "disabled";
@@ -496,7 +496,7 @@
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &gic GIC_SPI 131 IRQ_TYPE_NONE>;
+		interrupt-map = <0 0 0 0 &gic GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
 
 		linux,pci-domain = <0>;
 
@@ -519,10 +519,10 @@
 			compatible = "brcm,iproc-msi";
 			msi-controller;
 			interrupt-parent = <&gic>;
-			interrupts = <GIC_SPI 127 IRQ_TYPE_NONE>,
-				     <GIC_SPI 128 IRQ_TYPE_NONE>,
-				     <GIC_SPI 129 IRQ_TYPE_NONE>,
-				     <GIC_SPI 130 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
 			brcm,pcie-msi-inten;
 		};
 	};
@@ -533,7 +533,7 @@
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &gic GIC_SPI 137 IRQ_TYPE_NONE>;
+		interrupt-map = <0 0 0 0 &gic GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>;
 
 		linux,pci-domain = <1>;
 
@@ -556,10 +556,10 @@
 			compatible = "brcm,iproc-msi";
 			msi-controller;
 			interrupt-parent = <&gic>;
-			interrupts = <GIC_SPI 133 IRQ_TYPE_NONE>,
-				     <GIC_SPI 134 IRQ_TYPE_NONE>,
-				     <GIC_SPI 135 IRQ_TYPE_NONE>,
-				     <GIC_SPI 136 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>;
 			brcm,pcie-msi-inten;
 		};
 	};
@@ -570,7 +570,7 @@
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &gic GIC_SPI 143 IRQ_TYPE_NONE>;
+		interrupt-map = <0 0 0 0 &gic GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
 
 		linux,pci-domain = <2>;
 
@@ -593,10 +593,10 @@
 			compatible = "brcm,iproc-msi";
 			msi-controller;
 			interrupt-parent = <&gic>;
-			interrupts = <GIC_SPI 139 IRQ_TYPE_NONE>,
-				     <GIC_SPI 140 IRQ_TYPE_NONE>,
-				     <GIC_SPI 141 IRQ_TYPE_NONE>,
-				     <GIC_SPI 142 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>;
 			brcm,pcie-msi-inten;
 		};
 	};
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 9a076c409f4e..ef995e50ee12 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -365,7 +365,7 @@
 	i2c0: i2c@18009000 {
 		compatible = "brcm,iproc-i2c";
 		reg = <0x18009000 0x50>;
-		interrupts = <GIC_SPI 121 IRQ_TYPE_NONE>;
+		interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clock-frequency = <100000>;
diff --git a/arch/arm/boot/dts/da850.dtsi b/arch/arm/boot/dts/da850.dtsi
index f6f1597b03df..0f4f817a9e22 100644
--- a/arch/arm/boot/dts/da850.dtsi
+++ b/arch/arm/boot/dts/da850.dtsi
@@ -549,11 +549,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			reg = <0x226000 0x1000>;
-			interrupts = <42 IRQ_TYPE_EDGE_BOTH
-				43 IRQ_TYPE_EDGE_BOTH 44 IRQ_TYPE_EDGE_BOTH
-				45 IRQ_TYPE_EDGE_BOTH 46 IRQ_TYPE_EDGE_BOTH
-				47 IRQ_TYPE_EDGE_BOTH 48 IRQ_TYPE_EDGE_BOTH
-				49 IRQ_TYPE_EDGE_BOTH 50 IRQ_TYPE_EDGE_BOTH>;
+			interrupts = <42 43 44 45 46 47 48 49 50>;
 			ti,ngpio = <144>;
 			ti,davinci-gpio-unbanked = <0>;
 			status = "disabled";
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 9dcd14edc202..e03495a799ce 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1580,7 +1580,6 @@
 				dr_mode = "otg";
 				snps,dis_u3_susphy_quirk;
 				snps,dis_u2_susphy_quirk;
-				snps,dis_metastability_quirk;
 			};
 		};
 
@@ -1608,6 +1607,7 @@
 				dr_mode = "otg";
 				snps,dis_u3_susphy_quirk;
 				snps,dis_u2_susphy_quirk;
+				snps,dis_metastability_quirk;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/imx51-zii-rdu1.dts b/arch/arm/boot/dts/imx51-zii-rdu1.dts
index df9eca94d812..8a878687197b 100644
--- a/arch/arm/boot/dts/imx51-zii-rdu1.dts
+++ b/arch/arm/boot/dts/imx51-zii-rdu1.dts
@@ -770,7 +770,7 @@
 
 	pinctrl_ts: tsgrp {
 		fsl,pins = <
-			MX51_PAD_CSI1_D8__GPIO3_12		0x85
+			MX51_PAD_CSI1_D8__GPIO3_12		0x04
 			MX51_PAD_CSI1_D9__GPIO3_13		0x85
 		>;
 	};
diff --git a/arch/arm/boot/dts/imx6q.dtsi b/arch/arm/boot/dts/imx6q.dtsi
index 70483ce72ba6..77f8f030dd07 100644
--- a/arch/arm/boot/dts/imx6q.dtsi
+++ b/arch/arm/boot/dts/imx6q.dtsi
@@ -90,7 +90,7 @@
 					clocks = <&clks IMX6Q_CLK_ECSPI5>,
 						 <&clks IMX6Q_CLK_ECSPI5>;
 					clock-names = "ipg", "per";
-					dmas = <&sdma 11 7 1>, <&sdma 12 7 2>;
+					dmas = <&sdma 11 8 1>, <&sdma 12 8 2>;
 					dma-names = "rx", "tx";
 					status = "disabled";
 				};
diff --git a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
index 19a075aee19e..f14df0baf2ab 100644
--- a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
@@ -692,7 +692,7 @@
 			dsa,member = <0 0>;
 			eeprom-length = <512>;
 			interrupt-parent = <&gpio6>;
-			interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
+			interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index d8b94f47498b..4e4a55aad5c9 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -1344,7 +1344,7 @@
 			ranges = <0x81000000 0 0          0x08f80000 0 0x00010000 /* downstream I/O */
 				  0x82000000 0 0x08000000 0x08000000 0 0x00f00000>; /* non-prefetchable memory */
 			num-lanes = <1>;
-			interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts
index bdf73cbcec3a..e7c3c563ff8f 100644
--- a/arch/arm/boot/dts/omap4-droid4-xt894.dts
+++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts
@@ -159,13 +159,7 @@
 
 		dais = <&mcbsp2_port>, <&mcbsp3_port>;
 	};
-};
-
-&dss {
-	status = "okay";
-};
 
-&gpio6 {
 	pwm8: dmtimer-pwm-8 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&vibrator_direction_pin>;
@@ -192,7 +186,10 @@
 		pwm-names = "enable", "direction";
 		direction-duty-cycle-ns = <10000000>;
 	};
+};
 
+&dss {
+	status = "okay";
 };
 
 &dsi1 {
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index 486d4e7433ed..b38f8c240558 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -748,13 +748,13 @@
 		nand0: nand@ff900000 {
 			#address-cells = <0x1>;
 			#size-cells = <0x1>;
-			compatible = "denali,denali-nand-dt";
+			compatible = "altr,socfpga-denali-nand";
 			reg = <0xff900000 0x100000>,
 			      <0xffb80000 0x10000>;
 			reg-names = "nand_data", "denali_reg";
 			interrupts = <0x0 0x90 0x4>;
 			dma-mask = <0xffffffff>;
-			clocks = <&nand_clk>;
+			clocks = <&nand_x_clk>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index bead79e4b2aa..791ca15c799e 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -593,8 +593,7 @@
 			#size-cells = <0>;
 			reg = <0xffda5000 0x100>;
 			interrupts = <0 102 4>;
-			num-chipselect = <4>;
-			bus-num = <0>;
+			num-cs = <4>;
 			/*32bit_access;*/
 			tx-dma-channel = <&pdma 16>;
 			rx-dma-channel = <&pdma 17>;
@@ -633,7 +632,7 @@
 		nand: nand@ffb90000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
-			compatible = "denali,denali-nand-dt", "altr,socfpga-denali-nand";
+			compatible = "altr,socfpga-denali-nand";
 			reg = <0xffb90000 0x72000>,
 			      <0xffb80000 0x10000>;
 			reg-names = "nand_data", "denali_reg";
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 1e9f7af8f70f..3157be413297 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_DMABOUNCE)		+= dmabounce.o
 obj-$(CONFIG_SHARP_LOCOMO)	+= locomo.o
 obj-$(CONFIG_SHARP_PARAM)	+= sharpsl_param.o
 obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
-obj-$(CONFIG_SMP)		+= secure_cntvoff.o
+obj-$(CONFIG_CPU_V7)		+= secure_cntvoff.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
 obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
 CFLAGS_REMOVE_mcpm_entry.o	= -pg
diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig
index 054591dc9a00..4cd2f4a2bff4 100644
--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -141,9 +141,11 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_UDC=y
 CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_CHIPIDEA_ULPI=y
 CONFIG_NOP_USB_XCEIV=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_ETH=m
+CONFIG_USB_ULPI_BUS=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index f70507ab91ee..200ebda47e0c 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -302,6 +302,7 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_UDC=y
 CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_CHIPIDEA_ULPI=y
 CONFIG_USB_SERIAL=m
 CONFIG_USB_SERIAL_GENERIC=y
 CONFIG_USB_SERIAL_FTDI_SIO=m
@@ -338,6 +339,7 @@ CONFIG_USB_GADGETFS=m
 CONFIG_USB_FUNCTIONFS=m
 CONFIG_USB_MASS_STORAGE=m
 CONFIG_USB_G_SERIAL=m
+CONFIG_USB_ULPI_BUS=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 7e1c543162c3..8f6be1982545 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -1,5 +1,4 @@
 CONFIG_SYSVIPC=y
-CONFIG_FHANDLE=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_CGROUPS=y
@@ -10,20 +9,10 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_CMDLINE_PARTITION=y
-CONFIG_ARCH_MULTI_V7=y
-# CONFIG_ARCH_MULTI_V5 is not set
-# CONFIG_ARCH_MULTI_V4 is not set
 CONFIG_ARCH_VIRT=y
 CONFIG_ARCH_ALPINE=y
 CONFIG_ARCH_ARTPEC=y
 CONFIG_MACH_ARTPEC6=y
-CONFIG_ARCH_MVEBU=y
-CONFIG_MACH_ARMADA_370=y
-CONFIG_MACH_ARMADA_375=y
-CONFIG_MACH_ARMADA_38X=y
-CONFIG_MACH_ARMADA_39X=y
-CONFIG_MACH_ARMADA_XP=y
-CONFIG_MACH_DOVE=y
 CONFIG_ARCH_AT91=y
 CONFIG_SOC_SAMA5D2=y
 CONFIG_SOC_SAMA5D3=y
@@ -32,9 +21,9 @@ CONFIG_ARCH_BCM=y
 CONFIG_ARCH_BCM_CYGNUS=y
 CONFIG_ARCH_BCM_HR2=y
 CONFIG_ARCH_BCM_NSP=y
-CONFIG_ARCH_BCM_21664=y
-CONFIG_ARCH_BCM_281XX=y
 CONFIG_ARCH_BCM_5301X=y
+CONFIG_ARCH_BCM_281XX=y
+CONFIG_ARCH_BCM_21664=y
 CONFIG_ARCH_BCM2835=y
 CONFIG_ARCH_BCM_63XX=y
 CONFIG_ARCH_BRCMSTB=y
@@ -43,14 +32,14 @@ CONFIG_MACH_BERLIN_BG2=y
 CONFIG_MACH_BERLIN_BG2CD=y
 CONFIG_MACH_BERLIN_BG2Q=y
 CONFIG_ARCH_DIGICOLOR=y
+CONFIG_ARCH_EXYNOS=y
+CONFIG_EXYNOS5420_MCPM=y
 CONFIG_ARCH_HIGHBANK=y
 CONFIG_ARCH_HISI=y
 CONFIG_ARCH_HI3xxx=y
-CONFIG_ARCH_HIX5HD2=y
 CONFIG_ARCH_HIP01=y
 CONFIG_ARCH_HIP04=y
-CONFIG_ARCH_KEYSTONE=y
-CONFIG_ARCH_MESON=y
+CONFIG_ARCH_HIX5HD2=y
 CONFIG_ARCH_MXC=y
 CONFIG_SOC_IMX50=y
 CONFIG_SOC_IMX51=y
@@ -60,29 +49,30 @@ CONFIG_SOC_IMX6SL=y
 CONFIG_SOC_IMX6SX=y
 CONFIG_SOC_IMX6UL=y
 CONFIG_SOC_IMX7D=y
-CONFIG_SOC_VF610=y
 CONFIG_SOC_LS1021A=y
+CONFIG_SOC_VF610=y
+CONFIG_ARCH_KEYSTONE=y
+CONFIG_ARCH_MEDIATEK=y
+CONFIG_ARCH_MESON=y
+CONFIG_ARCH_MVEBU=y
+CONFIG_MACH_ARMADA_370=y
+CONFIG_MACH_ARMADA_375=y
+CONFIG_MACH_ARMADA_38X=y
+CONFIG_MACH_ARMADA_39X=y
+CONFIG_MACH_ARMADA_XP=y
+CONFIG_MACH_DOVE=y
 CONFIG_ARCH_OMAP3=y
 CONFIG_ARCH_OMAP4=y
 CONFIG_SOC_OMAP5=y
 CONFIG_SOC_AM33XX=y
 CONFIG_SOC_AM43XX=y
 CONFIG_SOC_DRA7XX=y
+CONFIG_ARCH_SIRF=y
 CONFIG_ARCH_QCOM=y
-CONFIG_ARCH_MEDIATEK=y
 CONFIG_ARCH_MSM8X60=y
 CONFIG_ARCH_MSM8960=y
 CONFIG_ARCH_MSM8974=y
 CONFIG_ARCH_ROCKCHIP=y
-CONFIG_ARCH_SOCFPGA=y
-CONFIG_PLAT_SPEAR=y
-CONFIG_ARCH_SPEAR13XX=y
-CONFIG_MACH_SPEAR1310=y
-CONFIG_MACH_SPEAR1340=y
-CONFIG_ARCH_STI=y
-CONFIG_ARCH_STM32=y
-CONFIG_ARCH_EXYNOS=y
-CONFIG_EXYNOS5420_MCPM=y
 CONFIG_ARCH_RENESAS=y
 CONFIG_ARCH_EMEV2=y
 CONFIG_ARCH_R7S72100=y
@@ -99,40 +89,33 @@ CONFIG_ARCH_R8A7792=y
 CONFIG_ARCH_R8A7793=y
 CONFIG_ARCH_R8A7794=y
 CONFIG_ARCH_SH73A0=y
+CONFIG_ARCH_SOCFPGA=y
+CONFIG_PLAT_SPEAR=y
+CONFIG_ARCH_SPEAR13XX=y
+CONFIG_MACH_SPEAR1310=y
+CONFIG_MACH_SPEAR1340=y
+CONFIG_ARCH_STI=y
+CONFIG_ARCH_STM32=y
 CONFIG_ARCH_SUNXI=y
-CONFIG_ARCH_SIRF=y
 CONFIG_ARCH_TEGRA=y
-CONFIG_ARCH_TEGRA_2x_SOC=y
-CONFIG_ARCH_TEGRA_3x_SOC=y
-CONFIG_ARCH_TEGRA_114_SOC=y
-CONFIG_ARCH_TEGRA_124_SOC=y
 CONFIG_ARCH_UNIPHIER=y
 CONFIG_ARCH_U8500=y
-CONFIG_MACH_HREFV60=y
-CONFIG_MACH_SNOWBALL=y
 CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_VEXPRESS_TC2_PM=y
 CONFIG_ARCH_WM8850=y
 CONFIG_ARCH_ZYNQ=y
-CONFIG_TRUSTED_FOUNDATIONS=y
-CONFIG_PCI=y
-CONFIG_PCI_HOST_GENERIC=y
-CONFIG_PCI_DRA7XX=y
-CONFIG_PCI_DRA7XX_EP=y
-CONFIG_PCI_KEYSTONE=y
-CONFIG_PCI_MSI=y
+CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_MVEBU=y
 CONFIG_PCI_TEGRA=y
 CONFIG_PCI_RCAR_GEN2=y
 CONFIG_PCIE_RCAR=y
-CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_DRA7XX_EP=y
+CONFIG_PCI_KEYSTONE=y
 CONFIG_PCI_ENDPOINT=y
 CONFIG_PCI_ENDPOINT_CONFIGFS=y
 CONFIG_PCI_EPF_TEST=m
 CONFIG_SMP=y
 CONFIG_NR_CPUS=16
-CONFIG_HIGHPTE=y
-CONFIG_CMA=y
 CONFIG_SECCOMP=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
@@ -145,14 +128,14 @@ CONFIG_CPU_FREQ_GOV_POWERSAVE=m
 CONFIG_CPU_FREQ_GOV_USERSPACE=m
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
 CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
+CONFIG_CPUFREQ_DT=y
 CONFIG_ARM_IMX6Q_CPUFREQ=y
 CONFIG_QORIQ_CPUFREQ=y
 CONFIG_CPU_IDLE=y
 CONFIG_ARM_CPUIDLE=y
-CONFIG_NEON=y
-CONFIG_KERNEL_MODE_NEON=y
 CONFIG_ARM_ZYNQ_CPUIDLE=y
 CONFIG_ARM_EXYNOS_CPUIDLE=y
+CONFIG_KERNEL_MODE_NEON=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -170,23 +153,13 @@ CONFIG_IPV6_MIP6=m
 CONFIG_IPV6_TUNNEL=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_NET_DSA=m
-CONFIG_NET_SWITCHDEV=y
 CONFIG_CAN=y
-CONFIG_CAN_RAW=y
-CONFIG_CAN_BCM=y
-CONFIG_CAN_DEV=y
 CONFIG_CAN_AT91=m
 CONFIG_CAN_FLEXCAN=m
-CONFIG_CAN_RCAR=m
+CONFIG_CAN_SUN4I=y
 CONFIG_CAN_XILINXCAN=y
+CONFIG_CAN_RCAR=m
 CONFIG_CAN_MCP251X=y
-CONFIG_NET_DSA_BCM_SF2=m
-CONFIG_B53=m
-CONFIG_B53_SPI_DRIVER=m
-CONFIG_B53_MDIO_DRIVER=m
-CONFIG_B53_MMAP_DRIVER=m
-CONFIG_B53_SRAB_DRIVER=m
-CONFIG_CAN_SUN4I=y
 CONFIG_BT=m
 CONFIG_BT_HCIUART=m
 CONFIG_BT_HCIUART_BCM=y
@@ -199,11 +172,9 @@ CONFIG_RFKILL_INPUT=y
 CONFIG_RFKILL_GPIO=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=64
 CONFIG_OMAP_OCP2SCP=y
 CONFIG_SIMPLE_PM_BUS=y
-CONFIG_SUNXI_RSB=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
@@ -236,7 +207,6 @@ CONFIG_PCI_ENDPOINT_TEST=m
 CONFIG_EEPROM_AT24=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=y
-CONFIG_SCSI_MULTI_LUN=y
 CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
 CONFIG_SATA_AHCI_PLATFORM=y
@@ -251,14 +221,20 @@ CONFIG_SATA_MV=y
 CONFIG_SATA_RCAR=y
 CONFIG_NETDEVICES=y
 CONFIG_VIRTIO_NET=y
-CONFIG_HIX5HD2_GMAC=y
+CONFIG_B53_SPI_DRIVER=m
+CONFIG_B53_MDIO_DRIVER=m
+CONFIG_B53_MMAP_DRIVER=m
+CONFIG_B53_SRAB_DRIVER=m
+CONFIG_NET_DSA_BCM_SF2=m
 CONFIG_SUN4I_EMAC=y
-CONFIG_MACB=y
 CONFIG_BCMGENET=m
 CONFIG_BGMAC_BCMA=y
 CONFIG_SYSTEMPORT=m
+CONFIG_MACB=y
 CONFIG_NET_CALXEDA_XGMAC=y
 CONFIG_GIANFAR=y
+CONFIG_HIX5HD2_GMAC=y
+CONFIG_E1000E=y
 CONFIG_IGB=y
 CONFIG_MV643XX_ETH=y
 CONFIG_MVNETA=y
@@ -268,19 +244,17 @@ CONFIG_R8169=y
 CONFIG_SH_ETH=y
 CONFIG_SMSC911X=y
 CONFIG_STMMAC_ETH=y
-CONFIG_STMMAC_PLATFORM=y
 CONFIG_DWMAC_DWC_QOS_ETH=y
 CONFIG_TI_CPSW=y
 CONFIG_XILINX_EMACLITE=y
 CONFIG_AT803X_PHY=y
-CONFIG_MARVELL_PHY=y
-CONFIG_SMSC_PHY=y
 CONFIG_BROADCOM_PHY=y
 CONFIG_ICPLUS_PHY=y
-CONFIG_REALTEK_PHY=y
+CONFIG_MARVELL_PHY=y
 CONFIG_MICREL_PHY=y
-CONFIG_FIXED_PHY=y
+CONFIG_REALTEK_PHY=y
 CONFIG_ROCKCHIP_PHY=y
+CONFIG_SMSC_PHY=y
 CONFIG_USB_PEGASUS=y
 CONFIG_USB_RTL8152=m
 CONFIG_USB_LAN78XX=m
@@ -288,29 +262,29 @@ CONFIG_USB_USBNET=y
 CONFIG_USB_NET_SMSC75XX=y
 CONFIG_USB_NET_SMSC95XX=y
 CONFIG_BRCMFMAC=m
-CONFIG_RT2X00=m
-CONFIG_RT2800USB=m
 CONFIG_MWIFIEX=m
 CONFIG_MWIFIEX_SDIO=m
+CONFIG_RT2X00=m
+CONFIG_RT2800USB=m
 CONFIG_INPUT_JOYDEV=y
 CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_QT1070=m
 CONFIG_KEYBOARD_GPIO=y
 CONFIG_KEYBOARD_TEGRA=y
-CONFIG_KEYBOARD_SPEAR=y
+CONFIG_KEYBOARD_SAMSUNG=m
 CONFIG_KEYBOARD_ST_KEYSCAN=y
+CONFIG_KEYBOARD_SPEAR=y
 CONFIG_KEYBOARD_CROS_EC=m
-CONFIG_KEYBOARD_SAMSUNG=m
 CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_MOUSE_CYAPA=m
 CONFIG_MOUSE_ELAN_I2C=y
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_TOUCHSCREEN_ATMEL_MXT=m
 CONFIG_TOUCHSCREEN_MMS114=m
+CONFIG_TOUCHSCREEN_WM97XX=m
 CONFIG_TOUCHSCREEN_ST1232=m
 CONFIG_TOUCHSCREEN_STMPE=y
 CONFIG_TOUCHSCREEN_SUN4I=y
-CONFIG_TOUCHSCREEN_WM97XX=m
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_MAX77693_HAPTIC=m
 CONFIG_INPUT_MAX8997_HAPTIC=m
@@ -327,13 +301,12 @@ CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_8250_EM=y
 CONFIG_SERIAL_8250_MT6577=y
 CONFIG_SERIAL_8250_UNIPHIER=y
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_SERIAL_ATMEL=y
 CONFIG_SERIAL_ATMEL_CONSOLE=y
 CONFIG_SERIAL_ATMEL_TTYAT=y
-CONFIG_SERIAL_BCM63XX=y
-CONFIG_SERIAL_BCM63XX_CONSOLE=y
 CONFIG_SERIAL_MESON=y
 CONFIG_SERIAL_MESON_CONSOLE=y
 CONFIG_SERIAL_SAMSUNG=y
@@ -345,15 +318,14 @@ CONFIG_SERIAL_IMX=y
 CONFIG_SERIAL_IMX_CONSOLE=y
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=20
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
-CONFIG_SERIAL_SH_SCI_DMA=y
 CONFIG_SERIAL_MSM=y
 CONFIG_SERIAL_MSM_CONSOLE=y
 CONFIG_SERIAL_VT8500=y
 CONFIG_SERIAL_VT8500_CONSOLE=y
-CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_OMAP=y
 CONFIG_SERIAL_OMAP_CONSOLE=y
+CONFIG_SERIAL_BCM63XX=y
+CONFIG_SERIAL_BCM63XX_CONSOLE=y
 CONFIG_SERIAL_XILINX_PS_UART=y
 CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
 CONFIG_SERIAL_FSL_LPUART=y
@@ -365,12 +337,10 @@ CONFIG_SERIAL_ST_ASC_CONSOLE=y
 CONFIG_SERIAL_STM32=y
 CONFIG_SERIAL_STM32_CONSOLE=y
 CONFIG_SERIAL_DEV_BUS=y
-CONFIG_HVC_DRIVER=y
 CONFIG_VIRTIO_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_ST=y
 CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_DAVINCI=y
-CONFIG_I2C_MESON=y
-CONFIG_I2C_MUX=y
 CONFIG_I2C_ARB_GPIO_CHALLENGE=m
 CONFIG_I2C_MUX_PCA954x=y
 CONFIG_I2C_MUX_PINCTRL=y
@@ -378,12 +348,13 @@ CONFIG_I2C_DEMUX_PINCTRL=y
 CONFIG_I2C_AT91=m
 CONFIG_I2C_BCM2835=y
 CONFIG_I2C_CADENCE=y
+CONFIG_I2C_DAVINCI=y
 CONFIG_I2C_DESIGNWARE_PLATFORM=y
 CONFIG_I2C_DIGICOLOR=m
 CONFIG_I2C_EMEV2=m
 CONFIG_I2C_GPIO=m
-CONFIG_I2C_EXYNOS5=y
 CONFIG_I2C_IMX=y
+CONFIG_I2C_MESON=y
 CONFIG_I2C_MV64XXX=y
 CONFIG_I2C_RIIC=y
 CONFIG_I2C_RK3X=y
@@ -427,7 +398,6 @@ CONFIG_SPI_SPIDEV=y
 CONFIG_SPMI=y
 CONFIG_PINCTRL_AS3722=y
 CONFIG_PINCTRL_PALMAS=y
-CONFIG_PINCTRL_BCM2835=y
 CONFIG_PINCTRL_APQ8064=y
 CONFIG_PINCTRL_APQ8084=y
 CONFIG_PINCTRL_IPQ8064=y
@@ -437,25 +407,33 @@ CONFIG_PINCTRL_MSM8X74=y
 CONFIG_PINCTRL_MSM8916=y
 CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
 CONFIG_PINCTRL_QCOM_SSBI_PMIC=y
-CONFIG_GPIO_GENERIC_PLATFORM=y
 CONFIG_GPIO_DAVINCI=y
 CONFIG_GPIO_DWAPB=y
 CONFIG_GPIO_EM=y
 CONFIG_GPIO_RCAR=y
+CONFIG_GPIO_SYSCON=y
 CONFIG_GPIO_UNIPHIER=y
 CONFIG_GPIO_XILINX=y
 CONFIG_GPIO_ZYNQ=y
 CONFIG_GPIO_PCA953X=y
 CONFIG_GPIO_PCA953X_IRQ=y
 CONFIG_GPIO_PCF857X=y
-CONFIG_GPIO_TWL4030=y
 CONFIG_GPIO_PALMAS=y
-CONFIG_GPIO_SYSCON=y
 CONFIG_GPIO_TPS6586X=y
 CONFIG_GPIO_TPS65910=y
+CONFIG_GPIO_TWL4030=y
+CONFIG_POWER_AVS=y
+CONFIG_ROCKCHIP_IODOMAIN=y
+CONFIG_POWER_RESET_AS3722=y
+CONFIG_POWER_RESET_GPIO=y
+CONFIG_POWER_RESET_GPIO_RESTART=y
+CONFIG_POWER_RESET_ST=y
+CONFIG_POWER_RESET_KEYSTONE=y
+CONFIG_POWER_RESET_RMOBILE=y
 CONFIG_BATTERY_ACT8945A=y
 CONFIG_BATTERY_CPCAP=m
 CONFIG_BATTERY_SBS=y
+CONFIG_AXP20X_POWER=m
 CONFIG_BATTERY_MAX17040=m
 CONFIG_BATTERY_MAX17042=m
 CONFIG_CHARGER_CPCAP=m
@@ -464,15 +442,6 @@ CONFIG_CHARGER_MAX77693=m
 CONFIG_CHARGER_MAX8997=m
 CONFIG_CHARGER_MAX8998=m
 CONFIG_CHARGER_TPS65090=y
-CONFIG_AXP20X_POWER=m
-CONFIG_POWER_RESET_AS3722=y
-CONFIG_POWER_RESET_GPIO=y
-CONFIG_POWER_RESET_GPIO_RESTART=y
-CONFIG_POWER_RESET_KEYSTONE=y
-CONFIG_POWER_RESET_RMOBILE=y
-CONFIG_POWER_RESET_ST=y
-CONFIG_POWER_AVS=y
-CONFIG_ROCKCHIP_IODOMAIN=y
 CONFIG_SENSORS_IIO_HWMON=y
 CONFIG_SENSORS_LM90=y
 CONFIG_SENSORS_LM95245=y
@@ -480,14 +449,12 @@ CONFIG_SENSORS_NTC_THERMISTOR=m
 CONFIG_SENSORS_PWM_FAN=m
 CONFIG_SENSORS_INA2XX=m
 CONFIG_CPU_THERMAL=y
-CONFIG_BCM2835_THERMAL=m
-CONFIG_BRCMSTB_THERMAL=m
 CONFIG_IMX_THERMAL=y
 CONFIG_ROCKCHIP_THERMAL=y
 CONFIG_RCAR_THERMAL=y
 CONFIG_ARMADA_THERMAL=y
-CONFIG_DAVINCI_WATCHDOG=m
-CONFIG_EXYNOS_THERMAL=m
+CONFIG_BCM2835_THERMAL=m
+CONFIG_BRCMSTB_THERMAL=m
 CONFIG_ST_THERMAL_MEMMAP=y
 CONFIG_WATCHDOG=y
 CONFIG_DA9063_WATCHDOG=m
@@ -495,20 +462,24 @@ CONFIG_XILINX_WATCHDOG=y
 CONFIG_ARM_SP805_WATCHDOG=y
 CONFIG_AT91SAM9X_WATCHDOG=y
 CONFIG_SAMA5D4_WATCHDOG=y
+CONFIG_DW_WATCHDOG=y
+CONFIG_DAVINCI_WATCHDOG=m
 CONFIG_ORION_WATCHDOG=y
 CONFIG_RN5T618_WATCHDOG=y
-CONFIG_ST_LPC_WATCHDOG=y
 CONFIG_SUNXI_WATCHDOG=y
 CONFIG_IMX2_WDT=y
+CONFIG_ST_LPC_WATCHDOG=y
 CONFIG_TEGRA_WATCHDOG=m
 CONFIG_MESON_WATCHDOG=y
-CONFIG_DW_WATCHDOG=y
 CONFIG_DIGICOLOR_WATCHDOG=y
 CONFIG_RENESAS_WDT=m
-CONFIG_BCM2835_WDT=y
 CONFIG_BCM47XX_WDT=y
-CONFIG_BCM7038_WDT=m
+CONFIG_BCM2835_WDT=y
 CONFIG_BCM_KONA_WDT=y
+CONFIG_BCM7038_WDT=m
+CONFIG_BCMA_HOST_SOC=y
+CONFIG_BCMA_DRIVER_GMAC_CMN=y
+CONFIG_BCMA_DRIVER_GPIO=y
 CONFIG_MFD_ACT8945A=y
 CONFIG_MFD_AS3711=y
 CONFIG_MFD_AS3722=y
@@ -516,7 +487,6 @@ CONFIG_MFD_ATMEL_FLEXCOM=y
 CONFIG_MFD_ATMEL_HLCDC=m
 CONFIG_MFD_BCM590XX=y
 CONFIG_MFD_AC100=y
-CONFIG_MFD_AXP20X=y
 CONFIG_MFD_AXP20X_I2C=y
 CONFIG_MFD_AXP20X_RSB=y
 CONFIG_MFD_CROS_EC=m
@@ -529,11 +499,11 @@ CONFIG_MFD_MAX77693=m
 CONFIG_MFD_MAX8907=y
 CONFIG_MFD_MAX8997=y
 CONFIG_MFD_MAX8998=y
-CONFIG_MFD_RK808=y
 CONFIG_MFD_CPCAP=y
 CONFIG_MFD_PM8XXX=y
 CONFIG_MFD_QCOM_RPM=y
 CONFIG_MFD_SPMI_PMIC=y
+CONFIG_MFD_RK808=y
 CONFIG_MFD_RN5T618=y
 CONFIG_MFD_SEC_CORE=y
 CONFIG_MFD_STMPE=y
@@ -543,10 +513,10 @@ CONFIG_MFD_TPS65217=y
 CONFIG_MFD_TPS65218=y
 CONFIG_MFD_TPS6586X=y
 CONFIG_MFD_TPS65910=y
-CONFIG_REGULATOR_ACT8945A=y
-CONFIG_REGULATOR_AB8500=y
 CONFIG_REGULATOR_ACT8865=y
+CONFIG_REGULATOR_ACT8945A=y
 CONFIG_REGULATOR_ANATOP=y
+CONFIG_REGULATOR_AB8500=y
 CONFIG_REGULATOR_AS3711=y
 CONFIG_REGULATOR_AS3722=y
 CONFIG_REGULATOR_AXP20X=y
@@ -554,10 +524,7 @@ CONFIG_REGULATOR_BCM590XX=y
 CONFIG_REGULATOR_CPCAP=y
 CONFIG_REGULATOR_DA9210=y
 CONFIG_REGULATOR_FAN53555=y
-CONFIG_REGULATOR_RK808=y
 CONFIG_REGULATOR_GPIO=y
-CONFIG_MFD_SYSCON=y
-CONFIG_POWER_RESET_SYSCON=y
 CONFIG_REGULATOR_LP872X=y
 CONFIG_REGULATOR_MAX14577=m
 CONFIG_REGULATOR_MAX8907=y
@@ -571,7 +538,8 @@ CONFIG_REGULATOR_PALMAS=y
 CONFIG_REGULATOR_PBIAS=y
 CONFIG_REGULATOR_PWM=y
 CONFIG_REGULATOR_QCOM_RPM=y
-CONFIG_REGULATOR_QCOM_SMD_RPM=y
+CONFIG_REGULATOR_QCOM_SMD_RPM=m
+CONFIG_REGULATOR_RK808=y
 CONFIG_REGULATOR_RN5T618=y
 CONFIG_REGULATOR_S2MPS11=y
 CONFIG_REGULATOR_S5M8767=y
@@ -592,18 +560,17 @@ CONFIG_MEDIA_CEC_SUPPORT=y
 CONFIG_MEDIA_CONTROLLER=y
 CONFIG_VIDEO_V4L2_SUBDEV_API=y
 CONFIG_MEDIA_USB_SUPPORT=y
-CONFIG_USB_VIDEO_CLASS=y
-CONFIG_USB_GSPCA=y
+CONFIG_USB_VIDEO_CLASS=m
 CONFIG_V4L_PLATFORM_DRIVERS=y
 CONFIG_SOC_CAMERA=m
 CONFIG_SOC_CAMERA_PLATFORM=m
-CONFIG_VIDEO_RCAR_VIN=m
-CONFIG_VIDEO_ATMEL_ISI=m
 CONFIG_VIDEO_SAMSUNG_EXYNOS4_IS=m
 CONFIG_VIDEO_S5P_FIMC=m
 CONFIG_VIDEO_S5P_MIPI_CSIS=m
 CONFIG_VIDEO_EXYNOS_FIMC_LITE=m
 CONFIG_VIDEO_EXYNOS4_FIMC_IS=m
+CONFIG_VIDEO_RCAR_VIN=m
+CONFIG_VIDEO_ATMEL_ISI=m
 CONFIG_V4L_MEM2MEM_DRIVERS=y
 CONFIG_VIDEO_SAMSUNG_S5P_JPEG=m
 CONFIG_VIDEO_SAMSUNG_S5P_MFC=m
@@ -614,19 +581,15 @@ CONFIG_VIDEO_STI_DELTA=m
 CONFIG_VIDEO_RENESAS_JPU=m
 CONFIG_VIDEO_RENESAS_VSP1=m
 CONFIG_V4L_TEST_DRIVERS=y
+CONFIG_VIDEO_VIVID=m
 CONFIG_CEC_PLATFORM_DRIVERS=y
 CONFIG_VIDEO_SAMSUNG_S5P_CEC=m
 # CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set
 CONFIG_VIDEO_ADV7180=m
 CONFIG_VIDEO_ML86V7667=m
 CONFIG_DRM=y
-CONFIG_DRM_I2C_ADV7511=m
-CONFIG_DRM_I2C_ADV7511_AUDIO=y
 # CONFIG_DRM_I2C_CH7006 is not set
 # CONFIG_DRM_I2C_SIL164 is not set
-CONFIG_DRM_DUMB_VGA_DAC=m
-CONFIG_DRM_NXP_PTN3460=m
-CONFIG_DRM_PARADE_PS8622=m
 CONFIG_DRM_NOUVEAU=m
 CONFIG_DRM_EXYNOS=m
 CONFIG_DRM_EXYNOS_FIMD=y
@@ -645,13 +608,18 @@ CONFIG_DRM_RCAR_LVDS=y
 CONFIG_DRM_SUN4I=m
 CONFIG_DRM_FSL_DCU=m
 CONFIG_DRM_TEGRA=y
+CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_DRM_PANEL_SAMSUNG_LD9040=m
 CONFIG_DRM_PANEL_SAMSUNG_S6E63J0X03=m
 CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=m
-CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_DRM_DUMB_VGA_DAC=m
+CONFIG_DRM_NXP_PTN3460=m
+CONFIG_DRM_PARADE_PS8622=m
 CONFIG_DRM_SII9234=m
+CONFIG_DRM_I2C_ADV7511=m
+CONFIG_DRM_I2C_ADV7511_AUDIO=y
 CONFIG_DRM_STI=m
-CONFIG_DRM_VC4=y
+CONFIG_DRM_VC4=m
 CONFIG_DRM_ETNAVIV=m
 CONFIG_DRM_MXSFB=m
 CONFIG_FB_ARMCLCD=y
@@ -659,8 +627,6 @@ CONFIG_FB_EFI=y
 CONFIG_FB_WM8505=y
 CONFIG_FB_SH_MOBILE_LCDC=y
 CONFIG_FB_SIMPLE=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=m
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_BACKLIGHT_AS3711=y
@@ -668,7 +634,6 @@ CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_SOUND=m
 CONFIG_SND=m
-CONFIG_SND_DYNAMIC_MINORS=y
 CONFIG_SND_HDA_TEGRA=m
 CONFIG_SND_HDA_INPUT_BEEP=y
 CONFIG_SND_HDA_PATCH_LOADER=y
@@ -692,7 +657,7 @@ CONFIG_SND_SOC_SNOW=m
 CONFIG_SND_SOC_ODROID=m
 CONFIG_SND_SOC_SH4_FSI=m
 CONFIG_SND_SOC_RCAR=m
-CONFIG_SND_SIMPLE_SCU_CARD=m
+CONFIG_SND_SOC_STI=m
 CONFIG_SND_SUN4I_CODEC=m
 CONFIG_SND_SOC_TEGRA=m
 CONFIG_SND_SOC_TEGRA20_I2S=m
@@ -703,31 +668,25 @@ CONFIG_SND_SOC_TEGRA_WM8903=m
 CONFIG_SND_SOC_TEGRA_WM9712=m
 CONFIG_SND_SOC_TEGRA_TRIMSLICE=m
 CONFIG_SND_SOC_TEGRA_ALC5632=m
-CONFIG_SND_SOC_CPCAP=m
 CONFIG_SND_SOC_TEGRA_MAX98090=m
 CONFIG_SND_SOC_AK4642=m
+CONFIG_SND_SOC_CPCAP=m
 CONFIG_SND_SOC_SGTL5000=m
 CONFIG_SND_SOC_SPDIF=m
-CONFIG_SND_SOC_WM8978=m
-CONFIG_SND_SOC_STI=m
 CONFIG_SND_SOC_STI_SAS=m
-CONFIG_SND_SIMPLE_CARD=m
+CONFIG_SND_SOC_WM8978=m
+CONFIG_SND_SIMPLE_SCU_CARD=m
 CONFIG_USB=y
 CONFIG_USB_OTG=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_XHCI_MVEBU=y
-CONFIG_USB_XHCI_RCAR=m
 CONFIG_USB_XHCI_TEGRA=m
 CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_MSM=m
-CONFIG_USB_EHCI_EXYNOS=y
-CONFIG_USB_EHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD_STI=y
-CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_ISP1760=y
+CONFIG_USB_EHCI_TEGRA=y
+CONFIG_USB_EHCI_EXYNOS=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_HCD_STI=y
-CONFIG_USB_OHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_EXYNOS=m
 CONFIG_USB_R8A66597_HCD=m
 CONFIG_USB_RENESAS_USBHS=m
@@ -746,18 +705,18 @@ CONFIG_USB_TI_CPPI41_DMA=y
 CONFIG_USB_TUSB_OMAP_DMA=y
 CONFIG_USB_DWC3=y
 CONFIG_USB_DWC2=y
-CONFIG_USB_HSIC_USB3503=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_UDC=y
 CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_ISP1760=y
+CONFIG_USB_HSIC_USB3503=y
 CONFIG_AB8500_USB=y
-CONFIG_KEYSTONE_USB_PHY=y
+CONFIG_KEYSTONE_USB_PHY=m
 CONFIG_NOP_USB_XCEIV=m
 CONFIG_AM335X_PHY_USB=m
 CONFIG_TWL6030_USB=m
 CONFIG_USB_GPIO_VBUS=y
 CONFIG_USB_ISP1301=y
-CONFIG_USB_MSM_OTG=m
 CONFIG_USB_MXS_PHY=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_FSL_USB2=y
@@ -793,21 +752,20 @@ CONFIG_MMC_SDHCI_OF_ESDHC=y
 CONFIG_MMC_SDHCI_ESDHC_IMX=y
 CONFIG_MMC_SDHCI_DOVE=y
 CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_MMC_SDHCI_S3C=y
 CONFIG_MMC_SDHCI_PXAV3=y
 CONFIG_MMC_SDHCI_SPEAR=y
-CONFIG_MMC_SDHCI_S3C=y
 CONFIG_MMC_SDHCI_S3C_DMA=y
 CONFIG_MMC_SDHCI_BCM_KONA=y
+CONFIG_MMC_MESON_MX_SDIO=y
 CONFIG_MMC_SDHCI_ST=y
 CONFIG_MMC_OMAP=y
 CONFIG_MMC_OMAP_HS=y
 CONFIG_MMC_ATMELMCI=y
 CONFIG_MMC_SDHCI_MSM=y
-CONFIG_MMC_MESON_MX_SDIO=y
 CONFIG_MMC_MVSDIO=y
 CONFIG_MMC_SDHI=y
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_PLTFM=y
 CONFIG_MMC_DW_EXYNOS=y
 CONFIG_MMC_DW_ROCKCHIP=y
 CONFIG_MMC_SH_MMCIF=y
@@ -847,94 +805,85 @@ CONFIG_RTC_DRV_MAX77686=y
 CONFIG_RTC_DRV_RK808=m
 CONFIG_RTC_DRV_RS5C372=m
 CONFIG_RTC_DRV_BQ32K=m
-CONFIG_RTC_DRV_PALMAS=y
-CONFIG_RTC_DRV_ST_LPC=y
 CONFIG_RTC_DRV_TWL4030=y
+CONFIG_RTC_DRV_PALMAS=y
 CONFIG_RTC_DRV_TPS6586X=y
 CONFIG_RTC_DRV_TPS65910=y
 CONFIG_RTC_DRV_S35390A=m
 CONFIG_RTC_DRV_RX8581=m
 CONFIG_RTC_DRV_EM3027=y
+CONFIG_RTC_DRV_S5M=m
 CONFIG_RTC_DRV_DA9063=m
 CONFIG_RTC_DRV_EFI=m
 CONFIG_RTC_DRV_DIGICOLOR=m
-CONFIG_RTC_DRV_S5M=m
 CONFIG_RTC_DRV_S3C=m
 CONFIG_RTC_DRV_PL031=y
 CONFIG_RTC_DRV_AT91RM9200=m
 CONFIG_RTC_DRV_AT91SAM9=m
 CONFIG_RTC_DRV_VT8500=y
-CONFIG_RTC_DRV_SUN6I=y
 CONFIG_RTC_DRV_SUNXI=y
 CONFIG_RTC_DRV_MV=y
 CONFIG_RTC_DRV_TEGRA=y
+CONFIG_RTC_DRV_ST_LPC=y
 CONFIG_RTC_DRV_CPCAP=m
 CONFIG_DMADEVICES=y
-CONFIG_DW_DMAC=y
 CONFIG_AT_HDMAC=y
 CONFIG_AT_XDMAC=y
+CONFIG_DMA_BCM2835=y
+CONFIG_DMA_SUN6I=y
 CONFIG_FSL_EDMA=y
+CONFIG_IMX_DMA=y
+CONFIG_IMX_SDMA=y
 CONFIG_MV_XOR=y
+CONFIG_MXS_DMA=y
+CONFIG_PL330_DMA=y
+CONFIG_SIRF_DMA=y
+CONFIG_STE_DMA40=y
+CONFIG_ST_FDMA=m
 CONFIG_TEGRA20_APB_DMA=y
+CONFIG_XILINX_DMA=y
+CONFIG_QCOM_BAM_DMA=y
+CONFIG_DW_DMAC=y
 CONFIG_SH_DMAE=y
 CONFIG_RCAR_DMAC=y
 CONFIG_RENESAS_USB_DMAC=m
-CONFIG_STE_DMA40=y
-CONFIG_SIRF_DMA=y
-CONFIG_TI_EDMA=y
-CONFIG_PL330_DMA=y
-CONFIG_IMX_SDMA=y
-CONFIG_IMX_DMA=y
-CONFIG_MXS_DMA=y
-CONFIG_DMA_BCM2835=y
-CONFIG_DMA_OMAP=y
-CONFIG_QCOM_BAM_DMA=y
-CONFIG_XILINX_DMA=y
-CONFIG_DMA_SUN6I=y
-CONFIG_ST_FDMA=m
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_MMIO=y
 CONFIG_STAGING=y
-CONFIG_SENSORS_ISL29018=y
-CONFIG_SENSORS_ISL29028=y
 CONFIG_MFD_NVEC=y
 CONFIG_KEYBOARD_NVEC=y
 CONFIG_SERIO_NVEC_PS2=y
 CONFIG_NVEC_POWER=y
 CONFIG_NVEC_PAZ00=y
-CONFIG_BCMA=y
-CONFIG_BCMA_HOST_SOC=y
-CONFIG_BCMA_DRIVER_GMAC_CMN=y
-CONFIG_BCMA_DRIVER_GPIO=y
-CONFIG_QCOM_GSBI=y
-CONFIG_QCOM_PM=y
-CONFIG_QCOM_SMEM=y
-CONFIG_QCOM_SMD_RPM=y
-CONFIG_QCOM_SMP2P=y
-CONFIG_QCOM_SMSM=y
-CONFIG_QCOM_WCNSS_CTRL=m
-CONFIG_ROCKCHIP_PM_DOMAINS=y
-CONFIG_COMMON_CLK_QCOM=y
-CONFIG_QCOM_CLK_RPM=y
-CONFIG_CHROME_PLATFORMS=y
 CONFIG_STAGING_BOARD=y
-CONFIG_CROS_EC_CHARDEV=m
 CONFIG_COMMON_CLK_MAX77686=y
 CONFIG_COMMON_CLK_RK808=m
 CONFIG_COMMON_CLK_S2MPS11=m
+CONFIG_COMMON_CLK_QCOM=y
+CONFIG_QCOM_CLK_RPM=y
 CONFIG_APQ_MMCC_8084=y
 CONFIG_MSM_GCC_8660=y
 CONFIG_MSM_MMCC_8960=y
 CONFIG_MSM_MMCC_8974=y
-CONFIG_HWSPINLOCK_QCOM=y
+CONFIG_BCM2835_MBOX=y
 CONFIG_ROCKCHIP_IOMMU=y
 CONFIG_TEGRA_IOMMU_GART=y
 CONFIG_TEGRA_IOMMU_SMMU=y
 CONFIG_REMOTEPROC=m
 CONFIG_ST_REMOTEPROC=m
 CONFIG_RPMSG_VIRTIO=m
+CONFIG_RASPBERRYPI_POWER=y
+CONFIG_QCOM_GSBI=y
+CONFIG_QCOM_PM=y
+CONFIG_QCOM_SMD_RPM=m
+CONFIG_QCOM_WCNSS_CTRL=m
+CONFIG_ROCKCHIP_PM_DOMAINS=y
+CONFIG_ARCH_TEGRA_2x_SOC=y
+CONFIG_ARCH_TEGRA_3x_SOC=y
+CONFIG_ARCH_TEGRA_114_SOC=y
+CONFIG_ARCH_TEGRA_124_SOC=y
 CONFIG_PM_DEVFREQ=y
 CONFIG_ARM_TEGRA_DEVFREQ=m
-CONFIG_MEMORY=y
-CONFIG_EXTCON=y
 CONFIG_TI_AEMIF=y
 CONFIG_IIO=y
 CONFIG_IIO_SW_TRIGGER=y
@@ -947,56 +896,54 @@ CONFIG_VF610_ADC=m
 CONFIG_XILINX_XADC=y
 CONFIG_MPU3050_I2C=y
 CONFIG_CM36651=m
+CONFIG_SENSORS_ISL29018=y
+CONFIG_SENSORS_ISL29028=y
 CONFIG_AK8975=y
-CONFIG_RASPBERRYPI_POWER=y
 CONFIG_IIO_HRTIMER_TRIGGER=y
 CONFIG_PWM=y
 CONFIG_PWM_ATMEL=m
 CONFIG_PWM_ATMEL_HLCDC_PWM=m
 CONFIG_PWM_ATMEL_TCB=m
+CONFIG_PWM_BCM2835=y
+CONFIG_PWM_BRCMSTB=m
 CONFIG_PWM_FSL_FTM=m
 CONFIG_PWM_MESON=m
 CONFIG_PWM_RCAR=m
 CONFIG_PWM_RENESAS_TPU=y
 CONFIG_PWM_ROCKCHIP=m
 CONFIG_PWM_SAMSUNG=m
+CONFIG_PWM_STI=y
 CONFIG_PWM_SUN4I=y
 CONFIG_PWM_TEGRA=y
 CONFIG_PWM_VT8500=y
+CONFIG_KEYSTONE_IRQ=y
+CONFIG_PHY_SUN4I_USB=y
+CONFIG_PHY_SUN9I_USB=y
 CONFIG_PHY_HIX5HD2_SATA=y
-CONFIG_E1000E=y
-CONFIG_PWM_STI=y
-CONFIG_PWM_BCM2835=y
-CONFIG_PWM_BRCMSTB=m
-CONFIG_PHY_DM816X_USB=m
-CONFIG_OMAP_USB2=y
-CONFIG_TI_PIPE3=y
-CONFIG_TWL4030_USB=m
+CONFIG_PHY_BERLIN_SATA=y
 CONFIG_PHY_BERLIN_USB=y
 CONFIG_PHY_CPCAP_USB=m
-CONFIG_PHY_BERLIN_SATA=y
+CONFIG_PHY_QCOM_APQ8064_SATA=m
+CONFIG_PHY_RCAR_GEN2=m
 CONFIG_PHY_ROCKCHIP_DP=m
 CONFIG_PHY_ROCKCHIP_USB=y
-CONFIG_PHY_QCOM_APQ8064_SATA=m
+CONFIG_PHY_SAMSUNG_USB2=m
 CONFIG_PHY_MIPHY28LP=y
-CONFIG_PHY_RCAR_GEN2=m
 CONFIG_PHY_STIH407_USB=y
 CONFIG_PHY_STM32_USBPHYC=y
-CONFIG_PHY_SUN4I_USB=y
-CONFIG_PHY_SUN9I_USB=y
-CONFIG_PHY_SAMSUNG_USB2=m
 CONFIG_PHY_TEGRA_XUSB=y
-CONFIG_PHY_BRCM_SATA=y
-CONFIG_NVMEM=y
+CONFIG_PHY_DM816X_USB=m
+CONFIG_OMAP_USB2=y
+CONFIG_TI_PIPE3=y
+CONFIG_TWL4030_USB=m
 CONFIG_NVMEM_IMX_OCOTP=y
 CONFIG_NVMEM_SUNXI_SID=y
 CONFIG_NVMEM_VF610_OCOTP=y
-CONFIG_BCM2835_MBOX=y
 CONFIG_RASPBERRYPI_FIRMWARE=y
-CONFIG_EFI_VARS=m
-CONFIG_EFI_CAPSULE_LOADER=m
 CONFIG_BCM47XX_NVRAM=y
 CONFIG_BCM47XX_SPROM=y
+CONFIG_EFI_VARS=m
+CONFIG_EFI_CAPSULE_LOADER=m
 CONFIG_EXT4_FS=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_MSDOS_FS=y
@@ -1004,7 +951,6 @@ CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_UBIFS_FS=y
-CONFIG_TMPFS=y
 CONFIG_SQUASHFS=y
 CONFIG_SQUASHFS_LZO=y
 CONFIG_SQUASHFS_XZ=y
@@ -1020,13 +966,7 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
 CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_LOCKUP_DETECTOR=y
-CONFIG_CPUFREQ_DT=y
-CONFIG_KEYSTONE_IRQ=y
-CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_ST=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
@@ -1035,27 +975,19 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_DEV_MARVELL_CESA=m
 CONFIG_CRYPTO_DEV_EXYNOS_RNG=m
 CONFIG_CRYPTO_DEV_S5P=m
+CONFIG_CRYPTO_DEV_ATMEL_AES=m
+CONFIG_CRYPTO_DEV_ATMEL_TDES=m
+CONFIG_CRYPTO_DEV_ATMEL_SHA=m
 CONFIG_CRYPTO_DEV_SUN4I_SS=m
 CONFIG_CRYPTO_DEV_ROCKCHIP=m
 CONFIG_ARM_CRYPTO=y
-CONFIG_CRYPTO_SHA1_ARM=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
 CONFIG_CRYPTO_SHA1_ARM_CE=m
 CONFIG_CRYPTO_SHA2_ARM_CE=m
-CONFIG_CRYPTO_SHA256_ARM=m
 CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM=m
 CONFIG_CRYPTO_AES_ARM_BS=m
 CONFIG_CRYPTO_AES_ARM_CE=m
-CONFIG_CRYPTO_CHACHA20_NEON=m
-CONFIG_CRYPTO_CRC32_ARM_CE=m
-CONFIG_CRYPTO_CRCT10DIF_ARM_CE=m
 CONFIG_CRYPTO_GHASH_ARM_CE=m
-CONFIG_CRYPTO_DEV_ATMEL_AES=m
-CONFIG_CRYPTO_DEV_ATMEL_TDES=m
-CONFIG_CRYPTO_DEV_ATMEL_SHA=m
-CONFIG_VIDEO_VIVID=m
-CONFIG_VIRTIO=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_PCI_LEGACY=y
-CONFIG_VIRTIO_MMIO=y
+CONFIG_CRYPTO_CRC32_ARM_CE=m
+CONFIG_CRYPTO_CHACHA20_NEON=m
diff --git a/arch/arm/crypto/speck-neon-core.S b/arch/arm/crypto/speck-neon-core.S
index 3c1e203e53b9..57caa742016e 100644
--- a/arch/arm/crypto/speck-neon-core.S
+++ b/arch/arm/crypto/speck-neon-core.S
@@ -272,9 +272,11 @@
 	 * Allocate stack space to store 128 bytes worth of tweaks.  For
 	 * performance, this space is aligned to a 16-byte boundary so that we
 	 * can use the load/store instructions that declare 16-byte alignment.
+	 * For Thumb2 compatibility, don't do the 'bic' directly on 'sp'.
 	 */
-	sub		sp, #128
-	bic		sp, #0xf
+	sub		r12, sp, #128
+	bic		r12, #0xf
+	mov		sp, r12
 
 .if \n == 64
 	// Load first tweak
diff --git a/arch/arm/firmware/Makefile b/arch/arm/firmware/Makefile
index a71f16536b6c..6e41336b0bc4 100644
--- a/arch/arm/firmware/Makefile
+++ b/arch/arm/firmware/Makefile
@@ -1 +1,4 @@
 obj-$(CONFIG_TRUSTED_FOUNDATIONS)	+= trusted_foundations.o
+
+# tf_generic_smc() fails to build with -fsanitize-coverage=trace-pc
+KCOV_INSTRUMENT                := n
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 0cd4dccbae78..b17ee03d280b 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -460,6 +460,10 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	adds	\tmp, \addr, #\size - 1
 	sbcccs	\tmp, \tmp, \limit
 	bcs	\bad
+#ifdef CONFIG_CPU_SPECTRE
+	movcs	\addr, #0
+	csdb
+#endif
 #endif
 	.endm
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 66d0e215a773..f74756641410 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -130,7 +130,7 @@ static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
 }
 #define atomic_cmpxchg_relaxed		atomic_cmpxchg_relaxed
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int oldval, newval;
 	unsigned long tmp;
@@ -156,6 +156,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return oldval;
 }
+#define atomic_fetch_add_unless		atomic_fetch_add_unless
 
 #else /* ARM_ARCH_6 */
 
@@ -215,15 +216,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
-		c = old;
-	return c;
-}
+#define atomic_fetch_andnot		atomic_fetch_andnot
 
 #endif /* __LINUX_ARM_ARCH__ */
 
@@ -254,17 +247,6 @@ ATOMIC_OPS(xor, ^=, eor)
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-#define atomic_inc(v)		atomic_add(1, v)
-#define atomic_dec(v)		atomic_sub(1, v)
-
-#define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return_relaxed(v)    (atomic_add_return_relaxed(1, v))
-#define atomic_dec_return_relaxed(v)    (atomic_sub_return_relaxed(1, v))
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
-
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
 	long long counter;
@@ -494,12 +476,13 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 
 	return result;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	long long val;
+	long long oldval, newval;
 	unsigned long tmp;
-	int ret = 1;
 
 	smp_mb();
 	prefetchw(&v->counter);
@@ -508,33 +491,23 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 "1:	ldrexd	%0, %H0, [%4]\n"
 "	teq	%0, %5\n"
 "	teqeq	%H0, %H5\n"
-"	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%Q0, %Q0, %Q6\n"
-"	adc	%R0, %R0, %R6\n"
-"	strexd	%2, %0, %H0, [%4]\n"
+"	adds	%Q1, %Q0, %Q6\n"
+"	adc	%R1, %R0, %R6\n"
+"	strexd	%2, %1, %H1, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
 "2:"
-	: "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter)
+	: "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (u), "r" (a)
 	: "cc");
 
-	if (ret)
+	if (oldval != u)
 		smp_mb();
 
-	return ret;
+	return oldval;
 }
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1LL, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif /* !CONFIG_GENERIC_ATOMIC64 */
 #endif
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 4cab9bb823fb..c92e42a5c8f7 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -215,7 +215,6 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 
 #if __LINUX_ARM_ARCH__ < 5
 
-#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/fls.h>
@@ -223,93 +222,20 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 
 #else
 
-static inline int constant_fls(int x)
-{
-	int r = 32;
-
-	if (!x)
-		return 0;
-	if (!(x & 0xffff0000u)) {
-		x <<= 16;
-		r -= 16;
-	}
-	if (!(x & 0xff000000u)) {
-		x <<= 8;
-		r -= 8;
-	}
-	if (!(x & 0xf0000000u)) {
-		x <<= 4;
-		r -= 4;
-	}
-	if (!(x & 0xc0000000u)) {
-		x <<= 2;
-		r -= 2;
-	}
-	if (!(x & 0x80000000u)) {
-		x <<= 1;
-		r -= 1;
-	}
-	return r;
-}
-
-/*
- * On ARMv5 and above those functions can be implemented around the
- * clz instruction for much better code efficiency.  __clz returns
- * the number of leading zeros, zero input will return 32, and
- * 0x80000000 will return 0.
- */
-static inline unsigned int __clz(unsigned int x)
-{
-	unsigned int ret;
-
-	asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
-
-	return ret;
-}
-
-/*
- * fls() returns zero if the input is zero, otherwise returns the bit
- * position of the last set bit, where the LSB is 1 and MSB is 32.
- */
-static inline int fls(int x)
-{
-	if (__builtin_constant_p(x))
-	       return constant_fls(x);
-
-	return 32 - __clz(x);
-}
-
-/*
- * __fls() returns the bit position of the last bit set, where the
- * LSB is 0 and MSB is 31.  Zero input is undefined.
- */
-static inline unsigned long __fls(unsigned long x)
-{
-	return fls(x) - 1;
-}
-
-/*
- * ffs() returns zero if the input was zero, otherwise returns the bit
- * position of the first set bit, where the LSB is 1 and MSB is 32.
- */
-static inline int ffs(int x)
-{
-	return fls(x & -x);
-}
-
 /*
- * __ffs() returns the bit position of the first bit set, where the
- * LSB is 0 and MSB is 31.  Zero input is undefined.
+ * On ARMv5 and above, the gcc built-ins may rely on the clz instruction
+ * and produce optimal inlined code in all cases. On ARMv7 it is even
+ * better by also using the rbit instruction.
  */
-static inline unsigned long __ffs(unsigned long x)
-{
-	return ffs(x) - 1;
-}
-
-#define ffz(x) __ffs( ~(x) )
+#include <asm-generic/bitops/builtin-__fls.h>
+#include <asm-generic/bitops/builtin-__ffs.h>
+#include <asm-generic/bitops/builtin-fls.h>
+#include <asm-generic/bitops/builtin-ffs.h>
 
 #endif
 
+#include <asm-generic/bitops/ffz.h>
+
 #include <asm-generic/bitops/fls64.h>
 
 #include <asm-generic/bitops/sched.h>
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 17f1f1a814ff..38badaae8d9d 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -58,6 +58,9 @@ void efi_virtmap_unload(void);
 #define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
 #define efi_is_64bit()			(false)
 
+#define efi_table_attr(table, attr, instance)				\
+	((table##_t *)instance)->attr
+
 #define efi_call_proto(protocol, f, instance, ...)			\
 	((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
 
diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index e46e4e7bdba3..ac54c06764e6 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -111,14 +111,17 @@ static inline void decode_ctrl_reg(u32 reg,
 	asm volatile("mcr p14, 0, %0, " #N "," #M ", " #OP2 : : "r" (VAL));\
 } while (0)
 
+struct perf_event_attr;
 struct notifier_block;
 struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  int *gen_len, int *gen_type);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index b6f319606e30..c883fcbe93b6 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -31,11 +31,6 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *);
 void handle_IRQ(unsigned int, struct pt_regs *);
 void init_IRQ(void);
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-extern void (*handle_arch_irq)(struct pt_regs *);
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-#endif
-
 #ifdef CONFIG_SMP
 extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
 					   bool exclude_self);
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index 59655459da59..82290f212d8e 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -44,8 +44,6 @@ struct prev_kprobe {
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
 	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 6493bd479ddc..fe2fb1ddd771 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -26,13 +26,13 @@
 #include <asm/cputype.h>
 
 /* arm64 compatibility macros */
-#define COMPAT_PSR_MODE_ABT	ABT_MODE
-#define COMPAT_PSR_MODE_UND	UND_MODE
-#define COMPAT_PSR_T_BIT	PSR_T_BIT
-#define COMPAT_PSR_I_BIT	PSR_I_BIT
-#define COMPAT_PSR_A_BIT	PSR_A_BIT
-#define COMPAT_PSR_E_BIT	PSR_E_BIT
-#define COMPAT_PSR_IT_MASK	PSR_IT_MASK
+#define PSR_AA32_MODE_ABT	ABT_MODE
+#define PSR_AA32_MODE_UND	UND_MODE
+#define PSR_AA32_T_BIT		PSR_T_BIT
+#define PSR_AA32_I_BIT		PSR_I_BIT
+#define PSR_AA32_A_BIT		PSR_A_BIT
+#define PSR_AA32_E_BIT		PSR_E_BIT
+#define PSR_AA32_IT_MASK	PSR_IT_MASK
 
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 5c1ad11aa392..bb8851208e17 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -59,7 +59,7 @@ struct machine_desc {
 	void			(*init_time)(void);
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	void			(*handle_irq)(struct pt_regs *);
 #endif
 	void			(*restart)(enum reboot_mode, const char *);
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index 0f79e4dec7f9..4ac3a019a46f 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -13,7 +13,6 @@
 extern void timer_tick(void);
 
 typedef void (*clock_access_fn)(struct timespec64 *);
-extern int register_persistent_clock(clock_access_fn read_boot,
-				     clock_access_fn read_persistent);
+extern int register_persistent_clock(clock_access_fn read_persistent);
 
 #endif
diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h
index 1e5b9bb92270..991c9127c650 100644
--- a/arch/arm/include/asm/probes.h
+++ b/arch/arm/include/asm/probes.h
@@ -51,7 +51,6 @@ struct arch_probes_insn {
  * We assume one instruction can consume at most 64 bytes stack, which is
  * 'push {r0-r15}'. Instructions consume more or unknown stack space like
  * 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe.
- * Both kprobe and jprobe use this macro.
  */
 #define MAX_STACK_SIZE			64
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index e71cc35de163..9b37b6ab27fe 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -123,8 +123,8 @@ struct user_vfp_exc;
 
 extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *,
 					   struct user_vfp_exc __user *);
-extern int vfp_restore_user_hwstate(struct user_vfp __user *,
-				    struct user_vfp_exc __user *);
+extern int vfp_restore_user_hwstate(struct user_vfp *,
+				    struct user_vfp_exc *);
 #endif
 
 /*
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index d5562f9ce600..f854148c8d7c 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -292,5 +292,13 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 {
 }
 
+static inline void tlb_flush_remove_tables(struct mm_struct *mm)
+{
+}
+
+static inline void tlb_flush_remove_tables_local(void *arg)
+{
+}
+
 #endif /* CONFIG_MMU */
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 3d614e90c19f..5451e1f05a19 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -85,6 +85,13 @@ static inline void set_fs(mm_segment_t fs)
 	flag; })
 
 /*
+ * This is a type: either unsigned long, if the argument fits into
+ * that type, or otherwise unsigned long long.
+ */
+#define __inttype(x) \
+	__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
+
+/*
  * Single-value transfer routines.  They automatically use the right
  * size if we just have the right pointer type.  Note that the functions
  * which read from user space (*get_*) need to take care not to leak
@@ -153,7 +160,7 @@ extern int __get_user_64t_4(void *);
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register typeof(*(p)) __user *__p asm("r0") = (p);	\
-		register typeof(x) __r2 asm("r2");			\
+		register __inttype(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		unsigned int __ua_flags = uaccess_save_and_enable();	\
@@ -243,6 +250,16 @@ static inline void set_fs(mm_segment_t fs)
 #define user_addr_max() \
 	(uaccess_kernel() ? ~0UL : get_fs())
 
+#ifdef CONFIG_CPU_SPECTRE
+/*
+ * When mitigating Spectre variant 1, it is not worth fixing the non-
+ * verifying accessors, because we need to add verification of the
+ * address space there.  Force these to use the standard get_user()
+ * version instead.
+ */
+#define __get_user(x, ptr) get_user(x, ptr)
+#else
+
 /*
  * The "__xxx" versions of the user access functions do not verify the
  * address space - it must have been done previously with a separate
@@ -259,12 +276,6 @@ static inline void set_fs(mm_segment_t fs)
 	__gu_err;							\
 })
 
-#define __get_user_error(x, ptr, err)					\
-({									\
-	__get_user_err((x), (ptr), err);				\
-	(void) 0;							\
-})
-
 #define __get_user_err(x, ptr, err)					\
 do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
@@ -324,6 +335,7 @@ do {									\
 
 #define __get_user_asm_word(x, addr, err)			\
 	__get_user_asm(x, addr, err, ldr)
+#endif
 
 
 #define __put_user_switch(x, ptr, __err, __fn)				\
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 179a9f6bd1e3..e85a3af9ddeb 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -22,7 +22,7 @@
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
 #include <asm/vfpmacros.h>
-#ifndef CONFIG_MULTI_IRQ_HANDLER
+#ifndef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 #include <mach/entry-macro.S>
 #endif
 #include <asm/thread_notify.h>
@@ -39,7 +39,7 @@
  * Interrupt handling.
  */
 	.macro	irq_handler
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	ldr	r1, =handle_arch_irq
 	mov	r0, sp
 	badr	lr, 9997f
@@ -1226,9 +1226,3 @@ vector_addrexcptn:
 	.globl	cr_alignment
 cr_alignment:
 	.space	4
-
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-	.globl	handle_arch_irq
-handle_arch_irq:
-	.space	4
-#endif
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 106a1466518d..746565a876dc 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -48,6 +48,7 @@ saved_pc	.req	lr
  * from those features make this path too inefficient.
  */
 ret_fast_syscall:
+__ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	disable_irq_notrace			@ disable interrupts
@@ -78,6 +79,7 @@ fast_work_pending:
  * call.
  */
 ret_fast_syscall:
+__ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
@@ -255,7 +257,7 @@ local_restart:
 	tst	r10, #_TIF_SYSCALL_WORK		@ are we tracing syscalls?
 	bne	__sys_trace
 
-	invoke_syscall tbl, scno, r10, ret_fast_syscall
+	invoke_syscall tbl, scno, r10, __ret_fast_syscall
 
 	add	r1, sp, #S_OFF
 2:	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index dd546d65a383..ec29de250076 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -53,7 +53,11 @@ ENTRY(stext)
  THUMB(1:			)
 #endif
 
-	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
+#ifdef CONFIG_ARM_VIRT_EXT
+	bl	__hyp_stub_install
+#endif
+	@ ensure svc mode and all interrupts masked
+	safe_svcmode_maskall r9
 						@ and irqs disabled
 #if defined(CONFIG_CPU_CP15)
 	mrc	p15, 0, r9, c0, c0		@ get processor id
@@ -89,7 +93,11 @@ ENTRY(secondary_startup)
 	 * the processor type - there is no need to check the machine type
 	 * as it has already been validated by the primary processor.
 	 */
-	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
+#ifdef CONFIG_ARM_VIRT_EXT
+	bl	__hyp_stub_install_secondary
+#endif
+	safe_svcmode_maskall r9
+
 #ifndef CONFIG_CPU_CP15
 	ldr	r9, =CONFIG_PROCESSOR_ID
 #else
@@ -177,7 +185,7 @@ M_CLASS(streq	r3, [r12, #PMSAv8_MAIR1])
 	bic	r0, r0, #CR_I
 #endif
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
-	isb
+	instr_sync
 #elif defined (CONFIG_CPU_V7M)
 #ifdef CONFIG_ARM_MPU
 	ldreq	r3, [r12, MPU_CTRL]
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 629e25152c0d..1d5fbf1d1c67 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -456,14 +456,13 @@ static int get_hbp_len(u8 hbp_len)
 /*
  * Check whether bp virtual address is in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->ctrl.len);
+	va = hw->address;
+	len = get_hbp_len(hw->ctrl.len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -518,42 +517,42 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+		hw->ctrl.type = ARM_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->ctrl.type = ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
-		if ((info->ctrl.type != ARM_BREAKPOINT_EXECUTE)
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
+		if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE)
 			&& max_watchpoint_len >= 8)
 			break;
 	default:
@@ -566,24 +565,24 @@ static int arch_build_bp_info(struct perf_event *bp)
 	 * by the hardware and must be aligned to the appropriate number of
 	 * bytes.
 	 */
-	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
-	    info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
-	    info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+	if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
+	    hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+	    hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
 		return -EINVAL;
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/* Privilege */
-	info->ctrl.privilege = ARM_BREAKPOINT_USER;
-	if (arch_check_bp_in_kernelspace(bp))
-		info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
+	hw->ctrl.privilege = ARM_BREAKPOINT_USER;
+	if (arch_check_bp_in_kernelspace(hw))
+		hw->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
 
 	/* Enabled? */
-	info->ctrl.enabled = !bp->attr.disabled;
+	hw->ctrl.enabled = !attr->disabled;
 
 	/* Mismatch */
-	info->ctrl.mismatch = 0;
+	hw->ctrl.mismatch = 0;
 
 	return 0;
 }
@@ -591,9 +590,10 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings.
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	int ret = 0;
 	u32 offset, alignment_mask = 0x3;
 
@@ -602,14 +602,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		return -ENODEV;
 
 	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		goto out;
 
 	/* Check address alignment. */
-	if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+	if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
 		alignment_mask = 0x7;
-	offset = info->address & alignment_mask;
+	offset = hw->address & alignment_mask;
 	switch (offset) {
 	case 0:
 		/* Aligned */
@@ -617,19 +617,19 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	case 1:
 	case 2:
 		/* Allow halfword watchpoints and breakpoints. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
 	case 3:
 		/* Allow single byte watchpoint. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 			break;
 	default:
 		ret = -EINVAL;
 		goto out;
 	}
 
-	info->address &= ~alignment_mask;
-	info->ctrl.len <<= offset;
+	hw->address &= ~alignment_mask;
+	hw->ctrl.len <<= offset;
 
 	if (is_default_overflow_handler(bp)) {
 		/*
@@ -640,7 +640,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 			return -EINVAL;
 
 		/* We don't allow mismatch breakpoints in kernel space. */
-		if (arch_check_bp_in_kernelspace(bp))
+		if (arch_check_bp_in_kernelspace(hw))
 			return -EPERM;
 
 		/*
@@ -655,8 +655,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		 * reports them.
 		 */
 		if (!debug_exception_updates_fsr() &&
-		    (info->ctrl.type == ARM_BREAKPOINT_LOAD ||
-		     info->ctrl.type == ARM_BREAKPOINT_STORE))
+		    (hw->ctrl.type == ARM_BREAKPOINT_LOAD ||
+		     hw->ctrl.type == ARM_BREAKPOINT_STORE))
 			return -EINVAL;
 	}
 
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index ece04a457486..9908dacf9229 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -102,16 +102,6 @@ void __init init_IRQ(void)
 	uniphier_cache_init();
 }
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	if (handle_arch_irq)
-		return;
-
-	handle_arch_irq = handle_irq;
-}
-#endif
-
 #ifdef CONFIG_SPARSE_IRQ
 int __init arch_probe_nr_irqs(void)
 {
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index be42c4f66a40..1ae99deeec54 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -233,7 +233,7 @@ armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
 	return ret;
 }
 
-static inline u32 armv6pmu_read_counter(struct perf_event *event)
+static inline u64 armv6pmu_read_counter(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -251,7 +251,7 @@ static inline u32 armv6pmu_read_counter(struct perf_event *event)
 	return value;
 }
 
-static inline void armv6pmu_write_counter(struct perf_event *event, u32 value)
+static inline void armv6pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -411,6 +411,12 @@ armv6pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	}
 }
 
+static void armv6pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				     struct perf_event *event)
+{
+	clear_bit(event->hw.idx, cpuc->used_mask);
+}
+
 static void armv6pmu_disable_event(struct perf_event *event)
 {
 	unsigned long val, mask, evt, flags;
@@ -491,11 +497,11 @@ static void armv6pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= armv6pmu_read_counter;
 	cpu_pmu->write_counter	= armv6pmu_write_counter;
 	cpu_pmu->get_event_idx	= armv6pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = armv6pmu_clear_event_idx;
 	cpu_pmu->start		= armv6pmu_start;
 	cpu_pmu->stop		= armv6pmu_stop;
 	cpu_pmu->map_event	= armv6_map_event;
 	cpu_pmu->num_events	= 3;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 }
 
 static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
@@ -542,11 +548,11 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= armv6pmu_read_counter;
 	cpu_pmu->write_counter	= armv6pmu_write_counter;
 	cpu_pmu->get_event_idx	= armv6pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = armv6pmu_clear_event_idx;
 	cpu_pmu->start		= armv6pmu_start;
 	cpu_pmu->stop		= armv6pmu_stop;
 	cpu_pmu->map_event	= armv6mpcore_map_event;
 	cpu_pmu->num_events	= 3;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 
 	return 0;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 57f01e059f39..a4fb0f8b8f84 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -743,7 +743,7 @@ static inline void armv7_pmnc_select_counter(int idx)
 	isb();
 }
 
-static inline u32 armv7pmu_read_counter(struct perf_event *event)
+static inline u64 armv7pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -763,7 +763,7 @@ static inline u32 armv7pmu_read_counter(struct perf_event *event)
 	return value;
 }
 
-static inline void armv7pmu_write_counter(struct perf_event *event, u32 value)
+static inline void armv7pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -1058,6 +1058,12 @@ static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	return -EAGAIN;
 }
 
+static void armv7pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				     struct perf_event *event)
+{
+	clear_bit(event->hw.idx, cpuc->used_mask);
+}
+
 /*
  * Add an event filter to a given event. This will only work for PMUv2 PMUs.
  */
@@ -1167,10 +1173,10 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= armv7pmu_read_counter;
 	cpu_pmu->write_counter	= armv7pmu_write_counter;
 	cpu_pmu->get_event_idx	= armv7pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = armv7pmu_clear_event_idx;
 	cpu_pmu->start		= armv7pmu_start;
 	cpu_pmu->stop		= armv7pmu_stop;
 	cpu_pmu->reset		= armv7pmu_reset;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 };
 
 static void armv7_read_num_pmnc_events(void *info)
@@ -1638,6 +1644,7 @@ static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 	bool venum_event = EVENT_VENUM(hwc->config_base);
 	bool krait_event = EVENT_CPU(hwc->config_base);
 
+	armv7pmu_clear_event_idx(cpuc, event);
 	if (venum_event || krait_event) {
 		bit = krait_event_to_bit(event, region, group);
 		clear_bit(bit, cpuc->used_mask);
@@ -1967,6 +1974,7 @@ static void scorpion_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 	bool venum_event = EVENT_VENUM(hwc->config_base);
 	bool scorpion_event = EVENT_CPU(hwc->config_base);
 
+	armv7pmu_clear_event_idx(cpuc, event);
 	if (venum_event || scorpion_event) {
 		bit = scorpion_event_to_bit(event, region, group);
 		clear_bit(bit, cpuc->used_mask);
@@ -2030,6 +2038,7 @@ static struct platform_driver armv7_pmu_driver = {
 	.driver		= {
 		.name	= "armv7-pmu",
 		.of_match_table = armv7_pmu_of_device_ids,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= armv7_pmu_device_probe,
 };
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 88d1a76f5367..f6cdcacfb96d 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -292,6 +292,12 @@ xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	}
 }
 
+static void xscalepmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				     struct perf_event *event)
+{
+	clear_bit(event->hw.idx, cpuc->used_mask);
+}
+
 static void xscale1pmu_start(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags, val;
@@ -316,7 +322,7 @@ static void xscale1pmu_stop(struct arm_pmu *cpu_pmu)
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
-static inline u32 xscale1pmu_read_counter(struct perf_event *event)
+static inline u64 xscale1pmu_read_counter(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -337,7 +343,7 @@ static inline u32 xscale1pmu_read_counter(struct perf_event *event)
 	return val;
 }
 
-static inline void xscale1pmu_write_counter(struct perf_event *event, u32 val)
+static inline void xscale1pmu_write_counter(struct perf_event *event, u64 val)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -370,11 +376,11 @@ static int xscale1pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= xscale1pmu_read_counter;
 	cpu_pmu->write_counter	= xscale1pmu_write_counter;
 	cpu_pmu->get_event_idx	= xscale1pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = xscalepmu_clear_event_idx;
 	cpu_pmu->start		= xscale1pmu_start;
 	cpu_pmu->stop		= xscale1pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
 	cpu_pmu->num_events	= 3;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 
 	return 0;
 }
@@ -679,7 +685,7 @@ static void xscale2pmu_stop(struct arm_pmu *cpu_pmu)
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
-static inline u32 xscale2pmu_read_counter(struct perf_event *event)
+static inline u64 xscale2pmu_read_counter(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -706,7 +712,7 @@ static inline u32 xscale2pmu_read_counter(struct perf_event *event)
 	return val;
 }
 
-static inline void xscale2pmu_write_counter(struct perf_event *event, u32 val)
+static inline void xscale2pmu_write_counter(struct perf_event *event, u64 val)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -739,11 +745,11 @@ static int xscale2pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= xscale2pmu_read_counter;
 	cpu_pmu->write_counter	= xscale2pmu_write_counter;
 	cpu_pmu->get_event_idx	= xscale2pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = xscalepmu_clear_event_idx;
 	cpu_pmu->start		= xscale2pmu_start;
 	cpu_pmu->stop		= xscale2pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
 	cpu_pmu->num_events	= 5;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 
 	return 0;
 }
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 225d1c58d2de..d9c299133111 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -338,6 +338,7 @@ static struct vm_area_struct gate_vma = {
 
 static int __init gate_vma_init(void)
 {
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
 	return 0;
 }
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 35ca494c028c..4c249cb261f3 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1145,7 +1145,7 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_crashkernel();
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	handle_arch_irq = mdesc->handle_irq;
 #endif
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index dec130e7078c..b8f766cf3a90 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -150,22 +150,18 @@ static int preserve_vfp_context(struct vfp_sigframe __user *frame)
 
 static int restore_vfp_context(char __user **auxp)
 {
-	struct vfp_sigframe __user *frame =
-		(struct vfp_sigframe __user *)*auxp;
-	unsigned long magic;
-	unsigned long size;
-	int err = 0;
-
-	__get_user_error(magic, &frame->magic, err);
-	__get_user_error(size, &frame->size, err);
+	struct vfp_sigframe frame;
+	int err;
 
+	err = __copy_from_user(&frame, *auxp, sizeof(frame));
 	if (err)
-		return -EFAULT;
-	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
+		return err;
+
+	if (frame.magic != VFP_MAGIC || frame.size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
-	*auxp += size;
-	return vfp_restore_user_hwstate(&frame->ufp, &frame->ufp_exc);
+	*auxp += sizeof(frame);
+	return vfp_restore_user_hwstate(&frame.ufp, &frame.ufp_exc);
 }
 
 #endif
@@ -176,6 +172,7 @@ static int restore_vfp_context(char __user **auxp)
 
 static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 {
+	struct sigcontext context;
 	char __user *aux;
 	sigset_t set;
 	int err;
@@ -184,23 +181,26 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 	if (err == 0)
 		set_current_blocked(&set);
 
-	__get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
-	__get_user_error(regs->ARM_r1, &sf->uc.uc_mcontext.arm_r1, err);
-	__get_user_error(regs->ARM_r2, &sf->uc.uc_mcontext.arm_r2, err);
-	__get_user_error(regs->ARM_r3, &sf->uc.uc_mcontext.arm_r3, err);
-	__get_user_error(regs->ARM_r4, &sf->uc.uc_mcontext.arm_r4, err);
-	__get_user_error(regs->ARM_r5, &sf->uc.uc_mcontext.arm_r5, err);
-	__get_user_error(regs->ARM_r6, &sf->uc.uc_mcontext.arm_r6, err);
-	__get_user_error(regs->ARM_r7, &sf->uc.uc_mcontext.arm_r7, err);
-	__get_user_error(regs->ARM_r8, &sf->uc.uc_mcontext.arm_r8, err);
-	__get_user_error(regs->ARM_r9, &sf->uc.uc_mcontext.arm_r9, err);
-	__get_user_error(regs->ARM_r10, &sf->uc.uc_mcontext.arm_r10, err);
-	__get_user_error(regs->ARM_fp, &sf->uc.uc_mcontext.arm_fp, err);
-	__get_user_error(regs->ARM_ip, &sf->uc.uc_mcontext.arm_ip, err);
-	__get_user_error(regs->ARM_sp, &sf->uc.uc_mcontext.arm_sp, err);
-	__get_user_error(regs->ARM_lr, &sf->uc.uc_mcontext.arm_lr, err);
-	__get_user_error(regs->ARM_pc, &sf->uc.uc_mcontext.arm_pc, err);
-	__get_user_error(regs->ARM_cpsr, &sf->uc.uc_mcontext.arm_cpsr, err);
+	err |= __copy_from_user(&context, &sf->uc.uc_mcontext, sizeof(context));
+	if (err == 0) {
+		regs->ARM_r0 = context.arm_r0;
+		regs->ARM_r1 = context.arm_r1;
+		regs->ARM_r2 = context.arm_r2;
+		regs->ARM_r3 = context.arm_r3;
+		regs->ARM_r4 = context.arm_r4;
+		regs->ARM_r5 = context.arm_r5;
+		regs->ARM_r6 = context.arm_r6;
+		regs->ARM_r7 = context.arm_r7;
+		regs->ARM_r8 = context.arm_r8;
+		regs->ARM_r9 = context.arm_r9;
+		regs->ARM_r10 = context.arm_r10;
+		regs->ARM_fp = context.arm_fp;
+		regs->ARM_ip = context.arm_ip;
+		regs->ARM_sp = context.arm_sp;
+		regs->ARM_lr = context.arm_lr;
+		regs->ARM_pc = context.arm_pc;
+		regs->ARM_cpsr = context.arm_cpsr;
+	}
 
 	err |= !valid_user_regs(regs);
 
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 1df21a61e379..f0dd4b6ebb63 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -329,9 +329,11 @@ asmlinkage long sys_oabi_semtimedop(int semid,
 		return -ENOMEM;
 	err = 0;
 	for (i = 0; i < nsops; i++) {
-		__get_user_error(sops[i].sem_num, &tsops->sem_num, err);
-		__get_user_error(sops[i].sem_op,  &tsops->sem_op,  err);
-		__get_user_error(sops[i].sem_flg, &tsops->sem_flg, err);
+		struct oabi_sembuf osb;
+		err |= __copy_from_user(&osb, tsops, sizeof(osb));
+		sops[i].sem_num = osb.sem_num;
+		sops[i].sem_op = osb.sem_op;
+		sops[i].sem_flg = osb.sem_flg;
 		tsops++;
 	}
 	if (timeout) {
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index cf2701cb0de8..078b259ead4e 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -83,29 +83,18 @@ static void dummy_clock_access(struct timespec64 *ts)
 }
 
 static clock_access_fn __read_persistent_clock = dummy_clock_access;
-static clock_access_fn __read_boot_clock = dummy_clock_access;
 
 void read_persistent_clock64(struct timespec64 *ts)
 {
 	__read_persistent_clock(ts);
 }
 
-void read_boot_clock64(struct timespec64 *ts)
-{
-	__read_boot_clock(ts);
-}
-
-int __init register_persistent_clock(clock_access_fn read_boot,
-				     clock_access_fn read_persistent)
+int __init register_persistent_clock(clock_access_fn read_persistent)
 {
 	/* Only allow the clockaccess functions to be registered once */
-	if (__read_persistent_clock == dummy_clock_access &&
-	    __read_boot_clock == dummy_clock_access) {
-		if (read_boot)
-			__read_boot_clock = read_boot;
+	if (__read_persistent_clock == dummy_clock_access) {
 		if (read_persistent)
 			__read_persistent_clock = read_persistent;
-
 		return 0;
 	}
 
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 7a4b06049001..a826df3d3814 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -90,6 +90,15 @@
 	.text
 
 ENTRY(arm_copy_from_user)
+#ifdef CONFIG_CPU_SPECTRE
+	get_thread_info r3
+	ldr	r3, [r3, #TI_ADDR_LIMIT]
+	adds	ip, r1, r2	@ ip=addr+size
+	sub	r3, r3, #1	@ addr_limit - 1
+	cmpcc	ip, r3		@ if (addr+size > addr_limit - 1)
+	movcs	r1, #0		@ addr = NULL
+	csdb
+#endif
 
 #include "copy_template.S"
 
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index c46a728df44e..25aac6ee2ab1 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -20,6 +20,7 @@ config ARCH_BCM_IPROC
 	select GPIOLIB
 	select ARM_AMBA
 	select PINCTRL
+	select PCI_DOMAINS if PCI
 	help
 	  This enables support for systems based on Broadcom IPROC architected SoCs.
 	  The IPROC complex contains one or more ARM CPUs along with common
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index e22fb40e34bc..6d5beb11bd96 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -774,7 +774,7 @@ static struct gpiod_lookup_table mmc_gpios_table = {
 		GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_CD_PIN, "cd",
 			    GPIO_ACTIVE_LOW),
 		GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_WP_PIN, "wp",
-			    GPIO_ACTIVE_LOW),
+			    GPIO_ACTIVE_HIGH),
 	},
 };
 
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index d3db306a5a70..f3384e3a675d 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -272,7 +272,7 @@ static int exynos5420_cpu_suspend(unsigned long arg)
 static void exynos_pm_set_wakeup_mask(void)
 {
 	/* Set wake-up mask registers */
-	pmu_raw_writel(exynos_get_eint_wake_mask(), S5P_EINT_WAKEUP_MASK);
+	pmu_raw_writel(exynos_get_eint_wake_mask(), EXYNOS_EINT_WAKEUP_MASK);
 	pmu_raw_writel(exynos_irqwake_intmask & ~(1 << 31), S5P_WAKEUP_MASK);
 }
 
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 69df3620eca5..1c73694c871a 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -109,6 +109,45 @@ void omap5_erratum_workaround_801819(void)
 static inline void omap5_erratum_workaround_801819(void) { }
 #endif
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+/*
+ * Configure ACR and enable ACTLR[0] (Enable invalidates of BTB with
+ * ICIALLU) to activate the workaround for secondary Core.
+ * NOTE: it is assumed that the primary core's configuration is done
+ * by the boot loader (kernel will detect a misconfiguration and complain
+ * if this is not done).
+ *
+ * In General Purpose(GP) devices, ACR bit settings can only be done
+ * by ROM code in "secure world" using the smc call and there is no
+ * option to update the "firmware" on such devices. This also works for
+ * High security(HS) devices, as a backup option in case the
+ * "update" is not done in the "security firmware".
+ */
+static void omap5_secondary_harden_predictor(void)
+{
+	u32 acr, acr_mask;
+
+	asm volatile ("mrc p15, 0, %0, c1, c0, 1" : "=r" (acr));
+
+	/*
+	 * ACTLR[0] (Enable invalidates of BTB with ICIALLU)
+	 */
+	acr_mask = BIT(0);
+
+	/* Do we already have it done.. if yes, skip expensive smc */
+	if ((acr & acr_mask) == acr_mask)
+		return;
+
+	acr |= acr_mask;
+	omap_smc1(OMAP5_DRA7_MON_SET_ACR_INDEX, acr);
+
+	pr_debug("%s: ARM ACR setup for CVE_2017_5715 applied on CPU%d\n",
+		 __func__, smp_processor_id());
+}
+#else
+static inline void omap5_secondary_harden_predictor(void) { }
+#endif
+
 static void omap4_secondary_init(unsigned int cpu)
 {
 	/*
@@ -131,6 +170,8 @@ static void omap4_secondary_init(unsigned int cpu)
 		set_cntfreq();
 		/* Configure ACR to disable streaming WA for 801819 */
 		omap5_erratum_workaround_801819();
+		/* Enable ACR to allow for ICUALLU workaround */
+		omap5_secondary_harden_predictor();
 	}
 
 	/*
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index f4f8f23bda8c..af46d2182533 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -688,7 +688,6 @@ struct platform_nand_data balloon3_nand_pdata = {
 		.chip_delay	= 50,
 	},
 	.ctrl = {
-		.hwcontrol	= 0,
 		.dev_ready	= balloon3_nand_dev_ready,
 		.select_chip	= balloon3_nand_select_chip,
 		.cmd_ctrl	= balloon3_nand_cmd_ctl,
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index d7c9a8476d57..5a16ea74e28a 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -4,6 +4,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/platform_data/i2c-pxa.h>
 
@@ -59,16 +60,6 @@ static struct resource pxamci_resources[] = {
 		.end	= IRQ_MMC,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		.start	= 21,
-		.end	= 21,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		.start	= 22,
-		.end	= 22,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 static u64 pxamci_dmamask = 0xffffffffUL;
@@ -406,16 +397,6 @@ static struct resource pxa_ir_resources[] = {
 		.end	= 0x40700023,
 		.flags  = IORESOURCE_MEM,
 	},
-	[5] = {
-		.start  = 17,
-		.end	= 17,
-		.flags  = IORESOURCE_DMA,
-	},
-	[6] = {
-		.start  = 18,
-		.end	= 18,
-		.flags  = IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa_device_ficp = {
@@ -544,18 +525,6 @@ static struct resource pxa25x_resource_ssp[] = {
 		.end	= IRQ_SSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 13,
-		.end	= 13,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 14,
-		.end	= 14,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa25x_device_ssp = {
@@ -582,18 +551,6 @@ static struct resource pxa25x_resource_nssp[] = {
 		.end	= IRQ_NSSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 15,
-		.end	= 15,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 16,
-		.end	= 16,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa25x_device_nssp = {
@@ -620,18 +577,6 @@ static struct resource pxa25x_resource_assp[] = {
 		.end	= IRQ_ASSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 23,
-		.end	= 23,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 24,
-		.end	= 24,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa25x_device_assp = {
@@ -750,18 +695,6 @@ static struct resource pxa27x_resource_ssp1[] = {
 		.end	= IRQ_SSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 13,
-		.end	= 13,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 14,
-		.end	= 14,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa27x_device_ssp1 = {
@@ -788,18 +721,6 @@ static struct resource pxa27x_resource_ssp2[] = {
 		.end	= IRQ_SSP2,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 15,
-		.end	= 15,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 16,
-		.end	= 16,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa27x_device_ssp2 = {
@@ -826,18 +747,6 @@ static struct resource pxa27x_resource_ssp3[] = {
 		.end	= IRQ_SSP3,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 66,
-		.end	= 66,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 67,
-		.end	= 67,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa27x_device_ssp3 = {
@@ -894,16 +803,6 @@ static struct resource pxa3xx_resources_mci2[] = {
 		.end	= IRQ_MMC2,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		.start	= 93,
-		.end	= 93,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		.start	= 94,
-		.end	= 94,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa3xx_device_mci2 = {
@@ -933,16 +832,6 @@ static struct resource pxa3xx_resources_mci3[] = {
 		.end	= IRQ_MMC3,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		.start	= 100,
-		.end	= 100,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		.start	= 101,
-		.end	= 101,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa3xx_device_mci3 = {
@@ -1020,18 +909,6 @@ static struct resource pxa3xx_resources_nand[] = {
 		.end	= IRQ_NAND,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for Data DMA */
-		.start	= 97,
-		.end	= 97,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for Command DMA */
-		.start	= 99,
-		.end	= 99,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 static u64 pxa3xx_nand_dma_mask = DMA_BIT_MASK(32);
@@ -1065,18 +942,6 @@ static struct resource pxa3xx_resource_ssp4[] = {
 		.end	= IRQ_SSP4,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 2,
-		.end	= 2,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 3,
-		.end	= 3,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 /*
@@ -1202,11 +1067,6 @@ void __init pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info)
 	platform_device_add(pd);
 }
 
-static struct mmp_dma_platdata pxa_dma_pdata = {
-	.dma_channels	= 0,
-	.nb_requestors	= 0,
-};
-
 static struct resource pxa_dma_resource[] = {
 	[0] = {
 		.start	= 0x40000000,
@@ -1233,9 +1093,7 @@ static struct platform_device pxa2xx_pxa_dma = {
 	.resource	= pxa_dma_resource,
 };
 
-void __init pxa2xx_set_dmac_info(int nb_channels, int nb_requestors)
+void __init pxa2xx_set_dmac_info(struct mmp_dma_platdata *dma_pdata)
 {
-	pxa_dma_pdata.dma_channels = nb_channels;
-	pxa_dma_pdata.nb_requestors = nb_requestors;
-	pxa_register_device(&pxa2xx_pxa_dma, &pxa_dma_pdata);
+	pxa_register_device(&pxa2xx_pxa_dma, dma_pdata);
 }
diff --git a/arch/arm/mach-pxa/devices.h b/arch/arm/mach-pxa/devices.h
index 11263f7c455b..498b07bc6a3e 100644
--- a/arch/arm/mach-pxa/devices.h
+++ b/arch/arm/mach-pxa/devices.h
@@ -1,4 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#define PDMA_FILTER_PARAM(_prio, _requestor) (&(struct pxad_param) { \
+	.prio = PXAD_PRIO_##_prio, .drcmr = _requestor })
+struct mmp_dma_platdata;
+
 extern struct platform_device pxa_device_pmu;
 extern struct platform_device pxa_device_mci;
 extern struct platform_device pxa3xx_device_mci2;
@@ -55,7 +59,7 @@ extern struct platform_device pxa3xx_device_gpio;
 extern struct platform_device pxa93x_device_gpio;
 
 void __init pxa_register_device(struct platform_device *dev, void *data);
-void __init pxa2xx_set_dmac_info(int nb_channels, int nb_requestors);
+void __init pxa2xx_set_dmac_info(struct mmp_dma_platdata *dma_pdata);
 
 struct i2c_pxa_platform_data;
 extern void pxa_set_i2c_info(struct i2c_pxa_platform_data *info);
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 49022ad338e9..29be04c6cc48 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -346,7 +346,6 @@ struct platform_nand_data em_x270_nand_platdata = {
 		.chip_delay = 20,
 	},
 	.ctrl = {
-		.hwcontrol = 0,
 		.dev_ready = em_x270_nand_device_ready,
 		.select_chip = 0,
 		.cmd_ctrl = em_x270_nand_cmd_ctl,
diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c
index 9c10248fadcc..4e8c2116808e 100644
--- a/arch/arm/mach-pxa/irq.c
+++ b/arch/arm/mach-pxa/irq.c
@@ -185,7 +185,7 @@ static int pxa_irq_suspend(void)
 {
 	int i;
 
-	for (i = 0; i < pxa_internal_irq_nr / 32; i++) {
+	for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) {
 		void __iomem *base = irq_base(i);
 
 		saved_icmr[i] = __raw_readl(base + ICMR);
@@ -204,7 +204,7 @@ static void pxa_irq_resume(void)
 {
 	int i;
 
-	for (i = 0; i < pxa_internal_irq_nr / 32; i++) {
+	for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) {
 		void __iomem *base = irq_base(i);
 
 		__raw_writel(saved_icmr[i], base + ICMR);
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index ba431fad5c47..ab8808ce7e21 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -16,6 +16,8 @@
  * initialization stuff for PXA machines which can be overridden later if
  * need be.
  */
+#include <linux/dmaengine.h>
+#include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/gpio-pxa.h>
 #include <linux/module.h>
@@ -26,6 +28,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/irq.h>
 #include <linux/irqchip.h>
+#include <linux/platform_data/mmp_dma.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
@@ -201,6 +204,39 @@ static struct platform_device *pxa25x_devices[] __initdata = {
 	&pxa_device_asoc_platform,
 };
 
+static const struct dma_slave_map pxa25x_slave_map[] = {
+	/* PXA25x, PXA27x and PXA3xx common entries */
+	{ "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_out",
+	  PDMA_FILTER_PARAM(LOWEST, 10) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) },
+	{ "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) },
+	{ "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) },
+	{ "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) },
+	{ "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) },
+
+	/* PXA25x specific map */
+	{ "pxa25x-ssp.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa25x-ssp.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa25x-nssp.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa25x-nssp.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa25x-nssp.2", "rx", PDMA_FILTER_PARAM(LOWEST, 23) },
+	{ "pxa25x-nssp.2", "tx", PDMA_FILTER_PARAM(LOWEST, 24) },
+};
+
+static struct mmp_dma_platdata pxa25x_dma_pdata = {
+	.dma_channels	= 16,
+	.nb_requestors	= 40,
+	.slave_map	= pxa25x_slave_map,
+	.slave_map_cnt	= ARRAY_SIZE(pxa25x_slave_map),
+};
+
 static int __init pxa25x_init(void)
 {
 	int ret = 0;
@@ -215,7 +251,7 @@ static int __init pxa25x_init(void)
 		register_syscore_ops(&pxa2xx_mfp_syscore_ops);
 
 		if (!of_have_populated_dt()) {
-			pxa2xx_set_dmac_info(16, 40);
+			pxa2xx_set_dmac_info(&pxa25x_dma_pdata);
 			pxa_register_device(&pxa25x_device_gpio, &pxa25x_gpio_info);
 			ret = platform_add_devices(pxa25x_devices,
 						   ARRAY_SIZE(pxa25x_devices));
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index 0c06f383ad52..5a8990a9313d 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -11,6 +11,8 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/dmaengine.h>
+#include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/gpio-pxa.h>
 #include <linux/module.h>
@@ -23,6 +25,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/platform_data/i2c-pxa.h>
+#include <linux/platform_data/mmp_dma.h>
 
 #include <asm/mach/map.h>
 #include <mach/hardware.h>
@@ -297,6 +300,40 @@ static struct platform_device *devices[] __initdata = {
 	&pxa27x_device_pwm1,
 };
 
+static const struct dma_slave_map pxa27x_slave_map[] = {
+	/* PXA25x, PXA27x and PXA3xx common entries */
+	{ "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_out",
+	  PDMA_FILTER_PARAM(LOWEST, 10) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) },
+	{ "pxa-ssp-dai.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa-ssp-dai.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) },
+	{ "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) },
+	{ "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) },
+	{ "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) },
+	{ "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 66) },
+	{ "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 67) },
+
+	/* PXA27x specific map */
+	{ "pxa2xx-i2s", "rx", PDMA_FILTER_PARAM(LOWEST, 2) },
+	{ "pxa2xx-i2s", "tx", PDMA_FILTER_PARAM(LOWEST, 3) },
+	{ "pxa27x-camera.0", "CI_Y", PDMA_FILTER_PARAM(HIGHEST, 68) },
+	{ "pxa27x-camera.0", "CI_U", PDMA_FILTER_PARAM(HIGHEST, 69) },
+	{ "pxa27x-camera.0", "CI_V", PDMA_FILTER_PARAM(HIGHEST, 70) },
+};
+
+static struct mmp_dma_platdata pxa27x_dma_pdata = {
+	.dma_channels	= 32,
+	.nb_requestors	= 75,
+	.slave_map	= pxa27x_slave_map,
+	.slave_map_cnt	= ARRAY_SIZE(pxa27x_slave_map),
+};
+
 static int __init pxa27x_init(void)
 {
 	int ret = 0;
@@ -313,7 +350,7 @@ static int __init pxa27x_init(void)
 		if (!of_have_populated_dt()) {
 			pxa_register_device(&pxa27x_device_gpio,
 					    &pxa27x_gpio_info);
-			pxa2xx_set_dmac_info(32, 75);
+			pxa2xx_set_dmac_info(&pxa27x_dma_pdata);
 			ret = platform_add_devices(devices,
 						   ARRAY_SIZE(devices));
 		}
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 8c64f93b669b..df9c8970adcf 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -12,6 +12,8 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/dmaengine.h>
+#include <linux/dma/pxa-dma.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -24,6 +26,7 @@
 #include <linux/of.h>
 #include <linux/syscore_ops.h>
 #include <linux/platform_data/i2c-pxa.h>
+#include <linux/platform_data/mmp_dma.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
@@ -421,6 +424,42 @@ static struct platform_device *devices[] __initdata = {
 	&pxa27x_device_pwm1,
 };
 
+static const struct dma_slave_map pxa3xx_slave_map[] = {
+	/* PXA25x, PXA27x and PXA3xx common entries */
+	{ "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_out",
+	  PDMA_FILTER_PARAM(LOWEST, 10) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) },
+	{ "pxa-ssp-dai.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa-ssp-dai.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) },
+	{ "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) },
+	{ "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) },
+	{ "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) },
+	{ "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 66) },
+	{ "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 67) },
+
+	/* PXA3xx specific map */
+	{ "pxa-ssp-dai.3", "rx", PDMA_FILTER_PARAM(LOWEST, 2) },
+	{ "pxa-ssp-dai.3", "tx", PDMA_FILTER_PARAM(LOWEST, 3) },
+	{ "pxa2xx-mci.1", "rx", PDMA_FILTER_PARAM(LOWEST, 93) },
+	{ "pxa2xx-mci.1", "tx", PDMA_FILTER_PARAM(LOWEST, 94) },
+	{ "pxa3xx-nand", "data", PDMA_FILTER_PARAM(LOWEST, 97) },
+	{ "pxa2xx-mci.2", "rx", PDMA_FILTER_PARAM(LOWEST, 100) },
+	{ "pxa2xx-mci.2", "tx", PDMA_FILTER_PARAM(LOWEST, 101) },
+};
+
+static struct mmp_dma_platdata pxa3xx_dma_pdata = {
+	.dma_channels	= 32,
+	.nb_requestors	= 100,
+	.slave_map	= pxa3xx_slave_map,
+	.slave_map_cnt	= ARRAY_SIZE(pxa3xx_slave_map),
+};
+
 static int __init pxa3xx_init(void)
 {
 	int ret = 0;
@@ -456,7 +495,7 @@ static int __init pxa3xx_init(void)
 		if (of_have_populated_dt())
 			return 0;
 
-		pxa2xx_set_dmac_info(32, 100);
+		pxa2xx_set_dmac_info(&pxa3xx_dma_pdata);
 		ret = platform_add_devices(devices, ARRAY_SIZE(devices));
 		if (ret)
 			return ret;
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index 39aef4876ed4..04b2f22c2739 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -212,7 +212,7 @@ static DEFINE_MUTEX(ecard_mutex);
  */
 static void ecard_init_pgtables(struct mm_struct *mm)
 {
-	struct vm_area_struct vma;
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, VM_EXEC);
 
 	/* We want to set up the page tables for the following mapping:
 	 *  Virtual	Physical
@@ -237,9 +237,6 @@ static void ecard_init_pgtables(struct mm_struct *mm)
 
 	memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE));
 
-	vma.vm_flags = VM_EXEC;
-	vma.vm_mm = mm;
-
 	flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE);
 	flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE);
 }
diff --git a/arch/arm/mach-socfpga/Kconfig b/arch/arm/mach-socfpga/Kconfig
index d0f62eacf59d..4adb901dd5eb 100644
--- a/arch/arm/mach-socfpga/Kconfig
+++ b/arch/arm/mach-socfpga/Kconfig
@@ -10,6 +10,7 @@ menuconfig ARCH_SOCFPGA
 	select HAVE_ARM_SCU
 	select HAVE_ARM_TWD if SMP
 	select MFD_SYSCON
+	select PCI_DOMAINS if PCI
 
 if ARCH_SOCFPGA
 config SOCFPGA_SUSPEND
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 96a7b6cf459b..b169e580bf82 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -702,7 +702,6 @@ config ARM_THUMBEE
 
 config ARM_VIRT_EXT
 	bool
-	depends on MMU
 	default y if CPU_V7
 	help
 	  Enable the kernel to make use of the ARM Virtualization
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index c186474422f3..0cc8e04295a4 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -736,20 +736,29 @@ static int __mark_rodata_ro(void *unused)
 	return 0;
 }
 
+static int kernel_set_to_readonly __read_mostly;
+
 void mark_rodata_ro(void)
 {
+	kernel_set_to_readonly = 1;
 	stop_machine(__mark_rodata_ro, NULL, NULL);
 	debug_checkwx();
 }
 
 void set_kernel_text_rw(void)
 {
+	if (!kernel_set_to_readonly)
+		return;
+
 	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false,
 				current->active_mm);
 }
 
 void set_kernel_text_ro(void)
 {
+	if (!kernel_set_to_readonly)
+		return;
+
 	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true,
 				current->active_mm);
 }
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 5dd6c58d653b..7d67c70bbded 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -53,7 +53,8 @@ static inline bool security_extensions_enabled(void)
 {
 	/* Check CPUID Identification Scheme before ID_PFR1 read */
 	if ((read_cpuid_id() & 0x000f0000) == 0x000f0000)
-		return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+		return cpuid_feature_extract(CPUID_EXT_PFR1, 4) ||
+			cpuid_feature_extract(CPUID_EXT_PFR1, 20);
 	return 0;
 }
 
diff --git a/arch/arm/mm/tcm.h b/arch/arm/mm/tcm.h
index 8015ad434a40..24101925fe64 100644
--- a/arch/arm/mm/tcm.h
+++ b/arch/arm/mm/tcm.h
@@ -11,7 +11,7 @@
 void __init tcm_init(void);
 #else
 /* No TCM support, just blank inlines to be optimized out */
-inline void tcm_init(void)
+static inline void tcm_init(void)
 {
 }
 #endif
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 6e8b71613039..f6a62ae44a65 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1844,7 +1844,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		/* there are 2 passes here */
 		bpf_jit_dump(prog->len, image_size, 2, ctx.target);
 
-	set_memory_ro((unsigned long)header, header->pages);
+	bpf_jit_binary_lock_ro(header);
 	prog->bpf_func = (void *)ctx.target;
 	prog->jited = 1;
 	prog->jited_len = image_size;
diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c
index 2438b96004c1..fcc5bfec8bd1 100644
--- a/arch/arm/plat-omap/counter_32k.c
+++ b/arch/arm/plat-omap/counter_32k.c
@@ -110,7 +110,7 @@ int __init omap_init_clocksource_32k(void __iomem *vbase)
 	}
 
 	sched_clock_register(omap_32k_read_sched_clock, 32, 32768);
-	register_persistent_clock(NULL, omap_read_persistent_clock64);
+	register_persistent_clock(omap_read_persistent_clock64);
 	pr_info("OMAP clocksource: 32k_counter at 32768 Hz\n");
 
 	return 0;
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index ba13f793fbce..ed36dcab80f1 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -127,53 +127,6 @@ static int pxa_ssp_probe(struct platform_device *pdev)
 	if (IS_ERR(ssp->clk))
 		return PTR_ERR(ssp->clk);
 
-	if (dev->of_node) {
-		struct of_phandle_args dma_spec;
-		struct device_node *np = dev->of_node;
-		int ret;
-
-		/*
-		 * FIXME: we should allocate the DMA channel from this
-		 * context and pass the channel down to the ssp users.
-		 * For now, we lookup the rx and tx indices manually
-		 */
-
-		/* rx */
-		ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
-						 0, &dma_spec);
-
-		if (ret) {
-			dev_err(dev, "Can't parse dmas property\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_rx = dma_spec.args[0];
-		of_node_put(dma_spec.np);
-
-		/* tx */
-		ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
-						 1, &dma_spec);
-		if (ret) {
-			dev_err(dev, "Can't parse dmas property\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_tx = dma_spec.args[0];
-		of_node_put(dma_spec.np);
-	} else {
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-		if (res == NULL) {
-			dev_err(dev, "no SSP RX DRCMR defined\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_rx = res->start;
-
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-		if (res == NULL) {
-			dev_err(dev, "no SSP TX DRCMR defined\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_tx = res->start;
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res == NULL) {
 		dev_err(dev, "no memory resource defined\n");
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index e90cc8a08186..f8bd523d64d1 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -47,9 +47,6 @@
 			   (unsigned long)(addr) +	\
 			   (size))
 
-/* Used as a marker in ARM_pc to note when we're in a jprobe. */
-#define JPROBE_MAGIC_ADDR		0xffffffff
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -289,8 +286,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				break;
 			case KPROBE_REENTER:
 				/* A nested probe was hit in FIQ, it is a BUG */
-				pr_warn("Unrecoverable kprobe detected at %p.\n",
-					p->addr);
+				pr_warn("Unrecoverable kprobe detected.\n");
+				dump_kprobe(p);
 				/* fall through */
 			default:
 				/* impossible cases */
@@ -303,10 +300,10 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 
 			/*
 			 * If we have no pre-handler or it returned 0, we
-			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry,
-			 * so get out doing nothing more here.
+			 * continue with normal processing. If we have a
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				kcb->kprobe_status = KPROBE_HIT_SS;
@@ -315,20 +312,9 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 					kcb->kprobe_status = KPROBE_HIT_SSDONE;
 					p->post_handler(p, regs, 0);
 				}
-				reset_current_kprobe();
-			}
-		}
-	} else if (cur) {
-		/* We probably hit a jprobe.  Call its break handler. */
-		if (cur->break_handler && cur->break_handler(cur, regs)) {
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			singlestep(cur, regs, kcb);
-			if (cur->post_handler) {
-				kcb->kprobe_status = KPROBE_HIT_SSDONE;
-				cur->post_handler(cur, regs, 0);
 			}
+			reset_current_kprobe();
 		}
-		reset_current_kprobe();
 	} else {
 		/*
 		 * The probe was removed and a race is in progress.
@@ -521,117 +507,6 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	regs->ARM_lr = (unsigned long)&kretprobe_trampoline;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long sp_addr = regs->ARM_sp;
-	long cpsr;
-
-	kcb->jprobe_saved_regs = *regs;
-	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
-	regs->ARM_pc = (long)jp->entry;
-
-	cpsr = regs->ARM_cpsr | PSR_I_BIT;
-#ifdef CONFIG_THUMB2_KERNEL
-	/* Set correct Thumb state in cpsr */
-	if (regs->ARM_pc & 1)
-		cpsr |= PSR_T_BIT;
-	else
-		cpsr &= ~PSR_T_BIT;
-#endif
-	regs->ARM_cpsr = cpsr;
-
-	preempt_disable();
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	__asm__ __volatile__ (
-		/*
-		 * Setup an empty pt_regs. Fill SP and PC fields as
-		 * they're needed by longjmp_break_handler.
-		 *
-		 * We allocate some slack between the original SP and start of
-		 * our fabricated regs. To be precise we want to have worst case
-		 * covered which is STMFD with all 16 regs so we allocate 2 *
-		 * sizeof(struct_pt_regs)).
-		 *
-		 * This is to prevent any simulated instruction from writing
-		 * over the regs when they are accessing the stack.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"sub    r0, %0, %1		\n\t"
-		"mov    sp, r0			\n\t"
-#else
-		"sub    sp, %0, %1		\n\t"
-#endif
-		"ldr    r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
-		"str    %0, [sp, %2]		\n\t"
-		"str    r0, [sp, %3]		\n\t"
-		"mov    r0, sp			\n\t"
-		"bl     kprobe_handler		\n\t"
-
-		/*
-		 * Return to the context saved by setjmp_pre_handler
-		 * and restored by longjmp_break_handler.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"ldr	lr, [sp, %2]		\n\t" /* lr = saved sp */
-		"ldrd	r0, r1, [sp, %5]	\n\t" /* r0,r1 = saved lr,pc */
-		"ldr	r2, [sp, %4]		\n\t" /* r2 = saved psr */
-		"stmdb	lr!, {r0, r1, r2}	\n\t" /* push saved lr and */
-						      /* rfe context */
-		"ldmia	sp, {r0 - r12}		\n\t"
-		"mov	sp, lr			\n\t"
-		"ldr	lr, [sp], #4		\n\t"
-		"rfeia	sp!			\n\t"
-#else
-		"ldr	r0, [sp, %4]		\n\t"
-		"msr	cpsr_cxsf, r0		\n\t"
-		"ldmia	sp, {r0 - pc}		\n\t"
-#endif
-		:
-		: "r" (kcb->jprobe_saved_regs.ARM_sp),
-		  "I" (sizeof(struct pt_regs) * 2),
-		  "J" (offsetof(struct pt_regs, ARM_sp)),
-		  "J" (offsetof(struct pt_regs, ARM_pc)),
-		  "J" (offsetof(struct pt_regs, ARM_cpsr)),
-		  "J" (offsetof(struct pt_regs, ARM_lr))
-		: "memory", "cc");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long stack_addr = kcb->jprobe_saved_regs.ARM_sp;
-	long orig_sp = regs->ARM_sp;
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-
-	if (regs->ARM_pc == JPROBE_MAGIC_ADDR) {
-		if (orig_sp != stack_addr) {
-			struct pt_regs *saved_regs =
-				(struct pt_regs *)kcb->jprobe_saved_regs.ARM_sp;
-			printk("current sp %lx does not match saved sp %lx\n",
-			       orig_sp, stack_addr);
-			printk("Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk("Current registers\n");
-			show_regs(regs);
-			BUG();
-		}
-		*regs = kcb->jprobe_saved_regs;
-		memcpy((void *)stack_addr, kcb->jprobes_stack,
-		       MIN_STACK_SIZE(stack_addr));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
 {
 	return 0;
diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c
index 14db14152909..cc237fa9b90f 100644
--- a/arch/arm/probes/kprobes/test-core.c
+++ b/arch/arm/probes/kprobes/test-core.c
@@ -1461,7 +1461,6 @@ fail:
 	print_registers(&result_regs);
 
 	if (mem) {
-		pr_err("current_stack=%p\n", current_stack);
 		pr_err("expected_memory:\n");
 		print_memory(expected_memory, mem_size);
 		pr_err("result_memory:\n");
diff --git a/arch/arm/vfp/Makefile b/arch/arm/vfp/Makefile
index a81404c09d5d..94516c40ebd3 100644
--- a/arch/arm/vfp/Makefile
+++ b/arch/arm/vfp/Makefile
@@ -8,8 +8,5 @@
 # asflags-y := -DDEBUG
 
 KBUILD_AFLAGS	:=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp -mfloat-abi=soft)
-LDFLAGS		+=--no-warn-mismatch
 
-obj-y			+= vfp.o
-
-vfp-$(CONFIG_VFP)	+= vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o
+obj-y		+= vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 35d0f823e823..dc7e6b50ef67 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -596,13 +596,11 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
 }
 
 /* Sanitise and restore the current VFP state from the provided structures. */
-int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
-			     struct user_vfp_exc __user *ufp_exc)
+int vfp_restore_user_hwstate(struct user_vfp *ufp, struct user_vfp_exc *ufp_exc)
 {
 	struct thread_info *thread = current_thread_info();
 	struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
 	unsigned long fpexc;
-	int err = 0;
 
 	/* Disable VFP to avoid corrupting the new thread state. */
 	vfp_flush_hwstate(thread);
@@ -611,17 +609,16 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
 	 * Copy the floating point registers. There can be unused
 	 * registers see asm/hwcap.h for details.
 	 */
-	err |= __copy_from_user(&hwstate->fpregs, &ufp->fpregs,
-				sizeof(hwstate->fpregs));
+	memcpy(&hwstate->fpregs, &ufp->fpregs, sizeof(hwstate->fpregs));
 	/*
 	 * Copy the status and control register.
 	 */
-	__get_user_error(hwstate->fpscr, &ufp->fpscr, err);
+	hwstate->fpscr = ufp->fpscr;
 
 	/*
 	 * Sanitise and restore the exception registers.
 	 */
-	__get_user_error(fpexc, &ufp_exc->fpexc, err);
+	fpexc = ufp_exc->fpexc;
 
 	/* Ensure the VFP is enabled. */
 	fpexc |= FPEXC_EN;
@@ -630,10 +627,10 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
 	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
 	hwstate->fpexc = fpexc;
 
-	__get_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
-	__get_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
+	hwstate->fpinst = ufp_exc->fpinst;
+	hwstate->fpinst2 = ufp_exc->fpinst2;
 
-	return err ? -EFAULT : 0;
+	return 0;
 }
 
 /*
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 42c090cf0292..260ff5da92ac 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -24,6 +24,7 @@ config ARM64
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
+	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK if !PREEMPT
@@ -42,8 +43,19 @@ config ARM64
 	select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPT
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPT
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPT
+	select ARCH_INLINE_SPIN_TRYLOCK if !PREEMPT
+	select ARCH_INLINE_SPIN_TRYLOCK_BH if !PREEMPT
+	select ARCH_INLINE_SPIN_LOCK if !PREEMPT
+	select ARCH_INLINE_SPIN_LOCK_BH if !PREEMPT
+	select ARCH_INLINE_SPIN_LOCK_IRQ if !PREEMPT
+	select ARCH_INLINE_SPIN_LOCK_IRQSAVE if !PREEMPT
+	select ARCH_INLINE_SPIN_UNLOCK if !PREEMPT
+	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPT
+	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPT
+	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPT
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG
@@ -74,6 +86,7 @@ config ARM64
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
@@ -96,6 +109,7 @@ config ARM64
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
@@ -127,6 +141,7 @@ config ARM64
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
+	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KPROBES
@@ -264,9 +279,6 @@ config ARCH_SUPPORTS_UPROBES
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
 
-config MULTI_IRQ_HANDLER
-	def_bool y
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
@@ -775,6 +787,9 @@ config ARCH_SPARSEMEM_DEFAULT
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool ARCH_SPARSEMEM_ENABLE
 
+config ARCH_FLATMEM_ENABLE
+	def_bool !NUMA
+
 config HAVE_ARCH_PFN_VALID
 	def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
 
@@ -1246,6 +1261,7 @@ config EFI
 	bool "UEFI runtime support"
 	depends on OF && !CPU_BIG_ENDIAN
 	depends on KERNEL_MODE_NEON
+	select ARCH_SUPPORTS_ACPI
 	select LIBFDT
 	select UCS2_STRING
 	select EFI_PARAMS_FROM_FDT
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 45272266dafb..efe61a2e4b5e 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -10,7 +10,7 @@
 #
 # Copyright (C) 1995-2001 by Russell King
 
-LDFLAGS_vmlinux	:=-p --no-undefined -X
+LDFLAGS_vmlinux	:=--no-undefined -X
 CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 GZFLAGS		:=-9
 
@@ -60,15 +60,16 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__AARCH64EB__
 AS		+= -EB
-LD		+= -EB
-LDFLAGS		+= -maarch64linuxb
+# Prefer the baremetal ELF build target, but not all toolchains include
+# it so fall back to the standard linux version if needed.
+LDFLAGS		+= -EB $(call ld-option, -maarch64elfb, -maarch64linuxb)
 UTS_MACHINE	:= aarch64_be
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 CHECKFLAGS	+= -D__AARCH64EL__
 AS		+= -EL
-LD		+= -EL
-LDFLAGS		+= -maarch64linux
+# Same as above, prefer ELF but fall back to linux target if needed.
+LDFLAGS		+= -EL $(call ld-option, -maarch64elf, -maarch64linux)
 UTS_MACHINE	:= aarch64
 endif
 
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index e6b059378dc0..67dac595dc72 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -309,8 +309,7 @@
 			interrupts = <0 99 4>;
 			resets = <&rst SPIM0_RESET>;
 			reg-io-width = <4>;
-			num-chipselect = <4>;
-			bus-num = <0>;
+			num-cs = <4>;
 			status = "disabled";
 		};
 
@@ -322,8 +321,7 @@
 			interrupts = <0 100 4>;
 			resets = <&rst SPIM1_RESET>;
 			reg-io-width = <4>;
-			num-chipselect = <4>;
-			bus-num = <0>;
+			num-cs = <4>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
index 4b3331fbfe39..dff9b15eb3c0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
@@ -66,9 +66,22 @@
 
 &ethmac {
 	status = "okay";
-	phy-mode = "rgmii";
 	pinctrl-0 = <&eth_rgmii_y_pins>;
 	pinctrl-names = "default";
+	phy-handle = <&eth_phy0>;
+	phy-mode = "rgmii";
+
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		eth_phy0: ethernet-phy@0 {
+			/* Realtek RTL8211F (0x001cc916) */
+			reg = <0>;
+			eee-broken-1000t;
+		};
+	};
 };
 
 &uart_A {
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index fee87737a201..67d7115e4eff 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -132,7 +132,7 @@
 
 			sd_emmc_b: sd@5000 {
 				compatible = "amlogic,meson-axg-mmc";
-				reg = <0x0 0x5000 0x0 0x2000>;
+				reg = <0x0 0x5000 0x0 0x800>;
 				interrupts = <GIC_SPI 217 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 				clocks = <&clkc CLKID_SD_EMMC_B>,
@@ -144,7 +144,7 @@
 
 			sd_emmc_c: mmc@7000 {
 				compatible = "amlogic,meson-axg-mmc";
-				reg = <0x0 0x7000 0x0 0x2000>;
+				reg = <0x0 0x7000 0x0 0x800>;
 				interrupts = <GIC_SPI 218 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 				clocks = <&clkc CLKID_SD_EMMC_C>,
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 3c31e21cbed7..b8dc4dbb391b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -35,6 +35,12 @@
 			no-map;
 		};
 
+		/* Alternate 3 MiB reserved for ARM Trusted Firmware (BL31) */
+		secmon_reserved_alt: secmon@5000000 {
+			reg = <0x0 0x05000000 0x0 0x300000>;
+			no-map;
+		};
+
 		linux,cma {
 			compatible = "shared-dma-pool";
 			reusable;
@@ -457,21 +463,21 @@
 
 			sd_emmc_a: mmc@70000 {
 				compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
-				reg = <0x0 0x70000 0x0 0x2000>;
+				reg = <0x0 0x70000 0x0 0x800>;
 				interrupts = <GIC_SPI 216 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
 			sd_emmc_b: mmc@72000 {
 				compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
-				reg = <0x0 0x72000 0x0 0x2000>;
+				reg = <0x0 0x72000 0x0 0x800>;
 				interrupts = <GIC_SPI 217 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
 			sd_emmc_c: mmc@74000 {
 				compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
-				reg = <0x0 0x74000 0x0 0x2000>;
+				reg = <0x0 0x74000 0x0 0x800>;
 				interrupts = <GIC_SPI 218 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-mali.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-mali.dtsi
index eb327664a4d8..6aaafff674f9 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-mali.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-mali.dtsi
@@ -6,7 +6,7 @@
 
 &apb {
 	mali: gpu@c0000 {
-		compatible = "amlogic,meson-gxbb-mali", "arm,mali-450";
+		compatible = "amlogic,meson-gxl-mali", "arm,mali-450";
 		reg = <0x0 0xc0000 0x0 0x40000>;
 		interrupts = <GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 161 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
index 3e3eb31748a3..f63bceb88caa 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
@@ -234,9 +234,6 @@
 
 	bus-width = <4>;
 	cap-sd-highspeed;
-	sd-uhs-sdr12;
-	sd-uhs-sdr25;
-	sd-uhs-sdr50;
 	max-frequency = <100000000>;
 	disable-wp;
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
index 0cfd701809de..a1b31013ab6e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
@@ -189,3 +189,10 @@
 &usb0 {
 	status = "okay";
 };
+
+&usb2_phy0 {
+	/*
+	 * HDMI_5V is also used as supply for the USB VBUS.
+	 */
+	phy-supply = <&hdmi_5v>;
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 27538eea547b..c87a80e9bcc6 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -13,14 +13,6 @@
 / {
 	compatible = "amlogic,meson-gxl";
 
-	reserved-memory {
-		/* Alternate 3 MiB reserved for ARM Trusted Firmware (BL31) */
-		secmon_reserved_alt: secmon@5000000 {
-			reg = <0x0 0x05000000 0x0 0x300000>;
-			no-map;
-		};
-	};
-
 	soc {
 		usb0: usb@c9000000 {
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
index 4a2a6af8e752..4057197048dc 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
@@ -118,7 +118,7 @@
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 281 IRQ_TYPE_NONE>;
+		interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 281 IRQ_TYPE_LEVEL_HIGH>;
 
 		linux,pci-domain = <0>;
 
@@ -149,7 +149,7 @@
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 305 IRQ_TYPE_NONE>;
+		interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
 
 		linux,pci-domain = <4>;
 
@@ -566,7 +566,7 @@
 			reg = <0x66080000 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 394 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 394 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
@@ -594,7 +594,7 @@
 			reg = <0x660b0000 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 395 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 395 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
diff --git a/arch/arm64/boot/dts/broadcom/stingray/bcm958742k.dts b/arch/arm64/boot/dts/broadcom/stingray/bcm958742k.dts
index eb6f08cdbd79..77efa28c4dd5 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/bcm958742k.dts
+++ b/arch/arm64/boot/dts/broadcom/stingray/bcm958742k.dts
@@ -43,6 +43,10 @@
 	enet-phy-lane-swap;
 };
 
+&sdio0 {
+	mmc-ddr-1_8v;
+};
+
 &uart2 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/broadcom/stingray/bcm958742t.dts b/arch/arm64/boot/dts/broadcom/stingray/bcm958742t.dts
index 5084b037320f..55ba495ef56e 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/bcm958742t.dts
+++ b/arch/arm64/boot/dts/broadcom/stingray/bcm958742t.dts
@@ -42,3 +42,7 @@
 &gphy0 {
 	enet-phy-lane-swap;
 };
+
+&sdio0 {
+	mmc-ddr-1_8v;
+};
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
index 99aaff0b6d72..b203152ad67c 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
@@ -409,7 +409,7 @@
 			reg = <0x000b0000 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 177 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 177 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
@@ -453,7 +453,7 @@
 			reg = <0x000e0000 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 178 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 178 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
diff --git a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
index c6999624ed8a..68c5a6c819ae 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
@@ -585,6 +585,8 @@
 	vmmc-supply = <&wlan_en>;
 	ti,non-removable;
 	non-removable;
+	cap-power-off-card;
+	keep-power-in-suspend;
 	#address-cells = <0x1>;
 	#size-cells = <0x0>;
 	status = "ok";
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index edb4ee0b8896..7f12624f6c8e 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -322,6 +322,8 @@
 		dwmmc_2: dwmmc2@f723f000 {
 			bus-width = <0x4>;
 			non-removable;
+			cap-power-off-card;
+			keep-power-in-suspend;
 			vmmc-supply = <&reg_vdd_3v3>;
 			mmc-pwrseq = <&wl1835_pwrseq>;
 
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
index 7dabe25f6774..1c6ff8197a88 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
@@ -149,7 +149,7 @@
 
 		CP110_LABEL(icu): interrupt-controller@1e0000 {
 			compatible = "marvell,cp110-icu";
-			reg = <0x1e0000 0x10>;
+			reg = <0x1e0000 0x440>;
 			#interrupt-cells = <3>;
 			interrupt-controller;
 			msi-parent = <&gicp>;
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
index 0f829db33efe..4d5ef01f43a3 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
@@ -75,7 +75,7 @@
 
 		serial@75b1000 {
 			label = "LS-UART0";
-			status = "okay";
+			status = "disabled";
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&blsp2_uart2_4pins_default>;
 			pinctrl-1 = <&blsp2_uart2_4pins_sleep>;
diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index 650f356f69ca..c2625d15a8c0 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -1191,14 +1191,14 @@
 
 				port@0 {
 					reg = <0>;
-					etf_out: endpoint {
+					etf_in: endpoint {
 						slave-mode;
 						remote-endpoint = <&funnel0_out>;
 					};
 				};
 				port@1 {
 					reg = <0>;
-					etf_in: endpoint {
+					etf_out: endpoint {
 						remote-endpoint = <&replicator_in>;
 					};
 				};
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld11-global.dts b/arch/arm64/boot/dts/socionext/uniphier-ld11-global.dts
index 9b4dc41703e3..ae3b5adf32df 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld11-global.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld11-global.dts
@@ -54,7 +54,7 @@
 	sound {
 		compatible = "audio-graph-card";
 		label = "UniPhier LD11";
-		widgets = "Headphone", "Headphone Jack";
+		widgets = "Headphone", "Headphones";
 		dais = <&i2s_port2
 			&i2s_port3
 			&i2s_port4
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20-global.dts b/arch/arm64/boot/dts/socionext/uniphier-ld20-global.dts
index fe6608ea3277..7919233c9ce2 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20-global.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20-global.dts
@@ -54,7 +54,7 @@
 	sound {
 		compatible = "audio-graph-card";
 		label = "UniPhier LD20";
-		widgets = "Headphone", "Headphone Jack";
+		widgets = "Headphone", "Headphones";
 		dais = <&i2s_port2
 			&i2s_port3
 			&i2s_port4
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 3cfa8ca26738..f9a186f6af8a 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -47,6 +47,7 @@ CONFIG_ARCH_MVEBU=y
 CONFIG_ARCH_QCOM=y
 CONFIG_ARCH_ROCKCHIP=y
 CONFIG_ARCH_SEATTLE=y
+CONFIG_ARCH_SYNQUACER=y
 CONFIG_ARCH_RENESAS=y
 CONFIG_ARCH_R8A7795=y
 CONFIG_ARCH_R8A7796=y
@@ -58,7 +59,6 @@ CONFIG_ARCH_R8A77995=y
 CONFIG_ARCH_STRATIX10=y
 CONFIG_ARCH_TEGRA=y
 CONFIG_ARCH_SPRD=y
-CONFIG_ARCH_SYNQUACER=y
 CONFIG_ARCH_THUNDER=y
 CONFIG_ARCH_THUNDER2=y
 CONFIG_ARCH_UNIPHIER=y
@@ -67,25 +67,23 @@ CONFIG_ARCH_XGENE=y
 CONFIG_ARCH_ZX=y
 CONFIG_ARCH_ZYNQMP=y
 CONFIG_PCI=y
-CONFIG_HOTPLUG_PCI_PCIE=y
 CONFIG_PCI_IOV=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_ACPI=y
-CONFIG_PCI_LAYERSCAPE=y
-CONFIG_PCI_HISI=y
-CONFIG_PCIE_QCOM=y
-CONFIG_PCIE_KIRIN=y
-CONFIG_PCIE_ARMADA_8K=y
-CONFIG_PCIE_HISI_STB=y
 CONFIG_PCI_AARDVARK=y
 CONFIG_PCI_TEGRA=y
 CONFIG_PCIE_RCAR=y
-CONFIG_PCIE_ROCKCHIP=y
-CONFIG_PCIE_ROCKCHIP_HOST=m
 CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCI_XGENE=y
 CONFIG_PCI_HOST_THUNDER_PEM=y
 CONFIG_PCI_HOST_THUNDER_ECAM=y
+CONFIG_PCIE_ROCKCHIP_HOST=m
+CONFIG_PCI_LAYERSCAPE=y
+CONFIG_PCI_HISI=y
+CONFIG_PCIE_QCOM=y
+CONFIG_PCIE_ARMADA_8K=y
+CONFIG_PCIE_KIRIN=y
+CONFIG_PCIE_HISI_STB=y
 CONFIG_ARM64_VA_BITS_48=y
 CONFIG_SCHED_MC=y
 CONFIG_NUMA=y
@@ -104,8 +102,6 @@ CONFIG_HIBERNATION=y
 CONFIG_WQ_POWER_EFFICIENT_DEFAULT=y
 CONFIG_ARM_CPUIDLE=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_GOV_ATTR_SET=y
-CONFIG_CPU_FREQ_GOV_COMMON=y
 CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
@@ -113,11 +109,11 @@ CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
 CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
 CONFIG_CPUFREQ_DT=y
+CONFIG_ACPI_CPPC_CPUFREQ=m
 CONFIG_ARM_ARMADA_37XX_CPUFREQ=y
 CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
 CONFIG_ARM_SCPI_CPUFREQ=y
 CONFIG_ARM_TEGRA186_CPUFREQ=y
-CONFIG_ACPI_CPPC_CPUFREQ=m
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -236,11 +232,6 @@ CONFIG_SMSC911X=y
 CONFIG_SNI_AVE=y
 CONFIG_SNI_NETSEC=y
 CONFIG_STMMAC_ETH=m
-CONFIG_DWMAC_IPQ806X=m
-CONFIG_DWMAC_MESON=m
-CONFIG_DWMAC_ROCKCHIP=m
-CONFIG_DWMAC_SUNXI=m
-CONFIG_DWMAC_SUN8I=m
 CONFIG_MDIO_BUS_MUX_MMIOREG=y
 CONFIG_AT803X_PHY=m
 CONFIG_MARVELL_PHY=m
@@ -269,8 +260,8 @@ CONFIG_WL18XX=m
 CONFIG_WLCORE_SDIO=m
 CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_ADC=m
-CONFIG_KEYBOARD_CROS_EC=y
 CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_CROS_EC=y
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_TOUCHSCREEN_ATMEL_MXT=m
 CONFIG_INPUT_MISC=y
@@ -296,17 +287,13 @@ CONFIG_SERIAL_SAMSUNG=y
 CONFIG_SERIAL_SAMSUNG_CONSOLE=y
 CONFIG_SERIAL_TEGRA=y
 CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=11
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
 CONFIG_SERIAL_MSM=y
 CONFIG_SERIAL_MSM_CONSOLE=y
 CONFIG_SERIAL_XILINX_PS_UART=y
 CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
 CONFIG_SERIAL_MVEBU_UART=y
 CONFIG_SERIAL_DEV_BUS=y
-CONFIG_SERIAL_DEV_CTRL_TTYPORT=y
 CONFIG_VIRTIO_CONSOLE=y
-CONFIG_I2C_HID=m
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MUX=y
 CONFIG_I2C_MUX_PCA954x=y
@@ -325,26 +312,26 @@ CONFIG_I2C_RCAR=y
 CONFIG_I2C_CROS_EC_TUNNEL=y
 CONFIG_SPI=y
 CONFIG_SPI_ARMADA_3700=y
-CONFIG_SPI_MESON_SPICC=m
-CONFIG_SPI_MESON_SPIFC=m
 CONFIG_SPI_BCM2835=m
 CONFIG_SPI_BCM2835AUX=m
+CONFIG_SPI_MESON_SPICC=m
+CONFIG_SPI_MESON_SPIFC=m
 CONFIG_SPI_ORION=y
 CONFIG_SPI_PL022=y
-CONFIG_SPI_QUP=y
 CONFIG_SPI_ROCKCHIP=y
+CONFIG_SPI_QUP=y
 CONFIG_SPI_S3C64XX=y
 CONFIG_SPI_SPIDEV=m
 CONFIG_SPMI=y
-CONFIG_PINCTRL_IPQ8074=y
 CONFIG_PINCTRL_SINGLE=y
 CONFIG_PINCTRL_MAX77620=y
+CONFIG_PINCTRL_IPQ8074=y
 CONFIG_PINCTRL_MSM8916=y
 CONFIG_PINCTRL_MSM8994=y
 CONFIG_PINCTRL_MSM8996=y
-CONFIG_PINCTRL_MT7622=y
 CONFIG_PINCTRL_QDF2XXX=y
 CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
+CONFIG_PINCTRL_MT7622=y
 CONFIG_GPIO_DWAPB=y
 CONFIG_GPIO_MB86S7X=y
 CONFIG_GPIO_PL061=y
@@ -368,13 +355,13 @@ CONFIG_SENSORS_INA2XX=m
 CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y
 CONFIG_CPU_THERMAL=y
 CONFIG_THERMAL_EMULATION=y
+CONFIG_ROCKCHIP_THERMAL=m
+CONFIG_RCAR_GEN3_THERMAL=y
 CONFIG_ARMADA_THERMAL=y
 CONFIG_BRCMSTB_THERMAL=m
 CONFIG_EXYNOS_THERMAL=y
-CONFIG_RCAR_GEN3_THERMAL=y
-CONFIG_QCOM_TSENS=y
-CONFIG_ROCKCHIP_THERMAL=m
 CONFIG_TEGRA_BPMP_THERMAL=m
+CONFIG_QCOM_TSENS=y
 CONFIG_UNIPHIER_THERMAL=y
 CONFIG_WATCHDOG=y
 CONFIG_S3C2410_WATCHDOG=y
@@ -395,9 +382,9 @@ CONFIG_MFD_MAX77620=y
 CONFIG_MFD_SPMI_PMIC=y
 CONFIG_MFD_RK808=y
 CONFIG_MFD_SEC_CORE=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_AXP20X=y
 CONFIG_REGULATOR_FAN53555=y
-CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_GPIO=y
 CONFIG_REGULATOR_HI6421V530=y
 CONFIG_REGULATOR_HI655X=y
@@ -407,16 +394,15 @@ CONFIG_REGULATOR_QCOM_SMD_RPM=y
 CONFIG_REGULATOR_QCOM_SPMI=y
 CONFIG_REGULATOR_RK808=y
 CONFIG_REGULATOR_S2MPS11=y
+CONFIG_RC_CORE=m
+CONFIG_RC_DECODERS=y
+CONFIG_RC_DEVICES=y
+CONFIG_IR_MESON=m
 CONFIG_MEDIA_SUPPORT=m
 CONFIG_MEDIA_CAMERA_SUPPORT=y
 CONFIG_MEDIA_ANALOG_TV_SUPPORT=y
 CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y
 CONFIG_MEDIA_CONTROLLER=y
-CONFIG_MEDIA_RC_SUPPORT=y
-CONFIG_RC_CORE=m
-CONFIG_RC_DEVICES=y
-CONFIG_RC_DECODERS=y
-CONFIG_IR_MESON=m
 CONFIG_VIDEO_V4L2_SUBDEV_API=y
 # CONFIG_DVB_NET is not set
 CONFIG_V4L_MEM2MEM_DRIVERS=y
@@ -441,8 +427,7 @@ CONFIG_ROCKCHIP_DW_HDMI=y
 CONFIG_ROCKCHIP_DW_MIPI_DSI=y
 CONFIG_ROCKCHIP_INNO_HDMI=y
 CONFIG_DRM_RCAR_DU=m
-CONFIG_DRM_RCAR_LVDS=y
-CONFIG_DRM_RCAR_VSP=y
+CONFIG_DRM_RCAR_LVDS=m
 CONFIG_DRM_TEGRA=m
 CONFIG_DRM_PANEL_SIMPLE=m
 CONFIG_DRM_I2C_ADV7511=m
@@ -455,7 +440,6 @@ CONFIG_FB_ARMCLCD=y
 CONFIG_BACKLIGHT_GENERIC=m
 CONFIG_BACKLIGHT_PWM=m
 CONFIG_BACKLIGHT_LP855X=m
-CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
@@ -468,6 +452,7 @@ CONFIG_SND_SOC_RCAR=m
 CONFIG_SND_SOC_AK4613=m
 CONFIG_SND_SIMPLE_CARD=m
 CONFIG_SND_AUDIO_GRAPH_CARD=m
+CONFIG_I2C_HID=m
 CONFIG_USB=y
 CONFIG_USB_OTG=y
 CONFIG_USB_XHCI_HCD=y
@@ -501,12 +486,12 @@ CONFIG_MMC_BLOCK_MINORS=32
 CONFIG_MMC_ARMMMCI=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_ACPI=y
-CONFIG_MMC_SDHCI_F_SDH30=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_OF_ARASAN=y
 CONFIG_MMC_SDHCI_OF_ESDHC=y
 CONFIG_MMC_SDHCI_CADENCE=y
 CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_MMC_SDHCI_F_SDH30=y
 CONFIG_MMC_MESON_GX=y
 CONFIG_MMC_SDHCI_MSM=y
 CONFIG_MMC_SPI=y
@@ -524,11 +509,11 @@ CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_GPIO=y
 CONFIG_LEDS_PWM=y
 CONFIG_LEDS_SYSCON=y
+CONFIG_LEDS_TRIGGER_DISK=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_CPU=y
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_LEDS_TRIGGER_PANIC=y
-CONFIG_LEDS_TRIGGER_DISK=y
 CONFIG_EDAC=y
 CONFIG_EDAC_GHES=y
 CONFIG_RTC_CLASS=y
@@ -537,13 +522,13 @@ CONFIG_RTC_DRV_RK808=m
 CONFIG_RTC_DRV_S5M=y
 CONFIG_RTC_DRV_DS3232=y
 CONFIG_RTC_DRV_EFI=y
+CONFIG_RTC_DRV_CROS_EC=y
 CONFIG_RTC_DRV_S3C=y
 CONFIG_RTC_DRV_PL031=y
 CONFIG_RTC_DRV_SUN6I=y
 CONFIG_RTC_DRV_ARMADA38X=y
 CONFIG_RTC_DRV_TEGRA=y
 CONFIG_RTC_DRV_XGENE=y
-CONFIG_RTC_DRV_CROS_EC=y
 CONFIG_DMADEVICES=y
 CONFIG_DMA_BCM2835=m
 CONFIG_K3_DMA=y
@@ -579,7 +564,6 @@ CONFIG_HWSPINLOCK_QCOM=y
 CONFIG_ARM_MHU=y
 CONFIG_PLATFORM_MHU=y
 CONFIG_BCM2835_MBOX=y
-CONFIG_HI6220_MBOX=y
 CONFIG_QCOM_APCS_IPC=y
 CONFIG_ROCKCHIP_IOMMU=y
 CONFIG_TEGRA_IOMMU_SMMU=y
@@ -602,7 +586,6 @@ CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
 CONFIG_EXTCON_USB_GPIO=y
 CONFIG_EXTCON_USBC_CROS_EC=y
 CONFIG_MEMORY=y
-CONFIG_TEGRA_MC=y
 CONFIG_IIO=y
 CONFIG_EXYNOS_ADC=y
 CONFIG_ROCKCHIP_SARADC=m
@@ -618,27 +601,27 @@ CONFIG_PWM_RCAR=m
 CONFIG_PWM_ROCKCHIP=y
 CONFIG_PWM_SAMSUNG=y
 CONFIG_PWM_TEGRA=m
+CONFIG_PHY_XGENE=y
+CONFIG_PHY_SUN4I_USB=y
+CONFIG_PHY_HI6220_USB=y
 CONFIG_PHY_HISTB_COMBPHY=y
 CONFIG_PHY_HISI_INNO_USB2=y
-CONFIG_PHY_RCAR_GEN3_USB2=y
-CONFIG_PHY_RCAR_GEN3_USB3=m
-CONFIG_PHY_HI6220_USB=y
-CONFIG_PHY_QCOM_USB_HS=y
-CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_MVEBU_CP110_COMPHY=y
 CONFIG_PHY_QCOM_QMP=m
-CONFIG_PHY_ROCKCHIP_INNO_USB2=y
+CONFIG_PHY_QCOM_USB_HS=y
+CONFIG_PHY_RCAR_GEN3_USB2=y
+CONFIG_PHY_RCAR_GEN3_USB3=m
 CONFIG_PHY_ROCKCHIP_EMMC=y
+CONFIG_PHY_ROCKCHIP_INNO_USB2=y
 CONFIG_PHY_ROCKCHIP_PCIE=m
 CONFIG_PHY_ROCKCHIP_TYPEC=y
-CONFIG_PHY_XGENE=y
 CONFIG_PHY_TEGRA_XUSB=y
 CONFIG_QCOM_L2_PMU=y
 CONFIG_QCOM_L3_PMU=y
-CONFIG_MESON_EFUSE=m
 CONFIG_QCOM_QFPROM=y
 CONFIG_ROCKCHIP_EFUSE=y
 CONFIG_UNIPHIER_EFUSE=y
+CONFIG_MESON_EFUSE=m
 CONFIG_TEE=y
 CONFIG_OPTEE=y
 CONFIG_ARM_SCPI_PROTOCOL=y
@@ -647,7 +630,6 @@ CONFIG_EFI_CAPSULE_LOADER=y
 CONFIG_ACPI=y
 CONFIG_ACPI_APEI=y
 CONFIG_ACPI_APEI_GHES=y
-CONFIG_ACPI_APEI_PCIEAER=y
 CONFIG_ACPI_APEI_MEMORY_FAILURE=y
 CONFIG_ACPI_APEI_EINJ=y
 CONFIG_EXT2_FS=y
@@ -682,7 +664,6 @@ CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
-CONFIG_LOCKUP_DETECTOR=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
 # CONFIG_FTRACE is not set
@@ -691,20 +672,15 @@ CONFIG_SECURITY=y
 CONFIG_CRYPTO_ECHAINIV=y
 CONFIG_CRYPTO_ANSI_CPRNG=y
 CONFIG_ARM64_CRYPTO=y
-CONFIG_CRYPTO_SHA256_ARM64=m
-CONFIG_CRYPTO_SHA512_ARM64=m
 CONFIG_CRYPTO_SHA1_ARM64_CE=y
 CONFIG_CRYPTO_SHA2_ARM64_CE=y
+CONFIG_CRYPTO_SHA512_ARM64_CE=m
+CONFIG_CRYPTO_SHA3_ARM64=m
+CONFIG_CRYPTO_SM3_ARM64_CE=m
 CONFIG_CRYPTO_GHASH_ARM64_CE=y
 CONFIG_CRYPTO_CRCT10DIF_ARM64_CE=m
 CONFIG_CRYPTO_CRC32_ARM64_CE=m
-CONFIG_CRYPTO_AES_ARM64=m
-CONFIG_CRYPTO_AES_ARM64_CE=m
 CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
 CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
-CONFIG_CRYPTO_AES_ARM64_NEON_BLK=m
 CONFIG_CRYPTO_CHACHA20_NEON=m
 CONFIG_CRYPTO_AES_ARM64_BS=m
-CONFIG_CRYPTO_SHA512_ARM64_CE=m
-CONFIG_CRYPTO_SHA3_ARM64=m
-CONFIG_CRYPTO_SM3_ARM64_CE=m
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index 88f5aef7934c..e3a375c4cb83 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -19,33 +19,24 @@
 	 *			     u32 *macp, u8 const rk[], u32 rounds);
 	 */
 ENTRY(ce_aes_ccm_auth_data)
-	frame_push	7
-
-	mov	x19, x0
-	mov	x20, x1
-	mov	x21, x2
-	mov	x22, x3
-	mov	x23, x4
-	mov	x24, x5
-
-	ldr	w25, [x22]			/* leftover from prev round? */
+	ldr	w8, [x3]			/* leftover from prev round? */
 	ld1	{v0.16b}, [x0]			/* load mac */
-	cbz	w25, 1f
-	sub	w25, w25, #16
+	cbz	w8, 1f
+	sub	w8, w8, #16
 	eor	v1.16b, v1.16b, v1.16b
-0:	ldrb	w7, [x20], #1			/* get 1 byte of input */
-	subs	w21, w21, #1
-	add	w25, w25, #1
+0:	ldrb	w7, [x1], #1			/* get 1 byte of input */
+	subs	w2, w2, #1
+	add	w8, w8, #1
 	ins	v1.b[0], w7
 	ext	v1.16b, v1.16b, v1.16b, #1	/* rotate in the input bytes */
 	beq	8f				/* out of input? */
-	cbnz	w25, 0b
+	cbnz	w8, 0b
 	eor	v0.16b, v0.16b, v1.16b
-1:	ld1	{v3.4s}, [x23]			/* load first round key */
-	prfm	pldl1strm, [x20]
-	cmp	w24, #12			/* which key size? */
-	add	x6, x23, #16
-	sub	w7, w24, #2			/* modified # of rounds */
+1:	ld1	{v3.4s}, [x4]			/* load first round key */
+	prfm	pldl1strm, [x1]
+	cmp	w5, #12				/* which key size? */
+	add	x6, x4, #16
+	sub	w7, w5, #2			/* modified # of rounds */
 	bmi	2f
 	bne	5f
 	mov	v5.16b, v3.16b
@@ -64,43 +55,33 @@ ENTRY(ce_aes_ccm_auth_data)
 	ld1	{v5.4s}, [x6], #16		/* load next round key */
 	bpl	3b
 	aese	v0.16b, v4.16b
-	subs	w21, w21, #16			/* last data? */
+	subs	w2, w2, #16			/* last data? */
 	eor	v0.16b, v0.16b, v5.16b		/* final round */
 	bmi	6f
-	ld1	{v1.16b}, [x20], #16		/* load next input block */
+	ld1	{v1.16b}, [x1], #16		/* load next input block */
 	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
-	beq	6f
-
-	if_will_cond_yield_neon
-	st1	{v0.16b}, [x19]			/* store mac */
-	do_cond_yield_neon
-	ld1	{v0.16b}, [x19]			/* reload mac */
-	endif_yield_neon
-
-	b	1b
-6:	st1	{v0.16b}, [x19]			/* store mac */
+	bne	1b
+6:	st1	{v0.16b}, [x0]			/* store mac */
 	beq	10f
-	adds	w21, w21, #16
+	adds	w2, w2, #16
 	beq	10f
-	mov	w25, w21
-7:	ldrb	w7, [x20], #1
+	mov	w8, w2
+7:	ldrb	w7, [x1], #1
 	umov	w6, v0.b[0]
 	eor	w6, w6, w7
-	strb	w6, [x19], #1
-	subs	w21, w21, #1
+	strb	w6, [x0], #1
+	subs	w2, w2, #1
 	beq	10f
 	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
 	b	7b
-8:	mov	w7, w25
-	add	w25, w25, #16
+8:	mov	w7, w8
+	add	w8, w8, #16
 9:	ext	v1.16b, v1.16b, v1.16b, #1
 	adds	w7, w7, #1
 	bne	9b
 	eor	v0.16b, v0.16b, v1.16b
-	st1	{v0.16b}, [x19]
-10:	str	w25, [x22]
-
-	frame_pop
+	st1	{v0.16b}, [x0]
+10:	str	w8, [x3]
 	ret
 ENDPROC(ce_aes_ccm_auth_data)
 
@@ -145,29 +126,19 @@ ENTRY(ce_aes_ccm_final)
 ENDPROC(ce_aes_ccm_final)
 
 	.macro	aes_ccm_do_crypt,enc
-	frame_push	8
-
-	mov	x19, x0
-	mov	x20, x1
-	mov	x21, x2
-	mov	x22, x3
-	mov	x23, x4
-	mov	x24, x5
-	mov	x25, x6
-
-	ldr	x26, [x25, #8]			/* load lower ctr */
-	ld1	{v0.16b}, [x24]			/* load mac */
-CPU_LE(	rev	x26, x26		)	/* keep swabbed ctr in reg */
+	ldr	x8, [x6, #8]			/* load lower ctr */
+	ld1	{v0.16b}, [x5]			/* load mac */
+CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 0:	/* outer loop */
-	ld1	{v1.8b}, [x25]			/* load upper ctr */
-	prfm	pldl1strm, [x20]
-	add	x26, x26, #1
-	rev	x9, x26
-	cmp	w23, #12			/* which key size? */
-	sub	w7, w23, #2			/* get modified # of rounds */
+	ld1	{v1.8b}, [x6]			/* load upper ctr */
+	prfm	pldl1strm, [x1]
+	add	x8, x8, #1
+	rev	x9, x8
+	cmp	w4, #12				/* which key size? */
+	sub	w7, w4, #2			/* get modified # of rounds */
 	ins	v1.d[1], x9			/* no carry in lower ctr */
-	ld1	{v3.4s}, [x22]			/* load first round key */
-	add	x10, x22, #16
+	ld1	{v3.4s}, [x3]			/* load first round key */
+	add	x10, x3, #16
 	bmi	1f
 	bne	4f
 	mov	v5.16b, v3.16b
@@ -194,9 +165,9 @@ CPU_LE(	rev	x26, x26		)	/* keep swabbed ctr in reg */
 	bpl	2b
 	aese	v0.16b, v4.16b
 	aese	v1.16b, v4.16b
-	subs	w21, w21, #16
-	bmi	7f				/* partial block? */
-	ld1	{v2.16b}, [x20], #16		/* load next input block */
+	subs	w2, w2, #16
+	bmi	6f				/* partial block? */
+	ld1	{v2.16b}, [x1], #16		/* load next input block */
 	.if	\enc == 1
 	eor	v2.16b, v2.16b, v5.16b		/* final round enc+mac */
 	eor	v1.16b, v1.16b, v2.16b		/* xor with crypted ctr */
@@ -205,29 +176,18 @@ CPU_LE(	rev	x26, x26		)	/* keep swabbed ctr in reg */
 	eor	v1.16b, v2.16b, v5.16b		/* final round enc */
 	.endif
 	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
-	st1	{v1.16b}, [x19], #16		/* write output block */
-	beq	5f
-
-	if_will_cond_yield_neon
-	st1	{v0.16b}, [x24]			/* store mac */
-	do_cond_yield_neon
-	ld1	{v0.16b}, [x24]			/* reload mac */
-	endif_yield_neon
-
-	b	0b
-5:
-CPU_LE(	rev	x26, x26			)
-	st1	{v0.16b}, [x24]			/* store mac */
-	str	x26, [x25, #8]			/* store lsb end of ctr (BE) */
-
-6:	frame_pop
-	ret
-
-7:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
+	st1	{v1.16b}, [x0], #16		/* write output block */
+	bne	0b
+CPU_LE(	rev	x8, x8			)
+	st1	{v0.16b}, [x5]			/* store mac */
+	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
+5:	ret
+
+6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
 	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
-	st1	{v0.16b}, [x24]			/* store mac */
-	add	w21, w21, #16			/* process partial tail block */
-8:	ldrb	w9, [x20], #1			/* get 1 byte of input */
+	st1	{v0.16b}, [x5]			/* store mac */
+	add	w2, w2, #16			/* process partial tail block */
+7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
 	umov	w6, v1.b[0]			/* get top crypted ctr byte */
 	umov	w7, v0.b[0]			/* get top mac byte */
 	.if	\enc == 1
@@ -237,13 +197,13 @@ CPU_LE(	rev	x26, x26			)
 	eor	w9, w9, w6
 	eor	w7, w7, w9
 	.endif
-	strb	w9, [x19], #1			/* store out byte */
-	strb	w7, [x24], #1			/* store mac byte */
-	subs	w21, w21, #1
-	beq	6b
+	strb	w9, [x0], #1			/* store out byte */
+	strb	w7, [x5], #1			/* store mac byte */
+	subs	w2, w2, #1
+	beq	5b
 	ext	v0.16b, v0.16b, v0.16b, #1	/* shift out mac byte */
 	ext	v1.16b, v1.16b, v1.16b, #1	/* shift out ctr byte */
-	b	8b
+	b	7b
 	.endm
 
 	/*
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index dcffb9e77589..c723647b37db 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -322,55 +322,41 @@ ENDPROC(pmull_ghash_update_p8)
 	.endm
 
 	.macro		pmull_gcm_do_crypt, enc
-	frame_push	10
+	ld1		{SHASH.2d}, [x4]
+	ld1		{XL.2d}, [x1]
+	ldr		x8, [x5, #8]			// load lower counter
 
-	mov		x19, x0
-	mov		x20, x1
-	mov		x21, x2
-	mov		x22, x3
-	mov		x23, x4
-	mov		x24, x5
-	mov		x25, x6
-	mov		x26, x7
-	.if		\enc == 1
-	ldr		x27, [sp, #96]			// first stacked arg
-	.endif
-
-	ldr		x28, [x24, #8]			// load lower counter
-CPU_LE(	rev		x28, x28	)
-
-0:	mov		x0, x25
-	load_round_keys	w26, x0
-	ld1		{SHASH.2d}, [x23]
-	ld1		{XL.2d}, [x20]
+	load_round_keys	w7, x6
 
 	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+CPU_LE(	rev		x8, x8		)
 	shl		MASK.2d, MASK.2d, #57
 	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	.if		\enc == 1
-	ld1		{KS.16b}, [x27]
+	ldr		x10, [sp]
+	ld1		{KS.16b}, [x10]
 	.endif
 
-1:	ld1		{CTR.8b}, [x24]			// load upper counter
-	ld1		{INP.16b}, [x22], #16
-	rev		x9, x28
-	add		x28, x28, #1
-	sub		w19, w19, #1
+0:	ld1		{CTR.8b}, [x5]			// load upper counter
+	ld1		{INP.16b}, [x3], #16
+	rev		x9, x8
+	add		x8, x8, #1
+	sub		w0, w0, #1
 	ins		CTR.d[1], x9			// set lower counter
 
 	.if		\enc == 1
 	eor		INP.16b, INP.16b, KS.16b	// encrypt input
-	st1		{INP.16b}, [x21], #16
+	st1		{INP.16b}, [x2], #16
 	.endif
 
 	rev64		T1.16b, INP.16b
 
-	cmp		w26, #12
-	b.ge		4f				// AES-192/256?
+	cmp		w7, #12
+	b.ge		2f				// AES-192/256?
 
-2:	enc_round	CTR, v21
+1:	enc_round	CTR, v21
 
 	ext		T2.16b, XL.16b, XL.16b, #8
 	ext		IN1.16b, T1.16b, T1.16b, #8
@@ -425,39 +411,27 @@ CPU_LE(	rev		x28, x28	)
 
 	.if		\enc == 0
 	eor		INP.16b, INP.16b, KS.16b
-	st1		{INP.16b}, [x21], #16
+	st1		{INP.16b}, [x2], #16
 	.endif
 
-	cbz		w19, 3f
+	cbnz		w0, 0b
 
-	if_will_cond_yield_neon
-	st1		{XL.2d}, [x20]
-	.if		\enc == 1
-	st1		{KS.16b}, [x27]
-	.endif
-	do_cond_yield_neon
-	b		0b
-	endif_yield_neon
+CPU_LE(	rev		x8, x8		)
+	st1		{XL.2d}, [x1]
+	str		x8, [x5, #8]			// store lower counter
 
-	b		1b
-
-3:	st1		{XL.2d}, [x20]
 	.if		\enc == 1
-	st1		{KS.16b}, [x27]
+	st1		{KS.16b}, [x10]
 	.endif
 
-CPU_LE(	rev		x28, x28	)
-	str		x28, [x24, #8]			// store lower counter
-
-	frame_pop
 	ret
 
-4:	b.eq		5f				// AES-192?
+2:	b.eq		3f				// AES-192?
 	enc_round	CTR, v17
 	enc_round	CTR, v18
-5:	enc_round	CTR, v19
+3:	enc_round	CTR, v19
 	enc_round	CTR, v20
-	b		2b
+	b		1b
 	.endm
 
 	/*
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 7cf0b1aa6ea8..8a10f1d7199a 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -488,9 +488,13 @@ static int gcm_decrypt(struct aead_request *req)
 			err = skcipher_walk_done(&walk,
 						 walk.nbytes % AES_BLOCK_SIZE);
 		}
-		if (walk.nbytes)
-			pmull_gcm_encrypt_block(iv, iv, NULL,
+		if (walk.nbytes) {
+			kernel_neon_begin();
+			pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc,
 						num_rounds(&ctx->aes_key));
+			kernel_neon_end();
+		}
+
 	} else {
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
 				    num_rounds(&ctx->aes_key));
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 3a9b84d39d71..6cd5d77b6b44 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += mm-arch-hooks.h
 generic-y += msi.h
 generic-y += preempt.h
 generic-y += qrwlock.h
+generic-y += qspinlock.h
 generic-y += rwsem.h
 generic-y += segment.h
 generic-y += serial.h
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 0db62a4cbce2..709208dfdc8b 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -12,10 +12,12 @@
 #ifndef _ASM_ACPI_H
 #define _ASM_ACPI_H
 
+#include <linux/efi.h>
 #include <linux/memblock.h>
 #include <linux/psci.h>
 
 #include <asm/cputype.h>
+#include <asm/io.h>
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
 
@@ -29,18 +31,22 @@
 
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
+pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
+
 /* ACPI table mapping after acpi_permanent_mmap is set */
 static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
 					    acpi_size size)
 {
+	/* For normal memory we already have a cacheable mapping. */
+	if (memblock_is_map_memory(phys))
+		return (void __iomem *)__phys_to_virt(phys);
+
 	/*
-	 * EFI's reserve_regions() call adds memory with the WB attribute
-	 * to memblock via early_init_dt_add_memory_arch().
+	 * We should still honor the memory's attribute here because
+	 * crash dump kernel possibly excludes some ACPI (reclaim)
+	 * regions from memblock list.
 	 */
-	if (!memblock_is_memory(phys))
-		return ioremap(phys, size);
-
-	return ioremap_cache(phys, size);
+	return __ioremap(phys, size, __acpi_get_mem_attribute(phys));
 }
 #define acpi_os_ioremap acpi_os_ioremap
 
@@ -129,15 +135,20 @@ static inline const char *acpi_get_enable_method(int cpu)
  * for compatibility.
  */
 #define acpi_disable_cmcff 1
-pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
+static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
+{
+	return __acpi_get_mem_attribute(addr);
+}
 #endif /* CONFIG_ACPI_APEI */
 
 #ifdef CONFIG_ACPI_NUMA
 int arm64_acpi_numa_init(void);
-int acpi_numa_get_nid(unsigned int cpu, u64 hwid);
+int acpi_numa_get_nid(unsigned int cpu);
+void acpi_map_cpus_to_nodes(void);
 #else
 static inline int arm64_acpi_numa_init(void) { return -ENOSYS; }
-static inline int acpi_numa_get_nid(unsigned int cpu, u64 hwid) { return NUMA_NO_NODE; }
+static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; }
+static inline void acpi_map_cpus_to_nodes(void) { }
 #endif /* CONFIG_ACPI_NUMA */
 
 #define ACPI_TABLE_UPGRADE_MAX_PHYS MEMBLOCK_ALLOC_ACCESSIBLE
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index a91933b1e2e6..4b650ec1d7dd 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -28,7 +28,12 @@ typedef void (*alternative_cb_t)(struct alt_instr *alt,
 				 __le32 *origptr, __le32 *updptr, int nr_inst);
 
 void __init apply_alternatives_all(void);
-void apply_alternatives(void *start, size_t length);
+
+#ifdef CONFIG_MODULES
+void apply_alternatives_module(void *start, size_t length);
+#else
+static inline void apply_alternatives_module(void *start, size_t length) { }
+#endif
 
 #define ALTINSTR_ENTRY(feature,cb)					      \
 	" .word 661b - .\n"				/* label           */ \
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index c0235e0ff849..9bca54dda75c 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -40,17 +40,6 @@
 
 #include <asm/cmpxchg.h>
 
-#define ___atomic_add_unless(v, a, u, sfx)				\
-({									\
-	typeof((v)->counter) c, old;					\
-									\
-	c = atomic##sfx##_read(v);					\
-	while (c != (u) &&						\
-	      (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c)	\
-		c = old;						\
-	c;								\
- })
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 #define atomic_read(v)			READ_ONCE((v)->counter)
@@ -61,21 +50,11 @@
 #define atomic_add_return_release	atomic_add_return_release
 #define atomic_add_return		atomic_add_return
 
-#define atomic_inc_return_relaxed(v)	atomic_add_return_relaxed(1, (v))
-#define atomic_inc_return_acquire(v)	atomic_add_return_acquire(1, (v))
-#define atomic_inc_return_release(v)	atomic_add_return_release(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
 #define atomic_sub_return_relaxed	atomic_sub_return_relaxed
 #define atomic_sub_return_acquire	atomic_sub_return_acquire
 #define atomic_sub_return_release	atomic_sub_return_release
 #define atomic_sub_return		atomic_sub_return
 
-#define atomic_dec_return_relaxed(v)	atomic_sub_return_relaxed(1, (v))
-#define atomic_dec_return_acquire(v)	atomic_sub_return_acquire(1, (v))
-#define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-
 #define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
 #define atomic_fetch_add_acquire	atomic_fetch_add_acquire
 #define atomic_fetch_add_release	atomic_fetch_add_release
@@ -119,13 +98,6 @@
 	cmpxchg_release(&((v)->counter), (old), (new))
 #define atomic_cmpxchg(v, old, new)	cmpxchg(&((v)->counter), (old), (new))
 
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_add_negative(i, v)	(atomic_add_return((i), (v)) < 0)
-#define __atomic_add_unless(v, a, u)	___atomic_add_unless(v, a, u,)
 #define atomic_andnot			atomic_andnot
 
 /*
@@ -140,21 +112,11 @@
 #define atomic64_add_return_release	atomic64_add_return_release
 #define atomic64_add_return		atomic64_add_return
 
-#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1, (v))
-#define atomic64_inc_return_acquire(v)	atomic64_add_return_acquire(1, (v))
-#define atomic64_inc_return_release(v)	atomic64_add_return_release(1, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-
 #define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
 #define atomic64_sub_return_acquire	atomic64_sub_return_acquire
 #define atomic64_sub_return_release	atomic64_sub_return_release
 #define atomic64_sub_return		atomic64_sub_return
 
-#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1, (v))
-#define atomic64_dec_return_acquire(v)	atomic64_sub_return_acquire(1, (v))
-#define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
-
 #define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
 #define atomic64_fetch_add_acquire	atomic64_fetch_add_acquire
 #define atomic64_fetch_add_release	atomic64_fetch_add_release
@@ -195,16 +157,9 @@
 #define atomic64_cmpxchg_release	atomic_cmpxchg_release
 #define atomic64_cmpxchg		atomic_cmpxchg
 
-#define atomic64_inc(v)			atomic64_add(1, (v))
-#define atomic64_dec(v)			atomic64_sub(1, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i, v)	(atomic64_sub_return((i), (v)) == 0)
-#define atomic64_add_negative(i, v)	(atomic64_add_return((i), (v)) < 0)
-#define atomic64_add_unless(v, a, u)	(___atomic_add_unless(v, a, u, 64) != u)
 #define atomic64_andnot			atomic64_andnot
 
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
+#define atomic64_dec_if_positive	atomic64_dec_if_positive
 
 #endif
 #endif
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index f11518af96a9..822a9192c551 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -128,6 +128,19 @@ do {									\
 	__u.__val;							\
 })
 
+#define smp_cond_load_relaxed(ptr, cond_expr)				\
+({									\
+	typeof(ptr) __PTR = (ptr);					\
+	typeof(*ptr) VAL;						\
+	for (;;) {							\
+		VAL = READ_ONCE(*__PTR);				\
+		if (cond_expr)						\
+			break;						\
+		__cmpwait_relaxed(__PTR, VAL);				\
+	}								\
+	VAL;								\
+})
+
 #define smp_cond_load_acquire(ptr, cond_expr)				\
 ({									\
 	typeof(ptr) __PTR = (ptr);					\
diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h
index 9c19594ce7cb..10d536b1af74 100644
--- a/arch/arm64/include/asm/bitops.h
+++ b/arch/arm64/include/asm/bitops.h
@@ -17,22 +17,11 @@
 #define __ASM_BITOPS_H
 
 #include <linux/compiler.h>
-#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
 #endif
 
-/*
- * Little endian assembly atomic bitops.
- */
-extern void set_bit(int nr, volatile unsigned long *p);
-extern void clear_bit(int nr, volatile unsigned long *p);
-extern void change_bit(int nr, volatile unsigned long *p);
-extern int test_and_set_bit(int nr, volatile unsigned long *p);
-extern int test_and_clear_bit(int nr, volatile unsigned long *p);
-extern int test_and_change_bit(int nr, volatile unsigned long *p);
-
 #include <asm-generic/bitops/builtin-__ffs.h>
 #include <asm-generic/bitops/builtin-ffs.h>
 #include <asm-generic/bitops/builtin-__fls.h>
@@ -44,15 +33,11 @@ extern int test_and_change_bit(int nr, volatile unsigned long *p);
 
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/non-atomic.h>
 #include <asm-generic/bitops/le.h>
-
-/*
- * Ext2 is defined to use little-endian byte ordering.
- */
-#define ext2_set_bit_atomic(lock, nr, p)	test_and_set_bit_le(nr, p)
-#define ext2_clear_bit_atomic(lock, nr, p)	test_and_clear_bit_le(nr, p)
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
 
 #endif /* __ASM_BITOPS_H */
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 5df5cfe1c143..5ee5bca8c24b 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -21,12 +21,16 @@
 #define CTR_L1IP_SHIFT		14
 #define CTR_L1IP_MASK		3
 #define CTR_DMINLINE_SHIFT	16
+#define CTR_IMINLINE_SHIFT	0
 #define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
 #define CTR_IDC_SHIFT		28
 #define CTR_DIC_SHIFT		29
 
+#define CTR_CACHE_MINLINE_MASK	\
+	(0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT)
+
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 
 #define ICACHE_POLICY_VPIPT	0
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index d264a7274811..19844211a4e6 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -19,6 +19,7 @@
 #ifndef __ASM_CACHEFLUSH_H
 #define __ASM_CACHEFLUSH_H
 
+#include <linux/kgdb.h>
 #include <linux/mm.h>
 
 /*
@@ -71,7 +72,7 @@
  *		- kaddr  - page address
  *		- size   - region size
  */
-extern void flush_icache_range(unsigned long start, unsigned long end);
+extern void __flush_icache_range(unsigned long start, unsigned long end);
 extern int  invalidate_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
 extern void __inval_dcache_area(void *addr, size_t len);
@@ -81,6 +82,30 @@ extern void __clean_dcache_area_pou(void *addr, size_t len);
 extern long __flush_cache_user_range(unsigned long start, unsigned long end);
 extern void sync_icache_aliases(void *kaddr, unsigned long len);
 
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+	__flush_icache_range(start, end);
+
+	/*
+	 * IPI all online CPUs so that they undergo a context synchronization
+	 * event and are forced to refetch the new instructions.
+	 */
+#ifdef CONFIG_KGDB
+	/*
+	 * KGDB performs cache maintenance with interrupts disabled, so we
+	 * will deadlock trying to IPI the secondary CPUs. In theory, we can
+	 * set CACHE_FLUSH_IS_SAFE to 0 to avoid this known issue, but that
+	 * just means that KGDB will elide the maintenance altogether! As it
+	 * turns out, KGDB uses IPIs to round-up the secondary CPUs during
+	 * the patching operation, so we don't need extra IPIs here anyway.
+	 * In which case, add a KGDB-specific bodge and return early.
+	 */
+	if (kgdb_connected && irqs_disabled())
+		return;
+#endif
+	kick_all_cpus_sync();
+}
+
 static inline void flush_cache_mm(struct mm_struct *mm)
 {
 }
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 8a699c708fc9..be3bf3d08916 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -49,7 +49,8 @@
 #define ARM64_HAS_CACHE_DIC			28
 #define ARM64_HW_DBM				29
 #define ARM64_SSBD				30
+#define ARM64_MISMATCHED_CACHE_TYPE		31
 
-#define ARM64_NCAPS				31
+#define ARM64_NCAPS				32
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 192d791f1103..7ed320895d1f 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -87,6 +87,9 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
 #define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
 #define efi_is_64bit()			(true)
 
+#define efi_table_attr(table, attr, instance)				\
+	((table##_t *)instance)->attr
+
 #define efi_call_proto(protocol, f, instance, ...)			\
 	((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
 
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index fa92747a49c8..dd1ad3950ef5 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -16,13 +16,15 @@
 #ifndef __ASM_FP_H
 #define __ASM_FP_H
 
-#include <asm/ptrace.h>
 #include <asm/errno.h>
+#include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
+#include <asm/sysreg.h>
 
 #ifndef __ASSEMBLY__
 
+#include <linux/build_bug.h>
 #include <linux/cache.h>
 #include <linux/init.h>
 #include <linux/stddef.h>
@@ -102,6 +104,16 @@ extern int sve_set_vector_length(struct task_struct *task,
 extern int sve_set_current_vl(unsigned long arg);
 extern int sve_get_current_vl(void);
 
+static inline void sve_user_disable(void)
+{
+	sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0);
+}
+
+static inline void sve_user_enable(void)
+{
+	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN);
+}
+
 /*
  * Probing and setup functions.
  * Calls to these functions must be serialised with one another.
@@ -128,6 +140,9 @@ static inline int sve_get_current_vl(void)
 	return -EINVAL;
 }
 
+static inline void sve_user_disable(void) { BUILD_BUG(); }
+static inline void sve_user_enable(void) { BUILD_BUG(); }
+
 static inline void sve_init_vq_map(void) { }
 static inline void sve_update_vq_map(void) { }
 static inline int sve_verify_vq_map(void) { return 0; }
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 41770766d964..6a53e59ced95 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -119,13 +119,16 @@ static inline void decode_ctrl_reg(u32 reg,
 
 struct task_struct;
 struct notifier_block;
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  int *gen_len, int *gen_type, int *offset);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index f62c56b1793f..c6802dea6cab 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -446,8 +446,6 @@ u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
 s32 aarch64_get_branch_offset(u32 insn);
 u32 aarch64_set_branch_offset(u32 insn, s32 offset);
 
-bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
-
 int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
 
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index a0fee6985e6a..b2b0c6405eb0 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -8,8 +8,6 @@
 
 struct pt_regs;
 
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
 static inline int nr_legacy_irqs(void)
 {
 	return 0;
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 6deb8d726041..d5a44cf859e9 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -48,7 +48,6 @@ struct kprobe_ctlblk {
 	unsigned long saved_irqflag;
 	struct prev_kprobe prev_kprobe;
 	struct kprobe_step_ctx ss_ctx;
-	struct pt_regs jprobe_saved_regs;
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 1dab3a984608..0c97e45d1dc3 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -140,7 +140,7 @@ static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
 
 static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 {
-	*vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT;
+	*vcpu_cpsr(vcpu) |= PSR_AA32_T_BIT;
 }
 
 /*
@@ -190,8 +190,8 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 	u32 mode;
 
 	if (vcpu_mode_is_32bit(vcpu)) {
-		mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
-		return mode > COMPAT_PSR_MODE_USR;
+		mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
+		return mode > PSR_AA32_MODE_USR;
 	}
 
 	mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
@@ -329,7 +329,7 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu)) {
-		*vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT;
+		*vcpu_cpsr(vcpu) |= PSR_AA32_E_BIT;
 	} else {
 		u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
 		sctlr |= (1 << 25);
@@ -340,7 +340,7 @@ static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu))
-		return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT);
+		return !!(*vcpu_cpsr(vcpu) & PSR_AA32_E_BIT);
 
 	return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & (1 << 25));
 }
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
index f922eaf780f9..fb9d137256a6 100644
--- a/arch/arm64/include/asm/neon.h
+++ b/arch/arm64/include/asm/neon.h
@@ -19,11 +19,4 @@
 void kernel_neon_begin(void);
 void kernel_neon_end(void);
 
-/*
- * Temporary macro to allow the crypto code to compile. Note that the
- * semantics of kernel_neon_begin_partial() are now different from the
- * original as it does not allow being called in an interrupt context.
- */
-#define kernel_neon_begin_partial(num_regs)	kernel_neon_begin()
-
 #endif /* ! __ASM_NEON_H */
diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
index 01bc46d5b43a..626ad01e83bf 100644
--- a/arch/arm64/include/asm/numa.h
+++ b/arch/arm64/include/asm/numa.h
@@ -35,10 +35,14 @@ void __init numa_set_distance(int from, int to, int distance);
 void __init numa_free_distance(void);
 void __init early_map_cpu_to_node(unsigned int cpu, int nid);
 void numa_store_cpu_info(unsigned int cpu);
+void numa_add_cpu(unsigned int cpu);
+void numa_remove_cpu(unsigned int cpu);
 
 #else	/* CONFIG_NUMA */
 
 static inline void numa_store_cpu_info(unsigned int cpu) { }
+static inline void numa_add_cpu(unsigned int cpu) { }
+static inline void numa_remove_cpu(unsigned int cpu) { }
 static inline void arm64_numa_init(void) { }
 static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9f82d6b53851..1bdeca8918a6 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -224,10 +224,8 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
 	 * or update_mmu_cache() have the necessary barriers.
 	 */
-	if (pte_valid_not_user(pte)) {
+	if (pte_valid_not_user(pte))
 		dsb(ishst);
-		isb();
-	}
 }
 
 extern void __sync_icache_dcache(pte_t pteval);
@@ -434,7 +432,6 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	WRITE_ONCE(*pmdp, pmd);
 	dsb(ishst);
-	isb();
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -485,7 +482,6 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 {
 	WRITE_ONCE(*pudp, pud);
 	dsb(ishst);
-	isb();
 }
 
 static inline void pud_clear(pud_t *pudp)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index a73ae1e49200..79657ad91397 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -182,12 +182,12 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 				       unsigned long sp)
 {
 	start_thread_common(regs, pc);
-	regs->pstate = COMPAT_PSR_MODE_USR;
+	regs->pstate = PSR_AA32_MODE_USR;
 	if (pc & 1)
-		regs->pstate |= COMPAT_PSR_T_BIT;
+		regs->pstate |= PSR_AA32_T_BIT;
 
 #ifdef __AARCH64EB__
-	regs->pstate |= COMPAT_PSR_E_BIT;
+	regs->pstate |= PSR_AA32_E_BIT;
 #endif
 
 	regs->compat_sp = sp;
@@ -266,5 +266,20 @@ extern void __init minsigstksz_setup(void);
 #define SVE_SET_VL(arg)	sve_set_current_vl(arg)
 #define SVE_GET_VL()	sve_get_current_vl()
 
+/*
+ * For CONFIG_GCC_PLUGIN_STACKLEAK
+ *
+ * These need to be macros because otherwise we get stuck in a nightmare
+ * of header definitions for the use of task_stack_page.
+ */
+
+#define current_top_of_stack()							\
+({										\
+	struct stack_info _info;						\
+	BUG_ON(!on_accessible_stack(current, current_stack_pointer, &_info));	\
+	_info.high;								\
+})
+#define on_thread_stack()	(on_task_stack(current, current_stack_pointer, NULL))
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 6069d66e0bc2..177b851ca6d9 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -35,36 +35,39 @@
 #define COMPAT_PTRACE_GETHBPREGS	29
 #define COMPAT_PTRACE_SETHBPREGS	30
 
-/* AArch32 CPSR bits */
-#define COMPAT_PSR_MODE_MASK	0x0000001f
-#define COMPAT_PSR_MODE_USR	0x00000010
-#define COMPAT_PSR_MODE_FIQ	0x00000011
-#define COMPAT_PSR_MODE_IRQ	0x00000012
-#define COMPAT_PSR_MODE_SVC	0x00000013
-#define COMPAT_PSR_MODE_ABT	0x00000017
-#define COMPAT_PSR_MODE_HYP	0x0000001a
-#define COMPAT_PSR_MODE_UND	0x0000001b
-#define COMPAT_PSR_MODE_SYS	0x0000001f
-#define COMPAT_PSR_T_BIT	0x00000020
-#define COMPAT_PSR_F_BIT	0x00000040
-#define COMPAT_PSR_I_BIT	0x00000080
-#define COMPAT_PSR_A_BIT	0x00000100
-#define COMPAT_PSR_E_BIT	0x00000200
-#define COMPAT_PSR_J_BIT	0x01000000
-#define COMPAT_PSR_Q_BIT	0x08000000
-#define COMPAT_PSR_V_BIT	0x10000000
-#define COMPAT_PSR_C_BIT	0x20000000
-#define COMPAT_PSR_Z_BIT	0x40000000
-#define COMPAT_PSR_N_BIT	0x80000000
-#define COMPAT_PSR_IT_MASK	0x0600fc00	/* If-Then execution state mask */
-#define COMPAT_PSR_GE_MASK	0x000f0000
+/* SPSR_ELx bits for exceptions taken from AArch32 */
+#define PSR_AA32_MODE_MASK	0x0000001f
+#define PSR_AA32_MODE_USR	0x00000010
+#define PSR_AA32_MODE_FIQ	0x00000011
+#define PSR_AA32_MODE_IRQ	0x00000012
+#define PSR_AA32_MODE_SVC	0x00000013
+#define PSR_AA32_MODE_ABT	0x00000017
+#define PSR_AA32_MODE_HYP	0x0000001a
+#define PSR_AA32_MODE_UND	0x0000001b
+#define PSR_AA32_MODE_SYS	0x0000001f
+#define PSR_AA32_T_BIT		0x00000020
+#define PSR_AA32_F_BIT		0x00000040
+#define PSR_AA32_I_BIT		0x00000080
+#define PSR_AA32_A_BIT		0x00000100
+#define PSR_AA32_E_BIT		0x00000200
+#define PSR_AA32_DIT_BIT	0x01000000
+#define PSR_AA32_Q_BIT		0x08000000
+#define PSR_AA32_V_BIT		0x10000000
+#define PSR_AA32_C_BIT		0x20000000
+#define PSR_AA32_Z_BIT		0x40000000
+#define PSR_AA32_N_BIT		0x80000000
+#define PSR_AA32_IT_MASK	0x0600fc00	/* If-Then execution state mask */
+#define PSR_AA32_GE_MASK	0x000f0000
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
-#define COMPAT_PSR_ENDSTATE	COMPAT_PSR_E_BIT
+#define PSR_AA32_ENDSTATE	PSR_AA32_E_BIT
 #else
-#define COMPAT_PSR_ENDSTATE	0
+#define PSR_AA32_ENDSTATE	0
 #endif
 
+/* AArch32 CPSR bits, as seen in AArch32 */
+#define COMPAT_PSR_DIT_BIT	0x00200000
+
 /*
  * These are 'magic' values for PTRACE_PEEKUSR that return info about where a
  * process is located in memory.
@@ -111,6 +114,30 @@
 #define compat_sp_fiq	regs[29]
 #define compat_lr_fiq	regs[30]
 
+static inline unsigned long compat_psr_to_pstate(const unsigned long psr)
+{
+	unsigned long pstate;
+
+	pstate = psr & ~COMPAT_PSR_DIT_BIT;
+
+	if (psr & COMPAT_PSR_DIT_BIT)
+		pstate |= PSR_AA32_DIT_BIT;
+
+	return pstate;
+}
+
+static inline unsigned long pstate_to_compat_psr(const unsigned long pstate)
+{
+	unsigned long psr;
+
+	psr = pstate & ~PSR_AA32_DIT_BIT;
+
+	if (pstate & PSR_AA32_DIT_BIT)
+		psr |= COMPAT_PSR_DIT_BIT;
+
+	return psr;
+}
+
 /*
  * This struct defines the way the registers are stored on the stack during an
  * exception. Note that sizeof(struct pt_regs) has to be a multiple of 16 (for
@@ -156,7 +183,7 @@ static inline void forget_syscall(struct pt_regs *regs)
 
 #ifdef CONFIG_COMPAT
 #define compat_thumb_mode(regs) \
-	(((regs)->pstate & COMPAT_PSR_T_BIT))
+	(((regs)->pstate & PSR_AA32_T_BIT))
 #else
 #define compat_thumb_mode(regs) (0)
 #endif
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
index e073e6886685..ffe47d766c25 100644
--- a/arch/arm64/include/asm/sdei.h
+++ b/arch/arm64/include/asm/sdei.h
@@ -40,15 +40,18 @@ asmlinkage unsigned long __sdei_handler(struct pt_regs *regs,
 unsigned long sdei_arch_get_entry_point(int conduit);
 #define sdei_arch_get_entry_point(x)	sdei_arch_get_entry_point(x)
 
-bool _on_sdei_stack(unsigned long sp);
-static inline bool on_sdei_stack(unsigned long sp)
+struct stack_info;
+
+bool _on_sdei_stack(unsigned long sp, struct stack_info *info);
+static inline bool on_sdei_stack(unsigned long sp,
+				struct stack_info *info)
 {
 	if (!IS_ENABLED(CONFIG_VMAP_STACK))
 		return false;
 	if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
 		return false;
 	if (in_nmi())
-		return _on_sdei_stack(sp);
+		return _on_sdei_stack(sp, info);
 
 	return false;
 }
diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h
index fa8b3fe932e6..6495cc51246f 100644
--- a/arch/arm64/include/asm/simd.h
+++ b/arch/arm64/include/asm/simd.h
@@ -29,20 +29,15 @@ DECLARE_PER_CPU(bool, kernel_neon_busy);
 static __must_check inline bool may_use_simd(void)
 {
 	/*
-	 * The raw_cpu_read() is racy if called with preemption enabled.
-	 * This is not a bug: kernel_neon_busy is only set when
-	 * preemption is disabled, so we cannot migrate to another CPU
-	 * while it is set, nor can we migrate to a CPU where it is set.
-	 * So, if we find it clear on some CPU then we're guaranteed to
-	 * find it clear on any CPU we could migrate to.
-	 *
-	 * If we are in between kernel_neon_begin()...kernel_neon_end(),
-	 * the flag will be set, but preemption is also disabled, so we
-	 * can't migrate to another CPU and spuriously see it become
-	 * false.
+	 * kernel_neon_busy is only set while preemption is disabled,
+	 * and is clear whenever preemption is enabled. Since
+	 * this_cpu_read() is atomic w.r.t. preemption, kernel_neon_busy
+	 * cannot change under our feet -- if it's set we cannot be
+	 * migrated, and if it's clear we cannot be migrated to a CPU
+	 * where it is set.
 	 */
 	return !in_irq() && !irqs_disabled() && !in_nmi() &&
-		!raw_cpu_read(kernel_neon_busy);
+		!this_cpu_read(kernel_neon_busy);
 }
 
 #else /* ! CONFIG_KERNEL_MODE_NEON */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 26c5bd7d88d8..38116008d18b 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -16,123 +16,8 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
-#include <asm/lse.h>
-#include <asm/spinlock_types.h>
-#include <asm/processor.h>
-
-/*
- * Spinlock implementation.
- *
- * The memory barriers are implicit with the load-acquire and store-release
- * instructions.
- */
-
-static inline void arch_spin_lock(arch_spinlock_t *lock)
-{
-	unsigned int tmp;
-	arch_spinlock_t lockval, newval;
-
-	asm volatile(
-	/* Atomically increment the next ticket. */
-	ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-"	prfm	pstl1strm, %3\n"
-"1:	ldaxr	%w0, %3\n"
-"	add	%w1, %w0, %w5\n"
-"	stxr	%w2, %w1, %3\n"
-"	cbnz	%w2, 1b\n",
-	/* LSE atomics */
-"	mov	%w2, %w5\n"
-"	ldadda	%w2, %w0, %3\n"
-	__nops(3)
-	)
-
-	/* Did we get the lock? */
-"	eor	%w1, %w0, %w0, ror #16\n"
-"	cbz	%w1, 3f\n"
-	/*
-	 * No: spin on the owner. Send a local event to avoid missing an
-	 * unlock before the exclusive load.
-	 */
-"	sevl\n"
-"2:	wfe\n"
-"	ldaxrh	%w2, %4\n"
-"	eor	%w1, %w2, %w0, lsr #16\n"
-"	cbnz	%w1, 2b\n"
-	/* We got the lock. Critical section starts here. */
-"3:"
-	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock)
-	: "Q" (lock->owner), "I" (1 << TICKET_SHIFT)
-	: "memory");
-}
-
-static inline int arch_spin_trylock(arch_spinlock_t *lock)
-{
-	unsigned int tmp;
-	arch_spinlock_t lockval;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	prfm	pstl1strm, %2\n"
-	"1:	ldaxr	%w0, %2\n"
-	"	eor	%w1, %w0, %w0, ror #16\n"
-	"	cbnz	%w1, 2f\n"
-	"	add	%w0, %w0, %3\n"
-	"	stxr	%w1, %w0, %2\n"
-	"	cbnz	%w1, 1b\n"
-	"2:",
-	/* LSE atomics */
-	"	ldr	%w0, %2\n"
-	"	eor	%w1, %w0, %w0, ror #16\n"
-	"	cbnz	%w1, 1f\n"
-	"	add	%w1, %w0, %3\n"
-	"	casa	%w0, %w1, %2\n"
-	"	sub	%w1, %w1, %3\n"
-	"	eor	%w1, %w1, %w0\n"
-	"1:")
-	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
-	: "I" (1 << TICKET_SHIFT)
-	: "memory");
-
-	return !tmp;
-}
-
-static inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
-	unsigned long tmp;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	ldrh	%w1, %0\n"
-	"	add	%w1, %w1, #1\n"
-	"	stlrh	%w1, %0",
-	/* LSE atomics */
-	"	mov	%w1, #1\n"
-	"	staddlh	%w1, %0\n"
-	__nops(1))
-	: "=Q" (lock->owner), "=&r" (tmp)
-	:
-	: "memory");
-}
-
-static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
-{
-	return lock.owner == lock.next;
-}
-
-static inline int arch_spin_is_locked(arch_spinlock_t *lock)
-{
-	return !arch_spin_value_unlocked(READ_ONCE(*lock));
-}
-
-static inline int arch_spin_is_contended(arch_spinlock_t *lock)
-{
-	arch_spinlock_t lockval = READ_ONCE(*lock);
-	return (lockval.next - lockval.owner) > 1;
-}
-#define arch_spin_is_contended	arch_spin_is_contended
-
 #include <asm/qrwlock.h>
+#include <asm/qspinlock.h>
 
 /* See include/linux/spinlock.h */
 #define smp_mb__after_spinlock()	smp_mb()
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 6b856012c51b..a157ff465e27 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -20,22 +20,7 @@
 # error "please don't include this file directly"
 #endif
 
-#include <linux/types.h>
-
-#define TICKET_SHIFT	16
-
-typedef struct {
-#ifdef __AARCH64EB__
-	u16 next;
-	u16 owner;
-#else
-	u16 owner;
-	u16 next;
-#endif
-} __aligned(4) arch_spinlock_t;
-
-#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 , 0 }
-
+#include <asm-generic/qspinlock_types.h>
 #include <asm-generic/qrwlock_types.h>
 
 #endif
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 902f9edacbea..e86737b7c924 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -32,6 +32,21 @@ struct stackframe {
 #endif
 };
 
+enum stack_type {
+	STACK_TYPE_UNKNOWN,
+	STACK_TYPE_TASK,
+	STACK_TYPE_IRQ,
+	STACK_TYPE_OVERFLOW,
+	STACK_TYPE_SDEI_NORMAL,
+	STACK_TYPE_SDEI_CRITICAL,
+};
+
+struct stack_info {
+	unsigned long low;
+	unsigned long high;
+	enum stack_type type;
+};
+
 extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame);
 extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 			    int (*fn)(struct stackframe *, void *), void *data);
@@ -39,7 +54,8 @@ extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk);
 
 DECLARE_PER_CPU(unsigned long *, irq_stack_ptr);
 
-static inline bool on_irq_stack(unsigned long sp)
+static inline bool on_irq_stack(unsigned long sp,
+				struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr);
 	unsigned long high = low + IRQ_STACK_SIZE;
@@ -47,46 +63,79 @@ static inline bool on_irq_stack(unsigned long sp)
 	if (!low)
 		return false;
 
-	return (low <= sp && sp < high);
+	if (sp < low || sp >= high)
+		return false;
+
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_IRQ;
+	}
+
+	return true;
 }
 
-static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp)
+static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp,
+				struct stack_info *info)
 {
 	unsigned long low = (unsigned long)task_stack_page(tsk);
 	unsigned long high = low + THREAD_SIZE;
 
-	return (low <= sp && sp < high);
+	if (sp < low || sp >= high)
+		return false;
+
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_TASK;
+	}
+
+	return true;
 }
 
 #ifdef CONFIG_VMAP_STACK
 DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
 
-static inline bool on_overflow_stack(unsigned long sp)
+static inline bool on_overflow_stack(unsigned long sp,
+				struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack);
 	unsigned long high = low + OVERFLOW_STACK_SIZE;
 
-	return (low <= sp && sp < high);
+	if (sp < low || sp >= high)
+		return false;
+
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_OVERFLOW;
+	}
+
+	return true;
 }
 #else
-static inline bool on_overflow_stack(unsigned long sp) { return false; }
+static inline bool on_overflow_stack(unsigned long sp,
+			struct stack_info *info) { return false; }
 #endif
 
+
 /*
  * We can only safely access per-cpu stacks from current in a non-preemptible
  * context.
  */
-static inline bool on_accessible_stack(struct task_struct *tsk, unsigned long sp)
+static inline bool on_accessible_stack(struct task_struct *tsk,
+					unsigned long sp,
+					struct stack_info *info)
 {
-	if (on_task_stack(tsk, sp))
+	if (on_task_stack(tsk, sp, info))
 		return true;
 	if (tsk != current || preemptible())
 		return false;
-	if (on_irq_stack(sp))
+	if (on_irq_stack(sp, info))
 		return true;
-	if (on_overflow_stack(sp))
+	if (on_overflow_stack(sp, info))
 		return true;
-	if (on_sdei_stack(sp))
+	if (on_sdei_stack(sp, info))
 		return true;
 
 	return false;
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 709a574468f0..ad8be16a39c9 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -20,7 +20,13 @@
 #include <linux/compat.h>
 #include <linux/err.h>
 
-extern const void *sys_call_table[];
+typedef long (*syscall_fn_t)(struct pt_regs *regs);
+
+extern const syscall_fn_t sys_call_table[];
+
+#ifdef CONFIG_COMPAT
+extern const syscall_fn_t compat_sys_call_table[];
+#endif
 
 static inline int syscall_get_nr(struct task_struct *task,
 				 struct pt_regs *regs)
diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h
new file mode 100644
index 000000000000..a4477e515b79
--- /dev/null
+++ b/arch/arm64/include/asm/syscall_wrapper.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * syscall_wrapper.h - arm64 specific wrappers to syscall definitions
+ *
+ * Based on arch/x86/include/asm_syscall_wrapper.h
+ */
+
+#ifndef __ASM_SYSCALL_WRAPPER_H
+#define __ASM_SYSCALL_WRAPPER_H
+
+#define SC_ARM64_REGS_TO_ARGS(x, ...)				\
+	__MAP(x,__SC_ARGS					\
+	      ,,regs->regs[0],,regs->regs[1],,regs->regs[2]	\
+	      ,,regs->regs[3],,regs->regs[4],,regs->regs[5])
+
+#ifdef CONFIG_COMPAT
+
+#define COMPAT_SYSCALL_DEFINEx(x, name, ...)						\
+	asmlinkage long __arm64_compat_sys##name(const struct pt_regs *regs);		\
+	ALLOW_ERROR_INJECTION(__arm64_compat_sys##name, ERRNO);				\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long __arm64_compat_sys##name(const struct pt_regs *regs)		\
+	{										\
+		return __se_compat_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__));	\
+	}										\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
+	{										\
+		return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));	\
+	}										\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#define COMPAT_SYSCALL_DEFINE0(sname)					\
+	asmlinkage long __arm64_compat_sys_##sname(void);		\
+	ALLOW_ERROR_INJECTION(__arm64_compat_sys_##sname, ERRNO);	\
+	asmlinkage long __arm64_compat_sys_##sname(void)
+
+#define COND_SYSCALL_COMPAT(name) \
+	cond_syscall(__arm64_compat_sys_##name);
+
+#define COMPAT_SYS_NI(name) \
+	SYSCALL_ALIAS(__arm64_compat_sys_##name, sys_ni_posix_timers);
+
+#endif /* CONFIG_COMPAT */
+
+#define __SYSCALL_DEFINEx(x, name, ...)						\
+	asmlinkage long __arm64_sys##name(const struct pt_regs *regs);		\
+	ALLOW_ERROR_INJECTION(__arm64_sys##name, ERRNO);			\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long __arm64_sys##name(const struct pt_regs *regs)		\
+	{									\
+		return __se_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__));	\
+	}									\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
+	{									\
+		long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
+		__MAP(x,__SC_TEST,__VA_ARGS__);					\
+		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));		\
+		return ret;							\
+	}									\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#ifndef SYSCALL_DEFINE0
+#define SYSCALL_DEFINE0(sname)					\
+	SYSCALL_METADATA(_##sname, 0);				\
+	asmlinkage long __arm64_sys_##sname(void);		\
+	ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO);	\
+	asmlinkage long __arm64_sys_##sname(void)
+#endif
+
+#ifndef COND_SYSCALL
+#define COND_SYSCALL(name) cond_syscall(__arm64_sys_##name)
+#endif
+
+#ifndef SYS_NI
+#define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers);
+#endif
+
+#endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index a8f84812c6e8..e205ec8489e9 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -436,7 +436,8 @@
 #define SCTLR_EL2_RES0	((1 << 6)  | (1 << 7)  | (1 << 8)  | (1 << 9)  | \
 			 (1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \
 			 (1 << 17) | (1 << 20) | (1 << 24) | (1 << 26) | \
-			 (1 << 27) | (1 << 30) | (1 << 31))
+			 (1 << 27) | (1 << 30) | (1 << 31) | \
+			 (0xffffffffUL << 32))
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define ENDIAN_SET_EL2		SCTLR_ELx_EE
@@ -452,9 +453,9 @@
 			 SCTLR_ELx_SA     | SCTLR_ELx_I    | SCTLR_ELx_WXN | \
 			 ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
 
-/* Check all the bits are accounted for */
-#define SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS	BUILD_BUG_ON((SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != ~0)
-
+#if (SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != 0xffffffffffffffff
+#error "Inconsistent SCTLR_EL2 set/clear bits"
+#endif
 
 /* SCTLR_EL1 specific flags. */
 #define SCTLR_EL1_UCI		(1 << 26)
@@ -473,7 +474,8 @@
 #define SCTLR_EL1_RES1	((1 << 11) | (1 << 20) | (1 << 22) | (1 << 28) | \
 			 (1 << 29))
 #define SCTLR_EL1_RES0  ((1 << 6)  | (1 << 10) | (1 << 13) | (1 << 17) | \
-			 (1 << 27) | (1 << 30) | (1 << 31))
+			 (1 << 27) | (1 << 30) | (1 << 31) | \
+			 (0xffffffffUL << 32))
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define ENDIAN_SET_EL1		(SCTLR_EL1_E0E | SCTLR_ELx_EE)
@@ -492,8 +494,9 @@
 			 SCTLR_EL1_UMA | SCTLR_ELx_WXN     | ENDIAN_CLEAR_EL1 |\
 			 SCTLR_EL1_RES0)
 
-/* Check all the bits are accounted for */
-#define SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS	BUILD_BUG_ON((SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != ~0)
+#if (SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != 0xffffffffffffffff
+#error "Inconsistent SCTLR_EL1 set/clear bits"
+#endif
 
 /* id_aa64isar0 */
 #define ID_AA64ISAR0_TS_SHIFT		52
@@ -739,19 +742,6 @@ asm(
 		write_sysreg(__scs_new, sysreg);			\
 } while (0)
 
-static inline void config_sctlr_el1(u32 clear, u32 set)
-{
-	u32 val;
-
-	SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS;
-	SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS;
-
-	val = read_sysreg(sctlr_el1);
-	val &= ~clear;
-	val |= set;
-	write_sysreg(val, sctlr_el1);
-}
-
 #endif
 
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index ffdaea7954bb..0ad1cf233470 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -37,7 +37,7 @@ static inline void __tlb_remove_table(void *_table)
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+	struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
 
 	/*
 	 * The ASID allocator will either invalidate the ASID or mark
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index dfc61d73f740..a4a1901140ee 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -218,6 +218,13 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
 	dsb(ish);
 }
 
+static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
+{
+	unsigned long addr = __TLBI_VADDR(kaddr, 0);
+
+	__tlbi(vaae1is, addr);
+	dsb(ish);
+}
 #endif
 
 #endif
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index df48212f767b..49a0fee4f89b 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -11,7 +11,7 @@ struct cpu_topology {
 	int llc_id;
 	cpumask_t thread_sibling;
 	cpumask_t core_sibling;
-	cpumask_t llc_siblings;
+	cpumask_t llc_sibling;
 };
 
 extern struct cpu_topology cpu_topology[NR_CPUS];
@@ -20,9 +20,11 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
 #define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_llc_cpumask(cpu)	(&cpu_topology[cpu].llc_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
+void remove_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #ifdef CONFIG_NUMA
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index a0baa9af5487..e0d0f5b856e7 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -43,7 +43,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		398
+#define __NR_compat_syscalls		399
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index ef292160748c..2cd6dcf8d246 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -260,7 +260,7 @@ __SYSCALL(117, sys_ni_syscall)
 #define __NR_fsync 118
 __SYSCALL(__NR_fsync, sys_fsync)
 #define __NR_sigreturn 119
-__SYSCALL(__NR_sigreturn, compat_sys_sigreturn_wrapper)
+__SYSCALL(__NR_sigreturn, compat_sys_sigreturn)
 #define __NR_clone 120
 __SYSCALL(__NR_clone, sys_clone)
 #define __NR_setdomainname 121
@@ -368,7 +368,7 @@ __SYSCALL(__NR_getresgid, sys_getresgid16)
 #define __NR_prctl 172
 __SYSCALL(__NR_prctl, sys_prctl)
 #define __NR_rt_sigreturn 173
-__SYSCALL(__NR_rt_sigreturn, compat_sys_rt_sigreturn_wrapper)
+__SYSCALL(__NR_rt_sigreturn, compat_sys_rt_sigreturn)
 #define __NR_rt_sigaction 174
 __SYSCALL(__NR_rt_sigaction, compat_sys_rt_sigaction)
 #define __NR_rt_sigprocmask 175
@@ -382,9 +382,9 @@ __SYSCALL(__NR_rt_sigqueueinfo, compat_sys_rt_sigqueueinfo)
 #define __NR_rt_sigsuspend 179
 __SYSCALL(__NR_rt_sigsuspend, compat_sys_rt_sigsuspend)
 #define __NR_pread64 180
-__SYSCALL(__NR_pread64, compat_sys_pread64_wrapper)
+__SYSCALL(__NR_pread64, compat_sys_aarch32_pread64)
 #define __NR_pwrite64 181
-__SYSCALL(__NR_pwrite64, compat_sys_pwrite64_wrapper)
+__SYSCALL(__NR_pwrite64, compat_sys_aarch32_pwrite64)
 #define __NR_chown 182
 __SYSCALL(__NR_chown, sys_chown16)
 #define __NR_getcwd 183
@@ -406,11 +406,11 @@ __SYSCALL(__NR_vfork, sys_vfork)
 #define __NR_ugetrlimit 191	/* SuS compliant getrlimit */
 __SYSCALL(__NR_ugetrlimit, compat_sys_getrlimit)		/* SuS compliant getrlimit */
 #define __NR_mmap2 192
-__SYSCALL(__NR_mmap2, compat_sys_mmap2_wrapper)
+__SYSCALL(__NR_mmap2, compat_sys_aarch32_mmap2)
 #define __NR_truncate64 193
-__SYSCALL(__NR_truncate64, compat_sys_truncate64_wrapper)
+__SYSCALL(__NR_truncate64, compat_sys_aarch32_truncate64)
 #define __NR_ftruncate64 194
-__SYSCALL(__NR_ftruncate64, compat_sys_ftruncate64_wrapper)
+__SYSCALL(__NR_ftruncate64, compat_sys_aarch32_ftruncate64)
 #define __NR_stat64 195
 __SYSCALL(__NR_stat64, sys_stat64)
 #define __NR_lstat64 196
@@ -472,7 +472,7 @@ __SYSCALL(223, sys_ni_syscall)
 #define __NR_gettid 224
 __SYSCALL(__NR_gettid, sys_gettid)
 #define __NR_readahead 225
-__SYSCALL(__NR_readahead, compat_sys_readahead_wrapper)
+__SYSCALL(__NR_readahead, compat_sys_aarch32_readahead)
 #define __NR_setxattr 226
 __SYSCALL(__NR_setxattr, sys_setxattr)
 #define __NR_lsetxattr 227
@@ -554,15 +554,15 @@ __SYSCALL(__NR_clock_getres, compat_sys_clock_getres)
 #define __NR_clock_nanosleep 265
 __SYSCALL(__NR_clock_nanosleep, compat_sys_clock_nanosleep)
 #define __NR_statfs64 266
-__SYSCALL(__NR_statfs64, compat_sys_statfs64_wrapper)
+__SYSCALL(__NR_statfs64, compat_sys_aarch32_statfs64)
 #define __NR_fstatfs64 267
-__SYSCALL(__NR_fstatfs64, compat_sys_fstatfs64_wrapper)
+__SYSCALL(__NR_fstatfs64, compat_sys_aarch32_fstatfs64)
 #define __NR_tgkill 268
 __SYSCALL(__NR_tgkill, sys_tgkill)
 #define __NR_utimes 269
 __SYSCALL(__NR_utimes, compat_sys_utimes)
 #define __NR_arm_fadvise64_64 270
-__SYSCALL(__NR_arm_fadvise64_64, compat_sys_fadvise64_64_wrapper)
+__SYSCALL(__NR_arm_fadvise64_64, compat_sys_aarch32_fadvise64_64)
 #define __NR_pciconfig_iobase 271
 __SYSCALL(__NR_pciconfig_iobase, sys_pciconfig_iobase)
 #define __NR_pciconfig_read 272
@@ -704,7 +704,7 @@ __SYSCALL(__NR_get_robust_list, compat_sys_get_robust_list)
 #define __NR_splice 340
 __SYSCALL(__NR_splice, sys_splice)
 #define __NR_sync_file_range2 341
-__SYSCALL(__NR_sync_file_range2, compat_sys_sync_file_range2_wrapper)
+__SYSCALL(__NR_sync_file_range2, compat_sys_aarch32_sync_file_range2)
 #define __NR_tee 342
 __SYSCALL(__NR_tee, sys_tee)
 #define __NR_vmsplice 343
@@ -726,7 +726,7 @@ __SYSCALL(__NR_timerfd_create, sys_timerfd_create)
 #define __NR_eventfd 351
 __SYSCALL(__NR_eventfd, sys_eventfd)
 #define __NR_fallocate 352
-__SYSCALL(__NR_fallocate, compat_sys_fallocate_wrapper)
+__SYSCALL(__NR_fallocate, compat_sys_aarch32_fallocate)
 #define __NR_timerfd_settime 353
 __SYSCALL(__NR_timerfd_settime, compat_sys_timerfd_settime)
 #define __NR_timerfd_gettime 354
@@ -817,6 +817,8 @@ __SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
 __SYSCALL(__NR_pkey_free, sys_pkey_free)
 #define __NR_statx 397
 __SYSCALL(__NR_statx, sys_statx)
+#define __NR_rseq 398
+__SYSCALL(__NR_rseq, sys_rseq)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 0025f8691046..95ac7374d723 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -18,7 +18,8 @@ arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   hyp-stub.o psci.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
-			   smp.o smp_spin_table.o topology.o smccc-call.o
+			   smp.o smp_spin_table.o topology.o smccc-call.o	\
+			   syscall.o
 
 extra-$(CONFIG_EFI)			:= efi-entry.o
 
@@ -27,7 +28,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
 	$(call if_changed,objcopy)
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
-					   sys_compat.o entry32.o
+					   sys_compat.o
 arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
 arm64-obj-$(CONFIG_ARM64_MODULE_PLTS)	+= module-plts.o
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 7b09487ff8fb..ed46dc188b22 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -18,6 +18,7 @@
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
 #include <linux/cpumask.h>
+#include <linux/efi.h>
 #include <linux/efi-bgrt.h>
 #include <linux/init.h>
 #include <linux/irq.h>
@@ -29,13 +30,9 @@
 
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
+#include <asm/pgtable.h>
 #include <asm/smp_plat.h>
 
-#ifdef CONFIG_ACPI_APEI
-# include <linux/efi.h>
-# include <asm/pgtable.h>
-#endif
-
 int acpi_noirq = 1;		/* skip ACPI IRQ initialization */
 int acpi_disabled = 1;
 EXPORT_SYMBOL(acpi_disabled);
@@ -239,8 +236,7 @@ done:
 	}
 }
 
-#ifdef CONFIG_ACPI_APEI
-pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
+pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
 {
 	/*
 	 * According to "Table 8 Map: EFI memory types to AArch64 memory
@@ -261,4 +257,3 @@ pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
 		return __pgprot(PROT_NORMAL_NC);
 	return __pgprot(PROT_DEVICE_nGnRnE);
 }
-#endif
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
index d190a7b231bf..4f4f1815e047 100644
--- a/arch/arm64/kernel/acpi_numa.c
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -26,36 +26,73 @@
 #include <linux/module.h>
 #include <linux/topology.h>
 
-#include <acpi/processor.h>
 #include <asm/numa.h>
 
-static int cpus_in_srat;
+static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE };
 
-struct __node_cpu_hwid {
-	u32 node_id;    /* logical node containing this CPU */
-	u64 cpu_hwid;   /* MPIDR for this CPU */
-};
+int __init acpi_numa_get_nid(unsigned int cpu)
+{
+	return acpi_early_node_map[cpu];
+}
+
+static inline int get_cpu_for_acpi_id(u32 uid)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (uid == get_acpi_id_for_cpu(cpu))
+			return cpu;
 
-static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = {
-[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} };
+	return -EINVAL;
+}
 
-int acpi_numa_get_nid(unsigned int cpu, u64 hwid)
+static int __init acpi_parse_gicc_pxm(struct acpi_subtable_header *header,
+				      const unsigned long end)
 {
-	int i;
+	struct acpi_srat_gicc_affinity *pa;
+	int cpu, pxm, node;
 
-	for (i = 0; i < cpus_in_srat; i++) {
-		if (hwid == early_node_cpu_hwid[i].cpu_hwid)
-			return early_node_cpu_hwid[i].node_id;
-	}
+	if (srat_disabled())
+		return -EINVAL;
+
+	pa = (struct acpi_srat_gicc_affinity *)header;
+	if (!pa)
+		return -EINVAL;
+
+	if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
+		return 0;
 
-	return NUMA_NO_NODE;
+	pxm = pa->proximity_domain;
+	node = pxm_to_node(pxm);
+
+	/*
+	 * If we can't map the UID to a logical cpu this
+	 * means that the UID is not part of possible cpus
+	 * so we do not need a NUMA mapping for it, skip
+	 * the SRAT entry and keep parsing.
+	 */
+	cpu = get_cpu_for_acpi_id(pa->acpi_processor_uid);
+	if (cpu < 0)
+		return 0;
+
+	acpi_early_node_map[cpu] = node;
+	pr_info("SRAT: PXM %d -> MPIDR 0x%llx -> Node %d\n", pxm,
+		cpu_logical_map(cpu), node);
+
+	return 0;
+}
+
+void __init acpi_map_cpus_to_nodes(void)
+{
+	acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat),
+					    ACPI_SRAT_TYPE_GICC_AFFINITY,
+					    acpi_parse_gicc_pxm, 0);
 }
 
 /* Callback for Proximity Domain -> ACPI processor UID mapping */
 void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
 {
 	int pxm, node;
-	phys_cpuid_t mpidr;
 
 	if (srat_disabled())
 		return;
@@ -70,12 +107,6 @@ void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
 	if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
 		return;
 
-	if (cpus_in_srat >= NR_CPUS) {
-		pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n",
-			     NR_CPUS);
-		return;
-	}
-
 	pxm = pa->proximity_domain;
 	node = acpi_map_pxm_to_node(pxm);
 
@@ -85,20 +116,7 @@ void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
 		return;
 	}
 
-	mpidr = acpi_map_madt_entry(pa->acpi_processor_uid);
-	if (mpidr == PHYS_CPUID_INVALID) {
-		pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n",
-			pxm, pa->acpi_processor_uid);
-		bad_srat();
-		return;
-	}
-
-	early_node_cpu_hwid[cpus_in_srat].node_id = node;
-	early_node_cpu_hwid[cpus_in_srat].cpu_hwid =  mpidr;
 	node_set(node, numa_nodes_parsed);
-	cpus_in_srat++;
-	pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n",
-		pxm, mpidr, node);
 }
 
 int __init arm64_acpi_numa_init(void)
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 5c4bce4ac381..b5d603992d40 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -47,11 +47,11 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 	unsigned long replptr;
 
 	if (kernel_text_address(pc))
-		return 1;
+		return true;
 
 	replptr = (unsigned long)ALT_REPL_PTR(alt);
 	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return 0;
+		return false;
 
 	/*
 	 * Branching into *another* alternate sequence is doomed, and
@@ -122,7 +122,30 @@ static void patch_alternative(struct alt_instr *alt,
 	}
 }
 
-static void __apply_alternatives(void *alt_region, bool use_linear_alias)
+/*
+ * We provide our own, private D-cache cleaning function so that we don't
+ * accidentally call into the cache.S code, which is patched by us at
+ * runtime.
+ */
+static void clean_dcache_range_nopatch(u64 start, u64 end)
+{
+	u64 cur, d_size, ctr_el0;
+
+	ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0);
+	d_size = 4 << cpuid_feature_extract_unsigned_field(ctr_el0,
+							   CTR_DMINLINE_SHIFT);
+	cur = start & ~(d_size - 1);
+	do {
+		/*
+		 * We must clean+invalidate to the PoC in order to avoid
+		 * Cortex-A53 errata 826319, 827319, 824069 and 819472
+		 * (this corresponds to ARM64_WORKAROUND_CLEAN_CACHE)
+		 */
+		asm volatile("dc civac, %0" : : "r" (cur) : "memory");
+	} while (cur += d_size, cur < end);
+}
+
+static void __apply_alternatives(void *alt_region, bool is_module)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
@@ -145,7 +168,7 @@ static void __apply_alternatives(void *alt_region, bool use_linear_alias)
 		pr_info_once("patching kernel code\n");
 
 		origptr = ALT_ORIG_PTR(alt);
-		updptr = use_linear_alias ? lm_alias(origptr) : origptr;
+		updptr = is_module ? origptr : lm_alias(origptr);
 		nr_inst = alt->orig_len / AARCH64_INSN_SIZE;
 
 		if (alt->cpufeature < ARM64_CB_PATCH)
@@ -155,8 +178,20 @@ static void __apply_alternatives(void *alt_region, bool use_linear_alias)
 
 		alt_cb(alt, origptr, updptr, nr_inst);
 
-		flush_icache_range((uintptr_t)origptr,
-				   (uintptr_t)(origptr + nr_inst));
+		if (!is_module) {
+			clean_dcache_range_nopatch((u64)origptr,
+						   (u64)(origptr + nr_inst));
+		}
+	}
+
+	/*
+	 * The core module code takes care of cache maintenance in
+	 * flush_module_icache().
+	 */
+	if (!is_module) {
+		dsb(ish);
+		__flush_icache_all();
+		isb();
 	}
 }
 
@@ -178,7 +213,7 @@ static int __apply_alternatives_multi_stop(void *unused)
 		isb();
 	} else {
 		BUG_ON(alternatives_applied);
-		__apply_alternatives(&region, true);
+		__apply_alternatives(&region, false);
 		/* Barriers provided by the cache flushing */
 		WRITE_ONCE(alternatives_applied, 1);
 	}
@@ -192,12 +227,14 @@ void __init apply_alternatives_all(void)
 	stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask);
 }
 
-void apply_alternatives(void *start, size_t length)
+#ifdef CONFIG_MODULES
+void apply_alternatives_module(void *start, size_t length)
 {
 	struct alt_region region = {
 		.begin	= start,
 		.end	= start + length,
 	};
 
-	__apply_alternatives(&region, false);
+	__apply_alternatives(&region, true);
 }
+#endif
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index d4707abb2f16..92be1d12d590 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -441,8 +441,8 @@ static struct undef_hook swp_hooks[] = {
 	{
 		.instr_mask	= 0x0fb00ff0,
 		.instr_val	= 0x01000090,
-		.pstate_mask	= COMPAT_PSR_MODE_MASK,
-		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.pstate_mask	= PSR_AA32_MODE_MASK,
+		.pstate_val	= PSR_AA32_MODE_USR,
 		.fn		= swp_handler
 	},
 	{ }
@@ -511,9 +511,9 @@ ret:
 static int cp15_barrier_set_hw_mode(bool enable)
 {
 	if (enable)
-		config_sctlr_el1(0, SCTLR_EL1_CP15BEN);
+		sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_CP15BEN);
 	else
-		config_sctlr_el1(SCTLR_EL1_CP15BEN, 0);
+		sysreg_clear_set(sctlr_el1, SCTLR_EL1_CP15BEN, 0);
 	return 0;
 }
 
@@ -521,15 +521,15 @@ static struct undef_hook cp15_barrier_hooks[] = {
 	{
 		.instr_mask	= 0x0fff0fdf,
 		.instr_val	= 0x0e070f9a,
-		.pstate_mask	= COMPAT_PSR_MODE_MASK,
-		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.pstate_mask	= PSR_AA32_MODE_MASK,
+		.pstate_val	= PSR_AA32_MODE_USR,
 		.fn		= cp15barrier_handler,
 	},
 	{
 		.instr_mask	= 0x0fff0fff,
 		.instr_val	= 0x0e070f95,
-		.pstate_mask	= COMPAT_PSR_MODE_MASK,
-		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.pstate_mask	= PSR_AA32_MODE_MASK,
+		.pstate_val	= PSR_AA32_MODE_USR,
 		.fn		= cp15barrier_handler,
 	},
 	{ }
@@ -548,9 +548,9 @@ static int setend_set_hw_mode(bool enable)
 		return -EINVAL;
 
 	if (enable)
-		config_sctlr_el1(SCTLR_EL1_SED, 0);
+		sysreg_clear_set(sctlr_el1, SCTLR_EL1_SED, 0);
 	else
-		config_sctlr_el1(0, SCTLR_EL1_SED);
+		sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_SED);
 	return 0;
 }
 
@@ -562,10 +562,10 @@ static int compat_setend_handler(struct pt_regs *regs, u32 big_endian)
 
 	if (big_endian) {
 		insn = "setend be";
-		regs->pstate |= COMPAT_PSR_E_BIT;
+		regs->pstate |= PSR_AA32_E_BIT;
 	} else {
 		insn = "setend le";
-		regs->pstate &= ~COMPAT_PSR_E_BIT;
+		regs->pstate &= ~PSR_AA32_E_BIT;
 	}
 
 	trace_instruction_emulation(insn, regs->pc);
@@ -593,16 +593,16 @@ static struct undef_hook setend_hooks[] = {
 	{
 		.instr_mask	= 0xfffffdff,
 		.instr_val	= 0xf1010000,
-		.pstate_mask	= COMPAT_PSR_MODE_MASK,
-		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.pstate_mask	= PSR_AA32_MODE_MASK,
+		.pstate_val	= PSR_AA32_MODE_USR,
 		.fn		= a32_setend_handler,
 	},
 	{
 		/* Thumb mode */
 		.instr_mask	= 0x0000fff7,
 		.instr_val	= 0x0000b650,
-		.pstate_mask	= (COMPAT_PSR_T_BIT | COMPAT_PSR_MODE_MASK),
-		.pstate_val	= (COMPAT_PSR_T_BIT | COMPAT_PSR_MODE_USR),
+		.pstate_mask	= (PSR_AA32_T_BIT | PSR_AA32_MODE_MASK),
+		.pstate_val	= (PSR_AA32_T_BIT | PSR_AA32_MODE_USR),
 		.fn		= t16_setend_handler,
 	},
 	{}
diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h
index 6c2b1b4f57c9..fad90e4935fb 100644
--- a/arch/arm64/kernel/cpu-reset.h
+++ b/arch/arm64/kernel/cpu-reset.h
@@ -16,13 +16,14 @@
 void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry,
 	unsigned long arg0, unsigned long arg1, unsigned long arg2);
 
-static inline void __noreturn cpu_soft_restart(unsigned long el2_switch,
-	unsigned long entry, unsigned long arg0, unsigned long arg1,
-	unsigned long arg2)
+static inline void __noreturn cpu_soft_restart(unsigned long entry,
+					       unsigned long arg0,
+					       unsigned long arg1,
+					       unsigned long arg2)
 {
 	typeof(__cpu_soft_restart) *restart;
 
-	el2_switch = el2_switch && !is_kernel_in_hyp_mode() &&
+	unsigned long el2_switch = !is_kernel_in_hyp_mode() &&
 		is_hyp_mode_available();
 	restart = (void *)__pa_symbol(__cpu_soft_restart);
 
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 1d2b6d768efe..dec10898d688 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -65,19 +65,24 @@ is_kryo_midr(const struct arm64_cpu_capabilities *entry, int scope)
 }
 
 static bool
-has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
-				int scope)
+has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
+			  int scope)
 {
+	u64 mask = CTR_CACHE_MINLINE_MASK;
+
+	/* Skip matching the min line sizes for cache type check */
+	if (entry->capability == ARM64_MISMATCHED_CACHE_TYPE)
+		mask ^= arm64_ftr_reg_ctrel0.strict_mask;
+
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return (read_cpuid_cachetype() & arm64_ftr_reg_ctrel0.strict_mask) !=
-		(arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
+	return (read_cpuid_cachetype() & mask) !=
+	       (arm64_ftr_reg_ctrel0.sys_val & mask);
 }
 
 static void
 cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
 {
-	/* Clear SCTLR_EL1.UCT */
-	config_sctlr_el1(SCTLR_EL1_UCT, 0);
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
 atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
@@ -101,7 +106,7 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 	for (i = 0; i < SZ_2K; i += 0x80)
 		memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start);
 
-	flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
+	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
 }
 
 static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
@@ -613,7 +618,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "Mismatched cache line size",
 		.capability = ARM64_MISMATCHED_CACHE_LINE_SIZE,
-		.matches = has_mismatched_cache_line_size,
+		.matches = has_mismatched_cache_type,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
+	{
+		.desc = "Mismatched cache type",
+		.capability = ARM64_MISMATCHED_CACHE_TYPE,
+		.matches = has_mismatched_cache_type,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.cpu_enable = cpu_enable_trap_ctr_access,
 	},
@@ -649,7 +661,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
-		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.cpu_enable = enable_smccc_arch_workaround_1,
 		ERRATA_MIDR_RANGE_LIST(arm64_bp_harden_smccc_cpus),
 	},
@@ -658,7 +669,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "EL2 vector hardening",
 		.capability = ARM64_HARDEN_EL2_VECTORS,
-		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
 	},
 #endif
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f24892a40d2c..611e8921c3d4 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -214,7 +214,7 @@ static const struct arm64_ftr_bits ftr_ctr[] = {
 	 * If we have differing I-cache policies, report it as the weakest - VIPT.
 	 */
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_VIPT),	/* L1Ip */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* IminLine */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IMINLINE_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -1351,9 +1351,9 @@ static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 
 static void update_cpu_capabilities(u16 scope_mask)
 {
-	__update_cpu_capabilities(arm64_features, scope_mask, "detected:");
 	__update_cpu_capabilities(arm64_errata, scope_mask,
 				  "enabling workaround for");
+	__update_cpu_capabilities(arm64_features, scope_mask, "detected:");
 }
 
 static int __enable_cpu_capability(void *arg)
@@ -1408,8 +1408,8 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 
 static void __init enable_cpu_capabilities(u16 scope_mask)
 {
-	__enable_cpu_capabilities(arm64_features, scope_mask);
 	__enable_cpu_capabilities(arm64_errata, scope_mask);
+	__enable_cpu_capabilities(arm64_features, scope_mask);
 }
 
 /*
@@ -1723,7 +1723,7 @@ static int emulate_mrs(struct pt_regs *regs, u32 insn)
 static struct undef_hook mrs_hook = {
 	.instr_mask = 0xfff00000,
 	.instr_val  = 0xd5300000,
-	.pstate_mask = COMPAT_PSR_MODE_MASK,
+	.pstate_mask = PSR_AA32_MODE_MASK,
 	.pstate_val = PSR_MODE_EL0t,
 	.fn = emulate_mrs,
 };
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 28ad8799406f..09dbea221a27 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -41,19 +41,9 @@
  * Context tracking subsystem.  Used to instrument transitions
  * between user and kernel mode.
  */
-	.macro ct_user_exit, syscall = 0
+	.macro ct_user_exit
 #ifdef CONFIG_CONTEXT_TRACKING
 	bl	context_tracking_user_exit
-	.if \syscall == 1
-	/*
-	 * Save/restore needed during syscalls.  Restore syscall arguments from
-	 * the values already saved on stack during kernel_entry.
-	 */
-	ldp	x0, x1, [sp]
-	ldp	x2, x3, [sp, #S_X2]
-	ldp	x4, x5, [sp, #S_X4]
-	ldp	x6, x7, [sp, #S_X6]
-	.endif
 #endif
 	.endm
 
@@ -63,6 +53,12 @@
 #endif
 	.endm
 
+	.macro	clear_gp_regs
+	.irp	n,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29
+	mov	x\n, xzr
+	.endr
+	.endm
+
 /*
  * Bad Abort numbers
  *-----------------
@@ -140,20 +136,21 @@ alternative_else_nop_endif
 
 	// This macro corrupts x0-x3. It is the caller's duty
 	// to save/restore them if required.
-	.macro	apply_ssbd, state, targ, tmp1, tmp2
+	.macro	apply_ssbd, state, tmp1, tmp2
 #ifdef CONFIG_ARM64_SSBD
 alternative_cb	arm64_enable_wa2_handling
-	b	\targ
+	b	.L__asm_ssbd_skip\@
 alternative_cb_end
 	ldr_this_cpu	\tmp2, arm64_ssbd_callback_required, \tmp1
-	cbz	\tmp2, \targ
+	cbz	\tmp2,	.L__asm_ssbd_skip\@
 	ldr	\tmp2, [tsk, #TSK_TI_FLAGS]
-	tbnz	\tmp2, #TIF_SSBD, \targ
+	tbnz	\tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@
 	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_2
 	mov	w1, #\state
 alternative_cb	arm64_update_smccc_conduit
 	nop					// Patched to SMC/HVC #0
 alternative_cb_end
+.L__asm_ssbd_skip\@:
 #endif
 	.endm
 
@@ -178,20 +175,14 @@ alternative_cb_end
 	stp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
+	clear_gp_regs
 	mrs	x21, sp_el0
 	ldr_this_cpu	tsk, __entry_task, x20	// Ensure MDSCR_EL1.SS is clear,
 	ldr	x19, [tsk, #TSK_TI_FLAGS]	// since we can unmask debug
 	disable_step_tsk x19, x20		// exceptions when scheduling.
 
-	apply_ssbd 1, 1f, x22, x23
-
-#ifdef CONFIG_ARM64_SSBD
-	ldp	x0, x1, [sp, #16 * 0]
-	ldp	x2, x3, [sp, #16 * 1]
-#endif
-1:
+	apply_ssbd 1, x22, x23
 
-	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	get_thread_info tsk
@@ -331,8 +322,7 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 3:
-	apply_ssbd 0, 5f, x0, x1
-5:
+	apply_ssbd 0, x0, x1
 	.endif
 
 	msr	elr_el1, x21			// set up the return data
@@ -720,14 +710,9 @@ el0_sync_compat:
 	b.ge	el0_dbg
 	b	el0_inv
 el0_svc_compat:
-	/*
-	 * AArch32 syscall handling
-	 */
-	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
-	adrp	stbl, compat_sys_call_table	// load compat syscall table pointer
-	mov	wscno, w7			// syscall number in w7 (r7)
-	mov     wsc_nr, #__NR_compat_syscalls
-	b	el0_svc_naked
+	mov	x0, sp
+	bl	el0_svc_compat_handler
+	b	ret_to_user
 
 	.align	6
 el0_irq_compat:
@@ -896,25 +881,6 @@ el0_error_naked:
 	b	ret_to_user
 ENDPROC(el0_error)
 
-
-/*
- * This is the fast syscall return path.  We do as little as possible here,
- * and this includes saving x0 back into the kernel stack.
- */
-ret_fast_syscall:
-	disable_daif
-	str	x0, [sp, #S_X0]			// returned x0
-	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for syscall tracing
-	and	x2, x1, #_TIF_SYSCALL_WORK
-	cbnz	x2, ret_fast_syscall_trace
-	and	x2, x1, #_TIF_WORK_MASK
-	cbnz	x2, work_pending
-	enable_step_tsk x1, x2
-	kernel_exit 0
-ret_fast_syscall_trace:
-	enable_daif
-	b	__sys_trace_return_skipped	// we already saved x0
-
 /*
  * Ok, we need to do extra processing, enter the slow path.
  */
@@ -936,6 +902,9 @@ ret_to_user:
 	cbnz	x2, work_pending
 finish_ret_to_user:
 	enable_step_tsk x1, x2
+#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+	bl	stackleak_erase
+#endif
 	kernel_exit 0
 ENDPROC(ret_to_user)
 
@@ -944,85 +913,10 @@ ENDPROC(ret_to_user)
  */
 	.align	6
 el0_svc:
-	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
-	adrp	stbl, sys_call_table		// load syscall table pointer
-	mov	wscno, w8			// syscall number in w8
-	mov	wsc_nr, #__NR_syscalls
-
-#ifdef CONFIG_ARM64_SVE
-alternative_if_not ARM64_SVE
-	b	el0_svc_naked
-alternative_else_nop_endif
-	tbz	x16, #TIF_SVE, el0_svc_naked	// Skip unless TIF_SVE set:
-	bic	x16, x16, #_TIF_SVE		// discard SVE state
-	str	x16, [tsk, #TSK_TI_FLAGS]
-
-	/*
-	 * task_fpsimd_load() won't be called to update CPACR_EL1 in
-	 * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
-	 * happens if a context switch or kernel_neon_begin() or context
-	 * modification (sigreturn, ptrace) intervenes.
-	 * So, ensure that CPACR_EL1 is already correct for the fast-path case:
-	 */
-	mrs	x9, cpacr_el1
-	bic	x9, x9, #CPACR_EL1_ZEN_EL0EN	// disable SVE for el0
-	msr	cpacr_el1, x9			// synchronised by eret to el0
-#endif
-
-el0_svc_naked:					// compat entry point
-	stp	x0, xscno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
-	enable_daif
-	ct_user_exit 1
-
-	tst	x16, #_TIF_SYSCALL_WORK		// check for syscall hooks
-	b.ne	__sys_trace
-	cmp     wscno, wsc_nr			// check upper syscall limit
-	b.hs	ni_sys
-	mask_nospec64 xscno, xsc_nr, x19	// enforce bounds for syscall number
-	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
-	blr	x16				// call sys_* routine
-	b	ret_fast_syscall
-ni_sys:
-	mov	x0, sp
-	bl	do_ni_syscall
-	b	ret_fast_syscall
-ENDPROC(el0_svc)
-
-	/*
-	 * This is the really slow path.  We're going to be doing context
-	 * switches, and waiting for our parent to respond.
-	 */
-__sys_trace:
-	cmp     wscno, #NO_SYSCALL		// user-issued syscall(-1)?
-	b.ne	1f
-	mov	x0, #-ENOSYS			// set default errno if so
-	str	x0, [sp, #S_X0]
-1:	mov	x0, sp
-	bl	syscall_trace_enter
-	cmp	w0, #NO_SYSCALL			// skip the syscall?
-	b.eq	__sys_trace_return_skipped
-	mov	wscno, w0			// syscall number (possibly new)
-	mov	x1, sp				// pointer to regs
-	cmp	wscno, wsc_nr			// check upper syscall limit
-	b.hs	__ni_sys_trace
-	ldp	x0, x1, [sp]			// restore the syscall args
-	ldp	x2, x3, [sp, #S_X2]
-	ldp	x4, x5, [sp, #S_X4]
-	ldp	x6, x7, [sp, #S_X6]
-	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
-	blr	x16				// call sys_* routine
-
-__sys_trace_return:
-	str	x0, [sp, #S_X0]			// save returned x0
-__sys_trace_return_skipped:
 	mov	x0, sp
-	bl	syscall_trace_exit
+	bl	el0_svc_handler
 	b	ret_to_user
-
-__ni_sys_trace:
-	mov	x0, sp
-	bl	do_ni_syscall
-	b	__sys_trace_return
+ENDPROC(el0_svc)
 
 	.popsection				// .entry.text
 
@@ -1138,14 +1032,6 @@ __entry_tramp_data_start:
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 /*
- * Special system call wrappers.
- */
-ENTRY(sys_rt_sigreturn_wrapper)
-	mov	x0, sp
-	b	sys_rt_sigreturn
-ENDPROC(sys_rt_sigreturn_wrapper)
-
-/*
  * Register switch for AArch64. The callee-saved registers need to be saved
  * and restored. On entry:
  *   x0 = previous task_struct (must be preserved across the switch)
diff --git a/arch/arm64/kernel/entry32.S b/arch/arm64/kernel/entry32.S
deleted file mode 100644
index f332d5d1f6b4..000000000000
--- a/arch/arm64/kernel/entry32.S
+++ /dev/null
@@ -1,121 +0,0 @@
-/*
- * Compat system call wrappers
- *
- * Copyright (C) 2012 ARM Ltd.
- * Authors: Will Deacon <will.deacon@arm.com>
- *	    Catalin Marinas <catalin.marinas@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <linux/const.h>
-
-#include <asm/assembler.h>
-#include <asm/asm-offsets.h>
-#include <asm/errno.h>
-#include <asm/page.h>
-
-/*
- * System call wrappers for the AArch32 compatibility layer.
- */
-
-ENTRY(compat_sys_sigreturn_wrapper)
-	mov	x0, sp
-	b	compat_sys_sigreturn
-ENDPROC(compat_sys_sigreturn_wrapper)
-
-ENTRY(compat_sys_rt_sigreturn_wrapper)
-	mov	x0, sp
-	b	compat_sys_rt_sigreturn
-ENDPROC(compat_sys_rt_sigreturn_wrapper)
-
-ENTRY(compat_sys_statfs64_wrapper)
-	mov	w3, #84
-	cmp	w1, #88
-	csel	w1, w3, w1, eq
-	b	compat_sys_statfs64
-ENDPROC(compat_sys_statfs64_wrapper)
-
-ENTRY(compat_sys_fstatfs64_wrapper)
-	mov	w3, #84
-	cmp	w1, #88
-	csel	w1, w3, w1, eq
-	b	compat_sys_fstatfs64
-ENDPROC(compat_sys_fstatfs64_wrapper)
-
-/*
- * Note: off_4k (w5) is always in units of 4K. If we can't do the
- * requested offset because it is not page-aligned, we return -EINVAL.
- */
-ENTRY(compat_sys_mmap2_wrapper)
-#if PAGE_SHIFT > 12
-	tst	w5, #~PAGE_MASK >> 12
-	b.ne	1f
-	lsr	w5, w5, #PAGE_SHIFT - 12
-#endif
-	b	sys_mmap_pgoff
-1:	mov	x0, #-EINVAL
-	ret
-ENDPROC(compat_sys_mmap2_wrapper)
-
-/*
- * Wrappers for AArch32 syscalls that either take 64-bit parameters
- * in registers or that take 32-bit parameters which require sign
- * extension.
- */
-ENTRY(compat_sys_pread64_wrapper)
-	regs_to_64	x3, x4, x5
-	b	sys_pread64
-ENDPROC(compat_sys_pread64_wrapper)
-
-ENTRY(compat_sys_pwrite64_wrapper)
-	regs_to_64	x3, x4, x5
-	b	sys_pwrite64
-ENDPROC(compat_sys_pwrite64_wrapper)
-
-ENTRY(compat_sys_truncate64_wrapper)
-	regs_to_64	x1, x2, x3
-	b	sys_truncate
-ENDPROC(compat_sys_truncate64_wrapper)
-
-ENTRY(compat_sys_ftruncate64_wrapper)
-	regs_to_64	x1, x2, x3
-	b	sys_ftruncate
-ENDPROC(compat_sys_ftruncate64_wrapper)
-
-ENTRY(compat_sys_readahead_wrapper)
-	regs_to_64	x1, x2, x3
-	mov	w2, w4
-	b	sys_readahead
-ENDPROC(compat_sys_readahead_wrapper)
-
-ENTRY(compat_sys_fadvise64_64_wrapper)
-	mov	w6, w1
-	regs_to_64	x1, x2, x3
-	regs_to_64	x2, x4, x5
-	mov	w3, w6
-	b	sys_fadvise64_64
-ENDPROC(compat_sys_fadvise64_64_wrapper)
-
-ENTRY(compat_sys_sync_file_range2_wrapper)
-	regs_to_64	x2, x2, x3
-	regs_to_64	x3, x4, x5
-	b	sys_sync_file_range2
-ENDPROC(compat_sys_sync_file_range2_wrapper)
-
-ENTRY(compat_sys_fallocate_wrapper)
-	regs_to_64	x2, x2, x3
-	regs_to_64	x3, x4, x5
-	b	sys_fallocate
-ENDPROC(compat_sys_fallocate_wrapper)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 84c68b14f1b2..58c53bc96928 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -159,25 +159,6 @@ static void sve_free(struct task_struct *task)
 	__sve_free(task);
 }
 
-static void change_cpacr(u64 val, u64 mask)
-{
-	u64 cpacr = read_sysreg(CPACR_EL1);
-	u64 new = (cpacr & ~mask) | val;
-
-	if (new != cpacr)
-		write_sysreg(new, CPACR_EL1);
-}
-
-static void sve_user_disable(void)
-{
-	change_cpacr(0, CPACR_EL1_ZEN_EL0EN);
-}
-
-static void sve_user_enable(void)
-{
-	change_cpacr(CPACR_EL1_ZEN_EL0EN, CPACR_EL1_ZEN_EL0EN);
-}
-
 /*
  * TIF_SVE controls whether a task can use SVE without trapping while
  * in userspace, and also the way a task's FPSIMD/SVE state is stored
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 413dbe530da8..8c9644376326 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -343,14 +343,13 @@ static int get_hbp_len(u8 hbp_len)
 /*
  * Check whether bp virtual address is in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->ctrl.len);
+	va = hw->address;
+	len = get_hbp_len(hw->ctrl.len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -421,53 +420,53 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+		hw->ctrl.type = ARM_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->ctrl.type = ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_3:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_3;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_3;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_5:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_5;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_5;
 		break;
 	case HW_BREAKPOINT_LEN_6:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_6;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_6;
 		break;
 	case HW_BREAKPOINT_LEN_7:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_7;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_7;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
 		break;
 	default:
 		return -EINVAL;
@@ -478,37 +477,37 @@ static int arch_build_bp_info(struct perf_event *bp)
 	 * AArch32 also requires breakpoints of length 2 for Thumb.
 	 * Watchpoints can be of length 1, 2, 4 or 8 bytes.
 	 */
-	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
+	if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		if (is_compat_bp(bp)) {
-			if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
-			    info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+			if (hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+			    hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
 				return -EINVAL;
-		} else if (info->ctrl.len != ARM_BREAKPOINT_LEN_4) {
+		} else if (hw->ctrl.len != ARM_BREAKPOINT_LEN_4) {
 			/*
 			 * FIXME: Some tools (I'm looking at you perf) assume
 			 *	  that breakpoints should be sizeof(long). This
 			 *	  is nonsense. For now, we fix up the parameter
 			 *	  but we should probably return -EINVAL instead.
 			 */
-			info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+			hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		}
 	}
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/*
 	 * Privilege
 	 * Note that we disallow combined EL0/EL1 breakpoints because
 	 * that would complicate the stepping code.
 	 */
-	if (arch_check_bp_in_kernelspace(bp))
-		info->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
+	if (arch_check_bp_in_kernelspace(hw))
+		hw->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
 	else
-		info->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
+		hw->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
 
 	/* Enabled? */
-	info->ctrl.enabled = !bp->attr.disabled;
+	hw->ctrl.enabled = !attr->disabled;
 
 	return 0;
 }
@@ -516,14 +515,15 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings.
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	int ret;
 	u64 alignment_mask, offset;
 
 	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
@@ -537,42 +537,42 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * that here.
 	 */
 	if (is_compat_bp(bp)) {
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
 			alignment_mask = 0x7;
 		else
 			alignment_mask = 0x3;
-		offset = info->address & alignment_mask;
+		offset = hw->address & alignment_mask;
 		switch (offset) {
 		case 0:
 			/* Aligned */
 			break;
 		case 1:
 			/* Allow single byte watchpoint. */
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 				break;
 		case 2:
 			/* Allow halfword watchpoints and breakpoints. */
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 				break;
 		default:
 			return -EINVAL;
 		}
 	} else {
-		if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE)
+		if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE)
 			alignment_mask = 0x3;
 		else
 			alignment_mask = 0x7;
-		offset = info->address & alignment_mask;
+		offset = hw->address & alignment_mask;
 	}
 
-	info->address &= ~alignment_mask;
-	info->ctrl.len <<= offset;
+	hw->address &= ~alignment_mask;
+	hw->ctrl.len <<= offset;
 
 	/*
 	 * Disallow per-task kernel breakpoints since these would
 	 * complicate the stepping code.
 	 */
-	if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
+	if (hw->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 816d03c4c913..2b3413549734 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -149,20 +149,6 @@ int __kprobes aarch64_insn_write(void *addr, u32 insn)
 	return __aarch64_insn_write(addr, cpu_to_le32(insn));
 }
 
-static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn)
-{
-	if (aarch64_get_insn_class(insn) != AARCH64_INSN_CLS_BR_SYS)
-		return false;
-
-	return	aarch64_insn_is_b(insn) ||
-		aarch64_insn_is_bl(insn) ||
-		aarch64_insn_is_svc(insn) ||
-		aarch64_insn_is_hvc(insn) ||
-		aarch64_insn_is_smc(insn) ||
-		aarch64_insn_is_brk(insn) ||
-		aarch64_insn_is_nop(insn);
-}
-
 bool __kprobes aarch64_insn_uses_literal(u32 insn)
 {
 	/* ldr/ldrsw (literal), prfm */
@@ -189,22 +175,6 @@ bool __kprobes aarch64_insn_is_branch(u32 insn)
 		aarch64_insn_is_bcond(insn);
 }
 
-/*
- * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
- * Section B2.6.5 "Concurrent modification and execution of instructions":
- * Concurrent modification and execution of instructions can lead to the
- * resulting instruction performing any behavior that can be achieved by
- * executing any sequence of instructions that can be executed from the
- * same Exception level, except where the instruction before modification
- * and the instruction after modification is a B, BL, NOP, BKPT, SVC, HVC,
- * or SMC instruction.
- */
-bool __kprobes aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn)
-{
-	return __aarch64_insn_hotpatch_safe(old_insn) &&
-	       __aarch64_insn_hotpatch_safe(new_insn);
-}
-
 int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
 {
 	u32 *tp = addr;
@@ -216,8 +186,8 @@ int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
 
 	ret = aarch64_insn_write(tp, insn);
 	if (ret == 0)
-		flush_icache_range((uintptr_t)tp,
-				   (uintptr_t)tp + AARCH64_INSN_SIZE);
+		__flush_icache_range((uintptr_t)tp,
+				     (uintptr_t)tp + AARCH64_INSN_SIZE);
 
 	return ret;
 }
@@ -239,11 +209,6 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 		for (i = 0; ret == 0 && i < pp->insn_cnt; i++)
 			ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i],
 							     pp->new_insns[i]);
-		/*
-		 * aarch64_insn_patch_text_nosync() calls flush_icache_range(),
-		 * which ends with "dsb; isb" pair guaranteeing global
-		 * visibility.
-		 */
 		/* Notify other processors with an additional increment. */
 		atomic_inc(&pp->cpu_count);
 	} else {
@@ -255,8 +220,7 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 	return ret;
 }
 
-static
-int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
+int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
 {
 	struct aarch64_insn_patch patch = {
 		.text_addrs = addrs,
@@ -272,34 +236,6 @@ int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
 				       cpu_online_mask);
 }
 
-int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
-{
-	int ret;
-	u32 insn;
-
-	/* Unsafe to patch multiple instructions without synchronizaiton */
-	if (cnt == 1) {
-		ret = aarch64_insn_read(addrs[0], &insn);
-		if (ret)
-			return ret;
-
-		if (aarch64_insn_hotpatch_safe(insn, insns[0])) {
-			/*
-			 * ARMv8 architecture doesn't guarantee all CPUs see
-			 * the new instruction after returning from function
-			 * aarch64_insn_patch_text_nosync(). So send IPIs to
-			 * all other CPUs to achieve instruction
-			 * synchronization.
-			 */
-			ret = aarch64_insn_patch_text_nosync(addrs[0], insns[0]);
-			kick_all_cpus_sync();
-			return ret;
-		}
-	}
-
-	return aarch64_insn_patch_text_sync(addrs, insns, cnt);
-}
-
 static int __kprobes aarch64_get_imm_shift_mask(enum aarch64_insn_imm_type type,
 						u32 *maskp, int *shiftp)
 {
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 60e5fc661f74..780a12f59a8f 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -42,16 +42,6 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-void (*handle_arch_irq)(struct pt_regs *) = NULL;
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	if (handle_arch_irq)
-		return;
-
-	handle_arch_irq = handle_irq;
-}
-
 #ifdef CONFIG_VMAP_STACK
 static void init_irq_stacks(void)
 {
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index f76ea92dff91..f6a5c6bc1434 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -184,8 +184,15 @@ void machine_kexec(struct kimage *kimage)
 
 	/* Flush the reboot_code_buffer in preparation for its execution. */
 	__flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size);
-	flush_icache_range((uintptr_t)reboot_code_buffer,
-		arm64_relocate_new_kernel_size);
+
+	/*
+	 * Although we've killed off the secondary CPUs, we don't update
+	 * the online mask if we're handling a crash kernel and consequently
+	 * need to avoid flush_icache_range(), which will attempt to IPI
+	 * the offline CPUs. Therefore, we must use the __* variant here.
+	 */
+	__flush_icache_range((uintptr_t)reboot_code_buffer,
+			     arm64_relocate_new_kernel_size);
 
 	/* Flush the kimage list and its buffers. */
 	kexec_list_flush(kimage);
@@ -207,8 +214,7 @@ void machine_kexec(struct kimage *kimage)
 	 * relocation is complete.
 	 */
 
-	cpu_soft_restart(kimage != kexec_crash_image,
-		reboot_code_buffer_phys, kimage->head, kimage->start, 0);
+	cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, 0);
 
 	BUG(); /* Should never get here. */
 }
@@ -361,4 +367,5 @@ void arch_crash_save_vmcoreinfo(void)
 						kimage_voffset);
 	vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
 						PHYS_OFFSET);
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
 }
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 155fd91e78f4..f0f27aeefb73 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -448,9 +448,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
-		if (strcmp(".altinstructions", secstrs + s->sh_name) == 0) {
-			apply_alternatives((void *)s->sh_addr, s->sh_size);
-		}
+		if (strcmp(".altinstructions", secstrs + s->sh_name) == 0)
+			apply_alternatives_module((void *)s->sh_addr, s->sh_size);
 #ifdef CONFIG_ARM64_MODULE_PLTS
 		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
 		    !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name))
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 33147aacdafd..8e38d5267f22 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -25,6 +25,7 @@
 #include <asm/virt.h>
 
 #include <linux/acpi.h>
+#include <linux/clocksource.h>
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
@@ -446,9 +447,16 @@ static struct attribute_group armv8_pmuv3_events_attr_group = {
 };
 
 PMU_FORMAT_ATTR(event, "config:0-15");
+PMU_FORMAT_ATTR(long, "config1:0");
+
+static inline bool armv8pmu_event_is_64bit(struct perf_event *event)
+{
+	return event->attr.config1 & 0x1;
+}
 
 static struct attribute *armv8_pmuv3_format_attrs[] = {
 	&format_attr_event.attr,
+	&format_attr_long.attr,
 	NULL,
 };
 
@@ -466,6 +474,21 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 	(ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
 
 /*
+ * We must chain two programmable counters for 64 bit events,
+ * except when we have allocated the 64bit cycle counter (for CPU
+ * cycles event). This must be called only when the event has
+ * a counter allocated.
+ */
+static inline bool armv8pmu_event_is_chained(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	return !WARN_ON(idx < 0) &&
+	       armv8pmu_event_is_64bit(event) &&
+	       (idx != ARMV8_IDX_CYCLE_COUNTER);
+}
+
+/*
  * ARMv8 low level PMU access
  */
 
@@ -503,34 +526,68 @@ static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
 	return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
 }
 
-static inline int armv8pmu_select_counter(int idx)
+static inline void armv8pmu_select_counter(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
 	write_sysreg(counter, pmselr_el0);
 	isb();
+}
 
-	return idx;
+static inline u32 armv8pmu_read_evcntr(int idx)
+{
+	armv8pmu_select_counter(idx);
+	return read_sysreg(pmxevcntr_el0);
+}
+
+static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+	u64 val = 0;
+
+	val = armv8pmu_read_evcntr(idx);
+	if (armv8pmu_event_is_chained(event))
+		val = (val << 32) | armv8pmu_read_evcntr(idx - 1);
+	return val;
 }
 
-static inline u32 armv8pmu_read_counter(struct perf_event *event)
+static inline u64 armv8pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	u32 value = 0;
+	u64 value = 0;
 
 	if (!armv8pmu_counter_valid(cpu_pmu, idx))
 		pr_err("CPU%u reading wrong counter %d\n",
 			smp_processor_id(), idx);
 	else if (idx == ARMV8_IDX_CYCLE_COUNTER)
 		value = read_sysreg(pmccntr_el0);
-	else if (armv8pmu_select_counter(idx) == idx)
-		value = read_sysreg(pmxevcntr_el0);
+	else
+		value = armv8pmu_read_hw_counter(event);
 
 	return value;
 }
 
-static inline void armv8pmu_write_counter(struct perf_event *event, u32 value)
+static inline void armv8pmu_write_evcntr(int idx, u32 value)
+{
+	armv8pmu_select_counter(idx);
+	write_sysreg(value, pmxevcntr_el0);
+}
+
+static inline void armv8pmu_write_hw_counter(struct perf_event *event,
+					     u64 value)
+{
+	int idx = event->hw.idx;
+
+	if (armv8pmu_event_is_chained(event)) {
+		armv8pmu_write_evcntr(idx, upper_32_bits(value));
+		armv8pmu_write_evcntr(idx - 1, lower_32_bits(value));
+	} else {
+		armv8pmu_write_evcntr(idx, value);
+	}
+}
+
+static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -541,22 +598,43 @@ static inline void armv8pmu_write_counter(struct perf_event *event, u32 value)
 			smp_processor_id(), idx);
 	else if (idx == ARMV8_IDX_CYCLE_COUNTER) {
 		/*
-		 * Set the upper 32bits as this is a 64bit counter but we only
-		 * count using the lower 32bits and we want an interrupt when
-		 * it overflows.
+		 * The cycles counter is really a 64-bit counter.
+		 * When treating it as a 32-bit counter, we only count
+		 * the lower 32 bits, and set the upper 32-bits so that
+		 * we get an interrupt upon 32-bit overflow.
 		 */
-		u64 value64 = 0xffffffff00000000ULL | value;
-
-		write_sysreg(value64, pmccntr_el0);
-	} else if (armv8pmu_select_counter(idx) == idx)
-		write_sysreg(value, pmxevcntr_el0);
+		if (!armv8pmu_event_is_64bit(event))
+			value |= 0xffffffff00000000ULL;
+		write_sysreg(value, pmccntr_el0);
+	} else
+		armv8pmu_write_hw_counter(event, value);
 }
 
 static inline void armv8pmu_write_evtype(int idx, u32 val)
 {
-	if (armv8pmu_select_counter(idx) == idx) {
-		val &= ARMV8_PMU_EVTYPE_MASK;
-		write_sysreg(val, pmxevtyper_el0);
+	armv8pmu_select_counter(idx);
+	val &= ARMV8_PMU_EVTYPE_MASK;
+	write_sysreg(val, pmxevtyper_el0);
+}
+
+static inline void armv8pmu_write_event_type(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	/*
+	 * For chained events, the low counter is programmed to count
+	 * the event of interest and the high counter is programmed
+	 * with CHAIN event code with filters set to count at all ELs.
+	 */
+	if (armv8pmu_event_is_chained(event)) {
+		u32 chain_evt = ARMV8_PMUV3_PERFCTR_CHAIN |
+				ARMV8_PMU_INCLUDE_EL2;
+
+		armv8pmu_write_evtype(idx - 1, hwc->config_base);
+		armv8pmu_write_evtype(idx, chain_evt);
+	} else {
+		armv8pmu_write_evtype(idx, hwc->config_base);
 	}
 }
 
@@ -567,6 +645,16 @@ static inline int armv8pmu_enable_counter(int idx)
 	return idx;
 }
 
+static inline void armv8pmu_enable_event_counter(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	armv8pmu_enable_counter(idx);
+	if (armv8pmu_event_is_chained(event))
+		armv8pmu_enable_counter(idx - 1);
+	isb();
+}
+
 static inline int armv8pmu_disable_counter(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
@@ -574,6 +662,16 @@ static inline int armv8pmu_disable_counter(int idx)
 	return idx;
 }
 
+static inline void armv8pmu_disable_event_counter(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (armv8pmu_event_is_chained(event))
+		armv8pmu_disable_counter(idx - 1);
+	armv8pmu_disable_counter(idx);
+}
+
 static inline int armv8pmu_enable_intens(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
@@ -581,6 +679,11 @@ static inline int armv8pmu_enable_intens(int idx)
 	return idx;
 }
 
+static inline int armv8pmu_enable_event_irq(struct perf_event *event)
+{
+	return armv8pmu_enable_intens(event->hw.idx);
+}
+
 static inline int armv8pmu_disable_intens(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
@@ -593,6 +696,11 @@ static inline int armv8pmu_disable_intens(int idx)
 	return idx;
 }
 
+static inline int armv8pmu_disable_event_irq(struct perf_event *event)
+{
+	return armv8pmu_disable_intens(event->hw.idx);
+}
+
 static inline u32 armv8pmu_getreset_flags(void)
 {
 	u32 value;
@@ -610,10 +718,8 @@ static inline u32 armv8pmu_getreset_flags(void)
 static void armv8pmu_enable_event(struct perf_event *event)
 {
 	unsigned long flags;
-	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-	int idx = hwc->idx;
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
@@ -624,22 +730,22 @@ static void armv8pmu_enable_event(struct perf_event *event)
 	/*
 	 * Disable counter
 	 */
-	armv8pmu_disable_counter(idx);
+	armv8pmu_disable_event_counter(event);
 
 	/*
 	 * Set event (if destined for PMNx counters).
 	 */
-	armv8pmu_write_evtype(idx, hwc->config_base);
+	armv8pmu_write_event_type(event);
 
 	/*
 	 * Enable interrupt for this counter
 	 */
-	armv8pmu_enable_intens(idx);
+	armv8pmu_enable_event_irq(event);
 
 	/*
 	 * Enable counter
 	 */
-	armv8pmu_enable_counter(idx);
+	armv8pmu_enable_event_counter(event);
 
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
@@ -647,10 +753,8 @@ static void armv8pmu_enable_event(struct perf_event *event)
 static void armv8pmu_disable_event(struct perf_event *event)
 {
 	unsigned long flags;
-	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-	int idx = hwc->idx;
 
 	/*
 	 * Disable counter and interrupt
@@ -660,16 +764,38 @@ static void armv8pmu_disable_event(struct perf_event *event)
 	/*
 	 * Disable counter
 	 */
-	armv8pmu_disable_counter(idx);
+	armv8pmu_disable_event_counter(event);
 
 	/*
 	 * Disable interrupt for this counter
 	 */
-	armv8pmu_disable_intens(idx);
+	armv8pmu_disable_event_irq(event);
 
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
+static void armv8pmu_start(struct arm_pmu *cpu_pmu)
+{
+	unsigned long flags;
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+	/* Enable all counters */
+	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
+{
+	unsigned long flags;
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+	/* Disable all counters */
+	armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
 static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 {
 	u32 pmovsr;
@@ -694,6 +820,11 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	 */
 	regs = get_irq_regs();
 
+	/*
+	 * Stop the PMU while processing the counter overflows
+	 * to prevent skews in group events.
+	 */
+	armv8pmu_stop(cpu_pmu);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
@@ -718,6 +849,7 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 		if (perf_event_overflow(event, &data, regs))
 			cpu_pmu->disable(event);
 	}
+	armv8pmu_start(cpu_pmu);
 
 	/*
 	 * Handle the pending perf events.
@@ -731,32 +863,42 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	return IRQ_HANDLED;
 }
 
-static void armv8pmu_start(struct arm_pmu *cpu_pmu)
+static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc,
+				    struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	int idx;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
-	/* Enable all counters */
-	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+	for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; idx ++) {
+		if (!test_and_set_bit(idx, cpuc->used_mask))
+			return idx;
+	}
+	return -EAGAIN;
 }
 
-static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
+static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
+				   struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	int idx;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
-	/* Disable all counters */
-	armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+	/*
+	 * Chaining requires two consecutive event counters, where
+	 * the lower idx must be even.
+	 */
+	for (idx = ARMV8_IDX_COUNTER0 + 1; idx < cpu_pmu->num_events; idx += 2) {
+		if (!test_and_set_bit(idx, cpuc->used_mask)) {
+			/* Check if the preceding even counter is available */
+			if (!test_and_set_bit(idx - 1, cpuc->used_mask))
+				return idx;
+			/* Release the Odd counter */
+			clear_bit(idx, cpuc->used_mask);
+		}
+	}
+	return -EAGAIN;
 }
 
 static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 				  struct perf_event *event)
 {
-	int idx;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT;
@@ -770,13 +912,20 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	/*
 	 * Otherwise use events counters
 	 */
-	for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) {
-		if (!test_and_set_bit(idx, cpuc->used_mask))
-			return idx;
-	}
+	if (armv8pmu_event_is_64bit(event))
+		return	armv8pmu_get_chain_idx(cpuc, cpu_pmu);
+	else
+		return armv8pmu_get_single_idx(cpuc, cpu_pmu);
+}
 
-	/* The counters are all in use. */
-	return -EAGAIN;
+static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				     struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	clear_bit(idx, cpuc->used_mask);
+	if (armv8pmu_event_is_chained(event))
+		clear_bit(idx - 1, cpuc->used_mask);
 }
 
 /*
@@ -851,6 +1000,9 @@ static int __armv8_pmuv3_map_event(struct perf_event *event,
 				       &armv8_pmuv3_perf_cache_map,
 				       ARMV8_PMU_EVTYPE_EVENT);
 
+	if (armv8pmu_event_is_64bit(event))
+		event->hw.flags |= ARMPMU_EVT_64BIT;
+
 	/* Onl expose micro/arch events supported by this PMU */
 	if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS)
 	    && test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
@@ -957,10 +1109,10 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter		= armv8pmu_read_counter,
 	cpu_pmu->write_counter		= armv8pmu_write_counter,
 	cpu_pmu->get_event_idx		= armv8pmu_get_event_idx,
+	cpu_pmu->clear_event_idx	= armv8pmu_clear_event_idx,
 	cpu_pmu->start			= armv8pmu_start,
 	cpu_pmu->stop			= armv8pmu_stop,
 	cpu_pmu->reset			= armv8pmu_reset,
-	cpu_pmu->max_period		= (1LLU << 32) - 1,
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
 
 	return 0;
@@ -1127,3 +1279,32 @@ static int __init armv8_pmu_driver_init(void)
 		return arm_pmu_acpi_probe(armv8_pmuv3_init);
 }
 device_initcall(armv8_pmu_driver_init)
+
+void arch_perf_update_userpage(struct perf_event *event,
+			       struct perf_event_mmap_page *userpg, u64 now)
+{
+	u32 freq;
+	u32 shift;
+
+	/*
+	 * Internal timekeeping for enabled/running/stopped times
+	 * is always computed with the sched_clock.
+	 */
+	freq = arch_timer_get_rate();
+	userpg->cap_user_time = 1;
+
+	clocks_calc_mult_shift(&userpg->time_mult, &shift, freq,
+			NSEC_PER_SEC, 0);
+	/*
+	 * time_shift is not expected to be greater than 31 due to
+	 * the original published conversion algorithm shifting a
+	 * 32-bit value (now specifies a 64-bit value) - refer
+	 * perf_event_mmap_page documentation in perf_event.h.
+	 */
+	if (shift == 32) {
+		shift = 31;
+		userpg->time_mult >>= 1;
+	}
+	userpg->time_shift = (u16)shift;
+	userpg->time_offset = -now;
+}
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d849d9804011..e78c3ef04d95 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -275,7 +275,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p,
 		break;
 	case KPROBE_HIT_SS:
 	case KPROBE_REENTER:
-		pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr);
+		pr_warn("Unrecoverable kprobe detected.\n");
 		dump_kprobe(p);
 		BUG();
 		break;
@@ -395,9 +395,9 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			/*
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry,
-			 * so get out doing nothing more here.
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
 			 *
 			 * pre_handler can hit a breakpoint and can step thru
 			 * before return, keep PSTATE D-flag enabled until
@@ -405,16 +405,8 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				setup_singlestep(p, regs, kcb, 0);
-				return;
-			}
-		}
-	} else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) ==
-	    BRK64_OPCODE_KPROBES) && cur_kprobe) {
-		/* We probably hit a jprobe.  Call its break handler. */
-		if (cur_kprobe->break_handler  &&
-		     cur_kprobe->break_handler(cur_kprobe, regs)) {
-			setup_singlestep(cur_kprobe, regs, kcb, 0);
-			return;
+			} else
+				reset_current_kprobe();
 		}
 	}
 	/*
@@ -465,74 +457,6 @@ kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
 	return DBG_HOOK_HANDLED;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	/*
-	 * Since we can't be sure where in the stack frame "stacked"
-	 * pass-by-value arguments are stored we just don't try to
-	 * duplicate any of the stack. Do not use jprobes on functions that
-	 * use more than 64 bytes (after padding each to an 8 byte boundary)
-	 * of arguments, or pass individual arguments larger than 16 bytes.
-	 */
-
-	instruction_pointer_set(regs, (unsigned long) jp->entry);
-	preempt_disable();
-	pause_graph_tracing();
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	/*
-	 * Jprobe handler return by entering break exception,
-	 * encoded same as kprobe, but with following conditions
-	 * -a special PC to identify it from the other kprobes.
-	 * -restore stack addr to original saved pt_regs
-	 */
-	asm volatile("				mov sp, %0	\n"
-		     "jprobe_return_break:	brk %1		\n"
-		     :
-		     : "r" (kcb->jprobe_saved_regs.sp),
-		       "I" (BRK64_ESR_KPROBES)
-		     : "memory");
-
-	unreachable();
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long stack_addr = kcb->jprobe_saved_regs.sp;
-	long orig_sp = kernel_stack_pointer(regs);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	extern const char jprobe_return_break[];
-
-	if (instruction_pointer(regs) != (u64) jprobe_return_break)
-		return 0;
-
-	if (orig_sp != stack_addr) {
-		struct pt_regs *saved_regs =
-		    (struct pt_regs *)kcb->jprobe_saved_regs.sp;
-		pr_err("current sp %lx does not match saved sp %lx\n",
-		       orig_sp, stack_addr);
-		pr_err("Saved registers for jprobe %p\n", jp);
-		__show_regs(saved_regs);
-		pr_err("Current registers\n");
-		__show_regs(regs);
-		BUG();
-	}
-	unpause_graph_tracing();
-	*regs = kcb->jprobe_saved_regs;
-	preempt_enable_no_resched();
-	return 1;
-}
-
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	if ((addr >= (unsigned long)__kprobes_text_start &&
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index e10bc363f533..7f1628effe6d 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -177,16 +177,16 @@ static void print_pstate(struct pt_regs *regs)
 	if (compat_user_mode(regs)) {
 		printk("pstate: %08llx (%c%c%c%c %c %s %s %c%c%c)\n",
 			pstate,
-			pstate & COMPAT_PSR_N_BIT ? 'N' : 'n',
-			pstate & COMPAT_PSR_Z_BIT ? 'Z' : 'z',
-			pstate & COMPAT_PSR_C_BIT ? 'C' : 'c',
-			pstate & COMPAT_PSR_V_BIT ? 'V' : 'v',
-			pstate & COMPAT_PSR_Q_BIT ? 'Q' : 'q',
-			pstate & COMPAT_PSR_T_BIT ? "T32" : "A32",
-			pstate & COMPAT_PSR_E_BIT ? "BE" : "LE",
-			pstate & COMPAT_PSR_A_BIT ? 'A' : 'a',
-			pstate & COMPAT_PSR_I_BIT ? 'I' : 'i',
-			pstate & COMPAT_PSR_F_BIT ? 'F' : 'f');
+			pstate & PSR_AA32_N_BIT ? 'N' : 'n',
+			pstate & PSR_AA32_Z_BIT ? 'Z' : 'z',
+			pstate & PSR_AA32_C_BIT ? 'C' : 'c',
+			pstate & PSR_AA32_V_BIT ? 'V' : 'v',
+			pstate & PSR_AA32_Q_BIT ? 'Q' : 'q',
+			pstate & PSR_AA32_T_BIT ? "T32" : "A32",
+			pstate & PSR_AA32_E_BIT ? "BE" : "LE",
+			pstate & PSR_AA32_A_BIT ? 'A' : 'a',
+			pstate & PSR_AA32_I_BIT ? 'I' : 'i',
+			pstate & PSR_AA32_F_BIT ? 'F' : 'f');
 	} else {
 		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO)\n",
 			pstate,
@@ -493,3 +493,25 @@ void arch_setup_new_exec(void)
 {
 	current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
 }
+
+#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+void __used stackleak_check_alloca(unsigned long size)
+{
+	unsigned long stack_left;
+	unsigned long current_sp = current_stack_pointer;
+	struct stack_info info;
+
+	BUG_ON(!on_accessible_stack(current, current_sp, &info));
+
+	stack_left = current_sp - info.low;
+
+	/*
+	 * There's a good chance we're almost out of stack space if this
+	 * is true. Using panic() over BUG() is more likely to give
+	 * reliable debugging output.
+	 */
+	if (size >= stack_left)
+		panic("alloca() over the kernel stack boundary\n");
+}
+EXPORT_SYMBOL(stackleak_check_alloca);
+#endif
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 5c338ce5a7fa..6219486fa25f 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -132,7 +132,7 @@ static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
 {
 	return ((addr & ~(THREAD_SIZE - 1))  ==
 		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) ||
-		on_irq_stack(addr);
+		on_irq_stack(addr, NULL);
 }
 
 /**
@@ -277,19 +277,22 @@ static int ptrace_hbp_set_event(unsigned int note_type,
 
 	switch (note_type) {
 	case NT_ARM_HW_BREAK:
-		if (idx < ARM_MAX_BRP) {
-			tsk->thread.debug.hbp_break[idx] = bp;
-			err = 0;
-		}
+		if (idx >= ARM_MAX_BRP)
+			goto out;
+		idx = array_index_nospec(idx, ARM_MAX_BRP);
+		tsk->thread.debug.hbp_break[idx] = bp;
+		err = 0;
 		break;
 	case NT_ARM_HW_WATCH:
-		if (idx < ARM_MAX_WRP) {
-			tsk->thread.debug.hbp_watch[idx] = bp;
-			err = 0;
-		}
+		if (idx >= ARM_MAX_WRP)
+			goto out;
+		idx = array_index_nospec(idx, ARM_MAX_WRP);
+		tsk->thread.debug.hbp_watch[idx] = bp;
+		err = 0;
 		break;
 	}
 
+out:
 	return err;
 }
 
@@ -1076,6 +1079,7 @@ static int compat_gpr_get(struct task_struct *target,
 			break;
 		case 16:
 			reg = task_pt_regs(target)->pstate;
+			reg = pstate_to_compat_psr(reg);
 			break;
 		case 17:
 			reg = task_pt_regs(target)->orig_x0;
@@ -1143,6 +1147,7 @@ static int compat_gpr_set(struct task_struct *target,
 			newregs.pc = reg;
 			break;
 		case 16:
+			reg = compat_psr_to_pstate(reg);
 			newregs.pstate = reg;
 			break;
 		case 17:
@@ -1629,7 +1634,7 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 	regs->regs[regno] = saved_reg;
 }
 
-asmlinkage int syscall_trace_enter(struct pt_regs *regs)
+int syscall_trace_enter(struct pt_regs *regs)
 {
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
@@ -1647,7 +1652,7 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 	return regs->syscallno;
 }
 
-asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+void syscall_trace_exit(struct pt_regs *regs)
 {
 	audit_syscall_exit(regs);
 
@@ -1656,18 +1661,24 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs)
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
+
+	rseq_syscall(regs);
 }
 
 /*
- * Bits which are always architecturally RES0 per ARM DDI 0487A.h
+ * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487C.a
+ * We also take into account DIT (bit 24), which is not yet documented, and
+ * treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may be
+ * allocated an EL0 meaning in future.
  * Userspace cannot use these until they have an architectural meaning.
+ * Note that this follows the SPSR_ELx format, not the AArch32 PSR format.
  * We also reserve IL for the kernel; SS is handled dynamically.
  */
 #define SPSR_EL1_AARCH64_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(27, 22) | GENMASK_ULL(20, 10) | \
-	 GENMASK_ULL(5, 5))
+	(GENMASK_ULL(63,32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
+	 GENMASK_ULL(20, 10) | GENMASK_ULL(5, 5))
 #define SPSR_EL1_AARCH32_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(24, 22) | GENMASK_ULL(20,20))
+	(GENMASK_ULL(63,32) | GENMASK_ULL(23, 22) | GENMASK_ULL(20,20))
 
 static int valid_compat_regs(struct user_pt_regs *regs)
 {
@@ -1675,15 +1686,15 @@ static int valid_compat_regs(struct user_pt_regs *regs)
 
 	if (!system_supports_mixed_endian_el0()) {
 		if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
-			regs->pstate |= COMPAT_PSR_E_BIT;
+			regs->pstate |= PSR_AA32_E_BIT;
 		else
-			regs->pstate &= ~COMPAT_PSR_E_BIT;
+			regs->pstate &= ~PSR_AA32_E_BIT;
 	}
 
 	if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) &&
-	    (regs->pstate & COMPAT_PSR_A_BIT) == 0 &&
-	    (regs->pstate & COMPAT_PSR_I_BIT) == 0 &&
-	    (regs->pstate & COMPAT_PSR_F_BIT) == 0) {
+	    (regs->pstate & PSR_AA32_A_BIT) == 0 &&
+	    (regs->pstate & PSR_AA32_I_BIT) == 0 &&
+	    (regs->pstate & PSR_AA32_F_BIT) == 0) {
 		return 1;
 	}
 
@@ -1691,11 +1702,11 @@ static int valid_compat_regs(struct user_pt_regs *regs)
 	 * Force PSR to a valid 32-bit EL0t, preserving the same bits as
 	 * arch/arm.
 	 */
-	regs->pstate &= COMPAT_PSR_N_BIT | COMPAT_PSR_Z_BIT |
-			COMPAT_PSR_C_BIT | COMPAT_PSR_V_BIT |
-			COMPAT_PSR_Q_BIT | COMPAT_PSR_IT_MASK |
-			COMPAT_PSR_GE_MASK | COMPAT_PSR_E_BIT |
-			COMPAT_PSR_T_BIT;
+	regs->pstate &= PSR_AA32_N_BIT | PSR_AA32_Z_BIT |
+			PSR_AA32_C_BIT | PSR_AA32_V_BIT |
+			PSR_AA32_Q_BIT | PSR_AA32_IT_MASK |
+			PSR_AA32_GE_MASK | PSR_AA32_E_BIT |
+			PSR_AA32_T_BIT;
 	regs->pstate |= PSR_MODE32_BIT;
 
 	return 0;
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 6b8d90d5ceae..5ba4465e44f0 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -13,6 +13,7 @@
 #include <asm/mmu.h>
 #include <asm/ptrace.h>
 #include <asm/sections.h>
+#include <asm/stacktrace.h>
 #include <asm/sysreg.h>
 #include <asm/vmap_stack.h>
 
@@ -88,23 +89,52 @@ static int init_sdei_stacks(void)
 	return err;
 }
 
-bool _on_sdei_stack(unsigned long sp)
+static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info)
 {
-	unsigned long low, high;
+	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
+	unsigned long high = low + SDEI_STACK_SIZE;
 
-	if (!IS_ENABLED(CONFIG_VMAP_STACK))
+	if (sp < low || sp >= high)
 		return false;
 
-	low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
-	high = low + SDEI_STACK_SIZE;
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_SDEI_NORMAL;
+	}
 
-	if (low <= sp && sp < high)
+	return true;
+}
+
+static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info)
+{
+	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
+	unsigned long high = low + SDEI_STACK_SIZE;
+
+	if (sp < low || sp >= high)
+		return false;
+
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_SDEI_CRITICAL;
+	}
+
+	return true;
+}
+
+bool _on_sdei_stack(unsigned long sp, struct stack_info *info)
+{
+	if (!IS_ENABLED(CONFIG_VMAP_STACK))
+		return false;
+
+	if (on_sdei_critical_stack(sp, info))
 		return true;
 
-	low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
-	high = low + SDEI_STACK_SIZE;
+	if (on_sdei_normal_stack(sp, info))
+		return true;
 
-	return (low <= sp && sp < high);
+	return false;
 }
 
 unsigned long sdei_arch_get_entry_point(int conduit)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 30ad2f085d1f..5b4fac434c84 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -241,6 +241,44 @@ static void __init request_standard_resources(void)
 	}
 }
 
+static int __init reserve_memblock_reserved_regions(void)
+{
+	phys_addr_t start, end, roundup_end = 0;
+	struct resource *mem, *res;
+	u64 i;
+
+	for_each_reserved_mem_region(i, &start, &end) {
+		if (end <= roundup_end)
+			continue; /* done already */
+
+		start = __pfn_to_phys(PFN_DOWN(start));
+		end = __pfn_to_phys(PFN_UP(end)) - 1;
+		roundup_end = end;
+
+		res = kzalloc(sizeof(*res), GFP_ATOMIC);
+		if (WARN_ON(!res))
+			return -ENOMEM;
+		res->start = start;
+		res->end = end;
+		res->name  = "reserved";
+		res->flags = IORESOURCE_MEM;
+
+		mem = request_resource_conflict(&iomem_resource, res);
+		/*
+		 * We expected memblock_reserve() regions to conflict with
+		 * memory created by request_standard_resources().
+		 */
+		if (WARN_ON_ONCE(!mem))
+			continue;
+		kfree(res);
+
+		reserve_region_with_split(mem, start, end, "reserved");
+	}
+
+	return 0;
+}
+arch_initcall(reserve_memblock_reserved_regions);
+
 u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 void __init setup_arch(char **cmdline_p)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 511af13e8d8f..5dcc942906db 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -539,8 +539,9 @@ static int restore_sigframe(struct pt_regs *regs,
 	return err;
 }
 
-asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
+SYSCALL_DEFINE0(rt_sigreturn)
 {
+	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -802,6 +803,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	int usig = ksig->sig;
 	int ret;
 
+	rseq_signal_deliver(ksig, regs);
+
 	/*
 	 * Set up the stack frame
 	 */
@@ -910,7 +913,7 @@ static void do_signal(struct pt_regs *regs)
 }
 
 asmlinkage void do_notify_resume(struct pt_regs *regs,
-				 unsigned int thread_flags)
+				 unsigned long thread_flags)
 {
 	/*
 	 * The assembly code enters us with IRQs off, but it hasn't
@@ -940,6 +943,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 			if (thread_flags & _TIF_NOTIFY_RESUME) {
 				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
+				rseq_handle_notify_resume(NULL, regs);
 			}
 
 			if (thread_flags & _TIF_FOREIGN_FPSTATE)
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 77b91f478995..24b09003f821 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -243,6 +243,7 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	int err;
 	sigset_t set;
 	struct compat_aux_sigframe __user *aux;
+	unsigned long psr;
 
 	err = get_sigset_t(&set, &sf->uc.uc_sigmask);
 	if (err == 0) {
@@ -266,7 +267,9 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	__get_user_error(regs->compat_sp, &sf->uc.uc_mcontext.arm_sp, err);
 	__get_user_error(regs->compat_lr, &sf->uc.uc_mcontext.arm_lr, err);
 	__get_user_error(regs->pc, &sf->uc.uc_mcontext.arm_pc, err);
-	__get_user_error(regs->pstate, &sf->uc.uc_mcontext.arm_cpsr, err);
+	__get_user_error(psr, &sf->uc.uc_mcontext.arm_cpsr, err);
+
+	regs->pstate = compat_psr_to_pstate(psr);
 
 	/*
 	 * Avoid compat_sys_sigreturn() restarting.
@@ -282,8 +285,9 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	return err;
 }
 
-asmlinkage int compat_sys_sigreturn(struct pt_regs *regs)
+COMPAT_SYSCALL_DEFINE0(sigreturn)
 {
+	struct pt_regs *regs = current_pt_regs();
 	struct compat_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -312,8 +316,9 @@ badframe:
 	return 0;
 }
 
-asmlinkage int compat_sys_rt_sigreturn(struct pt_regs *regs)
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 {
+	struct pt_regs *regs = current_pt_regs();
 	struct compat_rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -372,22 +377,22 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 {
 	compat_ulong_t handler = ptr_to_compat(ka->sa.sa_handler);
 	compat_ulong_t retcode;
-	compat_ulong_t spsr = regs->pstate & ~(PSR_f | COMPAT_PSR_E_BIT);
+	compat_ulong_t spsr = regs->pstate & ~(PSR_f | PSR_AA32_E_BIT);
 	int thumb;
 
 	/* Check if the handler is written for ARM or Thumb */
 	thumb = handler & 1;
 
 	if (thumb)
-		spsr |= COMPAT_PSR_T_BIT;
+		spsr |= PSR_AA32_T_BIT;
 	else
-		spsr &= ~COMPAT_PSR_T_BIT;
+		spsr &= ~PSR_AA32_T_BIT;
 
 	/* The IT state must be cleared for both ARM and Thumb-2 */
-	spsr &= ~COMPAT_PSR_IT_MASK;
+	spsr &= ~PSR_AA32_IT_MASK;
 
 	/* Restore the original endianness */
-	spsr |= COMPAT_PSR_ENDSTATE;
+	spsr |= PSR_AA32_ENDSTATE;
 
 	if (ka->sa.sa_flags & SA_RESTORER) {
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
@@ -414,6 +419,7 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf,
 				 struct pt_regs *regs, sigset_t *set)
 {
 	struct compat_aux_sigframe __user *aux;
+	unsigned long psr = pstate_to_compat_psr(regs->pstate);
 	int err = 0;
 
 	__put_user_error(regs->regs[0], &sf->uc.uc_mcontext.arm_r0, err);
@@ -432,7 +438,7 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf,
 	__put_user_error(regs->compat_sp, &sf->uc.uc_mcontext.arm_sp, err);
 	__put_user_error(regs->compat_lr, &sf->uc.uc_mcontext.arm_lr, err);
 	__put_user_error(regs->pc, &sf->uc.uc_mcontext.arm_pc, err);
-	__put_user_error(regs->pstate, &sf->uc.uc_mcontext.arm_cpsr, err);
+	__put_user_error(psr, &sf->uc.uc_mcontext.arm_cpsr, err);
 
 	__put_user_error((compat_ulong_t)0, &sf->uc.uc_mcontext.trap_no, err);
 	/* set the compat FSR WnR */
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2faa9863d2e5..25fcd22a4bb2 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -225,6 +225,7 @@ asmlinkage notrace void secondary_start_kernel(void)
 	notify_cpu_starting(cpu);
 
 	store_cpu_topology(cpu);
+	numa_add_cpu(cpu);
 
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
@@ -278,6 +279,9 @@ int __cpu_disable(void)
 	if (ret)
 		return ret;
 
+	remove_cpu_topology(cpu);
+	numa_remove_cpu(cpu);
+
 	/*
 	 * Take this CPU offline.  Once we clear this, we can't return,
 	 * and we must not schedule until we're ready to give up the cpu.
@@ -518,7 +522,6 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 		}
 		bootcpu_valid = true;
 		cpu_madt_gicc[0] = *processor;
-		early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid));
 		return;
 	}
 
@@ -541,8 +544,6 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 	 */
 	acpi_set_mailbox_entry(cpu_count, processor);
 
-	early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid));
-
 	cpu_count++;
 }
 
@@ -562,8 +563,34 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
 
 	return 0;
 }
+
+static void __init acpi_parse_and_init_cpus(void)
+{
+	int i;
+
+	/*
+	 * do a walk of MADT to determine how many CPUs
+	 * we have including disabled CPUs, and get information
+	 * we need for SMP init.
+	 */
+	acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
+				      acpi_parse_gic_cpu_interface, 0);
+
+	/*
+	 * In ACPI, SMP and CPU NUMA information is provided in separate
+	 * static tables, namely the MADT and the SRAT.
+	 *
+	 * Thus, it is simpler to first create the cpu logical map through
+	 * an MADT walk and then map the logical cpus to their node ids
+	 * as separate steps.
+	 */
+	acpi_map_cpus_to_nodes();
+
+	for (i = 0; i < nr_cpu_ids; i++)
+		early_map_cpu_to_node(i, acpi_numa_get_nid(i));
+}
 #else
-#define acpi_table_parse_madt(...)	do { } while (0)
+#define acpi_parse_and_init_cpus(...)	do { } while (0)
 #endif
 
 /*
@@ -636,13 +663,7 @@ void __init smp_init_cpus(void)
 	if (acpi_disabled)
 		of_parse_and_init_cpus();
 	else
-		/*
-		 * do a walk of MADT to determine how many CPUs
-		 * we have including disabled CPUs, and get information
-		 * we need for SMP init
-		 */
-		acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
-				      acpi_parse_gic_cpu_interface, 0);
+		acpi_parse_and_init_cpus();
 
 	if (cpu_count > nr_cpu_ids)
 		pr_warn("Number of cores (%d) exceeds configured maximum of %u - clipping\n",
@@ -679,6 +700,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	this_cpu = smp_processor_id();
 	store_cpu_topology(this_cpu);
 	numa_store_cpu_info(this_cpu);
+	numa_add_cpu(this_cpu);
 
 	/*
 	 * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index d5718a060672..4989f7ea1e59 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -50,7 +50,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	if (!tsk)
 		tsk = current;
 
-	if (!on_accessible_stack(tsk, fp))
+	if (!on_accessible_stack(tsk, fp, NULL))
 		return -EINVAL;
 
 	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index 72981bae10eb..b44065fb1616 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -25,11 +25,13 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
+
 #include <asm/cpufeature.h>
+#include <asm/syscall.h>
 
-asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
-			 unsigned long prot, unsigned long flags,
-			 unsigned long fd, off_t off)
+SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, off_t, off)
 {
 	if (offset_in_page(off) != 0)
 		return -EINVAL;
@@ -42,24 +44,25 @@ SYSCALL_DEFINE1(arm64_personality, unsigned int, personality)
 	if (personality(personality) == PER_LINUX32 &&
 		!system_supports_32bit_el0())
 		return -EINVAL;
-	return sys_personality(personality);
+	return ksys_personality(personality);
 }
 
 /*
  * Wrappers to pass the pt_regs argument.
  */
-asmlinkage long sys_rt_sigreturn_wrapper(void);
-#define sys_rt_sigreturn	sys_rt_sigreturn_wrapper
 #define sys_personality		sys_arm64_personality
 
+asmlinkage long sys_ni_syscall(const struct pt_regs *);
+#define __arm64_sys_ni_syscall	sys_ni_syscall
+
 #undef __SYSCALL
-#define __SYSCALL(nr, sym)	[nr] = sym,
+#define __SYSCALL(nr, sym)	asmlinkage long __arm64_##sym(const struct pt_regs *);
+#include <asm/unistd.h>
 
-/*
- * The sys_call_table array must be 4K aligned to be accessible from
- * kernel/entry.S.
- */
-void * const sys_call_table[__NR_syscalls] __aligned(4096) = {
-	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#undef __SYSCALL
+#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)__arm64_##sym,
+
+const syscall_fn_t sys_call_table[__NR_syscalls] = {
+	[0 ... __NR_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
 #include <asm/unistd.h>
 };
diff --git a/arch/arm64/kernel/sys32.c b/arch/arm64/kernel/sys32.c
index a40b1343b819..0f8bcb7de700 100644
--- a/arch/arm64/kernel/sys32.c
+++ b/arch/arm64/kernel/sys32.c
@@ -22,31 +22,128 @@
  */
 #define __COMPAT_SYSCALL_NR
 
+#include <linux/compat.h>
 #include <linux/compiler.h>
 #include <linux/syscalls.h>
 
-asmlinkage long compat_sys_sigreturn_wrapper(void);
-asmlinkage long compat_sys_rt_sigreturn_wrapper(void);
-asmlinkage long compat_sys_statfs64_wrapper(void);
-asmlinkage long compat_sys_fstatfs64_wrapper(void);
-asmlinkage long compat_sys_pread64_wrapper(void);
-asmlinkage long compat_sys_pwrite64_wrapper(void);
-asmlinkage long compat_sys_truncate64_wrapper(void);
-asmlinkage long compat_sys_ftruncate64_wrapper(void);
-asmlinkage long compat_sys_readahead_wrapper(void);
-asmlinkage long compat_sys_fadvise64_64_wrapper(void);
-asmlinkage long compat_sys_sync_file_range2_wrapper(void);
-asmlinkage long compat_sys_fallocate_wrapper(void);
-asmlinkage long compat_sys_mmap2_wrapper(void);
+#include <asm/syscall.h>
 
-#undef __SYSCALL
-#define __SYSCALL(nr, sym)	[nr] = sym,
+asmlinkage long compat_sys_sigreturn(void);
+asmlinkage long compat_sys_rt_sigreturn(void);
+
+COMPAT_SYSCALL_DEFINE3(aarch32_statfs64, const char __user *, pathname,
+		       compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	/*
+	 * 32-bit ARM applies an OABI compatibility fixup to statfs64 and
+	 * fstatfs64 regardless of whether OABI is in use, and therefore
+	 * arbitrary binaries may rely upon it, so we must do the same.
+	 * For more details, see commit:
+	 *
+	 * 713c481519f19df9 ("[ARM] 3108/2: old ABI compat: statfs64 and
+	 * fstatfs64")
+	 */
+	if (sz == 88)
+		sz = 84;
+
+	return kcompat_sys_statfs64(pathname, sz, buf);
+}
+
+COMPAT_SYSCALL_DEFINE3(aarch32_fstatfs64, unsigned int, fd, compat_size_t, sz,
+		       struct compat_statfs64 __user *, buf)
+{
+	/* see aarch32_statfs64 */
+	if (sz == 88)
+		sz = 84;
+
+	return kcompat_sys_fstatfs64(fd, sz, buf);
+}
 
 /*
- * The sys_call_table array must be 4K aligned to be accessible from
- * kernel/entry.S.
+ * Note: off_4k is always in units of 4K. If we can't do the
+ * requested offset because it is not page-aligned, we return -EINVAL.
  */
-void * const compat_sys_call_table[__NR_compat_syscalls] __aligned(4096) = {
-	[0 ... __NR_compat_syscalls - 1] = sys_ni_syscall,
+COMPAT_SYSCALL_DEFINE6(aarch32_mmap2, unsigned long, addr, unsigned long, len,
+		       unsigned long, prot, unsigned long, flags,
+		       unsigned long, fd, unsigned long, off_4k)
+{
+	if (off_4k & (~PAGE_MASK >> 12))
+		return -EINVAL;
+
+	off_4k >>= (PAGE_SHIFT - 12);
+
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, off_4k);
+}
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define arg_u32p(name)	u32, name##_hi, u32, name##_lo
+#else
+#define arg_u32p(name)	u32, name##_lo, u32, name##_hi
+#endif
+
+#define arg_u64(name)	(((u64)name##_hi << 32) | name##_lo)
+
+COMPAT_SYSCALL_DEFINE6(aarch32_pread64, unsigned int, fd, char __user *, buf,
+		       size_t, count, u32, __pad, arg_u32p(pos))
+{
+	return ksys_pread64(fd, buf, count, arg_u64(pos));
+}
+
+COMPAT_SYSCALL_DEFINE6(aarch32_pwrite64, unsigned int, fd,
+		       const char __user *, buf, size_t, count, u32, __pad,
+		       arg_u32p(pos))
+{
+	return ksys_pwrite64(fd, buf, count, arg_u64(pos));
+}
+
+COMPAT_SYSCALL_DEFINE4(aarch32_truncate64, const char __user *, pathname,
+		       u32, __pad, arg_u32p(length))
+{
+	return ksys_truncate(pathname, arg_u64(length));
+}
+
+COMPAT_SYSCALL_DEFINE4(aarch32_ftruncate64, unsigned int, fd, u32, __pad,
+		       arg_u32p(length))
+{
+	return ksys_ftruncate(fd, arg_u64(length));
+}
+
+COMPAT_SYSCALL_DEFINE5(aarch32_readahead, int, fd, u32, __pad,
+		       arg_u32p(offset), size_t, count)
+{
+	return ksys_readahead(fd, arg_u64(offset), count);
+}
+
+COMPAT_SYSCALL_DEFINE6(aarch32_fadvise64_64, int, fd, int, advice,
+		       arg_u32p(offset), arg_u32p(len))
+{
+	return ksys_fadvise64_64(fd, arg_u64(offset), arg_u64(len), advice);
+}
+
+COMPAT_SYSCALL_DEFINE6(aarch32_sync_file_range2, int, fd, unsigned int, flags,
+		       arg_u32p(offset), arg_u32p(nbytes))
+{
+	return ksys_sync_file_range(fd, arg_u64(offset), arg_u64(nbytes),
+				    flags);
+}
+
+COMPAT_SYSCALL_DEFINE6(aarch32_fallocate, int, fd, int, mode,
+		       arg_u32p(offset), arg_u32p(len))
+{
+	return ksys_fallocate(fd, mode, arg_u64(offset), arg_u64(len));
+}
+
+asmlinkage long sys_ni_syscall(const struct pt_regs *);
+#define __arm64_sys_ni_syscall	sys_ni_syscall
+
+#undef __SYSCALL
+#define __SYSCALL(nr, sym)	asmlinkage long __arm64_##sym(const struct pt_regs *);
+#include <asm/unistd32.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)__arm64_##sym,
+
+const syscall_fn_t compat_sys_call_table[__NR_compat_syscalls] = {
+	[0 ... __NR_compat_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
 #include <asm/unistd32.h>
 };
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
new file mode 100644
index 000000000000..032d22312881
--- /dev/null
+++ b/arch/arm64/kernel/syscall.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/compiler.h>
+#include <linux/context_tracking.h>
+#include <linux/errno.h>
+#include <linux/nospec.h>
+#include <linux/ptrace.h>
+#include <linux/syscalls.h>
+
+#include <asm/daifflags.h>
+#include <asm/fpsimd.h>
+#include <asm/syscall.h>
+#include <asm/thread_info.h>
+#include <asm/unistd.h>
+
+long compat_arm_syscall(struct pt_regs *regs);
+
+long sys_ni_syscall(void);
+
+asmlinkage long do_ni_syscall(struct pt_regs *regs)
+{
+#ifdef CONFIG_COMPAT
+	long ret;
+	if (is_compat_task()) {
+		ret = compat_arm_syscall(regs);
+		if (ret != -ENOSYS)
+			return ret;
+	}
+#endif
+
+	return sys_ni_syscall();
+}
+
+static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn)
+{
+	return syscall_fn(regs);
+}
+
+static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
+			   unsigned int sc_nr,
+			   const syscall_fn_t syscall_table[])
+{
+	long ret;
+
+	if (scno < sc_nr) {
+		syscall_fn_t syscall_fn;
+		syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)];
+		ret = __invoke_syscall(regs, syscall_fn);
+	} else {
+		ret = do_ni_syscall(regs);
+	}
+
+	regs->regs[0] = ret;
+}
+
+static inline bool has_syscall_work(unsigned long flags)
+{
+	return unlikely(flags & _TIF_SYSCALL_WORK);
+}
+
+int syscall_trace_enter(struct pt_regs *regs);
+void syscall_trace_exit(struct pt_regs *regs);
+
+static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
+			   const syscall_fn_t syscall_table[])
+{
+	unsigned long flags = current_thread_info()->flags;
+
+	regs->orig_x0 = regs->regs[0];
+	regs->syscallno = scno;
+
+	local_daif_restore(DAIF_PROCCTX);
+	user_exit();
+
+	if (has_syscall_work(flags)) {
+		/* set default errno for user-issued syscall(-1) */
+		if (scno == NO_SYSCALL)
+			regs->regs[0] = -ENOSYS;
+		scno = syscall_trace_enter(regs);
+		if (scno == NO_SYSCALL)
+			goto trace_exit;
+	}
+
+	invoke_syscall(regs, scno, sc_nr, syscall_table);
+
+	/*
+	 * The tracing status may have changed under our feet, so we have to
+	 * check again. However, if we were tracing entry, then we always trace
+	 * exit regardless, as the old entry assembly did.
+	 */
+	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
+		local_daif_mask();
+		flags = current_thread_info()->flags;
+		if (!has_syscall_work(flags)) {
+			/*
+			 * We're off to userspace, where interrupts are
+			 * always enabled after we restore the flags from
+			 * the SPSR.
+			 */
+			trace_hardirqs_on();
+			return;
+		}
+		local_daif_restore(DAIF_PROCCTX);
+	}
+
+trace_exit:
+	syscall_trace_exit(regs);
+}
+
+static inline void sve_user_discard(void)
+{
+	if (!system_supports_sve())
+		return;
+
+	clear_thread_flag(TIF_SVE);
+
+	/*
+	 * task_fpsimd_load() won't be called to update CPACR_EL1 in
+	 * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
+	 * happens if a context switch or kernel_neon_begin() or context
+	 * modification (sigreturn, ptrace) intervenes.
+	 * So, ensure that CPACR_EL1 is already correct for the fast-path case.
+	 */
+	sve_user_disable();
+}
+
+asmlinkage void el0_svc_handler(struct pt_regs *regs)
+{
+	sve_user_discard();
+	el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
+}
+
+#ifdef CONFIG_COMPAT
+asmlinkage void el0_svc_compat_handler(struct pt_regs *regs)
+{
+	el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls,
+		       compat_sys_call_table);
+}
+#endif
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index f845a8617812..0825c4a856e3 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -215,11 +215,16 @@ EXPORT_SYMBOL_GPL(cpu_topology);
 
 const struct cpumask *cpu_coregroup_mask(int cpu)
 {
-	const cpumask_t *core_mask = &cpu_topology[cpu].core_sibling;
+	const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));
 
+	/* Find the smaller of NUMA, core or LLC siblings */
+	if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
+		/* not numa in package, lets use the package siblings */
+		core_mask = &cpu_topology[cpu].core_sibling;
+	}
 	if (cpu_topology[cpu].llc_id != -1) {
-		if (cpumask_subset(&cpu_topology[cpu].llc_siblings, core_mask))
-			core_mask = &cpu_topology[cpu].llc_siblings;
+		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
+			core_mask = &cpu_topology[cpu].llc_sibling;
 	}
 
 	return core_mask;
@@ -231,27 +236,25 @@ static void update_siblings_masks(unsigned int cpuid)
 	int cpu;
 
 	/* update core and thread sibling masks */
-	for_each_possible_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		cpu_topo = &cpu_topology[cpu];
 
 		if (cpuid_topo->llc_id == cpu_topo->llc_id) {
-			cpumask_set_cpu(cpu, &cpuid_topo->llc_siblings);
-			cpumask_set_cpu(cpuid, &cpu_topo->llc_siblings);
+			cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
+			cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
 		}
 
 		if (cpuid_topo->package_id != cpu_topo->package_id)
 			continue;
 
 		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
-		if (cpu != cpuid)
-			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
 
 		if (cpuid_topo->core_id != cpu_topo->core_id)
 			continue;
 
 		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
-		if (cpu != cpuid)
-			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+		cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
 	}
 }
 
@@ -293,6 +296,19 @@ topology_populated:
 	update_siblings_masks(cpuid);
 }
 
+static void clear_cpu_topology(int cpu)
+{
+	struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+	cpumask_clear(&cpu_topo->llc_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);
+
+	cpumask_clear(&cpu_topo->core_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
+	cpumask_clear(&cpu_topo->thread_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
+}
+
 static void __init reset_cpu_topology(void)
 {
 	unsigned int cpu;
@@ -303,18 +319,26 @@ static void __init reset_cpu_topology(void)
 		cpu_topo->thread_id = -1;
 		cpu_topo->core_id = 0;
 		cpu_topo->package_id = -1;
-
 		cpu_topo->llc_id = -1;
-		cpumask_clear(&cpu_topo->llc_siblings);
-		cpumask_set_cpu(cpu, &cpu_topo->llc_siblings);
 
-		cpumask_clear(&cpu_topo->core_sibling);
-		cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
-		cpumask_clear(&cpu_topo->thread_sibling);
-		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
+		clear_cpu_topology(cpu);
 	}
 }
 
+void remove_cpu_topology(unsigned int cpu)
+{
+	int sibling;
+
+	for_each_cpu(sibling, topology_core_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
+	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
+	for_each_cpu(sibling, topology_llc_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));
+
+	clear_cpu_topology(cpu);
+}
+
 #ifdef CONFIG_ACPI
 /*
  * Propagate the topology information of the processor_topology_node tree to the
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index d399d459397b..039e9ff379cc 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -411,7 +411,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 
 void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
 {
-	config_sctlr_el1(SCTLR_EL1_UCI, 0);
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0);
 }
 
 #define __user_cache_maint(insn, address, res)			\
@@ -547,22 +547,6 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
 	do_undefinstr(regs);
 }
 
-long compat_arm_syscall(struct pt_regs *regs);
-
-asmlinkage long do_ni_syscall(struct pt_regs *regs)
-{
-#ifdef CONFIG_COMPAT
-	long ret;
-	if (is_compat_task()) {
-		ret = compat_arm_syscall(regs);
-		if (ret != -ENOSYS)
-			return ret;
-	}
-#endif
-
-	return sys_ni_syscall();
-}
-
 static const char *esr_class_str[] = {
 	[0 ... ESR_ELx_EC_MAX]		= "UNRECOGNIZED EC",
 	[ESR_ELx_EC_UNKNOWN]		= "Unknown/Uncategorized",
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 56a0260ceb11..cdd4d9d6d575 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -107,14 +107,14 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
-		u32 mode = (*(u32 *)valp) & COMPAT_PSR_MODE_MASK;
+		u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK;
 		switch (mode) {
-		case COMPAT_PSR_MODE_USR:
-		case COMPAT_PSR_MODE_FIQ:
-		case COMPAT_PSR_MODE_IRQ:
-		case COMPAT_PSR_MODE_SVC:
-		case COMPAT_PSR_MODE_ABT:
-		case COMPAT_PSR_MODE_UND:
+		case PSR_AA32_MODE_USR:
+		case PSR_AA32_MODE_FIQ:
+		case PSR_AA32_MODE_IRQ:
+		case PSR_AA32_MODE_SVC:
+		case PSR_AA32_MODE_ABT:
+		case PSR_AA32_MODE_UND:
 		case PSR_MODE_EL0t:
 		case PSR_MODE_EL1t:
 		case PSR_MODE_EL1h:
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 4313f7475333..2fabc2dc1966 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -3,7 +3,8 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
+ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
+		$(DISABLE_STACKLEAK_PLUGIN)
 
 KVM=../../../../virt/kvm
 
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 39be799d0417..215c7c0eb3b0 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -27,7 +27,7 @@
 static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu))
-		return !!(read_sysreg_el2(spsr) & COMPAT_PSR_E_BIT);
+		return !!(read_sysreg_el2(spsr) & PSR_AA32_E_BIT);
 
 	return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
 }
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
index eefe403a2e63..7a5173ea2276 100644
--- a/arch/arm64/kvm/regmap.c
+++ b/arch/arm64/kvm/regmap.c
@@ -112,22 +112,22 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = {
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
 {
 	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs.regs;
-	unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
+	unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
 
 	switch (mode) {
-	case COMPAT_PSR_MODE_USR ... COMPAT_PSR_MODE_SVC:
+	case PSR_AA32_MODE_USR ... PSR_AA32_MODE_SVC:
 		mode &= ~PSR_MODE32_BIT; /* 0 ... 3 */
 		break;
 
-	case COMPAT_PSR_MODE_ABT:
+	case PSR_AA32_MODE_ABT:
 		mode = 4;
 		break;
 
-	case COMPAT_PSR_MODE_UND:
+	case PSR_AA32_MODE_UND:
 		mode = 5;
 		break;
 
-	case COMPAT_PSR_MODE_SYS:
+	case PSR_AA32_MODE_SYS:
 		mode = 0;	/* SYS maps to USR */
 		break;
 
@@ -143,13 +143,13 @@ unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
  */
 static int vcpu_spsr32_mode(const struct kvm_vcpu *vcpu)
 {
-	unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
+	unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
 	switch (mode) {
-	case COMPAT_PSR_MODE_SVC: return KVM_SPSR_SVC;
-	case COMPAT_PSR_MODE_ABT: return KVM_SPSR_ABT;
-	case COMPAT_PSR_MODE_UND: return KVM_SPSR_UND;
-	case COMPAT_PSR_MODE_IRQ: return KVM_SPSR_IRQ;
-	case COMPAT_PSR_MODE_FIQ: return KVM_SPSR_FIQ;
+	case PSR_AA32_MODE_SVC: return KVM_SPSR_SVC;
+	case PSR_AA32_MODE_ABT: return KVM_SPSR_ABT;
+	case PSR_AA32_MODE_UND: return KVM_SPSR_UND;
+	case PSR_AA32_MODE_IRQ: return KVM_SPSR_IRQ;
+	case PSR_AA32_MODE_FIQ: return KVM_SPSR_FIQ;
 	default: BUG();
 	}
 }
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index a74311beda35..4e4aedaf7ab7 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -42,8 +42,8 @@ static const struct kvm_regs default_regs_reset = {
 };
 
 static const struct kvm_regs default_regs_reset32 = {
-	.regs.pstate = (COMPAT_PSR_MODE_SVC | COMPAT_PSR_A_BIT |
-			COMPAT_PSR_I_BIT | COMPAT_PSR_F_BIT),
+	.regs.pstate = (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT |
+			PSR_AA32_I_BIT | PSR_AA32_F_BIT),
 };
 
 static bool cpu_has_32bit_el1(void)
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 137710f4dac3..68755fd70dcf 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-lib-y		:= bitops.o clear_user.o delay.o copy_from_user.o	\
+lib-y		:= clear_user.o delay.o copy_from_user.o		\
 		   copy_to_user.o copy_in_user.o copy_page.o		\
 		   clear_page.o memchr.o memcpy.o memmove.o memset.o	\
 		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
deleted file mode 100644
index 43ac736baa5b..000000000000
--- a/arch/arm64/lib/bitops.S
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * Based on arch/arm/lib/bitops.h
- *
- * Copyright (C) 2013 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/lse.h>
-
-/*
- * x0: bits 5:0  bit offset
- *     bits 31:6 word offset
- * x1: address
- */
-	.macro	bitop, name, llsc, lse
-ENTRY(	\name	)
-	and	w3, w0, #63		// Get bit offset
-	eor	w0, w0, w3		// Clear low bits
-	mov	x2, #1
-	add	x1, x1, x0, lsr #3	// Get word offset
-alt_lse "	prfm	pstl1strm, [x1]",	"nop"
-	lsl	x3, x2, x3		// Create mask
-
-alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x3, [x1]"
-alt_lse	"	\llsc	x2, x2, x3",		"nop"
-alt_lse	"	stxr	w0, x2, [x1]",		"nop"
-alt_lse	"	cbnz	w0, 1b",		"nop"
-
-	ret
-ENDPROC(\name	)
-	.endm
-
-	.macro	testop, name, llsc, lse
-ENTRY(	\name	)
-	and	w3, w0, #63		// Get bit offset
-	eor	w0, w0, w3		// Clear low bits
-	mov	x2, #1
-	add	x1, x1, x0, lsr #3	// Get word offset
-alt_lse "	prfm	pstl1strm, [x1]",	"nop"
-	lsl	x4, x2, x3		// Create mask
-
-alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x4, x2, [x1]"
-	lsr	x0, x2, x3
-alt_lse	"	\llsc	x2, x2, x4",		"nop"
-alt_lse	"	stlxr	w5, x2, [x1]",		"nop"
-alt_lse	"	cbnz	w5, 1b",		"nop"
-alt_lse	"	dmb	ish",			"nop"
-
-	and	x0, x0, #1
-	ret
-ENDPROC(\name	)
-	.endm
-
-/*
- * Atomic bit operations.
- */
-	bitop	change_bit, eor, steor
-	bitop	clear_bit, bic, stclr
-	bitop	set_bit, orr, stset
-
-	testop	test_and_change_bit, eor, ldeoral
-	testop	test_and_clear_bit, bic, ldclral
-	testop	test_and_set_bit, orr, ldsetal
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 30334d81b021..0c22ede52f90 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -35,7 +35,7 @@
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-ENTRY(flush_icache_range)
+ENTRY(__flush_icache_range)
 	/* FALLTHROUGH */
 
 /*
@@ -77,7 +77,7 @@ alternative_else_nop_endif
 9:
 	mov	x0, #-EFAULT
 	b	1b
-ENDPROC(flush_icache_range)
+ENDPROC(__flush_icache_range)
 ENDPROC(__flush_cache_user_range)
 
 /*
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index b8eecc7b9531..9943690a3924 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -727,12 +727,7 @@ static const struct fault_info fault_info[] = {
 
 int handle_guest_sea(phys_addr_t addr, unsigned int esr)
 {
-	int ret = -ENOENT;
-
-	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA))
-		ret = ghes_notify_sea();
-
-	return ret;
+	return ghes_notify_sea();
 }
 
 asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
@@ -879,7 +874,7 @@ void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
 	 */
 	WARN_ON_ONCE(in_interrupt());
 
-	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0);
 	asm(SET_PSTATE_PAN(1));
 }
 #endif /* CONFIG_ARM64_PAN */
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 1059884f9a6f..30695a868107 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -66,6 +66,7 @@ void __sync_icache_dcache(pte_t pte)
 		sync_icache_aliases(page_address(page),
 				    PAGE_SIZE << compound_order(page));
 }
+EXPORT_SYMBOL_GPL(__sync_icache_dcache);
 
 /*
  * This function is called when a page has been modified by the kernel. Mark
@@ -82,7 +83,7 @@ EXPORT_SYMBOL(flush_dcache_page);
 /*
  * Additional functions defined in assembly.
  */
-EXPORT_SYMBOL(flush_icache_range);
+EXPORT_SYMBOL(__flush_icache_range);
 
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size)
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index ecc6818191df..192b3ba07075 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -108,7 +108,6 @@ static pte_t get_clear_flush(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	struct vm_area_struct vma = { .vm_mm = mm };
 	pte_t orig_pte = huge_ptep_get(ptep);
 	bool valid = pte_valid(orig_pte);
 	unsigned long i, saddr = addr;
@@ -125,8 +124,10 @@ static pte_t get_clear_flush(struct mm_struct *mm,
 			orig_pte = pte_mkdirty(orig_pte);
 	}
 
-	if (valid)
+	if (valid) {
+		struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
 		flush_tlb_range(&vma, saddr, addr);
+	}
 	return orig_pte;
 }
 
@@ -145,7 +146,7 @@ static void clear_flush(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	struct vm_area_struct vma = { .vm_mm = mm };
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
 	unsigned long i, saddr = addr;
 
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 325cfb3b858a..9abf8a1e7b25 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -611,11 +611,13 @@ void __init mem_init(void)
 	BUILD_BUG_ON(TASK_SIZE_32			> TASK_SIZE_64);
 #endif
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
 	/*
 	 * Make sure we chose the upper bound of sizeof(struct page)
-	 * correctly.
+	 * correctly when sizing the VMEMMAP array.
 	 */
 	BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT));
+#endif
 
 	if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
 		extern int sysctl_overcommit_memory;
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 493ff75670ff..65f86271f02b 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -45,6 +45,7 @@
 #include <asm/memblock.h>
 #include <asm/mmu_context.h>
 #include <asm/ptdump.h>
+#include <asm/tlbflush.h>
 
 #define NO_BLOCK_MAPPINGS	BIT(0)
 #define NO_CONT_MAPPINGS	BIT(1)
@@ -977,12 +978,51 @@ int pmd_clear_huge(pmd_t *pmdp)
 	return 1;
 }
 
-int pud_free_pmd_page(pud_t *pud)
+int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
 {
-	return pud_none(*pud);
+	pte_t *table;
+	pmd_t pmd;
+
+	pmd = READ_ONCE(*pmdp);
+
+	/* No-op for empty entry and WARN_ON for valid entry */
+	if (!pmd_present(pmd) || !pmd_table(pmd)) {
+		VM_WARN_ON(!pmd_table(pmd));
+		return 1;
+	}
+
+	table = pte_offset_kernel(pmdp, addr);
+	pmd_clear(pmdp);
+	__flush_tlb_kernel_pgtable(addr);
+	pte_free_kernel(NULL, table);
+	return 1;
 }
 
-int pmd_free_pte_page(pmd_t *pmd)
+int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
 {
-	return pmd_none(*pmd);
+	pmd_t *table;
+	pmd_t *pmdp;
+	pud_t pud;
+	unsigned long next, end;
+
+	pud = READ_ONCE(*pudp);
+
+	/* No-op for empty entry and WARN_ON for valid entry */
+	if (!pud_present(pud) || !pud_table(pud)) {
+		VM_WARN_ON(!pud_table(pud));
+		return 1;
+	}
+
+	table = pmd_offset(pudp, addr);
+	pmdp = table;
+	next = addr;
+	end = addr + PUD_SIZE;
+	do {
+		pmd_free_pte_page(pmdp, next);
+	} while (pmdp++, next += PMD_SIZE, next != end);
+
+	pud_clear(pudp);
+	__flush_tlb_kernel_pgtable(addr);
+	pmd_free(NULL, table);
+	return 1;
 }
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index dad128ba98bf..146c04ceaa51 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -70,19 +70,32 @@ EXPORT_SYMBOL(cpumask_of_node);
 
 #endif
 
-static void map_cpu_to_node(unsigned int cpu, int nid)
+static void numa_update_cpu(unsigned int cpu, bool remove)
 {
-	set_cpu_numa_node(cpu, nid);
-	if (nid >= 0)
+	int nid = cpu_to_node(cpu);
+
+	if (nid == NUMA_NO_NODE)
+		return;
+
+	if (remove)
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]);
+	else
 		cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
 }
 
-void numa_clear_node(unsigned int cpu)
+void numa_add_cpu(unsigned int cpu)
 {
-	int nid = cpu_to_node(cpu);
+	numa_update_cpu(cpu, false);
+}
 
-	if (nid >= 0)
-		cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]);
+void numa_remove_cpu(unsigned int cpu)
+{
+	numa_update_cpu(cpu, true);
+}
+
+void numa_clear_node(unsigned int cpu)
+{
+	numa_remove_cpu(cpu);
 	set_cpu_numa_node(cpu, NUMA_NO_NODE);
 }
 
@@ -116,7 +129,7 @@ static void __init setup_node_to_cpumask_map(void)
  */
 void numa_store_cpu_info(unsigned int cpu)
 {
-	map_cpu_to_node(cpu, cpu_to_node_map[cpu]);
+	set_cpu_numa_node(cpu, cpu_to_node_map[cpu]);
 }
 
 void __init early_map_cpu_to_node(unsigned int cpu, int nid)
diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c
index 02b18f8b2905..24d786fc3a4c 100644
--- a/arch/arm64/mm/ptdump_debugfs.c
+++ b/arch/arm64/mm/ptdump_debugfs.c
@@ -10,18 +10,7 @@ static int ptdump_show(struct seq_file *m, void *v)
 	ptdump_walk_pgd(m, info);
 	return 0;
 }
-
-static int ptdump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ptdump_show, inode->i_private);
-}
-
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(ptdump);
 
 int ptdump_debugfs_register(struct ptdump_info *info, const char *name)
 {
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 941e7554e886..c6b6a06231b2 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -2,8 +2,10 @@
 #ifndef __ARCH_H8300_ATOMIC__
 #define __ARCH_H8300_ATOMIC__
 
+#include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/irqflags.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -15,8 +17,6 @@
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
-#include <linux/kernel.h>
-
 #define ATOMIC_OP_RETURN(op, c_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)	\
 {								\
@@ -69,18 +69,6 @@ ATOMIC_OPS(sub, -=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
-
-#define atomic_inc_return(v)		atomic_add_return(1, v)
-#define atomic_dec_return(v)		atomic_sub_return(1, v)
-
-#define atomic_inc(v)			(void)atomic_inc_return(v)
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-
-#define atomic_dec(v)			(void)atomic_dec_return(v)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -94,7 +82,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int ret;
 	h8300flags flags;
@@ -106,5 +94,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	arch_local_irq_restore(flags);
 	return ret;
 }
+#define atomic_fetch_add_unless		atomic_fetch_add_unless
 
 #endif /* __ARCH_H8300_ATOMIC __ */
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index fb3dfb2a667e..311b9894ccc8 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -164,7 +164,7 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer to value
  * @a: amount to add
  * @u: unless value is equal to u
@@ -173,7 +173,7 @@ ATOMIC_OPS(xor)
  *
  */
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int __oldval;
 	register int tmp;
@@ -196,18 +196,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	);
 	return __oldval;
 }
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-#define atomic_inc(v) atomic_add(1, (v))
-#define atomic_dec(v) atomic_sub(1, (v))
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0)
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
-#define atomic_inc_return(v) (atomic_add_return(1, v))
-#define atomic_dec_return(v) (atomic_sub_return(1, v))
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #endif
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index ff861420b8f5..02eb68d5d1c0 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -16,6 +16,7 @@ config IA64
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select PCI if (!IA64_HP_SIM)
 	select ACPI if (!IA64_HP_SIM)
+	select ARCH_SUPPORTS_ACPI if (!IA64_HP_SIM)
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
 	select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
 	select HAVE_UNSTABLE_SCHED_CLOCK
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 2524fb60fbc2..206530d0751b 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -215,91 +215,10 @@ ATOMIC64_FETCH_OP(xor, ^)
 	(cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
-
-static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
-/*
- * Atomically add I to V and return TRUE if the resulting value is
- * negative.
- */
-static __inline__ int
-atomic_add_negative (int i, atomic_t *v)
-{
-	return atomic_add_return(i, v) < 0;
-}
-
-static __inline__ long
-atomic64_add_negative (__s64 i, atomic64_t *v)
-{
-	return atomic64_add_return(i, v) < 0;
-}
-
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
-#define atomic_inc_and_test(v)		(atomic_add_return(1, (v)) == 0)
-#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i), (v)) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_sub_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v)	(atomic64_add_return(1, (v)) == 0)
-
 #define atomic_add(i,v)			(void)atomic_add_return((i), (v))
 #define atomic_sub(i,v)			(void)atomic_sub_return((i), (v))
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
 
 #define atomic64_add(i,v)		(void)atomic64_add_return((i), (v))
 #define atomic64_sub(i,v)		(void)atomic64_sub_return((i), (v))
-#define atomic64_inc(v)			atomic64_add(1, (v))
-#define atomic64_dec(v)			atomic64_sub(1, (v))
 
 #endif /* _ASM_IA64_ATOMIC_H */
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index fb0651961e2c..6f952171abf9 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -83,12 +83,14 @@ virt_to_phys (volatile void *address)
 {
 	return (unsigned long) address - PAGE_OFFSET;
 }
+#define virt_to_phys virt_to_phys
 
 static inline void*
 phys_to_virt (unsigned long address)
 {
 	return (void *) (address + PAGE_OFFSET);
 }
+#define phys_to_virt phys_to_virt
 
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
 extern u64 kern_mem_attribute (unsigned long phys_addr, unsigned long size);
@@ -433,9 +435,11 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo
 {
 	return ioremap(phys_addr, size);
 }
+#define ioremap ioremap
+#define ioremap_nocache ioremap_nocache
 #define ioremap_cache ioremap_cache
 #define ioremap_uc ioremap_nocache
-
+#define iounmap iounmap
 
 /*
  * String version of IO memory access ops:
@@ -444,6 +448,13 @@ extern void memcpy_fromio(void *dst, const volatile void __iomem *src, long n);
 extern void memcpy_toio(volatile void __iomem *dst, const void *src, long n);
 extern void memset_io(volatile void __iomem *s, int c, long n);
 
+#define memcpy_fromio memcpy_fromio
+#define memcpy_toio memcpy_toio
+#define memset_io memset_io
+#define xlate_dev_kmem_ptr xlate_dev_kmem_ptr
+#define xlate_dev_mem_ptr xlate_dev_mem_ptr
+#include <asm-generic/io.h>
+
 # endif /* __KERNEL__ */
 
 #endif /* _ASM_IA64_IO_H */
diff --git a/arch/ia64/include/asm/kprobes.h b/arch/ia64/include/asm/kprobes.h
index 0302b3664789..580356a2eea6 100644
--- a/arch/ia64/include/asm/kprobes.h
+++ b/arch/ia64/include/asm/kprobes.h
@@ -82,8 +82,6 @@ struct prev_kprobe {
 #define ARCH_PREV_KPROBE_SZ 2
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
-	struct pt_regs jprobe_saved_regs;
-	unsigned long jprobes_saved_stacked_regs[MAX_PARAM_RSE_SIZE];
 	unsigned long *bsp;
 	unsigned long cfm;
 	atomic_t prev_kprobe_index;
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 44f0ac0df308..516355a774bf 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -115,12 +115,11 @@ ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned
 		flush_tlb_all();
 	} else {
 		/*
-		 * XXX fix me: flush_tlb_range() should take an mm pointer instead of a
-		 * vma pointer.
+		 * flush_tlb_range() takes a vma instead of a mm pointer because
+		 * some architectures want the vm_flags for ITLB/DTLB flush.
 		 */
-		struct vm_area_struct vma;
+		struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
 
-		vma.vm_mm = tlb->mm;
 		/* flush the address range from the tlb: */
 		flush_tlb_range(&vma, start, end);
 		/* now flush the virt. page-table area mapping the address range: */
diff --git a/arch/ia64/include/uapi/asm/break.h b/arch/ia64/include/uapi/asm/break.h
index 5d742bcb0018..4ca110f0a94b 100644
--- a/arch/ia64/include/uapi/asm/break.h
+++ b/arch/ia64/include/uapi/asm/break.h
@@ -14,7 +14,6 @@
  */
 #define __IA64_BREAK_KDB		0x80100
 #define __IA64_BREAK_KPROBE		0x81000 /* .. 0x81fff */
-#define __IA64_BREAK_JPROBE		0x82000
 
 /*
  * OS-specific break numbers:
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 498f3da3f225..d0c0ccdd656a 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -25,7 +25,7 @@ obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_PERFMON)		+= perfmon_default_smpl.o
 obj-$(CONFIG_IA64_CYCLONE)	+= cyclone.o
 obj-$(CONFIG_IA64_MCA_RECOVERY)	+= mca_recovery.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o jprobes.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S
deleted file mode 100644
index f69389c7be1d..000000000000
--- a/arch/ia64/kernel/jprobes.S
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Jprobe specific operations
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) Intel Corporation, 2005
- *
- * 2005-May     Rusty Lynch <rusty.lynch@intel.com> and Anil S Keshavamurthy
- *              <anil.s.keshavamurthy@intel.com> initial implementation
- *
- * Jprobes (a.k.a. "jump probes" which is built on-top of kprobes) allow a
- * probe to be inserted into the beginning of a function call.  The fundamental
- * difference between a jprobe and a kprobe is the jprobe handler is executed
- * in the same context as the target function, while the kprobe handlers
- * are executed in interrupt context.
- *
- * For jprobes we initially gain control by placing a break point in the
- * first instruction of the targeted function.  When we catch that specific
- * break, we:
- *        * set the return address to our jprobe_inst_return() function
- *        * jump to the jprobe handler function
- *
- * Since we fixed up the return address, the jprobe handler will return to our
- * jprobe_inst_return() function, giving us control again.  At this point we
- * are back in the parents frame marker, so we do yet another call to our
- * jprobe_break() function to fix up the frame marker as it would normally
- * exist in the target function.
- *
- * Our jprobe_return function then transfers control back to kprobes.c by
- * executing a break instruction using one of our reserved numbers.  When we
- * catch that break in kprobes.c, we continue like we do for a normal kprobe
- * by single stepping the emulated instruction, and then returning execution
- * to the correct location.
- */
-#include <asm/asmmacro.h>
-#include <asm/break.h>
-
-	/*
-	 * void jprobe_break(void)
-	 */
-	.section .kprobes.text, "ax"
-ENTRY(jprobe_break)
-	break.m __IA64_BREAK_JPROBE
-END(jprobe_break)
-
-	/*
-	 * void jprobe_inst_return(void)
-	 */
-GLOBAL_ENTRY(jprobe_inst_return)
-	br.call.sptk.many b0=jprobe_break
-END(jprobe_inst_return)
-
-GLOBAL_ENTRY(invalidate_stacked_regs)
-	movl r16=invalidate_restore_cfm
-	;;
-	mov b6=r16
-	;;
-	br.ret.sptk.many b6
-	;;
-invalidate_restore_cfm:
-	mov r16=ar.rsc
-	;;
-	mov ar.rsc=r0
-	;;
-	loadrs
-	;;
-	mov ar.rsc=r16
-	;;
-	br.cond.sptk.many rp
-END(invalidate_stacked_regs)
-
-GLOBAL_ENTRY(flush_register_stack)
-	// flush dirty regs to backing store (must be first in insn group)
-	flushrs
-	;;
-	br.ret.sptk.many rp
-END(flush_register_stack)
-
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index f5f3a5e6fcd1..aa41bd5cf9b7 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -35,8 +35,6 @@
 #include <asm/sections.h>
 #include <asm/exception.h>
 
-extern void jprobe_inst_return(void);
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -480,12 +478,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 			 */
 			break;
 	}
-
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
@@ -819,14 +814,6 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 			prepare_ss(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			return 1;
-		} else if (args->err == __IA64_BREAK_JPROBE) {
-			/*
-			 * jprobe instrumented function just completed
-			 */
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				goto ss_probe;
-			}
 		} else if (!is_ia64_break_inst(regs)) {
 			/* The breakpoint instruction was removed by
 			 * another cpu right after we hit, no further
@@ -861,15 +848,12 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 	set_current_kprobe(p, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/*
-		 * Our pre-handler is specifically requesting that we just
-		 * do a return.  This is used for both the jprobe pre-handler
-		 * and the kretprobe trampoline
-		 */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 #if !defined(CONFIG_PREEMPT)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
@@ -992,7 +976,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	case DIE_BREAK:
 		/* err is break number from ia64_bad_break() */
 		if ((args->err >> 12) == (__IA64_BREAK_KPROBE >> 12)
-			|| args->err == __IA64_BREAK_JPROBE
 			|| args->err == 0)
 			if (pre_kprobes_handler(args))
 				ret = NOTIFY_STOP;
@@ -1040,74 +1023,6 @@ unsigned long arch_deref_entry_point(void *entry)
 	return ((struct fnptr *)entry)->ip;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr = arch_deref_entry_point(jp->entry);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	struct param_bsp_cfm pa;
-	int bytes;
-
-	/*
-	 * Callee owns the argument space and could overwrite it, eg
-	 * tail call optimization. So to be absolutely safe
-	 * we save the argument space before transferring the control
-	 * to instrumented jprobe function which runs in
-	 * the process context
-	 */
-	pa.ip = regs->cr_iip;
-	unw_init_running(ia64_get_bsp_cfm, &pa);
-	bytes = (char *)ia64_rse_skip_regs(pa.bsp, pa.cfm & 0x3f)
-				- (char *)pa.bsp;
-	memcpy( kcb->jprobes_saved_stacked_regs,
-		pa.bsp,
-		bytes );
-	kcb->bsp = pa.bsp;
-	kcb->cfm = pa.cfm;
-
-	/* save architectural state */
-	kcb->jprobe_saved_regs = *regs;
-
-	/* after rfi, execute the jprobe instrumented function */
-	regs->cr_iip = addr & ~0xFULL;
-	ia64_psr(regs)->ri = addr & 0xf;
-	regs->r1 = ((struct fnptr *)(jp->entry))->gp;
-
-	/*
-	 * fix the return address to our jprobe_inst_return() function
-	 * in the jprobes.S file
-	 */
-	regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip;
-
-	return 1;
-}
-
-/* ia64 does not need this */
-void __kprobes jprobe_return(void)
-{
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	int bytes;
-
-	/* restoring architectural state */
-	*regs = kcb->jprobe_saved_regs;
-
-	/* restoring the original argument space */
-	flush_register_stack();
-	bytes = (char *)ia64_rse_skip_regs(kcb->bsp, kcb->cfm & 0x3f)
-				- (char *)kcb->bsp;
-	memcpy( kcb->bsp,
-		kcb->jprobes_saved_stacked_regs,
-		bytes );
-	invalidate_stacked_regs();
-
-	preempt_enable_no_resched();
-	return 1;
-}
-
 static struct kprobe trampoline_p = {
 	.pre_handler = trampoline_probe_handler
 };
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 3b38c717008a..46bff1661836 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2278,17 +2278,15 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	DPRINT(("smpl_buf @%p\n", smpl_buf));
 
 	/* allocate vma */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		DPRINT(("Cannot allocate vma\n"));
 		goto error_kmem;
 	}
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	/*
 	 * partially initialize the vma for the sampling buffer
 	 */
-	vma->vm_mm	     = mm;
 	vma->vm_file	     = get_file(filp);
 	vma->vm_flags	     = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP;
 	vma->vm_page_prot    = PAGE_READONLY; /* XXX may need to change */
@@ -2346,7 +2344,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	return 0;
 
 error:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 error_kmem:
 	pfm_rvfree(smpl_buf, size);
 
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 18278b448530..3b85c3ecac38 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -114,10 +114,9 @@ ia64_init_addr_space (void)
 	 * the problem.  When the process attempts to write to the register backing store
 	 * for the first time, it will get a SEGFAULT in this case.
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(current->mm);
 	if (vma) {
-		INIT_LIST_HEAD(&vma->anon_vma_chain);
-		vma->vm_mm = current->mm;
+		vma_set_anonymous(vma);
 		vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
 		vma->vm_end = vma->vm_start + PAGE_SIZE;
 		vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT;
@@ -125,7 +124,7 @@ ia64_init_addr_space (void)
 		down_write(&current->mm->mmap_sem);
 		if (insert_vm_struct(current->mm, vma)) {
 			up_write(&current->mm->mmap_sem);
-			kmem_cache_free(vm_area_cachep, vma);
+			vm_area_free(vma);
 			return;
 		}
 		up_write(&current->mm->mmap_sem);
@@ -133,10 +132,9 @@ ia64_init_addr_space (void)
 
 	/* map NaT-page at address zero to speed up speculative dereferencing of NULL: */
 	if (!(current->personality & MMAP_PAGE_ZERO)) {
-		vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+		vma = vm_area_alloc(current->mm);
 		if (vma) {
-			INIT_LIST_HEAD(&vma->anon_vma_chain);
-			vma->vm_mm = current->mm;
+			vma_set_anonymous(vma);
 			vma->vm_end = PAGE_SIZE;
 			vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
 			vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO |
@@ -144,7 +142,7 @@ ia64_init_addr_space (void)
 			down_write(&current->mm->mmap_sem);
 			if (insert_vm_struct(current->mm, vma)) {
 				up_write(&current->mm->mmap_sem);
-				kmem_cache_free(vm_area_cachep, vma);
+				vm_area_free(vma);
 				return;
 			}
 			up_write(&current->mm->mmap_sem);
@@ -277,7 +275,7 @@ static struct vm_area_struct gate_vma;
 
 static int __init gate_vma_init(void)
 {
-	gate_vma.vm_mm = NULL;
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 785612b576f7..b29f93774d95 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -2,6 +2,7 @@
 config M68K
 	bool
 	default y
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA
 	select ARCH_MIGHT_HAVE_PC_PARPORT if ISA
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 	select HAVE_IDE
@@ -24,6 +25,10 @@ config M68K
 	select MODULES_USE_ELF_RELA
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
+	select DMA_NONCOHERENT_OPS if HAS_DMA
+	select HAVE_MEMBLOCK
+	select ARCH_DISCARD_MEMBLOCK
+	select NO_BOOTMEM
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index b2a6bc63f8cd..aef8d42e078d 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -31,7 +31,6 @@ extern void dn_sched_init(irq_handler_t handler);
 extern void dn_init_IRQ(void);
 extern u32 dn_gettimeoffset(void);
 extern int dn_dummy_hwclk(int, struct rtc_time *);
-extern int dn_dummy_set_clock_mmss(unsigned long);
 extern void dn_dummy_reset(void);
 #ifdef CONFIG_HEARTBEAT
 static void dn_heartbeat(int on);
@@ -156,7 +155,6 @@ void __init config_apollo(void)
 	arch_gettimeoffset   = dn_gettimeoffset;
 	mach_max_dma_address = 0xffffffff;
 	mach_hwclk           = dn_dummy_hwclk; /* */
-	mach_set_clock_mmss  = dn_dummy_set_clock_mmss; /* */
 	mach_reset	     = dn_dummy_reset;  /* */
 #ifdef CONFIG_HEARTBEAT
 	mach_heartbeat = dn_heartbeat;
@@ -240,12 +238,6 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) {
 
 }
 
-int dn_dummy_set_clock_mmss(unsigned long nowtime)
-{
-	pr_info("set_clock_mmss\n");
-	return 0;
-}
-
 void dn_dummy_reset(void) {
 
   dn_serial_print("The end !\n");
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 565c6f06ab0b..bd96702a1ad0 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -81,9 +81,6 @@ extern void atari_sched_init(irq_handler_t);
 extern u32 atari_gettimeoffset(void);
 extern int atari_mste_hwclk (int, struct rtc_time *);
 extern int atari_tt_hwclk (int, struct rtc_time *);
-extern int atari_mste_set_clock_mmss (unsigned long);
-extern int atari_tt_set_clock_mmss (unsigned long);
-
 
 /* ++roman: This is a more elaborate test for an SCC chip, since the plain
  * Medusa board generates DTACK at the SCC's standard addresses, but a SCC
@@ -362,13 +359,11 @@ void __init config_atari(void)
 		ATARIHW_SET(TT_CLK);
 		pr_cont(" TT_CLK");
 		mach_hwclk = atari_tt_hwclk;
-		mach_set_clock_mmss = atari_tt_set_clock_mmss;
 	}
 	if (hwreg_present(&mste_rtc.sec_ones)) {
 		ATARIHW_SET(MSTE_CLK);
 		pr_cont(" MSTE_CLK");
 		mach_hwclk = atari_mste_hwclk;
-		mach_set_clock_mmss = atari_mste_set_clock_mmss;
 	}
 	if (!MACH_IS_MEDUSA && hwreg_present(&dma_wd.fdc_speed) &&
 	    hwreg_write(&dma_wd.fdc_speed, 0)) {
diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c
index c549b48174ec..9cca64286464 100644
--- a/arch/m68k/atari/time.c
+++ b/arch/m68k/atari/time.c
@@ -285,69 +285,6 @@ int atari_tt_hwclk( int op, struct rtc_time *t )
     return( 0 );
 }
 
-
-int atari_mste_set_clock_mmss (unsigned long nowtime)
-{
-    short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-    struct MSTE_RTC val;
-    unsigned char rtc_minutes;
-
-    mste_read(&val);
-    rtc_minutes= val.min_ones + val.min_tens * 10;
-    if ((rtc_minutes < real_minutes
-         ? real_minutes - rtc_minutes
-         : rtc_minutes - real_minutes) < 30)
-    {
-        val.sec_ones = real_seconds % 10;
-        val.sec_tens = real_seconds / 10;
-        val.min_ones = real_minutes % 10;
-        val.min_tens = real_minutes / 10;
-        mste_write(&val);
-    }
-    else
-        return -1;
-    return 0;
-}
-
-int atari_tt_set_clock_mmss (unsigned long nowtime)
-{
-    int retval = 0;
-    short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-    unsigned char save_control, save_freq_select, rtc_minutes;
-
-    save_control = RTC_READ (RTC_CONTROL); /* tell the clock it's being set */
-    RTC_WRITE (RTC_CONTROL, save_control | RTC_SET);
-
-    save_freq_select = RTC_READ (RTC_FREQ_SELECT); /* stop and reset prescaler */
-    RTC_WRITE (RTC_FREQ_SELECT, save_freq_select | RTC_DIV_RESET2);
-
-    rtc_minutes = RTC_READ (RTC_MINUTES);
-    if (!(save_control & RTC_DM_BINARY))
-	rtc_minutes = bcd2bin(rtc_minutes);
-
-    /* Since we're only adjusting minutes and seconds, don't interfere
-       with hour overflow.  This avoids messing with unknown time zones
-       but requires your RTC not to be off by more than 30 minutes.  */
-    if ((rtc_minutes < real_minutes
-         ? real_minutes - rtc_minutes
-         : rtc_minutes - real_minutes) < 30)
-        {
-            if (!(save_control & RTC_DM_BINARY))
-                {
-		    real_seconds = bin2bcd(real_seconds);
-		    real_minutes = bin2bcd(real_minutes);
-                }
-            RTC_WRITE (RTC_SECONDS, real_seconds);
-            RTC_WRITE (RTC_MINUTES, real_minutes);
-        }
-    else
-        retval = -1;
-
-    RTC_WRITE (RTC_FREQ_SELECT, save_freq_select);
-    RTC_WRITE (RTC_CONTROL, save_control);
-    return retval;
-}
-
 /*
  * Local variables:
  *  c-indent-level: 4
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 2cfff4765040..143ee9fa3893 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -41,7 +41,6 @@ static void bvme6000_get_model(char *model);
 extern void bvme6000_sched_init(irq_handler_t handler);
 extern u32 bvme6000_gettimeoffset(void);
 extern int bvme6000_hwclk (int, struct rtc_time *);
-extern int bvme6000_set_clock_mmss (unsigned long);
 extern void bvme6000_reset (void);
 void bvme6000_set_vectors (void);
 
@@ -113,7 +112,6 @@ void __init config_bvme6000(void)
     mach_init_IRQ        = bvme6000_init_IRQ;
     arch_gettimeoffset   = bvme6000_gettimeoffset;
     mach_hwclk           = bvme6000_hwclk;
-    mach_set_clock_mmss	 = bvme6000_set_clock_mmss;
     mach_reset		 = bvme6000_reset;
     mach_get_model       = bvme6000_get_model;
 
@@ -305,46 +303,3 @@ int bvme6000_hwclk(int op, struct rtc_time *t)
 
 	return 0;
 }
-
-/*
- * Set the minutes and seconds from seconds value 'nowtime'.  Fail if
- * clock is out by > 30 minutes.  Logic lifted from atari code.
- * Algorithm is to wait for the 10ms register to change, and then to
- * wait a short while, and then set it.
- */
-
-int bvme6000_set_clock_mmss (unsigned long nowtime)
-{
-	int retval = 0;
-	short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-	unsigned char rtc_minutes, rtc_tenms;
-	volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE;
-	unsigned char msr = rtc->msr & 0xc0;
-	unsigned long flags;
-	volatile int i;
-
-	rtc->msr = 0;		/* Ensure clock accessible */
-	rtc_minutes = bcd2bin (rtc->bcd_min);
-
-	if ((rtc_minutes < real_minutes
-		? real_minutes - rtc_minutes
-			: rtc_minutes - real_minutes) < 30)
-	{
-		local_irq_save(flags);
-		rtc_tenms = rtc->bcd_tenms;
-		while (rtc_tenms == rtc->bcd_tenms)
-			;
-		for (i = 0; i < 1000; i++)
-			;
-		rtc->bcd_min = bin2bcd(real_minutes);
-		rtc->bcd_sec = bin2bcd(real_seconds);
-		local_irq_restore(flags);
-	}
-	else
-		retval = -1;
-
-	rtc->msr = msr;
-
-	return retval;
-}
-
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index a874e54404d1..1d5483f6e457 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -52,6 +52,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -98,18 +99,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -122,6 +119,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -200,7 +198,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -231,7 +228,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -260,7 +256,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -356,6 +352,7 @@ CONFIG_A2091_SCSI=y
 CONFIG_GVP11_SCSI=y
 CONFIG_SCSI_A4000T=y
 CONFIG_SCSI_ZORRO7XX=y
+CONFIG_SCSI_ZORRO_ESP=y
 CONFIG_MD=y
 CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
@@ -363,6 +360,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -402,8 +400,8 @@ CONFIG_A2065=y
 CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -412,8 +410,10 @@ CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
+CONFIG_XSURF100=y
 CONFIG_HYDRA=y
 CONFIG_APNE=y
 CONFIG_ZORRO8390=y
@@ -426,9 +426,9 @@ CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -478,6 +478,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -499,7 +500,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -600,6 +601,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -622,6 +624,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -657,6 +664,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 8ce39e23aa42..52a0af127951 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -381,14 +378,15 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -400,9 +398,9 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -440,6 +438,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -458,7 +457,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -559,6 +558,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -581,6 +581,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -616,6 +621,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 346c4e75edf8..b3103e51268a 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -391,14 +388,15 @@ CONFIG_VETH=m
 CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
 CONFIG_NE2000=y
@@ -411,9 +409,9 @@ CONFIG_NE2000=y
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -480,7 +478,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -581,6 +579,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -603,6 +602,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -638,6 +642,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index fca9c7aa71a3..fb7d651a4cab 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -380,14 +377,15 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -399,9 +397,9 @@ CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -433,6 +431,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index f9eab174915c..6b37f5537c39 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -382,14 +379,15 @@ CONFIG_VETH=m
 CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -401,9 +399,9 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -443,6 +441,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -460,7 +459,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -561,6 +560,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -583,6 +583,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -618,6 +623,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index b52e597899eb..930cc2965a11 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -49,6 +49,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -95,18 +96,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -119,6 +116,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -197,7 +195,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -228,7 +225,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -257,7 +253,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -398,8 +395,8 @@ CONFIG_VETH=m
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -407,6 +404,7 @@ CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 CONFIG_MACSONIC=y
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -420,9 +418,9 @@ CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -465,6 +463,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -482,7 +481,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -583,6 +582,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -605,6 +605,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -640,6 +645,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 2a84eeec5b02..e7dd25300127 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -59,6 +59,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -105,18 +106,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -129,6 +126,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -207,7 +205,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -238,7 +235,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -267,7 +263,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -311,6 +306,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -373,6 +369,7 @@ CONFIG_A2091_SCSI=y
 CONFIG_GVP11_SCSI=y
 CONFIG_SCSI_A4000T=y
 CONFIG_SCSI_ZORRO7XX=y
+CONFIG_SCSI_ZORRO_ESP=y
 CONFIG_ATARI_SCSI=y
 CONFIG_MAC_SCSI=y
 CONFIG_SCSI_MAC_ESP=y
@@ -387,6 +384,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -438,8 +436,8 @@ CONFIG_SUN3LANCE=y
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -449,9 +447,11 @@ CONFIG_BVME6000_NET=y
 CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 CONFIG_MACSONIC=y
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
+CONFIG_XSURF100=y
 CONFIG_HYDRA=y
 CONFIG_MAC8390=y
 CONFIG_NE2000=y
@@ -466,9 +466,9 @@ CONFIG_ZORRO8390=y
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PLIP=m
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -533,6 +533,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -562,7 +563,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -663,6 +664,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -685,6 +687,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -720,6 +727,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 476e69994340..b383327fd77a 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -47,6 +47,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -93,18 +94,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -117,6 +114,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -195,7 +193,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -226,7 +223,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -255,7 +251,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -296,6 +291,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -343,6 +339,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -380,14 +377,15 @@ CONFIG_VETH=m
 CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -399,9 +397,9 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -433,6 +431,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 1477cda9146e..9783d3deb9e9 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -380,14 +377,15 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -399,9 +397,9 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -433,6 +431,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index b3a543dc48a0..a35d10ee10cb 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -350,6 +346,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -388,8 +385,8 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -398,6 +395,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
 CONFIG_NE2000=y
@@ -410,9 +408,9 @@ CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PLIP=m
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -455,6 +453,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -473,7 +472,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -574,6 +573,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -596,6 +596,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -631,6 +636,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index d543ed5dfa96..573bf922d448 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -385,6 +382,7 @@ CONFIG_SUN3LANCE=y
 CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -397,9 +395,9 @@ CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -435,6 +433,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -574,6 +574,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -609,6 +614,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index a67e54246023..efb27a7fcc55 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -378,14 +375,15 @@ CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -397,9 +395,9 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -435,6 +433,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -575,6 +575,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -610,6 +615,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 4d8d68c4e3dd..a4b8d3331a9e 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,6 +1,7 @@
 generic-y += barrier.h
 generic-y += compat.h
 generic-y += device.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index e993e2860ee1..47228b0d4163 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -126,11 +126,13 @@ static inline void atomic_inc(atomic_t *v)
 {
 	__asm__ __volatile__("addql #1,%0" : "+m" (*v));
 }
+#define atomic_inc atomic_inc
 
 static inline void atomic_dec(atomic_t *v)
 {
 	__asm__ __volatile__("subql #1,%0" : "+m" (*v));
 }
+#define atomic_dec atomic_dec
 
 static inline int atomic_dec_and_test(atomic_t *v)
 {
@@ -138,6 +140,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
 	__asm__ __volatile__("subql #1,%1; seq %0" : "=d" (c), "+m" (*v));
 	return c != 0;
 }
+#define atomic_dec_and_test atomic_dec_and_test
 
 static inline int atomic_dec_and_test_lt(atomic_t *v)
 {
@@ -155,6 +158,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
 	__asm__ __volatile__("addql #1,%1; seq %0" : "=d" (c), "+m" (*v));
 	return c != 0;
 }
+#define atomic_inc_and_test atomic_inc_and_test
 
 #ifdef CONFIG_RMW_INSNS
 
@@ -190,9 +194,6 @@ static inline int atomic_xchg(atomic_t *v, int new)
 
 #endif /* !CONFIG_RMW_INSNS */
 
-#define atomic_dec_return(v)	atomic_sub_return(1, (v))
-#define atomic_inc_return(v)	atomic_add_return(1, (v))
-
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
 	char c;
@@ -201,6 +202,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v)
 			     : ASM_DI (i));
 	return c != 0;
 }
+#define atomic_sub_and_test atomic_sub_and_test
 
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
@@ -210,20 +212,6 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 			     : ASM_DI (i));
 	return c != 0;
 }
-
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
+#define atomic_add_negative atomic_add_negative
 
 #endif /* __ARCH_M68K_ATOMIC __ */
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index 93b47b1f6fb4..d979f38af751 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -454,7 +454,7 @@ static inline unsigned long ffz(unsigned long word)
  */
 #if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \
 	!defined(CONFIG_M68000) && !defined(CONFIG_MCPU32)
-static inline int __ffs(int x)
+static inline unsigned long __ffs(unsigned long x)
 {
 	__asm__ __volatile__ ("bitrev %0; ff1 %0"
 		: "=d" (x)
@@ -493,7 +493,11 @@ static inline int ffs(int x)
 		: "dm" (x & -x));
 	return 32 - cnt;
 }
-#define __ffs(x) (ffs(x) - 1)
+
+static inline unsigned long __ffs(unsigned long x)
+{
+	return ffs(x) - 1;
+}
 
 /*
  *	fls: find last bit set.
@@ -515,12 +519,16 @@ static inline int __fls(int x)
 
 #endif
 
+/* Simple test-and-set bit locks */
+#define test_and_set_bit_lock	test_and_set_bit
+#define clear_bit_unlock	clear_bit
+#define __clear_bit_unlock	clear_bit_unlock
+
 #include <asm-generic/bitops/ext2-atomic.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
 
 #endif /* _M68K_BITOPS_H */
diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h
deleted file mode 100644
index e3722ed04fbb..000000000000
--- a/arch/m68k/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _M68K_DMA_MAPPING_H
-#define _M68K_DMA_MAPPING_H
-
-extern const struct dma_map_ops m68k_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-        return &m68k_dma_ops;
-}
-
-#endif  /* _M68K_DMA_MAPPING_H */
diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h
index ca2849afb087..aabe6420ead2 100644
--- a/arch/m68k/include/asm/io.h
+++ b/arch/m68k/include/asm/io.h
@@ -1,6 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _M68K_IO_H
+#define _M68K_IO_H
+
 #if defined(__uClinux__) || defined(CONFIG_COLDFIRE)
 #include <asm/io_no.h>
 #else
 #include <asm/io_mm.h>
 #endif
+
+#include <asm-generic/io.h>
+
+#endif /* _M68K_IO_H */
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index fe485f4f5fac..782b78f8a048 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -16,13 +16,11 @@
  *    isa_readX(),isa_writeX()  are for ISA memory
  */
 
-#ifndef _IO_H
-#define _IO_H
+#ifndef _M68K_IO_MM_H
+#define _M68K_IO_MM_H
 
 #ifdef __KERNEL__
 
-#define ARCH_HAS_IOREMAP_WT
-
 #include <linux/compiler.h>
 #include <asm/raw_io.h>
 #include <asm/virtconvert.h>
@@ -369,40 +367,6 @@ static inline void isa_delay(void)
 #define writew(val, addr)	out_le16((addr), (val))
 #endif /* CONFIG_ATARI_ROM_ISA */
 
-#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
-/*
- * We need to define dummy functions for GENERIC_IOMAP support.
- */
-#define inb(port)          0xff
-#define inb_p(port)        0xff
-#define outb(val,port)     ((void)0)
-#define outb_p(val,port)   ((void)0)
-#define inw(port)          0xffff
-#define inw_p(port)        0xffff
-#define outw(val,port)     ((void)0)
-#define outw_p(val,port)   ((void)0)
-#define inl(port)          0xffffffffUL
-#define inl_p(port)        0xffffffffUL
-#define outl(val,port)     ((void)0)
-#define outl_p(val,port)   ((void)0)
-
-#define insb(port,buf,nr)  ((void)0)
-#define outsb(port,buf,nr) ((void)0)
-#define insw(port,buf,nr)  ((void)0)
-#define outsw(port,buf,nr) ((void)0)
-#define insl(port,buf,nr)  ((void)0)
-#define outsl(port,buf,nr) ((void)0)
-
-/*
- * These should be valid on any ioremap()ed region
- */
-#define readb(addr)      in_8(addr)
-#define writeb(val,addr) out_8((addr),(val))
-#define readw(addr)      in_le16(addr)
-#define writew(val,addr) out_le16((addr),(val))
-
-#endif /* !CONFIG_ISA && !CONFIG_ATARI_ROM_ISA */
-
 #define readl(addr)      in_le32(addr)
 #define writel(val,addr) out_le32((addr),(val))
 
@@ -444,4 +408,4 @@ static inline void isa_delay(void)
 #define writew_relaxed(b, addr)	writew(b, addr)
 #define writel_relaxed(b, addr)	writel(b, addr)
 
-#endif /* _IO_H */
+#endif /* _M68K_IO_MM_H */
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index 83a0a6d449f4..0498192e1d98 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -131,19 +131,7 @@ static inline void writel(u32 value, volatile void __iomem *addr)
 #define PCI_SPACE_LIMIT	PCI_IO_MASK
 #endif /* CONFIG_PCI */
 
-/*
- * These are defined in kmap.h as static inline functions. To maintain
- * previous behavior we put these define guards here so io_mm.h doesn't
- * see them.
- */
-#ifdef CONFIG_MMU
-#define memset_io memset_io
-#define memcpy_fromio memcpy_fromio
-#define memcpy_toio memcpy_toio
-#endif
-
 #include <asm/kmap.h>
 #include <asm/virtconvert.h>
-#include <asm-generic/io.h>
 
 #endif /* _M68KNOMMU_IO_H */
diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h
index 84b8333db8ad..aac7f045f7f0 100644
--- a/arch/m68k/include/asm/kmap.h
+++ b/arch/m68k/include/asm/kmap.h
@@ -4,6 +4,8 @@
 
 #ifdef CONFIG_MMU
 
+#define ARCH_HAS_IOREMAP_WT
+
 /* Values for nocacheflag and cmode */
 #define IOMAP_FULL_CACHING		0
 #define IOMAP_NOCACHE_SER		1
@@ -16,6 +18,7 @@
  */
 extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size,
 			       int cacheflag);
+#define iounmap iounmap
 extern void iounmap(void __iomem *addr);
 extern void __iounmap(void *addr, unsigned long size);
 
@@ -33,31 +36,35 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr,
 }
 
 #define ioremap_uc ioremap_nocache
+#define ioremap_wt ioremap_wt
 static inline void __iomem *ioremap_wt(unsigned long physaddr,
 				       unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
 }
 
-#define ioremap_fillcache ioremap_fullcache
+#define ioremap_fullcache ioremap_fullcache
 static inline void __iomem *ioremap_fullcache(unsigned long physaddr,
 					      unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
 }
 
+#define memset_io memset_io
 static inline void memset_io(volatile void __iomem *addr, unsigned char val,
 			     int count)
 {
 	__builtin_memset((void __force *) addr, val, count);
 }
 
+#define memcpy_fromio memcpy_fromio
 static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
 				 int count)
 {
 	__builtin_memcpy(dst, (void __force *) src, count);
 }
 
+#define memcpy_toio memcpy_toio
 static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
 			       int count)
 {
diff --git a/arch/m68k/include/asm/machdep.h b/arch/m68k/include/asm/machdep.h
index 1605da48ebf2..49bd3266b4b1 100644
--- a/arch/m68k/include/asm/machdep.h
+++ b/arch/m68k/include/asm/machdep.h
@@ -22,7 +22,6 @@ extern int (*mach_hwclk)(int, struct rtc_time*);
 extern unsigned int (*mach_get_ss)(void);
 extern int (*mach_get_rtc_pll)(struct rtc_pll_info *);
 extern int (*mach_set_rtc_pll)(struct rtc_pll_info *);
-extern int (*mach_set_clock_mmss)(unsigned long);
 extern void (*mach_reset)( void );
 extern void (*mach_halt)( void );
 extern void (*mach_power_off)( void );
diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h
index 9b840c03ebb7..08cee11180e6 100644
--- a/arch/m68k/include/asm/macintosh.h
+++ b/arch/m68k/include/asm/macintosh.h
@@ -57,7 +57,6 @@ struct mac_model
 #define MAC_SCSI_IIFX		5
 #define MAC_SCSI_DUO		6
 #define MAC_SCSI_LC		7
-#define MAC_SCSI_LATE		8
 
 #define MAC_IDE_NONE		0
 #define MAC_IDE_QUADRA		1
diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h
index 8b707c249026..12fe700632f4 100644
--- a/arch/m68k/include/asm/mcf_pgalloc.h
+++ b/arch/m68k/include/asm/mcf_pgalloc.h
@@ -44,6 +44,7 @@ extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address)
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
 				  unsigned long address)
 {
+	pgtable_page_dtor(page);
 	__free_page(page);
 }
 
@@ -74,8 +75,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	return page;
 }
 
-extern inline void pte_free(struct mm_struct *mm, struct page *page)
+static inline void pte_free(struct mm_struct *mm, struct page *page)
 {
+	pgtable_page_dtor(page);
 	__free_page(page);
 }
 
diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
index e644c4daf540..6bbe52025de3 100644
--- a/arch/m68k/include/asm/page_no.h
+++ b/arch/m68k/include/asm/page_no.h
@@ -18,7 +18,7 @@ extern unsigned long memory_end;
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 #define __pa(vaddr)		((unsigned long)(vaddr))
-#define __va(paddr)		((void *)(paddr))
+#define __va(paddr)		((void *)((unsigned long)(paddr)))
 
 #define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
 #define pfn_to_virt(pfn)	__va((pfn) << PAGE_SHIFT)
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 463572c4943f..e99993c57d6b 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -6,7 +6,7 @@
 
 #undef DEBUG
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
@@ -19,7 +19,7 @@
 
 #if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE)
 
-static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		gfp_t flag, unsigned long attrs)
 {
 	struct page *page, **map;
@@ -62,7 +62,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	return addr;
 }
 
-static void m68k_dma_free(struct device *dev, size_t size, void *addr,
+void arch_dma_free(struct device *dev, size_t size, void *addr,
 		dma_addr_t handle, unsigned long attrs)
 {
 	pr_debug("dma_free_coherent: %p, %x\n", addr, handle);
@@ -73,8 +73,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *addr,
 
 #include <asm/cacheflush.h>
 
-static void *m68k_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	void *ret;
 
@@ -89,7 +89,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size,
 	return ret;
 }
 
-static void m68k_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	free_pages((unsigned long)vaddr, get_order(size));
@@ -97,8 +97,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *vaddr,
 
 #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */
 
-static void m68k_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle,
+		size_t size, enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
@@ -115,58 +115,6 @@ static void m68k_dma_sync_single_for_device(struct device *dev,
 	}
 }
 
-static void m68k_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sglist, int nents, enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
-					   dir);
-	}
-}
-
-static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	dma_addr_t handle = page_to_phys(page) + offset;
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_sync_single_for_device(dev, handle, size, dir);
-
-	return handle;
-}
-
-static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		sg->dma_address = sg_phys(sg);
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
-					   dir);
-	}
-	return nents;
-}
-
-const struct dma_map_ops m68k_dma_ops = {
-	.alloc			= m68k_dma_alloc,
-	.free			= m68k_dma_free,
-	.map_page		= m68k_dma_map_page,
-	.map_sg			= m68k_dma_map_sg,
-	.sync_single_for_device	= m68k_dma_sync_single_for_device,
-	.sync_sg_for_device	= m68k_dma_sync_sg_for_device,
-};
-EXPORT_SYMBOL(m68k_dma_ops);
-
 void arch_setup_pdev_archdata(struct platform_device *pdev)
 {
 	if (pdev->dev.coherent_dma_mask == DMA_MASK_NONE &&
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index f35e3ebd6331..5d3596c180f9 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/module.h>
@@ -88,7 +89,6 @@ void (*mach_get_hardware_list) (struct seq_file *m);
 /* machine dependent timer functions */
 int (*mach_hwclk) (int, struct rtc_time*);
 EXPORT_SYMBOL(mach_hwclk);
-int (*mach_set_clock_mmss) (unsigned long);
 unsigned int (*mach_get_ss)(void);
 int (*mach_get_rtc_pll)(struct rtc_pll_info *);
 int (*mach_set_rtc_pll)(struct rtc_pll_info *);
@@ -165,6 +165,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 					be32_to_cpu(m->addr);
 				m68k_memory[m68k_num_memory].size =
 					be32_to_cpu(m->size);
+				memblock_add(m68k_memory[m68k_num_memory].addr,
+					     m68k_memory[m68k_num_memory].size);
 				m68k_num_memory++;
 			} else
 				pr_warn("%s: too many memory chunks\n",
@@ -224,10 +226,6 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 
 void __init setup_arch(char **cmdline_p)
 {
-#ifndef CONFIG_SUN3
-	int i;
-#endif
-
 	/* The bootinfo is located right after the kernel */
 	if (!CPU_IS_COLDFIRE)
 		m68k_parse_bootinfo((const struct bi_record *)_end);
@@ -356,14 +354,9 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 #ifndef CONFIG_SUN3
-	for (i = 1; i < m68k_num_memory; i++)
-		free_bootmem_node(NODE_DATA(i), m68k_memory[i].addr,
-				  m68k_memory[i].size);
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (m68k_ramdisk.size) {
-		reserve_bootmem_node(__virt_to_node(phys_to_virt(m68k_ramdisk.addr)),
-				     m68k_ramdisk.addr, m68k_ramdisk.size,
-				     BOOTMEM_DEFAULT);
+		memblock_reserve(m68k_ramdisk.addr, m68k_ramdisk.size);
 		initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr);
 		initrd_end = initrd_start + m68k_ramdisk.size;
 		pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end);
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index a98af1018201..cfd5475bfc31 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -28,6 +28,7 @@
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/initrd.h>
@@ -51,7 +52,6 @@ char __initdata command_line[COMMAND_LINE_SIZE];
 
 /* machine dependent timer functions */
 void (*mach_sched_init)(irq_handler_t handler) __initdata = NULL;
-int (*mach_set_clock_mmss)(unsigned long);
 int (*mach_hwclk) (int, struct rtc_time*);
 
 /* machine dependent reboot functions */
@@ -86,8 +86,6 @@ void (*mach_power_off)(void);
 
 void __init setup_arch(char **cmdline_p)
 {
-	int bootmap_size;
-
 	memory_start = PAGE_ALIGN(_ramstart);
 	memory_end = _ramend;
 
@@ -142,6 +140,8 @@ void __init setup_arch(char **cmdline_p)
 	pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ",
 		 __bss_stop, memory_start, memory_start, memory_end);
 
+	memblock_add(memory_start, memory_end - memory_start);
+
 	/* Keep a copy of command line */
 	*cmdline_p = &command_line[0];
 	memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
@@ -158,23 +158,10 @@ void __init setup_arch(char **cmdline_p)
 	min_low_pfn = PFN_DOWN(memory_start);
 	max_pfn = max_low_pfn = PFN_DOWN(memory_end);
 
-	bootmap_size = init_bootmem_node(
-			NODE_DATA(0),
-			min_low_pfn,		/* map goes here */
-			PFN_DOWN(PAGE_OFFSET),
-			max_pfn);
-	/*
-	 * Free the usable memory, we have to make sure we do not free
-	 * the bootmem bitmap so we then reserve it after freeing it :-)
-	 */
-	free_bootmem(memory_start, memory_end - memory_start);
-	reserve_bootmem(memory_start, bootmap_size, BOOTMEM_DEFAULT);
-
 #if defined(CONFIG_UBOOT) && defined(CONFIG_BLK_DEV_INITRD)
 	if ((initrd_start > 0) && (initrd_start < initrd_end) &&
 			(initrd_end < memory_end))
-		reserve_bootmem(initrd_start, initrd_end - initrd_start,
-				 BOOTMEM_DEFAULT);
+		memblock_reserve(initrd_start, initrd_end - initrd_start);
 #endif /* if defined(CONFIG_BLK_DEV_INITRD) */
 
 	/*
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index e522307db47c..b02d7254b73a 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -57,7 +57,6 @@ static unsigned long mac_orig_videoaddr;
 /* Mac specific timer functions */
 extern u32 mac_gettimeoffset(void);
 extern int mac_hwclk(int, struct rtc_time *);
-extern int mac_set_clock_mmss(unsigned long);
 extern void iop_preinit(void);
 extern void iop_init(void);
 extern void via_init(void);
@@ -158,7 +157,6 @@ void __init config_mac(void)
 	mach_get_model = mac_get_model;
 	arch_gettimeoffset = mac_gettimeoffset;
 	mach_hwclk = mac_hwclk;
-	mach_set_clock_mmss = mac_set_clock_mmss;
 	mach_reset = mac_reset;
 	mach_halt = mac_poweroff;
 	mach_power_off = mac_poweroff;
@@ -709,7 +707,7 @@ static struct mac_model mac_data_table[] = {
 		.name		= "PowerBook 520",
 		.adb_type	= MAC_ADB_PB2,
 		.via_type	= MAC_VIA_QUADRA,
-		.scsi_type	= MAC_SCSI_LATE,
+		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
@@ -943,18 +941,6 @@ static const struct resource mac_scsi_old_rsrc[] __initconst = {
 	},
 };
 
-static const struct resource mac_scsi_late_rsrc[] __initconst = {
-	{
-		.flags = IORESOURCE_IRQ,
-		.start = IRQ_MAC_SCSI,
-		.end   = IRQ_MAC_SCSI,
-	}, {
-		.flags = IORESOURCE_MEM,
-		.start = 0x50010000,
-		.end   = 0x50011FFF,
-	},
-};
-
 static const struct resource mac_scsi_ccl_rsrc[] __initconst = {
 	{
 		.flags = IORESOURCE_IRQ,
@@ -1064,11 +1050,6 @@ int __init mac_platform_init(void)
 		platform_device_register_simple("mac_scsi", 0,
 			mac_scsi_old_rsrc, ARRAY_SIZE(mac_scsi_old_rsrc));
 		break;
-	case MAC_SCSI_LATE:
-		/* XXX PDMA support for PowerBook 500 series needs testing */
-		platform_device_register_simple("mac_scsi", 0,
-			mac_scsi_late_rsrc, ARRAY_SIZE(mac_scsi_late_rsrc));
-		break;
 	case MAC_SCSI_LC:
 		/* Addresses from Mac LC data in Designing Cards & Drivers 3ed.
 		 * Also from the Developer Notes for Classic II, LC III,
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index c68054361615..19e9d8eef1f2 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -26,33 +26,38 @@
 
 #include <asm/machdep.h>
 
-/* Offset between Unix time (1970-based) and Mac time (1904-based) */
+/*
+ * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU
+ * times wrap in 2040. If we need to handle later times, the read_time functions
+ * need to be changed to interpret wrapped times as post-2040.
+ */
 
 #define RTC_OFFSET 2082844800
 
 static void (*rom_reset)(void);
 
 #ifdef CONFIG_ADB_CUDA
-static long cuda_read_time(void)
+static time64_t cuda_read_time(void)
 {
 	struct adb_request req;
-	long time;
+	time64_t time;
 
 	if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0)
 		return 0;
 	while (!req.complete)
 		cuda_poll();
 
-	time = (req.reply[3] << 24) | (req.reply[4] << 16) |
-	       (req.reply[5] << 8) | req.reply[6];
+	time = (u32)((req.reply[3] << 24) | (req.reply[4] << 16) |
+		     (req.reply[5] << 8) | req.reply[6]);
+
 	return time - RTC_OFFSET;
 }
 
-static void cuda_write_time(long data)
+static void cuda_write_time(time64_t time)
 {
 	struct adb_request req;
+	u32 data = lower_32_bits(time + RTC_OFFSET);
 
-	data += RTC_OFFSET;
 	if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME,
 			 (data >> 24) & 0xFF, (data >> 16) & 0xFF,
 			 (data >> 8) & 0xFF, data & 0xFF) < 0)
@@ -86,26 +91,27 @@ static void cuda_write_pram(int offset, __u8 data)
 #endif /* CONFIG_ADB_CUDA */
 
 #ifdef CONFIG_ADB_PMU68K
-static long pmu_read_time(void)
+static time64_t pmu_read_time(void)
 {
 	struct adb_request req;
-	long time;
+	time64_t time;
 
 	if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
 		return 0;
 	while (!req.complete)
 		pmu_poll();
 
-	time = (req.reply[1] << 24) | (req.reply[2] << 16) |
-	       (req.reply[3] << 8) | req.reply[4];
+	time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) |
+		     (req.reply[3] << 8) | req.reply[4]);
+
 	return time - RTC_OFFSET;
 }
 
-static void pmu_write_time(long data)
+static void pmu_write_time(time64_t time)
 {
 	struct adb_request req;
+	u32 data = lower_32_bits(time + RTC_OFFSET);
 
-	data += RTC_OFFSET;
 	if (pmu_request(&req, NULL, 5, PMU_SET_RTC,
 			(data >> 24) & 0xFF, (data >> 16) & 0xFF,
 			(data >> 8) & 0xFF, data & 0xFF) < 0)
@@ -245,11 +251,11 @@ static void via_write_pram(int offset, __u8 data)
  * is basically any machine with Mac II-style ADB.
  */
 
-static long via_read_time(void)
+static time64_t via_read_time(void)
 {
 	union {
 		__u8 cdata[4];
-		long idata;
+		__u32 idata;
 	} result, last_result;
 	int count = 1;
 
@@ -270,7 +276,7 @@ static long via_read_time(void)
 		via_pram_command(0x8D, &result.cdata[0]);
 
 		if (result.idata == last_result.idata)
-			return result.idata - RTC_OFFSET;
+			return (time64_t)result.idata - RTC_OFFSET;
 
 		if (++count > 10)
 			break;
@@ -278,8 +284,8 @@ static long via_read_time(void)
 		last_result.idata = result.idata;
 	}
 
-	pr_err("via_read_time: failed to read a stable value; got 0x%08lx then 0x%08lx\n",
-	       last_result.idata, result.idata);
+	pr_err("%s: failed to read a stable value; got 0x%08x then 0x%08x\n",
+	       __func__, last_result.idata, result.idata);
 
 	return 0;
 }
@@ -291,11 +297,11 @@ static long via_read_time(void)
  * is basically any machine with Mac II-style ADB.
  */
 
-static void via_write_time(long time)
+static void via_write_time(time64_t time)
 {
 	union {
 		__u8 cdata[4];
-		long idata;
+		__u32 idata;
 	} data;
 	__u8 temp;
 
@@ -304,7 +310,7 @@ static void via_write_time(long time)
 	temp = 0x55;
 	via_pram_command(0x35, &temp);
 
-	data.idata = time + RTC_OFFSET;
+	data.idata = lower_32_bits(time + RTC_OFFSET);
 	via_pram_command(0x01, &data.cdata[3]);
 	via_pram_command(0x05, &data.cdata[2]);
 	via_pram_command(0x09, &data.cdata[1]);
@@ -585,12 +591,15 @@ void mac_reset(void)
  * This function translates seconds since 1970 into a proper date.
  *
  * Algorithm cribbed from glibc2.1, __offtime().
+ *
+ * This is roughly same as rtc_time64_to_tm(), which we should probably
+ * use here, but it's only available when CONFIG_RTC_LIB is enabled.
  */
 #define SECS_PER_MINUTE (60)
 #define SECS_PER_HOUR  (SECS_PER_MINUTE * 60)
 #define SECS_PER_DAY   (SECS_PER_HOUR * 24)
 
-static void unmktime(unsigned long time, long offset,
+static void unmktime(time64_t time, long offset,
 		     int *yearp, int *monp, int *dayp,
 		     int *hourp, int *minp, int *secp)
 {
@@ -602,11 +611,10 @@ static void unmktime(unsigned long time, long offset,
 		/* Leap years.  */
 		{ 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 }
 	};
-	long int days, rem, y, wday, yday;
+	int days, rem, y, wday, yday;
 	const unsigned short int *ip;
 
-	days = time / SECS_PER_DAY;
-	rem = time % SECS_PER_DAY;
+	days = div_u64_rem(time, SECS_PER_DAY, &rem);
 	rem += offset;
 	while (rem < 0) {
 		rem += SECS_PER_DAY;
@@ -657,7 +665,7 @@ static void unmktime(unsigned long time, long offset,
 
 int mac_hwclk(int op, struct rtc_time *t)
 {
-	unsigned long now;
+	time64_t now;
 
 	if (!op) { /* read */
 		switch (macintosh_config->adb_type) {
@@ -693,8 +701,8 @@ int mac_hwclk(int op, struct rtc_time *t)
 		         __func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
 		         t->tm_hour, t->tm_min, t->tm_sec);
 
-		now = mktime(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
-			     t->tm_hour, t->tm_min, t->tm_sec);
+		now = mktime64(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
+			       t->tm_hour, t->tm_min, t->tm_sec);
 
 		switch (macintosh_config->adb_type) {
 		case MAC_ADB_IOP:
@@ -719,19 +727,3 @@ int mac_hwclk(int op, struct rtc_time *t)
 	}
 	return 0;
 }
-
-/*
- * Set minutes/seconds in the hardware clock
- */
-
-int mac_set_clock_mmss (unsigned long nowtime)
-{
-	struct rtc_time now;
-
-	mac_hwclk(0, &now);
-	now.tm_sec = nowtime % 60;
-	now.tm_min = (nowtime / 60) % 60;
-	mac_hwclk(1, &now);
-
-	return 0;
-}
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 8827b7f91402..38e2b272c220 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -71,7 +71,6 @@ void __init m68k_setup_node(int node)
 		pg_data_table[i] = pg_data_map + node;
 	}
 #endif
-	pg_data_map[node].bdata = bootmem_node_data + node;
 	node_set_online(node);
 }
 
diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c
index 2925d795d71a..70dde040779b 100644
--- a/arch/m68k/mm/mcfmmu.c
+++ b/arch/m68k/mm/mcfmmu.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>
@@ -153,31 +154,31 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word)
 
 void __init cf_bootmem_alloc(void)
 {
-	unsigned long start_pfn;
 	unsigned long memstart;
 
 	/* _rambase and _ramend will be naturally page aligned */
 	m68k_memory[0].addr = _rambase;
 	m68k_memory[0].size = _ramend - _rambase;
 
+	memblock_add(m68k_memory[0].addr, m68k_memory[0].size);
+
 	/* compute total pages in system */
 	num_pages = PFN_DOWN(_ramend - _rambase);
 
 	/* page numbers */
 	memstart = PAGE_ALIGN(_ramstart);
 	min_low_pfn = PFN_DOWN(_rambase);
-	start_pfn = PFN_DOWN(memstart);
 	max_pfn = max_low_pfn = PFN_DOWN(_ramend);
 	high_memory = (void *)_ramend;
 
+	/* Reserve kernel text/data/bss */
+	memblock_reserve(memstart, memstart - _rambase);
+
 	m68k_virt_to_node_shift = fls(_ramend - 1) - 6;
 	module_fixup(NULL, __start_fixup, __stop_fixup);
 
-	/* setup bootmem data */
+	/* setup node data */
 	m68k_setup_node(0);
-	memstart += init_bootmem_node(NODE_DATA(0), start_pfn,
-		min_low_pfn, max_low_pfn);
-	free_bootmem_node(NODE_DATA(0), memstart, _ramend - memstart);
 }
 
 /*
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index e490ecc7842c..4e17ecb5928a 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/gfp.h>
 
 #include <asm/setup.h>
@@ -208,7 +209,7 @@ void __init paging_init(void)
 {
 	unsigned long zones_size[MAX_NR_ZONES] = { 0, };
 	unsigned long min_addr, max_addr;
-	unsigned long addr, size, end;
+	unsigned long addr;
 	int i;
 
 #ifdef DEBUG
@@ -253,34 +254,20 @@ void __init paging_init(void)
 	min_low_pfn = availmem >> PAGE_SHIFT;
 	max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT;
 
-	for (i = 0; i < m68k_num_memory; i++) {
-		addr = m68k_memory[i].addr;
-		end = addr + m68k_memory[i].size;
-		m68k_setup_node(i);
-		availmem = PAGE_ALIGN(availmem);
-		availmem += init_bootmem_node(NODE_DATA(i),
-					      availmem >> PAGE_SHIFT,
-					      addr >> PAGE_SHIFT,
-					      end >> PAGE_SHIFT);
-	}
+	/* Reserve kernel text/data/bss and the memory allocated in head.S */
+	memblock_reserve(m68k_memory[0].addr, availmem - m68k_memory[0].addr);
 
 	/*
 	 * Map the physical memory available into the kernel virtual
-	 * address space. First initialize the bootmem allocator with
-	 * the memory we already mapped, so map_node() has something
-	 * to allocate.
+	 * address space. Make sure memblock will not try to allocate
+	 * pages beyond the memory we already mapped in head.S
 	 */
-	addr = m68k_memory[0].addr;
-	size = m68k_memory[0].size;
-	free_bootmem_node(NODE_DATA(0), availmem,
-			  min(m68k_init_mapped_size, size) - (availmem - addr));
-	map_node(0);
-	if (size > m68k_init_mapped_size)
-		free_bootmem_node(NODE_DATA(0), addr + m68k_init_mapped_size,
-				  size - m68k_init_mapped_size);
-
-	for (i = 1; i < m68k_num_memory; i++)
+	memblock_set_bottom_up(true);
+
+	for (i = 0; i < m68k_num_memory; i++) {
+		m68k_setup_node(i);
 		map_node(i);
+	}
 
 	flush_tlb_all();
 
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index f8a710fd84cd..adea549d240e 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -40,7 +40,6 @@ static void mvme147_get_model(char *model);
 extern void mvme147_sched_init(irq_handler_t handler);
 extern u32 mvme147_gettimeoffset(void);
 extern int mvme147_hwclk (int, struct rtc_time *);
-extern int mvme147_set_clock_mmss (unsigned long);
 extern void mvme147_reset (void);
 
 
@@ -92,7 +91,6 @@ void __init config_mvme147(void)
 	mach_init_IRQ		= mvme147_init_IRQ;
 	arch_gettimeoffset	= mvme147_gettimeoffset;
 	mach_hwclk		= mvme147_hwclk;
-	mach_set_clock_mmss	= mvme147_set_clock_mmss;
 	mach_reset		= mvme147_reset;
 	mach_get_model		= mvme147_get_model;
 
@@ -164,8 +162,3 @@ int mvme147_hwclk(int op, struct rtc_time *t)
 	}
 	return 0;
 }
-
-int mvme147_set_clock_mmss (unsigned long nowtime)
-{
-	return 0;
-}
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 4ffd9ef98de4..6ee36a5b528d 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -46,7 +46,6 @@ static void mvme16x_get_model(char *model);
 extern void mvme16x_sched_init(irq_handler_t handler);
 extern u32 mvme16x_gettimeoffset(void);
 extern int mvme16x_hwclk (int, struct rtc_time *);
-extern int mvme16x_set_clock_mmss (unsigned long);
 extern void mvme16x_reset (void);
 
 int bcd2int (unsigned char b);
@@ -280,7 +279,6 @@ void __init config_mvme16x(void)
     mach_init_IRQ        = mvme16x_init_IRQ;
     arch_gettimeoffset   = mvme16x_gettimeoffset;
     mach_hwclk           = mvme16x_hwclk;
-    mach_set_clock_mmss	 = mvme16x_set_clock_mmss;
     mach_reset		 = mvme16x_reset;
     mach_get_model       = mvme16x_get_model;
     mach_get_hardware_list = mvme16x_get_hardware_list;
@@ -411,9 +409,3 @@ int mvme16x_hwclk(int op, struct rtc_time *t)
 	}
 	return 0;
 }
-
-int mvme16x_set_clock_mmss (unsigned long nowtime)
-{
-	return 0;
-}
-
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 71c0867ecf20..96810d91da2b 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -43,7 +43,6 @@ extern void q40_sched_init(irq_handler_t handler);
 static u32 q40_gettimeoffset(void);
 static int q40_hwclk(int, struct rtc_time *);
 static unsigned int q40_get_ss(void);
-static int q40_set_clock_mmss(unsigned long);
 static int q40_get_rtc_pll(struct rtc_pll_info *pll);
 static int q40_set_rtc_pll(struct rtc_pll_info *pll);
 
@@ -175,7 +174,6 @@ void __init config_q40(void)
 	mach_get_ss = q40_get_ss;
 	mach_get_rtc_pll = q40_get_rtc_pll;
 	mach_set_rtc_pll = q40_set_rtc_pll;
-	mach_set_clock_mmss = q40_set_clock_mmss;
 
 	mach_reset = q40_reset;
 	mach_get_model = q40_get_model;
@@ -267,34 +265,6 @@ static unsigned int q40_get_ss(void)
 	return bcd2bin(Q40_RTC_SECS);
 }
 
-/*
- * Set the minutes and seconds from seconds value 'nowtime'.  Fail if
- * clock is out by > 30 minutes.  Logic lifted from atari code.
- */
-
-static int q40_set_clock_mmss(unsigned long nowtime)
-{
-	int retval = 0;
-	short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-
-	int rtc_minutes;
-
-	rtc_minutes = bcd2bin(Q40_RTC_MINS);
-
-	if ((rtc_minutes < real_minutes ?
-	     real_minutes - rtc_minutes :
-	     rtc_minutes - real_minutes) < 30) {
-		Q40_RTC_CTRL |= Q40_RTC_WRITE;
-		Q40_RTC_MINS = bin2bcd(real_minutes);
-		Q40_RTC_SECS = bin2bcd(real_seconds);
-		Q40_RTC_CTRL &= ~(Q40_RTC_WRITE);
-	} else
-		retval = -1;
-
-	return retval;
-}
-
-
 /* get and set PLL calibration of RTC clock */
 #define Q40_RTC_PLL_MASK ((1<<5)-1)
 #define Q40_RTC_PLL_SIGN (1<<5)
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index 1d28d380e8cc..79a2bb857906 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -123,10 +123,6 @@ static void __init sun3_bootmem_alloc(unsigned long memory_start,
 	availmem = memory_start;
 
 	m68k_setup_node(0);
-	availmem += init_bootmem(start_page, num_pages);
-	availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK;
-
-	free_bootmem(__pa(availmem), memory_end - (availmem));
 }
 
 
diff --git a/arch/microblaze/Kconfig.debug b/arch/microblaze/Kconfig.debug
index 331a3bb66297..93a737c8d1a6 100644
--- a/arch/microblaze/Kconfig.debug
+++ b/arch/microblaze/Kconfig.debug
@@ -8,11 +8,4 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
-config HEART_BEAT
-	bool "Heart beat function for kernel"
-	default n
-	help
-	  This option turns on/off heart beat kernel functionality.
-	  First GPIO node is taken.
-
 endmenu
diff --git a/arch/microblaze/include/asm/setup.h b/arch/microblaze/include/asm/setup.h
index d5384f6f36f7..ce9b7b786156 100644
--- a/arch/microblaze/include/asm/setup.h
+++ b/arch/microblaze/include/asm/setup.h
@@ -19,15 +19,10 @@ extern char cmd_line[COMMAND_LINE_SIZE];
 
 extern char *klimit;
 
-void microblaze_heartbeat(void);
-void microblaze_setup_heartbeat(void);
-
 #   ifdef CONFIG_MMU
 extern void mmu_reset(void);
 #   endif /* CONFIG_MMU */
 
-extern void of_platform_reset_gpio_probe(void);
-
 void time_init(void);
 void init_IRQ(void);
 void machine_early_init(const char *cmdline, unsigned int ram,
diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h
index 9774e1d9507b..a62d09420a47 100644
--- a/arch/microblaze/include/asm/unistd.h
+++ b/arch/microblaze/include/asm/unistd.h
@@ -38,6 +38,6 @@
 
 #endif /* __ASSEMBLY__ */
 
-#define __NR_syscalls         399
+#define __NR_syscalls         401
 
 #endif /* _ASM_MICROBLAZE_UNISTD_H */
diff --git a/arch/microblaze/include/uapi/asm/unistd.h b/arch/microblaze/include/uapi/asm/unistd.h
index eb156f914793..7a9f16a76413 100644
--- a/arch/microblaze/include/uapi/asm/unistd.h
+++ b/arch/microblaze/include/uapi/asm/unistd.h
@@ -415,5 +415,7 @@
 #define __NR_pkey_alloc		396
 #define __NR_pkey_free		397
 #define __NR_statx		398
+#define __NR_io_pgetevents	399
+#define __NR_rseq		400
 
 #endif /* _UAPI_ASM_MICROBLAZE_UNISTD_H */
diff --git a/arch/microblaze/kernel/Makefile b/arch/microblaze/kernel/Makefile
index 7e99cf6984a1..dd71637437f4 100644
--- a/arch/microblaze/kernel/Makefile
+++ b/arch/microblaze/kernel/Makefile
@@ -8,7 +8,6 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_timer.o = -pg
 CFLAGS_REMOVE_intc.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
-CFLAGS_REMOVE_heartbeat.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_process.o = -pg
 endif
@@ -17,12 +16,11 @@ extra-y := head.o vmlinux.lds
 
 obj-y += dma.o exceptions.o \
 	hw_exception_handler.o irq.o \
-	platform.o process.o prom.o ptrace.o \
+	process.o prom.o ptrace.o \
 	reset.o setup.o signal.o sys_microblaze.o timer.o traps.o unwind.o
 
 obj-y += cpu/
 
-obj-$(CONFIG_HEART_BEAT)	+= heartbeat.o
 obj-$(CONFIG_MODULES)		+= microblaze_ksyms.o module.o
 obj-$(CONFIG_MMU)		+= misc.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
diff --git a/arch/microblaze/kernel/heartbeat.c b/arch/microblaze/kernel/heartbeat.c
deleted file mode 100644
index 2022130139d2..000000000000
--- a/arch/microblaze/kernel/heartbeat.c
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu>
- * Copyright (C) 2007-2009 PetaLogix
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#include <linux/sched.h>
-#include <linux/sched/loadavg.h>
-#include <linux/io.h>
-
-#include <asm/setup.h>
-#include <asm/page.h>
-#include <asm/prom.h>
-
-static unsigned int base_addr;
-
-void microblaze_heartbeat(void)
-{
-	static unsigned int cnt, period, dist;
-
-	if (base_addr) {
-		if (cnt == 0 || cnt == dist)
-			out_be32(base_addr, 1);
-		else if (cnt == 7 || cnt == dist + 7)
-			out_be32(base_addr, 0);
-
-		if (++cnt > period) {
-			cnt = 0;
-			/*
-			 * The hyperbolic function below modifies the heartbeat
-			 * period length in dependency of the current (5min)
-			 * load. It goes through the points f(0)=126, f(1)=86,
-			 * f(5)=51, f(inf)->30.
-			 */
-			period = ((672 << FSHIFT) / (5 * avenrun[0] +
-						(7 << FSHIFT))) + 30;
-			dist = period / 4;
-		}
-	}
-}
-
-void microblaze_setup_heartbeat(void)
-{
-	struct device_node *gpio = NULL;
-	int *prop;
-	int j;
-	const char * const gpio_list[] = {
-		"xlnx,xps-gpio-1.00.a",
-		NULL
-	};
-
-	for (j = 0; gpio_list[j] != NULL; j++) {
-		gpio = of_find_compatible_node(NULL, NULL, gpio_list[j]);
-		if (gpio)
-			break;
-	}
-
-	if (gpio) {
-		base_addr = be32_to_cpup(of_get_property(gpio, "reg", NULL));
-		base_addr = (unsigned long) ioremap(base_addr, PAGE_SIZE);
-		pr_notice("Heartbeat GPIO at 0x%x\n", base_addr);
-
-		/* GPIO is configured as output */
-		prop = (int *) of_get_property(gpio, "xlnx,is-bidir", NULL);
-		if (prop)
-			out_be32(base_addr + 4, 0);
-	}
-}
diff --git a/arch/microblaze/kernel/platform.c b/arch/microblaze/kernel/platform.c
deleted file mode 100644
index 2540d60610d9..000000000000
--- a/arch/microblaze/kernel/platform.c
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Copyright 2008 Michal Simek <monstr@monstr.eu>
- *
- * based on virtex.c file
- *
- * Copyright 2007 Secret Lab Technologies Ltd.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#include <linux/init.h>
-#include <linux/of_platform.h>
-#include <asm/setup.h>
-
-static struct of_device_id xilinx_of_bus_ids[] __initdata = {
-	{ .compatible = "simple-bus", },
-	{ .compatible = "xlnx,compound", },
-	{}
-};
-
-static int __init microblaze_device_probe(void)
-{
-	of_platform_bus_probe(NULL, xilinx_of_bus_ids, NULL);
-	of_platform_reset_gpio_probe();
-	return 0;
-}
-device_initcall(microblaze_device_probe);
diff --git a/arch/microblaze/kernel/reset.c b/arch/microblaze/kernel/reset.c
index bab4c8330ef4..fcbe1daf6316 100644
--- a/arch/microblaze/kernel/reset.c
+++ b/arch/microblaze/kernel/reset.c
@@ -18,7 +18,7 @@
 static int handle; /* reset pin handle */
 static unsigned int reset_val;
 
-void of_platform_reset_gpio_probe(void)
+static int of_platform_reset_gpio_probe(void)
 {
 	int ret;
 	handle = of_get_named_gpio(of_find_node_by_path("/"),
@@ -27,13 +27,13 @@ void of_platform_reset_gpio_probe(void)
 	if (!gpio_is_valid(handle)) {
 		pr_info("Skipping unavailable RESET gpio %d (%s)\n",
 				handle, "reset");
-		return;
+		return -ENODEV;
 	}
 
 	ret = gpio_request(handle, "reset");
 	if (ret < 0) {
 		pr_info("GPIO pin is already allocated\n");
-		return;
+		return ret;
 	}
 
 	/* get current setup value */
@@ -51,11 +51,12 @@ void of_platform_reset_gpio_probe(void)
 
 	pr_info("RESET: Registered gpio device: %d, current val: %d\n",
 							handle, reset_val);
-	return;
+	return 0;
 err:
 	gpio_free(handle);
-	return;
+	return ret;
 }
+device_initcall(of_platform_reset_gpio_probe);
 
 
 static void gpio_system_reset(void)
diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S
index 56bcf313121f..6ab650593792 100644
--- a/arch/microblaze/kernel/syscall_table.S
+++ b/arch/microblaze/kernel/syscall_table.S
@@ -400,3 +400,5 @@ ENTRY(sys_call_table)
 	.long sys_pkey_alloc
 	.long sys_pkey_free
 	.long sys_statx
+	.long sys_io_pgetevents
+	.long sys_rseq
diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c
index 7de941cbbd94..a6683484b3a1 100644
--- a/arch/microblaze/kernel/timer.c
+++ b/arch/microblaze/kernel/timer.c
@@ -156,9 +156,6 @@ static inline void timer_ack(void)
 static irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *evt = &clockevent_xilinx_timer;
-#ifdef CONFIG_HEART_BEAT
-	microblaze_heartbeat();
-#endif
 	timer_ack();
 	evt->event_handler(evt);
 	return IRQ_HANDLED;
@@ -318,10 +315,6 @@ static int __init xilinx_timer_init(struct device_node *timer)
 		return ret;
 	}
 
-#ifdef CONFIG_HEART_BEAT
-	microblaze_setup_heartbeat();
-#endif
-
 	ret = xilinx_clocksource_init();
 	if (ret)
 		return ret;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 08c10c518f83..642a56e2a1ea 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -16,6 +16,7 @@ config MIPS
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select CPU_PM if CPU_IDLE
+	select DMA_DIRECT_OPS
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CMOS_UPDATE
@@ -97,6 +98,7 @@ config MIPS_GENERIC
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
 	select LIBFDT
+	select MIPS_AUTO_PFN_OFFSET
 	select MIPS_CPU_SCACHE
 	select MIPS_GIC
 	select MIPS_L1_CACHE_SHIFT_7
@@ -193,6 +195,7 @@ config ATH79
 	select CSRC_R4K
 	select DMA_NONCOHERENT
 	select GPIOLIB
+	select PINCTRL
 	select HAVE_CLK
 	select COMMON_CLK
 	select CLKDEV_LOOKUP
@@ -211,6 +214,8 @@ config ATH79
 
 config BMIPS_GENERIC
 	bool "Broadcom Generic BMIPS kernel"
+	select ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+	select ARCH_HAS_PHYS_TO_DMA
 	select BOOT_RAW
 	select NO_EXCEPT_FILL
 	select USE_OF
@@ -438,7 +443,6 @@ config MACH_LOONGSON32
 
 config MACH_LOONGSON64
 	bool "Loongson-2/3 family of machines"
-	select ARCH_HAS_PHYS_TO_DMA
 	select SYS_SUPPORTS_ZBOOT
 	help
 	  This enables the support of Loongson-2/3 family of machines.
@@ -662,11 +666,11 @@ config SGI_IP22
 
 config SGI_IP27
 	bool "SGI IP27 (Origin200/2000)"
+	select ARCH_HAS_PHYS_TO_DMA
 	select FW_ARC
 	select FW_ARC64
 	select BOOT_ELF64
 	select DEFAULT_SGI_PARTITION
-	select DMA_COHERENT
 	select SYS_HAS_EARLY_PRINTK
 	select HW_HAS_PCI
 	select NR_CPUS_DEFAULT_64
@@ -721,6 +725,7 @@ config SGI_IP28
 
 config SGI_IP32
 	bool "SGI IP32 (O2)"
+	select ARCH_HAS_PHYS_TO_DMA
 	select FW_ARC
 	select FW_ARC32
 	select BOOT_ELF32
@@ -743,7 +748,6 @@ config SGI_IP32
 config SIBYTE_CRHINE
 	bool "Sibyte BCM91120C-CRhine"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -753,7 +757,6 @@ config SIBYTE_CRHINE
 config SIBYTE_CARMEL
 	bool "Sibyte BCM91120x-Carmel"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -763,7 +766,6 @@ config SIBYTE_CARMEL
 config SIBYTE_CRHONE
 	bool "Sibyte BCM91125C-CRhone"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1125
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -774,7 +776,6 @@ config SIBYTE_CRHONE
 config SIBYTE_RHONE
 	bool "Sibyte BCM91125E-Rhone"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1125H
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -784,7 +785,6 @@ config SIBYTE_RHONE
 config SIBYTE_SWARM
 	bool "Sibyte BCM91250A-SWARM"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select HAVE_PATA_PLATFORM
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -797,7 +797,6 @@ config SIBYTE_SWARM
 config SIBYTE_LITTLESUR
 	bool "Sibyte BCM91250C2-LittleSur"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select HAVE_PATA_PLATFORM
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -809,7 +808,6 @@ config SIBYTE_LITTLESUR
 config SIBYTE_SENTOSA
 	bool "Sibyte BCM91250E-Sentosa"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -819,7 +817,6 @@ config SIBYTE_SENTOSA
 config SIBYTE_BIGSUR
 	bool "Sibyte BCM91480B-BigSur"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select NR_CPUS_DEFAULT_4
 	select SIBYTE_BCM1x80
 	select SWAP_IO_SPACE
@@ -895,8 +892,8 @@ config CAVIUM_OCTEON_SOC
 	bool "Cavium Networks Octeon SoC based boards"
 	select CEVT_R4K
 	select ARCH_HAS_PHYS_TO_DMA
+	select HAS_RAPIDIO
 	select PHYS_ADDR_T_64BIT
-	select DMA_COHERENT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select EDAC_SUPPORT
@@ -945,7 +942,6 @@ config NLM_XLR_BOARD
 	select PHYS_ADDR_T_64BIT
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
-	select DMA_COHERENT
 	select NR_CPUS_DEFAULT_32
 	select CEVT_R4K
 	select CSRC_R4K
@@ -973,7 +969,6 @@ config NLM_XLP_BOARD
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
-	select DMA_COHERENT
 	select NR_CPUS_DEFAULT_32
 	select CEVT_R4K
 	select CSRC_R4K
@@ -992,7 +987,6 @@ config MIPS_PARAVIRT
 	bool "Para-Virtualized guest system"
 	select CEVT_R4K
 	select CSRC_R4K
-	select DMA_COHERENT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
@@ -1118,12 +1112,14 @@ config DMA_PERDEV_COHERENT
 	bool
 	select DMA_MAYBE_COHERENT
 
-config DMA_COHERENT
-	bool
-
 config DMA_NONCOHERENT
 	bool
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select NEED_DMA_MAP_STATE
+	select DMA_NONCOHERENT_MMAP
+	select DMA_NONCOHERENT_CACHE_SYNC
+	select DMA_NONCOHERENT_OPS
 
 config SYS_HAS_EARLY_PRINTK
 	bool
@@ -1365,6 +1361,7 @@ choice
 config CPU_LOONGSON3
 	bool "Loongson 3 CPU"
 	depends on SYS_HAS_CPU_LOONGSON3
+	select ARCH_HAS_PHYS_TO_DMA
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
@@ -1427,7 +1424,8 @@ config CPU_LOONGSON1B
 	select LEDS_GPIO_REGISTER
 	help
 	  The Loongson 1B is a 32-bit SoC, which implements the MIPS32
-	  release 2 instruction set.
+	  Release 1 instruction set and part of the MIPS32 Release 2
+	  instruction set.
 
 config CPU_LOONGSON1C
 	bool "Loongson 1C"
@@ -1436,7 +1434,8 @@ config CPU_LOONGSON1C
 	select LEDS_GPIO_REGISTER
 	help
 	  The Loongson 1C is a 32-bit SoC, which implements the MIPS32
-	  release 2 instruction set.
+	  Release 1 instruction set and part of the MIPS32 Release 2
+	  instruction set.
 
 config CPU_MIPS32_R1
 	bool "MIPS32 Release 1"
@@ -1831,11 +1830,12 @@ config CPU_LOONGSON2
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
+	select ARCH_HAS_PHYS_TO_DMA
 
 config CPU_LOONGSON1
 	bool
 	select CPU_MIPS32
-	select CPU_MIPSR2
+	select CPU_MIPSR1
 	select CPU_HAS_PREFETCH
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1979,12 +1979,6 @@ config SYS_HAS_CPU_XLR
 config SYS_HAS_CPU_XLP
 	bool
 
-config MIPS_MALTA_PM
-	depends on MIPS_MALTA
-	depends on PCI
-	bool
-	default y
-
 #
 # CPU may reorder R->R, R->W, W->R, W->W
 # Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC
@@ -2994,6 +2988,9 @@ config PGTABLE_LEVELS
 	default 3 if 64BIT && !PAGE_SIZE_64KB
 	default 2
 
+config MIPS_AUTO_PFN_OFFSET
+	bool
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
@@ -3115,10 +3112,13 @@ config ZONE_DMA32
 
 source "drivers/pcmcia/Kconfig"
 
+config HAS_RAPIDIO
+	bool
+	default n
+
 config RAPIDIO
 	tristate "RapidIO support"
-	depends on PCI
-	default n
+	depends on HAS_RAPIDIO || PCI
 	help
 	  If you say Y here, the kernel will include drivers and
 	  infrastructure code to support RapidIO interconnect devices.
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index e2122cca4ae2..5425df002a6b 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -122,12 +122,22 @@ cflags-y += -ffreestanding
 # are used, so we kludge that here.  A bug has been filed at
 # http://gcc.gnu.org/bugzilla/show_bug.cgi?id=29413.
 #
+# clang doesn't suffer from these issues and our checks against -dumpmachine
+# don't work so well when cross compiling, since without providing --target
+# clang's output will be based upon the build machine. So for clang we simply
+# unconditionally specify -EB or -EL as appropriate.
+#
+ifeq ($(cc-name),clang)
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -EB
+cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -EL
+else
 undef-all += -UMIPSEB -U_MIPSEB -U__MIPSEB -U__MIPSEB__
 undef-all += -UMIPSEL -U_MIPSEL -U__MIPSEL -U__MIPSEL__
 predef-be += -DMIPSEB -D_MIPSEB -D__MIPSEB -D__MIPSEB__
 predef-le += -DMIPSEL -D_MIPSEL -D__MIPSEL -D__MIPSEL__
 cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' && echo -EB $(undef-all) $(predef-be))
 cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' || echo -EL $(undef-all) $(predef-le))
+endif
 
 cflags-$(CONFIG_SB1XXX_CORELIS)	+= $(call cc-option,-mno-sched-prolog) \
 				   -fno-omit-frame-pointer
@@ -155,15 +165,11 @@ cflags-$(CONFIG_CPU_R4300)	+= -march=r4300 -Wa,--trap
 cflags-$(CONFIG_CPU_VR41XX)	+= -march=r4100 -Wa,--trap
 cflags-$(CONFIG_CPU_R4X00)	+= -march=r4600 -Wa,--trap
 cflags-$(CONFIG_CPU_TX49XX)	+= -march=r4600 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS32_R1)	+= $(call cc-option,-march=mips32,-mips32 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
-			-Wa,-mips32 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS32_R2)	+= $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
-			-Wa,-mips32r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS32_R1)	+= -march=mips32 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS32_R2)	+= -march=mips32r2 -Wa,--trap
 cflags-$(CONFIG_CPU_MIPS32_R6)	+= -march=mips32r6 -Wa,--trap -modd-spreg
-cflags-$(CONFIG_CPU_MIPS64_R1)	+= $(call cc-option,-march=mips64,-mips64 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
-			-Wa,-mips64 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS64_R2)	+= $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
-			-Wa,-mips64r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS64_R1)	+= -march=mips64 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS64_R2)	+= -march=mips64r2 -Wa,--trap
 cflags-$(CONFIG_CPU_MIPS64_R6)	+= -march=mips64r6 -Wa,--trap
 cflags-$(CONFIG_CPU_R5000)	+= -march=r5000 -Wa,--trap
 cflags-$(CONFIG_CPU_R5432)	+= $(call cc-option,-march=r5400,-march=r5000) \
diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c
index fa75d75b5ba9..ddff9a02513d 100644
--- a/arch/mips/alchemy/board-gpr.c
+++ b/arch/mips/alchemy/board-gpr.c
@@ -34,6 +34,7 @@
 #include <asm/bootinfo.h>
 #include <asm/idle.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/gpio-au1000.h>
 #include <prom.h>
@@ -60,7 +61,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index aab55aaf3d62..d625e6f99ae7 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -31,6 +31,7 @@
 #include <mtd/mtd-abi.h>
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/gpio-au1000.h>
 #include <asm/mach-au1x00/au1xxx_eth.h>
@@ -58,7 +59,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c
index 0fc53e08a894..5f05b8714385 100644
--- a/arch/mips/alchemy/board-xxs1500.c
+++ b/arch/mips/alchemy/board-xxs1500.c
@@ -29,6 +29,7 @@
 #include <linux/pm.h>
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <prom.h>
 
@@ -55,7 +56,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/devboards/platform.c b/arch/mips/alchemy/devboards/platform.c
index 203854ddd1bb..8d4b65c3268a 100644
--- a/arch/mips/alchemy/devboards/platform.c
+++ b/arch/mips/alchemy/devboards/platform.c
@@ -14,6 +14,7 @@
 #include <asm/bootinfo.h>
 #include <asm/idle.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-db1x00/bcsr.h>
 
@@ -36,7 +37,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	if (alchemy_get_cputype() == ALCHEMY_CPU_AU1300)
 		alchemy_uart_putchar(AU1300_UART2_PHYS_ADDR, c);
diff --git a/arch/mips/ar7/clock.c b/arch/mips/ar7/clock.c
index 0137656107a9..6b64fd96dba8 100644
--- a/arch/mips/ar7/clock.c
+++ b/arch/mips/ar7/clock.c
@@ -476,3 +476,32 @@ void __init ar7_init_clocks(void)
 	/* adjust vbus clock rate */
 	vbus_clk.rate = bus_clk.rate / 2;
 }
+
+/* dummy functions, should not be called */
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_round_rate);
+
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_rate);
+
+int clk_set_parent(struct clk *clk, struct clk *parent)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_parent);
+
+struct clk *clk_get_parent(struct clk *clk)
+{
+	WARN_ON(clk);
+	return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
diff --git a/arch/mips/ar7/prom.c b/arch/mips/ar7/prom.c
index dd53987a690f..2ec8d9ac91ec 100644
--- a/arch/mips/ar7/prom.c
+++ b/arch/mips/ar7/prom.c
@@ -25,6 +25,7 @@
 #include <linux/string.h>
 #include <linux/io.h>
 #include <asm/bootinfo.h>
+#include <asm/setup.h>
 
 #include <asm/mach-ar7/ar7.h>
 #include <asm/mach-ar7/prom.h>
@@ -259,10 +260,9 @@ static inline void serial_out(int offset, int value)
 	writel(value, (void *)PORT(offset));
 }
 
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	while ((serial_in(UART_LSR) & UART_LSR_TEMT) == 0)
 		;
 	serial_out(UART_TX, c);
-	return 1;
 }
diff --git a/arch/mips/ath25/Kconfig b/arch/mips/ath25/Kconfig
index 7070b4bcd01d..2c1dfd06c366 100644
--- a/arch/mips/ath25/Kconfig
+++ b/arch/mips/ath25/Kconfig
@@ -12,6 +12,7 @@ config SOC_AR2315
 config PCI_AR2315
 	bool "Atheros AR2315 PCI controller support"
 	depends on SOC_AR2315
+	select ARCH_HAS_PHYS_TO_DMA
 	select HW_HAS_PCI
 	select PCI
 	default y
diff --git a/arch/mips/ath25/board.c b/arch/mips/ath25/board.c
index 6d11ae581ea7..989e71015ee6 100644
--- a/arch/mips/ath25/board.c
+++ b/arch/mips/ath25/board.c
@@ -146,10 +146,10 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size)
 			pr_info("Fixing up empty mac addresses\n");
 			config->reset_config_gpio = 0xffff;
 			config->sys_led_gpio = 0xffff;
-			random_ether_addr(config->wlan0_mac);
+			eth_random_addr(config->wlan0_mac);
 			config->wlan0_mac[0] &= ~0x06;
-			random_ether_addr(config->enet0_mac);
-			random_ether_addr(config->enet1_mac);
+			eth_random_addr(config->enet0_mac);
+			eth_random_addr(config->enet1_mac);
 		}
 	}
 
diff --git a/arch/mips/ath25/early_printk.c b/arch/mips/ath25/early_printk.c
index 36035b628161..d534761e9cda 100644
--- a/arch/mips/ath25/early_printk.c
+++ b/arch/mips/ath25/early_printk.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/io.h>
 #include <linux/serial_reg.h>
+#include <asm/setup.h>
 
 #include "devices.h"
 #include "ar2315_regs.h"
@@ -25,7 +26,7 @@ static inline unsigned char prom_uart_rr(void __iomem *base, unsigned reg)
 	return __raw_readl(base + 4 * reg);
 }
 
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
 {
 	static void __iomem *base;
 
@@ -38,7 +39,7 @@ void prom_putchar(unsigned char ch)
 
 	while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0)
 		;
-	prom_uart_wr(base, UART_TX, ch);
+	prom_uart_wr(base, UART_TX, (unsigned char)ch);
 	while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0)
 		;
 }
diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c
index 6b1000b6a6a6..cf9158e3c2d9 100644
--- a/arch/mips/ath79/clock.c
+++ b/arch/mips/ath79/clock.c
@@ -355,6 +355,91 @@ static void __init ar934x_clocks_init(void)
 	iounmap(dpll_base);
 }
 
+static void __init qca953x_clocks_init(void)
+{
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
+	u32 pll, out_div, ref_div, nint, frac, clk_ctrl, postdiv;
+	u32 cpu_pll, ddr_pll;
+	u32 bootstrap;
+
+	bootstrap = ath79_reset_rr(QCA953X_RESET_REG_BOOTSTRAP);
+	if (bootstrap &	QCA953X_BOOTSTRAP_REF_CLK_40)
+		ref_rate = 40 * 1000 * 1000;
+	else
+		ref_rate = 25 * 1000 * 1000;
+
+	pll = ath79_pll_rr(QCA953X_PLL_CPU_CONFIG_REG);
+	out_div = (pll >> QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
+		  QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
+		  QCA953X_PLL_CPU_CONFIG_REFDIV_MASK;
+	nint = (pll >> QCA953X_PLL_CPU_CONFIG_NINT_SHIFT) &
+	       QCA953X_PLL_CPU_CONFIG_NINT_MASK;
+	frac = (pll >> QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT) &
+	       QCA953X_PLL_CPU_CONFIG_NFRAC_MASK;
+
+	cpu_pll = nint * ref_rate / ref_div;
+	cpu_pll += frac * (ref_rate >> 6) / ref_div;
+	cpu_pll /= (1 << out_div);
+
+	pll = ath79_pll_rr(QCA953X_PLL_DDR_CONFIG_REG);
+	out_div = (pll >> QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT) &
+		  QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT) &
+		  QCA953X_PLL_DDR_CONFIG_REFDIV_MASK;
+	nint = (pll >> QCA953X_PLL_DDR_CONFIG_NINT_SHIFT) &
+	       QCA953X_PLL_DDR_CONFIG_NINT_MASK;
+	frac = (pll >> QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT) &
+	       QCA953X_PLL_DDR_CONFIG_NFRAC_MASK;
+
+	ddr_pll = nint * ref_rate / ref_div;
+	ddr_pll += frac * (ref_rate >> 6) / (ref_div << 4);
+	ddr_pll /= (1 << out_div);
+
+	clk_ctrl = ath79_pll_rr(QCA953X_PLL_CLK_CTRL_REG);
+
+	postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) &
+		  QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
+		cpu_rate = ref_rate;
+	else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL)
+		cpu_rate = cpu_pll / (postdiv + 1);
+	else
+		cpu_rate = ddr_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
+		  QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
+		ddr_rate = ref_rate;
+	else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL)
+		ddr_rate = ddr_pll / (postdiv + 1);
+	else
+		ddr_rate = cpu_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
+		  QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
+		ahb_rate = ref_rate;
+	else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
+		ahb_rate = ddr_pll / (postdiv + 1);
+	else
+		ahb_rate = cpu_pll / (postdiv + 1);
+
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
+
+	clk_add_alias("wdt", NULL, "ref", NULL);
+	clk_add_alias("uart", NULL, "ref", NULL);
+}
+
 static void __init qca955x_clocks_init(void)
 {
 	unsigned long ref_rate;
@@ -440,6 +525,110 @@ static void __init qca955x_clocks_init(void)
 	clk_add_alias("uart", NULL, "ref", NULL);
 }
 
+static void __init qca956x_clocks_init(void)
+{
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
+	u32 pll, out_div, ref_div, nint, hfrac, lfrac, clk_ctrl, postdiv;
+	u32 cpu_pll, ddr_pll;
+	u32 bootstrap;
+
+	/*
+	 * QCA956x timer init workaround has to be applied right before setting
+	 * up the clock. Else, there will be no jiffies
+	 */
+	u32 misc;
+
+	misc = ath79_reset_rr(AR71XX_RESET_REG_MISC_INT_ENABLE);
+	misc |= MISC_INT_MIPS_SI_TIMERINT_MASK;
+	ath79_reset_wr(AR71XX_RESET_REG_MISC_INT_ENABLE, misc);
+
+	bootstrap = ath79_reset_rr(QCA956X_RESET_REG_BOOTSTRAP);
+	if (bootstrap &	QCA956X_BOOTSTRAP_REF_CLK_40)
+		ref_rate = 40 * 1000 * 1000;
+	else
+		ref_rate = 25 * 1000 * 1000;
+
+	pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG_REG);
+	out_div = (pll >> QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
+		  QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
+		  QCA956X_PLL_CPU_CONFIG_REFDIV_MASK;
+
+	pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG1_REG);
+	nint = (pll >> QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT) &
+	       QCA956X_PLL_CPU_CONFIG1_NINT_MASK;
+	hfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT) &
+	       QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK;
+	lfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT) &
+	       QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK;
+
+	cpu_pll = nint * ref_rate / ref_div;
+	cpu_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13);
+	cpu_pll += (hfrac >> 13) * ref_rate / ref_div;
+	cpu_pll /= (1 << out_div);
+
+	pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG_REG);
+	out_div = (pll >> QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT) &
+		  QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT) &
+		  QCA956X_PLL_DDR_CONFIG_REFDIV_MASK;
+	pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG1_REG);
+	nint = (pll >> QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT) &
+	       QCA956X_PLL_DDR_CONFIG1_NINT_MASK;
+	hfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT) &
+	       QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK;
+	lfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT) &
+	       QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK;
+
+	ddr_pll = nint * ref_rate / ref_div;
+	ddr_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13);
+	ddr_pll += (hfrac >> 13) * ref_rate / ref_div;
+	ddr_pll /= (1 << out_div);
+
+	clk_ctrl = ath79_pll_rr(QCA956X_PLL_CLK_CTRL_REG);
+
+	postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) &
+		  QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
+		cpu_rate = ref_rate;
+	else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL)
+		cpu_rate = ddr_pll / (postdiv + 1);
+	else
+		cpu_rate = cpu_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
+		  QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
+		ddr_rate = ref_rate;
+	else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL)
+		ddr_rate = cpu_pll / (postdiv + 1);
+	else
+		ddr_rate = ddr_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
+		  QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
+		ahb_rate = ref_rate;
+	else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
+		ahb_rate = ddr_pll / (postdiv + 1);
+	else
+		ahb_rate = cpu_pll / (postdiv + 1);
+
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
+
+	clk_add_alias("wdt", NULL, "ref", NULL);
+	clk_add_alias("uart", NULL, "ref", NULL);
+}
+
 void __init ath79_clocks_init(void)
 {
 	if (soc_is_ar71xx())
@@ -450,8 +639,12 @@ void __init ath79_clocks_init(void)
 		ar933x_clocks_init();
 	else if (soc_is_ar934x())
 		ar934x_clocks_init();
+	else if (soc_is_qca953x())
+		qca953x_clocks_init();
 	else if (soc_is_qca955x())
 		qca955x_clocks_init();
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		qca956x_clocks_init();
 	else
 		BUG();
 }
diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
index 10a405d593df..cd6055f9e7a0 100644
--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init);
 
 void ath79_ddr_wb_flush(u32 reg)
 {
-	void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg;
+	void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);
 
 	/* Flush the DDR write buffer. */
 	__raw_writel(0x1, flush_reg);
@@ -103,8 +103,12 @@ void ath79_device_reset_set(u32 mask)
 		reg = AR933X_RESET_REG_RESET_MODULE;
 	else if (soc_is_ar934x())
 		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
 	else if (soc_is_qca955x())
 		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
 	else
 		BUG();
 
@@ -131,8 +135,12 @@ void ath79_device_reset_clear(u32 mask)
 		reg = AR933X_RESET_REG_RESET_MODULE;
 	else if (soc_is_ar934x())
 		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
 	else if (soc_is_qca955x())
 		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
 	else
 		BUG();
 
diff --git a/arch/mips/ath79/early_printk.c b/arch/mips/ath79/early_printk.c
index d1adc59af5bf..4b1063117ef7 100644
--- a/arch/mips/ath79/early_printk.c
+++ b/arch/mips/ath79/early_printk.c
@@ -13,12 +13,13 @@
 #include <linux/errno.h>
 #include <linux/serial_reg.h>
 #include <asm/addrspace.h>
+#include <asm/setup.h>
 
 #include <asm/mach-ath79/ath79.h>
 #include <asm/mach-ath79/ar71xx_regs.h>
 #include <asm/mach-ath79/ar933x_uart.h>
 
-static void (*_prom_putchar) (unsigned char);
+static void (*_prom_putchar)(char);
 
 static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
 {
@@ -33,31 +34,72 @@ static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
 
 #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
 
-static void prom_putchar_ar71xx(unsigned char ch)
+static void prom_putchar_ar71xx(char ch)
 {
 	void __iomem *base = (void __iomem *)(KSEG1ADDR(AR71XX_UART_BASE));
 
 	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
-	__raw_writel(ch, base + UART_TX * 4);
+	__raw_writel((unsigned char)ch, base + UART_TX * 4);
 	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
 }
 
-static void prom_putchar_ar933x(unsigned char ch)
+static void prom_putchar_ar933x(char ch)
 {
 	void __iomem *base = (void __iomem *)(KSEG1ADDR(AR933X_UART_BASE));
 
 	prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR,
 			  AR933X_UART_DATA_TX_CSR);
-	__raw_writel(AR933X_UART_DATA_TX_CSR | ch, base + AR933X_UART_DATA_REG);
+	__raw_writel(AR933X_UART_DATA_TX_CSR | (unsigned char)ch,
+		     base + AR933X_UART_DATA_REG);
 	prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR,
 			  AR933X_UART_DATA_TX_CSR);
 }
 
-static void prom_putchar_dummy(unsigned char ch)
+static void prom_putchar_dummy(char ch)
 {
 	/* nothing to do */
 }
 
+static void prom_enable_uart(u32 id)
+{
+	void __iomem *gpio_base;
+	u32 uart_en;
+	u32 t;
+
+	switch (id) {
+	case REV_ID_MAJOR_AR71XX:
+		uart_en = AR71XX_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR7240:
+	case REV_ID_MAJOR_AR7241:
+	case REV_ID_MAJOR_AR7242:
+		uart_en = AR724X_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR913X:
+		uart_en = AR913X_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR9330:
+	case REV_ID_MAJOR_AR9331:
+		uart_en = AR933X_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR9341:
+	case REV_ID_MAJOR_AR9342:
+	case REV_ID_MAJOR_AR9344:
+		/* TODO */
+	default:
+		return;
+	}
+
+	gpio_base = (void __iomem *)KSEG1ADDR(AR71XX_GPIO_BASE);
+	t = __raw_readl(gpio_base + AR71XX_GPIO_REG_FUNC);
+	t |= uart_en;
+	__raw_writel(t, gpio_base + AR71XX_GPIO_REG_FUNC);
+}
+
 static void prom_putchar_init(void)
 {
 	void __iomem *base;
@@ -76,8 +118,12 @@ static void prom_putchar_init(void)
 	case REV_ID_MAJOR_AR9341:
 	case REV_ID_MAJOR_AR9342:
 	case REV_ID_MAJOR_AR9344:
+	case REV_ID_MAJOR_QCA9533:
+	case REV_ID_MAJOR_QCA9533_V2:
 	case REV_ID_MAJOR_QCA9556:
 	case REV_ID_MAJOR_QCA9558:
+	case REV_ID_MAJOR_TP9343:
+	case REV_ID_MAJOR_QCA956X:
 		_prom_putchar = prom_putchar_ar71xx;
 		break;
 
@@ -88,11 +134,13 @@ static void prom_putchar_init(void)
 
 	default:
 		_prom_putchar = prom_putchar_dummy;
-		break;
+		return;
 	}
+
+	prom_enable_uart(id);
 }
 
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
 {
 	if (!_prom_putchar)
 		prom_putchar_init();
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index f206dafbb0a3..4c7a93f4039a 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -40,6 +40,7 @@ static char ath79_sys_type[ATH79_SYS_TYPE_LEN];
 
 static void ath79_restart(char *command)
 {
+	local_irq_disable();
 	ath79_device_reset_set(AR71XX_RESET_FULL_CHIP);
 	for (;;)
 		if (cpu_wait)
@@ -59,6 +60,7 @@ static void __init ath79_detect_sys_type(void)
 	u32 major;
 	u32 minor;
 	u32 rev = 0;
+	u32 ver = 1;
 
 	id = ath79_reset_rr(AR71XX_RESET_REG_REV_ID);
 	major = id & REV_ID_MAJOR_MASK;
@@ -151,6 +153,17 @@ static void __init ath79_detect_sys_type(void)
 		rev = id & AR934X_REV_ID_REVISION_MASK;
 		break;
 
+	case REV_ID_MAJOR_QCA9533_V2:
+		ver = 2;
+		ath79_soc_rev = 2;
+		/* drop through */
+
+	case REV_ID_MAJOR_QCA9533:
+		ath79_soc = ATH79_SOC_QCA9533;
+		chip = "9533";
+		rev = id & QCA953X_REV_ID_REVISION_MASK;
+		break;
+
 	case REV_ID_MAJOR_QCA9556:
 		ath79_soc = ATH79_SOC_QCA9556;
 		chip = "9556";
@@ -163,14 +176,30 @@ static void __init ath79_detect_sys_type(void)
 		rev = id & QCA955X_REV_ID_REVISION_MASK;
 		break;
 
+	case REV_ID_MAJOR_QCA956X:
+		ath79_soc = ATH79_SOC_QCA956X;
+		chip = "956X";
+		rev = id & QCA956X_REV_ID_REVISION_MASK;
+		break;
+
+	case REV_ID_MAJOR_TP9343:
+		ath79_soc = ATH79_SOC_TP9343;
+		chip = "9343";
+		rev = id & QCA956X_REV_ID_REVISION_MASK;
+		break;
+
 	default:
 		panic("ath79: unknown SoC, id:0x%08x", id);
 	}
 
-	ath79_soc_rev = rev;
+	if (ver == 1)
+		ath79_soc_rev = rev;
 
-	if (soc_is_qca955x())
-		sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s rev %u",
+	if (soc_is_qca953x() || soc_is_qca955x() || soc_is_qca956x())
+		sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s ver %u rev %u",
+			chip, ver, rev);
+	else if (soc_is_tp9343())
+		sprintf(ath79_sys_type, "Qualcomm Atheros TP%s rev %u",
 			chip, rev);
 	else
 		sprintf(ath79_sys_type, "Atheros AR%s rev %u", chip, rev);
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 8c9cbf13d32a..6054d49e608e 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -212,12 +212,6 @@ static int __init bcm47xx_cpu_fixes(void)
 		 */
 		if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706)
 			cpu_wait = NULL;
-
-		/*
-		 * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail"
-		 * Enable ExternalSync for sync instruction to take effect
-		 */
-		set_c0_config7(MIPS_CONF7_ES);
 		break;
 #endif
 	}
diff --git a/arch/mips/bcm63xx/early_printk.c b/arch/mips/bcm63xx/early_printk.c
index 6092226a6d76..9e9ec27c282f 100644
--- a/arch/mips/bcm63xx/early_printk.c
+++ b/arch/mips/bcm63xx/early_printk.c
@@ -8,6 +8,7 @@
 
 #include <bcm63xx_io.h>
 #include <linux/serial_bcm63xx.h>
+#include <asm/setup.h>
 
 static void wait_xfered(void)
 {
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index 6dec30842b2f..3d13c77c125f 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -17,7 +17,7 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/types.h>
-#include <dma-coherence.h>
+#include <asm/bmips.h>
 
 /*
  * BCM338x has configurable address translation windows which allow the
@@ -40,7 +40,7 @@ static struct bmips_dma_range *bmips_dma_ranges;
 
 #define FLUSH_RAC		0x100
 
-static dma_addr_t bmips_phys_to_dma(struct device *dev, phys_addr_t pa)
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
 {
 	struct bmips_dma_range *r;
 
@@ -52,17 +52,7 @@ static dma_addr_t bmips_phys_to_dma(struct device *dev, phys_addr_t pa)
 	return pa;
 }
 
-dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
-	return bmips_phys_to_dma(dev, virt_to_phys(addr));
-}
-
-dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page)
-{
-	return bmips_phys_to_dma(dev, page_to_phys(page));
-}
-
-unsigned long plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	struct bmips_dma_range *r;
 
@@ -74,6 +64,22 @@ unsigned long plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
 	return dma_addr;
 }
 
+void arch_sync_dma_for_cpu_all(struct device *dev)
+{
+	void __iomem *cbr = BMIPS_GET_CBR();
+	u32 cfg;
+
+	if (boot_cpu_type() != CPU_BMIPS3300 &&
+	    boot_cpu_type() != CPU_BMIPS4350 &&
+	    boot_cpu_type() != CPU_BMIPS4380)
+		return;
+
+	/* Flush stale data out of the readahead cache */
+	cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
+	__raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG);
+	__raw_readl(cbr + BMIPS_RAC_CONFIG);
+}
+
 static int __init bmips_init_dma_ranges(void)
 {
 	struct device_node *np =
diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c
index 3b6f687f177c..231fc5ce375e 100644
--- a/arch/mips/bmips/setup.c
+++ b/arch/mips/bmips/setup.c
@@ -202,13 +202,6 @@ void __init device_tree_init(void)
 	of_node_put(np);
 }
 
-int __init plat_of_setup(void)
-{
-	return __dt_register_buses("simple-bus", NULL);
-}
-
-arch_initcall(plat_of_setup);
-
 static int __init plat_dev_init(void)
 {
 	of_clk_init(NULL);
diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index c22da16d67b8..35704c28a28b 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -105,28 +105,29 @@ $(obj)/uImage: $(obj)/uImage.$(suffix-y)
 # Flattened Image Tree (.itb) images
 #
 
-targets += vmlinux.itb
-targets += vmlinux.gz.itb
-targets += vmlinux.bz2.itb
-targets += vmlinux.lzma.itb
-targets += vmlinux.lzo.itb
-
 ifeq ($(ADDR_BITS),32)
-	itb_addr_cells = 1
+itb_addr_cells = 1
 endif
 ifeq ($(ADDR_BITS),64)
-	itb_addr_cells = 2
+itb_addr_cells = 2
 endif
 
+targets += vmlinux.its.S
+
 quiet_cmd_its_cat = CAT     $@
-      cmd_its_cat = cat $^ >$@
+      cmd_its_cat = cat $(filter-out $(PHONY), $^) >$@
 
-$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS))
+$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS)) FORCE
 	$(call if_changed,its_cat)
 
+targets += vmlinux.its
+targets += vmlinux.gz.its
+targets += vmlinux.bz2.its
+targets += vmlinux.lzmo.its
+targets += vmlinux.lzo.its
+
 quiet_cmd_cpp_its_S = ITS     $@
-      cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \
-			-D__ASSEMBLY__ \
+      cmd_cpp_its_S = $(CPP) -P -C -o $@ $< \
 		        -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \
 			-DVMLINUX_BINARY="\"$(3)\"" \
 			-DVMLINUX_COMPRESSION="\"$(2)\"" \
@@ -136,19 +137,25 @@ quiet_cmd_cpp_its_S = ITS     $@
 			-DADDR_CELLS=$(itb_addr_cells)
 
 $(obj)/vmlinux.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,none,vmlinux.bin)
+	$(call if_changed,cpp_its_S,none,vmlinux.bin)
 
 $(obj)/vmlinux.gz.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,gzip,vmlinux.bin.gz)
+	$(call if_changed,cpp_its_S,gzip,vmlinux.bin.gz)
 
 $(obj)/vmlinux.bz2.its: $(obj)/vmlinux.its.S $(VMLINUX)  FORCE
-	$(call if_changed_dep,cpp_its_S,bzip2,vmlinux.bin.bz2)
+	$(call if_changed,cpp_its_S,bzip2,vmlinux.bin.bz2)
 
 $(obj)/vmlinux.lzma.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,lzma,vmlinux.bin.lzma)
+	$(call if_changed,cpp_its_S,lzma,vmlinux.bin.lzma)
 
 $(obj)/vmlinux.lzo.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,lzo,vmlinux.bin.lzo)
+	$(call if_changed,cpp_its_S,lzo,vmlinux.bin.lzo)
+
+targets += vmlinux.itb
+targets += vmlinux.gz.itb
+targets += vmlinux.bz2.itb
+targets += vmlinux.lzma.itb
+targets += vmlinux.lzo.itb
 
 quiet_cmd_itb-image = ITB     $@
       cmd_itb-image = \
@@ -162,14 +169,5 @@ quiet_cmd_itb-image = ITB     $@
 $(obj)/vmlinux.itb: $(obj)/vmlinux.its $(obj)/vmlinux.bin FORCE
 	$(call if_changed,itb-image,$<)
 
-$(obj)/vmlinux.gz.itb: $(obj)/vmlinux.gz.its $(obj)/vmlinux.bin.gz FORCE
-	$(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.bz2.itb: $(obj)/vmlinux.bz2.its $(obj)/vmlinux.bin.bz2 FORCE
-	$(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.lzma.itb: $(obj)/vmlinux.lzma.its $(obj)/vmlinux.bin.lzma FORCE
-	$(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.lzo.itb: $(obj)/vmlinux.lzo.its $(obj)/vmlinux.bin.lzo FORCE
+$(obj)/vmlinux.%.itb: $(obj)/vmlinux.%.its $(obj)/vmlinux.bin.% FORCE
 	$(call if_changed,itb-image,$<)
diff --git a/arch/mips/boot/compressed/uart-prom.c b/arch/mips/boot/compressed/uart-prom.c
index d6f0fee0a151..a8a0a32e05d1 100644
--- a/arch/mips/boot/compressed/uart-prom.c
+++ b/arch/mips/boot/compressed/uart-prom.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-
-extern void prom_putchar(unsigned char ch);
+#include <asm/setup.h>
 
 void putc(char c)
 {
diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi
index aa4e8f75ff5d..ce93d57f1b4d 100644
--- a/arch/mips/boot/dts/ingenic/jz4780.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi
@@ -155,6 +155,25 @@
 		};
 	};
 
+	spi_gpio {
+		compatible = "spi-gpio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		num-chipselects = <2>;
+
+		gpio-miso = <&gpe 14 0>;
+		gpio-sck = <&gpe 15 0>;
+		gpio-mosi = <&gpe 17 0>;
+		cs-gpios = <&gpe 16 0
+			    &gpe 18 0>;
+
+		spidev@0 {
+			compatible = "spidev";
+			reg = <0>;
+			spi-max-frequency = <1000000>;
+		};
+	};
+
 	uart0: serial@10030000 {
 		compatible = "ingenic,jz4780-uart";
 		reg = <0x10030000 0x100>;
diff --git a/arch/mips/boot/dts/mscc/Makefile b/arch/mips/boot/dts/mscc/Makefile
index 3c6aed9f5439..9a9bb7ea0503 100644
--- a/arch/mips/boot/dts/mscc/Makefile
+++ b/arch/mips/boot/dts/mscc/Makefile
@@ -1,3 +1,3 @@
-dtb-$(CONFIG_LEGACY_BOARD_OCELOT)	+= ocelot_pcb123.dtb
+dtb-$(CONFIG_MSCC_OCELOT)	+= ocelot_pcb123.dtb
 
 obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index 4f33dbc67348..f7eb612b46ba 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -91,6 +91,17 @@
 			status = "disabled";
 		};
 
+		spi: spi@101000 {
+			compatible = "mscc,ocelot-spi", "snps,dw-apb-ssi";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x101000 0x100>, <0x3c 0x18>;
+			interrupts = <9>;
+			clocks = <&ahb_clk>;
+
+			status = "disabled";
+		};
+
 		switch@1010000 {
 			compatible = "mscc,vsc7514-switch";
 			reg = <0x1010000 0x10000>,
@@ -168,6 +179,9 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-ranges = <&gpio 0 0 22>;
+			interrupt-controller;
+			interrupts = <13>;
+			#interrupt-cells = <2>;
 
 			uart_pins: uart-pins {
 				pins = "GPIO_6", "GPIO_7";
@@ -178,13 +192,18 @@
 				pins = "GPIO_12", "GPIO_13";
 				function = "uart2";
 			};
+
+			miim1: miim1 {
+				pins = "GPIO_14", "GPIO_15";
+				function = "miim1";
+			};
 		};
 
 		mdio0: mdio@107009c {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "mscc,ocelot-miim";
-			reg = <0x107009c 0x36>, <0x10700f0 0x8>;
+			reg = <0x107009c 0x24>, <0x10700f0 0x8>;
 			interrupts = <14>;
 			status = "disabled";
 
@@ -201,5 +220,16 @@
 				reg = <3>;
 			};
 		};
+
+		mdio1: mdio@10700c0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "mscc,ocelot-miim";
+			reg = <0x10700c0 0x24>;
+			interrupts = <15>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&miim1>;
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
index 4ccd65379059..2266027759f9 100644
--- a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
+++ b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
@@ -26,6 +26,16 @@
 	status = "okay";
 };
 
+&spi {
+	status = "okay";
+
+	flash@0 {
+		compatible = "macronix,mx25l25635f", "jedec,spi-nor";
+		spi-max-frequency = <20000000>;
+		reg = <0>;
+	};
+};
+
 &mdio0 {
 	status = "okay";
 };
diff --git a/arch/mips/boot/dts/qca/ar9132.dtsi b/arch/mips/boot/dts/qca/ar9132.dtsi
index 1fe561c5f90e..61dcfa5b6ca7 100644
--- a/arch/mips/boot/dts/qca/ar9132.dtsi
+++ b/arch/mips/boot/dts/qca/ar9132.dtsi
@@ -161,7 +161,7 @@
 	usb_phy: usb-phy {
 		compatible = "qca,ar7100-usb-phy";
 
-		reset-names = "usb-phy", "usb-suspend-override";
+		reset-names = "phy", "suspend-override";
 		resets = <&rst 4>, <&rst 3>;
 
 		#phy-cells = <0>;
diff --git a/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts b/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
index 3931033e47c8..7fccf6357225 100644
--- a/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
+++ b/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
@@ -22,11 +22,10 @@
 	};
 
 	gpio-keys {
-		compatible = "gpio-keys-polled";
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		poll-interval = <20>;
 		button@0 {
 			label = "reset";
 			linux,code = <KEY_RESTART>;
diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi
index efd5f0722206..2bae201aa365 100644
--- a/arch/mips/boot/dts/qca/ar9331.dtsi
+++ b/arch/mips/boot/dts/qca/ar9331.dtsi
@@ -146,7 +146,7 @@
 	usb_phy: usb-phy {
 		compatible = "qca,ar7100-usb-phy";
 
-		reset-names = "usb-phy", "usb-suspend-override";
+		reset-names = "phy", "suspend-override";
 		resets = <&rst 4>, <&rst 3>;
 
 		#phy-cells = <0>;
diff --git a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
index d4e4502daaa8..e7af2cf5f4c1 100644
--- a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
+++ b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
@@ -29,11 +29,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "reset";
diff --git a/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts b/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts
index 4f95ccf17c4c..d38aa73f1a2e 100644
--- a/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts
+++ b/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts
@@ -47,11 +47,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "jumpstart";
diff --git a/arch/mips/boot/dts/qca/ar9331_omega.dts b/arch/mips/boot/dts/qca/ar9331_omega.dts
index f70f79c4d0d5..11778abacf66 100644
--- a/arch/mips/boot/dts/qca/ar9331_omega.dts
+++ b/arch/mips/boot/dts/qca/ar9331_omega.dts
@@ -29,11 +29,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "reset";
diff --git a/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts b/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts
index 748131aea22e..c8290d36cfbe 100644
--- a/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts
+++ b/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts
@@ -47,11 +47,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "wps";
diff --git a/arch/mips/boot/ecoff.h b/arch/mips/boot/ecoff.h
index b3e73c22c345..5be79ebfc3f8 100644
--- a/arch/mips/boot/ecoff.h
+++ b/arch/mips/boot/ecoff.h
@@ -2,14 +2,17 @@
 /*
  * Some ECOFF definitions.
  */
+
+#include <stdint.h>
+
 typedef struct filehdr {
-	unsigned short	f_magic;	/* magic number */
-	unsigned short	f_nscns;	/* number of sections */
-	long		f_timdat;	/* time & date stamp */
-	long		f_symptr;	/* file pointer to symbolic header */
-	long		f_nsyms;	/* sizeof(symbolic hdr) */
-	unsigned short	f_opthdr;	/* sizeof(optional hdr) */
-	unsigned short	f_flags;	/* flags */
+	uint16_t	f_magic;	/* magic number */
+	uint16_t	f_nscns;	/* number of sections */
+	int32_t		f_timdat;	/* time & date stamp */
+	int32_t		f_symptr;	/* file pointer to symbolic header */
+	int32_t		f_nsyms;	/* sizeof(symbolic hdr) */
+	uint16_t	f_opthdr;	/* sizeof(optional hdr) */
+	uint16_t	f_flags;	/* flags */
 } FILHDR;
 #define FILHSZ	sizeof(FILHDR)
 
@@ -18,32 +21,32 @@ typedef struct filehdr {
 
 typedef struct scnhdr {
 	char		s_name[8];	/* section name */
-	long		s_paddr;	/* physical address, aliased s_nlib */
-	long		s_vaddr;	/* virtual address */
-	long		s_size;		/* section size */
-	long		s_scnptr;	/* file ptr to raw data for section */
-	long		s_relptr;	/* file ptr to relocation */
-	long		s_lnnoptr;	/* file ptr to gp histogram */
-	unsigned short	s_nreloc;	/* number of relocation entries */
-	unsigned short	s_nlnno;	/* number of gp histogram entries */
-	long		s_flags;	/* flags */
+	int32_t		s_paddr;	/* physical address, aliased s_nlib */
+	int32_t		s_vaddr;	/* virtual address */
+	int32_t		s_size;		/* section size */
+	int32_t		s_scnptr;	/* file ptr to raw data for section */
+	int32_t		s_relptr;	/* file ptr to relocation */
+	int32_t		s_lnnoptr;	/* file ptr to gp histogram */
+	uint16_t	s_nreloc;	/* number of relocation entries */
+	uint16_t	s_nlnno;	/* number of gp histogram entries */
+	int32_t		s_flags;	/* flags */
 } SCNHDR;
 #define SCNHSZ		sizeof(SCNHDR)
-#define SCNROUND	((long)16)
+#define SCNROUND	((int32_t)16)
 
 typedef struct aouthdr {
-	short	magic;		/* see above				*/
-	short	vstamp;		/* version stamp			*/
-	long	tsize;		/* text size in bytes, padded to DW bdry*/
-	long	dsize;		/* initialized data "  "		*/
-	long	bsize;		/* uninitialized data "	  "		*/
-	long	entry;		/* entry pt.				*/
-	long	text_start;	/* base of text used for this file	*/
-	long	data_start;	/* base of data used for this file	*/
-	long	bss_start;	/* base of bss used for this file	*/
-	long	gprmask;	/* general purpose register mask	*/
-	long	cprmask[4];	/* co-processor register masks		*/
-	long	gp_value;	/* the gp value used for this object	*/
+	int16_t	magic;		/* see above				*/
+	int16_t	vstamp;		/* version stamp			*/
+	int32_t	tsize;		/* text size in bytes, padded to DW bdry*/
+	int32_t	dsize;		/* initialized data "  "		*/
+	int32_t	bsize;		/* uninitialized data "	  "		*/
+	int32_t	entry;		/* entry pt.				*/
+	int32_t	text_start;	/* base of text used for this file	*/
+	int32_t	data_start;	/* base of data used for this file	*/
+	int32_t	bss_start;	/* base of bss used for this file	*/
+	int32_t	gprmask;	/* general purpose register mask	*/
+	int32_t	cprmask[4];	/* co-processor register masks		*/
+	int32_t	gp_value;	/* the gp value used for this object	*/
 } AOUTHDR;
 #define AOUTHSZ sizeof(AOUTHDR)
 
diff --git a/arch/mips/boot/elf2ecoff.c b/arch/mips/boot/elf2ecoff.c
index 266c8137e859..6972b97235da 100644
--- a/arch/mips/boot/elf2ecoff.c
+++ b/arch/mips/boot/elf2ecoff.c
@@ -43,6 +43,8 @@
 #include <limits.h>
 #include <netinet/in.h>
 #include <stdlib.h>
+#include <stdint.h>
+#include <inttypes.h>
 
 #include "ecoff.h"
 
@@ -55,8 +57,8 @@
 /* -------------------------------------------------------------------- */
 
 struct sect {
-	unsigned long vaddr;
-	unsigned long len;
+	uint32_t vaddr;
+	uint32_t len;
 };
 
 int *symTypeTable;
@@ -153,16 +155,16 @@ static char *saveRead(int file, off_t offset, off_t len, char *name)
 }
 
 #define swab16(x) \
-	((unsigned short)( \
-		(((unsigned short)(x) & (unsigned short)0x00ffU) << 8) | \
-		(((unsigned short)(x) & (unsigned short)0xff00U) >> 8) ))
+	((uint16_t)( \
+		(((uint16_t)(x) & (uint16_t)0x00ffU) << 8) | \
+		(((uint16_t)(x) & (uint16_t)0xff00U) >> 8) ))
 
 #define swab32(x) \
 	((unsigned int)( \
-		(((unsigned int)(x) & (unsigned int)0x000000ffUL) << 24) | \
-		(((unsigned int)(x) & (unsigned int)0x0000ff00UL) <<  8) | \
-		(((unsigned int)(x) & (unsigned int)0x00ff0000UL) >>  8) | \
-		(((unsigned int)(x) & (unsigned int)0xff000000UL) >> 24) ))
+		(((uint32_t)(x) & (uint32_t)0x000000ffUL) << 24) | \
+		(((uint32_t)(x) & (uint32_t)0x0000ff00UL) <<  8) | \
+		(((uint32_t)(x) & (uint32_t)0x00ff0000UL) >>  8) | \
+		(((uint32_t)(x) & (uint32_t)0xff000000UL) >> 24) ))
 
 static void convert_elf_hdr(Elf32_Ehdr * e)
 {
@@ -274,7 +276,7 @@ int main(int argc, char *argv[])
 	struct aouthdr eah;
 	struct scnhdr esecs[6];
 	int infile, outfile;
-	unsigned long cur_vma = ULONG_MAX;
+	uint32_t cur_vma = UINT32_MAX;
 	int addflag = 0;
 	int nosecs;
 
@@ -518,7 +520,7 @@ int main(int argc, char *argv[])
 
 		for (i = 0; i < nosecs; i++) {
 			printf
-			    ("Section %d: %s phys %lx  size %lx	 file offset %lx\n",
+			    ("Section %d: %s phys %"PRIx32"  size %"PRIx32"\t file offset %"PRIx32"\n",
 			     i, esecs[i].s_name, esecs[i].s_paddr,
 			     esecs[i].s_size, esecs[i].s_scnptr);
 		}
@@ -564,17 +566,16 @@ int main(int argc, char *argv[])
 		   the section can be loaded before copying. */
 		if (ph[i].p_type == PT_LOAD && ph[i].p_filesz) {
 			if (cur_vma != ph[i].p_vaddr) {
-				unsigned long gap =
-				    ph[i].p_vaddr - cur_vma;
+				uint32_t gap = ph[i].p_vaddr - cur_vma;
 				char obuf[1024];
 				if (gap > 65536) {
 					fprintf(stderr,
-						"Intersegment gap (%ld bytes) too large.\n",
+						"Intersegment gap (%"PRId32" bytes) too large.\n",
 						gap);
 					exit(1);
 				}
 				fprintf(stderr,
-					"Warning: %ld byte intersegment gap.\n",
+					"Warning: %d byte intersegment gap.\n",
 					gap);
 				memset(obuf, 0, sizeof obuf);
 				while (gap) {
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 7b335ab21697..236833be6fbe 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -11,9 +11,7 @@
  * Copyright (C) 2010 Cavium Networks, Inc.
  */
 #include <linux/dma-direct.h>
-#include <linux/scatterlist.h>
 #include <linux/bootmem.h>
-#include <linux/export.h>
 #include <linux/swiotlb.h>
 #include <linux/types.h>
 #include <linux/init.h>
@@ -24,10 +22,16 @@
 #include <asm/octeon/octeon.h>
 
 #ifdef CONFIG_PCI
+#include <linux/pci.h>
 #include <asm/octeon/pci-octeon.h>
 #include <asm/octeon/cvmx-npi-defs.h>
 #include <asm/octeon/cvmx-pci-defs.h>
 
+struct octeon_dma_map_ops {
+	dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr);
+	phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr);
+};
+
 static dma_addr_t octeon_hole_phys_to_dma(phys_addr_t paddr)
 {
 	if (paddr >= CVMX_PCIE_BAR1_PHYS_BASE && paddr < (CVMX_PCIE_BAR1_PHYS_BASE + CVMX_PCIE_BAR1_PHYS_SIZE))
@@ -61,6 +65,11 @@ static phys_addr_t octeon_gen1_dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return daddr;
 }
 
+static const struct octeon_dma_map_ops octeon_gen1_ops = {
+	.phys_to_dma	= octeon_gen1_phys_to_dma,
+	.dma_to_phys	= octeon_gen1_dma_to_phys,
+};
+
 static dma_addr_t octeon_gen2_phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return octeon_hole_phys_to_dma(paddr);
@@ -71,6 +80,11 @@ static phys_addr_t octeon_gen2_dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return octeon_hole_dma_to_phys(daddr);
 }
 
+static const struct octeon_dma_map_ops octeon_gen2_ops = {
+	.phys_to_dma	= octeon_gen2_phys_to_dma,
+	.dma_to_phys	= octeon_gen2_dma_to_phys,
+};
+
 static dma_addr_t octeon_big_phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	if (paddr >= 0x410000000ull && paddr < 0x420000000ull)
@@ -93,6 +107,11 @@ static phys_addr_t octeon_big_dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return daddr;
 }
 
+static const struct octeon_dma_map_ops octeon_big_ops = {
+	.phys_to_dma	= octeon_big_phys_to_dma,
+	.dma_to_phys	= octeon_big_dma_to_phys,
+};
+
 static dma_addr_t octeon_small_phys_to_dma(struct device *dev,
 					   phys_addr_t paddr)
 {
@@ -121,105 +140,51 @@ static phys_addr_t octeon_small_dma_to_phys(struct device *dev,
 	return daddr;
 }
 
-#endif /* CONFIG_PCI */
-
-static dma_addr_t octeon_dma_map_page(struct device *dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
-					    direction, attrs);
-	mb();
-
-	return daddr;
-}
-
-static int octeon_dma_map_sg(struct device *dev, struct scatterlist *sg,
-	int nents, enum dma_data_direction direction, unsigned long attrs)
-{
-	int r = swiotlb_map_sg_attrs(dev, sg, nents, direction, attrs);
-	mb();
-	return r;
-}
-
-static void octeon_dma_sync_single_for_device(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	swiotlb_sync_single_for_device(dev, dma_handle, size, direction);
-	mb();
-}
-
-static void octeon_dma_sync_sg_for_device(struct device *dev,
-	struct scatterlist *sg, int nelems, enum dma_data_direction direction)
-{
-	swiotlb_sync_sg_for_device(dev, sg, nelems, direction);
-	mb();
-}
-
-static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
-
-	mb();
+static const struct octeon_dma_map_ops octeon_small_ops = {
+	.phys_to_dma	= octeon_small_phys_to_dma,
+	.dma_to_phys	= octeon_small_dma_to_phys,
+};
 
-	return ret;
-}
+static const struct octeon_dma_map_ops *octeon_pci_dma_ops;
 
-static dma_addr_t octeon_unity_phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return paddr;
-}
-
-static phys_addr_t octeon_unity_dma_to_phys(struct device *dev, dma_addr_t daddr)
+void __init octeon_pci_dma_init(void)
 {
-	return daddr;
+	switch (octeon_dma_bar_type) {
+	case OCTEON_DMA_BAR_TYPE_PCIE:
+		octeon_pci_dma_ops = &octeon_gen1_ops;
+		break;
+	case OCTEON_DMA_BAR_TYPE_PCIE2:
+		octeon_pci_dma_ops = &octeon_gen2_ops;
+		break;
+	case OCTEON_DMA_BAR_TYPE_BIG:
+		octeon_pci_dma_ops = &octeon_big_ops;
+		break;
+	case OCTEON_DMA_BAR_TYPE_SMALL:
+		octeon_pci_dma_ops = &octeon_small_ops;
+		break;
+	default:
+		BUG();
+	}
 }
-
-struct octeon_dma_map_ops {
-	const struct dma_map_ops dma_map_ops;
-	dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr);
-	phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr);
-};
+#endif /* CONFIG_PCI */
 
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
-						      struct octeon_dma_map_ops,
-						      dma_map_ops);
-
-	return ops->phys_to_dma(dev, paddr);
+#ifdef CONFIG_PCI
+	if (dev && dev_is_pci(dev))
+		return octeon_pci_dma_ops->phys_to_dma(dev, paddr);
+#endif
+	return paddr;
 }
-EXPORT_SYMBOL(__phys_to_dma);
 
 phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-	struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
-						      struct octeon_dma_map_ops,
-						      dma_map_ops);
-
-	return ops->dma_to_phys(dev, daddr);
+#ifdef CONFIG_PCI
+	if (dev && dev_is_pci(dev))
+		return octeon_pci_dma_ops->dma_to_phys(dev, daddr);
+#endif
+	return daddr;
 }
-EXPORT_SYMBOL(__dma_to_phys);
-
-static struct octeon_dma_map_ops octeon_linear_dma_map_ops = {
-	.dma_map_ops = {
-		.alloc = octeon_dma_alloc_coherent,
-		.free = swiotlb_free,
-		.map_page = octeon_dma_map_page,
-		.unmap_page = swiotlb_unmap_page,
-		.map_sg = octeon_dma_map_sg,
-		.unmap_sg = swiotlb_unmap_sg_attrs,
-		.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-		.sync_single_for_device = octeon_dma_sync_single_for_device,
-		.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-		.sync_sg_for_device = octeon_dma_sync_sg_for_device,
-		.mapping_error = swiotlb_dma_mapping_error,
-		.dma_supported = swiotlb_dma_supported
-	},
-	.phys_to_dma = octeon_unity_phys_to_dma,
-	.dma_to_phys = octeon_unity_dma_to_phys
-};
 
 char *octeon_swiotlb;
 
@@ -283,52 +248,4 @@ void __init plat_swiotlb_setup(void)
 
 	if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM)
 		panic("Cannot allocate SWIOTLB buffer");
-
-	mips_dma_map_ops = &octeon_linear_dma_map_ops.dma_map_ops;
 }
-
-#ifdef CONFIG_PCI
-static struct octeon_dma_map_ops _octeon_pci_dma_map_ops = {
-	.dma_map_ops = {
-		.alloc = octeon_dma_alloc_coherent,
-		.free = swiotlb_free,
-		.map_page = octeon_dma_map_page,
-		.unmap_page = swiotlb_unmap_page,
-		.map_sg = octeon_dma_map_sg,
-		.unmap_sg = swiotlb_unmap_sg_attrs,
-		.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-		.sync_single_for_device = octeon_dma_sync_single_for_device,
-		.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-		.sync_sg_for_device = octeon_dma_sync_sg_for_device,
-		.mapping_error = swiotlb_dma_mapping_error,
-		.dma_supported = swiotlb_dma_supported
-	},
-};
-
-const struct dma_map_ops *octeon_pci_dma_map_ops;
-
-void __init octeon_pci_dma_init(void)
-{
-	switch (octeon_dma_bar_type) {
-	case OCTEON_DMA_BAR_TYPE_PCIE2:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_gen2_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_gen2_dma_to_phys;
-		break;
-	case OCTEON_DMA_BAR_TYPE_PCIE:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_gen1_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_gen1_dma_to_phys;
-		break;
-	case OCTEON_DMA_BAR_TYPE_BIG:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_big_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_big_dma_to_phys;
-		break;
-	case OCTEON_DMA_BAR_TYPE_SMALL:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_small_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_small_dma_to_phys;
-		break;
-	default:
-		BUG();
-	}
-	octeon_pci_dma_map_ops = &_octeon_pci_dma_map_ops.dma_map_ops;
-}
-#endif /* CONFIG_PCI */
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
index d18ed5af62f4..b8898e2b8a6f 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -42,9 +42,6 @@
 #include <asm/octeon/cvmx-asxx-defs.h>
 #include <asm/octeon/cvmx-dbg-defs.h>
 
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_asxx_enable(int block);
-
 /**
  * Probe RGMII ports and determine the number present
  *
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
index 578283350776..a176358c5a21 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -39,10 +39,7 @@
 
 #include <asm/octeon/cvmx-gmxx-defs.h>
 #include <asm/octeon/cvmx-pcsx-defs.h>
-
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
-void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
+#include <asm/octeon/cvmx-pcsxx-defs.h>
 
 /**
  * Perform initialization required only once for an SGMII port.
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c
index ef16aa00167b..2a574d272671 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -25,10 +25,6 @@
  * Contact Cavium Networks for more information
  ***********************license end**************************************/
 
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_spxx_int_msk_enable(int index);
-void __cvmx_interrupt_stxx_int_msk_enable(int index);
-
 /*
  * Functions for SPI initialization, configuration,
  * and monitoring.
@@ -41,6 +37,8 @@ void __cvmx_interrupt_stxx_int_msk_enable(int index);
 
 #include <asm/octeon/cvmx-pip-defs.h>
 #include <asm/octeon/cvmx-pko-defs.h>
+#include <asm/octeon/cvmx-spxx-defs.h>
+#include <asm/octeon/cvmx-stxx-defs.h>
 
 /*
  * CVMX_HELPER_SPI_TIMEOUT is used to determine how long the SPI
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
index 19d54e02c185..2bb6912a580d 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -39,12 +39,9 @@
 
 #include <asm/octeon/cvmx-pko-defs.h>
 #include <asm/octeon/cvmx-gmxx-defs.h>
+#include <asm/octeon/cvmx-pcsx-defs.h>
 #include <asm/octeon/cvmx-pcsxx-defs.h>
 
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
-void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
-
 int __cvmx_helper_xaui_enumerate(int interface)
 {
 	union cvmx_gmxx_hg2_control gmx_hg2_control;
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index b3aec101a65d..8272d8c648ca 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -814,7 +814,7 @@ static int octeon_irq_ciu_set_affinity(struct irq_data *data,
 			pen = &per_cpu(octeon_irq_ciu1_en_mirror, cpu);
 
 		if (cpumask_test_cpu(cpu, dest) && enable_one) {
-			enable_one = 0;
+			enable_one = false;
 			__set_bit(cd->bit, pen);
 		} else {
 			__clear_bit(cd->bit, pen);
diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index 8505db478904..807cadaf554e 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -322,6 +322,7 @@ static int __init octeon_ehci_device_init(void)
 		return 0;
 
 	pd = of_find_device_by_node(ehci_node);
+	of_node_put(ehci_node);
 	if (!pd)
 		return 0;
 
@@ -384,6 +385,7 @@ static int __init octeon_ohci_device_init(void)
 		return 0;
 
 	pd = of_find_device_by_node(ohci_node);
+	of_node_put(ohci_node);
 	if (!pd)
 		return 0;
 
@@ -1067,6 +1069,6 @@ end_led:
 
 static int __init octeon_publish_devices(void)
 {
-	return of_platform_bus_probe(NULL, octeon_ids, NULL);
+	return of_platform_populate(NULL, octeon_ids, NULL, NULL);
 }
 arch_initcall(octeon_publish_devices);
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index a8034d0dcade..c2426232db06 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -36,6 +36,7 @@
 #include <asm/mipsregs.h>
 #include <asm/bootinfo.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 #include <asm/time.h>
 
 #include <asm/octeon/octeon.h>
@@ -1108,7 +1109,7 @@ void __init plat_mem_setup(void)
  * Emit one character to the boot UART.	 Exported for use by the
  * watchdog timer.
  */
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	uint64_t lsrval;
 
@@ -1119,7 +1120,6 @@ int prom_putchar(char c)
 
 	/* Write the byte */
 	cvmx_write_csr(CVMX_MIO_UARTX_THR(octeon_uart), c & 0xffull);
-	return 1;
 }
 EXPORT_SYMBOL(prom_putchar);
 
@@ -1154,11 +1154,7 @@ void __init prom_free_prom_memory(void)
 }
 
 void __init octeon_fill_mac_addresses(void);
-int octeon_prune_device_tree(void);
 
-extern const char __appended_dtb;
-extern const char __dtb_octeon_3xxx_begin;
-extern const char __dtb_octeon_68xx_begin;
 void __init device_tree_init(void)
 {
 	const void *fdt;
diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig
index be23fd25eeaa..030ff9c205fb 100644
--- a/arch/mips/configs/ci20_defconfig
+++ b/arch/mips/configs/ci20_defconfig
@@ -92,6 +92,8 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_I2C=y
 CONFIG_I2C_JZ4780=y
+CONFIG_SPI=y
+CONFIG_SPI_GPIO=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_INGENIC=y
 # CONFIG_HWMON is not set
diff --git a/arch/mips/configs/generic_defconfig b/arch/mips/configs/generic_defconfig
index 26b1cd5ffbf5..684c9dcba126 100644
--- a/arch/mips/configs/generic_defconfig
+++ b/arch/mips/configs/generic_defconfig
@@ -43,9 +43,6 @@ CONFIG_NETFILTER=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_SCSI=y
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_HW_RANDOM=y
 # CONFIG_HWMON is not set
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index df8a9a15ca83..81058295d35f 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -317,6 +317,7 @@ CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 14df9ef15d40..5c10cddc39d3 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -328,6 +328,7 @@ CONFIG_INPUT_MOUSEDEV=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig
index 25092e344574..bb694f5065f1 100644
--- a/arch/mips/configs/malta_kvm_guest_defconfig
+++ b/arch/mips/configs/malta_kvm_guest_defconfig
@@ -330,6 +330,7 @@ CONFIG_INPUT_MOUSEDEV=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
index 210bf609f785..5b5306b80576 100644
--- a/arch/mips/configs/malta_qemu_32r6_defconfig
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -133,6 +133,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig
index e5934aa98397..85543599448f 100644
--- a/arch/mips/configs/maltaaprp_defconfig
+++ b/arch/mips/configs/maltaaprp_defconfig
@@ -133,6 +133,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig
index cb2ca11c1789..067bb84ac916 100644
--- a/arch/mips/configs/maltasmvp_defconfig
+++ b/arch/mips/configs/maltasmvp_defconfig
@@ -134,6 +134,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index be29fcec69fc..dfc78c3172a3 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -137,6 +137,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig
index 40462d4c90a0..50a2288c69f8 100644
--- a/arch/mips/configs/maltaup_defconfig
+++ b/arch/mips/configs/maltaup_defconfig
@@ -132,6 +132,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 4e50176cb3df..99a19cf5f9ba 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -326,6 +326,7 @@ CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/fw/arc/arc_con.c b/arch/mips/fw/arc/arc_con.c
index 769d4b9ac82e..365e3913231e 100644
--- a/arch/mips/fw/arc/arc_con.c
+++ b/arch/mips/fw/arc/arc_con.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/fs.h>
+#include <asm/setup.h>
 #include <asm/sgialib.h>
 
 static void prom_console_write(struct console *co, const char *s,
diff --git a/arch/mips/fw/arc/promlib.c b/arch/mips/fw/arc/promlib.c
index 7e8ba5ce95be..be381307fbb0 100644
--- a/arch/mips/fw/arc/promlib.c
+++ b/arch/mips/fw/arc/promlib.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <asm/sgialib.h>
 #include <asm/bcache.h>
+#include <asm/setup.h>
 
 /*
  * IP22 boardcache is not compatible with board caches.	 Thus we disable it
diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c
index 6aa264b9856a..8772617b64ce 100644
--- a/arch/mips/fw/sni/sniprom.c
+++ b/arch/mips/fw/sni/sniprom.c
@@ -19,6 +19,7 @@
 #include <asm/mipsprom.h>
 #include <asm/mipsregs.h>
 #include <asm/bootinfo.h>
+#include <asm/setup.h>
 
 /* special SNI prom calls */
 /*
diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig
index ba9b2c8cce68..08e33c6b2539 100644
--- a/arch/mips/generic/Kconfig
+++ b/arch/mips/generic/Kconfig
@@ -35,13 +35,13 @@ config LEGACY_BOARD_OCELOT
 	depends on LEGACY_BOARD_SEAD3=n
 	select LEGACY_BOARDS
 	select MSCC_OCELOT
+	select SYS_HAS_EARLY_PRINTK
+	select USE_GENERIC_EARLY_PRINTK_8250
 
 config MSCC_OCELOT
 	bool
 	select GPIOLIB
 	select MSCC_OCELOT_IRQ
-	select SYS_HAS_EARLY_PRINTK
-	select USE_GENERIC_EARLY_PRINTK_8250
 
 comment "FIT/UHI Boards"
 
@@ -65,6 +65,14 @@ config FIT_IMAGE_FDT_XILFPGA
 	  Enable this to include the FDT for the MIPSfpga platform
 	  from Imagination Technologies in the FIT kernel image.
 
+config FIT_IMAGE_FDT_OCELOT_PCB123
+	bool "Include FDT for Microsemi Ocelot PCB123"
+	select MSCC_OCELOT
+	help
+	  Enable this to include the FDT for the Ocelot PCB123 platform
+	  from Microsemi in the FIT kernel image.
+	  This requires u-boot on the platform.
+
 config VIRT_BOARD_RANCHU
 	bool "Support Ranchu platform for Android emulator"
 	help
diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform
index 0dd0d5d460a5..879cb80396c8 100644
--- a/arch/mips/generic/Platform
+++ b/arch/mips/generic/Platform
@@ -16,4 +16,5 @@ all-$(CONFIG_MIPS_GENERIC)	:= vmlinux.gz.itb
 its-y					:= vmlinux.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_BOSTON)	+= board-boston.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_NI169445)	+= board-ni169445.its.S
+its-$(CONFIG_FIT_IMAGE_FDT_OCELOT_PCB123) += board-ocelot_pcb123.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_XILFPGA)	+= board-xilfpga.its.S
diff --git a/arch/mips/generic/board-ocelot_pcb123.its.S b/arch/mips/generic/board-ocelot_pcb123.its.S
new file mode 100644
index 000000000000..5a7d5e1c878a
--- /dev/null
+++ b/arch/mips/generic/board-ocelot_pcb123.its.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/ {
+	images {
+		fdt@ocelot_pcb123 {
+			description = "MSCC Ocelot PCB123 Device Tree";
+			data = /incbin/("boot/dts/mscc/ocelot_pcb123.dtb");
+			type = "flat_dt";
+			arch = "mips";
+			compression = "none";
+			hash@0 {
+				algo = "sha1";
+			};
+		};
+	};
+
+	configurations {
+		conf@ocelot_pcb123 {
+			description = "Ocelot Linux kernel";
+			kernel = "kernel@0";
+			fdt = "fdt@ocelot_pcb123";
+		};
+	};
+};
diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c
index 5ba6fcc26fa7..a106f8113842 100644
--- a/arch/mips/generic/init.c
+++ b/arch/mips/generic/init.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/irqchip.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 
 #include <asm/bootinfo.h>
 #include <asm/fw/fw.h>
@@ -204,22 +203,11 @@ void __init arch_init_irq(void)
 					    "mti,cpu-interrupt-controller");
 	if (!cpu_has_veic && !intc_node)
 		mips_cpu_irq_init();
+	of_node_put(intc_node);
 
 	irqchip_init();
 }
 
-static int __init publish_devices(void)
-{
-	if (!of_have_populated_dt())
-		panic("Device-tree not present");
-
-	if (of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL))
-		panic("Failed to populate DT");
-
-	return 0;
-}
-arch_initcall(publish_devices);
-
 void __init prom_free_prom_memory(void)
 {
 }
diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c
index b408dac722ac..7ba4ad5cc1d6 100644
--- a/arch/mips/generic/yamon-dt.c
+++ b/arch/mips/generic/yamon-dt.c
@@ -28,8 +28,6 @@ __init int yamon_dt_append_cmdline(void *fdt)
 	/* find or add chosen node */
 	chosen_off = fdt_path_offset(fdt, "/chosen");
 	if (chosen_off == -FDT_ERR_NOTFOUND)
-		chosen_off = fdt_path_offset(fdt, "/chosen@0");
-	if (chosen_off == -FDT_ERR_NOTFOUND)
 		chosen_off = fdt_add_subnode(fdt, 0, "chosen");
 	if (chosen_off < 0) {
 		pr_err("Unable to find or add DT chosen node: %d\n",
@@ -221,8 +219,6 @@ __init int yamon_dt_serial_config(void *fdt)
 	/* find or add chosen node */
 	chosen_off = fdt_path_offset(fdt, "/chosen");
 	if (chosen_off == -FDT_ERR_NOTFOUND)
-		chosen_off = fdt_path_offset(fdt, "/chosen@0");
-	if (chosen_off == -FDT_ERR_NOTFOUND)
 		chosen_off = fdt_add_subnode(fdt, 0, "chosen");
 	if (chosen_off < 0) {
 		pr_err("Unable to find or add DT chosen node: %d\n",
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 45d541baf359..58351e48421e 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -8,6 +8,7 @@ generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += msi.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 0ab176bdb8e8..0269b3de8b51 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -22,6 +22,17 @@
 #include <asm/cmpxchg.h>
 #include <asm/war.h>
 
+/*
+ * Using a branch-likely instruction to check the result of an sc instruction
+ * works around a bug present in R10000 CPUs prior to revision 3.0 that could
+ * cause ll-sc sequences to execute non-atomically.
+ */
+#if R10000_LLSC_WAR
+# define __scbeqz "beqzl"
+#else
+# define __scbeqz "beqz"
+#endif
+
 #define ATOMIC_INIT(i)	  { (i) }
 
 /*
@@ -44,31 +55,18 @@
 #define ATOMIC_OP(op, c_op, asm_op)					      \
 static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 {									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	ll	%0, %1		# atomic_" #op "	\n"   \
 		"	" #asm_op " %0, %2				\n"   \
 		"	sc	%0, %1					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		int temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	ll	%0, %1		# atomic_" #op "\n"   \
-			"	" #asm_op " %0, %2			\n"   \
-			"	sc	%0, %1				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)  \
-			: "Ir" (i));					      \
-		} while (unlikely(!temp));				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -83,36 +81,20 @@ static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v)	      \
 {									      \
 	int result;							      \
 									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	ll	%1, %2		# atomic_" #op "_return	\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	sc	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		int temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	ll	%1, %2	# atomic_" #op "_return	\n"   \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	sc	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i));					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp; result c_op i;				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -131,36 +113,20 @@ static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v)	      \
 {									      \
 	int result;							      \
 									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	ll	%1, %2		# atomic_fetch_" #op "	\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	sc	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	move	%0, %1					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		int temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	ll	%1, %2	# atomic_fetch_" #op "	\n"   \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	sc	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i));					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp;						      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -218,38 +184,17 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 
 	smp_mb__before_llsc();
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		int temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
-		"	subu	%0, %1, %3				\n"
-		"	bltz	%0, 1f					\n"
-		"	sc	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqzl	%0, 1b					\n"
-		"	 subu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
-		"1:							\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
-		: "memory");
-	} else if (kernel_uses_llsc) {
+	if (kernel_uses_llsc) {
 		int temp;
 
 		__asm__ __volatile__(
 		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
 		"	subu	%0, %1, %3				\n"
+		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
-		"	sc	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqz	%0, 1b					\n"
-		"	 subu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
+		"	sc	%1, %2					\n"
+		"\t" __scbeqz "	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
@@ -274,97 +219,12 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-
-/*
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-/*
- * atomic_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-
 /*
  * atomic_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
  */
 #define atomic_dec_if_positive(v)	atomic_sub_if_positive(1, v)
 
-/*
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1, (v))
-
-/*
- * atomic_dec - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1, (v))
-
-/*
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
 #ifdef CONFIG_64BIT
 
 #define ATOMIC64_INIT(i)    { (i) }
@@ -386,31 +246,18 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 #define ATOMIC64_OP(op, c_op, asm_op)					      \
 static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 {									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	lld	%0, %1		# atomic64_" #op "	\n"   \
 		"	" #asm_op " %0, %2				\n"   \
 		"	scd	%0, %1					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		long temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	lld	%0, %1		# atomic64_" #op "\n" \
-			"	" #asm_op " %0, %2			\n"   \
-			"	scd	%0, %1				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
-			: "Ir" (i));					      \
-		} while (unlikely(!temp));				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -425,37 +272,20 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
 {									      \
 	long result;							      \
 									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	lld	%1, %2		# atomic64_" #op "_return\n"  \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	scd	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		long temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	lld	%1, %2	# atomic64_" #op "_return\n"  \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	scd	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
-			: "memory");					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp; result c_op i;				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -478,33 +308,16 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)  \
 		long temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	lld	%1, %2		# atomic64_fetch_" #op "\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	scd	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	move	%0, %1					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		long temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	lld	%1, %2	# atomic64_fetch_" #op "\n"   \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	scd	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
-			: "memory");					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp;						      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -563,38 +376,17 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 
 	smp_mb__before_llsc();
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		long temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	bltz	%0, 1f					\n"
-		"	scd	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqzl	%0, 1b					\n"
-		"	 dsubu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
-		"1:							\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp),
-		  "=" GCC_OFF_SMALL_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
-		: "memory");
-	} else if (kernel_uses_llsc) {
+	if (kernel_uses_llsc) {
 		long temp;
 
 		__asm__ __volatile__(
 		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
 		"	dsubu	%0, %1, %3				\n"
+		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
-		"	scd	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqz	%0, 1b					\n"
-		"	 dsubu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
+		"	scd	%1, %2					\n"
+		"\t" __scbeqz "	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
@@ -620,99 +412,12 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1, (v))
-
-/*
- * atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0)
-
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-/*
- * atomic64_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic64_t
  */
 #define atomic64_dec_if_positive(v)	atomic64_sub_if_positive(1, v)
 
-/*
- * atomic64_inc - increment atomic variable
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic64_inc(v) atomic64_add(1, (v))
-
-/*
- * atomic64_dec - decrement and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic64_dec(v) atomic64_sub(1, (v))
-
-/*
- * atomic64_add_negative - add and test if negative
- * @v: pointer of type atomic64_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0)
-
 #endif /* CONFIG_64BIT */
 
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h
index b3e2975f83d3..bf6a8afd7ad2 100644
--- a/arch/mips/include/asm/bmips.h
+++ b/arch/mips/include/asm/bmips.h
@@ -123,22 +123,6 @@ static inline void bmips_write_zscm_reg(unsigned int offset, unsigned long data)
 	barrier();
 }
 
-static inline void bmips_post_dma_flush(struct device *dev)
-{
-	void __iomem *cbr = BMIPS_GET_CBR();
-	u32 cfg;
-
-	if (boot_cpu_type() != CPU_BMIPS3300 &&
-	    boot_cpu_type() != CPU_BMIPS4350 &&
-	    boot_cpu_type() != CPU_BMIPS4380)
-		return;
-
-	/* Flush stale data out of the readahead cache */
-	cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
-	__raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG);
-	__raw_readl(cbr + BMIPS_RAC_CONFIG);
-}
-
 #endif /* !defined(__ASSEMBLY__) */
 
 #endif /* _ASM_BMIPS_H */
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 9cdb4e4ce258..0edba3e75747 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -14,39 +14,77 @@
 #include <asm/isa-rev.h>
 #include <cpu-feature-overrides.h>
 
+#define __ase(ase)			(cpu_data[0].ases & (ase))
+#define __opt(opt)			(cpu_data[0].options & (opt))
+
+/*
+ * Check if MIPS_ISA_REV is >= isa *and* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * Note that these should only be used in cases where a kernel built for an
+ * older ISA *cannot* run on a CPU which supports the feature in question. For
+ * example this may be used for features introduced with MIPSr6, since a kernel
+ * built for an older ISA cannot run on a MIPSr6 CPU. This should not be used
+ * for MIPSr2 features however, since a MIPSr1 or earlier kernel might run on a
+ * MIPSr2 CPU.
+ */
+#define __isa_ge_and_ase(isa, ase)	((MIPS_ISA_REV >= (isa)) && __ase(ase))
+#define __isa_ge_and_opt(isa, opt)	((MIPS_ISA_REV >= (isa)) && __opt(opt))
+
+/*
+ * Check if MIPS_ISA_REV is >= isa *or* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * These are for use with features that are optional up until a particular ISA
+ * revision & then become required.
+ */
+#define __isa_ge_or_ase(isa, ase)	((MIPS_ISA_REV >= (isa)) || __ase(ase))
+#define __isa_ge_or_opt(isa, opt)	((MIPS_ISA_REV >= (isa)) || __opt(opt))
+
+/*
+ * Check if MIPS_ISA_REV is < isa *and* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * These are for use with features that are optional up until a particular ISA
+ * revision & are then removed - ie. no longer present in any CPU implementing
+ * the given ISA revision.
+ */
+#define __isa_lt_and_ase(isa, ase)	((MIPS_ISA_REV < (isa)) && __ase(ase))
+#define __isa_lt_and_opt(isa, opt)	((MIPS_ISA_REV < (isa)) && __opt(opt))
+
 /*
  * SMP assumption: Options of CPU 0 are a superset of all processors.
  * This is true for all known MIPS systems.
  */
 #ifndef cpu_has_tlb
-#define cpu_has_tlb		(cpu_data[0].options & MIPS_CPU_TLB)
+#define cpu_has_tlb		__opt(MIPS_CPU_TLB)
 #endif
 #ifndef cpu_has_ftlb
-#define cpu_has_ftlb		(cpu_data[0].options & MIPS_CPU_FTLB)
+#define cpu_has_ftlb		__opt(MIPS_CPU_FTLB)
 #endif
 #ifndef cpu_has_tlbinv
-#define cpu_has_tlbinv		(cpu_data[0].options & MIPS_CPU_TLBINV)
+#define cpu_has_tlbinv		__opt(MIPS_CPU_TLBINV)
 #endif
 #ifndef cpu_has_segments
-#define cpu_has_segments	(cpu_data[0].options & MIPS_CPU_SEGMENTS)
+#define cpu_has_segments	__opt(MIPS_CPU_SEGMENTS)
 #endif
 #ifndef cpu_has_eva
-#define cpu_has_eva		(cpu_data[0].options & MIPS_CPU_EVA)
+#define cpu_has_eva		__opt(MIPS_CPU_EVA)
 #endif
 #ifndef cpu_has_htw
-#define cpu_has_htw		(cpu_data[0].options & MIPS_CPU_HTW)
+#define cpu_has_htw		__opt(MIPS_CPU_HTW)
 #endif
 #ifndef cpu_has_ldpte
-#define cpu_has_ldpte		(cpu_data[0].options & MIPS_CPU_LDPTE)
+#define cpu_has_ldpte		__opt(MIPS_CPU_LDPTE)
 #endif
 #ifndef cpu_has_rixiex
-#define cpu_has_rixiex		(cpu_data[0].options & MIPS_CPU_RIXIEX)
+#define cpu_has_rixiex		__isa_ge_or_opt(6, MIPS_CPU_RIXIEX)
 #endif
 #ifndef cpu_has_maar
-#define cpu_has_maar		(cpu_data[0].options & MIPS_CPU_MAAR)
+#define cpu_has_maar		__opt(MIPS_CPU_MAAR)
 #endif
 #ifndef cpu_has_rw_llb
-#define cpu_has_rw_llb		(cpu_data[0].options & MIPS_CPU_RW_LLB)
+#define cpu_has_rw_llb		__isa_ge_or_opt(6, MIPS_CPU_RW_LLB)
 #endif
 
 /*
@@ -59,18 +97,18 @@
 #define cpu_has_3kex		(!cpu_has_4kex)
 #endif
 #ifndef cpu_has_4kex
-#define cpu_has_4kex		(cpu_data[0].options & MIPS_CPU_4KEX)
+#define cpu_has_4kex		__isa_ge_or_opt(1, MIPS_CPU_4KEX)
 #endif
 #ifndef cpu_has_3k_cache
-#define cpu_has_3k_cache	(cpu_data[0].options & MIPS_CPU_3K_CACHE)
+#define cpu_has_3k_cache	__isa_lt_and_opt(1, MIPS_CPU_3K_CACHE)
 #endif
 #define cpu_has_6k_cache	0
 #define cpu_has_8k_cache	0
 #ifndef cpu_has_4k_cache
-#define cpu_has_4k_cache	(cpu_data[0].options & MIPS_CPU_4K_CACHE)
+#define cpu_has_4k_cache	__isa_ge_or_opt(1, MIPS_CPU_4K_CACHE)
 #endif
 #ifndef cpu_has_tx39_cache
-#define cpu_has_tx39_cache	(cpu_data[0].options & MIPS_CPU_TX39_CACHE)
+#define cpu_has_tx39_cache	__opt(MIPS_CPU_TX39_CACHE)
 #endif
 #ifndef cpu_has_octeon_cache
 #define cpu_has_octeon_cache	0
@@ -83,92 +121,92 @@
 #define raw_cpu_has_fpu		cpu_has_fpu
 #endif
 #ifndef cpu_has_32fpr
-#define cpu_has_32fpr		(cpu_data[0].options & MIPS_CPU_32FPR)
+#define cpu_has_32fpr		__isa_ge_or_opt(1, MIPS_CPU_32FPR)
 #endif
 #ifndef cpu_has_counter
-#define cpu_has_counter		(cpu_data[0].options & MIPS_CPU_COUNTER)
+#define cpu_has_counter		__opt(MIPS_CPU_COUNTER)
 #endif
 #ifndef cpu_has_watch
-#define cpu_has_watch		(cpu_data[0].options & MIPS_CPU_WATCH)
+#define cpu_has_watch		__opt(MIPS_CPU_WATCH)
 #endif
 #ifndef cpu_has_divec
-#define cpu_has_divec		(cpu_data[0].options & MIPS_CPU_DIVEC)
+#define cpu_has_divec		__isa_ge_or_opt(1, MIPS_CPU_DIVEC)
 #endif
 #ifndef cpu_has_vce
-#define cpu_has_vce		(cpu_data[0].options & MIPS_CPU_VCE)
+#define cpu_has_vce		__opt(MIPS_CPU_VCE)
 #endif
 #ifndef cpu_has_cache_cdex_p
-#define cpu_has_cache_cdex_p	(cpu_data[0].options & MIPS_CPU_CACHE_CDEX_P)
+#define cpu_has_cache_cdex_p	__opt(MIPS_CPU_CACHE_CDEX_P)
 #endif
 #ifndef cpu_has_cache_cdex_s
-#define cpu_has_cache_cdex_s	(cpu_data[0].options & MIPS_CPU_CACHE_CDEX_S)
+#define cpu_has_cache_cdex_s	__opt(MIPS_CPU_CACHE_CDEX_S)
 #endif
 #ifndef cpu_has_prefetch
-#define cpu_has_prefetch	(cpu_data[0].options & MIPS_CPU_PREFETCH)
+#define cpu_has_prefetch	__isa_ge_or_opt(1, MIPS_CPU_PREFETCH)
 #endif
 #ifndef cpu_has_mcheck
-#define cpu_has_mcheck		(cpu_data[0].options & MIPS_CPU_MCHECK)
+#define cpu_has_mcheck		__isa_ge_or_opt(1, MIPS_CPU_MCHECK)
 #endif
 #ifndef cpu_has_ejtag
-#define cpu_has_ejtag		(cpu_data[0].options & MIPS_CPU_EJTAG)
+#define cpu_has_ejtag		__opt(MIPS_CPU_EJTAG)
 #endif
 #ifndef cpu_has_llsc
-#define cpu_has_llsc		(cpu_data[0].options & MIPS_CPU_LLSC)
+#define cpu_has_llsc		__isa_ge_or_opt(1, MIPS_CPU_LLSC)
 #endif
 #ifndef cpu_has_bp_ghist
-#define cpu_has_bp_ghist	(cpu_data[0].options & MIPS_CPU_BP_GHIST)
+#define cpu_has_bp_ghist	__opt(MIPS_CPU_BP_GHIST)
 #endif
 #ifndef kernel_uses_llsc
 #define kernel_uses_llsc	cpu_has_llsc
 #endif
 #ifndef cpu_has_guestctl0ext
-#define cpu_has_guestctl0ext	(cpu_data[0].options & MIPS_CPU_GUESTCTL0EXT)
+#define cpu_has_guestctl0ext	__opt(MIPS_CPU_GUESTCTL0EXT)
 #endif
 #ifndef cpu_has_guestctl1
-#define cpu_has_guestctl1	(cpu_data[0].options & MIPS_CPU_GUESTCTL1)
+#define cpu_has_guestctl1	__opt(MIPS_CPU_GUESTCTL1)
 #endif
 #ifndef cpu_has_guestctl2
-#define cpu_has_guestctl2	(cpu_data[0].options & MIPS_CPU_GUESTCTL2)
+#define cpu_has_guestctl2	__opt(MIPS_CPU_GUESTCTL2)
 #endif
 #ifndef cpu_has_guestid
-#define cpu_has_guestid		(cpu_data[0].options & MIPS_CPU_GUESTID)
+#define cpu_has_guestid		__opt(MIPS_CPU_GUESTID)
 #endif
 #ifndef cpu_has_drg
-#define cpu_has_drg		(cpu_data[0].options & MIPS_CPU_DRG)
+#define cpu_has_drg		__opt(MIPS_CPU_DRG)
 #endif
 #ifndef cpu_has_mips16
-#define cpu_has_mips16		(cpu_data[0].ases & MIPS_ASE_MIPS16)
+#define cpu_has_mips16		__isa_lt_and_ase(6, MIPS_ASE_MIPS16)
 #endif
 #ifndef cpu_has_mips16e2
-#define cpu_has_mips16e2	(cpu_data[0].ases & MIPS_ASE_MIPS16E2)
+#define cpu_has_mips16e2	__isa_lt_and_ase(6, MIPS_ASE_MIPS16E2)
 #endif
 #ifndef cpu_has_mdmx
-#define cpu_has_mdmx		(cpu_data[0].ases & MIPS_ASE_MDMX)
+#define cpu_has_mdmx		__isa_lt_and_ase(6, MIPS_ASE_MDMX)
 #endif
 #ifndef cpu_has_mips3d
-#define cpu_has_mips3d		(cpu_data[0].ases & MIPS_ASE_MIPS3D)
+#define cpu_has_mips3d		__isa_lt_and_ase(6, MIPS_ASE_MIPS3D)
 #endif
 #ifndef cpu_has_smartmips
-#define cpu_has_smartmips	(cpu_data[0].ases & MIPS_ASE_SMARTMIPS)
+#define cpu_has_smartmips	__isa_lt_and_ase(6, MIPS_ASE_SMARTMIPS)
 #endif
 
 #ifndef cpu_has_rixi
-#define cpu_has_rixi		(cpu_data[0].options & MIPS_CPU_RIXI)
+#define cpu_has_rixi		__isa_ge_or_opt(6, MIPS_CPU_RIXI)
 #endif
 
 #ifndef cpu_has_mmips
 # ifdef CONFIG_SYS_SUPPORTS_MICROMIPS
-#  define cpu_has_mmips		(cpu_data[0].options & MIPS_CPU_MICROMIPS)
+#  define cpu_has_mmips		__opt(MIPS_CPU_MICROMIPS)
 # else
 #  define cpu_has_mmips		0
 # endif
 #endif
 
 #ifndef cpu_has_lpa
-#define cpu_has_lpa		(cpu_data[0].options & MIPS_CPU_LPA)
+#define cpu_has_lpa		__opt(MIPS_CPU_LPA)
 #endif
 #ifndef cpu_has_mvh
-#define cpu_has_mvh		(cpu_data[0].options & MIPS_CPU_MVH)
+#define cpu_has_mvh		__opt(MIPS_CPU_MVH)
 #endif
 #ifndef cpu_has_xpa
 #define cpu_has_xpa		(cpu_has_lpa && cpu_has_mvh)
@@ -338,32 +376,32 @@
 #endif
 
 #ifndef cpu_has_dsp
-#define cpu_has_dsp		(cpu_data[0].ases & MIPS_ASE_DSP)
+#define cpu_has_dsp		__ase(MIPS_ASE_DSP)
 #endif
 
 #ifndef cpu_has_dsp2
-#define cpu_has_dsp2		(cpu_data[0].ases & MIPS_ASE_DSP2P)
+#define cpu_has_dsp2		__ase(MIPS_ASE_DSP2P)
 #endif
 
 #ifndef cpu_has_dsp3
-#define cpu_has_dsp3		(cpu_data[0].ases & MIPS_ASE_DSP3)
+#define cpu_has_dsp3		__ase(MIPS_ASE_DSP3)
 #endif
 
 #ifndef cpu_has_mipsmt
-#define cpu_has_mipsmt		(cpu_data[0].ases & MIPS_ASE_MIPSMT)
+#define cpu_has_mipsmt		__isa_lt_and_ase(6, MIPS_ASE_MIPSMT)
 #endif
 
 #ifndef cpu_has_vp
-#define cpu_has_vp		(cpu_data[0].options & MIPS_CPU_VP)
+#define cpu_has_vp		__isa_ge_and_opt(6, MIPS_CPU_VP)
 #endif
 
 #ifndef cpu_has_userlocal
-#define cpu_has_userlocal	(cpu_data[0].options & MIPS_CPU_ULRI)
+#define cpu_has_userlocal	__isa_ge_or_opt(6, MIPS_CPU_ULRI)
 #endif
 
 #ifdef CONFIG_32BIT
 # ifndef cpu_has_nofpuex
-# define cpu_has_nofpuex	(cpu_data[0].options & MIPS_CPU_NOFPUEX)
+# define cpu_has_nofpuex	__isa_lt_and_opt(1, MIPS_CPU_NOFPUEX)
 # endif
 # ifndef cpu_has_64bits
 # define cpu_has_64bits		(cpu_data[0].isa_level & MIPS_CPU_ISA_64BIT)
@@ -405,19 +443,19 @@
 #endif
 
 #if defined(CONFIG_CPU_MIPSR2_IRQ_VI) && !defined(cpu_has_vint)
-# define cpu_has_vint		(cpu_data[0].options & MIPS_CPU_VINT)
+# define cpu_has_vint		__opt(MIPS_CPU_VINT)
 #elif !defined(cpu_has_vint)
 # define cpu_has_vint			0
 #endif
 
 #if defined(CONFIG_CPU_MIPSR2_IRQ_EI) && !defined(cpu_has_veic)
-# define cpu_has_veic		(cpu_data[0].options & MIPS_CPU_VEIC)
+# define cpu_has_veic		__opt(MIPS_CPU_VEIC)
 #elif !defined(cpu_has_veic)
 # define cpu_has_veic			0
 #endif
 
 #ifndef cpu_has_inclusive_pcaches
-#define cpu_has_inclusive_pcaches	(cpu_data[0].options & MIPS_CPU_INCLUSIVE_CACHES)
+#define cpu_has_inclusive_pcaches	__opt(MIPS_CPU_INCLUSIVE_CACHES)
 #endif
 
 #ifndef cpu_dcache_line_size
@@ -438,63 +476,63 @@
 #endif
 
 #ifndef cpu_has_perf_cntr_intr_bit
-#define cpu_has_perf_cntr_intr_bit	(cpu_data[0].options & MIPS_CPU_PCI)
+#define cpu_has_perf_cntr_intr_bit	__opt(MIPS_CPU_PCI)
 #endif
 
 #ifndef cpu_has_vz
-#define cpu_has_vz		(cpu_data[0].ases & MIPS_ASE_VZ)
+#define cpu_has_vz		__ase(MIPS_ASE_VZ)
 #endif
 
 #if defined(CONFIG_CPU_HAS_MSA) && !defined(cpu_has_msa)
-# define cpu_has_msa		(cpu_data[0].ases & MIPS_ASE_MSA)
+# define cpu_has_msa		__ase(MIPS_ASE_MSA)
 #elif !defined(cpu_has_msa)
 # define cpu_has_msa		0
 #endif
 
 #ifndef cpu_has_ufr
-# define cpu_has_ufr		(cpu_data[0].options & MIPS_CPU_UFR)
+# define cpu_has_ufr		__opt(MIPS_CPU_UFR)
 #endif
 
 #ifndef cpu_has_fre
-# define cpu_has_fre		(cpu_data[0].options & MIPS_CPU_FRE)
+# define cpu_has_fre		__opt(MIPS_CPU_FRE)
 #endif
 
 #ifndef cpu_has_cdmm
-# define cpu_has_cdmm		(cpu_data[0].options & MIPS_CPU_CDMM)
+# define cpu_has_cdmm		__opt(MIPS_CPU_CDMM)
 #endif
 
 #ifndef cpu_has_small_pages
-# define cpu_has_small_pages	(cpu_data[0].options & MIPS_CPU_SP)
+# define cpu_has_small_pages	__opt(MIPS_CPU_SP)
 #endif
 
 #ifndef cpu_has_nan_legacy
-#define cpu_has_nan_legacy	(cpu_data[0].options & MIPS_CPU_NAN_LEGACY)
+#define cpu_has_nan_legacy	__isa_lt_and_opt(6, MIPS_CPU_NAN_LEGACY)
 #endif
 #ifndef cpu_has_nan_2008
-#define cpu_has_nan_2008	(cpu_data[0].options & MIPS_CPU_NAN_2008)
+#define cpu_has_nan_2008	__isa_ge_or_opt(6, MIPS_CPU_NAN_2008)
 #endif
 
 #ifndef cpu_has_ebase_wg
-# define cpu_has_ebase_wg	(cpu_data[0].options & MIPS_CPU_EBASE_WG)
+# define cpu_has_ebase_wg	__opt(MIPS_CPU_EBASE_WG)
 #endif
 
 #ifndef cpu_has_badinstr
-# define cpu_has_badinstr	(cpu_data[0].options & MIPS_CPU_BADINSTR)
+# define cpu_has_badinstr	__isa_ge_or_opt(6, MIPS_CPU_BADINSTR)
 #endif
 
 #ifndef cpu_has_badinstrp
-# define cpu_has_badinstrp	(cpu_data[0].options & MIPS_CPU_BADINSTRP)
+# define cpu_has_badinstrp	__isa_ge_or_opt(6, MIPS_CPU_BADINSTRP)
 #endif
 
 #ifndef cpu_has_contextconfig
-# define cpu_has_contextconfig	(cpu_data[0].options & MIPS_CPU_CTXTC)
+# define cpu_has_contextconfig	__opt(MIPS_CPU_CTXTC)
 #endif
 
 #ifndef cpu_has_perf
-# define cpu_has_perf		(cpu_data[0].options & MIPS_CPU_PERF)
+# define cpu_has_perf		__opt(MIPS_CPU_PERF)
 #endif
 
-#if defined(CONFIG_SMP) && (MIPS_ISA_REV >= 6)
+#ifdef CONFIG_SMP
 /*
  * Some systems share FTLB RAMs between threads within a core (siblings in
  * kernel parlance). This means that FTLB entries may become invalid at almost
@@ -507,7 +545,7 @@
  */
 # ifndef cpu_has_shared_ftlb_ram
 #  define cpu_has_shared_ftlb_ram \
-	(current_cpu_data.options & MIPS_CPU_SHARED_FTLB_RAM)
+	__isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_RAM)
 # endif
 
 /*
@@ -524,9 +562,9 @@
  */
 # ifndef cpu_has_shared_ftlb_entries
 #  define cpu_has_shared_ftlb_entries \
-	(current_cpu_data.options & MIPS_CPU_SHARED_FTLB_ENTRIES)
+	__isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_ENTRIES)
 # endif
-#endif /* SMP && MIPS_ISA_REV >= 6 */
+#endif /* SMP */
 
 #ifndef cpu_has_shared_ftlb_ram
 # define cpu_has_shared_ftlb_ram 0
@@ -537,7 +575,7 @@
 
 #ifdef CONFIG_MIPS_MT_SMP
 # define cpu_has_mipsmt_pertccounters \
-	(cpu_data[0].options & MIPS_CPU_MT_PER_TC_PERF_COUNTERS)
+	__isa_lt_and_opt(6, MIPS_CPU_MT_PER_TC_PERF_COUNTERS)
 #else
 # define cpu_has_mipsmt_pertccounters 0
 #endif /* CONFIG_MIPS_MT_SMP */
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 5b9d02ef4f60..dacbdb84516a 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -225,31 +225,32 @@
  * Definitions for 7:0 on legacy processors
  */
 
-#define PRID_REV_TX4927		0x0022
-#define PRID_REV_TX4937		0x0030
-#define PRID_REV_R4400		0x0040
-#define PRID_REV_R3000A		0x0030
-#define PRID_REV_R3000		0x0020
-#define PRID_REV_R2000A		0x0010
-#define PRID_REV_TX3912		0x0010
-#define PRID_REV_TX3922		0x0030
-#define PRID_REV_TX3927		0x0040
-#define PRID_REV_VR4111		0x0050
-#define PRID_REV_VR4181		0x0050	/* Same as VR4111 */
-#define PRID_REV_VR4121		0x0060
-#define PRID_REV_VR4122		0x0070
-#define PRID_REV_VR4181A	0x0070	/* Same as VR4122 */
-#define PRID_REV_VR4130		0x0080
-#define PRID_REV_34K_V1_0_2	0x0022
-#define PRID_REV_LOONGSON1B	0x0020
-#define PRID_REV_LOONGSON1C	0x0020	/* Same as Loongson-1B */
-#define PRID_REV_LOONGSON2E	0x0002
-#define PRID_REV_LOONGSON2F	0x0003
-#define PRID_REV_LOONGSON3A_R1	0x0005
-#define PRID_REV_LOONGSON3B_R1	0x0006
-#define PRID_REV_LOONGSON3B_R2	0x0007
-#define PRID_REV_LOONGSON3A_R2	0x0008
-#define PRID_REV_LOONGSON3A_R3	0x0009
+#define PRID_REV_TX4927			0x0022
+#define PRID_REV_TX4937			0x0030
+#define PRID_REV_R4400			0x0040
+#define PRID_REV_R3000A			0x0030
+#define PRID_REV_R3000			0x0020
+#define PRID_REV_R2000A			0x0010
+#define PRID_REV_TX3912			0x0010
+#define PRID_REV_TX3922			0x0030
+#define PRID_REV_TX3927			0x0040
+#define PRID_REV_VR4111			0x0050
+#define PRID_REV_VR4181			0x0050	/* Same as VR4111 */
+#define PRID_REV_VR4121			0x0060
+#define PRID_REV_VR4122			0x0070
+#define PRID_REV_VR4181A		0x0070	/* Same as VR4122 */
+#define PRID_REV_VR4130			0x0080
+#define PRID_REV_34K_V1_0_2		0x0022
+#define PRID_REV_LOONGSON1B		0x0020
+#define PRID_REV_LOONGSON1C		0x0020	/* Same as Loongson-1B */
+#define PRID_REV_LOONGSON2E		0x0002
+#define PRID_REV_LOONGSON2F		0x0003
+#define PRID_REV_LOONGSON3A_R1		0x0005
+#define PRID_REV_LOONGSON3B_R1		0x0006
+#define PRID_REV_LOONGSON3B_R2		0x0007
+#define PRID_REV_LOONGSON3A_R2		0x0008
+#define PRID_REV_LOONGSON3A_R3_0	0x0009
+#define PRID_REV_LOONGSON3A_R3_1	0x000d
 
 /*
  * Older processors used to encode processor version and revision in two
diff --git a/arch/mips/include/asm/dma-coherence.h b/arch/mips/include/asm/dma-coherence.h
index 72d0eab02afc..8eda48748ed5 100644
--- a/arch/mips/include/asm/dma-coherence.h
+++ b/arch/mips/include/asm/dma-coherence.h
@@ -21,10 +21,10 @@ enum coherent_io_user_state {
 extern enum coherent_io_user_state coherentio;
 extern int hw_coherentio;
 #else
-#ifdef CONFIG_DMA_COHERENT
-#define coherentio	IO_COHERENCE_ENABLED
-#else
+#ifdef CONFIG_DMA_NONCOHERENT
 #define coherentio	IO_COHERENCE_DISABLED
+#else
+#define coherentio	IO_COHERENCE_ENABLED
 #endif
 #define hw_coherentio	0
 #endif /* CONFIG_DMA_MAYBE_COHERENT */
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index f32f15530aba..b5c240806e1b 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -1 +1,16 @@
-#include <asm/dma-coherence.h>
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MIPS_DMA_DIRECT_H
+#define _MIPS_DMA_DIRECT_H 1
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return false;
+
+	return addr + size - 1 <= *dev->dma_mask;
+}
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
+
+#endif /* _MIPS_DMA_DIRECT_H */
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 886e75a383f2..e81c4e97ff1a 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -2,19 +2,21 @@
 #ifndef _ASM_DMA_MAPPING_H
 #define _ASM_DMA_MAPPING_H
 
-#include <linux/scatterlist.h>
-#include <asm/dma-coherence.h>
-#include <asm/cache.h>
+#include <linux/swiotlb.h>
 
-#ifndef CONFIG_SGI_IP27 /* Kludge to fix 2.6.39 build for IP27 */
-#include <dma-coherence.h>
-#endif
-
-extern const struct dma_map_ops *mips_dma_map_ops;
+extern const struct dma_map_ops jazz_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return mips_dma_map_ops;
+#if defined(CONFIG_MACH_JAZZ)
+	return &jazz_dma_ops;
+#elif defined(CONFIG_SWIOTLB)
+	return &swiotlb_dma_ops;
+#elif defined(CONFIG_DMA_NONCOHERENT_OPS)
+	return &dma_noncoherent_ops;
+#else
+	return &dma_direct_ops;
+#endif
 }
 
 #define arch_setup_dma_ops arch_setup_dma_ops
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index cea8ad864b3f..54c730aed327 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -12,6 +12,8 @@
 #ifndef _ASM_IO_H
 #define _ASM_IO_H
 
+#define ARCH_HAS_IOREMAP_WC
+
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -141,14 +143,14 @@ static inline void * phys_to_virt(unsigned long address)
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
  */
-static inline unsigned long isa_virt_to_bus(volatile void * address)
+static inline unsigned long isa_virt_to_bus(volatile void *address)
 {
-	return (unsigned long)address - PAGE_OFFSET;
+	return virt_to_phys(address);
 }
 
-static inline void * isa_bus_to_virt(unsigned long address)
+static inline void *isa_bus_to_virt(unsigned long address)
 {
-	return (void *)(address + PAGE_OFFSET);
+	return phys_to_virt(address);
 }
 
 #define isa_page_to_bus page_to_phys
@@ -278,15 +280,25 @@ static inline void __iomem * __ioremap_mode(phys_addr_t offset, unsigned long si
 #define ioremap_cache ioremap_cachable
 
 /*
- * These two are MIPS specific ioremap variant.	 ioremap_cacheable_cow
- * requests a cachable mapping, ioremap_uncached_accelerated requests a
- * mapping using the uncached accelerated mode which isn't supported on
- * all processors.
+ * ioremap_wc     -   map bus memory into CPU space
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap_wc performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked uncachable
+ * but accelerated by means of write-combining feature. It is specifically
+ * useful for PCIe prefetchable windows, which may vastly improve a
+ * communications performance. If it was determined on boot stage, what
+ * CPU CCA doesn't support UCA, the method shall fall-back to the
+ * _CACHE_UNCACHED option (see cpu_probe() method).
  */
-#define ioremap_cacheable_cow(offset, size)				\
-	__ioremap_mode((offset), (size), _CACHE_CACHABLE_COW)
-#define ioremap_uncached_accelerated(offset, size)			\
-	__ioremap_mode((offset), (size), _CACHE_UNCACHED_ACCELERATED)
+#define ioremap_wc(offset, size)					\
+	__ioremap_mode((offset), (size), boot_cpu_data.writecombine)
 
 static inline void iounmap(const volatile void __iomem *addr)
 {
@@ -590,7 +602,7 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int
  *
  * This API used to be exported; it now is for arch code internal use only.
  */
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 extern void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
 extern void (*_dma_cache_wback)(unsigned long start, unsigned long size);
@@ -609,7 +621,7 @@ extern void (*_dma_cache_inv)(unsigned long start, unsigned long size);
 #define dma_cache_inv(start,size)	\
 	do { (void) (start); (void) (size); } while (0)
 
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 /*
  * Read a 32-bit register that requires a 64-bit read cycle on the bus.
diff --git a/arch/mips/include/asm/kprobes.h b/arch/mips/include/asm/kprobes.h
index ad1a99948f27..a72dfbf1babb 100644
--- a/arch/mips/include/asm/kprobes.h
+++ b/arch/mips/include/asm/kprobes.h
@@ -68,16 +68,6 @@ struct prev_kprobe {
 	unsigned long saved_epc;
 };
 
-#define MAX_JPROBES_STACK_SIZE 128
-#define MAX_JPROBES_STACK_ADDR \
-	(((unsigned long)current_thread_info()) + THREAD_SIZE - 32 - sizeof(struct pt_regs))
-
-#define MIN_JPROBES_STACK_SIZE(ADDR)					\
-	((((ADDR) + MAX_JPROBES_STACK_SIZE) > MAX_JPROBES_STACK_ADDR)	\
-		? MAX_JPROBES_STACK_ADDR - (ADDR)			\
-		: MAX_JPROBES_STACK_SIZE)
-
-
 #define SKIP_DELAYSLOT 0x0001
 
 /* per-cpu kprobe control block */
@@ -86,12 +76,9 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_old_SR;
 	unsigned long kprobe_saved_SR;
 	unsigned long kprobe_saved_epc;
-	unsigned long jprobe_saved_sp;
-	struct pt_regs jprobe_saved_regs;
 	/* Per-thread fields, used while emulating branches */
 	unsigned long flags;
 	unsigned long target_epc;
-	u8 jprobes_stack[MAX_JPROBES_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/mips/include/asm/mach-ar7/spaces.h b/arch/mips/include/asm/mach-ar7/spaces.h
index 660ab64c0fc9..a004d94dfbdd 100644
--- a/arch/mips/include/asm/mach-ar7/spaces.h
+++ b/arch/mips/include/asm/mach-ar7/spaces.h
@@ -17,9 +17,6 @@
 #define PAGE_OFFSET	_AC(0x94000000, UL)
 #define PHYS_OFFSET	_AC(0x14000000, UL)
 
-#define UNCAC_BASE	_AC(0xb4000000, UL)	/* 0xa0000000 + PHYS_OFFSET */
-#define IO_BASE		UNCAC_BASE
-
 #include <asm/mach-generic/spaces.h>
 
 #endif /* __ASM_AR7_SPACES_H */
diff --git a/arch/mips/include/asm/mach-ath25/dma-coherence.h b/arch/mips/include/asm/mach-ath25/dma-coherence.h
deleted file mode 100644
index d5defdde32db..000000000000
--- a/arch/mips/include/asm/mach-ath25/dma-coherence.h
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2007  Felix Fietkau <nbd@openwrt.org>
- *
- */
-#ifndef __ASM_MACH_ATH25_DMA_COHERENCE_H
-#define __ASM_MACH_ATH25_DMA_COHERENCE_H
-
-#include <linux/device.h>
-
-/*
- * We need some arbitrary non-zero value to be programmed to the BAR1 register
- * of PCI host controller to enable DMA. The same value should be used as the
- * offset to calculate the physical address of DMA buffer for PCI devices.
- */
-#define AR2315_PCI_HOST_SDRAM_BASEADDR	0x20000000
-
-static inline dma_addr_t ath25_dev_offset(struct device *dev)
-{
-#ifdef CONFIG_PCI
-	extern struct bus_type pci_bus_type;
-
-	if (dev && dev->bus == &pci_bus_type)
-		return AR2315_PCI_HOST_SDRAM_BASEADDR;
-#endif
-	return 0;
-}
-
-static inline dma_addr_t
-plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
-	return virt_to_phys(addr) + ath25_dev_offset(dev);
-}
-
-static inline dma_addr_t
-plat_map_dma_mem_page(struct device *dev, struct page *page)
-{
-	return page_to_phys(page) + ath25_dev_offset(dev);
-}
-
-static inline unsigned long
-plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr - ath25_dev_offset(dev);
-}
-
-static inline void
-plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, size_t size,
-		   enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_COHERENT
-	return 1;
-#endif
-#ifdef CONFIG_DMA_NONCOHERENT
-	return 0;
-#endif
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-#endif /* __ASM_MACH_ATH25_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
index d99ca862dae3..284b4fa23e03 100644
--- a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
+++ b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
@@ -20,6 +20,10 @@
 #include <linux/bitops.h>
 
 #define AR71XX_APB_BASE		0x18000000
+#define AR71XX_GE0_BASE		0x19000000
+#define AR71XX_GE0_SIZE		0x10000
+#define AR71XX_GE1_BASE		0x1a000000
+#define AR71XX_GE1_SIZE		0x10000
 #define AR71XX_EHCI_BASE	0x1b000000
 #define AR71XX_EHCI_SIZE	0x1000
 #define AR71XX_OHCI_BASE	0x1c000000
@@ -39,6 +43,8 @@
 #define AR71XX_PLL_SIZE		0x100
 #define AR71XX_RESET_BASE	(AR71XX_APB_BASE + 0x00060000)
 #define AR71XX_RESET_SIZE	0x100
+#define AR71XX_MII_BASE		(AR71XX_APB_BASE + 0x00070000)
+#define AR71XX_MII_SIZE		0x100
 
 #define AR71XX_PCI_MEM_BASE	0x10000000
 #define AR71XX_PCI_MEM_SIZE	0x07000000
@@ -81,18 +87,39 @@
 
 #define AR933X_UART_BASE	(AR71XX_APB_BASE + 0x00020000)
 #define AR933X_UART_SIZE	0x14
+#define AR933X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define AR933X_GMAC_SIZE	0x04
 #define AR933X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
 #define AR933X_WMAC_SIZE	0x20000
 #define AR933X_EHCI_BASE	0x1b000000
 #define AR933X_EHCI_SIZE	0x1000
 
+#define AR934X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define AR934X_GMAC_SIZE	0x14
 #define AR934X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
 #define AR934X_WMAC_SIZE	0x20000
 #define AR934X_EHCI_BASE	0x1b000000
 #define AR934X_EHCI_SIZE	0x200
+#define AR934X_NFC_BASE		0x1b000200
+#define AR934X_NFC_SIZE		0xb8
 #define AR934X_SRIF_BASE	(AR71XX_APB_BASE + 0x00116000)
 #define AR934X_SRIF_SIZE	0x1000
 
+#define QCA953X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA953X_GMAC_SIZE	0x14
+#define QCA953X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
+#define QCA953X_WMAC_SIZE	0x20000
+#define QCA953X_EHCI_BASE	0x1b000000
+#define QCA953X_EHCI_SIZE	0x200
+#define QCA953X_SRIF_BASE	(AR71XX_APB_BASE + 0x00116000)
+#define QCA953X_SRIF_SIZE	0x1000
+
+#define QCA953X_PCI_CFG_BASE0	0x14000000
+#define QCA953X_PCI_CTRL_BASE0	(AR71XX_APB_BASE + 0x000f0000)
+#define QCA953X_PCI_CRP_BASE0	(AR71XX_APB_BASE + 0x000c0000)
+#define QCA953X_PCI_MEM_BASE0	0x10000000
+#define QCA953X_PCI_MEM_SIZE	0x02000000
+
 #define QCA955X_PCI_MEM_BASE0	0x10000000
 #define QCA955X_PCI_MEM_BASE1	0x12000000
 #define QCA955X_PCI_MEM_SIZE	0x02000000
@@ -106,11 +133,72 @@
 #define QCA955X_PCI_CTRL_BASE1	(AR71XX_APB_BASE + 0x00280000)
 #define QCA955X_PCI_CTRL_SIZE	0x100
 
+#define QCA955X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA955X_GMAC_SIZE	0x40
 #define QCA955X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
 #define QCA955X_WMAC_SIZE	0x20000
 #define QCA955X_EHCI0_BASE	0x1b000000
 #define QCA955X_EHCI1_BASE	0x1b400000
 #define QCA955X_EHCI_SIZE	0x1000
+#define QCA955X_NFC_BASE	0x1b800200
+#define QCA955X_NFC_SIZE	0xb8
+
+#define QCA956X_PCI_MEM_BASE1	0x12000000
+#define QCA956X_PCI_MEM_SIZE	0x02000000
+#define QCA956X_PCI_CFG_BASE1	0x16000000
+#define QCA956X_PCI_CFG_SIZE	0x1000
+#define QCA956X_PCI_CRP_BASE1	(AR71XX_APB_BASE + 0x00250000)
+#define QCA956X_PCI_CRP_SIZE	0x1000
+#define QCA956X_PCI_CTRL_BASE1	(AR71XX_APB_BASE + 0x00280000)
+#define QCA956X_PCI_CTRL_SIZE	0x100
+
+#define QCA956X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
+#define QCA956X_WMAC_SIZE	0x20000
+#define QCA956X_EHCI0_BASE	0x1b000000
+#define QCA956X_EHCI1_BASE	0x1b400000
+#define QCA956X_EHCI_SIZE	0x200
+#define QCA956X_GMAC_SGMII_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA956X_GMAC_SGMII_SIZE	0x64
+#define QCA956X_PLL_BASE	(AR71XX_APB_BASE + 0x00050000)
+#define QCA956X_PLL_SIZE	0x50
+#define QCA956X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA956X_GMAC_SIZE	0x64
+
+/*
+ * Hidden Registers
+ */
+#define QCA956X_MAC_CFG_BASE		0xb9000000
+#define QCA956X_MAC_CFG_SIZE		0x64
+
+#define QCA956X_MAC_CFG1_REG		0x00
+#define QCA956X_MAC_CFG1_SOFT_RST	BIT(31)
+#define QCA956X_MAC_CFG1_RX_RST		BIT(19)
+#define QCA956X_MAC_CFG1_TX_RST		BIT(18)
+#define QCA956X_MAC_CFG1_LOOPBACK	BIT(8)
+#define QCA956X_MAC_CFG1_RX_EN		BIT(2)
+#define QCA956X_MAC_CFG1_TX_EN		BIT(0)
+
+#define QCA956X_MAC_CFG2_REG		0x04
+#define QCA956X_MAC_CFG2_IF_1000	BIT(9)
+#define QCA956X_MAC_CFG2_IF_10_100	BIT(8)
+#define QCA956X_MAC_CFG2_HUGE_FRAME_EN	BIT(5)
+#define QCA956X_MAC_CFG2_LEN_CHECK	BIT(4)
+#define QCA956X_MAC_CFG2_PAD_CRC_EN	BIT(2)
+#define QCA956X_MAC_CFG2_FDX		BIT(0)
+
+#define QCA956X_MAC_MII_MGMT_CFG_REG	0x20
+#define QCA956X_MGMT_CFG_CLK_DIV_20	0x07
+
+#define QCA956X_MAC_FIFO_CFG0_REG	0x48
+#define QCA956X_MAC_FIFO_CFG1_REG	0x4c
+#define QCA956X_MAC_FIFO_CFG2_REG	0x50
+#define QCA956X_MAC_FIFO_CFG3_REG	0x54
+#define QCA956X_MAC_FIFO_CFG4_REG	0x58
+#define QCA956X_MAC_FIFO_CFG5_REG	0x5c
+
+#define QCA956X_DAM_RESET_OFFSET	0xb90001bc
+#define QCA956X_DAM_RESET_SIZE		0x4
+#define QCA956X_INLINE_CHKSUM_ENG	BIT(27)
 
 /*
  * DDR_CTRL block
@@ -149,6 +237,12 @@
 #define AR934X_DDR_REG_FLUSH_PCIE	0xa8
 #define AR934X_DDR_REG_FLUSH_WMAC	0xac
 
+#define QCA953X_DDR_REG_FLUSH_GE0	0x9c
+#define QCA953X_DDR_REG_FLUSH_GE1	0xa0
+#define QCA953X_DDR_REG_FLUSH_USB	0xa4
+#define QCA953X_DDR_REG_FLUSH_PCIE	0xa8
+#define QCA953X_DDR_REG_FLUSH_WMAC	0xac
+
 /*
  * PLL block
  */
@@ -166,9 +260,15 @@
 #define AR71XX_AHB_DIV_SHIFT		20
 #define AR71XX_AHB_DIV_MASK		0x7
 
+#define AR71XX_ETH0_PLL_SHIFT		17
+#define AR71XX_ETH1_PLL_SHIFT		19
+
 #define AR724X_PLL_REG_CPU_CONFIG	0x00
 #define AR724X_PLL_REG_PCIE_CONFIG	0x10
 
+#define AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS	BIT(16)
+#define AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET	BIT(25)
+
 #define AR724X_PLL_FB_SHIFT		0
 #define AR724X_PLL_FB_MASK		0x3ff
 #define AR724X_PLL_REF_DIV_SHIFT	10
@@ -178,6 +278,8 @@
 #define AR724X_DDR_DIV_SHIFT		22
 #define AR724X_DDR_DIV_MASK		0x3
 
+#define AR7242_PLL_REG_ETH0_INT_CLOCK	0x2c
+
 #define AR913X_PLL_REG_CPU_CONFIG	0x00
 #define AR913X_PLL_REG_ETH_CONFIG	0x04
 #define AR913X_PLL_REG_ETH0_INT_CLOCK	0x14
@@ -190,6 +292,9 @@
 #define AR913X_AHB_DIV_SHIFT		19
 #define AR913X_AHB_DIV_MASK		0x1
 
+#define AR913X_ETH0_PLL_SHIFT		20
+#define AR913X_ETH1_PLL_SHIFT		22
+
 #define AR933X_PLL_CPU_CONFIG_REG	0x00
 #define AR933X_PLL_CLOCK_CTRL_REG	0x08
 
@@ -211,6 +316,8 @@
 #define AR934X_PLL_CPU_CONFIG_REG		0x00
 #define AR934X_PLL_DDR_CONFIG_REG		0x04
 #define AR934X_PLL_CPU_DDR_CLK_CTRL_REG		0x08
+#define AR934X_PLL_SWITCH_CLOCK_CONTROL_REG	0x24
+#define AR934X_PLL_ETH_XMII_CONTROL_REG		0x2c
 
 #define AR934X_PLL_CPU_CONFIG_NFRAC_SHIFT	0
 #define AR934X_PLL_CPU_CONFIG_NFRAC_MASK	0x3f
@@ -243,9 +350,52 @@
 #define AR934X_PLL_CPU_DDR_CLK_CTRL_DDRCLK_FROM_DDRPLL	BIT(21)
 #define AR934X_PLL_CPU_DDR_CLK_CTRL_AHBCLK_FROM_DDRPLL	BIT(24)
 
+#define AR934X_PLL_SWITCH_CLOCK_CONTROL_MDIO_CLK_SEL	BIT(6)
+
+#define QCA953X_PLL_CPU_CONFIG_REG		0x00
+#define QCA953X_PLL_DDR_CONFIG_REG		0x04
+#define QCA953X_PLL_CLK_CTRL_REG		0x08
+#define QCA953X_PLL_SWITCH_CLOCK_CONTROL_REG	0x24
+#define QCA953X_PLL_ETH_XMII_CONTROL_REG	0x2c
+#define QCA953X_PLL_ETH_SGMII_CONTROL_REG	0x48
+
+#define QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT	0
+#define QCA953X_PLL_CPU_CONFIG_NFRAC_MASK	0x3f
+#define QCA953X_PLL_CPU_CONFIG_NINT_SHIFT	6
+#define QCA953X_PLL_CPU_CONFIG_NINT_MASK	0x3f
+#define QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT	12
+#define QCA953X_PLL_CPU_CONFIG_REFDIV_MASK	0x1f
+#define QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT	19
+#define QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK	0x7
+
+#define QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT	0
+#define QCA953X_PLL_DDR_CONFIG_NFRAC_MASK	0x3ff
+#define QCA953X_PLL_DDR_CONFIG_NINT_SHIFT	10
+#define QCA953X_PLL_DDR_CONFIG_NINT_MASK	0x3f
+#define QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT	16
+#define QCA953X_PLL_DDR_CONFIG_REFDIV_MASK	0x1f
+#define QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT	23
+#define QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK	0x7
+
+#define QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS		BIT(2)
+#define QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS		BIT(3)
+#define QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS		BIT(4)
+#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT		5
+#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK		0x1f
+#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT		10
+#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK		0x1f
+#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT		15
+#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK		0x1f
+#define QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL		BIT(20)
+#define QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL		BIT(21)
+#define QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL		BIT(24)
+
 #define QCA955X_PLL_CPU_CONFIG_REG		0x00
 #define QCA955X_PLL_DDR_CONFIG_REG		0x04
 #define QCA955X_PLL_CLK_CTRL_REG		0x08
+#define QCA955X_PLL_ETH_XMII_CONTROL_REG	0x28
+#define QCA955X_PLL_ETH_SGMII_CONTROL_REG	0x48
+#define QCA955X_PLL_ETH_SGMII_SERDES_REG	0x4c
 
 #define QCA955X_PLL_CPU_CONFIG_NFRAC_SHIFT	0
 #define QCA955X_PLL_CPU_CONFIG_NFRAC_MASK	0x3f
@@ -278,6 +428,81 @@
 #define QCA955X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL		BIT(21)
 #define QCA955X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL		BIT(24)
 
+#define QCA955X_PLL_ETH_SGMII_SERDES_LOCK_DETECT	BIT(2)
+#define QCA955X_PLL_ETH_SGMII_SERDES_PLL_REFCLK		BIT(1)
+#define QCA955X_PLL_ETH_SGMII_SERDES_EN_PLL		BIT(0)
+
+#define QCA956X_PLL_CPU_CONFIG_REG			0x00
+#define QCA956X_PLL_CPU_CONFIG1_REG			0x04
+#define QCA956X_PLL_DDR_CONFIG_REG			0x08
+#define QCA956X_PLL_DDR_CONFIG1_REG			0x0c
+#define QCA956X_PLL_CLK_CTRL_REG			0x10
+#define QCA956X_PLL_SWITCH_CLOCK_CONTROL_REG		0x28
+#define QCA956X_PLL_ETH_XMII_CONTROL_REG		0x30
+#define QCA956X_PLL_ETH_SGMII_SERDES_REG		0x4c
+
+#define QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT		12
+#define QCA956X_PLL_CPU_CONFIG_REFDIV_MASK		0x1f
+#define QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT		19
+#define QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK		0x7
+
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT		0
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK		0x1f
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT		5
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK		0x1fff
+#define QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT		18
+#define QCA956X_PLL_CPU_CONFIG1_NINT_MASK		0x1ff
+
+#define QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT		16
+#define QCA956X_PLL_DDR_CONFIG_REFDIV_MASK		0x1f
+#define QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT		23
+#define QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK		0x7
+
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT		0
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK		0x1f
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT		5
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK		0x1fff
+#define QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT		18
+#define QCA956X_PLL_DDR_CONFIG1_NINT_MASK		0x1ff
+
+#define QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS		BIT(2)
+#define QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS		BIT(3)
+#define QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS		BIT(4)
+#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT		5
+#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK		0x1f
+#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT		10
+#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK		0x1f
+#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT		15
+#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK		0x1f
+#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL	BIT(20)
+#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL	BIT(21)
+#define QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL		BIT(24)
+
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_I2C_CLK_SELB		BIT(5)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_1		BIT(6)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_UART1_CLK_SEL		BIT(7)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_SHIFT 8
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_MASK	 0xf
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EN_PLL_TOP		BIT(12)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_2		BIT(13)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_1		BIT(14)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_2		BIT(15)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCH_FUNC_TST_MODE	BIT(16)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EEE_ENABLE		BIT(17)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_OEN_CLK125M_PLL		BIT(18)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCHCLK_SEL		BIT(19)
+
+#define QCA956X_PLL_ETH_XMII_TX_INVERT			BIT(1)
+#define QCA956X_PLL_ETH_XMII_GIGE			BIT(25)
+#define QCA956X_PLL_ETH_XMII_RX_DELAY_SHIFT		28
+#define QCA956X_PLL_ETH_XMII_RX_DELAY_MASK		0x3
+#define QCA956X_PLL_ETH_XMII_TX_DELAY_SHIFT		26
+#define QCA956X_PLL_ETH_XMII_TX_DELAY_MASK		3
+
+#define QCA956X_PLL_ETH_SGMII_SERDES_LOCK_DETECT		BIT(2)
+#define QCA956X_PLL_ETH_SGMII_SERDES_PLL_REFCLK			BIT(1)
+#define QCA956X_PLL_ETH_SGMII_SERDES_EN_PLL			BIT(0)
+
 /*
  * USB_CONFIG block
  */
@@ -317,10 +542,19 @@
 #define AR934X_RESET_REG_BOOTSTRAP		0xb0
 #define AR934X_RESET_REG_PCIE_WMAC_INT_STATUS	0xac
 
+#define QCA953X_RESET_REG_RESET_MODULE		0x1c
+#define QCA953X_RESET_REG_BOOTSTRAP		0xb0
+#define QCA953X_RESET_REG_PCIE_WMAC_INT_STATUS	0xac
+
 #define QCA955X_RESET_REG_RESET_MODULE		0x1c
 #define QCA955X_RESET_REG_BOOTSTRAP		0xb0
 #define QCA955X_RESET_REG_EXT_INT_STATUS	0xac
 
+#define QCA956X_RESET_REG_RESET_MODULE		0x1c
+#define QCA956X_RESET_REG_BOOTSTRAP		0xb0
+#define QCA956X_RESET_REG_EXT_INT_STATUS	0xac
+
+#define MISC_INT_MIPS_SI_TIMERINT_MASK	BIT(28)
 #define MISC_INT_ETHSW			BIT(12)
 #define MISC_INT_TIMER4			BIT(10)
 #define MISC_INT_TIMER3			BIT(9)
@@ -370,16 +604,123 @@
 #define AR913X_RESET_USB_HOST		BIT(5)
 #define AR913X_RESET_USB_PHY		BIT(4)
 
+#define AR933X_RESET_GE1_MDIO		BIT(23)
+#define AR933X_RESET_GE0_MDIO		BIT(22)
+#define AR933X_RESET_GE1_MAC		BIT(13)
 #define AR933X_RESET_WMAC		BIT(11)
+#define AR933X_RESET_GE0_MAC		BIT(9)
 #define AR933X_RESET_USB_HOST		BIT(5)
 #define AR933X_RESET_USB_PHY		BIT(4)
 #define AR933X_RESET_USBSUS_OVERRIDE	BIT(3)
 
+#define AR934X_RESET_HOST		BIT(31)
+#define AR934X_RESET_SLIC		BIT(30)
+#define AR934X_RESET_HDMA		BIT(29)
+#define AR934X_RESET_EXTERNAL		BIT(28)
+#define AR934X_RESET_RTC		BIT(27)
+#define AR934X_RESET_PCIE_EP_INT	BIT(26)
+#define AR934X_RESET_CHKSUM_ACC		BIT(25)
+#define AR934X_RESET_FULL_CHIP		BIT(24)
+#define AR934X_RESET_GE1_MDIO		BIT(23)
+#define AR934X_RESET_GE0_MDIO		BIT(22)
+#define AR934X_RESET_CPU_NMI		BIT(21)
+#define AR934X_RESET_CPU_COLD		BIT(20)
+#define AR934X_RESET_HOST_RESET_INT	BIT(19)
+#define AR934X_RESET_PCIE_EP		BIT(18)
+#define AR934X_RESET_UART1		BIT(17)
+#define AR934X_RESET_DDR		BIT(16)
+#define AR934X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define AR934X_RESET_NANDF		BIT(14)
+#define AR934X_RESET_GE1_MAC		BIT(13)
+#define AR934X_RESET_ETH_SWITCH_ANALOG	BIT(12)
 #define AR934X_RESET_USB_PHY_ANALOG	BIT(11)
+#define AR934X_RESET_HOST_DMA_INT	BIT(10)
+#define AR934X_RESET_GE0_MAC		BIT(9)
+#define AR934X_RESET_ETH_SWITCH		BIT(8)
+#define AR934X_RESET_PCIE_PHY		BIT(7)
+#define AR934X_RESET_PCIE		BIT(6)
 #define AR934X_RESET_USB_HOST		BIT(5)
 #define AR934X_RESET_USB_PHY		BIT(4)
 #define AR934X_RESET_USBSUS_OVERRIDE	BIT(3)
-
+#define AR934X_RESET_LUT		BIT(2)
+#define AR934X_RESET_MBOX		BIT(1)
+#define AR934X_RESET_I2S		BIT(0)
+
+#define QCA953X_RESET_USB_EXT_PWR	BIT(29)
+#define QCA953X_RESET_EXTERNAL		BIT(28)
+#define QCA953X_RESET_RTC		BIT(27)
+#define QCA953X_RESET_FULL_CHIP		BIT(24)
+#define QCA953X_RESET_GE1_MDIO		BIT(23)
+#define QCA953X_RESET_GE0_MDIO		BIT(22)
+#define QCA953X_RESET_CPU_NMI		BIT(21)
+#define QCA953X_RESET_CPU_COLD		BIT(20)
+#define QCA953X_RESET_DDR		BIT(16)
+#define QCA953X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define QCA953X_RESET_GE1_MAC		BIT(13)
+#define QCA953X_RESET_ETH_SWITCH_ANALOG	BIT(12)
+#define QCA953X_RESET_USB_PHY_ANALOG	BIT(11)
+#define QCA953X_RESET_GE0_MAC		BIT(9)
+#define QCA953X_RESET_ETH_SWITCH	BIT(8)
+#define QCA953X_RESET_PCIE_PHY		BIT(7)
+#define QCA953X_RESET_PCIE		BIT(6)
+#define QCA953X_RESET_USB_HOST		BIT(5)
+#define QCA953X_RESET_USB_PHY		BIT(4)
+#define QCA953X_RESET_USBSUS_OVERRIDE	BIT(3)
+
+#define QCA955X_RESET_HOST		BIT(31)
+#define QCA955X_RESET_SLIC		BIT(30)
+#define QCA955X_RESET_HDMA		BIT(29)
+#define QCA955X_RESET_EXTERNAL		BIT(28)
+#define QCA955X_RESET_RTC		BIT(27)
+#define QCA955X_RESET_PCIE_EP_INT	BIT(26)
+#define QCA955X_RESET_CHKSUM_ACC	BIT(25)
+#define QCA955X_RESET_FULL_CHIP		BIT(24)
+#define QCA955X_RESET_GE1_MDIO		BIT(23)
+#define QCA955X_RESET_GE0_MDIO		BIT(22)
+#define QCA955X_RESET_CPU_NMI		BIT(21)
+#define QCA955X_RESET_CPU_COLD		BIT(20)
+#define QCA955X_RESET_HOST_RESET_INT	BIT(19)
+#define QCA955X_RESET_PCIE_EP		BIT(18)
+#define QCA955X_RESET_UART1		BIT(17)
+#define QCA955X_RESET_DDR		BIT(16)
+#define QCA955X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define QCA955X_RESET_NANDF		BIT(14)
+#define QCA955X_RESET_GE1_MAC		BIT(13)
+#define QCA955X_RESET_SGMII_ANALOG	BIT(12)
+#define QCA955X_RESET_USB_PHY_ANALOG	BIT(11)
+#define QCA955X_RESET_HOST_DMA_INT	BIT(10)
+#define QCA955X_RESET_GE0_MAC		BIT(9)
+#define QCA955X_RESET_SGMII		BIT(8)
+#define QCA955X_RESET_PCIE_PHY		BIT(7)
+#define QCA955X_RESET_PCIE		BIT(6)
+#define QCA955X_RESET_USB_HOST		BIT(5)
+#define QCA955X_RESET_USB_PHY		BIT(4)
+#define QCA955X_RESET_USBSUS_OVERRIDE	BIT(3)
+#define QCA955X_RESET_LUT		BIT(2)
+#define QCA955X_RESET_MBOX		BIT(1)
+#define QCA955X_RESET_I2S		BIT(0)
+
+#define QCA956X_RESET_EXTERNAL		BIT(28)
+#define QCA956X_RESET_FULL_CHIP		BIT(24)
+#define QCA956X_RESET_GE1_MDIO		BIT(23)
+#define QCA956X_RESET_GE0_MDIO		BIT(22)
+#define QCA956X_RESET_CPU_NMI		BIT(21)
+#define QCA956X_RESET_CPU_COLD		BIT(20)
+#define QCA956X_RESET_DMA		BIT(19)
+#define QCA956X_RESET_DDR		BIT(16)
+#define QCA956X_RESET_GE1_MAC		BIT(13)
+#define QCA956X_RESET_SGMII_ANALOG	BIT(12)
+#define QCA956X_RESET_USB_PHY_ANALOG	BIT(11)
+#define QCA956X_RESET_GE0_MAC		BIT(9)
+#define QCA956X_RESET_SGMII		BIT(8)
+#define QCA956X_RESET_USB_HOST		BIT(5)
+#define QCA956X_RESET_USB_PHY		BIT(4)
+#define QCA956X_RESET_USBSUS_OVERRIDE	BIT(3)
+#define QCA956X_RESET_SWITCH_ANALOG	BIT(2)
+#define QCA956X_RESET_SWITCH		BIT(0)
+
+#define AR933X_BOOTSTRAP_MDIO_GPIO_EN	BIT(18)
+#define AR933X_BOOTSTRAP_EEPBUSY	BIT(4)
 #define AR933X_BOOTSTRAP_REF_CLK_40	BIT(0)
 
 #define AR934X_BOOTSTRAP_SW_OPTION8	BIT(23)
@@ -398,8 +739,17 @@
 #define AR934X_BOOTSTRAP_SDRAM_DISABLED BIT(1)
 #define AR934X_BOOTSTRAP_DDR1		BIT(0)
 
+#define QCA953X_BOOTSTRAP_SW_OPTION2	BIT(12)
+#define QCA953X_BOOTSTRAP_SW_OPTION1	BIT(11)
+#define QCA953X_BOOTSTRAP_EJTAG_MODE	BIT(5)
+#define QCA953X_BOOTSTRAP_REF_CLK_40	BIT(4)
+#define QCA953X_BOOTSTRAP_SDRAM_DISABLED BIT(1)
+#define QCA953X_BOOTSTRAP_DDR1		BIT(0)
+
 #define QCA955X_BOOTSTRAP_REF_CLK_40	BIT(4)
 
+#define QCA956X_BOOTSTRAP_REF_CLK_40	BIT(2)
+
 #define AR934X_PCIE_WMAC_INT_WMAC_MISC		BIT(0)
 #define AR934X_PCIE_WMAC_INT_WMAC_TX		BIT(1)
 #define AR934X_PCIE_WMAC_INT_WMAC_RXLP		BIT(2)
@@ -418,6 +768,24 @@
 	 AR934X_PCIE_WMAC_INT_PCIE_RC1 | AR934X_PCIE_WMAC_INT_PCIE_RC2 | \
 	 AR934X_PCIE_WMAC_INT_PCIE_RC3)
 
+#define QCA953X_PCIE_WMAC_INT_WMAC_MISC		BIT(0)
+#define QCA953X_PCIE_WMAC_INT_WMAC_TX		BIT(1)
+#define QCA953X_PCIE_WMAC_INT_WMAC_RXLP		BIT(2)
+#define QCA953X_PCIE_WMAC_INT_WMAC_RXHP		BIT(3)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC		BIT(4)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC0		BIT(5)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC1		BIT(6)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC2		BIT(7)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC3		BIT(8)
+#define QCA953X_PCIE_WMAC_INT_WMAC_ALL \
+	(QCA953X_PCIE_WMAC_INT_WMAC_MISC | QCA953X_PCIE_WMAC_INT_WMAC_TX | \
+	 QCA953X_PCIE_WMAC_INT_WMAC_RXLP | QCA953X_PCIE_WMAC_INT_WMAC_RXHP)
+
+#define QCA953X_PCIE_WMAC_INT_PCIE_ALL \
+	(QCA953X_PCIE_WMAC_INT_PCIE_RC | QCA953X_PCIE_WMAC_INT_PCIE_RC0 | \
+	 QCA953X_PCIE_WMAC_INT_PCIE_RC1 | QCA953X_PCIE_WMAC_INT_PCIE_RC2 | \
+	 QCA953X_PCIE_WMAC_INT_PCIE_RC3)
+
 #define QCA955X_EXT_INT_WMAC_MISC		BIT(0)
 #define QCA955X_EXT_INT_WMAC_TX			BIT(1)
 #define QCA955X_EXT_INT_WMAC_RXLP		BIT(2)
@@ -449,6 +817,37 @@
 	 QCA955X_EXT_INT_PCIE_RC2_INT1 | QCA955X_EXT_INT_PCIE_RC2_INT2 | \
 	 QCA955X_EXT_INT_PCIE_RC2_INT3)
 
+#define QCA956X_EXT_INT_WMAC_MISC		BIT(0)
+#define QCA956X_EXT_INT_WMAC_TX			BIT(1)
+#define QCA956X_EXT_INT_WMAC_RXLP		BIT(2)
+#define QCA956X_EXT_INT_WMAC_RXHP		BIT(3)
+#define QCA956X_EXT_INT_PCIE_RC1		BIT(4)
+#define QCA956X_EXT_INT_PCIE_RC1_INT0		BIT(5)
+#define QCA956X_EXT_INT_PCIE_RC1_INT1		BIT(6)
+#define QCA956X_EXT_INT_PCIE_RC1_INT2		BIT(7)
+#define QCA956X_EXT_INT_PCIE_RC1_INT3		BIT(8)
+#define QCA956X_EXT_INT_PCIE_RC2		BIT(12)
+#define QCA956X_EXT_INT_PCIE_RC2_INT0		BIT(13)
+#define QCA956X_EXT_INT_PCIE_RC2_INT1		BIT(14)
+#define QCA956X_EXT_INT_PCIE_RC2_INT2		BIT(15)
+#define QCA956X_EXT_INT_PCIE_RC2_INT3		BIT(16)
+#define QCA956X_EXT_INT_USB1			BIT(24)
+#define QCA956X_EXT_INT_USB2			BIT(28)
+
+#define QCA956X_EXT_INT_WMAC_ALL \
+	(QCA956X_EXT_INT_WMAC_MISC | QCA956X_EXT_INT_WMAC_TX | \
+	 QCA956X_EXT_INT_WMAC_RXLP | QCA956X_EXT_INT_WMAC_RXHP)
+
+#define QCA956X_EXT_INT_PCIE_RC1_ALL \
+	(QCA956X_EXT_INT_PCIE_RC1 | QCA956X_EXT_INT_PCIE_RC1_INT0 | \
+	 QCA956X_EXT_INT_PCIE_RC1_INT1 | QCA956X_EXT_INT_PCIE_RC1_INT2 | \
+	 QCA956X_EXT_INT_PCIE_RC1_INT3)
+
+#define QCA956X_EXT_INT_PCIE_RC2_ALL \
+	(QCA956X_EXT_INT_PCIE_RC2 | QCA956X_EXT_INT_PCIE_RC2_INT0 | \
+	 QCA956X_EXT_INT_PCIE_RC2_INT1 | QCA956X_EXT_INT_PCIE_RC2_INT2 | \
+	 QCA956X_EXT_INT_PCIE_RC2_INT3)
+
 #define REV_ID_MAJOR_MASK		0xfff0
 #define REV_ID_MAJOR_AR71XX		0x00a0
 #define REV_ID_MAJOR_AR913X		0x00b0
@@ -460,8 +859,12 @@
 #define REV_ID_MAJOR_AR9341		0x0120
 #define REV_ID_MAJOR_AR9342		0x1120
 #define REV_ID_MAJOR_AR9344		0x2120
+#define REV_ID_MAJOR_QCA9533		0x0140
+#define REV_ID_MAJOR_QCA9533_V2		0x0160
 #define REV_ID_MAJOR_QCA9556		0x0130
 #define REV_ID_MAJOR_QCA9558		0x1130
+#define REV_ID_MAJOR_TP9343		0x0150
+#define REV_ID_MAJOR_QCA956X		0x1150
 
 #define AR71XX_REV_ID_MINOR_MASK	0x3
 #define AR71XX_REV_ID_MINOR_AR7130	0x0
@@ -482,8 +885,12 @@
 
 #define AR934X_REV_ID_REVISION_MASK	0xf
 
+#define QCA953X_REV_ID_REVISION_MASK	0xf
+
 #define QCA955X_REV_ID_REVISION_MASK	0xf
 
+#define QCA956X_REV_ID_REVISION_MASK	0xf
+
 /*
  * SPI block
  */
@@ -521,15 +928,63 @@
 #define AR71XX_GPIO_REG_INT_ENABLE	0x24
 #define AR71XX_GPIO_REG_FUNC		0x28
 
+#define AR934X_GPIO_REG_OUT_FUNC0	0x2c
+#define AR934X_GPIO_REG_OUT_FUNC1	0x30
+#define AR934X_GPIO_REG_OUT_FUNC2	0x34
+#define AR934X_GPIO_REG_OUT_FUNC3	0x38
+#define AR934X_GPIO_REG_OUT_FUNC4	0x3c
+#define AR934X_GPIO_REG_OUT_FUNC5	0x40
 #define AR934X_GPIO_REG_FUNC		0x6c
 
+#define QCA953X_GPIO_REG_OUT_FUNC0	0x2c
+#define QCA953X_GPIO_REG_OUT_FUNC1	0x30
+#define QCA953X_GPIO_REG_OUT_FUNC2	0x34
+#define QCA953X_GPIO_REG_OUT_FUNC3	0x38
+#define QCA953X_GPIO_REG_OUT_FUNC4	0x3c
+#define QCA953X_GPIO_REG_IN_ENABLE0	0x44
+#define QCA953X_GPIO_REG_FUNC		0x6c
+
+#define QCA953X_GPIO_OUT_MUX_SPI_CS1		10
+#define QCA953X_GPIO_OUT_MUX_SPI_CS2		11
+#define QCA953X_GPIO_OUT_MUX_SPI_CS0		9
+#define QCA953X_GPIO_OUT_MUX_SPI_CLK		8
+#define QCA953X_GPIO_OUT_MUX_SPI_MOSI		12
+#define QCA953X_GPIO_OUT_MUX_LED_LINK1		41
+#define QCA953X_GPIO_OUT_MUX_LED_LINK2		42
+#define QCA953X_GPIO_OUT_MUX_LED_LINK3		43
+#define QCA953X_GPIO_OUT_MUX_LED_LINK4		44
+#define QCA953X_GPIO_OUT_MUX_LED_LINK5		45
+
+#define QCA955X_GPIO_REG_OUT_FUNC0	0x2c
+#define QCA955X_GPIO_REG_OUT_FUNC1	0x30
+#define QCA955X_GPIO_REG_OUT_FUNC2	0x34
+#define QCA955X_GPIO_REG_OUT_FUNC3	0x38
+#define QCA955X_GPIO_REG_OUT_FUNC4	0x3c
+#define QCA955X_GPIO_REG_OUT_FUNC5	0x40
+#define QCA955X_GPIO_REG_FUNC		0x6c
+
+#define QCA956X_GPIO_REG_OUT_FUNC0	0x2c
+#define QCA956X_GPIO_REG_OUT_FUNC1	0x30
+#define QCA956X_GPIO_REG_OUT_FUNC2	0x34
+#define QCA956X_GPIO_REG_OUT_FUNC3	0x38
+#define QCA956X_GPIO_REG_OUT_FUNC4	0x3c
+#define QCA956X_GPIO_REG_OUT_FUNC5	0x40
+#define QCA956X_GPIO_REG_IN_ENABLE0	0x44
+#define QCA956X_GPIO_REG_IN_ENABLE3	0x50
+#define QCA956X_GPIO_REG_FUNC		0x6c
+
+#define QCA956X_GPIO_OUT_MUX_GE0_MDO	32
+#define QCA956X_GPIO_OUT_MUX_GE0_MDC	33
+
 #define AR71XX_GPIO_COUNT		16
 #define AR7240_GPIO_COUNT		18
 #define AR7241_GPIO_COUNT		20
 #define AR913X_GPIO_COUNT		22
 #define AR933X_GPIO_COUNT		30
 #define AR934X_GPIO_COUNT		23
+#define QCA953X_GPIO_COUNT		18
 #define QCA955X_GPIO_COUNT		24
+#define QCA956X_GPIO_COUNT		23
 
 /*
  * SRIF block
@@ -552,4 +1007,318 @@
 #define AR934X_SRIF_DPLL2_OUTDIV_SHIFT	13
 #define AR934X_SRIF_DPLL2_OUTDIV_MASK	0x7
 
+#define QCA953X_SRIF_CPU_DPLL1_REG	0x1c0
+#define QCA953X_SRIF_CPU_DPLL2_REG	0x1c4
+#define QCA953X_SRIF_CPU_DPLL3_REG	0x1c8
+
+#define QCA953X_SRIF_DDR_DPLL1_REG	0x240
+#define QCA953X_SRIF_DDR_DPLL2_REG	0x244
+#define QCA953X_SRIF_DDR_DPLL3_REG	0x248
+
+#define QCA953X_SRIF_DPLL1_REFDIV_SHIFT	27
+#define QCA953X_SRIF_DPLL1_REFDIV_MASK	0x1f
+#define QCA953X_SRIF_DPLL1_NINT_SHIFT	18
+#define QCA953X_SRIF_DPLL1_NINT_MASK	0x1ff
+#define QCA953X_SRIF_DPLL1_NFRAC_MASK	0x0003ffff
+
+#define QCA953X_SRIF_DPLL2_LOCAL_PLL	BIT(30)
+#define QCA953X_SRIF_DPLL2_OUTDIV_SHIFT	13
+#define QCA953X_SRIF_DPLL2_OUTDIV_MASK	0x7
+
+#define AR71XX_GPIO_FUNC_STEREO_EN		BIT(17)
+#define AR71XX_GPIO_FUNC_SLIC_EN		BIT(16)
+#define AR71XX_GPIO_FUNC_SPI_CS2_EN		BIT(13)
+#define AR71XX_GPIO_FUNC_SPI_CS1_EN		BIT(12)
+#define AR71XX_GPIO_FUNC_UART_EN		BIT(8)
+#define AR71XX_GPIO_FUNC_USB_OC_EN		BIT(4)
+#define AR71XX_GPIO_FUNC_USB_CLK_EN		BIT(0)
+
+#define AR724X_GPIO_FUNC_GE0_MII_CLK_EN		BIT(19)
+#define AR724X_GPIO_FUNC_SPI_EN			BIT(18)
+#define AR724X_GPIO_FUNC_SPI_CS_EN2		BIT(14)
+#define AR724X_GPIO_FUNC_SPI_CS_EN1		BIT(13)
+#define AR724X_GPIO_FUNC_CLK_OBS5_EN		BIT(12)
+#define AR724X_GPIO_FUNC_CLK_OBS4_EN		BIT(11)
+#define AR724X_GPIO_FUNC_CLK_OBS3_EN		BIT(10)
+#define AR724X_GPIO_FUNC_CLK_OBS2_EN		BIT(9)
+#define AR724X_GPIO_FUNC_CLK_OBS1_EN		BIT(8)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED4_EN	BIT(7)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED3_EN	BIT(6)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED2_EN	BIT(5)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED1_EN	BIT(4)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED0_EN	BIT(3)
+#define AR724X_GPIO_FUNC_UART_RTS_CTS_EN	BIT(2)
+#define AR724X_GPIO_FUNC_UART_EN		BIT(1)
+#define AR724X_GPIO_FUNC_JTAG_DISABLE		BIT(0)
+
+#define AR913X_GPIO_FUNC_WMAC_LED_EN		BIT(22)
+#define AR913X_GPIO_FUNC_EXP_PORT_CS_EN		BIT(21)
+#define AR913X_GPIO_FUNC_I2S_REFCLKEN		BIT(20)
+#define AR913X_GPIO_FUNC_I2S_MCKEN		BIT(19)
+#define AR913X_GPIO_FUNC_I2S1_EN		BIT(18)
+#define AR913X_GPIO_FUNC_I2S0_EN		BIT(17)
+#define AR913X_GPIO_FUNC_SLIC_EN		BIT(16)
+#define AR913X_GPIO_FUNC_UART_RTSCTS_EN		BIT(9)
+#define AR913X_GPIO_FUNC_UART_EN		BIT(8)
+#define AR913X_GPIO_FUNC_USB_CLK_EN		BIT(4)
+
+#define AR933X_GPIO_FUNC_SPDIF2TCK		BIT(31)
+#define AR933X_GPIO_FUNC_SPDIF_EN		BIT(30)
+#define AR933X_GPIO_FUNC_I2SO_22_18_EN		BIT(29)
+#define AR933X_GPIO_FUNC_I2S_MCK_EN		BIT(27)
+#define AR933X_GPIO_FUNC_I2SO_EN		BIT(26)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_DUPL	BIT(25)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_COLL	BIT(24)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_ACT	BIT(23)
+#define AR933X_GPIO_FUNC_SPI_EN			BIT(18)
+#define AR933X_GPIO_FUNC_SPI_CS_EN2		BIT(14)
+#define AR933X_GPIO_FUNC_SPI_CS_EN1		BIT(13)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED4_EN	BIT(7)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED3_EN	BIT(6)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED2_EN	BIT(5)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED1_EN	BIT(4)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED0_EN	BIT(3)
+#define AR933X_GPIO_FUNC_UART_RTS_CTS_EN	BIT(2)
+#define AR933X_GPIO_FUNC_UART_EN		BIT(1)
+#define AR933X_GPIO_FUNC_JTAG_DISABLE		BIT(0)
+
+#define AR934X_GPIO_FUNC_CLK_OBS7_EN		BIT(9)
+#define AR934X_GPIO_FUNC_CLK_OBS6_EN		BIT(8)
+#define AR934X_GPIO_FUNC_CLK_OBS5_EN		BIT(7)
+#define AR934X_GPIO_FUNC_CLK_OBS4_EN		BIT(6)
+#define AR934X_GPIO_FUNC_CLK_OBS3_EN		BIT(5)
+#define AR934X_GPIO_FUNC_CLK_OBS2_EN		BIT(4)
+#define AR934X_GPIO_FUNC_CLK_OBS1_EN		BIT(3)
+#define AR934X_GPIO_FUNC_CLK_OBS0_EN		BIT(2)
+#define AR934X_GPIO_FUNC_JTAG_DISABLE		BIT(1)
+
+#define AR934X_GPIO_OUT_GPIO		0
+#define AR934X_GPIO_OUT_SPI_CS1	7
+#define AR934X_GPIO_OUT_LED_LINK0	41
+#define AR934X_GPIO_OUT_LED_LINK1	42
+#define AR934X_GPIO_OUT_LED_LINK2	43
+#define AR934X_GPIO_OUT_LED_LINK3	44
+#define AR934X_GPIO_OUT_LED_LINK4	45
+#define AR934X_GPIO_OUT_EXT_LNA0	46
+#define AR934X_GPIO_OUT_EXT_LNA1	47
+
+#define QCA955X_GPIO_FUNC_CLK_OBS7_EN		BIT(9)
+#define QCA955X_GPIO_FUNC_CLK_OBS6_EN		BIT(8)
+#define QCA955X_GPIO_FUNC_CLK_OBS5_EN		BIT(7)
+#define QCA955X_GPIO_FUNC_CLK_OBS4_EN		BIT(6)
+#define QCA955X_GPIO_FUNC_CLK_OBS3_EN		BIT(5)
+#define QCA955X_GPIO_FUNC_CLK_OBS2_EN		BIT(4)
+#define QCA955X_GPIO_FUNC_CLK_OBS1_EN		BIT(3)
+#define QCA955X_GPIO_FUNC_JTAG_DISABLE		BIT(1)
+
+#define QCA955X_GPIO_OUT_GPIO		0
+#define QCA955X_MII_EXT_MDI		1
+#define QCA955X_SLIC_DATA_OUT		3
+#define QCA955X_SLIC_PCM_FS		4
+#define QCA955X_SLIC_PCM_CLK		5
+#define QCA955X_SPI_CLK			8
+#define QCA955X_SPI_CS_0		9
+#define QCA955X_SPI_CS_1		10
+#define QCA955X_SPI_CS_2		11
+#define QCA955X_SPI_MISO		12
+#define QCA955X_I2S_CLK			13
+#define QCA955X_I2S_WS			14
+#define QCA955X_I2S_SD			15
+#define QCA955X_I2S_MCK			16
+#define QCA955X_SPDIF_OUT		17
+#define QCA955X_UART1_TD		18
+#define QCA955X_UART1_RTS		19
+#define QCA955X_UART1_RD		20
+#define QCA955X_UART1_CTS		21
+#define QCA955X_UART0_SOUT		22
+#define QCA955X_SPDIF2_OUT		23
+#define QCA955X_LED_SGMII_SPEED0	24
+#define QCA955X_LED_SGMII_SPEED1	25
+#define QCA955X_LED_SGMII_DUPLEX	26
+#define QCA955X_LED_SGMII_LINK_UP	27
+#define QCA955X_SGMII_SPEED0_INVERT	28
+#define QCA955X_SGMII_SPEED1_INVERT	29
+#define QCA955X_SGMII_DUPLEX_INVERT	30
+#define QCA955X_SGMII_LINK_UP_INVERT	31
+#define QCA955X_GE1_MII_MDO		32
+#define QCA955X_GE1_MII_MDC		33
+#define QCA955X_SWCOM2			38
+#define QCA955X_SWCOM3			39
+#define QCA955X_MAC2_GPIO		40
+#define QCA955X_MAC3_GPIO		41
+#define QCA955X_ATT_LED			42
+#define QCA955X_PWR_LED			43
+#define QCA955X_TX_FRAME		44
+#define QCA955X_RX_CLEAR_EXTERNAL	45
+#define QCA955X_LED_NETWORK_EN		46
+#define QCA955X_LED_POWER_EN		47
+#define QCA955X_WMAC_GLUE_WOW		68
+#define QCA955X_RX_CLEAR_EXTENSION	70
+#define QCA955X_CP_NAND_CS1		73
+#define QCA955X_USB_SUSPEND		74
+#define QCA955X_ETH_TX_ERR		75
+#define QCA955X_DDR_DQ_OE		76
+#define QCA955X_CLKREQ_N_EP		77
+#define QCA955X_CLKREQ_N_RC		78
+#define QCA955X_CLK_OBS0		79
+#define QCA955X_CLK_OBS1		80
+#define QCA955X_CLK_OBS2		81
+#define QCA955X_CLK_OBS3		82
+#define QCA955X_CLK_OBS4		83
+#define QCA955X_CLK_OBS5		84
+
+/*
+ * MII_CTRL block
+ */
+#define AR71XX_MII_REG_MII0_CTRL	0x00
+#define AR71XX_MII_REG_MII1_CTRL	0x04
+
+#define AR71XX_MII_CTRL_IF_MASK		3
+#define AR71XX_MII_CTRL_SPEED_SHIFT	4
+#define AR71XX_MII_CTRL_SPEED_MASK	3
+#define AR71XX_MII_CTRL_SPEED_10	0
+#define AR71XX_MII_CTRL_SPEED_100	1
+#define AR71XX_MII_CTRL_SPEED_1000	2
+
+#define AR71XX_MII0_CTRL_IF_GMII	0
+#define AR71XX_MII0_CTRL_IF_MII		1
+#define AR71XX_MII0_CTRL_IF_RGMII	2
+#define AR71XX_MII0_CTRL_IF_RMII	3
+
+#define AR71XX_MII1_CTRL_IF_RGMII	0
+#define AR71XX_MII1_CTRL_IF_RMII	1
+
+/*
+ * AR933X GMAC interface
+ */
+#define AR933X_GMAC_REG_ETH_CFG		0x00
+
+#define AR933X_ETH_CFG_RGMII_GE0	BIT(0)
+#define AR933X_ETH_CFG_MII_GE0		BIT(1)
+#define AR933X_ETH_CFG_GMII_GE0		BIT(2)
+#define AR933X_ETH_CFG_MII_GE0_MASTER	BIT(3)
+#define AR933X_ETH_CFG_MII_GE0_SLAVE	BIT(4)
+#define AR933X_ETH_CFG_MII_GE0_ERR_EN	BIT(5)
+#define AR933X_ETH_CFG_SW_PHY_SWAP	BIT(7)
+#define AR933X_ETH_CFG_SW_PHY_ADDR_SWAP	BIT(8)
+#define AR933X_ETH_CFG_RMII_GE0		BIT(9)
+#define AR933X_ETH_CFG_RMII_GE0_SPD_10	0
+#define AR933X_ETH_CFG_RMII_GE0_SPD_100	BIT(10)
+
+/*
+ * AR934X GMAC Interface
+ */
+#define AR934X_GMAC_REG_ETH_CFG		0x00
+
+#define AR934X_ETH_CFG_RGMII_GMAC0	BIT(0)
+#define AR934X_ETH_CFG_MII_GMAC0	BIT(1)
+#define AR934X_ETH_CFG_GMII_GMAC0	BIT(2)
+#define AR934X_ETH_CFG_MII_GMAC0_MASTER	BIT(3)
+#define AR934X_ETH_CFG_MII_GMAC0_SLAVE	BIT(4)
+#define AR934X_ETH_CFG_MII_GMAC0_ERR_EN	BIT(5)
+#define AR934X_ETH_CFG_SW_ONLY_MODE	BIT(6)
+#define AR934X_ETH_CFG_SW_PHY_SWAP	BIT(7)
+#define AR934X_ETH_CFG_SW_APB_ACCESS	BIT(9)
+#define AR934X_ETH_CFG_RMII_GMAC0	BIT(10)
+#define AR933X_ETH_CFG_MII_CNTL_SPEED	BIT(11)
+#define AR934X_ETH_CFG_RMII_GMAC0_MASTER BIT(12)
+#define AR933X_ETH_CFG_SW_ACC_MSB_FIRST	BIT(13)
+#define AR934X_ETH_CFG_RXD_DELAY        BIT(14)
+#define AR934X_ETH_CFG_RXD_DELAY_MASK   0x3
+#define AR934X_ETH_CFG_RXD_DELAY_SHIFT  14
+#define AR934X_ETH_CFG_RDV_DELAY        BIT(16)
+#define AR934X_ETH_CFG_RDV_DELAY_MASK   0x3
+#define AR934X_ETH_CFG_RDV_DELAY_SHIFT  16
+
+/*
+ * QCA953X GMAC Interface
+ */
+#define QCA953X_GMAC_REG_ETH_CFG		0x00
+
+#define QCA953X_ETH_CFG_SW_ONLY_MODE		BIT(6)
+#define QCA953X_ETH_CFG_SW_PHY_SWAP		BIT(7)
+#define QCA953X_ETH_CFG_SW_APB_ACCESS		BIT(9)
+#define QCA953X_ETH_CFG_SW_ACC_MSB_FIRST	BIT(13)
+
+/*
+ * QCA955X GMAC Interface
+ */
+
+#define QCA955X_GMAC_REG_ETH_CFG	0x00
+#define QCA955X_GMAC_REG_SGMII_SERDES	0x18
+
+#define QCA955X_ETH_CFG_RGMII_EN	BIT(0)
+#define QCA955X_ETH_CFG_MII_GE0		BIT(1)
+#define QCA955X_ETH_CFG_GMII_GE0	BIT(2)
+#define QCA955X_ETH_CFG_MII_GE0_MASTER	BIT(3)
+#define QCA955X_ETH_CFG_MII_GE0_SLAVE	BIT(4)
+#define QCA955X_ETH_CFG_GE0_ERR_EN	BIT(5)
+#define QCA955X_ETH_CFG_GE0_SGMII	BIT(6)
+#define QCA955X_ETH_CFG_RMII_GE0	BIT(10)
+#define QCA955X_ETH_CFG_MII_CNTL_SPEED	BIT(11)
+#define QCA955X_ETH_CFG_RMII_GE0_MASTER	BIT(12)
+#define QCA955X_ETH_CFG_RXD_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_RXD_DELAY_SHIFT	14
+#define QCA955X_ETH_CFG_RDV_DELAY	BIT(16)
+#define QCA955X_ETH_CFG_RDV_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_RDV_DELAY_SHIFT	16
+#define QCA955X_ETH_CFG_TXD_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_TXD_DELAY_SHIFT	18
+#define QCA955X_ETH_CFG_TXE_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_TXE_DELAY_SHIFT	20
+
+#define QCA955X_SGMII_SERDES_LOCK_DETECT_STATUS	BIT(15)
+#define QCA955X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23
+#define QCA955X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf
+/*
+ * QCA956X GMAC Interface
+ */
+
+#define QCA956X_GMAC_REG_ETH_CFG	0x00
+#define QCA956X_GMAC_REG_SGMII_RESET	0x14
+#define QCA956X_GMAC_REG_SGMII_SERDES	0x18
+#define QCA956X_GMAC_REG_MR_AN_CONTROL	0x1c
+#define QCA956X_GMAC_REG_SGMII_CONFIG	0x34
+#define QCA956X_GMAC_REG_SGMII_DEBUG	0x58
+
+#define QCA956X_ETH_CFG_RGMII_EN		BIT(0)
+#define QCA956X_ETH_CFG_GE0_SGMII		BIT(6)
+#define QCA956X_ETH_CFG_SW_ONLY_MODE		BIT(7)
+#define QCA956X_ETH_CFG_SW_PHY_SWAP		BIT(8)
+#define QCA956X_ETH_CFG_SW_PHY_ADDR_SWAP	BIT(9)
+#define QCA956X_ETH_CFG_SW_APB_ACCESS		BIT(10)
+#define QCA956X_ETH_CFG_SW_ACC_MSB_FIRST	BIT(13)
+#define QCA956X_ETH_CFG_RXD_DELAY_MASK		0x3
+#define QCA956X_ETH_CFG_RXD_DELAY_SHIFT		14
+#define QCA956X_ETH_CFG_RDV_DELAY_MASK		0x3
+#define QCA956X_ETH_CFG_RDV_DELAY_SHIFT		16
+
+#define QCA956X_SGMII_RESET_RX_CLK_N_RESET	0x0
+#define QCA956X_SGMII_RESET_RX_CLK_N		BIT(0)
+#define QCA956X_SGMII_RESET_TX_CLK_N		BIT(1)
+#define QCA956X_SGMII_RESET_RX_125M_N		BIT(2)
+#define QCA956X_SGMII_RESET_TX_125M_N		BIT(3)
+#define QCA956X_SGMII_RESET_HW_RX_125M_N	BIT(4)
+
+#define QCA956X_SGMII_SERDES_CDR_BW_MASK	0x3
+#define QCA956X_SGMII_SERDES_CDR_BW_SHIFT	1
+#define QCA956X_SGMII_SERDES_TX_DR_CTRL_MASK	0x7
+#define QCA956X_SGMII_SERDES_TX_DR_CTRL_SHIFT	4
+#define QCA956X_SGMII_SERDES_PLL_BW		BIT(8)
+#define QCA956X_SGMII_SERDES_VCO_FAST		BIT(9)
+#define QCA956X_SGMII_SERDES_VCO_SLOW		BIT(10)
+#define QCA956X_SGMII_SERDES_LOCK_DETECT_STATUS	BIT(15)
+#define QCA956X_SGMII_SERDES_EN_SIGNAL_DETECT	BIT(16)
+#define QCA956X_SGMII_SERDES_FIBER_SDO		BIT(17)
+#define QCA956X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23
+#define QCA956X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf
+#define QCA956X_SGMII_SERDES_VCO_REG_SHIFT	27
+#define QCA956X_SGMII_SERDES_VCO_REG_MASK	0xf
+
+#define QCA956X_MR_AN_CONTROL_AN_ENABLE		BIT(12)
+#define QCA956X_MR_AN_CONTROL_PHY_RESET		BIT(15)
+
+#define QCA956X_SGMII_CONFIG_MODE_CTRL_SHIFT	0
+#define QCA956X_SGMII_CONFIG_MODE_CTRL_MASK	0x7
+
 #endif /* __ASM_MACH_AR71XX_REGS_H */
diff --git a/arch/mips/include/asm/mach-ath79/ath79.h b/arch/mips/include/asm/mach-ath79/ath79.h
index 441faa92c3cd..73dcd63b8243 100644
--- a/arch/mips/include/asm/mach-ath79/ath79.h
+++ b/arch/mips/include/asm/mach-ath79/ath79.h
@@ -32,8 +32,11 @@ enum ath79_soc_type {
 	ATH79_SOC_AR9341,
 	ATH79_SOC_AR9342,
 	ATH79_SOC_AR9344,
+	ATH79_SOC_QCA9533,
 	ATH79_SOC_QCA9556,
 	ATH79_SOC_QCA9558,
+	ATH79_SOC_TP9343,
+	ATH79_SOC_QCA956X,
 };
 
 extern enum ath79_soc_type ath79_soc;
@@ -100,6 +103,16 @@ static inline int soc_is_ar934x(void)
 	return soc_is_ar9341() || soc_is_ar9342() || soc_is_ar9344();
 }
 
+static inline int soc_is_qca9533(void)
+{
+	return ath79_soc == ATH79_SOC_QCA9533;
+}
+
+static inline int soc_is_qca953x(void)
+{
+	return soc_is_qca9533();
+}
+
 static inline int soc_is_qca9556(void)
 {
 	return ath79_soc == ATH79_SOC_QCA9556;
@@ -115,6 +128,26 @@ static inline int soc_is_qca955x(void)
 	return soc_is_qca9556() || soc_is_qca9558();
 }
 
+static inline int soc_is_tp9343(void)
+{
+	return ath79_soc == ATH79_SOC_TP9343;
+}
+
+static inline int soc_is_qca9561(void)
+{
+	return ath79_soc == ATH79_SOC_QCA956X;
+}
+
+static inline int soc_is_qca9563(void)
+{
+	return ath79_soc == ATH79_SOC_QCA956X;
+}
+
+static inline int soc_is_qca956x(void)
+{
+	return soc_is_qca9561() || soc_is_qca9563();
+}
+
 void ath79_ddr_wb_flush(unsigned int reg);
 void ath79_ddr_set_pci_windows(void);
 
@@ -134,6 +167,7 @@ static inline u32 ath79_pll_rr(unsigned reg)
 static inline void ath79_reset_wr(unsigned reg, u32 val)
 {
 	__raw_writel(val, ath79_reset_base + reg);
+	(void) __raw_readl(ath79_reset_base + reg); /* flush */
 }
 
 static inline u32 ath79_reset_rr(unsigned reg)
diff --git a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
index 0089a740e5ae..026ad90c8ac0 100644
--- a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
@@ -36,6 +36,7 @@
 #define cpu_has_mdmx		0
 #define cpu_has_mips3d		0
 #define cpu_has_smartmips	0
+#define cpu_has_rixi		0
 
 #define cpu_has_mips32r1	1
 #define cpu_has_mips32r2	1
@@ -43,6 +44,7 @@
 #define cpu_has_mips64r2	0
 
 #define cpu_has_mipsmt		0
+#define cpu_has_userlocal	0
 
 #define cpu_has_64bits		0
 #define cpu_has_64bit_zero_reg	0
@@ -51,5 +53,9 @@
 
 #define cpu_dcache_line_size()	32
 #define cpu_icache_line_size()	32
+#define cpu_has_vtag_icache	0
+#define cpu_has_dc_aliases	1
+#define cpu_has_ic_fills_f_dc	0
+#define cpu_has_pindexed_dcache	0
 
 #endif /* __ASM_MACH_ATH79_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-bmips/dma-coherence.h b/arch/mips/include/asm/mach-bmips/dma-coherence.h
deleted file mode 100644
index d29781f02285..000000000000
--- a/arch/mips/include/asm/mach-bmips/dma-coherence.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2009 Broadcom Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#ifndef __ASM_MACH_BMIPS_DMA_COHERENCE_H
-#define __ASM_MACH_BMIPS_DMA_COHERENCE_H
-
-#include <asm/bmips.h>
-#include <asm/cpu-type.h>
-#include <asm/cpu.h>
-
-struct device;
-
-extern dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size);
-extern dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page);
-extern unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr);
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;
-}
-
-#define plat_post_dma_flush	bmips_post_dma_flush
-
-#endif /* __ASM_MACH_BMIPS_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
deleted file mode 100644
index 6eb1ee548b11..000000000000
--- a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- *
- * Similar to mach-generic/dma-coherence.h except
- * plat_device_is_coherent hard coded to return 1.
- *
- */
-#ifndef __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
-#define __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
-
-#include <linux/bug.h>
-
-struct device;
-
-extern void octeon_pci_dma_init(void);
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	BUG();
-	return 0;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	BUG();
-	return 0;
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	BUG();
-	return 0;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-	BUG();
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	BUG();
-	return 0;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
-
-struct dma_map_ops;
-extern const struct dma_map_ops *octeon_pci_dma_map_ops;
-extern char *octeon_swiotlb;
-
-#endif /* __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-generic/dma-coherence.h b/arch/mips/include/asm/mach-generic/dma-coherence.h
deleted file mode 100644
index 8ad7a40ca786..000000000000
--- a/arch/mips/include/asm/mach-generic/dma-coherence.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_GENERIC_DMA_COHERENCE_H
-#define __ASM_MACH_GENERIC_DMA_COHERENCE_H
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	return virt_to_phys(addr);
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	return page_to_phys(page);
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return dma_addr;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_PERDEV_COHERENT
-	return dev->archdata.dma_coherent;
-#else
-	switch (coherentio) {
-	default:
-	case IO_COHERENCE_DEFAULT:
-		return hw_coherentio;
-	case IO_COHERENCE_ENABLED:
-		return 1;
-	case IO_COHERENCE_DISABLED:
-		return 0;
-	}
-#endif
-}
-
-#ifndef plat_post_dma_flush
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-#endif
-
-#endif /* __ASM_MACH_GENERIC_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-generic/kmalloc.h b/arch/mips/include/asm/mach-generic/kmalloc.h
index 74207c7bd00d..649a98338886 100644
--- a/arch/mips/include/asm/mach-generic/kmalloc.h
+++ b/arch/mips/include/asm/mach-generic/kmalloc.h
@@ -2,8 +2,7 @@
 #ifndef __ASM_MACH_GENERIC_KMALLOC_H
 #define __ASM_MACH_GENERIC_KMALLOC_H
 
-
-#ifndef CONFIG_DMA_COHERENT
+#ifdef CONFIG_DMA_NONCOHERENT
 /*
  * Total overkill for most systems but need as a safe default.
  * Set this one if any device in the system might do non-coherent DMA.
diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h
index 952b0fdfda0e..ee5ebe98f6cf 100644
--- a/arch/mips/include/asm/mach-generic/spaces.h
+++ b/arch/mips/include/asm/mach-generic/spaces.h
@@ -17,9 +17,13 @@
 /*
  * This gives the physical RAM offset.
  */
-#ifndef PHYS_OFFSET
-#define PHYS_OFFSET		_AC(0, UL)
-#endif
+#ifndef __ASSEMBLY__
+# if defined(CONFIG_MIPS_AUTO_PFN_OFFSET)
+#  define PHYS_OFFSET		((unsigned long)PFN_PHYS(ARCH_PFN_OFFSET))
+# elif !defined(PHYS_OFFSET)
+#  define PHYS_OFFSET		_AC(0, UL)
+# endif
+#endif /* __ASSEMBLY__ */
 
 #ifdef CONFIG_32BIT
 #ifdef CONFIG_KVM_GUEST
diff --git a/arch/mips/include/asm/mach-ip27/dma-coherence.h b/arch/mips/include/asm/mach-ip27/dma-coherence.h
deleted file mode 100644
index 04d862020ac9..000000000000
--- a/arch/mips/include/asm/mach-ip27/dma-coherence.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_IP27_DMA_COHERENCE_H
-#define __ASM_MACH_IP27_DMA_COHERENCE_H
-
-#include <asm/pci/bridge.h>
-
-#define pdev_to_baddr(pdev, addr) \
-	(BRIDGE_CONTROLLER(pdev->bus)->baddr + (addr))
-#define dev_to_baddr(dev, addr) \
-	pdev_to_baddr(to_pci_dev(dev), (addr))
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	dma_addr_t pa = dev_to_baddr(dev, virt_to_phys(addr));
-
-	return pa;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	dma_addr_t pa = dev_to_baddr(dev, page_to_phys(page));
-
-	return pa;
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return dma_addr & ~(0xffUL << 56);
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 1;		/* IP27 non-coherent mode is unsupported */
-}
-
-#endif /* __ASM_MACH_IP27_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-ip32/dma-coherence.h b/arch/mips/include/asm/mach-ip32/dma-coherence.h
deleted file mode 100644
index 7bdf212587a0..000000000000
--- a/arch/mips/include/asm/mach-ip32/dma-coherence.h
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_IP32_DMA_COHERENCE_H
-#define __ASM_MACH_IP32_DMA_COHERENCE_H
-
-#include <asm/ip32/crime.h>
-
-struct device;
-
-/*
- * Few notes.
- * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M
- * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for
- *    native-endian)
- * 3. All other devices see memory as one big chunk at 0x40000000
- * 4. Non-PCI devices will pass NULL as struct device*
- *
- * Thus we translate differently, depending on device.
- */
-
-#define RAM_OFFSET_MASK 0x3fffffffUL
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	dma_addr_t pa = virt_to_phys(addr) & RAM_OFFSET_MASK;
-
-	if (dev == NULL)
-		pa += CRIME_HI_MEM_BASE;
-
-	return pa;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	dma_addr_t pa;
-
-	pa = page_to_phys(page) & RAM_OFFSET_MASK;
-
-	if (dev == NULL)
-		pa += CRIME_HI_MEM_BASE;
-
-	return pa;
-}
-
-/* This is almost certainly wrong but it's what dma-ip32.c used to use	*/
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	unsigned long addr = dma_addr & RAM_OFFSET_MASK;
-
-	if (dma_addr >= 256*1024*1024)
-		addr += CRIME_HI_MEM_BASE;
-
-	return addr;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;		/* IP32 is non-coherent */
-}
-
-#endif /* __ASM_MACH_IP32_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-jazz/dma-coherence.h b/arch/mips/include/asm/mach-jazz/dma-coherence.h
deleted file mode 100644
index dc347c25c343..000000000000
--- a/arch/mips/include/asm/mach-jazz/dma-coherence.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- */
-#ifndef __ASM_MACH_JAZZ_DMA_COHERENCE_H
-#define __ASM_MACH_JAZZ_DMA_COHERENCE_H
-
-#include <asm/jazzdma.h>
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
-	return vdma_alloc(virt_to_phys(addr), size);
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	return vdma_alloc(page_to_phys(page), PAGE_SIZE);
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return vdma_log2phys(dma_addr);
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-	vdma_free(dma_addr);
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;
-}
-
-#endif /* __ASM_MACH_JAZZ_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-loongson64/dma-coherence.h b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
deleted file mode 100644
index 64fc44dec0a8..000000000000
--- a/arch/mips/include/asm/mach-loongson64/dma-coherence.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006, 07  Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology
- * Author: Fuxin Zhang, zhangfx@lemote.com
- *
- */
-#ifndef __ASM_MACH_LOONGSON64_DMA_COHERENCE_H
-#define __ASM_MACH_LOONGSON64_DMA_COHERENCE_H
-
-#ifdef CONFIG_SWIOTLB
-#include <linux/swiotlb.h>
-#endif
-
-struct device;
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-extern dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-extern phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-					  size_t size)
-{
-#ifdef CONFIG_CPU_LOONGSON3
-	return __phys_to_dma(dev, virt_to_phys(addr));
-#else
-	return virt_to_phys(addr) | 0x80000000;
-#endif
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-					       struct page *page)
-{
-#ifdef CONFIG_CPU_LOONGSON3
-	return __phys_to_dma(dev, page_to_phys(page));
-#else
-	return page_to_phys(page) | 0x80000000;
-#endif
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-#if defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_64BIT)
-	return __dma_to_phys(dev, dma_addr);
-#elif defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
-	return (dma_addr > 0x8fffffff) ? dma_addr : (dma_addr & 0x0fffffff);
-#else
-	return dma_addr & 0x7fffffff;
-#endif
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_NONCOHERENT
-	return 0;
-#else
-	return 1;
-#endif /* CONFIG_DMA_NONCOHERENT */
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-#endif /* __ASM_MACH_LOONGSON64_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
index 8393bc548987..312739117bb0 100644
--- a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
@@ -19,18 +19,18 @@
 	.set	push
 	.set	mips64
 	/* Set LPA on LOONGSON3 config3 */
-	mfc0	t0, $16, 3
+	mfc0	t0, CP0_CONFIG3
 	or	t0, (0x1 << 7)
-	mtc0	t0, $16, 3
+	mtc0	t0, CP0_CONFIG3
 	/* Set ELPA on LOONGSON3 pagegrain */
-	mfc0	t0, $5, 1
+	mfc0	t0, CP0_PAGEGRAIN
 	or	t0, (0x1 << 29)
-	mtc0	t0, $5, 1
+	mtc0	t0, CP0_PAGEGRAIN
 #ifdef CONFIG_LOONGSON3_ENHANCEMENT
 	/* Enable STFill Buffer */
-	mfc0	t0, $16, 6
+	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
-	mtc0	t0, $16, 6
+	mtc0	t0, CP0_CONFIG6
 #endif
 	_ehb
 	.set	pop
@@ -45,18 +45,18 @@
 	.set	push
 	.set	mips64
 	/* Set LPA on LOONGSON3 config3 */
-	mfc0	t0, $16, 3
+	mfc0	t0, CP0_CONFIG3
 	or	t0, (0x1 << 7)
-	mtc0	t0, $16, 3
+	mtc0	t0, CP0_CONFIG3
 	/* Set ELPA on LOONGSON3 pagegrain */
-	mfc0	t0, $5, 1
+	mfc0	t0, CP0_PAGEGRAIN
 	or	t0, (0x1 << 29)
-	mtc0	t0, $5, 1
+	mtc0	t0, CP0_PAGEGRAIN
 #ifdef CONFIG_LOONGSON3_ENHANCEMENT
 	/* Enable STFill Buffer */
-	mfc0	t0, $16, 6
+	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
-	mtc0	t0, $16, 6
+	mtc0	t0, CP0_CONFIG6
 #endif
 	_ehb
 	.set	pop
diff --git a/arch/mips/include/asm/mach-pic32/spaces.h b/arch/mips/include/asm/mach-pic32/spaces.h
index 046a0a9aa8b3..a1b9783b76ea 100644
--- a/arch/mips/include/asm/mach-pic32/spaces.h
+++ b/arch/mips/include/asm/mach-pic32/spaces.h
@@ -16,7 +16,6 @@
 
 #ifdef CONFIG_PIC32MZDA
 #define PHYS_OFFSET	_AC(0x08000000, UL)
-#define UNCAC_BASE	_AC(0xa8000000, UL)
 #endif
 
 #include <asm/mach-generic/spaces.h>
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 0bc270806ec5..01df9ad62fb8 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -16,6 +16,7 @@
 #include <linux/linkage.h>
 #include <linux/types.h>
 #include <asm/hazards.h>
+#include <asm/isa-rev.h>
 #include <asm/war.h>
 
 /*
@@ -51,6 +52,7 @@
 #define CP0_GLOBALNUMBER $3, 1
 #define CP0_CONTEXT $4
 #define CP0_PAGEMASK $5
+#define CP0_PAGEGRAIN $5, 1
 #define CP0_SEGCTL0 $5, 2
 #define CP0_SEGCTL1 $5, 3
 #define CP0_SEGCTL2 $5, 4
@@ -77,6 +79,7 @@
 #define CP0_CONFIG $16
 #define CP0_CONFIG3 $16, 3
 #define CP0_CONFIG5 $16, 5
+#define CP0_CONFIG6 $16, 6
 #define CP0_LLADDR $17
 #define CP0_WATCHLO $18
 #define CP0_WATCHHI $19
@@ -681,8 +684,6 @@
 #define MIPS_CONF7_WII		(_ULCAST_(1) << 31)
 
 #define MIPS_CONF7_RPS		(_ULCAST_(1) << 2)
-/* ExternalSync */
-#define MIPS_CONF7_ES		(_ULCAST_(1) << 8)
 
 #define MIPS_CONF7_IAR		(_ULCAST_(1) << 10)
 #define MIPS_CONF7_AR		(_ULCAST_(1) << 16)
@@ -1483,32 +1484,38 @@ do {									\
 
 #define __write_64bit_c0_split(source, sel, val)			\
 do {									\
-	unsigned long long __tmp;					\
+	unsigned long long __tmp = (val);				\
 	unsigned long __flags;						\
 									\
 	local_irq_save(__flags);					\
-	if (sel == 0)							\
+	if (MIPS_ISA_REV >= 2)						\
+		__asm__ __volatile__(					\
+			".set\tpush\n\t"				\
+			".set\t" MIPS_ISA_LEVEL "\n\t"			\
+			"dins\t%L0, %M0, 32, 32\n\t"			\
+			"dmtc0\t%L0, " #source ", " #sel "\n\t"		\
+			".set\tpop"					\
+			: "+r" (__tmp));				\
+	else if (sel == 0)						\
 		__asm__ __volatile__(					\
 			".set\tmips64\n\t"				\
-			"dsll\t%L0, %L1, 32\n\t"			\
+			"dsll\t%L0, %L0, 32\n\t"			\
 			"dsrl\t%L0, %L0, 32\n\t"			\
-			"dsll\t%M0, %M1, 32\n\t"			\
+			"dsll\t%M0, %M0, 32\n\t"			\
 			"or\t%L0, %L0, %M0\n\t"				\
 			"dmtc0\t%L0, " #source "\n\t"			\
 			".set\tmips0"					\
-			: "=&r,r" (__tmp)				\
-			: "r,0" (val));					\
+			: "+r" (__tmp));				\
 	else								\
 		__asm__ __volatile__(					\
 			".set\tmips64\n\t"				\
-			"dsll\t%L0, %L1, 32\n\t"			\
+			"dsll\t%L0, %L0, 32\n\t"			\
 			"dsrl\t%L0, %L0, 32\n\t"			\
-			"dsll\t%M0, %M1, 32\n\t"			\
+			"dsll\t%M0, %M0, 32\n\t"			\
 			"or\t%L0, %L0, %M0\n\t"				\
 			"dmtc0\t%L0, " #source ", " #sel "\n\t"		\
 			".set\tmips0"					\
-			: "=&r,r" (__tmp)				\
-			: "r,0" (val));					\
+			: "+r" (__tmp));				\
 	local_irq_restore(__flags);					\
 } while (0)
 
@@ -2767,7 +2774,6 @@ __BUILD_SET_C0(status)
 __BUILD_SET_C0(cause)
 __BUILD_SET_C0(config)
 __BUILD_SET_C0(config5)
-__BUILD_SET_C0(config7)
 __BUILD_SET_C0(intcontrol)
 __BUILD_SET_C0(intctl)
 __BUILD_SET_C0(srsmap)
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index da2004cef2d5..b509371a6b0c 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -126,8 +126,6 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	for_each_possible_cpu(i)
 		cpu_context(i, mm) = 0;
 
-	atomic_set(&mm->context.fp_mode_switching, 0);
-
 	mm->context.bd_emupage_allocmap = NULL;
 	spin_lock_init(&mm->context.bd_emupage_lock);
 	init_waitqueue_head(&mm->context.bd_emupage_queue);
diff --git a/arch/mips/include/asm/netlogic/xlr/fmn.h b/arch/mips/include/asm/netlogic/xlr/fmn.h
index 5604db3d1836..d79c68fa78d9 100644
--- a/arch/mips/include/asm/netlogic/xlr/fmn.h
+++ b/arch/mips/include/asm/netlogic/xlr/fmn.h
@@ -301,8 +301,6 @@ static inline int nlm_fmn_send(unsigned int size, unsigned int code,
 	for (i = 0; i < 8; i++) {
 		nlm_msgsnd(dest);
 		status = nlm_read_c2_status0();
-		if ((status & 0x2) == 1)
-			pr_info("Send pending fail!\n");
 		if ((status & 0x4) == 0)
 			return 0;
 	}
diff --git a/arch/mips/include/asm/octeon/cvmx-asxx-defs.h b/arch/mips/include/asm/octeon/cvmx-asxx-defs.h
index a1e21a3854cf..1eef155979f3 100644
--- a/arch/mips/include/asm/octeon/cvmx-asxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-asxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -55,6 +55,8 @@
 #define CVMX_ASXX_TX_HI_WATERX(offset, block_id) (CVMX_ADD_IO_SEG(0x00011800B0000080ull) + (((offset) & 3) + ((block_id) & 1) * 0x1000000ull) * 8)
 #define CVMX_ASXX_TX_PRT_EN(block_id) (CVMX_ADD_IO_SEG(0x00011800B0000008ull) + ((block_id) & 1) * 0x8000000ull)
 
+void __cvmx_interrupt_asxx_enable(int block);
+
 union cvmx_asxx_gmii_rx_clk_set {
 	uint64_t u64;
 	struct cvmx_asxx_gmii_rx_clk_set_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
index 6e61792d9248..1d18be8cdddc 100644
--- a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
@@ -1,10014 +1,176 @@
-/***********************license start***************
- * Author: Cavium Networks
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Octeon CIU definitions
  *
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2012 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- *
- * This file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
+ * Copyright (C) 2003-2018 Cavium, Inc.
+ */
 
 #ifndef __CVMX_CIU_DEFS_H__
 #define __CVMX_CIU_DEFS_H__
 
-#define CVMX_CIU_BIST (CVMX_ADD_IO_SEG(0x0001070000000730ull))
-#define CVMX_CIU_BLOCK_INT (CVMX_ADD_IO_SEG(0x00010700000007C0ull))
-#define CVMX_CIU_DINT (CVMX_ADD_IO_SEG(0x0001070000000720ull))
-#define CVMX_CIU_EN2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x000107000000A600ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_IOX_INT_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CE00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_IOX_INT_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AE00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x000107000000A000ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP2_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000C800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP2_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000A800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x000107000000A200ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CA00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AA00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x000107000000A400ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CC00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AC00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_FUSE (CVMX_ADD_IO_SEG(0x0001070000000728ull))
-#define CVMX_CIU_GSTOP (CVMX_ADD_IO_SEG(0x0001070000000710ull))
-#define CVMX_CIU_INT33_SUM0 (CVMX_ADD_IO_SEG(0x0001070000000110ull))
-#define CVMX_CIU_INTX_EN0(offset) (CVMX_ADD_IO_SEG(0x0001070000000200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1(offset) (CVMX_ADD_IO_SEG(0x0001070000000208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN4_0(offset) (CVMX_ADD_IO_SEG(0x0001070000000C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1(offset) (CVMX_ADD_IO_SEG(0x0001070000000C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_SUM0(offset) (CVMX_ADD_IO_SEG(0x0001070000000000ull) + ((offset) & 63) * 8)
-#define CVMX_CIU_INTX_SUM4(offset) (CVMX_ADD_IO_SEG(0x0001070000000C00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_INT_DBG_SEL (CVMX_ADD_IO_SEG(0x00010700000007D0ull))
-#define CVMX_CIU_INT_SUM1 (CVMX_ADD_IO_SEG(0x0001070000000108ull))
-static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned long offset)
+#include <asm/bitfield.h>
+
+#define CVMX_CIU_ADDR(addr, coreid, coremask, offset)			       \
+	(CVMX_ADD_IO_SEG(0x0001070000000000ull + addr##ull) +		       \
+	(((coreid) & (coremask)) * offset))
+
+#define CVMX_CIU_EN2_PPX_IP4(c)		CVMX_CIU_ADDR(0xA400, c, 0x0F, 8)
+#define CVMX_CIU_EN2_PPX_IP4_W1C(c)	CVMX_CIU_ADDR(0xCC00, c, 0x0F, 8)
+#define CVMX_CIU_EN2_PPX_IP4_W1S(c)	CVMX_CIU_ADDR(0xAC00, c, 0x0F, 8)
+#define CVMX_CIU_FUSE			CVMX_CIU_ADDR(0x0728, 0, 0x00, 0)
+#define CVMX_CIU_INT_SUM1		CVMX_CIU_ADDR(0x0108, 0, 0x00, 0)
+#define CVMX_CIU_INTX_EN0(c)		CVMX_CIU_ADDR(0x0200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN0_W1C(c)	CVMX_CIU_ADDR(0x2200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN0_W1S(c)	CVMX_CIU_ADDR(0x6200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1(c)		CVMX_CIU_ADDR(0x0208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1_W1C(c)	CVMX_CIU_ADDR(0x2208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1_W1S(c)	CVMX_CIU_ADDR(0x6208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_SUM0(c)		CVMX_CIU_ADDR(0x0000, c, 0x3F, 8)
+#define CVMX_CIU_NMI			CVMX_CIU_ADDR(0x0718, 0, 0x00, 0)
+#define CVMX_CIU_PCI_INTA		CVMX_CIU_ADDR(0x0750, 0, 0x00, 0)
+#define CVMX_CIU_PP_BIST_STAT		CVMX_CIU_ADDR(0x07E0, 0, 0x00, 0)
+#define CVMX_CIU_PP_DBG			CVMX_CIU_ADDR(0x0708, 0, 0x00, 0)
+#define CVMX_CIU_PP_RST			CVMX_CIU_ADDR(0x0700, 0, 0x00, 0)
+#define CVMX_CIU_QLM0			CVMX_CIU_ADDR(0x0780, 0, 0x00, 0)
+#define CVMX_CIU_QLM1			CVMX_CIU_ADDR(0x0788, 0, 0x00, 0)
+#define CVMX_CIU_QLM_JTGC		CVMX_CIU_ADDR(0x0768, 0, 0x00, 0)
+#define CVMX_CIU_QLM_JTGD		CVMX_CIU_ADDR(0x0770, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_BIST		CVMX_CIU_ADDR(0x0738, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_PRST1		CVMX_CIU_ADDR(0x0758, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_PRST		CVMX_CIU_ADDR(0x0748, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_RST		CVMX_CIU_ADDR(0x0740, 0, 0x00, 0)
+#define CVMX_CIU_SUM2_PPX_IP4(c)	CVMX_CIU_ADDR(0x8C00, c, 0x0F, 8)
+#define CVMX_CIU_TIM_MULTI_CAST		CVMX_CIU_ADDR(0xC200, 0, 0x00, 0)
+#define CVMX_CIU_TIMX(c)		CVMX_CIU_ADDR(0x0480, c, 0x0F, 8)
+
+static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned int coreid)
 {
-	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100600ull) + (offset) * 8;
-	}
-	return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
+	if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK))
+		return CVMX_CIU_ADDR(0x100100600, coreid, 0x0F, 8);
+	else
+		return CVMX_CIU_ADDR(0x000000680, coreid, 0x0F, 8);
 }
 
-static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned long offset)
+static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned int coreid)
 {
-	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100400ull) + (offset) * 8;
-	}
-	return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
+	if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK))
+		return CVMX_CIU_ADDR(0x100100400, coreid, 0x0F, 8);
+	else
+		return CVMX_CIU_ADDR(0x000000600, coreid, 0x0F, 8);
 }
 
-#define CVMX_CIU_NMI (CVMX_ADD_IO_SEG(0x0001070000000718ull))
-#define CVMX_CIU_PCI_INTA (CVMX_ADD_IO_SEG(0x0001070000000750ull))
-#define CVMX_CIU_PP_BIST_STAT (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
-#define CVMX_CIU_PP_DBG (CVMX_ADD_IO_SEG(0x0001070000000708ull))
-static inline uint64_t CVMX_CIU_PP_POKEX(unsigned long offset)
+static inline uint64_t CVMX_CIU_PP_POKEX(unsigned int coreid)
 {
 	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN70XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
 	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100200ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x100100200, coreid, 0x0F, 8);
 	case OCTEON_CNF75XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN73XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN78XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001010000030000ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x000030000, coreid, 0x0F, 8) -
+			0x60000000000ull;
+	default:
+		return CVMX_CIU_ADDR(0x000000580, coreid, 0x0F, 8);
 	}
-	return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
 }
 
-#define CVMX_CIU_PP_RST (CVMX_ADD_IO_SEG(0x0001070000000700ull))
-#define CVMX_CIU_QLM0 (CVMX_ADD_IO_SEG(0x0001070000000780ull))
-#define CVMX_CIU_QLM1 (CVMX_ADD_IO_SEG(0x0001070000000788ull))
-#define CVMX_CIU_QLM2 (CVMX_ADD_IO_SEG(0x0001070000000790ull))
-#define CVMX_CIU_QLM3 (CVMX_ADD_IO_SEG(0x0001070000000798ull))
-#define CVMX_CIU_QLM4 (CVMX_ADD_IO_SEG(0x00010700000007A0ull))
-#define CVMX_CIU_QLM_DCOK (CVMX_ADD_IO_SEG(0x0001070000000760ull))
-#define CVMX_CIU_QLM_JTGC (CVMX_ADD_IO_SEG(0x0001070000000768ull))
-#define CVMX_CIU_QLM_JTGD (CVMX_ADD_IO_SEG(0x0001070000000770ull))
-#define CVMX_CIU_SOFT_BIST (CVMX_ADD_IO_SEG(0x0001070000000738ull))
-#define CVMX_CIU_SOFT_PRST (CVMX_ADD_IO_SEG(0x0001070000000748ull))
-#define CVMX_CIU_SOFT_PRST1 (CVMX_ADD_IO_SEG(0x0001070000000758ull))
-#define CVMX_CIU_SOFT_PRST2 (CVMX_ADD_IO_SEG(0x00010700000007D8ull))
-#define CVMX_CIU_SOFT_PRST3 (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
-#define CVMX_CIU_SOFT_RST (CVMX_ADD_IO_SEG(0x0001070000000740ull))
-#define CVMX_CIU_SUM1_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008600ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_SUM1_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008000ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM1_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008200ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM1_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008400ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008E00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_SUM2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008A00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008C00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_TIMX(offset) (CVMX_ADD_IO_SEG(0x0001070000000480ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_TIM_MULTI_CAST (CVMX_ADD_IO_SEG(0x000107000000C200ull))
-static inline uint64_t CVMX_CIU_WDOGX(unsigned long offset)
+static inline uint64_t CVMX_CIU_WDOGX(unsigned int coreid)
 {
 	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN70XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
 	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100000ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x100100000, coreid, 0x0F, 8);
 	case OCTEON_CNF75XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN73XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN78XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001010000020000ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x000020000, coreid, 0x0F, 8) -
+			0x60000000000ull;
+	default:
+		return CVMX_CIU_ADDR(0x000000500, coreid, 0x0F, 8);
 	}
-	return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
 }
 
-union cvmx_ciu_bist {
-	uint64_t u64;
-	struct cvmx_ciu_bist_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_7_63:57;
-		uint64_t bist:7;
-#else
-		uint64_t bist:7;
-		uint64_t reserved_7_63:57;
-#endif
-	} s;
-	struct cvmx_ciu_bist_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t bist:4;
-#else
-		uint64_t bist:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_bist_cn30xx cn31xx;
-	struct cvmx_ciu_bist_cn30xx cn38xx;
-	struct cvmx_ciu_bist_cn30xx cn38xxp2;
-	struct cvmx_ciu_bist_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t bist:2;
-#else
-		uint64_t bist:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_bist_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_3_63:61;
-		uint64_t bist:3;
-#else
-		uint64_t bist:3;
-		uint64_t reserved_3_63:61;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_bist_cn52xx cn52xxp1;
-	struct cvmx_ciu_bist_cn30xx cn56xx;
-	struct cvmx_ciu_bist_cn30xx cn56xxp1;
-	struct cvmx_ciu_bist_cn30xx cn58xx;
-	struct cvmx_ciu_bist_cn30xx cn58xxp1;
-	struct cvmx_ciu_bist_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t bist:6;
-#else
-		uint64_t bist:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_bist_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_5_63:59;
-		uint64_t bist:5;
-#else
-		uint64_t bist:5;
-		uint64_t reserved_5_63:59;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_bist_cn63xx cn63xxp1;
-	struct cvmx_ciu_bist_cn61xx cn66xx;
-	struct cvmx_ciu_bist_s cn68xx;
-	struct cvmx_ciu_bist_s cn68xxp1;
-	struct cvmx_ciu_bist_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_block_int {
-	uint64_t u64;
-	struct cvmx_ciu_block_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_62_63:2;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_43_59:17;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t dfm:1;
-		uint64_t reserved_34_39:6;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_31_31:1;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_24_24:1;
-		uint64_t asxpcs1:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t gmx1:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t gmx1:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t asxpcs1:1;
-		uint64_t reserved_24_24:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_31:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t reserved_34_39:6;
-		uint64_t dfm:1;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_59:17;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_63:2;
-#endif
-	} s;
-	struct cvmx_ciu_block_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_43_63:21;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t reserved_31_40:10;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_24_24:1;
-		uint64_t asxpcs1:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t gmx1:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t gmx1:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t asxpcs1:1;
-		uint64_t reserved_24_24:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_40:10;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_63:21;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_block_int_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_43_63:21;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t dfm:1;
-		uint64_t reserved_34_39:6;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_31_31:1;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t reserved_2_2:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t reserved_2_2:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_31:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t reserved_34_39:6;
-		uint64_t dfm:1;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_63:21;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_block_int_cn63xx cn63xxp1;
-	struct cvmx_ciu_block_int_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_62_63:2;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_43_59:17;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t dfm:1;
-		uint64_t reserved_33_39:7;
-		uint64_t srio0:1;
-		uint64_t reserved_31_31:1;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_24_24:1;
-		uint64_t asxpcs1:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t gmx1:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t gmx1:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t asxpcs1:1;
-		uint64_t reserved_24_24:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_31:1;
-		uint64_t srio0:1;
-		uint64_t reserved_33_39:7;
-		uint64_t dfm:1;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_59:17;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_63:2;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_block_int_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_43_63:21;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t reserved_31_40:10;
-		uint64_t iob:1;
-		uint64_t reserved_27_29:3;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_6_8:3;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t reserved_2_2:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t reserved_2_2:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t reserved_6_8:3;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_29:3;
-		uint64_t iob:1;
-		uint64_t reserved_31_40:10;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_63:21;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_dint {
-	uint64_t u64;
-	struct cvmx_ciu_dint_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t dint:32;
-#else
-		uint64_t dint:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_dint_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t dint:1;
-#else
-		uint64_t dint:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_dint_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t dint:2;
-#else
-		uint64_t dint:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_dint_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t dint:16;
-#else
-		uint64_t dint:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_dint_cn38xx cn38xxp2;
-	struct cvmx_ciu_dint_cn31xx cn50xx;
-	struct cvmx_ciu_dint_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t dint:4;
-#else
-		uint64_t dint:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_dint_cn52xx cn52xxp1;
-	struct cvmx_ciu_dint_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t dint:12;
-#else
-		uint64_t dint:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_dint_cn56xx cn56xxp1;
-	struct cvmx_ciu_dint_cn38xx cn58xx;
-	struct cvmx_ciu_dint_cn38xx cn58xxp1;
-	struct cvmx_ciu_dint_cn52xx cn61xx;
-	struct cvmx_ciu_dint_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t dint:6;
-#else
-		uint64_t dint:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_dint_cn63xx cn63xxp1;
-	struct cvmx_ciu_dint_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t dint:10;
-#else
-		uint64_t dint:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_dint_s cn68xx;
-	struct cvmx_ciu_dint_s cn68xxp1;
-	struct cvmx_ciu_dint_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int {
-	uint64_t u64;
-	struct cvmx_ciu_en2_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_iox_int_cn61xx cn66xx;
-	struct cvmx_ciu_en2_iox_int_s cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_iox_int_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_iox_int_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_iox_int_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_iox_int_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_iox_int_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_iox_int_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_iox_int_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_iox_int_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2 {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip2_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip2_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3 {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip3_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip3_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4 {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip4_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip4_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_fuse {
-	uint64_t u64;
-	struct cvmx_ciu_fuse_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t fuse:32;
-#else
-		uint64_t fuse:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_fuse_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t fuse:1;
-#else
-		uint64_t fuse:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_fuse_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t fuse:2;
-#else
-		uint64_t fuse:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_fuse_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t fuse:16;
-#else
-		uint64_t fuse:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_fuse_cn38xx cn38xxp2;
-	struct cvmx_ciu_fuse_cn31xx cn50xx;
-	struct cvmx_ciu_fuse_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t fuse:4;
-#else
-		uint64_t fuse:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_fuse_cn52xx cn52xxp1;
-	struct cvmx_ciu_fuse_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t fuse:12;
-#else
-		uint64_t fuse:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_fuse_cn56xx cn56xxp1;
-	struct cvmx_ciu_fuse_cn38xx cn58xx;
-	struct cvmx_ciu_fuse_cn38xx cn58xxp1;
-	struct cvmx_ciu_fuse_cn52xx cn61xx;
-	struct cvmx_ciu_fuse_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t fuse:6;
-#else
-		uint64_t fuse:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_fuse_cn63xx cn63xxp1;
-	struct cvmx_ciu_fuse_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t fuse:10;
-#else
-		uint64_t fuse:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_fuse_s cn68xx;
-	struct cvmx_ciu_fuse_s cn68xxp1;
-	struct cvmx_ciu_fuse_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_gstop {
-	uint64_t u64;
-	struct cvmx_ciu_gstop_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t gstop:1;
-#else
-		uint64_t gstop:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_gstop_s cn30xx;
-	struct cvmx_ciu_gstop_s cn31xx;
-	struct cvmx_ciu_gstop_s cn38xx;
-	struct cvmx_ciu_gstop_s cn38xxp2;
-	struct cvmx_ciu_gstop_s cn50xx;
-	struct cvmx_ciu_gstop_s cn52xx;
-	struct cvmx_ciu_gstop_s cn52xxp1;
-	struct cvmx_ciu_gstop_s cn56xx;
-	struct cvmx_ciu_gstop_s cn56xxp1;
-	struct cvmx_ciu_gstop_s cn58xx;
-	struct cvmx_ciu_gstop_s cn58xxp1;
-	struct cvmx_ciu_gstop_s cn61xx;
-	struct cvmx_ciu_gstop_s cn63xx;
-	struct cvmx_ciu_gstop_s cn63xxp1;
-	struct cvmx_ciu_gstop_s cn66xx;
-	struct cvmx_ciu_gstop_s cn68xx;
-	struct cvmx_ciu_gstop_s cn68xxp1;
-	struct cvmx_ciu_gstop_s cnf71xx;
-};
-
-union cvmx_ciu_intx_en0 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en0_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_intx_en0_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_intx_en0_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_intx_en0_cn38xx cn38xxp2;
-	struct cvmx_ciu_intx_en0_cn30xx cn50xx;
-	struct cvmx_ciu_intx_en0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en0_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_en0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en0_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en0_cn38xx cn58xx;
-	struct cvmx_ciu_intx_en0_cn38xx cn58xxp1;
-	struct cvmx_ciu_intx_en0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en0_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en0_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en0_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en0_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en0_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en0_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en0_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en0_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en0_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en0_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en0_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en0_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en0_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en0_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en0_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en0_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en0_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en0_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en1 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en1_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t wdog:1;
-#else
-		uint64_t wdog:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_intx_en1_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t wdog:2;
-#else
-		uint64_t wdog:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_intx_en1_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_intx_en1_cn38xx cn38xxp2;
-	struct cvmx_ciu_intx_en1_cn31xx cn50xx;
-	struct cvmx_ciu_intx_en1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn52xxp1;
-	struct cvmx_ciu_intx_en1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en1_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en1_cn38xx cn58xx;
-	struct cvmx_ciu_intx_en1_cn38xx cn58xxp1;
-	struct cvmx_ciu_intx_en1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en1_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en1_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en1_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en1_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en1_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en1_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en1_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en1_w1c_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en1_w1c_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en1_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en1_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en1_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en1_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en1_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en1_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en1_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en1_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en1_w1s_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en1_w1s_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en1_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en1_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_0_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_en4_0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_0_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en4_0_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_0_cn58xx cn58xxp1;
-	struct cvmx_ciu_intx_en4_0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_0_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_0_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_0_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_0_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_0_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_0_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_1_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t wdog:2;
-#else
-		uint64_t wdog:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_intx_en4_1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn52xxp1;
-	struct cvmx_ciu_intx_en4_1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_1_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en4_1_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_1_cn58xx cn58xxp1;
-	struct cvmx_ciu_intx_en4_1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en4_1_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_1_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_1_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_1_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_1_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_1_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_1_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_sum0 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_sum0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_sum0_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_intx_sum0_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_intx_sum0_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_intx_sum0_cn38xx cn38xxp2;
-	struct cvmx_ciu_intx_sum0_cn30xx cn50xx;
-	struct cvmx_ciu_intx_sum0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_sum0_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_sum0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_sum0_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_sum0_cn38xx cn58xx;
-	struct cvmx_ciu_intx_sum0_cn38xx cn58xxp1;
-	struct cvmx_ciu_intx_sum0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_sum0_cn52xx cn63xx;
-	struct cvmx_ciu_intx_sum0_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_sum0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_sum0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_sum4 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_sum4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_sum4_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_intx_sum4_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_sum4_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_sum4_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_sum4_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_sum4_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_sum4_cn58xx cn58xxp1;
-	struct cvmx_ciu_intx_sum4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_sum4_cn52xx cn63xx;
-	struct cvmx_ciu_intx_sum4_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_sum4_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_sum4_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_int33_sum0 {
-	uint64_t u64;
-	struct cvmx_ciu_int33_sum0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_int33_sum0_s cn61xx;
-	struct cvmx_ciu_int33_sum0_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_int33_sum0_cn63xx cn63xxp1;
-	struct cvmx_ciu_int33_sum0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_int33_sum0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_int_dbg_sel {
-	uint64_t u64;
-	struct cvmx_ciu_int_dbg_sel_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t sel:3;
-		uint64_t reserved_10_15:6;
-		uint64_t irq:2;
-		uint64_t reserved_5_7:3;
-		uint64_t pp:5;
-#else
-		uint64_t pp:5;
-		uint64_t reserved_5_7:3;
-		uint64_t irq:2;
-		uint64_t reserved_10_15:6;
-		uint64_t sel:3;
-		uint64_t reserved_19_63:45;
-#endif
-	} s;
-	struct cvmx_ciu_int_dbg_sel_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t sel:3;
-		uint64_t reserved_10_15:6;
-		uint64_t irq:2;
-		uint64_t reserved_4_7:4;
-		uint64_t pp:4;
-#else
-		uint64_t pp:4;
-		uint64_t reserved_4_7:4;
-		uint64_t irq:2;
-		uint64_t reserved_10_15:6;
-		uint64_t sel:3;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_int_dbg_sel_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t sel:3;
-		uint64_t reserved_10_15:6;
-		uint64_t irq:2;
-		uint64_t reserved_3_7:5;
-		uint64_t pp:3;
-#else
-		uint64_t pp:3;
-		uint64_t reserved_3_7:5;
-		uint64_t irq:2;
-		uint64_t reserved_10_15:6;
-		uint64_t sel:3;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_int_dbg_sel_cn61xx cn66xx;
-	struct cvmx_ciu_int_dbg_sel_s cn68xx;
-	struct cvmx_ciu_int_dbg_sel_s cn68xxp1;
-	struct cvmx_ciu_int_dbg_sel_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_int_sum1 {
-	uint64_t u64;
-	struct cvmx_ciu_int_sum1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_int_sum1_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t wdog:1;
-#else
-		uint64_t wdog:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_int_sum1_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t wdog:2;
-#else
-		uint64_t wdog:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_int_sum1_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_int_sum1_cn38xx cn38xxp2;
-	struct cvmx_ciu_int_sum1_cn31xx cn50xx;
-	struct cvmx_ciu_int_sum1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_int_sum1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn52xxp1;
-	struct cvmx_ciu_int_sum1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_int_sum1_cn56xx cn56xxp1;
-	struct cvmx_ciu_int_sum1_cn38xx cn58xx;
-	struct cvmx_ciu_int_sum1_cn38xx cn58xxp1;
-	struct cvmx_ciu_int_sum1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_int_sum1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_int_sum1_cn63xx cn63xxp1;
-	struct cvmx_ciu_int_sum1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_int_sum1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_37_46:10;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_46:10;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_mbox_clrx {
-	uint64_t u64;
-	struct cvmx_ciu_mbox_clrx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t bits:32;
-#else
-		uint64_t bits:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_mbox_clrx_s cn30xx;
-	struct cvmx_ciu_mbox_clrx_s cn31xx;
-	struct cvmx_ciu_mbox_clrx_s cn38xx;
-	struct cvmx_ciu_mbox_clrx_s cn38xxp2;
-	struct cvmx_ciu_mbox_clrx_s cn50xx;
-	struct cvmx_ciu_mbox_clrx_s cn52xx;
-	struct cvmx_ciu_mbox_clrx_s cn52xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn56xx;
-	struct cvmx_ciu_mbox_clrx_s cn56xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn58xx;
-	struct cvmx_ciu_mbox_clrx_s cn58xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn61xx;
-	struct cvmx_ciu_mbox_clrx_s cn63xx;
-	struct cvmx_ciu_mbox_clrx_s cn63xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn66xx;
-	struct cvmx_ciu_mbox_clrx_s cn68xx;
-	struct cvmx_ciu_mbox_clrx_s cn68xxp1;
-	struct cvmx_ciu_mbox_clrx_s cnf71xx;
-};
-
-union cvmx_ciu_mbox_setx {
-	uint64_t u64;
-	struct cvmx_ciu_mbox_setx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t bits:32;
-#else
-		uint64_t bits:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_mbox_setx_s cn30xx;
-	struct cvmx_ciu_mbox_setx_s cn31xx;
-	struct cvmx_ciu_mbox_setx_s cn38xx;
-	struct cvmx_ciu_mbox_setx_s cn38xxp2;
-	struct cvmx_ciu_mbox_setx_s cn50xx;
-	struct cvmx_ciu_mbox_setx_s cn52xx;
-	struct cvmx_ciu_mbox_setx_s cn52xxp1;
-	struct cvmx_ciu_mbox_setx_s cn56xx;
-	struct cvmx_ciu_mbox_setx_s cn56xxp1;
-	struct cvmx_ciu_mbox_setx_s cn58xx;
-	struct cvmx_ciu_mbox_setx_s cn58xxp1;
-	struct cvmx_ciu_mbox_setx_s cn61xx;
-	struct cvmx_ciu_mbox_setx_s cn63xx;
-	struct cvmx_ciu_mbox_setx_s cn63xxp1;
-	struct cvmx_ciu_mbox_setx_s cn66xx;
-	struct cvmx_ciu_mbox_setx_s cn68xx;
-	struct cvmx_ciu_mbox_setx_s cn68xxp1;
-	struct cvmx_ciu_mbox_setx_s cnf71xx;
-};
-
-union cvmx_ciu_nmi {
-	uint64_t u64;
-	struct cvmx_ciu_nmi_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t nmi:32;
-#else
-		uint64_t nmi:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_nmi_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t nmi:1;
-#else
-		uint64_t nmi:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_nmi_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t nmi:2;
-#else
-		uint64_t nmi:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_nmi_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t nmi:16;
-#else
-		uint64_t nmi:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_nmi_cn38xx cn38xxp2;
-	struct cvmx_ciu_nmi_cn31xx cn50xx;
-	struct cvmx_ciu_nmi_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t nmi:4;
-#else
-		uint64_t nmi:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_nmi_cn52xx cn52xxp1;
-	struct cvmx_ciu_nmi_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t nmi:12;
-#else
-		uint64_t nmi:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_nmi_cn56xx cn56xxp1;
-	struct cvmx_ciu_nmi_cn38xx cn58xx;
-	struct cvmx_ciu_nmi_cn38xx cn58xxp1;
-	struct cvmx_ciu_nmi_cn52xx cn61xx;
-	struct cvmx_ciu_nmi_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t nmi:6;
-#else
-		uint64_t nmi:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_nmi_cn63xx cn63xxp1;
-	struct cvmx_ciu_nmi_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t nmi:10;
-#else
-		uint64_t nmi:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_nmi_s cn68xx;
-	struct cvmx_ciu_nmi_s cn68xxp1;
-	struct cvmx_ciu_nmi_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_pci_inta {
-	uint64_t u64;
-	struct cvmx_ciu_pci_inta_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t intr:2;
-#else
-		uint64_t intr:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} s;
-	struct cvmx_ciu_pci_inta_s cn30xx;
-	struct cvmx_ciu_pci_inta_s cn31xx;
-	struct cvmx_ciu_pci_inta_s cn38xx;
-	struct cvmx_ciu_pci_inta_s cn38xxp2;
-	struct cvmx_ciu_pci_inta_s cn50xx;
-	struct cvmx_ciu_pci_inta_s cn52xx;
-	struct cvmx_ciu_pci_inta_s cn52xxp1;
-	struct cvmx_ciu_pci_inta_s cn56xx;
-	struct cvmx_ciu_pci_inta_s cn56xxp1;
-	struct cvmx_ciu_pci_inta_s cn58xx;
-	struct cvmx_ciu_pci_inta_s cn58xxp1;
-	struct cvmx_ciu_pci_inta_s cn61xx;
-	struct cvmx_ciu_pci_inta_s cn63xx;
-	struct cvmx_ciu_pci_inta_s cn63xxp1;
-	struct cvmx_ciu_pci_inta_s cn66xx;
-	struct cvmx_ciu_pci_inta_s cn68xx;
-	struct cvmx_ciu_pci_inta_s cn68xxp1;
-	struct cvmx_ciu_pci_inta_s cnf71xx;
-};
-
-union cvmx_ciu_pp_bist_stat {
-	uint64_t u64;
-	struct cvmx_ciu_pp_bist_stat_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t pp_bist:32;
-#else
-		uint64_t pp_bist:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_pp_bist_stat_s cn68xx;
-	struct cvmx_ciu_pp_bist_stat_s cn68xxp1;
-};
-
-union cvmx_ciu_pp_dbg {
-	uint64_t u64;
-	struct cvmx_ciu_pp_dbg_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t ppdbg:32;
-#else
-		uint64_t ppdbg:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_pp_dbg_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t ppdbg:1;
-#else
-		uint64_t ppdbg:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_pp_dbg_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t ppdbg:2;
-#else
-		uint64_t ppdbg:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_pp_dbg_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t ppdbg:16;
-#else
-		uint64_t ppdbg:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_pp_dbg_cn38xx cn38xxp2;
-	struct cvmx_ciu_pp_dbg_cn31xx cn50xx;
-	struct cvmx_ciu_pp_dbg_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t ppdbg:4;
-#else
-		uint64_t ppdbg:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_pp_dbg_cn52xx cn52xxp1;
-	struct cvmx_ciu_pp_dbg_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t ppdbg:12;
-#else
-		uint64_t ppdbg:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_pp_dbg_cn56xx cn56xxp1;
-	struct cvmx_ciu_pp_dbg_cn38xx cn58xx;
-	struct cvmx_ciu_pp_dbg_cn38xx cn58xxp1;
-	struct cvmx_ciu_pp_dbg_cn52xx cn61xx;
-	struct cvmx_ciu_pp_dbg_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t ppdbg:6;
-#else
-		uint64_t ppdbg:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_pp_dbg_cn63xx cn63xxp1;
-	struct cvmx_ciu_pp_dbg_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t ppdbg:10;
-#else
-		uint64_t ppdbg:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_pp_dbg_s cn68xx;
-	struct cvmx_ciu_pp_dbg_s cn68xxp1;
-	struct cvmx_ciu_pp_dbg_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_pp_pokex {
-	uint64_t u64;
-	struct cvmx_ciu_pp_pokex_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t poke:64;
-#else
-		uint64_t poke:64;
-#endif
-	} s;
-	struct cvmx_ciu_pp_pokex_s cn30xx;
-	struct cvmx_ciu_pp_pokex_s cn31xx;
-	struct cvmx_ciu_pp_pokex_s cn38xx;
-	struct cvmx_ciu_pp_pokex_s cn38xxp2;
-	struct cvmx_ciu_pp_pokex_s cn50xx;
-	struct cvmx_ciu_pp_pokex_s cn52xx;
-	struct cvmx_ciu_pp_pokex_s cn52xxp1;
-	struct cvmx_ciu_pp_pokex_s cn56xx;
-	struct cvmx_ciu_pp_pokex_s cn56xxp1;
-	struct cvmx_ciu_pp_pokex_s cn58xx;
-	struct cvmx_ciu_pp_pokex_s cn58xxp1;
-	struct cvmx_ciu_pp_pokex_s cn61xx;
-	struct cvmx_ciu_pp_pokex_s cn63xx;
-	struct cvmx_ciu_pp_pokex_s cn63xxp1;
-	struct cvmx_ciu_pp_pokex_s cn66xx;
-	struct cvmx_ciu_pp_pokex_s cn68xx;
-	struct cvmx_ciu_pp_pokex_s cn68xxp1;
-	struct cvmx_ciu_pp_pokex_s cnf71xx;
-};
-
-union cvmx_ciu_pp_rst {
-	uint64_t u64;
-	struct cvmx_ciu_pp_rst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t rst:31;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:31;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_pp_rst_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_pp_rst_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t rst:1;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:1;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_pp_rst_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t rst:15;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:15;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_pp_rst_cn38xx cn38xxp2;
-	struct cvmx_ciu_pp_rst_cn31xx cn50xx;
-	struct cvmx_ciu_pp_rst_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t rst:3;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:3;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_pp_rst_cn52xx cn52xxp1;
-	struct cvmx_ciu_pp_rst_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t rst:11;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:11;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_pp_rst_cn56xx cn56xxp1;
-	struct cvmx_ciu_pp_rst_cn38xx cn58xx;
-	struct cvmx_ciu_pp_rst_cn38xx cn58xxp1;
-	struct cvmx_ciu_pp_rst_cn52xx cn61xx;
-	struct cvmx_ciu_pp_rst_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t rst:5;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:5;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_pp_rst_cn63xx cn63xxp1;
-	struct cvmx_ciu_pp_rst_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t rst:9;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:9;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_pp_rst_s cn68xx;
-	struct cvmx_ciu_pp_rst_s cn68xxp1;
-	struct cvmx_ciu_pp_rst_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_qlm0 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm0_s cn61xx;
-	struct cvmx_ciu_qlm0_s cn63xx;
-	struct cvmx_ciu_qlm0_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_20_30:11;
-		uint64_t txdeemph:4;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:4;
-		uint64_t reserved_20_30:11;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn63xxp1;
-	struct cvmx_ciu_qlm0_s cn66xx;
-	struct cvmx_ciu_qlm0_cn68xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn68xx;
-	struct cvmx_ciu_qlm0_cn68xx cn68xxp1;
-	struct cvmx_ciu_qlm0_s cnf71xx;
-};
-
-union cvmx_ciu_qlm1 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm1_s cn61xx;
-	struct cvmx_ciu_qlm1_s cn63xx;
-	struct cvmx_ciu_qlm1_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_20_30:11;
-		uint64_t txdeemph:4;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:4;
-		uint64_t reserved_20_30:11;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn63xxp1;
-	struct cvmx_ciu_qlm1_s cn66xx;
-	struct cvmx_ciu_qlm1_s cn68xx;
-	struct cvmx_ciu_qlm1_s cn68xxp1;
-	struct cvmx_ciu_qlm1_s cnf71xx;
-};
-
-union cvmx_ciu_qlm2 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_qlm2_cn61xx cn63xx;
-	struct cvmx_ciu_qlm2_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_20_30:11;
-		uint64_t txdeemph:4;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:4;
-		uint64_t reserved_20_30:11;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn63xxp1;
-	struct cvmx_ciu_qlm2_cn61xx cn66xx;
-	struct cvmx_ciu_qlm2_s cn68xx;
-	struct cvmx_ciu_qlm2_s cn68xxp1;
-	struct cvmx_ciu_qlm2_cn61xx cnf71xx;
-};
 
-union cvmx_ciu_qlm3 {
+union cvmx_ciu_qlm {
 	uint64_t u64;
-	struct cvmx_ciu_qlm3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
+	struct cvmx_ciu_qlm_s {
+		__BITFIELD_FIELD(uint64_t g2bypass:1,
+		__BITFIELD_FIELD(uint64_t reserved_53_62:10,
+		__BITFIELD_FIELD(uint64_t g2deemph:5,
+		__BITFIELD_FIELD(uint64_t reserved_45_47:3,
+		__BITFIELD_FIELD(uint64_t g2margin:5,
+		__BITFIELD_FIELD(uint64_t reserved_32_39:8,
+		__BITFIELD_FIELD(uint64_t txbypass:1,
+		__BITFIELD_FIELD(uint64_t reserved_21_30:10,
+		__BITFIELD_FIELD(uint64_t txdeemph:5,
+		__BITFIELD_FIELD(uint64_t reserved_13_15:3,
+		__BITFIELD_FIELD(uint64_t txmargin:5,
+		__BITFIELD_FIELD(uint64_t reserved_4_7:4,
+		__BITFIELD_FIELD(uint64_t lane_en:4,
+		;)))))))))))))
 	} s;
-	struct cvmx_ciu_qlm3_s cn68xx;
-	struct cvmx_ciu_qlm3_s cn68xxp1;
-};
-
-union cvmx_ciu_qlm4 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm4_s cn68xx;
-	struct cvmx_ciu_qlm4_s cn68xxp1;
-};
-
-union cvmx_ciu_qlm_dcok {
-	uint64_t u64;
-	struct cvmx_ciu_qlm_dcok_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t qlm_dcok:4;
-#else
-		uint64_t qlm_dcok:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} s;
-	struct cvmx_ciu_qlm_dcok_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t qlm_dcok:2;
-#else
-		uint64_t qlm_dcok:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_qlm_dcok_cn52xx cn52xxp1;
-	struct cvmx_ciu_qlm_dcok_s cn56xx;
-	struct cvmx_ciu_qlm_dcok_s cn56xxp1;
 };
 
 union cvmx_ciu_qlm_jtgc {
 	uint64_t u64;
 	struct cvmx_ciu_qlm_jtgc_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_17_63:47;
-		uint64_t bypass_ext:1;
-		uint64_t reserved_11_15:5;
-		uint64_t clk_div:3;
-		uint64_t reserved_7_7:1;
-		uint64_t mux_sel:3;
-		uint64_t bypass:4;
-#else
-		uint64_t bypass:4;
-		uint64_t mux_sel:3;
-		uint64_t reserved_7_7:1;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_15:5;
-		uint64_t bypass_ext:1;
-		uint64_t reserved_17_63:47;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_17_63:47,
+		__BITFIELD_FIELD(uint64_t bypass_ext:1,
+		__BITFIELD_FIELD(uint64_t reserved_11_15:5,
+		__BITFIELD_FIELD(uint64_t clk_div:3,
+		__BITFIELD_FIELD(uint64_t reserved_7_7:1,
+		__BITFIELD_FIELD(uint64_t mux_sel:3,
+		__BITFIELD_FIELD(uint64_t bypass:4,
+		;)))))))
 	} s;
-	struct cvmx_ciu_qlm_jtgc_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_11_63:53;
-		uint64_t clk_div:3;
-		uint64_t reserved_5_7:3;
-		uint64_t mux_sel:1;
-		uint64_t reserved_2_3:2;
-		uint64_t bypass:2;
-#else
-		uint64_t bypass:2;
-		uint64_t reserved_2_3:2;
-		uint64_t mux_sel:1;
-		uint64_t reserved_5_7:3;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_63:53;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_qlm_jtgc_cn52xx cn52xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_11_63:53;
-		uint64_t clk_div:3;
-		uint64_t reserved_6_7:2;
-		uint64_t mux_sel:2;
-		uint64_t bypass:4;
-#else
-		uint64_t bypass:4;
-		uint64_t mux_sel:2;
-		uint64_t reserved_6_7:2;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_63:53;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_qlm_jtgc_cn56xx cn56xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_11_63:53;
-		uint64_t clk_div:3;
-		uint64_t reserved_6_7:2;
-		uint64_t mux_sel:2;
-		uint64_t reserved_3_3:1;
-		uint64_t bypass:3;
-#else
-		uint64_t bypass:3;
-		uint64_t reserved_3_3:1;
-		uint64_t mux_sel:2;
-		uint64_t reserved_6_7:2;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_63:53;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cn63xx;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cn63xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cn66xx;
-	struct cvmx_ciu_qlm_jtgc_s cn68xx;
-	struct cvmx_ciu_qlm_jtgc_s cn68xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cnf71xx;
 };
 
 union cvmx_ciu_qlm_jtgd {
 	uint64_t u64;
 	struct cvmx_ciu_qlm_jtgd_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_45_60:16;
-		uint64_t select:5;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:5;
-		uint64_t reserved_45_60:16;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm_jtgd_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_42_60:19;
-		uint64_t select:2;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:2;
-		uint64_t reserved_42_60:19;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_qlm_jtgd_cn52xx cn52xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_44_60:17;
-		uint64_t select:4;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:4;
-		uint64_t reserved_44_60:17;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_qlm_jtgd_cn56xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_37_60:24;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_60:24;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn56xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_43_60:18;
-		uint64_t select:3;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:3;
-		uint64_t reserved_43_60:18;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cn63xx;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cn63xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cn66xx;
-	struct cvmx_ciu_qlm_jtgd_s cn68xx;
-	struct cvmx_ciu_qlm_jtgd_s cn68xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_soft_bist {
-	uint64_t u64;
-	struct cvmx_ciu_soft_bist_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_bist:1;
-#else
-		uint64_t soft_bist:1;
-		uint64_t reserved_1_63:63;
-#endif
+		__BITFIELD_FIELD(uint64_t capture:1,
+		__BITFIELD_FIELD(uint64_t shift:1,
+		__BITFIELD_FIELD(uint64_t update:1,
+		__BITFIELD_FIELD(uint64_t reserved_45_60:16,
+		__BITFIELD_FIELD(uint64_t select:5,
+		__BITFIELD_FIELD(uint64_t reserved_37_39:3,
+		__BITFIELD_FIELD(uint64_t shft_cnt:5,
+		__BITFIELD_FIELD(uint64_t shft_reg:32,
+		;))))))))
 	} s;
-	struct cvmx_ciu_soft_bist_s cn30xx;
-	struct cvmx_ciu_soft_bist_s cn31xx;
-	struct cvmx_ciu_soft_bist_s cn38xx;
-	struct cvmx_ciu_soft_bist_s cn38xxp2;
-	struct cvmx_ciu_soft_bist_s cn50xx;
-	struct cvmx_ciu_soft_bist_s cn52xx;
-	struct cvmx_ciu_soft_bist_s cn52xxp1;
-	struct cvmx_ciu_soft_bist_s cn56xx;
-	struct cvmx_ciu_soft_bist_s cn56xxp1;
-	struct cvmx_ciu_soft_bist_s cn58xx;
-	struct cvmx_ciu_soft_bist_s cn58xxp1;
-	struct cvmx_ciu_soft_bist_s cn61xx;
-	struct cvmx_ciu_soft_bist_s cn63xx;
-	struct cvmx_ciu_soft_bist_s cn63xxp1;
-	struct cvmx_ciu_soft_bist_s cn66xx;
-	struct cvmx_ciu_soft_bist_s cn68xx;
-	struct cvmx_ciu_soft_bist_s cn68xxp1;
-	struct cvmx_ciu_soft_bist_s cnf71xx;
 };
 
 union cvmx_ciu_soft_prst {
 	uint64_t u64;
 	struct cvmx_ciu_soft_prst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_3_63:61;
-		uint64_t host64:1;
-		uint64_t npi:1;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t npi:1;
-		uint64_t host64:1;
-		uint64_t reserved_3_63:61;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst_s cn30xx;
-	struct cvmx_ciu_soft_prst_s cn31xx;
-	struct cvmx_ciu_soft_prst_s cn38xx;
-	struct cvmx_ciu_soft_prst_s cn38xxp2;
-	struct cvmx_ciu_soft_prst_s cn50xx;
-	struct cvmx_ciu_soft_prst_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn52xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cn56xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn56xxp1;
-	struct cvmx_ciu_soft_prst_s cn58xx;
-	struct cvmx_ciu_soft_prst_s cn58xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cn61xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn63xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn63xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cn66xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn68xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn68xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_soft_prst1 {
-	uint64_t u64;
-	struct cvmx_ciu_soft_prst1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst1_s cn52xx;
-	struct cvmx_ciu_soft_prst1_s cn52xxp1;
-	struct cvmx_ciu_soft_prst1_s cn56xx;
-	struct cvmx_ciu_soft_prst1_s cn56xxp1;
-	struct cvmx_ciu_soft_prst1_s cn61xx;
-	struct cvmx_ciu_soft_prst1_s cn63xx;
-	struct cvmx_ciu_soft_prst1_s cn63xxp1;
-	struct cvmx_ciu_soft_prst1_s cn66xx;
-	struct cvmx_ciu_soft_prst1_s cn68xx;
-	struct cvmx_ciu_soft_prst1_s cn68xxp1;
-	struct cvmx_ciu_soft_prst1_s cnf71xx;
-};
-
-union cvmx_ciu_soft_prst2 {
-	uint64_t u64;
-	struct cvmx_ciu_soft_prst2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst2_s cn66xx;
-};
-
-union cvmx_ciu_soft_prst3 {
-	uint64_t u64;
-	struct cvmx_ciu_soft_prst3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst3_s cn66xx;
-};
-
-union cvmx_ciu_soft_rst {
-	uint64_t u64;
-	struct cvmx_ciu_soft_rst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_rst:1;
-#else
-		uint64_t soft_rst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_rst_s cn30xx;
-	struct cvmx_ciu_soft_rst_s cn31xx;
-	struct cvmx_ciu_soft_rst_s cn38xx;
-	struct cvmx_ciu_soft_rst_s cn38xxp2;
-	struct cvmx_ciu_soft_rst_s cn50xx;
-	struct cvmx_ciu_soft_rst_s cn52xx;
-	struct cvmx_ciu_soft_rst_s cn52xxp1;
-	struct cvmx_ciu_soft_rst_s cn56xx;
-	struct cvmx_ciu_soft_rst_s cn56xxp1;
-	struct cvmx_ciu_soft_rst_s cn58xx;
-	struct cvmx_ciu_soft_rst_s cn58xxp1;
-	struct cvmx_ciu_soft_rst_s cn61xx;
-	struct cvmx_ciu_soft_rst_s cn63xx;
-	struct cvmx_ciu_soft_rst_s cn63xxp1;
-	struct cvmx_ciu_soft_rst_s cn66xx;
-	struct cvmx_ciu_soft_rst_s cn68xx;
-	struct cvmx_ciu_soft_rst_s cn68xxp1;
-	struct cvmx_ciu_soft_rst_s cnf71xx;
-};
-
-union cvmx_ciu_sum1_iox_int {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_3_63:61,
+		__BITFIELD_FIELD(uint64_t host64:1,
+		__BITFIELD_FIELD(uint64_t npi:1,
+		__BITFIELD_FIELD(uint64_t soft_prst:1,
+		;))))
 	} s;
-	struct cvmx_ciu_sum1_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_iox_int_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_iox_int_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip2 {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_ppx_ip2_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_ppx_ip2_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip3 {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_ppx_ip3_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_ppx_ip3_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip4 {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_ppx_ip4_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_ppx_ip4_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum2_iox_int {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_iox_int_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_iox_int_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip2 {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_ppx_ip2_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_ppx_ip2_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip3 {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_ppx_ip3_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_ppx_ip3_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip4 {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_ppx_ip4_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_ppx_ip4_s cnf71xx;
 };
 
 union cvmx_ciu_timx {
 	uint64_t u64;
 	struct cvmx_ciu_timx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_37_63:27;
-		uint64_t one_shot:1;
-		uint64_t len:36;
-#else
-		uint64_t len:36;
-		uint64_t one_shot:1;
-		uint64_t reserved_37_63:27;
-#endif
-	} s;
-	struct cvmx_ciu_timx_s cn30xx;
-	struct cvmx_ciu_timx_s cn31xx;
-	struct cvmx_ciu_timx_s cn38xx;
-	struct cvmx_ciu_timx_s cn38xxp2;
-	struct cvmx_ciu_timx_s cn50xx;
-	struct cvmx_ciu_timx_s cn52xx;
-	struct cvmx_ciu_timx_s cn52xxp1;
-	struct cvmx_ciu_timx_s cn56xx;
-	struct cvmx_ciu_timx_s cn56xxp1;
-	struct cvmx_ciu_timx_s cn58xx;
-	struct cvmx_ciu_timx_s cn58xxp1;
-	struct cvmx_ciu_timx_s cn61xx;
-	struct cvmx_ciu_timx_s cn63xx;
-	struct cvmx_ciu_timx_s cn63xxp1;
-	struct cvmx_ciu_timx_s cn66xx;
-	struct cvmx_ciu_timx_s cn68xx;
-	struct cvmx_ciu_timx_s cn68xxp1;
-	struct cvmx_ciu_timx_s cnf71xx;
-};
-
-union cvmx_ciu_tim_multi_cast {
-	uint64_t u64;
-	struct cvmx_ciu_tim_multi_cast_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t en:1;
-#else
-		uint64_t en:1;
-		uint64_t reserved_1_63:63;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_37_63:27,
+		__BITFIELD_FIELD(uint64_t one_shot:1,
+		__BITFIELD_FIELD(uint64_t len:36,
+		;)))
 	} s;
-	struct cvmx_ciu_tim_multi_cast_s cn61xx;
-	struct cvmx_ciu_tim_multi_cast_s cn66xx;
-	struct cvmx_ciu_tim_multi_cast_s cnf71xx;
 };
 
 union cvmx_ciu_wdogx {
 	uint64_t u64;
 	struct cvmx_ciu_wdogx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_46_63:18;
-		uint64_t gstopen:1;
-		uint64_t dstop:1;
-		uint64_t cnt:24;
-		uint64_t len:16;
-		uint64_t state:2;
-		uint64_t mode:2;
-#else
-		uint64_t mode:2;
-		uint64_t state:2;
-		uint64_t len:16;
-		uint64_t cnt:24;
-		uint64_t dstop:1;
-		uint64_t gstopen:1;
-		uint64_t reserved_46_63:18;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_46_63:18,
+		__BITFIELD_FIELD(uint64_t gstopen:1,
+		__BITFIELD_FIELD(uint64_t dstop:1,
+		__BITFIELD_FIELD(uint64_t cnt:24,
+		__BITFIELD_FIELD(uint64_t len:16,
+		__BITFIELD_FIELD(uint64_t state:2,
+		__BITFIELD_FIELD(uint64_t mode:2,
+		;)))))))
 	} s;
-	struct cvmx_ciu_wdogx_s cn30xx;
-	struct cvmx_ciu_wdogx_s cn31xx;
-	struct cvmx_ciu_wdogx_s cn38xx;
-	struct cvmx_ciu_wdogx_s cn38xxp2;
-	struct cvmx_ciu_wdogx_s cn50xx;
-	struct cvmx_ciu_wdogx_s cn52xx;
-	struct cvmx_ciu_wdogx_s cn52xxp1;
-	struct cvmx_ciu_wdogx_s cn56xx;
-	struct cvmx_ciu_wdogx_s cn56xxp1;
-	struct cvmx_ciu_wdogx_s cn58xx;
-	struct cvmx_ciu_wdogx_s cn58xxp1;
-	struct cvmx_ciu_wdogx_s cn61xx;
-	struct cvmx_ciu_wdogx_s cn63xx;
-	struct cvmx_ciu_wdogx_s cn63xxp1;
-	struct cvmx_ciu_wdogx_s cn66xx;
-	struct cvmx_ciu_wdogx_s cn68xx;
-	struct cvmx_ciu_wdogx_s cn68xxp1;
-	struct cvmx_ciu_wdogx_s cnf71xx;
 };
 
-#endif
+#endif /* __CVMX_CIU_DEFS_H__ */
diff --git a/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h b/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h
index e347496a33c3..80e4f8358b81 100644
--- a/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -2070,6 +2070,8 @@ static inline uint64_t CVMX_GMXX_XAUI_EXT_LOOPBACK(unsigned long block_id)
 	return CVMX_ADD_IO_SEG(0x0001180008000540ull) + (block_id) * 0x8000000ull;
 }
 
+void __cvmx_interrupt_gmxx_enable(int interface);
+
 union cvmx_gmxx_bad_reg {
 	uint64_t u64;
 	struct cvmx_gmxx_bad_reg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h b/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h
index a5e8fd861c37..39da7f9d7b3f 100644
--- a/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -334,6 +334,8 @@ static inline uint64_t CVMX_PCSX_TX_RXX_POLARITY_REG(unsigned long offset, unsig
 	return CVMX_ADD_IO_SEG(0x00011800B0001048ull) + ((offset) + (block_id) * 0x20000ull) * 1024;
 }
 
+void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
+
 union cvmx_pcsx_anx_adv_reg {
 	uint64_t u64;
 	struct cvmx_pcsx_anx_adv_reg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h b/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h
index b5b45d26f1c5..847dd9dca6ea 100644
--- a/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -268,6 +268,8 @@ static inline uint64_t CVMX_PCSXX_TX_RX_STATES_REG(unsigned long block_id)
 	return CVMX_ADD_IO_SEG(0x00011800B0000830ull) + (block_id) * 0x1000000ull;
 }
 
+void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
+
 union cvmx_pcsxx_10gbx_status_reg {
 	uint64_t u64;
 	struct cvmx_pcsxx_10gbx_status_reg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-spxx-defs.h b/arch/mips/include/asm/octeon/cvmx-spxx-defs.h
index c7d601d9446e..f4c4e8051160 100644
--- a/arch/mips/include/asm/octeon/cvmx-spxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-spxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -45,6 +45,8 @@
 #define CVMX_SPXX_TPA_SEL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000328ull) + ((block_id) & 1) * 0x8000000ull)
 #define CVMX_SPXX_TRN4_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000360ull) + ((block_id) & 1) * 0x8000000ull)
 
+void __cvmx_interrupt_spxx_int_msk_enable(int index);
+
 union cvmx_spxx_bckprs_cnt {
 	uint64_t u64;
 	struct cvmx_spxx_bckprs_cnt_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-stxx-defs.h b/arch/mips/include/asm/octeon/cvmx-stxx-defs.h
index 146354005d3b..3c409a854d91 100644
--- a/arch/mips/include/asm/octeon/cvmx-stxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-stxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -45,6 +45,8 @@
 #define CVMX_STXX_STAT_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000638ull) + ((block_id) & 1) * 0x8000000ull)
 #define CVMX_STXX_STAT_PKT_XMT(block_id) (CVMX_ADD_IO_SEG(0x0001180090000640ull) + ((block_id) & 1) * 0x8000000ull)
 
+void __cvmx_interrupt_stxx_int_msk_enable(int index);
+
 union cvmx_stxx_arb_ctl {
 	uint64_t u64;
 	struct cvmx_stxx_arb_ctl_s {
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index c99c4b6a79f4..60481502826a 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -279,13 +279,12 @@ union octeon_cvmemctl {
 	} s;
 };
 
-extern void octeon_write_lcd(const char *s);
 extern void octeon_check_cpu_bist(void);
-extern int octeon_get_boot_uart(void);
 
-struct uart_port;
-extern unsigned int octeon_serial_in(struct uart_port *, int);
-extern void octeon_serial_out(struct uart_port *, int, int);
+int octeon_prune_device_tree(void);
+extern const char __appended_dtb;
+extern const char __dtb_octeon_3xxx_begin;
+extern const char __dtb_octeon_68xx_begin;
 
 /**
  * Write a 32bit value to the Octeon NPI register space
diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h
index 1884609741a8..b12d9a3fbfb6 100644
--- a/arch/mips/include/asm/octeon/pci-octeon.h
+++ b/arch/mips/include/asm/octeon/pci-octeon.h
@@ -63,4 +63,7 @@ enum octeon_dma_bar_type {
  */
 extern enum octeon_dma_bar_type octeon_dma_bar_type;
 
+void octeon_pci_dma_init(void);
+extern char *octeon_swiotlb;
+
 #endif
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index ad461216b5a1..e8cc328fce2d 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -80,7 +80,12 @@ extern void build_copy_page(void);
  * used in our early mem init code for all memory models.
  * So always define it.
  */
-#define ARCH_PFN_OFFSET		PFN_UP(PHYS_OFFSET)
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+extern unsigned long ARCH_PFN_OFFSET;
+# define ARCH_PFN_OFFSET	ARCH_PFN_OFFSET
+#else
+# define ARCH_PFN_OFFSET	PFN_UP(PHYS_OFFSET)
+#endif
 
 extern void clear_page(void * page);
 extern void copy_page(void * to, void * from);
@@ -252,8 +257,8 @@ extern int __virt_addr_valid(const volatile void *kaddr);
 	 ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
 	 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
-#define UNCAC_ADDR(addr)	((addr) - PAGE_OFFSET + UNCAC_BASE)
-#define CAC_ADDR(addr)		((addr) - UNCAC_BASE + PAGE_OFFSET)
+#define UNCAC_ADDR(addr)	(UNCAC_BASE + __pa(addr))
+#define CAC_ADDR(addr)		((unsigned long)__va((addr) - UNCAC_BASE))
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index af34afbc32d9..b2fa62922d88 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -141,7 +141,7 @@ struct mips_fpu_struct {
 
 #define NUM_DSP_REGS   6
 
-typedef __u32 dspreg_t;
+typedef unsigned long dspreg_t;
 
 struct mips_dsp_state {
 	dspreg_t	dspr[NUM_DSP_REGS];
@@ -386,7 +386,20 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29])
 #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
 
+#ifdef CONFIG_CPU_LOONGSON3
+/*
+ * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a
+ * tight read loop is executed, because reads take priority over writes & the
+ * hardware (incorrectly) doesn't ensure that writes will eventually occur.
+ *
+ * Since spin loops of any kind should have a cpu_relax() in them, force an SFB
+ * flush from cpu_relax() such that any pending writes will become visible as
+ * expected.
+ */
+#define cpu_relax()	smp_mb()
+#else
 #define cpu_relax()	barrier()
+#endif
 
 /*
  * Return_address is a replacement for __builtin_return_address(count)
diff --git a/arch/mips/include/asm/setup.h b/arch/mips/include/asm/setup.h
index d49d247d48a1..bb36a400203d 100644
--- a/arch/mips/include/asm/setup.h
+++ b/arch/mips/include/asm/setup.h
@@ -2,8 +2,10 @@
 #ifndef _MIPS_SETUP_H
 #define _MIPS_SETUP_H
 
+#include <linux/types.h>
 #include <uapi/asm/setup.h>
 
+extern void prom_putchar(char);
 extern void setup_early_printk(void);
 
 #ifdef CONFIG_EARLY_PRINTK_8250
diff --git a/arch/mips/include/asm/sgialib.h b/arch/mips/include/asm/sgialib.h
index 195db5045ae5..0d9fad5915fe 100644
--- a/arch/mips/include/asm/sgialib.h
+++ b/arch/mips/include/asm/sgialib.h
@@ -31,7 +31,6 @@ extern int prom_flags;
 #define PROM_FLAG_DONT_FREE_TEMP	4
 
 /* Simple char-by-char console I/O. */
-extern void prom_putchar(char c);
 extern char prom_getchar(void);
 
 /* Get next memory descriptor after CURR, returns first descriptor
diff --git a/arch/mips/include/asm/sim.h b/arch/mips/include/asm/sim.h
index 91831800c480..59f31a95facd 100644
--- a/arch/mips/include/asm/sim.h
+++ b/arch/mips/include/asm/sim.h
@@ -39,8 +39,6 @@ __asm__(								\
 	".end\t__" #symbol "\n\t"					\
 	".size\t__" #symbol",. - __" #symbol)
 
-#define nabi_no_regargs
-
 #endif /* CONFIG_32BIT */
 
 #ifdef CONFIG_64BIT
@@ -67,16 +65,6 @@ __asm__(								\
 	".end\t__" #symbol "\n\t"					\
 	".size\t__" #symbol",. - __" #symbol)
 
-#define nabi_no_regargs							\
-	unsigned long __dummy0,						\
-	unsigned long __dummy1,						\
-	unsigned long __dummy2,						\
-	unsigned long __dummy3,						\
-	unsigned long __dummy4,						\
-	unsigned long __dummy5,						\
-	unsigned long __dummy6,						\
-	unsigned long __dummy7,
-
 #endif /* CONFIG_64BIT */
 
 #endif /* _ASM_SIM_H */
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index 88ebd83b3bf9..056a6bf13491 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -25,7 +25,17 @@ extern cpumask_t cpu_sibling_map[];
 extern cpumask_t cpu_core_map[];
 extern cpumask_t cpu_foreign_map[];
 
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+static inline int raw_smp_processor_id(void)
+{
+#if defined(__VDSO__)
+	extern int vdso_smp_processor_id(void)
+		__compiletime_error("VDSO should not call smp_processor_id()");
+	return vdso_smp_processor_id();
+#else
+	return current_thread_info()->cpu;
+#endif
+}
+#define raw_smp_processor_id raw_smp_processor_id
 
 /* Map from cpu id to sequential logical cpu number.  This will only
    not be idempotent when cpus failed to come on-line.	*/
diff --git a/arch/mips/include/asm/txx9/generic.h b/arch/mips/include/asm/txx9/generic.h
index 64887d3c7ec3..9a2c47bf3c40 100644
--- a/arch/mips/include/asm/txx9/generic.h
+++ b/arch/mips/include/asm/txx9/generic.h
@@ -49,7 +49,6 @@ void txx9_spi_init(int busid, unsigned long base, int irq);
 void txx9_ethaddr_init(unsigned int id, unsigned char *ethaddr);
 void txx9_sio_init(unsigned long baseaddr, int irq,
 		   unsigned int line, unsigned int sclk, int nocts);
-void prom_putchar(char c);
 #ifdef CONFIG_EARLY_PRINTK
 extern void (*txx9_prom_putchar)(char c);
 void txx9_sio_putchar_init(unsigned long baseaddr);
diff --git a/arch/mips/include/asm/txx9/tx4939.h b/arch/mips/include/asm/txx9/tx4939.h
index 6d667087f2aa..00805ac6e9fc 100644
--- a/arch/mips/include/asm/txx9/tx4939.h
+++ b/arch/mips/include/asm/txx9/tx4939.h
@@ -101,13 +101,6 @@ struct tx4939_irc_reg {
 	struct tx4939_le_reg maskext;
 };
 
-struct tx4939_rtc_reg {
-	__u32 ctl;
-	__u32 adr;
-	__u32 dat;
-	__u32 tbc;
-};
-
 struct tx4939_crypto_reg {
 	struct tx4939_le_reg csr;
 	struct tx4939_le_reg idesptr;
@@ -370,26 +363,6 @@ struct tx4939_vpc_desc {
 #define TX4939_CLKCTR_CYPRST	0x00000001
 
 /*
- * RTC
- */
-#define TX4939_RTCCTL_ALME	0x00000080
-#define TX4939_RTCCTL_ALMD	0x00000040
-#define TX4939_RTCCTL_BUSY	0x00000020
-
-#define TX4939_RTCCTL_COMMAND	0x00000007
-#define TX4939_RTCCTL_COMMAND_NOP	0x00000000
-#define TX4939_RTCCTL_COMMAND_GETTIME	0x00000001
-#define TX4939_RTCCTL_COMMAND_SETTIME	0x00000002
-#define TX4939_RTCCTL_COMMAND_GETALARM	0x00000003
-#define TX4939_RTCCTL_COMMAND_SETALARM	0x00000004
-
-#define TX4939_RTCTBC_PM	0x00000080
-#define TX4939_RTCTBC_COMP	0x0000007f
-
-#define TX4939_RTC_REG_RAMSIZE	0x00000100
-#define TX4939_RTC_REG_RWBSIZE	0x00000006
-
-/*
  * CRYPTO
  */
 #define TX4939_CRYPTO_CSR_SAESO 0x08000000
@@ -498,8 +471,6 @@ struct tx4939_vpc_desc {
 #define tx4939_ccfgptr \
 		((struct tx4939_ccfg_reg __iomem *)TX4939_CCFG_REG)
 #define tx4939_sramcptr		tx4938_sramcptr
-#define tx4939_rtcptr \
-		((struct tx4939_rtc_reg __iomem *)TX4939_RTC_REG)
 #define tx4939_cryptoptr \
 		((struct tx4939_crypto_reg __iomem *)TX4939_CRYPTO_REG)
 #define tx4939_vpcptr	((struct tx4939_vpc_reg __iomem *)TX4939_VPC_REG)
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index d626a9a391cc..d31bc2f01208 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -16,6 +16,8 @@
 #include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
 #include <asm/io.h>
@@ -86,6 +88,7 @@ static int __init vdma_init(void)
 	printk(KERN_INFO "VDMA: R4030 DMA pagetables initialized.\n");
 	return 0;
 }
+arch_initcall(vdma_init);
 
 /*
  * Allocate DMA pagetables using a simple first-fit algorithm
@@ -556,4 +559,140 @@ int vdma_get_enable(int channel)
 	return enable;
 }
 
-arch_initcall(vdma_init);
+static void *jazz_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	void *ret;
+
+	ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+	if (!ret)
+		return NULL;
+
+	*dma_handle = vdma_alloc(virt_to_phys(ret), size);
+	if (*dma_handle == VDMA_ERROR) {
+		dma_direct_free(dev, size, ret, *dma_handle, attrs);
+		return NULL;
+	}
+
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT)) {
+		dma_cache_wback_inv((unsigned long)ret, size);
+		ret = (void *)UNCAC_ADDR(ret);
+	}
+	return ret;
+}
+
+static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	vdma_free(dma_handle);
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT))
+		vaddr = (void *)CAC_ADDR((unsigned long)vaddr);
+	return dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+}
+
+static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(dev, phys, size, dir);
+	return vdma_alloc(phys, size);
+}
+
+static void jazz_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_cpu(dev, vdma_log2phys(dma_addr), size, dir);
+	vdma_free(dma_addr);
+}
+
+static int jazz_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nents, i) {
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+				dir);
+		sg->dma_address = vdma_alloc(sg_phys(sg), sg->length);
+		if (sg->dma_address == VDMA_ERROR)
+			return 0;
+		sg_dma_len(sg) = sg->length;
+	}
+
+	return nents;
+}
+
+static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nents, i) {
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length,
+				dir);
+		vdma_free(sg->dma_address);
+	}
+}
+
+static void jazz_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	arch_sync_dma_for_device(dev, vdma_log2phys(addr), size, dir);
+}
+
+static void jazz_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	arch_sync_dma_for_cpu(dev, vdma_log2phys(addr), size, dir);
+}
+
+static void jazz_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+}
+
+static void jazz_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+}
+
+static int jazz_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == VDMA_ERROR;
+}
+
+const struct dma_map_ops jazz_dma_ops = {
+	.alloc			= jazz_dma_alloc,
+	.free			= jazz_dma_free,
+	.mmap			= arch_dma_mmap,
+	.map_page		= jazz_dma_map_page,
+	.unmap_page		= jazz_dma_unmap_page,
+	.map_sg			= jazz_dma_map_sg,
+	.unmap_sg		= jazz_dma_unmap_sg,
+	.sync_single_for_cpu	= jazz_dma_sync_single_for_cpu,
+	.sync_single_for_device	= jazz_dma_sync_single_for_device,
+	.sync_sg_for_cpu	= jazz_dma_sync_sg_for_cpu,
+	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
+	.dma_supported		= dma_direct_supported,
+	.cache_sync		= arch_dma_cache_sync,
+	.mapping_error		= jazz_dma_mapping_error,
+};
+EXPORT_SYMBOL(jazz_dma_ops);
diff --git a/arch/mips/jazz/setup.c b/arch/mips/jazz/setup.c
index 448fd41792e4..1b5e121c3f0d 100644
--- a/arch/mips/jazz/setup.c
+++ b/arch/mips/jazz/setup.c
@@ -16,6 +16,7 @@
 #include <linux/screen_info.h>
 #include <linux/platform_device.h>
 #include <linux/serial_8250.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/jazz.h>
 #include <asm/jazzdma.h>
@@ -136,10 +137,16 @@ static struct resource jazz_esp_rsrc[] = {
 	}
 };
 
+static u64 jazz_esp_dma_mask = DMA_BIT_MASK(32);
+
 static struct platform_device jazz_esp_pdev = {
 	.name		= "jazz_esp",
 	.num_resources	= ARRAY_SIZE(jazz_esp_rsrc),
-	.resource	= jazz_esp_rsrc
+	.resource	= jazz_esp_rsrc,
+	.dev = {
+		.dma_mask	   = &jazz_esp_dma_mask,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
+	}
 };
 
 static struct resource jazz_sonic_rsrc[] = {
@@ -155,10 +162,16 @@ static struct resource jazz_sonic_rsrc[] = {
 	}
 };
 
+static u64 jazz_sonic_dma_mask = DMA_BIT_MASK(32);
+
 static struct platform_device jazz_sonic_pdev = {
 	.name		= "jazzsonic",
 	.num_resources	= ARRAY_SIZE(jazz_sonic_rsrc),
-	.resource	= jazz_sonic_rsrc
+	.resource	= jazz_sonic_rsrc,
+	.dev = {
+		.dma_mask	   = &jazz_sonic_dma_mask,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
+	}
 };
 
 static struct resource jazz_cmos_rsrc[] = {
diff --git a/arch/mips/jz4740/Platform b/arch/mips/jz4740/Platform
index 28448d358c10..a2a5a85ea1f9 100644
--- a/arch/mips/jz4740/Platform
+++ b/arch/mips/jz4740/Platform
@@ -1,4 +1,4 @@
 platform-$(CONFIG_MACH_INGENIC)	+= jz4740/
 cflags-$(CONFIG_MACH_INGENIC)	+= -I$(srctree)/arch/mips/include/asm/mach-jz4740
 load-$(CONFIG_MACH_INGENIC)	+= 0xffffffff80010000
-zload-$(CONFIG_MACH_INGENIC)	+= 0xffffffff80600000
+zload-$(CONFIG_MACH_INGENIC)	+= 0xffffffff81000000
diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c
index 60f0767507c6..af0c8ace0141 100644
--- a/arch/mips/jz4740/board-qi_lb60.c
+++ b/arch/mips/jz4740/board-qi_lb60.c
@@ -29,10 +29,11 @@
 #include <linux/power/gpio-charger.h>
 #include <linux/pwm.h>
 
+#include <linux/platform_data/jz4740/jz4740_nand.h>
+
 #include <asm/mach-jz4740/gpio.h>
 #include <asm/mach-jz4740/jz4740_fb.h>
 #include <asm/mach-jz4740/jz4740_mmc.h>
-#include <asm/mach-jz4740/jz4740_nand.h>
 
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index b2509c19cfb5..d535fc706a8b 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1849,7 +1849,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 			set_elf_platform(cpu, "loongson3a");
 			set_isa(c, MIPS_CPU_ISA_M64R2);
 			break;
-		case PRID_REV_LOONGSON3A_R3:
+		case PRID_REV_LOONGSON3A_R3_0:
+		case PRID_REV_LOONGSON3A_R3_1:
 			c->cputype = CPU_LOONGSON3;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
diff --git a/arch/mips/kernel/early_printk.c b/arch/mips/kernel/early_printk.c
index 505cb77d1280..4a1647ddfbd9 100644
--- a/arch/mips/kernel/early_printk.c
+++ b/arch/mips/kernel/early_printk.c
@@ -14,8 +14,6 @@
 
 #include <asm/setup.h>
 
-extern void prom_putchar(char);
-
 static void early_console_write(struct console *con, const char *s, unsigned n)
 {
 	while (n-- && *s) {
diff --git a/arch/mips/kernel/early_printk_8250.c b/arch/mips/kernel/early_printk_8250.c
index 83cea3767556..ea26614afac6 100644
--- a/arch/mips/kernel/early_printk_8250.c
+++ b/arch/mips/kernel/early_printk_8250.c
@@ -20,6 +20,7 @@
 #include <linux/io.h>
 #include <linux/serial_core.h>
 #include <linux/serial_reg.h>
+#include <asm/setup.h>
 
 static void __iomem *serial8250_base;
 static unsigned int serial8250_reg_shift;
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 37b9383eacd3..6c257b52f57f 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -354,16 +354,56 @@ NESTED(ejtag_debug_handler, PT_SIZE, sp)
 	sll	k0, k0, 30	# Check for SDBBP.
 	bgez	k0, ejtag_return
 
+#ifdef CONFIG_SMP
+1:	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	ll	k0, 0(k0)
+	bnez	k0, 1b
+	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	sc	k0, 0(k0)
+	beqz	k0, 1b
+# ifdef CONFIG_WEAK_REORDERING_BEYOND_LLSC
+	sync
+# endif
+
+	PTR_LA	k0, ejtag_debug_buffer
+	LONG_S	k1, 0(k0)
+
+	ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+	PTR_SRL	k1, SMP_CPUID_PTRSHIFT
+	PTR_SLL	k1, LONGLOG
+	PTR_LA	k0, ejtag_debug_buffer_per_cpu
+	PTR_ADDU k0, k1
+
+	PTR_LA	k1, ejtag_debug_buffer
+	LONG_L	k1, 0(k1)
+	LONG_S	k1, 0(k0)
+
+	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	sw	zero, 0(k0)
+#else
 	PTR_LA	k0, ejtag_debug_buffer
 	LONG_S	k1, 0(k0)
+#endif
+
 	SAVE_ALL
 	move	a0, sp
 	jal	ejtag_exception_handler
 	RESTORE_ALL
+
+#ifdef CONFIG_SMP
+	ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+	PTR_SRL	k1, SMP_CPUID_PTRSHIFT
+	PTR_SLL	k1, LONGLOG
+	PTR_LA	k0, ejtag_debug_buffer_per_cpu
+	PTR_ADDU k0, k1
+	LONG_L	k1, 0(k0)
+#else
 	PTR_LA	k0, ejtag_debug_buffer
 	LONG_L	k1, 0(k0)
+#endif
 
 ejtag_return:
+	back_to_back_c0_hazard
 	MFC0	k0, CP0_DESAVE
 	.set	mips32
 	deret
@@ -377,6 +417,12 @@ ejtag_return:
 	.data
 EXPORT(ejtag_debug_buffer)
 	.fill	LONGSIZE
+#ifdef CONFIG_SMP
+EXPORT(ejtag_debug_buffer_spinlock)
+	.fill	LONGSIZE
+EXPORT(ejtag_debug_buffer_per_cpu)
+	.fill	LONGSIZE * NR_CPUS
+#endif
 	.previous
 
 	__INIT
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 7c246b69c545..046846999efd 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -33,21 +33,21 @@
 void (*cpu_wait)(void);
 EXPORT_SYMBOL(cpu_wait);
 
-static void r3081_wait(void)
+static void __cpuidle r3081_wait(void)
 {
 	unsigned long cfg = read_c0_conf();
 	write_c0_conf(cfg | R30XX_CONF_HALT);
 	local_irq_enable();
 }
 
-static void r39xx_wait(void)
+static void __cpuidle r39xx_wait(void)
 {
 	if (!need_resched())
 		write_c0_conf(read_c0_conf() | TX39_CONF_HALT);
 	local_irq_enable();
 }
 
-void r4k_wait(void)
+void __cpuidle r4k_wait(void)
 {
 	local_irq_enable();
 	__r4k_wait();
@@ -60,7 +60,7 @@ void r4k_wait(void)
  * interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes
  * using this version a gamble.
  */
-void r4k_wait_irqoff(void)
+void __cpuidle r4k_wait_irqoff(void)
 {
 	if (!need_resched())
 		__asm__(
@@ -75,7 +75,7 @@ void r4k_wait_irqoff(void)
  * The RM7000 variant has to handle erratum 38.	 The workaround is to not
  * have any pending stores when the WAIT instruction is executed.
  */
-static void rm7k_wait_irqoff(void)
+static void __cpuidle rm7k_wait_irqoff(void)
 {
 	if (!need_resched())
 		__asm__(
@@ -96,7 +96,7 @@ static void rm7k_wait_irqoff(void)
  * since coreclock (and the cp0 counter) stops upon executing it. Only an
  * interrupt can wake it, so they must be enabled before entering idle modes.
  */
-static void au1k_wait(void)
+static void __cpuidle au1k_wait(void)
 {
 	unsigned long c0status = read_c0_status() | 1;	/* irqs on */
 
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index f5c8bce70db2..54cd675c5d1d 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -326,19 +326,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				preempt_enable_no_resched();
 			}
 			return 1;
-		} else {
-			if (addr->word != breakpoint_insn.word) {
-				/*
-				 * The breakpoint instruction was removed by
-				 * another cpu right after we hit, no further
-				 * handling of this interrupt is appropriate
-				 */
-				ret = 1;
-				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs))
-				goto ss_probe;
+		} else if (addr->word != breakpoint_insn.word) {
+			/*
+			 * The breakpoint instruction was removed by
+			 * another cpu right after we hit, no further
+			 * handling of this interrupt is appropriate
+			 */
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -364,10 +358,11 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
 	}
 
-ss_probe:
 	prepare_singlestep(p, regs, kcb);
 	if (kcb->flags & SKIP_DELAYSLOT) {
 		kcb->kprobe_status = KPROBE_HIT_SSDONE;
@@ -468,51 +463,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_sp = regs->regs[29];
-
-	memcpy(kcb->jprobes_stack, (void *)kcb->jprobe_saved_sp,
-	       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
-
-	regs->cp0_epc = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-/* Defined in the inline asm below. */
-void jprobe_return_end(void);
-
-void __kprobes jprobe_return(void)
-{
-	/* Assembler quirk necessitates this '0,code' business.	 */
-	asm volatile(
-		"break 0,%0\n\t"
-		".globl jprobe_return_end\n"
-		"jprobe_return_end:\n"
-		: : "n" (BRK_KPROBE_BP) : "memory");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (regs->cp0_epc >= (unsigned long)jprobe_return &&
-	    regs->cp0_epc <= (unsigned long)jprobe_return_end) {
-		*regs = kcb->jprobe_saved_regs;
-		memcpy((void *)kcb->jprobe_saved_sp, kcb->jprobes_stack,
-		       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
-		preempt_enable_no_resched();
-
-		return 1;
-	}
-	return 0;
-}
-
 /*
  * Function return probe trampoline:
  *	- init_kprobes() establishes a probepoint here
@@ -595,9 +545,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	instruction_pointer(regs) = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 318f1c05c5b3..6b61be486303 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -43,17 +43,6 @@
 #include <asm/mmu_context.h>
 #include <asm/mman.h>
 
-/* Use this to get at 32-bit user passed pointers. */
-/* A() macro should be used for places where you e.g.
-   have some internal variable u32 and just want to get
-   rid of a compiler warning. AA() has to be used in
-   places where you want to convert a function argument
-   to 32bit pointer or when you e.g. access pt_regs
-   structure and want to consider 32bit registers only.
- */
-#define A(__x) ((unsigned long)(__x))
-#define AA(__x) ((unsigned long)((int)__x))
-
 #ifdef __MIPSEB__
 #define merge_64(r1, r2) ((((r1) & 0xffffffffUL) << 32) + ((r2) & 0xffffffffUL))
 #endif
@@ -61,24 +50,6 @@
 #define merge_64(r1, r2) ((((r2) & 0xffffffffUL) << 32) + ((r1) & 0xffffffffUL))
 #endif
 
-SYSCALL_DEFINE6(32_mmap2, unsigned long, addr, unsigned long, len,
-	unsigned long, prot, unsigned long, flags, unsigned long, fd,
-	unsigned long, pgoff)
-{
-	if (pgoff & (~PAGE_MASK >> 12))
-		return -EINVAL;
-	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
-			       pgoff >> (PAGE_SHIFT-12));
-}
-
-#define RLIM_INFINITY32 0x7fffffff
-#define RESOURCE32(x) ((x > RLIM_INFINITY32) ? RLIM_INFINITY32 : x)
-
-struct rlimit32 {
-	int	rlim_cur;
-	int	rlim_max;
-};
-
 SYSCALL_DEFINE4(32_truncate64, const char __user *, path,
 	unsigned long, __dummy, unsigned long, a2, unsigned long, a3)
 {
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 8d85046adcc8..8fc69891e117 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -29,6 +29,8 @@
 #include <linux/kallsyms.h>
 #include <linux/random.h>
 #include <linux/prctl.h>
+#include <linux/nmi.h>
+#include <linux/cpu.h>
 
 #include <asm/asm.h>
 #include <asm/bootinfo.h>
@@ -655,28 +657,42 @@ unsigned long arch_align_stack(unsigned long sp)
 	return sp & ALMASK;
 }
 
-static void arch_dump_stack(void *info)
+static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);
+static struct cpumask backtrace_csd_busy;
+
+static void handle_backtrace(void *info)
 {
-	struct pt_regs *regs;
+	nmi_cpu_backtrace(get_irq_regs());
+	cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);
+}
 
-	regs = get_irq_regs();
+static void raise_backtrace(cpumask_t *mask)
+{
+	call_single_data_t *csd;
+	int cpu;
 
-	if (regs)
-		show_regs(regs);
+	for_each_cpu(cpu, mask) {
+		/*
+		 * If we previously sent an IPI to the target CPU & it hasn't
+		 * cleared its bit in the busy cpumask then it didn't handle
+		 * our previous IPI & it's not safe for us to reuse the
+		 * call_single_data_t.
+		 */
+		if (cpumask_test_and_set_cpu(cpu, &backtrace_csd_busy)) {
+			pr_warn("Unable to send backtrace IPI to CPU%u - perhaps it hung?\n",
+				cpu);
+			continue;
+		}
 
-	dump_stack();
+		csd = &per_cpu(backtrace_csd, cpu);
+		csd->func = handle_backtrace;
+		smp_call_function_single_async(cpu, csd);
+	}
 }
 
 void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
 {
-	long this_cpu = get_cpu();
-
-	if (cpumask_test_cpu(this_cpu, mask) && !exclude_self)
-		dump_stack();
-
-	smp_call_function_many(mask, arch_dump_stack, NULL, 1);
-
-	put_cpu();
+	nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace);
 }
 
 int mips_get_process_fp_mode(struct task_struct *task)
@@ -691,19 +707,25 @@ int mips_get_process_fp_mode(struct task_struct *task)
 	return value;
 }
 
-static void prepare_for_fp_mode_switch(void *info)
+static long prepare_for_fp_mode_switch(void *unused)
 {
-	struct mm_struct *mm = info;
-
-	if (current->mm == mm)
-		lose_fpu(1);
+	/*
+	 * This is icky, but we use this to simply ensure that all CPUs have
+	 * context switched, regardless of whether they were previously running
+	 * kernel or user code. This ensures that no CPU currently has its FPU
+	 * enabled, or is about to attempt to enable it through any path other
+	 * than enable_restore_fp_context() which will wait appropriately for
+	 * fp_mode_switching to be zero.
+	 */
+	return 0;
 }
 
 int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 {
 	const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE;
 	struct task_struct *t;
-	int max_users;
+	struct cpumask process_cpus;
+	int cpu;
 
 	/* If nothing to change, return right away, successfully.  */
 	if (value == mips_get_process_fp_mode(task))
@@ -736,35 +758,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 	if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
 		return -EOPNOTSUPP;
 
-	/* Proceed with the mode switch */
-	preempt_disable();
-
-	/* Save FP & vector context, then disable FPU & MSA */
-	if (task->signal == current->signal)
-		lose_fpu(1);
-
-	/* Prevent any threads from obtaining live FP context */
-	atomic_set(&task->mm->context.fp_mode_switching, 1);
-	smp_mb__after_atomic();
-
-	/*
-	 * If there are multiple online CPUs then force any which are running
-	 * threads in this process to lose their FPU context, which they can't
-	 * regain until fp_mode_switching is cleared later.
-	 */
-	if (num_online_cpus() > 1) {
-		/* No need to send an IPI for the local CPU */
-		max_users = (task->mm == current->mm) ? 1 : 0;
-
-		if (atomic_read(&current->mm->mm_users) > max_users)
-			smp_call_function(prepare_for_fp_mode_switch,
-					  (void *)current->mm, 1);
-	}
-
-	/*
-	 * There are now no threads of the process with live FP context, so it
-	 * is safe to proceed with the FP mode switch.
-	 */
+	/* Indicate the new FP mode in each thread */
 	for_each_thread(task, t) {
 		/* Update desired FP register width */
 		if (value & PR_FP_MODE_FR) {
@@ -781,9 +775,34 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 			clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
 	}
 
-	/* Allow threads to use FP again */
-	atomic_set(&task->mm->context.fp_mode_switching, 0);
-	preempt_enable();
+	/*
+	 * We need to ensure that all threads in the process have switched mode
+	 * before returning, in order to allow userland to not worry about
+	 * races. We can do this by forcing all CPUs that any thread in the
+	 * process may be running on to schedule something else - in this case
+	 * prepare_for_fp_mode_switch().
+	 *
+	 * We begin by generating a mask of all CPUs that any thread in the
+	 * process may be running on.
+	 */
+	cpumask_clear(&process_cpus);
+	for_each_thread(task, t)
+		cpumask_set_cpu(task_cpu(t), &process_cpus);
+
+	/*
+	 * Now we schedule prepare_for_fp_mode_switch() on each of those CPUs.
+	 *
+	 * The CPUs may have rescheduled already since we switched mode or
+	 * generated the cpumask, but that doesn't matter. If the task in this
+	 * process is scheduled out then our scheduling
+	 * prepare_for_fp_mode_switch() will simply be redundant. If it's
+	 * scheduled in then it will already have picked up the new FP mode
+	 * whilst doing so.
+	 */
+	get_online_cpus();
+	for_each_cpu_and(cpu, &process_cpus, cpu_online_mask)
+		work_on_cpu(cpu, prepare_for_fp_mode_switch, NULL);
+	put_online_cpus();
 
 	wake_up_var(&task->mm->context.fp_mode_switching);
 
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 9f6c3f2aa2e2..e5ba56c01ee0 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -41,6 +41,7 @@
 #include <asm/mipsmtregs.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
+#include <asm/processor.h>
 #include <asm/syscall.h>
 #include <linux/uaccess.h>
 #include <asm/bootinfo.h>
@@ -589,9 +590,226 @@ static int fpr_set(struct task_struct *target,
 	return err;
 }
 
+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
+/*
+ * Copy the DSP context to the supplied 32-bit NT_MIPS_DSP buffer.
+ */
+static int dsp32_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u32 dspregs[NUM_DSP_REGS + 1];
+
+	BUG_ON(count % sizeof(u32));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u32);
+	num_regs = count / sizeof(u32);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			dspregs[i] = target->thread.dsp.dspr[i];
+			break;
+		case NUM_DSP_REGS:
+			dspregs[i] = target->thread.dsp.dspcontrol;
+			break;
+		}
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				   sizeof(dspregs));
+}
+
+/*
+ * Copy the supplied 32-bit NT_MIPS_DSP buffer to the DSP context.
+ */
+static int dsp32_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u32 dspregs[NUM_DSP_REGS + 1];
+	int err;
+
+	BUG_ON(count % sizeof(u32));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u32);
+	num_regs = count / sizeof(u32);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				 sizeof(dspregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			target->thread.dsp.dspr[i] = (s32)dspregs[i];
+			break;
+		case NUM_DSP_REGS:
+			target->thread.dsp.dspcontrol = (s32)dspregs[i];
+			break;
+		}
+
+	return 0;
+}
+
+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Copy the DSP context to the supplied 64-bit NT_MIPS_DSP buffer.
+ */
+static int dsp64_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u64 dspregs[NUM_DSP_REGS + 1];
+
+	BUG_ON(count % sizeof(u64));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u64);
+	num_regs = count / sizeof(u64);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			dspregs[i] = target->thread.dsp.dspr[i];
+			break;
+		case NUM_DSP_REGS:
+			dspregs[i] = target->thread.dsp.dspcontrol;
+			break;
+		}
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				   sizeof(dspregs));
+}
+
+/*
+ * Copy the supplied 64-bit NT_MIPS_DSP buffer to the DSP context.
+ */
+static int dsp64_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u64 dspregs[NUM_DSP_REGS + 1];
+	int err;
+
+	BUG_ON(count % sizeof(u64));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u64);
+	num_regs = count / sizeof(u64);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				 sizeof(dspregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			target->thread.dsp.dspr[i] = dspregs[i];
+			break;
+		case NUM_DSP_REGS:
+			target->thread.dsp.dspcontrol = dspregs[i];
+			break;
+		}
+
+	return 0;
+}
+
+#endif /* CONFIG_64BIT */
+
+/*
+ * Determine whether the DSP context is present.
+ */
+static int dsp_active(struct task_struct *target,
+		      const struct user_regset *regset)
+{
+	return cpu_has_dsp ? NUM_DSP_REGS + 1 : -ENODEV;
+}
+
+/* Copy the FP mode setting to the supplied NT_MIPS_FP_MODE buffer.  */
+static int fp_mode_get(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       void *kbuf, void __user *ubuf)
+{
+	int fp_mode;
+
+	fp_mode = mips_get_process_fp_mode(target);
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fp_mode, 0,
+				   sizeof(fp_mode));
+}
+
+/*
+ * Copy the supplied NT_MIPS_FP_MODE buffer to the FP mode setting.
+ *
+ * We optimize for the case where `count % sizeof(int) == 0', which
+ * is supposed to have been guaranteed by the kernel before calling
+ * us, e.g. in `ptrace_regset'.  We enforce that requirement, so
+ * that we can safely avoid preinitializing temporaries for partial
+ * mode writes.
+ */
+static int fp_mode_set(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       const void *kbuf, const void __user *ubuf)
+{
+	int fp_mode;
+	int err;
+
+	BUG_ON(count % sizeof(int));
+
+	if (pos + count > sizeof(fp_mode))
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fp_mode, 0,
+				 sizeof(fp_mode));
+	if (err)
+		return err;
+
+	if (count > 0)
+		err = mips_set_process_fp_mode(target, fp_mode);
+
+	return err;
+}
+
 enum mips_regset {
 	REGSET_GPR,
 	REGSET_FPR,
+	REGSET_DSP,
+	REGSET_FP_MODE,
 };
 
 struct pt_regs_offset {
@@ -697,6 +915,23 @@ static const struct user_regset mips_regsets[] = {
 		.get		= fpr_get,
 		.set		= fpr_set,
 	},
+	[REGSET_DSP] = {
+		.core_note_type	= NT_MIPS_DSP,
+		.n		= NUM_DSP_REGS + 1,
+		.size		= sizeof(u32),
+		.align		= sizeof(u32),
+		.get		= dsp32_get,
+		.set		= dsp32_set,
+		.active		= dsp_active,
+	},
+	[REGSET_FP_MODE] = {
+		.core_note_type	= NT_MIPS_FP_MODE,
+		.n		= 1,
+		.size		= sizeof(int),
+		.align		= sizeof(int),
+		.get		= fp_mode_get,
+		.set		= fp_mode_set,
+	},
 };
 
 static const struct user_regset_view user_mips_view = {
@@ -728,6 +963,23 @@ static const struct user_regset mips64_regsets[] = {
 		.get		= fpr_get,
 		.set		= fpr_set,
 	},
+	[REGSET_DSP] = {
+		.core_note_type	= NT_MIPS_DSP,
+		.n		= NUM_DSP_REGS + 1,
+		.size		= sizeof(u64),
+		.align		= sizeof(u64),
+		.get		= dsp64_get,
+		.set		= dsp64_set,
+		.active		= dsp_active,
+	},
+	[REGSET_FP_MODE] = {
+		.core_note_type	= NT_MIPS_FP_MODE,
+		.n		= 1,
+		.size		= sizeof(int),
+		.align		= sizeof(int),
+		.get		= fp_mode_get,
+		.set		= fp_mode_set,
+	},
 };
 
 static const struct user_regset_view user_mips64_view = {
@@ -856,7 +1108,7 @@ long arch_ptrace(struct task_struct *child, long request,
 				goto out;
 			}
 			dregs = __get_dsp_regs(child);
-			tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+			tmp = dregs[addr - DSP_BASE];
 			break;
 		}
 		case DSP_CONTROL:
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 7edc629304c8..bc348d44d151 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -142,7 +142,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 				goto out;
 			}
 			dregs = __get_dsp_regs(child);
-			tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+			tmp = dregs[addr - DSP_BASE];
 			break;
 		}
 		case DSP_CONTROL:
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index c6bbf2165051..419c92197b2f 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -85,7 +85,7 @@ done:
 
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 	/* We need to flush I-cache before jumping to new kernel.
-	 * Unfortunatelly, this code is cpu-specific.
+	 * Unfortunately, this code is cpu-specific.
 	 */
 	.set push
 	.set noreorder
@@ -145,7 +145,7 @@ LEAF(kexec_smp_wait)
 #endif
 
 /* All parameters to new kernel are passed in registers a0-a3.
- * kexec_args[0..3] are uses to prepare register values.
+ * kexec_args[0..3] are used to prepare register values.
  */
 
 kexec_args:
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 2c96c0c68116..c71d1eb7da59 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -36,6 +36,7 @@
 #include <asm/cdmm.h>
 #include <asm/cpu.h>
 #include <asm/debug.h>
+#include <asm/dma-coherence.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp-ops.h>
@@ -84,6 +85,11 @@ static struct resource bss_resource = { .name = "Kernel bss", };
 
 static void *detect_magic __initdata = detect_memory_region;
 
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+unsigned long ARCH_PFN_OFFSET;
+EXPORT_SYMBOL(ARCH_PFN_OFFSET);
+#endif
+
 void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type)
 {
 	int x = boot_mem_map.nr_map;
@@ -441,6 +447,12 @@ static void __init bootmem_init(void)
 		mapstart = max(reserved_end, start);
 	}
 
+	if (min_low_pfn >= max_low_pfn)
+		panic("Incorrect memory mapping !!!");
+
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+	ARCH_PFN_OFFSET = PFN_UP(ramstart);
+#else
 	/*
 	 * Reserve any memory between the start of RAM and PHYS_OFFSET
 	 */
@@ -448,8 +460,6 @@ static void __init bootmem_init(void)
 		add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET,
 				  BOOT_MEM_RESERVED);
 
-	if (min_low_pfn >= max_low_pfn)
-		panic("Incorrect memory mapping !!!");
 	if (min_low_pfn > ARCH_PFN_OFFSET) {
 		pr_info("Wasting %lu bytes for tracking %lu unused pages\n",
 			(min_low_pfn - ARCH_PFN_OFFSET) * sizeof(struct page),
@@ -459,6 +469,7 @@ static void __init bootmem_init(void)
 			ARCH_PFN_OFFSET - min_low_pfn);
 	}
 	min_low_pfn = ARCH_PFN_OFFSET;
+#endif
 
 	/*
 	 * Determine low and high memory ranges
@@ -1055,3 +1066,26 @@ static int __init debugfs_mips(void)
 }
 arch_initcall(debugfs_mips);
 #endif
+
+#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
+/* User defined DMA coherency from command line. */
+enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
+EXPORT_SYMBOL_GPL(coherentio);
+int hw_coherentio = 0;	/* Actual hardware supported DMA coherency setting. */
+
+static int __init setcoherentio(char *str)
+{
+	coherentio = IO_COHERENCE_ENABLED;
+	pr_info("Hardware DMA cache coherency (command line)\n");
+	return 0;
+}
+early_param("coherentio", setcoherentio);
+
+static int __init setnocoherentio(char *str)
+{
+	coherentio = IO_COHERENCE_DISABLED;
+	pr_info("Software DMA cache coherency (command line)\n");
+	return 0;
+}
+early_param("nocoherentio", setnocoherentio);
+#endif
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 00f2535d2226..109ed163a6a6 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -592,13 +592,15 @@ SYSCALL_DEFINE3(sigaction, int, sig, const struct sigaction __user *, act,
 #endif
 
 #ifdef CONFIG_TRAD_SIGNALS
-asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys_sigreturn(void)
 {
 	struct sigframe __user *frame;
+	struct pt_regs *regs;
 	sigset_t blocked;
 	int sig;
 
-	frame = (struct sigframe __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct sigframe __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&blocked, &frame->sf_mask, sizeof(blocked)))
@@ -606,7 +608,7 @@ asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&blocked);
 
-	sig = restore_sigcontext(&regs, &frame->sf_sc);
+	sig = restore_sigcontext(regs, &frame->sf_sc);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -618,8 +620,8 @@ asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
@@ -627,13 +629,15 @@ badframe:
 }
 #endif /* CONFIG_TRAD_SIGNALS */
 
-asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys_rt_sigreturn(void)
 {
 	struct rt_sigframe __user *frame;
+	struct pt_regs *regs;
 	sigset_t set;
 	int sig;
 
-	frame = (struct rt_sigframe __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct rt_sigframe __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&set, &frame->rs_uc.uc_sigmask, sizeof(set)))
@@ -641,7 +645,7 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&set);
 
-	sig = restore_sigcontext(&regs, &frame->rs_uc.uc_mcontext);
+	sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -656,8 +660,8 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
@@ -801,7 +805,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		regs->regs[0] = 0;		/* Don't deal with this again.	*/
 	}
 
-	rseq_signal_deliver(regs);
+	rseq_signal_deliver(ksig, regs);
 
 	if (sig_uses_siginfo(&ksig->ka, abi))
 		ret = abi->setup_rt_frame(vdso + abi->vdso->off_rt_sigreturn,
@@ -870,7 +874,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
-		rseq_handle_notify_resume(regs);
+		rseq_handle_notify_resume(NULL, regs);
 	}
 
 	user_enter();
diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c
index b672cebb4a1a..8f65aaf9206d 100644
--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@@ -64,13 +64,15 @@ struct rt_sigframe_n32 {
 	struct ucontextn32 rs_uc;
 };
 
-asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sysn32_rt_sigreturn(void)
 {
 	struct rt_sigframe_n32 __user *frame;
+	struct pt_regs *regs;
 	sigset_t set;
 	int sig;
 
-	frame = (struct rt_sigframe_n32 __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct rt_sigframe_n32 __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
@@ -78,7 +80,7 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&set);
 
-	sig = restore_sigcontext(&regs, &frame->rs_uc.uc_mcontext);
+	sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -93,8 +95,8 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
diff --git a/arch/mips/kernel/signal_o32.c b/arch/mips/kernel/signal_o32.c
index 2b3572fb5f1b..b6e3ddef48a0 100644
--- a/arch/mips/kernel/signal_o32.c
+++ b/arch/mips/kernel/signal_o32.c
@@ -151,13 +151,15 @@ static int setup_frame_32(void *sig_return, struct ksignal *ksig,
 	return 0;
 }
 
-asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys32_rt_sigreturn(void)
 {
 	struct rt_sigframe32 __user *frame;
+	struct pt_regs *regs;
 	sigset_t set;
 	int sig;
 
-	frame = (struct rt_sigframe32 __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct rt_sigframe32 __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
@@ -165,7 +167,7 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&set);
 
-	sig = restore_sigcontext32(&regs, &frame->rs_uc.uc_mcontext);
+	sig = restore_sigcontext32(regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -180,8 +182,8 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
@@ -251,13 +253,15 @@ struct mips_abi mips_abi_32 = {
 };
 
 
-asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys32_sigreturn(void)
 {
 	struct sigframe32 __user *frame;
+	struct pt_regs *regs;
 	sigset_t blocked;
 	int sig;
 
-	frame = (struct sigframe32 __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct sigframe32 __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask))
@@ -265,7 +269,7 @@ asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&blocked);
 
-	sig = restore_sigcontext32(&regs, &frame->sf_sc);
+	sig = restore_sigcontext32(regs, &frame->sf_sc);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -277,8 +281,8 @@ asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index d67fa74622ee..f8871d5b7eb3 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -351,6 +351,7 @@ static void __show_regs(const struct pt_regs *regs)
 void show_regs(struct pt_regs *regs)
 {
 	__show_regs((struct pt_regs *)regs);
+	dump_stack();
 }
 
 void show_registers(struct pt_regs *regs)
@@ -1220,13 +1221,6 @@ static int enable_restore_fp_context(int msa)
 {
 	int err, was_fpu_owner, prior_msa;
 
-	/*
-	 * If an FP mode switch is currently underway, wait for it to
-	 * complete before proceeding.
-	 */
-	wait_var_event(&current->mm->context.fp_mode_switching,
-		       !atomic_read(&current->mm->context.fp_mode_switching));
-
 	if (!used_math()) {
 		/* First time FP context user. */
 		preempt_disable();
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 7cd76f93a438..f7ea8e21656b 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -515,7 +515,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 	dvcpu->arch.wait = 0;
 
 	if (swq_has_sleeper(&dvcpu->wq))
-		swake_up(&dvcpu->wq);
+		swake_up_one(&dvcpu->wq);
 
 	return 0;
 }
@@ -1204,7 +1204,7 @@ static void kvm_mips_comparecount_func(unsigned long data)
 
 	vcpu->arch.wait = 0;
 	if (swq_has_sleeper(&vcpu->wq))
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 }
 
 /* low level hrtimer wake routine */
diff --git a/arch/mips/lantiq/early_printk.c b/arch/mips/lantiq/early_printk.c
index 44bccaee822b..c4aa140b7c91 100644
--- a/arch/mips/lantiq/early_printk.c
+++ b/arch/mips/lantiq/early_printk.c
@@ -8,6 +8,7 @@
 
 #include <linux/cpu.h>
 #include <lantiq_soc.h>
+#include <asm/setup.h>
 
 #define ASC_BUF		1024
 #define LTQ_ASC_FSTAT	((u32 *)(LTQ_EARLY_ASC + 0x0048))
diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c
index 9ff7ccde9de0..d984bd5c2ec5 100644
--- a/arch/mips/lantiq/prom.c
+++ b/arch/mips/lantiq/prom.c
@@ -9,7 +9,6 @@
 #include <linux/export.h>
 #include <linux/clk.h>
 #include <linux/bootmem.h>
-#include <linux/of_platform.h>
 #include <linux/of_fdt.h>
 
 #include <asm/bootinfo.h>
@@ -114,10 +113,3 @@ void __init prom_init(void)
 		panic("failed to register_vsmp_smp_ops()");
 #endif
 }
-
-int __init plat_of_setup(void)
-{
-	return of_platform_default_populate(NULL, NULL, NULL);
-}
-
-arch_initcall(plat_of_setup);
diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c
index 805b3a6ab2d6..4b9fbb6744ad 100644
--- a/arch/mips/lantiq/xway/dma.c
+++ b/arch/mips/lantiq/xway/dma.c
@@ -130,10 +130,9 @@ ltq_dma_alloc(struct ltq_dma_channel *ch)
 	unsigned long flags;
 
 	ch->desc = 0;
-	ch->desc_base = dma_alloc_coherent(NULL,
+	ch->desc_base = dma_zalloc_coherent(NULL,
 				LTQ_DESC_NUM * LTQ_DESC_SIZE,
 				&ch->phys, GFP_ATOMIC);
-	memset(ch->desc_base, 0, LTQ_DESC_NUM * LTQ_DESC_SIZE);
 
 	spin_lock_irqsave(&ltq_dma_lock, flags);
 	ltq_dma_w32(ch->nr, LTQ_DMA_CS);
diff --git a/arch/mips/lasat/prom.c b/arch/mips/lasat/prom.c
index 17e15b50a551..37b8fc5b9ac9 100644
--- a/arch/mips/lasat/prom.c
+++ b/arch/mips/lasat/prom.c
@@ -13,6 +13,7 @@
 #include <asm/bootinfo.h>
 #include <asm/lasat/lasat.h>
 #include <asm/cpu.h>
+#include <asm/setup.h>
 
 #include "at93c.h"
 #include <asm/lasat/eeprom.h>
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 1cc306520a55..3a6f34ef5ffc 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -195,6 +195,7 @@
 #endif
 #else
 	 PTR_SUBU	t0, $0, a2
+	move		a2, zero		/* No remaining longs */
 	PTR_ADDIU	t0, 1
 	STORE_BYTE(0)
 	STORE_BYTE(1)
@@ -231,16 +232,25 @@
 
 #ifdef CONFIG_CPU_MIPSR6
 .Lbyte_fixup\@:
-	PTR_SUBU	a2, $0, t0
+	/*
+	 * unset_bytes = (#bytes - (#unaligned bytes)) - (-#unaligned bytes remaining + 1) + 1
+	 *      a2     =             a2                -              t0                   + 1
+	 */
+	PTR_SUBU	a2, t0
 	jr		ra
 	 PTR_ADDIU	a2, 1
 #endif /* CONFIG_CPU_MIPSR6 */
 
 .Lfirst_fixup\@:
+	/* unset_bytes already in a2 */
 	jr	ra
 	 nop
 
 .Lfwd_fixup\@:
+	/*
+	 * unset_bytes = partial_start_addr +  #bytes   -     fault_addr
+	 *      a2     =         t1         + (a2 & 3f) - $28->task->BUADDR
+	 */
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, 0x3f
 	LONG_L		t0, THREAD_BUADDR(t0)
@@ -249,6 +259,10 @@
 	 LONG_SUBU	a2, t0
 
 .Lpartial_fixup\@:
+	/*
+	 * unset_bytes = partial_end_addr +      #bytes     -     fault_addr
+	 *      a2     =       a0         + (a2 & STORMASK) - $28->task->BUADDR
+	 */
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, STORMASK
 	LONG_L		t0, THREAD_BUADDR(t0)
@@ -257,10 +271,15 @@
 	 LONG_SUBU	a2, t0
 
 .Llast_fixup\@:
+	/* unset_bytes already in a2 */
 	jr		ra
 	 nop
 
 .Lsmall_fixup\@:
+	/*
+	 * unset_bytes = end_addr - current_addr + 1
+	 *      a2     =    t1    -      a0      + 1
+	 */
 	PTR_SUBU	a2, t1, a0
 	jr		ra
 	 PTR_ADDIU	a2, 1
diff --git a/arch/mips/loongson32/Platform b/arch/mips/loongson32/Platform
index ffe01c6d0037..a0dbb3b2f2de 100644
--- a/arch/mips/loongson32/Platform
+++ b/arch/mips/loongson32/Platform
@@ -1,8 +1,4 @@
-cflags-$(CONFIG_CPU_LOONGSON1)	+= \
-	$(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
-	-Wa,-mips32r2 -Wa,--trap
-
+cflags-$(CONFIG_CPU_LOONGSON1)		+= -march=mips32 -Wa,--trap
 platform-$(CONFIG_MACH_LOONGSON32)	+= loongson32/
 cflags-$(CONFIG_MACH_LOONGSON32)	+= -I$(srctree)/arch/mips/include/asm/mach-loongson32
-load-$(CONFIG_LOONGSON1_LS1B)		+= 0xffffffff80100000
-load-$(CONFIG_LOONGSON1_LS1C)		+= 0xffffffff80100000
+load-$(CONFIG_CPU_LOONGSON1)		+= 0xffffffff80100000
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index c79e6a565572..c865b4b9b775 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -91,7 +91,6 @@ config LOONGSON_MACH3X
 	select LOONGSON_MC146818
 	select ZONE_DMA32
 	select LEFI_FIRMWARE_INTERFACE
-	select PHYS48_TO_HT40
 	help
 		Generic Loongson 3 family machines utilize the 3A/3B revision
 		of Loongson processor and RS780/SBX00 chipset.
@@ -130,10 +129,6 @@ config LOONGSON_UART_BASE
 	default y
 	depends on EARLY_PRINTK || SERIAL_8250
 
-config PHYS48_TO_HT40
-	bool
-	default y if CPU_LOONGSON3
-
 config LOONGSON_MC146818
 	bool
 	default n
diff --git a/arch/mips/loongson64/common/Makefile b/arch/mips/loongson64/common/Makefile
index 8235ac7eac95..57ee03022941 100644
--- a/arch/mips/loongson64/common/Makefile
+++ b/arch/mips/loongson64/common/Makefile
@@ -6,6 +6,7 @@
 obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
     bonito-irq.o mem.o machtype.o platform.o serial.o
 obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_CPU_LOONGSON2) += dma.o
 
 #
 # Serial port support
@@ -25,8 +26,3 @@ obj-$(CONFIG_CS5536) += cs5536/
 #
 
 obj-$(CONFIG_SUSPEND) += pm.o
-
-#
-# Big Memory (SWIOTLB) Support
-#
-obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c b/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
index f7c905e50dc4..92dc6bafc127 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
+++ b/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
@@ -138,7 +138,7 @@ u32 pci_ohci_read_reg(int reg)
 		break;
 	case PCI_OHCI_INT_REG:
 		_rdmsr(DIVIL_MSR_REG(PIC_YSEL_LOW), &hi, &lo);
-		if ((lo & 0x00000f00) == CS5536_USB_INTR)
+		if (((lo >> PIC_YSEL_LOW_USB_SHIFT) & 0xf) == CS5536_USB_INTR)
 			conf_data = 1;
 		break;
 	default:
diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
deleted file mode 100644
index 6a739f8ae110..000000000000
--- a/arch/mips/loongson64/common/dma-swiotlb.c
+++ /dev/null
@@ -1,109 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/mm.h>
-#include <linux/init.h>
-#include <linux/dma-mapping.h>
-#include <linux/scatterlist.h>
-#include <linux/swiotlb.h>
-#include <linux/bootmem.h>
-
-#include <asm/bootinfo.h>
-#include <boot_param.h>
-#include <dma-coherence.h>
-
-static void *loongson_dma_alloc_coherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
-
-	mb();
-	return ret;
-}
-
-static dma_addr_t loongson_dma_map_page(struct device *dev, struct page *page,
-				unsigned long offset, size_t size,
-				enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
-					dir, attrs);
-	mb();
-	return daddr;
-}
-
-static int loongson_dma_map_sg(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, attrs);
-	mb();
-
-	return r;
-}
-
-static void loongson_dma_sync_single_for_device(struct device *dev,
-				dma_addr_t dma_handle, size_t size,
-				enum dma_data_direction dir)
-{
-	swiotlb_sync_single_for_device(dev, dma_handle, size, dir);
-	mb();
-}
-
-static void loongson_dma_sync_sg_for_device(struct device *dev,
-				struct scatterlist *sg, int nents,
-				enum dma_data_direction dir)
-{
-	swiotlb_sync_sg_for_device(dev, sg, nents, dir);
-	mb();
-}
-
-static int loongson_dma_supported(struct device *dev, u64 mask)
-{
-	if (mask > DMA_BIT_MASK(loongson_sysconf.dma_mask_bits))
-		return 0;
-	return swiotlb_dma_supported(dev, mask);
-}
-
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	long nid;
-#ifdef CONFIG_PHYS48_TO_HT40
-	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
-	 * Loongson-3's 48bit address space and embed it into 40bit */
-	nid = (paddr >> 44) & 0x3;
-	paddr = ((nid << 44) ^ paddr) | (nid << 37);
-#endif
-	return paddr;
-}
-
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	long nid;
-#ifdef CONFIG_PHYS48_TO_HT40
-	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
-	 * Loongson-3's 48bit address space and embed it into 40bit */
-	nid = (daddr >> 37) & 0x3;
-	daddr = ((nid << 37) ^ daddr) | (nid << 44);
-#endif
-	return daddr;
-}
-
-static const struct dma_map_ops loongson_dma_map_ops = {
-	.alloc = loongson_dma_alloc_coherent,
-	.free = swiotlb_free,
-	.map_page = loongson_dma_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.map_sg = loongson_dma_map_sg,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = loongson_dma_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = loongson_dma_sync_sg_for_device,
-	.mapping_error = swiotlb_dma_mapping_error,
-	.dma_supported = loongson_dma_supported,
-};
-
-void __init plat_swiotlb_setup(void)
-{
-	swiotlb_init(1);
-	mips_dma_map_ops = &loongson_dma_map_ops;
-}
diff --git a/arch/mips/loongson64/common/dma.c b/arch/mips/loongson64/common/dma.c
new file mode 100644
index 000000000000..48f04126bde2
--- /dev/null
+++ b/arch/mips/loongson64/common/dma.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-direct.h>
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr | 0x80000000;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+#if defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
+	if (dma_addr > 0x8fffffff)
+		return dma_addr;
+	return dma_addr & 0x0fffffff;
+#else
+	return dma_addr & 0x7fffffff;
+#endif
+}
diff --git a/arch/mips/loongson64/common/early_printk.c b/arch/mips/loongson64/common/early_printk.c
index 6ca632e529dc..a782e2b24747 100644
--- a/arch/mips/loongson64/common/early_printk.c
+++ b/arch/mips/loongson64/common/early_printk.c
@@ -10,6 +10,7 @@
  *  option) any later version.
  */
 #include <linux/serial_reg.h>
+#include <asm/setup.h>
 
 #include <loongson.h>
 
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c
index 1e8a955ae5a8..8f68ee02a8c2 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/common/env.c
@@ -198,7 +198,8 @@ void __init prom_init_env(void)
 			break;
 		case PRID_REV_LOONGSON3A_R1:
 		case PRID_REV_LOONGSON3A_R2:
-		case PRID_REV_LOONGSON3A_R3:
+		case PRID_REV_LOONGSON3A_R3_0:
+		case PRID_REV_LOONGSON3A_R3_1:
 			cpu_clock_freq = 900000000;
 			break;
 		case PRID_REV_LOONGSON3B_R1:
diff --git a/arch/mips/loongson64/loongson-3/Makefile b/arch/mips/loongson64/loongson-3/Makefile
index 44bc1482158b..b5a0c2fa5446 100644
--- a/arch/mips/loongson64/loongson-3/Makefile
+++ b/arch/mips/loongson64/loongson-3/Makefile
@@ -1,7 +1,7 @@
 #
 # Makefile for Loongson-3 family machines
 #
-obj-y			+= irq.o cop2-ex.o platform.o acpi_init.o
+obj-y			+= irq.o cop2-ex.o platform.o acpi_init.o dma.o
 
 obj-$(CONFIG_SMP)	+= smp.o
 
diff --git a/arch/mips/loongson64/loongson-3/dma.c b/arch/mips/loongson64/loongson-3/dma.c
new file mode 100644
index 000000000000..5e86635f71db
--- /dev/null
+++ b/arch/mips/loongson64/loongson-3/dma.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-direct.h>
+#include <linux/init.h>
+#include <linux/swiotlb.h>
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
+	 * Loongson-3's 48bit address space and embed it into 40bit */
+	long nid = (paddr >> 44) & 0x3;
+	return ((nid << 44) ^ paddr) | (nid << 37);
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
+	 * Loongson-3's 48bit address space and embed it into 40bit */
+	long nid = (daddr >> 37) & 0x3;
+	return ((nid << 37) ^ daddr) | (nid << 44);
+}
+
+void __init plat_swiotlb_setup(void)
+{
+	swiotlb_init(1);
+}
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index 8501109bb0f0..fea95d003269 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -682,7 +682,8 @@ void play_dead(void)
 			(void *)CKSEG1ADDR((unsigned long)loongson3a_r1_play_dead);
 		break;
 	case PRID_REV_LOONGSON3A_R2:
-	case PRID_REV_LOONGSON3A_R3:
+	case PRID_REV_LOONGSON3A_R3_0:
+	case PRID_REV_LOONGSON3A_R3_1:
 		play_dead_at_ckseg1 =
 			(void *)CKSEG1ADDR((unsigned long)loongson3a_r2r3_play_dead);
 		break;
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index c463bdad45c7..3e5bb203c95a 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the Linux/MIPS-specific parts of the memory manager.
 #
 
-obj-y				+= cache.o dma-default.o extable.o fault.o \
+obj-y				+= cache.o extable.o fault.o \
 				   gup.o init.o mmap.o page.o page-funcs.o \
 				   pgtable.o tlbex.o tlbex-fault.o tlb-funcs.o
 
@@ -17,6 +17,7 @@ obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-noncoherent.o
 
 obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o
 obj-$(CONFIG_CPU_R3000)		+= c-r3k.o tlb-r3k.o
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index e12dfa48b478..a9ef057c79fe 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -830,12 +830,13 @@ static void r4k_flush_icache_user_range(unsigned long start, unsigned long end)
 	return __r4k_flush_icache_range(start, end, true);
 }
 
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
@@ -871,7 +872,8 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
@@ -904,7 +906,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 	bc_inv(addr, size);
 	__sync();
 }
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 struct flush_cache_sigtramp_args {
 	struct mm_struct *mm;
@@ -1505,6 +1507,14 @@ static void probe_pcache(void)
 	if (c->dcache.flags & MIPS_CACHE_PINDEX)
 		c->dcache.flags &= ~MIPS_CACHE_ALIASES;
 
+	/*
+	 * In systems with CM the icache fills from L2 or closer caches, and
+	 * thus sees remote stores without needing to write them back any
+	 * further than that.
+	 */
+	if (mips_cm_present())
+		c->icache.flags |= MIPS_IC_SNOOPS_REMOTE;
+
 	switch (current_cpu_type()) {
 	case CPU_20KC:
 		/*
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 0d3c656feba0..70a523151ff3 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(local_flush_data_cache_page);
 EXPORT_SYMBOL(flush_data_cache_page);
 EXPORT_SYMBOL(flush_icache_all);
 
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 /* DMA cache operations. */
 void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
@@ -65,7 +65,7 @@ void (*_dma_cache_inv)(unsigned long start, unsigned long size);
 
 EXPORT_SYMBOL(_dma_cache_wback_inv);
 
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 /*
  * We could optimize the case where the cache argument is not BCACHE but
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
deleted file mode 100644
index f9fef0028ca2..000000000000
--- a/arch/mips/mm/dma-default.c
+++ /dev/null
@@ -1,404 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
- * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
- * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
- */
-
-#include <linux/types.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/export.h>
-#include <linux/scatterlist.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/highmem.h>
-#include <linux/dma-contiguous.h>
-
-#include <asm/cache.h>
-#include <asm/cpu-type.h>
-#include <asm/io.h>
-
-#include <dma-coherence.h>
-
-#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
-/* User defined DMA coherency from command line. */
-enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
-EXPORT_SYMBOL_GPL(coherentio);
-int hw_coherentio = 0;	/* Actual hardware supported DMA coherency setting. */
-
-static int __init setcoherentio(char *str)
-{
-	coherentio = IO_COHERENCE_ENABLED;
-	pr_info("Hardware DMA cache coherency (command line)\n");
-	return 0;
-}
-early_param("coherentio", setcoherentio);
-
-static int __init setnocoherentio(char *str)
-{
-	coherentio = IO_COHERENCE_DISABLED;
-	pr_info("Software DMA cache coherency (command line)\n");
-	return 0;
-}
-early_param("nocoherentio", setnocoherentio);
-#endif
-
-static inline struct page *dma_addr_to_page(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return pfn_to_page(
-		plat_dma_addr_to_phys(dev, dma_addr) >> PAGE_SHIFT);
-}
-
-/*
- * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
- * speculatively fill random cachelines with stale data at any time,
- * requiring an extra flush post-DMA.
- *
- * Warning on the terminology - Linux calls an uncached area coherent;
- * MIPS terminology calls memory areas with hardware maintained coherency
- * coherent.
- *
- * Note that the R14000 and R16000 should also be checked for in this
- * condition.  However this function is only called on non-I/O-coherent
- * systems and only the R10000 and R12000 are used in such systems, the
- * SGI IP28 Indigo² rsp. SGI IP32 aka O2.
- */
-static inline bool cpu_needs_post_dma_flush(struct device *dev)
-{
-	if (plat_device_is_coherent(dev))
-		return false;
-
-	switch (boot_cpu_type()) {
-	case CPU_R10000:
-	case CPU_R12000:
-	case CPU_BMIPS5000:
-		return true;
-
-	default:
-		/*
-		 * Presence of MAARs suggests that the CPU supports
-		 * speculatively prefetching data, and therefore requires
-		 * the post-DMA flush/invalidate.
-		 */
-		return cpu_has_maar;
-	}
-}
-
-static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
-{
-	gfp_t dma_flag;
-
-#ifdef CONFIG_ISA
-	if (dev == NULL)
-		dma_flag = __GFP_DMA;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && defined(CONFIG_ZONE_DMA)
-	     if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(32))
-			dma_flag = __GFP_DMA;
-	else if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
-			dma_flag = __GFP_DMA32;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_ZONE_DMA)
-	     if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(64))
-		dma_flag = __GFP_DMA32;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
-	     if (dev == NULL ||
-		 dev->coherent_dma_mask < DMA_BIT_MASK(sizeof(phys_addr_t) * 8))
-		dma_flag = __GFP_DMA;
-	else
-#endif
-		dma_flag = 0;
-
-	/* Don't invoke OOM killer */
-	gfp |= __GFP_NORETRY;
-
-	return gfp | dma_flag;
-}
-
-static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret;
-	struct page *page = NULL;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	gfp = massage_gfp_flags(dev, gfp);
-
-	if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
-		page = dma_alloc_from_contiguous(dev, count, get_order(size),
-						 gfp);
-	if (!page)
-		page = alloc_pages(gfp, get_order(size));
-
-	if (!page)
-		return NULL;
-
-	ret = page_address(page);
-	memset(ret, 0, size);
-	*dma_handle = plat_map_dma_mem(dev, ret, size);
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT) &&
-	    !plat_device_is_coherent(dev)) {
-		dma_cache_wback_inv((unsigned long) ret, size);
-		ret = UNCAC_ADDR(ret);
-	}
-
-	return ret;
-}
-
-static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-	dma_addr_t dma_handle, unsigned long attrs)
-{
-	unsigned long addr = (unsigned long) vaddr;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct page *page = NULL;
-
-	plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
-
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !plat_device_is_coherent(dev))
-		addr = CAC_ADDR(addr);
-
-	page = virt_to_page((void *) addr);
-
-	if (!dma_release_from_contiguous(dev, page, count))
-		__free_pages(page, get_order(size));
-}
-
-static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-	void *cpu_addr, dma_addr_t dma_addr, size_t size,
-	unsigned long attrs)
-{
-	unsigned long user_count = vma_pages(vma);
-	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long addr = (unsigned long)cpu_addr;
-	unsigned long off = vma->vm_pgoff;
-	unsigned long pfn;
-	int ret = -ENXIO;
-
-	if (!plat_device_is_coherent(dev))
-		addr = CAC_ADDR(addr);
-
-	pfn = page_to_pfn(virt_to_page((void *)addr));
-
-	if (attrs & DMA_ATTR_WRITE_COMBINE)
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-	else
-		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
-	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
-		return ret;
-
-	if (off < count && user_count <= (count - off)) {
-		ret = remap_pfn_range(vma, vma->vm_start,
-				      pfn + off,
-				      user_count << PAGE_SHIFT,
-				      vma->vm_page_prot);
-	}
-
-	return ret;
-}
-
-static inline void __dma_sync_virtual(void *addr, size_t size,
-	enum dma_data_direction direction)
-{
-	switch (direction) {
-	case DMA_TO_DEVICE:
-		dma_cache_wback((unsigned long)addr, size);
-		break;
-
-	case DMA_FROM_DEVICE:
-		dma_cache_inv((unsigned long)addr, size);
-		break;
-
-	case DMA_BIDIRECTIONAL:
-		dma_cache_wback_inv((unsigned long)addr, size);
-		break;
-
-	default:
-		BUG();
-	}
-}
-
-/*
- * A single sg entry may refer to multiple physically contiguous
- * pages. But we still need to process highmem pages individually.
- * If highmem is not configured then the bulk of this loop gets
- * optimized out.
- */
-static inline void __dma_sync(struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction)
-{
-	size_t left = size;
-
-	do {
-		size_t len = left;
-
-		if (PageHighMem(page)) {
-			void *addr;
-
-			if (offset + len > PAGE_SIZE) {
-				if (offset >= PAGE_SIZE) {
-					page += offset >> PAGE_SHIFT;
-					offset &= ~PAGE_MASK;
-				}
-				len = PAGE_SIZE - offset;
-			}
-
-			addr = kmap_atomic(page);
-			__dma_sync_virtual(addr + offset, len, direction);
-			kunmap_atomic(addr);
-		} else
-			__dma_sync_virtual(page_address(page) + offset,
-					   size, direction);
-		offset = 0;
-		page++;
-		left -= len;
-	} while (left);
-}
-
-static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction, unsigned long attrs)
-{
-	if (cpu_needs_post_dma_flush(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(dma_addr_to_page(dev, dma_addr),
-			   dma_addr & ~PAGE_MASK, size, direction);
-	plat_post_dma_flush(dev);
-	plat_unmap_dma_mem(dev, dma_addr, size, direction);
-}
-
-static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-	int nents, enum dma_data_direction direction, unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		if (!plat_device_is_coherent(dev) &&
-		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		sg->dma_length = sg->length;
-#endif
-		sg->dma_address = plat_map_dma_mem_page(dev, sg_page(sg)) +
-				  sg->offset;
-	}
-
-	return nents;
-}
-
-static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	if (!plat_device_is_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(page, offset, size, direction);
-
-	return plat_map_dma_mem_page(dev, page) + offset;
-}
-
-static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-	int nhwentries, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nhwentries, i) {
-		if (!plat_device_is_coherent(dev) &&
-		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-		    direction != DMA_TO_DEVICE)
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		plat_unmap_dma_mem(dev, sg->dma_address, sg->length, direction);
-	}
-}
-
-static void mips_dma_sync_single_for_cpu(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	if (cpu_needs_post_dma_flush(dev))
-		__dma_sync(dma_addr_to_page(dev, dma_handle),
-			   dma_handle & ~PAGE_MASK, size, direction);
-	plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_single_for_device(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	if (!plat_device_is_coherent(dev))
-		__dma_sync(dma_addr_to_page(dev, dma_handle),
-			   dma_handle & ~PAGE_MASK, size, direction);
-}
-
-static void mips_dma_sync_sg_for_cpu(struct device *dev,
-	struct scatterlist *sglist, int nelems,
-	enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	if (cpu_needs_post_dma_flush(dev)) {
-		for_each_sg(sglist, sg, nelems, i) {
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		}
-	}
-	plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_sg_for_device(struct device *dev,
-	struct scatterlist *sglist, int nelems,
-	enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	if (!plat_device_is_coherent(dev)) {
-		for_each_sg(sglist, sg, nelems, i) {
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		}
-	}
-}
-
-static int mips_dma_supported(struct device *dev, u64 mask)
-{
-	return plat_dma_supported(dev, mask);
-}
-
-static void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-			 enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	if (!plat_device_is_coherent(dev))
-		__dma_sync_virtual(vaddr, size, direction);
-}
-
-static const struct dma_map_ops mips_default_dma_map_ops = {
-	.alloc = mips_dma_alloc_coherent,
-	.free = mips_dma_free_coherent,
-	.mmap = mips_dma_mmap,
-	.map_page = mips_dma_map_page,
-	.unmap_page = mips_dma_unmap_page,
-	.map_sg = mips_dma_map_sg,
-	.unmap_sg = mips_dma_unmap_sg,
-	.sync_single_for_cpu = mips_dma_sync_single_for_cpu,
-	.sync_single_for_device = mips_dma_sync_single_for_device,
-	.sync_sg_for_cpu = mips_dma_sync_sg_for_cpu,
-	.sync_sg_for_device = mips_dma_sync_sg_for_device,
-	.dma_supported = mips_dma_supported,
-	.cache_sync = mips_dma_cache_sync,
-};
-
-const struct dma_map_ops *mips_dma_map_ops = &mips_default_dma_map_ops;
-EXPORT_SYMBOL(mips_dma_map_ops);
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
new file mode 100644
index 000000000000..2aca1236af36
--- /dev/null
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
+ * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
+ * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
+ */
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/dma-contiguous.h>
+#include <linux/highmem.h>
+
+#include <asm/cache.h>
+#include <asm/cpu-type.h>
+#include <asm/dma-coherence.h>
+#include <asm/io.h>
+
+#ifdef CONFIG_DMA_PERDEV_COHERENT
+static inline int dev_is_coherent(struct device *dev)
+{
+	return dev->archdata.dma_coherent;
+}
+#else
+static inline int dev_is_coherent(struct device *dev)
+{
+	switch (coherentio) {
+	default:
+	case IO_COHERENCE_DEFAULT:
+		return hw_coherentio;
+	case IO_COHERENCE_ENABLED:
+		return 1;
+	case IO_COHERENCE_DISABLED:
+		return 0;
+	}
+}
+#endif /* CONFIG_DMA_PERDEV_COHERENT */
+
+/*
+ * The affected CPUs below in 'cpu_needs_post_dma_flush()' can speculatively
+ * fill random cachelines with stale data at any time, requiring an extra
+ * flush post-DMA.
+ *
+ * Warning on the terminology - Linux calls an uncached area coherent;  MIPS
+ * terminology calls memory areas with hardware maintained coherency coherent.
+ *
+ * Note that the R14000 and R16000 should also be checked for in this condition.
+ * However this function is only called on non-I/O-coherent systems and only the
+ * R10000 and R12000 are used in such systems, the SGI IP28 Indigo² rsp.
+ * SGI IP32 aka O2.
+ */
+static inline bool cpu_needs_post_dma_flush(struct device *dev)
+{
+	if (dev_is_coherent(dev))
+		return false;
+
+	switch (boot_cpu_type()) {
+	case CPU_R10000:
+	case CPU_R12000:
+	case CPU_BMIPS5000:
+		return true;
+	default:
+		/*
+		 * Presence of MAARs suggests that the CPU supports
+		 * speculatively prefetching data, and therefore requires
+		 * the post-DMA flush/invalidate.
+		 */
+		return cpu_has_maar;
+	}
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	void *ret;
+
+	ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+	if (!ret)
+		return NULL;
+
+	if (!dev_is_coherent(dev) && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
+		dma_cache_wback_inv((unsigned long) ret, size);
+		ret = (void *)UNCAC_ADDR(ret);
+	}
+
+	return ret;
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs)
+{
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !dev_is_coherent(dev))
+		cpu_addr = (void *)CAC_ADDR((unsigned long)cpu_addr);
+	dma_direct_free(dev, size, cpu_addr, dma_addr, attrs);
+}
+
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	unsigned long user_count = vma_pages(vma);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)cpu_addr;
+	unsigned long off = vma->vm_pgoff;
+	unsigned long pfn;
+	int ret = -ENXIO;
+
+	if (!dev_is_coherent(dev))
+		addr = CAC_ADDR(addr);
+
+	pfn = page_to_pfn(virt_to_page((void *)addr));
+
+	if (attrs & DMA_ATTR_WRITE_COMBINE)
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < count && user_count <= (count - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      user_count << PAGE_SHIFT,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
+static inline void dma_sync_virt(void *addr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_wback((unsigned long)addr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		dma_cache_inv((unsigned long)addr, size);
+		break;
+
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv((unsigned long)addr, size);
+		break;
+
+	default:
+		BUG();
+	}
+}
+
+/*
+ * A single sg entry may refer to multiple physically contiguous pages.  But
+ * we still need to process highmem pages individually.  If highmem is not
+ * configured then the bulk of this loop gets optimized out.
+ */
+static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	unsigned long offset = paddr & ~PAGE_MASK;
+	size_t left = size;
+
+	do {
+		size_t len = left;
+
+		if (PageHighMem(page)) {
+			void *addr;
+
+			if (offset + len > PAGE_SIZE) {
+				if (offset >= PAGE_SIZE) {
+					page += offset >> PAGE_SHIFT;
+					offset &= ~PAGE_MASK;
+				}
+				len = PAGE_SIZE - offset;
+			}
+
+			addr = kmap_atomic(page);
+			dma_sync_virt(addr + offset, len, dir);
+			kunmap_atomic(addr);
+		} else
+			dma_sync_virt(page_address(page) + offset, size, dir);
+		offset = 0;
+		page++;
+		left -= len;
+	} while (left);
+}
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (!dev_is_coherent(dev))
+		dma_sync_phys(paddr, size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (cpu_needs_post_dma_flush(dev))
+		dma_sync_phys(paddr, size, dir);
+}
+
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		enum dma_data_direction direction)
+{
+	BUG_ON(direction == DMA_NONE);
+
+	if (!dev_is_coherent(dev))
+		dma_sync_virt(vaddr, size, direction);
+}
diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index 1986e09fb457..1601d90b087b 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -9,6 +9,7 @@
 #include <linux/export.h>
 #include <asm/addrspace.h>
 #include <asm/byteorder.h>
+#include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
@@ -98,6 +99,20 @@ static int remap_area_pages(unsigned long address, phys_addr_t phys_addr,
 	return error;
 }
 
+static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
+			       void *arg)
+{
+	unsigned long i;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (pfn_valid(start_pfn + i) &&
+		    !PageReserved(pfn_to_page(start_pfn + i)))
+			return 1;
+	}
+
+	return 0;
+}
+
 /*
  * Generic mapping function (not visible outside):
  */
@@ -116,8 +131,8 @@ static int remap_area_pages(unsigned long address, phys_addr_t phys_addr,
 
 void __iomem * __ioremap(phys_addr_t phys_addr, phys_addr_t size, unsigned long flags)
 {
+	unsigned long offset, pfn, last_pfn;
 	struct vm_struct * area;
-	unsigned long offset;
 	phys_addr_t last_addr;
 	void * addr;
 
@@ -137,18 +152,16 @@ void __iomem * __ioremap(phys_addr_t phys_addr, phys_addr_t size, unsigned long
 		return (void __iomem *) CKSEG1ADDR(phys_addr);
 
 	/*
-	 * Don't allow anybody to remap normal RAM that we're using..
+	 * Don't allow anybody to remap RAM that may be allocated by the page
+	 * allocator, since that could lead to races & data clobbering.
 	 */
-	if (phys_addr < virt_to_phys(high_memory)) {
-		char *t_addr, *t_end;
-		struct page *page;
-
-		t_addr = __va(phys_addr);
-		t_end = t_addr + (size - 1);
-
-		for(page = virt_to_page(t_addr); page <= virt_to_page(t_end); page++)
-			if(!PageReserved(page))
-				return NULL;
+	pfn = PFN_DOWN(phys_addr);
+	last_pfn = PFN_DOWN(last_addr);
+	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+				  __ioremap_check_ram) == 1) {
+		WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
+			  &phys_addr, &last_addr);
+		return NULL;
 	}
 
 	/*
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index d5d02993aa21..56e4f8bffd4c 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -623,21 +623,6 @@ struct dmadscr {
 	u64 pad_b;
 } ____cacheline_aligned_in_smp page_descr[DM_NUM_CHANNELS];
 
-void sb1_dma_init(void)
-{
-	int i;
-
-	for (i = 0; i < DM_NUM_CHANNELS; i++) {
-		const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) |
-				     V_DM_DSCR_BASE_RINGSZ(1);
-		void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE));
-
-		__raw_writeq(base_val, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg);
-	}
-}
-
 void clear_page(void *page)
 {
 	u64 to_phys = CPHYSADDR((unsigned long)page);
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 79b9f2ad3ff5..49312a14cd17 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1509,7 +1509,7 @@ static void setup_pw(void)
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	write_c0_pwctl(1 << 6 | psn);
 #endif
-	write_c0_kpgd(swapper_pg_dir);
+	write_c0_kpgd((long)swapper_pg_dir);
 	kscratch_used_mask |= (1 << 7); /* KScratch6 is used for KPGD */
 }
 
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index 9bb6baa45da3..24e5b0d06899 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -19,7 +19,6 @@
 #include <asm/inst.h>
 #include <asm/elf.h>
 #include <asm/bugs.h>
-#define UASM_ISA	_UASM_ISA_MICROMIPS
 #include <asm/uasm.h>
 
 #define RS_MASK		0x1f
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 9fea6c6bbf49..60ceb93c71a0 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -19,7 +19,6 @@
 #include <asm/inst.h>
 #include <asm/elf.h>
 #include <asm/bugs.h>
-#define UASM_ISA	_UASM_ISA_CLASSIC
 #include <asm/uasm.h>
 
 #define RS_MASK		0x1f
diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile
index 63940bdce698..17c7fd471a27 100644
--- a/arch/mips/mti-malta/Makefile
+++ b/arch/mips/mti-malta/Makefile
@@ -13,11 +13,9 @@ obj-y				+= malta-init.o
 obj-y				+= malta-int.o
 obj-y				+= malta-memory.o
 obj-y				+= malta-platform.o
-obj-y				+= malta-reset.o
 obj-y				+= malta-setup.o
 obj-y				+= malta-time.o
 
 obj-$(CONFIG_MIPS_CMP)		+= malta-amon.o
-obj-$(CONFIG_MIPS_MALTA_PM)	+= malta-pm.o
 
 CFLAGS_malta-dtshim.o = -I$(src)/../../../scripts/dtc/libfdt
diff --git a/arch/mips/mti-malta/malta-pm.c b/arch/mips/mti-malta/malta-pm.c
deleted file mode 100644
index efbd659fb602..000000000000
--- a/arch/mips/mti-malta/malta-pm.c
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * Copyright (C) 2014 Imagination Technologies
- * Author: Paul Burton <paul.burton@mips.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/pci.h>
-
-#include <asm/mach-malta/malta-pm.h>
-
-static struct pci_bus *pm_pci_bus;
-static resource_size_t pm_io_offset;
-
-int mips_pm_suspend(unsigned state)
-{
-	int spec_devid;
-	u16 sts;
-
-	if (!pm_pci_bus || !pm_io_offset)
-		return -ENODEV;
-
-	/* Ensure the power button status is clear */
-	while (1) {
-		sts = inw(pm_io_offset + PIIX4_FUNC3IO_PMSTS);
-		if (!(sts & PIIX4_FUNC3IO_PMSTS_PWRBTN_STS))
-			break;
-		outw(sts, pm_io_offset + PIIX4_FUNC3IO_PMSTS);
-	}
-
-	/* Enable entry to suspend */
-	outw(state | PIIX4_FUNC3IO_PMCNTRL_SUS_EN,
-	     pm_io_offset + PIIX4_FUNC3IO_PMCNTRL);
-
-	/* If the special cycle occurs too soon this doesn't work... */
-	mdelay(10);
-
-	/*
-	 * The PIIX4 will enter the suspend state only after seeing a special
-	 * cycle with the correct magic data on the PCI bus. Generate that
-	 * cycle now.
-	 */
-	spec_devid = PCI_DEVID(0, PCI_DEVFN(0x1f, 0x7));
-	pci_bus_write_config_dword(pm_pci_bus, spec_devid, 0,
-				   PIIX4_SUSPEND_MAGIC);
-
-	/* Give the system some time to power down */
-	mdelay(1000);
-
-	return 0;
-}
-
-static int __init malta_pm_setup(void)
-{
-	struct pci_dev *dev;
-	int res, io_region = PCI_BRIDGE_RESOURCES;
-
-	/* Find a reference to the PCI bus */
-	pm_pci_bus = pci_find_next_bus(NULL);
-	if (!pm_pci_bus) {
-		pr_warn("malta-pm: failed to find reference to PCI bus\n");
-		return -ENODEV;
-	}
-
-	/* Find the PIIX4 PM device */
-	dev = pci_get_subsys(PCI_VENDOR_ID_INTEL,
-			     PCI_DEVICE_ID_INTEL_82371AB_3, PCI_ANY_ID,
-			     PCI_ANY_ID, NULL);
-	if (!dev) {
-		pr_warn("malta-pm: failed to find PIIX4 PM\n");
-		return -ENODEV;
-	}
-
-	/* Request access to the PIIX4 PM IO registers */
-	res = pci_request_region(dev, io_region, "PIIX4 PM IO registers");
-	if (res) {
-		pr_warn("malta-pm: failed to request PM IO registers (%d)\n",
-			res);
-		pci_dev_put(dev);
-		return -ENODEV;
-	}
-
-	/* Find the offset to the PIIX4 PM IO registers */
-	pm_io_offset = pci_resource_start(dev, io_region);
-
-	pci_dev_put(dev);
-	return 0;
-}
-
-late_initcall(malta_pm_setup);
diff --git a/arch/mips/mti-malta/malta-reset.c b/arch/mips/mti-malta/malta-reset.c
deleted file mode 100644
index dd6f62ad4417..000000000000
--- a/arch/mips/mti-malta/malta-reset.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 1999,2000 MIPS Technologies, Inc.  All rights reserved.
- */
-#include <linux/io.h>
-#include <linux/pm.h>
-#include <linux/reboot.h>
-
-#include <asm/reboot.h>
-#include <asm/mach-malta/malta-pm.h>
-
-static void mips_machine_power_off(void)
-{
-	mips_pm_suspend(PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF);
-
-	pr_info("Failed to power down, resetting\n");
-	machine_restart(NULL);
-}
-
-static int __init mips_reboot_setup(void)
-{
-	pm_power_off = mips_machine_power_off;
-
-	return 0;
-}
-arch_initcall(mips_reboot_setup);
diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index 7b63914d2e58..5d4c5e5fbd69 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -26,6 +26,7 @@
 #include <linux/screen_info.h>
 #include <linux/time.h>
 
+#include <asm/dma-coherence.h>
 #include <asm/fw/fw.h>
 #include <asm/mach-malta/malta-dtshim.h>
 #include <asm/mips-cps.h>
@@ -144,12 +145,6 @@ static int __init plat_enable_iocoherency(void)
 
 static void __init plat_setup_iocoherency(void)
 {
-#ifdef CONFIG_DMA_NONCOHERENT
-	/*
-	 * Kernel has been configured with software coherency
-	 * but we might choose to turn it off and use hardware
-	 * coherency instead.
-	 */
 	if (plat_enable_iocoherency()) {
 		if (coherentio == IO_COHERENCE_DISABLED)
 			pr_info("Hardware DMA cache coherency disabled\n");
@@ -161,10 +156,6 @@ static void __init plat_setup_iocoherency(void)
 		else
 			pr_info("Software DMA cache coherency enabled\n");
 	}
-#else
-	if (!plat_enable_iocoherency())
-		panic("Hardware DMA cache coherency not supported!");
-#endif
 }
 
 static void __init pci_clock_check(void)
@@ -226,29 +217,6 @@ static void __init bonito_quirks_setup(void)
 		pr_info("Enabled Bonito debug mode\n");
 	} else
 		BONITO_BONGENCFG &= ~BONITO_BONGENCFG_DEBUGMODE;
-
-#ifdef CONFIG_DMA_COHERENT
-	if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) {
-		BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN;
-		pr_info("Enabled Bonito CPU coherency\n");
-
-		argptr = fw_getcmdline();
-		if (strstr(argptr, "iobcuncached")) {
-			BONITO_PCICACHECTRL &= ~BONITO_PCICACHECTRL_IOBCCOH_EN;
-			BONITO_PCIMEMBASECFG = BONITO_PCIMEMBASECFG &
-				~(BONITO_PCIMEMBASECFG_MEMBASE0_CACHED |
-					BONITO_PCIMEMBASECFG_MEMBASE1_CACHED);
-			pr_info("Disabled Bonito IOBC coherency\n");
-		} else {
-			BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_IOBCCOH_EN;
-			BONITO_PCIMEMBASECFG |=
-				(BONITO_PCIMEMBASECFG_MEMBASE0_CACHED |
-					BONITO_PCIMEMBASECFG_MEMBASE1_CACHED);
-			pr_info("Enabled Bonito IOBC coherency\n");
-		}
-	} else
-		panic("Hardware DMA cache coherency not supported");
-#endif
 }
 
 void __init *plat_get_fdt(void)
@@ -279,11 +247,6 @@ void __init plat_mem_setup(void)
 	 */
 	enable_dma(4);
 
-#ifdef CONFIG_DMA_COHERENT
-	if (mips_revision_sconid != MIPS_REVISION_SCON_BONITO)
-		panic("Hardware DMA cache coherency not supported");
-#endif
-
 	if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO)
 		bonito_quirks_setup();
 
diff --git a/arch/mips/netlogic/common/earlycons.c b/arch/mips/netlogic/common/earlycons.c
index 769f93032c53..8f5bc1597550 100644
--- a/arch/mips/netlogic/common/earlycons.c
+++ b/arch/mips/netlogic/common/earlycons.c
@@ -36,6 +36,7 @@
 #include <linux/serial_reg.h>
 
 #include <asm/mipsregs.h>
+#include <asm/setup.h>
 #include <asm/netlogic/haldefs.h>
 #include <asm/netlogic/common.h>
 
diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c
index 856a6e6d296e..b5ba83f4c646 100644
--- a/arch/mips/netlogic/xlp/dt.c
+++ b/arch/mips/netlogic/xlp/dt.c
@@ -93,17 +93,3 @@ void __init device_tree_init(void)
 {
 	unflatten_and_copy_device_tree();
 }
-
-static struct of_device_id __initdata xlp_ids[] = {
-	{ .compatible = "simple-bus", },
-	{},
-};
-
-int __init xlp8xx_ds_publish_devices(void)
-{
-	if (!of_have_populated_dt())
-		return 0;
-	return of_platform_bus_probe(NULL, xlp_ids, NULL);
-}
-
-device_initcall(xlp8xx_ds_publish_devices);
diff --git a/arch/mips/paravirt/serial.c b/arch/mips/paravirt/serial.c
index 02b665c02272..a37b6f9f0ede 100644
--- a/arch/mips/paravirt/serial.c
+++ b/arch/mips/paravirt/serial.c
@@ -9,16 +9,15 @@
 #include <linux/kernel.h>
 #include <linux/virtio_console.h>
 #include <linux/kvm_para.h>
+#include <asm/setup.h>
 
 /*
  * Emit one character to the boot console.
  */
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	kvm_hypercall3(KVM_HC_MIPS_CONSOLE_OUTPUT, 0 /*  port 0 */,
 		(unsigned long)&c, 1 /* len == 1 */);
-
-	return 1;
 }
 
 #ifdef CONFIG_VIRTIO_CONSOLE
diff --git a/arch/mips/pci/ops-bridge.c b/arch/mips/pci/ops-bridge.c
index 57e1463fcd02..a1d2c4ae0d1b 100644
--- a/arch/mips/pci/ops-bridge.c
+++ b/arch/mips/pci/ops-bridge.c
@@ -167,7 +167,7 @@ oh_my_gawd:
 static int pci_read_config(struct pci_bus *bus, unsigned int devfn,
 			   int where, int size, u32 * value)
 {
-	if (bus->number > 0)
+	if (!pci_is_root_bus(bus))
 		return pci_conf1_read_config(bus, devfn, where, size, value);
 
 	return pci_conf0_read_config(bus, devfn, where, size, value);
@@ -310,7 +310,7 @@ oh_my_gawd:
 static int pci_write_config(struct pci_bus *bus, unsigned int devfn,
 	int where, int size, u32 value)
 {
-	if (bus->number > 0)
+	if (!pci_is_root_bus(bus))
 		return pci_conf1_write_config(bus, devfn, where, size, value);
 
 	return pci_conf0_write_config(bus, devfn, where, size, value);
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index b4fa6413c4e5..c539d0d2b0cf 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -149,6 +149,13 @@
 #define AR2315_PCI_HOST_SLOT	3
 #define AR2315_PCI_HOST_DEVID	((0xff18 << 16) | PCI_VENDOR_ID_ATHEROS)
 
+/*
+ * We need some arbitrary non-zero value to be programmed to the BAR1 register
+ * of PCI host controller to enable DMA. The same value should be used as the
+ * offset to calculate the physical address of DMA buffer for PCI devices.
+ */
+#define AR2315_PCI_HOST_SDRAM_BASEADDR	0x20000000
+
 /* ??? access BAR */
 #define AR2315_PCI_HOST_MBAR0		0x10000000
 /* RAM access BAR */
@@ -167,6 +174,23 @@ struct ar2315_pci_ctrl {
 	struct resource io_res;
 };
 
+static inline dma_addr_t ar2315_dev_offset(struct device *dev)
+{
+	if (dev && dev_is_pci(dev))
+		return AR2315_PCI_HOST_SDRAM_BASEADDR;
+	return 0;
+}
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr + ar2315_dev_offset(dev);
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr - ar2315_dev_offset(dev);
+}
+
 static inline struct ar2315_pci_ctrl *ar2315_pci_bus_to_apc(struct pci_bus *bus)
 {
 	struct pci_controller *hose = bus->sysdata;
diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c
index 1e23c8d587bd..64b58cc48a91 100644
--- a/arch/mips/pci/pci-ar724x.c
+++ b/arch/mips/pci/pci-ar724x.c
@@ -12,14 +12,18 @@
 #include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <asm/mach-ath79/ath79.h>
 #include <asm/mach-ath79/ar71xx_regs.h>
 
+#define AR724X_PCI_REG_APP		0x00
 #define AR724X_PCI_REG_RESET		0x18
 #define AR724X_PCI_REG_INT_STATUS	0x4c
 #define AR724X_PCI_REG_INT_MASK		0x50
 
+#define AR724X_PCI_APP_LTSSM_ENABLE	BIT(0)
+
 #define AR724X_PCI_RESET_LINK_UP	BIT(0)
 
 #define AR724X_PCI_INT_DEV0		BIT(14)
@@ -325,6 +329,37 @@ static void ar724x_pci_irq_init(struct ar724x_pci_controller *apc,
 					 apc);
 }
 
+static void ar724x_pci_hw_init(struct ar724x_pci_controller *apc)
+{
+	u32 ppl, app;
+	int wait = 0;
+
+	/* deassert PCIe host controller and PCIe PHY reset */
+	ath79_device_reset_clear(AR724X_RESET_PCIE);
+	ath79_device_reset_clear(AR724X_RESET_PCIE_PHY);
+
+	/* remove the reset of the PCIE PLL */
+	ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG);
+	ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET;
+	ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl);
+
+	/* deassert bypass for the PCIE PLL */
+	ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG);
+	ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS;
+	ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl);
+
+	/* set PCIE Application Control to ready */
+	app = __raw_readl(apc->ctrl_base + AR724X_PCI_REG_APP);
+	app |= AR724X_PCI_APP_LTSSM_ENABLE;
+	__raw_writel(app, apc->ctrl_base + AR724X_PCI_REG_APP);
+
+	/* wait up to 100ms for PHY link up */
+	do {
+		mdelay(10);
+		wait++;
+	} while (wait < 10 && !ar724x_pci_check_link(apc));
+}
+
 static int ar724x_pci_probe(struct platform_device *pdev)
 {
 	struct ar724x_pci_controller *apc;
@@ -383,6 +418,13 @@ static int ar724x_pci_probe(struct platform_device *pdev)
 	apc->pci_controller.io_resource = &apc->io_res;
 	apc->pci_controller.mem_resource = &apc->mem_res;
 
+	/*
+	 * Do the full PCIE Root Complex Initialization Sequence if the PCIe
+	 * host controller is in reset.
+	 */
+	if (ath79_reset_rr(AR724X_RESET_REG_RESET_MODULE) & AR724X_RESET_PCIE)
+		ar724x_pci_hw_init(apc);
+
 	apc->link_up = ar724x_pci_check_link(apc);
 	if (!apc->link_up)
 		dev_warn(&pdev->dev, "PCIe link is down\n");
diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c
index 0f09eafa5e3a..c94a66070a60 100644
--- a/arch/mips/pci/pci-ip27.c
+++ b/arch/mips/pci/pci-ip27.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/smp.h>
+#include <linux/dma-direct.h>
 #include <asm/sn/arch.h>
 #include <asm/pci/bridge.h>
 #include <asm/paccess.h>
@@ -182,6 +183,19 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 	return 0;
 }
 
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
+
+	return bc->baddr + paddr;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr & ~(0xffUL << 56);
+}
+
 /*
  * Device might live on a subordinate PCI bus.	XXX Walk up the chain of buses
  * to find the slot number in sense of the bridge device register.
@@ -200,17 +214,6 @@ static inline void pci_disable_swapping(struct pci_dev *dev)
 	bridge->b_widget.w_tflush;	/* Flush */
 }
 
-static inline void pci_enable_swapping(struct pci_dev *dev)
-{
-	struct bridge_controller *bc = BRIDGE_CONTROLLER(dev->bus);
-	bridge_t *bridge = bc->base;
-	int slot = PCI_SLOT(dev->devfn);
-
-	/* Turn on byte swapping */
-	bridge->b_device[slot].reg |= BRIDGE_DEV_SWAP_DIR;
-	bridge->b_widget.w_tflush;	/* Flush */
-}
-
 static void pci_fixup_ioc3(struct pci_dev *d)
 {
 	pci_disable_swapping(d);
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index 3e92a06fa772..5017d5843c5a 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -21,8 +21,6 @@
 #include <asm/octeon/cvmx-pci-defs.h>
 #include <asm/octeon/pci-octeon.h>
 
-#include <dma-coherence.h>
-
 #define USE_OCTEON_INTERNAL_ARBITER
 
 /*
@@ -166,8 +164,6 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 		pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, dconfig);
 	}
 
-	dev->dev.dma_ops = octeon_pci_dma_map_ops;
-
 	return 0;
 }
 
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index 9632436d74d7..c2e94cf5ecda 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -54,5 +54,5 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 	phys_addr_t size = resource_size(rsrc);
 
 	*start = fixup_bigphys_addr(rsrc->start, size);
-	*end = rsrc->start + size;
+	*end = rsrc->start + size - 1;
 }
diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
index 87ba86bd8696..d919a0d813a1 100644
--- a/arch/mips/pci/pcie-octeon.c
+++ b/arch/mips/pci/pcie-octeon.c
@@ -94,8 +94,6 @@ union cvmx_pcie_address {
 
 static int cvmx_pcie_rc_initialize(int pcie_port);
 
-#include <dma-coherence.h>
-
 /**
  * Return the Core virtual base address for PCIe IO access. IOs are
  * read/written as an offset from this address.
@@ -1239,14 +1237,14 @@ static int __cvmx_pcie_rc_initialize_gen2(int pcie_port)
 	/* CN63XX Pass 1.0 errata G-14395 requires the QLM De-emphasis be programmed */
 	if (OCTEON_IS_MODEL(OCTEON_CN63XX_PASS1_0)) {
 		if (pcie_port) {
-			union cvmx_ciu_qlm1 ciu_qlm;
+			union cvmx_ciu_qlm ciu_qlm;
 			ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM1);
 			ciu_qlm.s.txbypass = 1;
 			ciu_qlm.s.txdeemph = 5;
 			ciu_qlm.s.txmargin = 0x17;
 			cvmx_write_csr(CVMX_CIU_QLM1, ciu_qlm.u64);
 		} else {
-			union cvmx_ciu_qlm0 ciu_qlm;
+			union cvmx_ciu_qlm ciu_qlm;
 			ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM0);
 			ciu_qlm.s.txbypass = 1;
 			ciu_qlm.s.txdeemph = 5;
diff --git a/arch/mips/pic32/pic32mzda/early_console.c b/arch/mips/pic32/pic32mzda/early_console.c
index d7b783463fac..8ed4961b1271 100644
--- a/arch/mips/pic32/pic32mzda/early_console.c
+++ b/arch/mips/pic32/pic32mzda/early_console.c
@@ -13,6 +13,7 @@
  */
 #include <asm/mach-pic32/pic32.h>
 #include <asm/fw/fw.h>
+#include <asm/setup.h>
 
 #include "pic32mzda.h"
 #include "early_pin.h"
@@ -157,7 +158,7 @@ void __init fw_init_early_console(char port)
 	setup_early_console(port, baud);
 }
 
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	if (console_port >= 0) {
 		while (__raw_readl(
@@ -166,6 +167,4 @@ int prom_putchar(char c)
 
 		__raw_writel(c, uart_base + U_TXR(console_port));
 	}
-
-	return 1;
 }
diff --git a/arch/mips/ralink/early_printk.c b/arch/mips/ralink/early_printk.c
index 3c59ffe5f5f5..ecd30ddfb3db 100644
--- a/arch/mips/ralink/early_printk.c
+++ b/arch/mips/ralink/early_printk.c
@@ -10,6 +10,7 @@
 #include <linux/serial_reg.h>
 
 #include <asm/addrspace.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_SOC_RT288X
 #define EARLY_UART_BASE		0x300c00
@@ -68,7 +69,7 @@ static void find_uart_base(void)
 	}
 }
 
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
 {
 	if (!init_complete) {
 		find_uart_base();
@@ -76,13 +77,13 @@ void prom_putchar(unsigned char ch)
 	}
 
 	if (IS_ENABLED(CONFIG_SOC_MT7621) || soc_is_mt7628()) {
-		uart_w32(ch, UART_TX);
+		uart_w32((unsigned char)ch, UART_TX);
 		while ((uart_r32(UART_REG_LSR) & UART_LSR_THRE) == 0)
 			;
 	} else {
 		while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0)
 			;
-		uart_w32(ch, UART_REG_TX);
+		uart_w32((unsigned char)ch, UART_REG_TX);
 		while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0)
 			;
 	}
diff --git a/arch/mips/sgi-ip27/ip27-console.c b/arch/mips/sgi-ip27/ip27-console.c
index 45fdfbcbd4c6..6bdb48d41276 100644
--- a/arch/mips/sgi-ip27/ip27-console.c
+++ b/arch/mips/sgi-ip27/ip27-console.c
@@ -7,6 +7,7 @@
  */
 
 #include <asm/page.h>
+#include <asm/setup.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/sn0/hub.h>
 #include <asm/sn/klconfig.h>
diff --git a/arch/mips/sgi-ip32/Makefile b/arch/mips/sgi-ip32/Makefile
index 60f0227425e7..4745cd94df11 100644
--- a/arch/mips/sgi-ip32/Makefile
+++ b/arch/mips/sgi-ip32/Makefile
@@ -4,4 +4,4 @@
 #
 
 obj-y	+= ip32-berr.o ip32-irq.o ip32-platform.o ip32-setup.o ip32-reset.o \
-	   crime.o ip32-memory.o
+	   crime.o ip32-memory.o ip32-dma.o
diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c
new file mode 100644
index 000000000000..fa7b17cb5385
--- /dev/null
+++ b/arch/mips/sgi-ip32/ip32-dma.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
+ */
+#include <linux/dma-direct.h>
+#include <asm/ip32/crime.h>
+
+/*
+ * Few notes.
+ * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M
+ * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for
+ *    native-endian)
+ * 3. All other devices see memory as one big chunk at 0x40000000
+ * 4. Non-PCI devices will pass NULL as struct device*
+ *
+ * Thus we translate differently, depending on device.
+ */
+
+#define RAM_OFFSET_MASK 0x3fffffffUL
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	dma_addr_t dma_addr = paddr & RAM_OFFSET_MASK;
+
+	if (!dev)
+		dma_addr += CRIME_HI_MEM_BASE;
+	return dma_addr;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK;
+
+	if (dma_addr >= 256*1024*1024)
+		paddr += CRIME_HI_MEM_BASE;
+	return paddr;
+}
diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig
index f4dbce25bc6a..7ec278d72096 100644
--- a/arch/mips/sibyte/Kconfig
+++ b/arch/mips/sibyte/Kconfig
@@ -70,7 +70,6 @@ config SIBYTE_BCM1x55
 
 config SIBYTE_SB1xxx_SOC
 	bool
-	select DMA_COHERENT
 	select IRQ_MIPS_CPU
 	select SWAP_IO_SPACE
 	select SYS_SUPPORTS_32BIT_KERNEL
diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c
index 115399202eab..092fb2a6ec4a 100644
--- a/arch/mips/sibyte/common/cfe.c
+++ b/arch/mips/sibyte/common/cfe.c
@@ -27,6 +27,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/sibyte/board.h>
 #include <asm/smp-ops.h>
 
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 1791a44ee570..f6d9182ef82a 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -20,6 +20,7 @@
 #include <linux/err.h>
 #include <linux/gpio/driver.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 #include <linux/serial_core.h>
 #include <linux/mtd/physmap.h>
 #include <linux/leds.h>
@@ -32,10 +33,10 @@
 #include <asm/reboot.h>
 #include <asm/r4kcache.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 #include <asm/txx9/generic.h>
 #include <asm/txx9/pci.h>
 #include <asm/txx9tmr.h>
-#include <asm/txx9/ndfmc.h>
 #include <asm/txx9/dmac.h>
 #ifdef CONFIG_CPU_TX49XX
 #include <asm/txx9/tx4938.h>
diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c
index 85d1795652da..17395d5d15ca 100644
--- a/arch/mips/txx9/generic/setup_tx4938.c
+++ b/arch/mips/txx9/generic/setup_tx4938.c
@@ -17,13 +17,13 @@
 #include <linux/ptrace.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 #include <asm/reboot.h>
 #include <asm/traps.h>
 #include <asm/txx9irq.h>
 #include <asm/txx9tmr.h>
 #include <asm/txx9pio.h>
 #include <asm/txx9/generic.h>
-#include <asm/txx9/ndfmc.h>
 #include <asm/txx9/dmac.h>
 #include <asm/txx9/tx4938.h>
 
diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c
index 274928987a21..360c388f4c82 100644
--- a/arch/mips/txx9/generic/setup_tx4939.c
+++ b/arch/mips/txx9/generic/setup_tx4939.c
@@ -21,13 +21,13 @@
 #include <linux/ptrace.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
 #include <asm/traps.h>
 #include <asm/txx9irq.h>
 #include <asm/txx9tmr.h>
 #include <asm/txx9/generic.h>
-#include <asm/txx9/ndfmc.h>
 #include <asm/txx9/dmac.h>
 #include <asm/txx9/tx4939.h>
 
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index ce196046ac3e..34605ca21498 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -7,7 +7,13 @@ ccflags-vdso := \
 	$(filter -I%,$(KBUILD_CFLAGS)) \
 	$(filter -E%,$(KBUILD_CFLAGS)) \
 	$(filter -mmicromips,$(KBUILD_CFLAGS)) \
-	$(filter -march=%,$(KBUILD_CFLAGS))
+	$(filter -march=%,$(KBUILD_CFLAGS)) \
+	-D__VDSO__
+
+ifeq ($(cc-name),clang)
+ccflags-vdso += $(filter --target=%,$(KBUILD_CFLAGS))
+endif
+
 cflags-vdso := $(ccflags-vdso) \
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
 	-O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
@@ -38,6 +44,7 @@ endif
 # VDSO linker flags.
 VDSO_LDFLAGS := \
 	-Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \
+	$(addprefix -Wl$(comma),$(filter -E%,$(KBUILD_CFLAGS))) \
 	-nostdlib -shared \
 	$(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
 	$(call cc-ldoption, -Wl$(comma)--build-id)
diff --git a/arch/mips/vdso/genvdso.h b/arch/mips/vdso/genvdso.h
index 94334727059a..611b06f01a3c 100644
--- a/arch/mips/vdso/genvdso.h
+++ b/arch/mips/vdso/genvdso.h
@@ -15,8 +15,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso)
 	ELF(Shdr) *shdr;
 	char *shstrtab, *name;
 	uint16_t sh_count, sh_entsize, i;
-	unsigned int local_gotno, symtabno, gotsym;
-	ELF(Dyn) *dyn = NULL;
 
 	shdrs = vdso + FUNC(swap_uint)(ehdr->e_shoff);
 	sh_count = swap_uint16(ehdr->e_shnum);
@@ -41,9 +39,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso)
 				"%s: '%s' contains relocation sections\n",
 				program_name, path);
 			return false;
-		case SHT_DYNAMIC:
-			dyn = vdso + FUNC(swap_uint)(shdr->sh_offset);
-			break;
 		}
 
 		/* Check for existing sections. */
@@ -61,52 +56,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso)
 		}
 	}
 
-	/*
-	 * Ensure the GOT has no entries other than the standard 2, for the same
-	 * reason we check that there's no relocation sections above.
-	 * The standard two entries are:
-	 * - Lazy resolver
-	 * - Module pointer
-	 */
-	if (dyn) {
-		local_gotno = symtabno = gotsym = 0;
-
-		while (FUNC(swap_uint)(dyn->d_tag) != DT_NULL) {
-			switch (FUNC(swap_uint)(dyn->d_tag)) {
-			/*
-			 * This member holds the number of local GOT entries.
-			 */
-			case DT_MIPS_LOCAL_GOTNO:
-				local_gotno = FUNC(swap_uint)(dyn->d_un.d_val);
-				break;
-			/*
-			 * This member holds the number of entries in the
-			 * .dynsym section.
-			 */
-			case DT_MIPS_SYMTABNO:
-				symtabno = FUNC(swap_uint)(dyn->d_un.d_val);
-				break;
-			/*
-			 * This member holds the index of the first dynamic
-			 * symbol table entry that corresponds to an entry in
-			 * the GOT.
-			 */
-			case DT_MIPS_GOTSYM:
-				gotsym = FUNC(swap_uint)(dyn->d_un.d_val);
-				break;
-			}
-
-			dyn++;
-		}
-
-		if (local_gotno > 2 || symtabno - gotsym) {
-			fprintf(stderr,
-				"%s: '%s' contains unexpected GOT entries\n",
-				program_name, path);
-			return false;
-		}
-	}
-
 	return true;
 }
 
diff --git a/arch/mips/vr41xx/common/pmu.c b/arch/mips/vr41xx/common/pmu.c
index 39a0db3e2b34..16e684b59875 100644
--- a/arch/mips/vr41xx/common/pmu.c
+++ b/arch/mips/vr41xx/common/pmu.c
@@ -17,6 +17,7 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
+#include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
@@ -46,7 +47,7 @@ static void __iomem *pmu_base;
 #define pmu_read(offset)		readw(pmu_base + (offset))
 #define pmu_write(offset, value)	writew((value), pmu_base + (offset))
 
-static void vr41xx_cpu_wait(void)
+static void __cpuidle vr41xx_cpu_wait(void)
 {
 	local_irq_disable();
 	if (!need_resched())
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 6aed974276d8..34f7222c5efe 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -12,17 +12,17 @@ config NDS32
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select DMA_NONCOHERENT_OPS
-	select GENERIC_ASHLDI3
-	select GENERIC_ASHRDI3
-	select GENERIC_LSHRDI3
-	select GENERIC_CMPDI2
-	select GENERIC_MULDI3
-	select GENERIC_UCMPDI2
 	select GENERIC_ATOMIC64
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_SHOW
+	select GENERIC_LIB_ASHLDI3
+	select GENERIC_LIB_ASHRDI3
+	select GENERIC_LIB_CMPDI2
+	select GENERIC_LIB_LSHRDI3
+	select GENERIC_LIB_MULDI3
+	select GENERIC_LIB_UCMPDI2
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 513bb2e9baf9..031c676821ff 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -34,10 +34,12 @@ ifdef CONFIG_CPU_LITTLE_ENDIAN
 KBUILD_CFLAGS   += $(call cc-option, -EL)
 KBUILD_AFLAGS   += $(call cc-option, -EL)
 LDFLAGS         += $(call cc-option, -EL)
+CHECKFLAGS      += -D__NDS32_EL__
 else
 KBUILD_CFLAGS   += $(call cc-option, -EB)
 KBUILD_AFLAGS   += $(call cc-option, -EB)
 LDFLAGS         += $(call cc-option, -EB)
+CHECKFLAGS      += -D__NDS32_EB__
 endif
 
 boot := arch/nds32/boot
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index 10b48f0d8e85..8b26198d51bb 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -8,6 +8,8 @@
 
 #define PG_dcache_dirty PG_arch_1
 
+void flush_icache_range(unsigned long start, unsigned long end);
+void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #ifdef CONFIG_CPU_CACHE_ALIASING
 void flush_cache_mm(struct mm_struct *mm);
 void flush_cache_dup_mm(struct mm_struct *mm);
@@ -34,13 +36,16 @@ void flush_anon_page(struct vm_area_struct *vma,
 void flush_kernel_dcache_page(struct page *page);
 void flush_kernel_vmap_range(void *addr, int size);
 void invalidate_kernel_vmap_range(void *addr, int size);
-void flush_icache_range(unsigned long start, unsigned long end);
-void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #define flush_dcache_mmap_lock(mapping)   xa_lock_irq(&(mapping)->i_pages)
 #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages)
 
 #else
 #include <asm-generic/cacheflush.h>
+#undef flush_icache_range
+#undef flush_icache_page
+#undef flush_icache_user_range
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+	                     unsigned long addr, int len);
 #endif
 
 #endif /* __NDS32_CACHEFLUSH_H__ */
diff --git a/arch/nds32/include/asm/futex.h b/arch/nds32/include/asm/futex.h
index eab5e84bd991..cb6cb91cfdf8 100644
--- a/arch/nds32/include/asm/futex.h
+++ b/arch/nds32/include/asm/futex.h
@@ -16,7 +16,7 @@
 	"	.popsection\n"					\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"4:	move	%0, " err_reg "\n"			\
-	"	j	3b\n"					\
+	"	b	3b\n"					\
 	"	.popsection"
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c
index 2f5b2ccebe47..63a1a5ef5219 100644
--- a/arch/nds32/kernel/setup.c
+++ b/arch/nds32/kernel/setup.c
@@ -278,7 +278,8 @@ static void __init setup_memory(void)
 
 void __init setup_arch(char **cmdline_p)
 {
-	early_init_devtree( __dtb_start);
+	early_init_devtree(__atags_pointer ? \
+		phys_to_virt(__atags_pointer) : __dtb_start);
 
 	setup_cpuinfo();
 
diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c
index ce8fd34497bf..254703653b6f 100644
--- a/arch/nds32/mm/cacheflush.c
+++ b/arch/nds32/mm/cacheflush.c
@@ -13,7 +13,39 @@
 
 extern struct cache_info L1_cache_info[2];
 
-#ifndef CONFIG_CPU_CACHE_ALIASING
+void flush_icache_range(unsigned long start, unsigned long end)
+{
+	unsigned long line_size, flags;
+	line_size = L1_cache_info[DCACHE].line_size;
+	start = start & ~(line_size - 1);
+	end = (end + line_size - 1) & ~(line_size - 1);
+	local_irq_save(flags);
+	cpu_cache_wbinval_range(start, end, 1);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_range);
+
+void flush_icache_page(struct vm_area_struct *vma, struct page *page)
+{
+	unsigned long flags;
+	unsigned long kaddr;
+	local_irq_save(flags);
+	kaddr = (unsigned long)kmap_atomic(page);
+	cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
+	kunmap_atomic((void *)kaddr);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_page);
+
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+	                     unsigned long addr, int len)
+{
+	unsigned long kaddr;
+	kaddr = (unsigned long)kmap_atomic(page) + (addr & ~PAGE_MASK);
+	flush_icache_range(kaddr, kaddr + len);
+	kunmap_atomic((void *)kaddr);
+}
+
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 		      pte_t * pte)
 {
@@ -35,19 +67,15 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 
 	if ((test_and_clear_bit(PG_dcache_dirty, &page->flags)) ||
 	    (vma->vm_flags & VM_EXEC)) {
-
-		if (!PageHighMem(page)) {
-			cpu_cache_wbinval_page((unsigned long)
-					       page_address(page),
-					       vma->vm_flags & VM_EXEC);
-		} else {
-			unsigned long kaddr = (unsigned long)kmap_atomic(page);
-			cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
-			kunmap_atomic((void *)kaddr);
-		}
+		unsigned long kaddr;
+		local_irq_save(flags);
+		kaddr = (unsigned long)kmap_atomic(page);
+		cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
+		kunmap_atomic((void *)kaddr);
+		local_irq_restore(flags);
 	}
 }
-#else
+#ifdef CONFIG_CPU_CACHE_ALIASING
 extern pte_t va_present(struct mm_struct *mm, unsigned long addr);
 
 static inline unsigned long aliasing(unsigned long addr, unsigned long page)
@@ -317,52 +345,4 @@ void invalidate_kernel_vmap_range(void *addr, int size)
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);
-
-void flush_icache_range(unsigned long start, unsigned long end)
-{
-	unsigned long line_size, flags;
-	line_size = L1_cache_info[DCACHE].line_size;
-	start = start & ~(line_size - 1);
-	end = (end + line_size - 1) & ~(line_size - 1);
-	local_irq_save(flags);
-	cpu_cache_wbinval_range(start, end, 1);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(flush_icache_range);
-
-void flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
-	unsigned long flags;
-	local_irq_save(flags);
-	cpu_cache_wbinval_page((unsigned long)page_address(page),
-			       vma->vm_flags & VM_EXEC);
-	local_irq_restore(flags);
-}
-
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
-		      pte_t * pte)
-{
-	struct page *page;
-	unsigned long flags;
-	unsigned long pfn = pte_pfn(*pte);
-
-	if (!pfn_valid(pfn))
-		return;
-
-	if (vma->vm_mm == current->active_mm) {
-		local_irq_save(flags);
-		__nds32__mtsr_dsb(addr, NDS32_SR_TLB_VPN);
-		__nds32__tlbop_rwr(*pte);
-		__nds32__isb();
-		local_irq_restore(flags);
-	}
-
-	page = pfn_to_page(pfn);
-	if (test_and_clear_bit(PG_dcache_dirty, &page->flags) ||
-	    (vma->vm_flags & VM_EXEC)) {
-		local_irq_save(flags);
-		cpu_dcache_wbinval_page((unsigned long)page_address(page));
-		local_irq_restore(flags);
-	}
-}
 #endif
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 3d4ec88f1db1..92035042cf62 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -1,6 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 config NIOS2
 	def_bool y
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_NONCOHERENT_OPS
 	select TIMER_OF
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 64ed3d656956..8fde4fa2c34f 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/nios2/include/asm/dma-mapping.h b/arch/nios2/include/asm/dma-mapping.h
deleted file mode 100644
index 6ceb92251da0..000000000000
--- a/arch/nios2/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (C) 2011 Tobias Klauser <tklauser@distanz.ch>
- * Copyright (C) 2009 Wind River Systems Inc
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file COPYING in the main directory of this
- * archive for more details.
- */
-
-#ifndef _ASM_NIOS2_DMA_MAPPING_H
-#define _ASM_NIOS2_DMA_MAPPING_H
-
-extern const struct dma_map_ops nios2_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &nios2_dma_ops;
-}
-
-#endif /* _ASM_NIOS2_DMA_MAPPING_H */
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index 4be815519dd4..4af9e5b5ba1c 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -12,18 +12,18 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <linux/export.h>
 #include <linux/string.h>
-#include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/cache.h>
 #include <asm/cacheflush.h>
 
-static inline void __dma_sync_for_device(void *vaddr, size_t size,
-			      enum dma_data_direction direction)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	switch (direction) {
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
 	case DMA_FROM_DEVICE:
 		invalidate_dcache_range((unsigned long)vaddr,
 			(unsigned long)(vaddr + size));
@@ -42,10 +42,12 @@ static inline void __dma_sync_for_device(void *vaddr, size_t size,
 	}
 }
 
-static inline void __dma_sync_for_cpu(void *vaddr, size_t size,
-			      enum dma_data_direction direction)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	switch (direction) {
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
 	case DMA_BIDIRECTIONAL:
 	case DMA_FROM_DEVICE:
 		invalidate_dcache_range((unsigned long)vaddr,
@@ -58,8 +60,8 @@ static inline void __dma_sync_for_cpu(void *vaddr, size_t size,
 	}
 }
 
-static void *nios2_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	void *ret;
 
@@ -80,125 +82,10 @@ static void *nios2_dma_alloc(struct device *dev, size_t size,
 	return ret;
 }
 
-static void nios2_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	unsigned long addr = (unsigned long) CAC_ADDR((unsigned long) vaddr);
 
 	free_pages(addr, get_order(size));
 }
-
-static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int i;
-
-	for_each_sg(sg, sg, nents, i) {
-		void *addr = sg_virt(sg);
-
-		if (!addr)
-			continue;
-
-		sg->dma_address = sg_phys(sg);
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		__dma_sync_for_device(addr, sg->length, direction);
-	}
-
-	return nents;
-}
-
-static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page,
-			unsigned long offset, size_t size,
-			enum dma_data_direction direction,
-			unsigned long attrs)
-{
-	void *addr = page_address(page) + offset;
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync_for_device(addr, size, direction);
-
-	return page_to_phys(page) + offset;
-}
-
-static void nios2_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-		size_t size, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
-}
-
-static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nhwentries, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	void *addr;
-	int i;
-
-	if (direction == DMA_TO_DEVICE)
-		return;
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	for_each_sg(sg, sg, nhwentries, i) {
-		addr = sg_virt(sg);
-		if (addr)
-			__dma_sync_for_cpu(addr, sg->length, direction);
-	}
-}
-
-static void nios2_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	__dma_sync_for_cpu(phys_to_virt(dma_handle), size, direction);
-}
-
-static void nios2_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	__dma_sync_for_device(phys_to_virt(dma_handle), size, direction);
-}
-
-static void nios2_dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sg, int nelems,
-		enum dma_data_direction direction)
-{
-	int i;
-
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for_each_sg(sg, sg, nelems, i)
-		__dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
-}
-
-static void nios2_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sg, int nelems,
-		enum dma_data_direction direction)
-{
-	int i;
-
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for_each_sg(sg, sg, nelems, i)
-		__dma_sync_for_device(sg_virt(sg), sg->length, direction);
-
-}
-
-const struct dma_map_ops nios2_dma_ops = {
-	.alloc			= nios2_dma_alloc,
-	.free			= nios2_dma_free,
-	.map_page		= nios2_dma_map_page,
-	.unmap_page		= nios2_dma_unmap_page,
-	.map_sg			= nios2_dma_map_sg,
-	.unmap_sg		= nios2_dma_unmap_sg,
-	.sync_single_for_device	= nios2_dma_sync_single_for_device,
-	.sync_single_for_cpu	= nios2_dma_sync_single_for_cpu,
-	.sync_sg_for_cpu	= nios2_dma_sync_sg_for_cpu,
-	.sync_sg_for_device	= nios2_dma_sync_sg_for_device,
-};
-EXPORT_SYMBOL(nios2_dma_ops);
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 9ecad05bfc73..dfb6a79ba7ff 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -27,7 +27,6 @@ config OPENRISC
 	select GENERIC_STRNLEN_USER
 	select GENERIC_SMP_IDLE_THREAD
 	select MODULES_USE_ELF_RELA
-	select MULTI_IRQ_HANDLER
 	select HAVE_DEBUG_STACKOVERFLOW
 	select OR1K_PIC
 	select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1
@@ -36,6 +35,7 @@ config OPENRISC
 	select ARCH_USE_QUEUED_RWLOCKS
 	select OMPIC if SMP
 	select ARCH_WANT_FRAME_POINTERS
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config CPU_BIG_ENDIAN
 	def_bool y
@@ -69,9 +69,6 @@ config STACKTRACE_SUPPORT
 config LOCKDEP_SUPPORT
 	def_bool  y
 
-config MULTI_IRQ_HANDLER
-	def_bool y
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/openrisc/include/asm/atomic.h b/arch/openrisc/include/asm/atomic.h
index 146e1660f00e..b589fac39b92 100644
--- a/arch/openrisc/include/asm/atomic.h
+++ b/arch/openrisc/include/asm/atomic.h
@@ -100,7 +100,7 @@ ATOMIC_OP(xor)
  *
  * This is often used through atomic_inc_not_zero()
  */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int old, tmp;
 
@@ -119,7 +119,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return old;
 }
-#define __atomic_add_unless	__atomic_add_unless
+#define atomic_fetch_add_unless	atomic_fetch_add_unless
 
 #include <asm-generic/atomic.h>
 
diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
index d29f7db53906..f9cd43a39d72 100644
--- a/arch/openrisc/include/asm/cmpxchg.h
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -16,8 +16,9 @@
 #ifndef __ASM_OPENRISC_CMPXCHG_H
 #define __ASM_OPENRISC_CMPXCHG_H
 
+#include  <linux/bits.h>
+#include  <linux/compiler.h>
 #include  <linux/types.h>
-#include  <linux/bitops.h>
 
 #define __HAVE_ARCH_CMPXCHG 1
 
diff --git a/arch/openrisc/include/asm/irq.h b/arch/openrisc/include/asm/irq.h
index d9eee0a2b7b4..eb612b1865d2 100644
--- a/arch/openrisc/include/asm/irq.h
+++ b/arch/openrisc/include/asm/irq.h
@@ -24,6 +24,4 @@
 
 #define NO_IRQ		(-1)
 
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
 #endif /* __ASM_OPENRISC_IRQ_H__ */
diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h
index 3e1a46615120..8999b9226512 100644
--- a/arch/openrisc/include/asm/pgalloc.h
+++ b/arch/openrisc/include/asm/pgalloc.h
@@ -98,8 +98,12 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte)
 	__free_page(pte);
 }
 
+#define __pte_free_tlb(tlb, pte, addr)	\
+do {					\
+	pgtable_page_dtor(pte);		\
+	tlb_remove_page((tlb), (pte));	\
+} while (0)
 
-#define __pte_free_tlb(tlb, pte, addr) tlb_remove_page((tlb), (pte))
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
 #define check_pgt_cache()          do { } while (0)
diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S
index 690d55272ba6..0c826ad6e994 100644
--- a/arch/openrisc/kernel/entry.S
+++ b/arch/openrisc/kernel/entry.S
@@ -277,12 +277,6 @@ EXCEPTION_ENTRY(_data_page_fault_handler)
 	l.addi  r3,r1,0                    // pt_regs
 	/* r4 set be EXCEPTION_HANDLE */   // effective address of fault
 
-	/*
-	 * __PHX__: TODO
-	 *
-	 * all this can be written much simpler. look at
-	 * DTLB miss handler in the CONFIG_GUARD_PROTECTED_CORE part
-	 */
 #ifdef CONFIG_OPENRISC_NO_SPR_SR_DSX
 	l.lwz   r6,PT_PC(r3)               // address of an offending insn
 	l.lwz   r6,0(r6)                   // instruction that caused pf
@@ -314,7 +308,7 @@ EXCEPTION_ENTRY(_data_page_fault_handler)
 
 #else
 
-	l.lwz   r6,PT_SR(r3)               // SR
+	l.mfspr r6,r0,SPR_SR               // SR
 	l.andi  r6,r6,SPR_SR_DSX           // check for delay slot exception
 	l.sfne  r6,r0                      // exception happened in delay slot
 	l.bnf   7f
diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S
index fb02b2a1d6f2..9fc6b60140f0 100644
--- a/arch/openrisc/kernel/head.S
+++ b/arch/openrisc/kernel/head.S
@@ -210,8 +210,7 @@
  *	 r4  - EEAR     exception EA
  *	 r10 - current	pointing to current_thread_info struct
  *	 r12 - syscall  0, since we didn't come from syscall
- *	 r13 - temp	it actually contains new SR, not needed anymore
- *	 r31 - handler	address of the handler we'll jump to
+ *	 r30 - handler	address of the handler we'll jump to
  *
  *	 handler has to save remaining registers to the exception
  *	 ksp frame *before* tainting them!
@@ -244,6 +243,7 @@
 	/* r1 is KSP, r30 is __pa(KSP) */			;\
 	tophys  (r30,r1)					;\
 	l.sw    PT_GPR12(r30),r12				;\
+	/* r4 use for tmp before EA */				;\
 	l.mfspr r12,r0,SPR_EPCR_BASE				;\
 	l.sw    PT_PC(r30),r12					;\
 	l.mfspr r12,r0,SPR_ESR_BASE				;\
@@ -263,7 +263,10 @@
 	/* r12 == 1 if we come from syscall */			;\
 	CLEAR_GPR(r12)						;\
 	/* ----- turn on MMU ----- */				;\
-	l.ori	r30,r0,(EXCEPTION_SR)				;\
+	/* Carry DSX into exception SR */			;\
+	l.mfspr r30,r0,SPR_SR					;\
+	l.andi	r30,r30,SPR_SR_DSX				;\
+	l.ori	r30,r30,(EXCEPTION_SR)				;\
 	l.mtspr	r0,r30,SPR_ESR_BASE				;\
 	/* r30:	EA address of handler */			;\
 	LOAD_SYMBOL_2_GPR(r30,handler)				;\
diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c
index 35e478a93116..5f9445effaf8 100644
--- a/arch/openrisc/kernel/irq.c
+++ b/arch/openrisc/kernel/irq.c
@@ -41,13 +41,6 @@ void __init init_IRQ(void)
 	irqchip_init();
 }
 
-static void (*handle_arch_irq)(struct pt_regs *);
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	handle_arch_irq = handle_irq;
-}
-
 void __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	handle_arch_irq(regs);
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index fac246e6f37a..d8981cbb852a 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -300,7 +300,7 @@ static inline int in_delay_slot(struct pt_regs *regs)
 		return 0;
 	}
 #else
-	return regs->sr & SPR_SR_DSX;
+	return mfspr(SPR_SR) & SPR_SR_DSX;
 #endif
 }
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index c480770fabcd..e21751fb24aa 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -11,7 +11,6 @@ config PARISC
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_WANTS_UBSAN_NO_NULL
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select RTC_CLASS
 	select RTC_DRV_GENERIC
@@ -46,6 +45,7 @@ config PARISC
 	select HAVE_ARCH_HASH
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_REGS_AND_STACK_ACCESS_API
 	select GENERIC_SCHED_CLOCK
 	select HAVE_UNSTABLE_SCHED_CLOCK if SMP
 	select GENERIC_CLOCKEVENTS
@@ -188,6 +188,10 @@ config PA20
 config PA11
 	def_bool y
 	depends on PA7000 || PA7100LC || PA7200 || PA7300LC
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_NONCOHERENT_OPS
+	select DMA_NONCOHERENT_CACHE_SYNC
 
 config PREFETCH
 	def_bool y
@@ -195,7 +199,7 @@ config PREFETCH
 
 config MLONGCALLS
 	bool "Enable the -mlong-calls compiler option for big kernels"
-	def_bool y if (!MODULES)
+	default y
 	depends on PA8X00
 	help
 	  If you configure the kernel to include many drivers built-in instead
@@ -244,11 +248,11 @@ config PARISC_PAGE_SIZE_4KB
 
 config PARISC_PAGE_SIZE_16KB
 	bool "16KB"
-	depends on PA8X00
+	depends on PA8X00 && BROKEN
 
 config PARISC_PAGE_SIZE_64KB
 	bool "64KB"
-	depends on PA8X00
+	depends on PA8X00 && BROKEN
 
 endchoice
 
@@ -347,7 +351,7 @@ config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
 	depends on SMP
-	default "32"
+	default "4"
 
 endmenu
 
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 714284ea6cc2..5ce030266e7d 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -65,10 +65,6 @@ endif
 # kernel.
 cflags-y	+= -mdisable-fpregs
 
-# Without this, "ld -r" results in .text sections that are too big
-# (> 0x40000) for branches to reach stubs.
-cflags-y	+= -ffunction-sections
-
 # Use long jumps instead of long branches (needed if your linker fails to
 # link a too big vmlinux executable). Not enabled for building modules.
 ifdef CONFIG_MLONGCALLS
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 60e6f07b7e32..e9c6385ef0d1 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -36,6 +36,7 @@
 #define RP_OFFSET	16
 #define FRAME_SIZE	128
 #define CALLEE_REG_FRAME_SIZE	144
+#define REG_SZ		8
 #define ASM_ULONG_INSN	.dword
 #else	/* CONFIG_64BIT */
 #define LDREG	ldw
@@ -50,6 +51,7 @@
 #define RP_OFFSET	20
 #define FRAME_SIZE	64
 #define CALLEE_REG_FRAME_SIZE	128
+#define REG_SZ		4
 #define ASM_ULONG_INSN	.word
 #endif
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 88bae6676c9b..118953d41763 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -77,30 +77,6 @@ static __inline__ int atomic_read(const atomic_t *v)
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define ATOMIC_OP(op, c_op)						\
 static __inline__ void atomic_##op(int i, atomic_t *v)			\
 {									\
@@ -160,28 +136,6 @@ ATOMIC_OPS(xor, ^=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_inc(v)	(atomic_add(   1,(v)))
-#define atomic_dec(v)	(atomic_add(  -1,(v)))
-
-#define atomic_inc_return(v)	(atomic_add_return(   1,(v)))
-#define atomic_dec_return(v)	(atomic_add_return(  -1,(v)))
-
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v)	(atomic_dec_return(v) == 0)
-
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i),(v)) == 0)
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef CONFIG_64BIT
@@ -264,72 +218,11 @@ atomic64_read(const atomic64_t *v)
 	return READ_ONCE((v)->counter);
 }
 
-#define atomic64_inc(v)		(atomic64_add(   1,(v)))
-#define atomic64_dec(v)		(atomic64_add(  -1,(v)))
-
-#define atomic64_inc_return(v)		(atomic64_add_return(   1,(v)))
-#define atomic64_dec_return(v)		(atomic64_add_return(  -1,(v)))
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
-#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i),(v)) == 0)
-
 /* exported interface */
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-/*
- * atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
 #endif /* !CONFIG_64BIT */
 
 
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
new file mode 100644
index 000000000000..dbaaca84f27f
--- /dev/null
+++ b/arch/parisc/include/asm/barrier.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+/* The synchronize caches instruction executes as a nop on systems in
+   which all memory references are performed in order. */
+#define synchronize_caches() __asm__ __volatile__ ("sync" : : : "memory")
+
+#if defined(CONFIG_SMP)
+#define mb()		do { synchronize_caches(); } while (0)
+#define rmb()		mb()
+#define wmb()		mb()
+#define dma_rmb()	mb()
+#define dma_wmb()	mb()
+#else
+#define mb()		barrier()
+#define rmb()		barrier()
+#define wmb()		barrier()
+#define dma_rmb()	barrier()
+#define dma_wmb()	barrier()
+#endif
+
+#define __smp_mb()	mb()
+#define __smp_rmb()	mb()
+#define __smp_wmb()	mb()
+
+#include <asm-generic/barrier.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_BARRIER_H */
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index 01e1fc057c83..44a9f97194aa 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -21,11 +21,6 @@
 ** flush/purge and allocate "regular" cacheable pages for everything.
 */
 
-#ifdef CONFIG_PA11
-extern const struct dma_map_ops pcxl_dma_ops;
-extern const struct dma_map_ops pcx_dma_ops;
-#endif
-
 extern const struct dma_map_ops *hppa_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/arch/parisc/include/asm/linkage.h b/arch/parisc/include/asm/linkage.h
index 9a69bf6fc4b6..49f6f3d772cc 100644
--- a/arch/parisc/include/asm/linkage.h
+++ b/arch/parisc/include/asm/linkage.h
@@ -18,9 +18,9 @@
 #ifdef __ASSEMBLY__
 
 #define ENTRY(name) \
-	.export name !\
-	ALIGN !\
-name:
+	ALIGN	!\
+name:		ASM_NL\
+	.export name
 
 #ifdef CONFIG_64BIT
 #define ENDPROC(name) \
@@ -31,13 +31,18 @@ name:
 	END(name)
 #endif
 
-#define ENTRY_CFI(name) \
+#define ENTRY_CFI(name, ...) \
 	ENTRY(name)	ASM_NL\
+	.proc		ASM_NL\
+	.callinfo __VA_ARGS__	ASM_NL\
+	.entry		ASM_NL\
 	CFI_STARTPROC
 
 #define ENDPROC_CFI(name) \
-	ENDPROC(name)	ASM_NL\
-	CFI_ENDPROC
+	CFI_ENDPROC	ASM_NL\
+	.exit		ASM_NL\
+	.procend	ASM_NL\
+	ENDPROC(name)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/parisc/include/asm/ptrace.h b/arch/parisc/include/asm/ptrace.h
index 46da07670c2b..2a27b275ab09 100644
--- a/arch/parisc/include/asm/ptrace.h
+++ b/arch/parisc/include/asm/ptrace.h
@@ -25,4 +25,15 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->gr[20];
 }
 
+static inline void instruction_pointer_set(struct pt_regs *regs,
+						unsigned long val)
+{
+        regs->iaoq[0] = val;
+}
+
+/* Query offset/name of register from its name/offset */
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, ipsw))
+
 #endif
diff --git a/arch/parisc/include/asm/signal.h b/arch/parisc/include/asm/signal.h
index eeb5c8858663..715c96ba2ec8 100644
--- a/arch/parisc/include/asm/signal.h
+++ b/arch/parisc/include/asm/signal.h
@@ -21,14 +21,6 @@ typedef struct {
 	unsigned long sig[_NSIG_WORDS];
 } sigset_t;
 
-#ifndef __KERNEL__
-struct sigaction {
-	__sighandler_t sa_handler;
-	unsigned long sa_flags;
-	sigset_t sa_mask;		/* mask last for extensibility */
-};
-#endif
-
 #include <asm/sigcontext.h>
 
 #endif /* !__ASSEMBLY */
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 6f84b6acc86e..8a63515f03bf 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -20,7 +20,6 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 {
 	volatile unsigned int *a;
 
-	mb();
 	a = __ldcw_align(x);
 	while (__ldcw(a) == 0)
 		while (*a == 0)
@@ -30,17 +29,16 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 				local_irq_disable();
 			} else
 				cpu_relax();
-	mb();
 }
 #define arch_spin_lock_flags arch_spin_lock_flags
 
 static inline void arch_spin_unlock(arch_spinlock_t *x)
 {
 	volatile unsigned int *a;
-	mb();
+
 	a = __ldcw_align(x);
-	*a = 1;
 	mb();
+	*a = 1;
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *x)
@@ -48,10 +46,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *x)
 	volatile unsigned int *a;
 	int ret;
 
-	mb();
 	a = __ldcw_align(x);
         ret = __ldcw(a) != 0;
-	mb();
 
 	return ret;
 }
diff --git a/arch/parisc/include/asm/unwind.h b/arch/parisc/include/asm/unwind.h
index c73a3ee20226..f133b7efbebb 100644
--- a/arch/parisc/include/asm/unwind.h
+++ b/arch/parisc/include/asm/unwind.h
@@ -4,6 +4,9 @@
 
 #include <linux/list.h>
 
+/* Max number of levels to backtrace */
+#define MAX_UNWIND_ENTRIES	30
+
 /* From ABI specifications */
 struct unwind_table_entry {
 	unsigned int region_start;
diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index fc0df353ff0d..87245c584784 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -113,7 +113,6 @@
 #define	ELOOP		249	/* Too many symbolic links encountered */
 #define	ENOSYS		251	/* Function not implemented */
 
-#define ENOTSUP		252	/* Function not implemented (POSIX.4 / HPUX) */
 #define ECANCELLED	253	/* aio request was canceled before complete (POSIX.4 / HPUX) */
 #define ECANCELED	ECANCELLED	/* SuSv3 and Solaris wants one 'L' */
 
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 4872e77aa96b..dc77c5a51db7 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -364,8 +364,9 @@
 #define __NR_preadv2		(__NR_Linux + 347)
 #define __NR_pwritev2		(__NR_Linux + 348)
 #define __NR_statx		(__NR_Linux + 349)
+#define __NR_io_pgetevents	(__NR_Linux + 350)
 
-#define __NR_Linux_syscalls	(__NR_statx + 1)
+#define __NR_Linux_syscalls	(__NR_io_pgetevents + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index e0e1c9775c32..5eb979d04b90 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -154,17 +154,14 @@ int register_parisc_driver(struct parisc_driver *driver)
 {
 	/* FIXME: we need this because apparently the sti
 	 * driver can be registered twice */
-	if(driver->drv.name) {
-		printk(KERN_WARNING 
-		       "BUG: skipping previously registered driver %s\n",
-		       driver->name);
+	if (driver->drv.name) {
+		pr_warn("BUG: skipping previously registered driver %s\n",
+			driver->name);
 		return 1;
 	}
 
 	if (!driver->probe) {
-		printk(KERN_WARNING 
-		       "BUG: driver %s has no probe routine\n",
-		       driver->name);
+		pr_warn("BUG: driver %s has no probe routine\n", driver->name);
 		return 1;
 	}
 
@@ -491,12 +488,9 @@ alloc_pa_dev(unsigned long hpa, struct hardware_path *mod_path)
 
 	dev = create_parisc_device(mod_path);
 	if (dev->id.hw_type != HPHW_FAULTY) {
-		printk(KERN_ERR "Two devices have hardware path [%s].  "
-				"IODC data for second device: "
-				"%02x%02x%02x%02x%02x%02x\n"
-				"Rearranging GSC cards sometimes helps\n",
-			parisc_pathname(dev), iodc_data[0], iodc_data[1],
-			iodc_data[3], iodc_data[4], iodc_data[5], iodc_data[6]);
+		pr_err("Two devices have hardware path [%s].  IODC data for second device: %7phN\n"
+		       "Rearranging GSC cards sometimes helps\n",
+			parisc_pathname(dev), iodc_data);
 		return NULL;
 	}
 
@@ -528,8 +522,7 @@ alloc_pa_dev(unsigned long hpa, struct hardware_path *mod_path)
 	 * the keyboard controller
 	 */
 	if ((hpa & 0xfff) == 0 && insert_resource(&iomem_resource, &dev->hpa))
-		printk("Unable to claim HPA %lx for device %s\n",
-				hpa, name);
+		pr_warn("Unable to claim HPA %lx for device %s\n", hpa, name);
 
 	return dev;
 }
@@ -875,7 +868,7 @@ static void print_parisc_device(struct parisc_device *dev)
 	static int count;
 
 	print_pa_hwpath(dev, hw_path);
-	printk(KERN_INFO "%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
+	pr_info("%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
 		++count, dev->name, (void*) dev->hpa.start, hw_path, dev->id.hw_type,
 		dev->id.hversion_rev, dev->id.hversion, dev->id.sversion);
 
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index e95207c0565e..c7508f5717fb 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -482,6 +482,8 @@
 	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
 	or,COND(=)	%r0,\spc,%r0
+	sync
+	or,COND(=)	%r0,\spc,%r0
 	stw             \spc,0(\tmp)
 #endif
 	.endm
@@ -764,7 +766,6 @@ END(fault_vector_11)
 #endif
 	/* Fault vector is separately protected and *must* be on its own page */
 	.align		PAGE_SIZE
-ENTRY(end_fault_vector)
 
 	.import		handle_interruption,code
 	.import		do_cpu_irq_mask,code
@@ -776,7 +777,6 @@ ENTRY(end_fault_vector)
 	 */
 
 ENTRY_CFI(ret_from_kernel_thread)
-
 	/* Call schedule_tail first though */
 	BL	schedule_tail, %r2
 	nop
@@ -815,8 +815,9 @@ ENTRY_CFI(_switch_to)
 	LDREG	TASK_THREAD_INFO(%r25), %r25
 	bv	%r0(%r2)
 	mtctl   %r25,%cr30
+ENDPROC_CFI(_switch_to)
 
-_switch_to_ret:
+ENTRY_CFI(_switch_to_ret)
 	mtctl	%r0, %cr0		/* Needed for single stepping */
 	callee_rest
 	callee_rest_float
@@ -824,7 +825,7 @@ _switch_to_ret:
 	LDREG	-RP_OFFSET(%r30), %r2
 	bv	%r0(%r2)
 	copy	%r26, %r28
-ENDPROC_CFI(_switch_to)
+ENDPROC_CFI(_switch_to_ret)
 
 	/*
 	 * Common rfi return path for interruptions, kernel execve, and
@@ -885,12 +886,14 @@ ENTRY_CFI(syscall_exit_rfi)
 	STREG   %r19,PT_SR5(%r16)
 	STREG   %r19,PT_SR6(%r16)
 	STREG   %r19,PT_SR7(%r16)
+ENDPROC_CFI(syscall_exit_rfi)
 
-intr_return:
+ENTRY_CFI(intr_return)
 	/* check for reschedule */
 	mfctl   %cr30,%r1
 	LDREG   TI_FLAGS(%r1),%r19	/* sched.h: TIF_NEED_RESCHED */
 	bb,<,n	%r19,31-TIF_NEED_RESCHED,intr_do_resched /* forward */
+ENDPROC_CFI(intr_return)
 
 	.import do_notify_resume,code
 intr_check_sig:
@@ -1046,7 +1049,6 @@ intr_extint:
 
 	b	do_cpu_irq_mask
 	ldo	R%intr_return(%r2), %r2	/* return to intr_return, not here */
-ENDPROC_CFI(syscall_exit_rfi)
 
 
 	/* Generic interruptions (illegal insn, unaligned, page fault, etc) */
@@ -1997,12 +1999,9 @@ ENDPROC_CFI(syscall_exit)
 	.align L1_CACHE_BYTES
 	.globl mcount
 	.type  mcount, @function
-ENTRY(mcount)
+ENTRY_CFI(mcount, caller)
 _mcount:
 	.export _mcount,data
-	.proc
-	.callinfo caller,frame=0
-	.entry
 	/*
 	 * The 64bit mcount() function pointer needs 4 dwords, of which the
 	 * first two are free.  We optimize it here and put 2 instructions for
@@ -2024,18 +2023,13 @@ ftrace_stub:
 	.dword mcount
 	.dword 0 /* code in head.S puts value of global gp here */
 #endif
-	.exit
-	.procend
-ENDPROC(mcount)
+ENDPROC_CFI(mcount)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	.align 8
 	.globl return_to_handler
 	.type  return_to_handler, @function
-ENTRY_CFI(return_to_handler)
-	.proc
-	.callinfo caller,frame=FRAME_SIZE
-	.entry
+ENTRY_CFI(return_to_handler, caller,frame=FRAME_SIZE)
 	.export parisc_return_to_handler,data
 parisc_return_to_handler:
 	copy %r3,%r1
@@ -2074,8 +2068,6 @@ parisc_return_to_handler:
 	bv	%r0(%rp)
 #endif
 	LDREGM -FRAME_SIZE(%sp),%r3
-	.exit
-	.procend
 ENDPROC_CFI(return_to_handler)
 
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -2085,31 +2077,30 @@ ENDPROC_CFI(return_to_handler)
 #ifdef CONFIG_IRQSTACKS
 /* void call_on_stack(unsigned long param1, void *func,
 		      unsigned long new_stack) */
-ENTRY_CFI(call_on_stack)
+ENTRY_CFI(call_on_stack, FRAME=2*FRAME_SIZE,CALLS,SAVE_RP,SAVE_SP)
 	copy	%sp, %r1
 
 	/* Regarding the HPPA calling conventions for function pointers,
 	   we assume the PIC register is not changed across call.  For
 	   CONFIG_64BIT, the argument pointer is left to point at the
 	   argument region allocated for the call to call_on_stack. */
+
+	/* Switch to new stack.  We allocate two frames.  */
+	ldo	2*FRAME_SIZE(%arg2), %sp
 # ifdef CONFIG_64BIT
-	/* Switch to new stack.  We allocate two 128 byte frames.  */
-	ldo	256(%arg2), %sp
 	/* Save previous stack pointer and return pointer in frame marker */
-	STREG	%rp, -144(%sp)
+	STREG	%rp, -FRAME_SIZE-RP_OFFSET(%sp)
 	/* Calls always use function descriptor */
 	LDREG	16(%arg1), %arg1
 	bve,l	(%arg1), %rp
-	STREG	%r1, -136(%sp)
-	LDREG	-144(%sp), %rp
+	STREG	%r1, -FRAME_SIZE-REG_SZ(%sp)
+	LDREG	-FRAME_SIZE-RP_OFFSET(%sp), %rp
 	bve	(%rp)
-	LDREG	-136(%sp), %sp
+	LDREG	-FRAME_SIZE-REG_SZ(%sp), %sp
 # else
-	/* Switch to new stack.  We allocate two 64 byte frames.  */
-	ldo	128(%arg2), %sp
 	/* Save previous stack pointer and return pointer in frame marker */
-	STREG	%r1, -68(%sp)
-	STREG	%rp, -84(%sp)
+	STREG	%r1, -FRAME_SIZE-REG_SZ(%sp)
+	STREG	%rp, -FRAME_SIZE-RP_OFFSET(%sp)
 	/* Calls use function descriptor if PLABEL bit is set */
 	bb,>=,n	%arg1, 30, 1f
 	depwi	0,31,2, %arg1
@@ -2117,9 +2108,9 @@ ENTRY_CFI(call_on_stack)
 1:
 	be,l	0(%sr4,%arg1), %sr0, %r31
 	copy	%r31, %rp
-	LDREG	-84(%sp), %rp
+	LDREG	-FRAME_SIZE-RP_OFFSET(%sp), %rp
 	bv	(%rp)
-	LDREG	-68(%sp), %sp
+	LDREG	-FRAME_SIZE-REG_SZ(%sp), %sp
 # endif /* CONFIG_64BIT */
 ENDPROC_CFI(call_on_stack)
 #endif /* CONFIG_IRQSTACKS */
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 22e6374ece44..f33bf2d306d6 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -44,10 +44,6 @@
 	.align	16
 
 ENTRY_CFI(flush_tlb_all_local)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/*
 	 * The pitlbe and pdtlbe instructions should only be used to
 	 * flush the entire tlb. Also, there needs to be no intervening
@@ -189,18 +185,11 @@ fdtdone:
 
 2:      bv		%r0(%r2)
 	nop
-
-	.exit
-	.procend
 ENDPROC_CFI(flush_tlb_all_local)
 
 	.import cache_info,data
 
 ENTRY_CFI(flush_instruction_cache_local)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	load32		cache_info, %r1
 
 	/* Flush Instruction Cache */
@@ -256,18 +245,11 @@ fisync:
 	mtsm		%r22			/* restore I-bit */
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_instruction_cache_local)
 
 
 	.import cache_info, data
 ENTRY_CFI(flush_data_cache_local)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	load32		cache_info, %r1
 
 	/* Flush Data Cache */
@@ -324,9 +306,6 @@ fdsync:
 	mtsm		%r22			/* restore I-bit */
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_data_cache_local)
 
 /* Macros to serialize TLB purge operations on SMP.  */
@@ -353,6 +332,7 @@ ENDPROC_CFI(flush_data_cache_local)
 	.macro	tlb_unlock	la,flags,tmp
 #ifdef CONFIG_SMP
 	ldi		1,\tmp
+	sync
 	stw		\tmp,0(\la)
 	mtsm		\flags
 #endif
@@ -361,10 +341,6 @@ ENDPROC_CFI(flush_data_cache_local)
 /* Clear page using kernel mapping.  */
 
 ENTRY_CFI(clear_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 #ifdef CONFIG_64BIT
 
 	/* Unroll the loop.  */
@@ -423,18 +399,11 @@ ENTRY_CFI(clear_page_asm)
 #endif
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(clear_page_asm)
 
 /* Copy page using kernel mapping.  */
 
 ENTRY_CFI(copy_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 #ifdef CONFIG_64BIT
 	/* PA8x00 CPUs can consume 2 loads or 1 store per cycle.
 	 * Unroll the loop by hand and arrange insn appropriately.
@@ -541,9 +510,6 @@ ENTRY_CFI(copy_page_asm)
 #endif
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(copy_page_asm)
 
 /*
@@ -597,10 +563,6 @@ ENDPROC_CFI(copy_page_asm)
 	 */
 
 ENTRY_CFI(copy_user_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/* Convert virtual `to' and `from' addresses to physical addresses.
 	   Move `from' physical address to non shadowed register.  */
 	ldil		L%(__PAGE_OFFSET), %r1
@@ -749,16 +711,9 @@ ENTRY_CFI(copy_user_page_asm)
 
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(copy_user_page_asm)
 
 ENTRY_CFI(clear_user_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	tophys_r1	%r26
 
 	ldil		L%(TMPALIAS_MAP_START), %r28
@@ -835,16 +790,9 @@ ENTRY_CFI(clear_user_page_asm)
 
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(clear_user_page_asm)
 
 ENTRY_CFI(flush_dcache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%(TMPALIAS_MAP_START), %r28
 #ifdef CONFIG_64BIT
 #if (TMPALIAS_MAP_START >= 0x80000000)
@@ -902,16 +850,9 @@ ENTRY_CFI(flush_dcache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_dcache_page_asm)
 
 ENTRY_CFI(flush_icache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%(TMPALIAS_MAP_START), %r28
 #ifdef CONFIG_64BIT
 #if (TMPALIAS_MAP_START >= 0x80000000)
@@ -976,16 +917,9 @@ ENTRY_CFI(flush_icache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_icache_page_asm)
 
 ENTRY_CFI(flush_kernel_dcache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 
@@ -1019,16 +953,9 @@ ENTRY_CFI(flush_kernel_dcache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_kernel_dcache_page_asm)
 
 ENTRY_CFI(purge_kernel_dcache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 
@@ -1061,16 +988,9 @@ ENTRY_CFI(purge_kernel_dcache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(purge_kernel_dcache_page_asm)
 
 ENTRY_CFI(flush_user_dcache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1082,16 +1002,9 @@ ENTRY_CFI(flush_user_dcache_range_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_user_dcache_range_asm)
 
 ENTRY_CFI(flush_kernel_dcache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1104,16 +1017,9 @@ ENTRY_CFI(flush_kernel_dcache_range_asm)
 	syncdma
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_kernel_dcache_range_asm)
 
 ENTRY_CFI(purge_kernel_dcache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1126,16 +1032,9 @@ ENTRY_CFI(purge_kernel_dcache_range_asm)
 	syncdma
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(purge_kernel_dcache_range_asm)
 
 ENTRY_CFI(flush_user_icache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1147,16 +1046,9 @@ ENTRY_CFI(flush_user_icache_range_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_user_icache_range_asm)
 
 ENTRY_CFI(flush_kernel_icache_page)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 
@@ -1190,16 +1082,9 @@ ENTRY_CFI(flush_kernel_icache_page)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_kernel_icache_page)
 
 ENTRY_CFI(flush_kernel_icache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1211,8 +1096,6 @@ ENTRY_CFI(flush_kernel_icache_range_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-	.procend
 ENDPROC_CFI(flush_kernel_icache_range_asm)
 
 	__INIT
@@ -1222,10 +1105,6 @@ ENDPROC_CFI(flush_kernel_icache_range_asm)
 	 */
 	.align	256
 ENTRY_CFI(disable_sr_hashing_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/*
 	 * Switch to real mode
 	 */
@@ -1307,9 +1186,6 @@ srdis_done:
 
 2:      bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(disable_sr_hashing_asm)
 
 	.end
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 6df07ce4f3c2..04c48f1ef3fb 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -21,13 +21,12 @@
 #include <linux/init.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
-#include <linux/pci.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/types.h>
-#include <linux/scatterlist.h>
-#include <linux/export.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 
 #include <asm/cacheflush.h>
 #include <asm/dma.h>    /* for DMA_CHUNK_SIZE */
@@ -395,7 +394,7 @@ pcxl_dma_init(void)
 
 __initcall(pcxl_dma_init);
 
-static void *pa11_dma_alloc(struct device *dev, size_t size,
+static void *pcxl_dma_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
 {
 	unsigned long vaddr;
@@ -422,190 +421,60 @@ static void *pa11_dma_alloc(struct device *dev, size_t size,
 	return (void *)vaddr;
 }
 
-static void pa11_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
+static void *pcx_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
 {
-	int order;
-
-	order = get_order(size);
-	size = 1 << (order + PAGE_SHIFT);
-	unmap_uncached_pages((unsigned long)vaddr, size);
-	pcxl_free_range((unsigned long)vaddr, size);
-	free_pages((unsigned long)__va(dma_handle), order);
-}
+	void *addr;
 
-static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size,
-		enum dma_data_direction direction, unsigned long attrs)
-{
-	void *addr = page_address(page) + offset;
-	BUG_ON(direction == DMA_NONE);
+	if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
+		return NULL;
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		flush_kernel_dcache_range((unsigned long) addr, size);
+	addr = (void *)__get_free_pages(flag, get_order(size));
+	if (addr)
+		*dma_handle = (dma_addr_t)virt_to_phys(addr);
 
-	return virt_to_phys(addr);
+	return addr;
 }
 
-static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
-		size_t size, enum dma_data_direction direction,
-		unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
-	BUG_ON(direction == DMA_NONE);
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
 
-	if (direction == DMA_TO_DEVICE)
-		return;
-
-	/*
-	 * For PCI_DMA_FROMDEVICE this flush is not necessary for the
-	 * simple map/unmap case. However, it IS necessary if if
-	 * pci_dma_sync_single_* has been called and the buffer reused.
-	 */
-
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), size);
+	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl)
+		return pcxl_dma_alloc(dev, size, dma_handle, gfp, attrs);
+	else
+		return pcx_dma_alloc(dev, size, dma_handle, gfp, attrs);
 }
 
-static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
 {
-	int i;
-	struct scatterlist *sg;
-
-	BUG_ON(direction == DMA_NONE);
+	int order = get_order(size);
 
-	for_each_sg(sglist, sg, nents, i) {
-		unsigned long vaddr = (unsigned long)sg_virt(sg);
+	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
+		size = 1 << (order + PAGE_SHIFT);
+		unmap_uncached_pages((unsigned long)vaddr, size);
+		pcxl_free_range((unsigned long)vaddr, size);
 
-		sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr);
-		sg_dma_len(sg) = sg->length;
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		flush_kernel_dcache_range(vaddr, sg->length);
+		vaddr = __va(dma_handle);
 	}
-	return nents;
-}
-
-static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	BUG_ON(direction == DMA_NONE);
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	if (direction == DMA_TO_DEVICE)
-		return;
-
-	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
-	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_vmap_range(sg_virt(sg), sg->length);
-}
-
-static void pa11_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
-			size);
-}
-
-static void pa11_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
-			size);
+	free_pages((unsigned long)vaddr, get_order(size));
 }
 
-static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	int i;
-	struct scatterlist *sg;
-
-	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
-	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_vmap_range(sg_virt(sg), sg->length);
+	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
 
-static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	int i;
-	struct scatterlist *sg;
-
-	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
-	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_vmap_range(sg_virt(sg), sg->length);
+	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
 
-static void pa11_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction)
 {
 	flush_kernel_dcache_range((unsigned long)vaddr, size);
 }
-
-const struct dma_map_ops pcxl_dma_ops = {
-	.alloc =		pa11_dma_alloc,
-	.free =			pa11_dma_free,
-	.map_page =		pa11_dma_map_page,
-	.unmap_page =		pa11_dma_unmap_page,
-	.map_sg =		pa11_dma_map_sg,
-	.unmap_sg =		pa11_dma_unmap_sg,
-	.sync_single_for_cpu =	pa11_dma_sync_single_for_cpu,
-	.sync_single_for_device = pa11_dma_sync_single_for_device,
-	.sync_sg_for_cpu =	pa11_dma_sync_sg_for_cpu,
-	.sync_sg_for_device =	pa11_dma_sync_sg_for_device,
-	.cache_sync =		pa11_dma_cache_sync,
-};
-
-static void *pcx_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
-{
-	void *addr;
-
-	if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
-		return NULL;
-
-	addr = (void *)__get_free_pages(flag, get_order(size));
-	if (addr)
-		*dma_handle = (dma_addr_t)virt_to_phys(addr);
-
-	return addr;
-}
-
-static void pcx_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t iova, unsigned long attrs)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-	return;
-}
-
-const struct dma_map_ops pcx_dma_ops = {
-	.alloc =		pcx_dma_alloc,
-	.free =			pcx_dma_free,
-	.map_page =		pa11_dma_map_page,
-	.unmap_page =		pa11_dma_unmap_page,
-	.map_sg =		pa11_dma_map_sg,
-	.unmap_sg =		pa11_dma_unmap_sg,
-	.sync_single_for_cpu =	pa11_dma_sync_single_for_cpu,
-	.sync_single_for_device = pa11_dma_sync_single_for_device,
-	.sync_sg_for_cpu =	pa11_dma_sync_sg_for_cpu,
-	.sync_sg_for_device =	pa11_dma_sync_sg_for_device,
-	.cache_sync =		pa11_dma_cache_sync,
-};
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index b931745815e0..eb39e7e380d7 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -302,7 +302,7 @@ get_wchan(struct task_struct *p)
 		ip = info.ip;
 		if (!in_sched_functions(ip))
 			return ip;
-	} while (count++ < 16);
+	} while (count++ < MAX_UNWIND_ENTRIES);
 	return 0;
 }
 
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 7aa1d4d0d444..2582df1c529b 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -676,3 +676,103 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 #endif
 	return &user_parisc_native_view;
 }
+
+
+/* HAVE_REGS_AND_STACK_ACCESS_API feature */
+
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(r)    {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_INDEX(r,i) {.name = #r#i, .offset = offsetof(struct pt_regs, r[i])}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_INDEX(gr,0),
+	REG_OFFSET_INDEX(gr,1),
+	REG_OFFSET_INDEX(gr,2),
+	REG_OFFSET_INDEX(gr,3),
+	REG_OFFSET_INDEX(gr,4),
+	REG_OFFSET_INDEX(gr,5),
+	REG_OFFSET_INDEX(gr,6),
+	REG_OFFSET_INDEX(gr,7),
+	REG_OFFSET_INDEX(gr,8),
+	REG_OFFSET_INDEX(gr,9),
+	REG_OFFSET_INDEX(gr,10),
+	REG_OFFSET_INDEX(gr,11),
+	REG_OFFSET_INDEX(gr,12),
+	REG_OFFSET_INDEX(gr,13),
+	REG_OFFSET_INDEX(gr,14),
+	REG_OFFSET_INDEX(gr,15),
+	REG_OFFSET_INDEX(gr,16),
+	REG_OFFSET_INDEX(gr,17),
+	REG_OFFSET_INDEX(gr,18),
+	REG_OFFSET_INDEX(gr,19),
+	REG_OFFSET_INDEX(gr,20),
+	REG_OFFSET_INDEX(gr,21),
+	REG_OFFSET_INDEX(gr,22),
+	REG_OFFSET_INDEX(gr,23),
+	REG_OFFSET_INDEX(gr,24),
+	REG_OFFSET_INDEX(gr,25),
+	REG_OFFSET_INDEX(gr,26),
+	REG_OFFSET_INDEX(gr,27),
+	REG_OFFSET_INDEX(gr,28),
+	REG_OFFSET_INDEX(gr,29),
+	REG_OFFSET_INDEX(gr,30),
+	REG_OFFSET_INDEX(gr,31),
+	REG_OFFSET_INDEX(sr,0),
+	REG_OFFSET_INDEX(sr,1),
+	REG_OFFSET_INDEX(sr,2),
+	REG_OFFSET_INDEX(sr,3),
+	REG_OFFSET_INDEX(sr,4),
+	REG_OFFSET_INDEX(sr,5),
+	REG_OFFSET_INDEX(sr,6),
+	REG_OFFSET_INDEX(sr,7),
+	REG_OFFSET_INDEX(iasq,0),
+	REG_OFFSET_INDEX(iasq,1),
+	REG_OFFSET_INDEX(iaoq,0),
+	REG_OFFSET_INDEX(iaoq,1),
+	REG_OFFSET_NAME(cr27),
+	REG_OFFSET_NAME(ksp),
+	REG_OFFSET_NAME(kpc),
+	REG_OFFSET_NAME(sar),
+	REG_OFFSET_NAME(iir),
+	REG_OFFSET_NAME(isr),
+	REG_OFFSET_NAME(ior),
+	REG_OFFSET_NAME(ipsw),
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset:	the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (roff->offset == offset)
+			return roff->name;
+	return NULL;
+}
diff --git a/arch/parisc/kernel/real2.S b/arch/parisc/kernel/real2.S
index cc9963421a19..2b16d8d6598f 100644
--- a/arch/parisc/kernel/real2.S
+++ b/arch/parisc/kernel/real2.S
@@ -35,12 +35,6 @@ real32_stack:
 real64_stack:
 	.block	8192
 
-#ifdef CONFIG_64BIT
-#  define REG_SZ 8
-#else
-#  define REG_SZ 4
-#endif
-
 #define N_SAVED_REGS 9
 
 save_cr_space:
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 8d3a7b80ac42..4e87c35c22b7 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -97,14 +97,12 @@ void __init dma_ops_init(void)
 		panic(	"PA-RISC Linux currently only supports machines that conform to\n"
 			"the PA-RISC 1.1 or 2.0 architecture specification.\n");
 
-	case pcxs:
-	case pcxt:
-		hppa_dma_ops = &pcx_dma_ops;
-		break;
 	case pcxl2:
 		pa7300lc_init();
 	case pcxl: /* falls through */
-		hppa_dma_ops = &pcxl_dma_ops;
+	case pcxs:
+	case pcxt:
+		hppa_dma_ops = &dma_noncoherent_ops;
 		break;
 	default:
 		break;
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index e775f80ae28c..5f7e57fcaeef 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -629,11 +629,12 @@ cas_action:
 	stw	%r1, 4(%sr2,%r20)
 #endif
 	/* The load and store could fail */
-1:	ldw,ma	0(%r26), %r28
+1:	ldw	0(%r26), %r28
 	sub,<>	%r28, %r25, %r0
-2:	stw,ma	%r24, 0(%r26)
+2:	stw	%r24, 0(%r26)
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
 	stw	%r0, 4(%sr2,%r20)
@@ -647,6 +648,7 @@ cas_action:
 3:		
 	/* Error occurred on load or store */
 	/* Free lock */
+	sync
 	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	stw	%r0, 4(%sr2,%r20)
@@ -796,30 +798,30 @@ cas2_action:
 	ldo	1(%r0),%r28
 
 	/* 8bit CAS */
-13:	ldb,ma	0(%r26), %r29
+13:	ldb	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-14:	stb,ma	%r24, 0(%r26)
+14:	stb	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop
 
 	/* 16bit CAS */
-15:	ldh,ma	0(%r26), %r29
+15:	ldh	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-16:	sth,ma	%r24, 0(%r26)
+16:	sth	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop
 
 	/* 32bit CAS */
-17:	ldw,ma	0(%r26), %r29
+17:	ldw	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-18:	stw,ma	%r24, 0(%r26)
+18:	stw	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
@@ -827,10 +829,10 @@ cas2_action:
 
 	/* 64bit CAS */
 #ifdef CONFIG_64BIT
-19:	ldd,ma	0(%r26), %r29
+19:	ldd	0(%r26), %r29
 	sub,*=	%r29, %r25, %r0
 	b,n	cas2_end
-20:	std,ma	%r24, 0(%r26)
+20:	std	%r24, 0(%r26)
 	copy	%r0, %r28
 #else
 	/* Compare first word */
@@ -848,7 +850,8 @@ cas2_action:
 
 cas2_end:
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 	/* Enable interrupts */
 	ssm	PSW_SM_I, %r0
 	/* Return to userspace, set no error */
@@ -858,6 +861,7 @@ cas2_end:
 22:
 	/* Error occurred on load or store */
 	/* Free lock */
+	sync
 	stw	%r20, 0(%sr2,%r20)
 	ssm	PSW_SM_I, %r0
 	ldo	1(%r0),%r28
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 6308749359e4..fe3f2a49d2b1 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -445,6 +445,7 @@
 	ENTRY_COMP(preadv2)
 	ENTRY_COMP(pwritev2)
 	ENTRY_SAME(statx)
+	ENTRY_COMP(io_pgetevents)	/* 350 */
 
 
 .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 4309ad31a874..318815212518 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -172,7 +172,7 @@ static void do_show_stack(struct unwind_frame_info *info)
 	int i = 1;
 
 	printk(KERN_CRIT "Backtrace:\n");
-	while (i <= 16) {
+	while (i <= MAX_UNWIND_ENTRIES) {
 		if (unwind_once(info) < 0 || info->ip == 0)
 			break;
 
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index 143f90e2f9f3..5cdf13069dd9 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -13,7 +13,6 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/kallsyms.h>
 #include <linux/sort.h>
 
 #include <linux/uaccess.h>
@@ -25,7 +24,7 @@
 
 /* #define DEBUG 1 */
 #ifdef DEBUG
-#define dbg(x...) printk(x)
+#define dbg(x...) pr_debug(x)
 #else
 #define dbg(x...)
 #endif
@@ -117,7 +116,8 @@ unwind_table_init(struct unwind_table *table, const char *name,
 	for (; start <= end; start++) {
 		if (start < end && 
 		    start->region_end > (start+1)->region_start) {
-			printk("WARNING: Out of order unwind entry! %p and %p\n", start, start+1);
+			pr_warn("Out of order unwind entry! %px and %px\n",
+				start, start+1);
 		}
 
 		start->region_start += base_addr;
@@ -182,7 +182,7 @@ int __init unwind_init(void)
 	start = (long)&__start___unwind[0];
 	stop = (long)&__stop___unwind[0];
 
-	printk("unwind_init: start = 0x%lx, end = 0x%lx, entries = %lu\n", 
+	dbg("unwind_init: start = 0x%lx, end = 0x%lx, entries = %lu\n",
 	    start, stop,
 	    (stop - start) / sizeof(struct unwind_table_entry));
 
@@ -203,25 +203,60 @@ int __init unwind_init(void)
 	return 0;
 }
 
-#ifdef CONFIG_64BIT
-#define get_func_addr(fptr) fptr[2]
-#else
-#define get_func_addr(fptr) fptr[0]
-#endif
-
 static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int frame_size)
 {
-	extern void handle_interruption(int, struct pt_regs *);
-	static unsigned long *hi = (unsigned long *)&handle_interruption;
-
-	if (pc == get_func_addr(hi)) {
+	/*
+	 * We have to use void * instead of a function pointer, because
+	 * function pointers aren't a pointer to the function on 64-bit.
+	 * Make them const so the compiler knows they live in .text
+	 */
+	extern void * const handle_interruption;
+	extern void * const ret_from_kernel_thread;
+	extern void * const syscall_exit;
+	extern void * const intr_return;
+	extern void * const _switch_to_ret;
+#ifdef CONFIG_IRQSTACKS
+	extern void * const call_on_stack;
+#endif /* CONFIG_IRQSTACKS */
+
+	if (pc == (unsigned long) &handle_interruption) {
 		struct pt_regs *regs = (struct pt_regs *)(info->sp - frame_size - PT_SZ_ALGN);
 		dbg("Unwinding through handle_interruption()\n");
 		info->prev_sp = regs->gr[30];
 		info->prev_ip = regs->iaoq[0];
+		return 1;
+	}
+
+	if (pc == (unsigned long) &ret_from_kernel_thread ||
+	    pc == (unsigned long) &syscall_exit) {
+		info->prev_sp = info->prev_ip = 0;
+		return 1;
+	}
+
+	if (pc == (unsigned long) &intr_return) {
+		struct pt_regs *regs;
+
+		dbg("Found intr_return()\n");
+		regs = (struct pt_regs *)(info->sp - PT_SZ_ALGN);
+		info->prev_sp = regs->gr[30];
+		info->prev_ip = regs->iaoq[0];
+		info->rp = regs->gr[2];
+		return 1;
+	}
+
+	if (pc == (unsigned long) &_switch_to_ret) {
+		info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
+		info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
+		return 1;
+	}
 
+#ifdef CONFIG_IRQSTACKS
+	if (pc == (unsigned long) &call_on_stack) {
+		info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ);
+		info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET);
 		return 1;
 	}
+#endif
 
 	return 0;
 }
@@ -238,34 +273,8 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
 	if (e == NULL) {
 		unsigned long sp;
 
-		dbg("Cannot find unwind entry for 0x%lx; forced unwinding\n", info->ip);
-
-#ifdef CONFIG_KALLSYMS
-		/* Handle some frequent special cases.... */
-		{
-			char symname[KSYM_NAME_LEN];
-			char *modname;
-
-			kallsyms_lookup(info->ip, NULL, NULL, &modname,
-				symname);
-
-			dbg("info->ip = 0x%lx, name = %s\n", info->ip, symname);
-
-			if (strcmp(symname, "_switch_to_ret") == 0) {
-				info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
-				info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
-				dbg("_switch_to_ret @ %lx - setting "
-				    "prev_sp=%lx prev_ip=%lx\n", 
-				    info->ip, info->prev_sp, 
-				    info->prev_ip);
-				return;
-			} else if (strcmp(symname, "ret_from_kernel_thread") == 0 ||
-				   strcmp(symname, "syscall_exit") == 0) {
-				info->prev_ip = info->prev_sp = 0;
-				return;
-			}
-		}
-#endif
+		dbg("Cannot find unwind entry for %pS; forced unwinding\n",
+			(void *) info->ip);
 
 		/* Since we are doing the unwinding blind, we don't know if
 		   we are adjusting the stack correctly or extracting the rp
@@ -439,8 +448,8 @@ unsigned long return_address(unsigned int level)
 	/* initialize unwind info */
 	asm volatile ("copy %%r30, %0" : "=r"(sp));
 	memset(&r, 0, sizeof(struct pt_regs));
-	r.iaoq[0] = (unsigned long) current_text_addr();
-	r.gr[2] = (unsigned long) __builtin_return_address(0);
+	r.iaoq[0] = _THIS_IP_;
+	r.gr[2] = _RET_IP_;
 	r.gr[30] = sp;
 	unwind_frame_init(&info, current, &r);
 
diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S
index d4fe19806d57..b53fb6fedf06 100644
--- a/arch/parisc/lib/lusercopy.S
+++ b/arch/parisc/lib/lusercopy.S
@@ -64,9 +64,6 @@
 	 */
 
 ENTRY_CFI(lclear_user)
-	.proc
-	.callinfo NO_CALLS
-	.entry
 	comib,=,n   0,%r25,$lclu_done
 	get_sr
 $lclu_loop:
@@ -81,13 +78,9 @@ $lclu_done:
 	ldo         1(%r25),%r25
 
 	ASM_EXCEPTIONTABLE_ENTRY(1b,2b)
-
-	.exit
 ENDPROC_CFI(lclear_user)
 
 
-	.procend
-
 	/*
 	 * long lstrnlen_user(char *s, long n)
 	 *
@@ -97,9 +90,6 @@ ENDPROC_CFI(lclear_user)
 	 */
 
 ENTRY_CFI(lstrnlen_user)
-	.proc
-	.callinfo NO_CALLS
-	.entry
 	comib,=     0,%r25,$lslen_nzero
 	copy	    %r26,%r24
 	get_sr
@@ -111,7 +101,6 @@ $lslen_loop:
 $lslen_done:
 	bv          %r0(%r2)
 	sub	    %r26,%r24,%r28
-	.exit
 
 $lslen_nzero:
 	b           $lslen_done
@@ -125,9 +114,6 @@ $lslen_nzero:
 
 ENDPROC_CFI(lstrnlen_user)
 
-	.procend
-
-
 
 /*
  * unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
@@ -186,10 +172,6 @@ ENDPROC_CFI(lstrnlen_user)
 	save_len = r31
 
 ENTRY_CFI(pa_memcpy)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/* Last destination address */
 	add	dst,len,end
 
@@ -439,9 +421,6 @@ ENTRY_CFI(pa_memcpy)
 	b	.Lcopy_done
 10:	stw,ma	t1,4(dstspc,dst)
 	ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
-
-	.exit
 ENDPROC_CFI(pa_memcpy)
-	.procend
 
 	.end
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 2607d2d33405..74842d28a7a1 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -19,7 +19,6 @@
 #include <linux/gfp.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/pci.h>		/* for hppa_dma_ops and pcxl_dma_ops */
 #include <linux/initrd.h>
 #include <linux/swap.h>
 #include <linux/unistd.h>
@@ -616,17 +615,13 @@ void __init mem_init(void)
 	free_all_bootmem();
 
 #ifdef CONFIG_PA11
-	if (hppa_dma_ops == &pcxl_dma_ops) {
+	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
 		pcxl_dma_start = (unsigned long)SET_MAP_OFFSET(MAP_START);
 		parisc_vmalloc_start = SET_MAP_OFFSET(pcxl_dma_start
 						+ PCXL_DMA_MAP_SIZE);
-	} else {
-		pcxl_dma_start = 0;
-		parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
-	}
-#else
-	parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
+	} else
 #endif
+		parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
 
 	mem_init_print_info(NULL);
 
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 2ea575cb3401..fb96206de317 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -243,6 +243,7 @@ endif
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
+cpu-as-$(CONFIG_E500)		+= -Wa,-me500
 cpu-as-$(CONFIG_PPC_BOOK3S_64)	+= -Wa,-mpower4
 cpu-as-$(CONFIG_PPC_E500MC)	+= $(call as-option,-Wa$(comma)-me500mc)
 
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 682b3e6a1e21..963abf8bf1c0 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -18,18 +18,11 @@
  * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
  * on the platform without lwsync.
  */
-#define __atomic_op_acquire(op, args...)				\
-({									\
-	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory");	\
-	__ret;								\
-})
-
-#define __atomic_op_release(op, args...)				\
-({									\
-	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory");	\
-	op##_relaxed(args);						\
-})
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory")
 
 static __inline__ int atomic_read(const atomic_t *v)
 {
@@ -129,8 +122,6 @@ ATOMIC_OPS(xor, xor)
 #undef ATOMIC_OP_RETURN_RELAXED
 #undef ATOMIC_OP
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
 static __inline__ void atomic_inc(atomic_t *v)
 {
 	int t;
@@ -145,6 +136,7 @@ static __inline__ void atomic_inc(atomic_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic_inc atomic_inc
 
 static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 {
@@ -163,16 +155,6 @@ static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 	return t;
 }
 
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
 static __inline__ void atomic_dec(atomic_t *v)
 {
 	int t;
@@ -187,6 +169,7 @@ static __inline__ void atomic_dec(atomic_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic_dec atomic_dec
 
 static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 {
@@ -218,7 +201,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -226,13 +209,13 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%1		# __atomic_add_unless\n\
+"1:	lwarx	%0,0,%1		# atomic_fetch_add_unless\n\
 	cmpw	0,%0,%3 \n\
 	beq	2f \n\
 	add	%0,%2,%0 \n"
@@ -248,6 +231,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return t;
 }
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 /**
  * atomic_inc_not_zero - increment unless the number is zero
@@ -280,9 +264,6 @@ static __inline__ int atomic_inc_not_zero(atomic_t *v)
 }
 #define atomic_inc_not_zero(v) atomic_inc_not_zero((v))
 
-#define atomic_sub_and_test(a, v)	(atomic_sub_return((a), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return((v)) == 0)
-
 /*
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1, even if
@@ -412,8 +393,6 @@ ATOMIC64_OPS(xor, xor)
 #undef ATOMIC64_OP_RETURN_RELAXED
 #undef ATOMIC64_OP
 
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
 static __inline__ void atomic64_inc(atomic64_t *v)
 {
 	long t;
@@ -427,6 +406,7 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic64_inc atomic64_inc
 
 static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 {
@@ -444,16 +424,6 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 	return t;
 }
 
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
 static __inline__ void atomic64_dec(atomic64_t *v)
 {
 	long t;
@@ -467,6 +437,7 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic64_dec atomic64_dec
 
 static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 {
@@ -487,9 +458,6 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
 #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
 
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-
 /*
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1.
@@ -513,6 +481,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 
 	return t;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_cmpxchg_relaxed(v, o, n) \
@@ -524,7 +493,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -532,13 +501,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
 	long t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
-"1:	ldarx	%0,0,%1		# __atomic_add_unless\n\
+"1:	ldarx	%0,0,%1		# atomic64_fetch_add_unless\n\
 	cmpd	0,%0,%3 \n\
 	beq	2f \n\
 	add	%0,%2,%0 \n"
@@ -551,8 +520,9 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 	: "r" (&v->counter), "r" (a), "r" (u)
 	: "cc", "memory");
 
-	return t != u;
+	return t;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 /**
  * atomic_inc64_not_zero - increment unless the number is zero
@@ -582,6 +552,7 @@ static __inline__ int atomic64_inc_not_zero(atomic64_t *v)
 
 	return t1 != 0;
 }
+#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v))
 
 #endif /* __powerpc64__ */
 
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index e4633803fe43..82e44b1a00ae 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -138,7 +138,6 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	pgtable_page_dtor(table);
 	pgtable_free_tlb(tlb, page_address(table), 0);
 }
 #endif /* _ASM_POWERPC_BOOK3S_32_PGALLOC_H */
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 8e7b09703ca4..27d6e3c8fde9 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -52,6 +52,7 @@ struct arch_hw_breakpoint {
 #include <asm/reg.h>
 #include <asm/debug.h>
 
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 struct perf_sample_data;
@@ -60,8 +61,10 @@ struct perf_sample_data;
 
 extern int hw_breakpoint_slots(int type);
 extern int arch_bp_generic_fields(int type, int *gen_bp_type);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 						unsigned long val, void *data);
 int arch_install_hw_breakpoint(struct perf_event *bp);
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 9f3be5c8a4a3..785c464b6588 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -88,7 +88,6 @@ struct prev_kprobe {
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_saved_msr;
-	struct pt_regs jprobe_saved_regs;
 	struct prev_kprobe prev_kprobe;
 };
 
@@ -103,17 +102,6 @@ extern int kprobe_exceptions_notify(struct notifier_block *self,
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_handler(struct pt_regs *regs);
 extern int kprobe_post_handler(struct pt_regs *regs);
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int __is_active_jprobe(unsigned long addr);
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			   struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				  struct kprobe_ctlblk *kcb)
-{
-	return 0;
-}
-#endif
 #else
 static inline int kprobe_handler(struct pt_regs *regs) { return 0; }
 static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; }
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 896efa559996..b2f89b621b15 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif
@@ -143,24 +143,33 @@ static inline void mm_context_remove_copro(struct mm_struct *mm)
 {
 	int c;
 
-	c = atomic_dec_if_positive(&mm->context.copros);
-
-	/* Detect imbalance between add and remove */
-	WARN_ON(c < 0);
-
 	/*
-	 * Need to broadcast a global flush of the full mm before
-	 * decrementing active_cpus count, as the next TLBI may be
-	 * local and the nMMU and/or PSL need to be cleaned up.
-	 * Should be rare enough so that it's acceptable.
+	 * When removing the last copro, we need to broadcast a global
+	 * flush of the full mm, as the next TLBI may be local and the
+	 * nMMU and/or PSL need to be cleaned up.
+	 *
+	 * Both the 'copros' and 'active_cpus' counts are looked at in
+	 * flush_all_mm() to determine the scope (local/global) of the
+	 * TLBIs, so we need to flush first before decrementing
+	 * 'copros'. If this API is used by several callers for the
+	 * same context, it can lead to over-flushing. It's hopefully
+	 * not common enough to be a problem.
 	 *
 	 * Skip on hash, as we don't know how to do the proper flush
 	 * for the time being. Invalidations will remain global if
-	 * used on hash.
+	 * used on hash. Note that we can't drop 'copros' either, as
+	 * it could make some invalidations local with no flush
+	 * in-between.
 	 */
-	if (c == 0 && radix_enabled()) {
+	if (radix_enabled()) {
 		flush_all_mm(mm);
-		dec_mm_active_cpus(mm);
+
+		c = atomic_dec_if_positive(&mm->context.copros);
+		/* Detect imbalance between add and remove */
+		WARN_ON(c < 0);
+
+		if (c == 0)
+			dec_mm_active_cpus(mm);
 	}
 }
 #else
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 9de40eb614da..8825953c225b 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -140,7 +140,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
 	tlb_flush_pgtable(tlb, address);
-	pgtable_page_dtor(table);
 	pgtable_free_tlb(tlb, page_address(table), 0);
 }
 #endif /* _ASM_POWERPC_PGALLOC_32_H */
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index cfcf6a874cfa..01b5171ea189 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -393,3 +393,4 @@ SYSCALL(pkey_alloc)
 SYSCALL(pkey_free)
 SYSCALL(pkey_mprotect)
 SYSCALL(rseq)
+COMPAT_SYS(io_pgetevents)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 1e9708632dce..c19379f0a32e 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		388
+#define NR_syscalls		389
 
 #define __NR__exit __NR_exit
 
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index ac5ba55066dd..985534d0b448 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -399,5 +399,6 @@
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
 #define __NR_rseq		387
+#define __NR_io_pgetevents	388
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 80547dad37da..fec8a6773119 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -119,11 +119,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp)
 /*
  * Check for virtual address in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	return is_kernel_addr(info->address);
+	return is_kernel_addr(hw->address);
 }
 
 int arch_bp_generic_fields(int type, int *gen_bp_type)
@@ -141,30 +139,31 @@ int arch_bp_generic_fields(int type, int *gen_bp_type)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
 	int ret = -EINVAL, length_max;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
 	if (!bp)
 		return ret;
 
-	info->type = HW_BRK_TYPE_TRANSLATE;
-	if (bp->attr.bp_type & HW_BREAKPOINT_R)
-		info->type |= HW_BRK_TYPE_READ;
-	if (bp->attr.bp_type & HW_BREAKPOINT_W)
-		info->type |= HW_BRK_TYPE_WRITE;
-	if (info->type == HW_BRK_TYPE_TRANSLATE)
+	hw->type = HW_BRK_TYPE_TRANSLATE;
+	if (attr->bp_type & HW_BREAKPOINT_R)
+		hw->type |= HW_BRK_TYPE_READ;
+	if (attr->bp_type & HW_BREAKPOINT_W)
+		hw->type |= HW_BRK_TYPE_WRITE;
+	if (hw->type == HW_BRK_TYPE_TRANSLATE)
 		/* must set alteast read or write */
 		return ret;
-	if (!(bp->attr.exclude_user))
-		info->type |= HW_BRK_TYPE_USER;
-	if (!(bp->attr.exclude_kernel))
-		info->type |= HW_BRK_TYPE_KERNEL;
-	if (!(bp->attr.exclude_hv))
-		info->type |= HW_BRK_TYPE_HYP;
-	info->address = bp->attr.bp_addr;
-	info->len = bp->attr.bp_len;
+	if (!attr->exclude_user)
+		hw->type |= HW_BRK_TYPE_USER;
+	if (!attr->exclude_kernel)
+		hw->type |= HW_BRK_TYPE_KERNEL;
+	if (!attr->exclude_hv)
+		hw->type |= HW_BRK_TYPE_HYP;
+	hw->address = attr->bp_addr;
+	hw->len = attr->bp_len;
 
 	/*
 	 * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8)
@@ -178,12 +177,12 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	if (cpu_has_feature(CPU_FTR_DAWR)) {
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
-		if ((bp->attr.bp_addr >> 9) !=
-		    ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9))
+		if ((attr->bp_addr >> 9) !=
+		    ((attr->bp_addr + attr->bp_len - 1) >> 9))
 			return -EINVAL;
 	}
-	if (info->len >
-	    (length_max - (info->address & HW_BREAKPOINT_ALIGN)))
+	if (hw->len >
+	    (length_max - (hw->address & HW_BREAKPOINT_ALIGN)))
 		return -EINVAL;
 	return 0;
 }
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index e734f6e45abc..689306118b48 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -144,7 +144,9 @@ power9_restore_additional_sprs:
 	mtspr	SPRN_MMCR1, r4
 
 	ld	r3, STOP_MMCR2(r13)
+	ld	r4, PACA_SPRG_VDSO(r13)
 	mtspr	SPRN_MMCR2, r3
+	mtspr	SPRN_SPRG3, r4
 	blr
 
 /*
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 7a1f99f1b47f..e4a49c051325 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -25,50 +25,6 @@
 #include <linux/preempt.h>
 #include <linux/ftrace.h>
 
-/*
- * This is called from ftrace code after invoking registered handlers to
- * disambiguate regs->nip changes done by jprobes and livepatch. We check if
- * there is an active jprobe at the provided address (mcount location).
- */
-int __is_active_jprobe(unsigned long addr)
-{
-	if (!preemptible()) {
-		struct kprobe *p = raw_cpu_read(current_kprobe);
-		return (p && (unsigned long)p->addr == addr) ? 1 : 0;
-	}
-
-	return 0;
-}
-
-static nokprobe_inline
-int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		      struct kprobe_ctlblk *kcb, unsigned long orig_nip)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->nip)
-	 * as if there is a nop
-	 */
-	regs->nip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-	if (orig_nip)
-		regs->nip = orig_nip;
-	return 1;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		    struct kprobe_ctlblk *kcb)
-{
-	if (kprobe_ftrace(p))
-		return __skip_singlestep(p, regs, kcb, 0);
-	else
-		return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
 /* Ftrace callback handler for kprobes */
 void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 			   struct ftrace_ops *ops, struct pt_regs *regs)
@@ -76,18 +32,14 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
-	preempt_disable();
-
 	p = get_kprobe((kprobe_opcode_t *)nip);
 	if (unlikely(!p) || kprobe_disabled(p))
-		goto end;
+		return;
 
 	kcb = get_kprobe_ctlblk();
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(p);
 	} else {
-		unsigned long orig_nip = regs->nip;
-
 		/*
 		 * On powerpc, NIP is *before* this instruction for the
 		 * pre handler
@@ -96,19 +48,23 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (!p->pre_handler || !p->pre_handler(p, regs))
-			__skip_singlestep(p, regs, kcb, orig_nip);
-		else {
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			/*
-			 * If pre_handler returns !0, it sets regs->nip and
-			 * resets current kprobe. In this case, we should not
-			 * re-enable preemption.
+			 * Emulate singlestep (and also recover regs->nip)
+			 * as if there is a nop
 			 */
-			return;
+			regs->nip += MCOUNT_INSN_SIZE;
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
 		}
+		/*
+		 * If pre_handler returns !0, it changes regs->nip. We have to
+		 * skip emulating post_handler.
+		 */
+		__this_cpu_write(current_kprobe, NULL);
 	}
-end:
-	preempt_enable_no_resched();
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index e4c5bf33970b..5c60bb0f927f 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -317,25 +317,17 @@ int kprobe_handler(struct pt_regs *regs)
 			}
 			prepare_singlestep(p, regs);
 			return 1;
-		} else {
-			if (*addr != BREAKPOINT_INSTRUCTION) {
-				/* If trap variant, then it belongs not to us */
-				kprobe_opcode_t cur_insn = *addr;
-				if (is_trap(cur_insn))
-		       			goto no_kprobe;
-				/* The breakpoint instruction was removed by
-				 * another cpu right after we hit, no further
-				 * handling of this interrupt is appropriate
-				 */
-				ret = 1;
+		} else if (*addr != BREAKPOINT_INSTRUCTION) {
+			/* If trap variant, then it belongs not to us */
+			kprobe_opcode_t cur_insn = *addr;
+
+			if (is_trap(cur_insn))
 				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				if (!skip_singlestep(p, regs, kcb))
-					goto ss_probe;
-				ret = 1;
-			}
+			/* The breakpoint instruction was removed by
+			 * another cpu right after we hit, no further
+			 * handling of this interrupt is appropriate
+			 */
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -350,7 +342,7 @@ int kprobe_handler(struct pt_regs *regs)
 			 */
 			kprobe_opcode_t cur_insn = *addr;
 			if (is_trap(cur_insn))
-		       		goto no_kprobe;
+				goto no_kprobe;
 			/*
 			 * The breakpoint instruction was removed right
 			 * after we hit it.  Another cpu has removed
@@ -366,11 +358,13 @@ int kprobe_handler(struct pt_regs *regs)
 
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 	set_current_kprobe(p, regs, kcb);
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/* handler has already set things up, so skip ss setup */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		/* handler changed execution path, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 	if (p->ainsn.boostable >= 0) {
 		ret = try_to_emulate(p, regs);
 
@@ -611,60 +605,6 @@ unsigned long arch_deref_entry_point(void *entry)
 }
 NOKPROBE_SYMBOL(arch_deref_entry_point);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
-	/* setup return addr to the jprobe handler routine */
-	regs->nip = arch_deref_entry_point(jp->entry);
-#ifdef PPC64_ELF_ABI_v2
-	regs->gpr[12] = (unsigned long)jp->entry;
-#elif defined(PPC64_ELF_ABI_v1)
-	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
-#endif
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void __used jprobe_return(void)
-{
-	asm volatile("jprobe_return_trap:\n"
-		     "trap\n"
-		     ::: "memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (regs->nip != ppc_kallsyms_lookup_name("jprobe_return_trap")) {
-		pr_debug("longjmp_break_handler NIP (0x%lx) does not match jprobe_return_trap (0x%lx)\n",
-				regs->nip, ppc_kallsyms_lookup_name("jprobe_return_trap"));
-		return 0;
-	}
-
-	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
-	/* It's OK to start function graph tracing again */
-	unpause_graph_tracing();
-	preempt_enable_no_resched();
-	return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 static struct kprobe trampoline_p = {
 	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index fe9733ffffaa..471aac313b89 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -42,6 +42,8 @@
 #include <asm/ppc-pci.h>
 #include <asm/eeh.h>
 
+#include "../../../drivers/pci/pci.h"
+
 /* hose_spinlock protects accesses to the the phb_bitmap. */
 static DEFINE_SPINLOCK(hose_spinlock);
 LIST_HEAD(hose_list);
@@ -1014,7 +1016,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus)
 		/* Cardbus can call us to add new devices to a bus, so ignore
 		 * those who are already fully discovered
 		 */
-		if (dev->is_added)
+		if (pci_dev_is_added(dev))
 			continue;
 
 		pcibios_setup_device(dev);
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 4f861055a852..d63b488d34d7 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -285,9 +285,6 @@ pci_bus_to_hose(int bus)
  * Note that the returned IO or memory base is a physical address
  */
 
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
 SYSCALL_DEFINE3(pciconfig_iobase, long, which,
 		unsigned long, bus, unsigned long, devfn)
 {
@@ -313,4 +310,3 @@ SYSCALL_DEFINE3(pciconfig_iobase, long, which,
 
 	return result;
 }
-#pragma GCC diagnostic pop
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 812171c09f42..dff28f903512 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -203,9 +203,6 @@ void pcibios_setup_phb_io_space(struct pci_controller *hose)
 #define IOBASE_ISA_IO		3
 #define IOBASE_ISA_MEM		4
 
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
 SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, in_bus,
 			  unsigned long, in_devfn)
 {
@@ -259,7 +256,6 @@ SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, in_bus,
 
 	return -EOPNOTSUPP;
 }
-#pragma GCC diagnostic pop
 
 #ifdef CONFIG_NUMA
 int pcibus_to_node(struct pci_bus *bus)
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 7fb9f83dcde8..8afd146bc9c7 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1051,9 +1051,6 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
 }
 
 /* We assume to be passed big endian arguments */
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
 SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 {
 	struct rtas_args args;
@@ -1140,7 +1137,6 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 
 	return 0;
 }
-#pragma GCC diagnostic pop
 
 /*
  * Call early during boot, before mem init, to retrieve the RTAS
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 5eedbb282d42..e6474a45cef5 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1038,9 +1038,6 @@ static int do_setcontext_tm(struct ucontext __user *ucp,
 }
 #endif
 
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
 #ifdef CONFIG_PPC64
 COMPAT_SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 		       struct ucontext __user *, new_ctx, int, ctx_size)
@@ -1134,7 +1131,6 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 	set_thread_flag(TIF_RESTOREALL);
 	return 0;
 }
-#pragma GCC diagnostic pop
 
 #ifdef CONFIG_PPC64
 COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
@@ -1231,9 +1227,6 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	return 0;
 }
 
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
 #ifdef CONFIG_PPC32
 SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx,
 			 int, ndbg, struct sig_dbg_op __user *, dbg)
@@ -1337,7 +1330,6 @@ SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx,
 	return 0;
 }
 #endif
-#pragma GCC diagnostic pop
 
 /*
  * OK, we're invoking a handler
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index d42b60020389..83d51bf586c7 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -625,9 +625,6 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp)
 /*
  * Handle {get,set,swap}_context operations
  */
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
 SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 		struct ucontext __user *, new_ctx, long, ctx_size)
 {
@@ -693,7 +690,6 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 	set_thread_flag(TIF_RESTOREALL);
 	return 0;
 }
-#pragma GCC diagnostic pop
 
 
 /*
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index 083fa06962fd..466216506eb2 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -62,9 +62,6 @@ out:
 	return ret;
 }
 
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
 SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len,
 		unsigned long, prot, unsigned long, flags,
 		unsigned long, fd, unsigned long, pgoff)
@@ -78,7 +75,6 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len,
 {
 	return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT);
 }
-#pragma GCC diagnostic pop
 
 #ifdef CONFIG_PPC32
 /*
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 9a5b5a513604..32476a6e4e9c 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -104,39 +104,13 @@ ftrace_regs_call:
 	bl	ftrace_stub
 	nop
 
-	/* Load the possibly modified NIP */
-	ld	r15, _NIP(r1)
-
+	/* Load ctr with the possibly modified NIP */
+	ld	r3, _NIP(r1)
+	mtctr	r3
 #ifdef CONFIG_LIVEPATCH
-	cmpd	r14, r15	/* has NIP been altered? */
+	cmpd	r14, r3		/* has NIP been altered? */
 #endif
 
-#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
-	/* NIP has not been altered, skip over further checks */
-	beq	1f
-
-	/* Check if there is an active jprobe on us */
-	subi	r3, r14, 4
-	bl	__is_active_jprobe
-	nop
-
-	/*
-	 * If r3 == 1, then this is a kprobe/jprobe.
-	 * else, this is livepatched function.
-	 *
-	 * The conditional branch for livepatch_handler below will use the
-	 * result of this comparison. For kprobe/jprobe, we just need to branch to
-	 * the new NIP, not call livepatch_handler. The branch below is bne, so we
-	 * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
-	 * CR0[EQ] = (r3 == 1).
-	 */
-	cmpdi	r3, 1
-1:
-#endif
-
-	/* Load CTR with the possibly modified NIP */
-	mtctr	r15
-
 	/* Restore gprs */
 	REST_GPR(0,r1)
 	REST_10GPRS(2,r1)
@@ -154,10 +128,7 @@ ftrace_regs_call:
 	addi r1, r1, SWITCH_FRAME_SIZE
 
 #ifdef CONFIG_LIVEPATCH
-        /*
-	 * Based on the cmpd or cmpdi above, if the NIP was altered and we're
-	 * not on a kprobe/jprobe, then handle livepatch.
-	 */
+        /* Based on the cmpd above, if the NIP was altered handle livepatch */
 	bne-	livepatch_handler
 #endif
 
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index d066e37551ec..8c456fa691a5 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa)))
 		return H_HARDWARE;
 
 	if (mm_iommu_mapped_inc(mem))
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 925fc316a104..5b298f5a1a14 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (!mem)
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
+			&hpa)))
 		return H_HARDWARE;
 
 	pua = (void *) vmalloc_to_phys(pua);
@@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
 		if (mem)
-			prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+			prereg = mm_iommu_ua_to_hpa_rm(mem, ua,
+					IOMMU_PAGE_SHIFT_4K, &tces) == 0;
 	}
 
 	if (!prereg) {
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de686b340f4a..ee4a8854985e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -216,7 +216,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
 	if (swq_has_sleeper(wqp)) {
-		swake_up(wqp);
+		swake_up_one(wqp);
 		++vcpu->stat.halt_wakeup;
 	}
 
@@ -3188,7 +3188,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 		}
 	}
 
-	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 
 	if (kvmppc_vcore_check_block(vc)) {
 		finish_swait(&vc->wq, &wait);
@@ -3311,7 +3311,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			swake_up(&vc->wq);
+			swake_up_one(&vc->wq);
 		}
 
 	}
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index abb43646927a..a4ca57612558 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -19,6 +19,7 @@
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <asm/mmu_context.h>
+#include <asm/pte-walk.h>
 
 static DEFINE_MUTEX(mem_list_mutex);
 
@@ -27,6 +28,7 @@ struct mm_iommu_table_group_mem_t {
 	struct rcu_head rcu;
 	unsigned long used;
 	atomic64_t mapped;
+	unsigned int pageshift;
 	u64 ua;			/* userspace address */
 	u64 entries;		/* number of entries in hpas[] */
 	u64 *hpas;		/* vmalloc'ed */
@@ -125,6 +127,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 {
 	struct mm_iommu_table_group_mem_t *mem;
 	long i, j, ret = 0, locked_entries = 0;
+	unsigned int pageshift;
+	unsigned long flags;
 	struct page *page = NULL;
 
 	mutex_lock(&mem_list_mutex);
@@ -159,6 +163,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		goto unlock_exit;
 	}
 
+	/*
+	 * For a starting point for a maximum page size calculation
+	 * we use @ua and @entries natural alignment to allow IOMMU pages
+	 * smaller than huge pages but still bigger than PAGE_SIZE.
+	 */
+	mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
 	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
 	if (!mem->hpas) {
 		kfree(mem);
@@ -199,6 +209,23 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 			}
 		}
 populate:
+		pageshift = PAGE_SHIFT;
+		if (PageCompound(page)) {
+			pte_t *pte;
+			struct page *head = compound_head(page);
+			unsigned int compshift = compound_order(head);
+
+			local_irq_save(flags); /* disables as well */
+			pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift);
+			local_irq_restore(flags);
+
+			/* Double check it is still the same pinned page */
+			if (pte && pte_page(*pte) == head &&
+					pageshift == compshift)
+				pageshift = max_t(unsigned int, pageshift,
+						PAGE_SHIFT);
+		}
+		mem->pageshift = min(mem->pageshift, pageshift);
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 	}
 
@@ -349,7 +376,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 EXPORT_SYMBOL_GPL(mm_iommu_find);
 
 long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	u64 *va = &mem->hpas[entry];
@@ -357,6 +384,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	*hpa = *va | (ua & ~PAGE_MASK);
 
 	return 0;
@@ -364,7 +394,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
 long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	void *va = &mem->hpas[entry];
@@ -373,6 +403,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	pa = (void *) vmalloc_to_phys(va);
 	if (!pa)
 		return -EFAULT;
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index 75cb646a79c3..9d16ee251fc0 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -186,9 +186,6 @@ static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
  * in a 2-bit field won't allow writes to a page that is otherwise
  * write-protected.
  */
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
 SYSCALL_DEFINE3(subpage_prot, unsigned long, addr,
 		unsigned long, len, u32 __user *, map)
 {
@@ -272,4 +269,3 @@ SYSCALL_DEFINE3(subpage_prot, unsigned long, addr,
 	up_write(&mm->mmap_sem);
 	return err;
 }
-#pragma GCC diagnostic pop
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 380cbf9a40d9..c0a9bcd28356 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -286,6 +286,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		u64 imm64;
 		u8 *func;
 		u32 true_cond;
+		u32 tmp_idx;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -637,11 +638,7 @@ emit_clear:
 		case BPF_STX | BPF_XADD | BPF_W:
 			/* Get EA into TMP_REG_1 */
 			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
-			/* error if EA is not word-aligned */
-			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
+			tmp_idx = ctx->idx * 4;
 			/* load value from memory into TMP_REG_2 */
 			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
 			/* add value from src_reg into this */
@@ -649,32 +646,16 @@ emit_clear:
 			/* store result back */
 			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
 			/* we're done if this succeeded */
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
-			/* otherwise, let's try once more */
-			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
-			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
-			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			/* exit if the store was not successful */
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_BCC(COND_NE, exit_addr);
+			PPC_BCC_SHORT(COND_NE, tmp_idx);
 			break;
 		/* *(u64 *)(dst + off) += src */
 		case BPF_STX | BPF_XADD | BPF_DW:
 			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
-			/* error if EA is not doubleword-aligned */
-			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4));
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
-			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
-			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
-			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
+			tmp_idx = ctx->idx * 4;
 			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
 			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
 			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_BCC(COND_NE, exit_addr);
+			PPC_BCC_SHORT(COND_NE, tmp_idx);
 			break;
 
 		/*
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 3f66fcf8ad99..19d8ab49d1bd 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1469,7 +1469,7 @@ static int collect_events(struct perf_event *group, int max_count,
 }
 
 /*
- * Add a event to the PMU.
+ * Add an event to the PMU.
  * If all events are not already frozen, then we disable and
  * re-enable the PMU in order to get hw_perf_enable to do the
  * actual work of reconfiguring the PMU.
@@ -1548,7 +1548,7 @@ nocheck:
 }
 
 /*
- * Remove a event from the PMU.
+ * Remove an event from the PMU.
  */
 static void power_pmu_del(struct perf_event *event, int ef_flags)
 {
@@ -1742,7 +1742,7 @@ static int power_pmu_commit_txn(struct pmu *pmu)
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
- * A event can only go on a limited PMC if it counts something
+ * An event can only go on a limited PMC if it counts something
  * that a limited PMC can count, doesn't require interrupts, and
  * doesn't exclude any processor mode.
  */
diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c
index 7c968e46736f..12e6e4d30602 100644
--- a/arch/powerpc/platforms/powermac/time.c
+++ b/arch/powerpc/platforms/powermac/time.c
@@ -42,7 +42,11 @@
 #define DBG(x...)
 #endif
 
-/* Apparently the RTC stores seconds since 1 Jan 1904 */
+/*
+ * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU
+ * times wrap in 2040. If we need to handle later times, the read_time functions
+ * need to be changed to interpret wrapped times as post-2040.
+ */
 #define RTC_OFFSET	2082844800
 
 /*
@@ -97,8 +101,11 @@ static time64_t cuda_get_time(void)
 	if (req.reply_len != 7)
 		printk(KERN_ERR "cuda_get_time: got %d byte reply\n",
 		       req.reply_len);
-	now = (req.reply[3] << 24) + (req.reply[4] << 16)
-		+ (req.reply[5] << 8) + req.reply[6];
+	now = (u32)((req.reply[3] << 24) + (req.reply[4] << 16) +
+		    (req.reply[5] << 8) + req.reply[6]);
+	/* it's either after year 2040, or the RTC has gone backwards */
+	WARN_ON(now < RTC_OFFSET);
+
 	return now - RTC_OFFSET;
 }
 
@@ -106,10 +113,10 @@ static time64_t cuda_get_time(void)
 
 static int cuda_set_rtc_time(struct rtc_time *tm)
 {
-	time64_t nowtime;
+	u32 nowtime;
 	struct adb_request req;
 
-	nowtime = rtc_tm_to_time64(tm) + RTC_OFFSET;
+	nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
 	if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME,
 			 nowtime >> 24, nowtime >> 16, nowtime >> 8,
 			 nowtime) < 0)
@@ -140,8 +147,12 @@ static time64_t pmu_get_time(void)
 	if (req.reply_len != 4)
 		printk(KERN_ERR "pmu_get_time: got %d byte reply from PMU\n",
 		       req.reply_len);
-	now = (req.reply[0] << 24) + (req.reply[1] << 16)
-		+ (req.reply[2] << 8) + req.reply[3];
+	now = (u32)((req.reply[0] << 24) + (req.reply[1] << 16)	+
+		    (req.reply[2] << 8) + req.reply[3]);
+
+	/* it's either after year 2040, or the RTC has gone backwards */
+	WARN_ON(now < RTC_OFFSET);
+
 	return now - RTC_OFFSET;
 }
 
@@ -149,10 +160,10 @@ static time64_t pmu_get_time(void)
 
 static int pmu_set_rtc_time(struct rtc_time *tm)
 {
-	time64_t nowtime;
+	u32 nowtime;
 	struct adb_request req;
 
-	nowtime = rtc_tm_to_time64(tm) + RTC_OFFSET;
+	nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
 	if (pmu_request(&req, NULL, 5, PMU_SET_RTC, nowtime >> 24,
 			nowtime >> 16, nowtime >> 8, nowtime) < 0)
 		return -ENXIO;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5bd0eb6681bc..70b2e1e0f23c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -46,6 +46,7 @@
 
 #include "powernv.h"
 #include "pci.h"
+#include "../../../../drivers/pci/pci.h"
 
 #define PNV_IODA1_M64_NUM	16	/* Number of M64 BARs	*/
 #define PNV_IODA1_M64_SEGS	8	/* Segments per M64 BAR	*/
@@ -3138,7 +3139,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 	struct pci_dn *pdn;
 	int mul, total_vfs;
 
-	if (!pdev->is_physfn || pdev->is_added)
+	if (!pdev->is_physfn || pci_dev_is_added(pdev))
 		return;
 
 	pdn = pci_get_pdn(pdev);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 139f0af6c3d9..8a4868a3964b 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -71,6 +71,7 @@
 #include <asm/security_features.h>
 
 #include "pseries.h"
+#include "../../../../drivers/pci/pci.h"
 
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
@@ -664,7 +665,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev)
 	const int *indexes;
 	struct device_node *dn = pci_device_to_OF_node(pdev);
 
-	if (!pdev->is_physfn || pdev->is_added)
+	if (!pdev->is_physfn || pci_dev_is_added(pdev))
 		return;
 	/*Firmware must support open sriov otherwise dont configure*/
 	indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 47166ad2a669..196978733e64 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2734,7 +2734,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 {
 	int nr, dotted;
 	unsigned long first_adr;
-	unsigned long inst, last_inst = 0;
+	unsigned int inst, last_inst = 0;
 	unsigned char val[4];
 
 	dotted = 0;
@@ -2758,7 +2758,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 		dotted = 0;
 		last_inst = inst;
 		if (praddr)
-			printf(REG"  %.8lx", adr, inst);
+			printf(REG"  %.8x", adr, inst);
 		printf("\t");
 		dump_func(inst, adr);
 		printf("\n");
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index f12680c9b947..4764fdeb4f1f 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -107,6 +107,7 @@ config ARCH_RV32I
 	select GENERIC_LIB_ASHLDI3
 	select GENERIC_LIB_ASHRDI3
 	select GENERIC_LIB_LSHRDI3
+	select GENERIC_LIB_UCMPDI2
 
 config ARCH_RV64I
 	bool "RV64I"
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 855115ace98c..c452359c9cb8 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -25,18 +25,11 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define __atomic_op_acquire(op, args...)				\
-({									\
-	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory");	\
-	__ret;								\
-})
-
-#define __atomic_op_release(op, args...)				\
-({									\
-	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");	\
-	op##_relaxed(args);						\
-})
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");
 
 static __always_inline int atomic_read(const atomic_t *v)
 {
@@ -209,130 +202,8 @@ ATOMIC_OPS(xor, xor, i)
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
-/*
- * The extra atomic operations that are constructed from one of the core
- * AMO-based operations above (aside from sub, which is easier to fit above).
- * These are required to perform a full barrier, but they're OK this way
- * because atomic_*_return is also required to perform a full barrier.
- *
- */
-#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix)		\
-static __always_inline							\
-bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
-{									\
-	return atomic##prefix##_##func_op##_return(i, v) comp_op I;	\
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, func_op, comp_op, I)				\
-        ATOMIC_OP(op, func_op, comp_op, I,  int,   )
-#else
-#define ATOMIC_OPS(op, func_op, comp_op, I)				\
-        ATOMIC_OP(op, func_op, comp_op, I,  int,   )			\
-        ATOMIC_OP(op, func_op, comp_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(add_and_test, add, ==, 0)
-ATOMIC_OPS(sub_and_test, sub, ==, 0)
-ATOMIC_OPS(add_negative, add,  <, 0)
-
-#undef ATOMIC_OP
-#undef ATOMIC_OPS
-
-#define ATOMIC_OP(op, func_op, I, c_type, prefix)			\
-static __always_inline							\
-void atomic##prefix##_##op(atomic##prefix##_t *v)			\
-{									\
-	atomic##prefix##_##func_op(I, v);				\
-}
-
-#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix)			\
-static __always_inline							\
-c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v)	\
-{									\
-	return atomic##prefix##_fetch_##func_op##_relaxed(I, v);	\
-}									\
-static __always_inline							\
-c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)		\
-{									\
-	return atomic##prefix##_fetch_##func_op(I, v);			\
-}
-
-#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix)		\
-static __always_inline							\
-c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v)	\
-{									\
-        return atomic##prefix##_fetch_##op##_relaxed(v) c_op I;		\
-}									\
-static __always_inline							\
-c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v)		\
-{									\
-        return atomic##prefix##_fetch_##op(v) c_op I;			\
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
-        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )
-#else
-#define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
-        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )			\
-        ATOMIC_OP(       op, asm_op,       I, long, 64)			\
-        ATOMIC_FETCH_OP( op, asm_op,       I, long, 64)			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(inc, add, +,  1)
-ATOMIC_OPS(dec, add, +, -1)
-
-#define atomic_inc_return_relaxed	atomic_inc_return_relaxed
-#define atomic_dec_return_relaxed	atomic_dec_return_relaxed
-#define atomic_inc_return		atomic_inc_return
-#define atomic_dec_return		atomic_dec_return
-
-#define atomic_fetch_inc_relaxed	atomic_fetch_inc_relaxed
-#define atomic_fetch_dec_relaxed	atomic_fetch_dec_relaxed
-#define atomic_fetch_inc		atomic_fetch_inc
-#define atomic_fetch_dec		atomic_fetch_dec
-
-#ifndef CONFIG_GENERIC_ATOMIC64
-#define atomic64_inc_return_relaxed	atomic64_inc_return_relaxed
-#define atomic64_dec_return_relaxed	atomic64_dec_return_relaxed
-#define atomic64_inc_return		atomic64_inc_return
-#define atomic64_dec_return		atomic64_dec_return
-
-#define atomic64_fetch_inc_relaxed	atomic64_fetch_inc_relaxed
-#define atomic64_fetch_dec_relaxed	atomic64_fetch_dec_relaxed
-#define atomic64_fetch_inc		atomic64_fetch_inc
-#define atomic64_fetch_dec		atomic64_fetch_dec
-#endif
-
-#undef ATOMIC_OPS
-#undef ATOMIC_OP
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP_RETURN
-
-#define ATOMIC_OP(op, func_op, comp_op, I, prefix)			\
-static __always_inline							\
-bool atomic##prefix##_##op(atomic##prefix##_t *v)			\
-{									\
-	return atomic##prefix##_##func_op##_return(v) comp_op I;	\
-}
-
-ATOMIC_OP(inc_and_test, inc, ==, 0,   )
-ATOMIC_OP(dec_and_test, dec, ==, 0,   )
-#ifndef CONFIG_GENERIC_ATOMIC64
-ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
-ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
-#endif
-
-#undef ATOMIC_OP
-
 /* This is required to provide a full barrier on success. */
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
        int prev, rc;
 
@@ -349,9 +220,10 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 		: "memory");
 	return prev;
 }
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
+static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
        long prev, rc;
 
@@ -368,27 +240,7 @@ static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
 		: "memory");
 	return prev;
 }
-
-static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	return __atomic64_add_unless(v, a, u) != u;
-}
-#endif
-
-/*
- * The extra atomic operations that are constructed from one of the core
- * LR/SC-based operations above.
- */
-static __always_inline int atomic_inc_not_zero(atomic_t *v)
-{
-        return __atomic_add_unless(v, 1, 0);
-}
-
-#ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
-{
-        return atomic64_add_unless(v, 1, 0);
-}
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 #endif
 
 /*
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
index 5cae4c30cd8e..1e0dfc36aab9 100644
--- a/arch/riscv/include/uapi/asm/elf.h
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -21,8 +21,13 @@ typedef struct user_regs_struct elf_gregset_t;
 
 typedef union __riscv_fp_state elf_fpregset_t;
 
-#define ELF_RISCV_R_SYM(r_info) ((r_info) >> 32)
-#define ELF_RISCV_R_TYPE(r_info) ((r_info) & 0xffffffff)
+#if __riscv_xlen == 64
+#define ELF_RISCV_R_SYM(r_info)		ELF64_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info)	ELF64_R_TYPE(r_info)
+#else
+#define ELF_RISCV_R_SYM(r_info)		ELF32_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info)	ELF32_R_TYPE(r_info)
+#endif
 
 /*
  * RISC-V relocation types
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
index b74cbfbce2d0..7bcdaed15703 100644
--- a/arch/riscv/kernel/irq.c
+++ b/arch/riscv/kernel/irq.c
@@ -16,10 +16,6 @@
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
 
-#ifdef CONFIG_RISCV_INTC
-#include <linux/irqchip/irq-riscv-intc.h>
-#endif
-
 void __init init_IRQ(void)
 {
 	irqchip_init();
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 1d5e9b934b8c..3303ed2cd419 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -37,7 +37,7 @@ static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
 static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
 				     Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	u32 imm12 = (offset & 0x1000) << (31 - 12);
 	u32 imm11 = (offset & 0x800) >> (11 - 7);
 	u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
@@ -50,7 +50,7 @@ static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
 static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
 				  Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	u32 imm20 = (offset & 0x100000) << (31 - 20);
 	u32 imm19_12 = (offset & 0xff000);
 	u32 imm11 = (offset & 0x800) << (20 - 11);
@@ -63,7 +63,7 @@ static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
 static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location,
 					 Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	u16 imm8 = (offset & 0x100) << (12 - 8);
 	u16 imm7_6 = (offset & 0xc0) >> (6 - 5);
 	u16 imm5 = (offset & 0x20) >> (5 - 2);
@@ -78,7 +78,7 @@ static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location,
 static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
 				       Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	u16 imm11 = (offset & 0x800) << (12 - 11);
 	u16 imm10 = (offset & 0x400) >> (10 - 8);
 	u16 imm9_8 = (offset & 0x300) << (12 - 11);
@@ -96,7 +96,7 @@ static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
 static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
 					 Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	s32 hi20;
 
 	if (offset != (s32)offset) {
@@ -178,7 +178,7 @@ static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location,
 static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
 				       Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	s32 hi20;
 
 	/* Always emit the got entry */
@@ -200,7 +200,7 @@ static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
 static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
 				       Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	s32 fill_v = offset;
 	u32 hi20, lo12;
 
@@ -227,7 +227,7 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
 static int apply_r_riscv_call_rela(struct module *me, u32 *location,
 				   Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	s32 fill_v = offset;
 	u32 hi20, lo12;
 
@@ -263,14 +263,14 @@ static int apply_r_riscv_align_rela(struct module *me, u32 *location,
 static int apply_r_riscv_add32_rela(struct module *me, u32 *location,
 				    Elf_Addr v)
 {
-	*(u32 *)location += (*(u32 *)v);
+	*(u32 *)location += (u32)v;
 	return 0;
 }
 
 static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
 				    Elf_Addr v)
 {
-	*(u32 *)location -= (*(u32 *)v);
+	*(u32 *)location -= (u32)v;
 	return 0;
 }
 
@@ -347,7 +347,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 			unsigned int j;
 
 			for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
-				u64 hi20_loc =
+				unsigned long hi20_loc =
 					sechdrs[sechdrs[relsec].sh_info].sh_addr
 					+ rel[j].r_offset;
 				u32 hi20_type = ELF_RISCV_R_TYPE(rel[j].r_info);
@@ -360,12 +360,12 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 					Elf_Sym *hi20_sym =
 						(Elf_Sym *)sechdrs[symindex].sh_addr
 						+ ELF_RISCV_R_SYM(rel[j].r_info);
-					u64 hi20_sym_val =
+					unsigned long hi20_sym_val =
 						hi20_sym->st_value
 						+ rel[j].r_addend;
 
 					/* Calculate lo12 */
-					u64 offset = hi20_sym_val - hi20_loc;
+					size_t offset = hi20_sym_val - hi20_loc;
 					if (IS_ENABLED(CONFIG_MODULE_SECTIONS)
 					    && hi20_type == R_RISCV_GOT_HI20) {
 						offset = module_emit_got_entry(
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index ba3e80712797..9f82a7e34c64 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -50,7 +50,7 @@ static int riscv_gpr_set(struct task_struct *target,
 	struct pt_regs *regs;
 
 	regs = task_pt_regs(target);
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &regs, 0, -1);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
 	return ret;
 }
 
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index ee44a48faf79..f0d2070866d4 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -220,8 +220,3 @@ void __init setup_arch(char **cmdline_p)
 	riscv_fill_hwcap();
 }
 
-static int __init riscv_device_init(void)
-{
-	return of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-subsys_initcall_sync(riscv_device_init);
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index c77df8142be2..58a522f9bcc3 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -28,7 +28,9 @@ static void __init zone_sizes_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
 
+#ifdef CONFIG_ZONE_DMA32
 	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn));
+#endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 
 	free_area_init_nodes(max_zone_pfns);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index baed39772c84..515240576930 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -106,7 +106,6 @@ config S390
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
-	select ARCH_WANTS_UBSAN_NO_NULL
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS2
@@ -140,12 +139,13 @@ config S390
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
-	select HAVE_GCC_PLUGINS
+	select HAVE_GCC_PLUGINS if BROKEN
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
+	select HAVE_KERNEL_UNCOMPRESSED
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
@@ -160,6 +160,7 @@ config S390
 	select HAVE_OPROFILE
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select MODULES_USE_ELF_RELA
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 68a690442be0..eee6703093c3 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -14,8 +14,18 @@ LD_BFD		:= elf64-s390
 LDFLAGS		:= -m elf64_s390
 KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
-KBUILD_CFLAGS	+= -m64
 KBUILD_AFLAGS	+= -m64
+KBUILD_CFLAGS	+= -m64
+aflags_dwarf	:= -Wa,-gdwarf-2
+KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__
+KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
+KBUILD_CFLAGS_DECOMPRESSOR := -m64 -O2
+KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
+KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float
+KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
+KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding)
+KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
+KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
 UTS_MACHINE	:= s390x
 STACK_SIZE	:= 16384
 CHECKFLAGS	+= -D__s390__ -D__s390x__
@@ -52,18 +62,14 @@ cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include
 #
 cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls
 
-# old style option for packed stacks
-ifeq ($(call cc-option-yn,-mkernel-backchain),y)
-cflags-$(CONFIG_PACK_STACK)  += -mkernel-backchain -D__PACK_STACK
-aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
-endif
-
-# new style option for packed stacks
 ifeq ($(call cc-option-yn,-mpacked-stack),y)
 cflags-$(CONFIG_PACK_STACK)  += -mpacked-stack -D__PACK_STACK
 aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
 endif
 
+KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y)
+KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y)
+
 ifeq ($(call cc-option-yn,-mstack-size=8192 -mstack-guard=128),y)
 cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE)
 ifneq ($(call cc-option-yn,-mstack-size=8192),y)
@@ -71,8 +77,11 @@ cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD)
 endif
 endif
 
-ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y)
-cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack
+ifdef CONFIG_WARN_DYNAMIC_STACK
+  ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y)
+    KBUILD_CFLAGS += -mwarn-dynamicstack
+    KBUILD_CFLAGS_DECOMPRESSOR += -mwarn-dynamicstack
+  endif
 endif
 
 ifdef CONFIG_EXPOLINE
@@ -82,6 +91,7 @@ ifdef CONFIG_EXPOLINE
     CC_FLAGS_EXPOLINE += -mindirect-branch-table
     export CC_FLAGS_EXPOLINE
     cflags-y += $(CC_FLAGS_EXPOLINE) -DCC_USING_EXPOLINE
+    aflags-y += -DCC_USING_EXPOLINE
   endif
 endif
 
@@ -102,11 +112,12 @@ KBUILD_CFLAGS	+= -mbackchain -msoft-float $(cflags-y)
 KBUILD_CFLAGS	+= -pipe -fno-strength-reduce -Wno-sign-compare
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables $(cfi)
 KBUILD_AFLAGS	+= $(aflags-y) $(cfi)
+export KBUILD_AFLAGS_DECOMPRESSOR
+export KBUILD_CFLAGS_DECOMPRESSOR
 
 OBJCOPYFLAGS	:= -O binary
 
-head-y		:= arch/s390/kernel/head.o
-head-y		+= arch/s390/kernel/head64.o
+head-y		:= arch/s390/kernel/head64.o
 
 # See arch/s390/Kbuild for content of core part of the kernel
 core-y		+= arch/s390/
@@ -121,7 +132,7 @@ boot		:= arch/s390/boot
 syscalls	:= arch/s390/kernel/syscalls
 tools		:= arch/s390/tools
 
-all: image bzImage
+all: bzImage
 
 #KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg...
 KBUILD_IMAGE	:= $(boot)/bzImage
@@ -129,7 +140,7 @@ KBUILD_IMAGE	:= $(boot)/bzImage
 install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
-image bzImage: vmlinux
+bzImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zfcpdump:
@@ -152,8 +163,7 @@ archprepare:
 
 # Don't use tabs in echo arguments
 define archhelp
-  echo  '* image           - Kernel image for IPL ($(boot)/image)'
-  echo	'* bzImage         - Compressed kernel image for IPL ($(boot)/bzImage)'
+  echo	'* bzImage         - Kernel image for IPL ($(boot)/bzImage)'
   echo	'  install         - Install kernel using'
   echo	'                    (your) ~/bin/$(INSTALLKERNEL) or'
   echo	'                    (distribution) /sbin/$(INSTALLKERNEL) or'
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index ee6a9c387c87..9bf8489df6e6 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -206,35 +206,28 @@ static int
 appldata_timer_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	unsigned int len;
-	char buf[2];
+	int timer_active = appldata_timer_active;
+	int zero = 0;
+	int one = 1;
+	int rc;
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &timer_active,
+		.maxlen		= sizeof(int),
+		.extra1		= &zero,
+		.extra2		= &one,
+	};
+
+	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
-		return 0;
-	}
-	if (!write) {
-		strncpy(buf, appldata_timer_active ? "1\n" : "0\n",
-			ARRAY_SIZE(buf));
-		len = strnlen(buf, ARRAY_SIZE(buf));
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
-		return -EFAULT;
 	spin_lock(&appldata_timer_lock);
-	if (buf[0] == '1')
+	if (timer_active)
 		__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
-	else if (buf[0] == '0')
+	else
 		__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
 	spin_unlock(&appldata_timer_lock);
-out:
-	*lenp = len;
-	*ppos += len;
 	return 0;
 }
 
@@ -248,37 +241,24 @@ static int
 appldata_interval_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	unsigned int len;
-	int interval;
-	char buf[16];
+	int interval = appldata_interval;
+	int one = 1;
+	int rc;
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &interval,
+		.maxlen		= sizeof(int),
+		.extra1		= &one,
+	};
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
-		return 0;
-	}
-	if (!write) {
-		len = sprintf(buf, "%i\n", appldata_interval);
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
-		return -EFAULT;
-	interval = 0;
-	sscanf(buf, "%i", &interval);
-	if (interval <= 0)
-		return -EINVAL;
+	rc = proc_dointvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
 	spin_lock(&appldata_timer_lock);
 	appldata_interval = interval;
 	__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
 	spin_unlock(&appldata_timer_lock);
-out:
-	*lenp = len;
-	*ppos += len;
 	return 0;
 }
 
@@ -293,10 +273,17 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct appldata_ops *ops = NULL, *tmp_ops;
-	unsigned int len;
-	int rc, found;
-	char buf[2];
 	struct list_head *lh;
+	int rc, found;
+	int active;
+	int zero = 0;
+	int one = 1;
+	struct ctl_table ctl_entry = {
+		.data		= &active,
+		.maxlen		= sizeof(int),
+		.extra1		= &zero,
+		.extra2		= &one,
+	};
 
 	found = 0;
 	mutex_lock(&appldata_ops_mutex);
@@ -317,31 +304,15 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 	}
 	mutex_unlock(&appldata_ops_mutex);
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
+	active = ops->active;
+	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write) {
 		module_put(ops->owner);
-		return 0;
-	}
-	if (!write) {
-		strncpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf));
-		len = strnlen(buf, ARRAY_SIZE(buf));
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len)) {
-			module_put(ops->owner);
-			return -EFAULT;
-		}
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer,
-			   len > sizeof(buf) ? sizeof(buf) : len)) {
-		module_put(ops->owner);
-		return -EFAULT;
+		return rc;
 	}
 
 	mutex_lock(&appldata_ops_mutex);
-	if ((buf[0] == '1') && (ops->active == 0)) {
+	if (active && (ops->active == 0)) {
 		// protect work queue callback
 		if (!try_module_get(ops->owner)) {
 			mutex_unlock(&appldata_ops_mutex);
@@ -359,7 +330,7 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 			module_put(ops->owner);
 		} else
 			ops->active = 1;
-	} else if ((buf[0] == '0') && (ops->active == 1)) {
+	} else if (!active && (ops->active == 1)) {
 		ops->active = 0;
 		rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
 				(unsigned long) ops->data, ops->size,
@@ -370,9 +341,6 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 		module_put(ops->owner);
 	}
 	mutex_unlock(&appldata_ops_mutex);
-out:
-	*lenp = len;
-	*ppos += len;
 	module_put(ops->owner);
 	return 0;
 }
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index d1fa37fcce83..9e6668ee93de 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -3,19 +3,52 @@
 # Makefile for the linux s390-specific parts of the memory manager.
 #
 
-targets := image
-targets += bzImage
-subdir- := compressed
+KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
 
-$(obj)/image: vmlinux FORCE
-	$(call if_changed,objcopy)
+KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
+KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
+
+#
+# Use -march=z900 for als.c to be able to print an error
+# message if the kernel is started on a machine which is too old
+#
+ifneq ($(CC_FLAGS_MARCH),-march=z900)
+AFLAGS_REMOVE_head.o		+= $(CC_FLAGS_MARCH)
+AFLAGS_head.o			+= -march=z900
+AFLAGS_REMOVE_mem.o		+= $(CC_FLAGS_MARCH)
+AFLAGS_mem.o			+= -march=z900
+CFLAGS_REMOVE_als.o		+= $(CC_FLAGS_MARCH)
+CFLAGS_als.o			+= -march=z900
+CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
+CFLAGS_sclp_early_core.o	+= -march=z900
+endif
+
+CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
+
+obj-y	:= head.o als.o ebcdic.o sclp_early_core.o mem.o
+targets	:= bzImage startup.a $(obj-y)
+subdir-	:= compressed
+
+OBJECTS := $(addprefix $(obj)/,$(obj-y))
 
 $(obj)/bzImage: $(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
 
-$(obj)/compressed/vmlinux: FORCE
+$(obj)/compressed/vmlinux: $(obj)/startup.a FORCE
 	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
 
+quiet_cmd_ar = AR      $@
+      cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(filter $(OBJECTS), $^)
+
+$(obj)/startup.a: $(OBJECTS) FORCE
+	$(call if_changed,ar)
+
 install: $(CONFIGURE) $(obj)/bzImage
 	sh -x  $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
 	      System.map "$(INSTALL_PATH)"
+
+chkbss := $(OBJECTS)
+chkbss-target := $(obj)/startup.a
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/als.c b/arch/s390/boot/als.c
index d1892bf36cab..d592e0d90d9f 100644
--- a/arch/s390/kernel/als.c
+++ b/arch/s390/boot/als.c
@@ -3,12 +3,10 @@
  *    Copyright IBM Corp. 2016
  */
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <asm/processor.h>
 #include <asm/facility.h>
 #include <asm/lowcore.h>
 #include <asm/sclp.h>
-#include "entry.h"
 
 /*
  * The code within this file will be called very early. It may _not_
@@ -18,9 +16,9 @@
  * For temporary objects the stack (16k) should be used.
  */
 
-static unsigned long als[] __initdata = { FACILITIES_ALS };
+static unsigned long als[] = { FACILITIES_ALS };
 
-static void __init u16_to_hex(char *str, u16 val)
+static void u16_to_hex(char *str, u16 val)
 {
 	int i, num;
 
@@ -33,9 +31,9 @@ static void __init u16_to_hex(char *str, u16 val)
 	*str = '\0';
 }
 
-static void __init print_machine_type(void)
+static void print_machine_type(void)
 {
-	static char mach_str[80] __initdata = "Detected machine-type number: ";
+	static char mach_str[80] = "Detected machine-type number: ";
 	char type_str[5];
 	struct cpuid id;
 
@@ -46,7 +44,7 @@ static void __init print_machine_type(void)
 	sclp_early_printk(mach_str);
 }
 
-static void __init u16_to_decimal(char *str, u16 val)
+static void u16_to_decimal(char *str, u16 val)
 {
 	int div = 1;
 
@@ -60,9 +58,9 @@ static void __init u16_to_decimal(char *str, u16 val)
 	*str = '\0';
 }
 
-static void __init print_missing_facilities(void)
+static void print_missing_facilities(void)
 {
-	static char als_str[80] __initdata = "Missing facilities: ";
+	static char als_str[80] = "Missing facilities: ";
 	unsigned long val;
 	char val_str[6];
 	int i, j, first;
@@ -95,7 +93,7 @@ static void __init print_missing_facilities(void)
 	sclp_early_printk("See Principles of Operations for facility bits\n");
 }
 
-static void __init facility_mismatch(void)
+static void facility_mismatch(void)
 {
 	sclp_early_printk("The Linux kernel requires more recent processor hardware\n");
 	print_machine_type();
@@ -103,7 +101,7 @@ static void __init facility_mismatch(void)
 	disabled_wait(0x8badcccc);
 }
 
-void __init verify_facilities(void)
+void verify_facilities(void)
 {
 	int i;
 
diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore
index 2088cc140629..45aeb4f08752 100644
--- a/arch/s390/boot/compressed/.gitignore
+++ b/arch/s390/boot/compressed/.gitignore
@@ -1,4 +1,5 @@
 sizes.h
 vmlinux
 vmlinux.lds
+vmlinux.scr.lds
 vmlinux.bin.full
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 5766f7b9b271..04609478d18b 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -6,39 +6,29 @@
 #
 
 KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
 
+obj-y	:= $(if $(CONFIG_KERNEL_UNCOMPRESSED),,head.o misc.o) piggy.o
 targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
-targets += misc.o piggy.o sizes.h head.o
-
-KBUILD_CFLAGS := -m64 -D__KERNEL__ -O2
-KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
-KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float
-KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
-KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
-KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
+targets += vmlinux.scr.lds $(obj-y) $(if $(CONFIG_KERNEL_UNCOMPRESSED),,sizes.h)
 
-GCOV_PROFILE := n
-UBSAN_SANITIZE := n
+KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
+KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 
-OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o ebcdic.o als.o)
-OBJECTS += $(objtree)/drivers/s390/char/sclp_early_core.o
-OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
+OBJECTS := $(addprefix $(obj)/,$(obj-y))
 
 LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS)
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS)
 	$(call if_changed,ld)
 
-TRIM_HEAD_SIZE := 0x11000
-
-sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - $(TRIM_HEAD_SIZE))/p'
+# extract required uncompressed vmlinux symbols and adjust them to reflect offsets inside vmlinux.bin
+sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - 0x100000)/p'
 
 quiet_cmd_sizes = GEN     $@
       cmd_sizes = $(NM) $< | sed -n $(sed-sizes) > $@
 
-quiet_cmd_trim_head = TRIM    $@
-      cmd_trim_head = tail -c +$$(($(TRIM_HEAD_SIZE) + 1)) $< > $@
-
 $(obj)/sizes.h: vmlinux
 	$(call if_changed,sizes)
 
@@ -48,21 +38,18 @@ $(obj)/head.o: $(obj)/sizes.h
 CFLAGS_misc.o += -I$(objtree)/$(obj)
 $(obj)/misc.o: $(obj)/sizes.h
 
-OBJCOPYFLAGS_vmlinux.bin.full :=  -R .comment -S
-$(obj)/vmlinux.bin.full: vmlinux
+OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
+$(obj)/vmlinux.bin: vmlinux
 	$(call if_changed,objcopy)
 
-$(obj)/vmlinux.bin: $(obj)/vmlinux.bin.full
-	$(call if_changed,trim_head)
-
 vmlinux.bin.all-y := $(obj)/vmlinux.bin
 
-suffix-$(CONFIG_KERNEL_GZIP)  := gz
-suffix-$(CONFIG_KERNEL_BZIP2) := bz2
-suffix-$(CONFIG_KERNEL_LZ4)  := lz4
-suffix-$(CONFIG_KERNEL_LZMA)  := lzma
-suffix-$(CONFIG_KERNEL_LZO)  := lzo
-suffix-$(CONFIG_KERNEL_XZ)  := xz
+suffix-$(CONFIG_KERNEL_GZIP)  := .gz
+suffix-$(CONFIG_KERNEL_BZIP2) := .bz2
+suffix-$(CONFIG_KERNEL_LZ4)  := .lz4
+suffix-$(CONFIG_KERNEL_LZMA)  := .lzma
+suffix-$(CONFIG_KERNEL_LZO)  := .lzo
+suffix-$(CONFIG_KERNEL_XZ)  := .xz
 
 $(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
 	$(call if_changed,gzip)
@@ -78,5 +65,9 @@ $(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y)
 	$(call if_changed,xzkern)
 
 LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y)
+$(obj)/piggy.o: $(obj)/vmlinux.scr.lds $(obj)/vmlinux.bin$(suffix-y)
 	$(call if_changed,ld)
+
+chkbss := $(filter-out $(obj)/misc.o $(obj)/piggy.o,$(OBJECTS))
+chkbss-target := $(obj)/vmlinux.bin
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S
index 9f94eca0f467..df8dbbc17bcc 100644
--- a/arch/s390/boot/compressed/head.S
+++ b/arch/s390/boot/compressed/head.S
@@ -15,7 +15,7 @@
 #include "sizes.h"
 
 __HEAD
-ENTRY(startup_continue)
+ENTRY(startup_decompressor)
 	basr	%r13,0			# get base
 .LPG1:
 	# setup stack
@@ -23,7 +23,7 @@ ENTRY(startup_continue)
 	aghi	%r15,-160
 	brasl	%r14,decompress_kernel
 	# Set up registers for memory mover. We move the decompressed image to
-	# 0x11000, where startup_continue of the decompressed image is supposed
+	# 0x100000, where startup_continue of the decompressed image is supposed
 	# to be.
 	lgr	%r4,%r2
 	lg	%r2,.Loffset-.LPG1(%r13)
@@ -33,7 +33,7 @@ ENTRY(startup_continue)
 	la	%r1,0x200
 	mvc	0(mover_end-mover,%r1),mover-.LPG1(%r13)
 	# When the memory mover is done we pass control to
-	# arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in
+	# arch/s390/kernel/head64.S:startup_continue which lives at 0x100000 in
 	# the decompressed image.
 	lgr	%r6,%r2
 	br	%r1
@@ -47,6 +47,6 @@ mover_end:
 .Lstack:
 	.quad	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
 .Loffset:
-	.quad	0x11000
+	.quad	0x100000
 .Lmvsize:
 	.quad	SZ__bss_start
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index 511b2cc9b91a..f66ad73c205b 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -71,43 +71,6 @@ static int puts(const char *s)
 	return 0;
 }
 
-void *memset(void *s, int c, size_t n)
-{
-	char *xs;
-
-	xs = s;
-	while (n--)
-		*xs++ = c;
-	return s;
-}
-
-void *memcpy(void *dest, const void *src, size_t n)
-{
-	const char *s = src;
-	char *d = dest;
-
-	while (n--)
-		*d++ = *s++;
-	return dest;
-}
-
-void *memmove(void *dest, const void *src, size_t n)
-{
-	const char *s = src;
-	char *d = dest;
-
-	if (d <= s) {
-		while (n--)
-			*d++ = *s++;
-	} else {
-		d += n;
-		s += n;
-		while (n--)
-			*--d = *--s;
-	}
-	return dest;
-}
-
 static void error(char *x)
 {
 	unsigned long long psw = 0x000a0000deadbeefULL;
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index d43c2db12d30..b16ac8b3c439 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -23,13 +23,10 @@ SECTIONS
 		*(.text.*)
 		_etext = . ;
 	}
-	.rodata.compressed : {
-		*(.rodata.compressed)
-	}
 	.rodata : {
 		_rodata = . ;
 		*(.rodata)	 /* read-only data */
-		*(.rodata.*)
+		*(EXCLUDE_FILE (*piggy.o) .rodata.compressed)
 		_erodata = . ;
 	}
 	.data :	{
@@ -38,6 +35,15 @@ SECTIONS
 		*(.data.*)
 		_edata = . ;
 	}
+	startup_continue = 0x100000;
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
+	. = 0x100000;
+#else
+	. = ALIGN(8);
+#endif
+	.rodata.compressed : {
+		*(.rodata.compressed)
+	}
 	. = ALIGN(256);
 	.bss : {
 		_bss = . ;
@@ -54,5 +60,6 @@ SECTIONS
 		*(.eh_frame)
 		*(__ex_table)
 		*(*__ksymtab*)
+		*(___kcrctab*)
 	}
 }
diff --git a/arch/s390/boot/compressed/vmlinux.scr b/arch/s390/boot/compressed/vmlinux.scr.lds.S
index 42a242597f34..ff01d18c9222 100644
--- a/arch/s390/boot/compressed/vmlinux.scr
+++ b/arch/s390/boot/compressed/vmlinux.scr.lds.S
@@ -2,10 +2,14 @@
 SECTIONS
 {
   .rodata.compressed : {
+#ifndef CONFIG_KERNEL_UNCOMPRESSED
 	input_len = .;
 	LONG(input_data_end - input_data) input_data = .;
+#endif
 	*(.data)
+#ifndef CONFIG_KERNEL_UNCOMPRESSED
 	output_len = . - 4;
 	input_data_end = .;
+#endif
 	}
 }
diff --git a/arch/s390/boot/ebcdic.c b/arch/s390/boot/ebcdic.c
new file mode 100644
index 000000000000..7391e7d36086
--- /dev/null
+++ b/arch/s390/boot/ebcdic.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../kernel/ebcdic.c"
diff --git a/arch/s390/kernel/head.S b/arch/s390/boot/head.S
index 5c42f16a54c4..f721913b73f1 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/boot/head.S
@@ -272,14 +272,14 @@ iplstart:
 	.org	0x10000
 ENTRY(startup)
 	j	.Lep_startup_normal
-	.org	0x10008
+	.org	EP_OFFSET
 #
 # This is a list of s390 kernel entry points. At address 0x1000f the number of
 # valid entry points is stored.
 #
 # IMPORTANT: Do not change this table, it is s390 kernel ABI!
 #
-	.ascii	"S390EP"
+	.ascii	EP_STRING
 	.byte	0x00,0x01
 #
 # kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
@@ -310,10 +310,11 @@ ENTRY(startup_kdump)
 	l	%r15,.Lstack-.LPG0(%r13)
 	ahi	%r15,-STACK_FRAME_OVERHEAD
 	brasl	%r14,verify_facilities
-# For uncompressed images, continue in
-# arch/s390/kernel/head64.S. For compressed images, continue in
-# arch/s390/boot/compressed/head.S.
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
 	jg	startup_continue
+#else
+	jg	startup_decompressor
+#endif
 
 .Lstack:
 	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/boot/head_kdump.S
index 174d6959bf5b..174d6959bf5b 100644
--- a/arch/s390/kernel/head_kdump.S
+++ b/arch/s390/boot/head_kdump.S
diff --git a/arch/s390/boot/mem.S b/arch/s390/boot/mem.S
new file mode 100644
index 000000000000..b33463633f03
--- /dev/null
+++ b/arch/s390/boot/mem.S
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "../lib/mem.S"
diff --git a/arch/s390/boot/sclp_early_core.c b/arch/s390/boot/sclp_early_core.c
new file mode 100644
index 000000000000..5a19fd7020b5
--- /dev/null
+++ b/arch/s390/boot/sclp_early_core.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../drivers/s390/char/sclp_early_core.c"
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index a2945b289a29..3452e18bb1ca 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -497,7 +497,7 @@ static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 	}
 	diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer);
 	rc = hypfs_create_str(cpu_dir, "type", buffer);
-	return PTR_RET(rc);
+	return PTR_ERR_OR_ZERO(rc);
 }
 
 static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr)
@@ -544,7 +544,7 @@ static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 		return PTR_ERR(rc);
 	diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer);
 	rc = hypfs_create_str(cpu_dir, "type", buffer);
-	return PTR_RET(rc);
+	return PTR_ERR_OR_ZERO(rc);
 }
 
 static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr)
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 06b513d192b9..c681329fdeec 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -36,7 +36,7 @@ struct hypfs_sb_info {
 	kuid_t uid;			/* uid used for files and dirs */
 	kgid_t gid;			/* gid used for files and dirs */
 	struct dentry *update_file;	/* file to trigger update */
-	time_t last_update;		/* last update time in secs since 1970 */
+	time64_t last_update;		/* last update, CLOCK_MONOTONIC time */
 	struct mutex lock;		/* lock to protect update process */
 };
 
@@ -52,7 +52,7 @@ static void hypfs_update_update(struct super_block *sb)
 	struct hypfs_sb_info *sb_info = sb->s_fs_info;
 	struct inode *inode = d_inode(sb_info->update_file);
 
-	sb_info->last_update = get_seconds();
+	sb_info->last_update = ktime_get_seconds();
 	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 }
 
@@ -179,7 +179,7 @@ static ssize_t hypfs_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	 *    to restart data collection in this case.
 	 */
 	mutex_lock(&fs_info->lock);
-	if (fs_info->last_update == get_seconds()) {
+	if (fs_info->last_update == ktime_get_seconds()) {
 		rc = -EBUSY;
 		goto out;
 	}
diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index c1bedb4c8de0..046e044a48d0 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -47,6 +47,50 @@ struct ap_queue_status {
 };
 
 /**
+ * ap_intructions_available() - Test if AP instructions are available.
+ *
+ * Returns 0 if the AP instructions are installed.
+ */
+static inline int ap_instructions_available(void)
+{
+	register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
+	register unsigned long reg1 asm ("1") = -ENODEV;
+	register unsigned long reg2 asm ("2");
+
+	asm volatile(
+		"   .long 0xb2af0000\n"		/* PQAP(TAPQ) */
+		"0: la    %0,0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: "+d" (reg1), "=d" (reg2)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
+/**
+ * ap_tapq(): Test adjunct processor queue.
+ * @qid: The AP queue number
+ * @info: Pointer to queue descriptor
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
+{
+	register unsigned long reg0 asm ("0") = qid;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm ("2");
+
+	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
+		     : "=d" (reg1), "=d" (reg2)
+		     : "d" (reg0)
+		     : "cc");
+	if (info)
+		*info = reg2;
+	return reg1;
+}
+
+/**
  * ap_test_queue(): Test adjunct processor queue.
  * @qid: The AP queue number
  * @tbit: Test facilities bit
@@ -54,10 +98,57 @@ struct ap_queue_status {
  *
  * Returns AP queue status structure.
  */
-struct ap_queue_status ap_test_queue(ap_qid_t qid,
-				     int tbit,
-				     unsigned long *info);
+static inline struct ap_queue_status ap_test_queue(ap_qid_t qid,
+						   int tbit,
+						   unsigned long *info)
+{
+	if (tbit)
+		qid |= 1UL << 23; /* set T bit*/
+	return ap_tapq(qid, info);
+}
 
+/**
+ * ap_pqap_rapq(): Reset adjunct processor queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
+{
+	register unsigned long reg0 asm ("0") = qid | (1UL << 24);
+	register struct ap_queue_status reg1 asm ("1");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(RAPQ) */
+		: "=d" (reg1)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
+/**
+ * ap_pqap_zapq(): Reset and zeroize adjunct processor queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_zapq(ap_qid_t qid)
+{
+	register unsigned long reg0 asm ("0") = qid | (2UL << 24);
+	register struct ap_queue_status reg1 asm ("1");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(ZAPQ) */
+		: "=d" (reg1)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
+/**
+ * struct ap_config_info - convenience struct for AP crypto
+ * config info as returned by the ap_qci() function.
+ */
 struct ap_config_info {
 	unsigned int apsc	 : 1;	/* S bit */
 	unsigned int apxa	 : 1;	/* N bit */
@@ -74,50 +165,189 @@ struct ap_config_info {
 	unsigned char _reserved4[16];
 } __aligned(8);
 
-/*
- * ap_query_configuration(): Fetch cryptographic config info
+/**
+ * ap_qci(): Get AP configuration data
  *
- * Returns the ap configuration info fetched via PQAP(QCI).
- * On success 0 is returned, on failure a negative errno
- * is returned, e.g. if the PQAP(QCI) instruction is not
- * available, the return value will be -EOPNOTSUPP.
+ * Returns 0 on success, or -EOPNOTSUPP.
  */
-int ap_query_configuration(struct ap_config_info *info);
+static inline int ap_qci(struct ap_config_info *config)
+{
+	register unsigned long reg0 asm ("0") = 4UL << 24;
+	register unsigned long reg1 asm ("1") = -EOPNOTSUPP;
+	register struct ap_config_info *reg2 asm ("2") = config;
+
+	asm volatile(
+		".long 0xb2af0000\n"		/* PQAP(QCI) */
+		"0: la    %0,0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: "+d" (reg1)
+		: "d" (reg0), "d" (reg2)
+		: "cc", "memory");
+
+	return reg1;
+}
 
 /*
  * struct ap_qirq_ctrl - convenient struct for easy invocation
- * of the ap_queue_irq_ctrl() function. This struct is passed
- * as GR1 parameter to the PQAP(AQIC) instruction. For details
- * please see the AR documentation.
+ * of the ap_aqic() function. This struct is passed as GR1
+ * parameter to the PQAP(AQIC) instruction. For details please
+ * see the AR documentation.
  */
 struct ap_qirq_ctrl {
 	unsigned int _res1 : 8;
-	unsigned int zone  : 8;  /* zone info */
-	unsigned int ir    : 1;  /* ir flag: enable (1) or disable (0) irq */
+	unsigned int zone  : 8;	/* zone info */
+	unsigned int ir    : 1;	/* ir flag: enable (1) or disable (0) irq */
 	unsigned int _res2 : 4;
-	unsigned int gisc  : 3;  /* guest isc field */
+	unsigned int gisc  : 3;	/* guest isc field */
 	unsigned int _res3 : 6;
-	unsigned int gf    : 2;  /* gisa format */
+	unsigned int gf    : 2;	/* gisa format */
 	unsigned int _res4 : 1;
-	unsigned int gisa  : 27; /* gisa origin */
+	unsigned int gisa  : 27;	/* gisa origin */
 	unsigned int _res5 : 1;
-	unsigned int isc   : 3;  /* irq sub class */
+	unsigned int isc   : 3;	/* irq sub class */
 };
 
 /**
- * ap_queue_irq_ctrl(): Control interruption on a AP queue.
+ * ap_aqic(): Control interruption for a specific AP.
  * @qid: The AP queue number
- * @qirqctrl: struct ap_qirq_ctrl, see above
+ * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
  * @ind: The notification indicator byte
  *
  * Returns AP queue status.
+ */
+static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
+					     struct ap_qirq_ctrl qirqctrl,
+					     void *ind)
+{
+	register unsigned long reg0 asm ("0") = qid | (3UL << 24);
+	register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
+	register struct ap_queue_status reg1_out asm ("1");
+	register void *reg2 asm ("2") = ind;
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(AQIC) */
+		: "=d" (reg1_out)
+		: "d" (reg0), "d" (reg1_in), "d" (reg2)
+		: "cc");
+	return reg1_out;
+}
+
+/*
+ * union ap_qact_ap_info - used together with the
+ * ap_aqic() function to provide a convenient way
+ * to handle the ap info needed by the qact function.
+ */
+union ap_qact_ap_info {
+	unsigned long val;
+	struct {
+		unsigned int	  : 3;
+		unsigned int mode : 3;
+		unsigned int	  : 26;
+		unsigned int cat  : 8;
+		unsigned int	  : 8;
+		unsigned char ver[2];
+	};
+};
+
+/**
+ * ap_qact(): Query AP combatibility type.
+ * @qid: The AP queue number
+ * @apinfo: On input the info about the AP queue. On output the
+ *	    alternate AP queue info provided by the qact function
+ *	    in GR2 is stored in.
  *
- * Control interruption on the given AP queue.
- * Just a simple wrapper function for the low level PQAP(AQIC)
- * instruction available for other kernel modules.
+ * Returns AP queue status. Check response_code field for failures.
  */
-struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid,
-					 struct ap_qirq_ctrl qirqctrl,
-					 void *ind);
+static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
+					     union ap_qact_ap_info *apinfo)
+{
+	register unsigned long reg0 asm ("0") = qid | (5UL << 24)
+		| ((ifbit & 0x01) << 22);
+	register unsigned long reg1_in asm ("1") = apinfo->val;
+	register struct ap_queue_status reg1_out asm ("1");
+	register unsigned long reg2 asm ("2");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(QACT) */
+		: "+d" (reg1_in), "=d" (reg1_out), "=d" (reg2)
+		: "d" (reg0)
+		: "cc");
+	apinfo->val = reg2;
+	return reg1_out;
+}
+
+/**
+ * ap_nqap(): Send message to adjunct processor queue.
+ * @qid: The AP queue number
+ * @psmid: The program supplied message identifier
+ * @msg: The message text
+ * @length: The message length
+ *
+ * Returns AP queue status structure.
+ * Condition code 1 on NQAP can't happen because the L bit is 1.
+ * Condition code 2 on NQAP also means the send is incomplete,
+ * because a segment boundary was reached. The NQAP is repeated.
+ */
+static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
+					     unsigned long long psmid,
+					     void *msg, size_t length)
+{
+	register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm ("2") = (unsigned long) msg;
+	register unsigned long reg3 asm ("3") = (unsigned long) length;
+	register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
+	register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
+
+	asm volatile (
+		"0: .long 0xb2ad0042\n"		/* NQAP */
+		"   brc   2,0b"
+		: "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
+		: "d" (reg4), "d" (reg5)
+		: "cc", "memory");
+	return reg1;
+}
+
+/**
+ * ap_dqap(): Receive message from adjunct processor queue.
+ * @qid: The AP queue number
+ * @psmid: Pointer to program supplied message identifier
+ * @msg: The message text
+ * @length: The message length
+ *
+ * Returns AP queue status structure.
+ * Condition code 1 on DQAP means the receive has taken place
+ * but only partially.	The response is incomplete, hence the
+ * DQAP is repeated.
+ * Condition code 2 on DQAP also means the receive is incomplete,
+ * this time because a segment boundary was reached. Again, the
+ * DQAP is repeated.
+ * Note that gpr2 is used by the DQAP instruction to keep track of
+ * any 'residual' length, in case the instruction gets interrupted.
+ * Hence it gets zeroed before the instruction.
+ */
+static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
+					     unsigned long long *psmid,
+					     void *msg, size_t length)
+{
+	register unsigned long reg0 asm("0") = qid | 0x80000000UL;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm("2") = 0UL;
+	register unsigned long reg4 asm("4") = (unsigned long) msg;
+	register unsigned long reg5 asm("5") = (unsigned long) length;
+	register unsigned long reg6 asm("6") = 0UL;
+	register unsigned long reg7 asm("7") = 0UL;
+
+
+	asm volatile(
+		"0: .long 0xb2ae0064\n"		/* DQAP */
+		"   brc   6,0b\n"
+		: "+d" (reg0), "=d" (reg1), "+d" (reg2),
+		  "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7)
+		: : "cc", "memory");
+	*psmid = (((unsigned long long) reg6) << 32) + reg7;
+	return reg1;
+}
 
 #endif /* _ASM_S390_AP_H_ */
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 4b55532f15c4..fd20ab5d4cf7 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -55,17 +55,9 @@ static inline void atomic_add(int i, atomic_t *v)
 	__atomic_add(i, &v->counter);
 }
 
-#define atomic_add_negative(_i, _v)	(atomic_add_return(_i, _v) < 0)
-#define atomic_inc(_v)			atomic_add(1, _v)
-#define atomic_inc_return(_v)		atomic_add_return(1, _v)
-#define atomic_inc_and_test(_v)		(atomic_add_return(1, _v) == 0)
 #define atomic_sub(_i, _v)		atomic_add(-(int)(_i), _v)
 #define atomic_sub_return(_i, _v)	atomic_add_return(-(int)(_i), _v)
 #define atomic_fetch_sub(_i, _v)	atomic_fetch_add(-(int)(_i), _v)
-#define atomic_sub_and_test(_i, _v)	(atomic_sub_return(_i, _v) == 0)
-#define atomic_dec(_v)			atomic_sub(1, _v)
-#define atomic_dec_return(_v)		atomic_sub_return(1, _v)
-#define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
 #define ATOMIC_OPS(op)							\
 static inline void atomic_##op(int i, atomic_t *v)			\
@@ -90,21 +82,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return __atomic_cmpxchg(&v->counter, old, new);
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == u))
-			break;
-		old = atomic_cmpxchg(v, c, c + a);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define ATOMIC64_INIT(i)  { (i) }
 
 static inline long atomic64_read(const atomic64_t *v)
@@ -168,50 +145,8 @@ ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
 
-static inline int atomic64_add_unless(atomic64_t *v, long i, long u)
-{
-	long c, old;
-
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == u))
-			break;
-		old = atomic64_cmpxchg(v, c, c + i);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != u;
-}
-
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
-#define atomic64_add_negative(_i, _v)	(atomic64_add_return(_i, _v) < 0)
-#define atomic64_inc(_v)		atomic64_add(1, _v)
-#define atomic64_inc_return(_v)		atomic64_add_return(1, _v)
-#define atomic64_inc_and_test(_v)	(atomic64_add_return(1, _v) == 0)
 #define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long)(_i), _v)
 #define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long)(_i), _v)
 #define atomic64_sub(_i, _v)		atomic64_add(-(long)(_i), _v)
-#define atomic64_sub_and_test(_i, _v)	(atomic64_sub_return(_i, _v) == 0)
-#define atomic64_dec(_v)		atomic64_sub(1, _v)
-#define atomic64_dec_return(_v)		atomic64_sub_return(1, _v)
-#define atomic64_dec_and_test(_v)	(atomic64_sub_return(1, _v) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
 #endif /* __ARCH_S390_ATOMIC__  */
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index de023a9a88ca..bf2cbff926ef 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -2,7 +2,7 @@
 /*
  * CPU-measurement facilities
  *
- *  Copyright IBM Corp. 2012
+ *  Copyright IBM Corp. 2012, 2018
  *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *	       Jan Glauber <jang@linux.vnet.ibm.com>
  */
@@ -139,8 +139,14 @@ struct hws_trailer_entry {
 	unsigned char timestamp[16];	 /* 16 - 31 timestamp		      */
 	unsigned long long reserved1;	 /* 32 -Reserved		      */
 	unsigned long long reserved2;	 /*				      */
-	unsigned long long progusage1;	 /* 48 - reserved for programming use */
-	unsigned long long progusage2;	 /*				      */
+	union {				 /* 48 - reserved for programming use */
+		struct {
+			unsigned int clock_base:1; /* in progusage2 */
+			unsigned long long progusage1:63;
+			unsigned long long progusage2;
+		};
+		unsigned long long progusage[2];
+	};
 } __packed;
 
 /* Load program parameter */
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index e07cce88dfb0..fcbd638fb9f4 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -9,6 +9,14 @@
 #ifndef _ASM_S390_GMAP_H
 #define _ASM_S390_GMAP_H
 
+/* Generic bits for GMAP notification on DAT table entry changes. */
+#define GMAP_NOTIFY_SHADOW	0x2
+#define GMAP_NOTIFY_MPROT	0x1
+
+/* Status bits only for huge segment entries */
+#define _SEGMENT_ENTRY_GMAP_IN		0x8000	/* invalidation notify bit */
+#define _SEGMENT_ENTRY_GMAP_UC		0x4000	/* dirty (migration) */
+
 /**
  * struct gmap_struct - guest address space
  * @list: list head for the mm->context gmap list
@@ -132,4 +140,6 @@ void gmap_pte_notify(struct mm_struct *, unsigned long addr, pte_t *,
 int gmap_mprotect_notify(struct gmap *, unsigned long start,
 			 unsigned long len, int prot);
 
+void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
+			     unsigned long gaddr, unsigned long vmaddr);
 #endif /* _ASM_S390_GMAP_H */
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 9c5fc50204dd..2d1afa58a4b6 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -37,7 +37,10 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-#define arch_clear_hugepage_flags(page)		do { } while (0)
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_arch_1, &page->flags);
+}
 
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep, unsigned long sz)
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 13de80cf741c..b106aa29bf55 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -68,8 +68,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_saved_imask;
 	unsigned long kprobe_saved_ctl[3];
 	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *p);
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 5bc888841eaf..406d940173ab 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -185,7 +185,7 @@ struct lowcore {
 	/* Transaction abort diagnostic block */
 	__u8	pgm_tdb[256];			/* 0x1800 */
 	__u8	pad_0x1900[0x2000-0x1900];	/* 0x1900 */
-} __packed;
+} __packed __aligned(8192);
 
 #define S390_lowcore (*((struct lowcore *) 0))
 
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index f5ff9dbad8ac..f31a15044c24 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -24,6 +24,8 @@ typedef struct {
 	unsigned int uses_skeys:1;
 	/* The mmu context uses CMM. */
 	unsigned int uses_cmm:1;
+	/* The gmaps associated with this context are allowed to use huge pages. */
+	unsigned int allow_gmap_hpage_1m:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index d16bc79c30bb..0717ee76885d 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -32,6 +32,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.has_pgste = 0;
 	mm->context.uses_skeys = 0;
 	mm->context.uses_cmm = 0;
+	mm->context.allow_gmap_hpage_1m = 0;
 #endif
 	switch (mm->context.asce_limit) {
 	case _REGION2_SIZE:
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
index a01f81186e86..123dac3717b3 100644
--- a/arch/s390/include/asm/nospec-insn.h
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -8,7 +8,7 @@
 
 #ifdef __ASSEMBLY__
 
-#ifdef CONFIG_EXPOLINE
+#ifdef CC_USING_EXPOLINE
 
 _LC_BR_R1 = __LC_BR_R1
 
@@ -189,7 +189,7 @@ _LC_BR_R1 = __LC_BR_R1
 	.macro BASR_EX rsave,rtarget,ruse=%r1
 	basr	\rsave,\rtarget
 	.endm
-#endif
+#endif /* CC_USING_EXPOLINE */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 94f8db468c9b..10fe982f2b4b 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -51,6 +51,10 @@ struct zpci_fmb_fmt2 {
 	u64 max_work_units;
 };
 
+struct zpci_fmb_fmt3 {
+	u64 tx_bytes;
+};
+
 struct zpci_fmb {
 	u32 format	: 8;
 	u32 fmt_ind	: 24;
@@ -66,6 +70,7 @@ struct zpci_fmb {
 		struct zpci_fmb_fmt0 fmt0;
 		struct zpci_fmb_fmt1 fmt1;
 		struct zpci_fmb_fmt2 fmt2;
+		struct zpci_fmb_fmt3 fmt3;
 	};
 } __packed __aligned(128);
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5ab636089c60..0e7cb0dc9c33 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -268,8 +268,10 @@ static inline int is_module_addr(void *addr)
 #define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL
 
 /* Bits in the segment table entry */
-#define _SEGMENT_ENTRY_BITS	0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_BITS			0xfffffffffffffe33UL
+#define _SEGMENT_ENTRY_BITS_LARGE		0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS		0xfffffffffffffe30UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE	0xfffffffffff00730UL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
 #define _SEGMENT_ENTRY_ORIGIN	~0x7ffUL/* page table origin		    */
 #define _SEGMENT_ENTRY_PROTECT	0x200	/* segment protection bit	    */
@@ -1101,7 +1103,8 @@ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
 		    pte_t *sptep, pte_t *tptep, pte_t pte);
 void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep);
 
-bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address);
+bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long address,
+			    pte_t *ptep);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq);
 int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
@@ -1116,6 +1119,10 @@ int set_pgste_bits(struct mm_struct *mm, unsigned long addr,
 int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep);
 int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 			unsigned long *oldpte, unsigned long *oldpgste);
+void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 
 /*
  * Certain architectures need to do special things when PTEs
diff --git a/arch/s390/include/asm/purgatory.h b/arch/s390/include/asm/purgatory.h
index 6090670df51f..e297bcfc476f 100644
--- a/arch/s390/include/asm/purgatory.h
+++ b/arch/s390/include/asm/purgatory.h
@@ -13,11 +13,5 @@
 
 int verify_sha256_digest(void);
 
-extern u64 kernel_entry;
-extern u64 kernel_type;
-
-extern u64 crash_start;
-extern u64 crash_size;
-
 #endif	/* __ASSEMBLY__ */
 #endif /* _S390_PURGATORY_H_ */
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index de11ecc99c7c..9c9970a5dfb1 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -262,7 +262,6 @@ struct qdio_outbuf_state {
 	void *user;
 };
 
-#define QDIO_OUTBUF_STATE_FLAG_NONE	0x00
 #define QDIO_OUTBUF_STATE_FLAG_PENDING	0x01
 
 #define CHSC_AC1_INITIATE_INPUTQ	0x80
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 54f81f8ed662..724faede8ac5 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -4,6 +4,4 @@
 
 #include <asm-generic/sections.h>
 
-extern char _ehead[];
-
 #endif
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 9c30ebe046f3..1d66016f4170 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -9,8 +9,10 @@
 #include <linux/const.h>
 #include <uapi/asm/setup.h>
 
-
+#define EP_OFFSET		0x10008
+#define EP_STRING		"S390EP"
 #define PARMAREA		0x10400
+#define PARMAREA_END		0x11000
 
 /*
  * Machine features detected in early.c
diff --git a/arch/s390/include/uapi/asm/chsc.h b/arch/s390/include/uapi/asm/chsc.h
index dc329aa03f76..83a574e95b3a 100644
--- a/arch/s390/include/uapi/asm/chsc.h
+++ b/arch/s390/include/uapi/asm/chsc.h
@@ -23,29 +23,29 @@ struct chsc_async_header {
 	__u32 key : 4;
 	__u32 : 28;
 	struct subchannel_id sid;
-} __attribute__ ((packed));
+};
 
 struct chsc_async_area {
 	struct chsc_async_header header;
 	__u8 data[CHSC_SIZE - sizeof(struct chsc_async_header)];
-} __attribute__ ((packed));
+};
 
 struct chsc_header {
 	__u16 length;
 	__u16 code;
-} __attribute__ ((packed));
+};
 
 struct chsc_sync_area {
 	struct chsc_header header;
 	__u8 data[CHSC_SIZE - sizeof(struct chsc_header)];
-} __attribute__ ((packed));
+};
 
 struct chsc_response_struct {
 	__u16 length;
 	__u16 code;
 	__u32 parms;
 	__u8 data[CHSC_SIZE - 2 * sizeof(__u16) - sizeof(__u32)];
-} __attribute__ ((packed));
+};
 
 struct chsc_chp_cd {
 	struct chp_id chpid;
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 2fed39b26b42..dbfd1730e631 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -9,39 +9,21 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o		= $(CC_FLAGS_FTRACE)
 
 # Do not trace early setup code
-CFLAGS_REMOVE_als.o		= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_early.o		= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_early_nobss.o	= $(CC_FLAGS_FTRACE)
 
 endif
 
-GCOV_PROFILE_als.o		:= n
 GCOV_PROFILE_early.o		:= n
 GCOV_PROFILE_early_nobss.o	:= n
 
-KCOV_INSTRUMENT_als.o		:= n
 KCOV_INSTRUMENT_early.o		:= n
 KCOV_INSTRUMENT_early_nobss.o	:= n
 
-UBSAN_SANITIZE_als.o		:= n
 UBSAN_SANITIZE_early.o		:= n
 UBSAN_SANITIZE_early_nobss.o	:= n
 
 #
-# Use -march=z900 for als.c to be able to print an error
-# message if the kernel is started on a machine which is too old
-#
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_EXPOLINE)
-CFLAGS_als.o		+= -march=z900
-AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
-AFLAGS_head.o		+= -march=z900
-endif
-
-CFLAGS_als.o		+= -D__NO_FORTIFY
-
-#
 # Passing null pointers is ok for smp code, since we access the lowcore here.
 #
 CFLAGS_smp.o		:= -Wno-nonnull
@@ -61,13 +43,13 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o early_nobss.o
+obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
 obj-y	+= nospec-branch.o
 
-extra-y				+= head.o head64.o vmlinux.lds
+extra-y				+= head64.o vmlinux.lds
 
 obj-$(CONFIG_SYSFS)		+= nospec-sysfs.o
 CFLAGS_REMOVE_nospec-branch.o	+= $(CC_FLAGS_EXPOLINE)
@@ -99,5 +81,5 @@ obj-$(CONFIG_TRACEPOINTS)	+= trace.o
 obj-y				+= vdso64/
 obj-$(CONFIG_COMPAT)		+= vdso32/
 
-chkbss := head.o head64.o als.o early_nobss.o
+chkbss := head64.o early_nobss.o
 include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index 607c5e9fba3d..2ce28bf0c5ec 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -183,3 +183,4 @@ COMPAT_SYSCALL_WRAP2(s390_guarded_storage, int, command, struct gs_cb *, gs_cb);
 COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
 COMPAT_SYSCALL_WRAP4(s390_sthyi, unsigned long, code, void __user *, info, u64 __user *, rc, unsigned long, flags);
 COMPAT_SYSCALL_WRAP5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags)
+COMPAT_SYSCALL_WRAP4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig)
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 9f5ea9d87069..c3620bafc374 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -306,6 +306,15 @@ static void *kzalloc_panic(int len)
 	return rc;
 }
 
+static const char *nt_name(Elf64_Word type)
+{
+	const char *name = "LINUX";
+
+	if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
+		name = KEXEC_CORE_NOTE_NAME;
+	return name;
+}
+
 /*
  * Initialize ELF note
  */
@@ -332,11 +341,26 @@ static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len,
 
 static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len)
 {
-	const char *note_name = "LINUX";
+	return nt_init_name(buf, type, desc, d_len, nt_name(type));
+}
+
+/*
+ * Calculate the size of ELF note
+ */
+static size_t nt_size_name(int d_len, const char *name)
+{
+	size_t size;
 
-	if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
-		note_name = KEXEC_CORE_NOTE_NAME;
-	return nt_init_name(buf, type, desc, d_len, note_name);
+	size = sizeof(Elf64_Nhdr);
+	size += roundup(strlen(name) + 1, 4);
+	size += roundup(d_len, 4);
+
+	return size;
+}
+
+static inline size_t nt_size(Elf64_Word type, int d_len)
+{
+	return nt_size_name(d_len, nt_name(type));
 }
 
 /*
@@ -375,6 +399,29 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa)
 }
 
 /*
+ * Calculate size of ELF notes per cpu
+ */
+static size_t get_cpu_elf_notes_size(void)
+{
+	struct save_area *sa = NULL;
+	size_t size;
+
+	size =	nt_size(NT_PRSTATUS, sizeof(struct elf_prstatus));
+	size +=  nt_size(NT_PRFPREG, sizeof(elf_fpregset_t));
+	size +=  nt_size(NT_S390_TIMER, sizeof(sa->timer));
+	size +=  nt_size(NT_S390_TODCMP, sizeof(sa->todcmp));
+	size +=  nt_size(NT_S390_TODPREG, sizeof(sa->todpreg));
+	size +=  nt_size(NT_S390_CTRS, sizeof(sa->ctrs));
+	size +=  nt_size(NT_S390_PREFIX, sizeof(sa->prefix));
+	if (MACHINE_HAS_VX) {
+		size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high));
+		size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low));
+	}
+
+	return size;
+}
+
+/*
  * Initialize prpsinfo note (new kernel)
  */
 static void *nt_prpsinfo(void *ptr)
@@ -429,6 +476,30 @@ static void *nt_vmcoreinfo(void *ptr)
 	return nt_init_name(ptr, 0, vmcoreinfo, size, "VMCOREINFO");
 }
 
+static size_t nt_vmcoreinfo_size(void)
+{
+	const char *name = "VMCOREINFO";
+	char nt_name[11];
+	Elf64_Nhdr note;
+	void *addr;
+
+	if (copy_oldmem_kernel(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
+		return 0;
+
+	if (copy_oldmem_kernel(&note, addr, sizeof(note)))
+		return 0;
+
+	memset(nt_name, 0, sizeof(nt_name));
+	if (copy_oldmem_kernel(nt_name, addr + sizeof(note),
+			       sizeof(nt_name) - 1))
+		return 0;
+
+	if (strcmp(nt_name, name) != 0)
+		return 0;
+
+	return nt_size_name(note.n_descsz, name);
+}
+
 /*
  * Initialize final note (needed for /proc/vmcore code)
  */
@@ -539,6 +610,27 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 	return ptr;
 }
 
+static size_t get_elfcorehdr_size(int mem_chunk_cnt)
+{
+	size_t size;
+
+	size = sizeof(Elf64_Ehdr);
+	/* PT_NOTES */
+	size += sizeof(Elf64_Phdr);
+	/* nt_prpsinfo */
+	size += nt_size(NT_PRPSINFO, sizeof(struct elf_prpsinfo));
+	/* regsets */
+	size += get_cpu_cnt() * get_cpu_elf_notes_size();
+	/* nt_vmcoreinfo */
+	size += nt_vmcoreinfo_size();
+	/* nt_final */
+	size += sizeof(Elf64_Nhdr);
+	/* PT_LOADS */
+	size += mem_chunk_cnt * sizeof(Elf64_Phdr);
+
+	return size;
+}
+
 /*
  * Create ELF core header (new kernel)
  */
@@ -566,8 +658,8 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 
 	mem_chunk_cnt = get_mem_chunk_cnt();
 
-	alloc_size = 0x1000 + get_cpu_cnt() * 0x4a0 +
-		mem_chunk_cnt * sizeof(Elf64_Phdr);
+	alloc_size = get_elfcorehdr_size(mem_chunk_cnt);
+
 	hdr = kzalloc_panic(alloc_size);
 	/* Init elf header */
 	ptr = ehdr_init(hdr, mem_chunk_cnt);
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 827699eb48fa..5b28b434f8a1 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -331,8 +331,20 @@ static void __init setup_boot_command_line(void)
 	append_to_cmdline(append_ipl_scpdata);
 }
 
+static void __init check_image_bootable(void)
+{
+	if (!memcmp(EP_STRING, (void *)EP_OFFSET, strlen(EP_STRING)))
+		return;
+
+	sclp_early_printk("Linux kernel boot failure: An attempt to boot a vmlinux ELF image failed.\n");
+	sclp_early_printk("This image does not contain all parts necessary for starting up. Use\n");
+	sclp_early_printk("bzImage or arch/s390/boot/compressed/vmlinux instead.\n");
+	disabled_wait(0xbadb007);
+}
+
 void __init startup_init(void)
 {
+	check_image_bootable();
 	time_early_init();
 	init_kernel_storage_key();
 	lockdep_off();
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index f03402efab4b..150130c897c3 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -357,6 +357,10 @@ ENTRY(system_call)
 	stg	%r2,__PT_R2(%r11)		# store return value
 
 .Lsysc_return:
+#ifdef CONFIG_DEBUG_RSEQ
+	lgr	%r2,%r11
+	brasl	%r14,rseq_syscall
+#endif
 	LOCKDEP_SYS_EXIT
 .Lsysc_tif:
 	TSTMSK	__PT_FLAGS(%r11),_PIF_WORK
@@ -1265,7 +1269,7 @@ cleanup_critical:
 	jl	0f
 	clg	%r9,BASED(.Lcleanup_table+104)	# .Lload_fpu_regs_end
 	jl	.Lcleanup_load_fpu_regs
-0:	BR_EX	%r14
+0:	BR_EX	%r14,%r11
 
 	.align	8
 .Lcleanup_table:
@@ -1301,7 +1305,7 @@ cleanup_critical:
 	ni	__SIE_PROG0C+3(%r9),0xfe	# no longer in SIE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	larl	%r9,sie_exit			# skip forward to sie_exit
-	BR_EX	%r14
+	BR_EX	%r14,%r11
 #endif
 
 .Lcleanup_system_call:
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 961abfac2c5f..472fa2f1a4a5 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -83,7 +83,6 @@ long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user
 
 DECLARE_PER_CPU(u64, mt_cycles[8]);
 
-void verify_facilities(void);
 void gs_load_bc_cb(struct pt_regs *regs);
 void set_fs_fixup(void);
 
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 791cb9000e86..6d14ad42ba88 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -48,11 +48,23 @@ ENTRY(startup_continue)
 # Early machine initialization and detection functions.
 #
 	brasl	%r14,startup_init
-	lpswe	.Lentry-.LPG1(13)	# jump to _stext in primary-space,
-					# virtual and never return ...
+
+# check control registers
+	stctg	%c0,%c15,0(%r15)
+	oi	6(%r15),0x60		# enable sigp emergency & external call
+	oi	4(%r15),0x10		# switch on low address proctection
+	lctlg	%c0,%c15,0(%r15)
+
+	lam	0,15,.Laregs-.LPG1(%r13)	# load acrs needed by uaccess
+	brasl	%r14,start_kernel		# go to C code
+#
+# We returned from start_kernel ?!? PANIK
+#
+	basr	%r13,0
+	lpswe	.Ldw-.(%r13)		# load disabled wait psw
+
 	.align	16
 .LPG1:
-.Lentry:.quad	0x0000000180000000,_stext
 .Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
 	.quad	0			# cr1: primary space segment table
 	.quad	.Lduct			# cr2: dispatchable unit control table
@@ -85,30 +97,5 @@ ENTRY(startup_continue)
 	.endr
 .Llinkage_stack:
 	.long	0,0,0x89000000,0,0,0,0x8a000000,0
-
-ENTRY(_ehead)
-
-	.org	0x100000 - 0x11000	# head.o ends at 0x11000
-#
-# startup-code, running in absolute addressing mode
-#
-ENTRY(_stext)
-	basr	%r13,0			# get base
-.LPG3:
-# check control registers
-	stctg	%c0,%c15,0(%r15)
-	oi	6(%r15),0x60		# enable sigp emergency & external call
-	oi	4(%r15),0x10		# switch on low address proctection
-	lctlg	%c0,%c15,0(%r15)
-
-	lam	0,15,.Laregs-.LPG3(%r13)	# load acrs needed by uaccess
-	brasl	%r14,start_kernel	# go to C code
-#
-# We returned from start_kernel ?!? PANIK
-#
-	basr	%r13,0
-	lpswe	.Ldw-.(%r13)		# load disabled wait psw
-
-	.align	8
 .Ldw:	.quad	0x0002000180000000,0x0000000000000000
 .Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 60f60afa645c..7c0a095e9c5f 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -321,38 +321,20 @@ static int kprobe_handler(struct pt_regs *regs)
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with single stepping. If we have a
 			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry
-			 * for jprobe processing, so get out doing nothing
-			 * more here.
+			 * for changing execution path, so get out doing
+			 * nothing more here.
 			 */
 			push_kprobe(kcb, p);
 			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-			if (p->pre_handler && p->pre_handler(p, regs))
+			if (p->pre_handler && p->pre_handler(p, regs)) {
+				pop_kprobe(kcb);
+				preempt_enable_no_resched();
 				return 1;
+			}
 			kcb->kprobe_status = KPROBE_HIT_SS;
 		}
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			/*
-			 * Continuation after the jprobe completed and
-			 * caused the jprobe_return trap. The jprobe
-			 * break_handler "returns" to the original
-			 * function that still has the kprobe breakpoint
-			 * installed. We continue with single stepping.
-			 */
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			enable_singlestep(kcb, regs,
-					  (unsigned long) p->ainsn.insn);
-			return 1;
-		} /* else:
-		   * No kprobe at this address and the current kprobe
-		   * has no break handler (no jprobe!). The kernel just
-		   * exploded, let the standard trap handler pick up the
-		   * pieces.
-		   */
 	} /* else:
 	   * No kprobe at this address and no active kprobe. The trap has
 	   * not been caused by a kprobe breakpoint. The race of breakpoint
@@ -452,9 +434,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 
 	regs->psw.addr = orig_ret_address;
 
-	pop_kprobe(get_kprobe_ctlblk());
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
@@ -661,60 +641,6 @@ int kprobe_exceptions_notify(struct notifier_block *self,
 }
 NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack;
-
-	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
-	/* setup return addr to the jprobe handler routine */
-	regs->psw.addr = (unsigned long) jp->entry;
-	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
-
-	/* r15 is the stack pointer */
-	stack = (unsigned long) regs->gprs[15];
-
-	memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack));
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer to get messed up.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void jprobe_return(void)
-{
-	asm volatile(".word 0x0002");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack;
-
-	/* It's OK to start function graph tracing again */
-	unpause_graph_tracing();
-
-	stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15];
-
-	/* Put the regs back */
-	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
-	/* put the stack back */
-	memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack));
-	preempt_enable_no_resched();
-	return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 static struct kprobe trampoline = {
 	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index 18ae7b9c71d6..bdddaae96559 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -35,6 +35,8 @@ early_param("nospec", nospec_setup_early);
 
 static int __init nospec_report(void)
 {
+	if (test_facility(156))
+		pr_info("Spectre V2 mitigation: etokens\n");
 	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
 		pr_info("Spectre V2 mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
@@ -56,7 +58,15 @@ early_param("nospectre_v2", nospectre_v2_setup_early);
 
 void __init nospec_auto_detect(void)
 {
-	if (IS_ENABLED(CC_USING_EXPOLINE)) {
+	if (test_facility(156)) {
+		/*
+		 * The machine supports etokens.
+		 * Disable expolines and disable nobp.
+		 */
+		if (IS_ENABLED(CC_USING_EXPOLINE))
+			nospec_disable = 1;
+		__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+	} else if (IS_ENABLED(CC_USING_EXPOLINE)) {
 		/*
 		 * The kernel has been compiled with expolines.
 		 * Keep expolines enabled and disable nobp.
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
index 8affad5f18cb..e30e580ae362 100644
--- a/arch/s390/kernel/nospec-sysfs.c
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -13,6 +13,8 @@ ssize_t cpu_show_spectre_v1(struct device *dev,
 ssize_t cpu_show_spectre_v2(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
+	if (test_facility(156))
+		return sprintf(buf, "Mitigation: etokens\n");
 	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
 		return sprintf(buf, "Mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 0292d68e7dde..cb198d4a6dca 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -2,7 +2,7 @@
 /*
  * Performance event support for the System z CPU-measurement Sampling Facility
  *
- * Copyright IBM Corp. 2013
+ * Copyright IBM Corp. 2013, 2018
  * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
 #define KMSG_COMPONENT	"cpum_sf"
@@ -1587,6 +1587,17 @@ static void aux_buffer_free(void *data)
 			    "%lu SDBTs\n", num_sdbt);
 }
 
+static void aux_sdb_init(unsigned long sdb)
+{
+	struct hws_trailer_entry *te;
+
+	te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb);
+
+	/* Save clock base */
+	te->clock_base = 1;
+	memcpy(&te->progusage2, &tod_clock_base[1], 8);
+}
+
 /*
  * aux_buffer_setup() - Setup AUX buffer for diagnostic mode sampling
  * @cpu:	On which to allocate, -1 means current
@@ -1666,6 +1677,7 @@ static void *aux_buffer_setup(int cpu, void **pages, int nr_pages,
 		/* Tail is the entry in a SDBT */
 		*tail = (unsigned long)pages[i];
 		aux->sdb_index[i] = (unsigned long)pages[i];
+		aux_sdb_init((unsigned long)pages[i]);
 	}
 	sfb->num_sdb = nr_pages;
 
diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index 54e2d634b849..4352a504f235 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -12,9 +12,6 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
 	freg_t fp;
 
-	if (WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX))
-		return 0;
-
 	if (idx >= PERF_REG_S390_R0 && idx <= PERF_REG_S390_R15)
 		return regs->gprs[idx];
 
@@ -33,7 +30,8 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	if (idx == PERF_REG_S390_PC)
 		return regs->psw.addr;
 
-	return regs->gprs[idx];
+	WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX);
+	return 0;
 }
 
 #define REG_RESERVED (~((1UL << PERF_REG_S390_MAX) - 1))
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index d82a9ec64ea9..c637c12f9e37 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -674,12 +674,12 @@ static void __init reserve_kernel(void)
 #ifdef CONFIG_DMA_API_DEBUG
 	/*
 	 * DMA_API_DEBUG code stumbles over addresses from the
-	 * range [_ehead, _stext]. Mark the memory as reserved
+	 * range [PARMAREA_END, _stext]. Mark the memory as reserved
 	 * so it is not used for CONFIG_DMA_API_DEBUG=y.
 	 */
 	memblock_reserve(0, PFN_PHYS(start_pfn));
 #else
-	memblock_reserve(0, (unsigned long)_ehead);
+	memblock_reserve(0, PARMAREA_END);
 	memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
 			 - (unsigned long)_stext);
 #endif
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 2d2960ab3e10..22f08245aa5d 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -498,7 +498,7 @@ void do_signal(struct pt_regs *regs)
 		}
 		/* No longer in a system call */
 		clear_pt_regs_flag(regs, PIF_SYSCALL);
-
+		rseq_signal_deliver(&ksig, regs);
 		if (is_compat_task())
 			handle_signal32(&ksig, oldset, regs);
 		else
@@ -537,4 +537,5 @@ void do_notify_resume(struct pt_regs *regs)
 {
 	clear_thread_flag(TIF_NOTIFY_RESUME);
 	tracehook_notify_resume(regs);
+	rseq_handle_notify_resume(NULL, regs);
 }
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 8b210ead7956..022fc099b628 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -389,3 +389,5 @@
 379  common	statx			sys_statx			compat_sys_statx
 380  common	s390_sthyi		sys_s390_sthyi			compat_sys_s390_sthyi
 381  common	kexec_file_load		sys_kexec_file_load		compat_sys_kexec_file_load
+382  common	io_pgetevents		sys_io_pgetevents		compat_sys_io_pgetevents
+383  common	rseq			sys_rseq			compat_sys_rseq
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 54f5496913fa..12f80d1f0415 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -59,6 +59,8 @@ int stsi(void *sysinfo, int fc, int sel1, int sel2)
 }
 EXPORT_SYMBOL(stsi);
 
+#ifdef CONFIG_PROC_FS
+
 static bool convert_ext_name(unsigned char encoding, char *name, size_t len)
 {
 	switch (encoding) {
@@ -301,6 +303,8 @@ static int __init sysinfo_create_proc(void)
 }
 device_initcall(sysinfo_create_proc);
 
+#endif /* CONFIG_PROC_FS */
+
 /*
  * Service levels interface.
  */
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index cf561160ea88..e8766beee5ad 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -221,17 +221,22 @@ void read_persistent_clock64(struct timespec64 *ts)
 	ext_to_timespec64(clk, ts);
 }
 
-void read_boot_clock64(struct timespec64 *ts)
+void __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+						 struct timespec64 *boot_offset)
 {
 	unsigned char clk[STORE_CLOCK_EXT_SIZE];
+	struct timespec64 boot_time;
 	__u64 delta;
 
 	delta = initial_leap_seconds + TOD_UNIX_EPOCH;
-	memcpy(clk, tod_clock_base, 16);
-	*(__u64 *) &clk[1] -= delta;
-	if (*(__u64 *) &clk[1] > delta)
+	memcpy(clk, tod_clock_base, STORE_CLOCK_EXT_SIZE);
+	*(__u64 *)&clk[1] -= delta;
+	if (*(__u64 *)&clk[1] > delta)
 		clk[0]--;
-	ext_to_timespec64(clk, ts);
+	ext_to_timespec64(clk, &boot_time);
+
+	read_persistent_clock64(wall_time);
+	*boot_offset = timespec64_sub(*wall_time, boot_time);
 }
 
 static u64 read_tod_clock(struct clocksource *cs)
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 4b6e0397f66d..e8184a15578a 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -579,41 +579,33 @@ early_param("topology", topology_setup);
 static int topology_ctl_handler(struct ctl_table *ctl, int write,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	unsigned int len;
+	int enabled = topology_is_enabled();
 	int new_mode;
-	char buf[2];
+	int zero = 0;
+	int one = 1;
+	int rc;
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &enabled,
+		.maxlen		= sizeof(int),
+		.extra1		= &zero,
+		.extra2		= &one,
+	};
+
+	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
-		return 0;
-	}
-	if (!write) {
-		strncpy(buf, topology_is_enabled() ? "1\n" : "0\n",
-			ARRAY_SIZE(buf));
-		len = strnlen(buf, ARRAY_SIZE(buf));
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
-		return -EFAULT;
-	if (buf[0] != '0' && buf[0] != '1')
-		return -EINVAL;
 	mutex_lock(&smp_cpu_state_mutex);
-	new_mode = topology_get_mode(buf[0] == '1');
+	new_mode = topology_get_mode(enabled);
 	if (topology_mode != new_mode) {
 		topology_mode = new_mode;
 		topology_schedule_update();
 	}
 	mutex_unlock(&smp_cpu_state_mutex);
 	topology_flush_work();
-out:
-	*lenp = len;
-	*ppos += len;
-	return 0;
+
+	return rc;
 }
 
 static struct ctl_table topology_ctl_table[] = {
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 09abae40f917..3031cc6dd0ab 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -47,7 +47,7 @@ static struct page **vdso64_pagelist;
  */
 unsigned int __read_mostly vdso_enabled = 1;
 
-static int vdso_fault(const struct vm_special_mapping *sm,
+static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
 		      struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct page **vdso_pagelist;
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index f0414f52817b..b43f8d33a369 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -19,7 +19,7 @@
 
 OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
 OUTPUT_ARCH(s390:64-bit)
-ENTRY(startup)
+ENTRY(startup_continue)
 jiffies = jiffies_64;
 
 PHDRS {
@@ -30,16 +30,12 @@ PHDRS {
 
 SECTIONS
 {
-	. = 0x00000000;
+	. = 0x100000;
+	_stext = .;		/* Start of text section */
 	.text : {
 		/* Text and read-only data */
+		_text = .;
 		HEAD_TEXT
-		/*
-		 * E.g. perf doesn't like symbols starting at address zero,
-		 * therefore skip the initial PSW and channel program located
-		 * at address zero and let _text start at 0x200.
-		 */
-	_text = 0x200;
 		TEXT_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT
@@ -47,6 +43,7 @@ SECTIONS
 		KPROBES_TEXT
 		IRQENTRY_TEXT
 		SOFTIRQENTRY_TEXT
+		*(.text.*_indirect_*)
 		*(.fixup)
 		*(.gnu.warning)
 	} :text = 0x0700
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index daa09f89ca2d..fcb55b02990e 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1145,7 +1145,7 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 		 * yield-candidate.
 		 */
 		vcpu->preempted = true;
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
 	}
 	/*
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 3b7a5151b6a5..f9d90337e64a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -172,6 +172,10 @@ static int nested;
 module_param(nested, int, S_IRUGO);
 MODULE_PARM_DESC(nested, "Nested virtualization support");
 
+/* allow 1m huge page guest backing, if !nested */
+static int hpage;
+module_param(hpage, int, 0444);
+MODULE_PARM_DESC(hpage, "1m huge page backing support");
 
 /*
  * For now we handle at most 16 double words as this is what the s390 base
@@ -475,6 +479,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_AIS_MIGRATION:
 		r = 1;
 		break;
+	case KVM_CAP_S390_HPAGE_1M:
+		r = 0;
+		if (hpage)
+			r = 1;
+		break;
 	case KVM_CAP_S390_MEM_OP:
 		r = MEM_OP_MAX_SIZE;
 		break;
@@ -511,19 +520,30 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 }
 
 static void kvm_s390_sync_dirty_log(struct kvm *kvm,
-					struct kvm_memory_slot *memslot)
+				    struct kvm_memory_slot *memslot)
 {
+	int i;
 	gfn_t cur_gfn, last_gfn;
-	unsigned long address;
+	unsigned long gaddr, vmaddr;
 	struct gmap *gmap = kvm->arch.gmap;
+	DECLARE_BITMAP(bitmap, _PAGE_ENTRIES);
 
-	/* Loop over all guest pages */
+	/* Loop over all guest segments */
+	cur_gfn = memslot->base_gfn;
 	last_gfn = memslot->base_gfn + memslot->npages;
-	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
-		address = gfn_to_hva_memslot(memslot, cur_gfn);
+	for (; cur_gfn <= last_gfn; cur_gfn += _PAGE_ENTRIES) {
+		gaddr = gfn_to_gpa(cur_gfn);
+		vmaddr = gfn_to_hva_memslot(memslot, cur_gfn);
+		if (kvm_is_error_hva(vmaddr))
+			continue;
+
+		bitmap_zero(bitmap, _PAGE_ENTRIES);
+		gmap_sync_dirty_log_pmd(gmap, bitmap, gaddr, vmaddr);
+		for (i = 0; i < _PAGE_ENTRIES; i++) {
+			if (test_bit(i, bitmap))
+				mark_page_dirty(kvm, cur_gfn + i);
+		}
 
-		if (test_and_clear_guest_dirty(gmap->mm, address))
-			mark_page_dirty(kvm, cur_gfn);
 		if (fatal_signal_pending(current))
 			return;
 		cond_resched();
@@ -667,6 +687,27 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_GS %s",
 			 r ? "(not available)" : "(success)");
 		break;
+	case KVM_CAP_S390_HPAGE_1M:
+		mutex_lock(&kvm->lock);
+		if (kvm->created_vcpus)
+			r = -EBUSY;
+		else if (!hpage || kvm->arch.use_cmma)
+			r = -EINVAL;
+		else {
+			r = 0;
+			kvm->mm->context.allow_gmap_hpage_1m = 1;
+			/*
+			 * We might have to create fake 4k page
+			 * tables. To avoid that the hardware works on
+			 * stale PGSTEs, we emulate these instructions.
+			 */
+			kvm->arch.use_skf = 0;
+			kvm->arch.use_pfmfi = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s",
+			 r ? "(not available)" : "(success)");
+		break;
 	case KVM_CAP_S390_USER_STSI:
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
 		kvm->arch.user_stsi = 1;
@@ -714,10 +755,13 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		if (!sclp.has_cmma)
 			break;
 
-		ret = -EBUSY;
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
 		mutex_lock(&kvm->lock);
-		if (!kvm->created_vcpus) {
+		if (kvm->created_vcpus)
+			ret = -EBUSY;
+		else if (kvm->mm->context.allow_gmap_hpage_1m)
+			ret = -EINVAL;
+		else {
 			kvm->arch.use_cmma = 1;
 			/* Not compatible with cmma. */
 			kvm->arch.use_pfmfi = 0;
@@ -1540,6 +1584,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	uint8_t *keys;
 	uint64_t hva;
 	int srcu_idx, i, r = 0;
+	bool unlocked;
 
 	if (args->flags != 0)
 		return -EINVAL;
@@ -1564,9 +1609,11 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	if (r)
 		goto out;
 
+	i = 0;
 	down_read(&current->mm->mmap_sem);
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	for (i = 0; i < args->count; i++) {
+        while (i < args->count) {
+		unlocked = false;
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
 		if (kvm_is_error_hva(hva)) {
 			r = -EFAULT;
@@ -1580,8 +1627,14 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 		}
 
 		r = set_guest_storage_key(current->mm, hva, keys[i], 0);
-		if (r)
-			break;
+		if (r) {
+			r = fixup_user_fault(current, current->mm, hva,
+					     FAULT_FLAG_WRITE, &unlocked);
+			if (r)
+				break;
+		}
+		if (!r)
+			i++;
 	}
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	up_read(&current->mm->mmap_sem);
@@ -4082,6 +4135,11 @@ static int __init kvm_s390_init(void)
 		return -ENODEV;
 	}
 
+	if (nested && hpage) {
+		pr_info("nested (vSIE) and hpage (huge page backing) can currently not be activated concurrently");
+		return -EINVAL;
+	}
+
 	for (i = 0; i < 16; i++)
 		kvm_s390_fac_base[i] |=
 			S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index eb0eb60c7be6..cfc5a62329f6 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -246,9 +246,10 @@ static int try_handle_skey(struct kvm_vcpu *vcpu)
 
 static int handle_iske(struct kvm_vcpu *vcpu)
 {
-	unsigned long addr;
+	unsigned long gaddr, vmaddr;
 	unsigned char key;
 	int reg1, reg2;
+	bool unlocked;
 	int rc;
 
 	vcpu->stat.instruction_iske++;
@@ -262,18 +263,28 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
-	addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
-	addr = kvm_s390_logical_to_effective(vcpu, addr);
-	addr = kvm_s390_real_to_abs(vcpu, addr);
-	addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
-	if (kvm_is_error_hva(addr))
+	gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	gaddr = kvm_s390_logical_to_effective(vcpu, gaddr);
+	gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
+	vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr));
+	if (kvm_is_error_hva(vmaddr))
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+retry:
+	unlocked = false;
 	down_read(&current->mm->mmap_sem);
-	rc = get_guest_storage_key(current->mm, addr, &key);
-	up_read(&current->mm->mmap_sem);
+	rc = get_guest_storage_key(current->mm, vmaddr, &key);
+
+	if (rc) {
+		rc = fixup_user_fault(current, current->mm, vmaddr,
+				      FAULT_FLAG_WRITE, &unlocked);
+		if (!rc) {
+			up_read(&current->mm->mmap_sem);
+			goto retry;
+		}
+	}
 	if (rc)
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	up_read(&current->mm->mmap_sem);
 	vcpu->run->s.regs.gprs[reg1] &= ~0xff;
 	vcpu->run->s.regs.gprs[reg1] |= key;
 	return 0;
@@ -281,8 +292,9 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 
 static int handle_rrbe(struct kvm_vcpu *vcpu)
 {
-	unsigned long addr;
+	unsigned long vmaddr, gaddr;
 	int reg1, reg2;
+	bool unlocked;
 	int rc;
 
 	vcpu->stat.instruction_rrbe++;
@@ -296,19 +308,27 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
 
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
-	addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
-	addr = kvm_s390_logical_to_effective(vcpu, addr);
-	addr = kvm_s390_real_to_abs(vcpu, addr);
-	addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
-	if (kvm_is_error_hva(addr))
+	gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	gaddr = kvm_s390_logical_to_effective(vcpu, gaddr);
+	gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
+	vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr));
+	if (kvm_is_error_hva(vmaddr))
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+retry:
+	unlocked = false;
 	down_read(&current->mm->mmap_sem);
-	rc = reset_guest_reference_bit(current->mm, addr);
-	up_read(&current->mm->mmap_sem);
+	rc = reset_guest_reference_bit(current->mm, vmaddr);
+	if (rc < 0) {
+		rc = fixup_user_fault(current, current->mm, vmaddr,
+				      FAULT_FLAG_WRITE, &unlocked);
+		if (!rc) {
+			up_read(&current->mm->mmap_sem);
+			goto retry;
+		}
+	}
 	if (rc < 0)
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+	up_read(&current->mm->mmap_sem);
 	kvm_s390_set_psw_cc(vcpu, rc);
 	return 0;
 }
@@ -323,6 +343,7 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 	unsigned long start, end;
 	unsigned char key, oldkey;
 	int reg1, reg2;
+	bool unlocked;
 	int rc;
 
 	vcpu->stat.instruction_sske++;
@@ -355,19 +376,28 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 	}
 
 	while (start != end) {
-		unsigned long addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+		unsigned long vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+		unlocked = false;
 
-		if (kvm_is_error_hva(addr))
+		if (kvm_is_error_hva(vmaddr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 		down_read(&current->mm->mmap_sem);
-		rc = cond_set_guest_storage_key(current->mm, addr, key, &oldkey,
+		rc = cond_set_guest_storage_key(current->mm, vmaddr, key, &oldkey,
 						m3 & SSKE_NQ, m3 & SSKE_MR,
 						m3 & SSKE_MC);
-		up_read(&current->mm->mmap_sem);
-		if (rc < 0)
+
+		if (rc < 0) {
+			rc = fixup_user_fault(current, current->mm, vmaddr,
+					      FAULT_FLAG_WRITE, &unlocked);
+			rc = !rc ? -EAGAIN : rc;
+		}
+		if (rc == -EFAULT)
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		start += PAGE_SIZE;
+
+		up_read(&current->mm->mmap_sem);
+		if (rc >= 0)
+			start += PAGE_SIZE;
 	}
 
 	if (m3 & (SSKE_MC | SSKE_MR)) {
@@ -948,15 +978,16 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 	}
 
 	while (start != end) {
-		unsigned long useraddr;
+		unsigned long vmaddr;
+		bool unlocked = false;
 
 		/* Translate guest address to host address */
-		useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
-		if (kvm_is_error_hva(useraddr))
+		vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+		if (kvm_is_error_hva(vmaddr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 		if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
-			if (clear_user((void __user *)useraddr, PAGE_SIZE))
+			if (clear_user((void __user *)vmaddr, PAGE_SIZE))
 				return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 		}
 
@@ -966,14 +997,20 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 			if (rc)
 				return rc;
 			down_read(&current->mm->mmap_sem);
-			rc = cond_set_guest_storage_key(current->mm, useraddr,
+			rc = cond_set_guest_storage_key(current->mm, vmaddr,
 							key, NULL, nq, mr, mc);
-			up_read(&current->mm->mmap_sem);
-			if (rc < 0)
+			if (rc < 0) {
+				rc = fixup_user_fault(current, current->mm, vmaddr,
+						      FAULT_FLAG_WRITE, &unlocked);
+				rc = !rc ? -EAGAIN : rc;
+			}
+			if (rc == -EFAULT)
 				return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		}
 
-		start += PAGE_SIZE;
+			up_read(&current->mm->mmap_sem);
+			if (rc >= 0)
+				start += PAGE_SIZE;
+		}
 	}
 	if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
 		if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) {
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 2311f15be9cf..40c4d59c926e 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -17,7 +17,7 @@
 ENTRY(memmove)
 	ltgr	%r4,%r4
 	lgr	%r1,%r2
-	bzr	%r14
+	jz	.Lmemmove_exit
 	aghi	%r4,-1
 	clgr	%r2,%r3
 	jnh	.Lmemmove_forward
@@ -36,6 +36,7 @@ ENTRY(memmove)
 .Lmemmove_forward_remainder:
 	larl	%r5,.Lmemmove_mvc
 	ex	%r4,0(%r5)
+.Lmemmove_exit:
 	BR_EX	%r14
 .Lmemmove_reverse:
 	ic	%r0,0(%r4,%r3)
@@ -65,7 +66,7 @@ EXPORT_SYMBOL(memmove)
  */
 ENTRY(memset)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.Lmemset_exit
 	ltgr	%r3,%r3
 	jnz	.Lmemset_fill
 	aghi	%r4,-1
@@ -80,6 +81,7 @@ ENTRY(memset)
 .Lmemset_clear_remainder:
 	larl	%r3,.Lmemset_xc
 	ex	%r4,0(%r3)
+.Lmemset_exit:
 	BR_EX	%r14
 .Lmemset_fill:
 	cghi	%r4,1
@@ -115,7 +117,7 @@ EXPORT_SYMBOL(memset)
  */
 ENTRY(memcpy)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.Lmemcpy_exit
 	aghi	%r4,-1
 	srlg	%r5,%r4,8
 	ltgr	%r5,%r5
@@ -124,6 +126,7 @@ ENTRY(memcpy)
 .Lmemcpy_remainder:
 	larl	%r5,.Lmemcpy_mvc
 	ex	%r4,0(%r5)
+.Lmemcpy_exit:
 	BR_EX	%r14
 .Lmemcpy_loop:
 	mvc	0(256,%r1),0(%r3)
@@ -145,9 +148,9 @@ EXPORT_SYMBOL(memcpy)
 .macro __MEMSET bits,bytes,insn
 ENTRY(__memset\bits)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.L__memset_exit\bits
 	cghi	%r4,\bytes
-	je	.L__memset_exit\bits
+	je	.L__memset_store\bits
 	aghi	%r4,-(\bytes+1)
 	srlg	%r5,%r4,8
 	ltgr	%r5,%r5
@@ -163,8 +166,9 @@ ENTRY(__memset\bits)
 	larl	%r5,.L__memset_mvc\bits
 	ex	%r4,0(%r5)
 	BR_EX	%r14
-.L__memset_exit\bits:
+.L__memset_store\bits:
 	\insn	%r3,0(%r2)
+.L__memset_exit\bits:
 	BR_EX	%r14
 .L__memset_mvc\bits:
 	mvc	\bytes(1,%r1),0(%r1)
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 6cf024eb2085..510a18299196 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -191,12 +191,7 @@ static void cmm_set_timer(void)
 			del_timer(&cmm_timer);
 		return;
 	}
-	if (timer_pending(&cmm_timer)) {
-		if (mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds*HZ))
-			return;
-	}
-	cmm_timer.expires = jiffies + cmm_timeout_seconds*HZ;
-	add_timer(&cmm_timer);
+	mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds * HZ);
 }
 
 static void cmm_timer_fn(struct timer_list *unused)
@@ -251,45 +246,42 @@ static int cmm_skip_blanks(char *cp, char **endp)
 	return str != cp;
 }
 
-static struct ctl_table cmm_table[];
-
 static int cmm_pages_handler(struct ctl_table *ctl, int write,
 			     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	char buf[16], *p;
-	unsigned int len;
-	long nr;
+	long nr = cmm_get_pages();
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &nr,
+		.maxlen		= sizeof(long),
+	};
+	int rc;
 
-	if (!*lenp || (*ppos && !write)) {
-		*lenp = 0;
-		return 0;
-	}
+	rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
-	if (write) {
-		len = *lenp;
-		if (copy_from_user(buf, buffer,
-				   len > sizeof(buf) ? sizeof(buf) : len))
-			return -EFAULT;
-		buf[sizeof(buf) - 1] = '\0';
-		cmm_skip_blanks(buf, &p);
-		nr = simple_strtoul(p, &p, 0);
-		if (ctl == &cmm_table[0])
-			cmm_set_pages(nr);
-		else
-			cmm_add_timed_pages(nr);
-	} else {
-		if (ctl == &cmm_table[0])
-			nr = cmm_get_pages();
-		else
-			nr = cmm_get_timed_pages();
-		len = sprintf(buf, "%ld\n", nr);
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-	}
-	*lenp = len;
-	*ppos += len;
+	cmm_set_pages(nr);
+	return 0;
+}
+
+static int cmm_timed_pages_handler(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	long nr = cmm_get_timed_pages();
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &nr,
+		.maxlen		= sizeof(long),
+	};
+	int rc;
+
+	rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
+
+	cmm_add_timed_pages(nr);
 	return 0;
 }
 
@@ -338,7 +330,7 @@ static struct ctl_table cmm_table[] = {
 	{
 		.procname	= "cmm_timed_pages",
 		.mode		= 0644,
-		.proc_handler	= cmm_pages_handler,
+		.proc_handler	= cmm_timed_pages_handler,
 	},
 	{
 		.procname	= "cmm_timeout",
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 6ad15d3fab81..84111a43ea29 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -80,7 +80,7 @@ struct qin64 {
 struct dcss_segment {
 	struct list_head list;
 	char dcss_name[8];
-	char res_name[15];
+	char res_name[16];
 	unsigned long start_addr;
 	unsigned long end;
 	atomic_t ref_count;
@@ -433,7 +433,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 	memcpy(&seg->res_name, seg->dcss_name, 8);
 	EBCASC(seg->res_name, 8);
 	seg->res_name[8] = '\0';
-	strncat(seg->res_name, " (DCSS)", 7);
+	strlcat(seg->res_name, " (DCSS)", sizeof(seg->res_name));
 	seg->res->name = seg->res_name;
 	rc = seg->vm_segtype;
 	if (rc == SEG_TYPE_SC ||
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index e074480d3598..4cc3f06b0ab3 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -502,6 +502,8 @@ retry:
 	/* No reason to continue if interrupted by SIGKILL. */
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
 		fault = VM_FAULT_SIGNAL;
+		if (flags & FAULT_FLAG_RETRY_NOWAIT)
+			goto out_up;
 		goto out;
 	}
 	if (unlikely(fault & VM_FAULT_ERROR))
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index bc56ec8abcf7..bb44990c8212 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2,8 +2,10 @@
 /*
  *  KVM guest address space mapping code
  *
- *    Copyright IBM Corp. 2007, 2016
+ *    Copyright IBM Corp. 2007, 2016, 2018
  *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *		 David Hildenbrand <david@redhat.com>
+ *		 Janosch Frank <frankja@linux.vnet.ibm.com>
  */
 
 #include <linux/kernel.h>
@@ -521,6 +523,9 @@ void gmap_unlink(struct mm_struct *mm, unsigned long *table,
 	rcu_read_unlock();
 }
 
+static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *old, pmd_t new,
+			   unsigned long gaddr);
+
 /**
  * gmap_link - set up shadow page tables to connect a host to a guest address
  * @gmap: pointer to guest mapping meta data structure
@@ -541,6 +546,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
+	u64 unprot;
 	int rc;
 
 	BUG_ON(gmap_is_shadow(gmap));
@@ -584,8 +590,8 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 		return -EFAULT;
 	pmd = pmd_offset(pud, vmaddr);
 	VM_BUG_ON(pmd_none(*pmd));
-	/* large pmds cannot yet be handled */
-	if (pmd_large(*pmd))
+	/* Are we allowed to use huge pages? */
+	if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m)
 		return -EFAULT;
 	/* Link gmap segment table entry location to page table. */
 	rc = radix_tree_preload(GFP_KERNEL);
@@ -596,10 +602,22 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	if (*table == _SEGMENT_ENTRY_EMPTY) {
 		rc = radix_tree_insert(&gmap->host_to_guest,
 				       vmaddr >> PMD_SHIFT, table);
-		if (!rc)
-			*table = pmd_val(*pmd);
-	} else
-		rc = 0;
+		if (!rc) {
+			if (pmd_large(*pmd)) {
+				*table = (pmd_val(*pmd) &
+					  _SEGMENT_ENTRY_HARDWARE_BITS_LARGE)
+					| _SEGMENT_ENTRY_GMAP_UC;
+			} else
+				*table = pmd_val(*pmd) &
+					_SEGMENT_ENTRY_HARDWARE_BITS;
+		}
+	} else if (*table & _SEGMENT_ENTRY_PROTECT &&
+		   !(pmd_val(*pmd) & _SEGMENT_ENTRY_PROTECT)) {
+		unprot = (u64)*table;
+		unprot &= ~_SEGMENT_ENTRY_PROTECT;
+		unprot |= _SEGMENT_ENTRY_GMAP_UC;
+		gmap_pmdp_xchg(gmap, (pmd_t *)table, __pmd(unprot), gaddr);
+	}
 	spin_unlock(&gmap->guest_table_lock);
 	spin_unlock(ptl);
 	radix_tree_preload_end();
@@ -690,6 +708,12 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
 		vmaddr |= gaddr & ~PMD_MASK;
 		/* Find vma in the parent mm */
 		vma = find_vma(gmap->mm, vmaddr);
+		/*
+		 * We do not discard pages that are backed by
+		 * hugetlbfs, so we don't have to refault them.
+		 */
+		if (vma && is_vm_hugetlb_page(vma))
+			continue;
 		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
 		zap_page_range(vma, vmaddr, size);
 	}
@@ -864,7 +888,128 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
  */
 static void gmap_pte_op_end(spinlock_t *ptl)
 {
-	spin_unlock(ptl);
+	if (ptl)
+		spin_unlock(ptl);
+}
+
+/**
+ * gmap_pmd_op_walk - walk the gmap tables, get the guest table lock
+ *		      and return the pmd pointer
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ *
+ * Returns a pointer to the pmd for a guest address, or NULL
+ */
+static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr)
+{
+	pmd_t *pmdp;
+
+	BUG_ON(gmap_is_shadow(gmap));
+	spin_lock(&gmap->guest_table_lock);
+	pmdp = (pmd_t *) gmap_table_walk(gmap, gaddr, 1);
+
+	if (!pmdp || pmd_none(*pmdp)) {
+		spin_unlock(&gmap->guest_table_lock);
+		return NULL;
+	}
+
+	/* 4k page table entries are locked via the pte (pte_alloc_map_lock). */
+	if (!pmd_large(*pmdp))
+		spin_unlock(&gmap->guest_table_lock);
+	return pmdp;
+}
+
+/**
+ * gmap_pmd_op_end - release the guest_table_lock if needed
+ * @gmap: pointer to the guest mapping meta data structure
+ * @pmdp: pointer to the pmd
+ */
+static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp)
+{
+	if (pmd_large(*pmdp))
+		spin_unlock(&gmap->guest_table_lock);
+}
+
+/*
+ * gmap_protect_pmd - remove access rights to memory and set pmd notification bits
+ * @pmdp: pointer to the pmd to be protected
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: notification bits to set
+ *
+ * Returns:
+ * 0 if successfully protected
+ * -EAGAIN if a fixup is needed
+ * -EINVAL if unsupported notifier bits have been specified
+ *
+ * Expected to be called with sg->mm->mmap_sem in read and
+ * guest_table_lock held.
+ */
+static int gmap_protect_pmd(struct gmap *gmap, unsigned long gaddr,
+			    pmd_t *pmdp, int prot, unsigned long bits)
+{
+	int pmd_i = pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID;
+	int pmd_p = pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT;
+	pmd_t new = *pmdp;
+
+	/* Fixup needed */
+	if ((pmd_i && (prot != PROT_NONE)) || (pmd_p && (prot == PROT_WRITE)))
+		return -EAGAIN;
+
+	if (prot == PROT_NONE && !pmd_i) {
+		pmd_val(new) |= _SEGMENT_ENTRY_INVALID;
+		gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
+	}
+
+	if (prot == PROT_READ && !pmd_p) {
+		pmd_val(new) &= ~_SEGMENT_ENTRY_INVALID;
+		pmd_val(new) |= _SEGMENT_ENTRY_PROTECT;
+		gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
+	}
+
+	if (bits & GMAP_NOTIFY_MPROT)
+		pmd_val(*pmdp) |= _SEGMENT_ENTRY_GMAP_IN;
+
+	/* Shadow GMAP protection needs split PMDs */
+	if (bits & GMAP_NOTIFY_SHADOW)
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * gmap_protect_pte - remove access rights to memory and set pgste bits
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @pmdp: pointer to the pmd associated with the pte
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: notification bits to set
+ *
+ * Returns 0 if successfully protected, -ENOMEM if out of memory and
+ * -EAGAIN if a fixup is needed.
+ *
+ * Expected to be called with sg->mm->mmap_sem in read
+ */
+static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
+			    pmd_t *pmdp, int prot, unsigned long bits)
+{
+	int rc;
+	pte_t *ptep;
+	spinlock_t *ptl = NULL;
+	unsigned long pbits = 0;
+
+	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+		return -EAGAIN;
+
+	ptep = pte_alloc_map_lock(gmap->mm, pmdp, gaddr, &ptl);
+	if (!ptep)
+		return -ENOMEM;
+
+	pbits |= (bits & GMAP_NOTIFY_MPROT) ? PGSTE_IN_BIT : 0;
+	pbits |= (bits & GMAP_NOTIFY_SHADOW) ? PGSTE_VSIE_BIT : 0;
+	/* Protect and unlock. */
+	rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, pbits);
+	gmap_pte_op_end(ptl);
+	return rc;
 }
 
 /*
@@ -883,30 +1028,45 @@ static void gmap_pte_op_end(spinlock_t *ptl)
 static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
 			      unsigned long len, int prot, unsigned long bits)
 {
-	unsigned long vmaddr;
-	spinlock_t *ptl;
-	pte_t *ptep;
+	unsigned long vmaddr, dist;
+	pmd_t *pmdp;
 	int rc;
 
 	BUG_ON(gmap_is_shadow(gmap));
 	while (len) {
 		rc = -EAGAIN;
-		ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
-		if (ptep) {
-			rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, bits);
-			gmap_pte_op_end(ptl);
+		pmdp = gmap_pmd_op_walk(gmap, gaddr);
+		if (pmdp) {
+			if (!pmd_large(*pmdp)) {
+				rc = gmap_protect_pte(gmap, gaddr, pmdp, prot,
+						      bits);
+				if (!rc) {
+					len -= PAGE_SIZE;
+					gaddr += PAGE_SIZE;
+				}
+			} else {
+				rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot,
+						      bits);
+				if (!rc) {
+					dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK);
+					len = len < dist ? 0 : len - dist;
+					gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE;
+				}
+			}
+			gmap_pmd_op_end(gmap, pmdp);
 		}
 		if (rc) {
+			if (rc == -EINVAL)
+				return rc;
+
+			/* -EAGAIN, fixup of userspace mm and gmap */
 			vmaddr = __gmap_translate(gmap, gaddr);
 			if (IS_ERR_VALUE(vmaddr))
 				return vmaddr;
 			rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot);
 			if (rc)
 				return rc;
-			continue;
 		}
-		gaddr += PAGE_SIZE;
-		len -= PAGE_SIZE;
 	}
 	return 0;
 }
@@ -935,7 +1095,7 @@ int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr,
 	if (!MACHINE_HAS_ESOP && prot == PROT_READ)
 		return -EINVAL;
 	down_read(&gmap->mm->mmap_sem);
-	rc = gmap_protect_range(gmap, gaddr, len, prot, PGSTE_IN_BIT);
+	rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT);
 	up_read(&gmap->mm->mmap_sem);
 	return rc;
 }
@@ -1474,6 +1634,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
 	unsigned long limit;
 	int rc;
 
+	BUG_ON(parent->mm->context.allow_gmap_hpage_1m);
 	BUG_ON(gmap_is_shadow(parent));
 	spin_lock(&parent->shadow_lock);
 	sg = gmap_find_shadow(parent, asce, edat_level);
@@ -1526,7 +1687,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
 	down_read(&parent->mm->mmap_sem);
 	rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN,
 				((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE,
-				PROT_READ, PGSTE_VSIE_BIT);
+				PROT_READ, GMAP_NOTIFY_SHADOW);
 	up_read(&parent->mm->mmap_sem);
 	spin_lock(&parent->shadow_lock);
 	new->initialized = true;
@@ -2092,6 +2253,225 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
 }
 EXPORT_SYMBOL_GPL(ptep_notify);
 
+static void pmdp_notify_gmap(struct gmap *gmap, pmd_t *pmdp,
+			     unsigned long gaddr)
+{
+	pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_IN;
+	gmap_call_notifier(gmap, gaddr, gaddr + HPAGE_SIZE - 1);
+}
+
+/**
+ * gmap_pmdp_xchg - exchange a gmap pmd with another
+ * @gmap: pointer to the guest address space structure
+ * @pmdp: pointer to the pmd entry
+ * @new: replacement entry
+ * @gaddr: the affected guest address
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *pmdp, pmd_t new,
+			   unsigned long gaddr)
+{
+	gaddr &= HPAGE_MASK;
+	pmdp_notify_gmap(gmap, pmdp, gaddr);
+	pmd_val(new) &= ~_SEGMENT_ENTRY_GMAP_IN;
+	if (MACHINE_HAS_TLB_GUEST)
+		__pmdp_idte(gaddr, (pmd_t *)pmdp, IDTE_GUEST_ASCE, gmap->asce,
+			    IDTE_GLOBAL);
+	else if (MACHINE_HAS_IDTE)
+		__pmdp_idte(gaddr, (pmd_t *)pmdp, 0, 0, IDTE_GLOBAL);
+	else
+		__pmdp_csp(pmdp);
+	*pmdp = new;
+}
+
+static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
+			    int purge)
+{
+	pmd_t *pmdp;
+	struct gmap *gmap;
+	unsigned long gaddr;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		spin_lock(&gmap->guest_table_lock);
+		pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest,
+						  vmaddr >> PMD_SHIFT);
+		if (pmdp) {
+			gaddr = __gmap_segment_gaddr((unsigned long *)pmdp);
+			pmdp_notify_gmap(gmap, pmdp, gaddr);
+			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+						   _SEGMENT_ENTRY_GMAP_UC));
+			if (purge)
+				__pmdp_csp(pmdp);
+			pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
+		}
+		spin_unlock(&gmap->guest_table_lock);
+	}
+	rcu_read_unlock();
+}
+
+/**
+ * gmap_pmdp_invalidate - invalidate all affected guest pmd entries without
+ *                        flushing
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr)
+{
+	gmap_pmdp_clear(mm, vmaddr, 0);
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_invalidate);
+
+/**
+ * gmap_pmdp_csp - csp all affected guest pmd entries
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr)
+{
+	gmap_pmdp_clear(mm, vmaddr, 1);
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_csp);
+
+/**
+ * gmap_pmdp_idte_local - invalidate and clear a guest pmd entry
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
+{
+	unsigned long *entry, gaddr;
+	struct gmap *gmap;
+	pmd_t *pmdp;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		spin_lock(&gmap->guest_table_lock);
+		entry = radix_tree_delete(&gmap->host_to_guest,
+					  vmaddr >> PMD_SHIFT);
+		if (entry) {
+			pmdp = (pmd_t *)entry;
+			gaddr = __gmap_segment_gaddr(entry);
+			pmdp_notify_gmap(gmap, pmdp, gaddr);
+			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+					   _SEGMENT_ENTRY_GMAP_UC));
+			if (MACHINE_HAS_TLB_GUEST)
+				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
+					    gmap->asce, IDTE_LOCAL);
+			else if (MACHINE_HAS_IDTE)
+				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL);
+			*entry = _SEGMENT_ENTRY_EMPTY;
+		}
+		spin_unlock(&gmap->guest_table_lock);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local);
+
+/**
+ * gmap_pmdp_idte_global - invalidate and clear a guest pmd entry
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
+{
+	unsigned long *entry, gaddr;
+	struct gmap *gmap;
+	pmd_t *pmdp;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		spin_lock(&gmap->guest_table_lock);
+		entry = radix_tree_delete(&gmap->host_to_guest,
+					  vmaddr >> PMD_SHIFT);
+		if (entry) {
+			pmdp = (pmd_t *)entry;
+			gaddr = __gmap_segment_gaddr(entry);
+			pmdp_notify_gmap(gmap, pmdp, gaddr);
+			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+					   _SEGMENT_ENTRY_GMAP_UC));
+			if (MACHINE_HAS_TLB_GUEST)
+				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
+					    gmap->asce, IDTE_GLOBAL);
+			else if (MACHINE_HAS_IDTE)
+				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL);
+			else
+				__pmdp_csp(pmdp);
+			*entry = _SEGMENT_ENTRY_EMPTY;
+		}
+		spin_unlock(&gmap->guest_table_lock);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global);
+
+/**
+ * gmap_test_and_clear_dirty_pmd - test and reset segment dirty status
+ * @gmap: pointer to guest address space
+ * @pmdp: pointer to the pmd to be tested
+ * @gaddr: virtual address in the guest address space
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp,
+				   unsigned long gaddr)
+{
+	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+		return false;
+
+	/* Already protected memory, which did not change is clean */
+	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT &&
+	    !(pmd_val(*pmdp) & _SEGMENT_ENTRY_GMAP_UC))
+		return false;
+
+	/* Clear UC indication and reset protection */
+	pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_UC;
+	gmap_protect_pmd(gmap, gaddr, pmdp, PROT_READ, 0);
+	return true;
+}
+
+/**
+ * gmap_sync_dirty_log_pmd - set bitmap based on dirty status of segment
+ * @gmap: pointer to guest address space
+ * @bitmap: dirty bitmap for this pmd
+ * @gaddr: virtual address in the guest address space
+ * @vmaddr: virtual address in the host address space
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4],
+			     unsigned long gaddr, unsigned long vmaddr)
+{
+	int i;
+	pmd_t *pmdp;
+	pte_t *ptep;
+	spinlock_t *ptl;
+
+	pmdp = gmap_pmd_op_walk(gmap, gaddr);
+	if (!pmdp)
+		return;
+
+	if (pmd_large(*pmdp)) {
+		if (gmap_test_and_clear_dirty_pmd(gmap, pmdp, gaddr))
+			bitmap_fill(bitmap, _PAGE_ENTRIES);
+	} else {
+		for (i = 0; i < _PAGE_ENTRIES; i++, vmaddr += PAGE_SIZE) {
+			ptep = pte_alloc_map_lock(gmap->mm, pmdp, vmaddr, &ptl);
+			if (!ptep)
+				continue;
+			if (ptep_test_and_clear_uc(gmap->mm, vmaddr, ptep))
+				set_bit(i, bitmap);
+			spin_unlock(ptl);
+		}
+	}
+	gmap_pmd_op_end(gmap, pmdp);
+}
+EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd);
+
 static inline void thp_split_mm(struct mm_struct *mm)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -2168,17 +2548,45 @@ EXPORT_SYMBOL_GPL(s390_enable_sie);
  * Enable storage key handling from now on and initialize the storage
  * keys with the default key.
  */
-static int __s390_enable_skey(pte_t *pte, unsigned long addr,
-			      unsigned long next, struct mm_walk *walk)
+static int __s390_enable_skey_pte(pte_t *pte, unsigned long addr,
+				  unsigned long next, struct mm_walk *walk)
 {
 	/* Clear storage key */
 	ptep_zap_key(walk->mm, addr, pte);
 	return 0;
 }
 
+static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
+				      unsigned long hmask, unsigned long next,
+				      struct mm_walk *walk)
+{
+	pmd_t *pmd = (pmd_t *)pte;
+	unsigned long start, end;
+	struct page *page = pmd_page(*pmd);
+
+	/*
+	 * The write check makes sure we do not set a key on shared
+	 * memory. This is needed as the walker does not differentiate
+	 * between actual guest memory and the process executable or
+	 * shared libraries.
+	 */
+	if (pmd_val(*pmd) & _SEGMENT_ENTRY_INVALID ||
+	    !(pmd_val(*pmd) & _SEGMENT_ENTRY_WRITE))
+		return 0;
+
+	start = pmd_val(*pmd) & HPAGE_MASK;
+	end = start + HPAGE_SIZE - 1;
+	__storage_key_init_range(start, end);
+	set_bit(PG_arch_1, &page->flags);
+	return 0;
+}
+
 int s390_enable_skey(void)
 {
-	struct mm_walk walk = { .pte_entry = __s390_enable_skey };
+	struct mm_walk walk = {
+		.hugetlb_entry = __s390_enable_skey_hugetlb,
+		.pte_entry = __s390_enable_skey_pte,
+	};
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	int rc = 0;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index e804090f4470..b0246c705a19 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -123,6 +123,29 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 	return pte;
 }
 
+static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
+{
+	struct page *page;
+	unsigned long size, paddr;
+
+	if (!mm_uses_skeys(mm) ||
+	    rste & _SEGMENT_ENTRY_INVALID)
+		return;
+
+	if ((rste & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) {
+		page = pud_page(__pud(rste));
+		size = PUD_SIZE;
+		paddr = rste & PUD_MASK;
+	} else {
+		page = pmd_page(__pmd(rste));
+		size = PMD_SIZE;
+		paddr = rste & PMD_MASK;
+	}
+
+	if (!test_and_set_bit(PG_arch_1, &page->flags))
+		__storage_key_init_range(paddr, paddr + size - 1);
+}
+
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte)
 {
@@ -137,6 +160,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE;
 	else
 		rste |= _SEGMENT_ENTRY_LARGE;
+	clear_huge_pte_skeys(mm, rste);
 	pte_val(*ptep) = rste;
 }
 
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index 382153ff17e3..dc3cede7f2ec 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -271,7 +271,7 @@ void arch_set_page_states(int make_stable)
 			list_for_each(l, &zone->free_area[order].free_list[t]) {
 				page = list_entry(l, struct page, lru);
 				if (make_stable)
-					set_page_stable_dat(page, 0);
+					set_page_stable_dat(page, order);
 				else
 					set_page_unused(page, order);
 			}
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index c44171588d08..f8c6faab41f4 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -14,7 +14,7 @@
 
 static inline unsigned long sske_frame(unsigned long addr, unsigned char skey)
 {
-	asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0"
+	asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],1,0"
 		     : [addr] "+a" (addr) : [skey] "d" (skey));
 	return addr;
 }
@@ -23,8 +23,6 @@ void __storage_key_init_range(unsigned long start, unsigned long end)
 {
 	unsigned long boundary, size;
 
-	if (!PAGE_DEFAULT_KEY)
-		return;
 	while (start < end) {
 		if (MACHINE_HAS_EDAT1) {
 			/* set storage keys for a 1MB frame */
@@ -37,7 +35,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end)
 				continue;
 			}
 		}
-		page_set_storage_key(start, PAGE_DEFAULT_KEY, 0);
+		page_set_storage_key(start, PAGE_DEFAULT_KEY, 1);
 		start += PAGE_SIZE;
 	}
 }
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 84bd6329a88d..76d89ee8b428 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -28,7 +28,7 @@ static struct ctl_table page_table_sysctl[] = {
 		.data		= &page_table_allocate_pgste,
 		.maxlen		= sizeof(int),
 		.mode		= S_IRUGO | S_IWUSR,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &page_table_allocate_pgste_min,
 		.extra2		= &page_table_allocate_pgste_max,
 	},
@@ -252,6 +252,8 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 		spin_unlock_bh(&mm->context.lock);
 		if (mask != 0)
 			return;
+	} else {
+		atomic_xor_bits(&page->_refcount, 3U << 24);
 	}
 
 	pgtable_page_dtor(page);
@@ -304,6 +306,8 @@ static void __tlb_remove_table(void *_table)
 			break;
 		/* fallthrough */
 	case 3:		/* 4K page table with pgstes */
+		if (mask & 3)
+			atomic_xor_bits(&page->_refcount, 3 << 24);
 		pgtable_page_dtor(page);
 		__free_page(page);
 		break;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 301e466e4263..f2cc7da473e4 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -347,18 +347,27 @@ static inline void pmdp_idte_local(struct mm_struct *mm,
 			    mm->context.asce, IDTE_LOCAL);
 	else
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_LOCAL);
+	if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+		gmap_pmdp_idte_local(mm, addr);
 }
 
 static inline void pmdp_idte_global(struct mm_struct *mm,
 				    unsigned long addr, pmd_t *pmdp)
 {
-	if (MACHINE_HAS_TLB_GUEST)
+	if (MACHINE_HAS_TLB_GUEST) {
 		__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
 			    mm->context.asce, IDTE_GLOBAL);
-	else if (MACHINE_HAS_IDTE)
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+			gmap_pmdp_idte_global(mm, addr);
+	} else if (MACHINE_HAS_IDTE) {
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL);
-	else
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+			gmap_pmdp_idte_global(mm, addr);
+	} else {
 		__pmdp_csp(pmdp);
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+			gmap_pmdp_csp(mm, addr);
+	}
 }
 
 static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
@@ -392,6 +401,8 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 			  cpumask_of(smp_processor_id()))) {
 		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
 		mm->context.flush_mm = 1;
+		if (mm_has_pgste(mm))
+			gmap_pmdp_invalidate(mm, addr);
 	} else {
 		pmdp_idte_global(mm, addr, pmdp);
 	}
@@ -399,6 +410,24 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 	return old;
 }
 
+static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+	pmd = pmd_alloc(mm, pud, addr);
+	return pmd;
+}
+
 pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t new)
 {
@@ -693,40 +722,14 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 /*
  * Test and reset if a guest page is dirty
  */
-bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
+bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long addr,
+		       pte_t *ptep)
 {
-	spinlock_t *ptl;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
 	pgste_t pgste;
-	pte_t *ptep;
 	pte_t pte;
 	bool dirty;
 	int nodat;
 
-	pgd = pgd_offset(mm, addr);
-	p4d = p4d_alloc(mm, pgd, addr);
-	if (!p4d)
-		return false;
-	pud = pud_alloc(mm, p4d, addr);
-	if (!pud)
-		return false;
-	pmd = pmd_alloc(mm, pud, addr);
-	if (!pmd)
-		return false;
-	/* We can't run guests backed by huge pages, but userspace can
-	 * still set them up and then try to migrate them without any
-	 * migration support.
-	 */
-	if (pmd_large(*pmd))
-		return true;
-
-	ptep = pte_alloc_map_lock(mm, pmd, addr, &ptl);
-	if (unlikely(!ptep))
-		return false;
-
 	pgste = pgste_get_lock(ptep);
 	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
 	pgste_val(pgste) &= ~PGSTE_UC_BIT;
@@ -742,21 +745,43 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
 		*ptep = pte;
 	}
 	pgste_set_unlock(ptep, pgste);
-
-	spin_unlock(ptl);
 	return dirty;
 }
-EXPORT_SYMBOL_GPL(test_and_clear_guest_dirty);
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_uc);
 
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq)
 {
-	unsigned long keyul;
+	unsigned long keyul, paddr;
 	spinlock_t *ptl;
 	pgste_t old, new;
+	pmd_t *pmdp;
 	pte_t *ptep;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pmdp = pmd_alloc_map(mm, addr);
+	if (unlikely(!pmdp))
+		return -EFAULT;
+
+	ptl = pmd_lock(mm, pmdp);
+	if (!pmd_present(*pmdp)) {
+		spin_unlock(ptl);
+		return -EFAULT;
+	}
+
+	if (pmd_large(*pmdp)) {
+		paddr = pmd_val(*pmdp) & HPAGE_MASK;
+		paddr |= addr & ~HPAGE_MASK;
+		/*
+		 * Huge pmds need quiescing operations, they are
+		 * always mapped.
+		 */
+		page_set_storage_key(paddr, key, 1);
+		spin_unlock(ptl);
+		return 0;
+	}
+	spin_unlock(ptl);
+
+	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
 
@@ -767,14 +792,14 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	pgste_val(new) |= (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
 	pgste_val(new) |= (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-		unsigned long address, bits, skey;
+		unsigned long bits, skey;
 
-		address = pte_val(*ptep) & PAGE_MASK;
-		skey = (unsigned long) page_get_storage_key(address);
+		paddr = pte_val(*ptep) & PAGE_MASK;
+		skey = (unsigned long) page_get_storage_key(paddr);
 		bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
 		skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT);
 		/* Set storage key ACC and FP */
-		page_set_storage_key(address, skey, !nq);
+		page_set_storage_key(paddr, skey, !nq);
 		/* Merge host changed & referenced into pgste  */
 		pgste_val(new) |= bits << 52;
 	}
@@ -830,11 +855,32 @@ EXPORT_SYMBOL(cond_set_guest_storage_key);
 int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 {
 	spinlock_t *ptl;
+	unsigned long paddr;
 	pgste_t old, new;
+	pmd_t *pmdp;
 	pte_t *ptep;
 	int cc = 0;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pmdp = pmd_alloc_map(mm, addr);
+	if (unlikely(!pmdp))
+		return -EFAULT;
+
+	ptl = pmd_lock(mm, pmdp);
+	if (!pmd_present(*pmdp)) {
+		spin_unlock(ptl);
+		return -EFAULT;
+	}
+
+	if (pmd_large(*pmdp)) {
+		paddr = pmd_val(*pmdp) & HPAGE_MASK;
+		paddr |= addr & ~HPAGE_MASK;
+		cc = page_reset_referenced(paddr);
+		spin_unlock(ptl);
+		return cc;
+	}
+	spin_unlock(ptl);
+
+	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
 
@@ -843,7 +889,8 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	pgste_val(new) &= ~PGSTE_GR_BIT;
 
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-		cc = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
+		paddr = pte_val(*ptep) & PAGE_MASK;
+		cc = page_reset_referenced(paddr);
 		/* Merge real referenced bit into host-set */
 		pgste_val(new) |= ((unsigned long) cc << 53) & PGSTE_HR_BIT;
 	}
@@ -862,18 +909,42 @@ EXPORT_SYMBOL(reset_guest_reference_bit);
 int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char *key)
 {
+	unsigned long paddr;
 	spinlock_t *ptl;
 	pgste_t pgste;
+	pmd_t *pmdp;
 	pte_t *ptep;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pmdp = pmd_alloc_map(mm, addr);
+	if (unlikely(!pmdp))
+		return -EFAULT;
+
+	ptl = pmd_lock(mm, pmdp);
+	if (!pmd_present(*pmdp)) {
+		/* Not yet mapped memory has a zero key */
+		spin_unlock(ptl);
+		*key = 0;
+		return 0;
+	}
+
+	if (pmd_large(*pmdp)) {
+		paddr = pmd_val(*pmdp) & HPAGE_MASK;
+		paddr |= addr & ~HPAGE_MASK;
+		*key = page_get_storage_key(paddr);
+		spin_unlock(ptl);
+		return 0;
+	}
+	spin_unlock(ptl);
+
+	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
 
 	pgste = pgste_get_lock(ptep);
 	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+	paddr = pte_val(*ptep) & PAGE_MASK;
 	if (!(pte_val(*ptep) & _PAGE_INVALID))
-		*key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);
+		*key = page_get_storage_key(paddr);
 	/* Reflect guest's logical view, not physical */
 	*key |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
 	pgste_set_unlock(ptep, pgste);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index d2db8acb1a55..d7052cbe984f 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -485,8 +485,6 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 			/* br %r1 */
 			_EMIT2(0x07f1);
 		} else {
-			/* larl %r1,.+14 */
-			EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
 			/* ex 0,S390_lowcore.br_r1_tampoline */
 			EMIT4_DISP(0x44000000, REG_0, REG_0,
 				   offsetof(struct lowcore, br_r1_trampoline));
@@ -1286,6 +1284,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		goto free_addrs;
 	}
 	if (bpf_jit_prog(&jit, fp)) {
+		bpf_jit_binary_free(header);
 		fp = orig_fp;
 		goto free_addrs;
 	}
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index 06a80434cfe6..5bd374491f94 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -134,6 +134,8 @@ void __init numa_setup(void)
 {
 	pr_info("NUMA mode: %s\n", mode->name);
 	nodes_clear(node_possible_map);
+	/* Initially attach all possible CPUs to node 0. */
+	cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
 	if (mode->setup)
 		mode->setup();
 	numa_setup_memory();
@@ -141,20 +143,6 @@ void __init numa_setup(void)
 }
 
 /*
- * numa_init_early() - Initialization initcall
- *
- * This runs when only one CPU is online and before the first
- * topology update is called for by the scheduler.
- */
-static int __init numa_init_early(void)
-{
-	/* Attach all possible CPUs to node 0 for now. */
-	cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
-	return 0;
-}
-early_initcall(numa_init_early);
-
-/*
  * numa_init_late() - Initialization initcall
  *
  * Register NUMA nodes.
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index b482e95b6249..57f7cdac70a3 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -48,6 +48,10 @@ static char *pci_fmt2_names[] = {
 	"Maximum work units",
 };
 
+static char *pci_fmt3_names[] = {
+	"Transmitted bytes",
+};
+
 static char *pci_sw_names[] = {
 	"Allocated pages",
 	"Mapped pages",
@@ -112,6 +116,10 @@ static int pci_perf_show(struct seq_file *m, void *v)
 		pci_fmb_show(m, pci_fmt2_names, ARRAY_SIZE(pci_fmt2_names),
 			     &zdev->fmb->fmt2.consumed_work_units);
 		break;
+	case 3:
+		pci_fmb_show(m, pci_fmt3_names, ARRAY_SIZE(pci_fmt3_names),
+			     &zdev->fmb->fmt3.tx_bytes);
+		break;
 	default:
 		seq_puts(m, "Unknown format\n");
 	}
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index 1ace023cbdce..8d61218a71aa 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -7,13 +7,13 @@ purgatory-y := head.o purgatory.o string.o sha256.o mem.o
 targets += $(purgatory-y) purgatory.ro kexec-purgatory.c
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 
-$(obj)/sha256.o: $(srctree)/lib/sha256.c
+$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S
+$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
 
-$(obj)/string.o: $(srctree)/arch/s390/lib/string.c
+$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib
@@ -21,8 +21,9 @@ LDFLAGS_purgatory.ro += -z nodefaultlib
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
-KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float
+KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
+KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S
index 660c96a05a9b..2e3707b12edd 100644
--- a/arch/s390/purgatory/head.S
+++ b/arch/s390/purgatory/head.S
@@ -243,33 +243,26 @@ gprregs:
 	.quad	0
 	.endr
 
-purgatory_sha256_digest:
-	.global purgatory_sha256_digest
-	.rept	32	/* SHA256_DIGEST_SIZE */
-	.byte	0
-	.endr
-
-purgatory_sha_regions:
-	.global purgatory_sha_regions
-	.rept	16 * __KEXEC_SHA_REGION_SIZE	/* KEXEC_SEGMENTS_MAX */
-	.byte	0
-	.endr
-
-kernel_entry:
-	.global kernel_entry
-	.quad	0
-
-kernel_type:
-	.global kernel_type
-	.quad	0
-
-crash_start:
-	.global crash_start
-	.quad	0
+/* Macro to define a global variable with name and size (in bytes) to be
+ * shared with C code.
+ *
+ * Add the .size and .type attribute to satisfy checks on the Elf_Sym during
+ * purgatory load.
+ */
+.macro GLOBAL_VARIABLE name,size
+\name:
+	.global \name
+	.size	\name,\size
+	.type	\name,object
+	.skip	\size,0
+.endm
 
-crash_size:
-	.global crash_size
-	.quad	0
+GLOBAL_VARIABLE purgatory_sha256_digest,32
+GLOBAL_VARIABLE purgatory_sha_regions,16*__KEXEC_SHA_REGION_SIZE
+GLOBAL_VARIABLE kernel_entry,8
+GLOBAL_VARIABLE kernel_type,8
+GLOBAL_VARIABLE crash_start,8
+GLOBAL_VARIABLE crash_size,8
 
 	.align	PAGE_SIZE
 stack:
diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c
index 4e2beb3c29b7..3528e6da4e87 100644
--- a/arch/s390/purgatory/purgatory.c
+++ b/arch/s390/purgatory/purgatory.c
@@ -12,15 +12,6 @@
 #include <linux/string.h>
 #include <asm/purgatory.h>
 
-struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX];
-u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE];
-
-u64 kernel_entry;
-u64 kernel_type;
-
-u64 crash_start;
-u64 crash_size;
-
 int verify_sha256_digest(void)
 {
 	struct kexec_sha_region *ptr, *end;
diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss
index d92f2d94a5d9..9bba2c14e0ca 100644
--- a/arch/s390/scripts/Makefile.chkbss
+++ b/arch/s390/scripts/Makefile.chkbss
@@ -2,13 +2,22 @@
 
 quiet_cmd_chkbss = CHKBSS  $<
 define cmd_chkbss
+	rm -f $@; \
 	if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
 		echo "error: $< .bss section is not empty" >&2; exit 1; \
 	fi; \
 	touch $@;
 endef
 
-$(obj)/built-in.a: $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+chkbss-target ?= $(obj)/built-in.a
+ifneq (,$(findstring /,$(chkbss)))
+chkbss-files := $(patsubst %, %.chkbss, $(chkbss))
+else
+chkbss-files := $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+endif
+
+$(chkbss-target): $(chkbss-files)
+targets += $(notdir $(chkbss-files))
 
 %.o.chkbss: %.o
 	$(call cmd,chkbss)
diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c
index 259aa0680d1a..a1bc02b29c81 100644
--- a/arch/s390/tools/gen_opcode_table.c
+++ b/arch/s390/tools/gen_opcode_table.c
@@ -257,7 +257,7 @@ static void add_to_group(struct gen_opcode *desc, struct insn *insn, int offset)
 	if (!desc->group)
 		exit(EXIT_FAILURE);
 	group = &desc->group[desc->nr_groups - 1];
-	strncpy(group->opcode, insn->opcode, 2);
+	memcpy(group->opcode, insn->opcode, 2);
 	group->type = insn->type;
 	group->offset = offset;
 	group->count = 1;
@@ -283,7 +283,7 @@ static void print_opcode_table(struct gen_opcode *desc)
 			continue;
 		add_to_group(desc, insn, offset);
 		if (strncmp(opcode, insn->opcode, 2)) {
-			strncpy(opcode, insn->opcode, 2);
+			memcpy(opcode, insn->opcode, 2);
 			printf("\t/* %.2s */ \\\n", opcode);
 		}
 		print_opcode(insn, offset);
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index dd4f3d3e644f..da4db4b5359f 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -51,7 +51,6 @@ config SUPERH
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_NMI
-	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
 
 	help
@@ -159,10 +158,13 @@ config SWAP_IO_SPACE
 	bool
 
 config DMA_COHERENT
+	select DMA_DIRECT_OPS
 	bool
 
 config DMA_NONCOHERENT
 	def_bool !DMA_COHERENT
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_NONCOHERENT_OPS
 
 config PGTABLE_LEVELS
 	default 3 if X2TLB
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 46dd82ab2c29..6a5609a55965 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -2,6 +2,7 @@ generic-y += compat.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += irq_regs.h
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index 0fd0099f43cc..f37b95a80232 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -32,44 +32,9 @@
 #include <asm/atomic-irq.h>
 #endif
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
-
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
-
 #define atomic_xchg(v, new)		(xchg(&((v)->counter), new))
 #define atomic_cmpxchg(v, o, n)		(cmpxchg(&((v)->counter), (o), (n)))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-
-	return c;
-}
-
 #endif /* CONFIG_CPU_J2 */
 
 #endif /* __ASM_SH_ATOMIC_H */
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index d103ab5a4e4b..b932e42ef028 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -101,5 +101,12 @@ void kunmap_coherent(void *kvaddr);
 
 void cpu_cache_init(void);
 
+static inline void *sh_cacheop_vaddr(void *vaddr)
+{
+	if (__in_29bit_mode())
+		vaddr = (void *)CAC_ADDR((unsigned long)vaddr);
+	return vaddr;
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_CACHEFLUSH_H */
diff --git a/arch/sh/include/asm/cmpxchg-xchg.h b/arch/sh/include/asm/cmpxchg-xchg.h
index 1e881f5db659..593a9704782b 100644
--- a/arch/sh/include/asm/cmpxchg-xchg.h
+++ b/arch/sh/include/asm/cmpxchg-xchg.h
@@ -8,7 +8,8 @@
  * This work is licensed under the terms of the GNU GPL, version 2.  See the
  * file "COPYING" in the main directory of this archive for more details.
  */
-#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/compiler.h>
 #include <asm/byteorder.h>
 
 /*
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
deleted file mode 100644
index 41167931e5d9..000000000000
--- a/arch/sh/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_SH_DMA_MAPPING_H
-#define __ASM_SH_DMA_MAPPING_H
-
-extern const struct dma_map_ops *dma_ops;
-extern void no_iommu_init(void);
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return dma_ops;
-}
-
-extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_addr, gfp_t flag,
-					unsigned long attrs);
-extern void dma_generic_free_coherent(struct device *dev, size_t size,
-				      void *vaddr, dma_addr_t dma_handle,
-				      unsigned long attrs);
-
-void sh_sync_dma_for_device(void *vaddr, size_t size,
-	    enum dma_data_direction dir);
-
-#endif /* __ASM_SH_DMA_MAPPING_H */
diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
index 7431c172c0cb..199d17b765f2 100644
--- a/arch/sh/include/asm/hw_breakpoint.h
+++ b/arch/sh/include/asm/hw_breakpoint.h
@@ -10,7 +10,6 @@
 #include <linux/types.h>
 
 struct arch_hw_breakpoint {
-	char		*name; /* Contains name of the symbol to set bkpt */
 	unsigned long	address;
 	u16		len;
 	u16		type;
@@ -41,6 +40,7 @@ struct sh_ubc {
 	struct clk	*clk;	/* optional interface clock / MSTP bit */
 };
 
+struct perf_event_attr;
 struct perf_event;
 struct task_struct;
 struct pmu;
@@ -54,8 +54,10 @@ static inline int hw_breakpoint_slots(int type)
 }
 
 /* arch/sh/kernel/hw_breakpoint.c */
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h
index 85d8bcaa8493..6171682f7798 100644
--- a/arch/sh/include/asm/kprobes.h
+++ b/arch/sh/include/asm/kprobes.h
@@ -27,7 +27,6 @@ struct kprobe;
 
 void arch_remove_kprobe(struct kprobe *);
 void kretprobe_trampoline(void);
-void jprobe_return_end(void);
 
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
@@ -43,9 +42,6 @@ struct prev_kprobe {
 /* per-cpu kprobe control block */
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
-	unsigned long jprobe_saved_r15;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index dc80041f7363..59673f8a3379 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -12,7 +12,7 @@ endif
 
 CFLAGS_REMOVE_return_address.o = -pg
 
-obj-y	:= debugtraps.o dma-nommu.o dumpstack.o 		\
+obj-y	:= debugtraps.o dumpstack.o 		\
 	   idle.o io.o irq.o irq_$(BITS).o kdebugfs.o			\
 	   machvec.o nmi_debug.o process.o				\
 	   process_$(BITS).o ptrace.o ptrace_$(BITS).o			\
@@ -45,7 +45,7 @@ obj-$(CONFIG_DUMP_CODE)		+= disassemble.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o
 obj-$(CONFIG_DWARF_UNWINDER)	+= dwarf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_callchain.o
-
+obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-coherent.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)		+= hw_breakpoint.o
 
 ccflags-y := -Werror
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
new file mode 100644
index 000000000000..a0021eef956b
--- /dev/null
+++ b/arch/sh/kernel/dma-coherent.c
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2004 - 2007  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/module.h>
+#include <asm/cacheflush.h>
+#include <asm/addrspace.h>
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
+{
+	void *ret, *ret_nocache;
+	int order = get_order(size);
+
+	gfp |= __GFP_ZERO;
+
+	ret = (void *)__get_free_pages(gfp, order);
+	if (!ret)
+		return NULL;
+
+	/*
+	 * Pages from the page allocator may have data present in
+	 * cache. So flush the cache before using uncached memory.
+	 */
+	arch_sync_dma_for_device(dev, virt_to_phys(ret), size,
+			DMA_BIDIRECTIONAL);
+
+	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
+	if (!ret_nocache) {
+		free_pages((unsigned long)ret, order);
+		return NULL;
+	}
+
+	split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
+
+	*dma_handle = virt_to_phys(ret);
+	if (!WARN_ON(!dev))
+		*dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
+
+	return ret_nocache;
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	int order = get_order(size);
+	unsigned long pfn = (dma_handle >> PAGE_SHIFT);
+	int k;
+
+	if (!WARN_ON(!dev))
+		pfn += dev->dma_pfn_offset;
+
+	for (k = 0; k < (1 << order); k++)
+		__free_pages(pfn_to_page(pfn + k), 0);
+
+	iounmap(vaddr);
+}
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	void *addr = sh_cacheop_vaddr(phys_to_virt(paddr));
+
+	switch (dir) {
+	case DMA_FROM_DEVICE:		/* invalidate only */
+		__flush_invalidate_region(addr, size);
+		break;
+	case DMA_TO_DEVICE:		/* writeback only */
+		__flush_wback_region(addr, size);
+		break;
+	case DMA_BIDIRECTIONAL:		/* writeback and invalidate */
+		__flush_purge_region(addr, size);
+		break;
+	default:
+		BUG();
+	}
+}
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
deleted file mode 100644
index 3e3a32fc676e..000000000000
--- a/arch/sh/kernel/dma-nommu.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * DMA mapping support for platforms lacking IOMMUs.
- *
- * Copyright (C) 2009  Paul Mundt
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/dma-mapping.h>
-#include <linux/io.h>
-#include <asm/cacheflush.h>
-
-static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction dir,
-				 unsigned long attrs)
-{
-	dma_addr_t addr = page_to_phys(page) + offset
-		- PFN_PHYS(dev->dma_pfn_offset);
-
-	WARN_ON(size == 0);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		sh_sync_dma_for_device(page_address(page) + offset, size, dir);
-
-	return addr;
-}
-
-static int nommu_map_sg(struct device *dev, struct scatterlist *sg,
-			int nents, enum dma_data_direction dir,
-			unsigned long attrs)
-{
-	struct scatterlist *s;
-	int i;
-
-	WARN_ON(nents == 0 || sg[0].length == 0);
-
-	for_each_sg(sg, s, nents, i) {
-		dma_addr_t offset = PFN_PHYS(dev->dma_pfn_offset);
-
-		BUG_ON(!sg_page(s));
-
-		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			sh_sync_dma_for_device(sg_virt(s), s->length, dir);
-
-		s->dma_address = sg_phys(s) - offset;
-		s->dma_length = s->length;
-	}
-
-	return nents;
-}
-
-#ifdef CONFIG_DMA_NONCOHERENT
-static void nommu_sync_single_for_device(struct device *dev, dma_addr_t addr,
-			      size_t size, enum dma_data_direction dir)
-{
-	sh_sync_dma_for_device(phys_to_virt(addr), size, dir);
-}
-
-static void nommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-			  int nelems, enum dma_data_direction dir)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nelems, i)
-		sh_sync_dma_for_device(sg_virt(s), s->length, dir);
-}
-#endif
-
-const struct dma_map_ops nommu_dma_ops = {
-	.alloc			= dma_generic_alloc_coherent,
-	.free			= dma_generic_free_coherent,
-	.map_page		= nommu_map_page,
-	.map_sg			= nommu_map_sg,
-#ifdef CONFIG_DMA_NONCOHERENT
-	.sync_single_for_device	= nommu_sync_single_for_device,
-	.sync_sg_for_device	= nommu_sync_sg_for_device,
-#endif
-};
-
-void __init no_iommu_init(void)
-{
-	if (dma_ops)
-		return;
-	dma_ops = &nommu_dma_ops;
-}
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index 8648ed05ccf0..d9ff3b42da7c 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -124,14 +124,13 @@ static int get_hbp_len(u16 hbp_len)
 /*
  * Check for virtual address in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->len);
+	va = hw->address;
+	len = get_hbp_len(hw->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -174,40 +173,40 @@ int arch_bp_generic_fields(int sh_len, int sh_type,
 	return 0;
 }
 
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->len = SH_BREAKPOINT_LEN_1;
+		hw->len = SH_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->len = SH_BREAKPOINT_LEN_2;
+		hw->len = SH_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->len = SH_BREAKPOINT_LEN_4;
+		hw->len = SH_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->len = SH_BREAKPOINT_LEN_8;
+		hw->len = SH_BREAKPOINT_LEN_8;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_R:
-		info->type = SH_BREAKPOINT_READ;
+		hw->type = SH_BREAKPOINT_READ;
 		break;
 	case HW_BREAKPOINT_W:
-		info->type = SH_BREAKPOINT_WRITE;
+		hw->type = SH_BREAKPOINT_WRITE;
 		break;
 	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
-		info->type = SH_BREAKPOINT_RW;
+		hw->type = SH_BREAKPOINT_RW;
 		break;
 	default:
 		return -EINVAL;
@@ -219,19 +218,20 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
 	int ret;
 
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
 	ret = -EINVAL;
 
-	switch (info->len) {
+	switch (hw->len) {
 	case SH_BREAKPOINT_LEN_1:
 		align = 0;
 		break;
@@ -249,17 +249,10 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	}
 
 	/*
-	 * For kernel-addresses, either the address or symbol name can be
-	 * specified.
-	 */
-	if (info->name)
-		info->address = (unsigned long)kallsyms_lookup_name(info->name);
-
-	/*
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
 	 */
-	if (info->address & align)
+	if (hw->address & align)
 		return -EINVAL;
 
 	return 0;
@@ -346,7 +339,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 		perf_bp_event(bp, args->regs);
 
 		/* Deliver the signal to userspace */
-		if (!arch_check_bp_in_kernelspace(bp)) {
+		if (!arch_check_bp_in_kernelspace(&bp->hw.info)) {
 			force_sig_fault(SIGTRAP, TRAP_HWBKPT,
 					(void __user *)NULL, current);
 		}
diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c
index 52a5e11247d1..241e903dd3ee 100644
--- a/arch/sh/kernel/kprobes.c
+++ b/arch/sh/kernel/kprobes.c
@@ -248,11 +248,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			prepare_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			return 1;
-		} else {
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				goto ss_probe;
-			}
 		}
 		goto no_kprobe;
 	}
@@ -277,11 +272,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 	prepare_singlestep(p, regs);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;
@@ -358,8 +355,6 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->pc = orig_ret_address;
 	kretprobe_hash_unlock(current, &flags);
 
-	preempt_enable_no_resched();
-
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
@@ -508,14 +503,8 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 				if (post_kprobe_handler(args->regs))
 					ret = NOTIFY_STOP;
 			} else {
-				if (kprobe_handler(args->regs)) {
+				if (kprobe_handler(args->regs))
 					ret = NOTIFY_STOP;
-				} else {
-					p = __this_cpu_read(current_kprobe);
-					if (p->break_handler &&
-					    p->break_handler(p, args->regs))
-						ret = NOTIFY_STOP;
-				}
 			}
 		}
 	}
@@ -523,57 +512,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_r15 = regs->regs[15];
-	addr = kcb->jprobe_saved_r15;
-
-	/*
-	 * TBD: As Linus pointed out, gcc assumes that the callee
-	 * owns the argument space and could overwrite it, e.g.
-	 * tailcall optimization. So, to be absolutely safe
-	 * we also save and restore enough stack bytes to cover
-	 * the argument area.
-	 */
-	memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr,
-	       MIN_STACK_SIZE(addr));
-
-	regs->pc = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack_addr = kcb->jprobe_saved_r15;
-	u8 *addr = (u8 *)regs->pc;
-
-	if ((addr >= (u8 *)jprobe_return) &&
-	    (addr <= (u8 *)jprobe_return_end)) {
-		*regs = kcb->jprobe_saved_regs;
-
-		memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack,
-		       MIN_STACK_SIZE(stack_addr));
-
-		kcb->kprobe_status = KPROBE_HIT_SS;
-		preempt_enable_no_resched();
-		return 1;
-	}
-
-	return 0;
-}
-
 static struct kprobe trampoline_p = {
 	.addr = (kprobe_opcode_t *)&kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index fceb2adfcac7..792f36129062 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -1,10 +1,6 @@
 /*
- * arch/sh/mm/consistent.c
- *
  * Copyright (C) 2004 - 2007  Paul Mundt
  *
- * Declared coherent memory functions based on arch/x86/kernel/pci-dma_32.c
- *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
@@ -13,90 +9,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
-#include <linux/dma-debug.h>
 #include <linux/io.h>
-#include <linux/module.h>
-#include <linux/gfp.h>
-#include <asm/cacheflush.h>
-#include <asm/addrspace.h>
-
-const struct dma_map_ops *dma_ops;
-EXPORT_SYMBOL(dma_ops);
-
-void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_handle, gfp_t gfp,
-				 unsigned long attrs)
-{
-	void *ret, *ret_nocache;
-	int order = get_order(size);
-
-	gfp |= __GFP_ZERO;
-
-	ret = (void *)__get_free_pages(gfp, order);
-	if (!ret)
-		return NULL;
-
-	/*
-	 * Pages from the page allocator may have data present in
-	 * cache. So flush the cache before using uncached memory.
-	 */
-	sh_sync_dma_for_device(ret, size, DMA_BIDIRECTIONAL);
-
-	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
-	if (!ret_nocache) {
-		free_pages((unsigned long)ret, order);
-		return NULL;
-	}
-
-	split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
-
-	*dma_handle = virt_to_phys(ret);
-	if (!WARN_ON(!dev))
-		*dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
-
-	return ret_nocache;
-}
-
-void dma_generic_free_coherent(struct device *dev, size_t size,
-			       void *vaddr, dma_addr_t dma_handle,
-			       unsigned long attrs)
-{
-	int order = get_order(size);
-	unsigned long pfn = dma_handle >> PAGE_SHIFT;
-	int k;
-
-	if (!WARN_ON(!dev))
-		pfn += dev->dma_pfn_offset;
-
-	for (k = 0; k < (1 << order); k++)
-		__free_pages(pfn_to_page(pfn + k), 0);
-
-	iounmap(vaddr);
-}
-
-void sh_sync_dma_for_device(void *vaddr, size_t size,
-		    enum dma_data_direction direction)
-{
-	void *addr;
-
-	addr = __in_29bit_mode() ?
-	       (void *)CAC_ADDR((unsigned long)vaddr) : vaddr;
-
-	switch (direction) {
-	case DMA_FROM_DEVICE:		/* invalidate only */
-		__flush_invalidate_region(addr, size);
-		break;
-	case DMA_TO_DEVICE:		/* writeback only */
-		__flush_wback_region(addr, size);
-		break;
-	case DMA_BIDIRECTIONAL:		/* writeback and invalidate */
-		__flush_purge_region(addr, size);
-		break;
-	default:
-		BUG();
-	}
-}
-EXPORT_SYMBOL(sh_sync_dma_for_device);
 
 static int __init memchunk_setup(char *str)
 {
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 4034035fbede..7713c084d040 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -339,22 +339,12 @@ void __init paging_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
-/*
- * Early initialization for any I/O MMUs we might have.
- */
-static void __init iommu_init(void)
-{
-	no_iommu_init();
-}
-
 unsigned int mem_init_done = 0;
 
 void __init mem_init(void)
 {
 	pg_data_t *pgdat;
 
-	iommu_init();
-
 	high_memory = NULL;
 	for_each_online_pgdat(pgdat)
 		high_memory = max_t(void *, high_memory,
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index ac67828da201..410b263ef5c8 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -13,6 +13,7 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += module.h
+generic-y += msi.h
 generic-y += preempt.h
 generic-y += rwsem.h
 generic-y += serial.h
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index d13ce517f4b9..94c930f0bc62 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -27,17 +27,17 @@ int atomic_fetch_or(int, atomic_t *);
 int atomic_fetch_xor(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
 int atomic_xchg(atomic_t *, int);
-int __atomic_add_unless(atomic_t *, int, int);
+int atomic_fetch_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
+#define atomic_fetch_add_unless	atomic_fetch_add_unless
+
 #define atomic_set_release(v, i)	atomic_set((v), (i))
 
 #define atomic_read(v)          READ_ONCE((v)->counter)
 
 #define atomic_add(i, v)	((void)atomic_add_return( (int)(i), (v)))
 #define atomic_sub(i, v)	((void)atomic_add_return(-(int)(i), (v)))
-#define atomic_inc(v)		((void)atomic_add_return(        1, (v)))
-#define atomic_dec(v)		((void)atomic_add_return(       -1, (v)))
 
 #define atomic_and(i, v)	((void)atomic_fetch_and((i), (v)))
 #define atomic_or(i, v)		((void)atomic_fetch_or((i), (v)))
@@ -46,22 +46,4 @@ void atomic_set(atomic_t *, int);
 #define atomic_sub_return(i, v)	(atomic_add_return(-(int)(i), (v)))
 #define atomic_fetch_sub(i, v)  (atomic_fetch_add (-(int)(i), (v)))
 
-#define atomic_inc_return(v)	(atomic_add_return(        1, (v)))
-#define atomic_dec_return(v)	(atomic_add_return(       -1, (v)))
-
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
 #endif /* !(__ARCH_SPARC_ATOMIC__) */
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 28db058d471b..6963482c81d8 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -50,38 +50,6 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_dec_return(v)   atomic_sub_return(1, v)
-#define atomic64_dec_return(v) atomic64_sub_return(1, v)
-
-#define atomic_inc_return(v)   atomic_add_return(1, v)
-#define atomic64_inc_return(v) atomic64_add_return(1, v)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0)
-
-#define atomic_inc(v) atomic_add(1, v)
-#define atomic64_inc(v) atomic64_add(1, v)
-
-#define atomic_dec(v) atomic_sub(1, v)
-#define atomic64_dec(v) atomic64_sub(1, v)
-
-#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0)
-
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 
 static inline int atomic_xchg(atomic_t *v, int new)
@@ -89,42 +57,11 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	return xchg(&v->counter, new);
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
 long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 9a1e9cbc7e6d..b162c23ae8c2 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -243,35 +243,42 @@ void insb(unsigned long, void *, unsigned long);
 void insw(unsigned long, void *, unsigned long);
 void insl(unsigned long, void *, unsigned long);
 
-static inline void ioread8_rep(void __iomem *port, void *buf, unsigned long count)
+static inline void readsb(void __iomem *port, void *buf, unsigned long count)
 {
 	insb((unsigned long __force)port, buf, count);
 }
-static inline void ioread16_rep(void __iomem *port, void *buf, unsigned long count)
+static inline void readsw(void __iomem *port, void *buf, unsigned long count)
 {
 	insw((unsigned long __force)port, buf, count);
 }
 
-static inline void ioread32_rep(void __iomem *port, void *buf, unsigned long count)
+static inline void readsl(void __iomem *port, void *buf, unsigned long count)
 {
 	insl((unsigned long __force)port, buf, count);
 }
 
-static inline void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count)
+static inline void writesb(void __iomem *port, const void *buf, unsigned long count)
 {
 	outsb((unsigned long __force)port, buf, count);
 }
 
-static inline void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count)
+static inline void writesw(void __iomem *port, const void *buf, unsigned long count)
 {
 	outsw((unsigned long __force)port, buf, count);
 }
 
-static inline void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count)
+static inline void writesl(void __iomem *port, const void *buf, unsigned long count)
 {
 	outsl((unsigned long __force)port, buf, count);
 }
 
+#define ioread8_rep(p,d,l)	readsb(p,d,l)
+#define ioread16_rep(p,d,l)	readsw(p,d,l)
+#define ioread32_rep(p,d,l)	readsl(p,d,l)
+#define iowrite8_rep(p,d,l)	writesb(p,d,l)
+#define iowrite16_rep(p,d,l)	writesw(p,d,l)
+#define iowrite32_rep(p,d,l)	writesl(p,d,l)
+
 /* Valid I/O Space regions are anywhere, because each PCI bus supported
  * can live in an arbitrary area of the physical address range.
  */
diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h
index 3704490b4488..bfcaa6326c20 100644
--- a/arch/sparc/include/asm/kprobes.h
+++ b/arch/sparc/include/asm/kprobes.h
@@ -44,7 +44,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_orig_tnpc;
 	unsigned long kprobe_orig_tstate_pil;
-	struct pt_regs jprobe_saved_regs;
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/sparc/include/asm/msi.h b/arch/sparc/include/asm/msi.h
deleted file mode 100644
index 3c17c1074431..000000000000
--- a/arch/sparc/include/asm/msi.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * msi.h:  Defines specific to the MBus - Sbus - Interface.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- * Copyright (C) 1996 Eddie C. Dost   (ecd@skynet.be)
- */
-
-#ifndef _SPARC_MSI_H
-#define _SPARC_MSI_H
-
-/*
- * Locations of MSI Registers.
- */
-#define MSI_MBUS_ARBEN	0xe0001008	/* MBus Arbiter Enable register */
-
-/*
- * Useful bits in the MSI Registers.
- */
-#define MSI_ASYNC_MODE  0x80000000	/* Operate the MSI asynchronously */
-
-
-static inline void msi_set_sync(void)
-{
-	__asm__ __volatile__ ("lda [%0] %1, %%g3\n\t"
-			      "andn %%g3, %2, %%g3\n\t"
-			      "sta %%g3, [%0] %1\n\t" : :
-			      "r" (MSI_MBUS_ARBEN),
-			      "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3");
-}
-
-#endif /* !(_SPARC_MSI_H) */
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index ab4ba4347941..dfbca2470536 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -147,18 +147,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			kcb->kprobe_status = KPROBE_REENTER;
 			prepare_singlestep(p, regs, kcb);
 			return 1;
-		} else {
-			if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
+		} else if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
 			/* The breakpoint instruction was removed by
 			 * another cpu right after we hit, no further
 			 * handling of this interrupt is appropriate
 			 */
-				ret = 1;
-				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs))
-				goto ss_probe;
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -181,10 +175,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 	prepare_singlestep(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;
@@ -441,53 +437,6 @@ out:
 	exception_exit(prev_state);
 }
 
-/* Jprobes support.  */
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	memcpy(&(kcb->jprobe_saved_regs), regs, sizeof(*regs));
-
-	regs->tpc  = (unsigned long) jp->entry;
-	regs->tnpc = ((unsigned long) jp->entry) + 0x4UL;
-	regs->tstate |= TSTATE_PIL;
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	register unsigned long orig_fp asm("g1");
-
-	orig_fp = kcb->jprobe_saved_regs.u_regs[UREG_FP];
-	__asm__ __volatile__("\n"
-"1:	cmp		%%sp, %0\n\t"
-	"blu,a,pt	%%xcc, 1b\n\t"
-	" restore\n\t"
-	".globl		jprobe_return_trap_instruction\n"
-"jprobe_return_trap_instruction:\n\t"
-	"ta		0x70"
-	: /* no outputs */
-	: "r" (orig_fp));
-}
-
-extern void jprobe_return_trap_instruction(void);
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	u32 *addr = (u32 *) regs->tpc;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (addr == (u32 *) jprobe_return_trap_instruction) {
-		memcpy(regs, &(kcb->jprobe_saved_regs), sizeof(*regs));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
 /* The value stored in the return address register is actually 2
  * instructions before where the callee will return to.
  * Sequences usually look something like this
@@ -562,9 +511,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	regs->tpc = orig_ret_address;
 	regs->tnpc = orig_ret_address + 4;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 2ef8cfa9677e..f0eba72aa1ad 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -814,7 +814,7 @@ static void __init get_tick_patch(void)
 	}
 }
 
-static void init_tick_ops(struct sparc64_tick_ops *ops)
+static void __init init_tick_ops(struct sparc64_tick_ops *ops)
 {
 	unsigned long freq, quotient, tick;
 
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 465a901a0ada..281fa634bb1a 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -95,7 +95,7 @@ int atomic_cmpxchg(atomic_t *v, int old, int new)
 }
 EXPORT_SYMBOL(atomic_cmpxchg);
 
-int __atomic_add_unless(atomic_t *v, int a, int u)
+int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int ret;
 	unsigned long flags;
@@ -107,7 +107,7 @@ int __atomic_add_unless(atomic_t *v, int a, int u)
 	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
 	return ret;
 }
-EXPORT_SYMBOL(__atomic_add_unless);
+EXPORT_SYMBOL(atomic_fetch_add_unless);
 
 /* Atomic operations are already serializing */
 void atomic_set(atomic_t *v, int i)
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 1d70c3f6d986..be9cb0065179 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -37,7 +37,6 @@
 #include <asm/mbus.h>
 #include <asm/page.h>
 #include <asm/asi.h>
-#include <asm/msi.h>
 #include <asm/smp.h>
 #include <asm/io.h>
 
@@ -116,6 +115,25 @@ static inline void srmmu_ctxd_set(ctxd_t *ctxp, pgd_t *pgdp)
 	set_pte((pte_t *)ctxp, pte);
 }
 
+/*
+ * Locations of MSI Registers.
+ */
+#define MSI_MBUS_ARBEN	0xe0001008	/* MBus Arbiter Enable register */
+
+/*
+ * Useful bits in the MSI Registers.
+ */
+#define MSI_ASYNC_MODE  0x80000000	/* Operate the MSI asynchronously */
+
+static void msi_set_sync(void)
+{
+	__asm__ __volatile__ ("lda [%0] %1, %%g3\n\t"
+			      "andn %%g3, %2, %%g3\n\t"
+			      "sta %%g3, [%0] %1\n\t" : :
+			      "r" (MSI_MBUS_ARBEN),
+			      "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3");
+}
+
 void pmd_set(pmd_t *pmdp, pte_t *ptep)
 {
 	unsigned long ptp;	/* Physical address, shifted right by 4 */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f1dbb4ee19d7..6d36e6b4b13a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -63,7 +63,7 @@ config X86
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
-	select ARCH_HAS_UACCESS_MCSAFE		if X86_64
+	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
@@ -75,6 +75,7 @@ config X86
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_SUPPORTS_ACPI
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
@@ -180,13 +181,14 @@ config X86
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_RELIABLE_STACKTRACE		if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION
+	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
 	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if X86_64
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
+	select HOTPLUG_SMT			if SMP
 	select IRQ_FORCED_THREADING
 	select NEED_SG_DMA_LENGTH
 	select PCI_LOCKLESS_CONFIG
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index a08e82856563..7e3c07d6ad42 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -80,11 +80,6 @@ ifeq ($(CONFIG_X86_32),y)
         # alignment instructions.
         KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4))
 
-        # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
-        # a lot more stack due to the lack of sharing of stacklots:
-        KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0400, \
-				$(call cc-option,-fno-unit-at-a-time))
-
         # CPU-specific tuning. Anything which can be shared with UML should go here.
         include arch/x86/Makefile_32.cpu
         KBUILD_CFLAGS += $(cflags-y)
diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h
index 0d41d68131cc..2e1382486e91 100644
--- a/arch/x86/boot/bitops.h
+++ b/arch/x86/boot/bitops.h
@@ -17,6 +17,7 @@
 #define _LINUX_BITOPS_H		/* Inhibit inclusion of <linux/bitops.h> */
 
 #include <linux/types.h>
+#include <asm/asm.h>
 
 static inline bool constant_test_bit(int nr, const void *addr)
 {
@@ -28,7 +29,7 @@ static inline bool variable_test_bit(int nr, const void *addr)
 	bool v;
 	const u32 *p = (const u32 *)addr;
 
-	asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));
+	asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr));
 	return v;
 }
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index fa42f895fdde..169c2feda14a 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -106,9 +106,13 @@ define cmd_check_data_rel
 	done
 endef
 
+# We need to run two commands under "if_changed", so merge them into a
+# single invocation.
+quiet_cmd_check-and-link-vmlinux = LD      $@
+      cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
+
 $(obj)/vmlinux: $(vmlinux-objs-y) FORCE
-	$(call if_changed,check_data_rel)
-	$(call if_changed,ld)
+	$(call if_changed,check-and-link-vmlinux)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
 $(obj)/vmlinux.bin: vmlinux FORCE
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index e57665b4ba1c..1458b1700fc7 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -34,74 +34,13 @@ static void setup_boot_services##bits(struct efi_config *c)		\
 									\
 	table = (typeof(table))sys_table;				\
 									\
-	c->runtime_services = table->runtime;				\
-	c->boot_services = table->boottime;				\
-	c->text_output = table->con_out;				\
+	c->runtime_services	= table->runtime;			\
+	c->boot_services	= table->boottime;			\
+	c->text_output		= table->con_out;			\
 }
 BOOT_SERVICES(32);
 BOOT_SERVICES(64);
 
-static inline efi_status_t __open_volume32(void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_32_t *image = __image;
-	efi_file_handle_32_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-	unsigned long func;
-
-	status = efi_call_early(handle_protocol, handle,
-				&fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	func = (unsigned long)io->open_volume;
-	status = efi_early->call(func, io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table, "Failed to open volume\n");
-
-	*__fh = fh;
-	return status;
-}
-
-static inline efi_status_t __open_volume64(void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_64_t *image = __image;
-	efi_file_handle_64_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-	unsigned long func;
-
-	status = efi_call_early(handle_protocol, handle,
-				&fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	func = (unsigned long)io->open_volume;
-	status = efi_early->call(func, io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table, "Failed to open volume\n");
-
-	*__fh = fh;
-	return status;
-}
-
-efi_status_t
-efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
-{
-	if (efi_early->is64)
-		return __open_volume64(__image, __fh);
-
-	return __open_volume32(__image, __fh);
-}
-
 void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 {
 	efi_call_proto(efi_simple_text_output_protocol, output_string,
@@ -109,23 +48,17 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 }
 
 static efi_status_t
-__setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
+preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 {
 	struct pci_setup_rom *rom = NULL;
 	efi_status_t status;
 	unsigned long size;
-	uint64_t attributes, romsize;
+	uint64_t romsize;
 	void *romimage;
 
-	status = efi_call_proto(efi_pci_io_protocol, attributes, pci,
-				EfiPciIoAttributeOperationGet, 0ULL,
-				&attributes);
-	if (status != EFI_SUCCESS)
-		return status;
-
 	/*
-	 * Some firmware images contain EFI function pointers at the place where the
-	 * romimage and romsize fields are supposed to be. Typically the EFI
+	 * Some firmware images contain EFI function pointers at the place where
+	 * the romimage and romsize fields are supposed to be. Typically the EFI
 	 * code is mapped at high addresses, translating to an unrealistically
 	 * large romsize. The UEFI spec limits the size of option ROMs to 16
 	 * MiB so we reject any ROMs over 16 MiB in size to catch this.
@@ -140,16 +73,16 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 
 	status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for rom\n");
+		efi_printk(sys_table, "Failed to allocate memory for 'rom'\n");
 		return status;
 	}
 
 	memset(rom, 0, sizeof(*rom));
 
-	rom->data.type = SETUP_PCI;
-	rom->data.len = size - sizeof(struct setup_data);
-	rom->data.next = 0;
-	rom->pcilen = pci->romsize;
+	rom->data.type	= SETUP_PCI;
+	rom->data.len	= size - sizeof(struct setup_data);
+	rom->data.next	= 0;
+	rom->pcilen	= pci->romsize;
 	*__rom = rom;
 
 	status = efi_call_proto(efi_pci_io_protocol, pci.read, pci,
@@ -185,96 +118,6 @@ free_struct:
 	return status;
 }
 
-static void
-setup_efi_pci32(struct boot_params *params, void **pci_handle,
-		unsigned long size)
-{
-	efi_pci_io_protocol_t *pci = NULL;
-	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
-	u32 *handles = (u32 *)(unsigned long)pci_handle;
-	efi_status_t status;
-	unsigned long nr_pci;
-	struct setup_data *data;
-	int i;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	nr_pci = size / sizeof(u32);
-	for (i = 0; i < nr_pci; i++) {
-		struct pci_setup_rom *rom = NULL;
-		u32 h = handles[i];
-
-		status = efi_call_early(handle_protocol, h,
-					&pci_proto, (void **)&pci);
-
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (!pci)
-			continue;
-
-		status = __setup_efi_pci(pci, &rom);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (data)
-			data->next = (unsigned long)rom;
-		else
-			params->hdr.setup_data = (unsigned long)rom;
-
-		data = (struct setup_data *)rom;
-
-	}
-}
-
-static void
-setup_efi_pci64(struct boot_params *params, void **pci_handle,
-		unsigned long size)
-{
-	efi_pci_io_protocol_t *pci = NULL;
-	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
-	u64 *handles = (u64 *)(unsigned long)pci_handle;
-	efi_status_t status;
-	unsigned long nr_pci;
-	struct setup_data *data;
-	int i;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	nr_pci = size / sizeof(u64);
-	for (i = 0; i < nr_pci; i++) {
-		struct pci_setup_rom *rom = NULL;
-		u64 h = handles[i];
-
-		status = efi_call_early(handle_protocol, h,
-					&pci_proto, (void **)&pci);
-
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (!pci)
-			continue;
-
-		status = __setup_efi_pci(pci, &rom);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (data)
-			data->next = (unsigned long)rom;
-		else
-			params->hdr.setup_data = (unsigned long)rom;
-
-		data = (struct setup_data *)rom;
-
-	}
-}
-
 /*
  * There's no way to return an informative status from this function,
  * because any analysis (and printing of error messages) needs to be
@@ -290,6 +133,9 @@ static void setup_efi_pci(struct boot_params *params)
 	void **pci_handle = NULL;
 	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
 	unsigned long size = 0;
+	unsigned long nr_pci;
+	struct setup_data *data;
+	int i;
 
 	status = efi_call_early(locate_handle,
 				EFI_LOCATE_BY_PROTOCOL,
@@ -301,7 +147,7 @@ static void setup_efi_pci(struct boot_params *params)
 					size, (void **)&pci_handle);
 
 		if (status != EFI_SUCCESS) {
-			efi_printk(sys_table, "Failed to alloc mem for pci_handle\n");
+			efi_printk(sys_table, "Failed to allocate memory for 'pci_handle'\n");
 			return;
 		}
 
@@ -313,10 +159,34 @@ static void setup_efi_pci(struct boot_params *params)
 	if (status != EFI_SUCCESS)
 		goto free_handle;
 
-	if (efi_early->is64)
-		setup_efi_pci64(params, pci_handle, size);
-	else
-		setup_efi_pci32(params, pci_handle, size);
+	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+	while (data && data->next)
+		data = (struct setup_data *)(unsigned long)data->next;
+
+	nr_pci = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32));
+	for (i = 0; i < nr_pci; i++) {
+		efi_pci_io_protocol_t *pci = NULL;
+		struct pci_setup_rom *rom;
+
+		status = efi_call_early(handle_protocol,
+					efi_is_64bit() ? ((u64 *)pci_handle)[i]
+						       : ((u32 *)pci_handle)[i],
+					&pci_proto, (void **)&pci);
+		if (status != EFI_SUCCESS || !pci)
+			continue;
+
+		status = preserve_pci_rom_image(pci, &rom);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		if (data)
+			data->next = (unsigned long)rom;
+		else
+			params->hdr.setup_data = (unsigned long)rom;
+
+		data = (struct setup_data *)rom;
+	}
 
 free_handle:
 	efi_call_early(free_pool, pci_handle);
@@ -347,8 +217,7 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 		status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
 					size + sizeof(struct setup_data), &new);
 		if (status != EFI_SUCCESS) {
-			efi_printk(sys_table,
-					"Failed to alloc mem for properties\n");
+			efi_printk(sys_table, "Failed to allocate memory for 'properties'\n");
 			return;
 		}
 
@@ -364,9 +233,9 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 	new->next = 0;
 
 	data = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
-	if (!data)
+	if (!data) {
 		boot_params->hdr.setup_data = (unsigned long)new;
-	else {
+	} else {
 		while (data->next)
 			data = (struct setup_data *)(unsigned long)data->next;
 		data->next = (unsigned long)new;
@@ -386,81 +255,55 @@ static void setup_quirks(struct boot_params *boot_params)
 	}
 }
 
+/*
+ * See if we have Universal Graphics Adapter (UGA) protocol
+ */
 static efi_status_t
-setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size)
 {
-	struct efi_uga_draw_protocol *uga = NULL, *first_uga;
-	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+	efi_status_t status;
+	u32 width, height;
+	void **uga_handle = NULL;
+	efi_uga_draw_protocol_t *uga = NULL, *first_uga;
 	unsigned long nr_ugas;
-	u32 *handles = (u32 *)uga_handle;
-	efi_status_t status = EFI_INVALID_PARAMETER;
 	int i;
 
-	first_uga = NULL;
-	nr_ugas = size / sizeof(u32);
-	for (i = 0; i < nr_ugas; i++) {
-		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
-		u32 w, h, depth, refresh;
-		void *pciio;
-		u32 handle = handles[i];
-
-		status = efi_call_early(handle_protocol, handle,
-					&uga_proto, (void **)&uga);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
-
-		status = efi_early->call((unsigned long)uga->get_mode, uga,
-					 &w, &h, &depth, &refresh);
-		if (status == EFI_SUCCESS && (!first_uga || pciio)) {
-			*width = w;
-			*height = h;
-
-			/*
-			 * Once we've found a UGA supporting PCIIO,
-			 * don't bother looking any further.
-			 */
-			if (pciio)
-				break;
-
-			first_uga = uga;
-		}
-	}
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				size, (void **)&uga_handle);
+	if (status != EFI_SUCCESS)
+		return status;
 
-	return status;
-}
+	status = efi_call_early(locate_handle,
+				EFI_LOCATE_BY_PROTOCOL,
+				uga_proto, NULL, &size, uga_handle);
+	if (status != EFI_SUCCESS)
+		goto free_handle;
 
-static efi_status_t
-setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
-{
-	struct efi_uga_draw_protocol *uga = NULL, *first_uga;
-	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
-	unsigned long nr_ugas;
-	u64 *handles = (u64 *)uga_handle;
-	efi_status_t status = EFI_INVALID_PARAMETER;
-	int i;
+	height = 0;
+	width = 0;
 
 	first_uga = NULL;
-	nr_ugas = size / sizeof(u64);
+	nr_ugas = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32));
 	for (i = 0; i < nr_ugas; i++) {
 		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
 		u32 w, h, depth, refresh;
 		void *pciio;
-		u64 handle = handles[i];
+		unsigned long handle = efi_is_64bit() ? ((u64 *)uga_handle)[i]
+						      : ((u32 *)uga_handle)[i];
 
 		status = efi_call_early(handle_protocol, handle,
-					&uga_proto, (void **)&uga);
+					uga_proto, (void **)&uga);
 		if (status != EFI_SUCCESS)
 			continue;
 
+		pciio = NULL;
 		efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
 
-		status = efi_early->call((unsigned long)uga->get_mode, uga,
-					 &w, &h, &depth, &refresh);
+		status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga,
+					&w, &h, &depth, &refresh);
 		if (status == EFI_SUCCESS && (!first_uga || pciio)) {
-			*width = w;
-			*height = h;
+			width = w;
+			height = h;
 
 			/*
 			 * Once we've found a UGA supporting PCIIO,
@@ -473,59 +316,28 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 		}
 	}
 
-	return status;
-}
-
-/*
- * See if we have Universal Graphics Adapter (UGA) protocol
- */
-static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
-			      unsigned long size)
-{
-	efi_status_t status;
-	u32 width, height;
-	void **uga_handle = NULL;
-
-	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
-				size, (void **)&uga_handle);
-	if (status != EFI_SUCCESS)
-		return status;
-
-	status = efi_call_early(locate_handle,
-				EFI_LOCATE_BY_PROTOCOL,
-				uga_proto, NULL, &size, uga_handle);
-	if (status != EFI_SUCCESS)
-		goto free_handle;
-
-	height = 0;
-	width = 0;
-
-	if (efi_early->is64)
-		status = setup_uga64(uga_handle, size, &width, &height);
-	else
-		status = setup_uga32(uga_handle, size, &width, &height);
-
 	if (!width && !height)
 		goto free_handle;
 
 	/* EFI framebuffer */
-	si->orig_video_isVGA = VIDEO_TYPE_EFI;
+	si->orig_video_isVGA	= VIDEO_TYPE_EFI;
 
-	si->lfb_depth = 32;
-	si->lfb_width = width;
-	si->lfb_height = height;
+	si->lfb_depth		= 32;
+	si->lfb_width		= width;
+	si->lfb_height		= height;
 
-	si->red_size = 8;
-	si->red_pos = 16;
-	si->green_size = 8;
-	si->green_pos = 8;
-	si->blue_size = 8;
-	si->blue_pos = 0;
-	si->rsvd_size = 8;
-	si->rsvd_pos = 24;
+	si->red_size		= 8;
+	si->red_pos		= 16;
+	si->green_size		= 8;
+	si->green_pos		= 8;
+	si->blue_size		= 8;
+	si->blue_pos		= 0;
+	si->rsvd_size		= 8;
+	si->rsvd_pos		= 24;
 
 free_handle:
 	efi_call_early(free_pool, uga_handle);
+
 	return status;
 }
 
@@ -592,7 +404,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		return NULL;
 
-	if (efi_early->is64)
+	if (efi_is_64bit())
 		setup_boot_services64(efi_early);
 	else
 		setup_boot_services32(efi_early);
@@ -607,7 +419,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	status = efi_low_alloc(sys_table, 0x4000, 1,
 			       (unsigned long *)&boot_params);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc lowmem for boot params\n");
+		efi_printk(sys_table, "Failed to allocate lowmem for boot params\n");
 		return NULL;
 	}
 
@@ -623,9 +435,9 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	 * Fill out some of the header fields ourselves because the
 	 * EFI firmware loader doesn't load the first sector.
 	 */
-	hdr->root_flags = 1;
-	hdr->vid_mode = 0xffff;
-	hdr->boot_flag = 0xAA55;
+	hdr->root_flags	= 1;
+	hdr->vid_mode	= 0xffff;
+	hdr->boot_flag	= 0xAA55;
 
 	hdr->type_of_loader = 0x21;
 
@@ -633,6 +445,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size);
 	if (!cmdline_ptr)
 		goto fail;
+
 	hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
 	/* Fill in upper bits of command line address, NOP on 32 bit  */
 	boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32;
@@ -669,10 +482,12 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	boot_params->ext_ramdisk_size  = (u64)ramdisk_size >> 32;
 
 	return boot_params;
+
 fail2:
 	efi_free(sys_table, options_size, hdr->cmd_line_ptr);
 fail:
 	efi_free(sys_table, 0x4000, (unsigned long)boot_params);
+
 	return NULL;
 }
 
@@ -684,7 +499,7 @@ static void add_e820ext(struct boot_params *params,
 	unsigned long size;
 
 	e820ext->type = SETUP_E820_EXT;
-	e820ext->len = nr_entries * sizeof(struct boot_e820_entry);
+	e820ext->len  = nr_entries * sizeof(struct boot_e820_entry);
 	e820ext->next = 0;
 
 	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
@@ -698,8 +513,8 @@ static void add_e820ext(struct boot_params *params,
 		params->hdr.setup_data = (unsigned long)e820ext;
 }
 
-static efi_status_t setup_e820(struct boot_params *params,
-			       struct setup_data *e820ext, u32 e820ext_size)
+static efi_status_t
+setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size)
 {
 	struct boot_e820_entry *entry = params->e820_table;
 	struct efi_info *efi = &params->efi_info;
@@ -820,11 +635,10 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
 }
 
 struct exit_boot_struct {
-	struct boot_params *boot_params;
-	struct efi_info *efi;
-	struct setup_data *e820ext;
-	__u32 e820ext_size;
-	bool is64;
+	struct boot_params	*boot_params;
+	struct efi_info		*efi;
+	struct setup_data	*e820ext;
+	__u32			e820ext_size;
 };
 
 static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
@@ -851,25 +665,25 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
 		first = false;
 	}
 
-	signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+	signature = efi_is_64bit() ? EFI64_LOADER_SIGNATURE
+				   : EFI32_LOADER_SIGNATURE;
 	memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
 
-	p->efi->efi_systab = (unsigned long)sys_table_arg;
-	p->efi->efi_memdesc_size = *map->desc_size;
-	p->efi->efi_memdesc_version = *map->desc_ver;
-	p->efi->efi_memmap = (unsigned long)*map->map;
-	p->efi->efi_memmap_size = *map->map_size;
+	p->efi->efi_systab		= (unsigned long)sys_table_arg;
+	p->efi->efi_memdesc_size	= *map->desc_size;
+	p->efi->efi_memdesc_version	= *map->desc_ver;
+	p->efi->efi_memmap		= (unsigned long)*map->map;
+	p->efi->efi_memmap_size		= *map->map_size;
 
 #ifdef CONFIG_X86_64
-	p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
-	p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
+	p->efi->efi_systab_hi		= (unsigned long)sys_table_arg >> 32;
+	p->efi->efi_memmap_hi		= (unsigned long)*map->map >> 32;
 #endif
 
 	return EFI_SUCCESS;
 }
 
-static efi_status_t exit_boot(struct boot_params *boot_params,
-			      void *handle, bool is64)
+static efi_status_t exit_boot(struct boot_params *boot_params, void *handle)
 {
 	unsigned long map_sz, key, desc_size, buff_size;
 	efi_memory_desc_t *mem_map;
@@ -880,17 +694,16 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 	struct efi_boot_memmap map;
 	struct exit_boot_struct priv;
 
-	map.map =		&mem_map;
-	map.map_size =		&map_sz;
-	map.desc_size =		&desc_size;
-	map.desc_ver =		&desc_version;
-	map.key_ptr =		&key;
-	map.buff_size =		&buff_size;
-	priv.boot_params =	boot_params;
-	priv.efi =		&boot_params->efi_info;
-	priv.e820ext =		NULL;
-	priv.e820ext_size =	0;
-	priv.is64 =		is64;
+	map.map			= &mem_map;
+	map.map_size		= &map_sz;
+	map.desc_size		= &desc_size;
+	map.desc_ver		= &desc_version;
+	map.key_ptr		= &key;
+	map.buff_size		= &buff_size;
+	priv.boot_params	= boot_params;
+	priv.efi		= &boot_params->efi_info;
+	priv.e820ext		= NULL;
+	priv.e820ext_size	= 0;
 
 	/* Might as well exit boot services now */
 	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
@@ -898,10 +711,11 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 	if (status != EFI_SUCCESS)
 		return status;
 
-	e820ext = priv.e820ext;
-	e820ext_size = priv.e820ext_size;
+	e820ext			= priv.e820ext;
+	e820ext_size		= priv.e820ext_size;
+
 	/* Historic? */
-	boot_params->alt_mem_k = 32 * 1024;
+	boot_params->alt_mem_k	= 32 * 1024;
 
 	status = setup_e820(boot_params, e820ext, e820ext_size);
 	if (status != EFI_SUCCESS)
@@ -914,8 +728,8 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
  * On success we return a pointer to a boot_params structure, and NULL
  * on failure.
  */
-struct boot_params *efi_main(struct efi_config *c,
-			     struct boot_params *boot_params)
+struct boot_params *
+efi_main(struct efi_config *c, struct boot_params *boot_params)
 {
 	struct desc_ptr *gdt = NULL;
 	efi_loaded_image_t *image;
@@ -924,13 +738,11 @@ struct boot_params *efi_main(struct efi_config *c,
 	struct desc_struct *desc;
 	void *handle;
 	efi_system_table_t *_table;
-	bool is64;
 
 	efi_early = c;
 
 	_table = (efi_system_table_t *)(unsigned long)efi_early->table;
 	handle = (void *)(unsigned long)efi_early->image_handle;
-	is64 = efi_early->is64;
 
 	sys_table = _table;
 
@@ -938,7 +750,7 @@ struct boot_params *efi_main(struct efi_config *c,
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		goto fail;
 
-	if (is64)
+	if (efi_is_64bit())
 		setup_boot_services64(efi_early);
 	else
 		setup_boot_services32(efi_early);
@@ -963,7 +775,7 @@ struct boot_params *efi_main(struct efi_config *c,
 	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
 				sizeof(*gdt), (void **)&gdt);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
+		efi_printk(sys_table, "Failed to allocate memory for 'gdt' structure\n");
 		goto fail;
 	}
 
@@ -971,7 +783,7 @@ struct boot_params *efi_main(struct efi_config *c,
 	status = efi_low_alloc(sys_table, gdt->size, 8,
 			   (unsigned long *)&gdt->address);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for gdt\n");
+		efi_printk(sys_table, "Failed to allocate memory for 'gdt'\n");
 		goto fail;
 	}
 
@@ -994,7 +806,7 @@ struct boot_params *efi_main(struct efi_config *c,
 		hdr->code32_start = bzimage_addr;
 	}
 
-	status = exit_boot(boot_params, handle, is64);
+	status = exit_boot(boot_params, handle);
 	if (status != EFI_SUCCESS) {
 		efi_printk(sys_table, "exit_boot() failed!\n");
 		goto fail;
@@ -1008,19 +820,20 @@ struct boot_params *efi_main(struct efi_config *c,
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		/* __KERNEL32_CS */
-		desc->limit0 = 0xffff;
-		desc->base0 = 0x0000;
-		desc->base1 = 0x0000;
-		desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
-		desc->s = DESC_TYPE_CODE_DATA;
-		desc->dpl = 0;
-		desc->p = 1;
-		desc->limit1 = 0xf;
-		desc->avl = 0;
-		desc->l = 0;
-		desc->d = SEG_OP_SIZE_32BIT;
-		desc->g = SEG_GRANULARITY_4KB;
-		desc->base2 = 0x00;
+		desc->limit0	= 0xffff;
+		desc->base0	= 0x0000;
+		desc->base1	= 0x0000;
+		desc->type	= SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+		desc->s		= DESC_TYPE_CODE_DATA;
+		desc->dpl	= 0;
+		desc->p		= 1;
+		desc->limit1	= 0xf;
+		desc->avl	= 0;
+		desc->l		= 0;
+		desc->d		= SEG_OP_SIZE_32BIT;
+		desc->g		= SEG_GRANULARITY_4KB;
+		desc->base2	= 0x00;
+
 		desc++;
 	} else {
 		/* Second entry is unused on 32-bit */
@@ -1028,15 +841,16 @@ struct boot_params *efi_main(struct efi_config *c,
 	}
 
 	/* __KERNEL_CS */
-	desc->limit0 = 0xffff;
-	desc->base0 = 0x0000;
-	desc->base1 = 0x0000;
-	desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
-	desc->s = DESC_TYPE_CODE_DATA;
-	desc->dpl = 0;
-	desc->p = 1;
-	desc->limit1 = 0xf;
-	desc->avl = 0;
+	desc->limit0	= 0xffff;
+	desc->base0	= 0x0000;
+	desc->base1	= 0x0000;
+	desc->type	= SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+	desc->s		= DESC_TYPE_CODE_DATA;
+	desc->dpl	= 0;
+	desc->p		= 1;
+	desc->limit1	= 0xf;
+	desc->avl	= 0;
+
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		desc->l = 1;
 		desc->d = 0;
@@ -1044,41 +858,41 @@ struct boot_params *efi_main(struct efi_config *c,
 		desc->l = 0;
 		desc->d = SEG_OP_SIZE_32BIT;
 	}
-	desc->g = SEG_GRANULARITY_4KB;
-	desc->base2 = 0x00;
+	desc->g		= SEG_GRANULARITY_4KB;
+	desc->base2	= 0x00;
 	desc++;
 
 	/* __KERNEL_DS */
-	desc->limit0 = 0xffff;
-	desc->base0 = 0x0000;
-	desc->base1 = 0x0000;
-	desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
-	desc->s = DESC_TYPE_CODE_DATA;
-	desc->dpl = 0;
-	desc->p = 1;
-	desc->limit1 = 0xf;
-	desc->avl = 0;
-	desc->l = 0;
-	desc->d = SEG_OP_SIZE_32BIT;
-	desc->g = SEG_GRANULARITY_4KB;
-	desc->base2 = 0x00;
+	desc->limit0	= 0xffff;
+	desc->base0	= 0x0000;
+	desc->base1	= 0x0000;
+	desc->type	= SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
+	desc->s		= DESC_TYPE_CODE_DATA;
+	desc->dpl	= 0;
+	desc->p		= 1;
+	desc->limit1	= 0xf;
+	desc->avl	= 0;
+	desc->l		= 0;
+	desc->d		= SEG_OP_SIZE_32BIT;
+	desc->g		= SEG_GRANULARITY_4KB;
+	desc->base2	= 0x00;
 	desc++;
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		/* Task segment value */
-		desc->limit0 = 0x0000;
-		desc->base0 = 0x0000;
-		desc->base1 = 0x0000;
-		desc->type = SEG_TYPE_TSS;
-		desc->s = 0;
-		desc->dpl = 0;
-		desc->p = 1;
-		desc->limit1 = 0x0;
-		desc->avl = 0;
-		desc->l = 0;
-		desc->d = 0;
-		desc->g = SEG_GRANULARITY_4KB;
-		desc->base2 = 0x00;
+		desc->limit0	= 0x0000;
+		desc->base0	= 0x0000;
+		desc->base1	= 0x0000;
+		desc->type	= SEG_TYPE_TSS;
+		desc->s		= 0;
+		desc->dpl	= 0;
+		desc->p		= 1;
+		desc->limit1	= 0x0;
+		desc->avl	= 0;
+		desc->l		= 0;
+		desc->d		= 0;
+		desc->g		= SEG_GRANULARITY_4KB;
+		desc->base2	= 0x00;
 		desc++;
 	}
 
@@ -1088,5 +902,6 @@ struct boot_params *efi_main(struct efi_config *c,
 	return boot_params;
 fail:
 	efi_printk(sys_table, "efi_main() failed!\n");
+
 	return NULL;
 }
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index e799dc5c6448..8297387c4676 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -12,22 +12,22 @@
 
 #define DESC_TYPE_CODE_DATA	(1 << 0)
 
-struct efi_uga_draw_protocol_32 {
+typedef struct {
 	u32 get_mode;
 	u32 set_mode;
 	u32 blt;
-};
+} efi_uga_draw_protocol_32_t;
 
-struct efi_uga_draw_protocol_64 {
+typedef struct {
 	u64 get_mode;
 	u64 set_mode;
 	u64 blt;
-};
+} efi_uga_draw_protocol_64_t;
 
-struct efi_uga_draw_protocol {
+typedef struct {
 	void *get_mode;
 	void *set_mode;
 	void *blt;
-};
+} efi_uga_draw_protocol_t;
 
 #endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index b87a7582853d..302517929932 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -102,7 +102,7 @@ static bool memmap_too_large;
 
 
 /* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */
-unsigned long long mem_limit = ULLONG_MAX;
+static unsigned long long mem_limit = ULLONG_MAX;
 
 
 enum mem_avoid_index {
@@ -215,7 +215,36 @@ static void mem_avoid_memmap(char *str)
 		memmap_too_large = true;
 }
 
-static int handle_mem_memmap(void)
+/* Store the number of 1GB huge pages which users specified: */
+static unsigned long max_gb_huge_pages;
+
+static void parse_gb_huge_pages(char *param, char *val)
+{
+	static bool gbpage_sz;
+	char *p;
+
+	if (!strcmp(param, "hugepagesz")) {
+		p = val;
+		if (memparse(p, &p) != PUD_SIZE) {
+			gbpage_sz = false;
+			return;
+		}
+
+		if (gbpage_sz)
+			warn("Repeatedly set hugeTLB page size of 1G!\n");
+		gbpage_sz = true;
+		return;
+	}
+
+	if (!strcmp(param, "hugepages") && gbpage_sz) {
+		p = val;
+		max_gb_huge_pages = simple_strtoull(p, &p, 0);
+		return;
+	}
+}
+
+
+static int handle_mem_options(void)
 {
 	char *args = (char *)get_cmd_line_ptr();
 	size_t len = strlen((char *)args);
@@ -223,7 +252,8 @@ static int handle_mem_memmap(void)
 	char *param, *val;
 	u64 mem_size;
 
-	if (!strstr(args, "memmap=") && !strstr(args, "mem="))
+	if (!strstr(args, "memmap=") && !strstr(args, "mem=") &&
+		!strstr(args, "hugepages"))
 		return 0;
 
 	tmp_cmdline = malloc(len + 1);
@@ -248,6 +278,8 @@ static int handle_mem_memmap(void)
 
 		if (!strcmp(param, "memmap")) {
 			mem_avoid_memmap(val);
+		} else if (strstr(param, "hugepages")) {
+			parse_gb_huge_pages(param, val);
 		} else if (!strcmp(param, "mem")) {
 			char *p = val;
 
@@ -387,7 +419,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	/* We don't need to set a mapping for setup_data. */
 
 	/* Mark the memmap regions we need to avoid */
-	handle_mem_memmap();
+	handle_mem_options();
 
 #ifdef CONFIG_X86_VERBOSE_BOOTUP
 	/* Make sure video RAM can be used. */
@@ -466,6 +498,60 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 	}
 }
 
+/*
+ * Skip as many 1GB huge pages as possible in the passed region
+ * according to the number which users specified:
+ */
+static void
+process_gb_huge_pages(struct mem_vector *region, unsigned long image_size)
+{
+	unsigned long addr, size = 0;
+	struct mem_vector tmp;
+	int i = 0;
+
+	if (!max_gb_huge_pages) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	addr = ALIGN(region->start, PUD_SIZE);
+	/* Did we raise the address above the passed in memory entry? */
+	if (addr < region->start + region->size)
+		size = region->size - (addr - region->start);
+
+	/* Check how many 1GB huge pages can be filtered out: */
+	while (size > PUD_SIZE && max_gb_huge_pages) {
+		size -= PUD_SIZE;
+		max_gb_huge_pages--;
+		i++;
+	}
+
+	/* No good 1GB huge pages found: */
+	if (!i) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	/*
+	 * Skip those 'i'*1GB good huge pages, and continue checking and
+	 * processing the remaining head or tail part of the passed region
+	 * if available.
+	 */
+
+	if (addr >= region->start + image_size) {
+		tmp.start = region->start;
+		tmp.size = addr - region->start;
+		store_slot_info(&tmp, image_size);
+	}
+
+	size  = region->size - (addr - region->start) - i * PUD_SIZE;
+	if (size >= image_size) {
+		tmp.start = addr + i * PUD_SIZE;
+		tmp.size = size;
+		store_slot_info(&tmp, image_size);
+	}
+}
+
 static unsigned long slots_fetch_random(void)
 {
 	unsigned long slot;
@@ -546,7 +632,7 @@ static void process_mem_region(struct mem_vector *entry,
 
 		/* If nothing overlaps, store the region and return. */
 		if (!mem_avoid_overlap(&region, &overlap)) {
-			store_slot_info(&region, image_size);
+			process_gb_huge_pages(&region, image_size);
 			return;
 		}
 
@@ -556,7 +642,7 @@ static void process_mem_region(struct mem_vector *entry,
 
 			beginning.start = region.start;
 			beginning.size = overlap.start - region.start;
-			store_slot_info(&beginning, image_size);
+			process_gb_huge_pages(&beginning, image_size);
 		}
 
 		/* Return if overlap extends to or past end of region. */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 8c5107545251..9e2157371491 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,3 +1,4 @@
+#include <asm/e820/types.h>
 #include <asm/processor.h>
 #include "pgtable.h"
 #include "../string.h"
@@ -34,10 +35,62 @@ unsigned long *trampoline_32bit __section(.data);
 extern struct boot_params *boot_params;
 int cmdline_find_option_bool(const char *option);
 
+static unsigned long find_trampoline_placement(void)
+{
+	unsigned long bios_start, ebda_start;
+	unsigned long trampoline_start;
+	struct boot_e820_entry *entry;
+	int i;
+
+	/*
+	 * Find a suitable spot for the trampoline.
+	 * This code is based on reserve_bios_regions().
+	 */
+
+	ebda_start = *(unsigned short *)0x40e << 4;
+	bios_start = *(unsigned short *)0x413 << 10;
+
+	if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
+		bios_start = BIOS_START_MAX;
+
+	if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
+		bios_start = ebda_start;
+
+	bios_start = round_down(bios_start, PAGE_SIZE);
+
+	/* Find the first usable memory region under bios_start. */
+	for (i = boot_params->e820_entries - 1; i >= 0; i--) {
+		entry = &boot_params->e820_table[i];
+
+		/* Skip all entries above bios_start. */
+		if (bios_start <= entry->addr)
+			continue;
+
+		/* Skip non-RAM entries. */
+		if (entry->type != E820_TYPE_RAM)
+			continue;
+
+		/* Adjust bios_start to the end of the entry if needed. */
+		if (bios_start > entry->addr + entry->size)
+			bios_start = entry->addr + entry->size;
+
+		/* Keep bios_start page-aligned. */
+		bios_start = round_down(bios_start, PAGE_SIZE);
+
+		/* Skip the entry if it's too small. */
+		if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr)
+			continue;
+
+		break;
+	}
+
+	/* Place the trampoline just below the end of low memory */
+	return bios_start - TRAMPOLINE_32BIT_SIZE;
+}
+
 struct paging_config paging_prepare(void *rmode)
 {
 	struct paging_config paging_config = {};
-	unsigned long bios_start, ebda_start;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
 	boot_params = rmode;
@@ -61,23 +114,7 @@ struct paging_config paging_prepare(void *rmode)
 		paging_config.l5_required = 1;
 	}
 
-	/*
-	 * Find a suitable spot for the trampoline.
-	 * This code is based on reserve_bios_regions().
-	 */
-
-	ebda_start = *(unsigned short *)0x40e << 4;
-	bios_start = *(unsigned short *)0x413 << 10;
-
-	if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
-		bios_start = BIOS_START_MAX;
-
-	if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
-		bios_start = ebda_start;
-
-	/* Place the trampoline just below the end of low memory, aligned to 4k */
-	paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE;
-	paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE);
+	paging_config.trampoline_start = find_trampoline_placement();
 
 	trampoline_32bit = (unsigned long *)paging_config.trampoline_start;
 
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 16f49123d747..c4428a176973 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/types.h>
+#include <asm/asm.h>
 #include "ctype.h"
 #include "string.h"
 
@@ -28,8 +29,8 @@
 int memcmp(const void *s1, const void *s2, size_t len)
 {
 	bool diff;
-	asm("repe; cmpsb; setnz %0"
-	    : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm("repe; cmpsb" CC_SET(nz)
+	    : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 
diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
index 9254e0b6cc06..5f7e43d4f64a 100644
--- a/arch/x86/crypto/aegis128-aesni-asm.S
+++ b/arch/x86/crypto/aegis128-aesni-asm.S
@@ -75,7 +75,7 @@
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG, MSG
 
 	mov LEN, %r8
@@ -535,6 +535,7 @@ ENTRY(crypto_aegis128_aesni_enc_tail)
 	movdqu STATE3, 0x40(STATEP)
 
 	FRAME_END
+	ret
 ENDPROC(crypto_aegis128_aesni_enc_tail)
 
 .macro decrypt_block a s0 s1 s2 s3 s4 i
diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c
index 5de7c0d46edf..acd11b3bf639 100644
--- a/arch/x86/crypto/aegis128-aesni-glue.c
+++ b/arch/x86/crypto/aegis128-aesni-glue.c
@@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128_aesni_alg[] = {
 	}
 };
 
-static const struct x86_cpu_id aesni_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_AES),
-	X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
-
 static int __init crypto_aegis128_aesni_module_init(void)
 {
-	if (!x86_match_cpu(aesni_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_AES) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_aegis128_aesni_alg,
diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S
index 9263c344f2c7..491dd61c845c 100644
--- a/arch/x86/crypto/aegis128l-aesni-asm.S
+++ b/arch/x86/crypto/aegis128l-aesni-asm.S
@@ -66,7 +66,7 @@
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG0, MSG0
 	pxor MSG1, MSG1
 
@@ -645,6 +645,7 @@ ENTRY(crypto_aegis128l_aesni_enc_tail)
 	state_store0
 
 	FRAME_END
+	ret
 ENDPROC(crypto_aegis128l_aesni_enc_tail)
 
 /*
diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c
index 876e4866e633..2071c3d1ae07 100644
--- a/arch/x86/crypto/aegis128l-aesni-glue.c
+++ b/arch/x86/crypto/aegis128l-aesni-glue.c
@@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128l_aesni_alg[] = {
 	}
 };
 
-static const struct x86_cpu_id aesni_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_AES),
-	X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
-
 static int __init crypto_aegis128l_aesni_module_init(void)
 {
-	if (!x86_match_cpu(aesni_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_AES) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_aegis128l_aesni_alg,
diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S
index 1d977d515bf9..8870c7c5d9a4 100644
--- a/arch/x86/crypto/aegis256-aesni-asm.S
+++ b/arch/x86/crypto/aegis256-aesni-asm.S
@@ -59,7 +59,7 @@
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG, MSG
 
 	mov LEN, %r8
@@ -543,6 +543,7 @@ ENTRY(crypto_aegis256_aesni_enc_tail)
 	state_store0
 
 	FRAME_END
+	ret
 ENDPROC(crypto_aegis256_aesni_enc_tail)
 
 /*
diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c
index 2b5dd3af8f4d..b5f2a8fd5a71 100644
--- a/arch/x86/crypto/aegis256-aesni-glue.c
+++ b/arch/x86/crypto/aegis256-aesni-glue.c
@@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis256_aesni_alg[] = {
 	}
 };
 
-static const struct x86_cpu_id aesni_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_AES),
-	X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
-
 static int __init crypto_aegis256_aesni_module_init(void)
 {
-	if (!x86_match_cpu(aesni_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_AES) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_aegis256_aesni_alg,
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index e762ef417562..9bd139569b41 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -258,7 +258,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 .macro GCM_INIT Iv SUBKEY AAD AADLEN
 	mov \AADLEN, %r11
 	mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length
-	xor %r11, %r11
+	xor %r11d, %r11d
 	mov %r11, InLen(%arg2) # ctx_data.in_length = 0
 	mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0
 	mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0
@@ -286,7 +286,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	movdqu HashKey(%arg2), %xmm13
 	add %arg5, InLen(%arg2)
 
-	xor %r11, %r11 # initialise the data pointer offset as zero
+	xor %r11d, %r11d # initialise the data pointer offset as zero
 	PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation
 
 	sub %r11, %arg5		# sub partial block data used
@@ -702,7 +702,7 @@ _no_extra_mask_1_\@:
 
 	# GHASH computation for the last <16 Byte block
 	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
-	xor	%rax,%rax
+	xor	%eax, %eax
 
 	mov	%rax, PBlockLen(%arg2)
 	jmp	_dec_done_\@
@@ -737,7 +737,7 @@ _no_extra_mask_2_\@:
 
 	# GHASH computation for the last <16 Byte block
 	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
-	xor	%rax,%rax
+	xor	%eax, %eax
 
 	mov	%rax, PBlockLen(%arg2)
 	jmp	_encode_done_\@
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index faecb1518bf8..1985ea0b551b 100644
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -463,7 +463,7 @@ _get_AAD_rest_final\@:
 
 _get_AAD_done\@:
 	# initialize the data pointer offset as zero
-	xor     %r11, %r11
+	xor     %r11d, %r11d
 
 	# start AES for num_initial_blocks blocks
 	mov     arg5, %rax                     # rax = *Y0
@@ -1770,7 +1770,7 @@ _get_AAD_rest_final\@:
 
 _get_AAD_done\@:
 	# initialize the data pointer offset as zero
-	xor     %r11, %r11
+	xor     %r11d, %r11d
 
 	# start AES for num_initial_blocks blocks
 	mov     arg5, %rax                     # rax = *Y0
diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S
index 37d422e77931..de182c460f82 100644
--- a/arch/x86/crypto/morus1280-avx2-asm.S
+++ b/arch/x86/crypto/morus1280-avx2-asm.S
@@ -113,7 +113,7 @@ ENDPROC(__morus1280_update_zero)
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	vpxor MSG, MSG, MSG
 
 	mov %rcx, %r8
@@ -453,6 +453,7 @@ ENTRY(crypto_morus1280_avx2_enc_tail)
 	vmovdqu STATE4, (4 * 32)(%rdi)
 
 	FRAME_END
+	ret
 ENDPROC(crypto_morus1280_avx2_enc_tail)
 
 /*
diff --git a/arch/x86/crypto/morus1280-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c
index f111f36d26dc..6634907d6ccd 100644
--- a/arch/x86/crypto/morus1280-avx2-glue.c
+++ b/arch/x86/crypto/morus1280-avx2-glue.c
@@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor,
 
 MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400);
 
-static const struct x86_cpu_id avx2_cpu_id[] = {
-    X86_FEATURE_MATCH(X86_FEATURE_AVX2),
-    {}
-};
-MODULE_DEVICE_TABLE(x86cpu, avx2_cpu_id);
-
 static int __init crypto_morus1280_avx2_module_init(void)
 {
-	if (!x86_match_cpu(avx2_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_morus1280_avx2_algs,
diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S
index 1fe637c7be9d..da5d2905db60 100644
--- a/arch/x86/crypto/morus1280-sse2-asm.S
+++ b/arch/x86/crypto/morus1280-sse2-asm.S
@@ -235,7 +235,7 @@ ENDPROC(__morus1280_update_zero)
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG_LO, MSG_LO
 	pxor MSG_HI, MSG_HI
 
@@ -652,6 +652,7 @@ ENTRY(crypto_morus1280_sse2_enc_tail)
 	movdqu STATE4_HI, (9 * 16)(%rdi)
 
 	FRAME_END
+	ret
 ENDPROC(crypto_morus1280_sse2_enc_tail)
 
 /*
diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c
index 839270aa713c..95cf857d2cbb 100644
--- a/arch/x86/crypto/morus1280-sse2-glue.c
+++ b/arch/x86/crypto/morus1280-sse2-glue.c
@@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor,
 
 MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350);
 
-static const struct x86_cpu_id sse2_cpu_id[] = {
-    X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-    {}
-};
-MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id);
-
 static int __init crypto_morus1280_sse2_module_init(void)
 {
-	if (!x86_match_cpu(sse2_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_morus1280_sse2_algs,
diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S
index 71c72a0a0862..414db480250e 100644
--- a/arch/x86/crypto/morus640-sse2-asm.S
+++ b/arch/x86/crypto/morus640-sse2-asm.S
@@ -113,7 +113,7 @@ ENDPROC(__morus640_update_zero)
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG, MSG
 
 	mov %rcx, %r8
@@ -437,6 +437,7 @@ ENTRY(crypto_morus640_sse2_enc_tail)
 	movdqu STATE4, (4 * 16)(%rdi)
 
 	FRAME_END
+	ret
 ENDPROC(crypto_morus640_sse2_enc_tail)
 
 /*
diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c
index 26b47e2db8d2..615fb7bc9a32 100644
--- a/arch/x86/crypto/morus640-sse2-glue.c
+++ b/arch/x86/crypto/morus640-sse2-glue.c
@@ -37,15 +37,11 @@ asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor,
 
 MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400);
 
-static const struct x86_cpu_id sse2_cpu_id[] = {
-    X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-    {}
-};
-MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id);
-
 static int __init crypto_morus640_sse2_module_init(void)
 {
-	if (!x86_match_cpu(sse2_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_morus640_sse2_algs,
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index 6204bd53528c..613d0bfc3d84 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -96,7 +96,7 @@
 	# cleanup workspace
 	mov	$8, %ecx
 	mov	%rsp, %rdi
-	xor	%rax, %rax
+	xor	%eax, %eax
 	rep stosq
 
 	mov	%rbp, %rsp		# deallocate workspace
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 2582881d19ce..2767c625a52c 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -65,7 +65,7 @@
 # define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
 #else
 # define preempt_stop(clobbers)
-# define resume_kernel		restore_all
+# define resume_kernel		restore_all_kernel
 #endif
 
 .macro TRACE_IRQS_IRET
@@ -77,6 +77,8 @@
 #endif
 .endm
 
+#define PTI_SWITCH_MASK         (1 << PAGE_SHIFT)
+
 /*
  * User gs save/restore
  *
@@ -154,7 +156,52 @@
 
 #endif /* CONFIG_X86_32_LAZY_GS */
 
-.macro SAVE_ALL pt_regs_ax=%eax
+/* Unconditionally switch to user cr3 */
+.macro SWITCH_TO_USER_CR3 scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+	movl	%cr3, \scratch_reg
+	orl	$PTI_SWITCH_MASK, \scratch_reg
+	movl	\scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro BUG_IF_WRONG_CR3 no_user_check=0
+#ifdef CONFIG_DEBUG_ENTRY
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	.if \no_user_check == 0
+	/* coming from usermode? */
+	testl	$SEGMENT_RPL_MASK, PT_CS(%esp)
+	jz	.Lend_\@
+	.endif
+	/* On user-cr3? */
+	movl	%cr3, %eax
+	testl	$PTI_SWITCH_MASK, %eax
+	jnz	.Lend_\@
+	/* From userspace with kernel cr3 - BUG */
+	ud2
+.Lend_\@:
+#endif
+.endm
+
+/*
+ * Switch to kernel cr3 if not already loaded and return current cr3 in
+ * \scratch_reg
+ */
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	movl	%cr3, \scratch_reg
+	/* Test if we are already on kernel CR3 */
+	testl	$PTI_SWITCH_MASK, \scratch_reg
+	jz	.Lend_\@
+	andl	$(~PTI_SWITCH_MASK), \scratch_reg
+	movl	\scratch_reg, %cr3
+	/* Return original CR3 in \scratch_reg */
+	orl	$PTI_SWITCH_MASK, \scratch_reg
+.Lend_\@:
+.endm
+
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
 	cld
 	PUSH_GS
 	pushl	%fs
@@ -173,6 +220,29 @@
 	movl	$(__KERNEL_PERCPU), %edx
 	movl	%edx, %fs
 	SET_KERNEL_GS %edx
+
+	/* Switch to kernel stack if necessary */
+.if \switch_stacks > 0
+	SWITCH_TO_KERNEL_STACK
+.endif
+
+.endm
+
+.macro SAVE_ALL_NMI cr3_reg:req
+	SAVE_ALL
+
+	BUG_IF_WRONG_CR3
+
+	/*
+	 * Now switch the CR3 when PTI is enabled.
+	 *
+	 * We can enter with either user or kernel cr3, the code will
+	 * store the old cr3 in \cr3_reg and switches to the kernel cr3
+	 * if necessary.
+	 */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=\cr3_reg
+
+.Lend_\@:
 .endm
 
 /*
@@ -221,6 +291,349 @@
 	POP_GS_EX
 .endm
 
+.macro RESTORE_ALL_NMI cr3_reg:req pop=0
+	/*
+	 * Now switch the CR3 when PTI is enabled.
+	 *
+	 * We enter with kernel cr3 and switch the cr3 to the value
+	 * stored on \cr3_reg, which is either a user or a kernel cr3.
+	 */
+	ALTERNATIVE "jmp .Lswitched_\@", "", X86_FEATURE_PTI
+
+	testl	$PTI_SWITCH_MASK, \cr3_reg
+	jz	.Lswitched_\@
+
+	/* User cr3 in \cr3_reg - write it to hardware cr3 */
+	movl	\cr3_reg, %cr3
+
+.Lswitched_\@:
+
+	BUG_IF_WRONG_CR3
+
+	RESTORE_REGS pop=\pop
+.endm
+
+.macro CHECK_AND_APPLY_ESPFIX
+#ifdef CONFIG_X86_ESPFIX32
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+
+	ALTERNATIVE	"jmp .Lend_\@", "", X86_BUG_ESPFIX
+
+	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
+	/*
+	 * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+	 * are returning to the kernel.
+	 * See comments in process.c:copy_thread() for details.
+	 */
+	movb	PT_OLDSS(%esp), %ah
+	movb	PT_CS(%esp), %al
+	andl	$(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+	cmpl	$((SEGMENT_LDT << 8) | USER_RPL), %eax
+	jne	.Lend_\@	# returning to user-space with LDT SS
+
+	/*
+	 * Setup and switch to ESPFIX stack
+	 *
+	 * We're returning to userspace with a 16 bit stack. The CPU will not
+	 * restore the high word of ESP for us on executing iret... This is an
+	 * "official" bug of all the x86-compatible CPUs, which we can work
+	 * around to make dosemu and wine happy. We do this by preloading the
+	 * high word of ESP with the high word of the userspace ESP while
+	 * compensating for the offset by changing to the ESPFIX segment with
+	 * a base address that matches for the difference.
+	 */
+	mov	%esp, %edx			/* load kernel esp */
+	mov	PT_OLDESP(%esp), %eax		/* load userspace esp */
+	mov	%dx, %ax			/* eax: new kernel esp */
+	sub	%eax, %edx			/* offset (low word is 0) */
+	shr	$16, %edx
+	mov	%dl, GDT_ESPFIX_SS + 4		/* bits 16..23 */
+	mov	%dh, GDT_ESPFIX_SS + 7		/* bits 24..31 */
+	pushl	$__ESPFIX_SS
+	pushl	%eax				/* new kernel esp */
+	/*
+	 * Disable interrupts, but do not irqtrace this section: we
+	 * will soon execute iret and the tracer was already set to
+	 * the irqstate after the IRET:
+	 */
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	lss	(%esp), %esp			/* switch to espfix segment */
+.Lend_\@:
+#endif /* CONFIG_X86_ESPFIX32 */
+.endm
+
+/*
+ * Called with pt_regs fully populated and kernel segments loaded,
+ * so we can access PER_CPU and use the integer registers.
+ *
+ * We need to be very careful here with the %esp switch, because an NMI
+ * can happen everywhere. If the NMI handler finds itself on the
+ * entry-stack, it will overwrite the task-stack and everything we
+ * copied there. So allocate the stack-frame on the task-stack and
+ * switch to it before we do any copying.
+ */
+
+#define CS_FROM_ENTRY_STACK	(1 << 31)
+#define CS_FROM_USER_CR3	(1 << 30)
+
+.macro SWITCH_TO_KERNEL_STACK
+
+	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+	BUG_IF_WRONG_CR3
+
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+
+	/*
+	 * %eax now contains the entry cr3 and we carry it forward in
+	 * that register for the time this macro runs
+	 */
+
+	/* Are we on the entry stack? Bail out if not! */
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%esp, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
+	jae	.Lend_\@
+
+	/* Load stack pointer into %esi and %edi */
+	movl	%esp, %esi
+	movl	%esi, %edi
+
+	/* Move %edi to the top of the entry stack */
+	andl	$(MASK_entry_stack), %edi
+	addl	$(SIZEOF_entry_stack), %edi
+
+	/* Load top of task-stack into %edi */
+	movl	TSS_entry2task_stack(%edi), %edi
+
+	/*
+	 * Clear unused upper bits of the dword containing the word-sized CS
+	 * slot in pt_regs in case hardware didn't clear it for us.
+	 */
+	andl	$(0x0000ffff), PT_CS(%esp)
+
+	/* Special case - entry from kernel mode via entry stack */
+#ifdef CONFIG_VM86
+	movl	PT_EFLAGS(%esp), %ecx		# mix EFLAGS and CS
+	movb	PT_CS(%esp), %cl
+	andl	$(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %ecx
+#else
+	movl	PT_CS(%esp), %ecx
+	andl	$SEGMENT_RPL_MASK, %ecx
+#endif
+	cmpl	$USER_RPL, %ecx
+	jb	.Lentry_from_kernel_\@
+
+	/* Bytes to copy */
+	movl	$PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+	testl	$X86_EFLAGS_VM, PT_EFLAGS(%esi)
+	jz	.Lcopy_pt_regs_\@
+
+	/*
+	 * Stack-frame contains 4 additional segment registers when
+	 * coming from VM86 mode
+	 */
+	addl	$(4 * 4), %ecx
+
+#endif
+.Lcopy_pt_regs_\@:
+
+	/* Allocate frame on task-stack */
+	subl	%ecx, %edi
+
+	/* Switch to task-stack */
+	movl	%edi, %esp
+
+	/*
+	 * We are now on the task-stack and can safely copy over the
+	 * stack-frame
+	 */
+	shrl	$2, %ecx
+	cld
+	rep movsl
+
+	jmp .Lend_\@
+
+.Lentry_from_kernel_\@:
+
+	/*
+	 * This handles the case when we enter the kernel from
+	 * kernel-mode and %esp points to the entry-stack. When this
+	 * happens we need to switch to the task-stack to run C code,
+	 * but switch back to the entry-stack again when we approach
+	 * iret and return to the interrupted code-path. This usually
+	 * happens when we hit an exception while restoring user-space
+	 * segment registers on the way back to user-space or when the
+	 * sysenter handler runs with eflags.tf set.
+	 *
+	 * When we switch to the task-stack here, we can't trust the
+	 * contents of the entry-stack anymore, as the exception handler
+	 * might be scheduled out or moved to another CPU. Therefore we
+	 * copy the complete entry-stack to the task-stack and set a
+	 * marker in the iret-frame (bit 31 of the CS dword) to detect
+	 * what we've done on the iret path.
+	 *
+	 * On the iret path we copy everything back and switch to the
+	 * entry-stack, so that the interrupted kernel code-path
+	 * continues on the same stack it was interrupted with.
+	 *
+	 * Be aware that an NMI can happen anytime in this code.
+	 *
+	 * %esi: Entry-Stack pointer (same as %esp)
+	 * %edi: Top of the task stack
+	 * %eax: CR3 on kernel entry
+	 */
+
+	/* Calculate number of bytes on the entry stack in %ecx */
+	movl	%esi, %ecx
+
+	/* %ecx to the top of entry-stack */
+	andl	$(MASK_entry_stack), %ecx
+	addl	$(SIZEOF_entry_stack), %ecx
+
+	/* Number of bytes on the entry stack to %ecx */
+	sub	%esi, %ecx
+
+	/* Mark stackframe as coming from entry stack */
+	orl	$CS_FROM_ENTRY_STACK, PT_CS(%esp)
+
+	/*
+	 * Test the cr3 used to enter the kernel and add a marker
+	 * so that we can switch back to it before iret.
+	 */
+	testl	$PTI_SWITCH_MASK, %eax
+	jz	.Lcopy_pt_regs_\@
+	orl	$CS_FROM_USER_CR3, PT_CS(%esp)
+
+	/*
+	 * %esi and %edi are unchanged, %ecx contains the number of
+	 * bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate
+	 * the stack-frame on task-stack and copy everything over
+	 */
+	jmp .Lcopy_pt_regs_\@
+
+.Lend_\@:
+.endm
+
+/*
+ * Switch back from the kernel stack to the entry stack.
+ *
+ * The %esp register must point to pt_regs on the task stack. It will
+ * first calculate the size of the stack-frame to copy, depending on
+ * whether we return to VM86 mode or not. With that it uses 'rep movsl'
+ * to copy the contents of the stack over to the entry stack.
+ *
+ * We must be very careful here, as we can't trust the contents of the
+ * task-stack once we switched to the entry-stack. When an NMI happens
+ * while on the entry-stack, the NMI handler will switch back to the top
+ * of the task stack, overwriting our stack-frame we are about to copy.
+ * Therefore we switch the stack only after everything is copied over.
+ */
+.macro SWITCH_TO_ENTRY_STACK
+
+	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+	/* Bytes to copy */
+	movl	$PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+	testl	$(X86_EFLAGS_VM), PT_EFLAGS(%esp)
+	jz	.Lcopy_pt_regs_\@
+
+	/* Additional 4 registers to copy when returning to VM86 mode */
+	addl    $(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+	/* Initialize source and destination for movsl */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+	subl	%ecx, %edi
+	movl	%esp, %esi
+
+	/* Save future stack pointer in %ebx */
+	movl	%edi, %ebx
+
+	/* Copy over the stack-frame */
+	shrl	$2, %ecx
+	cld
+	rep movsl
+
+	/*
+	 * Switch to entry-stack - needs to happen after everything is
+	 * copied because the NMI handler will overwrite the task-stack
+	 * when on entry-stack
+	 */
+	movl	%ebx, %esp
+
+.Lend_\@:
+.endm
+
+/*
+ * This macro handles the case when we return to kernel-mode on the iret
+ * path and have to switch back to the entry stack and/or user-cr3
+ *
+ * See the comments below the .Lentry_from_kernel_\@ label in the
+ * SWITCH_TO_KERNEL_STACK macro for more details.
+ */
+.macro PARANOID_EXIT_TO_KERNEL_MODE
+
+	/*
+	 * Test if we entered the kernel with the entry-stack. Most
+	 * likely we did not, because this code only runs on the
+	 * return-to-kernel path.
+	 */
+	testl	$CS_FROM_ENTRY_STACK, PT_CS(%esp)
+	jz	.Lend_\@
+
+	/* Unlikely slow-path */
+
+	/* Clear marker from stack-frame */
+	andl	$(~CS_FROM_ENTRY_STACK), PT_CS(%esp)
+
+	/* Copy the remaining task-stack contents to entry-stack */
+	movl	%esp, %esi
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+
+	/* Bytes on the task-stack to ecx */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %ecx
+	subl	%esi, %ecx
+
+	/* Allocate stack-frame on entry-stack */
+	subl	%ecx, %edi
+
+	/*
+	 * Save future stack-pointer, we must not switch until the
+	 * copy is done, otherwise the NMI handler could destroy the
+	 * contents of the task-stack we are about to copy.
+	 */
+	movl	%edi, %ebx
+
+	/* Do the copy */
+	shrl	$2, %ecx
+	cld
+	rep movsl
+
+	/* Safe to switch to entry-stack now */
+	movl	%ebx, %esp
+
+	/*
+	 * We came from entry-stack and need to check if we also need to
+	 * switch back to user cr3.
+	 */
+	testl	$CS_FROM_USER_CR3, PT_CS(%esp)
+	jz	.Lend_\@
+
+	/* Clear marker from stack-frame */
+	andl	$(~CS_FROM_USER_CR3), PT_CS(%esp)
+
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+.Lend_\@:
+.endm
 /*
  * %eax: prev task
  * %edx: next task
@@ -351,9 +764,9 @@ ENTRY(resume_kernel)
 	DISABLE_INTERRUPTS(CLBR_ANY)
 .Lneed_resched:
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
-	jnz	restore_all
+	jnz	restore_all_kernel
 	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
-	jz	restore_all
+	jz	restore_all_kernel
 	call	preempt_schedule_irq
 	jmp	.Lneed_resched
 END(resume_kernel)
@@ -412,7 +825,21 @@ ENTRY(xen_sysenter_target)
  * 0(%ebp) arg6
  */
 ENTRY(entry_SYSENTER_32)
-	movl	TSS_sysenter_sp0(%esp), %esp
+	/*
+	 * On entry-stack with all userspace-regs live - save and
+	 * restore eflags and %eax to use it as scratch-reg for the cr3
+	 * switch.
+	 */
+	pushfl
+	pushl	%eax
+	BUG_IF_WRONG_CR3 no_user_check=1
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+	popl	%eax
+	popfl
+
+	/* Stack empty again, switch to task stack */
+	movl	TSS_entry2task_stack(%esp), %esp
+
 .Lsysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
 	pushl	%ebp			/* pt_regs->sp (stashed in bp) */
@@ -421,7 +848,7 @@ ENTRY(entry_SYSENTER_32)
 	pushl	$__USER_CS		/* pt_regs->cs */
 	pushl	$0			/* pt_regs->ip = 0 (placeholder) */
 	pushl	%eax			/* pt_regs->orig_ax */
-	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
+	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest, stack already switched */
 
 	/*
 	 * SYSENTER doesn't filter flags, so we need to clear NT, AC
@@ -460,25 +887,49 @@ ENTRY(entry_SYSENTER_32)
 
 /* Opportunistic SYSEXIT */
 	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+
+	/*
+	 * Setup entry stack - we keep the pointer in %eax and do the
+	 * switch after almost all user-state is restored.
+	 */
+
+	/* Load entry stack pointer and allocate frame for eflags/eax */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %eax
+	subl	$(2*4), %eax
+
+	/* Copy eflags and eax to entry stack */
+	movl	PT_EFLAGS(%esp), %edi
+	movl	PT_EAX(%esp), %esi
+	movl	%edi, (%eax)
+	movl	%esi, 4(%eax)
+
+	/* Restore user registers and segments */
 	movl	PT_EIP(%esp), %edx	/* pt_regs->ip */
 	movl	PT_OLDESP(%esp), %ecx	/* pt_regs->sp */
 1:	mov	PT_FS(%esp), %fs
 	PTGS_TO_GS
+
 	popl	%ebx			/* pt_regs->bx */
 	addl	$2*4, %esp		/* skip pt_regs->cx and pt_regs->dx */
 	popl	%esi			/* pt_regs->si */
 	popl	%edi			/* pt_regs->di */
 	popl	%ebp			/* pt_regs->bp */
-	popl	%eax			/* pt_regs->ax */
+
+	/* Switch to entry stack */
+	movl	%eax, %esp
+
+	/* Now ready to switch the cr3 */
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
 
 	/*
 	 * Restore all flags except IF. (We restore IF separately because
 	 * STI gives a one-instruction window in which we won't be interrupted,
 	 * whereas POPF does not.)
 	 */
-	addl	$PT_EFLAGS-PT_DS, %esp	/* point esp at pt_regs->flags */
-	btr	$X86_EFLAGS_IF_BIT, (%esp)
+	btrl	$X86_EFLAGS_IF_BIT, (%esp)
+	BUG_IF_WRONG_CR3 no_user_check=1
 	popfl
+	popl	%eax
 
 	/*
 	 * Return back to the vDSO, which will pop ecx and edx.
@@ -532,7 +983,8 @@ ENDPROC(entry_SYSENTER_32)
 ENTRY(entry_INT80_32)
 	ASM_CLAC
 	pushl	%eax			/* pt_regs->orig_ax */
-	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
+
+	SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1	/* save rest */
 
 	/*
 	 * User mode is traced as though IRQs are on, and the interrupt gate
@@ -546,24 +998,17 @@ ENTRY(entry_INT80_32)
 
 restore_all:
 	TRACE_IRQS_IRET
+	SWITCH_TO_ENTRY_STACK
 .Lrestore_all_notrace:
-#ifdef CONFIG_X86_ESPFIX32
-	ALTERNATIVE	"jmp .Lrestore_nocheck", "", X86_BUG_ESPFIX
-
-	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
-	/*
-	 * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
-	 * are returning to the kernel.
-	 * See comments in process.c:copy_thread() for details.
-	 */
-	movb	PT_OLDSS(%esp), %ah
-	movb	PT_CS(%esp), %al
-	andl	$(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
-	cmpl	$((SEGMENT_LDT << 8) | USER_RPL), %eax
-	je .Lldt_ss				# returning to user-space with LDT SS
-#endif
+	CHECK_AND_APPLY_ESPFIX
 .Lrestore_nocheck:
-	RESTORE_REGS 4				# skip orig_eax/error_code
+	/* Switch back to user CR3 */
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+	BUG_IF_WRONG_CR3
+
+	/* Restore user state */
+	RESTORE_REGS pop=4			# skip orig_eax/error_code
 .Lirq_return:
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
@@ -572,46 +1017,33 @@ restore_all:
 	 */
 	INTERRUPT_RETURN
 
+restore_all_kernel:
+	TRACE_IRQS_IRET
+	PARANOID_EXIT_TO_KERNEL_MODE
+	BUG_IF_WRONG_CR3
+	RESTORE_REGS 4
+	jmp	.Lirq_return
+
 .section .fixup, "ax"
 ENTRY(iret_exc	)
 	pushl	$0				# no error code
 	pushl	$do_iret_error
-	jmp	common_exception
-.previous
-	_ASM_EXTABLE(.Lirq_return, iret_exc)
 
-#ifdef CONFIG_X86_ESPFIX32
-.Lldt_ss:
-/*
- * Setup and switch to ESPFIX stack
- *
- * We're returning to userspace with a 16 bit stack. The CPU will not
- * restore the high word of ESP for us on executing iret... This is an
- * "official" bug of all the x86-compatible CPUs, which we can work
- * around to make dosemu and wine happy. We do this by preloading the
- * high word of ESP with the high word of the userspace ESP while
- * compensating for the offset by changing to the ESPFIX segment with
- * a base address that matches for the difference.
- */
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
-	mov	%esp, %edx			/* load kernel esp */
-	mov	PT_OLDESP(%esp), %eax		/* load userspace esp */
-	mov	%dx, %ax			/* eax: new kernel esp */
-	sub	%eax, %edx			/* offset (low word is 0) */
-	shr	$16, %edx
-	mov	%dl, GDT_ESPFIX_SS + 4		/* bits 16..23 */
-	mov	%dh, GDT_ESPFIX_SS + 7		/* bits 24..31 */
-	pushl	$__ESPFIX_SS
-	pushl	%eax				/* new kernel esp */
+#ifdef CONFIG_DEBUG_ENTRY
 	/*
-	 * Disable interrupts, but do not irqtrace this section: we
-	 * will soon execute iret and the tracer was already set to
-	 * the irqstate after the IRET:
+	 * The stack-frame here is the one that iret faulted on, so its a
+	 * return-to-user frame. We are on kernel-cr3 because we come here from
+	 * the fixup code. This confuses the CR3 checker, so switch to user-cr3
+	 * as the checker expects it.
 	 */
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	lss	(%esp), %esp			/* switch to espfix segment */
-	jmp	.Lrestore_nocheck
+	pushl	%eax
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+	popl	%eax
 #endif
+
+	jmp	common_exception
+.previous
+	_ASM_EXTABLE(.Lirq_return, iret_exc)
 ENDPROC(entry_INT80_32)
 
 .macro FIXUP_ESPFIX_STACK
@@ -671,7 +1103,8 @@ END(irq_entries_start)
 common_interrupt:
 	ASM_CLAC
 	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
-	SAVE_ALL
+
+	SAVE_ALL switch_stacks=1
 	ENCODE_FRAME_POINTER
 	TRACE_IRQS_OFF
 	movl	%esp, %eax
@@ -679,16 +1112,16 @@ common_interrupt:
 	jmp	ret_from_intr
 ENDPROC(common_interrupt)
 
-#define BUILD_INTERRUPT3(name, nr, fn)	\
-ENTRY(name)				\
-	ASM_CLAC;			\
-	pushl	$~(nr);			\
-	SAVE_ALL;			\
-	ENCODE_FRAME_POINTER;		\
-	TRACE_IRQS_OFF			\
-	movl	%esp, %eax;		\
-	call	fn;			\
-	jmp	ret_from_intr;		\
+#define BUILD_INTERRUPT3(name, nr, fn)			\
+ENTRY(name)						\
+	ASM_CLAC;					\
+	pushl	$~(nr);					\
+	SAVE_ALL switch_stacks=1;			\
+	ENCODE_FRAME_POINTER;				\
+	TRACE_IRQS_OFF					\
+	movl	%esp, %eax;				\
+	call	fn;					\
+	jmp	ret_from_intr;				\
 ENDPROC(name)
 
 #define BUILD_INTERRUPT(name, nr)		\
@@ -920,16 +1353,20 @@ common_exception:
 	pushl	%es
 	pushl	%ds
 	pushl	%eax
+	movl	$(__USER_DS), %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	$(__KERNEL_PERCPU), %eax
+	movl	%eax, %fs
 	pushl	%ebp
 	pushl	%edi
 	pushl	%esi
 	pushl	%edx
 	pushl	%ecx
 	pushl	%ebx
+	SWITCH_TO_KERNEL_STACK
 	ENCODE_FRAME_POINTER
 	cld
-	movl	$(__KERNEL_PERCPU), %ecx
-	movl	%ecx, %fs
 	UNWIND_ESPFIX_STACK
 	GS_TO_REG %ecx
 	movl	PT_GS(%esp), %edi		# get the function address
@@ -937,9 +1374,6 @@ common_exception:
 	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
 	REG_TO_PTGS %ecx
 	SET_KERNEL_GS %ecx
-	movl	$(__USER_DS), %ecx
-	movl	%ecx, %ds
-	movl	%ecx, %es
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
 	CALL_NOSPEC %edi
@@ -948,40 +1382,12 @@ END(common_exception)
 
 ENTRY(debug)
 	/*
-	 * #DB can happen at the first instruction of
-	 * entry_SYSENTER_32 or in Xen's SYSENTER prologue.  If this
-	 * happens, then we will be running on a very small stack.  We
-	 * need to detect this condition and switch to the thread
-	 * stack before calling any C code at all.
-	 *
-	 * If you edit this code, keep in mind that NMIs can happen in here.
+	 * Entry from sysenter is now handled in common_exception
 	 */
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
-	SAVE_ALL
-	ENCODE_FRAME_POINTER
-	xorl	%edx, %edx			# error code 0
-	movl	%esp, %eax			# pt_regs pointer
-
-	/* Are we currently on the SYSENTER stack? */
-	movl	PER_CPU_VAR(cpu_entry_area), %ecx
-	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
-	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
-	cmpl	$SIZEOF_entry_stack, %ecx
-	jb	.Ldebug_from_sysenter_stack
-
-	TRACE_IRQS_OFF
-	call	do_debug
-	jmp	ret_from_exception
-
-.Ldebug_from_sysenter_stack:
-	/* We're on the SYSENTER stack.  Switch off. */
-	movl	%esp, %ebx
-	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
-	TRACE_IRQS_OFF
-	call	do_debug
-	movl	%ebx, %esp
-	jmp	ret_from_exception
+	pushl	$do_debug
+	jmp	common_exception
 END(debug)
 
 /*
@@ -993,6 +1399,7 @@ END(debug)
  */
 ENTRY(nmi)
 	ASM_CLAC
+
 #ifdef CONFIG_X86_ESPFIX32
 	pushl	%eax
 	movl	%ss, %eax
@@ -1002,7 +1409,7 @@ ENTRY(nmi)
 #endif
 
 	pushl	%eax				# pt_regs->orig_ax
-	SAVE_ALL
+	SAVE_ALL_NMI cr3_reg=%edi
 	ENCODE_FRAME_POINTER
 	xorl	%edx, %edx			# zero error code
 	movl	%esp, %eax			# pt_regs pointer
@@ -1016,7 +1423,7 @@ ENTRY(nmi)
 
 	/* Not on SYSENTER stack. */
 	call	do_nmi
-	jmp	.Lrestore_all_notrace
+	jmp	.Lnmi_return
 
 .Lnmi_from_sysenter_stack:
 	/*
@@ -1027,7 +1434,11 @@ ENTRY(nmi)
 	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
 	call	do_nmi
 	movl	%ebx, %esp
-	jmp	.Lrestore_all_notrace
+
+.Lnmi_return:
+	CHECK_AND_APPLY_ESPFIX
+	RESTORE_ALL_NMI cr3_reg=%edi pop=4
+	jmp	.Lirq_return
 
 #ifdef CONFIG_X86_ESPFIX32
 .Lnmi_espfix_stack:
@@ -1042,12 +1453,12 @@ ENTRY(nmi)
 	pushl	16(%esp)
 	.endr
 	pushl	%eax
-	SAVE_ALL
+	SAVE_ALL_NMI cr3_reg=%edi
 	ENCODE_FRAME_POINTER
 	FIXUP_ESPFIX_STACK			# %eax == %esp
 	xorl	%edx, %edx			# zero error code
 	call	do_nmi
-	RESTORE_REGS
+	RESTORE_ALL_NMI cr3_reg=%edi
 	lss	12+4(%esp), %esp		# back to espfix stack
 	jmp	.Lirq_return
 #endif
@@ -1056,7 +1467,8 @@ END(nmi)
 ENTRY(int3)
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
-	SAVE_ALL
+
+	SAVE_ALL switch_stacks=1
 	ENCODE_FRAME_POINTER
 	TRACE_IRQS_OFF
 	xorl	%edx, %edx			# zero error code
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 73a522d53b53..957dfb693ecc 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -92,7 +92,7 @@ END(native_usergs_sysret64)
 .endm
 
 .macro TRACE_IRQS_IRETQ_DEBUG
-	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
+	btl	$9, EFLAGS(%rsp)		/* interrupts off? */
 	jnc	1f
 	TRACE_IRQS_ON_DEBUG
 1:
@@ -408,6 +408,7 @@ ENTRY(ret_from_fork)
 
 1:
 	/* kernel thread */
+	UNWIND_HINT_EMPTY
 	movq	%r12, %rdi
 	CALL_NOSPEC %rbx
 	/*
@@ -701,7 +702,7 @@ retint_kernel:
 #ifdef CONFIG_PREEMPT
 	/* Interrupts are off */
 	/* Check if we need preemption */
-	bt	$9, EFLAGS(%rsp)		/* were interrupts off? */
+	btl	$9, EFLAGS(%rsp)		/* were interrupts off? */
 	jnc	1f
 0:	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	1f
@@ -981,7 +982,7 @@ ENTRY(\sym)
 
 	call	\do_sym
 
-	jmp	error_exit			/* %ebx: no swapgs flag */
+	jmp	error_exit
 	.endif
 END(\sym)
 .endm
@@ -1222,7 +1223,6 @@ END(paranoid_exit)
 
 /*
  * Save all registers in pt_regs, and switch GS if needed.
- * Return: EBX=0: came from user mode; EBX=1: otherwise
  */
 ENTRY(error_entry)
 	UNWIND_HINT_FUNC
@@ -1269,7 +1269,6 @@ ENTRY(error_entry)
 	 * for these here too.
 	 */
 .Lerror_kernelspace:
-	incl	%ebx
 	leaq	native_irq_return_iret(%rip), %rcx
 	cmpq	%rcx, RIP+8(%rsp)
 	je	.Lerror_bad_iret
@@ -1303,28 +1302,20 @@ ENTRY(error_entry)
 
 	/*
 	 * Pretend that the exception came from user mode: set up pt_regs
-	 * as if we faulted immediately after IRET and clear EBX so that
-	 * error_exit knows that we will be returning to user mode.
+	 * as if we faulted immediately after IRET.
 	 */
 	mov	%rsp, %rdi
 	call	fixup_bad_iret
 	mov	%rax, %rsp
-	decl	%ebx
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 END(error_entry)
 
-
-/*
- * On entry, EBX is a "return to kernel mode" flag:
- *   1: already in kernel mode, don't need SWAPGS
- *   0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
- */
 ENTRY(error_exit)
 	UNWIND_HINT_REGS
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
-	testl	%ebx, %ebx
-	jnz	retint_kernel
+	testb	$3, CS(%rsp)
+	jz	retint_kernel
 	jmp	retint_user
 END(error_exit)
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 9de7f1e1dede..7d0df78db727 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -84,13 +84,13 @@ ENTRY(entry_SYSENTER_compat)
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	pushq   %r8			/* pt_regs->r8 */
+	pushq   $0			/* pt_regs->r8  = 0 */
 	xorl	%r8d, %r8d		/* nospec   r8 */
-	pushq   %r9			/* pt_regs->r9 */
+	pushq   $0			/* pt_regs->r9  = 0 */
 	xorl	%r9d, %r9d		/* nospec   r9 */
-	pushq   %r10			/* pt_regs->r10 */
+	pushq   $0			/* pt_regs->r10 = 0 */
 	xorl	%r10d, %r10d		/* nospec   r10 */
-	pushq   %r11			/* pt_regs->r11 */
+	pushq   $0			/* pt_regs->r11 = 0 */
 	xorl	%r11d, %r11d		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	xorl	%ebx, %ebx		/* nospec   rbx */
@@ -374,13 +374,13 @@ ENTRY(entry_INT80_compat)
 	pushq	%rcx			/* pt_regs->cx */
 	xorl	%ecx, %ecx		/* nospec   cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	pushq   $0			/* pt_regs->r8  = 0 */
+	pushq   %r8			/* pt_regs->r8 */
 	xorl	%r8d, %r8d		/* nospec   r8 */
-	pushq   $0			/* pt_regs->r9  = 0 */
+	pushq   %r9			/* pt_regs->r9 */
 	xorl	%r9d, %r9d		/* nospec   r9 */
-	pushq   $0			/* pt_regs->r10 = 0 */
+	pushq   %r10			/* pt_regs->r10*/
 	xorl	%r10d, %r10d		/* nospec   r10 */
-	pushq   $0			/* pt_regs->r11 = 0 */
+	pushq   %r11			/* pt_regs->r11 */
 	xorl	%r11d, %r11d		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	xorl	%ebx, %ebx		/* nospec   rbx */
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 261802b1cc50..9f695f517747 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -46,10 +46,8 @@ targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
 
 CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
-			-Wl,--no-undefined \
-			-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
-			$(DISABLE_LTO)
+VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
+			-z max-page-size=4096 -z common-page-size=4096
 
 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
@@ -58,9 +56,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(src
 hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@
-define cmd_vdso2c
-	$(obj)/vdso2c $< $(<:%.dbg=%) $@
-endef
+      cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@
 
 $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 	$(call if_changed,vdso2c)
@@ -95,10 +91,8 @@ CFLAGS_REMOVE_vvar.o = -pg
 #
 
 CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
-			   -Wl,-soname=linux-vdso.so.1 \
-			   -Wl,-z,max-page-size=4096 \
-			   -Wl,-z,common-page-size=4096
+VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \
+			   -z max-page-size=4096 -z common-page-size=4096
 
 # x32-rebranded versions
 vobjx32s-y := $(vobjs-y:.o=-x32.o)
@@ -123,7 +117,7 @@ $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
 	$(call if_changed,vdso)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
+VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
 
 targets += vdso32/vdso32.lds
 targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
@@ -157,13 +151,13 @@ $(obj)/vdso32.so.dbg: FORCE \
 # The DSO images are built using a special linker script.
 #
 quiet_cmd_vdso = VDSO    $@
-      cmd_vdso = $(CC) -nostdlib -o $@ \
+      cmd_vdso = $(LD) -nostdlib -o $@ \
 		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
+		       -T $(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \
-	$(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS)
+VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \
+	$(call ld-option, --build-id) -Bsymbolic
 GCOV_PROFILE := n
 
 #
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 4b98101209a1..d50bb4dc0650 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 {
 	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
 	struct perf_event *event = pcpu->event;
-	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event *hwc;
 	struct perf_sample_data data;
 	struct perf_raw_record raw;
 	struct pt_regs regs;
@@ -602,6 +602,10 @@ fail:
 		return 0;
 	}
 
+	if (WARN_ON_ONCE(!event))
+		goto fail;
+
+	hwc = &event->hw;
 	msr = hwc->config_base;
 	buf = ibs_data.regs;
 	rdmsrl(msr, *buf);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 707b2a96e516..035c37481f57 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2041,15 +2041,15 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
-
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
@@ -2068,17 +2068,19 @@ static void intel_pmu_read_event(struct perf_event *event)
 		x86_perf_event_update(event);
 }
 
-static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
-	u64 ctrl_val, bits, mask;
+	u64 ctrl_val, mask, bits = 0;
 
 	/*
-	 * Enable IRQ generation (0x8),
+	 * Enable IRQ generation (0x8), if not PEBS,
 	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
 	 * if requested:
 	 */
-	bits = 0x8ULL;
+	if (!event->attr.precise_ip)
+		bits |= 0x8;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
 		bits |= 0x2;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
@@ -2120,14 +2122,14 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	if (unlikely(event_is_checkpointed(event)))
 		cpuc->intel_cp_status |= (1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_enable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_enable_fixed(hwc);
+		intel_pmu_enable_fixed(event);
 		return;
 	}
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_enable(event);
-
 	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
@@ -2280,7 +2282,10 @@ again:
 	 * counters from the GLOBAL_STATUS mask and we always process PEBS
 	 * events via drain_pebs().
 	 */
-	status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		status &= ~cpuc->pebs_enabled;
+	else
+		status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
@@ -2997,6 +3002,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
+
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY;
 	}
 
 	if (needs_branch_stack(event)) {
@@ -4069,7 +4077,6 @@ __init int intel_pmu_init(void)
 		intel_pmu_lbr_init_skl();
 
 		x86_pmu.event_constraints = intel_slm_event_constraints;
-		x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_glm_extra_regs;
 		/*
 		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
@@ -4079,6 +4086,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.lbr_pt_coexist = true;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.get_event_constraints = glp_get_event_constraints;
 		x86_pmu.cpu_events = glm_events_attrs;
 		/* Goldmont Plus has 4-wide pipeline */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8a10a045b57b..b7b01d762d32 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -408,9 +408,11 @@ static int alloc_bts_buffer(int cpu)
 	ds->bts_buffer_base = (unsigned long) cea;
 	ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
 	ds->bts_index = ds->bts_buffer_base;
-	max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
-	ds->bts_absolute_maximum = ds->bts_buffer_base + max;
-	ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
+	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+	ds->bts_absolute_maximum = ds->bts_buffer_base +
+					max * BTS_RECORD_SIZE;
+	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+					(max / 16) * BTS_RECORD_SIZE;
 	return 0;
 }
 
@@ -711,12 +713,6 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_glp_pebs_event_constraints[] = {
-	/* Allow all events as PEBS with no flags */
-	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
-	EVENT_CONSTRAINT_END
-};
-
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
@@ -869,6 +865,13 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 		}
 	}
 
+	/*
+	 * Extended PEBS support
+	 * Makes the PEBS code search the normal constraints.
+	 */
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		return NULL;
+
 	return &emptyconstraint;
 }
 
@@ -894,10 +897,16 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
 	u64 threshold;
+	int reserved;
+
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
+	else
+		reserved = x86_pmu.max_pebs_events;
 
 	if (cpuc->n_pebs == cpuc->n_large_pebs) {
 		threshold = ds->pebs_absolute_maximum -
-			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+			reserved * x86_pmu.pebs_record_size;
 	} else {
 		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
 	}
@@ -961,7 +970,11 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
 	 */
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		ds->pebs_event_reset[hwc->idx] =
+		unsigned int idx = hwc->idx;
+
+		if (idx >= INTEL_PMC_IDX_FIXED)
+			idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+		ds->pebs_event_reset[idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
 	} else {
 		ds->pebs_event_reset[hwc->idx] = 0;
@@ -1184,16 +1197,20 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	}
 
 	/*
+	 * We must however always use iregs for the unwinder to stay sane; the
+	 * record BP,SP,IP can point into thin air when the record is from a
+	 * previous PMI context or an (I)RET happend between the record and
+	 * PMI.
+	 */
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		data->callchain = perf_callchain(event, iregs);
+
+	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
 	 * contain a full regs set, specifically it seems to lack segment
 	 * descriptors, which get used by things like user_mode().
 	 *
 	 * In the simple case fix up only the IP for PERF_SAMPLE_IP.
-	 *
-	 * We must however always use BP,SP from iregs for the unwinder to stay
-	 * sane; the record BP,SP can point into thin air when the record is
-	 * from a previous PMI context or an (I)RET happend between the record
-	 * and PMI.
 	 */
 	*regs = *iregs;
 
@@ -1212,15 +1229,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		regs->si = pebs->si;
 		regs->di = pebs->di;
 
-		/*
-		 * Per the above; only set BP,SP if we don't need callchains.
-		 *
-		 * XXX: does this make sense?
-		 */
-		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
-			regs->bp = pebs->bp;
-			regs->sp = pebs->sp;
-		}
+		regs->bp = pebs->bp;
+		regs->sp = pebs->sp;
 
 #ifndef CONFIG_X86_32
 		regs->r8 = pebs->r8;
@@ -1482,9 +1492,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event;
 	void *base, *at, *top;
-	short counts[MAX_PEBS_EVENTS] = {};
-	short error[MAX_PEBS_EVENTS] = {};
-	int bit, i;
+	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	int bit, i, size;
+	u64 mask;
 
 	if (!x86_pmu.pebs_active)
 		return;
@@ -1494,6 +1505,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
+	mask = (1ULL << x86_pmu.max_pebs_events) - 1;
+	size = x86_pmu.max_pebs_events;
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
+		mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
+		size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+	}
+
 	if (unlikely(base >= top)) {
 		/*
 		 * The drain_pebs() could be called twice in a short period
@@ -1503,7 +1521,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		 * update the event->count for this case.
 		 */
 		for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
-				 x86_pmu.max_pebs_events) {
+				 size) {
 			event = cpuc->events[bit];
 			if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
 				intel_pmu_save_and_restart_reload(event, 0);
@@ -1516,12 +1534,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		u64 pebs_status;
 
 		pebs_status = p->status & cpuc->pebs_enabled;
-		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+		pebs_status &= mask;
 
 		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
 			for_each_set_bit(bit, (unsigned long *)&pebs_status,
-					 x86_pmu.max_pebs_events)
+					 size)
 				counts[bit]++;
 
 			continue;
@@ -1569,7 +1587,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		counts[bit]++;
 	}
 
-	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+	for (bit = 0; bit < size; bit++) {
 		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index cf372b90557e..f3e006bed9a7 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -216,6 +216,8 @@ static void intel_pmu_lbr_reset_64(void)
 
 void intel_pmu_lbr_reset(void)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
 	if (!x86_pmu.lbr_nr)
 		return;
 
@@ -223,6 +225,9 @@ void intel_pmu_lbr_reset(void)
 		intel_pmu_lbr_reset_32();
 	else
 		intel_pmu_lbr_reset_64();
+
+	cpuc->last_task_ctx = NULL;
+	cpuc->last_log_id = 0;
 }
 
 /*
@@ -334,6 +339,7 @@ static inline u64 rdlbr_to(unsigned int idx)
 
 static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 	unsigned lbr_idx, mask;
 	u64 tos;
@@ -344,9 +350,21 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		return;
 	}
 
-	mask = x86_pmu.lbr_nr - 1;
 	tos = task_ctx->tos;
-	for (i = 0; i < tos; i++) {
+	/*
+	 * Does not restore the LBR registers, if
+	 * - No one else touched them, and
+	 * - Did not enter C6
+	 */
+	if ((task_ctx == cpuc->last_task_ctx) &&
+	    (task_ctx->log_id == cpuc->last_log_id) &&
+	    rdlbr_from(tos)) {
+		task_ctx->lbr_stack_state = LBR_NONE;
+		return;
+	}
+
+	mask = x86_pmu.lbr_nr - 1;
+	for (i = 0; i < task_ctx->valid_lbrs; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
 		wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
@@ -354,14 +372,24 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+
+	for (; i < x86_pmu.lbr_nr; i++) {
+		lbr_idx = (tos - i) & mask;
+		wrlbr_from(lbr_idx, 0);
+		wrlbr_to(lbr_idx, 0);
+		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0);
+	}
+
 	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
 
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned lbr_idx, mask;
-	u64 tos;
+	u64 tos, from;
 	int i;
 
 	if (task_ctx->lbr_callstack_users == 0) {
@@ -371,15 +399,22 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 	mask = x86_pmu.lbr_nr - 1;
 	tos = intel_pmu_lbr_tos();
-	for (i = 0; i < tos; i++) {
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		lbr_idx = (tos - i) & mask;
-		task_ctx->lbr_from[i] = rdlbr_from(lbr_idx);
+		from = rdlbr_from(lbr_idx);
+		if (!from)
+			break;
+		task_ctx->lbr_from[i] = from;
 		task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->valid_lbrs = i;
 	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
+
+	cpuc->last_task_ctx = task_ctx;
+	cpuc->last_log_id = ++task_ctx->log_id;
 }
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
@@ -531,7 +566,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
  */
 static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
-	bool need_info = false;
+	bool need_info = false, call_stack = false;
 	unsigned long mask = x86_pmu.lbr_nr - 1;
 	int lbr_format = x86_pmu.intel_cap.lbr_format;
 	u64 tos = intel_pmu_lbr_tos();
@@ -542,7 +577,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	if (cpuc->lbr_sel) {
 		need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
 		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
-			num = tos;
+			call_stack = true;
 	}
 
 	for (i = 0; i < num; i++) {
@@ -555,6 +590,13 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		from = rdlbr_from(lbr_idx);
 		to   = rdlbr_to(lbr_idx);
 
+		/*
+		 * Read LBR call stack entries
+		 * until invalid entry (0s) is detected.
+		 */
+		if (call_stack && !from)
+			break;
+
 		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
 
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index c9e1e0bef3c3..e17ab885b1e9 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -28,7 +28,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	3
+#define UNCORE_EXTRA_PCI_DEV_MAX	4
 
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 87dc0263a2e1..51d7c117e3c7 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	BDX_PCI_QPI_PORT2_FILTER,
 	HSWEP_PCI_PCU_3,
 };
 
@@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
 	},
 	{ /* QPI Port 0 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
 	},
 	{ /* QPI Port 1 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
 	{ /* QPI Port 2 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   BDX_PCI_QPI_PORT2_FILTER),
 	},
 	{ /* PCU.3 (for Capability registers) */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 9f3711470ec1..156286335351 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -163,6 +163,7 @@ struct intel_excl_cntrs {
 	unsigned	core_id;	/* per-core: core id */
 };
 
+struct x86_perf_task_context;
 #define MAX_LBR_ENTRIES		32
 
 enum {
@@ -214,6 +215,8 @@ struct cpu_hw_events {
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
 	u64				br_sel;
+	struct x86_perf_task_context	*last_task_ctx;
+	int				last_log_id;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -648,8 +651,10 @@ struct x86_perf_task_context {
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
 	int tos;
+	int valid_lbrs;
 	int lbr_callstack_users;
 	int lbr_stack_state;
+	int log_id;
 };
 
 #define x86_add_quirk(func_)						\
@@ -668,6 +673,7 @@ do {									\
 #define PMU_FL_HAS_RSP_1	0x2 /* has 2 equivalent offcore_rsp regs   */
 #define PMU_FL_EXCL_CNTRS	0x4 /* has exclusive counter requirements  */
 #define PMU_FL_EXCL_ENABLED	0x8 /* exclusive counter active */
+#define PMU_FL_PEBS_ALL		0x10 /* all events are valid PEBS events */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index f68855499391..5b0f613428c2 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -31,6 +31,8 @@
 #include <asm/mshyperv.h>
 #include <asm/apic.h>
 
+#include <asm/trace/hyperv.h>
+
 static struct apic orig_apic;
 
 static u64 hv_apic_icr_read(void)
@@ -99,6 +101,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 	int nr_bank = 0;
 	int ret = 1;
 
+	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+		return false;
+
 	local_irq_save(flags);
 	arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
 
@@ -114,6 +119,8 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 		ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
 		nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
 	}
+	if (nr_bank < 0)
+		goto ipi_mask_ex_done;
 	if (!nr_bank)
 		ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
 
@@ -128,10 +135,10 @@ ipi_mask_ex_done:
 static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 {
 	int cur_cpu, vcpu;
-	struct ipi_arg_non_ex **arg;
-	struct ipi_arg_non_ex *ipi_arg;
+	struct ipi_arg_non_ex ipi_arg;
 	int ret = 1;
-	unsigned long flags;
+
+	trace_hyperv_send_ipi_mask(mask, vector);
 
 	if (cpumask_empty(mask))
 		return true;
@@ -142,37 +149,43 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
 		return false;
 
-	if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-		return __send_ipi_mask_ex(mask, vector);
-
-	local_irq_save(flags);
-	arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
-
-	ipi_arg = *arg;
-	if (unlikely(!ipi_arg))
-		goto ipi_mask_done;
-
-	ipi_arg->vector = vector;
-	ipi_arg->reserved = 0;
-	ipi_arg->cpu_mask = 0;
+	/*
+	 * From the supplied CPU set we need to figure out if we can get away
+	 * with cheaper HVCALL_SEND_IPI hypercall. This is possible when the
+	 * highest VP number in the set is < 64. As VP numbers are usually in
+	 * ascending order and match Linux CPU ids, here is an optimization:
+	 * we check the VP number for the highest bit in the supplied set first
+	 * so we can quickly find out if using HVCALL_SEND_IPI_EX hypercall is
+	 * a must. We will also check all VP numbers when walking the supplied
+	 * CPU set to remain correct in all cases.
+	 */
+	if (hv_cpu_number_to_vp_number(cpumask_last(mask)) >= 64)
+		goto do_ex_hypercall;
+
+	ipi_arg.vector = vector;
+	ipi_arg.cpu_mask = 0;
 
 	for_each_cpu(cur_cpu, mask) {
 		vcpu = hv_cpu_number_to_vp_number(cur_cpu);
+		if (vcpu == VP_INVAL)
+			return false;
+
 		/*
 		 * This particular version of the IPI hypercall can
 		 * only target upto 64 CPUs.
 		 */
 		if (vcpu >= 64)
-			goto ipi_mask_done;
+			goto do_ex_hypercall;
 
-		__set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask);
+		__set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask);
 	}
 
-	ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL);
-
-ipi_mask_done:
-	local_irq_restore(flags);
+	ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector,
+				     ipi_arg.cpu_mask);
 	return ((ret == 0) ? true : false);
+
+do_ex_hypercall:
+	return __send_ipi_mask_ex(mask, vector);
 }
 
 static bool __send_ipi_one(int cpu, int vector)
@@ -228,10 +241,7 @@ static void hv_send_ipi_self(int vector)
 void __init hv_apic_init(void)
 {
 	if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) {
-		if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-			pr_info("Hyper-V: Using ext hypercalls for IPI\n");
-		else
-			pr_info("Hyper-V: Using IPI hypercalls\n");
+		pr_info("Hyper-V: Using IPI hypercalls\n");
 		/*
 		 * Set the IPI entry points.
 		 */
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 4c431e1c1eff..1ff420217298 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -265,7 +265,7 @@ void __init hyperv_init(void)
 {
 	u64 guest_id, required_msrs;
 	union hv_x64_msr_hypercall_contents hypercall_msr;
-	int cpuhp;
+	int cpuhp, i;
 
 	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
 		return;
@@ -293,6 +293,9 @@ void __init hyperv_init(void)
 	if (!hv_vp_index)
 		return;
 
+	for (i = 0; i < num_possible_cpus(); i++)
+		hv_vp_index[i] = VP_INVAL;
+
 	hv_vp_assist_page = kcalloc(num_possible_cpus(),
 				    sizeof(*hv_vp_assist_page), GFP_KERNEL);
 	if (!hv_vp_assist_page) {
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index de27615c51ea..1147e1fed7ff 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -16,6 +16,8 @@
 /* Each gva in gva_list encodes up to 4096 pages to flush */
 #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
 
+static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+				      const struct flush_tlb_info *info);
 
 /*
  * Fills in gva_list starting from offset. Returns the number of items added.
@@ -93,10 +95,29 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	if (cpumask_equal(cpus, cpu_present_mask)) {
 		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
 	} else {
+		/*
+		 * From the supplied CPU set we need to figure out if we can get
+		 * away with cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}
+		 * hypercalls. This is possible when the highest VP number in
+		 * the set is < 64. As VP numbers are usually in ascending order
+		 * and match Linux CPU ids, here is an optimization: we check
+		 * the VP number for the highest bit in the supplied set first
+		 * so we can quickly find out if using *_EX hypercalls is a
+		 * must. We will also check all VP numbers when walking the
+		 * supplied CPU set to remain correct in all cases.
+		 */
+		if (hv_cpu_number_to_vp_number(cpumask_last(cpus)) >= 64)
+			goto do_ex_hypercall;
+
 		for_each_cpu(cpu, cpus) {
 			vcpu = hv_cpu_number_to_vp_number(cpu);
-			if (vcpu >= 64)
+			if (vcpu == VP_INVAL) {
+				local_irq_restore(flags);
 				goto do_native;
+			}
+
+			if (vcpu >= 64)
+				goto do_ex_hypercall;
 
 			__set_bit(vcpu, (unsigned long *)
 				  &flush->processor_mask);
@@ -123,7 +144,12 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 		status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST,
 					     gva_n, 0, flush, NULL);
 	}
+	goto check_status;
+
+do_ex_hypercall:
+	status = hyperv_flush_tlb_others_ex(cpus, info);
 
+check_status:
 	local_irq_restore(flags);
 
 	if (!(status & HV_HYPERCALL_RESULT_MASK))
@@ -132,35 +158,22 @@ do_native:
 	native_flush_tlb_others(cpus, info);
 }
 
-static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
-				       const struct flush_tlb_info *info)
+static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+				      const struct flush_tlb_info *info)
 {
 	int nr_bank = 0, max_gvas, gva_n;
 	struct hv_tlb_flush_ex **flush_pcpu;
 	struct hv_tlb_flush_ex *flush;
-	u64 status = U64_MAX;
-	unsigned long flags;
+	u64 status;
 
-	trace_hyperv_mmu_flush_tlb_others(cpus, info);
-
-	if (!hv_hypercall_pg)
-		goto do_native;
-
-	if (cpumask_empty(cpus))
-		return;
-
-	local_irq_save(flags);
+	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+		return U64_MAX;
 
 	flush_pcpu = (struct hv_tlb_flush_ex **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
 
 	flush = *flush_pcpu;
 
-	if (unlikely(!flush)) {
-		local_irq_restore(flags);
-		goto do_native;
-	}
-
 	if (info->mm) {
 		/*
 		 * AddressSpace argument must match the CR3 with PCID bits
@@ -176,15 +189,10 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 
 	flush->hv_vp_set.valid_bank_mask = 0;
 
-	if (!cpumask_equal(cpus, cpu_present_mask)) {
-		flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
-		nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
-	}
-
-	if (!nr_bank) {
-		flush->hv_vp_set.format = HV_GENERIC_SET_ALL;
-		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
-	}
+	flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+	nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
+	if (nr_bank < 0)
+		return U64_MAX;
 
 	/*
 	 * We can flush not more than max_gvas with one hypercall. Flush the
@@ -213,12 +221,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 			gva_n, nr_bank, flush, NULL);
 	}
 
-	local_irq_restore(flags);
-
-	if (!(status & HV_HYPERCALL_RESULT_MASK))
-		return;
-do_native:
-	native_flush_tlb_others(cpus, info);
+	return status;
 }
 
 void hyperv_setup_mmu_ops(void)
@@ -226,11 +229,6 @@ void hyperv_setup_mmu_ops(void)
 	if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
 		return;
 
-	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) {
-		pr_info("Using hypercall for remote TLB flush\n");
-		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
-	} else {
-		pr_info("Using ext hypercall for remote TLB flush\n");
-		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex;
-	}
+	pr_info("Using hypercall for remote TLB flush\n");
+	pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
 }
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 74a9e06b6cfd..130e81e10fc7 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -10,6 +10,7 @@
 #include <asm/fixmap.h>
 #include <asm/mpspec.h>
 #include <asm/msr.h>
+#include <asm/hardirq.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
 
@@ -502,12 +503,19 @@ extern int default_check_phys_apicid_present(int phys_apicid);
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
+#ifdef CONFIG_SMP
+bool apic_id_is_primary_thread(unsigned int id);
+#else
+static inline bool apic_id_is_primary_thread(unsigned int id) { return false; }
+#endif
+
 extern void irq_enter(void);
 extern void irq_exit(void);
 
 static inline void entering_irq(void)
 {
 	irq_enter();
+	kvm_set_cpu_l1tf_flush_l1d();
 }
 
 static inline void entering_ack_irq(void)
@@ -520,6 +528,7 @@ static inline void ipi_entering_ack_irq(void)
 {
 	irq_enter();
 	ack_APIC_irq();
+	kvm_set_cpu_l1tf_flush_l1d();
 }
 
 static inline void exiting_irq(void)
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index c356098b6fb9..4d4015ddcf26 100644
--- a/arch/x86/include/asm/apm.h
+++ b/arch/x86/include/asm/apm.h
@@ -7,8 +7,6 @@
 #ifndef _ASM_X86_MACH_DEFAULT_APM_H
 #define _ASM_X86_MACH_DEFAULT_APM_H
 
-#include <asm/nospec-branch.h>
-
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
 		"pushl %%ds\n\t" \
@@ -34,7 +32,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
-	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -47,7 +44,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		  "=S" (*esi)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
-	firmware_restrict_branch_speculation_end();
 }
 
 static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
@@ -60,7 +56,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
-	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -73,7 +68,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 		  "=S" (si)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
-	firmware_restrict_branch_speculation_end();
 	return error;
 }
 
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 219faaec51df..990770f9e76b 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -46,6 +46,65 @@
 #define _ASM_SI		__ASM_REG(si)
 #define _ASM_DI		__ASM_REG(di)
 
+#ifndef __x86_64__
+/* 32 bit */
+
+#define _ASM_ARG1	_ASM_AX
+#define _ASM_ARG2	_ASM_DX
+#define _ASM_ARG3	_ASM_CX
+
+#define _ASM_ARG1L	eax
+#define _ASM_ARG2L	edx
+#define _ASM_ARG3L	ecx
+
+#define _ASM_ARG1W	ax
+#define _ASM_ARG2W	dx
+#define _ASM_ARG3W	cx
+
+#define _ASM_ARG1B	al
+#define _ASM_ARG2B	dl
+#define _ASM_ARG3B	cl
+
+#else
+/* 64 bit */
+
+#define _ASM_ARG1	_ASM_DI
+#define _ASM_ARG2	_ASM_SI
+#define _ASM_ARG3	_ASM_DX
+#define _ASM_ARG4	_ASM_CX
+#define _ASM_ARG5	r8
+#define _ASM_ARG6	r9
+
+#define _ASM_ARG1Q	rdi
+#define _ASM_ARG2Q	rsi
+#define _ASM_ARG3Q	rdx
+#define _ASM_ARG4Q	rcx
+#define _ASM_ARG5Q	r8
+#define _ASM_ARG6Q	r9
+
+#define _ASM_ARG1L	edi
+#define _ASM_ARG2L	esi
+#define _ASM_ARG3L	edx
+#define _ASM_ARG4L	ecx
+#define _ASM_ARG5L	r8d
+#define _ASM_ARG6L	r9d
+
+#define _ASM_ARG1W	di
+#define _ASM_ARG2W	si
+#define _ASM_ARG3W	dx
+#define _ASM_ARG4W	cx
+#define _ASM_ARG5W	r8w
+#define _ASM_ARG6W	r9w
+
+#define _ASM_ARG1B	dil
+#define _ASM_ARG2B	sil
+#define _ASM_ARG3B	dl
+#define _ASM_ARG4B	cl
+#define _ASM_ARG5B	r8b
+#define _ASM_ARG6B	r9b
+
+#endif
+
 /*
  * Macros to generate condition code outputs from inline assembly,
  * The output operand must be type "bool".
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 0db6bec95489..b143717b92b3 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -80,6 +80,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic_sub_and_test arch_atomic_sub_and_test
 static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
@@ -91,6 +92,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic_inc arch_atomic_inc
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
@@ -103,6 +105,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic_dec arch_atomic_dec
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
@@ -117,6 +120,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
+#define arch_atomic_dec_and_test arch_atomic_dec_and_test
 static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
@@ -130,6 +134,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic_inc_and_test arch_atomic_inc_and_test
 static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
@@ -144,6 +149,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
+#define arch_atomic_add_negative arch_atomic_add_negative
 static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
@@ -173,9 +179,6 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
 	return arch_atomic_add_return(-i, v);
 }
 
-#define arch_atomic_inc_return(v)  (arch_atomic_add_return(1, v))
-#define arch_atomic_dec_return(v)  (arch_atomic_sub_return(1, v))
-
 static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
 {
 	return xadd(&v->counter, i);
@@ -199,7 +202,7 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n
 
 static inline int arch_atomic_xchg(atomic_t *v, int new)
 {
-	return xchg(&v->counter, new);
+	return arch_xchg(&v->counter, new);
 }
 
 static inline void arch_atomic_and(int i, atomic_t *v)
@@ -253,27 +256,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
 	return val;
 }
 
-/**
- * __arch_atomic_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns the old value of @v.
- */
-static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c = arch_atomic_read(v);
-
-	do {
-		if (unlikely(c == u))
-			break;
-	} while (!arch_atomic_try_cmpxchg(v, &c, c + a));
-
-	return c;
-}
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 92212bf0484f..ef959f02d070 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -158,6 +158,7 @@ static inline long long arch_atomic64_inc_return(atomic64_t *v)
 			     "S" (v) : "memory", "ecx");
 	return a;
 }
+#define arch_atomic64_inc_return arch_atomic64_inc_return
 
 static inline long long arch_atomic64_dec_return(atomic64_t *v)
 {
@@ -166,6 +167,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v)
 			     "S" (v) : "memory", "ecx");
 	return a;
 }
+#define arch_atomic64_dec_return arch_atomic64_dec_return
 
 /**
  * arch_atomic64_add - add integer to atomic64 variable
@@ -198,25 +200,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
 }
 
 /**
- * arch_atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v)
-{
-	return arch_atomic64_sub_return(i, v) == 0;
-}
-
-/**
  * arch_atomic64_inc - increment atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic64_inc arch_atomic64_inc
 static inline void arch_atomic64_inc(atomic64_t *v)
 {
 	__alternative_atomic64(inc, inc_return, /* no output */,
@@ -229,6 +218,7 @@ static inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic64_dec arch_atomic64_dec
 static inline void arch_atomic64_dec(atomic64_t *v)
 {
 	__alternative_atomic64(dec, dec_return, /* no output */,
@@ -236,46 +226,6 @@ static inline void arch_atomic64_dec(atomic64_t *v)
 }
 
 /**
- * arch_atomic64_dec_and_test - decrement and test
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int arch_atomic64_dec_and_test(atomic64_t *v)
-{
-	return arch_atomic64_dec_return(v) == 0;
-}
-
-/**
- * atomic64_inc_and_test - increment and test
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_inc_and_test(atomic64_t *v)
-{
-	return arch_atomic64_inc_return(v) == 0;
-}
-
-/**
- * arch_atomic64_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int arch_atomic64_add_negative(long long i, atomic64_t *v)
-{
-	return arch_atomic64_add_return(i, v) < 0;
-}
-
-/**
  * arch_atomic64_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
@@ -295,7 +245,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
 	return (int)a;
 }
 
-
+#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
 static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
@@ -304,6 +254,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 	return r;
 }
 
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
 static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	long long r;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 6106b59d3260..4343d9b4f30e 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -71,6 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
 static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
@@ -82,6 +83,7 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic64_inc arch_atomic64_inc
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
@@ -95,6 +97,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic64_dec arch_atomic64_dec
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
@@ -110,6 +113,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
+#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
 static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
@@ -123,6 +127,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
 static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
@@ -137,6 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
+#define arch_atomic64_add_negative arch_atomic64_add_negative
 static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
@@ -169,9 +175,6 @@ static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v)
 	return xadd(&v->counter, -i);
 }
 
-#define arch_atomic64_inc_return(v)  (arch_atomic64_add_return(1, (v)))
-#define arch_atomic64_dec_return(v)  (arch_atomic64_sub_return(1, (v)))
-
 static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
 {
 	return arch_cmpxchg(&v->counter, old, new);
@@ -185,46 +188,7 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, l
 
 static inline long arch_atomic64_xchg(atomic64_t *v, long new)
 {
-	return xchg(&v->counter, new);
-}
-
-/**
- * arch_atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	s64 c = arch_atomic64_read(v);
-	do {
-		if (unlikely(c == u))
-			return false;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, c + a));
-	return true;
-}
-
-#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0)
-
-/*
- * arch_atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
-{
-	s64 dec, c = arch_atomic64_read(v);
-	do {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, dec));
-	return dec;
+	return arch_xchg(&v->counter, new);
 }
 
 static inline void arch_atomic64_and(long i, atomic64_t *v)
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index e3efd8a06066..a55d79b233d3 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -75,7 +75,7 @@ extern void __add_wrong_size(void)
  * use "asm volatile" and "memory" clobbers to prevent gcc from moving
  * information around.
  */
-#define xchg(ptr, v)	__xchg_op((ptr), (v), xchg, "")
+#define arch_xchg(ptr, v)	__xchg_op((ptr), (v), xchg, "")
 
 /*
  * Atomic compare and exchange.  Compare OLD with MEM, if identical,
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index bfca3b346c74..072e5459fe2f 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -10,13 +10,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 #define arch_cmpxchg64(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg((ptr), (o), (n));					\
+	arch_cmpxchg((ptr), (o), (n));					\
 })
 
 #define arch_cmpxchg64_local(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
+	arch_cmpxchg_local((ptr), (o), (n));				\
 })
 
 #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 5701f5cecd31..89a048c2faec 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -219,6 +219,8 @@
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
+#define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -229,7 +231,7 @@
 
 #define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
 #define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
-
+#define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -341,6 +343,7 @@
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
@@ -373,5 +376,6 @@
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h
index 0ab2ab27ad1f..b825cb201251 100644
--- a/arch/x86/include/asm/dmi.h
+++ b/arch/x86/include/asm/dmi.h
@@ -4,8 +4,8 @@
 
 #include <linux/compiler.h>
 #include <linux/init.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/setup.h>
 
 static __always_inline __init void *dmi_alloc(unsigned len)
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 740a428acf1e..d9069bb26c7f 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -3,10 +3,12 @@
 #define _ASM_X86_HARDIRQ_H
 
 #include <linux/threads.h>
-#include <linux/irq.h>
 
 typedef struct {
-	unsigned int __softirq_pending;
+	u16	     __softirq_pending;
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+	u8	     kvm_cpu_l1tf_flush_l1d;
+#endif
 	unsigned int __nmi_count;	/* arch dependent */
 #ifdef CONFIG_X86_LOCAL_APIC
 	unsigned int apic_timer_irqs;	/* arch dependent */
@@ -58,4 +60,24 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu);
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat		arch_irq_stat
 
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+static inline void kvm_set_cpu_l1tf_flush_l1d(void)
+{
+	__this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1);
+}
+
+static inline void kvm_clear_cpu_l1tf_flush_l1d(void)
+{
+	__this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 0);
+}
+
+static inline bool kvm_get_cpu_l1tf_flush_l1d(void)
+{
+	return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d);
+}
+#else /* !IS_ENABLED(CONFIG_KVM_INTEL) */
+static inline void kvm_set_cpu_l1tf_flush_l1d(void) { }
+#endif /* IS_ENABLED(CONFIG_KVM_INTEL) */
+
 #endif /* _ASM_X86_HARDIRQ_H */
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index f59c39835a5a..a1f0e90d0818 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -49,11 +49,14 @@ static inline int hw_breakpoint_slots(int type)
 	return HBP_NUM;
 }
 
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index cf090e584202..7ed08a7c3398 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -76,4 +76,17 @@
 #define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
 #define INTEL_FAM6_XEON_PHI_KNM		0x85 /* Knights Mill */
 
+/* Useful macros */
+#define INTEL_CPU_FAM_ANY(_family, _model, _driver_data)	\
+{								\
+	.vendor		= X86_VENDOR_INTEL,			\
+	.family		= _family,				\
+	.model		= _model,				\
+	.feature	= X86_FEATURE_ANY,			\
+	.driver_data	= (kernel_ulong_t)&_driver_data		\
+}
+
+#define INTEL_CPU_FAM6(_model, _driver_data)			\
+	INTEL_CPU_FAM_ANY(6, INTEL_FAM6_##_model, _driver_data)
+
 #endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index fe04491130ae..52f815a80539 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -80,35 +80,6 @@ enum intel_mid_cpu_type {
 
 extern enum intel_mid_cpu_type __intel_mid_cpu_chip;
 
-/**
- * struct intel_mid_ops - Interface between intel-mid & sub archs
- * @arch_setup: arch_setup function to re-initialize platform
- *		structures (x86_init, x86_platform_init)
- *
- * This structure can be extended if any new interface is required
- * between intel-mid & its sub arch files.
- */
-struct intel_mid_ops {
-	void (*arch_setup)(void);
-};
-
-/* Helper API's for INTEL_MID_OPS_INIT */
-#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid)				\
-	[cpuid] = get_##cpuname##_ops
-
-/* Maximum number of CPU ops */
-#define MAX_CPU_OPS(a)			(sizeof(a)/sizeof(void *))
-
-/*
- * For every new cpu addition, a weak get_<cpuname>_ops() function needs be
- * declared in arch/x86/platform/intel_mid/intel_mid_weak_decls.h.
- */
-#define INTEL_MID_OPS_INIT {							\
-	DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL),	\
-	DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW),	\
-	DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER)		\
-};
-
 #ifdef CONFIG_X86_INTEL_MID
 
 static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void)
@@ -136,20 +107,6 @@ enum intel_mid_timer_options {
 
 extern enum intel_mid_timer_options intel_mid_timer_options;
 
-/*
- * Penwell uses spread spectrum clock, so the freq number is not exactly
- * the same as reported by MSR based on SDM.
- */
-#define FSB_FREQ_83SKU			83200
-#define FSB_FREQ_100SKU			99840
-#define FSB_FREQ_133SKU			133000
-
-#define FSB_FREQ_167SKU			167000
-#define FSB_FREQ_200SKU			200000
-#define FSB_FREQ_267SKU			267000
-#define FSB_FREQ_333SKU			333000
-#define FSB_FREQ_400SKU			400000
-
 /* Bus Select SoC Fuse value */
 #define BSEL_SOC_FUSE_MASK		0x7
 /* FSB 133MHz */
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index 62a9f4966b42..ae26df1c2789 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -8,6 +8,7 @@
 
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS		8
+#define MAX_FIXED_PEBS_EVENTS	3
 
 /*
  * A debug store configuration.
@@ -23,7 +24,7 @@ struct debug_store {
 	u64	pebs_index;
 	u64	pebs_absolute_maximum;
 	u64	pebs_interrupt_threshold;
-	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+	u64	pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS];
 } __aligned(PAGE_SIZE);
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 89f08955fff7..c14f2a74b2be 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -13,7 +13,9 @@
  * Interrupt control:
  */
 
-static inline unsigned long native_save_fl(void)
+/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */
+extern inline unsigned long native_save_fl(void);
+extern inline unsigned long native_save_fl(void)
 {
 	unsigned long flags;
 
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 367d99cff426..c8cec1b39b88 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -78,7 +78,7 @@ struct arch_specific_insn {
 	 * boostable = true: This instruction has been boosted: we have
 	 * added a relative jump after the instruction copy in insn,
 	 * so no single-step and fixup are needed (unless there's
-	 * a post_handler or break_handler).
+	 * a post_handler).
 	 */
 	bool boostable;
 	bool if_modifier;
@@ -111,9 +111,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_old_flags;
 	unsigned long kprobe_saved_flags;
-	unsigned long *jprobe_saved_sp;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/x86/include/asm/kvm_guest.h b/arch/x86/include/asm/kvm_guest.h
deleted file mode 100644
index 46185263d9c2..000000000000
--- a/arch/x86/include/asm/kvm_guest.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_KVM_GUEST_H
-#define _ASM_X86_KVM_GUEST_H
-
-int kvm_setup_vsyscall_timeinfo(void);
-
-#endif /* _ASM_X86_KVM_GUEST_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c13cd28d9d1b..acebb808c4b5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -17,6 +17,7 @@
 #include <linux/tracepoint.h>
 #include <linux/cpumask.h>
 #include <linux/irq_work.h>
+#include <linux/irq.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
@@ -713,6 +714,9 @@ struct kvm_vcpu_arch {
 
 	/* be preempted when it's in kernel-mode(cpl=0) */
 	bool preempted_in_kernel;
+
+	/* Flush the L1 Data cache for L1TF mitigation on VMENTER */
+	bool l1tf_flush_l1d;
 };
 
 struct kvm_lpage_info {
@@ -881,6 +885,7 @@ struct kvm_vcpu_stat {
 	u64 signal_exits;
 	u64 irq_window_exits;
 	u64 nmi_window_exits;
+	u64 l1d_flush;
 	u64 halt_exits;
 	u64 halt_successful_poll;
 	u64 halt_attempted_poll;
@@ -1413,6 +1418,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
 
+u64 kvm_get_arch_capabilities(void);
 void kvm_define_shared_msr(unsigned index, u32 msr);
 int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 3aea2658323a..4c723632c036 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -7,7 +7,6 @@
 #include <uapi/asm/kvm_para.h>
 
 extern void kvmclock_init(void);
-extern int kvm_register_clock(char *txt);
 
 #ifdef CONFIG_KVM_GUEST
 bool kvm_check_and_clear_guest_paused(void);
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index bbc796eb0a3b..eeeb9289c764 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -71,12 +71,7 @@ struct ldt_struct {
 
 static inline void *ldt_slot_va(int slot)
 {
-#ifdef CONFIG_X86_64
 	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
-#else
-	BUG();
-	return (void *)fix_to_virt(FIX_HOLE);
-#endif
 }
 
 /*
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 3cd14311edfa..19886fef1dfc 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -9,6 +9,8 @@
 #include <asm/hyperv-tlfs.h>
 #include <asm/nospec-branch.h>
 
+#define VP_INVAL	U32_MAX
+
 struct ms_hyperv_info {
 	u32 features;
 	u32 misc_features;
@@ -20,7 +22,6 @@ struct ms_hyperv_info {
 
 extern struct ms_hyperv_info ms_hyperv;
 
-
 /*
  * Generate the guest ID.
  */
@@ -193,6 +194,40 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 		return hv_status;
 }
 
+/* Fast hypercall with 16 bytes of input */
+static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
+{
+	u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
+
+#ifdef CONFIG_X86_64
+	{
+		__asm__ __volatile__("mov %4, %%r8\n"
+				     CALL_NOSPEC
+				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
+				       "+c" (control), "+d" (input1)
+				     : "r" (input2),
+				       THUNK_TARGET(hv_hypercall_pg)
+				     : "cc", "r8", "r9", "r10", "r11");
+	}
+#else
+	{
+		u32 input1_hi = upper_32_bits(input1);
+		u32 input1_lo = lower_32_bits(input1);
+		u32 input2_hi = upper_32_bits(input2);
+		u32 input2_lo = lower_32_bits(input2);
+
+		__asm__ __volatile__ (CALL_NOSPEC
+				      : "=A"(hv_status),
+					"+c"(input1_lo), ASM_CALL_CONSTRAINT
+				      :	"A" (control), "b" (input1_hi),
+					"D"(input2_hi), "S"(input2_lo),
+					THUNK_TARGET(hv_hypercall_pg)
+				      : "cc");
+	}
+#endif
+		return hv_status;
+}
+
 /*
  * Rep hypercalls. Callers of this functions are supposed to ensure that
  * rep_count and varhead_size comply with Hyper-V hypercall definition.
@@ -281,6 +316,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 	 */
 	for_each_cpu(cpu, cpus) {
 		vcpu = hv_cpu_number_to_vp_number(cpu);
+		if (vcpu == VP_INVAL)
+			return -1;
 		vcpu_bank = vcpu / 64;
 		vcpu_offset = vcpu % 64;
 		__set_bit(vcpu_offset, (unsigned long *)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 68b2c3150de1..4731f0cf97c5 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -70,12 +70,19 @@
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
 #define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
 #define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	(1 << 3)   /* Skip L1D flush on vmentry */
 #define ARCH_CAP_SSB_NO			(1 << 4)   /*
 						    * Not susceptible to Speculative Store Bypass
 						    * attack, so no Speculative Store Bypass
 						    * control required.
 						    */
 
+#define MSR_IA32_FLUSH_CMD		0x0000010b
+#define L1D_FLUSH			(1 << 0)   /*
+						    * Writeback and invalidate the
+						    * L1 data cache.
+						    */
+
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index f6f6c63da62f..fd2a8c1b88bc 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -214,7 +214,7 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
 	SPECTRE_V2_RETPOLINE_GENERIC,
 	SPECTRE_V2_RETPOLINE_AMD,
-	SPECTRE_V2_IBRS,
+	SPECTRE_V2_IBRS_ENHANCED,
 };
 
 /* The Speculative Store Bypass disable variants */
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 9c9dc579bd7d..46f516dd80ce 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -88,6 +88,7 @@ struct orc_entry {
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
+	unsigned	end:1;
 } __packed;
 
 /*
@@ -101,6 +102,7 @@ struct unwind_hint {
 	s16		sp_offset;
 	u8		sp_reg;
 	u8		type;
+	u8		end;
 };
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index aa30c3241ea7..0d5c739eebd7 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -29,8 +29,13 @@
 #define N_EXCEPTION_STACKS 1
 
 #ifdef CONFIG_X86_PAE
-/* 44=32+12, the limit we can fit into an unsigned long pfn */
-#define __PHYSICAL_MASK_SHIFT	44
+/*
+ * This is beyond the 44 bit limit imposed by the 32bit long pfns,
+ * but we need the full mask to make sure inverted PROT_NONE
+ * entries have all the host bits set in a guest.
+ * The real limit is still 44 bits.
+ */
+#define __PHYSICAL_MASK_SHIFT	52
 #define __VIRTUAL_MASK_SHIFT	32
 
 #else  /* !CONFIG_X86_PAE */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index a06b07399d17..e9202a0de8f0 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -450,9 +450,10 @@ do {									\
 	bool __ret;							\
 	typeof(pcp1) __o1 = (o1), __n1 = (n1);				\
 	typeof(pcp2) __o2 = (o2), __n2 = (n2);				\
-	asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t"	\
-		    : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \
-		    :  "b" (__n1), "c" (__n2), "a" (__o1));		\
+	asm volatile("cmpxchg8b "__percpu_arg(1)			\
+		     CC_SET(z)						\
+		     : CC_OUT(z) (__ret), "+m" (pcp1), "+m" (pcp2), "+a" (__o1), "+d" (__o2) \
+		     : "b" (__n1), "c" (__n2));				\
 	__ret;								\
 })
 
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index ada6410fd2ec..fbd578daa66e 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -184,6 +184,9 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
 
 static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
 {
+	if (!pgtable_l5_enabled())
+		return;
+
 	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
 	free_page((unsigned long)p4d);
 }
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 685ffe8a0eaf..24c6cf5f16b7 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -19,6 +19,9 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte)
 
 static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd);
+#endif
 	*pmdp = pmd;
 }
 
@@ -58,6 +61,9 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #ifdef CONFIG_SMP
 static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0));
+#endif
 	return __pmd(xchg((pmdval_t *)xp, 0));
 }
 #else
@@ -67,6 +73,9 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #ifdef CONFIG_SMP
 static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0));
+#endif
 	return __pud(xchg((pudval_t *)xp, 0));
 }
 #else
@@ -95,4 +104,21 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
 
+/* No inverted PFNs on 2 level page tables */
+
+static inline u64 protnone_mask(u64 val)
+{
+	return 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	return val;
+}
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_PGTABLE_2LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index f982ef808e7e..6deb6cd236e3 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -35,4 +35,7 @@ typedef union {
 
 #define PTRS_PER_PTE	1024
 
+/* This covers all VMSPLIT_* and VMSPLIT_*_OPT variants */
+#define PGD_KERNEL_START	(CONFIG_PAGE_OFFSET >> PGDIR_SHIFT)
+
 #endif /* _ASM_X86_PGTABLE_2LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index f24df59c40b2..a564084c6141 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -98,6 +98,9 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 
 static inline void native_set_pud(pud_t *pudp, pud_t pud)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd);
+#endif
 	set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
 }
 
@@ -229,6 +232,10 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
 {
 	union split_pud res, *orig = (union split_pud *)pudp;
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pti_set_user_pgtbl(&pudp->p4d.pgd, __pgd(0));
+#endif
+
 	/* xchg acts as a barrier before setting of the high bits */
 	res.pud_low = xchg(&orig->pud_low, 0);
 	res.pud_high = orig->pud_high;
@@ -241,12 +248,43 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
 #endif
 
 /* Encode and de-code a swap entry */
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS)
+
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
 #define __swp_type(x)			(((x).val) & 0x1f)
 #define __swp_offset(x)			((x).val >> 5)
 #define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << 5})
-#define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
-#define __swp_entry_to_pte(x)		((pte_t){ { .pte_high = (x).val } })
+
+/*
+ * Normally, __swp_entry() converts from arch-independent swp_entry_t to
+ * arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result
+ * to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the
+ * whole 64 bits. Thus, we shift the "real" arch-dependent conversion to
+ * __swp_entry_to_pte() through the following helper macro based on 64bit
+ * __swp_entry().
+ */
+#define __swp_pteval_entry(type, offset) ((pteval_t) { \
+	(~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) })
+
+#define __swp_entry_to_pte(x)	((pte_t){ .pte = \
+		__swp_pteval_entry(__swp_type(x), __swp_offset(x)) })
+/*
+ * Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent
+ * swp_entry_t, but also has to convert it from 64bit to the 32bit
+ * intermediate representation, using the following macros based on 64bit
+ * __swp_type() and __swp_offset().
+ */
+#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS)))
+#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT))
+
+#define __pte_to_swp_entry(pte)	(__swp_entry(__pteval_swp_type(pte), \
+					     __pteval_swp_offset(pte)))
 
 #define gup_get_pte gup_get_pte
 /*
@@ -295,4 +333,6 @@ static inline pte_t gup_get_pte(pte_t *ptep)
 	return pte;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* _ASM_X86_PGTABLE_3LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 6a59a6d0cc50..858358a82b14 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -21,9 +21,10 @@ typedef union {
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_PARAVIRT
-#define SHARED_KERNEL_PMD	(pv_info.shared_kernel_pmd)
+#define SHARED_KERNEL_PMD	((!static_cpu_has(X86_FEATURE_PTI) &&	\
+				 (pv_info.shared_kernel_pmd)))
 #else
-#define SHARED_KERNEL_PMD	1
+#define SHARED_KERNEL_PMD	(!static_cpu_has(X86_FEATURE_PTI))
 #endif
 
 /*
@@ -45,5 +46,6 @@ typedef union {
 #define PTRS_PER_PTE	512
 
 #define MAX_POSSIBLE_PHYSMEM_BITS	36
+#define PGD_KERNEL_START	(CONFIG_PAGE_OFFSET >> PGDIR_SHIFT)
 
 #endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h
new file mode 100644
index 000000000000..44b1203ece12
--- /dev/null
+++ b/arch/x86/include/asm/pgtable-invert.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_PGTABLE_INVERT_H
+#define _ASM_PGTABLE_INVERT_H 1
+
+#ifndef __ASSEMBLY__
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return !(val & _PAGE_PRESENT);
+}
+
+/* Get a mask to xor with the page table entry to get the correct pfn. */
+static inline u64 protnone_mask(u64 val)
+{
+	return __pte_needs_invert(val) ?  ~0ull : 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	/*
+	 * When a PTE transitions from NONE to !NONE or vice-versa
+	 * invert the PFN part to stop speculation.
+	 * pte_pfn undoes this when needed.
+	 */
+	if (__pte_needs_invert(oldval) != __pte_needs_invert(val))
+		val = (val & ~mask) | (~val & mask);
+	return val;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 99ecde23c3ec..e4ffa565a69f 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -30,11 +30,14 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
 void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
 void ptdump_walk_pgd_level_checkwx(void);
+void ptdump_walk_user_pgd_level_checkwx(void);
 
 #ifdef CONFIG_DEBUG_WX
-#define debug_checkwx() ptdump_walk_pgd_level_checkwx()
+#define debug_checkwx()		ptdump_walk_pgd_level_checkwx()
+#define debug_checkwx_user()	ptdump_walk_user_pgd_level_checkwx()
 #else
-#define debug_checkwx() do { } while (0)
+#define debug_checkwx()		do { } while (0)
+#define debug_checkwx_user()	do { } while (0)
 #endif
 
 /*
@@ -185,19 +188,29 @@ static inline int pte_special(pte_t pte)
 	return pte_flags(pte) & _PAGE_SPECIAL;
 }
 
+/* Entries that were set to PROT_NONE are inverted */
+
+static inline u64 protnone_mask(u64 val);
+
 static inline unsigned long pte_pfn(pte_t pte)
 {
-	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
+	phys_addr_t pfn = pte_val(pte);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
+	phys_addr_t pfn = pmd_val(pmd);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pud_pfn(pud_t pud)
 {
-	return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
+	phys_addr_t pfn = pud_val(pud);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long p4d_pfn(p4d_t p4d)
@@ -400,11 +413,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_RW);
 }
 
-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
-{
-	return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
-}
-
 static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
 {
 	pudval_t v = native_pud_val(pud);
@@ -459,11 +467,6 @@ static inline pud_t pud_mkwrite(pud_t pud)
 	return pud_set_flags(pud, _PAGE_RW);
 }
 
-static inline pud_t pud_mknotpresent(pud_t pud)
-{
-	return pud_clear_flags(pud, _PAGE_PRESENT | _PAGE_PROTNONE);
-}
-
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline int pte_soft_dirty(pte_t pte)
 {
@@ -545,25 +548,45 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot)
 
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PTE_PFN_MASK;
+	return __pte(pfn | check_pgprot(pgprot));
 }
 
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PMD_PAGE_MASK;
+	return __pmd(pfn | check_pgprot(pgprot));
 }
 
 static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PUD_PAGE_MASK;
+	return __pud(pfn | check_pgprot(pgprot));
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return pfn_pmd(pmd_pfn(pmd),
+		      __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
+}
+
+static inline pud_t pud_mknotpresent(pud_t pud)
+{
+	return pfn_pud(pud_pfn(pud),
+	      __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
 }
 
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);
+
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	pteval_t val = pte_val(pte);
+	pteval_t val = pte_val(pte), oldval = val;
 
 	/*
 	 * Chop off the NX bit (if present), and add the NX portion of
@@ -571,17 +594,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 */
 	val &= _PAGE_CHG_MASK;
 	val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PTE_PFN_MASK);
 	return __pte(val);
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	pmdval_t val = pmd_val(pmd);
+	pmdval_t val = pmd_val(pmd), oldval = val;
 
 	val &= _HPAGE_CHG_MASK;
 	val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);
 	return __pmd(val);
 }
 
@@ -640,8 +663,31 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 
 pmd_t *populate_extra_pmd(unsigned long vaddr);
 pte_t *populate_extra_pte(unsigned long vaddr);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return pgd;
+	return __pti_set_user_pgtbl(pgdp, pgd);
+}
+#else   /* CONFIG_PAGE_TABLE_ISOLATION */
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+#endif  /* CONFIG_PAGE_TABLE_ISOLATION */
+
 #endif	/* __ASSEMBLY__ */
 
+
 #ifdef CONFIG_X86_32
 # include <asm/pgtable_32.h>
 #else
@@ -898,7 +944,7 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
 #define pgd_page(pgd)	pfn_to_page(pgd_pfn(pgd))
 
 /* to find an entry in a page-table-directory. */
-static __always_inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
 	if (!pgtable_l5_enabled())
 		return (p4d_t *)pgd;
@@ -1154,6 +1200,70 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 	}
 }
 #endif
+/*
+ * Page table pages are page-aligned.  The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+	unsigned long ptr = (unsigned long)__ptr;
+
+	return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
+}
+
+static inline int pgd_large(pgd_t pgd) { return 0; }
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
+ * the user one is in the last 4k.  To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr |= BIT(bit);
+	return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr &= ~BIT(bit);
+	return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
 
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
@@ -1320,6 +1430,14 @@ static inline bool pud_access_permitted(pud_t pud, bool write)
 	return __pte_access_permitted(pud_val(pud), write);
 }
 
+#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1
+extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot);
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return boot_cpu_has_bug(X86_BUG_L1TF);
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 88a056b01db4..b3ec519e3982 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -34,8 +34,6 @@ static inline void check_pgt_cache(void) { }
 void paging_init(void);
 void sync_initial_page_table(void);
 
-static inline int pgd_large(pgd_t pgd) { return 0; }
-
 /*
  * Define this if things work differently on an i386 and an i486:
  * it will (on an i486) warn about kernel memory accesses that are
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index d9a001a4a872..b0bc0fff5f1f 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -50,13 +50,18 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 	((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1))   \
 	 & PMD_MASK)
 
-#define PKMAP_BASE		\
+#define LDT_BASE_ADDR		\
 	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
+#define LDT_END_ADDR		(LDT_BASE_ADDR + PMD_SIZE)
+
+#define PKMAP_BASE		\
+	((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK)
+
 #ifdef CONFIG_HIGHMEM
 # define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
 #else
-# define VMALLOC_END	(CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
+# define VMALLOC_END	(LDT_BASE_ADDR - 2 * PAGE_SIZE)
 #endif
 
 #define MODULES_VADDR	VMALLOC_START
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 0fdcd21dadbd..f773d5e6c8cc 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -132,91 +132,7 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-/*
- * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
- * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
- * the user one is in the last 4k.  To switch between them, you
- * just need to flip the 12th bit in their addresses.
- */
-#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
-
-/*
- * This generates better code than the inline assembly in
- * __set_bit().
- */
-static inline void *ptr_set_bit(void *ptr, int bit)
-{
-	unsigned long __ptr = (unsigned long)ptr;
-
-	__ptr |= BIT(bit);
-	return (void *)__ptr;
-}
-static inline void *ptr_clear_bit(void *ptr, int bit)
-{
-	unsigned long __ptr = (unsigned long)ptr;
-
-	__ptr &= ~BIT(bit);
-	return (void *)__ptr;
-}
-
-static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
-{
-	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
-{
-	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
-{
-	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
-{
-	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
-#endif /* CONFIG_PAGE_TABLE_ISOLATION */
-
-/*
- * Page table pages are page-aligned.  The lower half of the top
- * level is used for userspace and the top half for the kernel.
- *
- * Returns true for parts of the PGD that map userspace and
- * false for the parts that map the kernel.
- */
-static inline bool pgdp_maps_userspace(void *__ptr)
-{
-	unsigned long ptr = (unsigned long)__ptr;
-
-	return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
-}
-
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
-
-/*
- * Take a PGD location (pgdp) and a pgd value that needs to be set there.
- * Populates the user and returns the resulting PGD that must be set in
- * the kernel copy of the page tables.
- */
-static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	if (!static_cpu_has(X86_FEATURE_PTI))
-		return pgd;
-	return __pti_set_user_pgd(pgdp, pgd);
-}
-#else
-static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	return pgd;
-}
-#endif
-
-static __always_inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
+static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	pgd_t pgd;
 
@@ -226,18 +142,18 @@ static __always_inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 	}
 
 	pgd = native_make_pgd(native_p4d_val(p4d));
-	pgd = pti_set_user_pgd((pgd_t *)p4dp, pgd);
+	pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd);
 	*p4dp = native_make_p4d(native_pgd_val(pgd));
 }
 
-static __always_inline void native_p4d_clear(p4d_t *p4d)
+static inline void native_p4d_clear(p4d_t *p4d)
 {
 	native_set_p4d(p4d, native_make_p4d(0));
 }
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
-	*pgdp = pti_set_user_pgd(pgdp, pgd);
+	*pgdp = pti_set_user_pgtbl(pgdp, pgd);
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)
@@ -255,7 +171,6 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
 /*
  * Level 4 access.
  */
-static inline int pgd_large(pgd_t pgd) { return 0; }
 #define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
 
 /* PUD - Level3 access */
@@ -273,7 +188,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | OFFSET (14->63) | TYPE (9-13)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -286,20 +201,34 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
+ *
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
  */
-#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
-#define SWP_TYPE_BITS 5
-/* Place the offset above the type: */
-#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS)
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS)
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 
-#define __swp_type(x)			(((x).val >> (SWP_TYPE_FIRST_BIT)) \
-					 & ((1U << SWP_TYPE_BITS) - 1))
-#define __swp_offset(x)			((x).val >> SWP_OFFSET_FIRST_BIT)
-#define __swp_entry(type, offset)	((swp_entry_t) { \
-					 ((type) << (SWP_TYPE_FIRST_BIT)) \
-					 | ((offset) << SWP_OFFSET_FIRST_BIT) })
+/* Extract the high bits for type */
+#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS))
+
+/* Shift up (to get rid of type), then down to get value */
+#define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
+
+/*
+ * Shift the offset up "too far" by TYPE bits, then down again
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
+ */
+#define __swp_entry(type, offset) ((swp_entry_t) { \
+	(~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((unsigned long)(type) << (64-SWP_TYPE_BITS)) })
+
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __pmd_to_swp_entry(pmd)		((swp_entry_t) { pmd_val((pmd)) })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
@@ -343,5 +272,7 @@ static inline bool gup_fast_permitted(unsigned long start, int nr_pages,
 	return true;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_PGTABLE_64_H */
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 054765ab2da2..04edd2d58211 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -115,6 +115,7 @@ extern unsigned int ptrs_per_p4d;
 #define LDT_PGD_ENTRY_L5	-112UL
 #define LDT_PGD_ENTRY		(pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
 #define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
+#define LDT_END_ADDR		(LDT_BASE_ADDR + PGDIR_SIZE)
 
 #define __VMALLOC_BASE_L4	0xffffc90000000000UL
 #define __VMALLOC_BASE_L5 	0xffa0000000000000UL
@@ -153,4 +154,6 @@ extern unsigned int ptrs_per_p4d;
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
+#define PGD_KERNEL_START	((PAGE_SIZE / 2) / sizeof(pgd_t))
+
 #endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 99fff853c944..b64acb08a62b 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -50,6 +50,7 @@
 #define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
 #define _PAGE_SOFTW1	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
 #define _PAGE_SOFTW2	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
+#define _PAGE_SOFTW3	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW3)
 #define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
@@ -266,14 +267,37 @@ typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
 
 typedef struct { pgdval_t pgd; } pgd_t;
 
+#ifdef CONFIG_X86_PAE
+
+/*
+ * PHYSICAL_PAGE_MASK might be non-constant when SME is compiled in, so we can't
+ * use it here.
+ */
+
+#define PGD_PAE_PAGE_MASK	((signed long)PAGE_MASK)
+#define PGD_PAE_PHYS_MASK	(((1ULL << __PHYSICAL_MASK_SHIFT)-1) & PGD_PAE_PAGE_MASK)
+
+/*
+ * PAE allows Base Address, P, PWT, PCD and AVL bits to be set in PGD entries.
+ * All other bits are Reserved MBZ
+ */
+#define PGD_ALLOWED_BITS	(PGD_PAE_PHYS_MASK | _PAGE_PRESENT | \
+				 _PAGE_PWT | _PAGE_PCD | \
+				 _PAGE_SOFTW1 | _PAGE_SOFTW2 | _PAGE_SOFTW3)
+
+#else
+/* No need to mask any bits for !PAE */
+#define PGD_ALLOWED_BITS	(~0ULL)
+#endif
+
 static inline pgd_t native_make_pgd(pgdval_t val)
 {
-	return (pgd_t) { val };
+	return (pgd_t) { val & PGD_ALLOWED_BITS };
 }
 
 static inline pgdval_t native_pgd_val(pgd_t pgd)
 {
-	return pgd.pgd;
+	return pgd.pgd & PGD_ALLOWED_BITS;
 }
 
 static inline pgdval_t pgd_flags(pgd_t pgd)
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 625a52a5594f..02c2cbda4a74 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -39,10 +39,6 @@
 #define CR3_PCID_MASK	0xFFFull
 #define CR3_NOFLUSH	BIT_ULL(63)
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-# define X86_CR3_PTI_PCID_USER_BIT	11
-#endif
-
 #else
 /*
  * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
@@ -53,4 +49,8 @@
 #define CR3_NOFLUSH	0
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_PCID_USER_BIT	11
+#endif
+
 #endif /* _ASM_X86_PROCESSOR_FLAGS_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cfd29ee8c3da..682286aca881 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -181,6 +181,11 @@ extern const struct seq_operations cpuinfo_op;
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
 
+static inline unsigned long l1tf_pfn_limit(void)
+{
+	return BIT(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT) - 1;
+}
+
 extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);
@@ -966,6 +971,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 
 extern unsigned long arch_align_stack(unsigned long sp);
 extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+extern void free_kernel_image_pages(void *begin, void *end);
 
 void default_idle(void);
 #ifdef	CONFIG_XEN
@@ -977,4 +983,16 @@ bool xen_set_default_idle(void);
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
 void microcode_check(void);
+
+enum l1tf_mitigations {
+	L1TF_MITIGATION_OFF,
+	L1TF_MITIGATION_FLUSH_NOWARN,
+	L1TF_MITIGATION_FLUSH,
+	L1TF_MITIGATION_FLUSH_NOSMT,
+	L1TF_MITIGATION_FULL,
+	L1TF_MITIGATION_FULL_FORCE
+};
+
+extern enum l1tf_mitigations l1tf_mitigation;
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
index 38a17f1d5c9d..5df09a0b80b8 100644
--- a/arch/x86/include/asm/pti.h
+++ b/arch/x86/include/asm/pti.h
@@ -6,10 +6,9 @@
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 extern void pti_init(void);
 extern void pti_check_boottime_disable(void);
-extern void pti_clone_kernel_text(void);
+extern void pti_finalize(void);
 #else
 static inline void pti_check_boottime_disable(void) { }
-static inline void pti_clone_kernel_text(void) { }
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 9ef5ee03d2d7..159622ee0674 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -43,7 +43,7 @@ asm    (".pushsection .text;"
 	"push  %rdx;"
 	"mov   $0x1,%eax;"
 	"xor   %edx,%edx;"
-	"lock cmpxchg %dl,(%rdi);"
+	LOCK_PREFIX "cmpxchg %dl,(%rdi);"
 	"cmp   $0x1,%al;"
 	"jne   .slowpath;"
 	"pop   %rdx;"
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 4cf11d88d3b3..19b90521954c 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -5,6 +5,7 @@
  * PaX/grsecurity.
  */
 #include <linux/refcount.h>
+#include <asm/bug.h>
 
 /*
  * This is the first portion of the refcount error handling, which lives in
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 5c019d23d06b..4a911a382ade 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -7,6 +7,7 @@
 
 extern char __brk_base[], __brk_limit[];
 extern struct exception_table_entry __stop___ex_table[];
+extern char __end_rodata_aligned[];
 
 #if defined(CONFIG_X86_64)
 extern char __end_rodata_hpage_align[];
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index bd090367236c..34cffcef7375 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -46,6 +46,7 @@ int set_memory_np(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
 int set_memory_encrypted(unsigned long addr, int numpages);
 int set_memory_decrypted(unsigned long addr, int numpages);
+int set_memory_np_noalias(unsigned long addr, int numpages);
 
 int set_memory_array_uc(unsigned long *addr, int addrinarray);
 int set_memory_array_wc(unsigned long *addr, int addrinarray);
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index eb5f7999a893..36bd243843d6 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -87,15 +87,25 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
 #endif
 
 /* This is used when switching tasks or entering/exiting vm86 mode. */
-static inline void update_sp0(struct task_struct *task)
+static inline void update_task_stack(struct task_struct *task)
 {
-	/* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
+	/* sp0 always points to the entry trampoline stack, which is constant: */
 #ifdef CONFIG_X86_32
-	load_sp0(task->thread.sp0);
+	if (static_cpu_has(X86_FEATURE_XENPV))
+		load_sp0(task->thread.sp0);
+	else
+		this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
 #else
+	/*
+	 * x86-64 updates x86_tss.sp1 via cpu_current_top_of_stack. That
+	 * doesn't work on x86-32 because sp1 and
+	 * cpu_current_top_of_stack have different values (because of
+	 * the non-zero stack-padding on 32bit).
+	 */
 	if (static_cpu_has(X86_FEATURE_XENPV))
 		load_sp0(task_top_of_stack(task));
 #endif
+
 }
 
 #endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 2ecd34e2d46c..e85ff65c43c3 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -37,5 +37,6 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern int after_bootmem;
 
 #endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6690cd3fc8b1..511bf5fae8b8 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -148,22 +148,6 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 #define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
 #endif
 
-static inline bool tlb_defer_switch_to_init_mm(void)
-{
-	/*
-	 * If we have PCID, then switching to init_mm is reasonably
-	 * fast.  If we don't have PCID, then switching to init_mm is
-	 * quite slow, so we try to defer it in the hopes that we can
-	 * avoid it entirely.  The latter approach runs the risk of
-	 * receiving otherwise unnecessary IPIs.
-	 *
-	 * This choice is just a heuristic.  The tlb code can handle this
-	 * function returning true or false regardless of whether we have
-	 * PCID.
-	 */
-	return !static_cpu_has(X86_FEATURE_PCID);
-}
-
 struct tlb_context {
 	u64 ctx_id;
 	u64 tlb_gen;
@@ -554,4 +538,9 @@ extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 	native_flush_tlb_others(mask, info)
 #endif
 
+extern void tlb_flush_remove_tables(struct mm_struct *mm);
+extern void tlb_flush_remove_tables_local(void *arg);
+
+#define HAVE_TLB_FLUSH_REMOVE_TABLES
+
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index c1d2a9892352..453cf38a1c33 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -123,13 +123,17 @@ static inline int topology_max_smt_threads(void)
 }
 
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
-extern int topology_phys_to_logical_pkg(unsigned int pkg);
+int topology_phys_to_logical_pkg(unsigned int pkg);
+bool topology_is_primary_thread(unsigned int cpu);
+bool topology_smt_supported(void);
 #else
 #define topology_max_packages()			(1)
 static inline int
 topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
 static inline int topology_max_smt_threads(void) { return 1; }
+static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
+static inline bool topology_smt_supported(void) { return false; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h
index 4253bca99989..9c0d4b588e3f 100644
--- a/arch/x86/include/asm/trace/hyperv.h
+++ b/arch/x86/include/asm/trace/hyperv.h
@@ -28,6 +28,21 @@ TRACE_EVENT(hyperv_mmu_flush_tlb_others,
 		      __entry->addr, __entry->end)
 	);
 
+TRACE_EVENT(hyperv_send_ipi_mask,
+	    TP_PROTO(const struct cpumask *cpus,
+		     int vector),
+	    TP_ARGS(cpus, vector),
+	    TP_STRUCT__entry(
+		    __field(unsigned int, ncpus)
+		    __field(int, vector)
+		    ),
+	    TP_fast_assign(__entry->ncpus = cpumask_weight(cpus);
+			   __entry->vector = vector;
+		    ),
+	    TP_printk("ncpus %d vector %x",
+		      __entry->ncpus, __entry->vector)
+	);
+
 #endif /* CONFIG_HYPERV */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 2701d221583a..eb5bbfeccb66 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -33,13 +33,13 @@ static inline cycles_t get_cycles(void)
 extern struct system_counterval_t convert_art_to_tsc(u64 art);
 extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns);
 
-extern void tsc_early_delay_calibrate(void);
+extern void tsc_early_init(void);
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
 extern void mark_tsc_async_resets(char *reason);
-extern unsigned long native_calibrate_cpu(void);
+extern unsigned long native_calibrate_cpu_early(void);
 extern unsigned long native_calibrate_tsc(void);
 extern unsigned long long native_sched_clock_from_tsc(u64 tsc);
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 62acb613114b..a9d637bc301d 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -52,7 +52,12 @@ copy_to_user_mcsafe(void *to, const void *from, unsigned len)
 	unsigned long ret;
 
 	__uaccess_begin();
-	ret = memcpy_mcsafe(to, from, len);
+	/*
+	 * Note, __memcpy_mcsafe() is explicitly used since it can
+	 * handle exceptions / faults.  memcpy_mcsafe() may fall back to
+	 * memcpy() which lacks this handling.
+	 */
+	ret = __memcpy_mcsafe(to, from, len);
 	__uaccess_end();
 	return ret;
 }
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index bae46fc6b9de..0bcdb1279361 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -26,7 +26,7 @@
  * the debuginfo as necessary.  It will also warn if it sees any
  * inconsistencies.
  */
-.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL
+.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0
 #ifdef CONFIG_STACK_VALIDATION
 .Lunwind_hint_ip_\@:
 	.pushsection .discard.unwind_hints
@@ -35,12 +35,14 @@
 		.short \sp_offset
 		.byte \sp_reg
 		.byte \type
+		.byte \end
+		.balign 4
 	.popsection
 #endif
 .endm
 
 .macro UNWIND_HINT_EMPTY
-	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED
+	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1
 .endm
 
 .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0
@@ -86,19 +88,21 @@
 
 #else /* !__ASSEMBLY__ */
 
-#define UNWIND_HINT(sp_reg, sp_offset, type)			\
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
 	"987: \n\t"						\
 	".pushsection .discard.unwind_hints\n\t"		\
 	/* struct unwind_hint */				\
 	".long 987b - .\n\t"					\
-	".short " __stringify(sp_offset) "\n\t"		\
+	".short " __stringify(sp_offset) "\n\t"			\
 	".byte " __stringify(sp_reg) "\n\t"			\
 	".byte " __stringify(type) "\n\t"			\
+	".byte " __stringify(end) "\n\t"			\
+	".balign 4 \n\t"					\
 	".popsection\n\t"
 
-#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE)
+#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0)
 
-#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE)
+#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 6aa8499e1f62..95f9107449bf 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -576,4 +576,15 @@ enum vm_instruction_error_number {
 	VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID = 28,
 };
 
+enum vmx_l1d_flush_state {
+	VMENTER_L1D_FLUSH_AUTO,
+	VMENTER_L1D_FLUSH_NEVER,
+	VMENTER_L1D_FLUSH_COND,
+	VMENTER_L1D_FLUSH_ALWAYS,
+	VMENTER_L1D_FLUSH_EPT_DISABLED,
+	VMENTER_L1D_FLUSH_NOT_REQUIRED,
+};
+
+extern enum vmx_l1d_flush_state l1tf_vmx_mitigation;
+
 #endif
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index bfd882617613..6b2f90a0b149 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -209,24 +209,37 @@ extern struct { char _entry[32]; } hypercall_page[];
 })
 
 static inline long
-privcmd_call(unsigned call,
-	     unsigned long a1, unsigned long a2,
-	     unsigned long a3, unsigned long a4,
-	     unsigned long a5)
+xen_single_call(unsigned int call,
+		unsigned long a1, unsigned long a2,
+		unsigned long a3, unsigned long a4,
+		unsigned long a5)
 {
 	__HYPERCALL_DECLS;
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
-	stac();
 	asm volatile(CALL_NOSPEC
 		     : __HYPERCALL_5PARAM
 		     : [thunk_target] "a" (&hypercall_page[call])
 		     : __HYPERCALL_CLOBBER5);
-	clac();
 
 	return (long)__res;
 }
 
+static inline long
+privcmd_call(unsigned int call,
+	     unsigned long a1, unsigned long a2,
+	     unsigned long a3, unsigned long a4,
+	     unsigned long a5)
+{
+	long res;
+
+	stac();
+	res = xen_single_call(call, a1, a2, a3, a4, a5);
+	clac();
+
+	return res;
+}
+
 static inline int
 HYPERVISOR_set_trap_table(struct trap_info *table)
 {
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 02d6f5cf4e70..8824d01c0c35 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -61,6 +61,7 @@ obj-y			+= alternative.o i8253.o hw_breakpoint.o
 obj-y			+= tsc.o tsc_msr.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
+obj-y			+= irqflags.o
 
 obj-y				+= process.o
 obj-y				+= fpu/
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a481763a3776..014f214da581 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -668,6 +668,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 	local_irq_save(flags);
 	memcpy(addr, opcode, len);
 	local_irq_restore(flags);
+	sync_core();
 	/* Could also do a CLFLUSH here to speed up CPU recovery; but
 	   that causes hangs on some VIA CPUs. */
 	return addr;
@@ -693,6 +694,12 @@ void *text_poke(void *addr, const void *opcode, size_t len)
 	struct page *pages[2];
 	int i;
 
+	/*
+	 * While boot memory allocator is runnig we cannot use struct
+	 * pages as they are not yet initialized.
+	 */
+	BUG_ON(!after_bootmem);
+
 	if (!core_kernel_text((unsigned long)addr)) {
 		pages[0] = vmalloc_to_page(addr);
 		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2aabd4cb0e3f..84132eddb5a8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -56,6 +56,7 @@
 #include <asm/hypervisor.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/irq_regs.h>
 
 unsigned int num_processors;
 
@@ -573,6 +574,9 @@ static u32 skx_deadline_rev(void)
 	case 0x04: return 0x02000014;
 	}
 
+	if (boot_cpu_data.x86_stepping > 4)
+		return 0;
+
 	return ~0U;
 }
 
@@ -937,7 +941,7 @@ static int __init calibrate_APIC_clock(void)
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
 		pr_warning("APIC timer disabled due to verification failure\n");
-			return -1;
+		return -1;
 	}
 
 	return 0;
@@ -2189,6 +2193,23 @@ static int cpuid_to_apicid[] = {
 	[0 ... NR_CPUS - 1] = -1,
 };
 
+#ifdef CONFIG_SMP
+/**
+ * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread
+ * @id:	APIC ID to check
+ */
+bool apic_id_is_primary_thread(unsigned int apicid)
+{
+	u32 mask;
+
+	if (smp_num_siblings == 1)
+		return true;
+	/* Isolate the SMT bit(s) in the APICID and check for 0 */
+	mask = (1U << (fls(smp_num_siblings) - 1)) - 1;
+	return !(apicid & mask);
+}
+#endif
+
 /*
  * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
  * and cpuid_to_apicid[] synchronized.
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 3982f79d2377..ff0d14cd9e82 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -33,6 +33,7 @@
 
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index ce503c99f5c4..72a94401f9e0 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -12,6 +12,7 @@
  */
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/dmar.h>
 #include <linux/hpet.h>
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 35aaee4fc028..9f148e3d45b4 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -11,6 +11,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/compiler.h>
@@ -218,7 +219,8 @@ static int reserve_irq_vector(struct irq_data *irqd)
 	return 0;
 }
 
-static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest)
+static int
+assign_vector_locked(struct irq_data *irqd, const struct cpumask *dest)
 {
 	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	bool resvd = apicd->has_reserved;
@@ -245,22 +247,12 @@ static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest)
 		return -EBUSY;
 
 	vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu);
-	if (vector > 0)
-		apic_update_vector(irqd, vector, cpu);
 	trace_vector_alloc(irqd->irq, vector, resvd, vector);
-	return vector;
-}
-
-static int assign_vector_locked(struct irq_data *irqd,
-				const struct cpumask *dest)
-{
-	struct apic_chip_data *apicd = apic_chip_data(irqd);
-	int vector = allocate_vector(irqd, dest);
-
 	if (vector < 0)
 		return vector;
+	apic_update_vector(irqd, vector, cpu);
+	apic_update_irq_cfg(irqd, vector, cpu);
 
-	apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu);
 	return 0;
 }
 
@@ -433,7 +425,7 @@ static int activate_managed(struct irq_data *irqd)
 		pr_err("Managed startup irq %u, no vector available\n",
 		       irqd->irq);
 	}
-       return ret;
+	return ret;
 }
 
 static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d492752f79e1..391f358ebb4c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -394,10 +394,10 @@ extern int uv_hub_info_version(void)
 EXPORT_SYMBOL(uv_hub_info_version);
 
 /* Default UV memory block size is 2GB */
-static unsigned long mem_block_size = (2UL << 30);
+static unsigned long mem_block_size __initdata = (2UL << 30);
 
 /* Kernel parameter to specify UV mem block size */
-static int parse_mem_block_size(char *ptr)
+static int __init parse_mem_block_size(char *ptr)
 {
 	unsigned long size = memparse(ptr, NULL);
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5d0de79fdab0..ec00d1ff5098 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -240,6 +240,7 @@
 #include <asm/olpc.h>
 #include <asm/paravirt.h>
 #include <asm/reboot.h>
+#include <asm/nospec-branch.h>
 
 #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
 extern int (*console_blank_hook)(int);
@@ -614,11 +615,13 @@ static long __apm_bios_call(void *_call)
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
+	firmware_restrict_branch_speculation_start();
 	APM_DO_SAVE_SEGS;
 	apm_bios_call_asm(call->func, call->ebx, call->ecx,
 			  &call->eax, &call->ebx, &call->ecx, &call->edx,
 			  &call->esi);
 	APM_DO_RESTORE_SEGS;
+	firmware_restrict_branch_speculation_end();
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
@@ -690,10 +693,12 @@ static long __apm_bios_call_simple(void *_call)
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
+	firmware_restrict_branch_speculation_start();
 	APM_DO_SAVE_SEGS;
 	error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx,
 					 &call->eax);
 	APM_DO_RESTORE_SEGS;
+	firmware_restrict_branch_speculation_end();
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index dcb008c320fe..01de31db300d 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -103,4 +103,9 @@ void common(void) {
 	OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
 	OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
 	DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
+	DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1)));
+
+	/* Offset for sp0 and sp1 into the tss_struct */
+	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
+	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 }
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index a4a3be399f4b..82826f2275cc 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -46,8 +46,14 @@ void foo(void)
 	OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
 	BLANK();
 
-	/* Offset from the sysenter stack to tss.sp0 */
-	DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+	/*
+	 * Offset from the entry stack to task stack stored in TSS. Kernel entry
+	 * happens on the per-cpu entry-stack, and the asm code switches to the
+	 * task-stack pointer stored in x86_tss.sp1, which is a copy of
+	 * task->thread.sp0 where entry code can find it.
+	 */
+	DEFINE(TSS_entry2task_stack,
+	       offsetof(struct cpu_entry_area, tss.x86_tss.sp1) -
 	       offsetofend(struct cpu_entry_area, entry_stack_page.stack));
 
 #ifdef CONFIG_STACKPROTECTOR
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index b2dcd161f514..3b9405e7ba2b 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -65,8 +65,6 @@ int main(void)
 #undef ENTRY
 
 	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
-	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
-	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	BLANK();
 
 #ifdef CONFIG_STACKPROTECTOR
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 7a40196967cb..347137e80bf5 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -35,7 +35,9 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o
+obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o
+obj-$(CONFIG_INTEL_RDT)	+= intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o
+CFLAGS_intel_rdt_pseudo_lock.o = -I$(src)
 
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 082d7875cef8..22ab408177b2 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -232,8 +232,6 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
 		}
 	}
 
-	set_cpu_cap(c, X86_FEATURE_K7);
-
 	/* calling is from identify_secondary_cpu() ? */
 	if (!c->cpu_index)
 		return;
@@ -315,6 +313,13 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
 	c->cpu_core_id %= cus_per_node;
 }
 
+
+static void amd_get_topology_early(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_TOPOEXT))
+		smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
+}
+
 /*
  * Fixup core topology information for
  * (1) AMD multi-node processors
@@ -334,7 +339,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
 
 		node_id  = ecx & 0xff;
-		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
 
 		if (c->x86 == 0x15)
 			c->cu_id = ebx & 0xff;
@@ -543,7 +547,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		nodes_per_socket = ((value >> 3) & 7) + 1;
 	}
 
-	if (c->x86 >= 0x15 && c->x86 <= 0x17) {
+	if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
+	    !boot_cpu_has(X86_FEATURE_VIRT_SSBD) &&
+	    c->x86 >= 0x15 && c->x86 <= 0x17) {
 		unsigned int bit;
 
 		switch (c->x86) {
@@ -611,10 +617,19 @@ clear_sev:
 
 static void early_init_amd(struct cpuinfo_x86 *c)
 {
+	u64 value;
 	u32 dummy;
 
 	early_init_amd_mc(c);
 
+#ifdef CONFIG_X86_32
+	if (c->x86 == 6)
+		set_cpu_cap(c, X86_FEATURE_K7);
+#endif
+
+	if (c->x86 >= 0xf)
+		set_cpu_cap(c, X86_FEATURE_K8);
+
 	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
 
 	/*
@@ -681,6 +696,22 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_AMD_E400);
 
 	early_detect_mem_encrypt(c);
+
+	/* Re-enable TopologyExtensions if switched off by BIOS */
+	if (c->x86 == 0x15 &&
+	    (c->x86_model >= 0x10 && c->x86_model <= 0x6f) &&
+	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+
+		if (msr_set_bit(0xc0011005, 54) > 0) {
+			rdmsrl(0xc0011005, value);
+			if (value & BIT_64(54)) {
+				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+				pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
+			}
+		}
+	}
+
+	amd_get_topology_early(c);
 }
 
 static void init_amd_k8(struct cpuinfo_x86 *c)
@@ -772,19 +803,6 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 {
 	u64 value;
 
-	/* re-enable TopologyExtensions if switched off by BIOS */
-	if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) &&
-	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
-
-		if (msr_set_bit(0xc0011005, 54) > 0) {
-			rdmsrl(0xc0011005, value);
-			if (value & BIT_64(54)) {
-				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
-				pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
-			}
-		}
-	}
-
 	/*
 	 * The way access filter has a performance penalty on some workloads.
 	 * Disable it on the affected CPUs.
@@ -848,22 +866,12 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	cpu_detect_cache_sizes(c);
 
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level >= 0x80000008) {
-		amd_detect_cmp(c);
-		amd_get_topology(c);
-		srat_detect_node(c);
-	}
-
-#ifdef CONFIG_X86_32
-	detect_ht(c);
-#endif
+	amd_detect_cmp(c);
+	amd_get_topology(c);
+	srat_detect_node(c);
 
 	init_amd_cacheinfo(c);
 
-	if (c->x86 >= 0xf)
-		set_cpu_cap(c, X86_FEATURE_K8);
-
 	if (cpu_has(c, X86_FEATURE_XMM2)) {
 		unsigned long long val;
 		int ret;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 404df26b7de8..cb4a16292aa7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -22,15 +22,18 @@
 #include <asm/processor-flags.h>
 #include <asm/fpu/internal.h>
 #include <asm/msr.h>
+#include <asm/vmx.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
 #include <asm/intel-family.h>
+#include <asm/e820/api.h>
 #include <asm/hypervisor.h>
 
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
+static void __init l1tf_select_mitigation(void);
 
 /*
  * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
@@ -56,6 +59,12 @@ void __init check_bugs(void)
 {
 	identify_boot_cpu();
 
+	/*
+	 * identify_boot_cpu() initialized SMT support information, let the
+	 * core code know.
+	 */
+	cpu_smt_check_topology_early();
+
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
 		print_cpu_info(&boot_cpu_data);
@@ -82,6 +91,8 @@ void __init check_bugs(void)
 	 */
 	ssb_select_mitigation();
 
+	l1tf_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -130,6 +141,7 @@ static const char *spectre_v2_strings[] = {
 	[SPECTRE_V2_RETPOLINE_MINIMAL_AMD]	= "Vulnerable: Minimal AMD ASM retpoline",
 	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
 	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
+	[SPECTRE_V2_IBRS_ENHANCED]		= "Mitigation: Enhanced IBRS",
 };
 
 #undef pr_fmt
@@ -155,7 +167,8 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 		guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
 
 		/* SSBD controlled in MSR_SPEC_CTRL */
-		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
+		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+		    static_cpu_has(X86_FEATURE_AMD_SSBD))
 			hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
 
 		if (hostval != guestval) {
@@ -312,23 +325,6 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	return cmd;
 }
 
-/* Check for Skylake-like CPUs (for RSB handling) */
-static bool __init is_skylake_era(void)
-{
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6) {
-		switch (boot_cpu_data.x86_model) {
-		case INTEL_FAM6_SKYLAKE_MOBILE:
-		case INTEL_FAM6_SKYLAKE_DESKTOP:
-		case INTEL_FAM6_SKYLAKE_X:
-		case INTEL_FAM6_KABYLAKE_MOBILE:
-		case INTEL_FAM6_KABYLAKE_DESKTOP:
-			return true;
-		}
-	}
-	return false;
-}
-
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -348,6 +344,13 @@ static void __init spectre_v2_select_mitigation(void)
 
 	case SPECTRE_V2_CMD_FORCE:
 	case SPECTRE_V2_CMD_AUTO:
+		if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
+			mode = SPECTRE_V2_IBRS_ENHANCED;
+			/* Force it so VMEXIT will restore correctly */
+			x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
+			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+			goto specv2_set_mode;
+		}
 		if (IS_ENABLED(CONFIG_RETPOLINE))
 			goto retpoline_auto;
 		break;
@@ -385,26 +388,20 @@ retpoline_auto:
 		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
 	}
 
+specv2_set_mode:
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If neither SMEP nor PTI are available, there is a risk of
-	 * hitting userspace addresses in the RSB after a context switch
-	 * from a shallow call stack to a deeper one. To prevent this fill
-	 * the entire RSB, even when using IBRS.
+	 * If spectre v2 protection has been enabled, unconditionally fill
+	 * RSB during a context switch; this protects against two independent
+	 * issues:
 	 *
-	 * Skylake era CPUs have a separate issue with *underflow* of the
-	 * RSB, when they will predict 'ret' targets from the generic BTB.
-	 * The proper mitigation for this is IBRS. If IBRS is not supported
-	 * or deactivated in favour of retpolines the RSB fill on context
-	 * switch is required.
+	 *	- RSB underflow (and switch to BTB) on Skylake+
+	 *	- SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
 	 */
-	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
-	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
-		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-		pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
-	}
+	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
@@ -414,9 +411,16 @@ retpoline_auto:
 
 	/*
 	 * Retpoline means the kernel is safe because it has no indirect
-	 * branches. But firmware isn't, so use IBRS to protect that.
+	 * branches. Enhanced IBRS protects firmware too, so, enable restricted
+	 * speculation around firmware calls only when Enhanced IBRS isn't
+	 * supported.
+	 *
+	 * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
+	 * the user might select retpoline on the kernel command line and if
+	 * the CPU supports Enhanced IBRS, kernel might un-intentionally not
+	 * enable IBRS around firmware calls.
 	 */
-	if (boot_cpu_has(X86_FEATURE_IBRS)) {
+	if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
@@ -533,9 +537,10 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 		 * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may
 		 * use a completely different MSR and bit dependent on family.
 		 */
-		if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+		if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) &&
+		    !static_cpu_has(X86_FEATURE_AMD_SSBD)) {
 			x86_amd_ssb_disable();
-		else {
+		} else {
 			x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
 			x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
 			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
@@ -652,8 +657,120 @@ void x86_spec_ctrl_setup_ap(void)
 		x86_amd_ssb_disable();
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"L1TF: " fmt
+
+/* Default mitigation for L1TF-affected CPUs */
+enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH;
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+EXPORT_SYMBOL_GPL(l1tf_mitigation);
+#endif
+enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
+EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
+
+static void __init l1tf_select_mitigation(void)
+{
+	u64 half_pa;
+
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return;
+
+	switch (l1tf_mitigation) {
+	case L1TF_MITIGATION_OFF:
+	case L1TF_MITIGATION_FLUSH_NOWARN:
+	case L1TF_MITIGATION_FLUSH:
+		break;
+	case L1TF_MITIGATION_FLUSH_NOSMT:
+	case L1TF_MITIGATION_FULL:
+		cpu_smt_disable(false);
+		break;
+	case L1TF_MITIGATION_FULL_FORCE:
+		cpu_smt_disable(true);
+		break;
+	}
+
+#if CONFIG_PGTABLE_LEVELS == 2
+	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
+	return;
+#endif
+
+	/*
+	 * This is extremely unlikely to happen because almost all
+	 * systems have far more MAX_PA/2 than RAM can be fit into
+	 * DIMM slots.
+	 */
+	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
+	if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
+		pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
+		return;
+	}
+
+	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
+}
+
+static int __init l1tf_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		l1tf_mitigation = L1TF_MITIGATION_OFF;
+	else if (!strcmp(str, "flush,nowarn"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOWARN;
+	else if (!strcmp(str, "flush"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH;
+	else if (!strcmp(str, "flush,nosmt"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+	else if (!strcmp(str, "full"))
+		l1tf_mitigation = L1TF_MITIGATION_FULL;
+	else if (!strcmp(str, "full,force"))
+		l1tf_mitigation = L1TF_MITIGATION_FULL_FORCE;
+
+	return 0;
+}
+early_param("l1tf", l1tf_cmdline);
+
+#undef pr_fmt
+
 #ifdef CONFIG_SYSFS
 
+#define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion"
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+static const char *l1tf_vmx_states[] = {
+	[VMENTER_L1D_FLUSH_AUTO]		= "auto",
+	[VMENTER_L1D_FLUSH_NEVER]		= "vulnerable",
+	[VMENTER_L1D_FLUSH_COND]		= "conditional cache flushes",
+	[VMENTER_L1D_FLUSH_ALWAYS]		= "cache flushes",
+	[VMENTER_L1D_FLUSH_EPT_DISABLED]	= "EPT disabled",
+	[VMENTER_L1D_FLUSH_NOT_REQUIRED]	= "flush not necessary"
+};
+
+static ssize_t l1tf_show_state(char *buf)
+{
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO)
+		return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
+
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED ||
+	    (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER &&
+	     cpu_smt_control == CPU_SMT_ENABLED))
+		return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG,
+			       l1tf_vmx_states[l1tf_vmx_mitigation]);
+
+	return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG,
+		       l1tf_vmx_states[l1tf_vmx_mitigation],
+		       cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled");
+}
+#else
+static ssize_t l1tf_show_state(char *buf)
+{
+	return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
+}
+#endif
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -682,6 +799,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_SPEC_STORE_BYPASS:
 		return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
 
+	case X86_BUG_L1TF:
+		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
+			return l1tf_show_state(buf);
+		break;
 	default:
 		break;
 	}
@@ -708,4 +829,9 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
 }
+
+ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index eb4cb3efd20e..84dee5ab745a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -661,33 +661,36 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
 }
 
-void detect_ht(struct cpuinfo_x86 *c)
+int detect_ht_early(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
-	int index_msb, core_bits;
-	static bool printed;
 
 	if (!cpu_has(c, X86_FEATURE_HT))
-		return;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		goto out;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
-		return;
+		return -1;
 
 	cpuid(1, &eax, &ebx, &ecx, &edx);
 
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
-
-	if (smp_num_siblings == 1) {
+	if (smp_num_siblings == 1)
 		pr_info_once("CPU0: Hyper-Threading is disabled\n");
-		goto out;
-	}
+#endif
+	return 0;
+}
 
-	if (smp_num_siblings <= 1)
-		goto out;
+void detect_ht(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	int index_msb, core_bits;
+
+	if (detect_ht_early(c) < 0)
+		return;
 
 	index_msb = get_count_order(smp_num_siblings);
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
@@ -700,15 +703,6 @@ void detect_ht(struct cpuinfo_x86 *c)
 
 	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
 				       ((1 << core_bits) - 1);
-
-out:
-	if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) {
-		pr_info("CPU: Physical Processor ID: %d\n",
-			c->phys_proc_id);
-		pr_info("CPU: Processor Core ID: %d\n",
-			c->cpu_core_id);
-		printed = 1;
-	}
 #endif
 }
 
@@ -911,7 +905,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	apply_forced_caps(c);
 }
 
-static void get_cpu_address_sizes(struct cpuinfo_x86 *c)
+void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
 
@@ -987,6 +981,21 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
 	{}
 };
 
+static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
+	/* in addition to cpu_no_speculation */
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MOOREFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_DENVERTON	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GEMINI_LAKE	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
+	{}
+};
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
@@ -1005,6 +1014,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
+	if (ia32_cap & ARCH_CAP_IBRS_ALL)
+		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
+
 	if (x86_match_cpu(cpu_no_meltdown))
 		return;
 
@@ -1013,6 +1025,29 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 		return;
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+
+	if (x86_match_cpu(cpu_no_l1tf))
+		return;
+
+	setup_force_cpu_bug(X86_BUG_L1TF);
+}
+
+/*
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
+ * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
+ */
+static void detect_nopl(void)
+{
+#ifdef CONFIG_X86_32
+	setup_clear_cpu_cap(X86_FEATURE_NOPL);
+#else
+	setup_force_cpu_cap(X86_FEATURE_NOPL);
+#endif
 }
 
 /*
@@ -1089,6 +1124,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	if (!pgtable_l5_enabled())
 		setup_clear_cpu_cap(X86_FEATURE_LA57);
+
+	detect_nopl();
 }
 
 void __init early_cpu_init(void)
@@ -1124,24 +1161,6 @@ void __init early_cpu_init(void)
 	early_identify_cpu(&boot_cpu_data);
 }
 
-/*
- * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
- * unfortunately, that's not true in practice because of early VIA
- * chips and (more importantly) broken virtualizers that are not easy
- * to detect. In the latter case it doesn't even *fail* reliably, so
- * probing for it doesn't even work. Disable it completely on 32-bit
- * unless we can find a reliable way to detect all the broken cases.
- * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
- */
-static void detect_nopl(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_X86_32
-	clear_cpu_cap(c, X86_FEATURE_NOPL);
-#else
-	set_cpu_cap(c, X86_FEATURE_NOPL);
-#endif
-}
-
 static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_64
@@ -1204,8 +1223,6 @@ static void generic_identify(struct cpuinfo_x86 *c)
 
 	get_model_name(c); /* Default name */
 
-	detect_nopl(c);
-
 	detect_null_seg_behavior(c);
 
 	/*
@@ -1804,11 +1821,12 @@ void cpu_init(void)
 	enter_lazy_tlb(&init_mm, curr);
 
 	/*
-	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
-	 * task never enters user mode.
+	 * Initialize the TSS.  sp0 points to the entry trampoline stack
+	 * regardless of what task is running.
 	 */
 	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
+	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
 
 	load_mm_ldt(&init_mm);
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 38216f678fc3..7b229afa0a37 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -46,6 +46,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
 			    *const __x86_cpu_dev_end[];
 
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
+extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
 extern u32 get_scattered_cpuid_leaf(unsigned int level,
@@ -55,7 +56,9 @@ extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 
 extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
+extern int detect_extended_topology_early(struct cpuinfo_x86 *c);
 extern int detect_extended_topology(struct cpuinfo_x86 *c);
+extern int detect_ht_early(struct cpuinfo_x86 *c);
 extern void detect_ht(struct cpuinfo_x86 *c);
 
 unsigned int aperfmperf_get_khz(int cpu);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index eb75564f2d25..401e8c133108 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -301,6 +301,13 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	}
 
 	check_mpx_erratum(c);
+
+	/*
+	 * Get the number of SMT siblings early from the extended topology
+	 * leaf, if available. Otherwise try the legacy SMT detection.
+	 */
+	if (detect_extended_topology_early(c) < 0)
+		detect_ht_early(c);
 }
 
 #ifdef CONFIG_X86_32
@@ -465,14 +472,17 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
 #define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC	0x00000001
 #define X86_VMX_FEATURE_PROC_CTLS2_EPT		0x00000002
 #define X86_VMX_FEATURE_PROC_CTLS2_VPID		0x00000020
+#define x86_VMX_FEATURE_EPT_CAP_AD		0x00200000
 
 	u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+	u32 msr_vpid_cap, msr_ept_cap;
 
 	clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
 	clear_cpu_cap(c, X86_FEATURE_VNMI);
 	clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
 	clear_cpu_cap(c, X86_FEATURE_EPT);
 	clear_cpu_cap(c, X86_FEATURE_VPID);
+	clear_cpu_cap(c, X86_FEATURE_EPT_AD);
 
 	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
 	msr_ctl = vmx_msr_high | vmx_msr_low;
@@ -487,8 +497,13 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
 		if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
 		    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
 			set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
-		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) {
 			set_cpu_cap(c, X86_FEATURE_EPT);
+			rdmsr(MSR_IA32_VMX_EPT_VPID_CAP,
+			      msr_ept_cap, msr_vpid_cap);
+			if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD)
+				set_cpu_cap(c, X86_FEATURE_EPT_AD);
+		}
 		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
 			set_cpu_cap(c, X86_FEATURE_VPID);
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index ec4754f81cbd..abb71ac70443 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -859,6 +859,8 @@ static __init bool get_rdt_resources(void)
 	return (rdt_mon_capable || rdt_alloc_capable);
 }
 
+static enum cpuhp_state rdt_online;
+
 static int __init intel_rdt_late_init(void)
 {
 	struct rdt_resource *r;
@@ -880,6 +882,7 @@ static int __init intel_rdt_late_init(void)
 		cpuhp_remove_state(state);
 		return ret;
 	}
+	rdt_online = state;
 
 	for_each_alloc_capable_rdt_resource(r)
 		pr_info("Intel RDT %s allocation detected\n", r->name);
@@ -891,3 +894,11 @@ static int __init intel_rdt_late_init(void)
 }
 
 late_initcall(intel_rdt_late_init);
+
+static void __exit intel_rdt_exit(void)
+{
+	cpuhp_remove_state(rdt_online);
+	rdtgroup_exit();
+}
+
+__exitcall(intel_rdt_exit);
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 39752825e376..4e588f36228f 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -81,6 +81,34 @@ enum rdt_group_type {
 };
 
 /**
+ * enum rdtgrp_mode - Mode of a RDT resource group
+ * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
+ * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed
+ * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking
+ * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations
+ *                          allowed AND the allocations are Cache Pseudo-Locked
+ *
+ * The mode of a resource group enables control over the allowed overlap
+ * between allocations associated with different resource groups (classes
+ * of service). User is able to modify the mode of a resource group by
+ * writing to the "mode" resctrl file associated with the resource group.
+ *
+ * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by
+ * writing the appropriate text to the "mode" file. A resource group enters
+ * "pseudo-locked" mode after the schemata is written while the resource
+ * group is in "pseudo-locksetup" mode.
+ */
+enum rdtgrp_mode {
+	RDT_MODE_SHAREABLE = 0,
+	RDT_MODE_EXCLUSIVE,
+	RDT_MODE_PSEUDO_LOCKSETUP,
+	RDT_MODE_PSEUDO_LOCKED,
+
+	/* Must be last */
+	RDT_NUM_MODES,
+};
+
+/**
  * struct mongroup - store mon group's data in resctrl fs.
  * @mon_data_kn		kernlfs node for the mon_data directory
  * @parent:			parent rdtgrp
@@ -95,6 +123,43 @@ struct mongroup {
 };
 
 /**
+ * struct pseudo_lock_region - pseudo-lock region information
+ * @r:			RDT resource to which this pseudo-locked region
+ *			belongs
+ * @d:			RDT domain to which this pseudo-locked region
+ *			belongs
+ * @cbm:		bitmask of the pseudo-locked region
+ * @lock_thread_wq:	waitqueue used to wait on the pseudo-locking thread
+ *			completion
+ * @thread_done:	variable used by waitqueue to test if pseudo-locking
+ *			thread completed
+ * @cpu:		core associated with the cache on which the setup code
+ *			will be run
+ * @line_size:		size of the cache lines
+ * @size:		size of pseudo-locked region in bytes
+ * @kmem:		the kernel memory associated with pseudo-locked region
+ * @minor:		minor number of character device associated with this
+ *			region
+ * @debugfs_dir:	pointer to this region's directory in the debugfs
+ *			filesystem
+ * @pm_reqs:		Power management QoS requests related to this region
+ */
+struct pseudo_lock_region {
+	struct rdt_resource	*r;
+	struct rdt_domain	*d;
+	u32			cbm;
+	wait_queue_head_t	lock_thread_wq;
+	int			thread_done;
+	int			cpu;
+	unsigned int		line_size;
+	unsigned int		size;
+	void			*kmem;
+	unsigned int		minor;
+	struct dentry		*debugfs_dir;
+	struct list_head	pm_reqs;
+};
+
+/**
  * struct rdtgroup - store rdtgroup's data in resctrl file system.
  * @kn:				kernfs node
  * @rdtgroup_list:		linked list for all rdtgroups
@@ -106,16 +171,20 @@ struct mongroup {
  * @type:			indicates type of this rdtgroup - either
  *				monitor only or ctrl_mon group
  * @mon:			mongroup related data
+ * @mode:			mode of resource group
+ * @plr:			pseudo-locked region
  */
 struct rdtgroup {
-	struct kernfs_node	*kn;
-	struct list_head	rdtgroup_list;
-	u32			closid;
-	struct cpumask		cpu_mask;
-	int			flags;
-	atomic_t		waitcount;
-	enum rdt_group_type	type;
-	struct mongroup		mon;
+	struct kernfs_node		*kn;
+	struct list_head		rdtgroup_list;
+	u32				closid;
+	struct cpumask			cpu_mask;
+	int				flags;
+	atomic_t			waitcount;
+	enum rdt_group_type		type;
+	struct mongroup			mon;
+	enum rdtgrp_mode		mode;
+	struct pseudo_lock_region	*plr;
 };
 
 /* rdtgroup.flags */
@@ -148,6 +217,7 @@ extern struct list_head rdt_all_groups;
 extern int max_name_width, max_data_width;
 
 int __init rdtgroup_init(void);
+void __exit rdtgroup_exit(void);
 
 /**
  * struct rftype - describe each file in the resctrl file system
@@ -216,22 +286,24 @@ struct mbm_state {
  * @mbps_val:	When mba_sc is enabled, this holds the bandwidth in MBps
  * @new_ctrl:	new ctrl value to be loaded
  * @have_new_ctrl: did user provide new_ctrl for this domain
+ * @plr:	pseudo-locked region (if any) associated with domain
  */
 struct rdt_domain {
-	struct list_head	list;
-	int			id;
-	struct cpumask		cpu_mask;
-	unsigned long		*rmid_busy_llc;
-	struct mbm_state	*mbm_total;
-	struct mbm_state	*mbm_local;
-	struct delayed_work	mbm_over;
-	struct delayed_work	cqm_limbo;
-	int			mbm_work_cpu;
-	int			cqm_work_cpu;
-	u32			*ctrl_val;
-	u32			*mbps_val;
-	u32			new_ctrl;
-	bool			have_new_ctrl;
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+	unsigned long			*rmid_busy_llc;
+	struct mbm_state		*mbm_total;
+	struct mbm_state		*mbm_local;
+	struct delayed_work		mbm_over;
+	struct delayed_work		cqm_limbo;
+	int				mbm_work_cpu;
+	int				cqm_work_cpu;
+	u32				*ctrl_val;
+	u32				*mbps_val;
+	u32				new_ctrl;
+	bool				have_new_ctrl;
+	struct pseudo_lock_region	*plr;
 };
 
 /**
@@ -351,7 +423,7 @@ struct rdt_resource {
 	struct rdt_cache	cache;
 	struct rdt_membw	membw;
 	const char		*format_str;
-	int (*parse_ctrlval)	(char *buf, struct rdt_resource *r,
+	int (*parse_ctrlval)	(void *data, struct rdt_resource *r,
 				 struct rdt_domain *d);
 	struct list_head	evt_list;
 	int			num_rmid;
@@ -359,8 +431,8 @@ struct rdt_resource {
 	unsigned long		fflags;
 };
 
-int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d);
-int parse_bw(char *buf, struct rdt_resource *r,  struct rdt_domain *d);
+int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d);
+int parse_bw(void *_buf, struct rdt_resource *r,  struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
@@ -368,7 +440,7 @@ extern struct rdt_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
-int __init rdtgroup_init(void);
+extern struct dentry *debugfs_resctrl;
 
 enum {
 	RDT_RESOURCE_L3,
@@ -439,13 +511,32 @@ void rdt_last_cmd_printf(const char *fmt, ...);
 void rdt_ctrl_update(void *arg);
 struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
 void rdtgroup_kn_unlock(struct kernfs_node *kn);
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+			     umode_t mask);
 struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 				   struct list_head **pos);
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+			   u32 _cbm, int closid, bool exclusive);
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
+				  u32 cbm);
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
+int rdtgroup_tasks_assigned(struct rdtgroup *r);
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm);
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
+int rdt_pseudo_lock_init(void);
+void rdt_pseudo_lock_release(void);
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
+int update_domains(struct rdt_resource *r, int closid);
+void closid_free(int closid);
 int alloc_rmid(void);
 void free_rmid(u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 116d57b248d3..af358ca05160 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -64,9 +64,10 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	return true;
 }
 
-int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d)
 {
 	unsigned long data;
+	char *buf = _buf;
 
 	if (d->have_new_ctrl) {
 		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
@@ -87,7 +88,7 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
  */
-static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
 	unsigned long first_bit, zero_bit, val;
 	unsigned int cbm_len = r->cache.cbm_len;
@@ -122,22 +123,64 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	return true;
 }
 
+struct rdt_cbm_parse_data {
+	struct rdtgroup		*rdtgrp;
+	char			*buf;
+};
+
 /*
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
-int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
 {
-	unsigned long data;
+	struct rdt_cbm_parse_data *data = _data;
+	struct rdtgroup *rdtgrp = data->rdtgrp;
+	u32 cbm_val;
 
 	if (d->have_new_ctrl) {
 		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
 		return -EINVAL;
 	}
 
-	if(!cbm_validate(buf, &data, r))
+	/*
+	 * Cannot set up more than one pseudo-locked region in a cache
+	 * hierarchy.
+	 */
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
+		rdt_last_cmd_printf("pseudo-locked region in hierarchy\n");
 		return -EINVAL;
-	d->new_ctrl = data;
+	}
+
+	if (!cbm_validate(data->buf, &cbm_val, r))
+		return -EINVAL;
+
+	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
+	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
+		rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * The CBM may not overlap with the CBM of another closid if
+	 * either is exclusive.
+	 */
+	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) {
+		rdt_last_cmd_printf("overlaps with exclusive group\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) {
+		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			rdt_last_cmd_printf("overlaps with other group\n");
+			return -EINVAL;
+		}
+	}
+
+	d->new_ctrl = cbm_val;
 	d->have_new_ctrl = true;
 
 	return 0;
@@ -149,8 +192,10 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
  * separated by ";". The "id" is in decimal, and must match one of
  * the "id"s for this resource.
  */
-static int parse_line(char *line, struct rdt_resource *r)
+static int parse_line(char *line, struct rdt_resource *r,
+		      struct rdtgroup *rdtgrp)
 {
+	struct rdt_cbm_parse_data data;
 	char *dom = NULL, *id;
 	struct rdt_domain *d;
 	unsigned long dom_id;
@@ -167,15 +212,32 @@ next:
 	dom = strim(dom);
 	list_for_each_entry(d, &r->domains, list) {
 		if (d->id == dom_id) {
-			if (r->parse_ctrlval(dom, r, d))
+			data.buf = dom;
+			data.rdtgrp = rdtgrp;
+			if (r->parse_ctrlval(&data, r, d))
 				return -EINVAL;
+			if (rdtgrp->mode ==  RDT_MODE_PSEUDO_LOCKSETUP) {
+				/*
+				 * In pseudo-locking setup mode and just
+				 * parsed a valid CBM that should be
+				 * pseudo-locked. Only one locked region per
+				 * resource group and domain so just do
+				 * the required initialization for single
+				 * region and return.
+				 */
+				rdtgrp->plr->r = r;
+				rdtgrp->plr->d = d;
+				rdtgrp->plr->cbm = d->new_ctrl;
+				d->plr = rdtgrp->plr;
+				return 0;
+			}
 			goto next;
 		}
 	}
 	return -EINVAL;
 }
 
-static int update_domains(struct rdt_resource *r, int closid)
+int update_domains(struct rdt_resource *r, int closid)
 {
 	struct msr_param msr_param;
 	cpumask_var_t cpu_mask;
@@ -220,13 +282,14 @@ done:
 	return 0;
 }
 
-static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
+static int rdtgroup_parse_resource(char *resname, char *tok,
+				   struct rdtgroup *rdtgrp)
 {
 	struct rdt_resource *r;
 
 	for_each_alloc_enabled_rdt_resource(r) {
-		if (!strcmp(resname, r->name) && closid < r->num_closid)
-			return parse_line(tok, r);
+		if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid)
+			return parse_line(tok, r, rdtgrp);
 	}
 	rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname);
 	return -EINVAL;
@@ -239,7 +302,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	struct rdt_domain *dom;
 	struct rdt_resource *r;
 	char *tok, *resname;
-	int closid, ret = 0;
+	int ret = 0;
 
 	/* Valid input requires a trailing newline */
 	if (nbytes == 0 || buf[nbytes - 1] != '\n')
@@ -253,7 +316,15 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	}
 	rdt_last_cmd_clear();
 
-	closid = rdtgrp->closid;
+	/*
+	 * No changes to pseudo-locked region allowed. It has to be removed
+	 * and re-created instead.
+	 */
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("resource group is pseudo-locked\n");
+		goto out;
+	}
 
 	for_each_alloc_enabled_rdt_resource(r) {
 		list_for_each_entry(dom, &r->domains, list)
@@ -272,17 +343,27 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 			ret = -EINVAL;
 			goto out;
 		}
-		ret = rdtgroup_parse_resource(resname, tok, closid);
+		ret = rdtgroup_parse_resource(resname, tok, rdtgrp);
 		if (ret)
 			goto out;
 	}
 
 	for_each_alloc_enabled_rdt_resource(r) {
-		ret = update_domains(r, closid);
+		ret = update_domains(r, rdtgrp->closid);
 		if (ret)
 			goto out;
 	}
 
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		/*
+		 * If pseudo-locking fails we keep the resource group in
+		 * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service
+		 * active and updated for just the domain the pseudo-locked
+		 * region was requested for.
+		 */
+		ret = rdtgroup_pseudo_lock_create(rdtgrp);
+	}
+
 out:
 	rdtgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
@@ -318,10 +399,18 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (rdtgrp) {
-		closid = rdtgrp->closid;
-		for_each_alloc_enabled_rdt_resource(r) {
-			if (closid < r->num_closid)
-				show_doms(s, r, closid);
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			for_each_alloc_enabled_rdt_resource(r)
+				seq_printf(s, "%s:uninitialized\n", r->name);
+		} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name,
+				   rdtgrp->plr->d->id, rdtgrp->plr->cbm);
+		} else {
+			closid = rdtgrp->closid;
+			for_each_alloc_enabled_rdt_resource(r) {
+				if (closid < r->num_closid)
+					show_doms(s, r, closid);
+			}
 		}
 	} else {
 		ret = -ENOENT;
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
new file mode 100644
index 000000000000..40f3903ae5d9
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -0,0 +1,1522 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Resource Director Technology (RDT)
+ *
+ * Pseudo-locking support built on top of Cache Allocation Technology (CAT)
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Author: Reinette Chatre <reinette.chatre@intel.com>
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/cacheinfo.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/debugfs.h>
+#include <linux/kthread.h>
+#include <linux/mman.h>
+#include <linux/pm_qos.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/intel-family.h>
+#include <asm/intel_rdt_sched.h>
+#include <asm/perf_event.h>
+
+#include "intel_rdt.h"
+
+#define CREATE_TRACE_POINTS
+#include "intel_rdt_pseudo_lock_event.h"
+
+/*
+ * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware
+ * prefetcher state. Details about this register can be found in the MSR
+ * tables for specific platforms found in Intel's SDM.
+ */
+#define MSR_MISC_FEATURE_CONTROL	0x000001a4
+
+/*
+ * The bits needed to disable hardware prefetching varies based on the
+ * platform. During initialization we will discover which bits to use.
+ */
+static u64 prefetch_disable_bits;
+
+/*
+ * Major number assigned to and shared by all devices exposing
+ * pseudo-locked regions.
+ */
+static unsigned int pseudo_lock_major;
+static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
+static struct class *pseudo_lock_class;
+
+/**
+ * get_prefetch_disable_bits - prefetch disable bits of supported platforms
+ *
+ * Capture the list of platforms that have been validated to support
+ * pseudo-locking. This includes testing to ensure pseudo-locked regions
+ * with low cache miss rates can be created under variety of load conditions
+ * as well as that these pseudo-locked regions can maintain their low cache
+ * miss rates under variety of load conditions for significant lengths of time.
+ *
+ * After a platform has been validated to support pseudo-locking its
+ * hardware prefetch disable bits are included here as they are documented
+ * in the SDM.
+ *
+ * When adding a platform here also add support for its cache events to
+ * measure_cycles_perf_fn()
+ *
+ * Return:
+ * If platform is supported, the bits to disable hardware prefetchers, 0
+ * if platform is not supported.
+ */
+static u64 get_prefetch_disable_bits(void)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+	    boot_cpu_data.x86 != 6)
+		return 0;
+
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_BROADWELL_X:
+		/*
+		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
+		 * as:
+		 * 0    L2 Hardware Prefetcher Disable (R/W)
+		 * 1    L2 Adjacent Cache Line Prefetcher Disable (R/W)
+		 * 2    DCU Hardware Prefetcher Disable (R/W)
+		 * 3    DCU IP Prefetcher Disable (R/W)
+		 * 63:4 Reserved
+		 */
+		return 0xF;
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+		/*
+		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
+		 * as:
+		 * 0     L2 Hardware Prefetcher Disable (R/W)
+		 * 1     Reserved
+		 * 2     DCU Hardware Prefetcher Disable (R/W)
+		 * 63:3  Reserved
+		 */
+		return 0x5;
+	}
+
+	return 0;
+}
+
+/*
+ * Helper to write 64bit value to MSR without tracing. Used when
+ * use of the cache should be restricted and use of registers used
+ * for local variables avoided.
+ */
+static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val)
+{
+	__wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
+}
+
+/**
+ * pseudo_lock_minor_get - Obtain available minor number
+ * @minor: Pointer to where new minor number will be stored
+ *
+ * A bitmask is used to track available minor numbers. Here the next free
+ * minor number is marked as unavailable and returned.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+static int pseudo_lock_minor_get(unsigned int *minor)
+{
+	unsigned long first_bit;
+
+	first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);
+
+	if (first_bit == MINORBITS)
+		return -ENOSPC;
+
+	__clear_bit(first_bit, &pseudo_lock_minor_avail);
+	*minor = first_bit;
+
+	return 0;
+}
+
+/**
+ * pseudo_lock_minor_release - Return minor number to available
+ * @minor: The minor number made available
+ */
+static void pseudo_lock_minor_release(unsigned int minor)
+{
+	__set_bit(minor, &pseudo_lock_minor_avail);
+}
+
+/**
+ * region_find_by_minor - Locate a pseudo-lock region by inode minor number
+ * @minor: The minor number of the device representing pseudo-locked region
+ *
+ * When the character device is accessed we need to determine which
+ * pseudo-locked region it belongs to. This is done by matching the minor
+ * number of the device to the pseudo-locked region it belongs.
+ *
+ * Minor numbers are assigned at the time a pseudo-locked region is associated
+ * with a cache instance.
+ *
+ * Return: On success return pointer to resource group owning the pseudo-locked
+ *         region, NULL on failure.
+ */
+static struct rdtgroup *region_find_by_minor(unsigned int minor)
+{
+	struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
+			rdtgrp_match = rdtgrp;
+			break;
+		}
+	}
+	return rdtgrp_match;
+}
+
+/**
+ * pseudo_lock_pm_req - A power management QoS request list entry
+ * @list:	Entry within the @pm_reqs list for a pseudo-locked region
+ * @req:	PM QoS request
+ */
+struct pseudo_lock_pm_req {
+	struct list_head list;
+	struct dev_pm_qos_request req;
+};
+
+static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
+{
+	struct pseudo_lock_pm_req *pm_req, *next;
+
+	list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
+		dev_pm_qos_remove_request(&pm_req->req);
+		list_del(&pm_req->list);
+		kfree(pm_req);
+	}
+}
+
+/**
+ * pseudo_lock_cstates_constrain - Restrict cores from entering C6
+ *
+ * To prevent the cache from being affected by power management entering
+ * C6 has to be avoided. This is accomplished by requesting a latency
+ * requirement lower than lowest C6 exit latency of all supported
+ * platforms as found in the cpuidle state tables in the intel_idle driver.
+ * At this time it is possible to do so with a single latency requirement
+ * for all supported platforms.
+ *
+ * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
+ * the ACPI latencies need to be considered while keeping in mind that C2
+ * may be set to map to deeper sleep states. In this case the latency
+ * requirement needs to prevent entering C2 also.
+ */
+static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
+{
+	struct pseudo_lock_pm_req *pm_req;
+	int cpu;
+	int ret;
+
+	for_each_cpu(cpu, &plr->d->cpu_mask) {
+		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
+		if (!pm_req) {
+			rdt_last_cmd_puts("fail allocating mem for PM QoS\n");
+			ret = -ENOMEM;
+			goto out_err;
+		}
+		ret = dev_pm_qos_add_request(get_cpu_device(cpu),
+					     &pm_req->req,
+					     DEV_PM_QOS_RESUME_LATENCY,
+					     30);
+		if (ret < 0) {
+			rdt_last_cmd_printf("fail to add latency req cpu%d\n",
+					    cpu);
+			kfree(pm_req);
+			ret = -1;
+			goto out_err;
+		}
+		list_add(&pm_req->list, &plr->pm_reqs);
+	}
+
+	return 0;
+
+out_err:
+	pseudo_lock_cstates_relax(plr);
+	return ret;
+}
+
+/**
+ * pseudo_lock_region_clear - Reset pseudo-lock region data
+ * @plr: pseudo-lock region
+ *
+ * All content of the pseudo-locked region is reset - any memory allocated
+ * freed.
+ *
+ * Return: void
+ */
+static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
+{
+	plr->size = 0;
+	plr->line_size = 0;
+	kfree(plr->kmem);
+	plr->kmem = NULL;
+	plr->r = NULL;
+	if (plr->d)
+		plr->d->plr = NULL;
+	plr->d = NULL;
+	plr->cbm = 0;
+	plr->debugfs_dir = NULL;
+}
+
+/**
+ * pseudo_lock_region_init - Initialize pseudo-lock region information
+ * @plr: pseudo-lock region
+ *
+ * Called after user provided a schemata to be pseudo-locked. From the
+ * schemata the &struct pseudo_lock_region is on entry already initialized
+ * with the resource, domain, and capacity bitmask. Here the information
+ * required for pseudo-locking is deduced from this data and &struct
+ * pseudo_lock_region initialized further. This information includes:
+ * - size in bytes of the region to be pseudo-locked
+ * - cache line size to know the stride with which data needs to be accessed
+ *   to be pseudo-locked
+ * - a cpu associated with the cache instance on which the pseudo-locking
+ *   flow can be executed
+ *
+ * Return: 0 on success, <0 on failure. Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
+{
+	struct cpu_cacheinfo *ci;
+	int ret;
+	int i;
+
+	/* Pick the first cpu we find that is associated with the cache. */
+	plr->cpu = cpumask_first(&plr->d->cpu_mask);
+
+	if (!cpu_online(plr->cpu)) {
+		rdt_last_cmd_printf("cpu %u associated with cache not online\n",
+				    plr->cpu);
+		ret = -ENODEV;
+		goto out_region;
+	}
+
+	ci = get_cpu_cacheinfo(plr->cpu);
+
+	plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm);
+
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == plr->r->cache_level) {
+			plr->line_size = ci->info_list[i].coherency_line_size;
+			return 0;
+		}
+	}
+
+	ret = -1;
+	rdt_last_cmd_puts("unable to determine cache line size\n");
+out_region:
+	pseudo_lock_region_clear(plr);
+	return ret;
+}
+
+/**
+ * pseudo_lock_init - Initialize a pseudo-lock region
+ * @rdtgrp: resource group to which new pseudo-locked region will belong
+ *
+ * A pseudo-locked region is associated with a resource group. When this
+ * association is created the pseudo-locked region is initialized. The
+ * details of the pseudo-locked region are not known at this time so only
+ * allocation is done and association established.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_init(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr;
+
+	plr = kzalloc(sizeof(*plr), GFP_KERNEL);
+	if (!plr)
+		return -ENOMEM;
+
+	init_waitqueue_head(&plr->lock_thread_wq);
+	INIT_LIST_HEAD(&plr->pm_reqs);
+	rdtgrp->plr = plr;
+	return 0;
+}
+
+/**
+ * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
+ * @plr: pseudo-lock region
+ *
+ * Initialize the details required to set up the pseudo-locked region and
+ * allocate the contiguous memory that will be pseudo-locked to the cache.
+ *
+ * Return: 0 on success, <0 on failure.  Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
+{
+	int ret;
+
+	ret = pseudo_lock_region_init(plr);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * We do not yet support contiguous regions larger than
+	 * KMALLOC_MAX_SIZE.
+	 */
+	if (plr->size > KMALLOC_MAX_SIZE) {
+		rdt_last_cmd_puts("requested region exceeds maximum size\n");
+		ret = -E2BIG;
+		goto out_region;
+	}
+
+	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
+	if (!plr->kmem) {
+		rdt_last_cmd_puts("unable to allocate memory\n");
+		ret = -ENOMEM;
+		goto out_region;
+	}
+
+	ret = 0;
+	goto out;
+out_region:
+	pseudo_lock_region_clear(plr);
+out:
+	return ret;
+}
+
+/**
+ * pseudo_lock_free - Free a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-locked region belonged
+ *
+ * The pseudo-locked region's resources have already been released, or not
+ * yet created at this point. Now it can be freed and disassociated from the
+ * resource group.
+ *
+ * Return: void
+ */
+static void pseudo_lock_free(struct rdtgroup *rdtgrp)
+{
+	pseudo_lock_region_clear(rdtgrp->plr);
+	kfree(rdtgrp->plr);
+	rdtgrp->plr = NULL;
+}
+
+/**
+ * pseudo_lock_fn - Load kernel memory into cache
+ * @_rdtgrp: resource group to which pseudo-lock region belongs
+ *
+ * This is the core pseudo-locking flow.
+ *
+ * First we ensure that the kernel memory cannot be found in the cache.
+ * Then, while taking care that there will be as little interference as
+ * possible, the memory to be loaded is accessed while core is running
+ * with class of service set to the bitmask of the pseudo-locked region.
+ * After this is complete no future CAT allocations will be allowed to
+ * overlap with this bitmask.
+ *
+ * Local register variables are utilized to ensure that the memory region
+ * to be locked is the only memory access made during the critical locking
+ * loop.
+ *
+ * Return: 0. Waiter on waitqueue will be woken on completion.
+ */
+static int pseudo_lock_fn(void *_rdtgrp)
+{
+	struct rdtgroup *rdtgrp = _rdtgrp;
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	u32 rmid_p, closid_p;
+	unsigned long i;
+#ifdef CONFIG_KASAN
+	/*
+	 * The registers used for local register variables are also used
+	 * when KASAN is active. When KASAN is active we use a regular
+	 * variable to ensure we always use a valid pointer, but the cost
+	 * is that this variable will enter the cache through evicting the
+	 * memory we are trying to lock into the cache. Thus expect lower
+	 * pseudo-locking success rate when KASAN is active.
+	 */
+	unsigned int line_size;
+	unsigned int size;
+	void *mem_r;
+#else
+	register unsigned int line_size asm("esi");
+	register unsigned int size asm("edi");
+#ifdef CONFIG_X86_64
+	register void *mem_r asm("rbx");
+#else
+	register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+	/*
+	 * Make sure none of the allocated memory is cached. If it is we
+	 * will get a cache hit in below loop from outside of pseudo-locked
+	 * region.
+	 * wbinvd (as opposed to clflush/clflushopt) is required to
+	 * increase likelihood that allocated cache portion will be filled
+	 * with associated memory.
+	 */
+	native_wbinvd();
+
+	/*
+	 * Always called with interrupts enabled. By disabling interrupts
+	 * ensure that we will not be preempted during this critical section.
+	 */
+	local_irq_disable();
+
+	/*
+	 * Call wrmsr and rdmsr as directly as possible to avoid tracing
+	 * clobbering local register variables or affecting cache accesses.
+	 *
+	 * Disable the hardware prefetcher so that when the end of the memory
+	 * being pseudo-locked is reached the hardware will not read beyond
+	 * the buffer and evict pseudo-locked memory read earlier from the
+	 * cache.
+	 */
+	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	closid_p = this_cpu_read(pqr_state.cur_closid);
+	rmid_p = this_cpu_read(pqr_state.cur_rmid);
+	mem_r = plr->kmem;
+	size = plr->size;
+	line_size = plr->line_size;
+	/*
+	 * Critical section begin: start by writing the closid associated
+	 * with the capacity bitmask of the cache region being
+	 * pseudo-locked followed by reading of kernel memory to load it
+	 * into the cache.
+	 */
+	__wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid);
+	/*
+	 * Cache was flushed earlier. Now access kernel memory to read it
+	 * into cache region associated with just activated plr->closid.
+	 * Loop over data twice:
+	 * - In first loop the cache region is shared with the page walker
+	 *   as it populates the paging structure caches (including TLB).
+	 * - In the second loop the paging structure caches are used and
+	 *   cache region is populated with the memory being referenced.
+	 */
+	for (i = 0; i < size; i += PAGE_SIZE) {
+		/*
+		 * Add a barrier to prevent speculative execution of this
+		 * loop reading beyond the end of the buffer.
+		 */
+		rmb();
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			:
+			: "r" (mem_r), "r" (i)
+			: "%eax", "memory");
+	}
+	for (i = 0; i < size; i += line_size) {
+		/*
+		 * Add a barrier to prevent speculative execution of this
+		 * loop reading beyond the end of the buffer.
+		 */
+		rmb();
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			:
+			: "r" (mem_r), "r" (i)
+			: "%eax", "memory");
+	}
+	/*
+	 * Critical section end: restore closid with capacity bitmask that
+	 * does not overlap with pseudo-locked region.
+	 */
+	__wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p);
+
+	/* Re-enable the hardware prefetcher(s) */
+	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	local_irq_enable();
+
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
+/**
+ * rdtgroup_monitor_in_progress - Test if monitoring in progress
+ * @r: resource group being queried
+ *
+ * Return: 1 if monitor groups have been created for this resource
+ * group, 0 otherwise.
+ */
+static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
+{
+	return !list_empty(&rdtgrp->mon.crdtgrp_list);
+}
+
+/**
+ * rdtgroup_locksetup_user_restrict - Restrict user access to group
+ * @rdtgrp: resource group needing access restricted
+ *
+ * A resource group used for cache pseudo-locking cannot have cpus or tasks
+ * assigned to it. This is communicated to the user by restricting access
+ * to all the files that can be used to make such changes.
+ *
+ * Permissions restored with rdtgroup_locksetup_user_restore()
+ *
+ * Return: 0 on success, <0 on failure. If a failure occurs during the
+ * restriction of access an attempt will be made to restore permissions but
+ * the state of the mode of these files will be uncertain when a failure
+ * occurs.
+ */
+static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+	if (ret)
+		goto err_tasks;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+	if (ret)
+		goto err_cpus;
+
+	if (rdt_mon_capable) {
+		ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
+		if (ret)
+			goto err_cpus_list;
+	}
+
+	ret = 0;
+	goto out;
+
+err_cpus_list:
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
+err_cpus:
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
+err_tasks:
+	rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_user_restore - Restore user access to group
+ * @rdtgrp: resource group needing access restored
+ *
+ * Restore all file access previously removed using
+ * rdtgroup_locksetup_user_restrict()
+ *
+ * Return: 0 on success, <0 on failure.  If a failure occurs during the
+ * restoration of access an attempt will be made to restrict permissions
+ * again but the state of the mode of these files will be uncertain when
+ * a failure occurs.
+ */
+static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
+	if (ret)
+		goto err_tasks;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
+	if (ret)
+		goto err_cpus;
+
+	if (rdt_mon_capable) {
+		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
+		if (ret)
+			goto err_cpus_list;
+	}
+
+	ret = 0;
+	goto out;
+
+err_cpus_list:
+	rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+err_cpus:
+	rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+err_tasks:
+	rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_enter - Resource group enters locksetup mode
+ * @rdtgrp: resource group requested to enter locksetup mode
+ *
+ * A resource group enters locksetup mode to reflect that it would be used
+ * to represent a pseudo-locked region and is in the process of being set
+ * up to do so. A resource group used for a pseudo-locked region would
+ * lose the closid associated with it so we cannot allow it to have any
+ * tasks or cpus assigned nor permit tasks or cpus to be assigned in the
+ * future. Monitoring of a pseudo-locked region is not allowed either.
+ *
+ * The above and more restrictions on a pseudo-locked region are checked
+ * for and enforced before the resource group enters the locksetup mode.
+ *
+ * Returns: 0 if the resource group successfully entered locksetup mode, <0
+ * on failure. On failure the last_cmd_status buffer is updated with text to
+ * communicate details of failure to the user.
+ */
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	/*
+	 * The default resource group can neither be removed nor lose the
+	 * default closid associated with it.
+	 */
+	if (rdtgrp == &rdtgroup_default) {
+		rdt_last_cmd_puts("cannot pseudo-lock default group\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Cache Pseudo-locking not supported when CDP is enabled.
+	 *
+	 * Some things to consider if you would like to enable this
+	 * support (using L3 CDP as example):
+	 * - When CDP is enabled two separate resources are exposed,
+	 *   L3DATA and L3CODE, but they are actually on the same cache.
+	 *   The implication for pseudo-locking is that if a
+	 *   pseudo-locked region is created on a domain of one
+	 *   resource (eg. L3CODE), then a pseudo-locked region cannot
+	 *   be created on that same domain of the other resource
+	 *   (eg. L3DATA). This is because the creation of a
+	 *   pseudo-locked region involves a call to wbinvd that will
+	 *   affect all cache allocations on particular domain.
+	 * - Considering the previous, it may be possible to only
+	 *   expose one of the CDP resources to pseudo-locking and
+	 *   hide the other. For example, we could consider to only
+	 *   expose L3DATA and since the L3 cache is unified it is
+	 *   still possible to place instructions there are execute it.
+	 * - If only one region is exposed to pseudo-locking we should
+	 *   still keep in mind that availability of a portion of cache
+	 *   for pseudo-locking should take into account both resources.
+	 *   Similarly, if a pseudo-locked region is created in one
+	 *   resource, the portion of cache used by it should be made
+	 *   unavailable to all future allocations from both resources.
+	 */
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled ||
+	    rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) {
+		rdt_last_cmd_puts("CDP enabled\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Not knowing the bits to disable prefetching implies that this
+	 * platform does not support Cache Pseudo-Locking.
+	 */
+	prefetch_disable_bits = get_prefetch_disable_bits();
+	if (prefetch_disable_bits == 0) {
+		rdt_last_cmd_puts("pseudo-locking not supported\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_monitor_in_progress(rdtgrp)) {
+		rdt_last_cmd_puts("monitoring in progress\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_tasks_assigned(rdtgrp)) {
+		rdt_last_cmd_puts("tasks assigned to resource group\n");
+		return -EINVAL;
+	}
+
+	if (!cpumask_empty(&rdtgrp->cpu_mask)) {
+		rdt_last_cmd_puts("CPUs assigned to resource group\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
+		rdt_last_cmd_puts("unable to modify resctrl permissions\n");
+		return -EIO;
+	}
+
+	ret = pseudo_lock_init(rdtgrp);
+	if (ret) {
+		rdt_last_cmd_puts("unable to init pseudo-lock region\n");
+		goto out_release;
+	}
+
+	/*
+	 * If this system is capable of monitoring a rmid would have been
+	 * allocated when the control group was created. This is not needed
+	 * anymore when this group would be used for pseudo-locking. This
+	 * is safe to call on platforms not capable of monitoring.
+	 */
+	free_rmid(rdtgrp->mon.rmid);
+
+	ret = 0;
+	goto out;
+
+out_release:
+	rdtgroup_locksetup_user_restore(rdtgrp);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_exit - resource group exist locksetup mode
+ * @rdtgrp: resource group
+ *
+ * When a resource group exits locksetup mode the earlier restrictions are
+ * lifted.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	if (rdt_mon_capable) {
+		ret = alloc_rmid();
+		if (ret < 0) {
+			rdt_last_cmd_puts("out of RMIDs\n");
+			return ret;
+		}
+		rdtgrp->mon.rmid = ret;
+	}
+
+	ret = rdtgroup_locksetup_user_restore(rdtgrp);
+	if (ret) {
+		free_rmid(rdtgrp->mon.rmid);
+		return ret;
+	}
+
+	pseudo_lock_free(rdtgrp);
+	return 0;
+}
+
+/**
+ * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
+ * @d: RDT domain
+ * @_cbm: CBM to test
+ *
+ * @d represents a cache instance and @_cbm a capacity bitmask that is
+ * considered for it. Determine if @_cbm overlaps with any existing
+ * pseudo-locked region on @d.
+ *
+ * Return: true if @_cbm overlaps with pseudo-locked region on @d, false
+ * otherwise.
+ */
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm)
+{
+	unsigned long *cbm = (unsigned long *)&_cbm;
+	unsigned long *cbm_b;
+	unsigned int cbm_len;
+
+	if (d->plr) {
+		cbm_len = d->plr->r->cache.cbm_len;
+		cbm_b = (unsigned long *)&d->plr->cbm;
+		if (bitmap_intersects(cbm, cbm_b, cbm_len))
+			return true;
+	}
+	return false;
+}
+
+/**
+ * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy
+ * @d: RDT domain under test
+ *
+ * The setup of a pseudo-locked region affects all cache instances within
+ * the hierarchy of the region. It is thus essential to know if any
+ * pseudo-locked regions exist within a cache hierarchy to prevent any
+ * attempts to create new pseudo-locked regions in the same hierarchy.
+ *
+ * Return: true if a pseudo-locked region exists in the hierarchy of @d or
+ *         if it is not possible to test due to memory allocation issue,
+ *         false otherwise.
+ */
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+{
+	cpumask_var_t cpu_with_psl;
+	struct rdt_resource *r;
+	struct rdt_domain *d_i;
+	bool ret = false;
+
+	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
+		return true;
+
+	/*
+	 * First determine which cpus have pseudo-locked regions
+	 * associated with them.
+	 */
+	for_each_alloc_enabled_rdt_resource(r) {
+		list_for_each_entry(d_i, &r->domains, list) {
+			if (d_i->plr)
+				cpumask_or(cpu_with_psl, cpu_with_psl,
+					   &d_i->cpu_mask);
+		}
+	}
+
+	/*
+	 * Next test if new pseudo-locked region would intersect with
+	 * existing region.
+	 */
+	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+		ret = true;
+
+	free_cpumask_var(cpu_with_psl);
+	return ret;
+}
+
+/**
+ * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory
+ * @_plr: pseudo-lock region to measure
+ *
+ * There is no deterministic way to test if a memory region is cached. One
+ * way is to measure how long it takes to read the memory, the speed of
+ * access is a good way to learn how close to the cpu the data was. Even
+ * more, if the prefetcher is disabled and the memory is read at a stride
+ * of half the cache line, then a cache miss will be easy to spot since the
+ * read of the first half would be significantly slower than the read of
+ * the second half.
+ *
+ * Return: 0. Waiter on waitqueue will be woken on completion.
+ */
+static int measure_cycles_lat_fn(void *_plr)
+{
+	struct pseudo_lock_region *plr = _plr;
+	unsigned long i;
+	u64 start, end;
+#ifdef CONFIG_KASAN
+	/*
+	 * The registers used for local register variables are also used
+	 * when KASAN is active. When KASAN is active we use a regular
+	 * variable to ensure we always use a valid pointer to access memory.
+	 * The cost is that accessing this pointer, which could be in
+	 * cache, will be included in the measurement of memory read latency.
+	 */
+	void *mem_r;
+#else
+#ifdef CONFIG_X86_64
+	register void *mem_r asm("rbx");
+#else
+	register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+	local_irq_disable();
+	/*
+	 * The wrmsr call may be reordered with the assignment below it.
+	 * Call wrmsr as directly as possible to avoid tracing clobbering
+	 * local register variable used for memory pointer.
+	 */
+	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	mem_r = plr->kmem;
+	/*
+	 * Dummy execute of the time measurement to load the needed
+	 * instructions into the L1 instruction cache.
+	 */
+	start = rdtsc_ordered();
+	for (i = 0; i < plr->size; i += 32) {
+		start = rdtsc_ordered();
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			     :
+			     : "r" (mem_r), "r" (i)
+			     : "%eax", "memory");
+		end = rdtsc_ordered();
+		trace_pseudo_lock_mem_latency((u32)(end - start));
+	}
+	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	local_irq_enable();
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
+static int measure_cycles_perf_fn(void *_plr)
+{
+	unsigned long long l3_hits = 0, l3_miss = 0;
+	u64 l3_hit_bits = 0, l3_miss_bits = 0;
+	struct pseudo_lock_region *plr = _plr;
+	unsigned long long l2_hits, l2_miss;
+	u64 l2_hit_bits, l2_miss_bits;
+	unsigned long i;
+#ifdef CONFIG_KASAN
+	/*
+	 * The registers used for local register variables are also used
+	 * when KASAN is active. When KASAN is active we use regular variables
+	 * at the cost of including cache access latency to these variables
+	 * in the measurements.
+	 */
+	unsigned int line_size;
+	unsigned int size;
+	void *mem_r;
+#else
+	register unsigned int line_size asm("esi");
+	register unsigned int size asm("edi");
+#ifdef CONFIG_X86_64
+	register void *mem_r asm("rbx");
+#else
+	register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+	/*
+	 * Non-architectural event for the Goldmont Microarchitecture
+	 * from Intel x86 Architecture Software Developer Manual (SDM):
+	 * MEM_LOAD_UOPS_RETIRED D1H (event number)
+	 * Umask values:
+	 *     L1_HIT   01H
+	 *     L2_HIT   02H
+	 *     L1_MISS  08H
+	 *     L2_MISS  10H
+	 *
+	 * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
+	 * has two "no fix" errata associated with it: BDM35 and BDM100. On
+	 * this platform we use the following events instead:
+	 *  L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/)
+	 *       REFERENCES FFH
+	 *       MISS       3FH
+	 *  LONGEST_LAT_CACHE 2EH (Documented in SDM)
+	 *       REFERENCE 4FH
+	 *       MISS      41H
+	 */
+
+	/*
+	 * Start by setting flags for IA32_PERFEVTSELx:
+	 *     OS  (Operating system mode)  0x2
+	 *     INT (APIC interrupt enable)  0x10
+	 *     EN  (Enable counter)         0x40
+	 *
+	 * Then add the Umask value and event number to select performance
+	 * event.
+	 */
+
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+		l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1;
+		l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1;
+		break;
+	case INTEL_FAM6_BROADWELL_X:
+		/* On BDW the l2_hit_bits count references, not hits */
+		l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24;
+		l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24;
+		/* On BDW the l3_hit_bits count references, not hits */
+		l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e;
+		l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e;
+		break;
+	default:
+		goto out;
+	}
+
+	local_irq_disable();
+	/*
+	 * Call wrmsr direcly to avoid the local register variables from
+	 * being overwritten due to reordering of their assignment with
+	 * the wrmsr calls.
+	 */
+	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	/* Disable events and reset counters */
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0);
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0);
+	}
+	/* Set and enable the L2 counters */
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits);
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+				      l3_hit_bits);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+				      l3_miss_bits);
+	}
+	mem_r = plr->kmem;
+	size = plr->size;
+	line_size = plr->line_size;
+	for (i = 0; i < size; i += line_size) {
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			     :
+			     : "r" (mem_r), "r" (i)
+			     : "%eax", "memory");
+	}
+	/*
+	 * Call wrmsr directly (no tracing) to not influence
+	 * the cache access counters as they are disabled.
+	 */
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0,
+			      l2_hit_bits & ~(0x40ULL << 16));
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1,
+			      l2_miss_bits & ~(0x40ULL << 16));
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+				      l3_hit_bits & ~(0x40ULL << 16));
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+				      l3_miss_bits & ~(0x40ULL << 16));
+	}
+	l2_hits = native_read_pmc(0);
+	l2_miss = native_read_pmc(1);
+	if (l3_hit_bits > 0) {
+		l3_hits = native_read_pmc(2);
+		l3_miss = native_read_pmc(3);
+	}
+	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	local_irq_enable();
+	/*
+	 * On BDW we count references and misses, need to adjust. Sometimes
+	 * the "hits" counter is a bit more than the references, for
+	 * example, x references but x + 1 hits. To not report invalid
+	 * hit values in this case we treat that as misses eaqual to
+	 * references.
+	 */
+	if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+		l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss);
+	trace_pseudo_lock_l2(l2_hits, l2_miss);
+	if (l3_hit_bits > 0) {
+		if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+			l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss);
+		trace_pseudo_lock_l3(l3_hits, l3_miss);
+	}
+
+out:
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
+/**
+ * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
+ *
+ * The measurement of latency to access a pseudo-locked region should be
+ * done from a cpu that is associated with that pseudo-locked region.
+ * Determine which cpu is associated with this region and start a thread on
+ * that cpu to perform the measurement, wait for that thread to complete.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct task_struct *thread;
+	unsigned int cpu;
+	int ret = -1;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	if (rdtgrp->flags & RDT_DELETED) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	plr->thread_done = 0;
+	cpu = cpumask_first(&plr->d->cpu_mask);
+	if (!cpu_online(cpu)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (sel == 1)
+		thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
+						cpu_to_node(cpu),
+						"pseudo_lock_measure/%u",
+						cpu);
+	else if (sel == 2)
+		thread = kthread_create_on_node(measure_cycles_perf_fn, plr,
+						cpu_to_node(cpu),
+						"pseudo_lock_measure/%u",
+						cpu);
+	else
+		goto out;
+
+	if (IS_ERR(thread)) {
+		ret = PTR_ERR(thread);
+		goto out;
+	}
+	kthread_bind(thread, cpu);
+	wake_up_process(thread);
+
+	ret = wait_event_interruptible(plr->lock_thread_wq,
+				       plr->thread_done == 1);
+	if (ret < 0)
+		goto out;
+
+	ret = 0;
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+	return ret;
+}
+
+static ssize_t pseudo_lock_measure_trigger(struct file *file,
+					   const char __user *user_buf,
+					   size_t count, loff_t *ppos)
+{
+	struct rdtgroup *rdtgrp = file->private_data;
+	size_t buf_size;
+	char buf[32];
+	int ret;
+	int sel;
+
+	buf_size = min(count, (sizeof(buf) - 1));
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	ret = kstrtoint(buf, 10, &sel);
+	if (ret == 0) {
+		if (sel != 1)
+			return -EINVAL;
+		ret = debugfs_file_get(file->f_path.dentry);
+		if (ret)
+			return ret;
+		ret = pseudo_lock_measure_cycles(rdtgrp, sel);
+		if (ret == 0)
+			ret = count;
+		debugfs_file_put(file->f_path.dentry);
+	}
+
+	return ret;
+}
+
+static const struct file_operations pseudo_measure_fops = {
+	.write = pseudo_lock_measure_trigger,
+	.open = simple_open,
+	.llseek = default_llseek,
+};
+
+/**
+ * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-lock region belongs
+ *
+ * Called when a resource group in the pseudo-locksetup mode receives a
+ * valid schemata that should be pseudo-locked. Since the resource group is
+ * in pseudo-locksetup mode the &struct pseudo_lock_region has already been
+ * allocated and initialized with the essential information. If a failure
+ * occurs the resource group remains in the pseudo-locksetup mode with the
+ * &struct pseudo_lock_region associated with it, but cleared from all
+ * information and ready for the user to re-attempt pseudo-locking by
+ * writing the schemata again.
+ *
+ * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0
+ * on failure. Descriptive error will be written to last_cmd_status buffer.
+ */
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct task_struct *thread;
+	unsigned int new_minor;
+	struct device *dev;
+	int ret;
+
+	ret = pseudo_lock_region_alloc(plr);
+	if (ret < 0)
+		return ret;
+
+	ret = pseudo_lock_cstates_constrain(plr);
+	if (ret < 0) {
+		ret = -EINVAL;
+		goto out_region;
+	}
+
+	plr->thread_done = 0;
+
+	thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp,
+					cpu_to_node(plr->cpu),
+					"pseudo_lock/%u", plr->cpu);
+	if (IS_ERR(thread)) {
+		ret = PTR_ERR(thread);
+		rdt_last_cmd_printf("locking thread returned error %d\n", ret);
+		goto out_cstates;
+	}
+
+	kthread_bind(thread, plr->cpu);
+	wake_up_process(thread);
+
+	ret = wait_event_interruptible(plr->lock_thread_wq,
+				       plr->thread_done == 1);
+	if (ret < 0) {
+		/*
+		 * If the thread does not get on the CPU for whatever
+		 * reason and the process which sets up the region is
+		 * interrupted then this will leave the thread in runnable
+		 * state and once it gets on the CPU it will derefence
+		 * the cleared, but not freed, plr struct resulting in an
+		 * empty pseudo-locking loop.
+		 */
+		rdt_last_cmd_puts("locking thread interrupted\n");
+		goto out_cstates;
+	}
+
+	ret = pseudo_lock_minor_get(&new_minor);
+	if (ret < 0) {
+		rdt_last_cmd_puts("unable to obtain a new minor number\n");
+		goto out_cstates;
+	}
+
+	/*
+	 * Unlock access but do not release the reference. The
+	 * pseudo-locked region will still be here on return.
+	 *
+	 * The mutex has to be released temporarily to avoid a potential
+	 * deadlock with the mm->mmap_sem semaphore which is obtained in
+	 * the device_create() and debugfs_create_dir() callpath below
+	 * as well as before the mmap() callback is called.
+	 */
+	mutex_unlock(&rdtgroup_mutex);
+
+	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
+		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
+						      debugfs_resctrl);
+		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
+			debugfs_create_file("pseudo_lock_measure", 0200,
+					    plr->debugfs_dir, rdtgrp,
+					    &pseudo_measure_fops);
+	}
+
+	dev = device_create(pseudo_lock_class, NULL,
+			    MKDEV(pseudo_lock_major, new_minor),
+			    rdtgrp, "%s", rdtgrp->kn->name);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		rdt_last_cmd_printf("failed to create character device: %d\n",
+				    ret);
+		goto out_debugfs;
+	}
+
+	/* We released the mutex - check if group was removed while we did so */
+	if (rdtgrp->flags & RDT_DELETED) {
+		ret = -ENODEV;
+		goto out_device;
+	}
+
+	plr->minor = new_minor;
+
+	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
+	closid_free(rdtgrp->closid);
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444);
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444);
+
+	ret = 0;
+	goto out;
+
+out_device:
+	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
+out_debugfs:
+	debugfs_remove_recursive(plr->debugfs_dir);
+	pseudo_lock_minor_release(new_minor);
+out_cstates:
+	pseudo_lock_cstates_relax(plr);
+out_region:
+	pseudo_lock_region_clear(plr);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region
+ * @rdtgrp: resource group to which the pseudo-locked region belongs
+ *
+ * The removal of a pseudo-locked region can be initiated when the resource
+ * group is removed from user space via a "rmdir" from userspace or the
+ * unmount of the resctrl filesystem. On removal the resource group does
+ * not go back to pseudo-locksetup mode before it is removed, instead it is
+ * removed directly. There is thus assymmetry with the creation where the
+ * &struct pseudo_lock_region is removed here while it was not created in
+ * rdtgroup_pseudo_lock_create().
+ *
+ * Return: void
+ */
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		/*
+		 * Default group cannot be a pseudo-locked region so we can
+		 * free closid here.
+		 */
+		closid_free(rdtgrp->closid);
+		goto free;
+	}
+
+	pseudo_lock_cstates_relax(plr);
+	debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
+	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
+	pseudo_lock_minor_release(plr->minor);
+
+free:
+	pseudo_lock_free(rdtgrp);
+}
+
+static int pseudo_lock_dev_open(struct inode *inode, struct file *filp)
+{
+	struct rdtgroup *rdtgrp;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgrp = region_find_by_minor(iminor(inode));
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
+	filp->private_data = rdtgrp;
+	atomic_inc(&rdtgrp->waitcount);
+	/* Perform a non-seekable open - llseek is not supported */
+	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
+{
+	struct rdtgroup *rdtgrp;
+
+	mutex_lock(&rdtgroup_mutex);
+	rdtgrp = filp->private_data;
+	WARN_ON(!rdtgrp);
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+	filp->private_data = NULL;
+	atomic_dec(&rdtgrp->waitcount);
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
+static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
+{
+	/* Not supported */
+	return -EINVAL;
+}
+
+static const struct vm_operations_struct pseudo_mmap_ops = {
+	.mremap = pseudo_lock_dev_mremap,
+};
+
+static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	unsigned long vsize = vma->vm_end - vma->vm_start;
+	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
+	struct pseudo_lock_region *plr;
+	struct rdtgroup *rdtgrp;
+	unsigned long physical;
+	unsigned long psize;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgrp = filp->private_data;
+	WARN_ON(!rdtgrp);
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
+	plr = rdtgrp->plr;
+
+	/*
+	 * Task is required to run with affinity to the cpus associated
+	 * with the pseudo-locked region. If this is not the case the task
+	 * may be scheduled elsewhere and invalidate entries in the
+	 * pseudo-locked region.
+	 */
+	if (!cpumask_subset(&current->cpus_allowed, &plr->d->cpu_mask)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EINVAL;
+	}
+
+	physical = __pa(plr->kmem) >> PAGE_SHIFT;
+	psize = plr->size - off;
+
+	if (off > plr->size) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENOSPC;
+	}
+
+	/*
+	 * Ensure changes are carried directly to the memory being mapped,
+	 * do not allow copy-on-write mapping.
+	 */
+	if (!(vma->vm_flags & VM_SHARED)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EINVAL;
+	}
+
+	if (vsize > psize) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENOSPC;
+	}
+
+	memset(plr->kmem + off, 0, vsize);
+
+	if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
+			    vsize, vma->vm_page_prot)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EAGAIN;
+	}
+	vma->vm_ops = &pseudo_mmap_ops;
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
+static const struct file_operations pseudo_lock_dev_fops = {
+	.owner =	THIS_MODULE,
+	.llseek =	no_llseek,
+	.read =		NULL,
+	.write =	NULL,
+	.open =		pseudo_lock_dev_open,
+	.release =	pseudo_lock_dev_release,
+	.mmap =		pseudo_lock_dev_mmap,
+};
+
+static char *pseudo_lock_devnode(struct device *dev, umode_t *mode)
+{
+	struct rdtgroup *rdtgrp;
+
+	rdtgrp = dev_get_drvdata(dev);
+	if (mode)
+		*mode = 0600;
+	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
+}
+
+int rdt_pseudo_lock_init(void)
+{
+	int ret;
+
+	ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops);
+	if (ret < 0)
+		return ret;
+
+	pseudo_lock_major = ret;
+
+	pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock");
+	if (IS_ERR(pseudo_lock_class)) {
+		ret = PTR_ERR(pseudo_lock_class);
+		unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+		return ret;
+	}
+
+	pseudo_lock_class->devnode = pseudo_lock_devnode;
+	return 0;
+}
+
+void rdt_pseudo_lock_release(void)
+{
+	class_destroy(pseudo_lock_class);
+	pseudo_lock_class = NULL;
+	unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+	pseudo_lock_major = 0;
+}
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
new file mode 100644
index 000000000000..2c041e6d9f05
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM resctrl
+
+#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PSEUDO_LOCK_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(pseudo_lock_mem_latency,
+	    TP_PROTO(u32 latency),
+	    TP_ARGS(latency),
+	    TP_STRUCT__entry(__field(u32, latency)),
+	    TP_fast_assign(__entry->latency = latency),
+	    TP_printk("latency=%u", __entry->latency)
+	   );
+
+TRACE_EVENT(pseudo_lock_l2,
+	    TP_PROTO(u64 l2_hits, u64 l2_miss),
+	    TP_ARGS(l2_hits, l2_miss),
+	    TP_STRUCT__entry(__field(u64, l2_hits)
+			     __field(u64, l2_miss)),
+	    TP_fast_assign(__entry->l2_hits = l2_hits;
+			   __entry->l2_miss = l2_miss;),
+	    TP_printk("hits=%llu miss=%llu",
+		      __entry->l2_hits, __entry->l2_miss));
+
+TRACE_EVENT(pseudo_lock_l3,
+	    TP_PROTO(u64 l3_hits, u64 l3_miss),
+	    TP_ARGS(l3_hits, l3_miss),
+	    TP_STRUCT__entry(__field(u64, l3_hits)
+			     __field(u64, l3_miss)),
+	    TP_fast_assign(__entry->l3_hits = l3_hits;
+			   __entry->l3_miss = l3_miss;),
+	    TP_printk("hits=%llu miss=%llu",
+		      __entry->l3_hits, __entry->l3_miss));
+
+#endif /* _TRACE_PSEUDO_LOCK_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event
+#include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 749856a2e736..d6d7ea7349d0 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -20,7 +20,9 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/cacheinfo.h>
 #include <linux/cpu.h>
+#include <linux/debugfs.h>
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
@@ -55,6 +57,8 @@ static struct kernfs_node *kn_mondata;
 static struct seq_buf last_cmd_status;
 static char last_cmd_status_buf[512];
 
+struct dentry *debugfs_resctrl;
+
 void rdt_last_cmd_clear(void)
 {
 	lockdep_assert_held(&rdtgroup_mutex);
@@ -121,11 +125,65 @@ static int closid_alloc(void)
 	return closid;
 }
 
-static void closid_free(int closid)
+void closid_free(int closid)
 {
 	closid_free_map |= 1 << closid;
 }
 
+/**
+ * closid_allocated - test if provided closid is in use
+ * @closid: closid to be tested
+ *
+ * Return: true if @closid is currently associated with a resource group,
+ * false if @closid is free
+ */
+static bool closid_allocated(unsigned int closid)
+{
+	return (closid_free_map & (1 << closid)) == 0;
+}
+
+/**
+ * rdtgroup_mode_by_closid - Return mode of resource group with closid
+ * @closid: closid if the resource group
+ *
+ * Each resource group is associated with a @closid. Here the mode
+ * of a resource group can be queried by searching for it using its closid.
+ *
+ * Return: mode as &enum rdtgrp_mode of resource group with closid @closid
+ */
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
+{
+	struct rdtgroup *rdtgrp;
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (rdtgrp->closid == closid)
+			return rdtgrp->mode;
+	}
+
+	return RDT_NUM_MODES;
+}
+
+static const char * const rdt_mode_str[] = {
+	[RDT_MODE_SHAREABLE]		= "shareable",
+	[RDT_MODE_EXCLUSIVE]		= "exclusive",
+	[RDT_MODE_PSEUDO_LOCKSETUP]	= "pseudo-locksetup",
+	[RDT_MODE_PSEUDO_LOCKED]	= "pseudo-locked",
+};
+
+/**
+ * rdtgroup_mode_str - Return the string representation of mode
+ * @mode: the resource group mode as &enum rdtgroup_mode
+ *
+ * Return: string representation of valid mode, "unknown" otherwise
+ */
+static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
+{
+	if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
+		return "unknown";
+
+	return rdt_mode_str[mode];
+}
+
 /* set uid and gid of rdtgroup dirs and files to that of the creator */
 static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
 {
@@ -207,8 +265,12 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 
 	if (rdtgrp) {
-		seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
-			   cpumask_pr_args(&rdtgrp->cpu_mask));
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+				   cpumask_pr_args(&rdtgrp->plr->d->cpu_mask));
+		else
+			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+				   cpumask_pr_args(&rdtgrp->cpu_mask));
 	} else {
 		ret = -ENOENT;
 	}
@@ -394,6 +456,13 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		goto unlock;
 	}
 
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		goto unlock;
+	}
+
 	if (is_cpu_list(of))
 		ret = cpulist_parse(buf, newmask);
 	else
@@ -509,6 +578,32 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	return ret;
 }
 
+/**
+ * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
+ * @r: Resource group
+ *
+ * Return: 1 if tasks have been assigned to @r, 0 otherwise
+ */
+int rdtgroup_tasks_assigned(struct rdtgroup *r)
+{
+	struct task_struct *p, *t;
+	int ret = 0;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	rcu_read_lock();
+	for_each_process_thread(p, t) {
+		if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
+		    (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) {
+			ret = 1;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static int rdtgroup_task_write_permission(struct task_struct *task,
 					  struct kernfs_open_file *of)
 {
@@ -570,13 +665,22 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
 	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
 		return -EINVAL;
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
 	rdt_last_cmd_clear();
 
-	if (rdtgrp)
-		ret = rdtgroup_move_task(pid, rdtgrp, of);
-	else
-		ret = -ENOENT;
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		goto unlock;
+	}
 
+	ret = rdtgroup_move_task(pid, rdtgrp, of);
+
+unlock:
 	rdtgroup_kn_unlock(of->kn);
 
 	return ret ?: nbytes;
@@ -662,6 +766,94 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+/**
+ * rdt_bit_usage_show - Display current usage of resources
+ *
+ * A domain is a shared resource that can now be allocated differently. Here
+ * we display the current regions of the domain as an annotated bitmask.
+ * For each domain of this resource its allocation bitmask
+ * is annotated as below to indicate the current usage of the corresponding bit:
+ *   0 - currently unused
+ *   X - currently available for sharing and used by software and hardware
+ *   H - currently used by hardware only but available for software use
+ *   S - currently used and shareable by software only
+ *   E - currently used exclusively by one resource group
+ *   P - currently pseudo-locked by one resource group
+ */
+static int rdt_bit_usage_show(struct kernfs_open_file *of,
+			      struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+	u32 sw_shareable = 0, hw_shareable = 0;
+	u32 exclusive = 0, pseudo_locked = 0;
+	struct rdt_domain *dom;
+	int i, hwb, swb, excl, psl;
+	enum rdtgrp_mode mode;
+	bool sep = false;
+	u32 *ctrl;
+
+	mutex_lock(&rdtgroup_mutex);
+	hw_shareable = r->cache.shareable_bits;
+	list_for_each_entry(dom, &r->domains, list) {
+		if (sep)
+			seq_putc(seq, ';');
+		ctrl = dom->ctrl_val;
+		sw_shareable = 0;
+		exclusive = 0;
+		seq_printf(seq, "%d=", dom->id);
+		for (i = 0; i < r->num_closid; i++, ctrl++) {
+			if (!closid_allocated(i))
+				continue;
+			mode = rdtgroup_mode_by_closid(i);
+			switch (mode) {
+			case RDT_MODE_SHAREABLE:
+				sw_shareable |= *ctrl;
+				break;
+			case RDT_MODE_EXCLUSIVE:
+				exclusive |= *ctrl;
+				break;
+			case RDT_MODE_PSEUDO_LOCKSETUP:
+			/*
+			 * RDT_MODE_PSEUDO_LOCKSETUP is possible
+			 * here but not included since the CBM
+			 * associated with this CLOSID in this mode
+			 * is not initialized and no task or cpu can be
+			 * assigned this CLOSID.
+			 */
+				break;
+			case RDT_MODE_PSEUDO_LOCKED:
+			case RDT_NUM_MODES:
+				WARN(1,
+				     "invalid mode for closid %d\n", i);
+				break;
+			}
+		}
+		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
+			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
+			hwb = test_bit(i, (unsigned long *)&hw_shareable);
+			swb = test_bit(i, (unsigned long *)&sw_shareable);
+			excl = test_bit(i, (unsigned long *)&exclusive);
+			psl = test_bit(i, (unsigned long *)&pseudo_locked);
+			if (hwb && swb)
+				seq_putc(seq, 'X');
+			else if (hwb && !swb)
+				seq_putc(seq, 'H');
+			else if (!hwb && swb)
+				seq_putc(seq, 'S');
+			else if (excl)
+				seq_putc(seq, 'E');
+			else if (psl)
+				seq_putc(seq, 'P');
+			else /* Unused bits remain */
+				seq_putc(seq, '0');
+		}
+		sep = true;
+	}
+	seq_putc(seq, '\n');
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
 static int rdt_min_bw_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
@@ -740,6 +932,269 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+/*
+ * rdtgroup_mode_show - Display mode of this resource group
+ */
+static int rdtgroup_mode_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));
+
+	rdtgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+/**
+ * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
+ * @r: Resource to which domain instance @d belongs.
+ * @d: The domain instance for which @closid is being tested.
+ * @cbm: Capacity bitmask being tested.
+ * @closid: Intended closid for @cbm.
+ * @exclusive: Only check if overlaps with exclusive resource groups
+ *
+ * Checks if provided @cbm intended to be used for @closid on domain
+ * @d overlaps with any other closids or other hardware usage associated
+ * with this domain. If @exclusive is true then only overlaps with
+ * resource groups in exclusive mode will be considered. If @exclusive
+ * is false then overlaps with any resource group or hardware entities
+ * will be considered.
+ *
+ * Return: false if CBM does not overlap, true if it does.
+ */
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+			   u32 _cbm, int closid, bool exclusive)
+{
+	unsigned long *cbm = (unsigned long *)&_cbm;
+	unsigned long *ctrl_b;
+	enum rdtgrp_mode mode;
+	u32 *ctrl;
+	int i;
+
+	/* Check for any overlap with regions used by hardware directly */
+	if (!exclusive) {
+		if (bitmap_intersects(cbm,
+				      (unsigned long *)&r->cache.shareable_bits,
+				      r->cache.cbm_len))
+			return true;
+	}
+
+	/* Check for overlap with other resource groups */
+	ctrl = d->ctrl_val;
+	for (i = 0; i < r->num_closid; i++, ctrl++) {
+		ctrl_b = (unsigned long *)ctrl;
+		mode = rdtgroup_mode_by_closid(i);
+		if (closid_allocated(i) && i != closid &&
+		    mode != RDT_MODE_PSEUDO_LOCKSETUP) {
+			if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) {
+				if (exclusive) {
+					if (mode == RDT_MODE_EXCLUSIVE)
+						return true;
+					continue;
+				}
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+/**
+ * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
+ *
+ * An exclusive resource group implies that there should be no sharing of
+ * its allocated resources. At the time this group is considered to be
+ * exclusive this test can determine if its current schemata supports this
+ * setting by testing for overlap with all other resource groups.
+ *
+ * Return: true if resource group can be exclusive, false if there is overlap
+ * with allocations of other resource groups and thus this resource group
+ * cannot be exclusive.
+ */
+static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
+{
+	int closid = rdtgrp->closid;
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		list_for_each_entry(d, &r->domains, list) {
+			if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
+						  rdtgrp->closid, false))
+				return false;
+		}
+	}
+
+	return true;
+}
+
+/**
+ * rdtgroup_mode_write - Modify the resource group's mode
+ *
+ */
+static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
+				   char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	enum rdtgrp_mode mode;
+	int ret = 0;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	rdt_last_cmd_clear();
+
+	mode = rdtgrp->mode;
+
+	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
+	    (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) ||
+	    (!strcmp(buf, "pseudo-locksetup") &&
+	     mode == RDT_MODE_PSEUDO_LOCKSETUP) ||
+	    (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED))
+		goto out;
+
+	if (mode == RDT_MODE_PSEUDO_LOCKED) {
+		rdt_last_cmd_printf("cannot change pseudo-locked group\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!strcmp(buf, "shareable")) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			ret = rdtgroup_locksetup_exit(rdtgrp);
+			if (ret)
+				goto out;
+		}
+		rdtgrp->mode = RDT_MODE_SHAREABLE;
+	} else if (!strcmp(buf, "exclusive")) {
+		if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
+			rdt_last_cmd_printf("schemata overlaps\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			ret = rdtgroup_locksetup_exit(rdtgrp);
+			if (ret)
+				goto out;
+		}
+		rdtgrp->mode = RDT_MODE_EXCLUSIVE;
+	} else if (!strcmp(buf, "pseudo-locksetup")) {
+		ret = rdtgroup_locksetup_enter(rdtgrp);
+		if (ret)
+			goto out;
+		rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
+	} else {
+		rdt_last_cmd_printf("unknown/unsupported mode\n");
+		ret = -EINVAL;
+	}
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+	return ret ?: nbytes;
+}
+
+/**
+ * rdtgroup_cbm_to_size - Translate CBM to size in bytes
+ * @r: RDT resource to which @d belongs.
+ * @d: RDT domain instance.
+ * @cbm: bitmask for which the size should be computed.
+ *
+ * The bitmask provided associated with the RDT domain instance @d will be
+ * translated into how many bytes it represents. The size in bytes is
+ * computed by first dividing the total cache size by the CBM length to
+ * determine how many bytes each bit in the bitmask represents. The result
+ * is multiplied with the number of bits set in the bitmask.
+ */
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
+				  struct rdt_domain *d, u32 cbm)
+{
+	struct cpu_cacheinfo *ci;
+	unsigned int size = 0;
+	int num_b, i;
+
+	num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len);
+	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == r->cache_level) {
+			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
+			break;
+		}
+	}
+
+	return size;
+}
+
+/**
+ * rdtgroup_size_show - Display size in bytes of allocated regions
+ *
+ * The "size" file mirrors the layout of the "schemata" file, printing the
+ * size in bytes of each region instead of the capacity bitmask.
+ *
+ */
+static int rdtgroup_size_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+	unsigned int size;
+	bool sep = false;
+	u32 cbm;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+		seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name);
+		size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+					    rdtgrp->plr->d,
+					    rdtgrp->plr->cbm);
+		seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+		goto out;
+	}
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		seq_printf(s, "%*s:", max_name_width, r->name);
+		list_for_each_entry(d, &r->domains, list) {
+			if (sep)
+				seq_putc(s, ';');
+			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+				size = 0;
+			} else {
+				cbm = d->ctrl_val[rdtgrp->closid];
+				size = rdtgroup_cbm_to_size(r, d, cbm);
+			}
+			seq_printf(s, "%d=%u", d->id, size);
+			sep = true;
+		}
+		seq_putc(s, '\n');
+	}
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+
+	return 0;
+}
+
 /* rdtgroup information files for one cache resource. */
 static struct rftype res_common_files[] = {
 	{
@@ -792,6 +1247,13 @@ static struct rftype res_common_files[] = {
 		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
 	},
 	{
+		.name		= "bit_usage",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_bit_usage_show,
+		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
+	},
+	{
 		.name		= "min_bandwidth",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -853,6 +1315,22 @@ static struct rftype res_common_files[] = {
 		.seq_show	= rdtgroup_schemata_show,
 		.fflags		= RF_CTRL_BASE,
 	},
+	{
+		.name		= "mode",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_mode_write,
+		.seq_show	= rdtgroup_mode_show,
+		.fflags		= RF_CTRL_BASE,
+	},
+	{
+		.name		= "size",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdtgroup_size_show,
+		.fflags		= RF_CTRL_BASE,
+	},
+
 };
 
 static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
@@ -883,6 +1361,103 @@ error:
 	return ret;
 }
 
+/**
+ * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ *
+ * The permissions of named resctrl file, directory, or link are modified
+ * to not allow read, write, or execute by any user.
+ *
+ * WARNING: This function is intended to communicate to the user that the
+ * resctrl file has been locked down - that it is not relevant to the
+ * particular state the system finds itself in. It should not be relied
+ * on to protect from user access because after the file's permissions
+ * are restricted the user can still change the permissions using chmod
+ * from the command line.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
+{
+	struct iattr iattr = {.ia_valid = ATTR_MODE,};
+	struct kernfs_node *kn;
+	int ret = 0;
+
+	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+	if (!kn)
+		return -ENOENT;
+
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		iattr.ia_mode = S_IFDIR;
+		break;
+	case KERNFS_FILE:
+		iattr.ia_mode = S_IFREG;
+		break;
+	case KERNFS_LINK:
+		iattr.ia_mode = S_IFLNK;
+		break;
+	}
+
+	ret = kernfs_setattr(kn, &iattr);
+	kernfs_put(kn);
+	return ret;
+}
+
+/**
+ * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ * @mask: Mask of permissions that should be restored
+ *
+ * Restore the permissions of the named file. If @name is a directory the
+ * permissions of its parent will be used.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+			     umode_t mask)
+{
+	struct iattr iattr = {.ia_valid = ATTR_MODE,};
+	struct kernfs_node *kn, *parent;
+	struct rftype *rfts, *rft;
+	int ret, len;
+
+	rfts = res_common_files;
+	len = ARRAY_SIZE(res_common_files);
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		if (!strcmp(rft->name, name))
+			iattr.ia_mode = rft->mode & mask;
+	}
+
+	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+	if (!kn)
+		return -ENOENT;
+
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		parent = kernfs_get_parent(kn);
+		if (parent) {
+			iattr.ia_mode |= parent->mode;
+			kernfs_put(parent);
+		}
+		iattr.ia_mode |= S_IFDIR;
+		break;
+	case KERNFS_FILE:
+		iattr.ia_mode |= S_IFREG;
+		break;
+	case KERNFS_LINK:
+		iattr.ia_mode |= S_IFLNK;
+		break;
+	}
+
+	ret = kernfs_setattr(kn, &iattr);
+	kernfs_put(kn);
+	return ret;
+}
+
 static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
 				      unsigned long fflags)
 {
@@ -1224,6 +1799,9 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 
 	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
 	    (rdtgrp->flags & RDT_DELETED)) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
 		kernfs_unbreak_active_protection(kn);
 		kernfs_put(rdtgrp->kn);
 		kfree(rdtgrp);
@@ -1289,10 +1867,16 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 		rdtgroup_default.mon.mon_data_kn = kn_mondata;
 	}
 
+	ret = rdt_pseudo_lock_init();
+	if (ret) {
+		dentry = ERR_PTR(ret);
+		goto out_mondata;
+	}
+
 	dentry = kernfs_mount(fs_type, flags, rdt_root,
 			      RDTGROUP_SUPER_MAGIC, NULL);
 	if (IS_ERR(dentry))
-		goto out_mondata;
+		goto out_psl;
 
 	if (rdt_alloc_capable)
 		static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
@@ -1310,6 +1894,8 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 
 	goto out;
 
+out_psl:
+	rdt_pseudo_lock_release();
 out_mondata:
 	if (rdt_mon_capable)
 		kernfs_remove(kn_mondata);
@@ -1447,6 +2033,10 @@ static void rmdir_all_sub(void)
 		if (rdtgrp == &rdtgroup_default)
 			continue;
 
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
+
 		/*
 		 * Give any CPUs back to the default group. We cannot copy
 		 * cpu_online_mask because a CPU might have executed the
@@ -1483,6 +2073,8 @@ static void rdt_kill_sb(struct super_block *sb)
 		reset_all_ctrls(r);
 	cdp_disable_all();
 	rmdir_all_sub();
+	rdt_pseudo_lock_release();
+	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
 	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
 	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
 	static_branch_disable_cpuslocked(&rdt_enable_key);
@@ -1682,6 +2274,114 @@ out_destroy:
 	return ret;
 }
 
+/**
+ * cbm_ensure_valid - Enforce validity on provided CBM
+ * @_val:	Candidate CBM
+ * @r:		RDT resource to which the CBM belongs
+ *
+ * The provided CBM represents all cache portions available for use. This
+ * may be represented by a bitmap that does not consist of contiguous ones
+ * and thus be an invalid CBM.
+ * Here the provided CBM is forced to be a valid CBM by only considering
+ * the first set of contiguous bits as valid and clearing all bits.
+ * The intention here is to provide a valid default CBM with which a new
+ * resource group is initialized. The user can follow this with a
+ * modification to the CBM if the default does not satisfy the
+ * requirements.
+ */
+static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
+{
+	/*
+	 * Convert the u32 _val to an unsigned long required by all the bit
+	 * operations within this function. No more than 32 bits of this
+	 * converted value can be accessed because all bit operations are
+	 * additionally provided with cbm_len that is initialized during
+	 * hardware enumeration using five bits from the EAX register and
+	 * thus never can exceed 32 bits.
+	 */
+	unsigned long *val = (unsigned long *)_val;
+	unsigned int cbm_len = r->cache.cbm_len;
+	unsigned long first_bit, zero_bit;
+
+	if (*val == 0)
+		return;
+
+	first_bit = find_first_bit(val, cbm_len);
+	zero_bit = find_next_zero_bit(val, cbm_len, first_bit);
+
+	/* Clear any remaining bits to ensure contiguous region */
+	bitmap_clear(val, zero_bit, cbm_len - zero_bit);
+}
+
+/**
+ * rdtgroup_init_alloc - Initialize the new RDT group's allocations
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations. That is, all shareable and unused bits.
+ *
+ * All-zero CBM is invalid. If there are no more shareable bits available
+ * on any domain then the entire allocation will fail.
+ */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+	u32 used_b = 0, unused_b = 0;
+	u32 closid = rdtgrp->closid;
+	struct rdt_resource *r;
+	enum rdtgrp_mode mode;
+	struct rdt_domain *d;
+	int i, ret;
+	u32 *ctrl;
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		list_for_each_entry(d, &r->domains, list) {
+			d->have_new_ctrl = false;
+			d->new_ctrl = r->cache.shareable_bits;
+			used_b = r->cache.shareable_bits;
+			ctrl = d->ctrl_val;
+			for (i = 0; i < r->num_closid; i++, ctrl++) {
+				if (closid_allocated(i) && i != closid) {
+					mode = rdtgroup_mode_by_closid(i);
+					if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+						break;
+					used_b |= *ctrl;
+					if (mode == RDT_MODE_SHAREABLE)
+						d->new_ctrl |= *ctrl;
+				}
+			}
+			if (d->plr && d->plr->cbm > 0)
+				used_b |= d->plr->cbm;
+			unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+			unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+			d->new_ctrl |= unused_b;
+			/*
+			 * Force the initial CBM to be valid, user can
+			 * modify the CBM based on system availability.
+			 */
+			cbm_ensure_valid(&d->new_ctrl, r);
+			if (bitmap_weight((unsigned long *) &d->new_ctrl,
+					  r->cache.cbm_len) <
+					r->cache.min_cbm_bits) {
+				rdt_last_cmd_printf("no space on %s:%d\n",
+						    r->name, d->id);
+				return -ENOSPC;
+			}
+			d->have_new_ctrl = true;
+		}
+	}
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		ret = update_domains(r, rdtgrp->closid);
+		if (ret < 0) {
+			rdt_last_cmd_puts("failed to initialize allocations\n");
+			return ret;
+		}
+		rdtgrp->mode = RDT_MODE_SHAREABLE;
+	}
+
+	return 0;
+}
+
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 			     struct kernfs_node *prgrp_kn,
 			     const char *name, umode_t mode,
@@ -1700,6 +2400,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 		goto out_unlock;
 	}
 
+	if (rtype == RDTMON_GROUP &&
+	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		goto out_unlock;
+	}
+
 	/* allocate the rdtgroup. */
 	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
 	if (!rdtgrp) {
@@ -1840,6 +2548,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 	ret = 0;
 
 	rdtgrp->closid = closid;
+	ret = rdtgroup_init_alloc(rdtgrp);
+	if (ret < 0)
+		goto out_id_free;
+
 	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
 
 	if (rdt_mon_capable) {
@@ -1850,15 +2562,16 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 		ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL);
 		if (ret) {
 			rdt_last_cmd_puts("kernfs subdir error\n");
-			goto out_id_free;
+			goto out_del_list;
 		}
 	}
 
 	goto out_unlock;
 
+out_del_list:
+	list_del(&rdtgrp->rdtgroup_list);
 out_id_free:
 	closid_free(closid);
-	list_del(&rdtgrp->rdtgroup_list);
 out_common_fail:
 	mkdir_rdt_prepare_clean(rdtgrp);
 out_unlock:
@@ -1945,6 +2658,21 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	return 0;
 }
 
+static int rdtgroup_ctrl_remove(struct kernfs_node *kn,
+				struct rdtgroup *rdtgrp)
+{
+	rdtgrp->flags = RDT_DELETED;
+	list_del(&rdtgrp->rdtgroup_list);
+
+	/*
+	 * one extra hold on this, will drop when we kfree(rdtgrp)
+	 * in rdtgroup_kn_unlock()
+	 */
+	kernfs_get(kn);
+	kernfs_remove(rdtgrp->kn);
+	return 0;
+}
+
 static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 			       cpumask_var_t tmpmask)
 {
@@ -1970,7 +2698,6 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
 	update_closid_rmid(tmpmask, NULL);
 
-	rdtgrp->flags = RDT_DELETED;
 	closid_free(rdtgrp->closid);
 	free_rmid(rdtgrp->mon.rmid);
 
@@ -1979,14 +2706,7 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	 */
 	free_all_child_rdtgrp(rdtgrp);
 
-	list_del(&rdtgrp->rdtgroup_list);
-
-	/*
-	 * one extra hold on this, will drop when we kfree(rdtgrp)
-	 * in rdtgroup_kn_unlock()
-	 */
-	kernfs_get(kn);
-	kernfs_remove(rdtgrp->kn);
+	rdtgroup_ctrl_remove(kn, rdtgrp);
 
 	return 0;
 }
@@ -2014,13 +2734,19 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	 * If the rdtgroup is a mon group and parent directory
 	 * is a valid "mon_groups" directory, remove the mon group.
 	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn)
-		ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
-	else if (rdtgrp->type == RDTMON_GROUP &&
-		 is_mon_groups(parent_kn, kn->name))
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			ret = rdtgroup_ctrl_remove(kn, rdtgrp);
+		} else {
+			ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
+		}
+	} else if (rdtgrp->type == RDTMON_GROUP &&
+		 is_mon_groups(parent_kn, kn->name)) {
 		ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask);
-	else
+	} else {
 		ret = -EPERM;
+	}
 
 out:
 	rdtgroup_kn_unlock(kn);
@@ -2046,7 +2772,8 @@ static int __init rdtgroup_setup_root(void)
 	int ret;
 
 	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
-				      KERNFS_ROOT_CREATE_DEACTIVATED,
+				      KERNFS_ROOT_CREATE_DEACTIVATED |
+				      KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
 				      &rdtgroup_default);
 	if (IS_ERR(rdt_root))
 		return PTR_ERR(rdt_root);
@@ -2102,6 +2829,29 @@ int __init rdtgroup_init(void)
 	if (ret)
 		goto cleanup_mountpoint;
 
+	/*
+	 * Adding the resctrl debugfs directory here may not be ideal since
+	 * it would let the resctrl debugfs directory appear on the debugfs
+	 * filesystem before the resctrl filesystem is mounted.
+	 * It may also be ok since that would enable debugging of RDT before
+	 * resctrl is mounted.
+	 * The reason why the debugfs directory is created here and not in
+	 * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and
+	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
+	 * (the lockdep class of inode->i_rwsem). Other filesystem
+	 * interactions (eg. SyS_getdents) have the lock ordering:
+	 * &sb->s_type->i_mutex_key --> &mm->mmap_sem
+	 * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex
+	 * is taken, thus creating dependency:
+	 * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause
+	 * issues considering the other two lock dependencies.
+	 * By creating the debugfs directory here we avoid a dependency
+	 * that may cause deadlock (even though file operations cannot
+	 * occur until the filesystem is mounted, but I do not know how to
+	 * tell lockdep that).
+	 */
+	debugfs_resctrl = debugfs_create_dir("resctrl", NULL);
+
 	return 0;
 
 cleanup_mountpoint:
@@ -2111,3 +2861,11 @@ cleanup_root:
 
 	return ret;
 }
+
+void __exit rdtgroup_exit(void)
+{
+	debugfs_remove_recursive(debugfs_resctrl);
+	unregister_filesystem(&rdt_fs_type);
+	sysfs_remove_mount_point(fs_kobj, "resctrl");
+	kernfs_destroy_root(rdt_root);
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index c102ad51025e..4b767284b7f5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -123,8 +123,8 @@ void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
-	/* We hope get_seconds stays lockless */
-	m->time = get_seconds();
+	/* need the internal __ version to avoid deadlocks */
+	m->time = __ktime_get_real_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
 	m->cpuid = cpuid_eax(1);
 	m->socketid = cpu_data(m->extcpu).phys_proc_id;
@@ -1104,6 +1104,101 @@ static void mce_unmap_kpfn(unsigned long pfn)
 }
 #endif
 
+
+/*
+ * Cases where we avoid rendezvous handler timeout:
+ * 1) If this CPU is offline.
+ *
+ * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+ *  skip those CPUs which remain looping in the 1st kernel - see
+ *  crash_nmi_callback().
+ *
+ * Note: there still is a small window between kexec-ing and the new,
+ * kdump kernel establishing a new #MC handler where a broadcasted MCE
+ * might not get handled properly.
+ */
+static bool __mc_check_crashing_cpu(int cpu)
+{
+	if (cpu_is_offline(cpu) ||
+	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
+		u64 mcgstatus;
+
+		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+		if (mcgstatus & MCG_STATUS_RIPV) {
+			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+			return true;
+		}
+	}
+	return false;
+}
+
+static void __mc_scan_banks(struct mce *m, struct mce *final,
+			    unsigned long *toclear, unsigned long *valid_banks,
+			    int no_way_out, int *worst)
+{
+	struct mca_config *cfg = &mca_cfg;
+	int severity, i;
+
+	for (i = 0; i < cfg->banks; i++) {
+		__clear_bit(i, toclear);
+		if (!test_bit(i, valid_banks))
+			continue;
+
+		if (!mce_banks[i].ctl)
+			continue;
+
+		m->misc = 0;
+		m->addr = 0;
+		m->bank = i;
+
+		m->status = mce_rdmsrl(msr_ops.status(i));
+		if (!(m->status & MCI_STATUS_VAL))
+			continue;
+
+		/*
+		 * Corrected or non-signaled errors are handled by
+		 * machine_check_poll(). Leave them alone, unless this panics.
+		 */
+		if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
+			!no_way_out)
+			continue;
+
+		/* Set taint even when machine check was not enabled. */
+		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
+		severity = mce_severity(m, cfg->tolerant, NULL, true);
+
+		/*
+		 * When machine check was for corrected/deferred handler don't
+		 * touch, unless we're panicking.
+		 */
+		if ((severity == MCE_KEEP_SEVERITY ||
+		     severity == MCE_UCNA_SEVERITY) && !no_way_out)
+			continue;
+
+		__set_bit(i, toclear);
+
+		/* Machine check event was not enabled. Clear, but ignore. */
+		if (severity == MCE_NO_SEVERITY)
+			continue;
+
+		mce_read_aux(m, i);
+
+		/* assuming valid severity level != 0 */
+		m->severity = severity;
+
+		mce_log(m);
+
+		if (severity > *worst) {
+			*final = *m;
+			*worst = severity;
+		}
+	}
+
+	/* mce_clear_state will clear *final, save locally for use later */
+	*m = *final;
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1118,68 +1213,45 @@ static void mce_unmap_kpfn(unsigned long pfn)
  */
 void do_machine_check(struct pt_regs *regs, long error_code)
 {
+	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
+	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	struct mca_config *cfg = &mca_cfg;
+	int cpu = smp_processor_id();
+	char *msg = "Unknown";
 	struct mce m, *final;
-	int i;
 	int worst = 0;
-	int severity;
 
 	/*
 	 * Establish sequential order between the CPUs entering the machine
 	 * check handler.
 	 */
 	int order = -1;
+
 	/*
 	 * If no_way_out gets set, there is no safe way to recover from this
 	 * MCE.  If mca_cfg.tolerant is cranked up, we'll try anyway.
 	 */
 	int no_way_out = 0;
+
 	/*
 	 * If kill_it gets set, there might be a way to recover from this
 	 * error.
 	 */
 	int kill_it = 0;
-	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
-	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
-	char *msg = "Unknown";
 
 	/*
 	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
 	 * on Intel.
 	 */
 	int lmce = 1;
-	int cpu = smp_processor_id();
-
-	/*
-	 * Cases where we avoid rendezvous handler timeout:
-	 * 1) If this CPU is offline.
-	 *
-	 * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
-	 *  skip those CPUs which remain looping in the 1st kernel - see
-	 *  crash_nmi_callback().
-	 *
-	 * Note: there still is a small window between kexec-ing and the new,
-	 * kdump kernel establishing a new #MC handler where a broadcasted MCE
-	 * might not get handled properly.
-	 */
-	if (cpu_is_offline(cpu) ||
-	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
-		u64 mcgstatus;
 
-		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
-		if (mcgstatus & MCG_STATUS_RIPV) {
-			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
-			return;
-		}
-	}
+	if (__mc_check_crashing_cpu(cpu))
+		return;
 
 	ist_enter(regs);
 
 	this_cpu_inc(mce_exception_count);
 
-	if (!cfg->banks)
-		goto out;
-
 	mce_gather_info(&m, regs);
 	m.tsc = rdtsc();
 
@@ -1220,67 +1292,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		order = mce_start(&no_way_out);
 	}
 
-	for (i = 0; i < cfg->banks; i++) {
-		__clear_bit(i, toclear);
-		if (!test_bit(i, valid_banks))
-			continue;
-		if (!mce_banks[i].ctl)
-			continue;
-
-		m.misc = 0;
-		m.addr = 0;
-		m.bank = i;
-
-		m.status = mce_rdmsrl(msr_ops.status(i));
-		if ((m.status & MCI_STATUS_VAL) == 0)
-			continue;
-
-		/*
-		 * Non uncorrected or non signaled errors are handled by
-		 * machine_check_poll. Leave them alone, unless this panics.
-		 */
-		if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
-			!no_way_out)
-			continue;
-
-		/*
-		 * Set taint even when machine check was not enabled.
-		 */
-		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
-
-		severity = mce_severity(&m, cfg->tolerant, NULL, true);
-
-		/*
-		 * When machine check was for corrected/deferred handler don't
-		 * touch, unless we're panicing.
-		 */
-		if ((severity == MCE_KEEP_SEVERITY ||
-		     severity == MCE_UCNA_SEVERITY) && !no_way_out)
-			continue;
-		__set_bit(i, toclear);
-		if (severity == MCE_NO_SEVERITY) {
-			/*
-			 * Machine check event was not enabled. Clear, but
-			 * ignore.
-			 */
-			continue;
-		}
-
-		mce_read_aux(&m, i);
-
-		/* assuming valid severity level != 0 */
-		m.severity = severity;
-
-		mce_log(&m);
-
-		if (severity > worst) {
-			*final = m;
-			worst = severity;
-		}
-	}
-
-	/* mce_clear_state will clear *final, save locally for use later */
-	m = *final;
+	__mc_scan_banks(&m, final, toclear, valid_banks, no_way_out, &worst);
 
 	if (!no_way_out)
 		mce_clear_state(toclear);
@@ -1319,7 +1331,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	if (worst > 0)
 		mce_report_event(regs);
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
-out:
+
 	sync_core();
 
 	if (worst != MCE_AR_SEVERITY && !kill_it)
@@ -2165,9 +2177,6 @@ static ssize_t store_int_with_restart(struct device *s,
 	if (check_interval == old_check_interval)
 		return ret;
 
-	if (check_interval < 1)
-		check_interval = 1;
-
 	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
 	mutex_unlock(&mce_sysfs_mutex);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 08286269fd24..b9bc8a1a584e 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -509,12 +509,20 @@ static struct platform_device	*microcode_pdev;
 
 static int check_online_cpus(void)
 {
-	if (num_online_cpus() == num_present_cpus())
-		return 0;
+	unsigned int cpu;
 
-	pr_err("Not all CPUs online, aborting microcode update.\n");
+	/*
+	 * Make sure all CPUs are online.  It's fine for SMT to be disabled if
+	 * all the primary threads are still online.
+	 */
+	for_each_present_cpu(cpu) {
+		if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) {
+			pr_err("Not all CPUs online, aborting microcode update.\n");
+			return -EINVAL;
+		}
+	}
 
-	return -EINVAL;
+	return 0;
 }
 
 static atomic_t late_cpus_in;
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 4021d3859499..40eee6cc4124 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -106,7 +106,8 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 
 	memset(line, 0, LINE_SIZE);
 
-	length = strncpy_from_user(line, buf, LINE_SIZE - 1);
+	len = min_t(size_t, len, LINE_SIZE - 1);
+	length = strncpy_from_user(line, buf, len);
 	if (length < 0)
 		return length;
 
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 81c0afb39d0a..71ca064e3794 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -22,18 +22,10 @@
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 #define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
 
-/*
- * Check for extended topology enumeration cpuid leaf 0xb and if it
- * exists, use it for populating initial_apicid and cpu topology
- * detection.
- */
-int detect_extended_topology(struct cpuinfo_x86 *c)
+int detect_extended_topology_early(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
-	unsigned int eax, ebx, ecx, edx, sub_index;
-	unsigned int ht_mask_width, core_plus_mask_width;
-	unsigned int core_select_mask, core_level_siblings;
-	static bool printed;
+	unsigned int eax, ebx, ecx, edx;
 
 	if (c->cpuid_level < 0xb)
 		return -1;
@@ -52,10 +44,30 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	 * initial apic id, which also represents 32-bit extended x2apic id.
 	 */
 	c->initial_apicid = edx;
+	smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+#endif
+	return 0;
+}
+
+/*
+ * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * exists, use it for populating initial_apicid and cpu topology
+ * detection.
+ */
+int detect_extended_topology(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int eax, ebx, ecx, edx, sub_index;
+	unsigned int ht_mask_width, core_plus_mask_width;
+	unsigned int core_select_mask, core_level_siblings;
+
+	if (detect_extended_topology_early(c) < 0)
+		return -1;
 
 	/*
 	 * Populate HT related information from sub-leaf level 0.
 	 */
+	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
@@ -86,15 +98,6 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 
 	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
-
-	if (!printed) {
-		pr_info("CPU: Physical Processor ID: %d\n",
-		       c->phys_proc_id);
-		if (c->x86_max_cores > 1)
-			pr_info("CPU: Processor Core ID: %d\n",
-			       c->cpu_core_id);
-		printed = 1;
-	}
 #endif
 	return 0;
 }
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 666a284116ac..9c8652974f8e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -22,8 +22,6 @@
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
-#define OPCODE_BUFSIZE 64
-
 int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
 static int die_counter;
@@ -93,26 +91,18 @@ static void printk_stack_address(unsigned long address, int reliable,
  */
 void show_opcodes(u8 *rip, const char *loglvl)
 {
-	unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3;
+#define PROLOGUE_SIZE 42
+#define EPILOGUE_SIZE 21
+#define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
 	u8 opcodes[OPCODE_BUFSIZE];
-	u8 *ip;
-	int i;
-
-	printk("%sCode: ", loglvl);
-
-	ip = (u8 *)rip - code_prologue;
-	if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) {
-		pr_cont("Bad RIP value.\n");
-		return;
-	}
 
-	for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) {
-		if (ip == rip)
-			pr_cont("<%02x> ", opcodes[i]);
-		else
-			pr_cont("%02x ", opcodes[i]);
+	if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) {
+		printk("%sCode: Bad RIP value.\n", loglvl);
+	} else {
+		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
+		       __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes,
+		       opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1);
 	}
-	pr_cont("\n");
 }
 
 void show_ip(struct pt_regs *regs, const char *loglvl)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index d1f25c831447..c88c23c658c1 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1248,6 +1248,7 @@ void __init e820__memblock_setup(void)
 {
 	int i;
 	u64 end;
+	u64 addr = 0;
 
 	/*
 	 * The bootstrap memblock region count maximum is 128 entries
@@ -1264,13 +1265,21 @@ void __init e820__memblock_setup(void)
 		struct e820_entry *entry = &e820_table->entries[i];
 
 		end = entry->addr + entry->size;
+		if (addr < entry->addr)
+			memblock_reserve(addr, entry->addr - addr);
+		addr = end;
 		if (end != (resource_size_t)end)
 			continue;
 
+		/*
+		 * all !E820_TYPE_RAM ranges (including gap ranges) are put
+		 * into memblock.reserved to make sure that struct pages in
+		 * such regions are not left uninitialized after bootup.
+		 */
 		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
-			continue;
-
-		memblock_add(entry->addr, entry->size);
+			memblock_reserve(entry->addr, entry->size);
+		else
+			memblock_add(entry->addr, entry->size);
 	}
 
 	/* Throw away partial pages: */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index f92a6593de1e..2ea85b32421a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -10,6 +10,7 @@
 #include <asm/fpu/signal.h>
 #include <asm/fpu/types.h>
 #include <asm/traps.h>
+#include <asm/irq_regs.h>
 
 #include <linux/hardirq.h>
 #include <linux/pkeys.h>
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index abe6df15a8fb..30f9cb2c0b55 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -512,11 +512,18 @@ ENTRY(initial_code)
 ENTRY(setup_once_ref)
 	.long setup_once
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#define	PGD_ALIGN	(2 * PAGE_SIZE)
+#define PTI_USER_PGD_FILL	1024
+#else
+#define	PGD_ALIGN	(PAGE_SIZE)
+#define PTI_USER_PGD_FILL	0
+#endif
 /*
  * BSS section
  */
 __PAGE_ALIGNED_BSS
-	.align PAGE_SIZE
+	.align PGD_ALIGN
 #ifdef CONFIG_X86_PAE
 .globl initial_pg_pmd
 initial_pg_pmd:
@@ -526,14 +533,17 @@ initial_pg_pmd:
 initial_page_table:
 	.fill 1024,4,0
 #endif
+	.align PGD_ALIGN
 initial_pg_fixmap:
 	.fill 1024,4,0
-.globl empty_zero_page
-empty_zero_page:
-	.fill 4096,1,0
 .globl swapper_pg_dir
+	.align PGD_ALIGN
 swapper_pg_dir:
 	.fill 1024,4,0
+	.fill PTI_USER_PGD_FILL,4,0
+.globl empty_zero_page
+empty_zero_page:
+	.fill 4096,1,0
 EXPORT_SYMBOL(empty_zero_page)
 
 /*
@@ -542,7 +552,7 @@ EXPORT_SYMBOL(empty_zero_page)
 #ifdef CONFIG_X86_PAE
 __PAGE_ALIGNED_DATA
 	/* Page-aligned for the benefit of paravirt? */
-	.align PAGE_SIZE
+	.align PGD_ALIGN
 ENTRY(initial_page_table)
 	.long	pa(initial_pg_pmd+PGD_IDENT_ATTR),0	/* low identity map */
 # if KPMDS == 3
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 8344dd2f310a..15ebc2fc166e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -235,7 +235,7 @@ ENTRY(secondary_startup_64)
 	 *		address given in m16:64.
 	 */
 	pushq	$.Lafter_lret	# put return address on stack for unwinder
-	xorq	%rbp, %rbp	# clear frame pointer
+	xorl	%ebp, %ebp	# clear frame pointer
 	movq	initial_code(%rip), %rax
 	pushq	$__KERNEL_CS	# set correct cs
 	pushq	%rax		# target address in negative space
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 346b24883911..b0acb22e5a46 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1,6 +1,7 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 8771766d46b6..34a5c1715148 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -169,28 +169,29 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 		set_dr_addr_mask(0, i);
 }
 
-/*
- * Check for virtual address in kernel space.
- */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+static int arch_bp_generic_len(int x86_len)
 {
-	unsigned int len;
-	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	va = info->address;
-	len = bp->attr.bp_len;
-
-	/*
-	 * We don't need to worry about va + len - 1 overflowing:
-	 * we already require that va is aligned to a multiple of len.
-	 */
-	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+	switch (x86_len) {
+	case X86_BREAKPOINT_LEN_1:
+		return HW_BREAKPOINT_LEN_1;
+	case X86_BREAKPOINT_LEN_2:
+		return HW_BREAKPOINT_LEN_2;
+	case X86_BREAKPOINT_LEN_4:
+		return HW_BREAKPOINT_LEN_4;
+#ifdef CONFIG_X86_64
+	case X86_BREAKPOINT_LEN_8:
+		return HW_BREAKPOINT_LEN_8;
+#endif
+	default:
+		return -EINVAL;
+	}
 }
 
 int arch_bp_generic_fields(int x86_len, int x86_type,
 			   int *gen_len, int *gen_type)
 {
+	int len;
+
 	/* Type */
 	switch (x86_type) {
 	case X86_BREAKPOINT_EXECUTE:
@@ -211,42 +212,47 @@ int arch_bp_generic_fields(int x86_len, int x86_type,
 	}
 
 	/* Len */
-	switch (x86_len) {
-	case X86_BREAKPOINT_LEN_1:
-		*gen_len = HW_BREAKPOINT_LEN_1;
-		break;
-	case X86_BREAKPOINT_LEN_2:
-		*gen_len = HW_BREAKPOINT_LEN_2;
-		break;
-	case X86_BREAKPOINT_LEN_4:
-		*gen_len = HW_BREAKPOINT_LEN_4;
-		break;
-#ifdef CONFIG_X86_64
-	case X86_BREAKPOINT_LEN_8:
-		*gen_len = HW_BREAKPOINT_LEN_8;
-		break;
-#endif
-	default:
+	len = arch_bp_generic_len(x86_len);
+	if (len < 0)
 		return -EINVAL;
-	}
+	*gen_len = len;
 
 	return 0;
 }
 
-
-static int arch_build_bp_info(struct perf_event *bp)
+/*
+ * Check for virtual address in kernel space.
+ */
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	unsigned long va;
+	int len;
 
-	info->address = bp->attr.bp_addr;
+	va = hw->address;
+	len = arch_bp_generic_len(hw->len);
+	WARN_ON_ONCE(len < 0);
+
+	/*
+	 * We don't need to worry about va + len - 1 overflowing:
+	 * we already require that va is aligned to a multiple of len.
+	 */
+	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+}
+
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
+{
+	hw->address = attr->bp_addr;
+	hw->mask = 0;
 
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_W:
-		info->type = X86_BREAKPOINT_WRITE;
+		hw->type = X86_BREAKPOINT_WRITE;
 		break;
 	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
-		info->type = X86_BREAKPOINT_RW;
+		hw->type = X86_BREAKPOINT_RW;
 		break;
 	case HW_BREAKPOINT_X:
 		/*
@@ -254,23 +260,23 @@ static int arch_build_bp_info(struct perf_event *bp)
 		 * acceptable for kprobes.  On non-kprobes kernels, we don't
 		 * allow kernel breakpoints at all.
 		 */
-		if (bp->attr.bp_addr >= TASK_SIZE_MAX) {
+		if (attr->bp_addr >= TASK_SIZE_MAX) {
 #ifdef CONFIG_KPROBES
-			if (within_kprobe_blacklist(bp->attr.bp_addr))
+			if (within_kprobe_blacklist(attr->bp_addr))
 				return -EINVAL;
 #else
 			return -EINVAL;
 #endif
 		}
 
-		info->type = X86_BREAKPOINT_EXECUTE;
+		hw->type = X86_BREAKPOINT_EXECUTE;
 		/*
 		 * x86 inst breakpoints need to have a specific undefined len.
 		 * But we still need to check userspace is not trying to setup
 		 * an unsupported length, to get a range breakpoint for example.
 		 */
-		if (bp->attr.bp_len == sizeof(long)) {
-			info->len = X86_BREAKPOINT_LEN_X;
+		if (attr->bp_len == sizeof(long)) {
+			hw->len = X86_BREAKPOINT_LEN_X;
 			return 0;
 		}
 	default:
@@ -278,28 +284,26 @@ static int arch_build_bp_info(struct perf_event *bp)
 	}
 
 	/* Len */
-	info->mask = 0;
-
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->len = X86_BREAKPOINT_LEN_1;
+		hw->len = X86_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->len = X86_BREAKPOINT_LEN_2;
+		hw->len = X86_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->len = X86_BREAKPOINT_LEN_4;
+		hw->len = X86_BREAKPOINT_LEN_4;
 		break;
 #ifdef CONFIG_X86_64
 	case HW_BREAKPOINT_LEN_8:
-		info->len = X86_BREAKPOINT_LEN_8;
+		hw->len = X86_BREAKPOINT_LEN_8;
 		break;
 #endif
 	default:
 		/* AMD range breakpoint */
-		if (!is_power_of_2(bp->attr.bp_len))
+		if (!is_power_of_2(attr->bp_len))
 			return -EINVAL;
-		if (bp->attr.bp_addr & (bp->attr.bp_len - 1))
+		if (attr->bp_addr & (attr->bp_len - 1))
 			return -EINVAL;
 
 		if (!boot_cpu_has(X86_FEATURE_BPEXT))
@@ -312,8 +316,8 @@ static int arch_build_bp_info(struct perf_event *bp)
 		 * breakpoints, then we'll have to check for kprobe-blacklisted
 		 * addresses anywhere in the range.
 		 */
-		info->mask = bp->attr.bp_len - 1;
-		info->len = X86_BREAKPOINT_LEN_1;
+		hw->mask = attr->bp_len - 1;
+		hw->len = X86_BREAKPOINT_LEN_1;
 	}
 
 	return 0;
@@ -322,22 +326,23 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
 	int ret;
 
 
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
-	switch (info->len) {
+	switch (hw->len) {
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
-		if (info->mask)
-			align = info->mask;
+		if (hw->mask)
+			align = hw->mask;
 		break;
 	case X86_BREAKPOINT_LEN_2:
 		align = 1;
@@ -358,7 +363,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
 	 */
-	if (info->address & align)
+	if (hw->address & align)
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 86c4439f9d74..519649ddf100 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/timex.h>
 #include <linux/random.h>
 #include <linux/init.h>
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 74383a3780dc..01adea278a71 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -8,6 +8,7 @@
 #include <asm/traps.h>
 #include <asm/proto.h>
 #include <asm/desc.h>
+#include <asm/hw_irq.h>
 
 struct idt_data {
 	unsigned int	vector;
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 328d027d829d..59b5f2ea7c2f 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -10,6 +10,7 @@
 #include <linux/ftrace.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/irq.h>
 
 #include <asm/apic.h>
 #include <asm/io_apic.h>
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index c1bdbd3d3232..95600a99ae93 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -11,6 +11,7 @@
 
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kernel_stat.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index d86e344f5b3d..0469cd078db1 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -11,6 +11,7 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/delay.h>
 #include <linux/ftrace.h>
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
new file mode 100644
index 000000000000..ddeeaac8adda
--- /dev/null
+++ b/arch/x86/kernel/irqflags.S
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/asm.h>
+#include <asm/export.h>
+#include <linux/linkage.h>
+
+/*
+ * unsigned long native_save_fl(void)
+ */
+ENTRY(native_save_fl)
+	pushf
+	pop %_ASM_AX
+	ret
+ENDPROC(native_save_fl)
+EXPORT_SYMBOL(native_save_fl)
+
+/*
+ * void native_restore_fl(unsigned long flags)
+ * %eax/%rdi: flags
+ */
+ENTRY(native_restore_fl)
+	push %_ASM_ARG1
+	popf
+	ret
+ENDPROC(native_restore_fl)
+EXPORT_SYMBOL(native_restore_fl)
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 772196c1b8c4..a0693b71cfc1 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/timex.h>
 #include <linux/random.h>
 #include <linux/kprobes.h>
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index e56c95be2808..eeea935e9bb5 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -37,15 +37,18 @@ static void bug_at(unsigned char *ip, int line)
 	BUG();
 }
 
-static void __jump_label_transform(struct jump_entry *entry,
-				   enum jump_label_type type,
-				   void *(*poker)(void *, const void *, size_t),
-				   int init)
+static void __ref __jump_label_transform(struct jump_entry *entry,
+					 enum jump_label_type type,
+					 void *(*poker)(void *, const void *, size_t),
+					 int init)
 {
 	union jump_code_union code;
 	const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
 	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
 
+	if (early_boot_irqs_disabled)
+		poker = text_poke_early;
+
 	if (type == JUMP_LABEL_JMP) {
 		if (init) {
 			/*
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index ae38dccf0c8f..2b949f4fd4d8 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -105,14 +105,4 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig
 }
 #endif
 
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			   struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				  struct kprobe_ctlblk *kcb)
-{
-	return 0;
-}
-#endif
 #endif
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6f4d42377fe5..b0d1e81c96bb 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -66,8 +66,6 @@
 
 #include "common.h"
 
-void jprobe_return_end(void);
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -395,8 +393,6 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 			  - (u8 *) real;
 		if ((s64) (s32) newdisp != newdisp) {
 			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
-			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n",
-				src, real, insn->displacement.value);
 			return 0;
 		}
 		disp = (u8 *) dest + insn_offset_displacement(insn);
@@ -596,7 +592,6 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 		 * stepping.
 		 */
 		regs->ip = (unsigned long)p->ainsn.insn;
-		preempt_enable_no_resched();
 		return;
 	}
 #endif
@@ -640,8 +635,7 @@ static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
 		 * Raise a BUG or we'll continue in an endless reentering loop
 		 * and eventually a stack overflow.
 		 */
-		printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
-		       p->addr);
+		pr_err("Unrecoverable kprobe detected.\n");
 		dump_kprobe(p);
 		BUG();
 	default:
@@ -669,12 +663,10 @@ int kprobe_int3_handler(struct pt_regs *regs)
 
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
 	/*
-	 * We don't want to be preempted for the entire
-	 * duration of kprobe processing. We conditionally
-	 * re-enable preemption at the end of this function,
-	 * and also in reenter_kprobe() and setup_singlestep().
+	 * We don't want to be preempted for the entire duration of kprobe
+	 * processing. Since int3 and debug trap disables irqs and we clear
+	 * IF while singlestepping, it must be no preemptible.
 	 */
-	preempt_disable();
 
 	kcb = get_kprobe_ctlblk();
 	p = get_kprobe(addr);
@@ -690,13 +682,14 @@ int kprobe_int3_handler(struct pt_regs *regs)
 			/*
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry
-			 * for jprobe processing, so get out doing nothing
-			 * more here.
+			 * pre-handler and it returned non-zero, that means
+			 * user handler setup registers to exit to another
+			 * instruction, we must skip the single stepping.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs))
 				setup_singlestep(p, regs, kcb, 0);
+			else
+				reset_current_kprobe();
 			return 1;
 		}
 	} else if (*addr != BREAKPOINT_INSTRUCTION) {
@@ -710,18 +703,9 @@ int kprobe_int3_handler(struct pt_regs *regs)
 		 * the original instruction.
 		 */
 		regs->ip = (unsigned long)addr;
-		preempt_enable_no_resched();
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			if (!skip_singlestep(p, regs, kcb))
-				setup_singlestep(p, regs, kcb, 0);
-			return 1;
-		}
 	} /* else: not a kprobe fault; let the kernel handle it */
 
-	preempt_enable_no_resched();
 	return 0;
 }
 NOKPROBE_SYMBOL(kprobe_int3_handler);
@@ -972,8 +956,6 @@ int kprobe_debug_handler(struct pt_regs *regs)
 	}
 	reset_current_kprobe();
 out:
-	preempt_enable_no_resched();
-
 	/*
 	 * if somebody else is singlestepping across a probe point, flags
 	 * will have TF set, in which case, continue the remaining processing
@@ -1020,7 +1002,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 			restore_previous_kprobe(kcb);
 		else
 			reset_current_kprobe();
-		preempt_enable_no_resched();
 	} else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
 		   kcb->kprobe_status == KPROBE_HIT_SSDONE) {
 		/*
@@ -1083,93 +1064,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
 }
 NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_sp = stack_addr(regs);
-	addr = (unsigned long)(kcb->jprobe_saved_sp);
-
-	/*
-	 * As Linus pointed out, gcc assumes that the callee
-	 * owns the argument space and could overwrite it, e.g.
-	 * tailcall optimization. So, to be absolutely safe
-	 * we also save and restore enough stack bytes to cover
-	 * the argument area.
-	 * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy
-	 * raw stack chunk with redzones:
-	 */
-	__memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
-	regs->ip = (unsigned long)(jp->entry);
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer to get messed up.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	/* Unpoison stack redzones in the frames we are going to jump over. */
-	kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp);
-
-	asm volatile (
-#ifdef CONFIG_X86_64
-			"       xchg   %%rbx,%%rsp	\n"
-#else
-			"       xchgl   %%ebx,%%esp	\n"
-#endif
-			"       int3			\n"
-			"       .globl jprobe_return_end\n"
-			"       jprobe_return_end:	\n"
-			"       nop			\n"::"b"
-			(kcb->jprobe_saved_sp):"memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-NOKPROBE_SYMBOL(jprobe_return_end);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	u8 *addr = (u8 *) (regs->ip - 1);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	void *saved_sp = kcb->jprobe_saved_sp;
-
-	if ((addr > (u8 *) jprobe_return) &&
-	    (addr < (u8 *) jprobe_return_end)) {
-		if (stack_addr(regs) != saved_sp) {
-			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
-			printk(KERN_ERR
-			       "current sp %p does not match saved sp %p\n",
-			       stack_addr(regs), saved_sp);
-			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk(KERN_ERR "Current registers\n");
-			show_regs(regs);
-			BUG();
-		}
-		/* It's OK to start function graph tracing again */
-		unpause_graph_tracing();
-		*regs = kcb->jprobe_saved_regs;
-		__memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	bool is_in_entry_trampoline_section = false;
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 8dc0161cec8f..ef819e19650b 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -25,36 +25,6 @@
 
 #include "common.h"
 
-static nokprobe_inline
-void __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		      struct kprobe_ctlblk *kcb, unsigned long orig_ip)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->ip)
-	 * as if there is a 5byte nop
-	 */
-	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-	if (orig_ip)
-		regs->ip = orig_ip;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		    struct kprobe_ctlblk *kcb)
-{
-	if (kprobe_ftrace(p)) {
-		__skip_singlestep(p, regs, kcb, 0);
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
 /* Ftrace callback handler for kprobes -- called under preepmt disabed */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 			   struct ftrace_ops *ops, struct pt_regs *regs)
@@ -75,18 +45,25 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
 		regs->ip = ip + sizeof(kprobe_opcode_t);
 
-		/* To emulate trap based kprobes, preempt_disable here */
-		preempt_disable();
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
-			__skip_singlestep(p, regs, kcb, orig_ip);
-			preempt_enable_no_resched();
+			/*
+			 * Emulate singlestep (and also recover regs->ip)
+			 * as if there is a 5byte nop
+			 */
+			regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
+			regs->ip = orig_ip;
 		}
 		/*
-		 * If pre_handler returns !0, it sets regs->ip and
-		 * resets current kprobe, and keep preempt count +1.
+		 * If pre_handler returns !0, it changes regs->ip. We have to
+		 * skip emulating post_handler.
 		 */
+		__this_cpu_write(current_kprobe, NULL);
 	}
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 203d398802a3..eaf02f2e7300 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -491,7 +491,6 @@ int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
 		if (!reenter)
 			reset_current_kprobe();
-		preempt_enable_no_resched();
 		return 1;
 	}
 	return 0;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5b2300b818af..09aaabb2bbf1 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -45,7 +45,6 @@
 #include <asm/apic.h>
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
-#include <asm/kvm_guest.h>
 
 static int kvmapf = 1;
 
@@ -66,15 +65,6 @@ static int __init parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
-static int kvmclock_vsyscall = 1;
-static int __init parse_no_kvmclock_vsyscall(char *arg)
-{
-        kvmclock_vsyscall = 0;
-        return 0;
-}
-
-early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
-
 static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
 static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64);
 static int has_steal_clock = 0;
@@ -154,7 +144,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
 
 	for (;;) {
 		if (!n.halted)
-			prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+			prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
 		if (hlist_unhashed(&n.link))
 			break;
 
@@ -188,7 +178,7 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
 	else if (swq_has_sleeper(&n->wq))
-		swake_up(&n->wq);
+		swake_up_one(&n->wq);
 }
 
 static void apf_task_wake_all(void)
@@ -560,9 +550,6 @@ static void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
 		apic_set_eoi_write(kvm_guest_apic_eoi_write);
 
-	if (kvmclock_vsyscall)
-		kvm_setup_vsyscall_timeinfo();
-
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
@@ -628,6 +615,7 @@ const __initconst struct hypervisor_x86 x86_hyper_kvm = {
 	.name			= "KVM",
 	.detect			= kvm_detect,
 	.type			= X86_HYPER_KVM,
+	.init.init_platform	= kvmclock_init,
 	.init.guest_late_init	= kvm_guest_init,
 	.init.x2apic_available	= kvm_para_available,
 };
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index bf8d1eb7fca3..1e6764648af3 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -23,30 +23,57 @@
 #include <asm/apic.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
-#include <linux/memblock.h>
+#include <linux/cpuhotplug.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
 
+#include <asm/hypervisor.h>
 #include <asm/mem_encrypt.h>
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 #include <asm/kvmclock.h>
 
-static int kvmclock __ro_after_init = 1;
-static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
-static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
-static u64 kvm_sched_clock_offset;
+static int kvmclock __initdata = 1;
+static int kvmclock_vsyscall __initdata = 1;
+static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
+static u64 kvm_sched_clock_offset __ro_after_init;
 
-static int parse_no_kvmclock(char *arg)
+static int __init parse_no_kvmclock(char *arg)
 {
 	kvmclock = 0;
 	return 0;
 }
 early_param("no-kvmclock", parse_no_kvmclock);
 
-/* The hypervisor will put information about time periodically here */
-static struct pvclock_vsyscall_time_info *hv_clock;
-static struct pvclock_wall_clock *wall_clock;
+static int __init parse_no_kvmclock_vsyscall(char *arg)
+{
+	kvmclock_vsyscall = 0;
+	return 0;
+}
+early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
+
+/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
+#define HV_CLOCK_SIZE	(sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
+#define HVC_BOOT_ARRAY_SIZE \
+	(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
+
+static struct pvclock_vsyscall_time_info
+			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE);
+static struct pvclock_wall_clock wall_clock;
+static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+
+static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+{
+	return &this_cpu_read(hv_clock_per_cpu)->pvti;
+}
+
+static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
+{
+	return this_cpu_read(hv_clock_per_cpu);
+}
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
@@ -55,21 +82,10 @@ static struct pvclock_wall_clock *wall_clock;
  */
 static void kvm_get_wallclock(struct timespec64 *now)
 {
-	struct pvclock_vcpu_time_info *vcpu_time;
-	int low, high;
-	int cpu;
-
-	low = (int)slow_virt_to_phys(wall_clock);
-	high = ((u64)slow_virt_to_phys(wall_clock) >> 32);
-
-	native_write_msr(msr_kvm_wall_clock, low, high);
-
-	cpu = get_cpu();
-
-	vcpu_time = &hv_clock[cpu].pvti;
-	pvclock_read_wallclock(wall_clock, vcpu_time, now);
-
-	put_cpu();
+	wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
+	preempt_disable();
+	pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now);
+	preempt_enable();
 }
 
 static int kvm_set_wallclock(const struct timespec64 *now)
@@ -79,14 +95,10 @@ static int kvm_set_wallclock(const struct timespec64 *now)
 
 static u64 kvm_clock_read(void)
 {
-	struct pvclock_vcpu_time_info *src;
 	u64 ret;
-	int cpu;
 
 	preempt_disable_notrace();
-	cpu = smp_processor_id();
-	src = &hv_clock[cpu].pvti;
-	ret = pvclock_clocksource_read(src);
+	ret = pvclock_clocksource_read(this_cpu_pvti());
 	preempt_enable_notrace();
 	return ret;
 }
@@ -112,11 +124,11 @@ static inline void kvm_sched_clock_init(bool stable)
 	kvm_sched_clock_offset = kvm_clock_read();
 	pv_time_ops.sched_clock = kvm_sched_clock_read;
 
-	printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
-			kvm_sched_clock_offset);
+	pr_info("kvm-clock: using sched offset of %llu cycles",
+		kvm_sched_clock_offset);
 
 	BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) >
-	         sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
+		sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
 }
 
 /*
@@ -130,18 +142,11 @@ static inline void kvm_sched_clock_init(bool stable)
  */
 static unsigned long kvm_get_tsc_khz(void)
 {
-	struct pvclock_vcpu_time_info *src;
-	int cpu;
-	unsigned long tsc_khz;
-
-	cpu = get_cpu();
-	src = &hv_clock[cpu].pvti;
-	tsc_khz = pvclock_tsc_khz(src);
-	put_cpu();
-	return tsc_khz;
+	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+	return pvclock_tsc_khz(this_cpu_pvti());
 }
 
-static void kvm_get_preset_lpj(void)
+static void __init kvm_get_preset_lpj(void)
 {
 	unsigned long khz;
 	u64 lpj;
@@ -155,49 +160,40 @@ static void kvm_get_preset_lpj(void)
 
 bool kvm_check_and_clear_guest_paused(void)
 {
+	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
 	bool ret = false;
-	struct pvclock_vcpu_time_info *src;
-	int cpu = smp_processor_id();
 
-	if (!hv_clock)
+	if (!src)
 		return ret;
 
-	src = &hv_clock[cpu].pvti;
-	if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
-		src->flags &= ~PVCLOCK_GUEST_STOPPED;
+	if ((src->pvti.flags & PVCLOCK_GUEST_STOPPED) != 0) {
+		src->pvti.flags &= ~PVCLOCK_GUEST_STOPPED;
 		pvclock_touch_watchdogs();
 		ret = true;
 	}
-
 	return ret;
 }
 
 struct clocksource kvm_clock = {
-	.name = "kvm-clock",
-	.read = kvm_clock_get_cycles,
-	.rating = 400,
-	.mask = CLOCKSOURCE_MASK(64),
-	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
+	.name	= "kvm-clock",
+	.read	= kvm_clock_get_cycles,
+	.rating	= 400,
+	.mask	= CLOCKSOURCE_MASK(64),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 EXPORT_SYMBOL_GPL(kvm_clock);
 
-int kvm_register_clock(char *txt)
+static void kvm_register_clock(char *txt)
 {
-	int cpu = smp_processor_id();
-	int low, high, ret;
-	struct pvclock_vcpu_time_info *src;
-
-	if (!hv_clock)
-		return 0;
+	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
+	u64 pa;
 
-	src = &hv_clock[cpu].pvti;
-	low = (int)slow_virt_to_phys(src) | 1;
-	high = ((u64)slow_virt_to_phys(src) >> 32);
-	ret = native_write_msr_safe(msr_kvm_system_time, low, high);
-	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
-	       cpu, high, low, txt);
+	if (!src)
+		return;
 
-	return ret;
+	pa = slow_virt_to_phys(&src->pvti) | 0x01ULL;
+	wrmsrl(msr_kvm_system_time, pa);
+	pr_info("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt);
 }
 
 static void kvm_save_sched_clock_state(void)
@@ -212,11 +208,7 @@ static void kvm_restore_sched_clock_state(void)
 #ifdef CONFIG_X86_LOCAL_APIC
 static void kvm_setup_secondary_clock(void)
 {
-	/*
-	 * Now that the first cpu already had this clocksource initialized,
-	 * we shouldn't fail.
-	 */
-	WARN_ON(kvm_register_clock("secondary cpu clock"));
+	kvm_register_clock("secondary cpu clock");
 }
 #endif
 
@@ -244,98 +236,84 @@ static void kvm_shutdown(void)
 	native_machine_shutdown();
 }
 
-static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size,
-					     phys_addr_t align)
+static int __init kvm_setup_vsyscall_timeinfo(void)
 {
-	phys_addr_t mem;
+#ifdef CONFIG_X86_64
+	u8 flags;
 
-	mem = memblock_alloc(size, align);
-	if (!mem)
+	if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
 		return 0;
 
-	if (sev_active()) {
-		if (early_set_memory_decrypted((unsigned long)__va(mem), size))
-			goto e_free;
-	}
+	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+		return 0;
 
-	return mem;
-e_free:
-	memblock_free(mem, size);
+	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
+#endif
 	return 0;
 }
+early_initcall(kvm_setup_vsyscall_timeinfo);
 
-static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size)
+static int kvmclock_setup_percpu(unsigned int cpu)
 {
-	if (sev_active())
-		early_set_memory_encrypted((unsigned long)__va(addr), size);
+	struct pvclock_vsyscall_time_info *p = per_cpu(hv_clock_per_cpu, cpu);
+
+	/*
+	 * The per cpu area setup replicates CPU0 data to all cpu
+	 * pointers. So carefully check. CPU0 has been set up in init
+	 * already.
+	 */
+	if (!cpu || (p && p != per_cpu(hv_clock_per_cpu, 0)))
+		return 0;
+
+	/* Use the static page for the first CPUs, allocate otherwise */
+	if (cpu < HVC_BOOT_ARRAY_SIZE)
+		p = &hv_clock_boot[cpu];
+	else
+		p = kzalloc(sizeof(*p), GFP_KERNEL);
 
-	memblock_free(addr, size);
+	per_cpu(hv_clock_per_cpu, cpu) = p;
+	return p ? 0 : -ENOMEM;
 }
 
 void __init kvmclock_init(void)
 {
-	struct pvclock_vcpu_time_info *vcpu_time;
-	unsigned long mem, mem_wall_clock;
-	int size, cpu, wall_clock_size;
 	u8 flags;
 
-	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
-	if (!kvm_para_available())
+	if (!kvm_para_available() || !kvmclock)
 		return;
 
-	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
 		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
 		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
-	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
-		return;
-
-	wall_clock_size = PAGE_ALIGN(sizeof(struct pvclock_wall_clock));
-	mem_wall_clock = kvm_memblock_alloc(wall_clock_size, PAGE_SIZE);
-	if (!mem_wall_clock)
-		return;
-
-	wall_clock = __va(mem_wall_clock);
-	memset(wall_clock, 0, wall_clock_size);
-
-	mem = kvm_memblock_alloc(size, PAGE_SIZE);
-	if (!mem) {
-		kvm_memblock_free(mem_wall_clock, wall_clock_size);
-		wall_clock = NULL;
+	} else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
 		return;
 	}
 
-	hv_clock = __va(mem);
-	memset(hv_clock, 0, size);
-
-	if (kvm_register_clock("primary cpu clock")) {
-		hv_clock = NULL;
-		kvm_memblock_free(mem, size);
-		kvm_memblock_free(mem_wall_clock, wall_clock_size);
-		wall_clock = NULL;
+	if (cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "kvmclock:setup_percpu",
+			      kvmclock_setup_percpu, NULL) < 0) {
 		return;
 	}
 
-	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+	pr_info("kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
+	this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]);
+	kvm_register_clock("primary cpu clock");
+	pvclock_set_pvti_cpu0_va(hv_clock_boot);
+
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
 		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 
-	cpu = get_cpu();
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-
+	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
 	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
-	put_cpu();
 
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
 	x86_platform.calibrate_cpu = kvm_get_tsc_khz;
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-	x86_cpuinit.early_percpu_clock_init =
-		kvm_setup_secondary_clock;
+	x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock;
 #endif
 	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
 	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
@@ -347,34 +325,3 @@ void __init kvmclock_init(void)
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
 	pv_info.name = "KVM";
 }
-
-int __init kvm_setup_vsyscall_timeinfo(void)
-{
-#ifdef CONFIG_X86_64
-	int cpu;
-	u8 flags;
-	struct pvclock_vcpu_time_info *vcpu_time;
-	unsigned int size;
-
-	if (!hv_clock)
-		return 0;
-
-	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
-	cpu = get_cpu();
-
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-
-	if (!(flags & PVCLOCK_TSC_STABLE_BIT)) {
-		put_cpu();
-		return 1;
-	}
-
-	pvclock_set_pvti_cpu0_va(hv_clock);
-	put_cpu();
-
-	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
-#endif
-	return 0;
-}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c9b14020f4dd..733e6ace0fa4 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -100,6 +100,102 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 	return new_ldt;
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+static void do_sanity_check(struct mm_struct *mm,
+			    bool had_kernel_mapping,
+			    bool had_user_mapping)
+{
+	if (mm->context.ldt) {
+		/*
+		 * We already had an LDT.  The top-level entry should already
+		 * have been allocated and synchronized with the usermode
+		 * tables.
+		 */
+		WARN_ON(!had_kernel_mapping);
+		if (static_cpu_has(X86_FEATURE_PTI))
+			WARN_ON(!had_user_mapping);
+	} else {
+		/*
+		 * This is the first time we're mapping an LDT for this process.
+		 * Sync the pgd to the usermode tables.
+		 */
+		WARN_ON(had_kernel_mapping);
+		if (static_cpu_has(X86_FEATURE_PTI))
+			WARN_ON(had_user_mapping);
+	}
+}
+
+#ifdef CONFIG_X86_PAE
+
+static pmd_t *pgd_to_pmd_walk(pgd_t *pgd, unsigned long va)
+{
+	p4d_t *p4d;
+	pud_t *pud;
+
+	if (pgd->pgd == 0)
+		return NULL;
+
+	p4d = p4d_offset(pgd, va);
+	if (p4d_none(*p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, va);
+	if (pud_none(*pud))
+		return NULL;
+
+	return pmd_offset(pud, va);
+}
+
+static void map_ldt_struct_to_user(struct mm_struct *mm)
+{
+	pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	pmd_t *k_pmd, *u_pmd;
+
+	k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
+	u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
+
+	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+		set_pmd(u_pmd, *k_pmd);
+}
+
+static void sanity_check_ldt_mapping(struct mm_struct *mm)
+{
+	pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	bool had_kernel, had_user;
+	pmd_t *k_pmd, *u_pmd;
+
+	k_pmd      = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
+	u_pmd      = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
+	had_kernel = (k_pmd->pmd != 0);
+	had_user   = (u_pmd->pmd != 0);
+
+	do_sanity_check(mm, had_kernel, had_user);
+}
+
+#else /* !CONFIG_X86_PAE */
+
+static void map_ldt_struct_to_user(struct mm_struct *mm)
+{
+	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
+
+	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+		set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+}
+
+static void sanity_check_ldt_mapping(struct mm_struct *mm)
+{
+	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	bool had_kernel = (pgd->pgd != 0);
+	bool had_user   = (kernel_to_user_pgdp(pgd)->pgd != 0);
+
+	do_sanity_check(mm, had_kernel, had_user);
+}
+
+#endif /* CONFIG_X86_PAE */
+
 /*
  * If PTI is enabled, this maps the LDT into the kernelmode and
  * usermode tables for the given mm.
@@ -115,9 +211,8 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 static int
 map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 {
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-	bool is_vmalloc, had_top_level_entry;
 	unsigned long va;
+	bool is_vmalloc;
 	spinlock_t *ptl;
 	pgd_t *pgd;
 	int i;
@@ -131,13 +226,15 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	 */
 	WARN_ON(ldt->slot != -1);
 
+	/* Check if the current mappings are sane */
+	sanity_check_ldt_mapping(mm);
+
 	/*
 	 * Did we already have the top level entry allocated?  We can't
 	 * use pgd_none() for this because it doens't do anything on
 	 * 4-level page table kernels.
 	 */
 	pgd = pgd_offset(mm, LDT_BASE_ADDR);
-	had_top_level_entry = (pgd->pgd != 0);
 
 	is_vmalloc = is_vmalloc_addr(ldt->entries);
 
@@ -172,41 +269,31 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 		pte_unmap_unlock(ptep, ptl);
 	}
 
-	if (mm->context.ldt) {
-		/*
-		 * We already had an LDT.  The top-level entry should already
-		 * have been allocated and synchronized with the usermode
-		 * tables.
-		 */
-		WARN_ON(!had_top_level_entry);
-		if (static_cpu_has(X86_FEATURE_PTI))
-			WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
-	} else {
-		/*
-		 * This is the first time we're mapping an LDT for this process.
-		 * Sync the pgd to the usermode tables.
-		 */
-		WARN_ON(had_top_level_entry);
-		if (static_cpu_has(X86_FEATURE_PTI)) {
-			WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
-			set_pgd(kernel_to_user_pgdp(pgd), *pgd);
-		}
-	}
+	/* Propagate LDT mapping to the user page-table */
+	map_ldt_struct_to_user(mm);
 
 	va = (unsigned long)ldt_slot_va(slot);
 	flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
 
 	ldt->slot = slot;
-#endif
 	return 0;
 }
 
+#else /* !CONFIG_PAGE_TABLE_ISOLATION */
+
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+	return 0;
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
 static void free_ldt_pgtables(struct mm_struct *mm)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 	struct mmu_gather tlb;
 	unsigned long start = LDT_BASE_ADDR;
-	unsigned long end = start + (1UL << PGDIR_SHIFT);
+	unsigned long end = LDT_END_ADDR;
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return;
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index d1ab07ec8c9a..5409c2800ab5 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -56,7 +56,7 @@ static void load_segments(void)
 
 static void machine_kexec_free_page_tables(struct kimage *image)
 {
-	free_page((unsigned long)image->arch.pgd);
+	free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
 	image->arch.pgd = NULL;
 #ifdef CONFIG_X86_PAE
 	free_page((unsigned long)image->arch.pmd0);
@@ -72,7 +72,8 @@ static void machine_kexec_free_page_tables(struct kimage *image)
 
 static int machine_kexec_alloc_page_tables(struct kimage *image)
 {
-	image->arch.pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+	image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						    PGD_ALLOCATION_ORDER);
 #ifdef CONFIG_X86_PAE
 	image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
 	image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 99dc79e76bdc..930c88341e4e 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -88,10 +88,12 @@ unsigned paravirt_patch_call(void *insnbuf,
 	struct branch *b = insnbuf;
 	unsigned long delta = (unsigned long)target - (addr+5);
 
-	if (tgt_clobbers & ~site_clobbers)
-		return len;	/* target would clobber too much for this site */
-	if (len < 5)
+	if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+		WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+#endif
 		return len;	/* call too long for patch site */
+	}
 
 	b->opcode = 0xe8; /* call */
 	b->delta = delta;
@@ -106,8 +108,12 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
 	struct branch *b = insnbuf;
 	unsigned long delta = (unsigned long)target - (addr+5);
 
-	if (len < 5)
+	if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+		WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+#endif
 		return len;	/* call too long for patch site */
+	}
 
 	b->opcode = 0xe9;	/* jmp */
 	b->delta = delta;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 9edadabf04f6..9cb98f7b07c9 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -20,7 +20,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
 #endif
 
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index ab5d9dd668d2..80f9fe8d27d0 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -175,7 +175,7 @@ rootfs_initcall(pci_iommu_init);
 
 static int via_no_dac_cb(struct pci_dev *pdev, void *data)
 {
-	pdev->dev.dma_32bit_limit = true;
+	pdev->dev.bus_dma_mask = DMA_BIT_MASK(32);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
index 4dfd90a75e63..2e9006c1e240 100644
--- a/arch/x86/kernel/pci-iommu_table.c
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -60,7 +60,7 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
 			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
 			       p->detect, q->detect);
 			/* Heavy handed way..*/
-			x->depend = 0;
+			x->depend = NULL;
 		}
 	}
 
diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c
index da5190a1ea16..4a710ffffd9a 100644
--- a/arch/x86/kernel/pcspeaker.c
+++ b/arch/x86/kernel/pcspeaker.c
@@ -9,6 +9,6 @@ static __init int add_pcspkr(void)
 
 	pd = platform_device_register_simple("pcspkr", -1, NULL, 0);
 
-	return IS_ERR(pd) ? PTR_ERR(pd) : 0;
+	return PTR_ERR_OR_ZERO(pd);
 }
 device_initcall(add_pcspkr);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 30ca2d1a9231..c93fcfdf1673 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -57,14 +57,12 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
 		 */
 		.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
 
-#ifdef CONFIG_X86_64
 		/*
 		 * .sp1 is cpu_current_top_of_stack.  The init task never
 		 * runs user code, but cpu_current_top_of_stack should still
 		 * be well defined before the first context switch.
 		 */
 		.sp1 = TOP_OF_INIT_STACK,
-#endif
 
 #ifdef CONFIG_X86_32
 		.ss0 = __KERNEL_DS,
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0ae659de21eb..2924fd447e61 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -285,7 +285,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
-	update_sp0(next_p);
+	update_task_stack(next_p);
 	refresh_sysenter_cs(next);
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 12bb445fb98d..476e3ddf8890 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -478,7 +478,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	/* Reload sp0. */
-	update_sp0(next_p);
+	update_task_stack(next_p);
 
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2f86d883dd95..8fe740e22030 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -823,6 +823,12 @@ void __init setup_arch(char **cmdline_p)
 	memblock_reserve(__pa_symbol(_text),
 			 (unsigned long)__bss_stop - (unsigned long)_text);
 
+	/*
+	 * Make sure page 0 is always reserved because on systems with
+	 * L1TF its contents can be leaked to user processes.
+	 */
+	memblock_reserve(0, PAGE_SIZE);
+
 	early_reserve_initrd();
 
 	/*
@@ -866,6 +872,8 @@ void __init setup_arch(char **cmdline_p)
 
 	idt_setup_early_traps();
 	early_cpu_init();
+	arch_init_ideal_nops();
+	jump_label_init();
 	early_ioremap_init();
 
 	setup_olpc_ofw_pgd();
@@ -1012,6 +1020,7 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	init_hypervisor_platform();
 
+	tsc_early_init();
 	x86_init.resources.probe_roms();
 
 	/* after parse_early_param, so could debug it */
@@ -1197,11 +1206,6 @@ void __init setup_arch(char **cmdline_p)
 
 	memblock_find_dma_reserve();
 
-#ifdef CONFIG_KVM_GUEST
-	kvmclock_init();
-#endif
-
-	tsc_early_delay_calibrate();
 	if (!early_xdbc_setup_hardware())
 		early_xdbc_register_console();
 
@@ -1272,8 +1276,6 @@ void __init setup_arch(char **cmdline_p)
 
 	mcheck_init();
 
-	arch_init_ideal_nops();
-
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 5c574dff4c1a..04adc8d60aed 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -261,6 +261,7 @@ __visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	inc_irq_stat(irq_resched_count);
+	kvm_set_cpu_l1tf_flush_l1d();
 
 	if (trace_resched_ipi_enabled()) {
 		/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c2f7d1d2a5c3..f02ecaf97904 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -80,6 +80,7 @@
 #include <asm/intel-family.h>
 #include <asm/cpu_device_id.h>
 #include <asm/spec-ctrl.h>
+#include <asm/hw_irq.h>
 
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
@@ -221,6 +222,11 @@ static void notrace start_secondary(void *unused)
 #ifdef CONFIG_X86_32
 	/* switch away from the initial page table */
 	load_cr3(swapper_pg_dir);
+	/*
+	 * Initialize the CR4 shadow before doing anything that could
+	 * try to read it.
+	 */
+	cr4_init_shadow();
 	__flush_tlb_all();
 #endif
 	load_current_idt();
@@ -266,6 +272,23 @@ static void notrace start_secondary(void *unused)
 }
 
 /**
+ * topology_is_primary_thread - Check whether CPU is the primary SMT thread
+ * @cpu:	CPU to check
+ */
+bool topology_is_primary_thread(unsigned int cpu)
+{
+	return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu));
+}
+
+/**
+ * topology_smt_supported - Check whether SMT is supported by the CPUs
+ */
+bool topology_smt_supported(void)
+{
+	return smp_num_siblings > 1;
+}
+
+/**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
  *
  * Returns logical package id or -1 if not found
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 093f2ea5dd56..7627455047c2 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -81,16 +81,6 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 #ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
 
-#define STACKTRACE_DUMP_ONCE(task) ({				\
-	static bool __section(.data.unlikely) __dumped;		\
-								\
-	if (!__dumped) {					\
-		__dumped = true;				\
-		WARN_ON(1);					\
-		show_stack(task, NULL);				\
-	}							\
-})
-
 static int __always_inline
 __save_stack_trace_reliable(struct stack_trace *trace,
 			    struct task_struct *task)
@@ -99,30 +89,25 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 	struct pt_regs *regs;
 	unsigned long addr;
 
-	for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
+	for (unwind_start(&state, task, NULL, NULL);
+	     !unwind_done(&state) && !unwind_error(&state);
 	     unwind_next_frame(&state)) {
 
 		regs = unwind_get_entry_regs(&state, NULL);
 		if (regs) {
+			/* Success path for user tasks */
+			if (user_mode(regs))
+				goto success;
+
 			/*
 			 * Kernel mode registers on the stack indicate an
 			 * in-kernel interrupt or exception (e.g., preemption
 			 * or a page fault), which can make frame pointers
 			 * unreliable.
 			 */
-			if (!user_mode(regs))
-				return -EINVAL;
 
-			/*
-			 * The last frame contains the user mode syscall
-			 * pt_regs.  Skip it and finish the unwind.
-			 */
-			unwind_next_frame(&state);
-			if (!unwind_done(&state)) {
-				STACKTRACE_DUMP_ONCE(task);
+			if (IS_ENABLED(CONFIG_FRAME_POINTER))
 				return -EINVAL;
-			}
-			break;
 		}
 
 		addr = unwind_get_return_address(&state);
@@ -132,21 +117,22 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 		 * generated code which __kernel_text_address() doesn't know
 		 * about.
 		 */
-		if (!addr) {
-			STACKTRACE_DUMP_ONCE(task);
+		if (!addr)
 			return -EINVAL;
-		}
 
 		if (save_stack_address(trace, addr, false))
 			return -EINVAL;
 	}
 
 	/* Check for stack corruption */
-	if (unwind_error(&state)) {
-		STACKTRACE_DUMP_ONCE(task);
+	if (unwind_error(&state))
+		return -EINVAL;
+
+	/* Success path for non-user tasks, i.e. kthreads and idle tasks */
+	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
 		return -EINVAL;
-	}
 
+success:
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 774ebafa97c4..be01328eb755 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -12,6 +12,7 @@
 
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/i8253.h>
 #include <linux/time.h>
 #include <linux/export.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 74392d9d51e0..1463468ba9a0 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -33,16 +33,13 @@ EXPORT_SYMBOL(cpu_khz);
 unsigned int __read_mostly tsc_khz;
 EXPORT_SYMBOL(tsc_khz);
 
+#define KHZ	1000
+
 /*
  * TSC can be unstable due to cpufreq or due to unsynced TSCs
  */
 static int __read_mostly tsc_unstable;
 
-/* native_sched_clock() is called before tsc_init(), so
-   we must start with the TSC soft disabled to prevent
-   erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */
-static int __read_mostly tsc_disabled = -1;
-
 static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
@@ -106,23 +103,6 @@ void cyc2ns_read_end(void)
  *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
  */
 
-static void cyc2ns_data_init(struct cyc2ns_data *data)
-{
-	data->cyc2ns_mul = 0;
-	data->cyc2ns_shift = 0;
-	data->cyc2ns_offset = 0;
-}
-
-static void __init cyc2ns_init(int cpu)
-{
-	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
-
-	cyc2ns_data_init(&c2n->data[0]);
-	cyc2ns_data_init(&c2n->data[1]);
-
-	seqcount_init(&c2n->seq);
-}
-
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
 	struct cyc2ns_data data;
@@ -138,18 +118,11 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 	return ns;
 }
 
-static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+static void __set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
 {
 	unsigned long long ns_now;
 	struct cyc2ns_data data;
 	struct cyc2ns *c2n;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	sched_clock_idle_sleep_event();
-
-	if (!khz)
-		goto done;
 
 	ns_now = cycles_2_ns(tsc_now);
 
@@ -181,13 +154,56 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_
 	c2n->data[0] = data;
 	raw_write_seqcount_latch(&c2n->seq);
 	c2n->data[1] = data;
+}
+
+static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	sched_clock_idle_sleep_event();
+
+	if (khz)
+		__set_cyc2ns_scale(khz, cpu, tsc_now);
 
-done:
 	sched_clock_idle_wakeup_event();
 	local_irq_restore(flags);
 }
 
 /*
+ * Initialize cyc2ns for boot cpu
+ */
+static void __init cyc2ns_init_boot_cpu(void)
+{
+	struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+
+	seqcount_init(&c2n->seq);
+	__set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc());
+}
+
+/*
+ * Secondary CPUs do not run through tsc_init(), so set up
+ * all the scale factors for all CPUs, assuming the same
+ * speed as the bootup CPU. (cpufreq notifiers will fix this
+ * up if their speed diverges)
+ */
+static void __init cyc2ns_init_secondary_cpus(void)
+{
+	unsigned int cpu, this_cpu = smp_processor_id();
+	struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+	struct cyc2ns_data *data = c2n->data;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu != this_cpu) {
+			seqcount_init(&c2n->seq);
+			c2n = per_cpu_ptr(&cyc2ns, cpu);
+			c2n->data[0] = data[0];
+			c2n->data[1] = data[1];
+		}
+	}
+}
+
+/*
  * Scheduler clock - returns current time in nanosec units.
  */
 u64 native_sched_clock(void)
@@ -248,8 +264,7 @@ EXPORT_SYMBOL_GPL(check_tsc_unstable);
 #ifdef CONFIG_X86_TSC
 int __init notsc_setup(char *str)
 {
-	pr_warn("Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely\n");
-	tsc_disabled = 1;
+	mark_tsc_unstable("boot parameter notsc");
 	return 1;
 }
 #else
@@ -665,30 +680,17 @@ static unsigned long cpu_khz_from_cpuid(void)
 	return eax_base_mhz * 1000;
 }
 
-/**
- * native_calibrate_cpu - calibrate the cpu on boot
+/*
+ * calibrate cpu using pit, hpet, and ptimer methods. They are available
+ * later in boot after acpi is initialized.
  */
-unsigned long native_calibrate_cpu(void)
+static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 {
 	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags, latch, ms, fast_calibrate;
+	unsigned long flags, latch, ms;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
-	fast_calibrate = cpu_khz_from_cpuid();
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	fast_calibrate = cpu_khz_from_msr();
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	local_irq_save(flags);
-	fast_calibrate = quick_pit_calibrate();
-	local_irq_restore(flags);
-	if (fast_calibrate)
-		return fast_calibrate;
-
 	/*
 	 * Run 5 calibration loops to get the lowest frequency value
 	 * (the best estimate). We use two different calibration modes
@@ -831,6 +833,37 @@ unsigned long native_calibrate_cpu(void)
 	return tsc_pit_min;
 }
 
+/**
+ * native_calibrate_cpu_early - can calibrate the cpu early in boot
+ */
+unsigned long native_calibrate_cpu_early(void)
+{
+	unsigned long flags, fast_calibrate = cpu_khz_from_cpuid();
+
+	if (!fast_calibrate)
+		fast_calibrate = cpu_khz_from_msr();
+	if (!fast_calibrate) {
+		local_irq_save(flags);
+		fast_calibrate = quick_pit_calibrate();
+		local_irq_restore(flags);
+	}
+	return fast_calibrate;
+}
+
+
+/**
+ * native_calibrate_cpu - calibrate the cpu
+ */
+static unsigned long native_calibrate_cpu(void)
+{
+	unsigned long tsc_freq = native_calibrate_cpu_early();
+
+	if (!tsc_freq)
+		tsc_freq = pit_hpet_ptimer_calibrate_cpu();
+
+	return tsc_freq;
+}
+
 void recalibrate_cpu_khz(void)
 {
 #ifndef CONFIG_SMP
@@ -1307,7 +1340,7 @@ unreg:
 
 static int __init init_tsc_clocksource(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
+	if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz)
 		return 0;
 
 	if (tsc_unstable)
@@ -1341,40 +1374,22 @@ unreg:
  */
 device_initcall(init_tsc_clocksource);
 
-void __init tsc_early_delay_calibrate(void)
+static bool __init determine_cpu_tsc_frequencies(bool early)
 {
-	unsigned long lpj;
-
-	if (!boot_cpu_has(X86_FEATURE_TSC))
-		return;
-
-	cpu_khz = x86_platform.calibrate_cpu();
-	tsc_khz = x86_platform.calibrate_tsc();
-
-	tsc_khz = tsc_khz ? : cpu_khz;
-	if (!tsc_khz)
-		return;
-
-	lpj = tsc_khz * 1000;
-	do_div(lpj, HZ);
-	loops_per_jiffy = lpj;
-}
-
-void __init tsc_init(void)
-{
-	u64 lpj, cyc;
-	int cpu;
-
-	if (!boot_cpu_has(X86_FEATURE_TSC)) {
-		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
-		return;
+	/* Make sure that cpu and tsc are not already calibrated */
+	WARN_ON(cpu_khz || tsc_khz);
+
+	if (early) {
+		cpu_khz = x86_platform.calibrate_cpu();
+		tsc_khz = x86_platform.calibrate_tsc();
+	} else {
+		/* We should not be here with non-native cpu calibration */
+		WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu);
+		cpu_khz = pit_hpet_ptimer_calibrate_cpu();
 	}
 
-	cpu_khz = x86_platform.calibrate_cpu();
-	tsc_khz = x86_platform.calibrate_tsc();
-
 	/*
-	 * Trust non-zero tsc_khz as authorative,
+	 * Trust non-zero tsc_khz as authoritative,
 	 * and use it to sanity check cpu_khz,
 	 * which will be off if system timer is off.
 	 */
@@ -1383,52 +1398,78 @@ void __init tsc_init(void)
 	else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz)
 		cpu_khz = tsc_khz;
 
-	if (!tsc_khz) {
-		mark_tsc_unstable("could not calculate TSC khz");
-		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
-		return;
-	}
+	if (tsc_khz == 0)
+		return false;
 
 	pr_info("Detected %lu.%03lu MHz processor\n",
-		(unsigned long)cpu_khz / 1000,
-		(unsigned long)cpu_khz % 1000);
+		(unsigned long)cpu_khz / KHZ,
+		(unsigned long)cpu_khz % KHZ);
 
 	if (cpu_khz != tsc_khz) {
 		pr_info("Detected %lu.%03lu MHz TSC",
-			(unsigned long)tsc_khz / 1000,
-			(unsigned long)tsc_khz % 1000);
+			(unsigned long)tsc_khz / KHZ,
+			(unsigned long)tsc_khz % KHZ);
 	}
+	return true;
+}
+
+static unsigned long __init get_loops_per_jiffy(void)
+{
+	unsigned long lpj = tsc_khz * KHZ;
 
+	do_div(lpj, HZ);
+	return lpj;
+}
+
+static void __init tsc_enable_sched_clock(void)
+{
 	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
 	tsc_store_and_check_tsc_adjust(true);
+	cyc2ns_init_boot_cpu();
+	static_branch_enable(&__use_tsc);
+}
+
+void __init tsc_early_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_TSC))
+		return;
+	if (!determine_cpu_tsc_frequencies(true))
+		return;
+	loops_per_jiffy = get_loops_per_jiffy();
 
+	tsc_enable_sched_clock();
+}
+
+void __init tsc_init(void)
+{
 	/*
-	 * Secondary CPUs do not run through tsc_init(), so set up
-	 * all the scale factors for all CPUs, assuming the same
-	 * speed as the bootup CPU. (cpufreq notifiers will fix this
-	 * up if their speed diverges)
+	 * native_calibrate_cpu_early can only calibrate using methods that are
+	 * available early in boot.
 	 */
-	cyc = rdtsc();
-	for_each_possible_cpu(cpu) {
-		cyc2ns_init(cpu);
-		set_cyc2ns_scale(tsc_khz, cpu, cyc);
-	}
+	if (x86_platform.calibrate_cpu == native_calibrate_cpu_early)
+		x86_platform.calibrate_cpu = native_calibrate_cpu;
 
-	if (tsc_disabled > 0)
+	if (!boot_cpu_has(X86_FEATURE_TSC)) {
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
+	}
 
-	/* now allow native_sched_clock() to use rdtsc */
+	if (!tsc_khz) {
+		/* We failed to determine frequencies earlier, try again */
+		if (!determine_cpu_tsc_frequencies(false)) {
+			mark_tsc_unstable("could not calculate TSC khz");
+			setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
+			return;
+		}
+		tsc_enable_sched_clock();
+	}
 
-	tsc_disabled = 0;
-	static_branch_enable(&__use_tsc);
+	cyc2ns_init_secondary_cpus();
 
 	if (!no_sched_irq_time)
 		enable_sched_clock_irqtime();
 
-	lpj = ((u64)tsc_khz * 1000);
-	do_div(lpj, HZ);
-	lpj_fine = lpj;
-
+	lpj_fine = get_loops_per_jiffy();
 	use_tsc_delay();
 
 	check_system_tsc_reliable();
@@ -1455,7 +1496,7 @@ unsigned long calibrate_delay_is_known(void)
 	int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC);
 	const struct cpumask *mask = topology_core_cpumask(cpu);
 
-	if (tsc_disabled || !constant_tsc || !mask)
+	if (!constant_tsc || !mask)
 		return 0;
 
 	sibling = cpumask_any_but(mask, cpu);
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 19afdbd7d0a7..27ef714d886c 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -1,17 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * tsc_msr.c - TSC frequency enumeration via MSR
+ * TSC frequency enumeration via MSR
  *
- * Copyright (C) 2013 Intel Corporation
+ * Copyright (C) 2013, 2018 Intel Corporation
  * Author: Bin Gao <bin.gao@intel.com>
- *
- * This file is released under the GPLv2.
  */
 
 #include <linux/kernel.h>
-#include <asm/processor.h>
-#include <asm/setup.h>
+
 #include <asm/apic.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include <asm/msr.h>
 #include <asm/param.h>
+#include <asm/tsc.h>
 
 #define MAX_NUM_FREQS	9
 
@@ -23,44 +25,48 @@
  * field msr_plat does.
  */
 struct freq_desc {
-	u8 x86_family;	/* CPU family */
-	u8 x86_model;	/* model */
 	u8 msr_plat;	/* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */
 	u32 freqs[MAX_NUM_FREQS];
 };
 
-static struct freq_desc freq_desc_tables[] = {
-	/* PNW */
-	{ 6, 0x27, 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 } },
-	/* CLV+ */
-	{ 6, 0x35, 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 } },
-	/* TNG - Intel Atom processor Z3400 series */
-	{ 6, 0x4a, 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 } },
-	/* VLV2 - Intel Atom processor E3000, Z3600, Z3700 series */
-	{ 6, 0x37, 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 } },
-	/* ANN - Intel Atom processor Z3500 series */
-	{ 6, 0x5a, 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } },
-	/* AMT - Intel Atom processor X7-Z8000 and X5-Z8000 series */
-	{ 6, 0x4c, 1, { 83300, 100000, 133300, 116700,
-			80000, 93300, 90000, 88900, 87500 } },
+/*
+ * Penwell and Clovertrail use spread spectrum clock,
+ * so the freq number is not exactly the same as reported
+ * by MSR based on SDM.
+ */
+static const struct freq_desc freq_desc_pnw = {
+	0, { 0, 0, 0, 0, 0, 99840, 0, 83200 }
 };
 
-static int match_cpu(u8 family, u8 model)
-{
-	int i;
+static const struct freq_desc freq_desc_clv = {
+	0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 }
+};
 
-	for (i = 0; i < ARRAY_SIZE(freq_desc_tables); i++) {
-		if ((family == freq_desc_tables[i].x86_family) &&
-			(model == freq_desc_tables[i].x86_model))
-			return i;
-	}
+static const struct freq_desc freq_desc_byt = {
+	1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 }
+};
 
-	return -1;
-}
+static const struct freq_desc freq_desc_cht = {
+	1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 }
+};
 
-/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
-#define id_to_freq(cpu_index, freq_id) \
-	(freq_desc_tables[cpu_index].freqs[freq_id])
+static const struct freq_desc freq_desc_tng = {
+	1, { 0, 100000, 133300, 0, 0, 0, 0, 0 }
+};
+
+static const struct freq_desc freq_desc_ann = {
+	1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 }
+};
+
+static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
+	INTEL_CPU_FAM6(ATOM_PENWELL,		freq_desc_pnw),
+	INTEL_CPU_FAM6(ATOM_CLOVERVIEW,		freq_desc_clv),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT1,	freq_desc_byt),
+	INTEL_CPU_FAM6(ATOM_AIRMONT,		freq_desc_cht),
+	INTEL_CPU_FAM6(ATOM_MERRIFIELD,		freq_desc_tng),
+	INTEL_CPU_FAM6(ATOM_MOOREFIELD,		freq_desc_ann),
+	{}
+};
 
 /*
  * MSR-based CPU/TSC frequency discovery for certain CPUs.
@@ -70,18 +76,17 @@ static int match_cpu(u8 family, u8 model)
  */
 unsigned long cpu_khz_from_msr(void)
 {
-	u32 lo, hi, ratio, freq_id, freq;
+	u32 lo, hi, ratio, freq;
+	const struct freq_desc *freq_desc;
+	const struct x86_cpu_id *id;
 	unsigned long res;
-	int cpu_index;
-
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
-		return 0;
 
-	cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model);
-	if (cpu_index < 0)
+	id = x86_match_cpu(tsc_msr_cpu_ids);
+	if (!id)
 		return 0;
 
-	if (freq_desc_tables[cpu_index].msr_plat) {
+	freq_desc = (struct freq_desc *)id->driver_data;
+	if (freq_desc->msr_plat) {
 		rdmsr(MSR_PLATFORM_INFO, lo, hi);
 		ratio = (lo >> 8) & 0xff;
 	} else {
@@ -91,8 +96,9 @@ unsigned long cpu_khz_from_msr(void)
 
 	/* Get FSB FREQ ID */
 	rdmsr(MSR_FSB_FREQ, lo, hi);
-	freq_id = lo & 0x7;
-	freq = id_to_freq(cpu_index, freq_id);
+
+	/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
+	freq = freq_desc->freqs[lo & 0x7];
 
 	/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
 	res = freq * ratio;
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index feb28fee6cea..26038eacf74a 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -198,7 +198,7 @@ static int orc_sort_cmp(const void *_a, const void *_b)
 	 * whitelisted .o files which didn't get objtool generation.
 	 */
 	orc_a = cur_orc_table + (a - cur_orc_ip_table);
-	return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1;
+	return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1;
 }
 
 #ifdef CONFIG_MODULES
@@ -352,7 +352,7 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 
 bool unwind_next_frame(struct unwind_state *state)
 {
-	unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
+	unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
 	bool indirect = false;
@@ -363,9 +363,9 @@ bool unwind_next_frame(struct unwind_state *state)
 	/* Don't let modules unload while we're reading their ORC data. */
 	preempt_disable();
 
-	/* Have we reached the end? */
+	/* End-of-stack check for user tasks: */
 	if (state->regs && user_mode(state->regs))
-		goto done;
+		goto the_end;
 
 	/*
 	 * Find the orc_entry associated with the text address.
@@ -374,9 +374,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	 * calls and calls to noreturn functions.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
-	if (!orc || orc->sp_reg == ORC_REG_UNDEFINED)
-		goto done;
-	orig_ip = state->ip;
+	if (!orc)
+		goto err;
+
+	/* End-of-stack check for kernel threads: */
+	if (orc->sp_reg == ORC_REG_UNDEFINED) {
+		if (!orc->end)
+			goto err;
+
+		goto the_end;
+	}
 
 	/* Find the previous frame's stack: */
 	switch (orc->sp_reg) {
@@ -402,7 +409,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg R10 at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->r10;
 		break;
@@ -411,7 +418,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg R13 at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->r13;
 		break;
@@ -420,7 +427,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg DI at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->di;
 		break;
@@ -429,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg DX at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->dx;
 		break;
@@ -437,12 +444,12 @@ bool unwind_next_frame(struct unwind_state *state)
 	default:
 		orc_warn("unknown SP base reg %d for ip %pB\n",
 			 orc->sp_reg, (void *)state->ip);
-		goto done;
+		goto err;
 	}
 
 	if (indirect) {
 		if (!deref_stack_reg(state, sp, &sp))
-			goto done;
+			goto err;
 	}
 
 	/* Find IP, SP and possibly regs: */
@@ -451,7 +458,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		ip_p = sp - sizeof(long);
 
 		if (!deref_stack_reg(state, ip_p, &state->ip))
-			goto done;
+			goto err;
 
 		state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
 						  state->ip, (void *)ip_p);
@@ -465,7 +472,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
-			goto done;
+			goto err;
 		}
 
 		state->regs = (struct pt_regs *)sp;
@@ -477,7 +484,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference iret registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
-			goto done;
+			goto err;
 		}
 
 		state->regs = (void *)sp - IRET_FRAME_OFFSET;
@@ -500,18 +507,18 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_REG_PREV_SP:
 		if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp))
-			goto done;
+			goto err;
 		break;
 
 	case ORC_REG_BP:
 		if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp))
-			goto done;
+			goto err;
 		break;
 
 	default:
 		orc_warn("unknown BP base reg %d for ip %pB\n",
 			 orc->bp_reg, (void *)orig_ip);
-		goto done;
+		goto err;
 	}
 
 	/* Prevent a recursive loop due to bad ORC data: */
@@ -520,13 +527,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	    state->sp <= prev_sp) {
 		orc_warn("stack going in the wrong direction? ip=%pB\n",
 			 (void *)orig_ip);
-		goto done;
+		goto err;
 	}
 
 	preempt_enable();
 	return true;
 
-done:
+err:
+	state->error = true;
+
+the_end:
 	preempt_enable();
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 9d0b5af7db91..1c03e4aa6474 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -149,7 +149,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 	preempt_disable();
 	tsk->thread.sp0 = vm86->saved_sp0;
 	tsk->thread.sysenter_cs = __KERNEL_CS;
-	update_sp0(tsk);
+	update_task_stack(tsk);
 	refresh_sysenter_cs(&tsk->thread);
 	vm86->saved_sp0 = 0;
 	preempt_enable();
@@ -374,7 +374,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 		refresh_sysenter_cs(&tsk->thread);
 	}
 
-	update_sp0(tsk);
+	update_task_stack(tsk);
 	preempt_enable();
 
 	if (vm86->flags & VM86_SCREEN_BITMAP)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 5e1458f609a1..8bde0a419f86 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -55,19 +55,22 @@ jiffies_64 = jiffies;
  * so we can enable protection checks as well as retain 2MB large page
  * mappings for kernel text.
  */
-#define X64_ALIGN_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
+#define X86_ALIGN_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
 
-#define X64_ALIGN_RODATA_END					\
+#define X86_ALIGN_RODATA_END					\
 		. = ALIGN(HPAGE_SIZE);				\
-		__end_rodata_hpage_align = .;
+		__end_rodata_hpage_align = .;			\
+		__end_rodata_aligned = .;
 
 #define ALIGN_ENTRY_TEXT_BEGIN	. = ALIGN(PMD_SIZE);
 #define ALIGN_ENTRY_TEXT_END	. = ALIGN(PMD_SIZE);
 
 #else
 
-#define X64_ALIGN_RODATA_BEGIN
-#define X64_ALIGN_RODATA_END
+#define X86_ALIGN_RODATA_BEGIN
+#define X86_ALIGN_RODATA_END					\
+		. = ALIGN(PAGE_SIZE);				\
+		__end_rodata_aligned = .;
 
 #define ALIGN_ENTRY_TEXT_BEGIN
 #define ALIGN_ENTRY_TEXT_END
@@ -141,9 +144,9 @@ SECTIONS
 
 	/* .text should occupy whole number of pages */
 	. = ALIGN(PAGE_SIZE);
-	X64_ALIGN_RODATA_BEGIN
+	X86_ALIGN_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
-	X64_ALIGN_RODATA_END
+	X86_ALIGN_RODATA_END
 
 	/* Data */
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 3ab867603e81..2792b5573818 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -109,7 +109,7 @@ struct x86_cpuinit_ops x86_cpuinit = {
 static void default_nmi_init(void) { };
 
 struct x86_platform_ops x86_platform __ro_after_init = {
-	.calibrate_cpu			= native_calibrate_cpu,
+	.calibrate_cpu			= native_calibrate_cpu_early,
 	.calibrate_tsc			= native_calibrate_tsc,
 	.get_wallclock			= mach_get_cmos_time,
 	.set_wallclock			= mach_set_rtc_mmss,
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 92fd433c50b9..1bbec387d289 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -85,7 +85,7 @@ config KVM_AMD_SEV
 	def_bool y
 	bool "AMD Secure Encrypted Virtualization (SEV) support"
 	depends on KVM_AMD && X86_64
-	depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP
+	depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
 	---help---
 	Provides support for launching Encrypted VMs on AMD processors.
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b5cd8465d44f..d536d457517b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1379,7 +1379,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	 * using swait_active() is safe.
 	 */
 	if (swait_active(q))
-		swake_up(q);
+		swake_up_one(q);
 
 	if (apic_lvtt_tscdeadline(apic))
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d594690d8b95..a44e568363a4 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
 	if (cache->nobjs >= min)
 		return 0;
 	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
-		page = (void *)__get_free_page(GFP_KERNEL);
+		page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
 		if (!page)
 			return -ENOMEM;
 		cache->objects[cache->nobjs++] = page;
@@ -3840,6 +3840,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 {
 	int r = 1;
 
+	vcpu->arch.l1tf_flush_l1d = true;
 	switch (vcpu->arch.apf.host_apf_reason) {
 	default:
 		trace_kvm_page_fault(fault_address, error_code);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1689f433f3a0..46b428c0990e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -188,6 +188,150 @@ module_param(ple_window_max, uint, 0444);
 
 extern const ulong vmx_return;
 
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
+static DEFINE_MUTEX(vmx_l1d_flush_mutex);
+
+/* Storage for pre module init parameter parsing */
+static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO;
+
+static const struct {
+	const char *option;
+	enum vmx_l1d_flush_state cmd;
+} vmentry_l1d_param[] = {
+	{"auto",	VMENTER_L1D_FLUSH_AUTO},
+	{"never",	VMENTER_L1D_FLUSH_NEVER},
+	{"cond",	VMENTER_L1D_FLUSH_COND},
+	{"always",	VMENTER_L1D_FLUSH_ALWAYS},
+};
+
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
+{
+	struct page *page;
+	unsigned int i;
+
+	if (!enable_ept) {
+		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
+		return 0;
+	}
+
+       if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
+	       u64 msr;
+
+	       rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
+	       if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
+		       l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+		       return 0;
+	       }
+       }
+
+	/* If set to auto use the default l1tf mitigation method */
+	if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+			l1tf = VMENTER_L1D_FLUSH_NEVER;
+			break;
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+			l1tf = VMENTER_L1D_FLUSH_COND;
+			break;
+		case L1TF_MITIGATION_FULL:
+		case L1TF_MITIGATION_FULL_FORCE:
+			l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+			break;
+		}
+	} else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) {
+		l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+	}
+
+	if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
+	    !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+		if (!page)
+			return -ENOMEM;
+		vmx_l1d_flush_pages = page_address(page);
+
+		/*
+		 * Initialize each page with a different pattern in
+		 * order to protect against KSM in the nested
+		 * virtualization case.
+		 */
+		for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) {
+			memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1,
+			       PAGE_SIZE);
+		}
+	}
+
+	l1tf_vmx_mitigation = l1tf;
+
+	if (l1tf != VMENTER_L1D_FLUSH_NEVER)
+		static_branch_enable(&vmx_l1d_should_flush);
+	else
+		static_branch_disable(&vmx_l1d_should_flush);
+
+	if (l1tf == VMENTER_L1D_FLUSH_COND)
+		static_branch_enable(&vmx_l1d_flush_cond);
+	else
+		static_branch_disable(&vmx_l1d_flush_cond);
+	return 0;
+}
+
+static int vmentry_l1d_flush_parse(const char *s)
+{
+	unsigned int i;
+
+	if (s) {
+		for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
+			if (sysfs_streq(s, vmentry_l1d_param[i].option))
+				return vmentry_l1d_param[i].cmd;
+		}
+	}
+	return -EINVAL;
+}
+
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+	int l1tf, ret;
+
+	if (!boot_cpu_has(X86_BUG_L1TF))
+		return 0;
+
+	l1tf = vmentry_l1d_flush_parse(s);
+	if (l1tf < 0)
+		return l1tf;
+
+	/*
+	 * Has vmx_init() run already? If not then this is the pre init
+	 * parameter parsing. In that case just store the value and let
+	 * vmx_init() do the proper setup after enable_ept has been
+	 * established.
+	 */
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) {
+		vmentry_l1d_flush_param = l1tf;
+		return 0;
+	}
+
+	mutex_lock(&vmx_l1d_flush_mutex);
+	ret = vmx_setup_l1d_flush(l1tf);
+	mutex_unlock(&vmx_l1d_flush_mutex);
+	return ret;
+}
+
+static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
+{
+	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
+}
+
+static const struct kernel_param_ops vmentry_l1d_flush_ops = {
+	.set = vmentry_l1d_flush_set,
+	.get = vmentry_l1d_flush_get,
+};
+module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);
+
 struct kvm_vmx {
 	struct kvm kvm;
 
@@ -757,6 +901,11 @@ static inline int pi_test_sn(struct pi_desc *pi_desc)
 			(unsigned long *)&pi_desc->control);
 }
 
+struct vmx_msrs {
+	unsigned int		nr;
+	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
+};
+
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
@@ -790,9 +939,8 @@ struct vcpu_vmx {
 	struct loaded_vmcs   *loaded_vmcs;
 	bool                  __launched; /* temporary, used in vmx_vcpu_run */
 	struct msr_autoload {
-		unsigned nr;
-		struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
-		struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+		struct vmx_msrs guest;
+		struct vmx_msrs host;
 	} msr_autoload;
 	struct {
 		int           loaded;
@@ -2377,9 +2525,20 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 	vm_exit_controls_clearbit(vmx, exit);
 }
 
+static int find_msr(struct vmx_msrs *m, unsigned int msr)
+{
+	unsigned int i;
+
+	for (i = 0; i < m->nr; ++i) {
+		if (m->val[i].index == msr)
+			return i;
+	}
+	return -ENOENT;
+}
+
 static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 {
-	unsigned i;
+	int i;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {
@@ -2400,18 +2559,21 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 		}
 		break;
 	}
+	i = find_msr(&m->guest, msr);
+	if (i < 0)
+		goto skip_guest;
+	--m->guest.nr;
+	m->guest.val[i] = m->guest.val[m->guest.nr];
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
 
-	for (i = 0; i < m->nr; ++i)
-		if (m->guest[i].index == msr)
-			break;
-
-	if (i == m->nr)
+skip_guest:
+	i = find_msr(&m->host, msr);
+	if (i < 0)
 		return;
-	--m->nr;
-	m->guest[i] = m->guest[m->nr];
-	m->host[i] = m->host[m->nr];
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+
+	--m->host.nr;
+	m->host.val[i] = m->host.val[m->host.nr];
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
 }
 
 static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
@@ -2426,9 +2588,9 @@ static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 }
 
 static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
-				  u64 guest_val, u64 host_val)
+				  u64 guest_val, u64 host_val, bool entry_only)
 {
-	unsigned i;
+	int i, j = 0;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {
@@ -2463,24 +2625,31 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	for (i = 0; i < m->nr; ++i)
-		if (m->guest[i].index == msr)
-			break;
+	i = find_msr(&m->guest, msr);
+	if (!entry_only)
+		j = find_msr(&m->host, msr);
 
-	if (i == NR_AUTOLOAD_MSRS) {
+	if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
-	} else if (i == m->nr) {
-		++m->nr;
-		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
-		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
 	}
+	if (i < 0) {
+		i = m->guest.nr++;
+		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+	}
+	m->guest.val[i].index = msr;
+	m->guest.val[i].value = guest_val;
 
-	m->guest[i].index = msr;
-	m->guest[i].value = guest_val;
-	m->host[i].index = msr;
-	m->host[i].value = host_val;
+	if (entry_only)
+		return;
+
+	if (j < 0) {
+		j = m->host.nr++;
+		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
+	}
+	m->host.val[j].index = msr;
+	m->host.val[j].value = host_val;
 }
 
 static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
@@ -2524,7 +2693,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 			guest_efer &= ~EFER_LME;
 		if (guest_efer != host_efer)
 			add_atomic_switch_msr(vmx, MSR_EFER,
-					      guest_efer, host_efer);
+					      guest_efer, host_efer, false);
 		return false;
 	} else {
 		guest_efer &= ~ignore_bits;
@@ -2571,6 +2740,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 #ifdef CONFIG_X86_64
 	int cpu = raw_smp_processor_id();
+	unsigned long fs_base, kernel_gs_base;
 #endif
 	int i;
 
@@ -2586,12 +2756,20 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel;
 
 #ifdef CONFIG_X86_64
-	save_fsgs_for_kvm();
-	vmx->host_state.fs_sel = current->thread.fsindex;
-	vmx->host_state.gs_sel = current->thread.gsindex;
-#else
-	savesegment(fs, vmx->host_state.fs_sel);
-	savesegment(gs, vmx->host_state.gs_sel);
+	if (likely(is_64bit_mm(current->mm))) {
+		save_fsgs_for_kvm();
+		vmx->host_state.fs_sel = current->thread.fsindex;
+		vmx->host_state.gs_sel = current->thread.gsindex;
+		fs_base = current->thread.fsbase;
+		kernel_gs_base = current->thread.gsbase;
+	} else {
+#endif
+		savesegment(fs, vmx->host_state.fs_sel);
+		savesegment(gs, vmx->host_state.gs_sel);
+#ifdef CONFIG_X86_64
+		fs_base = read_msr(MSR_FS_BASE);
+		kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+	}
 #endif
 	if (!(vmx->host_state.fs_sel & 7)) {
 		vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel);
@@ -2611,10 +2789,10 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	savesegment(ds, vmx->host_state.ds_sel);
 	savesegment(es, vmx->host_state.es_sel);
 
-	vmcs_writel(HOST_FS_BASE, current->thread.fsbase);
+	vmcs_writel(HOST_FS_BASE, fs_base);
 	vmcs_writel(HOST_GS_BASE, cpu_kernelmode_gs_base(cpu));
 
-	vmx->msr_host_kernel_gs_base = current->thread.gsbase;
+	vmx->msr_host_kernel_gs_base = kernel_gs_base;
 	if (is_long_mode(&vmx->vcpu))
 		wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #else
@@ -3978,7 +4156,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.ia32_xss = data;
 		if (vcpu->arch.ia32_xss != host_xss)
 			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
-				vcpu->arch.ia32_xss, host_xss);
+				vcpu->arch.ia32_xss, host_xss, false);
 		else
 			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
 		break;
@@ -4322,11 +4500,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	vmcs_conf->order = get_order(vmcs_conf->size);
 	vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
 
-	/* KVM supports Enlightened VMCS v1 only */
-	if (static_branch_unlikely(&enable_evmcs))
-		vmcs_conf->revision_id = KVM_EVMCS_VERSION;
-	else
-		vmcs_conf->revision_id = vmx_msr_low;
+	vmcs_conf->revision_id = vmx_msr_low;
 
 	vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
 	vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
@@ -4396,7 +4570,13 @@ static struct vmcs *alloc_vmcs_cpu(int cpu)
 		return NULL;
 	vmcs = page_address(pages);
 	memset(vmcs, 0, vmcs_config.size);
-	vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */
+
+	/* KVM supports Enlightened VMCS v1 only */
+	if (static_branch_unlikely(&enable_evmcs))
+		vmcs->revision_id = KVM_EVMCS_VERSION;
+	else
+		vmcs->revision_id = vmcs_config.revision_id;
+
 	return vmcs;
 }
 
@@ -4564,6 +4744,19 @@ static __init int alloc_kvm_area(void)
 			return -ENOMEM;
 		}
 
+		/*
+		 * When eVMCS is enabled, alloc_vmcs_cpu() sets
+		 * vmcs->revision_id to KVM_EVMCS_VERSION instead of
+		 * revision_id reported by MSR_IA32_VMX_BASIC.
+		 *
+		 * However, even though not explictly documented by
+		 * TLFS, VMXArea passed as VMXON argument should
+		 * still be marked with revision_id reported by
+		 * physical CPU.
+		 */
+		if (static_branch_unlikely(&enable_evmcs))
+			vmcs->revision_id = vmcs_config.revision_id;
+
 		per_cpu(vmxarea, cpu) = vmcs;
 	}
 	return 0;
@@ -6250,9 +6443,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
 	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
@@ -6272,8 +6465,7 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities);
+	vmx->arch_capabilities = kvm_get_arch_capabilities();
 
 	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
 
@@ -7869,6 +8061,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 		     HRTIMER_MODE_REL_PINNED);
 	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
 
+	vmx->nested.vpid02 = allocate_vpid();
+
 	vmx->nested.vmxon = true;
 	return 0;
 
@@ -8456,21 +8650,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 /* Emulate the VMPTRST instruction */
 static int handle_vmptrst(struct kvm_vcpu *vcpu)
 {
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	gva_t vmcs_gva;
+	unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION);
+	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr;
 	struct x86_exception e;
+	gva_t gva;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, exit_qualification,
-			vmx_instruction_info, true, &vmcs_gva))
+	if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva))
 		return 1;
 	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
-	if (kvm_write_guest_virt_system(vcpu, vmcs_gva,
-					(void *)&to_vmx(vcpu)->nested.current_vmptr,
-					sizeof(u64), &e)) {
+	if (kvm_write_guest_virt_system(vcpu, gva, (void *)&current_vmptr,
+					sizeof(gpa_t), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -9523,6 +9716,79 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	}
 }
 
+/*
+ * Software based L1D cache flush which is used when microcode providing
+ * the cache control MSR is not loaded.
+ *
+ * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to
+ * flush it is required to read in 64 KiB because the replacement algorithm
+ * is not exactly LRU. This could be sized at runtime via topology
+ * information but as all relevant affected CPUs have 32KiB L1D cache size
+ * there is no point in doing so.
+ */
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
+{
+	int size = PAGE_SIZE << L1D_CACHE_ORDER;
+
+	/*
+	 * This code is only executed when the the flush mode is 'cond' or
+	 * 'always'
+	 */
+	if (static_branch_likely(&vmx_l1d_flush_cond)) {
+		bool flush_l1d;
+
+		/*
+		 * Clear the per-vcpu flush bit, it gets set again
+		 * either from vcpu_run() or from one of the unsafe
+		 * VMEXIT handlers.
+		 */
+		flush_l1d = vcpu->arch.l1tf_flush_l1d;
+		vcpu->arch.l1tf_flush_l1d = false;
+
+		/*
+		 * Clear the per-cpu flush bit, it gets set again from
+		 * the interrupt handlers.
+		 */
+		flush_l1d |= kvm_get_cpu_l1tf_flush_l1d();
+		kvm_clear_cpu_l1tf_flush_l1d();
+
+		if (!flush_l1d)
+			return;
+	}
+
+	vcpu->stat.l1d_flush++;
+
+	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		return;
+	}
+
+	asm volatile(
+		/* First ensure the pages are in the TLB */
+		"xorl	%%eax, %%eax\n"
+		".Lpopulate_tlb:\n\t"
+		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$4096, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lpopulate_tlb\n\t"
+		"xorl	%%eax, %%eax\n\t"
+		"cpuid\n\t"
+		/* Now fill the cache */
+		"xorl	%%eax, %%eax\n"
+		".Lfill_cache:\n"
+		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$64, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lfill_cache\n\t"
+		"lfence\n"
+		:: [flush_pages] "r" (vmx_l1d_flush_pages),
+		    [size] "r" (size)
+		: "eax", "ebx", "ecx", "edx");
+}
+
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -9924,7 +10190,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 			clear_atomic_switch_msr(vmx, msrs[i].msr);
 		else
 			add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
-					msrs[i].host);
+					msrs[i].host, false);
 }
 
 static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
@@ -10019,6 +10285,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	evmcs_rsp = static_branch_unlikely(&enable_evmcs) ?
 		(unsigned long)&current_evmcs->host_rsp : 0;
 
+	if (static_branch_unlikely(&vmx_l1d_should_flush))
+		vmx_l1d_flush(vcpu);
+
 	asm(
 		/* Store host registers */
 		"push %%" _ASM_DX "; push %%" _ASM_BP ";"
@@ -10346,11 +10615,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 			goto free_vmcs;
 	}
 
-	if (nested) {
+	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
 					   kvm_vcpu_apicv_active(&vmx->vcpu));
-		vmx->nested.vpid02 = allocate_vpid();
-	}
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
@@ -10367,7 +10634,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	return &vmx->vcpu;
 
 free_vmcs:
-	free_vpid(vmx->nested.vpid02);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
@@ -10381,10 +10647,37 @@ free_vcpu:
 	return ERR_PTR(err);
 }
 
+#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+
 static int vmx_vm_init(struct kvm *kvm)
 {
 	if (!ple_gap)
 		kvm->arch.pause_in_guest = true;
+
+	if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+			/* 'I explicitly don't care' is set */
+			break;
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+		case L1TF_MITIGATION_FULL:
+			/*
+			 * Warn upon starting the first VM in a potentially
+			 * insecure environment.
+			 */
+			if (cpu_smt_control == CPU_SMT_ENABLED)
+				pr_warn_once(L1TF_MSG_SMT);
+			if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER)
+				pr_warn_once(L1TF_MSG_L1D);
+			break;
+		case L1TF_MITIGATION_FULL_FORCE:
+			/* Flush is enforced */
+			break;
+		}
+	}
 	return 0;
 }
 
@@ -11238,10 +11531,10 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	 * Set the MSR load/store lists to match L0's settings.
 	 */
 	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
 	set_cr4_guest_host_mask(vmx);
 
@@ -11753,7 +12046,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	u32 msr_entry_idx;
 	u32 exit_qual;
 	int r;
 
@@ -11775,10 +12067,10 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu)
 	nested_get_vmcs12_pages(vcpu, vmcs12);
 
 	r = EXIT_REASON_MSR_LOAD_FAIL;
-	msr_entry_idx = nested_vmx_load_msr(vcpu,
-					    vmcs12->vm_entry_msr_load_addr,
-					    vmcs12->vm_entry_msr_load_count);
-	if (msr_entry_idx)
+	exit_qual = nested_vmx_load_msr(vcpu,
+					vmcs12->vm_entry_msr_load_addr,
+					vmcs12->vm_entry_msr_load_count);
+	if (exit_qual)
 		goto fail;
 
 	/*
@@ -11878,6 +12170,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return ret;
 	}
 
+	/* Hide L1D cache contents from the nested guest.  */
+	vmx->vcpu.arch.l1tf_flush_l1d = true;
+
 	/*
 	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
 	 * by event injection, halt vcpu.
@@ -12398,8 +12693,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vmx_segment_cache_clear(vmx);
 
 	/* Update any VMCS fields that might have changed while L2 ran */
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 	if (vmx->hv_deadline_tsc == -1)
 		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
@@ -13116,6 +13411,51 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.enable_smi_window = enable_smi_window,
 };
 
+static void vmx_cleanup_l1d_flush(void)
+{
+	if (vmx_l1d_flush_pages) {
+		free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
+		vmx_l1d_flush_pages = NULL;
+	}
+	/* Restore state so sysfs ignores VMX */
+	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
+}
+
+static void vmx_exit(void)
+{
+#ifdef CONFIG_KEXEC_CORE
+	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
+	synchronize_rcu();
+#endif
+
+	kvm_exit();
+
+#if IS_ENABLED(CONFIG_HYPERV)
+	if (static_branch_unlikely(&enable_evmcs)) {
+		int cpu;
+		struct hv_vp_assist_page *vp_ap;
+		/*
+		 * Reset everything to support using non-enlightened VMCS
+		 * access later (e.g. when we reload the module with
+		 * enlightened_vmcs=0)
+		 */
+		for_each_online_cpu(cpu) {
+			vp_ap =	hv_get_vp_assist_page(cpu);
+
+			if (!vp_ap)
+				continue;
+
+			vp_ap->current_nested_vmcs = 0;
+			vp_ap->enlighten_vmentry = 0;
+		}
+
+		static_branch_disable(&enable_evmcs);
+	}
+#endif
+	vmx_cleanup_l1d_flush();
+}
+module_exit(vmx_exit);
+
 static int __init vmx_init(void)
 {
 	int r;
@@ -13150,10 +13490,25 @@ static int __init vmx_init(void)
 #endif
 
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
-                     __alignof__(struct vcpu_vmx), THIS_MODULE);
+		     __alignof__(struct vcpu_vmx), THIS_MODULE);
 	if (r)
 		return r;
 
+	/*
+	 * Must be called after kvm_init() so enable_ept is properly set
+	 * up. Hand the parameter mitigation value in which was stored in
+	 * the pre module init parser. If no parameter was given, it will
+	 * contain 'auto' which will be turned into the default 'cond'
+	 * mitigation mode.
+	 */
+	if (boot_cpu_has(X86_BUG_L1TF)) {
+		r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
+		if (r) {
+			vmx_exit();
+			return r;
+		}
+	}
+
 #ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);
@@ -13162,39 +13517,4 @@ static int __init vmx_init(void)
 
 	return 0;
 }
-
-static void __exit vmx_exit(void)
-{
-#ifdef CONFIG_KEXEC_CORE
-	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
-	synchronize_rcu();
-#endif
-
-	kvm_exit();
-
-#if IS_ENABLED(CONFIG_HYPERV)
-	if (static_branch_unlikely(&enable_evmcs)) {
-		int cpu;
-		struct hv_vp_assist_page *vp_ap;
-		/*
-		 * Reset everything to support using non-enlightened VMCS
-		 * access later (e.g. when we reload the module with
-		 * enlightened_vmcs=0)
-		 */
-		for_each_online_cpu(cpu) {
-			vp_ap =	hv_get_vp_assist_page(cpu);
-
-			if (!vp_ap)
-				continue;
-
-			vp_ap->current_nested_vmcs = 0;
-			vp_ap->enlighten_vmentry = 0;
-		}
-
-		static_branch_disable(&enable_evmcs);
-	}
-#endif
-}
-
-module_init(vmx_init)
-module_exit(vmx_exit)
+module_init(vmx_init);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0046aa70205a..a5caa5e5480c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -195,6 +195,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "irq_injections", VCPU_STAT(irq_injections) },
 	{ "nmi_injections", VCPU_STAT(nmi_injections) },
 	{ "req_event", VCPU_STAT(req_event) },
+	{ "l1d_flush", VCPU_STAT(l1d_flush) },
 	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
 	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
 	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
@@ -1097,15 +1098,41 @@ static u32 msr_based_features[] = {
 
 	MSR_F10H_DECFG,
 	MSR_IA32_UCODE_REV,
+	MSR_IA32_ARCH_CAPABILITIES,
 };
 
 static unsigned int num_msr_based_features;
 
+u64 kvm_get_arch_capabilities(void)
+{
+	u64 data;
+
+	rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
+
+	/*
+	 * If we're doing cache flushes (either "always" or "cond")
+	 * we will do one whenever the guest does a vmlaunch/vmresume.
+	 * If an outer hypervisor is doing the cache flush for us
+	 * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that
+	 * capability to the guest too, and if EPT is disabled we're not
+	 * vulnerable.  Overall, only VMENTER_L1D_FLUSH_NEVER will
+	 * require a nested hypervisor to do a flush of its own.
+	 */
+	if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
+		data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;
+
+	return data;
+}
+EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
+
 static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
 {
 	switch (msr->index) {
+	case MSR_IA32_ARCH_CAPABILITIES:
+		msr->data = kvm_get_arch_capabilities();
+		break;
 	case MSR_IA32_UCODE_REV:
-		rdmsrl(msr->index, msr->data);
+		rdmsrl_safe(msr->index, &msr->data);
 		break;
 	default:
 		if (kvm_x86_ops->get_msr_feature(msr))
@@ -4874,6 +4901,9 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v
 int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
 				unsigned int bytes, struct x86_exception *exception)
 {
+	/* kvm_write_guest_virt_system can pull in tons of pages. */
+	vcpu->arch.l1tf_flush_l1d = true;
+
 	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
 					   PFERR_WRITE_MASK, exception);
 }
@@ -6050,6 +6080,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 	bool writeback = true;
 	bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 
+	vcpu->arch.l1tf_flush_l1d = true;
+
 	/*
 	 * Clear write_fault_to_shadow_pgtable here to ensure it is
 	 * never reused.
@@ -7579,6 +7611,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
 		if (kvm_vcpu_running(vcpu)) {
@@ -8698,6 +8731,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
+	vcpu->arch.l1tf_flush_l1d = true;
 	kvm_x86_ops->sched_in(vcpu, cpu);
 }
 
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 298ef1479240..3b24dc05251c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -256,7 +256,7 @@ ENTRY(__memcpy_mcsafe)
 
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
-	xorq %rax, %rax
+	xorl %eax, %eax
 	ret
 ENDPROC(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 2f3c9196b834..a12afff146d1 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -111,6 +111,8 @@ static struct addr_marker address_markers[] = {
 	[END_OF_SPACE_NR]	= { -1,			NULL }
 };
 
+#define INIT_PGD	((pgd_t *) &init_top_pgt)
+
 #else /* CONFIG_X86_64 */
 
 enum address_markers_idx {
@@ -121,6 +123,9 @@ enum address_markers_idx {
 #ifdef CONFIG_HIGHMEM
 	PKMAP_BASE_NR,
 #endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	LDT_NR,
+#endif
 	CPU_ENTRY_AREA_NR,
 	FIXADDR_START_NR,
 	END_OF_SPACE_NR,
@@ -134,11 +139,16 @@ static struct addr_marker address_markers[] = {
 #ifdef CONFIG_HIGHMEM
 	[PKMAP_BASE_NR]		= { 0UL,		"Persistent kmap() Area" },
 #endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	[LDT_NR]		= { 0UL,		"LDT remap" },
+#endif
 	[CPU_ENTRY_AREA_NR]	= { 0UL,		"CPU entry area" },
 	[FIXADDR_START_NR]	= { 0UL,		"Fixmap area" },
 	[END_OF_SPACE_NR]	= { -1,			NULL }
 };
 
+#define INIT_PGD	(swapper_pg_dir)
+
 #endif /* !CONFIG_X86_64 */
 
 /* Multipliers for offsets within the PTEs */
@@ -496,11 +506,7 @@ static inline bool is_hypervisor_range(int idx)
 static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 				       bool checkwx, bool dmesg)
 {
-#ifdef CONFIG_X86_64
-	pgd_t *start = (pgd_t *) &init_top_pgt;
-#else
-	pgd_t *start = swapper_pg_dir;
-#endif
+	pgd_t *start = INIT_PGD;
 	pgprotval_t prot, eff;
 	int i;
 	struct pg_state st = {};
@@ -563,12 +569,13 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
 }
 EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
 
-static void ptdump_walk_user_pgd_level_checkwx(void)
+void ptdump_walk_user_pgd_level_checkwx(void)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
-	pgd_t *pgd = (pgd_t *) &init_top_pgt;
+	pgd_t *pgd = INIT_PGD;
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!(__supported_pte_mask & _PAGE_NX) ||
+	    !static_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pr_info("x86/mm: Checking user space page tables\n");
@@ -580,7 +587,6 @@ static void ptdump_walk_user_pgd_level_checkwx(void)
 void ptdump_walk_pgd_level_checkwx(void)
 {
 	ptdump_walk_pgd_level_core(NULL, NULL, true, false);
-	ptdump_walk_user_pgd_level_checkwx();
 }
 
 static int __init pt_dump_init(void)
@@ -609,6 +615,9 @@ static int __init pt_dump_init(void)
 # endif
 	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
 	address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
+# ifdef CONFIG_MODIFY_LDT_SYSCALL
+	address_markers[LDT_NR].start_address = LDT_BASE_ADDR;
+# endif
 #endif
 	return 0;
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9a84a0d08727..db1c042e9853 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -317,8 +317,6 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
-	WARN_ON_ONCE(in_nmi());
-
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
@@ -641,11 +639,6 @@ static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
 	return 0;
 }
 
-static const char nx_warning[] = KERN_CRIT
-"kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n";
-static const char smep_warning[] = KERN_CRIT
-"unable to execute userspace code (SMEP?) (uid: %d)\n";
-
 static void
 show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 		unsigned long address)
@@ -664,20 +657,18 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 		pte = lookup_address_in_pgd(pgd, address, &level);
 
 		if (pte && pte_present(*pte) && !pte_exec(*pte))
-			printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
+			pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n",
+				from_kuid(&init_user_ns, current_uid()));
 		if (pte && pte_present(*pte) && pte_exec(*pte) &&
 				(pgd_flags(*pgd) & _PAGE_USER) &&
 				(__read_cr4() & X86_CR4_SMEP))
-			printk(smep_warning, from_kuid(&init_user_ns, current_uid()));
+			pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n",
+				from_kuid(&init_user_ns, current_uid()));
 	}
 
-	printk(KERN_ALERT "BUG: unable to handle kernel ");
-	if (address < PAGE_SIZE)
-		printk(KERN_CONT "NULL pointer dereference");
-	else
-		printk(KERN_CONT "paging request");
-
-	printk(KERN_CONT " at %px\n", (void *) address);
+	pr_alert("BUG: unable to handle kernel %s at %px\n",
+		 address < PAGE_SIZE ? "NULL pointer dereference" : "paging request",
+		 (void *)address);
 
 	dump_pagetable(address);
 }
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index cee58a972cb2..acfab322fbe0 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -4,6 +4,8 @@
 #include <linux/swap.h>
 #include <linux/memblock.h>
 #include <linux/bootmem.h>	/* for max_low_pfn */
+#include <linux/swapfile.h>
+#include <linux/swapops.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -773,13 +775,44 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	}
 }
 
+/*
+ * begin/end can be in the direct map or the "high kernel mapping"
+ * used for the kernel image only.  free_init_pages() will do the
+ * right thing for either kind of address.
+ */
+void free_kernel_image_pages(void *begin, void *end)
+{
+	unsigned long begin_ul = (unsigned long)begin;
+	unsigned long end_ul = (unsigned long)end;
+	unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT;
+
+
+	free_init_pages("unused kernel image", begin_ul, end_ul);
+
+	/*
+	 * PTI maps some of the kernel into userspace.  For performance,
+	 * this includes some kernel areas that do not contain secrets.
+	 * Those areas might be adjacent to the parts of the kernel image
+	 * being freed, which may contain secrets.  Remove the "high kernel
+	 * image mapping" for these freed areas, ensuring they are not even
+	 * potentially vulnerable to Meltdown regardless of the specific
+	 * optimizations PTI is currently using.
+	 *
+	 * The "noalias" prevents unmapping the direct map alias which is
+	 * needed to access the freed pages.
+	 *
+	 * This is only valid for 64bit kernels. 32bit has only one mapping
+	 * which can't be treated in this way for obvious reasons.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI))
+		set_memory_np_noalias(begin_ul, len_pages);
+}
+
 void __ref free_initmem(void)
 {
 	e820__reallocate_tables();
 
-	free_init_pages("unused kernel",
-			(unsigned long)(&__init_begin),
-			(unsigned long)(&__init_end));
+	free_kernel_image_pages(&__init_begin, &__init_end);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -880,3 +913,26 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
 	__cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
 	__pte2cachemode_tbl[entry] = cache;
 }
+
+#ifdef CONFIG_SWAP
+unsigned long max_swapfile_size(void)
+{
+	unsigned long pages;
+
+	pages = generic_max_swapfile_size();
+
+	if (boot_cpu_has_bug(X86_BUG_L1TF)) {
+		/* Limit the swap file size to MAX_PA/2 for L1TF workaround */
+		unsigned long l1tf_limit = l1tf_pfn_limit() + 1;
+		/*
+		 * We encode swap offsets also with 3 bits below those for pfn
+		 * which makes the usable limit higher.
+		 */
+#if CONFIG_PGTABLE_LEVELS > 2
+		l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
+#endif
+		pages = min_t(unsigned long, l1tf_limit, pages);
+	}
+	return pages;
+}
+#endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a688617c727e..dd519f372169 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1283,20 +1283,10 @@ void mark_rodata_ro(void)
 	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
 #endif
 
-	free_init_pages("unused kernel",
-			(unsigned long) __va(__pa_symbol(text_end)),
-			(unsigned long) __va(__pa_symbol(rodata_start)));
-	free_init_pages("unused kernel",
-			(unsigned long) __va(__pa_symbol(rodata_end)),
-			(unsigned long) __va(__pa_symbol(_sdata)));
+	free_kernel_image_pages((void *)text_end, (void *)rodata_start);
+	free_kernel_image_pages((void *)rodata_end, (void *)_sdata);
 
 	debug_checkwx();
-
-	/*
-	 * Do this after all of the manipulation of the
-	 * kernel text page tables are complete.
-	 */
-	pti_clone_kernel_text();
 }
 
 int kern_addr_valid(unsigned long addr)
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 7c8686709636..79eb55ce69a9 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -126,24 +126,29 @@ static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr)
 
 static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old)
 {
+	pmd_t new_pmd;
 	pmdval_t v = pmd_val(*pmd);
 	if (clear) {
-		*old = v & _PAGE_PRESENT;
-		v &= ~_PAGE_PRESENT;
-	} else	/* presume this has been called with clear==true previously */
-		v |= *old;
-	set_pmd(pmd, __pmd(v));
+		*old = v;
+		new_pmd = pmd_mknotpresent(*pmd);
+	} else {
+		/* Presume this has been called with clear==true previously */
+		new_pmd = __pmd(*old);
+	}
+	set_pmd(pmd, new_pmd);
 }
 
 static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
 {
 	pteval_t v = pte_val(*pte);
 	if (clear) {
-		*old = v & _PAGE_PRESENT;
-		v &= ~_PAGE_PRESENT;
-	} else	/* presume this has been called with clear==true previously */
-		v |= *old;
-	set_pte_atomic(pte, __pte(v));
+		*old = v;
+		/* Nothing should care about address */
+		pte_clear(&init_mm, 0, pte);
+	} else {
+		/* Presume this has been called with clear==true previously */
+		set_pte_atomic(pte, __pte(*old));
+	}
 }
 
 static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 48c591251600..f40ab8185d94 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -240,3 +240,24 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t count)
 
 	return phys_addr_valid(addr + count - 1);
 }
+
+/*
+ * Only allow root to set high MMIO mappings to PROT_NONE.
+ * This prevents an unpriv. user to set them to PROT_NONE and invert
+ * them, then pointing to valid memory for L1TF speculation.
+ *
+ * Note: for locked down kernels may want to disable the root override.
+ */
+bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return true;
+	if (!__pte_needs_invert(pgprot_val(prot)))
+		return true;
+	/* If it's real memory always allow */
+	if (pfn_valid(pfn))
+		return true;
+	if (pfn > l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN))
+		return false;
+	return true;
+}
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 34a2a3bfde9c..b54d52a2d00a 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -61,7 +61,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
 	eb->nid = nid;
 
 	if (emu_nid_to_phys[nid] == NUMA_NO_NODE)
-		emu_nid_to_phys[nid] = nid;
+		emu_nid_to_phys[nid] = pb->nid;
 
 	pb->start += size;
 	if (pb->start >= pb->end) {
@@ -198,40 +198,73 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 	return end;
 }
 
+static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes)
+{
+	unsigned long max_pfn = PHYS_PFN(max_addr);
+	unsigned long base_pfn = PHYS_PFN(base);
+	unsigned long hole_pfns = PHYS_PFN(hole);
+
+	return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes);
+}
+
 /*
  * Sets up fake nodes of `size' interleaved over physical nodes ranging from
  * `addr' to `max_addr'.
  *
  * Returns zero on success or negative on error.
  */
-static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
 					      struct numa_meminfo *pi,
-					      u64 addr, u64 max_addr, u64 size)
+					      u64 addr, u64 max_addr, u64 size,
+					      int nr_nodes, struct numa_memblk *pblk,
+					      int nid)
 {
 	nodemask_t physnode_mask = numa_nodes_parsed;
+	int i, ret, uniform = 0;
 	u64 min_size;
-	int nid = 0;
-	int i, ret;
 
-	if (!size)
+	if ((!size && !nr_nodes) || (nr_nodes && !pblk))
 		return -1;
+
 	/*
-	 * The limit on emulated nodes is MAX_NUMNODES, so the size per node is
-	 * increased accordingly if the requested size is too small.  This
-	 * creates a uniform distribution of node sizes across the entire
-	 * machine (but not necessarily over physical nodes).
+	 * In the 'uniform' case split the passed in physical node by
+	 * nr_nodes, in the non-uniform case, ignore the passed in
+	 * physical block and try to create nodes of at least size
+	 * @size.
+	 *
+	 * In the uniform case, split the nodes strictly by physical
+	 * capacity, i.e. ignore holes. In the non-uniform case account
+	 * for holes and treat @size as a minimum floor.
 	 */
-	min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES;
-	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
-	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
-		min_size = (min_size + FAKE_NODE_MIN_SIZE) &
-						FAKE_NODE_MIN_HASH_MASK;
+	if (!nr_nodes)
+		nr_nodes = MAX_NUMNODES;
+	else {
+		nodes_clear(physnode_mask);
+		node_set(pblk->nid, physnode_mask);
+		uniform = 1;
+	}
+
+	if (uniform) {
+		min_size = uniform_size(max_addr, addr, 0, nr_nodes);
+		size = min_size;
+	} else {
+		/*
+		 * The limit on emulated nodes is MAX_NUMNODES, so the
+		 * size per node is increased accordingly if the
+		 * requested size is too small.  This creates a uniform
+		 * distribution of node sizes across the entire machine
+		 * (but not necessarily over physical nodes).
+		 */
+		min_size = uniform_size(max_addr, addr,
+				mem_hole_size(addr, max_addr), nr_nodes);
+	}
+	min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE);
 	if (size < min_size) {
 		pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
 			size >> 20, min_size >> 20);
 		size = min_size;
 	}
-	size &= FAKE_NODE_MIN_HASH_MASK;
+	size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE);
 
 	/*
 	 * Fill physical nodes with fake nodes of size until there is no memory
@@ -248,10 +281,14 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 				node_clear(i, physnode_mask);
 				continue;
 			}
+
 			start = pi->blk[phys_blk].start;
 			limit = pi->blk[phys_blk].end;
 
-			end = find_end_of_node(start, limit, size);
+			if (uniform)
+				end = start + size;
+			else
+				end = find_end_of_node(start, limit, size);
 			/*
 			 * If there won't be at least FAKE_NODE_MIN_SIZE of
 			 * non-reserved memory in ZONE_DMA32 for the next node,
@@ -266,7 +303,8 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 			 * next node, this one must extend to the end of the
 			 * physical node.
 			 */
-			if (limit - end - mem_hole_size(end, limit) < size)
+			if ((limit - end - mem_hole_size(end, limit) < size)
+					&& !uniform)
 				end = limit;
 
 			ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
@@ -276,7 +314,15 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 				return ret;
 		}
 	}
-	return 0;
+	return nid;
+}
+
+static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+					      struct numa_meminfo *pi,
+					      u64 addr, u64 max_addr, u64 size)
+{
+	return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
+			0, NULL, NUMA_NO_NODE);
 }
 
 int __init setup_emu2phys_nid(int *dfl_phys_nid)
@@ -346,7 +392,28 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	 * the fixed node size.  Otherwise, if it is just a single number N,
 	 * split the system RAM into N fake nodes.
 	 */
-	if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
+	if (strchr(emu_cmdline, 'U')) {
+		nodemask_t physnode_mask = numa_nodes_parsed;
+		unsigned long n;
+		int nid = 0;
+
+		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
+		ret = -1;
+		for_each_node_mask(i, physnode_mask) {
+			ret = split_nodes_size_interleave_uniform(&ei, &pi,
+					pi.blk[i].start, pi.blk[i].end, 0,
+					n, &pi.blk[i], nid);
+			if (ret < 0)
+				break;
+			if (ret < n) {
+				pr_info("%s: phys: %d only got %d of %ld nodes, failing\n",
+						__func__, i, ret, n);
+				ret = -1;
+				break;
+			}
+			nid = ret;
+		}
+	} else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
 		u64 size;
 
 		size = memparse(emu_cmdline, &emu_cmdline);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 3bded76e8d5c..8d6c34fe49be 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -53,6 +53,7 @@ static DEFINE_SPINLOCK(cpa_lock);
 #define CPA_FLUSHTLB 1
 #define CPA_ARRAY 2
 #define CPA_PAGES_ARRAY 4
+#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
 
 #ifdef CONFIG_PROC_FS
 static unsigned long direct_pages_count[PG_LEVEL_NUM];
@@ -1014,8 +1015,8 @@ static long populate_pmd(struct cpa_data *cpa,
 
 		pmd = pmd_offset(pud, start);
 
-		set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
-				   massage_pgprot(pmd_pgprot)));
+		set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn,
+					canon_pgprot(pmd_pgprot))));
 
 		start	  += PMD_SIZE;
 		cpa->pfn  += PMD_SIZE >> PAGE_SHIFT;
@@ -1087,8 +1088,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d,
 	 * Map everything starting from the Gb boundary, possibly with 1G pages
 	 */
 	while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) {
-		set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
-				   massage_pgprot(pud_pgprot)));
+		set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn,
+				   canon_pgprot(pud_pgprot))));
 
 		start	  += PUD_SIZE;
 		cpa->pfn  += PUD_SIZE >> PAGE_SHIFT;
@@ -1486,6 +1487,9 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	/* No alias checking for _NX bit modifications */
 	checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;
+	/* Has caller explicitly disabled alias checking? */
+	if (in_flag & CPA_NO_CHECK_ALIAS)
+		checkalias = 0;
 
 	ret = __change_page_attr_set_clr(&cpa, checkalias);
 
@@ -1772,6 +1776,15 @@ int set_memory_np(unsigned long addr, int numpages)
 	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
 }
 
+int set_memory_np_noalias(unsigned long addr, int numpages)
+{
+	int cpa_flags = CPA_NO_CHECK_ALIAS;
+
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+					__pgprot(_PAGE_PRESENT), 0,
+					cpa_flags, NULL);
+}
+
 int set_memory_4k(unsigned long addr, int numpages)
 {
 	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
@@ -1784,6 +1797,12 @@ int set_memory_nonglobal(unsigned long addr, int numpages)
 				      __pgprot(_PAGE_GLOBAL), 0);
 }
 
+int set_memory_global(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages,
+				    __pgprot(_PAGE_GLOBAL), 0);
+}
+
 static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 {
 	struct cpa_data cpa;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 47b5951e592b..3ef095c70ae3 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -182,6 +182,14 @@ static void pgd_dtor(pgd_t *pgd)
  */
 #define PREALLOCATED_PMDS	UNSHARED_PTRS_PER_PGD
 
+/*
+ * We allocate separate PMDs for the kernel part of the user page-table
+ * when PTI is enabled. We need them to map the per-process LDT into the
+ * user-space page-table.
+ */
+#define PREALLOCATED_USER_PMDS	 (static_cpu_has(X86_FEATURE_PTI) ? \
+					KERNEL_PGD_PTRS : 0)
+
 void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 {
 	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
@@ -202,14 +210,14 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 
 /* No need to prepopulate any pagetable entries in non-PAE modes. */
 #define PREALLOCATED_PMDS	0
-
+#define PREALLOCATED_USER_PMDS	 0
 #endif	/* CONFIG_X86_PAE */
 
-static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
+static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
 {
 	int i;
 
-	for(i = 0; i < PREALLOCATED_PMDS; i++)
+	for (i = 0; i < count; i++)
 		if (pmds[i]) {
 			pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
 			free_page((unsigned long)pmds[i]);
@@ -217,7 +225,7 @@ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
 		}
 }
 
-static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
+static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
 {
 	int i;
 	bool failed = false;
@@ -226,7 +234,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
 	if (mm == &init_mm)
 		gfp &= ~__GFP_ACCOUNT;
 
-	for(i = 0; i < PREALLOCATED_PMDS; i++) {
+	for (i = 0; i < count; i++) {
 		pmd_t *pmd = (pmd_t *)__get_free_page(gfp);
 		if (!pmd)
 			failed = true;
@@ -241,7 +249,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
 	}
 
 	if (failed) {
-		free_pmds(mm, pmds);
+		free_pmds(mm, pmds, count);
 		return -ENOMEM;
 	}
 
@@ -254,23 +262,38 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
  * preallocate which never got a corresponding vma will need to be
  * freed manually.
  */
+static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp)
+{
+	pgd_t pgd = *pgdp;
+
+	if (pgd_val(pgd) != 0) {
+		pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+
+		*pgdp = native_make_pgd(0);
+
+		paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
+		pmd_free(mm, pmd);
+		mm_dec_nr_pmds(mm);
+	}
+}
+
 static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
 {
 	int i;
 
-	for(i = 0; i < PREALLOCATED_PMDS; i++) {
-		pgd_t pgd = pgdp[i];
+	for (i = 0; i < PREALLOCATED_PMDS; i++)
+		mop_up_one_pmd(mm, &pgdp[i]);
 
-		if (pgd_val(pgd) != 0) {
-			pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
 
-			pgdp[i] = native_make_pgd(0);
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
 
-			paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
-			pmd_free(mm, pmd);
-			mm_dec_nr_pmds(mm);
-		}
-	}
+	pgdp = kernel_to_user_pgdp(pgdp);
+
+	for (i = 0; i < PREALLOCATED_USER_PMDS; i++)
+		mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]);
+#endif
 }
 
 static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
@@ -296,6 +319,38 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
 	}
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+				     pgd_t *k_pgd, pmd_t *pmds[])
+{
+	pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	p4d_t *u_p4d;
+	pud_t *u_pud;
+	int i;
+
+	u_p4d = p4d_offset(u_pgd, 0);
+	u_pud = pud_offset(u_p4d, 0);
+
+	s_pgd += KERNEL_PGD_BOUNDARY;
+	u_pud += KERNEL_PGD_BOUNDARY;
+
+	for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) {
+		pmd_t *pmd = pmds[i];
+
+		memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd),
+		       sizeof(pmd_t) * PTRS_PER_PMD);
+
+		pud_populate(mm, u_pud, pmd);
+	}
+
+}
+#else
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+				     pgd_t *k_pgd, pmd_t *pmds[])
+{
+}
+#endif
 /*
  * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also
  * assumes that pgd should be in one page.
@@ -329,9 +384,6 @@ static int __init pgd_cache_init(void)
 	 */
 	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
 				      SLAB_PANIC, NULL);
-	if (!pgd_cache)
-		return -ENOMEM;
-
 	return 0;
 }
 core_initcall(pgd_cache_init);
@@ -343,7 +395,8 @@ static inline pgd_t *_pgd_alloc(void)
 	 * We allocate one page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return (pgd_t *)__get_free_page(PGALLOC_GFP);
+		return (pgd_t *)__get_free_pages(PGALLOC_GFP,
+						 PGD_ALLOCATION_ORDER);
 
 	/*
 	 * Now PAE kernel is not running as a Xen domain. We can allocate
@@ -355,7 +408,7 @@ static inline pgd_t *_pgd_alloc(void)
 static inline void _pgd_free(pgd_t *pgd)
 {
 	if (!SHARED_KERNEL_PMD)
-		free_page((unsigned long)pgd);
+		free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
 	else
 		kmem_cache_free(pgd_cache, pgd);
 }
@@ -375,6 +428,7 @@ static inline void _pgd_free(pgd_t *pgd)
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd;
+	pmd_t *u_pmds[PREALLOCATED_USER_PMDS];
 	pmd_t *pmds[PREALLOCATED_PMDS];
 
 	pgd = _pgd_alloc();
@@ -384,12 +438,15 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	mm->pgd = pgd;
 
-	if (preallocate_pmds(mm, pmds) != 0)
+	if (preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0)
 		goto out_free_pgd;
 
-	if (paravirt_pgd_alloc(mm) != 0)
+	if (preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0)
 		goto out_free_pmds;
 
+	if (paravirt_pgd_alloc(mm) != 0)
+		goto out_free_user_pmds;
+
 	/*
 	 * Make sure that pre-populating the pmds is atomic with
 	 * respect to anything walking the pgd_list, so that they
@@ -399,13 +456,16 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	pgd_ctor(mm, pgd);
 	pgd_prepopulate_pmd(mm, pgd, pmds);
+	pgd_prepopulate_user_pmd(mm, pgd, u_pmds);
 
 	spin_unlock(&pgd_lock);
 
 	return pgd;
 
+out_free_user_pmds:
+	free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS);
 out_free_pmds:
-	free_pmds(mm, pmds);
+	free_pmds(mm, pmds, PREALLOCATED_PMDS);
 out_free_pgd:
 	_pgd_free(pgd);
 out:
@@ -719,28 +779,50 @@ int pmd_clear_huge(pmd_t *pmd)
 	return 0;
 }
 
+#ifdef CONFIG_X86_64
 /**
  * pud_free_pmd_page - Clear pud entry and free pmd page.
  * @pud: Pointer to a PUD.
+ * @addr: Virtual address associated with pud.
  *
- * Context: The pud range has been unmaped and TLB purged.
+ * Context: The pud range has been unmapped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ *
+ * NOTE: Callers must allow a single page allocation.
  */
-int pud_free_pmd_page(pud_t *pud)
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
-	pmd_t *pmd;
+	pmd_t *pmd, *pmd_sv;
+	pte_t *pte;
 	int i;
 
 	if (pud_none(*pud))
 		return 1;
 
 	pmd = (pmd_t *)pud_page_vaddr(*pud);
+	pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL);
+	if (!pmd_sv)
+		return 0;
 
-	for (i = 0; i < PTRS_PER_PMD; i++)
-		if (!pmd_free_pte_page(&pmd[i]))
-			return 0;
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd_sv[i] = pmd[i];
+		if (!pmd_none(pmd[i]))
+			pmd_clear(&pmd[i]);
+	}
 
 	pud_clear(pud);
+
+	/* INVLPG to clear all paging-structure caches */
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(pmd_sv[i])) {
+			pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
+			free_page((unsigned long)pte);
+		}
+	}
+
+	free_page((unsigned long)pmd_sv);
 	free_page((unsigned long)pmd);
 
 	return 1;
@@ -749,11 +831,12 @@ int pud_free_pmd_page(pud_t *pud)
 /**
  * pmd_free_pte_page - Clear pmd entry and free pte page.
  * @pmd: Pointer to a PMD.
+ * @addr: Virtual address associated with pmd.
  *
- * Context: The pmd range has been unmaped and TLB purged.
+ * Context: The pmd range has been unmapped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
  */
-int pmd_free_pte_page(pmd_t *pmd)
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	pte_t *pte;
 
@@ -762,8 +845,30 @@ int pmd_free_pte_page(pmd_t *pmd)
 
 	pte = (pte_t *)pmd_page_vaddr(*pmd);
 	pmd_clear(pmd);
+
+	/* INVLPG to clear all paging-structure caches */
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
 	free_page((unsigned long)pte);
 
 	return 1;
 }
+
+#else /* !CONFIG_X86_64 */
+
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
+{
+	return pud_none(*pud);
+}
+
+/*
+ * Disable free page handling on x86-PAE. This assures that ioremap()
+ * does not update sync'd pmd entries. See vmalloc_sync_one().
+ */
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+{
+	return pmd_none(*pmd);
+}
+
+#endif /* CONFIG_X86_64 */
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 4d418e705878..31341ae7309f 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -45,6 +45,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
+#include <asm/sections.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt)     "Kernel/User page tables isolation: " fmt
@@ -54,6 +55,16 @@
 #define __GFP_NOTRACK	0
 #endif
 
+/*
+ * Define the page-table levels we clone for user-space on 32
+ * and 64 bit.
+ */
+#ifdef CONFIG_X86_64
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PMD
+#else
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PTE
+#endif
+
 static void __init pti_print_if_insecure(const char *reason)
 {
 	if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
@@ -117,7 +128,7 @@ enable:
 	setup_force_cpu_cap(X86_FEATURE_PTI);
 }
 
-pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 {
 	/*
 	 * Changes to the high (kernel) portion of the kernelmode page
@@ -176,7 +187,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
 
 	if (pgd_none(*pgd)) {
 		unsigned long new_p4d_page = __get_free_page(gfp);
-		if (!new_p4d_page)
+		if (WARN_ON_ONCE(!new_p4d_page))
 			return NULL;
 
 		set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
@@ -195,13 +206,17 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
 static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 {
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
-	p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
+	p4d_t *p4d;
 	pud_t *pud;
 
+	p4d = pti_user_pagetable_walk_p4d(address);
+	if (!p4d)
+		return NULL;
+
 	BUILD_BUG_ON(p4d_large(*p4d) != 0);
 	if (p4d_none(*p4d)) {
 		unsigned long new_pud_page = __get_free_page(gfp);
-		if (!new_pud_page)
+		if (WARN_ON_ONCE(!new_pud_page))
 			return NULL;
 
 		set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
@@ -215,7 +230,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	}
 	if (pud_none(*pud)) {
 		unsigned long new_pmd_page = __get_free_page(gfp);
-		if (!new_pmd_page)
+		if (WARN_ON_ONCE(!new_pmd_page))
 			return NULL;
 
 		set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
@@ -224,7 +239,6 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	return pmd_offset(pud, address);
 }
 
-#ifdef CONFIG_X86_VSYSCALL_EMULATION
 /*
  * Walk the shadow copy of the page tables (optionally) trying to allocate
  * page table pages on the way down.  Does not support large pages.
@@ -237,9 +251,13 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 {
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
-	pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
+	pmd_t *pmd;
 	pte_t *pte;
 
+	pmd = pti_user_pagetable_walk_pmd(address);
+	if (!pmd)
+		return NULL;
+
 	/* We can't do anything sensible if we hit a large mapping. */
 	if (pmd_large(*pmd)) {
 		WARN_ON(1);
@@ -262,6 +280,7 @@ static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 	return pte;
 }
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 static void __init pti_setup_vsyscall(void)
 {
 	pte_t *pte, *target_pte;
@@ -282,8 +301,14 @@ static void __init pti_setup_vsyscall(void)
 static void __init pti_setup_vsyscall(void) { }
 #endif
 
+enum pti_clone_level {
+	PTI_CLONE_PMD,
+	PTI_CLONE_PTE,
+};
+
 static void
-pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+pti_clone_pgtable(unsigned long start, unsigned long end,
+		  enum pti_clone_level level)
 {
 	unsigned long addr;
 
@@ -291,59 +316,105 @@ pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
 	 * Clone the populated PMDs which cover start to end. These PMD areas
 	 * can have holes.
 	 */
-	for (addr = start; addr < end; addr += PMD_SIZE) {
+	for (addr = start; addr < end;) {
+		pte_t *pte, *target_pte;
 		pmd_t *pmd, *target_pmd;
 		pgd_t *pgd;
 		p4d_t *p4d;
 		pud_t *pud;
 
+		/* Overflow check */
+		if (addr < start)
+			break;
+
 		pgd = pgd_offset_k(addr);
 		if (WARN_ON(pgd_none(*pgd)))
 			return;
 		p4d = p4d_offset(pgd, addr);
 		if (WARN_ON(p4d_none(*p4d)))
 			return;
+
 		pud = pud_offset(p4d, addr);
-		if (pud_none(*pud))
+		if (pud_none(*pud)) {
+			addr += PUD_SIZE;
 			continue;
+		}
+
 		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd))
+		if (pmd_none(*pmd)) {
+			addr += PMD_SIZE;
 			continue;
+		}
 
-		target_pmd = pti_user_pagetable_walk_pmd(addr);
-		if (WARN_ON(!target_pmd))
-			return;
-
-		/*
-		 * Only clone present PMDs.  This ensures only setting
-		 * _PAGE_GLOBAL on present PMDs.  This should only be
-		 * called on well-known addresses anyway, so a non-
-		 * present PMD would be a surprise.
-		 */
-		if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
-			return;
-
-		/*
-		 * Setting 'target_pmd' below creates a mapping in both
-		 * the user and kernel page tables.  It is effectively
-		 * global, so set it as global in both copies.  Note:
-		 * the X86_FEATURE_PGE check is not _required_ because
-		 * the CPU ignores _PAGE_GLOBAL when PGE is not
-		 * supported.  The check keeps consistentency with
-		 * code that only set this bit when supported.
-		 */
-		if (boot_cpu_has(X86_FEATURE_PGE))
-			*pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
-
-		/*
-		 * Copy the PMD.  That is, the kernelmode and usermode
-		 * tables will share the last-level page tables of this
-		 * address range
-		 */
-		*target_pmd = pmd_clear_flags(*pmd, clear);
+		if (pmd_large(*pmd) || level == PTI_CLONE_PMD) {
+			target_pmd = pti_user_pagetable_walk_pmd(addr);
+			if (WARN_ON(!target_pmd))
+				return;
+
+			/*
+			 * Only clone present PMDs.  This ensures only setting
+			 * _PAGE_GLOBAL on present PMDs.  This should only be
+			 * called on well-known addresses anyway, so a non-
+			 * present PMD would be a surprise.
+			 */
+			if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
+				return;
+
+			/*
+			 * Setting 'target_pmd' below creates a mapping in both
+			 * the user and kernel page tables.  It is effectively
+			 * global, so set it as global in both copies.  Note:
+			 * the X86_FEATURE_PGE check is not _required_ because
+			 * the CPU ignores _PAGE_GLOBAL when PGE is not
+			 * supported.  The check keeps consistentency with
+			 * code that only set this bit when supported.
+			 */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
+
+			/*
+			 * Copy the PMD.  That is, the kernelmode and usermode
+			 * tables will share the last-level page tables of this
+			 * address range
+			 */
+			*target_pmd = *pmd;
+
+			addr += PMD_SIZE;
+
+		} else if (level == PTI_CLONE_PTE) {
+
+			/* Walk the page-table down to the pte level */
+			pte = pte_offset_kernel(pmd, addr);
+			if (pte_none(*pte)) {
+				addr += PAGE_SIZE;
+				continue;
+			}
+
+			/* Only clone present PTEs */
+			if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT)))
+				return;
+
+			/* Allocate PTE in the user page-table */
+			target_pte = pti_user_pagetable_walk_pte(addr);
+			if (WARN_ON(!target_pte))
+				return;
+
+			/* Set GLOBAL bit in both PTEs */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pte = pte_set_flags(*pte, _PAGE_GLOBAL);
+
+			/* Clone the PTE */
+			*target_pte = *pte;
+
+			addr += PAGE_SIZE;
+
+		} else {
+			BUG();
+		}
 	}
 }
 
+#ifdef CONFIG_X86_64
 /*
  * Clone a single p4d (i.e. a top-level entry on 4-level systems and a
  * next-level entry on 5-level systems.
@@ -354,6 +425,9 @@ static void __init pti_clone_p4d(unsigned long addr)
 	pgd_t *kernel_pgd;
 
 	user_p4d = pti_user_pagetable_walk_p4d(addr);
+	if (!user_p4d)
+		return;
+
 	kernel_pgd = pgd_offset_k(addr);
 	kernel_p4d = p4d_offset(kernel_pgd, addr);
 	*user_p4d = *kernel_p4d;
@@ -367,6 +441,25 @@ static void __init pti_clone_user_shared(void)
 	pti_clone_p4d(CPU_ENTRY_AREA_BASE);
 }
 
+#else /* CONFIG_X86_64 */
+
+/*
+ * On 32 bit PAE systems with 1GB of Kernel address space there is only
+ * one pgd/p4d for the whole kernel. Cloning that would map the whole
+ * address space into the user page-tables, making PTI useless. So clone
+ * the page-table on the PMD level to prevent that.
+ */
+static void __init pti_clone_user_shared(void)
+{
+	unsigned long start, end;
+
+	start = CPU_ENTRY_AREA_BASE;
+	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
+
+	pti_clone_pgtable(start, end, PTI_CLONE_PMD);
+}
+#endif /* CONFIG_X86_64 */
+
 /*
  * Clone the ESPFIX P4D into the user space visible page table
  */
@@ -380,11 +473,11 @@ static void __init pti_setup_espfix64(void)
 /*
  * Clone the populated PMDs of the entry and irqentry text and force it RO.
  */
-static void __init pti_clone_entry_text(void)
+static void pti_clone_entry_text(void)
 {
-	pti_clone_pmds((unsigned long) __entry_text_start,
-			(unsigned long) __irqentry_text_end,
-		       _PAGE_RW);
+	pti_clone_pgtable((unsigned long) __entry_text_start,
+			  (unsigned long) __irqentry_text_end,
+			  PTI_CLONE_PMD);
 }
 
 /*
@@ -435,10 +528,17 @@ static inline bool pti_kernel_image_global_ok(void)
 }
 
 /*
+ * This is the only user for these and it is not arch-generic
+ * like the other set_memory.h functions.  Just extern them.
+ */
+extern int set_memory_nonglobal(unsigned long addr, int numpages);
+extern int set_memory_global(unsigned long addr, int numpages);
+
+/*
  * For some configurations, map all of kernel text into the user page
  * tables.  This reduces TLB misses, especially on non-PCID systems.
  */
-void pti_clone_kernel_text(void)
+static void pti_clone_kernel_text(void)
 {
 	/*
 	 * rodata is part of the kernel image and is normally
@@ -446,7 +546,8 @@ void pti_clone_kernel_text(void)
 	 * clone the areas past rodata, they might contain secrets.
 	 */
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = (unsigned long)__end_rodata_hpage_align;
+	unsigned long end_clone  = (unsigned long)__end_rodata_aligned;
+	unsigned long end_global = PFN_ALIGN((unsigned long)__stop___ex_table);
 
 	if (!pti_kernel_image_global_ok())
 		return;
@@ -458,14 +559,18 @@ void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pmds(start, end, _PAGE_RW);
+	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE);
+
+	/*
+	 * pti_clone_pgtable() will set the global bit in any PMDs
+	 * that it clones, but we also need to get any PTEs in
+	 * the last level for areas that are not huge-page-aligned.
+	 */
+
+	/* Set the global bit for normal non-__init kernel text: */
+	set_memory_global(start, (end_global - start) >> PAGE_SHIFT);
 }
 
-/*
- * This is the only user for it and it is not arch-generic like
- * the other set_memory.h functions.  Just extern it.
- */
-extern int set_memory_nonglobal(unsigned long addr, int numpages);
 void pti_set_kernel_image_nonglobal(void)
 {
 	/*
@@ -477,9 +582,11 @@ void pti_set_kernel_image_nonglobal(void)
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
 
-	if (pti_kernel_image_global_ok())
-		return;
-
+	/*
+	 * This clears _PAGE_GLOBAL from the entire kernel image.
+	 * pti_clone_kernel_text() map put _PAGE_GLOBAL back for
+	 * areas that are mapped to userspace.
+	 */
 	set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT);
 }
 
@@ -493,6 +600,28 @@ void __init pti_init(void)
 
 	pr_info("enabled\n");
 
+#ifdef CONFIG_X86_32
+	/*
+	 * We check for X86_FEATURE_PCID here. But the init-code will
+	 * clear the feature flag on 32 bit because the feature is not
+	 * supported on 32 bit anyway. To print the warning we need to
+	 * check with cpuid directly again.
+	 */
+	if (cpuid_ecx(0x1) & BIT(17)) {
+		/* Use printk to work around pr_fmt() */
+		printk(KERN_WARNING "\n");
+		printk(KERN_WARNING "************************************************************\n");
+		printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!  **\n");
+		printk(KERN_WARNING "**                                                        **\n");
+		printk(KERN_WARNING "** You are using 32-bit PTI on a 64-bit PCID-capable CPU. **\n");
+		printk(KERN_WARNING "** Your performance will increase dramatically if you     **\n");
+		printk(KERN_WARNING "** switch to a 64-bit kernel!                             **\n");
+		printk(KERN_WARNING "**                                                        **\n");
+		printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!  **\n");
+		printk(KERN_WARNING "************************************************************\n");
+	}
+#endif
+
 	pti_clone_user_shared();
 
 	/* Undo all global bits from the init pagetables in head_64.S: */
@@ -502,3 +631,22 @@ void __init pti_init(void)
 	pti_setup_espfix64();
 	pti_setup_vsyscall();
 }
+
+/*
+ * Finalize the kernel mappings in the userspace page-table. Some of the
+ * mappings for the kernel image might have changed since pti_init()
+ * cloned them. This is because parts of the kernel image have been
+ * mapped RO and/or NX.  These changes need to be cloned again to the
+ * userspace page-table.
+ */
+void pti_finalize(void)
+{
+	/*
+	 * We need to clone everything (again) that maps parts of the
+	 * kernel image.
+	 */
+	pti_clone_entry_text();
+	pti_clone_kernel_text();
+
+	debug_checkwx_user();
+}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6eb1f34c3c85..752dbf4e0e50 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
+#include <linux/gfp.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -35,7 +36,7 @@
  * necessary invalidation by clearing out the 'ctx_id' which
  * forces a TLB flush when the context is loaded.
  */
-void clear_asid_other(void)
+static void clear_asid_other(void)
 {
 	u16 asid;
 
@@ -185,8 +186,11 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 {
 	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy);
 	unsigned cpu = smp_processor_id();
 	u64 next_tlb_gen;
+	bool need_flush;
+	u16 new_asid;
 
 	/*
 	 * NB: The scheduler will call us with prev == next when switching
@@ -240,20 +244,41 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			   next->context.ctx_id);
 
 		/*
-		 * We don't currently support having a real mm loaded without
-		 * our cpu set in mm_cpumask().  We have all the bookkeeping
-		 * in place to figure out whether we would need to flush
-		 * if our cpu were cleared in mm_cpumask(), but we don't
-		 * currently use it.
+		 * Even in lazy TLB mode, the CPU should stay set in the
+		 * mm_cpumask. The TLB shootdown code can figure out from
+		 * from cpu_tlbstate.is_lazy whether or not to send an IPI.
 		 */
 		if (WARN_ON_ONCE(real_prev != &init_mm &&
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 
-		return;
+		/*
+		 * If the CPU is not in lazy TLB mode, we are just switching
+		 * from one thread in a process to another thread in the same
+		 * process. No TLB flush required.
+		 */
+		if (!was_lazy)
+			return;
+
+		/*
+		 * Read the tlb_gen to check whether a flush is needed.
+		 * If the TLB is up to date, just use it.
+		 * The barrier synchronizes with the tlb_gen increment in
+		 * the TLB shootdown code.
+		 */
+		smp_mb();
+		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+		if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) ==
+				next_tlb_gen)
+			return;
+
+		/*
+		 * TLB contents went out of date while we were in lazy
+		 * mode. Fall through to the TLB switching code below.
+		 */
+		new_asid = prev_asid;
+		need_flush = true;
 	} else {
-		u16 new_asid;
-		bool need_flush;
 		u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
 
 		/*
@@ -285,53 +310,60 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			sync_current_stack_to_mm(next);
 		}
 
-		/* Stop remote flushes for the previous mm */
-		VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
-				real_prev != &init_mm);
-		cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+		/*
+		 * Stop remote flushes for the previous mm.
+		 * Skip kernel threads; we never send init_mm TLB flushing IPIs,
+		 * but the bitmap manipulation can cause cache line contention.
+		 */
+		if (real_prev != &init_mm) {
+			VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
+						mm_cpumask(real_prev)));
+			cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+		}
 
 		/*
 		 * Start remote flushes and then read tlb_gen.
 		 */
-		cpumask_set_cpu(cpu, mm_cpumask(next));
+		if (next != &init_mm)
+			cpumask_set_cpu(cpu, mm_cpumask(next));
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
 		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+	}
 
-		if (need_flush) {
-			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
-			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-			load_new_mm_cr3(next->pgd, new_asid, true);
-
-			/*
-			 * NB: This gets called via leave_mm() in the idle path
-			 * where RCU functions differently.  Tracing normally
-			 * uses RCU, so we need to use the _rcuidle variant.
-			 *
-			 * (There is no good reason for this.  The idle code should
-			 *  be rearranged to call this before rcu_idle_enter().)
-			 */
-			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-		} else {
-			/* The new ASID is already up to date. */
-			load_new_mm_cr3(next->pgd, new_asid, false);
-
-			/* See above wrt _rcuidle. */
-			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
-		}
+	if (need_flush) {
+		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
+		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
+		load_new_mm_cr3(next->pgd, new_asid, true);
 
 		/*
-		 * Record last user mm's context id, so we can avoid
-		 * flushing branch buffer with IBPB if we switch back
-		 * to the same user.
+		 * NB: This gets called via leave_mm() in the idle path
+		 * where RCU functions differently.  Tracing normally
+		 * uses RCU, so we need to use the _rcuidle variant.
+		 *
+		 * (There is no good reason for this.  The idle code should
+		 *  be rearranged to call this before rcu_idle_enter().)
 		 */
-		if (next != &init_mm)
-			this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+	} else {
+		/* The new ASID is already up to date. */
+		load_new_mm_cr3(next->pgd, new_asid, false);
 
-		this_cpu_write(cpu_tlbstate.loaded_mm, next);
-		this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+		/* See above wrt _rcuidle. */
+		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
 
+	/*
+	 * Record last user mm's context id, so we can avoid
+	 * flushing branch buffer with IBPB if we switch back
+	 * to the same user.
+	 */
+	if (next != &init_mm)
+		this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+
+	this_cpu_write(cpu_tlbstate.loaded_mm, next);
+	this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+
 	load_mm_cr4(next);
 	switch_ldt(real_prev, next);
 }
@@ -354,20 +386,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
 		return;
 
-	if (tlb_defer_switch_to_init_mm()) {
-		/*
-		 * There's a significant optimization that may be possible
-		 * here.  We have accurate enough TLB flush tracking that we
-		 * don't need to maintain coherence of TLB per se when we're
-		 * lazy.  We do, however, need to maintain coherence of
-		 * paging-structure caches.  We could, in principle, leave our
-		 * old mm loaded and only switch to init_mm when
-		 * tlb_remove_page() happens.
-		 */
-		this_cpu_write(cpu_tlbstate.is_lazy, true);
-	} else {
-		switch_mm(NULL, &init_mm, NULL);
-	}
+	this_cpu_write(cpu_tlbstate.is_lazy, true);
 }
 
 /*
@@ -454,6 +473,9 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 		 * paging-structure cache to avoid speculatively reading
 		 * garbage into our TLB.  Since switching to init_mm is barely
 		 * slower than a minimal flush, just switch to init_mm.
+		 *
+		 * This should be rare, with native_flush_tlb_others skipping
+		 * IPIs to lazy TLB mode CPUs.
 		 */
 		switch_mm_irqs_off(NULL, &init_mm, NULL);
 		return;
@@ -560,6 +582,9 @@ static void flush_tlb_func_remote(void *info)
 void native_flush_tlb_others(const struct cpumask *cpumask,
 			     const struct flush_tlb_info *info)
 {
+	cpumask_var_t lazymask;
+	unsigned int cpu;
+
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (info->end == TLB_FLUSH_ALL)
 		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
@@ -583,8 +608,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 		 * that UV should be updated so that smp_call_function_many(),
 		 * etc, are optimal on UV.
 		 */
-		unsigned int cpu;
-
 		cpu = smp_processor_id();
 		cpumask = uv_flush_tlb_others(cpumask, info);
 		if (cpumask)
@@ -592,8 +615,29 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 					       (void *)info, 1);
 		return;
 	}
-	smp_call_function_many(cpumask, flush_tlb_func_remote,
+
+	/*
+	 * A temporary cpumask is used in order to skip sending IPIs
+	 * to CPUs in lazy TLB state, while keeping them in mm_cpumask(mm).
+	 * If the allocation fails, simply IPI every CPU in mm_cpumask.
+	 */
+	if (!alloc_cpumask_var(&lazymask, GFP_ATOMIC)) {
+		smp_call_function_many(cpumask, flush_tlb_func_remote,
 			       (void *)info, 1);
+		return;
+	}
+
+	cpumask_copy(lazymask, cpumask);
+
+	for_each_cpu(cpu, lazymask) {
+		if (per_cpu(cpu_tlbstate.is_lazy, cpu))
+			cpumask_clear_cpu(cpu, lazymask);
+	}
+
+	smp_call_function_many(lazymask, flush_tlb_func_remote,
+			       (void *)info, 1);
+
+	free_cpumask_var(lazymask);
 }
 
 /*
@@ -646,6 +690,68 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	put_cpu();
 }
 
+void tlb_flush_remove_tables_local(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm &&
+			this_cpu_read(cpu_tlbstate.is_lazy)) {
+		/*
+		 * We're in lazy mode.  We need to at least flush our
+		 * paging-structure cache to avoid speculatively reading
+		 * garbage into our TLB.  Since switching to init_mm is barely
+		 * slower than a minimal flush, just switch to init_mm.
+		 */
+		switch_mm_irqs_off(NULL, &init_mm, NULL);
+	}
+}
+
+static void mm_fill_lazy_tlb_cpu_mask(struct mm_struct *mm,
+				      struct cpumask *lazy_cpus)
+{
+	int cpu;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		if (!per_cpu(cpu_tlbstate.is_lazy, cpu))
+			cpumask_set_cpu(cpu, lazy_cpus);
+	}
+}
+
+void tlb_flush_remove_tables(struct mm_struct *mm)
+{
+	int cpu = get_cpu();
+	cpumask_var_t lazy_cpus;
+
+	if (cpumask_any_but(mm_cpumask(mm), cpu) >= nr_cpu_ids) {
+		put_cpu();
+		return;
+	}
+
+	if (!zalloc_cpumask_var(&lazy_cpus, GFP_ATOMIC)) {
+		/*
+		 * If the cpumask allocation fails, do a brute force flush
+		 * on all the CPUs that have this mm loaded.
+		 */
+		smp_call_function_many(mm_cpumask(mm),
+				tlb_flush_remove_tables_local, (void *)mm, 1);
+		put_cpu();
+		return;
+	}
+
+	/*
+	 * CPUs with !is_lazy either received a TLB flush IPI while the user
+	 * pages in this address range were unmapped, or have context switched
+	 * and reloaded %CR3 since then.
+	 *
+	 * Shootdown IPIs at page table freeing time only need to be sent to
+	 * CPUs that may have out of date TLB contents.
+	 */
+	mm_fill_lazy_tlb_cpu_mask(mm, lazy_cpus);
+	smp_call_function_many(lazy_cpus,
+				tlb_flush_remove_tables_local, (void *)mm, 1);
+	free_cpumask_var(lazy_cpus);
+	put_cpu();
+}
 
 static void do_flush_tlb_all(void *info)
 {
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 55799873ebe5..8f6cc71e0848 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -1441,8 +1441,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth)
 
 	/* sub esp,STACK_SIZE */
 	EMIT2_off32(0x81, 0xEC, STACK_SIZE);
-	/* sub ebp,SCRATCH_SIZE+4+12*/
-	EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16);
+	/* sub ebp,SCRATCH_SIZE+12*/
+	EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 12);
 	/* xor ebx,ebx */
 	EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX));
 
@@ -1475,8 +1475,8 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth)
 	/* mov edx,dword ptr [ebp+off]*/
 	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1]));
 
-	/* add ebp,SCRATCH_SIZE+4+12*/
-	EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16);
+	/* add ebp,SCRATCH_SIZE+12*/
+	EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 12);
 
 	/* mov ebx,dword ptr [ebp-12]*/
 	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index e01f7ceb9e7a..ee5d08f25ce4 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -166,14 +166,14 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 		pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
 		set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
 
-		if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+		if (!pgd_present(*pgd))
 			continue;
 
 		for (i = 0; i < PTRS_PER_P4D; i++) {
 			p4d = p4d_offset(pgd,
 					 pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
 
-			if (!(p4d_val(*p4d) & _PAGE_PRESENT))
+			if (!p4d_present(*p4d))
 				continue;
 
 			pud = (pud_t *)p4d_page_vaddr(*p4d);
@@ -417,7 +417,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va)
 	if (!(md->attribute & EFI_MEMORY_WB))
 		flags |= _PAGE_PCD;
 
-	if (sev_active())
+	if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO)
 		flags |= _PAGE_ENC;
 
 	pfn = md->phys_addr >> PAGE_SHIFT;
@@ -636,6 +636,8 @@ void efi_switch_mm(struct mm_struct *mm)
 #ifdef CONFIG_EFI_MIXED
 extern efi_status_t efi64_thunk(u32, ...);
 
+static DEFINE_SPINLOCK(efi_runtime_lock);
+
 #define runtime_service32(func)						 \
 ({									 \
 	u32 table = (u32)(unsigned long)efi.systab;			 \
@@ -657,17 +659,14 @@ extern efi_status_t efi64_thunk(u32, ...);
 #define efi_thunk(f, ...)						\
 ({									\
 	efi_status_t __s;						\
-	unsigned long __flags;						\
 	u32 __func;							\
 									\
-	local_irq_save(__flags);					\
 	arch_efi_call_virt_setup();					\
 									\
 	__func = runtime_service32(f);					\
 	__s = efi64_thunk(__func, __VA_ARGS__);				\
 									\
 	arch_efi_call_virt_teardown();					\
-	local_irq_restore(__flags);					\
 									\
 	__s;								\
 })
@@ -702,14 +701,17 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	efi_status_t status;
 	u32 phys_tm, phys_tc;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_tm = virt_to_phys_or_null(tm);
 	phys_tc = virt_to_phys_or_null(tc);
 
 	status = efi_thunk(get_time, phys_tm, phys_tc);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -719,13 +721,16 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm)
 {
 	efi_status_t status;
 	u32 phys_tm;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_time, phys_tm);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -737,8 +742,10 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
 {
 	efi_status_t status;
 	u32 phys_enabled, phys_pending, phys_tm;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_enabled = virt_to_phys_or_null(enabled);
 	phys_pending = virt_to_phys_or_null(pending);
@@ -747,6 +754,7 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
 	status = efi_thunk(get_wakeup_time, phys_enabled,
 			     phys_pending, phys_tm);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -757,13 +765,16 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 {
 	efi_status_t status;
 	u32 phys_tm;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_wakeup_time, enabled, phys_tm);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -781,6 +792,9 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 	efi_status_t status;
 	u32 phys_name, phys_vendor, phys_attr;
 	u32 phys_data_size, phys_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_data_size = virt_to_phys_or_null(data_size);
 	phys_vendor = virt_to_phys_or_null(vendor);
@@ -791,6 +805,8 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 	status = efi_thunk(get_variable, phys_name, phys_vendor,
 			   phys_attr, phys_data_size, phys_data);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -800,6 +816,34 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 {
 	u32 phys_name, phys_vendor, phys_data;
 	efi_status_t status;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_data = virt_to_phys_or_null_size(data, data_size);
+
+	/* If data_size is > sizeof(u32) we've got problems */
+	status = efi_thunk(set_variable, phys_name, phys_vendor,
+			   attr, data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
+				   u32 attr, unsigned long data_size,
+				   void *data)
+{
+	u32 phys_name, phys_vendor, phys_data;
+	efi_status_t status;
+	unsigned long flags;
+
+	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+		return EFI_NOT_READY;
 
 	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
 	phys_vendor = virt_to_phys_or_null(vendor);
@@ -809,6 +853,8 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	status = efi_thunk(set_variable, phys_name, phys_vendor,
 			   attr, data_size, phys_data);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -819,6 +865,9 @@ efi_thunk_get_next_variable(unsigned long *name_size,
 {
 	efi_status_t status;
 	u32 phys_name_size, phys_name, phys_vendor;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_name_size = virt_to_phys_or_null(name_size);
 	phys_vendor = virt_to_phys_or_null(vendor);
@@ -827,6 +876,8 @@ efi_thunk_get_next_variable(unsigned long *name_size,
 	status = efi_thunk(get_next_variable, phys_name_size,
 			   phys_name, phys_vendor);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -835,10 +886,15 @@ efi_thunk_get_next_high_mono_count(u32 *count)
 {
 	efi_status_t status;
 	u32 phys_count;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_count = virt_to_phys_or_null(count);
 	status = efi_thunk(get_next_high_mono_count, phys_count);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -847,10 +903,15 @@ efi_thunk_reset_system(int reset_type, efi_status_t status,
 		       unsigned long data_size, efi_char16_t *data)
 {
 	u32 phys_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_data = virt_to_phys_or_null_size(data, data_size);
 
 	efi_thunk(reset_system, reset_type, status, data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 }
 
 static efi_status_t
@@ -872,10 +933,40 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
 {
 	efi_status_t status;
 	u32 phys_storage, phys_remaining, phys_max;
+	unsigned long flags;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
+	phys_storage = virt_to_phys_or_null(storage_space);
+	phys_remaining = virt_to_phys_or_null(remaining_space);
+	phys_max = virt_to_phys_or_null(max_variable_size);
+
+	status = efi_thunk(query_variable_info, attr, phys_storage,
+			   phys_remaining, phys_max);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_query_variable_info_nonblocking(u32 attr, u64 *storage_space,
+					  u64 *remaining_space,
+					  u64 *max_variable_size)
+{
+	efi_status_t status;
+	u32 phys_storage, phys_remaining, phys_max;
+	unsigned long flags;
 
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
+	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+		return EFI_NOT_READY;
+
 	phys_storage = virt_to_phys_or_null(storage_space);
 	phys_remaining = virt_to_phys_or_null(remaining_space);
 	phys_max = virt_to_phys_or_null(max_variable_size);
@@ -883,6 +974,8 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
 	status = efi_thunk(query_variable_info, attr, phys_storage,
 			   phys_remaining, phys_max);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -908,9 +1001,11 @@ void efi_thunk_runtime_setup(void)
 	efi.get_variable = efi_thunk_get_variable;
 	efi.get_next_variable = efi_thunk_get_next_variable;
 	efi.set_variable = efi_thunk_set_variable;
+	efi.set_variable_nonblocking = efi_thunk_set_variable_nonblocking;
 	efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count;
 	efi.reset_system = efi_thunk_reset_system;
 	efi.query_variable_info = efi_thunk_query_variable_info;
+	efi.query_variable_info_nonblocking = efi_thunk_query_variable_info_nonblocking;
 	efi.update_capsule = efi_thunk_update_capsule;
 	efi.query_capsule_caps = efi_thunk_query_capsule_caps;
 }
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 36c1f8b9f7e0..844d31cb8a0c 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -105,12 +105,11 @@ early_param("efi_no_storage_paranoia", setup_storage_paranoia);
 */
 void efi_delete_dummy_variable(void)
 {
-	efi.set_variable((efi_char16_t *)efi_dummy_name,
-			 &EFI_DUMMY_GUID,
-			 EFI_VARIABLE_NON_VOLATILE |
-			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
-			 EFI_VARIABLE_RUNTIME_ACCESS,
-			 0, NULL);
+	efi.set_variable_nonblocking((efi_char16_t *)efi_dummy_name,
+				     &EFI_DUMMY_GUID,
+				     EFI_VARIABLE_NON_VOLATILE |
+				     EFI_VARIABLE_BOOTSERVICE_ACCESS |
+				     EFI_VARIABLE_RUNTIME_ACCESS, 0, NULL);
 }
 
 /*
@@ -249,7 +248,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 	int num_entries;
 	void *new;
 
-	if (efi_mem_desc_lookup(addr, &md)) {
+	if (efi_mem_desc_lookup(addr, &md) ||
+	    md.type != EFI_BOOT_SERVICES_DATA) {
 		pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr);
 		return;
 	}
diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile
index fa021dfab088..5cf886c867c2 100644
--- a/arch/x86/platform/intel-mid/Makefile
+++ b/arch/x86/platform/intel-mid/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o mfld.o mrfld.o pwr.o
+obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o pwr.o
 
 # SFI specific code
 ifdef CONFIG_X86_INTEL_MID
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index 4f5fa65a1011..2acd6be13375 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -18,6 +18,7 @@
 #include <asm/intel-mid.h>
 #include <asm/intel_scu_ipc.h>
 #include <asm/io_apic.h>
+#include <asm/hw_irq.h>
 
 #define TANGIER_EXT_TIMER0_MSI 12
 
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 2ebdf31d9996..56f66eafb94f 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -36,8 +36,6 @@
 #include <asm/apb_timer.h>
 #include <asm/reboot.h>
 
-#include "intel_mid_weak_decls.h"
-
 /*
  * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
  * cmdline option x86_intel_mid_timer can be used to override the configuration
@@ -61,10 +59,6 @@
 
 enum intel_mid_timer_options intel_mid_timer_options;
 
-/* intel_mid_ops to store sub arch ops */
-static struct intel_mid_ops *intel_mid_ops;
-/* getter function for sub arch ops*/
-static void *(*get_intel_mid_ops[])(void) = INTEL_MID_OPS_INIT;
 enum intel_mid_cpu_type __intel_mid_cpu_chip;
 EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip);
 
@@ -82,11 +76,6 @@ static void intel_mid_reboot(void)
 	intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
 }
 
-static unsigned long __init intel_mid_calibrate_tsc(void)
-{
-	return 0;
-}
-
 static void __init intel_mid_setup_bp_timer(void)
 {
 	apbt_time_init();
@@ -133,6 +122,7 @@ static void intel_mid_arch_setup(void)
 	case 0x3C:
 	case 0x4A:
 		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_TANGIER;
+		x86_platform.legacy.rtc = 1;
 		break;
 	case 0x27:
 	default:
@@ -140,17 +130,7 @@ static void intel_mid_arch_setup(void)
 		break;
 	}
 
-	if (__intel_mid_cpu_chip < MAX_CPU_OPS(get_intel_mid_ops))
-		intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
-	else {
-		intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
-		pr_info("ARCH: Unknown SoC, assuming Penwell!\n");
-	}
-
 out:
-	if (intel_mid_ops->arch_setup)
-		intel_mid_ops->arch_setup();
-
 	/*
 	 * Intel MID platforms are using explicitly defined regulators.
 	 *
@@ -191,7 +171,6 @@ void __init x86_intel_mid_early_setup(void)
 
 	x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock;
 
-	x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
 	x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
 
 	x86_init.pci.arch_init = intel_mid_pci_init;
diff --git a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
deleted file mode 100644
index 3c1c3866d82b..000000000000
--- a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * intel_mid_weak_decls.h: Weak declarations of intel-mid.c
- *
- * (C) Copyright 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-
-/* For every CPU addition a new get_<cpuname>_ops interface needs
- * to be added.
- */
-extern void *get_penwell_ops(void);
-extern void *get_cloverview_ops(void);
-extern void *get_tangier_ops(void);
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
deleted file mode 100644
index e42978d4deaf..000000000000
--- a/arch/x86/platform/intel-mid/mfld.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * mfld.c: Intel Medfield platform setup code
- *
- * (C) Copyright 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/init.h>
-
-#include <asm/apic.h>
-#include <asm/intel-mid.h>
-#include <asm/intel_mid_vrtc.h>
-
-#include "intel_mid_weak_decls.h"
-
-static unsigned long __init mfld_calibrate_tsc(void)
-{
-	unsigned long fast_calibrate;
-	u32 lo, hi, ratio, fsb;
-
-	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
-	pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
-	ratio = (hi >> 8) & 0x1f;
-	pr_debug("ratio is %d\n", ratio);
-	if (!ratio) {
-		pr_err("read a zero ratio, should be incorrect!\n");
-		pr_err("force tsc ratio to 16 ...\n");
-		ratio = 16;
-	}
-	rdmsr(MSR_FSB_FREQ, lo, hi);
-	if ((lo & 0x7) == 0x7)
-		fsb = FSB_FREQ_83SKU;
-	else
-		fsb = FSB_FREQ_100SKU;
-	fast_calibrate = ratio * fsb;
-	pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
-	lapic_timer_frequency = fsb * 1000 / HZ;
-
-	/*
-	 * TSC on Intel Atom SoCs is reliable and of known frequency.
-	 * See tsc_msr.c for details.
-	 */
-	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-
-	return fast_calibrate;
-}
-
-static void __init penwell_arch_setup(void)
-{
-	x86_platform.calibrate_tsc = mfld_calibrate_tsc;
-}
-
-static struct intel_mid_ops penwell_ops = {
-	.arch_setup = penwell_arch_setup,
-};
-
-void *get_penwell_ops(void)
-{
-	return &penwell_ops;
-}
-
-void *get_cloverview_ops(void)
-{
-	return &penwell_ops;
-}
diff --git a/arch/x86/platform/intel-mid/mrfld.c b/arch/x86/platform/intel-mid/mrfld.c
deleted file mode 100644
index ae7bdeb0e507..000000000000
--- a/arch/x86/platform/intel-mid/mrfld.c
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * Intel Merrifield platform specific setup code
- *
- * (C) Copyright 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/init.h>
-
-#include <asm/apic.h>
-#include <asm/intel-mid.h>
-
-#include "intel_mid_weak_decls.h"
-
-static unsigned long __init tangier_calibrate_tsc(void)
-{
-	unsigned long fast_calibrate;
-	u32 lo, hi, ratio, fsb, bus_freq;
-
-	/* *********************** */
-	/* Compute TSC:Ratio * FSB */
-	/* *********************** */
-
-	/* Compute Ratio */
-	rdmsr(MSR_PLATFORM_INFO, lo, hi);
-	pr_debug("IA32 PLATFORM_INFO is 0x%x : %x\n", hi, lo);
-
-	ratio = (lo >> 8) & 0xFF;
-	pr_debug("ratio is %d\n", ratio);
-	if (!ratio) {
-		pr_err("Read a zero ratio, force tsc ratio to 4 ...\n");
-		ratio = 4;
-	}
-
-	/* Compute FSB */
-	rdmsr(MSR_FSB_FREQ, lo, hi);
-	pr_debug("Actual FSB frequency detected by SOC 0x%x : %x\n",
-			hi, lo);
-
-	bus_freq = lo & 0x7;
-	pr_debug("bus_freq = 0x%x\n", bus_freq);
-
-	if (bus_freq == 0)
-		fsb = FSB_FREQ_100SKU;
-	else if (bus_freq == 1)
-		fsb = FSB_FREQ_100SKU;
-	else if (bus_freq == 2)
-		fsb = FSB_FREQ_133SKU;
-	else if (bus_freq == 3)
-		fsb = FSB_FREQ_167SKU;
-	else if (bus_freq == 4)
-		fsb = FSB_FREQ_83SKU;
-	else if (bus_freq == 5)
-		fsb = FSB_FREQ_400SKU;
-	else if (bus_freq == 6)
-		fsb = FSB_FREQ_267SKU;
-	else if (bus_freq == 7)
-		fsb = FSB_FREQ_333SKU;
-	else {
-		BUG();
-		pr_err("Invalid bus_freq! Setting to minimal value!\n");
-		fsb = FSB_FREQ_100SKU;
-	}
-
-	/* TSC = FSB Freq * Resolved HFM Ratio */
-	fast_calibrate = ratio * fsb;
-	pr_debug("calculate tangier tsc %lu KHz\n", fast_calibrate);
-
-	/* ************************************ */
-	/* Calculate Local APIC Timer Frequency */
-	/* ************************************ */
-	lapic_timer_frequency = (fsb * 1000) / HZ;
-
-	pr_debug("Setting lapic_timer_frequency = %d\n",
-			lapic_timer_frequency);
-
-	/*
-	 * TSC on Intel Atom SoCs is reliable and of known frequency.
-	 * See tsc_msr.c for details.
-	 */
-	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-
-	return fast_calibrate;
-}
-
-static void __init tangier_arch_setup(void)
-{
-	x86_platform.calibrate_tsc = tangier_calibrate_tsc;
-	x86_platform.legacy.rtc = 1;
-}
-
-/* tangier arch ops */
-static struct intel_mid_ops tangier_ops = {
-	.arch_setup = tangier_arch_setup,
-};
-
-void *get_tangier_ops(void)
-{
-	return &tangier_ops;
-}
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index 7c3077e58fa0..f0e920fb98ad 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -311,10 +311,8 @@ static int __init add_xo1_platform_devices(void)
 		return PTR_ERR(pdev);
 
 	pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 static int olpc_xo1_ec_probe(struct platform_device *pdev)
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index ca446da48fd2..a4130b84d1ff 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1285,6 +1285,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 	struct msg_desc msgdesc;
 
 	ack_APIC_irq();
+	kvm_set_cpu_l1tf_flush_l1d();
 	time_start = get_cycles();
 
 	bcp = &per_cpu(bau_control, smp_processor_id());
@@ -1607,8 +1608,6 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr,
 				*tunables[cnt].tunp = val;
 			continue;
 		}
-		if (q == p)
-			break;
 	}
 	return 0;
 }
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 67ccf64c8bd8..f8e3b668d20b 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -233,29 +233,35 @@ struct restore_data_record {
  */
 static int get_e820_md5(struct e820_table *table, void *buf)
 {
-	struct scatterlist sg;
-	struct crypto_ahash *tfm;
+	struct crypto_shash *tfm;
+	struct shash_desc *desc;
 	int size;
 	int ret = 0;
 
-	tfm = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_shash("md5", 0, 0);
 	if (IS_ERR(tfm))
 		return -ENOMEM;
 
-	{
-		AHASH_REQUEST_ON_STACK(req, tfm);
-		size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * table->nr_entries;
-		ahash_request_set_tfm(req, tfm);
-		sg_init_one(&sg, (u8 *)table, size);
-		ahash_request_set_callback(req, 0, NULL, NULL);
-		ahash_request_set_crypt(req, &sg, buf, size);
-
-		if (crypto_ahash_digest(req))
-			ret = -EINVAL;
-		ahash_request_zero(req);
+	desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
+		       GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto free_tfm;
 	}
-	crypto_free_ahash(tfm);
 
+	desc->tfm = tfm;
+	desc->flags = 0;
+
+	size = offsetof(struct e820_table, entries) +
+		sizeof(struct e820_entry) * table->nr_entries;
+
+	if (crypto_shash_digest(desc, (u8 *)table, size, buf))
+		ret = -EINVAL;
+
+	kzfree(desc);
+
+free_tfm:
+	crypto_free_shash(tfm);
 	return ret;
 }
 
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index ce8da3a0412c..fd369a6e9ff8 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -137,7 +137,7 @@ ENTRY(restore_registers)
 	/* Saved in save_processor_state. */
 	lgdt	saved_context_gdt_desc(%rax)
 
-	xorq	%rax, %rax
+	xorl	%eax, %eax
 
 	/* tell the hibernation core that we've just restored the memory */
 	movq	%rax, in_suspend(%rip)
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 2e9ee023e6bc..81a8e33115ad 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -6,7 +6,7 @@ purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string
 targets += $(purgatory-y)
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 
-$(obj)/sha256.o: $(srctree)/lib/sha256.c
+$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 220e97841e49..3a6c8ebc8032 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -67,6 +67,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 	"__tracedata_(start|end)|"
 	"__(start|stop)_notes|"
 	"__end_rodata|"
+	"__end_rodata_aligned|"
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c
index 744afdc18cf3..56c44d865f7b 100644
--- a/arch/x86/um/mem_32.c
+++ b/arch/x86/um/mem_32.c
@@ -16,7 +16,7 @@ static int __init gate_vma_init(void)
 	if (!FIXADDR_USER_START)
 		return 0;
 
-	gate_vma.vm_mm = NULL;
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
diff --git a/arch/x86/um/vdso/.gitignore b/arch/x86/um/vdso/.gitignore
index 9cac6d072199..f8b69d84238e 100644
--- a/arch/x86/um/vdso/.gitignore
+++ b/arch/x86/um/vdso/.gitignore
@@ -1,2 +1 @@
-vdso-syms.lds
 vdso.lds
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index b2d6967262b2..822ccdba93ad 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -53,22 +53,6 @@ $(vobjs): KBUILD_CFLAGS += $(CFL)
 CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage
 CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage
 
-targets += vdso-syms.lds
-extra-$(VDSO64-y)			+= vdso-syms.lds
-
-#
-# Match symbols in the DSO that look like VDSO*; produce a file of constants.
-#
-sed-vdsosym := -e 's/^00*/0/' \
-	-e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p'
-quiet_cmd_vdsosym = VDSOSYM $@
-define cmd_vdsosym
-	$(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@
-endef
-
-$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE
-	$(call if_changed,vdsosym)
-
 #
 # The DSO images are built using a special linker script.
 #
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 3b5318505c69..2eeddd814653 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -3,6 +3,7 @@
 #endif
 #include <linux/cpu.h>
 #include <linux/kexec.h>
+#include <linux/slab.h>
 
 #include <xen/features.h>
 #include <xen/page.h>
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 8d4e2e1ae60b..ee3b00c7acda 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -119,6 +119,27 @@ static void __init xen_banner(void)
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
+
+static void __init xen_pv_init_platform(void)
+{
+	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
+	HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
+
+	/* xen clock uses per-cpu vcpu_info, need to init it for boot cpu */
+	xen_vcpu_info_reset(0);
+
+	/* pvclock is in shared info area */
+	xen_init_time_ops();
+}
+
+static void __init xen_pv_guest_late_init(void)
+{
+#ifndef CONFIG_SMP
+	/* Setup shared vcpu info for non-smp configurations */
+	xen_setup_vcpu_info_placement();
+#endif
+}
+
 /* Check if running on Xen version (major, minor) or later */
 bool
 xen_running_on_version_or_later(unsigned int major, unsigned int minor)
@@ -947,34 +968,8 @@ static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
 	xen_write_msr_safe(msr, low, high);
 }
 
-void xen_setup_shared_info(void)
-{
-	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
-
-	HYPERVISOR_shared_info =
-		(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
-
-	xen_setup_mfn_list_list();
-
-	if (system_state == SYSTEM_BOOTING) {
-#ifndef CONFIG_SMP
-		/*
-		 * In UP this is as good a place as any to set up shared info.
-		 * Limit this to boot only, at restore vcpu setup is done via
-		 * xen_vcpu_restore().
-		 */
-		xen_setup_vcpu_info_placement();
-#endif
-		/*
-		 * Now that shared info is set up we can start using routines
-		 * that point to pvclock area.
-		 */
-		xen_init_time_ops();
-	}
-}
-
 /* This is called once we have the cpu_possible_mask */
-void __ref xen_setup_vcpu_info_placement(void)
+void __init xen_setup_vcpu_info_placement(void)
 {
 	int cpu;
 
@@ -1207,12 +1202,20 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	xen_setup_features();
 
-	xen_setup_machphys_mapping();
-
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops.patch = paravirt_patch_default;
 	pv_cpu_ops = xen_cpu_ops;
+	xen_init_irq_ops();
+
+	/*
+	 * Setup xen_vcpu early because it is needed for
+	 * local_irq_disable(), irqs_disabled(), e.g. in printk().
+	 *
+	 * Don't do the full vcpu_info placement stuff until we have
+	 * the cpu_possible_mask and a non-dummy shared_info.
+	 */
+	xen_vcpu_info_reset(0);
 
 	x86_platform.get_nmi_reason = xen_get_nmi_reason;
 
@@ -1220,15 +1223,19 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	x86_init.irqs.intr_mode_init	= x86_init_noop;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
+	x86_init.hyper.init_platform = xen_pv_init_platform;
+	x86_init.hyper.guest_late_init = xen_pv_guest_late_init;
 
 	/*
 	 * Set up some pagetable state before starting to set any ptes.
 	 */
 
+	xen_setup_machphys_mapping();
 	xen_init_mmu_ops();
 
 	/* Prevent unwanted bits from being set in PTEs. */
 	__supported_pte_mask &= ~_PAGE_GLOBAL;
+	__default_kernel_pte_mask &= ~_PAGE_GLOBAL;
 
 	/*
 	 * Prevent page tables from being allocated in highmem, even
@@ -1249,20 +1256,12 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	get_cpu_cap(&boot_cpu_data);
 	x86_configure_nx();
 
-	xen_init_irq_ops();
+	/* Determine virtual and physical address sizes */
+	get_cpu_address_sizes(&boot_cpu_data);
 
 	/* Let's presume PV guests always boot on vCPU with id 0. */
 	per_cpu(xen_vcpu_id, 0) = 0;
 
-	/*
-	 * Setup xen_vcpu early because idt_setup_early_handler needs it for
-	 * local_irq_disable(), irqs_disabled().
-	 *
-	 * Don't do the full vcpu_info placement stuff until we have
-	 * the cpu_possible_mask and a non-dummy shared_info.
-	 */
-	xen_vcpu_info_reset(0);
-
 	idt_setup_early_handler();
 
 	xen_init_capabilities();
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 74179852e46c..7515a19fd324 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -128,8 +128,6 @@ static const struct pv_irq_ops xen_irq_ops __initconst = {
 
 void __init xen_init_irq_ops(void)
 {
-	/* For PVH we use default pv_irq_ops settings. */
-	if (!xen_feature(XENFEAT_hvm_callback_vector))
-		pv_irq_ops = xen_irq_ops;
+	pv_irq_ops = xen_irq_ops;
 	x86_init.irqs.intr_init = xen_init_IRQ;
 }
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2c30cabfda90..52206ad81e4b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1230,8 +1230,7 @@ static void __init xen_pagetable_p2m_free(void)
 	 * We roundup to the PMD, which means that if anybody at this stage is
 	 * using the __ka address of xen_start_info or
 	 * xen_start_info->shared_info they are in going to crash. Fortunatly
-	 * we have already revectored in xen_setup_kernel_pagetable and in
-	 * xen_setup_shared_info.
+	 * we have already revectored in xen_setup_kernel_pagetable.
 	 */
 	size = roundup(size, PMD_SIZE);
 
@@ -1292,8 +1291,7 @@ static void __init xen_pagetable_init(void)
 
 	/* Remap memory freed due to conflicts with E820 map */
 	xen_remap_memory();
-
-	xen_setup_shared_info();
+	xen_setup_mfn_list_list();
 }
 static void xen_write_cr2(unsigned long cr2)
 {
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index dc502ca8263e..2bce7958ce8b 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -80,9 +80,9 @@ void xen_mc_flush(void)
 		   and just do the call directly. */
 		mc = &b->entries[0];
 
-		mc->result = privcmd_call(mc->op,
-					  mc->args[0], mc->args[1], mc->args[2], 
-					  mc->args[3], mc->args[4]);
+		mc->result = xen_single_call(mc->op, mc->args[0], mc->args[1],
+					     mc->args[2], mc->args[3],
+					     mc->args[4]);
 		ret = mc->result < 0;
 		break;
 
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cd97a62394e7..973f10e05211 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -130,6 +130,10 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen);
 void __init xen_init_spinlocks(void)
 {
 
+	/*  Don't need to use pvqspinlock code if there is only 1 vCPU. */
+	if (num_possible_cpus() == 1)
+		xen_pvspin = false;
+
 	if (!xen_pvspin) {
 		printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
 		return;
diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c
index a2e0f110af56..8303b58c79a9 100644
--- a/arch/x86/xen/suspend_pv.c
+++ b/arch/x86/xen/suspend_pv.c
@@ -27,8 +27,9 @@ void xen_pv_pre_suspend(void)
 void xen_pv_post_suspend(int suspend_cancelled)
 {
 	xen_build_mfn_list_list();
-
-	xen_setup_shared_info();
+	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
+	HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
+	xen_setup_mfn_list_list();
 
 	if (suspend_cancelled) {
 		xen_start_info->store_mfn =
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index e0f1bcf01d63..c84f1e039d84 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -31,6 +31,8 @@
 /* Xen may fire a timer up to this many ns early */
 #define TIMER_SLOP	100000
 
+static u64 xen_sched_clock_offset __read_mostly;
+
 /* Get the TSC speed from Xen */
 static unsigned long xen_tsc_khz(void)
 {
@@ -40,7 +42,7 @@ static unsigned long xen_tsc_khz(void)
 	return pvclock_tsc_khz(info);
 }
 
-u64 xen_clocksource_read(void)
+static u64 xen_clocksource_read(void)
 {
         struct pvclock_vcpu_time_info *src;
 	u64 ret;
@@ -57,6 +59,11 @@ static u64 xen_clocksource_get_cycles(struct clocksource *cs)
 	return xen_clocksource_read();
 }
 
+static u64 xen_sched_clock(void)
+{
+	return xen_clocksource_read() - xen_sched_clock_offset;
+}
+
 static void xen_read_wallclock(struct timespec64 *ts)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
@@ -367,7 +374,7 @@ void xen_timer_resume(void)
 }
 
 static const struct pv_time_ops xen_time_ops __initconst = {
-	.sched_clock = xen_clocksource_read,
+	.sched_clock = xen_sched_clock,
 	.steal_clock = xen_steal_clock,
 };
 
@@ -503,8 +510,9 @@ static void __init xen_time_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 }
 
-void __ref xen_init_time_ops(void)
+void __init xen_init_time_ops(void)
 {
+	xen_sched_clock_offset = xen_clocksource_read();
 	pv_time_ops = xen_time_ops;
 
 	x86_init.timers.timer_init = xen_time_init;
@@ -542,11 +550,11 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
-		printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
-				"disable pv timer\n");
+		pr_info("Xen doesn't support pvclock on HVM, disable pv timer");
 		return;
 	}
 
+	xen_sched_clock_offset = xen_clocksource_read();
 	pv_time_ops = xen_time_ops;
 	x86_init.timers.setup_percpu_clockev = xen_time_init;
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 3b34745d0a52..e78684597f57 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -31,7 +31,6 @@ extern struct shared_info xen_dummy_shared_info;
 extern struct shared_info *HYPERVISOR_shared_info;
 
 void xen_setup_mfn_list_list(void);
-void xen_setup_shared_info(void);
 void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
@@ -68,12 +67,11 @@ void xen_init_irq_ops(void);
 void xen_setup_timer(int cpu);
 void xen_setup_runstate_info(int cpu);
 void xen_teardown_timer(int cpu);
-u64 xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);
 void xen_save_time_memory_area(void);
 void xen_restore_time_memory_area(void);
-void __ref xen_init_time_ops(void);
-void __init xen_hvm_init_time_ops(void);
+void xen_init_time_ops(void);
+void xen_hvm_init_time_ops(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index e7a23f2a519a..7de0149e1cf7 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -197,107 +197,9 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0)
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1,(v))
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1,(v))
-
-/**
- * atomic_dec_return - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1,(v)) == 0)
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_add_return(1,(v)) == 0)
-
-/**
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i,v) (atomic_add_return((i),(v)) < 0)
-
 #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #endif /* __KERNEL__ */
 
 #endif /* _XTENSA_ATOMIC_H */
diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index dbe3053b284a..9f119c1ca0b5 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -30,13 +30,16 @@ struct arch_hw_breakpoint {
 	u16 type;
 };
 
+struct perf_event_attr;
 struct perf_event;
 struct pt_regs;
 struct task_struct;
 
 int hw_breakpoint_slots(int type);
-int arch_check_bp_in_kernelspace(struct perf_event *bp);
-int arch_validate_hwbkpt_settings(struct perf_event *bp);
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw);
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data);
 
diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c
index b35656ab7dbd..c2e387c19cda 100644
--- a/arch/xtensa/kernel/hw_breakpoint.c
+++ b/arch/xtensa/kernel/hw_breakpoint.c
@@ -33,14 +33,13 @@ int hw_breakpoint_slots(int type)
 	}
 }
 
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = bp->attr.bp_len;
+	va = hw->address;
+	len = hw->len;
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -48,50 +47,41 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->type = XTENSA_BREAKPOINT_EXECUTE;
+		hw->type = XTENSA_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->type = XTENSA_BREAKPOINT_LOAD;
+		hw->type = XTENSA_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->type = XTENSA_BREAKPOINT_STORE;
+		hw->type = XTENSA_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
+		hw->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	info->len = bp->attr.bp_len;
-	if (info->len < 1 || info->len > 64 || !is_power_of_2(info->len))
+	hw->len = attr->bp_len;
+	if (hw->len < 1 || hw->len > 64 || !is_power_of_2(hw->len))
 		return -EINVAL;
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
-	if (info->address & (info->len - 1))
+	hw->address = attr->bp_addr;
+	if (hw->address & (hw->len - 1))
 		return -EINVAL;
 
 	return 0;
 }
 
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
-{
-	int ret;
-
-	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
-	return ret;
-}
-
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data)
 {
diff --git a/block/Kconfig b/block/Kconfig
index eb50fd4977c2..1f2469a0123c 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -149,6 +149,18 @@ config BLK_WBT
 	dynamically on an algorithm loosely based on CoDel, factoring in
 	the realtime performance of the disk.
 
+config BLK_CGROUP_IOLATENCY
+	bool "Enable support for latency based cgroup IO protection"
+	depends on BLK_CGROUP=y
+	default n
+	---help---
+	Enabling this option enables the .latency interface for IO throttling.
+	The IO controller will attempt to maintain average IO latencies below
+	the configured latency target, throttling anybody with a higher latency
+	target than the victimized group.
+
+	Note, this is an experimental interface and could be changed someday.
+
 config BLK_WBT_SQ
 	bool "Single queue writeback throttling"
 	default n
@@ -177,6 +189,10 @@ config BLK_DEBUG_FS
 	Unless you are building a kernel for a tiny system, you should
 	say Y here.
 
+config BLK_DEBUG_FS_ZONED
+       bool
+       default BLK_DEBUG_FS && BLK_DEV_ZONED
+
 config BLK_SED_OPAL
 	bool "Logic for interfacing with Opal enabled SEDs"
 	---help---
diff --git a/block/Makefile b/block/Makefile
index 6a56303b9925..572b33f32c07 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o partition-generic.o ioprio.o \
-			badblocks.o partitions/
+			badblocks.o partitions/ blk-rq-qos.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
@@ -17,6 +17,7 @@ obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
+obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
@@ -34,4 +35,5 @@ obj-$(CONFIG_BLK_MQ_RDMA)	+= blk-mq-rdma.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
+obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 495b9ddb3355..41d9036b1822 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -634,7 +634,7 @@ static bool bfq_differentiated_weights(struct bfq_data *bfqd)
  * The following function returns true if every queue must receive the
  * same share of the throughput (this condition is used when deciding
  * whether idling may be disabled, see the comments in the function
- * bfq_bfqq_may_idle()).
+ * bfq_better_to_idle()).
  *
  * Such a scenario occurs when:
  * 1) all active queues have the same weight,
@@ -742,8 +742,9 @@ inc_counter:
  * See the comments to the function bfq_weights_tree_add() for considerations
  * about overhead.
  */
-void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
-			     struct rb_root *root)
+void __bfq_weights_tree_remove(struct bfq_data *bfqd,
+			       struct bfq_entity *entity,
+			       struct rb_root *root)
 {
 	if (!entity->weight_counter)
 		return;
@@ -760,6 +761,43 @@ reset_entity_pointer:
 }
 
 /*
+ * Invoke __bfq_weights_tree_remove on bfqq and all its inactive
+ * parent entities.
+ */
+void bfq_weights_tree_remove(struct bfq_data *bfqd,
+			     struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = bfqq->entity.parent;
+
+	__bfq_weights_tree_remove(bfqd, &bfqq->entity,
+				  &bfqd->queue_weights_tree);
+
+	for_each_entity(entity) {
+		struct bfq_sched_data *sd = entity->my_sched_data;
+
+		if (sd->next_in_service || sd->in_service_entity) {
+			/*
+			 * entity is still active, because either
+			 * next_in_service or in_service_entity is not
+			 * NULL (see the comments on the definition of
+			 * next_in_service for details on why
+			 * in_service_entity must be checked too).
+			 *
+			 * As a consequence, the weight of entity is
+			 * not to be removed. In addition, if entity
+			 * is active, then its parent entities are
+			 * active as well, and thus their weights are
+			 * not to be removed either. In the end, this
+			 * loop must stop here.
+			 */
+			break;
+		}
+		__bfq_weights_tree_remove(bfqd, entity,
+					  &bfqd->group_weights_tree);
+	}
+}
+
+/*
  * Return expired entry, or NULL to just start from scratch in rbtree.
  */
 static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
@@ -1344,18 +1382,30 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
 		 * remain unchanged after such an expiration, and the
 		 * following statement therefore assigns to
 		 * entity->budget the remaining budget on such an
-		 * expiration. For clarity, entity->service is not
-		 * updated on expiration in any case, and, in normal
-		 * operation, is reset only when bfqq is selected for
-		 * service (see bfq_get_next_queue).
+		 * expiration.
 		 */
 		entity->budget = min_t(unsigned long,
 				       bfq_bfqq_budget_left(bfqq),
 				       bfqq->max_budget);
 
+		/*
+		 * At this point, we have used entity->service to get
+		 * the budget left (needed for updating
+		 * entity->budget). Thus we finally can, and have to,
+		 * reset entity->service. The latter must be reset
+		 * because bfqq would otherwise be charged again for
+		 * the service it has received during its previous
+		 * service slot(s).
+		 */
+		entity->service = 0;
+
 		return true;
 	}
 
+	/*
+	 * We can finally complete expiration, by setting service to 0.
+	 */
+	entity->service = 0;
 	entity->budget = max_t(unsigned long, bfqq->max_budget,
 			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
 	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
@@ -3233,11 +3283,21 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	ref = bfqq->ref;
 	__bfq_bfqq_expire(bfqd, bfqq);
 
+	if (ref == 1) /* bfqq is gone, no more actions on it */
+		return;
+
 	/* mark bfqq as waiting a request only if a bic still points to it */
-	if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
+	if (!bfq_bfqq_busy(bfqq) &&
 	    reason != BFQQE_BUDGET_TIMEOUT &&
-	    reason != BFQQE_BUDGET_EXHAUSTED)
+	    reason != BFQQE_BUDGET_EXHAUSTED) {
 		bfq_mark_bfqq_non_blocking_wait_rq(bfqq);
+		/*
+		 * Not setting service to 0, because, if the next rq
+		 * arrives in time, the queue will go on receiving
+		 * service with this same budget (as if it never expired)
+		 */
+	} else
+		entity->service = 0;
 }
 
 /*
@@ -3295,7 +3355,7 @@ static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
  * issues taken into account are not trivial. We discuss these issues
  * individually while introducing the variables.
  */
-static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
+static bool bfq_better_to_idle(struct bfq_queue *bfqq)
 {
 	struct bfq_data *bfqd = bfqq->bfqd;
 	bool rot_without_queueing =
@@ -3528,19 +3588,19 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 }
 
 /*
- * If the in-service queue is empty but the function bfq_bfqq_may_idle
+ * If the in-service queue is empty but the function bfq_better_to_idle
  * returns true, then:
  * 1) the queue must remain in service and cannot be expired, and
  * 2) the device must be idled to wait for the possible arrival of a new
  *    request for the queue.
- * See the comments on the function bfq_bfqq_may_idle for the reasons
+ * See the comments on the function bfq_better_to_idle for the reasons
  * why performing device idling is the best choice to boost the throughput
- * and preserve service guarantees when bfq_bfqq_may_idle itself
+ * and preserve service guarantees when bfq_better_to_idle itself
  * returns true.
  */
 static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
 {
-	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_may_idle(bfqq);
+	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq);
 }
 
 /*
@@ -3559,8 +3619,14 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 
 	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
 
+	/*
+	 * Do not expire bfqq for budget timeout if bfqq may be about
+	 * to enjoy device idling. The reason why, in this case, we
+	 * prevent bfqq from expiring is the same as in the comments
+	 * on the case where bfq_bfqq_must_idle() returns true, in
+	 * bfq_completed_request().
+	 */
 	if (bfq_may_expire_for_budg_timeout(bfqq) &&
-	    !bfq_bfqq_wait_request(bfqq) &&
 	    !bfq_bfqq_must_idle(bfqq))
 		goto expire;
 
@@ -3620,7 +3686,7 @@ check_queue:
 	 * may idle after their completion, then keep it anyway.
 	 */
 	if (bfq_bfqq_wait_request(bfqq) ||
-	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
+	    (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) {
 		bfqq = NULL;
 		goto keep_queue;
 	}
@@ -4582,8 +4648,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 		 */
 		bfqq->budget_timeout = jiffies;
 
-		bfq_weights_tree_remove(bfqd, &bfqq->entity,
-					&bfqd->queue_weights_tree);
+		bfq_weights_tree_remove(bfqd, bfqq);
 	}
 
 	now_ns = ktime_get_ns();
@@ -4637,15 +4702,39 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 	 * or if we want to idle in case it has no pending requests.
 	 */
 	if (bfqd->in_service_queue == bfqq) {
-		if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
-			bfq_arm_slice_timer(bfqd);
+		if (bfq_bfqq_must_idle(bfqq)) {
+			if (bfqq->dispatched == 0)
+				bfq_arm_slice_timer(bfqd);
+			/*
+			 * If we get here, we do not expire bfqq, even
+			 * if bfqq was in budget timeout or had no
+			 * more requests (as controlled in the next
+			 * conditional instructions). The reason for
+			 * not expiring bfqq is as follows.
+			 *
+			 * Here bfqq->dispatched > 0 holds, but
+			 * bfq_bfqq_must_idle() returned true. This
+			 * implies that, even if no request arrives
+			 * for bfqq before bfqq->dispatched reaches 0,
+			 * bfqq will, however, not be expired on the
+			 * completion event that causes bfqq->dispatch
+			 * to reach zero. In contrast, on this event,
+			 * bfqq will start enjoying device idling
+			 * (I/O-dispatch plugging).
+			 *
+			 * But, if we expired bfqq here, bfqq would
+			 * not have the chance to enjoy device idling
+			 * when bfqq->dispatched finally reaches
+			 * zero. This would expose bfqq to violation
+			 * of its reserved service guarantees.
+			 */
 			return;
 		} else if (bfq_may_expire_for_budg_timeout(bfqq))
 			bfq_bfqq_expire(bfqd, bfqq, false,
 					BFQQE_BUDGET_TIMEOUT);
 		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
 			 (bfqq->dispatched == 0 ||
-			  !bfq_bfqq_may_idle(bfqq)))
+			  !bfq_better_to_idle(bfqq)))
 			bfq_bfqq_expire(bfqd, bfqq, false,
 					BFQQE_NO_MORE_REQUESTS);
 	}
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 0f712e03b035..a8a2e5aca4d4 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -827,8 +827,11 @@ struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
 void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
 			  struct rb_root *root);
-void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
-			     struct rb_root *root);
+void __bfq_weights_tree_remove(struct bfq_data *bfqd,
+			       struct bfq_entity *entity,
+			       struct rb_root *root);
+void bfq_weights_tree_remove(struct bfq_data *bfqd,
+			     struct bfq_queue *bfqq);
 void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		     bool compensate, enum bfqq_expiration reason);
 void bfq_put_queue(struct bfq_queue *bfqq);
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 4498c43245e2..dbc07b456059 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -499,9 +499,6 @@ static void bfq_active_insert(struct bfq_service_tree *st,
 	if (bfqq)
 		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	else /* bfq_group */
-		bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
-
 	if (bfqg != bfqd->root_group)
 		bfqg->active_entities++;
 #endif
@@ -601,10 +598,6 @@ static void bfq_active_extract(struct bfq_service_tree *st,
 	if (bfqq)
 		list_del(&bfqq->bfqq_list);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	else /* bfq_group */
-		bfq_weights_tree_remove(bfqd, entity,
-					&bfqd->group_weights_tree);
-
 	if (bfqg != bfqd->root_group)
 		bfqg->active_entities--;
 #endif
@@ -799,7 +792,7 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		if (prev_weight != new_weight) {
 			root = bfqq ? &bfqd->queue_weights_tree :
 				      &bfqd->group_weights_tree;
-			bfq_weights_tree_remove(bfqd, entity, root);
+			__bfq_weights_tree_remove(bfqd, entity, root);
 		}
 		entity->weight = new_weight;
 		/*
@@ -971,7 +964,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
  * one of its children receives a new request.
  *
  * Basically, this function updates the timestamps of entity and
- * inserts entity into its active tree, ater possibly extracting it
+ * inserts entity into its active tree, after possibly extracting it
  * from its idle tree.
  */
 static void __bfq_activate_entity(struct bfq_entity *entity,
@@ -1015,6 +1008,16 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
 		entity->on_st = true;
 	}
 
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_weights_tree_add(bfqg->bfqd, entity,
+				     &bfqd->group_weights_tree);
+	}
+#endif
+
 	bfq_update_fin_time_enqueue(entity, st, backshifted);
 }
 
@@ -1542,12 +1545,6 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 		sd->in_service_entity = entity;
 
 		/*
-		 * Reset the accumulator of the amount of service that
-		 * the entity is about to receive.
-		 */
-		entity->service = 0;
-
-		/*
 		 * If entity is no longer a candidate for next
 		 * service, then it must be extracted from its active
 		 * tree, so as to make sure that it won't be
@@ -1664,8 +1661,7 @@ void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	bfqd->busy_queues--;
 
 	if (!bfqq->dispatched)
-		bfq_weights_tree_remove(bfqd, &bfqq->entity,
-					&bfqd->queue_weights_tree);
+		bfq_weights_tree_remove(bfqd, bfqq);
 
 	if (bfqq->wr_coeff > 1)
 		bfqd->wr_busy_queues--;
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index add7c7c85335..67b5fb861a51 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -160,28 +160,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL(bio_integrity_add_page);
 
 /**
- * bio_integrity_intervals - Return number of integrity intervals for a bio
- * @bi:		blk_integrity profile for device
- * @sectors:	Size of the bio in 512-byte sectors
- *
- * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the data integrity
- * interval size of the storage device.  Convert the block layer sectors
- * to the appropriate number of integrity intervals.
- */
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
-						   unsigned int sectors)
-{
-	return sectors >> (bi->interval_exp - 9);
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
-					       unsigned int sectors)
-{
-	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
-}
-
-/**
  * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
  * @proc_iter:  iterator to process
diff --git a/block/bio.c b/block/bio.c
index 67eff5eddc49..b12966e415d3 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -28,9 +28,11 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
+#include <linux/blk-cgroup.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
+#include "blk-rq-qos.h"
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
@@ -156,7 +158,7 @@ out:
 
 unsigned int bvec_nr_vecs(unsigned short idx)
 {
-	return bvec_slabs[idx].nr_vecs;
+	return bvec_slabs[--idx].nr_vecs;
 }
 
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
@@ -645,83 +647,6 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 EXPORT_SYMBOL(bio_clone_fast);
 
 /**
- * 	bio_clone_bioset - clone a bio
- * 	@bio_src: bio to clone
- *	@gfp_mask: allocation priority
- *	@bs: bio_set to allocate from
- *
- *	Clone bio. Caller will own the returned bio, but not the actual data it
- *	points to. Reference count of returned bio will be one.
- */
-struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
-			     struct bio_set *bs)
-{
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	struct bio *bio;
-
-	/*
-	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
-	 * bio_src->bi_io_vec to bio->bi_io_vec.
-	 *
-	 * We can't do that anymore, because:
-	 *
-	 *  - The point of cloning the biovec is to produce a bio with a biovec
-	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
-	 *
-	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
-	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
-	 *    But the clone should succeed as long as the number of biovecs we
-	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
-	 *
-	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
-	 *    that does not own the bio - reason being drivers don't use it for
-	 *    iterating over the biovec anymore, so expecting it to be kept up
-	 *    to date (i.e. for clones that share the parent biovec) is just
-	 *    asking for trouble and would force extra work on
-	 *    __bio_clone_fast() anyways.
-	 */
-
-	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
-	if (!bio)
-		return NULL;
-	bio->bi_disk		= bio_src->bi_disk;
-	bio->bi_opf		= bio_src->bi_opf;
-	bio->bi_write_hint	= bio_src->bi_write_hint;
-	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
-	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
-
-	switch (bio_op(bio)) {
-	case REQ_OP_DISCARD:
-	case REQ_OP_SECURE_ERASE:
-	case REQ_OP_WRITE_ZEROES:
-		break;
-	case REQ_OP_WRITE_SAME:
-		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
-		break;
-	default:
-		bio_for_each_segment(bv, bio_src, iter)
-			bio->bi_io_vec[bio->bi_vcnt++] = bv;
-		break;
-	}
-
-	if (bio_integrity(bio_src)) {
-		int ret;
-
-		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
-		if (ret < 0) {
-			bio_put(bio);
-			return NULL;
-		}
-	}
-
-	bio_clone_blkcg_association(bio, bio_src);
-
-	return bio;
-}
-EXPORT_SYMBOL(bio_clone_bioset);
-
-/**
  *	bio_add_pc_page	-	attempt to add page to bio
  *	@q: the target queue
  *	@bio: destination bio
@@ -903,25 +828,27 @@ int bio_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL(bio_add_page);
 
 /**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * Pins pages from *iter and appends them to @bio's bvec array. The
  * pages will have to be released using put_page() when done.
+ * For multi-segment *iter, this function only adds pages from the
+ * the next non-empty segment of the iov iterator.
  */
-int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
-	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
-	size_t offset, diff;
+	size_t offset;
 	ssize_t size;
 
 	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
-	nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+	idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
 
 	/*
 	 * Deep magic below:  We need to walk the pinned pages backwards
@@ -934,21 +861,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	bio->bi_iter.bi_size += size;
 	bio->bi_vcnt += nr_pages;
 
-	diff = (nr_pages * PAGE_SIZE - offset) - size;
-	while (nr_pages--) {
-		bv[nr_pages].bv_page = pages[nr_pages];
-		bv[nr_pages].bv_len = PAGE_SIZE;
-		bv[nr_pages].bv_offset = 0;
+	while (idx--) {
+		bv[idx].bv_page = pages[idx];
+		bv[idx].bv_len = PAGE_SIZE;
+		bv[idx].bv_offset = 0;
 	}
 
 	bv[0].bv_offset += offset;
 	bv[0].bv_len -= offset;
-	if (diff)
-		bv[bio->bi_vcnt - 1].bv_len -= diff;
+	bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size;
 
 	iov_iter_advance(iter, size);
 	return 0;
 }
+
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ * The function tries, but does not guarantee, to pin as many pages as
+ * fit into the bio, or are requested in *iter, whatever is smaller.
+ * If MM encounters an error pinning the requested pages, it stops.
+ * Error is returned only if 0 pages could be pinned.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short orig_vcnt = bio->bi_vcnt;
+
+	do {
+		int ret = __bio_iov_iter_get_pages(bio, iter);
+
+		if (unlikely(ret))
+			return bio->bi_vcnt > orig_vcnt ? 0 : ret;
+
+	} while (iov_iter_count(iter) && !bio_full(bio));
+
+	return 0;
+}
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
 static void submit_bio_wait_endio(struct bio *bio)
@@ -1634,10 +1586,8 @@ void bio_set_pages_dirty(struct bio *bio)
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page && !PageCompound(page))
-			set_page_dirty_lock(page);
+		if (!PageCompound(bvec->bv_page))
+			set_page_dirty_lock(bvec->bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
@@ -1647,19 +1597,15 @@ static void bio_release_pages(struct bio *bio)
 	struct bio_vec *bvec;
 	int i;
 
-	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page)
-			put_page(page);
-	}
+	bio_for_each_segment_all(bvec, bio, i)
+		put_page(bvec->bv_page);
 }
 
 /*
  * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
  * If they are, then fine.  If, however, some pages are clean then they must
  * have been written out during the direct-IO read.  So we take another ref on
- * the BIO and the offending pages and re-dirty the pages in process context.
+ * the BIO and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
  * here on.  It will run one put_page() against each page and will run one
@@ -1677,78 +1623,70 @@ static struct bio *bio_dirty_list;
  */
 static void bio_dirty_fn(struct work_struct *work)
 {
-	unsigned long flags;
-	struct bio *bio;
+	struct bio *bio, *next;
 
-	spin_lock_irqsave(&bio_dirty_lock, flags);
-	bio = bio_dirty_list;
+	spin_lock_irq(&bio_dirty_lock);
+	next = bio_dirty_list;
 	bio_dirty_list = NULL;
-	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	spin_unlock_irq(&bio_dirty_lock);
 
-	while (bio) {
-		struct bio *next = bio->bi_private;
+	while ((bio = next) != NULL) {
+		next = bio->bi_private;
 
 		bio_set_pages_dirty(bio);
 		bio_release_pages(bio);
 		bio_put(bio);
-		bio = next;
 	}
 }
 
 void bio_check_pages_dirty(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int nr_clean_pages = 0;
+	unsigned long flags;
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (PageDirty(page) || PageCompound(page)) {
-			put_page(page);
-			bvec->bv_page = NULL;
-		} else {
-			nr_clean_pages++;
-		}
+		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
+			goto defer;
 	}
 
-	if (nr_clean_pages) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&bio_dirty_lock, flags);
-		bio->bi_private = bio_dirty_list;
-		bio_dirty_list = bio;
-		spin_unlock_irqrestore(&bio_dirty_lock, flags);
-		schedule_work(&bio_dirty_work);
-	} else {
-		bio_put(bio);
-	}
+	bio_release_pages(bio);
+	bio_put(bio);
+	return;
+defer:
+	spin_lock_irqsave(&bio_dirty_lock, flags);
+	bio->bi_private = bio_dirty_list;
+	bio_dirty_list = bio;
+	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	schedule_work(&bio_dirty_work);
 }
 EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
 
-void generic_start_io_acct(struct request_queue *q, int rw,
+void generic_start_io_acct(struct request_queue *q, int op,
 			   unsigned long sectors, struct hd_struct *part)
 {
+	const int sgrp = op_stat_group(op);
 	int cpu = part_stat_lock();
 
 	part_round_stats(q, cpu, part);
-	part_stat_inc(cpu, part, ios[rw]);
-	part_stat_add(cpu, part, sectors[rw], sectors);
-	part_inc_in_flight(q, part, rw);
+	part_stat_inc(cpu, part, ios[sgrp]);
+	part_stat_add(cpu, part, sectors[sgrp], sectors);
+	part_inc_in_flight(q, part, op_is_write(op));
 
 	part_stat_unlock();
 }
 EXPORT_SYMBOL(generic_start_io_acct);
 
-void generic_end_io_acct(struct request_queue *q, int rw,
+void generic_end_io_acct(struct request_queue *q, int req_op,
 			 struct hd_struct *part, unsigned long start_time)
 {
 	unsigned long duration = jiffies - start_time;
+	const int sgrp = op_stat_group(req_op);
 	int cpu = part_stat_lock();
 
-	part_stat_add(cpu, part, ticks[rw], duration);
+	part_stat_add(cpu, part, ticks[sgrp], duration);
 	part_round_stats(q, cpu, part);
-	part_dec_in_flight(q, part, rw);
+	part_dec_in_flight(q, part, op_is_write(req_op));
 
 	part_stat_unlock();
 }
@@ -1807,6 +1745,9 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
+	if (bio->bi_disk)
+		rq_qos_done_bio(bio->bi_disk->queue, bio);
+
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that
@@ -1866,6 +1807,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 		bio_integrity_trim(split);
 
 	bio_advance(bio, split->bi_iter.bi_size);
+	bio->bi_iter.bi_done = 0;
 
 	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
 		bio_set_flag(split, BIO_TRACE_COMPLETION);
@@ -2014,6 +1956,30 @@ EXPORT_SYMBOL(bioset_init_from_src);
 
 #ifdef CONFIG_BLK_CGROUP
 
+#ifdef CONFIG_MEMCG
+/**
+ * bio_associate_blkcg_from_page - associate a bio with the page's blkcg
+ * @bio: target bio
+ * @page: the page to lookup the blkcg from
+ *
+ * Associate @bio with the blkcg from @page's owning memcg.  This works like
+ * every other associate function wrt references.
+ */
+int bio_associate_blkcg_from_page(struct bio *bio, struct page *page)
+{
+	struct cgroup_subsys_state *blkcg_css;
+
+	if (unlikely(bio->bi_css))
+		return -EBUSY;
+	if (!page->mem_cgroup)
+		return 0;
+	blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup,
+				     &io_cgrp_subsys);
+	bio->bi_css = blkcg_css;
+	return 0;
+}
+#endif /* CONFIG_MEMCG */
+
 /**
  * bio_associate_blkcg - associate a bio with the specified blkcg
  * @bio: target bio
@@ -2037,6 +2003,24 @@ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
 EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
 /**
+ * bio_associate_blkg - associate a bio with the specified blkg
+ * @bio: target bio
+ * @blkg: the blkg to associate
+ *
+ * Associate @bio with the blkg specified by @blkg.  This is the queue specific
+ * blkcg information associated with the @bio, a reference will be taken on the
+ * @blkg and will be freed when the bio is freed.
+ */
+int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
+{
+	if (unlikely(bio->bi_blkg))
+		return -EBUSY;
+	blkg_get(blkg);
+	bio->bi_blkg = blkg;
+	return 0;
+}
+
+/**
  * bio_disassociate_task - undo bio_associate_current()
  * @bio: target bio
  */
@@ -2050,6 +2034,10 @@ void bio_disassociate_task(struct bio *bio)
 		css_put(bio->bi_css);
 		bio->bi_css = NULL;
 	}
+	if (bio->bi_blkg) {
+		blkg_put(bio->bi_blkg);
+		bio->bi_blkg = NULL;
+	}
 }
 
 /**
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index eb85cb87c40f..694595b29b8f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -27,6 +27,7 @@
 #include <linux/atomic.h>
 #include <linux/ctype.h>
 #include <linux/blk-cgroup.h>
+#include <linux/tracehook.h>
 #include "blk.h"
 
 #define MAX_KEY_LEN 100
@@ -50,6 +51,8 @@ static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
 static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
 
+static bool blkcg_debug_stats = false;
+
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -564,6 +567,7 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
 		[BLKG_RWSTAT_WRITE]	= "Write",
 		[BLKG_RWSTAT_SYNC]	= "Sync",
 		[BLKG_RWSTAT_ASYNC]	= "Async",
+		[BLKG_RWSTAT_DISCARD]	= "Discard",
 	};
 	const char *dname = blkg_dev_name(pd->blkg);
 	u64 v;
@@ -577,7 +581,8 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
 			   (unsigned long long)atomic64_read(&rwstat->aux_cnt[i]));
 
 	v = atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_READ]) +
-		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]);
+		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]) +
+		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_DISCARD]);
 	seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v);
 	return v;
 }
@@ -954,30 +959,77 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
 		const char *dname;
+		char *buf;
 		struct blkg_rwstat rwstat;
-		u64 rbytes, wbytes, rios, wios;
+		u64 rbytes, wbytes, rios, wios, dbytes, dios;
+		size_t size = seq_get_buf(sf, &buf), off = 0;
+		int i;
+		bool has_stats = false;
 
 		dname = blkg_dev_name(blkg);
 		if (!dname)
 			continue;
 
+		/*
+		 * Hooray string manipulation, count is the size written NOT
+		 * INCLUDING THE \0, so size is now count+1 less than what we
+		 * had before, but we want to start writing the next bit from
+		 * the \0 so we only add count to buf.
+		 */
+		off += scnprintf(buf+off, size-off, "%s ", dname);
+
 		spin_lock_irq(blkg->q->queue_lock);
 
 		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
 					offsetof(struct blkcg_gq, stat_bytes));
 		rbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
 		wbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
+		dbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]);
 
 		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
 					offsetof(struct blkcg_gq, stat_ios));
 		rios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
 		wios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
+		dios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]);
 
 		spin_unlock_irq(blkg->q->queue_lock);
 
-		if (rbytes || wbytes || rios || wios)
-			seq_printf(sf, "%s rbytes=%llu wbytes=%llu rios=%llu wios=%llu\n",
-				   dname, rbytes, wbytes, rios, wios);
+		if (rbytes || wbytes || rios || wios) {
+			has_stats = true;
+			off += scnprintf(buf+off, size-off,
+					 "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu",
+					 rbytes, wbytes, rios, wios,
+					 dbytes, dios);
+		}
+
+		if (!blkcg_debug_stats)
+			goto next;
+
+		if (atomic_read(&blkg->use_delay)) {
+			has_stats = true;
+			off += scnprintf(buf+off, size-off,
+					 " use_delay=%d delay_nsec=%llu",
+					 atomic_read(&blkg->use_delay),
+					(unsigned long long)atomic64_read(&blkg->delay_nsec));
+		}
+
+		for (i = 0; i < BLKCG_MAX_POLS; i++) {
+			struct blkcg_policy *pol = blkcg_policy[i];
+			size_t written;
+
+			if (!blkg->pd[i] || !pol->pd_stat_fn)
+				continue;
+
+			written = pol->pd_stat_fn(blkg->pd[i], buf+off, size-off);
+			if (written)
+				has_stats = true;
+			off += written;
+		}
+next:
+		if (has_stats) {
+			off += scnprintf(buf+off, size-off, "\n");
+			seq_commit(sf, off);
+		}
 	}
 
 	rcu_read_unlock();
@@ -1191,6 +1243,14 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
+	ret = blk_iolatency_init(q);
+	if (ret) {
+		spin_lock_irq(q->queue_lock);
+		blkg_destroy_all(q);
+		spin_unlock_irq(q->queue_lock);
+		return ret;
+	}
+
 	ret = blk_throtl_init(q);
 	if (ret) {
 		spin_lock_irq(q->queue_lock);
@@ -1288,6 +1348,13 @@ static void blkcg_bind(struct cgroup_subsys_state *root_css)
 	mutex_unlock(&blkcg_pol_mutex);
 }
 
+static void blkcg_exit(struct task_struct *tsk)
+{
+	if (tsk->throttle_queue)
+		blk_put_queue(tsk->throttle_queue);
+	tsk->throttle_queue = NULL;
+}
+
 struct cgroup_subsys io_cgrp_subsys = {
 	.css_alloc = blkcg_css_alloc,
 	.css_offline = blkcg_css_offline,
@@ -1297,6 +1364,7 @@ struct cgroup_subsys io_cgrp_subsys = {
 	.dfl_cftypes = blkcg_files,
 	.legacy_cftypes = blkcg_legacy_files,
 	.legacy_name = "blkio",
+	.exit = blkcg_exit,
 #ifdef CONFIG_MEMCG
 	/*
 	 * This ensures that, if available, memcg is automatically enabled
@@ -1547,3 +1615,209 @@ out_unlock:
 	mutex_unlock(&blkcg_pol_register_mutex);
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
+
+/*
+ * Scale the accumulated delay based on how long it has been since we updated
+ * the delay.  We only call this when we are adding delay, in case it's been a
+ * while since we added delay, and when we are checking to see if we need to
+ * delay a task, to account for any delays that may have occurred.
+ */
+static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
+{
+	u64 old = atomic64_read(&blkg->delay_start);
+
+	/*
+	 * We only want to scale down every second.  The idea here is that we
+	 * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain
+	 * time window.  We only want to throttle tasks for recent delay that
+	 * has occurred, in 1 second time windows since that's the maximum
+	 * things can be throttled.  We save the current delay window in
+	 * blkg->last_delay so we know what amount is still left to be charged
+	 * to the blkg from this point onward.  blkg->last_use keeps track of
+	 * the use_delay counter.  The idea is if we're unthrottling the blkg we
+	 * are ok with whatever is happening now, and we can take away more of
+	 * the accumulated delay as we've already throttled enough that
+	 * everybody is happy with their IO latencies.
+	 */
+	if (time_before64(old + NSEC_PER_SEC, now) &&
+	    atomic64_cmpxchg(&blkg->delay_start, old, now) == old) {
+		u64 cur = atomic64_read(&blkg->delay_nsec);
+		u64 sub = min_t(u64, blkg->last_delay, now - old);
+		int cur_use = atomic_read(&blkg->use_delay);
+
+		/*
+		 * We've been unthrottled, subtract a larger chunk of our
+		 * accumulated delay.
+		 */
+		if (cur_use < blkg->last_use)
+			sub = max_t(u64, sub, blkg->last_delay >> 1);
+
+		/*
+		 * This shouldn't happen, but handle it anyway.  Our delay_nsec
+		 * should only ever be growing except here where we subtract out
+		 * min(last_delay, 1 second), but lord knows bugs happen and I'd
+		 * rather not end up with negative numbers.
+		 */
+		if (unlikely(cur < sub)) {
+			atomic64_set(&blkg->delay_nsec, 0);
+			blkg->last_delay = 0;
+		} else {
+			atomic64_sub(sub, &blkg->delay_nsec);
+			blkg->last_delay = cur - sub;
+		}
+		blkg->last_use = cur_use;
+	}
+}
+
+/*
+ * This is called when we want to actually walk up the hierarchy and check to
+ * see if we need to throttle, and then actually throttle if there is some
+ * accumulated delay.  This should only be called upon return to user space so
+ * we're not holding some lock that would induce a priority inversion.
+ */
+static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
+{
+	u64 now = ktime_to_ns(ktime_get());
+	u64 exp;
+	u64 delay_nsec = 0;
+	int tok;
+
+	while (blkg->parent) {
+		if (atomic_read(&blkg->use_delay)) {
+			blkcg_scale_delay(blkg, now);
+			delay_nsec = max_t(u64, delay_nsec,
+					   atomic64_read(&blkg->delay_nsec));
+		}
+		blkg = blkg->parent;
+	}
+
+	if (!delay_nsec)
+		return;
+
+	/*
+	 * Let's not sleep for all eternity if we've amassed a huge delay.
+	 * Swapping or metadata IO can accumulate 10's of seconds worth of
+	 * delay, and we want userspace to be able to do _something_ so cap the
+	 * delays at 1 second.  If there's 10's of seconds worth of delay then
+	 * the tasks will be delayed for 1 second for every syscall.
+	 */
+	delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
+
+	/*
+	 * TODO: the use_memdelay flag is going to be for the upcoming psi stuff
+	 * that hasn't landed upstream yet.  Once that stuff is in place we need
+	 * to do a psi_memstall_enter/leave if memdelay is set.
+	 */
+
+	exp = ktime_add_ns(now, delay_nsec);
+	tok = io_schedule_prepare();
+	do {
+		__set_current_state(TASK_KILLABLE);
+		if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS))
+			break;
+	} while (!fatal_signal_pending(current));
+	io_schedule_finish(tok);
+}
+
+/**
+ * blkcg_maybe_throttle_current - throttle the current task if it has been marked
+ *
+ * This is only called if we've been marked with set_notify_resume().  Obviously
+ * we can be set_notify_resume() for reasons other than blkcg throttling, so we
+ * check to see if current->throttle_queue is set and if not this doesn't do
+ * anything.  This should only ever be called by the resume code, it's not meant
+ * to be called by people willy-nilly as it will actually do the work to
+ * throttle the task if it is setup for throttling.
+ */
+void blkcg_maybe_throttle_current(void)
+{
+	struct request_queue *q = current->throttle_queue;
+	struct cgroup_subsys_state *css;
+	struct blkcg *blkcg;
+	struct blkcg_gq *blkg;
+	bool use_memdelay = current->use_memdelay;
+
+	if (!q)
+		return;
+
+	current->throttle_queue = NULL;
+	current->use_memdelay = false;
+
+	rcu_read_lock();
+	css = kthread_blkcg();
+	if (css)
+		blkcg = css_to_blkcg(css);
+	else
+		blkcg = css_to_blkcg(task_css(current, io_cgrp_id));
+
+	if (!blkcg)
+		goto out;
+	blkg = blkg_lookup(blkcg, q);
+	if (!blkg)
+		goto out;
+	blkg = blkg_try_get(blkg);
+	if (!blkg)
+		goto out;
+	rcu_read_unlock();
+
+	blkcg_maybe_throttle_blkg(blkg, use_memdelay);
+	blkg_put(blkg);
+	blk_put_queue(q);
+	return;
+out:
+	rcu_read_unlock();
+	blk_put_queue(q);
+}
+EXPORT_SYMBOL_GPL(blkcg_maybe_throttle_current);
+
+/**
+ * blkcg_schedule_throttle - this task needs to check for throttling
+ * @q - the request queue IO was submitted on
+ * @use_memdelay - do we charge this to memory delay for PSI
+ *
+ * This is called by the IO controller when we know there's delay accumulated
+ * for the blkg for this task.  We do not pass the blkg because there are places
+ * we call this that may not have that information, the swapping code for
+ * instance will only have a request_queue at that point.  This set's the
+ * notify_resume for the task to check and see if it requires throttling before
+ * returning to user space.
+ *
+ * We will only schedule once per syscall.  You can call this over and over
+ * again and it will only do the check once upon return to user space, and only
+ * throttle once.  If the task needs to be throttled again it'll need to be
+ * re-set at the next time we see the task.
+ */
+void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay)
+{
+	if (unlikely(current->flags & PF_KTHREAD))
+		return;
+
+	if (!blk_get_queue(q))
+		return;
+
+	if (current->throttle_queue)
+		blk_put_queue(current->throttle_queue);
+	current->throttle_queue = q;
+	if (use_memdelay)
+		current->use_memdelay = use_memdelay;
+	set_notify_resume(current);
+}
+EXPORT_SYMBOL_GPL(blkcg_schedule_throttle);
+
+/**
+ * blkcg_add_delay - add delay to this blkg
+ * @now - the current time in nanoseconds
+ * @delta - how many nanoseconds of delay to add
+ *
+ * Charge @delta to the blkg's current delay accumulation.  This is used to
+ * throttle tasks if an IO controller thinks we need more throttling.
+ */
+void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
+{
+	blkcg_scale_delay(blkg, now);
+	atomic64_add(delta, &blkg->delay_nsec);
+}
+EXPORT_SYMBOL_GPL(blkcg_add_delay);
+
+module_param(blkcg_debug_stats, bool, 0644);
+MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not");
diff --git a/block/blk-core.c b/block/blk-core.c
index afd2596ea3d3..12550340418d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -42,7 +42,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-sched.h"
-#include "blk-wbt.h"
+#include "blk-rq-qos.h"
 
 #ifdef CONFIG_DEBUG_FS
 struct dentry *blk_debugfs_root;
@@ -715,6 +715,35 @@ void blk_set_queue_dying(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
 
+/* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
+void blk_exit_queue(struct request_queue *q)
+{
+	/*
+	 * Since the I/O scheduler exit code may access cgroup information,
+	 * perform I/O scheduler exit before disassociating from the block
+	 * cgroup controller.
+	 */
+	if (q->elevator) {
+		ioc_clear_queue(q);
+		elevator_exit(q, q->elevator);
+		q->elevator = NULL;
+	}
+
+	/*
+	 * Remove all references to @q from the block cgroup controller before
+	 * restoring @q->queue_lock to avoid that restoring this pointer causes
+	 * e.g. blkcg_print_blkgs() to crash.
+	 */
+	blkcg_exit_queue(q);
+
+	/*
+	 * Since the cgroup code may dereference the @q->backing_dev_info
+	 * pointer, only decrease its reference count after having removed the
+	 * association with the block cgroup controller.
+	 */
+	bdi_put(q->backing_dev_info);
+}
+
 /**
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
@@ -762,9 +791,13 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * make sure all in-progress dispatch are completed because
 	 * blk_freeze_queue() can only complete all requests, and
 	 * dispatch may still be in-progress since we dispatch requests
-	 * from more than one contexts
+	 * from more than one contexts.
+	 *
+	 * No need to quiesce queue if it isn't initialized yet since
+	 * blk_freeze_queue() should be enough for cases of passthrough
+	 * request.
 	 */
-	if (q->mq_ops)
+	if (q->mq_ops && blk_queue_init_done(q))
 		blk_mq_quiesce_queue(q);
 
 	/* for synchronous bio-based driver finish in-flight integrity i/o */
@@ -780,30 +813,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	 */
 	WARN_ON_ONCE(q->kobj.state_in_sysfs);
 
-	/*
-	 * Since the I/O scheduler exit code may access cgroup information,
-	 * perform I/O scheduler exit before disassociating from the block
-	 * cgroup controller.
-	 */
-	if (q->elevator) {
-		ioc_clear_queue(q);
-		elevator_exit(q, q->elevator);
-		q->elevator = NULL;
-	}
-
-	/*
-	 * Remove all references to @q from the block cgroup controller before
-	 * restoring @q->queue_lock to avoid that restoring this pointer causes
-	 * e.g. blkcg_print_blkgs() to crash.
-	 */
-	blkcg_exit_queue(q);
-
-	/*
-	 * Since the cgroup code may dereference the @q->backing_dev_info
-	 * pointer, only decrease its reference count after having removed the
-	 * association with the block cgroup controller.
-	 */
-	bdi_put(q->backing_dev_info);
+	blk_exit_queue(q);
 
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
@@ -1180,6 +1190,7 @@ out_exit_flush_rq:
 		q->exit_rq_fn(q, q->fq->flush_rq);
 out_free_flush_queue:
 	blk_free_flush_queue(q->fq);
+	q->fq = NULL;
 	return -ENOMEM;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -1641,7 +1652,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 	blk_delete_timer(rq);
 	blk_clear_rq_complete(rq);
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, rq);
+	rq_qos_requeue(q, rq);
 
 	if (rq->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, rq);
@@ -1748,7 +1759,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	/* this is a bio leak */
 	WARN_ON(req->bio != NULL);
 
-	wbt_done(q->rq_wb, req);
+	rq_qos_done(q, req);
 
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
@@ -1982,7 +1993,6 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	int where = ELEVATOR_INSERT_SORT;
 	struct request *req, *free;
 	unsigned int request_count = 0;
-	unsigned int wb_acct;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -2040,7 +2050,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 get_rq:
-	wb_acct = wbt_wait(q->rq_wb, bio, q->queue_lock);
+	rq_qos_throttle(q, bio, q->queue_lock);
 
 	/*
 	 * Grab a free request. This is might sleep but can not fail.
@@ -2050,7 +2060,7 @@ get_rq:
 	req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
 	if (IS_ERR(req)) {
 		blk_queue_exit(q);
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, bio);
 		if (PTR_ERR(req) == -ENOMEM)
 			bio->bi_status = BLK_STS_RESOURCE;
 		else
@@ -2059,7 +2069,7 @@ get_rq:
 		goto out_unlock;
 	}
 
-	wbt_track(req, wb_acct);
+	rq_qos_track(q, req, bio);
 
 	/*
 	 * After dropping the lock and possibly sleeping here, our request
@@ -2155,11 +2165,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 	if (part->policy && op_is_write(bio_op(bio))) {
 		char b[BDEVNAME_SIZE];
 
-		printk(KERN_ERR
+		WARN_ONCE(1,
 		       "generic_make_request: Trying to write "
 			"to read-only block-device %s (partno %d)\n",
 			bio_devname(bio, b), part->partno);
-		return true;
+		/* Older lvm-tools actually trigger this */
+		return false;
 	}
 
 	return false;
@@ -2699,13 +2710,13 @@ EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (blk_do_io_stat(req)) {
-		const int rw = rq_data_dir(req);
+		const int sgrp = op_stat_group(req_op(req));
 		struct hd_struct *part;
 		int cpu;
 
 		cpu = part_stat_lock();
 		part = req->part;
-		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+		part_stat_add(cpu, part, sectors[sgrp], bytes >> 9);
 		part_stat_unlock();
 	}
 }
@@ -2719,7 +2730,7 @@ void blk_account_io_done(struct request *req, u64 now)
 	 */
 	if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
 		unsigned long duration;
-		const int rw = rq_data_dir(req);
+		const int sgrp = op_stat_group(req_op(req));
 		struct hd_struct *part;
 		int cpu;
 
@@ -2727,10 +2738,10 @@ void blk_account_io_done(struct request *req, u64 now)
 		cpu = part_stat_lock();
 		part = req->part;
 
-		part_stat_inc(cpu, part, ios[rw]);
-		part_stat_add(cpu, part, ticks[rw], duration);
+		part_stat_inc(cpu, part, ios[sgrp]);
+		part_stat_add(cpu, part, ticks[sgrp], duration);
 		part_round_stats(req->q, cpu, part);
-		part_dec_in_flight(req->q, part, rw);
+		part_dec_in_flight(req->q, part, rq_data_dir(req));
 
 		hd_struct_put(part);
 		part_stat_unlock();
@@ -2750,9 +2761,9 @@ static bool blk_pm_allow_request(struct request *rq)
 		return rq->rq_flags & RQF_PM;
 	case RPM_SUSPENDED:
 		return false;
+	default:
+		return true;
 	}
-
-	return true;
 }
 #else
 static bool blk_pm_allow_request(struct request *rq)
@@ -2979,7 +2990,7 @@ void blk_start_request(struct request *req)
 		req->throtl_size = blk_rq_sectors(req);
 #endif
 		req->rq_flags |= RQF_STATS;
-		wbt_issue(req->q->rq_wb, req);
+		rq_qos_issue(req->q, req);
 	}
 
 	BUG_ON(blk_rq_is_complete(req));
@@ -3052,6 +3063,10 @@ EXPORT_SYMBOL_GPL(blk_steal_bios);
  *     Passing the result of blk_rq_bytes() as @nr_bytes guarantees
  *     %false return from this function.
  *
+ * Note:
+ *	The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in both
+ *	blk_rq_bytes() and in blk_update_request().
+ *
  * Return:
  *     %false - this request doesn't have any more data
  *     %true  - this request has more data
@@ -3199,7 +3214,7 @@ void blk_finish_request(struct request *req, blk_status_t error)
 	blk_account_io_done(req, now);
 
 	if (req->end_io) {
-		wbt_done(req->q->rq_wb, req);
+		rq_qos_done(q, req);
 		req->end_io(req, error);
 	} else {
 		if (blk_bidi_rq(req))
@@ -3473,6 +3488,10 @@ static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 	dst->cpu = src->cpu;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
+	if (src->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		dst->rq_flags |= RQF_SPECIAL_PAYLOAD;
+		dst->special_vec = src->special_vec;
+	}
 	dst->nr_phys_segments = src->nr_phys_segments;
 	dst->ioprio = src->ioprio;
 	dst->extra_len = src->extra_len;
@@ -3758,9 +3777,11 @@ EXPORT_SYMBOL(blk_finish_plug);
  */
 void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
 {
-	/* not support for RQF_PM and ->rpm_status in blk-mq yet */
-	if (q->mq_ops)
+	/* Don't enable runtime PM for blk-mq until it is ready */
+	if (q->mq_ops) {
+		pm_runtime_disable(dev);
 		return;
+	}
 
 	q->dev = dev;
 	q->rpm_status = RPM_ACTIVE;
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index f23311e4b201..01580f88fcb3 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -278,7 +278,7 @@ int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
 	atomic_set(&ioc->nr_tasks, 1);
 	atomic_set(&ioc->active_ref, 1);
 	spin_lock_init(&ioc->lock);
-	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC | __GFP_HIGH);
+	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC);
 	INIT_HLIST_HEAD(&ioc->icq_list);
 	INIT_WORK(&ioc->release_work, ioc_release_fn);
 
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
new file mode 100644
index 000000000000..19923f8a029d
--- /dev/null
+++ b/block/blk-iolatency.c
@@ -0,0 +1,955 @@
+/*
+ * Block rq-qos base io controller
+ *
+ * This works similar to wbt with a few exceptions
+ *
+ * - It's bio based, so the latency covers the whole block layer in addition to
+ *   the actual io.
+ * - We will throttle all IO that comes in here if we need to.
+ * - We use the mean latency over the 100ms window.  This is because writes can
+ *   be particularly fast, which could give us a false sense of the impact of
+ *   other workloads on our protected workload.
+ * - By default there's no throttling, we set the queue_depth to UINT_MAX so
+ *   that we can have as many outstanding bio's as we're allowed to.  Only at
+ *   throttle time do we pay attention to the actual queue depth.
+ *
+ * The hierarchy works like the cpu controller does, we track the latency at
+ * every configured node, and each configured node has it's own independent
+ * queue depth.  This means that we only care about our latency targets at the
+ * peer level.  Some group at the bottom of the hierarchy isn't going to affect
+ * a group at the end of some other path if we're only configred at leaf level.
+ *
+ * Consider the following
+ *
+ *                   root blkg
+ *             /                     \
+ *        fast (target=5ms)     slow (target=10ms)
+ *         /     \                  /        \
+ *       a        b          normal(15ms)   unloved
+ *
+ * "a" and "b" have no target, but their combined io under "fast" cannot exceed
+ * an average latency of 5ms.  If it does then we will throttle the "slow"
+ * group.  In the case of "normal", if it exceeds its 15ms target, we will
+ * throttle "unloved", but nobody else.
+ *
+ * In this example "fast", "slow", and "normal" will be the only groups actually
+ * accounting their io latencies.  We have to walk up the heirarchy to the root
+ * on every submit and complete so we can do the appropriate stat recording and
+ * adjust the queue depth of ourselves if needed.
+ *
+ * There are 2 ways we throttle IO.
+ *
+ * 1) Queue depth throttling.  As we throttle down we will adjust the maximum
+ * number of IO's we're allowed to have in flight.  This starts at (u64)-1 down
+ * to 1.  If the group is only ever submitting IO for itself then this is the
+ * only way we throttle.
+ *
+ * 2) Induced delay throttling.  This is for the case that a group is generating
+ * IO that has to be issued by the root cg to avoid priority inversion. So think
+ * REQ_META or REQ_SWAP.  If we are already at qd == 1 and we're getting a lot
+ * of work done for us on behalf of the root cg and are being asked to scale
+ * down more then we induce a latency at userspace return.  We accumulate the
+ * total amount of time we need to be punished by doing
+ *
+ * total_time += min_lat_nsec - actual_io_completion
+ *
+ * and then at throttle time will do
+ *
+ * throttle_time = min(total_time, NSEC_PER_SEC)
+ *
+ * This induced delay will throttle back the activity that is generating the
+ * root cg issued io's, wethere that's some metadata intensive operation or the
+ * group is using so much memory that it is pushing us into swap.
+ *
+ * Copyright (C) 2018 Josef Bacik
+ */
+#include <linux/kernel.h>
+#include <linux/blk_types.h>
+#include <linux/backing-dev.h>
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/memcontrol.h>
+#include <linux/sched/loadavg.h>
+#include <linux/sched/signal.h>
+#include <trace/events/block.h>
+#include "blk-rq-qos.h"
+#include "blk-stat.h"
+
+#define DEFAULT_SCALE_COOKIE 1000000U
+
+static struct blkcg_policy blkcg_policy_iolatency;
+struct iolatency_grp;
+
+struct blk_iolatency {
+	struct rq_qos rqos;
+	struct timer_list timer;
+	atomic_t enabled;
+};
+
+static inline struct blk_iolatency *BLKIOLATENCY(struct rq_qos *rqos)
+{
+	return container_of(rqos, struct blk_iolatency, rqos);
+}
+
+static inline bool blk_iolatency_enabled(struct blk_iolatency *blkiolat)
+{
+	return atomic_read(&blkiolat->enabled) > 0;
+}
+
+struct child_latency_info {
+	spinlock_t lock;
+
+	/* Last time we adjusted the scale of everybody. */
+	u64 last_scale_event;
+
+	/* The latency that we missed. */
+	u64 scale_lat;
+
+	/* Total io's from all of our children for the last summation. */
+	u64 nr_samples;
+
+	/* The guy who actually changed the latency numbers. */
+	struct iolatency_grp *scale_grp;
+
+	/* Cookie to tell if we need to scale up or down. */
+	atomic_t scale_cookie;
+};
+
+struct iolatency_grp {
+	struct blkg_policy_data pd;
+	struct blk_rq_stat __percpu *stats;
+	struct blk_iolatency *blkiolat;
+	struct rq_depth rq_depth;
+	struct rq_wait rq_wait;
+	atomic64_t window_start;
+	atomic_t scale_cookie;
+	u64 min_lat_nsec;
+	u64 cur_win_nsec;
+
+	/* total running average of our io latency. */
+	u64 lat_avg;
+
+	/* Our current number of IO's for the last summation. */
+	u64 nr_samples;
+
+	struct child_latency_info child_lat;
+};
+
+#define BLKIOLATENCY_MIN_WIN_SIZE (100 * NSEC_PER_MSEC)
+#define BLKIOLATENCY_MAX_WIN_SIZE NSEC_PER_SEC
+/*
+ * These are the constants used to fake the fixed-point moving average
+ * calculation just like load average.  The call to CALC_LOAD folds
+ * (FIXED_1 (2048) - exp_factor) * new_sample into lat_avg.  The sampling
+ * window size is bucketed to try to approximately calculate average
+ * latency such that 1/exp (decay rate) is [1 min, 2.5 min) when windows
+ * elapse immediately.  Note, windows only elapse with IO activity.  Idle
+ * periods extend the most recent window.
+ */
+#define BLKIOLATENCY_NR_EXP_FACTORS 5
+#define BLKIOLATENCY_EXP_BUCKET_SIZE (BLKIOLATENCY_MAX_WIN_SIZE / \
+				      (BLKIOLATENCY_NR_EXP_FACTORS - 1))
+static const u64 iolatency_exp_factors[BLKIOLATENCY_NR_EXP_FACTORS] = {
+	2045, // exp(1/600) - 600 samples
+	2039, // exp(1/240) - 240 samples
+	2031, // exp(1/120) - 120 samples
+	2023, // exp(1/80)  - 80 samples
+	2014, // exp(1/60)  - 60 samples
+};
+
+static inline struct iolatency_grp *pd_to_lat(struct blkg_policy_data *pd)
+{
+	return pd ? container_of(pd, struct iolatency_grp, pd) : NULL;
+}
+
+static inline struct iolatency_grp *blkg_to_lat(struct blkcg_gq *blkg)
+{
+	return pd_to_lat(blkg_to_pd(blkg, &blkcg_policy_iolatency));
+}
+
+static inline struct blkcg_gq *lat_to_blkg(struct iolatency_grp *iolat)
+{
+	return pd_to_blkg(&iolat->pd);
+}
+
+static inline bool iolatency_may_queue(struct iolatency_grp *iolat,
+				       wait_queue_entry_t *wait,
+				       bool first_block)
+{
+	struct rq_wait *rqw = &iolat->rq_wait;
+
+	if (first_block && waitqueue_active(&rqw->wait) &&
+	    rqw->wait.head.next != &wait->entry)
+		return false;
+	return rq_wait_inc_below(rqw, iolat->rq_depth.max_depth);
+}
+
+static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
+				       struct iolatency_grp *iolat,
+				       spinlock_t *lock, bool issue_as_root,
+				       bool use_memdelay)
+	__releases(lock)
+	__acquires(lock)
+{
+	struct rq_wait *rqw = &iolat->rq_wait;
+	unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay);
+	DEFINE_WAIT(wait);
+	bool first_block = true;
+
+	if (use_delay)
+		blkcg_schedule_throttle(rqos->q, use_memdelay);
+
+	/*
+	 * To avoid priority inversions we want to just take a slot if we are
+	 * issuing as root.  If we're being killed off there's no point in
+	 * delaying things, we may have been killed by OOM so throttling may
+	 * make recovery take even longer, so just let the IO's through so the
+	 * task can go away.
+	 */
+	if (issue_as_root || fatal_signal_pending(current)) {
+		atomic_inc(&rqw->inflight);
+		return;
+	}
+
+	if (iolatency_may_queue(iolat, &wait, first_block))
+		return;
+
+	do {
+		prepare_to_wait_exclusive(&rqw->wait, &wait,
+					  TASK_UNINTERRUPTIBLE);
+
+		if (iolatency_may_queue(iolat, &wait, first_block))
+			break;
+		first_block = false;
+
+		if (lock) {
+			spin_unlock_irq(lock);
+			io_schedule();
+			spin_lock_irq(lock);
+		} else {
+			io_schedule();
+		}
+	} while (1);
+
+	finish_wait(&rqw->wait, &wait);
+}
+
+#define SCALE_DOWN_FACTOR 2
+#define SCALE_UP_FACTOR 4
+
+static inline unsigned long scale_amount(unsigned long qd, bool up)
+{
+	return max(up ? qd >> SCALE_UP_FACTOR : qd >> SCALE_DOWN_FACTOR, 1UL);
+}
+
+/*
+ * We scale the qd down faster than we scale up, so we need to use this helper
+ * to adjust the scale_cookie accordingly so we don't prematurely get
+ * scale_cookie at DEFAULT_SCALE_COOKIE and unthrottle too much.
+ *
+ * Each group has their own local copy of the last scale cookie they saw, so if
+ * the global scale cookie goes up or down they know which way they need to go
+ * based on their last knowledge of it.
+ */
+static void scale_cookie_change(struct blk_iolatency *blkiolat,
+				struct child_latency_info *lat_info,
+				bool up)
+{
+	unsigned long qd = blk_queue_depth(blkiolat->rqos.q);
+	unsigned long scale = scale_amount(qd, up);
+	unsigned long old = atomic_read(&lat_info->scale_cookie);
+	unsigned long max_scale = qd << 1;
+	unsigned long diff = 0;
+
+	if (old < DEFAULT_SCALE_COOKIE)
+		diff = DEFAULT_SCALE_COOKIE - old;
+
+	if (up) {
+		if (scale + old > DEFAULT_SCALE_COOKIE)
+			atomic_set(&lat_info->scale_cookie,
+				   DEFAULT_SCALE_COOKIE);
+		else if (diff > qd)
+			atomic_inc(&lat_info->scale_cookie);
+		else
+			atomic_add(scale, &lat_info->scale_cookie);
+	} else {
+		/*
+		 * We don't want to dig a hole so deep that it takes us hours to
+		 * dig out of it.  Just enough that we don't throttle/unthrottle
+		 * with jagged workloads but can still unthrottle once pressure
+		 * has sufficiently dissipated.
+		 */
+		if (diff > qd) {
+			if (diff < max_scale)
+				atomic_dec(&lat_info->scale_cookie);
+		} else {
+			atomic_sub(scale, &lat_info->scale_cookie);
+		}
+	}
+}
+
+/*
+ * Change the queue depth of the iolatency_grp.  We add/subtract 1/16th of the
+ * queue depth at a time so we don't get wild swings and hopefully dial in to
+ * fairer distribution of the overall queue depth.
+ */
+static void scale_change(struct iolatency_grp *iolat, bool up)
+{
+	unsigned long qd = blk_queue_depth(iolat->blkiolat->rqos.q);
+	unsigned long scale = scale_amount(qd, up);
+	unsigned long old = iolat->rq_depth.max_depth;
+	bool changed = false;
+
+	if (old > qd)
+		old = qd;
+
+	if (up) {
+		if (old == 1 && blkcg_unuse_delay(lat_to_blkg(iolat)))
+			return;
+
+		if (old < qd) {
+			changed = true;
+			old += scale;
+			old = min(old, qd);
+			iolat->rq_depth.max_depth = old;
+			wake_up_all(&iolat->rq_wait.wait);
+		}
+	} else if (old > 1) {
+		old >>= 1;
+		changed = true;
+		iolat->rq_depth.max_depth = max(old, 1UL);
+	}
+}
+
+/* Check our parent and see if the scale cookie has changed. */
+static void check_scale_change(struct iolatency_grp *iolat)
+{
+	struct iolatency_grp *parent;
+	struct child_latency_info *lat_info;
+	unsigned int cur_cookie;
+	unsigned int our_cookie = atomic_read(&iolat->scale_cookie);
+	u64 scale_lat;
+	unsigned int old;
+	int direction = 0;
+
+	if (lat_to_blkg(iolat)->parent == NULL)
+		return;
+
+	parent = blkg_to_lat(lat_to_blkg(iolat)->parent);
+	if (!parent)
+		return;
+
+	lat_info = &parent->child_lat;
+	cur_cookie = atomic_read(&lat_info->scale_cookie);
+	scale_lat = READ_ONCE(lat_info->scale_lat);
+
+	if (cur_cookie < our_cookie)
+		direction = -1;
+	else if (cur_cookie > our_cookie)
+		direction = 1;
+	else
+		return;
+
+	old = atomic_cmpxchg(&iolat->scale_cookie, our_cookie, cur_cookie);
+
+	/* Somebody beat us to the punch, just bail. */
+	if (old != our_cookie)
+		return;
+
+	if (direction < 0 && iolat->min_lat_nsec) {
+		u64 samples_thresh;
+
+		if (!scale_lat || iolat->min_lat_nsec <= scale_lat)
+			return;
+
+		/*
+		 * Sometimes high priority groups are their own worst enemy, so
+		 * instead of taking it out on some poor other group that did 5%
+		 * or less of the IO's for the last summation just skip this
+		 * scale down event.
+		 */
+		samples_thresh = lat_info->nr_samples * 5;
+		samples_thresh = div64_u64(samples_thresh, 100);
+		if (iolat->nr_samples <= samples_thresh)
+			return;
+	}
+
+	/* We're as low as we can go. */
+	if (iolat->rq_depth.max_depth == 1 && direction < 0) {
+		blkcg_use_delay(lat_to_blkg(iolat));
+		return;
+	}
+
+	/* We're back to the default cookie, unthrottle all the things. */
+	if (cur_cookie == DEFAULT_SCALE_COOKIE) {
+		blkcg_clear_delay(lat_to_blkg(iolat));
+		iolat->rq_depth.max_depth = UINT_MAX;
+		wake_up_all(&iolat->rq_wait.wait);
+		return;
+	}
+
+	scale_change(iolat, direction > 0);
+}
+
+static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
+				     spinlock_t *lock)
+{
+	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
+	struct blkcg *blkcg;
+	struct blkcg_gq *blkg;
+	struct request_queue *q = rqos->q;
+	bool issue_as_root = bio_issue_as_root_blkg(bio);
+
+	if (!blk_iolatency_enabled(blkiolat))
+		return;
+
+	rcu_read_lock();
+	blkcg = bio_blkcg(bio);
+	bio_associate_blkcg(bio, &blkcg->css);
+	blkg = blkg_lookup(blkcg, q);
+	if (unlikely(!blkg)) {
+		if (!lock)
+			spin_lock_irq(q->queue_lock);
+		blkg = blkg_lookup_create(blkcg, q);
+		if (IS_ERR(blkg))
+			blkg = NULL;
+		if (!lock)
+			spin_unlock_irq(q->queue_lock);
+	}
+	if (!blkg)
+		goto out;
+
+	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
+	bio_associate_blkg(bio, blkg);
+out:
+	rcu_read_unlock();
+	while (blkg && blkg->parent) {
+		struct iolatency_grp *iolat = blkg_to_lat(blkg);
+		if (!iolat) {
+			blkg = blkg->parent;
+			continue;
+		}
+
+		check_scale_change(iolat);
+		__blkcg_iolatency_throttle(rqos, iolat, lock, issue_as_root,
+				     (bio->bi_opf & REQ_SWAP) == REQ_SWAP);
+		blkg = blkg->parent;
+	}
+	if (!timer_pending(&blkiolat->timer))
+		mod_timer(&blkiolat->timer, jiffies + HZ);
+}
+
+static void iolatency_record_time(struct iolatency_grp *iolat,
+				  struct bio_issue *issue, u64 now,
+				  bool issue_as_root)
+{
+	struct blk_rq_stat *rq_stat;
+	u64 start = bio_issue_time(issue);
+	u64 req_time;
+
+	/*
+	 * Have to do this so we are truncated to the correct time that our
+	 * issue is truncated to.
+	 */
+	now = __bio_issue_time(now);
+
+	if (now <= start)
+		return;
+
+	req_time = now - start;
+
+	/*
+	 * We don't want to count issue_as_root bio's in the cgroups latency
+	 * statistics as it could skew the numbers downwards.
+	 */
+	if (unlikely(issue_as_root && iolat->rq_depth.max_depth != UINT_MAX)) {
+		u64 sub = iolat->min_lat_nsec;
+		if (req_time < sub)
+			blkcg_add_delay(lat_to_blkg(iolat), now, sub - req_time);
+		return;
+	}
+
+	rq_stat = get_cpu_ptr(iolat->stats);
+	blk_rq_stat_add(rq_stat, req_time);
+	put_cpu_ptr(rq_stat);
+}
+
+#define BLKIOLATENCY_MIN_ADJUST_TIME (500 * NSEC_PER_MSEC)
+#define BLKIOLATENCY_MIN_GOOD_SAMPLES 5
+
+static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now)
+{
+	struct blkcg_gq *blkg = lat_to_blkg(iolat);
+	struct iolatency_grp *parent;
+	struct child_latency_info *lat_info;
+	struct blk_rq_stat stat;
+	unsigned long flags;
+	int cpu, exp_idx;
+
+	blk_rq_stat_init(&stat);
+	preempt_disable();
+	for_each_online_cpu(cpu) {
+		struct blk_rq_stat *s;
+		s = per_cpu_ptr(iolat->stats, cpu);
+		blk_rq_stat_sum(&stat, s);
+		blk_rq_stat_init(s);
+	}
+	preempt_enable();
+
+	parent = blkg_to_lat(blkg->parent);
+	if (!parent)
+		return;
+
+	lat_info = &parent->child_lat;
+
+	/*
+	 * CALC_LOAD takes in a number stored in fixed point representation.
+	 * Because we are using this for IO time in ns, the values stored
+	 * are significantly larger than the FIXED_1 denominator (2048).
+	 * Therefore, rounding errors in the calculation are negligible and
+	 * can be ignored.
+	 */
+	exp_idx = min_t(int, BLKIOLATENCY_NR_EXP_FACTORS - 1,
+			div64_u64(iolat->cur_win_nsec,
+				  BLKIOLATENCY_EXP_BUCKET_SIZE));
+	CALC_LOAD(iolat->lat_avg, iolatency_exp_factors[exp_idx], stat.mean);
+
+	/* Everything is ok and we don't need to adjust the scale. */
+	if (stat.mean <= iolat->min_lat_nsec &&
+	    atomic_read(&lat_info->scale_cookie) == DEFAULT_SCALE_COOKIE)
+		return;
+
+	/* Somebody beat us to the punch, just bail. */
+	spin_lock_irqsave(&lat_info->lock, flags);
+	lat_info->nr_samples -= iolat->nr_samples;
+	lat_info->nr_samples += stat.nr_samples;
+	iolat->nr_samples = stat.nr_samples;
+
+	if ((lat_info->last_scale_event >= now ||
+	    now - lat_info->last_scale_event < BLKIOLATENCY_MIN_ADJUST_TIME) &&
+	    lat_info->scale_lat <= iolat->min_lat_nsec)
+		goto out;
+
+	if (stat.mean <= iolat->min_lat_nsec &&
+	    stat.nr_samples >= BLKIOLATENCY_MIN_GOOD_SAMPLES) {
+		if (lat_info->scale_grp == iolat) {
+			lat_info->last_scale_event = now;
+			scale_cookie_change(iolat->blkiolat, lat_info, true);
+		}
+	} else if (stat.mean > iolat->min_lat_nsec) {
+		lat_info->last_scale_event = now;
+		if (!lat_info->scale_grp ||
+		    lat_info->scale_lat > iolat->min_lat_nsec) {
+			WRITE_ONCE(lat_info->scale_lat, iolat->min_lat_nsec);
+			lat_info->scale_grp = iolat;
+		}
+		scale_cookie_change(iolat->blkiolat, lat_info, false);
+	}
+out:
+	spin_unlock_irqrestore(&lat_info->lock, flags);
+}
+
+static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
+{
+	struct blkcg_gq *blkg;
+	struct rq_wait *rqw;
+	struct iolatency_grp *iolat;
+	u64 window_start;
+	u64 now = ktime_to_ns(ktime_get());
+	bool issue_as_root = bio_issue_as_root_blkg(bio);
+	bool enabled = false;
+
+	blkg = bio->bi_blkg;
+	if (!blkg)
+		return;
+
+	iolat = blkg_to_lat(bio->bi_blkg);
+	if (!iolat)
+		return;
+
+	enabled = blk_iolatency_enabled(iolat->blkiolat);
+	while (blkg && blkg->parent) {
+		iolat = blkg_to_lat(blkg);
+		if (!iolat) {
+			blkg = blkg->parent;
+			continue;
+		}
+		rqw = &iolat->rq_wait;
+
+		atomic_dec(&rqw->inflight);
+		if (!enabled || iolat->min_lat_nsec == 0)
+			goto next;
+		iolatency_record_time(iolat, &bio->bi_issue, now,
+				      issue_as_root);
+		window_start = atomic64_read(&iolat->window_start);
+		if (now > window_start &&
+		    (now - window_start) >= iolat->cur_win_nsec) {
+			if (atomic64_cmpxchg(&iolat->window_start,
+					window_start, now) == window_start)
+				iolatency_check_latencies(iolat, now);
+		}
+next:
+		wake_up(&rqw->wait);
+		blkg = blkg->parent;
+	}
+}
+
+static void blkcg_iolatency_cleanup(struct rq_qos *rqos, struct bio *bio)
+{
+	struct blkcg_gq *blkg;
+
+	blkg = bio->bi_blkg;
+	while (blkg && blkg->parent) {
+		struct rq_wait *rqw;
+		struct iolatency_grp *iolat;
+
+		iolat = blkg_to_lat(blkg);
+		if (!iolat)
+			goto next;
+
+		rqw = &iolat->rq_wait;
+		atomic_dec(&rqw->inflight);
+		wake_up(&rqw->wait);
+next:
+		blkg = blkg->parent;
+	}
+}
+
+static void blkcg_iolatency_exit(struct rq_qos *rqos)
+{
+	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
+
+	del_timer_sync(&blkiolat->timer);
+	blkcg_deactivate_policy(rqos->q, &blkcg_policy_iolatency);
+	kfree(blkiolat);
+}
+
+static struct rq_qos_ops blkcg_iolatency_ops = {
+	.throttle = blkcg_iolatency_throttle,
+	.cleanup = blkcg_iolatency_cleanup,
+	.done_bio = blkcg_iolatency_done_bio,
+	.exit = blkcg_iolatency_exit,
+};
+
+static void blkiolatency_timer_fn(struct timer_list *t)
+{
+	struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer);
+	struct blkcg_gq *blkg;
+	struct cgroup_subsys_state *pos_css;
+	u64 now = ktime_to_ns(ktime_get());
+
+	rcu_read_lock();
+	blkg_for_each_descendant_pre(blkg, pos_css,
+				     blkiolat->rqos.q->root_blkg) {
+		struct iolatency_grp *iolat;
+		struct child_latency_info *lat_info;
+		unsigned long flags;
+		u64 cookie;
+
+		/*
+		 * We could be exiting, don't access the pd unless we have a
+		 * ref on the blkg.
+		 */
+		if (!blkg_try_get(blkg))
+			continue;
+
+		iolat = blkg_to_lat(blkg);
+		if (!iolat)
+			goto next;
+
+		lat_info = &iolat->child_lat;
+		cookie = atomic_read(&lat_info->scale_cookie);
+
+		if (cookie >= DEFAULT_SCALE_COOKIE)
+			goto next;
+
+		spin_lock_irqsave(&lat_info->lock, flags);
+		if (lat_info->last_scale_event >= now)
+			goto next_lock;
+
+		/*
+		 * We scaled down but don't have a scale_grp, scale up and carry
+		 * on.
+		 */
+		if (lat_info->scale_grp == NULL) {
+			scale_cookie_change(iolat->blkiolat, lat_info, true);
+			goto next_lock;
+		}
+
+		/*
+		 * It's been 5 seconds since our last scale event, clear the
+		 * scale grp in case the group that needed the scale down isn't
+		 * doing any IO currently.
+		 */
+		if (now - lat_info->last_scale_event >=
+		    ((u64)NSEC_PER_SEC * 5))
+			lat_info->scale_grp = NULL;
+next_lock:
+		spin_unlock_irqrestore(&lat_info->lock, flags);
+next:
+		blkg_put(blkg);
+	}
+	rcu_read_unlock();
+}
+
+int blk_iolatency_init(struct request_queue *q)
+{
+	struct blk_iolatency *blkiolat;
+	struct rq_qos *rqos;
+	int ret;
+
+	blkiolat = kzalloc(sizeof(*blkiolat), GFP_KERNEL);
+	if (!blkiolat)
+		return -ENOMEM;
+
+	rqos = &blkiolat->rqos;
+	rqos->id = RQ_QOS_CGROUP;
+	rqos->ops = &blkcg_iolatency_ops;
+	rqos->q = q;
+
+	rq_qos_add(q, rqos);
+
+	ret = blkcg_activate_policy(q, &blkcg_policy_iolatency);
+	if (ret) {
+		rq_qos_del(q, rqos);
+		kfree(blkiolat);
+		return ret;
+	}
+
+	timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0);
+
+	return 0;
+}
+
+static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
+{
+	struct iolatency_grp *iolat = blkg_to_lat(blkg);
+	struct blk_iolatency *blkiolat = iolat->blkiolat;
+	u64 oldval = iolat->min_lat_nsec;
+
+	iolat->min_lat_nsec = val;
+	iolat->cur_win_nsec = max_t(u64, val << 4, BLKIOLATENCY_MIN_WIN_SIZE);
+	iolat->cur_win_nsec = min_t(u64, iolat->cur_win_nsec,
+				    BLKIOLATENCY_MAX_WIN_SIZE);
+
+	if (!oldval && val)
+		atomic_inc(&blkiolat->enabled);
+	if (oldval && !val)
+		atomic_dec(&blkiolat->enabled);
+}
+
+static void iolatency_clear_scaling(struct blkcg_gq *blkg)
+{
+	if (blkg->parent) {
+		struct iolatency_grp *iolat = blkg_to_lat(blkg->parent);
+		struct child_latency_info *lat_info;
+		if (!iolat)
+			return;
+
+		lat_info = &iolat->child_lat;
+		spin_lock(&lat_info->lock);
+		atomic_set(&lat_info->scale_cookie, DEFAULT_SCALE_COOKIE);
+		lat_info->last_scale_event = 0;
+		lat_info->scale_grp = NULL;
+		lat_info->scale_lat = 0;
+		spin_unlock(&lat_info->lock);
+	}
+}
+
+static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
+			     size_t nbytes, loff_t off)
+{
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
+	struct blkcg_gq *blkg;
+	struct blk_iolatency *blkiolat;
+	struct blkg_conf_ctx ctx;
+	struct iolatency_grp *iolat;
+	char *p, *tok;
+	u64 lat_val = 0;
+	u64 oldval;
+	int ret;
+
+	ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx);
+	if (ret)
+		return ret;
+
+	iolat = blkg_to_lat(ctx.blkg);
+	blkiolat = iolat->blkiolat;
+	p = ctx.body;
+
+	ret = -EINVAL;
+	while ((tok = strsep(&p, " "))) {
+		char key[16];
+		char val[21];	/* 18446744073709551616 */
+
+		if (sscanf(tok, "%15[^=]=%20s", key, val) != 2)
+			goto out;
+
+		if (!strcmp(key, "target")) {
+			u64 v;
+
+			if (!strcmp(val, "max"))
+				lat_val = 0;
+			else if (sscanf(val, "%llu", &v) == 1)
+				lat_val = v * NSEC_PER_USEC;
+			else
+				goto out;
+		} else {
+			goto out;
+		}
+	}
+
+	/* Walk up the tree to see if our new val is lower than it should be. */
+	blkg = ctx.blkg;
+	oldval = iolat->min_lat_nsec;
+
+	iolatency_set_min_lat_nsec(blkg, lat_val);
+	if (oldval != iolat->min_lat_nsec) {
+		iolatency_clear_scaling(blkg);
+	}
+
+	ret = 0;
+out:
+	blkg_conf_finish(&ctx);
+	return ret ?: nbytes;
+}
+
+static u64 iolatency_prfill_limit(struct seq_file *sf,
+				  struct blkg_policy_data *pd, int off)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	const char *dname = blkg_dev_name(pd->blkg);
+
+	if (!dname || !iolat->min_lat_nsec)
+		return 0;
+	seq_printf(sf, "%s target=%llu\n",
+		   dname, div_u64(iolat->min_lat_nsec, NSEC_PER_USEC));
+	return 0;
+}
+
+static int iolatency_print_limit(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  iolatency_prfill_limit,
+			  &blkcg_policy_iolatency, seq_cft(sf)->private, false);
+	return 0;
+}
+
+static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf,
+				size_t size)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	unsigned long long avg_lat = div64_u64(iolat->lat_avg, NSEC_PER_USEC);
+	unsigned long long cur_win = div64_u64(iolat->cur_win_nsec, NSEC_PER_MSEC);
+
+	if (iolat->rq_depth.max_depth == UINT_MAX)
+		return scnprintf(buf, size, " depth=max avg_lat=%llu win=%llu",
+				 avg_lat, cur_win);
+
+	return scnprintf(buf, size, " depth=%u avg_lat=%llu win=%llu",
+			 iolat->rq_depth.max_depth, avg_lat, cur_win);
+}
+
+
+static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, int node)
+{
+	struct iolatency_grp *iolat;
+
+	iolat = kzalloc_node(sizeof(*iolat), gfp, node);
+	if (!iolat)
+		return NULL;
+	iolat->stats = __alloc_percpu_gfp(sizeof(struct blk_rq_stat),
+				       __alignof__(struct blk_rq_stat), gfp);
+	if (!iolat->stats) {
+		kfree(iolat);
+		return NULL;
+	}
+	return &iolat->pd;
+}
+
+static void iolatency_pd_init(struct blkg_policy_data *pd)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	struct blkcg_gq *blkg = lat_to_blkg(iolat);
+	struct rq_qos *rqos = blkcg_rq_qos(blkg->q);
+	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
+	u64 now = ktime_to_ns(ktime_get());
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct blk_rq_stat *stat;
+		stat = per_cpu_ptr(iolat->stats, cpu);
+		blk_rq_stat_init(stat);
+	}
+
+	rq_wait_init(&iolat->rq_wait);
+	spin_lock_init(&iolat->child_lat.lock);
+	iolat->rq_depth.queue_depth = blk_queue_depth(blkg->q);
+	iolat->rq_depth.max_depth = UINT_MAX;
+	iolat->rq_depth.default_depth = iolat->rq_depth.queue_depth;
+	iolat->blkiolat = blkiolat;
+	iolat->cur_win_nsec = 100 * NSEC_PER_MSEC;
+	atomic64_set(&iolat->window_start, now);
+
+	/*
+	 * We init things in list order, so the pd for the parent may not be
+	 * init'ed yet for whatever reason.
+	 */
+	if (blkg->parent && blkg_to_pd(blkg->parent, &blkcg_policy_iolatency)) {
+		struct iolatency_grp *parent = blkg_to_lat(blkg->parent);
+		atomic_set(&iolat->scale_cookie,
+			   atomic_read(&parent->child_lat.scale_cookie));
+	} else {
+		atomic_set(&iolat->scale_cookie, DEFAULT_SCALE_COOKIE);
+	}
+
+	atomic_set(&iolat->child_lat.scale_cookie, DEFAULT_SCALE_COOKIE);
+}
+
+static void iolatency_pd_offline(struct blkg_policy_data *pd)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	struct blkcg_gq *blkg = lat_to_blkg(iolat);
+
+	iolatency_set_min_lat_nsec(blkg, 0);
+	iolatency_clear_scaling(blkg);
+}
+
+static void iolatency_pd_free(struct blkg_policy_data *pd)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	free_percpu(iolat->stats);
+	kfree(iolat);
+}
+
+static struct cftype iolatency_files[] = {
+	{
+		.name = "latency",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = iolatency_print_limit,
+		.write = iolatency_set_limit,
+	},
+	{}
+};
+
+static struct blkcg_policy blkcg_policy_iolatency = {
+	.dfl_cftypes	= iolatency_files,
+	.pd_alloc_fn	= iolatency_pd_alloc,
+	.pd_init_fn	= iolatency_pd_init,
+	.pd_offline_fn	= iolatency_pd_offline,
+	.pd_free_fn	= iolatency_pd_free,
+	.pd_stat_fn	= iolatency_pd_stat,
+};
+
+static int __init iolatency_init(void)
+{
+	return blkcg_policy_register(&blkcg_policy_iolatency);
+}
+
+static void __exit iolatency_exit(void)
+{
+	return blkcg_policy_unregister(&blkcg_policy_iolatency);
+}
+
+module_init(iolatency_init);
+module_exit(iolatency_exit);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 8faa70f26fcd..d1b9dd03da25 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -68,6 +68,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		 */
 		req_sects = min_t(sector_t, nr_sects,
 					q->limits.max_discard_sectors);
+		if (!req_sects)
+			goto fail;
 		if (req_sects > UINT_MAX >> 9)
 			req_sects = UINT_MAX >> 9;
 
@@ -105,6 +107,14 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	*biop = bio;
 	return 0;
+
+fail:
+	if (bio) {
+		submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	*biop = NULL;
+	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL(__blkdev_issue_discard);
 
diff --git a/block/blk-mq-debugfs-zoned.c b/block/blk-mq-debugfs-zoned.c
new file mode 100644
index 000000000000..fb2c82c351e4
--- /dev/null
+++ b/block/blk-mq-debugfs-zoned.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/blkdev.h>
+#include "blk-mq-debugfs.h"
+
+int queue_zone_wlock_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	unsigned int i;
+
+	if (!q->seq_zones_wlock)
+		return 0;
+
+	for (i = 0; i < q->nr_zones; i++)
+		if (test_bit(i, q->seq_zones_wlock))
+			seq_printf(m, "%u\n", i);
+
+	return 0;
+}
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 1c4532e92938..cb1e6cf7ac48 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -206,21 +206,6 @@ static ssize_t queue_write_hint_store(void *data, const char __user *buf,
 	return count;
 }
 
-static int queue_zone_wlock_show(void *data, struct seq_file *m)
-{
-	struct request_queue *q = data;
-	unsigned int i;
-
-	if (!q->seq_zones_wlock)
-		return 0;
-
-	for (i = 0; i < blk_queue_nr_zones(q); i++)
-		if (test_bit(i, q->seq_zones_wlock))
-			seq_printf(m, "%u\n", i);
-
-	return 0;
-}
-
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
 	{ "poll_stat", 0400, queue_poll_stat_show },
 	{ "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops },
@@ -637,6 +622,14 @@ static int hctx_active_show(void *data, struct seq_file *m)
 	return 0;
 }
 
+static int hctx_dispatch_busy_show(void *data, struct seq_file *m)
+{
+	struct blk_mq_hw_ctx *hctx = data;
+
+	seq_printf(m, "%u\n", hctx->dispatch_busy);
+	return 0;
+}
+
 static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
 	__acquires(&ctx->lock)
 {
@@ -798,6 +791,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"queued", 0600, hctx_queued_show, hctx_queued_write},
 	{"run", 0600, hctx_run_show, hctx_run_write},
 	{"active", 0400, hctx_active_show},
+	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
 	{},
 };
 
diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h
index b9d366e57097..a9160be12be0 100644
--- a/block/blk-mq-debugfs.h
+++ b/block/blk-mq-debugfs.h
@@ -80,4 +80,13 @@ static inline void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hc
 }
 #endif
 
+#ifdef CONFIG_BLK_DEBUG_FS_ZONED
+int queue_zone_wlock_show(void *data, struct seq_file *m);
+#else
+static inline int queue_zone_wlock_show(void *data, struct seq_file *m)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c
index e233996bb76f..db644ec624f5 100644
--- a/block/blk-mq-pci.c
+++ b/block/blk-mq-pci.c
@@ -17,6 +17,8 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 
+#include "blk-mq.h"
+
 /**
  * blk_mq_pci_map_queues - provide a default queue mapping for PCI device
  * @set:	tagset to provide the mapping for
@@ -48,8 +50,7 @@ int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
 
 fallback:
 	WARN_ON_ONCE(set->nr_hw_queues > 1);
-	for_each_possible_cpu(cpu)
-		set->mq_map[cpu] = 0;
+	blk_mq_clear_mq_map(set);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 56c493c6cd90..cf9c66c6d35a 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -59,29 +59,16 @@ static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
 	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
 		return;
 
-	if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-		struct request_queue *q = hctx->queue;
-
-		if (!test_and_set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-			atomic_inc(&q->shared_hctx_restart);
-	} else
-		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+	set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 }
 
-static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 {
 	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-		return false;
-
-	if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-		struct request_queue *q = hctx->queue;
-
-		if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-			atomic_dec(&q->shared_hctx_restart);
-	} else
-		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		return;
+	clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
-	return blk_mq_run_hw_queue(hctx, true);
+	blk_mq_run_hw_queue(hctx, true);
 }
 
 /*
@@ -219,15 +206,8 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 		}
 	} else if (has_sched_dispatch) {
 		blk_mq_do_dispatch_sched(hctx);
-	} else if (q->mq_ops->get_budget) {
-		/*
-		 * If we need to get budget before queuing request, we
-		 * dequeue request one by one from sw queue for avoiding
-		 * to mess up I/O merge when dispatch runs out of resource.
-		 *
-		 * TODO: get more budgets, and dequeue more requests in
-		 * one time.
-		 */
+	} else if (hctx->dispatch_busy) {
+		/* dequeue request one by one from sw queue if queue is busy */
 		blk_mq_do_dispatch_ctx(hctx);
 	} else {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
@@ -339,7 +319,8 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 		return e->type->ops.mq.bio_merge(hctx, bio);
 	}
 
-	if (hctx->flags & BLK_MQ_F_SHOULD_MERGE) {
+	if ((hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
+			!list_empty_careful(&ctx->rq_list)) {
 		/* default per sw-queue merge */
 		spin_lock(&ctx->lock);
 		ret = blk_mq_attempt_merge(q, ctx, bio);
@@ -380,68 +361,6 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
 	return false;
 }
 
-/**
- * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
- * @pos:    loop cursor.
- * @skip:   the list element that will not be examined. Iteration starts at
- *          @skip->next.
- * @head:   head of the list to examine. This list must have at least one
- *          element, namely @skip.
- * @member: name of the list_head structure within typeof(*pos).
- */
-#define list_for_each_entry_rcu_rr(pos, skip, head, member)		\
-	for ((pos) = (skip);						\
-	     (pos = (pos)->member.next != (head) ? list_entry_rcu(	\
-			(pos)->member.next, typeof(*pos), member) :	\
-	      list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
-	     (pos) != (skip); )
-
-/*
- * Called after a driver tag has been freed to check whether a hctx needs to
- * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
- * queues in a round-robin fashion if the tag set of @hctx is shared with other
- * hardware queues.
- */
-void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
-{
-	struct blk_mq_tags *const tags = hctx->tags;
-	struct blk_mq_tag_set *const set = hctx->queue->tag_set;
-	struct request_queue *const queue = hctx->queue, *q;
-	struct blk_mq_hw_ctx *hctx2;
-	unsigned int i, j;
-
-	if (set->flags & BLK_MQ_F_TAG_SHARED) {
-		/*
-		 * If this is 0, then we know that no hardware queues
-		 * have RESTART marked. We're done.
-		 */
-		if (!atomic_read(&queue->shared_hctx_restart))
-			return;
-
-		rcu_read_lock();
-		list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
-					   tag_set_list) {
-			queue_for_each_hw_ctx(q, hctx2, i)
-				if (hctx2->tags == tags &&
-				    blk_mq_sched_restart_hctx(hctx2))
-					goto done;
-		}
-		j = hctx->queue_num + 1;
-		for (i = 0; i < queue->nr_hw_queues; i++, j++) {
-			if (j == queue->nr_hw_queues)
-				j = 0;
-			hctx2 = queue->queue_hw_ctx[j];
-			if (hctx2->tags == tags &&
-			    blk_mq_sched_restart_hctx(hctx2))
-				break;
-		}
-done:
-		rcu_read_unlock();
-	} else {
-		blk_mq_sched_restart_hctx(hctx);
-	}
-}
-
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 				 bool run_queue, bool async)
 {
@@ -486,8 +405,19 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 
 	if (e && e->type->ops.mq.insert_requests)
 		e->type->ops.mq.insert_requests(hctx, list, false);
-	else
+	else {
+		/*
+		 * try to issue requests directly if the hw queue isn't
+		 * busy in case of 'none' scheduler, and this way may save
+		 * us one extra enqueue & dequeue to sw queue.
+		 */
+		if (!hctx->dispatch_busy && !e && !run_queue_async) {
+			blk_mq_try_issue_list_directly(hctx, list);
+			if (list_empty(list))
+				return;
+		}
 		blk_mq_insert_requests(hctx, ctx, list);
+	}
 
 	blk_mq_run_hw_queue(hctx, run_queue_async);
 }
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 09b2ee6694fb..816923bf874d 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -23,6 +23,9 @@ bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
 
 /*
  * If a previously inactive queue goes active, bump the active user count.
+ * We need to do this before try to allocate driver tag, then even if fail
+ * to get tag when first time, the other shared-tag users could reserve
+ * budget for it.
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
@@ -271,7 +274,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * test and set the bit before assining ->rqs[].
 	 */
 	rq = tags->rqs[bitnr];
-	if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
+	if (rq && blk_mq_request_started(rq))
 		iter_data->fn(rq, iter_data->data, reserved);
 
 	return true;
@@ -399,8 +402,6 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 	if (tdepth <= tags->nr_reserved_tags)
 		return -EINVAL;
 
-	tdepth -= tags->nr_reserved_tags;
-
 	/*
 	 * If we are allowed to grow beyond the original size, allocate
 	 * a new set of tags before freeing the old one.
@@ -420,7 +421,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 		if (tdepth > 16 * BLKDEV_MAX_RQ)
 			return -EINVAL;
 
-		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, 0);
+		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth,
+				tags->nr_reserved_tags);
 		if (!new)
 			return -ENOMEM;
 		ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth);
@@ -437,7 +439,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 		 * Don't need (or can't) update reserved tags here, they
 		 * remain static and should never need resizing.
 		 */
-		sbitmap_queue_resize(&tags->bitmap_tags, tdepth);
+		sbitmap_queue_resize(&tags->bitmap_tags,
+				tdepth - tags->nr_reserved_tags);
 	}
 
 	return 0;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b429d515b568..72a0033ccee9 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -34,8 +34,8 @@
 #include "blk-mq-debugfs.h"
 #include "blk-mq-tag.h"
 #include "blk-stat.h"
-#include "blk-wbt.h"
 #include "blk-mq-sched.h"
+#include "blk-rq-qos.h"
 
 static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
 static void blk_mq_poll_stats_start(struct request_queue *q);
@@ -285,7 +285,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 		rq->tag = -1;
 		rq->internal_tag = tag;
 	} else {
-		if (blk_mq_tag_busy(data->hctx)) {
+		if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
 			rq_flags = RQF_MQ_INFLIGHT;
 			atomic_inc(&data->hctx->nr_active);
 		}
@@ -367,6 +367,8 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 		if (!op_is_flush(op) && e->type->ops.mq.limit_depth &&
 		    !(data->flags & BLK_MQ_REQ_RESERVED))
 			e->type->ops.mq.limit_depth(op, data);
+	} else {
+		blk_mq_tag_busy(data->hctx);
 	}
 
 	tag = blk_mq_get_tag(data);
@@ -504,7 +506,7 @@ void blk_mq_free_request(struct request *rq)
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
 
-	wbt_done(q->rq_wb, rq);
+	rq_qos_done(q, rq);
 
 	if (blk_rq_rl(rq))
 		blk_put_rl(blk_rq_rl(rq));
@@ -527,7 +529,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 	blk_account_io_done(rq, now);
 
 	if (rq->end_io) {
-		wbt_done(rq->q->rq_wb, rq);
+		rq_qos_done(rq->q, rq);
 		rq->end_io(rq, error);
 	} else {
 		if (unlikely(blk_bidi_rq(rq)))
@@ -558,10 +560,8 @@ static void __blk_mq_complete_request(struct request *rq)
 	bool shared = false;
 	int cpu;
 
-	if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) !=
-			MQ_RQ_IN_FLIGHT)
+	if (!blk_mq_mark_complete(rq))
 		return;
-
 	if (rq->internal_tag != -1)
 		blk_mq_sched_completed_request(rq);
 
@@ -641,7 +641,7 @@ void blk_mq_start_request(struct request *rq)
 		rq->throtl_size = blk_rq_sectors(rq);
 #endif
 		rq->rq_flags |= RQF_STATS;
-		wbt_issue(q->rq_wb, rq);
+		rq_qos_issue(q, rq);
 	}
 
 	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
@@ -667,7 +667,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 	blk_mq_put_driver_tag(rq);
 
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, rq);
+	rq_qos_requeue(q, rq);
 
 	if (blk_mq_request_started(rq)) {
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
@@ -964,16 +964,14 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
-bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
-			   bool wait)
+bool blk_mq_get_driver_tag(struct request *rq)
 {
 	struct blk_mq_alloc_data data = {
 		.q = rq->q,
 		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
-		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
+		.flags = BLK_MQ_REQ_NOWAIT,
 	};
-
-	might_sleep_if(wait);
+	bool shared;
 
 	if (rq->tag != -1)
 		goto done;
@@ -981,9 +979,10 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
 		data.flags |= BLK_MQ_REQ_RESERVED;
 
+	shared = blk_mq_tag_busy(data.hctx);
 	rq->tag = blk_mq_get_tag(&data);
 	if (rq->tag >= 0) {
-		if (blk_mq_tag_busy(data.hctx)) {
+		if (shared) {
 			rq->rq_flags |= RQF_MQ_INFLIGHT;
 			atomic_inc(&data.hctx->nr_active);
 		}
@@ -991,8 +990,6 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 	}
 
 done:
-	if (hctx)
-		*hctx = data.hctx;
 	return rq->tag != -1;
 }
 
@@ -1003,7 +1000,10 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 
 	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
 
+	spin_lock(&hctx->dispatch_wait_lock);
 	list_del_init(&wait->entry);
+	spin_unlock(&hctx->dispatch_wait_lock);
+
 	blk_mq_run_hw_queue(hctx, true);
 	return 1;
 }
@@ -1014,17 +1014,16 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
  * restart. For both cases, take care to check the condition again after
  * marking us as waiting.
  */
-static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
+static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 				 struct request *rq)
 {
-	struct blk_mq_hw_ctx *this_hctx = *hctx;
-	struct sbq_wait_state *ws;
+	struct wait_queue_head *wq;
 	wait_queue_entry_t *wait;
 	bool ret;
 
-	if (!(this_hctx->flags & BLK_MQ_F_TAG_SHARED)) {
-		if (!test_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state))
-			set_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state);
+	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
+		if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+			set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
 		/*
 		 * It's possible that a tag was freed in the window between the
@@ -1034,30 +1033,35 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 		 * Don't clear RESTART here, someone else could have set it.
 		 * At most this will cost an extra queue run.
 		 */
-		return blk_mq_get_driver_tag(rq, hctx, false);
+		return blk_mq_get_driver_tag(rq);
 	}
 
-	wait = &this_hctx->dispatch_wait;
+	wait = &hctx->dispatch_wait;
 	if (!list_empty_careful(&wait->entry))
 		return false;
 
-	spin_lock(&this_hctx->lock);
+	wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait;
+
+	spin_lock_irq(&wq->lock);
+	spin_lock(&hctx->dispatch_wait_lock);
 	if (!list_empty(&wait->entry)) {
-		spin_unlock(&this_hctx->lock);
+		spin_unlock(&hctx->dispatch_wait_lock);
+		spin_unlock_irq(&wq->lock);
 		return false;
 	}
 
-	ws = bt_wait_ptr(&this_hctx->tags->bitmap_tags, this_hctx);
-	add_wait_queue(&ws->wait, wait);
+	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue(wq, wait);
 
 	/*
 	 * It's possible that a tag was freed in the window between the
 	 * allocation failure and adding the hardware queue to the wait
 	 * queue.
 	 */
-	ret = blk_mq_get_driver_tag(rq, hctx, false);
+	ret = blk_mq_get_driver_tag(rq);
 	if (!ret) {
-		spin_unlock(&this_hctx->lock);
+		spin_unlock(&hctx->dispatch_wait_lock);
+		spin_unlock_irq(&wq->lock);
 		return false;
 	}
 
@@ -1065,16 +1069,47 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 	 * We got a tag, remove ourselves from the wait queue to ensure
 	 * someone else gets the wakeup.
 	 */
-	spin_lock_irq(&ws->wait.lock);
 	list_del_init(&wait->entry);
-	spin_unlock_irq(&ws->wait.lock);
-	spin_unlock(&this_hctx->lock);
+	spin_unlock(&hctx->dispatch_wait_lock);
+	spin_unlock_irq(&wq->lock);
 
 	return true;
 }
 
+#define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT  8
+#define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR  4
+/*
+ * Update dispatch busy with the Exponential Weighted Moving Average(EWMA):
+ * - EWMA is one simple way to compute running average value
+ * - weight(7/8 and 1/8) is applied so that it can decrease exponentially
+ * - take 4 as factor for avoiding to get too small(0) result, and this
+ *   factor doesn't matter because EWMA decreases exponentially
+ */
+static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
+{
+	unsigned int ewma;
+
+	if (hctx->queue->elevator)
+		return;
+
+	ewma = hctx->dispatch_busy;
+
+	if (!ewma && !busy)
+		return;
+
+	ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1;
+	if (busy)
+		ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR;
+	ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT;
+
+	hctx->dispatch_busy = ewma;
+}
+
 #define BLK_MQ_RESOURCE_DELAY	3		/* ms units */
 
+/*
+ * Returns true if we did some work AND can potentially do more.
+ */
 bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			     bool got_budget)
 {
@@ -1102,7 +1137,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
 			break;
 
-		if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+		if (!blk_mq_get_driver_tag(rq)) {
 			/*
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed. The
@@ -1110,7 +1145,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			 * before we add this entry back on the dispatch list,
 			 * we'll re-run it below.
 			 */
-			if (!blk_mq_mark_tag_wait(&hctx, rq)) {
+			if (!blk_mq_mark_tag_wait(hctx, rq)) {
 				blk_mq_put_dispatch_budget(hctx);
 				/*
 				 * For non-shared tags, the RESTART check
@@ -1134,7 +1169,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			bd.last = true;
 		else {
 			nxt = list_first_entry(list, struct request, queuelist);
-			bd.last = !blk_mq_get_driver_tag(nxt, NULL, false);
+			bd.last = !blk_mq_get_driver_tag(nxt);
 		}
 
 		ret = q->mq_ops->queue_rq(hctx, &bd);
@@ -1205,7 +1240,18 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			blk_mq_run_hw_queue(hctx, true);
 		else if (needs_restart && (ret == BLK_STS_RESOURCE))
 			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
-	}
+
+		blk_mq_update_dispatch_busy(hctx, true);
+		return false;
+	} else
+		blk_mq_update_dispatch_busy(hctx, false);
+
+	/*
+	 * If the host/device is unable to accept more work, inform the
+	 * caller of that.
+	 */
+	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
+		return false;
 
 	return (queued + errors) != 0;
 }
@@ -1532,19 +1578,19 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 			    struct list_head *list)
 
 {
+	struct request *rq;
+
 	/*
 	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
 	 * offline now
 	 */
-	spin_lock(&ctx->lock);
-	while (!list_empty(list)) {
-		struct request *rq;
-
-		rq = list_first_entry(list, struct request, queuelist);
+	list_for_each_entry(rq, list, queuelist) {
 		BUG_ON(rq->mq_ctx != ctx);
-		list_del_init(&rq->queuelist);
-		__blk_mq_insert_req_list(hctx, rq, false);
+		trace_block_rq_insert(hctx->queue, rq);
 	}
+
+	spin_lock(&ctx->lock);
+	list_splice_tail_init(list, &ctx->rq_list);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
 }
@@ -1647,13 +1693,16 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 	ret = q->mq_ops->queue_rq(hctx, &bd);
 	switch (ret) {
 	case BLK_STS_OK:
+		blk_mq_update_dispatch_busy(hctx, false);
 		*cookie = new_cookie;
 		break;
 	case BLK_STS_RESOURCE:
 	case BLK_STS_DEV_RESOURCE:
+		blk_mq_update_dispatch_busy(hctx, true);
 		__blk_mq_requeue_request(rq);
 		break;
 	default:
+		blk_mq_update_dispatch_busy(hctx, false);
 		*cookie = BLK_QC_T_NONE;
 		break;
 	}
@@ -1688,7 +1737,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (!blk_mq_get_dispatch_budget(hctx))
 		goto insert;
 
-	if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+	if (!blk_mq_get_driver_tag(rq)) {
 		blk_mq_put_dispatch_budget(hctx);
 		goto insert;
 	}
@@ -1736,6 +1785,27 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq)
 	return ret;
 }
 
+void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+		struct list_head *list)
+{
+	while (!list_empty(list)) {
+		blk_status_t ret;
+		struct request *rq = list_first_entry(list, struct request,
+				queuelist);
+
+		list_del_init(&rq->queuelist);
+		ret = blk_mq_request_issue_directly(rq);
+		if (ret != BLK_STS_OK) {
+			if (ret == BLK_STS_RESOURCE ||
+					ret == BLK_STS_DEV_RESOURCE) {
+				list_add(&rq->queuelist, list);
+				break;
+			}
+			blk_mq_end_request(rq, ret);
+		}
+	}
+}
+
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
@@ -1746,7 +1816,6 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	blk_qc_t cookie;
-	unsigned int wb_acct;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1762,19 +1831,19 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	if (blk_mq_sched_bio_merge(q, bio))
 		return BLK_QC_T_NONE;
 
-	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
+	rq_qos_throttle(q, bio, NULL);
 
 	trace_block_getrq(q, bio, bio->bi_opf);
 
 	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, bio);
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
 		return BLK_QC_T_NONE;
 	}
 
-	wbt_track(rq, wb_acct);
+	rq_qos_track(q, rq, bio);
 
 	cookie = request_to_qc_t(data.hctx, rq);
 
@@ -1837,7 +1906,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
 					&cookie);
 		}
-	} else if (q->nr_hw_queues > 1 && is_sync) {
+	} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
+			!data.hctx->dispatch_busy)) {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
@@ -2136,6 +2206,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 
 	hctx->nr_ctx = 0;
 
+	spin_lock_init(&hctx->dispatch_wait_lock);
 	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
 	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
 
@@ -2321,15 +2392,10 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		if (shared) {
-			if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-				atomic_inc(&q->shared_hctx_restart);
+		if (shared)
 			hctx->flags |= BLK_MQ_F_TAG_SHARED;
-		} else {
-			if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-				atomic_dec(&q->shared_hctx_restart);
+		else
 			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
-		}
 	}
 }
 
@@ -2360,7 +2426,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 		blk_mq_update_tag_set_depth(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
-	synchronize_rcu();
 	INIT_LIST_HEAD(&q->tag_set_list);
 }
 
@@ -2675,7 +2740,6 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 {
 	if (set->ops->map_queues) {
-		int cpu;
 		/*
 		 * transport .map_queues is usually done in the following
 		 * way:
@@ -2690,8 +2754,7 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 		 * killing stale mapping since one CPU may not be mapped
 		 * to any hw queue.
 		 */
-		for_each_possible_cpu(cpu)
-			set->mq_map[cpu] = 0;
+		blk_mq_clear_mq_map(set);
 
 		return set->ops->map_queues(set);
 	} else
@@ -2701,7 +2764,7 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
- * requested depth down, if if it too large. In that case, the set
+ * requested depth down, if it's too large. In that case, the set
  * value will be stored in set->queue_depth.
  */
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 89231e439b2f..9497b47e2526 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -36,8 +36,7 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
-bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
-				bool wait);
+bool blk_mq_get_driver_tag(struct request *rq);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);
 
@@ -65,6 +64,8 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 
 /* Used by blk_insert_cloned_request() to issue request directly */
 blk_status_t blk_mq_request_issue_directly(struct request *rq);
+void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+				    struct list_head *list);
 
 /*
  * CPU -> queue mappings
@@ -203,4 +204,12 @@ static inline void blk_mq_put_driver_tag(struct request *rq)
 	__blk_mq_put_driver_tag(hctx, rq);
 }
 
+static inline void blk_mq_clear_mq_map(struct blk_mq_tag_set *set)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		set->mq_map[cpu] = 0;
+}
+
 #endif
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
new file mode 100644
index 000000000000..0005dfd568dd
--- /dev/null
+++ b/block/blk-rq-qos.c
@@ -0,0 +1,194 @@
+#include "blk-rq-qos.h"
+
+/*
+ * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
+ * false if 'v' + 1 would be bigger than 'below'.
+ */
+static bool atomic_inc_below(atomic_t *v, unsigned int below)
+{
+	unsigned int cur = atomic_read(v);
+
+	for (;;) {
+		unsigned int old;
+
+		if (cur >= below)
+			return false;
+		old = atomic_cmpxchg(v, cur, cur + 1);
+		if (old == cur)
+			break;
+		cur = old;
+	}
+
+	return true;
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit)
+{
+	return atomic_inc_below(&rq_wait->inflight, limit);
+}
+
+void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->cleanup)
+			rqos->ops->cleanup(rqos, bio);
+	}
+}
+
+void rq_qos_done(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->done)
+			rqos->ops->done(rqos, rq);
+	}
+}
+
+void rq_qos_issue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->issue)
+			rqos->ops->issue(rqos, rq);
+	}
+}
+
+void rq_qos_requeue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->requeue)
+			rqos->ops->requeue(rqos, rq);
+	}
+}
+
+void rq_qos_throttle(struct request_queue *q, struct bio *bio,
+		     spinlock_t *lock)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->throttle)
+			rqos->ops->throttle(rqos, bio, lock);
+	}
+}
+
+void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->track)
+			rqos->ops->track(rqos, rq, bio);
+	}
+}
+
+void rq_qos_done_bio(struct request_queue *q, struct bio *bio)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->done_bio)
+			rqos->ops->done_bio(rqos, bio);
+	}
+}
+
+/*
+ * Return true, if we can't increase the depth further by scaling
+ */
+bool rq_depth_calc_max_depth(struct rq_depth *rqd)
+{
+	unsigned int depth;
+	bool ret = false;
+
+	/*
+	 * For QD=1 devices, this is a special case. It's important for those
+	 * to have one request ready when one completes, so force a depth of
+	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
+	 * since the device can't have more than that in flight. If we're
+	 * scaling down, then keep a setting of 1/1/1.
+	 */
+	if (rqd->queue_depth == 1) {
+		if (rqd->scale_step > 0)
+			rqd->max_depth = 1;
+		else {
+			rqd->max_depth = 2;
+			ret = true;
+		}
+	} else {
+		/*
+		 * scale_step == 0 is our default state. If we have suffered
+		 * latency spikes, step will be > 0, and we shrink the
+		 * allowed write depths. If step is < 0, we're only doing
+		 * writes, and we allow a temporarily higher depth to
+		 * increase performance.
+		 */
+		depth = min_t(unsigned int, rqd->default_depth,
+			      rqd->queue_depth);
+		if (rqd->scale_step > 0)
+			depth = 1 + ((depth - 1) >> min(31, rqd->scale_step));
+		else if (rqd->scale_step < 0) {
+			unsigned int maxd = 3 * rqd->queue_depth / 4;
+
+			depth = 1 + ((depth - 1) << -rqd->scale_step);
+			if (depth > maxd) {
+				depth = maxd;
+				ret = true;
+			}
+		}
+
+		rqd->max_depth = depth;
+	}
+
+	return ret;
+}
+
+void rq_depth_scale_up(struct rq_depth *rqd)
+{
+	/*
+	 * Hit max in previous round, stop here
+	 */
+	if (rqd->scaled_max)
+		return;
+
+	rqd->scale_step--;
+
+	rqd->scaled_max = rq_depth_calc_max_depth(rqd);
+}
+
+/*
+ * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
+ * had a latency violation.
+ */
+void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
+{
+	/*
+	 * Stop scaling down when we've hit the limit. This also prevents
+	 * ->scale_step from going to crazy values, if the device can't
+	 * keep up.
+	 */
+	if (rqd->max_depth == 1)
+		return;
+
+	if (rqd->scale_step < 0 && hard_throttle)
+		rqd->scale_step = 0;
+	else
+		rqd->scale_step++;
+
+	rqd->scaled_max = false;
+	rq_depth_calc_max_depth(rqd);
+}
+
+void rq_qos_exit(struct request_queue *q)
+{
+	while (q->rq_qos) {
+		struct rq_qos *rqos = q->rq_qos;
+		q->rq_qos = rqos->next;
+		rqos->ops->exit(rqos);
+	}
+}
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
new file mode 100644
index 000000000000..32b02efbfa66
--- /dev/null
+++ b/block/blk-rq-qos.h
@@ -0,0 +1,109 @@
+#ifndef RQ_QOS_H
+#define RQ_QOS_H
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blk_types.h>
+#include <linux/atomic.h>
+#include <linux/wait.h>
+
+enum rq_qos_id {
+	RQ_QOS_WBT,
+	RQ_QOS_CGROUP,
+};
+
+struct rq_wait {
+	wait_queue_head_t wait;
+	atomic_t inflight;
+};
+
+struct rq_qos {
+	struct rq_qos_ops *ops;
+	struct request_queue *q;
+	enum rq_qos_id id;
+	struct rq_qos *next;
+};
+
+struct rq_qos_ops {
+	void (*throttle)(struct rq_qos *, struct bio *, spinlock_t *);
+	void (*track)(struct rq_qos *, struct request *, struct bio *);
+	void (*issue)(struct rq_qos *, struct request *);
+	void (*requeue)(struct rq_qos *, struct request *);
+	void (*done)(struct rq_qos *, struct request *);
+	void (*done_bio)(struct rq_qos *, struct bio *);
+	void (*cleanup)(struct rq_qos *, struct bio *);
+	void (*exit)(struct rq_qos *);
+};
+
+struct rq_depth {
+	unsigned int max_depth;
+
+	int scale_step;
+	bool scaled_max;
+
+	unsigned int queue_depth;
+	unsigned int default_depth;
+};
+
+static inline struct rq_qos *rq_qos_id(struct request_queue *q,
+				       enum rq_qos_id id)
+{
+	struct rq_qos *rqos;
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->id == id)
+			break;
+	}
+	return rqos;
+}
+
+static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_WBT);
+}
+
+static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_CGROUP);
+}
+
+static inline void rq_wait_init(struct rq_wait *rq_wait)
+{
+	atomic_set(&rq_wait->inflight, 0);
+	init_waitqueue_head(&rq_wait->wait);
+}
+
+static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
+{
+	rqos->next = q->rq_qos;
+	q->rq_qos = rqos;
+}
+
+static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
+{
+	struct rq_qos *cur, *prev = NULL;
+	for (cur = q->rq_qos; cur; cur = cur->next) {
+		if (cur == rqos) {
+			if (prev)
+				prev->next = rqos->next;
+			else
+				q->rq_qos = cur;
+			break;
+		}
+		prev = cur;
+	}
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit);
+void rq_depth_scale_up(struct rq_depth *rqd);
+void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
+bool rq_depth_calc_max_depth(struct rq_depth *rqd);
+
+void rq_qos_cleanup(struct request_queue *, struct bio *);
+void rq_qos_done(struct request_queue *, struct request *);
+void rq_qos_issue(struct request_queue *, struct request *);
+void rq_qos_requeue(struct request_queue *, struct request *);
+void rq_qos_done_bio(struct request_queue *q, struct bio *bio);
+void rq_qos_throttle(struct request_queue *, struct bio *, spinlock_t *);
+void rq_qos_track(struct request_queue *q, struct request *, struct bio *);
+void rq_qos_exit(struct request_queue *);
+#endif
diff --git a/block/blk-settings.c b/block/blk-settings.c
index d1de71124656..ffd459969689 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -128,7 +128,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 
 	/* Inherit limits from component devices */
 	lim->max_segments = USHRT_MAX;
-	lim->max_discard_segments = 1;
+	lim->max_discard_segments = USHRT_MAX;
 	lim->max_hw_sectors = UINT_MAX;
 	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
@@ -875,7 +875,7 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
 void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 	q->queue_depth = depth;
-	wbt_set_queue_depth(q->rq_wb, depth);
+	wbt_set_queue_depth(q, depth);
 }
 EXPORT_SYMBOL(blk_set_queue_depth);
 
@@ -900,7 +900,7 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 		queue_flag_clear(QUEUE_FLAG_FUA, q);
 	spin_unlock_irq(q->queue_lock);
 
-	wbt_set_write_cache(q->rq_wb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
+	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 175c143ac5b9..7587b1c3caaf 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -17,7 +17,7 @@ struct blk_queue_stats {
 	bool enable_accounting;
 };
 
-static void blk_stat_init(struct blk_rq_stat *stat)
+void blk_rq_stat_init(struct blk_rq_stat *stat)
 {
 	stat->min = -1ULL;
 	stat->max = stat->nr_samples = stat->mean = 0;
@@ -25,7 +25,7 @@ static void blk_stat_init(struct blk_rq_stat *stat)
 }
 
 /* src is a per-cpu stat, mean isn't initialized */
-static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
+void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 {
 	if (!src->nr_samples)
 		return;
@@ -39,7 +39,7 @@ static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 	dst->nr_samples += src->nr_samples;
 }
 
-static void __blk_stat_add(struct blk_rq_stat *stat, u64 value)
+void blk_rq_stat_add(struct blk_rq_stat *stat, u64 value)
 {
 	stat->min = min(stat->min, value);
 	stat->max = max(stat->max, value);
@@ -69,7 +69,7 @@ void blk_stat_add(struct request *rq, u64 now)
 			continue;
 
 		stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
-		__blk_stat_add(stat, value);
+		blk_rq_stat_add(stat, value);
 		put_cpu_ptr(cb->cpu_stat);
 	}
 	rcu_read_unlock();
@@ -82,15 +82,15 @@ static void blk_stat_timer_fn(struct timer_list *t)
 	int cpu;
 
 	for (bucket = 0; bucket < cb->buckets; bucket++)
-		blk_stat_init(&cb->stat[bucket]);
+		blk_rq_stat_init(&cb->stat[bucket]);
 
 	for_each_online_cpu(cpu) {
 		struct blk_rq_stat *cpu_stat;
 
 		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
 		for (bucket = 0; bucket < cb->buckets; bucket++) {
-			blk_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
-			blk_stat_init(&cpu_stat[bucket]);
+			blk_rq_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
+			blk_rq_stat_init(&cpu_stat[bucket]);
 		}
 	}
 
@@ -143,7 +143,7 @@ void blk_stat_add_callback(struct request_queue *q,
 
 		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
 		for (bucket = 0; bucket < cb->buckets; bucket++)
-			blk_stat_init(&cpu_stat[bucket]);
+			blk_rq_stat_init(&cpu_stat[bucket]);
 	}
 
 	spin_lock(&q->stats->lock);
diff --git a/block/blk-stat.h b/block/blk-stat.h
index 78399cdde9c9..f4a1568e81a4 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -159,4 +159,8 @@ static inline void blk_stat_activate_msecs(struct blk_stat_callback *cb,
 	mod_timer(&cb->timer, jiffies + msecs_to_jiffies(msecs));
 }
 
+void blk_rq_stat_add(struct blk_rq_stat *, u64);
+void blk_rq_stat_sum(struct blk_rq_stat *, struct blk_rq_stat *);
+void blk_rq_stat_init(struct blk_rq_stat *);
+
 #endif
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 94987b1f69e1..bb109bb0a055 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -422,16 +422,16 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 
 static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
 {
-	if (!q->rq_wb)
+	if (!wbt_rq_qos(q))
 		return -EINVAL;
 
-	return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000));
+	return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
 }
 
 static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 				  size_t count)
 {
-	struct rq_wb *rwb;
+	struct rq_qos *rqos;
 	ssize_t ret;
 	s64 val;
 
@@ -441,23 +441,21 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 	if (val < -1)
 		return -EINVAL;
 
-	rwb = q->rq_wb;
-	if (!rwb) {
+	rqos = wbt_rq_qos(q);
+	if (!rqos) {
 		ret = wbt_init(q);
 		if (ret)
 			return ret;
 	}
 
-	rwb = q->rq_wb;
 	if (val == -1)
-		rwb->min_lat_nsec = wbt_default_latency_nsec(q);
+		val = wbt_default_latency_nsec(q);
 	else if (val >= 0)
-		rwb->min_lat_nsec = val * 1000ULL;
+		val *= 1000ULL;
 
-	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
-		rwb->enable_state = WBT_STATE_ON_MANUAL;
+	wbt_set_min_lat(q, val);
 
-	wbt_update_limits(rwb);
+	wbt_update_limits(q);
 	return count;
 }
 
@@ -804,6 +802,21 @@ static void __blk_release_queue(struct work_struct *work)
 		blk_stat_remove_callback(q, q->poll_cb);
 	blk_stat_free_callback(q->poll_cb);
 
+	if (!blk_queue_dead(q)) {
+		/*
+		 * Last reference was dropped without having called
+		 * blk_cleanup_queue().
+		 */
+		WARN_ONCE(blk_queue_init_done(q),
+			  "request queue %p has been registered but blk_cleanup_queue() has not been called for that queue\n",
+			  q);
+		blk_exit_queue(q);
+	}
+
+	WARN(blk_queue_root_blkg(q),
+	     "request queue %p is being released but it has not yet been removed from the blkcg controller\n",
+	     q);
+
 	blk_free_queue_stats(q->stats);
 
 	blk_exit_rl(q, &q->root_rl);
@@ -964,7 +977,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
-	wbt_exit(q);
+	rq_qos_exit(q);
 
 	mutex_lock(&q->sysfs_lock);
 	if (q->request_fn || (q->mq_ops && q->elevator))
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 82282e6fdcf8..a3eede00d302 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -579,8 +579,10 @@ static void blk_throtl_update_limit_valid(struct throtl_data *td)
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 
 		if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
-		    tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+		    tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) {
 			low_valid = true;
+			break;
+		}
 	}
 	rcu_read_unlock();
 
@@ -920,12 +922,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	}
 
 	/* Calc approx time to dispatch */
-	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ) / tg_iops_limit(tg, rw) + 1;
-
-	if (jiffy_wait > jiffy_elapsed)
-		jiffy_wait = jiffy_wait - jiffy_elapsed;
-	else
-		jiffy_wait = 1;
+	jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed;
 
 	if (wait)
 		*wait = jiffy_wait;
@@ -2132,12 +2129,8 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td)
 static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
 {
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	if (bio->bi_css) {
-		if (bio->bi_cg_private)
-			blkg_put(tg_to_blkg(bio->bi_cg_private));
-		bio->bi_cg_private = tg;
-		blkg_get(tg_to_blkg(tg));
-	}
+	if (bio->bi_css)
+		bio_associate_blkg(bio, tg_to_blkg(tg));
 	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
 #endif
 }
@@ -2285,6 +2278,7 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns)
 
 void blk_throtl_bio_endio(struct bio *bio)
 {
+	struct blkcg_gq *blkg;
 	struct throtl_grp *tg;
 	u64 finish_time_ns;
 	unsigned long finish_time;
@@ -2292,20 +2286,18 @@ void blk_throtl_bio_endio(struct bio *bio)
 	unsigned long lat;
 	int rw = bio_data_dir(bio);
 
-	tg = bio->bi_cg_private;
-	if (!tg)
+	blkg = bio->bi_blkg;
+	if (!blkg)
 		return;
-	bio->bi_cg_private = NULL;
+	tg = blkg_to_tg(blkg);
 
 	finish_time_ns = ktime_get_ns();
 	tg->last_finish_time = finish_time_ns >> 10;
 
 	start_time = bio_issue_time(&bio->bi_issue) >> 10;
 	finish_time = __bio_issue_time(finish_time_ns) >> 10;
-	if (!start_time || finish_time <= start_time) {
-		blkg_put(tg_to_blkg(tg));
+	if (!start_time || finish_time <= start_time)
 		return;
-	}
 
 	lat = finish_time - start_time;
 	/* this is only for bio based driver */
@@ -2334,8 +2326,6 @@ void blk_throtl_bio_endio(struct bio *bio)
 		tg->bio_cnt /= 2;
 		tg->bad_bio_cnt /= 2;
 	}
-
-	blkg_put(tg_to_blkg(tg));
 }
 #endif
 
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 4f89b28fa652..1d94a20374fc 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -25,6 +25,7 @@
 #include <linux/swap.h>
 
 #include "blk-wbt.h"
+#include "blk-rq-qos.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/wbt.h>
@@ -78,28 +79,6 @@ static inline bool rwb_enabled(struct rq_wb *rwb)
 	return rwb && rwb->wb_normal != 0;
 }
 
-/*
- * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
- * false if 'v' + 1 would be bigger than 'below'.
- */
-static bool atomic_inc_below(atomic_t *v, int below)
-{
-	int cur = atomic_read(v);
-
-	for (;;) {
-		int old;
-
-		if (cur >= below)
-			return false;
-		old = atomic_cmpxchg(v, cur, cur + 1);
-		if (old == cur)
-			break;
-		cur = old;
-	}
-
-	return true;
-}
-
 static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
 {
 	if (rwb_enabled(rwb)) {
@@ -116,7 +95,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb;
+	struct bdi_writeback *wb = &rwb->rqos.q->backing_dev_info->wb;
 
 	return time_before(jiffies, wb->dirty_sleep + HZ);
 }
@@ -144,8 +123,9 @@ static void rwb_wake_all(struct rq_wb *rwb)
 	}
 }
 
-void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
+static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	struct rq_wait *rqw;
 	int inflight, limit;
 
@@ -186,7 +166,7 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
 		int diff = limit - inflight;
 
 		if (!inflight || diff >= rwb->wb_background / 2)
-			wake_up_all(&rqw->wait);
+			wake_up(&rqw->wait);
 	}
 }
 
@@ -194,10 +174,9 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
  * Called on completion of a request. Note that it's also called when
  * a request is merged, when the request gets freed.
  */
-void wbt_done(struct rq_wb *rwb, struct request *rq)
+static void wbt_done(struct rq_qos *rqos, struct request *rq)
 {
-	if (!rwb)
-		return;
+	struct rq_wb *rwb = RQWB(rqos);
 
 	if (!wbt_is_tracked(rq)) {
 		if (rwb->sync_cookie == rq) {
@@ -209,72 +188,11 @@ void wbt_done(struct rq_wb *rwb, struct request *rq)
 			wb_timestamp(rwb, &rwb->last_comp);
 	} else {
 		WARN_ON_ONCE(rq == rwb->sync_cookie);
-		__wbt_done(rwb, wbt_flags(rq));
+		__wbt_done(rqos, wbt_flags(rq));
 	}
 	wbt_clear_state(rq);
 }
 
-/*
- * Return true, if we can't increase the depth further by scaling
- */
-static bool calc_wb_limits(struct rq_wb *rwb)
-{
-	unsigned int depth;
-	bool ret = false;
-
-	if (!rwb->min_lat_nsec) {
-		rwb->wb_max = rwb->wb_normal = rwb->wb_background = 0;
-		return false;
-	}
-
-	/*
-	 * For QD=1 devices, this is a special case. It's important for those
-	 * to have one request ready when one completes, so force a depth of
-	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
-	 * since the device can't have more than that in flight. If we're
-	 * scaling down, then keep a setting of 1/1/1.
-	 */
-	if (rwb->queue_depth == 1) {
-		if (rwb->scale_step > 0)
-			rwb->wb_max = rwb->wb_normal = 1;
-		else {
-			rwb->wb_max = rwb->wb_normal = 2;
-			ret = true;
-		}
-		rwb->wb_background = 1;
-	} else {
-		/*
-		 * scale_step == 0 is our default state. If we have suffered
-		 * latency spikes, step will be > 0, and we shrink the
-		 * allowed write depths. If step is < 0, we're only doing
-		 * writes, and we allow a temporarily higher depth to
-		 * increase performance.
-		 */
-		depth = min_t(unsigned int, RWB_DEF_DEPTH, rwb->queue_depth);
-		if (rwb->scale_step > 0)
-			depth = 1 + ((depth - 1) >> min(31, rwb->scale_step));
-		else if (rwb->scale_step < 0) {
-			unsigned int maxd = 3 * rwb->queue_depth / 4;
-
-			depth = 1 + ((depth - 1) << -rwb->scale_step);
-			if (depth > maxd) {
-				depth = maxd;
-				ret = true;
-			}
-		}
-
-		/*
-		 * Set our max/normal/bg queue depths based on how far
-		 * we have scaled down (->scale_step).
-		 */
-		rwb->wb_max = depth;
-		rwb->wb_normal = (rwb->wb_max + 1) / 2;
-		rwb->wb_background = (rwb->wb_max + 3) / 4;
-	}
-
-	return ret;
-}
-
 static inline bool stat_sample_valid(struct blk_rq_stat *stat)
 {
 	/*
@@ -307,7 +225,8 @@ enum {
 
 static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 {
-	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info;
+	struct rq_depth *rqd = &rwb->rq_depth;
 	u64 thislat;
 
 	/*
@@ -351,7 +270,7 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 		return LAT_EXCEEDED;
 	}
 
-	if (rwb->scale_step)
+	if (rqd->scale_step)
 		trace_wbt_stat(bdi, stat);
 
 	return LAT_OK;
@@ -359,58 +278,48 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 
 static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
 {
-	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info;
+	struct rq_depth *rqd = &rwb->rq_depth;
 
-	trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec,
-			rwb->wb_background, rwb->wb_normal, rwb->wb_max);
+	trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec,
+			rwb->wb_background, rwb->wb_normal, rqd->max_depth);
 }
 
-static void scale_up(struct rq_wb *rwb)
+static void calc_wb_limits(struct rq_wb *rwb)
 {
-	/*
-	 * Hit max in previous round, stop here
-	 */
-	if (rwb->scaled_max)
-		return;
+	if (rwb->min_lat_nsec == 0) {
+		rwb->wb_normal = rwb->wb_background = 0;
+	} else if (rwb->rq_depth.max_depth <= 2) {
+		rwb->wb_normal = rwb->rq_depth.max_depth;
+		rwb->wb_background = 1;
+	} else {
+		rwb->wb_normal = (rwb->rq_depth.max_depth + 1) / 2;
+		rwb->wb_background = (rwb->rq_depth.max_depth + 3) / 4;
+	}
+}
 
-	rwb->scale_step--;
+static void scale_up(struct rq_wb *rwb)
+{
+	rq_depth_scale_up(&rwb->rq_depth);
+	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
-
-	rwb->scaled_max = calc_wb_limits(rwb);
-
-	rwb_wake_all(rwb);
-
-	rwb_trace_step(rwb, "step up");
+	rwb_trace_step(rwb, "scale up");
 }
 
-/*
- * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
- * had a latency violation.
- */
 static void scale_down(struct rq_wb *rwb, bool hard_throttle)
 {
-	/*
-	 * Stop scaling down when we've hit the limit. This also prevents
-	 * ->scale_step from going to crazy values, if the device can't
-	 * keep up.
-	 */
-	if (rwb->wb_max == 1)
-		return;
-
-	if (rwb->scale_step < 0 && hard_throttle)
-		rwb->scale_step = 0;
-	else
-		rwb->scale_step++;
-
-	rwb->scaled_max = false;
-	rwb->unknown_cnt = 0;
+	rq_depth_scale_down(&rwb->rq_depth, hard_throttle);
 	calc_wb_limits(rwb);
-	rwb_trace_step(rwb, "step down");
+	rwb->unknown_cnt = 0;
+	rwb_wake_all(rwb);
+	rwb_trace_step(rwb, "scale down");
 }
 
 static void rwb_arm_timer(struct rq_wb *rwb)
 {
-	if (rwb->scale_step > 0) {
+	struct rq_depth *rqd = &rwb->rq_depth;
+
+	if (rqd->scale_step > 0) {
 		/*
 		 * We should speed this up, using some variant of a fast
 		 * integer inverse square root calculation. Since we only do
@@ -418,7 +327,7 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 		 * though.
 		 */
 		rwb->cur_win_nsec = div_u64(rwb->win_nsec << 4,
-					int_sqrt((rwb->scale_step + 1) << 8));
+					int_sqrt((rqd->scale_step + 1) << 8));
 	} else {
 		/*
 		 * For step < 0, we don't want to increase/decrease the
@@ -433,12 +342,13 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 static void wb_timer_fn(struct blk_stat_callback *cb)
 {
 	struct rq_wb *rwb = cb->data;
+	struct rq_depth *rqd = &rwb->rq_depth;
 	unsigned int inflight = wbt_inflight(rwb);
 	int status;
 
 	status = latency_exceeded(rwb, cb->stat);
 
-	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
+	trace_wbt_timer(rwb->rqos.q->backing_dev_info, status, rqd->scale_step,
 			inflight);
 
 	/*
@@ -469,9 +379,9 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
 		 * currently don't have a valid read/write sample. For that
 		 * case, slowly return to center state (step == 0).
 		 */
-		if (rwb->scale_step > 0)
+		if (rqd->scale_step > 0)
 			scale_up(rwb);
-		else if (rwb->scale_step < 0)
+		else if (rqd->scale_step < 0)
 			scale_down(rwb, false);
 		break;
 	default:
@@ -481,19 +391,50 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
 	/*
 	 * Re-arm timer, if we have IO in flight
 	 */
-	if (rwb->scale_step || inflight)
+	if (rqd->scale_step || inflight)
 		rwb_arm_timer(rwb);
 }
 
-void wbt_update_limits(struct rq_wb *rwb)
+static void __wbt_update_limits(struct rq_wb *rwb)
 {
-	rwb->scale_step = 0;
-	rwb->scaled_max = false;
+	struct rq_depth *rqd = &rwb->rq_depth;
+
+	rqd->scale_step = 0;
+	rqd->scaled_max = false;
+
+	rq_depth_calc_max_depth(rqd);
 	calc_wb_limits(rwb);
 
 	rwb_wake_all(rwb);
 }
 
+void wbt_update_limits(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return;
+	__wbt_update_limits(RQWB(rqos));
+}
+
+u64 wbt_get_min_lat(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return 0;
+	return RQWB(rqos)->min_lat_nsec;
+}
+
+void wbt_set_min_lat(struct request_queue *q, u64 val)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return;
+	RQWB(rqos)->min_lat_nsec = val;
+	RQWB(rqos)->enable_state = WBT_STATE_ON_MANUAL;
+	__wbt_update_limits(RQWB(rqos));
+}
+
+
 static bool close_io(struct rq_wb *rwb)
 {
 	const unsigned long now = jiffies;
@@ -520,7 +461,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 	 * IO for a bit.
 	 */
 	if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
-		limit = rwb->wb_max;
+		limit = rwb->rq_depth.max_depth;
 	else if ((rw & REQ_BACKGROUND) || close_io(rwb)) {
 		/*
 		 * If less than 100ms since we completed unrelated IO,
@@ -533,30 +474,6 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 	return limit;
 }
 
-static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
-			     wait_queue_entry_t *wait, unsigned long rw)
-{
-	/*
-	 * inc it here even if disabled, since we'll dec it at completion.
-	 * this only happens if the task was sleeping in __wbt_wait(),
-	 * and someone turned it off at the same time.
-	 */
-	if (!rwb_enabled(rwb)) {
-		atomic_inc(&rqw->inflight);
-		return true;
-	}
-
-	/*
-	 * If the waitqueue is already active and we are not the next
-	 * in line to be woken up, wait for our turn.
-	 */
-	if (waitqueue_active(&rqw->wait) &&
-	    rqw->wait.head.next != &wait->entry)
-		return false;
-
-	return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw));
-}
-
 /*
  * Block if we will exceed our limit, or if we are currently waiting for
  * the timer to kick off queuing again.
@@ -567,16 +484,32 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
 	__acquires(lock)
 {
 	struct rq_wait *rqw = get_rq_wait(rwb, wb_acct);
-	DEFINE_WAIT(wait);
+	DECLARE_WAITQUEUE(wait, current);
 
-	if (may_queue(rwb, rqw, &wait, rw))
+	/*
+	* inc it here even if disabled, since we'll dec it at completion.
+	* this only happens if the task was sleeping in __wbt_wait(),
+	* and someone turned it off at the same time.
+	*/
+	if (!rwb_enabled(rwb)) {
+		atomic_inc(&rqw->inflight);
 		return;
+	}
 
+	if (!waitqueue_active(&rqw->wait)
+		&& rq_wait_inc_below(rqw, get_limit(rwb, rw)))
+		return;
+
+	add_wait_queue_exclusive(&rqw->wait, &wait);
 	do {
-		prepare_to_wait_exclusive(&rqw->wait, &wait,
-						TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE);
 
-		if (may_queue(rwb, rqw, &wait, rw))
+		if (!rwb_enabled(rwb)) {
+			atomic_inc(&rqw->inflight);
+			break;
+		}
+
+		if (rq_wait_inc_below(rqw, get_limit(rwb, rw)))
 			break;
 
 		if (lock) {
@@ -587,7 +520,8 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
 			io_schedule();
 	} while (1);
 
-	finish_wait(&rqw->wait, &wait);
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&rqw->wait, &wait);
 }
 
 static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
@@ -608,43 +542,72 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
 	}
 }
 
+static enum wbt_flags bio_to_wbt_flags(struct rq_wb *rwb, struct bio *bio)
+{
+	enum wbt_flags flags = 0;
+
+	if (bio_op(bio) == REQ_OP_READ) {
+		flags = WBT_READ;
+	} else if (wbt_should_throttle(rwb, bio)) {
+		if (current_is_kswapd())
+			flags |= WBT_KSWAPD;
+		if (bio_op(bio) == REQ_OP_DISCARD)
+			flags |= WBT_DISCARD;
+		flags |= WBT_TRACKED;
+	}
+	return flags;
+}
+
+static void wbt_cleanup(struct rq_qos *rqos, struct bio *bio)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	enum wbt_flags flags = bio_to_wbt_flags(rwb, bio);
+	__wbt_done(rqos, flags);
+}
+
 /*
  * Returns true if the IO request should be accounted, false if not.
  * May sleep, if we have exceeded the writeback limits. Caller can pass
  * in an irq held spinlock, if it holds one when calling this function.
  * If we do sleep, we'll release and re-grab it.
  */
-enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
+static void wbt_wait(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock)
 {
-	enum wbt_flags ret = 0;
+	struct rq_wb *rwb = RQWB(rqos);
+	enum wbt_flags flags;
 
 	if (!rwb_enabled(rwb))
-		return 0;
+		return;
 
-	if (bio_op(bio) == REQ_OP_READ)
-		ret = WBT_READ;
+	flags = bio_to_wbt_flags(rwb, bio);
 
 	if (!wbt_should_throttle(rwb, bio)) {
-		if (ret & WBT_READ)
+		if (flags & WBT_READ)
 			wb_timestamp(rwb, &rwb->last_issue);
-		return ret;
+		return;
 	}
 
 	if (current_is_kswapd())
-		ret |= WBT_KSWAPD;
+		flags |= WBT_KSWAPD;
 	if (bio_op(bio) == REQ_OP_DISCARD)
-		ret |= WBT_DISCARD;
+		flags |= WBT_DISCARD;
 
-	__wbt_wait(rwb, ret, bio->bi_opf, lock);
+	__wbt_wait(rwb, flags, bio->bi_opf, lock);
 
 	if (!blk_stat_is_active(rwb->cb))
 		rwb_arm_timer(rwb);
+}
 
-	return ret | WBT_TRACKED;
+static void wbt_track(struct rq_qos *rqos, struct request *rq, struct bio *bio)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	rq->wbt_flags |= bio_to_wbt_flags(rwb, bio);
 }
 
-void wbt_issue(struct rq_wb *rwb, struct request *rq)
+void wbt_issue(struct rq_qos *rqos, struct request *rq)
 {
+	struct rq_wb *rwb = RQWB(rqos);
+
 	if (!rwb_enabled(rwb))
 		return;
 
@@ -661,8 +624,9 @@ void wbt_issue(struct rq_wb *rwb, struct request *rq)
 	}
 }
 
-void wbt_requeue(struct rq_wb *rwb, struct request *rq)
+void wbt_requeue(struct rq_qos *rqos, struct request *rq)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	if (!rwb_enabled(rwb))
 		return;
 	if (rq == rwb->sync_cookie) {
@@ -671,39 +635,30 @@ void wbt_requeue(struct rq_wb *rwb, struct request *rq)
 	}
 }
 
-void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
-	if (rwb) {
-		rwb->queue_depth = depth;
-		wbt_update_limits(rwb);
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (rqos) {
+		RQWB(rqos)->rq_depth.queue_depth = depth;
+		__wbt_update_limits(RQWB(rqos));
 	}
 }
 
-void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on)
+void wbt_set_write_cache(struct request_queue *q, bool write_cache_on)
 {
-	if (rwb)
-		rwb->wc = write_cache_on;
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (rqos)
+		RQWB(rqos)->wc = write_cache_on;
 }
 
 /*
- * Disable wbt, if enabled by default.
- */
-void wbt_disable_default(struct request_queue *q)
-{
-	struct rq_wb *rwb = q->rq_wb;
-
-	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT)
-		wbt_exit(q);
-}
-EXPORT_SYMBOL_GPL(wbt_disable_default);
-
-/*
  * Enable wbt if defaults are configured that way
  */
 void wbt_enable_default(struct request_queue *q)
 {
+	struct rq_qos *rqos = wbt_rq_qos(q);
 	/* Throttling already enabled? */
-	if (q->rq_wb)
+	if (rqos)
 		return;
 
 	/* Queue not registered? Maybe shutting down... */
@@ -741,6 +696,42 @@ static int wbt_data_dir(const struct request *rq)
 	return -1;
 }
 
+static void wbt_exit(struct rq_qos *rqos)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	struct request_queue *q = rqos->q;
+
+	blk_stat_remove_callback(q, rwb->cb);
+	blk_stat_free_callback(rwb->cb);
+	kfree(rwb);
+}
+
+/*
+ * Disable wbt, if enabled by default.
+ */
+void wbt_disable_default(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	struct rq_wb *rwb;
+	if (!rqos)
+		return;
+	rwb = RQWB(rqos);
+	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
+		rwb->wb_normal = 0;
+}
+EXPORT_SYMBOL_GPL(wbt_disable_default);
+
+
+static struct rq_qos_ops wbt_rqos_ops = {
+	.throttle = wbt_wait,
+	.issue = wbt_issue,
+	.track = wbt_track,
+	.requeue = wbt_requeue,
+	.done = wbt_done,
+	.cleanup = wbt_cleanup,
+	.exit = wbt_exit,
+};
+
 int wbt_init(struct request_queue *q)
 {
 	struct rq_wb *rwb;
@@ -756,39 +747,29 @@ int wbt_init(struct request_queue *q)
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < WBT_NUM_RWQ; i++) {
-		atomic_set(&rwb->rq_wait[i].inflight, 0);
-		init_waitqueue_head(&rwb->rq_wait[i].wait);
-	}
+	for (i = 0; i < WBT_NUM_RWQ; i++)
+		rq_wait_init(&rwb->rq_wait[i]);
 
+	rwb->rqos.id = RQ_QOS_WBT;
+	rwb->rqos.ops = &wbt_rqos_ops;
+	rwb->rqos.q = q;
 	rwb->last_comp = rwb->last_issue = jiffies;
-	rwb->queue = q;
 	rwb->win_nsec = RWB_WINDOW_NSEC;
 	rwb->enable_state = WBT_STATE_ON_DEFAULT;
-	wbt_update_limits(rwb);
+	rwb->wc = 1;
+	rwb->rq_depth.default_depth = RWB_DEF_DEPTH;
+	__wbt_update_limits(rwb);
 
 	/*
 	 * Assign rwb and add the stats callback.
 	 */
-	q->rq_wb = rwb;
+	rq_qos_add(q, &rwb->rqos);
 	blk_stat_add_callback(q, rwb->cb);
 
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
 
-	wbt_set_queue_depth(rwb, blk_queue_depth(q));
-	wbt_set_write_cache(rwb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
+	wbt_set_queue_depth(q, blk_queue_depth(q));
+	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 
 	return 0;
 }
-
-void wbt_exit(struct request_queue *q)
-{
-	struct rq_wb *rwb = q->rq_wb;
-
-	if (rwb) {
-		blk_stat_remove_callback(q, rwb->cb);
-		blk_stat_free_callback(rwb->cb);
-		q->rq_wb = NULL;
-		kfree(rwb);
-	}
-}
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index 300df531d0a6..f47218d5b3b2 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -9,6 +9,7 @@
 #include <linux/ktime.h>
 
 #include "blk-stat.h"
+#include "blk-rq-qos.h"
 
 enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
@@ -35,20 +36,12 @@ enum {
 	WBT_STATE_ON_MANUAL	= 2,
 };
 
-struct rq_wait {
-	wait_queue_head_t wait;
-	atomic_t inflight;
-};
-
 struct rq_wb {
 	/*
 	 * Settings that govern how we throttle
 	 */
 	unsigned int wb_background;		/* background writeback */
 	unsigned int wb_normal;			/* normal writeback */
-	unsigned int wb_max;			/* max throughput writeback */
-	int scale_step;
-	bool scaled_max;
 
 	short enable_state;			/* WBT_STATE_* */
 
@@ -67,15 +60,20 @@ struct rq_wb {
 	void *sync_cookie;
 
 	unsigned int wc;
-	unsigned int queue_depth;
 
 	unsigned long last_issue;		/* last non-throttled issue */
 	unsigned long last_comp;		/* last non-throttled comp */
 	unsigned long min_lat_nsec;
-	struct request_queue *queue;
+	struct rq_qos rqos;
 	struct rq_wait rq_wait[WBT_NUM_RWQ];
+	struct rq_depth rq_depth;
 };
 
+static inline struct rq_wb *RQWB(struct rq_qos *rqos)
+{
+	return container_of(rqos, struct rq_wb, rqos);
+}
+
 static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 {
 	unsigned int i, ret = 0;
@@ -86,26 +84,19 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 	return ret;
 }
 
-#ifdef CONFIG_BLK_WBT
 
-static inline void wbt_track(struct request *rq, enum wbt_flags flags)
-{
-	rq->wbt_flags |= flags;
-}
+#ifdef CONFIG_BLK_WBT
 
-void __wbt_done(struct rq_wb *, enum wbt_flags);
-void wbt_done(struct rq_wb *, struct request *);
-enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *);
 int wbt_init(struct request_queue *);
-void wbt_exit(struct request_queue *);
-void wbt_update_limits(struct rq_wb *);
-void wbt_requeue(struct rq_wb *, struct request *);
-void wbt_issue(struct rq_wb *, struct request *);
+void wbt_update_limits(struct request_queue *);
 void wbt_disable_default(struct request_queue *);
 void wbt_enable_default(struct request_queue *);
 
-void wbt_set_queue_depth(struct rq_wb *, unsigned int);
-void wbt_set_write_cache(struct rq_wb *, bool);
+u64 wbt_get_min_lat(struct request_queue *q);
+void wbt_set_min_lat(struct request_queue *q, u64 val);
+
+void wbt_set_queue_depth(struct request_queue *, unsigned int);
+void wbt_set_write_cache(struct request_queue *, bool);
 
 u64 wbt_default_latency_nsec(struct request_queue *);
 
@@ -114,43 +105,30 @@ u64 wbt_default_latency_nsec(struct request_queue *);
 static inline void wbt_track(struct request *rq, enum wbt_flags flags)
 {
 }
-static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
-{
-}
-static inline void wbt_done(struct rq_wb *rwb, struct request *rq)
-{
-}
-static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio,
-				      spinlock_t *lock)
-{
-	return 0;
-}
 static inline int wbt_init(struct request_queue *q)
 {
 	return -EINVAL;
 }
-static inline void wbt_exit(struct request_queue *q)
-{
-}
-static inline void wbt_update_limits(struct rq_wb *rwb)
+static inline void wbt_update_limits(struct request_queue *q)
 {
 }
-static inline void wbt_requeue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_disable_default(struct request_queue *q)
 {
 }
-static inline void wbt_issue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_enable_default(struct request_queue *q)
 {
 }
-static inline void wbt_disable_default(struct request_queue *q)
+static inline void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 }
-static inline void wbt_enable_default(struct request_queue *q)
+static inline void wbt_set_write_cache(struct request_queue *q, bool wc)
 {
 }
-static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+static inline u64 wbt_get_min_lat(struct request_queue *q)
 {
+	return 0;
 }
-static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc)
+static inline void wbt_set_min_lat(struct request_queue *q, u64 val)
 {
 }
 static inline u64 wbt_default_latency_nsec(struct request_queue *q)
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 51000914e23f..c461cf63f1f4 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -200,7 +200,7 @@ int blkdev_report_zones(struct block_device *bdev,
 		/* Get header in the first page */
 		ofst = 0;
 		if (!nr_rep) {
-			hdr = (struct blk_zone_report_hdr *) addr;
+			hdr = addr;
 			nr_rep = hdr->nr_zones;
 			ofst = sizeof(struct blk_zone_report_hdr);
 		}
diff --git a/block/blk.h b/block/blk.h
index 8d23aea96ce9..d4d67e948920 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -130,6 +130,7 @@ void blk_free_flush_queue(struct blk_flush_queue *q);
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask);
 void blk_exit_rl(struct request_queue *q, struct request_list *rl);
+void blk_exit_queue(struct request_queue *q);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
 void blk_queue_bypass_start(struct request_queue *q);
@@ -412,4 +413,10 @@ static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
 
 extern void blk_drain_queue(struct request_queue *q);
 
+#ifdef CONFIG_BLK_CGROUP_IOLATENCY
+extern int blk_iolatency_init(struct request_queue *q);
+#else
+static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
+#endif
+
 #endif /* BLK_INTERNAL_H */
diff --git a/block/bounce.c b/block/bounce.c
index fd31347b7836..bc63b3a2d18c 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -195,6 +195,73 @@ static void bounce_end_io_read_isa(struct bio *bio)
 	__bounce_end_io_read(bio, &isa_page_pool);
 }
 
+static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask,
+		struct bio_set *bs)
+{
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	struct bio *bio;
+
+	/*
+	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
+	 * bio_src->bi_io_vec to bio->bi_io_vec.
+	 *
+	 * We can't do that anymore, because:
+	 *
+	 *  - The point of cloning the biovec is to produce a bio with a biovec
+	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
+	 *
+	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
+	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
+	 *    But the clone should succeed as long as the number of biovecs we
+	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
+	 *
+	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
+	 *    that does not own the bio - reason being drivers don't use it for
+	 *    iterating over the biovec anymore, so expecting it to be kept up
+	 *    to date (i.e. for clones that share the parent biovec) is just
+	 *    asking for trouble and would force extra work on
+	 *    __bio_clone_fast() anyways.
+	 */
+
+	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
+	if (!bio)
+		return NULL;
+	bio->bi_disk		= bio_src->bi_disk;
+	bio->bi_opf		= bio_src->bi_opf;
+	bio->bi_write_hint	= bio_src->bi_write_hint;
+	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
+	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
+
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_ZEROES:
+		break;
+	case REQ_OP_WRITE_SAME:
+		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
+		break;
+	default:
+		bio_for_each_segment(bv, bio_src, iter)
+			bio->bi_io_vec[bio->bi_vcnt++] = bv;
+		break;
+	}
+
+	if (bio_integrity(bio_src)) {
+		int ret;
+
+		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
+		if (ret < 0) {
+			bio_put(bio);
+			return NULL;
+		}
+	}
+
+	bio_clone_blkcg_association(bio, bio_src);
+
+	return bio;
+}
+
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 			       mempool_t *pool)
 {
@@ -222,7 +289,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 		generic_make_request(*bio_orig);
 		*bio_orig = bio;
 	}
-	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
+	bio = bounce_clone_bio(*bio_orig, GFP_NOIO, passthrough ? NULL :
 			&bounce_bio_set);
 
 	bio_for_each_segment_all(to, bio, i) {
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 9419def8c017..f3501cdaf1a6 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -48,9 +48,8 @@ static int bsg_transport_fill_hdr(struct request *rq, struct sg_io_v4 *hdr,
 
 	job->request_len = hdr->request_len;
 	job->request = memdup_user(uptr64(hdr->request), hdr->request_len);
-	if (IS_ERR(job->request))
-		return PTR_ERR(job->request);
-	return 0;
+
+	return PTR_ERR_OR_ZERO(job->request);
 }
 
 static int bsg_transport_complete_rq(struct request *rq, struct sg_io_v4 *hdr)
diff --git a/block/bsg.c b/block/bsg.c
index 66602c489956..db588add6ba6 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -13,11 +13,9 @@
 #include <linux/init.h>
 #include <linux/file.h>
 #include <linux/blkdev.h>
-#include <linux/poll.h>
 #include <linux/cdev.h>
 #include <linux/jiffies.h>
 #include <linux/percpu.h>
-#include <linux/uio.h>
 #include <linux/idr.h>
 #include <linux/bsg.h>
 #include <linux/slab.h>
@@ -38,21 +36,10 @@
 struct bsg_device {
 	struct request_queue *queue;
 	spinlock_t lock;
-	struct list_head busy_list;
-	struct list_head done_list;
 	struct hlist_node dev_list;
 	atomic_t ref_count;
-	int queued_cmds;
-	int done_cmds;
-	wait_queue_head_t wq_done;
-	wait_queue_head_t wq_free;
 	char name[20];
 	int max_queue;
-	unsigned long flags;
-};
-
-enum {
-	BSG_F_BLOCK		= 1,
 };
 
 #define BSG_DEFAULT_CMDS	64
@@ -67,64 +54,6 @@ static struct hlist_head bsg_device_list[BSG_LIST_ARRAY_SIZE];
 static struct class *bsg_class;
 static int bsg_major;
 
-static struct kmem_cache *bsg_cmd_cachep;
-
-/*
- * our internal command type
- */
-struct bsg_command {
-	struct bsg_device *bd;
-	struct list_head list;
-	struct request *rq;
-	struct bio *bio;
-	struct bio *bidi_bio;
-	int err;
-	struct sg_io_v4 hdr;
-};
-
-static void bsg_free_command(struct bsg_command *bc)
-{
-	struct bsg_device *bd = bc->bd;
-	unsigned long flags;
-
-	kmem_cache_free(bsg_cmd_cachep, bc);
-
-	spin_lock_irqsave(&bd->lock, flags);
-	bd->queued_cmds--;
-	spin_unlock_irqrestore(&bd->lock, flags);
-
-	wake_up(&bd->wq_free);
-}
-
-static struct bsg_command *bsg_alloc_command(struct bsg_device *bd)
-{
-	struct bsg_command *bc = ERR_PTR(-EINVAL);
-
-	spin_lock_irq(&bd->lock);
-
-	if (bd->queued_cmds >= bd->max_queue)
-		goto out;
-
-	bd->queued_cmds++;
-	spin_unlock_irq(&bd->lock);
-
-	bc = kmem_cache_zalloc(bsg_cmd_cachep, GFP_KERNEL);
-	if (unlikely(!bc)) {
-		spin_lock_irq(&bd->lock);
-		bd->queued_cmds--;
-		bc = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	bc->bd = bd;
-	INIT_LIST_HEAD(&bc->list);
-	bsg_dbg(bd, "returning free cmd %p\n", bc);
-	return bc;
-out:
-	spin_unlock_irq(&bd->lock);
-	return bc;
-}
-
 static inline struct hlist_head *bsg_dev_idx_hash(int index)
 {
 	return &bsg_device_list[index & (BSG_LIST_ARRAY_SIZE - 1)];
@@ -267,8 +196,6 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode)
 	} else if (hdr->din_xfer_len) {
 		ret = blk_rq_map_user(q, rq, NULL, uptr64(hdr->din_xferp),
 				hdr->din_xfer_len, GFP_KERNEL);
-	} else {
-		ret = blk_rq_map_user(q, rq, NULL, NULL, 0, GFP_KERNEL);
 	}
 
 	if (ret)
@@ -287,101 +214,6 @@ out:
 	return ERR_PTR(ret);
 }
 
-/*
- * async completion call-back from the block layer, when scsi/ide/whatever
- * calls end_that_request_last() on a request
- */
-static void bsg_rq_end_io(struct request *rq, blk_status_t status)
-{
-	struct bsg_command *bc = rq->end_io_data;
-	struct bsg_device *bd = bc->bd;
-	unsigned long flags;
-
-	bsg_dbg(bd, "finished rq %p bc %p, bio %p\n",
-		rq, bc, bc->bio);
-
-	bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration);
-
-	spin_lock_irqsave(&bd->lock, flags);
-	list_move_tail(&bc->list, &bd->done_list);
-	bd->done_cmds++;
-	spin_unlock_irqrestore(&bd->lock, flags);
-
-	wake_up(&bd->wq_done);
-}
-
-/*
- * do final setup of a 'bc' and submit the matching 'rq' to the block
- * layer for io
- */
-static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
-			    struct bsg_command *bc, struct request *rq)
-{
-	int at_head = (0 == (bc->hdr.flags & BSG_FLAG_Q_AT_TAIL));
-
-	/*
-	 * add bc command to busy queue and submit rq for io
-	 */
-	bc->rq = rq;
-	bc->bio = rq->bio;
-	if (rq->next_rq)
-		bc->bidi_bio = rq->next_rq->bio;
-	bc->hdr.duration = jiffies;
-	spin_lock_irq(&bd->lock);
-	list_add_tail(&bc->list, &bd->busy_list);
-	spin_unlock_irq(&bd->lock);
-
-	bsg_dbg(bd, "queueing rq %p, bc %p\n", rq, bc);
-
-	rq->end_io_data = bc;
-	blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io);
-}
-
-static struct bsg_command *bsg_next_done_cmd(struct bsg_device *bd)
-{
-	struct bsg_command *bc = NULL;
-
-	spin_lock_irq(&bd->lock);
-	if (bd->done_cmds) {
-		bc = list_first_entry(&bd->done_list, struct bsg_command, list);
-		list_del(&bc->list);
-		bd->done_cmds--;
-	}
-	spin_unlock_irq(&bd->lock);
-
-	return bc;
-}
-
-/*
- * Get a finished command from the done list
- */
-static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd)
-{
-	struct bsg_command *bc;
-	int ret;
-
-	do {
-		bc = bsg_next_done_cmd(bd);
-		if (bc)
-			break;
-
-		if (!test_bit(BSG_F_BLOCK, &bd->flags)) {
-			bc = ERR_PTR(-EAGAIN);
-			break;
-		}
-
-		ret = wait_event_interruptible(bd->wq_done, bd->done_cmds);
-		if (ret) {
-			bc = ERR_PTR(-ERESTARTSYS);
-			break;
-		}
-	} while (1);
-
-	bsg_dbg(bd, "returning done %p\n", bc);
-
-	return bc;
-}
-
 static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 				    struct bio *bio, struct bio *bidi_bio)
 {
@@ -400,234 +232,6 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	return ret;
 }
 
-static bool bsg_complete(struct bsg_device *bd)
-{
-	bool ret = false;
-	bool spin;
-
-	do {
-		spin_lock_irq(&bd->lock);
-
-		BUG_ON(bd->done_cmds > bd->queued_cmds);
-
-		/*
-		 * All commands consumed.
-		 */
-		if (bd->done_cmds == bd->queued_cmds)
-			ret = true;
-
-		spin = !test_bit(BSG_F_BLOCK, &bd->flags);
-
-		spin_unlock_irq(&bd->lock);
-	} while (!ret && spin);
-
-	return ret;
-}
-
-static int bsg_complete_all_commands(struct bsg_device *bd)
-{
-	struct bsg_command *bc;
-	int ret, tret;
-
-	bsg_dbg(bd, "entered\n");
-
-	/*
-	 * wait for all commands to complete
-	 */
-	io_wait_event(bd->wq_done, bsg_complete(bd));
-
-	/*
-	 * discard done commands
-	 */
-	ret = 0;
-	do {
-		spin_lock_irq(&bd->lock);
-		if (!bd->queued_cmds) {
-			spin_unlock_irq(&bd->lock);
-			break;
-		}
-		spin_unlock_irq(&bd->lock);
-
-		bc = bsg_get_done_cmd(bd);
-		if (IS_ERR(bc))
-			break;
-
-		tret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio,
-						bc->bidi_bio);
-		if (!ret)
-			ret = tret;
-
-		bsg_free_command(bc);
-	} while (1);
-
-	return ret;
-}
-
-static int
-__bsg_read(char __user *buf, size_t count, struct bsg_device *bd,
-	   const struct iovec *iov, ssize_t *bytes_read)
-{
-	struct bsg_command *bc;
-	int nr_commands, ret;
-
-	if (count % sizeof(struct sg_io_v4))
-		return -EINVAL;
-
-	ret = 0;
-	nr_commands = count / sizeof(struct sg_io_v4);
-	while (nr_commands) {
-		bc = bsg_get_done_cmd(bd);
-		if (IS_ERR(bc)) {
-			ret = PTR_ERR(bc);
-			break;
-		}
-
-		/*
-		 * this is the only case where we need to copy data back
-		 * after completing the request. so do that here,
-		 * bsg_complete_work() cannot do that for us
-		 */
-		ret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio,
-					       bc->bidi_bio);
-
-		if (copy_to_user(buf, &bc->hdr, sizeof(bc->hdr)))
-			ret = -EFAULT;
-
-		bsg_free_command(bc);
-
-		if (ret)
-			break;
-
-		buf += sizeof(struct sg_io_v4);
-		*bytes_read += sizeof(struct sg_io_v4);
-		nr_commands--;
-	}
-
-	return ret;
-}
-
-static inline void bsg_set_block(struct bsg_device *bd, struct file *file)
-{
-	if (file->f_flags & O_NONBLOCK)
-		clear_bit(BSG_F_BLOCK, &bd->flags);
-	else
-		set_bit(BSG_F_BLOCK, &bd->flags);
-}
-
-/*
- * Check if the error is a "real" error that we should return.
- */
-static inline int err_block_err(int ret)
-{
-	if (ret && ret != -ENOSPC && ret != -ENODATA && ret != -EAGAIN)
-		return 1;
-
-	return 0;
-}
-
-static ssize_t
-bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
-{
-	struct bsg_device *bd = file->private_data;
-	int ret;
-	ssize_t bytes_read;
-
-	bsg_dbg(bd, "read %zd bytes\n", count);
-
-	bsg_set_block(bd, file);
-
-	bytes_read = 0;
-	ret = __bsg_read(buf, count, bd, NULL, &bytes_read);
-	*ppos = bytes_read;
-
-	if (!bytes_read || err_block_err(ret))
-		bytes_read = ret;
-
-	return bytes_read;
-}
-
-static int __bsg_write(struct bsg_device *bd, const char __user *buf,
-		       size_t count, ssize_t *bytes_written, fmode_t mode)
-{
-	struct bsg_command *bc;
-	struct request *rq;
-	int ret, nr_commands;
-
-	if (count % sizeof(struct sg_io_v4))
-		return -EINVAL;
-
-	nr_commands = count / sizeof(struct sg_io_v4);
-	rq = NULL;
-	bc = NULL;
-	ret = 0;
-	while (nr_commands) {
-		struct request_queue *q = bd->queue;
-
-		bc = bsg_alloc_command(bd);
-		if (IS_ERR(bc)) {
-			ret = PTR_ERR(bc);
-			bc = NULL;
-			break;
-		}
-
-		if (copy_from_user(&bc->hdr, buf, sizeof(bc->hdr))) {
-			ret = -EFAULT;
-			break;
-		}
-
-		/*
-		 * get a request, fill in the blanks, and add to request queue
-		 */
-		rq = bsg_map_hdr(bd->queue, &bc->hdr, mode);
-		if (IS_ERR(rq)) {
-			ret = PTR_ERR(rq);
-			rq = NULL;
-			break;
-		}
-
-		bsg_add_command(bd, q, bc, rq);
-		bc = NULL;
-		rq = NULL;
-		nr_commands--;
-		buf += sizeof(struct sg_io_v4);
-		*bytes_written += sizeof(struct sg_io_v4);
-	}
-
-	if (bc)
-		bsg_free_command(bc);
-
-	return ret;
-}
-
-static ssize_t
-bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
-{
-	struct bsg_device *bd = file->private_data;
-	ssize_t bytes_written;
-	int ret;
-
-	bsg_dbg(bd, "write %zd bytes\n", count);
-
-	if (unlikely(uaccess_kernel()))
-		return -EINVAL;
-
-	bsg_set_block(bd, file);
-
-	bytes_written = 0;
-	ret = __bsg_write(bd, buf, count, &bytes_written, file->f_mode);
-
-	*ppos = bytes_written;
-
-	/*
-	 * return bytes written on non-fatal errors
-	 */
-	if (!bytes_written || err_block_err(ret))
-		bytes_written = ret;
-
-	bsg_dbg(bd, "returning %zd\n", bytes_written);
-	return bytes_written;
-}
-
 static struct bsg_device *bsg_alloc_device(void)
 {
 	struct bsg_device *bd;
@@ -637,29 +241,20 @@ static struct bsg_device *bsg_alloc_device(void)
 		return NULL;
 
 	spin_lock_init(&bd->lock);
-
 	bd->max_queue = BSG_DEFAULT_CMDS;
-
-	INIT_LIST_HEAD(&bd->busy_list);
-	INIT_LIST_HEAD(&bd->done_list);
 	INIT_HLIST_NODE(&bd->dev_list);
-
-	init_waitqueue_head(&bd->wq_free);
-	init_waitqueue_head(&bd->wq_done);
 	return bd;
 }
 
 static int bsg_put_device(struct bsg_device *bd)
 {
-	int ret = 0, do_free;
 	struct request_queue *q = bd->queue;
 
 	mutex_lock(&bsg_mutex);
 
-	do_free = atomic_dec_and_test(&bd->ref_count);
-	if (!do_free) {
+	if (!atomic_dec_and_test(&bd->ref_count)) {
 		mutex_unlock(&bsg_mutex);
-		goto out;
+		return 0;
 	}
 
 	hlist_del(&bd->dev_list);
@@ -670,20 +265,9 @@ static int bsg_put_device(struct bsg_device *bd)
 	/*
 	 * close can always block
 	 */
-	set_bit(BSG_F_BLOCK, &bd->flags);
-
-	/*
-	 * correct error detection baddies here again. it's the responsibility
-	 * of the app to properly reap commands before close() if it wants
-	 * fool-proof error detection
-	 */
-	ret = bsg_complete_all_commands(bd);
-
 	kfree(bd);
-out:
-	if (do_free)
-		blk_put_queue(q);
-	return ret;
+	blk_put_queue(q);
+	return 0;
 }
 
 static struct bsg_device *bsg_add_device(struct inode *inode,
@@ -706,8 +290,6 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 
 	bd->queue = rq;
 
-	bsg_set_block(bd, file);
-
 	atomic_set(&bd->ref_count, 1);
 	hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
 
@@ -781,24 +363,6 @@ static int bsg_release(struct inode *inode, struct file *file)
 	return bsg_put_device(bd);
 }
 
-static __poll_t bsg_poll(struct file *file, poll_table *wait)
-{
-	struct bsg_device *bd = file->private_data;
-	__poll_t mask = 0;
-
-	poll_wait(file, &bd->wq_done, wait);
-	poll_wait(file, &bd->wq_free, wait);
-
-	spin_lock_irq(&bd->lock);
-	if (!list_empty(&bd->done_list))
-		mask |= EPOLLIN | EPOLLRDNORM;
-	if (bd->queued_cmds < bd->max_queue)
-		mask |= EPOLLOUT;
-	spin_unlock_irq(&bd->lock);
-
-	return mask;
-}
-
 static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct bsg_device *bd = file->private_data;
@@ -872,9 +436,6 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 }
 
 static const struct file_operations bsg_fops = {
-	.read		=	bsg_read,
-	.write		=	bsg_write,
-	.poll		=	bsg_poll,
 	.open		=	bsg_open,
 	.release	=	bsg_release,
 	.unlocked_ioctl	=	bsg_ioctl,
@@ -979,21 +540,12 @@ static int __init bsg_init(void)
 	int ret, i;
 	dev_t devid;
 
-	bsg_cmd_cachep = kmem_cache_create("bsg_cmd",
-				sizeof(struct bsg_command), 0, 0, NULL);
-	if (!bsg_cmd_cachep) {
-		printk(KERN_ERR "bsg: failed creating slab cache\n");
-		return -ENOMEM;
-	}
-
 	for (i = 0; i < BSG_LIST_ARRAY_SIZE; i++)
 		INIT_HLIST_HEAD(&bsg_device_list[i]);
 
 	bsg_class = class_create(THIS_MODULE, "bsg");
-	if (IS_ERR(bsg_class)) {
-		ret = PTR_ERR(bsg_class);
-		goto destroy_kmemcache;
-	}
+	if (IS_ERR(bsg_class))
+		return PTR_ERR(bsg_class);
 	bsg_class->devnode = bsg_devnode;
 
 	ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg");
@@ -1014,8 +566,6 @@ unregister_chrdev:
 	unregister_chrdev_region(MKDEV(bsg_major, 0), BSG_MAX_DEVS);
 destroy_bsg_class:
 	class_destroy(bsg_class);
-destroy_kmemcache:
-	kmem_cache_destroy(bsg_cmd_cachep);
 	return ret;
 }
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 82b6c27b3245..2eb87444b157 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3666,6 +3666,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct cfq_io_cq *cic)
 	switch (ioprio_class) {
 	default:
 		printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
+		/* fall through */
 	case IOPRIO_CLASS_NONE:
 		/*
 		 * no prio set, inherit CPU scheduling settings
@@ -4735,12 +4736,13 @@ USEC_SHOW_FUNCTION(cfq_target_latency_us_show, cfqd->cfq_target_latency);
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
-	unsigned int __data;						\
+	unsigned int __data, __min = (MIN), __max = (MAX);		\
+									\
 	cfq_var_store(&__data, (page));					\
-	if (__data < (MIN))						\
-		__data = (MIN);						\
-	else if (__data > (MAX))					\
-		__data = (MAX);						\
+	if (__data < __min)						\
+		__data = __min;						\
+	else if (__data > __max)					\
+		__data = __max;						\
 	if (__CONV)							\
 		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
 	else								\
@@ -4769,12 +4771,13 @@ STORE_FUNCTION(cfq_target_latency_store, &cfqd->cfq_target_latency, 1, UINT_MAX,
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
-	unsigned int __data;						\
+	unsigned int __data, __min = (MIN), __max = (MAX);		\
+									\
 	cfq_var_store(&__data, (page));					\
-	if (__data < (MIN))						\
-		__data = (MIN);						\
-	else if (__data > (MAX))					\
-		__data = (MAX);						\
+	if (__data < __min)						\
+		__data = __min;						\
+	else if (__data > __max)					\
+		__data = __max;						\
 	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
 	return count;							\
 }
diff --git a/block/genhd.c b/block/genhd.c
index f1543a45e73b..8cc719a37b32 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1333,21 +1333,28 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 		part_round_stats(gp->queue, cpu, hd);
 		part_stat_unlock();
 		part_in_flight(gp->queue, hd, inflight);
-		seq_printf(seqf, "%4d %7d %s %lu %lu %lu "
-			   "%u %lu %lu %lu %u %u %u %u\n",
+		seq_printf(seqf, "%4d %7d %s "
+			   "%lu %lu %lu %u "
+			   "%lu %lu %lu %u "
+			   "%u %u %u "
+			   "%lu %lu %lu %u\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
-			   part_stat_read(hd, ios[READ]),
-			   part_stat_read(hd, merges[READ]),
-			   part_stat_read(hd, sectors[READ]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[READ])),
-			   part_stat_read(hd, ios[WRITE]),
-			   part_stat_read(hd, merges[WRITE]),
-			   part_stat_read(hd, sectors[WRITE]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])),
+			   part_stat_read(hd, ios[STAT_READ]),
+			   part_stat_read(hd, merges[STAT_READ]),
+			   part_stat_read(hd, sectors[STAT_READ]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])),
+			   part_stat_read(hd, ios[STAT_WRITE]),
+			   part_stat_read(hd, merges[STAT_WRITE]),
+			   part_stat_read(hd, sectors[STAT_WRITE]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])),
 			   inflight[0],
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
-			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
+			   jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
+			   part_stat_read(hd, ios[STAT_DISCARD]),
+			   part_stat_read(hd, merges[STAT_DISCARD]),
+			   part_stat_read(hd, sectors[STAT_DISCARD]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD]))
 			);
 	}
 	disk_part_iter_exit(&piter);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 3dcfd4ec0e11..5a8975a1201c 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -130,19 +130,24 @@ ssize_t part_stat_show(struct device *dev,
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
-		"%8u %8u %8u"
+		"%8u %8u %8u "
+		"%8lu %8lu %8llu %8u"
 		"\n",
-		part_stat_read(p, ios[READ]),
-		part_stat_read(p, merges[READ]),
-		(unsigned long long)part_stat_read(p, sectors[READ]),
-		jiffies_to_msecs(part_stat_read(p, ticks[READ])),
-		part_stat_read(p, ios[WRITE]),
-		part_stat_read(p, merges[WRITE]),
-		(unsigned long long)part_stat_read(p, sectors[WRITE]),
-		jiffies_to_msecs(part_stat_read(p, ticks[WRITE])),
+		part_stat_read(p, ios[STAT_READ]),
+		part_stat_read(p, merges[STAT_READ]),
+		(unsigned long long)part_stat_read(p, sectors[STAT_READ]),
+		jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])),
+		part_stat_read(p, ios[STAT_WRITE]),
+		part_stat_read(p, merges[STAT_WRITE]),
+		(unsigned long long)part_stat_read(p, sectors[STAT_WRITE]),
+		jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])),
 		inflight[0],
 		jiffies_to_msecs(part_stat_read(p, io_ticks)),
-		jiffies_to_msecs(part_stat_read(p, time_in_queue)));
+		jiffies_to_msecs(part_stat_read(p, time_in_queue)),
+		part_stat_read(p, ios[STAT_DISCARD]),
+		part_stat_read(p, merges[STAT_DISCARD]),
+		(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
+		jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD])));
 }
 
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
diff --git a/block/partitions/aix.c b/block/partitions/aix.c
index 007f95eea0e1..903f3ed175d0 100644
--- a/block/partitions/aix.c
+++ b/block/partitions/aix.c
@@ -178,7 +178,7 @@ int aix_partition(struct parsed_partitions *state)
 	u32 vgda_sector = 0;
 	u32 vgda_len = 0;
 	int numlvs = 0;
-	struct pvd *pvd;
+	struct pvd *pvd = NULL;
 	struct lv_info {
 		unsigned short pps_per_lv;
 		unsigned short pps_found;
@@ -232,10 +232,11 @@ int aix_partition(struct parsed_partitions *state)
 				if (lvip[i].pps_per_lv)
 					foundlvs += 1;
 			}
+			/* pvd loops depend on n[].name and lvip[].pps_per_lv */
+			pvd = alloc_pvd(state, vgda_sector + 17);
 		}
 		put_dev_sector(sect);
 	}
-	pvd = alloc_pvd(state, vgda_sector + 17);
 	if (pvd) {
 		int numpps = be16_to_cpu(pvd->pp_count);
 		int psn_part1 = be32_to_cpu(pvd->psn_part1);
@@ -282,10 +283,14 @@ int aix_partition(struct parsed_partitions *state)
 				next_lp_ix += 1;
 		}
 		for (i = 0; i < state->limit; i += 1)
-			if (lvip[i].pps_found && !lvip[i].lv_is_contiguous)
+			if (lvip[i].pps_found && !lvip[i].lv_is_contiguous) {
+				char tmp[sizeof(n[i].name) + 1]; // null char
+
+				snprintf(tmp, sizeof(tmp), "%s", n[i].name);
 				pr_warn("partition %s (%u pp's found) is "
 					"not contiguous\n",
-					n[i].name, lvip[i].pps_found);
+					tmp, lvip[i].pps_found);
+			}
 		kfree(pvd);
 	}
 	kfree(n);
diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c
index 0417937dfe99..16766f267559 100644
--- a/block/partitions/ldm.c
+++ b/block/partitions/ldm.c
@@ -830,7 +830,6 @@ static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb)
 {
 	char buf[64];
 	int r_objid, r_name, r_id1, r_id2, len;
-	struct vblk_dgrp *dgrp;
 
 	BUG_ON (!buffer || !vb);
 
@@ -853,8 +852,6 @@ static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb)
 	if (len != get_unaligned_be32(buffer + 0x14))
 		return false;
 
-	dgrp = &vb->vblk.dgrp;
-
 	ldm_get_vstr (buffer + 0x18 + r_objid, buf, sizeof (buf));
 	return true;
 }
diff --git a/block/t10-pi.c b/block/t10-pi.c
index a98db384048f..62aed77d0bb9 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -184,3 +184,113 @@ const struct blk_integrity_profile t10_pi_type3_ip = {
 	.verify_fn		= t10_pi_type3_verify_ip,
 };
 EXPORT_SYMBOL(t10_pi_type3_ip);
+
+/**
+ * t10_pi_prepare - prepare PI prior submitting request to device
+ * @rq:              request with PI that should be prepared
+ * @protection_type: PI type (Type 1/Type 2/Type 3)
+ *
+ * For Type 1/Type 2, the virtual start sector is the one that was
+ * originally submitted by the block layer for the ref_tag usage. Due to
+ * partitioning, MD/DM cloning, etc. the actual physical start sector is
+ * likely to be different. Remap protection information to match the
+ * physical LBA.
+ *
+ * Type 3 does not have a reference tag so no remapping is required.
+ */
+void t10_pi_prepare(struct request *rq, u8 protection_type)
+{
+	const int tuple_sz = rq->q->integrity.tuple_size;
+	u32 ref_tag = t10_pi_ref_tag(rq);
+	struct bio *bio;
+
+	if (protection_type == T10_PI_TYPE3_PROTECTION)
+		return;
+
+	__rq_for_each_bio(bio, rq) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
+		u32 virt = bip_get_seed(bip) & 0xffffffff;
+		struct bio_vec iv;
+		struct bvec_iter iter;
+
+		/* Already remapped? */
+		if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
+			break;
+
+		bip_for_each_vec(iv, bip, iter) {
+			void *p, *pmap;
+			unsigned int j;
+
+			pmap = kmap_atomic(iv.bv_page);
+			p = pmap + iv.bv_offset;
+			for (j = 0; j < iv.bv_len; j += tuple_sz) {
+				struct t10_pi_tuple *pi = p;
+
+				if (be32_to_cpu(pi->ref_tag) == virt)
+					pi->ref_tag = cpu_to_be32(ref_tag);
+				virt++;
+				ref_tag++;
+				p += tuple_sz;
+			}
+
+			kunmap_atomic(pmap);
+		}
+
+		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
+	}
+}
+EXPORT_SYMBOL(t10_pi_prepare);
+
+/**
+ * t10_pi_complete - prepare PI prior returning request to the block layer
+ * @rq:              request with PI that should be prepared
+ * @protection_type: PI type (Type 1/Type 2/Type 3)
+ * @intervals:       total elements to prepare
+ *
+ * For Type 1/Type 2, the virtual start sector is the one that was
+ * originally submitted by the block layer for the ref_tag usage. Due to
+ * partitioning, MD/DM cloning, etc. the actual physical start sector is
+ * likely to be different. Since the physical start sector was submitted
+ * to the device, we should remap it back to virtual values expected by the
+ * block layer.
+ *
+ * Type 3 does not have a reference tag so no remapping is required.
+ */
+void t10_pi_complete(struct request *rq, u8 protection_type,
+		     unsigned int intervals)
+{
+	const int tuple_sz = rq->q->integrity.tuple_size;
+	u32 ref_tag = t10_pi_ref_tag(rq);
+	struct bio *bio;
+
+	if (protection_type == T10_PI_TYPE3_PROTECTION)
+		return;
+
+	__rq_for_each_bio(bio, rq) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
+		u32 virt = bip_get_seed(bip) & 0xffffffff;
+		struct bio_vec iv;
+		struct bvec_iter iter;
+
+		bip_for_each_vec(iv, bip, iter) {
+			void *p, *pmap;
+			unsigned int j;
+
+			pmap = kmap_atomic(iv.bv_page);
+			p = pmap + iv.bv_offset;
+			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
+				struct t10_pi_tuple *pi = p;
+
+				if (be32_to_cpu(pi->ref_tag) == ref_tag)
+					pi->ref_tag = cpu_to_be32(virt);
+				virt++;
+				ref_tag++;
+				intervals--;
+				p += tuple_sz;
+			}
+
+			kunmap_atomic(pmap);
+		}
+	}
+}
+EXPORT_SYMBOL(t10_pi_complete);
diff --git a/certs/blacklist.h b/certs/blacklist.h
index 150d82da8e99..1efd6fa0dc60 100644
--- a/certs/blacklist.h
+++ b/certs/blacklist.h
@@ -1,3 +1,3 @@
 #include <linux/kernel.h>
 
-extern const char __initdata *const blacklist_hashes[];
+extern const char __initconst *const blacklist_hashes[];
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 49fa8582138b..c166f424871c 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1060,12 +1060,19 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err)
 }
 EXPORT_SYMBOL_GPL(af_alg_async_cb);
 
-__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
+/**
+ * af_alg_poll - poll system call handler
+ */
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
+			 poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct af_alg_ctx *ctx = ask->private;
-	__poll_t mask = 0;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	if (!ctx->more || ctx->used)
 		mask |= EPOLLIN | EPOLLRDNORM;
@@ -1075,7 +1082,7 @@ __poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
 
 	return mask;
 }
-EXPORT_SYMBOL_GPL(af_alg_poll_mask);
+EXPORT_SYMBOL_GPL(af_alg_poll);
 
 /**
  * af_alg_alloc_areq - allocate struct af_alg_async_req
@@ -1148,8 +1155,10 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
 
 		/* make one iovec available as scatterlist */
 		err = af_alg_make_sg(&rsgl->sgl, &msg->msg_iter, seglen);
-		if (err < 0)
+		if (err < 0) {
+			rsgl->sg_num_bytes = 0;
 			return err;
+		}
 
 		/* chain the new scatterlist with previous one */
 		if (areq->last_rsgl)
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 825524f27438..c40a8c7ee8ae 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -375,7 +375,7 @@ static struct proto_ops algif_aead_ops = {
 	.sendmsg	=	aead_sendmsg,
 	.sendpage	=	af_alg_sendpage,
 	.recvmsg	=	aead_recvmsg,
-	.poll_mask	=	af_alg_poll_mask,
+	.poll		=	af_alg_poll,
 };
 
 static int aead_check_key(struct socket *sock)
@@ -471,7 +471,7 @@ static struct proto_ops algif_aead_ops_nokey = {
 	.sendmsg	=	aead_sendmsg_nokey,
 	.sendpage	=	aead_sendpage_nokey,
 	.recvmsg	=	aead_recvmsg_nokey,
-	.poll_mask	=	af_alg_poll_mask,
+	.poll		=	af_alg_poll,
 };
 
 static void *aead_bind(const char *name, u32 type, u32 mask)
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 4c04eb9888ad..cfdaab2b7d76 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -206,7 +206,7 @@ static struct proto_ops algif_skcipher_ops = {
 	.sendmsg	=	skcipher_sendmsg,
 	.sendpage	=	af_alg_sendpage,
 	.recvmsg	=	skcipher_recvmsg,
-	.poll_mask	=	af_alg_poll_mask,
+	.poll		=	af_alg_poll,
 };
 
 static int skcipher_check_key(struct socket *sock)
@@ -302,7 +302,7 @@ static struct proto_ops algif_skcipher_ops_nokey = {
 	.sendmsg	=	skcipher_sendmsg_nokey,
 	.sendpage	=	skcipher_sendpage_nokey,
 	.recvmsg	=	skcipher_recvmsg_nokey,
-	.poll_mask	=	af_alg_poll_mask,
+	.poll		=	af_alg_poll,
 };
 
 static void *skcipher_bind(const char *name, u32 type, u32 mask)
diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index 7d81e6bb461a..b6cabac4b62b 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -249,6 +249,15 @@ int x509_note_signature(void *context, size_t hdrlen,
 		return -EINVAL;
 	}
 
+	if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0) {
+		/* Discard the BIT STRING metadata */
+		if (vlen < 1 || *(const u8 *)value != 0)
+			return -EBADMSG;
+
+		value++;
+		vlen--;
+	}
+
 	ctx->cert->raw_sig = value;
 	ctx->cert->raw_sig_size = vlen;
 	return 0;
diff --git a/drivers/Makefile b/drivers/Makefile
index 24cd47014657..a6abd7a856c6 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -76,7 +76,7 @@ obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= macintosh/
 obj-$(CONFIG_IDE)		+= ide/
-obj-$(CONFIG_SCSI)		+= scsi/
+obj-y				+= scsi/
 obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index b533eeb6139d..4a46344bf0e3 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -5,11 +5,10 @@
 
 menuconfig ACPI
 	bool "ACPI (Advanced Configuration and Power Interface) Support"
-	depends on !IA64_HP_SIM
-	depends on IA64 || X86 || ARM64
+	depends on ARCH_SUPPORTS_ACPI
 	depends on PCI
 	select PNP
-	default y if (IA64 || X86)
+	default y if X86
 	help
 	  Advanced Configuration and Power Interface (ACPI) support for 
 	  Linux requires an ACPI-compliant platform (hardware/firmware),
@@ -41,6 +40,9 @@ menuconfig ACPI
 	  <http://www.acpi.info>
 	  <http://www.uefi.org/acpi/specs>
 
+config ARCH_SUPPORTS_ACPI
+	bool
+
 if ACPI
 
 config ACPI_LEGACY_TABLES_LOOKUP
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index f8fecfec5df9..9706613eecf9 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -879,6 +879,7 @@ static void acpi_lpss_dismiss(struct device *dev)
 #define LPSS_GPIODEF0_DMA_LLP		BIT(13)
 
 static DEFINE_MUTEX(lpss_iosf_mutex);
+static bool lpss_iosf_d3_entered;
 
 static void lpss_iosf_enter_d3_state(void)
 {
@@ -921,6 +922,9 @@ static void lpss_iosf_enter_d3_state(void)
 
 	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE,
 			LPSS_IOSF_GPIODEF0, value1, mask1);
+
+	lpss_iosf_d3_entered = true;
+
 exit:
 	mutex_unlock(&lpss_iosf_mutex);
 }
@@ -935,6 +939,11 @@ static void lpss_iosf_exit_d3_state(void)
 
 	mutex_lock(&lpss_iosf_mutex);
 
+	if (!lpss_iosf_d3_entered)
+		goto exit;
+
+	lpss_iosf_d3_entered = false;
+
 	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE,
 			LPSS_IOSF_GPIODEF0, value1, mask1);
 
@@ -944,13 +953,13 @@ static void lpss_iosf_exit_d3_state(void)
 	iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO1, MBI_CFG_WRITE,
 			LPSS_IOSF_PMCSR, value2, mask2);
 
+exit:
 	mutex_unlock(&lpss_iosf_mutex);
 }
 
-static int acpi_lpss_suspend(struct device *dev, bool runtime)
+static int acpi_lpss_suspend(struct device *dev, bool wakeup)
 {
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
-	bool wakeup = runtime || device_may_wakeup(dev);
 	int ret;
 
 	if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
@@ -963,14 +972,14 @@ static int acpi_lpss_suspend(struct device *dev, bool runtime)
 	 * wrong status for devices being about to be powered off. See
 	 * lpss_iosf_enter_d3_state() for further information.
 	 */
-	if ((runtime || !pm_suspend_via_firmware()) &&
+	if (acpi_target_system_state() == ACPI_STATE_S0 &&
 	    lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
 		lpss_iosf_enter_d3_state();
 
 	return ret;
 }
 
-static int acpi_lpss_resume(struct device *dev, bool runtime)
+static int acpi_lpss_resume(struct device *dev)
 {
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
 	int ret;
@@ -979,8 +988,7 @@ static int acpi_lpss_resume(struct device *dev, bool runtime)
 	 * This call is kept first to be in symmetry with
 	 * acpi_lpss_runtime_suspend() one.
 	 */
-	if ((runtime || !pm_resume_via_firmware()) &&
-	    lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
+	if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
 		lpss_iosf_exit_d3_state();
 
 	ret = acpi_dev_resume(dev);
@@ -1004,12 +1012,12 @@ static int acpi_lpss_suspend_late(struct device *dev)
 		return 0;
 
 	ret = pm_generic_suspend_late(dev);
-	return ret ? ret : acpi_lpss_suspend(dev, false);
+	return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev));
 }
 
 static int acpi_lpss_resume_early(struct device *dev)
 {
-	int ret = acpi_lpss_resume(dev, false);
+	int ret = acpi_lpss_resume(dev);
 
 	return ret ? ret : pm_generic_resume_early(dev);
 }
@@ -1024,7 +1032,7 @@ static int acpi_lpss_runtime_suspend(struct device *dev)
 
 static int acpi_lpss_runtime_resume(struct device *dev)
 {
-	int ret = acpi_lpss_resume(dev, true);
+	int ret = acpi_lpss_resume(dev);
 
 	return ret ? ret : pm_generic_runtime_resume(dev);
 }
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 51c386bf230d..c5367bf5487f 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -165,7 +165,6 @@ struct acpi_namespace_node {
 #define ANOBJ_EVALUATED                 0x20	/* Set on first evaluation of node */
 #define ANOBJ_ALLOCATED_BUFFER          0x40	/* Method AML buffer is dynamic (install_method) */
 
-#define IMPLICIT_EXTERNAL               0x02	/* iASL only: This object created implicitly via External */
 #define ANOBJ_IS_EXTERNAL               0x08	/* iASL only: This object created via External() */
 #define ANOBJ_METHOD_NO_RETVAL          0x10	/* iASL only: Method has no return value */
 #define ANOBJ_METHOD_SOME_NO_RETVAL     0x20	/* iASL only: Method has at least one return value */
diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c
index fc0c2e2328cd..fe9d46d81750 100644
--- a/drivers/acpi/acpica/hwsleep.c
+++ b/drivers/acpi/acpica/hwsleep.c
@@ -51,16 +51,23 @@ acpi_status acpi_hw_legacy_sleep(u8 sleep_state)
 		return_ACPI_STATUS(status);
 	}
 
-	/*
-	 * 1) Disable all GPEs
-	 * 2) Enable all wakeup GPEs
-	 */
+	/* Disable all GPEs */
 	status = acpi_hw_disable_all_gpes();
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
 	}
+	/*
+	 * If the target sleep state is S5, clear all GPEs and fixed events too
+	 */
+	if (sleep_state == ACPI_STATE_S5) {
+		status = acpi_hw_clear_acpi_status();
+		if (ACPI_FAILURE(status)) {
+			return_ACPI_STATUS(status);
+		}
+	}
 	acpi_gbl_system_awake_and_running = FALSE;
 
+	 /* Enable all wakeup GPEs */
 	status = acpi_hw_enable_all_wakeup_gpes();
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 220a718fbce9..83a593e2155d 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -613,13 +613,6 @@ acpi_ns_lookup(union acpi_generic_state *scope_info,
 		/* Special handling for the last segment (num_segments == 0) */
 
 		else {
-#ifdef ACPI_ASL_COMPILER
-			if (!acpi_gbl_disasm_flag
-			    && (this_node->flags & ANOBJ_IS_EXTERNAL)) {
-				this_node->flags &= ~IMPLICIT_EXTERNAL;
-			}
-#endif
-
 			/*
 			 * Sanity typecheck of the target object:
 			 *
diff --git a/drivers/acpi/acpica/nssearch.c b/drivers/acpi/acpica/nssearch.c
index e9c9a63bb6a4..f594ab75a5fe 100644
--- a/drivers/acpi/acpica/nssearch.c
+++ b/drivers/acpi/acpica/nssearch.c
@@ -381,7 +381,6 @@ acpi_ns_search_and_enter(u32 target_name,
 	if (flags & ACPI_NS_EXTERNAL ||
 	    (walk_state && walk_state->opcode == AML_SCOPE_OP)) {
 		new_node->flags |= ANOBJ_IS_EXTERNAL;
-		new_node->flags |= IMPLICIT_EXTERNAL;
 	}
 #endif
 
diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c
index bc5f05906bd1..44f35ab3347d 100644
--- a/drivers/acpi/acpica/psloop.c
+++ b/drivers/acpi/acpica/psloop.c
@@ -497,6 +497,18 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state)
 			status =
 			    acpi_ps_create_op(walk_state, aml_op_start, &op);
 			if (ACPI_FAILURE(status)) {
+				/*
+				 * ACPI_PARSE_MODULE_LEVEL means that we are loading a table by
+				 * executing it as a control method. However, if we encounter
+				 * an error while loading the table, we need to keep trying to
+				 * load the table rather than aborting the table load. Set the
+				 * status to AE_OK to proceed with the table load.
+				 */
+				if ((walk_state->
+				     parse_flags & ACPI_PARSE_MODULE_LEVEL)
+				    && status == AE_ALREADY_EXISTS) {
+					status = AE_OK;
+				}
 				if (status == AE_CTRL_PARSE_CONTINUE) {
 					continue;
 				}
@@ -694,6 +706,25 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state)
 			    acpi_ps_next_parse_state(walk_state, op, status);
 			if (status == AE_CTRL_PENDING) {
 				status = AE_OK;
+			} else
+			    if ((walk_state->
+				 parse_flags & ACPI_PARSE_MODULE_LEVEL)
+				&& status != AE_CTRL_TRANSFER
+				&& ACPI_FAILURE(status)) {
+				/*
+				 * ACPI_PARSE_MODULE_LEVEL flag means that we are currently
+				 * loading a table by executing it as a control method.
+				 * However, if we encounter an error while loading the table,
+				 * we need to keep trying to load the table rather than
+				 * aborting the table load (setting the status to AE_OK
+				 * continues the table load). If we get a failure at this
+				 * point, it means that the dispatcher got an error while
+				 * processing Op (most likely an AML operand error) or a
+				 * control method was called from module level and the
+				 * dispatcher returned AE_CTRL_TRANSFER. In the latter case,
+				 * leave the status alone, there's nothing wrong with it.
+				 */
+				status = AE_OK;
 			}
 		}
 
diff --git a/drivers/acpi/acpica/uterror.c b/drivers/acpi/acpica/uterror.c
index 5a64ddaed8a3..e47430272692 100644
--- a/drivers/acpi/acpica/uterror.c
+++ b/drivers/acpi/acpica/uterror.c
@@ -182,19 +182,19 @@ acpi_ut_prefixed_namespace_error(const char *module_name,
 	switch (lookup_status) {
 	case AE_ALREADY_EXISTS:
 
-		acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR);
+		acpi_os_printf(ACPI_MSG_BIOS_ERROR);
 		message = "Failure creating";
 		break;
 
 	case AE_NOT_FOUND:
 
-		acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR);
+		acpi_os_printf(ACPI_MSG_BIOS_ERROR);
 		message = "Could not resolve";
 		break;
 
 	default:
 
-		acpi_os_printf("\n" ACPI_MSG_ERROR);
+		acpi_os_printf(ACPI_MSG_ERROR);
 		message = "Failure resolving";
 		break;
 	}
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 7a3a541046ed..08f26db2da7e 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -947,6 +947,24 @@ static int nc_dma_get_range(struct device *dev, u64 *size)
 	return 0;
 }
 
+static int rc_dma_get_range(struct device *dev, u64 *size)
+{
+	struct acpi_iort_node *node;
+	struct acpi_iort_root_complex *rc;
+
+	node = iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX,
+			      iort_match_node_callback, dev);
+	if (!node || node->revision < 1)
+		return -ENODEV;
+
+	rc = (struct acpi_iort_root_complex *)node->node_data;
+
+	*size = rc->memory_address_limit >= 64 ? U64_MAX :
+			1ULL<<rc->memory_address_limit;
+
+	return 0;
+}
+
 /**
  * iort_dma_setup() - Set-up device DMA parameters.
  *
@@ -960,25 +978,28 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	int ret, msb;
 
 	/*
-	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to
-	 * setup the correct supported mask.
+	 * If @dev is expected to be DMA-capable then the bus code that created
+	 * it should have initialised its dma_mask pointer by this point. For
+	 * now, we'll continue the legacy behaviour of coercing it to the
+	 * coherent mask if not, but we'll no longer do so quietly.
 	 */
-	if (!dev->coherent_dma_mask)
-		dev->coherent_dma_mask = DMA_BIT_MASK(32);
-
-	/*
-	 * Set it to coherent_dma_mask by default if the architecture
-	 * code has not set it.
-	 */
-	if (!dev->dma_mask)
+	if (!dev->dma_mask) {
+		dev_warn(dev, "DMA mask not set\n");
 		dev->dma_mask = &dev->coherent_dma_mask;
+	}
 
-	size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	if (dev->coherent_dma_mask)
+		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	else
+		size = 1ULL << 32;
 
-	if (dev_is_pci(dev))
+	if (dev_is_pci(dev)) {
 		ret = acpi_dma_get_range(dev, &dmaaddr, &offset, &size);
-	else
+		if (ret == -ENODEV)
+			ret = rc_dma_get_range(dev, &size);
+	} else {
 		ret = nc_dma_get_range(dev, &size);
+	}
 
 	if (!ret) {
 		msb = fls64(dmaaddr + size - 1);
@@ -993,6 +1014,7 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 		 * Limit coherent and dma mask based on size
 		 * retrieved from firmware.
 		 */
+		dev->bus_dma_mask = mask;
 		dev->coherent_dma_mask = mask;
 		*dev->dma_mask = mask;
 	}
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index b0113a5802a3..cb97b6105f52 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -23,18 +23,18 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/async.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/jiffies.h>
-#include <linux/async.h>
-#include <linux/dmi.h>
-#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/types.h>
+
 #include <asm/unaligned.h>
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
@@ -364,6 +364,20 @@ static enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
+static enum power_supply_property energy_battery_full_cap_broken_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_POWER_NOW,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_MODEL_NAME,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+	POWER_SUPPLY_PROP_SERIAL_NUMBER,
+};
+
 /* --------------------------------------------------------------------------
                                Battery Management
    -------------------------------------------------------------------------- */
@@ -577,8 +591,7 @@ static int acpi_battery_get_state(struct acpi_battery *battery)
 		battery->rate_now != ACPI_BATTERY_VALUE_UNKNOWN &&
 		(s16)(battery->rate_now) < 0) {
 		battery->rate_now = abs((s16)battery->rate_now);
-		printk_once(KERN_WARNING FW_BUG
-			    "battery: (dis)charge rate invalid.\n");
+		pr_warn_once(FW_BUG "battery: (dis)charge rate invalid.\n");
 	}
 
 	if (test_bit(ACPI_BATTERY_QUIRK_PERCENTAGE_CAPACITY, &battery->flags)
@@ -717,10 +730,11 @@ void battery_hook_register(struct acpi_battery_hook *hook)
 			 */
 			pr_err("extension failed to load: %s", hook->name);
 			__battery_hook_unregister(hook, 0);
-			return;
+			goto end;
 		}
 	}
 	pr_info("new extension: %s\n", hook->name);
+end:
 	mutex_unlock(&hook_mutex);
 }
 EXPORT_SYMBOL_GPL(battery_hook_register);
@@ -732,7 +746,7 @@ EXPORT_SYMBOL_GPL(battery_hook_register);
 */
 static void battery_hook_add_battery(struct acpi_battery *battery)
 {
-	struct acpi_battery_hook *hook_node;
+	struct acpi_battery_hook *hook_node, *tmp;
 
 	mutex_lock(&hook_mutex);
 	INIT_LIST_HEAD(&battery->list);
@@ -744,15 +758,15 @@ static void battery_hook_add_battery(struct acpi_battery *battery)
 	 * when a battery gets hotplugged or initialized
 	 * during the battery module initialization.
 	 */
-	list_for_each_entry(hook_node, &battery_hook_list, list) {
+	list_for_each_entry_safe(hook_node, tmp, &battery_hook_list, list) {
 		if (hook_node->add_battery(battery->bat)) {
 			/*
 			 * The notification of the extensions has failed, to
 			 * prevent further errors we will unload the extension.
 			 */
-			__battery_hook_unregister(hook_node, 0);
 			pr_err("error in extension, unloading: %s",
 					hook_node->name);
+			__battery_hook_unregister(hook_node, 0);
 		}
 	}
 	mutex_unlock(&hook_mutex);
@@ -798,6 +812,11 @@ static int sysfs_add_battery(struct acpi_battery *battery)
 		battery->bat_desc.properties = charge_battery_props;
 		battery->bat_desc.num_properties =
 			ARRAY_SIZE(charge_battery_props);
+	} else if (battery->full_charge_capacity == 0) {
+		battery->bat_desc.properties =
+			energy_battery_full_cap_broken_props;
+		battery->bat_desc.num_properties =
+			ARRAY_SIZE(energy_battery_full_cap_broken_props);
 	} else {
 		battery->bat_desc.properties = energy_battery_props;
 		battery->bat_desc.num_properties =
@@ -917,10 +936,11 @@ static void acpi_battery_quirks(struct acpi_battery *battery)
 
 static int acpi_battery_update(struct acpi_battery *battery, bool resume)
 {
-	int result, old_present = acpi_battery_present(battery);
-	result = acpi_battery_get_status(battery);
+	int result = acpi_battery_get_status(battery);
+
 	if (result)
 		return result;
+
 	if (!acpi_battery_present(battery)) {
 		sysfs_remove_battery(battery);
 		battery->update_time = 0;
@@ -930,8 +950,7 @@ static int acpi_battery_update(struct acpi_battery *battery, bool resume)
 	if (resume)
 		return 0;
 
-	if (!battery->update_time ||
-	    old_present != acpi_battery_present(battery)) {
+	if (!battery->update_time) {
 		result = acpi_battery_get_info(battery);
 		if (result)
 			return result;
@@ -1020,7 +1039,7 @@ static int acpi_battery_info_proc_show(struct seq_file *seq, void *offset)
 			   acpi_battery_units(battery));
 
 	seq_printf(seq, "battery technology:      %srechargeable\n",
-		   (!battery->technology)?"non-":"");
+		   battery->technology ? "" : "non-");
 
 	if (battery->design_voltage == ACPI_BATTERY_VALUE_UNKNOWN)
 		seq_printf(seq, "design voltage:          unknown\n");
@@ -1111,11 +1130,12 @@ static int acpi_battery_alarm_proc_show(struct seq_file *seq, void *offset)
 		goto end;
 	}
 	seq_printf(seq, "alarm:                   ");
-	if (!battery->alarm)
-		seq_printf(seq, "unsupported\n");
-	else
+	if (battery->alarm) {
 		seq_printf(seq, "%u %sh\n", battery->alarm,
 				acpi_battery_units(battery));
+	} else {
+		seq_printf(seq, "unsupported\n");
+	}
       end:
 	if (result)
 		seq_printf(seq, "ERROR: Unable to read battery alarm\n");
@@ -1148,9 +1168,9 @@ static ssize_t acpi_battery_write_alarm(struct file *file,
 	}
 	result = acpi_battery_set_alarm(battery);
       end:
-	if (!result)
-		return count;
-	return result;
+	if (result)
+		return result;
+	return count;
 }
 
 static int acpi_battery_alarm_proc_open(struct inode *inode, struct file *file)
@@ -1169,8 +1189,7 @@ static const struct file_operations acpi_battery_alarm_fops = {
 
 static int acpi_battery_add_fs(struct acpi_device *device)
 {
-	printk(KERN_WARNING PREFIX "Deprecated procfs I/F for battery is loaded,"
-			" please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
+	pr_warning(PREFIX "Deprecated procfs I/F for battery is loaded, please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
 	if (!acpi_device_dir(device)) {
 		acpi_device_dir(device) = proc_mkdir(acpi_device_bid(device),
 						     acpi_battery_dir);
@@ -1246,7 +1265,9 @@ static int battery_notify(struct notifier_block *nb,
 		if (!acpi_battery_present(battery))
 			return 0;
 
-		if (!battery->bat) {
+		if (battery->bat) {
+			acpi_battery_refresh(battery);
+		} else {
 			result = acpi_battery_get_info(battery);
 			if (result)
 				return result;
@@ -1254,8 +1275,7 @@ static int battery_notify(struct notifier_block *nb,
 			result = sysfs_add_battery(battery);
 			if (result)
 				return result;
-		} else
-			acpi_battery_refresh(battery);
+		}
 
 		acpi_battery_init_alarm(battery);
 		acpi_battery_get_state(battery);
@@ -1397,7 +1417,7 @@ static int acpi_battery_add(struct acpi_device *device)
 	}
 #endif
 
-	printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n",
+	pr_info(PREFIX "%s Slot [%s] (battery %s)\n",
 		ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device),
 		device->status.battery_present ? "present" : "absent");
 
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 84b4a62018eb..292088fcc624 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -66,37 +66,10 @@ static int set_copy_dsdt(const struct dmi_system_id *id)
 	return 0;
 }
 #endif
-static int set_gbl_term_list(const struct dmi_system_id *id)
-{
-	acpi_gbl_execute_tables_as_methods = 1;
-	return 0;
-}
 
-static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
-	/*
-	 * Touchpad on Dell XPS 9570/Precision M5530 doesn't work under I2C
-	 * mode.
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=198515
-	 */
-	{
-		.callback = set_gbl_term_list,
-		.ident = "Dell Precision M5530",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Precision M5530"),
-		},
-	},
-	{
-		.callback = set_gbl_term_list,
-		.ident = "Dell XPS 15 9570",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9570"),
-		},
-	},
+static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
 	/*
 	 * Invoke DSDT corruption work-around on all Toshiba Satellite.
-	 * DSDT will be copied to memory.
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=14679
 	 */
 	{
@@ -110,7 +83,7 @@ static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
 	{}
 };
 #else
-static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
+static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
 	{}
 };
 #endif
@@ -962,7 +935,7 @@ static int acpi_device_probe(struct device *dev)
 	return 0;
 }
 
-static int acpi_device_remove(struct device * dev)
+static int acpi_device_remove(struct device *dev)
 {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
 	struct acpi_driver *acpi_drv = acpi_dev->driver;
@@ -1060,8 +1033,11 @@ void __init acpi_early_init(void)
 
 	acpi_permanent_mmap = true;
 
-	/* Check machine-specific quirks */
-	dmi_check_system(acpi_quirks_dmi_table);
+	/*
+	 * If the machine falls into the DMI check table,
+	 * DSDT will be copied to memory
+	 */
+	dmi_check_system(dsdt_dmi_table);
 
 	status = acpi_reallocate_root_table();
 	if (ACPI_FAILURE(status)) {
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 2345a5ee2dbb..a19ff3977ac4 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -21,6 +21,7 @@
 
 #define pr_fmt(fmt) "ACPI: button: " fmt
 
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -235,9 +236,6 @@ static int acpi_lid_notify_state(struct acpi_device *device, int state)
 		button->last_time = ktime_get();
 	}
 
-	if (state)
-		acpi_pm_wakeup_event(&device->dev);
-
 	ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
 	if (ret == NOTIFY_DONE)
 		ret = blocking_notifier_call_chain(&acpi_lid_notifier, state,
@@ -252,7 +250,8 @@ static int acpi_lid_notify_state(struct acpi_device *device, int state)
 	return ret;
 }
 
-static int acpi_button_state_seq_show(struct seq_file *seq, void *offset)
+static int __maybe_unused acpi_button_state_seq_show(struct seq_file *seq,
+						     void *offset)
 {
 	struct acpi_device *device = seq->private;
 	int state;
@@ -366,7 +365,8 @@ int acpi_lid_open(void)
 }
 EXPORT_SYMBOL(acpi_lid_open);
 
-static int acpi_lid_update_state(struct acpi_device *device)
+static int acpi_lid_update_state(struct acpi_device *device,
+				 bool signal_wakeup)
 {
 	int state;
 
@@ -374,6 +374,9 @@ static int acpi_lid_update_state(struct acpi_device *device)
 	if (state < 0)
 		return state;
 
+	if (state && signal_wakeup)
+		acpi_pm_wakeup_event(&device->dev);
+
 	return acpi_lid_notify_state(device, state);
 }
 
@@ -384,7 +387,7 @@ static void acpi_lid_initialize_state(struct acpi_device *device)
 		(void)acpi_lid_notify_state(device, 1);
 		break;
 	case ACPI_BUTTON_LID_INIT_METHOD:
-		(void)acpi_lid_update_state(device);
+		(void)acpi_lid_update_state(device, false);
 		break;
 	case ACPI_BUTTON_LID_INIT_IGNORE:
 	default:
@@ -409,7 +412,7 @@ static void acpi_button_notify(struct acpi_device *device, u32 event)
 			users = button->input->users;
 			mutex_unlock(&button->input->mutex);
 			if (users)
-				acpi_lid_update_state(device);
+				acpi_lid_update_state(device, true);
 		} else {
 			int keycode;
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 442a9e24f439..d4e5610e09c5 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -2042,7 +2042,21 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 		.ident = "Thinkpad X1 Carbon 6th",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "20KGS3JF01"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"),
+		},
+	},
+	{
+		.ident = "ThinkPad X1 Carbon 6th",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Carbon 6th"),
+		},
+	},
+	{
+		.ident = "ThinkPad X1 Yoga 3rd",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Yoga 3rd"),
 		},
 	},
 	{ },
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index d15814e1727f..7c479002e798 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -408,6 +408,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	const guid_t *guid;
 	int rc, i;
 
+	if (cmd_rc)
+		*cmd_rc = -EINVAL;
 	func = cmd;
 	if (cmd == ND_CMD_CALL) {
 		call_pkg = buf;
@@ -518,6 +520,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		 * If we return an error (like elsewhere) then caller wouldn't
 		 * be able to rely upon data returned to make calculation.
 		 */
+		if (cmd_rc)
+			*cmd_rc = 0;
 		return 0;
 	}
 
@@ -1273,7 +1277,7 @@ static ssize_t scrub_show(struct device *dev,
 
 		mutex_lock(&acpi_desc->init_mutex);
 		rc = sprintf(buf, "%d%s", acpi_desc->scrub_count,
-				work_busy(&acpi_desc->dwork.work)
+				acpi_desc->scrub_busy
 				&& !acpi_desc->cancel ? "+\n" : "\n");
 		mutex_unlock(&acpi_desc->init_mutex);
 	}
@@ -2939,6 +2943,32 @@ static unsigned int __acpi_nfit_scrub(struct acpi_nfit_desc *acpi_desc,
 	return 0;
 }
 
+static void __sched_ars(struct acpi_nfit_desc *acpi_desc, unsigned int tmo)
+{
+	lockdep_assert_held(&acpi_desc->init_mutex);
+
+	acpi_desc->scrub_busy = 1;
+	/* note this should only be set from within the workqueue */
+	if (tmo)
+		acpi_desc->scrub_tmo = tmo;
+	queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ);
+}
+
+static void sched_ars(struct acpi_nfit_desc *acpi_desc)
+{
+	__sched_ars(acpi_desc, 0);
+}
+
+static void notify_ars_done(struct acpi_nfit_desc *acpi_desc)
+{
+	lockdep_assert_held(&acpi_desc->init_mutex);
+
+	acpi_desc->scrub_busy = 0;
+	acpi_desc->scrub_count++;
+	if (acpi_desc->scrub_count_state)
+		sysfs_notify_dirent(acpi_desc->scrub_count_state);
+}
+
 static void acpi_nfit_scrub(struct work_struct *work)
 {
 	struct acpi_nfit_desc *acpi_desc;
@@ -2949,14 +2979,10 @@ static void acpi_nfit_scrub(struct work_struct *work)
 	mutex_lock(&acpi_desc->init_mutex);
 	query_rc = acpi_nfit_query_poison(acpi_desc);
 	tmo = __acpi_nfit_scrub(acpi_desc, query_rc);
-	if (tmo) {
-		queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ);
-		acpi_desc->scrub_tmo = tmo;
-	} else {
-		acpi_desc->scrub_count++;
-		if (acpi_desc->scrub_count_state)
-			sysfs_notify_dirent(acpi_desc->scrub_count_state);
-	}
+	if (tmo)
+		__sched_ars(acpi_desc, tmo);
+	else
+		notify_ars_done(acpi_desc);
 	memset(acpi_desc->ars_status, 0, acpi_desc->max_ars);
 	mutex_unlock(&acpi_desc->init_mutex);
 }
@@ -3037,7 +3063,7 @@ static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc)
 			break;
 		}
 
-	queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0);
+	sched_ars(acpi_desc);
 	return 0;
 }
 
@@ -3239,7 +3265,7 @@ int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, unsigned long flags)
 		}
 	}
 	if (scheduled) {
-		queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0);
+		sched_ars(acpi_desc);
 		dev_dbg(dev, "ars_scan triggered\n");
 	}
 	mutex_unlock(&acpi_desc->init_mutex);
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index 7d15856a739f..a97ff42fe311 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -203,6 +203,7 @@ struct acpi_nfit_desc {
 	unsigned int max_ars;
 	unsigned int scrub_count;
 	unsigned int scrub_mode;
+	unsigned int scrub_busy:1;
 	unsigned int cancel:1;
 	unsigned long dimm_cmd_force_en;
 	unsigned long bus_cmd_force_en;
diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c
index 8a8f43568510..b2a16ed7e81a 100644
--- a/drivers/acpi/osi.c
+++ b/drivers/acpi/osi.c
@@ -66,6 +66,14 @@ osi_setup_entries[OSI_STRING_ENTRIES_MAX] __initdata = {
 	 * be removed if both new and old graphics cards are supported.
 	 */
 	{"Linux-Dell-Video", true},
+	/*
+	 * Linux-Lenovo-NV-HDMI-Audio is used by BIOS to power on NVidia's HDMI
+	 * audio device which is turned off for power-saving in Windows OS.
+	 * This power management feature observed on some Lenovo Thinkpad
+	 * systems which will not be able to output audio via HDMI without
+	 * a BIOS workaround.
+	 */
+	{"Linux-Lenovo-NV-HDMI-Audio", true},
 };
 
 static u32 acpi_osi_handler(acpi_string interface, u32 supported)
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 7ca41bf023c9..8df9abfa947b 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -45,6 +45,8 @@
 #include <linux/uaccess.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 
+#include "acpica/accommon.h"
+#include "acpica/acnamesp.h"
 #include "internal.h"
 
 #define _COMPONENT		ACPI_OS_SERVICES
@@ -1490,6 +1492,76 @@ int acpi_check_region(resource_size_t start, resource_size_t n,
 }
 EXPORT_SYMBOL(acpi_check_region);
 
+static acpi_status acpi_deactivate_mem_region(acpi_handle handle, u32 level,
+					      void *_res, void **return_value)
+{
+	struct acpi_mem_space_context **mem_ctx;
+	union acpi_operand_object *handler_obj;
+	union acpi_operand_object *region_obj2;
+	union acpi_operand_object *region_obj;
+	struct resource *res = _res;
+	acpi_status status;
+
+	region_obj = acpi_ns_get_attached_object(handle);
+	if (!region_obj)
+		return AE_OK;
+
+	handler_obj = region_obj->region.handler;
+	if (!handler_obj)
+		return AE_OK;
+
+	if (region_obj->region.space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY)
+		return AE_OK;
+
+	if (!(region_obj->region.flags & AOPOBJ_SETUP_COMPLETE))
+		return AE_OK;
+
+	region_obj2 = acpi_ns_get_secondary_object(region_obj);
+	if (!region_obj2)
+		return AE_OK;
+
+	mem_ctx = (void *)&region_obj2->extra.region_context;
+
+	if (!(mem_ctx[0]->address >= res->start &&
+	      mem_ctx[0]->address < res->end))
+		return AE_OK;
+
+	status = handler_obj->address_space.setup(region_obj,
+						  ACPI_REGION_DEACTIVATE,
+						  NULL, (void **)mem_ctx);
+	if (ACPI_SUCCESS(status))
+		region_obj->region.flags &= ~(AOPOBJ_SETUP_COMPLETE);
+
+	return status;
+}
+
+/**
+ * acpi_release_memory - Release any mappings done to a memory region
+ * @handle: Handle to namespace node
+ * @res: Memory resource
+ * @level: A level that terminates the search
+ *
+ * Walks through @handle and unmaps all SystemMemory Operation Regions that
+ * overlap with @res and that have already been activated (mapped).
+ *
+ * This is a helper that allows drivers to place special requirements on memory
+ * region that may overlap with operation regions, primarily allowing them to
+ * safely map the region as non-cached memory.
+ *
+ * The unmapped Operation Regions will be automatically remapped next time they
+ * are called, so the drivers do not need to do anything else.
+ */
+acpi_status acpi_release_memory(acpi_handle handle, struct resource *res,
+				u32 level)
+{
+	if (!(res->flags & IORESOURCE_MEM))
+		return AE_TYPE;
+
+	return acpi_walk_namespace(ACPI_TYPE_REGION, handle, level,
+				   acpi_deactivate_mem_region, NULL, res, NULL);
+}
+EXPORT_SYMBOL_GPL(acpi_release_memory);
+
 /*
  * Let drivers know whether the resource checks are effective
  */
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index e5ea1974d1e3..d1e26cb599bf 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -481,8 +481,14 @@ static int topology_get_acpi_cpu_tag(struct acpi_table_header *table,
 	if (cpu_node) {
 		cpu_node = acpi_find_processor_package_id(table, cpu_node,
 							  level, flag);
-		/* Only the first level has a guaranteed id */
-		if (level == 0)
+		/*
+		 * As per specification if the processor structure represents
+		 * an actual processor, then ACPI processor ID must be valid.
+		 * For processor containers ACPI_PPTT_ACPI_PROCESSOR_ID_VALID
+		 * should be set if the UID is valid
+		 */
+		if (level == 0 ||
+		    cpu_node->flags & ACPI_PPTT_ACPI_PROCESSOR_ID_VALID)
 			return cpu_node->acpi_processor_id;
 		return ACPI_PTR_DIFF(cpu_node, table);
 	}
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 5815356ea6ad..693cf05b0cc4 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -542,6 +542,23 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data,
 	return 0;
 }
 
+static struct fwnode_handle *
+acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode,
+				 const char *childname)
+{
+	struct fwnode_handle *child;
+
+	/*
+	 * Find first matching named child node of this fwnode.
+	 * For ACPI this will be a data only sub-node.
+	 */
+	fwnode_for_each_child_node(fwnode, child)
+		if (acpi_data_node_match(child, childname))
+			return child;
+
+	return NULL;
+}
+
 /**
  * __acpi_node_get_property_reference - returns handle to the referenced object
  * @fwnode: Firmware node to get the property from
@@ -579,7 +596,7 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data,
  */
 int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 	const char *propname, size_t index, size_t num_args,
-	struct acpi_reference_args *args)
+	struct fwnode_reference_args *args)
 {
 	const union acpi_object *element, *end;
 	const union acpi_object *obj;
@@ -607,7 +624,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		if (ret)
 			return ret == -ENODEV ? -EINVAL : ret;
 
-		args->adev = device;
+		args->fwnode = acpi_fwnode_handle(device);
 		args->nargs = 0;
 		return 0;
 	}
@@ -633,6 +650,8 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		u32 nargs, i;
 
 		if (element->type == ACPI_TYPE_LOCAL_REFERENCE) {
+			struct fwnode_handle *ref_fwnode;
+
 			ret = acpi_bus_get_device(element->reference.handle,
 						  &device);
 			if (ret)
@@ -641,6 +660,19 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 			nargs = 0;
 			element++;
 
+			/*
+			 * Find the referred data extension node under the
+			 * referred device node.
+			 */
+			for (ref_fwnode = acpi_fwnode_handle(device);
+			     element < end && element->type == ACPI_TYPE_STRING;
+			     element++) {
+				ref_fwnode = acpi_fwnode_get_named_child_node(
+					ref_fwnode, element->string.pointer);
+				if (!ref_fwnode)
+					return -EINVAL;
+			}
+
 			/* assume following integer elements are all args */
 			for (i = 0; element + i < end && i < num_args; i++) {
 				int type = element[i].type;
@@ -653,11 +685,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 					return -EINVAL;
 			}
 
-			if (nargs > MAX_ACPI_REFERENCE_ARGS)
+			if (nargs > NR_FWNODE_REFERENCE_ARGS)
 				return -EINVAL;
 
 			if (idx == index) {
-				args->adev = device;
+				args->fwnode = ref_fwnode;
 				args->nargs = nargs;
 				for (i = 0; i < nargs; i++)
 					args->args[i] = element[i].integer.value;
@@ -995,16 +1027,36 @@ struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode)
 	return NULL;
 }
 
+/*
+ * Return true if the node is an ACPI graph node. Called on either ports
+ * or endpoints.
+ */
+static bool is_acpi_graph_node(struct fwnode_handle *fwnode,
+			       const char *str)
+{
+	unsigned int len = strlen(str);
+	const char *name;
+
+	if (!len || !is_acpi_data_node(fwnode))
+		return false;
+
+	name = to_acpi_data_node(fwnode)->name;
+
+	return (fwnode_property_present(fwnode, "reg") &&
+		!strncmp(name, str, len) && name[len] == '@') ||
+		fwnode_property_present(fwnode, str);
+}
+
 /**
  * acpi_graph_get_next_endpoint - Get next endpoint ACPI firmware node
  * @fwnode: Pointer to the parent firmware node
  * @prev: Previous endpoint node or %NULL to get the first
  *
  * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns
- * %NULL if there is no next endpoint, ERR_PTR() in case of error. In case
- * of success the next endpoint is returned.
+ * %NULL if there is no next endpoint or in case of error. In case of success
+ * the next endpoint is returned.
  */
-struct fwnode_handle *acpi_graph_get_next_endpoint(
+static struct fwnode_handle *acpi_graph_get_next_endpoint(
 	const struct fwnode_handle *fwnode, struct fwnode_handle *prev)
 {
 	struct fwnode_handle *port = NULL;
@@ -1013,8 +1065,14 @@ struct fwnode_handle *acpi_graph_get_next_endpoint(
 	if (!prev) {
 		do {
 			port = fwnode_get_next_child_node(fwnode, port);
-			/* Ports must have port property */
-			if (fwnode_property_present(port, "port"))
+			/*
+			 * The names of the port nodes begin with "port@"
+			 * followed by the number of the port node and they also
+			 * have a "reg" property that also has the number of the
+			 * port node. For compatibility reasons a node is also
+			 * recognised as a port node from the "port" property.
+			 */
+			if (is_acpi_graph_node(port, "port"))
 				break;
 		} while (port);
 	} else {
@@ -1029,15 +1087,19 @@ struct fwnode_handle *acpi_graph_get_next_endpoint(
 		port = fwnode_get_next_child_node(fwnode, port);
 		if (!port)
 			break;
-		if (fwnode_property_present(port, "port"))
+		if (is_acpi_graph_node(port, "port"))
 			endpoint = fwnode_get_next_child_node(port, NULL);
 	}
 
-	if (endpoint) {
-		/* Endpoints must have "endpoint" property */
-		if (!fwnode_property_present(endpoint, "endpoint"))
-			return ERR_PTR(-EPROTO);
-	}
+	/*
+	 * The names of the endpoint nodes begin with "endpoint@" followed by
+	 * the number of the endpoint node and they also have a "reg" property
+	 * that also has the number of the endpoint node. For compatibility
+	 * reasons a node is also recognised as an endpoint node from the
+	 * "endpoint" property.
+	 */
+	if (!is_acpi_graph_node(endpoint, "endpoint"))
+		return NULL;
 
 	return endpoint;
 }
@@ -1074,65 +1136,42 @@ static struct fwnode_handle *acpi_graph_get_child_prop_value(
 /**
  * acpi_graph_get_remote_enpoint - Parses and returns remote end of an endpoint
  * @fwnode: Endpoint firmware node pointing to a remote device
- * @parent: Firmware node of remote port parent is filled here if not %NULL
- * @port: Firmware node of remote port is filled here if not %NULL
  * @endpoint: Firmware node of remote endpoint is filled here if not %NULL
  *
- * Function parses remote end of ACPI firmware remote endpoint and fills in
- * fields requested by the caller. Returns %0 in case of success and
- * negative errno otherwise.
+ * Returns the remote endpoint corresponding to @__fwnode. NULL on error.
  */
-int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode,
-				   struct fwnode_handle **parent,
-				   struct fwnode_handle **port,
-				   struct fwnode_handle **endpoint)
+static struct fwnode_handle *
+acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode)
 {
 	struct fwnode_handle *fwnode;
 	unsigned int port_nr, endpoint_nr;
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	int ret;
 
 	memset(&args, 0, sizeof(args));
 	ret = acpi_node_get_property_reference(__fwnode, "remote-endpoint", 0,
 					       &args);
 	if (ret)
-		return ret;
+		return NULL;
+
+	/* Direct endpoint reference? */
+	if (!is_acpi_device_node(args.fwnode))
+		return args.nargs ? NULL : args.fwnode;
 
 	/*
 	 * Always require two arguments with the reference: port and
 	 * endpoint indices.
 	 */
 	if (args.nargs != 2)
-		return -EPROTO;
+		return NULL;
 
-	fwnode = acpi_fwnode_handle(args.adev);
+	fwnode = args.fwnode;
 	port_nr = args.args[0];
 	endpoint_nr = args.args[1];
 
-	if (parent)
-		*parent = fwnode;
-
-	if (!port && !endpoint)
-		return 0;
-
 	fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr);
-	if (!fwnode)
-		return -EPROTO;
-
-	if (port)
-		*port = fwnode;
-
-	if (!endpoint)
-		return 0;
 
-	fwnode = acpi_graph_get_child_prop_value(fwnode, "endpoint",
-						 endpoint_nr);
-	if (!fwnode)
-		return -EPROTO;
-
-	*endpoint = fwnode;
-
-	return 0;
+	return acpi_graph_get_child_prop_value(fwnode, "endpoint", endpoint_nr);
 }
 
 static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode)
@@ -1186,70 +1225,14 @@ acpi_fwnode_property_read_string_array(const struct fwnode_handle *fwnode,
 				   val, nval);
 }
 
-static struct fwnode_handle *
-acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode,
-				 const char *childname)
-{
-	struct fwnode_handle *child;
-
-	/*
-	 * Find first matching named child node of this fwnode.
-	 * For ACPI this will be a data only sub-node.
-	 */
-	fwnode_for_each_child_node(fwnode, child)
-		if (acpi_data_node_match(child, childname))
-			return child;
-
-	return NULL;
-}
-
 static int
 acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode,
 			       const char *prop, const char *nargs_prop,
 			       unsigned int args_count, unsigned int index,
 			       struct fwnode_reference_args *args)
 {
-	struct acpi_reference_args acpi_args;
-	unsigned int i;
-	int ret;
-
-	ret = __acpi_node_get_property_reference(fwnode, prop, index,
-						 args_count, &acpi_args);
-	if (ret < 0)
-		return ret;
-	if (!args)
-		return 0;
-
-	args->nargs = acpi_args.nargs;
-	args->fwnode = acpi_fwnode_handle(acpi_args.adev);
-
-	for (i = 0; i < NR_FWNODE_REFERENCE_ARGS; i++)
-		args->args[i] = i < acpi_args.nargs ? acpi_args.args[i] : 0;
-
-	return 0;
-}
-
-static struct fwnode_handle *
-acpi_fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
-				    struct fwnode_handle *prev)
-{
-	struct fwnode_handle *endpoint;
-
-	endpoint = acpi_graph_get_next_endpoint(fwnode, prev);
-	if (IS_ERR(endpoint))
-		return NULL;
-
-	return endpoint;
-}
-
-static struct fwnode_handle *
-acpi_fwnode_graph_get_remote_endpoint(const struct fwnode_handle *fwnode)
-{
-	struct fwnode_handle *endpoint = NULL;
-
-	acpi_graph_get_remote_endpoint(fwnode, NULL, NULL, &endpoint);
-
-	return endpoint;
+	return __acpi_node_get_property_reference(fwnode, prop, index,
+						  args_count, args);
 }
 
 static struct fwnode_handle *
@@ -1265,8 +1248,10 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 
 	endpoint->local_fwnode = fwnode;
 
-	fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
-	fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
+	if (fwnode_property_read_u32(port_fwnode, "reg", &endpoint->port))
+		fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
+	if (fwnode_property_read_u32(fwnode, "reg", &endpoint->id))
+		fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
 
 	return 0;
 }
@@ -1292,9 +1277,9 @@ acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 		.get_named_child_node = acpi_fwnode_get_named_child_node, \
 		.get_reference_args = acpi_fwnode_get_reference_args,	\
 		.graph_get_next_endpoint =				\
-			acpi_fwnode_graph_get_next_endpoint,		\
+			acpi_graph_get_next_endpoint,			\
 		.graph_get_remote_endpoint =				\
-			acpi_fwnode_graph_get_remote_endpoint,		\
+			acpi_graph_get_remote_endpoint,			\
 		.graph_get_port_parent = acpi_fwnode_get_parent,	\
 		.graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \
 	};								\
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 970dd87d347c..e1b6231cfa1c 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1528,7 +1528,7 @@ static int acpi_check_serial_bus_slave(struct acpi_resource *ares, void *data)
 static bool acpi_is_indirect_io_slave(struct acpi_device *device)
 {
 	struct acpi_device *parent = device->parent;
-	const struct acpi_device_id indirect_io_hosts[] = {
+	static const struct acpi_device_id indirect_io_hosts[] = {
 		{"HISI0191", 0},
 		{}
 	};
@@ -1540,6 +1540,18 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 {
 	struct list_head resource_list;
 	bool is_serial_bus_slave = false;
+	/*
+	 * These devices have multiple I2cSerialBus resources and an i2c-client
+	 * must be instantiated for each, each with its own i2c_device_id.
+	 * Normally we only instantiate an i2c-client for the first resource,
+	 * using the ACPI HID as id. These special cases are handled by the
+	 * drivers/platform/x86/i2c-multi-instantiate.c driver, which knows
+	 * which i2c_device_id to use for each resource.
+	 */
+	static const struct acpi_device_id i2c_multi_instantiate_ids[] = {
+		{"BSG1160", },
+		{}
+	};
 
 	if (acpi_is_indirect_io_slave(device))
 		return true;
@@ -1551,6 +1563,10 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 	     fwnode_property_present(&device->fwnode, "baud")))
 		return true;
 
+	/* Instantiate a pdev for the i2c-multi-instantiate drv to bind to */
+	if (!acpi_match_device_ids(device, i2c_multi_instantiate_ids))
+		return false;
+
 	INIT_LIST_HEAD(&resource_list);
 	acpi_dev_get_resources(device, &resource_list,
 			       acpi_check_serial_bus_slave,
@@ -1612,7 +1628,8 @@ static int acpi_add_single_object(struct acpi_device **child,
 	 * Note this must be done before the get power-/wakeup_dev-flags calls.
 	 */
 	if (type == ACPI_BUS_TYPE_DEVICE)
-		acpi_bus_get_status(device);
+		if (acpi_bus_get_status(device) < 0)
+			acpi_set_device_status(device, 0);
 
 	acpi_bus_get_power_flags(device);
 	acpi_bus_get_wakeup_device_flags(device);
@@ -1690,7 +1707,7 @@ static int acpi_bus_type_and_status(acpi_handle handle, int *type,
 		 * acpi_add_single_object updates this once we've an acpi_device
 		 * so that acpi_bus_get_status' quirk handling can be used.
 		 */
-		*sta = 0;
+		*sta = ACPI_STA_DEFAULT;
 		break;
 	case ACPI_TYPE_PROCESSOR:
 		*type = ACPI_BUS_TYPE_PROCESSOR;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 5d0486f1cfcd..754d59f95500 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -338,6 +338,14 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "K54HR"),
 		},
 	},
+	{
+	.callback = init_nvs_save_s3,
+	.ident = "Asus 1025C",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "1025C"),
+		},
+	},
 	/*
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=189431
 	 * Lenovo G50-45 is a platform later than 2012, but needs nvs memory
@@ -718,9 +726,6 @@ static const struct acpi_device_id lps0_device_ids[] = {
 #define ACPI_LPS0_ENTRY		5
 #define ACPI_LPS0_EXIT		6
 
-#define ACPI_LPS0_SCREEN_MASK	((1 << ACPI_LPS0_SCREEN_OFF) | (1 << ACPI_LPS0_SCREEN_ON))
-#define ACPI_LPS0_PLATFORM_MASK	((1 << ACPI_LPS0_ENTRY) | (1 << ACPI_LPS0_EXIT))
-
 static acpi_handle lps0_device_handle;
 static guid_t lps0_dsm_guid;
 static char lps0_dsm_func_mask;
@@ -924,17 +929,14 @@ static int lps0_device_attach(struct acpi_device *adev,
 	if (out_obj && out_obj->type == ACPI_TYPE_BUFFER) {
 		char bitmask = *(char *)out_obj->buffer.pointer;
 
-		if ((bitmask & ACPI_LPS0_PLATFORM_MASK) == ACPI_LPS0_PLATFORM_MASK ||
-		    (bitmask & ACPI_LPS0_SCREEN_MASK) == ACPI_LPS0_SCREEN_MASK) {
-			lps0_dsm_func_mask = bitmask;
-			lps0_device_handle = adev->handle;
-			/*
-			 * Use suspend-to-idle by default if the default
-			 * suspend mode was not set from the command line.
-			 */
-			if (mem_sleep_default > PM_SUSPEND_MEM)
-				mem_sleep_current = PM_SUSPEND_TO_IDLE;
-		}
+		lps0_dsm_func_mask = bitmask;
+		lps0_device_handle = adev->handle;
+		/*
+		 * Use suspend-to-idle by default if the default
+		 * suspend mode was not set from the command line.
+		 */
+		if (mem_sleep_default > PM_SUSPEND_MEM)
+			mem_sleep_current = PM_SUSPEND_TO_IDLE;
 
 		acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n",
 				  bitmask);
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index ec5b0f190231..06c31ec3cc70 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -62,14 +62,20 @@ static const struct always_present_id always_present_ids[] = {
 	 */
 	ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}),
 	/*
-	 * On the Dell Venue 11 Pro 7130 the DSDT hides the touchscreen ACPI
-	 * device until a certain time after _SB.PCI0.GFX0.LCD.LCD1._ON gets
-	 * called has passed *and* _STA has been called at least 3 times since.
+	 * On the Dell Venue 11 Pro 7130 and 7139, the DSDT hides
+	 * the touchscreen ACPI device until a certain time
+	 * after _SB.PCI0.GFX0.LCD.LCD1._ON gets called has passed
+	 * *and* _STA has been called at least 3 times since.
 	 */
 	ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_ULT), {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"),
 	      }),
+	ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_ULT), {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7139"),
+	      }),
+
 	/*
 	 * The GPD win BIOS dated 20170221 has disabled the accelerometer, the
 	 * drivers sometimes cause crashes under Windows and this is how the
@@ -103,13 +109,9 @@ static const struct always_present_id always_present_ids[] = {
 
 bool acpi_device_always_present(struct acpi_device *adev)
 {
-	u32 *status = (u32 *)&adev->status;
-	u32 old_status = *status;
 	bool ret = false;
 	unsigned int i;
 
-	/* acpi_match_device_ids checks status, so set it to default */
-	*status = ACPI_STA_DEFAULT;
 	for (i = 0; i < ARRAY_SIZE(always_present_ids); i++) {
 		if (acpi_match_device_ids(adev, always_present_ids[i].hid))
 			continue;
@@ -125,15 +127,9 @@ bool acpi_device_always_present(struct acpi_device *adev)
 		    !dmi_check_system(always_present_ids[i].dmi_ids))
 			continue;
 
-		if (old_status != ACPI_STA_DEFAULT) /* Log only once */
-			dev_info(&adev->dev,
-				 "Device [%s] is in always present list\n",
-				 adev->pnp.bus_id);
-
 		ret = true;
 		break;
 	}
-	*status = old_status;
 
 	return ret;
 }
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 2b16e7c8fff3..39b181d6bd0d 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -398,7 +398,6 @@ config SATA_DWC_VDEBUG
 
 config SATA_HIGHBANK
 	tristate "Calxeda Highbank SATA support"
-	depends on HAS_DMA
 	depends on ARCH_HIGHBANK || COMPILE_TEST
 	help
 	  This option enables support for the Calxeda Highbank SoC's
@@ -408,7 +407,6 @@ config SATA_HIGHBANK
 
 config SATA_MV
 	tristate "Marvell SATA support"
-	depends on HAS_DMA
 	depends on PCI || ARCH_DOVE || ARCH_MV78XX0 || \
 		   ARCH_MVEBU || ARCH_ORION5X || COMPILE_TEST
 	select GENERIC_PHY
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 738fb22978dd..b2b9eba1d214 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -400,6 +400,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x0f23), board_ahci_mobile }, /* Bay Trail AHCI */
 	{ PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */
 	{ PCI_VDEVICE(INTEL, 0x5ae3), board_ahci_mobile }, /* ApolloLake AHCI */
+	{ PCI_VDEVICE(INTEL, 0x34d3), board_ahci_mobile }, /* Ice Lake LP AHCI */
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
@@ -1280,6 +1281,59 @@ static bool ahci_broken_suspend(struct pci_dev *pdev)
 	return strcmp(buf, dmi->driver_data) < 0;
 }
 
+static bool ahci_broken_lpm(struct pci_dev *pdev)
+{
+	static const struct dmi_system_id sysids[] = {
+		/* Various Lenovo 50 series have LPM issues with older BIOSen */
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X250"),
+			},
+			.driver_data = "20180406", /* 1.31 */
+		},
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L450"),
+			},
+			.driver_data = "20180420", /* 1.28 */
+		},
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T450s"),
+			},
+			.driver_data = "20180315", /* 1.33 */
+		},
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W541"),
+			},
+			/*
+			 * Note date based on release notes, 2.35 has been
+			 * reported to be good, but I've been unable to get
+			 * a hold of the reporter to get the DMI BIOS date.
+			 * TODO: fix this.
+			 */
+			.driver_data = "20180310", /* 2.35 */
+		},
+		{ }	/* terminate list */
+	};
+	const struct dmi_system_id *dmi = dmi_first_match(sysids);
+	int year, month, date;
+	char buf[9];
+
+	if (!dmi)
+		return false;
+
+	dmi_get_date(DMI_BIOS_DATE, &year, &month, &date);
+	snprintf(buf, sizeof(buf), "%04d%02d%02d", year, month, date);
+
+	return strcmp(buf, dmi->driver_data) < 0;
+}
+
 static bool ahci_broken_online(struct pci_dev *pdev)
 {
 #define ENCODE_BUSDEVFN(bus, slot, func)			\
@@ -1694,6 +1748,12 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			"quirky BIOS, skipping spindown on poweroff\n");
 	}
 
+	if (ahci_broken_lpm(pdev)) {
+		pi.flags |= ATA_FLAG_NO_LPM;
+		dev_warn(&pdev->dev,
+			 "BIOS update required for Link Power Management support\n");
+	}
+
 	if (ahci_broken_suspend(pdev)) {
 		hpriv->flags |= AHCI_HFLAG_NO_SUSPEND;
 		dev_warn(&pdev->dev,
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
index 0045dacd814b..72d90b4c3aae 100644
--- a/drivers/ata/ahci_mvebu.c
+++ b/drivers/ata/ahci_mvebu.c
@@ -82,7 +82,7 @@ static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv)
  *
  * Return: 0 on success; Error code otherwise.
  */
-int ahci_mvebu_stop_engine(struct ata_port *ap)
+static int ahci_mvebu_stop_engine(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
 	u32 tmp, port_fbs;
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 965842a08743..09620c2ffa0f 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
+#include <linux/nospec.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
@@ -1146,10 +1147,12 @@ static ssize_t ahci_led_store(struct ata_port *ap, const char *buf,
 
 	/* get the slot number from the message */
 	pmp = (state & EM_MSG_LED_PMP_SLOT) >> 8;
-	if (pmp < EM_MAX_SLOTS)
+	if (pmp < EM_MAX_SLOTS) {
+		pmp = array_index_nospec(pmp, EM_MAX_SLOTS);
 		emp = &pp->em_priv[pmp];
-	else
+	} else {
 		return -EINVAL;
+	}
 
 	/* mask off the activity bits if we are in sw_activity
 	 * mode, user should turn off sw_activity before setting
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 27d15ed7fa3d..cc71c63df381 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2493,6 +2493,9 @@ int ata_dev_configure(struct ata_device *dev)
 	    (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2)
 		dev->horkage |= ATA_HORKAGE_NOLPM;
 
+	if (ap->flags & ATA_FLAG_NO_LPM)
+		dev->horkage |= ATA_HORKAGE_NOLPM;
+
 	if (dev->horkage & ATA_HORKAGE_NOLPM) {
 		ata_dev_warn(dev, "LPM support broken, forcing max_power\n");
 		dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER;
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index d5412145d76d..01306c018398 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -614,8 +614,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 		list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) {
 			struct ata_queued_cmd *qc;
 
-			for (i = 0; i < ATA_MAX_QUEUE; i++) {
-				qc = __ata_qc_from_tag(ap, i);
+			ata_qc_for_each_raw(ap, qc, i) {
 				if (qc->flags & ATA_QCFLAG_ACTIVE &&
 				    qc->scsicmd == scmd)
 					break;
@@ -818,14 +817,13 @@ EXPORT_SYMBOL_GPL(ata_port_wait_eh);
 
 static int ata_eh_nr_in_flight(struct ata_port *ap)
 {
+	struct ata_queued_cmd *qc;
 	unsigned int tag;
 	int nr = 0;
 
 	/* count only non-internal commands */
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		if (ata_tag_internal(tag))
-			continue;
-		if (ata_qc_from_tag(ap, tag))
+	ata_qc_for_each(ap, qc, tag) {
+		if (qc)
 			nr++;
 	}
 
@@ -847,13 +845,13 @@ void ata_eh_fastdrain_timerfn(struct timer_list *t)
 		goto out_unlock;
 
 	if (cnt == ap->fastdrain_cnt) {
+		struct ata_queued_cmd *qc;
 		unsigned int tag;
 
 		/* No progress during the last interval, tag all
 		 * in-flight qcs as timed out and freeze the port.
 		 */
-		for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-			struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);
+		ata_qc_for_each(ap, qc, tag) {
 			if (qc)
 				qc->err_mask |= AC_ERR_TIMEOUT;
 		}
@@ -999,6 +997,7 @@ void ata_port_schedule_eh(struct ata_port *ap)
 
 static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link)
 {
+	struct ata_queued_cmd *qc;
 	int tag, nr_aborted = 0;
 
 	WARN_ON(!ap->ops->error_handler);
@@ -1007,9 +1006,7 @@ static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link)
 	ata_eh_set_pending(ap, 0);
 
 	/* include internal tag in iteration */
-	for (tag = 0; tag <= ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_with_internal(ap, qc, tag) {
 		if (qc && (!link || qc->dev->link == link)) {
 			qc->flags |= ATA_QCFLAG_FAILED;
 			ata_qc_complete(qc);
@@ -1712,9 +1709,7 @@ void ata_eh_analyze_ncq_error(struct ata_link *link)
 		return;
 
 	/* has LLDD analyzed already? */
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		qc = __ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_FAILED))
 			continue;
 
@@ -2136,6 +2131,7 @@ static void ata_eh_link_autopsy(struct ata_link *link)
 {
 	struct ata_port *ap = link->ap;
 	struct ata_eh_context *ehc = &link->eh_context;
+	struct ata_queued_cmd *qc;
 	struct ata_device *dev;
 	unsigned int all_err_mask = 0, eflags = 0;
 	int tag, nr_failed = 0, nr_quiet = 0;
@@ -2168,9 +2164,7 @@ static void ata_eh_link_autopsy(struct ata_link *link)
 
 	all_err_mask |= ehc->i.err_mask;
 
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_FAILED) ||
 		    ata_dev_phys_link(qc->dev) != link)
 			continue;
@@ -2436,6 +2430,7 @@ static void ata_eh_link_report(struct ata_link *link)
 {
 	struct ata_port *ap = link->ap;
 	struct ata_eh_context *ehc = &link->eh_context;
+	struct ata_queued_cmd *qc;
 	const char *frozen, *desc;
 	char tries_buf[6] = "";
 	int tag, nr_failed = 0;
@@ -2447,9 +2442,7 @@ static void ata_eh_link_report(struct ata_link *link)
 	if (ehc->i.desc[0] != '\0')
 		desc = ehc->i.desc;
 
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_FAILED) ||
 		    ata_dev_phys_link(qc->dev) != link ||
 		    ((qc->flags & ATA_QCFLAG_QUIET) &&
@@ -2511,8 +2504,7 @@ static void ata_eh_link_report(struct ata_link *link)
 		  ehc->i.serror & SERR_DEV_XCHG ? "DevExch " : "");
 #endif
 
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
+	ata_qc_for_each_raw(ap, qc, tag) {
 		struct ata_taskfile *cmd = &qc->tf, *res = &qc->result_tf;
 		char data_buf[20] = "";
 		char cdb_buf[70] = "";
@@ -3992,12 +3984,11 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
  */
 void ata_eh_finish(struct ata_port *ap)
 {
+	struct ata_queued_cmd *qc;
 	int tag;
 
 	/* retry or finish qcs */
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_FAILED))
 			continue;
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 6a91d04351d9..8e270962b2f3 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -597,8 +597,9 @@ static int ata_get_identity(struct ata_port *ap, struct scsi_device *sdev,
 int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 {
 	int rc = 0;
+	u8 sensebuf[SCSI_SENSE_BUFFERSIZE];
 	u8 scsi_cmd[MAX_COMMAND_SIZE];
-	u8 args[4], *argbuf = NULL, *sensebuf = NULL;
+	u8 args[4], *argbuf = NULL;
 	int argsize = 0;
 	enum dma_data_direction data_dir;
 	struct scsi_sense_hdr sshdr;
@@ -610,10 +611,7 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	if (copy_from_user(args, arg, sizeof(args)))
 		return -EFAULT;
 
-	sensebuf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
-	if (!sensebuf)
-		return -ENOMEM;
-
+	memset(sensebuf, 0, sizeof(sensebuf));
 	memset(scsi_cmd, 0, sizeof(scsi_cmd));
 
 	if (args[3]) {
@@ -685,7 +683,6 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	 && copy_to_user(arg + sizeof(args), argbuf, argsize))
 		rc = -EFAULT;
 error:
-	kfree(sensebuf);
 	kfree(argbuf);
 	return rc;
 }
@@ -704,8 +701,9 @@ error:
 int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 {
 	int rc = 0;
+	u8 sensebuf[SCSI_SENSE_BUFFERSIZE];
 	u8 scsi_cmd[MAX_COMMAND_SIZE];
-	u8 args[7], *sensebuf = NULL;
+	u8 args[7];
 	struct scsi_sense_hdr sshdr;
 	int cmd_result;
 
@@ -715,10 +713,7 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	if (copy_from_user(args, arg, sizeof(args)))
 		return -EFAULT;
 
-	sensebuf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
-	if (!sensebuf)
-		return -ENOMEM;
-
+	memset(sensebuf, 0, sizeof(sensebuf));
 	memset(scsi_cmd, 0, sizeof(scsi_cmd));
 	scsi_cmd[0]  = ATA_16;
 	scsi_cmd[1]  = (3 << 1); /* Non-data */
@@ -769,7 +764,6 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	}
 
  error:
-	kfree(sensebuf);
 	return rc;
 }
 
@@ -3805,10 +3799,20 @@ static unsigned int ata_scsi_zbc_out_xlat(struct ata_queued_cmd *qc)
 		 */
 		goto invalid_param_len;
 	}
-	if (block > dev->n_sectors)
-		goto out_of_range;
 
 	all = cdb[14] & 0x1;
+	if (all) {
+		/*
+		 * Ignore the block address (zone ID) as defined by ZBC.
+		 */
+		block = 0;
+	} else if (block >= dev->n_sectors) {
+		/*
+		 * Block must be a valid zone ID (a zone start LBA).
+		 */
+		fp = 2;
+		goto invalid_fld;
+	}
 
 	if (ata_ncq_enabled(qc->dev) &&
 	    ata_fpdma_zac_mgmt_out_supported(qc->dev)) {
@@ -3837,10 +3841,6 @@ static unsigned int ata_scsi_zbc_out_xlat(struct ata_queued_cmd *qc)
  invalid_fld:
 	ata_scsi_set_invalid_field(qc->dev, scmd, fp, 0xff);
 	return 1;
- out_of_range:
-	/* "Logical Block Address out of range" */
-	ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x21, 0x00);
-	return 1;
 invalid_param_len:
 	/* "Parameter list length error" */
 	ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x1a, 0x0);
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index f6c46e9a4dc0..e8b6a2e464c9 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -25,7 +25,6 @@
 #include <linux/libata.h>
 #include <linux/platform_device.h>
 #include <linux/dmaengine.h>
-#include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
 #include <linux/completion.h>
@@ -180,8 +179,6 @@ static int pxa_ata_probe(struct platform_device *pdev)
 	struct resource *irq_res;
 	struct pata_pxa_pdata *pdata = dev_get_platdata(&pdev->dev);
 	struct dma_slave_config	config;
-	dma_cap_mask_t mask;
-	struct pxad_param param;
 	int ret = 0;
 
 	/*
@@ -278,10 +275,6 @@ static int pxa_ata_probe(struct platform_device *pdev)
 
 	ap->private_data = data;
 
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	param.prio = PXAD_PRIO_LOWEST;
-	param.drcmr = pdata->dma_dreq;
 	memset(&config, 0, sizeof(config));
 	config.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 	config.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
@@ -294,8 +287,7 @@ static int pxa_ata_probe(struct platform_device *pdev)
 	 * Request the DMA channel
 	 */
 	data->dma_chan =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param, &pdev->dev, "data");
+		dma_request_slave_channel(&pdev->dev, "data");
 	if (!data->dma_chan)
 		return -EBUSY;
 	ret = dmaengine_slave_config(data->dma_chan, &config);
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index b8d9cfc60374..4dc528bf8e85 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -395,12 +395,6 @@ static inline unsigned int sata_fsl_tag(unsigned int tag,
 {
 	/* We let libATA core do actual (queue) tag allocation */
 
-	/* all non NCQ/queued commands should have tag#0 */
-	if (ata_tag_internal(tag)) {
-		DPRINTK("mapping internal cmds to tag#0\n");
-		return 0;
-	}
-
 	if (unlikely(tag >= SATA_FSL_QUEUE_DEPTH)) {
 		DPRINTK("tag %d invalid : out of range\n", tag);
 		return 0;
@@ -1229,8 +1223,7 @@ static void sata_fsl_host_intr(struct ata_port *ap)
 
 	/* Workaround for data length mismatch errata */
 	if (unlikely(hstatus & INT_ON_DATA_LENGTH_MISMATCH)) {
-		for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-			qc = ata_qc_from_tag(ap, tag);
+		ata_qc_for_each_with_internal(ap, qc, tag) {
 			if (qc && ata_is_atapi(qc->tf.protocol)) {
 				u32 hcontrol;
 				/* Set HControl[27] to clear error registers */
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 10ae11aa1926..72c9b922a77b 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -675,7 +675,6 @@ static int nv_adma_slave_config(struct scsi_device *sdev)
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 	struct nv_adma_port_priv *pp = ap->private_data;
 	struct nv_adma_port_priv *port0, *port1;
-	struct scsi_device *sdev0, *sdev1;
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 	unsigned long segment_boundary, flags;
 	unsigned short sg_tablesize;
@@ -736,8 +735,6 @@ static int nv_adma_slave_config(struct scsi_device *sdev)
 
 	port0 = ap->host->ports[0]->private_data;
 	port1 = ap->host->ports[1]->private_data;
-	sdev0 = ap->host->ports[0]->link.device[0].sdev;
-	sdev1 = ap->host->ports[1]->link.device[0].sdev;
 	if ((port0->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) ||
 	    (port1->flags & NV_ADMA_ATAPI_SETUP_COMPLETE)) {
 		/*
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index ff81a576347e..82532c299bb5 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -1618,7 +1618,7 @@ static int rx_init(struct atm_dev *dev)
 	skb_queue_head_init(&iadev->rx_dma_q);  
 	iadev->rx_free_desc_qhead = NULL;   
 
-	iadev->rx_open = kcalloc(4, iadev->num_vc, GFP_KERNEL);
+	iadev->rx_open = kcalloc(iadev->num_vc, sizeof(void *), GFP_KERNEL);
 	if (!iadev->rx_open) {
 		printk(KERN_ERR DEV_LABEL "itf %d couldn't get free page\n",
 		dev->number);  
diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index a8d2eb0ceb8d..2c288d1f42bb 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -1483,6 +1483,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 					return -EFAULT;
 				if (pool < 0 || pool > ZATM_LAST_POOL)
 					return -EINVAL;
+				pool = array_index_nospec(pool,
+							  ZATM_LAST_POOL + 1);
 				if (copy_from_user(&info,
 				    &((struct zatm_pool_req __user *) arg)->info,
 				    sizeof(info))) return -EFAULT;
diff --git a/drivers/base/core.c b/drivers/base/core.c
index df3e1a44707a..9d3c15d4dde8 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -178,10 +178,10 @@ void device_pm_move_to_tail(struct device *dev)
  * of the link.  If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be
  * ignored.
  *
- * If the DL_FLAG_AUTOREMOVE is set, the link will be removed automatically
- * when the consumer device driver unbinds from it.  The combination of both
- * DL_FLAG_AUTOREMOVE and DL_FLAG_STATELESS set is invalid and will cause NULL
- * to be returned.
+ * If the DL_FLAG_AUTOREMOVE_CONSUMER is set, the link will be removed
+ * automatically when the consumer device driver unbinds from it.
+ * The combination of both DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_STATELESS
+ * set is invalid and will cause NULL to be returned.
  *
  * A side effect of the link creation is re-ordering of dpm_list and the
  * devices_kset list by moving the consumer device and all devices depending
@@ -198,7 +198,8 @@ struct device_link *device_link_add(struct device *consumer,
 	struct device_link *link;
 
 	if (!consumer || !supplier ||
-	    ((flags & DL_FLAG_STATELESS) && (flags & DL_FLAG_AUTOREMOVE)))
+	    ((flags & DL_FLAG_STATELESS) &&
+	     (flags & DL_FLAG_AUTOREMOVE_CONSUMER)))
 		return NULL;
 
 	device_links_write_lock();
@@ -372,6 +373,36 @@ void device_link_del(struct device_link *link)
 }
 EXPORT_SYMBOL_GPL(device_link_del);
 
+/**
+ * device_link_remove - remove a link between two devices.
+ * @consumer: Consumer end of the link.
+ * @supplier: Supplier end of the link.
+ *
+ * The caller must ensure proper synchronization of this function with runtime
+ * PM.
+ */
+void device_link_remove(void *consumer, struct device *supplier)
+{
+	struct device_link *link;
+
+	if (WARN_ON(consumer == supplier))
+		return;
+
+	device_links_write_lock();
+	device_pm_lock();
+
+	list_for_each_entry(link, &supplier->links.consumers, s_node) {
+		if (link->consumer == consumer) {
+			kref_put(&link->kref, __device_link_del);
+			break;
+		}
+	}
+
+	device_pm_unlock();
+	device_links_write_unlock();
+}
+EXPORT_SYMBOL_GPL(device_link_remove);
+
 static void device_links_missing_supplier(struct device *dev)
 {
 	struct device_link *link;
@@ -479,7 +510,7 @@ static void __device_links_no_driver(struct device *dev)
 		if (link->flags & DL_FLAG_STATELESS)
 			continue;
 
-		if (link->flags & DL_FLAG_AUTOREMOVE)
+		if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER)
 			kref_put(&link->kref, __device_link_del);
 		else if (link->status != DL_STATE_SUPPLIER_UNBIND)
 			WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
@@ -515,8 +546,18 @@ void device_links_driver_cleanup(struct device *dev)
 		if (link->flags & DL_FLAG_STATELESS)
 			continue;
 
-		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE);
+		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER);
 		WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND);
+
+		/*
+		 * autoremove the links between this @dev and its consumer
+		 * devices that are not active, i.e. where the link state
+		 * has moved to DL_STATE_SUPPLIER_UNBIND.
+		 */
+		if (link->status == DL_STATE_SUPPLIER_UNBIND &&
+		    link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
+			kref_put(&link->kref, __device_link_del);
+
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
 	}
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 30cc9c877ebb..eb9443d5bae1 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -540,16 +540,24 @@ ssize_t __weak cpu_show_spec_store_bypass(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_l1tf(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
 static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
+static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
 	&dev_attr_spectre_v1.attr,
 	&dev_attr_spectre_v2.attr,
 	&dev_attr_spec_store_bypass.attr,
+	&dev_attr_l1tf.attr,
 	NULL
 };
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 1435d7281c66..6ebcd65d64b6 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -434,14 +434,6 @@ re_probe:
 			goto probe_failed;
 	}
 
-	/*
-	 * Ensure devices are listed in devices_kset in correct order
-	 * It's important to move Dev to the end of devices_kset before
-	 * calling .probe, because it could be recursive and parent Dev
-	 * should always go first
-	 */
-	devices_kset_move_last(dev);
-
 	if (dev->bus->probe) {
 		ret = dev->bus->probe(dev);
 		if (ret)
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index df41b4780b3b..b413951c6abc 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -153,6 +153,23 @@ struct device *dev_pm_domain_attach_by_id(struct device *dev,
 EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id);
 
 /**
+ * dev_pm_domain_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * For a detailed function description, see dev_pm_domain_attach_by_id().
+ */
+struct device *dev_pm_domain_attach_by_name(struct device *dev,
+					    char *name)
+{
+	if (dev->pm_domain)
+		return ERR_PTR(-EEXIST);
+
+	return genpd_dev_pm_attach_by_name(dev, name);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name);
+
+/**
  * dev_pm_domain_detach - Detach a device from its PM domain.
  * @dev: Device to detach.
  * @power_off: Used to indicate whether we should power off the device.
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 4925af5c4cf0..79bdca70a81a 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2235,7 +2235,7 @@ static void genpd_dev_pm_sync(struct device *dev)
 }
 
 static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np,
-				 unsigned int index)
+				 unsigned int index, bool power_on)
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
@@ -2271,9 +2271,11 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np,
 	dev->pm_domain->detach = genpd_dev_pm_detach;
 	dev->pm_domain->sync = genpd_dev_pm_sync;
 
-	genpd_lock(pd);
-	ret = genpd_power_on(pd, 0);
-	genpd_unlock(pd);
+	if (power_on) {
+		genpd_lock(pd);
+		ret = genpd_power_on(pd, 0);
+		genpd_unlock(pd);
+	}
 
 	if (ret)
 		genpd_remove_device(pd, dev);
@@ -2307,7 +2309,7 @@ int genpd_dev_pm_attach(struct device *dev)
 				       "#power-domain-cells") != 1)
 		return 0;
 
-	return __genpd_dev_pm_attach(dev, dev->of_node, 0);
+	return __genpd_dev_pm_attach(dev, dev->of_node, 0, true);
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
 
@@ -2359,19 +2361,43 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 	}
 
 	/* Try to attach the device to the PM domain at the specified index. */
-	ret = __genpd_dev_pm_attach(genpd_dev, dev->of_node, index);
+	ret = __genpd_dev_pm_attach(genpd_dev, dev->of_node, index, false);
 	if (ret < 1) {
 		device_unregister(genpd_dev);
 		return ret ? ERR_PTR(ret) : NULL;
 	}
 
-	pm_runtime_set_active(genpd_dev);
 	pm_runtime_enable(genpd_dev);
+	genpd_queue_power_off_work(dev_to_genpd(genpd_dev));
 
 	return genpd_dev;
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id);
 
+/**
+ * genpd_dev_pm_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * Parse device's OF node to find a PM domain specifier using the
+ * power-domain-names DT property. For further description see
+ * genpd_dev_pm_attach_by_id().
+ */
+struct device *genpd_dev_pm_attach_by_name(struct device *dev, char *name)
+{
+	int index;
+
+	if (!dev->of_node)
+		return NULL;
+
+	index = of_property_match_string(dev->of_node, "power-domain-names",
+					 name);
+	if (index < 0)
+		return NULL;
+
+	return genpd_dev_pm_attach_by_id(dev, index);
+}
+
 static const struct of_device_id idle_state_match[] = {
 	{ .compatible = "domain-idle-state", },
 	{ }
@@ -2487,10 +2513,9 @@ EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states);
  * power domain corresponding to a DT node's "required-opps" property.
  *
  * @dev: Device for which the performance-state needs to be found.
- * @opp_node: DT node where the "required-opps" property is present. This can be
+ * @np: DT node where the "required-opps" property is present. This can be
  *	the device node itself (if it doesn't have an OPP table) or a node
  *	within the OPP table of a device (if device has an OPP table).
- * @state: Pointer to return performance state.
  *
  * Returns performance state corresponding to the "required-opps" property of
  * a DT node. This calls platform specific genpd->opp_to_performance_state()
@@ -2499,7 +2524,7 @@ EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states);
  * Returns performance state on success and 0 on failure.
  */
 unsigned int of_genpd_opp_to_performance_state(struct device *dev,
-					       struct device_node *opp_node)
+					       struct device_node *np)
 {
 	struct generic_pm_domain *genpd;
 	struct dev_pm_opp *opp;
@@ -2514,7 +2539,7 @@ unsigned int of_genpd_opp_to_performance_state(struct device *dev,
 
 	genpd_lock(genpd);
 
-	opp = of_dev_pm_opp_find_required_opp(&genpd->dev, opp_node);
+	opp = of_dev_pm_opp_find_required_opp(&genpd->dev, np);
 	if (IS_ERR(opp)) {
 		dev_err(dev, "Failed to find required OPP: %ld\n",
 			PTR_ERR(opp));
diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig
index aff34c0c2a3e..6ad5ef48b61e 100644
--- a/drivers/base/regmap/Kconfig
+++ b/drivers/base/regmap/Kconfig
@@ -45,3 +45,7 @@ config REGMAP_IRQ
 config REGMAP_SOUNDWIRE
 	tristate
 	depends on SOUNDWIRE_BUS
+
+config REGMAP_SCCB
+	tristate
+	depends on I2C
diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile
index 5ed0023fabda..f5b4e8851d00 100644
--- a/drivers/base/regmap/Makefile
+++ b/drivers/base/regmap/Makefile
@@ -15,3 +15,4 @@ obj-$(CONFIG_REGMAP_MMIO) += regmap-mmio.o
 obj-$(CONFIG_REGMAP_IRQ) += regmap-irq.o
 obj-$(CONFIG_REGMAP_W1) += regmap-w1.o
 obj-$(CONFIG_REGMAP_SOUNDWIRE) += regmap-sdw.o
+obj-$(CONFIG_REGMAP_SCCB) += regmap-sccb.o
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 53785e0e297a..a6bf34d6394e 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -94,10 +94,12 @@ struct regmap {
 	bool (*readable_reg)(struct device *dev, unsigned int reg);
 	bool (*volatile_reg)(struct device *dev, unsigned int reg);
 	bool (*precious_reg)(struct device *dev, unsigned int reg);
+	bool (*readable_noinc_reg)(struct device *dev, unsigned int reg);
 	const struct regmap_access_table *wr_table;
 	const struct regmap_access_table *rd_table;
 	const struct regmap_access_table *volatile_table;
 	const struct regmap_access_table *precious_table;
+	const struct regmap_access_table *rd_noinc_table;
 
 	int (*reg_read)(void *context, unsigned int reg, unsigned int *val);
 	int (*reg_write)(void *context, unsigned int reg, unsigned int val);
@@ -181,6 +183,7 @@ bool regmap_writeable(struct regmap *map, unsigned int reg);
 bool regmap_readable(struct regmap *map, unsigned int reg);
 bool regmap_volatile(struct regmap *map, unsigned int reg);
 bool regmap_precious(struct regmap *map, unsigned int reg);
+bool regmap_readable_noinc(struct regmap *map, unsigned int reg);
 
 int _regmap_write(struct regmap *map, unsigned int reg,
 		  unsigned int val);
diff --git a/drivers/base/regmap/regmap-sccb.c b/drivers/base/regmap/regmap-sccb.c
new file mode 100644
index 000000000000..597042e2d009
--- /dev/null
+++ b/drivers/base/regmap/regmap-sccb.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+// Register map access API - SCCB support
+
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+#include "internal.h"
+
+/**
+ * sccb_is_available - Check if the adapter supports SCCB protocol
+ * @adap: I2C adapter
+ *
+ * Return true if the I2C adapter is capable of using SCCB helper functions,
+ * false otherwise.
+ */
+static bool sccb_is_available(struct i2c_adapter *adap)
+{
+	u32 needed_funcs = I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_WRITE_BYTE_DATA;
+
+	/*
+	 * If we ever want support for hardware doing SCCB natively, we will
+	 * introduce a sccb_xfer() callback to struct i2c_algorithm and check
+	 * for it here.
+	 */
+
+	return (i2c_get_functionality(adap) & needed_funcs) == needed_funcs;
+}
+
+/**
+ * regmap_sccb_read - Read data from SCCB slave device
+ * @context: Device that will be interacted with
+ * @reg: Register to be read from
+ * @val: Pointer to store read value
+ *
+ * This executes the 2-phase write transmission cycle that is followed by a
+ * 2-phase read transmission cycle, returning negative errno else zero on
+ * success.
+ */
+static int regmap_sccb_read(void *context, unsigned int reg, unsigned int *val)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	int ret;
+	union i2c_smbus_data data;
+
+	i2c_lock_bus(i2c->adapter, I2C_LOCK_SEGMENT);
+
+	ret = __i2c_smbus_xfer(i2c->adapter, i2c->addr, i2c->flags,
+			       I2C_SMBUS_WRITE, reg, I2C_SMBUS_BYTE, NULL);
+	if (ret < 0)
+		goto out;
+
+	ret = __i2c_smbus_xfer(i2c->adapter, i2c->addr, i2c->flags,
+			       I2C_SMBUS_READ, 0, I2C_SMBUS_BYTE, &data);
+	if (ret < 0)
+		goto out;
+
+	*val = data.byte;
+out:
+	i2c_unlock_bus(i2c->adapter, I2C_LOCK_SEGMENT);
+
+	return ret;
+}
+
+/**
+ * regmap_sccb_write - Write data to SCCB slave device
+ * @context: Device that will be interacted with
+ * @reg: Register to write to
+ * @val: Value to be written
+ *
+ * This executes the SCCB 3-phase write transmission cycle, returning negative
+ * errno else zero on success.
+ */
+static int regmap_sccb_write(void *context, unsigned int reg, unsigned int val)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+
+	return i2c_smbus_write_byte_data(i2c, reg, val);
+}
+
+static struct regmap_bus regmap_sccb_bus = {
+	.reg_write = regmap_sccb_write,
+	.reg_read = regmap_sccb_read,
+};
+
+static const struct regmap_bus *regmap_get_sccb_bus(struct i2c_client *i2c,
+					const struct regmap_config *config)
+{
+	if (config->val_bits == 8 && config->reg_bits == 8 &&
+			sccb_is_available(i2c->adapter))
+		return &regmap_sccb_bus;
+
+	return ERR_PTR(-ENOTSUPP);
+}
+
+struct regmap *__regmap_init_sccb(struct i2c_client *i2c,
+				  const struct regmap_config *config,
+				  struct lock_class_key *lock_key,
+				  const char *lock_name)
+{
+	const struct regmap_bus *bus = regmap_get_sccb_bus(i2c, config);
+
+	if (IS_ERR(bus))
+		return ERR_CAST(bus);
+
+	return __regmap_init(&i2c->dev, bus, &i2c->dev, config,
+			     lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__regmap_init_sccb);
+
+struct regmap *__devm_regmap_init_sccb(struct i2c_client *i2c,
+				       const struct regmap_config *config,
+				       struct lock_class_key *lock_key,
+				       const char *lock_name)
+{
+	const struct regmap_bus *bus = regmap_get_sccb_bus(i2c, config);
+
+	if (IS_ERR(bus))
+		return ERR_CAST(bus);
+
+	return __devm_regmap_init(&i2c->dev, bus, &i2c->dev, config,
+				  lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__devm_regmap_init_sccb);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/base/regmap/regmap-slimbus.c b/drivers/base/regmap/regmap-slimbus.c
index 91d501eda8a9..0968059f1ef5 100644
--- a/drivers/base/regmap/regmap-slimbus.c
+++ b/drivers/base/regmap/regmap-slimbus.c
@@ -7,33 +7,24 @@
 
 #include "internal.h"
 
-static int regmap_slimbus_byte_reg_read(void *context, unsigned int reg,
-					unsigned int *val)
+static int regmap_slimbus_write(void *context, const void *data, size_t count)
 {
 	struct slim_device *sdev = context;
-	int v;
 
-	v = slim_readb(sdev, reg);
-
-	if (v < 0)
-		return v;
-
-	*val = v;
-
-	return 0;
+	return slim_write(sdev, *(u16 *)data, count - 2, (u8 *)data + 2);
 }
 
-static int regmap_slimbus_byte_reg_write(void *context, unsigned int reg,
-					 unsigned int val)
+static int regmap_slimbus_read(void *context, const void *reg, size_t reg_size,
+			       void *val, size_t val_size)
 {
 	struct slim_device *sdev = context;
 
-	return slim_writeb(sdev, reg, val);
+	return slim_read(sdev, *(u16 *)reg, val_size, val);
 }
 
 static struct regmap_bus regmap_slimbus_bus = {
-	.reg_write = regmap_slimbus_byte_reg_write,
-	.reg_read = regmap_slimbus_byte_reg_read,
+	.write = regmap_slimbus_write,
+	.read = regmap_slimbus_read,
 	.reg_format_endian_default = REGMAP_ENDIAN_LITTLE,
 	.val_format_endian_default = REGMAP_ENDIAN_LITTLE,
 };
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 3bc84885eb91..0360a90ad6b6 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -168,6 +168,17 @@ bool regmap_precious(struct regmap *map, unsigned int reg)
 	return false;
 }
 
+bool regmap_readable_noinc(struct regmap *map, unsigned int reg)
+{
+	if (map->readable_noinc_reg)
+		return map->readable_noinc_reg(map->dev, reg);
+
+	if (map->rd_noinc_table)
+		return regmap_check_range_table(map, reg, map->rd_noinc_table);
+
+	return true;
+}
+
 static bool regmap_volatile_range(struct regmap *map, unsigned int reg,
 	size_t num)
 {
@@ -766,10 +777,12 @@ struct regmap *__regmap_init(struct device *dev,
 	map->rd_table = config->rd_table;
 	map->volatile_table = config->volatile_table;
 	map->precious_table = config->precious_table;
+	map->rd_noinc_table = config->rd_noinc_table;
 	map->writeable_reg = config->writeable_reg;
 	map->readable_reg = config->readable_reg;
 	map->volatile_reg = config->volatile_reg;
 	map->precious_reg = config->precious_reg;
+	map->readable_noinc_reg = config->readable_noinc_reg;
 	map->cache_type = config->cache_type;
 
 	spin_lock_init(&map->async_lock);
@@ -1285,6 +1298,7 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config)
 	map->readable_reg = config->readable_reg;
 	map->volatile_reg = config->volatile_reg;
 	map->precious_reg = config->precious_reg;
+	map->readable_noinc_reg = config->readable_noinc_reg;
 	map->cache_type = config->cache_type;
 
 	regmap_debugfs_init(map, config->name);
@@ -2564,7 +2578,70 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 EXPORT_SYMBOL_GPL(regmap_raw_read);
 
 /**
- * regmap_field_read() - Read a value to a single register field
+ * regmap_noinc_read(): Read data from a register without incrementing the
+ *			register number
+ *
+ * @map: Register map to read from
+ * @reg: Register to read from
+ * @val: Pointer to data buffer
+ * @val_len: Length of output buffer in bytes.
+ *
+ * The regmap API usually assumes that bulk bus read operations will read a
+ * range of registers. Some devices have certain registers for which a read
+ * operation read will read from an internal FIFO.
+ *
+ * The target register must be volatile but registers after it can be
+ * completely unrelated cacheable registers.
+ *
+ * This will attempt multiple reads as required to read val_len bytes.
+ *
+ * A value of zero will be returned on success, a negative errno will be
+ * returned in error cases.
+ */
+int regmap_noinc_read(struct regmap *map, unsigned int reg,
+		      void *val, size_t val_len)
+{
+	size_t read_len;
+	int ret;
+
+	if (!map->bus)
+		return -EINVAL;
+	if (!map->bus->read)
+		return -ENOTSUPP;
+	if (val_len % map->format.val_bytes)
+		return -EINVAL;
+	if (!IS_ALIGNED(reg, map->reg_stride))
+		return -EINVAL;
+	if (val_len == 0)
+		return -EINVAL;
+
+	map->lock(map->lock_arg);
+
+	if (!regmap_volatile(map, reg) || !regmap_readable_noinc(map, reg)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	while (val_len) {
+		if (map->max_raw_read && map->max_raw_read < val_len)
+			read_len = map->max_raw_read;
+		else
+			read_len = val_len;
+		ret = _regmap_raw_read(map, reg, val, read_len);
+		if (ret)
+			goto out_unlock;
+		val = ((u8 *)val) + read_len;
+		val_len -= read_len;
+	}
+
+out_unlock:
+	map->unlock(map->lock_arg);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regmap_noinc_read);
+
+/**
+ * regmap_field_read(): Read a value to a single register field
  *
  * @field: Register field to read from
  * @val: Pointer to store read value
diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index cb0f1aad20b7..b9558ff20830 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -30,6 +30,7 @@ config BCMA_HOST_PCI
 
 config BCMA_HOST_SOC
 	bool "Support for BCMA in a SoC"
+	depends on HAS_IOMEM
 	help
 	  Host interface for a Broadcom AIX bus directly mapped into
 	  the memory. This only works with the Broadcom SoCs from the
@@ -61,7 +62,7 @@ config BCMA_DRIVER_PCI_HOSTMODE
 
 config BCMA_DRIVER_MIPS
 	bool "BCMA Broadcom MIPS core driver"
-	depends on MIPS
+	depends on MIPS || COMPILE_TEST
 	help
 	  Driver for the Broadcom MIPS core attached to Broadcom specific
 	  Advanced Microcontroller Bus.
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index f6518067aa7d..f99e5c883368 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -21,6 +21,7 @@
 #define DAC960_DriverDate			"21 Aug 2007"
 
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
@@ -6426,7 +6427,7 @@ static bool DAC960_V2_ExecuteUserCommand(DAC960_Controller_T *Controller,
   return true;
 }
 
-static int dac960_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_proc_show(struct seq_file *m, void *v)
 {
   unsigned char *StatusMessage = "OK\n";
   int ControllerNumber;
@@ -6446,14 +6447,16 @@ static int dac960_proc_show(struct seq_file *m, void *v)
   return 0;
 }
 
-static int dac960_initial_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_initial_status_proc_show(struct seq_file *m,
+							  void *v)
 {
 	DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private;
 	seq_printf(m, "%.*s", Controller->InitialStatusLength, Controller->CombinedStatusBuffer);
 	return 0;
 }
 
-static int dac960_current_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_current_status_proc_show(struct seq_file *m,
+							  void *v)
 {
   DAC960_Controller_T *Controller = (DAC960_Controller_T *) m->private;
   unsigned char *StatusMessage =
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index ad9b687a236a..d4913516823f 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -74,12 +74,12 @@ config AMIGA_Z2RAM
 
 config CDROM
 	tristate
+	select BLK_SCSI_REQUEST
 
 config GDROM
 	tristate "SEGA Dreamcast GD-ROM drive"
 	depends on SH_DREAMCAST
 	select CDROM
-	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	help
 	  A standard SEGA Dreamcast comes with a modified CD ROM drive called a
 	  "GD-ROM" by SEGA to signify it is capable of reading special disks
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index dc061158b403..8566b188368b 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -36,8 +36,11 @@ obj-$(CONFIG_BLK_DEV_RBD)     += rbd.o
 obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX)	+= mtip32xx/
 
 obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
-obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
 obj-$(CONFIG_ZRAM) += zram/
 
+obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
+null_blk-objs	:= null_blk_main.o
+null_blk-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
+
 skd-y		:= skd_main.o
 swim_mod-y	:= swim.o swim_asm.o
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 096882e54095..136dc507d020 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1137,6 +1137,7 @@ noskb:		if (buf)
 			break;
 		}
 		bvcpy(skb, f->buf->bio, f->iter, n);
+		/* fall through */
 	case ATA_CMD_PIO_WRITE:
 	case ATA_CMD_PIO_WRITE_EXT:
 		spin_lock_irq(&d->lock);
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 697f735b07a4..41060e9cedf2 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -284,8 +284,8 @@ freedev(struct aoedev *d)
 	e = t + d->ntargets;
 	for (; t < e && *t; t++)
 		freetgt(d, *t);
-	if (d->bufpool)
-		mempool_destroy(d->bufpool);
+
+	mempool_destroy(d->bufpool);
 	skbpoolfree(d);
 	minor_free(d->sysminor);
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index bb976598ee43..df8103dd40ac 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -254,20 +254,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  * Process a single bvec of a bio.
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	void *mem;
 	int err = 0;
 
-	if (is_write) {
+	if (op_is_write(op)) {
 		err = copy_to_brd_setup(brd, sector, len);
 		if (err)
 			goto out;
 	}
 
 	mem = kmap_atomic(page);
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		copy_from_brd(mem + off, brd, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -296,7 +296,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		int err;
 
 		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
-					op_is_write(bio_op(bio)), sector);
+				  bio_op(bio), sector);
 		if (err)
 			goto io_error;
 		sector += len >> SECTOR_SHIFT;
@@ -310,15 +310,15 @@ io_error:
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	int err;
 
 	if (PageTransHuge(page))
 		return -ENOTSUPP;
-	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
-	page_endio(page, is_write, err);
+	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+	page_endio(page, op_is_write(op), err);
 	return err;
 }
 
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index bc4ed2ed40a2..e35a234b0a8f 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -55,12 +55,10 @@
 # define __protected_by(x)       __attribute__((require_context(x,1,999,"rdwr")))
 # define __protected_read_by(x)  __attribute__((require_context(x,1,999,"read")))
 # define __protected_write_by(x) __attribute__((require_context(x,1,999,"write")))
-# define __must_hold(x)       __attribute__((context(x,1,1), require_context(x,1,999,"call")))
 #else
 # define __protected_by(x)
 # define __protected_read_by(x)
 # define __protected_write_by(x)
-# define __must_hold(x)
 #endif
 
 /* shared module parameters, defined in drbd_main.c */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index a80809bd3057..ef8212a4b73e 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2103,14 +2103,10 @@ static void drbd_destroy_mempools(void)
 	mempool_exit(&drbd_md_io_page_pool);
 	mempool_exit(&drbd_ee_mempool);
 	mempool_exit(&drbd_request_mempool);
-	if (drbd_ee_cache)
-		kmem_cache_destroy(drbd_ee_cache);
-	if (drbd_request_cache)
-		kmem_cache_destroy(drbd_request_cache);
-	if (drbd_bm_ext_cache)
-		kmem_cache_destroy(drbd_bm_ext_cache);
-	if (drbd_al_ext_cache)
-		kmem_cache_destroy(drbd_al_ext_cache);
+	kmem_cache_destroy(drbd_ee_cache);
+	kmem_cache_destroy(drbd_request_cache);
+	kmem_cache_destroy(drbd_bm_ext_cache);
+	kmem_cache_destroy(drbd_al_ext_cache);
 
 	drbd_ee_cache        = NULL;
 	drbd_request_cache   = NULL;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index be9450f5ad1c..75f6b47169e6 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2674,8 +2674,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 	if (c_min_rate == 0)
 		return false;
 
-	curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
-		      (int)part_stat_read(&disk->part0, sectors[1]) -
+	curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
@@ -2790,6 +2789,7 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 		   then we would do something smarter here than reading
 		   the block... */
 		peer_req->flags |= EE_RS_THIN_REQ;
+		/* fall through */
 	case P_RS_DATA_REQUEST:
 		peer_req->w.cb = w_e_end_rsdata_req;
 		fault_type = DRBD_FAULT_RS_RD;
@@ -2968,6 +2968,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		/* Else fall through to one of the other strategies... */
 		drbd_warn(device, "Discard younger/older primary did not find a decision\n"
 		     "Using discard-least-changes instead\n");
+		/* fall through */
 	case ASB_DISCARD_ZERO_CHG:
 		if (ch_peer == 0 && ch_self == 0) {
 			rv = test_bit(RESOLVE_CONFLICTS, &peer_device->connection->flags)
@@ -2979,6 +2980,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		}
 		if (after_sb_0p == ASB_DISCARD_ZERO_CHG)
 			break;
+		/* else: fall through */
 	case ASB_DISCARD_LEAST_CHG:
 		if	(ch_self < ch_peer)
 			rv = -1;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index a47e4987ee46..19cac36e9737 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -38,7 +38,7 @@ static void _drbd_start_io_acct(struct drbd_device *device, struct drbd_request
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_start_io_acct(q, bio_data_dir(req->master_bio),
+	generic_start_io_acct(q, bio_op(req->master_bio),
 				req->i.size >> 9, &device->vdisk->part0);
 }
 
@@ -47,7 +47,7 @@ static void _drbd_end_io_acct(struct drbd_device *device, struct drbd_request *r
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_end_io_acct(q, bio_data_dir(req->master_bio),
+	generic_end_io_acct(q, bio_op(req->master_bio),
 			    &device->vdisk->part0, req->start_jif);
 }
 
@@ -1244,8 +1244,8 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
 	_drbd_start_io_acct(device, req);
 
 	/* process discards always from our submitter thread */
-	if ((bio_op(bio) & REQ_OP_WRITE_ZEROES) ||
-	    (bio_op(bio) & REQ_OP_DISCARD))
+	if (bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+	    bio_op(bio) == REQ_OP_DISCARD)
 		goto queue_for_submitter_thread;
 
 	if (rw == WRITE && req->private_bio && req->i.size
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 1476cb3439f4..b8f77e83d456 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -282,8 +282,8 @@ void drbd_request_endio(struct bio *bio)
 		what = COMPLETED_OK;
 	}
 
-	bio_put(req->private_bio);
 	req->private_bio = ERR_PTR(blk_status_to_errno(bio->bi_status));
+	bio_put(bio);
 
 	/* not req_mod(), we need irqsave here! */
 	spin_lock_irqsave(&device->resource->req_lock, flags);
@@ -1690,9 +1690,7 @@ void drbd_rs_controller_reset(struct drbd_device *device)
 	atomic_set(&device->rs_sect_in, 0);
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
-	device->rs_last_events =
-		(int)part_stat_read(&disk->part0, sectors[0]) +
-		(int)part_stat_read(&disk->part0, sectors[1]);
+	device->rs_last_events = (int)part_stat_read_accum(&disk->part0, sectors);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 8871b5044d9e..48f622728ce6 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -1461,7 +1461,6 @@ static void setup_rw_floppy(void)
 	int i;
 	int r;
 	int flags;
-	int dflags;
 	unsigned long ready_date;
 	void (*function)(void);
 
@@ -1485,8 +1484,6 @@ static void setup_rw_floppy(void)
 		if (fd_wait_for_completion(ready_date, function))
 			return;
 	}
-	dflags = DRS->flags;
-
 	if ((flags & FD_RAW_READ) || (flags & FD_RAW_WRITE))
 		setup_DMA();
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d6b6f434fd4b..ea9debf59b22 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -690,7 +690,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 			  unsigned int arg)
 {
 	struct file	*file, *old_file;
-	struct inode	*inode;
 	int		error;
 
 	error = -ENXIO;
@@ -711,7 +710,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (error)
 		goto out_putf;
 
-	inode = file->f_mapping->host;
 	old_file = lo->lo_backing_file;
 
 	error = -EINVAL;
@@ -1611,8 +1609,10 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_GET_STATUS64:
 	case LOOP_SET_STATUS64:
 		arg = (unsigned long) compat_ptr(arg);
+		/* fall through */
 	case LOOP_SET_FD:
 	case LOOP_CHANGE_FD:
+	case LOOP_SET_BLOCK_SIZE:
 		err = lo_ioctl(bdev, mode, cmd, arg);
 		break;
 	default:
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index c73626decb46..db253cd5b32a 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2575,8 +2575,7 @@ static int mtip_hw_debugfs_init(struct driver_data *dd)
 
 static void mtip_hw_debugfs_exit(struct driver_data *dd)
 {
-	if (dd->dfs_node)
-		debugfs_remove_recursive(dd->dfs_node);
+	debugfs_remove_recursive(dd->dfs_node);
 }
 
 /*
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 74a05561b620..3fb95c8d9fd8 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -112,12 +112,16 @@ struct nbd_device {
 	struct task_struct *task_setup;
 };
 
+#define NBD_CMD_REQUEUED	1
+
 struct nbd_cmd {
 	struct nbd_device *nbd;
+	struct mutex lock;
 	int index;
 	int cookie;
-	struct completion send_complete;
 	blk_status_t status;
+	unsigned long flags;
+	u32 cmd_cookie;
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -146,6 +150,35 @@ static inline struct device *nbd_to_dev(struct nbd_device *nbd)
 	return disk_to_dev(nbd->disk);
 }
 
+static void nbd_requeue_cmd(struct nbd_cmd *cmd)
+{
+	struct request *req = blk_mq_rq_from_pdu(cmd);
+
+	if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags))
+		blk_mq_requeue_request(req, true);
+}
+
+#define NBD_COOKIE_BITS 32
+
+static u64 nbd_cmd_handle(struct nbd_cmd *cmd)
+{
+	struct request *req = blk_mq_rq_from_pdu(cmd);
+	u32 tag = blk_mq_unique_tag(req);
+	u64 cookie = cmd->cmd_cookie;
+
+	return (cookie << NBD_COOKIE_BITS) | tag;
+}
+
+static u32 nbd_handle_to_tag(u64 handle)
+{
+	return (u32)handle;
+}
+
+static u32 nbd_handle_to_cookie(u64 handle)
+{
+	return (u32)(handle >> NBD_COOKIE_BITS);
+}
+
 static const char *nbdcmd_to_ascii(int cmd)
 {
 	switch (cmd) {
@@ -319,6 +352,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	}
 	config = nbd->config;
 
+	if (!mutex_trylock(&cmd->lock))
+		return BLK_EH_RESET_TIMER;
+
 	if (config->num_connections > 1) {
 		dev_err_ratelimited(nbd_to_dev(nbd),
 				    "Connection timed out, retrying (%d/%d alive)\n",
@@ -343,7 +379,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 					nbd_mark_nsock_dead(nbd, nsock, 1);
 				mutex_unlock(&nsock->tx_lock);
 			}
-			blk_mq_requeue_request(req, true);
+			mutex_unlock(&cmd->lock);
+			nbd_requeue_cmd(cmd);
 			nbd_config_put(nbd);
 			return BLK_EH_DONE;
 		}
@@ -353,6 +390,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	}
 	set_bit(NBD_TIMEDOUT, &config->runtime_flags);
 	cmd->status = BLK_STS_IOERR;
+	mutex_unlock(&cmd->lock);
 	sock_shutdown(nbd);
 	nbd_config_put(nbd);
 done:
@@ -430,9 +468,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	struct iov_iter from;
 	unsigned long size = blk_rq_bytes(req);
 	struct bio *bio;
+	u64 handle;
 	u32 type;
 	u32 nbd_cmd_flags = 0;
-	u32 tag = blk_mq_unique_tag(req);
 	int sent = nsock->sent, skip = 0;
 
 	iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
@@ -474,6 +512,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 			goto send_pages;
 		}
 		iov_iter_advance(&from, sent);
+	} else {
+		cmd->cmd_cookie++;
 	}
 	cmd->index = index;
 	cmd->cookie = nsock->cookie;
@@ -482,7 +522,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
 		request.len = htonl(size);
 	}
-	memcpy(request.handle, &tag, sizeof(tag));
+	handle = nbd_cmd_handle(cmd);
+	memcpy(request.handle, &handle, sizeof(handle));
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
 		req, nbdcmd_to_ascii(type),
@@ -500,6 +541,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 				nsock->pending = req;
 				nsock->sent = sent;
 			}
+			set_bit(NBD_CMD_REQUEUED, &cmd->flags);
 			return BLK_STS_RESOURCE;
 		}
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
@@ -541,6 +583,7 @@ send_pages:
 					 */
 					nsock->pending = req;
 					nsock->sent = sent;
+					set_bit(NBD_CMD_REQUEUED, &cmd->flags);
 					return BLK_STS_RESOURCE;
 				}
 				dev_err(disk_to_dev(nbd->disk),
@@ -573,10 +616,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	struct nbd_reply reply;
 	struct nbd_cmd *cmd;
 	struct request *req = NULL;
+	u64 handle;
 	u16 hwq;
 	u32 tag;
 	struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)};
 	struct iov_iter to;
+	int ret = 0;
 
 	reply.magic = 0;
 	iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
@@ -594,8 +639,8 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		return ERR_PTR(-EPROTO);
 	}
 
-	memcpy(&tag, reply.handle, sizeof(u32));
-
+	memcpy(&handle, reply.handle, sizeof(handle));
+	tag = nbd_handle_to_tag(handle);
 	hwq = blk_mq_unique_tag_to_hwq(tag);
 	if (hwq < nbd->tag_set.nr_hw_queues)
 		req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq],
@@ -606,11 +651,25 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		return ERR_PTR(-ENOENT);
 	}
 	cmd = blk_mq_rq_to_pdu(req);
+
+	mutex_lock(&cmd->lock);
+	if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) {
+		dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n",
+			req, cmd->cmd_cookie, nbd_handle_to_cookie(handle));
+		ret = -ENOENT;
+		goto out;
+	}
+	if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) {
+		dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n",
+			req);
+		ret = -ENOENT;
+		goto out;
+	}
 	if (ntohl(reply.error)) {
 		dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
 			ntohl(reply.error));
 		cmd->status = BLK_STS_IOERR;
-		return cmd;
+		goto out;
 	}
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req);
@@ -635,18 +694,18 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 				if (nbd_disconnected(config) ||
 				    config->num_connections <= 1) {
 					cmd->status = BLK_STS_IOERR;
-					return cmd;
+					goto out;
 				}
-				return ERR_PTR(-EIO);
+				ret = -EIO;
+				goto out;
 			}
 			dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
 				req, bvec.bv_len);
 		}
-	} else {
-		/* See the comment in nbd_queue_rq. */
-		wait_for_completion(&cmd->send_complete);
 	}
-	return cmd;
+out:
+	mutex_unlock(&cmd->lock);
+	return ret ? ERR_PTR(ret) : cmd;
 }
 
 static void recv_work(struct work_struct *work)
@@ -805,7 +864,7 @@ again:
 	 */
 	blk_mq_start_request(req);
 	if (unlikely(nsock->pending && nsock->pending != req)) {
-		blk_mq_requeue_request(req, true);
+		nbd_requeue_cmd(cmd);
 		ret = 0;
 		goto out;
 	}
@@ -818,7 +877,7 @@ again:
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Request send failed, requeueing\n");
 		nbd_mark_nsock_dead(nbd, nsock, 1);
-		blk_mq_requeue_request(req, true);
+		nbd_requeue_cmd(cmd);
 		ret = 0;
 	}
 out:
@@ -842,7 +901,8 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * that the server is misbehaving (or there was an error) before we're
 	 * done sending everything over the wire.
 	 */
-	init_completion(&cmd->send_complete);
+	mutex_lock(&cmd->lock);
+	clear_bit(NBD_CMD_REQUEUED, &cmd->flags);
 
 	/* We can be called directly from the user space process, which means we
 	 * could possibly have signals pending so our sendmsg will fail.  In
@@ -854,7 +914,7 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 		ret = BLK_STS_IOERR;
 	else if (!ret)
 		ret = BLK_STS_OK;
-	complete(&cmd->send_complete);
+	mutex_unlock(&cmd->lock);
 
 	return ret;
 }
@@ -1460,6 +1520,8 @@ static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq,
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	cmd->nbd = set->driver_data;
+	cmd->flags = 0;
+	mutex_init(&cmd->lock);
 	return 0;
 }
 
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
new file mode 100644
index 000000000000..d81781f22dba
--- /dev/null
+++ b/drivers/block/null_blk.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BLK_NULL_BLK_H
+#define __BLK_NULL_BLK_H
+
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/blk-mq.h>
+#include <linux/hrtimer.h>
+#include <linux/configfs.h>
+#include <linux/badblocks.h>
+#include <linux/fault-inject.h>
+
+struct nullb_cmd {
+	struct list_head list;
+	struct llist_node ll_list;
+	struct __call_single_data csd;
+	struct request *rq;
+	struct bio *bio;
+	unsigned int tag;
+	blk_status_t error;
+	struct nullb_queue *nq;
+	struct hrtimer timer;
+};
+
+struct nullb_queue {
+	unsigned long *tag_map;
+	wait_queue_head_t wait;
+	unsigned int queue_depth;
+	struct nullb_device *dev;
+	unsigned int requeue_selection;
+
+	struct nullb_cmd *cmds;
+};
+
+struct nullb_device {
+	struct nullb *nullb;
+	struct config_item item;
+	struct radix_tree_root data; /* data stored in the disk */
+	struct radix_tree_root cache; /* disk cache data */
+	unsigned long flags; /* device flags */
+	unsigned int curr_cache;
+	struct badblocks badblocks;
+
+	unsigned int nr_zones;
+	struct blk_zone *zones;
+	sector_t zone_size_sects;
+
+	unsigned long size; /* device size in MB */
+	unsigned long completion_nsec; /* time in ns to complete a request */
+	unsigned long cache_size; /* disk cache size in MB */
+	unsigned long zone_size; /* zone size in MB if device is zoned */
+	unsigned int submit_queues; /* number of submission queues */
+	unsigned int home_node; /* home node for the device */
+	unsigned int queue_mode; /* block interface */
+	unsigned int blocksize; /* block size */
+	unsigned int irqmode; /* IRQ completion handler */
+	unsigned int hw_queue_depth; /* queue depth */
+	unsigned int index; /* index of the disk, only valid with a disk */
+	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
+	bool blocking; /* blocking blk-mq device */
+	bool use_per_node_hctx; /* use per-node allocation for hardware context */
+	bool power; /* power on/off the device */
+	bool memory_backed; /* if data is stored in memory */
+	bool discard; /* if support discard */
+	bool zoned; /* if device is zoned */
+};
+
+struct nullb {
+	struct nullb_device *dev;
+	struct list_head list;
+	unsigned int index;
+	struct request_queue *q;
+	struct gendisk *disk;
+	struct blk_mq_tag_set *tag_set;
+	struct blk_mq_tag_set __tag_set;
+	unsigned int queue_depth;
+	atomic_long_t cur_bytes;
+	struct hrtimer bw_timer;
+	unsigned long cache_flush_pos;
+	spinlock_t lock;
+
+	struct nullb_queue *queues;
+	unsigned int nr_queues;
+	char disk_name[DISK_NAME_LEN];
+};
+
+#ifdef CONFIG_BLK_DEV_ZONED
+int null_zone_init(struct nullb_device *dev);
+void null_zone_exit(struct nullb_device *dev);
+blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd);
+void null_zone_write(struct nullb_cmd *cmd);
+void null_zone_reset(struct nullb_cmd *cmd);
+#else
+static inline int null_zone_init(struct nullb_device *dev)
+{
+	return -EINVAL;
+}
+static inline void null_zone_exit(struct nullb_device *dev) {}
+static inline blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd)
+{
+	return BLK_STS_NOTSUPP;
+}
+static inline void null_zone_write(struct nullb_cmd *cmd) {}
+static inline void null_zone_reset(struct nullb_cmd *cmd) {}
+#endif /* CONFIG_BLK_DEV_ZONED */
+#endif /* __NULL_BLK_H */
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk_main.c
index 042c778e5a4e..6127e3ff7b4b 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk_main.c
@@ -7,14 +7,8 @@
 #include <linux/moduleparam.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
-#include <linux/blkdev.h>
 #include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/blk-mq.h>
-#include <linux/hrtimer.h>
-#include <linux/configfs.h>
-#include <linux/badblocks.h>
-#include <linux/fault-inject.h>
+#include "null_blk.h"
 
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
@@ -35,28 +29,6 @@ static inline u64 mb_per_tick(int mbps)
 	return (1 << 20) / TICKS_PER_SEC * ((u64) mbps);
 }
 
-struct nullb_cmd {
-	struct list_head list;
-	struct llist_node ll_list;
-	struct __call_single_data csd;
-	struct request *rq;
-	struct bio *bio;
-	unsigned int tag;
-	blk_status_t error;
-	struct nullb_queue *nq;
-	struct hrtimer timer;
-};
-
-struct nullb_queue {
-	unsigned long *tag_map;
-	wait_queue_head_t wait;
-	unsigned int queue_depth;
-	struct nullb_device *dev;
-	unsigned int requeue_selection;
-
-	struct nullb_cmd *cmds;
-};
-
 /*
  * Status flags for nullb_device.
  *
@@ -92,52 +64,6 @@ struct nullb_page {
 #define NULLB_PAGE_LOCK (MAP_SZ - 1)
 #define NULLB_PAGE_FREE (MAP_SZ - 2)
 
-struct nullb_device {
-	struct nullb *nullb;
-	struct config_item item;
-	struct radix_tree_root data; /* data stored in the disk */
-	struct radix_tree_root cache; /* disk cache data */
-	unsigned long flags; /* device flags */
-	unsigned int curr_cache;
-	struct badblocks badblocks;
-
-	unsigned long size; /* device size in MB */
-	unsigned long completion_nsec; /* time in ns to complete a request */
-	unsigned long cache_size; /* disk cache size in MB */
-	unsigned int submit_queues; /* number of submission queues */
-	unsigned int home_node; /* home node for the device */
-	unsigned int queue_mode; /* block interface */
-	unsigned int blocksize; /* block size */
-	unsigned int irqmode; /* IRQ completion handler */
-	unsigned int hw_queue_depth; /* queue depth */
-	unsigned int index; /* index of the disk, only valid with a disk */
-	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
-	bool blocking; /* blocking blk-mq device */
-	bool use_per_node_hctx; /* use per-node allocation for hardware context */
-	bool power; /* power on/off the device */
-	bool memory_backed; /* if data is stored in memory */
-	bool discard; /* if support discard */
-};
-
-struct nullb {
-	struct nullb_device *dev;
-	struct list_head list;
-	unsigned int index;
-	struct request_queue *q;
-	struct gendisk *disk;
-	struct blk_mq_tag_set *tag_set;
-	struct blk_mq_tag_set __tag_set;
-	unsigned int queue_depth;
-	atomic_long_t cur_bytes;
-	struct hrtimer bw_timer;
-	unsigned long cache_flush_pos;
-	spinlock_t lock;
-
-	struct nullb_queue *queues;
-	unsigned int nr_queues;
-	char disk_name[DISK_NAME_LEN];
-};
-
 static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
@@ -254,6 +180,14 @@ static bool g_use_per_node_hctx;
 module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
 MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
 
+static bool g_zoned;
+module_param_named(zoned, g_zoned, bool, S_IRUGO);
+MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false");
+
+static unsigned long g_zone_size = 256;
+module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
+MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -357,6 +291,8 @@ NULLB_DEVICE_ATTR(memory_backed, bool);
 NULLB_DEVICE_ATTR(discard, bool);
 NULLB_DEVICE_ATTR(mbps, uint);
 NULLB_DEVICE_ATTR(cache_size, ulong);
+NULLB_DEVICE_ATTR(zoned, bool);
+NULLB_DEVICE_ATTR(zone_size, ulong);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -390,6 +326,7 @@ static ssize_t nullb_device_power_store(struct config_item *item,
 		null_del_dev(dev->nullb);
 		mutex_unlock(&lock);
 		clear_bit(NULLB_DEV_FL_UP, &dev->flags);
+		clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 	}
 
 	return count;
@@ -468,6 +405,8 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_mbps,
 	&nullb_device_attr_cache_size,
 	&nullb_device_attr_badblocks,
+	&nullb_device_attr_zoned,
+	&nullb_device_attr_zone_size,
 	NULL,
 };
 
@@ -520,7 +459,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks\n");
+	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -579,6 +518,8 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->hw_queue_depth = g_hw_queue_depth;
 	dev->blocking = g_blocking;
 	dev->use_per_node_hctx = g_use_per_node_hctx;
+	dev->zoned = g_zoned;
+	dev->zone_size = g_zone_size;
 	return dev;
 }
 
@@ -587,6 +528,7 @@ static void null_free_dev(struct nullb_device *dev)
 	if (!dev)
 		return;
 
+	null_zone_exit(dev);
 	badblocks_exit(&dev->badblocks);
 	kfree(dev);
 }
@@ -862,7 +804,9 @@ static struct nullb_page *null_lookup_page(struct nullb *nullb,
 }
 
 static struct nullb_page *null_insert_page(struct nullb *nullb,
-	sector_t sector, bool ignore_cache)
+					   sector_t sector, bool ignore_cache)
+	__releases(&nullb->lock)
+	__acquires(&nullb->lock)
 {
 	u64 idx;
 	struct nullb_page *t_page;
@@ -1219,6 +1163,11 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 	struct nullb *nullb = dev->nullb;
 	int err = 0;
 
+	if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) {
+		cmd->error = null_zone_report(nullb, cmd);
+		goto out;
+	}
+
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
 		struct request *rq = cmd->rq;
 
@@ -1283,6 +1232,13 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 		}
 	}
 	cmd->error = errno_to_blk_status(err);
+
+	if (!cmd->error && dev->zoned) {
+		if (req_op(cmd->rq) == REQ_OP_WRITE)
+			null_zone_write(cmd);
+		else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET)
+			null_zone_reset(cmd);
+	}
 out:
 	/* Complete IO by inline, softirq or timer */
 	switch (dev->irqmode) {
@@ -1810,6 +1766,15 @@ static int null_add_dev(struct nullb_device *dev)
 		blk_queue_flush_queueable(nullb->q, true);
 	}
 
+	if (dev->zoned) {
+		rv = null_zone_init(dev);
+		if (rv)
+			goto out_cleanup_blk_queue;
+
+		blk_queue_chunk_sectors(nullb->q, dev->zone_size_sects);
+		nullb->q->limits.zoned = BLK_ZONED_HM;
+	}
+
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q);
@@ -1828,13 +1793,16 @@ static int null_add_dev(struct nullb_device *dev)
 
 	rv = null_gendisk_register(nullb);
 	if (rv)
-		goto out_cleanup_blk_queue;
+		goto out_cleanup_zone;
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
 	mutex_unlock(&lock);
 
 	return 0;
+out_cleanup_zone:
+	if (dev->zoned)
+		null_zone_exit(dev);
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
@@ -1861,6 +1829,11 @@ static int __init null_init(void)
 		g_bs = PAGE_SIZE;
 	}
 
+	if (!is_power_of_2(g_zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
 	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
 		if (g_submit_queues != nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.\n",
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
new file mode 100644
index 000000000000..a979ca00d7be
--- /dev/null
+++ b/drivers/block/null_blk_zoned.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/vmalloc.h>
+#include "null_blk.h"
+
+/* zone_size in MBs to sectors. */
+#define ZONE_SIZE_SHIFT		11
+
+static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
+{
+	return sect >> ilog2(dev->zone_size_sects);
+}
+
+int null_zone_init(struct nullb_device *dev)
+{
+	sector_t dev_size = (sector_t)dev->size * 1024 * 1024;
+	sector_t sector = 0;
+	unsigned int i;
+
+	if (!is_power_of_2(dev->zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
+	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
+	dev->nr_zones = dev_size >>
+				(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
+	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct blk_zone),
+			GFP_KERNEL | __GFP_ZERO);
+	if (!dev->zones)
+		return -ENOMEM;
+
+	for (i = 0; i < dev->nr_zones; i++) {
+		struct blk_zone *zone = &dev->zones[i];
+
+		zone->start = zone->wp = sector;
+		zone->len = dev->zone_size_sects;
+		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
+		zone->cond = BLK_ZONE_COND_EMPTY;
+
+		sector += dev->zone_size_sects;
+	}
+
+	return 0;
+}
+
+void null_zone_exit(struct nullb_device *dev)
+{
+	kvfree(dev->zones);
+}
+
+static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq,
+			      unsigned int zno, unsigned int nr_zones)
+{
+	struct blk_zone_report_hdr *hdr = NULL;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	void *addr;
+	unsigned int zones_to_cpy;
+
+	bio_for_each_segment(bvec, rq->bio, iter) {
+		addr = kmap_atomic(bvec.bv_page);
+
+		zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone);
+
+		if (!hdr) {
+			hdr = (struct blk_zone_report_hdr *)addr;
+			hdr->nr_zones = nr_zones;
+			zones_to_cpy--;
+			addr += sizeof(struct blk_zone_report_hdr);
+		}
+
+		zones_to_cpy = min_t(unsigned int, zones_to_cpy, nr_zones);
+
+		memcpy(addr, &dev->zones[zno],
+				zones_to_cpy * sizeof(struct blk_zone));
+
+		kunmap_atomic(addr);
+
+		nr_zones -= zones_to_cpy;
+		zno += zones_to_cpy;
+
+		if (!nr_zones)
+			break;
+	}
+}
+
+blk_status_t null_zone_report(struct nullb *nullb,
+				     struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = nullb->dev;
+	struct request *rq = cmd->rq;
+	unsigned int zno = null_zone_no(dev, blk_rq_pos(rq));
+	unsigned int nr_zones = dev->nr_zones - zno;
+	unsigned int max_zones = (blk_rq_bytes(rq) /
+					sizeof(struct blk_zone)) - 1;
+
+	nr_zones = min_t(unsigned int, nr_zones, max_zones);
+
+	null_zone_fill_rq(nullb->dev, rq, zno, nr_zones);
+
+	return BLK_STS_OK;
+}
+
+void null_zone_write(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct request *rq = cmd->rq;
+	sector_t sector = blk_rq_pos(rq);
+	unsigned int rq_sectors = blk_rq_sectors(rq);
+	unsigned int zno = null_zone_no(dev, sector);
+	struct blk_zone *zone = &dev->zones[zno];
+
+	switch (zone->cond) {
+	case BLK_ZONE_COND_FULL:
+		/* Cannot write to a full zone */
+		cmd->error = BLK_STS_IOERR;
+		break;
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_IMP_OPEN:
+		/* Writes must be at the write pointer position */
+		if (blk_rq_pos(rq) != zone->wp) {
+			cmd->error = BLK_STS_IOERR;
+			break;
+		}
+
+		if (zone->cond == BLK_ZONE_COND_EMPTY)
+			zone->cond = BLK_ZONE_COND_IMP_OPEN;
+
+		zone->wp += rq_sectors;
+		if (zone->wp == zone->start + zone->len)
+			zone->cond = BLK_ZONE_COND_FULL;
+		break;
+	default:
+		/* Invalid zone condition */
+		cmd->error = BLK_STS_IOERR;
+		break;
+	}
+}
+
+void null_zone_reset(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct request *rq = cmd->rq;
+	unsigned int zno = null_zone_no(dev, blk_rq_pos(rq));
+	struct blk_zone *zone = &dev->zones[zno];
+
+	zone->cond = BLK_ZONE_COND_EMPTY;
+	zone->wp = zone->start;
+}
diff --git a/drivers/block/paride/bpck.c b/drivers/block/paride/bpck.c
index 4f27e7392e38..f5f63ca2889d 100644
--- a/drivers/block/paride/bpck.c
+++ b/drivers/block/paride/bpck.c
@@ -347,7 +347,7 @@ static int bpck_test_proto( PIA *pi, char * scratch, int verbose )
 
 static void bpck_read_eeprom ( PIA *pi, char * buf )
 
-{       int i,j,k,n,p,v,f, om, od;
+{       int i, j, k, p, v, f, om, od;
 
 	bpck_force_spp(pi);
 
@@ -356,7 +356,6 @@ static void bpck_read_eeprom ( PIA *pi, char * buf )
 
 	bpck_connect(pi);
 	
-	n = 0;
 	WR(4,0);
 	for (i=0;i<64;i++) {
 	    WR(6,8);  
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 8961b190e256..7cf947586fe4 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -426,6 +426,7 @@ static void run_fsm(void)
 				pd_claimed = 1;
 				if (!pi_schedule_claimed(pi_current, run_fsm))
 					return;
+				/* fall through */
 			case 1:
 				pd_claimed = 2;
 				pi_current->proto->connect(pi_current);
@@ -445,6 +446,7 @@ static void run_fsm(void)
 				spin_unlock_irqrestore(&pd_lock, saved_flags);
 				if (stop)
 					return;
+				/* fall through */
 			case Hold:
 				schedule_fsm();
 				return;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index b3f83cd96f33..e285413d4a75 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -67,7 +67,7 @@
 #include <scsi/scsi.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
-
+#include <linux/nospec.h>
 #include <linux/uaccess.h>
 
 #define DRIVER_NAME	"pktcdvd"
@@ -748,13 +748,13 @@ static const char *sense_key_string(__u8 index)
 static void pkt_dump_sense(struct pktcdvd_device *pd,
 			   struct packet_command *cgc)
 {
-	struct request_sense *sense = cgc->sense;
+	struct scsi_sense_hdr *sshdr = cgc->sshdr;
 
-	if (sense)
+	if (sshdr)
 		pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
 			CDROM_PACKET_SIZE, cgc->cmd,
-			sense->sense_key, sense->asc, sense->ascq,
-			sense_key_string(sense->sense_key));
+			sshdr->sense_key, sshdr->asc, sshdr->ascq,
+			sense_key_string(sshdr->sense_key));
 	else
 		pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
 }
@@ -787,18 +787,19 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
 				unsigned write_speed, unsigned read_speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int ret;
 
 	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_SET_SPEED;
 	cgc.cmd[2] = (read_speed >> 8) & 0xff;
 	cgc.cmd[3] = read_speed & 0xff;
 	cgc.cmd[4] = (write_speed >> 8) & 0xff;
 	cgc.cmd[5] = write_speed & 0xff;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		pkt_dump_sense(pd, &cgc);
 
 	return ret;
@@ -1562,7 +1563,8 @@ static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
 	cgc.cmd[8] = cgc.buflen = 2;
 	cgc.quiet = 1;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		return ret;
 
 	/* not all drives have the same disc_info length, so requeue
@@ -1591,7 +1593,8 @@ static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type,
 	cgc.cmd[8] = 8;
 	cgc.quiet = 1;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		return ret;
 
 	cgc.buflen = be16_to_cpu(ti->track_information_length) +
@@ -1612,17 +1615,20 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
 	__u32 last_track;
 	int ret = -1;
 
-	if ((ret = pkt_get_disc_info(pd, &di)))
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret)
 		return ret;
 
 	last_track = (di.last_track_msb << 8) | di.last_track_lsb;
-	if ((ret = pkt_get_track_info(pd, last_track, 1, &ti)))
+	ret = pkt_get_track_info(pd, last_track, 1, &ti);
+	if (ret)
 		return ret;
 
 	/* if this track is blank, try the previous. */
 	if (ti.blank) {
 		last_track--;
-		if ((ret = pkt_get_track_info(pd, last_track, 1, &ti)))
+		ret = pkt_get_track_info(pd, last_track, 1, &ti);
+		if (ret)
 			return ret;
 	}
 
@@ -1645,7 +1651,7 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
 static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	write_param_page *wp;
 	char buffer[128];
 	int ret, size;
@@ -1656,8 +1662,9 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 
 	memset(buffer, 0, sizeof(buffer));
 	init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
-	cgc.sense = &sense;
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
+	cgc.sshdr = &sshdr;
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1671,8 +1678,9 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	 * now get it all
 	 */
 	init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
-	cgc.sense = &sense;
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
+	cgc.sshdr = &sshdr;
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1714,7 +1722,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
 
 	cgc.buflen = cgc.cmd[8] = size;
-	if ((ret = pkt_mode_select(pd, &cgc))) {
+	ret = pkt_mode_select(pd, &cgc);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1819,7 +1828,8 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	memset(&di, 0, sizeof(disc_information));
 	memset(&ti, 0, sizeof(track_information));
 
-	if ((ret = pkt_get_disc_info(pd, &di))) {
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret) {
 		pkt_err(pd, "failed get_disc\n");
 		return ret;
 	}
@@ -1830,7 +1840,8 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;
 
 	track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
-	if ((ret = pkt_get_track_info(pd, track, 1, &ti))) {
+	ret = pkt_get_track_info(pd, track, 1, &ti);
+	if (ret) {
 		pkt_err(pd, "failed get_track\n");
 		return ret;
 	}
@@ -1905,12 +1916,12 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 						int set)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[64];
 	int ret;
 
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.buflen = pd->mode_offset + 12;
 
 	/*
@@ -1918,7 +1929,8 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 	 */
 	cgc.quiet = 1;
 
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0)))
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
+	if (ret)
 		return ret;
 
 	buf[pd->mode_offset + 10] |= (!!set << 2);
@@ -1950,14 +1962,14 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
 						unsigned *write_speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[256+18];
 	unsigned char *cap_buf;
 	int ret, offset;
 
 	cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 
 	ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
 	if (ret) {
@@ -2011,13 +2023,13 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 						unsigned *speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[64];
 	unsigned int size, st, sp;
 	int ret;
 
 	init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
 	cgc.cmd[1] = 2;
 	cgc.cmd[2] = 4; /* READ ATIP */
@@ -2032,7 +2044,7 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 		size = sizeof(buf);
 
 	init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
 	cgc.cmd[1] = 2;
 	cgc.cmd[2] = 4;
@@ -2083,17 +2095,18 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int ret;
 
 	pkt_dbg(2, pd, "Performing OPC\n");
 
 	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.timeout = 60*HZ;
 	cgc.cmd[0] = GPCMD_SEND_OPC;
 	cgc.cmd[1] = 1;
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		pkt_dump_sense(pd, &cgc);
 	return ret;
 }
@@ -2103,19 +2116,22 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 	int ret;
 	unsigned int write_speed, media_write_speed, read_speed;
 
-	if ((ret = pkt_probe_settings(pd))) {
+	ret = pkt_probe_settings(pd);
+	if (ret) {
 		pkt_dbg(2, pd, "failed probe\n");
 		return ret;
 	}
 
-	if ((ret = pkt_set_write_settings(pd))) {
+	ret = pkt_set_write_settings(pd);
+	if (ret) {
 		pkt_dbg(1, pd, "failed saving write settings\n");
 		return -EIO;
 	}
 
 	pkt_write_caching(pd, USE_WCACHING);
 
-	if ((ret = pkt_get_max_speed(pd, &write_speed)))
+	ret = pkt_get_max_speed(pd, &write_speed);
+	if (ret)
 		write_speed = 16 * 177;
 	switch (pd->mmc3_profile) {
 		case 0x13: /* DVD-RW */
@@ -2124,7 +2140,8 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 			pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
 			break;
 		default:
-			if ((ret = pkt_media_speed(pd, &media_write_speed)))
+			ret = pkt_media_speed(pd, &media_write_speed);
+			if (ret)
 				media_write_speed = 16;
 			write_speed = min(write_speed, media_write_speed * 177);
 			pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
@@ -2132,14 +2149,16 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 	}
 	read_speed = write_speed;
 
-	if ((ret = pkt_set_speed(pd, write_speed, read_speed))) {
+	ret = pkt_set_speed(pd, write_speed, read_speed);
+	if (ret) {
 		pkt_dbg(1, pd, "couldn't set write speed\n");
 		return -EIO;
 	}
 	pd->write_speed = write_speed;
 	pd->read_speed = read_speed;
 
-	if ((ret = pkt_perform_opc(pd))) {
+	ret = pkt_perform_opc(pd);
+	if (ret) {
 		pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
 	}
 
@@ -2161,10 +2180,12 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 	 * so bdget() can't fail.
 	 */
 	bdget(pd->bdev->bd_dev);
-	if ((ret = blkdev_get(pd->bdev, FMODE_READ | FMODE_EXCL, pd)))
+	ret = blkdev_get(pd->bdev, FMODE_READ | FMODE_EXCL, pd);
+	if (ret)
 		goto out;
 
-	if ((ret = pkt_get_last_written(pd, &lba))) {
+	ret = pkt_get_last_written(pd, &lba);
+	if (ret) {
 		pkt_err(pd, "pkt_get_last_written failed\n");
 		goto out_putdev;
 	}
@@ -2175,7 +2196,8 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 
 	q = bdev_get_queue(pd->bdev);
 	if (write) {
-		if ((ret = pkt_open_write(pd)))
+		ret = pkt_open_write(pd);
+		if (ret)
 			goto out_putdev;
 		/*
 		 * Some CDRW drives can not handle writes larger than one packet,
@@ -2190,7 +2212,8 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 		clear_bit(PACKET_WRITABLE, &pd->flags);
 	}
 
-	if ((ret = pkt_set_segment_merging(pd, q)))
+	ret = pkt_set_segment_merging(pd, q);
+	if (ret)
 		goto out_putdev;
 
 	if (write) {
@@ -2231,6 +2254,8 @@ static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
 {
 	if (dev_minor >= MAX_WRITERS)
 		return NULL;
+
+	dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
 	return pkt_devs[dev_minor];
 }
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index fa0729c1e776..d81c653b9bf6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -61,7 +61,7 @@ static int atomic_inc_return_safe(atomic_t *v)
 {
 	unsigned int counter;
 
-	counter = (unsigned int)__atomic_add_unless(v, 1, 0);
+	counter = (unsigned int)atomic_fetch_add_unless(v, 1, 0);
 	if (counter <= (unsigned int)INT_MAX)
 		return (int)counter;
 
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index dddb3f2490b6..1a92f9e65937 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -112,7 +112,7 @@ static const struct block_device_operations rsxx_fops = {
 
 static void disk_stats_start(struct rsxx_cardinfo *card, struct bio *bio)
 {
-	generic_start_io_acct(card->queue, bio_data_dir(bio), bio_sectors(bio),
+	generic_start_io_acct(card->queue, bio_op(bio), bio_sectors(bio),
 			     &card->gendisk->part0);
 }
 
@@ -120,8 +120,8 @@ static void disk_stats_complete(struct rsxx_cardinfo *card,
 				struct bio *bio,
 				unsigned long start_time)
 {
-	generic_end_io_acct(card->queue, bio_data_dir(bio),
-				&card->gendisk->part0, start_time);
+	generic_end_io_acct(card->queue, bio_op(bio),
+			    &card->gendisk->part0, start_time);
 }
 
 static void bio_dma_done_cb(struct rsxx_cardinfo *card,
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index bc7aea6d7b7c..87b9e7fbf062 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -657,8 +657,8 @@ static bool skd_preop_sg_list(struct skd_device *skdev,
 
 	if (unlikely(skdev->dbg_level > 1)) {
 		dev_dbg(&skdev->pdev->dev,
-			"skreq=%x sksg_list=%p sksg_dma=%llx\n",
-			skreq->id, skreq->sksg_list, skreq->sksg_dma_address);
+			"skreq=%x sksg_list=%p sksg_dma=%pad\n",
+			skreq->id, skreq->sksg_list, &skreq->sksg_dma_address);
 		for (i = 0; i < n_sg; i++) {
 			struct fit_sg_descriptor *sgd = &skreq->sksg_list[i];
 
@@ -1190,8 +1190,8 @@ static void skd_send_fitmsg(struct skd_device *skdev,
 {
 	u64 qcmd;
 
-	dev_dbg(&skdev->pdev->dev, "dma address 0x%llx, busy=%d\n",
-		skmsg->mb_dma_address, skd_in_flight(skdev));
+	dev_dbg(&skdev->pdev->dev, "dma address %pad, busy=%d\n",
+		&skmsg->mb_dma_address, skd_in_flight(skdev));
 	dev_dbg(&skdev->pdev->dev, "msg_buf %p\n", skmsg->msg_buf);
 
 	qcmd = skmsg->mb_dma_address;
@@ -1250,9 +1250,9 @@ static void skd_send_special_fitmsg(struct skd_device *skdev,
 		}
 
 		dev_dbg(&skdev->pdev->dev,
-			"skspcl=%p id=%04x sksg_list=%p sksg_dma=%llx\n",
+			"skspcl=%p id=%04x sksg_list=%p sksg_dma=%pad\n",
 			skspcl, skspcl->req.id, skspcl->req.sksg_list,
-			skspcl->req.sksg_dma_address);
+			&skspcl->req.sksg_dma_address);
 		for (i = 0; i < skspcl->req.n_sg; i++) {
 			struct fit_sg_descriptor *sgd =
 				&skspcl->req.sksg_list[i];
@@ -2685,8 +2685,8 @@ static int skd_cons_skmsg(struct skd_device *skdev)
 
 		WARN(((uintptr_t)skmsg->msg_buf | skmsg->mb_dma_address) &
 		     (FIT_QCMD_ALIGN - 1),
-		     "not aligned: msg_buf %p mb_dma_address %#llx\n",
-		     skmsg->msg_buf, skmsg->mb_dma_address);
+		     "not aligned: msg_buf %p mb_dma_address %pad\n",
+		     skmsg->msg_buf, &skmsg->mb_dma_address);
 		memset(skmsg->msg_buf, 0, SKD_N_FITMSG_BYTES);
 	}
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index b5cedccb5d7d..8986adab9bf5 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -251,14 +251,9 @@ static DEFINE_SPINLOCK(minor_lock);
 #define GRANTS_PER_INDIRECT_FRAME \
 	(XEN_PAGE_SIZE / sizeof(struct blkif_request_segment))
 
-#define PSEGS_PER_INDIRECT_FRAME	\
-	(GRANTS_INDIRECT_FRAME / GRANTS_PSEGS)
-
 #define INDIRECT_GREFS(_grants)		\
 	DIV_ROUND_UP(_grants, GRANTS_PER_INDIRECT_FRAME)
 
-#define GREFS(_psegs)	((_psegs) * GRANTS_PER_PSEG)
-
 static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo);
 static void blkfront_gather_backend_features(struct blkfront_info *info);
 static int negotiate_mq(struct blkfront_info *info);
@@ -1441,7 +1436,7 @@ static bool blkif_completion(unsigned long *id,
 
 		/* Wait the second response if not yet here. */
 		if (s2->status == REQ_WAITING)
-			return 0;
+			return false;
 
 		bret->status = blkif_get_final_status(s->status,
 						      s2->status);
@@ -1542,7 +1537,7 @@ static bool blkif_completion(unsigned long *id,
 		}
 	}
 
-	return 1;
+	return true;
 }
 
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 7436b2d27fa3..c7acf74253a1 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -298,7 +298,8 @@ static void reset_bdev(struct zram *zram)
 	zram->backing_dev = NULL;
 	zram->old_block_size = 0;
 	zram->bdev = NULL;
-
+	zram->disk->queue->backing_dev_info->capabilities |=
+				BDI_CAP_SYNCHRONOUS_IO;
 	kvfree(zram->bitmap);
 	zram->bitmap = NULL;
 }
@@ -400,6 +401,18 @@ static ssize_t backing_dev_store(struct device *dev,
 	zram->backing_dev = backing_dev;
 	zram->bitmap = bitmap;
 	zram->nr_pages = nr_pages;
+	/*
+	 * With writeback feature, zram does asynchronous IO so it's no longer
+	 * synchronous device so let's remove synchronous io flag. Othewise,
+	 * upper layer(e.g., swap) could wait IO completion rather than
+	 * (submit and return), which will cause system sluggish.
+	 * Furthermore, when the IO function returns(e.g., swap_readpage),
+	 * upper layer expects IO was done so it could deallocate the page
+	 * freely but in fact, IO is going on so finally could cause
+	 * use-after-free when the IO is really done.
+	 */
+	zram->disk->queue->backing_dev_info->capabilities &=
+			~BDI_CAP_SYNCHRONOUS_IO;
 	up_write(&zram->init_lock);
 
 	pr_info("setup backing device %s\n", file_name);
@@ -1274,17 +1287,16 @@ static void zram_bio_discard(struct zram *zram, u32 index,
  * Returns 1 if IO request was successfully submitted.
  */
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, bool is_write, struct bio *bio)
+			int offset, unsigned int op, struct bio *bio)
 {
 	unsigned long start_time = jiffies;
-	int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
 	struct request_queue *q = zram->disk->queue;
 	int ret;
 
-	generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT,
+	generic_start_io_acct(q, op, bvec->bv_len >> SECTOR_SHIFT,
 			&zram->disk->part0);
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		atomic64_inc(&zram->stats.num_reads);
 		ret = zram_bvec_read(zram, bvec, index, offset, bio);
 		flush_dcache_page(bvec->bv_page);
@@ -1293,14 +1305,14 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 		ret = zram_bvec_write(zram, bvec, index, offset, bio);
 	}
 
-	generic_end_io_acct(q, rw_acct, &zram->disk->part0, start_time);
+	generic_end_io_acct(q, op, &zram->disk->part0, start_time);
 
 	zram_slot_lock(zram, index);
 	zram_accessed(zram, index);
 	zram_slot_unlock(zram, index);
 
 	if (unlikely(ret < 0)) {
-		if (!is_write)
+		if (!op_is_write(op))
 			atomic64_inc(&zram->stats.failed_reads);
 		else
 			atomic64_inc(&zram->stats.failed_writes);
@@ -1338,7 +1350,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
 							unwritten);
 			if (zram_bvec_rw(zram, &bv, index, offset,
-					op_is_write(bio_op(bio)), bio) < 0)
+					 bio_op(bio), bio) < 0)
 				goto out;
 
 			bv.bv_offset += bv.bv_len;
@@ -1390,7 +1402,7 @@ static void zram_slot_free_notify(struct block_device *bdev,
 }
 
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	int offset, ret;
 	u32 index;
@@ -1414,7 +1426,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_len = PAGE_SIZE;
 	bv.bv_offset = 0;
 
-	ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
+	ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL);
 out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
@@ -1429,7 +1441,7 @@ out:
 
 	switch (ret) {
 	case 0:
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 		break;
 	case 1:
 		ret = 0;
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 1cc29629d238..80d60f43db56 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -169,9 +169,9 @@ static int sysc_get_clocks(struct sysc *ddata)
 	const char *name;
 	int nr_fck = 0, nr_ick = 0, i, error = 0;
 
-	ddata->clock_roles = devm_kzalloc(ddata->dev,
-					  sizeof(*ddata->clock_roles) *
+	ddata->clock_roles = devm_kcalloc(ddata->dev,
 					  SYSC_MAX_CLOCKS,
+					  sizeof(*ddata->clock_roles),
 					  GFP_KERNEL);
 	if (!ddata->clock_roles)
 		return -ENOMEM;
@@ -200,8 +200,8 @@ static int sysc_get_clocks(struct sysc *ddata)
 		return -EINVAL;
 	}
 
-	ddata->clocks = devm_kzalloc(ddata->dev,
-				     sizeof(*ddata->clocks) * ddata->nr_clocks,
+	ddata->clocks = devm_kcalloc(ddata->dev,
+				     ddata->nr_clocks, sizeof(*ddata->clocks),
 				     GFP_KERNEL);
 	if (!ddata->clocks)
 		return -ENOMEM;
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index a78b8e7085e9..113fc6edb2b0 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -282,6 +282,7 @@
 #include <linux/blkdev.h>
 #include <linux/times.h>
 #include <linux/uaccess.h>
+#include <scsi/scsi_common.h>
 #include <scsi/scsi_request.h>
 
 /* used to tell the module to turn on full debugging messages */
@@ -345,10 +346,10 @@ static LIST_HEAD(cdrom_list);
 int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
 			       struct packet_command *cgc)
 {
-	if (cgc->sense) {
-		cgc->sense->sense_key = 0x05;
-		cgc->sense->asc = 0x20;
-		cgc->sense->ascq = 0x00;
+	if (cgc->sshdr) {
+		cgc->sshdr->sense_key = 0x05;
+		cgc->sshdr->asc = 0x20;
+		cgc->sshdr->ascq = 0x00;
 	}
 
 	cgc->stat = -EIO;
@@ -2222,9 +2223,12 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 
 		blk_execute_rq(q, cdi->disk, rq, 0);
 		if (scsi_req(rq)->result) {
-			struct request_sense *s = req->sense;
+			struct scsi_sense_hdr sshdr;
+
 			ret = -EIO;
-			cdi->last_sense = s->sense_key;
+			scsi_normalize_sense(req->sense, req->sense_len,
+					     &sshdr);
+			cdi->last_sense = sshdr.sense_key;
 		}
 
 		if (blk_rq_unmap_user(bio))
@@ -2943,7 +2947,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 					      struct packet_command *cgc,
 					      int cmd)
 {
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	struct cdrom_msf msf;
 	int blocksize = 0, format = 0, lba;
 	int ret;
@@ -2971,13 +2975,13 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 	if (cgc->buffer == NULL)
 		return -ENOMEM;
 
-	memset(&sense, 0, sizeof(sense));
-	cgc->sense = &sense;
+	memset(&sshdr, 0, sizeof(sshdr));
+	cgc->sshdr = &sshdr;
 	cgc->data_direction = CGC_DATA_READ;
 	ret = cdrom_read_block(cdi, cgc, lba, 1, format, blocksize);
-	if (ret && sense.sense_key == 0x05 &&
-	    sense.asc == 0x20 &&
-	    sense.ascq == 0x00) {
+	if (ret && sshdr.sense_key == 0x05 &&
+	    sshdr.asc == 0x20 &&
+	    sshdr.ascq == 0x00) {
 		/*
 		 * SCSI-II devices are not required to support
 		 * READ_CD, so let's try switching block size
@@ -2986,7 +2990,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 		ret = cdrom_switch_blocksize(cdi, blocksize);
 		if (ret)
 			goto out;
-		cgc->sense = NULL;
+		cgc->sshdr = NULL;
 		ret = cdrom_read_cd(cdi, cgc, lba, blocksize, 1);
 		ret |= cdrom_switch_blocksize(cdi, blocksize);
 	}
diff --git a/drivers/char/agp/alpha-agp.c b/drivers/char/agp/alpha-agp.c
index 53fe633df1e8..c9bf2c219841 100644
--- a/drivers/char/agp/alpha-agp.c
+++ b/drivers/char/agp/alpha-agp.c
@@ -11,7 +11,7 @@
 
 #include "agp.h"
 
-static int alpha_core_agp_vm_fault(struct vm_fault *vmf)
+static vm_fault_t alpha_core_agp_vm_fault(struct vm_fault *vmf)
 {
 	alpha_agp_info *agp = agp_bridge->dev_private_data;
 	dma_addr_t dma_addr;
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index e50c29c97ca7..c69e39fdd02b 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -156,7 +156,7 @@ static u64 amd64_configure(struct pci_dev *hammer, u64 gatt_table)
 
 	/* Address to map to */
 	pci_read_config_dword(hammer, AMD64_GARTAPERTUREBASE, &tmp);
-	aperturebase = tmp << 25;
+	aperturebase = (u64)tmp << 25;
 	aper_base = (aperturebase & PCI_BASE_ADDRESS_MEM_MASK);
 
 	enable_gart_translation(hammer, gatt_table);
@@ -277,7 +277,7 @@ static int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp, u16 cap)
 	pci_read_config_dword(nb, AMD64_GARTAPERTURECTL, &nb_order);
 	nb_order = (nb_order >> 1) & 7;
 	pci_read_config_dword(nb, AMD64_GARTAPERTUREBASE, &nb_base);
-	nb_aper = nb_base << 25;
+	nb_aper = (u64)nb_base << 25;
 
 	/* Northbridge seems to contain crap. Try the AGP bridge. */
 
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index ad353be871bf..90ec010bffbd 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -2088,8 +2088,10 @@ static int try_smi_init(struct smi_info *new_smi)
 	return 0;
 
 out_err:
-	ipmi_unregister_smi(new_smi->intf);
-	new_smi->intf = NULL;
+	if (new_smi->intf) {
+		ipmi_unregister_smi(new_smi->intf);
+		new_smi->intf = NULL;
+	}
 
 	kfree(init_name);
 
diff --git a/drivers/char/ipmi/kcs_bmc.c b/drivers/char/ipmi/kcs_bmc.c
index fbfc05e3f3d1..bb882ab161fe 100644
--- a/drivers/char/ipmi/kcs_bmc.c
+++ b/drivers/char/ipmi/kcs_bmc.c
@@ -210,34 +210,23 @@ static void kcs_bmc_handle_cmd(struct kcs_bmc *kcs_bmc)
 int kcs_bmc_handle_event(struct kcs_bmc *kcs_bmc)
 {
 	unsigned long flags;
-	int ret = 0;
+	int ret = -ENODATA;
 	u8 status;
 
 	spin_lock_irqsave(&kcs_bmc->lock, flags);
 
-	if (!kcs_bmc->running) {
-		kcs_force_abort(kcs_bmc);
-		ret = -ENODEV;
-		goto out_unlock;
-	}
-
-	status = read_status(kcs_bmc) & (KCS_STATUS_IBF | KCS_STATUS_CMD_DAT);
-
-	switch (status) {
-	case KCS_STATUS_IBF | KCS_STATUS_CMD_DAT:
-		kcs_bmc_handle_cmd(kcs_bmc);
-		break;
-
-	case KCS_STATUS_IBF:
-		kcs_bmc_handle_data(kcs_bmc);
-		break;
+	status = read_status(kcs_bmc);
+	if (status & KCS_STATUS_IBF) {
+		if (!kcs_bmc->running)
+			kcs_force_abort(kcs_bmc);
+		else if (status & KCS_STATUS_CMD_DAT)
+			kcs_bmc_handle_cmd(kcs_bmc);
+		else
+			kcs_bmc_handle_data(kcs_bmc);
 
-	default:
-		ret = -ENODATA;
-		break;
+		ret = 0;
 	}
 
-out_unlock:
 	spin_unlock_irqrestore(&kcs_bmc->lock, flags);
 
 	return ret;
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index ffeb60d3434c..df66a9dd0aae 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -708,6 +708,7 @@ static int mmap_zero(struct file *file, struct vm_area_struct *vma)
 #endif
 	if (vma->vm_flags & VM_SHARED)
 		return shmem_zero_setup(vma);
+	vma_set_anonymous(vma);
 	return 0;
 }
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index a8fb0020ba5c..bd449ad52442 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -402,7 +402,8 @@ static struct poolinfo {
 /*
  * Static global variables
  */
-static DECLARE_WAIT_QUEUE_HEAD(random_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
 static struct fasync_struct *fasync;
 
 static DEFINE_SPINLOCK(random_ready_list_lock);
@@ -721,8 +722,8 @@ retry:
 
 		/* should we wake readers? */
 		if (entropy_bits >= random_read_wakeup_bits &&
-		    wq_has_sleeper(&random_wait)) {
-			wake_up_interruptible_poll(&random_wait, POLLIN);
+		    wq_has_sleeper(&random_read_wait)) {
+			wake_up_interruptible(&random_read_wait);
 			kill_fasync(&fasync, SIGIO, POLL_IN);
 		}
 		/* If the input pool is getting full, send some
@@ -1396,7 +1397,7 @@ retry:
 	trace_debit_entropy(r->name, 8 * ibytes);
 	if (ibytes &&
 	    (r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
-		wake_up_interruptible_poll(&random_wait, POLLOUT);
+		wake_up_interruptible(&random_write_wait);
 		kill_fasync(&fasync, SIGIO, POLL_OUT);
 	}
 
@@ -1838,7 +1839,7 @@ _random_read(int nonblock, char __user *buf, size_t nbytes)
 		if (nonblock)
 			return -EAGAIN;
 
-		wait_event_interruptible(random_wait,
+		wait_event_interruptible(random_read_wait,
 			ENTROPY_BITS(&input_pool) >=
 			random_read_wakeup_bits);
 		if (signal_pending(current))
@@ -1875,17 +1876,14 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 	return ret;
 }
 
-static struct wait_queue_head *
-random_get_poll_head(struct file *file, __poll_t events)
-{
-	return &random_wait;
-}
-
 static __poll_t
-random_poll_mask(struct file *file, __poll_t events)
+random_poll(struct file *file, poll_table * wait)
 {
-	__poll_t mask = 0;
+	__poll_t mask;
 
+	poll_wait(file, &random_read_wait, wait);
+	poll_wait(file, &random_write_wait, wait);
+	mask = 0;
 	if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
@@ -1897,14 +1895,22 @@ static int
 write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
 {
 	size_t bytes;
-	__u32 buf[16];
+	__u32 t, buf[16];
 	const char __user *p = buffer;
 
 	while (count > 0) {
+		int b, i = 0;
+
 		bytes = min(count, sizeof(buf));
 		if (copy_from_user(&buf, p, bytes))
 			return -EFAULT;
 
+		for (b = bytes ; b > 0 ; b -= sizeof(__u32), i++) {
+			if (!arch_get_random_int(&t))
+				break;
+			buf[i] ^= t;
+		}
+
 		count -= bytes;
 		p += bytes;
 
@@ -1992,8 +1998,7 @@ static int random_fasync(int fd, struct file *filp, int on)
 const struct file_operations random_fops = {
 	.read  = random_read,
 	.write = random_write,
-	.get_poll_head  = random_get_poll_head,
-	.poll_mask  = random_poll_mask,
+	.poll  = random_poll,
 	.unlocked_ioctl = random_ioctl,
 	.fasync = random_fasync,
 	.llseek = noop_llseek,
@@ -2326,7 +2331,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
 	 * We'll be woken up again once below random_write_wakeup_thresh,
 	 * or when the calling thread is about to terminate.
 	 */
-	wait_event_interruptible(random_wait, kthread_should_stop() ||
+	wait_event_interruptible(random_write_wait, kthread_should_stop() ||
 			ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
 	mix_pool_bytes(poolp, buffer, count);
 	credit_entropy_bits(poolp, entropy);
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index ae40cbe770f0..0bb25dd009d1 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -96,7 +96,7 @@ obj-$(CONFIG_ARCH_SPRD)			+= sprd/
 obj-$(CONFIG_ARCH_STI)			+= st/
 obj-$(CONFIG_ARCH_STRATIX10)		+= socfpga/
 obj-$(CONFIG_ARCH_SUNXI)		+= sunxi/
-obj-$(CONFIG_ARCH_SUNXI)		+= sunxi-ng/
+obj-$(CONFIG_SUNXI_CCU)			+= sunxi-ng/
 obj-$(CONFIG_ARCH_TEGRA)		+= tegra/
 obj-y					+= ti/
 obj-$(CONFIG_CLK_UNIPHIER)		+= uniphier/
diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c
index 38b366b00c57..7b70a074095d 100644
--- a/drivers/clk/clk-aspeed.c
+++ b/drivers/clk/clk-aspeed.c
@@ -24,7 +24,7 @@
 #define ASPEED_MPLL_PARAM	0x20
 #define ASPEED_HPLL_PARAM	0x24
 #define  AST2500_HPLL_BYPASS_EN	BIT(20)
-#define  AST2400_HPLL_STRAPPED	BIT(18)
+#define  AST2400_HPLL_PROGRAMMED BIT(18)
 #define  AST2400_HPLL_BYPASS_EN	BIT(17)
 #define ASPEED_MISC_CTRL	0x2c
 #define  UART_DIV13_EN		BIT(12)
@@ -91,8 +91,8 @@ static const struct aspeed_gate_data aspeed_gates[] = {
 	[ASPEED_CLK_GATE_GCLK] =	{  1,  7, "gclk-gate",		NULL,	0 }, /* 2D engine */
 	[ASPEED_CLK_GATE_MCLK] =	{  2, -1, "mclk-gate",		"mpll",	CLK_IS_CRITICAL }, /* SDRAM */
 	[ASPEED_CLK_GATE_VCLK] =	{  3,  6, "vclk-gate",		NULL,	0 }, /* Video Capture */
-	[ASPEED_CLK_GATE_BCLK] =	{  4,  8, "bclk-gate",		"bclk",	0 }, /* PCIe/PCI */
-	[ASPEED_CLK_GATE_DCLK] =	{  5, -1, "dclk-gate",		NULL,	0 }, /* DAC */
+	[ASPEED_CLK_GATE_BCLK] =	{  4,  8, "bclk-gate",		"bclk",	CLK_IS_CRITICAL }, /* PCIe/PCI */
+	[ASPEED_CLK_GATE_DCLK] =	{  5, -1, "dclk-gate",		NULL,	CLK_IS_CRITICAL }, /* DAC */
 	[ASPEED_CLK_GATE_REFCLK] =	{  6, -1, "refclk-gate",	"clkin", CLK_IS_CRITICAL },
 	[ASPEED_CLK_GATE_USBPORT2CLK] =	{  7,  3, "usb-port2-gate",	NULL,	0 }, /* USB2.0 Host port 2 */
 	[ASPEED_CLK_GATE_LCLK] =	{  8,  5, "lclk-gate",		NULL,	0 }, /* LPC */
@@ -212,9 +212,22 @@ static int aspeed_clk_is_enabled(struct clk_hw *hw)
 {
 	struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw);
 	u32 clk = BIT(gate->clock_idx);
+	u32 rst = BIT(gate->reset_idx);
 	u32 enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? 0 : clk;
 	u32 reg;
 
+	/*
+	 * If the IP is in reset, treat the clock as not enabled,
+	 * this happens with some clocks such as the USB one when
+	 * coming from cold reset. Without this, aspeed_clk_enable()
+	 * will fail to lift the reset.
+	 */
+	if (gate->reset_idx >= 0) {
+		regmap_read(gate->map, ASPEED_RESET_CTRL, &reg);
+		if (reg & rst)
+			return 0;
+	}
+
 	regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, &reg);
 
 	return ((reg & clk) == enval) ? 1 : 0;
@@ -565,29 +578,45 @@ builtin_platform_driver(aspeed_clk_driver);
 static void __init aspeed_ast2400_cc(struct regmap *map)
 {
 	struct clk_hw *hw;
-	u32 val, freq, div;
+	u32 val, div, clkin, hpll;
+	const u16 hpll_rates[][4] = {
+		{384, 360, 336, 408},
+		{400, 375, 350, 425},
+	};
+	int rate;
 
 	/*
 	 * CLKIN is the crystal oscillator, 24, 48 or 25MHz selected by
 	 * strapping
 	 */
 	regmap_read(map, ASPEED_STRAP, &val);
-	if (val & CLKIN_25MHZ_EN)
-		freq = 25000000;
-	else if (val & AST2400_CLK_SOURCE_SEL)
-		freq = 48000000;
-	else
-		freq = 24000000;
-	hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, freq);
-	pr_debug("clkin @%u MHz\n", freq / 1000000);
+	rate = (val >> 8) & 3;
+	if (val & CLKIN_25MHZ_EN) {
+		clkin = 25000000;
+		hpll = hpll_rates[1][rate];
+	} else if (val & AST2400_CLK_SOURCE_SEL) {
+		clkin = 48000000;
+		hpll = hpll_rates[0][rate];
+	} else {
+		clkin = 24000000;
+		hpll = hpll_rates[0][rate];
+	}
+	hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, clkin);
+	pr_debug("clkin @%u MHz\n", clkin / 1000000);
 
 	/*
 	 * High-speed PLL clock derived from the crystal. This the CPU clock,
-	 * and we assume that it is enabled
+	 * and we assume that it is enabled. It can be configured through the
+	 * HPLL_PARAM register, or set to a specified frequency by strapping.
 	 */
 	regmap_read(map, ASPEED_HPLL_PARAM, &val);
-	WARN(val & AST2400_HPLL_STRAPPED, "hpll is strapped not configured");
-	aspeed_clk_data->hws[ASPEED_CLK_HPLL] = aspeed_ast2400_calc_pll("hpll", val);
+	if (val & AST2400_HPLL_PROGRAMMED)
+		hw = aspeed_ast2400_calc_pll("hpll", val);
+	else
+		hw = clk_hw_register_fixed_rate(NULL, "hpll", "clkin", 0,
+				hpll * 1000000);
+
+	aspeed_clk_data->hws[ASPEED_CLK_HPLL] = hw;
 
 	/*
 	 * Strap bits 11:10 define the CPU/AHB clock frequency ratio (aka HCLK)
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 9760b526ca31..976f59e11f9a 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -24,7 +24,6 @@
 #include <linux/pm_runtime.h>
 #include <linux/sched.h>
 #include <linux/clkdev.h>
-#include <linux/stringify.h>
 
 #include "clk.h"
 
@@ -68,6 +67,7 @@ struct clk_core {
 	unsigned long		max_rate;
 	unsigned long		accuracy;
 	int			phase;
+	struct clk_duty		duty;
 	struct hlist_head	children;
 	struct hlist_node	child_node;
 	struct hlist_head	clks;
@@ -2402,6 +2402,172 @@ int clk_get_phase(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(clk_get_phase);
 
+static void clk_core_reset_duty_cycle_nolock(struct clk_core *core)
+{
+	/* Assume a default value of 50% */
+	core->duty.num = 1;
+	core->duty.den = 2;
+}
+
+static int clk_core_update_duty_cycle_parent_nolock(struct clk_core *core);
+
+static int clk_core_update_duty_cycle_nolock(struct clk_core *core)
+{
+	struct clk_duty *duty = &core->duty;
+	int ret = 0;
+
+	if (!core->ops->get_duty_cycle)
+		return clk_core_update_duty_cycle_parent_nolock(core);
+
+	ret = core->ops->get_duty_cycle(core->hw, duty);
+	if (ret)
+		goto reset;
+
+	/* Don't trust the clock provider too much */
+	if (duty->den == 0 || duty->num > duty->den) {
+		ret = -EINVAL;
+		goto reset;
+	}
+
+	return 0;
+
+reset:
+	clk_core_reset_duty_cycle_nolock(core);
+	return ret;
+}
+
+static int clk_core_update_duty_cycle_parent_nolock(struct clk_core *core)
+{
+	int ret = 0;
+
+	if (core->parent &&
+	    core->flags & CLK_DUTY_CYCLE_PARENT) {
+		ret = clk_core_update_duty_cycle_nolock(core->parent);
+		memcpy(&core->duty, &core->parent->duty, sizeof(core->duty));
+	} else {
+		clk_core_reset_duty_cycle_nolock(core);
+	}
+
+	return ret;
+}
+
+static int clk_core_set_duty_cycle_parent_nolock(struct clk_core *core,
+						 struct clk_duty *duty);
+
+static int clk_core_set_duty_cycle_nolock(struct clk_core *core,
+					  struct clk_duty *duty)
+{
+	int ret;
+
+	lockdep_assert_held(&prepare_lock);
+
+	if (clk_core_rate_is_protected(core))
+		return -EBUSY;
+
+	trace_clk_set_duty_cycle(core, duty);
+
+	if (!core->ops->set_duty_cycle)
+		return clk_core_set_duty_cycle_parent_nolock(core, duty);
+
+	ret = core->ops->set_duty_cycle(core->hw, duty);
+	if (!ret)
+		memcpy(&core->duty, duty, sizeof(*duty));
+
+	trace_clk_set_duty_cycle_complete(core, duty);
+
+	return ret;
+}
+
+static int clk_core_set_duty_cycle_parent_nolock(struct clk_core *core,
+						 struct clk_duty *duty)
+{
+	int ret = 0;
+
+	if (core->parent &&
+	    core->flags & (CLK_DUTY_CYCLE_PARENT | CLK_SET_RATE_PARENT)) {
+		ret = clk_core_set_duty_cycle_nolock(core->parent, duty);
+		memcpy(&core->duty, &core->parent->duty, sizeof(core->duty));
+	}
+
+	return ret;
+}
+
+/**
+ * clk_set_duty_cycle - adjust the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @num: numerator of the duty cycle ratio to be applied
+ * @den: denominator of the duty cycle ratio to be applied
+ *
+ * Apply the duty cycle ratio if the ratio is valid and the clock can
+ * perform this operation
+ *
+ * Returns (0) on success, a negative errno otherwise.
+ */
+int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den)
+{
+	int ret;
+	struct clk_duty duty;
+
+	if (!clk)
+		return 0;
+
+	/* sanity check the ratio */
+	if (den == 0 || num > den)
+		return -EINVAL;
+
+	duty.num = num;
+	duty.den = den;
+
+	clk_prepare_lock();
+
+	if (clk->exclusive_count)
+		clk_core_rate_unprotect(clk->core);
+
+	ret = clk_core_set_duty_cycle_nolock(clk->core, &duty);
+
+	if (clk->exclusive_count)
+		clk_core_rate_protect(clk->core);
+
+	clk_prepare_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_set_duty_cycle);
+
+static int clk_core_get_scaled_duty_cycle(struct clk_core *core,
+					  unsigned int scale)
+{
+	struct clk_duty *duty = &core->duty;
+	int ret;
+
+	clk_prepare_lock();
+
+	ret = clk_core_update_duty_cycle_nolock(core);
+	if (!ret)
+		ret = mult_frac(scale, duty->num, duty->den);
+
+	clk_prepare_unlock();
+
+	return ret;
+}
+
+/**
+ * clk_get_scaled_duty_cycle - return the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @scale: scaling factor to be applied to represent the ratio as an integer
+ *
+ * Returns the duty cycle ratio of a clock node multiplied by the provided
+ * scaling factor, or negative errno on error.
+ */
+int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale)
+{
+	if (!clk)
+		return 0;
+
+	return clk_core_get_scaled_duty_cycle(clk->core, scale);
+}
+EXPORT_SYMBOL_GPL(clk_get_scaled_duty_cycle);
+
 /**
  * clk_is_match - check if two clk's point to the same hardware clock
  * @p: clk compared against q
@@ -2455,12 +2621,13 @@ static void clk_summary_show_one(struct seq_file *s, struct clk_core *c,
 	if (!c)
 		return;
 
-	seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %-3d\n",
+	seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %5d %6d\n",
 		   level * 3 + 1, "",
 		   30 - level * 3, c->name,
 		   c->enable_count, c->prepare_count, c->protect_count,
 		   clk_core_get_rate(c), clk_core_get_accuracy(c),
-		   clk_core_get_phase(c));
+		   clk_core_get_phase(c),
+		   clk_core_get_scaled_duty_cycle(c, 100000));
 }
 
 static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c,
@@ -2482,9 +2649,9 @@ static int clk_summary_show(struct seq_file *s, void *data)
 	struct clk_core *c;
 	struct hlist_head **lists = (struct hlist_head **)s->private;
 
-	seq_puts(s, "                                 enable  prepare  protect                               \n");
-	seq_puts(s, "   clock                          count    count    count        rate   accuracy   phase\n");
-	seq_puts(s, "----------------------------------------------------------------------------------------\n");
+	seq_puts(s, "                                 enable  prepare  protect                                duty\n");
+	seq_puts(s, "   clock                          count    count    count        rate   accuracy phase  cycle\n");
+	seq_puts(s, "---------------------------------------------------------------------------------------------\n");
 
 	clk_prepare_lock();
 
@@ -2511,6 +2678,8 @@ static void clk_dump_one(struct seq_file *s, struct clk_core *c, int level)
 	seq_printf(s, "\"rate\": %lu,", clk_core_get_rate(c));
 	seq_printf(s, "\"accuracy\": %lu,", clk_core_get_accuracy(c));
 	seq_printf(s, "\"phase\": %d", clk_core_get_phase(c));
+	seq_printf(s, "\"duty_cycle\": %u",
+		   clk_core_get_scaled_duty_cycle(c, 100000));
 }
 
 static void clk_dump_subtree(struct seq_file *s, struct clk_core *c, int level)
@@ -2559,7 +2728,7 @@ static const struct {
 	unsigned long flag;
 	const char *name;
 } clk_flags[] = {
-#define ENTRY(f) { f, __stringify(f) }
+#define ENTRY(f) { f, #f }
 	ENTRY(CLK_SET_RATE_GATE),
 	ENTRY(CLK_SET_PARENT_GATE),
 	ENTRY(CLK_SET_RATE_PARENT),
@@ -2572,6 +2741,7 @@ static const struct {
 	ENTRY(CLK_SET_RATE_UNGATE),
 	ENTRY(CLK_IS_CRITICAL),
 	ENTRY(CLK_OPS_PARENT_ENABLE),
+	ENTRY(CLK_DUTY_CYCLE_PARENT),
 #undef ENTRY
 };
 
@@ -2610,6 +2780,17 @@ static int possible_parents_show(struct seq_file *s, void *data)
 }
 DEFINE_SHOW_ATTRIBUTE(possible_parents);
 
+static int clk_duty_cycle_show(struct seq_file *s, void *data)
+{
+	struct clk_core *core = s->private;
+	struct clk_duty *duty = &core->duty;
+
+	seq_printf(s, "%u/%u\n", duty->num, duty->den);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(clk_duty_cycle);
+
 static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
 {
 	struct dentry *root;
@@ -2628,6 +2809,8 @@ static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
 	debugfs_create_u32("clk_enable_count", 0444, root, &core->enable_count);
 	debugfs_create_u32("clk_protect_count", 0444, root, &core->protect_count);
 	debugfs_create_u32("clk_notifier_count", 0444, root, &core->notifier_count);
+	debugfs_create_file("clk_duty_cycle", 0444, root, core,
+			    &clk_duty_cycle_fops);
 
 	if (core->num_parents > 1)
 		debugfs_create_file("clk_possible_parents", 0444, root, core,
@@ -2846,6 +3029,11 @@ static int __clk_core_init(struct clk_core *core)
 		core->phase = 0;
 
 	/*
+	 * Set clk's duty cycle.
+	 */
+	clk_core_update_duty_cycle_nolock(core);
+
+	/*
 	 * Set clk's rate.  The preferred method is to use .recalc_rate.  For
 	 * simple clocks and lazy developers the default fallback is to use the
 	 * parent's rate.  If a clock doesn't have a parent (or is orphaned)
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 7513411140b6..9ab3db8b3988 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -35,9 +35,6 @@ static struct clk *__of_clk_get(struct device_node *np, int index,
 	struct clk *clk;
 	int rc;
 
-	if (index < 0)
-		return ERR_PTR(-EINVAL);
-
 	rc = of_parse_phandle_with_args(np, "clocks", "#clock-cells", index,
 					&clkspec);
 	if (rc)
@@ -199,7 +196,7 @@ struct clk *clk_get(struct device *dev, const char *con_id)
 	const char *dev_id = dev ? dev_name(dev) : NULL;
 	struct clk *clk;
 
-	if (dev) {
+	if (dev && dev->of_node) {
 		clk = __of_clk_get_by_name(dev->of_node, dev_id, con_id);
 		if (!IS_ERR(clk) || PTR_ERR(clk) == -EPROBE_DEFER)
 			return clk;
diff --git a/drivers/clk/davinci/da8xx-cfgchip.c b/drivers/clk/davinci/da8xx-cfgchip.c
index aae62a5b8734..d1bbee19ed0f 100644
--- a/drivers/clk/davinci/da8xx-cfgchip.c
+++ b/drivers/clk/davinci/da8xx-cfgchip.c
@@ -672,7 +672,7 @@ static int of_da8xx_usb_phy_clk_init(struct device *dev, struct regmap *regmap)
 
 	usb1 = da8xx_cfgchip_register_usb1_clk48(dev, regmap);
 	if (IS_ERR(usb1)) {
-		if (PTR_ERR(usb0) == -EPROBE_DEFER)
+		if (PTR_ERR(usb1) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
 
 		dev_warn(dev, "Failed to register usb1_clk48 (%ld)\n",
diff --git a/drivers/clk/davinci/psc.h b/drivers/clk/davinci/psc.h
index 6a42529d31a9..cc5614567a70 100644
--- a/drivers/clk/davinci/psc.h
+++ b/drivers/clk/davinci/psc.h
@@ -107,7 +107,7 @@ extern const struct davinci_psc_init_data of_da850_psc1_init_data;
 #ifdef CONFIG_ARCH_DAVINCI_DM355
 extern const struct davinci_psc_init_data dm355_psc_init_data;
 #endif
-#ifdef CONFIG_ARCH_DAVINCI_DM356
+#ifdef CONFIG_ARCH_DAVINCI_DM365
 extern const struct davinci_psc_init_data dm365_psc_init_data;
 #endif
 #ifdef CONFIG_ARCH_DAVINCI_DM644x
diff --git a/drivers/clk/meson/clk-audio-divider.c b/drivers/clk/meson/clk-audio-divider.c
index 58f546e04807..e4cf96ba704e 100644
--- a/drivers/clk/meson/clk-audio-divider.c
+++ b/drivers/clk/meson/clk-audio-divider.c
@@ -51,7 +51,7 @@ static unsigned long audio_divider_recalc_rate(struct clk_hw *hw,
 	struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk);
 	unsigned long divider;
 
-	divider = meson_parm_read(clk->map, &adiv->div);
+	divider = meson_parm_read(clk->map, &adiv->div) + 1;
 
 	return DIV_ROUND_UP_ULL((u64)parent_rate, divider);
 }
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 240658404367..177fffb9ebef 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -498,6 +498,7 @@ static struct clk_regmap gxbb_fclk_div2 = {
 		.ops = &clk_regmap_gate_ops,
 		.parent_names = (const char *[]){ "fclk_div2_div" },
 		.num_parents = 1,
+		.flags = CLK_IS_CRITICAL,
 	},
 };
 
diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index 6860bd5a37c5..44e4e27eddad 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -35,6 +35,7 @@
 #define CLK_SEL		0x10
 #define CLK_DIS		0x14
 
+#define  ARMADA_37XX_DVFS_LOAD_1 1
 #define LOAD_LEVEL_NR	4
 
 #define ARMADA_37XX_NB_L0L1	0x18
@@ -507,6 +508,40 @@ static long clk_pm_cpu_round_rate(struct clk_hw *hw, unsigned long rate,
 	return -EINVAL;
 }
 
+/*
+ * Switching the CPU from the L2 or L3 frequencies (300 and 200 Mhz
+ * respectively) to L0 frequency (1.2 Ghz) requires a significant
+ * amount of time to let VDD stabilize to the appropriate
+ * voltage. This amount of time is large enough that it cannot be
+ * covered by the hardware countdown register. Due to this, the CPU
+ * might start operating at L0 before the voltage is stabilized,
+ * leading to CPU stalls.
+ *
+ * To work around this problem, we prevent switching directly from the
+ * L2/L3 frequencies to the L0 frequency, and instead switch to the L1
+ * frequency in-between. The sequence therefore becomes:
+ * 1. First switch from L2/L3(200/300MHz) to L1(600MHZ)
+ * 2. Sleep 20ms for stabling VDD voltage
+ * 3. Then switch from L1(600MHZ) to L0(1200Mhz).
+ */
+static void clk_pm_cpu_set_rate_wa(unsigned long rate, struct regmap *base)
+{
+	unsigned int cur_level;
+
+	if (rate != 1200 * 1000 * 1000)
+		return;
+
+	regmap_read(base, ARMADA_37XX_NB_CPU_LOAD, &cur_level);
+	cur_level &= ARMADA_37XX_NB_CPU_LOAD_MASK;
+	if (cur_level <= ARMADA_37XX_DVFS_LOAD_1)
+		return;
+
+	regmap_update_bits(base, ARMADA_37XX_NB_CPU_LOAD,
+			   ARMADA_37XX_NB_CPU_LOAD_MASK,
+			   ARMADA_37XX_DVFS_LOAD_1);
+	msleep(20);
+}
+
 static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
 			       unsigned long parent_rate)
 {
@@ -537,6 +572,9 @@ static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
 			 */
 			reg = ARMADA_37XX_NB_CPU_LOAD;
 			mask = ARMADA_37XX_NB_CPU_LOAD_MASK;
+
+			clk_pm_cpu_set_rate_wa(rate, base);
+
 			regmap_update_bits(base, reg, mask, load_level);
 
 			return rate;
diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c
index 9f35b3fe1d97..ff8d66fd94e6 100644
--- a/drivers/clk/qcom/gcc-msm8996.c
+++ b/drivers/clk/qcom/gcc-msm8996.c
@@ -2781,6 +2781,7 @@ static struct clk_branch gcc_ufs_rx_cfg_clk = {
 
 static struct clk_branch gcc_ufs_tx_symbol_0_clk = {
 	.halt_reg = 0x75018,
+	.halt_check = BRANCH_HALT_SKIP,
 	.clkr = {
 		.enable_reg = 0x75018,
 		.enable_mask = BIT(0),
diff --git a/drivers/clk/qcom/mmcc-msm8996.c b/drivers/clk/qcom/mmcc-msm8996.c
index 1a25ee4f3658..4b20d1b67a1b 100644
--- a/drivers/clk/qcom/mmcc-msm8996.c
+++ b/drivers/clk/qcom/mmcc-msm8996.c
@@ -2910,6 +2910,7 @@ static struct gdsc mmagic_bimc_gdsc = {
 		.name = "mmagic_bimc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.flags = ALWAYS_ON,
 };
 
 static struct gdsc mmagic_video_gdsc = {
diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile
index acaa14cfa25c..49454700f2e5 100644
--- a/drivers/clk/sunxi-ng/Makefile
+++ b/drivers/clk/sunxi-ng/Makefile
@@ -1,24 +1,24 @@
 # SPDX-License-Identifier: GPL-2.0
 # Common objects
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_common.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_mmc_timing.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_reset.o
+obj-y				+= ccu_common.o
+obj-y				+= ccu_mmc_timing.o
+obj-y				+= ccu_reset.o
 
 # Base clock types
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_div.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_frac.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_gate.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_mux.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_mult.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_phase.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_sdm.o
+obj-y				+= ccu_div.o
+obj-y				+= ccu_frac.o
+obj-y				+= ccu_gate.o
+obj-y				+= ccu_mux.o
+obj-y				+= ccu_mult.o
+obj-y				+= ccu_phase.o
+obj-y				+= ccu_sdm.o
 
 # Multi-factor clocks
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_nk.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_nkm.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_nkmp.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_nm.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_mp.o
+obj-y				+= ccu_nk.o
+obj-y				+= ccu_nkm.o
+obj-y				+= ccu_nkmp.o
+obj-y				+= ccu_nm.o
+obj-y				+= ccu_mp.o
 
 # SoC support
 obj-$(CONFIG_SUN50I_A64_CCU)	+= ccu-sun50i-a64.o
@@ -38,12 +38,3 @@ obj-$(CONFIG_SUN8I_R40_CCU)	+= ccu-sun8i-r40.o
 obj-$(CONFIG_SUN9I_A80_CCU)	+= ccu-sun9i-a80.o
 obj-$(CONFIG_SUN9I_A80_CCU)	+= ccu-sun9i-a80-de.o
 obj-$(CONFIG_SUN9I_A80_CCU)	+= ccu-sun9i-a80-usb.o
-
-# The lib-y file goals is supposed to work only in arch/*/lib or lib/. In our
-# case, we want to use that goal, but even though lib.a will be properly
-# generated, it will not be linked in, eventually resulting in a linker error
-# for missing symbols.
-#
-# We can work around that by explicitly adding lib.a to the obj-y goal. This is
-# an undocumented behaviour, but works well for now.
-obj-$(CONFIG_SUNXI_CCU)		+= lib.a
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 00caf37e52f9..c070cc7992e9 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -49,7 +49,7 @@ obj-$(CONFIG_CLKSRC_SAMSUNG_PWM)	+= samsung_pwm_timer.o
 obj-$(CONFIG_FSL_FTM_TIMER)	+= fsl_ftm_timer.o
 obj-$(CONFIG_VF_PIT_TIMER)	+= vf_pit_timer.o
 obj-$(CONFIG_CLKSRC_QCOM)	+= qcom-timer.o
-obj-$(CONFIG_MTK_TIMER)		+= mtk_timer.o
+obj-$(CONFIG_MTK_TIMER)		+= timer-mediatek.o
 obj-$(CONFIG_CLKSRC_PISTACHIO)	+= time-pistachio.o
 obj-$(CONFIG_CLKSRC_TI_32K)	+= timer-ti-32k.o
 obj-$(CONFIG_CLKSRC_NPS)	+= timer-nps.o
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 57cb2f00fc07..d8c7f5750cdb 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -735,7 +735,7 @@ static void __arch_timer_setup(unsigned type,
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
 		clk->rating = 400;
-		clk->cpumask = cpu_all_mask;
+		clk->cpumask = cpu_possible_mask;
 		if (arch_timer_mem_use_virtual) {
 			clk->set_state_shutdown = arch_timer_shutdown_virt_mem;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem;
diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c
deleted file mode 100644
index f9b724fd9950..000000000000
--- a/drivers/clocksource/mtk_timer.c
+++ /dev/null
@@ -1,268 +0,0 @@
-/*
- * Mediatek SoCs General-Purpose Timer handling.
- *
- * Copyright (C) 2014 Matthias Brugger
- *
- * Matthias Brugger <matthias.bgg@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
-
-#include <linux/clk.h>
-#include <linux/clockchips.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqreturn.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/sched_clock.h>
-#include <linux/slab.h>
-
-#define GPT_IRQ_EN_REG		0x00
-#define GPT_IRQ_ENABLE(val)	BIT((val) - 1)
-#define GPT_IRQ_ACK_REG		0x08
-#define GPT_IRQ_ACK(val)	BIT((val) - 1)
-
-#define TIMER_CTRL_REG(val)	(0x10 * (val))
-#define TIMER_CTRL_OP(val)	(((val) & 0x3) << 4)
-#define TIMER_CTRL_OP_ONESHOT	(0)
-#define TIMER_CTRL_OP_REPEAT	(1)
-#define TIMER_CTRL_OP_FREERUN	(3)
-#define TIMER_CTRL_CLEAR	(2)
-#define TIMER_CTRL_ENABLE	(1)
-#define TIMER_CTRL_DISABLE	(0)
-
-#define TIMER_CLK_REG(val)	(0x04 + (0x10 * (val)))
-#define TIMER_CLK_SRC(val)	(((val) & 0x1) << 4)
-#define TIMER_CLK_SRC_SYS13M	(0)
-#define TIMER_CLK_SRC_RTC32K	(1)
-#define TIMER_CLK_DIV1		(0x0)
-#define TIMER_CLK_DIV2		(0x1)
-
-#define TIMER_CNT_REG(val)	(0x08 + (0x10 * (val)))
-#define TIMER_CMP_REG(val)	(0x0C + (0x10 * (val)))
-
-#define GPT_CLK_EVT	1
-#define GPT_CLK_SRC	2
-
-struct mtk_clock_event_device {
-	void __iomem *gpt_base;
-	u32 ticks_per_jiffy;
-	struct clock_event_device dev;
-};
-
-static void __iomem *gpt_sched_reg __read_mostly;
-
-static u64 notrace mtk_read_sched_clock(void)
-{
-	return readl_relaxed(gpt_sched_reg);
-}
-
-static inline struct mtk_clock_event_device *to_mtk_clk(
-				struct clock_event_device *c)
-{
-	return container_of(c, struct mtk_clock_event_device, dev);
-}
-
-static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer)
-{
-	u32 val;
-
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-	writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base +
-			TIMER_CTRL_REG(timer));
-}
-
-static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt,
-				unsigned long delay, u8 timer)
-{
-	writel(delay, evt->gpt_base + TIMER_CMP_REG(timer));
-}
-
-static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt,
-		bool periodic, u8 timer)
-{
-	u32 val;
-
-	/* Acknowledge interrupt */
-	writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG);
-
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-
-	/* Clear 2 bit timer operation mode field */
-	val &= ~TIMER_CTRL_OP(0x3);
-
-	if (periodic)
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT);
-	else
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT);
-
-	writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR,
-	       evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static int mtk_clkevt_shutdown(struct clock_event_device *clk)
-{
-	mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT);
-	return 0;
-}
-
-static int mtk_clkevt_set_periodic(struct clock_event_device *clk)
-{
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, true, GPT_CLK_EVT);
-	return 0;
-}
-
-static int mtk_clkevt_next_event(unsigned long event,
-				   struct clock_event_device *clk)
-{
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, false, GPT_CLK_EVT);
-
-	return 0;
-}
-
-static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id)
-{
-	struct mtk_clock_event_device *evt = dev_id;
-
-	/* Acknowledge timer0 irq */
-	writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG);
-	evt->dev.event_handler(&evt->dev);
-
-	return IRQ_HANDLED;
-}
-
-static void
-__init mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option)
-{
-	writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE,
-		evt->gpt_base + TIMER_CTRL_REG(timer));
-
-	writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1,
-			evt->gpt_base + TIMER_CLK_REG(timer));
-
-	writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer));
-
-	writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE,
-			evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
-{
-	u32 val;
-
-	/* Disable all interrupts */
-	writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG);
-
-	/* Acknowledge all spurious pending interrupts */
-	writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG);
-
-	val = readl(evt->gpt_base + GPT_IRQ_EN_REG);
-	writel(val | GPT_IRQ_ENABLE(timer),
-			evt->gpt_base + GPT_IRQ_EN_REG);
-}
-
-static int __init mtk_timer_init(struct device_node *node)
-{
-	struct mtk_clock_event_device *evt;
-	struct resource res;
-	unsigned long rate = 0;
-	struct clk *clk;
-
-	evt = kzalloc(sizeof(*evt), GFP_KERNEL);
-	if (!evt)
-		return -ENOMEM;
-
-	evt->dev.name = "mtk_tick";
-	evt->dev.rating = 300;
-	evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	evt->dev.set_state_shutdown = mtk_clkevt_shutdown;
-	evt->dev.set_state_periodic = mtk_clkevt_set_periodic;
-	evt->dev.set_state_oneshot = mtk_clkevt_shutdown;
-	evt->dev.tick_resume = mtk_clkevt_shutdown;
-	evt->dev.set_next_event = mtk_clkevt_next_event;
-	evt->dev.cpumask = cpu_possible_mask;
-
-	evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer");
-	if (IS_ERR(evt->gpt_base)) {
-		pr_err("Can't get resource\n");
-		goto err_kzalloc;
-	}
-
-	evt->dev.irq = irq_of_parse_and_map(node, 0);
-	if (evt->dev.irq <= 0) {
-		pr_err("Can't parse IRQ\n");
-		goto err_mem;
-	}
-
-	clk = of_clk_get(node, 0);
-	if (IS_ERR(clk)) {
-		pr_err("Can't get timer clock\n");
-		goto err_irq;
-	}
-
-	if (clk_prepare_enable(clk)) {
-		pr_err("Can't prepare clock\n");
-		goto err_clk_put;
-	}
-	rate = clk_get_rate(clk);
-
-	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
-			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
-		pr_err("failed to setup irq %d\n", evt->dev.irq);
-		goto err_clk_disable;
-	}
-
-	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
-
-	/* Configure clock source */
-	mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
-	clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
-			node->name, rate, 300, 32, clocksource_mmio_readl_up);
-	gpt_sched_reg = evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC);
-	sched_clock_register(mtk_read_sched_clock, 32, rate);
-
-	/* Configure clock event */
-	mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
-	clockevents_config_and_register(&evt->dev, rate, 0x3,
-					0xffffffff);
-
-	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
-
-	return 0;
-
-err_clk_disable:
-	clk_disable_unprepare(clk);
-err_clk_put:
-	clk_put(clk);
-err_irq:
-	irq_dispose_mapping(evt->dev.irq);
-err_mem:
-	iounmap(evt->gpt_base);
-	of_address_to_resource(node, 0, &res);
-	release_mem_region(res.start, resource_size(&res));
-err_kzalloc:
-	kfree(evt);
-
-	return -EINVAL;
-}
-TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init);
diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index c337a8100a7b..aa624885e0e2 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -230,7 +230,7 @@ static int __init tegra20_init_timer(struct device_node *np)
 		return ret;
 	}
 
-	tegra_clockevent.cpumask = cpu_all_mask;
+	tegra_clockevent.cpumask = cpu_possible_mask;
 	tegra_clockevent.irq = tegra_timer_irq.irq;
 	clockevents_config_and_register(&tegra_clockevent, 1000000,
 					0x1, 0x1fffffff);
@@ -259,6 +259,6 @@ static int __init tegra20_init_rtc(struct device_node *np)
 	else
 		clk_prepare_enable(clk);
 
-	return register_persistent_clock(NULL, tegra_read_persistent_clock64);
+	return register_persistent_clock(tegra_read_persistent_clock64);
 }
 TIMER_OF_DECLARE(tegra20_rtc, "nvidia,tegra20-rtc", tegra20_init_rtc);
diff --git a/drivers/clocksource/timer-atcpit100.c b/drivers/clocksource/timer-atcpit100.c
index 5e23d7b4a722..b4bd2f5b801d 100644
--- a/drivers/clocksource/timer-atcpit100.c
+++ b/drivers/clocksource/timer-atcpit100.c
@@ -185,7 +185,7 @@ static struct timer_of to = {
 		.set_state_oneshot = atcpit100_clkevt_set_oneshot,
 		.tick_resume = atcpit100_clkevt_shutdown,
 		.set_next_event = atcpit100_clkevt_next_event,
-		.cpumask = cpu_all_mask,
+		.cpumask = cpu_possible_mask,
 	},
 
 	.of_irq = {
diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c
index 0eee03250cfc..f5b2eda30bf3 100644
--- a/drivers/clocksource/timer-keystone.c
+++ b/drivers/clocksource/timer-keystone.c
@@ -211,7 +211,7 @@ static int __init keystone_timer_init(struct device_node *np)
 	event_dev->set_state_shutdown = keystone_shutdown;
 	event_dev->set_state_periodic = keystone_set_periodic;
 	event_dev->set_state_oneshot = keystone_shutdown;
-	event_dev->cpumask = cpu_all_mask;
+	event_dev->cpumask = cpu_possible_mask;
 	event_dev->owner = THIS_MODULE;
 	event_dev->name = TIMER_NAME;
 	event_dev->irq = irq;
diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
new file mode 100644
index 000000000000..eb10321f8517
--- /dev/null
+++ b/drivers/clocksource/timer-mediatek.c
@@ -0,0 +1,328 @@
+/*
+ * Mediatek SoCs General-Purpose Timer handling.
+ *
+ * Copyright (C) 2014 Matthias Brugger
+ *
+ * Matthias Brugger <matthias.bgg@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/irqreturn.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+#include "timer-of.h"
+
+#define TIMER_CLK_EVT           (1)
+#define TIMER_CLK_SRC           (2)
+
+#define TIMER_SYNC_TICKS        (3)
+
+/* gpt */
+#define GPT_IRQ_EN_REG          0x00
+#define GPT_IRQ_ENABLE(val)     BIT((val) - 1)
+#define GPT_IRQ_ACK_REG	        0x08
+#define GPT_IRQ_ACK(val)        BIT((val) - 1)
+
+#define GPT_CTRL_REG(val)       (0x10 * (val))
+#define GPT_CTRL_OP(val)        (((val) & 0x3) << 4)
+#define GPT_CTRL_OP_ONESHOT     (0)
+#define GPT_CTRL_OP_REPEAT      (1)
+#define GPT_CTRL_OP_FREERUN     (3)
+#define GPT_CTRL_CLEAR          (2)
+#define GPT_CTRL_ENABLE         (1)
+#define GPT_CTRL_DISABLE        (0)
+
+#define GPT_CLK_REG(val)        (0x04 + (0x10 * (val)))
+#define GPT_CLK_SRC(val)        (((val) & 0x1) << 4)
+#define GPT_CLK_SRC_SYS13M      (0)
+#define GPT_CLK_SRC_RTC32K      (1)
+#define GPT_CLK_DIV1            (0x0)
+#define GPT_CLK_DIV2            (0x1)
+
+#define GPT_CNT_REG(val)        (0x08 + (0x10 * (val)))
+#define GPT_CMP_REG(val)        (0x0C + (0x10 * (val)))
+
+/* system timer */
+#define SYST_BASE               (0x40)
+
+#define SYST_CON                (SYST_BASE + 0x0)
+#define SYST_VAL                (SYST_BASE + 0x4)
+
+#define SYST_CON_REG(to)        (timer_of_base(to) + SYST_CON)
+#define SYST_VAL_REG(to)        (timer_of_base(to) + SYST_VAL)
+
+/*
+ * SYST_CON_EN: Clock enable. Shall be set to
+ *   - Start timer countdown.
+ *   - Allow timeout ticks being updated.
+ *   - Allow changing interrupt functions.
+ *
+ * SYST_CON_IRQ_EN: Set to allow interrupt.
+ *
+ * SYST_CON_IRQ_CLR: Set to clear interrupt.
+ */
+#define SYST_CON_EN              BIT(0)
+#define SYST_CON_IRQ_EN          BIT(1)
+#define SYST_CON_IRQ_CLR         BIT(4)
+
+static void __iomem *gpt_sched_reg __read_mostly;
+
+static void mtk_syst_ack_irq(struct timer_of *to)
+{
+	/* Clear and disable interrupt */
+	writel(SYST_CON_IRQ_CLR | SYST_CON_EN, SYST_CON_REG(to));
+}
+
+static irqreturn_t mtk_syst_handler(int irq, void *dev_id)
+{
+	struct clock_event_device *clkevt = dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
+
+	mtk_syst_ack_irq(to);
+	clkevt->event_handler(clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static int mtk_syst_clkevt_next_event(unsigned long ticks,
+				      struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	/* Enable clock to allow timeout tick update later */
+	writel(SYST_CON_EN, SYST_CON_REG(to));
+
+	/*
+	 * Write new timeout ticks. Timer shall start countdown
+	 * after timeout ticks are updated.
+	 */
+	writel(ticks, SYST_VAL_REG(to));
+
+	/* Enable interrupt */
+	writel(SYST_CON_EN | SYST_CON_IRQ_EN, SYST_CON_REG(to));
+
+	return 0;
+}
+
+static int mtk_syst_clkevt_shutdown(struct clock_event_device *clkevt)
+{
+	/* Disable timer */
+	writel(0, SYST_CON_REG(to_timer_of(clkevt)));
+
+	return 0;
+}
+
+static int mtk_syst_clkevt_resume(struct clock_event_device *clkevt)
+{
+	return mtk_syst_clkevt_shutdown(clkevt);
+}
+
+static int mtk_syst_clkevt_oneshot(struct clock_event_device *clkevt)
+{
+	return 0;
+}
+
+static u64 notrace mtk_gpt_read_sched_clock(void)
+{
+	return readl_relaxed(gpt_sched_reg);
+}
+
+static void mtk_gpt_clkevt_time_stop(struct timer_of *to, u8 timer)
+{
+	u32 val;
+
+	val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
+	writel(val & ~GPT_CTRL_ENABLE, timer_of_base(to) +
+	       GPT_CTRL_REG(timer));
+}
+
+static void mtk_gpt_clkevt_time_setup(struct timer_of *to,
+				      unsigned long delay, u8 timer)
+{
+	writel(delay, timer_of_base(to) + GPT_CMP_REG(timer));
+}
+
+static void mtk_gpt_clkevt_time_start(struct timer_of *to,
+				      bool periodic, u8 timer)
+{
+	u32 val;
+
+	/* Acknowledge interrupt */
+	writel(GPT_IRQ_ACK(timer), timer_of_base(to) + GPT_IRQ_ACK_REG);
+
+	val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
+
+	/* Clear 2 bit timer operation mode field */
+	val &= ~GPT_CTRL_OP(0x3);
+
+	if (periodic)
+		val |= GPT_CTRL_OP(GPT_CTRL_OP_REPEAT);
+	else
+		val |= GPT_CTRL_OP(GPT_CTRL_OP_ONESHOT);
+
+	writel(val | GPT_CTRL_ENABLE | GPT_CTRL_CLEAR,
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
+}
+
+static int mtk_gpt_clkevt_shutdown(struct clock_event_device *clk)
+{
+	mtk_gpt_clkevt_time_stop(to_timer_of(clk), TIMER_CLK_EVT);
+
+	return 0;
+}
+
+static int mtk_gpt_clkevt_set_periodic(struct clock_event_device *clk)
+{
+	struct timer_of *to = to_timer_of(clk);
+
+	mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(to, to->of_clk.period, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(to, true, TIMER_CLK_EVT);
+
+	return 0;
+}
+
+static int mtk_gpt_clkevt_next_event(unsigned long event,
+				     struct clock_event_device *clk)
+{
+	struct timer_of *to = to_timer_of(clk);
+
+	mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(to, event, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(to, false, TIMER_CLK_EVT);
+
+	return 0;
+}
+
+static irqreturn_t mtk_gpt_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *clkevt = (struct clock_event_device *)dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
+
+	/* Acknowledge timer0 irq */
+	writel(GPT_IRQ_ACK(TIMER_CLK_EVT), timer_of_base(to) + GPT_IRQ_ACK_REG);
+	clkevt->event_handler(clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static void
+__init mtk_gpt_setup(struct timer_of *to, u8 timer, u8 option)
+{
+	writel(GPT_CTRL_CLEAR | GPT_CTRL_DISABLE,
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
+
+	writel(GPT_CLK_SRC(GPT_CLK_SRC_SYS13M) | GPT_CLK_DIV1,
+	       timer_of_base(to) + GPT_CLK_REG(timer));
+
+	writel(0x0, timer_of_base(to) + GPT_CMP_REG(timer));
+
+	writel(GPT_CTRL_OP(option) | GPT_CTRL_ENABLE,
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
+}
+
+static void mtk_gpt_enable_irq(struct timer_of *to, u8 timer)
+{
+	u32 val;
+
+	/* Disable all interrupts */
+	writel(0x0, timer_of_base(to) + GPT_IRQ_EN_REG);
+
+	/* Acknowledge all spurious pending interrupts */
+	writel(0x3f, timer_of_base(to) + GPT_IRQ_ACK_REG);
+
+	val = readl(timer_of_base(to) + GPT_IRQ_EN_REG);
+	writel(val | GPT_IRQ_ENABLE(timer),
+	       timer_of_base(to) + GPT_IRQ_EN_REG);
+}
+
+static struct timer_of to = {
+	.flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+	.clkevt = {
+		.name = "mtk-clkevt",
+		.rating = 300,
+		.cpumask = cpu_possible_mask,
+	},
+
+	.of_irq = {
+		.flags = IRQF_TIMER | IRQF_IRQPOLL,
+	},
+};
+
+static int __init mtk_syst_init(struct device_node *node)
+{
+	int ret;
+
+	to.clkevt.features = CLOCK_EVT_FEAT_DYNIRQ | CLOCK_EVT_FEAT_ONESHOT;
+	to.clkevt.set_state_shutdown = mtk_syst_clkevt_shutdown;
+	to.clkevt.set_state_oneshot = mtk_syst_clkevt_oneshot;
+	to.clkevt.tick_resume = mtk_syst_clkevt_resume;
+	to.clkevt.set_next_event = mtk_syst_clkevt_next_event;
+	to.of_irq.handler = mtk_syst_handler;
+
+	ret = timer_of_init(node, &to);
+	if (ret)
+		goto err;
+
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					TIMER_SYNC_TICKS, 0xffffffff);
+
+	return 0;
+err:
+	timer_of_cleanup(&to);
+	return ret;
+}
+
+static int __init mtk_gpt_init(struct device_node *node)
+{
+	int ret;
+
+	to.clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	to.clkevt.set_state_shutdown = mtk_gpt_clkevt_shutdown;
+	to.clkevt.set_state_periodic = mtk_gpt_clkevt_set_periodic;
+	to.clkevt.set_state_oneshot = mtk_gpt_clkevt_shutdown;
+	to.clkevt.tick_resume = mtk_gpt_clkevt_shutdown;
+	to.clkevt.set_next_event = mtk_gpt_clkevt_next_event;
+	to.of_irq.handler = mtk_gpt_interrupt;
+
+	ret = timer_of_init(node, &to);
+	if (ret)
+		goto err;
+
+	/* Configure clock source */
+	mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
+	clocksource_mmio_init(timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC),
+			      node->name, timer_of_rate(&to), 300, 32,
+			      clocksource_mmio_readl_up);
+	gpt_sched_reg = timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC);
+	sched_clock_register(mtk_gpt_read_sched_clock, 32, timer_of_rate(&to));
+
+	/* Configure clock event */
+	mtk_gpt_setup(&to, TIMER_CLK_EVT, GPT_CTRL_OP_REPEAT);
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					TIMER_SYNC_TICKS, 0xffffffff);
+
+	mtk_gpt_enable_irq(&to, TIMER_CLK_EVT);
+
+	return 0;
+err:
+	timer_of_cleanup(&to);
+	return ret;
+}
+TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
+TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init);
diff --git a/drivers/clocksource/timer-sprd.c b/drivers/clocksource/timer-sprd.c
index ef9ebeafb3ed..430cb99d8d79 100644
--- a/drivers/clocksource/timer-sprd.c
+++ b/drivers/clocksource/timer-sprd.c
@@ -156,4 +156,54 @@ static int __init sprd_timer_init(struct device_node *np)
 	return 0;
 }
 
+static struct timer_of suspend_to = {
+	.flags = TIMER_OF_BASE | TIMER_OF_CLOCK,
+};
+
+static u64 sprd_suspend_timer_read(struct clocksource *cs)
+{
+	return ~(u64)readl_relaxed(timer_of_base(&suspend_to) +
+				   TIMER_VALUE_SHDW_LO) & cs->mask;
+}
+
+static int sprd_suspend_timer_enable(struct clocksource *cs)
+{
+	sprd_timer_update_counter(timer_of_base(&suspend_to),
+				  TIMER_VALUE_LO_MASK);
+	sprd_timer_enable(timer_of_base(&suspend_to), TIMER_CTL_PERIOD_MODE);
+
+	return 0;
+}
+
+static void sprd_suspend_timer_disable(struct clocksource *cs)
+{
+	sprd_timer_disable(timer_of_base(&suspend_to));
+}
+
+static struct clocksource suspend_clocksource = {
+	.name	= "sprd_suspend_timer",
+	.rating	= 200,
+	.read	= sprd_suspend_timer_read,
+	.enable = sprd_suspend_timer_enable,
+	.disable = sprd_suspend_timer_disable,
+	.mask	= CLOCKSOURCE_MASK(32),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_SUSPEND_NONSTOP,
+};
+
+static int __init sprd_suspend_timer_init(struct device_node *np)
+{
+	int ret;
+
+	ret = timer_of_init(np, &suspend_to);
+	if (ret)
+		return ret;
+
+	clocksource_register_hz(&suspend_clocksource,
+				timer_of_rate(&suspend_to));
+
+	return 0;
+}
+
 TIMER_OF_DECLARE(sc9860_timer, "sprd,sc9860-timer", sprd_timer_init);
+TIMER_OF_DECLARE(sc9860_persistent_timer, "sprd,sc9860-suspend-timer",
+		 sprd_suspend_timer_init);
diff --git a/drivers/clocksource/timer-ti-32k.c b/drivers/clocksource/timer-ti-32k.c
index 880a861ab3c8..29e2e1a78a43 100644
--- a/drivers/clocksource/timer-ti-32k.c
+++ b/drivers/clocksource/timer-ti-32k.c
@@ -78,8 +78,7 @@ static struct ti_32k ti_32k_timer = {
 		.rating		= 250,
 		.read		= ti_32k_read_cycles,
 		.mask		= CLOCKSOURCE_MASK(32),
-		.flags		= CLOCK_SOURCE_IS_CONTINUOUS |
-				CLOCK_SOURCE_SUSPEND_NONSTOP,
+		.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 	},
 };
 
diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c
index a6a0338eea77..f74689334f7c 100644
--- a/drivers/clocksource/zevio-timer.c
+++ b/drivers/clocksource/zevio-timer.c
@@ -162,7 +162,7 @@ static int __init zevio_timer_add(struct device_node *node)
 		timer->clkevt.set_state_oneshot = zevio_timer_set_oneshot;
 		timer->clkevt.tick_resume	= zevio_timer_set_oneshot;
 		timer->clkevt.rating		= 200;
-		timer->clkevt.cpumask		= cpu_all_mask;
+		timer->clkevt.cpumask		= cpu_possible_mask;
 		timer->clkevt.features		= CLOCK_EVT_FEAT_ONESHOT;
 		timer->clkevt.irq		= irqnr;
 
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 739da90ff3f6..75491fc841a6 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -51,6 +51,16 @@
 #define  ARMADA_37XX_DVFS_LOAD_2	2
 #define  ARMADA_37XX_DVFS_LOAD_3	3
 
+/* AVS register set */
+#define ARMADA_37XX_AVS_CTL0		0x0
+#define	 ARMADA_37XX_AVS_ENABLE		BIT(30)
+#define	 ARMADA_37XX_AVS_HIGH_VDD_LIMIT	16
+#define	 ARMADA_37XX_AVS_LOW_VDD_LIMIT	22
+#define	 ARMADA_37XX_AVS_VDD_MASK	0x3F
+#define ARMADA_37XX_AVS_CTL2		0x8
+#define	 ARMADA_37XX_AVS_LOW_VDD_EN	BIT(6)
+#define ARMADA_37XX_AVS_VSET(x)	    (0x1C + 4 * (x))
+
 /*
  * On Armada 37xx the Power management manages 4 level of CPU load,
  * each level can be associated with a CPU clock source, a CPU
@@ -58,6 +68,17 @@
  */
 #define LOAD_LEVEL_NR	4
 
+#define MIN_VOLT_MV 1000
+
+/*  AVS value for the corresponding voltage (in mV) */
+static int avs_map[] = {
+	747, 758, 770, 782, 793, 805, 817, 828, 840, 852, 863, 875, 887, 898,
+	910, 922, 933, 945, 957, 968, 980, 992, 1003, 1015, 1027, 1038, 1050,
+	1062, 1073, 1085, 1097, 1108, 1120, 1132, 1143, 1155, 1167, 1178, 1190,
+	1202, 1213, 1225, 1237, 1248, 1260, 1272, 1283, 1295, 1307, 1318, 1330,
+	1342
+};
+
 struct armada37xx_cpufreq_state {
 	struct regmap *regmap;
 	u32 nb_l0l1;
@@ -71,6 +92,7 @@ static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state;
 struct armada_37xx_dvfs {
 	u32 cpu_freq_max;
 	u8 divider[LOAD_LEVEL_NR];
+	u32 avs[LOAD_LEVEL_NR];
 };
 
 static struct armada_37xx_dvfs armada_37xx_dvfs[] = {
@@ -148,6 +170,128 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
 	clk_set_parent(clk, parent);
 }
 
+/*
+ * Find out the armada 37x supported AVS value whose voltage value is
+ * the round-up closest to the target voltage value.
+ */
+static u32 armada_37xx_avs_val_match(int target_vm)
+{
+	u32 avs;
+
+	/* Find out the round-up closest supported voltage value */
+	for (avs = 0; avs < ARRAY_SIZE(avs_map); avs++)
+		if (avs_map[avs] >= target_vm)
+			break;
+
+	/*
+	 * If all supported voltages are smaller than target one,
+	 * choose the largest supported voltage
+	 */
+	if (avs == ARRAY_SIZE(avs_map))
+		avs = ARRAY_SIZE(avs_map) - 1;
+
+	return avs;
+}
+
+/*
+ * For Armada 37xx soc, L0(VSET0) VDD AVS value is set to SVC revision
+ * value or a default value when SVC is not supported.
+ * - L0 can be read out from the register of AVS_CTRL_0 and L0 voltage
+ *   can be got from the mapping table of avs_map.
+ * - L1 voltage should be about 100mv smaller than L0 voltage
+ * - L2 & L3 voltage should be about 150mv smaller than L0 voltage.
+ * This function calculates L1 & L2 & L3 AVS values dynamically based
+ * on L0 voltage and fill all AVS values to the AVS value table.
+ */
+static void __init armada37xx_cpufreq_avs_configure(struct regmap *base,
+						struct armada_37xx_dvfs *dvfs)
+{
+	unsigned int target_vm;
+	int load_level = 0;
+	u32 l0_vdd_min;
+
+	if (base == NULL)
+		return;
+
+	/* Get L0 VDD min value */
+	regmap_read(base, ARMADA_37XX_AVS_CTL0, &l0_vdd_min);
+	l0_vdd_min = (l0_vdd_min >> ARMADA_37XX_AVS_LOW_VDD_LIMIT) &
+		ARMADA_37XX_AVS_VDD_MASK;
+	if (l0_vdd_min >= ARRAY_SIZE(avs_map))  {
+		pr_err("L0 VDD MIN %d is not correct.\n", l0_vdd_min);
+		return;
+	}
+	dvfs->avs[0] = l0_vdd_min;
+
+	if (avs_map[l0_vdd_min] <= MIN_VOLT_MV) {
+		/*
+		 * If L0 voltage is smaller than 1000mv, then all VDD sets
+		 * use L0 voltage;
+		 */
+		u32 avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV);
+
+		for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++)
+			dvfs->avs[load_level] = avs_min;
+
+		return;
+	}
+
+	/*
+	 * L1 voltage is equal to L0 voltage - 100mv and it must be
+	 * larger than 1000mv
+	 */
+
+	target_vm = avs_map[l0_vdd_min] - 100;
+	target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV;
+	dvfs->avs[1] = armada_37xx_avs_val_match(target_vm);
+
+	/*
+	 * L2 & L3 voltage is equal to L0 voltage - 150mv and it must
+	 * be larger than 1000mv
+	 */
+	target_vm = avs_map[l0_vdd_min] - 150;
+	target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV;
+	dvfs->avs[2] = dvfs->avs[3] = armada_37xx_avs_val_match(target_vm);
+}
+
+static void __init armada37xx_cpufreq_avs_setup(struct regmap *base,
+						struct armada_37xx_dvfs *dvfs)
+{
+	unsigned int avs_val = 0, freq;
+	int load_level = 0;
+
+	if (base == NULL)
+		return;
+
+	/* Disable AVS before the configuration */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL0,
+			   ARMADA_37XX_AVS_ENABLE, 0);
+
+
+	/* Enable low voltage mode */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL2,
+			   ARMADA_37XX_AVS_LOW_VDD_EN,
+			   ARMADA_37XX_AVS_LOW_VDD_EN);
+
+
+	for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++) {
+		freq = dvfs->cpu_freq_max / dvfs->divider[load_level];
+
+		avs_val = dvfs->avs[load_level];
+		regmap_update_bits(base, ARMADA_37XX_AVS_VSET(load_level-1),
+		    ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_HIGH_VDD_LIMIT |
+		    ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_LOW_VDD_LIMIT,
+		    avs_val << ARMADA_37XX_AVS_HIGH_VDD_LIMIT |
+		    avs_val << ARMADA_37XX_AVS_LOW_VDD_LIMIT);
+	}
+
+	/* Enable AVS after the configuration */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL0,
+			   ARMADA_37XX_AVS_ENABLE,
+			   ARMADA_37XX_AVS_ENABLE);
+
+}
+
 static void armada37xx_cpufreq_disable_dvfs(struct regmap *base)
 {
 	unsigned int reg = ARMADA_37XX_NB_DYN_MOD,
@@ -216,7 +360,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	struct platform_device *pdev;
 	unsigned long freq;
 	unsigned int cur_frequency;
-	struct regmap *nb_pm_base;
+	struct regmap *nb_pm_base, *avs_base;
 	struct device *cpu_dev;
 	int load_lvl, ret;
 	struct clk *clk;
@@ -227,6 +371,14 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	if (IS_ERR(nb_pm_base))
 		return -ENODEV;
 
+	avs_base =
+		syscon_regmap_lookup_by_compatible("marvell,armada-3700-avs");
+
+	/* if AVS is not present don't use it but still try to setup dvfs */
+	if (IS_ERR(avs_base)) {
+		pr_info("Syscon failed for Adapting Voltage Scaling: skip it\n");
+		avs_base = NULL;
+	}
 	/* Before doing any configuration on the DVFS first, disable it */
 	armada37xx_cpufreq_disable_dvfs(nb_pm_base);
 
@@ -270,16 +422,21 @@ static int __init armada37xx_cpufreq_driver_init(void)
 
 	armada37xx_cpufreq_state->regmap = nb_pm_base;
 
+	armada37xx_cpufreq_avs_configure(avs_base, dvfs);
+	armada37xx_cpufreq_avs_setup(avs_base, dvfs);
+
 	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
 	clk_put(clk);
 
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
 	     load_lvl++) {
+		unsigned long u_volt = avs_map[dvfs->avs[load_lvl]] * 1000;
 		freq = cur_frequency / dvfs->divider[load_lvl];
-
-		ret = dev_pm_opp_add(cpu_dev, freq, 0);
+		ret = dev_pm_opp_add(cpu_dev, freq, u_volt);
 		if (ret)
 			goto remove_opp;
+
+
 	}
 
 	/* Now that everything is setup, enable the DVFS at hardware level */
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index a9d3eec32795..30f302149730 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -296,10 +296,62 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	return ret;
 }
 
+static inline u64 get_delta(u64 t1, u64 t0)
+{
+	if (t1 > t0 || t0 > ~(u32)0)
+		return t1 - t0;
+
+	return (u32)t1 - (u32)t0;
+}
+
+static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
+{
+	u64 delta_reference, delta_delivered;
+	u64 reference_perf, delivered_perf;
+
+	reference_perf = fb_ctrs_t0.reference_perf;
+
+	delta_reference = get_delta(fb_ctrs_t1.reference,
+				    fb_ctrs_t0.reference);
+	delta_delivered = get_delta(fb_ctrs_t1.delivered,
+				    fb_ctrs_t0.delivered);
+
+	/* Check to avoid divide-by zero */
+	if (delta_reference || delta_delivered)
+		delivered_perf = (reference_perf * delta_delivered) /
+					delta_reference;
+	else
+		delivered_perf = cpu->perf_ctrls.desired_perf;
+
+	return cppc_cpufreq_perf_to_khz(cpu, delivered_perf);
+}
+
+static unsigned int cppc_cpufreq_get_rate(unsigned int cpunum)
+{
+	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
+	struct cppc_cpudata *cpu = all_cpu_data[cpunum];
+	int ret;
+
+	ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t0);
+	if (ret)
+		return ret;
+
+	udelay(2); /* 2usec delay between sampling */
+
+	ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t1);
+	if (ret)
+		return ret;
+
+	return cppc_get_rate_from_fbctrs(cpu, fb_ctrs_t0, fb_ctrs_t1);
+}
+
 static struct cpufreq_driver cppc_cpufreq_driver = {
 	.flags = CPUFREQ_CONST_LOOPS,
 	.verify = cppc_verify_policy,
 	.target = cppc_cpufreq_set_target,
+	.get = cppc_cpufreq_get_rate,
 	.init = cppc_cpufreq_cpu_init,
 	.stop_cpu = cppc_cpufreq_stop_cpu,
 	.name = "cppc_cpufreq",
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b0dfd3222013..f53fb41efb7b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -923,7 +923,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
 
-	cpus_read_lock();
+	/*
+	 * cpus_read_trylock() is used here to work around a circular lock
+	 * dependency problem with respect to the cpufreq_register_driver().
+	 */
+	if (!cpus_read_trylock())
+		return -EBUSY;
 
 	if (cpu_online(policy->cpu)) {
 		down_write(&policy->rwsem);
@@ -2236,6 +2241,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	policy->min = new_policy->min;
 	policy->max = new_policy->max;
+	trace_cpu_frequency_limits(policy);
 
 	policy->cached_target_freq = UINT_MAX;
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 8b3c2a79ad6c..b2ff423ad7f8 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -9,6 +9,7 @@
 #include <linux/clk.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_cooling.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -50,6 +51,7 @@ static struct clk_bulk_data clks[] = {
 };
 
 static struct device *cpu_dev;
+static struct thermal_cooling_device *cdev;
 static bool free_opp;
 static struct cpufreq_frequency_table *freq_table;
 static unsigned int max_freq;
@@ -191,6 +193,16 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 	return 0;
 }
 
+static void imx6q_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	cdev = of_cpufreq_cooling_register(policy);
+
+	if (!cdev)
+		dev_err(cpu_dev,
+			"running cpufreq without cooling device: %ld\n",
+			PTR_ERR(cdev));
+}
+
 static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret;
@@ -202,13 +214,22 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 	return ret;
 }
 
+static int imx6q_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_cooling_unregister(cdev);
+
+	return 0;
+}
+
 static struct cpufreq_driver imx6q_cpufreq_driver = {
 	.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = imx6q_set_target,
 	.get = cpufreq_generic_get,
 	.init = imx6q_cpufreq_init,
+	.exit = imx6q_cpufreq_exit,
 	.name = "imx6q-cpufreq",
+	.ready = imx6q_cpufreq_ready,
 	.attr = cpufreq_generic_attr,
 	.suspend = cpufreq_generic_suspend,
 };
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index ece120da3353..b6a1aadaff9f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -311,12 +311,20 @@ static DEFINE_MUTEX(intel_pstate_limits_lock);
 
 #ifdef CONFIG_ACPI
 
-static bool intel_pstate_get_ppc_enable_status(void)
+static bool intel_pstate_acpi_pm_profile_server(void)
 {
 	if (acpi_gbl_FADT.preferred_profile == PM_ENTERPRISE_SERVER ||
 	    acpi_gbl_FADT.preferred_profile == PM_PERFORMANCE_SERVER)
 		return true;
 
+	return false;
+}
+
+static bool intel_pstate_get_ppc_enable_status(void)
+{
+	if (intel_pstate_acpi_pm_profile_server())
+		return true;
+
 	return acpi_ppc;
 }
 
@@ -459,6 +467,11 @@ static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *pol
 static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
 {
 }
+
+static inline bool intel_pstate_acpi_pm_profile_server(void)
+{
+	return false;
+}
 #endif
 
 static inline void update_turbo_state(void)
@@ -657,21 +670,18 @@ static ssize_t store_energy_performance_preference(
 {
 	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
 	char str_preference[21];
-	int ret, i = 0;
+	int ret;
 
 	ret = sscanf(buf, "%20s", str_preference);
 	if (ret != 1)
 		return -EINVAL;
 
-	while (energy_perf_strings[i] != NULL) {
-		if (!strcmp(str_preference, energy_perf_strings[i])) {
-			intel_pstate_set_energy_pref_index(cpu_data, i);
-			return count;
-		}
-		++i;
-	}
+	ret = match_string(energy_perf_strings, -1, str_preference);
+	if (ret < 0)
+		return ret;
 
-	return -EINVAL;
+	intel_pstate_set_energy_pref_index(cpu_data, ret);
+	return count;
 }
 
 static ssize_t show_energy_performance_preference(
@@ -1841,7 +1851,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 		intel_pstate_hwp_enable(cpu);
 
 		id = x86_match_cpu(intel_pstate_hwp_boost_ids);
-		if (id)
+		if (id && intel_pstate_acpi_pm_profile_server())
 			hwp_boost = true;
 	}
 
@@ -1998,7 +2008,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy,
 					 struct cpudata *cpu)
 {
-	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
+	if (!hwp_active &&
+	    cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
 	    policy->max < policy->cpuinfo.max_freq &&
 	    policy->max > cpu->pstate.max_freq) {
 		pr_debug("policy->max > max non turbo frequency\n");
@@ -2072,6 +2083,15 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
 
+	if (hwp_active) {
+		unsigned int max_freq;
+
+		max_freq = global.turbo_disabled ?
+			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
+		if (max_freq < policy->cpuinfo.max_freq)
+			policy->cpuinfo.max_freq = max_freq;
+	}
+
 	intel_pstate_init_acpi_perf_limits(policy);
 
 	policy->fast_switch_possible = true;
@@ -2394,6 +2414,18 @@ static bool __init intel_pstate_no_acpi_pss(void)
 	return true;
 }
 
+static bool __init intel_pstate_no_acpi_pcch(void)
+{
+	acpi_status status;
+	acpi_handle handle;
+
+	status = acpi_get_handle(NULL, "\\_SB", &handle);
+	if (ACPI_FAILURE(status))
+		return true;
+
+	return !acpi_has_method(handle, "PCCH");
+}
+
 static bool __init intel_pstate_has_acpi_ppc(void)
 {
 	int i;
@@ -2453,7 +2485,10 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
 
 	switch (plat_info[idx].data) {
 	case PSS:
-		return intel_pstate_no_acpi_pss();
+		if (!intel_pstate_no_acpi_pss())
+			return false;
+
+		return intel_pstate_no_acpi_pcch();
 	case PPC:
 		return intel_pstate_has_acpi_ppc() && !force_load;
 	}
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 3f0ce2ae35ee..099a849396f6 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -580,6 +580,10 @@ static int __init pcc_cpufreq_init(void)
 {
 	int ret;
 
+	/* Skip initialization if another cpufreq driver is there. */
+	if (cpufreq_get_current_driver())
+		return 0;
+
 	if (acpi_disabled)
 		return 0;
 
@@ -589,6 +593,15 @@ static int __init pcc_cpufreq_init(void)
 		return ret;
 	}
 
+	if (num_present_cpus() > 4) {
+		pcc_cpufreq_driver.flags |= CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING;
+		pr_err("%s: Too many CPUs, dynamic performance scaling disabled\n",
+		       __func__);
+		pr_err("%s: Try to enable another scaling driver through BIOS settings\n",
+		       __func__);
+		pr_err("%s: and complain to the system vendor\n", __func__);
+	}
+
 	ret = cpufreq_register_driver(&pcc_cpufreq_driver);
 
 	return ret;
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
index 01bddacf5c3b..a1830fa25fc5 100644
--- a/drivers/cpufreq/qcom-cpufreq-kryo.c
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -87,8 +87,8 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 	int ret;
 
 	cpu_dev = get_cpu_device(0);
-	if (NULL == cpu_dev)
-		ret = -ENODEV;
+	if (!cpu_dev)
+		return -ENODEV;
 
 	msm8996_version = qcom_cpufreq_kryo_get_msm_id();
 	if (NUM_OF_MSM8996_VERSIONS == msm8996_version) {
@@ -97,8 +97,8 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 	}
 
 	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
-	if (IS_ERR(np))
-		return PTR_ERR(np);
+	if (!np)
+		return -ENOENT;
 
 	ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
 	if (!ret) {
@@ -109,8 +109,9 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 	speedbin_nvmem = of_nvmem_cell_get(np, NULL);
 	of_node_put(np);
 	if (IS_ERR(speedbin_nvmem)) {
-		dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
-			PTR_ERR(speedbin_nvmem));
+		if (PTR_ERR(speedbin_nvmem) != -EPROBE_DEFER)
+			dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
+				PTR_ERR(speedbin_nvmem));
 		return PTR_ERR(speedbin_nvmem);
 	}
 
@@ -183,6 +184,7 @@ static struct platform_driver qcom_cpufreq_kryo_driver = {
 static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = {
 	{ .compatible = "qcom,apq8096", },
 	{ .compatible = "qcom,msm8996", },
+	{}
 };
 
 /*
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index e07bc7ace774..073557f433eb 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -105,7 +105,8 @@ static int __init arm_idle_init_cpu(int cpu)
 
 	ret = cpuidle_register_driver(drv);
 	if (ret) {
-		pr_err("Failed to register cpuidle driver\n");
+		if (ret != -EBUSY)
+			pr_err("Failed to register cpuidle driver\n");
 		goto out_kfree_drv;
 	}
 
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 1c6cbda56afe..09d823d36d3a 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -266,6 +266,8 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key,
 		return;
 	}
 
+	count -= initial;
+
 	if (initial)
 		asm volatile (".byte 0xf3,0x0f,0xa7,0xc8"	/* rep xcryptecb */
 			      : "+S"(input), "+D"(output)
@@ -273,7 +275,7 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key,
 
 	asm volatile (".byte 0xf3,0x0f,0xa7,0xc8"	/* rep xcryptecb */
 		      : "+S"(input), "+D"(output)
-		      : "d"(control_word), "b"(key), "c"(count - initial));
+		      : "d"(control_word), "b"(key), "c"(count));
 }
 
 static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
@@ -284,6 +286,8 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
 	if (count < cbc_fetch_blocks)
 		return cbc_crypt(input, output, key, iv, control_word, count);
 
+	count -= initial;
+
 	if (initial)
 		asm volatile (".byte 0xf3,0x0f,0xa7,0xd0"	/* rep xcryptcbc */
 			      : "+S" (input), "+D" (output), "+a" (iv)
@@ -291,7 +295,7 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
 
 	asm volatile (".byte 0xf3,0x0f,0xa7,0xd0"	/* rep xcryptcbc */
 		      : "+S" (input), "+D" (output), "+a" (iv)
-		      : "d" (control_word), "b" (key), "c" (count-initial));
+		      : "d" (control_word), "b" (key), "c" (count));
 	return iv;
 }
 
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index de2f8297a210..108c37fca782 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -189,14 +189,16 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 
 	/* prevent private mappings from being established */
 	if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
-		dev_info(dev, "%s: %s: fail, attempted private mapping\n",
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, attempted private mapping\n",
 				current->comm, func);
 		return -EINVAL;
 	}
 
 	mask = dax_region->align - 1;
 	if (vma->vm_start & mask || vma->vm_end & mask) {
-		dev_info(dev, "%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
 				current->comm, func, vma->vm_start, vma->vm_end,
 				mask);
 		return -EINVAL;
@@ -204,13 +206,15 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 
 	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV
 			&& (vma->vm_flags & VM_DONTCOPY) == 0) {
-		dev_info(dev, "%s: %s: fail, dax range requires MADV_DONTFORK\n",
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, dax range requires MADV_DONTFORK\n",
 				current->comm, func);
 		return -EINVAL;
 	}
 
 	if (!vma_is_dax(vma)) {
-		dev_info(dev, "%s: %s: fail, vma is not DAX capable\n",
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, vma is not DAX capable\n",
 				current->comm, func);
 		return -EINVAL;
 	}
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 903d9c473749..45276abf03aa 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -86,6 +86,7 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 {
 	struct dax_device *dax_dev;
 	bool dax_enabled = false;
+	struct request_queue *q;
 	pgoff_t pgoff;
 	int err, id;
 	void *kaddr;
@@ -99,6 +100,13 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 		return false;
 	}
 
+	q = bdev_get_queue(bdev);
+	if (!q || !blk_queue_dax(q)) {
+		pr_debug("%s: error: request queue doesn't support dax\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
 	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
 	if (err) {
 		pr_debug("%s: error: unaligned partition for dax\n",
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 0b5b3abe054e..4c49bb1330b5 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -604,28 +604,29 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		mutex_lock(&devfreq->lock);
 	}
 
-	devfreq->min_freq = find_available_min_freq(devfreq);
-	if (!devfreq->min_freq) {
+	devfreq->scaling_min_freq = find_available_min_freq(devfreq);
+	if (!devfreq->scaling_min_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_min_freq = devfreq->min_freq;
+	devfreq->min_freq = devfreq->scaling_min_freq;
 
-	devfreq->max_freq = find_available_max_freq(devfreq);
-	if (!devfreq->max_freq) {
+	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
+	if (!devfreq->scaling_max_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_max_freq = devfreq->max_freq;
+	devfreq->max_freq = devfreq->scaling_max_freq;
 
 	dev_set_name(&devfreq->dev, "devfreq%d",
 				atomic_inc_return(&devfreq_no));
 	err = device_register(&devfreq->dev);
 	if (err) {
 		mutex_unlock(&devfreq->lock);
-		goto err_dev;
+		put_device(&devfreq->dev);
+		goto err_out;
 	}
 
 	devfreq->trans_table =
@@ -672,6 +673,7 @@ err_init:
 	mutex_unlock(&devfreq_list_lock);
 
 	device_unregister(&devfreq->dev);
+	devfreq = NULL;
 err_dev:
 	if (devfreq)
 		kfree(devfreq);
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 3cd6a184fe7c..a9c64f0d3284 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -627,11 +627,9 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 
 	size = sizeof(struct devfreq_event_dev *) * info->num_events;
 	info->edev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
-	if (!info->edev) {
-		dev_err(&pdev->dev,
-			"failed to allocate memory devfreq-event devices\n");
+	if (!info->edev)
 		return -ENOMEM;
-	}
+
 	edev = info->edev;
 	platform_set_drvdata(pdev, info);
 
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 5dfbfa3cc878..e795ad2b3f6b 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -68,15 +68,6 @@ struct rk3399_dmcfreq {
 	struct devfreq_event_dev *edev;
 	struct mutex lock;
 	struct dram_timing timing;
-
-	/*
-	 * DDR Converser of Frequency (DCF) is used to implement DDR frequency
-	 * conversion without the participation of CPU, we will implement and
-	 * control it in arm trust firmware.
-	 */
-	wait_queue_head_t	wait_dcf_queue;
-	int irq;
-	int wait_dcf_flag;
 	struct regulator *vdd_center;
 	unsigned long rate, target_rate;
 	unsigned long volt, target_volt;
@@ -112,31 +103,22 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 		if (err) {
-			dev_err(dev, "Cannot to set voltage %lu uV\n",
+			dev_err(dev, "Cannot set voltage %lu uV\n",
 				target_volt);
 			goto out;
 		}
 	}
-	dmcfreq->wait_dcf_flag = 1;
 
 	err = clk_set_rate(dmcfreq->dmc_clk, target_rate);
 	if (err) {
-		dev_err(dev, "Cannot to set frequency %lu (%d)\n",
-			target_rate, err);
+		dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
+			err);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
 	}
 
 	/*
-	 * Wait until bcf irq happen, it means freq scaling finish in
-	 * arm trust firmware, use 100ms as timeout time.
-	 */
-	if (!wait_event_timeout(dmcfreq->wait_dcf_queue,
-				!dmcfreq->wait_dcf_flag, HZ / 10))
-		dev_warn(dev, "Timeout waiting for dcf interrupt\n");
-
-	/*
 	 * Check the dpll rate,
 	 * There only two result we will get,
 	 * 1. Ddr frequency scaling fail, we still get the old rate.
@@ -146,8 +128,8 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 
 	/* If get the incorrect rate, set voltage to old value. */
 	if (dmcfreq->rate != target_rate) {
-		dev_err(dev, "Get wrong ddr frequency, Request frequency %lu,\
-			Current frequency %lu\n", target_rate, dmcfreq->rate);
+		dev_err(dev, "Got wrong frequency, Request %lu, Current %lu\n",
+			target_rate, dmcfreq->rate);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
@@ -155,7 +137,7 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 	if (err)
-		dev_err(dev, "Cannot to set vol %lu uV\n", target_volt);
+		dev_err(dev, "Cannot set voltage %lu uV\n", target_volt);
 
 	dmcfreq->rate = target_rate;
 	dmcfreq->volt = target_volt;
@@ -241,22 +223,6 @@ static __maybe_unused int rk3399_dmcfreq_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(rk3399_dmcfreq_pm, rk3399_dmcfreq_suspend,
 			 rk3399_dmcfreq_resume);
 
-static irqreturn_t rk3399_dmc_irq(int irq, void *dev_id)
-{
-	struct rk3399_dmcfreq *dmcfreq = dev_id;
-	struct arm_smccc_res res;
-
-	dmcfreq->wait_dcf_flag = 0;
-	wake_up(&dmcfreq->wait_dcf_queue);
-
-	/* Clear the DCF interrupt */
-	arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0,
-		      ROCKCHIP_SIP_CONFIG_DRAM_CLR_IRQ,
-		      0, 0, 0, 0, &res);
-
-	return IRQ_HANDLED;
-}
-
 static int of_get_ddr_timings(struct dram_timing *timing,
 			      struct device_node *np)
 {
@@ -330,16 +296,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = pdev->dev.of_node;
 	struct rk3399_dmcfreq *data;
-	int ret, irq, index, size;
+	int ret, index, size;
 	uint32_t *timing;
 	struct dev_pm_opp *opp;
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev,
-			"Cannot get the dmc interrupt resource: %d\n", irq);
-		return irq;
-	}
 	data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
@@ -348,27 +308,22 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 	data->vdd_center = devm_regulator_get(dev, "center");
 	if (IS_ERR(data->vdd_center)) {
+		if (PTR_ERR(data->vdd_center) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the regulator \"center\"\n");
 		return PTR_ERR(data->vdd_center);
 	}
 
 	data->dmc_clk = devm_clk_get(dev, "dmc_clk");
 	if (IS_ERR(data->dmc_clk)) {
+		if (PTR_ERR(data->dmc_clk) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the clk dmc_clk\n");
 		return PTR_ERR(data->dmc_clk);
 	};
 
-	data->irq = irq;
-	ret = devm_request_irq(dev, irq, rk3399_dmc_irq, 0,
-			       dev_name(dev), data);
-	if (ret) {
-		dev_err(dev, "Failed to request dmc irq: %d\n", ret);
-		return ret;
-	}
-
-	init_waitqueue_head(&data->wait_dcf_queue);
-	data->wait_dcf_flag = 0;
-
 	data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
 	if (IS_ERR(data->edev))
 		return -EPROBE_DEFER;
@@ -420,8 +375,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	data->rate = clk_get_rate(data->dmc_clk);
 
 	opp = devfreq_recommended_opp(dev, &data->rate, 0);
-	if (IS_ERR(opp))
-		return PTR_ERR(opp);
+	if (IS_ERR(opp)) {
+		ret = PTR_ERR(opp);
+		goto err_free_opp;
+	}
 
 	data->rate = dev_pm_opp_get_freq(opp);
 	data->volt = dev_pm_opp_get_voltage(opp);
@@ -433,14 +390,34 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 					   &rk3399_devfreq_dmc_profile,
 					   DEVFREQ_GOV_SIMPLE_ONDEMAND,
 					   &data->ondemand_data);
-	if (IS_ERR(data->devfreq))
-		return PTR_ERR(data->devfreq);
+	if (IS_ERR(data->devfreq)) {
+		ret = PTR_ERR(data->devfreq);
+		goto err_free_opp;
+	}
+
 	devm_devfreq_register_opp_notifier(dev, data->devfreq);
 
 	data->dev = dev;
 	platform_set_drvdata(pdev, data);
 
 	return 0;
+
+err_free_opp:
+	dev_pm_opp_of_remove_table(&pdev->dev);
+	return ret;
+}
+
+static int rk3399_dmcfreq_remove(struct platform_device *pdev)
+{
+	struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(&pdev->dev);
+
+	/*
+	 * Before remove the opp table we need to unregister the opp notifier.
+	 */
+	devm_devfreq_unregister_opp_notifier(dmcfreq->dev, dmcfreq->devfreq);
+	dev_pm_opp_of_remove_table(dmcfreq->dev);
+
+	return 0;
 }
 
 static const struct of_device_id rk3399dmc_devfreq_of_match[] = {
@@ -451,6 +428,7 @@ MODULE_DEVICE_TABLE(of, rk3399dmc_devfreq_of_match);
 
 static struct platform_driver rk3399_dmcfreq_driver = {
 	.probe	= rk3399_dmcfreq_probe,
+	.remove = rk3399_dmcfreq_remove,
 	.driver = {
 		.name	= "rk3399-dmc-freq",
 		.pm	= &rk3399_dmcfreq_pm,
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index fa31cccbe04f..6bfa217ed6d0 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -794,7 +794,7 @@ static struct dma_chan *k3_of_dma_simple_xlate(struct of_phandle_args *dma_spec,
 	struct k3_dma_dev *d = ofdma->of_dma_data;
 	unsigned int request = dma_spec->args[0];
 
-	if (request > d->dma_requests)
+	if (request >= d->dma_requests)
 		return NULL;
 
 	return dma_get_slave_channel(&(d->chans[request].vc.chan));
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index defcdde4d358..de0957fe9668 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -3033,7 +3033,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	pd->src_addr_widths = PL330_DMA_BUSWIDTHS;
 	pd->dst_addr_widths = PL330_DMA_BUSWIDTHS;
 	pd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
-	pd->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	pd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	pd->max_burst = ((pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP) ?
 			 1 : PL330_MAX_BURST);
 
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index b53fb618bbf6..b31c28b67ad3 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -179,6 +179,8 @@ static unsigned int pxad_drcmr(unsigned int line)
 	return 0x1000 + line * 4;
 }
 
+bool pxad_filter_fn(struct dma_chan *chan, void *param);
+
 /*
  * Debug fs
  */
@@ -760,6 +762,8 @@ static void pxad_free_chan_resources(struct dma_chan *dchan)
 	dma_pool_destroy(chan->desc_pool);
 	chan->desc_pool = NULL;
 
+	chan->drcmr = U32_MAX;
+	chan->prio = PXAD_PRIO_LOWEST;
 }
 
 static void pxad_free_desc(struct virt_dma_desc *vd)
@@ -1384,6 +1388,9 @@ static int pxad_init_dmadev(struct platform_device *op,
 		c = devm_kzalloc(&op->dev, sizeof(*c), GFP_KERNEL);
 		if (!c)
 			return -ENOMEM;
+
+		c->drcmr = U32_MAX;
+		c->prio = PXAD_PRIO_LOWEST;
 		c->vc.desc_free = pxad_free_desc;
 		vchan_init(&c->vc, &pdev->slave);
 		init_waitqueue_head(&c->wq_state);
@@ -1396,9 +1403,10 @@ static int pxad_probe(struct platform_device *op)
 {
 	struct pxad_device *pdev;
 	const struct of_device_id *of_id;
+	const struct dma_slave_map *slave_map = NULL;
 	struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev);
 	struct resource *iores;
-	int ret, dma_channels = 0, nb_requestors = 0;
+	int ret, dma_channels = 0, nb_requestors = 0, slave_map_cnt = 0;
 	const enum dma_slave_buswidth widths =
 		DMA_SLAVE_BUSWIDTH_1_BYTE   | DMA_SLAVE_BUSWIDTH_2_BYTES |
 		DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -1429,6 +1437,8 @@ static int pxad_probe(struct platform_device *op)
 	} else if (pdata && pdata->dma_channels) {
 		dma_channels = pdata->dma_channels;
 		nb_requestors = pdata->nb_requestors;
+		slave_map = pdata->slave_map;
+		slave_map_cnt = pdata->slave_map_cnt;
 	} else {
 		dma_channels = 32;	/* default 32 channel */
 	}
@@ -1440,6 +1450,9 @@ static int pxad_probe(struct platform_device *op)
 	pdev->slave.device_prep_dma_memcpy = pxad_prep_memcpy;
 	pdev->slave.device_prep_slave_sg = pxad_prep_slave_sg;
 	pdev->slave.device_prep_dma_cyclic = pxad_prep_dma_cyclic;
+	pdev->slave.filter.map = slave_map;
+	pdev->slave.filter.mapcnt = slave_map_cnt;
+	pdev->slave.filter.fn = pxad_filter_fn;
 
 	pdev->slave.copy_align = PDMA_ALIGNMENT;
 	pdev->slave.src_addr_widths = widths;
diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
index 9b5ca8691f27..a4a931ddf6f6 100644
--- a/drivers/dma/ti/omap-dma.c
+++ b/drivers/dma/ti/omap-dma.c
@@ -1485,7 +1485,11 @@ static int omap_dma_probe(struct platform_device *pdev)
 	od->ddev.src_addr_widths = OMAP_DMA_BUSWIDTHS;
 	od->ddev.dst_addr_widths = OMAP_DMA_BUSWIDTHS;
 	od->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
-	od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	if (__dma_omap15xx(od->plat->dma_attr))
+		od->ddev.residue_granularity =
+				DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	else
+		od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	od->ddev.max_burst = SZ_16M - 1; /* CCEN: 24bit unsigned */
 	od->ddev.dev = &pdev->dev;
 	INIT_LIST_HEAD(&od->ddev.channels);
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 781a4a337557..d8e159feb573 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -87,6 +87,18 @@ config EFI_RUNTIME_WRAPPERS
 config EFI_ARMSTUB
 	bool
 
+config EFI_ARMSTUB_DTB_LOADER
+	bool "Enable the DTB loader"
+	depends on EFI_ARMSTUB
+	help
+	  Select this config option to add support for the dtb= command
+	  line parameter, allowing a device tree blob to be loaded into
+	  memory from the EFI System Partition by the stub.
+
+	  The device tree is typically provided by the platform or by
+	  the bootloader, so this option is mostly for development
+	  purposes only.
+
 config EFI_BOOTLOADER_CONTROL
 	tristate "EFI Bootloader Control"
 	depends on EFI_VARS
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index b5214c143fee..388a929baf95 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -259,7 +259,6 @@ void __init efi_init(void)
 
 	reserve_regions();
 	efi_esrt_init();
-	efi_memmap_unmap();
 
 	memblock_reserve(params.mmap & PAGE_MASK,
 			 PAGE_ALIGN(params.mmap_size +
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 5889cbea60b8..922cfb813109 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -110,11 +110,20 @@ static int __init arm_enable_runtime_services(void)
 {
 	u64 mapsize;
 
-	if (!efi_enabled(EFI_BOOT)) {
+	if (!efi_enabled(EFI_BOOT) || !efi_enabled(EFI_MEMMAP)) {
 		pr_info("EFI services will not be available.\n");
 		return 0;
 	}
 
+	efi_memmap_unmap();
+
+	mapsize = efi.memmap.desc_size * efi.memmap.nr_map;
+
+	if (efi_memmap_init_late(efi.memmap.phys_map, mapsize)) {
+		pr_err("Failed to remap EFI memory map\n");
+		return 0;
+	}
+
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
 		return 0;
@@ -127,13 +136,6 @@ static int __init arm_enable_runtime_services(void)
 
 	pr_info("Remapping and enabling EFI services.\n");
 
-	mapsize = efi.memmap.desc_size * efi.memmap.nr_map;
-
-	if (efi_memmap_init_late(efi.memmap.phys_map, mapsize)) {
-		pr_err("Failed to remap EFI memory map\n");
-		return -ENOMEM;
-	}
-
 	if (!efi_virtmap_init()) {
 		pr_err("UEFI virtual mapping missing or invalid -- runtime services will not be available\n");
 		return -ENOMEM;
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 3bf0dca378a6..a7902fccdcfa 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -48,8 +48,21 @@ u64 cper_next_record_id(void)
 {
 	static atomic64_t seq;
 
-	if (!atomic64_read(&seq))
-		atomic64_set(&seq, ((u64)get_seconds()) << 32);
+	if (!atomic64_read(&seq)) {
+		time64_t time = ktime_get_real_seconds();
+
+		/*
+		 * This code is unlikely to still be needed in year 2106,
+		 * but just in case, let's use a few more bits for timestamps
+		 * after y2038 to be sure they keep increasing monotonically
+		 * for the next few hundred years...
+		 */
+		if (time < 0x80000000)
+			atomic64_set(&seq, (ktime_get_real_seconds()) << 32);
+		else
+			atomic64_set(&seq, 0x8000000000000000ull |
+					   ktime_get_real_seconds() << 24);
+	}
 
 	return atomic64_inc_return(&seq);
 }
@@ -459,7 +472,7 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		else
 			goto err_section_too_small;
 #if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
-	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_ARM)) {
+	} else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 		struct cper_sec_proc_arm *arm_err = acpi_hest_get_payload(gdata);
 
 		printk("%ssection_type: ARM processor error\n", newpfx);
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 232f4915223b..2a29dd9c986d 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -82,8 +82,11 @@ struct mm_struct efi_mm = {
 	.mmap_sem		= __RWSEM_INITIALIZER(efi_mm.mmap_sem),
 	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
+	.cpu_bitmap		= { [BITS_TO_LONGS(NR_CPUS)] = 0},
 };
 
+struct workqueue_struct *efi_rts_wq;
+
 static bool disable_runtime;
 static int __init setup_noefi(char *arg)
 {
@@ -337,6 +340,18 @@ static int __init efisubsys_init(void)
 	if (!efi_enabled(EFI_BOOT))
 		return 0;
 
+	/*
+	 * Since we process only one efi_runtime_service() at a time, an
+	 * ordered workqueue (which creates only one execution context)
+	 * should suffice all our needs.
+	 */
+	efi_rts_wq = alloc_ordered_workqueue("efi_rts_wq", 0);
+	if (!efi_rts_wq) {
+		pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return 0;
+	}
+
 	/* We register the efi directory at /sys/firmware/efi */
 	efi_kobj = kobject_create_and_add("efi", firmware_kobj);
 	if (!efi_kobj) {
@@ -388,7 +403,7 @@ subsys_initcall(efisubsys_init);
  * and if so, populate the supplied memory descriptor with the appropriate
  * data.
  */
-int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
+int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 {
 	efi_memory_desc_t *md;
 
@@ -406,12 +421,6 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 		u64 size;
 		u64 end;
 
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_DATA &&
-		    md->type != EFI_RUNTIME_SERVICES_DATA) {
-			continue;
-		}
-
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
 		if (phys_addr >= md->phys_addr && phys_addr < end) {
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 1ab80e06e7c5..5d06bd247d07 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -250,7 +250,10 @@ void __init efi_esrt_init(void)
 		return;
 
 	rc = efi_mem_desc_lookup(efi.esrt, &md);
-	if (rc < 0) {
+	if (rc < 0 ||
+	    (!(md.attribute & EFI_MEMORY_RUNTIME) &&
+	     md.type != EFI_BOOT_SERVICES_DATA &&
+	     md.type != EFI_RUNTIME_SERVICES_DATA)) {
 		pr_warn("ESRT header is not in the memory map.\n");
 		return;
 	}
@@ -326,7 +329,8 @@ void __init efi_esrt_init(void)
 
 	end = esrt_data + size;
 	pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end);
-	efi_mem_reserve(esrt_data, esrt_data_size);
+	if (md.type == EFI_BOOT_SERVICES_DATA)
+		efi_mem_reserve(esrt_data, esrt_data_size);
 
 	pr_debug("esrt-init: loaded.\n");
 }
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index a34e9290a699..88c322d7c71e 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -11,7 +11,10 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -O2 \
 				   -fPIC -fno-strict-aliasing -mno-red-zone \
 				   -mno-mmx -mno-sse -fshort-wchar
 
-cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie
+# arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
+# disable the stackleak plugin
+cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie \
+				   $(DISABLE_STACKLEAK_PLUGIN)
 cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic -mno-single-pic-base
 
@@ -20,7 +23,7 @@ cflags-$(CONFIG_EFI_ARMSTUB)	+= -I$(srctree)/scripts/dtc/libfdt
 KBUILD_CFLAGS			:= $(cflags-y) -DDISABLE_BRANCH_PROFILING \
 				   -D__NO_FORTIFY \
 				   $(call cc-option,-ffreestanding) \
-				   $(call cc-option,-fno-stack-protector)
+				   $(call cc-option,-fno-stack-protector) \
 
 GCOV_PROFILE			:= n
 KASAN_SANITIZE			:= n
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 01a9d78ee415..6920033de6d4 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -40,31 +40,6 @@
 
 static u64 virtmap_base = EFI_RT_VIRTUAL_BASE;
 
-efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
-			     void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_t *image = __image;
-	efi_file_handle_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-
-	status = sys_table_arg->boottime->handle_protocol(handle,
-				 &fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	status = io->open_volume(io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table_arg, "Failed to open volume\n");
-
-	*__fh = fh;
-	return status;
-}
-
 void efi_char16_printk(efi_system_table_t *sys_table_arg,
 			      efi_char16_t *str)
 {
@@ -202,9 +177,10 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 	 * 'dtb=' unless UEFI Secure Boot is disabled.  We assume that secure
 	 * boot is enabled if we can't determine its state.
 	 */
-	if (secure_boot != efi_secureboot_mode_disabled &&
-	    strstr(cmdline_ptr, "dtb=")) {
-		pr_efi(sys_table, "Ignoring DTB from command line.\n");
+	if (!IS_ENABLED(CONFIG_EFI_ARMSTUB_DTB_LOADER) ||
+	     secure_boot != efi_secureboot_mode_disabled) {
+		if (strstr(cmdline_ptr, "dtb="))
+			pr_efi(sys_table, "Ignoring DTB from command line.\n");
 	} else {
 		status = handle_cmdline_files(sys_table, image, cmdline_ptr,
 					      "dtb=",
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 50a9cab5a834..e94975f4655b 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -413,6 +413,34 @@ static efi_status_t efi_file_close(void *handle)
 	return efi_call_proto(efi_file_handle, close, handle);
 }
 
+static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
+				    efi_loaded_image_t *image,
+				    efi_file_handle_t **__fh)
+{
+	efi_file_io_interface_t *io;
+	efi_file_handle_t *fh;
+	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+	efi_status_t status;
+	void *handle = (void *)(unsigned long)efi_table_attr(efi_loaded_image,
+							     device_handle,
+							     image);
+
+	status = efi_call_early(handle_protocol, handle,
+				&fs_proto, (void **)&io);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
+		return status;
+	}
+
+	status = efi_call_proto(efi_file_io_interface, open_volume, io, &fh);
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table_arg, "Failed to open volume\n");
+	else
+		*__fh = fh;
+
+	return status;
+}
+
 /*
  * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi=
  * option, e.g. efi=nochunk.
@@ -563,8 +591,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
 
 		/* Only open the volume once. */
 		if (!i) {
-			status = efi_open_volume(sys_table_arg, image,
-						 (void **)&fh);
+			status = efi_open_volume(sys_table_arg, image, &fh);
 			if (status != EFI_SUCCESS)
 				goto free_files;
 		}
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index f59564b72ddc..32799cf039ef 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -36,9 +36,6 @@ extern int __pure is_quiet(void);
 
 void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
-efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
-			     void **__fh);
-
 unsigned long get_dram_base(efi_system_table_t *sys_table_arg);
 
 efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index ae54870b2788..aa66cbf23512 100644
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -1,6 +1,15 @@
 /*
  * runtime-wrappers.c - Runtime Services function call wrappers
  *
+ * Implementation summary:
+ * -----------------------
+ * 1. When user/kernel thread requests to execute efi_runtime_service(),
+ * enqueue work to efi_rts_wq.
+ * 2. Caller thread waits for completion until the work is finished
+ * because it's dependent on the return status and execution of
+ * efi_runtime_service().
+ * For instance, get_variable() and get_next_variable().
+ *
  * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  * Split off from arch/x86/platform/efi/efi.c
@@ -22,6 +31,9 @@
 #include <linux/mutex.h>
 #include <linux/semaphore.h>
 #include <linux/stringify.h>
+#include <linux/workqueue.h>
+#include <linux/completion.h>
+
 #include <asm/efi.h>
 
 /*
@@ -33,6 +45,76 @@
 #define __efi_call_virt(f, args...) \
 	__efi_call_virt_pointer(efi.systab->runtime, f, args)
 
+/* efi_runtime_service() function identifiers */
+enum efi_rts_ids {
+	GET_TIME,
+	SET_TIME,
+	GET_WAKEUP_TIME,
+	SET_WAKEUP_TIME,
+	GET_VARIABLE,
+	GET_NEXT_VARIABLE,
+	SET_VARIABLE,
+	QUERY_VARIABLE_INFO,
+	GET_NEXT_HIGH_MONO_COUNT,
+	UPDATE_CAPSULE,
+	QUERY_CAPSULE_CAPS,
+};
+
+/*
+ * efi_runtime_work:	Details of EFI Runtime Service work
+ * @arg<1-5>:		EFI Runtime Service function arguments
+ * @status:		Status of executing EFI Runtime Service
+ * @efi_rts_id:		EFI Runtime Service function identifier
+ * @efi_rts_comp:	Struct used for handling completions
+ */
+struct efi_runtime_work {
+	void *arg1;
+	void *arg2;
+	void *arg3;
+	void *arg4;
+	void *arg5;
+	efi_status_t status;
+	struct work_struct work;
+	enum efi_rts_ids efi_rts_id;
+	struct completion efi_rts_comp;
+};
+
+/*
+ * efi_queue_work:	Queue efi_runtime_service() and wait until it's done
+ * @rts:		efi_runtime_service() function identifier
+ * @rts_arg<1-5>:	efi_runtime_service() function arguments
+ *
+ * Accesses to efi_runtime_services() are serialized by a binary
+ * semaphore (efi_runtime_lock) and caller waits until the work is
+ * finished, hence _only_ one work is queued at a time and the caller
+ * thread waits for completion.
+ */
+#define efi_queue_work(_rts, _arg1, _arg2, _arg3, _arg4, _arg5)		\
+({									\
+	struct efi_runtime_work efi_rts_work;				\
+	efi_rts_work.status = EFI_ABORTED;				\
+									\
+	init_completion(&efi_rts_work.efi_rts_comp);			\
+	INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts);		\
+	efi_rts_work.arg1 = _arg1;					\
+	efi_rts_work.arg2 = _arg2;					\
+	efi_rts_work.arg3 = _arg3;					\
+	efi_rts_work.arg4 = _arg4;					\
+	efi_rts_work.arg5 = _arg5;					\
+	efi_rts_work.efi_rts_id = _rts;					\
+									\
+	/*								\
+	 * queue_work() returns 0 if work was already on queue,         \
+	 * _ideally_ this should never happen.                          \
+	 */								\
+	if (queue_work(efi_rts_wq, &efi_rts_work.work))			\
+		wait_for_completion(&efi_rts_work.efi_rts_comp);	\
+	else								\
+		pr_err("Failed to queue work to efi_rts_wq.\n");	\
+									\
+	efi_rts_work.status;						\
+})
+
 void efi_call_virt_check_flags(unsigned long flags, const char *call)
 {
 	unsigned long cur_flags, mismatch;
@@ -90,13 +172,98 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call)
  */
 static DEFINE_SEMAPHORE(efi_runtime_lock);
 
+/*
+ * Calls the appropriate efi_runtime_service() with the appropriate
+ * arguments.
+ *
+ * Semantics followed by efi_call_rts() to understand efi_runtime_work:
+ * 1. If argument was a pointer, recast it from void pointer to original
+ * pointer type.
+ * 2. If argument was a value, recast it from void pointer to original
+ * pointer type and dereference it.
+ */
+static void efi_call_rts(struct work_struct *work)
+{
+	struct efi_runtime_work *efi_rts_work;
+	void *arg1, *arg2, *arg3, *arg4, *arg5;
+	efi_status_t status = EFI_NOT_FOUND;
+
+	efi_rts_work = container_of(work, struct efi_runtime_work, work);
+	arg1 = efi_rts_work->arg1;
+	arg2 = efi_rts_work->arg2;
+	arg3 = efi_rts_work->arg3;
+	arg4 = efi_rts_work->arg4;
+	arg5 = efi_rts_work->arg5;
+
+	switch (efi_rts_work->efi_rts_id) {
+	case GET_TIME:
+		status = efi_call_virt(get_time, (efi_time_t *)arg1,
+				       (efi_time_cap_t *)arg2);
+		break;
+	case SET_TIME:
+		status = efi_call_virt(set_time, (efi_time_t *)arg1);
+		break;
+	case GET_WAKEUP_TIME:
+		status = efi_call_virt(get_wakeup_time, (efi_bool_t *)arg1,
+				       (efi_bool_t *)arg2, (efi_time_t *)arg3);
+		break;
+	case SET_WAKEUP_TIME:
+		status = efi_call_virt(set_wakeup_time, *(efi_bool_t *)arg1,
+				       (efi_time_t *)arg2);
+		break;
+	case GET_VARIABLE:
+		status = efi_call_virt(get_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, (u32 *)arg3,
+				       (unsigned long *)arg4, (void *)arg5);
+		break;
+	case GET_NEXT_VARIABLE:
+		status = efi_call_virt(get_next_variable, (unsigned long *)arg1,
+				       (efi_char16_t *)arg2,
+				       (efi_guid_t *)arg3);
+		break;
+	case SET_VARIABLE:
+		status = efi_call_virt(set_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, *(u32 *)arg3,
+				       *(unsigned long *)arg4, (void *)arg5);
+		break;
+	case QUERY_VARIABLE_INFO:
+		status = efi_call_virt(query_variable_info, *(u32 *)arg1,
+				       (u64 *)arg2, (u64 *)arg3, (u64 *)arg4);
+		break;
+	case GET_NEXT_HIGH_MONO_COUNT:
+		status = efi_call_virt(get_next_high_mono_count, (u32 *)arg1);
+		break;
+	case UPDATE_CAPSULE:
+		status = efi_call_virt(update_capsule,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2,
+				       *(unsigned long *)arg3);
+		break;
+	case QUERY_CAPSULE_CAPS:
+		status = efi_call_virt(query_capsule_caps,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2, (u64 *)arg3,
+				       (int *)arg4);
+		break;
+	default:
+		/*
+		 * Ideally, we should never reach here because a caller of this
+		 * function should have put the right efi_runtime_service()
+		 * function identifier into efi_rts_work->efi_rts_id
+		 */
+		pr_err("Requested executing invalid EFI Runtime Service.\n");
+	}
+	efi_rts_work->status = status;
+	complete(&efi_rts_work->efi_rts_comp);
+}
+
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	efi_status_t status;
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_time, tm, tc);
+	status = efi_queue_work(GET_TIME, tm, tc, NULL, NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -107,7 +274,7 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_time, tm);
+	status = efi_queue_work(SET_TIME, tm, NULL, NULL, NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -120,7 +287,8 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
+	status = efi_queue_work(GET_WAKEUP_TIME, enabled, pending, tm, NULL,
+				NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -131,7 +299,8 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_wakeup_time, enabled, tm);
+	status = efi_queue_work(SET_WAKEUP_TIME, &enabled, tm, NULL, NULL,
+				NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -146,8 +315,8 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_variable, name, vendor, attr, data_size,
-			       data);
+	status = efi_queue_work(GET_VARIABLE, name, vendor, attr, data_size,
+				data);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -160,7 +329,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_next_variable, name_size, name, vendor);
+	status = efi_queue_work(GET_NEXT_VARIABLE, name_size, name, vendor,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -175,8 +345,8 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
-			       data);
+	status = efi_queue_work(SET_VARIABLE, name, vendor, &attr, &data_size,
+				data);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -210,8 +380,8 @@ static efi_status_t virt_efi_query_variable_info(u32 attr,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(query_variable_info, attr, storage_space,
-			       remaining_space, max_variable_size);
+	status = efi_queue_work(QUERY_VARIABLE_INFO, &attr, storage_space,
+				remaining_space, max_variable_size, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -242,7 +412,8 @@ static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_next_high_mono_count, count);
+	status = efi_queue_work(GET_NEXT_HIGH_MONO_COUNT, count, NULL, NULL,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -272,7 +443,8 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(update_capsule, capsules, count, sg_list);
+	status = efi_queue_work(UPDATE_CAPSULE, capsules, &count, &sg_list,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -289,8 +461,8 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(query_capsule_caps, capsules, count, max_size,
-			       reset_type);
+	status = efi_queue_work(QUERY_CAPSULE_CAPS, capsules, &count,
+				max_size, reset_type, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c
index dd4edd8f22ce..7fa793672a7a 100644
--- a/drivers/fpga/altera-cvp.c
+++ b/drivers/fpga/altera-cvp.c
@@ -455,8 +455,10 @@ static int altera_cvp_probe(struct pci_dev *pdev,
 
 	mgr = fpga_mgr_create(&pdev->dev, conf->mgr_name,
 			      &altera_cvp_ops, conf);
-	if (!mgr)
-		return -ENOMEM;
+	if (!mgr) {
+		ret = -ENOMEM;
+		goto err_unmap;
+	}
 
 	pci_set_drvdata(pdev, mgr);
 
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 94396caaca75..d5d79727c55d 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -720,4 +720,4 @@ static int __init tegra_gpio_init(void)
 {
 	return platform_driver_register(&tegra_gpio_driver);
 }
-postcore_initcall(tegra_gpio_init);
+subsys_initcall(tegra_gpio_init);
diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c
index d3cf9502e7e7..58faeb1cef63 100644
--- a/drivers/gpio/gpio-uniphier.c
+++ b/drivers/gpio/gpio-uniphier.c
@@ -181,7 +181,11 @@ static int uniphier_gpio_to_irq(struct gpio_chip *chip, unsigned int offset)
 	fwspec.fwnode = of_node_to_fwnode(chip->parent->of_node);
 	fwspec.param_count = 2;
 	fwspec.param[0] = offset - UNIPHIER_GPIO_IRQ_OFFSET;
-	fwspec.param[1] = IRQ_TYPE_NONE;
+	/*
+	 * IRQ_TYPE_NONE is rejected by the parent irq domain. Set LEVEL_HIGH
+	 * temporarily. Anyway, ->irq_set_type() will override it later.
+	 */
+	fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH;
 
 	return irq_create_fwspec_mapping(&fwspec);
 }
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index e2232cbcec8b..c48ed9d89ff5 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -25,6 +25,7 @@
 
 struct acpi_gpio_event {
 	struct list_head node;
+	struct list_head initial_sync_list;
 	acpi_handle handle;
 	unsigned int pin;
 	unsigned int irq;
@@ -50,6 +51,9 @@ struct acpi_gpio_chip {
 	struct list_head events;
 };
 
+static LIST_HEAD(acpi_gpio_initial_sync_list);
+static DEFINE_MUTEX(acpi_gpio_initial_sync_list_lock);
+
 static int acpi_gpiochip_find(struct gpio_chip *gc, void *data)
 {
 	if (!gc->parent)
@@ -85,6 +89,21 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin)
 	return gpiochip_get_desc(chip, pin);
 }
 
+static void acpi_gpio_add_to_initial_sync_list(struct acpi_gpio_event *event)
+{
+	mutex_lock(&acpi_gpio_initial_sync_list_lock);
+	list_add(&event->initial_sync_list, &acpi_gpio_initial_sync_list);
+	mutex_unlock(&acpi_gpio_initial_sync_list_lock);
+}
+
+static void acpi_gpio_del_from_initial_sync_list(struct acpi_gpio_event *event)
+{
+	mutex_lock(&acpi_gpio_initial_sync_list_lock);
+	if (!list_empty(&event->initial_sync_list))
+		list_del_init(&event->initial_sync_list);
+	mutex_unlock(&acpi_gpio_initial_sync_list_lock);
+}
+
 static irqreturn_t acpi_gpio_irq_handler(int irq, void *data)
 {
 	struct acpi_gpio_event *event = data;
@@ -136,7 +155,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 	irq_handler_t handler = NULL;
 	struct gpio_desc *desc;
 	unsigned long irqflags;
-	int ret, pin, irq;
+	int ret, pin, irq, value;
 
 	if (!acpi_gpio_get_irq_resource(ares, &agpio))
 		return AE_OK;
@@ -167,6 +186,8 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 
 	gpiod_direction_input(desc);
 
+	value = gpiod_get_value(desc);
+
 	ret = gpiochip_lock_as_irq(chip, pin);
 	if (ret) {
 		dev_err(chip->parent, "Failed to lock GPIO as interrupt\n");
@@ -208,6 +229,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 	event->irq = irq;
 	event->pin = pin;
 	event->desc = desc;
+	INIT_LIST_HEAD(&event->initial_sync_list);
 
 	ret = request_threaded_irq(event->irq, NULL, handler, irqflags,
 				   "ACPI:Event", event);
@@ -222,6 +244,18 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 		enable_irq_wake(irq);
 
 	list_add_tail(&event->node, &acpi_gpio->events);
+
+	/*
+	 * Make sure we trigger the initial state of the IRQ when using RISING
+	 * or FALLING.  Note we run the handlers on late_init, the AML code
+	 * may refer to OperationRegions from other (builtin) drivers which
+	 * may be probed after us.
+	 */
+	if (handler == acpi_gpio_irq_handler &&
+	    (((irqflags & IRQF_TRIGGER_RISING) && value == 1) ||
+	     ((irqflags & IRQF_TRIGGER_FALLING) && value == 0)))
+		acpi_gpio_add_to_initial_sync_list(event);
+
 	return AE_OK;
 
 fail_free_event:
@@ -294,6 +328,8 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip)
 	list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) {
 		struct gpio_desc *desc;
 
+		acpi_gpio_del_from_initial_sync_list(event);
+
 		if (irqd_is_wakeup_set(irq_get_irq_data(event->irq)))
 			disable_irq_wake(event->irq);
 
@@ -353,7 +389,7 @@ EXPORT_SYMBOL_GPL(devm_acpi_dev_remove_driver_gpios);
 
 static bool acpi_get_driver_gpio_data(struct acpi_device *adev,
 				      const char *name, int index,
-				      struct acpi_reference_args *args,
+				      struct fwnode_reference_args *args,
 				      unsigned int *quirks)
 {
 	const struct acpi_gpio_mapping *gm;
@@ -365,7 +401,7 @@ static bool acpi_get_driver_gpio_data(struct acpi_device *adev,
 		if (!strcmp(name, gm->name) && gm->data && index < gm->size) {
 			const struct acpi_gpio_params *par = gm->data + index;
 
-			args->adev = adev;
+			args->fwnode = acpi_fwnode_handle(adev);
 			args->args[0] = par->crs_entry_index;
 			args->args[1] = par->line_index;
 			args->args[2] = par->active_low;
@@ -528,7 +564,7 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 				     const char *propname, int index,
 				     struct acpi_gpio_lookup *lookup)
 {
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	unsigned int quirks = 0;
 	int ret;
 
@@ -549,6 +585,8 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 	 * The property was found and resolved, so need to lookup the GPIO based
 	 * on returned args.
 	 */
+	if (!to_acpi_device_node(args.fwnode))
+		return -EINVAL;
 	if (args.nargs != 3)
 		return -EPROTO;
 
@@ -556,8 +594,9 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 	lookup->pin_index = args.args[1];
 	lookup->active_low = !!args.args[2];
 
-	lookup->info.adev = args.adev;
+	lookup->info.adev = to_acpi_device_node(args.fwnode);
 	lookup->info.quirks = quirks;
+
 	return 0;
 }
 
@@ -1158,3 +1197,21 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id)
 
 	return con_id == NULL;
 }
+
+/* Sync the initial state of handlers after all builtin drivers have probed */
+static int acpi_gpio_initial_sync(void)
+{
+	struct acpi_gpio_event *event, *ep;
+
+	mutex_lock(&acpi_gpio_initial_sync_list_lock);
+	list_for_each_entry_safe(event, ep, &acpi_gpio_initial_sync_list,
+				 initial_sync_list) {
+		acpi_evaluate_object(event->handle, NULL, NULL, NULL);
+		list_del_init(&event->initial_sync_list);
+	}
+	mutex_unlock(&acpi_gpio_initial_sync_list_lock);
+
+	return 0;
+}
+/* We must use _sync so that this runs after the first deferred_probe run */
+late_initcall_sync(acpi_gpio_initial_sync);
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 28d968088131..53a14ee8ad6d 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -64,7 +64,8 @@ static void of_gpio_flags_quirks(struct device_node *np,
 	 * Note that active low is the default.
 	 */
 	if (IS_ENABLED(CONFIG_REGULATOR) &&
-	    (of_device_is_compatible(np, "reg-fixed-voltage") ||
+	    (of_device_is_compatible(np, "regulator-fixed") ||
+	     of_device_is_compatible(np, "reg-fixed-voltage") ||
 	     of_device_is_compatible(np, "regulator-gpio"))) {
 		/*
 		 * The regulator GPIO handles are specified such that the
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index a59c07590cee..7dcbac8af9a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -190,6 +190,7 @@ struct amdgpu_job;
 struct amdgpu_irq_src;
 struct amdgpu_fpriv;
 struct amdgpu_bo_va_mapping;
+struct amdgpu_atif;
 
 enum amdgpu_cp_irq {
 	AMDGPU_CP_IRQ_GFX_EOP = 0,
@@ -1269,43 +1270,6 @@ struct amdgpu_vram_scratch {
 /*
  * ACPI
  */
-struct amdgpu_atif_notification_cfg {
-	bool enabled;
-	int command_code;
-};
-
-struct amdgpu_atif_notifications {
-	bool display_switch;
-	bool expansion_mode_change;
-	bool thermal_state;
-	bool forced_power_state;
-	bool system_power_state;
-	bool display_conf_change;
-	bool px_gfx_switch;
-	bool brightness_change;
-	bool dgpu_display_event;
-};
-
-struct amdgpu_atif_functions {
-	bool system_params;
-	bool sbios_requests;
-	bool select_active_disp;
-	bool lid_state;
-	bool get_tv_standard;
-	bool set_tv_standard;
-	bool get_panel_expansion_mode;
-	bool set_panel_expansion_mode;
-	bool temperature_change;
-	bool graphics_device_types;
-};
-
-struct amdgpu_atif {
-	struct amdgpu_atif_notifications notifications;
-	struct amdgpu_atif_functions functions;
-	struct amdgpu_atif_notification_cfg notification_cfg;
-	struct amdgpu_encoder *encoder_for_bl;
-};
-
 struct amdgpu_atcs_functions {
 	bool get_ext_state;
 	bool pcie_perf_req;
@@ -1466,7 +1430,7 @@ struct amdgpu_device {
 #if defined(CONFIG_DEBUG_FS)
 	struct dentry			*debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
 #endif
-	struct amdgpu_atif		atif;
+	struct amdgpu_atif		*atif;
 	struct amdgpu_atcs		atcs;
 	struct mutex			srbm_mutex;
 	/* GRBM index mutex. Protects concurrent access to GRBM index */
@@ -1894,6 +1858,12 @@ static inline bool amdgpu_atpx_dgpu_req_power_for_displays(void) { return false;
 static inline bool amdgpu_has_atpx(void) { return false; }
 #endif
 
+#if defined(CONFIG_VGA_SWITCHEROO) && defined(CONFIG_ACPI)
+void *amdgpu_atpx_get_dhandle(void);
+#else
+static inline void *amdgpu_atpx_get_dhandle(void) { return NULL; }
+#endif
+
 /*
  * KMS
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index f4c474a95875..71efcf38f11b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -57,6 +57,10 @@
 #define ACP_I2S_COMP2_CAP_REG_OFFSET		0xa8
 #define ACP_I2S_COMP1_PLAY_REG_OFFSET		0x6c
 #define ACP_I2S_COMP2_PLAY_REG_OFFSET		0x68
+#define ACP_BT_PLAY_REGS_START			0x14970
+#define ACP_BT_PLAY_REGS_END			0x14a24
+#define ACP_BT_COMP1_REG_OFFSET			0xac
+#define ACP_BT_COMP2_REG_OFFSET			0xa8
 
 #define mmACP_PGFSM_RETAIN_REG			0x51c9
 #define mmACP_PGFSM_CONFIG_REG			0x51ca
@@ -77,7 +81,7 @@
 #define ACP_SOFT_RESET_DONE_TIME_OUT_VALUE	0x000000FF
 
 #define ACP_TIMEOUT_LOOP			0x000000FF
-#define ACP_DEVS				3
+#define ACP_DEVS				4
 #define ACP_SRC_ID				162
 
 enum {
@@ -316,14 +320,13 @@ static int acp_hw_init(void *handle)
 	if (adev->acp.acp_cell == NULL)
 		return -ENOMEM;
 
-	adev->acp.acp_res = kcalloc(4, sizeof(struct resource), GFP_KERNEL);
-
+	adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL);
 	if (adev->acp.acp_res == NULL) {
 		kfree(adev->acp.acp_cell);
 		return -ENOMEM;
 	}
 
-	i2s_pdata = kcalloc(2, sizeof(struct i2s_platform_data), GFP_KERNEL);
+	i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL);
 	if (i2s_pdata == NULL) {
 		kfree(adev->acp.acp_res);
 		kfree(adev->acp.acp_cell);
@@ -358,6 +361,20 @@ static int acp_hw_init(void *handle)
 	i2s_pdata[1].i2s_reg_comp1 = ACP_I2S_COMP1_CAP_REG_OFFSET;
 	i2s_pdata[1].i2s_reg_comp2 = ACP_I2S_COMP2_CAP_REG_OFFSET;
 
+	i2s_pdata[2].quirks = DW_I2S_QUIRK_COMP_REG_OFFSET;
+	switch (adev->asic_type) {
+	case CHIP_STONEY:
+		i2s_pdata[2].quirks |= DW_I2S_QUIRK_16BIT_IDX_OVERRIDE;
+		break;
+	default:
+		break;
+	}
+
+	i2s_pdata[2].cap = DWC_I2S_PLAY | DWC_I2S_RECORD;
+	i2s_pdata[2].snd_rates = SNDRV_PCM_RATE_8000_96000;
+	i2s_pdata[2].i2s_reg_comp1 = ACP_BT_COMP1_REG_OFFSET;
+	i2s_pdata[2].i2s_reg_comp2 = ACP_BT_COMP2_REG_OFFSET;
+
 	adev->acp.acp_res[0].name = "acp2x_dma";
 	adev->acp.acp_res[0].flags = IORESOURCE_MEM;
 	adev->acp.acp_res[0].start = acp_base;
@@ -373,13 +390,18 @@ static int acp_hw_init(void *handle)
 	adev->acp.acp_res[2].start = acp_base + ACP_I2S_CAP_REGS_START;
 	adev->acp.acp_res[2].end = acp_base + ACP_I2S_CAP_REGS_END;
 
-	adev->acp.acp_res[3].name = "acp2x_dma_irq";
-	adev->acp.acp_res[3].flags = IORESOURCE_IRQ;
-	adev->acp.acp_res[3].start = amdgpu_irq_create_mapping(adev, 162);
-	adev->acp.acp_res[3].end = adev->acp.acp_res[3].start;
+	adev->acp.acp_res[3].name = "acp2x_dw_bt_i2s_play_cap";
+	adev->acp.acp_res[3].flags = IORESOURCE_MEM;
+	adev->acp.acp_res[3].start = acp_base + ACP_BT_PLAY_REGS_START;
+	adev->acp.acp_res[3].end = acp_base + ACP_BT_PLAY_REGS_END;
+
+	adev->acp.acp_res[4].name = "acp2x_dma_irq";
+	adev->acp.acp_res[4].flags = IORESOURCE_IRQ;
+	adev->acp.acp_res[4].start = amdgpu_irq_create_mapping(adev, 162);
+	adev->acp.acp_res[4].end = adev->acp.acp_res[4].start;
 
 	adev->acp.acp_cell[0].name = "acp_audio_dma";
-	adev->acp.acp_cell[0].num_resources = 4;
+	adev->acp.acp_cell[0].num_resources = 5;
 	adev->acp.acp_cell[0].resources = &adev->acp.acp_res[0];
 	adev->acp.acp_cell[0].platform_data = &adev->asic_type;
 	adev->acp.acp_cell[0].pdata_size = sizeof(adev->asic_type);
@@ -396,6 +418,12 @@ static int acp_hw_init(void *handle)
 	adev->acp.acp_cell[2].platform_data = &i2s_pdata[1];
 	adev->acp.acp_cell[2].pdata_size = sizeof(struct i2s_platform_data);
 
+	adev->acp.acp_cell[3].name = "designware-i2s";
+	adev->acp.acp_cell[3].num_resources = 1;
+	adev->acp.acp_cell[3].resources = &adev->acp.acp_res[3];
+	adev->acp.acp_cell[3].platform_data = &i2s_pdata[2];
+	adev->acp.acp_cell[3].pdata_size = sizeof(struct i2s_platform_data);
+
 	r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell,
 								ACP_DEVS);
 	if (r)
@@ -451,7 +479,6 @@ static int acp_hw_init(void *handle)
 	val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
 	val &= ~ACP_SOFT_RESET__SoftResetAud_MASK;
 	cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 8fa850a070e0..0d8c3fc6eace 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -34,6 +34,45 @@
 #include "amd_acpi.h"
 #include "atom.h"
 
+struct amdgpu_atif_notification_cfg {
+	bool enabled;
+	int command_code;
+};
+
+struct amdgpu_atif_notifications {
+	bool display_switch;
+	bool expansion_mode_change;
+	bool thermal_state;
+	bool forced_power_state;
+	bool system_power_state;
+	bool display_conf_change;
+	bool px_gfx_switch;
+	bool brightness_change;
+	bool dgpu_display_event;
+};
+
+struct amdgpu_atif_functions {
+	bool system_params;
+	bool sbios_requests;
+	bool select_active_disp;
+	bool lid_state;
+	bool get_tv_standard;
+	bool set_tv_standard;
+	bool get_panel_expansion_mode;
+	bool set_panel_expansion_mode;
+	bool temperature_change;
+	bool graphics_device_types;
+};
+
+struct amdgpu_atif {
+	acpi_handle handle;
+
+	struct amdgpu_atif_notifications notifications;
+	struct amdgpu_atif_functions functions;
+	struct amdgpu_atif_notification_cfg notification_cfg;
+	struct amdgpu_encoder *encoder_for_bl;
+};
+
 /* Call the ATIF method
  */
 /**
@@ -46,8 +85,9 @@
  * Executes the requested ATIF function (all asics).
  * Returns a pointer to the acpi output buffer.
  */
-static union acpi_object *amdgpu_atif_call(acpi_handle handle, int function,
-		struct acpi_buffer *params)
+static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
+					   int function,
+					   struct acpi_buffer *params)
 {
 	acpi_status status;
 	union acpi_object atif_arg_elements[2];
@@ -70,7 +110,8 @@ static union acpi_object *amdgpu_atif_call(acpi_handle handle, int function,
 		atif_arg_elements[1].integer.value = 0;
 	}
 
-	status = acpi_evaluate_object(handle, "ATIF", &atif_arg, &buffer);
+	status = acpi_evaluate_object(atif->handle, NULL, &atif_arg,
+				      &buffer);
 
 	/* Fail only if calling the method fails and ATIF is supported */
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
@@ -141,15 +182,14 @@ static void amdgpu_atif_parse_functions(struct amdgpu_atif_functions *f, u32 mas
  * (all asics).
  * returns 0 on success, error on failure.
  */
-static int amdgpu_atif_verify_interface(acpi_handle handle,
-		struct amdgpu_atif *atif)
+static int amdgpu_atif_verify_interface(struct amdgpu_atif *atif)
 {
 	union acpi_object *info;
 	struct atif_verify_interface output;
 	size_t size;
 	int err = 0;
 
-	info = amdgpu_atif_call(handle, ATIF_FUNCTION_VERIFY_INTERFACE, NULL);
+	info = amdgpu_atif_call(atif, ATIF_FUNCTION_VERIFY_INTERFACE, NULL);
 	if (!info)
 		return -EIO;
 
@@ -176,6 +216,35 @@ out:
 	return err;
 }
 
+static acpi_handle amdgpu_atif_probe_handle(acpi_handle dhandle)
+{
+	acpi_handle handle = NULL;
+	char acpi_method_name[255] = { 0 };
+	struct acpi_buffer buffer = { sizeof(acpi_method_name), acpi_method_name };
+	acpi_status status;
+
+	/* For PX/HG systems, ATIF and ATPX are in the iGPU's namespace, on dGPU only
+	 * systems, ATIF is in the dGPU's namespace.
+	 */
+	status = acpi_get_handle(dhandle, "ATIF", &handle);
+	if (ACPI_SUCCESS(status))
+		goto out;
+
+	if (amdgpu_has_atpx()) {
+		status = acpi_get_handle(amdgpu_atpx_get_dhandle(), "ATIF",
+					 &handle);
+		if (ACPI_SUCCESS(status))
+			goto out;
+	}
+
+	DRM_DEBUG_DRIVER("No ATIF handle found\n");
+	return NULL;
+out:
+	acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+	DRM_DEBUG_DRIVER("Found ATIF handle %s\n", acpi_method_name);
+	return handle;
+}
+
 /**
  * amdgpu_atif_get_notification_params - determine notify configuration
  *
@@ -188,15 +257,16 @@ out:
  * where n is specified in the result if a notifier is used.
  * Returns 0 on success, error on failure.
  */
-static int amdgpu_atif_get_notification_params(acpi_handle handle,
-		struct amdgpu_atif_notification_cfg *n)
+static int amdgpu_atif_get_notification_params(struct amdgpu_atif *atif)
 {
 	union acpi_object *info;
+	struct amdgpu_atif_notification_cfg *n = &atif->notification_cfg;
 	struct atif_system_params params;
 	size_t size;
 	int err = 0;
 
-	info = amdgpu_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_PARAMETERS, NULL);
+	info = amdgpu_atif_call(atif, ATIF_FUNCTION_GET_SYSTEM_PARAMETERS,
+				NULL);
 	if (!info) {
 		err = -EIO;
 		goto out;
@@ -250,14 +320,15 @@ out:
  * (all asics).
  * Returns 0 on success, error on failure.
  */
-static int amdgpu_atif_get_sbios_requests(acpi_handle handle,
-		struct atif_sbios_requests *req)
+static int amdgpu_atif_get_sbios_requests(struct amdgpu_atif *atif,
+					  struct atif_sbios_requests *req)
 {
 	union acpi_object *info;
 	size_t size;
 	int count = 0;
 
-	info = amdgpu_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS, NULL);
+	info = amdgpu_atif_call(atif, ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS,
+				NULL);
 	if (!info)
 		return -EIO;
 
@@ -290,11 +361,10 @@ out:
  * Returns NOTIFY code
  */
 static int amdgpu_atif_handler(struct amdgpu_device *adev,
-			struct acpi_bus_event *event)
+			       struct acpi_bus_event *event)
 {
-	struct amdgpu_atif *atif = &adev->atif;
+	struct amdgpu_atif *atif = adev->atif;
 	struct atif_sbios_requests req;
-	acpi_handle handle;
 	int count;
 
 	DRM_DEBUG_DRIVER("event, device_class = %s, type = %#x\n",
@@ -303,14 +373,14 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 	if (strcmp(event->device_class, ACPI_VIDEO_CLASS) != 0)
 		return NOTIFY_DONE;
 
-	if (!atif->notification_cfg.enabled ||
+	if (!atif ||
+	    !atif->notification_cfg.enabled ||
 	    event->type != atif->notification_cfg.command_code)
 		/* Not our event */
 		return NOTIFY_DONE;
 
 	/* Check pending SBIOS requests */
-	handle = ACPI_HANDLE(&adev->pdev->dev);
-	count = amdgpu_atif_get_sbios_requests(handle, &req);
+	count = amdgpu_atif_get_sbios_requests(atif, &req);
 
 	if (count <= 0)
 		return NOTIFY_DONE;
@@ -641,8 +711,8 @@ static int amdgpu_acpi_event(struct notifier_block *nb,
  */
 int amdgpu_acpi_init(struct amdgpu_device *adev)
 {
-	acpi_handle handle;
-	struct amdgpu_atif *atif = &adev->atif;
+	acpi_handle handle, atif_handle;
+	struct amdgpu_atif *atif;
 	struct amdgpu_atcs *atcs = &adev->atcs;
 	int ret;
 
@@ -658,12 +728,26 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 		DRM_DEBUG_DRIVER("Call to ATCS verify_interface failed: %d\n", ret);
 	}
 
+	/* Probe for ATIF, and initialize it if found */
+	atif_handle = amdgpu_atif_probe_handle(handle);
+	if (!atif_handle)
+		goto out;
+
+	atif = kzalloc(sizeof(*atif), GFP_KERNEL);
+	if (!atif) {
+		DRM_WARN("Not enough memory to initialize ATIF\n");
+		goto out;
+	}
+	atif->handle = atif_handle;
+
 	/* Call the ATIF method */
-	ret = amdgpu_atif_verify_interface(handle, atif);
+	ret = amdgpu_atif_verify_interface(atif);
 	if (ret) {
 		DRM_DEBUG_DRIVER("Call to ATIF verify_interface failed: %d\n", ret);
+		kfree(atif);
 		goto out;
 	}
+	adev->atif = atif;
 
 	if (atif->notifications.brightness_change) {
 		struct drm_encoder *tmp;
@@ -693,8 +777,7 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 	}
 
 	if (atif->functions.system_params) {
-		ret = amdgpu_atif_get_notification_params(handle,
-				&atif->notification_cfg);
+		ret = amdgpu_atif_get_notification_params(atif);
 		if (ret) {
 			DRM_DEBUG_DRIVER("Call to GET_SYSTEM_PARAMS failed: %d\n",
 					ret);
@@ -720,4 +803,6 @@ out:
 void amdgpu_acpi_fini(struct amdgpu_device *adev)
 {
 	unregister_acpi_notifier(&adev->acpi_nb);
+	if (adev->atif)
+		kfree(adev->atif);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index daa06e7c5bb7..ca8bf1c9a98e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -90,6 +90,12 @@ bool amdgpu_atpx_dgpu_req_power_for_displays(void) {
 	return amdgpu_atpx_priv.atpx.dgpu_req_power_for_displays;
 }
 
+#if defined(CONFIG_ACPI)
+void *amdgpu_atpx_get_dhandle(void) {
+	return amdgpu_atpx_priv.dhandle;
+}
+#endif
+
 /**
  * amdgpu_atpx_call - call an ATPX method
  *
@@ -569,6 +575,7 @@ static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = {
 	{ 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX },
+	{ 0x1002, 0x6900, 0x1025, 0x125A, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0, 0, 0, 0, 0 },
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 82312a7bc6ad..9c85a90be293 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -927,6 +927,10 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 		r = amdgpu_bo_vm_update_pte(p);
 		if (r)
 			return r;
+
+		r = reservation_object_reserve_shared(vm->root.base.bo->tbo.resv);
+		if (r)
+			return r;
 	}
 
 	return amdgpu_cs_sync_rings(p);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6e5284e6c028..2c5f093e79e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2747,6 +2747,9 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	if (r)
 		return r;
 
+	/* Make sure IB tests flushed */
+	flush_delayed_work(&adev->late_init_work);
+
 	/* blat the mode back in */
 	if (fbcon) {
 		if (!amdgpu_device_has_dc_support(adev)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 39ec6b8890a1..e74d620d9699 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -376,7 +376,7 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 	struct amdgpu_device *adev = ring->adev;
 	uint64_t index;
 
-	if (ring != &adev->uvd.inst[ring->me].ring) {
+	if (ring->funcs->type != AMDGPU_RING_TYPE_UVD) {
 		ring->fence_drv.cpu_addr = &adev->wb.wb[ring->fence_offs];
 		ring->fence_drv.gpu_addr = adev->wb.gpu_addr + (ring->fence_offs * 4);
 	} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index f70eeed9ed76..7aaa263ad8c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -231,6 +231,12 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	if (ib->flags & AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE)
 		fence_flags |= AMDGPU_FENCE_FLAG_TC_WB_ONLY;
 
+	/* wrap the last IB with fence */
+	if (job && job->uf_addr) {
+		amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
+				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
+	}
+
 	r = amdgpu_fence_emit(ring, f, fence_flags);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
@@ -243,12 +249,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	if (ring->funcs->insert_end)
 		ring->funcs->insert_end(ring);
 
-	/* wrap the last IB with fence */
-	if (job && job->uf_addr) {
-		amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
-				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
-	}
-
 	if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
 		amdgpu_ring_patch_cond_exec(ring, patch_offset);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index b455da487782..fc818b4d849c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -1882,7 +1882,7 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 		if (!amdgpu_device_has_dc_support(adev)) {
 			mutex_lock(&adev->pm.mutex);
 			amdgpu_dpm_get_active_displays(adev);
-			adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtcs;
+			adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtc_count;
 			adev->pm.pm_display_cfg.vrefresh = amdgpu_dpm_get_vrefresh(adev);
 			adev->pm.pm_display_cfg.min_vblank_time = amdgpu_dpm_get_vblank_time(adev);
 			/* we have issues with mclk switching with refresh rates over 120 hz on the non-DC code. */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 127e87b470ff..1b4ad9b2a755 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -52,7 +52,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 	unsigned long bo_size;
 	const char *fw_name;
 	const struct common_firmware_header *hdr;
-	unsigned version_major, version_minor, family_id;
+	unsigned char fw_check;
 	int r;
 
 	INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler);
@@ -83,12 +83,33 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 
 	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
 	adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
-	family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
-	version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
-	version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
-	DRM_INFO("Found VCN firmware Version: %hu.%hu Family ID: %hu\n",
-		version_major, version_minor, family_id);
 
+	/* Bit 20-23, it is encode major and non-zero for new naming convention.
+	 * This field is part of version minor and DRM_DISABLED_FLAG in old naming
+	 * convention. Since the l:wq!atest version minor is 0x5B and DRM_DISABLED_FLAG
+	 * is zero in old naming convention, this field is always zero so far.
+	 * These four bits are used to tell which naming convention is present.
+	 */
+	fw_check = (le32_to_cpu(hdr->ucode_version) >> 20) & 0xf;
+	if (fw_check) {
+		unsigned int dec_ver, enc_major, enc_minor, vep, fw_rev;
+
+		fw_rev = le32_to_cpu(hdr->ucode_version) & 0xfff;
+		enc_minor = (le32_to_cpu(hdr->ucode_version) >> 12) & 0xff;
+		enc_major = fw_check;
+		dec_ver = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xf;
+		vep = (le32_to_cpu(hdr->ucode_version) >> 28) & 0xf;
+		DRM_INFO("Found VCN firmware Version ENC: %hu.%hu DEC: %hu VEP: %hu Revision: %hu\n",
+			enc_major, enc_minor, dec_ver, vep, fw_rev);
+	} else {
+		unsigned int version_major, version_minor, family_id;
+
+		family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
+		version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
+		version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
+		DRM_INFO("Found VCN firmware Version: %hu.%hu Family ID: %hu\n",
+			version_major, version_minor, family_id);
+	}
 
 	bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8)
 		  +  AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_HEAP_SIZE
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index b0eb2f537392..fdcb498f6d19 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -107,6 +107,9 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 		return;
 	list_add_tail(&base->bo_list, &bo->va);
 
+	if (bo->tbo.type == ttm_bo_type_kernel)
+		list_move(&base->vm_status, &vm->relocated);
+
 	if (bo->tbo.resv != vm->root.base.bo->tbo.resv)
 		return;
 
@@ -468,7 +471,6 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 			pt->parent = amdgpu_bo_ref(parent->base.bo);
 
 			amdgpu_vm_bo_base_init(&entry->base, vm, pt);
-			list_move(&entry->base.vm_status, &vm->relocated);
 		}
 
 		if (level < AMDGPU_VM_PTB) {
@@ -1463,7 +1465,9 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 			uint64_t count;
 
 			max_entries = min(max_entries, 16ull * 1024ull);
-			for (count = 1; count < max_entries; ++count) {
+			for (count = 1;
+			     count < max_entries / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+			     ++count) {
 				uint64_t idx = pfn + count;
 
 				if (pages_addr[idx] !=
@@ -1476,7 +1480,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 				dma_addr = pages_addr;
 			} else {
 				addr = pages_addr[pfn];
-				max_entries = count;
+				max_entries = count * (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
 			}
 
 		} else if (flags & AMDGPU_PTE_VALID) {
@@ -1491,7 +1495,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		if (r)
 			return r;
 
-		pfn += last - start + 1;
+		pfn += (last - start + 1) / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
 		if (nodes && nodes->size == pfn) {
 			pfn = 0;
 			++nodes;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 0999c843f623..a71b97519cc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -900,7 +900,7 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_phys_funcs = {
 	.emit_frame_size =
 		4 + /* vce_v3_0_emit_pipeline_sync */
 		6, /* amdgpu_vce_ring_emit_fence x1 no user fence */
-	.emit_ib_size = 5, /* vce_v3_0_ring_emit_ib */
+	.emit_ib_size = 4, /* amdgpu_vce_ring_emit_ib */
 	.emit_ib = amdgpu_vce_ring_emit_ib,
 	.emit_fence = amdgpu_vce_ring_emit_fence,
 	.test_ring = amdgpu_vce_ring_test_ring,
@@ -924,7 +924,7 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_vm_funcs = {
 		6 + /* vce_v3_0_emit_vm_flush */
 		4 + /* vce_v3_0_emit_pipeline_sync */
 		6 + 6, /* amdgpu_vce_ring_emit_fence x2 vm fence */
-	.emit_ib_size = 4, /* amdgpu_vce_ring_emit_ib */
+	.emit_ib_size = 5, /* vce_v3_0_ring_emit_ib */
 	.emit_ib = vce_v3_0_ring_emit_ib,
 	.emit_vm_flush = vce_v3_0_emit_vm_flush,
 	.emit_pipeline_sync = vce_v3_0_emit_pipeline_sync,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index f9add85157e7..770c6b24be0b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2175,6 +2175,46 @@ get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing)
 	return color_space;
 }
 
+static void reduce_mode_colour_depth(struct dc_crtc_timing *timing_out)
+{
+	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
+		return;
+
+	timing_out->display_color_depth--;
+}
+
+static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_out,
+						const struct drm_display_info *info)
+{
+	int normalized_clk;
+	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
+		return;
+	do {
+		normalized_clk = timing_out->pix_clk_khz;
+		/* YCbCr 4:2:0 requires additional adjustment of 1/2 */
+		if (timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+			normalized_clk /= 2;
+		/* Adjusting pix clock following on HDMI spec based on colour depth */
+		switch (timing_out->display_color_depth) {
+		case COLOR_DEPTH_101010:
+			normalized_clk = (normalized_clk * 30) / 24;
+			break;
+		case COLOR_DEPTH_121212:
+			normalized_clk = (normalized_clk * 36) / 24;
+			break;
+		case COLOR_DEPTH_161616:
+			normalized_clk = (normalized_clk * 48) / 24;
+			break;
+		default:
+			return;
+		}
+		if (normalized_clk <= info->max_tmds_clock)
+			return;
+		reduce_mode_colour_depth(timing_out);
+
+	} while (timing_out->display_color_depth > COLOR_DEPTH_888);
+
+}
 /*****************************************************************************/
 
 static void
@@ -2183,6 +2223,7 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 					     const struct drm_connector *connector)
 {
 	struct dc_crtc_timing *timing_out = &stream->timing;
+	const struct drm_display_info *info = &connector->display_info;
 
 	memset(timing_out, 0, sizeof(struct dc_crtc_timing));
 
@@ -2191,8 +2232,10 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 	timing_out->v_border_top = 0;
 	timing_out->v_border_bottom = 0;
 	/* TODO: un-hardcode */
-
-	if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCRCB444)
+	if (drm_mode_is_420_only(info, mode_in)
+			&& stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
+		timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
+	else if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCRCB444)
 			&& stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
 		timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR444;
 	else
@@ -2228,6 +2271,8 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 
 	stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
 	stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
+	if (stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
+		adjust_colour_depth_from_display_info(timing_out, info);
 }
 
 static void fill_audio_info(struct audio_info *audio_info,
@@ -3928,10 +3973,11 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 	if (acrtc->base.state->event)
 		prepare_flip_isr(acrtc);
 
+	spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
 	surface_updates->surface = dc_stream_get_status(acrtc_state->stream)->plane_states[0];
 	surface_updates->flip_addr = &addr;
 
-
 	dc_commit_updates_for_stream(adev->dm.dc,
 					     surface_updates,
 					     1,
@@ -3944,9 +3990,6 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 			 __func__,
 			 addr.address.grph.addr.high_part,
 			 addr.address.grph.addr.low_part);
-
-
-	spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 }
 
 /*
@@ -4206,6 +4249,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	struct drm_connector *connector;
 	struct drm_connector_state *old_con_state, *new_con_state;
 	struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
+	int crtc_disable_count = 0;
 
 	drm_atomic_helper_update_legacy_modeset_state(dev, state);
 
@@ -4410,6 +4454,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
 		bool modeset_needed;
 
+		if (old_crtc_state->active && !new_crtc_state->active)
+			crtc_disable_count++;
+
 		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
 		dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
 		modeset_needed = modeset_required(
@@ -4463,11 +4510,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	 * so we can put the GPU into runtime suspend if we're not driving any
 	 * displays anymore
 	 */
+	for (i = 0; i < crtc_disable_count; i++)
+		pm_runtime_put_autosuspend(dev->dev);
 	pm_runtime_mark_last_busy(dev->dev);
-	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-		if (old_crtc_state->active && !new_crtc_state->active)
-			pm_runtime_put_autosuspend(dev->dev);
-	}
 }
 
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 4304d9e408b8..ace9ad578ca0 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -83,22 +83,21 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
 		I2C_MOT_TRUE : I2C_MOT_FALSE;
 	enum ddc_result res;
-	uint32_t read_bytes = msg->size;
+	ssize_t read_bytes;
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
 
 	switch (msg->request & ~DP_AUX_I2C_MOT) {
 	case DP_AUX_NATIVE_READ:
-		res = dal_ddc_service_read_dpcd_data(
+		read_bytes = dal_ddc_service_read_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
 				false,
 				I2C_MOT_UNDEF,
 				msg->address,
 				msg->buffer,
-				msg->size,
-				&read_bytes);
-		break;
+				msg->size);
+		return read_bytes;
 	case DP_AUX_NATIVE_WRITE:
 		res = dal_ddc_service_write_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
@@ -109,15 +108,14 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				msg->size);
 		break;
 	case DP_AUX_I2C_READ:
-		res = dal_ddc_service_read_dpcd_data(
+		read_bytes = dal_ddc_service_read_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
 				true,
 				mot,
 				msg->address,
 				msg->buffer,
-				msg->size,
-				&read_bytes);
-		break;
+				msg->size);
+		return read_bytes;
 	case DP_AUX_I2C_WRITE:
 		res = dal_ddc_service_write_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
@@ -139,9 +137,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 		 r == DDC_RESULT_SUCESSFULL);
 #endif
 
-	if (res != DDC_RESULT_SUCESSFULL)
-		return -EIO;
-	return read_bytes;
+	return msg->size;
 }
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 5a3346124a01..5a2e952c5bea 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -255,8 +255,9 @@ static void pp_to_dc_clock_levels_with_latency(
 			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
 
 	for (i = 0; i < clk_level_info->num_levels; i++) {
-		DRM_DEBUG("DM_PPLIB:\t %d\n", pp_clks->data[i].clocks_in_khz);
-		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
+		DRM_DEBUG("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
+		/* translate 10kHz to kHz */
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
 		clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
 	}
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index ae48d603ebd6..49c2face1e7a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -629,14 +629,13 @@ bool dal_ddc_service_query_ddc_data(
 	return ret;
 }
 
-enum ddc_result dal_ddc_service_read_dpcd_data(
+ssize_t dal_ddc_service_read_dpcd_data(
 	struct ddc_service *ddc,
 	bool i2c,
 	enum i2c_mot_mode mot,
 	uint32_t address,
 	uint8_t *data,
-	uint32_t len,
-	uint32_t *read)
+	uint32_t len)
 {
 	struct aux_payload read_payload = {
 		.i2c_over_aux = i2c,
@@ -653,8 +652,6 @@ enum ddc_result dal_ddc_service_read_dpcd_data(
 		.mot = mot
 	};
 
-	*read = 0;
-
 	if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
 		BREAK_TO_DEBUGGER();
 		return DDC_RESULT_FAILED_INVALID_OPERATION;
@@ -664,8 +661,7 @@ enum ddc_result dal_ddc_service_read_dpcd_data(
 		ddc->ctx->i2caux,
 		ddc->ddc_pin,
 		&command)) {
-		*read = command.payloads->length;
-		return DDC_RESULT_SUCESSFULL;
+		return (ssize_t)command.payloads->length;
 	}
 
 	return DDC_RESULT_FAILED_OPERATION;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 7857cb42b3e6..bdd121485cbc 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1767,12 +1767,10 @@ static void dp_test_send_link_training(struct dc_link *link)
 	dp_retrain_link_dp_test(link, &link_settings, false);
 }
 
-/* TODO hbr2 compliance eye output is unstable
+/* TODO Raven hbr2 compliance eye output is unstable
  * (toggling on and off) with debugger break
  * This caueses intermittent PHY automation failure
  * Need to look into the root cause */
-static uint8_t force_tps4_for_cp2520 = 1;
-
 static void dp_test_send_phy_test_pattern(struct dc_link *link)
 {
 	union phy_test_pattern dpcd_test_pattern;
@@ -1832,13 +1830,13 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link)
 		break;
 	case PHY_TEST_PATTERN_CP2520_1:
 		/* CP2520 pattern is unstable, temporarily use TPS4 instead */
-		test_pattern = (force_tps4_for_cp2520 == 1) ?
+		test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ?
 				DP_TEST_PATTERN_TRAINING_PATTERN4 :
 				DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE;
 		break;
 	case PHY_TEST_PATTERN_CP2520_2:
 		/* CP2520 pattern is unstable, temporarily use TPS4 instead */
-		test_pattern = (force_tps4_for_cp2520 == 1) ?
+		test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ?
 				DP_TEST_PATTERN_TRAINING_PATTERN4 :
 				DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE;
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 9cfde0ccf4e9..53c71296f3dd 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -76,6 +76,7 @@ struct dc_caps {
 	bool is_apu;
 	bool dual_link_dvi;
 	bool post_blend_color_processing;
+	bool force_dp_tps4_for_cp2520;
 };
 
 struct dc_dcc_surface_param {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
index b235a75355b8..bae752332a9f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
@@ -741,6 +741,29 @@ static struct mem_input_funcs dce_mi_funcs = {
 	.mem_input_is_flip_pending = dce_mi_is_flip_pending
 };
 
+static struct mem_input_funcs dce112_mi_funcs = {
+	.mem_input_program_display_marks = dce112_mi_program_display_marks,
+	.allocate_mem_input = dce_mi_allocate_dmif,
+	.free_mem_input = dce_mi_free_dmif,
+	.mem_input_program_surface_flip_and_addr =
+			dce_mi_program_surface_flip_and_addr,
+	.mem_input_program_pte_vm = dce_mi_program_pte_vm,
+	.mem_input_program_surface_config =
+			dce_mi_program_surface_config,
+	.mem_input_is_flip_pending = dce_mi_is_flip_pending
+};
+
+static struct mem_input_funcs dce120_mi_funcs = {
+	.mem_input_program_display_marks = dce120_mi_program_display_marks,
+	.allocate_mem_input = dce_mi_allocate_dmif,
+	.free_mem_input = dce_mi_free_dmif,
+	.mem_input_program_surface_flip_and_addr =
+			dce_mi_program_surface_flip_and_addr,
+	.mem_input_program_pte_vm = dce_mi_program_pte_vm,
+	.mem_input_program_surface_config =
+			dce_mi_program_surface_config,
+	.mem_input_is_flip_pending = dce_mi_is_flip_pending
+};
 
 void dce_mem_input_construct(
 	struct dce_mem_input *dce_mi,
@@ -769,7 +792,7 @@ void dce112_mem_input_construct(
 	const struct dce_mem_input_mask *mi_mask)
 {
 	dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
-	dce_mi->base.funcs->mem_input_program_display_marks = dce112_mi_program_display_marks;
+	dce_mi->base.funcs = &dce112_mi_funcs;
 }
 
 void dce120_mem_input_construct(
@@ -781,5 +804,5 @@ void dce120_mem_input_construct(
 	const struct dce_mem_input_mask *mi_mask)
 {
 	dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
-	dce_mi->base.funcs->mem_input_program_display_marks = dce120_mi_program_display_marks;
+	dce_mi->base.funcs = &dce120_mi_funcs;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 38ec0d609297..344dd2e69e7c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -678,9 +678,22 @@ bool dce100_validate_bandwidth(
 	struct dc  *dc,
 	struct dc_state *context)
 {
-	/* TODO implement when needed but for now hardcode max value*/
-	context->bw.dce.dispclk_khz = 681000;
-	context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER;
+	int i;
+	bool at_least_one_pipe = false;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].stream)
+			at_least_one_pipe = true;
+	}
+
+	if (at_least_one_pipe) {
+		/* TODO implement when needed but for now hardcode max value*/
+		context->bw.dce.dispclk_khz = 681000;
+		context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER;
+	} else {
+		context->bw.dce.dispclk_khz = 0;
+		context->bw.dce.yclk_khz = 0;
+	}
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index df5cb2d1d164..34dac84066a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1027,6 +1027,8 @@ static bool construct(
 	dc->caps.max_slave_planes = 1;
 	dc->caps.is_apu = true;
 	dc->caps.post_blend_color_processing = false;
+	/* Raven DP PHY HBR2 eye diagram pattern is not stable. Use TP4 */
+	dc->caps.force_dp_tps4_for_cp2520 = true;
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
index 30b3a08b91be..090b7a8dd67b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
@@ -102,14 +102,13 @@ bool dal_ddc_service_query_ddc_data(
 		uint8_t *read_buf,
 		uint32_t read_size);
 
-enum ddc_result dal_ddc_service_read_dpcd_data(
+ssize_t dal_ddc_service_read_dpcd_data(
 		struct ddc_service *ddc,
 		bool i2c,
 		enum i2c_mot_mode mot,
 		uint32_t address,
 		uint8_t *data,
-		uint32_t len,
-		uint32_t *read);
+		uint32_t len);
 
 enum ddc_result dal_ddc_service_write_dpcd_data(
 		struct ddc_service *ddc,
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 092d800b703a..33b4de4ad66e 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -1433,7 +1433,10 @@ struct atom_smc_dpm_info_v4_1
 	uint8_t  acggfxclkspreadpercent;
 	uint16_t acggfxclkspreadfreq;
 
-	uint32_t boardreserved[10];
+	uint8_t Vr2_I2C_address;
+	uint8_t padding_vr2[3];
+
+	uint32_t boardreserved[9];
 };
 
 /* 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
index 5325661fedff..d27c1c9df286 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
@@ -512,14 +512,82 @@ int pp_atomfwctrl_get_clk_information_by_clkid(struct pp_hwmgr *hwmgr, BIOS_CLKI
 	return 0;
 }
 
+static void pp_atomfwctrl_copy_vbios_bootup_values_3_2(struct pp_hwmgr *hwmgr,
+			struct pp_atomfwctrl_bios_boot_up_values *boot_values,
+			struct atom_firmware_info_v3_2 *fw_info)
+{
+	uint32_t frequency = 0;
+
+	boot_values->ulRevision = fw_info->firmware_revision;
+	boot_values->ulGfxClk   = fw_info->bootup_sclk_in10khz;
+	boot_values->ulUClk     = fw_info->bootup_mclk_in10khz;
+	boot_values->usVddc     = fw_info->bootup_vddc_mv;
+	boot_values->usVddci    = fw_info->bootup_vddci_mv;
+	boot_values->usMvddc    = fw_info->bootup_mvddc_mv;
+	boot_values->usVddGfx   = fw_info->bootup_vddgfx_mv;
+	boot_values->ucCoolingID = fw_info->coolingsolution_id;
+	boot_values->ulSocClk   = 0;
+	boot_values->ulDCEFClk   = 0;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_SOCCLK_ID, &frequency))
+		boot_values->ulSocClk   = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_DCEFCLK_ID, &frequency))
+		boot_values->ulDCEFClk  = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_ECLK_ID, &frequency))
+		boot_values->ulEClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_VCLK_ID, &frequency))
+		boot_values->ulVClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_DCLK_ID, &frequency))
+		boot_values->ulDClk     = frequency;
+}
+
+static void pp_atomfwctrl_copy_vbios_bootup_values_3_1(struct pp_hwmgr *hwmgr,
+			struct pp_atomfwctrl_bios_boot_up_values *boot_values,
+			struct atom_firmware_info_v3_1 *fw_info)
+{
+	uint32_t frequency = 0;
+
+	boot_values->ulRevision = fw_info->firmware_revision;
+	boot_values->ulGfxClk   = fw_info->bootup_sclk_in10khz;
+	boot_values->ulUClk     = fw_info->bootup_mclk_in10khz;
+	boot_values->usVddc     = fw_info->bootup_vddc_mv;
+	boot_values->usVddci    = fw_info->bootup_vddci_mv;
+	boot_values->usMvddc    = fw_info->bootup_mvddc_mv;
+	boot_values->usVddGfx   = fw_info->bootup_vddgfx_mv;
+	boot_values->ucCoolingID = fw_info->coolingsolution_id;
+	boot_values->ulSocClk   = 0;
+	boot_values->ulDCEFClk   = 0;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_SOCCLK_ID, &frequency))
+		boot_values->ulSocClk   = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_DCEFCLK_ID, &frequency))
+		boot_values->ulDCEFClk  = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_ECLK_ID, &frequency))
+		boot_values->ulEClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_VCLK_ID, &frequency))
+		boot_values->ulVClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_DCLK_ID, &frequency))
+		boot_values->ulDClk     = frequency;
+}
+
 int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
 			struct pp_atomfwctrl_bios_boot_up_values *boot_values)
 {
-	struct atom_firmware_info_v3_1 *info = NULL;
+	struct atom_firmware_info_v3_2 *fwinfo_3_2;
+	struct atom_firmware_info_v3_1 *fwinfo_3_1;
+	struct atom_common_table_header *info = NULL;
 	uint16_t ix;
 
 	ix = GetIndexIntoMasterDataTable(firmwareinfo);
-	info = (struct atom_firmware_info_v3_1 *)
+	info = (struct atom_common_table_header *)
 		smu_atom_get_data_table(hwmgr->adev,
 				ix, NULL, NULL, NULL);
 
@@ -528,16 +596,18 @@ int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 	}
 
-	boot_values->ulRevision = info->firmware_revision;
-	boot_values->ulGfxClk   = info->bootup_sclk_in10khz;
-	boot_values->ulUClk     = info->bootup_mclk_in10khz;
-	boot_values->usVddc     = info->bootup_vddc_mv;
-	boot_values->usVddci    = info->bootup_vddci_mv;
-	boot_values->usMvddc    = info->bootup_mvddc_mv;
-	boot_values->usVddGfx   = info->bootup_vddgfx_mv;
-	boot_values->ucCoolingID = info->coolingsolution_id;
-	boot_values->ulSocClk   = 0;
-	boot_values->ulDCEFClk   = 0;
+	if ((info->format_revision == 3) && (info->content_revision == 2)) {
+		fwinfo_3_2 = (struct atom_firmware_info_v3_2 *)info;
+		pp_atomfwctrl_copy_vbios_bootup_values_3_2(hwmgr,
+				boot_values, fwinfo_3_2);
+	} else if ((info->format_revision == 3) && (info->content_revision == 1)) {
+		fwinfo_3_1 = (struct atom_firmware_info_v3_1 *)info;
+		pp_atomfwctrl_copy_vbios_bootup_values_3_1(hwmgr,
+				boot_values, fwinfo_3_1);
+	} else {
+		pr_info("Fw info table revision does not match!");
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -629,5 +699,7 @@ int pp_atomfwctrl_get_smc_dpm_information(struct pp_hwmgr *hwmgr,
 	param->acggfxclkspreadpercent = info->acggfxclkspreadpercent;
 	param->acggfxclkspreadfreq = info->acggfxclkspreadfreq;
 
+	param->Vr2_I2C_address = info->Vr2_I2C_address;
+
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
index fe10aa4db5e6..22e21668c93a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
@@ -136,6 +136,9 @@ struct pp_atomfwctrl_bios_boot_up_values {
 	uint32_t   ulUClk;
 	uint32_t   ulSocClk;
 	uint32_t   ulDCEFClk;
+	uint32_t   ulEClk;
+	uint32_t   ulVClk;
+	uint32_t   ulDClk;
 	uint16_t   usVddc;
 	uint16_t   usVddci;
 	uint16_t   usMvddc;
@@ -207,6 +210,8 @@ struct pp_atomfwctrl_smc_dpm_parameters
 	uint8_t  acggfxclkspreadenabled;
 	uint8_t  acggfxclkspreadpercent;
 	uint16_t acggfxclkspreadfreq;
+
+	uint8_t Vr2_I2C_address;
 };
 
 int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 782e2098824d..c98e5de777cd 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -81,6 +81,7 @@ static void vega12_set_default_registry_data(struct pp_hwmgr *hwmgr)
 
 	data->registry_data.disallowed_features = 0x0;
 	data->registry_data.od_state_in_dc_support = 0;
+	data->registry_data.thermal_support = 1;
 	data->registry_data.skip_baco_hardware = 0;
 
 	data->registry_data.log_avfs_param = 0;
@@ -803,6 +804,9 @@ static int vega12_init_smc_table(struct pp_hwmgr *hwmgr)
 		data->vbios_boot_state.soc_clock = boot_up_values.ulSocClk;
 		data->vbios_boot_state.dcef_clock = boot_up_values.ulDCEFClk;
 		data->vbios_boot_state.uc_cooling_id = boot_up_values.ucCoolingID;
+		data->vbios_boot_state.eclock = boot_up_values.ulEClk;
+		data->vbios_boot_state.dclock = boot_up_values.ulDClk;
+		data->vbios_boot_state.vclock = boot_up_values.ulVClk;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetMinDeepSleepDcefclk,
 			(uint32_t)(data->vbios_boot_state.dcef_clock / 100));
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
index e81ded1ec198..49b38df8c7f2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
@@ -167,6 +167,9 @@ struct vega12_vbios_boot_state {
 	uint32_t    mem_clock;
 	uint32_t    soc_clock;
 	uint32_t    dcef_clock;
+	uint32_t    eclock;
+	uint32_t    dclock;
+	uint32_t    vclock;
 };
 
 #define DPMTABLE_OD_UPDATE_SCLK     0x00000001
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
index 888ddca902d8..29914700ee82 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
@@ -230,6 +230,8 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable
 		ppsmc_pptable->AcgThresholdFreqLow = 0xFFFF;
 	}
 
+	ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
index 2f8a3b983cce..b08526fd1619 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
@@ -499,7 +499,10 @@ typedef struct {
 	uint8_t      AcgGfxclkSpreadPercent;
 	uint16_t     AcgGfxclkSpreadFreq;
 
-	uint32_t     BoardReserved[10];
+  uint8_t      Vr2_I2C_address;
+  uint8_t      padding_vr2[3];
+
+  uint32_t     BoardReserved[9];
 
 
   uint32_t     MmHubPadding[7];
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
index d644a9bb9078..9f407c48d4f0 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
@@ -381,6 +381,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 	uint32_t fw_to_load;
 	int result = 0;
 	struct SMU_DRAMData_TOC *toc;
+	uint32_t num_entries = 0;
 
 	if (!hwmgr->reload_fw) {
 		pr_info("skip reloading...\n");
@@ -422,41 +423,41 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 	}
 
 	toc = (struct SMU_DRAMData_TOC *)smu_data->header;
-	toc->num_entries = 0;
 	toc->structure_version = 1;
 
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_RLC_G, &toc->entry[toc->num_entries++]),
+				UCODE_ID_RLC_G, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_CE, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_CE, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_PFP, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_PFP, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_ME, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_ME, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_MEC, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC_JT1, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_MEC_JT1, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC_JT2, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_MEC_JT2, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_SDMA0, &toc->entry[toc->num_entries++]),
+				UCODE_ID_SDMA0, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_SDMA1, &toc->entry[toc->num_entries++]),
+				UCODE_ID_SDMA1, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	if (!hwmgr->not_vf)
 		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_MEC_STORAGE, &toc->entry[toc->num_entries++]),
+				UCODE_ID_MEC_STORAGE, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 
+	toc->num_entries = num_entries;
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_HI, upper_32_bits(smu_data->header_buffer.mc_addr));
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_LO, lower_32_bits(smu_data->header_buffer.mc_addr));
 
diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 8d20faa198cf..0a788d76ed5f 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -278,7 +278,6 @@ static int malidp_init(struct drm_device *drm)
 
 static void malidp_fini(struct drm_device *drm)
 {
-	drm_atomic_helper_shutdown(drm);
 	drm_mode_config_cleanup(drm);
 }
 
@@ -646,6 +645,7 @@ vblank_fail:
 	malidp_de_irq_fini(drm);
 	drm->irq_enabled = false;
 irq_init_fail:
+	drm_atomic_helper_shutdown(drm);
 	component_unbind_all(dev, drm);
 bind_fail:
 	of_node_put(malidp->crtc.port);
@@ -681,6 +681,7 @@ static void malidp_unbind(struct device *dev)
 	malidp_se_irq_fini(drm);
 	malidp_de_irq_fini(drm);
 	drm->irq_enabled = false;
+	drm_atomic_helper_shutdown(drm);
 	component_unbind_all(dev, drm);
 	of_node_put(malidp->crtc.port);
 	malidp->crtc.port = NULL;
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index d789b46dc817..069783e715f1 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -634,7 +634,8 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 				.vsync_irq = MALIDP500_DE_IRQ_VSYNC,
 			},
 			.se_irq_map = {
-				.irq_mask = MALIDP500_SE_IRQ_CONF_MODE,
+				.irq_mask = MALIDP500_SE_IRQ_CONF_MODE |
+					    MALIDP500_SE_IRQ_GLOBAL,
 				.vsync_irq = 0,
 			},
 			.dc_irq_map = {
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 7a44897c50fe..29409a65d864 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -23,6 +23,7 @@
 
 /* Layer specific register offsets */
 #define MALIDP_LAYER_FORMAT		0x000
+#define   LAYER_FORMAT_MASK		0x3f
 #define MALIDP_LAYER_CONTROL		0x004
 #define   LAYER_ENABLE			(1 << 0)
 #define   LAYER_FLOWCFG_MASK		7
@@ -235,8 +236,8 @@ static int malidp_de_plane_check(struct drm_plane *plane,
 	if (state->rotation & MALIDP_ROTATED_MASK) {
 		int val;
 
-		val = mp->hwdev->hw->rotmem_required(mp->hwdev, state->crtc_h,
-						     state->crtc_w,
+		val = mp->hwdev->hw->rotmem_required(mp->hwdev, state->crtc_w,
+						     state->crtc_h,
 						     fb->format->format);
 		if (val < 0)
 			return val;
@@ -337,7 +338,9 @@ static void malidp_de_plane_update(struct drm_plane *plane,
 	dest_w = plane->state->crtc_w;
 	dest_h = plane->state->crtc_h;
 
-	malidp_hw_write(mp->hwdev, ms->format, mp->layer->base);
+	val = malidp_hw_read(mp->hwdev, mp->layer->base);
+	val = (val & ~LAYER_FORMAT_MASK) | ms->format;
+	malidp_hw_write(mp->hwdev, val, mp->layer->base);
 
 	for (i = 0; i < ms->n_planes; i++) {
 		/* calculate the offset for the layer's plane registers */
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 03eeee11dd5b..42a40daff132 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -519,8 +519,9 @@ static irqreturn_t armada_drm_irq(int irq, void *arg)
 	u32 v, stat = readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR);
 
 	/*
-	 * This is rediculous - rather than writing bits to clear, we
-	 * have to set the actual status register value.  This is racy.
+	 * Reading the ISR appears to clear bits provided CLEAN_SPU_IRQ_ISR
+	 * is set.  Writing has some other effect to acknowledge the IRQ -
+	 * without this, we only get a single IRQ.
 	 */
 	writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR);
 
@@ -1116,16 +1117,22 @@ armada_drm_crtc_set_property(struct drm_crtc *crtc,
 static int armada_drm_crtc_enable_vblank(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	unsigned long flags;
 
+	spin_lock_irqsave(&dcrtc->irq_lock, flags);
 	armada_drm_crtc_enable_irq(dcrtc, VSYNC_IRQ_ENA);
+	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 	return 0;
 }
 
 static void armada_drm_crtc_disable_vblank(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	unsigned long flags;
 
+	spin_lock_irqsave(&dcrtc->irq_lock, flags);
 	armada_drm_crtc_disable_irq(dcrtc, VSYNC_IRQ_ENA);
+	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 }
 
 static const struct drm_crtc_funcs armada_crtc_funcs = {
@@ -1415,6 +1422,7 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 		       CFG_PDWN64x66, dcrtc->base + LCD_SPU_SRAM_PARA1);
 	writel_relaxed(0x2032ff81, dcrtc->base + LCD_SPU_DMA_CTRL1);
 	writel_relaxed(dcrtc->irq_ena, dcrtc->base + LCD_SPU_IRQ_ENA);
+	readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR);
 	writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR);
 
 	ret = devm_request_irq(dev, irq, armada_drm_irq, 0, "armada_drm_crtc",
diff --git a/drivers/gpu/drm/armada/armada_hw.h b/drivers/gpu/drm/armada/armada_hw.h
index 27319a8335e2..345dc4d0851e 100644
--- a/drivers/gpu/drm/armada/armada_hw.h
+++ b/drivers/gpu/drm/armada/armada_hw.h
@@ -160,6 +160,7 @@ enum {
 	CFG_ALPHAM_GRA		= 0x1 << 16,
 	CFG_ALPHAM_CFG		= 0x2 << 16,
 	CFG_ALPHA_MASK		= 0xff << 8,
+#define CFG_ALPHA(x)		((x) << 8)
 	CFG_PIXCMD_MASK		= 0xff,
 };
 
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index c391955009d6..afa7ded3ae31 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -28,6 +28,7 @@ struct armada_ovl_plane_properties {
 	uint16_t contrast;
 	uint16_t saturation;
 	uint32_t colorkey_mode;
+	uint32_t colorkey_enable;
 };
 
 struct armada_ovl_plane {
@@ -54,11 +55,13 @@ armada_ovl_update_attr(struct armada_ovl_plane_properties *prop,
 	writel_relaxed(0x00002000, dcrtc->base + LCD_SPU_CBSH_HUE);
 
 	spin_lock_irq(&dcrtc->irq_lock);
-	armada_updatel(prop->colorkey_mode | CFG_ALPHAM_GRA,
-		     CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
-		     dcrtc->base + LCD_SPU_DMA_CTRL1);
-
-	armada_updatel(ADV_GRACOLORKEY, 0, dcrtc->base + LCD_SPU_ADV_REG);
+	armada_updatel(prop->colorkey_mode,
+		       CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
+		       dcrtc->base + LCD_SPU_DMA_CTRL1);
+	if (dcrtc->variant->has_spu_adv_reg)
+		armada_updatel(prop->colorkey_enable,
+			       ADV_GRACOLORKEY | ADV_VIDCOLORKEY,
+			       dcrtc->base + LCD_SPU_ADV_REG);
 	spin_unlock_irq(&dcrtc->irq_lock);
 }
 
@@ -321,8 +324,17 @@ static int armada_ovl_plane_set_property(struct drm_plane *plane,
 		dplane->prop.colorkey_vb |= K2B(val);
 		update_attr = true;
 	} else if (property == priv->colorkey_mode_prop) {
-		dplane->prop.colorkey_mode &= ~CFG_CKMODE_MASK;
-		dplane->prop.colorkey_mode |= CFG_CKMODE(val);
+		if (val == CKMODE_DISABLE) {
+			dplane->prop.colorkey_mode =
+				CFG_CKMODE(CKMODE_DISABLE) |
+				CFG_ALPHAM_CFG | CFG_ALPHA(255);
+			dplane->prop.colorkey_enable = 0;
+		} else {
+			dplane->prop.colorkey_mode =
+				CFG_CKMODE(val) |
+				CFG_ALPHAM_GRA | CFG_ALPHA(0);
+			dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
+		}
 		update_attr = true;
 	} else if (property == priv->brightness_prop) {
 		dplane->prop.brightness = val - 256;
@@ -453,7 +465,9 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 	dplane->prop.colorkey_yr = 0xfefefe00;
 	dplane->prop.colorkey_ug = 0x01010100;
 	dplane->prop.colorkey_vb = 0x01010100;
-	dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB);
+	dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB) |
+				     CFG_ALPHAM_GRA | CFG_ALPHA(0);
+	dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
 	dplane->prop.brightness = 0;
 	dplane->prop.contrast = 0x4000;
 	dplane->prop.saturation = 0x4000;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 73021b388e12..dd3ff2f2cdce 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -429,6 +429,18 @@ static void adv7511_hpd_work(struct work_struct *work)
 	else
 		status = connector_status_disconnected;
 
+	/*
+	 * The bridge resets its registers on unplug. So when we get a plug
+	 * event and we're already supposed to be powered, cycle the bridge to
+	 * restore its state.
+	 */
+	if (status == connector_status_connected &&
+	    adv7511->connector.status == connector_status_disconnected &&
+	    adv7511->powered) {
+		regcache_mark_dirty(adv7511->regmap);
+		adv7511_power_on(adv7511);
+	}
+
 	if (adv7511->connector.status != status) {
 		adv7511->connector.status = status;
 		if (status == connector_status_disconnected)
diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c
index 250effa0e6b8..a6e8f4591e63 100644
--- a/drivers/gpu/drm/bridge/sil-sii8620.c
+++ b/drivers/gpu/drm/bridge/sil-sii8620.c
@@ -14,6 +14,7 @@
 #include <drm/bridge/mhl.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_edid.h>
+#include <drm/drm_encoder.h>
 
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -72,9 +73,7 @@ struct sii8620 {
 	struct regulator_bulk_data supplies[2];
 	struct mutex lock; /* context lock, protects fields below */
 	int error;
-	int pixel_clock;
 	unsigned int use_packed_pixel:1;
-	int video_code;
 	enum sii8620_mode mode;
 	enum sii8620_sink_type sink_type;
 	u8 cbus_status;
@@ -82,7 +81,6 @@ struct sii8620 {
 	u8 xstat[MHL_XDS_SIZE];
 	u8 devcap[MHL_DCAP_SIZE];
 	u8 xdevcap[MHL_XDC_SIZE];
-	u8 avif[HDMI_INFOFRAME_SIZE(AVI)];
 	bool feature_complete;
 	bool devcap_read;
 	bool sink_detected;
@@ -1017,21 +1015,36 @@ static void sii8620_stop_video(struct sii8620 *ctx)
 
 static void sii8620_set_format(struct sii8620 *ctx)
 {
+	u8 out_fmt;
+
 	if (sii8620_is_mhl3(ctx)) {
 		sii8620_setbits(ctx, REG_M3_P0CTRL,
 				BIT_M3_P0CTRL_MHL3_P0_PIXEL_MODE_PACKED,
 				ctx->use_packed_pixel ? ~0 : 0);
 	} else {
+		if (ctx->use_packed_pixel) {
+			sii8620_write_seq_static(ctx,
+				REG_VID_MODE, BIT_VID_MODE_M1080P,
+				REG_MHL_TOP_CTL, BIT_MHL_TOP_CTL_MHL_PP_SEL | 1,
+				REG_MHLTX_CTL6, 0x60
+			);
+		} else {
 			sii8620_write_seq_static(ctx,
 				REG_VID_MODE, 0,
 				REG_MHL_TOP_CTL, 1,
 				REG_MHLTX_CTL6, 0xa0
 			);
+		}
 	}
 
+	if (ctx->use_packed_pixel)
+		out_fmt = VAL_TPI_FORMAT(YCBCR422, FULL);
+	else
+		out_fmt = VAL_TPI_FORMAT(RGB, FULL);
+
 	sii8620_write_seq(ctx,
 		REG_TPI_INPUT, VAL_TPI_FORMAT(RGB, FULL),
-		REG_TPI_OUTPUT, VAL_TPI_FORMAT(RGB, FULL),
+		REG_TPI_OUTPUT, out_fmt,
 	);
 }
 
@@ -1082,18 +1095,28 @@ static ssize_t mhl3_infoframe_pack(struct mhl3_infoframe *frame,
 	return frm_len;
 }
 
-static void sii8620_set_infoframes(struct sii8620 *ctx)
+static void sii8620_set_infoframes(struct sii8620 *ctx,
+				   struct drm_display_mode *mode)
 {
 	struct mhl3_infoframe mhl_frm;
 	union hdmi_infoframe frm;
 	u8 buf[31];
 	int ret;
 
+	ret = drm_hdmi_avi_infoframe_from_display_mode(&frm.avi,
+						       mode,
+						       true);
+	if (ctx->use_packed_pixel)
+		frm.avi.colorspace = HDMI_COLORSPACE_YUV422;
+
+	if (!ret)
+		ret = hdmi_avi_infoframe_pack(&frm.avi, buf, ARRAY_SIZE(buf));
+	if (ret > 0)
+		sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, buf + 3, ret - 3);
+
 	if (!sii8620_is_mhl3(ctx) || !ctx->use_packed_pixel) {
 		sii8620_write(ctx, REG_TPI_SC,
 			BIT_TPI_SC_TPI_OUTPUT_MODE_0_HDMI);
-		sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, ctx->avif + 3,
-			ARRAY_SIZE(ctx->avif) - 3);
 		sii8620_write(ctx, REG_PKT_FILTER_0,
 			BIT_PKT_FILTER_0_DROP_CEA_GAMUT_PKT |
 			BIT_PKT_FILTER_0_DROP_MPEG_PKT |
@@ -1102,16 +1125,6 @@ static void sii8620_set_infoframes(struct sii8620 *ctx)
 		return;
 	}
 
-	ret = hdmi_avi_infoframe_init(&frm.avi);
-	frm.avi.colorspace = HDMI_COLORSPACE_YUV422;
-	frm.avi.active_aspect = HDMI_ACTIVE_ASPECT_PICTURE;
-	frm.avi.picture_aspect = HDMI_PICTURE_ASPECT_16_9;
-	frm.avi.colorimetry = HDMI_COLORIMETRY_ITU_709;
-	frm.avi.video_code = ctx->video_code;
-	if (!ret)
-		ret = hdmi_avi_infoframe_pack(&frm.avi, buf, ARRAY_SIZE(buf));
-	if (ret > 0)
-		sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, buf + 3, ret - 3);
 	sii8620_write(ctx, REG_PKT_FILTER_0,
 		BIT_PKT_FILTER_0_DROP_CEA_GAMUT_PKT |
 		BIT_PKT_FILTER_0_DROP_MPEG_PKT |
@@ -1131,6 +1144,9 @@ static void sii8620_set_infoframes(struct sii8620 *ctx)
 
 static void sii8620_start_video(struct sii8620 *ctx)
 {
+	struct drm_display_mode *mode =
+		&ctx->bridge.encoder->crtc->state->adjusted_mode;
+
 	if (!sii8620_is_mhl3(ctx))
 		sii8620_stop_video(ctx);
 
@@ -1149,8 +1165,14 @@ static void sii8620_start_video(struct sii8620 *ctx)
 	sii8620_set_format(ctx);
 
 	if (!sii8620_is_mhl3(ctx)) {
-		sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
-			MHL_DST_LM_CLK_MODE_NORMAL | MHL_DST_LM_PATH_ENABLED);
+		u8 link_mode = MHL_DST_LM_PATH_ENABLED;
+
+		if (ctx->use_packed_pixel)
+			link_mode |= MHL_DST_LM_CLK_MODE_PACKED_PIXEL;
+		else
+			link_mode |= MHL_DST_LM_CLK_MODE_NORMAL;
+
+		sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), link_mode);
 		sii8620_set_auto_zone(ctx);
 	} else {
 		static const struct {
@@ -1167,7 +1189,7 @@ static void sii8620_start_video(struct sii8620 *ctx)
 			  MHL_XDS_LINK_RATE_6_0_GBPS, 0x40 },
 		};
 		u8 p0_ctrl = BIT_M3_P0CTRL_MHL3_P0_PORT_EN;
-		int clk = ctx->pixel_clock * (ctx->use_packed_pixel ? 2 : 3);
+		int clk = mode->clock * (ctx->use_packed_pixel ? 2 : 3);
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(clk_spec) - 1; ++i)
@@ -1196,7 +1218,7 @@ static void sii8620_start_video(struct sii8620 *ctx)
 			clk_spec[i].link_rate);
 	}
 
-	sii8620_set_infoframes(ctx);
+	sii8620_set_infoframes(ctx, mode);
 }
 
 static void sii8620_disable_hpd(struct sii8620 *ctx)
@@ -1661,14 +1683,18 @@ static void sii8620_status_dcap_ready(struct sii8620 *ctx)
 
 static void sii8620_status_changed_path(struct sii8620 *ctx)
 {
-	if (ctx->stat[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED) {
-		sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
-				      MHL_DST_LM_CLK_MODE_NORMAL
-				      | MHL_DST_LM_PATH_ENABLED);
-	} else {
-		sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
-				      MHL_DST_LM_CLK_MODE_NORMAL);
-	}
+	u8 link_mode;
+
+	if (ctx->use_packed_pixel)
+		link_mode = MHL_DST_LM_CLK_MODE_PACKED_PIXEL;
+	else
+		link_mode = MHL_DST_LM_CLK_MODE_NORMAL;
+
+	if (ctx->stat[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED)
+		link_mode |= MHL_DST_LM_PATH_ENABLED;
+
+	sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
+			      link_mode);
 }
 
 static void sii8620_msc_mr_write_stat(struct sii8620 *ctx)
@@ -2242,8 +2268,6 @@ static bool sii8620_mode_fixup(struct drm_bridge *bridge,
 	mutex_lock(&ctx->lock);
 
 	ctx->use_packed_pixel = sii8620_is_packing_required(ctx, adjusted_mode);
-	ctx->video_code = drm_match_cea_mode(adjusted_mode);
-	ctx->pixel_clock = adjusted_mode->clock;
 
 	mutex_unlock(&ctx->lock);
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 130da5195f3b..81e32199d3ef 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1510,8 +1510,9 @@ int drm_atomic_helper_async_check(struct drm_device *dev,
 {
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
-	struct drm_plane *plane;
-	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane *plane = NULL;
+	struct drm_plane_state *old_plane_state = NULL;
+	struct drm_plane_state *new_plane_state = NULL;
 	const struct drm_plane_helper_funcs *funcs;
 	int i, n_planes = 0;
 
@@ -1527,7 +1528,8 @@ int drm_atomic_helper_async_check(struct drm_device *dev,
 	if (n_planes != 1)
 		return -EINVAL;
 
-	if (!new_plane_state->crtc)
+	if (!new_plane_state->crtc ||
+	    old_plane_state->crtc != new_plane_state->crtc)
 		return -EINVAL;
 
 	funcs = plane->helper_private;
diff --git a/drivers/gpu/drm/drm_context.c b/drivers/gpu/drm/drm_context.c
index 3c4000facb36..f973d287696a 100644
--- a/drivers/gpu/drm/drm_context.c
+++ b/drivers/gpu/drm/drm_context.c
@@ -372,7 +372,7 @@ int drm_legacy_addctx(struct drm_device *dev, void *data,
 		ctx->handle = drm_legacy_ctxbitmap_next(dev);
 	}
 	DRM_DEBUG("%d\n", ctx->handle);
-	if (ctx->handle == -1) {
+	if (ctx->handle < 0) {
 		DRM_DEBUG("Not enough free contexts.\n");
 		/* Should this return -EBUSY instead? */
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index 50c73c0a20b9..b54fb78a283c 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -553,24 +553,13 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 
 	/* Clone the lessor file to create a new file for us */
 	DRM_DEBUG_LEASE("Allocating lease file\n");
-	path_get(&lessor_file->f_path);
-	lessee_file = alloc_file(&lessor_file->f_path,
-				 lessor_file->f_mode,
-				 fops_get(lessor_file->f_inode->i_fop));
-
+	lessee_file = file_clone_open(lessor_file);
 	if (IS_ERR(lessee_file)) {
 		ret = PTR_ERR(lessee_file);
 		goto out_lessee;
 	}
 
-	/* Initialize the new file for DRM */
-	DRM_DEBUG_LEASE("Initializing the file with %p\n", lessee_file->f_op->open);
-	ret = lessee_file->f_op->open(lessee_file->f_inode, lessee_file);
-	if (ret)
-		goto out_lessee_file;
-
 	lessee_priv = lessee_file->private_data;
-
 	/* Change the file to a master one */
 	drm_master_put(&lessee_priv->master);
 	lessee_priv->master = lessee;
@@ -588,9 +577,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n");
 	return 0;
 
-out_lessee_file:
-	fput(lessee_file);
-
 out_lessee:
 	drm_master_put(&lessee);
 
diff --git a/drivers/gpu/drm/drm_property.c b/drivers/gpu/drm/drm_property.c
index 1f8031e30f53..cdb10f885a4f 100644
--- a/drivers/gpu/drm/drm_property.c
+++ b/drivers/gpu/drm/drm_property.c
@@ -532,7 +532,7 @@ static void drm_property_free_blob(struct kref *kref)
 
 	drm_mode_object_unregister(blob->dev, &blob->base);
 
-	kfree(blob);
+	kvfree(blob);
 }
 
 /**
@@ -559,7 +559,7 @@ drm_property_create_blob(struct drm_device *dev, size_t length,
 	if (!length || length > ULONG_MAX - sizeof(struct drm_property_blob))
 		return ERR_PTR(-EINVAL);
 
-	blob = kzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL);
+	blob = kvzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL);
 	if (!blob)
 		return ERR_PTR(-ENOMEM);
 
@@ -576,7 +576,7 @@ drm_property_create_blob(struct drm_device *dev, size_t length,
 	ret = __drm_mode_object_add(dev, &blob->base, DRM_MODE_OBJECT_BLOB,
 				    true, drm_property_free_blob);
 	if (ret) {
-		kfree(blob);
+		kvfree(blob);
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index e5013a999147..540b59fb4103 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -631,8 +631,11 @@ static struct platform_driver etnaviv_platform_driver = {
 	},
 };
 
+static struct platform_device *etnaviv_drm;
+
 static int __init etnaviv_init(void)
 {
+	struct platform_device *pdev;
 	int ret;
 	struct device_node *np;
 
@@ -644,7 +647,7 @@ static int __init etnaviv_init(void)
 
 	ret = platform_driver_register(&etnaviv_platform_driver);
 	if (ret != 0)
-		platform_driver_unregister(&etnaviv_gpu_driver);
+		goto unregister_gpu_driver;
 
 	/*
 	 * If the DT contains at least one available GPU device, instantiate
@@ -653,20 +656,33 @@ static int __init etnaviv_init(void)
 	for_each_compatible_node(np, NULL, "vivante,gc") {
 		if (!of_device_is_available(np))
 			continue;
-
-		platform_device_register_simple("etnaviv", -1, NULL, 0);
+		pdev = platform_device_register_simple("etnaviv", -1,
+						       NULL, 0);
+		if (IS_ERR(pdev)) {
+			ret = PTR_ERR(pdev);
+			of_node_put(np);
+			goto unregister_platform_driver;
+		}
+		etnaviv_drm = pdev;
 		of_node_put(np);
 		break;
 	}
 
+	return 0;
+
+unregister_platform_driver:
+	platform_driver_unregister(&etnaviv_platform_driver);
+unregister_gpu_driver:
+	platform_driver_unregister(&etnaviv_gpu_driver);
 	return ret;
 }
 module_init(etnaviv_init);
 
 static void __exit etnaviv_exit(void)
 {
-	platform_driver_unregister(&etnaviv_gpu_driver);
+	platform_device_unregister(etnaviv_drm);
 	platform_driver_unregister(&etnaviv_platform_driver);
+	platform_driver_unregister(&etnaviv_gpu_driver);
 }
 module_exit(etnaviv_exit);
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index dd430f0f8ff5..90f17ff7888e 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -131,6 +131,9 @@ struct etnaviv_gpu {
 	struct work_struct sync_point_work;
 	int sync_point_event;
 
+	/* hang detection */
+	u32 hangcheck_dma_addr;
+
 	void __iomem *mmio;
 	int irq;
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index a74eb57af15b..50d6b88cb7aa 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -10,6 +10,7 @@
 #include "etnaviv_gem.h"
 #include "etnaviv_gpu.h"
 #include "etnaviv_sched.h"
+#include "state.xml.h"
 
 static int etnaviv_job_hang_limit = 0;
 module_param_named(job_hang_limit, etnaviv_job_hang_limit, int , 0444);
@@ -85,6 +86,29 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
 {
 	struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job);
 	struct etnaviv_gpu *gpu = submit->gpu;
+	u32 dma_addr;
+	int change;
+
+	/*
+	 * If the GPU managed to complete this jobs fence, the timout is
+	 * spurious. Bail out.
+	 */
+	if (fence_completed(gpu, submit->out_fence->seqno))
+		return;
+
+	/*
+	 * If the GPU is still making forward progress on the front-end (which
+	 * should never loop) we shift out the timeout to give it a chance to
+	 * finish the job.
+	 */
+	dma_addr = gpu_read(gpu, VIVS_FE_DMA_ADDRESS);
+	change = dma_addr - gpu->hangcheck_dma_addr;
+	if (change < 0 || change > 16) {
+		gpu->hangcheck_dma_addr = dma_addr;
+		schedule_delayed_work(&sched_job->work_tdr,
+				      sched_job->sched->timeout);
+		return;
+	}
 
 	/* block scheduler */
 	kthread_park(gpu->sched.thread);
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 82c95c34447f..e868773ea509 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -265,7 +265,7 @@ static void decon_win_set_pixfmt(struct decon_context *ctx, unsigned int win,
 	unsigned long val;
 
 	val = readl(ctx->addr + DECON_WINCONx(win));
-	val &= ~WINCONx_BPPMODE_MASK;
+	val &= WINCONx_ENWIN_F;
 
 	switch (fb->format->format) {
 	case DRM_FORMAT_XRGB1555:
@@ -356,8 +356,8 @@ static void decon_update_plane(struct exynos_drm_crtc *crtc,
 		writel(val, ctx->addr + DECON_VIDOSDxB(win));
 	}
 
-	val = VIDOSD_Wx_ALPHA_R_F(0x0) | VIDOSD_Wx_ALPHA_G_F(0x0) |
-		VIDOSD_Wx_ALPHA_B_F(0x0);
+	val = VIDOSD_Wx_ALPHA_R_F(0xff) | VIDOSD_Wx_ALPHA_G_F(0xff) |
+		VIDOSD_Wx_ALPHA_B_F(0xff);
 	writel(val, ctx->addr + DECON_VIDOSDxC(win));
 
 	val = VIDOSD_Wx_ALPHA_R_F(0x0) | VIDOSD_Wx_ALPHA_G_F(0x0) |
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index a81b4a5e24a7..ed3cc2989f93 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -420,7 +420,7 @@ err_mode_config_cleanup:
 err_free_private:
 	kfree(private);
 err_free_drm:
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 
 	return ret;
 }
@@ -444,7 +444,7 @@ static void exynos_drm_unbind(struct device *dev)
 	drm->dev_private = NULL;
 	dev_set_drvdata(dev, NULL);
 
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops exynos_drm_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 7fcc1a7ab1a0..27b7d34d776c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -138,7 +138,7 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 
 err:
 	while (i--)
-		drm_gem_object_unreference_unlocked(&exynos_gem[i]->base);
+		drm_gem_object_put_unlocked(&exynos_gem[i]->base);
 
 	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 6127ef25acd6..e8d0670bb5f8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -470,17 +470,18 @@ static void fimc_src_set_transf(struct fimc_context *ctx, unsigned int rotation)
 static void fimc_set_window(struct fimc_context *ctx,
 			    struct exynos_drm_ipp_buffer *buf)
 {
+	unsigned int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
 	u32 cfg, h1, h2, v1, v2;
 
 	/* cropped image */
 	h1 = buf->rect.x;
-	h2 = buf->buf.width - buf->rect.w - buf->rect.x;
+	h2 = real_width - buf->rect.w - buf->rect.x;
 	v1 = buf->rect.y;
 	v2 = buf->buf.height - buf->rect.h - buf->rect.y;
 
 	DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]hsize[%d]vsize[%d]\n",
 		buf->rect.x, buf->rect.y, buf->rect.w, buf->rect.h,
-		buf->buf.width, buf->buf.height);
+		real_width, buf->buf.height);
 	DRM_DEBUG_KMS("h1[%d]h2[%d]v1[%d]v2[%d]\n", h1, h2, v1, v2);
 
 	/*
@@ -503,12 +504,13 @@ static void fimc_set_window(struct fimc_context *ctx,
 static void fimc_src_set_size(struct fimc_context *ctx,
 			      struct exynos_drm_ipp_buffer *buf)
 {
+	unsigned int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
 	u32 cfg;
 
-	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", buf->buf.width, buf->buf.height);
+	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", real_width, buf->buf.height);
 
 	/* original size */
-	cfg = (EXYNOS_ORGISIZE_HORIZONTAL(buf->buf.width) |
+	cfg = (EXYNOS_ORGISIZE_HORIZONTAL(real_width) |
 		EXYNOS_ORGISIZE_VERTICAL(buf->buf.height));
 
 	fimc_write(ctx, cfg, EXYNOS_ORGISIZE);
@@ -529,7 +531,7 @@ static void fimc_src_set_size(struct fimc_context *ctx,
 	 * for now, we support only ITU601 8 bit mode
 	 */
 	cfg = (EXYNOS_CISRCFMT_ITU601_8BIT |
-		EXYNOS_CISRCFMT_SOURCEHSIZE(buf->buf.width) |
+		EXYNOS_CISRCFMT_SOURCEHSIZE(real_width) |
 		EXYNOS_CISRCFMT_SOURCEVSIZE(buf->buf.height));
 	fimc_write(ctx, cfg, EXYNOS_CISRCFMT);
 
@@ -842,12 +844,13 @@ static void fimc_set_scaler(struct fimc_context *ctx, struct fimc_scaler *sc)
 static void fimc_dst_set_size(struct fimc_context *ctx,
 			     struct exynos_drm_ipp_buffer *buf)
 {
+	unsigned int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
 	u32 cfg, cfg_ext;
 
-	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", buf->buf.width, buf->buf.height);
+	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", real_width, buf->buf.height);
 
 	/* original size */
-	cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(buf->buf.width) |
+	cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(real_width) |
 		EXYNOS_ORGOSIZE_VERTICAL(buf->buf.height));
 
 	fimc_write(ctx, cfg, EXYNOS_ORGOSIZE);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 6e1494fa71b4..bdf5a7655228 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -143,7 +143,7 @@ static int exynos_drm_gem_handle_create(struct drm_gem_object *obj,
 	DRM_DEBUG_KMS("gem handle = 0x%x\n", *handle);
 
 	/* drop reference from allocate - handle holds it now. */
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 
 	return 0;
 }
@@ -186,7 +186,7 @@ unsigned long exynos_drm_gem_get_size(struct drm_device *dev,
 
 	exynos_gem = to_exynos_gem(obj);
 
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 
 	return exynos_gem->size;
 }
@@ -329,13 +329,13 @@ void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
 		return;
 	}
 
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 
 	/*
 	 * decrease obj->refcount one more time because we has already
 	 * increased it at exynos_drm_gem_get_dma_addr().
 	 */
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 }
 
 static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem *exynos_gem,
@@ -383,7 +383,7 @@ int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data,
 	args->flags = exynos_gem->flags;
 	args->size = exynos_gem->size;
 
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 35ac66730563..7ba414b52faa 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -492,21 +492,25 @@ static void gsc_src_set_fmt(struct gsc_context *ctx, u32 fmt)
 			GSC_IN_CHROMA_ORDER_CRCB);
 		break;
 	case DRM_FORMAT_NV21:
+		cfg |= (GSC_IN_CHROMA_ORDER_CRCB | GSC_IN_YUV420_2P);
+		break;
 	case DRM_FORMAT_NV61:
-		cfg |= (GSC_IN_CHROMA_ORDER_CRCB |
-			GSC_IN_YUV420_2P);
+		cfg |= (GSC_IN_CHROMA_ORDER_CRCB | GSC_IN_YUV422_2P);
 		break;
 	case DRM_FORMAT_YUV422:
 		cfg |= GSC_IN_YUV422_3P;
 		break;
 	case DRM_FORMAT_YUV420:
+		cfg |= (GSC_IN_CHROMA_ORDER_CBCR | GSC_IN_YUV420_3P);
+		break;
 	case DRM_FORMAT_YVU420:
-		cfg |= GSC_IN_YUV420_3P;
+		cfg |= (GSC_IN_CHROMA_ORDER_CRCB | GSC_IN_YUV420_3P);
 		break;
 	case DRM_FORMAT_NV12:
+		cfg |= (GSC_IN_CHROMA_ORDER_CBCR | GSC_IN_YUV420_2P);
+		break;
 	case DRM_FORMAT_NV16:
-		cfg |= (GSC_IN_CHROMA_ORDER_CBCR |
-			GSC_IN_YUV420_2P);
+		cfg |= (GSC_IN_CHROMA_ORDER_CBCR | GSC_IN_YUV422_2P);
 		break;
 	}
 
@@ -523,30 +527,30 @@ static void gsc_src_set_transf(struct gsc_context *ctx, unsigned int rotation)
 
 	switch (degree) {
 	case DRM_MODE_ROTATE_0:
-		if (rotation & DRM_MODE_REFLECT_Y)
-			cfg |= GSC_IN_ROT_XFLIP;
 		if (rotation & DRM_MODE_REFLECT_X)
+			cfg |= GSC_IN_ROT_XFLIP;
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg |= GSC_IN_ROT_YFLIP;
 		break;
 	case DRM_MODE_ROTATE_90:
 		cfg |= GSC_IN_ROT_90;
-		if (rotation & DRM_MODE_REFLECT_Y)
-			cfg |= GSC_IN_ROT_XFLIP;
 		if (rotation & DRM_MODE_REFLECT_X)
+			cfg |= GSC_IN_ROT_XFLIP;
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg |= GSC_IN_ROT_YFLIP;
 		break;
 	case DRM_MODE_ROTATE_180:
 		cfg |= GSC_IN_ROT_180;
-		if (rotation & DRM_MODE_REFLECT_Y)
-			cfg &= ~GSC_IN_ROT_XFLIP;
 		if (rotation & DRM_MODE_REFLECT_X)
+			cfg &= ~GSC_IN_ROT_XFLIP;
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg &= ~GSC_IN_ROT_YFLIP;
 		break;
 	case DRM_MODE_ROTATE_270:
 		cfg |= GSC_IN_ROT_270;
-		if (rotation & DRM_MODE_REFLECT_Y)
-			cfg &= ~GSC_IN_ROT_XFLIP;
 		if (rotation & DRM_MODE_REFLECT_X)
+			cfg &= ~GSC_IN_ROT_XFLIP;
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg &= ~GSC_IN_ROT_YFLIP;
 		break;
 	}
@@ -577,7 +581,7 @@ static void gsc_src_set_size(struct gsc_context *ctx,
 	cfg &= ~(GSC_SRCIMG_HEIGHT_MASK |
 		GSC_SRCIMG_WIDTH_MASK);
 
-	cfg |= (GSC_SRCIMG_WIDTH(buf->buf.width) |
+	cfg |= (GSC_SRCIMG_WIDTH(buf->buf.pitch[0] / buf->format->cpp[0]) |
 		GSC_SRCIMG_HEIGHT(buf->buf.height));
 
 	gsc_write(cfg, GSC_SRCIMG_SIZE);
@@ -672,18 +676,25 @@ static void gsc_dst_set_fmt(struct gsc_context *ctx, u32 fmt)
 			GSC_OUT_CHROMA_ORDER_CRCB);
 		break;
 	case DRM_FORMAT_NV21:
-	case DRM_FORMAT_NV61:
 		cfg |= (GSC_OUT_CHROMA_ORDER_CRCB | GSC_OUT_YUV420_2P);
 		break;
+	case DRM_FORMAT_NV61:
+		cfg |= (GSC_OUT_CHROMA_ORDER_CRCB | GSC_OUT_YUV422_2P);
+		break;
 	case DRM_FORMAT_YUV422:
+		cfg |= GSC_OUT_YUV422_3P;
+		break;
 	case DRM_FORMAT_YUV420:
+		cfg |= (GSC_OUT_CHROMA_ORDER_CBCR | GSC_OUT_YUV420_3P);
+		break;
 	case DRM_FORMAT_YVU420:
-		cfg |= GSC_OUT_YUV420_3P;
+		cfg |= (GSC_OUT_CHROMA_ORDER_CRCB | GSC_OUT_YUV420_3P);
 		break;
 	case DRM_FORMAT_NV12:
+		cfg |= (GSC_OUT_CHROMA_ORDER_CBCR | GSC_OUT_YUV420_2P);
+		break;
 	case DRM_FORMAT_NV16:
-		cfg |= (GSC_OUT_CHROMA_ORDER_CBCR |
-			GSC_OUT_YUV420_2P);
+		cfg |= (GSC_OUT_CHROMA_ORDER_CBCR | GSC_OUT_YUV422_2P);
 		break;
 	}
 
@@ -868,7 +879,7 @@ static void gsc_dst_set_size(struct gsc_context *ctx,
 	/* original size */
 	cfg = gsc_read(GSC_DSTIMG_SIZE);
 	cfg &= ~(GSC_DSTIMG_HEIGHT_MASK | GSC_DSTIMG_WIDTH_MASK);
-	cfg |= GSC_DSTIMG_WIDTH(buf->buf.width) |
+	cfg |= GSC_DSTIMG_WIDTH(buf->buf.pitch[0] / buf->format->cpp[0]) |
 	       GSC_DSTIMG_HEIGHT(buf->buf.height);
 	gsc_write(cfg, GSC_DSTIMG_SIZE);
 
@@ -1341,7 +1352,7 @@ static const struct drm_exynos_ipp_limit gsc_5420_limits[] = {
 };
 
 static const struct drm_exynos_ipp_limit gsc_5433_limits[] = {
-	{ IPP_SIZE_LIMIT(BUFFER, .h = { 32, 8191, 2 }, .v = { 16, 8191, 2 }) },
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 32, 8191, 16 }, .v = { 16, 8191, 2 }) },
 	{ IPP_SIZE_LIMIT(AREA, .h = { 16, 4800, 1 }, .v = { 8, 3344, 1 }) },
 	{ IPP_SIZE_LIMIT(ROTATED, .h = { 32, 2047 }, .v = { 8, 8191 }) },
 	{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 16, (1 << 16) * 8 },
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index 26374e58c557..b435db8fc916 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -345,27 +345,6 @@ static int exynos_drm_ipp_task_setup_buffer(struct exynos_drm_ipp_buffer *buf,
 	int ret = 0;
 	int i;
 
-	/* basic checks */
-	if (buf->buf.width == 0 || buf->buf.height == 0)
-		return -EINVAL;
-	buf->format = drm_format_info(buf->buf.fourcc);
-	for (i = 0; i < buf->format->num_planes; i++) {
-		unsigned int width = (i == 0) ? buf->buf.width :
-			     DIV_ROUND_UP(buf->buf.width, buf->format->hsub);
-
-		if (buf->buf.pitch[i] == 0)
-			buf->buf.pitch[i] = width * buf->format->cpp[i];
-		if (buf->buf.pitch[i] < width * buf->format->cpp[i])
-			return -EINVAL;
-		if (!buf->buf.gem_id[i])
-			return -ENOENT;
-	}
-
-	/* pitch for additional planes must match */
-	if (buf->format->num_planes > 2 &&
-	    buf->buf.pitch[1] != buf->buf.pitch[2])
-		return -EINVAL;
-
 	/* get GEM buffers and check their size */
 	for (i = 0; i < buf->format->num_planes; i++) {
 		unsigned int height = (i == 0) ? buf->buf.height :
@@ -428,7 +407,7 @@ enum drm_ipp_size_id {
 	IPP_LIMIT_BUFFER, IPP_LIMIT_AREA, IPP_LIMIT_ROTATED, IPP_LIMIT_MAX
 };
 
-static const enum drm_ipp_size_id limit_id_fallback[IPP_LIMIT_MAX][4] = {
+static const enum drm_exynos_ipp_limit_type limit_id_fallback[IPP_LIMIT_MAX][4] = {
 	[IPP_LIMIT_BUFFER]  = { DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER },
 	[IPP_LIMIT_AREA]    = { DRM_EXYNOS_IPP_LIMIT_SIZE_AREA,
 				DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER },
@@ -495,12 +474,13 @@ static int exynos_drm_ipp_check_size_limits(struct exynos_drm_ipp_buffer *buf,
 	enum drm_ipp_size_id id = rotate ? IPP_LIMIT_ROTATED : IPP_LIMIT_AREA;
 	struct drm_ipp_limit l;
 	struct drm_exynos_ipp_limit_val *lh = &l.h, *lv = &l.v;
+	int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
 
 	if (!limits)
 		return 0;
 
 	__get_size_limit(limits, num_limits, IPP_LIMIT_BUFFER, &l);
-	if (!__size_limit_check(buf->buf.width, &l.h) ||
+	if (!__size_limit_check(real_width, &l.h) ||
 	    !__size_limit_check(buf->buf.height, &l.v))
 		return -EINVAL;
 
@@ -560,10 +540,62 @@ static int exynos_drm_ipp_check_scale_limits(
 	return 0;
 }
 
+static int exynos_drm_ipp_check_format(struct exynos_drm_ipp_task *task,
+				       struct exynos_drm_ipp_buffer *buf,
+				       struct exynos_drm_ipp_buffer *src,
+				       struct exynos_drm_ipp_buffer *dst,
+				       bool rotate, bool swap)
+{
+	const struct exynos_drm_ipp_formats *fmt;
+	int ret, i;
+
+	fmt = __ipp_format_get(task->ipp, buf->buf.fourcc, buf->buf.modifier,
+			       buf == src ? DRM_EXYNOS_IPP_FORMAT_SOURCE :
+					    DRM_EXYNOS_IPP_FORMAT_DESTINATION);
+	if (!fmt) {
+		DRM_DEBUG_DRIVER("Task %pK: %s format not supported\n", task,
+				 buf == src ? "src" : "dst");
+		return -EINVAL;
+	}
+
+	/* basic checks */
+	if (buf->buf.width == 0 || buf->buf.height == 0)
+		return -EINVAL;
+
+	buf->format = drm_format_info(buf->buf.fourcc);
+	for (i = 0; i < buf->format->num_planes; i++) {
+		unsigned int width = (i == 0) ? buf->buf.width :
+			     DIV_ROUND_UP(buf->buf.width, buf->format->hsub);
+
+		if (buf->buf.pitch[i] == 0)
+			buf->buf.pitch[i] = width * buf->format->cpp[i];
+		if (buf->buf.pitch[i] < width * buf->format->cpp[i])
+			return -EINVAL;
+		if (!buf->buf.gem_id[i])
+			return -ENOENT;
+	}
+
+	/* pitch for additional planes must match */
+	if (buf->format->num_planes > 2 &&
+	    buf->buf.pitch[1] != buf->buf.pitch[2])
+		return -EINVAL;
+
+	/* check driver limits */
+	ret = exynos_drm_ipp_check_size_limits(buf, fmt->limits,
+					       fmt->num_limits,
+					       rotate,
+					       buf == dst ? swap : false);
+	if (ret)
+		return ret;
+	ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
+						fmt->limits,
+						fmt->num_limits, swap);
+	return ret;
+}
+
 static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
 {
 	struct exynos_drm_ipp *ipp = task->ipp;
-	const struct exynos_drm_ipp_formats *src_fmt, *dst_fmt;
 	struct exynos_drm_ipp_buffer *src = &task->src, *dst = &task->dst;
 	unsigned int rotation = task->transform.rotation;
 	int ret = 0;
@@ -607,37 +639,11 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
 		return -EINVAL;
 	}
 
-	src_fmt = __ipp_format_get(ipp, src->buf.fourcc, src->buf.modifier,
-				   DRM_EXYNOS_IPP_FORMAT_SOURCE);
-	if (!src_fmt) {
-		DRM_DEBUG_DRIVER("Task %pK: src format not supported\n", task);
-		return -EINVAL;
-	}
-	ret = exynos_drm_ipp_check_size_limits(src, src_fmt->limits,
-					       src_fmt->num_limits,
-					       rotate, false);
-	if (ret)
-		return ret;
-	ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
-						src_fmt->limits,
-						src_fmt->num_limits, swap);
+	ret = exynos_drm_ipp_check_format(task, src, src, dst, rotate, swap);
 	if (ret)
 		return ret;
 
-	dst_fmt = __ipp_format_get(ipp, dst->buf.fourcc, dst->buf.modifier,
-				   DRM_EXYNOS_IPP_FORMAT_DESTINATION);
-	if (!dst_fmt) {
-		DRM_DEBUG_DRIVER("Task %pK: dst format not supported\n", task);
-		return -EINVAL;
-	}
-	ret = exynos_drm_ipp_check_size_limits(dst, dst_fmt->limits,
-					       dst_fmt->num_limits,
-					       false, swap);
-	if (ret)
-		return ret;
-	ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
-						dst_fmt->limits,
-						dst_fmt->num_limits, swap);
+	ret = exynos_drm_ipp_check_format(task, dst, src, dst, false, swap);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index 38a2a7f1204b..7098c6d35266 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -132,7 +132,7 @@ static void exynos_drm_plane_reset(struct drm_plane *plane)
 	if (plane->state) {
 		exynos_state = to_exynos_plane_state(plane->state);
 		if (exynos_state->base.fb)
-			drm_framebuffer_unreference(exynos_state->base.fb);
+			drm_framebuffer_put(exynos_state->base.fb);
 		kfree(exynos_state);
 		plane->state = NULL;
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 1a76dd3d52e1..a820a68429b9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -168,9 +168,9 @@ static void rotator_dst_set_transf(struct rot_context *rot,
 	val &= ~ROT_CONTROL_FLIP_MASK;
 
 	if (rotation & DRM_MODE_REFLECT_X)
-		val |= ROT_CONTROL_FLIP_HORIZONTAL;
-	if (rotation & DRM_MODE_REFLECT_Y)
 		val |= ROT_CONTROL_FLIP_VERTICAL;
+	if (rotation & DRM_MODE_REFLECT_Y)
+		val |= ROT_CONTROL_FLIP_HORIZONTAL;
 
 	val &= ~ROT_CONTROL_ROT_MASK;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
index 91d4382343d0..0ddb6eec7b11 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
@@ -30,6 +30,7 @@
 #define scaler_write(cfg, offset)	writel(cfg, scaler->regs + (offset))
 #define SCALER_MAX_CLK			4
 #define SCALER_AUTOSUSPEND_DELAY	2000
+#define SCALER_RESET_WAIT_RETRIES	100
 
 struct scaler_data {
 	const char	*clk_name[SCALER_MAX_CLK];
@@ -51,9 +52,9 @@ struct scaler_context {
 static u32 scaler_get_format(u32 drm_fmt)
 {
 	switch (drm_fmt) {
-	case DRM_FORMAT_NV21:
-		return SCALER_YUV420_2P_UV;
 	case DRM_FORMAT_NV12:
+		return SCALER_YUV420_2P_UV;
+	case DRM_FORMAT_NV21:
 		return SCALER_YUV420_2P_VU;
 	case DRM_FORMAT_YUV420:
 		return SCALER_YUV420_3P;
@@ -63,15 +64,15 @@ static u32 scaler_get_format(u32 drm_fmt)
 		return SCALER_YUV422_1P_UYVY;
 	case DRM_FORMAT_YVYU:
 		return SCALER_YUV422_1P_YVYU;
-	case DRM_FORMAT_NV61:
-		return SCALER_YUV422_2P_UV;
 	case DRM_FORMAT_NV16:
+		return SCALER_YUV422_2P_UV;
+	case DRM_FORMAT_NV61:
 		return SCALER_YUV422_2P_VU;
 	case DRM_FORMAT_YUV422:
 		return SCALER_YUV422_3P;
-	case DRM_FORMAT_NV42:
-		return SCALER_YUV444_2P_UV;
 	case DRM_FORMAT_NV24:
+		return SCALER_YUV444_2P_UV;
+	case DRM_FORMAT_NV42:
 		return SCALER_YUV444_2P_VU;
 	case DRM_FORMAT_YUV444:
 		return SCALER_YUV444_3P;
@@ -100,6 +101,23 @@ static u32 scaler_get_format(u32 drm_fmt)
 	return 0;
 }
 
+static inline int scaler_reset(struct scaler_context *scaler)
+{
+	int retry = SCALER_RESET_WAIT_RETRIES;
+
+	scaler_write(SCALER_CFG_SOFT_RESET, SCALER_CFG);
+	do {
+		cpu_relax();
+	} while (retry > 1 &&
+		 scaler_read(SCALER_CFG) & SCALER_CFG_SOFT_RESET);
+	do {
+		cpu_relax();
+		scaler_write(1, SCALER_INT_EN);
+	} while (retry > 0 && scaler_read(SCALER_INT_EN) != 1);
+
+	return retry ? 0 : -EIO;
+}
+
 static inline void scaler_enable_int(struct scaler_context *scaler)
 {
 	u32 val;
@@ -354,9 +372,13 @@ static int scaler_commit(struct exynos_drm_ipp *ipp,
 	u32 dst_fmt = scaler_get_format(task->dst.buf.fourcc);
 	struct drm_exynos_ipp_task_rect *dst_pos = &task->dst.rect;
 
-	scaler->task = task;
-
 	pm_runtime_get_sync(scaler->dev);
+	if (scaler_reset(scaler)) {
+		pm_runtime_put(scaler->dev);
+		return -EIO;
+	}
+
+	scaler->task = task;
 
 	scaler_set_src_fmt(scaler, src_fmt);
 	scaler_set_src_base(scaler, &task->src);
@@ -394,7 +416,11 @@ static inline void scaler_disable_int(struct scaler_context *scaler)
 
 static inline u32 scaler_get_int_status(struct scaler_context *scaler)
 {
-	return scaler_read(SCALER_INT_STATUS);
+	u32 val = scaler_read(SCALER_INT_STATUS);
+
+	scaler_write(val, SCALER_INT_STATUS);
+
+	return val;
 }
 
 static inline int scaler_task_done(u32 val)
diff --git a/drivers/gpu/drm/exynos/regs-gsc.h b/drivers/gpu/drm/exynos/regs-gsc.h
index 4704a993cbb7..16b39734115c 100644
--- a/drivers/gpu/drm/exynos/regs-gsc.h
+++ b/drivers/gpu/drm/exynos/regs-gsc.h
@@ -138,6 +138,7 @@
 #define GSC_OUT_YUV420_3P		(3 << 4)
 #define GSC_OUT_YUV422_1P		(4 << 4)
 #define GSC_OUT_YUV422_2P		(5 << 4)
+#define GSC_OUT_YUV422_3P		(6 << 4)
 #define GSC_OUT_YUV444			(7 << 4)
 #define GSC_OUT_TILE_TYPE_MASK		(1 << 2)
 #define GSC_OUT_TILE_C_16x8		(0 << 2)
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index dfd95889f4b7..5c607f2c707b 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -23,6 +23,7 @@ config DRM_I915
 	select SYNC_FILE
 	select IOSF_MBI
 	select CRC32
+	select SND_HDA_I915 if SND_HDA_CORE
 	help
 	  Choose this option if you have a system that has "Intel Graphics
 	  Media Accelerator" or "HD Graphics" integrated graphics,
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index b51c05d03f14..7f562410f9cf 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -862,6 +862,7 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 {
 	struct intel_vgpu *vgpu = s->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
+	u32 ctx_sr_ctl;
 
 	if (offset + 4 > gvt->device_info.mmio_size) {
 		gvt_vgpu_err("%s access to (%x) outside of MMIO range\n",
@@ -894,6 +895,28 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 		patch_value(s, cmd_ptr(s, index), VGT_PVINFO_PAGE);
 	}
 
+	/* TODO
+	 * Right now only scan LRI command on KBL and in inhibit context.
+	 * It's good enough to support initializing mmio by lri command in
+	 * vgpu inhibit context on KBL.
+	 */
+	if (IS_KABYLAKE(s->vgpu->gvt->dev_priv) &&
+			intel_gvt_mmio_is_in_ctx(gvt, offset) &&
+			!strncmp(cmd, "lri", 3)) {
+		intel_gvt_hypervisor_read_gpa(s->vgpu,
+			s->workload->ring_context_gpa + 12, &ctx_sr_ctl, 4);
+		/* check inhibit context */
+		if (ctx_sr_ctl & 1) {
+			u32 data = cmd_val(s, index + 1);
+
+			if (intel_gvt_mmio_has_mode_mask(s->vgpu->gvt, offset))
+				intel_vgpu_mask_mmio_write(vgpu,
+							offset, &data, 4);
+			else
+				vgpu_vreg(vgpu, offset) = data;
+		}
+	}
+
 	/* TODO: Update the global mask if this MMIO is a masked-MMIO */
 	intel_gvt_mmio_set_cmd_accessed(gvt, offset);
 	return 0;
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 6d8180e8d1e2..4b072ade8c38 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -196,7 +196,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
 			TRANS_DDI_PORT_MASK);
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
-			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
 			(PORT_B << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
 		if (IS_BROADWELL(dev_priv)) {
@@ -216,7 +216,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
 			TRANS_DDI_PORT_MASK);
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
-			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
 			(PORT_C << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
 		if (IS_BROADWELL(dev_priv)) {
@@ -236,7 +236,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
 			TRANS_DDI_PORT_MASK);
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
-			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
 			(PORT_D << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
 		if (IS_BROADWELL(dev_priv)) {
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 23296547da95..4efec8fa6c1d 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1592,6 +1592,7 @@ static struct intel_vgpu_mm *intel_vgpu_create_ggtt_mm(struct intel_vgpu *vgpu)
 		vgpu_free_mm(mm);
 		return ERR_PTR(-ENOMEM);
 	}
+	mm->ggtt_mm.last_partial_off = -1UL;
 
 	return mm;
 }
@@ -1616,6 +1617,7 @@ void _intel_vgpu_mm_release(struct kref *mm_ref)
 		invalidate_ppgtt_mm(mm);
 	} else {
 		vfree(mm->ggtt_mm.virtual_ggtt);
+		mm->ggtt_mm.last_partial_off = -1UL;
 	}
 
 	vgpu_free_mm(mm);
@@ -1868,6 +1870,62 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data,
 			bytes);
 
+	/* If ggtt entry size is 8 bytes, and it's split into two 4 bytes
+	 * write, we assume the two 4 bytes writes are consecutive.
+	 * Otherwise, we abort and report error
+	 */
+	if (bytes < info->gtt_entry_size) {
+		if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) {
+			/* the first partial part*/
+			ggtt_mm->ggtt_mm.last_partial_off = off;
+			ggtt_mm->ggtt_mm.last_partial_data = e.val64;
+			return 0;
+		} else if ((g_gtt_index ==
+				(ggtt_mm->ggtt_mm.last_partial_off >>
+				info->gtt_entry_size_shift)) &&
+			(off !=	ggtt_mm->ggtt_mm.last_partial_off)) {
+			/* the second partial part */
+
+			int last_off = ggtt_mm->ggtt_mm.last_partial_off &
+				(info->gtt_entry_size - 1);
+
+			memcpy((void *)&e.val64 + last_off,
+				(void *)&ggtt_mm->ggtt_mm.last_partial_data +
+				last_off, bytes);
+
+			ggtt_mm->ggtt_mm.last_partial_off = -1UL;
+		} else {
+			int last_offset;
+
+			gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n",
+					ggtt_mm->ggtt_mm.last_partial_off, off,
+					bytes, info->gtt_entry_size);
+
+			/* set host ggtt entry to scratch page and clear
+			 * virtual ggtt entry as not present for last
+			 * partially write offset
+			 */
+			last_offset = ggtt_mm->ggtt_mm.last_partial_off &
+					(~(info->gtt_entry_size - 1));
+
+			ggtt_get_host_entry(ggtt_mm, &m, last_offset);
+			ggtt_invalidate_pte(vgpu, &m);
+			ops->set_pfn(&m, gvt->gtt.scratch_mfn);
+			ops->clear_present(&m);
+			ggtt_set_host_entry(ggtt_mm, &m, last_offset);
+			ggtt_invalidate(gvt->dev_priv);
+
+			ggtt_get_guest_entry(ggtt_mm, &e, last_offset);
+			ops->clear_present(&e);
+			ggtt_set_guest_entry(ggtt_mm, &e, last_offset);
+
+			ggtt_mm->ggtt_mm.last_partial_off = off;
+			ggtt_mm->ggtt_mm.last_partial_data = e.val64;
+
+			return 0;
+		}
+	}
+
 	if (ops->test_present(&e)) {
 		gfn = ops->get_pfn(&e);
 		m = e;
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 3792f2b7f4ff..97e62647418a 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -150,6 +150,8 @@ struct intel_vgpu_mm {
 		} ppgtt_mm;
 		struct {
 			void *virtual_ggtt;
+			unsigned long last_partial_off;
+			u64 last_partial_data;
 		} ggtt_mm;
 	};
 };
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 05d15a095310..858967daf04b 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -268,6 +268,8 @@ struct intel_gvt_mmio {
 #define F_CMD_ACCESSED	(1 << 5)
 /* This reg could be accessed by unaligned address */
 #define F_UNALIGN	(1 << 6)
+/* This reg is saved/restored in context */
+#define F_IN_CTX	(1 << 7)
 
 	struct gvt_mmio_block *mmio_block;
 	unsigned int num_mmio_block;
@@ -639,6 +641,33 @@ static inline bool intel_gvt_mmio_has_mode_mask(
 	return gvt->mmio.mmio_attribute[offset >> 2] & F_MODE_MASK;
 }
 
+/**
+ * intel_gvt_mmio_is_in_ctx - check if a MMIO has in-ctx mask
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ * Returns:
+ * True if a MMIO has a in-context mask, false if it isn't.
+ *
+ */
+static inline bool intel_gvt_mmio_is_in_ctx(
+			struct intel_gvt *gvt, unsigned int offset)
+{
+	return gvt->mmio.mmio_attribute[offset >> 2] & F_IN_CTX;
+}
+
+/**
+ * intel_gvt_mmio_set_in_ctx - mask a MMIO in logical context
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ */
+static inline void intel_gvt_mmio_set_in_ctx(
+			struct intel_gvt *gvt, unsigned int offset)
+{
+	gvt->mmio.mmio_attribute[offset >> 2] |= F_IN_CTX;
+}
+
 int intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu);
 void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu);
 int intel_gvt_debugfs_init(struct intel_gvt *gvt);
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index bcbc47a88a70..8f1caacdc78a 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -3046,6 +3046,30 @@ int intel_vgpu_default_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 }
 
 /**
+ * intel_vgpu_mask_mmio_write - write mask register
+ * @vgpu: a vGPU
+ * @offset: access offset
+ * @p_data: write data buffer
+ * @bytes: access data length
+ *
+ * Returns:
+ * Zero on success, negative error code if failed.
+ */
+int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+		void *p_data, unsigned int bytes)
+{
+	u32 mask, old_vreg;
+
+	old_vreg = vgpu_vreg(vgpu, offset);
+	write_vreg(vgpu, offset, p_data, bytes);
+	mask = vgpu_vreg(vgpu, offset) >> 16;
+	vgpu_vreg(vgpu, offset) = (old_vreg & ~mask) |
+				(vgpu_vreg(vgpu, offset) & mask);
+
+	return 0;
+}
+
+/**
  * intel_gvt_in_force_nonpriv_whitelist - if a mmio is in whitelist to be
  * force-nopriv register
  *
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 71b620875943..dac8c6401e26 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -98,4 +98,6 @@ bool intel_gvt_in_force_nonpriv_whitelist(struct intel_gvt *gvt,
 int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset,
 			   void *pdata, unsigned int bytes, bool is_read);
 
+int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+				  void *p_data, unsigned int bytes);
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 0f949554d118..5ca9caf7552a 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -581,7 +581,9 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt)
 
 	for (mmio = gvt->engine_mmio_list.mmio;
 	     i915_mmio_reg_valid(mmio->reg); mmio++) {
-		if (mmio->in_context)
+		if (mmio->in_context) {
 			gvt->engine_mmio_list.ctx_mmio_count[mmio->ring_id]++;
+			intel_gvt_mmio_set_in_ctx(gvt, mmio->reg.reg);
+		}
 	}
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7014a96546f4..71e1aa54f774 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -652,6 +652,7 @@ enum intel_sbi_destination {
 #define QUIRK_BACKLIGHT_PRESENT (1<<3)
 #define QUIRK_PIN_SWIZZLED_PAGES (1<<5)
 #define QUIRK_INCREASE_T12_DELAY (1<<6)
+#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7)
 
 struct intel_fbdev;
 struct intel_fbc_work;
@@ -2245,9 +2246,6 @@ static inline struct scatterlist *____sg_next(struct scatterlist *sg)
  **/
 static inline struct scatterlist *__sg_next(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	return sg_is_last(sg) ? NULL : ____sg_next(sg);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d44ad7bc1e94..17c5097721e8 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2002,7 +2002,6 @@ int i915_gem_fault(struct vm_fault *vmf)
 	bool write = !!(vmf->flags & FAULT_FLAG_WRITE);
 	struct i915_vma *vma;
 	pgoff_t page_offset;
-	unsigned int flags;
 	int ret;
 
 	/* We don't use vmf->pgoff since that has the fake offset */
@@ -2038,27 +2037,34 @@ int i915_gem_fault(struct vm_fault *vmf)
 		goto err_unlock;
 	}
 
-	/* If the object is smaller than a couple of partial vma, it is
-	 * not worth only creating a single partial vma - we may as well
-	 * clear enough space for the full object.
-	 */
-	flags = PIN_MAPPABLE;
-	if (obj->base.size > 2 * MIN_CHUNK_PAGES << PAGE_SHIFT)
-		flags |= PIN_NONBLOCK | PIN_NONFAULT;
 
 	/* Now pin it into the GTT as needed */
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, flags);
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+				       PIN_MAPPABLE |
+				       PIN_NONBLOCK |
+				       PIN_NONFAULT);
 	if (IS_ERR(vma)) {
 		/* Use a partial view if it is bigger than available space */
 		struct i915_ggtt_view view =
 			compute_partial_view(obj, page_offset, MIN_CHUNK_PAGES);
+		unsigned int flags;
 
-		/* Userspace is now writing through an untracked VMA, abandon
+		flags = PIN_MAPPABLE;
+		if (view.type == I915_GGTT_VIEW_NORMAL)
+			flags |= PIN_NONBLOCK; /* avoid warnings for pinned */
+
+		/*
+		 * Userspace is now writing through an untracked VMA, abandon
 		 * all hope that the hardware is able to track future writes.
 		 */
 		obj->frontbuffer_ggtt_origin = ORIGIN_CPU;
 
-		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, PIN_MAPPABLE);
+		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+		if (IS_ERR(vma) && !view.type) {
+			flags = PIN_MAPPABLE;
+			view.type = I915_GGTT_VIEW_PARTIAL;
+			vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+		}
 	}
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4a02747ac658..c16cb025755e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1998,10 +1998,38 @@ static void valleyview_pipestat_irq_handler(struct drm_i915_private *dev_priv,
 
 static u32 i9xx_hpd_irq_ack(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
+	u32 hotplug_status = 0, hotplug_status_mask;
+	int i;
+
+	if (IS_G4X(dev_priv) ||
+	    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		hotplug_status_mask = HOTPLUG_INT_STATUS_G4X |
+			DP_AUX_CHANNEL_MASK_INT_STATUS_G4X;
+	else
+		hotplug_status_mask = HOTPLUG_INT_STATUS_I915;
 
-	if (hotplug_status)
+	/*
+	 * We absolutely have to clear all the pending interrupt
+	 * bits in PORT_HOTPLUG_STAT. Otherwise the ISR port
+	 * interrupt bit won't have an edge, and the i965/g4x
+	 * edge triggered IIR will not notice that an interrupt
+	 * is still pending. We can't use PORT_HOTPLUG_EN to
+	 * guarantee the edge as the act of toggling the enable
+	 * bits can itself generate a new hotplug interrupt :(
+	 */
+	for (i = 0; i < 10; i++) {
+		u32 tmp = I915_READ(PORT_HOTPLUG_STAT) & hotplug_status_mask;
+
+		if (tmp == 0)
+			return hotplug_status;
+
+		hotplug_status |= tmp;
 		I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
+	}
+
+	WARN_ONCE(1,
+		  "PORT_HOTPLUG_STAT did not clear (0x%08x)\n",
+		  I915_READ(PORT_HOTPLUG_STAT));
 
 	return hotplug_status;
 }
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index dc87797db500..b50b74053664 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -4,6 +4,7 @@
  * Copyright © 2017-2018 Intel Corporation
  */
 
+#include <linux/irq.h>
 #include "i915_pmu.h"
 #include "intel_ringbuffer.h"
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 9324d476e0a7..0531c01c3604 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -109,7 +109,7 @@ vma_create(struct drm_i915_gem_object *obj,
 						     obj->base.size >> PAGE_SHIFT));
 			vma->size = view->partial.size;
 			vma->size <<= PAGE_SHIFT;
-			GEM_BUG_ON(vma->size >= obj->base.size);
+			GEM_BUG_ON(vma->size > obj->base.size);
 		} else if (view->type == I915_GGTT_VIEW_ROTATED) {
 			vma->size = intel_rotation_info_size(&view->rotated);
 			vma->size <<= PAGE_SHIFT;
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 3ea566f99450..7dd5605d94ae 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -639,11 +639,12 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 	dev_priv->av_enc_map[pipe] = encoder;
 	mutex_unlock(&dev_priv->av_mutex);
 
-	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) {
+	if (acomp && acomp->base.audio_ops &&
+	    acomp->base.audio_ops->pin_eld_notify) {
 		/* audio drivers expect pipe = -1 to indicate Non-MST cases */
 		if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST))
 			pipe = -1;
-		acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr,
+		acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr,
 						 (int) port, (int) pipe);
 	}
 
@@ -681,11 +682,12 @@ void intel_audio_codec_disable(struct intel_encoder *encoder,
 	dev_priv->av_enc_map[pipe] = NULL;
 	mutex_unlock(&dev_priv->av_mutex);
 
-	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) {
+	if (acomp && acomp->base.audio_ops &&
+	    acomp->base.audio_ops->pin_eld_notify) {
 		/* audio drivers expect pipe = -1 to indicate Non-MST cases */
 		if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST))
 			pipe = -1;
-		acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr,
+		acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr,
 						 (int) port, (int) pipe);
 	}
 
@@ -880,7 +882,7 @@ static int i915_audio_component_get_eld(struct device *kdev, int port,
 	return ret;
 }
 
-static const struct i915_audio_component_ops i915_audio_component_ops = {
+static const struct drm_audio_component_ops i915_audio_component_ops = {
 	.owner		= THIS_MODULE,
 	.get_power	= i915_audio_component_get_power,
 	.put_power	= i915_audio_component_put_power,
@@ -897,12 +899,12 @@ static int i915_audio_component_bind(struct device *i915_kdev,
 	struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev);
 	int i;
 
-	if (WARN_ON(acomp->ops || acomp->dev))
+	if (WARN_ON(acomp->base.ops || acomp->base.dev))
 		return -EEXIST;
 
 	drm_modeset_lock_all(&dev_priv->drm);
-	acomp->ops = &i915_audio_component_ops;
-	acomp->dev = i915_kdev;
+	acomp->base.ops = &i915_audio_component_ops;
+	acomp->base.dev = i915_kdev;
 	BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS);
 	for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++)
 		acomp->aud_sample_rate[i] = 0;
@@ -919,8 +921,8 @@ static void i915_audio_component_unbind(struct device *i915_kdev,
 	struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev);
 
 	drm_modeset_lock_all(&dev_priv->drm);
-	acomp->ops = NULL;
-	acomp->dev = NULL;
+	acomp->base.ops = NULL;
+	acomp->base.dev = NULL;
 	dev_priv->audio_component = NULL;
 	drm_modeset_unlock_all(&dev_priv->drm);
 }
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index f4a8598a2d39..fed26d6e4e27 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1782,15 +1782,24 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
 }
 
-void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
-				       enum transcoder cpu_transcoder)
+void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder);
 	uint32_t val = I915_READ(reg);
 
 	val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK | TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
 	val |= TRANS_DDI_PORT_NONE;
 	I915_WRITE(reg, val);
+
+	if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME &&
+	    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
+		DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n");
+		/* Quirk time at 100ms for reliable operation */
+		msleep(100);
+	}
 }
 
 int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 2cc6faa1daa8..dec0d60921bf 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5809,7 +5809,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 		intel_ddi_set_vc_payload_alloc(intel_crtc->config, false);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
+		intel_ddi_disable_transcoder_func(old_crtc_state);
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		skylake_scaler_disable(intel_crtc);
@@ -14646,6 +14646,18 @@ static void quirk_increase_t12_delay(struct drm_device *dev)
 	DRM_INFO("Applying T12 delay quirk\n");
 }
 
+/*
+ * GeminiLake NUC HDMI outputs require additional off time
+ * this allows the onboard retimer to correctly sync to signal
+ */
+static void quirk_increase_ddi_disabled_time(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	dev_priv->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME;
+	DRM_INFO("Applying Increase DDI Disabled quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -14732,6 +14744,13 @@ static struct intel_quirk intel_quirks[] = {
 
 	/* Toshiba Satellite P50-C-18C */
 	{ 0x191B, 0x1179, 0xF840, quirk_increase_t12_delay },
+
+	/* GeminiLake NUC */
+	{ 0x3185, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+	/* ASRock ITX*/
+	{ 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0361130500a6..b8eefbffc77d 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1388,8 +1388,7 @@ void hsw_fdi_link_train(struct intel_crtc *crtc,
 void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port);
 bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe);
 void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state);
-void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
-				       enum transcoder cpu_transcoder);
+void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state);
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state);
 void intel_ddi_disable_pipe_clock(const  struct intel_crtc_state *crtc_state);
 struct intel_encoder *
diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c
index 6269750e2b54..b4941101f21a 100644
--- a/drivers/gpu/drm/i915/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/intel_lpe_audio.c
@@ -62,6 +62,7 @@
 
 #include <linux/acpi.h>
 #include <linux/device.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 56dd7a9a8e25..dd5312b02a8d 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -612,6 +612,9 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		return PTR_ERR(imx_ldb->regmap);
 	}
 
+	/* disable LDB by resetting the control register to POR default */
+	regmap_write(imx_ldb->regmap, IOMUXC_GPR2, 0);
+
 	imx_ldb->dev = dev;
 
 	if (of_id)
@@ -652,14 +655,14 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		if (ret || i < 0 || i > 1)
 			return -EINVAL;
 
+		if (!of_device_is_available(child))
+			continue;
+
 		if (dual && i > 0) {
 			dev_warn(dev, "dual-channel mode, ignoring second output\n");
 			continue;
 		}
 
-		if (!of_device_is_available(child))
-			continue;
-
 		channel = &imx_ldb->channel[i];
 		channel->ldb = imx_ldb;
 		channel->chno = i;
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 32b1a6cdecfc..d3443125e661 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -197,8 +197,10 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	priv->io_base = regs;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hhi");
-	if (!res)
-		return -EINVAL;
+	if (!res) {
+		ret = -EINVAL;
+		goto free_drm;
+	}
 	/* Simply ioremap since it may be a shared register zone */
 	regs = devm_ioremap(dev, res->start, resource_size(res));
 	if (!regs) {
@@ -215,8 +217,10 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dmc");
-	if (!res)
-		return -EINVAL;
+	if (!res) {
+		ret = -EINVAL;
+		goto free_drm;
+	}
 	/* Simply ioremap since it may be a shared register zone */
 	regs = devm_ioremap(dev, res->start, resource_size(res));
 	if (!regs) {
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c
index 501d2d290e9c..70dce544984e 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c
@@ -55,6 +55,9 @@ nv04_display_create(struct drm_device *dev)
 	nouveau_display(dev)->init = nv04_display_init;
 	nouveau_display(dev)->fini = nv04_display_fini;
 
+	/* Pre-nv50 doesn't support atomic, so don't expose the ioctls */
+	dev->driver->driver_features &= ~DRIVER_ATOMIC;
+
 	nouveau_hw_save_vga_fonts(dev, 1);
 
 	nv04_crtc_create(dev, 0);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index b83465ae7c1b..9bae4db84cfb 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -1585,8 +1585,9 @@ nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe)
  *****************************************************************************/
 
 static void
-nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock)
+nv50_disp_atomic_commit_core(struct drm_atomic_state *state, u32 *interlock)
 {
+	struct nouveau_drm *drm = nouveau_drm(state->dev);
 	struct nv50_disp *disp = nv50_disp(drm->dev);
 	struct nv50_core *core = disp->core;
 	struct nv50_mstm *mstm;
@@ -1618,6 +1619,22 @@ nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock)
 }
 
 static void
+nv50_disp_atomic_commit_wndw(struct drm_atomic_state *state, u32 *interlock)
+{
+	struct drm_plane_state *new_plane_state;
+	struct drm_plane *plane;
+	int i;
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		struct nv50_wndw *wndw = nv50_wndw(plane);
+		if (interlock[wndw->interlock.type] & wndw->interlock.data) {
+			if (wndw->func->update)
+				wndw->func->update(wndw, interlock);
+		}
+	}
+}
+
+static void
 nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
@@ -1684,7 +1701,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 			help->disable(encoder);
 			interlock[NV50_DISP_INTERLOCK_CORE] |= 1;
 			if (outp->flush_disable) {
-				nv50_disp_atomic_commit_core(drm, interlock);
+				nv50_disp_atomic_commit_wndw(state, interlock);
+				nv50_disp_atomic_commit_core(state, interlock);
 				memset(interlock, 0x00, sizeof(interlock));
 			}
 		}
@@ -1693,15 +1711,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 	/* Flush disable. */
 	if (interlock[NV50_DISP_INTERLOCK_CORE]) {
 		if (atom->flush_disable) {
-			for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-				struct nv50_wndw *wndw = nv50_wndw(plane);
-				if (interlock[wndw->interlock.type] & wndw->interlock.data) {
-					if (wndw->func->update)
-						wndw->func->update(wndw, interlock);
-				}
-			}
-
-			nv50_disp_atomic_commit_core(drm, interlock);
+			nv50_disp_atomic_commit_wndw(state, interlock);
+			nv50_disp_atomic_commit_core(state, interlock);
 			memset(interlock, 0x00, sizeof(interlock));
 		}
 	}
@@ -1762,18 +1773,14 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 	}
 
 	/* Flush update. */
-	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		struct nv50_wndw *wndw = nv50_wndw(plane);
-		if (interlock[wndw->interlock.type] & wndw->interlock.data) {
-			if (wndw->func->update)
-				wndw->func->update(wndw, interlock);
-		}
-	}
+	nv50_disp_atomic_commit_wndw(state, interlock);
 
 	if (interlock[NV50_DISP_INTERLOCK_CORE]) {
 		if (interlock[NV50_DISP_INTERLOCK_BASE] ||
+		    interlock[NV50_DISP_INTERLOCK_OVLY] ||
+		    interlock[NV50_DISP_INTERLOCK_WNDW] ||
 		    !atom->state.legacy_cursor_update)
-			nv50_disp_atomic_commit_core(drm, interlock);
+			nv50_disp_atomic_commit_core(state, interlock);
 		else
 			disp->core->func->update(disp->core, interlock, false);
 	}
@@ -1871,7 +1878,7 @@ nv50_disp_atomic_commit(struct drm_device *dev,
 		nv50_disp_atomic_commit_tail(state);
 
 	drm_for_each_crtc(crtc, dev) {
-		if (crtc->state->enable) {
+		if (crtc->state->active) {
 			if (!drm->have_disp_power_ref) {
 				drm->have_disp_power_ref = true;
 				return 0;
@@ -2119,10 +2126,6 @@ nv50_display_destroy(struct drm_device *dev)
 	kfree(disp);
 }
 
-MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)");
-static int nouveau_atomic = 0;
-module_param_named(atomic, nouveau_atomic, int, 0400);
-
 int
 nv50_display_create(struct drm_device *dev)
 {
@@ -2147,8 +2150,6 @@ nv50_display_create(struct drm_device *dev)
 	disp->disp = &nouveau_display(dev)->disp;
 	dev->mode_config.funcs = &nv50_disp_func;
 	dev->driver->driver_features |= DRIVER_PREFER_XBGR_30BPP;
-	if (nouveau_atomic)
-		dev->driver->driver_features |= DRIVER_ATOMIC;
 
 	/* small shared memory area we use for notifiers and semaphores */
 	ret = nouveau_bo_new(&drm->client, 4096, 0x1000, TTM_PL_FLAG_VRAM,
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index debbbf0fd4bd..408b955e5c39 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -267,6 +267,7 @@ nouveau_backlight_init(struct drm_device *dev)
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvif_device *device = &drm->client.device;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
 
 	INIT_LIST_HEAD(&drm->bl_connectors);
 
@@ -275,7 +276,8 @@ nouveau_backlight_init(struct drm_device *dev)
 		return 0;
 	}
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
 		if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS &&
 		    connector->connector_type != DRM_MODE_CONNECTOR_eDP)
 			continue;
@@ -292,7 +294,7 @@ nouveau_backlight_init(struct drm_device *dev)
 			break;
 		}
 	}
-
+	drm_connector_list_iter_end(&conn_iter);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 7b557c354307..af68eae4c626 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -1208,14 +1208,19 @@ nouveau_connector_create(struct drm_device *dev, int index)
 	struct nouveau_display *disp = nouveau_display(dev);
 	struct nouveau_connector *nv_connector = NULL;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
 	int type, ret = 0;
 	bool dummy;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
 		nv_connector = nouveau_connector(connector);
-		if (nv_connector->index == index)
+		if (nv_connector->index == index) {
+			drm_connector_list_iter_end(&conn_iter);
 			return connector;
+		}
 	}
+	drm_connector_list_iter_end(&conn_iter);
 
 	nv_connector = kzalloc(sizeof(*nv_connector), GFP_KERNEL);
 	if (!nv_connector)
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index a4d1a059bd3d..dc7454e7f19a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -33,6 +33,7 @@
 #include <drm/drm_encoder.h>
 #include <drm/drm_dp_helper.h>
 #include "nouveau_crtc.h"
+#include "nouveau_encoder.h"
 
 struct nvkm_i2c_port;
 
@@ -60,19 +61,46 @@ static inline struct nouveau_connector *nouveau_connector(
 	return container_of(con, struct nouveau_connector, base);
 }
 
+static inline bool
+nouveau_connector_is_mst(struct drm_connector *connector)
+{
+	const struct nouveau_encoder *nv_encoder;
+	const struct drm_encoder *encoder;
+
+	if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort)
+		return false;
+
+	nv_encoder = find_encoder(connector, DCB_OUTPUT_ANY);
+	if (!nv_encoder)
+		return false;
+
+	encoder = &nv_encoder->base.base;
+	return encoder->encoder_type == DRM_MODE_ENCODER_DPMST;
+}
+
+#define nouveau_for_each_non_mst_connector_iter(connector, iter) \
+	drm_for_each_connector_iter(connector, iter) \
+		for_each_if(!nouveau_connector_is_mst(connector))
+
 static inline struct nouveau_connector *
 nouveau_crtc_connector_get(struct nouveau_crtc *nv_crtc)
 {
 	struct drm_device *dev = nv_crtc->base.dev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
+	struct nouveau_connector *nv_connector = NULL;
 	struct drm_crtc *crtc = to_drm_crtc(nv_crtc);
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		if (connector->encoder && connector->encoder->crtc == crtc)
-			return nouveau_connector(connector);
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
+		if (connector->encoder && connector->encoder->crtc == crtc) {
+			nv_connector = nouveau_connector(connector);
+			break;
+		}
 	}
+	drm_connector_list_iter_end(&conn_iter);
 
-	return NULL;
+	return nv_connector;
 }
 
 struct drm_connector *
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 774b429142bc..ec7861457b84 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -404,6 +404,7 @@ nouveau_display_init(struct drm_device *dev)
 	struct nouveau_display *disp = nouveau_display(dev);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
 	int ret;
 
 	ret = disp->init(dev);
@@ -411,10 +412,12 @@ nouveau_display_init(struct drm_device *dev)
 		return ret;
 
 	/* enable hotplug interrupts */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
 		struct nouveau_connector *conn = nouveau_connector(connector);
 		nvif_notify_get(&conn->hpd);
 	}
+	drm_connector_list_iter_end(&conn_iter);
 
 	/* enable flip completion events */
 	nvif_notify_get(&drm->flip);
@@ -427,6 +430,7 @@ nouveau_display_fini(struct drm_device *dev, bool suspend)
 	struct nouveau_display *disp = nouveau_display(dev);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
 
 	if (!suspend) {
 		if (drm_drv_uses_atomic_modeset(dev))
@@ -439,10 +443,12 @@ nouveau_display_fini(struct drm_device *dev, bool suspend)
 	nvif_notify_put(&drm->flip);
 
 	/* disable hotplug interrupts */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
 		struct nouveau_connector *conn = nouveau_connector(connector);
 		nvif_notify_put(&conn->hpd);
 	}
+	drm_connector_list_iter_end(&conn_iter);
 
 	drm_kms_helper_poll_disable(dev);
 	disp->fini(dev);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 775443c9af94..f5d3158f0378 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -81,6 +81,10 @@ MODULE_PARM_DESC(modeset, "enable driver (default: auto, "
 int nouveau_modeset = -1;
 module_param_named(modeset, nouveau_modeset, int, 0400);
 
+MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)");
+static int nouveau_atomic = 0;
+module_param_named(atomic, nouveau_atomic, int, 0400);
+
 MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1)");
 static int nouveau_runtime_pm = -1;
 module_param_named(runpm, nouveau_runtime_pm, int, 0400);
@@ -509,6 +513,9 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
+	if (nouveau_atomic)
+		driver_pci.driver_features |= DRIVER_ATOMIC;
+
 	ret = drm_get_pci_dev(pdev, pent, &driver_pci);
 	if (ret) {
 		nvkm_device_del(&device);
@@ -874,22 +881,11 @@ nouveau_pmops_runtime_resume(struct device *dev)
 static int
 nouveau_pmops_runtime_idle(struct device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct drm_device *drm_dev = pci_get_drvdata(pdev);
-	struct nouveau_drm *drm = nouveau_drm(drm_dev);
-	struct drm_crtc *crtc;
-
 	if (!nouveau_pmops_runtime()) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 
-	list_for_each_entry(crtc, &drm->dev->mode_config.crtc_list, head) {
-		if (crtc->enabled) {
-			DRM_DEBUG_DRIVER("failing to power off - crtc active\n");
-			return -EBUSY;
-		}
-	}
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_autosuspend(dev);
 	/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 300daee74209..e6ccafcb9c41 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -616,7 +616,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 		struct nouveau_bo *nvbo;
 		uint32_t data;
 
-		if (unlikely(r->bo_index > req->nr_buffers)) {
+		if (unlikely(r->bo_index >= req->nr_buffers)) {
 			NV_PRINTK(err, cli, "reloc bo index invalid\n");
 			ret = -EINVAL;
 			break;
@@ -626,7 +626,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 		if (b->presumed.valid)
 			continue;
 
-		if (unlikely(r->reloc_bo_index > req->nr_buffers)) {
+		if (unlikely(r->reloc_bo_index >= req->nr_buffers)) {
 			NV_PRINTK(err, cli, "reloc container bo index invalid\n");
 			ret = -EINVAL;
 			break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
index 73b5d46104bd..434d2fc5bb1c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
@@ -140,6 +140,9 @@ nvkm_fb_init(struct nvkm_subdev *subdev)
 	if (fb->func->init)
 		fb->func->init(fb);
 
+	if (fb->func->init_remapper)
+		fb->func->init_remapper(fb);
+
 	if (fb->func->init_page) {
 		ret = fb->func->init_page(fb);
 		if (WARN_ON(ret))
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
index dffe1f5e1071..8205ce436b3e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
@@ -37,6 +37,14 @@ gp100_fb_init_unkn(struct nvkm_fb *base)
 }
 
 void
+gp100_fb_init_remapper(struct nvkm_fb *fb)
+{
+	struct nvkm_device *device = fb->subdev.device;
+	/* Disable address remapper. */
+	nvkm_mask(device, 0x100c14, 0x00040000, 0x00000000);
+}
+
+void
 gp100_fb_init(struct nvkm_fb *base)
 {
 	struct gf100_fb *fb = gf100_fb(base);
@@ -56,6 +64,7 @@ gp100_fb = {
 	.dtor = gf100_fb_dtor,
 	.oneinit = gf100_fb_oneinit,
 	.init = gp100_fb_init,
+	.init_remapper = gp100_fb_init_remapper,
 	.init_page = gm200_fb_init_page,
 	.init_unkn = gp100_fb_init_unkn,
 	.ram_new = gp100_ram_new,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c
index b84b9861ef26..b4d74e815674 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c
@@ -31,6 +31,7 @@ gp102_fb = {
 	.dtor = gf100_fb_dtor,
 	.oneinit = gf100_fb_oneinit,
 	.init = gp100_fb_init,
+	.init_remapper = gp100_fb_init_remapper,
 	.init_page = gm200_fb_init_page,
 	.ram_new = gp100_ram_new,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
index 2857f31466bf..1e4ad61c19e1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
@@ -11,6 +11,7 @@ struct nvkm_fb_func {
 	u32 (*tags)(struct nvkm_fb *);
 	int (*oneinit)(struct nvkm_fb *);
 	void (*init)(struct nvkm_fb *);
+	void (*init_remapper)(struct nvkm_fb *);
 	int (*init_page)(struct nvkm_fb *);
 	void (*init_unkn)(struct nvkm_fb *);
 	void (*intr)(struct nvkm_fb *);
@@ -69,5 +70,6 @@ int gf100_fb_init_page(struct nvkm_fb *);
 
 int gm200_fb_init_page(struct nvkm_fb *);
 
+void gp100_fb_init_remapper(struct nvkm_fb *);
 void gp100_fb_init_unkn(struct nvkm_fb *);
 #endif
diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile
index 2589f4acd5ae..9c81301d0eed 100644
--- a/drivers/gpu/drm/sun4i/Makefile
+++ b/drivers/gpu/drm/sun4i/Makefile
@@ -32,7 +32,10 @@ obj-$(CONFIG_DRM_SUN4I)		+= sun4i-tcon.o
 obj-$(CONFIG_DRM_SUN4I)		+= sun4i_tv.o
 obj-$(CONFIG_DRM_SUN4I)		+= sun6i_drc.o
 
-obj-$(CONFIG_DRM_SUN4I_BACKEND)	+= sun4i-backend.o sun4i-frontend.o
+obj-$(CONFIG_DRM_SUN4I_BACKEND)	+= sun4i-backend.o
+ifdef CONFIG_DRM_SUN4I_BACKEND
+obj-$(CONFIG_DRM_SUN4I)		+= sun4i-frontend.o
+endif
 obj-$(CONFIG_DRM_SUN4I_HDMI)	+= sun4i-drm-hdmi.o
 obj-$(CONFIG_DRM_SUN6I_DSI)	+= sun6i-dsi.o
 obj-$(CONFIG_DRM_SUN8I_DW_HDMI)	+= sun8i-drm-hdmi.o
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index c3afe7b2237e..965088afcfad 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -2312,7 +2312,7 @@ static int tegra_dc_couple(struct tegra_dc *dc)
 	 * POWER_CONTROL registers during CRTC enabling.
 	 */
 	if (dc->soc->coupled_pm && dc->pipe == 1) {
-		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE;
+		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER;
 		struct device_link *link;
 		struct device *partner;
 
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 776c1513e582..a2bd5876c633 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -398,7 +398,7 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		 * unaligned offset is malformed and cause commands stream
 		 * corruption on the buffer address relocation.
 		 */
-		if (offset & 3 || offset >= obj->gem.size) {
+		if (offset & 3 || offset > obj->gem.size) {
 			err = -EINVAL;
 			goto fail;
 		}
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index 2ebdc6d5a76e..d5583190f3e4 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -137,7 +137,10 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 
 	if (cmd > (char *) urb->transfer_buffer) {
 		/* Send partial buffer remaining before exiting */
-		int len = cmd - (char *) urb->transfer_buffer;
+		int len;
+		if (cmd < (char *) urb->transfer_buffer + urb->transfer_buffer_length)
+			*cmd++ = 0xAF;
+		len = cmd - (char *) urb->transfer_buffer;
 		ret = udl_submit_urb(dev, urb, len);
 		bytes_sent += len;
 	} else
diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c
index 0c87b1ac6b68..b992644c17e6 100644
--- a/drivers/gpu/drm/udl/udl_transfer.c
+++ b/drivers/gpu/drm/udl/udl_transfer.c
@@ -153,11 +153,11 @@ static void udl_compress_hline16(
 		raw_pixels_count_byte = cmd++; /*  we'll know this later */
 		raw_pixel_start = pixel;
 
-		cmd_pixel_end = pixel + (min(MAX_CMD_PIXELS + 1,
-			min((int)(pixel_end - pixel) / bpp,
-			    (int)(cmd_buffer_end - cmd) / 2))) * bpp;
+		cmd_pixel_end = pixel + min3(MAX_CMD_PIXELS + 1UL,
+					(unsigned long)(pixel_end - pixel) / bpp,
+					(unsigned long)(cmd_buffer_end - 1 - cmd) / 2) * bpp;
 
-		prefetch_range((void *) pixel, (cmd_pixel_end - pixel) * bpp);
+		prefetch_range((void *) pixel, cmd_pixel_end - pixel);
 		pixel_val16 = get_pixel_val16(pixel, bpp);
 
 		while (pixel < cmd_pixel_end) {
@@ -193,6 +193,9 @@ static void udl_compress_hline16(
 		if (pixel > raw_pixel_start) {
 			/* finalize last RAW span */
 			*raw_pixels_count_byte = ((pixel-raw_pixel_start) / bpp) & 0xFF;
+		} else {
+			/* undo unused byte */
+			cmd--;
 		}
 
 		*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) / bpp) & 0xFF;
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 1d34619eb3fe..a951ec75d01f 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -320,6 +320,9 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state)
 			vc4_state->x_scaling[0] = VC4_SCALING_TPZ;
 		if (vc4_state->y_scaling[0] == VC4_SCALING_NONE)
 			vc4_state->y_scaling[0] = VC4_SCALING_TPZ;
+	} else {
+		vc4_state->x_scaling[1] = VC4_SCALING_NONE;
+		vc4_state->y_scaling[1] = VC4_SCALING_NONE;
 	}
 
 	vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE &&
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index f1d5f76e9c33..d88073e7d22d 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -218,6 +218,9 @@ static int host1x_probe(struct platform_device *pdev)
 		return err;
 	}
 
+	if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL))
+		goto skip_iommu;
+
 	host->group = iommu_group_get(&pdev->dev);
 	if (host->group) {
 		struct iommu_domain_geometry *geometry;
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index e2f4a4d93d20..527a1cddb14f 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -569,7 +569,8 @@ void host1x_job_unpin(struct host1x_job *job)
 	for (i = 0; i < job->num_unpins; i++) {
 		struct host1x_job_unpin_data *unpin = &job->unpins[i];
 
-		if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && host->domain) {
+		if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) &&
+		    unpin->size && host->domain) {
 			iommu_unmap(host->domain, job->addr_phys[i],
 				    unpin->size);
 			free_iova(&host->iova,
diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c
index caa05b0702e1..5450a2db1219 100644
--- a/drivers/gpu/ipu-v3/ipu-csi.c
+++ b/drivers/gpu/ipu-v3/ipu-csi.c
@@ -339,7 +339,8 @@ static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
 		break;
 	case V4L2_MBUS_BT656:
 		csicfg->ext_vsync = 0;
-		if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field))
+		if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field) ||
+		    mbus_fmt->field == V4L2_FIELD_ALTERNATE)
 			csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_INTERLACED;
 		else
 			csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE;
diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c
index 0f70e8847540..2f8db9d62551 100644
--- a/drivers/gpu/ipu-v3/ipu-pre.c
+++ b/drivers/gpu/ipu-v3/ipu-pre.c
@@ -128,7 +128,8 @@ ipu_pre_lookup_by_phandle(struct device *dev, const char *name, int index)
 	list_for_each_entry(pre, &ipu_pre_list, list) {
 		if (pre_node == pre->dev->of_node) {
 			mutex_unlock(&ipu_pre_list_mutex);
-			device_link_add(dev, pre->dev, DL_FLAG_AUTOREMOVE);
+			device_link_add(dev, pre->dev,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
 			of_node_put(pre_node);
 			return pre;
 		}
diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c
index 83f9dd934a5d..38a3a9764e49 100644
--- a/drivers/gpu/ipu-v3/ipu-prg.c
+++ b/drivers/gpu/ipu-v3/ipu-prg.c
@@ -100,7 +100,8 @@ ipu_prg_lookup_by_phandle(struct device *dev, const char *name, int ipu_id)
 	list_for_each_entry(prg, &ipu_prg_list, list) {
 		if (prg_node == prg->dev->of_node) {
 			mutex_unlock(&ipu_prg_list_mutex);
-			device_link_add(dev, prg->dev, DL_FLAG_AUTOREMOVE);
+			device_link_add(dev, prg->dev,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
 			prg->id = ipu_id;
 			of_node_put(prg_node);
 			return prg;
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index fc4adf3d34e8..a96bf46bc483 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -103,9 +103,11 @@
  *	runtime pm. If true, writing ON and OFF to the vga_switcheroo debugfs
  *	interface is a no-op so as not to interfere with runtime pm
  * @list: client list
+ * @vga_dev: pci device, indicate which GPU is bound to current audio client
  *
  * Registered client. A client can be either a GPU or an audio device on a GPU.
- * For audio clients, the @fb_info and @active members are bogus.
+ * For audio clients, the @fb_info and @active members are bogus. For GPU
+ * clients, the @vga_dev is bogus.
  */
 struct vga_switcheroo_client {
 	struct pci_dev *pdev;
@@ -116,6 +118,7 @@ struct vga_switcheroo_client {
 	bool active;
 	bool driver_power_control;
 	struct list_head list;
+	struct pci_dev *vga_dev;
 };
 
 /*
@@ -161,9 +164,8 @@ struct vgasr_priv {
 };
 
 #define ID_BIT_AUDIO		0x100
-#define client_is_audio(c)	((c)->id & ID_BIT_AUDIO)
-#define client_is_vga(c)	((c)->id == VGA_SWITCHEROO_UNKNOWN_ID || \
-				 !client_is_audio(c))
+#define client_is_audio(c)		((c)->id & ID_BIT_AUDIO)
+#define client_is_vga(c)		(!client_is_audio(c))
 #define client_id(c)		((c)->id & ~ID_BIT_AUDIO)
 
 static int vga_switcheroo_debugfs_init(struct vgasr_priv *priv);
@@ -192,14 +194,29 @@ static void vga_switcheroo_enable(void)
 		vgasr_priv.handler->init();
 
 	list_for_each_entry(client, &vgasr_priv.clients, list) {
-		if (client->id != VGA_SWITCHEROO_UNKNOWN_ID)
+		if (!client_is_vga(client) ||
+		     client_id(client) != VGA_SWITCHEROO_UNKNOWN_ID)
 			continue;
+
 		ret = vgasr_priv.handler->get_client_id(client->pdev);
 		if (ret < 0)
 			return;
 
 		client->id = ret;
 	}
+
+	list_for_each_entry(client, &vgasr_priv.clients, list) {
+		if (!client_is_audio(client) ||
+		     client_id(client) != VGA_SWITCHEROO_UNKNOWN_ID)
+			continue;
+
+		ret = vgasr_priv.handler->get_client_id(client->vga_dev);
+		if (ret < 0)
+			return;
+
+		client->id = ret | ID_BIT_AUDIO;
+	}
+
 	vga_switcheroo_debugfs_init(&vgasr_priv);
 	vgasr_priv.active = true;
 }
@@ -272,7 +289,9 @@ EXPORT_SYMBOL(vga_switcheroo_handler_flags);
 
 static int register_client(struct pci_dev *pdev,
 			   const struct vga_switcheroo_client_ops *ops,
-			   enum vga_switcheroo_client_id id, bool active,
+			   enum vga_switcheroo_client_id id,
+			   struct pci_dev *vga_dev,
+			   bool active,
 			   bool driver_power_control)
 {
 	struct vga_switcheroo_client *client;
@@ -287,6 +306,7 @@ static int register_client(struct pci_dev *pdev,
 	client->id = id;
 	client->active = active;
 	client->driver_power_control = driver_power_control;
+	client->vga_dev = vga_dev;
 
 	mutex_lock(&vgasr_mutex);
 	list_add_tail(&client->list, &vgasr_priv.clients);
@@ -319,7 +339,7 @@ int vga_switcheroo_register_client(struct pci_dev *pdev,
 				   const struct vga_switcheroo_client_ops *ops,
 				   bool driver_power_control)
 {
-	return register_client(pdev, ops, VGA_SWITCHEROO_UNKNOWN_ID,
+	return register_client(pdev, ops, VGA_SWITCHEROO_UNKNOWN_ID, NULL,
 			       pdev == vga_default_device(),
 			       driver_power_control);
 }
@@ -329,19 +349,40 @@ EXPORT_SYMBOL(vga_switcheroo_register_client);
  * vga_switcheroo_register_audio_client - register audio client
  * @pdev: client pci device
  * @ops: client callbacks
- * @id: client identifier
+ * @vga_dev:  pci device which is bound to current audio client
  *
  * Register audio client (audio device on a GPU). The client is assumed
  * to use runtime PM. Beforehand, vga_switcheroo_client_probe_defer()
  * shall be called to ensure that all prerequisites are met.
  *
- * Return: 0 on success, -ENOMEM on memory allocation error.
+ * Return: 0 on success, -ENOMEM on memory allocation error, -EINVAL on getting
+ * client id error.
  */
 int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 			const struct vga_switcheroo_client_ops *ops,
-			enum vga_switcheroo_client_id id)
+			struct pci_dev *vga_dev)
 {
-	return register_client(pdev, ops, id | ID_BIT_AUDIO, false, true);
+	enum vga_switcheroo_client_id id = VGA_SWITCHEROO_UNKNOWN_ID;
+
+	/*
+	 * if vga_switcheroo has enabled, that mean two GPU clients and also
+	 * handler are registered. Get audio client id from bound GPU client
+	 * id directly, otherwise, set it as VGA_SWITCHEROO_UNKNOWN_ID,
+	 * it will set to correct id in later when vga_switcheroo_enable()
+	 * is called.
+	 */
+	mutex_lock(&vgasr_mutex);
+	if (vgasr_priv.active) {
+		id = vgasr_priv.handler->get_client_id(vga_dev);
+		if (id < 0) {
+			mutex_unlock(&vgasr_mutex);
+			return -EINVAL;
+		}
+	}
+	mutex_unlock(&vgasr_mutex);
+
+	return register_client(pdev, ops, id | ID_BIT_AUDIO, vga_dev,
+			       false, true);
 }
 EXPORT_SYMBOL(vga_switcheroo_register_audio_client);
 
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index f858cc72011d..3942ee61bd1c 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1952,6 +1952,8 @@ static int hid_device_probe(struct device *dev)
 	}
 	hdev->io_started = false;
 
+	clear_bit(ffs(HID_STAT_REPROBED), &hdev->status);
+
 	if (!hdev->driver) {
 		id = hid_match_device(hdev, hdrv);
 		if (id == NULL) {
@@ -2215,7 +2217,8 @@ static int __hid_bus_reprobe_drivers(struct device *dev, void *data)
 	struct hid_device *hdev = to_hid_device(dev);
 
 	if (hdev->driver == hdrv &&
-	    !hdrv->match(hdev, hid_ignore_special_drivers))
+	    !hdrv->match(hdev, hid_ignore_special_drivers) &&
+	    !test_and_set_bit(ffs(HID_STAT_REPROBED), &hdev->status))
 		return device_reprobe(dev);
 
 	return 0;
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index 8469b6964ff6..b48100236df8 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -1154,6 +1154,8 @@ copy_rest:
 			goto out;
 		if (list->tail > list->head) {
 			len = list->tail - list->head;
+			if (len > count)
+				len = count;
 
 			if (copy_to_user(buffer + ret, &list->hid_debug_buf[list->head], len)) {
 				ret = -EFAULT;
@@ -1163,6 +1165,8 @@ copy_rest:
 			list->head += len;
 		} else {
 			len = HID_DEBUG_BUFSIZE - list->head;
+			if (len > count)
+				len = count;
 
 			if (copy_to_user(buffer, &list->hid_debug_buf[list->head], len)) {
 				ret = -EFAULT;
@@ -1170,7 +1174,9 @@ copy_rest:
 			}
 			list->head = 0;
 			ret += len;
-			goto copy_rest;
+			count -= len;
+			if (count > 0)
+				goto copy_rest;
 		}
 
 	}
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index c1652bb7bd15..eae0cb3ddec6 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -484,7 +484,7 @@ static void i2c_hid_get_input(struct i2c_hid *ihid)
 		return;
 	}
 
-	if ((ret_size > size) || (ret_size <= 2)) {
+	if ((ret_size > size) || (ret_size < 2)) {
 		dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n",
 			__func__, size, ret_size);
 		return;
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index e3ce233f8bdc..23872d08308c 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -36,6 +36,7 @@
 #include <linux/hiddev.h>
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
+#include <linux/nospec.h>
 #include "usbhid.h"
 
 #ifdef CONFIG_USB_DYNAMIC_MINORS
@@ -469,10 +470,14 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 
 		if (uref->field_index >= report->maxfield)
 			goto inval;
+		uref->field_index = array_index_nospec(uref->field_index,
+						       report->maxfield);
 
 		field = report->field[uref->field_index];
 		if (uref->usage_index >= field->maxusage)
 			goto inval;
+		uref->usage_index = array_index_nospec(uref->usage_index,
+						       field->maxusage);
 
 		uref->usage_code = field->usage[uref->usage_index].hid;
 
@@ -499,6 +504,8 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 
 			if (uref->field_index >= report->maxfield)
 				goto inval;
+			uref->field_index = array_index_nospec(uref->field_index,
+							       report->maxfield);
 
 			field = report->field[uref->field_index];
 
@@ -753,6 +760,8 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 		if (finfo.field_index >= report->maxfield)
 			break;
+		finfo.field_index = array_index_nospec(finfo.field_index,
+						       report->maxfield);
 
 		field = report->field[finfo.field_index];
 		memset(&finfo, 0, sizeof(finfo));
@@ -797,6 +806,8 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 		if (cinfo.index >= hid->maxcollection)
 			break;
+		cinfo.index = array_index_nospec(cinfo.index,
+						 hid->maxcollection);
 
 		cinfo.type = hid->collection[cinfo.index].type;
 		cinfo.usage = hid->collection[cinfo.index].usage;
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 0bb44d0088ed..ad7afa74d365 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -3365,8 +3365,14 @@ void wacom_setup_device_quirks(struct wacom *wacom)
 			if (features->type >= INTUOSHT && features->type <= BAMBOO_PT)
 				features->device_type |= WACOM_DEVICETYPE_PAD;
 
-			features->x_max = 4096;
-			features->y_max = 4096;
+			if (features->type == INTUOSHT2) {
+				features->x_max = features->x_max / 10;
+				features->y_max = features->y_max / 10;
+			}
+			else {
+				features->x_max = 4096;
+				features->y_max = 4096;
+			}
 		}
 		else if (features->pktlen == WACOM_PKGLEN_BBTOUCH) {
 			features->device_type |= WACOM_DEVICETYPE_PAD;
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index f10840ad465c..ccf42663a908 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -937,6 +937,18 @@ config SENSORS_MCP3021
 	  This driver can also be built as a module.  If so, the module
 	  will be called mcp3021.
 
+config SENSORS_MLXREG_FAN
+	tristate "Mellanox Mellanox FAN driver"
+	depends on MELLANOX_PLATFORM
+	imply THERMAL
+	select REGMAP
+	help
+	  This option enables support for the FAN control on the Mellanox
+	  Ethernet and InfiniBand switches. The driver can be activated by the
+	  platform device add call. Say Y to enable these. To compile this
+	  driver as a module, choose 'M' here: the module will be called
+	  mlxreg-fan.
+
 config SENSORS_TC654
 	tristate "Microchip TC654/TC655 and compatibles"
 	depends on I2C
@@ -1256,6 +1268,16 @@ config SENSORS_NCT7904
 	  This driver can also be built as a module.  If so, the module
 	  will be called nct7904.
 
+config SENSORS_NPCM7XX
+	tristate "Nuvoton NPCM750 and compatible PWM and Fan controllers"
+	imply THERMAL
+	help
+	  This driver provides support for Nuvoton NPCM750/730/715/705 PWM
+          and Fan controllers.
+
+          This driver can also be built as a module. If so, the module
+          will be called npcm750-pwm-fan.
+
 config SENSORS_NSA320
 	tristate "ZyXEL NSA320 and compatible fan speed and temperature sensors"
 	depends on GPIOLIB && OF
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index e7d52a36e6c4..842c92f83ce6 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -129,11 +129,13 @@ obj-$(CONFIG_SENSORS_MAX31790)	+= max31790.o
 obj-$(CONFIG_SENSORS_MC13783_ADC)+= mc13783-adc.o
 obj-$(CONFIG_SENSORS_MCP3021)	+= mcp3021.o
 obj-$(CONFIG_SENSORS_TC654)	+= tc654.o
+obj-$(CONFIG_SENSORS_MLXREG_FAN) += mlxreg-fan.o
 obj-$(CONFIG_SENSORS_MENF21BMC_HWMON) += menf21bmc_hwmon.o
 obj-$(CONFIG_SENSORS_NCT6683)	+= nct6683.o
 obj-$(CONFIG_SENSORS_NCT6775)	+= nct6775.o
 obj-$(CONFIG_SENSORS_NCT7802)	+= nct7802.o
 obj-$(CONFIG_SENSORS_NCT7904)	+= nct7904.o
+obj-$(CONFIG_SENSORS_NPCM7XX)	+= npcm750-pwm-fan.o
 obj-$(CONFIG_SENSORS_NSA320)	+= nsa320-hwmon.o
 obj-$(CONFIG_SENSORS_NTC_THERMISTOR)	+= ntc_thermistor.o
 obj-$(CONFIG_SENSORS_PC87360)	+= pc87360.o
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index 9ef84998c7f3..90837f7c7d0f 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -194,8 +194,7 @@ struct adt7475_data {
 	struct mutex lock;
 
 	unsigned long measure_updated;
-	unsigned long limits_updated;
-	char valid;
+	bool valid;
 
 	u8 config4;
 	u8 config5;
@@ -326,6 +325,9 @@ static ssize_t show_voltage(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	unsigned short val;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	switch (sattr->nr) {
 	case ALARM:
 		return sprintf(buf, "%d\n",
@@ -381,6 +383,9 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	switch (sattr->nr) {
 	case HYSTERSIS:
 		mutex_lock(&data->lock);
@@ -625,6 +630,9 @@ static ssize_t show_point2(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out, val;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	mutex_lock(&data->lock);
 	out = (data->range[sattr->index] >> 4) & 0x0F;
 	val = reg2temp(data, data->temp[AUTOMIN][sattr->index]);
@@ -683,6 +691,9 @@ static ssize_t show_tach(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	if (sattr->nr == ALARM)
 		out = (data->alarms >> (sattr->index + 10)) & 1;
 	else
@@ -720,6 +731,9 @@ static ssize_t show_pwm(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwm[sattr->nr][sattr->index]);
 }
 
@@ -729,6 +743,9 @@ static ssize_t show_pwmchan(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwmchan[sattr->index]);
 }
 
@@ -738,6 +755,9 @@ static ssize_t show_pwmctrl(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwmctl[sattr->index]);
 }
 
@@ -945,6 +965,9 @@ static ssize_t show_pwmfreq(struct device *dev, struct device_attribute *attr,
 	int i = clamp_val(data->range[sattr->index] & 0xf, 0,
 			  ARRAY_SIZE(pwmfreq_table) - 1);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", pwmfreq_table[i]);
 }
 
@@ -1035,6 +1058,10 @@ static ssize_t cpu0_vid_show(struct device *dev,
 			     struct device_attribute *devattr, char *buf)
 {
 	struct adt7475_data *data = adt7475_update_device(dev);
+
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
 
@@ -1385,6 +1412,121 @@ static void adt7475_remove_files(struct i2c_client *client,
 		sysfs_remove_group(&client->dev.kobj, &vid_attr_group);
 }
 
+static int adt7475_update_limits(struct i2c_client *client)
+{
+	struct adt7475_data *data = i2c_get_clientdata(client);
+	int i;
+	int ret;
+
+	ret = adt7475_read(REG_CONFIG4);
+	if (ret < 0)
+		return ret;
+	data->config4 = ret;
+
+	ret = adt7475_read(REG_CONFIG5);
+	if (ret < 0)
+		return ret;
+	data->config5 = ret;
+
+	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+		if (!(data->has_voltage & (1 << i)))
+			continue;
+		/* Adjust values so they match the input precision */
+		ret = adt7475_read(VOLTAGE_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[MIN][i] = ret << 2;
+
+		ret = adt7475_read(VOLTAGE_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[MAX][i] = ret << 2;
+	}
+
+	if (data->has_voltage & (1 << 5)) {
+		ret = adt7475_read(REG_VTT_MIN);
+		if (ret < 0)
+			return ret;
+		data->voltage[MIN][5] = ret << 2;
+
+		ret = adt7475_read(REG_VTT_MAX);
+		if (ret < 0)
+			return ret;
+		data->voltage[MAX][5] = ret << 2;
+	}
+
+	for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+		/* Adjust values so they match the input precision */
+		ret = adt7475_read(TEMP_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[MIN][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[MAX][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_TMIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[AUTOMIN][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_THERM_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[THERM][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_OFFSET_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[OFFSET][i] = ret;
+	}
+	adt7475_read_hystersis(client);
+
+	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+		if (i == 3 && !data->has_fan4)
+			continue;
+		ret = adt7475_read_word(client, TACH_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->tach[MIN][i] = ret;
+	}
+
+	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+		if (i == 1 && !data->has_pwm2)
+			continue;
+		ret = adt7475_read(PWM_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[MAX][i] = ret;
+
+		ret = adt7475_read(PWM_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[MIN][i] = ret;
+		/* Set the channel and control information */
+		adt7475_read_pwm(client, i);
+	}
+
+	ret = adt7475_read(TEMP_TRANGE_REG(0));
+	if (ret < 0)
+		return ret;
+	data->range[0] = ret;
+
+	ret = adt7475_read(TEMP_TRANGE_REG(1));
+	if (ret < 0)
+		return ret;
+	data->range[1] = ret;
+
+	ret = adt7475_read(TEMP_TRANGE_REG(2));
+	if (ret < 0)
+		return ret;
+	data->range[2] = ret;
+
+	return 0;
+}
+
 static int adt7475_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
@@ -1562,6 +1704,11 @@ static int adt7475_probe(struct i2c_client *client,
 			 (data->bypass_attn & (1 << 3)) ? " in3" : "",
 			 (data->bypass_attn & (1 << 4)) ? " in4" : "");
 
+	/* Limits and settings, should never change update more than once */
+	ret = adt7475_update_limits(client);
+	if (ret)
+		goto eremove;
+
 	return 0;
 
 eremove:
@@ -1658,121 +1805,122 @@ static void adt7475_read_pwm(struct i2c_client *client, int index)
 	}
 }
 
-static struct adt7475_data *adt7475_update_device(struct device *dev)
+static int adt7475_update_measure(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adt7475_data *data = i2c_get_clientdata(client);
 	u16 ext;
 	int i;
+	int ret;
 
-	mutex_lock(&data->lock);
+	ret = adt7475_read(REG_STATUS2);
+	if (ret < 0)
+		return ret;
+	data->alarms = ret << 8;
 
-	/* Measurement values update every 2 seconds */
-	if (time_after(jiffies, data->measure_updated + HZ * 2) ||
-	    !data->valid) {
-		data->alarms = adt7475_read(REG_STATUS2) << 8;
-		data->alarms |= adt7475_read(REG_STATUS1);
-
-		ext = (adt7475_read(REG_EXTEND2) << 8) |
-			adt7475_read(REG_EXTEND1);
-		for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
-			if (!(data->has_voltage & (1 << i)))
-				continue;
-			data->voltage[INPUT][i] =
-				(adt7475_read(VOLTAGE_REG(i)) << 2) |
-				((ext >> (i * 2)) & 3);
-		}
+	ret = adt7475_read(REG_STATUS1);
+	if (ret < 0)
+		return ret;
+	data->alarms |= ret;
 
-		for (i = 0; i < ADT7475_TEMP_COUNT; i++)
-			data->temp[INPUT][i] =
-				(adt7475_read(TEMP_REG(i)) << 2) |
-				((ext >> ((i + 5) * 2)) & 3);
+	ret = adt7475_read(REG_EXTEND2);
+	if (ret < 0)
+		return ret;
 
-		if (data->has_voltage & (1 << 5)) {
-			data->alarms |= adt7475_read(REG_STATUS4) << 24;
-			ext = adt7475_read(REG_EXTEND3);
-			data->voltage[INPUT][5] = adt7475_read(REG_VTT) << 2 |
-				((ext >> 4) & 3);
-		}
+	ext = (ret << 8);
 
-		for (i = 0; i < ADT7475_TACH_COUNT; i++) {
-			if (i == 3 && !data->has_fan4)
-				continue;
-			data->tach[INPUT][i] =
-				adt7475_read_word(client, TACH_REG(i));
-		}
+	ret = adt7475_read(REG_EXTEND1);
+	if (ret < 0)
+		return ret;
 
-		/* Updated by hw when in auto mode */
-		for (i = 0; i < ADT7475_PWM_COUNT; i++) {
-			if (i == 1 && !data->has_pwm2)
-				continue;
-			data->pwm[INPUT][i] = adt7475_read(PWM_REG(i));
-		}
+	ext |= ret;
+
+	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+		if (!(data->has_voltage & (1 << i)))
+			continue;
+		ret = adt7475_read(VOLTAGE_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[INPUT][i] =
+			(ret << 2) |
+			((ext >> (i * 2)) & 3);
+	}
 
-		if (data->has_vid)
-			data->vid = adt7475_read(REG_VID) & 0x3f;
+	for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+		ret = adt7475_read(TEMP_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[INPUT][i] =
+			(ret << 2) |
+			((ext >> ((i + 5) * 2)) & 3);
+	}
 
-		data->measure_updated = jiffies;
+	if (data->has_voltage & (1 << 5)) {
+		ret = adt7475_read(REG_STATUS4);
+		if (ret < 0)
+			return ret;
+		data->alarms |= ret << 24;
+
+		ret = adt7475_read(REG_EXTEND3);
+		if (ret < 0)
+			return ret;
+		ext = ret;
+
+		ret = adt7475_read(REG_VTT);
+		if (ret < 0)
+			return ret;
+		data->voltage[INPUT][5] = ret << 2 |
+			((ext >> 4) & 3);
 	}
 
-	/* Limits and settings, should never change update every 60 seconds */
-	if (time_after(jiffies, data->limits_updated + HZ * 60) ||
-	    !data->valid) {
-		data->config4 = adt7475_read(REG_CONFIG4);
-		data->config5 = adt7475_read(REG_CONFIG5);
-
-		for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
-			if (!(data->has_voltage & (1 << i)))
-				continue;
-			/* Adjust values so they match the input precision */
-			data->voltage[MIN][i] =
-				adt7475_read(VOLTAGE_MIN_REG(i)) << 2;
-			data->voltage[MAX][i] =
-				adt7475_read(VOLTAGE_MAX_REG(i)) << 2;
-		}
+	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+		if (i == 3 && !data->has_fan4)
+			continue;
+		ret = adt7475_read_word(client, TACH_REG(i));
+		if (ret < 0)
+			return ret;
+		data->tach[INPUT][i] = ret;
+	}
 
-		if (data->has_voltage & (1 << 5)) {
-			data->voltage[MIN][5] = adt7475_read(REG_VTT_MIN) << 2;
-			data->voltage[MAX][5] = adt7475_read(REG_VTT_MAX) << 2;
-		}
+	/* Updated by hw when in auto mode */
+	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+		if (i == 1 && !data->has_pwm2)
+			continue;
+		ret = adt7475_read(PWM_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[INPUT][i] = ret;
+	}
 
-		for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
-			/* Adjust values so they match the input precision */
-			data->temp[MIN][i] =
-				adt7475_read(TEMP_MIN_REG(i)) << 2;
-			data->temp[MAX][i] =
-				adt7475_read(TEMP_MAX_REG(i)) << 2;
-			data->temp[AUTOMIN][i] =
-				adt7475_read(TEMP_TMIN_REG(i)) << 2;
-			data->temp[THERM][i] =
-				adt7475_read(TEMP_THERM_REG(i)) << 2;
-			data->temp[OFFSET][i] =
-				adt7475_read(TEMP_OFFSET_REG(i));
-		}
-		adt7475_read_hystersis(client);
+	if (data->has_vid) {
+		ret = adt7475_read(REG_VID);
+		if (ret < 0)
+			return ret;
+		data->vid = ret & 0x3f;
+	}
 
-		for (i = 0; i < ADT7475_TACH_COUNT; i++) {
-			if (i == 3 && !data->has_fan4)
-				continue;
-			data->tach[MIN][i] =
-				adt7475_read_word(client, TACH_MIN_REG(i));
-		}
+	return 0;
+}
 
-		for (i = 0; i < ADT7475_PWM_COUNT; i++) {
-			if (i == 1 && !data->has_pwm2)
-				continue;
-			data->pwm[MAX][i] = adt7475_read(PWM_MAX_REG(i));
-			data->pwm[MIN][i] = adt7475_read(PWM_MIN_REG(i));
-			/* Set the channel and control information */
-			adt7475_read_pwm(client, i);
-		}
+static struct adt7475_data *adt7475_update_device(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct adt7475_data *data = i2c_get_clientdata(client);
+	int ret;
 
-		data->range[0] = adt7475_read(TEMP_TRANGE_REG(0));
-		data->range[1] = adt7475_read(TEMP_TRANGE_REG(1));
-		data->range[2] = adt7475_read(TEMP_TRANGE_REG(2));
+	mutex_lock(&data->lock);
 
-		data->limits_updated = jiffies;
-		data->valid = 1;
+	/* Measurement values update every 2 seconds */
+	if (time_after(jiffies, data->measure_updated + HZ * 2) ||
+	    !data->valid) {
+		ret = adt7475_update_measure(dev);
+		if (ret) {
+			data->valid = false;
+			mutex_unlock(&data->lock);
+			return ERR_PTR(ret);
+		}
+		data->measure_updated = jiffies;
+		data->valid = true;
 	}
 
 	mutex_unlock(&data->lock);
diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c
index 1ea7ca510f84..aaebeb726d6a 100644
--- a/drivers/hwmon/emc1403.c
+++ b/drivers/hwmon/emc1403.c
@@ -443,8 +443,10 @@ static int emc1403_probe(struct i2c_client *client,
 	switch (id->driver_data) {
 	case emc1404:
 		data->groups[2] = &emc1404_group;
+		/* fall through */
 	case emc1403:
 		data->groups[1] = &emc1403_group;
+		/* fall through */
 	case emc1402:
 		data->groups[0] = &emc1402_group;
 	}
diff --git a/drivers/hwmon/iio_hwmon.c b/drivers/hwmon/iio_hwmon.c
index 69031a0f7ed2..2f3f875c06ac 100644
--- a/drivers/hwmon/iio_hwmon.c
+++ b/drivers/hwmon/iio_hwmon.c
@@ -22,7 +22,6 @@
  * struct iio_hwmon_state - device instance state
  * @channels:		filled with array of channels from iio
  * @num_channels:	number of channels in channels (saves counting twice)
- * @hwmon_dev:		associated hwmon device
  * @attr_group:		the group of attributes
  * @groups:		null terminated array of attribute groups
  * @attrs:		null terminated array of attribute pointers.
@@ -30,7 +29,6 @@
 struct iio_hwmon_state {
 	struct iio_channel *channels;
 	int num_channels;
-	struct device *hwmon_dev;
 	struct attribute_group attr_group;
 	const struct attribute_group *groups[2];
 	struct attribute **attrs;
@@ -68,12 +66,13 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	enum iio_chan_type type;
 	struct iio_channel *channels;
 	const char *name = "iio_hwmon";
+	struct device *hwmon_dev;
 	char *sname;
 
 	if (dev->of_node && dev->of_node->name)
 		name = dev->of_node->name;
 
-	channels = iio_channel_get_all(dev);
+	channels = devm_iio_channel_get_all(dev);
 	if (IS_ERR(channels)) {
 		if (PTR_ERR(channels) == -ENODEV)
 			return -EPROBE_DEFER;
@@ -81,10 +80,8 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	}
 
 	st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL);
-	if (st == NULL) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (st == NULL)
+		return -ENOMEM;
 
 	st->channels = channels;
 
@@ -95,22 +92,18 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	st->attrs = devm_kcalloc(dev,
 				 st->num_channels + 1, sizeof(*st->attrs),
 				 GFP_KERNEL);
-	if (st->attrs == NULL) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (st->attrs == NULL)
+		return -ENOMEM;
 
 	for (i = 0; i < st->num_channels; i++) {
 		a = devm_kzalloc(dev, sizeof(*a), GFP_KERNEL);
-		if (a == NULL) {
-			ret = -ENOMEM;
-			goto error_release_channels;
-		}
+		if (a == NULL)
+			return -ENOMEM;
 
 		sysfs_attr_init(&a->dev_attr.attr);
 		ret = iio_get_channel_type(&st->channels[i], &type);
 		if (ret < 0)
-			goto error_release_channels;
+			return ret;
 
 		switch (type) {
 		case IIO_VOLTAGE:
@@ -134,13 +127,11 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 							       humidity_i++);
 			break;
 		default:
-			ret = -EINVAL;
-			goto error_release_channels;
-		}
-		if (a->dev_attr.attr.name == NULL) {
-			ret = -ENOMEM;
-			goto error_release_channels;
+			return -EINVAL;
 		}
+		if (a->dev_attr.attr.name == NULL)
+			return -ENOMEM;
+
 		a->dev_attr.show = iio_hwmon_read_val;
 		a->dev_attr.attr.mode = S_IRUGO;
 		a->index = i;
@@ -151,34 +142,13 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	st->groups[0] = &st->attr_group;
 
 	sname = devm_kstrdup(dev, name, GFP_KERNEL);
-	if (!sname) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (!sname)
+		return -ENOMEM;
 
 	strreplace(sname, '-', '_');
-	st->hwmon_dev = hwmon_device_register_with_groups(dev, sname, st,
-							  st->groups);
-	if (IS_ERR(st->hwmon_dev)) {
-		ret = PTR_ERR(st->hwmon_dev);
-		goto error_release_channels;
-	}
-	platform_set_drvdata(pdev, st);
-	return 0;
-
-error_release_channels:
-	iio_channel_release_all(channels);
-	return ret;
-}
-
-static int iio_hwmon_remove(struct platform_device *pdev)
-{
-	struct iio_hwmon_state *st = platform_get_drvdata(pdev);
-
-	hwmon_device_unregister(st->hwmon_dev);
-	iio_channel_release_all(st->channels);
-
-	return 0;
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, sname, st,
+							   st->groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static const struct of_device_id iio_hwmon_of_match[] = {
@@ -193,7 +163,6 @@ static struct platform_driver __refdata iio_hwmon_driver = {
 		.of_match_table = iio_hwmon_of_match,
 	},
 	.probe = iio_hwmon_probe,
-	.remove = iio_hwmon_remove,
 };
 
 module_platform_driver(iio_hwmon_driver);
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 17c6460ae351..bb15d7816a29 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -99,12 +99,8 @@ static const struct tctl_offset tctl_offset_table[] = {
 	{ 0x17, "AMD Ryzen 7 1700X", 20000 },
 	{ 0x17, "AMD Ryzen 7 1800X", 20000 },
 	{ 0x17, "AMD Ryzen 7 2700X", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1950X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1920X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1900X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1950", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1920", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1910", 10000 },
+	{ 0x17, "AMD Ryzen Threadripper 19", 27000 }, /* 19{00,20,50}X */
+	{ 0x17, "AMD Ryzen Threadripper 29", 27000 }, /* 29{20,50,70,90}[W]X */
 };
 
 static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c
new file mode 100644
index 000000000000..de46577c7d5a
--- /dev/null
+++ b/drivers/hwmon/mlxreg-fan.c
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+//
+// Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+// Copyright (c) 2018 Vadim Pasternak <vadimp@mellanox.com>
+
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/module.h>
+#include <linux/platform_data/mlxreg.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/thermal.h>
+
+#define MLXREG_FAN_MAX_TACHO		12
+#define MLXREG_FAN_MAX_STATE		10
+#define MLXREG_FAN_MIN_DUTY		51	/* 20% */
+#define MLXREG_FAN_MAX_DUTY		255	/* 100% */
+/*
+ * Minimum and maximum FAN allowed speed in percent: from 20% to 100%. Values
+ * MLXREG_FAN_MAX_STATE + x, where x is between 2 and 10 are used for
+ * setting FAN speed dynamic minimum. For example, if value is set to 14 (40%)
+ * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to
+ * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100.
+ */
+#define MLXREG_FAN_SPEED_MIN			(MLXREG_FAN_MAX_STATE + 2)
+#define MLXREG_FAN_SPEED_MAX			(MLXREG_FAN_MAX_STATE * 2)
+#define MLXREG_FAN_SPEED_MIN_LEVEL		2	/* 20 percent */
+#define MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF	44
+#define MLXREG_FAN_TACHO_DIVIDER_DEF		1132
+/*
+ * FAN datasheet defines the formula for RPM calculations as RPM = 15/t-high.
+ * The logic in a programmable device measures the time t-high by sampling the
+ * tachometer every t-sample (with the default value 11.32 uS) and increment
+ * a counter (N) as long as the pulse has not change:
+ * RPM = 15 / (t-sample * (K + Regval)), where:
+ * Regval: is the value read from the programmable device register;
+ *  - 0xff - represents tachometer fault;
+ *  - 0xfe - represents tachometer minimum value , which is 4444 RPM;
+ *  - 0x00 - represents tachometer maximum value , which is 300000 RPM;
+ * K: is 44 and it represents the minimum allowed samples per pulse;
+ * N: is equal K + Regval;
+ * In order to calculate RPM from the register value the following formula is
+ * used: RPM = 15 / ((Regval + K) * 11.32) * 10^(-6)), which in  the
+ * default case is modified to:
+ * RPM = 15000000 * 100 / ((Regval + 44) * 1132);
+ * - for Regval 0x00, RPM will be 15000000 * 100 / (44 * 1132) = 30115;
+ * - for Regval 0xfe, RPM will be 15000000 * 100 / ((254 + 44) * 1132) = 4446;
+ * In common case the formula is modified to:
+ * RPM = 15000000 * 100 / ((Regval + samples) * divider).
+ */
+#define MLXREG_FAN_GET_RPM(rval, d, s)	(DIV_ROUND_CLOSEST(15000000 * 100, \
+					 ((rval) + (s)) * (d)))
+#define MLXREG_FAN_GET_FAULT(val, mask) (!!((val) ^ (mask)))
+#define MLXREG_FAN_PWM_DUTY2STATE(duty)	(DIV_ROUND_CLOSEST((duty) *	\
+					 MLXREG_FAN_MAX_STATE,		\
+					 MLXREG_FAN_MAX_DUTY))
+#define MLXREG_FAN_PWM_STATE2DUTY(stat)	(DIV_ROUND_CLOSEST((stat) *	\
+					 MLXREG_FAN_MAX_DUTY,		\
+					 MLXREG_FAN_MAX_STATE))
+
+/*
+ * struct mlxreg_fan_tacho - tachometer data (internal use):
+ *
+ * @connected: indicates if tachometer is connected;
+ * @reg: register offset;
+ * @mask: fault mask;
+ */
+struct mlxreg_fan_tacho {
+	bool connected;
+	u32 reg;
+	u32 mask;
+};
+
+/*
+ * struct mlxreg_fan_pwm - PWM data (internal use):
+ *
+ * @connected: indicates if PWM is connected;
+ * @reg: register offset;
+ */
+struct mlxreg_fan_pwm {
+	bool connected;
+	u32 reg;
+};
+
+/*
+ * struct mlxreg_fan - private data (internal use):
+ *
+ * @dev: basic device;
+ * @regmap: register map of parent device;
+ * @tacho: tachometer data;
+ * @pwm: PWM data;
+ * @samples: minimum allowed samples per pulse;
+ * @divider: divider value for tachometer RPM calculation;
+ * @cooling: cooling device levels;
+ * @cdev: cooling device;
+ */
+struct mlxreg_fan {
+	struct device *dev;
+	void *regmap;
+	struct mlxreg_core_platform_data *pdata;
+	struct mlxreg_fan_tacho tacho[MLXREG_FAN_MAX_TACHO];
+	struct mlxreg_fan_pwm pwm;
+	int samples;
+	int divider;
+	u8 cooling_levels[MLXREG_FAN_MAX_STATE + 1];
+	struct thermal_cooling_device *cdev;
+};
+
+static int
+mlxreg_fan_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+		int channel, long *val)
+{
+	struct mlxreg_fan *fan = dev_get_drvdata(dev);
+	struct mlxreg_fan_tacho *tacho;
+	u32 regval;
+	int err;
+
+	switch (type) {
+	case hwmon_fan:
+		tacho = &fan->tacho[channel];
+		switch (attr) {
+		case hwmon_fan_input:
+			err = regmap_read(fan->regmap, tacho->reg, &regval);
+			if (err)
+				return err;
+
+			*val = MLXREG_FAN_GET_RPM(regval, fan->divider,
+						  fan->samples);
+			break;
+
+		case hwmon_fan_fault:
+			err = regmap_read(fan->regmap, tacho->reg, &regval);
+			if (err)
+				return err;
+
+			*val = MLXREG_FAN_GET_FAULT(regval, tacho->mask);
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+			if (err)
+				return err;
+
+			*val = regval;
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+mlxreg_fan_write(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+		 int channel, long val)
+{
+	struct mlxreg_fan *fan = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			if (val < MLXREG_FAN_MIN_DUTY ||
+			    val > MLXREG_FAN_MAX_DUTY)
+				return -EINVAL;
+			return regmap_write(fan->regmap, fan->pwm.reg, val);
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static umode_t
+mlxreg_fan_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
+		      int channel)
+{
+	switch (type) {
+	case hwmon_fan:
+		if (!(((struct mlxreg_fan *)data)->tacho[channel].connected))
+			return 0;
+
+		switch (attr) {
+		case hwmon_fan_input:
+		case hwmon_fan_fault:
+			return 0444;
+		default:
+			break;
+		}
+		break;
+
+	case hwmon_pwm:
+		if (!(((struct mlxreg_fan *)data)->pwm.connected))
+			return 0;
+
+		switch (attr) {
+		case hwmon_pwm_input:
+			return 0644;
+		default:
+			break;
+		}
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const u32 mlxreg_fan_hwmon_fan_config[] = {
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_fan = {
+	.type = hwmon_fan,
+	.config = mlxreg_fan_hwmon_fan_config,
+};
+
+static const u32 mlxreg_fan_hwmon_pwm_config[] = {
+	HWMON_PWM_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_pwm = {
+	.type = hwmon_pwm,
+	.config = mlxreg_fan_hwmon_pwm_config,
+};
+
+static const struct hwmon_channel_info *mlxreg_fan_hwmon_info[] = {
+	&mlxreg_fan_hwmon_fan,
+	&mlxreg_fan_hwmon_pwm,
+	NULL
+};
+
+static const struct hwmon_ops mlxreg_fan_hwmon_hwmon_ops = {
+	.is_visible = mlxreg_fan_is_visible,
+	.read = mlxreg_fan_read,
+	.write = mlxreg_fan_write,
+};
+
+static const struct hwmon_chip_info mlxreg_fan_hwmon_chip_info = {
+	.ops = &mlxreg_fan_hwmon_hwmon_ops,
+	.info = mlxreg_fan_hwmon_info,
+};
+
+static int mlxreg_fan_get_max_state(struct thermal_cooling_device *cdev,
+				    unsigned long *state)
+{
+	*state = MLXREG_FAN_MAX_STATE;
+	return 0;
+}
+
+static int mlxreg_fan_get_cur_state(struct thermal_cooling_device *cdev,
+				    unsigned long *state)
+
+{
+	struct mlxreg_fan *fan = cdev->devdata;
+	u32 regval;
+	int err;
+
+	err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+	if (err) {
+		dev_err(fan->dev, "Failed to query PWM duty\n");
+		return err;
+	}
+
+	*state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+
+	return 0;
+}
+
+static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev,
+				    unsigned long state)
+
+{
+	struct mlxreg_fan *fan = cdev->devdata;
+	unsigned long cur_state;
+	u32 regval;
+	int i;
+	int err;
+
+	/*
+	 * Verify if this request is for changing allowed FAN dynamical
+	 * minimum. If it is - update cooling levels accordingly and update
+	 * state, if current state is below the newly requested minimum state.
+	 * For example, if current state is 5, and minimal state is to be
+	 * changed from 4 to 6, fan->cooling_levels[0 to 5] will be changed all
+	 * from 4 to 6. And state 5 (fan->cooling_levels[4]) should be
+	 * overwritten.
+	 */
+	if (state >= MLXREG_FAN_SPEED_MIN && state <= MLXREG_FAN_SPEED_MAX) {
+		state -= MLXREG_FAN_MAX_STATE;
+		for (i = 0; i < state; i++)
+			fan->cooling_levels[i] = state;
+		for (i = state; i <= MLXREG_FAN_MAX_STATE; i++)
+			fan->cooling_levels[i] = i;
+
+		err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+		if (err) {
+			dev_err(fan->dev, "Failed to query PWM duty\n");
+			return err;
+		}
+
+		cur_state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+		if (state < cur_state)
+			return 0;
+
+		state = cur_state;
+	}
+
+	if (state > MLXREG_FAN_MAX_STATE)
+		return -EINVAL;
+
+	/* Normalize the state to the valid speed range. */
+	state = fan->cooling_levels[state];
+	err = regmap_write(fan->regmap, fan->pwm.reg,
+			   MLXREG_FAN_PWM_STATE2DUTY(state));
+	if (err) {
+		dev_err(fan->dev, "Failed to write PWM duty\n");
+		return err;
+	}
+	return 0;
+}
+
+static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = {
+	.get_max_state	= mlxreg_fan_get_max_state,
+	.get_cur_state	= mlxreg_fan_get_cur_state,
+	.set_cur_state	= mlxreg_fan_set_cur_state,
+};
+
+static int mlxreg_fan_config(struct mlxreg_fan *fan,
+			     struct mlxreg_core_platform_data *pdata)
+{
+	struct mlxreg_core_data *data = pdata->data;
+	bool configured = false;
+	int tacho_num = 0, i;
+
+	fan->samples = MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF;
+	fan->divider = MLXREG_FAN_TACHO_DIVIDER_DEF;
+	for (i = 0; i < pdata->counter; i++, data++) {
+		if (strnstr(data->label, "tacho", sizeof(data->label))) {
+			if (tacho_num == MLXREG_FAN_MAX_TACHO) {
+				dev_err(fan->dev, "too many tacho entries: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->tacho[tacho_num].reg = data->reg;
+			fan->tacho[tacho_num].mask = data->mask;
+			fan->tacho[tacho_num++].connected = true;
+		} else if (strnstr(data->label, "pwm", sizeof(data->label))) {
+			if (fan->pwm.connected) {
+				dev_err(fan->dev, "duplicate pwm entry: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->pwm.reg = data->reg;
+			fan->pwm.connected = true;
+		} else if (strnstr(data->label, "conf", sizeof(data->label))) {
+			if (configured) {
+				dev_err(fan->dev, "duplicate conf entry: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			/* Validate that conf parameters are not zeros. */
+			if (!data->mask || !data->bit) {
+				dev_err(fan->dev, "invalid conf entry params: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->samples = data->mask;
+			fan->divider = data->bit;
+			configured = true;
+		} else {
+			dev_err(fan->dev, "invalid label: %s\n", data->label);
+			return -EINVAL;
+		}
+	}
+
+	/* Init cooling levels per PWM state. */
+	for (i = 0; i < MLXREG_FAN_SPEED_MIN_LEVEL; i++)
+		fan->cooling_levels[i] = MLXREG_FAN_SPEED_MIN_LEVEL;
+	for (i = MLXREG_FAN_SPEED_MIN_LEVEL; i <= MLXREG_FAN_MAX_STATE; i++)
+		fan->cooling_levels[i] = i;
+
+	return 0;
+}
+
+static int mlxreg_fan_probe(struct platform_device *pdev)
+{
+	struct mlxreg_core_platform_data *pdata;
+	struct mlxreg_fan *fan;
+	struct device *hwm;
+	int err;
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata) {
+		dev_err(&pdev->dev, "Failed to get platform data.\n");
+		return -EINVAL;
+	}
+
+	fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL);
+	if (!fan)
+		return -ENOMEM;
+
+	fan->dev = &pdev->dev;
+	fan->regmap = pdata->regmap;
+	platform_set_drvdata(pdev, fan);
+
+	err = mlxreg_fan_config(fan, pdata);
+	if (err)
+		return err;
+
+	hwm = devm_hwmon_device_register_with_info(&pdev->dev, "mlxreg_fan",
+						   fan,
+						   &mlxreg_fan_hwmon_chip_info,
+						   NULL);
+	if (IS_ERR(hwm)) {
+		dev_err(&pdev->dev, "Failed to register hwmon device\n");
+		return PTR_ERR(hwm);
+	}
+
+	if (IS_REACHABLE(CONFIG_THERMAL)) {
+		fan->cdev = thermal_cooling_device_register("mlxreg_fan", fan,
+						&mlxreg_fan_cooling_ops);
+		if (IS_ERR(fan->cdev)) {
+			dev_err(&pdev->dev, "Failed to register cooling device\n");
+			return PTR_ERR(fan->cdev);
+		}
+	}
+
+	return 0;
+}
+
+static int mlxreg_fan_remove(struct platform_device *pdev)
+{
+	struct mlxreg_fan *fan = platform_get_drvdata(pdev);
+
+	if (IS_REACHABLE(CONFIG_THERMAL))
+		thermal_cooling_device_unregister(fan->cdev);
+
+	return 0;
+}
+
+static struct platform_driver mlxreg_fan_driver = {
+	.driver = {
+	    .name = "mlxreg-fan",
+	},
+	.probe = mlxreg_fan_probe,
+	.remove = mlxreg_fan_remove,
+};
+
+module_platform_driver(mlxreg_fan_driver);
+
+MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox FAN driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mlxreg-fan");
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index f9d1349c3286..c6bd61e4695a 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -1050,8 +1050,8 @@ struct nct6775_data {
 	u64 beeps;
 
 	u8 pwm_num;	/* number of pwm */
-	u8 pwm_mode[NUM_FAN];	/* 1->DC variable voltage,
-				 * 0->PWM variable duty cycle
+	u8 pwm_mode[NUM_FAN];	/* 0->DC variable voltage,
+				 * 1->PWM variable duty cycle
 				 */
 	enum pwm_enable pwm_enable[NUM_FAN];
 			/* 0->off
@@ -2541,7 +2541,7 @@ static void pwm_update_registers(struct nct6775_data *data, int nr)
 	case thermal_cruise:
 		nct6775_write_value(data, data->REG_TARGET[nr],
 				    data->target_temp[nr]);
-		/* intentional */
+		/* fall through  */
 	default:
 		reg = nct6775_read_value(data, data->REG_FAN_MODE[nr]);
 		reg = (reg & ~data->tolerance_mask) |
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index 95a68ab175c7..7815ddf149f6 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -77,7 +77,7 @@ struct nct7904_data {
 };
 
 /* Access functions */
-static int nct7904_bank_lock(struct nct7904_data *data, unsigned bank)
+static int nct7904_bank_lock(struct nct7904_data *data, unsigned int bank)
 {
 	int ret;
 
@@ -99,7 +99,7 @@ static inline void nct7904_bank_release(struct nct7904_data *data)
 
 /* Read 1-byte register. Returns unsigned reg or -ERRNO on error. */
 static int nct7904_read_reg(struct nct7904_data *data,
-			    unsigned bank, unsigned reg)
+			    unsigned int bank, unsigned int reg)
 {
 	struct i2c_client *client = data->client;
 	int ret;
@@ -117,7 +117,7 @@ static int nct7904_read_reg(struct nct7904_data *data,
  * -ERRNO on error.
  */
 static int nct7904_read_reg16(struct nct7904_data *data,
-			      unsigned bank, unsigned reg)
+			      unsigned int bank, unsigned int reg)
 {
 	struct i2c_client *client = data->client;
 	int ret, hi;
@@ -139,7 +139,7 @@ static int nct7904_read_reg16(struct nct7904_data *data,
 
 /* Write 1-byte register. Returns 0 or -ERRNO on error. */
 static int nct7904_write_reg(struct nct7904_data *data,
-			     unsigned bank, unsigned reg, u8 val)
+			     unsigned int bank, unsigned int reg, u8 val)
 {
 	struct i2c_client *client = data->client;
 	int ret;
@@ -159,7 +159,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel,
 	unsigned int cnt, rpm;
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_fan_input:
 		ret = nct7904_read_reg16(data, BANK_0,
 					 FANIN1_HV_REG + channel * 2);
@@ -200,7 +200,7 @@ static int nct7904_read_in(struct device *dev, u32 attr, int channel,
 
 	index = nct7904_chan_to_index[channel];
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_in_input:
 		ret = nct7904_read_reg16(data, BANK_0,
 					 VSEN1_HV_REG + index * 2);
@@ -236,7 +236,7 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret, temp;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_temp_input:
 		if (channel == 0)
 			ret = nct7904_read_reg16(data, BANK_0, LTD_HV_REG);
@@ -276,7 +276,7 @@ static int nct7904_read_pwm(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 		ret = nct7904_read_reg(data, BANK_3, FANCTL1_OUT_REG + channel);
 		if (ret < 0)
@@ -301,7 +301,7 @@ static int nct7904_write_pwm(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 		if (val < 0 || val > 255)
 			return -EINVAL;
@@ -322,7 +322,7 @@ static int nct7904_write_pwm(struct device *dev, u32 attr, int channel,
 
 static umode_t nct7904_pwm_is_visible(const void *_data, u32 attr, int channel)
 {
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 	case hwmon_pwm_enable:
 		return S_IRUGO | S_IWUSR;
@@ -431,15 +431,15 @@ static const struct hwmon_channel_info nct7904_in = {
 };
 
 static const u32 nct7904_fan_config[] = {
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-	    0
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_fan = {
@@ -448,11 +448,11 @@ static const struct hwmon_channel_info nct7904_fan = {
 };
 
 static const u32 nct7904_pwm_config[] = {
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	    0
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_pwm = {
@@ -461,16 +461,16 @@ static const struct hwmon_channel_info nct7904_pwm = {
 };
 
 static const u32 nct7904_temp_config[] = {
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-	    0
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_temp = {
diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c
new file mode 100644
index 000000000000..8474d601aa63
--- /dev/null
+++ b/drivers/hwmon/npcm750-pwm-fan.c
@@ -0,0 +1,1057 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2014-2018 Nuvoton Technology corporation.
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
+#include <linux/thermal.h>
+
+/* NPCM7XX PWM registers */
+#define NPCM7XX_PWM_REG_BASE(base, n)    ((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_PWM_REG_PR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_PWM_REG_CSR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_PWM_REG_CR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_PWM_REG_CNRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x0C + (12 * (ch)))
+#define NPCM7XX_PWM_REG_CMRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x10 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PDRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x14 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PIER(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x3C)
+#define NPCM7XX_PWM_REG_PIIR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x40)
+
+#define NPCM7XX_PWM_CTRL_CH0_MODE_BIT		BIT(3)
+#define NPCM7XX_PWM_CTRL_CH1_MODE_BIT		BIT(11)
+#define NPCM7XX_PWM_CTRL_CH2_MODE_BIT		BIT(15)
+#define NPCM7XX_PWM_CTRL_CH3_MODE_BIT		BIT(19)
+
+#define NPCM7XX_PWM_CTRL_CH0_INV_BIT		BIT(2)
+#define NPCM7XX_PWM_CTRL_CH1_INV_BIT		BIT(10)
+#define NPCM7XX_PWM_CTRL_CH2_INV_BIT		BIT(14)
+#define NPCM7XX_PWM_CTRL_CH3_INV_BIT		BIT(18)
+
+#define NPCM7XX_PWM_CTRL_CH0_EN_BIT		BIT(0)
+#define NPCM7XX_PWM_CTRL_CH1_EN_BIT		BIT(8)
+#define NPCM7XX_PWM_CTRL_CH2_EN_BIT		BIT(12)
+#define NPCM7XX_PWM_CTRL_CH3_EN_BIT		BIT(16)
+
+/* Define the maximum PWM channel number */
+#define NPCM7XX_PWM_MAX_CHN_NUM			8
+#define NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE	4
+#define NPCM7XX_PWM_MAX_MODULES                 2
+
+/* Define the Counter Register, value = 100 for match 100% */
+#define NPCM7XX_PWM_COUNTER_DEFAULT_NUM		255
+#define NPCM7XX_PWM_CMR_DEFAULT_NUM		127
+#define NPCM7XX_PWM_CMR_MAX			255
+
+/* default all PWM channels PRESCALE2 = 1 */
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0	0x4
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1	0x40
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2	0x400
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3	0x4000
+
+#define PWM_OUTPUT_FREQ_25KHZ			25000
+#define PWN_CNT_DEFAULT				256
+#define MIN_PRESCALE1				2
+#define NPCM7XX_PWM_PRESCALE_SHIFT_CH01		8
+
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT	(NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3)
+
+#define NPCM7XX_PWM_CTRL_MODE_DEFAULT	(NPCM7XX_PWM_CTRL_CH0_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH1_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH2_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH3_MODE_BIT)
+
+/* NPCM7XX FAN Tacho registers */
+#define NPCM7XX_FAN_REG_BASE(base, n)	((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_FAN_REG_TCNT1(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_FAN_REG_TCRA(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x02)
+#define NPCM7XX_FAN_REG_TCRB(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_FAN_REG_TCNT2(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x06)
+#define NPCM7XX_FAN_REG_TPRSC(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_FAN_REG_TCKC(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x0A)
+#define NPCM7XX_FAN_REG_TMCTRL(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x0C)
+#define NPCM7XX_FAN_REG_TICTRL(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x0E)
+#define NPCM7XX_FAN_REG_TICLR(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x10)
+#define NPCM7XX_FAN_REG_TIEN(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x12)
+#define NPCM7XX_FAN_REG_TCPA(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x14)
+#define NPCM7XX_FAN_REG_TCPB(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x16)
+#define NPCM7XX_FAN_REG_TCPCFG(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x18)
+#define NPCM7XX_FAN_REG_TINASEL(base, n)  (NPCM7XX_FAN_REG_BASE(base, n) + 0x1A)
+#define NPCM7XX_FAN_REG_TINBSEL(base, n)  (NPCM7XX_FAN_REG_BASE(base, n) + 0x1C)
+
+#define NPCM7XX_FAN_TCKC_CLKX_NONE	0
+#define NPCM7XX_FAN_TCKC_CLK1_APB	BIT(0)
+#define NPCM7XX_FAN_TCKC_CLK2_APB	BIT(3)
+
+#define NPCM7XX_FAN_TMCTRL_TBEN		BIT(6)
+#define NPCM7XX_FAN_TMCTRL_TAEN		BIT(5)
+#define NPCM7XX_FAN_TMCTRL_TBEDG	BIT(4)
+#define NPCM7XX_FAN_TMCTRL_TAEDG	BIT(3)
+#define NPCM7XX_FAN_TMCTRL_MODE_5	BIT(2)
+
+#define NPCM7XX_FAN_TICLR_CLEAR_ALL	GENMASK(5, 0)
+#define NPCM7XX_FAN_TICLR_TFCLR		BIT(5)
+#define NPCM7XX_FAN_TICLR_TECLR		BIT(4)
+#define NPCM7XX_FAN_TICLR_TDCLR		BIT(3)
+#define NPCM7XX_FAN_TICLR_TCCLR		BIT(2)
+#define NPCM7XX_FAN_TICLR_TBCLR		BIT(1)
+#define NPCM7XX_FAN_TICLR_TACLR		BIT(0)
+
+#define NPCM7XX_FAN_TIEN_ENABLE_ALL	GENMASK(5, 0)
+#define NPCM7XX_FAN_TIEN_TFIEN		BIT(5)
+#define NPCM7XX_FAN_TIEN_TEIEN		BIT(4)
+#define NPCM7XX_FAN_TIEN_TDIEN		BIT(3)
+#define NPCM7XX_FAN_TIEN_TCIEN		BIT(2)
+#define NPCM7XX_FAN_TIEN_TBIEN		BIT(1)
+#define NPCM7XX_FAN_TIEN_TAIEN		BIT(0)
+
+#define NPCM7XX_FAN_TICTRL_TFPND	BIT(5)
+#define NPCM7XX_FAN_TICTRL_TEPND	BIT(4)
+#define NPCM7XX_FAN_TICTRL_TDPND	BIT(3)
+#define NPCM7XX_FAN_TICTRL_TCPND	BIT(2)
+#define NPCM7XX_FAN_TICTRL_TBPND	BIT(1)
+#define NPCM7XX_FAN_TICTRL_TAPND	BIT(0)
+
+#define NPCM7XX_FAN_TCPCFG_HIBEN	BIT(7)
+#define NPCM7XX_FAN_TCPCFG_EQBEN	BIT(6)
+#define NPCM7XX_FAN_TCPCFG_LOBEN	BIT(5)
+#define NPCM7XX_FAN_TCPCFG_CPBSEL	BIT(4)
+#define NPCM7XX_FAN_TCPCFG_HIAEN	BIT(3)
+#define NPCM7XX_FAN_TCPCFG_EQAEN	BIT(2)
+#define NPCM7XX_FAN_TCPCFG_LOAEN	BIT(1)
+#define NPCM7XX_FAN_TCPCFG_CPASEL	BIT(0)
+
+/* FAN General Definition */
+/* Define the maximum FAN channel number */
+#define NPCM7XX_FAN_MAX_MODULE			8
+#define NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE	2
+#define NPCM7XX_FAN_MAX_CHN_NUM			16
+
+/*
+ * Get Fan Tach Timeout (base on clock 214843.75Hz, 1 cnt = 4.654us)
+ * Timeout 94ms ~= 0x5000
+ * (The minimum FAN speed could to support ~640RPM/pulse 1,
+ * 320RPM/pulse 2, ...-- 10.6Hz)
+ */
+#define NPCM7XX_FAN_TIMEOUT	0x5000
+#define NPCM7XX_FAN_TCNT	0xFFFF
+#define NPCM7XX_FAN_TCPA	(NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+#define NPCM7XX_FAN_TCPB	(NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+
+#define NPCM7XX_FAN_POLL_TIMER_200MS			200
+#define NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION	2
+#define NPCM7XX_FAN_TINASEL_FANIN_DEFAULT		0
+#define NPCM7XX_FAN_CLK_PRESCALE			255
+
+#define NPCM7XX_FAN_CMPA				0
+#define NPCM7XX_FAN_CMPB				1
+
+/* Obtain the fan number */
+#define NPCM7XX_FAN_INPUT(fan, cmp)		(((fan) << 1) + (cmp))
+
+/* fan sample status */
+#define FAN_DISABLE				0xFF
+#define FAN_INIT				0x00
+#define FAN_PREPARE_TO_GET_FIRST_CAPTURE	0x01
+#define FAN_ENOUGH_SAMPLE			0x02
+
+struct npcm7xx_fan_dev {
+	u8 fan_st_flg;
+	u8 fan_pls_per_rev;
+	u16 fan_cnt;
+	u32 fan_cnt_tmp;
+};
+
+struct npcm7xx_cooling_device {
+	char name[THERMAL_NAME_LENGTH];
+	struct npcm7xx_pwm_fan_data *data;
+	struct thermal_cooling_device *tcdev;
+	int pwm_port;
+	u8 *cooling_levels;
+	u8 max_state;
+	u8 cur_state;
+};
+
+struct npcm7xx_pwm_fan_data {
+	void __iomem *pwm_base;
+	void __iomem *fan_base;
+	unsigned long pwm_clk_freq;
+	unsigned long fan_clk_freq;
+	struct clk *pwm_clk;
+	struct clk *fan_clk;
+	struct mutex pwm_lock[NPCM7XX_PWM_MAX_MODULES];
+	spinlock_t fan_lock[NPCM7XX_FAN_MAX_MODULE];
+	int fan_irq[NPCM7XX_FAN_MAX_MODULE];
+	bool pwm_present[NPCM7XX_PWM_MAX_CHN_NUM];
+	bool fan_present[NPCM7XX_FAN_MAX_CHN_NUM];
+	u32 input_clk_freq;
+	struct timer_list fan_timer;
+	struct npcm7xx_fan_dev fan_dev[NPCM7XX_FAN_MAX_CHN_NUM];
+	struct npcm7xx_cooling_device *cdev[NPCM7XX_PWM_MAX_CHN_NUM];
+	u8 fan_select;
+};
+
+static int npcm7xx_pwm_config_set(struct npcm7xx_pwm_fan_data *data,
+				  int channel, u16 val)
+{
+	u32 pwm_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 tmp_buf, ctrl_en_bit, env_bit;
+
+	/*
+	 * Config PWM Comparator register for setting duty cycle
+	 */
+	mutex_lock(&data->pwm_lock[module]);
+
+	/* write new CMR value  */
+	iowrite32(val, NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pwm_ch));
+	tmp_buf = ioread32(NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+
+	switch (pwm_ch) {
+	case 0:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH0_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH0_INV_BIT;
+		break;
+	case 1:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH1_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH1_INV_BIT;
+		break;
+	case 2:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH2_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH2_INV_BIT;
+		break;
+	case 3:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH3_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH3_INV_BIT;
+		break;
+	default:
+		mutex_unlock(&data->pwm_lock[module]);
+		return -ENODEV;
+	}
+
+	if (val == 0) {
+		/* Disable PWM */
+		tmp_buf &= ~ctrl_en_bit;
+		tmp_buf |= env_bit;
+	} else {
+		/* Enable PWM */
+		tmp_buf |= ctrl_en_bit;
+		tmp_buf &= ~env_bit;
+	}
+
+	iowrite32(tmp_buf, NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+	mutex_unlock(&data->pwm_lock[module]);
+
+	return 0;
+}
+
+static inline void npcm7xx_fan_start_capture(struct npcm7xx_pwm_fan_data *data,
+					     u8 fan, u8 cmp)
+{
+	u8 fan_id;
+	u8 reg_mode;
+	u8 reg_int;
+	unsigned long flags;
+
+	fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+	/* to check whether any fan tach is enable */
+	if (data->fan_dev[fan_id].fan_st_flg != FAN_DISABLE) {
+		/* reset status */
+		spin_lock_irqsave(&data->fan_lock[fan], flags);
+
+		data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+		reg_int = ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/*
+		 * the interrupt enable bits do not need to be cleared before
+		 * it sets, the interrupt enable bits are cleared only on reset.
+		 * the clock unit control register is behaving in the same
+		 * manner that the interrupt enable register behave.
+		 */
+		if (cmp == NPCM7XX_FAN_CMPA) {
+			/* enable interrupt */
+			iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TAIEN |
+					    NPCM7XX_FAN_TIEN_TEIEN),
+				 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+			reg_mode = NPCM7XX_FAN_TCKC_CLK1_APB
+				| ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+							       fan));
+
+			/* start to Capture */
+			iowrite8(reg_mode, NPCM7XX_FAN_REG_TCKC(data->fan_base,
+								fan));
+		} else {
+			/* enable interrupt */
+			iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TBIEN |
+					    NPCM7XX_FAN_TIEN_TFIEN),
+				 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+			reg_mode =
+				NPCM7XX_FAN_TCKC_CLK2_APB
+				| ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+							       fan));
+
+			/* start to Capture */
+			iowrite8(reg_mode,
+				 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+		}
+
+		spin_unlock_irqrestore(&data->fan_lock[fan], flags);
+	}
+}
+
+/*
+ * Enable a background timer to poll fan tach value, (200ms * 4)
+ * to polling all fan
+ */
+static void npcm7xx_fan_polling(struct timer_list *t)
+{
+	struct npcm7xx_pwm_fan_data *data;
+	int i;
+
+	data = from_timer(data, t, fan_timer);
+
+	/*
+	 * Polling two module per one round,
+	 * FAN01 & FAN89 / FAN23 & FAN1011 / FAN45 & FAN1213 / FAN67 & FAN1415
+	 */
+	for (i = data->fan_select; i < NPCM7XX_FAN_MAX_MODULE;
+	      i = i + 4) {
+		/* clear the flag and reset the counter (TCNT) */
+		iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, i));
+
+		if (data->fan_present[i * 2]) {
+			iowrite16(NPCM7XX_FAN_TCNT,
+				  NPCM7XX_FAN_REG_TCNT1(data->fan_base, i));
+			npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPA);
+		}
+		if (data->fan_present[(i * 2) + 1]) {
+			iowrite16(NPCM7XX_FAN_TCNT,
+				  NPCM7XX_FAN_REG_TCNT2(data->fan_base, i));
+			npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPB);
+		}
+	}
+
+	data->fan_select++;
+	data->fan_select &= 0x3;
+
+	/* reset the timer interval */
+	data->fan_timer.expires = jiffies +
+		msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+	add_timer(&data->fan_timer);
+}
+
+static inline void npcm7xx_fan_compute(struct npcm7xx_pwm_fan_data *data,
+				       u8 fan, u8 cmp, u8 fan_id, u8 flag_int,
+				       u8 flag_mode, u8 flag_clear)
+{
+	u8  reg_int;
+	u8  reg_mode;
+	u16 fan_cap;
+
+	if (cmp == NPCM7XX_FAN_CMPA)
+		fan_cap = ioread16(NPCM7XX_FAN_REG_TCRA(data->fan_base, fan));
+	else
+		fan_cap = ioread16(NPCM7XX_FAN_REG_TCRB(data->fan_base, fan));
+
+	/* clear capature flag, H/W will auto reset the NPCM7XX_FAN_TCNTx */
+	iowrite8(flag_clear, NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+	if (data->fan_dev[fan_id].fan_st_flg == FAN_INIT) {
+		/* First capture, drop it */
+		data->fan_dev[fan_id].fan_st_flg =
+			FAN_PREPARE_TO_GET_FIRST_CAPTURE;
+
+		/* reset counter */
+		data->fan_dev[fan_id].fan_cnt_tmp = 0;
+	} else if (data->fan_dev[fan_id].fan_st_flg < FAN_ENOUGH_SAMPLE) {
+		/*
+		 * collect the enough sample,
+		 * (ex: 2 pulse fan need to get 2 sample)
+		 */
+		data->fan_dev[fan_id].fan_cnt_tmp +=
+			(NPCM7XX_FAN_TCNT - fan_cap);
+
+		data->fan_dev[fan_id].fan_st_flg++;
+	} else {
+		/* get enough sample or fan disable */
+		if (data->fan_dev[fan_id].fan_st_flg == FAN_ENOUGH_SAMPLE) {
+			data->fan_dev[fan_id].fan_cnt_tmp +=
+				(NPCM7XX_FAN_TCNT - fan_cap);
+
+			/* compute finial average cnt per pulse */
+			data->fan_dev[fan_id].fan_cnt =
+				data->fan_dev[fan_id].fan_cnt_tmp /
+				FAN_ENOUGH_SAMPLE;
+
+			data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+		}
+
+		reg_int =  ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* disable interrupt */
+		iowrite8((reg_int & ~flag_int),
+			 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+		reg_mode =  ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/* stop capturing */
+		iowrite8((reg_mode & ~flag_mode),
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+	}
+}
+
+static inline void npcm7xx_check_cmp(struct npcm7xx_pwm_fan_data *data,
+				     u8 fan, u8 cmp, u8 flag)
+{
+	u8 reg_int;
+	u8 reg_mode;
+	u8 flag_timeout;
+	u8 flag_cap;
+	u8 flag_clear;
+	u8 flag_int;
+	u8 flag_mode;
+	u8 fan_id;
+
+	fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+	if (cmp == NPCM7XX_FAN_CMPA) {
+		flag_cap = NPCM7XX_FAN_TICTRL_TAPND;
+		flag_timeout = NPCM7XX_FAN_TICTRL_TEPND;
+		flag_int = NPCM7XX_FAN_TIEN_TAIEN | NPCM7XX_FAN_TIEN_TEIEN;
+		flag_mode = NPCM7XX_FAN_TCKC_CLK1_APB;
+		flag_clear = NPCM7XX_FAN_TICLR_TACLR | NPCM7XX_FAN_TICLR_TECLR;
+	} else {
+		flag_cap = NPCM7XX_FAN_TICTRL_TBPND;
+		flag_timeout = NPCM7XX_FAN_TICTRL_TFPND;
+		flag_int = NPCM7XX_FAN_TIEN_TBIEN | NPCM7XX_FAN_TIEN_TFIEN;
+		flag_mode = NPCM7XX_FAN_TCKC_CLK2_APB;
+		flag_clear = NPCM7XX_FAN_TICLR_TBCLR | NPCM7XX_FAN_TICLR_TFCLR;
+	}
+
+	if (flag & flag_timeout) {
+		reg_int =  ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* disable interrupt */
+		iowrite8((reg_int & ~flag_int),
+			 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* clear interrupt flag */
+		iowrite8(flag_clear,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+		reg_mode =  ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/* stop capturing */
+		iowrite8((reg_mode & ~flag_mode),
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/*
+		 *  If timeout occurs (NPCM7XX_FAN_TIMEOUT), the fan doesn't
+		 *  connect or speed is lower than 10.6Hz (320RPM/pulse2).
+		 *  In these situation, the RPM output should be zero.
+		 */
+		data->fan_dev[fan_id].fan_cnt = 0;
+	} else {
+	    /* input capture is occurred */
+		if (flag & flag_cap)
+			npcm7xx_fan_compute(data, fan, cmp, fan_id, flag_int,
+					    flag_mode, flag_clear);
+	}
+}
+
+static irqreturn_t npcm7xx_fan_isr(int irq, void *dev_id)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_id;
+	unsigned long flags;
+	int module;
+	u8 flag;
+
+	module = irq - data->fan_irq[0];
+	spin_lock_irqsave(&data->fan_lock[module], flags);
+
+	flag = ioread8(NPCM7XX_FAN_REG_TICTRL(data->fan_base, module));
+	if (flag > 0) {
+		npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPA, flag);
+		npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPB, flag);
+		spin_unlock_irqrestore(&data->fan_lock[module], flags);
+		return IRQ_HANDLED;
+	}
+
+	spin_unlock_irqrestore(&data->fan_lock[module], flags);
+
+	return IRQ_NONE;
+}
+
+static int npcm7xx_read_pwm(struct device *dev, u32 attr, int channel,
+			    long *val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+	u32 pmw_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		*val = ioread32
+			(NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pmw_ch));
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int npcm7xx_write_pwm(struct device *dev, u32 attr, int channel,
+			     long val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+	int err;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		if (val < 0 || val > NPCM7XX_PWM_CMR_MAX)
+			return -EINVAL;
+		err = npcm7xx_pwm_config_set(data, channel, (u16)val);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static umode_t npcm7xx_pwm_is_visible(const void *_data, u32 attr, int channel)
+{
+	const struct npcm7xx_pwm_fan_data *data = _data;
+
+	if (!data->pwm_present[channel])
+		return 0;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		return 0644;
+	default:
+		return 0;
+	}
+}
+
+static int npcm7xx_read_fan(struct device *dev, u32 attr, int channel,
+			    long *val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+
+	switch (attr) {
+	case hwmon_fan_input:
+		*val = 0;
+		if (data->fan_dev[channel].fan_cnt <= 0)
+			return data->fan_dev[channel].fan_cnt;
+
+		/* Convert the raw reading to RPM */
+		if (data->fan_dev[channel].fan_cnt > 0 &&
+		    data->fan_dev[channel].fan_pls_per_rev > 0)
+			*val = ((data->input_clk_freq * 60) /
+				(data->fan_dev[channel].fan_cnt *
+				 data->fan_dev[channel].fan_pls_per_rev));
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t npcm7xx_fan_is_visible(const void *_data, u32 attr, int channel)
+{
+	const struct npcm7xx_pwm_fan_data *data = _data;
+
+	if (!data->fan_present[channel])
+		return 0;
+
+	switch (attr) {
+	case hwmon_fan_input:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static int npcm7xx_read(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long *val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_read_pwm(dev, attr, channel, val);
+	case hwmon_fan:
+		return npcm7xx_read_fan(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int npcm7xx_write(struct device *dev, enum hwmon_sensor_types type,
+			 u32 attr, int channel, long val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_write_pwm(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t npcm7xx_is_visible(const void *data,
+				  enum hwmon_sensor_types type,
+				  u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_pwm_is_visible(data, attr, channel);
+	case hwmon_fan:
+		return npcm7xx_fan_is_visible(data, attr, channel);
+	default:
+		return 0;
+	}
+}
+
+static const u32 npcm7xx_pwm_config[] = {
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info npcm7xx_pwm = {
+	.type = hwmon_pwm,
+	.config = npcm7xx_pwm_config,
+};
+
+static const u32 npcm7xx_fan_config[] = {
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info npcm7xx_fan = {
+	.type = hwmon_fan,
+	.config = npcm7xx_fan_config,
+};
+
+static const struct hwmon_channel_info *npcm7xx_info[] = {
+	&npcm7xx_pwm,
+	&npcm7xx_fan,
+	NULL
+};
+
+static const struct hwmon_ops npcm7xx_hwmon_ops = {
+	.is_visible = npcm7xx_is_visible,
+	.read = npcm7xx_read,
+	.write = npcm7xx_write,
+};
+
+static const struct hwmon_chip_info npcm7xx_chip_info = {
+	.ops = &npcm7xx_hwmon_ops,
+	.info = npcm7xx_info,
+};
+
+static u32 npcm7xx_pwm_init(struct npcm7xx_pwm_fan_data *data)
+{
+	int m, ch;
+	u32 prescale_val, output_freq;
+
+	data->pwm_clk_freq = clk_get_rate(data->pwm_clk);
+
+	/* Adjust NPCM7xx PWMs output frequency to ~25Khz */
+	output_freq = data->pwm_clk_freq / PWN_CNT_DEFAULT;
+	prescale_val = DIV_ROUND_CLOSEST(output_freq, PWM_OUTPUT_FREQ_25KHZ);
+
+	/* If prescale_val = 0, then the prescale output clock is stopped */
+	if (prescale_val < MIN_PRESCALE1)
+		prescale_val = MIN_PRESCALE1;
+	/*
+	 * prescale_val need to decrement in one because in the PWM Prescale
+	 * register the Prescale value increment by one
+	 */
+	prescale_val--;
+
+	/* Setting PWM Prescale Register value register to both modules */
+	prescale_val |= (prescale_val << NPCM7XX_PWM_PRESCALE_SHIFT_CH01);
+
+	for (m = 0; m < NPCM7XX_PWM_MAX_MODULES  ; m++) {
+		iowrite32(prescale_val, NPCM7XX_PWM_REG_PR(data->pwm_base, m));
+		iowrite32(NPCM7XX_PWM_PRESCALE2_DEFAULT,
+			  NPCM7XX_PWM_REG_CSR(data->pwm_base, m));
+		iowrite32(NPCM7XX_PWM_CTRL_MODE_DEFAULT,
+			  NPCM7XX_PWM_REG_CR(data->pwm_base, m));
+
+		for (ch = 0; ch < NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE; ch++) {
+			iowrite32(NPCM7XX_PWM_COUNTER_DEFAULT_NUM,
+				  NPCM7XX_PWM_REG_CNRx(data->pwm_base, m, ch));
+		}
+	}
+
+	return output_freq / ((prescale_val & 0xf) + 1);
+}
+
+static void npcm7xx_fan_init(struct npcm7xx_pwm_fan_data *data)
+{
+	int md;
+	int ch;
+	int i;
+	u32 apb_clk_freq;
+
+	for (md = 0; md < NPCM7XX_FAN_MAX_MODULE; md++) {
+		/* stop FAN0~7 clock */
+		iowrite8(NPCM7XX_FAN_TCKC_CLKX_NONE,
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, md));
+
+		/* disable all interrupt */
+		iowrite8(0x00, NPCM7XX_FAN_REG_TIEN(data->fan_base, md));
+
+		/* clear all interrupt */
+		iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, md));
+
+		/* set FAN0~7 clock prescaler */
+		iowrite8(NPCM7XX_FAN_CLK_PRESCALE,
+			 NPCM7XX_FAN_REG_TPRSC(data->fan_base, md));
+
+		/* set FAN0~7 mode (high-to-low transition) */
+		iowrite8((NPCM7XX_FAN_TMCTRL_MODE_5 | NPCM7XX_FAN_TMCTRL_TBEN |
+			  NPCM7XX_FAN_TMCTRL_TAEN),
+			 NPCM7XX_FAN_REG_TMCTRL(data->fan_base, md));
+
+		/* set FAN0~7 Initial Count/Cap */
+		iowrite16(NPCM7XX_FAN_TCNT,
+			  NPCM7XX_FAN_REG_TCNT1(data->fan_base, md));
+		iowrite16(NPCM7XX_FAN_TCNT,
+			  NPCM7XX_FAN_REG_TCNT2(data->fan_base, md));
+
+		/* set FAN0~7 compare (equal to count) */
+		iowrite8((NPCM7XX_FAN_TCPCFG_EQAEN | NPCM7XX_FAN_TCPCFG_EQBEN),
+			 NPCM7XX_FAN_REG_TCPCFG(data->fan_base, md));
+
+		/* set FAN0~7 compare value */
+		iowrite16(NPCM7XX_FAN_TCPA,
+			  NPCM7XX_FAN_REG_TCPA(data->fan_base, md));
+		iowrite16(NPCM7XX_FAN_TCPB,
+			  NPCM7XX_FAN_REG_TCPB(data->fan_base, md));
+
+		/* set FAN0~7 fan input FANIN 0~15 */
+		iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+			 NPCM7XX_FAN_REG_TINASEL(data->fan_base, md));
+		iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+			 NPCM7XX_FAN_REG_TINBSEL(data->fan_base, md));
+
+		for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE; i++) {
+			ch = md * NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE + i;
+			data->fan_dev[ch].fan_st_flg = FAN_DISABLE;
+			data->fan_dev[ch].fan_pls_per_rev =
+				NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION;
+			data->fan_dev[ch].fan_cnt = 0;
+		}
+	}
+
+	apb_clk_freq = clk_get_rate(data->fan_clk);
+
+	/* Fan tach input clock = APB clock / prescalar, default is 255. */
+	data->input_clk_freq = apb_clk_freq / (NPCM7XX_FAN_CLK_PRESCALE + 1);
+}
+
+static int
+npcm7xx_pwm_cz_get_max_state(struct thermal_cooling_device *tcdev,
+			     unsigned long *state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+	*state = cdev->max_state;
+
+	return 0;
+}
+
+static int
+npcm7xx_pwm_cz_get_cur_state(struct thermal_cooling_device *tcdev,
+			     unsigned long *state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+	*state = cdev->cur_state;
+
+	return 0;
+}
+
+static int
+npcm7xx_pwm_cz_set_cur_state(struct thermal_cooling_device *tcdev,
+			     unsigned long state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+	int ret;
+
+	if (state > cdev->max_state)
+		return -EINVAL;
+
+	cdev->cur_state = state;
+	ret = npcm7xx_pwm_config_set(cdev->data, cdev->pwm_port,
+				     cdev->cooling_levels[cdev->cur_state]);
+
+	return ret;
+}
+
+static const struct thermal_cooling_device_ops npcm7xx_pwm_cool_ops = {
+	.get_max_state = npcm7xx_pwm_cz_get_max_state,
+	.get_cur_state = npcm7xx_pwm_cz_get_cur_state,
+	.set_cur_state = npcm7xx_pwm_cz_set_cur_state,
+};
+
+static int npcm7xx_create_pwm_cooling(struct device *dev,
+				      struct device_node *child,
+				      struct npcm7xx_pwm_fan_data *data,
+				      u32 pwm_port, u8 num_levels)
+{
+	int ret;
+	struct npcm7xx_cooling_device *cdev;
+
+	cdev = devm_kzalloc(dev, sizeof(*cdev), GFP_KERNEL);
+	if (!cdev)
+		return -ENOMEM;
+
+	cdev->cooling_levels = devm_kzalloc(dev, num_levels, GFP_KERNEL);
+	if (!cdev->cooling_levels)
+		return -ENOMEM;
+
+	cdev->max_state = num_levels - 1;
+	ret = of_property_read_u8_array(child, "cooling-levels",
+					cdev->cooling_levels,
+					num_levels);
+	if (ret) {
+		dev_err(dev, "Property 'cooling-levels' cannot be read.\n");
+		return ret;
+	}
+	snprintf(cdev->name, THERMAL_NAME_LENGTH, "%s%d", child->name,
+		 pwm_port);
+
+	cdev->tcdev = thermal_of_cooling_device_register(child,
+							 cdev->name,
+							 cdev,
+							 &npcm7xx_pwm_cool_ops);
+	if (IS_ERR(cdev->tcdev))
+		return PTR_ERR(cdev->tcdev);
+
+	cdev->data = data;
+	cdev->pwm_port = pwm_port;
+
+	data->cdev[pwm_port] = cdev;
+
+	return 0;
+}
+
+static int npcm7xx_en_pwm_fan(struct device *dev,
+			      struct device_node *child,
+			      struct npcm7xx_pwm_fan_data *data)
+{
+	u8 *fan_ch;
+	u32 pwm_port;
+	int ret, fan_cnt;
+	u8 index, ch;
+
+	ret = of_property_read_u32(child, "reg", &pwm_port);
+	if (ret)
+		return ret;
+
+	data->pwm_present[pwm_port] = true;
+	ret = npcm7xx_pwm_config_set(data, pwm_port,
+				     NPCM7XX_PWM_CMR_DEFAULT_NUM);
+
+	ret = of_property_count_u8_elems(child, "cooling-levels");
+	if (ret > 0) {
+		ret = npcm7xx_create_pwm_cooling(dev, child, data, pwm_port,
+						 ret);
+		if (ret)
+			return ret;
+	}
+
+	fan_cnt = of_property_count_u8_elems(child, "fan-tach-ch");
+	if (fan_cnt < 1)
+		return -EINVAL;
+
+	fan_ch = devm_kzalloc(dev, sizeof(*fan_ch) * fan_cnt, GFP_KERNEL);
+	if (!fan_ch)
+		return -ENOMEM;
+
+	ret = of_property_read_u8_array(child, "fan-tach-ch", fan_ch, fan_cnt);
+	if (ret)
+		return ret;
+
+	for (ch = 0; ch < fan_cnt; ch++) {
+		index = fan_ch[ch];
+		data->fan_present[index] = true;
+		data->fan_dev[index].fan_st_flg = FAN_INIT;
+	}
+
+	return 0;
+}
+
+static int npcm7xx_pwm_fan_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np, *child;
+	struct npcm7xx_pwm_fan_data *data;
+	struct resource *res;
+	struct device *hwmon;
+	char name[20];
+	int ret, cnt;
+	u32 output_freq;
+	u32 i;
+
+	np = dev->of_node;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm");
+	if (!res) {
+		dev_err(dev, "pwm resource not found\n");
+		return -ENODEV;
+	}
+
+	data->pwm_base = devm_ioremap_resource(dev, res);
+	dev_dbg(dev, "pwm base resource is %pR\n", res);
+	if (IS_ERR(data->pwm_base))
+		return PTR_ERR(data->pwm_base);
+
+	data->pwm_clk = devm_clk_get(dev, "pwm");
+	if (IS_ERR(data->pwm_clk)) {
+		dev_err(dev, "couldn't get pwm clock\n");
+		return PTR_ERR(data->pwm_clk);
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "fan");
+	if (!res) {
+		dev_err(dev, "fan resource not found\n");
+		return -ENODEV;
+	}
+
+	data->fan_base = devm_ioremap_resource(dev, res);
+	dev_dbg(dev, "fan base resource is %pR\n", res);
+	if (IS_ERR(data->fan_base))
+		return PTR_ERR(data->fan_base);
+
+	data->fan_clk = devm_clk_get(dev, "fan");
+	if (IS_ERR(data->fan_clk)) {
+		dev_err(dev, "couldn't get fan clock\n");
+		return PTR_ERR(data->fan_clk);
+	}
+
+	output_freq = npcm7xx_pwm_init(data);
+	npcm7xx_fan_init(data);
+
+	for (cnt = 0; cnt < NPCM7XX_PWM_MAX_MODULES  ; cnt++)
+		mutex_init(&data->pwm_lock[cnt]);
+
+	for (i = 0; i < NPCM7XX_FAN_MAX_MODULE; i++) {
+		spin_lock_init(&data->fan_lock[i]);
+
+		data->fan_irq[i] = platform_get_irq(pdev, i);
+		if (data->fan_irq[i] < 0) {
+			dev_err(dev, "get IRQ fan%d failed\n", i);
+			return data->fan_irq[i];
+		}
+
+		sprintf(name, "NPCM7XX-FAN-MD%d", i);
+		ret = devm_request_irq(dev, data->fan_irq[i], npcm7xx_fan_isr,
+				       0, name, (void *)data);
+		if (ret) {
+			dev_err(dev, "register IRQ fan%d failed\n", i);
+			return ret;
+		}
+	}
+
+	for_each_child_of_node(np, child) {
+		ret = npcm7xx_en_pwm_fan(dev, child, data);
+		if (ret) {
+			dev_err(dev, "enable pwm and fan failed\n");
+			of_node_put(child);
+			return ret;
+		}
+	}
+
+	hwmon = devm_hwmon_device_register_with_info(dev, "npcm7xx_pwm_fan",
+						     data, &npcm7xx_chip_info,
+						     NULL);
+	if (IS_ERR(hwmon)) {
+		dev_err(dev, "unable to register hwmon device\n");
+		return PTR_ERR(hwmon);
+	}
+
+	for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM; i++) {
+		if (data->fan_present[i]) {
+			/* fan timer initialization */
+			data->fan_timer.expires = jiffies +
+				msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+			timer_setup(&data->fan_timer,
+				    npcm7xx_fan_polling, 0);
+			add_timer(&data->fan_timer);
+			break;
+		}
+	}
+
+	pr_info("NPCM7XX PWM-FAN Driver probed, output Freq %dHz[PWM], input Freq %dHz[FAN]\n",
+		output_freq, data->input_clk_freq);
+
+	return 0;
+}
+
+static const struct of_device_id of_pwm_fan_match_table[] = {
+	{ .compatible = "nuvoton,npcm750-pwm-fan", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_pwm_fan_match_table);
+
+static struct platform_driver npcm7xx_pwm_fan_driver = {
+	.probe		= npcm7xx_pwm_fan_probe,
+	.driver		= {
+		.name	= "npcm7xx_pwm_fan",
+		.of_match_table = of_pwm_fan_match_table,
+	},
+};
+
+module_platform_driver(npcm7xx_pwm_fan_driver);
+
+MODULE_DESCRIPTION("Nuvoton NPCM7XX PWM and Fan Tacho driver");
+MODULE_AUTHOR("Tomer Maimon <tomer.maimon@nuvoton.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index e71aec69e76e..a82018aaf473 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -130,7 +130,7 @@ config SENSORS_MAX34440
 	default n
 	help
 	  If you say yes here you get hardware monitoring support for Maxim
-	  MAX34440, MAX34441, MAX34446, MAX34460, and MAX34461.
+	  MAX34440, MAX34441, MAX34446, MAX34451, MAX34460, and MAX34461.
 
 	  This driver can also be built as a module. If so, the module will
 	  be called max34440.
diff --git a/drivers/hwmon/pmbus/max34440.c b/drivers/hwmon/pmbus/max34440.c
index 74a1f6f68fb3..47576c460010 100644
--- a/drivers/hwmon/pmbus/max34440.c
+++ b/drivers/hwmon/pmbus/max34440.c
@@ -27,7 +27,7 @@
 #include <linux/i2c.h>
 #include "pmbus.h"
 
-enum chips { max34440, max34441, max34446, max34460, max34461 };
+enum chips { max34440, max34441, max34446, max34451, max34460, max34461 };
 
 #define MAX34440_MFR_VOUT_PEAK		0xd4
 #define MAX34440_MFR_IOUT_PEAK		0xd5
@@ -44,6 +44,9 @@ enum chips { max34440, max34441, max34446, max34460, max34461 };
 #define MAX34440_STATUS_OT_FAULT	BIT(5)
 #define MAX34440_STATUS_OT_WARN		BIT(6)
 
+#define MAX34451_MFR_CHANNEL_CONFIG	0xe4
+#define MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK	0x3f
+
 struct max34440_data {
 	int id;
 	struct pmbus_driver_info info;
@@ -67,7 +70,7 @@ static int max34440_read_word_data(struct i2c_client *client, int page, int reg)
 					   MAX34440_MFR_VOUT_PEAK);
 		break;
 	case PMBUS_VIRT_READ_IOUT_AVG:
-		if (data->id != max34446)
+		if (data->id != max34446 && data->id != max34451)
 			return -ENXIO;
 		ret = pmbus_read_word_data(client, page,
 					   MAX34446_MFR_IOUT_AVG);
@@ -143,7 +146,7 @@ static int max34440_write_word_data(struct i2c_client *client, int page,
 	case PMBUS_VIRT_RESET_IOUT_HISTORY:
 		ret = pmbus_write_word_data(client, page,
 					    MAX34440_MFR_IOUT_PEAK, 0);
-		if (!ret && data->id == max34446)
+		if (!ret && (data->id == max34446 || data->id == max34451))
 			ret = pmbus_write_word_data(client, page,
 					MAX34446_MFR_IOUT_AVG, 0);
 
@@ -202,6 +205,58 @@ static int max34440_read_byte_data(struct i2c_client *client, int page, int reg)
 	return ret;
 }
 
+static int max34451_set_supported_funcs(struct i2c_client *client,
+					 struct max34440_data *data)
+{
+	/*
+	 * Each of the channel 0-15 can be configured to monitor the following
+	 * functions based on MFR_CHANNEL_CONFIG[5:0]
+	 * 0x10: Sequencing + voltage monitoring (only valid for PAGES 0–11)
+	 * 0x20: Voltage monitoring (no sequencing)
+	 * 0x21: Voltage read only
+	 * 0x22: Current monitoring
+	 * 0x23: Current read only
+	 * 0x30: General-purpose input active low
+	 * 0x34: General-purpose input active high
+	 * 0x00:  Disabled
+	 */
+
+	int page, rv;
+
+	for (page = 0; page < 16; page++) {
+		rv = i2c_smbus_write_byte_data(client, PMBUS_PAGE, page);
+		if (rv < 0)
+			return rv;
+
+		rv = i2c_smbus_read_word_data(client,
+					      MAX34451_MFR_CHANNEL_CONFIG);
+		if (rv < 0)
+			return rv;
+
+		switch (rv & MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK) {
+		case 0x10:
+		case 0x20:
+			data->info.func[page] = PMBUS_HAVE_VOUT |
+				PMBUS_HAVE_STATUS_VOUT;
+			break;
+		case 0x21:
+			data->info.func[page] = PMBUS_HAVE_VOUT;
+			break;
+		case 0x22:
+			data->info.func[page] = PMBUS_HAVE_IOUT |
+				PMBUS_HAVE_STATUS_IOUT;
+			break;
+		case 0x23:
+			data->info.func[page] = PMBUS_HAVE_IOUT;
+			break;
+		default:
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static struct pmbus_driver_info max34440_info[] = {
 	[max34440] = {
 		.pages = 14,
@@ -325,6 +380,30 @@ static struct pmbus_driver_info max34440_info[] = {
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
 	},
+	[max34451] = {
+		.pages = 21,
+		.format[PSC_VOLTAGE_OUT] = direct,
+		.format[PSC_TEMPERATURE] = direct,
+		.format[PSC_CURRENT_OUT] = direct,
+		.m[PSC_VOLTAGE_OUT] = 1,
+		.b[PSC_VOLTAGE_OUT] = 0,
+		.R[PSC_VOLTAGE_OUT] = 3,
+		.m[PSC_CURRENT_OUT] = 1,
+		.b[PSC_CURRENT_OUT] = 0,
+		.R[PSC_CURRENT_OUT] = 2,
+		.m[PSC_TEMPERATURE] = 1,
+		.b[PSC_TEMPERATURE] = 0,
+		.R[PSC_TEMPERATURE] = 2,
+		/* func 0-15 is set dynamically before probing */
+		.func[16] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[17] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[19] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[20] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.read_byte_data = max34440_read_byte_data,
+		.read_word_data = max34440_read_word_data,
+		.write_word_data = max34440_write_word_data,
+	},
 	[max34460] = {
 		.pages = 18,
 		.format[PSC_VOLTAGE_OUT] = direct,
@@ -398,6 +477,7 @@ static int max34440_probe(struct i2c_client *client,
 			  const struct i2c_device_id *id)
 {
 	struct max34440_data *data;
+	int rv;
 
 	data = devm_kzalloc(&client->dev, sizeof(struct max34440_data),
 			    GFP_KERNEL);
@@ -406,6 +486,12 @@ static int max34440_probe(struct i2c_client *client,
 	data->id = id->driver_data;
 	data->info = max34440_info[id->driver_data];
 
+	if (data->id == max34451) {
+		rv = max34451_set_supported_funcs(client, data);
+		if (rv)
+			return rv;
+	}
+
 	return pmbus_do_probe(client, id, &data->info);
 }
 
@@ -413,6 +499,7 @@ static const struct i2c_device_id max34440_id[] = {
 	{"max34440", max34440},
 	{"max34441", max34441},
 	{"max34446", max34446},
+	{"max34451", max34451},
 	{"max34460", max34460},
 	{"max34461", max34461},
 	{}
diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c
index 4a34f311e1ff..6ec65adaba49 100644
--- a/drivers/i2c/algos/i2c-algo-bit.c
+++ b/drivers/i2c/algos/i2c-algo-bit.c
@@ -647,10 +647,10 @@ static int __i2c_bit_add_bus(struct i2c_adapter *adap,
 	if (bit_adap->getscl == NULL)
 		adap->quirks = &i2c_bit_quirk_no_clk_stretch;
 
-	/* Bring bus to a known state. Looks like STOP if bus is not free yet */
-	setscl(bit_adap, 1);
-	udelay(bit_adap->udelay);
-	setsda(bit_adap, 1);
+	/*
+	 * We tried forcing SCL/SDA to an initial state here. But that caused a
+	 * regression, sadly. Check Bugzilla #200045 for details.
+	 */
 
 	ret = add_adapter(adap);
 	if (ret < 0)
diff --git a/drivers/i2c/busses/i2c-cht-wc.c b/drivers/i2c/busses/i2c-cht-wc.c
index 44cffad43701..c4d176f5ed79 100644
--- a/drivers/i2c/busses/i2c-cht-wc.c
+++ b/drivers/i2c/busses/i2c-cht-wc.c
@@ -234,7 +234,8 @@ static const struct irq_chip cht_wc_i2c_irq_chip = {
 	.name			= "cht_wc_ext_chrg_irq_chip",
 };
 
-static const char * const bq24190_suppliers[] = { "fusb302-typec-source" };
+static const char * const bq24190_suppliers[] = {
+	"tcpm-source-psy-i2c-fusb302" };
 
 static const struct property_entry bq24190_props[] = {
 	PROPERTY_ENTRY_STRING_ARRAY("supplied-from", bq24190_suppliers),
diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c
index 75d6ab177055..7379043711df 100644
--- a/drivers/i2c/busses/i2c-davinci.c
+++ b/drivers/i2c/busses/i2c-davinci.c
@@ -237,12 +237,16 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev)
 	/*
 	 * It's not always possible to have 1 to 2 ratio when d=7, so fall back
 	 * to minimal possible clkh in this case.
+	 *
+	 * Note:
+	 * CLKH is not allowed to be 0, in this case I2C clock is not generated
+	 * at all
 	 */
-	if (clk >= clkl + d) {
+	if (clk > clkl + d) {
 		clkh = clk - clkl - d;
 		clkl -= d;
 	} else {
-		clkh = 0;
+		clkh = 1;
 		clkl = clk - (d << 1);
 	}
 
diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c
index 005e6e0330c2..66f85bbf3591 100644
--- a/drivers/i2c/busses/i2c-gpio.c
+++ b/drivers/i2c/busses/i2c-gpio.c
@@ -279,9 +279,9 @@ static int i2c_gpio_probe(struct platform_device *pdev)
 	 * required for an I2C bus.
 	 */
 	if (pdata->scl_is_open_drain)
-		gflags = GPIOD_OUT_LOW;
+		gflags = GPIOD_OUT_HIGH;
 	else
-		gflags = GPIOD_OUT_LOW_OPEN_DRAIN;
+		gflags = GPIOD_OUT_HIGH_OPEN_DRAIN;
 	priv->scl = i2c_gpio_get_desc(dev, "scl", 1, gflags);
 	if (IS_ERR(priv->scl))
 		return PTR_ERR(priv->scl);
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 0207e194f84b..498c5e891649 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -368,6 +368,7 @@ static int i2c_imx_dma_xfer(struct imx_i2c_struct *i2c_imx,
 		goto err_desc;
 	}
 
+	reinit_completion(&dma->cmd_complete);
 	txdesc->callback = i2c_imx_dma_callback;
 	txdesc->callback_param = i2c_imx;
 	if (dma_submit_error(dmaengine_submit(txdesc))) {
@@ -622,7 +623,6 @@ static int i2c_imx_dma_write(struct imx_i2c_struct *i2c_imx,
 	 * The first byte must be transmitted by the CPU.
 	 */
 	imx_i2c_write_reg(i2c_8bit_addr_from_msg(msgs), i2c_imx, IMX_I2C_I2DR);
-	reinit_completion(&i2c_imx->dma->cmd_complete);
 	time_left = wait_for_completion_timeout(
 				&i2c_imx->dma->cmd_complete,
 				msecs_to_jiffies(DMA_TIMEOUT));
@@ -681,7 +681,6 @@ static int i2c_imx_dma_read(struct imx_i2c_struct *i2c_imx,
 	if (result)
 		return result;
 
-	reinit_completion(&i2c_imx->dma->cmd_complete);
 	time_left = wait_for_completion_timeout(
 				&i2c_imx->dma->cmd_complete,
 				msecs_to_jiffies(DMA_TIMEOUT));
@@ -1010,7 +1009,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx,
 	i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl,
 			"gpio");
 	rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN);
-	rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH);
+	rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN);
 
 	if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER ||
 	    PTR_ERR(rinfo->scl_gpiod) == -EPROBE_DEFER) {
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 5e310efd9446..3c1c817f6968 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -32,6 +32,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/reset.h>
 #include <linux/slab.h>
 
 /* register offsets */
@@ -111,8 +112,9 @@
 #define ID_ARBLOST	(1 << 3)
 #define ID_NACK		(1 << 4)
 /* persistent flags */
+#define ID_P_NO_RXDMA	(1 << 30) /* HW forbids RXDMA sometimes */
 #define ID_P_PM_BLOCKED	(1 << 31)
-#define ID_P_MASK	ID_P_PM_BLOCKED
+#define ID_P_MASK	(ID_P_PM_BLOCKED | ID_P_NO_RXDMA)
 
 enum rcar_i2c_type {
 	I2C_RCAR_GEN1,
@@ -141,6 +143,8 @@ struct rcar_i2c_priv {
 	struct dma_chan *dma_rx;
 	struct scatterlist sg;
 	enum dma_data_direction dma_direction;
+
+	struct reset_control *rstc;
 };
 
 #define rcar_i2c_priv_to_dev(p)		((p)->adap.dev.parent)
@@ -370,6 +374,11 @@ static void rcar_i2c_dma_unmap(struct rcar_i2c_priv *priv)
 	dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg),
 			 sg_dma_len(&priv->sg), priv->dma_direction);
 
+	/* Gen3 can only do one RXDMA per transfer and we just completed it */
+	if (priv->devtype == I2C_RCAR_GEN3 &&
+	    priv->dma_direction == DMA_FROM_DEVICE)
+		priv->flags |= ID_P_NO_RXDMA;
+
 	priv->dma_direction = DMA_NONE;
 }
 
@@ -407,8 +416,9 @@ static void rcar_i2c_dma(struct rcar_i2c_priv *priv)
 	unsigned char *buf;
 	int len;
 
-	/* Do not use DMA if it's not available or for messages < 8 bytes */
-	if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE))
+	/* Do various checks to see if DMA is feasible at all */
+	if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE) ||
+	    (read && priv->flags & ID_P_NO_RXDMA))
 		return;
 
 	if (read) {
@@ -739,6 +749,25 @@ static void rcar_i2c_release_dma(struct rcar_i2c_priv *priv)
 	}
 }
 
+/* I2C is a special case, we need to poll the status of a reset */
+static int rcar_i2c_do_reset(struct rcar_i2c_priv *priv)
+{
+	int i, ret;
+
+	ret = reset_control_reset(priv->rstc);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < LOOP_TIMEOUT; i++) {
+		ret = reset_control_status(priv->rstc);
+		if (ret == 0)
+			return 0;
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
+}
+
 static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 				struct i2c_msg *msgs,
 				int num)
@@ -750,6 +779,16 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 
 	pm_runtime_get_sync(dev);
 
+	/* Gen3 needs a reset before allowing RXDMA once */
+	if (priv->devtype == I2C_RCAR_GEN3) {
+		priv->flags |= ID_P_NO_RXDMA;
+		if (!IS_ERR(priv->rstc)) {
+			ret = rcar_i2c_do_reset(priv);
+			if (ret == 0)
+				priv->flags &= ~ID_P_NO_RXDMA;
+		}
+	}
+
 	rcar_i2c_init(priv);
 
 	ret = rcar_i2c_bus_barrier(priv);
@@ -920,6 +959,15 @@ static int rcar_i2c_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto out_pm_put;
 
+	if (priv->devtype == I2C_RCAR_GEN3) {
+		priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
+		if (!IS_ERR(priv->rstc)) {
+			ret = reset_control_status(priv->rstc);
+			if (ret < 0)
+				priv->rstc = ERR_PTR(-ENOTSUPP);
+		}
+	}
+
 	/* Stay always active when multi-master to keep arbitration working */
 	if (of_property_read_bool(dev->of_node, "multi-master"))
 		priv->flags |= ID_P_PM_BLOCKED;
diff --git a/drivers/i2c/busses/i2c-stu300.c b/drivers/i2c/busses/i2c-stu300.c
index e866c481bfc3..fce52bdab2b7 100644
--- a/drivers/i2c/busses/i2c-stu300.c
+++ b/drivers/i2c/busses/i2c-stu300.c
@@ -127,7 +127,7 @@ enum stu300_error {
 
 /*
  * The number of address send athemps tried before giving up.
- * If the first one failes it seems like 5 to 8 attempts are required.
+ * If the first one fails it seems like 5 to 8 attempts are required.
  */
 #define NUM_ADDR_RESEND_ATTEMPTS 12
 
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index 5fccd1f1bca8..797def5319f1 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -545,6 +545,14 @@ static int tegra_i2c_disable_packet_mode(struct tegra_i2c_dev *i2c_dev)
 {
 	u32 cnfg;
 
+	/*
+	 * NACK interrupt is generated before the I2C controller generates
+	 * the STOP condition on the bus. So wait for 2 clock periods
+	 * before disabling the controller so that the STOP condition has
+	 * been delivered properly.
+	 */
+	udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate));
+
 	cnfg = i2c_readl(i2c_dev, I2C_CNFG);
 	if (cnfg & I2C_CNFG_PACKET_MODE_EN)
 		i2c_writel(i2c_dev, cnfg & ~I2C_CNFG_PACKET_MODE_EN, I2C_CNFG);
@@ -706,15 +714,6 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev,
 	if (likely(i2c_dev->msg_err == I2C_ERR_NONE))
 		return 0;
 
-	/*
-	 * NACK interrupt is generated before the I2C controller generates
-	 * the STOP condition on the bus. So wait for 2 clock periods
-	 * before resetting the controller so that the STOP condition has
-	 * been delivered properly.
-	 */
-	if (i2c_dev->msg_err == I2C_ERR_NO_ACK)
-		udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate));
-
 	tegra_i2c_init(i2c_dev);
 	if (i2c_dev->msg_err == I2C_ERR_NO_ACK) {
 		if (msg->flags & I2C_M_IGNORE_NAK)
diff --git a/drivers/i2c/busses/i2c-xlp9xx.c b/drivers/i2c/busses/i2c-xlp9xx.c
index 1f41a4f89c08..8a873975cf12 100644
--- a/drivers/i2c/busses/i2c-xlp9xx.c
+++ b/drivers/i2c/busses/i2c-xlp9xx.c
@@ -191,28 +191,43 @@ static void xlp9xx_i2c_drain_rx_fifo(struct xlp9xx_i2c_dev *priv)
 	if (priv->len_recv) {
 		/* read length byte */
 		rlen = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO);
+
+		/*
+		 * We expect at least 2 interrupts for I2C_M_RECV_LEN
+		 * transactions. The length is updated during the first
+		 * interrupt, and the buffer contents are only copied
+		 * during subsequent interrupts. If in case the interrupts
+		 * get merged we would complete the transaction without
+		 * copying out the bytes from RX fifo. To avoid this now we
+		 * drain the fifo as and when data is available.
+		 * We drained the rlen byte already, decrement total length
+		 * by one.
+		 */
+
+		len--;
 		if (rlen > I2C_SMBUS_BLOCK_MAX || rlen == 0) {
 			rlen = 0;	/*abort transfer */
 			priv->msg_buf_remaining = 0;
 			priv->msg_len = 0;
-		} else {
-			*buf++ = rlen;
-			if (priv->client_pec)
-				++rlen; /* account for error check byte */
-			/* update remaining bytes and message length */
-			priv->msg_buf_remaining = rlen;
-			priv->msg_len = rlen + 1;
+			xlp9xx_i2c_update_rlen(priv);
+			return;
 		}
+
+		*buf++ = rlen;
+		if (priv->client_pec)
+			++rlen; /* account for error check byte */
+		/* update remaining bytes and message length */
+		priv->msg_buf_remaining = rlen;
+		priv->msg_len = rlen + 1;
 		xlp9xx_i2c_update_rlen(priv);
 		priv->len_recv = false;
-	} else {
-		len = min(priv->msg_buf_remaining, len);
-		for (i = 0; i < len; i++, buf++)
-			*buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO);
-
-		priv->msg_buf_remaining -= len;
 	}
 
+	len = min(priv->msg_buf_remaining, len);
+	for (i = 0; i < len; i++, buf++)
+		*buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO);
+
+	priv->msg_buf_remaining -= len;
 	priv->msg_buf = buf;
 
 	if (priv->msg_buf_remaining)
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 31d16ada6e7d..15c95aaa484c 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -198,7 +198,16 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 
 		val = !val;
 		bri->set_scl(adap, val);
-		ndelay(RECOVERY_NDELAY);
+
+		/*
+		 * If we can set SDA, we will always create STOP here to ensure
+		 * the additional pulses will do no harm. This is achieved by
+		 * letting SDA follow SCL half a cycle later.
+		 */
+		ndelay(RECOVERY_NDELAY / 2);
+		if (bri->set_sda)
+			bri->set_sda(adap, val);
+		ndelay(RECOVERY_NDELAY / 2);
 	}
 
 	/* check if recovery actually succeeded */
@@ -615,7 +624,7 @@ static int i2c_check_addr_busy(struct i2c_adapter *adapter, int addr)
 static void i2c_adapter_lock_bus(struct i2c_adapter *adapter,
 				 unsigned int flags)
 {
-	rt_mutex_lock(&adapter->bus_lock);
+	rt_mutex_lock_nested(&adapter->bus_lock, i2c_adapter_depth(adapter));
 }
 
 /**
diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c
index f3f683041e7f..9cd66cabb84f 100644
--- a/drivers/i2c/i2c-core-smbus.c
+++ b/drivers/i2c/i2c-core-smbus.c
@@ -463,17 +463,20 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,
 			msg[num-1].len++;
 	}
 
-	status = i2c_transfer(adapter, msg, num);
+	status = __i2c_transfer(adapter, msg, num);
 	if (status < 0)
-		return status;
-	if (status != num)
-		return -EIO;
+		goto cleanup;
+	if (status != num) {
+		status = -EIO;
+		goto cleanup;
+	}
+	status = 0;
 
 	/* Check PEC if last message is a read */
 	if (i && (msg[num-1].flags & I2C_M_RD)) {
 		status = i2c_smbus_check_pec(partial_pec, &msg[num-1]);
 		if (status < 0)
-			return status;
+			goto cleanup;
 	}
 
 	if (read_write == I2C_SMBUS_READ)
@@ -499,12 +502,13 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,
 			break;
 		}
 
+cleanup:
 	if (msg[0].flags & I2C_M_DMA_SAFE)
 		kfree(msg[0].buf);
 	if (msg[1].flags & I2C_M_DMA_SAFE)
 		kfree(msg[1].buf);
 
-	return 0;
+	return status;
 }
 
 /**
@@ -520,9 +524,24 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,
  * This executes an SMBus protocol operation, and returns a negative
  * errno code else zero on success.
  */
-s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
-		   char read_write, u8 command, int protocol,
-		   union i2c_smbus_data *data)
+s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		   unsigned short flags, char read_write,
+		   u8 command, int protocol, union i2c_smbus_data *data)
+{
+	s32 res;
+
+	i2c_lock_bus(adapter, I2C_LOCK_SEGMENT);
+	res = __i2c_smbus_xfer(adapter, addr, flags, read_write,
+			       command, protocol, data);
+	i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT);
+
+	return res;
+}
+EXPORT_SYMBOL(i2c_smbus_xfer);
+
+s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		     unsigned short flags, char read_write,
+		     u8 command, int protocol, union i2c_smbus_data *data)
 {
 	unsigned long orig_jiffies;
 	int try;
@@ -539,8 +558,6 @@ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
 	flags &= I2C_M_TEN | I2C_CLIENT_PEC | I2C_CLIENT_SCCB;
 
 	if (adapter->algo->smbus_xfer) {
-		i2c_lock_bus(adapter, I2C_LOCK_SEGMENT);
-
 		/* Retry automatically on arbitration loss */
 		orig_jiffies = jiffies;
 		for (res = 0, try = 0; try <= adapter->retries; try++) {
@@ -553,7 +570,6 @@ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
 				       orig_jiffies + adapter->timeout))
 				break;
 		}
-		i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT);
 
 		if (res != -EOPNOTSUPP || !adapter->algo->master_xfer)
 			goto trace;
@@ -575,7 +591,7 @@ trace:
 
 	return res;
 }
-EXPORT_SYMBOL(i2c_smbus_xfer);
+EXPORT_SYMBOL(__i2c_smbus_xfer);
 
 /**
  * i2c_smbus_read_i2c_block_data_or_emulated - read block or emulate
diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index 300ab4b672e4..29646aa6132e 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -144,7 +144,7 @@ static void i2c_mux_lock_bus(struct i2c_adapter *adapter, unsigned int flags)
 	struct i2c_mux_priv *priv = adapter->algo_data;
 	struct i2c_adapter *parent = priv->muxc->parent;
 
-	rt_mutex_lock(&parent->mux_lock);
+	rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter));
 	if (!(flags & I2C_LOCK_ROOT_ADAPTER))
 		return;
 	i2c_lock_bus(parent, flags);
@@ -181,7 +181,7 @@ static void i2c_parent_lock_bus(struct i2c_adapter *adapter,
 	struct i2c_mux_priv *priv = adapter->algo_data;
 	struct i2c_adapter *parent = priv->muxc->parent;
 
-	rt_mutex_lock(&parent->mux_lock);
+	rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter));
 	i2c_lock_bus(parent, flags);
 }
 
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 5f178384876f..44a7a255ef74 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -419,10 +419,11 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd)
 
 int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		    int write, void *buffer, unsigned *bufflen,
-		    struct request_sense *sense, int timeout,
+		    struct scsi_sense_hdr *sshdr, int timeout,
 		    req_flags_t rq_flags)
 {
 	struct cdrom_info *info = drive->driver_data;
+	struct scsi_sense_hdr local_sshdr;
 	int retries = 10;
 	bool failed;
 
@@ -430,6 +431,9 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 				  "rq_flags: 0x%x",
 				  cmd[0], write, timeout, rq_flags);
 
+	if (!sshdr)
+		sshdr = &local_sshdr;
+
 	/* start of retry loop */
 	do {
 		struct request *rq;
@@ -456,8 +460,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 
 		if (buffer)
 			*bufflen = scsi_req(rq)->resid_len;
-		if (sense)
-			memcpy(sense, scsi_req(rq)->sense, sizeof(*sense));
+		scsi_normalize_sense(scsi_req(rq)->sense,
+				     scsi_req(rq)->sense_len, sshdr);
 
 		/*
 		 * FIXME: we should probably abort/retry or something in case of
@@ -469,12 +473,10 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 			 * The request failed.  Retry if it was due to a unit
 			 * attention status (usually means media was changed).
 			 */
-			struct request_sense *reqbuf = scsi_req(rq)->sense;
-
-			if (reqbuf->sense_key == UNIT_ATTENTION)
+			if (sshdr->sense_key == UNIT_ATTENTION)
 				cdrom_saw_media_change(drive);
-			else if (reqbuf->sense_key == NOT_READY &&
-				 reqbuf->asc == 4 && reqbuf->ascq != 4) {
+			else if (sshdr->sense_key == NOT_READY &&
+				 sshdr->asc == 4 && sshdr->ascq != 4) {
 				/*
 				 * The drive is in the process of loading
 				 * a disk.  Retry, but wait a little to give
@@ -864,7 +866,7 @@ static void msf_from_bcd(struct atapi_msf *msf)
 	msf->frame  = bcd2bin(msf->frame);
 }
 
-int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense)
+int cdrom_check_status(ide_drive_t *drive, struct scsi_sense_hdr *sshdr)
 {
 	struct cdrom_info *info = drive->driver_data;
 	struct cdrom_device_info *cdi;
@@ -886,12 +888,11 @@ int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense)
 	 */
 	cmd[7] = cdi->sanyo_slot % 3;
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, RQF_QUIET);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sshdr, 0, RQF_QUIET);
 }
 
 static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
-			       unsigned long *sectors_per_frame,
-			       struct request_sense *sense)
+			       unsigned long *sectors_per_frame)
 {
 	struct {
 		__be32 lba;
@@ -908,7 +909,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 	memset(cmd, 0, BLK_MAX_CDB);
 	cmd[0] = GPCMD_READ_CDVD_CAPACITY;
 
-	stat = ide_cd_queue_pc(drive, cmd, 0, &capbuf, &len, sense, 0,
+	stat = ide_cd_queue_pc(drive, cmd, 0, &capbuf, &len, NULL, 0,
 			       RQF_QUIET);
 	if (stat)
 		return stat;
@@ -944,8 +945,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 }
 
 static int cdrom_read_tocentry(ide_drive_t *drive, int trackno, int msf_flag,
-				int format, char *buf, int buflen,
-				struct request_sense *sense)
+				int format, char *buf, int buflen)
 {
 	unsigned char cmd[BLK_MAX_CDB];
 
@@ -962,11 +962,11 @@ static int cdrom_read_tocentry(ide_drive_t *drive, int trackno, int msf_flag,
 	if (msf_flag)
 		cmd[1] = 2;
 
-	return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, sense, 0, RQF_QUIET);
+	return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, NULL, 0, RQF_QUIET);
 }
 
 /* Try to read the entire TOC for the disk into our internal buffer. */
-int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
+int ide_cd_read_toc(ide_drive_t *drive)
 {
 	int stat, ntracks, i;
 	struct cdrom_info *info = drive->driver_data;
@@ -996,14 +996,13 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	 * Check to see if the existing data is still valid. If it is,
 	 * just return.
 	 */
-	(void) cdrom_check_status(drive, sense);
+	(void) cdrom_check_status(drive, NULL);
 
 	if (drive->atapi_flags & IDE_AFLAG_TOC_VALID)
 		return 0;
 
 	/* try to get the total cdrom capacity and sector size */
-	stat = cdrom_read_capacity(drive, &toc->capacity, &sectors_per_frame,
-				   sense);
+	stat = cdrom_read_capacity(drive, &toc->capacity, &sectors_per_frame);
 	if (stat)
 		toc->capacity = 0x1fffff;
 
@@ -1016,7 +1015,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 
 	/* first read just the header, so we know how long the TOC is */
 	stat = cdrom_read_tocentry(drive, 0, 1, 0, (char *) &toc->hdr,
-				    sizeof(struct atapi_toc_header), sense);
+				    sizeof(struct atapi_toc_header));
 	if (stat)
 		return stat;
 
@@ -1036,7 +1035,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 				  (char *)&toc->hdr,
 				   sizeof(struct atapi_toc_header) +
 				   (ntracks + 1) *
-				   sizeof(struct atapi_toc_entry), sense);
+				   sizeof(struct atapi_toc_entry));
 
 	if (stat && toc->hdr.first_track > 1) {
 		/*
@@ -1056,8 +1055,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 					   (char *)&toc->hdr,
 					   sizeof(struct atapi_toc_header) +
 					   (ntracks + 1) *
-					   sizeof(struct atapi_toc_entry),
-					   sense);
+					   sizeof(struct atapi_toc_entry));
 		if (stat)
 			return stat;
 
@@ -1094,7 +1092,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	if (toc->hdr.first_track != CDROM_LEADOUT) {
 		/* read the multisession information */
 		stat = cdrom_read_tocentry(drive, 0, 0, 1, (char *)&ms_tmp,
-					   sizeof(ms_tmp), sense);
+					   sizeof(ms_tmp));
 		if (stat)
 			return stat;
 
@@ -1108,7 +1106,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	if (drive->atapi_flags & IDE_AFLAG_TOCADDR_AS_BCD) {
 		/* re-read multisession information using MSF format */
 		stat = cdrom_read_tocentry(drive, 0, 1, 1, (char *)&ms_tmp,
-					   sizeof(ms_tmp), sense);
+					   sizeof(ms_tmp));
 		if (stat)
 			return stat;
 
@@ -1412,7 +1410,7 @@ static sector_t ide_cdrom_capacity(ide_drive_t *drive)
 {
 	unsigned long capacity, sectors_per_frame;
 
-	if (cdrom_read_capacity(drive, &capacity, &sectors_per_frame, NULL))
+	if (cdrom_read_capacity(drive, &capacity, &sectors_per_frame))
 		return 0;
 
 	return capacity * sectors_per_frame;
@@ -1710,9 +1708,8 @@ static unsigned int idecd_check_events(struct gendisk *disk,
 static int idecd_revalidate_disk(struct gendisk *disk)
 {
 	struct cdrom_info *info = ide_drv_g(disk, cdrom_info);
-	struct request_sense sense;
 
-	ide_cd_read_toc(info->drive, &sense);
+	ide_cd_read_toc(info->drive);
 
 	return  0;
 }
@@ -1736,7 +1733,6 @@ static int ide_cd_probe(ide_drive_t *drive)
 {
 	struct cdrom_info *info;
 	struct gendisk *g;
-	struct request_sense sense;
 
 	ide_debug_log(IDE_DBG_PROBE, "driver_req: %s, media: 0x%x",
 				     drive->driver_req, drive->media);
@@ -1785,7 +1781,7 @@ static int ide_cd_probe(ide_drive_t *drive)
 		goto failed;
 	}
 
-	ide_cd_read_toc(drive, &sense);
+	ide_cd_read_toc(drive);
 	g->fops = &idecd_ops;
 	g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
 	device_add_disk(&drive->gendev, g);
diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h
index 04f0f310a856..a69dc7f61c4d 100644
--- a/drivers/ide/ide-cd.h
+++ b/drivers/ide/ide-cd.h
@@ -98,11 +98,11 @@ void ide_cd_log_error(const char *, struct request *, struct request_sense *);
 
 /* ide-cd.c functions used by ide-cd_ioctl.c */
 int ide_cd_queue_pc(ide_drive_t *, const unsigned char *, int, void *,
-		    unsigned *, struct request_sense *, int, req_flags_t);
-int ide_cd_read_toc(ide_drive_t *, struct request_sense *);
+		    unsigned *, struct scsi_sense_hdr *, int, req_flags_t);
+int ide_cd_read_toc(ide_drive_t *);
 int ide_cdrom_get_capabilities(ide_drive_t *, u8 *);
 void ide_cdrom_update_speed(ide_drive_t *, u8 *);
-int cdrom_check_status(ide_drive_t *, struct request_sense *);
+int cdrom_check_status(ide_drive_t *, struct scsi_sense_hdr *);
 
 /* ide-cd_ioctl.c */
 int ide_cdrom_open_real(struct cdrom_device_info *, int);
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index b1322400887b..4a6e1a413ead 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -43,14 +43,14 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct media_event_desc med;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int stat;
 
 	if (slot_nr != CDSL_CURRENT)
 		return -EINVAL;
 
-	stat = cdrom_check_status(drive, &sense);
-	if (!stat || sense.sense_key == UNIT_ATTENTION)
+	stat = cdrom_check_status(drive, &sshdr);
+	if (!stat || sshdr.sense_key == UNIT_ATTENTION)
 		return CDS_DISC_OK;
 
 	if (!cdrom_get_media_event(cdi, &med)) {
@@ -62,8 +62,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 			return CDS_NO_DISC;
 	}
 
-	if (sense.sense_key == NOT_READY && sense.asc == 0x04
-			&& sense.ascq == 0x04)
+	if (sshdr.sense_key == NOT_READY && sshdr.asc == 0x04
+			&& sshdr.ascq == 0x04)
 		return CDS_DISC_OK;
 
 	/*
@@ -71,8 +71,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 	 * just return TRAY_OPEN since ATAPI doesn't provide
 	 * any other way to detect this...
 	 */
-	if (sense.sense_key == NOT_READY) {
-		if (sense.asc == 0x3a && sense.ascq == 1)
+	if (sshdr.sense_key == NOT_READY) {
+		if (sshdr.asc == 0x3a && sshdr.ascq == 1)
 			return CDS_NO_DISC;
 		else
 			return CDS_TRAY_OPEN;
@@ -105,8 +105,7 @@ unsigned int ide_cdrom_check_events_real(struct cdrom_device_info *cdi,
 /* Eject the disk if EJECTFLAG is 0.
    If EJECTFLAG is 1, try to reload the disk. */
 static
-int cdrom_eject(ide_drive_t *drive, int ejectflag,
-		struct request_sense *sense)
+int cdrom_eject(ide_drive_t *drive, int ejectflag)
 {
 	struct cdrom_info *cd = drive->driver_data;
 	struct cdrom_device_info *cdi = &cd->devinfo;
@@ -129,20 +128,16 @@ int cdrom_eject(ide_drive_t *drive, int ejectflag,
 	cmd[0] = GPCMD_START_STOP_UNIT;
 	cmd[4] = loej | (ejectflag != 0);
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, 0);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 }
 
 /* Lock the door if LOCKFLAG is nonzero; unlock it otherwise. */
 static
-int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
-		    struct request_sense *sense)
+int ide_cd_lockdoor(ide_drive_t *drive, int lockflag)
 {
-	struct request_sense my_sense;
+	struct scsi_sense_hdr sshdr;
 	int stat;
 
-	if (sense == NULL)
-		sense = &my_sense;
-
 	/* If the drive cannot lock the door, just pretend. */
 	if ((drive->dev_flags & IDE_DFLAG_DOORLOCKING) == 0) {
 		stat = 0;
@@ -155,14 +150,14 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 		cmd[4] = lockflag ? 1 : 0;
 
 		stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL,
-				       sense, 0, 0);
+				       &sshdr, 0, 0);
 	}
 
 	/* If we got an illegal field error, the drive
 	   probably cannot lock the door. */
 	if (stat != 0 &&
-	    sense->sense_key == ILLEGAL_REQUEST &&
-	    (sense->asc == 0x24 || sense->asc == 0x20)) {
+	    sshdr.sense_key == ILLEGAL_REQUEST &&
+	    (sshdr.asc == 0x24 || sshdr.asc == 0x20)) {
 		printk(KERN_ERR "%s: door locking not supported\n",
 			drive->name);
 		drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING;
@@ -170,7 +165,7 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 	}
 
 	/* no medium, that's alright. */
-	if (stat != 0 && sense->sense_key == NOT_READY && sense->asc == 0x3a)
+	if (stat != 0 && sshdr.sense_key == NOT_READY && sshdr.asc == 0x3a)
 		stat = 0;
 
 	if (stat == 0) {
@@ -186,23 +181,22 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 int ide_cdrom_tray_move(struct cdrom_device_info *cdi, int position)
 {
 	ide_drive_t *drive = cdi->handle;
-	struct request_sense sense;
 
 	if (position) {
-		int stat = ide_cd_lockdoor(drive, 0, &sense);
+		int stat = ide_cd_lockdoor(drive, 0);
 
 		if (stat)
 			return stat;
 	}
 
-	return cdrom_eject(drive, !position, &sense);
+	return cdrom_eject(drive, !position);
 }
 
 int ide_cdrom_lock_door(struct cdrom_device_info *cdi, int lock)
 {
 	ide_drive_t *drive = cdi->handle;
 
-	return ide_cd_lockdoor(drive, lock, NULL);
+	return ide_cd_lockdoor(drive, lock);
 }
 
 /*
@@ -213,7 +207,6 @@ int ide_cdrom_select_speed(struct cdrom_device_info *cdi, int speed)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *cd = drive->driver_data;
-	struct request_sense sense;
 	u8 buf[ATAPI_CAPABILITIES_PAGE_SIZE];
 	int stat;
 	unsigned char cmd[BLK_MAX_CDB];
@@ -236,7 +229,7 @@ int ide_cdrom_select_speed(struct cdrom_device_info *cdi, int speed)
 		cmd[5] = speed & 0xff;
 	}
 
-	stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, &sense, 0, 0);
+	stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 
 	if (!ide_cdrom_get_capabilities(drive, buf)) {
 		ide_cdrom_update_speed(drive, buf);
@@ -252,11 +245,10 @@ int ide_cdrom_get_last_session(struct cdrom_device_info *cdi,
 	struct atapi_toc *toc;
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *info = drive->driver_data;
-	struct request_sense sense;
 	int ret;
 
 	if ((drive->atapi_flags & IDE_AFLAG_TOC_VALID) == 0 || !info->toc) {
-		ret = ide_cd_read_toc(drive, &sense);
+		ret = ide_cd_read_toc(drive);
 		if (ret)
 			return ret;
 	}
@@ -300,7 +292,6 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *cd = drive->driver_data;
-	struct request_sense sense;
 	struct request *rq;
 	int ret;
 
@@ -315,7 +306,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	 * lock it again.
 	 */
 	if (drive->atapi_flags & IDE_AFLAG_DOOR_LOCKED)
-		(void)ide_cd_lockdoor(drive, 1, &sense);
+		(void)ide_cd_lockdoor(drive, 1);
 
 	return ret;
 }
@@ -355,7 +346,6 @@ static int ide_cd_fake_play_trkind(ide_drive_t *drive, void *arg)
 	struct atapi_toc_entry *first_toc, *last_toc;
 	unsigned long lba_start, lba_end;
 	int stat;
-	struct request_sense sense;
 	unsigned char cmd[BLK_MAX_CDB];
 
 	stat = ide_cd_get_toc_entry(drive, ti->cdti_trk0, &first_toc);
@@ -380,7 +370,7 @@ static int ide_cd_fake_play_trkind(ide_drive_t *drive, void *arg)
 	lba_to_msf(lba_start,   &cmd[3], &cmd[4], &cmd[5]);
 	lba_to_msf(lba_end - 1, &cmd[6], &cmd[7], &cmd[8]);
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, &sense, 0, 0);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 }
 
 static int ide_cd_read_tochdr(ide_drive_t *drive, void *arg)
@@ -391,7 +381,7 @@ static int ide_cd_read_tochdr(ide_drive_t *drive, void *arg)
 	int stat;
 
 	/* Make sure our saved TOC is valid. */
-	stat = ide_cd_read_toc(drive, NULL);
+	stat = ide_cd_read_toc(drive);
 	if (stat)
 		return stat;
 
@@ -461,8 +451,8 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi,
 	   layer. the packet must be complete, as we do not
 	   touch it at all. */
 
-	if (cgc->sense)
-		memset(cgc->sense, 0, sizeof(struct request_sense));
+	if (cgc->sshdr)
+		memset(cgc->sshdr, 0, sizeof(*cgc->sshdr));
 
 	if (cgc->quiet)
 		flags |= RQF_QUIET;
@@ -470,7 +460,7 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi,
 	cgc->stat = ide_cd_queue_pc(drive, cgc->cmd,
 				    cgc->data_direction == CGC_DATA_WRITE,
 				    cgc->buffer, &len,
-				    cgc->sense, cgc->timeout, flags);
+				    cgc->sshdr, cgc->timeout, flags);
 	if (!cgc->stat)
 		cgc->buflen -= len;
 	return cgc->stat;
diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c
index 7e3d82cff3d5..c149c9c360fc 100644
--- a/drivers/iio/accel/mma8452.c
+++ b/drivers/iio/accel/mma8452.c
@@ -1053,7 +1053,7 @@ static irqreturn_t mma8452_interrupt(int irq, void *p)
 	if (src < 0)
 		return IRQ_NONE;
 
-	if (!(src & data->chip_info->enabled_events))
+	if (!(src & (data->chip_info->enabled_events | MMA8452_INT_DRDY)))
 		return IRQ_NONE;
 
 	if (src & MMA8452_INT_DRDY) {
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index f9c0624505a2..42618fe4f83e 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -959,6 +959,8 @@ int inv_mpu_core_probe(struct regmap *regmap, int irq, const char *name,
 	}
 
 	irq_type = irqd_get_trigger_type(desc);
+	if (!irq_type)
+		irq_type = IRQF_TRIGGER_RISING;
 	if (irq_type == IRQF_TRIGGER_RISING)
 		st->irq_mask = INV_MPU6050_ACTIVE_HIGH;
 	else if (irq_type == IRQF_TRIGGER_FALLING)
diff --git a/drivers/iio/light/tsl2772.c b/drivers/iio/light/tsl2772.c
index 34d42a2504c9..df5b2a0da96c 100644
--- a/drivers/iio/light/tsl2772.c
+++ b/drivers/iio/light/tsl2772.c
@@ -582,6 +582,8 @@ static int tsl2772_als_calibrate(struct iio_dev *indio_dev)
 			"%s: failed to get lux\n", __func__);
 		return lux_val;
 	}
+	if (lux_val == 0)
+		return -ERANGE;
 
 	ret = (chip->settings.als_cal_target * chip->settings.als_gain_trim) /
 			lux_val;
diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index 5ec3e41b65f2..fe87d27779d9 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -415,10 +415,9 @@ static int bmp280_read_humid(struct bmp280_data *data, int *val, int *val2)
 	}
 	comp_humidity = bmp280_compensate_humidity(data, adc_humidity);
 
-	*val = comp_humidity;
-	*val2 = 1024;
+	*val = comp_humidity * 1000 / 1024;
 
-	return IIO_VAL_FRACTIONAL;
+	return IIO_VAL_INT;
 }
 
 static int bmp280_read_raw(struct iio_dev *indio_dev,
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index a6e904973ba8..475910ffbcb6 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -121,7 +121,7 @@ static int uverbs_try_lock_object(struct ib_uobject *uobj, bool exclusive)
 	 * this lock.
 	 */
 	if (!exclusive)
-		return __atomic_add_unless(&uobj->usecnt, 1, -1) == -1 ?
+		return atomic_fetch_add_unless(&uobj->usecnt, 1, -1) == -1 ?
 			-EBUSY : 0;
 
 	/* lock is either WRITE or DESTROY - should be exclusive */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 3e90b6a1d9d2..583d3a10b940 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1984,15 +1984,64 @@ static int modify_qp(struct ib_uverbs_file *file,
 		goto release_qp;
 	}
 
-	if ((cmd->base.attr_mask & IB_QP_AV) &&
-	    !rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) {
-		ret = -EINVAL;
-		goto release_qp;
+	if ((cmd->base.attr_mask & IB_QP_AV)) {
+		if (!rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) {
+			ret = -EINVAL;
+			goto release_qp;
+		}
+
+		if (cmd->base.attr_mask & IB_QP_STATE &&
+		    cmd->base.qp_state == IB_QPS_RTR) {
+		/* We are in INIT->RTR TRANSITION (if we are not,
+		 * this transition will be rejected in subsequent checks).
+		 * In the INIT->RTR transition, we cannot have IB_QP_PORT set,
+		 * but the IB_QP_STATE flag is required.
+		 *
+		 * Since kernel 3.14 (commit dbf727de7440), the uverbs driver,
+		 * when IB_QP_AV is set, has required inclusion of a valid
+		 * port number in the primary AV. (AVs are created and handled
+		 * differently for infiniband and ethernet (RoCE) ports).
+		 *
+		 * Check the port number included in the primary AV against
+		 * the port number in the qp struct, which was set (and saved)
+		 * in the RST->INIT transition.
+		 */
+			if (cmd->base.dest.port_num != qp->real_qp->port) {
+				ret = -EINVAL;
+				goto release_qp;
+			}
+		} else {
+		/* We are in SQD->SQD. (If we are not, this transition will
+		 * be rejected later in the verbs layer checks).
+		 * Check for both IB_QP_PORT and IB_QP_AV, these can be set
+		 * together in the SQD->SQD transition.
+		 *
+		 * If only IP_QP_AV was set, add in IB_QP_PORT as well (the
+		 * verbs layer driver does not track primary port changes
+		 * resulting from path migration. Thus, in SQD, if the primary
+		 * AV is modified, the primary port should also be modified).
+		 *
+		 * Note that in this transition, the IB_QP_STATE flag
+		 * is not allowed.
+		 */
+			if (((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT))
+			     == (IB_QP_AV | IB_QP_PORT)) &&
+			    cmd->base.port_num != cmd->base.dest.port_num) {
+				ret = -EINVAL;
+				goto release_qp;
+			}
+			if ((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT))
+			    == IB_QP_AV) {
+				cmd->base.attr_mask |= IB_QP_PORT;
+				cmd->base.port_num = cmd->base.dest.port_num;
+			}
+		}
 	}
 
 	if ((cmd->base.attr_mask & IB_QP_ALT_PATH) &&
 	    (!rdma_is_port_valid(qp->device, cmd->base.alt_port_num) ||
-	    !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num))) {
+	    !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num) ||
+	    cmd->base.alt_port_num != cmd->base.alt_dest.port_num)) {
 		ret = -EINVAL;
 		goto release_qp;
 	}
@@ -3488,8 +3537,8 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 	struct ib_flow_attr		  *flow_attr;
 	struct ib_qp			  *qp;
 	struct ib_uflow_resources	  *uflow_res;
+	struct ib_uverbs_flow_spec_hdr	  *kern_spec;
 	int err = 0;
-	void *kern_spec;
 	void *ib_spec;
 	int i;
 
@@ -3538,8 +3587,8 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 		if (!kern_flow_attr)
 			return -ENOMEM;
 
-		memcpy(kern_flow_attr, &cmd.flow_attr, sizeof(*kern_flow_attr));
-		err = ib_copy_from_udata(kern_flow_attr + 1, ucore,
+		*kern_flow_attr = cmd.flow_attr;
+		err = ib_copy_from_udata(&kern_flow_attr->flow_specs, ucore,
 					 cmd.flow_attr.size);
 		if (err)
 			goto err_free_attr;
@@ -3559,6 +3608,11 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 		goto err_uobj;
 	}
 
+	if (qp->qp_type != IB_QPT_UD && qp->qp_type != IB_QPT_RAW_PACKET) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
 	flow_attr = kzalloc(struct_size(flow_attr, flows,
 				cmd.flow_attr.num_of_specs), GFP_KERNEL);
 	if (!flow_attr) {
@@ -3578,21 +3632,22 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 	flow_attr->flags = kern_flow_attr->flags;
 	flow_attr->size = sizeof(*flow_attr);
 
-	kern_spec = kern_flow_attr + 1;
+	kern_spec = kern_flow_attr->flow_specs;
 	ib_spec = flow_attr + 1;
 	for (i = 0; i < flow_attr->num_of_specs &&
-	     cmd.flow_attr.size > offsetof(struct ib_uverbs_flow_spec, reserved) &&
-	     cmd.flow_attr.size >=
-	     ((struct ib_uverbs_flow_spec *)kern_spec)->size; i++) {
-		err = kern_spec_to_ib_spec(file->ucontext, kern_spec, ib_spec,
-					   uflow_res);
+			cmd.flow_attr.size >= sizeof(*kern_spec) &&
+			cmd.flow_attr.size >= kern_spec->size;
+	     i++) {
+		err = kern_spec_to_ib_spec(
+				file->ucontext, (struct ib_uverbs_flow_spec *)kern_spec,
+				ib_spec, uflow_res);
 		if (err)
 			goto err_free;
 
 		flow_attr->size +=
 			((union ib_flow_spec *) ib_spec)->size;
-		cmd.flow_attr.size -= ((struct ib_uverbs_flow_spec *)kern_spec)->size;
-		kern_spec += ((struct ib_uverbs_flow_spec *) kern_spec)->size;
+		cmd.flow_attr.size -= kern_spec->size;
+		kern_spec = ((void *)kern_spec) + kern_spec->size;
 		ib_spec += ((union ib_flow_spec *) ib_spec)->size;
 	}
 	if (cmd.flow_attr.size || (i != flow_attr->num_of_specs)) {
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 1445918e3239..7b76e6f81aeb 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -774,7 +774,7 @@ static int c4iw_set_page(struct ib_mr *ibmr, u64 addr)
 {
 	struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
 
-	if (unlikely(mhp->mpl_len == mhp->max_mpl_len))
+	if (unlikely(mhp->mpl_len == mhp->attr.pbl_size))
 		return -ENOMEM;
 
 	mhp->mpl[mhp->mpl_len++] = addr;
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 1a1a47ac53c6..f15c93102081 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -271,7 +271,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 
 	lockdep_assert_held(&qp->s_lock);
 	ps->s_txreq = get_txreq(ps->dev, qp);
-	if (IS_ERR(ps->s_txreq))
+	if (!ps->s_txreq)
 		goto bail_no_tx;
 
 	if (priv->hdr_type == HFI1_PKT_TYPE_9B) {
diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
index b7b671017e59..e254dcec6f64 100644
--- a/drivers/infiniband/hw/hfi1/uc.c
+++ b/drivers/infiniband/hw/hfi1/uc.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -72,7 +72,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	int middle = 0;
 
 	ps->s_txreq = get_txreq(ps->dev, qp);
-	if (IS_ERR(ps->s_txreq))
+	if (!ps->s_txreq)
 		goto bail_no_tx;
 
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index 1ab332f1866e..70d39fc450a1 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -503,7 +503,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	u32 lid;
 
 	ps->s_txreq = get_txreq(ps->dev, qp);
-	if (IS_ERR(ps->s_txreq))
+	if (!ps->s_txreq)
 		goto bail_no_tx;
 
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_NEXT_SEND_OK)) {
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c
index 873e48ea923f..c4ab2d5b4502 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.c
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2016 - 2017 Intel Corporation.
+ * Copyright(c) 2016 - 2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -94,7 +94,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
 				struct rvt_qp *qp)
 	__must_hold(&qp->s_lock)
 {
-	struct verbs_txreq *tx = ERR_PTR(-EBUSY);
+	struct verbs_txreq *tx = NULL;
 
 	write_seqlock(&dev->txwait_lock);
 	if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h
index 729244c3086c..1c19bbc764b2 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.h
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2016 Intel Corporation.
+ * Copyright(c) 2016 - 2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -83,7 +83,7 @@ static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev,
 	if (unlikely(!tx)) {
 		/* call slow path to get the lock */
 		tx = __get_txreq(dev, qp);
-		if (IS_ERR(tx))
+		if (!tx)
 			return tx;
 	}
 	tx->qp = qp;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 8013d69c5ac4..8444234ed092 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -1435,7 +1435,7 @@ static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset)
 		}
 		fwnode = &dsaf_node->fwnode;
 	} else if (is_acpi_device_node(dev->fwnode)) {
-		struct acpi_reference_args args;
+		struct fwnode_reference_args args;
 
 		ret = acpi_node_get_property_reference(dev->fwnode,
 						       "dsaf-handle", 0, &args);
@@ -1443,7 +1443,7 @@ static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset)
 			dev_err(dev, "could not find dsaf-handle\n");
 			return ret;
 		}
-		fwnode = acpi_fwnode_handle(args.adev);
+		fwnode = args.fwnode;
 	} else {
 		dev_err(dev, "cannot read data from DT or ACPI\n");
 		return -ENXIO;
@@ -4835,16 +4835,14 @@ static int hns_roce_get_cfg(struct hns_roce_dev *hr_dev)
 				continue;
 			pdev = of_find_device_by_node(net_node);
 		} else if (is_acpi_device_node(dev->fwnode)) {
-			struct acpi_reference_args args;
-			struct fwnode_handle *fwnode;
+			struct fwnode_reference_args args;
 
 			ret = acpi_node_get_property_reference(dev->fwnode,
 							       "eth-handle",
 							       i, &args);
 			if (ret)
 				continue;
-			fwnode = acpi_fwnode_handle(args.adev);
-			pdev = hns_roce_find_pdev(fwnode);
+			pdev = hns_roce_find_pdev(args.fwnode);
 		} else {
 			dev_err(dev, "cannot read data from DT or ACPI\n");
 			return -ENXIO;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index e3e330f59c2c..b3ba9a222550 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -6113,7 +6113,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
 			     MLX5_CAP_GEN(mdev, num_vhca_ports));
 
-	if (MLX5_VPORT_MANAGER(mdev) &&
+	if (MLX5_ESWITCH_MANAGER(mdev) &&
 	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
 		dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0);
 
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 0af7b7905550..f5de5adc9b1a 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -266,18 +266,24 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 
 	desc_size = sizeof(struct mlx5_wqe_srq_next_seg) +
 		    srq->msrq.max_gs * sizeof(struct mlx5_wqe_data_seg);
-	if (desc_size == 0 || srq->msrq.max_gs > desc_size)
-		return ERR_PTR(-EINVAL);
+	if (desc_size == 0 || srq->msrq.max_gs > desc_size) {
+		err = -EINVAL;
+		goto err_srq;
+	}
 	desc_size = roundup_pow_of_two(desc_size);
 	desc_size = max_t(size_t, 32, desc_size);
-	if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg))
-		return ERR_PTR(-EINVAL);
+	if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg)) {
+		err = -EINVAL;
+		goto err_srq;
+	}
 	srq->msrq.max_avail_gather = (desc_size - sizeof(struct mlx5_wqe_srq_next_seg)) /
 		sizeof(struct mlx5_wqe_data_seg);
 	srq->msrq.wqe_shift = ilog2(desc_size);
 	buf_size = srq->msrq.max * desc_size;
-	if (buf_size < desc_size)
-		return ERR_PTR(-EINVAL);
+	if (buf_size < desc_size) {
+		err = -EINVAL;
+		goto err_srq;
+	}
 	in.type = init_attr->srq_type;
 
 	if (pd->uobject)
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index ca844a926e6a..130bf163f066 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -311,7 +311,7 @@ iser_set_dif_domain(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs,
 {
 	domain->sig_type = IB_SIG_TYPE_T10_DIF;
 	domain->sig.dif.pi_interval = scsi_prot_interval(sc);
-	domain->sig.dif.ref_tag = scsi_prot_ref_tag(sc);
+	domain->sig.dif.ref_tag = t10_pi_ref_tag(sc->request);
 	/*
 	 * At the moment we hard code those, but in the future
 	 * we will take them from sc.
diff --git a/drivers/input/input-mt.c b/drivers/input/input-mt.c
index cf30523c6ef6..6c7326c93721 100644
--- a/drivers/input/input-mt.c
+++ b/drivers/input/input-mt.c
@@ -131,8 +131,10 @@ EXPORT_SYMBOL(input_mt_destroy_slots);
  * inactive, or if the tool type is changed, a new tracking id is
  * assigned to the slot. The tool type is only reported if the
  * corresponding absbit field is set.
+ *
+ * Returns true if contact is active.
  */
-void input_mt_report_slot_state(struct input_dev *dev,
+bool input_mt_report_slot_state(struct input_dev *dev,
 				unsigned int tool_type, bool active)
 {
 	struct input_mt *mt = dev->mt;
@@ -140,22 +142,24 @@ void input_mt_report_slot_state(struct input_dev *dev,
 	int id;
 
 	if (!mt)
-		return;
+		return false;
 
 	slot = &mt->slots[mt->slot];
 	slot->frame = mt->frame;
 
 	if (!active) {
 		input_event(dev, EV_ABS, ABS_MT_TRACKING_ID, -1);
-		return;
+		return false;
 	}
 
 	id = input_mt_get_value(slot, ABS_MT_TRACKING_ID);
-	if (id < 0 || input_mt_get_value(slot, ABS_MT_TOOL_TYPE) != tool_type)
+	if (id < 0)
 		id = input_mt_new_trkid(mt);
 
 	input_event(dev, EV_ABS, ABS_MT_TRACKING_ID, id);
 	input_event(dev, EV_ABS, ABS_MT_TOOL_TYPE, tool_type);
+
+	return true;
 }
 EXPORT_SYMBOL(input_mt_report_slot_state);
 
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 48e36acbeb49..cd620e009bad 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -125,7 +125,7 @@ static const struct xpad_device {
 	u8 mapping;
 	u8 xtype;
 } xpad_device[] = {
-	{ 0x0079, 0x18d4, "GPD Win 2 Controller", 0, XTYPE_XBOX360 },
+	{ 0x0079, 0x18d4, "GPD Win 2 X-Box Controller", 0, XTYPE_XBOX360 },
 	{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
diff --git a/drivers/input/keyboard/goldfish_events.c b/drivers/input/keyboard/goldfish_events.c
index f6e643b589b6..e8dae6195b30 100644
--- a/drivers/input/keyboard/goldfish_events.c
+++ b/drivers/input/keyboard/goldfish_events.c
@@ -45,7 +45,7 @@ struct event_dev {
 static irqreturn_t events_interrupt(int irq, void *dev_id)
 {
 	struct event_dev *edev = dev_id;
-	unsigned type, code, value;
+	unsigned int type, code, value;
 
 	type = __raw_readl(edev->addr + REG_READ);
 	code = __raw_readl(edev->addr + REG_READ);
@@ -57,7 +57,7 @@ static irqreturn_t events_interrupt(int irq, void *dev_id)
 }
 
 static void events_import_bits(struct event_dev *edev,
-			unsigned long bits[], unsigned type, size_t count)
+			unsigned long bits[], unsigned int type, size_t count)
 {
 	void __iomem *addr = edev->addr;
 	int i, j;
@@ -99,6 +99,7 @@ static void events_import_abs_params(struct event_dev *edev)
 
 		for (j = 0; j < ARRAY_SIZE(val); j++) {
 			int offset = (i * ARRAY_SIZE(val) + j) * sizeof(u32);
+
 			val[j] = __raw_readl(edev->addr + REG_DATA + offset);
 		}
 
@@ -112,7 +113,7 @@ static int events_probe(struct platform_device *pdev)
 	struct input_dev *input_dev;
 	struct event_dev *edev;
 	struct resource *res;
-	unsigned keymapnamelen;
+	unsigned int keymapnamelen;
 	void __iomem *addr;
 	int irq;
 	int i;
@@ -150,7 +151,7 @@ static int events_probe(struct platform_device *pdev)
 	for (i = 0; i < keymapnamelen; i++)
 		edev->name[i] = __raw_readb(edev->addr + REG_DATA + i);
 
-	pr_debug("events_probe() keymap=%s\n", edev->name);
+	pr_debug("%s: keymap=%s\n", __func__, edev->name);
 
 	input_dev->name = edev->name;
 	input_dev->id.bustype = BUS_HOST;
diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c
index a4e404aaf64b..5c7afdec192c 100644
--- a/drivers/input/keyboard/hilkbd.c
+++ b/drivers/input/keyboard/hilkbd.c
@@ -57,8 +57,8 @@ MODULE_LICENSE("GPL v2");
  #define HIL_DATA		0x1
  #define HIL_CMD		0x3
  #define HIL_IRQ		2
- #define hil_readb(p)		readb(p)
- #define hil_writeb(v,p)	writeb((v),(p))
+ #define hil_readb(p)		readb((const volatile void __iomem *)(p))
+ #define hil_writeb(v, p)	writeb((v), (volatile void __iomem *)(p))
 
 #else
 #error "HIL is not supported on this platform"
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index c25606e00693..ca59a2be9bc5 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -841,4 +841,14 @@ config INPUT_RAVE_SP_PWRBUTTON
 	  To compile this driver as a module, choose M here: the
 	  module will be called rave-sp-pwrbutton.
 
+config INPUT_SC27XX_VIBRA
+	tristate "Spreadtrum sc27xx vibrator support"
+	depends on MFD_SC27XX_PMIC || COMPILE_TEST
+	select INPUT_FF_MEMLESS
+	help
+	  This option enables support for Spreadtrum sc27xx vibrator driver.
+
+	  To compile this driver as a module, choose M here. The module will
+	  be called sc27xx_vibra.
+
 endif
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index 72cde28649e2..9d0f9d1ff68f 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -66,6 +66,7 @@ obj-$(CONFIG_INPUT_RETU_PWRBUTTON)	+= retu-pwrbutton.o
 obj-$(CONFIG_INPUT_AXP20X_PEK)		+= axp20x-pek.o
 obj-$(CONFIG_INPUT_GPIO_ROTARY_ENCODER)	+= rotary_encoder.o
 obj-$(CONFIG_INPUT_RK805_PWRKEY)	+= rk805-pwrkey.o
+obj-$(CONFIG_INPUT_SC27XX_VIBRA)	+= sc27xx-vibra.o
 obj-$(CONFIG_INPUT_SGI_BTNS)		+= sgi_btns.o
 obj-$(CONFIG_INPUT_SIRFSOC_ONKEY)	+= sirfsoc-onkey.o
 obj-$(CONFIG_INPUT_SOC_BUTTON_ARRAY)	+= soc_button_array.o
diff --git a/drivers/input/misc/sc27xx-vibra.c b/drivers/input/misc/sc27xx-vibra.c
new file mode 100644
index 000000000000..295251abbdac
--- /dev/null
+++ b/drivers/input/misc/sc27xx-vibra.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Spreadtrum Communications Inc.
+ */
+
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/input.h>
+#include <linux/workqueue.h>
+
+#define CUR_DRV_CAL_SEL		GENMASK(13, 12)
+#define SLP_LDOVIBR_PD_EN	BIT(9)
+#define LDO_VIBR_PD		BIT(8)
+
+struct vibra_info {
+	struct input_dev	*input_dev;
+	struct work_struct	play_work;
+	struct regmap		*regmap;
+	u32			base;
+	u32			strength;
+	bool			enabled;
+};
+
+static void sc27xx_vibra_set(struct vibra_info *info, bool on)
+{
+	if (on) {
+		regmap_update_bits(info->regmap, info->base, LDO_VIBR_PD, 0);
+		regmap_update_bits(info->regmap, info->base,
+				   SLP_LDOVIBR_PD_EN, 0);
+		info->enabled = true;
+	} else {
+		regmap_update_bits(info->regmap, info->base, LDO_VIBR_PD,
+				   LDO_VIBR_PD);
+		regmap_update_bits(info->regmap, info->base,
+				   SLP_LDOVIBR_PD_EN, SLP_LDOVIBR_PD_EN);
+		info->enabled = false;
+	}
+}
+
+static int sc27xx_vibra_hw_init(struct vibra_info *info)
+{
+	return regmap_update_bits(info->regmap, info->base, CUR_DRV_CAL_SEL, 0);
+}
+
+static void sc27xx_vibra_play_work(struct work_struct *work)
+{
+	struct vibra_info *info = container_of(work, struct vibra_info,
+					       play_work);
+
+	if (info->strength && !info->enabled)
+		sc27xx_vibra_set(info, true);
+	else if (info->strength == 0 && info->enabled)
+		sc27xx_vibra_set(info, false);
+}
+
+static int sc27xx_vibra_play(struct input_dev *input, void *data,
+			     struct ff_effect *effect)
+{
+	struct vibra_info *info = input_get_drvdata(input);
+
+	info->strength = effect->u.rumble.weak_magnitude;
+	schedule_work(&info->play_work);
+
+	return 0;
+}
+
+static void sc27xx_vibra_close(struct input_dev *input)
+{
+	struct vibra_info *info = input_get_drvdata(input);
+
+	cancel_work_sync(&info->play_work);
+	if (info->enabled)
+		sc27xx_vibra_set(info, false);
+}
+
+static int sc27xx_vibra_probe(struct platform_device *pdev)
+{
+	struct vibra_info *info;
+	int error;
+
+	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!info->regmap) {
+		dev_err(&pdev->dev, "failed to get vibrator regmap.\n");
+		return -ENODEV;
+	}
+
+	error = device_property_read_u32(&pdev->dev, "reg", &info->base);
+	if (error) {
+		dev_err(&pdev->dev, "failed to get vibrator base address.\n");
+		return error;
+	}
+
+	info->input_dev = devm_input_allocate_device(&pdev->dev);
+	if (!info->input_dev) {
+		dev_err(&pdev->dev, "failed to allocate input device.\n");
+		return -ENOMEM;
+	}
+
+	info->input_dev->name = "sc27xx:vibrator";
+	info->input_dev->id.version = 0;
+	info->input_dev->close = sc27xx_vibra_close;
+
+	input_set_drvdata(info->input_dev, info);
+	input_set_capability(info->input_dev, EV_FF, FF_RUMBLE);
+	INIT_WORK(&info->play_work, sc27xx_vibra_play_work);
+	info->enabled = false;
+
+	error = sc27xx_vibra_hw_init(info);
+	if (error) {
+		dev_err(&pdev->dev, "failed to initialize the vibrator.\n");
+		return error;
+	}
+
+	error = input_ff_create_memless(info->input_dev, NULL,
+					sc27xx_vibra_play);
+	if (error) {
+		dev_err(&pdev->dev, "failed to register vibrator to FF.\n");
+		return error;
+	}
+
+	error = input_register_device(info->input_dev);
+	if (error) {
+		dev_err(&pdev->dev, "failed to register input device.\n");
+		return error;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id sc27xx_vibra_of_match[] = {
+	{ .compatible = "sprd,sc2731-vibrator", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sc27xx_vibra_of_match);
+
+static struct platform_driver sc27xx_vibra_driver = {
+	.driver = {
+		.name = "sc27xx-vibrator",
+		.of_match_table = sc27xx_vibra_of_match,
+	},
+	.probe = sc27xx_vibra_probe,
+};
+
+module_platform_driver(sc27xx_vibra_driver);
+
+MODULE_DESCRIPTION("Spreadtrum SC27xx Vibrator Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Xiaotong Lu <xiaotong.lu@spreadtrum.com>");
diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h
index 599544c1a91c..243e0fa6e3e3 100644
--- a/drivers/input/mouse/elan_i2c.h
+++ b/drivers/input/mouse/elan_i2c.h
@@ -27,6 +27,8 @@
 #define ETP_DISABLE_POWER	0x0001
 #define ETP_PRESSURE_OFFSET	25
 
+#define ETP_CALIBRATE_MAX_LEN	3
+
 /* IAP Firmware handling */
 #define ETP_PRODUCT_ID_FORMAT_STRING	"%d.0"
 #define ETP_FW_NAME		"elan_i2c_" ETP_PRODUCT_ID_FORMAT_STRING ".bin"
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 8ff75114e762..f5ae24865355 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -613,7 +613,7 @@ static ssize_t calibrate_store(struct device *dev,
 	int tries = 20;
 	int retval;
 	int error;
-	u8 val[3];
+	u8 val[ETP_CALIBRATE_MAX_LEN];
 
 	retval = mutex_lock_interruptible(&data->sysfs_mutex);
 	if (retval)
@@ -1345,6 +1345,9 @@ static const struct acpi_device_id elan_acpi_id[] = {
 	{ "ELAN060C", 0 },
 	{ "ELAN0611", 0 },
 	{ "ELAN0612", 0 },
+	{ "ELAN0618", 0 },
+	{ "ELAN061D", 0 },
+	{ "ELAN0622", 0 },
 	{ "ELAN1000", 0 },
 	{ }
 };
diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c
index cfcb32559925..c060d270bc4d 100644
--- a/drivers/input/mouse/elan_i2c_smbus.c
+++ b/drivers/input/mouse/elan_i2c_smbus.c
@@ -56,7 +56,7 @@
 static int elan_smbus_initialize(struct i2c_client *client)
 {
 	u8 check[ETP_SMBUS_HELLOPACKET_LEN] = { 0x55, 0x55, 0x55, 0x55, 0x55 };
-	u8 values[ETP_SMBUS_HELLOPACKET_LEN] = { 0, 0, 0, 0, 0 };
+	u8 values[I2C_SMBUS_BLOCK_MAX] = {0};
 	int len, error;
 
 	/* Get hello packet */
@@ -117,12 +117,16 @@ static int elan_smbus_calibrate(struct i2c_client *client)
 static int elan_smbus_calibrate_result(struct i2c_client *client, u8 *val)
 {
 	int error;
+	u8 buf[I2C_SMBUS_BLOCK_MAX] = {0};
+
+	BUILD_BUG_ON(ETP_CALIBRATE_MAX_LEN > sizeof(buf));
 
 	error = i2c_smbus_read_block_data(client,
-					  ETP_SMBUS_CALIBRATE_QUERY, val);
+					  ETP_SMBUS_CALIBRATE_QUERY, buf);
 	if (error < 0)
 		return error;
 
+	memcpy(val, buf, ETP_CALIBRATE_MAX_LEN);
 	return 0;
 }
 
@@ -472,6 +476,8 @@ static int elan_smbus_get_report(struct i2c_client *client, u8 *report)
 {
 	int len;
 
+	BUILD_BUG_ON(I2C_SMBUS_BLOCK_MAX > ETP_SMBUS_REPORT_LEN);
+
 	len = i2c_smbus_read_block_data(client,
 					ETP_SMBUS_PACKET_QUERY,
 					&report[ETP_SMBUS_REPORT_OFFSET]);
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index fb4d902c4403..dd85b16dc6f8 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -799,7 +799,7 @@ static int elantech_packet_check_v4(struct psmouse *psmouse)
 	else if (ic_version == 7 && etd->info.samples[1] == 0x2A)
 		sanity_check = ((packet[3] & 0x1c) == 0x10);
 	else
-		sanity_check = ((packet[0] & 0x0c) == 0x04 &&
+		sanity_check = ((packet[0] & 0x08) == 0x00 &&
 				(packet[3] & 0x1c) == 0x10);
 
 	if (!sanity_check)
@@ -1175,6 +1175,12 @@ static const struct dmi_system_id elantech_dmi_has_middle_button[] = {
 	{ }
 };
 
+static const char * const middle_button_pnp_ids[] = {
+	"LEN2131", /* ThinkPad P52 w/ NFC */
+	"LEN2132", /* ThinkPad P52 */
+	NULL
+};
+
 /*
  * Set the appropriate event bits for the input subsystem
  */
@@ -1194,7 +1200,8 @@ static int elantech_set_input_params(struct psmouse *psmouse)
 	__clear_bit(EV_REL, dev->evbit);
 
 	__set_bit(BTN_LEFT, dev->keybit);
-	if (dmi_check_system(elantech_dmi_has_middle_button))
+	if (dmi_check_system(elantech_dmi_has_middle_button) ||
+			psmouse_matches_pnp_id(psmouse, middle_button_pnp_ids))
 		__set_bit(BTN_MIDDLE, dev->keybit);
 	__set_bit(BTN_RIGHT, dev->keybit);
 
diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c
index 5ff5b1952be0..d3ff1fc09af7 100644
--- a/drivers/input/mouse/psmouse-base.c
+++ b/drivers/input/mouse/psmouse-base.c
@@ -192,8 +192,8 @@ psmouse_ret_t psmouse_process_byte(struct psmouse *psmouse)
 			else
 				input_report_rel(dev, REL_WHEEL, -wheel);
 
-			input_report_key(dev, BTN_SIDE,  BIT(4));
-			input_report_key(dev, BTN_EXTRA, BIT(5));
+			input_report_key(dev, BTN_SIDE,  packet[3] & BIT(4));
+			input_report_key(dev, BTN_EXTRA, packet[3] & BIT(5));
 			break;
 		}
 		break;
@@ -203,13 +203,13 @@ psmouse_ret_t psmouse_process_byte(struct psmouse *psmouse)
 		input_report_rel(dev, REL_WHEEL, -(s8) packet[3]);
 
 		/* Extra buttons on Genius NewNet 3D */
-		input_report_key(dev, BTN_SIDE,  BIT(6));
-		input_report_key(dev, BTN_EXTRA, BIT(7));
+		input_report_key(dev, BTN_SIDE,  packet[0] & BIT(6));
+		input_report_key(dev, BTN_EXTRA, packet[0] & BIT(7));
 		break;
 
 	case PSMOUSE_THINKPS:
 		/* Extra button on ThinkingMouse */
-		input_report_key(dev, BTN_EXTRA, BIT(3));
+		input_report_key(dev, BTN_EXTRA, packet[0] & BIT(3));
 
 		/*
 		 * Without this bit of weirdness moving up gives wildly
@@ -223,7 +223,7 @@ psmouse_ret_t psmouse_process_byte(struct psmouse *psmouse)
 		 * Cortron PS2 Trackball reports SIDE button in the
 		 * 4th bit of the first byte.
 		 */
-		input_report_key(dev, BTN_SIDE, BIT(3));
+		input_report_key(dev, BTN_SIDE, packet[0] & BIT(3));
 		packet[0] |= BIT(3);
 		break;
 
diff --git a/drivers/input/rmi4/Kconfig b/drivers/input/rmi4/Kconfig
index 7172b88cd064..fad2eae4a118 100644
--- a/drivers/input/rmi4/Kconfig
+++ b/drivers/input/rmi4/Kconfig
@@ -3,6 +3,7 @@
 #
 config RMI4_CORE
 	tristate "Synaptics RMI4 bus support"
+	select IRQ_DOMAIN
 	help
 	  Say Y here if you want to support the Synaptics RMI4 bus.  This is
 	  required for all RMI4 device support.
diff --git a/drivers/input/rmi4/rmi_2d_sensor.c b/drivers/input/rmi4/rmi_2d_sensor.c
index 8bb866c7b985..8eeffa066022 100644
--- a/drivers/input/rmi4/rmi_2d_sensor.c
+++ b/drivers/input/rmi4/rmi_2d_sensor.c
@@ -32,15 +32,15 @@ void rmi_2d_sensor_abs_process(struct rmi_2d_sensor *sensor,
 	if (obj->type == RMI_2D_OBJECT_NONE)
 		return;
 
-	if (axis_align->swap_axes)
-		swap(obj->x, obj->y);
-
 	if (axis_align->flip_x)
 		obj->x = sensor->max_x - obj->x;
 
 	if (axis_align->flip_y)
 		obj->y = sensor->max_y - obj->y;
 
+	if (axis_align->swap_axes)
+		swap(obj->x, obj->y);
+
 	/*
 	 * Here checking if X offset or y offset are specified is
 	 * redundant. We just add the offsets or clip the values.
@@ -120,15 +120,15 @@ void rmi_2d_sensor_rel_report(struct rmi_2d_sensor *sensor, int x, int y)
 	x = min(RMI_2D_REL_POS_MAX, max(RMI_2D_REL_POS_MIN, (int)x));
 	y = min(RMI_2D_REL_POS_MAX, max(RMI_2D_REL_POS_MIN, (int)y));
 
-	if (axis_align->swap_axes)
-		swap(x, y);
-
 	if (axis_align->flip_x)
 		x = min(RMI_2D_REL_POS_MAX, -x);
 
 	if (axis_align->flip_y)
 		y = min(RMI_2D_REL_POS_MAX, -y);
 
+	if (axis_align->swap_axes)
+		swap(x, y);
+
 	if (x || y) {
 		input_report_rel(sensor->input, REL_X, x);
 		input_report_rel(sensor->input, REL_Y, y);
@@ -141,17 +141,10 @@ static void rmi_2d_sensor_set_input_params(struct rmi_2d_sensor *sensor)
 	struct input_dev *input = sensor->input;
 	int res_x;
 	int res_y;
+	int max_x, max_y;
 	int input_flags = 0;
 
 	if (sensor->report_abs) {
-		if (sensor->axis_align.swap_axes) {
-			swap(sensor->max_x, sensor->max_y);
-			swap(sensor->axis_align.clip_x_low,
-			     sensor->axis_align.clip_y_low);
-			swap(sensor->axis_align.clip_x_high,
-			     sensor->axis_align.clip_y_high);
-		}
-
 		sensor->min_x = sensor->axis_align.clip_x_low;
 		if (sensor->axis_align.clip_x_high)
 			sensor->max_x = min(sensor->max_x,
@@ -163,14 +156,19 @@ static void rmi_2d_sensor_set_input_params(struct rmi_2d_sensor *sensor)
 				sensor->axis_align.clip_y_high);
 
 		set_bit(EV_ABS, input->evbit);
-		input_set_abs_params(input, ABS_MT_POSITION_X, 0, sensor->max_x,
-					0, 0);
-		input_set_abs_params(input, ABS_MT_POSITION_Y, 0, sensor->max_y,
-					0, 0);
+
+		max_x = sensor->max_x;
+		max_y = sensor->max_y;
+		if (sensor->axis_align.swap_axes)
+			swap(max_x, max_y);
+		input_set_abs_params(input, ABS_MT_POSITION_X, 0, max_x, 0, 0);
+		input_set_abs_params(input, ABS_MT_POSITION_Y, 0, max_y, 0, 0);
 
 		if (sensor->x_mm && sensor->y_mm) {
 			res_x = (sensor->max_x - sensor->min_x) / sensor->x_mm;
 			res_y = (sensor->max_y - sensor->min_y) / sensor->y_mm;
+			if (sensor->axis_align.swap_axes)
+				swap(res_x, res_y);
 
 			input_abs_set_res(input, ABS_X, res_x);
 			input_abs_set_res(input, ABS_Y, res_y);
diff --git a/drivers/input/rmi4/rmi_bus.c b/drivers/input/rmi4/rmi_bus.c
index c5fa53adba8d..bd0d5ff01b08 100644
--- a/drivers/input/rmi4/rmi_bus.c
+++ b/drivers/input/rmi4/rmi_bus.c
@@ -9,6 +9,8 @@
 
 #include <linux/kernel.h>
 #include <linux/device.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/list.h>
 #include <linux/pm.h>
 #include <linux/rmi.h>
@@ -167,6 +169,39 @@ static inline void rmi_function_of_probe(struct rmi_function *fn)
 {}
 #endif
 
+static struct irq_chip rmi_irq_chip = {
+	.name = "rmi4",
+};
+
+static int rmi_create_function_irq(struct rmi_function *fn,
+				   struct rmi_function_handler *handler)
+{
+	struct rmi_driver_data *drvdata = dev_get_drvdata(&fn->rmi_dev->dev);
+	int i, error;
+
+	for (i = 0; i < fn->num_of_irqs; i++) {
+		set_bit(fn->irq_pos + i, fn->irq_mask);
+
+		fn->irq[i] = irq_create_mapping(drvdata->irqdomain,
+						fn->irq_pos + i);
+
+		irq_set_chip_data(fn->irq[i], fn);
+		irq_set_chip_and_handler(fn->irq[i], &rmi_irq_chip,
+					 handle_simple_irq);
+		irq_set_nested_thread(fn->irq[i], 1);
+
+		error = devm_request_threaded_irq(&fn->dev, fn->irq[i], NULL,
+					handler->attention, IRQF_ONESHOT,
+					dev_name(&fn->dev), fn);
+		if (error) {
+			dev_err(&fn->dev, "Error %d registering IRQ\n", error);
+			return error;
+		}
+	}
+
+	return 0;
+}
+
 static int rmi_function_probe(struct device *dev)
 {
 	struct rmi_function *fn = to_rmi_function(dev);
@@ -178,7 +213,14 @@ static int rmi_function_probe(struct device *dev)
 
 	if (handler->probe) {
 		error = handler->probe(fn);
-		return error;
+		if (error)
+			return error;
+	}
+
+	if (fn->num_of_irqs && handler->attention) {
+		error = rmi_create_function_irq(fn, handler);
+		if (error)
+			return error;
 	}
 
 	return 0;
@@ -230,12 +272,18 @@ err_put_device:
 
 void rmi_unregister_function(struct rmi_function *fn)
 {
+	int i;
+
 	rmi_dbg(RMI_DEBUG_CORE, &fn->dev, "Unregistering F%02X.\n",
 			fn->fd.function_number);
 
 	device_del(&fn->dev);
 	of_node_put(fn->dev.of_node);
 	put_device(&fn->dev);
+
+	for (i = 0; i < fn->num_of_irqs; i++)
+		irq_dispose_mapping(fn->irq[i]);
+
 }
 
 /**
diff --git a/drivers/input/rmi4/rmi_bus.h b/drivers/input/rmi4/rmi_bus.h
index b7625a9ac66a..96383eab41ba 100644
--- a/drivers/input/rmi4/rmi_bus.h
+++ b/drivers/input/rmi4/rmi_bus.h
@@ -14,6 +14,12 @@
 
 struct rmi_device;
 
+/*
+ * The interrupt source count in the function descriptor can represent up to
+ * 6 interrupt sources in the normal manner.
+ */
+#define RMI_FN_MAX_IRQS	6
+
 /**
  * struct rmi_function - represents the implementation of an RMI4
  * function for a particular device (basically, a driver for that RMI4 function)
@@ -26,6 +32,7 @@ struct rmi_device;
  * @irq_pos: The position in the irq bitfield this function holds
  * @irq_mask: For convenience, can be used to mask IRQ bits off during ATTN
  * interrupt handling.
+ * @irqs: assigned virq numbers (up to num_of_irqs)
  *
  * @node: entry in device's list of functions
  */
@@ -36,6 +43,7 @@ struct rmi_function {
 	struct list_head node;
 
 	unsigned int num_of_irqs;
+	int irq[RMI_FN_MAX_IRQS];
 	unsigned int irq_pos;
 	unsigned long irq_mask[];
 };
@@ -76,7 +84,7 @@ struct rmi_function_handler {
 	void (*remove)(struct rmi_function *fn);
 	int (*config)(struct rmi_function *fn);
 	int (*reset)(struct rmi_function *fn);
-	int (*attention)(struct rmi_function *fn, unsigned long *irq_bits);
+	irqreturn_t (*attention)(int irq, void *ctx);
 	int (*suspend)(struct rmi_function *fn);
 	int (*resume)(struct rmi_function *fn);
 };
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 7d29053dfb0f..fc3ab93b7aea 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -21,6 +21,7 @@
 #include <linux/pm.h>
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <linux/irqdomain.h>
 #include <uapi/linux/input.h>
 #include <linux/rmi.h>
 #include "rmi_bus.h"
@@ -127,28 +128,11 @@ static int rmi_driver_process_config_requests(struct rmi_device *rmi_dev)
 	return 0;
 }
 
-static void process_one_interrupt(struct rmi_driver_data *data,
-				  struct rmi_function *fn)
-{
-	struct rmi_function_handler *fh;
-
-	if (!fn || !fn->dev.driver)
-		return;
-
-	fh = to_rmi_function_handler(fn->dev.driver);
-	if (fh->attention) {
-		bitmap_and(data->fn_irq_bits, data->irq_status, fn->irq_mask,
-				data->irq_count);
-		if (!bitmap_empty(data->fn_irq_bits, data->irq_count))
-			fh->attention(fn, data->fn_irq_bits);
-	}
-}
-
 static int rmi_process_interrupt_requests(struct rmi_device *rmi_dev)
 {
 	struct rmi_driver_data *data = dev_get_drvdata(&rmi_dev->dev);
 	struct device *dev = &rmi_dev->dev;
-	struct rmi_function *entry;
+	int i;
 	int error;
 
 	if (!data)
@@ -173,16 +157,8 @@ static int rmi_process_interrupt_requests(struct rmi_device *rmi_dev)
 	 */
 	mutex_unlock(&data->irq_mutex);
 
-	/*
-	 * It would be nice to be able to use irq_chip to handle these
-	 * nested IRQs.  Unfortunately, most of the current customers for
-	 * this driver are using older kernels (3.0.x) that don't support
-	 * the features required for that.  Once they've shifted to more
-	 * recent kernels (say, 3.3 and higher), this should be switched to
-	 * use irq_chip.
-	 */
-	list_for_each_entry(entry, &data->function_list, node)
-		process_one_interrupt(data, entry);
+	for_each_set_bit(i, data->irq_status, data->irq_count)
+		handle_nested_irq(irq_find_mapping(data->irqdomain, i));
 
 	if (data->input)
 		input_sync(data->input);
@@ -1001,9 +977,13 @@ EXPORT_SYMBOL_GPL(rmi_driver_resume);
 static int rmi_driver_remove(struct device *dev)
 {
 	struct rmi_device *rmi_dev = to_rmi_device(dev);
+	struct rmi_driver_data *data = dev_get_drvdata(&rmi_dev->dev);
 
 	rmi_disable_irq(rmi_dev, false);
 
+	irq_domain_remove(data->irqdomain);
+	data->irqdomain = NULL;
+
 	rmi_f34_remove_sysfs(rmi_dev);
 	rmi_free_function_list(rmi_dev);
 
@@ -1035,7 +1015,8 @@ int rmi_probe_interrupts(struct rmi_driver_data *data)
 {
 	struct rmi_device *rmi_dev = data->rmi_dev;
 	struct device *dev = &rmi_dev->dev;
-	int irq_count;
+	struct fwnode_handle *fwnode = rmi_dev->xport->dev->fwnode;
+	int irq_count = 0;
 	size_t size;
 	int retval;
 
@@ -1046,7 +1027,6 @@ int rmi_probe_interrupts(struct rmi_driver_data *data)
 	 * being accessed.
 	 */
 	rmi_dbg(RMI_DEBUG_CORE, dev, "%s: Counting IRQs.\n", __func__);
-	irq_count = 0;
 	data->bootloader_mode = false;
 
 	retval = rmi_scan_pdt(rmi_dev, &irq_count, rmi_count_irqs);
@@ -1058,6 +1038,15 @@ int rmi_probe_interrupts(struct rmi_driver_data *data)
 	if (data->bootloader_mode)
 		dev_warn(dev, "Device in bootloader mode.\n");
 
+	/* Allocate and register a linear revmap irq_domain */
+	data->irqdomain = irq_domain_create_linear(fwnode, irq_count,
+						   &irq_domain_simple_ops,
+						   data);
+	if (!data->irqdomain) {
+		dev_err(&rmi_dev->dev, "Failed to create IRQ domain\n");
+		return -ENOMEM;
+	}
+
 	data->irq_count = irq_count;
 	data->num_of_irq_regs = (data->irq_count + 7) / 8;
 
@@ -1080,10 +1069,9 @@ int rmi_init_functions(struct rmi_driver_data *data)
 {
 	struct rmi_device *rmi_dev = data->rmi_dev;
 	struct device *dev = &rmi_dev->dev;
-	int irq_count;
+	int irq_count = 0;
 	int retval;
 
-	irq_count = 0;
 	rmi_dbg(RMI_DEBUG_CORE, dev, "%s: Creating functions.\n", __func__);
 	retval = rmi_scan_pdt(rmi_dev, &irq_count, rmi_create_function);
 	if (retval < 0) {
diff --git a/drivers/input/rmi4/rmi_f01.c b/drivers/input/rmi4/rmi_f01.c
index 8a07ae147df6..4edaa14fe878 100644
--- a/drivers/input/rmi4/rmi_f01.c
+++ b/drivers/input/rmi4/rmi_f01.c
@@ -681,9 +681,9 @@ static int rmi_f01_resume(struct rmi_function *fn)
 	return 0;
 }
 
-static int rmi_f01_attention(struct rmi_function *fn,
-			     unsigned long *irq_bits)
+static irqreturn_t rmi_f01_attention(int irq, void *ctx)
 {
+	struct rmi_function *fn = ctx;
 	struct rmi_device *rmi_dev = fn->rmi_dev;
 	int error;
 	u8 device_status;
@@ -692,7 +692,7 @@ static int rmi_f01_attention(struct rmi_function *fn,
 	if (error) {
 		dev_err(&fn->dev,
 			"Failed to read device status: %d.\n", error);
-		return error;
+		return IRQ_RETVAL(error);
 	}
 
 	if (RMI_F01_STATUS_BOOTLOADER(device_status))
@@ -704,11 +704,11 @@ static int rmi_f01_attention(struct rmi_function *fn,
 		error = rmi_dev->driver->reset_handler(rmi_dev);
 		if (error) {
 			dev_err(&fn->dev, "Device reset failed: %d\n", error);
-			return error;
+			return IRQ_RETVAL(error);
 		}
 	}
 
-	return 0;
+	return IRQ_HANDLED;
 }
 
 struct rmi_function_handler rmi_f01_handler = {
diff --git a/drivers/input/rmi4/rmi_f03.c b/drivers/input/rmi4/rmi_f03.c
index 88822196d6b7..aaa1edc95522 100644
--- a/drivers/input/rmi4/rmi_f03.c
+++ b/drivers/input/rmi4/rmi_f03.c
@@ -244,8 +244,9 @@ static int rmi_f03_config(struct rmi_function *fn)
 	return 0;
 }
 
-static int rmi_f03_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f03_attention(int irq, void *ctx)
 {
+	struct rmi_function *fn = ctx;
 	struct rmi_device *rmi_dev = fn->rmi_dev;
 	struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
 	struct f03_data *f03 = dev_get_drvdata(&fn->dev);
@@ -262,7 +263,7 @@ static int rmi_f03_attention(struct rmi_function *fn, unsigned long *irq_bits)
 		/* First grab the data passed by the transport device */
 		if (drvdata->attn_data.size < ob_len) {
 			dev_warn(&fn->dev, "F03 interrupted, but data is missing!\n");
-			return 0;
+			return IRQ_HANDLED;
 		}
 
 		memcpy(obs, drvdata->attn_data.data, ob_len);
@@ -277,7 +278,7 @@ static int rmi_f03_attention(struct rmi_function *fn, unsigned long *irq_bits)
 				"%s: Failed to read F03 output buffers: %d\n",
 				__func__, error);
 			serio_interrupt(f03->serio, 0, SERIO_TIMEOUT);
-			return error;
+			return IRQ_RETVAL(error);
 		}
 	}
 
@@ -303,7 +304,7 @@ static int rmi_f03_attention(struct rmi_function *fn, unsigned long *irq_bits)
 		serio_interrupt(f03->serio, ob_data, serio_flags);
 	}
 
-	return 0;
+	return IRQ_HANDLED;
 }
 
 static void rmi_f03_remove(struct rmi_function *fn)
diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c
index 12a233251793..df64d6aed4f7 100644
--- a/drivers/input/rmi4/rmi_f11.c
+++ b/drivers/input/rmi4/rmi_f11.c
@@ -570,9 +570,7 @@ static inline u8 rmi_f11_parse_finger_state(const u8 *f_state, u8 n_finger)
 }
 
 static void rmi_f11_finger_handler(struct f11_data *f11,
-				   struct rmi_2d_sensor *sensor,
-				   unsigned long *irq_bits, int num_irq_regs,
-				   int size)
+				   struct rmi_2d_sensor *sensor, int size)
 {
 	const u8 *f_state = f11->data.f_state;
 	u8 finger_state;
@@ -581,12 +579,7 @@ static void rmi_f11_finger_handler(struct f11_data *f11,
 	int rel_fingers;
 	int abs_size = sensor->nbr_fingers * RMI_F11_ABS_BYTES;
 
-	int abs_bits = bitmap_and(f11->result_bits, irq_bits, f11->abs_mask,
-				  num_irq_regs * 8);
-	int rel_bits = bitmap_and(f11->result_bits, irq_bits, f11->rel_mask,
-				  num_irq_regs * 8);
-
-	if (abs_bits) {
+	if (sensor->report_abs) {
 		if (abs_size > size)
 			abs_fingers = size / RMI_F11_ABS_BYTES;
 		else
@@ -604,19 +597,7 @@ static void rmi_f11_finger_handler(struct f11_data *f11,
 			rmi_f11_abs_pos_process(f11, sensor, &sensor->objs[i],
 							finger_state, i);
 		}
-	}
 
-	if (rel_bits) {
-		if ((abs_size + sensor->nbr_fingers * RMI_F11_REL_BYTES) > size)
-			rel_fingers = (size - abs_size) / RMI_F11_REL_BYTES;
-		else
-			rel_fingers = sensor->nbr_fingers;
-
-		for (i = 0; i < rel_fingers; i++)
-			rmi_f11_rel_pos_report(f11, i);
-	}
-
-	if (abs_bits) {
 		/*
 		 * the absolute part is made in 2 parts to allow the kernel
 		 * tracking to take place.
@@ -638,7 +619,16 @@ static void rmi_f11_finger_handler(struct f11_data *f11,
 		}
 
 		input_mt_sync_frame(sensor->input);
+	} else if (sensor->report_rel) {
+		if ((abs_size + sensor->nbr_fingers * RMI_F11_REL_BYTES) > size)
+			rel_fingers = (size - abs_size) / RMI_F11_REL_BYTES;
+		else
+			rel_fingers = sensor->nbr_fingers;
+
+		for (i = 0; i < rel_fingers; i++)
+			rmi_f11_rel_pos_report(f11, i);
 	}
+
 }
 
 static int f11_2d_construct_data(struct f11_data *f11)
@@ -1276,8 +1266,9 @@ static int rmi_f11_config(struct rmi_function *fn)
 	return 0;
 }
 
-static int rmi_f11_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f11_attention(int irq, void *ctx)
 {
+	struct rmi_function *fn = ctx;
 	struct rmi_device *rmi_dev = fn->rmi_dev;
 	struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
 	struct f11_data *f11 = dev_get_drvdata(&fn->dev);
@@ -1303,13 +1294,12 @@ static int rmi_f11_attention(struct rmi_function *fn, unsigned long *irq_bits)
 				data_base_addr, f11->sensor.data_pkt,
 				f11->sensor.pkt_size);
 		if (error < 0)
-			return error;
+			return IRQ_RETVAL(error);
 	}
 
-	rmi_f11_finger_handler(f11, &f11->sensor, irq_bits,
-				drvdata->num_of_irq_regs, valid_bytes);
+	rmi_f11_finger_handler(f11, &f11->sensor, valid_bytes);
 
-	return 0;
+	return IRQ_HANDLED;
 }
 
 static int rmi_f11_resume(struct rmi_function *fn)
diff --git a/drivers/input/rmi4/rmi_f12.c b/drivers/input/rmi4/rmi_f12.c
index a3d1aa88f2a9..5c7f48915779 100644
--- a/drivers/input/rmi4/rmi_f12.c
+++ b/drivers/input/rmi4/rmi_f12.c
@@ -197,10 +197,10 @@ static void rmi_f12_process_objects(struct f12_data *f12, u8 *data1, int size)
 		rmi_2d_sensor_abs_report(sensor, &sensor->objs[i], i);
 }
 
-static int rmi_f12_attention(struct rmi_function *fn,
-			     unsigned long *irq_nr_regs)
+static irqreturn_t rmi_f12_attention(int irq, void *ctx)
 {
 	int retval;
+	struct rmi_function *fn = ctx;
 	struct rmi_device *rmi_dev = fn->rmi_dev;
 	struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
 	struct f12_data *f12 = dev_get_drvdata(&fn->dev);
@@ -222,7 +222,7 @@ static int rmi_f12_attention(struct rmi_function *fn,
 		if (retval < 0) {
 			dev_err(&fn->dev, "Failed to read object data. Code: %d.\n",
 				retval);
-			return retval;
+			return IRQ_RETVAL(retval);
 		}
 	}
 
@@ -232,7 +232,7 @@ static int rmi_f12_attention(struct rmi_function *fn,
 
 	input_mt_sync_frame(sensor->input);
 
-	return 0;
+	return IRQ_HANDLED;
 }
 
 static int rmi_f12_write_control_regs(struct rmi_function *fn)
diff --git a/drivers/input/rmi4/rmi_f30.c b/drivers/input/rmi4/rmi_f30.c
index 82e0f0d43d55..5e3ed5ac0c3e 100644
--- a/drivers/input/rmi4/rmi_f30.c
+++ b/drivers/input/rmi4/rmi_f30.c
@@ -122,8 +122,9 @@ static void rmi_f30_report_button(struct rmi_function *fn,
 	}
 }
 
-static int rmi_f30_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f30_attention(int irq, void *ctx)
 {
+	struct rmi_function *fn = ctx;
 	struct f30_data *f30 = dev_get_drvdata(&fn->dev);
 	struct rmi_driver_data *drvdata = dev_get_drvdata(&fn->rmi_dev->dev);
 	int error;
@@ -134,7 +135,7 @@ static int rmi_f30_attention(struct rmi_function *fn, unsigned long *irq_bits)
 		if (drvdata->attn_data.size < f30->register_count) {
 			dev_warn(&fn->dev,
 				 "F30 interrupted, but data is missing\n");
-			return 0;
+			return IRQ_HANDLED;
 		}
 		memcpy(f30->data_regs, drvdata->attn_data.data,
 			f30->register_count);
@@ -147,7 +148,7 @@ static int rmi_f30_attention(struct rmi_function *fn, unsigned long *irq_bits)
 			dev_err(&fn->dev,
 				"%s: Failed to read F30 data registers: %d\n",
 				__func__, error);
-			return error;
+			return IRQ_RETVAL(error);
 		}
 	}
 
@@ -159,7 +160,7 @@ static int rmi_f30_attention(struct rmi_function *fn, unsigned long *irq_bits)
 			rmi_f03_commit_buttons(f30->f03);
 	}
 
-	return 0;
+	return IRQ_HANDLED;
 }
 
 static int rmi_f30_config(struct rmi_function *fn)
diff --git a/drivers/input/rmi4/rmi_f34.c b/drivers/input/rmi4/rmi_f34.c
index f1f5ac539d5d..87a7d4ba382d 100644
--- a/drivers/input/rmi4/rmi_f34.c
+++ b/drivers/input/rmi4/rmi_f34.c
@@ -100,8 +100,9 @@ static int rmi_f34_command(struct f34_data *f34, u8 command,
 	return 0;
 }
 
-static int rmi_f34_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f34_attention(int irq, void *ctx)
 {
+	struct rmi_function *fn = ctx;
 	struct f34_data *f34 = dev_get_drvdata(&fn->dev);
 	int ret;
 	u8 status;
@@ -126,7 +127,7 @@ static int rmi_f34_attention(struct rmi_function *fn, unsigned long *irq_bits)
 			complete(&f34->v7.cmd_done);
 	}
 
-	return 0;
+	return IRQ_HANDLED;
 }
 
 static int rmi_f34_write_blocks(struct f34_data *f34, const void *data,
diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c
index e8a59d164019..a6f515bcab22 100644
--- a/drivers/input/rmi4/rmi_f54.c
+++ b/drivers/input/rmi4/rmi_f54.c
@@ -610,11 +610,6 @@ error:
 	mutex_unlock(&f54->data_mutex);
 }
 
-static int rmi_f54_attention(struct rmi_function *fn, unsigned long *irqbits)
-{
-	return 0;
-}
-
 static int rmi_f54_config(struct rmi_function *fn)
 {
 	struct rmi_driver *drv = fn->rmi_dev->driver;
@@ -756,6 +751,5 @@ struct rmi_function_handler rmi_f54_handler = {
 	.func = 0x54,
 	.probe = rmi_f54_probe,
 	.config = rmi_f54_config,
-	.attention = rmi_f54_attention,
 	.remove = rmi_f54_remove,
 };
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index b353d494ad40..136f6e7bf797 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -527,6 +527,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"),
 		},
 	},
+	{
+		/* Lenovo LaVie Z */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c
index ff7043f74a3d..d196ac3d8b8c 100644
--- a/drivers/input/touchscreen/silead.c
+++ b/drivers/input/touchscreen/silead.c
@@ -603,6 +603,7 @@ static const struct acpi_device_id silead_ts_acpi_match[] = {
 	{ "GSL3692", 0 },
 	{ "MSSL1680", 0 },
 	{ "MSSL0001", 0 },
+	{ "MSSL0002", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, silead_ts_acpi_match);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index e055d228bfb9..689ffe538370 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -142,7 +142,6 @@ config DMAR_TABLE
 config INTEL_IOMMU
 	bool "Support for Intel IOMMU using DMA Remapping Devices"
 	depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC)
-	select DMA_DIRECT_OPS
 	select IOMMU_API
 	select IOMMU_IOVA
 	select NEED_DMA_MAP_STATE
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index ddcbbdb5d658..511ff9a1d6d9 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -367,6 +367,9 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
 		iova_len = roundup_pow_of_two(iova_len);
 
+	if (dev->bus_dma_mask)
+		dma_limit &= dev->bus_dma_mask;
+
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, domain->geometry.aperture_end);
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 14e4b3722428..115ff26e9ced 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -31,7 +31,6 @@
 #include <linux/pci.h>
 #include <linux/dmar.h>
 #include <linux/dma-mapping.h>
-#include <linux/dma-direct.h>
 #include <linux/mempool.h>
 #include <linux/memory.h>
 #include <linux/cpu.h>
@@ -485,14 +484,37 @@ static int dmar_forcedac;
 static int intel_iommu_strict;
 static int intel_iommu_superpage = 1;
 static int intel_iommu_ecs = 1;
+static int intel_iommu_pasid28;
 static int iommu_identity_mapping;
 
 #define IDENTMAP_ALL		1
 #define IDENTMAP_GFX		2
 #define IDENTMAP_AZALIA		4
 
-#define ecs_enabled(iommu)	(intel_iommu_ecs && ecap_ecs(iommu->ecap))
-#define pasid_enabled(iommu)	(ecs_enabled(iommu) && ecap_pasid(iommu->ecap))
+/* Broadwell and Skylake have broken ECS support — normal so-called "second
+ * level" translation of DMA requests-without-PASID doesn't actually happen
+ * unless you also set the NESTE bit in an extended context-entry. Which of
+ * course means that SVM doesn't work because it's trying to do nested
+ * translation of the physical addresses it finds in the process page tables,
+ * through the IOVA->phys mapping found in the "second level" page tables.
+ *
+ * The VT-d specification was retroactively changed to change the definition
+ * of the capability bits and pretend that Broadwell/Skylake never happened...
+ * but unfortunately the wrong bit was changed. It's ECS which is broken, but
+ * for some reason it was the PASID capability bit which was redefined (from
+ * bit 28 on BDW/SKL to bit 40 in future).
+ *
+ * So our test for ECS needs to eschew those implementations which set the old
+ * PASID capabiity bit 28, since those are the ones on which ECS is broken.
+ * Unless we are working around the 'pasid28' limitations, that is, by putting
+ * the device into passthrough mode for normal DMA and thus masking the bug.
+ */
+#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
+			    (intel_iommu_pasid28 || !ecap_broken_pasid(iommu->ecap)))
+/* PASID support is thus enabled if ECS is enabled and *either* of the old
+ * or new capability bits are set. */
+#define pasid_enabled(iommu) (ecs_enabled(iommu) &&			\
+			      (ecap_pasid(iommu->ecap) || ecap_broken_pasid(iommu->ecap)))
 
 int intel_iommu_gfx_mapped;
 EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
@@ -555,6 +577,11 @@ static int __init intel_iommu_setup(char *str)
 			printk(KERN_INFO
 				"Intel-IOMMU: disable extended context table support\n");
 			intel_iommu_ecs = 0;
+		} else if (!strncmp(str, "pasid28", 7)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: enable pre-production PASID support\n");
+			intel_iommu_pasid28 = 1;
+			iommu_identity_mapping |= IDENTMAP_GFX;
 		} else if (!strncmp(str, "tboot_noforce", 13)) {
 			printk(KERN_INFO
 				"Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
@@ -3713,30 +3740,61 @@ static void *intel_alloc_coherent(struct device *dev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flags,
 				  unsigned long attrs)
 {
-	void *vaddr;
+	struct page *page = NULL;
+	int order;
 
-	vaddr = dma_direct_alloc(dev, size, dma_handle, flags, attrs);
-	if (iommu_no_mapping(dev) || !vaddr)
-		return vaddr;
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
 
-	*dma_handle = __intel_map_single(dev, virt_to_phys(vaddr),
-			PAGE_ALIGN(size), DMA_BIDIRECTIONAL,
-			dev->coherent_dma_mask);
-	if (!*dma_handle)
-		goto out_free_pages;
-	return vaddr;
+	if (!iommu_no_mapping(dev))
+		flags &= ~(GFP_DMA | GFP_DMA32);
+	else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) {
+		if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
+			flags |= GFP_DMA;
+		else
+			flags |= GFP_DMA32;
+	}
+
+	if (gfpflags_allow_blocking(flags)) {
+		unsigned int count = size >> PAGE_SHIFT;
+
+		page = dma_alloc_from_contiguous(dev, count, order, flags);
+		if (page && iommu_no_mapping(dev) &&
+		    page_to_phys(page) + size > dev->coherent_dma_mask) {
+			dma_release_from_contiguous(dev, page, count);
+			page = NULL;
+		}
+	}
+
+	if (!page)
+		page = alloc_pages(flags, order);
+	if (!page)
+		return NULL;
+	memset(page_address(page), 0, size);
+
+	*dma_handle = __intel_map_single(dev, page_to_phys(page), size,
+					 DMA_BIDIRECTIONAL,
+					 dev->coherent_dma_mask);
+	if (*dma_handle)
+		return page_address(page);
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, order);
 
-out_free_pages:
-	dma_direct_free(dev, size, vaddr, *dma_handle, attrs);
 	return NULL;
 }
 
 static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
 				dma_addr_t dma_handle, unsigned long attrs)
 {
-	if (!iommu_no_mapping(dev))
-		intel_unmap(dev, dma_handle, PAGE_ALIGN(size));
-	dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+	int order;
+	struct page *page = virt_to_page(vaddr);
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	intel_unmap(dev, dma_handle, size);
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, order);
 }
 
 static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index e9233db16e03..d564d21245c5 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -8,7 +8,7 @@ config ARM_GIC
 	bool
 	select IRQ_DOMAIN
 	select IRQ_DOMAIN_HIERARCHY
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
 config ARM_GIC_PM
@@ -34,7 +34,7 @@ config GIC_NON_BANKED
 config ARM_GIC_V3
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select IRQ_DOMAIN_HIERARCHY
 	select PARTITION_PERCPU
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
@@ -66,7 +66,7 @@ config ARM_NVIC
 config ARM_VIC
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config ARM_VIC_NR
 	int
@@ -93,14 +93,14 @@ config ATMEL_AIC_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config ATMEL_AIC5_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config I8259
@@ -137,7 +137,7 @@ config DW_APB_ICTL
 config FARADAY_FTINTC010
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config HISILICON_IRQ_MBIGEN
@@ -162,7 +162,7 @@ config CLPS711X_IRQCHIP
 	bool
 	depends on ARCH_CLPS711X
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 	default y
 
@@ -181,7 +181,7 @@ config OMAP_IRQCHIP
 config ORION_IRQCHIP
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config PIC32_EVIC
 	bool
diff --git a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
index 4eca5c763766..606efa64adff 100644
--- a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
@@ -45,6 +45,9 @@ static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain,
 	 */
 	info->scratchpad[0].ul = mc_bus_dev->icid;
 	msi_info = msi_get_domain_info(msi_domain->parent);
+
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(msi_domain->parent, dev, nvec, info);
 }
 
diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
index 25a98de5cfb2..8d6d009d1d58 100644
--- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
@@ -66,7 +66,7 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 {
 	struct pci_dev *pdev, *alias_dev;
 	struct msi_domain_info *msi_info;
-	int alias_count = 0;
+	int alias_count = 0, minnvec = 1;
 
 	if (!dev_is_pci(dev))
 		return -EINVAL;
@@ -86,8 +86,18 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev);
 
-	return msi_info->ops->msi_prepare(domain->parent,
-					  dev, max(nvec, alias_count), info);
+	/*
+	 * Always allocate a power of 2, and special case device 0 for
+	 * broken systems where the DevID is not wired (and all devices
+	 * appear as DevID 0). For that reason, we generously allocate a
+	 * minimum of 32 MSIs for DevID 0. If you want more because all
+	 * your devices are aliasing to DevID 0, consider fixing your HW.
+	 */
+	nvec = max(nvec, alias_count);
+	if (!info->scratchpad[0].ul)
+		minnvec = 32;
+	nvec = max_t(int, minnvec, roundup_pow_of_two(nvec));
+	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
 }
 
 static struct msi_domain_ops its_pci_msi_ops = {
diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
index 8881a053c173..7b8e87b493fe 100644
--- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
@@ -73,6 +73,8 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = dev_id;
 
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(domain->parent,
 					  dev, nvec, info);
 }
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d7842d312d3e..316a57530f6d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -23,6 +23,8 @@
 #include <linux/dma-iommu.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
+#include <linux/list.h>
+#include <linux/list_sort.h>
 #include <linux/log2.h>
 #include <linux/mm.h>
 #include <linux/msi.h>
@@ -160,7 +162,7 @@ static struct {
 } vpe_proxy;
 
 static LIST_HEAD(its_nodes);
-static DEFINE_SPINLOCK(its_lock);
+static DEFINE_RAW_SPINLOCK(its_lock);
 static struct rdists *gic_rdists;
 static struct irq_domain *its_parent;
 
@@ -1421,112 +1423,176 @@ static struct irq_chip its_irq_chip = {
 	.irq_set_vcpu_affinity	= its_irq_set_vcpu_affinity,
 };
 
+
 /*
  * How we allocate LPIs:
  *
- * The GIC has id_bits bits for interrupt identifiers. From there, we
- * must subtract 8192 which are reserved for SGIs/PPIs/SPIs. Then, as
- * we allocate LPIs by chunks of 32, we can shift the whole thing by 5
- * bits to the right.
+ * lpi_range_list contains ranges of LPIs that are to available to
+ * allocate from. To allocate LPIs, just pick the first range that
+ * fits the required allocation, and reduce it by the required
+ * amount. Once empty, remove the range from the list.
+ *
+ * To free a range of LPIs, add a free range to the list, sort it and
+ * merge the result if the new range happens to be adjacent to an
+ * already free block.
  *
- * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations.
+ * The consequence of the above is that allocation is cost is low, but
+ * freeing is expensive. We assumes that freeing rarely occurs.
  */
-#define IRQS_PER_CHUNK_SHIFT	5
-#define IRQS_PER_CHUNK		(1UL << IRQS_PER_CHUNK_SHIFT)
-#define ITS_MAX_LPI_NRBITS	16 /* 64K LPIs */
 
-static unsigned long *lpi_bitmap;
-static u32 lpi_chunks;
-static DEFINE_SPINLOCK(lpi_lock);
+static DEFINE_MUTEX(lpi_range_lock);
+static LIST_HEAD(lpi_range_list);
+
+struct lpi_range {
+	struct list_head	entry;
+	u32			base_id;
+	u32			span;
+};
 
-static int its_lpi_to_chunk(int lpi)
+static struct lpi_range *mk_lpi_range(u32 base, u32 span)
 {
-	return (lpi - 8192) >> IRQS_PER_CHUNK_SHIFT;
+	struct lpi_range *range;
+
+	range = kzalloc(sizeof(*range), GFP_KERNEL);
+	if (range) {
+		INIT_LIST_HEAD(&range->entry);
+		range->base_id = base;
+		range->span = span;
+	}
+
+	return range;
 }
 
-static int its_chunk_to_lpi(int chunk)
+static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
-	return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192;
+	struct lpi_range *ra, *rb;
+
+	ra = container_of(a, struct lpi_range, entry);
+	rb = container_of(b, struct lpi_range, entry);
+
+	return rb->base_id - ra->base_id;
 }
 
-static int __init its_lpi_init(u32 id_bits)
+static void merge_lpi_ranges(void)
 {
-	lpi_chunks = its_lpi_to_chunk(1UL << id_bits);
+	struct lpi_range *range, *tmp;
 
-	lpi_bitmap = kcalloc(BITS_TO_LONGS(lpi_chunks), sizeof(long),
-			     GFP_KERNEL);
-	if (!lpi_bitmap) {
-		lpi_chunks = 0;
-		return -ENOMEM;
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (!list_is_last(&range->entry, &lpi_range_list) &&
+		    (tmp->base_id == (range->base_id + range->span))) {
+			tmp->base_id = range->base_id;
+			tmp->span += range->span;
+			list_del(&range->entry);
+			kfree(range);
+		}
 	}
+}
 
-	pr_info("ITS: Allocated %d chunks for LPIs\n", (int)lpi_chunks);
-	return 0;
+static int alloc_lpi_range(u32 nr_lpis, u32 *base)
+{
+	struct lpi_range *range, *tmp;
+	int err = -ENOSPC;
+
+	mutex_lock(&lpi_range_lock);
+
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (range->span >= nr_lpis) {
+			*base = range->base_id;
+			range->base_id += nr_lpis;
+			range->span -= nr_lpis;
+
+			if (range->span == 0) {
+				list_del(&range->entry);
+				kfree(range);
+			}
+
+			err = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&lpi_range_lock);
+
+	pr_debug("ITS: alloc %u:%u\n", *base, nr_lpis);
+	return err;
 }
 
-static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids)
+static int free_lpi_range(u32 base, u32 nr_lpis)
 {
-	unsigned long *bitmap = NULL;
-	int chunk_id;
-	int nr_chunks;
-	int i;
+	struct lpi_range *new;
+	int err = 0;
+
+	mutex_lock(&lpi_range_lock);
+
+	new = mk_lpi_range(base, nr_lpis);
+	if (!new) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	list_add(&new->entry, &lpi_range_list);
+	list_sort(NULL, &lpi_range_list, lpi_range_cmp);
+	merge_lpi_ranges();
+out:
+	mutex_unlock(&lpi_range_lock);
+	return err;
+}
+
+static int __init its_lpi_init(u32 id_bits)
+{
+	u32 lpis = (1UL << id_bits) - 8192;
+	u32 numlpis;
+	int err;
+
+	numlpis = 1UL << GICD_TYPER_NUM_LPIS(gic_rdists->gicd_typer);
+
+	if (numlpis > 2 && !WARN_ON(numlpis > lpis)) {
+		lpis = numlpis;
+		pr_info("ITS: Using hypervisor restricted LPI range [%u]\n",
+			lpis);
+	}
 
-	nr_chunks = DIV_ROUND_UP(nr_irqs, IRQS_PER_CHUNK);
+	/*
+	 * Initializing the allocator is just the same as freeing the
+	 * full range of LPIs.
+	 */
+	err = free_lpi_range(8192, lpis);
+	pr_debug("ITS: Allocator initialized for %u LPIs\n", lpis);
+	return err;
+}
 
-	spin_lock(&lpi_lock);
+static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids)
+{
+	unsigned long *bitmap = NULL;
+	int err = 0;
 
 	do {
-		chunk_id = bitmap_find_next_zero_area(lpi_bitmap, lpi_chunks,
-						      0, nr_chunks, 0);
-		if (chunk_id < lpi_chunks)
+		err = alloc_lpi_range(nr_irqs, base);
+		if (!err)
 			break;
 
-		nr_chunks--;
-	} while (nr_chunks > 0);
+		nr_irqs /= 2;
+	} while (nr_irqs > 0);
 
-	if (!nr_chunks)
+	if (err)
 		goto out;
 
-	bitmap = kcalloc(BITS_TO_LONGS(nr_chunks * IRQS_PER_CHUNK),
-			 sizeof(long),
-			 GFP_ATOMIC);
+	bitmap = kcalloc(BITS_TO_LONGS(nr_irqs), sizeof (long), GFP_ATOMIC);
 	if (!bitmap)
 		goto out;
 
-	for (i = 0; i < nr_chunks; i++)
-		set_bit(chunk_id + i, lpi_bitmap);
-
-	*base = its_chunk_to_lpi(chunk_id);
-	*nr_ids = nr_chunks * IRQS_PER_CHUNK;
+	*nr_ids = nr_irqs;
 
 out:
-	spin_unlock(&lpi_lock);
-
 	if (!bitmap)
 		*base = *nr_ids = 0;
 
 	return bitmap;
 }
 
-static void its_lpi_free_chunks(unsigned long *bitmap, int base, int nr_ids)
+static void its_lpi_free(unsigned long *bitmap, u32 base, u32 nr_ids)
 {
-	int lpi;
-
-	spin_lock(&lpi_lock);
-
-	for (lpi = base; lpi < (base + nr_ids); lpi += IRQS_PER_CHUNK) {
-		int chunk = its_lpi_to_chunk(lpi);
-
-		BUG_ON(chunk > lpi_chunks);
-		if (test_bit(chunk, lpi_bitmap)) {
-			clear_bit(chunk, lpi_bitmap);
-		} else {
-			pr_err("Bad LPI chunk %d\n", chunk);
-		}
-	}
-
-	spin_unlock(&lpi_lock);
-
+	WARN_ON(free_lpi_range(base, nr_ids));
 	kfree(bitmap);
 }
 
@@ -1559,7 +1625,7 @@ static int __init its_alloc_lpi_tables(void)
 {
 	phys_addr_t paddr;
 
-	lpi_id_bits = min_t(u32, gic_rdists->id_bits, ITS_MAX_LPI_NRBITS);
+	lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer);
 	gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT);
 	if (!gic_rdists->prop_page) {
 		pr_err("Failed to allocate PROPBASE\n");
@@ -1997,12 +2063,12 @@ static void its_cpu_init_collections(void)
 {
 	struct its_node *its;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 
 	list_for_each_entry(its, &its_nodes, entry)
 		its_cpu_init_collection(its);
 
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
@@ -2134,17 +2200,20 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	if (!its_alloc_device_table(its, dev_id))
 		return NULL;
 
+	if (WARN_ON(!is_power_of_2(nvecs)))
+		nvecs = roundup_pow_of_two(nvecs);
+
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	/*
-	 * We allocate at least one chunk worth of LPIs bet device,
-	 * and thus that many ITEs. The device may require less though.
+	 * Even if the device wants a single LPI, the ITT must be
+	 * sized as a power of two (and you need at least one bit...).
 	 */
-	nr_ites = max(IRQS_PER_CHUNK, roundup_pow_of_two(nvecs));
+	nr_ites = max(2, nvecs);
 	sz = nr_ites * its->ite_size;
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
 	itt = kzalloc(sz, GFP_KERNEL);
 	if (alloc_lpis) {
-		lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis);
+		lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
 		if (lpi_map)
 			col_map = kcalloc(nr_lpis, sizeof(*col_map),
 					  GFP_KERNEL);
@@ -2379,9 +2448,9 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 	/* If all interrupts have been freed, start mopping the floor */
 	if (bitmap_empty(its_dev->event_map.lpi_map,
 			 its_dev->event_map.nr_lpis)) {
-		its_lpi_free_chunks(its_dev->event_map.lpi_map,
-				    its_dev->event_map.lpi_base,
-				    its_dev->event_map.nr_lpis);
+		its_lpi_free(its_dev->event_map.lpi_map,
+			     its_dev->event_map.lpi_base,
+			     its_dev->event_map.nr_lpis);
 		kfree(its_dev->event_map.col_map);
 
 		/* Unmap device/itt */
@@ -2780,7 +2849,7 @@ static void its_vpe_irq_domain_free(struct irq_domain *domain,
 	}
 
 	if (bitmap_empty(vm->db_bitmap, vm->nr_db_lpis)) {
-		its_lpi_free_chunks(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
+		its_lpi_free(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
 		its_free_prop_table(vm->vprop_page);
 	}
 }
@@ -2795,18 +2864,18 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 
 	BUG_ON(!vm);
 
-	bitmap = its_lpi_alloc_chunks(nr_irqs, &base, &nr_ids);
+	bitmap = its_lpi_alloc(roundup_pow_of_two(nr_irqs), &base, &nr_ids);
 	if (!bitmap)
 		return -ENOMEM;
 
 	if (nr_ids < nr_irqs) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
 	vprop_page = its_allocate_prop_table(GFP_KERNEL);
 	if (!vprop_page) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
@@ -2833,7 +2902,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 		if (i > 0)
 			its_vpe_irq_domain_free(domain, virq, i - 1);
 
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		its_free_prop_table(vprop_page);
 	}
 
@@ -3070,7 +3139,7 @@ static int its_save_disable(void)
 	struct its_node *its;
 	int err = 0;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 
@@ -3102,7 +3171,7 @@ err:
 			writel_relaxed(its->ctlr_save, base + GITS_CTLR);
 		}
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return err;
 }
@@ -3112,7 +3181,7 @@ static void its_restore_enable(void)
 	struct its_node *its;
 	int ret;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 		int i;
@@ -3164,7 +3233,7 @@ static void its_restore_enable(void)
 		    GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER)))
 			its_cpu_init_collection(its);
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct syscore_ops its_syscore_ops = {
@@ -3398,9 +3467,9 @@ static int __init its_probe_one(struct resource *res,
 	if (err)
 		goto out_free_tables;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_add(&its->entry, &its_nodes);
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return 0;
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 76ea56d779a1..e214181b77b7 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -877,7 +877,7 @@ static struct irq_chip gic_eoimode1_chip = {
 	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
-#define GIC_ID_NR		(1U << gic_data.rdists.id_bits)
+#define GIC_ID_NR	(1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
 
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hw)
@@ -1091,7 +1091,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
 	 */
 	typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
-	gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
+	gic_data.rdists.gicd_typer = typer;
 	gic_irqs = GICD_TYPER_IRQS(typer);
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;
diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c
index fc5953dea509..2ff08986b536 100644
--- a/drivers/irqchip/irq-ingenic.c
+++ b/drivers/irqchip/irq-ingenic.c
@@ -165,6 +165,7 @@ static int __init intc_1chip_of_init(struct device_node *node,
 	return ingenic_intc_of_init(node, 1);
 }
 IRQCHIP_DECLARE(jz4740_intc, "ingenic,jz4740-intc", intc_1chip_of_init);
+IRQCHIP_DECLARE(jz4725b_intc, "ingenic,jz4725b-intc", intc_1chip_of_init);
 
 static int __init intc_2chip_of_init(struct device_node *node,
 	struct device_node *parent)
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 3a7e8905a97e..3df527fcf4e1 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -159,6 +159,7 @@ static const struct stm32_exti_bank *stm32mp1_exti_banks[] = {
 };
 
 static const struct stm32_desc_irq stm32mp1_desc_irq[] = {
+	{ .exti = 0, .irq_parent = 6 },
 	{ .exti = 1, .irq_parent = 7 },
 	{ .exti = 2, .irq_parent = 8 },
 	{ .exti = 3, .irq_parent = 9 },
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 98f90aadd141..18c0a1281914 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -588,7 +588,7 @@ static const struct proto_ops data_sock_ops = {
 	.getname	= data_sock_getname,
 	.sendmsg	= mISDN_sock_sendmsg,
 	.recvmsg	= mISDN_sock_recvmsg,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= data_sock_setsockopt,
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 6e3a998f3370..44097a3e0fcc 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -57,12 +57,13 @@ config LEDS_AAT1290
 	depends on PINCTRL
 	help
 	 This option enables support for the LEDs on the AAT1290.
+
 config LEDS_APU
-	tristate "Front panel LED support for PC Engines APU/APU2 boards"
+	tristate "Front panel LED support for PC Engines APU/APU2/APU3 boards"
 	depends on LEDS_CLASS
 	depends on X86 && DMI
 	help
-	  This driver makes the PC Engines APU/APU2 front panel LEDs
+	  This driver makes the PC Engines APU/APU2/APU3 front panel LEDs
 	  accessible from userspace programs through the LED subsystem.
 
 	  To compile this driver as a module, choose M here: the
diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index 431123b048a2..17d73db1456e 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -103,15 +103,16 @@ ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr,
 EXPORT_SYMBOL_GPL(led_trigger_show);
 
 /* Caller must ensure led_cdev->trigger_lock held */
-void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
+int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 {
 	unsigned long flags;
 	char *event = NULL;
 	char *envp[2];
 	const char *name;
+	int ret;
 
 	if (!led_cdev->trigger && !trig)
-		return;
+		return 0;
 
 	name = trig ? trig->name : "none";
 	event = kasprintf(GFP_KERNEL, "TRIGGER=%s", name);
@@ -126,7 +127,10 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 		led_stop_software_blink(led_cdev);
 		if (led_cdev->trigger->deactivate)
 			led_cdev->trigger->deactivate(led_cdev);
+		device_remove_groups(led_cdev->dev, led_cdev->trigger->groups);
 		led_cdev->trigger = NULL;
+		led_cdev->trigger_data = NULL;
+		led_cdev->activated = false;
 		led_set_brightness(led_cdev, LED_OFF);
 	}
 	if (trig) {
@@ -134,8 +138,20 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 		list_add_tail(&led_cdev->trig_list, &trig->led_cdevs);
 		write_unlock_irqrestore(&trig->leddev_list_lock, flags);
 		led_cdev->trigger = trig;
+
 		if (trig->activate)
-			trig->activate(led_cdev);
+			ret = trig->activate(led_cdev);
+		else
+			ret = 0;
+
+		if (ret)
+			goto err_activate;
+
+		ret = device_add_groups(led_cdev->dev, trig->groups);
+		if (ret) {
+			dev_err(led_cdev->dev, "Failed to add trigger attributes\n");
+			goto err_add_groups;
+		}
 	}
 
 	if (event) {
@@ -146,6 +162,23 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 				"%s: Error sending uevent\n", __func__);
 		kfree(event);
 	}
+
+	return 0;
+
+err_add_groups:
+
+	if (trig->deactivate)
+		trig->deactivate(led_cdev);
+err_activate:
+
+	led_cdev->trigger = NULL;
+	led_cdev->trigger_data = NULL;
+	write_lock_irqsave(&led_cdev->trigger->leddev_list_lock, flags);
+	list_del(&led_cdev->trig_list);
+	write_unlock_irqrestore(&led_cdev->trigger->leddev_list_lock, flags);
+	led_set_brightness(led_cdev, LED_OFF);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(led_trigger_set);
 
diff --git a/drivers/leds/leds-apu.c b/drivers/leds/leds-apu.c
index 8c93d68964c7..8d42e46e2de3 100644
--- a/drivers/leds/leds-apu.c
+++ b/drivers/leds/leds-apu.c
@@ -102,6 +102,13 @@ static const struct apu_led_profile apu2_led_profile[] = {
 	{ "apu2:green:3", LED_OFF, APU2_FCH_GPIO_BASE + 70 * APU2_IOSIZE },
 };
 
+/* Same as apu2_led_profile, but with "3" in the LED names. */
+static const struct apu_led_profile apu3_led_profile[] = {
+	{ "apu3:green:1", LED_ON,  APU2_FCH_GPIO_BASE + 68 * APU2_IOSIZE },
+	{ "apu3:green:2", LED_OFF, APU2_FCH_GPIO_BASE + 69 * APU2_IOSIZE },
+	{ "apu3:green:3", LED_OFF, APU2_FCH_GPIO_BASE + 70 * APU2_IOSIZE },
+};
+
 static const struct dmi_system_id apu_led_dmi_table[] __initconst = {
 	{
 		.ident = "apu",
@@ -134,6 +141,30 @@ static const struct dmi_system_id apu_led_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_BOARD_NAME, "PC Engines apu2")
 		}
 	},
+	/* PC Engines APU3 with "Legacy" bios < 4.0.8 */
+	{
+		.ident = "apu3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"),
+			DMI_MATCH(DMI_BOARD_NAME, "APU3")
+		}
+	},
+	/* PC Engines APU3 with "Legacy" bios >= 4.0.8 */
+	{
+		.ident = "apu3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"),
+			DMI_MATCH(DMI_BOARD_NAME, "apu3")
+		}
+	},
+	/* PC Engines APU2 with "Mainline" bios */
+	{
+		.ident = "apu3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"),
+			DMI_MATCH(DMI_BOARD_NAME, "PC Engines apu3")
+		}
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(dmi, apu_led_dmi_table);
@@ -235,6 +266,14 @@ static int __init apu_led_probe(struct platform_device *pdev)
 		apu_led->platform = APU2_LED_PLATFORM;
 		apu_led->num_led_instances = ARRAY_SIZE(apu2_led_profile);
 		apu_led->iosize = APU2_IOSIZE;
+	} else if (dmi_match(DMI_BOARD_NAME, "APU3") ||
+		   dmi_match(DMI_BOARD_NAME, "apu3") ||
+		   dmi_match(DMI_BOARD_NAME, "PC Engines apu3")) {
+		apu_led->profile = apu3_led_profile;
+		/* Otherwise identical to APU2. */
+		apu_led->platform = APU2_LED_PLATFORM;
+		apu_led->num_led_instances = ARRAY_SIZE(apu3_led_profile);
+		apu_led->iosize = APU2_IOSIZE;
 	}
 
 	spin_lock_init(&apu_led->lock);
@@ -259,7 +298,10 @@ static int __init apu_led_init(void)
 	if (!(dmi_match(DMI_PRODUCT_NAME, "APU") ||
 	      dmi_match(DMI_PRODUCT_NAME, "APU2") ||
 	      dmi_match(DMI_PRODUCT_NAME, "apu2") ||
-	      dmi_match(DMI_PRODUCT_NAME, "PC Engines apu2"))) {
+	      dmi_match(DMI_PRODUCT_NAME, "PC Engines apu2") ||
+	      dmi_match(DMI_PRODUCT_NAME, "APU3") ||
+	      dmi_match(DMI_PRODUCT_NAME, "apu3") ||
+	      dmi_match(DMI_PRODUCT_NAME, "PC Engines apu3"))) {
 		pr_err("Unknown PC Engines board: %s\n",
 				dmi_get_system_info(DMI_PRODUCT_NAME));
 		return -ENODEV;
diff --git a/drivers/leds/leds-lm3692x.c b/drivers/leds/leds-lm3692x.c
index 437173d1712c..4f413a7c5f05 100644
--- a/drivers/leds/leds-lm3692x.c
+++ b/drivers/leds/leds-lm3692x.c
@@ -1,17 +1,6 @@
-/*
- * TI lm3692x LED Driver
- *
- * Copyright (C) 2017 Texas Instruments
- *
- * Author: Dan Murphy <dmurphy@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * Data sheet is located
- * http://www.ti.com/lit/ds/snvsa29/snvsa29.pdf
- */
+// SPDX-License-Identifier: GPL-2.0
+// TI LM3692x LED chip family driver
+// Copyright (C) 2017-18 Texas Instruments Incorporated - http://www.ti.com/
 
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
@@ -26,6 +15,9 @@
 #include <linux/slab.h>
 #include <uapi/linux/uleds.h>
 
+#define LM36922_MODEL	0
+#define LM36923_MODEL	1
+
 #define LM3692X_REV		0x0
 #define LM3692X_RESET		0x1
 #define LM3692X_EN		0x10
@@ -44,6 +36,9 @@
 #define LM3692X_DEVICE_EN	BIT(0)
 #define LM3692X_LED1_EN		BIT(1)
 #define LM3692X_LED2_EN		BIT(2)
+#define LM36923_LED3_EN		BIT(3)
+#define LM3692X_ENABLE_MASK	(LM3692X_DEVICE_EN | LM3692X_LED1_EN | \
+				 LM3692X_LED2_EN | LM36923_LED3_EN)
 
 /* Brightness Control Bits */
 #define LM3692X_BL_ADJ_POL	BIT(0)
@@ -109,6 +104,8 @@
  * @enable_gpio - VDDIO/EN gpio to enable communication interface
  * @regulator - LED supply regulator pointer
  * @label - LED label
+ * @led_enable - LED sync to be enabled
+ * @model_id - Current device model ID enumerated
  */
 struct lm3692x_led {
 	struct mutex lock;
@@ -118,6 +115,8 @@ struct lm3692x_led {
 	struct gpio_desc *enable_gpio;
 	struct regulator *regulator;
 	char label[LED_MAX_NAME_SIZE];
+	int led_enable;
+	int model_id;
 };
 
 static const struct reg_default lm3692x_reg_defs[] = {
@@ -200,6 +199,7 @@ out:
 
 static int lm3692x_init(struct lm3692x_led *led)
 {
+	int enable_state;
 	int ret;
 
 	if (led->regulator) {
@@ -226,9 +226,25 @@ static int lm3692x_init(struct lm3692x_led *led)
 
 	/*
 	 * For glitch free operation, the following data should
-	 * only be written while device enable bit is 0
+	 * only be written while LEDx enable bits are 0 and the device enable
+	 * bit is set to 1.
 	 * per Section 7.5.14 of the data sheet
 	 */
+	ret = regmap_write(led->regmap, LM3692X_EN, LM3692X_DEVICE_EN);
+	if (ret)
+		goto out;
+
+	/* Set the brightness to 0 so when enabled the LEDs do not come
+	 * on with full brightness.
+	 */
+	ret = regmap_write(led->regmap, LM3692X_BRT_MSB, 0);
+	if (ret)
+		goto out;
+
+	ret = regmap_write(led->regmap, LM3692X_BRT_LSB, 0);
+	if (ret)
+		goto out;
+
 	ret = regmap_write(led->regmap, LM3692X_PWM_CTRL,
 		LM3692X_PWM_FILTER_100 | LM3692X_PWM_SAMP_24MHZ);
 	if (ret)
@@ -258,6 +274,38 @@ static int lm3692x_init(struct lm3692x_led *led)
 	if (ret)
 		goto out;
 
+	switch (led->led_enable) {
+	case 0:
+	default:
+		if (led->model_id == LM36923_MODEL)
+			enable_state = LM3692X_LED1_EN | LM3692X_LED2_EN |
+			       LM36923_LED3_EN;
+		else
+			enable_state = LM3692X_LED1_EN | LM3692X_LED2_EN;
+
+		break;
+	case 1:
+		enable_state = LM3692X_LED1_EN;
+		break;
+	case 2:
+		enable_state = LM3692X_LED2_EN;
+		break;
+
+	case 3:
+		if (led->model_id == LM36923_MODEL) {
+			enable_state = LM36923_LED3_EN;
+			break;
+		}
+
+		ret = -EINVAL;
+		dev_err(&led->client->dev,
+			"LED3 sync not available on this device\n");
+		goto out;
+	}
+
+	ret = regmap_update_bits(led->regmap, LM3692X_EN, LM3692X_ENABLE_MASK,
+				 enable_state | LM3692X_DEVICE_EN);
+
 	return ret;
 out:
 	dev_err(&led->client->dev, "Fail writing initialization values\n");
@@ -274,52 +322,75 @@ out:
 
 	return ret;
 }
-
-static int lm3692x_probe(struct i2c_client *client,
-			const struct i2c_device_id *id)
+static int lm3692x_probe_dt(struct lm3692x_led *led)
 {
-	int ret;
-	struct lm3692x_led *led;
-	struct device_node *np = client->dev.of_node;
-	struct device_node *child_node;
+	struct fwnode_handle *child = NULL;
 	const char *name;
+	int ret;
 
-	led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL);
-	if (!led)
-		return -ENOMEM;
-
-	for_each_available_child_of_node(np, child_node) {
-		led->led_dev.default_trigger = of_get_property(child_node,
-						    "linux,default-trigger",
-						    NULL);
-
-		ret = of_property_read_string(child_node, "label", &name);
-		if (!ret)
-			snprintf(led->label, sizeof(led->label),
-				 "%s:%s", id->name, name);
-		else
-			snprintf(led->label, sizeof(led->label),
-				 "%s::backlight_cluster", id->name);
-	};
-
-	led->enable_gpio = devm_gpiod_get_optional(&client->dev,
+	led->enable_gpio = devm_gpiod_get_optional(&led->client->dev,
 						   "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(led->enable_gpio)) {
 		ret = PTR_ERR(led->enable_gpio);
-		dev_err(&client->dev, "Failed to get enable gpio: %d\n", ret);
+		dev_err(&led->client->dev, "Failed to get enable gpio: %d\n",
+			ret);
 		return ret;
 	}
 
-	led->regulator = devm_regulator_get(&client->dev, "vled");
+	led->regulator = devm_regulator_get(&led->client->dev, "vled");
 	if (IS_ERR(led->regulator))
 		led->regulator = NULL;
 
-	led->client = client;
+	child = device_get_next_child_node(&led->client->dev, child);
+	if (!child) {
+		dev_err(&led->client->dev, "No LED Child node\n");
+		return -ENODEV;
+	}
+
+	fwnode_property_read_string(child, "linux,default-trigger",
+				    &led->led_dev.default_trigger);
+
+	ret = fwnode_property_read_string(child, "label", &name);
+	if (ret)
+		snprintf(led->label, sizeof(led->label),
+			"%s::", led->client->name);
+	else
+		snprintf(led->label, sizeof(led->label),
+			 "%s:%s", led->client->name, name);
+
+	ret = fwnode_property_read_u32(child, "reg", &led->led_enable);
+	if (ret) {
+		dev_err(&led->client->dev, "reg DT property missing\n");
+		return ret;
+	}
+
 	led->led_dev.name = led->label;
-	led->led_dev.brightness_set_blocking = lm3692x_brightness_set;
 
-	mutex_init(&led->lock);
+	ret = devm_led_classdev_register(&led->client->dev, &led->led_dev);
+	if (ret) {
+		dev_err(&led->client->dev, "led register err: %d\n", ret);
+		return ret;
+	}
+
+	led->led_dev.dev->of_node = to_of_node(child);
+
+	return 0;
+}
 
+static int lm3692x_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
+{
+	struct lm3692x_led *led;
+	int ret;
+
+	led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+
+	mutex_init(&led->lock);
+	led->client = client;
+	led->led_dev.brightness_set_blocking = lm3692x_brightness_set;
+	led->model_id = id->driver_data;
 	i2c_set_clientdata(client, led);
 
 	led->regmap = devm_regmap_init_i2c(client, &lm3692x_regmap_config);
@@ -330,15 +401,13 @@ static int lm3692x_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	ret = lm3692x_init(led);
+	ret = lm3692x_probe_dt(led);
 	if (ret)
 		return ret;
 
-	ret = devm_led_classdev_register(&client->dev, &led->led_dev);
-	if (ret) {
-		dev_err(&client->dev, "led register err: %d\n", ret);
+	ret = lm3692x_init(led);
+	if (ret)
 		return ret;
-	}
 
 	return 0;
 }
@@ -348,6 +417,12 @@ static int lm3692x_remove(struct i2c_client *client)
 	struct lm3692x_led *led = i2c_get_clientdata(client);
 	int ret;
 
+	ret = regmap_update_bits(led->regmap, LM3692X_EN, LM3692X_DEVICE_EN, 0);
+	if (ret) {
+		dev_err(&led->client->dev, "Failed to disable regulator\n");
+		return ret;
+	}
+
 	if (led->enable_gpio)
 		gpiod_direction_output(led->enable_gpio, 0);
 
@@ -364,8 +439,8 @@ static int lm3692x_remove(struct i2c_client *client)
 }
 
 static const struct i2c_device_id lm3692x_id[] = {
-	{ "lm36922", 0 },
-	{ "lm36923", 1 },
+	{ "lm36922", LM36922_MODEL },
+	{ "lm36923", LM36923_MODEL },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, lm3692x_id);
diff --git a/drivers/leds/leds-lt3593.c b/drivers/leds/leds-lt3593.c
index 5ec730a31b65..de3623e0d094 100644
--- a/drivers/leds/leds-lt3593.c
+++ b/drivers/leds/leds-lt3593.c
@@ -1,32 +1,21 @@
-/*
- * LEDs driver for LT3593 controllers
- *
- * See the datasheet at http://cds.linear.com/docs/Datasheet/3593f.pdf
- *
- * Copyright (c) 2009 Daniel Mack <daniel@caiaq.de>
- *
- * Based on leds-gpio.c,
- *
- *   Copyright (C) 2007 8D Technologies inc.
- *   Raphael Assenat <raph@8d.com>
- *   Copyright (C) 2008 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2009,2018 Daniel Mack <daniel@zonque.org>
 
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/leds.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/of.h>
+#include <uapi/linux/uleds.h>
 
 struct lt3593_led_data {
+	char name[LED_MAX_NAME_SIZE];
 	struct led_classdev cdev;
-	unsigned gpio;
+	struct gpio_desc *gpiod;
 };
 
 static int lt3593_led_set(struct led_classdev *led_cdev,
@@ -46,137 +35,168 @@ static int lt3593_led_set(struct led_classdev *led_cdev,
 	 */
 
 	if (value == 0) {
-		gpio_set_value_cansleep(led_dat->gpio, 0);
+		gpiod_set_value_cansleep(led_dat->gpiod, 0);
 		return 0;
 	}
 
 	pulses = 32 - (value * 32) / 255;
 
 	if (pulses == 0) {
-		gpio_set_value_cansleep(led_dat->gpio, 0);
+		gpiod_set_value_cansleep(led_dat->gpiod, 0);
 		mdelay(1);
-		gpio_set_value_cansleep(led_dat->gpio, 1);
+		gpiod_set_value_cansleep(led_dat->gpiod, 1);
 		return 0;
 	}
 
-	gpio_set_value_cansleep(led_dat->gpio, 1);
+	gpiod_set_value_cansleep(led_dat->gpiod, 1);
 
 	while (pulses--) {
-		gpio_set_value_cansleep(led_dat->gpio, 0);
+		gpiod_set_value_cansleep(led_dat->gpiod, 0);
 		udelay(1);
-		gpio_set_value_cansleep(led_dat->gpio, 1);
+		gpiod_set_value_cansleep(led_dat->gpiod, 1);
 		udelay(1);
 	}
 
 	return 0;
 }
 
-static int create_lt3593_led(const struct gpio_led *template,
-	struct lt3593_led_data *led_dat, struct device *parent)
+static struct lt3593_led_data *lt3593_led_probe_pdata(struct device *dev)
 {
+	struct gpio_led_platform_data *pdata = dev_get_platdata(dev);
+	const struct gpio_led *template = &pdata->leds[0];
+	struct lt3593_led_data *led_data;
 	int ret, state;
 
-	/* skip leds on GPIOs that aren't available */
-	if (!gpio_is_valid(template->gpio)) {
-		dev_info(parent, "%s: skipping unavailable LT3593 LED at gpio %d (%s)\n",
-				KBUILD_MODNAME, template->gpio, template->name);
-		return 0;
-	}
+	if (pdata->num_leds != 1)
+		return ERR_PTR(-EINVAL);
 
-	led_dat->cdev.name = template->name;
-	led_dat->cdev.default_trigger = template->default_trigger;
-	led_dat->gpio = template->gpio;
+	led_data = devm_kzalloc(dev, sizeof(*led_data), GFP_KERNEL);
+	if (!led_data)
+		return ERR_PTR(-ENOMEM);
 
-	led_dat->cdev.brightness_set_blocking = lt3593_led_set;
+	led_data->cdev.name = template->name;
+	led_data->cdev.default_trigger = template->default_trigger;
+	led_data->cdev.brightness_set_blocking = lt3593_led_set;
 
 	state = (template->default_state == LEDS_GPIO_DEFSTATE_ON);
-	led_dat->cdev.brightness = state ? LED_FULL : LED_OFF;
+	led_data->cdev.brightness = state ? LED_FULL : LED_OFF;
 
 	if (!template->retain_state_suspended)
-		led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
+		led_data->cdev.flags |= LED_CORE_SUSPENDRESUME;
 
-	ret = devm_gpio_request_one(parent, template->gpio, state ?
+	ret = devm_gpio_request_one(dev, template->gpio, state ?
 				    GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW,
 				    template->name);
 	if (ret < 0)
-		return ret;
-
-	ret = led_classdev_register(parent, &led_dat->cdev);
-	if (ret < 0)
-		return ret;
+		return ERR_PTR(ret);
 
-	dev_info(parent, "%s: registered LT3593 LED '%s' at GPIO %d\n",
-		KBUILD_MODNAME, template->name, template->gpio);
+	led_data->gpiod = gpio_to_desc(template->gpio);
+	if (!led_data->gpiod)
+		return ERR_PTR(-EPROBE_DEFER);
 
-	return 0;
-}
+	ret = devm_led_classdev_register(dev, &led_data->cdev);
+	if (ret < 0)
+		return ERR_PTR(ret);
 
-static void delete_lt3593_led(struct lt3593_led_data *led)
-{
-	if (!gpio_is_valid(led->gpio))
-		return;
+	dev_info(dev, "registered LT3593 LED '%s' at GPIO %d\n",
+		 template->name, template->gpio);
 
-	led_classdev_unregister(&led->cdev);
+	return led_data;
 }
 
 static int lt3593_led_probe(struct platform_device *pdev)
 {
-	struct gpio_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	struct lt3593_led_data *leds_data;
-	int i, ret = 0;
+	struct device *dev = &pdev->dev;
+	struct lt3593_led_data *led_data;
+	struct fwnode_handle *child;
+	int ret, state = LEDS_GPIO_DEFSTATE_OFF;
+	enum gpiod_flags flags = GPIOD_OUT_LOW;
+	const char *tmp;
+
+	if (dev_get_platdata(dev)) {
+		led_data = lt3593_led_probe_pdata(dev);
+		if (IS_ERR(led_data))
+			return PTR_ERR(led_data);
+
+		goto out;
+	}
 
-	if (!pdata)
-		return -EBUSY;
+	if (!dev->of_node)
+		return -ENODEV;
 
-	leds_data = devm_kcalloc(&pdev->dev,
-			pdata->num_leds, sizeof(struct lt3593_led_data),
-			GFP_KERNEL);
-	if (!leds_data)
+	led_data = devm_kzalloc(dev, sizeof(*led_data), GFP_KERNEL);
+	if (!led_data)
 		return -ENOMEM;
 
-	for (i = 0; i < pdata->num_leds; i++) {
-		ret = create_lt3593_led(&pdata->leds[i], &leds_data[i],
-				      &pdev->dev);
-		if (ret < 0)
-			goto err;
+	if (device_get_child_node_count(dev) != 1) {
+		dev_err(dev, "Device must have exactly one LED sub-node.");
+		return -EINVAL;
 	}
 
-	platform_set_drvdata(pdev, leds_data);
+	led_data->gpiod = devm_gpiod_get(dev, "lltc,ctrl", 0);
+	if (IS_ERR(led_data->gpiod))
+		return PTR_ERR(led_data->gpiod);
 
-	return 0;
+	child = device_get_next_child_node(dev, NULL);
 
-err:
-	for (i = i - 1; i >= 0; i--)
-		delete_lt3593_led(&leds_data[i]);
+	ret = fwnode_property_read_string(child, "label", &tmp);
+	if (ret < 0)
+		snprintf(led_data->name, sizeof(led_data->name),
+			 "lt3593::");
+	else
+		snprintf(led_data->name, sizeof(led_data->name),
+			 "lt3593:%s", tmp);
+
+	fwnode_property_read_string(child, "linux,default-trigger",
+				    &led_data->cdev.default_trigger);
+
+	if (!fwnode_property_read_string(child, "default-state", &tmp)) {
+		if (!strcmp(tmp, "keep")) {
+			state = LEDS_GPIO_DEFSTATE_KEEP;
+			flags = GPIOD_ASIS;
+		} else if (!strcmp(tmp, "on")) {
+			state = LEDS_GPIO_DEFSTATE_ON;
+			flags = GPIOD_OUT_HIGH;
+		}
+	}
 
-	return ret;
-}
+	led_data->cdev.name = led_data->name;
+	led_data->cdev.brightness_set_blocking = lt3593_led_set;
+	led_data->cdev.brightness = state ? LED_FULL : LED_OFF;
 
-static int lt3593_led_remove(struct platform_device *pdev)
-{
-	int i;
-	struct gpio_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	struct lt3593_led_data *leds_data;
+	ret = devm_led_classdev_register(dev, &led_data->cdev);
+	if (ret < 0) {
+		fwnode_handle_put(child);
+		return ret;
+	}
 
-	leds_data = platform_get_drvdata(pdev);
+	led_data->cdev.dev->of_node = dev->of_node;
 
-	for (i = 0; i < pdata->num_leds; i++)
-		delete_lt3593_led(&leds_data[i]);
+out:
+	platform_set_drvdata(pdev, led_data);
 
 	return 0;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id of_lt3593_leds_match[] = {
+	{ .compatible = "lltc,lt3593", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_lt3593_leds_match);
+#endif
+
 static struct platform_driver lt3593_led_driver = {
 	.probe		= lt3593_led_probe,
-	.remove		= lt3593_led_remove,
 	.driver		= {
 		.name	= "leds-lt3593",
+		.of_match_table = of_match_ptr(of_lt3593_leds_match),
 	},
 };
 
 module_platform_driver(lt3593_led_driver);
 
-MODULE_AUTHOR("Daniel Mack <daniel@caiaq.de>");
+MODULE_AUTHOR("Daniel Mack <daniel@zonque.org>");
 MODULE_DESCRIPTION("LED driver for LT3593 controllers");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:leds-lt3593");
diff --git a/drivers/leds/leds-max8997.c b/drivers/leds/leds-max8997.c
index 4edf74f1d6d4..8c019c28f9f5 100644
--- a/drivers/leds/leds-max8997.c
+++ b/drivers/leds/leds-max8997.c
@@ -268,7 +268,7 @@ static int max8997_led_probe(struct platform_device *pdev)
 		mode = pdata->led_pdata->mode[led->id];
 		brightness = pdata->led_pdata->brightness[led->id];
 
-		max8997_led_set_mode(led, pdata->led_pdata->mode[led->id]);
+		max8997_led_set_mode(led, mode);
 
 		if (brightness > led->cdev.max_brightness)
 			brightness = led->cdev.max_brightness;
diff --git a/drivers/leds/leds-ns2.c b/drivers/leds/leds-ns2.c
index 14fe5cd43232..a0a7dc2ef87c 100644
--- a/drivers/leds/leds-ns2.c
+++ b/drivers/leds/leds-ns2.c
@@ -42,8 +42,8 @@
 
 struct ns2_led_data {
 	struct led_classdev	cdev;
-	unsigned		cmd;
-	unsigned		slow;
+	unsigned int		cmd;
+	unsigned int		slow;
 	bool			can_sleep;
 	unsigned char		sata; /* True when SATA mode active. */
 	rwlock_t		rw_lock; /* Lock GPIOs. */
diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig
index a2559b4fdfff..4018af769969 100644
--- a/drivers/leds/trigger/Kconfig
+++ b/drivers/leds/trigger/Kconfig
@@ -10,7 +10,6 @@ if LEDS_TRIGGERS
 
 config LEDS_TRIGGER_TIMER
 	tristate "LED Timer Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by a programmable timer
 	  via sysfs. Some LED hardware can be programmed to start
@@ -21,7 +20,6 @@ config LEDS_TRIGGER_TIMER
 
 config LEDS_TRIGGER_ONESHOT
 	tristate "LED One-shot Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to blink in one-shot pulses with parameters
 	  controlled via sysfs.  It's useful to notify the user on
@@ -36,7 +34,6 @@ config LEDS_TRIGGER_ONESHOT
 config LEDS_TRIGGER_DISK
 	bool "LED Disk Trigger"
 	depends on IDE_GD_ATA || ATA
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by disk activity.
 	  If unsure, say Y.
@@ -44,14 +41,12 @@ config LEDS_TRIGGER_DISK
 config LEDS_TRIGGER_MTD
 	bool "LED MTD (NAND/NOR) Trigger"
 	depends on MTD
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by MTD activity.
 	  If unsure, say N.
 
 config LEDS_TRIGGER_HEARTBEAT
 	tristate "LED Heartbeat Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by a CPU load average.
 	  The flash frequency is a hyperbolic function of the 1-minute
@@ -60,7 +55,6 @@ config LEDS_TRIGGER_HEARTBEAT
 
 config LEDS_TRIGGER_BACKLIGHT
 	tristate "LED backlight Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled as a backlight device: they
 	  turn off and on when the display is blanked and unblanked.
@@ -69,7 +63,6 @@ config LEDS_TRIGGER_BACKLIGHT
 
 config LEDS_TRIGGER_CPU
 	bool "LED CPU Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by active CPUs. This shows
 	  the active CPUs across an array of LEDs so you can see which
@@ -79,7 +72,6 @@ config LEDS_TRIGGER_CPU
 
 config LEDS_TRIGGER_ACTIVITY
 	tristate "LED activity Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by an immediate CPU usage.
 	  The flash frequency and duty cycle varies from faint flashes to
@@ -88,7 +80,6 @@ config LEDS_TRIGGER_ACTIVITY
 
 config LEDS_TRIGGER_GPIO
 	tristate "LED GPIO Trigger"
-	depends on LEDS_TRIGGERS
 	depends on GPIOLIB || COMPILE_TEST
 	help
 	  This allows LEDs to be controlled by gpio events. It's good
@@ -101,7 +92,6 @@ config LEDS_TRIGGER_GPIO
 
 config LEDS_TRIGGER_DEFAULT_ON
 	tristate "LED Default ON Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be initialised in the ON state.
 	  If unsure, say Y.
@@ -111,7 +101,6 @@ comment "iptables trigger is under Netfilter config (LED target)"
 
 config LEDS_TRIGGER_TRANSIENT
 	tristate "LED Transient Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows one time activation of a transient state on
 	  GPIO/PWM based hardware.
@@ -119,7 +108,6 @@ config LEDS_TRIGGER_TRANSIENT
 
 config LEDS_TRIGGER_CAMERA
 	tristate "LED Camera Flash/Torch Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled as a camera flash/torch device.
 	  This enables direct flash/torch on/off by the driver, kernel space.
@@ -127,7 +115,6 @@ config LEDS_TRIGGER_CAMERA
 
 config LEDS_TRIGGER_PANIC
 	bool "LED Panic Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be configured to blink on a kernel panic.
 	  Enabling this option will allow to mark certain LEDs as panic indicators,
@@ -137,7 +124,7 @@ config LEDS_TRIGGER_PANIC
 
 config LEDS_TRIGGER_NETDEV
 	tristate "LED Netdev Trigger"
-	depends on NET && LEDS_TRIGGERS
+	depends on NET
 	help
 	  This allows LEDs to be controlled by network device activity.
 	  If unsure, say Y.
diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c
index 5081894082bd..bcbf41c90c30 100644
--- a/drivers/leds/trigger/ledtrig-activity.c
+++ b/drivers/leds/trigger/ledtrig-activity.c
@@ -7,8 +7,8 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
+
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/kernel_stat.h>
@@ -37,7 +37,6 @@ static void led_activity_function(struct timer_list *t)
 	struct activity_data *activity_data = from_timer(activity_data, t,
 							 timer);
 	struct led_classdev *led_cdev = activity_data->led_cdev;
-	struct timespec boot_time;
 	unsigned int target;
 	unsigned int usage;
 	int delay;
@@ -57,8 +56,6 @@ static void led_activity_function(struct timer_list *t)
 		return;
 	}
 
-	get_monotonic_boottime(&boot_time);
-
 	cpus = 0;
 	curr_used = 0;
 
@@ -76,7 +73,7 @@ static void led_activity_function(struct timer_list *t)
 	 * down to 16us, ensuring we won't overflow 32-bit computations below
 	 * even up to 3k CPUs, while keeping divides cheap on smaller systems.
 	 */
-	curr_boot = timespec_to_ns(&boot_time) * cpus;
+	curr_boot = ktime_get_boot_ns() * cpus;
 	diff_boot = (curr_boot - activity_data->last_boot) >> 16;
 	diff_used = (curr_used - activity_data->last_used) >> 16;
 	activity_data->last_boot = curr_boot;
@@ -155,8 +152,7 @@ static void led_activity_function(struct timer_list *t)
 static ssize_t led_invert_show(struct device *dev,
                                struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct activity_data *activity_data = led_cdev->trigger_data;
+	struct activity_data *activity_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", activity_data->invert);
 }
@@ -165,8 +161,7 @@ static ssize_t led_invert_store(struct device *dev,
                                 struct device_attribute *attr,
                                 const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct activity_data *activity_data = led_cdev->trigger_data;
+	struct activity_data *activity_data = led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 
@@ -181,21 +176,21 @@ static ssize_t led_invert_store(struct device *dev,
 
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 
-static void activity_activate(struct led_classdev *led_cdev)
+static struct attribute *activity_led_attrs[] = {
+	&dev_attr_invert.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(activity_led);
+
+static int activity_activate(struct led_classdev *led_cdev)
 {
 	struct activity_data *activity_data;
-	int rc;
 
 	activity_data = kzalloc(sizeof(*activity_data), GFP_KERNEL);
 	if (!activity_data)
-		return;
+		return -ENOMEM;
 
-	led_cdev->trigger_data = activity_data;
-	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
-	if (rc) {
-		kfree(led_cdev->trigger_data);
-		return;
-	}
+	led_set_trigger_data(led_cdev, activity_data);
 
 	activity_data->led_cdev = led_cdev;
 	timer_setup(&activity_data->timer, led_activity_function, 0);
@@ -203,26 +198,24 @@ static void activity_activate(struct led_classdev *led_cdev)
 		led_cdev->blink_brightness = led_cdev->max_brightness;
 	led_activity_function(&activity_data->timer);
 	set_bit(LED_BLINK_SW, &led_cdev->work_flags);
-	led_cdev->activated = true;
+
+	return 0;
 }
 
 static void activity_deactivate(struct led_classdev *led_cdev)
 {
-	struct activity_data *activity_data = led_cdev->trigger_data;
-
-	if (led_cdev->activated) {
-		del_timer_sync(&activity_data->timer);
-		device_remove_file(led_cdev->dev, &dev_attr_invert);
-		kfree(activity_data);
-		clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
-		led_cdev->activated = false;
-	}
+	struct activity_data *activity_data = led_get_trigger_data(led_cdev);
+
+	del_timer_sync(&activity_data->timer);
+	kfree(activity_data);
+	clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
 }
 
 static struct led_trigger activity_led_trigger = {
 	.name       = "activity",
 	.activate   = activity_activate,
 	.deactivate = activity_deactivate,
+	.groups     = activity_led_groups,
 };
 
 static int activity_reboot_notifier(struct notifier_block *nb,
@@ -272,4 +265,4 @@ module_exit(activity_exit);
 
 MODULE_AUTHOR("Willy Tarreau <w@1wt.eu>");
 MODULE_DESCRIPTION("Activity LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-backlight.c b/drivers/leds/trigger/ledtrig-backlight.c
index 1ca1f1608f76..c2b57beef718 100644
--- a/drivers/leds/trigger/ledtrig-backlight.c
+++ b/drivers/leds/trigger/ledtrig-backlight.c
@@ -64,8 +64,7 @@ static int fb_notifier_callback(struct notifier_block *p,
 static ssize_t bl_trig_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct bl_trig_notifier *n = led->trigger_data;
+	struct bl_trig_notifier *n = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", n->invert);
 }
@@ -73,8 +72,8 @@ static ssize_t bl_trig_invert_show(struct device *dev,
 static ssize_t bl_trig_invert_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t num)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct bl_trig_notifier *n = led->trigger_data;
+	struct led_classdev *led = led_trigger_get_led(dev);
+	struct bl_trig_notifier *n = led_trigger_get_drvdata(dev);
 	unsigned long invert;
 	int ret;
 
@@ -97,22 +96,22 @@ static ssize_t bl_trig_invert_store(struct device *dev,
 }
 static DEVICE_ATTR(inverted, 0644, bl_trig_invert_show, bl_trig_invert_store);
 
-static void bl_trig_activate(struct led_classdev *led)
+static struct attribute *bl_trig_attrs[] = {
+	&dev_attr_inverted.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(bl_trig);
+
+static int bl_trig_activate(struct led_classdev *led)
 {
 	int ret;
 
 	struct bl_trig_notifier *n;
 
 	n = kzalloc(sizeof(struct bl_trig_notifier), GFP_KERNEL);
-	led->trigger_data = n;
-	if (!n) {
-		dev_err(led->dev, "unable to allocate backlight trigger\n");
-		return;
-	}
-
-	ret = device_create_file(led->dev, &dev_attr_inverted);
-	if (ret)
-		goto err_invert;
+	if (!n)
+		return -ENOMEM;
+	led_set_trigger_data(led, n);
 
 	n->led = led;
 	n->brightness = led->brightness;
@@ -122,46 +121,25 @@ static void bl_trig_activate(struct led_classdev *led)
 	ret = fb_register_client(&n->notifier);
 	if (ret)
 		dev_err(led->dev, "unable to register backlight trigger\n");
-	led->activated = true;
 
-	return;
-
-err_invert:
-	led->trigger_data = NULL;
-	kfree(n);
+	return 0;
 }
 
 static void bl_trig_deactivate(struct led_classdev *led)
 {
-	struct bl_trig_notifier *n =
-		(struct bl_trig_notifier *) led->trigger_data;
-
-	if (led->activated) {
-		device_remove_file(led->dev, &dev_attr_inverted);
-		fb_unregister_client(&n->notifier);
-		kfree(n);
-		led->activated = false;
-	}
+	struct bl_trig_notifier *n = led_get_trigger_data(led);
+
+	fb_unregister_client(&n->notifier);
+	kfree(n);
 }
 
 static struct led_trigger bl_led_trigger = {
 	.name		= "backlight",
 	.activate	= bl_trig_activate,
-	.deactivate	= bl_trig_deactivate
+	.deactivate	= bl_trig_deactivate,
+	.groups		= bl_trig_groups,
 };
-
-static int __init bl_trig_init(void)
-{
-	return led_trigger_register(&bl_led_trigger);
-}
-
-static void __exit bl_trig_exit(void)
-{
-	led_trigger_unregister(&bl_led_trigger);
-}
-
-module_init(bl_trig_init);
-module_exit(bl_trig_exit);
+module_led_trigger(bl_led_trigger);
 
 MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>");
 MODULE_DESCRIPTION("Backlight emulation LED trigger");
diff --git a/drivers/leds/trigger/ledtrig-camera.c b/drivers/leds/trigger/ledtrig-camera.c
index 9bd73a8bad5c..091a09a20c58 100644
--- a/drivers/leds/trigger/ledtrig-camera.c
+++ b/drivers/leds/trigger/ledtrig-camera.c
@@ -10,7 +10,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -54,4 +53,4 @@ module_exit(ledtrig_camera_exit);
 
 MODULE_DESCRIPTION("LED Trigger for Camera Flash/Torch Control");
 MODULE_AUTHOR("Milo Kim");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-default-on.c b/drivers/leds/trigger/ledtrig-default-on.c
index ff455cb46680..7f6d9219711e 100644
--- a/drivers/leds/trigger/ledtrig-default-on.c
+++ b/drivers/leds/trigger/ledtrig-default-on.c
@@ -8,7 +8,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -17,29 +16,18 @@
 #include <linux/leds.h>
 #include "../leds.h"
 
-static void defon_trig_activate(struct led_classdev *led_cdev)
+static int defon_trig_activate(struct led_classdev *led_cdev)
 {
 	led_set_brightness_nosleep(led_cdev, led_cdev->max_brightness);
+	return 0;
 }
 
 static struct led_trigger defon_led_trigger = {
 	.name     = "default-on",
 	.activate = defon_trig_activate,
 };
-
-static int __init defon_trig_init(void)
-{
-	return led_trigger_register(&defon_led_trigger);
-}
-
-static void __exit defon_trig_exit(void)
-{
-	led_trigger_unregister(&defon_led_trigger);
-}
-
-module_init(defon_trig_init);
-module_exit(defon_trig_exit);
+module_led_trigger(defon_led_trigger);
 
 MODULE_AUTHOR("Nick Forbes <nick.forbes@incepta.com>");
 MODULE_DESCRIPTION("Default-ON LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index 8891e88d54dd..ed0db8ed825f 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -6,7 +6,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -29,7 +28,7 @@ struct gpio_trig_data {
 static irqreturn_t gpio_trig_irq(int irq, void *_led)
 {
 	struct led_classdev *led = _led;
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_get_trigger_data(led);
 	int tmp;
 
 	tmp = gpio_get_value_cansleep(gpio_data->gpio);
@@ -52,8 +51,7 @@ static irqreturn_t gpio_trig_irq(int irq, void *_led)
 static ssize_t gpio_trig_brightness_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", gpio_data->desired_brightness);
 }
@@ -61,8 +59,7 @@ static ssize_t gpio_trig_brightness_show(struct device *dev,
 static ssize_t gpio_trig_brightness_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 	unsigned desired_brightness;
 	int ret;
 
@@ -82,8 +79,7 @@ static DEVICE_ATTR(desired_brightness, 0644, gpio_trig_brightness_show,
 static ssize_t gpio_trig_inverted_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", gpio_data->inverted);
 }
@@ -91,8 +87,8 @@ static ssize_t gpio_trig_inverted_show(struct device *dev,
 static ssize_t gpio_trig_inverted_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct led_classdev *led = led_trigger_get_led(dev);
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 	unsigned long inverted;
 	int ret;
 
@@ -116,8 +112,7 @@ static DEVICE_ATTR(inverted, 0644, gpio_trig_inverted_show,
 static ssize_t gpio_trig_gpio_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", gpio_data->gpio);
 }
@@ -125,8 +120,8 @@ static ssize_t gpio_trig_gpio_show(struct device *dev,
 static ssize_t gpio_trig_gpio_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct led_classdev *led = led_trigger_get_led(dev);
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 	unsigned gpio;
 	int ret;
 
@@ -163,76 +158,45 @@ static ssize_t gpio_trig_gpio_store(struct device *dev,
 }
 static DEVICE_ATTR(gpio, 0644, gpio_trig_gpio_show, gpio_trig_gpio_store);
 
-static void gpio_trig_activate(struct led_classdev *led)
+static struct attribute *gpio_trig_attrs[] = {
+	&dev_attr_desired_brightness.attr,
+	&dev_attr_inverted.attr,
+	&dev_attr_gpio.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(gpio_trig);
+
+static int gpio_trig_activate(struct led_classdev *led)
 {
 	struct gpio_trig_data *gpio_data;
-	int ret;
 
 	gpio_data = kzalloc(sizeof(*gpio_data), GFP_KERNEL);
 	if (!gpio_data)
-		return;
-
-	ret = device_create_file(led->dev, &dev_attr_gpio);
-	if (ret)
-		goto err_gpio;
-
-	ret = device_create_file(led->dev, &dev_attr_inverted);
-	if (ret)
-		goto err_inverted;
-
-	ret = device_create_file(led->dev, &dev_attr_desired_brightness);
-	if (ret)
-		goto err_brightness;
+		return -ENOMEM;
 
 	gpio_data->led = led;
-	led->trigger_data = gpio_data;
-	led->activated = true;
-
-	return;
-
-err_brightness:
-	device_remove_file(led->dev, &dev_attr_inverted);
+	led_set_trigger_data(led, gpio_data);
 
-err_inverted:
-	device_remove_file(led->dev, &dev_attr_gpio);
-
-err_gpio:
-	kfree(gpio_data);
+	return 0;
 }
 
 static void gpio_trig_deactivate(struct led_classdev *led)
 {
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_get_trigger_data(led);
 
-	if (led->activated) {
-		device_remove_file(led->dev, &dev_attr_gpio);
-		device_remove_file(led->dev, &dev_attr_inverted);
-		device_remove_file(led->dev, &dev_attr_desired_brightness);
-		if (gpio_data->gpio != 0)
-			free_irq(gpio_to_irq(gpio_data->gpio), led);
-		kfree(gpio_data);
-		led->activated = false;
-	}
+	if (gpio_data->gpio != 0)
+		free_irq(gpio_to_irq(gpio_data->gpio), led);
+	kfree(gpio_data);
 }
 
 static struct led_trigger gpio_led_trigger = {
 	.name		= "gpio",
 	.activate	= gpio_trig_activate,
 	.deactivate	= gpio_trig_deactivate,
+	.groups		= gpio_trig_groups,
 };
-
-static int __init gpio_trig_init(void)
-{
-	return led_trigger_register(&gpio_led_trigger);
-}
-module_init(gpio_trig_init);
-
-static void __exit gpio_trig_exit(void)
-{
-	led_trigger_unregister(&gpio_led_trigger);
-}
-module_exit(gpio_trig_exit);
+module_led_trigger(gpio_led_trigger);
 
 MODULE_AUTHOR("Felipe Balbi <me@felipebalbi.com>");
 MODULE_DESCRIPTION("GPIO LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index f0896de410b8..7a2b12e19329 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -9,8 +9,8 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -96,8 +96,8 @@ static void led_heartbeat_function(struct timer_list *t)
 static ssize_t led_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct heartbeat_trig_data *heartbeat_data = led_cdev->trigger_data;
+	struct heartbeat_trig_data *heartbeat_data =
+		led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", heartbeat_data->invert);
 }
@@ -105,8 +105,8 @@ static ssize_t led_invert_show(struct device *dev,
 static ssize_t led_invert_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct heartbeat_trig_data *heartbeat_data = led_cdev->trigger_data;
+	struct heartbeat_trig_data *heartbeat_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 
@@ -121,22 +121,22 @@ static ssize_t led_invert_store(struct device *dev,
 
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 
-static void heartbeat_trig_activate(struct led_classdev *led_cdev)
+static struct attribute *heartbeat_trig_attrs[] = {
+	&dev_attr_invert.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(heartbeat_trig);
+
+static int heartbeat_trig_activate(struct led_classdev *led_cdev)
 {
 	struct heartbeat_trig_data *heartbeat_data;
-	int rc;
 
 	heartbeat_data = kzalloc(sizeof(*heartbeat_data), GFP_KERNEL);
 	if (!heartbeat_data)
-		return;
+		return -ENOMEM;
 
-	led_cdev->trigger_data = heartbeat_data;
+	led_set_trigger_data(led_cdev, heartbeat_data);
 	heartbeat_data->led_cdev = led_cdev;
-	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
-	if (rc) {
-		kfree(led_cdev->trigger_data);
-		return;
-	}
 
 	timer_setup(&heartbeat_data->timer, led_heartbeat_function, 0);
 	heartbeat_data->phase = 0;
@@ -144,26 +144,25 @@ static void heartbeat_trig_activate(struct led_classdev *led_cdev)
 		led_cdev->blink_brightness = led_cdev->max_brightness;
 	led_heartbeat_function(&heartbeat_data->timer);
 	set_bit(LED_BLINK_SW, &led_cdev->work_flags);
-	led_cdev->activated = true;
+
+	return 0;
 }
 
 static void heartbeat_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct heartbeat_trig_data *heartbeat_data = led_cdev->trigger_data;
-
-	if (led_cdev->activated) {
-		del_timer_sync(&heartbeat_data->timer);
-		device_remove_file(led_cdev->dev, &dev_attr_invert);
-		kfree(heartbeat_data);
-		clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
-		led_cdev->activated = false;
-	}
+	struct heartbeat_trig_data *heartbeat_data =
+		led_get_trigger_data(led_cdev);
+
+	del_timer_sync(&heartbeat_data->timer);
+	kfree(heartbeat_data);
+	clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
 }
 
 static struct led_trigger heartbeat_led_trigger = {
 	.name     = "heartbeat",
 	.activate = heartbeat_trig_activate,
 	.deactivate = heartbeat_trig_deactivate,
+	.groups = heartbeat_trig_groups,
 };
 
 static int heartbeat_reboot_notifier(struct notifier_block *nb,
@@ -213,4 +212,4 @@ module_exit(heartbeat_trig_exit);
 
 MODULE_AUTHOR("Atsushi Nemoto <anemo@mba.ocn.ne.jp>");
 MODULE_DESCRIPTION("Heartbeat LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index 6df4781a6308..3dd3ed46d473 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -94,8 +94,7 @@ static void set_baseline_state(struct led_netdev_data *trigger_data)
 static ssize_t device_name_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	ssize_t len;
 
 	spin_lock_bh(&trigger_data->lock);
@@ -109,8 +108,7 @@ static ssize_t device_name_store(struct device *dev,
 				 struct device_attribute *attr, const char *buf,
 				 size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 
 	if (size >= IFNAMSIZ)
 		return -EINVAL;
@@ -150,8 +148,7 @@ static DEVICE_ATTR_RW(device_name);
 static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
 	enum netdev_led_attr attr)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	int bit;
 
 	switch (attr) {
@@ -174,8 +171,7 @@ static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
 static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	size_t size, enum netdev_led_attr attr)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 	int bit;
@@ -255,8 +251,7 @@ static DEVICE_ATTR_RW(rx);
 static ssize_t interval_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n",
 		       jiffies_to_msecs(atomic_read(&trigger_data->interval)));
@@ -266,8 +261,7 @@ static ssize_t interval_store(struct device *dev,
 			      struct device_attribute *attr, const char *buf,
 			      size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	unsigned long value;
 	int ret;
 
@@ -288,15 +282,23 @@ static ssize_t interval_store(struct device *dev,
 
 static DEVICE_ATTR_RW(interval);
 
+static struct attribute *netdev_trig_attrs[] = {
+	&dev_attr_device_name.attr,
+	&dev_attr_link.attr,
+	&dev_attr_rx.attr,
+	&dev_attr_tx.attr,
+	&dev_attr_interval.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(netdev_trig);
+
 static int netdev_trig_notify(struct notifier_block *nb,
 			      unsigned long evt, void *dv)
 {
 	struct net_device *dev =
 		netdev_notifier_info_to_dev((struct netdev_notifier_info *)dv);
-	struct led_netdev_data *trigger_data = container_of(nb,
-							    struct
-							    led_netdev_data,
-							    notifier);
+	struct led_netdev_data *trigger_data =
+		container_of(nb, struct led_netdev_data, notifier);
 
 	if (evt != NETDEV_UP && evt != NETDEV_DOWN && evt != NETDEV_CHANGE
 	    && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER
@@ -342,10 +344,8 @@ static int netdev_trig_notify(struct notifier_block *nb,
 /* here's the real work! */
 static void netdev_trig_work(struct work_struct *work)
 {
-	struct led_netdev_data *trigger_data = container_of(work,
-							    struct
-							    led_netdev_data,
-							    work.work);
+	struct led_netdev_data *trigger_data =
+		container_of(work, struct led_netdev_data, work.work);
 	struct rtnl_link_stats64 *dev_stats;
 	unsigned int new_activity;
 	struct rtnl_link_stats64 temp;
@@ -388,14 +388,14 @@ static void netdev_trig_work(struct work_struct *work)
 			(atomic_read(&trigger_data->interval)*2));
 }
 
-static void netdev_trig_activate(struct led_classdev *led_cdev)
+static int netdev_trig_activate(struct led_classdev *led_cdev)
 {
 	struct led_netdev_data *trigger_data;
 	int rc;
 
 	trigger_data = kzalloc(sizeof(struct led_netdev_data), GFP_KERNEL);
 	if (!trigger_data)
-		return;
+		return -ENOMEM;
 
 	spin_lock_init(&trigger_data->lock);
 
@@ -412,69 +412,34 @@ static void netdev_trig_activate(struct led_classdev *led_cdev)
 	atomic_set(&trigger_data->interval, msecs_to_jiffies(50));
 	trigger_data->last_activity = 0;
 
-	led_cdev->trigger_data = trigger_data;
+	led_set_trigger_data(led_cdev, trigger_data);
 
-	rc = device_create_file(led_cdev->dev, &dev_attr_device_name);
-	if (rc)
-		goto err_out;
-	rc = device_create_file(led_cdev->dev, &dev_attr_link);
-	if (rc)
-		goto err_out_device_name;
-	rc = device_create_file(led_cdev->dev, &dev_attr_rx);
-	if (rc)
-		goto err_out_link;
-	rc = device_create_file(led_cdev->dev, &dev_attr_tx);
-	if (rc)
-		goto err_out_rx;
-	rc = device_create_file(led_cdev->dev, &dev_attr_interval);
-	if (rc)
-		goto err_out_tx;
 	rc = register_netdevice_notifier(&trigger_data->notifier);
 	if (rc)
-		goto err_out_interval;
-	return;
-
-err_out_interval:
-	device_remove_file(led_cdev->dev, &dev_attr_interval);
-err_out_tx:
-	device_remove_file(led_cdev->dev, &dev_attr_tx);
-err_out_rx:
-	device_remove_file(led_cdev->dev, &dev_attr_rx);
-err_out_link:
-	device_remove_file(led_cdev->dev, &dev_attr_link);
-err_out_device_name:
-	device_remove_file(led_cdev->dev, &dev_attr_device_name);
-err_out:
-	led_cdev->trigger_data = NULL;
-	kfree(trigger_data);
+		kfree(trigger_data);
+
+	return rc;
 }
 
 static void netdev_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
-
-	if (trigger_data) {
-		unregister_netdevice_notifier(&trigger_data->notifier);
+	struct led_netdev_data *trigger_data = led_get_trigger_data(led_cdev);
 
-		device_remove_file(led_cdev->dev, &dev_attr_device_name);
-		device_remove_file(led_cdev->dev, &dev_attr_link);
-		device_remove_file(led_cdev->dev, &dev_attr_rx);
-		device_remove_file(led_cdev->dev, &dev_attr_tx);
-		device_remove_file(led_cdev->dev, &dev_attr_interval);
+	unregister_netdevice_notifier(&trigger_data->notifier);
 
-		cancel_delayed_work_sync(&trigger_data->work);
+	cancel_delayed_work_sync(&trigger_data->work);
 
-		if (trigger_data->net_dev)
-			dev_put(trigger_data->net_dev);
+	if (trigger_data->net_dev)
+		dev_put(trigger_data->net_dev);
 
-		kfree(trigger_data);
-	}
+	kfree(trigger_data);
 }
 
 static struct led_trigger netdev_led_trigger = {
 	.name = "netdev",
 	.activate = netdev_trig_activate,
 	.deactivate = netdev_trig_deactivate,
+	.groups = netdev_trig_groups,
 };
 
 static int __init netdev_trig_init(void)
diff --git a/drivers/leds/trigger/ledtrig-oneshot.c b/drivers/leds/trigger/ledtrig-oneshot.c
index b8ea9f0f1e19..95c9be4b6e7e 100644
--- a/drivers/leds/trigger/ledtrig-oneshot.c
+++ b/drivers/leds/trigger/ledtrig-oneshot.c
@@ -8,7 +8,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -29,8 +28,8 @@ struct oneshot_trig_data {
 static ssize_t led_shot(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct oneshot_trig_data *oneshot_data = led_trigger_get_drvdata(dev);
 
 	led_blink_set_oneshot(led_cdev,
 			&led_cdev->blink_delay_on, &led_cdev->blink_delay_off,
@@ -42,8 +41,7 @@ static ssize_t led_shot(struct device *dev,
 static ssize_t led_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct oneshot_trig_data *oneshot_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", oneshot_data->invert);
 }
@@ -51,8 +49,8 @@ static ssize_t led_invert_show(struct device *dev,
 static ssize_t led_invert_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct oneshot_trig_data *oneshot_data = led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 
@@ -73,7 +71,7 @@ static ssize_t led_invert_store(struct device *dev,
 static ssize_t led_delay_on_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_on);
 }
@@ -81,7 +79,7 @@ static ssize_t led_delay_on_show(struct device *dev,
 static ssize_t led_delay_on_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	int ret;
 
@@ -93,10 +91,11 @@ static ssize_t led_delay_on_store(struct device *dev,
 
 	return size;
 }
+
 static ssize_t led_delay_off_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_off);
 }
@@ -104,7 +103,7 @@ static ssize_t led_delay_off_show(struct device *dev,
 static ssize_t led_delay_off_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	int ret;
 
@@ -122,59 +121,36 @@ static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store);
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 static DEVICE_ATTR(shot, 0200, NULL, led_shot);
 
-static void oneshot_trig_activate(struct led_classdev *led_cdev)
+static struct attribute *oneshot_trig_attrs[] = {
+	&dev_attr_delay_on.attr,
+	&dev_attr_delay_off.attr,
+	&dev_attr_invert.attr,
+	&dev_attr_shot.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(oneshot_trig);
+
+static int oneshot_trig_activate(struct led_classdev *led_cdev)
 {
 	struct oneshot_trig_data *oneshot_data;
-	int rc;
 
 	oneshot_data = kzalloc(sizeof(*oneshot_data), GFP_KERNEL);
 	if (!oneshot_data)
-		return;
-
-	led_cdev->trigger_data = oneshot_data;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_on);
-	if (rc)
-		goto err_out_trig_data;
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_off);
-	if (rc)
-		goto err_out_delayon;
-	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
-	if (rc)
-		goto err_out_delayoff;
-	rc = device_create_file(led_cdev->dev, &dev_attr_shot);
-	if (rc)
-		goto err_out_invert;
+		return -ENOMEM;
+
+	led_set_trigger_data(led_cdev, oneshot_data);
 
 	led_cdev->blink_delay_on = DEFAULT_DELAY;
 	led_cdev->blink_delay_off = DEFAULT_DELAY;
 
-	led_cdev->activated = true;
-
-	return;
-
-err_out_invert:
-	device_remove_file(led_cdev->dev, &dev_attr_invert);
-err_out_delayoff:
-	device_remove_file(led_cdev->dev, &dev_attr_delay_off);
-err_out_delayon:
-	device_remove_file(led_cdev->dev, &dev_attr_delay_on);
-err_out_trig_data:
-	kfree(led_cdev->trigger_data);
+	return 0;
 }
 
 static void oneshot_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct oneshot_trig_data *oneshot_data = led_get_trigger_data(led_cdev);
 
-	if (led_cdev->activated) {
-		device_remove_file(led_cdev->dev, &dev_attr_delay_on);
-		device_remove_file(led_cdev->dev, &dev_attr_delay_off);
-		device_remove_file(led_cdev->dev, &dev_attr_invert);
-		device_remove_file(led_cdev->dev, &dev_attr_shot);
-		kfree(oneshot_data);
-		led_cdev->activated = false;
-	}
+	kfree(oneshot_data);
 
 	/* Stop blinking */
 	led_set_brightness(led_cdev, LED_OFF);
@@ -184,20 +160,9 @@ static struct led_trigger oneshot_led_trigger = {
 	.name     = "oneshot",
 	.activate = oneshot_trig_activate,
 	.deactivate = oneshot_trig_deactivate,
+	.groups = oneshot_trig_groups,
 };
-
-static int __init oneshot_trig_init(void)
-{
-	return led_trigger_register(&oneshot_led_trigger);
-}
-
-static void __exit oneshot_trig_exit(void)
-{
-	led_trigger_unregister(&oneshot_led_trigger);
-}
-
-module_init(oneshot_trig_init);
-module_exit(oneshot_trig_exit);
+module_led_trigger(oneshot_led_trigger);
 
 MODULE_AUTHOR("Fabio Baltieri <fabio.baltieri@gmail.com>");
 MODULE_DESCRIPTION("One-shot LED trigger");
diff --git a/drivers/leds/trigger/ledtrig-timer.c b/drivers/leds/trigger/ledtrig-timer.c
index 8d09327b5719..7c14983781ee 100644
--- a/drivers/leds/trigger/ledtrig-timer.c
+++ b/drivers/leds/trigger/ledtrig-timer.c
@@ -8,7 +8,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -21,7 +20,7 @@
 static ssize_t led_delay_on_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_on);
 }
@@ -29,7 +28,7 @@ static ssize_t led_delay_on_show(struct device *dev,
 static ssize_t led_delay_on_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	ssize_t ret = -EINVAL;
 
@@ -46,7 +45,7 @@ static ssize_t led_delay_on_store(struct device *dev,
 static ssize_t led_delay_off_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_off);
 }
@@ -54,7 +53,7 @@ static ssize_t led_delay_off_show(struct device *dev,
 static ssize_t led_delay_off_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	ssize_t ret = -EINVAL;
 
@@ -71,37 +70,23 @@ static ssize_t led_delay_off_store(struct device *dev,
 static DEVICE_ATTR(delay_on, 0644, led_delay_on_show, led_delay_on_store);
 static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store);
 
-static void timer_trig_activate(struct led_classdev *led_cdev)
-{
-	int rc;
-
-	led_cdev->trigger_data = NULL;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_on);
-	if (rc)
-		return;
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_off);
-	if (rc)
-		goto err_out_delayon;
+static struct attribute *timer_trig_attrs[] = {
+	&dev_attr_delay_on.attr,
+	&dev_attr_delay_off.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(timer_trig);
 
+static int timer_trig_activate(struct led_classdev *led_cdev)
+{
 	led_blink_set(led_cdev, &led_cdev->blink_delay_on,
 		      &led_cdev->blink_delay_off);
-	led_cdev->activated = true;
 
-	return;
-
-err_out_delayon:
-	device_remove_file(led_cdev->dev, &dev_attr_delay_on);
+	return 0;
 }
 
 static void timer_trig_deactivate(struct led_classdev *led_cdev)
 {
-	if (led_cdev->activated) {
-		device_remove_file(led_cdev->dev, &dev_attr_delay_on);
-		device_remove_file(led_cdev->dev, &dev_attr_delay_off);
-		led_cdev->activated = false;
-	}
-
 	/* Stop blinking */
 	led_set_brightness(led_cdev, LED_OFF);
 }
@@ -110,21 +95,10 @@ static struct led_trigger timer_led_trigger = {
 	.name     = "timer",
 	.activate = timer_trig_activate,
 	.deactivate = timer_trig_deactivate,
+	.groups = timer_trig_groups,
 };
-
-static int __init timer_trig_init(void)
-{
-	return led_trigger_register(&timer_led_trigger);
-}
-
-static void __exit timer_trig_exit(void)
-{
-	led_trigger_unregister(&timer_led_trigger);
-}
-
-module_init(timer_trig_init);
-module_exit(timer_trig_exit);
+module_led_trigger(timer_led_trigger);
 
 MODULE_AUTHOR("Richard Purdie <rpurdie@openedhand.com>");
 MODULE_DESCRIPTION("Timer LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-transient.c b/drivers/leds/trigger/ledtrig-transient.c
index 9d1769073562..a80bb82aacc2 100644
--- a/drivers/leds/trigger/ledtrig-transient.c
+++ b/drivers/leds/trigger/ledtrig-transient.c
@@ -42,8 +42,8 @@ static void transient_timer_function(struct timer_list *t)
 static ssize_t transient_activate_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%d\n", transient_data->activate);
 }
@@ -51,8 +51,9 @@ static ssize_t transient_activate_show(struct device *dev,
 static ssize_t transient_activate_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	ssize_t ret;
 
@@ -94,8 +95,7 @@ static ssize_t transient_activate_store(struct device *dev,
 static ssize_t transient_duration_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%lu\n", transient_data->duration);
 }
@@ -103,8 +103,8 @@ static ssize_t transient_duration_show(struct device *dev,
 static ssize_t transient_duration_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	ssize_t ret;
 
@@ -119,8 +119,8 @@ static ssize_t transient_duration_store(struct device *dev,
 static ssize_t transient_state_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	int state;
 
 	state = (transient_data->state == LED_FULL) ? 1 : 0;
@@ -130,8 +130,8 @@ static ssize_t transient_state_show(struct device *dev,
 static ssize_t transient_state_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	ssize_t ret;
 
@@ -152,82 +152,46 @@ static DEVICE_ATTR(duration, 0644, transient_duration_show,
 		   transient_duration_store);
 static DEVICE_ATTR(state, 0644, transient_state_show, transient_state_store);
 
-static void transient_trig_activate(struct led_classdev *led_cdev)
+static struct attribute *transient_trig_attrs[] = {
+	&dev_attr_activate.attr,
+	&dev_attr_duration.attr,
+	&dev_attr_state.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(transient_trig);
+
+static int transient_trig_activate(struct led_classdev *led_cdev)
 {
-	int rc;
 	struct transient_trig_data *tdata;
 
 	tdata = kzalloc(sizeof(struct transient_trig_data), GFP_KERNEL);
-	if (!tdata) {
-		dev_err(led_cdev->dev,
-			"unable to allocate transient trigger\n");
-		return;
-	}
-	led_cdev->trigger_data = tdata;
-	tdata->led_cdev = led_cdev;
+	if (!tdata)
+		return -ENOMEM;
 
-	rc = device_create_file(led_cdev->dev, &dev_attr_activate);
-	if (rc)
-		goto err_out;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_duration);
-	if (rc)
-		goto err_out_duration;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_state);
-	if (rc)
-		goto err_out_state;
+	led_set_trigger_data(led_cdev, tdata);
+	tdata->led_cdev = led_cdev;
 
 	timer_setup(&tdata->timer, transient_timer_function, 0);
-	led_cdev->activated = true;
-
-	return;
-
-err_out_state:
-	device_remove_file(led_cdev->dev, &dev_attr_duration);
-err_out_duration:
-	device_remove_file(led_cdev->dev, &dev_attr_activate);
-err_out:
-	dev_err(led_cdev->dev, "unable to register transient trigger\n");
-	led_cdev->trigger_data = NULL;
-	kfree(tdata);
+
+	return 0;
 }
 
 static void transient_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data = led_get_trigger_data(led_cdev);
 
-	if (led_cdev->activated) {
-		del_timer_sync(&transient_data->timer);
-		led_set_brightness_nosleep(led_cdev,
-					transient_data->restore_state);
-		device_remove_file(led_cdev->dev, &dev_attr_activate);
-		device_remove_file(led_cdev->dev, &dev_attr_duration);
-		device_remove_file(led_cdev->dev, &dev_attr_state);
-		led_cdev->trigger_data = NULL;
-		led_cdev->activated = false;
-		kfree(transient_data);
-	}
+	del_timer_sync(&transient_data->timer);
+	led_set_brightness_nosleep(led_cdev, transient_data->restore_state);
+	kfree(transient_data);
 }
 
 static struct led_trigger transient_trigger = {
 	.name     = "transient",
 	.activate = transient_trig_activate,
 	.deactivate = transient_trig_deactivate,
+	.groups = transient_trig_groups,
 };
-
-static int __init transient_trig_init(void)
-{
-	return led_trigger_register(&transient_trigger);
-}
-
-static void __exit transient_trig_exit(void)
-{
-	led_trigger_unregister(&transient_trigger);
-}
-
-module_init(transient_trig_init);
-module_exit(transient_trig_exit);
+module_led_trigger(transient_trigger);
 
 MODULE_AUTHOR("Shuah Khan <shuahkhan@gmail.com>");
 MODULE_DESCRIPTION("Transient LED trigger");
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 9c03f35d9df1..439bf90d084d 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -17,23 +17,25 @@ menuconfig NVM
 
 if NVM
 
-config NVM_DEBUG
-	bool "Open-Channel SSD debugging support"
-	default n
-	---help---
-	Exposes a debug management interface to create/remove targets at:
+config NVM_PBLK
+	tristate "Physical Block Device Open-Channel SSD target"
+	help
+	  Allows an open-channel SSD to be exposed as a block device to the
+	  host. The target assumes the device exposes raw flash and must be
+	  explicitly managed by the host.
 
-	  /sys/module/lnvm/parameters/configure_debug
+	  Please note the disk format is considered EXPERIMENTAL for now.
 
-	It is required to create/remove targets without IOCTLs.
+if NVM_PBLK
 
-config NVM_PBLK
-	tristate "Physical Block Device Open-Channel SSD target"
-	---help---
-	Allows an open-channel SSD to be exposed as a block device to the
-	host. The target assumes the device exposes raw flash and must be
-	explicitly managed by the host.
+config NVM_PBLK_DEBUG
+	bool "PBlk Debug Support"
+	default n
+	help
+	  Enables debug support for pblk. This includes extra checks, more
+	  vocal error messages, and extra tracking fields in the pblk sysfs
+	  entries.
 
-	Please note the disk format is considered EXPERIMENTAL for now.
+endif # NVM_PBLK_DEBUG
 
 endif # NVM
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
index b1c6d7eb6115..f565a56b898a 100644
--- a/drivers/lightnvm/pblk-cache.c
+++ b/drivers/lightnvm/pblk-cache.c
@@ -27,7 +27,8 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
 	int nr_entries = pblk_get_secs(bio);
 	int i, ret;
 
-	generic_start_io_acct(q, WRITE, bio_sectors(bio), &pblk->disk->part0);
+	generic_start_io_acct(q, REQ_OP_WRITE, bio_sectors(bio),
+			      &pblk->disk->part0);
 
 	/* Update the write buffer head (mem) with the entries that we can
 	 * write. The write in itself cannot fail, so there is no need to
@@ -67,7 +68,7 @@ retry:
 
 	atomic64_add(nr_entries, &pblk->user_wa);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(nr_entries, &pblk->inflight_writes);
 	atomic_long_add(nr_entries, &pblk->req_writes);
 #endif
@@ -75,7 +76,7 @@ retry:
 	pblk_rl_inserted(&pblk->rl, nr_entries);
 
 out:
-	generic_end_io_acct(q, WRITE, &pblk->disk->part0, start_time);
+	generic_end_io_acct(q, REQ_OP_WRITE, &pblk->disk->part0, start_time);
 	pblk_write_should_kick(pblk);
 	return ret;
 }
@@ -123,7 +124,7 @@ retry:
 
 	atomic64_add(valid_entries, &pblk->gc_wa);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(valid_entries, &pblk->inflight_writes);
 	atomic_long_add(valid_entries, &pblk->recov_gc_writes);
 #endif
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index ed9cc977c8b3..00984b486fea 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -35,7 +35,7 @@ static void pblk_line_mark_bb(struct work_struct *work)
 		line = &pblk->lines[pblk_ppa_to_line(*ppa)];
 		pos = pblk_ppa_to_pos(&dev->geo, *ppa);
 
-		pr_err("pblk: failed to mark bb, line:%d, pos:%d\n",
+		pblk_err(pblk, "failed to mark bb, line:%d, pos:%d\n",
 				line->id, pos);
 	}
 
@@ -51,12 +51,12 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
 	struct ppa_addr *ppa;
 	int pos = pblk_ppa_to_pos(geo, ppa_addr);
 
-	pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
+	pblk_debug(pblk, "erase failed: line:%d, pos:%d\n", line->id, pos);
 	atomic_long_inc(&pblk->erase_failed);
 
 	atomic_dec(&line->blk_in_line);
 	if (test_and_set_bit(pos, line->blk_bitmap))
-		pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
+		pblk_err(pblk, "attempted to erase bb: line:%d, pos:%d\n",
 							line->id, pos);
 
 	/* Not necessary to mark bad blocks on 2.0 spec. */
@@ -194,7 +194,7 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
 	u64 paddr;
 	int line_id;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a device address */
 	BUG_ON(pblk_addr_in_cache(ppa));
 	BUG_ON(pblk_ppa_empty(ppa));
@@ -264,6 +264,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 	switch (type) {
 	case PBLK_WRITE:
 		kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap);
+		/* fall through */
 	case PBLK_WRITE_INT:
 		pool = &pblk->w_rq_pool;
 		break;
@@ -274,7 +275,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 		pool = &pblk->e_rq_pool;
 		break;
 	default:
-		pr_err("pblk: trying to free unknown rqd type\n");
+		pblk_err(pblk, "trying to free unknown rqd type\n");
 		return;
 	}
 
@@ -310,7 +311,7 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
 
 		ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
 		if (ret != PBLK_EXPOSED_PAGE_SIZE) {
-			pr_err("pblk: could not add page to bio\n");
+			pblk_err(pblk, "could not add page to bio\n");
 			mempool_free(page, &pblk->page_bio_pool);
 			goto err;
 		}
@@ -410,7 +411,7 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
 		line->state = PBLK_LINESTATE_CORRUPT;
 		line->gc_group = PBLK_LINEGC_NONE;
 		move_list =  &l_mg->corrupt_list;
-		pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
+		pblk_err(pblk, "corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
 						line->id, vsc,
 						line->sec_in_line,
 						lm->high_thrs, lm->mid_thrs);
@@ -430,7 +431,7 @@ void pblk_discard(struct pblk *pblk, struct bio *bio)
 void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	atomic_long_inc(&pblk->write_failed);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pblk_print_failed_rqd(pblk, rqd, rqd->error);
 #endif
 }
@@ -452,9 +453,9 @@ void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
 		atomic_long_inc(&pblk->read_failed);
 		break;
 	default:
-		pr_err("pblk: unknown read error:%d\n", rqd->error);
+		pblk_err(pblk, "unknown read error:%d\n", rqd->error);
 	}
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pblk_print_failed_rqd(pblk, rqd, rqd->error);
 #endif
 }
@@ -470,7 +471,7 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
 
 	atomic_inc(&pblk->inflight_io);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (pblk_check_io(pblk, rqd))
 		return NVM_IO_ERR;
 #endif
@@ -484,7 +485,7 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
 
 	atomic_inc(&pblk->inflight_io);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (pblk_check_io(pblk, rqd))
 		return NVM_IO_ERR;
 #endif
@@ -517,7 +518,7 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 	for (i = 0; i < nr_secs; i++) {
 		page = vmalloc_to_page(kaddr);
 		if (!page) {
-			pr_err("pblk: could not map vmalloc bio\n");
+			pblk_err(pblk, "could not map vmalloc bio\n");
 			bio_put(bio);
 			bio = ERR_PTR(-ENOMEM);
 			goto out;
@@ -525,7 +526,7 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 
 		ret = bio_add_pc_page(dev->q, bio, page, PAGE_SIZE, 0);
 		if (ret != PAGE_SIZE) {
-			pr_err("pblk: could not add page to bio\n");
+			pblk_err(pblk, "could not add page to bio\n");
 			bio_put(bio);
 			bio = ERR_PTR(-ENOMEM);
 			goto out;
@@ -711,7 +712,7 @@ next_rq:
 			while (test_bit(pos, line->blk_bitmap)) {
 				paddr += min;
 				if (pblk_boundary_paddr_checks(pblk, paddr)) {
-					pr_err("pblk: corrupt emeta line:%d\n",
+					pblk_err(pblk, "corrupt emeta line:%d\n",
 								line->id);
 					bio_put(bio);
 					ret = -EINTR;
@@ -723,7 +724,7 @@ next_rq:
 			}
 
 			if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
-				pr_err("pblk: corrupt emeta line:%d\n",
+				pblk_err(pblk, "corrupt emeta line:%d\n",
 								line->id);
 				bio_put(bio);
 				ret = -EINTR;
@@ -738,7 +739,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, &rqd);
 	if (ret) {
-		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		goto free_rqd_dma;
 	}
@@ -843,7 +844,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	 */
 	ret = pblk_submit_io_sync(pblk, &rqd);
 	if (ret) {
-		pr_err("pblk: smeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "smeta I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		goto free_ppa_list;
 	}
@@ -905,7 +906,7 @@ static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_tgt_dev *dev = pblk->dev;
 		struct nvm_geo *geo = &dev->geo;
 
-		pr_err("pblk: could not sync erase line:%d,blk:%d\n",
+		pblk_err(pblk, "could not sync erase line:%d,blk:%d\n",
 					pblk_ppa_to_line(ppa),
 					pblk_ppa_to_pos(geo, ppa));
 
@@ -945,7 +946,7 @@ int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
 
 		ret = pblk_blk_erase_sync(pblk, ppa);
 		if (ret) {
-			pr_err("pblk: failed to erase line %d\n", line->id);
+			pblk_err(pblk, "failed to erase line %d\n", line->id);
 			return ret;
 		}
 	} while (1);
@@ -1012,7 +1013,7 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
 		list_add_tail(&line->list, &l_mg->bad_list);
 		spin_unlock(&l_mg->free_lock);
 
-		pr_debug("pblk: line %d is bad\n", line->id);
+		pblk_debug(pblk, "line %d is bad\n", line->id);
 
 		return 0;
 	}
@@ -1122,7 +1123,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 	line->cur_sec = off + lm->smeta_sec;
 
 	if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) {
-		pr_debug("pblk: line smeta I/O failed. Retry\n");
+		pblk_debug(pblk, "line smeta I/O failed. Retry\n");
 		return 0;
 	}
 
@@ -1154,7 +1155,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 		spin_unlock(&line->lock);
 
 		list_add_tail(&line->list, &l_mg->bad_list);
-		pr_err("pblk: unexpected line %d is bad\n", line->id);
+		pblk_err(pblk, "unexpected line %d is bad\n", line->id);
 
 		return 0;
 	}
@@ -1299,7 +1300,7 @@ struct pblk_line *pblk_line_get(struct pblk *pblk)
 
 retry:
 	if (list_empty(&l_mg->free_list)) {
-		pr_err("pblk: no free lines\n");
+		pblk_err(pblk, "no free lines\n");
 		return NULL;
 	}
 
@@ -1315,7 +1316,7 @@ retry:
 
 		list_add_tail(&line->list, &l_mg->bad_list);
 
-		pr_debug("pblk: line %d is bad\n", line->id);
+		pblk_debug(pblk, "line %d is bad\n", line->id);
 		goto retry;
 	}
 
@@ -1329,7 +1330,7 @@ retry:
 			list_add(&line->list, &l_mg->corrupt_list);
 			goto retry;
 		default:
-			pr_err("pblk: failed to prepare line %d\n", line->id);
+			pblk_err(pblk, "failed to prepare line %d\n", line->id);
 			list_add(&line->list, &l_mg->free_list);
 			l_mg->nr_free_lines++;
 			return NULL;
@@ -1477,7 +1478,7 @@ static void pblk_line_close_meta_sync(struct pblk *pblk)
 
 			ret = pblk_submit_meta_io(pblk, line);
 			if (ret) {
-				pr_err("pblk: sync meta line %d failed (%d)\n",
+				pblk_err(pblk, "sync meta line %d failed (%d)\n",
 							line->id, ret);
 				return;
 			}
@@ -1507,7 +1508,7 @@ void __pblk_pipeline_flush(struct pblk *pblk)
 
 	ret = pblk_recov_pad(pblk);
 	if (ret) {
-		pr_err("pblk: could not close data on teardown(%d)\n", ret);
+		pblk_err(pblk, "could not close data on teardown(%d)\n", ret);
 		return;
 	}
 
@@ -1687,7 +1688,7 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_tgt_dev *dev = pblk->dev;
 		struct nvm_geo *geo = &dev->geo;
 
-		pr_err("pblk: could not async erase line:%d,blk:%d\n",
+		pblk_err(pblk, "could not async erase line:%d,blk:%d\n",
 					pblk_ppa_to_line(ppa),
 					pblk_ppa_to_pos(geo, ppa));
 	}
@@ -1726,7 +1727,7 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
 	struct list_head *move_list;
 	int i;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN(!bitmap_full(line->map_bitmap, lm->sec_per_line),
 				"pblk: corrupt closed line %d\n", line->id);
 #endif
@@ -1856,7 +1857,7 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list,
 	 * Only send one inflight I/O per LUN. Since we map at a page
 	 * granurality, all ppas in the I/O will map to the same LUN
 	 */
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	int i;
 
 	for (i = 1; i < nr_ppas; i++)
@@ -1866,7 +1867,8 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list,
 
 	ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(30000));
 	if (ret == -ETIME || ret == -EINTR)
-		pr_err("pblk: taking lun semaphore timed out: err %d\n", -ret);
+		pblk_err(pblk, "taking lun semaphore timed out: err %d\n",
+				-ret);
 }
 
 void pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas)
@@ -1901,7 +1903,7 @@ void pblk_up_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas)
 	struct pblk_lun *rlun;
 	int pos = pblk_ppa_to_pos(geo, ppa_list[0]);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	int i;
 
 	for (i = 1; i < nr_ppas; i++)
@@ -1951,7 +1953,7 @@ void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
 void pblk_update_map_cache(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
 {
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(!pblk_addr_in_cache(ppa));
 	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
@@ -1966,7 +1968,7 @@ int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa_new,
 	struct ppa_addr ppa_l2p, ppa_gc;
 	int ret = 1;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(!pblk_addr_in_cache(ppa_new));
 	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa_new)));
@@ -2003,14 +2005,14 @@ void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
 {
 	struct ppa_addr ppa_l2p;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a device address */
 	BUG_ON(pblk_addr_in_cache(ppa_mapped));
 #endif
 	/* Invalidate and discard padded entries */
 	if (lba == ADDR_EMPTY) {
 		atomic64_inc(&pblk->pad_wa);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		atomic_long_inc(&pblk->padded_wb);
 #endif
 		if (!pblk_ppa_empty(ppa_mapped))
@@ -2036,7 +2038,7 @@ void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
 		goto out;
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN_ON(!pblk_addr_in_cache(ppa_l2p) && !pblk_ppa_empty(ppa_l2p));
 #endif
 
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 080469d90b40..157c2567c9e8 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -90,7 +90,7 @@ static void pblk_gc_line_ws(struct work_struct *work)
 
 	gc_rq->data = vmalloc(array_size(gc_rq->nr_secs, geo->csecs));
 	if (!gc_rq->data) {
-		pr_err("pblk: could not GC line:%d (%d/%d)\n",
+		pblk_err(pblk, "could not GC line:%d (%d/%d)\n",
 					line->id, *line->vsc, gc_rq->nr_secs);
 		goto out;
 	}
@@ -98,7 +98,7 @@ static void pblk_gc_line_ws(struct work_struct *work)
 	/* Read from GC victim block */
 	ret = pblk_submit_read_gc(pblk, gc_rq);
 	if (ret) {
-		pr_err("pblk: failed GC read in line:%d (err:%d)\n",
+		pblk_err(pblk, "failed GC read in line:%d (err:%d)\n",
 								line->id, ret);
 		goto out;
 	}
@@ -146,7 +146,7 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
 
 	ret = pblk_line_read_emeta(pblk, line, emeta_buf);
 	if (ret) {
-		pr_err("pblk: line %d read emeta failed (%d)\n",
+		pblk_err(pblk, "line %d read emeta failed (%d)\n",
 				line->id, ret);
 		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 		return NULL;
@@ -160,7 +160,7 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
 
 	ret = pblk_recov_check_emeta(pblk, emeta_buf);
 	if (ret) {
-		pr_err("pblk: inconsistent emeta (line %d)\n",
+		pblk_err(pblk, "inconsistent emeta (line %d)\n",
 				line->id);
 		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 		return NULL;
@@ -201,7 +201,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	} else {
 		lba_list = get_lba_list_from_emeta(pblk, line);
 		if (!lba_list) {
-			pr_err("pblk: could not interpret emeta (line %d)\n",
+			pblk_err(pblk, "could not interpret emeta (line %d)\n",
 					line->id);
 			goto fail_free_invalid_bitmap;
 		}
@@ -213,7 +213,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	spin_unlock(&line->lock);
 
 	if (sec_left < 0) {
-		pr_err("pblk: corrupted GC line (%d)\n", line->id);
+		pblk_err(pblk, "corrupted GC line (%d)\n", line->id);
 		goto fail_free_lba_list;
 	}
 
@@ -289,7 +289,7 @@ fail_free_ws:
 	kref_put(&line->ref, pblk_line_put);
 	atomic_dec(&gc->read_inflight_gc);
 
-	pr_err("pblk: Failed to GC line %d\n", line->id);
+	pblk_err(pblk, "failed to GC line %d\n", line->id);
 }
 
 static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
@@ -297,7 +297,7 @@ static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
 	struct pblk_gc *gc = &pblk->gc;
 	struct pblk_line_ws *line_ws;
 
-	pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
+	pblk_debug(pblk, "line '%d' being reclaimed for GC\n", line->id);
 
 	line_ws = kmalloc(sizeof(struct pblk_line_ws), GFP_KERNEL);
 	if (!line_ws)
@@ -351,7 +351,7 @@ static int pblk_gc_read(struct pblk *pblk)
 	pblk_gc_kick(pblk);
 
 	if (pblk_gc_line(pblk, line))
-		pr_err("pblk: failed to GC line %d\n", line->id);
+		pblk_err(pblk, "failed to GC line %d\n", line->id);
 
 	return 0;
 }
@@ -522,8 +522,8 @@ static int pblk_gc_reader_ts(void *data)
 		io_schedule();
 	}
 
-#ifdef CONFIG_NVM_DEBUG
-	pr_info("pblk: flushing gc pipeline, %d lines left\n",
+#ifdef CONFIG_NVM_PBLK_DEBUG
+	pblk_info(pblk, "flushing gc pipeline, %d lines left\n",
 		atomic_read(&gc->pipeline_gc));
 #endif
 
@@ -540,7 +540,7 @@ static int pblk_gc_reader_ts(void *data)
 static void pblk_gc_start(struct pblk *pblk)
 {
 	pblk->gc.gc_active = 1;
-	pr_debug("pblk: gc start\n");
+	pblk_debug(pblk, "gc start\n");
 }
 
 void pblk_gc_should_start(struct pblk *pblk)
@@ -605,14 +605,14 @@ int pblk_gc_init(struct pblk *pblk)
 
 	gc->gc_ts = kthread_create(pblk_gc_ts, pblk, "pblk-gc-ts");
 	if (IS_ERR(gc->gc_ts)) {
-		pr_err("pblk: could not allocate GC main kthread\n");
+		pblk_err(pblk, "could not allocate GC main kthread\n");
 		return PTR_ERR(gc->gc_ts);
 	}
 
 	gc->gc_writer_ts = kthread_create(pblk_gc_writer_ts, pblk,
 							"pblk-gc-writer-ts");
 	if (IS_ERR(gc->gc_writer_ts)) {
-		pr_err("pblk: could not allocate GC writer kthread\n");
+		pblk_err(pblk, "could not allocate GC writer kthread\n");
 		ret = PTR_ERR(gc->gc_writer_ts);
 		goto fail_free_main_kthread;
 	}
@@ -620,7 +620,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_reader_ts = kthread_create(pblk_gc_reader_ts, pblk,
 							"pblk-gc-reader-ts");
 	if (IS_ERR(gc->gc_reader_ts)) {
-		pr_err("pblk: could not allocate GC reader kthread\n");
+		pblk_err(pblk, "could not allocate GC reader kthread\n");
 		ret = PTR_ERR(gc->gc_reader_ts);
 		goto fail_free_writer_kthread;
 	}
@@ -641,7 +641,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_line_reader_wq = alloc_workqueue("pblk-gc-line-reader-wq",
 			WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_GC_MAX_READERS);
 	if (!gc->gc_line_reader_wq) {
-		pr_err("pblk: could not allocate GC line reader workqueue\n");
+		pblk_err(pblk, "could not allocate GC line reader workqueue\n");
 		ret = -ENOMEM;
 		goto fail_free_reader_kthread;
 	}
@@ -650,7 +650,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_reader_wq = alloc_workqueue("pblk-gc-line_wq",
 					WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
 	if (!gc->gc_reader_wq) {
-		pr_err("pblk: could not allocate GC reader workqueue\n");
+		pblk_err(pblk, "could not allocate GC reader workqueue\n");
 		ret = -ENOMEM;
 		goto fail_free_reader_line_wq;
 	}
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index b57f764d6a16..537e98f2b24a 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -91,7 +91,7 @@ static size_t pblk_trans_map_size(struct pblk *pblk)
 	return entry_size * pblk->rl.nr_secs;
 }
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static u32 pblk_l2p_crc(struct pblk *pblk)
 {
 	size_t map_size;
@@ -117,13 +117,13 @@ static int pblk_l2p_recover(struct pblk *pblk, bool factory_init)
 	} else {
 		line = pblk_recov_l2p(pblk);
 		if (IS_ERR(line)) {
-			pr_err("pblk: could not recover l2p table\n");
+			pblk_err(pblk, "could not recover l2p table\n");
 			return -EFAULT;
 		}
 	}
 
-#ifdef CONFIG_NVM_DEBUG
-	pr_info("pblk init: L2P CRC: %x\n", pblk_l2p_crc(pblk));
+#ifdef CONFIG_NVM_PBLK_DEBUG
+	pblk_info(pblk, "init: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
 	/* Free full lines directly as GC has not been started yet */
@@ -166,7 +166,7 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init)
 static void pblk_rwb_free(struct pblk *pblk)
 {
 	if (pblk_rb_tear_down_check(&pblk->rwb))
-		pr_err("pblk: write buffer error on tear down\n");
+		pblk_err(pblk, "write buffer error on tear down\n");
 
 	pblk_rb_data_free(&pblk->rwb);
 	vfree(pblk_rb_entries_ref(&pblk->rwb));
@@ -179,11 +179,14 @@ static int pblk_rwb_init(struct pblk *pblk)
 	struct pblk_rb_entry *entries;
 	unsigned long nr_entries, buffer_size;
 	unsigned int power_size, power_seg_sz;
+	int pgs_in_buffer;
 
-	if (write_buffer_size && (write_buffer_size > pblk->pgs_in_buffer))
+	pgs_in_buffer = max(geo->mw_cunits, geo->ws_opt) * geo->all_luns;
+
+	if (write_buffer_size && (write_buffer_size > pgs_in_buffer))
 		buffer_size = write_buffer_size;
 	else
-		buffer_size = pblk->pgs_in_buffer;
+		buffer_size = pgs_in_buffer;
 
 	nr_entries = pblk_rb_calculate_size(buffer_size);
 
@@ -200,7 +203,8 @@ static int pblk_rwb_init(struct pblk *pblk)
 /* Minimum pages needed within a lun */
 #define ADDR_POOL_SIZE 64
 
-static int pblk_set_addrf_12(struct nvm_geo *geo, struct nvm_addrf_12 *dst)
+static int pblk_set_addrf_12(struct pblk *pblk, struct nvm_geo *geo,
+			     struct nvm_addrf_12 *dst)
 {
 	struct nvm_addrf_12 *src = (struct nvm_addrf_12 *)&geo->addrf;
 	int power_len;
@@ -208,14 +212,14 @@ static int pblk_set_addrf_12(struct nvm_geo *geo, struct nvm_addrf_12 *dst)
 	/* Re-calculate channel and lun format to adapt to configuration */
 	power_len = get_count_order(geo->num_ch);
 	if (1 << power_len != geo->num_ch) {
-		pr_err("pblk: supports only power-of-two channel config.\n");
+		pblk_err(pblk, "supports only power-of-two channel config.\n");
 		return -EINVAL;
 	}
 	dst->ch_len = power_len;
 
 	power_len = get_count_order(geo->num_lun);
 	if (1 << power_len != geo->num_lun) {
-		pr_err("pblk: supports only power-of-two LUN config.\n");
+		pblk_err(pblk, "supports only power-of-two LUN config.\n");
 		return -EINVAL;
 	}
 	dst->lun_len = power_len;
@@ -282,18 +286,19 @@ static int pblk_set_addrf(struct pblk *pblk)
 	case NVM_OCSSD_SPEC_12:
 		div_u64_rem(geo->clba, pblk->min_write_pgs, &mod);
 		if (mod) {
-			pr_err("pblk: bad configuration of sectors/pages\n");
+			pblk_err(pblk, "bad configuration of sectors/pages\n");
 			return -EINVAL;
 		}
 
-		pblk->addrf_len = pblk_set_addrf_12(geo, (void *)&pblk->addrf);
+		pblk->addrf_len = pblk_set_addrf_12(pblk, geo,
+							(void *)&pblk->addrf);
 		break;
 	case NVM_OCSSD_SPEC_20:
 		pblk->addrf_len = pblk_set_addrf_20(geo, (void *)&pblk->addrf,
-								&pblk->uaddrf);
+							&pblk->uaddrf);
 		break;
 	default:
-		pr_err("pblk: OCSSD revision not supported (%d)\n",
+		pblk_err(pblk, "OCSSD revision not supported (%d)\n",
 								geo->version);
 		return -EINVAL;
 	}
@@ -366,15 +371,13 @@ static int pblk_core_init(struct pblk *pblk)
 	atomic64_set(&pblk->nr_flush, 0);
 	pblk->nr_flush_rst = 0;
 
-	pblk->pgs_in_buffer = geo->mw_cunits * geo->all_luns;
-
 	pblk->min_write_pgs = geo->ws_opt * (geo->csecs / PAGE_SIZE);
 	max_write_ppas = pblk->min_write_pgs * geo->all_luns;
 	pblk->max_write_pgs = min_t(int, max_write_ppas, NVM_MAX_VLBA);
 	pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
 
 	if (pblk->max_write_pgs > PBLK_MAX_REQ_ADDRS) {
-		pr_err("pblk: vector list too big(%u > %u)\n",
+		pblk_err(pblk, "vector list too big(%u > %u)\n",
 				pblk->max_write_pgs, PBLK_MAX_REQ_ADDRS);
 		return -EINVAL;
 	}
@@ -607,7 +610,7 @@ static int pblk_luns_init(struct pblk *pblk)
 
 	/* TODO: Implement unbalanced LUN support */
 	if (geo->num_lun < 0) {
-		pr_err("pblk: unbalanced LUN config.\n");
+		pblk_err(pblk, "unbalanced LUN config.\n");
 		return -EINVAL;
 	}
 
@@ -716,10 +719,11 @@ static int pblk_setup_line_meta_12(struct pblk *pblk, struct pblk_line *line,
 
 		/*
 		 * In 1.2 spec. chunk state is not persisted by the device. Thus
-		 * some of the values are reset each time pblk is instantiated.
+		 * some of the values are reset each time pblk is instantiated,
+		 * so we have to assume that the block is closed.
 		 */
 		if (lun_bb_meta[line->id] == NVM_BLK_T_FREE)
-			chunk->state =  NVM_CHK_ST_FREE;
+			chunk->state =  NVM_CHK_ST_CLOSED;
 		else
 			chunk->state = NVM_CHK_ST_OFFLINE;
 
@@ -1026,7 +1030,7 @@ add_emeta_page:
 					lm->emeta_sec[0], geo->clba);
 
 	if (lm->min_blk_line > lm->blk_per_line) {
-		pr_err("pblk: config. not supported. Min. LUN in line:%d\n",
+		pblk_err(pblk, "config. not supported. Min. LUN in line:%d\n",
 							lm->blk_per_line);
 		return -EINVAL;
 	}
@@ -1078,7 +1082,7 @@ static int pblk_lines_init(struct pblk *pblk)
 	}
 
 	if (!nr_free_chks) {
-		pr_err("pblk: too many bad blocks prevent for sane instance\n");
+		pblk_err(pblk, "too many bad blocks prevent for sane instance\n");
 		return -EINTR;
 	}
 
@@ -1108,7 +1112,7 @@ static int pblk_writer_init(struct pblk *pblk)
 		int err = PTR_ERR(pblk->writer_ts);
 
 		if (err != -EINTR)
-			pr_err("pblk: could not allocate writer kthread (%d)\n",
+			pblk_err(pblk, "could not allocate writer kthread (%d)\n",
 					err);
 		return err;
 	}
@@ -1154,7 +1158,7 @@ static void pblk_tear_down(struct pblk *pblk, bool graceful)
 	pblk_rb_sync_l2p(&pblk->rwb);
 	pblk_rl_free(&pblk->rl);
 
-	pr_debug("pblk: consistent tear down (graceful:%d)\n", graceful);
+	pblk_debug(pblk, "consistent tear down (graceful:%d)\n", graceful);
 }
 
 static void pblk_exit(void *private, bool graceful)
@@ -1165,8 +1169,8 @@ static void pblk_exit(void *private, bool graceful)
 	pblk_gc_exit(pblk, graceful);
 	pblk_tear_down(pblk, graceful);
 
-#ifdef CONFIG_NVM_DEBUG
-	pr_info("pblk exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
+#ifdef CONFIG_NVM_PBLK_DEBUG
+	pblk_info(pblk, "exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
 	pblk_free(pblk);
@@ -1189,34 +1193,35 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	struct pblk *pblk;
 	int ret;
 
-	/* pblk supports 1.2 and 2.0 versions */
+	pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
+	if (!pblk)
+		return ERR_PTR(-ENOMEM);
+
+	pblk->dev = dev;
+	pblk->disk = tdisk;
+	pblk->state = PBLK_STATE_RUNNING;
+	pblk->gc.gc_enabled = 0;
+
 	if (!(geo->version == NVM_OCSSD_SPEC_12 ||
 					geo->version == NVM_OCSSD_SPEC_20)) {
-		pr_err("pblk: OCSSD version not supported (%u)\n",
+		pblk_err(pblk, "OCSSD version not supported (%u)\n",
 							geo->version);
+		kfree(pblk);
 		return ERR_PTR(-EINVAL);
 	}
 
 	if (geo->version == NVM_OCSSD_SPEC_12 && geo->dom & NVM_RSP_L2P) {
-		pr_err("pblk: host-side L2P table not supported. (%x)\n",
+		pblk_err(pblk, "host-side L2P table not supported. (%x)\n",
 							geo->dom);
+		kfree(pblk);
 		return ERR_PTR(-EINVAL);
 	}
 
-	pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
-	if (!pblk)
-		return ERR_PTR(-ENOMEM);
-
-	pblk->dev = dev;
-	pblk->disk = tdisk;
-	pblk->state = PBLK_STATE_RUNNING;
-	pblk->gc.gc_enabled = 0;
-
 	spin_lock_init(&pblk->resubmit_lock);
 	spin_lock_init(&pblk->trans_lock);
 	spin_lock_init(&pblk->lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_set(&pblk->inflight_writes, 0);
 	atomic_long_set(&pblk->padded_writes, 0);
 	atomic_long_set(&pblk->padded_wb, 0);
@@ -1241,38 +1246,38 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 
 	ret = pblk_core_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize core\n");
+		pblk_err(pblk, "could not initialize core\n");
 		goto fail;
 	}
 
 	ret = pblk_lines_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize lines\n");
+		pblk_err(pblk, "could not initialize lines\n");
 		goto fail_free_core;
 	}
 
 	ret = pblk_rwb_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize write buffer\n");
+		pblk_err(pblk, "could not initialize write buffer\n");
 		goto fail_free_lines;
 	}
 
 	ret = pblk_l2p_init(pblk, flags & NVM_TARGET_FACTORY);
 	if (ret) {
-		pr_err("pblk: could not initialize maps\n");
+		pblk_err(pblk, "could not initialize maps\n");
 		goto fail_free_rwb;
 	}
 
 	ret = pblk_writer_init(pblk);
 	if (ret) {
 		if (ret != -EINTR)
-			pr_err("pblk: could not initialize write thread\n");
+			pblk_err(pblk, "could not initialize write thread\n");
 		goto fail_free_l2p;
 	}
 
 	ret = pblk_gc_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize gc\n");
+		pblk_err(pblk, "could not initialize gc\n");
 		goto fail_stop_writer;
 	}
 
@@ -1287,8 +1292,7 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	blk_queue_max_discard_sectors(tqueue, UINT_MAX >> 9);
 	blk_queue_flag_set(QUEUE_FLAG_DISCARD, tqueue);
 
-	pr_info("pblk(%s): luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
-			tdisk->disk_name,
+	pblk_info(pblk, "luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
 			geo->all_luns, pblk->l_mg.nr_lines,
 			(unsigned long long)pblk->rl.nr_secs,
 			pblk->rwb.nr_entries);
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 55e9442a99e2..f6eec0212dfc 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -111,7 +111,7 @@ int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
 	} while (iter > 0);
 	up_write(&pblk_rb_lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_set(&rb->inflight_flush_point, 0);
 #endif
 
@@ -308,7 +308,7 @@ void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
 
 	entry = &rb->entries[ring_pos];
 	flags = READ_ONCE(entry->w_ctx.flags);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must guarantee that the entry is free */
 	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
 #endif
@@ -332,7 +332,7 @@ void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
 
 	entry = &rb->entries[ring_pos];
 	flags = READ_ONCE(entry->w_ctx.flags);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must guarantee that the entry is free */
 	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
 #endif
@@ -362,7 +362,7 @@ static int pblk_rb_flush_point_set(struct pblk_rb *rb, struct bio *bio,
 		return 0;
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_inc(&rb->inflight_flush_point);
 #endif
 
@@ -547,7 +547,7 @@ try:
 
 		page = virt_to_page(entry->data);
 		if (!page) {
-			pr_err("pblk: could not allocate write bio page\n");
+			pblk_err(pblk, "could not allocate write bio page\n");
 			flags &= ~PBLK_WRITTEN_DATA;
 			flags |= PBLK_SUBMITTED_ENTRY;
 			/* Release flags on context. Protect from writes */
@@ -557,7 +557,7 @@ try:
 
 		if (bio_add_pc_page(q, bio, page, rb->seg_size, 0) !=
 								rb->seg_size) {
-			pr_err("pblk: could not add page to write bio\n");
+			pblk_err(pblk, "could not add page to write bio\n");
 			flags &= ~PBLK_WRITTEN_DATA;
 			flags |= PBLK_SUBMITTED_ENTRY;
 			/* Release flags on context. Protect from writes */
@@ -576,19 +576,19 @@ try:
 
 	if (pad) {
 		if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, pad)) {
-			pr_err("pblk: could not pad page in write bio\n");
+			pblk_err(pblk, "could not pad page in write bio\n");
 			return NVM_IO_ERR;
 		}
 
 		if (pad < pblk->min_write_pgs)
 			atomic64_inc(&pblk->pad_dist[pad - 1]);
 		else
-			pr_warn("pblk: padding more than min. sectors\n");
+			pblk_warn(pblk, "padding more than min. sectors\n");
 
 		atomic64_add(pad, &pblk->pad_wa);
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(pad, &pblk->padded_writes);
 #endif
 
@@ -613,7 +613,7 @@ int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
 	int ret = 1;
 
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must ensure that the access will not cause an overflow */
 	BUG_ON(pos >= rb->nr_entries);
 #endif
@@ -820,7 +820,7 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
 			rb->subm,
 			rb->sync,
 			rb->l2p_update,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_read(&rb->inflight_flush_point),
 #else
 			0,
@@ -838,7 +838,7 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
 			rb->subm,
 			rb->sync,
 			rb->l2p_update,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_read(&rb->inflight_flush_point),
 #else
 			0,
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 18694694e5f0..5a46d7f9302f 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -28,7 +28,7 @@ static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
 				sector_t lba, struct ppa_addr ppa,
 				int bio_iter, bool advanced_bio)
 {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(pblk_ppa_empty(ppa));
 	BUG_ON(!pblk_addr_in_cache(ppa));
@@ -79,7 +79,7 @@ retry:
 			WARN_ON(test_and_set_bit(i, read_bitmap));
 			meta_list[i].lba = cpu_to_le64(lba);
 			advanced_bio = true;
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_long_inc(&pblk->cache_reads);
 #endif
 		} else {
@@ -97,7 +97,7 @@ next:
 	else
 		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(nr_secs, &pblk->inflight_reads);
 #endif
 }
@@ -117,13 +117,13 @@ static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
 			continue;
 
 		if (lba != blba + i) {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			struct ppa_addr *p;
 
 			p = (nr_lbas == 1) ? &rqd->ppa_list[i] : &rqd->ppa_addr;
-			print_ppa(&pblk->dev->geo, p, "seq", i);
+			print_ppa(pblk, p, "seq", i);
 #endif
-			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
 							lba, (u64)blba + i);
 			WARN_ON(1);
 		}
@@ -149,14 +149,14 @@ static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
 		meta_lba = le64_to_cpu(meta_lba_list[j].lba);
 
 		if (lba != meta_lba) {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			struct ppa_addr *p;
 			int nr_ppas = rqd->nr_ppas;
 
 			p = (nr_ppas == 1) ? &rqd->ppa_list[j] : &rqd->ppa_addr;
-			print_ppa(&pblk->dev->geo, p, "seq", j);
+			print_ppa(pblk, p, "seq", j);
 #endif
-			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
 								lba, meta_lba);
 			WARN_ON(1);
 		}
@@ -185,7 +185,7 @@ static void pblk_read_put_rqd_kref(struct pblk *pblk, struct nvm_rq *rqd)
 
 static void pblk_end_user_read(struct bio *bio)
 {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN_ONCE(bio->bi_status, "pblk: corrupted read bio\n");
 #endif
 	bio_endio(bio);
@@ -199,7 +199,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 	struct bio *int_bio = rqd->bio;
 	unsigned long start_time = r_ctx->start_time;
 
-	generic_end_io_acct(dev->q, READ, &pblk->disk->part0, start_time);
+	generic_end_io_acct(dev->q, REQ_OP_READ, &pblk->disk->part0, start_time);
 
 	if (rqd->error)
 		pblk_log_read_err(pblk, rqd);
@@ -212,7 +212,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 	if (put_line)
 		pblk_read_put_rqd_kref(pblk, rqd);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(rqd->nr_ppas, &pblk->sync_reads);
 	atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads);
 #endif
@@ -231,74 +231,36 @@ static void pblk_end_io_read(struct nvm_rq *rqd)
 	__pblk_end_io_read(pblk, rqd, true);
 }
 
-static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
-			     struct bio *orig_bio, unsigned int bio_init_idx,
-			     unsigned long *read_bitmap)
+static void pblk_end_partial_read(struct nvm_rq *rqd)
 {
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
-	struct bio *new_bio;
+	struct pblk *pblk = rqd->private;
+	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_pr_ctx *pr_ctx = r_ctx->private;
+	struct bio *new_bio = rqd->bio;
+	struct bio *bio = pr_ctx->orig_bio;
 	struct bio_vec src_bv, dst_bv;
-	void *ppa_ptr = NULL;
-	void *src_p, *dst_p;
-	dma_addr_t dma_ppa_list = 0;
-	__le64 *lba_list_mem, *lba_list_media;
-	int nr_secs = rqd->nr_ppas;
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	int bio_init_idx = pr_ctx->bio_init_idx;
+	unsigned long *read_bitmap = pr_ctx->bitmap;
+	int nr_secs = pr_ctx->orig_nr_secs;
 	int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
-	int i, ret, hole;
-
-	/* Re-use allocated memory for intermediate lbas */
-	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
-	lba_list_media = (((void *)rqd->ppa_list) + 2 * pblk_dma_ppa_size);
-
-	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
-
-	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
-		goto fail_add_pages;
-
-	if (nr_holes != new_bio->bi_vcnt) {
-		pr_err("pblk: malformed bio\n");
-		goto fail;
-	}
-
-	for (i = 0; i < nr_secs; i++)
-		lba_list_mem[i] = meta_list[i].lba;
-
-	new_bio->bi_iter.bi_sector = 0; /* internal bio */
-	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
-
-	rqd->bio = new_bio;
-	rqd->nr_ppas = nr_holes;
-	rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
-
-	if (unlikely(nr_holes == 1)) {
-		ppa_ptr = rqd->ppa_list;
-		dma_ppa_list = rqd->dma_ppa_list;
-		rqd->ppa_addr = rqd->ppa_list[0];
-	}
-
-	ret = pblk_submit_io_sync(pblk, rqd);
-	if (ret) {
-		bio_put(rqd->bio);
-		pr_err("pblk: sync read IO submission failed\n");
-		goto fail;
-	}
-
-	if (rqd->error) {
-		atomic_long_inc(&pblk->read_failed);
-#ifdef CONFIG_NVM_DEBUG
-		pblk_print_failed_rqd(pblk, rqd, rqd->error);
-#endif
-	}
+	__le64 *lba_list_mem, *lba_list_media;
+	void *src_p, *dst_p;
+	int hole, i;
 
 	if (unlikely(nr_holes == 1)) {
 		struct ppa_addr ppa;
 
 		ppa = rqd->ppa_addr;
-		rqd->ppa_list = ppa_ptr;
-		rqd->dma_ppa_list = dma_ppa_list;
+		rqd->ppa_list = pr_ctx->ppa_ptr;
+		rqd->dma_ppa_list = pr_ctx->dma_ppa_list;
 		rqd->ppa_list[0] = ppa;
 	}
 
+	/* Re-use allocated memory for intermediate lbas */
+	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
+	lba_list_media = (((void *)rqd->ppa_list) + 2 * pblk_dma_ppa_size);
+
 	for (i = 0; i < nr_secs; i++) {
 		lba_list_media[i] = meta_list[i].lba;
 		meta_list[i].lba = lba_list_mem[i];
@@ -316,7 +278,7 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 		meta_list[hole].lba = lba_list_media[i];
 
 		src_bv = new_bio->bi_io_vec[i++];
-		dst_bv = orig_bio->bi_io_vec[bio_init_idx + hole];
+		dst_bv = bio->bi_io_vec[bio_init_idx + hole];
 
 		src_p = kmap_atomic(src_bv.bv_page);
 		dst_p = kmap_atomic(dst_bv.bv_page);
@@ -334,19 +296,107 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 	} while (hole < nr_secs);
 
 	bio_put(new_bio);
+	kfree(pr_ctx);
 
 	/* restore original request */
 	rqd->bio = NULL;
 	rqd->nr_ppas = nr_secs;
 
+	bio_endio(bio);
 	__pblk_end_io_read(pblk, rqd, false);
-	return NVM_IO_DONE;
+}
 
-fail:
-	/* Free allocated pages in new bio */
+static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
+			    unsigned int bio_init_idx,
+			    unsigned long *read_bitmap,
+			    int nr_holes)
+{
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_pr_ctx *pr_ctx;
+	struct bio *new_bio, *bio = r_ctx->private;
+	__le64 *lba_list_mem;
+	int nr_secs = rqd->nr_ppas;
+	int i;
+
+	/* Re-use allocated memory for intermediate lbas */
+	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
+
+	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
+
+	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
+		goto fail_bio_put;
+
+	if (nr_holes != new_bio->bi_vcnt) {
+		WARN_ONCE(1, "pblk: malformed bio\n");
+		goto fail_free_pages;
+	}
+
+	pr_ctx = kmalloc(sizeof(struct pblk_pr_ctx), GFP_KERNEL);
+	if (!pr_ctx)
+		goto fail_free_pages;
+
+	for (i = 0; i < nr_secs; i++)
+		lba_list_mem[i] = meta_list[i].lba;
+
+	new_bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
+
+	rqd->bio = new_bio;
+	rqd->nr_ppas = nr_holes;
+	rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
+	pr_ctx->ppa_ptr = NULL;
+	pr_ctx->orig_bio = bio;
+	bitmap_copy(pr_ctx->bitmap, read_bitmap, NVM_MAX_VLBA);
+	pr_ctx->bio_init_idx = bio_init_idx;
+	pr_ctx->orig_nr_secs = nr_secs;
+	r_ctx->private = pr_ctx;
+
+	if (unlikely(nr_holes == 1)) {
+		pr_ctx->ppa_ptr = rqd->ppa_list;
+		pr_ctx->dma_ppa_list = rqd->dma_ppa_list;
+		rqd->ppa_addr = rqd->ppa_list[0];
+	}
+	return 0;
+
+fail_free_pages:
 	pblk_bio_free_pages(pblk, new_bio, 0, new_bio->bi_vcnt);
-fail_add_pages:
-	pr_err("pblk: failed to perform partial read\n");
+fail_bio_put:
+	bio_put(new_bio);
+
+	return -ENOMEM;
+}
+
+static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
+				 unsigned int bio_init_idx,
+				 unsigned long *read_bitmap, int nr_secs)
+{
+	int nr_holes;
+	int ret;
+
+	nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
+
+	if (pblk_setup_partial_read(pblk, rqd, bio_init_idx, read_bitmap,
+				    nr_holes))
+		return NVM_IO_ERR;
+
+	rqd->end_io = pblk_end_partial_read;
+
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		bio_put(rqd->bio);
+		pblk_err(pblk, "partial read IO submission failed\n");
+		goto err;
+	}
+
+	return NVM_IO_OK;
+
+err:
+	pblk_err(pblk, "failed to perform partial read\n");
+
+	/* Free allocated pages in new bio */
+	pblk_bio_free_pages(pblk, rqd->bio, 0, rqd->bio->bi_vcnt);
 	__pblk_end_io_read(pblk, rqd, false);
 	return NVM_IO_ERR;
 }
@@ -359,7 +409,7 @@ static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
 
 	pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_inc(&pblk->inflight_reads);
 #endif
 
@@ -382,7 +432,7 @@ retry:
 		WARN_ON(test_and_set_bit(0, read_bitmap));
 		meta_list[0].lba = cpu_to_le64(lba);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		atomic_long_inc(&pblk->cache_reads);
 #endif
 	} else {
@@ -401,7 +451,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	struct pblk_g_ctx *r_ctx;
 	struct nvm_rq *rqd;
 	unsigned int bio_init_idx;
-	unsigned long read_bitmap; /* Max 64 ppas per request */
+	DECLARE_BITMAP(read_bitmap, NVM_MAX_VLBA);
 	int ret = NVM_IO_ERR;
 
 	/* logic error: lba out-of-bounds. Ignore read request */
@@ -411,9 +461,10 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		return NVM_IO_ERR;
 	}
 
-	generic_start_io_acct(q, READ, bio_sectors(bio), &pblk->disk->part0);
+	generic_start_io_acct(q, REQ_OP_READ, bio_sectors(bio),
+			      &pblk->disk->part0);
 
-	bitmap_zero(&read_bitmap, nr_secs);
+	bitmap_zero(read_bitmap, nr_secs);
 
 	rqd = pblk_alloc_rqd(pblk, PBLK_READ);
 
@@ -436,7 +487,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
 							&rqd->dma_meta_list);
 	if (!rqd->meta_list) {
-		pr_err("pblk: not able to allocate ppa list\n");
+		pblk_err(pblk, "not able to allocate ppa list\n");
 		goto fail_rqd_free;
 	}
 
@@ -444,32 +495,32 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
 		rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
 
-		pblk_read_ppalist_rq(pblk, rqd, bio, blba, &read_bitmap);
+		pblk_read_ppalist_rq(pblk, rqd, bio, blba, read_bitmap);
 	} else {
-		pblk_read_rq(pblk, rqd, bio, blba, &read_bitmap);
+		pblk_read_rq(pblk, rqd, bio, blba, read_bitmap);
 	}
 
-	if (bitmap_full(&read_bitmap, nr_secs)) {
+	if (bitmap_full(read_bitmap, nr_secs)) {
 		atomic_inc(&pblk->inflight_io);
 		__pblk_end_io_read(pblk, rqd, false);
 		return NVM_IO_DONE;
 	}
 
 	/* All sectors are to be read from the device */
-	if (bitmap_empty(&read_bitmap, rqd->nr_ppas)) {
+	if (bitmap_empty(read_bitmap, rqd->nr_ppas)) {
 		struct bio *int_bio = NULL;
 
 		/* Clone read bio to deal with read errors internally */
 		int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);
 		if (!int_bio) {
-			pr_err("pblk: could not clone read bio\n");
+			pblk_err(pblk, "could not clone read bio\n");
 			goto fail_end_io;
 		}
 
 		rqd->bio = int_bio;
 
 		if (pblk_submit_io(pblk, rqd)) {
-			pr_err("pblk: read IO submission failed\n");
+			pblk_err(pblk, "read IO submission failed\n");
 			ret = NVM_IO_ERR;
 			goto fail_end_io;
 		}
@@ -480,8 +531,15 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	/* The read bio request could be partially filled by the write buffer,
 	 * but there are some holes that need to be read from the drive.
 	 */
-	return pblk_partial_read(pblk, rqd, bio, bio_init_idx, &read_bitmap);
+	ret = pblk_partial_read_bio(pblk, rqd, bio_init_idx, read_bitmap,
+				    nr_secs);
+	if (ret)
+		goto fail_meta_free;
+
+	return NVM_IO_OK;
 
+fail_meta_free:
+	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 fail_rqd_free:
 	pblk_free_rqd(pblk, rqd, PBLK_READ);
 	return ret;
@@ -514,7 +572,7 @@ static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
 		rqd->ppa_list[valid_secs++] = ppa_list_l2p[i];
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(valid_secs, &pblk->inflight_reads);
 #endif
 
@@ -548,7 +606,7 @@ static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
 	rqd->ppa_addr = ppa_l2p;
 	valid_secs = 1;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_inc(&pblk->inflight_reads);
 #endif
 
@@ -595,7 +653,8 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 	bio = pblk_bio_map_addr(pblk, gc_rq->data, gc_rq->secs_to_gc, data_len,
 						PBLK_VMALLOC_META, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		pr_err("pblk: could not allocate GC bio (%lu)\n", PTR_ERR(bio));
+		pblk_err(pblk, "could not allocate GC bio (%lu)\n",
+				PTR_ERR(bio));
 		goto err_free_dma;
 	}
 
@@ -609,7 +668,7 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 
 	if (pblk_submit_io_sync(pblk, &rqd)) {
 		ret = -EIO;
-		pr_err("pblk: GC read request failed\n");
+		pblk_err(pblk, "GC read request failed\n");
 		goto err_free_bio;
 	}
 
@@ -619,12 +678,12 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 
 	if (rqd.error) {
 		atomic_long_inc(&pblk->read_failed_gc);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		pblk_print_failed_rqd(pblk, &rqd, rqd.error);
 #endif
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(gc_rq->secs_to_gc, &pblk->sync_reads);
 	atomic_long_add(gc_rq->secs_to_gc, &pblk->recov_gc_reads);
 	atomic_long_sub(gc_rq->secs_to_gc, &pblk->inflight_reads);
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 3a5069183859..e232e47e1353 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -77,7 +77,7 @@ static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
 	}
 
 	if (nr_valid_lbas != nr_lbas)
-		pr_err("pblk: line %d - inconsistent lba list(%llu/%llu)\n",
+		pblk_err(pblk, "line %d - inconsistent lba list(%llu/%llu)\n",
 				line->id, nr_valid_lbas, nr_lbas);
 
 	line->left_msecs = 0;
@@ -184,7 +184,7 @@ next_read_rq:
 	/* If read fails, more padding is needed */
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		return ret;
 	}
 
@@ -194,7 +194,7 @@ next_read_rq:
 	 * we cannot recover from here. Need FTL log.
 	 */
 	if (rqd->error && rqd->error != NVM_RSP_WARN_HIGHECC) {
-		pr_err("pblk: L2P recovery failed (%d)\n", rqd->error);
+		pblk_err(pblk, "L2P recovery failed (%d)\n", rqd->error);
 		return -EINTR;
 	}
 
@@ -273,7 +273,7 @@ static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
 next_pad_rq:
 	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
 	if (rq_ppas < pblk->min_write_pgs) {
-		pr_err("pblk: corrupted pad line %d\n", line->id);
+		pblk_err(pblk, "corrupted pad line %d\n", line->id);
 		goto fail_free_pad;
 	}
 
@@ -342,7 +342,7 @@ next_pad_rq:
 
 	ret = pblk_submit_io(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		pblk_up_page(pblk, rqd->ppa_list, rqd->nr_ppas);
 		goto fail_free_bio;
 	}
@@ -356,12 +356,12 @@ next_pad_rq:
 
 	if (!wait_for_completion_io_timeout(&pad_rq->wait,
 				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
-		pr_err("pblk: pad write timed out\n");
+		pblk_err(pblk, "pad write timed out\n");
 		ret = -ETIME;
 	}
 
 	if (!pblk_line_is_full(line))
-		pr_err("pblk: corrupted padded line: %d\n", line->id);
+		pblk_err(pblk, "corrupted padded line: %d\n", line->id);
 
 	vfree(data);
 free_rq:
@@ -461,7 +461,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		return ret;
 	}
 
@@ -501,11 +501,11 @@ next_rq:
 
 		ret = pblk_recov_pad_oob(pblk, line, pad_secs);
 		if (ret)
-			pr_err("pblk: OOB padding failed (err:%d)\n", ret);
+			pblk_err(pblk, "OOB padding failed (err:%d)\n", ret);
 
 		ret = pblk_recov_read_oob(pblk, line, p, r_ptr);
 		if (ret)
-			pr_err("pblk: OOB read failed (err:%d)\n", ret);
+			pblk_err(pblk, "OOB read failed (err:%d)\n", ret);
 
 		left_ppas = 0;
 	}
@@ -592,7 +592,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		return ret;
 	}
@@ -671,14 +671,14 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
 
 	ret = pblk_recov_scan_oob(pblk, line, p, &done);
 	if (ret) {
-		pr_err("pblk: could not recover L2P from OOB\n");
+		pblk_err(pblk, "could not recover L2P from OOB\n");
 		goto out;
 	}
 
 	if (!done) {
 		ret = pblk_recov_scan_all_oob(pblk, line, p);
 		if (ret) {
-			pr_err("pblk: could not recover L2P from OOB\n");
+			pblk_err(pblk, "could not recover L2P from OOB\n");
 			goto out;
 		}
 	}
@@ -737,14 +737,15 @@ static int pblk_recov_check_line_version(struct pblk *pblk,
 	struct line_header *header = &emeta->header;
 
 	if (header->version_major != EMETA_VERSION_MAJOR) {
-		pr_err("pblk: line major version mismatch: %d, expected: %d\n",
-		       header->version_major, EMETA_VERSION_MAJOR);
+		pblk_err(pblk, "line major version mismatch: %d, expected: %d\n",
+			 header->version_major, EMETA_VERSION_MAJOR);
 		return 1;
 	}
 
-#ifdef NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (header->version_minor > EMETA_VERSION_MINOR)
-		pr_info("pblk: newer line minor version found: %d\n", line_v);
+		pblk_info(pblk, "newer line minor version found: %d\n",
+				header->version_minor);
 #endif
 
 	return 0;
@@ -851,7 +852,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 			continue;
 
 		if (smeta_buf->header.version_major != SMETA_VERSION_MAJOR) {
-			pr_err("pblk: found incompatible line version %u\n",
+			pblk_err(pblk, "found incompatible line version %u\n",
 					smeta_buf->header.version_major);
 			return ERR_PTR(-EINVAL);
 		}
@@ -863,7 +864,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 		}
 
 		if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) {
-			pr_debug("pblk: ignore line %u due to uuid mismatch\n",
+			pblk_debug(pblk, "ignore line %u due to uuid mismatch\n",
 					i);
 			continue;
 		}
@@ -887,7 +888,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 
 		pblk_recov_line_add_ordered(&recov_list, line);
 		found_lines++;
-		pr_debug("pblk: recovering data line %d, seq:%llu\n",
+		pblk_debug(pblk, "recovering data line %d, seq:%llu\n",
 						line->id, smeta_buf->seq_nr);
 	}
 
@@ -947,7 +948,7 @@ next:
 			line->emeta = NULL;
 		} else {
 			if (open_lines > 1)
-				pr_err("pblk: failed to recover L2P\n");
+				pblk_err(pblk, "failed to recover L2P\n");
 
 			open_lines++;
 			line->meta_line = meta_line;
@@ -976,7 +977,7 @@ next:
 
 out:
 	if (found_lines != recovered_lines)
-		pr_err("pblk: failed to recover all found lines %d/%d\n",
+		pblk_err(pblk, "failed to recover all found lines %d/%d\n",
 						found_lines, recovered_lines);
 
 	return data_line;
@@ -999,7 +1000,7 @@ int pblk_recov_pad(struct pblk *pblk)
 
 	ret = pblk_recov_pad_oob(pblk, line, left_msecs);
 	if (ret) {
-		pr_err("pblk: Tear down padding failed (%d)\n", ret);
+		pblk_err(pblk, "tear down padding failed (%d)\n", ret);
 		return ret;
 	}
 
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
index 88a0a7c407aa..9fc3dfa168b4 100644
--- a/drivers/lightnvm/pblk-sysfs.c
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -268,7 +268,7 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
 	spin_unlock(&l_mg->free_lock);
 
 	if (nr_free_lines != free_line_cnt)
-		pr_err("pblk: corrupted free line list:%d/%d\n",
+		pblk_err(pblk, "corrupted free line list:%d/%d\n",
 						nr_free_lines, free_line_cnt);
 
 	sz = snprintf(page, PAGE_SIZE - sz,
@@ -421,7 +421,7 @@ static ssize_t pblk_sysfs_get_padding_dist(struct pblk *pblk, char *page)
 	return sz;
 }
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
 {
 	return snprintf(page, PAGE_SIZE,
@@ -598,7 +598,7 @@ static struct attribute sys_padding_dist = {
 	.mode = 0644,
 };
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static struct attribute sys_stats_debug_attr = {
 	.name = "stats",
 	.mode = 0444,
@@ -619,7 +619,7 @@ static struct attribute *pblk_attrs[] = {
 	&sys_write_amp_mileage,
 	&sys_write_amp_trip,
 	&sys_padding_dist,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	&sys_stats_debug_attr,
 #endif
 	NULL,
@@ -654,7 +654,7 @@ static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr,
 		return pblk_sysfs_get_write_amp_trip(pblk, buf);
 	else if (strcmp(attr->name, "padding_dist") == 0)
 		return pblk_sysfs_get_padding_dist(pblk, buf);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	else if (strcmp(attr->name, "stats") == 0)
 		return pblk_sysfs_stats_debug(pblk, buf);
 #endif
@@ -697,8 +697,7 @@ int pblk_sysfs_init(struct gendisk *tdisk)
 					kobject_get(&parent_dev->kobj),
 					"%s", "pblk");
 	if (ret) {
-		pr_err("pblk: could not register %s/pblk\n",
-						tdisk->disk_name);
+		pblk_err(pblk, "could not register\n");
 		return ret;
 	}
 
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index f353e52941f5..ee774a86cf1e 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -38,7 +38,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 			/* Release flags on context. Protect from writes */
 			smp_store_release(&w_ctx->flags, flags);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_dec(&rwb->inflight_flush_point);
 #endif
 		}
@@ -51,7 +51,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 		pblk_bio_free_pages(pblk, rqd->bio, c_ctx->nr_valid,
 							c_ctx->nr_padded);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(rqd->nr_ppas, &pblk->sync_writes);
 #endif
 
@@ -78,7 +78,7 @@ static void pblk_complete_write(struct pblk *pblk, struct nvm_rq *rqd,
 	unsigned long flags;
 	unsigned long pos;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_sub(c_ctx->nr_valid, &pblk->inflight_writes);
 #endif
 
@@ -196,7 +196,7 @@ static void pblk_queue_resubmit(struct pblk *pblk, struct pblk_c_ctx *c_ctx)
 	list_add_tail(&r_ctx->list, &pblk->resubmit_list);
 	spin_unlock(&pblk->resubmit_lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(c_ctx->nr_valid, &pblk->recov_writes);
 #endif
 }
@@ -238,7 +238,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
 
 	recovery = mempool_alloc(&pblk->rec_pool, GFP_ATOMIC);
 	if (!recovery) {
-		pr_err("pblk: could not allocate recovery work\n");
+		pblk_err(pblk, "could not allocate recovery work\n");
 		return;
 	}
 
@@ -258,7 +258,7 @@ static void pblk_end_io_write(struct nvm_rq *rqd)
 		pblk_end_w_fail(pblk, rqd);
 		return;
 	}
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	else
 		WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n");
 #endif
@@ -279,7 +279,7 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 
 	if (rqd->error) {
 		pblk_log_write_err(pblk, rqd);
-		pr_err("pblk: metadata I/O failed. Line %d\n", line->id);
+		pblk_err(pblk, "metadata I/O failed. Line %d\n", line->id);
 		line->w_err_gc->has_write_err = 1;
 	}
 
@@ -356,11 +356,11 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
 
 	secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if ((!secs_to_sync && secs_to_flush)
 			|| (secs_to_sync < 0)
 			|| (secs_to_sync > secs_avail && !secs_to_flush)) {
-		pr_err("pblk: bad sector calculation (a:%d,s:%d,f:%d)\n",
+		pblk_err(pblk, "bad sector calculation (a:%d,s:%d,f:%d)\n",
 				secs_avail, secs_to_sync, secs_to_flush);
 	}
 #endif
@@ -397,7 +397,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 	bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
 					l_mg->emeta_alloc_type, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		pr_err("pblk: failed to map emeta io");
+		pblk_err(pblk, "failed to map emeta io");
 		ret = PTR_ERR(bio);
 		goto fail_free_rqd;
 	}
@@ -428,7 +428,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 
 	ret = pblk_submit_io(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
 		goto fail_rollback;
 	}
 
@@ -518,7 +518,7 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 	/* Assign lbas to ppas and populate request structure */
 	err = pblk_setup_w_rq(pblk, rqd, &erase_ppa);
 	if (err) {
-		pr_err("pblk: could not setup write request: %d\n", err);
+		pblk_err(pblk, "could not setup write request: %d\n", err);
 		return NVM_IO_ERR;
 	}
 
@@ -527,7 +527,7 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 	/* Submit data write for current data line */
 	err = pblk_submit_io(pblk, rqd);
 	if (err) {
-		pr_err("pblk: data I/O submission failed: %d\n", err);
+		pblk_err(pblk, "data I/O submission failed: %d\n", err);
 		return NVM_IO_ERR;
 	}
 
@@ -549,7 +549,8 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 		/* Submit metadata write for previous data line */
 		err = pblk_submit_meta_io(pblk, meta_line);
 		if (err) {
-			pr_err("pblk: metadata I/O submission failed: %d", err);
+			pblk_err(pblk, "metadata I/O submission failed: %d",
+					err);
 			return NVM_IO_ERR;
 		}
 	}
@@ -614,7 +615,7 @@ static int pblk_submit_write(struct pblk *pblk)
 		secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
 					secs_to_flush);
 		if (secs_to_sync > pblk->max_write_pgs) {
-			pr_err("pblk: bad buffer sync calculation\n");
+			pblk_err(pblk, "bad buffer sync calculation\n");
 			return 1;
 		}
 
@@ -633,14 +634,14 @@ static int pblk_submit_write(struct pblk *pblk)
 
 	if (pblk_rb_read_to_bio(&pblk->rwb, rqd, pos, secs_to_sync,
 								secs_avail)) {
-		pr_err("pblk: corrupted write bio\n");
+		pblk_err(pblk, "corrupted write bio\n");
 		goto fail_put_bio;
 	}
 
 	if (pblk_submit_io_set(pblk, rqd))
 		goto fail_free_bio;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(secs_to_sync, &pblk->sub_writes);
 #endif
 
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 34cc1d64a9d4..4760af7b6499 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -119,6 +119,16 @@ struct pblk_g_ctx {
 	u64 lba;
 };
 
+/* partial read context */
+struct pblk_pr_ctx {
+	struct bio *orig_bio;
+	DECLARE_BITMAP(bitmap, NVM_MAX_VLBA);
+	unsigned int orig_nr_secs;
+	unsigned int bio_init_idx;
+	void *ppa_ptr;
+	dma_addr_t dma_ppa_list;
+};
+
 /* Pad context */
 struct pblk_pad_rq {
 	struct pblk *pblk;
@@ -193,7 +203,7 @@ struct pblk_rb {
 	spinlock_t w_lock;		/* Write lock */
 	spinlock_t s_lock;		/* Sync lock */
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_t inflight_flush_point;	/* Not served REQ_FLUSH | REQ_FUA */
 #endif
 };
@@ -608,9 +618,6 @@ struct pblk {
 
 	int min_write_pgs; /* Minimum amount of pages required by controller */
 	int max_write_pgs; /* Maximum amount of pages supported by controller */
-	int pgs_in_buffer; /* Number of pages that need to be held in buffer to
-			    * guarantee successful reads.
-			    */
 
 	sector_t capacity; /* Device capacity when bad blocks are subtracted */
 
@@ -639,7 +646,7 @@ struct pblk {
 	u64 nr_flush_rst;		/* Flushes reset value for pad dist.*/
 	atomic64_t nr_flush;		/* Number of flush/fua I/O */
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Non-persistent debug counters, 4kb sector I/Os */
 	atomic_long_t inflight_writes;	/* Inflight writes (user and gc) */
 	atomic_long_t padded_writes;	/* Sectors padded due to flush/fua */
@@ -706,6 +713,15 @@ struct pblk_line_ws {
 #define pblk_g_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_g_ctx))
 #define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx))
 
+#define pblk_err(pblk, fmt, ...)			\
+	pr_err("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_info(pblk, fmt, ...)			\
+	pr_info("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_warn(pblk, fmt, ...)			\
+	pr_warn("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_debug(pblk, fmt, ...)			\
+	pr_debug("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+
 /*
  * pblk ring buffer operations
  */
@@ -1282,20 +1298,22 @@ static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs)
 	return !(nr_secs % pblk->min_write_pgs);
 }
 
-#ifdef CONFIG_NVM_DEBUG
-static inline void print_ppa(struct nvm_geo *geo, struct ppa_addr *p,
+#ifdef CONFIG_NVM_PBLK_DEBUG
+static inline void print_ppa(struct pblk *pblk, struct ppa_addr *p,
 			     char *msg, int error)
 {
+	struct nvm_geo *geo = &pblk->dev->geo;
+
 	if (p->c.is_cached) {
-		pr_err("ppa: (%s: %x) cache line: %llu\n",
+		pblk_err(pblk, "ppa: (%s: %x) cache line: %llu\n",
 				msg, error, (u64)p->c.line);
 	} else if (geo->version == NVM_OCSSD_SPEC_12) {
-		pr_err("ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
+		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
 			msg, error,
 			p->g.ch, p->g.lun, p->g.blk,
 			p->g.pg, p->g.pl, p->g.sec);
 	} else {
-		pr_err("ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n",
+		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n",
 			msg, error,
 			p->m.grp, p->m.pu, p->m.chk, p->m.sec);
 	}
@@ -1307,16 +1325,16 @@ static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd,
 	int bit = -1;
 
 	if (rqd->nr_ppas ==  1) {
-		print_ppa(&pblk->dev->geo, &rqd->ppa_addr, "rqd", error);
+		print_ppa(pblk, &rqd->ppa_addr, "rqd", error);
 		return;
 	}
 
 	while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas,
 						bit + 1)) < rqd->nr_ppas) {
-		print_ppa(&pblk->dev->geo, &rqd->ppa_list[bit], "rqd", error);
+		print_ppa(pblk, &rqd->ppa_list[bit], "rqd", error);
 	}
 
-	pr_err("error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
+	pblk_err(pblk, "error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
 }
 
 static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
@@ -1347,7 +1365,7 @@ static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
 				continue;
 		}
 
-		print_ppa(geo, ppa, "boundary", i);
+		print_ppa(tgt_dev->q->queuedata, ppa, "boundary", i);
 
 		return 1;
 	}
@@ -1377,7 +1395,7 @@ static inline int pblk_check_io(struct pblk *pblk, struct nvm_rq *rqd)
 
 			spin_lock(&line->lock);
 			if (line->state != PBLK_LINESTATE_OPEN) {
-				pr_err("pblk: bad ppa: line:%d,state:%d\n",
+				pblk_err(pblk, "bad ppa: line:%d,state:%d\n",
 							line->id, line->state);
 				WARN_ON(1);
 				spin_unlock(&line->lock);
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index d6bf294f3907..05f82ff6f016 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -328,13 +328,6 @@ struct cached_dev {
 	 */
 	atomic_t		has_dirty;
 
-	/*
-	 * Set to zero by things that touch the backing volume-- except
-	 * writeback.  Incremented by writeback.  Used to determine when to
-	 * accelerate idle writeback.
-	 */
-	atomic_t		backing_idle;
-
 	struct bch_ratelimit	writeback_rate;
 	struct delayed_work	writeback_rate_update;
 
@@ -423,9 +416,9 @@ struct cache {
 	/*
 	 * When allocating new buckets, prio_write() gets first dibs - since we
 	 * may not be allocate at all without writing priorities and gens.
-	 * prio_buckets[] contains the last buckets we wrote priorities to (so
-	 * gc can mark them as metadata), prio_next[] contains the buckets
-	 * allocated for the next prio write.
+	 * prio_last_buckets[] contains the last buckets we wrote priorities to
+	 * (so gc can mark them as metadata), prio_buckets[] contains the
+	 * buckets allocated for the next prio write.
 	 */
 	uint64_t		*prio_buckets;
 	uint64_t		*prio_last_buckets;
@@ -474,6 +467,7 @@ struct cache {
 
 struct gc_stat {
 	size_t			nodes;
+	size_t			nodes_pre;
 	size_t			key_bytes;
 
 	size_t			nkeys;
@@ -514,6 +508,8 @@ struct cache_set {
 	struct cache_accounting accounting;
 
 	unsigned long		flags;
+	atomic_t		idle_counter;
+	atomic_t		at_max_writeback_rate;
 
 	struct cache_sb		sb;
 
@@ -523,8 +519,10 @@ struct cache_set {
 
 	struct bcache_device	**devices;
 	unsigned		devices_max_used;
+	atomic_t		attached_dev_nr;
 	struct list_head	cached_devs;
 	uint64_t		cached_dev_sectors;
+	atomic_long_t		flash_dev_dirty_sectors;
 	struct closure		caching;
 
 	struct closure		sb_write;
@@ -603,6 +601,10 @@ struct cache_set {
 	 */
 	atomic_t		rescale;
 	/*
+	 * used for GC, identify if any front side I/Os is inflight
+	 */
+	atomic_t		search_inflight;
+	/*
 	 * When we invalidate buckets, we use both the priority and the amount
 	 * of good data to determine which buckets to reuse first - to weight
 	 * those together consistently we keep track of the smallest nonzero
@@ -995,7 +997,7 @@ void bch_open_buckets_free(struct cache_set *);
 int bch_cache_allocator_start(struct cache *ca);
 
 void bch_debug_exit(void);
-int bch_debug_init(struct kobject *);
+void bch_debug_init(struct kobject *kobj);
 void bch_request_exit(void);
 int bch_request_init(void);
 
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index f3403b45bc28..596c93b44e9b 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -366,6 +366,10 @@ EXPORT_SYMBOL(bch_btree_keys_init);
 
 /* Binary tree stuff for auxiliary search trees */
 
+/*
+ * return array index next to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
 static unsigned inorder_next(unsigned j, unsigned size)
 {
 	if (j * 2 + 1 < size) {
@@ -379,6 +383,10 @@ static unsigned inorder_next(unsigned j, unsigned size)
 	return j;
 }
 
+/*
+ * return array index previous to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
 static unsigned inorder_prev(unsigned j, unsigned size)
 {
 	if (j * 2 < size) {
@@ -421,6 +429,10 @@ static unsigned __to_inorder(unsigned j, unsigned size, unsigned extra)
 	return j;
 }
 
+/*
+ * Return the cacheline index in bset_tree->data, where j is index
+ * from a linear array which stores the auxiliar binary tree
+ */
 static unsigned to_inorder(unsigned j, struct bset_tree *t)
 {
 	return __to_inorder(j, t->size, t->extra);
@@ -441,6 +453,10 @@ static unsigned __inorder_to_tree(unsigned j, unsigned size, unsigned extra)
 	return j;
 }
 
+/*
+ * Return an index from a linear array which stores the auxiliar binary
+ * tree, j is the cacheline index of t->data.
+ */
 static unsigned inorder_to_tree(unsigned j, struct bset_tree *t)
 {
 	return __inorder_to_tree(j, t->size, t->extra);
@@ -546,6 +562,20 @@ static inline uint64_t shrd128(uint64_t high, uint64_t low, uint8_t shift)
 	return low;
 }
 
+/*
+ * Calculate mantissa value for struct bkey_float.
+ * If most significant bit of f->exponent is not set, then
+ *  - f->exponent >> 6 is 0
+ *  - p[0] points to bkey->low
+ *  - p[-1] borrows bits from KEY_INODE() of bkey->high
+ * if most isgnificant bits of f->exponent is set, then
+ *  - f->exponent >> 6 is 1
+ *  - p[0] points to bits from KEY_INODE() of bkey->high
+ *  - p[-1] points to other bits from KEY_INODE() of
+ *    bkey->high too.
+ * See make_bfloat() to check when most significant bit of f->exponent
+ * is set or not.
+ */
 static inline unsigned bfloat_mantissa(const struct bkey *k,
 				       struct bkey_float *f)
 {
@@ -570,6 +600,16 @@ static void make_bfloat(struct bset_tree *t, unsigned j)
 	BUG_ON(m < l || m > r);
 	BUG_ON(bkey_next(p) != m);
 
+	/*
+	 * If l and r have different KEY_INODE values (different backing
+	 * device), f->exponent records how many least significant bits
+	 * are different in KEY_INODE values and sets most significant
+	 * bits to 1 (by +64).
+	 * If l and r have same KEY_INODE value, f->exponent records
+	 * how many different bits in least significant bits of bkey->low.
+	 * See bfloat_mantiss() how the most significant bit of
+	 * f->exponent is used to calculate bfloat mantissa value.
+	 */
 	if (KEY_INODE(l) != KEY_INODE(r))
 		f->exponent = fls64(KEY_INODE(r) ^ KEY_INODE(l)) + 64;
 	else
@@ -633,6 +673,15 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic)
 }
 EXPORT_SYMBOL(bch_bset_init_next);
 
+/*
+ * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to
+ * accelerate bkey search in a btree node (pointed by bset_tree->data in
+ * memory). After search in the auxiliar tree by calling bset_search_tree(),
+ * a struct bset_search_iter is returned which indicates range [l, r] from
+ * bset_tree->data where the searching bkey might be inside. Then a followed
+ * linear comparison does the exact search, see __bch_bset_search() for how
+ * the auxiliary tree is used.
+ */
 void bch_bset_build_written_tree(struct btree_keys *b)
 {
 	struct bset_tree *t = bset_tree_last(b);
@@ -898,6 +947,17 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
 	unsigned inorder, j, n = 1;
 
 	do {
+		/*
+		 * A bit trick here.
+		 * If p < t->size, (int)(p - t->size) is a minus value and
+		 * the most significant bit is set, right shifting 31 bits
+		 * gets 1. If p >= t->size, the most significant bit is
+		 * not set, right shifting 31 bits gets 0.
+		 * So the following 2 lines equals to
+		 *	if (p >= t->size)
+		 *		p = 0;
+		 * but a branch instruction is avoided.
+		 */
 		unsigned p = n << 4;
 		p &= ((int) (p - t->size)) >> 31;
 
@@ -907,6 +967,9 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
 		f = &t->tree[j];
 
 		/*
+		 * Similar bit trick, use subtract operation to avoid a branch
+		 * instruction.
+		 *
 		 * n = (f->mantissa > bfloat_mantissa())
 		 *	? j * 2
 		 *	: j * 2 + 1;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 547c9eedc2f4..c19f7716df88 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -90,6 +90,9 @@
 
 #define MAX_NEED_GC		64
 #define MAX_SAVE_PRIO		72
+#define MAX_GC_TIMES		100
+#define MIN_GC_NODES		100
+#define GC_SLEEP_MS		100
 
 #define PTR_DIRTY_BIT		(((uint64_t) 1 << 36))
 
@@ -1008,6 +1011,13 @@ retry:
 		BUG_ON(b->level != level);
 	}
 
+	if (btree_node_io_error(b)) {
+		rw_unlock(write, b);
+		return ERR_PTR(-EIO);
+	}
+
+	BUG_ON(!b->written);
+
 	b->parent = parent;
 	b->accessed = 1;
 
@@ -1019,13 +1029,6 @@ retry:
 	for (; i <= b->keys.nsets; i++)
 		prefetch(b->keys.set[i].data);
 
-	if (btree_node_io_error(b)) {
-		rw_unlock(write, b);
-		return ERR_PTR(-EIO);
-	}
-
-	BUG_ON(!b->written);
-
 	return b;
 }
 
@@ -1520,6 +1523,32 @@ static unsigned btree_gc_count_keys(struct btree *b)
 	return ret;
 }
 
+static size_t btree_gc_min_nodes(struct cache_set *c)
+{
+	size_t min_nodes;
+
+	/*
+	 * Since incremental GC would stop 100ms when front
+	 * side I/O comes, so when there are many btree nodes,
+	 * if GC only processes constant (100) nodes each time,
+	 * GC would last a long time, and the front side I/Os
+	 * would run out of the buckets (since no new bucket
+	 * can be allocated during GC), and be blocked again.
+	 * So GC should not process constant nodes, but varied
+	 * nodes according to the number of btree nodes, which
+	 * realized by dividing GC into constant(100) times,
+	 * so when there are many btree nodes, GC can process
+	 * more nodes each time, otherwise, GC will process less
+	 * nodes each time (but no less than MIN_GC_NODES)
+	 */
+	min_nodes = c->gc_stats.nodes / MAX_GC_TIMES;
+	if (min_nodes < MIN_GC_NODES)
+		min_nodes = MIN_GC_NODES;
+
+	return min_nodes;
+}
+
+
 static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 			    struct closure *writes, struct gc_stat *gc)
 {
@@ -1585,6 +1614,13 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 		memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1));
 		r->b = NULL;
 
+		if (atomic_read(&b->c->search_inflight) &&
+		    gc->nodes >= gc->nodes_pre + btree_gc_min_nodes(b->c)) {
+			gc->nodes_pre =  gc->nodes;
+			ret = -EAGAIN;
+			break;
+		}
+
 		if (need_resched()) {
 			ret = -EAGAIN;
 			break;
@@ -1753,7 +1789,10 @@ static void bch_btree_gc(struct cache_set *c)
 		closure_sync(&writes);
 		cond_resched();
 
-		if (ret && ret != -EAGAIN)
+		if (ret == -EAGAIN)
+			schedule_timeout_interruptible(msecs_to_jiffies
+						       (GC_SLEEP_MS));
+		else if (ret)
 			pr_warn("gc failed!");
 	} while (ret && !test_bit(CACHE_SET_IO_DISABLE, &c->flags));
 
@@ -1834,8 +1873,14 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 		do {
 			k = bch_btree_iter_next_filter(&iter, &b->keys,
 						       bch_ptr_bad);
-			if (k)
+			if (k) {
 				btree_node_prefetch(b, k);
+				/*
+				 * initiallize c->gc_stats.nodes
+				 * for incremental GC
+				 */
+				b->c->gc_stats.nodes++;
+			}
 
 			if (p)
 				ret = btree(check_recurse, p, b, op);
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index d211e2c25b6b..68e9d926134d 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -152,7 +152,7 @@ static inline bool btree_node_ ## flag(struct btree *b)			\
 {	return test_bit(BTREE_NODE_ ## flag, &b->flags); }		\
 									\
 static inline void set_btree_node_ ## flag(struct btree *b)		\
-{	set_bit(BTREE_NODE_ ## flag, &b->flags); }			\
+{	set_bit(BTREE_NODE_ ## flag, &b->flags); }
 
 enum btree_flags {
 	BTREE_NODE_io_error,
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 0e14969182c6..618253683d40 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -199,11 +199,16 @@ static const struct file_operations debug_ops = {
 	.release	= single_release
 };
 
-int __init closure_debug_init(void)
+void  __init closure_debug_init(void)
 {
-	closure_debug = debugfs_create_file("closures",
-				0400, bcache_debug, NULL, &debug_ops);
-	return IS_ERR_OR_NULL(closure_debug);
+	if (!IS_ERR_OR_NULL(bcache_debug))
+		/*
+		 * it is unnecessary to check return value of
+		 * debugfs_create_file(), we should not care
+		 * about this.
+		 */
+		closure_debug = debugfs_create_file(
+			"closures", 0400, bcache_debug, NULL, &debug_ops);
 }
 #endif
 
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 71427eb5fdae..7c2c5bc7c88b 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -186,13 +186,13 @@ static inline void closure_sync(struct closure *cl)
 
 #ifdef CONFIG_BCACHE_CLOSURES_DEBUG
 
-int closure_debug_init(void);
+void closure_debug_init(void);
 void closure_debug_create(struct closure *cl);
 void closure_debug_destroy(struct closure *cl);
 
 #else
 
-static inline int closure_debug_init(void) { return 0; }
+static inline void closure_debug_init(void) {}
 static inline void closure_debug_create(struct closure *cl) {}
 static inline void closure_debug_destroy(struct closure *cl) {}
 
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index d030ce3025a6..12034c07257b 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -110,11 +110,15 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 	struct bio_vec bv, cbv;
 	struct bvec_iter iter, citer = { 0 };
 
-	check = bio_clone_kmalloc(bio, GFP_NOIO);
+	check = bio_kmalloc(GFP_NOIO, bio_segments(bio));
 	if (!check)
 		return;
+	check->bi_disk = bio->bi_disk;
 	check->bi_opf = REQ_OP_READ;
+	check->bi_iter.bi_sector = bio->bi_iter.bi_sector;
+	check->bi_iter.bi_size = bio->bi_iter.bi_size;
 
+	bch_bio_map(check, NULL);
 	if (bch_bio_alloc_pages(check, GFP_NOIO))
 		goto out_put;
 
@@ -248,11 +252,12 @@ void bch_debug_exit(void)
 		debugfs_remove_recursive(bcache_debug);
 }
 
-int __init bch_debug_init(struct kobject *kobj)
+void __init bch_debug_init(struct kobject *kobj)
 {
-	if (!IS_ENABLED(CONFIG_DEBUG_FS))
-		return 0;
-
+	/*
+	 * it is unnecessary to check return value of
+	 * debugfs_create_file(), we should not care
+	 * about this.
+	 */
 	bcache_debug = debugfs_create_dir("bcache", NULL);
-	return IS_ERR_OR_NULL(bcache_debug);
 }
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 18f1b5239620..10748c626a1d 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -828,6 +828,7 @@ void bch_journal_free(struct cache_set *c)
 	free_pages((unsigned long) c->journal.w[1].data, JSET_BITS);
 	free_pages((unsigned long) c->journal.w[0].data, JSET_BITS);
 	free_fifo(&c->journal.pin);
+	free_heap(&c->flush_btree);
 }
 
 int bch_journal_alloc(struct cache_set *c)
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index ae67f5fa8047..7dbe8b6316a0 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -107,7 +107,7 @@ static int bch_keylist_realloc(struct keylist *l, unsigned u64s,
 	/*
 	 * The journalling code doesn't handle the case where the keys to insert
 	 * is bigger than an empty write: If we just return -ENOMEM here,
-	 * bio_insert() and bio_invalidate() will insert the keys created so far
+	 * bch_data_insert_keys() will insert the keys created so far
 	 * and finish the rest when the keylist is empty.
 	 */
 	if (newsize * sizeof(uint64_t) > block_bytes(c) - sizeof(struct jset))
@@ -667,8 +667,7 @@ static void backing_request_endio(struct bio *bio)
 static void bio_complete(struct search *s)
 {
 	if (s->orig_bio) {
-		generic_end_io_acct(s->d->disk->queue,
-				    bio_data_dir(s->orig_bio),
+		generic_end_io_acct(s->d->disk->queue, bio_op(s->orig_bio),
 				    &s->d->disk->part0, s->start_time);
 
 		trace_bcache_request_end(s->d, s->orig_bio);
@@ -702,6 +701,8 @@ static void search_free(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 
+	atomic_dec(&s->d->c->search_inflight);
+
 	if (s->iop.bio)
 		bio_put(s->iop.bio);
 
@@ -719,6 +720,7 @@ static inline struct search *search_alloc(struct bio *bio,
 
 	closure_init(&s->cl, NULL);
 	do_bio_hook(s, bio, request_endio);
+	atomic_inc(&d->c->search_inflight);
 
 	s->orig_bio		= bio;
 	s->cache_miss		= NULL;
@@ -1062,8 +1064,7 @@ static void detached_dev_end_io(struct bio *bio)
 	bio->bi_end_io = ddip->bi_end_io;
 	bio->bi_private = ddip->bi_private;
 
-	generic_end_io_acct(ddip->d->disk->queue,
-			    bio_data_dir(bio),
+	generic_end_io_acct(ddip->d->disk->queue, bio_op(bio),
 			    &ddip->d->disk->part0, ddip->start_time);
 
 	if (bio->bi_status) {
@@ -1102,6 +1103,44 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
 		generic_make_request(bio);
 }
 
+static void quit_max_writeback_rate(struct cache_set *c,
+				    struct cached_dev *this_dc)
+{
+	int i;
+	struct bcache_device *d;
+	struct cached_dev *dc;
+
+	/*
+	 * mutex bch_register_lock may compete with other parallel requesters,
+	 * or attach/detach operations on other backing device. Waiting to
+	 * the mutex lock may increase I/O request latency for seconds or more.
+	 * To avoid such situation, if mutext_trylock() failed, only writeback
+	 * rate of current cached device is set to 1, and __update_write_back()
+	 * will decide writeback rate of other cached devices (remember now
+	 * c->idle_counter is 0 already).
+	 */
+	if (mutex_trylock(&bch_register_lock)) {
+		for (i = 0; i < c->devices_max_used; i++) {
+			if (!c->devices[i])
+				continue;
+
+			if (UUID_FLASH_ONLY(&c->uuids[i]))
+				continue;
+
+			d = c->devices[i];
+			dc = container_of(d, struct cached_dev, disk);
+			/*
+			 * set writeback rate to default minimum value,
+			 * then let update_writeback_rate() to decide the
+			 * upcoming rate.
+			 */
+			atomic_long_set(&dc->writeback_rate.rate, 1);
+		}
+		mutex_unlock(&bch_register_lock);
+	} else
+		atomic_long_set(&this_dc->writeback_rate.rate, 1);
+}
+
 /* Cached devices - read & write stuff */
 
 static blk_qc_t cached_dev_make_request(struct request_queue *q,
@@ -1119,8 +1158,25 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
 		return BLK_QC_T_NONE;
 	}
 
-	atomic_set(&dc->backing_idle, 0);
-	generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0);
+	if (likely(d->c)) {
+		if (atomic_read(&d->c->idle_counter))
+			atomic_set(&d->c->idle_counter, 0);
+		/*
+		 * If at_max_writeback_rate of cache set is true and new I/O
+		 * comes, quit max writeback rate of all cached devices
+		 * attached to this cache set, and set at_max_writeback_rate
+		 * to false.
+		 */
+		if (unlikely(atomic_read(&d->c->at_max_writeback_rate) == 1)) {
+			atomic_set(&d->c->at_max_writeback_rate, 0);
+			quit_max_writeback_rate(d->c, dc);
+		}
+	}
+
+	generic_start_io_acct(q,
+			      bio_op(bio),
+			      bio_sectors(bio),
+			      &d->disk->part0);
 
 	bio_set_dev(bio, dc->bdev);
 	bio->bi_iter.bi_sector += dc->sb.data_offset;
@@ -1229,7 +1285,6 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 	struct search *s;
 	struct closure *cl;
 	struct bcache_device *d = bio->bi_disk->private_data;
-	int rw = bio_data_dir(bio);
 
 	if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) {
 		bio->bi_status = BLK_STS_IOERR;
@@ -1237,7 +1292,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 		return BLK_QC_T_NONE;
 	}
 
-	generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0);
+	generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0);
 
 	s = search_alloc(bio, d);
 	cl = &s->cl;
@@ -1254,7 +1309,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 				      flash_dev_nodata,
 				      bcache_wq);
 		return BLK_QC_T_NONE;
-	} else if (rw) {
+	} else if (bio_data_dir(bio)) {
 		bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
 					&KEY(d->id, bio->bi_iter.bi_sector, 0),
 					&KEY(d->id, bio_end_sector(bio), 0));
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index fa4058e43202..55a37641aa95 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -181,7 +181,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 		goto err;
 	}
 
-	sb->last_mount = get_seconds();
+	sb->last_mount = (u32)ktime_get_real_seconds();
 	err = NULL;
 
 	get_page(bh->b_page);
@@ -696,12 +696,14 @@ static void bcache_device_detach(struct bcache_device *d)
 {
 	lockdep_assert_held(&bch_register_lock);
 
+	atomic_dec(&d->c->attached_dev_nr);
+
 	if (test_bit(BCACHE_DEV_DETACHING, &d->flags)) {
 		struct uuid_entry *u = d->c->uuids + d->id;
 
 		SET_UUID_FLASH_ONLY(u, 0);
 		memcpy(u->uuid, invalid_uuid, 16);
-		u->invalidated = cpu_to_le32(get_seconds());
+		u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
 		bch_uuid_write(d->c);
 	}
 
@@ -796,11 +798,12 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 		return idx;
 
 	if (bioset_init(&d->bio_split, 4, offsetof(struct bbio, bio),
-			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
-	    !(d->disk = alloc_disk(BCACHE_MINORS))) {
-		ida_simple_remove(&bcache_device_idx, idx);
-		return -ENOMEM;
-	}
+			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
+		goto err;
+
+	d->disk = alloc_disk(BCACHE_MINORS);
+	if (!d->disk)
+		goto err;
 
 	set_capacity(d->disk, sectors);
 	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
@@ -834,6 +837,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	blk_queue_write_cache(q, true, true);
 
 	return 0;
+
+err:
+	ida_simple_remove(&bcache_device_idx, idx);
+	return -ENOMEM;
+
 }
 
 /* Cached device */
@@ -1027,7 +1035,7 @@ void bch_cached_dev_detach(struct cached_dev *dc)
 int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 			  uint8_t *set_uuid)
 {
-	uint32_t rtime = cpu_to_le32(get_seconds());
+	uint32_t rtime = cpu_to_le32((u32)ktime_get_real_seconds());
 	struct uuid_entry *u;
 	struct cached_dev *exist_dc, *t;
 
@@ -1070,7 +1078,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	    (BDEV_STATE(&dc->sb) == BDEV_STATE_STALE ||
 	     BDEV_STATE(&dc->sb) == BDEV_STATE_NONE)) {
 		memcpy(u->uuid, invalid_uuid, 16);
-		u->invalidated = cpu_to_le32(get_seconds());
+		u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
 		u = NULL;
 	}
 
@@ -1138,6 +1146,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 
 	bch_cached_dev_run(dc);
 	bcache_device_link(&dc->disk, c, "bdev");
+	atomic_inc(&c->attached_dev_nr);
 
 	/* Allow the writeback thread to proceed */
 	up_write(&dc->writeback_lock);
@@ -1285,6 +1294,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 	pr_info("registered backing device %s", dc->backing_dev_name);
 
 	list_add(&dc->list, &uncached_devices);
+	/* attach to a matched cache set if it exists */
 	list_for_each_entry(c, &bch_cache_sets, list)
 		bch_cached_dev_attach(dc, c, NULL);
 
@@ -1311,6 +1321,8 @@ static void flash_dev_free(struct closure *cl)
 {
 	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
 	mutex_lock(&bch_register_lock);
+	atomic_long_sub(bcache_dev_sectors_dirty(d),
+			&d->c->flash_dev_dirty_sectors);
 	bcache_device_free(d);
 	mutex_unlock(&bch_register_lock);
 	kobject_put(&d->kobj);
@@ -1390,7 +1402,7 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size)
 
 	get_random_bytes(u->uuid, 16);
 	memset(u->label, 0, 32);
-	u->first_reg = u->last_reg = cpu_to_le32(get_seconds());
+	u->first_reg = u->last_reg = cpu_to_le32((u32)ktime_get_real_seconds());
 
 	SET_UUID_FLASH_ONLY(u, 1);
 	u->sectors = size >> 9;
@@ -1687,6 +1699,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	c->block_bits		= ilog2(sb->block_size);
 	c->nr_uuids		= bucket_bytes(c) / sizeof(struct uuid_entry);
 	c->devices_max_used	= 0;
+	atomic_set(&c->attached_dev_nr, 0);
 	c->btree_pages		= bucket_pages(c);
 	if (c->btree_pages > BTREE_MAX_PAGES)
 		c->btree_pages = max_t(int, c->btree_pages / 4,
@@ -1894,7 +1907,7 @@ static void run_cache_set(struct cache_set *c)
 		goto err;
 
 	closure_sync(&cl);
-	c->sb.last_mount = get_seconds();
+	c->sb.last_mount = (u32)ktime_get_real_seconds();
 	bcache_write_super(c);
 
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
@@ -2163,8 +2176,12 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (!try_module_get(THIS_MODULE))
 		return -EBUSY;
 
-	if (!(path = kstrndup(buffer, size, GFP_KERNEL)) ||
-	    !(sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL)))
+	path = kstrndup(buffer, size, GFP_KERNEL);
+	if (!path)
+		goto err;
+
+	sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL);
+	if (!sb)
 		goto err;
 
 	err = "failed to open device";
@@ -2324,13 +2341,21 @@ static int __init bcache_init(void)
 		return bcache_major;
 	}
 
-	if (!(bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0)) ||
-	    !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
-	    bch_request_init() ||
-	    bch_debug_init(bcache_kobj) || closure_debug_init() ||
+	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
+	if (!bcache_wq)
+		goto err;
+
+	bcache_kobj = kobject_create_and_add("bcache", fs_kobj);
+	if (!bcache_kobj)
+		goto err;
+
+	if (bch_request_init() ||
 	    sysfs_create_files(bcache_kobj, files))
 		goto err;
 
+	bch_debug_init(bcache_kobj);
+	closure_debug_init();
+
 	return 0;
 err:
 	bcache_exit();
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 225b15aa0340..81d3520b0702 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -149,6 +149,7 @@ SHOW(__bch_cached_dev)
 	struct cached_dev *dc = container_of(kobj, struct cached_dev,
 					     disk.kobj);
 	const char *states[] = { "no cache", "clean", "dirty", "inconsistent" };
+	int wb = dc->writeback_running;
 
 #define var(stat)		(dc->stat)
 
@@ -170,7 +171,8 @@ SHOW(__bch_cached_dev)
 	var_printf(writeback_running,	"%i");
 	var_print(writeback_delay);
 	var_print(writeback_percent);
-	sysfs_hprint(writeback_rate,	dc->writeback_rate.rate << 9);
+	sysfs_hprint(writeback_rate,
+		     wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0);
 	sysfs_hprint(io_errors,		atomic_read(&dc->io_errors));
 	sysfs_printf(io_error_limit,	"%i", dc->error_limit);
 	sysfs_printf(io_disable,	"%i", dc->io_disable);
@@ -188,15 +190,22 @@ SHOW(__bch_cached_dev)
 		char change[20];
 		s64 next_io;
 
-		bch_hprint(rate,	dc->writeback_rate.rate << 9);
-		bch_hprint(dirty,	bcache_dev_sectors_dirty(&dc->disk) << 9);
-		bch_hprint(target,	dc->writeback_rate_target << 9);
-		bch_hprint(proportional,dc->writeback_rate_proportional << 9);
-		bch_hprint(integral,	dc->writeback_rate_integral_scaled << 9);
-		bch_hprint(change,	dc->writeback_rate_change << 9);
-
-		next_io = div64_s64(dc->writeback_rate.next - local_clock(),
-				    NSEC_PER_MSEC);
+		/*
+		 * Except for dirty and target, other values should
+		 * be 0 if writeback is not running.
+		 */
+		bch_hprint(rate,
+			   wb ? atomic_long_read(&dc->writeback_rate.rate) << 9
+			      : 0);
+		bch_hprint(dirty, bcache_dev_sectors_dirty(&dc->disk) << 9);
+		bch_hprint(target, dc->writeback_rate_target << 9);
+		bch_hprint(proportional,
+			   wb ? dc->writeback_rate_proportional << 9 : 0);
+		bch_hprint(integral,
+			   wb ? dc->writeback_rate_integral_scaled << 9 : 0);
+		bch_hprint(change, wb ? dc->writeback_rate_change << 9 : 0);
+		next_io = wb ? div64_s64(dc->writeback_rate.next-local_clock(),
+					 NSEC_PER_MSEC) : 0;
 
 		return sprintf(buf,
 			       "rate:\t\t%s/sec\n"
@@ -255,8 +264,19 @@ STORE(__cached_dev)
 
 	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40);
 
-	sysfs_strtoul_clamp(writeback_rate,
-			    dc->writeback_rate.rate, 1, INT_MAX);
+	if (attr == &sysfs_writeback_rate) {
+		ssize_t ret;
+		long int v = atomic_long_read(&dc->writeback_rate.rate);
+
+		ret = strtoul_safe_clamp(buf, v, 1, INT_MAX);
+
+		if (!ret) {
+			atomic_long_set(&dc->writeback_rate.rate, v);
+			ret = size;
+		}
+
+		return ret;
+	}
 
 	sysfs_strtoul_clamp(writeback_rate_update_seconds,
 			    dc->writeback_rate_update_seconds,
@@ -338,8 +358,8 @@ STORE(__cached_dev)
 			if (!v)
 				return size;
 		}
-
-		pr_err("Can't attach %s: cache set not found", buf);
+		if (v == -ENOENT)
+			pr_err("Can't attach %s: cache set not found", buf);
 		return v;
 	}
 
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index fc479b026d6d..b15256bcf0e7 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -200,7 +200,7 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
 {
 	uint64_t now = local_clock();
 
-	d->next += div_u64(done * NSEC_PER_SEC, d->rate);
+	d->next += div_u64(done * NSEC_PER_SEC, atomic_long_read(&d->rate));
 
 	/* Bound the time.  Don't let us fall further than 2 seconds behind
 	 * (this prevents unnecessary backlog that would make it impossible
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index cced87f8eb27..f7b0133c9d2f 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -442,7 +442,7 @@ struct bch_ratelimit {
 	 * Rate at which we want to do work, in units per second
 	 * The units here correspond to the units passed to bch_next_delay()
 	 */
-	uint32_t		rate;
+	atomic_long_t		rate;
 };
 
 static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index ad45ebe1a74b..481d4cf38ac0 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -27,7 +27,7 @@ static uint64_t __calc_target_rate(struct cached_dev *dc)
 	 * flash-only devices
 	 */
 	uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size -
-				bcache_flash_devs_sectors_dirty(c);
+				atomic_long_read(&c->flash_dev_dirty_sectors);
 
 	/*
 	 * Unfortunately there is no control of global dirty data.  If the
@@ -104,11 +104,56 @@ static void __update_writeback_rate(struct cached_dev *dc)
 
 	dc->writeback_rate_proportional = proportional_scaled;
 	dc->writeback_rate_integral_scaled = integral_scaled;
-	dc->writeback_rate_change = new_rate - dc->writeback_rate.rate;
-	dc->writeback_rate.rate = new_rate;
+	dc->writeback_rate_change = new_rate -
+			atomic_long_read(&dc->writeback_rate.rate);
+	atomic_long_set(&dc->writeback_rate.rate, new_rate);
 	dc->writeback_rate_target = target;
 }
 
+static bool set_at_max_writeback_rate(struct cache_set *c,
+				       struct cached_dev *dc)
+{
+	/*
+	 * Idle_counter is increased everytime when update_writeback_rate() is
+	 * called. If all backing devices attached to the same cache set have
+	 * identical dc->writeback_rate_update_seconds values, it is about 6
+	 * rounds of update_writeback_rate() on each backing device before
+	 * c->at_max_writeback_rate is set to 1, and then max wrteback rate set
+	 * to each dc->writeback_rate.rate.
+	 * In order to avoid extra locking cost for counting exact dirty cached
+	 * devices number, c->attached_dev_nr is used to calculate the idle
+	 * throushold. It might be bigger if not all cached device are in write-
+	 * back mode, but it still works well with limited extra rounds of
+	 * update_writeback_rate().
+	 */
+	if (atomic_inc_return(&c->idle_counter) <
+	    atomic_read(&c->attached_dev_nr) * 6)
+		return false;
+
+	if (atomic_read(&c->at_max_writeback_rate) != 1)
+		atomic_set(&c->at_max_writeback_rate, 1);
+
+	atomic_long_set(&dc->writeback_rate.rate, INT_MAX);
+
+	/* keep writeback_rate_target as existing value */
+	dc->writeback_rate_proportional = 0;
+	dc->writeback_rate_integral_scaled = 0;
+	dc->writeback_rate_change = 0;
+
+	/*
+	 * Check c->idle_counter and c->at_max_writeback_rate agagain in case
+	 * new I/O arrives during before set_at_max_writeback_rate() returns.
+	 * Then the writeback rate is set to 1, and its new value should be
+	 * decided via __update_writeback_rate().
+	 */
+	if ((atomic_read(&c->idle_counter) <
+	     atomic_read(&c->attached_dev_nr) * 6) ||
+	    !atomic_read(&c->at_max_writeback_rate))
+		return false;
+
+	return true;
+}
+
 static void update_writeback_rate(struct work_struct *work)
 {
 	struct cached_dev *dc = container_of(to_delayed_work(work),
@@ -136,13 +181,20 @@ static void update_writeback_rate(struct work_struct *work)
 		return;
 	}
 
-	down_read(&dc->writeback_lock);
-
-	if (atomic_read(&dc->has_dirty) &&
-	    dc->writeback_percent)
-		__update_writeback_rate(dc);
+	if (atomic_read(&dc->has_dirty) && dc->writeback_percent) {
+		/*
+		 * If the whole cache set is idle, set_at_max_writeback_rate()
+		 * will set writeback rate to a max number. Then it is
+		 * unncessary to update writeback rate for an idle cache set
+		 * in maximum writeback rate number(s).
+		 */
+		if (!set_at_max_writeback_rate(c, dc)) {
+			down_read(&dc->writeback_lock);
+			__update_writeback_rate(dc);
+			up_read(&dc->writeback_lock);
+		}
+	}
 
-	up_read(&dc->writeback_lock);
 
 	/*
 	 * CACHE_SET_IO_DISABLE might be set via sysfs interface,
@@ -422,27 +474,6 @@ static void read_dirty(struct cached_dev *dc)
 
 		delay = writeback_delay(dc, size);
 
-		/* If the control system would wait for at least half a
-		 * second, and there's been no reqs hitting the backing disk
-		 * for awhile: use an alternate mode where we have at most
-		 * one contiguous set of writebacks in flight at a time.  If
-		 * someone wants to do IO it will be quick, as it will only
-		 * have to contend with one operation in flight, and we'll
-		 * be round-tripping data to the backing disk as quickly as
-		 * it can accept it.
-		 */
-		if (delay >= HZ / 2) {
-			/* 3 means at least 1.5 seconds, up to 7.5 if we
-			 * have slowed way down.
-			 */
-			if (atomic_inc_return(&dc->backing_idle) >= 3) {
-				/* Wait for current I/Os to finish */
-				closure_sync(&cl);
-				/* And immediately launch a new set. */
-				delay = 0;
-			}
-		}
-
 		while (!kthread_should_stop() &&
 		       !test_bit(CACHE_SET_IO_DISABLE, &dc->disk.c->flags) &&
 		       delay) {
@@ -476,6 +507,9 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
 	if (!d)
 		return;
 
+	if (UUID_FLASH_ONLY(&c->uuids[inode]))
+		atomic_long_add(nr_sectors, &c->flash_dev_dirty_sectors);
+
 	stripe = offset_to_stripe(d, offset);
 	stripe_offset = offset & (d->stripe_size - 1);
 
@@ -673,10 +707,14 @@ static int bch_writeback_thread(void *arg)
 }
 
 /* Init */
+#define INIT_KEYS_EACH_TIME	500000
+#define INIT_KEYS_SLEEP_MS	100
 
 struct sectors_dirty_init {
 	struct btree_op	op;
 	unsigned	inode;
+	size_t		count;
+	struct bkey	start;
 };
 
 static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
@@ -691,18 +729,37 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
 		bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k),
 					     KEY_START(k), KEY_SIZE(k));
 
+	op->count++;
+	if (atomic_read(&b->c->search_inflight) &&
+	    !(op->count % INIT_KEYS_EACH_TIME)) {
+		bkey_copy_key(&op->start, k);
+		return -EAGAIN;
+	}
+
 	return MAP_CONTINUE;
 }
 
 void bch_sectors_dirty_init(struct bcache_device *d)
 {
 	struct sectors_dirty_init op;
+	int ret;
 
 	bch_btree_op_init(&op.op, -1);
 	op.inode = d->id;
-
-	bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0),
-			   sectors_dirty_init_fn, 0);
+	op.count = 0;
+	op.start = KEY(op.inode, 0, 0);
+
+	do {
+		ret = bch_btree_map_keys(&op.op, d->c, &op.start,
+					 sectors_dirty_init_fn, 0);
+		if (ret == -EAGAIN)
+			schedule_timeout_interruptible(
+				msecs_to_jiffies(INIT_KEYS_SLEEP_MS));
+		else if (ret < 0) {
+			pr_warn("sectors dirty init failed, ret=%d!", ret);
+			break;
+		}
+	} while (ret == -EAGAIN);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
@@ -715,7 +772,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 	dc->writeback_running		= true;
 	dc->writeback_percent		= 10;
 	dc->writeback_delay		= 30;
-	dc->writeback_rate.rate		= 1024;
+	atomic_long_set(&dc->writeback_rate.rate, 1024);
 	dc->writeback_rate_minimum	= 8;
 
 	dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 610fb01de629..3745d7004c47 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -28,25 +28,6 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
 	return ret;
 }
 
-static inline uint64_t  bcache_flash_devs_sectors_dirty(struct cache_set *c)
-{
-	uint64_t i, ret = 0;
-
-	mutex_lock(&bch_register_lock);
-
-	for (i = 0; i < c->devices_max_used; i++) {
-		struct bcache_device *d = c->devices[i];
-
-		if (!d || !UUID_FLASH_ONLY(&c->uuids[i]))
-			continue;
-		ret += bcache_dev_sectors_dirty(d);
-	}
-
-	mutex_unlock(&bch_register_lock);
-
-	return ret;
-}
-
 static inline unsigned offset_to_stripe(struct bcache_device *d,
 					uint64_t offset)
 {
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index ab13fcec3fca..75df4c9d8b54 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -588,7 +588,7 @@ static const char *raid10_md_layout_to_format(int layout)
 }
 
 /* Return md raid10 algorithm for @name */
-static const int raid10_name_to_format(const char *name)
+static int raid10_name_to_format(const char *name)
 {
 	if (!strcasecmp(name, "near"))
 		return ALGORITHM_RAID10_NEAR;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 938766794c2e..3d0e2c198f06 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -885,9 +885,7 @@ EXPORT_SYMBOL_GPL(dm_table_set_type);
 static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
 			       sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return q && blk_queue_dax(q);
+	return bdev_dax_supported(dev->bdev, PAGE_SIZE);
 }
 
 static bool dm_table_supports_dax(struct dm_table *t)
@@ -1907,6 +1905,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 
 	if (dm_table_supports_dax(t))
 		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
+
 	if (dm_table_supports_dax_write_cache(t))
 		dax_write_cache(t->md->dax_dev, true);
 
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 36ef284ad086..72142021b5c9 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -776,7 +776,6 @@ static int __write_changed_details(struct dm_pool_metadata *pmd)
 static int __commit_transaction(struct dm_pool_metadata *pmd)
 {
 	int r;
-	size_t metadata_len, data_len;
 	struct thin_disk_superblock *disk_super;
 	struct dm_block *sblock;
 
@@ -797,14 +796,6 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	if (r < 0)
 		return r;
 
-	r = dm_sm_root_size(pmd->metadata_sm, &metadata_len);
-	if (r < 0)
-		return r;
-
-	r = dm_sm_root_size(pmd->data_sm, &data_len);
-	if (r < 0)
-		return r;
-
 	r = save_sm_roots(pmd);
 	if (r < 0)
 		return r;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 7945238df1c0..b900723bbd0f 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -1386,6 +1386,8 @@ static void schedule_external_copy(struct thin_c *tc, dm_block_t virt_block,
 
 static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
 
+static void requeue_bios(struct pool *pool);
+
 static void check_for_space(struct pool *pool)
 {
 	int r;
@@ -1398,8 +1400,10 @@ static void check_for_space(struct pool *pool)
 	if (r)
 		return;
 
-	if (nr_free)
+	if (nr_free) {
 		set_pool_mode(pool, PM_WRITE);
+		requeue_bios(pool);
+	}
 }
 
 /*
@@ -1476,7 +1480,10 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
 
 	r = dm_pool_alloc_data_block(pool->pmd, result);
 	if (r) {
-		metadata_operation_failed(pool, "dm_pool_alloc_data_block", r);
+		if (r == -ENOSPC)
+			set_pool_mode(pool, PM_OUT_OF_DATA_SPACE);
+		else
+			metadata_operation_failed(pool, "dm_pool_alloc_data_block", r);
 		return r;
 	}
 
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 5961c7794ef3..87107c995cb5 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -136,6 +136,7 @@ struct dm_writecache {
 	struct dm_target *ti;
 	struct dm_dev *dev;
 	struct dm_dev *ssd_dev;
+	sector_t start_sector;
 	void *memory_map;
 	uint64_t memory_map_size;
 	size_t metadata_sectors;
@@ -259,7 +260,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 	if (da != p) {
 		long i;
 		wc->memory_map = NULL;
-		pages = kvmalloc(p * sizeof(struct page *), GFP_KERNEL);
+		pages = kvmalloc_array(p, sizeof(struct page *), GFP_KERNEL);
 		if (!pages) {
 			r = -ENOMEM;
 			goto err2;
@@ -293,6 +294,10 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 	}
 
 	dax_read_unlock(id);
+
+	wc->memory_map += (size_t)wc->start_sector << SECTOR_SHIFT;
+	wc->memory_map_size -= (size_t)wc->start_sector << SECTOR_SHIFT;
+
 	return 0;
 err3:
 	kvfree(pages);
@@ -311,7 +316,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 static void persistent_memory_release(struct dm_writecache *wc)
 {
 	if (wc->memory_vmapped)
-		vunmap(wc->memory_map);
+		vunmap(wc->memory_map - ((size_t)wc->start_sector << SECTOR_SHIFT));
 }
 
 static struct page *persistent_memory_page(void *addr)
@@ -359,7 +364,7 @@ static void *memory_data(struct dm_writecache *wc, struct wc_entry *e)
 
 static sector_t cache_sector(struct dm_writecache *wc, struct wc_entry *e)
 {
-	return wc->metadata_sectors +
+	return wc->start_sector + wc->metadata_sectors +
 		((sector_t)e->index << (wc->block_size_bits - SECTOR_SHIFT));
 }
 
@@ -471,6 +476,7 @@ static void ssd_commit_flushed(struct dm_writecache *wc)
 		if (unlikely(region.sector + region.count > wc->metadata_sectors))
 			region.count = wc->metadata_sectors - region.sector;
 
+		region.sector += wc->start_sector;
 		atomic_inc(&endio.count);
 		req.bi_op = REQ_OP_WRITE;
 		req.bi_op_flags = REQ_SYNC;
@@ -859,7 +865,7 @@ static int writecache_alloc_entries(struct dm_writecache *wc)
 
 	if (wc->entries)
 		return 0;
-	wc->entries = vmalloc(sizeof(struct wc_entry) * wc->n_blocks);
+	wc->entries = vmalloc(array_size(sizeof(struct wc_entry), wc->n_blocks));
 	if (!wc->entries)
 		return -ENOMEM;
 	for (b = 0; b < wc->n_blocks; b++) {
@@ -1481,9 +1487,9 @@ static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeba
 		wb->bio.bi_iter.bi_sector = read_original_sector(wc, e);
 		wb->page_offset = PAGE_SIZE;
 		if (max_pages <= WB_LIST_INLINE ||
-		    unlikely(!(wb->wc_list = kmalloc(max_pages * sizeof(struct wc_entry *),
-						     GFP_NOIO | __GFP_NORETRY |
-						     __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
+		    unlikely(!(wb->wc_list = kmalloc_array(max_pages, sizeof(struct wc_entry *),
+							   GFP_NOIO | __GFP_NORETRY |
+							   __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
 			wb->wc_list = wb->wc_list_inline;
 			max_pages = WB_LIST_INLINE;
 		}
@@ -1946,14 +1952,6 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	}
 	wc->memory_map_size = i_size_read(wc->ssd_dev->bdev->bd_inode);
 
-	if (WC_MODE_PMEM(wc)) {
-		r = persistent_memory_claim(wc);
-		if (r) {
-			ti->error = "Unable to map persistent memory for cache";
-			goto bad;
-		}
-	}
-
 	/*
 	 * Parse the cache block size
 	 */
@@ -1982,7 +1980,16 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	while (opt_params) {
 		string = dm_shift_arg(&as), opt_params--;
-		if (!strcasecmp(string, "high_watermark") && opt_params >= 1) {
+		if (!strcasecmp(string, "start_sector") && opt_params >= 1) {
+			unsigned long long start_sector;
+			string = dm_shift_arg(&as), opt_params--;
+			if (sscanf(string, "%llu%c", &start_sector, &dummy) != 1)
+				goto invalid_optional;
+			wc->start_sector = start_sector;
+			if (wc->start_sector != start_sector ||
+			    wc->start_sector >= wc->memory_map_size >> SECTOR_SHIFT)
+				goto invalid_optional;
+		} else if (!strcasecmp(string, "high_watermark") && opt_params >= 1) {
 			string = dm_shift_arg(&as), opt_params--;
 			if (sscanf(string, "%d%c", &high_wm_percent, &dummy) != 1)
 				goto invalid_optional;
@@ -2039,12 +2046,20 @@ invalid_optional:
 		goto bad;
 	}
 
-	if (!WC_MODE_PMEM(wc)) {
+	if (WC_MODE_PMEM(wc)) {
+		r = persistent_memory_claim(wc);
+		if (r) {
+			ti->error = "Unable to map persistent memory for cache";
+			goto bad;
+		}
+	} else {
 		struct dm_io_region region;
 		struct dm_io_request req;
 		size_t n_blocks, n_metadata_blocks;
 		uint64_t n_bitmap_bits;
 
+		wc->memory_map_size -= (uint64_t)wc->start_sector << SECTOR_SHIFT;
+
 		bio_list_init(&wc->flush_list);
 		wc->flush_thread = kthread_create(writecache_flush_thread, wc, "dm_writecache_flush");
 		if (IS_ERR(wc->flush_thread)) {
@@ -2097,7 +2112,7 @@ invalid_optional:
 		}
 
 		region.bdev = wc->ssd_dev->bdev;
-		region.sector = 0;
+		region.sector = wc->start_sector;
 		region.count = wc->metadata_sectors;
 		req.bi_op = REQ_OP_READ;
 		req.bi_op_flags = REQ_SYNC;
@@ -2265,7 +2280,7 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 
 static struct target_type writecache_target = {
 	.name			= "writecache",
-	.version		= {1, 0, 0},
+	.version		= {1, 1, 0},
 	.module			= THIS_MODULE,
 	.ctr			= writecache_ctr,
 	.dtr			= writecache_dtr,
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 3c0e45f4dcf5..a44183ff4be0 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -787,7 +787,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	/* Chunk BIO work */
 	mutex_init(&dmz->chunk_lock);
-	INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_KERNEL);
+	INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOIO);
 	dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", WQ_MEM_RECLAIM | WQ_UNBOUND,
 					0, dev->name);
 	if (!dmz->chunk_wq) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index e65429a29c06..20f7e4ef5342 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -609,7 +609,8 @@ static void start_io_acct(struct dm_io *io)
 
 	io->start_time = jiffies;
 
-	generic_start_io_acct(md->queue, rw, bio_sectors(bio), &dm_disk(md)->part0);
+	generic_start_io_acct(md->queue, bio_op(bio), bio_sectors(bio),
+			      &dm_disk(md)->part0);
 
 	atomic_set(&dm_disk(md)->part0.in_flight[rw],
 		   atomic_inc_return(&md->pending[rw]));
@@ -628,7 +629,8 @@ static void end_io_acct(struct dm_io *io)
 	int pending;
 	int rw = bio_data_dir(bio);
 
-	generic_end_io_acct(md->queue, rw, &dm_disk(md)->part0, io->start_time);
+	generic_end_io_acct(md->queue, bio_op(bio), &dm_disk(md)->part0,
+			    io->start_time);
 
 	if (unlikely(dm_stats_used(&md->stats)))
 		dm_stats_account_io(&md->stats, bio_data_dir(bio),
@@ -1056,8 +1058,7 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	if (len < 1)
 		goto out;
 	nr_pages = min(len, nr_pages);
-	if (ti->type->direct_access)
-		ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
+	ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
 
  out:
 	dm_put_live_table(md, srcu_idx);
@@ -1606,10 +1607,9 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 				 * the usage of io->orig_bio in dm_remap_zone_report()
 				 * won't be affected by this reassignment.
 				 */
-				struct bio *b = bio_clone_bioset(bio, GFP_NOIO,
-								 &md->queue->bio_split);
+				struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count,
+							  GFP_NOIO, &md->queue->bio_split);
 				ci.io->orig_bio = b;
-				bio_advance(bio, (bio_sectors(bio) - ci.sector_count) << 9);
 				bio_chain(b, bio);
 				ret = generic_make_request(bio);
 				break;
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 021cbf9ef1bf..e8a74e92be30 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -304,15 +304,6 @@ static void recover_bitmaps(struct md_thread *thread)
 	while (cinfo->recovery_map) {
 		slot = fls64((u64)cinfo->recovery_map) - 1;
 
-		/* Clear suspend_area associated with the bitmap */
-		spin_lock_irq(&cinfo->suspend_lock);
-		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
-			if (slot == s->slot) {
-				list_del(&s->list);
-				kfree(s);
-			}
-		spin_unlock_irq(&cinfo->suspend_lock);
-
 		snprintf(str, 64, "bitmap%04d", slot);
 		bm_lockres = lockres_init(mddev, str, NULL, 1);
 		if (!bm_lockres) {
@@ -331,14 +322,30 @@ static void recover_bitmaps(struct md_thread *thread)
 			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
 			goto clear_bit;
 		}
+
+		/* Clear suspend_area associated with the bitmap */
+		spin_lock_irq(&cinfo->suspend_lock);
+		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
+			if (slot == s->slot) {
+				list_del(&s->list);
+				kfree(s);
+			}
+		spin_unlock_irq(&cinfo->suspend_lock);
+
 		if (hi > 0) {
 			if (lo < mddev->recovery_cp)
 				mddev->recovery_cp = lo;
 			/* wake up thread to continue resync in case resync
 			 * is not finished */
 			if (mddev->recovery_cp != MaxSector) {
-			    set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			    md_wakeup_thread(mddev->thread);
+				/*
+				 * clear the REMOTE flag since we will launch
+				 * resync thread in current node.
+				 */
+				clear_bit(MD_RESYNCING_REMOTE,
+					  &mddev->recovery);
+				set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+				md_wakeup_thread(mddev->thread);
 			}
 		}
 clear_bit:
@@ -457,6 +464,11 @@ static void process_suspend_info(struct mddev *mddev,
 	struct suspend_info *s;
 
 	if (!hi) {
+		/*
+		 * clear the REMOTE flag since resync or recovery is finished
+		 * in remote node.
+		 */
+		clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 		remove_suspend_info(mddev, slot);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
@@ -585,6 +597,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 		revalidate_disk(mddev->gendisk);
 		break;
 	case RESYNCING:
+		set_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 		process_suspend_info(mddev, le32_to_cpu(msg->slot),
 				     le64_to_cpu(msg->low),
 				     le64_to_cpu(msg->high));
@@ -1265,8 +1278,18 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
 static int resync_finish(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
+
+	clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 	dlm_unlock_sync(cinfo->resync_lockres);
-	return resync_info_update(mddev, 0, 0);
+
+	/*
+	 * If resync thread is interrupted so we can't say resync is finished,
+	 * another node will launch resync thread to continue.
+	 */
+	if (test_bit(MD_CLOSING, &mddev->flags))
+		return 0;
+	else
+		return resync_info_update(mddev, 0, 0);
 }
 
 static int area_resyncing(struct mddev *mddev, int direction,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 29b0cd9ec951..724def2f9eaa 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -204,10 +204,6 @@ static int start_readonly;
  */
 static bool create_on_open = true;
 
-/* bio_clone_mddev
- * like bio_clone_bioset, but with a local bio set
- */
-
 struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 			    struct mddev *mddev)
 {
@@ -335,6 +331,7 @@ EXPORT_SYMBOL(md_handle_request);
 static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
+	const int sgrp = op_stat_group(bio_op(bio));
 	struct mddev *mddev = q->queuedata;
 	unsigned int sectors;
 	int cpu;
@@ -363,8 +360,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 	md_handle_request(mddev, bio);
 
 	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
+	part_stat_inc(cpu, &mddev->gendisk->part0, ios[sgrp]);
+	part_stat_add(cpu, &mddev->gendisk->part0, sectors[sgrp], sectors);
 	part_stat_unlock();
 
 	return BLK_QC_T_NONE;
@@ -5547,7 +5544,8 @@ int md_run(struct mddev *mddev)
 		else
 			pr_warn("md: personality for level %s is not loaded!\n",
 				mddev->clevel);
-		return -EINVAL;
+		err = -EINVAL;
+		goto abort;
 	}
 	spin_unlock(&pers_lock);
 	if (mddev->level != pers->level) {
@@ -5560,7 +5558,8 @@ int md_run(struct mddev *mddev)
 	    pers->start_reshape == NULL) {
 		/* This personality cannot handle reshaping... */
 		module_put(pers->owner);
-		return -EINVAL;
+		err = -EINVAL;
+		goto abort;
 	}
 
 	if (pers->sync_request) {
@@ -5629,7 +5628,7 @@ int md_run(struct mddev *mddev)
 		mddev->private = NULL;
 		module_put(pers->owner);
 		bitmap_destroy(mddev);
-		return err;
+		goto abort;
 	}
 	if (mddev->queue) {
 		bool nonrot = true;
@@ -7678,6 +7677,23 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 		resync -= atomic_read(&mddev->recovery_active);
 
 	if (resync == 0) {
+		if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery)) {
+			struct md_rdev *rdev;
+
+			rdev_for_each(rdev, mddev)
+				if (rdev->raid_disk >= 0 &&
+				    !test_bit(Faulty, &rdev->flags) &&
+				    rdev->recovery_offset != MaxSector &&
+				    rdev->recovery_offset) {
+					seq_printf(seq, "\trecover=REMOTE");
+					return 1;
+				}
+			if (mddev->reshape_position != MaxSector)
+				seq_printf(seq, "\treshape=REMOTE");
+			else
+				seq_printf(seq, "\tresync=REMOTE");
+			return 1;
+		}
 		if (mddev->recovery_cp < MaxSector) {
 			seq_printf(seq, "\tresync=PENDING");
 			return 1;
@@ -8044,8 +8060,7 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_contains->bd_disk;
-		curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
-			      (int)part_stat_read(&disk->part0, sectors[1]) -
+		curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2d148bdaba74..8afd6bfdbfb9 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -496,6 +496,7 @@ enum recovery_flags {
 	MD_RECOVERY_FROZEN,	/* User request to abort, and not restart, any action */
 	MD_RECOVERY_ERROR,	/* sync-action interrupted because io-error */
 	MD_RECOVERY_WAIT,	/* waiting for pers->start() to finish */
+	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
 static inline int __must_check mddev_lock(struct mddev *mddev)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 478cf446827f..35bd3a62451b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3893,6 +3893,13 @@ static int raid10_run(struct mddev *mddev)
 			    disk->rdev->saved_raid_disk < 0)
 				conf->fullsync = 1;
 		}
+
+		if (disk->replacement &&
+		    !test_bit(In_sync, &disk->replacement->flags) &&
+		    disk->replacement->saved_raid_disk < 0) {
+			conf->fullsync = 1;
+		}
+
 		disk->recovery_disabled = mddev->recovery_disabled - 1;
 	}
 
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 2b775abf377b..7416db70c6cc 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -717,7 +717,6 @@ static void r5c_disable_writeback_async(struct work_struct *work)
 static void r5l_submit_current_io(struct r5l_log *log)
 {
 	struct r5l_io_unit *io = log->current_io;
-	struct bio *bio;
 	struct r5l_meta_block *block;
 	unsigned long flags;
 	u32 crc;
@@ -730,7 +729,6 @@ static void r5l_submit_current_io(struct r5l_log *log)
 	block->meta_size = cpu_to_le32(io->meta_offset);
 	crc = crc32c_le(log->uuid_checksum, block, PAGE_SIZE);
 	block->checksum = cpu_to_le32(crc);
-	bio = io->current_bio;
 
 	log->current_io = NULL;
 	spin_lock_irqsave(&log->io_list_lock, flags);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2031506a0ecd..81eaa221216c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -409,16 +409,14 @@ void raid5_release_stripe(struct stripe_head *sh)
 		md_wakeup_thread(conf->mddev->thread);
 	return;
 slow_path:
-	local_irq_save(flags);
 	/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
-	if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
+	if (atomic_dec_and_lock_irqsave(&sh->count, &conf->device_lock, flags)) {
 		INIT_LIST_HEAD(&list);
 		hash = sh->hash_lock_index;
 		do_release_stripe(conf, sh, &list);
-		spin_unlock(&conf->device_lock);
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		release_inactive_stripe_list(conf, &list, hash);
 	}
-	local_irq_restore(flags);
 }
 
 static inline void remove_hash(struct stripe_head *sh)
@@ -4521,6 +4519,12 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			s->failed++;
 			if (rdev && !test_bit(Faulty, &rdev->flags))
 				do_recovery = 1;
+			else if (!rdev) {
+				rdev = rcu_dereference(
+				    conf->disks[i].replacement);
+				if (rdev && !test_bit(Faulty, &rdev->flags))
+					do_recovery = 1;
+			}
 		}
 
 		if (test_bit(R5_InJournal, &dev->flags))
diff --git a/drivers/media/platform/pxa_camera.c b/drivers/media/platform/pxa_camera.c
index d85ffbfb7c1f..b6e9e93bde7a 100644
--- a/drivers/media/platform/pxa_camera.c
+++ b/drivers/media/platform/pxa_camera.c
@@ -2375,8 +2375,6 @@ static int pxa_camera_probe(struct platform_device *pdev)
 		.src_maxburst = 8,
 		.direction = DMA_DEV_TO_MEM,
 	};
-	dma_cap_mask_t mask;
-	struct pxad_param params;
 	char clk_name[V4L2_CLK_NAME_SIZE];
 	int irq;
 	int err = 0, i;
@@ -2450,34 +2448,20 @@ static int pxa_camera_probe(struct platform_device *pdev)
 	pcdev->base = base;
 
 	/* request dma */
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	dma_cap_set(DMA_PRIVATE, mask);
-
-	params.prio = 0;
-	params.drcmr = 68;
-	pcdev->dma_chans[0] =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &params, &pdev->dev, "CI_Y");
+	pcdev->dma_chans[0] = dma_request_slave_channel(&pdev->dev, "CI_Y");
 	if (!pcdev->dma_chans[0]) {
 		dev_err(&pdev->dev, "Can't request DMA for Y\n");
 		return -ENODEV;
 	}
 
-	params.drcmr = 69;
-	pcdev->dma_chans[1] =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &params, &pdev->dev, "CI_U");
+	pcdev->dma_chans[1] = dma_request_slave_channel(&pdev->dev, "CI_U");
 	if (!pcdev->dma_chans[1]) {
 		dev_err(&pdev->dev, "Can't request DMA for Y\n");
 		err = -ENODEV;
 		goto exit_free_dma_y;
 	}
 
-	params.drcmr = 70;
-	pcdev->dma_chans[2] =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &params, &pdev->dev, "CI_V");
+	pcdev->dma_chans[2] = dma_request_slave_channel(&pdev->dev, "CI_V");
 	if (!pcdev->dma_chans[2]) {
 		dev_err(&pdev->dev, "Can't request DMA for V\n");
 		err = -ENODEV;
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index edb35a5c57ea..a99fc0ced7a7 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -728,9 +728,6 @@ EXPORT_SYMBOL_GPL(vsp1_du_setup_lif);
  */
 void vsp1_du_atomic_begin(struct device *dev, unsigned int pipe_index)
 {
-	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
-
-	mutex_lock(&vsp1->drm->lock);
 }
 EXPORT_SYMBOL_GPL(vsp1_du_atomic_begin);
 
@@ -846,6 +843,7 @@ void vsp1_du_atomic_flush(struct device *dev, unsigned int pipe_index,
 
 	drm_pipe->crc = cfg->crc;
 
+	mutex_lock(&vsp1->drm->lock);
 	vsp1_du_pipeline_setup_inputs(vsp1, pipe);
 	vsp1_du_pipeline_configure(pipe);
 	mutex_unlock(&vsp1->drm->lock);
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index 40826bba06b6..81b150e5dfdb 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -174,6 +174,7 @@ static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog)
 
 	rcu_assign_pointer(raw->progs, new_array);
 	bpf_prog_array_free(old_array);
+	bpf_prog_put(prog);
 unlock:
 	mutex_unlock(&ir_raw_handler_lock);
 	return ret;
@@ -207,29 +208,19 @@ void lirc_bpf_free(struct rc_dev *rcdev)
 	bpf_prog_array_free(rcdev->raw->progs);
 }
 
-int lirc_prog_attach(const union bpf_attr *attr)
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
-	struct bpf_prog *prog;
 	struct rc_dev *rcdev;
 	int ret;
 
 	if (attr->attach_flags)
 		return -EINVAL;
 
-	prog = bpf_prog_get_type(attr->attach_bpf_fd,
-				 BPF_PROG_TYPE_LIRC_MODE2);
-	if (IS_ERR(prog))
-		return PTR_ERR(prog);
-
 	rcdev = rc_dev_get_from_fd(attr->target_fd);
-	if (IS_ERR(rcdev)) {
-		bpf_prog_put(prog);
+	if (IS_ERR(rcdev))
 		return PTR_ERR(rcdev);
-	}
 
 	ret = lirc_bpf_attach(rcdev, prog);
-	if (ret)
-		bpf_prog_put(prog);
 
 	put_device(&rcdev->dev);
 
diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c
index 2e0066b1a31c..e7948908e78c 100644
--- a/drivers/media/rc/rc-ir-raw.c
+++ b/drivers/media/rc/rc-ir-raw.c
@@ -30,13 +30,13 @@ static int ir_raw_event_thread(void *data)
 		while (kfifo_out(&raw->kfifo, &ev, 1)) {
 			if (is_timing_event(ev)) {
 				if (ev.duration == 0)
-					dev_err(&dev->dev, "nonsensical timing event of duration 0");
+					dev_warn_once(&dev->dev, "nonsensical timing event of duration 0");
 				if (is_timing_event(raw->prev_ev) &&
 				    !is_transition(&ev, &raw->prev_ev))
-					dev_err(&dev->dev, "two consecutive events of type %s",
-						TO_STR(ev.pulse));
+					dev_warn_once(&dev->dev, "two consecutive events of type %s",
+						      TO_STR(ev.pulse));
 				if (raw->prev_ev.reset && ev.pulse == 0)
-					dev_err(&dev->dev, "timing event after reset should be pulse");
+					dev_warn_once(&dev->dev, "timing event after reset should be pulse");
 			}
 			list_for_each_entry(handler, &ir_raw_handler_list, list)
 				if (dev->enabled_protocols &
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 2e222d9ee01f..ca68e1d2b2f9 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -679,6 +679,14 @@ static void ir_timer_repeat(struct timer_list *t)
 	spin_unlock_irqrestore(&dev->keylock, flags);
 }
 
+static unsigned int repeat_period(int protocol)
+{
+	if (protocol >= ARRAY_SIZE(protocols))
+		return 100;
+
+	return protocols[protocol].repeat_period;
+}
+
 /**
  * rc_repeat() - signals that a key is still pressed
  * @dev:	the struct rc_dev descriptor of the device
@@ -691,7 +699,7 @@ void rc_repeat(struct rc_dev *dev)
 {
 	unsigned long flags;
 	unsigned int timeout = nsecs_to_jiffies(dev->timeout) +
-		msecs_to_jiffies(protocols[dev->last_protocol].repeat_period);
+		msecs_to_jiffies(repeat_period(dev->last_protocol));
 	struct lirc_scancode sc = {
 		.scancode = dev->last_scancode, .rc_proto = dev->last_protocol,
 		.keycode = dev->keypressed ? dev->last_keycode : KEY_RESERVED,
@@ -803,7 +811,7 @@ void rc_keydown(struct rc_dev *dev, enum rc_proto protocol, u32 scancode,
 
 	if (dev->keypressed) {
 		dev->keyup_jiffies = jiffies + nsecs_to_jiffies(dev->timeout) +
-			msecs_to_jiffies(protocols[protocol].repeat_period);
+			msecs_to_jiffies(repeat_period(protocol));
 		mod_timer(&dev->timer_keyup, dev->keyup_jiffies);
 	}
 	spin_unlock_irqrestore(&dev->keylock, flags);
diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c
index 3f77aa318035..82595cebc0b8 100644
--- a/drivers/media/v4l2-core/v4l2-fwnode.c
+++ b/drivers/media/v4l2-core/v4l2-fwnode.c
@@ -739,7 +739,7 @@ static struct fwnode_handle *v4l2_fwnode_reference_get_int_prop(
 	const char * const *props, unsigned int nprops)
 {
 	struct fwnode_reference_args fwnode_args;
-	unsigned int *args = fwnode_args.args;
+	u64 *args = fwnode_args.args;
 	struct fwnode_handle *child;
 	int ret;
 
diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index 8d731d6c3e54..63389f075f1d 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -116,12 +116,14 @@ config FSL_CORENET_CF
 
 config FSL_IFC
 	bool
-	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
+	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+	depends on HAS_IOMEM
 
 config JZ4780_NEMC
 	bool "Ingenic JZ4780 SoC NEMC driver"
 	default y
-	depends on MACH_JZ4780
+	depends on MACH_JZ4780 || COMPILE_TEST
+	depends on HAS_IOMEM && OF
 	help
 	  This driver is for the NAND/External Memory Controller (NEMC) in
 	  the Ingenic JZ4780. This controller is used to handle external
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 753b1a698fc4..8fd5ec4d6042 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -67,10 +67,8 @@ static struct file *cxl_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	/* strongly inspired by anon_inode_getfile() */
@@ -91,27 +89,15 @@ static struct file *cxl_getfile(const char *name,
 		goto err_fs;
 	}
 
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(cxl_vfs_mount->mnt_sb, &this);
-	if (!path.dentry)
+	file = alloc_file_pseudo(inode, cxl_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
+	if (IS_ERR(file))
 		goto err_inode;
 
-	path.mnt = mntget(cxl_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
-	if (IS_ERR(file))
-		goto err_dput;
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
 
-err_dput:
-	path_put(&path);
 err_inode:
 	iput(inode);
 err_fs:
diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c
index e05c3245930a..fa840666bdd1 100644
--- a/drivers/misc/ibmasm/ibmasmfs.c
+++ b/drivers/misc/ibmasm/ibmasmfs.c
@@ -507,35 +507,14 @@ static int remote_settings_file_close(struct inode *inode, struct file *file)
 static ssize_t remote_settings_file_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
 {
 	void __iomem *address = (void __iomem *)file->private_data;
-	unsigned char *page;
-	int retval;
 	int len = 0;
 	unsigned int value;
-
-	if (*offset < 0)
-		return -EINVAL;
-	if (count == 0 || count > 1024)
-		return 0;
-	if (*offset != 0)
-		return 0;
-
-	page = (unsigned char *)__get_free_page(GFP_KERNEL);
-	if (!page)
-		return -ENOMEM;
+	char lbuf[20];
 
 	value = readl(address);
-	len = sprintf(page, "%d\n", value);
-
-	if (copy_to_user(buf, page, len)) {
-		retval = -EFAULT;
-		goto exit;
-	}
-	*offset += len;
-	retval = len;
+	len = snprintf(lbuf, sizeof(lbuf), "%d\n", value);
 
-exit:
-	free_page((unsigned long)page);
-	return retval;
+	return simple_read_from_buffer(buf, count, offset, lbuf, len);
 }
 
 static ssize_t remote_settings_file_write(struct file *file, const char __user *ubuff, size_t count, loff_t *offset)
diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c
index b0b8f18a85e3..6649f0d56d2f 100644
--- a/drivers/misc/mei/interrupt.c
+++ b/drivers/misc/mei/interrupt.c
@@ -310,8 +310,11 @@ int mei_irq_read_handler(struct mei_device *dev,
 	if (&cl->link == &dev->file_list) {
 		/* A message for not connected fixed address clients
 		 * should be silently discarded
+		 * On power down client may be force cleaned,
+		 * silently discard such messages
 		 */
-		if (hdr_is_fixed(mei_hdr)) {
+		if (hdr_is_fixed(mei_hdr) ||
+		    dev->dev_state == MEI_DEV_POWER_DOWN) {
 			mei_irq_discard_msg(dev, mei_hdr);
 			ret = 0;
 			goto reset_slots;
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index efd733472a35..56c6f79a5c5a 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -467,7 +467,7 @@ static int vmballoon_send_batched_lock(struct vmballoon *b,
 		unsigned int num_pages, bool is_2m_pages, unsigned int *target)
 {
 	unsigned long status;
-	unsigned long pfn = page_to_pfn(b->page);
+	unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page));
 
 	STATS_INC(b->stats.lock[is_2m_pages]);
 
@@ -515,7 +515,7 @@ static bool vmballoon_send_batched_unlock(struct vmballoon *b,
 		unsigned int num_pages, bool is_2m_pages, unsigned int *target)
 {
 	unsigned long status;
-	unsigned long pfn = page_to_pfn(b->page);
+	unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page));
 
 	STATS_INC(b->stats.unlock[is_2m_pages]);
 
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index ef05e0039378..2a833686784b 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -27,8 +27,8 @@ struct mmc_gpio {
 	bool override_cd_active_level;
 	irqreturn_t (*cd_gpio_isr)(int irq, void *dev_id);
 	char *ro_label;
-	char cd_label[0];
 	u32 cd_debounce_delay_ms;
+	char cd_label[];
 };
 
 static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id)
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 623f4d27fa01..80dc2fd6576c 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -1065,8 +1065,8 @@ static void dw_mci_ctrl_thld(struct dw_mci *host, struct mmc_data *data)
 	 * It's used when HS400 mode is enabled.
 	 */
 	if (data->flags & MMC_DATA_WRITE &&
-		!(host->timing != MMC_TIMING_MMC_HS400))
-		return;
+		host->timing != MMC_TIMING_MMC_HS400)
+		goto disable;
 
 	if (data->flags & MMC_DATA_WRITE)
 		enable = SDMMC_CARD_WR_THR_EN;
@@ -1074,7 +1074,8 @@ static void dw_mci_ctrl_thld(struct dw_mci *host, struct mmc_data *data)
 		enable = SDMMC_CARD_RD_THR_EN;
 
 	if (host->timing != MMC_TIMING_MMC_HS200 &&
-	    host->timing != MMC_TIMING_UHS_SDR104)
+	    host->timing != MMC_TIMING_UHS_SDR104 &&
+	    host->timing != MMC_TIMING_MMC_HS400)
 		goto disable;
 
 	blksz_depth = blksz / (1 << host->data_shift);
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 75f781c11e89..de4e6e5bf304 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -293,9 +293,10 @@ static void mxcmci_swap_buffers(struct mmc_data *data)
 	int i;
 
 	for_each_sg(data->sg, sg, data->sg_len, i) {
-		void *buf = kmap_atomic(sg_page(sg) + sg->offset;
+		void *buf = kmap_atomic(sg_page(sg) + sg->offset);
 		buffer_swap32(buf, sg->length);
 		kunmap_atomic(buf);
+	}
 }
 #else
 static inline void mxcmci_swap_buffers(struct mmc_data *data) {}
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index c763b404510f..6c94474e36f4 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -24,7 +24,6 @@
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
-#include <linux/dma/pxa-dma.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/mmc/host.h>
@@ -637,10 +636,8 @@ static int pxamci_probe(struct platform_device *pdev)
 {
 	struct mmc_host *mmc;
 	struct pxamci_host *host = NULL;
-	struct resource *r, *dmarx, *dmatx;
-	struct pxad_param param_rx, param_tx;
+	struct resource *r;
 	int ret, irq, gpio_cd = -1, gpio_ro = -1, gpio_power = -1;
-	dma_cap_mask_t mask;
 
 	ret = pxamci_of_init(pdev);
 	if (ret)
@@ -739,34 +736,14 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, mmc);
 
-	if (!pdev->dev.of_node) {
-		dmarx = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-		dmatx = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-		if (!dmarx || !dmatx) {
-			ret = -ENXIO;
-			goto out;
-		}
-		param_rx.prio = PXAD_PRIO_LOWEST;
-		param_rx.drcmr = dmarx->start;
-		param_tx.prio = PXAD_PRIO_LOWEST;
-		param_tx.drcmr = dmatx->start;
-	}
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-
-	host->dma_chan_rx =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param_rx, &pdev->dev, "rx");
+	host->dma_chan_rx = dma_request_slave_channel(&pdev->dev, "rx");
 	if (host->dma_chan_rx == NULL) {
 		dev_err(&pdev->dev, "unable to request rx dma channel\n");
 		ret = -ENODEV;
 		goto out;
 	}
 
-	host->dma_chan_tx =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param_tx,  &pdev->dev, "tx");
+	host->dma_chan_tx = dma_request_slave_channel(&pdev->dev, "tx");
 	if (host->dma_chan_tx == NULL) {
 		dev_err(&pdev->dev, "unable to request tx dma channel\n");
 		ret = -ENODEV;
diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
index f7f9773d161f..d032bd63444d 100644
--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
@@ -139,8 +139,7 @@ renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) {
 	renesas_sdhi_internal_dmac_dm_write(host, DM_CM_RST,
 					    RST_RESERVED_BITS | val);
 
-	if (host->data && host->data->flags & MMC_DATA_READ)
-		clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+	clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
 
 	renesas_sdhi_internal_dmac_enable_dma(host, true);
 }
@@ -164,17 +163,14 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
 		goto force_pio;
 
 	/* This DMAC cannot handle if buffer is not 8-bytes alignment */
-	if (!IS_ALIGNED(sg_dma_address(sg), 8)) {
-		dma_unmap_sg(&host->pdev->dev, sg, host->sg_len,
-			     mmc_get_dma_dir(data));
-		goto force_pio;
-	}
+	if (!IS_ALIGNED(sg_dma_address(sg), 8))
+		goto force_pio_with_unmap;
 
 	if (data->flags & MMC_DATA_READ) {
 		dtran_mode |= DTRAN_MODE_CH_NUM_CH1;
 		if (test_bit(SDHI_INTERNAL_DMAC_ONE_RX_ONLY, &global_flags) &&
 		    test_and_set_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags))
-			goto force_pio;
+			goto force_pio_with_unmap;
 	} else {
 		dtran_mode |= DTRAN_MODE_CH_NUM_CH0;
 	}
@@ -189,6 +185,9 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
 
 	return;
 
+force_pio_with_unmap:
+	dma_unmap_sg(&host->pdev->dev, sg, host->sg_len, mmc_get_dma_dir(data));
+
 force_pio:
 	host->force_pio = true;
 	renesas_sdhi_internal_dmac_enable_dma(host, false);
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index d6aef70d34fa..4eb3d29ecde1 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -312,6 +312,15 @@ static u32 esdhc_readl_le(struct sdhci_host *host, int reg)
 
 			if (imx_data->socdata->flags & ESDHC_FLAG_HS400)
 				val |= SDHCI_SUPPORT_HS400;
+
+			/*
+			 * Do not advertise faster UHS modes if there are no
+			 * pinctrl states for 100MHz/200MHz.
+			 */
+			if (IS_ERR_OR_NULL(imx_data->pins_100mhz) ||
+			    IS_ERR_OR_NULL(imx_data->pins_200mhz))
+				val &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_DDR50
+					 | SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_HS400);
 		}
 	}
 
@@ -1158,18 +1167,6 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 						ESDHC_PINCTRL_STATE_100MHZ);
 		imx_data->pins_200mhz = pinctrl_lookup_state(imx_data->pinctrl,
 						ESDHC_PINCTRL_STATE_200MHZ);
-		if (IS_ERR(imx_data->pins_100mhz) ||
-				IS_ERR(imx_data->pins_200mhz)) {
-			dev_warn(mmc_dev(host->mmc),
-				"could not get ultra high speed state, work on normal mode\n");
-			/*
-			 * fall back to not supporting uhs by specifying no
-			 * 1.8v quirk
-			 */
-			host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
-		}
-	} else {
-		host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
 	}
 
 	/* call to generic mmc_of_parse to support additional capabilities */
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index e7472590f2ed..8e7f3e35ee3d 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -1446,6 +1446,7 @@ static int sunxi_mmc_runtime_resume(struct device *dev)
 	sunxi_mmc_init_host(host);
 	sunxi_mmc_set_bus_width(host, mmc->ios.bus_width);
 	sunxi_mmc_set_clk(host, &mmc->ios);
+	enable_irq(host->irq);
 
 	return 0;
 }
@@ -1455,6 +1456,12 @@ static int sunxi_mmc_runtime_suspend(struct device *dev)
 	struct mmc_host	*mmc = dev_get_drvdata(dev);
 	struct sunxi_mmc_host *host = mmc_priv(mmc);
 
+	/*
+	 * When clocks are off, it's possible receiving
+	 * fake interrupts, which will stall the system.
+	 * Disabling the irq  will prevent this.
+	 */
+	disable_irq(host->irq);
 	sunxi_mmc_reset_host(host);
 	sunxi_mmc_disable(host);
 
diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index 46ab7feec6b6..c77f537323ec 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -24,7 +24,7 @@ config MTD_TESTS
 
 config MTD_REDBOOT_PARTS
 	tristate "RedBoot partition table parsing"
-	---help---
+	help
 	  RedBoot is a ROM monitor and bootloader which deals with multiple
 	  'images' in flash devices by putting a table one of the erase
 	  blocks on the device, similar to a partition table, which gives
@@ -45,7 +45,7 @@ if MTD_REDBOOT_PARTS
 config MTD_REDBOOT_DIRECTORY_BLOCK
 	int "Location of RedBoot partition table"
 	default "-1"
-	---help---
+	help
 	  This option is the Linux counterpart to the
 	  CYGNUM_REDBOOT_FIS_DIRECTORY_BLOCK RedBoot compile time
 	  option.
@@ -75,7 +75,7 @@ endif # MTD_REDBOOT_PARTS
 config MTD_CMDLINE_PARTS
 	tristate "Command line partition table parsing"
 	depends on MTD
-	---help---
+	help
 	  Allow generic configuration of the MTD partition tables via the kernel
 	  command line. Multiple flash resources are supported for hardware where
 	  different kinds of flash memory are available.
@@ -112,7 +112,7 @@ config MTD_CMDLINE_PARTS
 config MTD_AFS_PARTS
 	tristate "ARM Firmware Suite partition parsing"
 	depends on (ARM || ARM64)
-	---help---
+	help
 	  The ARM Firmware Suite allows the user to divide flash devices into
 	  multiple 'images'. Each such image has a header containing its name
 	  and offset/size etc.
@@ -136,7 +136,7 @@ config MTD_OF_PARTS
 
 config MTD_AR7_PARTS
 	tristate "TI AR7 partitioning support"
-	---help---
+	help
 	  TI AR7 partitioning support
 
 config MTD_BCM63XX_PARTS
@@ -170,7 +170,7 @@ config MTD_BLOCK
 	tristate "Caching block device access to MTD devices"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  Although most flash chips have an erase size too large to be useful
 	  as block devices, it is possible to use MTD devices which are based
 	  on RAM chips in this manner. This block device is a user of MTD
@@ -205,7 +205,7 @@ config FTL
 	tristate "FTL (Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the original Flash Translation Layer which
 	  is part of the PCMCIA specification. It uses a kind of pseudo-
 	  file system on a flash device to emulate a block device with
@@ -222,7 +222,7 @@ config NFTL
 	tristate "NFTL (NAND Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the NAND Flash Translation Layer which is
 	  used on M-Systems' DiskOnChip devices. It uses a kind of pseudo-
 	  file system on a flash device to emulate a block device with
@@ -246,7 +246,7 @@ config INFTL
 	tristate "INFTL (Inverse NAND Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the Inverse NAND Flash Translation
 	  Layer which is used on M-Systems' newer DiskOnChip devices. It
 	  uses a kind of pseudo-file system on a flash device to emulate
@@ -261,10 +261,10 @@ config INFTL
 	  not use it.
 
 config RFD_FTL
-        tristate "Resident Flash Disk (Flash Translation Layer) support"
+	tristate "Resident Flash Disk (Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the flash translation layer known
 	  as the Resident Flash Disk (RFD), as used by the Embedded BIOS
 	  of General Software. There is a blurb at:
@@ -308,7 +308,7 @@ config MTD_SWAP
 	select MTD_BLKDEVS
 	help
 	  Provides volatile block device driver on top of mtd partition
-          suitable for swapping.  The mapping of written blocks is not saved.
+	  suitable for swapping.  The mapping of written blocks is not saved.
 	  The driver provides wear leveling by storing erase counter into the
 	  OOB.
 
diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig
index bbfa1f129266..39ec32a29051 100644
--- a/drivers/mtd/chips/Kconfig
+++ b/drivers/mtd/chips/Kconfig
@@ -44,7 +44,7 @@ choice
 	prompt "Flash cmd/query data swapping"
 	depends on MTD_CFI_ADV_OPTIONS
 	default MTD_CFI_NOSWAP
-	---help---
+	help
 	  This option defines the way in which the CPU attempts to arrange
 	  data bits when writing the 'magic' commands to the chips. Saying
 	  'NO', which is the default when CONFIG_MTD_CFI_ADV_OPTIONS isn't
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index a0c655628d6d..72428b6bfc47 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -1216,7 +1216,6 @@ static inline int do_read_secsi_onechip(struct map_info *map,
 					size_t grouplen)
 {
 	DECLARE_WAITQUEUE(wait, current);
-	unsigned long timeo = jiffies + HZ;
 
  retry:
 	mutex_lock(&chip->mutex);
@@ -1229,7 +1228,6 @@ static inline int do_read_secsi_onechip(struct map_info *map,
 
 		schedule();
 		remove_wait_queue(&chip->wq, &wait);
-		timeo = jiffies + HZ;
 
 		goto retry;
 	}
@@ -2526,7 +2524,7 @@ static int cfi_atmel_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 
 struct ppb_lock {
 	struct flchip *chip;
-	loff_t offset;
+	unsigned long adr;
 	int locked;
 };
 
@@ -2544,8 +2542,9 @@ static int __maybe_unused do_ppb_xxlock(struct map_info *map,
 	unsigned long timeo;
 	int ret;
 
+	adr += chip->start;
 	mutex_lock(&chip->mutex);
-	ret = get_chip(map, chip, adr + chip->start, FL_LOCKING);
+	ret = get_chip(map, chip, adr, FL_LOCKING);
 	if (ret) {
 		mutex_unlock(&chip->mutex);
 		return ret;
@@ -2563,8 +2562,8 @@ static int __maybe_unused do_ppb_xxlock(struct map_info *map,
 
 	if (thunk == DO_XXLOCK_ONEBLOCK_LOCK) {
 		chip->state = FL_LOCKING;
-		map_write(map, CMD(0xA0), chip->start + adr);
-		map_write(map, CMD(0x00), chip->start + adr);
+		map_write(map, CMD(0xA0), adr);
+		map_write(map, CMD(0x00), adr);
 	} else if (thunk == DO_XXLOCK_ONEBLOCK_UNLOCK) {
 		/*
 		 * Unlocking of one specific sector is not supported, so we
@@ -2602,7 +2601,7 @@ static int __maybe_unused do_ppb_xxlock(struct map_info *map,
 	map_write(map, CMD(0x00), chip->start);
 
 	chip->state = FL_READY;
-	put_chip(map, chip, adr + chip->start);
+	put_chip(map, chip, adr);
 	mutex_unlock(&chip->mutex);
 
 	return ret;
@@ -2659,9 +2658,9 @@ static int __maybe_unused cfi_ppb_unlock(struct mtd_info *mtd, loff_t ofs,
 		 * sectors shall be unlocked, so lets keep their locking
 		 * status at "unlocked" (locked=0) for the final re-locking.
 		 */
-		if ((adr < ofs) || (adr >= (ofs + len))) {
+		if ((offset < ofs) || (offset >= (ofs + len))) {
 			sect[sectors].chip = &cfi->chips[chipnum];
-			sect[sectors].offset = offset;
+			sect[sectors].adr = adr;
 			sect[sectors].locked = do_ppb_xxlock(
 				map, &cfi->chips[chipnum], adr, 0,
 				DO_XXLOCK_ONEBLOCK_GETLOCK);
@@ -2675,6 +2674,8 @@ static int __maybe_unused cfi_ppb_unlock(struct mtd_info *mtd, loff_t ofs,
 			i++;
 
 		if (adr >> cfi->chipshift) {
+			if (offset >= (ofs + len))
+				break;
 			adr = 0;
 			chipnum++;
 
@@ -2705,7 +2706,7 @@ static int __maybe_unused cfi_ppb_unlock(struct mtd_info *mtd, loff_t ofs,
 	 */
 	for (i = 0; i < sectors; i++) {
 		if (sect[i].locked)
-			do_ppb_xxlock(map, sect[i].chip, sect[i].offset, 0,
+			do_ppb_xxlock(map, sect[i].chip, sect[i].adr, 0,
 				      DO_XXLOCK_ONEBLOCK_LOCK);
 	}
 
diff --git a/drivers/mtd/chips/gen_probe.c b/drivers/mtd/chips/gen_probe.c
index b57ceea21513..837b04ab96a9 100644
--- a/drivers/mtd/chips/gen_probe.c
+++ b/drivers/mtd/chips/gen_probe.c
@@ -202,16 +202,19 @@ static inline struct mtd_info *cfi_cmdset_unknown(struct map_info *map,
 	struct cfi_private *cfi = map->fldrv_priv;
 	__u16 type = primary?cfi->cfiq->P_ID:cfi->cfiq->A_ID;
 #ifdef CONFIG_MODULES
-	char probename[sizeof(VMLINUX_SYMBOL_STR(cfi_cmdset_%4.4X))];
 	cfi_cmdset_fn_t *probe_function;
+	char *probename;
 
-	sprintf(probename, VMLINUX_SYMBOL_STR(cfi_cmdset_%4.4X), type);
+	probename = kasprintf(GFP_KERNEL, "cfi_cmdset_%4.4X", type);
+	if (!probename)
+		return NULL;
 
 	probe_function = __symbol_get(probename);
 	if (!probe_function) {
 		request_module("cfi_cmdset_%4.4X", type);
 		probe_function = __symbol_get(probename);
 	}
+	kfree(probename);
 
 	if (probe_function) {
 		struct mtd_info *mtd;
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 57b02c4b3f63..e514d57a0419 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -5,7 +5,7 @@ menu "Self-contained MTD device drivers"
 config MTD_PMC551
 	tristate "Ramix PMC551 PCI Mezzanine RAM card support"
 	depends on PCI
-	---help---
+	help
 	  This provides a MTD device driver for the Ramix PMC551 RAM PCI card
 	  from Ramix Inc. <http://www.ramix.com/products/memory/pmc551.html>.
 	  These devices come in memory configurations from 32M - 1G.  If you
@@ -209,7 +209,7 @@ config MTD_DOCG3
 	select BCH
 	select BCH_CONST_PARAMS
 	select BITREVERSE
-	---help---
+	help
 	  This provides an MTD device driver for the M-Systems DiskOnChip
 	  G3 devices.
 
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index e84563d2067f..cbfafc453274 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -28,11 +28,9 @@
 #include <linux/spi/flash.h>
 #include <linux/mtd/spi-nor.h>
 
-#define	MAX_CMD_SIZE		6
 struct m25p {
 	struct spi_mem		*spimem;
 	struct spi_nor		spi_nor;
-	u8			command[MAX_CMD_SIZE];
 };
 
 static int m25p80_read_reg(struct spi_nor *nor, u8 code, u8 *val, int len)
@@ -70,7 +68,7 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 1),
 				   SPI_MEM_OP_ADDR(nor->addr_width, to, 1),
-				   SPI_MEM_OP_DUMMY(0, 1),
+				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_OUT(len, buf, 1));
 	size_t remaining = len;
 	int ret;
@@ -78,7 +76,6 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	/* get transfer protocols. */
 	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->write_proto);
 	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->write_proto);
-	op.dummy.buswidth = op.addr.buswidth;
 	op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->write_proto);
 
 	if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
@@ -202,6 +199,9 @@ static int m25p_probe(struct spi_mem *spimem)
 	if (data && data->name)
 		nor->mtd.name = data->name;
 
+	if (!nor->mtd.name)
+		nor->mtd.name = spi_mem_get_name(spimem);
+
 	/* For some (historical?) reason many platforms provide two different
 	 * names in flash_platform_data: "name" and "type". Quite often name is
 	 * set to "m25p80" and then "type" provides a real chip name.
diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c
index 3a6f450d1093..53febe8a68c3 100644
--- a/drivers/mtd/devices/mtd_dataflash.c
+++ b/drivers/mtd/devices/mtd_dataflash.c
@@ -733,8 +733,8 @@ static struct flash_info dataflash_data[] = {
 	{ "AT45DB642x",  0x1f2800, 8192, 1056, 11, SUP_POW2PS},
 	{ "at45db642d",  0x1f2800, 8192, 1024, 10, SUP_POW2PS | IS_POW2PS},
 
-	{ "AT45DB641E",  0x1f28000100, 32768, 264, 9, SUP_EXTID | SUP_POW2PS},
-	{ "at45db641e",  0x1f28000100, 32768, 256, 8, SUP_EXTID | SUP_POW2PS | IS_POW2PS},
+	{ "AT45DB641E",  0x1f28000100ULL, 32768, 264, 9, SUP_EXTID | SUP_POW2PS},
+	{ "at45db641e",  0x1f28000100ULL, 32768, 256, 8, SUP_EXTID | SUP_POW2PS | IS_POW2PS},
 };
 
 static struct flash_info *jedec_lookup(struct spi_device *spi,
diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c
index c1312b141ae0..33593122e49b 100644
--- a/drivers/mtd/devices/powernv_flash.c
+++ b/drivers/mtd/devices/powernv_flash.c
@@ -223,6 +223,7 @@ static int powernv_flash_set_driver_info(struct device *dev,
 	mtd->_read = powernv_flash_read;
 	mtd->_write = powernv_flash_write;
 	mtd->dev.parent = dev;
+	mtd_set_of_node(mtd, dev->of_node);
 	return 0;
 }
 
diff --git a/drivers/mtd/devices/sst25l.c b/drivers/mtd/devices/sst25l.c
index 1897f33fe3e7..10d24efb4629 100644
--- a/drivers/mtd/devices/sst25l.c
+++ b/drivers/mtd/devices/sst25l.c
@@ -394,9 +394,8 @@ static int sst25l_probe(struct spi_device *spi)
 	      flash->mtd.numeraseregions);
 
 
-	ret = mtd_device_parse_register(&flash->mtd, NULL, NULL,
-					data ? data->parts : NULL,
-					data ? data->nr_parts : 0);
+	ret = mtd_device_register(&flash->mtd, data ? data->parts : NULL,
+				  data ? data->nr_parts : 0);
 	if (ret)
 		return -ENODEV;
 
diff --git a/drivers/mtd/lpddr/Kconfig b/drivers/mtd/lpddr/Kconfig
index 3a19cbee24d7..a5a332fbd593 100644
--- a/drivers/mtd/lpddr/Kconfig
+++ b/drivers/mtd/lpddr/Kconfig
@@ -13,10 +13,10 @@ config MTD_QINFO_PROBE
 	depends on MTD_LPDDR
 	tristate "Detect flash chips by QINFO probe"
 	help
-	    Device Information for LPDDR chips is offered through the Overlay
-	    Window QINFO interface, permits software to be used for entire
-	    families of devices. This serves similar purpose of CFI on legacy
-	    Flash products
+	  Device Information for LPDDR chips is offered through the Overlay
+	  Window QINFO interface, permits software to be used for entire
+	  families of devices. This serves similar purpose of CFI on legacy
+	  Flash products
 
 config MTD_LPDDR2_NVM
 	# ARM dependency is only for writel_relaxed()
diff --git a/drivers/mtd/lpddr/lpddr2_nvm.c b/drivers/mtd/lpddr/lpddr2_nvm.c
index 5d73db2a496d..c950c880ad59 100644
--- a/drivers/mtd/lpddr/lpddr2_nvm.c
+++ b/drivers/mtd/lpddr/lpddr2_nvm.c
@@ -476,7 +476,7 @@ static int lpddr2_nvm_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 	/* Parse partitions and register the MTD device */
-	return mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+	return mtd_device_register(mtd, NULL, 0);
 }
 
 /*
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index bdc1283f30fb..afb36bff13a7 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -207,13 +207,13 @@ config MTD_ICHXROM
 	  BE VERY CAREFUL.
 
 config MTD_ESB2ROM
-        tristate "BIOS flash chip on Intel ESB Controller Hub 2"
-        depends on X86 && MTD_JEDECPROBE && PCI
-        help
-          Support for treating the BIOS flash chip on ESB2 motherboards
-          as an MTD device - with this you can reprogram your BIOS.
+	tristate "BIOS flash chip on Intel ESB Controller Hub 2"
+	depends on X86 && MTD_JEDECPROBE && PCI
+	help
+	  Support for treating the BIOS flash chip on ESB2 motherboards
+	  as an MTD device - with this you can reprogram your BIOS.
 
-          BE VERY CAREFUL.
+	  BE VERY CAREFUL.
 
 config MTD_CK804XROM
 	tristate "BIOS flash chip on Nvidia CK804"
@@ -401,12 +401,12 @@ config MTD_PISMO
 	  When built as a module, it will be called pismo.ko
 
 config MTD_LATCH_ADDR
-        tristate "Latch-assisted Flash Chip Support"
-        depends on MTD_COMPLEX_MAPPINGS
-        help
-          Map driver which allows flashes to be partially physically addressed
-          and have the upper address lines set by a board specific code.
+	tristate "Latch-assisted Flash Chip Support"
+	depends on MTD_COMPLEX_MAPPINGS
+	help
+	  Map driver which allows flashes to be partially physically addressed
+	  and have the upper address lines set by a board specific code.
 
-          If compiled as a module, it will be called latch-addr-flash.
+	  If compiled as a module, it will be called latch-addr-flash.
 
 endmenu
diff --git a/drivers/mtd/maps/gpio-addr-flash.c b/drivers/mtd/maps/gpio-addr-flash.c
index 385305e66fd1..9d9723693217 100644
--- a/drivers/mtd/maps/gpio-addr-flash.c
+++ b/drivers/mtd/maps/gpio-addr-flash.c
@@ -239,6 +239,9 @@ static int gpio_flash_probe(struct platform_device *pdev)
 	state->map.bankwidth  = pdata->width;
 	state->map.size       = state->win_size * (1 << state->gpio_count);
 	state->map.virt       = ioremap_nocache(memory->start, state->map.size);
+	if (!state->map.virt)
+		return -ENOMEM;
+
 	state->map.phys       = NO_XIP;
 	state->map.map_priv_1 = (unsigned long)state;
 
diff --git a/drivers/mtd/maps/impa7.c b/drivers/mtd/maps/impa7.c
index a0b8fa7849a9..815e2db87955 100644
--- a/drivers/mtd/maps/impa7.c
+++ b/drivers/mtd/maps/impa7.c
@@ -88,9 +88,8 @@ static int __init init_impa7(void)
 		if (impa7_mtd[i]) {
 			impa7_mtd[i]->owner = THIS_MODULE;
 			devicesfound++;
-			mtd_device_parse_register(impa7_mtd[i], NULL, NULL,
-						  partitions,
-						  ARRAY_SIZE(partitions));
+			mtd_device_register(impa7_mtd[i], partitions,
+					    ARRAY_SIZE(partitions));
 		} else {
 			iounmap((void __iomem *)impa7_map[i].virt);
 		}
diff --git a/drivers/mtd/maps/intel_vr_nor.c b/drivers/mtd/maps/intel_vr_nor.c
index dd5d6855f543..69503aef981e 100644
--- a/drivers/mtd/maps/intel_vr_nor.c
+++ b/drivers/mtd/maps/intel_vr_nor.c
@@ -71,7 +71,7 @@ static int vr_nor_init_partitions(struct vr_nor_mtd *p)
 {
 	/* register the flash bank */
 	/* partition the flash bank */
-	return mtd_device_parse_register(p->info, NULL, NULL, NULL, 0);
+	return mtd_device_register(p->info, NULL, 0);
 }
 
 static void vr_nor_destroy_mtd_setup(struct vr_nor_mtd *p)
diff --git a/drivers/mtd/maps/latch-addr-flash.c b/drivers/mtd/maps/latch-addr-flash.c
index 6dc97aa667dc..51db24b7f88d 100644
--- a/drivers/mtd/maps/latch-addr-flash.c
+++ b/drivers/mtd/maps/latch-addr-flash.c
@@ -197,9 +197,8 @@ static int latch_addr_flash_probe(struct platform_device *dev)
 	}
 	info->mtd->dev.parent = &dev->dev;
 
-	mtd_device_parse_register(info->mtd, NULL, NULL,
-				  latch_addr_data->parts,
-				  latch_addr_data->nr_parts);
+	mtd_device_register(info->mtd, latch_addr_data->parts,
+			    latch_addr_data->nr_parts);
 	return 0;
 
 iounmap:
diff --git a/drivers/mtd/maps/rbtx4939-flash.c b/drivers/mtd/maps/rbtx4939-flash.c
index 3a06ecfc55ff..80a187167c92 100644
--- a/drivers/mtd/maps/rbtx4939-flash.c
+++ b/drivers/mtd/maps/rbtx4939-flash.c
@@ -97,8 +97,7 @@ static int rbtx4939_flash_probe(struct platform_device *dev)
 		goto err_out;
 	}
 	info->mtd->dev.parent = &dev->dev;
-	err = mtd_device_parse_register(info->mtd, NULL, NULL, pdata->parts,
-					pdata->nr_parts);
+	err = mtd_device_register(info->mtd, pdata->parts, pdata->nr_parts);
 
 	if (err)
 		goto err_out;
diff --git a/drivers/mtd/maps/solutionengine.c b/drivers/mtd/maps/solutionengine.c
index bb580bc16445..c07f21b20463 100644
--- a/drivers/mtd/maps/solutionengine.c
+++ b/drivers/mtd/maps/solutionengine.c
@@ -59,9 +59,9 @@ static int __init init_soleng_maps(void)
 			return -ENXIO;
 		}
 	}
-	printk(KERN_NOTICE "Solution Engine: Flash at 0x%08lx, EPROM at 0x%08lx\n",
-	       soleng_flash_map.phys & 0x1fffffff,
-	       soleng_eprom_map.phys & 0x1fffffff);
+	printk(KERN_NOTICE "Solution Engine: Flash at 0x%pap, EPROM at 0x%pap\n",
+	       &soleng_flash_map.phys,
+	       &soleng_eprom_map.phys);
 	flash_mtd->owner = THIS_MODULE;
 
 	eprom_mtd = do_map_probe("map_rom", &soleng_eprom_map);
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index cd67c85cc87d..02389528f622 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -160,8 +160,12 @@ static ssize_t mtdchar_read(struct file *file, char __user *buf, size_t count,
 
 	pr_debug("MTD_read\n");
 
-	if (*ppos + count > mtd->size)
-		count = mtd->size - *ppos;
+	if (*ppos + count > mtd->size) {
+		if (*ppos < mtd->size)
+			count = mtd->size - *ppos;
+		else
+			count = 0;
+	}
 
 	if (!count)
 		return 0;
@@ -246,7 +250,7 @@ static ssize_t mtdchar_write(struct file *file, const char __user *buf, size_t c
 
 	pr_debug("MTD_write\n");
 
-	if (*ppos == mtd->size)
+	if (*ppos >= mtd->size)
 		return -ENOSPC;
 
 	if (*ppos + count > mtd->size)
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 42395df06be9..97ac219c082e 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1155,21 +1155,29 @@ int mtd_read_oob(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops)
 {
 	int ret_code;
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->_read_oob)
-		return -EOPNOTSUPP;
 
 	ret_code = mtd_check_oob_ops(mtd, from, ops);
 	if (ret_code)
 		return ret_code;
 
 	ledtrig_mtd_activity();
+
+	/* Check the validity of a potential fallback on mtd->_read */
+	if (!mtd->_read_oob && (!mtd->_read || ops->oobbuf))
+		return -EOPNOTSUPP;
+
+	if (mtd->_read_oob)
+		ret_code = mtd->_read_oob(mtd, from, ops);
+	else
+		ret_code = mtd->_read(mtd, from, ops->len, &ops->retlen,
+				      ops->datbuf);
+
 	/*
 	 * In cases where ops->datbuf != NULL, mtd->_read_oob() has semantics
 	 * similar to mtd->_read(), returning a non-negative integer
 	 * representing max bitflips. In other cases, mtd->_read_oob() may
 	 * return -EUCLEAN. In all cases, perform similar logic to mtd_read().
 	 */
-	ret_code = mtd->_read_oob(mtd, from, ops);
 	if (unlikely(ret_code < 0))
 		return ret_code;
 	if (mtd->ecc_strength == 0)
@@ -1184,8 +1192,7 @@ int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 	int ret;
 
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->_write_oob)
-		return -EOPNOTSUPP;
+
 	if (!(mtd->flags & MTD_WRITEABLE))
 		return -EROFS;
 
@@ -1194,7 +1201,16 @@ int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 		return ret;
 
 	ledtrig_mtd_activity();
-	return mtd->_write_oob(mtd, to, ops);
+
+	/* Check the validity of a potential fallback on mtd->_write */
+	if (!mtd->_write_oob && (!mtd->_write || ops->oobbuf))
+		return -EOPNOTSUPP;
+
+	if (mtd->_write_oob)
+		return mtd->_write_oob(mtd, to, ops);
+	else
+		return mtd->_write(mtd, to, ops->len, &ops->retlen,
+				   ops->datbuf);
 }
 EXPORT_SYMBOL_GPL(mtd_write_oob);
 
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index f8d3a015cdad..52e2cb35fc79 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -322,22 +322,6 @@ static inline void free_partition(struct mtd_part *p)
 	kfree(p);
 }
 
-/**
- * mtd_parse_part - parse MTD partition looking for subpartitions
- *
- * @slave: part that is supposed to be a container and should be parsed
- * @types: NULL-terminated array with names of partition parsers to try
- *
- * Some partitions are kind of containers with extra subpartitions (volumes).
- * There can be various formats of such containers. This function tries to use
- * specified parsers to analyze given partition and registers found
- * subpartitions on success.
- */
-static int mtd_parse_part(struct mtd_part *slave, const char *const *types)
-{
-	return parse_mtd_partitions(&slave->mtd, types, NULL);
-}
-
 static struct mtd_part *allocate_partition(struct mtd_info *parent,
 			const struct mtd_partition *part, int partno,
 			uint64_t cur_offset)
@@ -735,8 +719,8 @@ int add_mtd_partitions(struct mtd_info *master,
 
 		add_mtd_device(&slave->mtd);
 		mtd_add_partition_attrs(slave);
-		if (parts[i].types)
-			mtd_parse_part(slave, parts[i].types);
+		/* Look for subpartitions */
+		parse_mtd_partitions(&slave->mtd, parts[i].types, NULL);
 
 		cur_offset = slave->offset + slave->mtd.size;
 	}
@@ -812,6 +796,12 @@ static const char * const default_mtd_part_types[] = {
 	NULL
 };
 
+/* Check DT only when looking for subpartitions. */
+static const char * const default_subpartition_types[] = {
+	"ofpart",
+	NULL
+};
+
 static int mtd_part_do_parse(struct mtd_part_parser *parser,
 			     struct mtd_info *master,
 			     struct mtd_partitions *pparts,
@@ -882,7 +872,9 @@ static int mtd_part_of_parse(struct mtd_info *master,
 	const char *fixed = "fixed-partitions";
 	int ret, err = 0;
 
-	np = of_get_child_by_name(mtd_get_of_node(master), "partitions");
+	np = mtd_get_of_node(master);
+	if (!mtd_is_partition(master))
+		np = of_get_child_by_name(np, "partitions");
 	of_property_for_each_string(np, "compatible", prop, compat) {
 		parser = mtd_part_get_compatible_parser(compat);
 		if (!parser)
@@ -945,7 +937,8 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types,
 	int ret, err = 0;
 
 	if (!types)
-		types = default_mtd_part_types;
+		types = mtd_is_partition(master) ? default_subpartition_types :
+			default_mtd_part_types;
 
 	for ( ; *types; types++) {
 		/*
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 88c7d3b4ff8b..9033215e62ea 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -4,3 +4,4 @@ config MTD_NAND_CORE
 source "drivers/mtd/nand/onenand/Kconfig"
 
 source "drivers/mtd/nand/raw/Kconfig"
+source "drivers/mtd/nand/spi/Kconfig"
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 3f0cb87f1a57..7ecd80c0a66e 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -5,3 +5,4 @@ obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o
 
 obj-y	+= onenand/
 obj-y	+= raw/
+obj-y	+= spi/
diff --git a/drivers/mtd/nand/onenand/generic.c b/drivers/mtd/nand/onenand/generic.c
index d5ccaf943b91..acad17ec6581 100644
--- a/drivers/mtd/nand/onenand/generic.c
+++ b/drivers/mtd/nand/onenand/generic.c
@@ -66,9 +66,8 @@ static int generic_onenand_probe(struct platform_device *pdev)
 		goto out_iounmap;
 	}
 
-	err = mtd_device_parse_register(&info->mtd, NULL, NULL,
-					pdata ? pdata->parts : NULL,
-					pdata ? pdata->nr_parts : 0);
+	err = mtd_device_register(&info->mtd, pdata ? pdata->parts : NULL,
+				  pdata ? pdata->nr_parts : 0);
 
 	platform_set_drvdata(pdev, info);
 
diff --git a/drivers/mtd/nand/onenand/samsung.c b/drivers/mtd/nand/onenand/samsung.c
index 4cce4c0311ca..e64d0fdf7eb5 100644
--- a/drivers/mtd/nand/onenand/samsung.c
+++ b/drivers/mtd/nand/onenand/samsung.c
@@ -933,9 +933,8 @@ static int s3c_onenand_probe(struct platform_device *pdev)
 	if (s3c_read_reg(MEM_CFG_OFFSET) & ONENAND_SYS_CFG1_SYNC_READ)
 		dev_info(&onenand->pdev->dev, "OneNAND Sync. Burst Read enabled\n");
 
-	err = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata ? pdata->parts : NULL,
-					pdata ? pdata->nr_parts : 0);
+	err = mtd_device_register(mtd, pdata ? pdata->parts : NULL,
+				  pdata ? pdata->nr_parts : 0);
 	if (err) {
 		dev_err(&pdev->dev, "failed to parse partitions and register the MTD device\n");
 		onenand_release(mtd);
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 6871ff0fd300..5fc9a1bde4ac 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -44,12 +44,12 @@ config MTD_NAND_DENALI
 	tristate
 
 config MTD_NAND_DENALI_PCI
-        tristate "Support Denali NAND controller on Intel Moorestown"
+	tristate "Support Denali NAND controller on Intel Moorestown"
 	select MTD_NAND_DENALI
 	depends on PCI
-        help
-          Enable the driver for NAND flash on Intel Moorestown, using the
-          Denali NAND controller core.
+	help
+	  Enable the driver for NAND flash on Intel Moorestown, using the
+	  Denali NAND controller core.
 
 config MTD_NAND_DENALI_DT
 	tristate "Support Denali NAND controller as a DT device"
@@ -77,9 +77,10 @@ config MTD_NAND_AMS_DELTA
 
 config MTD_NAND_OMAP2
 	tristate "NAND Flash device on OMAP2, OMAP3, OMAP4 and Keystone"
-	depends on (ARCH_OMAP2PLUS || ARCH_KEYSTONE)
+	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
-          Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4
+	  Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4
 	  and Keystone platforms.
 
 config MTD_NAND_OMAP_BCH
@@ -137,7 +138,7 @@ config MTD_NAND_NDFC
 	depends on 4xx
 	select MTD_NAND_ECC_SMC
 	help
-	 NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs
+	  NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs
 
 config MTD_NAND_S3C2410_CLKSTOP
 	bool "Samsung S3C NAND IDLE clock stop"
@@ -152,6 +153,7 @@ config MTD_NAND_S3C2410_CLKSTOP
 config MTD_NAND_TANGO
 	tristate "NAND Flash support for Tango chips"
 	depends on ARCH_TANGO || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables the NAND Flash controller on Tango chips.
 
@@ -168,40 +170,40 @@ config MTD_NAND_DISKONCHIP
 	  these devices.
 
 config MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        bool "Advanced detection options for DiskOnChip"
-        depends on MTD_NAND_DISKONCHIP
-        help
-          This option allows you to specify nonstandard address at which to
-          probe for a DiskOnChip, or to change the detection options.  You
-          are unlikely to need any of this unless you are using LinuxBIOS.
-          Say 'N'.
+	bool "Advanced detection options for DiskOnChip"
+	depends on MTD_NAND_DISKONCHIP
+	help
+	  This option allows you to specify nonstandard address at which to
+	  probe for a DiskOnChip, or to change the detection options.  You
+	  are unlikely to need any of this unless you are using LinuxBIOS.
+	  Say 'N'.
 
 config MTD_NAND_DISKONCHIP_PROBE_ADDRESS
-        hex "Physical address of DiskOnChip" if MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        depends on MTD_NAND_DISKONCHIP
-        default "0"
-        ---help---
-        By default, the probe for DiskOnChip devices will look for a
-        DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
-        This option allows you to specify a single address at which to probe
-        for the device, which is useful if you have other devices in that
-        range which get upset when they are probed.
-
-        (Note that on PowerPC, the normal probe will only check at
-        0xE4000000.)
-
-        Normally, you should leave this set to zero, to allow the probe at
-        the normal addresses.
+	hex "Physical address of DiskOnChip" if MTD_NAND_DISKONCHIP_PROBE_ADVANCED
+	depends on MTD_NAND_DISKONCHIP
+	default "0"
+	help
+	  By default, the probe for DiskOnChip devices will look for a
+	  DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
+	  This option allows you to specify a single address at which to probe
+	  for the device, which is useful if you have other devices in that
+	  range which get upset when they are probed.
+
+	  (Note that on PowerPC, the normal probe will only check at
+	  0xE4000000.)
+
+	  Normally, you should leave this set to zero, to allow the probe at
+	  the normal addresses.
 
 config MTD_NAND_DISKONCHIP_PROBE_HIGH
-        bool "Probe high addresses"
-        depends on MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        help
-          By default, the probe for DiskOnChip devices will look for a
-          DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
-          This option changes to make it probe between 0xFFFC8000 and
-          0xFFFEE000.  Unless you are using LinuxBIOS, this is unlikely to be
-          useful to you.  Say 'N'.
+	bool "Probe high addresses"
+	depends on MTD_NAND_DISKONCHIP_PROBE_ADVANCED
+	help
+	  By default, the probe for DiskOnChip devices will look for a
+	  DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
+	  This option changes to make it probe between 0xFFFC8000 and
+	  0xFFFEE000.  Unless you are using LinuxBIOS, this is unlikely to be
+	  useful to you.  Say 'N'.
 
 config MTD_NAND_DISKONCHIP_BBTWRITE
 	bool "Allow BBT writes on DiskOnChip Millennium and 2000TSOP"
@@ -247,7 +249,8 @@ config MTD_NAND_DOCG4
 
 config MTD_NAND_SHARPSL
 	tristate "Support for NAND Flash on Sharp SL Series (C7xx + others)"
-	depends on ARCH_PXA
+	depends on ARCH_PXA || COMPILE_TEST
+	depends on HAS_IOMEM
 
 config MTD_NAND_CAFE
 	tristate "NAND support for OLPC CAFÉ chip"
@@ -274,7 +277,9 @@ config MTD_NAND_CS553X
 
 config MTD_NAND_ATMEL
 	tristate "Support for NAND Flash / SmartMedia on AT91"
-	depends on ARCH_AT91
+	depends on ARCH_AT91 || COMPILE_TEST
+	depends on HAS_IOMEM
+	select GENERIC_ALLOCATOR
 	select MFD_ATMEL_SMC
 	help
 	  Enables support for NAND Flash / Smart Media Card interface
@@ -294,7 +299,8 @@ config MTD_NAND_MARVELL
 
 config MTD_NAND_SLC_LPC32XX
 	tristate "NXP LPC32xx SLC Controller"
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NXP's LPC32XX SLC (i.e. for Single Level Cell
 	  chips) NAND controller. This is the default for the PHYTEC 3250
@@ -305,7 +311,8 @@ config MTD_NAND_SLC_LPC32XX
 
 config MTD_NAND_MLC_LPC32XX
 	tristate "NXP LPC32xx MLC Controller"
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Uses the LPC32XX MLC (i.e. for Multi Level Cell chips) NAND
 	  controller. This is the default for the WORK92105 controller
@@ -339,17 +346,18 @@ config MTD_NAND_NANDSIM
 	  MTD nand layer.
 
 config MTD_NAND_GPMI_NAND
-        tristate "GPMI NAND Flash Controller driver"
-        depends on MTD_NAND && MXS_DMA
-        help
-	 Enables NAND Flash support for IMX23, IMX28 or IMX6.
-	 The GPMI controller is very powerful, with the help of BCH
-	 module, it can do the hardware ECC. The GPMI supports several
-	 NAND flashs at the same time.
+	tristate "GPMI NAND Flash Controller driver"
+	depends on MXS_DMA
+	help
+	  Enables NAND Flash support for IMX23, IMX28 or IMX6.
+	  The GPMI controller is very powerful, with the help of BCH
+	  module, it can do the hardware ECC. The GPMI supports several
+	  NAND flashs at the same time.
 
 config MTD_NAND_BRCMNAND
 	tristate "Broadcom STB NAND controller"
-	depends on ARM || ARM64 || MIPS
+	depends on ARM || ARM64 || MIPS || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables the Broadcom NAND controller driver. The controller was
 	  originally designed for Set-Top Box but is used on various BCM7xxx,
@@ -358,6 +366,7 @@ config MTD_NAND_BRCMNAND
 config MTD_NAND_BCM47XXNFLASH
 	tristate "Support for NAND flash on BCM4706 BCMA bus"
 	depends on BCMA_NFLASH
+	depends on BCMA
 	help
 	  BCMA bus can have various flash memories attached, they are
 	  registered by bcma as platform devices. This enables driver for
@@ -399,7 +408,8 @@ config MTD_NAND_FSL_ELBC
 
 config MTD_NAND_FSL_IFC
 	tristate "NAND support for Freescale IFC controller"
-	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
+	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+	depends on HAS_IOMEM
 	select FSL_IFC
 	select MEMORY
 	help
@@ -437,7 +447,8 @@ config MTD_NAND_VF610_NFC
 
 config MTD_NAND_MXC
 	tristate "MXC NAND support"
-	depends on ARCH_MXC
+	depends on ARCH_MXC || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the driver for the NAND flash controller on the
 	  MXC processors.
@@ -451,15 +462,17 @@ config MTD_NAND_SH_FLCTL
 	  for NAND Flash using FLCTL.
 
 config MTD_NAND_DAVINCI
-        tristate "Support NAND on DaVinci/Keystone SoC"
-        depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF)
-        help
+	tristate "Support NAND on DaVinci/Keystone SoC"
+	depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF) || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
 	  Enable the driver for NAND flash chips on Texas Instruments
 	  DaVinci/Keystone processors.
 
 config MTD_NAND_TXX9NDFMC
 	tristate "NAND Flash support for TXx9 SoC"
-	depends on SOC_TX4938 || SOC_TX4939
+	depends on SOC_TX4938 || SOC_TX4939 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the NAND flash controller on the TXx9 SoCs.
 
@@ -471,28 +484,31 @@ config MTD_NAND_SOCRATES
 
 config MTD_NAND_NUC900
 	tristate "Support for NAND on Nuvoton NUC9xx/w90p910 evaluation boards."
-	depends on ARCH_W90X900
+	depends on ARCH_W90X900 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the driver for the NAND Flash on evaluation board based
 	  on w90p910 / NUC9xx.
 
 config MTD_NAND_JZ4740
 	tristate "Support for JZ4740 SoC NAND controller"
-	depends on MACH_JZ4740
+	depends on MACH_JZ4740 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
-		Enables support for NAND Flash on JZ4740 SoC based boards.
+	  Enables support for NAND Flash on JZ4740 SoC based boards.
 
 config MTD_NAND_JZ4780
 	tristate "Support for NAND on JZ4780 SoC"
-	depends on MACH_JZ4780 && JZ4780_NEMC
+	depends on JZ4780_NEMC
 	help
 	  Enables support for NAND Flash connected to the NEMC on JZ4780 SoC
 	  based boards, using the BCH controller for hardware error correction.
 
 config MTD_NAND_FSMC
 	tristate "Support for NAND on ST Micros FSMC"
-	depends on OF
-	depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300
+	depends on OF && HAS_IOMEM
+	depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300 || \
+		   COMPILE_TEST
 	help
 	  Enables support for NAND Flash chips on the ST Microelectronics
 	  Flexible Static Memory Controller (FSMC)
@@ -506,19 +522,22 @@ config MTD_NAND_XWAY
 
 config MTD_NAND_SUNXI
 	tristate "Support for NAND on Allwinner SoCs"
-	depends on ARCH_SUNXI
+	depends on ARCH_SUNXI || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND Flash chips on Allwinner SoCs.
 
 config MTD_NAND_HISI504
 	tristate "Support for NAND controller on Hisilicon SoC Hip04"
 	depends on ARCH_HISI || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND controller on Hisilicon SoC Hip04.
 
 config MTD_NAND_QCOM
 	tristate "Support for NAND on QCOM SoCs"
-	depends on ARCH_QCOM
+	depends on ARCH_QCOM || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND flash chips on SoCs containing the EBI2 NAND
 	  controller. This controller is found on IPQ806x SoC.
@@ -526,8 +545,20 @@ config MTD_NAND_QCOM
 config MTD_NAND_MTK
 	tristate "Support for NAND controller on MTK SoCs"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND controller on MTK SoCs.
 	  This controller is found on mt27xx, mt81xx, mt65xx SoCs.
 
+config MTD_NAND_TEGRA
+	tristate "Support for NAND controller on NVIDIA Tegra"
+	depends on ARCH_TEGRA || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
+	  Enables support for NAND flash controller on NVIDIA Tegra SoC.
+	  The driver has been developed and tested on a Tegra 2 SoC. DMA
+	  support, raw read/write page as well as HW ECC read/write page
+	  is supported. Extra OOB bytes when using HW ECC are currently
+	  not supported.
+
 endif # MTD_NAND
diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile
index 165b7ef9e9a1..d5a5f9832b88 100644
--- a/drivers/mtd/nand/raw/Makefile
+++ b/drivers/mtd/nand/raw/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_MTD_NAND_HISI504)	        += hisi504_nand.o
 obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= brcmnand/
 obj-$(CONFIG_MTD_NAND_QCOM)		+= qcom_nandc.o
 obj-$(CONFIG_MTD_NAND_MTK)		+= mtk_ecc.o mtk_nand.o
+obj-$(CONFIG_MTD_NAND_TEGRA)		+= tegra_nand.o
 
 nand-objs := nand_base.o nand_bbt.o nand_timings.o nand_ids.o
 nand-objs += nand_amd.o
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 12f6753d47ae..a068b214ebaa 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -52,7 +52,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/genalloc.h>
-#include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/mfd/syscon.h>
@@ -129,6 +128,11 @@
 #define DEFAULT_TIMEOUT_MS			1000
 #define MIN_DMA_LEN				128
 
+static bool atmel_nand_avoid_dma __read_mostly;
+
+MODULE_PARM_DESC(avoiddma, "Avoid using DMA");
+module_param_named(avoiddma, atmel_nand_avoid_dma, bool, 0400);
+
 enum atmel_nand_rb_type {
 	ATMEL_NAND_NO_RB,
 	ATMEL_NAND_NATIVE_RB,
@@ -197,7 +201,7 @@ struct atmel_nand_controller_ops {
 	int (*remove)(struct atmel_nand_controller *nc);
 	void (*nand_init)(struct atmel_nand_controller *nc,
 			  struct atmel_nand *nand);
-	int (*ecc_init)(struct atmel_nand *nand);
+	int (*ecc_init)(struct nand_chip *chip);
 	int (*setup_data_interface)(struct atmel_nand *nand, int csline,
 				    const struct nand_data_interface *conf);
 };
@@ -211,7 +215,7 @@ struct atmel_nand_controller_caps {
 };
 
 struct atmel_nand_controller {
-	struct nand_hw_control base;
+	struct nand_controller base;
 	const struct atmel_nand_controller_caps *caps;
 	struct device *dev;
 	struct regmap *smc;
@@ -222,7 +226,7 @@ struct atmel_nand_controller {
 };
 
 static inline struct atmel_nand_controller *
-to_nand_controller(struct nand_hw_control *ctl)
+to_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(ctl, struct atmel_nand_controller, base);
 }
@@ -234,7 +238,7 @@ struct atmel_smc_nand_controller {
 };
 
 static inline struct atmel_smc_nand_controller *
-to_smc_nand_controller(struct nand_hw_control *ctl)
+to_smc_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(to_nand_controller(ctl),
 			    struct atmel_smc_nand_controller, base);
@@ -258,7 +262,7 @@ struct atmel_hsmc_nand_controller {
 };
 
 static inline struct atmel_hsmc_nand_controller *
-to_hsmc_nand_controller(struct nand_hw_control *ctl)
+to_hsmc_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(to_nand_controller(ctl),
 			    struct atmel_hsmc_nand_controller, base);
@@ -1128,9 +1132,8 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 	return 0;
 }
 
-static int atmel_nand_ecc_init(struct atmel_nand *nand)
+static int atmel_nand_ecc_init(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->base;
 	struct atmel_nand_controller *nc;
 	int ret;
 
@@ -1165,12 +1168,11 @@ static int atmel_nand_ecc_init(struct atmel_nand *nand)
 	return 0;
 }
 
-static int atmel_hsmc_nand_ecc_init(struct atmel_nand *nand)
+static int atmel_hsmc_nand_ecc_init(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->base;
 	int ret;
 
-	ret = atmel_nand_ecc_init(nand);
+	ret = atmel_nand_ecc_init(chip);
 	if (ret)
 		return ret;
 
@@ -1553,23 +1555,7 @@ static void atmel_hsmc_nand_init(struct atmel_nand_controller *nc,
 	chip->select_chip = atmel_hsmc_nand_select_chip;
 }
 
-static int atmel_nand_detect(struct atmel_nand *nand)
-{
-	struct nand_chip *chip = &nand->base;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	struct atmel_nand_controller *nc;
-	int ret;
-
-	nc = to_nand_controller(chip->controller);
-
-	ret = nand_scan_ident(mtd, nand->numcs, NULL);
-	if (ret)
-		dev_err(nc->dev, "nand_scan_ident() failed: %d\n", ret);
-
-	return ret;
-}
-
-static int atmel_nand_unregister(struct atmel_nand *nand)
+static int atmel_nand_controller_remove_nand(struct atmel_nand *nand)
 {
 	struct nand_chip *chip = &nand->base;
 	struct mtd_info *mtd = nand_to_mtd(chip);
@@ -1585,60 +1571,6 @@ static int atmel_nand_unregister(struct atmel_nand *nand)
 	return 0;
 }
 
-static int atmel_nand_register(struct atmel_nand *nand)
-{
-	struct nand_chip *chip = &nand->base;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	struct atmel_nand_controller *nc;
-	int ret;
-
-	nc = to_nand_controller(chip->controller);
-
-	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
-		/*
-		 * We keep the MTD name unchanged to avoid breaking platforms
-		 * where the MTD cmdline parser is used and the bootloader
-		 * has not been updated to use the new naming scheme.
-		 */
-		mtd->name = "atmel_nand";
-	} else if (!mtd->name) {
-		/*
-		 * If the new bindings are used and the bootloader has not been
-		 * updated to pass a new mtdparts parameter on the cmdline, you
-		 * should define the following property in your nand node:
-		 *
-		 *	label = "atmel_nand";
-		 *
-		 * This way, mtd->name will be set by the core when
-		 * nand_set_flash_node() is called.
-		 */
-		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
-					   "%s:nand.%d", dev_name(nc->dev),
-					   nand->cs[0].id);
-		if (!mtd->name) {
-			dev_err(nc->dev, "Failed to allocate mtd->name\n");
-			return -ENOMEM;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(nc->dev, "nand_scan_tail() failed: %d\n", ret);
-		return ret;
-	}
-
-	ret = mtd_device_register(mtd, NULL, 0);
-	if (ret) {
-		dev_err(nc->dev, "Failed to register mtd device: %d\n", ret);
-		nand_cleanup(chip);
-		return ret;
-	}
-
-	list_add_tail(&nand->node, &nc->chips);
-
-	return 0;
-}
-
 static struct atmel_nand *atmel_nand_create(struct atmel_nand_controller *nc,
 					    struct device_node *np,
 					    int reg_cells)
@@ -1750,6 +1682,8 @@ static int
 atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
 			       struct atmel_nand *nand)
 {
+	struct nand_chip *chip = &nand->base;
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
 
 	/* No card inserted, skip this NAND. */
@@ -1760,15 +1694,22 @@ atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
 
 	nc->caps->ops->nand_init(nc, nand);
 
-	ret = atmel_nand_detect(nand);
-	if (ret)
+	ret = nand_scan(mtd, nand->numcs);
+	if (ret) {
+		dev_err(nc->dev, "NAND scan failed: %d\n", ret);
 		return ret;
+	}
 
-	ret = nc->caps->ops->ecc_init(nand);
-	if (ret)
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(nc->dev, "Failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
 		return ret;
+	}
+
+	list_add_tail(&nand->node, &nc->chips);
 
-	return atmel_nand_register(nand);
+	return 0;
 }
 
 static int
@@ -1778,7 +1719,7 @@ atmel_nand_controller_remove_nands(struct atmel_nand_controller *nc)
 	int ret;
 
 	list_for_each_entry_safe(nand, tmp, &nc->chips, node) {
-		ret = atmel_nand_unregister(nand);
+		ret = atmel_nand_controller_remove_nand(nand);
 		if (ret)
 			return ret;
 	}
@@ -1953,6 +1894,51 @@ static const struct of_device_id atmel_matrix_of_ids[] = {
 	{ /* sentinel */ },
 };
 
+static int atmel_nand_attach_chip(struct nand_chip *chip)
+{
+	struct atmel_nand_controller *nc = to_nand_controller(chip->controller);
+	struct atmel_nand *nand = to_atmel_nand(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ret;
+
+	ret = nc->caps->ops->ecc_init(chip);
+	if (ret)
+		return ret;
+
+	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
+		/*
+		 * We keep the MTD name unchanged to avoid breaking platforms
+		 * where the MTD cmdline parser is used and the bootloader
+		 * has not been updated to use the new naming scheme.
+		 */
+		mtd->name = "atmel_nand";
+	} else if (!mtd->name) {
+		/*
+		 * If the new bindings are used and the bootloader has not been
+		 * updated to pass a new mtdparts parameter on the cmdline, you
+		 * should define the following property in your nand node:
+		 *
+		 *	label = "atmel_nand";
+		 *
+		 * This way, mtd->name will be set by the core when
+		 * nand_set_flash_node() is called.
+		 */
+		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
+					   "%s:nand.%d", dev_name(nc->dev),
+					   nand->cs[0].id);
+		if (!mtd->name) {
+			dev_err(nc->dev, "Failed to allocate mtd->name\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops atmel_nand_controller_ops = {
+	.attach_chip = atmel_nand_attach_chip,
+};
+
 static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 				struct platform_device *pdev,
 				const struct atmel_nand_controller_caps *caps)
@@ -1961,7 +1947,8 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 	struct device_node *np = dev->of_node;
 	int ret;
 
-	nand_hw_control_init(&nc->base);
+	nand_controller_init(&nc->base);
+	nc->base.ops = &atmel_nand_controller_ops;
 	INIT_LIST_HEAD(&nc->chips);
 	nc->dev = dev;
 	nc->caps = caps;
@@ -1977,7 +1964,7 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 		return ret;
 	}
 
-	if (nc->caps->has_dma) {
+	if (nc->caps->has_dma && !atmel_nand_avoid_dma) {
 		dma_cap_mask_t mask;
 
 		dma_cap_zero(mask);
@@ -2045,7 +2032,7 @@ atmel_smc_nand_controller_init(struct atmel_smc_nand_controller *nc)
 		return ret;
 	}
 
-	nc->ebi_csa_offs = (unsigned int)match->data;
+	nc->ebi_csa_offs = (uintptr_t)match->data;
 
 	/*
 	 * The at91sam9263 has 2 EBIs, if the NAND controller is under EBI1
@@ -2214,9 +2201,9 @@ atmel_hsmc_nand_controller_init(struct atmel_hsmc_nand_controller *nc)
 		return -ENOMEM;
 	}
 
-	nc->sram.virt = gen_pool_dma_alloc(nc->sram.pool,
-					    ATMEL_NFC_SRAM_SIZE,
-					    &nc->sram.dma);
+	nc->sram.virt = (void __iomem *)gen_pool_dma_alloc(nc->sram.pool,
+							   ATMEL_NFC_SRAM_SIZE,
+							   &nc->sram.dma);
 	if (!nc->sram.virt) {
 		dev_err(nc->base.dev,
 			"Could not allocate memory from the NFC SRAM pool\n");
diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c
index df0ef1f1e2f5..35f5c84cd331 100644
--- a/drivers/mtd/nand/raw/au1550nd.c
+++ b/drivers/mtd/nand/raw/au1550nd.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/slab.h>
-#include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/mtd/mtd.h>
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 1306aaa7a8bf..4b90d5b380c2 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -114,7 +114,7 @@ enum {
 
 struct brcmnand_controller {
 	struct device		*dev;
-	struct nand_hw_control	controller;
+	struct nand_controller	controller;
 	void __iomem		*nand_base;
 	void __iomem		*nand_fc; /* flash cache */
 	void __iomem		*flash_dma_base;
@@ -2208,6 +2208,40 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 	return 0;
 }
 
+static int brcmnand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct brcmnand_host *host = nand_get_controller_data(chip);
+	int ret;
+
+	chip->options |= NAND_NO_SUBPAGE_WRITE;
+	/*
+	 * Avoid (for instance) kmap()'d buffers from JFFS2, which we can't DMA
+	 * to/from, and have nand_base pass us a bounce buffer instead, as
+	 * needed.
+	 */
+	chip->options |= NAND_USE_BOUNCE_BUFFER;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	if (brcmnand_setup_dev(host))
+		return -ENXIO;
+
+	chip->ecc.size = host->hwcfg.sector_size_1k ? 1024 : 512;
+
+	/* only use our internal HW threshold */
+	mtd->bitflip_threshold = 1;
+
+	ret = brcmstb_choose_ecc_layout(host);
+
+	return ret;
+}
+
+static const struct nand_controller_ops brcmnand_controller_ops = {
+	.attach_chip = brcmnand_attach_chip,
+};
+
 static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 {
 	struct brcmnand_controller *ctrl = host->ctrl;
@@ -2267,33 +2301,7 @@ static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 	nand_writereg(ctrl, cfg_offs,
 		      nand_readreg(ctrl, cfg_offs) & ~CFG_BUS_WIDTH);
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	chip->options |= NAND_NO_SUBPAGE_WRITE;
-	/*
-	 * Avoid (for instance) kmap()'d buffers from JFFS2, which we can't DMA
-	 * to/from, and have nand_base pass us a bounce buffer instead, as
-	 * needed.
-	 */
-	chip->options |= NAND_USE_BOUNCE_BUFFER;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH)
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-	if (brcmnand_setup_dev(host))
-		return -ENXIO;
-
-	chip->ecc.size = host->hwcfg.sector_size_1k ? 1024 : 512;
-	/* only use our internal HW threshold */
-	mtd->bitflip_threshold = 1;
-
-	ret = brcmstb_choose_ecc_layout(host);
-	if (ret)
-		return ret;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
@@ -2433,7 +2441,8 @@ int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc)
 
 	init_completion(&ctrl->done);
 	init_completion(&ctrl->dma_done);
-	nand_hw_control_init(&ctrl->controller);
+	nand_controller_init(&ctrl->controller);
+	ctrl->controller.ops = &brcmnand_controller_ops;
 	INIT_LIST_HEAD(&ctrl->host_list);
 
 	/* NAND register range */
diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index d721f489b38b..1dbe43adcfe7 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -67,6 +67,7 @@ struct cafe_priv {
 	int nr_data;
 	int data_pos;
 	int page_addr;
+	bool usedma;
 	dma_addr_t dmaaddr;
 	unsigned char *dmabuf;
 };
@@ -121,7 +122,7 @@ static void cafe_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct cafe_priv *cafe = nand_get_controller_data(chip);
 
-	if (usedma)
+	if (cafe->usedma)
 		memcpy(cafe->dmabuf + cafe->datalen, buf, len);
 	else
 		memcpy_toio(cafe->mmio + CAFE_NAND_WRITE_DATA + cafe->datalen, buf, len);
@@ -137,7 +138,7 @@ static void cafe_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct cafe_priv *cafe = nand_get_controller_data(chip);
 
-	if (usedma)
+	if (cafe->usedma)
 		memcpy(buf, cafe->dmabuf + cafe->datalen, len);
 	else
 		memcpy_fromio(buf, cafe->mmio + CAFE_NAND_READ_DATA + cafe->datalen, len);
@@ -253,7 +254,7 @@ static void cafe_nand_cmdfunc(struct mtd_info *mtd, unsigned command,
 	/* NB: The datasheet lies -- we really should be subtracting 1 here */
 	cafe_writel(cafe, cafe->datalen, NAND_DATA_LEN);
 	cafe_writel(cafe, 0x90000000, NAND_IRQ);
-	if (usedma && (ctl1 & (3<<25))) {
+	if (cafe->usedma && (ctl1 & (3<<25))) {
 		uint32_t dmactl = 0xc0000000 + cafe->datalen;
 		/* If WR or RD bits set, set up DMA */
 		if (ctl1 & (1<<26)) {
@@ -345,11 +346,6 @@ static irqreturn_t cafe_nand_interrupt(int irq, void *id)
 	return IRQ_HANDLED;
 }
 
-static void cafe_nand_bug(struct mtd_info *mtd)
-{
-	BUG();
-}
-
 static int cafe_nand_write_oob(struct mtd_info *mtd,
 			       struct nand_chip *chip, int page)
 {
@@ -598,6 +594,76 @@ static int cafe_mul(int x)
 	return gf4096_mul(x, 0xe01);
 }
 
+static int cafe_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct cafe_priv *cafe = nand_get_controller_data(chip);
+	int err = 0;
+
+	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev, 2112,
+					  &cafe->dmaaddr, GFP_KERNEL);
+	if (!cafe->dmabuf)
+		return -ENOMEM;
+
+	/* Set up DMA address */
+	cafe_writel(cafe, lower_32_bits(cafe->dmaaddr), NAND_DMA_ADDR0);
+	cafe_writel(cafe, upper_32_bits(cafe->dmaaddr), NAND_DMA_ADDR1);
+
+	cafe_dev_dbg(&cafe->pdev->dev, "Set DMA address to %x (virt %p)\n",
+		     cafe_readl(cafe, NAND_DMA_ADDR0), cafe->dmabuf);
+
+	/* Restore the DMA flag */
+	cafe->usedma = usedma;
+
+	cafe->ctl2 = BIT(27); /* Reed-Solomon ECC */
+	if (mtd->writesize == 2048)
+		cafe->ctl2 |= BIT(29); /* 2KiB page size */
+
+	/* Set up ECC according to the type of chip we found */
+	mtd_set_ooblayout(mtd, &cafe_ooblayout_ops);
+	if (mtd->writesize == 2048) {
+		cafe->nand.bbt_td = &cafe_bbt_main_descr_2048;
+		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_2048;
+	} else if (mtd->writesize == 512) {
+		cafe->nand.bbt_td = &cafe_bbt_main_descr_512;
+		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_512;
+	} else {
+		dev_warn(&cafe->pdev->dev,
+			 "Unexpected NAND flash writesize %d. Aborting\n",
+			 mtd->writesize);
+		err = -ENOTSUPP;
+		goto out_free_dma;
+	}
+
+	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
+	cafe->nand.ecc.size = mtd->writesize;
+	cafe->nand.ecc.bytes = 14;
+	cafe->nand.ecc.strength = 4;
+	cafe->nand.ecc.write_page = cafe_nand_write_page_lowlevel;
+	cafe->nand.ecc.write_oob = cafe_nand_write_oob;
+	cafe->nand.ecc.read_page = cafe_nand_read_page;
+	cafe->nand.ecc.read_oob = cafe_nand_read_oob;
+
+	return 0;
+
+ out_free_dma:
+	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
+
+	return err;
+}
+
+static void cafe_nand_detach_chip(struct nand_chip *chip)
+{
+	struct cafe_priv *cafe = nand_get_controller_data(chip);
+
+	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
+}
+
+static const struct nand_controller_ops cafe_nand_controller_ops = {
+	.attach_chip = cafe_nand_attach_chip,
+	.detach_chip = cafe_nand_detach_chip,
+};
+
 static int cafe_nand_probe(struct pci_dev *pdev,
 				     const struct pci_device_id *ent)
 {
@@ -605,7 +671,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	struct cafe_priv *cafe;
 	uint32_t ctrl;
 	int err = 0;
-	int old_dma;
 
 	/* Very old versions shared the same PCI ident for all three
 	   functions on the chip. Verify the class too... */
@@ -713,65 +778,15 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 		cafe_readl(cafe, GLOBAL_CTRL),
 		cafe_readl(cafe, GLOBAL_IRQ_MASK));
 
-	/* Do not use the DMA for the nand_scan_ident() */
-	old_dma = usedma;
-	usedma = 0;
+	/* Do not use the DMA during the NAND identification */
+	cafe->usedma = 0;
 
 	/* Scan to find existence of the device */
-	err = nand_scan_ident(mtd, 2, NULL);
+	cafe->nand.dummy_controller.ops = &cafe_nand_controller_ops;
+	err = nand_scan(mtd, 2);
 	if (err)
 		goto out_irq;
 
-	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev, 2112,
-					  &cafe->dmaaddr, GFP_KERNEL);
-	if (!cafe->dmabuf) {
-		err = -ENOMEM;
-		goto out_irq;
-	}
-
-	/* Set up DMA address */
-	cafe_writel(cafe, lower_32_bits(cafe->dmaaddr), NAND_DMA_ADDR0);
-	cafe_writel(cafe, upper_32_bits(cafe->dmaaddr), NAND_DMA_ADDR1);
-
-	cafe_dev_dbg(&cafe->pdev->dev, "Set DMA address to %x (virt %p)\n",
-		cafe_readl(cafe, NAND_DMA_ADDR0), cafe->dmabuf);
-
-	/* Restore the DMA flag */
-	usedma = old_dma;
-
-	cafe->ctl2 = 1<<27; /* Reed-Solomon ECC */
-	if (mtd->writesize == 2048)
-		cafe->ctl2 |= 1<<29; /* 2KiB page size */
-
-	/* Set up ECC according to the type of chip we found */
-	mtd_set_ooblayout(mtd, &cafe_ooblayout_ops);
-	if (mtd->writesize == 2048) {
-		cafe->nand.bbt_td = &cafe_bbt_main_descr_2048;
-		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_2048;
-	} else if (mtd->writesize == 512) {
-		cafe->nand.bbt_td = &cafe_bbt_main_descr_512;
-		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_512;
-	} else {
-		pr_warn("Unexpected NAND flash writesize %d. Aborting\n",
-			mtd->writesize);
-		goto out_free_dma;
-	}
-	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
-	cafe->nand.ecc.size = mtd->writesize;
-	cafe->nand.ecc.bytes = 14;
-	cafe->nand.ecc.strength = 4;
-	cafe->nand.ecc.hwctl  = (void *)cafe_nand_bug;
-	cafe->nand.ecc.calculate = (void *)cafe_nand_bug;
-	cafe->nand.ecc.correct  = (void *)cafe_nand_bug;
-	cafe->nand.ecc.write_page = cafe_nand_write_page_lowlevel;
-	cafe->nand.ecc.write_oob = cafe_nand_write_oob;
-	cafe->nand.ecc.read_page = cafe_nand_read_page;
-	cafe->nand.ecc.read_oob = cafe_nand_read_oob;
-
-	err = nand_scan_tail(mtd);
-	if (err)
-		goto out_free_dma;
-
 	pci_set_drvdata(pdev, mtd);
 
 	mtd->name = "cafe_nand";
@@ -783,8 +798,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 
  out_cleanup_nand:
 	nand_cleanup(&cafe->nand);
- out_free_dma:
-	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
  out_irq:
 	/* Disable NAND IRQ in global IRQ mask register */
 	cafe_writel(cafe, ~1 & cafe_readl(cafe, GLOBAL_IRQ_MASK), GLOBAL_IRQ_MASK);
diff --git a/drivers/mtd/nand/raw/cmx270_nand.c b/drivers/mtd/nand/raw/cmx270_nand.c
index 02d6751e9efe..b66e254b6802 100644
--- a/drivers/mtd/nand/raw/cmx270_nand.c
+++ b/drivers/mtd/nand/raw/cmx270_nand.c
@@ -200,8 +200,8 @@ static int __init cmx270_init(void)
 	}
 
 	/* Register the partitions */
-	ret = mtd_device_parse_register(cmx270_nand_mtd, NULL, NULL,
-					partition_info, NUM_PARTITIONS);
+	ret = mtd_device_register(cmx270_nand_mtd, partition_info,
+				  NUM_PARTITIONS);
 	if (ret)
 		goto err_scan;
 
diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c
index 82269fde9e66..beafad62e7d5 100644
--- a/drivers/mtd/nand/raw/cs553x_nand.c
+++ b/drivers/mtd/nand/raw/cs553x_nand.c
@@ -310,8 +310,7 @@ static int __init cs553x_init(void)
 	for (i = 0; i < NR_CS553X_CONTROLLERS; i++) {
 		if (cs553x_mtd[i]) {
 			/* If any devices registered, return success. Else the last error. */
-			mtd_device_parse_register(cs553x_mtd[i], NULL, NULL,
-						  NULL, 0);
+			mtd_device_register(cs553x_mtd[i], NULL, 0);
 			err = 0;
 		}
 	}
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index cd12e5abafde..40145e206a6b 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -53,15 +53,14 @@
 struct davinci_nand_info {
 	struct nand_chip	chip;
 
-	struct device		*dev;
+	struct platform_device	*pdev;
 
 	bool			is_readmode;
 
 	void __iomem		*base;
 	void __iomem		*vaddr;
 
-	uint32_t		ioaddr;
-	uint32_t		current_cs;
+	void __iomem		*current_cs;
 
 	uint32_t		mask_chipsel;
 	uint32_t		mask_ale;
@@ -102,17 +101,17 @@ static void nand_davinci_hwcontrol(struct mtd_info *mtd, int cmd,
 				   unsigned int ctrl)
 {
 	struct davinci_nand_info	*info = to_davinci_nand(mtd);
-	uint32_t			addr = info->current_cs;
+	void __iomem			*addr = info->current_cs;
 	struct nand_chip		*nand = mtd_to_nand(mtd);
 
 	/* Did the control lines change? */
 	if (ctrl & NAND_CTRL_CHANGE) {
 		if ((ctrl & NAND_CTRL_CLE) == NAND_CTRL_CLE)
-			addr |= info->mask_cle;
+			addr += info->mask_cle;
 		else if ((ctrl & NAND_CTRL_ALE) == NAND_CTRL_ALE)
-			addr |= info->mask_ale;
+			addr += info->mask_ale;
 
-		nand->IO_ADDR_W = (void __iomem __force *)addr;
+		nand->IO_ADDR_W = addr;
 	}
 
 	if (cmd != NAND_CMD_NONE)
@@ -122,14 +121,14 @@ static void nand_davinci_hwcontrol(struct mtd_info *mtd, int cmd,
 static void nand_davinci_select_chip(struct mtd_info *mtd, int chip)
 {
 	struct davinci_nand_info	*info = to_davinci_nand(mtd);
-	uint32_t			addr = info->ioaddr;
+
+	info->current_cs = info->vaddr;
 
 	/* maybe kick in a second chipselect */
 	if (chip > 0)
-		addr |= info->mask_chipsel;
-	info->current_cs = addr;
+		info->current_cs += info->mask_chipsel;
 
-	info->chip.IO_ADDR_W = (void __iomem __force *)addr;
+	info->chip.IO_ADDR_W = info->current_cs;
 	info->chip.IO_ADDR_R = info->chip.IO_ADDR_W;
 }
 
@@ -319,7 +318,7 @@ static int nand_davinci_correct_4bit(struct mtd_info *mtd,
 	/* Unpack ten bytes into eight 10 bit values.  We know we're
 	 * little-endian, and use type punning for less shifting/masking.
 	 */
-	if (WARN_ON(0x01 & (unsigned) ecc_code))
+	if (WARN_ON(0x01 & (uintptr_t)ecc_code))
 		return -EINVAL;
 	ecc16 = (unsigned short *)ecc_code;
 
@@ -441,9 +440,9 @@ static void nand_davinci_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if ((0x03 & ((unsigned)buf)) == 0 && (0x03 & len) == 0)
+	if ((0x03 & ((uintptr_t)buf)) == 0 && (0x03 & len) == 0)
 		ioread32_rep(chip->IO_ADDR_R, buf, len >> 2);
-	else if ((0x01 & ((unsigned)buf)) == 0 && (0x01 & len) == 0)
+	else if ((0x01 & ((uintptr_t)buf)) == 0 && (0x01 & len) == 0)
 		ioread16_rep(chip->IO_ADDR_R, buf, len >> 1);
 	else
 		ioread8_rep(chip->IO_ADDR_R, buf, len);
@@ -454,9 +453,9 @@ static void nand_davinci_write_buf(struct mtd_info *mtd,
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if ((0x03 & ((unsigned)buf)) == 0 && (0x03 & len) == 0)
+	if ((0x03 & ((uintptr_t)buf)) == 0 && (0x03 & len) == 0)
 		iowrite32_rep(chip->IO_ADDR_R, buf, len >> 2);
-	else if ((0x01 & ((unsigned)buf)) == 0 && (0x01 & len) == 0)
+	else if ((0x01 & ((uintptr_t)buf)) == 0 && (0x01 & len) == 0)
 		iowrite16_rep(chip->IO_ADDR_R, buf, len >> 1);
 	else
 		iowrite8_rep(chip->IO_ADDR_R, buf, len);
@@ -606,6 +605,104 @@ static struct davinci_nand_pdata
 }
 #endif
 
+static int davinci_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct davinci_nand_info *info = to_davinci_nand(mtd);
+	struct davinci_nand_pdata *pdata = nand_davinci_get_pdata(info->pdev);
+	int ret = 0;
+
+	if (IS_ERR(pdata))
+		return PTR_ERR(pdata);
+
+	switch (info->chip.ecc.mode) {
+	case NAND_ECC_NONE:
+		pdata->ecc_bits = 0;
+		break;
+	case NAND_ECC_SOFT:
+		pdata->ecc_bits = 0;
+		/*
+		 * This driver expects Hamming based ECC when ecc_mode is set
+		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
+		 * avoid adding an extra ->ecc_algo field to
+		 * davinci_nand_pdata.
+		 */
+		info->chip.ecc.algo = NAND_ECC_HAMMING;
+		break;
+	case NAND_ECC_HW:
+		if (pdata->ecc_bits == 4) {
+			/*
+			 * No sanity checks:  CPUs must support this,
+			 * and the chips may not use NAND_BUSWIDTH_16.
+			 */
+
+			/* No sharing 4-bit hardware between chipselects yet */
+			spin_lock_irq(&davinci_nand_lock);
+			if (ecc4_busy)
+				ret = -EBUSY;
+			else
+				ecc4_busy = true;
+			spin_unlock_irq(&davinci_nand_lock);
+
+			if (ret == -EBUSY)
+				return ret;
+
+			info->chip.ecc.calculate = nand_davinci_calculate_4bit;
+			info->chip.ecc.correct = nand_davinci_correct_4bit;
+			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
+			info->chip.ecc.bytes = 10;
+			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
+			info->chip.ecc.algo = NAND_ECC_BCH;
+		} else {
+			/* 1bit ecc hamming */
+			info->chip.ecc.calculate = nand_davinci_calculate_1bit;
+			info->chip.ecc.correct = nand_davinci_correct_1bit;
+			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
+			info->chip.ecc.bytes = 3;
+			info->chip.ecc.algo = NAND_ECC_HAMMING;
+		}
+		info->chip.ecc.size = 512;
+		info->chip.ecc.strength = pdata->ecc_bits;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * Update ECC layout if needed ... for 1-bit HW ECC, the default
+	 * is OK, but it allocates 6 bytes when only 3 are needed (for
+	 * each 512 bytes).  For the 4-bit HW ECC, that default is not
+	 * usable:  10 bytes are needed, not 6.
+	 */
+	if (pdata->ecc_bits == 4) {
+		int chunks = mtd->writesize / 512;
+
+		if (!chunks || mtd->oobsize < 16) {
+			dev_dbg(&info->pdev->dev, "too small\n");
+			return -EINVAL;
+		}
+
+		/* For small page chips, preserve the manufacturer's
+		 * badblock marking data ... and make sure a flash BBT
+		 * table marker fits in the free bytes.
+		 */
+		if (chunks == 1) {
+			mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops);
+		} else if (chunks == 4 || chunks == 8) {
+			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+			info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
+		} else {
+			return -EIO;
+		}
+	}
+
+	return ret;
+}
+
+static const struct nand_controller_ops davinci_nand_controller_ops = {
+	.attach_chip = davinci_nand_attach_chip,
+};
+
 static int nand_davinci_probe(struct platform_device *pdev)
 {
 	struct davinci_nand_pdata	*pdata;
@@ -659,7 +756,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 		return -EADDRNOTAVAIL;
 	}
 
-	info->dev		= &pdev->dev;
+	info->pdev		= pdev;
 	info->base		= base;
 	info->vaddr		= vaddr;
 
@@ -680,9 +777,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	info->chip.bbt_md	= pdata->bbt_md;
 	info->timing		= pdata->timing;
 
-	info->ioaddr		= (uint32_t __force) vaddr;
-
-	info->current_cs	= info->ioaddr;
+	info->current_cs	= info->vaddr;
 	info->core_chipsel	= pdata->core_chipsel;
 	info->mask_chipsel	= pdata->mask_chipsel;
 
@@ -711,100 +806,15 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	spin_unlock_irq(&davinci_nand_lock);
 
 	/* Scan to find existence of the device(s) */
-	ret = nand_scan_ident(mtd, pdata->mask_chipsel ? 2 : 1, NULL);
+	info->chip.dummy_controller.ops = &davinci_nand_controller_ops;
+	ret = nand_scan(mtd, pdata->mask_chipsel ? 2 : 1);
 	if (ret < 0) {
 		dev_dbg(&pdev->dev, "no NAND chip(s) found\n");
 		return ret;
 	}
 
-	switch (info->chip.ecc.mode) {
-	case NAND_ECC_NONE:
-		pdata->ecc_bits = 0;
-		break;
-	case NAND_ECC_SOFT:
-		pdata->ecc_bits = 0;
-		/*
-		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
-		 * avoid adding an extra ->ecc_algo field to
-		 * davinci_nand_pdata.
-		 */
-		info->chip.ecc.algo = NAND_ECC_HAMMING;
-		break;
-	case NAND_ECC_HW:
-		if (pdata->ecc_bits == 4) {
-			/* No sanity checks:  CPUs must support this,
-			 * and the chips may not use NAND_BUSWIDTH_16.
-			 */
-
-			/* No sharing 4-bit hardware between chipselects yet */
-			spin_lock_irq(&davinci_nand_lock);
-			if (ecc4_busy)
-				ret = -EBUSY;
-			else
-				ecc4_busy = true;
-			spin_unlock_irq(&davinci_nand_lock);
-
-			if (ret == -EBUSY)
-				return ret;
-
-			info->chip.ecc.calculate = nand_davinci_calculate_4bit;
-			info->chip.ecc.correct = nand_davinci_correct_4bit;
-			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
-			info->chip.ecc.bytes = 10;
-			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
-			info->chip.ecc.algo = NAND_ECC_BCH;
-		} else {
-			/* 1bit ecc hamming */
-			info->chip.ecc.calculate = nand_davinci_calculate_1bit;
-			info->chip.ecc.correct = nand_davinci_correct_1bit;
-			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
-			info->chip.ecc.bytes = 3;
-			info->chip.ecc.algo = NAND_ECC_HAMMING;
-		}
-		info->chip.ecc.size = 512;
-		info->chip.ecc.strength = pdata->ecc_bits;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* Update ECC layout if needed ... for 1-bit HW ECC, the default
-	 * is OK, but it allocates 6 bytes when only 3 are needed (for
-	 * each 512 bytes).  For the 4-bit HW ECC, that default is not
-	 * usable:  10 bytes are needed, not 6.
-	 */
-	if (pdata->ecc_bits == 4) {
-		int	chunks = mtd->writesize / 512;
-
-		if (!chunks || mtd->oobsize < 16) {
-			dev_dbg(&pdev->dev, "too small\n");
-			ret = -EINVAL;
-			goto err;
-		}
-
-		/* For small page chips, preserve the manufacturer's
-		 * badblock marking data ... and make sure a flash BBT
-		 * table marker fits in the free bytes.
-		 */
-		if (chunks == 1) {
-			mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops);
-		} else if (chunks == 4 || chunks == 8) {
-			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
-			info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
-		} else {
-			ret = -EIO;
-			goto err;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret < 0)
-		goto err;
-
 	if (pdata->parts)
-		ret = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata->parts, pdata->nr_parts);
+		ret = mtd_device_register(mtd, pdata->parts, pdata->nr_parts);
 	else
 		ret = mtd_device_register(mtd, NULL, 0);
 	if (ret < 0)
@@ -819,11 +829,6 @@ static int nand_davinci_probe(struct platform_device *pdev)
 err_cleanup_nand:
 	nand_cleanup(&info->chip);
 
-err:
-	spin_lock_irq(&davinci_nand_lock);
-	if (info->chip.ecc.mode == NAND_ECC_HW_SYNDROME)
-		ecc4_busy = false;
-	spin_unlock_irq(&davinci_nand_lock);
 	return ret;
 }
 
diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 2a302a1d1430..ca18612c4201 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -51,14 +51,6 @@ MODULE_LICENSE("GPL");
 #define DENALI_INVALID_BANK	-1
 #define DENALI_NR_BANKS		4
 
-/*
- * The bus interface clock, clk_x, is phase aligned with the core clock.  The
- * clk_x is an integral multiple N of the core clk.  The value N is configured
- * at IP delivery time, and its available value is 4, 5, or 6.  We need to align
- * to the largest value to make it work with any possible configuration.
- */
-#define DENALI_CLK_X_MULT	6
-
 static inline struct denali_nand_info *mtd_to_denali(struct mtd_info *mtd)
 {
 	return container_of(mtd_to_nand(mtd), struct denali_nand_info, nand);
@@ -954,7 +946,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	const struct nand_sdr_timings *timings;
-	unsigned long t_clk;
+	unsigned long t_x, mult_x;
 	int acc_clks, re_2_we, re_2_re, we_2_re, addr_2_data;
 	int rdwr_en_lo, rdwr_en_hi, rdwr_en_lo_hi, cs_setup;
 	int addr_2_data_mask;
@@ -965,15 +957,24 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 		return PTR_ERR(timings);
 
 	/* clk_x period in picoseconds */
-	t_clk = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate);
-	if (!t_clk)
+	t_x = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate);
+	if (!t_x)
+		return -EINVAL;
+
+	/*
+	 * The bus interface clock, clk_x, is phase aligned with the core clock.
+	 * The clk_x is an integral multiple N of the core clk.  The value N is
+	 * configured at IP delivery time, and its available value is 4, 5, 6.
+	 */
+	mult_x = DIV_ROUND_CLOSEST_ULL(denali->clk_x_rate, denali->clk_rate);
+	if (mult_x < 4 || mult_x > 6)
 		return -EINVAL;
 
 	if (chipnr == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	/* tREA -> ACC_CLKS */
-	acc_clks = DIV_ROUND_UP(timings->tREA_max, t_clk);
+	acc_clks = DIV_ROUND_UP(timings->tREA_max, t_x);
 	acc_clks = min_t(int, acc_clks, ACC_CLKS__VALUE);
 
 	tmp = ioread32(denali->reg + ACC_CLKS);
@@ -982,7 +983,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + ACC_CLKS);
 
 	/* tRWH -> RE_2_WE */
-	re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_clk);
+	re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_x);
 	re_2_we = min_t(int, re_2_we, RE_2_WE__VALUE);
 
 	tmp = ioread32(denali->reg + RE_2_WE);
@@ -991,7 +992,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RE_2_WE);
 
 	/* tRHZ -> RE_2_RE */
-	re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_clk);
+	re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_x);
 	re_2_re = min_t(int, re_2_re, RE_2_RE__VALUE);
 
 	tmp = ioread32(denali->reg + RE_2_RE);
@@ -1005,8 +1006,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	 * With WE_2_RE properly set, the Denali controller automatically takes
 	 * care of the delay; the driver need not set NAND_WAIT_TCCS.
 	 */
-	we_2_re = DIV_ROUND_UP(max(timings->tCCS_min, timings->tWHR_min),
-			       t_clk);
+	we_2_re = DIV_ROUND_UP(max(timings->tCCS_min, timings->tWHR_min), t_x);
 	we_2_re = min_t(int, we_2_re, TWHR2_AND_WE_2_RE__WE_2_RE);
 
 	tmp = ioread32(denali->reg + TWHR2_AND_WE_2_RE);
@@ -1021,7 +1021,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	if (denali->revision < 0x0501)
 		addr_2_data_mask >>= 1;
 
-	addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_clk);
+	addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_x);
 	addr_2_data = min_t(int, addr_2_data, addr_2_data_mask);
 
 	tmp = ioread32(denali->reg + TCWAW_AND_ADDR_2_DATA);
@@ -1031,7 +1031,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 
 	/* tREH, tWH -> RDWR_EN_HI_CNT */
 	rdwr_en_hi = DIV_ROUND_UP(max(timings->tREH_min, timings->tWH_min),
-				  t_clk);
+				  t_x);
 	rdwr_en_hi = min_t(int, rdwr_en_hi, RDWR_EN_HI_CNT__VALUE);
 
 	tmp = ioread32(denali->reg + RDWR_EN_HI_CNT);
@@ -1040,11 +1040,10 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RDWR_EN_HI_CNT);
 
 	/* tRP, tWP -> RDWR_EN_LO_CNT */
-	rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min),
-				  t_clk);
+	rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min), t_x);
 	rdwr_en_lo_hi = DIV_ROUND_UP(max(timings->tRC_min, timings->tWC_min),
-				     t_clk);
-	rdwr_en_lo_hi = max(rdwr_en_lo_hi, DENALI_CLK_X_MULT);
+				     t_x);
+	rdwr_en_lo_hi = max_t(int, rdwr_en_lo_hi, mult_x);
 	rdwr_en_lo = max(rdwr_en_lo, rdwr_en_lo_hi - rdwr_en_hi);
 	rdwr_en_lo = min_t(int, rdwr_en_lo, RDWR_EN_LO_CNT__VALUE);
 
@@ -1054,8 +1053,8 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RDWR_EN_LO_CNT);
 
 	/* tCS, tCEA -> CS_SETUP_CNT */
-	cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_clk) - rdwr_en_lo,
-			(int)DIV_ROUND_UP(timings->tCEA_max, t_clk) - acc_clks,
+	cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_x) - rdwr_en_lo,
+			(int)DIV_ROUND_UP(timings->tCEA_max, t_x) - acc_clks,
 			0);
 	cs_setup = min_t(int, cs_setup, CS_SETUP_CNT__VALUE);
 
@@ -1120,33 +1119,6 @@ int denali_calc_ecc_bytes(int step_size, int strength)
 }
 EXPORT_SYMBOL(denali_calc_ecc_bytes);
 
-static int denali_ecc_setup(struct mtd_info *mtd, struct nand_chip *chip,
-			    struct denali_nand_info *denali)
-{
-	int oobavail = mtd->oobsize - denali->oob_skip_bytes;
-	int ret;
-
-	/*
-	 * If .size and .strength are already set (usually by DT),
-	 * check if they are supported by this controller.
-	 */
-	if (chip->ecc.size && chip->ecc.strength)
-		return nand_check_ecc_caps(chip, denali->ecc_caps, oobavail);
-
-	/*
-	 * We want .size and .strength closest to the chip's requirement
-	 * unless NAND_ECC_MAXIMIZE is requested.
-	 */
-	if (!(chip->ecc.options & NAND_ECC_MAXIMIZE)) {
-		ret = nand_match_ecc_req(chip, denali->ecc_caps, oobavail);
-		if (!ret)
-			return 0;
-	}
-
-	/* Max ECC strength is the last thing we can do */
-	return nand_maximize_ecc(chip, denali->ecc_caps, oobavail);
-}
-
 static int denali_ooblayout_ecc(struct mtd_info *mtd, int section,
 				struct mtd_oob_region *oobregion)
 {
@@ -1233,62 +1205,12 @@ static int denali_multidev_fixup(struct denali_nand_info *denali)
 	return 0;
 }
 
-int denali_init(struct denali_nand_info *denali)
+static int denali_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &denali->nand;
 	struct mtd_info *mtd = nand_to_mtd(chip);
-	u32 features = ioread32(denali->reg + FEATURES);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	int ret;
 
-	mtd->dev.parent = denali->dev;
-	denali_hw_init(denali);
-
-	init_completion(&denali->complete);
-	spin_lock_init(&denali->irq_lock);
-
-	denali_clear_irq_all(denali);
-
-	ret = devm_request_irq(denali->dev, denali->irq, denali_isr,
-			       IRQF_SHARED, DENALI_NAND_NAME, denali);
-	if (ret) {
-		dev_err(denali->dev, "Unable to request IRQ\n");
-		return ret;
-	}
-
-	denali_enable_irq(denali);
-	denali_reset_banks(denali);
-
-	denali->active_bank = DENALI_INVALID_BANK;
-
-	nand_set_flash_node(chip, denali->dev->of_node);
-	/* Fallback to the default name if DT did not give "label" property */
-	if (!mtd->name)
-		mtd->name = "denali-nand";
-
-	chip->select_chip = denali_select_chip;
-	chip->read_byte = denali_read_byte;
-	chip->write_byte = denali_write_byte;
-	chip->read_word = denali_read_word;
-	chip->cmd_ctrl = denali_cmd_ctrl;
-	chip->dev_ready = denali_dev_ready;
-	chip->waitfunc = denali_waitfunc;
-
-	if (features & FEATURES__INDEX_ADDR) {
-		denali->host_read = denali_indexed_read;
-		denali->host_write = denali_indexed_write;
-	} else {
-		denali->host_read = denali_direct_read;
-		denali->host_write = denali_direct_write;
-	}
-
-	/* clk rate info is needed for setup_data_interface */
-	if (denali->clk_x_rate)
-		chip->setup_data_interface = denali_setup_data_interface;
-
-	ret = nand_scan_ident(mtd, denali->max_banks, NULL);
-	if (ret)
-		goto disable_irq;
-
 	if (ioread32(denali->reg + FEATURES) & FEATURES__DMA)
 		denali->dma_avail = 1;
 
@@ -1317,10 +1239,11 @@ int denali_init(struct denali_nand_info *denali)
 	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
-	ret = denali_ecc_setup(mtd, chip, denali);
+	ret = nand_ecc_choose_conf(chip, denali->ecc_caps,
+				   mtd->oobsize - denali->oob_skip_bytes);
 	if (ret) {
 		dev_err(denali->dev, "Failed to setup ECC settings.\n");
-		goto disable_irq;
+		return ret;
 	}
 
 	dev_dbg(denali->dev,
@@ -1364,7 +1287,7 @@ int denali_init(struct denali_nand_info *denali)
 
 	ret = denali_multidev_fixup(denali);
 	if (ret)
-		goto disable_irq;
+		return ret;
 
 	/*
 	 * This buffer is DMA-mapped by denali_{read,write}_page_raw.  Do not
@@ -1372,26 +1295,92 @@ int denali_init(struct denali_nand_info *denali)
 	 * guarantee DMA-safe alignment.
 	 */
 	denali->buf = kmalloc(mtd->writesize + mtd->oobsize, GFP_KERNEL);
-	if (!denali->buf) {
-		ret = -ENOMEM;
-		goto disable_irq;
+	if (!denali->buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void denali_detach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+
+	kfree(denali->buf);
+}
+
+static const struct nand_controller_ops denali_controller_ops = {
+	.attach_chip = denali_attach_chip,
+	.detach_chip = denali_detach_chip,
+};
+
+int denali_init(struct denali_nand_info *denali)
+{
+	struct nand_chip *chip = &denali->nand;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u32 features = ioread32(denali->reg + FEATURES);
+	int ret;
+
+	mtd->dev.parent = denali->dev;
+	denali_hw_init(denali);
+
+	init_completion(&denali->complete);
+	spin_lock_init(&denali->irq_lock);
+
+	denali_clear_irq_all(denali);
+
+	ret = devm_request_irq(denali->dev, denali->irq, denali_isr,
+			       IRQF_SHARED, DENALI_NAND_NAME, denali);
+	if (ret) {
+		dev_err(denali->dev, "Unable to request IRQ\n");
+		return ret;
 	}
 
-	ret = nand_scan_tail(mtd);
+	denali_enable_irq(denali);
+	denali_reset_banks(denali);
+
+	denali->active_bank = DENALI_INVALID_BANK;
+
+	nand_set_flash_node(chip, denali->dev->of_node);
+	/* Fallback to the default name if DT did not give "label" property */
+	if (!mtd->name)
+		mtd->name = "denali-nand";
+
+	chip->select_chip = denali_select_chip;
+	chip->read_byte = denali_read_byte;
+	chip->write_byte = denali_write_byte;
+	chip->read_word = denali_read_word;
+	chip->cmd_ctrl = denali_cmd_ctrl;
+	chip->dev_ready = denali_dev_ready;
+	chip->waitfunc = denali_waitfunc;
+
+	if (features & FEATURES__INDEX_ADDR) {
+		denali->host_read = denali_indexed_read;
+		denali->host_write = denali_indexed_write;
+	} else {
+		denali->host_read = denali_direct_read;
+		denali->host_write = denali_direct_write;
+	}
+
+	/* clk rate info is needed for setup_data_interface */
+	if (denali->clk_rate && denali->clk_x_rate)
+		chip->setup_data_interface = denali_setup_data_interface;
+
+	chip->dummy_controller.ops = &denali_controller_ops;
+	ret = nand_scan(mtd, denali->max_banks);
 	if (ret)
-		goto free_buf;
+		goto disable_irq;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(denali->dev, "Failed to register MTD: %d\n", ret);
 		goto cleanup_nand;
 	}
+
 	return 0;
 
 cleanup_nand:
 	nand_cleanup(chip);
-free_buf:
-	kfree(denali->buf);
 disable_irq:
 	denali_disable_irq(denali);
 
@@ -1404,7 +1393,6 @@ void denali_remove(struct denali_nand_info *denali)
 	struct mtd_info *mtd = nand_to_mtd(&denali->nand);
 
 	nand_release(mtd);
-	kfree(denali->buf);
 	denali_disable_irq(denali);
 }
 EXPORT_SYMBOL(denali_remove);
diff --git a/drivers/mtd/nand/raw/denali.h b/drivers/mtd/nand/raw/denali.h
index 9ad33d237378..1f8feaf924eb 100644
--- a/drivers/mtd/nand/raw/denali.h
+++ b/drivers/mtd/nand/raw/denali.h
@@ -300,6 +300,7 @@
 
 struct denali_nand_info {
 	struct nand_chip nand;
+	unsigned long clk_rate;		/* core clock rate */
 	unsigned long clk_x_rate;	/* bus interface clock rate */
 	int active_bank;		/* currently selected bank */
 	struct device *dev;
diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c
index cfd33e6ca77f..0faaad032e5f 100644
--- a/drivers/mtd/nand/raw/denali_dt.c
+++ b/drivers/mtd/nand/raw/denali_dt.c
@@ -27,7 +27,9 @@
 
 struct denali_dt {
 	struct denali_nand_info	denali;
-	struct clk		*clk;
+	struct clk *clk;	/* core clock */
+	struct clk *clk_x;	/* bus interface clock */
+	struct clk *clk_ecc;	/* ECC circuit clock */
 };
 
 struct denali_dt_data {
@@ -79,59 +81,99 @@ MODULE_DEVICE_TABLE(of, denali_nand_dt_ids);
 
 static int denali_dt_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct denali_dt *dt;
 	const struct denali_dt_data *data;
 	struct denali_nand_info *denali;
 	int ret;
 
-	dt = devm_kzalloc(&pdev->dev, sizeof(*dt), GFP_KERNEL);
+	dt = devm_kzalloc(dev, sizeof(*dt), GFP_KERNEL);
 	if (!dt)
 		return -ENOMEM;
 	denali = &dt->denali;
 
-	data = of_device_get_match_data(&pdev->dev);
+	data = of_device_get_match_data(dev);
 	if (data) {
 		denali->revision = data->revision;
 		denali->caps = data->caps;
 		denali->ecc_caps = data->ecc_caps;
 	}
 
-	denali->dev = &pdev->dev;
+	denali->dev = dev;
 	denali->irq = platform_get_irq(pdev, 0);
 	if (denali->irq < 0) {
-		dev_err(&pdev->dev, "no irq defined\n");
+		dev_err(dev, "no irq defined\n");
 		return denali->irq;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg");
-	denali->reg = devm_ioremap_resource(&pdev->dev, res);
+	denali->reg = devm_ioremap_resource(dev, res);
 	if (IS_ERR(denali->reg))
 		return PTR_ERR(denali->reg);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data");
-	denali->host = devm_ioremap_resource(&pdev->dev, res);
+	denali->host = devm_ioremap_resource(dev, res);
 	if (IS_ERR(denali->host))
 		return PTR_ERR(denali->host);
 
-	dt->clk = devm_clk_get(&pdev->dev, NULL);
+	/*
+	 * A single anonymous clock is supported for the backward compatibility.
+	 * New platforms should support all the named clocks.
+	 */
+	dt->clk = devm_clk_get(dev, "nand");
+	if (IS_ERR(dt->clk))
+		dt->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(dt->clk)) {
-		dev_err(&pdev->dev, "no clk available\n");
+		dev_err(dev, "no clk available\n");
 		return PTR_ERR(dt->clk);
 	}
+
+	dt->clk_x = devm_clk_get(dev, "nand_x");
+	if (IS_ERR(dt->clk_x))
+		dt->clk_x = NULL;
+
+	dt->clk_ecc = devm_clk_get(dev, "ecc");
+	if (IS_ERR(dt->clk_ecc))
+		dt->clk_ecc = NULL;
+
 	ret = clk_prepare_enable(dt->clk);
 	if (ret)
 		return ret;
 
-	denali->clk_x_rate = clk_get_rate(dt->clk);
+	ret = clk_prepare_enable(dt->clk_x);
+	if (ret)
+		goto out_disable_clk;
+
+	ret = clk_prepare_enable(dt->clk_ecc);
+	if (ret)
+		goto out_disable_clk_x;
+
+	if (dt->clk_x) {
+		denali->clk_rate = clk_get_rate(dt->clk);
+		denali->clk_x_rate = clk_get_rate(dt->clk_x);
+	} else {
+		/*
+		 * Hardcode the clock rates for the backward compatibility.
+		 * This works for both SOCFPGA and UniPhier.
+		 */
+		dev_notice(dev,
+			   "necessary clock is missing. default clock rates are used.\n");
+		denali->clk_rate = 50000000;
+		denali->clk_x_rate = 200000000;
+	}
 
 	ret = denali_init(denali);
 	if (ret)
-		goto out_disable_clk;
+		goto out_disable_clk_ecc;
 
 	platform_set_drvdata(pdev, dt);
 	return 0;
 
+out_disable_clk_ecc:
+	clk_disable_unprepare(dt->clk_ecc);
+out_disable_clk_x:
+	clk_disable_unprepare(dt->clk_x);
 out_disable_clk:
 	clk_disable_unprepare(dt->clk);
 
@@ -143,6 +185,8 @@ static int denali_dt_remove(struct platform_device *pdev)
 	struct denali_dt *dt = platform_get_drvdata(pdev);
 
 	denali_remove(&dt->denali);
+	clk_disable_unprepare(dt->clk_ecc);
+	clk_disable_unprepare(dt->clk_x);
 	clk_disable_unprepare(dt->clk);
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/denali_pci.c b/drivers/mtd/nand/raw/denali_pci.c
index 49cb3e1f8bd0..7c8efc4c7bdf 100644
--- a/drivers/mtd/nand/raw/denali_pci.c
+++ b/drivers/mtd/nand/raw/denali_pci.c
@@ -73,6 +73,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	denali->irq = dev->irq;
 	denali->ecc_caps = &denali_pci_ecc_caps;
 	denali->nand.ecc.options |= NAND_ECC_MAXIMIZE;
+	denali->clk_rate = 50000000;		/* 50 MHz */
 	denali->clk_x_rate = 200000000;		/* 200 MHz */
 
 	ret = pci_request_regions(dev, DENALI_NAND_NAME);
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 8d10061abb4b..3c46188dd6d2 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1291,7 +1291,7 @@ static int __init nftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md = NULL;
 	}
 
-	ret = this->scan_bbt(mtd);
+	ret = nand_create_bbt(this);
 	if (ret)
 		return ret;
 
@@ -1338,7 +1338,7 @@ static int __init inftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md->pattern = "TBB_SYSM";
 	}
 
-	ret = this->scan_bbt(mtd);
+	ret = nand_create_bbt(this);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/nand/raw/docg4.c b/drivers/mtd/nand/raw/docg4.c
index 1314aa99b9ab..a3f04315c05c 100644
--- a/drivers/mtd/nand/raw/docg4.c
+++ b/drivers/mtd/nand/raw/docg4.c
@@ -1227,10 +1227,9 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	 * required within a nand driver because they are performed by the nand
 	 * infrastructure code as part of nand_scan().  In this case they need
 	 * to be initialized here because we skip call to nand_scan_ident() (the
-	 * first half of nand_scan()).  The call to nand_scan_ident() is skipped
-	 * because for this device the chip id is not read in the manner of a
-	 * standard nand device.  Unfortunately, nand_scan_ident() does other
-	 * things as well, such as call nand_set_defaults().
+	 * first half of nand_scan()).  The call to nand_scan_ident() could be
+	 * skipped because for this device the chip id is not read in the manner
+	 * of a standard nand device.
 	 */
 
 	struct nand_chip *nand = mtd_to_nand(mtd);
@@ -1257,8 +1256,8 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	nand->ecc.strength = DOCG4_T;
 	nand->options = NAND_BUSWIDTH_16 | NAND_NO_SUBPAGE_WRITE;
 	nand->IO_ADDR_R = nand->IO_ADDR_W = doc->virtadr + DOC_IOSPACE_DATA;
-	nand->controller = &nand->hwcontrol;
-	nand_hw_control_init(nand->controller);
+	nand->controller = &nand->dummy_controller;
+	nand_controller_init(nand->controller);
 
 	/* methods */
 	nand->cmdfunc = docg4_command;
@@ -1315,6 +1314,40 @@ static int __init read_id_reg(struct mtd_info *mtd)
 
 static char const *part_probes[] = { "cmdlinepart", "saftlpart", NULL };
 
+static int docg4_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct docg4_priv *doc = (struct docg4_priv *)(chip + 1);
+	int ret;
+
+	init_mtd_structs(mtd);
+
+	/* Initialize kernel BCH algorithm */
+	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
+	if (!doc->bch)
+		return -EINVAL;
+
+	reset(mtd);
+
+	ret = read_id_reg(mtd);
+	if (ret)
+		free_bch(doc->bch);
+
+	return ret;
+}
+
+static void docg4_detach_chip(struct nand_chip *chip)
+{
+	struct docg4_priv *doc = (struct docg4_priv *)(chip + 1);
+
+	free_bch(doc->bch);
+}
+
+static const struct nand_controller_ops docg4_controller_ops = {
+	.attach_chip = docg4_attach_chip,
+	.detach_chip = docg4_detach_chip,
+};
+
 static int __init probe_docg4(struct platform_device *pdev)
 {
 	struct mtd_info *mtd;
@@ -1341,7 +1374,7 @@ static int __init probe_docg4(struct platform_device *pdev)
 	nand = kzalloc(len, GFP_KERNEL);
 	if (nand == NULL) {
 		retval = -ENOMEM;
-		goto fail_unmap;
+		goto unmap;
 	}
 
 	mtd = nand_to_mtd(nand);
@@ -1350,46 +1383,35 @@ static int __init probe_docg4(struct platform_device *pdev)
 	mtd->dev.parent = &pdev->dev;
 	doc->virtadr = virtadr;
 	doc->dev = dev;
-
-	init_mtd_structs(mtd);
-
-	/* initialize kernel bch algorithm */
-	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
-	if (doc->bch == NULL) {
-		retval = -EINVAL;
-		goto fail;
-	}
-
 	platform_set_drvdata(pdev, doc);
 
-	reset(mtd);
-	retval = read_id_reg(mtd);
-	if (retval == -ENODEV) {
-		dev_warn(dev, "No diskonchip G4 device found.\n");
-		goto fail;
-	}
-
-	retval = nand_scan_tail(mtd);
+	/*
+	 * Running nand_scan() with maxchips == 0 will skip nand_scan_ident(),
+	 * which is a specific operation with this driver and done in the
+	 * ->attach_chip callback.
+	 */
+	nand->dummy_controller.ops = &docg4_controller_ops;
+	retval = nand_scan(mtd, 0);
 	if (retval)
-		goto fail;
+		goto free_nand;
 
 	retval = read_factory_bbt(mtd);
 	if (retval)
-		goto fail;
+		goto cleanup_nand;
 
 	retval = mtd_device_parse_register(mtd, part_probes, NULL, NULL, 0);
 	if (retval)
-		goto fail;
+		goto cleanup_nand;
 
 	doc->mtd = mtd;
+
 	return 0;
 
-fail:
-	nand_release(mtd); /* deletes partitions and mtd devices */
-	free_bch(doc->bch);
+cleanup_nand:
+	nand_cleanup(nand);
+free_nand:
 	kfree(nand);
-
-fail_unmap:
+unmap:
 	iounmap(virtadr);
 
 	return retval;
@@ -1399,7 +1421,6 @@ static int __exit cleanup_docg4(struct platform_device *pdev)
 {
 	struct docg4_priv *doc = platform_get_drvdata(pdev);
 	nand_release(doc->mtd);
-	free_bch(doc->bch);
 	kfree(mtd_to_nand(doc->mtd));
 	iounmap(doc->virtadr);
 	return 0;
diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index 51f0b340bc0d..55f449b711fd 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -61,7 +61,7 @@ struct fsl_elbc_mtd {
 /* Freescale eLBC FCM controller information */
 
 struct fsl_elbc_fcm_ctrl {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct fsl_elbc_mtd *chips[MAX_BANKS];
 
 	u8 __iomem *addr;        /* Address of assigned FCM buffer        */
@@ -637,9 +637,9 @@ static int fsl_elbc_wait(struct mtd_info *mtd, struct nand_chip *chip)
 	return (elbc_fcm_ctrl->mdr & 0xff) | NAND_STATUS_WP;
 }
 
-static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
+static int fsl_elbc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct fsl_elbc_mtd *priv = nand_get_controller_data(chip);
 	struct fsl_lbc_ctrl *ctrl = priv->ctrl;
 	struct fsl_lbc_regs __iomem *lbc = ctrl->regs;
@@ -700,12 +700,16 @@ static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
 		dev_err(priv->dev,
 		        "fsl_elbc_init: page size %d is not supported\n",
 		        mtd->writesize);
-		return -1;
+		return -ENOTSUPP;
 	}
 
 	return 0;
 }
 
+static const struct nand_controller_ops fsl_elbc_controller_ops = {
+	.attach_chip = fsl_elbc_attach_chip,
+};
+
 static int fsl_elbc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 			      uint8_t *buf, int oob_required, int page)
 {
@@ -879,7 +883,7 @@ static int fsl_elbc_nand_probe(struct platform_device *pdev)
 		}
 		elbc_fcm_ctrl->counter++;
 
-		nand_hw_control_init(&elbc_fcm_ctrl->controller);
+		nand_controller_init(&elbc_fcm_ctrl->controller);
 		fsl_lbc_ctrl_dev->nand = elbc_fcm_ctrl;
 	} else {
 		elbc_fcm_ctrl = fsl_lbc_ctrl_dev->nand;
@@ -910,15 +914,8 @@ static int fsl_elbc_nand_probe(struct platform_device *pdev)
 	if (ret)
 		goto err;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		goto err;
-
-	ret = fsl_elbc_chip_init_tail(mtd);
-	if (ret)
-		goto err;
-
-	ret = nand_scan_tail(mtd);
+	priv->chip.controller->ops = &fsl_elbc_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto err;
 
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 382b67e97174..24f59d0066af 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -51,7 +51,7 @@ struct fsl_ifc_mtd {
 
 /* overview of the fsl ifc controller */
 struct fsl_ifc_nand_ctrl {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct fsl_ifc_mtd *chips[FSL_IFC_BANK_COUNT];
 
 	void __iomem *addr;	/* Address of assigned IFC buffer	*/
@@ -225,7 +225,7 @@ static void fsl_ifc_run_command(struct mtd_info *mtd)
 		int bufnum = nctrl->page & priv->bufnum_mask;
 		int sector_start = bufnum * chip->ecc.steps;
 		int sector_end = sector_start + chip->ecc.steps - 1;
-		__be32 *eccstat_regs;
+		__be32 __iomem *eccstat_regs;
 
 		eccstat_regs = ifc->ifc_nand.nand_eccstat;
 		eccstat = ifc_in32(&eccstat_regs[sector_start / 4]);
@@ -714,9 +714,9 @@ static int fsl_ifc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return nand_prog_page_end_op(chip);
 }
 
-static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
+static int fsl_ifc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
 
 	dev_dbg(priv->dev, "%s: nand->numchips = %d\n", __func__,
@@ -757,6 +757,10 @@ static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
 	return 0;
 }
 
+static const struct nand_controller_ops fsl_ifc_controller_ops = {
+	.attach_chip = fsl_ifc_attach_chip,
+};
+
 static void fsl_ifc_sram_init(struct fsl_ifc_mtd *priv)
 {
 	struct fsl_ifc_ctrl *ctrl = priv->ctrl;
@@ -1004,7 +1008,7 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
 		ifc_nand_ctrl->addr = NULL;
 		fsl_ifc_ctrl_dev->nand = ifc_nand_ctrl;
 
-		nand_hw_control_init(&ifc_nand_ctrl->controller);
+		nand_controller_init(&ifc_nand_ctrl->controller);
 	} else {
 		ifc_nand_ctrl = fsl_ifc_ctrl_dev->nand;
 	}
@@ -1046,15 +1050,8 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
 	if (ret)
 		goto err;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		goto err;
-
-	ret = fsl_ifc_chip_init_tail(mtd);
-	if (ret)
-		goto err;
-
-	ret = nand_scan_tail(mtd);
+	priv->chip.controller->ops = &fsl_ifc_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto err;
 
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index f4a5a317d4ae..f418236fa020 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -62,7 +62,7 @@
 						reg)
 
 /* fsmc controller registers for NAND flash */
-#define PC			0x00
+#define FSMC_PC			0x00
 	/* pc register definitions */
 	#define FSMC_RESET		(1 << 0)
 	#define FSMC_WAITON		(1 << 1)
@@ -273,12 +273,13 @@ static void fsmc_nand_setup(struct fsmc_nand_data *host,
 	tset = (tims->tset & FSMC_TSET_MASK) << FSMC_TSET_SHIFT;
 
 	if (host->nand.options & NAND_BUSWIDTH_16)
-		writel_relaxed(value | FSMC_DEVWID_16, host->regs_va + PC);
+		writel_relaxed(value | FSMC_DEVWID_16,
+			       host->regs_va + FSMC_PC);
 	else
-		writel_relaxed(value | FSMC_DEVWID_8, host->regs_va + PC);
+		writel_relaxed(value | FSMC_DEVWID_8, host->regs_va + FSMC_PC);
 
-	writel_relaxed(readl(host->regs_va + PC) | tclr | tar,
-		       host->regs_va + PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) | tclr | tar,
+		       host->regs_va + FSMC_PC);
 	writel_relaxed(thiz | thold | twait | tset, host->regs_va + COMM);
 	writel_relaxed(thiz | thold | twait | tset, host->regs_va + ATTRIB);
 }
@@ -371,12 +372,12 @@ static void fsmc_enable_hwecc(struct mtd_info *mtd, int mode)
 {
 	struct fsmc_nand_data *host = mtd_to_fsmc(mtd);
 
-	writel_relaxed(readl(host->regs_va + PC) & ~FSMC_ECCPLEN_256,
-		       host->regs_va + PC);
-	writel_relaxed(readl(host->regs_va + PC) & ~FSMC_ECCEN,
-		       host->regs_va + PC);
-	writel_relaxed(readl(host->regs_va + PC) | FSMC_ECCEN,
-		       host->regs_va + PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) & ~FSMC_ECCPLEN_256,
+		       host->regs_va + FSMC_PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) & ~FSMC_ECCEN,
+		       host->regs_va + FSMC_PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) | FSMC_ECCEN,
+		       host->regs_va + FSMC_PC);
 }
 
 /*
@@ -546,7 +547,7 @@ static void fsmc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	struct fsmc_nand_data *host  = mtd_to_fsmc(mtd);
 	int i;
 
-	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+	if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) &&
 			IS_ALIGNED(len, sizeof(uint32_t))) {
 		uint32_t *p = (uint32_t *)buf;
 		len = len >> 2;
@@ -569,7 +570,7 @@ static void fsmc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	struct fsmc_nand_data *host  = mtd_to_fsmc(mtd);
 	int i;
 
-	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+	if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) &&
 			IS_ALIGNED(len, sizeof(uint32_t))) {
 		uint32_t *p = (uint32_t *)buf;
 		len = len >> 2;
@@ -618,11 +619,11 @@ static void fsmc_select_chip(struct mtd_info *mtd, int chipnr)
 	if (chipnr > 0)
 		return;
 
-	pc = readl(host->regs_va + PC);
+	pc = readl(host->regs_va + FSMC_PC);
 	if (chipnr < 0)
-		writel_relaxed(pc & ~FSMC_ENABLE, host->regs_va + PC);
+		writel_relaxed(pc & ~FSMC_ENABLE, host->regs_va + FSMC_PC);
 	else
-		writel_relaxed(pc | FSMC_ENABLE, host->regs_va + PC);
+		writel_relaxed(pc | FSMC_ENABLE, host->regs_va + FSMC_PC);
 
 	/* nCE line must be asserted before starting any operation */
 	mb();
@@ -740,7 +741,7 @@ static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
 	for (i = 0, s = 0; s < eccsteps; s++, i += eccbytes, p += eccsize) {
 		nand_read_page_op(chip, page, s * eccsize, NULL, 0);
 		chip->ecc.hwctl(mtd, NAND_ECC_READ);
-		chip->read_buf(mtd, p, eccsize);
+		nand_read_data_op(chip, p, eccsize, false);
 
 		for (j = 0; j < eccbytes;) {
 			struct mtd_oob_region oobregion;
@@ -918,6 +919,82 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
 	return 0;
 }
 
+static int fsmc_nand_attach_chip(struct nand_chip *nand)
+{
+	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct fsmc_nand_data *host = mtd_to_fsmc(mtd);
+
+	if (AMBA_REV_BITS(host->pid) >= 8) {
+		switch (mtd->oobsize) {
+		case 16:
+		case 64:
+		case 128:
+		case 224:
+		case 256:
+			break;
+		default:
+			dev_warn(host->dev,
+				 "No oob scheme defined for oobsize %d\n",
+				 mtd->oobsize);
+			return -EINVAL;
+		}
+
+		mtd_set_ooblayout(mtd, &fsmc_ecc4_ooblayout_ops);
+
+		return 0;
+	}
+
+	switch (nand->ecc.mode) {
+	case NAND_ECC_HW:
+		dev_info(host->dev, "Using 1-bit HW ECC scheme\n");
+		nand->ecc.calculate = fsmc_read_hwecc_ecc1;
+		nand->ecc.correct = nand_correct_data;
+		nand->ecc.bytes = 3;
+		nand->ecc.strength = 1;
+		break;
+
+	case NAND_ECC_SOFT:
+		if (nand->ecc.algo == NAND_ECC_BCH) {
+			dev_info(host->dev,
+				 "Using 4-bit SW BCH ECC scheme\n");
+			break;
+		}
+
+	case NAND_ECC_ON_DIE:
+		break;
+
+	default:
+		dev_err(host->dev, "Unsupported ECC mode!\n");
+		return -ENOTSUPP;
+	}
+
+	/*
+	 * Don't set layout for BCH4 SW ECC. This will be
+	 * generated later in nand_bch_init() later.
+	 */
+	if (nand->ecc.mode == NAND_ECC_HW) {
+		switch (mtd->oobsize) {
+		case 16:
+		case 64:
+		case 128:
+			mtd_set_ooblayout(mtd,
+					  &fsmc_ecc1_ooblayout_ops);
+			break;
+		default:
+			dev_warn(host->dev,
+				 "No oob scheme defined for oobsize %d\n",
+				 mtd->oobsize);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops fsmc_nand_controller_ops = {
+	.attach_chip = fsmc_nand_attach_chip,
+};
+
 /*
  * fsmc_nand_probe - Probe function
  * @pdev:       platform device structure
@@ -1047,76 +1124,8 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	/*
 	 * Scan to find existence of the device
 	 */
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret) {
-		dev_err(&pdev->dev, "No NAND Device found!\n");
-		goto release_dma_write_chan;
-	}
-
-	if (AMBA_REV_BITS(host->pid) >= 8) {
-		switch (mtd->oobsize) {
-		case 16:
-		case 64:
-		case 128:
-		case 224:
-		case 256:
-			break;
-		default:
-			dev_warn(&pdev->dev, "No oob scheme defined for oobsize %d\n",
-				 mtd->oobsize);
-			ret = -EINVAL;
-			goto release_dma_write_chan;
-		}
-
-		mtd_set_ooblayout(mtd, &fsmc_ecc4_ooblayout_ops);
-	} else {
-		switch (nand->ecc.mode) {
-		case NAND_ECC_HW:
-			dev_info(&pdev->dev, "Using 1-bit HW ECC scheme\n");
-			nand->ecc.calculate = fsmc_read_hwecc_ecc1;
-			nand->ecc.correct = nand_correct_data;
-			nand->ecc.bytes = 3;
-			nand->ecc.strength = 1;
-			break;
-
-		case NAND_ECC_SOFT:
-			if (nand->ecc.algo == NAND_ECC_BCH) {
-				dev_info(&pdev->dev, "Using 4-bit SW BCH ECC scheme\n");
-				break;
-			}
-
-		case NAND_ECC_ON_DIE:
-			break;
-
-		default:
-			dev_err(&pdev->dev, "Unsupported ECC mode!\n");
-			goto release_dma_write_chan;
-		}
-
-		/*
-		 * Don't set layout for BCH4 SW ECC. This will be
-		 * generated later in nand_bch_init() later.
-		 */
-		if (nand->ecc.mode == NAND_ECC_HW) {
-			switch (mtd->oobsize) {
-			case 16:
-			case 64:
-			case 128:
-				mtd_set_ooblayout(mtd,
-						  &fsmc_ecc1_ooblayout_ops);
-				break;
-			default:
-				dev_warn(&pdev->dev,
-					 "No oob scheme defined for oobsize %d\n",
-					 mtd->oobsize);
-				ret = -EINVAL;
-				goto release_dma_write_chan;
-			}
-		}
-	}
-
-	/* Second stage of scan to fill MTD data-structures */
-	ret = nand_scan_tail(mtd);
+	nand->dummy_controller.ops = &fsmc_nand_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto release_dma_write_chan;
 
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
index 83697b8df871..88ea2203e263 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #include <linux/delay.h>
 #include <linux/clk.h>
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index f6aa358a3452..1c1ebbc82824 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2010-2015 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #include <linux/clk.h>
 #include <linux/slab.h>
@@ -757,9 +744,9 @@ static int gpmi_alloc_dma_buffer(struct gpmi_nand_data *this)
 	 * [2] Allocate a read/write data buffer.
 	 *     The gpmi_alloc_dma_buffer can be called twice.
 	 *     We allocate a PAGE_SIZE length buffer if gpmi_alloc_dma_buffer
-	 *     is called before the nand_scan_ident; and we allocate a buffer
-	 *     of the real NAND page size when the gpmi_alloc_dma_buffer is
-	 *     called after the nand_scan_ident.
+	 *     is called before the NAND identification; and we allocate a
+	 *     buffer of the real NAND page size when the gpmi_alloc_dma_buffer
+	 *     is called after.
 	 */
 	this->data_buffer_dma = kzalloc(mtd->writesize ?: PAGE_SIZE,
 					GFP_DMA | GFP_KERNEL);
@@ -957,7 +944,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 	struct gpmi_nand_data *this = nand_get_controller_data(chip);
 	struct bch_geometry *nfc_geo = &this->bch_geometry;
 	struct mtd_info *mtd = nand_to_mtd(chip);
-	void          *payload_virt;
 	dma_addr_t    payload_phys;
 	unsigned int  i;
 	unsigned char *status;
@@ -967,7 +953,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 
 	dev_dbg(this->dev, "page number is : %d\n", page);
 
-	payload_virt = this->payload_virt;
 	payload_phys = this->payload_phys;
 
 	if (virt_addr_valid(buf)) {
@@ -976,7 +961,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 		dest_phys = dma_map_single(this->dev, buf, nfc_geo->payload_size,
 					   DMA_FROM_DEVICE);
 		if (!dma_mapping_error(this->dev, dest_phys)) {
-			payload_virt = buf;
 			payload_phys = dest_phys;
 			direct = true;
 		}
@@ -1881,6 +1865,34 @@ static int gpmi_init_last(struct gpmi_nand_data *this)
 	return 0;
 }
 
+static int gpmi_nand_attach_chip(struct nand_chip *chip)
+{
+	struct gpmi_nand_data *this = nand_get_controller_data(chip);
+	int ret;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+		if (of_property_read_bool(this->dev->of_node,
+					  "fsl,no-blockmark-swap"))
+			this->swap_block_mark = false;
+	}
+	dev_dbg(this->dev, "Blockmark swapping %sabled\n",
+		this->swap_block_mark ? "en" : "dis");
+
+	ret = gpmi_init_last(this);
+	if (ret)
+		return ret;
+
+	chip->options |= NAND_SKIP_BBTSCAN;
+
+	return 0;
+}
+
+static const struct nand_controller_ops gpmi_nand_controller_ops = {
+	.attach_chip = gpmi_nand_attach_chip,
+};
+
 static int gpmi_nand_init(struct gpmi_nand_data *this)
 {
 	struct nand_chip *chip = &this->nand;
@@ -1921,33 +1933,15 @@ static int gpmi_nand_init(struct gpmi_nand_data *this)
 	if (ret)
 		goto err_out;
 
-	ret = nand_scan_ident(mtd, GPMI_IS_MX6(this) ? 2 : 1, NULL);
-	if (ret)
-		goto err_out;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-		if (of_property_read_bool(this->dev->of_node,
-						"fsl,no-blockmark-swap"))
-			this->swap_block_mark = false;
-	}
-	dev_dbg(this->dev, "Blockmark swapping %sabled\n",
-		this->swap_block_mark ? "en" : "dis");
-
-	ret = gpmi_init_last(this);
-	if (ret)
-		goto err_out;
-
-	chip->options |= NAND_SKIP_BBTSCAN;
-	ret = nand_scan_tail(mtd);
+	chip->dummy_controller.ops = &gpmi_nand_controller_ops;
+	ret = nand_scan(mtd, GPMI_IS_MX6(this) ? 2 : 1);
 	if (ret)
 		goto err_out;
 
 	ret = nand_boot_init(this);
 	if (ret)
 		goto err_nand_cleanup;
-	ret = chip->scan_bbt(mtd);
+	ret = nand_create_bbt(chip);
 	if (ret)
 		goto err_nand_cleanup;
 
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
index 6aa10d6962d6..69cd0cbde4f2 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
@@ -1,18 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2010-2011 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef __DRIVERS_MTD_NAND_GPMI_NAND_H
 #define __DRIVERS_MTD_NAND_GPMI_NAND_H
diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c
index a1e009c8e556..950dc7789296 100644
--- a/drivers/mtd/nand/raw/hisi504_nand.c
+++ b/drivers/mtd/nand/raw/hisi504_nand.c
@@ -709,9 +709,50 @@ static int hisi_nfc_ecc_probe(struct hinfc_host *host)
 	return 0;
 }
 
+static int hisi_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct hinfc_host *host = nand_get_controller_data(chip);
+	int flag;
+
+	host->buffer = dmam_alloc_coherent(host->dev,
+					   mtd->writesize + mtd->oobsize,
+					   &host->dma_buffer, GFP_KERNEL);
+	if (!host->buffer)
+		return -ENOMEM;
+
+	host->dma_oob = host->dma_buffer + mtd->writesize;
+	memset(host->buffer, 0xff, mtd->writesize + mtd->oobsize);
+
+	flag = hinfc_read(host, HINFC504_CON);
+	flag &= ~(HINFC504_CON_PAGESIZE_MASK << HINFC504_CON_PAGEISZE_SHIFT);
+	switch (mtd->writesize) {
+	case 2048:
+		flag |= (0x001 << HINFC504_CON_PAGEISZE_SHIFT);
+		break;
+	/*
+	 * TODO: add more pagesize support,
+	 * default pagesize has been set in hisi_nfc_host_init
+	 */
+	default:
+		dev_err(host->dev, "NON-2KB page size nand flash\n");
+		return -EINVAL;
+	}
+	hinfc_write(host, flag, HINFC504_CON);
+
+	if (chip->ecc.mode == NAND_ECC_HW)
+		hisi_nfc_ecc_probe(host);
+
+	return 0;
+}
+
+static const struct nand_controller_ops hisi_nfc_controller_ops = {
+	.attach_chip = hisi_nfc_attach_chip,
+};
+
 static int hisi_nfc_probe(struct platform_device *pdev)
 {
-	int ret = 0, irq, flag, max_chips = HINFC504_MAX_CHIP;
+	int ret = 0, irq, max_chips = HINFC504_MAX_CHIP;
 	struct device *dev = &pdev->dev;
 	struct hinfc_host *host;
 	struct nand_chip  *chip;
@@ -769,42 +810,11 @@ static int hisi_nfc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = nand_scan_ident(mtd, max_chips, NULL);
+	chip->dummy_controller.ops = &hisi_nfc_controller_ops;
+	ret = nand_scan(mtd, max_chips);
 	if (ret)
 		return ret;
 
-	host->buffer = dmam_alloc_coherent(dev, mtd->writesize + mtd->oobsize,
-		&host->dma_buffer, GFP_KERNEL);
-	if (!host->buffer)
-		return -ENOMEM;
-
-	host->dma_oob = host->dma_buffer + mtd->writesize;
-	memset(host->buffer, 0xff, mtd->writesize + mtd->oobsize);
-
-	flag = hinfc_read(host, HINFC504_CON);
-	flag &= ~(HINFC504_CON_PAGESIZE_MASK << HINFC504_CON_PAGEISZE_SHIFT);
-	switch (mtd->writesize) {
-	case 2048:
-		flag |= (0x001 << HINFC504_CON_PAGEISZE_SHIFT); break;
-	/*
-	 * TODO: add more pagesize support,
-	 * default pagesize has been set in hisi_nfc_host_init
-	 */
-	default:
-		dev_err(dev, "NON-2KB page size nand flash\n");
-		return -EINVAL;
-	}
-	hinfc_write(host, flag, HINFC504_CON);
-
-	if (chip->ecc.mode == NAND_ECC_HW)
-		hisi_nfc_ecc_probe(host);
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
-		return ret;
-	}
-
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "Err MTD partition=%d\n", ret);
diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index 613b00a9604b..a7515452bc59 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -23,9 +24,9 @@
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
-#include <asm/mach-jz4740/jz4740_nand.h>
+#include <linux/platform_data/jz4740/jz4740_nand.h>
 
 #define JZ_REG_NAND_CTRL	0x50
 #define JZ_REG_NAND_ECC_CTRL	0x100
@@ -330,7 +331,7 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 
 	if (chipnr == 0) {
 		/* Detect first chip. */
-		ret = nand_scan_ident(mtd, 1, NULL);
+		ret = nand_scan(mtd, 1);
 		if (ret)
 			goto notfound_id;
 
@@ -355,7 +356,7 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 		mtd->size += chip->chipsize;
 	}
 
-	dev_info(&pdev->dev, "Found chip %i on bank %i\n", chipnr, bank);
+	dev_info(&pdev->dev, "Found chip %zu on bank %i\n", chipnr, bank);
 	return 0;
 
 notfound_id:
@@ -367,6 +368,24 @@ notfound_id:
 	return ret;
 }
 
+static int jz_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct device *dev = mtd->dev.parent;
+	struct jz_nand_platform_data *pdata = dev_get_platdata(dev);
+	struct platform_device *pdev = to_platform_device(dev);
+
+	if (pdata && pdata->ident_callback)
+		pdata->ident_callback(pdev, mtd, &pdata->partitions,
+				      &pdata->num_partitions);
+
+	return 0;
+}
+
+static const struct nand_controller_ops jz_nand_controller_ops = {
+	.attach_chip = jz_nand_attach_chip,
+};
+
 static int jz_nand_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -410,6 +429,7 @@ static int jz_nand_probe(struct platform_device *pdev)
 	chip->chip_delay = 50;
 	chip->cmd_ctrl = jz_nand_cmd_ctrl;
 	chip->select_chip = jz_nand_select_chip;
+	chip->dummy_controller.ops = &jz_nand_controller_ops;
 
 	if (nand->busy_gpio)
 		chip->dev_ready = jz_nand_dev_ready;
@@ -455,33 +475,20 @@ static int jz_nand_probe(struct platform_device *pdev)
 		goto err_iounmap_mmio;
 	}
 
-	if (pdata && pdata->ident_callback) {
-		pdata->ident_callback(pdev, mtd, &pdata->partitions,
-					&pdata->num_partitions);
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(&pdev->dev,  "Failed to scan NAND\n");
-		goto err_unclaim_banks;
-	}
-
-	ret = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata ? pdata->partitions : NULL,
-					pdata ? pdata->num_partitions : 0);
+	ret = mtd_device_register(mtd, pdata ? pdata->partitions : NULL,
+				  pdata ? pdata->num_partitions : 0);
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to add mtd device\n");
-		goto err_nand_release;
+		goto err_cleanup_nand;
 	}
 
 	dev_info(&pdev->dev, "Successfully registered JZ4740 NAND driver\n");
 
 	return 0;
 
-err_nand_release:
-	nand_release(mtd);
-err_unclaim_banks:
+err_cleanup_nand:
+	nand_cleanup(chip);
 	while (chipnr--) {
 		unsigned char bank = nand->banks[chipnr];
 		jz_nand_iounmap_resource(nand->bank_mem[bank - 1],
diff --git a/drivers/mtd/nand/raw/jz4780_nand.c b/drivers/mtd/nand/raw/jz4780_nand.c
index e69f6ae4c539..db4fa60bd52a 100644
--- a/drivers/mtd/nand/raw/jz4780_nand.c
+++ b/drivers/mtd/nand/raw/jz4780_nand.c
@@ -44,7 +44,7 @@ struct jz4780_nand_cs {
 struct jz4780_nand_controller {
 	struct device *dev;
 	struct jz4780_bch *bch;
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	unsigned int num_banks;
 	struct list_head chips;
 	int selected;
@@ -65,7 +65,8 @@ static inline struct jz4780_nand_chip *to_jz4780_nand_chip(struct mtd_info *mtd)
 	return container_of(mtd_to_nand(mtd), struct jz4780_nand_chip, chip);
 }
 
-static inline struct jz4780_nand_controller *to_jz4780_nand_controller(struct nand_hw_control *ctrl)
+static inline struct jz4780_nand_controller
+*to_jz4780_nand_controller(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct jz4780_nand_controller, controller);
 }
@@ -157,9 +158,8 @@ static int jz4780_nand_ecc_correct(struct mtd_info *mtd, u8 *dat,
 	return jz4780_bch_correct(nfc->bch, &params, dat, read_ecc);
 }
 
-static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *dev)
+static int jz4780_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct jz4780_nand_controller *nfc = to_jz4780_nand_controller(chip->controller);
 	int eccbytes;
@@ -170,7 +170,8 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	switch (chip->ecc.mode) {
 	case NAND_ECC_HW:
 		if (!nfc->bch) {
-			dev_err(dev, "HW BCH selected, but BCH controller not found\n");
+			dev_err(nfc->dev,
+				"HW BCH selected, but BCH controller not found\n");
 			return -ENODEV;
 		}
 
@@ -179,15 +180,16 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 		chip->ecc.correct = jz4780_nand_ecc_correct;
 		/* fall through */
 	case NAND_ECC_SOFT:
-		dev_info(dev, "using %s (strength %d, size %d, bytes %d)\n",
-			(nfc->bch) ? "hardware BCH" : "software ECC",
-			chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
+		dev_info(nfc->dev, "using %s (strength %d, size %d, bytes %d)\n",
+			 (nfc->bch) ? "hardware BCH" : "software ECC",
+			 chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
 		break;
 	case NAND_ECC_NONE:
-		dev_info(dev, "not using ECC\n");
+		dev_info(nfc->dev, "not using ECC\n");
 		break;
 	default:
-		dev_err(dev, "ECC mode %d not supported\n", chip->ecc.mode);
+		dev_err(nfc->dev, "ECC mode %d not supported\n",
+			chip->ecc.mode);
 		return -EINVAL;
 	}
 
@@ -199,7 +201,7 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	eccbytes = mtd->writesize / chip->ecc.size * chip->ecc.bytes;
 
 	if (eccbytes > mtd->oobsize - 2) {
-		dev_err(dev,
+		dev_err(nfc->dev,
 			"invalid ECC config: required %d ECC bytes, but only %d are available",
 			eccbytes, mtd->oobsize - 2);
 		return -EINVAL;
@@ -210,6 +212,10 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	return 0;
 }
 
+static const struct nand_controller_ops jz4780_nand_controller_ops = {
+	.attach_chip = jz4780_nand_attach_chip,
+};
+
 static int jz4780_nand_init_chip(struct platform_device *pdev,
 				struct jz4780_nand_controller *nfc,
 				struct device_node *np,
@@ -279,15 +285,8 @@ static int jz4780_nand_init_chip(struct platform_device *pdev,
 	chip->controller = &nfc->controller;
 	nand_set_flash_node(chip, np);
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	ret = jz4780_nand_init_ecc(nand, dev);
-	if (ret)
-		return ret;
-
-	ret = nand_scan_tail(mtd);
+	chip->controller->ops = &jz4780_nand_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
@@ -368,7 +367,7 @@ static int jz4780_nand_probe(struct platform_device *pdev)
 	nfc->dev = dev;
 	nfc->num_banks = num_banks;
 
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
 	INIT_LIST_HEAD(&nfc->chips);
 
 	ret = jz4780_nand_init_chips(nfc, pdev);
diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 052d123a8304..e82abada130a 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -184,6 +184,7 @@ static struct nand_bbt_descr lpc32xx_nand_bbt_mirror = {
 };
 
 struct lpc32xx_nand_host {
+	struct platform_device	*pdev;
 	struct nand_chip	nand_chip;
 	struct lpc32xx_mlc_platform_data *pdata;
 	struct clk		*clk;
@@ -653,6 +654,32 @@ static struct lpc32xx_nand_cfg_mlc *lpc32xx_parse_dt(struct device *dev)
 	return ncfg;
 }
 
+static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
+	struct device *dev = &host->pdev->dev;
+
+	host->dma_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL);
+	if (!host->dma_buf)
+		return -ENOMEM;
+
+	host->dummy_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL);
+	if (!host->dummy_buf)
+		return -ENOMEM;
+
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.size = 512;
+	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
+	host->mlcsubpages = mtd->writesize / 512;
+
+	return 0;
+}
+
+static const struct nand_controller_ops lpc32xx_nand_controller_ops = {
+	.attach_chip = lpc32xx_nand_attach_chip,
+};
+
 /*
  * Probe for NAND controller
  */
@@ -669,6 +696,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	if (!host)
 		return -ENOMEM;
 
+	host->pdev = pdev;
+
 	rc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->io_base = devm_ioremap_resource(&pdev->dev, rc);
 	if (IS_ERR(host->io_base))
@@ -748,31 +777,6 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 		}
 	}
 
-	/*
-	 * Scan to find existance of the device and
-	 * Get the type of NAND device SMALL block or LARGE block
-	 */
-	res = nand_scan_ident(mtd, 1, NULL);
-	if (res)
-		goto release_dma_chan;
-
-	host->dma_buf = devm_kzalloc(&pdev->dev, mtd->writesize, GFP_KERNEL);
-	if (!host->dma_buf) {
-		res = -ENOMEM;
-		goto release_dma_chan;
-	}
-
-	host->dummy_buf = devm_kzalloc(&pdev->dev, mtd->writesize, GFP_KERNEL);
-	if (!host->dummy_buf) {
-		res = -ENOMEM;
-		goto release_dma_chan;
-	}
-
-	nand_chip->ecc.mode = NAND_ECC_HW;
-	nand_chip->ecc.size = 512;
-	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
-	host->mlcsubpages = mtd->writesize / 512;
-
 	/* initially clear interrupt status */
 	readb(MLC_IRQ_SR(host->io_base));
 
@@ -794,10 +798,11 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	}
 
 	/*
-	 * Fills out all the uninitialized function pointers with the defaults
-	 * And scans for a bad block table if appropriate.
+	 * Scan to find existence of the device and get the type of NAND device:
+	 * SMALL block or LARGE block.
 	 */
-	res = nand_scan_tail(mtd);
+	nand_chip->dummy_controller.ops = &lpc32xx_nand_controller_ops;
+	res = nand_scan(mtd, 1);
 	if (res)
 		goto free_irq;
 
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index 42820aa1abab..a4e8b7e75135 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -779,6 +779,46 @@ static struct lpc32xx_nand_cfg_slc *lpc32xx_parse_dt(struct device *dev)
 	return ncfg;
 }
 
+static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
+
+	/* OOB and ECC CPU and DMA work areas */
+	host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE);
+
+	/*
+	 * Small page FLASH has a unique OOB layout, but large and huge
+	 * page FLASH use the standard layout. Small page FLASH uses a
+	 * custom BBT marker layout.
+	 */
+	if (mtd->writesize <= 512)
+		mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
+
+	/* These sizes remain the same regardless of page size */
+	chip->ecc.size = 256;
+	chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
+	chip->ecc.prepad = 0;
+	chip->ecc.postpad = 0;
+
+	/*
+	 * Use a custom BBT marker setup for small page FLASH that
+	 * won't interfere with the ECC layout. Large and huge page
+	 * FLASH use the standard layout.
+	 */
+	if ((chip->bbt_options & NAND_BBT_USE_FLASH) &&
+	    mtd->writesize <= 512) {
+		chip->bbt_td = &bbt_smallpage_main_descr;
+		chip->bbt_md = &bbt_smallpage_mirror_descr;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops lpc32xx_nand_controller_ops = {
+	.attach_chip = lpc32xx_nand_attach_chip,
+};
+
 /*
  * Probe for NAND controller
  */
@@ -884,41 +924,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	}
 
 	/* Find NAND device */
-	res = nand_scan_ident(mtd, 1, NULL);
-	if (res)
-		goto release_dma;
-
-	/* OOB and ECC CPU and DMA work areas */
-	host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE);
-
-	/*
-	 * Small page FLASH has a unique OOB layout, but large and huge
-	 * page FLASH use the standard layout. Small page FLASH uses a
-	 * custom BBT marker layout.
-	 */
-	if (mtd->writesize <= 512)
-		mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
-
-	/* These sizes remain the same regardless of page size */
-	chip->ecc.size = 256;
-	chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
-	chip->ecc.prepad = chip->ecc.postpad = 0;
-
-	/*
-	 * Use a custom BBT marker setup for small page FLASH that
-	 * won't interfere with the ECC layout. Large and huge page
-	 * FLASH use the standard layout.
-	 */
-	if ((chip->bbt_options & NAND_BBT_USE_FLASH) &&
-	    mtd->writesize <= 512) {
-		chip->bbt_td = &bbt_smallpage_main_descr;
-		chip->bbt_md = &bbt_smallpage_mirror_descr;
-	}
-
-	/*
-	 * Fills out all the uninitialized function pointers with the defaults
-	 */
-	res = nand_scan_tail(mtd);
+	chip->dummy_controller.ops = &lpc32xx_nand_controller_ops;
+	res = nand_scan(mtd, 1);
 	if (res)
 		goto release_dma;
 
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index ebb1d141b900..7af4d6213ee5 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -318,7 +318,7 @@ struct marvell_nfc_caps {
  * @dma_buf:		32-bit aligned buffer for DMA transfers (NFCv1 only)
  */
 struct marvell_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct device *dev;
 	void __iomem *regs;
 	struct clk *core_clk;
@@ -335,7 +335,7 @@ struct marvell_nfc {
 	u8 *dma_buf;
 };
 
-static inline struct marvell_nfc *to_marvell_nfc(struct nand_hw_control *ctrl)
+static inline struct marvell_nfc *to_marvell_nfc(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct marvell_nfc, controller);
 }
@@ -650,11 +650,6 @@ static void marvell_nfc_select_chip(struct mtd_info *mtd, int die_nr)
 		return;
 	}
 
-	/*
-	 * Do not change the timing registers when using the DT property
-	 * marvell,nand-keep-config; in that case ->ndtr0 and ->ndtr1 from the
-	 * marvell_nand structure are supposedly empty.
-	 */
 	writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
 	writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
 
@@ -2157,6 +2152,7 @@ static int marvell_nand_ecc_init(struct mtd_info *mtd,
 		break;
 	case NAND_ECC_NONE:
 	case NAND_ECC_SOFT:
+	case NAND_ECC_ON_DIE:
 		if (!nfc->caps->is_nfcv2 && mtd->writesize != SZ_512 &&
 		    mtd->writesize != SZ_2K) {
 			dev_err(nfc->dev, "NFCv1 cannot write %d bytes pages\n",
@@ -2294,6 +2290,111 @@ static int marvell_nfc_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	return 0;
 }
 
+static int marvell_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip);
+	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
+	struct pxa3xx_nand_platform_data *pdata = dev_get_platdata(nfc->dev);
+	int ret;
+
+	if (pdata && pdata->flash_bbt)
+		chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		/*
+		 * We'll use a bad block table stored in-flash and don't
+		 * allow writing the bad block marker to the flash.
+		 */
+		chip->bbt_options |= NAND_BBT_NO_OOB_BBM;
+		chip->bbt_td = &bbt_main_descr;
+		chip->bbt_md = &bbt_mirror_descr;
+	}
+
+	/* Save the chip-specific fields of NDCR */
+	marvell_nand->ndcr = NDCR_PAGE_SZ(mtd->writesize);
+	if (chip->options & NAND_BUSWIDTH_16)
+		marvell_nand->ndcr |= NDCR_DWIDTH_M | NDCR_DWIDTH_C;
+
+	/*
+	 * On small page NANDs, only one cycle is needed to pass the
+	 * column address.
+	 */
+	if (mtd->writesize <= 512) {
+		marvell_nand->addr_cyc = 1;
+	} else {
+		marvell_nand->addr_cyc = 2;
+		marvell_nand->ndcr |= NDCR_RA_START;
+	}
+
+	/*
+	 * Now add the number of cycles needed to pass the row
+	 * address.
+	 *
+	 * Addressing a chip using CS 2 or 3 should also need the third row
+	 * cycle but due to inconsistance in the documentation and lack of
+	 * hardware to test this situation, this case is not supported.
+	 */
+	if (chip->options & NAND_ROW_ADDR_3)
+		marvell_nand->addr_cyc += 3;
+	else
+		marvell_nand->addr_cyc += 2;
+
+	if (pdata) {
+		chip->ecc.size = pdata->ecc_step_size;
+		chip->ecc.strength = pdata->ecc_strength;
+	}
+
+	ret = marvell_nand_ecc_init(mtd, &chip->ecc);
+	if (ret) {
+		dev_err(nfc->dev, "ECC init failed: %d\n", ret);
+		return ret;
+	}
+
+	if (chip->ecc.mode == NAND_ECC_HW) {
+		/*
+		 * Subpage write not available with hardware ECC, prohibit also
+		 * subpage read as in userspace subpage access would still be
+		 * allowed and subpage write, if used, would lead to numerous
+		 * uncorrectable ECC errors.
+		 */
+		chip->options |= NAND_NO_SUBPAGE_WRITE;
+	}
+
+	if (pdata || nfc->caps->legacy_of_bindings) {
+		/*
+		 * We keep the MTD name unchanged to avoid breaking platforms
+		 * where the MTD cmdline parser is used and the bootloader
+		 * has not been updated to use the new naming scheme.
+		 */
+		mtd->name = "pxa3xx_nand-0";
+	} else if (!mtd->name) {
+		/*
+		 * If the new bindings are used and the bootloader has not been
+		 * updated to pass a new mtdparts parameter on the cmdline, you
+		 * should define the following property in your NAND node, ie:
+		 *
+		 *	label = "main-storage";
+		 *
+		 * This way, mtd->name will be set by the core when
+		 * nand_set_flash_node() is called.
+		 */
+		mtd->name = devm_kasprintf(nfc->dev, GFP_KERNEL,
+					   "%s:nand.%d", dev_name(nfc->dev),
+					   marvell_nand->sels[0].cs);
+		if (!mtd->name) {
+			dev_err(nfc->dev, "Failed to allocate mtd->name\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops marvell_nand_controller_ops = {
+	.attach_chip = marvell_nand_attach_chip,
+};
+
 static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 				  struct device_node *np)
 {
@@ -2436,105 +2537,10 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 	marvell_nand->ndtr1 = readl_relaxed(nfc->regs + NDTR1);
 
 	chip->options |= NAND_BUSWIDTH_AUTO;
-	ret = nand_scan_ident(mtd, marvell_nand->nsels, NULL);
-	if (ret) {
-		dev_err(dev, "could not identify the nand chip\n");
-		return ret;
-	}
-
-	if (pdata && pdata->flash_bbt)
-		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
-	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
-		/*
-		 * We'll use a bad block table stored in-flash and don't
-		 * allow writing the bad block marker to the flash.
-		 */
-		chip->bbt_options |= NAND_BBT_NO_OOB_BBM;
-		chip->bbt_td = &bbt_main_descr;
-		chip->bbt_md = &bbt_mirror_descr;
-	}
-
-	/* Save the chip-specific fields of NDCR */
-	marvell_nand->ndcr = NDCR_PAGE_SZ(mtd->writesize);
-	if (chip->options & NAND_BUSWIDTH_16)
-		marvell_nand->ndcr |= NDCR_DWIDTH_M | NDCR_DWIDTH_C;
-
-	/*
-	 * On small page NANDs, only one cycle is needed to pass the
-	 * column address.
-	 */
-	if (mtd->writesize <= 512) {
-		marvell_nand->addr_cyc = 1;
-	} else {
-		marvell_nand->addr_cyc = 2;
-		marvell_nand->ndcr |= NDCR_RA_START;
-	}
-
-	/*
-	 * Now add the number of cycles needed to pass the row
-	 * address.
-	 *
-	 * Addressing a chip using CS 2 or 3 should also need the third row
-	 * cycle but due to inconsistance in the documentation and lack of
-	 * hardware to test this situation, this case is not supported.
-	 */
-	if (chip->options & NAND_ROW_ADDR_3)
-		marvell_nand->addr_cyc += 3;
-	else
-		marvell_nand->addr_cyc += 2;
-
-	if (pdata) {
-		chip->ecc.size = pdata->ecc_step_size;
-		chip->ecc.strength = pdata->ecc_strength;
-	}
-
-	ret = marvell_nand_ecc_init(mtd, &chip->ecc);
-	if (ret) {
-		dev_err(dev, "ECC init failed: %d\n", ret);
-		return ret;
-	}
-
-	if (chip->ecc.mode == NAND_ECC_HW) {
-		/*
-		 * Subpage write not available with hardware ECC, prohibit also
-		 * subpage read as in userspace subpage access would still be
-		 * allowed and subpage write, if used, would lead to numerous
-		 * uncorrectable ECC errors.
-		 */
-		chip->options |= NAND_NO_SUBPAGE_WRITE;
-	}
-
-	if (pdata || nfc->caps->legacy_of_bindings) {
-		/*
-		 * We keep the MTD name unchanged to avoid breaking platforms
-		 * where the MTD cmdline parser is used and the bootloader
-		 * has not been updated to use the new naming scheme.
-		 */
-		mtd->name = "pxa3xx_nand-0";
-	} else if (!mtd->name) {
-		/*
-		 * If the new bindings are used and the bootloader has not been
-		 * updated to pass a new mtdparts parameter on the cmdline, you
-		 * should define the following property in your NAND node, ie:
-		 *
-		 *	label = "main-storage";
-		 *
-		 * This way, mtd->name will be set by the core when
-		 * nand_set_flash_node() is called.
-		 */
-		mtd->name = devm_kasprintf(nfc->dev, GFP_KERNEL,
-					   "%s:nand.%d", dev_name(nfc->dev),
-					   marvell_nand->sels[0].cs);
-		if (!mtd->name) {
-			dev_err(nfc->dev, "Failed to allocate mtd->name\n");
-			return -ENOMEM;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, marvell_nand->nsels);
 	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
+		dev_err(dev, "could not scan the nand chip\n");
 		return ret;
 	}
 
@@ -2612,8 +2618,6 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 						    dev);
 	struct dma_slave_config config = {};
 	struct resource *r;
-	dma_cap_mask_t mask;
-	struct pxad_param param;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_PXA_DMA)) {
@@ -2626,20 +2630,7 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 	if (ret)
 		return ret;
 
-	r = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (!r) {
-		dev_err(nfc->dev, "No resource defined for data DMA\n");
-		return -ENXIO;
-	}
-
-	param.drcmr = r->start;
-	param.prio = PXAD_PRIO_LOWEST;
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	nfc->dma_chan =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param, nfc->dev,
-						 "data");
+	nfc->dma_chan =	dma_request_slave_channel(nfc->dev, "data");
 	if (!nfc->dma_chan) {
 		dev_err(nfc->dev,
 			"Unable to request data DMA channel\n");
@@ -2677,6 +2668,21 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 	return 0;
 }
 
+static void marvell_nfc_reset(struct marvell_nfc *nfc)
+{
+	/*
+	 * ECC operations and interruptions are only enabled when specifically
+	 * needed. ECC shall not be activated in the early stages (fails probe).
+	 * Arbiter flag, even if marked as "reserved", must be set (empirical).
+	 * SPARE_EN bit must always be set or ECC bytes will not be at the same
+	 * offset in the read page and this will fail the protection.
+	 */
+	writel_relaxed(NDCR_ALL_INT | NDCR_ND_ARB_EN | NDCR_SPARE_EN |
+		       NDCR_RD_ID_CNT(NFCV1_READID_LEN), nfc->regs + NDCR);
+	writel_relaxed(0xFFFFFFFF, nfc->regs + NDSR);
+	writel_relaxed(0, nfc->regs + NDECCCTRL);
+}
+
 static int marvell_nfc_init(struct marvell_nfc *nfc)
 {
 	struct device_node *np = nfc->dev->of_node;
@@ -2715,17 +2721,7 @@ static int marvell_nfc_init(struct marvell_nfc *nfc)
 	if (!nfc->caps->is_nfcv2)
 		marvell_nfc_init_dma(nfc);
 
-	/*
-	 * ECC operations and interruptions are only enabled when specifically
-	 * needed. ECC shall not be activated in the early stages (fails probe).
-	 * Arbiter flag, even if marked as "reserved", must be set (empirical).
-	 * SPARE_EN bit must always be set or ECC bytes will not be at the same
-	 * offset in the read page and this will fail the protection.
-	 */
-	writel_relaxed(NDCR_ALL_INT | NDCR_ND_ARB_EN | NDCR_SPARE_EN |
-		       NDCR_RD_ID_CNT(NFCV1_READID_LEN), nfc->regs + NDCR);
-	writel_relaxed(0xFFFFFFFF, nfc->regs + NDSR);
-	writel_relaxed(0, nfc->regs + NDECCCTRL);
+	marvell_nfc_reset(nfc);
 
 	return 0;
 }
@@ -2744,7 +2740,8 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	nfc->dev = dev;
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
+	nfc->controller.ops = &marvell_nand_controller_ops;
 	INIT_LIST_HEAD(&nfc->chips);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -2772,17 +2769,19 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return ret;
 
 	nfc->reg_clk = devm_clk_get(&pdev->dev, "reg");
-	if (PTR_ERR(nfc->reg_clk) != -ENOENT) {
-		if (!IS_ERR(nfc->reg_clk)) {
-			ret = clk_prepare_enable(nfc->reg_clk);
-			if (ret)
-				goto unprepare_core_clk;
-		} else {
+	if (IS_ERR(nfc->reg_clk)) {
+		if (PTR_ERR(nfc->reg_clk) != -ENOENT) {
 			ret = PTR_ERR(nfc->reg_clk);
 			goto unprepare_core_clk;
 		}
+
+		nfc->reg_clk = NULL;
 	}
 
+	ret = clk_prepare_enable(nfc->reg_clk);
+	if (ret)
+		goto unprepare_core_clk;
+
 	marvell_nfc_disable_int(nfc, NDCR_ALL_INT);
 	marvell_nfc_clear_int(nfc, NDCR_ALL_INT);
 	ret = devm_request_irq(dev, irq, marvell_nfc_isr,
@@ -2840,6 +2839,49 @@ static int marvell_nfc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused marvell_nfc_suspend(struct device *dev)
+{
+	struct marvell_nfc *nfc = dev_get_drvdata(dev);
+	struct marvell_nand_chip *chip;
+
+	list_for_each_entry(chip, &nfc->chips, node)
+		marvell_nfc_wait_ndrun(&chip->chip);
+
+	clk_disable_unprepare(nfc->reg_clk);
+	clk_disable_unprepare(nfc->core_clk);
+
+	return 0;
+}
+
+static int __maybe_unused marvell_nfc_resume(struct device *dev)
+{
+	struct marvell_nfc *nfc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(nfc->core_clk);
+	if (ret < 0)
+		return ret;
+
+	ret = clk_prepare_enable(nfc->reg_clk);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Reset nfc->selected_chip so the next command will cause the timing
+	 * registers to be restored in marvell_nfc_select_chip().
+	 */
+	nfc->selected_chip = NULL;
+
+	/* Reset registers that have lost their contents */
+	marvell_nfc_reset(nfc);
+
+	return 0;
+}
+
+static const struct dev_pm_ops marvell_nfc_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(marvell_nfc_suspend, marvell_nfc_resume)
+};
+
 static const struct marvell_nfc_caps marvell_armada_8k_nfc_caps = {
 	.max_cs_nb = 4,
 	.max_rb_nb = 2,
@@ -2924,6 +2966,7 @@ static struct platform_driver marvell_nfc_driver = {
 	.driver	= {
 		.name		= "marvell-nfc",
 		.of_match_table = marvell_nfc_of_ids,
+		.pm		= &marvell_nfc_pm_ops,
 	},
 	.id_table = marvell_nfc_platform_ids,
 	.probe = marvell_nfc_probe,
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index 75c845adb050..57b5ed1699e3 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -145,7 +145,7 @@ struct mtk_nfc_clk {
 };
 
 struct mtk_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct mtk_ecc_config ecc_cfg;
 	struct mtk_nfc_clk clk;
 	struct mtk_ecc *ecc;
@@ -1250,13 +1250,54 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
 	return 0;
 }
 
+static int mtk_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct device *dev = mtd->dev.parent;
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	int len;
+	int ret;
+
+	if (chip->options & NAND_BUSWIDTH_16) {
+		dev_err(dev, "16bits buswidth not supported");
+		return -EINVAL;
+	}
+
+	/* store bbt magic in page, cause OOB is not protected */
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	ret = mtk_nfc_ecc_init(dev, mtd);
+	if (ret)
+		return ret;
+
+	ret = mtk_nfc_set_spare_per_sector(&mtk_nand->spare_per_sector, mtd);
+	if (ret)
+		return ret;
+
+	mtk_nfc_set_fdm(&mtk_nand->fdm, mtd);
+	mtk_nfc_set_bad_mark_ctl(&mtk_nand->bad_mark, mtd);
+
+	len = mtd->writesize + mtd->oobsize;
+	nfc->buffer = devm_kzalloc(dev, len, GFP_KERNEL);
+	if (!nfc->buffer)
+		return  -ENOMEM;
+
+	return 0;
+}
+
+static const struct nand_controller_ops mtk_nfc_controller_ops = {
+	.attach_chip = mtk_nfc_attach_chip,
+};
+
 static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 				  struct device_node *np)
 {
 	struct mtk_nfc_nand_chip *chip;
 	struct nand_chip *nand;
 	struct mtd_info *mtd;
-	int nsels, len;
+	int nsels;
 	u32 tmp;
 	int ret;
 	int i;
@@ -1324,40 +1365,11 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 
 	mtk_nfc_hw_init(nfc);
 
-	ret = nand_scan_ident(mtd, nsels, NULL);
-	if (ret)
-		return ret;
-
-	/* store bbt magic in page, cause OOB is not protected */
-	if (nand->bbt_options & NAND_BBT_USE_FLASH)
-		nand->bbt_options |= NAND_BBT_NO_OOB;
-
-	ret = mtk_nfc_ecc_init(dev, mtd);
-	if (ret)
-		return -EINVAL;
-
-	if (nand->options & NAND_BUSWIDTH_16) {
-		dev_err(dev, "16bits buswidth not supported");
-		return -EINVAL;
-	}
-
-	ret = mtk_nfc_set_spare_per_sector(&chip->spare_per_sector, mtd);
-	if (ret)
-		return ret;
-
-	mtk_nfc_set_fdm(&chip->fdm, mtd);
-	mtk_nfc_set_bad_mark_ctl(&chip->bad_mark, mtd);
-
-	len = mtd->writesize + mtd->oobsize;
-	nfc->buffer = devm_kzalloc(dev, len, GFP_KERNEL);
-	if (!nfc->buffer)
-		return  -ENOMEM;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, nsels);
 	if (ret)
 		return ret;
 
-	ret = mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "mtd parse partition error\n");
 		nand_release(mtd);
@@ -1443,6 +1455,7 @@ static int mtk_nfc_probe(struct platform_device *pdev)
 	spin_lock_init(&nfc->controller.lock);
 	init_waitqueue_head(&nfc->controller.wq);
 	INIT_LIST_HEAD(&nfc->chips);
+	nfc->controller.ops = &mtk_nfc_controller_ops;
 
 	/* probe defer if not ready */
 	nfc->ecc = of_mtk_ecc_get(np);
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 45786e707b7b..4c9214dea424 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
  * Copyright 2008 Sascha Hauer, kernel@pengutronix.de
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
  */
 
 #include <linux/delay.h>
@@ -34,8 +21,6 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-
-#include <asm/mach/flash.h>
 #include <linux/platform_data/mtd-mxc_nand.h>
 
 #define DRIVER_NAME "mxc_nand"
@@ -48,7 +33,7 @@
 #define NFC_V1_V2_CONFIG		(host->regs + 0x0a)
 #define NFC_V1_V2_ECC_STATUS_RESULT	(host->regs + 0x0c)
 #define NFC_V1_V2_RSLTMAIN_AREA		(host->regs + 0x0e)
-#define NFC_V1_V2_RSLTSPARE_AREA	(host->regs + 0x10)
+#define NFC_V21_RSLTSPARE_AREA		(host->regs + 0x10)
 #define NFC_V1_V2_WRPROT		(host->regs + 0x12)
 #define NFC_V1_UNLOCKSTART_BLKADDR	(host->regs + 0x14)
 #define NFC_V1_UNLOCKEND_BLKADDR	(host->regs + 0x16)
@@ -1274,6 +1259,9 @@ static void preset_v2(struct mtd_info *mtd)
 	writew(config1, NFC_V1_V2_CONFIG1);
 	/* preset operation */
 
+	/* spare area size in 16-bit half-words */
+	writew(mtd->oobsize / 2, NFC_V21_RSLTSPARE_AREA);
+
 	/* Unlock the internal RAM Buffer */
 	writew(0x2, NFC_V1_V2_CONFIG);
 
@@ -1683,7 +1671,7 @@ static const struct of_device_id mxcnd_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, mxcnd_dt_ids);
 
-static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
+static int mxcnd_probe_dt(struct mxc_nand_host *host)
 {
 	struct device_node *np = host->dev->of_node;
 	const struct of_device_id *of_id =
@@ -1697,12 +1685,80 @@ static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
 	return 0;
 }
 #else
-static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
+static int mxcnd_probe_dt(struct mxc_nand_host *host)
 {
 	return 1;
 }
 #endif
 
+static int mxcnd_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct mxc_nand_host *host = nand_get_controller_data(chip);
+	struct device *dev = mtd->dev.parent;
+
+	switch (chip->ecc.mode) {
+	case NAND_ECC_HW:
+		chip->ecc.read_page = mxc_nand_read_page;
+		chip->ecc.read_page_raw = mxc_nand_read_page_raw;
+		chip->ecc.read_oob = mxc_nand_read_oob;
+		chip->ecc.write_page = mxc_nand_write_page_ecc;
+		chip->ecc.write_page_raw = mxc_nand_write_page_raw;
+		chip->ecc.write_oob = mxc_nand_write_oob;
+		break;
+
+	case NAND_ECC_SOFT:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		chip->bbt_td = &bbt_main_descr;
+		chip->bbt_md = &bbt_mirror_descr;
+	}
+
+	/* Allocate the right size buffer now */
+	devm_kfree(dev, (void *)host->data_buf);
+	host->data_buf = devm_kzalloc(dev, mtd->writesize + mtd->oobsize,
+				      GFP_KERNEL);
+	if (!host->data_buf)
+		return -ENOMEM;
+
+	/* Call preset again, with correct writesize chip time */
+	host->devtype_data->preset(mtd);
+
+	if (!chip->ecc.bytes) {
+		if (host->eccsize == 8)
+			chip->ecc.bytes = 18;
+		else if (host->eccsize == 4)
+			chip->ecc.bytes = 9;
+	}
+
+	/*
+	 * Experimentation shows that i.MX NFC can only handle up to 218 oob
+	 * bytes. Limit used_oobsize to 218 so as to not confuse copy_spare()
+	 * into copying invalid data to/from the spare IO buffer, as this
+	 * might cause ECC data corruption when doing sub-page write to a
+	 * partially written page.
+	 */
+	host->used_oobsize = min(mtd->oobsize, 218U);
+
+	if (chip->ecc.mode == NAND_ECC_HW) {
+		if (is_imx21_nfc(host) || is_imx27_nfc(host))
+			chip->ecc.strength = 1;
+		else
+			chip->ecc.strength = (host->eccsize == 4) ? 4 : 8;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops mxcnd_controller_ops = {
+	.attach_chip = mxcnd_attach_chip,
+};
+
 static int mxcnd_probe(struct platform_device *pdev)
 {
 	struct nand_chip *this;
@@ -1842,71 +1898,9 @@ static int mxcnd_probe(struct platform_device *pdev)
 		host->devtype_data->irq_control(host, 1);
 	}
 
-	/* first scan to find the device and get the page size */
-	err = nand_scan_ident(mtd, is_imx25_nfc(host) ? 4 : 1, NULL);
-	if (err)
-		goto escan;
-
-	switch (this->ecc.mode) {
-	case NAND_ECC_HW:
-		this->ecc.read_page = mxc_nand_read_page;
-		this->ecc.read_page_raw = mxc_nand_read_page_raw;
-		this->ecc.read_oob = mxc_nand_read_oob;
-		this->ecc.write_page = mxc_nand_write_page_ecc;
-		this->ecc.write_page_raw = mxc_nand_write_page_raw;
-		this->ecc.write_oob = mxc_nand_write_oob;
-		break;
-
-	case NAND_ECC_SOFT:
-		break;
-
-	default:
-		err = -EINVAL;
-		goto escan;
-	}
-
-	if (this->bbt_options & NAND_BBT_USE_FLASH) {
-		this->bbt_td = &bbt_main_descr;
-		this->bbt_md = &bbt_mirror_descr;
-	}
-
-	/* allocate the right size buffer now */
-	devm_kfree(&pdev->dev, (void *)host->data_buf);
-	host->data_buf = devm_kzalloc(&pdev->dev, mtd->writesize + mtd->oobsize,
-					GFP_KERNEL);
-	if (!host->data_buf) {
-		err = -ENOMEM;
-		goto escan;
-	}
-
-	/* Call preset again, with correct writesize this time */
-	host->devtype_data->preset(mtd);
-
-	if (!this->ecc.bytes) {
-		if (host->eccsize == 8)
-			this->ecc.bytes = 18;
-		else if (host->eccsize == 4)
-			this->ecc.bytes = 9;
-	}
-
-	/*
-	 * Experimentation shows that i.MX NFC can only handle up to 218 oob
-	 * bytes. Limit used_oobsize to 218 so as to not confuse copy_spare()
-	 * into copying invalid data to/from the spare IO buffer, as this
-	 * might cause ECC data corruption when doing sub-page write to a
-	 * partially written page.
-	 */
-	host->used_oobsize = min(mtd->oobsize, 218U);
-
-	if (this->ecc.mode == NAND_ECC_HW) {
-		if (is_imx21_nfc(host) || is_imx27_nfc(host))
-			this->ecc.strength = 1;
-		else
-			this->ecc.strength = (host->eccsize == 4) ? 4 : 8;
-	}
-
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	/* Scan the NAND device */
+	this->dummy_controller.ops = &mxcnd_controller_ops;
+	err = nand_scan(mtd, is_imx25_nfc(host) ? 4 : 1);
 	if (err)
 		goto escan;
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 10c4f9919850..d527e448ce19 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -440,7 +440,7 @@ static int nand_block_bad(struct mtd_info *mtd, loff_t ofs)
 
 	for (; page < page_end; page++) {
 		res = chip->ecc.read_oob(mtd, chip, page);
-		if (res)
+		if (res < 0)
 			return res;
 
 		bad = chip->oob_poi[chip->badblockpos];
@@ -2668,8 +2668,8 @@ static bool nand_subop_instr_is_valid(const struct nand_subop *subop,
 	return subop && instr_idx < subop->ninstrs;
 }
 
-static int nand_subop_get_start_off(const struct nand_subop *subop,
-				    unsigned int instr_idx)
+static unsigned int nand_subop_get_start_off(const struct nand_subop *subop,
+					     unsigned int instr_idx)
 {
 	if (instr_idx)
 		return 0;
@@ -2688,12 +2688,12 @@ static int nand_subop_get_start_off(const struct nand_subop *subop,
  *
  * Given an address instruction, returns the offset of the first cycle to issue.
  */
-int nand_subop_get_addr_start_off(const struct nand_subop *subop,
-				  unsigned int instr_idx)
+unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop,
+					   unsigned int instr_idx)
 {
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR))
+		return 0;
 
 	return nand_subop_get_start_off(subop, instr_idx);
 }
@@ -2710,14 +2710,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_addr_start_off);
  *
  * Given an address instruction, returns the number of address cycle to issue.
  */
-int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
-				unsigned int instr_idx)
+unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
+					 unsigned int instr_idx)
 {
 	int start_off, end_off;
 
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR))
+		return 0;
 
 	start_off = nand_subop_get_addr_start_off(subop, instr_idx);
 
@@ -2742,12 +2742,12 @@ EXPORT_SYMBOL_GPL(nand_subop_get_num_addr_cyc);
  *
  * Given a data instruction, returns the offset to start from.
  */
-int nand_subop_get_data_start_off(const struct nand_subop *subop,
-				  unsigned int instr_idx)
+unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop,
+					   unsigned int instr_idx)
 {
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    !nand_instr_is_data(&subop->instrs[instr_idx]))
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    !nand_instr_is_data(&subop->instrs[instr_idx])))
+		return 0;
 
 	return nand_subop_get_start_off(subop, instr_idx);
 }
@@ -2764,14 +2764,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_data_start_off);
  *
  * Returns the length of the chunk of data to send/receive.
  */
-int nand_subop_get_data_len(const struct nand_subop *subop,
-			    unsigned int instr_idx)
+unsigned int nand_subop_get_data_len(const struct nand_subop *subop,
+				     unsigned int instr_idx)
 {
 	int start_off = 0, end_off;
 
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    !nand_instr_is_data(&subop->instrs[instr_idx]))
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    !nand_instr_is_data(&subop->instrs[instr_idx])))
+		return 0;
 
 	start_off = nand_subop_get_data_start_off(subop, instr_idx);
 
@@ -2967,6 +2967,23 @@ int nand_check_erased_ecc_chunk(void *data, int datalen,
 EXPORT_SYMBOL(nand_check_erased_ecc_chunk);
 
 /**
+ * nand_read_page_raw_notsupp - dummy read raw page function
+ * @mtd: mtd info structure
+ * @chip: nand chip info structure
+ * @buf: buffer to store read data
+ * @oob_required: caller requires OOB data read to chip->oob_poi
+ * @page: page number to read
+ *
+ * Returns -ENOTSUPP unconditionally.
+ */
+int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+			       u8 *buf, int oob_required, int page)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_read_page_raw_notsupp);
+
+/**
  * nand_read_page_raw - [INTERN] read raw page data without ecc
  * @mtd: mtd info structure
  * @chip: nand chip info structure
@@ -3960,6 +3977,22 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from,
 	return ret;
 }
 
+/**
+ * nand_write_page_raw_notsupp - dummy raw page write function
+ * @mtd: mtd info structure
+ * @chip: nand chip info structure
+ * @buf: data buffer
+ * @oob_required: must write chip->oob_poi to OOB
+ * @page: page number to write
+ *
+ * Returns -ENOTSUPP unconditionally.
+ */
+int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+				const u8 *buf, int oob_required, int page)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_write_page_raw_notsupp);
 
 /**
  * nand_write_page_raw - [INTERN] raw page write function
@@ -4965,12 +4998,10 @@ static void nand_set_defaults(struct nand_chip *chip)
 		chip->write_byte = busw ? nand_write_byte16 : nand_write_byte;
 	if (!chip->read_buf || chip->read_buf == nand_read_buf)
 		chip->read_buf = busw ? nand_read_buf16 : nand_read_buf;
-	if (!chip->scan_bbt)
-		chip->scan_bbt = nand_default_bbt;
 
 	if (!chip->controller) {
-		chip->controller = &chip->hwcontrol;
-		nand_hw_control_init(chip->controller);
+		chip->controller = &chip->dummy_controller;
+		nand_controller_init(chip->controller);
 	}
 
 	if (!chip->buf_align)
@@ -5120,6 +5151,8 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_onfi_params *p;
+	struct onfi_params *onfi;
+	int onfi_version = 0;
 	char id[4];
 	int i, ret, val;
 
@@ -5168,30 +5201,35 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 		}
 	}
 
+	if (chip->manufacturer.desc && chip->manufacturer.desc->ops &&
+	    chip->manufacturer.desc->ops->fixup_onfi_param_page)
+		chip->manufacturer.desc->ops->fixup_onfi_param_page(chip, p);
+
 	/* Check version */
 	val = le16_to_cpu(p->revision);
-	if (val & (1 << 5))
-		chip->parameters.onfi.version = 23;
-	else if (val & (1 << 4))
-		chip->parameters.onfi.version = 22;
-	else if (val & (1 << 3))
-		chip->parameters.onfi.version = 21;
-	else if (val & (1 << 2))
-		chip->parameters.onfi.version = 20;
-	else if (val & (1 << 1))
-		chip->parameters.onfi.version = 10;
-
-	if (!chip->parameters.onfi.version) {
+	if (val & ONFI_VERSION_2_3)
+		onfi_version = 23;
+	else if (val & ONFI_VERSION_2_2)
+		onfi_version = 22;
+	else if (val & ONFI_VERSION_2_1)
+		onfi_version = 21;
+	else if (val & ONFI_VERSION_2_0)
+		onfi_version = 20;
+	else if (val & ONFI_VERSION_1_0)
+		onfi_version = 10;
+
+	if (!onfi_version) {
 		pr_info("unsupported ONFI version: %d\n", val);
 		goto free_onfi_param_page;
-	} else {
-		ret = 1;
 	}
 
 	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
 	sanitize_string(p->model, sizeof(p->model));
-	strncpy(chip->parameters.model, p->model,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(p->model, GFP_KERNEL);
+	if (!chip->parameters.model) {
+		ret = -ENOMEM;
+		goto free_onfi_param_page;
+	}
 
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
 
@@ -5219,7 +5257,7 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 	if (p->ecc_bits != 0xff) {
 		chip->ecc_strength_ds = p->ecc_bits;
 		chip->ecc_step_ds = 512;
-	} else if (chip->parameters.onfi.version >= 21 &&
+	} else if (onfi_version >= 21 &&
 		(le16_to_cpu(p->features) & ONFI_FEATURE_EXT_PARAM_PAGE)) {
 
 		/*
@@ -5246,19 +5284,33 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 		bitmap_set(chip->parameters.set_feature_list,
 			   ONFI_FEATURE_ADDR_TIMING_MODE, 1);
 	}
-	chip->parameters.onfi.tPROG = le16_to_cpu(p->t_prog);
-	chip->parameters.onfi.tBERS = le16_to_cpu(p->t_bers);
-	chip->parameters.onfi.tR = le16_to_cpu(p->t_r);
-	chip->parameters.onfi.tCCS = le16_to_cpu(p->t_ccs);
-	chip->parameters.onfi.async_timing_mode =
-		le16_to_cpu(p->async_timing_mode);
-	chip->parameters.onfi.vendor_revision =
-		le16_to_cpu(p->vendor_revision);
-	memcpy(chip->parameters.onfi.vendor, p->vendor,
-	       sizeof(p->vendor));
 
+	onfi = kzalloc(sizeof(*onfi), GFP_KERNEL);
+	if (!onfi) {
+		ret = -ENOMEM;
+		goto free_model;
+	}
+
+	onfi->version = onfi_version;
+	onfi->tPROG = le16_to_cpu(p->t_prog);
+	onfi->tBERS = le16_to_cpu(p->t_bers);
+	onfi->tR = le16_to_cpu(p->t_r);
+	onfi->tCCS = le16_to_cpu(p->t_ccs);
+	onfi->async_timing_mode = le16_to_cpu(p->async_timing_mode);
+	onfi->vendor_revision = le16_to_cpu(p->vendor_revision);
+	memcpy(onfi->vendor, p->vendor, sizeof(p->vendor));
+	chip->parameters.onfi = onfi;
+
+	/* Identification done, free the full ONFI parameter page and exit */
+	kfree(p);
+
+	return 1;
+
+free_model:
+	kfree(chip->parameters.model);
 free_onfi_param_page:
 	kfree(p);
+
 	return ret;
 }
 
@@ -5321,8 +5373,11 @@ static int nand_flash_detect_jedec(struct nand_chip *chip)
 
 	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
 	sanitize_string(p->model, sizeof(p->model));
-	strncpy(chip->parameters.model, p->model,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(p->model, GFP_KERNEL);
+	if (!chip->parameters.model) {
+		ret = -ENOMEM;
+		goto free_jedec_param_page;
+	}
 
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
 
@@ -5511,8 +5566,9 @@ static bool find_full_id_nand(struct nand_chip *chip,
 		chip->onfi_timing_mode_default =
 					type->onfi_timing_mode_default;
 
-		strncpy(chip->parameters.model, type->name,
-			sizeof(chip->parameters.model) - 1);
+		chip->parameters.model = kstrdup(type->name, GFP_KERNEL);
+		if (!chip->parameters.model)
+			return false;
 
 		return true;
 	}
@@ -5651,7 +5707,6 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 		}
 	}
 
-	chip->parameters.onfi.version = 0;
 	if (!type->name || !type->pagesize) {
 		/* Check if the chip is ONFI compliant */
 		ret = nand_flash_detect_onfi(chip);
@@ -5671,8 +5726,9 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 	if (!type->name)
 		return -ENODEV;
 
-	strncpy(chip->parameters.model, type->name,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(type->name, GFP_KERNEL);
+	if (!chip->parameters.model)
+		return -ENOMEM;
 
 	chip->chipsize = (uint64_t)type->chipsize << 20;
 
@@ -5702,7 +5758,9 @@ ident_done:
 			mtd->name);
 		pr_warn("bus width %d instead of %d bits\n", busw ? 16 : 8,
 			(chip->options & NAND_BUSWIDTH_16) ? 16 : 8);
-		return -EINVAL;
+		ret = -EINVAL;
+
+		goto free_detect_allocation;
 	}
 
 	nand_decode_bbm_options(chip);
@@ -5739,6 +5797,11 @@ ident_done:
 		(int)(chip->chipsize >> 20), nand_is_slc(chip) ? "SLC" : "MLC",
 		mtd->erasesize >> 10, mtd->writesize, mtd->oobsize);
 	return 0;
+
+free_detect_allocation:
+	kfree(chip->parameters.model);
+
+	return ret;
 }
 
 static const char * const nand_ecc_modes[] = {
@@ -5777,6 +5840,7 @@ static int of_get_nand_ecc_mode(struct device_node *np)
 static const char * const nand_ecc_algos[] = {
 	[NAND_ECC_HAMMING]	= "hamming",
 	[NAND_ECC_BCH]		= "bch",
+	[NAND_ECC_RS]		= "rs",
 };
 
 static int of_get_nand_ecc_algo(struct device_node *np)
@@ -5858,6 +5922,9 @@ static int nand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_bus_width(dn) == 16)
 		chip->options |= NAND_BUSWIDTH_16;
 
+	if (of_property_read_bool(dn, "nand-is-boot-medium"))
+		chip->options |= NAND_IS_BOOT_MEDIUM;
+
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
@@ -5885,7 +5952,7 @@ static int nand_dt_init(struct nand_chip *chip)
 }
 
 /**
- * nand_scan_ident - [NAND Interface] Scan for the NAND device
+ * nand_scan_ident - Scan for the NAND device
  * @mtd: MTD device structure
  * @maxchips: number of chips to scan for
  * @table: alternative NAND ID table
@@ -5893,9 +5960,13 @@ static int nand_dt_init(struct nand_chip *chip)
  * This is the first phase of the normal nand_scan() function. It reads the
  * flash ID and sets up MTD fields accordingly.
  *
+ * This helper used to be called directly from controller drivers that needed
+ * to tweak some ECC-related parameters before nand_scan_tail(). This separation
+ * prevented dynamic allocations during this phase which was unconvenient and
+ * as been banned for the benefit of the ->init_ecc()/cleanup_ecc() hooks.
  */
-int nand_scan_ident(struct mtd_info *mtd, int maxchips,
-		    struct nand_flash_dev *table)
+static int nand_scan_ident(struct mtd_info *mtd, int maxchips,
+			   struct nand_flash_dev *table)
 {
 	int i, nand_maf_id, nand_dev_id;
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -5969,7 +6040,12 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 
 	return 0;
 }
-EXPORT_SYMBOL(nand_scan_ident);
+
+static void nand_scan_ident_cleanup(struct nand_chip *chip)
+{
+	kfree(chip->parameters.model);
+	kfree(chip->parameters.onfi);
+}
 
 static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
 {
@@ -6077,24 +6153,17 @@ static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
  * by the controller and the calculated ECC bytes fit within the chip's OOB.
  * On success, the calculated ECC bytes is set.
  */
-int nand_check_ecc_caps(struct nand_chip *chip,
-			const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_check_ecc_caps(struct nand_chip *chip,
+		    const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
 	int preset_step = chip->ecc.size;
 	int preset_strength = chip->ecc.strength;
-	int nsteps, ecc_bytes;
+	int ecc_bytes, nsteps = mtd->writesize / preset_step;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
-	if (!preset_step || !preset_strength)
-		return -ENODATA;
-
-	nsteps = mtd->writesize / preset_step;
-
 	for (i = 0; i < caps->nstepinfos; i++) {
 		stepinfo = &caps->stepinfos[i];
 
@@ -6127,7 +6196,6 @@ int nand_check_ecc_caps(struct nand_chip *chip,
 
 	return -ENOTSUPP;
 }
-EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
 
 /**
  * nand_match_ecc_req - meet the chip's requirement with least ECC bytes
@@ -6139,8 +6207,9 @@ EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
  * number of ECC bytes (i.e. with the largest number of OOB-free bytes).
  * On success, the chosen ECC settings are set.
  */
-int nand_match_ecc_req(struct nand_chip *chip,
-		       const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_match_ecc_req(struct nand_chip *chip,
+		   const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
@@ -6151,9 +6220,6 @@ int nand_match_ecc_req(struct nand_chip *chip,
 	int best_ecc_bytes_total = INT_MAX;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
 	/* No information provided by the NAND chip */
 	if (!req_step || !req_strength)
 		return -ENOTSUPP;
@@ -6212,7 +6278,6 @@ int nand_match_ecc_req(struct nand_chip *chip,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nand_match_ecc_req);
 
 /**
  * nand_maximize_ecc - choose the max ECC strength available
@@ -6223,8 +6288,9 @@ EXPORT_SYMBOL_GPL(nand_match_ecc_req);
  * Choose the max ECC strength that is supported on the controller, and can fit
  * within the chip's OOB.  On success, the chosen ECC settings are set.
  */
-int nand_maximize_ecc(struct nand_chip *chip,
-		      const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_maximize_ecc(struct nand_chip *chip,
+		  const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
@@ -6234,9 +6300,6 @@ int nand_maximize_ecc(struct nand_chip *chip,
 	int best_strength, best_ecc_bytes;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
 	for (i = 0; i < caps->nstepinfos; i++) {
 		stepinfo = &caps->stepinfos[i];
 		step_size = stepinfo->stepsize;
@@ -6285,7 +6348,44 @@ int nand_maximize_ecc(struct nand_chip *chip,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nand_maximize_ecc);
+
+/**
+ * nand_ecc_choose_conf - Set the ECC strength and ECC step size
+ * @chip: nand chip info structure
+ * @caps: ECC engine caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * Choose the ECC configuration according to following logic
+ *
+ * 1. If both ECC step size and ECC strength are already set (usually by DT)
+ *    then check if it is supported by this controller.
+ * 2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength.
+ * 3. Otherwise, try to match the ECC step size and ECC strength closest
+ *    to the chip's requirement. If available OOB size can't fit the chip
+ *    requirement then fallback to the maximum ECC step size and ECC strength.
+ *
+ * On success, the chosen ECC settings are set.
+ */
+int nand_ecc_choose_conf(struct nand_chip *chip,
+			 const struct nand_ecc_caps *caps, int oobavail)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	if (WARN_ON(oobavail < 0 || oobavail > mtd->oobsize))
+		return -EINVAL;
+
+	if (chip->ecc.size && chip->ecc.strength)
+		return nand_check_ecc_caps(chip, caps, oobavail);
+
+	if (chip->ecc.options & NAND_ECC_MAXIMIZE)
+		return nand_maximize_ecc(chip, caps, oobavail);
+
+	if (!nand_match_ecc_req(chip, caps, oobavail))
+		return 0;
+
+	return nand_maximize_ecc(chip, caps, oobavail);
+}
+EXPORT_SYMBOL_GPL(nand_ecc_choose_conf);
 
 /*
  * Check if the chip configuration meet the datasheet requirements.
@@ -6322,14 +6422,14 @@ static bool nand_ecc_strength_good(struct mtd_info *mtd)
 }
 
 /**
- * nand_scan_tail - [NAND Interface] Scan for the NAND device
+ * nand_scan_tail - Scan for the NAND device
  * @mtd: MTD device structure
  *
  * This is the second phase of the normal nand_scan() function. It fills out
  * all the uninitialized function pointers with the defaults and scans for a
  * bad block table if appropriate.
  */
-int nand_scan_tail(struct mtd_info *mtd)
+static int nand_scan_tail(struct mtd_info *mtd)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
@@ -6636,7 +6736,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 		return 0;
 
 	/* Build bad block table */
-	ret = chip->scan_bbt(mtd);
+	ret = nand_create_bbt(chip);
 	if (ret)
 		goto err_nand_manuf_cleanup;
 
@@ -6653,24 +6753,27 @@ err_free_buf:
 
 	return ret;
 }
-EXPORT_SYMBOL(nand_scan_tail);
 
-/*
- * is_module_text_address() isn't exported, and it's mostly a pointless
- * test if this is a module _anyway_ -- they'd have to try _really_ hard
- * to call us from in-kernel code if the core NAND support is modular.
- */
-#ifdef MODULE
-#define caller_is_module() (1)
-#else
-#define caller_is_module() \
-	is_module_text_address((unsigned long)__builtin_return_address(0))
-#endif
+static int nand_attach(struct nand_chip *chip)
+{
+	if (chip->controller->ops && chip->controller->ops->attach_chip)
+		return chip->controller->ops->attach_chip(chip);
+
+	return 0;
+}
+
+static void nand_detach(struct nand_chip *chip)
+{
+	if (chip->controller->ops && chip->controller->ops->detach_chip)
+		chip->controller->ops->detach_chip(chip);
+}
 
 /**
  * nand_scan_with_ids - [NAND Interface] Scan for the NAND device
  * @mtd: MTD device structure
- * @maxchips: number of chips to scan for
+ * @maxchips: number of chips to scan for. @nand_scan_ident() will not be run if
+ *	      this parameter is zero (useful for specific drivers that must
+ *	      handle this part of the process themselves, e.g docg4).
  * @ids: optional flash IDs table
  *
  * This fills out all the uninitialized function pointers with the defaults.
@@ -6680,11 +6783,30 @@ EXPORT_SYMBOL(nand_scan_tail);
 int nand_scan_with_ids(struct mtd_info *mtd, int maxchips,
 		       struct nand_flash_dev *ids)
 {
+	struct nand_chip *chip = mtd_to_nand(mtd);
 	int ret;
 
-	ret = nand_scan_ident(mtd, maxchips, ids);
-	if (!ret)
-		ret = nand_scan_tail(mtd);
+	if (maxchips) {
+		ret = nand_scan_ident(mtd, maxchips, ids);
+		if (ret)
+			return ret;
+	}
+
+	ret = nand_attach(chip);
+	if (ret)
+		goto cleanup_ident;
+
+	ret = nand_scan_tail(mtd);
+	if (ret)
+		goto detach_chip;
+
+	return 0;
+
+detach_chip:
+	nand_detach(chip);
+cleanup_ident:
+	nand_scan_ident_cleanup(chip);
+
 	return ret;
 }
 EXPORT_SYMBOL(nand_scan_with_ids);
@@ -6712,7 +6834,14 @@ void nand_cleanup(struct nand_chip *chip)
 
 	/* Free manufacturer priv data. */
 	nand_manufacturer_cleanup(chip);
+
+	/* Free controller specific allocations after chip identification */
+	nand_detach(chip);
+
+	/* Free identification phase allocations */
+	nand_scan_ident_cleanup(chip);
 }
+
 EXPORT_SYMBOL_GPL(nand_cleanup);
 
 /**
diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c
index d9f4ceff2568..39db352f8757 100644
--- a/drivers/mtd/nand/raw/nand_bbt.c
+++ b/drivers/mtd/nand/raw/nand_bbt.c
@@ -1349,15 +1349,14 @@ static int nand_create_badblock_pattern(struct nand_chip *this)
 }
 
 /**
- * nand_default_bbt - [NAND Interface] Select a default bad block table for the device
- * @mtd: MTD device structure
+ * nand_create_bbt - [NAND Interface] Select a default bad block table for the device
+ * @this: NAND chip object
  *
  * This function selects the default bad block table support for the device and
  * calls the nand_scan_bbt function.
  */
-int nand_default_bbt(struct mtd_info *mtd)
+int nand_create_bbt(struct nand_chip *this)
 {
-	struct nand_chip *this = mtd_to_nand(mtd);
 	int ret;
 
 	/* Is a flash based bad block table requested? */
@@ -1383,8 +1382,9 @@ int nand_default_bbt(struct mtd_info *mtd)
 			return ret;
 	}
 
-	return nand_scan_bbt(mtd, this->badblock_pattern);
+	return nand_scan_bbt(nand_to_mtd(this), this->badblock_pattern);
 }
+EXPORT_SYMBOL(nand_create_bbt);
 
 /**
  * nand_isreserved_bbt - [NAND Interface] Check if a block is reserved
diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c
index d542908a0ebb..4ffbb26e76d6 100644
--- a/drivers/mtd/nand/raw/nand_hynix.c
+++ b/drivers/mtd/nand/raw/nand_hynix.c
@@ -100,6 +100,16 @@ static int hynix_nand_reg_write_op(struct nand_chip *chip, u8 addr, u8 val)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	u16 column = ((u16)addr << 8) | addr;
 
+	if (chip->exec_op) {
+		struct nand_op_instr instrs[] = {
+			NAND_OP_ADDR(1, &addr, 0),
+			NAND_OP_8BIT_DATA_OUT(1, &val, 0),
+		};
+		struct nand_operation op = NAND_OPERATION(instrs);
+
+		return nand_exec_op(chip, &op);
+	}
+
 	chip->cmdfunc(mtd, NAND_CMD_NONE, column, -1);
 	chip->write_byte(mtd, val);
 
@@ -473,6 +483,19 @@ static void hynix_nand_extract_oobsize(struct nand_chip *chip,
 			WARN(1, "Invalid OOB size");
 			break;
 		}
+
+		/*
+		 * The datasheet of H27UCG8T2BTR mentions that the "Redundant
+		 * Area Size" is encoded "per 8KB" (page size). This chip uses
+		 * a page size of 16KiB. The datasheet mentions an OOB size of
+		 * 1.280 bytes, but the OOB size encoded in the ID bytes (using
+		 * the existing logic above) is 640 bytes.
+		 * Update the OOB size for this chip by taking the value
+		 * determined above and scaling it to the actual page size (so
+		 * the actual OOB size for this chip is: 640 * 16k / 8k).
+		 */
+		if (chip->id.data[1] == 0xde)
+			mtd->oobsize *= mtd->writesize / SZ_8K;
 	}
 }
 
diff --git a/drivers/mtd/nand/raw/nand_macronix.c b/drivers/mtd/nand/raw/nand_macronix.c
index 7ed1f87e742a..49c546c97c6f 100644
--- a/drivers/mtd/nand/raw/nand_macronix.c
+++ b/drivers/mtd/nand/raw/nand_macronix.c
@@ -17,23 +17,47 @@
 
 #include <linux/mtd/rawnand.h>
 
+/*
+ * Macronix AC series does not support using SET/GET_FEATURES to change
+ * the timings unlike what is declared in the parameter page. Unflag
+ * this feature to avoid unnecessary downturns.
+ */
+static void macronix_nand_fix_broken_get_timings(struct nand_chip *chip)
+{
+	unsigned int i;
+	static const char * const broken_get_timings[] = {
+		"MX30LF1G18AC",
+		"MX30LF1G28AC",
+		"MX30LF2G18AC",
+		"MX30LF2G28AC",
+		"MX30LF4G18AC",
+		"MX30LF4G28AC",
+		"MX60LF8G18AC",
+	};
+
+	if (!chip->parameters.supports_set_get_features)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(broken_get_timings); i++) {
+		if (!strcmp(broken_get_timings[i], chip->parameters.model))
+			break;
+	}
+
+	if (i == ARRAY_SIZE(broken_get_timings))
+		return;
+
+	bitmap_clear(chip->parameters.get_feature_list,
+		     ONFI_FEATURE_ADDR_TIMING_MODE, 1);
+	bitmap_clear(chip->parameters.set_feature_list,
+		     ONFI_FEATURE_ADDR_TIMING_MODE, 1);
+}
+
 static int macronix_nand_init(struct nand_chip *chip)
 {
 	if (nand_is_slc(chip))
 		chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
 
-	/*
-	 * MX30LF2G18AC chip does not support using SET/GET_FEATURES to change
-	 * the timings unlike what is declared in the parameter page. Unflag
-	 * this feature to avoid unnecessary downturns.
-	 */
-	if (chip->parameters.supports_set_get_features &&
-	    !strcmp("MX30LF2G18AC", chip->parameters.model)) {
-		bitmap_clear(chip->parameters.get_feature_list,
-			     ONFI_FEATURE_ADDR_TIMING_MODE, 1);
-		bitmap_clear(chip->parameters.set_feature_list,
-			     ONFI_FEATURE_ADDR_TIMING_MODE, 1);
-	}
+	macronix_nand_fix_broken_get_timings(chip);
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 0af45b134c0c..f5dc0a7a2456 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -16,12 +16,33 @@
  */
 
 #include <linux/mtd/rawnand.h>
+#include <linux/slab.h>
 
 /*
- * Special Micron status bit that indicates when the block has been
- * corrected by on-die ECC and should be rewritten
+ * Special Micron status bit 3 indicates that the block has been
+ * corrected by on-die ECC and should be rewritten.
  */
-#define NAND_STATUS_WRITE_RECOMMENDED	BIT(3)
+#define NAND_ECC_STATUS_WRITE_RECOMMENDED	BIT(3)
+
+/*
+ * On chips with 8-bit ECC and additional bit can be used to distinguish
+ * cases where a errors were corrected without needing a rewrite
+ *
+ * Bit 4 Bit 3 Bit 0 Description
+ * ----- ----- ----- -----------
+ * 0     0     0     No Errors
+ * 0     0     1     Multiple uncorrected errors
+ * 0     1     0     4 - 6 errors corrected, recommend rewrite
+ * 0     1     1     Reserved
+ * 1     0     0     1 - 3 errors corrected
+ * 1     0     1     Reserved
+ * 1     1     0     7 - 8 errors corrected, recommend rewrite
+ */
+#define NAND_ECC_STATUS_MASK		(BIT(4) | BIT(3) | BIT(0))
+#define NAND_ECC_STATUS_UNCORRECTABLE	BIT(0)
+#define NAND_ECC_STATUS_4_6_CORRECTED	BIT(3)
+#define NAND_ECC_STATUS_1_3_CORRECTED	BIT(4)
+#define NAND_ECC_STATUS_7_8_CORRECTED	(BIT(4) | BIT(3))
 
 struct nand_onfi_vendor_micron {
 	u8 two_plane_read;
@@ -43,6 +64,16 @@ struct nand_onfi_vendor_micron {
 	u8 param_revision;
 } __packed;
 
+struct micron_on_die_ecc {
+	bool forced;
+	bool enabled;
+	void *rawbuf;
+};
+
+struct micron_nand {
+	struct micron_on_die_ecc ecc;
+};
+
 static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -57,23 +88,27 @@ static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
 static int micron_nand_onfi_init(struct nand_chip *chip)
 {
 	struct nand_parameters *p = &chip->parameters;
-	struct nand_onfi_vendor_micron *micron = (void *)p->onfi.vendor;
 
-	if (chip->parameters.onfi.version && p->onfi.vendor_revision) {
+	if (p->onfi) {
+		struct nand_onfi_vendor_micron *micron = (void *)p->onfi->vendor;
+
 		chip->read_retries = micron->read_retry_options;
 		chip->setup_read_retry = micron_nand_setup_read_retry;
 	}
 
 	if (p->supports_set_get_features) {
 		set_bit(ONFI_FEATURE_ADDR_READ_RETRY, p->set_feature_list);
+		set_bit(ONFI_FEATURE_ON_DIE_ECC, p->set_feature_list);
 		set_bit(ONFI_FEATURE_ADDR_READ_RETRY, p->get_feature_list);
+		set_bit(ONFI_FEATURE_ON_DIE_ECC, p->get_feature_list);
 	}
 
 	return 0;
 }
 
-static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
-					    struct mtd_oob_region *oobregion)
+static int micron_nand_on_die_4_ooblayout_ecc(struct mtd_info *mtd,
+					      int section,
+					      struct mtd_oob_region *oobregion)
 {
 	if (section >= 4)
 		return -ERANGE;
@@ -84,8 +119,9 @@ static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
 	return 0;
 }
 
-static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
-					     struct mtd_oob_region *oobregion)
+static int micron_nand_on_die_4_ooblayout_free(struct mtd_info *mtd,
+					       int section,
+					       struct mtd_oob_region *oobregion)
 {
 	if (section >= 4)
 		return -ERANGE;
@@ -96,19 +132,161 @@ static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
 	return 0;
 }
 
-static const struct mtd_ooblayout_ops micron_nand_on_die_ooblayout_ops = {
-	.ecc = micron_nand_on_die_ooblayout_ecc,
-	.free = micron_nand_on_die_ooblayout_free,
+static const struct mtd_ooblayout_ops micron_nand_on_die_4_ooblayout_ops = {
+	.ecc = micron_nand_on_die_4_ooblayout_ecc,
+	.free = micron_nand_on_die_4_ooblayout_free,
+};
+
+static int micron_nand_on_die_8_ooblayout_ecc(struct mtd_info *mtd,
+					      int section,
+					      struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = mtd->oobsize - chip->ecc.total;
+	oobregion->length = chip->ecc.total;
+
+	return 0;
+}
+
+static int micron_nand_on_die_8_ooblayout_free(struct mtd_info *mtd,
+					       int section,
+					       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = 2;
+	oobregion->length = mtd->oobsize - chip->ecc.total - 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops micron_nand_on_die_8_ooblayout_ops = {
+	.ecc = micron_nand_on_die_8_ooblayout_ecc,
+	.free = micron_nand_on_die_8_ooblayout_free,
 };
 
 static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
 {
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
 	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	int ret;
+
+	if (micron->ecc.forced)
+		return 0;
+
+	if (micron->ecc.enabled == enable)
+		return 0;
 
 	if (enable)
 		feature[0] |= ONFI_FEATURE_ON_DIE_ECC_EN;
 
-	return nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
+	ret = nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
+	if (!ret)
+		micron->ecc.enabled = enable;
+
+	return ret;
+}
+
+static int micron_nand_on_die_ecc_status_4(struct nand_chip *chip, u8 status,
+					   void *buf, int page,
+					   int oob_required)
+{
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	unsigned int step, max_bitflips = 0;
+	int ret;
+
+	if (!(status & NAND_ECC_STATUS_WRITE_RECOMMENDED)) {
+		if (status & NAND_STATUS_FAIL)
+			mtd->ecc_stats.failed++;
+
+		return 0;
+	}
+
+	/*
+	 * The internal ECC doesn't tell us the number of bitflips that have
+	 * been corrected, but tells us if it recommends to rewrite the block.
+	 * If it's the case, we need to read the page in raw mode and compare
+	 * its content to the corrected version to extract the actual number of
+	 * bitflips.
+	 * But before we do that, we must make sure we have all OOB bytes read
+	 * in non-raw mode, even if the user did not request those bytes.
+	 */
+	if (!oob_required) {
+		ret = nand_read_data_op(chip, chip->oob_poi, mtd->oobsize,
+					false);
+		if (ret)
+			return ret;
+	}
+
+	micron_nand_on_die_ecc_setup(chip, false);
+
+	ret = nand_read_page_op(chip, page, 0, micron->ecc.rawbuf,
+				mtd->writesize + mtd->oobsize);
+	if (ret)
+		return ret;
+
+	for (step = 0; step < chip->ecc.steps; step++) {
+		unsigned int offs, i, nbitflips = 0;
+		u8 *rawbuf, *corrbuf;
+
+		offs = step * chip->ecc.size;
+		rawbuf = micron->ecc.rawbuf + offs;
+		corrbuf = buf + offs;
+
+		for (i = 0; i < chip->ecc.size; i++)
+			nbitflips += hweight8(corrbuf[i] ^ rawbuf[i]);
+
+		offs = (step * 16) + 4;
+		rawbuf = micron->ecc.rawbuf + mtd->writesize + offs;
+		corrbuf = chip->oob_poi + offs;
+
+		for (i = 0; i < chip->ecc.bytes + 4; i++)
+			nbitflips += hweight8(corrbuf[i] ^ rawbuf[i]);
+
+		if (WARN_ON(nbitflips > chip->ecc.strength))
+			return -EINVAL;
+
+		max_bitflips = max(nbitflips, max_bitflips);
+		mtd->ecc_stats.corrected += nbitflips;
+	}
+
+	return max_bitflips;
+}
+
+static int micron_nand_on_die_ecc_status_8(struct nand_chip *chip, u8 status)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	/*
+	 * With 8/512 we have more information but still don't know precisely
+	 * how many bit-flips were seen.
+	 */
+	switch (status & NAND_ECC_STATUS_MASK) {
+	case NAND_ECC_STATUS_UNCORRECTABLE:
+		mtd->ecc_stats.failed++;
+		return 0;
+	case NAND_ECC_STATUS_1_3_CORRECTED:
+		mtd->ecc_stats.corrected += 3;
+		return 3;
+	case NAND_ECC_STATUS_4_6_CORRECTED:
+		mtd->ecc_stats.corrected += 6;
+		/* rewrite recommended */
+		return 6;
+	case NAND_ECC_STATUS_7_8_CORRECTED:
+		mtd->ecc_stats.corrected += 8;
+		/* rewrite recommended */
+		return 8;
+	default:
+		return 0;
+	}
 }
 
 static int
@@ -135,24 +313,18 @@ micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
 	if (ret)
 		goto out;
 
-	if (status & NAND_STATUS_FAIL)
-		mtd->ecc_stats.failed++;
-
-	/*
-	 * The internal ECC doesn't tell us the number of bitflips
-	 * that have been corrected, but tells us if it recommends to
-	 * rewrite the block. If it's the case, then we pretend we had
-	 * a number of bitflips equal to the ECC strength, which will
-	 * hint the NAND core to rewrite the block.
-	 */
-	else if (status & NAND_STATUS_WRITE_RECOMMENDED)
-		max_bitflips = chip->ecc.strength;
-
 	ret = nand_read_data_op(chip, buf, mtd->writesize, false);
 	if (!ret && oob_required)
 		ret = nand_read_data_op(chip, chip->oob_poi, mtd->oobsize,
 					false);
 
+	if (chip->ecc.strength == 4)
+		max_bitflips = micron_nand_on_die_ecc_status_4(chip, status,
+							       buf, page,
+							       oob_required);
+	else
+		max_bitflips = micron_nand_on_die_ecc_status_8(chip, status);
+
 out:
 	micron_nand_on_die_ecc_setup(chip, false);
 
@@ -193,6 +365,9 @@ enum {
 	MICRON_ON_DIE_MANDATORY,
 };
 
+#define MICRON_ID_INTERNAL_ECC_MASK	GENMASK(1, 0)
+#define MICRON_ID_ECC_ENABLED		BIT(7)
+
 /*
  * Try to detect if the NAND support on-die ECC. To do this, we enable
  * the feature, and read back if it has been enabled as expected. We
@@ -205,42 +380,52 @@ enum {
  */
 static int micron_supports_on_die_ecc(struct nand_chip *chip)
 {
-	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	u8 id[5];
 	int ret;
 
-	if (!chip->parameters.onfi.version)
+	if (!chip->parameters.onfi)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	if (chip->bits_per_cell != 1)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
+	/*
+	 * We only support on-die ECC of 4/512 or 8/512
+	 */
+	if  (chip->ecc_strength_ds != 4 && chip->ecc_strength_ds != 8)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	/* 0x2 means on-die ECC is available. */
+	if (chip->id.len != 5 ||
+	    (chip->id.data[4] & MICRON_ID_INTERNAL_ECC_MASK) != 0x2)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
 	ret = micron_nand_on_die_ecc_setup(chip, true);
 	if (ret)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
-	ret = nand_get_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
-	if (ret < 0)
-		return ret;
+	ret = nand_readid_op(chip, 0, id, sizeof(id));
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
 
-	if ((feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN) == 0)
+	if (!(id[4] & MICRON_ID_ECC_ENABLED))
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	ret = micron_nand_on_die_ecc_setup(chip, false);
 	if (ret)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
-	ret = nand_get_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
-	if (ret < 0)
-		return ret;
+	ret = nand_readid_op(chip, 0, id, sizeof(id));
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
 
-	if (feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN)
+	if (id[4] & MICRON_ID_ECC_ENABLED)
 		return MICRON_ON_DIE_MANDATORY;
 
 	/*
-	 * Some Micron NANDs have an on-die ECC of 4/512, some other
-	 * 8/512. We only support the former.
+	 * We only support on-die ECC of 4/512 or 8/512
 	 */
-	if (chip->ecc_strength_ds != 4)
+	if  (chip->ecc_strength_ds != 4 && chip->ecc_strength_ds != 8)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	return MICRON_ON_DIE_SUPPORTED;
@@ -249,44 +434,116 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip)
 static int micron_nand_init(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct micron_nand *micron;
 	int ondie;
 	int ret;
 
+	micron = kzalloc(sizeof(*micron), GFP_KERNEL);
+	if (!micron)
+		return -ENOMEM;
+
+	nand_set_manufacturer_data(chip, micron);
+
 	ret = micron_nand_onfi_init(chip);
 	if (ret)
-		return ret;
+		goto err_free_manuf_data;
 
 	if (mtd->writesize == 2048)
 		chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
 
 	ondie = micron_supports_on_die_ecc(chip);
 
-	if (ondie == MICRON_ON_DIE_MANDATORY) {
+	if (ondie == MICRON_ON_DIE_MANDATORY &&
+	    chip->ecc.mode != NAND_ECC_ON_DIE) {
 		pr_err("On-die ECC forcefully enabled, not supported\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_free_manuf_data;
 	}
 
 	if (chip->ecc.mode == NAND_ECC_ON_DIE) {
 		if (ondie == MICRON_ON_DIE_UNSUPPORTED) {
 			pr_err("On-die ECC selected but not supported\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_free_manuf_data;
+		}
+
+		if (ondie == MICRON_ON_DIE_MANDATORY) {
+			micron->ecc.forced = true;
+			micron->ecc.enabled = true;
+		}
+
+		/*
+		 * In case of 4bit on-die ECC, we need a buffer to store a
+		 * page dumped in raw mode so that we can compare its content
+		 * to the same page after ECC correction happened and extract
+		 * the real number of bitflips from this comparison.
+		 * That's not needed for 8-bit ECC, because the status expose
+		 * a better approximation of the number of bitflips in a page.
+		 */
+		if (chip->ecc_strength_ds == 4) {
+			micron->ecc.rawbuf = kmalloc(mtd->writesize +
+						     mtd->oobsize,
+						     GFP_KERNEL);
+			if (!micron->ecc.rawbuf) {
+				ret = -ENOMEM;
+				goto err_free_manuf_data;
+			}
 		}
 
-		chip->ecc.bytes = 8;
+		if (chip->ecc_strength_ds == 4)
+			mtd_set_ooblayout(mtd,
+					  &micron_nand_on_die_4_ooblayout_ops);
+		else
+			mtd_set_ooblayout(mtd,
+					  &micron_nand_on_die_8_ooblayout_ops);
+
+		chip->ecc.bytes = chip->ecc_strength_ds * 2;
 		chip->ecc.size = 512;
-		chip->ecc.strength = 4;
+		chip->ecc.strength = chip->ecc_strength_ds;
 		chip->ecc.algo = NAND_ECC_BCH;
 		chip->ecc.read_page = micron_nand_read_page_on_die_ecc;
 		chip->ecc.write_page = micron_nand_write_page_on_die_ecc;
-		chip->ecc.read_page_raw = nand_read_page_raw;
-		chip->ecc.write_page_raw = nand_write_page_raw;
 
-		mtd_set_ooblayout(mtd, &micron_nand_on_die_ooblayout_ops);
+		if (ondie == MICRON_ON_DIE_MANDATORY) {
+			chip->ecc.read_page_raw = nand_read_page_raw_notsupp;
+			chip->ecc.write_page_raw = nand_write_page_raw_notsupp;
+		} else {
+			chip->ecc.read_page_raw = nand_read_page_raw;
+			chip->ecc.write_page_raw = nand_write_page_raw;
+		}
 	}
 
 	return 0;
+
+err_free_manuf_data:
+	kfree(micron->ecc.rawbuf);
+	kfree(micron);
+
+	return ret;
+}
+
+static void micron_nand_cleanup(struct nand_chip *chip)
+{
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
+
+	kfree(micron->ecc.rawbuf);
+	kfree(micron);
+}
+
+static void micron_fixup_onfi_param_page(struct nand_chip *chip,
+					 struct nand_onfi_params *p)
+{
+	/*
+	 * MT29F1G08ABAFAWP-ITE:F and possibly others report 00 00 for the
+	 * revision number field of the ONFI parameter page. Assume ONFI
+	 * version 1.0 if the revision number is 00 00.
+	 */
+	if (le16_to_cpu(p->revision) == 0)
+		p->revision = cpu_to_le16(ONFI_VERSION_1_0);
 }
 
 const struct nand_manufacturer_ops micron_nand_manuf_ops = {
 	.init = micron_nand_init,
+	.cleanup = micron_nand_cleanup,
+	.fixup_onfi_param_page = micron_fixup_onfi_param_page,
 };
diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c
index 7c4e4a371bbc..ebc7b5f76f77 100644
--- a/drivers/mtd/nand/raw/nand_timings.c
+++ b/drivers/mtd/nand/raw/nand_timings.c
@@ -13,6 +13,8 @@
 #include <linux/export.h>
 #include <linux/mtd/rawnand.h>
 
+#define ONFI_DYN_TIMING_MAX U16_MAX
+
 static const struct nand_data_interface onfi_sdr_timings[] = {
 	/* Mode 0 */
 	{
@@ -292,6 +294,7 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 			     int timing_mode)
 {
 	struct nand_data_interface *iface = &chip->data_interface;
+	struct onfi_params *onfi = chip->parameters.onfi;
 
 	if (type != NAND_SDR_IFACE)
 		return -EINVAL;
@@ -303,20 +306,35 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 
 	/*
 	 * Initialize timings that cannot be deduced from timing mode:
-	 * tR, tPROG, tCCS, ...
+	 * tPROG, tBERS, tR and tCCS.
 	 * These information are part of the ONFI parameter page.
 	 */
-	if (chip->parameters.onfi.version) {
-		struct nand_parameters *params = &chip->parameters;
+	if (onfi) {
+		struct nand_sdr_timings *timings = &iface->timings.sdr;
+
+		/* microseconds -> picoseconds */
+		timings->tPROG_max = 1000000ULL * onfi->tPROG;
+		timings->tBERS_max = 1000000ULL * onfi->tBERS;
+		timings->tR_max = 1000000ULL * onfi->tR;
+
+		/* nanoseconds -> picoseconds */
+		timings->tCCS_min = 1000UL * onfi->tCCS;
+	} else {
 		struct nand_sdr_timings *timings = &iface->timings.sdr;
+		/*
+		 * For non-ONFI chips we use the highest possible value for
+		 * tPROG and tBERS. tR and tCCS will take the default values
+		 * precised in the ONFI specification for timing mode 0,
+		 * respectively 200us and 500ns.
+		 */
 
 		/* microseconds -> picoseconds */
-		timings->tPROG_max = 1000000ULL * params->onfi.tPROG;
-		timings->tBERS_max = 1000000ULL * params->onfi.tBERS;
-		timings->tR_max = 1000000ULL * params->onfi.tR;
+		timings->tPROG_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
+		timings->tBERS_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
+		timings->tR_max = 1000000ULL * 200000000ULL;
 
 		/* nanoseconds -> picoseconds */
-		timings->tCCS_min = 1000UL * params->onfi.tCCS;
+		timings->tCCS_min = 1000UL * 500000;
 	}
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index f8edacde49ab..71ac034aee9c 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -2192,6 +2192,48 @@ static void ns_nand_read_buf(struct mtd_info *mtd, u_char *buf, int len)
 	return;
 }
 
+static int ns_attach_chip(struct nand_chip *chip)
+{
+	unsigned int eccsteps, eccbytes;
+
+	if (!bch)
+		return 0;
+
+	if (!mtd_nand_has_bch()) {
+		NS_ERR("BCH ECC support is disabled\n");
+		return -EINVAL;
+	}
+
+	/* Use 512-byte ecc blocks */
+	eccsteps = nsmtd->writesize / 512;
+	eccbytes = ((bch * 13) + 7) / 8;
+
+	/* Do not bother supporting small page devices */
+	if (nsmtd->oobsize < 64 || !eccsteps) {
+		NS_ERR("BCH not available on small page devices\n");
+		return -EINVAL;
+	}
+
+	if (((eccbytes * eccsteps) + 2) > nsmtd->oobsize) {
+		NS_ERR("Invalid BCH value %u\n", bch);
+		return -EINVAL;
+	}
+
+	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.algo = NAND_ECC_BCH;
+	chip->ecc.size = 512;
+	chip->ecc.strength = bch;
+	chip->ecc.bytes = eccbytes;
+
+	NS_INFO("Using %u-bit/%u bytes BCH ECC\n", bch, chip->ecc.size);
+
+	return 0;
+}
+
+static const struct nand_controller_ops ns_controller_ops = {
+	.attach_chip = ns_attach_chip,
+};
+
 /*
  * Module initialization function
  */
@@ -2276,44 +2318,10 @@ static int __init ns_init_module(void)
 	if ((retval = parse_gravepages()) != 0)
 		goto error;
 
-	retval = nand_scan_ident(nsmtd, 1, NULL);
-	if (retval) {
-		NS_ERR("cannot scan NAND Simulator device\n");
-		goto error;
-	}
-
-	if (bch) {
-		unsigned int eccsteps, eccbytes;
-		if (!mtd_nand_has_bch()) {
-			NS_ERR("BCH ECC support is disabled\n");
-			retval = -EINVAL;
-			goto error;
-		}
-		/* use 512-byte ecc blocks */
-		eccsteps = nsmtd->writesize/512;
-		eccbytes = (bch*13+7)/8;
-		/* do not bother supporting small page devices */
-		if ((nsmtd->oobsize < 64) || !eccsteps) {
-			NS_ERR("bch not available on small page devices\n");
-			retval = -EINVAL;
-			goto error;
-		}
-		if ((eccbytes*eccsteps+2) > nsmtd->oobsize) {
-			NS_ERR("invalid bch value %u\n", bch);
-			retval = -EINVAL;
-			goto error;
-		}
-		chip->ecc.mode = NAND_ECC_SOFT;
-		chip->ecc.algo = NAND_ECC_BCH;
-		chip->ecc.size = 512;
-		chip->ecc.strength = bch;
-		chip->ecc.bytes = eccbytes;
-		NS_INFO("using %u-bit/%u bytes BCH ECC\n", bch, chip->ecc.size);
-	}
-
-	retval = nand_scan_tail(nsmtd);
+	chip->dummy_controller.ops = &ns_controller_ops;
+	retval = nand_scan(nsmtd, 1);
 	if (retval) {
-		NS_ERR("can't register NAND Simulator\n");
+		NS_ERR("Could not scan NAND Simulator device\n");
 		goto error;
 	}
 
@@ -2337,7 +2345,7 @@ static int __init ns_init_module(void)
 	if ((retval = init_nandsim(nsmtd)) != 0)
 		goto err_exit;
 
-	if ((retval = chip->scan_bbt(nsmtd)) != 0)
+	if ((retval = nand_create_bbt(chip)) != 0)
 		goto err_exit;
 
 	if ((retval = parse_badblocks(nand, nsmtd)) != 0)
diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c
index d8a806894937..540fa1a0ea24 100644
--- a/drivers/mtd/nand/raw/ndfc.c
+++ b/drivers/mtd/nand/raw/ndfc.c
@@ -39,7 +39,7 @@ struct ndfc_controller {
 	void __iomem *ndfcbase;
 	struct nand_chip chip;
 	int chip_select;
-	struct nand_hw_control ndfc_control;
+	struct nand_controller ndfc_control;
 };
 
 static struct ndfc_controller ndfc_ctrl[NDFC_MAX_CS];
@@ -218,7 +218,7 @@ static int ndfc_probe(struct platform_device *ofdev)
 	ndfc = &ndfc_ctrl[cs];
 	ndfc->chip_select = cs;
 
-	nand_hw_control_init(&ndfc->ndfc_control);
+	nand_controller_init(&ndfc->ndfc_control);
 	ndfc->ofdev = ofdev;
 	dev_set_drvdata(&ofdev->dev, ndfc);
 
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index e50c64adc3c8..4546ac0bed4a 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -144,12 +144,6 @@ static u_char bch8_vector[] = {0xf3, 0xdb, 0x14, 0x16, 0x8b, 0xd2, 0xbe, 0xcc,
 	0xac, 0x6b, 0xff, 0x99, 0x7b};
 static u_char bch4_vector[] = {0x00, 0x6b, 0x31, 0xdd, 0x41, 0xbc, 0x10};
 
-/* Shared among all NAND instances to synchronize access to the ECC Engine */
-static struct nand_hw_control omap_gpmc_controller = {
-	.lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock),
-	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq),
-};
-
 struct omap_nand_info {
 	struct nand_chip		nand;
 	struct platform_device		*pdev;
@@ -1915,106 +1909,26 @@ static const struct mtd_ooblayout_ops omap_sw_ooblayout_ops = {
 	.free = omap_sw_ooblayout_free,
 };
 
-static int omap_nand_probe(struct platform_device *pdev)
+static int omap_nand_attach_chip(struct nand_chip *chip)
 {
-	struct omap_nand_info		*info;
-	struct mtd_info			*mtd;
-	struct nand_chip		*nand_chip;
-	int				err;
-	dma_cap_mask_t			mask;
-	struct resource			*res;
-	struct device			*dev = &pdev->dev;
-	int				min_oobbytes = BADBLOCK_MARKER_LENGTH;
-	int				oobbytes_per_step;
-
-	info = devm_kzalloc(&pdev->dev, sizeof(struct omap_nand_info),
-				GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info->pdev = pdev;
-
-	err = omap_get_dt_info(dev, info);
-	if (err)
-		return err;
-
-	info->ops = gpmc_omap_get_nand_ops(&info->reg, info->gpmc_cs);
-	if (!info->ops) {
-		dev_err(&pdev->dev, "Failed to get GPMC->NAND interface\n");
-		return -ENODEV;
-	}
-
-	nand_chip		= &info->nand;
-	mtd			= nand_to_mtd(nand_chip);
-	mtd->dev.parent		= &pdev->dev;
-	nand_chip->ecc.priv	= NULL;
-	nand_set_flash_node(nand_chip, dev->of_node);
-
-	if (!mtd->name) {
-		mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-					   "omap2-nand.%d", info->gpmc_cs);
-		if (!mtd->name) {
-			dev_err(&pdev->dev, "Failed to set MTD name\n");
-			return -ENOMEM;
-		}
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(nand_chip->IO_ADDR_R))
-		return PTR_ERR(nand_chip->IO_ADDR_R);
-
-	info->phys_base = res->start;
-
-	nand_chip->controller = &omap_gpmc_controller;
-
-	nand_chip->IO_ADDR_W = nand_chip->IO_ADDR_R;
-	nand_chip->cmd_ctrl  = omap_hwcontrol;
-
-	info->ready_gpiod = devm_gpiod_get_optional(&pdev->dev, "rb",
-						    GPIOD_IN);
-	if (IS_ERR(info->ready_gpiod)) {
-		dev_err(dev, "failed to get ready gpio\n");
-		return PTR_ERR(info->ready_gpiod);
-	}
-
-	/*
-	 * If RDY/BSY line is connected to OMAP then use the omap ready
-	 * function and the generic nand_wait function which reads the status
-	 * register after monitoring the RDY/BSY line. Otherwise use a standard
-	 * chip delay which is slightly more than tR (AC Timing) of the NAND
-	 * device and read status register until you get a failure or success
-	 */
-	if (info->ready_gpiod) {
-		nand_chip->dev_ready = omap_dev_ready;
-		nand_chip->chip_delay = 0;
-	} else {
-		nand_chip->waitfunc = omap_wait;
-		nand_chip->chip_delay = 50;
-	}
-
-	if (info->flash_bbt)
-		nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
-
-	/* scan NAND device connected to chip controller */
-	nand_chip->options |= info->devsize & NAND_BUSWIDTH_16;
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err) {
-		dev_err(&info->pdev->dev,
-			"scan failed, may be bus-width mismatch\n");
-		goto return_error;
-	}
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct omap_nand_info *info = mtd_to_omap(mtd);
+	struct device *dev = &info->pdev->dev;
+	int min_oobbytes = BADBLOCK_MARKER_LENGTH;
+	int oobbytes_per_step;
+	dma_cap_mask_t mask;
+	int err;
 
-	if (nand_chip->bbt_options & NAND_BBT_USE_FLASH)
-		nand_chip->bbt_options |= NAND_BBT_NO_OOB;
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
 	else
-		nand_chip->options |= NAND_SKIP_BBTSCAN;
+		chip->options |= NAND_SKIP_BBTSCAN;
 
-	/* re-populate low-level callbacks based on xfer modes */
+	/* Re-populate low-level callbacks based on xfer modes */
 	switch (info->xfer_type) {
 	case NAND_OMAP_PREFETCH_POLLED:
-		nand_chip->read_buf   = omap_read_buf_pref;
-		nand_chip->write_buf  = omap_write_buf_pref;
+		chip->read_buf = omap_read_buf_pref;
+		chip->write_buf = omap_write_buf_pref;
 		break;
 
 	case NAND_OMAP_POLLED:
@@ -2024,12 +1938,11 @@ static int omap_nand_probe(struct platform_device *pdev)
 	case NAND_OMAP_PREFETCH_DMA:
 		dma_cap_zero(mask);
 		dma_cap_set(DMA_SLAVE, mask);
-		info->dma = dma_request_chan(pdev->dev.parent, "rxtx");
+		info->dma = dma_request_chan(dev, "rxtx");
 
 		if (IS_ERR(info->dma)) {
-			dev_err(&pdev->dev, "DMA engine request failed\n");
-			err = PTR_ERR(info->dma);
-			goto return_error;
+			dev_err(dev, "DMA engine request failed\n");
+			return PTR_ERR(info->dma);
 		} else {
 			struct dma_slave_config cfg;
 
@@ -2042,222 +1955,306 @@ static int omap_nand_probe(struct platform_device *pdev)
 			cfg.dst_maxburst = 16;
 			err = dmaengine_slave_config(info->dma, &cfg);
 			if (err) {
-				dev_err(&pdev->dev, "DMA engine slave config failed: %d\n",
+				dev_err(dev,
+					"DMA engine slave config failed: %d\n",
 					err);
-				goto return_error;
+				return err;
 			}
-			nand_chip->read_buf   = omap_read_buf_dma_pref;
-			nand_chip->write_buf  = omap_write_buf_dma_pref;
+			chip->read_buf = omap_read_buf_dma_pref;
+			chip->write_buf = omap_write_buf_dma_pref;
 		}
 		break;
 
 	case NAND_OMAP_PREFETCH_IRQ:
-		info->gpmc_irq_fifo = platform_get_irq(pdev, 0);
+		info->gpmc_irq_fifo = platform_get_irq(info->pdev, 0);
 		if (info->gpmc_irq_fifo <= 0) {
-			dev_err(&pdev->dev, "error getting fifo irq\n");
-			err = -ENODEV;
-			goto return_error;
+			dev_err(dev, "Error getting fifo IRQ\n");
+			return -ENODEV;
 		}
-		err = devm_request_irq(&pdev->dev, info->gpmc_irq_fifo,
-					omap_nand_irq, IRQF_SHARED,
-					"gpmc-nand-fifo", info);
+		err = devm_request_irq(dev, info->gpmc_irq_fifo,
+				       omap_nand_irq, IRQF_SHARED,
+				       "gpmc-nand-fifo", info);
 		if (err) {
-			dev_err(&pdev->dev, "requesting irq(%d) error:%d",
-						info->gpmc_irq_fifo, err);
+			dev_err(dev, "Requesting IRQ %d, error %d\n",
+				info->gpmc_irq_fifo, err);
 			info->gpmc_irq_fifo = 0;
-			goto return_error;
+			return err;
 		}
 
-		info->gpmc_irq_count = platform_get_irq(pdev, 1);
+		info->gpmc_irq_count = platform_get_irq(info->pdev, 1);
 		if (info->gpmc_irq_count <= 0) {
-			dev_err(&pdev->dev, "error getting count irq\n");
-			err = -ENODEV;
-			goto return_error;
+			dev_err(dev, "Error getting IRQ count\n");
+			return -ENODEV;
 		}
-		err = devm_request_irq(&pdev->dev, info->gpmc_irq_count,
-					omap_nand_irq, IRQF_SHARED,
-					"gpmc-nand-count", info);
+		err = devm_request_irq(dev, info->gpmc_irq_count,
+				       omap_nand_irq, IRQF_SHARED,
+				       "gpmc-nand-count", info);
 		if (err) {
-			dev_err(&pdev->dev, "requesting irq(%d) error:%d",
-						info->gpmc_irq_count, err);
+			dev_err(dev, "Requesting IRQ %d, error %d\n",
+				info->gpmc_irq_count, err);
 			info->gpmc_irq_count = 0;
-			goto return_error;
+			return err;
 		}
 
-		nand_chip->read_buf  = omap_read_buf_irq_pref;
-		nand_chip->write_buf = omap_write_buf_irq_pref;
+		chip->read_buf = omap_read_buf_irq_pref;
+		chip->write_buf = omap_write_buf_irq_pref;
 
 		break;
 
 	default:
-		dev_err(&pdev->dev,
-			"xfer_type(%d) not supported!\n", info->xfer_type);
-		err = -EINVAL;
-		goto return_error;
+		dev_err(dev, "xfer_type %d not supported!\n", info->xfer_type);
+		return -EINVAL;
 	}
 
-	if (!omap2_nand_ecc_check(info)) {
-		err = -EINVAL;
-		goto return_error;
-	}
+	if (!omap2_nand_ecc_check(info))
+		return -EINVAL;
 
 	/*
 	 * Bail out earlier to let NAND_ECC_SOFT code create its own
 	 * ooblayout instead of using ours.
 	 */
 	if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW) {
-		nand_chip->ecc.mode = NAND_ECC_SOFT;
-		nand_chip->ecc.algo = NAND_ECC_HAMMING;
-		goto scan_tail;
+		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.algo = NAND_ECC_HAMMING;
+		return 0;
 	}
 
-	/* populate MTD interface based on ECC scheme */
+	/* Populate MTD interface based on ECC scheme */
 	switch (info->ecc_opt) {
 	case OMAP_ECC_HAM1_CODE_HW:
-		pr_info("nand: using OMAP_ECC_HAM1_CODE_HW\n");
-		nand_chip->ecc.mode             = NAND_ECC_HW;
-		nand_chip->ecc.bytes            = 3;
-		nand_chip->ecc.size             = 512;
-		nand_chip->ecc.strength         = 1;
-		nand_chip->ecc.calculate        = omap_calculate_ecc;
-		nand_chip->ecc.hwctl            = omap_enable_hwecc;
-		nand_chip->ecc.correct          = omap_correct_data;
+		dev_info(dev, "nand: using OMAP_ECC_HAM1_CODE_HW\n");
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.bytes		= 3;
+		chip->ecc.size		= 512;
+		chip->ecc.strength	= 1;
+		chip->ecc.calculate	= omap_calculate_ecc;
+		chip->ecc.hwctl		= omap_enable_hwecc;
+		chip->ecc.correct	= omap_correct_data;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
-		if (!(nand_chip->options & NAND_BUSWIDTH_16))
-			min_oobbytes		= 1;
+		if (!(chip->options & NAND_BUSWIDTH_16))
+			min_oobbytes	= 1;
 
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW_DETECTION_SW\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 7;
-		nand_chip->ecc.strength		= 4;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= nand_bch_correct_data;
-		nand_chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 7;
+		chip->ecc.strength	= 4;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
-		oobbytes_per_step		= nand_chip->ecc.bytes + 1;
-		/* software bch library is used for locating errors */
-		nand_chip->ecc.priv		= nand_bch_init(mtd);
-		if (!nand_chip->ecc.priv) {
-			dev_err(&info->pdev->dev, "unable to use BCH library\n");
-			err = -EINVAL;
-			goto return_error;
+		oobbytes_per_step	= chip->ecc.bytes + 1;
+		/* Software BCH library is used for locating errors */
+		chip->ecc.priv		= nand_bch_init(mtd);
+		if (!chip->ecc.priv) {
+			dev_err(dev, "Unable to use BCH library\n");
+			return -EINVAL;
 		}
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
-		nand_chip->ecc.bytes		= 7 + 1;
-		nand_chip->ecc.strength		= 4;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		chip->ecc.bytes		= 7 + 1;
+		chip->ecc.strength	= 4;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH4_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 		break;
 
 	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW_DETECTION_SW\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 13;
-		nand_chip->ecc.strength		= 8;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= nand_bch_correct_data;
-		nand_chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 13;
+		chip->ecc.strength	= 8;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
-		oobbytes_per_step		= nand_chip->ecc.bytes + 1;
-		/* software bch library is used for locating errors */
-		nand_chip->ecc.priv		= nand_bch_init(mtd);
-		if (!nand_chip->ecc.priv) {
-			dev_err(&info->pdev->dev, "unable to use BCH library\n");
-			err = -EINVAL;
-			goto return_error;
+		oobbytes_per_step	= chip->ecc.bytes + 1;
+		/* Software BCH library is used for locating errors */
+		chip->ecc.priv		= nand_bch_init(mtd);
+		if (!chip->ecc.priv) {
+			dev_err(dev, "unable to use BCH library\n");
+			return -EINVAL;
 		}
 		break;
 
 	case OMAP_ECC_BCH8_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
-		nand_chip->ecc.bytes		= 13 + 1;
-		nand_chip->ecc.strength		= 8;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		chip->ecc.bytes		= 13 + 1;
+		chip->ecc.strength	= 8;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH8_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 
 		break;
 
 	case OMAP_ECC_BCH16_CODE_HW:
-		pr_info("using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 26;
-		nand_chip->ecc.strength		= 16;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		pr_info("Using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 26;
+		chip->ecc.strength	= 16;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH16_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 
 		break;
 	default:
-		dev_err(&info->pdev->dev, "invalid or unsupported ECC scheme\n");
-		err = -EINVAL;
-		goto return_error;
+		dev_err(dev, "Invalid or unsupported ECC scheme\n");
+		return -EINVAL;
 	}
 
-	/* check if NAND device's OOB is enough to store ECC signatures */
+	/* Check if NAND device's OOB is enough to store ECC signatures */
 	min_oobbytes += (oobbytes_per_step *
-			 (mtd->writesize / nand_chip->ecc.size));
+			 (mtd->writesize / chip->ecc.size));
 	if (mtd->oobsize < min_oobbytes) {
-		dev_err(&info->pdev->dev,
-			"not enough OOB bytes required = %d, available=%d\n",
+		dev_err(dev,
+			"Not enough OOB bytes: required = %d, available=%d\n",
 			min_oobbytes, mtd->oobsize);
-		err = -EINVAL;
-		goto return_error;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops omap_nand_controller_ops = {
+	.attach_chip = omap_nand_attach_chip,
+};
+
+/* Shared among all NAND instances to synchronize access to the ECC Engine */
+static struct nand_controller omap_gpmc_controller = {
+	.lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock),
+	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq),
+	.ops = &omap_nand_controller_ops,
+};
+
+static int omap_nand_probe(struct platform_device *pdev)
+{
+	struct omap_nand_info		*info;
+	struct mtd_info			*mtd;
+	struct nand_chip		*nand_chip;
+	int				err;
+	struct resource			*res;
+	struct device			*dev = &pdev->dev;
+
+	info = devm_kzalloc(&pdev->dev, sizeof(struct omap_nand_info),
+				GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->pdev = pdev;
+
+	err = omap_get_dt_info(dev, info);
+	if (err)
+		return err;
+
+	info->ops = gpmc_omap_get_nand_ops(&info->reg, info->gpmc_cs);
+	if (!info->ops) {
+		dev_err(&pdev->dev, "Failed to get GPMC->NAND interface\n");
+		return -ENODEV;
 	}
 
-scan_tail:
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	nand_chip		= &info->nand;
+	mtd			= nand_to_mtd(nand_chip);
+	mtd->dev.parent		= &pdev->dev;
+	nand_chip->ecc.priv	= NULL;
+	nand_set_flash_node(nand_chip, dev->of_node);
+
+	if (!mtd->name) {
+		mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+					   "omap2-nand.%d", info->gpmc_cs);
+		if (!mtd->name) {
+			dev_err(&pdev->dev, "Failed to set MTD name\n");
+			return -ENOMEM;
+		}
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(nand_chip->IO_ADDR_R))
+		return PTR_ERR(nand_chip->IO_ADDR_R);
+
+	info->phys_base = res->start;
+
+	nand_chip->controller = &omap_gpmc_controller;
+
+	nand_chip->IO_ADDR_W = nand_chip->IO_ADDR_R;
+	nand_chip->cmd_ctrl  = omap_hwcontrol;
+
+	info->ready_gpiod = devm_gpiod_get_optional(&pdev->dev, "rb",
+						    GPIOD_IN);
+	if (IS_ERR(info->ready_gpiod)) {
+		dev_err(dev, "failed to get ready gpio\n");
+		return PTR_ERR(info->ready_gpiod);
+	}
+
+	/*
+	 * If RDY/BSY line is connected to OMAP then use the omap ready
+	 * function and the generic nand_wait function which reads the status
+	 * register after monitoring the RDY/BSY line. Otherwise use a standard
+	 * chip delay which is slightly more than tR (AC Timing) of the NAND
+	 * device and read status register until you get a failure or success
+	 */
+	if (info->ready_gpiod) {
+		nand_chip->dev_ready = omap_dev_ready;
+		nand_chip->chip_delay = 0;
+	} else {
+		nand_chip->waitfunc = omap_wait;
+		nand_chip->chip_delay = 50;
+	}
+
+	if (info->flash_bbt)
+		nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+	/* scan NAND device connected to chip controller */
+	nand_chip->options |= info->devsize & NAND_BUSWIDTH_16;
+
+	err = nand_scan(mtd, 1);
 	if (err)
 		goto return_error;
 
diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index 7825fd3ce66b..52d435285a3f 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -18,7 +18,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
 #include <linux/platform_data/mtd-orion_nand.h>
 
 struct orion_nand_info {
@@ -52,7 +52,7 @@ static void orion_nand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	void __iomem *io_base = chip->IO_ADDR_R;
-#if __LINUX_ARM_ARCH__ >= 5
+#if defined(__LINUX_ARM_ARCH__) && __LINUX_ARM_ARCH__ >= 5
 	uint64_t *buf64;
 #endif
 	int i = 0;
@@ -61,7 +61,7 @@ static void orion_nand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 		*buf++ = readb(io_base);
 		len--;
 	}
-#if __LINUX_ARM_ARCH__ >= 5
+#if defined(__LINUX_ARM_ARCH__) && __LINUX_ARM_ARCH__ >= 5
 	buf64 = (uint64_t *)buf;
 	while (i < len/8) {
 		/*
@@ -153,9 +153,6 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	if (board->width == 16)
 		nc->options |= NAND_BUSWIDTH_16;
 
-	if (board->dev_ready)
-		nc->dev_ready = board->dev_ready;
-
 	platform_set_drvdata(pdev, info);
 
 	/* Not all platforms can gate the clock, so it is not
diff --git a/drivers/mtd/nand/raw/oxnas_nand.c b/drivers/mtd/nand/raw/oxnas_nand.c
index d649d5944826..01b00bb69c1e 100644
--- a/drivers/mtd/nand/raw/oxnas_nand.c
+++ b/drivers/mtd/nand/raw/oxnas_nand.c
@@ -32,7 +32,7 @@
 #define OXNAS_NAND_MAX_CHIPS	1
 
 struct oxnas_nand_ctrl {
-	struct nand_hw_control base;
+	struct nand_controller base;
 	void __iomem *io_base;
 	struct clk *clk;
 	struct nand_chip *chips[OXNAS_NAND_MAX_CHIPS];
@@ -96,7 +96,7 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 	if (!oxnas)
 		return -ENOMEM;
 
-	nand_hw_control_init(&oxnas->base);
+	nand_controller_init(&oxnas->base);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	oxnas->io_base = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c
index 925a1323604d..222626df4b96 100644
--- a/drivers/mtd/nand/raw/plat_nand.c
+++ b/drivers/mtd/nand/raw/plat_nand.c
@@ -67,12 +67,10 @@ static int plat_nand_probe(struct platform_device *pdev)
 	data->chip.select_chip = pdata->ctrl.select_chip;
 	data->chip.write_buf = pdata->ctrl.write_buf;
 	data->chip.read_buf = pdata->ctrl.read_buf;
-	data->chip.read_byte = pdata->ctrl.read_byte;
 	data->chip.chip_delay = pdata->chip.chip_delay;
 	data->chip.options |= pdata->chip.options;
 	data->chip.bbt_options |= pdata->chip.bbt_options;
 
-	data->chip.ecc.hwctl = pdata->ctrl.hwcontrol;
 	data->chip.ecc.mode = NAND_ECC_SOFT;
 	data->chip.ecc.algo = NAND_ECC_HAMMING;
 
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 6a5519f0ff25..d1d470bb32e4 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -213,6 +213,8 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
 #define QPIC_PER_CW_CMD_SGL		32
 #define QPIC_PER_CW_DATA_SGL		8
 
+#define QPIC_NAND_COMPLETION_TIMEOUT	msecs_to_jiffies(2000)
+
 /*
  * Flags used in DMA descriptor preparation helper functions
  * (i.e. read_reg_dma/write_reg_dma/read_data_dma/write_data_dma)
@@ -245,6 +247,11 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
  * @tx_sgl_start - start index in data sgl for tx.
  * @rx_sgl_pos - current index in data sgl for rx.
  * @rx_sgl_start - start index in data sgl for rx.
+ * @wait_second_completion - wait for second DMA desc completion before making
+ *			     the NAND transfer completion.
+ * @txn_done - completion for NAND transfer.
+ * @last_data_desc - last DMA desc in data channel (tx/rx).
+ * @last_cmd_desc - last DMA desc in command channel.
  */
 struct bam_transaction {
 	struct bam_cmd_element *bam_ce;
@@ -258,6 +265,10 @@ struct bam_transaction {
 	u32 tx_sgl_start;
 	u32 rx_sgl_pos;
 	u32 rx_sgl_start;
+	bool wait_second_completion;
+	struct completion txn_done;
+	struct dma_async_tx_descriptor *last_data_desc;
+	struct dma_async_tx_descriptor *last_cmd_desc;
 };
 
 /*
@@ -354,7 +365,7 @@ struct nandc_regs {
  *				from all connected NAND devices pagesize
  */
 struct qcom_nand_controller {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct list_head host_list;
 
 	struct device *dev;
@@ -504,6 +515,8 @@ alloc_bam_transaction(struct qcom_nand_controller *nandc)
 
 	bam_txn->data_sgl = bam_txn_buf;
 
+	init_completion(&bam_txn->txn_done);
+
 	return bam_txn;
 }
 
@@ -523,11 +536,33 @@ static void clear_bam_transaction(struct qcom_nand_controller *nandc)
 	bam_txn->tx_sgl_start = 0;
 	bam_txn->rx_sgl_pos = 0;
 	bam_txn->rx_sgl_start = 0;
+	bam_txn->last_data_desc = NULL;
+	bam_txn->wait_second_completion = false;
 
 	sg_init_table(bam_txn->cmd_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_CMD_SGL);
 	sg_init_table(bam_txn->data_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_DATA_SGL);
+
+	reinit_completion(&bam_txn->txn_done);
+}
+
+/* Callback for DMA descriptor completion */
+static void qpic_bam_dma_done(void *data)
+{
+	struct bam_transaction *bam_txn = data;
+
+	/*
+	 * In case of data transfer with NAND, 2 callbacks will be generated.
+	 * One for command channel and another one for data channel.
+	 * If current transaction has data descriptors
+	 * (i.e. wait_second_completion is true), then set this to false
+	 * and wait for second DMA descriptor completion.
+	 */
+	if (bam_txn->wait_second_completion)
+		bam_txn->wait_second_completion = false;
+	else
+		complete(&bam_txn->txn_done);
 }
 
 static inline struct qcom_nand_host *to_qcom_nand_host(struct nand_chip *chip)
@@ -756,6 +791,12 @@ static int prepare_bam_async_desc(struct qcom_nand_controller *nandc,
 
 	desc->dma_desc = dma_desc;
 
+	/* update last data/command descriptor */
+	if (chan == nandc->cmd_chan)
+		bam_txn->last_cmd_desc = dma_desc;
+	else
+		bam_txn->last_data_desc = dma_desc;
+
 	list_add_tail(&desc->node, &nandc->desc_list);
 
 	return 0;
@@ -1055,7 +1096,8 @@ static void config_nand_page_read(struct qcom_nand_controller *nandc)
  * Helper to prepare DMA descriptors for configuring registers
  * before reading each codeword in NAND page.
  */
-static void config_nand_cw_read(struct qcom_nand_controller *nandc)
+static void
+config_nand_cw_read(struct qcom_nand_controller *nandc, bool use_ecc)
 {
 	if (nandc->props->is_bam)
 		write_reg_dma(nandc, NAND_READ_LOCATION_0, 4,
@@ -1064,19 +1106,25 @@ static void config_nand_cw_read(struct qcom_nand_controller *nandc)
 	write_reg_dma(nandc, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL);
 	write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL);
 
-	read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0);
-	read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1,
-		     NAND_BAM_NEXT_SGL);
+	if (use_ecc) {
+		read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0);
+		read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1,
+			     NAND_BAM_NEXT_SGL);
+	} else {
+		read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL);
+	}
 }
 
 /*
  * Helper to prepare dma descriptors to configure registers needed for reading a
  * single codeword in page
  */
-static void config_nand_single_cw_page_read(struct qcom_nand_controller *nandc)
+static void
+config_nand_single_cw_page_read(struct qcom_nand_controller *nandc,
+				bool use_ecc)
 {
 	config_nand_page_read(nandc);
-	config_nand_cw_read(nandc);
+	config_nand_cw_read(nandc, use_ecc);
 }
 
 /*
@@ -1157,7 +1205,7 @@ static int nandc_param(struct qcom_nand_host *host)
 	nandc->buf_count = 512;
 	memset(nandc->data_buffer, 0xff, nandc->buf_count);
 
-	config_nand_single_cw_page_read(nandc);
+	config_nand_single_cw_page_read(nandc, false);
 
 	read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer,
 		      nandc->buf_count, 0);
@@ -1273,10 +1321,20 @@ static int submit_descs(struct qcom_nand_controller *nandc)
 		cookie = dmaengine_submit(desc->dma_desc);
 
 	if (nandc->props->is_bam) {
+		bam_txn->last_cmd_desc->callback = qpic_bam_dma_done;
+		bam_txn->last_cmd_desc->callback_param = bam_txn;
+		if (bam_txn->last_data_desc) {
+			bam_txn->last_data_desc->callback = qpic_bam_dma_done;
+			bam_txn->last_data_desc->callback_param = bam_txn;
+			bam_txn->wait_second_completion = true;
+		}
+
 		dma_async_issue_pending(nandc->tx_chan);
 		dma_async_issue_pending(nandc->rx_chan);
+		dma_async_issue_pending(nandc->cmd_chan);
 
-		if (dma_sync_wait(nandc->cmd_chan, cookie) != DMA_COMPLETE)
+		if (!wait_for_completion_timeout(&bam_txn->txn_done,
+						 QPIC_NAND_COMPLETION_TIMEOUT))
 			return -ETIMEDOUT;
 	} else {
 		if (dma_sync_wait(nandc->chan, cookie) != DMA_COMPLETE)
@@ -1512,20 +1570,180 @@ struct read_stats {
 	__le32 erased_cw;
 };
 
+/* reads back FLASH_STATUS register set by the controller */
+static int check_flash_errors(struct qcom_nand_host *host, int cw_cnt)
+{
+	struct nand_chip *chip = &host->chip;
+	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
+	int i;
+
+	for (i = 0; i < cw_cnt; i++) {
+		u32 flash = le32_to_cpu(nandc->reg_read_buf[i]);
+
+		if (flash & (FS_OP_ERR | FS_MPU_ERR))
+			return -EIO;
+	}
+
+	return 0;
+}
+
+/* performs raw read for one codeword */
+static int
+qcom_nandc_read_cw_raw(struct mtd_info *mtd, struct nand_chip *chip,
+		       u8 *data_buf, u8 *oob_buf, int page, int cw)
+{
+	struct qcom_nand_host *host = to_qcom_nand_host(chip);
+	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	int data_size1, data_size2, oob_size1, oob_size2;
+	int ret, reg_off = FLASH_BUF_ACC, read_loc = 0;
+
+	nand_read_page_op(chip, page, 0, NULL, 0);
+	host->use_ecc = false;
+
+	clear_bam_transaction(nandc);
+	set_address(host, host->cw_size * cw, page);
+	update_rw_regs(host, 1, true);
+	config_nand_page_read(nandc);
+
+	data_size1 = mtd->writesize - host->cw_size * (ecc->steps - 1);
+	oob_size1 = host->bbm_size;
+
+	if (cw == (ecc->steps - 1)) {
+		data_size2 = ecc->size - data_size1 -
+			     ((ecc->steps - 1) * 4);
+		oob_size2 = (ecc->steps * 4) + host->ecc_bytes_hw +
+			    host->spare_bytes;
+	} else {
+		data_size2 = host->cw_data - data_size1;
+		oob_size2 = host->ecc_bytes_hw + host->spare_bytes;
+	}
+
+	if (nandc->props->is_bam) {
+		nandc_set_read_loc(nandc, 0, read_loc, data_size1, 0);
+		read_loc += data_size1;
+
+		nandc_set_read_loc(nandc, 1, read_loc, oob_size1, 0);
+		read_loc += oob_size1;
+
+		nandc_set_read_loc(nandc, 2, read_loc, data_size2, 0);
+		read_loc += data_size2;
+
+		nandc_set_read_loc(nandc, 3, read_loc, oob_size2, 1);
+	}
+
+	config_nand_cw_read(nandc, false);
+
+	read_data_dma(nandc, reg_off, data_buf, data_size1, 0);
+	reg_off += data_size1;
+
+	read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0);
+	reg_off += oob_size1;
+
+	read_data_dma(nandc, reg_off, data_buf + data_size1, data_size2, 0);
+	reg_off += data_size2;
+
+	read_data_dma(nandc, reg_off, oob_buf + oob_size1, oob_size2, 0);
+
+	ret = submit_descs(nandc);
+	free_descs(nandc);
+	if (ret) {
+		dev_err(nandc->dev, "failure to read raw cw %d\n", cw);
+		return ret;
+	}
+
+	return check_flash_errors(host, 1);
+}
+
+/*
+ * Bitflips can happen in erased codewords also so this function counts the
+ * number of 0 in each CW for which ECC engine returns the uncorrectable
+ * error. The page will be assumed as erased if this count is less than or
+ * equal to the ecc->strength for each CW.
+ *
+ * 1. Both DATA and OOB need to be checked for number of 0. The
+ *    top-level API can be called with only data buf or OOB buf so use
+ *    chip->data_buf if data buf is null and chip->oob_poi if oob buf
+ *    is null for copying the raw bytes.
+ * 2. Perform raw read for all the CW which has uncorrectable errors.
+ * 3. For each CW, check the number of 0 in cw_data and usable OOB bytes.
+ *    The BBM and spare bytes bit flip won’t affect the ECC so don’t check
+ *    the number of bitflips in this area.
+ */
+static int
+check_for_erased_page(struct qcom_nand_host *host, u8 *data_buf,
+		      u8 *oob_buf, unsigned long uncorrectable_cws,
+		      int page, unsigned int max_bitflips)
+{
+	struct nand_chip *chip = &host->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	u8 *cw_data_buf, *cw_oob_buf;
+	int cw, data_size, oob_size, ret = 0;
+
+	if (!data_buf) {
+		data_buf = chip->data_buf;
+		chip->pagebuf = -1;
+	}
+
+	if (!oob_buf) {
+		oob_buf = chip->oob_poi;
+		chip->pagebuf = -1;
+	}
+
+	for_each_set_bit(cw, &uncorrectable_cws, ecc->steps) {
+		if (cw == (ecc->steps - 1)) {
+			data_size = ecc->size - ((ecc->steps - 1) * 4);
+			oob_size = (ecc->steps * 4) + host->ecc_bytes_hw;
+		} else {
+			data_size = host->cw_data;
+			oob_size = host->ecc_bytes_hw;
+		}
+
+		/* determine starting buffer address for current CW */
+		cw_data_buf = data_buf + (cw * host->cw_data);
+		cw_oob_buf = oob_buf + (cw * ecc->bytes);
+
+		ret = qcom_nandc_read_cw_raw(mtd, chip, cw_data_buf,
+					     cw_oob_buf, page, cw);
+		if (ret)
+			return ret;
+
+		/*
+		 * make sure it isn't an erased page reported
+		 * as not-erased by HW because of a few bitflips
+		 */
+		ret = nand_check_erased_ecc_chunk(cw_data_buf, data_size,
+						  cw_oob_buf + host->bbm_size,
+						  oob_size, NULL,
+						  0, ecc->strength);
+		if (ret < 0) {
+			mtd->ecc_stats.failed++;
+		} else {
+			mtd->ecc_stats.corrected += ret;
+			max_bitflips = max_t(unsigned int, max_bitflips, ret);
+		}
+	}
+
+	return max_bitflips;
+}
+
 /*
  * reads back status registers set by the controller to notify page read
  * errors. this is equivalent to what 'ecc->correct()' would do.
  */
 static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
-			     u8 *oob_buf)
+			     u8 *oob_buf, int page)
 {
 	struct nand_chip *chip = &host->chip;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	unsigned int max_bitflips = 0;
+	unsigned int max_bitflips = 0, uncorrectable_cws = 0;
 	struct read_stats *buf;
+	bool flash_op_err = false, erased;
 	int i;
+	u8 *data_buf_start = data_buf, *oob_buf_start = oob_buf;
 
 	buf = (struct read_stats *)nandc->reg_read_buf;
 	nandc_read_buffer_sync(nandc, true);
@@ -1546,48 +1764,49 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 		buffer = le32_to_cpu(buf->buffer);
 		erased_cw = le32_to_cpu(buf->erased_cw);
 
-		if (flash & (FS_OP_ERR | FS_MPU_ERR)) {
-			bool erased;
-
-			/* ignore erased codeword errors */
+		/*
+		 * Check ECC failure for each codeword. ECC failure can
+		 * happen in either of the following conditions
+		 * 1. If number of bitflips are greater than ECC engine
+		 *    capability.
+		 * 2. If this codeword contains all 0xff for which erased
+		 *    codeword detection check will be done.
+		 */
+		if ((flash & FS_OP_ERR) && (buffer & BS_UNCORRECTABLE_BIT)) {
+			/*
+			 * For BCH ECC, ignore erased codeword errors, if
+			 * ERASED_CW bits are set.
+			 */
 			if (host->bch_enabled) {
 				erased = (erased_cw & ERASED_CW) == ERASED_CW ?
 					 true : false;
-			} else {
+			/*
+			 * For RS ECC, HW reports the erased CW by placing
+			 * special characters at certain offsets in the buffer.
+			 * These special characters will be valid only if
+			 * complete page is read i.e. data_buf is not NULL.
+			 */
+			} else if (data_buf) {
 				erased = erased_chunk_check_and_fixup(data_buf,
 								      data_len);
+			} else {
+				erased = false;
 			}
 
-			if (erased) {
-				data_buf += data_len;
-				if (oob_buf)
-					oob_buf += oob_len + ecc->bytes;
-				continue;
-			}
-
-			if (buffer & BS_UNCORRECTABLE_BIT) {
-				int ret, ecclen, extraooblen;
-				void *eccbuf;
-
-				eccbuf = oob_buf ? oob_buf + oob_len : NULL;
-				ecclen = oob_buf ? host->ecc_bytes_hw : 0;
-				extraooblen = oob_buf ? oob_len : 0;
-
-				/*
-				 * make sure it isn't an erased page reported
-				 * as not-erased by HW because of a few bitflips
-				 */
-				ret = nand_check_erased_ecc_chunk(data_buf,
-					data_len, eccbuf, ecclen, oob_buf,
-					extraooblen, ecc->strength);
-				if (ret < 0) {
-					mtd->ecc_stats.failed++;
-				} else {
-					mtd->ecc_stats.corrected += ret;
-					max_bitflips =
-						max_t(unsigned int, max_bitflips, ret);
-				}
-			}
+			if (!erased)
+				uncorrectable_cws |= BIT(i);
+		/*
+		 * Check if MPU or any other operational error (timeout,
+		 * device failure, etc.) happened for this codeword and
+		 * make flash_op_err true. If flash_op_err is set, then
+		 * EIO will be returned for page read.
+		 */
+		} else if (flash & (FS_OP_ERR | FS_MPU_ERR)) {
+			flash_op_err = true;
+		/*
+		 * No ECC or operational errors happened. Check the number of
+		 * bits corrected and update the ecc_stats.corrected.
+		 */
 		} else {
 			unsigned int stat;
 
@@ -1596,12 +1815,21 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 			max_bitflips = max(max_bitflips, stat);
 		}
 
-		data_buf += data_len;
+		if (data_buf)
+			data_buf += data_len;
 		if (oob_buf)
 			oob_buf += oob_len + ecc->bytes;
 	}
 
-	return max_bitflips;
+	if (flash_op_err)
+		return -EIO;
+
+	if (!uncorrectable_cws)
+		return max_bitflips;
+
+	return check_for_erased_page(host, data_buf_start, oob_buf_start,
+				     uncorrectable_cws, page,
+				     max_bitflips);
 }
 
 /*
@@ -1609,11 +1837,12 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
  * ecc->read_oob()
  */
 static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
-			 u8 *oob_buf)
+			 u8 *oob_buf, int page)
 {
 	struct nand_chip *chip = &host->chip;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	u8 *data_buf_start = data_buf, *oob_buf_start = oob_buf;
 	int i, ret;
 
 	config_nand_page_read(nandc);
@@ -1644,7 +1873,7 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 			}
 		}
 
-		config_nand_cw_read(nandc);
+		config_nand_cw_read(nandc, true);
 
 		if (data_buf)
 			read_data_dma(nandc, FLASH_BUF_ACC, data_buf,
@@ -1674,12 +1903,14 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 	}
 
 	ret = submit_descs(nandc);
-	if (ret)
-		dev_err(nandc->dev, "failure to read page/oob\n");
-
 	free_descs(nandc);
 
-	return ret;
+	if (ret) {
+		dev_err(nandc->dev, "failure to read page/oob\n");
+		return ret;
+	}
+
+	return parse_read_errors(host, data_buf_start, oob_buf_start, page);
 }
 
 /*
@@ -1704,7 +1935,7 @@ static int copy_last_cw(struct qcom_nand_host *host, int page)
 	set_address(host, host->cw_size * (ecc->steps - 1), page);
 	update_rw_regs(host, 1, true);
 
-	config_nand_single_cw_page_read(nandc);
+	config_nand_single_cw_page_read(nandc, host->use_ecc);
 
 	read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer, size, 0);
 
@@ -1724,20 +1955,14 @@ static int qcom_nandc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	u8 *data_buf, *oob_buf = NULL;
-	int ret;
 
 	nand_read_page_op(chip, page, 0, NULL, 0);
 	data_buf = buf;
 	oob_buf = oob_required ? chip->oob_poi : NULL;
 
 	clear_bam_transaction(nandc);
-	ret = read_page_ecc(host, data_buf, oob_buf);
-	if (ret) {
-		dev_err(nandc->dev, "failure to read page\n");
-		return ret;
-	}
 
-	return parse_read_errors(host, data_buf, oob_buf);
+	return read_page_ecc(host, data_buf, oob_buf, page);
 }
 
 /* implements ecc->read_page_raw() */
@@ -1746,77 +1971,20 @@ static int qcom_nandc_read_page_raw(struct mtd_info *mtd,
 				    int oob_required, int page)
 {
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
-	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
-	u8 *data_buf, *oob_buf;
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int i, ret;
-	int read_loc;
-
-	nand_read_page_op(chip, page, 0, NULL, 0);
-	data_buf = buf;
-	oob_buf = chip->oob_poi;
-
-	host->use_ecc = false;
+	int cw, ret;
+	u8 *data_buf = buf, *oob_buf = chip->oob_poi;
 
-	clear_bam_transaction(nandc);
-	update_rw_regs(host, ecc->steps, true);
-	config_nand_page_read(nandc);
-
-	for (i = 0; i < ecc->steps; i++) {
-		int data_size1, data_size2, oob_size1, oob_size2;
-		int reg_off = FLASH_BUF_ACC;
-
-		data_size1 = mtd->writesize - host->cw_size * (ecc->steps - 1);
-		oob_size1 = host->bbm_size;
-
-		if (i == (ecc->steps - 1)) {
-			data_size2 = ecc->size - data_size1 -
-				     ((ecc->steps - 1) << 2);
-			oob_size2 = (ecc->steps << 2) + host->ecc_bytes_hw +
-				    host->spare_bytes;
-		} else {
-			data_size2 = host->cw_data - data_size1;
-			oob_size2 = host->ecc_bytes_hw + host->spare_bytes;
-		}
-
-		if (nandc->props->is_bam) {
-			read_loc = 0;
-			nandc_set_read_loc(nandc, 0, read_loc, data_size1, 0);
-			read_loc += data_size1;
-
-			nandc_set_read_loc(nandc, 1, read_loc, oob_size1, 0);
-			read_loc += oob_size1;
-
-			nandc_set_read_loc(nandc, 2, read_loc, data_size2, 0);
-			read_loc += data_size2;
-
-			nandc_set_read_loc(nandc, 3, read_loc, oob_size2, 1);
-		}
-
-		config_nand_cw_read(nandc);
-
-		read_data_dma(nandc, reg_off, data_buf, data_size1, 0);
-		reg_off += data_size1;
-		data_buf += data_size1;
-
-		read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0);
-		reg_off += oob_size1;
-		oob_buf += oob_size1;
-
-		read_data_dma(nandc, reg_off, data_buf, data_size2, 0);
-		reg_off += data_size2;
-		data_buf += data_size2;
+	for (cw = 0; cw < ecc->steps; cw++) {
+		ret = qcom_nandc_read_cw_raw(mtd, chip, data_buf, oob_buf,
+					     page, cw);
+		if (ret)
+			return ret;
 
-		read_data_dma(nandc, reg_off, oob_buf, oob_size2, 0);
-		oob_buf += oob_size2;
+		data_buf += host->cw_data;
+		oob_buf += ecc->bytes;
 	}
 
-	ret = submit_descs(nandc);
-	if (ret)
-		dev_err(nandc->dev, "failure to read raw page\n");
-
-	free_descs(nandc);
-
 	return 0;
 }
 
@@ -1827,7 +1995,6 @@ static int qcom_nandc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int ret;
 
 	clear_read_regs(nandc);
 	clear_bam_transaction(nandc);
@@ -1836,11 +2003,7 @@ static int qcom_nandc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	set_address(host, 0, page);
 	update_rw_regs(host, ecc->steps, true);
 
-	ret = read_page_ecc(host, NULL, chip->oob_poi);
-	if (ret)
-		dev_err(nandc->dev, "failure to read oob\n");
-
-	return ret;
+	return read_page_ecc(host, NULL, chip->oob_poi, page);
 }
 
 /* implements ecc->write_page() */
@@ -1988,11 +2151,9 @@ static int qcom_nandc_write_page_raw(struct mtd_info *mtd,
 /*
  * implements ecc->write_oob()
  *
- * the NAND controller cannot write only data or only oob within a codeword,
- * since ecc is calculated for the combined codeword. we first copy the
- * entire contents for the last codeword(data + oob), replace the old oob
- * with the new one in chip->oob_poi, and then write the entire codeword.
- * this read-copy-write operation results in a slight performance loss.
+ * the NAND controller cannot write only data or only OOB within a codeword
+ * since ECC is calculated for the combined codeword. So update the OOB from
+ * chip->oob_poi, and pad the data area with OxFF before writing.
  */
 static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
 				int page)
@@ -2005,19 +2166,13 @@ static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	int ret;
 
 	host->use_ecc = true;
-
-	clear_bam_transaction(nandc);
-	ret = copy_last_cw(host, page);
-	if (ret)
-		return ret;
-
-	clear_read_regs(nandc);
 	clear_bam_transaction(nandc);
 
 	/* calculate the data and oob size for the last codeword/step */
 	data_size = ecc->size - ((ecc->steps - 1) << 2);
 	oob_size = mtd->oobavail;
 
+	memset(nandc->data_buffer, 0xff, host->cw_data);
 	/* override new oob content to last codeword */
 	mtd_ooblayout_get_databytes(mtd, nandc->data_buffer + data_size, oob,
 				    0, mtd->oobavail);
@@ -2049,7 +2204,6 @@ static int qcom_nandc_block_bad(struct mtd_info *mtd, loff_t ofs)
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	int page, ret, bbpos, bad = 0;
-	u32 flash_status;
 
 	page = (int)(ofs >> chip->page_shift) & chip->pagemask;
 
@@ -2066,9 +2220,7 @@ static int qcom_nandc_block_bad(struct mtd_info *mtd, loff_t ofs)
 	if (ret)
 		goto err;
 
-	flash_status = le32_to_cpu(nandc->reg_read_buf[0]);
-
-	if (flash_status & (FS_OP_ERR | FS_MPU_ERR)) {
+	if (check_flash_errors(host, 1)) {
 		dev_warn(nandc->dev, "error when trying to read BBM\n");
 		goto err;
 	}
@@ -2315,27 +2467,40 @@ static const struct mtd_ooblayout_ops qcom_nand_ooblayout_ops = {
 	.free = qcom_nand_ooblayout_free,
 };
 
-static int qcom_nand_host_setup(struct qcom_nand_host *host)
+static int
+qcom_nandc_calc_ecc_bytes(int step_size, int strength)
+{
+	return strength == 4 ? 12 : 16;
+}
+NAND_ECC_CAPS_SINGLE(qcom_nandc_ecc_caps, qcom_nandc_calc_ecc_bytes,
+		     NANDC_STEP_SIZE, 4, 8);
+
+static int qcom_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &host->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
-	int cwperpage, bad_block_byte;
+	int cwperpage, bad_block_byte, ret;
 	bool wide_bus;
 	int ecc_mode = 1;
 
+	/* controller only supports 512 bytes data steps */
+	ecc->size = NANDC_STEP_SIZE;
+	wide_bus = chip->options & NAND_BUSWIDTH_16 ? true : false;
+	cwperpage = mtd->writesize / NANDC_STEP_SIZE;
+
 	/*
-	 * the controller requires each step consists of 512 bytes of data.
-	 * bail out if DT has populated a wrong step size.
+	 * Each CW has 4 available OOB bytes which will be protected with ECC
+	 * so remaining bytes can be used for ECC.
 	 */
-	if (ecc->size != NANDC_STEP_SIZE) {
-		dev_err(nandc->dev, "invalid ecc size\n");
-		return -EINVAL;
+	ret = nand_ecc_choose_conf(chip, &qcom_nandc_ecc_caps,
+				   mtd->oobsize - (cwperpage * 4));
+	if (ret) {
+		dev_err(nandc->dev, "No valid ECC settings possible\n");
+		return ret;
 	}
 
-	wide_bus = chip->options & NAND_BUSWIDTH_16 ? true : false;
-
 	if (ecc->strength >= 8) {
 		/* 8 bit ECC defaults to BCH ECC on all platforms */
 		host->bch_enabled = true;
@@ -2403,7 +2568,6 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 
 	mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops);
 
-	cwperpage = mtd->writesize / ecc->size;
 	nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage,
 				     cwperpage);
 
@@ -2419,12 +2583,6 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 	 * for 8 bit ECC
 	 */
 	host->cw_size = host->cw_data + ecc->bytes;
-
-	if (ecc->bytes * (mtd->writesize / ecc->size) > mtd->oobsize) {
-		dev_err(nandc->dev, "ecc data doesn't fit in OOB area\n");
-		return -EINVAL;
-	}
-
 	bad_block_byte = mtd->writesize - host->cw_size * (cwperpage - 1) + 1;
 
 	host->cfg0 = (cwperpage - 1) << CW_PER_PAGE
@@ -2482,6 +2640,10 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 	return 0;
 }
 
+static const struct nand_controller_ops qcom_nandc_ops = {
+	.attach_chip = qcom_nand_attach_chip,
+};
+
 static int qcom_nandc_alloc(struct qcom_nand_controller *nandc)
 {
 	int ret;
@@ -2570,7 +2732,8 @@ static int qcom_nandc_alloc(struct qcom_nand_controller *nandc)
 	INIT_LIST_HEAD(&nandc->desc_list);
 	INIT_LIST_HEAD(&nandc->host_list);
 
-	nand_hw_control_init(&nandc->controller);
+	nand_controller_init(&nandc->controller);
+	nandc->controller.ops = &qcom_nandc_ops;
 
 	return 0;
 }
@@ -2623,9 +2786,9 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc)
 	return 0;
 }
 
-static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
-			       struct qcom_nand_host *host,
-			       struct device_node *dn)
+static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc,
+					    struct qcom_nand_host *host,
+					    struct device_node *dn)
 {
 	struct nand_chip *chip = &host->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
@@ -2672,30 +2835,13 @@ static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
 	/* set up initial status value */
 	host->status = NAND_STATUS_READY | NAND_STATUS_WP;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	ret = qcom_nand_host_setup(host);
-
-	return ret;
-}
-
-static int qcom_nand_mtd_register(struct qcom_nand_controller *nandc,
-				  struct qcom_nand_host *host,
-				  struct device_node *dn)
-{
-	struct nand_chip *chip = &host->chip;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	int ret;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret)
-		nand_cleanup(mtd_to_nand(mtd));
+		nand_cleanup(chip);
 
 	return ret;
 }
@@ -2704,28 +2850,9 @@ static int qcom_probe_nand_devices(struct qcom_nand_controller *nandc)
 {
 	struct device *dev = nandc->dev;
 	struct device_node *dn = dev->of_node, *child;
-	struct qcom_nand_host *host, *tmp;
+	struct qcom_nand_host *host;
 	int ret;
 
-	for_each_available_child_of_node(dn, child) {
-		host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
-		if (!host) {
-			of_node_put(child);
-			return -ENOMEM;
-		}
-
-		ret = qcom_nand_host_init(nandc, host, child);
-		if (ret) {
-			devm_kfree(dev, host);
-			continue;
-		}
-
-		list_add_tail(&host->node, &nandc->host_list);
-	}
-
-	if (list_empty(&nandc->host_list))
-		return -ENODEV;
-
 	if (nandc->props->is_bam) {
 		free_bam_transaction(nandc);
 		nandc->bam_txn = alloc_bam_transaction(nandc);
@@ -2736,12 +2863,20 @@ static int qcom_probe_nand_devices(struct qcom_nand_controller *nandc)
 		}
 	}
 
-	list_for_each_entry_safe(host, tmp, &nandc->host_list, node) {
-		ret = qcom_nand_mtd_register(nandc, host, child);
+	for_each_available_child_of_node(dn, child) {
+		host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+		if (!host) {
+			of_node_put(child);
+			return -ENOMEM;
+		}
+
+		ret = qcom_nand_host_init_and_register(nandc, host, child);
 		if (ret) {
-			list_del(&host->node);
 			devm_kfree(dev, host);
+			continue;
 		}
+
+		list_add_tail(&host->node, &nandc->host_list);
 	}
 
 	if (list_empty(&nandc->host_list))
@@ -2799,14 +2934,6 @@ static int qcom_nandc_probe(struct platform_device *pdev)
 
 	nandc->props = dev_data;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	nandc->base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(nandc->base))
-		return PTR_ERR(nandc->base);
-
-	nandc->base_phys = res->start;
-	nandc->base_dma = phys_to_dma(dev, (phys_addr_t)res->start);
-
 	nandc->core_clk = devm_clk_get(dev, "core");
 	if (IS_ERR(nandc->core_clk))
 		return PTR_ERR(nandc->core_clk);
@@ -2819,9 +2946,21 @@ static int qcom_nandc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	nandc->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(nandc->base))
+		return PTR_ERR(nandc->base);
+
+	nandc->base_phys = res->start;
+	nandc->base_dma = dma_map_resource(dev, res->start,
+					   resource_size(res),
+					   DMA_BIDIRECTIONAL, 0);
+	if (!nandc->base_dma)
+		return -ENXIO;
+
 	ret = qcom_nandc_alloc(nandc);
 	if (ret)
-		goto err_core_clk;
+		goto err_nandc_alloc;
 
 	ret = clk_prepare_enable(nandc->core_clk);
 	if (ret)
@@ -2847,6 +2986,9 @@ err_aon_clk:
 	clk_disable_unprepare(nandc->core_clk);
 err_core_clk:
 	qcom_nandc_unalloc(nandc);
+err_nandc_alloc:
+	dma_unmap_resource(dev, res->start, resource_size(res),
+			   DMA_BIDIRECTIONAL, 0);
 
 	return ret;
 }
@@ -2854,16 +2996,21 @@ err_core_clk:
 static int qcom_nandc_remove(struct platform_device *pdev)
 {
 	struct qcom_nand_controller *nandc = platform_get_drvdata(pdev);
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	struct qcom_nand_host *host;
 
 	list_for_each_entry(host, &nandc->host_list, node)
 		nand_release(nand_to_mtd(&host->chip));
 
+
 	qcom_nandc_unalloc(nandc);
 
 	clk_disable_unprepare(nandc->aon_clk);
 	clk_disable_unprepare(nandc->core_clk);
 
+	dma_unmap_resource(&pdev->dev, nandc->base_dma, resource_size(res),
+			   DMA_BIDIRECTIONAL, 0);
+
 	return 0;
 }
 
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 19661c5d3220..c21e8892394a 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -162,7 +162,7 @@ enum s3c_nand_clk_state {
  */
 struct s3c2410_nand_info {
 	/* mtd info */
-	struct nand_hw_control		controller;
+	struct nand_controller		controller;
 	struct s3c2410_nand_mtd		*mtds;
 	struct s3c2410_platform_nand	*platform;
 
@@ -802,8 +802,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 
 		mtdinfo->name = set->name;
 
-		return mtd_device_parse_register(mtdinfo, NULL, NULL,
-					 set->partitions, set->nr_partitions);
+		return mtd_device_register(mtdinfo, set->partitions,
+					   set->nr_partitions);
 	}
 
 	return -ENODEV;
@@ -915,20 +915,19 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info,
 }
 
 /**
- * s3c2410_nand_update_chip - post probe update
- * @info: The controller instance.
- * @nmtd: The driver version of the MTD instance.
+ * s3c2410_nand_attach_chip - Init the ECC engine after NAND scan
+ * @chip: The NAND chip
  *
- * This routine is called after the chip probe has successfully completed
- * and the relevant per-chip information updated. This call ensure that
+ * This hook is called by the core after the identification of the NAND chip,
+ * once the relevant per-chip information is up to date.. This call ensure that
  * we update the internal state accordingly.
  *
  * The internal state is currently limited to the ECC state information.
 */
-static int s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
-				    struct s3c2410_nand_mtd *nmtd)
+static int s3c2410_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nmtd->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd);
 
 	switch (chip->ecc.mode) {
 
@@ -998,6 +997,10 @@ static int s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
 	return 0;
 }
 
+static const struct nand_controller_ops s3c24xx_nand_controller_ops = {
+	.attach_chip = s3c2410_nand_attach_chip,
+};
+
 static const struct of_device_id s3c24xx_nand_dt_ids[] = {
 	{
 		.compatible = "samsung,s3c2410-nand",
@@ -1094,7 +1097,8 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, info);
 
-	nand_hw_control_init(&info->controller);
+	nand_controller_init(&info->controller);
+	info->controller.ops = &s3c24xx_nand_controller_ops;
 
 	/* get the clock source and enable it */
 
@@ -1134,8 +1138,13 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "mapped registers at %p\n", info->regs);
 
-	sets = (plat != NULL) ? plat->sets : NULL;
-	nr_sets = (plat != NULL) ? plat->nr_sets : 1;
+	if (!plat->sets || plat->nr_sets < 1) {
+		err = -EINVAL;
+		goto exit_error;
+	}
+
+	sets = plat->sets;
+	nr_sets = plat->nr_sets;
 
 	info->mtd_count = nr_sets;
 
@@ -1152,7 +1161,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	nmtd = info->mtds;
 
-	for (setno = 0; setno < nr_sets; setno++, nmtd++) {
+	for (setno = 0; setno < nr_sets; setno++, nmtd++, sets++) {
 		struct mtd_info *mtd = nand_to_mtd(&nmtd->chip);
 
 		pr_debug("initialising set %d (%p, info %p)\n",
@@ -1161,22 +1170,11 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 		mtd->dev.parent = &pdev->dev;
 		s3c2410_nand_init_chip(info, nmtd, sets);
 
-		err = nand_scan_ident(mtd, (sets) ? sets->nr_chips : 1, NULL);
-		if (err)
-			goto exit_error;
-
-		err = s3c2410_nand_update_chip(info, nmtd);
-		if (err < 0)
-			goto exit_error;
-
-		err = nand_scan_tail(mtd);
+		err = nand_scan(mtd, sets ? sets->nr_chips : 1);
 		if (err)
 			goto exit_error;
 
 		s3c2410_nand_add_partition(info, nmtd, sets);
-
-		if (sets != NULL)
-			sets++;
 	}
 
 	/* initialise the hardware */
diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c
index c7abceffcc40..bb8866e05ff7 100644
--- a/drivers/mtd/nand/raw/sh_flctl.c
+++ b/drivers/mtd/nand/raw/sh_flctl.c
@@ -1002,10 +1002,17 @@ static void flctl_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	flctl->index += len;
 }
 
-static int flctl_chip_init_tail(struct mtd_info *mtd)
+static int flctl_chip_attach_chip(struct nand_chip *chip)
 {
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
-	struct nand_chip *chip = &flctl->chip;
+
+	/*
+	 * NAND_BUSWIDTH_16 may have been set by nand_scan_ident().
+	 * Add the SEL_16BIT flag in flctl->flcmncr_base.
+	 */
+	if (chip->options & NAND_BUSWIDTH_16)
+		flctl->flcmncr_base |= SEL_16BIT;
 
 	if (mtd->writesize == 512) {
 		flctl->page_size = 0;
@@ -1063,6 +1070,10 @@ static int flctl_chip_init_tail(struct mtd_info *mtd)
 	return 0;
 }
 
+static const struct nand_controller_ops flctl_nand_controller_ops = {
+	.attach_chip = flctl_chip_attach_chip,
+};
+
 static irqreturn_t flctl_handle_flste(int irq, void *dev_id)
 {
 	struct sh_flctl *flctl = dev_id;
@@ -1191,25 +1202,8 @@ static int flctl_probe(struct platform_device *pdev)
 
 	flctl_setup_dma(flctl);
 
-	ret = nand_scan_ident(flctl_mtd, 1, NULL);
-	if (ret)
-		goto err_chip;
-
-	if (nand->options & NAND_BUSWIDTH_16) {
-		/*
-		 * NAND_BUSWIDTH_16 may have been set by nand_scan_ident().
-		 * Add the SEL_16BIT flag in pdata->flcmncr_val and re-assign
-		 * flctl->flcmncr_base to pdata->flcmncr_val.
-		 */
-		pdata->flcmncr_val |= SEL_16BIT;
-		flctl->flcmncr_base = pdata->flcmncr_val;
-	}
-
-	ret = flctl_chip_init_tail(flctl_mtd);
-	if (ret)
-		goto err_chip;
-
-	ret = nand_scan_tail(flctl_mtd);
+	nand->dummy_controller.ops = &flctl_nand_controller_ops;
+	ret = nand_scan(flctl_mtd, 1);
 	if (ret)
 		goto err_chip;
 
diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index e93df02c825e..fc171b17a39b 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -21,10 +21,7 @@
 #include <linux/mtd/sharpsl.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
-
-#include <asm/io.h>
-#include <mach/hardware.h>
-#include <asm/mach-types.h>
+#include <linux/io.h>
 
 struct sharpsl_nand {
 	struct nand_chip	chip;
diff --git a/drivers/mtd/nand/raw/sm_common.c b/drivers/mtd/nand/raw/sm_common.c
index 7f5044a79f01..73aafe8c3ef3 100644
--- a/drivers/mtd/nand/raw/sm_common.c
+++ b/drivers/mtd/nand/raw/sm_common.c
@@ -160,19 +160,9 @@ static struct nand_flash_dev nand_xd_flash_ids[] = {
 	{NULL}
 };
 
-int sm_register_device(struct mtd_info *mtd, int smartmedia)
+static int sm_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	int ret;
-
-	chip->options |= NAND_SKIP_BBTSCAN;
-
-	/* Scan for card properties */
-	ret = nand_scan_ident(mtd, 1, smartmedia ?
-		nand_smartmedia_flash_ids : nand_xd_flash_ids);
-
-	if (ret)
-		return ret;
+	struct mtd_info *mtd = nand_to_mtd(chip);
 
 	/* Bad block marker position */
 	chip->badblockpos = 0x05;
@@ -187,12 +177,33 @@ int sm_register_device(struct mtd_info *mtd, int smartmedia)
 	else
 		return -ENODEV;
 
-	ret = nand_scan_tail(mtd);
+	return 0;
+}
+
+static const struct nand_controller_ops sm_controller_ops = {
+	.attach_chip = sm_attach_chip,
+};
+
+int sm_register_device(struct mtd_info *mtd, int smartmedia)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct nand_flash_dev *flash_ids;
+	int ret;
+
+	chip->options |= NAND_SKIP_BBTSCAN;
 
+	/* Scan for card properties */
+	chip->dummy_controller.ops = &sm_controller_ops;
+	flash_ids = smartmedia ? nand_smartmedia_flash_ids : nand_xd_flash_ids;
+	ret = nand_scan_with_ids(mtd, 1, flash_ids);
 	if (ret)
 		return ret;
 
-	return mtd_device_register(mtd, NULL, 0);
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret)
+		nand_cleanup(chip);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(sm_register_device);
 
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index d831a141a196..1f0b7ee38df5 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -29,14 +29,12 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/reset.h>
@@ -127,7 +125,7 @@
 #define NFC_CMD_TYPE_MSK	GENMASK(31, 30)
 #define NFC_NORMAL_OP		(0 << 30)
 #define NFC_ECC_OP		(1 << 30)
-#define NFC_PAGE_OP		(2 << 30)
+#define NFC_PAGE_OP		(2U << 30)
 
 /* define bit use in NFC_RCMD_SET */
 #define NFC_READ_CMD_MSK	GENMASK(7, 0)
@@ -234,7 +232,7 @@ static inline struct sunxi_nand_chip *to_sunxi_nand(struct nand_chip *nand)
  *			controller events
  */
 struct sunxi_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct device *dev;
 	void __iomem *regs;
 	struct clk *ahb_clk;
@@ -247,7 +245,7 @@ struct sunxi_nfc {
 	struct dma_chan *dmac;
 };
 
-static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_hw_control *ctrl)
+static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct sunxi_nfc, controller);
 }
@@ -544,7 +542,7 @@ static void sunxi_nfc_write_buf(struct mtd_info *mtd, const uint8_t *buf,
 
 static uint8_t sunxi_nfc_read_byte(struct mtd_info *mtd)
 {
-	uint8_t ret;
+	uint8_t ret = 0;
 
 	sunxi_nfc_read_buf(mtd, &ret, 1);
 
@@ -1816,12 +1814,21 @@ static void sunxi_nand_ecc_cleanup(struct nand_ecc_ctrl *ecc)
 	}
 }
 
-static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
-			       struct device_node *np)
+static int sunxi_nand_attach_chip(struct nand_chip *nand)
 {
-	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct nand_ecc_ctrl *ecc = &nand->ecc;
+	struct device_node *np = nand_get_flash_node(nand);
 	int ret;
 
+	if (nand->bbt_options & NAND_BBT_USE_FLASH)
+		nand->bbt_options |= NAND_BBT_NO_OOB;
+
+	if (nand->options & NAND_NEED_SCRAMBLING)
+		nand->options |= NAND_NO_SUBPAGE_WRITE;
+
+	nand->options |= NAND_SUBPAGE_READ;
+
 	if (!ecc->size) {
 		ecc->size = nand->ecc_step_ds;
 		ecc->strength = nand->ecc_strength_ds;
@@ -1846,6 +1853,10 @@ static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
 	return 0;
 }
 
+static const struct nand_controller_ops sunxi_nand_controller_ops = {
+	.attach_chip = sunxi_nand_attach_chip,
+};
+
 static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 				struct device_node *np)
 {
@@ -1911,6 +1922,8 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	/* Default tR value specified in the ONFI spec (chapter 4.15.1) */
 	nand->chip_delay = 200;
 	nand->controller = &nfc->controller;
+	nand->controller->ops = &sunxi_nand_controller_ops;
+
 	/*
 	 * Set the ECC mode to the default value in case nothing is specified
 	 * in the DT.
@@ -1927,30 +1940,10 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	mtd = nand_to_mtd(nand);
 	mtd->dev.parent = dev;
 
-	ret = nand_scan_ident(mtd, nsels, NULL);
+	ret = nand_scan(mtd, nsels);
 	if (ret)
 		return ret;
 
-	if (nand->bbt_options & NAND_BBT_USE_FLASH)
-		nand->bbt_options |= NAND_BBT_NO_OOB;
-
-	if (nand->options & NAND_NEED_SCRAMBLING)
-		nand->options |= NAND_NO_SUBPAGE_WRITE;
-
-	nand->options |= NAND_SUBPAGE_READ;
-
-	ret = sunxi_nand_ecc_init(mtd, &nand->ecc, np);
-	if (ret) {
-		dev_err(dev, "ECC init failed: %d\n", ret);
-		return ret;
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
-		return ret;
-	}
-
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "failed to register mtd device: %d\n", ret);
@@ -2012,7 +2005,7 @@ static int sunxi_nfc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	nfc->dev = dev;
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
 	INIT_LIST_HEAD(&nfc->chips);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index f2052fae21c7..72698691727d 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -83,7 +83,7 @@
 #define MAX_CS		4
 
 struct tango_nfc {
-	struct nand_hw_control hw;
+	struct nand_controller hw;
 	void __iomem *reg_base;
 	void __iomem *mem_base;
 	void __iomem *pbus_base;
@@ -517,6 +517,28 @@ static int tango_set_timings(struct mtd_info *mtd, int csline,
 	return 0;
 }
 
+static int tango_attach_chip(struct nand_chip *chip)
+{
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+
+	ecc->mode = NAND_ECC_HW;
+	ecc->algo = NAND_ECC_BCH;
+	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
+
+	ecc->read_page_raw = tango_read_page_raw;
+	ecc->write_page_raw = tango_write_page_raw;
+	ecc->read_page = tango_read_page;
+	ecc->write_page = tango_write_page;
+	ecc->read_oob = tango_read_oob;
+	ecc->write_oob = tango_write_oob;
+
+	return 0;
+}
+
+static const struct nand_controller_ops tango_controller_ops = {
+	.attach_chip = tango_attach_chip,
+};
+
 static int chip_init(struct device *dev, struct device_node *np)
 {
 	u32 cs;
@@ -566,22 +588,7 @@ static int chip_init(struct device *dev, struct device_node *np)
 	mtd_set_ooblayout(mtd, &tango_nand_ooblayout_ops);
 	mtd->dev.parent = dev;
 
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err)
-		return err;
-
-	ecc->mode = NAND_ECC_HW;
-	ecc->algo = NAND_ECC_BCH;
-	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
-
-	ecc->read_page_raw = tango_read_page_raw;
-	ecc->write_page_raw = tango_write_page_raw;
-	ecc->read_page = tango_read_page;
-	ecc->write_page = tango_write_page;
-	ecc->read_oob = tango_read_oob;
-	ecc->write_oob = tango_write_oob;
-
-	err = nand_scan_tail(mtd);
+	err = nand_scan(mtd, 1);
 	if (err)
 		return err;
 
@@ -654,7 +661,8 @@ static int tango_nand_probe(struct platform_device *pdev)
 		return PTR_ERR(nfc->chan);
 
 	platform_set_drvdata(pdev, nfc);
-	nand_hw_control_init(&nfc->hw);
+	nand_controller_init(&nfc->hw);
+	nfc->hw.ops = &tango_controller_ops;
 	nfc->freq_kHz = clk_get_rate(clk) / 1000;
 
 	for_each_child_of_node(pdev->dev.of_node, np) {
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
new file mode 100644
index 000000000000..79da1efc88d1
--- /dev/null
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -0,0 +1,1246 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Stefan Agner <stefan@agner.ch>
+ * Copyright (C) 2014-2015 Lucas Stach <dev@lynxeye.de>
+ * Copyright (C) 2012 Avionic Design GmbH
+ */
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/rawnand.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#define COMMAND					0x00
+#define   COMMAND_GO				BIT(31)
+#define   COMMAND_CLE				BIT(30)
+#define   COMMAND_ALE				BIT(29)
+#define   COMMAND_PIO				BIT(28)
+#define   COMMAND_TX				BIT(27)
+#define   COMMAND_RX				BIT(26)
+#define   COMMAND_SEC_CMD			BIT(25)
+#define   COMMAND_AFT_DAT			BIT(24)
+#define   COMMAND_TRANS_SIZE(size)		((((size) - 1) & 0xf) << 20)
+#define   COMMAND_A_VALID			BIT(19)
+#define   COMMAND_B_VALID			BIT(18)
+#define   COMMAND_RD_STATUS_CHK			BIT(17)
+#define   COMMAND_RBSY_CHK			BIT(16)
+#define   COMMAND_CE(x)				BIT(8 + ((x) & 0x7))
+#define   COMMAND_CLE_SIZE(size)		((((size) - 1) & 0x3) << 4)
+#define   COMMAND_ALE_SIZE(size)		((((size) - 1) & 0xf) << 0)
+
+#define STATUS					0x04
+
+#define ISR					0x08
+#define   ISR_CORRFAIL_ERR			BIT(24)
+#define   ISR_UND				BIT(7)
+#define   ISR_OVR				BIT(6)
+#define   ISR_CMD_DONE				BIT(5)
+#define   ISR_ECC_ERR				BIT(4)
+
+#define IER					0x0c
+#define   IER_ERR_TRIG_VAL(x)			(((x) & 0xf) << 16)
+#define   IER_UND				BIT(7)
+#define   IER_OVR				BIT(6)
+#define   IER_CMD_DONE				BIT(5)
+#define   IER_ECC_ERR				BIT(4)
+#define   IER_GIE				BIT(0)
+
+#define CONFIG					0x10
+#define   CONFIG_HW_ECC				BIT(31)
+#define   CONFIG_ECC_SEL			BIT(30)
+#define   CONFIG_ERR_COR			BIT(29)
+#define   CONFIG_PIPE_EN			BIT(28)
+#define   CONFIG_TVAL_4				(0 << 24)
+#define   CONFIG_TVAL_6				(1 << 24)
+#define   CONFIG_TVAL_8				(2 << 24)
+#define   CONFIG_SKIP_SPARE			BIT(23)
+#define   CONFIG_BUS_WIDTH_16			BIT(21)
+#define   CONFIG_COM_BSY			BIT(20)
+#define   CONFIG_PS_256				(0 << 16)
+#define   CONFIG_PS_512				(1 << 16)
+#define   CONFIG_PS_1024			(2 << 16)
+#define   CONFIG_PS_2048			(3 << 16)
+#define   CONFIG_PS_4096			(4 << 16)
+#define   CONFIG_SKIP_SPARE_SIZE_4		(0 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_8		(1 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_12		(2 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_16		(3 << 14)
+#define   CONFIG_TAG_BYTE_SIZE(x)			((x) & 0xff)
+
+#define TIMING_1				0x14
+#define   TIMING_TRP_RESP(x)			(((x) & 0xf) << 28)
+#define   TIMING_TWB(x)				(((x) & 0xf) << 24)
+#define   TIMING_TCR_TAR_TRR(x)			(((x) & 0xf) << 20)
+#define   TIMING_TWHR(x)			(((x) & 0xf) << 16)
+#define   TIMING_TCS(x)				(((x) & 0x3) << 14)
+#define   TIMING_TWH(x)				(((x) & 0x3) << 12)
+#define   TIMING_TWP(x)				(((x) & 0xf) <<  8)
+#define   TIMING_TRH(x)				(((x) & 0x3) <<  4)
+#define   TIMING_TRP(x)				(((x) & 0xf) <<  0)
+
+#define RESP					0x18
+
+#define TIMING_2				0x1c
+#define   TIMING_TADL(x)			((x) & 0xf)
+
+#define CMD_REG1				0x20
+#define CMD_REG2				0x24
+#define ADDR_REG1				0x28
+#define ADDR_REG2				0x2c
+
+#define DMA_MST_CTRL				0x30
+#define   DMA_MST_CTRL_GO			BIT(31)
+#define   DMA_MST_CTRL_IN			(0 << 30)
+#define   DMA_MST_CTRL_OUT			BIT(30)
+#define   DMA_MST_CTRL_PERF_EN			BIT(29)
+#define   DMA_MST_CTRL_IE_DONE			BIT(28)
+#define   DMA_MST_CTRL_REUSE			BIT(27)
+#define   DMA_MST_CTRL_BURST_1			(2 << 24)
+#define   DMA_MST_CTRL_BURST_4			(3 << 24)
+#define   DMA_MST_CTRL_BURST_8			(4 << 24)
+#define   DMA_MST_CTRL_BURST_16			(5 << 24)
+#define   DMA_MST_CTRL_IS_DONE			BIT(20)
+#define   DMA_MST_CTRL_EN_A			BIT(2)
+#define   DMA_MST_CTRL_EN_B			BIT(1)
+
+#define DMA_CFG_A				0x34
+#define DMA_CFG_B				0x38
+
+#define FIFO_CTRL				0x3c
+#define   FIFO_CTRL_CLR_ALL			BIT(3)
+
+#define DATA_PTR				0x40
+#define TAG_PTR					0x44
+#define ECC_PTR					0x48
+
+#define DEC_STATUS				0x4c
+#define   DEC_STATUS_A_ECC_FAIL			BIT(1)
+#define   DEC_STATUS_ERR_COUNT_MASK		0x00ff0000
+#define   DEC_STATUS_ERR_COUNT_SHIFT		16
+
+#define HWSTATUS_CMD				0x50
+#define HWSTATUS_MASK				0x54
+#define   HWSTATUS_RDSTATUS_MASK(x)		(((x) & 0xff) << 24)
+#define   HWSTATUS_RDSTATUS_VALUE(x)		(((x) & 0xff) << 16)
+#define   HWSTATUS_RBSY_MASK(x)			(((x) & 0xff) << 8)
+#define   HWSTATUS_RBSY_VALUE(x)		(((x) & 0xff) << 0)
+
+#define BCH_CONFIG				0xcc
+#define   BCH_ENABLE				BIT(0)
+#define   BCH_TVAL_4				(0 << 4)
+#define   BCH_TVAL_8				(1 << 4)
+#define   BCH_TVAL_14				(2 << 4)
+#define   BCH_TVAL_16				(3 << 4)
+
+#define DEC_STAT_RESULT				0xd0
+#define DEC_STAT_BUF				0xd4
+#define   DEC_STAT_BUF_FAIL_SEC_FLAG_MASK	0xff000000
+#define   DEC_STAT_BUF_FAIL_SEC_FLAG_SHIFT	24
+#define   DEC_STAT_BUF_CORR_SEC_FLAG_MASK	0x00ff0000
+#define   DEC_STAT_BUF_CORR_SEC_FLAG_SHIFT	16
+#define   DEC_STAT_BUF_MAX_CORR_CNT_MASK	0x00001f00
+#define   DEC_STAT_BUF_MAX_CORR_CNT_SHIFT	8
+
+#define OFFSET(val, off)	((val) < (off) ? 0 : (val) - (off))
+
+#define SKIP_SPARE_BYTES	4
+#define BITS_PER_STEP_RS	18
+#define BITS_PER_STEP_BCH	13
+
+#define INT_MASK		(IER_UND | IER_OVR | IER_CMD_DONE | IER_GIE)
+#define HWSTATUS_CMD_DEFAULT	NAND_STATUS_READY
+#define HWSTATUS_MASK_DEFAULT	(HWSTATUS_RDSTATUS_MASK(1) | \
+				HWSTATUS_RDSTATUS_VALUE(0) | \
+				HWSTATUS_RBSY_MASK(NAND_STATUS_READY) | \
+				HWSTATUS_RBSY_VALUE(NAND_STATUS_READY))
+
+struct tegra_nand_controller {
+	struct nand_controller controller;
+	struct device *dev;
+	void __iomem *regs;
+	int irq;
+	struct clk *clk;
+	struct completion command_complete;
+	struct completion dma_complete;
+	bool last_read_error;
+	int cur_cs;
+	struct nand_chip *chip;
+};
+
+struct tegra_nand_chip {
+	struct nand_chip chip;
+	struct gpio_desc *wp_gpio;
+	struct mtd_oob_region ecc;
+	u32 config;
+	u32 config_ecc;
+	u32 bch_config;
+	int cs[1];
+};
+
+static inline struct tegra_nand_controller *
+			to_tegra_ctrl(struct nand_controller *hw_ctrl)
+{
+	return container_of(hw_ctrl, struct tegra_nand_controller, controller);
+}
+
+static inline struct tegra_nand_chip *to_tegra_chip(struct nand_chip *chip)
+{
+	return container_of(chip, struct tegra_nand_chip, chip);
+}
+
+static int tegra_nand_ooblayout_rs_ecc(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	int bytes_per_step = DIV_ROUND_UP(BITS_PER_STEP_RS * chip->ecc.strength,
+					  BITS_PER_BYTE);
+
+	if (section > 0)
+		return -ERANGE;
+
+	oobregion->offset = SKIP_SPARE_BYTES;
+	oobregion->length = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+	return 0;
+}
+
+static int tegra_nand_ooblayout_no_free(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *oobregion)
+{
+	return -ERANGE;
+}
+
+static const struct mtd_ooblayout_ops tegra_nand_oob_rs_ops = {
+	.ecc = tegra_nand_ooblayout_rs_ecc,
+	.free = tegra_nand_ooblayout_no_free,
+};
+
+static int tegra_nand_ooblayout_bch_ecc(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	int bytes_per_step = DIV_ROUND_UP(BITS_PER_STEP_BCH * chip->ecc.strength,
+					  BITS_PER_BYTE);
+
+	if (section > 0)
+		return -ERANGE;
+
+	oobregion->offset = SKIP_SPARE_BYTES;
+	oobregion->length = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops tegra_nand_oob_bch_ops = {
+	.ecc = tegra_nand_ooblayout_bch_ecc,
+	.free = tegra_nand_ooblayout_no_free,
+};
+
+static irqreturn_t tegra_nand_irq(int irq, void *data)
+{
+	struct tegra_nand_controller *ctrl = data;
+	u32 isr, dma;
+
+	isr = readl_relaxed(ctrl->regs + ISR);
+	dma = readl_relaxed(ctrl->regs + DMA_MST_CTRL);
+	dev_dbg(ctrl->dev, "isr %08x\n", isr);
+
+	if (!isr && !(dma & DMA_MST_CTRL_IS_DONE))
+		return IRQ_NONE;
+
+	/*
+	 * The bit name is somewhat missleading: This is also set when
+	 * HW ECC was successful. The data sheet states:
+	 * Correctable OR Un-correctable errors occurred in the DMA transfer...
+	 */
+	if (isr & ISR_CORRFAIL_ERR)
+		ctrl->last_read_error = true;
+
+	if (isr & ISR_CMD_DONE)
+		complete(&ctrl->command_complete);
+
+	if (isr & ISR_UND)
+		dev_err(ctrl->dev, "FIFO underrun\n");
+
+	if (isr & ISR_OVR)
+		dev_err(ctrl->dev, "FIFO overrun\n");
+
+	/* handle DMA interrupts */
+	if (dma & DMA_MST_CTRL_IS_DONE) {
+		writel_relaxed(dma, ctrl->regs + DMA_MST_CTRL);
+		complete(&ctrl->dma_complete);
+	}
+
+	/* clear interrupts */
+	writel_relaxed(isr, ctrl->regs + ISR);
+
+	return IRQ_HANDLED;
+}
+
+static const char * const tegra_nand_reg_names[] = {
+	"COMMAND",
+	"STATUS",
+	"ISR",
+	"IER",
+	"CONFIG",
+	"TIMING",
+	NULL,
+	"TIMING2",
+	"CMD_REG1",
+	"CMD_REG2",
+	"ADDR_REG1",
+	"ADDR_REG2",
+	"DMA_MST_CTRL",
+	"DMA_CFG_A",
+	"DMA_CFG_B",
+	"FIFO_CTRL",
+};
+
+static void tegra_nand_dump_reg(struct tegra_nand_controller *ctrl)
+{
+	u32 reg;
+	int i;
+
+	dev_err(ctrl->dev, "Tegra NAND controller register dump\n");
+	for (i = 0; i < ARRAY_SIZE(tegra_nand_reg_names); i++) {
+		const char *reg_name = tegra_nand_reg_names[i];
+
+		if (!reg_name)
+			continue;
+
+		reg = readl_relaxed(ctrl->regs + (i * 4));
+		dev_err(ctrl->dev, "%s: 0x%08x\n", reg_name, reg);
+	}
+}
+
+static void tegra_nand_controller_abort(struct tegra_nand_controller *ctrl)
+{
+	u32 isr, dma;
+
+	disable_irq(ctrl->irq);
+
+	/* Abort current command/DMA operation */
+	writel_relaxed(0, ctrl->regs + DMA_MST_CTRL);
+	writel_relaxed(0, ctrl->regs + COMMAND);
+
+	/* clear interrupts */
+	isr = readl_relaxed(ctrl->regs + ISR);
+	writel_relaxed(isr, ctrl->regs + ISR);
+	dma = readl_relaxed(ctrl->regs + DMA_MST_CTRL);
+	writel_relaxed(dma, ctrl->regs + DMA_MST_CTRL);
+
+	reinit_completion(&ctrl->command_complete);
+	reinit_completion(&ctrl->dma_complete);
+
+	enable_irq(ctrl->irq);
+}
+
+static int tegra_nand_cmd(struct nand_chip *chip,
+			  const struct nand_subop *subop)
+{
+	const struct nand_op_instr *instr;
+	const struct nand_op_instr *instr_data_in = NULL;
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	unsigned int op_id, size = 0, offset = 0;
+	bool first_cmd = true;
+	u32 reg, cmd = 0;
+	int ret;
+
+	for (op_id = 0; op_id < subop->ninstrs; op_id++) {
+		unsigned int naddrs, i;
+		const u8 *addrs;
+		u32 addr1 = 0, addr2 = 0;
+
+		instr = &subop->instrs[op_id];
+
+		switch (instr->type) {
+		case NAND_OP_CMD_INSTR:
+			if (first_cmd) {
+				cmd |= COMMAND_CLE;
+				writel_relaxed(instr->ctx.cmd.opcode,
+					       ctrl->regs + CMD_REG1);
+			} else {
+				cmd |= COMMAND_SEC_CMD;
+				writel_relaxed(instr->ctx.cmd.opcode,
+					       ctrl->regs + CMD_REG2);
+			}
+			first_cmd = false;
+			break;
+
+		case NAND_OP_ADDR_INSTR:
+			offset = nand_subop_get_addr_start_off(subop, op_id);
+			naddrs = nand_subop_get_num_addr_cyc(subop, op_id);
+			addrs = &instr->ctx.addr.addrs[offset];
+
+			cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(naddrs);
+			for (i = 0; i < min_t(unsigned int, 4, naddrs); i++)
+				addr1 |= *addrs++ << (BITS_PER_BYTE * i);
+			naddrs -= i;
+			for (i = 0; i < min_t(unsigned int, 4, naddrs); i++)
+				addr2 |= *addrs++ << (BITS_PER_BYTE * i);
+
+			writel_relaxed(addr1, ctrl->regs + ADDR_REG1);
+			writel_relaxed(addr2, ctrl->regs + ADDR_REG2);
+			break;
+
+		case NAND_OP_DATA_IN_INSTR:
+			size = nand_subop_get_data_len(subop, op_id);
+			offset = nand_subop_get_data_start_off(subop, op_id);
+
+			cmd |= COMMAND_TRANS_SIZE(size) | COMMAND_PIO |
+				COMMAND_RX | COMMAND_A_VALID;
+
+			instr_data_in = instr;
+			break;
+
+		case NAND_OP_DATA_OUT_INSTR:
+			size = nand_subop_get_data_len(subop, op_id);
+			offset = nand_subop_get_data_start_off(subop, op_id);
+
+			cmd |= COMMAND_TRANS_SIZE(size) | COMMAND_PIO |
+				COMMAND_TX | COMMAND_A_VALID;
+			memcpy(&reg, instr->ctx.data.buf.out + offset, size);
+
+			writel_relaxed(reg, ctrl->regs + RESP);
+			break;
+
+		case NAND_OP_WAITRDY_INSTR:
+			cmd |= COMMAND_RBSY_CHK;
+			break;
+		}
+	}
+
+	cmd |= COMMAND_GO | COMMAND_CE(ctrl->cur_cs);
+	writel_relaxed(cmd, ctrl->regs + COMMAND);
+	ret = wait_for_completion_timeout(&ctrl->command_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "COMMAND timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		return -ETIMEDOUT;
+	}
+
+	if (instr_data_in) {
+		reg = readl_relaxed(ctrl->regs + RESP);
+		memcpy(instr_data_in->ctx.data.buf.in + offset, &reg, size);
+	}
+
+	return 0;
+}
+
+static const struct nand_op_parser tegra_nand_op_parser = NAND_OP_PARSER(
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(true, 8),
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(true)),
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_DATA_OUT_ELEM(false, 4)),
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(true, 8),
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(true),
+		NAND_OP_PARSER_PAT_DATA_IN_ELEM(true, 4)),
+	);
+
+static int tegra_nand_exec_op(struct nand_chip *chip,
+			      const struct nand_operation *op,
+			      bool check_only)
+{
+	return nand_op_parser_exec_op(chip, &tegra_nand_op_parser, op,
+				      check_only);
+}
+
+static void tegra_nand_select_chip(struct mtd_info *mtd, int die_nr)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+
+	WARN_ON(die_nr >= (int)ARRAY_SIZE(nand->cs));
+
+	if (die_nr < 0 || die_nr > 0) {
+		ctrl->cur_cs = -1;
+		return;
+	}
+
+	ctrl->cur_cs = nand->cs[die_nr];
+}
+
+static void tegra_nand_hw_ecc(struct tegra_nand_controller *ctrl,
+			      struct nand_chip *chip, bool enable)
+{
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+
+	if (chip->ecc.algo == NAND_ECC_BCH && enable)
+		writel_relaxed(nand->bch_config, ctrl->regs + BCH_CONFIG);
+	else
+		writel_relaxed(0, ctrl->regs + BCH_CONFIG);
+
+	if (enable)
+		writel_relaxed(nand->config_ecc, ctrl->regs + CONFIG);
+	else
+		writel_relaxed(nand->config, ctrl->regs + CONFIG);
+}
+
+static int tegra_nand_page_xfer(struct mtd_info *mtd, struct nand_chip *chip,
+				void *buf, void *oob_buf, int oob_len, int page,
+				bool read)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	dma_addr_t dma_addr = 0, dma_addr_oob = 0;
+	u32 addr1, cmd, dma_ctrl;
+	int ret;
+
+	if (read) {
+		writel_relaxed(NAND_CMD_READ0, ctrl->regs + CMD_REG1);
+		writel_relaxed(NAND_CMD_READSTART, ctrl->regs + CMD_REG2);
+	} else {
+		writel_relaxed(NAND_CMD_SEQIN, ctrl->regs + CMD_REG1);
+		writel_relaxed(NAND_CMD_PAGEPROG, ctrl->regs + CMD_REG2);
+	}
+	cmd = COMMAND_CLE | COMMAND_SEC_CMD;
+
+	/* Lower 16-bits are column, by default 0 */
+	addr1 = page << 16;
+
+	if (!buf)
+		addr1 |= mtd->writesize;
+	writel_relaxed(addr1, ctrl->regs + ADDR_REG1);
+
+	if (chip->options & NAND_ROW_ADDR_3) {
+		writel_relaxed(page >> 16, ctrl->regs + ADDR_REG2);
+		cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(5);
+	} else {
+		cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(4);
+	}
+
+	if (buf) {
+		dma_addr = dma_map_single(ctrl->dev, buf, mtd->writesize, dir);
+		ret = dma_mapping_error(ctrl->dev, dma_addr);
+		if (ret) {
+			dev_err(ctrl->dev, "dma mapping error\n");
+			return -EINVAL;
+		}
+
+		writel_relaxed(mtd->writesize - 1, ctrl->regs + DMA_CFG_A);
+		writel_relaxed(dma_addr, ctrl->regs + DATA_PTR);
+	}
+
+	if (oob_buf) {
+		dma_addr_oob = dma_map_single(ctrl->dev, oob_buf, mtd->oobsize,
+					      dir);
+		ret = dma_mapping_error(ctrl->dev, dma_addr_oob);
+		if (ret) {
+			dev_err(ctrl->dev, "dma mapping error\n");
+			ret = -EINVAL;
+			goto err_unmap_dma_page;
+		}
+
+		writel_relaxed(oob_len - 1, ctrl->regs + DMA_CFG_B);
+		writel_relaxed(dma_addr_oob, ctrl->regs + TAG_PTR);
+	}
+
+	dma_ctrl = DMA_MST_CTRL_GO | DMA_MST_CTRL_PERF_EN |
+		   DMA_MST_CTRL_IE_DONE | DMA_MST_CTRL_IS_DONE |
+		   DMA_MST_CTRL_BURST_16;
+
+	if (buf)
+		dma_ctrl |= DMA_MST_CTRL_EN_A;
+	if (oob_buf)
+		dma_ctrl |= DMA_MST_CTRL_EN_B;
+
+	if (read)
+		dma_ctrl |= DMA_MST_CTRL_IN | DMA_MST_CTRL_REUSE;
+	else
+		dma_ctrl |= DMA_MST_CTRL_OUT;
+
+	writel_relaxed(dma_ctrl, ctrl->regs + DMA_MST_CTRL);
+
+	cmd |= COMMAND_GO | COMMAND_RBSY_CHK | COMMAND_TRANS_SIZE(9) |
+	       COMMAND_CE(ctrl->cur_cs);
+
+	if (buf)
+		cmd |= COMMAND_A_VALID;
+	if (oob_buf)
+		cmd |= COMMAND_B_VALID;
+
+	if (read)
+		cmd |= COMMAND_RX;
+	else
+		cmd |= COMMAND_TX | COMMAND_AFT_DAT;
+
+	writel_relaxed(cmd, ctrl->regs + COMMAND);
+
+	ret = wait_for_completion_timeout(&ctrl->command_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "COMMAND timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		ret = -ETIMEDOUT;
+		goto err_unmap_dma;
+	}
+
+	ret = wait_for_completion_timeout(&ctrl->dma_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "DMA timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		ret = -ETIMEDOUT;
+		goto err_unmap_dma;
+	}
+	ret = 0;
+
+err_unmap_dma:
+	if (oob_buf)
+		dma_unmap_single(ctrl->dev, dma_addr_oob, mtd->oobsize, dir);
+err_unmap_dma_page:
+	if (buf)
+		dma_unmap_single(ctrl->dev, dma_addr, mtd->writesize, dir);
+
+	return ret;
+}
+
+static int tegra_nand_read_page_raw(struct mtd_info *mtd,
+				    struct nand_chip *chip, u8 *buf,
+				    int oob_required, int page)
+{
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+
+	return tegra_nand_page_xfer(mtd, chip, buf, oob_buf,
+				    mtd->oobsize, page, true);
+}
+
+static int tegra_nand_write_page_raw(struct mtd_info *mtd,
+				     struct nand_chip *chip, const u8 *buf,
+				     int oob_required, int page)
+{
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+
+	return tegra_nand_page_xfer(mtd, chip, (void *)buf, oob_buf,
+				     mtd->oobsize, page, false);
+}
+
+static int tegra_nand_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
+			       int page)
+{
+	return tegra_nand_page_xfer(mtd, chip, NULL, chip->oob_poi,
+				    mtd->oobsize, page, true);
+}
+
+static int tegra_nand_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
+				int page)
+{
+	return tegra_nand_page_xfer(mtd, chip, NULL, chip->oob_poi,
+				    mtd->oobsize, page, false);
+}
+
+static int tegra_nand_read_page_hwecc(struct mtd_info *mtd,
+				      struct nand_chip *chip, u8 *buf,
+				      int oob_required, int page)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+	u32 dec_stat, max_corr_cnt;
+	unsigned long fail_sec_flag;
+	int ret;
+
+	tegra_nand_hw_ecc(ctrl, chip, true);
+	ret = tegra_nand_page_xfer(mtd, chip, buf, oob_buf, 0, page, true);
+	tegra_nand_hw_ecc(ctrl, chip, false);
+	if (ret)
+		return ret;
+
+	/* No correctable or un-correctable errors, page must have 0 bitflips */
+	if (!ctrl->last_read_error)
+		return 0;
+
+	/*
+	 * Correctable or un-correctable errors occurred. Use DEC_STAT_BUF
+	 * which contains information for all ECC selections.
+	 *
+	 * Note that since we do not use Command Queues DEC_RESULT does not
+	 * state the number of pages we can read from the DEC_STAT_BUF. But
+	 * since CORRFAIL_ERR did occur during page read we do have a valid
+	 * result in DEC_STAT_BUF.
+	 */
+	ctrl->last_read_error = false;
+	dec_stat = readl_relaxed(ctrl->regs + DEC_STAT_BUF);
+
+	fail_sec_flag = (dec_stat & DEC_STAT_BUF_FAIL_SEC_FLAG_MASK) >>
+			DEC_STAT_BUF_FAIL_SEC_FLAG_SHIFT;
+
+	max_corr_cnt = (dec_stat & DEC_STAT_BUF_MAX_CORR_CNT_MASK) >>
+		       DEC_STAT_BUF_MAX_CORR_CNT_SHIFT;
+
+	if (fail_sec_flag) {
+		int bit, max_bitflips = 0;
+
+		/*
+		 * Since we do not support subpage writes, a complete page
+		 * is either written or not. We can take a shortcut here by
+		 * checking wheather any of the sector has been successful
+		 * read. If at least one sectors has been read successfully,
+		 * the page must have been a written previously. It cannot
+		 * be an erased page.
+		 *
+		 * E.g. controller might return fail_sec_flag with 0x4, which
+		 * would mean only the third sector failed to correct. The
+		 * page must have been written and the third sector is really
+		 * not correctable anymore.
+		 */
+		if (fail_sec_flag ^ GENMASK(chip->ecc.steps - 1, 0)) {
+			mtd->ecc_stats.failed += hweight8(fail_sec_flag);
+			return max_corr_cnt;
+		}
+
+		/*
+		 * All sectors failed to correct, but the ECC isn't smart
+		 * enough to figure out if a page is really just erased.
+		 * Read OOB data and check whether data/OOB is completely
+		 * erased or if error correction just failed for all sub-
+		 * pages.
+		 */
+		ret = tegra_nand_read_oob(mtd, chip, page);
+		if (ret < 0)
+			return ret;
+
+		for_each_set_bit(bit, &fail_sec_flag, chip->ecc.steps) {
+			u8 *data = buf + (chip->ecc.size * bit);
+			u8 *oob = chip->oob_poi + nand->ecc.offset +
+				  (chip->ecc.bytes * bit);
+
+			ret = nand_check_erased_ecc_chunk(data, chip->ecc.size,
+							  oob, chip->ecc.bytes,
+							  NULL, 0,
+							  chip->ecc.strength);
+			if (ret < 0) {
+				mtd->ecc_stats.failed++;
+			} else {
+				mtd->ecc_stats.corrected += ret;
+				max_bitflips = max(ret, max_bitflips);
+			}
+		}
+
+		return max_t(unsigned int, max_corr_cnt, max_bitflips);
+	} else {
+		int corr_sec_flag;
+
+		corr_sec_flag = (dec_stat & DEC_STAT_BUF_CORR_SEC_FLAG_MASK) >>
+				DEC_STAT_BUF_CORR_SEC_FLAG_SHIFT;
+
+		/*
+		 * The value returned in the register is the maximum of
+		 * bitflips encountered in any of the ECC regions. As there is
+		 * no way to get the number of bitflips in a specific regions
+		 * we are not able to deliver correct stats but instead
+		 * overestimate the number of corrected bitflips by assuming
+		 * that all regions where errors have been corrected
+		 * encountered the maximum number of bitflips.
+		 */
+		mtd->ecc_stats.corrected += max_corr_cnt * hweight8(corr_sec_flag);
+
+		return max_corr_cnt;
+	}
+}
+
+static int tegra_nand_write_page_hwecc(struct mtd_info *mtd,
+				       struct nand_chip *chip, const u8 *buf,
+				       int oob_required, int page)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+	int ret;
+
+	tegra_nand_hw_ecc(ctrl, chip, true);
+	ret = tegra_nand_page_xfer(mtd, chip, (void *)buf, oob_buf,
+				   0, page, false);
+	tegra_nand_hw_ecc(ctrl, chip, false);
+
+	return ret;
+}
+
+static void tegra_nand_setup_timing(struct tegra_nand_controller *ctrl,
+				    const struct nand_sdr_timings *timings)
+{
+	/*
+	 * The period (and all other timings in this function) is in ps,
+	 * so need to take care here to avoid integer overflows.
+	 */
+	unsigned int rate = clk_get_rate(ctrl->clk) / 1000000;
+	unsigned int period = DIV_ROUND_UP(1000000, rate);
+	u32 val, reg = 0;
+
+	val = DIV_ROUND_UP(max3(timings->tAR_min, timings->tRR_min,
+				timings->tRC_min), period);
+	reg |= TIMING_TCR_TAR_TRR(OFFSET(val, 3));
+
+	val = DIV_ROUND_UP(max(max(timings->tCS_min, timings->tCH_min),
+			       max(timings->tALS_min, timings->tALH_min)),
+			   period);
+	reg |= TIMING_TCS(OFFSET(val, 2));
+
+	val = DIV_ROUND_UP(max(timings->tRP_min, timings->tREA_max) + 6000,
+			   period);
+	reg |= TIMING_TRP(OFFSET(val, 1)) | TIMING_TRP_RESP(OFFSET(val, 1));
+
+	reg |= TIMING_TWB(OFFSET(DIV_ROUND_UP(timings->tWB_max, period), 1));
+	reg |= TIMING_TWHR(OFFSET(DIV_ROUND_UP(timings->tWHR_min, period), 1));
+	reg |= TIMING_TWH(OFFSET(DIV_ROUND_UP(timings->tWH_min, period), 1));
+	reg |= TIMING_TWP(OFFSET(DIV_ROUND_UP(timings->tWP_min, period), 1));
+	reg |= TIMING_TRH(OFFSET(DIV_ROUND_UP(timings->tREH_min, period), 1));
+
+	writel_relaxed(reg, ctrl->regs + TIMING_1);
+
+	val = DIV_ROUND_UP(timings->tADL_min, period);
+	reg = TIMING_TADL(OFFSET(val, 3));
+
+	writel_relaxed(reg, ctrl->regs + TIMING_2);
+}
+
+static int tegra_nand_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	const struct nand_sdr_timings *timings;
+
+	timings = nand_get_sdr_timings(conf);
+	if (IS_ERR(timings))
+		return PTR_ERR(timings);
+
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
+		return 0;
+
+	tegra_nand_setup_timing(ctrl, timings);
+
+	return 0;
+}
+
+static const int rs_strength_bootable[] = { 4 };
+static const int rs_strength[] = { 4, 6, 8 };
+static const int bch_strength_bootable[] = { 8, 16 };
+static const int bch_strength[] = { 4, 8, 14, 16 };
+
+static int tegra_nand_get_strength(struct nand_chip *chip, const int *strength,
+				   int strength_len, int bits_per_step,
+				   int oobsize)
+{
+	bool maximize = chip->ecc.options & NAND_ECC_MAXIMIZE;
+	int i;
+
+	/*
+	 * Loop through available strengths. Backwards in case we try to
+	 * maximize the BCH strength.
+	 */
+	for (i = 0; i < strength_len; i++) {
+		int strength_sel, bytes_per_step, bytes_per_page;
+
+		if (maximize) {
+			strength_sel = strength[strength_len - i - 1];
+		} else {
+			strength_sel = strength[i];
+
+			if (strength_sel < chip->ecc_strength_ds)
+				continue;
+		}
+
+		bytes_per_step = DIV_ROUND_UP(bits_per_step * strength_sel,
+					      BITS_PER_BYTE);
+		bytes_per_page = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+		/* Check whether strength fits OOB */
+		if (bytes_per_page < (oobsize - SKIP_SPARE_BYTES))
+			return strength_sel;
+	}
+
+	return -EINVAL;
+}
+
+static int tegra_nand_select_strength(struct nand_chip *chip, int oobsize)
+{
+	const int *strength;
+	int strength_len, bits_per_step;
+
+	switch (chip->ecc.algo) {
+	case NAND_ECC_RS:
+		bits_per_step = BITS_PER_STEP_RS;
+		if (chip->options & NAND_IS_BOOT_MEDIUM) {
+			strength = rs_strength_bootable;
+			strength_len = ARRAY_SIZE(rs_strength_bootable);
+		} else {
+			strength = rs_strength;
+			strength_len = ARRAY_SIZE(rs_strength);
+		}
+		break;
+	case NAND_ECC_BCH:
+		bits_per_step = BITS_PER_STEP_BCH;
+		if (chip->options & NAND_IS_BOOT_MEDIUM) {
+			strength = bch_strength_bootable;
+			strength_len = ARRAY_SIZE(bch_strength_bootable);
+		} else {
+			strength = bch_strength;
+			strength_len = ARRAY_SIZE(bch_strength);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return tegra_nand_get_strength(chip, strength, strength_len,
+				       bits_per_step, oobsize);
+}
+
+static int tegra_nand_attach_chip(struct nand_chip *chip)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int bits_per_step;
+	int ret;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.size = 512;
+	chip->ecc.steps = mtd->writesize / chip->ecc.size;
+	if (chip->ecc_step_ds != 512) {
+		dev_err(ctrl->dev, "Unsupported step size %d\n",
+			chip->ecc_step_ds);
+		return -EINVAL;
+	}
+
+	chip->ecc.read_page = tegra_nand_read_page_hwecc;
+	chip->ecc.write_page = tegra_nand_write_page_hwecc;
+	chip->ecc.read_page_raw = tegra_nand_read_page_raw;
+	chip->ecc.write_page_raw = tegra_nand_write_page_raw;
+	chip->ecc.read_oob = tegra_nand_read_oob;
+	chip->ecc.write_oob = tegra_nand_write_oob;
+
+	if (chip->options & NAND_BUSWIDTH_16)
+		nand->config |= CONFIG_BUS_WIDTH_16;
+
+	if (chip->ecc.algo == NAND_ECC_UNKNOWN) {
+		if (mtd->writesize < 2048)
+			chip->ecc.algo = NAND_ECC_RS;
+		else
+			chip->ecc.algo = NAND_ECC_BCH;
+	}
+
+	if (chip->ecc.algo == NAND_ECC_BCH && mtd->writesize < 2048) {
+		dev_err(ctrl->dev, "BCH supports 2K or 4K page size only\n");
+		return -EINVAL;
+	}
+
+	if (!chip->ecc.strength) {
+		ret = tegra_nand_select_strength(chip, mtd->oobsize);
+		if (ret < 0) {
+			dev_err(ctrl->dev,
+				"No valid strength found, minimum %d\n",
+				chip->ecc_strength_ds);
+			return ret;
+		}
+
+		chip->ecc.strength = ret;
+	}
+
+	nand->config_ecc = CONFIG_PIPE_EN | CONFIG_SKIP_SPARE |
+			   CONFIG_SKIP_SPARE_SIZE_4;
+
+	switch (chip->ecc.algo) {
+	case NAND_ECC_RS:
+		bits_per_step = BITS_PER_STEP_RS * chip->ecc.strength;
+		mtd_set_ooblayout(mtd, &tegra_nand_oob_rs_ops);
+		nand->config_ecc |= CONFIG_HW_ECC | CONFIG_ECC_SEL |
+				    CONFIG_ERR_COR;
+		switch (chip->ecc.strength) {
+		case 4:
+			nand->config_ecc |= CONFIG_TVAL_4;
+			break;
+		case 6:
+			nand->config_ecc |= CONFIG_TVAL_6;
+			break;
+		case 8:
+			nand->config_ecc |= CONFIG_TVAL_8;
+			break;
+		default:
+			dev_err(ctrl->dev, "ECC strength %d not supported\n",
+				chip->ecc.strength);
+			return -EINVAL;
+		}
+		break;
+	case NAND_ECC_BCH:
+		bits_per_step = BITS_PER_STEP_BCH * chip->ecc.strength;
+		mtd_set_ooblayout(mtd, &tegra_nand_oob_bch_ops);
+		nand->bch_config = BCH_ENABLE;
+		switch (chip->ecc.strength) {
+		case 4:
+			nand->bch_config |= BCH_TVAL_4;
+			break;
+		case 8:
+			nand->bch_config |= BCH_TVAL_8;
+			break;
+		case 14:
+			nand->bch_config |= BCH_TVAL_14;
+			break;
+		case 16:
+			nand->bch_config |= BCH_TVAL_16;
+			break;
+		default:
+			dev_err(ctrl->dev, "ECC strength %d not supported\n",
+				chip->ecc.strength);
+			return -EINVAL;
+		}
+		break;
+	default:
+		dev_err(ctrl->dev, "ECC algorithm not supported\n");
+		return -EINVAL;
+	}
+
+	dev_info(ctrl->dev, "Using %s with strength %d per 512 byte step\n",
+		 chip->ecc.algo == NAND_ECC_BCH ? "BCH" : "RS",
+		 chip->ecc.strength);
+
+	chip->ecc.bytes = DIV_ROUND_UP(bits_per_step, BITS_PER_BYTE);
+
+	switch (mtd->writesize) {
+	case 256:
+		nand->config |= CONFIG_PS_256;
+		break;
+	case 512:
+		nand->config |= CONFIG_PS_512;
+		break;
+	case 1024:
+		nand->config |= CONFIG_PS_1024;
+		break;
+	case 2048:
+		nand->config |= CONFIG_PS_2048;
+		break;
+	case 4096:
+		nand->config |= CONFIG_PS_4096;
+		break;
+	default:
+		dev_err(ctrl->dev, "Unsupported writesize %d\n",
+			mtd->writesize);
+		return -ENODEV;
+	}
+
+	/* Store complete configuration for HW ECC in config_ecc */
+	nand->config_ecc |= nand->config;
+
+	/* Non-HW ECC read/writes complete OOB */
+	nand->config |= CONFIG_TAG_BYTE_SIZE(mtd->oobsize - 1);
+	writel_relaxed(nand->config, ctrl->regs + CONFIG);
+
+	return 0;
+}
+
+static const struct nand_controller_ops tegra_nand_controller_ops = {
+	.attach_chip = &tegra_nand_attach_chip,
+};
+
+static int tegra_nand_chips_init(struct device *dev,
+				 struct tegra_nand_controller *ctrl)
+{
+	struct device_node *np = dev->of_node;
+	struct device_node *np_nand;
+	int nsels, nchips = of_get_child_count(np);
+	struct tegra_nand_chip *nand;
+	struct mtd_info *mtd;
+	struct nand_chip *chip;
+	int ret;
+	u32 cs;
+
+	if (nchips != 1) {
+		dev_err(dev, "Currently only one NAND chip supported\n");
+		return -EINVAL;
+	}
+
+	np_nand = of_get_next_child(np, NULL);
+
+	nsels = of_property_count_elems_of_size(np_nand, "reg", sizeof(u32));
+	if (nsels != 1) {
+		dev_err(dev, "Missing/invalid reg property\n");
+		return -EINVAL;
+	}
+
+	/* Retrieve CS id, currently only single die NAND supported */
+	ret = of_property_read_u32(np_nand, "reg", &cs);
+	if (ret) {
+		dev_err(dev, "could not retrieve reg property: %d\n", ret);
+		return ret;
+	}
+
+	nand = devm_kzalloc(dev, sizeof(*nand), GFP_KERNEL);
+	if (!nand)
+		return -ENOMEM;
+
+	nand->cs[0] = cs;
+
+	nand->wp_gpio = devm_gpiod_get_optional(dev, "wp", GPIOD_OUT_LOW);
+
+	if (IS_ERR(nand->wp_gpio)) {
+		ret = PTR_ERR(nand->wp_gpio);
+		dev_err(dev, "Failed to request WP GPIO: %d\n", ret);
+		return ret;
+	}
+
+	chip = &nand->chip;
+	chip->controller = &ctrl->controller;
+
+	mtd = nand_to_mtd(chip);
+
+	mtd->dev.parent = dev;
+	mtd->owner = THIS_MODULE;
+
+	nand_set_flash_node(chip, np_nand);
+
+	if (!mtd->name)
+		mtd->name = "tegra_nand";
+
+	chip->options = NAND_NO_SUBPAGE_WRITE | NAND_USE_BOUNCE_BUFFER;
+	chip->exec_op = tegra_nand_exec_op;
+	chip->select_chip = tegra_nand_select_chip;
+	chip->setup_data_interface = tegra_nand_setup_data_interface;
+
+	ret = nand_scan(mtd, 1);
+	if (ret)
+		return ret;
+
+	mtd_ooblayout_ecc(mtd, 0, &nand->ecc);
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(dev, "Failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
+		return ret;
+	}
+
+	ctrl->chip = chip;
+
+	return 0;
+}
+
+static int tegra_nand_probe(struct platform_device *pdev)
+{
+	struct reset_control *rst;
+	struct tegra_nand_controller *ctrl;
+	struct resource *res;
+	int err = 0;
+
+	ctrl = devm_kzalloc(&pdev->dev, sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return -ENOMEM;
+
+	ctrl->dev = &pdev->dev;
+	nand_controller_init(&ctrl->controller);
+	ctrl->controller.ops = &tegra_nand_controller_ops;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctrl->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ctrl->regs))
+		return PTR_ERR(ctrl->regs);
+
+	rst = devm_reset_control_get(&pdev->dev, "nand");
+	if (IS_ERR(rst))
+		return PTR_ERR(rst);
+
+	ctrl->clk = devm_clk_get(&pdev->dev, "nand");
+	if (IS_ERR(ctrl->clk))
+		return PTR_ERR(ctrl->clk);
+
+	err = clk_prepare_enable(ctrl->clk);
+	if (err)
+		return err;
+
+	err = reset_control_reset(rst);
+	if (err) {
+		dev_err(ctrl->dev, "Failed to reset HW: %d\n", err);
+		goto err_disable_clk;
+	}
+
+	writel_relaxed(HWSTATUS_CMD_DEFAULT, ctrl->regs + HWSTATUS_CMD);
+	writel_relaxed(HWSTATUS_MASK_DEFAULT, ctrl->regs + HWSTATUS_MASK);
+	writel_relaxed(INT_MASK, ctrl->regs + IER);
+
+	init_completion(&ctrl->command_complete);
+	init_completion(&ctrl->dma_complete);
+
+	ctrl->irq = platform_get_irq(pdev, 0);
+	err = devm_request_irq(&pdev->dev, ctrl->irq, tegra_nand_irq, 0,
+			       dev_name(&pdev->dev), ctrl);
+	if (err) {
+		dev_err(ctrl->dev, "Failed to get IRQ: %d\n", err);
+		goto err_disable_clk;
+	}
+
+	writel_relaxed(DMA_MST_CTRL_IS_DONE, ctrl->regs + DMA_MST_CTRL);
+
+	err = tegra_nand_chips_init(ctrl->dev, ctrl);
+	if (err)
+		goto err_disable_clk;
+
+	platform_set_drvdata(pdev, ctrl);
+
+	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(ctrl->clk);
+	return err;
+}
+
+static int tegra_nand_remove(struct platform_device *pdev)
+{
+	struct tegra_nand_controller *ctrl = platform_get_drvdata(pdev);
+	struct nand_chip *chip = ctrl->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ret;
+
+	ret = mtd_device_unregister(mtd);
+	if (ret)
+		return ret;
+
+	nand_cleanup(chip);
+
+	clk_disable_unprepare(ctrl->clk);
+
+	return 0;
+}
+
+static const struct of_device_id tegra_nand_of_match[] = {
+	{ .compatible = "nvidia,tegra20-nand" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, tegra_nand_of_match);
+
+static struct platform_driver tegra_nand_driver = {
+	.driver = {
+		.name = "tegra-nand",
+		.of_match_table = tegra_nand_of_match,
+	},
+	.probe = tegra_nand_probe,
+	.remove = tegra_nand_remove,
+};
+module_platform_driver(tegra_nand_driver);
+
+MODULE_DESCRIPTION("NVIDIA Tegra NAND driver");
+MODULE_AUTHOR("Thierry Reding <thierry.reding@nvidia.com>");
+MODULE_AUTHOR("Lucas Stach <dev@lynxeye.de>");
+MODULE_AUTHOR("Stefan Agner <stefan@agner.ch>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index b567d212fe7d..4d61a14fcb65 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -20,7 +20,7 @@
 #include <linux/mtd/nand_ecc.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
-#include <asm/txx9/ndfmc.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 
 /* TXX9 NDFMC Registers */
 #define TXX9_NDFDTR	0x00
@@ -73,7 +73,7 @@ struct txx9ndfmc_drvdata {
 	void __iomem *base;
 	unsigned char hold;	/* in gbusclock */
 	unsigned char spw;	/* in gbusclock */
-	struct nand_hw_control hw_control;
+	struct nand_controller controller;
 };
 
 static struct platform_device *mtd_to_platdev(struct mtd_info *mtd)
@@ -254,23 +254,25 @@ static void txx9ndfmc_initialize(struct platform_device *dev)
 #define TXX9NDFMC_NS_TO_CYC(gbusclk, ns) \
 	DIV_ROUND_UP((ns) * DIV_ROUND_UP(gbusclk, 1000), 1000000)
 
-static int txx9ndfmc_nand_scan(struct mtd_info *mtd)
+static int txx9ndfmc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	int ret;
-
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (!ret) {
-		if (mtd->writesize >= 512) {
-			/* Hardware ECC 6 byte ECC per 512 Byte data */
-			chip->ecc.size = 512;
-			chip->ecc.bytes = 6;
-		}
-		ret = nand_scan_tail(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	if (mtd->writesize >= 512) {
+		chip->ecc.size = 512;
+		chip->ecc.bytes = 6;
+	} else {
+		chip->ecc.size = 256;
+		chip->ecc.bytes = 3;
 	}
-	return ret;
+
+	return 0;
 }
 
+static const struct nand_controller_ops txx9ndfmc_controller_ops = {
+	.attach_chip = txx9ndfmc_attach_chip,
+};
+
 static int __init txx9ndfmc_probe(struct platform_device *dev)
 {
 	struct txx9ndfmc_platform_data *plat = dev_get_platdata(&dev->dev);
@@ -303,7 +305,8 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 	dev_info(&dev->dev, "CLK:%ldMHz HOLD:%d SPW:%d\n",
 		 (gbusclk + 500000) / 1000000, hold, spw);
 
-	nand_hw_control_init(&drvdata->hw_control);
+	nand_controller_init(&drvdata->controller);
+	drvdata->controller.ops = &txx9ndfmc_controller_ops;
 
 	platform_set_drvdata(dev, drvdata);
 	txx9ndfmc_initialize(dev);
@@ -332,12 +335,9 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		chip->ecc.correct = txx9ndfmc_correct_data;
 		chip->ecc.hwctl = txx9ndfmc_enable_hwecc;
 		chip->ecc.mode = NAND_ECC_HW;
-		/* txx9ndfmc_nand_scan will overwrite ecc.size and ecc.bytes */
-		chip->ecc.size = 256;
-		chip->ecc.bytes = 3;
 		chip->ecc.strength = 1;
 		chip->chip_delay = 100;
-		chip->controller = &drvdata->hw_control;
+		chip->controller = &drvdata->controller;
 
 		nand_set_controller_data(chip, txx9_priv);
 		txx9_priv->dev = dev;
@@ -359,14 +359,14 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		if (plat->wide_mask & (1 << i))
 			chip->options |= NAND_BUSWIDTH_16;
 
-		if (txx9ndfmc_nand_scan(mtd)) {
+		if (nand_scan(mtd, 1)) {
 			kfree(txx9_priv->mtdname);
 			kfree(txx9_priv);
 			continue;
 		}
 		mtd->name = txx9_priv->mtdname;
 
-		mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+		mtd_device_register(mtd, NULL, 0);
 		drvdata->mtds[i] = mtd;
 	}
 
diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c
index d5a22fc96878..6f6dcbf9095b 100644
--- a/drivers/mtd/nand/raw/vf610_nfc.c
+++ b/drivers/mtd/nand/raw/vf610_nfc.c
@@ -747,6 +747,69 @@ static void vf610_nfc_init_controller(struct vf610_nfc *nfc)
 	}
 }
 
+static int vf610_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct vf610_nfc *nfc = mtd_to_nfc(mtd);
+
+	vf610_nfc_init_controller(nfc);
+
+	/* Bad block options. */
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	/* Single buffer only, max 256 OOB minus ECC status */
+	if (mtd->writesize + mtd->oobsize > PAGE_2K + OOB_MAX - 8) {
+		dev_err(nfc->dev, "Unsupported flash page size\n");
+		return -ENXIO;
+	}
+
+	if (chip->ecc.mode != NAND_ECC_HW)
+		return 0;
+
+	if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
+		dev_err(nfc->dev, "Unsupported flash with hwecc\n");
+		return -ENXIO;
+	}
+
+	if (chip->ecc.size != mtd->writesize) {
+		dev_err(nfc->dev, "Step size needs to be page size\n");
+		return -ENXIO;
+	}
+
+	/* Only 64 byte ECC layouts known */
+	if (mtd->oobsize > 64)
+		mtd->oobsize = 64;
+
+	/* Use default large page ECC layout defined in NAND core */
+	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	if (chip->ecc.strength == 32) {
+		nfc->ecc_mode = ECC_60_BYTE;
+		chip->ecc.bytes = 60;
+	} else if (chip->ecc.strength == 24) {
+		nfc->ecc_mode = ECC_45_BYTE;
+		chip->ecc.bytes = 45;
+	} else {
+		dev_err(nfc->dev, "Unsupported ECC strength\n");
+		return -ENXIO;
+	}
+
+	chip->ecc.read_page = vf610_nfc_read_page;
+	chip->ecc.write_page = vf610_nfc_write_page;
+	chip->ecc.read_page_raw = vf610_nfc_read_page_raw;
+	chip->ecc.write_page_raw = vf610_nfc_write_page_raw;
+	chip->ecc.read_oob = vf610_nfc_read_oob;
+	chip->ecc.write_oob = vf610_nfc_write_oob;
+
+	chip->ecc.size = PAGE_2K;
+
+	return 0;
+}
+
+static const struct nand_controller_ops vf610_nfc_controller_ops = {
+	.attach_chip = vf610_nfc_attach_chip,
+};
+
 static int vf610_nfc_probe(struct platform_device *pdev)
 {
 	struct vf610_nfc *nfc;
@@ -827,67 +890,9 @@ static int vf610_nfc_probe(struct platform_device *pdev)
 
 	vf610_nfc_preinit_controller(nfc);
 
-	/* first scan to find the device and get the page size */
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err)
-		goto err_disable_clk;
-
-	vf610_nfc_init_controller(nfc);
-
-	/* Bad block options. */
-	if (chip->bbt_options & NAND_BBT_USE_FLASH)
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-	/* Single buffer only, max 256 OOB minus ECC status */
-	if (mtd->writesize + mtd->oobsize > PAGE_2K + OOB_MAX - 8) {
-		dev_err(nfc->dev, "Unsupported flash page size\n");
-		err = -ENXIO;
-		goto err_disable_clk;
-	}
-
-	if (chip->ecc.mode == NAND_ECC_HW) {
-		if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
-			dev_err(nfc->dev, "Unsupported flash with hwecc\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		if (chip->ecc.size != mtd->writesize) {
-			dev_err(nfc->dev, "Step size needs to be page size\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		/* Only 64 byte ECC layouts known */
-		if (mtd->oobsize > 64)
-			mtd->oobsize = 64;
-
-		/* Use default large page ECC layout defined in NAND core */
-		mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
-		if (chip->ecc.strength == 32) {
-			nfc->ecc_mode = ECC_60_BYTE;
-			chip->ecc.bytes = 60;
-		} else if (chip->ecc.strength == 24) {
-			nfc->ecc_mode = ECC_45_BYTE;
-			chip->ecc.bytes = 45;
-		} else {
-			dev_err(nfc->dev, "Unsupported ECC strength\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		chip->ecc.read_page = vf610_nfc_read_page;
-		chip->ecc.write_page = vf610_nfc_write_page;
-		chip->ecc.read_page_raw = vf610_nfc_read_page_raw;
-		chip->ecc.write_page_raw = vf610_nfc_write_page_raw;
-		chip->ecc.read_oob = vf610_nfc_read_oob;
-		chip->ecc.write_oob = vf610_nfc_write_oob;
-
-		chip->ecc.size = PAGE_2K;
-	}
-
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	/* Scan the NAND chip */
+	chip->dummy_controller.ops = &vf610_nfc_controller_ops;
+	err = nand_scan(mtd, 1);
 	if (err)
 		goto err_disable_clk;
 
diff --git a/drivers/mtd/nand/spi/Kconfig b/drivers/mtd/nand/spi/Kconfig
new file mode 100644
index 000000000000..7c37d2929b68
--- /dev/null
+++ b/drivers/mtd/nand/spi/Kconfig
@@ -0,0 +1,7 @@
+menuconfig MTD_SPI_NAND
+	tristate "SPI NAND device Support"
+	select MTD_NAND_CORE
+	depends on SPI_MASTER
+	select SPI_MEM
+	help
+	  This is the framework for the SPI NAND device drivers.
diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile
new file mode 100644
index 000000000000..b74e074b363a
--- /dev/null
+++ b/drivers/mtd/nand/spi/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+spinand-objs := core.o macronix.o micron.o winbond.o
+obj-$(CONFIG_MTD_SPI_NAND) += spinand.o
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
new file mode 100644
index 000000000000..30f83649c481
--- /dev/null
+++ b/drivers/mtd/nand/spi/core.c
@@ -0,0 +1,1155 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016-2017 Micron Technology, Inc.
+ *
+ * Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#define pr_fmt(fmt)	"spi-nand: " fmt
+
+#include <linux/device.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mtd/spinand.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+static void spinand_cache_op_adjust_colum(struct spinand_device *spinand,
+					  const struct nand_page_io_req *req,
+					  u16 *column)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int shift;
+
+	if (nand->memorg.planes_per_lun < 2)
+		return;
+
+	/* The plane number is passed in MSB just above the column address */
+	shift = fls(nand->memorg.pagesize);
+	*column |= req->pos.plane << shift;
+}
+
+static int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val)
+{
+	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(reg,
+						      spinand->scratchbuf);
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (ret)
+		return ret;
+
+	*val = *spinand->scratchbuf;
+	return 0;
+}
+
+static int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val)
+{
+	struct spi_mem_op op = SPINAND_SET_FEATURE_OP(reg,
+						      spinand->scratchbuf);
+
+	*spinand->scratchbuf = val;
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_read_status(struct spinand_device *spinand, u8 *status)
+{
+	return spinand_read_reg_op(spinand, REG_STATUS, status);
+}
+
+static int spinand_get_cfg(struct spinand_device *spinand, u8 *cfg)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	if (WARN_ON(spinand->cur_target < 0 ||
+		    spinand->cur_target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	*cfg = spinand->cfg_cache[spinand->cur_target];
+	return 0;
+}
+
+static int spinand_set_cfg(struct spinand_device *spinand, u8 cfg)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	if (WARN_ON(spinand->cur_target < 0 ||
+		    spinand->cur_target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	if (spinand->cfg_cache[spinand->cur_target] == cfg)
+		return 0;
+
+	ret = spinand_write_reg_op(spinand, REG_CFG, cfg);
+	if (ret)
+		return ret;
+
+	spinand->cfg_cache[spinand->cur_target] = cfg;
+	return 0;
+}
+
+/**
+ * spinand_upd_cfg() - Update the configuration register
+ * @spinand: the spinand device
+ * @mask: the mask encoding the bits to update in the config reg
+ * @val: the new value to apply
+ *
+ * Update the configuration register.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val)
+{
+	int ret;
+	u8 cfg;
+
+	ret = spinand_get_cfg(spinand, &cfg);
+	if (ret)
+		return ret;
+
+	cfg &= ~mask;
+	cfg |= val;
+
+	return spinand_set_cfg(spinand, cfg);
+}
+
+/**
+ * spinand_select_target() - Select a specific NAND target/die
+ * @spinand: the spinand device
+ * @target: the target/die to select
+ *
+ * Select a new target/die. If chip only has one die, this function is a NOOP.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_select_target(struct spinand_device *spinand, unsigned int target)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	if (WARN_ON(target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	if (spinand->cur_target == target)
+		return 0;
+
+	if (nand->memorg.ntargets == 1) {
+		spinand->cur_target = target;
+		return 0;
+	}
+
+	ret = spinand->select_target(spinand, target);
+	if (ret)
+		return ret;
+
+	spinand->cur_target = target;
+	return 0;
+}
+
+static int spinand_init_cfg_cache(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct device *dev = &spinand->spimem->spi->dev;
+	unsigned int target;
+	int ret;
+
+	spinand->cfg_cache = devm_kcalloc(dev,
+					  nand->memorg.ntargets,
+					  sizeof(*spinand->cfg_cache),
+					  GFP_KERNEL);
+	if (!spinand->cfg_cache)
+		return -ENOMEM;
+
+	for (target = 0; target < nand->memorg.ntargets; target++) {
+		ret = spinand_select_target(spinand, target);
+		if (ret)
+			return ret;
+
+		/*
+		 * We use spinand_read_reg_op() instead of spinand_get_cfg()
+		 * here to bypass the config cache.
+		 */
+		ret = spinand_read_reg_op(spinand, REG_CFG,
+					  &spinand->cfg_cache[target]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int spinand_init_quad_enable(struct spinand_device *spinand)
+{
+	bool enable = false;
+
+	if (!(spinand->flags & SPINAND_HAS_QE_BIT))
+		return 0;
+
+	if (spinand->op_templates.read_cache->data.buswidth == 4 ||
+	    spinand->op_templates.write_cache->data.buswidth == 4 ||
+	    spinand->op_templates.update_cache->data.buswidth == 4)
+		enable = true;
+
+	return spinand_upd_cfg(spinand, CFG_QUAD_ENABLE,
+			       enable ? CFG_QUAD_ENABLE : 0);
+}
+
+static int spinand_ecc_enable(struct spinand_device *spinand,
+			      bool enable)
+{
+	return spinand_upd_cfg(spinand, CFG_ECC_ENABLE,
+			       enable ? CFG_ECC_ENABLE : 0);
+}
+
+static int spinand_write_enable_op(struct spinand_device *spinand)
+{
+	struct spi_mem_op op = SPINAND_WR_EN_DIS_OP(true);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_load_page_op(struct spinand_device *spinand,
+				const struct nand_page_io_req *req)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, &req->pos);
+	struct spi_mem_op op = SPINAND_PAGE_READ_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_read_from_cache_op(struct spinand_device *spinand,
+				      const struct nand_page_io_req *req)
+{
+	struct spi_mem_op op = *spinand->op_templates.read_cache;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_page_io_req adjreq = *req;
+	unsigned int nbytes = 0;
+	void *buf = NULL;
+	u16 column = 0;
+	int ret;
+
+	if (req->datalen) {
+		adjreq.datalen = nanddev_page_size(nand);
+		adjreq.dataoffs = 0;
+		adjreq.databuf.in = spinand->databuf;
+		buf = spinand->databuf;
+		nbytes = adjreq.datalen;
+	}
+
+	if (req->ooblen) {
+		adjreq.ooblen = nanddev_per_page_oobsize(nand);
+		adjreq.ooboffs = 0;
+		adjreq.oobbuf.in = spinand->oobbuf;
+		nbytes += nanddev_per_page_oobsize(nand);
+		if (!buf) {
+			buf = spinand->oobbuf;
+			column = nanddev_page_size(nand);
+		}
+	}
+
+	spinand_cache_op_adjust_colum(spinand, &adjreq, &column);
+	op.addr.val = column;
+
+	/*
+	 * Some controllers are limited in term of max RX data size. In this
+	 * case, just repeat the READ_CACHE operation after updating the
+	 * column.
+	 */
+	while (nbytes) {
+		op.data.buf.in = buf;
+		op.data.nbytes = nbytes;
+		ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		ret = spi_mem_exec_op(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		buf += op.data.nbytes;
+		nbytes -= op.data.nbytes;
+		op.addr.val += op.data.nbytes;
+	}
+
+	if (req->datalen)
+		memcpy(req->databuf.in, spinand->databuf + req->dataoffs,
+		       req->datalen);
+
+	if (req->ooblen) {
+		if (req->mode == MTD_OPS_AUTO_OOB)
+			mtd_ooblayout_get_databytes(mtd, req->oobbuf.in,
+						    spinand->oobbuf,
+						    req->ooboffs,
+						    req->ooblen);
+		else
+			memcpy(req->oobbuf.in, spinand->oobbuf + req->ooboffs,
+			       req->ooblen);
+	}
+
+	return 0;
+}
+
+static int spinand_write_to_cache_op(struct spinand_device *spinand,
+				     const struct nand_page_io_req *req)
+{
+	struct spi_mem_op op = *spinand->op_templates.write_cache;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_page_io_req adjreq = *req;
+	unsigned int nbytes = 0;
+	void *buf = NULL;
+	u16 column = 0;
+	int ret;
+
+	memset(spinand->databuf, 0xff,
+	       nanddev_page_size(nand) +
+	       nanddev_per_page_oobsize(nand));
+
+	if (req->datalen) {
+		memcpy(spinand->databuf + req->dataoffs, req->databuf.out,
+		       req->datalen);
+		adjreq.dataoffs = 0;
+		adjreq.datalen = nanddev_page_size(nand);
+		adjreq.databuf.out = spinand->databuf;
+		nbytes = adjreq.datalen;
+		buf = spinand->databuf;
+	}
+
+	if (req->ooblen) {
+		if (req->mode == MTD_OPS_AUTO_OOB)
+			mtd_ooblayout_set_databytes(mtd, req->oobbuf.out,
+						    spinand->oobbuf,
+						    req->ooboffs,
+						    req->ooblen);
+		else
+			memcpy(spinand->oobbuf + req->ooboffs, req->oobbuf.out,
+			       req->ooblen);
+
+		adjreq.ooblen = nanddev_per_page_oobsize(nand);
+		adjreq.ooboffs = 0;
+		nbytes += nanddev_per_page_oobsize(nand);
+		if (!buf) {
+			buf = spinand->oobbuf;
+			column = nanddev_page_size(nand);
+		}
+	}
+
+	spinand_cache_op_adjust_colum(spinand, &adjreq, &column);
+
+	op = *spinand->op_templates.write_cache;
+	op.addr.val = column;
+
+	/*
+	 * Some controllers are limited in term of max TX data size. In this
+	 * case, split the operation into one LOAD CACHE and one or more
+	 * LOAD RANDOM CACHE.
+	 */
+	while (nbytes) {
+		op.data.buf.out = buf;
+		op.data.nbytes = nbytes;
+
+		ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		ret = spi_mem_exec_op(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		buf += op.data.nbytes;
+		nbytes -= op.data.nbytes;
+		op.addr.val += op.data.nbytes;
+
+		/*
+		 * We need to use the RANDOM LOAD CACHE operation if there's
+		 * more than one iteration, because the LOAD operation resets
+		 * the cache to 0xff.
+		 */
+		if (nbytes) {
+			column = op.addr.val;
+			op = *spinand->op_templates.update_cache;
+			op.addr.val = column;
+		}
+	}
+
+	return 0;
+}
+
+static int spinand_program_op(struct spinand_device *spinand,
+			      const struct nand_page_io_req *req)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, &req->pos);
+	struct spi_mem_op op = SPINAND_PROG_EXEC_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_erase_op(struct spinand_device *spinand,
+			    const struct nand_pos *pos)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, pos);
+	struct spi_mem_op op = SPINAND_BLK_ERASE_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_wait(struct spinand_device *spinand, u8 *s)
+{
+	unsigned long timeo =  jiffies + msecs_to_jiffies(400);
+	u8 status;
+	int ret;
+
+	do {
+		ret = spinand_read_status(spinand, &status);
+		if (ret)
+			return ret;
+
+		if (!(status & STATUS_BUSY))
+			goto out;
+	} while (time_before(jiffies, timeo));
+
+	/*
+	 * Extra read, just in case the STATUS_READY bit has changed
+	 * since our last check
+	 */
+	ret = spinand_read_status(spinand, &status);
+	if (ret)
+		return ret;
+
+out:
+	if (s)
+		*s = status;
+
+	return status & STATUS_BUSY ? -ETIMEDOUT : 0;
+}
+
+static int spinand_read_id_op(struct spinand_device *spinand, u8 *buf)
+{
+	struct spi_mem_op op = SPINAND_READID_OP(0, spinand->scratchbuf,
+						 SPINAND_MAX_ID_LEN);
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (!ret)
+		memcpy(buf, spinand->scratchbuf, SPINAND_MAX_ID_LEN);
+
+	return ret;
+}
+
+static int spinand_reset_op(struct spinand_device *spinand)
+{
+	struct spi_mem_op op = SPINAND_RESET_OP;
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (ret)
+		return ret;
+
+	return spinand_wait(spinand, NULL);
+}
+
+static int spinand_lock_block(struct spinand_device *spinand, u8 lock)
+{
+	return spinand_write_reg_op(spinand, REG_BLOCK_LOCK, lock);
+}
+
+static int spinand_check_ecc_status(struct spinand_device *spinand, u8 status)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	if (spinand->eccinfo.get_status)
+		return spinand->eccinfo.get_status(spinand, status);
+
+	switch (status & STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_HAS_BITFLIPS:
+		/*
+		 * We have no way to know exactly how many bitflips have been
+		 * fixed, so let's return the maximum possible value so that
+		 * wear-leveling layers move the data immediately.
+		 */
+		return nand->eccreq.strength;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static int spinand_read_page(struct spinand_device *spinand,
+			     const struct nand_page_io_req *req,
+			     bool ecc_enabled)
+{
+	u8 status;
+	int ret;
+
+	ret = spinand_load_page_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (ret < 0)
+		return ret;
+
+	ret = spinand_read_from_cache_op(spinand, req);
+	if (ret)
+		return ret;
+
+	if (!ecc_enabled)
+		return 0;
+
+	return spinand_check_ecc_status(spinand, status);
+}
+
+static int spinand_write_page(struct spinand_device *spinand,
+			      const struct nand_page_io_req *req)
+{
+	u8 status;
+	int ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_to_cache_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_program_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (!ret && (status & STATUS_PROG_FAILED))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int spinand_mtd_read(struct mtd_info *mtd, loff_t from,
+			    struct mtd_oob_ops *ops)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int max_bitflips = 0;
+	struct nand_io_iter iter;
+	bool enable_ecc = false;
+	bool ecc_failed = false;
+	int ret = 0;
+
+	if (ops->mode != MTD_OPS_RAW && spinand->eccinfo.ooblayout)
+		enable_ecc = true;
+
+	mutex_lock(&spinand->lock);
+
+	nanddev_io_for_each_page(nand, from, ops, &iter) {
+		ret = spinand_select_target(spinand, iter.req.pos.target);
+		if (ret)
+			break;
+
+		ret = spinand_ecc_enable(spinand, enable_ecc);
+		if (ret)
+			break;
+
+		ret = spinand_read_page(spinand, &iter.req, enable_ecc);
+		if (ret < 0 && ret != -EBADMSG)
+			break;
+
+		if (ret == -EBADMSG) {
+			ecc_failed = true;
+			mtd->ecc_stats.failed++;
+			ret = 0;
+		} else {
+			mtd->ecc_stats.corrected += ret;
+			max_bitflips = max_t(unsigned int, max_bitflips, ret);
+		}
+
+		ops->retlen += iter.req.datalen;
+		ops->oobretlen += iter.req.ooblen;
+	}
+
+	mutex_unlock(&spinand->lock);
+
+	if (ecc_failed && !ret)
+		ret = -EBADMSG;
+
+	return ret ? ret : max_bitflips;
+}
+
+static int spinand_mtd_write(struct mtd_info *mtd, loff_t to,
+			     struct mtd_oob_ops *ops)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct nand_io_iter iter;
+	bool enable_ecc = false;
+	int ret = 0;
+
+	if (ops->mode != MTD_OPS_RAW && mtd->ooblayout)
+		enable_ecc = true;
+
+	mutex_lock(&spinand->lock);
+
+	nanddev_io_for_each_page(nand, to, ops, &iter) {
+		ret = spinand_select_target(spinand, iter.req.pos.target);
+		if (ret)
+			break;
+
+		ret = spinand_ecc_enable(spinand, enable_ecc);
+		if (ret)
+			break;
+
+		ret = spinand_write_page(spinand, &iter.req);
+		if (ret)
+			break;
+
+		ops->retlen += iter.req.datalen;
+		ops->oobretlen += iter.req.ooblen;
+	}
+
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static bool spinand_isbad(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_page_io_req req = {
+		.pos = *pos,
+		.ooblen = 2,
+		.ooboffs = 0,
+		.oobbuf.in = spinand->oobbuf,
+		.mode = MTD_OPS_RAW,
+	};
+
+	memset(spinand->oobbuf, 0, 2);
+	spinand_select_target(spinand, pos->target);
+	spinand_read_page(spinand, &req, false);
+	if (spinand->oobbuf[0] != 0xff || spinand->oobbuf[1] != 0xff)
+		return true;
+
+	return false;
+}
+
+static int spinand_mtd_block_isbad(struct mtd_info *mtd, loff_t offs)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_isbad(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_markbad(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_page_io_req req = {
+		.pos = *pos,
+		.ooboffs = 0,
+		.ooblen = 2,
+		.oobbuf.out = spinand->oobbuf,
+	};
+	int ret;
+
+	/* Erase block before marking it bad. */
+	ret = spinand_select_target(spinand, pos->target);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	spinand_erase_op(spinand, pos);
+
+	memset(spinand->oobbuf, 0, 2);
+	return spinand_write_page(spinand, &req);
+}
+
+static int spinand_mtd_block_markbad(struct mtd_info *mtd, loff_t offs)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_markbad(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_erase(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	u8 status;
+	int ret;
+
+	ret = spinand_select_target(spinand, pos->target);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_erase_op(spinand, pos);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (!ret && (status & STATUS_ERASE_FAILED))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int spinand_mtd_erase(struct mtd_info *mtd,
+			     struct erase_info *einfo)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	int ret;
+
+	mutex_lock(&spinand->lock);
+	ret = nanddev_mtd_erase(mtd, einfo);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_mtd_block_isreserved(struct mtd_info *mtd, loff_t offs)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_isreserved(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static const struct nand_ops spinand_ops = {
+	.erase = spinand_erase,
+	.markbad = spinand_markbad,
+	.isbad = spinand_isbad,
+};
+
+static const struct spinand_manufacturer *spinand_manufacturers[] = {
+	&macronix_spinand_manufacturer,
+	&micron_spinand_manufacturer,
+	&winbond_spinand_manufacturer,
+};
+
+static int spinand_manufacturer_detect(struct spinand_device *spinand)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(spinand_manufacturers); i++) {
+		ret = spinand_manufacturers[i]->ops->detect(spinand);
+		if (ret > 0) {
+			spinand->manufacturer = spinand_manufacturers[i];
+			return 0;
+		} else if (ret < 0) {
+			return ret;
+		}
+	}
+
+	return -ENOTSUPP;
+}
+
+static int spinand_manufacturer_init(struct spinand_device *spinand)
+{
+	if (spinand->manufacturer->ops->init)
+		return spinand->manufacturer->ops->init(spinand);
+
+	return 0;
+}
+
+static void spinand_manufacturer_cleanup(struct spinand_device *spinand)
+{
+	/* Release manufacturer private data */
+	if (spinand->manufacturer->ops->cleanup)
+		return spinand->manufacturer->ops->cleanup(spinand);
+}
+
+static const struct spi_mem_op *
+spinand_select_op_variant(struct spinand_device *spinand,
+			  const struct spinand_op_variants *variants)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	for (i = 0; i < variants->nops; i++) {
+		struct spi_mem_op op = variants->ops[i];
+		unsigned int nbytes;
+		int ret;
+
+		nbytes = nanddev_per_page_oobsize(nand) +
+			 nanddev_page_size(nand);
+
+		while (nbytes) {
+			op.data.nbytes = nbytes;
+			ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+			if (ret)
+				break;
+
+			if (!spi_mem_supports_op(spinand->spimem, &op))
+				break;
+
+			nbytes -= op.data.nbytes;
+		}
+
+		if (!nbytes)
+			return &variants->ops[i];
+	}
+
+	return NULL;
+}
+
+/**
+ * spinand_match_and_init() - Try to find a match between a device ID and an
+ *			      entry in a spinand_info table
+ * @spinand: SPI NAND object
+ * @table: SPI NAND device description table
+ * @table_size: size of the device description table
+ *
+ * Should be used by SPI NAND manufacturer drivers when they want to find a
+ * match between a device ID retrieved through the READ_ID command and an
+ * entry in the SPI NAND description table. If a match is found, the spinand
+ * object will be initialized with information provided by the matching
+ * spinand_info entry.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_match_and_init(struct spinand_device *spinand,
+			   const struct spinand_info *table,
+			   unsigned int table_size, u8 devid)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	for (i = 0; i < table_size; i++) {
+		const struct spinand_info *info = &table[i];
+		const struct spi_mem_op *op;
+
+		if (devid != info->devid)
+			continue;
+
+		nand->memorg = table[i].memorg;
+		nand->eccreq = table[i].eccreq;
+		spinand->eccinfo = table[i].eccinfo;
+		spinand->flags = table[i].flags;
+		spinand->select_target = table[i].select_target;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.read_cache);
+		if (!op)
+			return -ENOTSUPP;
+
+		spinand->op_templates.read_cache = op;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.write_cache);
+		if (!op)
+			return -ENOTSUPP;
+
+		spinand->op_templates.write_cache = op;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.update_cache);
+		spinand->op_templates.update_cache = op;
+
+		return 0;
+	}
+
+	return -ENOTSUPP;
+}
+
+static int spinand_detect(struct spinand_device *spinand)
+{
+	struct device *dev = &spinand->spimem->spi->dev;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	ret = spinand_reset_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_read_id_op(spinand, spinand->id.data);
+	if (ret)
+		return ret;
+
+	spinand->id.len = SPINAND_MAX_ID_LEN;
+
+	ret = spinand_manufacturer_detect(spinand);
+	if (ret) {
+		dev_err(dev, "unknown raw ID %*phN\n", SPINAND_MAX_ID_LEN,
+			spinand->id.data);
+		return ret;
+	}
+
+	if (nand->memorg.ntargets > 1 && !spinand->select_target) {
+		dev_err(dev,
+			"SPI NANDs with more than one die must implement ->select_target()\n");
+		return -EINVAL;
+	}
+
+	dev_info(&spinand->spimem->spi->dev,
+		 "%s SPI NAND was found.\n", spinand->manufacturer->name);
+	dev_info(&spinand->spimem->spi->dev,
+		 "%llu MiB, block size: %zu KiB, page size: %zu, OOB size: %u\n",
+		 nanddev_size(nand) >> 20, nanddev_eraseblock_size(nand) >> 10,
+		 nanddev_page_size(nand), nanddev_per_page_oobsize(nand));
+
+	return 0;
+}
+
+static int spinand_noecc_ooblayout_ecc(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *region)
+{
+	return -ERANGE;
+}
+
+static int spinand_noecc_ooblayout_free(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	/* Reserve 2 bytes for the BBM. */
+	region->offset = 2;
+	region->length = 62;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops spinand_noecc_ooblayout = {
+	.ecc = spinand_noecc_ooblayout_ecc,
+	.free = spinand_noecc_ooblayout_free,
+};
+
+static int spinand_init(struct spinand_device *spinand)
+{
+	struct device *dev = &spinand->spimem->spi->dev;
+	struct mtd_info *mtd = spinand_to_mtd(spinand);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	int ret, i;
+
+	/*
+	 * We need a scratch buffer because the spi_mem interface requires that
+	 * buf passed in spi_mem_op->data.buf be DMA-able.
+	 */
+	spinand->scratchbuf = kzalloc(SPINAND_MAX_ID_LEN, GFP_KERNEL);
+	if (!spinand->scratchbuf)
+		return -ENOMEM;
+
+	ret = spinand_detect(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	/*
+	 * Use kzalloc() instead of devm_kzalloc() here, because some drivers
+	 * may use this buffer for DMA access.
+	 * Memory allocated by devm_ does not guarantee DMA-safe alignment.
+	 */
+	spinand->databuf = kzalloc(nanddev_page_size(nand) +
+			       nanddev_per_page_oobsize(nand),
+			       GFP_KERNEL);
+	if (!spinand->databuf) {
+		ret = -ENOMEM;
+		goto err_free_bufs;
+	}
+
+	spinand->oobbuf = spinand->databuf + nanddev_page_size(nand);
+
+	ret = spinand_init_cfg_cache(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_init_quad_enable(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_upd_cfg(spinand, CFG_OTP_ENABLE, 0);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_manufacturer_init(spinand);
+	if (ret) {
+		dev_err(dev,
+			"Failed to initialize the SPI NAND chip (err = %d)\n",
+			ret);
+		goto err_free_bufs;
+	}
+
+	/* After power up, all blocks are locked, so unlock them here. */
+	for (i = 0; i < nand->memorg.ntargets; i++) {
+		ret = spinand_select_target(spinand, i);
+		if (ret)
+			goto err_free_bufs;
+
+		ret = spinand_lock_block(spinand, BL_ALL_UNLOCKED);
+		if (ret)
+			goto err_free_bufs;
+	}
+
+	ret = nanddev_init(nand, &spinand_ops, THIS_MODULE);
+	if (ret)
+		goto err_manuf_cleanup;
+
+	/*
+	 * Right now, we don't support ECC, so let the whole oob
+	 * area is available for user.
+	 */
+	mtd->_read_oob = spinand_mtd_read;
+	mtd->_write_oob = spinand_mtd_write;
+	mtd->_block_isbad = spinand_mtd_block_isbad;
+	mtd->_block_markbad = spinand_mtd_block_markbad;
+	mtd->_block_isreserved = spinand_mtd_block_isreserved;
+	mtd->_erase = spinand_mtd_erase;
+
+	if (spinand->eccinfo.ooblayout)
+		mtd_set_ooblayout(mtd, spinand->eccinfo.ooblayout);
+	else
+		mtd_set_ooblayout(mtd, &spinand_noecc_ooblayout);
+
+	ret = mtd_ooblayout_count_freebytes(mtd);
+	if (ret < 0)
+		goto err_cleanup_nanddev;
+
+	mtd->oobavail = ret;
+
+	return 0;
+
+err_cleanup_nanddev:
+	nanddev_cleanup(nand);
+
+err_manuf_cleanup:
+	spinand_manufacturer_cleanup(spinand);
+
+err_free_bufs:
+	kfree(spinand->databuf);
+	kfree(spinand->scratchbuf);
+	return ret;
+}
+
+static void spinand_cleanup(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	nanddev_cleanup(nand);
+	spinand_manufacturer_cleanup(spinand);
+	kfree(spinand->databuf);
+	kfree(spinand->scratchbuf);
+}
+
+static int spinand_probe(struct spi_mem *mem)
+{
+	struct spinand_device *spinand;
+	struct mtd_info *mtd;
+	int ret;
+
+	spinand = devm_kzalloc(&mem->spi->dev, sizeof(*spinand),
+			       GFP_KERNEL);
+	if (!spinand)
+		return -ENOMEM;
+
+	spinand->spimem = mem;
+	spi_mem_set_drvdata(mem, spinand);
+	spinand_set_of_node(spinand, mem->spi->dev.of_node);
+	mutex_init(&spinand->lock);
+	mtd = spinand_to_mtd(spinand);
+	mtd->dev.parent = &mem->spi->dev;
+
+	ret = spinand_init(spinand);
+	if (ret)
+		return ret;
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret)
+		goto err_spinand_cleanup;
+
+	return 0;
+
+err_spinand_cleanup:
+	spinand_cleanup(spinand);
+
+	return ret;
+}
+
+static int spinand_remove(struct spi_mem *mem)
+{
+	struct spinand_device *spinand;
+	struct mtd_info *mtd;
+	int ret;
+
+	spinand = spi_mem_get_drvdata(mem);
+	mtd = spinand_to_mtd(spinand);
+
+	ret = mtd_device_unregister(mtd);
+	if (ret)
+		return ret;
+
+	spinand_cleanup(spinand);
+
+	return 0;
+}
+
+static const struct spi_device_id spinand_ids[] = {
+	{ .name = "spi-nand" },
+	{ /* sentinel */ },
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id spinand_of_ids[] = {
+	{ .compatible = "spi-nand" },
+	{ /* sentinel */ },
+};
+#endif
+
+static struct spi_mem_driver spinand_drv = {
+	.spidrv = {
+		.id_table = spinand_ids,
+		.driver = {
+			.name = "spi-nand",
+			.of_match_table = of_match_ptr(spinand_of_ids),
+		},
+	},
+	.probe = spinand_probe,
+	.remove = spinand_remove,
+};
+module_spi_mem_driver(spinand_drv);
+
+MODULE_DESCRIPTION("SPI NAND framework");
+MODULE_AUTHOR("Peter Pan<peterpandong@micron.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c
new file mode 100644
index 000000000000..98f6b9c4b684
--- /dev/null
+++ b/drivers/mtd/nand/spi/macronix.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Macronix
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_MACRONIX		0xC2
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int mx35lfxge4ab_ooblayout_ecc(struct mtd_info *mtd, int section,
+				      struct mtd_oob_region *region)
+{
+	return -ERANGE;
+}
+
+static int mx35lfxge4ab_ooblayout_free(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 2;
+	region->length = mtd->oobsize - 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops mx35lfxge4ab_ooblayout = {
+	.ecc = mx35lfxge4ab_ooblayout_ecc,
+	.free = mx35lfxge4ab_ooblayout_free,
+};
+
+static int mx35lf1ge4ab_get_eccsr(struct spinand_device *spinand, u8 *eccsr)
+{
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0x7c, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_DUMMY(1, 1),
+					  SPI_MEM_OP_DATA_IN(1, eccsr, 1));
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int mx35lf1ge4ab_ecc_get_status(struct spinand_device *spinand,
+				       u8 status)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	u8 eccsr;
+
+	switch (status & STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	case STATUS_ECC_HAS_BITFLIPS:
+		/*
+		 * Let's try to retrieve the real maximum number of bitflips
+		 * in order to avoid forcing the wear-leveling layer to move
+		 * data around if it's not necessary.
+		 */
+		if (mx35lf1ge4ab_get_eccsr(spinand, &eccsr))
+			return nand->eccreq.strength;
+
+		if (WARN_ON(eccsr > nand->eccreq.strength || !eccsr))
+			return nand->eccreq.strength;
+
+		return eccsr;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct spinand_info macronix_spinand_table[] = {
+	SPINAND_INFO("MX35LF1GE4AB", 0x12,
+		     NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 1),
+		     NAND_ECCREQ(4, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout,
+				     mx35lf1ge4ab_ecc_get_status)),
+	SPINAND_INFO("MX35LF2GE4AB", 0x22,
+		     NAND_MEMORG(1, 2048, 64, 64, 2048, 2, 1, 1),
+		     NAND_ECCREQ(4, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL)),
+};
+
+static int macronix_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Macronix SPI NAND read ID needs a dummy byte, so the first byte in
+	 * raw_id is garbage.
+	 */
+	if (id[1] != SPINAND_MFR_MACRONIX)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, macronix_spinand_table,
+				     ARRAY_SIZE(macronix_spinand_table),
+				     id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static const struct spinand_manufacturer_ops macronix_spinand_manuf_ops = {
+	.detect = macronix_spinand_detect,
+};
+
+const struct spinand_manufacturer macronix_spinand_manufacturer = {
+	.id = SPINAND_MFR_MACRONIX,
+	.name = "Macronix",
+	.ops = &macronix_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/nand/spi/micron.c b/drivers/mtd/nand/spi/micron.c
new file mode 100644
index 000000000000..9c4381d6847b
--- /dev/null
+++ b/drivers/mtd/nand/spi/micron.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2017 Micron Technology, Inc.
+ *
+ * Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_MICRON		0x2c
+
+#define MICRON_STATUS_ECC_MASK		GENMASK(7, 4)
+#define MICRON_STATUS_ECC_NO_BITFLIPS	(0 << 4)
+#define MICRON_STATUS_ECC_1TO3_BITFLIPS	(1 << 4)
+#define MICRON_STATUS_ECC_4TO6_BITFLIPS	(3 << 4)
+#define MICRON_STATUS_ECC_7TO8_BITFLIPS	(5 << 4)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int mt29f2g01abagd_ooblayout_ecc(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 64;
+	region->length = 64;
+
+	return 0;
+}
+
+static int mt29f2g01abagd_ooblayout_free(struct mtd_info *mtd, int section,
+					 struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	/* Reserve 2 bytes for the BBM. */
+	region->offset = 2;
+	region->length = 62;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops mt29f2g01abagd_ooblayout = {
+	.ecc = mt29f2g01abagd_ooblayout_ecc,
+	.free = mt29f2g01abagd_ooblayout_free,
+};
+
+static int mt29f2g01abagd_ecc_get_status(struct spinand_device *spinand,
+					 u8 status)
+{
+	switch (status & MICRON_STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	case MICRON_STATUS_ECC_1TO3_BITFLIPS:
+		return 3;
+
+	case MICRON_STATUS_ECC_4TO6_BITFLIPS:
+		return 6;
+
+	case MICRON_STATUS_ECC_7TO8_BITFLIPS:
+		return 8;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct spinand_info micron_spinand_table[] = {
+	SPINAND_INFO("MT29F2G01ABAGD", 0x24,
+		     NAND_MEMORG(1, 2048, 128, 64, 2048, 2, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&mt29f2g01abagd_ooblayout,
+				     mt29f2g01abagd_ecc_get_status)),
+};
+
+static int micron_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Micron SPI NAND read ID need a dummy byte,
+	 * so the first byte in raw_id is dummy.
+	 */
+	if (id[1] != SPINAND_MFR_MICRON)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, micron_spinand_table,
+				     ARRAY_SIZE(micron_spinand_table), id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static const struct spinand_manufacturer_ops micron_spinand_manuf_ops = {
+	.detect = micron_spinand_detect,
+};
+
+const struct spinand_manufacturer micron_spinand_manufacturer = {
+	.id = SPINAND_MFR_MICRON,
+	.name = "Micron",
+	.ops = &micron_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
new file mode 100644
index 000000000000..67baa1b32c00
--- /dev/null
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017 exceet electronics GmbH
+ *
+ * Authors:
+ *	Frieder Schrempf <frieder.schrempf@exceet.de>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_WINBOND		0xEF
+
+#define WINBOND_CFG_BUF_READ		BIT(3)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int w25m02gv_ooblayout_ecc(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section) + 8;
+	region->length = 8;
+
+	return 0;
+}
+
+static int w25m02gv_ooblayout_free(struct mtd_info *mtd, int section,
+				   struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section) + 2;
+	region->length = 6;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops w25m02gv_ooblayout = {
+	.ecc = w25m02gv_ooblayout_ecc,
+	.free = w25m02gv_ooblayout_free,
+};
+
+static int w25m02gv_select_target(struct spinand_device *spinand,
+				  unsigned int target)
+{
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0xc2, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_NO_DUMMY,
+					  SPI_MEM_OP_DATA_OUT(1,
+							spinand->scratchbuf,
+							1));
+
+	*spinand->scratchbuf = target;
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static const struct spinand_info winbond_spinand_table[] = {
+	SPINAND_INFO("W25M02GV", 0xAB,
+		     NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 2),
+		     NAND_ECCREQ(1, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL),
+		     SPINAND_SELECT_TARGET(w25m02gv_select_target)),
+};
+
+/**
+ * winbond_spinand_detect - initialize device related part in spinand_device
+ * struct if it is a Winbond device.
+ * @spinand: SPI NAND device structure
+ */
+static int winbond_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Winbond SPI NAND read ID need a dummy byte,
+	 * so the first byte in raw_id is dummy.
+	 */
+	if (id[1] != SPINAND_MFR_WINBOND)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, winbond_spinand_table,
+				     ARRAY_SIZE(winbond_spinand_table), id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static int winbond_spinand_init(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	/*
+	 * Make sure all dies are in buffer read mode and not continuous read
+	 * mode.
+	 */
+	for (i = 0; i < nand->memorg.ntargets; i++) {
+		spinand_select_target(spinand, i);
+		spinand_upd_cfg(spinand, WINBOND_CFG_BUF_READ,
+				WINBOND_CFG_BUF_READ);
+	}
+
+	return 0;
+}
+
+static const struct spinand_manufacturer_ops winbond_spinand_manuf_ops = {
+	.detect = winbond_spinand_detect,
+	.init = winbond_spinand_init,
+};
+
+const struct spinand_manufacturer winbond_spinand_manufacturer = {
+	.id = SPINAND_MFR_WINBOND,
+	.name = "Winbond",
+	.ops = &winbond_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/nftlmount.c b/drivers/mtd/nftlmount.c
index 27184e3874db..91b7fb326f9a 100644
--- a/drivers/mtd/nftlmount.c
+++ b/drivers/mtd/nftlmount.c
@@ -577,7 +577,7 @@ static int get_fold_mark(struct NFTLrecord *nftl, unsigned int block)
 int NFTL_mount(struct NFTLrecord *s)
 {
 	int i;
-	unsigned int first_logical_block, logical_block, rep_block, nb_erases, erase_mark;
+	unsigned int first_logical_block, logical_block, rep_block, erase_mark;
 	unsigned int block, first_block, is_first_block;
 	int chain_length, do_format_chain;
 	struct nftl_uci0 h0;
@@ -621,7 +621,6 @@ int NFTL_mount(struct NFTLrecord *s)
 
 				logical_block = le16_to_cpu ((h0.VirtUnitNum | h0.SpareVirtUnitNum));
 				rep_block = le16_to_cpu ((h0.ReplUnitNum | h0.SpareReplUnitNum));
-				nb_erases = le32_to_cpu (h1.WearInfo);
 				erase_mark = le16_to_cpu ((h1.EraseMark | h1.EraseMark1));
 
 				is_first_block = !(logical_block >> 15);
diff --git a/drivers/mtd/parsers/parser_trx.c b/drivers/mtd/parsers/parser_trx.c
index 17ac33599783..4a89a68622fe 100644
--- a/drivers/mtd/parsers/parser_trx.c
+++ b/drivers/mtd/parsers/parser_trx.c
@@ -116,9 +116,16 @@ static int parser_trx_parse(struct mtd_info *mtd,
 	return i;
 };
 
+static const struct of_device_id mtd_parser_trx_of_match_table[] = {
+	{ .compatible = "brcm,trx" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtd_parser_trx_of_match_table);
+
 static struct mtd_part_parser mtd_parser_trx = {
 	.parse_fn = parser_trx_parse,
 	.name = "trx",
+	.of_match_table = mtd_parser_trx_of_match_table,
 };
 module_mtd_part_parser(mtd_parser_trx);
 
diff --git a/drivers/mtd/spi-nor/atmel-quadspi.c b/drivers/mtd/spi-nor/atmel-quadspi.c
index 6c5708bacad8..820048726b4f 100644
--- a/drivers/mtd/spi-nor/atmel-quadspi.c
+++ b/drivers/mtd/spi-nor/atmel-quadspi.c
@@ -34,7 +34,7 @@
 #include <linux/of.h>
 
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 /* QSPI register offsets */
 #define QSPI_CR      0x0000  /* Control Register */
@@ -737,6 +737,26 @@ static int atmel_qspi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused atmel_qspi_suspend(struct device *dev)
+{
+	struct atmel_qspi *aq = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(aq->clk);
+
+	return 0;
+}
+
+static int __maybe_unused atmel_qspi_resume(struct device *dev)
+{
+	struct atmel_qspi *aq = dev_get_drvdata(dev);
+
+	clk_prepare_enable(aq->clk);
+
+	return atmel_qspi_init(aq);
+}
+
+static SIMPLE_DEV_PM_OPS(atmel_qspi_pm_ops, atmel_qspi_suspend,
+			 atmel_qspi_resume);
 
 static const struct of_device_id atmel_qspi_dt_ids[] = {
 	{ .compatible = "atmel,sama5d2-qspi" },
@@ -749,6 +769,7 @@ static struct platform_driver atmel_qspi_driver = {
 	.driver = {
 		.name	= "atmel_qspi",
 		.of_match_table	= atmel_qspi_dt_ids,
+		.pm	= &atmel_qspi_pm_ops,
 	},
 	.probe		= atmel_qspi_probe,
 	.remove		= atmel_qspi_remove,
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index c3f7aaa5d18f..8e714fbfa521 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -525,15 +525,14 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor, u8 *rxbuf,
 	       reg_base + CQSPI_REG_INDIRECTRD);
 
 	while (remaining > 0) {
-		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
-						  msecs_to_jiffies
-						  (CQSPI_READ_TIMEOUT_MS));
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+				msecs_to_jiffies(CQSPI_READ_TIMEOUT_MS)))
+			ret = -ETIMEDOUT;
 
 		bytes_to_read = cqspi_get_rd_sram_level(cqspi);
 
-		if (!ret && bytes_to_read == 0) {
+		if (ret && bytes_to_read == 0) {
 			dev_err(nor->dev, "Indirect read timeout, no bytes\n");
-			ret = -ETIMEDOUT;
 			goto failrd;
 		}
 
@@ -649,10 +648,8 @@ static int cqspi_indirect_write_execute(struct spi_nor *nor, loff_t to_addr,
 		iowrite32_rep(cqspi->ahb_base, txbuf,
 			      DIV_ROUND_UP(write_bytes, 4));
 
-		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
-						  msecs_to_jiffies
-						  (CQSPI_TIMEOUT_MS));
-		if (!ret) {
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+					msecs_to_jiffies(CQSPI_TIMEOUT_MS))) {
 			dev_err(nor->dev, "Indirect write timeout\n");
 			ret = -ETIMEDOUT;
 			goto failwr;
@@ -926,10 +923,12 @@ static ssize_t cqspi_write(struct spi_nor *nor, loff_t to,
 	if (ret)
 		return ret;
 
-	if (f_pdata->use_direct_mode)
+	if (f_pdata->use_direct_mode) {
 		memcpy_toio(cqspi->ahb_base + to, buf, len);
-	else
+		ret = cqspi_wait_idle(cqspi);
+	} else {
 		ret = cqspi_indirect_write_execute(nor, to, buf, len);
+	}
 	if (ret)
 		return ret;
 
@@ -986,9 +985,8 @@ static int cqspi_direct_read_execute(struct spi_nor *nor, u_char *buf,
 	}
 
 	dma_async_issue_pending(cqspi->rx_chan);
-	ret = wait_for_completion_timeout(&cqspi->rx_dma_complete,
-					  msecs_to_jiffies(len));
-	if (ret <= 0) {
+	if (!wait_for_completion_timeout(&cqspi->rx_dma_complete,
+					 msecs_to_jiffies(len))) {
 		dmaengine_terminate_sync(cqspi->rx_chan);
 		dev_err(nor->dev, "DMA wait_for_completion_timeout\n");
 		ret = -ETIMEDOUT;
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index d2cbfc27826e..af0a22019516 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -908,7 +908,7 @@ struct intel_spi *intel_spi_probe(struct device *dev,
 	if (!ispi->writeable || !writeable)
 		ispi->nor.mtd.flags &= ~MTD_WRITEABLE;
 
-	ret = mtd_device_parse_register(&ispi->nor.mtd, NULL, NULL, &part, 1);
+	ret = mtd_device_register(&ispi->nor.mtd, &part, 1);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c
index 15374216d4d9..0c9094ec5966 100644
--- a/drivers/mtd/spi-nor/nxp-spifi.c
+++ b/drivers/mtd/spi-nor/nxp-spifi.c
@@ -436,6 +436,7 @@ static int nxp_spifi_probe(struct platform_device *pdev)
 	}
 
 	ret = nxp_spifi_setup_flash(spifi, flash_np);
+	of_node_put(flash_np);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to setup flash chip\n");
 		goto dis_clks;
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index d9c368c44194..f028277fb1ce 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -2757,8 +2757,18 @@ static int spi_nor_init(struct spi_nor *nor)
 
 	if ((nor->addr_width == 4) &&
 	    (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) &&
-	    !(nor->info->flags & SPI_NOR_4B_OPCODES))
+	    !(nor->info->flags & SPI_NOR_4B_OPCODES)) {
+		/*
+		 * If the RESET# pin isn't hooked up properly, or the system
+		 * otherwise doesn't perform a reset command in the boot
+		 * sequence, it's impossible to 100% protect against unexpected
+		 * reboots (e.g., crashes). Warn the user (or hopefully, system
+		 * designer) that this is bad.
+		 */
+		WARN_ONCE(nor->flags & SNOR_F_BROKEN_RESET,
+			  "enabling reset hack; may not recover from unexpected reboots\n");
 		set_4byte(nor, nor->info, 1);
+	}
 
 	return 0;
 }
@@ -2781,7 +2791,8 @@ void spi_nor_restore(struct spi_nor *nor)
 	/* restore the addressing mode */
 	if ((nor->addr_width == 4) &&
 	    (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) &&
-	    !(nor->info->flags & SPI_NOR_4B_OPCODES))
+	    !(nor->info->flags & SPI_NOR_4B_OPCODES) &&
+	    (nor->flags & SNOR_F_BROKEN_RESET))
 		set_4byte(nor, nor->info, 0);
 }
 EXPORT_SYMBOL_GPL(spi_nor_restore);
@@ -2911,6 +2922,9 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 		params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
 	}
 
+	if (of_property_read_bool(np, "broken-flash-reset"))
+		nor->flags |= SNOR_F_BROKEN_RESET;
+
 	/* Some devices cannot do fast-read, no matter what DT tells us */
 	if (info->flags & SPI_NOR_NO_FR)
 		params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST;
diff --git a/drivers/mtd/spi-nor/stm32-quadspi.c b/drivers/mtd/spi-nor/stm32-quadspi.c
index 72553506a00b..13e9fc961d3b 100644
--- a/drivers/mtd/spi-nor/stm32-quadspi.c
+++ b/drivers/mtd/spi-nor/stm32-quadspi.c
@@ -355,7 +355,7 @@ static int stm32_qspi_read_reg(struct spi_nor *nor,
 	struct device *dev = flash->qspi->dev;
 	struct stm32_qspi_cmd cmd;
 
-	dev_dbg(dev, "read_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+	dev_dbg(dev, "read_reg: cmd:%#.2x buf:%pK len:%#x\n", opcode, buf, len);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode = opcode;
@@ -376,7 +376,7 @@ static int stm32_qspi_write_reg(struct spi_nor *nor, u8 opcode,
 	struct device *dev = flash->qspi->dev;
 	struct stm32_qspi_cmd cmd;
 
-	dev_dbg(dev, "write_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+	dev_dbg(dev, "write_reg: cmd:%#.2x buf:%pK len:%#x\n", opcode, buf, len);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode = opcode;
@@ -398,7 +398,7 @@ static ssize_t stm32_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
 	struct stm32_qspi_cmd cmd;
 	int err;
 
-	dev_dbg(qspi->dev, "read(%#.2x): buf:%p from:%#.8x len:%#zx\n",
+	dev_dbg(qspi->dev, "read(%#.2x): buf:%pK from:%#.8x len:%#zx\n",
 		nor->read_opcode, buf, (u32)from, len);
 
 	memset(&cmd, 0, sizeof(cmd));
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 63e3844c5bec..217b790d22ed 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1717,6 +1717,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		goto err_upper_unlink;
 	}
 
+	bond->nest_level = dev_get_nest_level(bond_dev) + 1;
+
 	/* If the mode uses primary, then the following is handled by
 	 * bond_change_active_slave().
 	 */
@@ -1764,7 +1766,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	if (bond_mode_can_use_xmit_hash(bond))
 		bond_update_slave_arr(bond, NULL);
 
-	bond->nest_level = dev_get_nest_level(bond_dev);
 
 	netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
 		    slave_dev->name,
@@ -3415,6 +3416,13 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	}
 }
 
+static int bond_get_nest_level(struct net_device *bond_dev)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+
+	return bond->nest_level;
+}
+
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3423,7 +3431,7 @@ static void bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
-	spin_lock(&bond->stats_lock);
+	spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev));
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
@@ -4227,6 +4235,7 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_neigh_setup	= bond_neigh_setup,
 	.ndo_vlan_rx_add_vid	= bond_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= bond_vlan_rx_kill_vid,
+	.ndo_get_lock_subclass  = bond_get_nest_level,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_netpoll_setup	= bond_netpoll_setup,
 	.ndo_netpoll_cleanup	= bond_netpoll_cleanup,
@@ -4725,6 +4734,7 @@ static int bond_init(struct net_device *bond_dev)
 	if (!bond->wq)
 		return -ENOMEM;
 
+	bond->nest_level = SINGLE_DEPTH_NESTING;
 	netdev_lockdep_set_classes(bond_dev);
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 98663c50ded0..4d5d01cb8141 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -743,15 +743,20 @@ const struct bond_option *bond_opt_get(unsigned int option)
 static int bond_option_mode_set(struct bonding *bond,
 				const struct bond_opt_value *newval)
 {
-	if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) {
-		netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
-			   newval->string);
-		/* disable arp monitoring */
-		bond->params.arp_interval = 0;
-		/* set miimon to default value */
-		bond->params.miimon = BOND_DEFAULT_MIIMON;
-		netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
-			   bond->params.miimon);
+	if (!bond_mode_uses_arp(newval->value)) {
+		if (bond->params.arp_interval) {
+			netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
+				   newval->string);
+			/* disable arp monitoring */
+			bond->params.arp_interval = 0;
+		}
+
+		if (!bond->params.miimon) {
+			/* set miimon to default value */
+			bond->params.miimon = BOND_DEFAULT_MIIMON;
+			netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
+				   bond->params.miimon);
+		}
 	}
 
 	if (newval->value == BOND_MODE_ALB)
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 2cb75988b328..7cdd0cead693 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -73,6 +73,12 @@ config CAN_CALC_BITTIMING
 config CAN_LEDS
 	bool "Enable LED triggers for Netlink based drivers"
 	depends on LEDS_CLASS
+	# The netdev trigger (LEDS_TRIGGER_NETDEV) should be able to do
+	# everything that this driver is doing. This is marked as broken
+	# because it uses stuff that is intended to be changed or removed.
+	# Please consider switching to the netdev trigger and confirm it
+	# fulfills your needs instead of fixing this driver.
+	depends on BROKEN
 	select LEDS_TRIGGERS
 	---help---
 	  This option adds two LED triggers for packet receive and transmit
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index b397a33f3d32..9b449400376b 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -634,10 +634,12 @@ static int m_can_clk_start(struct m_can_priv *priv)
 	int err;
 
 	err = pm_runtime_get_sync(priv->device);
-	if (err)
+	if (err < 0) {
 		pm_runtime_put_noidle(priv->device);
+		return err;
+	}
 
-	return err;
+	return 0;
 }
 
 static void m_can_clk_stop(struct m_can_priv *priv)
@@ -1109,7 +1111,8 @@ static void m_can_chip_config(struct net_device *dev)
 
 	} else {
 	/* Version 3.1.x or 3.2.x */
-		cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE);
+		cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE |
+			  CCCR_NISO);
 
 		/* Only 3.2.x has NISO Bit implemented */
 		if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)
@@ -1642,8 +1645,6 @@ static int m_can_plat_probe(struct platform_device *pdev)
 	priv->can.clock.freq = clk_get_rate(cclk);
 	priv->mram_base = mram_addr;
 
-	m_can_of_parse_mram(priv, mram_config_vals);
-
 	platform_set_drvdata(pdev, dev);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
@@ -1666,6 +1667,8 @@ static int m_can_plat_probe(struct platform_device *pdev)
 		goto clk_disable;
 	}
 
+	m_can_of_parse_mram(priv, mram_config_vals);
+
 	devm_can_led_init(dev);
 
 	of_can_transceiver(dev);
@@ -1687,8 +1690,6 @@ failed_ret:
 	return ret;
 }
 
-/* TODO: runtime PM with power down or sleep mode  */
-
 static __maybe_unused int m_can_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
@@ -1715,8 +1716,6 @@ static __maybe_unused int m_can_resume(struct device *dev)
 
 	pinctrl_pm_select_default_state(dev);
 
-	m_can_init_ram(priv);
-
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 
 	if (netif_running(ndev)) {
@@ -1726,6 +1725,7 @@ static __maybe_unused int m_can_resume(struct device *dev)
 		if (ret)
 			return ret;
 
+		m_can_init_ram(priv);
 		m_can_start(ndev);
 		netif_device_attach(ndev);
 		netif_start_queue(ndev);
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index c7427bdd3a4b..2949a381a94d 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -86,6 +86,11 @@ static u32 mpc52xx_can_get_clock(struct platform_device *ofdev,
 		return 0;
 	}
 	cdm = of_iomap(np_cdm, 0);
+	if (!cdm) {
+		of_node_put(np_cdm);
+		dev_err(&ofdev->dev, "can't map clock node!\n");
+		return 0;
+	}
 
 	if (in_8(&cdm->ipb_clk_sel) & 0x1)
 		freq *= 2;
diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index b9e28578bc7b..455a3797a200 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -58,6 +58,10 @@ MODULE_LICENSE("GPL v2");
 #define PCIEFD_REG_SYS_VER1		0x0040	/* version reg #1 */
 #define PCIEFD_REG_SYS_VER2		0x0044	/* version reg #2 */
 
+#define PCIEFD_FW_VERSION(x, y, z)	(((u32)(x) << 24) | \
+					 ((u32)(y) << 16) | \
+					 ((u32)(z) << 8))
+
 /* System Control Registers Bits */
 #define PCIEFD_SYS_CTL_TS_RST		0x00000001	/* timestamp clock */
 #define PCIEFD_SYS_CTL_CLK_EN		0x00000002	/* system clock */
@@ -782,6 +786,21 @@ static int peak_pciefd_probe(struct pci_dev *pdev,
 		 "%ux CAN-FD PCAN-PCIe FPGA v%u.%u.%u:\n", can_count,
 		 hw_ver_major, hw_ver_minor, hw_ver_sub);
 
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	/* FW < v3.3.0 DMA logic doesn't handle correctly the mix of 32-bit and
+	 * 64-bit logical addresses: this workaround forces usage of 32-bit
+	 * DMA addresses only when such a fw is detected.
+	 */
+	if (PCIEFD_FW_VERSION(hw_ver_major, hw_ver_minor, hw_ver_sub) <
+	    PCIEFD_FW_VERSION(3, 3, 0)) {
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (err)
+			dev_warn(&pdev->dev,
+				 "warning: can't set DMA mask %llxh (err %d)\n",
+				 DMA_BIT_MASK(32), err);
+	}
+#endif
+
 	/* stop system clock */
 	pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN,
 			    PCIEFD_REG_SYS_CTL_CLR);
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 12ff0020ecd6..b7dfd4109d24 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -1072,6 +1072,7 @@ static void ems_usb_disconnect(struct usb_interface *intf)
 		usb_free_urb(dev->intr_urb);
 
 		kfree(dev->intr_in_buffer);
+		kfree(dev->tx_msg_buffer);
 	}
 }
 
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 89aec07c225f..5a24039733ef 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -2,6 +2,7 @@
  *
  * Copyright (C) 2012 - 2014 Xilinx, Inc.
  * Copyright (C) 2009 PetaLogix. All rights reserved.
+ * Copyright (C) 2017 Sandvik Mining and Construction Oy
  *
  * Description:
  * This driver is developed for Axi CAN IP and for Zynq CANPS Controller.
@@ -25,8 +26,10 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/skbuff.h>
+#include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/can/dev.h>
@@ -101,7 +104,7 @@ enum xcan_reg {
 #define XCAN_INTR_ALL		(XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\
 				 XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \
 				 XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \
-				 XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK)
+				 XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK)
 
 /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */
 #define XCAN_BTR_SJW_SHIFT		7  /* Synchronous jump width */
@@ -118,6 +121,7 @@ enum xcan_reg {
 /**
  * struct xcan_priv - This definition define CAN driver instance
  * @can:			CAN private data structure.
+ * @tx_lock:			Lock for synchronizing TX interrupt handling
  * @tx_head:			Tx CAN packets ready to send on the queue
  * @tx_tail:			Tx CAN packets successfully sended on the queue
  * @tx_max:			Maximum number packets the driver can send
@@ -132,6 +136,7 @@ enum xcan_reg {
  */
 struct xcan_priv {
 	struct can_priv can;
+	spinlock_t tx_lock;
 	unsigned int tx_head;
 	unsigned int tx_tail;
 	unsigned int tx_max;
@@ -159,6 +164,11 @@ static const struct can_bittiming_const xcan_bittiming_const = {
 	.brp_inc = 1,
 };
 
+#define XCAN_CAP_WATERMARK	0x0001
+struct xcan_devtype_data {
+	unsigned int caps;
+};
+
 /**
  * xcan_write_reg_le - Write a value to the device register little endian
  * @priv:	Driver private data structure
@@ -238,6 +248,10 @@ static int set_reset_mode(struct net_device *ndev)
 		usleep_range(500, 10000);
 	}
 
+	/* reset clears FIFOs */
+	priv->tx_head = 0;
+	priv->tx_tail = 0;
+
 	return 0;
 }
 
@@ -392,6 +406,7 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct net_device_stats *stats = &ndev->stats;
 	struct can_frame *cf = (struct can_frame *)skb->data;
 	u32 id, dlc, data[2] = {0, 0};
+	unsigned long flags;
 
 	if (can_dropped_invalid_skb(ndev, skb))
 		return NETDEV_TX_OK;
@@ -439,6 +454,9 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		data[1] = be32_to_cpup((__be32 *)(cf->data + 4));
 
 	can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max);
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
 	priv->tx_head++;
 
 	/* Write the Frame to Xilinx CAN TX FIFO */
@@ -454,10 +472,16 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		stats->tx_bytes += cf->can_dlc;
 	}
 
+	/* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */
+	if (priv->tx_max > 1)
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK);
+
 	/* Check if the TX buffer is full */
 	if ((priv->tx_head - priv->tx_tail) == priv->tx_max)
 		netif_stop_queue(ndev);
 
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
 	return NETDEV_TX_OK;
 }
 
@@ -530,6 +554,123 @@ static int xcan_rx(struct net_device *ndev)
 }
 
 /**
+ * xcan_current_error_state - Get current error state from HW
+ * @ndev:	Pointer to net_device structure
+ *
+ * Checks the current CAN error state from the HW. Note that this
+ * only checks for ERROR_PASSIVE and ERROR_WARNING.
+ *
+ * Return:
+ * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE
+ * otherwise.
+ */
+static enum can_state xcan_current_error_state(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 status = priv->read_reg(priv, XCAN_SR_OFFSET);
+
+	if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK)
+		return CAN_STATE_ERROR_PASSIVE;
+	else if (status & XCAN_SR_ERRWRN_MASK)
+		return CAN_STATE_ERROR_WARNING;
+	else
+		return CAN_STATE_ERROR_ACTIVE;
+}
+
+/**
+ * xcan_set_error_state - Set new CAN error state
+ * @ndev:	Pointer to net_device structure
+ * @new_state:	The new CAN state to be set
+ * @cf:		Error frame to be populated or NULL
+ *
+ * Set new CAN error state for the device, updating statistics and
+ * populating the error frame if given.
+ */
+static void xcan_set_error_state(struct net_device *ndev,
+				 enum can_state new_state,
+				 struct can_frame *cf)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET);
+	u32 txerr = ecr & XCAN_ECR_TEC_MASK;
+	u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT;
+
+	priv->can.state = new_state;
+
+	if (cf) {
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
+
+	switch (new_state) {
+	case CAN_STATE_ERROR_PASSIVE:
+		priv->can.can_stats.error_passive++;
+		if (cf)
+			cf->data[1] = (rxerr > 127) ?
+					CAN_ERR_CRTL_RX_PASSIVE :
+					CAN_ERR_CRTL_TX_PASSIVE;
+		break;
+	case CAN_STATE_ERROR_WARNING:
+		priv->can.can_stats.error_warning++;
+		if (cf)
+			cf->data[1] |= (txerr > rxerr) ?
+					CAN_ERR_CRTL_TX_WARNING :
+					CAN_ERR_CRTL_RX_WARNING;
+		break;
+	case CAN_STATE_ERROR_ACTIVE:
+		if (cf)
+			cf->data[1] |= CAN_ERR_CRTL_ACTIVE;
+		break;
+	default:
+		/* non-ERROR states are handled elsewhere */
+		WARN_ON(1);
+		break;
+	}
+}
+
+/**
+ * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX
+ * @ndev:	Pointer to net_device structure
+ *
+ * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if
+ * the performed RX/TX has caused it to drop to a lesser state and set
+ * the interface state accordingly.
+ */
+static void xcan_update_error_state_after_rxtx(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	enum can_state old_state = priv->can.state;
+	enum can_state new_state;
+
+	/* changing error state due to successful frame RX/TX can only
+	 * occur from these states
+	 */
+	if (old_state != CAN_STATE_ERROR_WARNING &&
+	    old_state != CAN_STATE_ERROR_PASSIVE)
+		return;
+
+	new_state = xcan_current_error_state(ndev);
+
+	if (new_state != old_state) {
+		struct sk_buff *skb;
+		struct can_frame *cf;
+
+		skb = alloc_can_err_skb(ndev, &cf);
+
+		xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
+
+		if (skb) {
+			struct net_device_stats *stats = &ndev->stats;
+
+			stats->rx_packets++;
+			stats->rx_bytes += cf->can_dlc;
+			netif_rx(skb);
+		}
+	}
+}
+
+/**
  * xcan_err_interrupt - error frame Isr
  * @ndev:	net_device pointer
  * @isr:	interrupt status register value
@@ -544,16 +685,12 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 	struct net_device_stats *stats = &ndev->stats;
 	struct can_frame *cf;
 	struct sk_buff *skb;
-	u32 err_status, status, txerr = 0, rxerr = 0;
+	u32 err_status;
 
 	skb = alloc_can_err_skb(ndev, &cf);
 
 	err_status = priv->read_reg(priv, XCAN_ESR_OFFSET);
 	priv->write_reg(priv, XCAN_ESR_OFFSET, err_status);
-	txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK;
-	rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) &
-			XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT);
-	status = priv->read_reg(priv, XCAN_SR_OFFSET);
 
 	if (isr & XCAN_IXR_BSOFF_MASK) {
 		priv->can.state = CAN_STATE_BUS_OFF;
@@ -563,28 +700,10 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 		can_bus_off(ndev);
 		if (skb)
 			cf->can_id |= CAN_ERR_BUSOFF;
-	} else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) {
-		priv->can.state = CAN_STATE_ERROR_PASSIVE;
-		priv->can.can_stats.error_passive++;
-		if (skb) {
-			cf->can_id |= CAN_ERR_CRTL;
-			cf->data[1] = (rxerr > 127) ?
-					CAN_ERR_CRTL_RX_PASSIVE :
-					CAN_ERR_CRTL_TX_PASSIVE;
-			cf->data[6] = txerr;
-			cf->data[7] = rxerr;
-		}
-	} else if (status & XCAN_SR_ERRWRN_MASK) {
-		priv->can.state = CAN_STATE_ERROR_WARNING;
-		priv->can.can_stats.error_warning++;
-		if (skb) {
-			cf->can_id |= CAN_ERR_CRTL;
-			cf->data[1] |= (txerr > rxerr) ?
-					CAN_ERR_CRTL_TX_WARNING :
-					CAN_ERR_CRTL_RX_WARNING;
-			cf->data[6] = txerr;
-			cf->data[7] = rxerr;
-		}
+	} else {
+		enum can_state new_state = xcan_current_error_state(ndev);
+
+		xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
 	}
 
 	/* Check for Arbitration lost interrupt */
@@ -600,7 +719,6 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 	if (isr & XCAN_IXR_RXOFLW_MASK) {
 		stats->rx_over_errors++;
 		stats->rx_errors++;
-		priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
 		if (skb) {
 			cf->can_id |= CAN_ERR_CRTL;
 			cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW;
@@ -709,26 +827,20 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)
 
 	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) {
-		if (isr & XCAN_IXR_RXOK_MASK) {
-			priv->write_reg(priv, XCAN_ICR_OFFSET,
-				XCAN_IXR_RXOK_MASK);
-			work_done += xcan_rx(ndev);
-		} else {
-			priv->write_reg(priv, XCAN_ICR_OFFSET,
-				XCAN_IXR_RXNEMP_MASK);
-			break;
-		}
+		work_done += xcan_rx(ndev);
 		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK);
 		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	}
 
-	if (work_done)
+	if (work_done) {
 		can_led_event(ndev, CAN_LED_EVENT_RX);
+		xcan_update_error_state_after_rxtx(ndev);
+	}
 
 	if (work_done < quota) {
 		napi_complete_done(napi, work_done);
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK);
+		ier |= XCAN_IXR_RXNEMP_MASK;
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 	}
 	return work_done;
@@ -743,18 +855,71 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
 	struct net_device_stats *stats = &ndev->stats;
+	unsigned int frames_in_fifo;
+	int frames_sent = 1; /* TXOK => at least 1 frame was sent */
+	unsigned long flags;
+	int retries = 0;
+
+	/* Synchronize with xmit as we need to know the exact number
+	 * of frames in the FIFO to stay in sync due to the TXFEMP
+	 * handling.
+	 * This also prevents a race between netif_wake_queue() and
+	 * netif_stop_queue().
+	 */
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
+	frames_in_fifo = priv->tx_head - priv->tx_tail;
+
+	if (WARN_ON_ONCE(frames_in_fifo == 0)) {
+		/* clear TXOK anyway to avoid getting back here */
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+		return;
+	}
+
+	/* Check if 2 frames were sent (TXOK only means that at least 1
+	 * frame was sent).
+	 */
+	if (frames_in_fifo > 1) {
+		WARN_ON(frames_in_fifo > priv->tx_max);
+
+		/* Synchronize TXOK and isr so that after the loop:
+		 * (1) isr variable is up-to-date at least up to TXOK clear
+		 *     time. This avoids us clearing a TXOK of a second frame
+		 *     but not noticing that the FIFO is now empty and thus
+		 *     marking only a single frame as sent.
+		 * (2) No TXOK is left. Having one could mean leaving a
+		 *     stray TXOK as we might process the associated frame
+		 *     via TXFEMP handling as we read TXFEMP *after* TXOK
+		 *     clear to satisfy (1).
+		 */
+		while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) {
+			priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+			isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+		}
 
-	while ((priv->tx_head - priv->tx_tail > 0) &&
-			(isr & XCAN_IXR_TXOK_MASK)) {
+		if (isr & XCAN_IXR_TXFEMP_MASK) {
+			/* nothing in FIFO anymore */
+			frames_sent = frames_in_fifo;
+		}
+	} else {
+		/* single frame in fifo, just clear TXOK */
 		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+	}
+
+	while (frames_sent--) {
 		can_get_echo_skb(ndev, priv->tx_tail %
 					priv->tx_max);
 		priv->tx_tail++;
 		stats->tx_packets++;
-		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	}
-	can_led_event(ndev, CAN_LED_EVENT_TX);
+
 	netif_wake_queue(ndev);
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+	can_led_event(ndev, CAN_LED_EVENT_TX);
+	xcan_update_error_state_after_rxtx(ndev);
 }
 
 /**
@@ -773,6 +938,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 	struct net_device *ndev = (struct net_device *)dev_id;
 	struct xcan_priv *priv = netdev_priv(ndev);
 	u32 isr, ier;
+	u32 isr_errors;
 
 	/* Get the interrupt status from Xilinx CAN */
 	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
@@ -791,18 +957,17 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 		xcan_tx_interrupt(ndev, isr);
 
 	/* Check for the type of error interrupt and Processing it */
-	if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
-			XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) {
-		priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK |
-				XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK |
-				XCAN_IXR_ARBLST_MASK));
+	isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
+			    XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK);
+	if (isr_errors) {
+		priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors);
 		xcan_err_interrupt(ndev, isr);
 	}
 
 	/* Check for the type of receive interrupt and Processing it */
-	if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) {
+	if (isr & XCAN_IXR_RXNEMP_MASK) {
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK);
+		ier &= ~XCAN_IXR_RXNEMP_MASK;
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 		napi_schedule(&priv->napi);
 	}
@@ -819,13 +984,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 static void xcan_chip_stop(struct net_device *ndev)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
-	u32 ier;
 
 	/* Disable interrupts and leave the can in configuration mode */
-	ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-	ier &= ~XCAN_INTR_ALL;
-	priv->write_reg(priv, XCAN_IER_OFFSET, ier);
-	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
+	set_reset_mode(ndev);
 	priv->can.state = CAN_STATE_STOPPED;
 }
 
@@ -958,10 +1119,15 @@ static const struct net_device_ops xcan_netdev_ops = {
  */
 static int __maybe_unused xcan_suspend(struct device *dev)
 {
-	if (!device_may_wakeup(dev))
-		return pm_runtime_force_suspend(dev);
+	struct net_device *ndev = dev_get_drvdata(dev);
 
-	return 0;
+	if (netif_running(ndev)) {
+		netif_stop_queue(ndev);
+		netif_device_detach(ndev);
+		xcan_chip_stop(ndev);
+	}
+
+	return pm_runtime_force_suspend(dev);
 }
 
 /**
@@ -973,11 +1139,27 @@ static int __maybe_unused xcan_suspend(struct device *dev)
  */
 static int __maybe_unused xcan_resume(struct device *dev)
 {
-	if (!device_may_wakeup(dev))
-		return pm_runtime_force_resume(dev);
+	struct net_device *ndev = dev_get_drvdata(dev);
+	int ret;
 
-	return 0;
+	ret = pm_runtime_force_resume(dev);
+	if (ret) {
+		dev_err(dev, "pm_runtime_force_resume failed on resume\n");
+		return ret;
+	}
+
+	if (netif_running(ndev)) {
+		ret = xcan_chip_start(ndev);
+		if (ret) {
+			dev_err(dev, "xcan_chip_start failed on resume\n");
+			return ret;
+		}
+
+		netif_device_attach(ndev);
+		netif_start_queue(ndev);
+	}
 
+	return 0;
 }
 
 /**
@@ -992,14 +1174,6 @@ static int __maybe_unused xcan_runtime_suspend(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct xcan_priv *priv = netdev_priv(ndev);
 
-	if (netif_running(ndev)) {
-		netif_stop_queue(ndev);
-		netif_device_detach(ndev);
-	}
-
-	priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK);
-	priv->can.state = CAN_STATE_SLEEPING;
-
 	clk_disable_unprepare(priv->bus_clk);
 	clk_disable_unprepare(priv->can_clk);
 
@@ -1018,7 +1192,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct xcan_priv *priv = netdev_priv(ndev);
 	int ret;
-	u32 isr, status;
 
 	ret = clk_prepare_enable(priv->bus_clk);
 	if (ret) {
@@ -1032,27 +1205,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev)
 		return ret;
 	}
 
-	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
-	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
-	status = priv->read_reg(priv, XCAN_SR_OFFSET);
-
-	if (netif_running(ndev)) {
-		if (isr & XCAN_IXR_BSOFF_MASK) {
-			priv->can.state = CAN_STATE_BUS_OFF;
-			priv->write_reg(priv, XCAN_SRR_OFFSET,
-					XCAN_SRR_RESET_MASK);
-		} else if ((status & XCAN_SR_ESTAT_MASK) ==
-					XCAN_SR_ESTAT_MASK) {
-			priv->can.state = CAN_STATE_ERROR_PASSIVE;
-		} else if (status & XCAN_SR_ERRWRN_MASK) {
-			priv->can.state = CAN_STATE_ERROR_WARNING;
-		} else {
-			priv->can.state = CAN_STATE_ERROR_ACTIVE;
-		}
-		netif_device_attach(ndev);
-		netif_start_queue(ndev);
-	}
-
 	return 0;
 }
 
@@ -1061,6 +1213,18 @@ static const struct dev_pm_ops xcan_dev_pm_ops = {
 	SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL)
 };
 
+static const struct xcan_devtype_data xcan_zynq_data = {
+	.caps = XCAN_CAP_WATERMARK,
+};
+
+/* Match table for OF platform binding */
+static const struct of_device_id xcan_of_match[] = {
+	{ .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data },
+	{ .compatible = "xlnx,axi-can-1.00.a", },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, xcan_of_match);
+
 /**
  * xcan_probe - Platform registration call
  * @pdev:	Handle to the platform device structure
@@ -1075,8 +1239,10 @@ static int xcan_probe(struct platform_device *pdev)
 	struct resource *res; /* IO mem resources */
 	struct net_device *ndev;
 	struct xcan_priv *priv;
+	const struct of_device_id *of_id;
+	int caps = 0;
 	void __iomem *addr;
-	int ret, rx_max, tx_max;
+	int ret, rx_max, tx_max, tx_fifo_depth;
 
 	/* Get the virtual base address for the device */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1086,7 +1252,8 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max);
+	ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth",
+				   &tx_fifo_depth);
 	if (ret < 0)
 		goto err;
 
@@ -1094,6 +1261,30 @@ static int xcan_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err;
 
+	of_id = of_match_device(xcan_of_match, &pdev->dev);
+	if (of_id) {
+		const struct xcan_devtype_data *devtype_data = of_id->data;
+
+		if (devtype_data)
+			caps = devtype_data->caps;
+	}
+
+	/* There is no way to directly figure out how many frames have been
+	 * sent when the TXOK interrupt is processed. If watermark programming
+	 * is supported, we can have 2 frames in the FIFO and use TXFEMP
+	 * to determine if 1 or 2 frames have been sent.
+	 * Theoretically we should be able to use TXFWMEMP to determine up
+	 * to 3 frames, but it seems that after putting a second frame in the
+	 * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less
+	 * than 2 frames in FIFO) is set anyway with no TXOK (a frame was
+	 * sent), which is not a sensible state - possibly TXFWMEMP is not
+	 * completely synchronized with the rest of the bits?
+	 */
+	if (caps & XCAN_CAP_WATERMARK)
+		tx_max = min(tx_fifo_depth, 2);
+	else
+		tx_max = 1;
+
 	/* Create a CAN device instance */
 	ndev = alloc_candev(sizeof(struct xcan_priv), tx_max);
 	if (!ndev)
@@ -1108,6 +1299,7 @@ static int xcan_probe(struct platform_device *pdev)
 					CAN_CTRLMODE_BERR_REPORTING;
 	priv->reg_base = addr;
 	priv->tx_max = tx_max;
+	spin_lock_init(&priv->tx_lock);
 
 	/* Get IRQ for the device */
 	ndev->irq = platform_get_irq(pdev, 0);
@@ -1172,9 +1364,9 @@ static int xcan_probe(struct platform_device *pdev)
 
 	pm_runtime_put(&pdev->dev);
 
-	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n",
+	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n",
 			priv->reg_base, ndev->irq, priv->can.clock.freq,
-			priv->tx_max);
+			tx_fifo_depth, priv->tx_max);
 
 	return 0;
 
@@ -1208,14 +1400,6 @@ static int xcan_remove(struct platform_device *pdev)
 	return 0;
 }
 
-/* Match table for OF platform binding */
-static const struct of_device_id xcan_of_match[] = {
-	{ .compatible = "xlnx,zynq-can-1.0", },
-	{ .compatible = "xlnx,axi-can-1.00.a", },
-	{ /* end of list */ },
-};
-MODULE_DEVICE_TABLE(of, xcan_of_match);
-
 static struct platform_driver xcan_driver = {
 	.probe = xcan_probe,
 	.remove	= xcan_remove,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 437cd6eb4faa..bb28c701381a 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -343,6 +343,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = {
 	.xlate	= irq_domain_xlate_twocell,
 };
 
+/* To be called with reg_lock held */
 static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
 {
 	int irq, virq;
@@ -362,9 +363,15 @@ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip)
 {
-	mv88e6xxx_g1_irq_free_common(chip);
-
+	/*
+	 * free_irq must be called without reg_lock taken because the irq
+	 * handler takes this lock, too.
+	 */
 	free_irq(chip->irq, chip);
+
+	mutex_lock(&chip->reg_lock);
+	mv88e6xxx_g1_irq_free_common(chip);
+	mutex_unlock(&chip->reg_lock);
 }
 
 static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip)
@@ -469,10 +476,12 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip)
 {
-	mv88e6xxx_g1_irq_free_common(chip);
-
 	kthread_cancel_delayed_work_sync(&chip->irq_poll_work);
 	kthread_destroy_worker(chip->kworker);
+
+	mutex_lock(&chip->reg_lock);
+	mv88e6xxx_g1_irq_free_common(chip);
+	mutex_unlock(&chip->reg_lock);
 }
 
 int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask)
@@ -2608,7 +2617,6 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.rmu_disable = mv88e6085_g1_rmu_disable,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
-	.serdes_power = mv88e6341_serdes_power,
 };
 
 static const struct mv88e6xxx_ops mv88e6095_ops = {
@@ -2774,6 +2782,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.serdes_power = mv88e6341_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 };
 
@@ -2951,7 +2960,6 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
-	.serdes_power = mv88e6341_serdes_power,
 };
 
 static const struct mv88e6xxx_ops mv88e6176_ops = {
@@ -3327,6 +3335,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.serdes_power = mv88e6341_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 };
@@ -4506,12 +4515,10 @@ out_g2_irq:
 	if (chip->info->g2_irqs > 0)
 		mv88e6xxx_g2_irq_free(chip);
 out_g1_irq:
-	mutex_lock(&chip->reg_lock);
 	if (chip->irq > 0)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
-	mutex_unlock(&chip->reg_lock);
 out:
 	if (pdata)
 		dev_put(pdata->netdev);
@@ -4539,12 +4546,10 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 	if (chip->info->g2_irqs > 0)
 		mv88e6xxx_g2_irq_free(chip);
 
-	mutex_lock(&chip->reg_lock);
 	if (chip->irq > 0)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
-	mutex_unlock(&chip->reg_lock);
 }
 
 static const struct of_device_id mv88e6xxx_of_match[] = {
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index 5b7658bcf020..5c3ef9fc8207 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -32,7 +32,7 @@ config EL3
 
 config 3C515
 	tristate "3c515 ISA \"Fast EtherLink\""
-	depends on ISA && ISA_DMA_API
+	depends on ISA && ISA_DMA_API && !PPC32
 	---help---
 	  If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet
 	  network card, say Y here.
diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index b6d735bf8011..342ae08ec3c2 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -153,9 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count,
 static void dayna_block_output(struct net_device *dev, int count,
 			       const unsigned char *buf, int start_page);
 
-#define memcpy_fromio(a, b, c)	memcpy((a), (void *)(b), (c))
-#define memcpy_toio(a, b, c)	memcpy((void *)(a), (b), (c))
-
 #define memcmp_withio(a, b, c)	memcmp((a), (void *)(b), (c))
 
 /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
@@ -239,7 +236,7 @@ static enum mac8390_access mac8390_testio(unsigned long membase)
 	unsigned long outdata = 0xA5A0B5B0;
 	unsigned long indata =  0x00000000;
 	/* Try writing 32 bits */
-	memcpy_toio(membase, &outdata, 4);
+	memcpy_toio((void __iomem *)membase, &outdata, 4);
 	/* Now compare them */
 	if (memcmp_withio(&outdata, membase, 4) == 0)
 		return ACCESS_32;
@@ -711,7 +708,7 @@ static void sane_get_8390_hdr(struct net_device *dev,
 			      struct e8390_pkt_hdr *hdr, int ring_page)
 {
 	unsigned long hdr_start = (ring_page - WD_START_PG)<<8;
-	memcpy_fromio(hdr, dev->mem_start + hdr_start, 4);
+	memcpy_fromio(hdr, (void __iomem *)dev->mem_start + hdr_start, 4);
 	/* Fix endianness */
 	hdr->count = swab16(hdr->count);
 }
@@ -725,13 +722,16 @@ static void sane_block_input(struct net_device *dev, int count,
 	if (xfer_start + count > ei_status.rmem_end) {
 		/* We must wrap the input move. */
 		int semi_count = ei_status.rmem_end - xfer_start;
-		memcpy_fromio(skb->data, dev->mem_start + xfer_base,
+		memcpy_fromio(skb->data,
+			      (void __iomem *)dev->mem_start + xfer_base,
 			      semi_count);
 		count -= semi_count;
-		memcpy_fromio(skb->data + semi_count, ei_status.rmem_start,
-			      count);
+		memcpy_fromio(skb->data + semi_count,
+			      (void __iomem *)ei_status.rmem_start, count);
 	} else {
-		memcpy_fromio(skb->data, dev->mem_start + xfer_base, count);
+		memcpy_fromio(skb->data,
+			      (void __iomem *)dev->mem_start + xfer_base,
+			      count);
 	}
 }
 
@@ -740,7 +740,7 @@ static void sane_block_output(struct net_device *dev, int count,
 {
 	long shmem = (start_page - WD_START_PG)<<8;
 
-	memcpy_toio(dev->mem_start + shmem, buf, count);
+	memcpy_toio((void __iomem *)dev->mem_start + shmem, buf, count);
 }
 
 /* dayna block input/output */
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 1b9d3130af4d..17f12c18d225 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -333,6 +333,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 
 	memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr));
 
+	io_sq->dma_addr_bits = ena_dev->dma_addr_bits;
 	io_sq->desc_entry_size =
 		(io_sq->direction == ENA_COM_IO_QUEUE_DIRECTION_TX) ?
 		sizeof(struct ena_eth_io_tx_desc) :
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index d5c15e8bb3de..9e5cf5583c87 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -44,7 +44,7 @@ config AMD8111_ETH
 
 config LANCE
 	tristate "AMD LANCE and PCnet (AT1500 and NE2100) support"
-	depends on ISA && ISA_DMA_API && !ARM
+	depends on ISA && ISA_DMA_API && !ARM && !PPC32
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y here.
 	  Some LinkSys cards are of this type.
@@ -138,7 +138,7 @@ config PCMCIA_NMCLAN
 
 config NI65
 	tristate "NI6510 support"
-	depends on ISA && ISA_DMA_API && !ARM
+	depends on ISA && ISA_DMA_API && !ARM && !PPC32
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y here.
 
@@ -173,7 +173,7 @@ config SUNLANCE
 
 config AMD_XGBE
 	tristate "AMD 10GbE Ethernet driver"
-	depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM && HAS_DMA
+	depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM
 	depends on X86 || ARM64 || COMPILE_TEST
 	select BITREVERSE
 	select CRC32
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 4b5d625de8f0..8a3a60bb2688 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1111,14 +1111,14 @@ static void xgbe_phy_adjust_link(struct xgbe_prv_data *pdata)
 
 		if (pdata->tx_pause != pdata->phy.tx_pause) {
 			new_state = 1;
-			pdata->hw_if.config_tx_flow_control(pdata);
 			pdata->tx_pause = pdata->phy.tx_pause;
+			pdata->hw_if.config_tx_flow_control(pdata);
 		}
 
 		if (pdata->rx_pause != pdata->phy.rx_pause) {
 			new_state = 1;
-			pdata->hw_if.config_rx_flow_control(pdata);
 			pdata->rx_pause = pdata->phy.rx_pause;
+			pdata->hw_if.config_rx_flow_control(pdata);
 		}
 
 		/* Speed support */
diff --git a/drivers/net/ethernet/apm/xgene-v2/Kconfig b/drivers/net/ethernet/apm/xgene-v2/Kconfig
index 1205861b6318..eedd3f3dd22e 100644
--- a/drivers/net/ethernet/apm/xgene-v2/Kconfig
+++ b/drivers/net/ethernet/apm/xgene-v2/Kconfig
@@ -1,6 +1,5 @@
 config NET_XGENE_V2
 	tristate "APM X-Gene SoC Ethernet-v2 Driver"
-	depends on HAS_DMA
 	depends on ARCH_XGENE || COMPILE_TEST
 	help
 	  This is the Ethernet driver for the on-chip ethernet interface
diff --git a/drivers/net/ethernet/apm/xgene/Kconfig b/drivers/net/ethernet/apm/xgene/Kconfig
index afccb033177b..e4e33c900b57 100644
--- a/drivers/net/ethernet/apm/xgene/Kconfig
+++ b/drivers/net/ethernet/apm/xgene/Kconfig
@@ -1,6 +1,5 @@
 config NET_XGENE
 	tristate "APM X-Gene SoC Ethernet Driver"
-	depends on HAS_DMA
 	depends on ARCH_XGENE || COMPILE_TEST
 	select PHYLIB
 	select MDIO_XGENE
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index 3188f553da35..078a04dc1182 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -836,19 +836,19 @@ static void xgene_enet_adjust_link(struct net_device *ndev)
 #ifdef CONFIG_ACPI
 static struct acpi_device *acpi_phy_find_device(struct device *dev)
 {
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	struct fwnode_handle *fw_node;
 	int status;
 
 	fw_node = acpi_fwnode_handle(ACPI_COMPANION(dev));
 	status = acpi_node_get_property_reference(fw_node, "phy-handle", 0,
 						  &args);
-	if (ACPI_FAILURE(status)) {
+	if (ACPI_FAILURE(status) || !is_acpi_device_node(args.fwnode)) {
 		dev_dbg(dev, "No matching phy in ACPI table\n");
 		return NULL;
 	}
 
-	return args.adev;
+	return to_acpi_device_node(args.fwnode);
 }
 #endif
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index fc7383106946..91eb8910b1c9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -63,8 +63,6 @@
 
 #define AQ_CFG_NAPI_WEIGHT     64U
 
-#define AQ_CFG_MULTICAST_ADDRESS_MAX     32U
-
 /*#define AQ_CFG_MAC_ADDR_PERMANENT {0x30, 0x0E, 0xE3, 0x12, 0x34, 0x56}*/
 
 #define AQ_NIC_FC_OFF    0U
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index a2d416b24ffc..2c6ebd91a9f2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -98,6 +98,8 @@ struct aq_stats_s {
 #define AQ_HW_MEDIA_TYPE_TP    1U
 #define AQ_HW_MEDIA_TYPE_FIBRE 2U
 
+#define AQ_HW_MULTICAST_ADDRESS_MAX     32U
+
 struct aq_hw_s {
 	atomic_t flags;
 	u8 rbl_enabled:1;
@@ -177,7 +179,7 @@ struct aq_hw_ops {
 				    unsigned int packet_filter);
 
 	int (*hw_multicast_list_set)(struct aq_hw_s *self,
-				     u8 ar_mac[AQ_CFG_MULTICAST_ADDRESS_MAX]
+				     u8 ar_mac[AQ_HW_MULTICAST_ADDRESS_MAX]
 				     [ETH_ALEN],
 				     u32 count);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index ba5fe8c4125d..e3ae29e523f0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -135,17 +135,10 @@ err_exit:
 static void aq_ndev_set_multicast_settings(struct net_device *ndev)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
-	int err = 0;
 
-	err = aq_nic_set_packet_filter(aq_nic, ndev->flags);
-	if (err < 0)
-		return;
+	aq_nic_set_packet_filter(aq_nic, ndev->flags);
 
-	if (netdev_mc_count(ndev)) {
-		err = aq_nic_set_multicast_list(aq_nic, ndev);
-		if (err < 0)
-			return;
-	}
+	aq_nic_set_multicast_list(aq_nic, ndev);
 }
 
 static const struct net_device_ops aq_ndev_ops = {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 1a1a6380c128..7a22d0257e04 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -563,34 +563,41 @@ err_exit:
 
 int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 {
+	unsigned int packet_filter = self->packet_filter;
 	struct netdev_hw_addr *ha = NULL;
 	unsigned int i = 0U;
 
-	self->mc_list.count = 0U;
-
-	netdev_for_each_mc_addr(ha, ndev) {
-		ether_addr_copy(self->mc_list.ar[i++], ha->addr);
-		++self->mc_list.count;
+	self->mc_list.count = 0;
+	if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+		packet_filter |= IFF_PROMISC;
+	} else {
+		netdev_for_each_uc_addr(ha, ndev) {
+			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
 
-		if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX)
-			break;
+			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
+				break;
+		}
 	}
 
-	if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) {
-		/* Number of filters is too big: atlantic does not support this.
-		 * Force all multi filter to support this.
-		 * With this we disable all UC filters and setup "all pass"
-		 * multicast mask
-		 */
-		self->packet_filter |= IFF_ALLMULTI;
-		self->aq_nic_cfg.mc_list_count = 0;
-		return self->aq_hw_ops->hw_packet_filter_set(self->aq_hw,
-							     self->packet_filter);
+	if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+		packet_filter |= IFF_ALLMULTI;
 	} else {
-		return self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
-						    self->mc_list.ar,
-						    self->mc_list.count);
+		netdev_for_each_mc_addr(ha, ndev) {
+			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
+
+			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
+				break;
+		}
+	}
+
+	if (i > 0 && i < AQ_HW_MULTICAST_ADDRESS_MAX) {
+		packet_filter |= IFF_MULTICAST;
+		self->mc_list.count = i;
+		self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
+						       self->mc_list.ar,
+						       self->mc_list.count);
 	}
+	return aq_nic_set_packet_filter(self, packet_filter);
 }
 
 int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index faa533a0ec47..fecfc401f95d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -75,7 +75,7 @@ struct aq_nic_s {
 	struct aq_hw_link_status_s link_status;
 	struct {
 		u32 count;
-		u8 ar[AQ_CFG_MULTICAST_ADDRESS_MAX][ETH_ALEN];
+		u8 ar[AQ_HW_MULTICAST_ADDRESS_MAX][ETH_ALEN];
 	} mc_list;
 
 	struct pci_dev *pdev;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 67e2f9fb9402..8cc6abadc03b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -765,7 +765,7 @@ static int hw_atl_a0_hw_packet_filter_set(struct aq_hw_s *self,
 
 static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self,
 					   u8 ar_mac
-					   [AQ_CFG_MULTICAST_ADDRESS_MAX]
+					   [AQ_HW_MULTICAST_ADDRESS_MAX]
 					   [ETH_ALEN],
 					   u32 count)
 {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 819f6bcf9b4e..3bdab972420b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -762,7 +762,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 
 	hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC));
 	hw_atl_rpfl2multicast_flr_en_set(self,
-					 IS_FILTER_ENABLED(IFF_MULTICAST), 0);
+					 IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
 
 	hw_atl_rpfl2_accept_all_mc_packets_set(self,
 					       IS_FILTER_ENABLED(IFF_ALLMULTI));
@@ -784,7 +784,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 
 static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self,
 					   u8 ar_mac
-					   [AQ_CFG_MULTICAST_ADDRESS_MAX]
+					   [AQ_HW_MULTICAST_ADDRESS_MAX]
 					   [ETH_ALEN],
 					   u32 count)
 {
@@ -812,7 +812,7 @@ static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self,
 
 		hw_atl_rpfl2_uc_flr_en_set(self,
 					   (self->aq_nic_cfg->is_mc_list_enabled),
-				    HW_ATL_B0_MAC_MIN + i);
+					   HW_ATL_B0_MAC_MIN + i);
 	}
 
 	err = aq_hw_err_from_flags(self);
diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig
index e743ddf46343..5d0ab8e74b68 100644
--- a/drivers/net/ethernet/arc/Kconfig
+++ b/drivers/net/ethernet/arc/Kconfig
@@ -24,7 +24,8 @@ config ARC_EMAC_CORE
 config ARC_EMAC
 	tristate "ARC EMAC support"
 	select ARC_EMAC_CORE
-	depends on OF_IRQ && OF_NET && HAS_DMA && (ARC || COMPILE_TEST)
+	depends on OF_IRQ && OF_NET
+	depends on ARC || COMPILE_TEST
 	---help---
 	  On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x
 	  non-standard on-chip ethernet device ARC EMAC 10/100 is used.
@@ -33,7 +34,8 @@ config ARC_EMAC
 config EMAC_ROCKCHIP
 	tristate "Rockchip EMAC support"
 	select ARC_EMAC_CORE
-	depends on OF_IRQ && OF_NET && REGULATOR && HAS_DMA && (ARCH_ROCKCHIP || COMPILE_TEST)
+	depends on OF_IRQ && OF_NET && REGULATOR
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
 	---help---
 	  Support for Rockchip RK3036/RK3066/RK3188 EMAC ethernet controllers.
 	  This selects Rockchip SoC glue layer support for the
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 567ee54504bc..5e5022fa1d04 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1897,13 +1897,19 @@ static int alx_resume(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct alx_priv *alx = pci_get_drvdata(pdev);
 	struct alx_hw *hw = &alx->hw;
+	int err;
 
 	alx_reset_phy(hw);
 
 	if (!netif_running(alx->dev))
 		return 0;
 	netif_device_attach(alx->dev);
-	return __alx_open(alx, true);
+
+	rtnl_lock();
+	err = __alx_open(alx, true);
+	rtnl_unlock();
+
+	return err;
 }
 
 static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 94270f654b3b..7087b88550db 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1686,6 +1686,7 @@ static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter)
 	skb = build_skb(page_address(page) + adapter->rx_page_offset,
 			adapter->rx_frag_size);
 	if (likely(skb)) {
+		skb_reserve(skb, NET_SKB_PAD);
 		adapter->rx_page_offset += adapter->rx_frag_size;
 		if (adapter->rx_page_offset >= PAGE_SIZE)
 			adapter->rx_page = NULL;
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index af75156919ed..4c3bfde6e8de 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -157,7 +157,6 @@ config BGMAC
 config BGMAC_BCMA
 	tristate "Broadcom iProc GBit BCMA support"
 	depends on BCMA && BCMA_HOST_SOC
-	depends on HAS_DMA
 	depends on BCM47XX || ARCH_BCM_5301X || COMPILE_TEST
 	select BGMAC
 	select PHYLIB
@@ -170,7 +169,6 @@ config BGMAC_BCMA
 
 config BGMAC_PLATFORM
 	tristate "Broadcom iProc GBit platform support"
-	depends on HAS_DMA
 	depends on ARCH_BCM_IPROC || COMPILE_TEST
 	depends on OF
 	select BGMAC
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index d5fca2e5a9bc..a1f60f89e059 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1946,8 +1946,8 @@ static int bcm_sysport_open(struct net_device *dev)
 	if (!priv->is_lite)
 		priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD);
 	else
-		priv->crc_fwd = !!(gib_readl(priv, GIB_CONTROL) &
-				   GIB_FCS_STRIP);
+		priv->crc_fwd = !((gib_readl(priv, GIB_CONTROL) &
+				  GIB_FCS_STRIP) >> GIB_FCS_STRIP_SHIFT);
 
 	phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
 				0, priv->phy_interface);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index d6e5d0cbf3a3..cf440b91fd04 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -278,7 +278,8 @@ struct bcm_rsb {
 #define  GIB_GTX_CLK_EXT_CLK		(0 << GIB_GTX_CLK_SEL_SHIFT)
 #define  GIB_GTX_CLK_125MHZ		(1 << GIB_GTX_CLK_SEL_SHIFT)
 #define  GIB_GTX_CLK_250MHZ		(2 << GIB_GTX_CLK_SEL_SHIFT)
-#define  GIB_FCS_STRIP			(1 << 6)
+#define  GIB_FCS_STRIP_SHIFT		6
+#define  GIB_FCS_STRIP			(1 << GIB_FCS_STRIP_SHIFT)
 #define  GIB_LCL_LOOP_EN		(1 << 7)
 #define  GIB_LCL_LOOP_TXEN		(1 << 8)
 #define  GIB_RMT_LOOP_EN		(1 << 9)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index d847e1b9c37b..be1506169076 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1533,6 +1533,7 @@ struct bnx2x {
 	struct link_vars	link_vars;
 	u32			link_cnt;
 	struct bnx2x_link_report_data last_reported_link;
+	bool			force_link_down;
 
 	struct mdio_if_info	mdio;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 8cd73ff5debc..af7b5a4d8ba0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1261,6 +1261,11 @@ void __bnx2x_link_report(struct bnx2x *bp)
 {
 	struct bnx2x_link_report_data cur_data;
 
+	if (bp->force_link_down) {
+		bp->link_vars.link_up = 0;
+		return;
+	}
+
 	/* reread mf_cfg */
 	if (IS_PF(bp) && !CHIP_IS_E1(bp))
 		bnx2x_read_mf_cfg(bp);
@@ -2817,6 +2822,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 		bp->pending_max = 0;
 	}
 
+	bp->force_link_down = false;
 	if (bp->port.pmf) {
 		rc = bnx2x_initial_phy_init(bp, load_mode);
 		if (rc)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index da18aa239acb..a4a90b6cdb46 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -3388,14 +3388,18 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
 			DP(BNX2X_MSG_ETHTOOL,
 			   "rss re-configured, UDP 4-tupple %s\n",
 			   udp_rss_requested ? "enabled" : "disabled");
-			return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
+			if (bp->state == BNX2X_STATE_OPEN)
+				return bnx2x_rss(bp, &bp->rss_conf_obj, false,
+						 true);
 		} else if ((info->flow_type == UDP_V6_FLOW) &&
 			   (bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) {
 			bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested;
 			DP(BNX2X_MSG_ETHTOOL,
 			   "rss re-configured, UDP 4-tupple %s\n",
 			   udp_rss_requested ? "enabled" : "disabled");
-			return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
+			if (bp->state == BNX2X_STATE_OPEN)
+				return bnx2x_rss(bp, &bp->rss_conf_obj, false,
+						 true);
 		}
 		return 0;
 
@@ -3509,7 +3513,10 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
 		bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id;
 	}
 
-	return bnx2x_config_rss_eth(bp, false);
+	if (bp->state == BNX2X_STATE_OPEN)
+		return bnx2x_config_rss_eth(bp, false);
+
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 5b1ed240bf18..57348f2b49a3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -10279,6 +10279,12 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work)
 		bp->sp_rtnl_state = 0;
 		smp_mb();
 
+		/* Immediately indicate link as down */
+		bp->link_vars.link_up = 0;
+		bp->force_link_down = true;
+		netif_carrier_off(bp->dev);
+		BNX2X_ERR("Indicating link is down due to Tx-timeout\n");
+
 		bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
 		/* When ret value shows failure of allocation failure,
 		 * the nic is rebooted again. If open still fails, a error
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 176fc9f4d7de..4394c1162be4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5712,7 +5712,9 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 	}
 	vnic->uc_filter_count = 1;
 
-	vnic->rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
+	vnic->rx_mask = 0;
+	if (bp->dev->flags & IFF_BROADCAST)
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
 
 	if ((bp->dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp))
 		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
@@ -5917,7 +5919,7 @@ unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 	return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_cp_rings);
 }
 
-void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
+static void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
 {
 	bp->hw_resc.max_irqs = max_irqs;
 }
@@ -6888,7 +6890,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		rc = bnxt_request_irq(bp);
 		if (rc) {
 			netdev_err(bp->dev, "bnxt_request_irq err: %x\n", rc);
-			goto open_err;
+			goto open_err_irq;
 		}
 	}
 
@@ -6928,6 +6930,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 open_err:
 	bnxt_debug_dev_exit(bp);
 	bnxt_disable_napi(bp);
+
+open_err_irq:
 	bnxt_del_napi(bp);
 
 open_err_free_mem:
@@ -7214,13 +7218,16 @@ static void bnxt_set_rx_mode(struct net_device *dev)
 
 	mask &= ~(CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS |
 		  CFA_L2_SET_RX_MASK_REQ_MASK_MCAST |
-		  CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST);
+		  CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST |
+		  CFA_L2_SET_RX_MASK_REQ_MASK_BCAST);
 
 	if ((dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp))
 		mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
 
 	uc_update = bnxt_uc_list_updated(bp);
 
+	if (dev->flags & IFF_BROADCAST)
+		mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
 	if (dev->flags & IFF_ALLMULTI) {
 		mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
 		vnic->mc_list_count = 0;
@@ -8502,11 +8509,11 @@ int bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, bool shared)
 	int rx, tx, cp;
 
 	_bnxt_get_max_rings(bp, &rx, &tx, &cp);
+	*max_rx = rx;
+	*max_tx = tx;
 	if (!rx || !tx || !cp)
 		return -ENOMEM;
 
-	*max_rx = rx;
-	*max_tx = tx;
 	return bnxt_trim_rings(bp, max_rx, max_tx, cp, shared);
 }
 
@@ -8520,8 +8527,11 @@ static int bnxt_get_dflt_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 		/* Not enough rings, try disabling agg rings. */
 		bp->flags &= ~BNXT_FLAG_AGG_RINGS;
 		rc = bnxt_get_max_rings(bp, max_rx, max_tx, shared);
-		if (rc)
+		if (rc) {
+			/* set BNXT_FLAG_AGG_RINGS back for consistency */
+			bp->flags |= BNXT_FLAG_AGG_RINGS;
 			return rc;
+		}
 		bp->flags |= BNXT_FLAG_NO_AGG_RINGS;
 		bp->dev->hw_features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
 		bp->dev->features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 9b14eb610b9f..91575ef97c8c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1470,7 +1470,6 @@ void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
 void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_irqs(struct bnxt *bp);
-void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp);
 void bnxt_tx_disable(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 795f45024c20..491bd40a254d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -27,6 +27,15 @@
 #define BNXT_FID_INVALID			0xffff
 #define VLAN_TCI(vid, prio)	((vid) | ((prio) << VLAN_PRIO_SHIFT))
 
+#define is_vlan_pcp_wildcarded(vlan_tci_mask)	\
+	((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == 0x0000)
+#define is_vlan_pcp_exactmatch(vlan_tci_mask)	\
+	((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == VLAN_PRIO_MASK)
+#define is_vlan_pcp_zero(vlan_tci)	\
+	((ntohs(vlan_tci) & VLAN_PRIO_MASK) == 0x0000)
+#define is_vid_exactmatch(vlan_tci_mask)	\
+	((ntohs(vlan_tci_mask) & VLAN_VID_MASK) == VLAN_VID_MASK)
+
 /* Return the dst fid of the func for flow forwarding
  * For PFs: src_fid is the fid of the PF
  * For VF-reps: src_fid the fid of the VF
@@ -389,6 +398,21 @@ static bool is_exactmatch(void *mask, int len)
 	return true;
 }
 
+static bool is_vlan_tci_allowed(__be16  vlan_tci_mask,
+				__be16  vlan_tci)
+{
+	/* VLAN priority must be either exactly zero or fully wildcarded and
+	 * VLAN id must be exact match.
+	 */
+	if (is_vid_exactmatch(vlan_tci_mask) &&
+	    ((is_vlan_pcp_exactmatch(vlan_tci_mask) &&
+	      is_vlan_pcp_zero(vlan_tci)) ||
+	     is_vlan_pcp_wildcarded(vlan_tci_mask)))
+		return true;
+
+	return false;
+}
+
 static bool bits_set(void *key, int len)
 {
 	const u8 *p = key;
@@ -803,9 +827,9 @@ static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow)
 	/* Currently VLAN fields cannot be partial wildcard */
 	if (bits_set(&flow->l2_key.inner_vlan_tci,
 		     sizeof(flow->l2_key.inner_vlan_tci)) &&
-	    !is_exactmatch(&flow->l2_mask.inner_vlan_tci,
-			   sizeof(flow->l2_mask.inner_vlan_tci))) {
-		netdev_info(bp->dev, "Wildcard match unsupported for VLAN TCI\n");
+	    !is_vlan_tci_allowed(flow->l2_mask.inner_vlan_tci,
+				 flow->l2_key.inner_vlan_tci)) {
+		netdev_info(bp->dev, "Unsupported VLAN TCI\n");
 		return false;
 	}
 	if (bits_set(&flow->l2_key.inner_vlan_tpid,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 347e4f946eb2..840f6e505f73 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -169,7 +169,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 		edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
 	}
 	bnxt_fill_msix_vecs(bp, ent);
-	bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) - avail_msix);
 	bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix);
 	edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;
 	return avail_msix;
@@ -192,7 +191,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id)
 	msix_requested = edev->ulp_tbl[ulp_id].msix_requested;
 	bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested);
 	edev->ulp_tbl[ulp_id].msix_requested = 0;
-	bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) + msix_requested);
 	edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
 	if (netif_running(dev)) {
 		bnxt_close_nic(bp, true, false);
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 30273a7717e2..4fd829b5e65d 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -660,7 +660,7 @@ static int cnic_init_id_tbl(struct cnic_id_tbl *id_tbl, u32 size, u32 start_id,
 	id_tbl->max = size;
 	id_tbl->next = next;
 	spin_lock_init(&id_tbl->lock);
-	id_tbl->table = kcalloc(DIV_ROUND_UP(size, 32), 4, GFP_KERNEL);
+	id_tbl->table = kcalloc(BITS_TO_LONGS(size), sizeof(long), GFP_KERNEL);
 	if (!id_tbl->table)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 3be87efdc93d..aa1374d0af93 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6,11 +6,15 @@
  * Copyright (C) 2004 Sun Microsystems Inc.
  * Copyright (C) 2005-2016 Broadcom Corporation.
  * Copyright (C) 2016-2017 Broadcom Limited.
+ * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom"
+ * refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Firmware is:
  *	Derived from proprietary unpublished source code,
  *	Copyright (C) 2000-2016 Broadcom Corporation.
  *	Copyright (C) 2016-2017 Broadcom Ltd.
+ *	Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom"
+ *	refers to Broadcom Inc. and/or its subsidiaries.
  *
  *	Permission is hereby granted for the distribution of this firmware
  *	data in hexadecimal or equivalent format, provided this copyright
@@ -9290,6 +9294,15 @@ static int tg3_chip_reset(struct tg3 *tp)
 
 	tg3_restore_clk(tp);
 
+	/* Increase the core clock speed to fix tx timeout issue for 5762
+	 * with 100Mbps link speed.
+	 */
+	if (tg3_asic_rev(tp) == ASIC_REV_5762) {
+		val = tr32(TG3_CPMU_CLCK_ORIDE_ENABLE);
+		tw32(TG3_CPMU_CLCK_ORIDE_ENABLE, val |
+		     TG3_CPMU_MAC_ORIDE_ENABLE);
+	}
+
 	/* Reprobe ASF enable state.  */
 	tg3_flag_clear(tp, ENABLE_ASF);
 	tp->phy_flags &= ~(TG3_PHYFLG_1G_ON_VAUX_OK |
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index 1d61aa3efda1..a772a33b685c 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -7,6 +7,8 @@
  * Copyright (C) 2004 Sun Microsystems Inc.
  * Copyright (C) 2007-2016 Broadcom Corporation.
  * Copyright (C) 2016-2017 Broadcom Limited.
+ * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom"
+ * refers to Broadcom Inc. and/or its subsidiaries.
  */
 
 #ifndef _T3_H
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 86659823b259..3d45f4c92cf6 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -166,6 +166,7 @@
 #define GEM_DCFG6		0x0294 /* Design Config 6 */
 #define GEM_DCFG7		0x0298 /* Design Config 7 */
 #define GEM_DCFG8		0x029C /* Design Config 8 */
+#define GEM_DCFG10		0x02A4 /* Design Config 10 */
 
 #define GEM_TXBDCTRL	0x04cc /* TX Buffer Descriptor control register */
 #define GEM_RXBDCTRL	0x04d0 /* RX Buffer Descriptor control register */
@@ -490,6 +491,12 @@
 #define GEM_SCR2CMP_OFFSET			0
 #define GEM_SCR2CMP_SIZE			8
 
+/* Bitfields in DCFG10 */
+#define GEM_TXBD_RDBUFF_OFFSET			12
+#define GEM_TXBD_RDBUFF_SIZE			4
+#define GEM_RXBD_RDBUFF_OFFSET			8
+#define GEM_RXBD_RDBUFF_SIZE			4
+
 /* Bitfields in TISUBN */
 #define GEM_SUBNSINCR_OFFSET			0
 #define GEM_SUBNSINCR_SIZE			16
@@ -635,6 +642,7 @@
 #define MACB_CAPS_USRIO_DISABLED		0x00000010
 #define MACB_CAPS_JUMBO				0x00000020
 #define MACB_CAPS_GEM_HAS_PTP			0x00000040
+#define MACB_CAPS_BD_RD_PREFETCH		0x00000080
 #define MACB_CAPS_FIFO_MODE			0x10000000
 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
 #define MACB_CAPS_SG_DISABLED			0x40000000
@@ -1203,6 +1211,9 @@ struct macb {
 	unsigned int max_tuples;
 
 	struct tasklet_struct	hresp_err_tasklet;
+
+	int	rx_bd_rd_prefetch;
+	int	tx_bd_rd_prefetch;
 };
 
 #ifdef CONFIG_MACB_USE_HWSTAMP
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 3e93df5d4e3b..a6c911bb5ce2 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1811,23 +1811,25 @@ static void macb_free_consistent(struct macb *bp)
 {
 	struct macb_queue *queue;
 	unsigned int q;
+	int size;
 
-	queue = &bp->queues[0];
 	bp->macbgem_ops.mog_free_rx_buffers(bp);
-	if (queue->rx_ring) {
-		dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES(bp),
-				queue->rx_ring, queue->rx_ring_dma);
-		queue->rx_ring = NULL;
-	}
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
 		kfree(queue->tx_skb);
 		queue->tx_skb = NULL;
 		if (queue->tx_ring) {
-			dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES(bp),
+			size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
+			dma_free_coherent(&bp->pdev->dev, size,
 					  queue->tx_ring, queue->tx_ring_dma);
 			queue->tx_ring = NULL;
 		}
+		if (queue->rx_ring) {
+			size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
+			dma_free_coherent(&bp->pdev->dev, size,
+					  queue->rx_ring, queue->rx_ring_dma);
+			queue->rx_ring = NULL;
+		}
 	}
 }
 
@@ -1874,7 +1876,7 @@ static int macb_alloc_consistent(struct macb *bp)
 	int size;
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		size = TX_RING_BYTES(bp);
+		size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
 		queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
 						    &queue->tx_ring_dma,
 						    GFP_KERNEL);
@@ -1890,7 +1892,7 @@ static int macb_alloc_consistent(struct macb *bp)
 		if (!queue->tx_skb)
 			goto out_err;
 
-		size = RX_RING_BYTES(bp);
+		size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
 		queue->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
 						 &queue->rx_ring_dma, GFP_KERNEL);
 		if (!queue->rx_ring)
@@ -3726,6 +3728,8 @@ static int at91ether_init(struct platform_device *pdev)
 	int err;
 	u32 reg;
 
+	bp->queues[0].bp = bp;
+
 	dev->netdev_ops = &at91ether_netdev_ops;
 	dev->ethtool_ops = &macb_ethtool_ops;
 
@@ -3795,7 +3799,7 @@ static const struct macb_config np4_config = {
 static const struct macb_config zynqmp_config = {
 	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE |
 			MACB_CAPS_JUMBO |
-			MACB_CAPS_GEM_HAS_PTP,
+			MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
@@ -3856,7 +3860,7 @@ static int macb_probe(struct platform_device *pdev)
 	void __iomem *mem;
 	const char *mac;
 	struct macb *bp;
-	int err;
+	int err, val;
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	mem = devm_ioremap_resource(&pdev->dev, regs);
@@ -3945,6 +3949,18 @@ static int macb_probe(struct platform_device *pdev)
 	else
 		dev->max_mtu = ETH_DATA_LEN;
 
+	if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) {
+		val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10));
+		if (val)
+			bp->rx_bd_rd_prefetch = (2 << (val - 1)) *
+						macb_dma_desc_get_size(bp);
+
+		val = GEM_BFEXT(TXBD_RDBUFF, gem_readl(bp, DCFG10));
+		if (val)
+			bp->tx_bd_rd_prefetch = (2 << (val - 1)) *
+						macb_dma_desc_get_size(bp);
+	}
+
 	mac = of_get_mac_address(np);
 	if (mac) {
 		ether_addr_copy(bp->dev->dev_addr, mac);
diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index 2220c771092b..678835136bf8 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -170,10 +170,7 @@ static int gem_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 	if (delta > TSU_NSEC_MAX_VAL) {
 		gem_tsu_get_time(&bp->ptp_clock_info, &now);
-		if (sign)
-			now = timespec64_sub(now, then);
-		else
-			now = timespec64_add(now, then);
+		now = timespec64_add(now, then);
 
 		gem_tsu_set_time(&bp->ptp_clock_info,
 				 (const struct timespec64 *)&now);
diff --git a/drivers/net/ethernet/calxeda/Kconfig b/drivers/net/ethernet/calxeda/Kconfig
index 07d2201530d2..9fdd496b90ff 100644
--- a/drivers/net/ethernet/calxeda/Kconfig
+++ b/drivers/net/ethernet/calxeda/Kconfig
@@ -1,6 +1,6 @@
 config NET_CALXEDA_XGMAC
 	tristate "Calxeda 1G/10G XGMAC Ethernet driver"
-	depends on HAS_IOMEM && HAS_DMA
+	depends on HAS_IOMEM
 	depends on ARCH_HIGHBANK || COMPILE_TEST
 	select CRC32
 	help
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 043e3c11c42b..92d88c5f76fb 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -15,7 +15,7 @@ if NET_VENDOR_CAVIUM
 
 config THUNDER_NIC_PF
 	tristate "Thunder Physical function driver"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	select THUNDER_NIC_BGX
 	---help---
 	  This driver supports Thunder's NIC physical function.
@@ -28,13 +28,13 @@ config THUNDER_NIC_PF
 config THUNDER_NIC_VF
 	tristate "Thunder Virtual function driver"
 	imply CAVIUM_PTP
-	depends on 64BIT
+	depends on 64BIT && PCI
 	---help---
 	  This driver supports Thunder's NIC virtual function
 
 config	THUNDER_NIC_BGX
 	tristate "Thunder MAC interface driver (BGX)"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	select PHYLIB
 	select MDIO_THUNDER
 	select THUNDER_NIC_RGX
@@ -44,7 +44,7 @@ config	THUNDER_NIC_BGX
 
 config	THUNDER_NIC_RGX
 	tristate "Thunder MAC interface driver (RGX)"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	select PHYLIB
 	select MDIO_THUNDER
 	---help---
@@ -53,7 +53,7 @@ config	THUNDER_NIC_RGX
 
 config CAVIUM_PTP
 	tristate "Cavium PTP coprocessor as PTP clock"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	imply PTP_1588_CLOCK
 	default y
 	---help---
@@ -65,7 +65,7 @@ config CAVIUM_PTP
 
 config LIQUIDIO
 	tristate "Cavium LiquidIO support"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	depends on MAY_USE_DEVLINK
 	imply PTP_1588_CLOCK
 	select FW_LOADER
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 8a815bb57177..7e8454d3b1ad 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -91,6 +91,9 @@ static int octeon_console_debug_enabled(u32 console)
  */
 #define LIO_SYNC_OCTEON_TIME_INTERVAL_MS 60000
 
+/* time to wait for possible in-flight requests in milliseconds */
+#define WAIT_INFLIGHT_REQUEST	msecs_to_jiffies(1000)
+
 struct lio_trusted_vf_ctx {
 	struct completion complete;
 	int status;
@@ -259,7 +262,7 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct)
 	force_io_queues_off(oct);
 
 	/* To allow for in-flight requests */
-	schedule_timeout_uninterruptible(100);
+	schedule_timeout_uninterruptible(WAIT_INFLIGHT_REQUEST);
 
 	if (wait_for_pending_requests(oct))
 		dev_err(&oct->pci_dev->dev, "There were pending requests\n");
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 3f6afb54a5eb..bb43ddb7539e 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -643,13 +643,21 @@ static int octeon_mgmt_set_mac_address(struct net_device *netdev, void *addr)
 static int octeon_mgmt_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct octeon_mgmt *p = netdev_priv(netdev);
-	int size_without_fcs = new_mtu + OCTEON_MGMT_RX_HEADROOM;
+	int max_packet = new_mtu + ETH_HLEN + ETH_FCS_LEN;
 
 	netdev->mtu = new_mtu;
 
-	cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, size_without_fcs);
+	/* HW lifts the limit if the frame is VLAN tagged
+	 * (+4 bytes per each tag, up to two tags)
+	 */
+	cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, max_packet);
+	/* Set the hardware to truncate packets larger than the MTU. The jabber
+	 * register must be set to a multiple of 8 bytes, so round up. JABBER is
+	 * an unconditional limit, so we need to account for two possible VLAN
+	 * tags.
+	 */
 	cvmx_write_csr(p->agl + AGL_GMX_RX_JABBER,
-		       (size_without_fcs + 7) & 0xfff8);
+		       (max_packet + 7 + VLAN_HLEN * 2) & 0xfff8);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 5d08d2aeb172..e337da6ba2a4 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1083,6 +1083,8 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 	lmac->dmacs_count = (RX_DMAC_COUNT / bgx->lmac_count);
 	lmac->dmacs = kcalloc(lmac->dmacs_count, sizeof(*lmac->dmacs),
 			      GFP_KERNEL);
+	if (!lmac->dmacs)
+		return -ENOMEM;
 
 	/* Enable lmac */
 	bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 7b795edd9d3a..a19172dbe6be 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -51,6 +51,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/nospec.h>
 
 #include "common.h"
 #include "cxgb3_ioctl.h"
@@ -2268,6 +2269,7 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 
 		if (t.qset_idx >= nqsets)
 			return -EINVAL;
+		t.qset_idx = array_index_nospec(t.qset_idx, nqsets);
 
 		q = &adapter->params.sge.qset[q1 + t.qset_idx];
 		t.rspq_size = q->rspq_size;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 00fc5f1afb1d..7dddb9e748b8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -1038,10 +1038,8 @@ static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb,
 	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, qid_filterid));
 	req->local_port = cpu_to_be16(f->fs.val.lport);
 	req->peer_port = cpu_to_be16(f->fs.val.fport);
-	req->local_ip = f->fs.val.lip[0] | f->fs.val.lip[1] << 8 |
-		f->fs.val.lip[2] << 16 | f->fs.val.lip[3] << 24;
-	req->peer_ip = f->fs.val.fip[0] | f->fs.val.fip[1] << 8 |
-		f->fs.val.fip[2] << 16 | f->fs.val.fip[3] << 24;
+	memcpy(&req->local_ip, f->fs.val.lip, 4);
+	memcpy(&req->peer_ip, f->fs.val.fip, 4);
 	req->opt0 = cpu_to_be64(NAGLE_V(f->fs.newvlan == VLAN_REMOVE ||
 					f->fs.newvlan == VLAN_REWRITE) |
 				DELACK_V(f->fs.hitcnts) |
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index dd04a2f89ce6..a8926e97935e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -263,7 +263,7 @@ static void dcb_tx_queue_prio_enable(struct net_device *dev, int enable)
 				"Can't %s DCB Priority on port %d, TX Queue %d: err=%d\n",
 				enable ? "set" : "unset", pi->port_id, i, -err);
 		else
-			txq->dcb_prio = value;
+			txq->dcb_prio = enable ? value : 0;
 	}
 }
 
@@ -3072,6 +3072,7 @@ static void cxgb_del_udp_tunnel(struct net_device *netdev,
 
 		adapter->geneve_port = 0;
 		t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, 0);
+		break;
 	default:
 		return;
 	}
@@ -3157,6 +3158,7 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev,
 
 		t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A,
 			     GENEVE_V(be16_to_cpu(ti->port)) | GENEVE_EN_F);
+		break;
 	default:
 		return;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 974a868a4824..3720c3e11ebb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -8702,7 +8702,7 @@ static int t4_get_flash_params(struct adapter *adap)
 	};
 
 	unsigned int part, manufacturer;
-	unsigned int density, size;
+	unsigned int density, size = 0;
 	u32 flashid = 0;
 	int ret;
 
@@ -8772,11 +8772,6 @@ static int t4_get_flash_params(struct adapter *adap)
 		case 0x22: /* 256MB */
 			size = 1 << 28;
 			break;
-
-		default:
-			dev_err(adap->pdev_dev, "Micron Flash Part has bad size, ID = %#x, Density code = %#x\n",
-				flashid, density);
-			return -EINVAL;
 		}
 		break;
 	}
@@ -8792,10 +8787,6 @@ static int t4_get_flash_params(struct adapter *adap)
 		case 0x17: /* 64MB */
 			size = 1 << 26;
 			break;
-		default:
-			dev_err(adap->pdev_dev, "ISSI Flash Part has bad size, ID = %#x, Density code = %#x\n",
-				flashid, density);
-			return -EINVAL;
 		}
 		break;
 	}
@@ -8811,10 +8802,6 @@ static int t4_get_flash_params(struct adapter *adap)
 		case 0x18: /* 16MB */
 			size = 1 << 24;
 			break;
-		default:
-			dev_err(adap->pdev_dev, "Macronix Flash Part has bad size, ID = %#x, Density code = %#x\n",
-				flashid, density);
-			return -EINVAL;
 		}
 		break;
 	}
@@ -8830,17 +8817,21 @@ static int t4_get_flash_params(struct adapter *adap)
 		case 0x18: /* 16MB */
 			size = 1 << 24;
 			break;
-		default:
-			dev_err(adap->pdev_dev, "Winbond Flash Part has bad size, ID = %#x, Density code = %#x\n",
-				flashid, density);
-			return -EINVAL;
 		}
 		break;
 	}
-	default:
-		dev_err(adap->pdev_dev, "Unsupported Flash Part, ID = %#x\n",
-			flashid);
-		return -EINVAL;
+	}
+
+	/* If we didn't recognize the FLASH part, that's no real issue: the
+	 * Hardware/Software contract says that Hardware will _*ALWAYS*_
+	 * use a FLASH part which is at least 4MB in size and has 64KB
+	 * sectors.  The unrecognized FLASH part is likely to be much larger
+	 * than 4MB, but that's all we really need.
+	 */
+	if (size == 0) {
+		dev_warn(adap->pdev_dev, "Unknown Flash Part, ID = %#x, assuming 4MB\n",
+			 flashid);
+		size = 1 << 22;
 	}
 
 	/* Store decoded Flash size and fall through into vetting code. */
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index 5ab912937aff..ec0b545197e2 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -19,6 +19,7 @@ if NET_VENDOR_CIRRUS
 config CS89x0
 	tristate "CS89x0 support"
 	depends on ISA || EISA || ARM
+	depends on !PPC32
 	---help---
 	  Support for CS89x0 chipset based Ethernet cards. If you have a
 	  network (Ethernet) card of this type, say Y and read the file
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 90c645b8538e..60641e202534 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2047,28 +2047,42 @@ static int enic_stop(struct net_device *netdev)
 	return 0;
 }
 
+static int _enic_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	bool running = netif_running(netdev);
+	int err = 0;
+
+	ASSERT_RTNL();
+	if (running) {
+		err = enic_stop(netdev);
+		if (err)
+			return err;
+	}
+
+	netdev->mtu = new_mtu;
+
+	if (running) {
+		err = enic_open(netdev);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int enic_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct enic *enic = netdev_priv(netdev);
-	int running = netif_running(netdev);
 
 	if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic))
 		return -EOPNOTSUPP;
 
-	if (running)
-		enic_stop(netdev);
-
-	netdev->mtu = new_mtu;
-
 	if (netdev->mtu > enic->port_mtu)
 		netdev_warn(netdev,
-			"interface MTU (%d) set higher than port MTU (%d)\n",
-			netdev->mtu, enic->port_mtu);
+			    "interface MTU (%d) set higher than port MTU (%d)\n",
+			    netdev->mtu, enic->port_mtu);
 
-	if (running)
-		enic_open(netdev);
-
-	return 0;
+	return _enic_change_mtu(netdev, new_mtu);
 }
 
 static void enic_change_mtu_work(struct work_struct *work)
@@ -2076,47 +2090,9 @@ static void enic_change_mtu_work(struct work_struct *work)
 	struct enic *enic = container_of(work, struct enic, change_mtu_work);
 	struct net_device *netdev = enic->netdev;
 	int new_mtu = vnic_dev_mtu(enic->vdev);
-	int err;
-	unsigned int i;
-
-	new_mtu = max_t(int, ENIC_MIN_MTU, min_t(int, ENIC_MAX_MTU, new_mtu));
 
 	rtnl_lock();
-
-	/* Stop RQ */
-	del_timer_sync(&enic->notify_timer);
-
-	for (i = 0; i < enic->rq_count; i++)
-		napi_disable(&enic->napi[i]);
-
-	vnic_intr_mask(&enic->intr[0]);
-	enic_synchronize_irqs(enic);
-	err = vnic_rq_disable(&enic->rq[0]);
-	if (err) {
-		rtnl_unlock();
-		netdev_err(netdev, "Unable to disable RQ.\n");
-		return;
-	}
-	vnic_rq_clean(&enic->rq[0], enic_free_rq_buf);
-	vnic_cq_clean(&enic->cq[0]);
-	vnic_intr_clean(&enic->intr[0]);
-
-	/* Fill RQ with new_mtu-sized buffers */
-	netdev->mtu = new_mtu;
-	vnic_rq_fill(&enic->rq[0], enic_rq_alloc_buf);
-	/* Need at least one buffer on ring to get going */
-	if (vnic_rq_desc_used(&enic->rq[0]) == 0) {
-		rtnl_unlock();
-		netdev_err(netdev, "Unable to alloc receive buffers.\n");
-		return;
-	}
-
-	/* Start RQ */
-	vnic_rq_enable(&enic->rq[0]);
-	napi_enable(&enic->napi[0]);
-	vnic_intr_unmask(&enic->intr[0]);
-	enic_notify_timer_start(enic);
-
+	(void)_enic_change_mtu(netdev, new_mtu);
 	rtnl_unlock();
 
 	netdev_info(netdev, "interface MTU set as %d\n", netdev->mtu);
@@ -2916,7 +2892,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 
 	enic->port_mtu = enic->config.mtu;
-	(void)enic_change_mtu(netdev, enic->port_mtu);
 
 	err = enic_set_mac_addr(netdev, enic->mac_addr);
 	if (err) {
@@ -3006,6 +2981,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* MTU range: 68 - 9000 */
 	netdev->min_mtu = ENIC_MIN_MTU;
 	netdev->max_mtu = ENIC_MAX_MTU;
+	netdev->mtu	= enic->port_mtu;
 
 	err = register_netdev(netdev);
 	if (err) {
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 5f4e1ffa7b95..ab02057ac730 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -125,6 +125,9 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms");
 /* Default alignment for start of data in an Rx FD */
 #define DPAA_FD_DATA_ALIGNMENT  16
 
+/* The DPAA requires 256 bytes reserved and mapped for the SGT */
+#define DPAA_SGT_SIZE 256
+
 /* Values for the L3R field of the FM Parse Results
  */
 /* L3 Type field: First IP Present IPv4 */
@@ -1617,8 +1620,8 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 
 	if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
 		nr_frags = skb_shinfo(skb)->nr_frags;
-		dma_unmap_single(dev, addr, qm_fd_get_offset(fd) +
-				 sizeof(struct qm_sg_entry) * (1 + nr_frags),
+		dma_unmap_single(dev, addr,
+				 qm_fd_get_offset(fd) + DPAA_SGT_SIZE,
 				 dma_dir);
 
 		/* The sgt buffer has been allocated with netdev_alloc_frag(),
@@ -1903,8 +1906,7 @@ static int skb_to_sg_fd(struct dpaa_priv *priv,
 	void *sgt_buf;
 
 	/* get a page frag to store the SGTable */
-	sz = SKB_DATA_ALIGN(priv->tx_headroom +
-		sizeof(struct qm_sg_entry) * (1 + nr_frags));
+	sz = SKB_DATA_ALIGN(priv->tx_headroom + DPAA_SGT_SIZE);
 	sgt_buf = netdev_alloc_frag(sz);
 	if (unlikely(!sgt_buf)) {
 		netdev_err(net_dev, "netdev_alloc_frag() failed for size %d\n",
@@ -1972,9 +1974,8 @@ static int skb_to_sg_fd(struct dpaa_priv *priv,
 	skbh = (struct sk_buff **)buffer_start;
 	*skbh = skb;
 
-	addr = dma_map_single(dev, buffer_start, priv->tx_headroom +
-			      sizeof(struct qm_sg_entry) * (1 + nr_frags),
-			      dma_dir);
+	addr = dma_map_single(dev, buffer_start,
+			      priv->tx_headroom + DPAA_SGT_SIZE, dma_dir);
 	if (unlikely(dma_mapping_error(dev, addr))) {
 		dev_err(dev, "DMA mapping failed");
 		err = -EINVAL;
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index ce6e24c74978..ecbf6187e13a 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -324,6 +324,10 @@ struct fman_port_qmi_regs {
 #define HWP_HXS_PHE_REPORT 0x00000800
 #define HWP_HXS_PCAC_PSTAT 0x00000100
 #define HWP_HXS_PCAC_PSTOP 0x00000001
+#define HWP_HXS_TCP_OFFSET 0xA
+#define HWP_HXS_UDP_OFFSET 0xB
+#define HWP_HXS_SH_PAD_REM 0x80000000
+
 struct fman_port_hwp_regs {
 	struct {
 		u32 ssa; /* Soft Sequence Attachment */
@@ -728,6 +732,10 @@ static void init_hwp(struct fman_port *port)
 		iowrite32be(0xffffffff, &regs->pmda[i].lcv);
 	}
 
+	/* Short packet padding removal from checksum calculation */
+	iowrite32be(HWP_HXS_SH_PAD_REM, &regs->pmda[HWP_HXS_TCP_OFFSET].ssa);
+	iowrite32be(HWP_HXS_SH_PAD_REM, &regs->pmda[HWP_HXS_UDP_OFFSET].ssa);
+
 	start_port_hwp(port);
 }
 
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 8bcf470ff5f3..fb1a7251f45d 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -5,7 +5,7 @@
 config NET_VENDOR_HISILICON
 	bool "Hisilicon devices"
 	default y
-	depends on (OF || ACPI) && HAS_DMA
+	depends on OF || ACPI
 	depends on ARM || ARM64 || COMPILE_TEST
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 9dcc5765f11f..794516718d9d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -708,7 +708,7 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb,
 
 static int hns_mac_register_phy(struct hns_mac_cb *mac_cb)
 {
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	struct platform_device *pdev;
 	struct mii_bus *mii_bus;
 	int rc;
@@ -722,13 +722,15 @@ static int hns_mac_register_phy(struct hns_mac_cb *mac_cb)
 			mac_cb->fw_port, "mdio-node", 0, &args);
 	if (rc)
 		return rc;
+	if (!is_acpi_device_node(args.fwnode))
+		return -EINVAL;
 
 	addr = hns_mac_phy_parse_addr(mac_cb->dev, mac_cb->fw_port);
 	if (addr < 0)
 		return addr;
 
 	/* dev address in adev */
-	pdev = hns_dsaf_find_platform_device(acpi_fwnode_handle(args.adev));
+	pdev = hns_dsaf_find_platform_device(args.fwnode);
 	if (!pdev) {
 		dev_err(mac_cb->dev, "mac%d mdio pdev is NULL\n",
 			mac_cb->mac_id);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index ef9ef703d13a..5608f807d7ba 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2377,7 +2377,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 		}
 		priv->fwnode = &ae_node->fwnode;
 	} else if (is_acpi_node(dev->fwnode)) {
-		struct acpi_reference_args args;
+		struct fwnode_reference_args args;
 
 		if (acpi_dev_found(hns_enet_acpi_match[0].id))
 			priv->enet_ver = AE_VERSION_1;
@@ -2393,7 +2393,11 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 			dev_err(dev, "not find ae-handle\n");
 			goto out_read_prop_fail;
 		}
-		priv->fwnode = acpi_fwnode_handle(args.adev);
+		if (!is_acpi_device_node(args.fwnode)) {
+			ret = -EINVAL;
+			goto out_read_prop_fail;
+		}
+		priv->fwnode = args.fwnode;
 	} else {
 		dev_err(dev, "cannot read cfg data from OF or acpi\n");
 		return -ENXIO;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 5b122728dcb4..09e9da10b786 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -983,6 +983,7 @@ static int nic_dev_init(struct pci_dev *pdev)
 	hinic_hwdev_cb_register(nic_dev->hwdev, HINIC_MGMT_MSG_CMD_LINK_STATUS,
 				nic_dev, link_status_event_handler);
 
+	SET_NETDEV_DEV(netdev, &pdev->dev);
 	err = register_netdev(netdev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to register netdev\n");
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index e2e5cdc7119c..4c0f7eda1166 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -439,6 +439,7 @@ static void rx_free_irq(struct hinic_rxq *rxq)
 {
 	struct hinic_rq *rq = rxq->rq;
 
+	irq_set_affinity_hint(rq->irq, NULL);
 	free_irq(rq->irq, rxq);
 	rx_del_napi(rxq);
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 9128858479c4..2353ec829c04 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -229,6 +229,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 		txq->txq_stats.tx_busy++;
 		u64_stats_update_end(&txq->txq_stats.syncp);
 		err = NETDEV_TX_BUSY;
+		wqe_size = 0;
 		goto flush_skbs;
 	}
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index d0e196bff081..ffe7acbeaa22 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -329,7 +329,8 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 	return;
 
 failure:
-	dev_info(dev, "replenish pools failure\n");
+	if (lpar_rc != H_PARAMETER && lpar_rc != H_CLOSED)
+		dev_err_ratelimited(dev, "rx: replenish packet buffer failed\n");
 	pool->free_map[pool->next_free] = index;
 	pool->rx_buff[index].skb = NULL;
 
@@ -1617,7 +1618,8 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 				      &tx_crq);
 	}
 	if (lpar_rc != H_SUCCESS) {
-		dev_err(dev, "tx failed with code %ld\n", lpar_rc);
+		if (lpar_rc != H_CLOSED && lpar_rc != H_PARAMETER)
+			dev_err_ratelimited(dev, "tx: send failed\n");
 		dev_kfree_skb_any(skb);
 		tx_buff->skb = NULL;
 
@@ -1825,8 +1827,8 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 
 		rc = ibmvnic_login(netdev);
 		if (rc) {
-			adapter->state = VNIC_PROBED;
-			return 0;
+			adapter->state = reset_state;
+			return rc;
 		}
 
 		if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM ||
@@ -3204,6 +3206,25 @@ static union ibmvnic_crq *ibmvnic_next_crq(struct ibmvnic_adapter *adapter)
 	return crq;
 }
 
+static void print_subcrq_error(struct device *dev, int rc, const char *func)
+{
+	switch (rc) {
+	case H_PARAMETER:
+		dev_warn_ratelimited(dev,
+				     "%s failed: Send request is malformed or adapter failover pending. (rc=%d)\n",
+				     func, rc);
+		break;
+	case H_CLOSED:
+		dev_warn_ratelimited(dev,
+				     "%s failed: Backing queue closed. Adapter is down or failover pending. (rc=%d)\n",
+				     func, rc);
+		break;
+	default:
+		dev_err_ratelimited(dev, "%s failed: (rc=%d)\n", func, rc);
+		break;
+	}
+}
+
 static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
 		       union sub_crq *sub_crq)
 {
@@ -3230,11 +3251,8 @@ static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
 				cpu_to_be64(u64_crq[2]),
 				cpu_to_be64(u64_crq[3]));
 
-	if (rc) {
-		if (rc == H_CLOSED)
-			dev_warn(dev, "CRQ Queue closed\n");
-		dev_err(dev, "Send error (rc=%d)\n", rc);
-	}
+	if (rc)
+		print_subcrq_error(dev, rc, __func__);
 
 	return rc;
 }
@@ -3252,11 +3270,8 @@ static int send_subcrq_indirect(struct ibmvnic_adapter *adapter,
 				cpu_to_be64(remote_handle),
 				ioba, num_entries);
 
-	if (rc) {
-		if (rc == H_CLOSED)
-			dev_warn(dev, "CRQ Queue closed\n");
-		dev_err(dev, "Send (indirect) error (rc=%d)\n", rc);
-	}
+	if (rc)
+		print_subcrq_error(dev, rc, __func__);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index ed6dbcfd4e96..b151ae316546 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2199,9 +2199,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
 	return true;
 }
 
-#define I40E_XDP_PASS 0
-#define I40E_XDP_CONSUMED 1
-#define I40E_XDP_TX 2
+#define I40E_XDP_PASS		0
+#define I40E_XDP_CONSUMED	BIT(0)
+#define I40E_XDP_TX		BIT(1)
+#define I40E_XDP_REDIR		BIT(2)
 
 static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 			      struct i40e_ring *xdp_ring);
@@ -2248,7 +2249,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_TX : I40E_XDP_CONSUMED;
+		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
@@ -2311,7 +2312,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	bool failure = false, xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
+	bool failure = false;
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
@@ -2372,8 +2374,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		}
 
 		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -I40E_XDP_TX) {
-				xdp_xmit = true;
+			unsigned int xdp_res = -PTR_ERR(skb);
+
+			if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
+				xdp_xmit |= xdp_res;
 				i40e_rx_buffer_flip(rx_ring, rx_buffer, size);
 			} else {
 				rx_buffer->pagecnt_bias++;
@@ -2427,12 +2431,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		total_rx_packets++;
 	}
 
-	if (xdp_xmit) {
+	if (xdp_xmit & I40E_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & I40E_XDP_TX) {
 		struct i40e_ring *xdp_ring =
 			rx_ring->vsi->xdp_rings[rx_ring->queue_index];
 
 		i40e_xdp_ring_update_tail(xdp_ring);
-		xdp_do_flush_map();
 	}
 
 	rx_ring->skb = skb;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 3f5c350716bb..0bd1294ba517 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -1871,7 +1871,12 @@ s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq,
 	if (enable_addr != 0)
 		rar_high |= IXGBE_RAH_AV;
 
+	/* Record lower 32 bits of MAC address and then make
+	 * sure that write is flushed to hardware before writing
+	 * the upper 16 bits and setting the valid bit.
+	 */
 	IXGBE_WRITE_REG(hw, IXGBE_RAL(index), rar_low);
+	IXGBE_WRITE_FLUSH(hw);
 	IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high);
 
 	return 0;
@@ -1903,8 +1908,13 @@ s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index)
 	rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(index));
 	rar_high &= ~(0x0000FFFF | IXGBE_RAH_AV);
 
-	IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0);
+	/* Clear the address valid bit and upper 16 bits of the address
+	 * before clearing the lower bits. This way we aren't updating
+	 * a live filter.
+	 */
 	IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high);
+	IXGBE_WRITE_FLUSH(hw);
+	IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0);
 
 	/* clear VMDq pool/queue selection for this RAR */
 	hw->mac.ops.clear_vmdq(hw, index, IXGBE_CLEAR_VMDQ_ALL);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index c116f459945d..da4322e4daed 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -839,7 +839,7 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
 	}
 
 	itd->sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX;
-	if (unlikely(itd->sa_idx > IXGBE_IPSEC_MAX_SA_COUNT)) {
+	if (unlikely(itd->sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT)) {
 		netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n",
 			   __func__, itd->sa_idx, xs->xso.offload_handle);
 		return 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 3e87dbbc9024..62e57b05a0ae 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2186,9 +2186,10 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	return skb;
 }
 
-#define IXGBE_XDP_PASS 0
-#define IXGBE_XDP_CONSUMED 1
-#define IXGBE_XDP_TX 2
+#define IXGBE_XDP_PASS		0
+#define IXGBE_XDP_CONSUMED	BIT(0)
+#define IXGBE_XDP_TX		BIT(1)
+#define IXGBE_XDP_REDIR		BIT(2)
 
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 			       struct xdp_frame *xdpf);
@@ -2225,7 +2226,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
 		if (!err)
-			result = IXGBE_XDP_TX;
+			result = IXGBE_XDP_REDIR;
 		else
 			result = IXGBE_XDP_CONSUMED;
 		break;
@@ -2285,7 +2286,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	unsigned int mss = 0;
 #endif /* IXGBE_FCOE */
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
-	bool xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
@@ -2328,8 +2329,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		}
 
 		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -IXGBE_XDP_TX) {
-				xdp_xmit = true;
+			unsigned int xdp_res = -PTR_ERR(skb);
+
+			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+				xdp_xmit |= xdp_res;
 				ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
 			} else {
 				rx_buffer->pagecnt_bias++;
@@ -2401,7 +2404,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		total_rx_packets++;
 	}
 
-	if (xdp_xmit) {
+	if (xdp_xmit & IXGBE_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & IXGBE_XDP_TX) {
 		struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
 
 		/* Force memory writes to complete before letting h/w
@@ -2409,8 +2415,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		 */
 		wmb();
 		writel(ring->next_to_use, ring->tail);
-
-		xdp_do_flush_map();
 	}
 
 	u64_stats_update_begin(&rx_ring->syncp);
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index cc2f7701e71e..f33fd22b351c 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -18,8 +18,8 @@ if NET_VENDOR_MARVELL
 
 config MV643XX_ETH
 	tristate "Marvell Discovery (643XX) and Orion ethernet support"
-	depends on (MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST) && INET
-	depends on HAS_DMA
+	depends on MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST
+	depends on INET
 	select PHYLIB
 	select MVMDIO
 	---help---
@@ -58,7 +58,6 @@ config MVNETA_BM_ENABLE
 config MVNETA
 	tristate "Marvell Armada 370/38x/XP/37xx network interface support"
 	depends on ARCH_MVEBU || COMPILE_TEST
-	depends on HAS_DMA
 	select MVMDIO
 	select PHYLINK
 	---help---
@@ -84,7 +83,6 @@ config MVNETA_BM
 config MVPP2
 	tristate "Marvell Armada 375/7K/8K network interface support"
 	depends on ARCH_MVEBU || COMPILE_TEST
-	depends on HAS_DMA
 	select MVMDIO
 	select PHYLINK
 	---help---
@@ -93,7 +91,7 @@ config MVPP2
 
 config PXA168_ETH
 	tristate "Marvell pxa168 ethernet support"
-	depends on HAS_IOMEM && HAS_DMA
+	depends on HAS_IOMEM
 	depends on CPU_PXA168 || ARCH_BERLIN || COMPILE_TEST
 	select PHYLIB
 	---help---
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 17a904cc6a5e..0ad2f3f7da85 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1932,7 +1932,7 @@ static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo,
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		index = rx_desc - rxq->descs;
 		data = rxq->buf_virt_addr[index];
-		phys_addr = rx_desc->buf_phys_addr;
+		phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction;
 
 		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
 		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 9f54ccbddea7..3360f7b9ee73 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -474,10 +474,10 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 {
 	const struct mlx4_en_frag_info *frag_info = priv->frag_info;
 	unsigned int truesize = 0;
+	bool release = true;
 	int nr, frag_size;
 	struct page *page;
 	dma_addr_t dma;
-	bool release;
 
 	/* Collect used fragments while replacing them in the HW descriptors */
 	for (nr = 0;; frags++) {
@@ -500,7 +500,11 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 			release = page_count(page) != 1 ||
 				  page_is_pfmemalloc(page) ||
 				  page_to_nid(page) != numa_mem_id();
-		} else {
+		} else if (!priv->rx_headroom) {
+			/* rx_headroom for non XDP setup is always 0.
+			 * When XDP is set, the above condition will
+			 * guarantee page is always released.
+			 */
 			u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES);
 
 			frags->page_offset += sz_align;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 7b1b5ac986d0..31bd56727022 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2958,7 +2958,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 	u32 srqn = qp_get_srqn(qpc) & 0xffffff;
 	int use_srq = (qp_get_srqn(qpc) >> 24) & 1;
 	struct res_srq *srq;
-	int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
+	int local_qpn = vhcr->in_modifier & 0xffffff;
 
 	err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 323ffe8bf7e4..456f30007ad6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -123,7 +123,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 	int i;
 
 	buf->size = size;
-	buf->npages = 1 << get_order(size);
+	buf->npages = DIV_ROUND_UP(size, PAGE_SIZE);
 	buf->page_shift = PAGE_SHIFT;
 	buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list),
 			     GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 487388aed98f..384c1fa49081 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -807,6 +807,7 @@ static void cmd_work_handler(struct work_struct *work)
 	unsigned long flags;
 	bool poll_cmd = ent->polling;
 	int alloc_ret;
+	int cmd_mode;
 
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
@@ -853,6 +854,7 @@ static void cmd_work_handler(struct work_struct *work)
 	set_signature(ent, !cmd->checksum_disabled);
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
+	cmd_mode = cmd->mode;
 
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
@@ -877,7 +879,7 @@ static void cmd_work_handler(struct work_struct *work)
 	iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
 	mmiowb();
 	/* if not in polling don't use ent after this point */
-	if (cmd->mode == CMD_MODE_POLLING || poll_cmd) {
+	if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
@@ -1276,7 +1278,7 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf,
 {
 	struct mlx5_core_dev *dev = filp->private_data;
 	struct mlx5_cmd_debug *dbg = &dev->cmd.dbg;
-	char outlen_str[8];
+	char outlen_str[8] = {0};
 	int outlen;
 	void *ptr;
 	int err;
@@ -1291,8 +1293,6 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf,
 	if (copy_from_user(outlen_str, buf, count))
 		return -EFAULT;
 
-	outlen_str[7] = 0;
-
 	err = sscanf(outlen_str, "%d", &outlen);
 	if (err < 0)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index eb9eb7aa953a..405236cf0b04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -858,8 +858,6 @@ struct mlx5e_profile {
 		mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 		mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
 	} rx_handlers;
-	void	(*netdev_registered_init)(struct mlx5e_priv *priv);
-	void    (*netdev_registered_remove)(struct mlx5e_priv *priv);
 	int	max_tc;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 75e4308ba786..d258bb679271 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -381,14 +381,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv)
 	HLIST_HEAD(del_list);
 	spin_lock_bh(&priv->fs.arfs.arfs_lock);
 	mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) {
-		if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
-			break;
 		if (!work_pending(&arfs_rule->arfs_work) &&
 		    rps_may_expire_flow(priv->netdev,
 					arfs_rule->rxq, arfs_rule->flow_id,
 					arfs_rule->filter_id)) {
 			hlist_del_init(&arfs_rule->hlist);
 			hlist_add_head(&arfs_rule->hlist, &del_list);
+			if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
+				break;
 		}
 	}
 	spin_unlock_bh(&priv->fs.arfs.arfs_lock);
@@ -711,6 +711,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	    skb->protocol != htons(ETH_P_IPV6))
 		return -EPROTONOSUPPORT;
 
+	if (skb->encapsulation)
+		return -EPROTONOSUPPORT;
+
 	arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
 	if (!arfs_t)
 		return -EPROTONOSUPPORT;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 0a52f31fef37..722998d68564 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -275,7 +275,8 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets)
 }
 
 static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
-				    struct ieee_ets *ets)
+				    struct ieee_ets *ets,
+				    bool zero_sum_allowed)
 {
 	bool have_ets_tc = false;
 	int bw_sum = 0;
@@ -300,8 +301,9 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
 	}
 
 	if (have_ets_tc && bw_sum != 100) {
-		netdev_err(netdev,
-			   "Failed to validate ETS: BW sum is illegal\n");
+		if (bw_sum || (!bw_sum && !zero_sum_allowed))
+			netdev_err(netdev,
+				   "Failed to validate ETS: BW sum is illegal\n");
 		return -EINVAL;
 	}
 	return 0;
@@ -316,7 +318,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev,
 	if (!MLX5_CAP_GEN(priv->mdev, ets))
 		return -EOPNOTSUPP;
 
-	err = mlx5e_dbcnl_validate_ets(netdev, ets);
+	err = mlx5e_dbcnl_validate_ets(netdev, ets, false);
 	if (err)
 		return err;
 
@@ -441,16 +443,12 @@ static int mlx5e_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app)
 	bool is_new;
 	int err;
 
-	if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
-		return -EINVAL;
-
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
-		return -EINVAL;
-
-	if (!MLX5_DSCP_SUPPORTED(priv->mdev))
-		return -EINVAL;
+	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) ||
+	    !MLX5_DSCP_SUPPORTED(priv->mdev))
+		return -EOPNOTSUPP;
 
-	if (app->protocol >= MLX5E_MAX_DSCP)
+	if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) ||
+	    (app->protocol >= MLX5E_MAX_DSCP))
 		return -EINVAL;
 
 	/* Save the old entry info */
@@ -498,16 +496,12 @@ static int mlx5e_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int err;
 
-	if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
-		return -EINVAL;
-
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
-		return -EINVAL;
-
-	if (!MLX5_DSCP_SUPPORTED(priv->mdev))
-		return -EINVAL;
+	if  (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) ||
+	     !MLX5_DSCP_SUPPORTED(priv->mdev))
+		return -EOPNOTSUPP;
 
-	if (app->protocol >= MLX5E_MAX_DSCP)
+	if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) ||
+	    (app->protocol >= MLX5E_MAX_DSCP))
 		return -EINVAL;
 
 	/* Skip if no dscp app entry */
@@ -642,12 +636,9 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev)
 			  ets.prio_tc[i]);
 	}
 
-	err = mlx5e_dbcnl_validate_ets(netdev, &ets);
-	if (err) {
-		netdev_err(netdev,
-			   "%s, Failed to validate ETS: %d\n", __func__, err);
+	err = mlx5e_dbcnl_validate_ets(netdev, &ets, true);
+	if (err)
 		goto out;
-	}
 
 	err = mlx5e_dcbnl_ieee_setets_core(priv, &ets);
 	if (err) {
@@ -1147,7 +1138,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state)
 {
 	int err;
 
-	err =  mlx5_set_trust_state(priv->mdev, trust_state);
+	err = mlx5_set_trust_state(priv->mdev, trust_state);
 	if (err)
 		return err;
 	priv->dcbx_dp.trust_state = trust_state;
@@ -1173,6 +1164,8 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
+	priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_PCP;
+
 	if (!MLX5_DSCP_SUPPORTED(mdev))
 		return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 56c1b6f5593e..c592678ab5f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2846,7 +2846,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	mlx5e_activate_channels(&priv->channels);
 	netif_tx_start_all_queues(priv->netdev);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_add_sqs_fwd_rules(priv);
 
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
@@ -2857,7 +2857,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	mlx5e_redirect_rqts_to_drop(priv);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_remove_sqs_fwd_rules(priv);
 
 	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
@@ -3712,7 +3712,8 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 
 	if (!reset) {
 		params->sw_mtu = new_mtu;
-		set_mtu_cb(priv);
+		if (set_mtu_cb)
+			set_mtu_cb(priv);
 		netdev->mtu = params->sw_mtu;
 		goto out;
 	}
@@ -4597,7 +4598,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	mlx5e_set_netdev_dev_addr(netdev);
 
 #if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-	if (MLX5_VPORT_MANAGER(mdev))
+	if (MLX5_ESWITCH_MANAGER(mdev))
 		netdev->switchdev_ops = &mlx5e_switchdev_ops;
 #endif
 
@@ -4753,7 +4754,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 	mlx5e_enable_async_events(priv);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_register_vport_reps(priv);
 
 	if (netdev->reg_state != NETREG_REGISTERED)
@@ -4788,7 +4789,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_unregister_vport_reps(priv);
 
 	mlx5e_disable_async_events(priv);
@@ -4972,7 +4973,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 		return NULL;
 
 #ifdef CONFIG_MLX5_ESWITCH
-	if (MLX5_VPORT_MANAGER(mdev)) {
+	if (MLX5_ESWITCH_MANAGER(mdev)) {
 		rpriv = mlx5e_alloc_nic_rep_priv(mdev);
 		if (!rpriv) {
 			mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 57987f6546e8..2b8040a3cdbd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -823,7 +823,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep;
 
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
 		return false;
 
 	rep = rpriv->rep;
@@ -837,8 +837,12 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	struct mlx5_eswitch_rep *rep;
 
+	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
+		return false;
+
+	rep = rpriv->rep;
 	if (rep && rep->vport != FDB_UPLINK_VPORT)
 		return true;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 0edf4751a8ba..dfbcda0d0e08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1957,6 +1957,10 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 	else
 		actions = flow->nic_attr->action;
 
+	if (flow->flags & MLX5E_TC_FLOW_EGRESS &&
+	    !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP))
+		return false;
+
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		return modify_header_match_supported(&parse_attr->spec, exts);
 
@@ -1966,15 +1970,15 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
 {
 	struct mlx5_core_dev *fmdev, *pmdev;
-	u16 func_id, peer_id;
+	u64 fsystem_guid, psystem_guid;
 
 	fmdev = priv->mdev;
 	pmdev = peer_priv->mdev;
 
-	func_id = (u16)((fmdev->pdev->bus->number << 8) | PCI_SLOT(fmdev->pdev->devfn));
-	peer_id = (u16)((pmdev->pdev->bus->number << 8) | PCI_SLOT(pmdev->pdev->devfn));
+	mlx5_query_nic_vport_system_image_guid(fmdev, &fsystem_guid);
+	mlx5_query_nic_vport_system_image_guid(pmdev, &psystem_guid);
 
-	return (func_id == peer_id);
+	return (fsystem_guid == psystem_guid);
 }
 
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index f63dfbcd29fe..40dba9e8af92 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1594,17 +1594,15 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 }
 
 /* Public E-Switch API */
-#define ESW_ALLOWED(esw) ((esw) && MLX5_VPORT_MANAGER((esw)->dev))
+#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
+
 
 int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 {
 	int err;
 	int i, enabled_events;
 
-	if (!ESW_ALLOWED(esw))
-		return 0;
-
-	if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) ||
+	if (!ESW_ALLOWED(esw) ||
 	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
 		esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
 		return -EOPNOTSUPP;
@@ -1698,7 +1696,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	int vport_num;
 	int err;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	esw_info(dev,
@@ -1767,7 +1765,7 @@ abort:
 
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 {
-	if (!esw || !MLX5_VPORT_MANAGER(esw->dev))
+	if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev))
 		return;
 
 	esw_info(esw->dev, "cleanup\n");
@@ -1806,7 +1804,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 	u64 node_guid;
 	int err = 0;
 
-	if (!ESW_ALLOWED(esw))
+	if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
 		return -EPERM;
 	if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
 		return -EINVAL;
@@ -1883,7 +1881,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 {
 	struct mlx5_vport *evport;
 
-	if (!ESW_ALLOWED(esw))
+	if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
 		return -EPERM;
 	if (!LEGAL_VPORT(esw, vport))
 		return -EINVAL;
@@ -2218,6 +2216,6 @@ free_out:
 
 u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
 {
-	return esw->mode;
+	return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index cecd201f0b73..91f1209886ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1079,8 +1079,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink)
 	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
 		return -EOPNOTSUPP;
 
-	if (!MLX5_CAP_GEN(dev, vport_group_manager))
-		return -EOPNOTSUPP;
+	if(!MLX5_ESWITCH_MANAGER(dev))
+		return -EPERM;
 
 	if (dev->priv.eswitch->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 49a75d31185e..6ddb2565884d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -32,6 +32,7 @@
 
 #include <linux/mutex.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/eswitch.h>
 
 #include "mlx5_core.h"
 #include "fs_core.h"
@@ -1886,7 +1887,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!fwd_next_prio_supported(ft))
 			return ERR_PTR(-EOPNOTSUPP);
-		if (dest)
+		if (dest_num)
 			return ERR_PTR(-EINVAL);
 		mutex_lock(&root->chain_lock);
 		next_ft = find_next_chained_ft(prio);
@@ -2652,7 +2653,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
-	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	if (MLX5_ESWITCH_MANAGER(dev)) {
 		if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
 			err = init_fdb_root_ns(steering);
 			if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index afd9f4fa22f4..41ad24f0de2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -32,6 +32,7 @@
 
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
+#include <linux/mlx5/eswitch.h>
 #include <linux/module.h>
 #include "mlx5_core.h"
 #include "../../mlxfw/mlxfw.h"
@@ -159,13 +160,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	}
 
 	if (MLX5_CAP_GEN(dev, vport_group_manager) &&
-	    MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	    MLX5_ESWITCH_MANAGER(dev)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE);
 		if (err)
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	if (MLX5_ESWITCH_MANAGER(dev)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH);
 		if (err)
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index af3bb2f7a504..b7c21eb21a21 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -76,6 +76,7 @@ void mlx5i_init(struct mlx5_core_dev *mdev,
 		void *ppriv)
 {
 	struct mlx5e_priv *priv  = mlx5i_epriv(netdev);
+	u16 max_mtu;
 
 	/* priv init */
 	priv->mdev        = mdev;
@@ -84,6 +85,9 @@ void mlx5i_init(struct mlx5_core_dev *mdev,
 	priv->ppriv       = ppriv;
 	mutex_init(&priv->state_lock);
 
+	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+	netdev->mtu = max_mtu;
+
 	mlx5e_build_nic_params(mdev, &priv->channels.params,
 			       profile->max_nch(mdev), netdev->mtu);
 	mlx5i_build_nic_params(mdev, &priv->channels.params);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 1e062e6b2587..3f767cde4c1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -488,6 +488,7 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev,
 void mlx5_init_clock(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_clock *clock = &mdev->clock;
+	u64 overflow_cycles;
 	u64 ns;
 	u64 frac = 0;
 	u32 dev_freq;
@@ -511,10 +512,17 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 
 	/* Calculate period in seconds to call the overflow watchdog - to make
 	 * sure counter is checked at least once every wrap around.
+	 * The period is calculated as the minimum between max HW cycles count
+	 * (The clock source mask) and max amount of cycles that can be
+	 * multiplied by clock multiplier where the result doesn't exceed
+	 * 64bits.
 	 */
-	ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask,
+	overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult);
+	overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1);
+
+	ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles,
 				 frac, &frac);
-	do_div(ns, NSEC_PER_SEC / 2 / HZ);
+	do_div(ns, NSEC_PER_SEC / HZ);
 	clock->overflow_period = ns;
 
 	mdev->clock_info_page = alloc_page(GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index 7cb67122e8b5..98359559c77e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -33,6 +33,7 @@
 #include <linux/etherdevice.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/eswitch.h>
 #include "mlx5_core.h"
 #include "lib/mpfs.h"
 
@@ -98,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev)
 	int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table);
 	struct mlx5_mpfs *mpfs;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL);
@@ -122,7 +123,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_mpfs *mpfs = dev->priv.mpfs;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return;
 
 	WARN_ON(!hlist_empty(mpfs->hash));
@@ -137,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
 	u32 index;
 	int err;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mutex_lock(&mpfs->lock);
@@ -179,7 +180,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 	int err = 0;
 	u32 index;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mutex_lock(&mpfs->lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index fa9d0760dd36..31a9cbd85689 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -701,7 +701,7 @@ EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc);
 static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 				   int inlen)
 {
-	u32 out[MLX5_ST_SZ_DW(qtct_reg)];
+	u32 out[MLX5_ST_SZ_DW(qetc_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
 		return -EOPNOTSUPP;
@@ -713,7 +713,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out,
 				     int outlen)
 {
-	u32 in[MLX5_ST_SZ_DW(qtct_reg)];
+	u32 in[MLX5_ST_SZ_DW(qetc_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 2a8b529ce6dd..a0674962f02c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -88,6 +88,9 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 		return -EBUSY;
 	}
 
+	if (!MLX5_ESWITCH_MANAGER(dev))
+		goto enable_vfs_hca;
+
 	err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
 	if (err) {
 		mlx5_core_warn(dev,
@@ -95,6 +98,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 		return err;
 	}
 
+enable_vfs_hca:
 	for (vf = 0; vf < num_vfs; vf++) {
 		err = mlx5_core_enable_hca(dev, vf + 1);
 		if (err) {
@@ -140,7 +144,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 	}
 
 out:
-	mlx5_eswitch_disable_sriov(dev->priv.eswitch);
+	if (MLX5_ESWITCH_MANAGER(dev))
+		mlx5_eswitch_disable_sriov(dev->priv.eswitch);
 
 	if (mlx5_wait_for_vf_pages(dev))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 719cecb182c6..7eecd5b07bb1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -549,8 +549,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 		return -EINVAL;
 	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
 		return -EACCES;
-	if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
-		return -EOPNOTSUPP;
 
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index b97bb72b4db4..86478a6b99c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -113,35 +113,45 @@ err_db_free:
 	return err;
 }
 
-static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf,
-				  struct mlx5_wq_qp *qp)
+static void mlx5_qp_set_frag_buf(struct mlx5_frag_buf *buf,
+				 struct mlx5_wq_qp *qp)
 {
+	struct mlx5_frag_buf_ctrl *sq_fbc;
 	struct mlx5_frag_buf *rqb, *sqb;
 
-	rqb = &qp->rq.fbc.frag_buf;
+	rqb  = &qp->rq.fbc.frag_buf;
 	*rqb = *buf;
 	rqb->size   = mlx5_wq_cyc_get_byte_size(&qp->rq);
-	rqb->npages = 1 << get_order(rqb->size);
+	rqb->npages = DIV_ROUND_UP(rqb->size, PAGE_SIZE);
 
-	sqb = &qp->sq.fbc.frag_buf;
-	*sqb = *buf;
-	sqb->size   = mlx5_wq_cyc_get_byte_size(&qp->rq);
-	sqb->npages = 1 << get_order(sqb->size);
+	sq_fbc = &qp->sq.fbc;
+	sqb    = &sq_fbc->frag_buf;
+	*sqb   = *buf;
+	sqb->size   = mlx5_wq_cyc_get_byte_size(&qp->sq);
+	sqb->npages = DIV_ROUND_UP(sqb->size, PAGE_SIZE);
 	sqb->frags += rqb->npages; /* first part is for the rq */
+	if (sq_fbc->strides_offset)
+		sqb->frags--;
 }
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
 {
+	u32 sq_strides_offset;
 	int err;
 
 	mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4,
 		      MLX5_GET(qpc, qpc, log_rq_size),
 		      &wq->rq.fbc);
-	mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB),
-		      MLX5_GET(qpc, qpc, log_sq_size),
-		      &wq->sq.fbc);
+
+	sq_strides_offset =
+		((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB;
+
+	mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB),
+			     MLX5_GET(qpc, qpc, log_sq_size),
+			     sq_strides_offset,
+			     &wq->sq.fbc);
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
@@ -156,7 +166,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		goto err_db_free;
 	}
 
-	mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq);
+	mlx5_qp_set_frag_buf(&wq_ctrl->buf, wq);
 
 	wq->rq.db  = &wq_ctrl->db.db[MLX5_RCV_DBR];
 	wq->sq.db  = &wq_ctrl->db.db[MLX5_SND_DBR];
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index f4d9c9975ac3..82827a8d3d67 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -30,7 +30,7 @@ config MLXSW_CORE_THERMAL
 
 config MLXSW_PCI
 	tristate "PCI bus implementation for Mellanox Technologies Switch ASICs"
-	depends on PCI && HAS_DMA && HAS_IOMEM && MLXSW_CORE
+	depends on PCI && HAS_IOMEM && MLXSW_CORE
 	default m
 	---help---
 	  This is PCI bus implementation for Mellanox Technologies Switch ASICs.
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 3c0d882ba183..f6f6a568d66a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -327,12 +327,16 @@ static void mlxsw_afa_resource_add(struct mlxsw_afa_block *block,
 	list_add(&resource->list, &block->resource_list);
 }
 
+static void mlxsw_afa_resource_del(struct mlxsw_afa_resource *resource)
+{
+	list_del(&resource->list);
+}
+
 static void mlxsw_afa_resources_destroy(struct mlxsw_afa_block *block)
 {
 	struct mlxsw_afa_resource *resource, *tmp;
 
 	list_for_each_entry_safe(resource, tmp, &block->resource_list, list) {
-		list_del(&resource->list);
 		resource->destructor(block, resource);
 	}
 }
@@ -530,6 +534,7 @@ static void
 mlxsw_afa_fwd_entry_ref_destroy(struct mlxsw_afa_block *block,
 				struct mlxsw_afa_fwd_entry_ref *fwd_entry_ref)
 {
+	mlxsw_afa_resource_del(&fwd_entry_ref->resource);
 	mlxsw_afa_fwd_entry_put(block->afa, fwd_entry_ref->fwd_entry);
 	kfree(fwd_entry_ref);
 }
@@ -579,6 +584,7 @@ static void
 mlxsw_afa_counter_destroy(struct mlxsw_afa_block *block,
 			  struct mlxsw_afa_counter *counter)
 {
+	mlxsw_afa_resource_del(&counter->resource);
 	block->afa->ops->counter_index_put(block->afa->ops_priv,
 					   counter->counter_index);
 	kfree(counter);
@@ -626,8 +632,8 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block,
 	char *oneact;
 	char *actions;
 
-	if (WARN_ON(block->finished))
-		return NULL;
+	if (block->finished)
+		return ERR_PTR(-EINVAL);
 	if (block->cur_act_index + action_size >
 	    block->afa->max_acts_per_set) {
 		struct mlxsw_afa_set *set;
@@ -637,7 +643,7 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block,
 		 */
 		set = mlxsw_afa_set_create(false);
 		if (!set)
-			return NULL;
+			return ERR_PTR(-ENOBUFS);
 		set->prev = block->cur_set;
 		block->cur_act_index = 0;
 		block->cur_set->next = set;
@@ -724,8 +730,8 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
 						  MLXSW_AFA_VLAN_CODE,
 						  MLXSW_AFA_VLAN_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
 			    MLXSW_AFA_VLAN_CMD_SET_OUTER, vid,
 			    MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp,
@@ -806,8 +812,8 @@ int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block)
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, 0);
 	return 0;
@@ -820,8 +826,8 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id)
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD,
 				trap_id);
@@ -836,8 +842,8 @@ int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block,
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD,
 				trap_id);
@@ -856,6 +862,7 @@ static void
 mlxsw_afa_mirror_destroy(struct mlxsw_afa_block *block,
 			 struct mlxsw_afa_mirror *mirror)
 {
+	mlxsw_afa_resource_del(&mirror->resource);
 	block->afa->ops->mirror_del(block->afa->ops_priv,
 				    mirror->local_in_port,
 				    mirror->span_id,
@@ -908,8 +915,8 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block,
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, 0);
 	mlxsw_afa_trapdisc_mirror_pack(act, true, mirror_agent);
@@ -996,8 +1003,8 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
 
 	act = mlxsw_afa_block_append_action(block, MLXSW_AFA_FORWARD_CODE,
 					    MLXSW_AFA_FORWARD_SIZE);
-	if (!act) {
-		err = -ENOBUFS;
+	if (IS_ERR(act)) {
+		err = PTR_ERR(act);
 		goto err_append_action;
 	}
 	mlxsw_afa_forward_pack(act, MLXSW_AFA_FORWARD_TYPE_PBS,
@@ -1052,8 +1059,8 @@ int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block,
 {
 	char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_POLCNT_CODE,
 						  MLXSW_AFA_POLCNT_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES,
 			      counter_index);
 	return 0;
@@ -1123,8 +1130,8 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid)
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_VIRFWD_CODE,
 						  MLXSW_AFA_VIRFWD_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid);
 	return 0;
 }
@@ -1193,8 +1200,8 @@ int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_MCROUTER_CODE,
 						  MLXSW_AFA_MCROUTER_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_mcrouter_pack(act, MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP,
 				expected_irif, min_mtu, rmid_valid, kvdl_index);
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 6aaaf3d9ba31..77b2adb29341 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4756,6 +4756,12 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
 	kfree(mlxsw_sp_rt6);
 }
 
+static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
+{
+	/* RTF_CACHE routes are ignored */
+	return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY;
+}
+
 static struct fib6_info *
 mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
 {
@@ -4765,11 +4771,11 @@ mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
 
 static struct mlxsw_sp_fib6_entry *
 mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
-				 const struct fib6_info *nrt, bool append)
+				 const struct fib6_info *nrt, bool replace)
 {
 	struct mlxsw_sp_fib6_entry *fib6_entry;
 
-	if (!append)
+	if (!mlxsw_sp_fib6_rt_can_mp(nrt) || replace)
 		return NULL;
 
 	list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
@@ -4784,7 +4790,8 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
 			break;
 		if (rt->fib6_metric < nrt->fib6_metric)
 			continue;
-		if (rt->fib6_metric == nrt->fib6_metric)
+		if (rt->fib6_metric == nrt->fib6_metric &&
+		    mlxsw_sp_fib6_rt_can_mp(rt))
 			return fib6_entry;
 		if (rt->fib6_metric > nrt->fib6_metric)
 			break;
@@ -5163,7 +5170,7 @@ static struct mlxsw_sp_fib6_entry *
 mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
 			      const struct fib6_info *nrt, bool replace)
 {
-	struct mlxsw_sp_fib6_entry *fib6_entry;
+	struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL;
 
 	list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
 		struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
@@ -5172,13 +5179,18 @@ mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
 			continue;
 		if (rt->fib6_table->tb6_id != nrt->fib6_table->tb6_id)
 			break;
-		if (replace && rt->fib6_metric == nrt->fib6_metric)
-			return fib6_entry;
+		if (replace && rt->fib6_metric == nrt->fib6_metric) {
+			if (mlxsw_sp_fib6_rt_can_mp(rt) ==
+			    mlxsw_sp_fib6_rt_can_mp(nrt))
+				return fib6_entry;
+			if (mlxsw_sp_fib6_rt_can_mp(nrt))
+				fallback = fallback ?: fib6_entry;
+		}
 		if (rt->fib6_metric > nrt->fib6_metric)
-			return fib6_entry;
+			return fallback ?: fib6_entry;
 	}
 
-	return NULL;
+	return fallback;
 }
 
 static int
@@ -5304,8 +5316,7 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
-				    struct fib6_info *rt, bool replace,
-				    bool append)
+				    struct fib6_info *rt, bool replace)
 {
 	struct mlxsw_sp_fib6_entry *fib6_entry;
 	struct mlxsw_sp_fib_node *fib_node;
@@ -5331,7 +5342,7 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
 	/* Before creating a new entry, try to append route to an existing
 	 * multipath entry.
 	 */
-	fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, append);
+	fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, replace);
 	if (fib6_entry) {
 		err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt);
 		if (err)
@@ -5339,14 +5350,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 	}
 
-	/* We received an append event, yet did not find any route to
-	 * append to.
-	 */
-	if (WARN_ON(append)) {
-		err = -EINVAL;
-		goto err_fib6_entry_append;
-	}
-
 	fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt);
 	if (IS_ERR(fib6_entry)) {
 		err = PTR_ERR(fib6_entry);
@@ -5364,7 +5367,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
 err_fib6_node_entry_link:
 	mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry);
 err_fib6_entry_create:
-err_fib6_entry_append:
 err_fib6_entry_nexthop_add:
 	mlxsw_sp_fib_node_put(mlxsw_sp, fib_node);
 	return err;
@@ -5715,7 +5717,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
 	struct mlxsw_sp_fib_event_work *fib_work =
 		container_of(work, struct mlxsw_sp_fib_event_work, work);
 	struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
-	bool replace, append;
+	bool replace;
 	int err;
 
 	rtnl_lock();
@@ -5726,10 +5728,8 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
 	case FIB_EVENT_ENTRY_APPEND: /* fall through */
 	case FIB_EVENT_ENTRY_ADD:
 		replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
-		append = fib_work->event == FIB_EVENT_ENTRY_APPEND;
 		err = mlxsw_sp_router_fib6_add(mlxsw_sp,
-					       fib_work->fen6_info.rt, replace,
-					       append);
+					       fib_work->fen6_info.rt, replace);
 		if (err)
 			mlxsw_sp_router_fib_abort(mlxsw_sp);
 		mlxsw_sp_rt6_release(fib_work->fen6_info.rt);
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index fb2c8f8071e6..776a8a9be8e3 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -344,10 +344,9 @@ static int ocelot_port_stop(struct net_device *dev)
 static int ocelot_gen_ifh(u32 *ifh, struct frame_info *info)
 {
 	ifh[0] = IFH_INJ_BYPASS;
-	ifh[1] = (0xff00 & info->port) >> 8;
+	ifh[1] = (0xf00 & info->port) >> 8;
 	ifh[2] = (0xff & info->port) << 24;
-	ifh[3] = IFH_INJ_POP_CNT_DISABLE | (info->cpuq << 20) |
-		 (info->tag_type << 16) | info->vid;
+	ifh[3] = (info->tag_type << 16) | info->vid;
 
 	return 0;
 }
@@ -370,11 +369,13 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev)
 			 QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);
 
 	info.port = BIT(port->chip_port);
-	info.cpuq = 0xff;
+	info.tag_type = IFH_TAG_TYPE_C;
+	info.vid = skb_vlan_tag_get(skb);
 	ocelot_gen_ifh(ifh, &info);
 
 	for (i = 0; i < IFH_LEN; i++)
-		ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp);
+		ocelot_write_rix(ocelot, (__force u32)cpu_to_be32(ifh[i]),
+				 QS_INJ_WR, grp);
 
 	count = (skb->len + 3) / 4;
 	last = skb->len % 4;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index fcdfb8e7fdea..40216d56dddc 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -81,10 +81,10 @@ nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn,
 
 	ret = nfp_net_bpf_offload(nn, prog, running, extack);
 	/* Stop offload if replace not possible */
-	if (ret && prog)
-		nfp_bpf_xdp_offload(app, nn, NULL, extack);
+	if (ret)
+		return ret;
 
-	nn->dp.bpf_offload_xdp = prog && !ret;
+	nn->dp.bpf_offload_xdp = !!prog;
 	return ret;
 }
 
@@ -202,6 +202,9 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	if (tcf_block_shared(f->block))
+		return -EOPNOTSUPP;
+
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 1decf3a1cad3..e57d23746585 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -80,7 +80,7 @@ nfp_flower_repr_get_type_and_port(struct nfp_app *app, u32 port_id, u8 *port)
 			return NFP_REPR_TYPE_VF;
 	}
 
-	return NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC;
+	return __NFP_REPR_TYPE_MAX;
 }
 
 static struct net_device *
@@ -91,6 +91,8 @@ nfp_flower_repr_get(struct nfp_app *app, u32 port_id)
 	u8 port = 0;
 
 	repr_type = nfp_flower_repr_get_type_and_port(app, port_id, &port);
+	if (repr_type > NFP_REPR_TYPE_MAX)
+		return NULL;
 
 	reprs = rcu_dereference(app->reprs[repr_type]);
 	if (!reprs)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index 91935405f586..84f7a5dbea9d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -123,6 +123,20 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame,
 			 NFP_FLOWER_MASK_MPLS_Q;
 
 		frame->mpls_lse = cpu_to_be32(t_mpls);
+	} else if (dissector_uses_key(flow->dissector,
+				      FLOW_DISSECTOR_KEY_BASIC)) {
+		/* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q
+		 * bit, which indicates an mpls ether type but without any
+		 * mpls fields.
+		 */
+		struct flow_dissector_key_basic *key_basic;
+
+		key_basic = skb_flow_dissector_target(flow->dissector,
+						      FLOW_DISSECTOR_KEY_BASIC,
+						      flow->key);
+		if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
+		    key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC))
+			frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
 	}
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index c42e64f32333..525057bee0ed 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -264,6 +264,14 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		case cpu_to_be16(ETH_P_ARP):
 			return -EOPNOTSUPP;
 
+		case cpu_to_be16(ETH_P_MPLS_UC):
+		case cpu_to_be16(ETH_P_MPLS_MC):
+			if (!(key_layer & NFP_FLOWER_LAYER_MAC)) {
+				key_layer |= NFP_FLOWER_LAYER_MAC;
+				key_size += sizeof(struct nfp_flower_mac_mpls);
+			}
+			break;
+
 		/* Will be included in layer 2. */
 		case cpu_to_be16(ETH_P_8021Q):
 			break;
@@ -623,6 +631,9 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	if (tcf_block_shared(f->block))
+		return -EOPNOTSUPP;
+
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 78afe75129ab..382bb93cb090 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -317,7 +317,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app,
 	payload.dst_ipv4 = flow->daddr;
 
 	/* If entry has expired send dst IP with all other fields 0. */
-	if (!(neigh->nud_state & NUD_VALID)) {
+	if (!(neigh->nud_state & NUD_VALID) || neigh->dead) {
 		nfp_tun_del_route_from_cache(app, payload.dst_ipv4);
 		/* Trigger ARP to verify invalid neighbour state. */
 		neigh_event_send(neigh, NULL);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index 46b76d5a726c..152283d7e59c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -240,7 +240,6 @@ static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf)
 		return pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs);
 
 	pf->limit_vfs = ~0;
-	pci_sriov_set_totalvfs(pf->pdev, 0); /* 0 is unset */
 	/* Allow any setting for backwards compatibility if symbol not found */
 	if (err == -ENOENT)
 		return 0;
@@ -668,7 +667,7 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 
 	err = nfp_net_pci_probe(pf);
 	if (err)
-		goto err_sriov_unlimit;
+		goto err_fw_unload;
 
 	err = nfp_hwmon_register(pf);
 	if (err) {
@@ -680,8 +679,6 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 
 err_net_remove:
 	nfp_net_pci_remove(pf);
-err_sriov_unlimit:
-	pci_sriov_set_totalvfs(pf->pdev, 0);
 err_fw_unload:
 	kfree(pf->rtbl);
 	nfp_mip_close(pf->mip);
@@ -715,7 +712,6 @@ static void nfp_pci_remove(struct pci_dev *pdev)
 	nfp_hwmon_unregister(pf);
 
 	nfp_pcie_sriov_disable(pdev);
-	pci_sriov_set_totalvfs(pf->pdev, 0);
 
 	nfp_net_pci_remove(pf);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
index cd34097b79f1..37a6d7822a38 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
@@ -232,7 +232,7 @@ struct nfp_nffw_info *nfp_nffw_info_open(struct nfp_cpp *cpp)
 	err = nfp_cpp_read(cpp, nfp_resource_cpp_id(state->res),
 			   nfp_resource_address(state->res),
 			   fwinf, sizeof(*fwinf));
-	if (err < sizeof(*fwinf))
+	if (err < (int)sizeof(*fwinf))
 		goto err_release;
 
 	if (!nffw_res_flg_init_get(fwinf))
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 00db3401b898..1dfaccd151f0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -502,6 +502,7 @@ enum BAR_ID {
 struct qed_nvm_image_info {
 	u32 num_images;
 	struct bist_nvm_image_att *image_att;
+	bool valid;
 };
 
 #define DRV_MODULE_VERSION		      \
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index f0b01385d5cb..e0680ce91328 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -709,9 +709,9 @@ qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn,
 	p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE];
 
 	memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id,
-	       ARRAY_SIZE(p_local->local_chassis_id));
+	       sizeof(p_local->local_chassis_id));
 	memcpy(params->lldp_local.local_port_id, p_local->local_port_id,
-	       ARRAY_SIZE(p_local->local_port_id));
+	       sizeof(p_local->local_port_id));
 }
 
 static void
@@ -723,9 +723,9 @@ qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn,
 	p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE];
 
 	memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id,
-	       ARRAY_SIZE(p_remote->peer_chassis_id));
+	       sizeof(p_remote->peer_chassis_id));
 	memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id,
-	       ARRAY_SIZE(p_remote->peer_port_id));
+	       sizeof(p_remote->peer_port_id));
 }
 
 static int
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index a14e48489029..4340c4c90bcb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -6723,7 +6723,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf,
 		format_idx = header & MFW_TRACE_EVENTID_MASK;
 
 		/* Skip message if its index doesn't exist in the meta data */
-		if (format_idx > s_mcp_trace_meta.formats_num) {
+		if (format_idx >= s_mcp_trace_meta.formats_num) {
 			u8 format_size =
 				(u8)((header & MFW_TRACE_PRM_SIZE_MASK) >>
 				     MFW_TRACE_PRM_SIZE_SHIFT);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 329781cda77f..e5249b4741d0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1804,7 +1804,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			DP_INFO(p_hwfn, "Failed to update driver state\n");
 
 		rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt,
-					       QED_OV_ESWITCH_VEB);
+					       QED_OV_ESWITCH_NONE);
 		if (rc)
 			DP_INFO(p_hwfn, "Failed to update eswitch mode\n");
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 99973e10b179..5ede6408649d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -665,7 +665,7 @@ qed_sp_update_mcast_bin(struct qed_hwfn *p_hwfn,
 
 	p_ramrod->common.update_approx_mcast_flg = 1;
 	for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) {
-		u32 *p_bins = (u32 *)p_params->bins;
+		u32 *p_bins = p_params->bins;
 
 		p_ramrod->approx_mcast.bins[i] = cpu_to_le32(p_bins[i]);
 	}
@@ -1476,8 +1476,8 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn,
 			enum spq_mode comp_mode,
 			struct qed_spq_comp_cb *p_comp_data)
 {
-	unsigned long bins[ETH_MULTICAST_MAC_BINS_IN_REGS];
 	struct vport_update_ramrod_data *p_ramrod = NULL;
+	u32 bins[ETH_MULTICAST_MAC_BINS_IN_REGS];
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
 	u8 abs_vport_id = 0;
@@ -1513,26 +1513,25 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn,
 	/* explicitly clear out the entire vector */
 	memset(&p_ramrod->approx_mcast.bins, 0,
 	       sizeof(p_ramrod->approx_mcast.bins));
-	memset(bins, 0, sizeof(unsigned long) *
-	       ETH_MULTICAST_MAC_BINS_IN_REGS);
+	memset(bins, 0, sizeof(bins));
 	/* filter ADD op is explicit set op and it removes
 	 *  any existing filters for the vport
 	 */
 	if (p_filter_cmd->opcode == QED_FILTER_ADD) {
 		for (i = 0; i < p_filter_cmd->num_mc_addrs; i++) {
-			u32 bit;
+			u32 bit, nbits;
 
 			bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]);
-			__set_bit(bit, bins);
+			nbits = sizeof(u32) * BITS_PER_BYTE;
+			bins[bit / nbits] |= 1 << (bit % nbits);
 		}
 
 		/* Convert to correct endianity */
 		for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) {
 			struct vport_update_ramrod_mcast *p_ramrod_bins;
-			u32 *p_bins = (u32 *)bins;
 
 			p_ramrod_bins = &p_ramrod->approx_mcast;
-			p_ramrod_bins->bins[i] = cpu_to_le32(p_bins[i]);
+			p_ramrod_bins->bins[i] = cpu_to_le32(bins[i]);
 		}
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h
index 806a8da257e9..8d80f1095d17 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h
@@ -215,7 +215,7 @@ struct qed_sp_vport_update_params {
 	u8				anti_spoofing_en;
 	u8				update_accept_any_vlan_flg;
 	u8				accept_any_vlan;
-	unsigned long			bins[8];
+	u32				bins[8];
 	struct qed_rss_params		*rss_params;
 	struct qed_filter_accept_flags	accept_flags;
 	struct qed_sge_tpa_params	*sge_tpa_params;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 5c10fd7210c3..758a9a5127fa 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -371,7 +371,7 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev,
 		goto err2;
 	}
 
-	DP_INFO(cdev, "qed_probe completed successffuly\n");
+	DP_INFO(cdev, "qed_probe completed successfully\n");
 
 	return cdev;
 
@@ -789,6 +789,14 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
 	/* We want a minimum of one slowpath and one fastpath vector per hwfn */
 	cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2;
 
+	if (is_kdump_kernel()) {
+		DP_INFO(cdev,
+			"Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n",
+			cdev->int_params.in.min_msix_cnt);
+		cdev->int_params.in.num_vectors =
+			cdev->int_params.in.min_msix_cnt;
+	}
+
 	rc = qed_set_int_mode(cdev, false);
 	if (rc)  {
 		DP_ERR(cdev, "qed_slowpath_setup_int ERR\n");
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 4e0b443c9519..cdd645024a32 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -592,6 +592,9 @@ int qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn,
 	*o_mcp_resp = mb_params.mcp_resp;
 	*o_mcp_param = mb_params.mcp_param;
 
+	/* nvm_info needs to be updated */
+	p_hwfn->nvm_info.valid = false;
+
 	return 0;
 }
 
@@ -1208,6 +1211,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn,
 		break;
 	default:
 		p_link->speed = 0;
+		p_link->link_up = 0;
 	}
 
 	if (p_link->link_up && p_link->speed)
@@ -1305,9 +1309,15 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 	phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
 	phy_cfg.adv_speed = params->speed.advertised_speeds;
 	phy_cfg.loopback_mode = params->loopback_mode;
-	if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) {
-		if (params->eee.enable)
-			phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED;
+
+	/* There are MFWs that share this capability regardless of whether
+	 * this is feasible or not. And given that at the very least adv_caps
+	 * would be set internally by qed, we want to make sure LFA would
+	 * still work.
+	 */
+	if ((p_hwfn->mcp_info->capabilities &
+	     FW_MB_PARAM_FEATURE_SUPPORT_EEE) && params->eee.enable) {
+		phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED;
 		if (params->eee.tx_lpi_enable)
 			phy_cfg.eee_cfg |= EEE_CFG_TX_LPI;
 		if (params->eee.adv_caps & QED_EEE_1G_ADV)
@@ -2555,11 +2565,14 @@ int qed_mcp_bist_nvm_get_image_att(struct qed_hwfn *p_hwfn,
 
 int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
 {
-	struct qed_nvm_image_info *nvm_info = &p_hwfn->nvm_info;
+	struct qed_nvm_image_info nvm_info;
 	struct qed_ptt *p_ptt;
 	int rc;
 	u32 i;
 
+	if (p_hwfn->nvm_info.valid)
+		return 0;
+
 	p_ptt = qed_ptt_acquire(p_hwfn);
 	if (!p_ptt) {
 		DP_ERR(p_hwfn, "failed to acquire ptt\n");
@@ -2567,29 +2580,29 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
 	}
 
 	/* Acquire from MFW the amount of available images */
-	nvm_info->num_images = 0;
+	nvm_info.num_images = 0;
 	rc = qed_mcp_bist_nvm_get_num_images(p_hwfn,
-					     p_ptt, &nvm_info->num_images);
+					     p_ptt, &nvm_info.num_images);
 	if (rc == -EOPNOTSUPP) {
 		DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n");
 		goto out;
-	} else if (rc || !nvm_info->num_images) {
+	} else if (rc || !nvm_info.num_images) {
 		DP_ERR(p_hwfn, "Failed getting number of images\n");
 		goto err0;
 	}
 
-	nvm_info->image_att = kmalloc_array(nvm_info->num_images,
-					    sizeof(struct bist_nvm_image_att),
-					    GFP_KERNEL);
-	if (!nvm_info->image_att) {
+	nvm_info.image_att = kmalloc_array(nvm_info.num_images,
+					   sizeof(struct bist_nvm_image_att),
+					   GFP_KERNEL);
+	if (!nvm_info.image_att) {
 		rc = -ENOMEM;
 		goto err0;
 	}
 
 	/* Iterate over images and get their attributes */
-	for (i = 0; i < nvm_info->num_images; i++) {
+	for (i = 0; i < nvm_info.num_images; i++) {
 		rc = qed_mcp_bist_nvm_get_image_att(p_hwfn, p_ptt,
-						    &nvm_info->image_att[i], i);
+						    &nvm_info.image_att[i], i);
 		if (rc) {
 			DP_ERR(p_hwfn,
 			       "Failed getting image index %d attributes\n", i);
@@ -2597,14 +2610,22 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
 		}
 
 		DP_VERBOSE(p_hwfn, QED_MSG_SP, "image index %d, size %x\n", i,
-			   nvm_info->image_att[i].len);
+			   nvm_info.image_att[i].len);
 	}
 out:
+	/* Update hwfn's nvm_info */
+	if (nvm_info.num_images) {
+		p_hwfn->nvm_info.num_images = nvm_info.num_images;
+		kfree(p_hwfn->nvm_info.image_att);
+		p_hwfn->nvm_info.image_att = nvm_info.image_att;
+		p_hwfn->nvm_info.valid = true;
+	}
+
 	qed_ptt_release(p_hwfn, p_ptt);
 	return 0;
 
 err1:
-	kfree(nvm_info->image_att);
+	kfree(nvm_info.image_att);
 err0:
 	qed_ptt_release(p_hwfn, p_ptt);
 	return rc;
@@ -2641,6 +2662,7 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn,
 		return -EINVAL;
 	}
 
+	qed_mcp_nvm_info_populate(p_hwfn);
 	for (i = 0; i < p_hwfn->nvm_info.num_images; i++)
 		if (type == p_hwfn->nvm_info.image_att[i].image_type)
 			break;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index f01bf52bc381..26e918d7f2f9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -2831,7 +2831,7 @@ qed_iov_vp_update_mcast_bin_param(struct qed_hwfn *p_hwfn,
 
 	p_data->update_approx_mcast_flg = 1;
 	memcpy(p_data->bins, p_mcast_tlv->bins,
-	       sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS);
+	       sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS);
 	*tlvs_mask |= 1 << QED_IOV_VP_UPDATE_MCAST;
 }
 
@@ -4513,6 +4513,8 @@ static void qed_sriov_enable_qid_config(struct qed_hwfn *hwfn,
 static int qed_sriov_enable(struct qed_dev *cdev, int num)
 {
 	struct qed_iov_vf_init_params params;
+	struct qed_hwfn *hwfn;
+	struct qed_ptt *ptt;
 	int i, j, rc;
 
 	if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) {
@@ -4525,8 +4527,8 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
 
 	/* Initialize HW for VF access */
 	for_each_hwfn(cdev, j) {
-		struct qed_hwfn *hwfn = &cdev->hwfns[j];
-		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
+		hwfn = &cdev->hwfns[j];
+		ptt = qed_ptt_acquire(hwfn);
 
 		/* Make sure not to use more than 16 queues per VF */
 		params.num_queues = min_t(int,
@@ -4562,6 +4564,19 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
 		goto err;
 	}
 
+	hwfn = QED_LEADING_HWFN(cdev);
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt) {
+		DP_ERR(hwfn, "Failed to acquire ptt\n");
+		rc = -EBUSY;
+		goto err;
+	}
+
+	rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB);
+	if (rc)
+		DP_INFO(cdev, "Failed to update eswitch mode\n");
+	qed_ptt_release(hwfn, ptt);
+
 	return num;
 
 err:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 2d7fcd6a0777..be6ddde1a104 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -1126,7 +1126,7 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 		resp_size += sizeof(struct pfvf_def_resp_tlv);
 
 		memcpy(p_mcast_tlv->bins, p_params->bins,
-		       sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS);
+		       sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS);
 	}
 
 	update_rx = p_params->accept_flags.update_rx_mode_config;
@@ -1272,7 +1272,7 @@ void qed_vf_pf_filter_mcast(struct qed_hwfn *p_hwfn,
 			u32 bit;
 
 			bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]);
-			__set_bit(bit, sp_params.bins);
+			sp_params.bins[bit / 32] |= 1 << (bit % 32);
 		}
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h
index 4f05d5eb3cf5..033409db86ae 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h
@@ -392,7 +392,12 @@ struct vfpf_vport_update_mcast_bin_tlv {
 	struct channel_tlv tl;
 	u8 padding[4];
 
-	u64 bins[8];
+	/* There are only 256 approx bins, and in HSI they're divided into
+	 * 32-bit values. As old VFs used to set-bit to the values on its side,
+	 * the upper half of the array is never expected to contain any data.
+	 */
+	u64 bins[4];
+	u64 obsolete_bins[4];
 };
 
 struct vfpf_vport_update_accept_param_tlv {
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 02adb513f475..013ff567283c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -337,8 +337,14 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info)
 {
 	struct qede_ptp *ptp = edev->ptp;
 
-	if (!ptp)
-		return -EIO;
+	if (!ptp) {
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+					SOF_TIMESTAMPING_RX_SOFTWARE |
+					SOF_TIMESTAMPING_SOFTWARE;
+		info->phc_index = -1;
+
+		return 0;
+	}
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
 				SOF_TIMESTAMPING_RX_SOFTWARE |
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
index 891f03a7a33d..8d7b9bb910f2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
@@ -1128,6 +1128,8 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp,
 	struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
 
 	ret = kstrtoul(buf, 16, &data);
+	if (ret)
+		return ret;
 
 	switch (data) {
 	case QLC_83XX_FLASH_SECTOR_ERASE_CMD:
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 5803cd6db406..206f0266463e 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -658,7 +658,7 @@ qcaspi_netdev_open(struct net_device *dev)
 		return ret;
 	}
 
-	netif_start_queue(qca->net_dev);
+	/* SPI thread takes care of TX queue */
 
 	return 0;
 }
@@ -760,6 +760,9 @@ qcaspi_netdev_tx_timeout(struct net_device *dev)
 	qca->net_dev->stats.tx_errors++;
 	/* Trigger tx queue flush and QCA7000 reset */
 	qca->sync = QCASPI_SYNC_UNKNOWN;
+
+	if (qca->spi_thread)
+		wake_up_process(qca->spi_thread);
 }
 
 static int
@@ -878,22 +881,22 @@ qca_spi_probe(struct spi_device *spi)
 
 	if ((qcaspi_clkspeed < QCASPI_CLK_SPEED_MIN) ||
 	    (qcaspi_clkspeed > QCASPI_CLK_SPEED_MAX)) {
-		dev_info(&spi->dev, "Invalid clkspeed: %d\n",
-			 qcaspi_clkspeed);
+		dev_err(&spi->dev, "Invalid clkspeed: %d\n",
+			qcaspi_clkspeed);
 		return -EINVAL;
 	}
 
 	if ((qcaspi_burst_len < QCASPI_BURST_LEN_MIN) ||
 	    (qcaspi_burst_len > QCASPI_BURST_LEN_MAX)) {
-		dev_info(&spi->dev, "Invalid burst len: %d\n",
-			 qcaspi_burst_len);
+		dev_err(&spi->dev, "Invalid burst len: %d\n",
+			qcaspi_burst_len);
 		return -EINVAL;
 	}
 
 	if ((qcaspi_pluggable < QCASPI_PLUGGABLE_MIN) ||
 	    (qcaspi_pluggable > QCASPI_PLUGGABLE_MAX)) {
-		dev_info(&spi->dev, "Invalid pluggable: %d\n",
-			 qcaspi_pluggable);
+		dev_err(&spi->dev, "Invalid pluggable: %d\n",
+			qcaspi_pluggable);
 		return -EINVAL;
 	}
 
@@ -955,8 +958,8 @@ qca_spi_probe(struct spi_device *spi)
 	}
 
 	if (register_netdev(qcaspi_devs)) {
-		dev_info(&spi->dev, "Unable to register net device %s\n",
-			 qcaspi_devs->name);
+		dev_err(&spi->dev, "Unable to register net device %s\n",
+			qcaspi_devs->name);
 		free_netdev(qcaspi_devs);
 		return -EFAULT;
 	}
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 75dfac0248f4..eaedc11ed686 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7148,7 +7148,7 @@ static void rtl8169_netpoll(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	rtl8169_interrupt(pci_irq_vector(tp->pci_dev, 0), dev);
+	rtl8169_interrupt(pci_irq_vector(tp->pci_dev, 0), tp);
 }
 #endif
 
@@ -7734,8 +7734,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return rc;
 	}
 
-	/* override BIOS settings, use userspace tools to enable WOL */
-	__rtl8169_set_wol(tp, 0);
+	tp->saved_wolopts = __rtl8169_get_wol(tp);
 
 	if (rtl_tbi_enabled(tp)) {
 		tp->set_speed = rtl8169_set_speed_tbi;
@@ -7789,6 +7788,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		NETIF_F_HW_VLAN_CTAG_RX;
 	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
 		NETIF_F_HIGHDMA;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	tp->cp_cmd |= RxChkSum | RxVlan;
 
diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig
index 27be51f0a421..f3f7477043ce 100644
--- a/drivers/net/ethernet/renesas/Kconfig
+++ b/drivers/net/ethernet/renesas/Kconfig
@@ -17,7 +17,6 @@ if NET_VENDOR_RENESAS
 
 config SH_ETH
 	tristate "Renesas SuperH Ethernet support"
-	depends on HAS_DMA
 	depends on ARCH_RENESAS || SUPERH || COMPILE_TEST
 	select CRC32
 	select MII
@@ -31,7 +30,6 @@ config SH_ETH
 
 config RAVB
 	tristate "Renesas Ethernet AVB support"
-	depends on HAS_DMA
 	depends on ARCH_RENESAS || COMPILE_TEST
 	select CRC32
 	select MII
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 68f122140966..0d811c02ff34 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -980,6 +980,13 @@ static void ravb_adjust_link(struct net_device *ndev)
 	struct ravb_private *priv = netdev_priv(ndev);
 	struct phy_device *phydev = ndev->phydev;
 	bool new_state = false;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	/* Disable TX and RX right over here, if E-MAC change is ignored */
+	if (priv->no_avb_link)
+		ravb_rcv_snd_disable(ndev);
 
 	if (phydev->link) {
 		if (phydev->duplex != priv->duplex) {
@@ -997,18 +1004,21 @@ static void ravb_adjust_link(struct net_device *ndev)
 			ravb_modify(ndev, ECMR, ECMR_TXF, 0);
 			new_state = true;
 			priv->link = phydev->link;
-			if (priv->no_avb_link)
-				ravb_rcv_snd_enable(ndev);
 		}
 	} else if (priv->link) {
 		new_state = true;
 		priv->link = 0;
 		priv->speed = 0;
 		priv->duplex = -1;
-		if (priv->no_avb_link)
-			ravb_rcv_snd_disable(ndev);
 	}
 
+	/* Enable TX and RX right over here, if E-MAC change is ignored */
+	if (priv->no_avb_link && phydev->link)
+		ravb_rcv_snd_enable(ndev);
+
+	mmiowb();
+	spin_unlock_irqrestore(&priv->lock, flags);
+
 	if (new_state && netif_msg_link(priv))
 		phy_print_status(phydev);
 }
@@ -1096,75 +1106,6 @@ static int ravb_phy_start(struct net_device *ndev)
 	return 0;
 }
 
-static int ravb_get_link_ksettings(struct net_device *ndev,
-				   struct ethtool_link_ksettings *cmd)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-	unsigned long flags;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&priv->lock, flags);
-	phy_ethtool_ksettings_get(ndev->phydev, cmd);
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	return 0;
-}
-
-static int ravb_set_link_ksettings(struct net_device *ndev,
-				   const struct ethtool_link_ksettings *cmd)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-	unsigned long flags;
-	int error;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&priv->lock, flags);
-
-	/* Disable TX and RX */
-	ravb_rcv_snd_disable(ndev);
-
-	error = phy_ethtool_ksettings_set(ndev->phydev, cmd);
-	if (error)
-		goto error_exit;
-
-	if (cmd->base.duplex == DUPLEX_FULL)
-		priv->duplex = 1;
-	else
-		priv->duplex = 0;
-
-	ravb_set_duplex(ndev);
-
-error_exit:
-	mdelay(1);
-
-	/* Enable TX and RX */
-	ravb_rcv_snd_enable(ndev);
-
-	mmiowb();
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	return error;
-}
-
-static int ravb_nway_reset(struct net_device *ndev)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-	int error = -ENODEV;
-	unsigned long flags;
-
-	if (ndev->phydev) {
-		spin_lock_irqsave(&priv->lock, flags);
-		error = phy_start_aneg(ndev->phydev);
-		spin_unlock_irqrestore(&priv->lock, flags);
-	}
-
-	return error;
-}
-
 static u32 ravb_get_msglevel(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
@@ -1377,7 +1318,7 @@ static int ravb_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
 }
 
 static const struct ethtool_ops ravb_ethtool_ops = {
-	.nway_reset		= ravb_nway_reset,
+	.nway_reset		= phy_ethtool_nway_reset,
 	.get_msglevel		= ravb_get_msglevel,
 	.set_msglevel		= ravb_set_msglevel,
 	.get_link		= ethtool_op_get_link,
@@ -1387,8 +1328,8 @@ static const struct ethtool_ops ravb_ethtool_ops = {
 	.get_ringparam		= ravb_get_ringparam,
 	.set_ringparam		= ravb_set_ringparam,
 	.get_ts_info		= ravb_get_ts_info,
-	.get_link_ksettings	= ravb_get_link_ksettings,
-	.set_link_ksettings	= ravb_set_link_ksettings,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 	.get_wol		= ravb_get_wol,
 	.set_wol		= ravb_set_wol,
 };
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index e9007b613f17..5614fd231bbe 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1927,8 +1927,15 @@ static void sh_eth_adjust_link(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
 	struct phy_device *phydev = ndev->phydev;
+	unsigned long flags;
 	int new_state = 0;
 
+	spin_lock_irqsave(&mdp->lock, flags);
+
+	/* Disable TX and RX right over here, if E-MAC change is ignored */
+	if (mdp->cd->no_psr || mdp->no_ether_link)
+		sh_eth_rcv_snd_disable(ndev);
+
 	if (phydev->link) {
 		if (phydev->duplex != mdp->duplex) {
 			new_state = 1;
@@ -1947,18 +1954,21 @@ static void sh_eth_adjust_link(struct net_device *ndev)
 			sh_eth_modify(ndev, ECMR, ECMR_TXF, 0);
 			new_state = 1;
 			mdp->link = phydev->link;
-			if (mdp->cd->no_psr || mdp->no_ether_link)
-				sh_eth_rcv_snd_enable(ndev);
 		}
 	} else if (mdp->link) {
 		new_state = 1;
 		mdp->link = 0;
 		mdp->speed = 0;
 		mdp->duplex = -1;
-		if (mdp->cd->no_psr || mdp->no_ether_link)
-			sh_eth_rcv_snd_disable(ndev);
 	}
 
+	/* Enable TX and RX right over here, if E-MAC change is ignored */
+	if ((mdp->cd->no_psr || mdp->no_ether_link) && phydev->link)
+		sh_eth_rcv_snd_enable(ndev);
+
+	mmiowb();
+	spin_unlock_irqrestore(&mdp->lock, flags);
+
 	if (new_state && netif_msg_link(mdp))
 		phy_print_status(phydev);
 }
@@ -2030,60 +2040,6 @@ static int sh_eth_phy_start(struct net_device *ndev)
 	return 0;
 }
 
-static int sh_eth_get_link_ksettings(struct net_device *ndev,
-				     struct ethtool_link_ksettings *cmd)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	unsigned long flags;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&mdp->lock, flags);
-	phy_ethtool_ksettings_get(ndev->phydev, cmd);
-	spin_unlock_irqrestore(&mdp->lock, flags);
-
-	return 0;
-}
-
-static int sh_eth_set_link_ksettings(struct net_device *ndev,
-				     const struct ethtool_link_ksettings *cmd)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	unsigned long flags;
-	int ret;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&mdp->lock, flags);
-
-	/* disable tx and rx */
-	sh_eth_rcv_snd_disable(ndev);
-
-	ret = phy_ethtool_ksettings_set(ndev->phydev, cmd);
-	if (ret)
-		goto error_exit;
-
-	if (cmd->base.duplex == DUPLEX_FULL)
-		mdp->duplex = 1;
-	else
-		mdp->duplex = 0;
-
-	if (mdp->cd->set_duplex)
-		mdp->cd->set_duplex(ndev);
-
-error_exit:
-	mdelay(1);
-
-	/* enable tx and rx */
-	sh_eth_rcv_snd_enable(ndev);
-
-	spin_unlock_irqrestore(&mdp->lock, flags);
-
-	return ret;
-}
-
 /* If it is ever necessary to increase SH_ETH_REG_DUMP_MAX_REGS, the
  * version must be bumped as well.  Just adding registers up to that
  * limit is fine, as long as the existing register indices don't
@@ -2263,22 +2219,6 @@ static void sh_eth_get_regs(struct net_device *ndev, struct ethtool_regs *regs,
 	pm_runtime_put_sync(&mdp->pdev->dev);
 }
 
-static int sh_eth_nway_reset(struct net_device *ndev)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	unsigned long flags;
-	int ret;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&mdp->lock, flags);
-	ret = phy_start_aneg(ndev->phydev);
-	spin_unlock_irqrestore(&mdp->lock, flags);
-
-	return ret;
-}
-
 static u32 sh_eth_get_msglevel(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
@@ -2429,7 +2369,7 @@ static int sh_eth_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
 static const struct ethtool_ops sh_eth_ethtool_ops = {
 	.get_regs_len	= sh_eth_get_regs_len,
 	.get_regs	= sh_eth_get_regs,
-	.nway_reset	= sh_eth_nway_reset,
+	.nway_reset	= phy_ethtool_nway_reset,
 	.get_msglevel	= sh_eth_get_msglevel,
 	.set_msglevel	= sh_eth_set_msglevel,
 	.get_link	= ethtool_op_get_link,
@@ -2438,8 +2378,8 @@ static const struct ethtool_ops sh_eth_ethtool_ops = {
 	.get_sset_count     = sh_eth_get_sset_count,
 	.get_ringparam	= sh_eth_get_ringparam,
 	.set_ringparam	= sh_eth_set_ringparam,
-	.get_link_ksettings = sh_eth_get_link_ksettings,
-	.set_link_ksettings = sh_eth_set_link_ksettings,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 	.get_wol	= sh_eth_get_wol,
 	.set_wol	= sh_eth_set_wol,
 };
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 23f0785c0573..7eeac3d6cfe8 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -4288,9 +4288,9 @@ static int efx_ef10_filter_pri(struct efx_ef10_filter_table *table,
 	return -EPROTONOSUPPORT;
 }
 
-static s32 efx_ef10_filter_insert(struct efx_nic *efx,
-				  struct efx_filter_spec *spec,
-				  bool replace_equal)
+static s32 efx_ef10_filter_insert_locked(struct efx_nic *efx,
+					 struct efx_filter_spec *spec,
+					 bool replace_equal)
 {
 	DECLARE_BITMAP(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
@@ -4307,7 +4307,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
 	bool is_mc_recip;
 	s32 rc;
 
-	down_read(&efx->filter_sem);
+	WARN_ON(!rwsem_is_locked(&efx->filter_sem));
 	table = efx->filter_state;
 	down_write(&table->lock);
 
@@ -4498,10 +4498,22 @@ out_unlock:
 	if (rss_locked)
 		mutex_unlock(&efx->rss_lock);
 	up_write(&table->lock);
-	up_read(&efx->filter_sem);
 	return rc;
 }
 
+static s32 efx_ef10_filter_insert(struct efx_nic *efx,
+				  struct efx_filter_spec *spec,
+				  bool replace_equal)
+{
+	s32 ret;
+
+	down_read(&efx->filter_sem);
+	ret = efx_ef10_filter_insert_locked(efx, spec, replace_equal);
+	up_read(&efx->filter_sem);
+
+	return ret;
+}
+
 static void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx)
 {
 	/* no need to do anything here on EF10 */
@@ -5285,7 +5297,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
 		EFX_WARN_ON_PARANOID(ids[i] != EFX_EF10_FILTER_ID_INVALID);
 		efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
 		efx_filter_set_eth_local(&spec, vlan->vid, addr_list[i].addr);
-		rc = efx_ef10_filter_insert(efx, &spec, true);
+		rc = efx_ef10_filter_insert_locked(efx, &spec, true);
 		if (rc < 0) {
 			if (rollback) {
 				netif_info(efx, drv, efx->net_dev,
@@ -5314,7 +5326,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
 		efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
 		eth_broadcast_addr(baddr);
 		efx_filter_set_eth_local(&spec, vlan->vid, baddr);
-		rc = efx_ef10_filter_insert(efx, &spec, true);
+		rc = efx_ef10_filter_insert_locked(efx, &spec, true);
 		if (rc < 0) {
 			netif_warn(efx, drv, efx->net_dev,
 				   "Broadcast filter insert failed rc=%d\n", rc);
@@ -5370,7 +5382,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx,
 	if (vlan->vid != EFX_FILTER_VID_UNSPEC)
 		efx_filter_set_eth_local(&spec, vlan->vid, NULL);
 
-	rc = efx_ef10_filter_insert(efx, &spec, true);
+	rc = efx_ef10_filter_insert_locked(efx, &spec, true);
 	if (rc < 0) {
 		const char *um = multicast ? "Multicast" : "Unicast";
 		const char *encap_name = "";
@@ -5430,7 +5442,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx,
 					   filter_flags, 0);
 			eth_broadcast_addr(baddr);
 			efx_filter_set_eth_local(&spec, vlan->vid, baddr);
-			rc = efx_ef10_filter_insert(efx, &spec, true);
+			rc = efx_ef10_filter_insert_locked(efx, &spec, true);
 			if (rc < 0) {
 				netif_warn(efx, drv, efx->net_dev,
 					   "Broadcast filter insert failed rc=%d\n",
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index ad4a354ce570..ce3a177081a8 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1871,12 +1871,6 @@ static void efx_remove_filters(struct efx_nic *efx)
 	up_write(&efx->filter_sem);
 }
 
-static void efx_restore_filters(struct efx_nic *efx)
-{
-	down_read(&efx->filter_sem);
-	efx->type->filter_table_restore(efx);
-	up_read(&efx->filter_sem);
-}
 
 /**************************************************************************
  *
@@ -2688,6 +2682,7 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method)
 	efx_disable_interrupts(efx);
 
 	mutex_lock(&efx->mac_lock);
+	down_write(&efx->filter_sem);
 	mutex_lock(&efx->rss_lock);
 	if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
 	    method != RESET_TYPE_DATAPATH)
@@ -2745,9 +2740,8 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 	if (efx->type->rx_restore_rss_contexts)
 		efx->type->rx_restore_rss_contexts(efx);
 	mutex_unlock(&efx->rss_lock);
-	down_read(&efx->filter_sem);
-	efx_restore_filters(efx);
-	up_read(&efx->filter_sem);
+	efx->type->filter_table_restore(efx);
+	up_write(&efx->filter_sem);
 	if (efx->type->sriov_reset)
 		efx->type->sriov_reset(efx);
 
@@ -2764,6 +2758,7 @@ fail:
 	efx->port_initialized = false;
 
 	mutex_unlock(&efx->rss_lock);
+	up_write(&efx->filter_sem);
 	mutex_unlock(&efx->mac_lock);
 
 	return rc;
@@ -3180,6 +3175,7 @@ bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
 	return true;
 }
 
+static
 struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
 				       const struct efx_filter_spec *spec)
 {
@@ -3472,7 +3468,9 @@ static int efx_pci_probe_main(struct efx_nic *efx)
 
 	efx_init_napi(efx);
 
+	down_write(&efx->filter_sem);
 	rc = efx->type->init(efx);
+	up_write(&efx->filter_sem);
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
 			  "failed to initialise NIC\n");
@@ -3764,7 +3762,9 @@ static int efx_pm_resume(struct device *dev)
 	rc = efx->type->reset(efx, RESET_TYPE_ALL);
 	if (rc)
 		return rc;
+	down_write(&efx->filter_sem);
 	rc = efx->type->init(efx);
+	up_write(&efx->filter_sem);
 	if (rc)
 		return rc;
 	rc = efx_pm_thaw(dev);
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 8edf20967c82..e045a5d6b938 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -2794,6 +2794,7 @@ int efx_farch_filter_table_probe(struct efx_nic *efx)
 	if (!state)
 		return -ENOMEM;
 	efx->filter_state = state;
+	init_rwsem(&state->lock);
 
 	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
 	table->id = EFX_FARCH_FILTER_TABLE_RX_IP;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 2e6e2a96b4f2..f9a61f90cfbc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -37,7 +37,7 @@
  *		is done in the "stmmac files"
  */
 
-/* struct emac_variant - Descrive dwmac-sun8i hardware variant
+/* struct emac_variant - Describe dwmac-sun8i hardware variant
  * @default_syscon_value:	The default value of the EMAC register in syscon
  *				This value is used for disabling properly EMAC
  *				and used as a good starting value in case of the
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index d37f17ca62fe..65bc3556bd8f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -407,6 +407,16 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
 	}
 }
 
+static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
+{
+	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
+
+	value &= ~DMA_RBSZ_MASK;
+	value |= (bfsize << DMA_RBSZ_SHIFT) & DMA_RBSZ_MASK;
+
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
+}
+
 const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
@@ -431,6 +441,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
 	.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
 	.enable_tso = dwmac4_enable_tso,
+	.set_bfsize = dwmac4_set_bfsize,
 };
 
 const struct stmmac_dma_ops dwmac410_dma_ops = {
@@ -457,4 +468,5 @@ const struct stmmac_dma_ops dwmac410_dma_ops = {
 	.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
 	.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
 	.enable_tso = dwmac4_enable_tso,
+	.set_bfsize = dwmac4_set_bfsize,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index c63c1fe3f26b..22a4a6dbb1a4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -120,6 +120,8 @@
 
 /* DMA Rx Channel X Control register defines */
 #define DMA_CONTROL_SR			BIT(0)
+#define DMA_RBSZ_MASK			GENMASK(14, 1)
+#define DMA_RBSZ_SHIFT			1
 
 /* Interrupt status per channel */
 #define DMA_CHAN_STATUS_REB		GENMASK(21, 19)
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index e44e7b26ce82..fe8b536b13f8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -183,6 +183,7 @@ struct stmmac_dma_ops {
 	void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
+	void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan);
 };
 
 #define stmmac_reset(__priv, __args...) \
@@ -235,6 +236,8 @@ struct stmmac_dma_ops {
 	stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args)
 #define stmmac_enable_tso(__priv, __args...) \
 	stmmac_do_void_callback(__priv, dma, enable_tso, __args)
+#define stmmac_set_dma_bfsize(__priv, __args...) \
+	stmmac_do_void_callback(__priv, dma, set_bfsize, __args)
 
 struct mac_device_info;
 struct net_device;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index cba46b62a1cd..ef6a8d39db2f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -53,7 +53,7 @@
 #include "dwmac1000.h"
 #include "hwif.h"
 
-#define STMMAC_ALIGN(x)	L1_CACHE_ALIGN(x)
+#define	STMMAC_ALIGN(x)		__ALIGN_KERNEL(x, SMP_CACHE_BYTES)
 #define	TSO_MAX_BUFF_SIZE	(SZ_16K - 1)
 
 /* Module parameters */
@@ -1804,6 +1804,8 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 
 		stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan,
 				rxfifosz, qmode);
+		stmmac_set_dma_bfsize(priv, priv->ioaddr, priv->dma_buf_sz,
+				chan);
 	}
 
 	for (chan = 0; chan < tx_channels_count; chan++) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 8d375e51a526..6a393b16a1fc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -257,7 +257,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 		return -ENOMEM;
 
 	/* Enable pci device */
-	ret = pcim_enable_device(pdev);
+	ret = pci_enable_device(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n",
 			__func__);
@@ -300,9 +300,45 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 static void stmmac_pci_remove(struct pci_dev *pdev)
 {
 	stmmac_dvr_remove(&pdev->dev);
+	pci_disable_device(pdev);
 }
 
-static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_suspend, stmmac_resume);
+static int stmmac_pci_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	ret = stmmac_suspend(dev);
+	if (ret)
+		return ret;
+
+	ret = pci_save_state(pdev);
+	if (ret)
+		return ret;
+
+	pci_disable_device(pdev);
+	pci_wake_from_d3(pdev, true);
+	return 0;
+}
+
+static int stmmac_pci_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	pci_restore_state(pdev);
+	pci_set_power_state(pdev, PCI_D0);
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	pci_set_master(pdev);
+
+	return stmmac_resume(dev);
+}
+
+static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume);
 
 /* synthetic ID, no official vendor */
 #define PCI_VENDOR_ID_STMMAC 0x700
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 6d141f3931eb..72da77b94ecd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -94,7 +94,6 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries)
 /**
  * stmmac_axi_setup - parse DT parameters for programming the AXI register
  * @pdev: platform device
- * @priv: driver private struct.
  * Description:
  * if required, from device-tree the AXI internal register can be tuned
  * by using platform parameters.
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 358edab9e72e..3e34cb8ac1d3 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2086,14 +2086,16 @@ static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
 		int i;
 
 		for (i = 0; i < cpsw->data.slaves; i++) {
-			if (vid == cpsw->slaves[i].port_vlan)
-				return -EINVAL;
+			if (vid == cpsw->slaves[i].port_vlan) {
+				ret = -EINVAL;
+				goto err;
+			}
 		}
 	}
 
 	dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid);
 	ret = cpsw_add_vlan_ale_entry(priv, vid);
-
+err:
 	pm_runtime_put(cpsw->dev);
 	return ret;
 }
@@ -2119,22 +2121,17 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
 
 		for (i = 0; i < cpsw->data.slaves; i++) {
 			if (vid == cpsw->slaves[i].port_vlan)
-				return -EINVAL;
+				goto err;
 		}
 	}
 
 	dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid);
 	ret = cpsw_ale_del_vlan(cpsw->ale, vid, 0);
-	if (ret != 0)
-		return ret;
-
-	ret = cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
-				 HOST_PORT_NUM, ALE_VLAN, vid);
-	if (ret != 0)
-		return ret;
-
-	ret = cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
-				 0, ALE_VLAN, vid);
+	ret |= cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
+				  HOST_PORT_NUM, ALE_VLAN, vid);
+	ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
+				  0, ALE_VLAN, vid);
+err:
 	pm_runtime_put(cpsw->dev);
 	return ret;
 }
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 93dc05c194d3..5766225a4ce1 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -394,7 +394,7 @@ int cpsw_ale_del_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask,
 
 	idx = cpsw_ale_match_addr(ale, addr, (flags & ALE_VLAN) ? vid : 0);
 	if (idx < 0)
-		return -EINVAL;
+		return -ENOENT;
 
 	cpsw_ale_read(ale, idx, ale_entry);
 
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index cdbddf16dd29..4f1267477aa4 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -205,7 +205,7 @@ static void cpdma_desc_pool_destroy(struct cpdma_ctlr *ctlr)
  * devices (e.g. cpsw switches) use plain old memory.  Descriptor pools
  * abstract out these details
  */
-int cpdma_desc_pool_create(struct cpdma_ctlr *ctlr)
+static int cpdma_desc_pool_create(struct cpdma_ctlr *ctlr)
 {
 	struct cpdma_params *cpdma_params = &ctlr->params;
 	struct cpdma_desc_pool *pool;
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index a1a6445b5a7e..f270beebb428 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1387,6 +1387,10 @@ static int emac_devioctl(struct net_device *ndev, struct ifreq *ifrq, int cmd)
 
 static int match_first_device(struct device *dev, void *data)
 {
+	if (dev->parent && dev->parent->of_node)
+		return of_device_is_compatible(dev->parent->of_node,
+					       "ti,davinci_mdio");
+
 	return !strncmp(dev_name(dev), "davinci_mdio", 12);
 }
 
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
index 16c3bfbe1992..757a3b37ae8a 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
@@ -218,6 +218,7 @@ issue:
 	ret = of_mdiobus_register(bus, np1);
 	if (ret) {
 		mdiobus_free(bus);
+		lp->mii_bus = NULL;
 		return ret;
 	}
 	return 0;
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 750eaa53bf0c..ada33c2d9ac2 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -476,7 +476,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 1a924b867b07..4b6e308199d2 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -210,7 +210,7 @@ int netvsc_recv_callback(struct net_device *net,
 void netvsc_channel_cb(void *context);
 int netvsc_poll(struct napi_struct *napi, int budget);
 
-void rndis_set_subchannel(struct work_struct *w);
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev);
 int rndis_filter_open(struct netvsc_device *nvdev);
 int rndis_filter_close(struct netvsc_device *nvdev);
 struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 5d5bd513847f..31c3d77b4733 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -65,6 +65,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf)
 			       VM_PKT_DATA_INBAND, 0);
 }
 
+/* Worker to setup sub channels on initial setup
+ * Initial hotplug event occurs in softirq context
+ * and can't wait for channels.
+ */
+static void netvsc_subchan_work(struct work_struct *w)
+{
+	struct netvsc_device *nvdev =
+		container_of(w, struct netvsc_device, subchan_work);
+	struct rndis_device *rdev;
+	int i, ret;
+
+	/* Avoid deadlock with device removal already under RTNL */
+	if (!rtnl_trylock()) {
+		schedule_work(w);
+		return;
+	}
+
+	rdev = nvdev->extension;
+	if (rdev) {
+		ret = rndis_set_subchannel(rdev->ndev, nvdev);
+		if (ret == 0) {
+			netif_device_attach(rdev->ndev);
+		} else {
+			/* fallback to only primary channel */
+			for (i = 1; i < nvdev->num_chn; i++)
+				netif_napi_del(&nvdev->chan_table[i].napi);
+
+			nvdev->max_chn = 1;
+			nvdev->num_chn = 1;
+		}
+	}
+
+	rtnl_unlock();
+}
+
 static struct netvsc_device *alloc_net_device(void)
 {
 	struct netvsc_device *net_device;
@@ -81,7 +116,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_completion(&net_device->channel_init_wait);
 	init_waitqueue_head(&net_device->subchan_open);
-	INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
+	INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);
 
 	return net_device;
 }
@@ -1239,6 +1274,7 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 	struct hv_device *device = netvsc_channel_to_device(channel);
 	struct net_device *ndev = hv_get_drvdata(device);
 	int work_done = 0;
+	int ret;
 
 	/* If starting a new interval */
 	if (!nvchan->desc)
@@ -1250,16 +1286,18 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 		nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
 	}
 
-	/* If send of pending receive completions suceeded
-	 *   and did not exhaust NAPI budget this time
-	 *   and not doing busy poll
+	/* Send any pending receive completions */
+	ret = send_recv_completions(ndev, net_device, nvchan);
+
+	/* If it did not exhaust NAPI budget this time
+	 *  and not doing busy poll
 	 * then re-enable host interrupts
-	 *     and reschedule if ring is not empty.
+	 *  and reschedule if ring is not empty
+	 *   or sending receive completion failed.
 	 */
-	if (send_recv_completions(ndev, net_device, nvchan) == 0 &&
-	    work_done < budget &&
+	if (work_done < budget &&
 	    napi_complete_done(napi, work_done) &&
-	    hv_end_read(&channel->inbound) &&
+	    (ret || hv_end_read(&channel->inbound)) &&
 	    napi_schedule_prep(napi)) {
 		hv_begin_read(&channel->inbound);
 		__napi_schedule(napi);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index fe2256bf1d13..dd1d6e115145 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -905,8 +905,20 @@ static int netvsc_attach(struct net_device *ndev,
 	if (IS_ERR(nvdev))
 		return PTR_ERR(nvdev);
 
-	/* Note: enable and attach happen when sub-channels setup */
+	if (nvdev->num_chn > 1) {
+		ret = rndis_set_subchannel(ndev, nvdev);
+
+		/* if unavailable, just proceed with one queue */
+		if (ret) {
+			nvdev->max_chn = 1;
+			nvdev->num_chn = 1;
+		}
+	}
+
+	/* In any case device is now ready */
+	netif_device_attach(ndev);
 
+	/* Note: enable and attach happen when sub-channels setup */
 	netif_carrier_off(ndev);
 
 	if (netif_running(ndev)) {
@@ -2089,6 +2101,9 @@ static int netvsc_probe(struct hv_device *dev,
 
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
+	if (nvdev->num_chn > 1)
+		schedule_work(&nvdev->subchan_work);
+
 	/* hw_features computed in rndis_netdev_set_hwcaps() */
 	net->features = net->hw_features |
 		NETIF_F_HIGHDMA | NETIF_F_SG |
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 5428bb261102..408ece27131c 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1062,29 +1062,15 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
  * This breaks overlap of processing the host message for the
  * new primary channel with the initialization of sub-channels.
  */
-void rndis_set_subchannel(struct work_struct *w)
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev)
 {
-	struct netvsc_device *nvdev
-		= container_of(w, struct netvsc_device, subchan_work);
 	struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
-	struct net_device_context *ndev_ctx;
-	struct rndis_device *rdev;
-	struct net_device *ndev;
-	struct hv_device *hv_dev;
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct hv_device *hv_dev = ndev_ctx->device_ctx;
+	struct rndis_device *rdev = nvdev->extension;
 	int i, ret;
 
-	if (!rtnl_trylock()) {
-		schedule_work(w);
-		return;
-	}
-
-	rdev = nvdev->extension;
-	if (!rdev)
-		goto unlock;	/* device was removed */
-
-	ndev = rdev->ndev;
-	ndev_ctx = netdev_priv(ndev);
-	hv_dev = ndev_ctx->device_ctx;
+	ASSERT_RTNL();
 
 	memset(init_packet, 0, sizeof(struct nvsp_message));
 	init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
@@ -1100,13 +1086,13 @@ void rndis_set_subchannel(struct work_struct *w)
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret) {
 		netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
-		goto failed;
+		return ret;
 	}
 
 	wait_for_completion(&nvdev->channel_init_wait);
 	if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
 		netdev_err(ndev, "sub channel request failed\n");
-		goto failed;
+		return -EIO;
 	}
 
 	nvdev->num_chn = 1 +
@@ -1125,21 +1111,7 @@ void rndis_set_subchannel(struct work_struct *w)
 	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
 		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
 
-	netif_device_attach(ndev);
-	rtnl_unlock();
-	return;
-
-failed:
-	/* fallback to only primary channel */
-	for (i = 1; i < nvdev->num_chn; i++)
-		netif_napi_del(&nvdev->chan_table[i].napi);
-
-	nvdev->max_chn = 1;
-	nvdev->num_chn = 1;
-
-	netif_device_attach(ndev);
-unlock:
-	rtnl_unlock();
+	return 0;
 }
 
 static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
@@ -1360,21 +1332,13 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 		netif_napi_add(net, &net_device->chan_table[i].napi,
 			       netvsc_poll, NAPI_POLL_WEIGHT);
 
-	if (net_device->num_chn > 1)
-		schedule_work(&net_device->subchan_work);
+	return net_device;
 
 out:
-	/* if unavailable, just proceed with one queue */
-	if (ret) {
-		net_device->max_chn = 1;
-		net_device->num_chn = 1;
-	}
-
-	/* No sub channels, device is ready */
-	if (net_device->num_chn == 1)
-		netif_device_attach(net);
-
-	return net_device;
+	/* setting up multiple channels failed */
+	net_device->max_chn = 1;
+	net_device->num_chn = 1;
+	return 0;
 
 err_dev_remv:
 	rndis_filter_device_remove(dev, net_device);
diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c
index 64f1b1e77bc0..23a52b9293f3 100644
--- a/drivers/net/ieee802154/adf7242.c
+++ b/drivers/net/ieee802154/adf7242.c
@@ -275,6 +275,8 @@ struct adf7242_local {
 	struct spi_message stat_msg;
 	struct spi_transfer stat_xfer;
 	struct dentry *debugfs_root;
+	struct delayed_work work;
+	struct workqueue_struct *wqueue;
 	unsigned long flags;
 	int tx_stat;
 	bool promiscuous;
@@ -575,10 +577,26 @@ static int adf7242_cmd_rx(struct adf7242_local *lp)
 	/* Wait until the ACK is sent */
 	adf7242_wait_status(lp, RC_STATUS_PHY_RDY, RC_STATUS_MASK, __LINE__);
 	adf7242_clear_irqstat(lp);
+	mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400));
 
 	return adf7242_cmd(lp, CMD_RC_RX);
 }
 
+static void adf7242_rx_cal_work(struct work_struct *work)
+{
+	struct adf7242_local *lp =
+	container_of(work, struct adf7242_local, work.work);
+
+	/* Reissuing RC_RX every 400ms - to adjust for offset
+	 * drift in receiver (datasheet page 61, OCL section)
+	 */
+
+	if (!test_bit(FLAG_XMIT, &lp->flags)) {
+		adf7242_cmd(lp, CMD_RC_PHY_RDY);
+		adf7242_cmd_rx(lp);
+	}
+}
+
 static int adf7242_set_txpower(struct ieee802154_hw *hw, int mbm)
 {
 	struct adf7242_local *lp = hw->priv;
@@ -686,7 +704,7 @@ static int adf7242_start(struct ieee802154_hw *hw)
 	enable_irq(lp->spi->irq);
 	set_bit(FLAG_START, &lp->flags);
 
-	return adf7242_cmd(lp, CMD_RC_RX);
+	return adf7242_cmd_rx(lp);
 }
 
 static void adf7242_stop(struct ieee802154_hw *hw)
@@ -694,6 +712,7 @@ static void adf7242_stop(struct ieee802154_hw *hw)
 	struct adf7242_local *lp = hw->priv;
 
 	disable_irq(lp->spi->irq);
+	cancel_delayed_work_sync(&lp->work);
 	adf7242_cmd(lp, CMD_RC_IDLE);
 	clear_bit(FLAG_START, &lp->flags);
 	adf7242_clear_irqstat(lp);
@@ -719,7 +738,10 @@ static int adf7242_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
 	adf7242_write_reg(lp, REG_CH_FREQ1, freq >> 8);
 	adf7242_write_reg(lp, REG_CH_FREQ2, freq >> 16);
 
-	return adf7242_cmd(lp, CMD_RC_RX);
+	if (test_bit(FLAG_START, &lp->flags))
+		return adf7242_cmd_rx(lp);
+	else
+		return adf7242_cmd(lp, CMD_RC_PHY_RDY);
 }
 
 static int adf7242_set_hw_addr_filt(struct ieee802154_hw *hw,
@@ -814,6 +836,7 @@ static int adf7242_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
 	/* ensure existing instances of the IRQ handler have completed */
 	disable_irq(lp->spi->irq);
 	set_bit(FLAG_XMIT, &lp->flags);
+	cancel_delayed_work_sync(&lp->work);
 	reinit_completion(&lp->tx_complete);
 	adf7242_cmd(lp, CMD_RC_PHY_RDY);
 	adf7242_clear_irqstat(lp);
@@ -952,6 +975,7 @@ static irqreturn_t adf7242_isr(int irq, void *data)
 	unsigned int xmit;
 	u8 irq1;
 
+	mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400));
 	adf7242_read_reg(lp, REG_IRQ1_SRC1, &irq1);
 
 	if (!(irq1 & (IRQ_RX_PKT_RCVD | IRQ_CSMA_CA)))
@@ -1241,6 +1265,9 @@ static int adf7242_probe(struct spi_device *spi)
 	spi_message_add_tail(&lp->stat_xfer, &lp->stat_msg);
 
 	spi_set_drvdata(spi, lp);
+	INIT_DELAYED_WORK(&lp->work, adf7242_rx_cal_work);
+	lp->wqueue = alloc_ordered_workqueue(dev_name(&spi->dev),
+					     WQ_MEM_RECLAIM);
 
 	ret = adf7242_hw_init(lp);
 	if (ret)
@@ -1284,6 +1311,9 @@ static int adf7242_remove(struct spi_device *spi)
 	if (!IS_ERR_OR_NULL(lp->debugfs_root))
 		debugfs_remove_recursive(lp->debugfs_root);
 
+	cancel_delayed_work_sync(&lp->work);
+	destroy_workqueue(lp->wqueue);
+
 	ieee802154_unregister_hw(lp->hw);
 	mutex_destroy(&lp->bmux);
 	ieee802154_free_hw(lp->hw);
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 77abedf0b524..3d9e91579866 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -940,7 +940,7 @@ at86rf230_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
 static int
 at86rf230_ed(struct ieee802154_hw *hw, u8 *level)
 {
-	BUG_ON(!level);
+	WARN_ON(!level);
 	*level = 0xbe;
 	return 0;
 }
@@ -1121,8 +1121,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw,
 	if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
 		u16 addr = le16_to_cpu(filt->short_addr);
 
-		dev_vdbg(&lp->spi->dev,
-			 "at86rf230_set_hw_addr_filt called for saddr\n");
+		dev_vdbg(&lp->spi->dev, "%s called for saddr\n", __func__);
 		__at86rf230_write(lp, RG_SHORT_ADDR_0, addr);
 		__at86rf230_write(lp, RG_SHORT_ADDR_1, addr >> 8);
 	}
@@ -1130,8 +1129,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw,
 	if (changed & IEEE802154_AFILT_PANID_CHANGED) {
 		u16 pan = le16_to_cpu(filt->pan_id);
 
-		dev_vdbg(&lp->spi->dev,
-			 "at86rf230_set_hw_addr_filt called for pan id\n");
+		dev_vdbg(&lp->spi->dev, "%s called for pan id\n", __func__);
 		__at86rf230_write(lp, RG_PAN_ID_0, pan);
 		__at86rf230_write(lp, RG_PAN_ID_1, pan >> 8);
 	}
@@ -1140,15 +1138,13 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw,
 		u8 i, addr[8];
 
 		memcpy(addr, &filt->ieee_addr, 8);
-		dev_vdbg(&lp->spi->dev,
-			 "at86rf230_set_hw_addr_filt called for IEEE addr\n");
+		dev_vdbg(&lp->spi->dev, "%s called for IEEE addr\n", __func__);
 		for (i = 0; i < 8; i++)
 			__at86rf230_write(lp, RG_IEEE_ADDR_0 + i, addr[i]);
 	}
 
 	if (changed & IEEE802154_AFILT_PANC_CHANGED) {
-		dev_vdbg(&lp->spi->dev,
-			 "at86rf230_set_hw_addr_filt called for panc change\n");
+		dev_vdbg(&lp->spi->dev, "%s called for panc change\n", __func__);
 		if (filt->pan_coord)
 			at86rf230_write_subreg(lp, SR_AACK_I_AM_COORD, 1);
 		else
@@ -1252,7 +1248,6 @@ at86rf230_set_cca_mode(struct ieee802154_hw *hw,
 	return at86rf230_write_subreg(lp, SR_CCA_MODE, val);
 }
 
-
 static int
 at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm)
 {
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 0d673f7682ee..176395e4b7bb 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -49,7 +49,7 @@ struct fakelb_phy {
 
 static int fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level)
 {
-	BUG_ON(!level);
+	WARN_ON(!level);
 	*level = 0xbe;
 
 	return 0;
diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c
index de0d7f28a181..e428277781ac 100644
--- a/drivers/net/ieee802154/mcr20a.c
+++ b/drivers/net/ieee802154/mcr20a.c
@@ -15,10 +15,11 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/spi/spi.h>
 #include <linux/workqueue.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/skbuff.h>
 #include <linux/of_gpio.h>
 #include <linux/regmap.h>
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index d02f0a7c534e..4a949569ec4c 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -75,10 +75,23 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 {
 	struct ipvl_dev *ipvlan;
 	struct net_device *mdev = port->dev;
-	int err = 0;
+	unsigned int flags;
+	int err;
 
 	ASSERT_RTNL();
 	if (port->mode != nval) {
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+			flags = ipvlan->dev->flags;
+			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
+				err = dev_change_flags(ipvlan->dev,
+						       flags | IFF_NOARP);
+			} else {
+				err = dev_change_flags(ipvlan->dev,
+						       flags & ~IFF_NOARP);
+			}
+			if (unlikely(err))
+				goto fail;
+		}
 		if (nval == IPVLAN_MODE_L3S) {
 			/* New mode is L3S */
 			err = ipvlan_register_nf_hook(read_pnet(&port->pnet));
@@ -86,21 +99,28 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 				mdev->l3mdev_ops = &ipvl_l3mdev_ops;
 				mdev->priv_flags |= IFF_L3MDEV_MASTER;
 			} else
-				return err;
+				goto fail;
 		} else if (port->mode == IPVLAN_MODE_L3S) {
 			/* Old mode was L3S */
 			mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
 			ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
 			mdev->l3mdev_ops = NULL;
 		}
-		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S)
-				ipvlan->dev->flags |= IFF_NOARP;
-			else
-				ipvlan->dev->flags &= ~IFF_NOARP;
-		}
 		port->mode = nval;
 	}
+	return 0;
+
+fail:
+	/* Undo the flags changes that have been done so far. */
+	list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) {
+		flags = ipvlan->dev->flags;
+		if (port->mode == IPVLAN_MODE_L3 ||
+		    port->mode == IPVLAN_MODE_L3S)
+			dev_change_flags(ipvlan->dev, flags | IFF_NOARP);
+		else
+			dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP);
+	}
+
 	return err;
 }
 
@@ -594,7 +614,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	ipvlan->phy_dev = phy_dev;
 	ipvlan->dev = dev;
 	ipvlan->sfeatures = IPVLAN_FEATURES;
-	ipvlan_adjust_mtu(ipvlan, phy_dev);
+	if (!tb[IFLA_MTU])
+		ipvlan_adjust_mtu(ipvlan, phy_dev);
 	INIT_LIST_HEAD(&ipvlan->addrs);
 	spin_lock_init(&ipvlan->addrs_lock);
 
diff --git a/drivers/net/netdevsim/devlink.c b/drivers/net/netdevsim/devlink.c
index ba663e5af168..5135fc371f01 100644
--- a/drivers/net/netdevsim/devlink.c
+++ b/drivers/net/netdevsim/devlink.c
@@ -207,6 +207,7 @@ void nsim_devlink_teardown(struct netdevsim *ns)
 		struct net *net = nsim_to_net(ns);
 		bool *reg_devlink = net_generic(net, nsim_devlink_id);
 
+		devlink_resources_unregister(ns->devlink, NULL);
 		devlink_unregister(ns->devlink);
 		devlink_free(ns->devlink);
 		ns->devlink = NULL;
diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c
index 081d99aa3985..49ac678eb2dc 100644
--- a/drivers/net/phy/dp83tc811.c
+++ b/drivers/net/phy/dp83tc811.c
@@ -222,7 +222,7 @@ static int dp83811_config_intr(struct phy_device *phydev)
 		if (err < 0)
 			return err;
 
-		err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
+		err = phy_write(phydev, MII_DP83811_INT_STAT2, 0);
 	}
 
 	return err;
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index b8f57e9b9379..1cd439bdf608 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -130,8 +130,9 @@
 #define MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS		BIT(12)
 #define MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE	BIT(14)
 
-#define MII_88E1121_PHY_LED_CTRL	16
+#define MII_PHY_LED_CTRL	        16
 #define MII_88E1121_PHY_LED_DEF		0x0030
+#define MII_88E1510_PHY_LED_DEF		0x1177
 
 #define MII_M1011_PHY_STATUS		0x11
 #define MII_M1011_PHY_STATUS_1000	0x8000
@@ -632,8 +633,40 @@ error:
 	return err;
 }
 
+static void marvell_config_led(struct phy_device *phydev)
+{
+	u16 def_config;
+	int err;
+
+	switch (MARVELL_PHY_FAMILY_ID(phydev->phy_id)) {
+	/* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */
+	case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1121R):
+	case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1318S):
+		def_config = MII_88E1121_PHY_LED_DEF;
+		break;
+	/* Default PHY LED config:
+	 * LED[0] .. 1000Mbps Link
+	 * LED[1] .. 100Mbps Link
+	 * LED[2] .. Blink, Activity
+	 */
+	case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1510):
+		def_config = MII_88E1510_PHY_LED_DEF;
+		break;
+	default:
+		return;
+	}
+
+	err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE, MII_PHY_LED_CTRL,
+			      def_config);
+	if (err < 0)
+		pr_warn("Fail to config marvell phy LED.\n");
+}
+
 static int marvell_config_init(struct phy_device *phydev)
 {
+	/* Set defalut LED */
+	marvell_config_led(phydev);
+
 	/* Set registers from marvell,reg-init DT property */
 	return marvell_of_reg_init(phydev);
 }
@@ -813,21 +846,6 @@ static int m88e1111_config_init(struct phy_device *phydev)
 	return genphy_soft_reset(phydev);
 }
 
-static int m88e1121_config_init(struct phy_device *phydev)
-{
-	int err;
-
-	/* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */
-	err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE,
-			      MII_88E1121_PHY_LED_CTRL,
-			      MII_88E1121_PHY_LED_DEF);
-	if (err < 0)
-		return err;
-
-	/* Set marvell,reg-init configuration from device tree */
-	return marvell_config_init(phydev);
-}
-
 static int m88e1318_config_init(struct phy_device *phydev)
 {
 	if (phy_interrupt_is_valid(phydev)) {
@@ -841,7 +859,7 @@ static int m88e1318_config_init(struct phy_device *phydev)
 			return err;
 	}
 
-	return m88e1121_config_init(phydev);
+	return marvell_config_init(phydev);
 }
 
 static int m88e1510_config_init(struct phy_device *phydev)
@@ -2087,7 +2105,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = &m88e1121_probe,
-		.config_init = &m88e1121_config_init,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1121_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 0831b7142df7..0c5b68e7da51 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -218,7 +218,7 @@ out:
 
 static int mdio_mux_iproc_remove(struct platform_device *pdev)
 {
-	struct iproc_mdiomux_desc *md = dev_get_platdata(&pdev->dev);
+	struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
 
 	mdio_mux_uninit(md->mux_handle);
 	mdiobus_unregister(md->mii_bus);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 537297d2b4b4..6c9b24fe3148 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -514,7 +514,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 	 * negotiation may already be done and aneg interrupt may not be
 	 * generated.
 	 */
-	if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+	if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) {
 		err = phy_aneg_done(phydev);
 		if (err > 0) {
 			trigger = true;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index bd0f339f69fd..b9f5f40a7ac1 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1724,11 +1724,8 @@ EXPORT_SYMBOL(genphy_loopback);
 
 static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	/* The default values for phydev->supported are provided by the PHY
-	 * driver "features" member, we want to reset to sane defaults first
-	 * before supporting higher speeds.
-	 */
-	phydev->supported &= PHY_DEFAULT_FEATURES;
+	phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES |
+			       PHY_10BT_FEATURES);
 
 	switch (max_speed) {
 	default:
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index d437f4f5ed52..740655261e5b 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -349,7 +349,6 @@ static int sfp_register_bus(struct sfp_bus *bus)
 	}
 	if (bus->started)
 		bus->socket_ops->start(bus->sfp);
-	bus->netdev->sfp_bus = bus;
 	bus->registered = true;
 	return 0;
 }
@@ -364,7 +363,6 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 		if (bus->phydev && ops && ops->disconnect_phy)
 			ops->disconnect_phy(bus->upstream);
 	}
-	bus->netdev->sfp_bus = NULL;
 	bus->registered = false;
 }
 
@@ -436,6 +434,14 @@ void sfp_upstream_stop(struct sfp_bus *bus)
 }
 EXPORT_SYMBOL_GPL(sfp_upstream_stop);
 
+static void sfp_upstream_clear(struct sfp_bus *bus)
+{
+	bus->upstream_ops = NULL;
+	bus->upstream = NULL;
+	bus->netdev->sfp_bus = NULL;
+	bus->netdev = NULL;
+}
+
 /**
  * sfp_register_upstream() - Register the neighbouring device
  * @fwnode: firmware node for the SFP bus
@@ -461,9 +467,13 @@ struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode,
 		bus->upstream_ops = ops;
 		bus->upstream = upstream;
 		bus->netdev = ndev;
+		ndev->sfp_bus = bus;
 
-		if (bus->sfp)
+		if (bus->sfp) {
 			ret = sfp_register_bus(bus);
+			if (ret)
+				sfp_upstream_clear(bus);
+		}
 		rtnl_unlock();
 	}
 
@@ -488,8 +498,7 @@ void sfp_unregister_upstream(struct sfp_bus *bus)
 	rtnl_lock();
 	if (bus->sfp)
 		sfp_unregister_bus(bus);
-	bus->upstream = NULL;
-	bus->netdev = NULL;
+	sfp_upstream_clear(bus);
 	rtnl_unlock();
 
 	sfp_bus_put(bus);
@@ -561,6 +570,13 @@ void sfp_module_remove(struct sfp_bus *bus)
 }
 EXPORT_SYMBOL_GPL(sfp_module_remove);
 
+static void sfp_socket_clear(struct sfp_bus *bus)
+{
+	bus->sfp_dev = NULL;
+	bus->sfp = NULL;
+	bus->socket_ops = NULL;
+}
+
 struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp,
 				    const struct sfp_socket_ops *ops)
 {
@@ -573,8 +589,11 @@ struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp,
 		bus->sfp = sfp;
 		bus->socket_ops = ops;
 
-		if (bus->netdev)
+		if (bus->netdev) {
 			ret = sfp_register_bus(bus);
+			if (ret)
+				sfp_socket_clear(bus);
+		}
 		rtnl_unlock();
 	}
 
@@ -592,9 +611,7 @@ void sfp_unregister_socket(struct sfp_bus *bus)
 	rtnl_lock();
 	if (bus->netdev)
 		sfp_unregister_bus(bus);
-	bus->sfp_dev = NULL;
-	bus->sfp = NULL;
-	bus->socket_ops = NULL;
+	sfp_socket_clear(bus);
 	rtnl_unlock();
 
 	sfp_bus_put(bus);
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index de51e8f70f44..ce61231e96ea 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1107,7 +1107,7 @@ static const struct proto_ops pppoe_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pppoe_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a192a017cc68..f5727baac84a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1688,7 +1688,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		case XDP_TX:
 			get_page(alloc_frag->page);
 			alloc_frag->offset += buflen;
-			if (tun_xdp_tx(tun->dev, &xdp))
+			if (tun_xdp_tx(tun->dev, &xdp) < 0)
 				goto err_redirect;
 			rcu_read_unlock();
 			local_bh_enable();
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 3d4f7959dabb..b1b3d8f7e67d 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -642,10 +642,12 @@ static void ax88772_restore_phy(struct usbnet *dev)
 				     priv->presvd_phy_advertise);
 
 		/* Restore BMCR */
+		if (priv->presvd_phy_bmcr & BMCR_ANENABLE)
+			priv->presvd_phy_bmcr |= BMCR_ANRESTART;
+
 		asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR,
 				     priv->presvd_phy_bmcr);
 
-		mii_nway_restart(&dev->mii);
 		priv->presvd_phy_advertise = 0;
 		priv->presvd_phy_bmcr = 0;
 	}
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 8dff87ec6d99..aeca484a75b8 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -64,6 +64,7 @@
 #define DEFAULT_RX_CSUM_ENABLE		(true)
 #define DEFAULT_TSO_CSUM_ENABLE		(true)
 #define DEFAULT_VLAN_FILTER_ENABLE	(true)
+#define DEFAULT_VLAN_RX_OFFLOAD		(true)
 #define TX_OVERHEAD			(8)
 #define RXW_PADDING			2
 
@@ -1241,6 +1242,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 			mod_timer(&dev->stat_monitor,
 				  jiffies + STAT_UPDATE_TIMER);
 		}
+
+		tasklet_schedule(&dev->bh);
 	}
 
 	return ret;
@@ -2298,7 +2301,7 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu)
 	if ((ll_mtu % dev->maxpacket) == 0)
 		return -EDOM;
 
-	ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + ETH_HLEN);
+	ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN);
 
 	netdev->mtu = new_mtu;
 
@@ -2364,6 +2367,11 @@ static int lan78xx_set_features(struct net_device *netdev,
 	}
 
 	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		pdata->rfe_ctl |= RFE_CTL_VLAN_STRIP_;
+	else
+		pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_;
+
+	if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
 		pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_;
 	else
 		pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_;
@@ -2587,7 +2595,8 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	buf |= FCT_TX_CTL_EN_;
 	ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf);
 
-	ret = lan78xx_set_rx_max_frame_length(dev, dev->net->mtu + ETH_HLEN);
+	ret = lan78xx_set_rx_max_frame_length(dev,
+					      dev->net->mtu + VLAN_ETH_HLEN);
 
 	ret = lan78xx_read_reg(dev, MAC_RX, &buf);
 	buf |= MAC_RX_RXEN_;
@@ -2975,6 +2984,12 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 	if (DEFAULT_TSO_CSUM_ENABLE)
 		dev->net->features |= NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_SG;
 
+	if (DEFAULT_VLAN_RX_OFFLOAD)
+		dev->net->features |= NETIF_F_HW_VLAN_CTAG_RX;
+
+	if (DEFAULT_VLAN_FILTER_ENABLE)
+		dev->net->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
 	dev->net->hw_features = dev->net->features;
 
 	ret = lan78xx_setup_irq_domain(dev);
@@ -3039,8 +3054,13 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev,
 				    struct sk_buff *skb,
 				    u32 rx_cmd_a, u32 rx_cmd_b)
 {
+	/* HW Checksum offload appears to be flawed if used when not stripping
+	 * VLAN headers. Drop back to S/W checksums under these conditions.
+	 */
 	if (!(dev->net->features & NETIF_F_RXCSUM) ||
-	    unlikely(rx_cmd_a & RX_CMD_A_ICSM_)) {
+	    unlikely(rx_cmd_a & RX_CMD_A_ICSM_) ||
+	    ((rx_cmd_a & RX_CMD_A_FVTG_) &&
+	     !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) {
 		skb->ip_summed = CHECKSUM_NONE;
 	} else {
 		skb->csum = ntohs((u16)(rx_cmd_b >> RX_CMD_B_CSUM_SHIFT_));
@@ -3048,6 +3068,16 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev,
 	}
 }
 
+static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev,
+				    struct sk_buff *skb,
+				    u32 rx_cmd_a, u32 rx_cmd_b)
+{
+	if ((dev->net->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+	    (rx_cmd_a & RX_CMD_A_FVTG_))
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+				       (rx_cmd_b & 0xffff));
+}
+
 static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb)
 {
 	int		status;
@@ -3112,6 +3142,8 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb)
 			if (skb->len == size) {
 				lan78xx_rx_csum_offload(dev, skb,
 							rx_cmd_a, rx_cmd_b);
+				lan78xx_rx_vlan_offload(dev, skb,
+							rx_cmd_a, rx_cmd_b);
 
 				skb_trim(skb, skb->len - 4); /* remove fcs */
 				skb->truesize = size + sizeof(struct sk_buff);
@@ -3130,6 +3162,7 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb)
 			skb_set_tail_pointer(skb2, size);
 
 			lan78xx_rx_csum_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
+			lan78xx_rx_vlan_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
 
 			skb_trim(skb2, skb2->len - 4); /* remove fcs */
 			skb2->truesize = size + sizeof(struct sk_buff);
@@ -3313,6 +3346,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev)
 	pkt_cnt = 0;
 	count = 0;
 	length = 0;
+	spin_lock_irqsave(&tqp->lock, flags);
 	for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) {
 		if (skb_is_gso(skb)) {
 			if (pkt_cnt) {
@@ -3321,7 +3355,8 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev)
 			}
 			count = 1;
 			length = skb->len - TX_OVERHEAD;
-			skb2 = skb_dequeue(tqp);
+			__skb_unlink(skb, tqp);
+			spin_unlock_irqrestore(&tqp->lock, flags);
 			goto gso_skb;
 		}
 
@@ -3330,6 +3365,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev)
 		skb_totallen = skb->len + roundup(skb_totallen, sizeof(u32));
 		pkt_cnt++;
 	}
+	spin_unlock_irqrestore(&tqp->lock, flags);
 
 	/* copy to a single skb */
 	skb = alloc_skb(skb_totallen, GFP_ATOMIC);
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8e8b51f171f4..cb0cc30c3d6a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1246,12 +1246,14 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)},	/* HP lt4120 Snapdragon X5 LTE */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
 	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)},	/* SIMCom 7100E, 7230E, 7600E ++ */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)},	/* Quectel EP06 Mini PCIe */
 
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 86f7196f9d91..2a58607a6aea 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3962,7 +3962,8 @@ static int rtl8152_close(struct net_device *netdev)
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&tp->pm_notifier);
 #endif
-	napi_disable(&tp->napi);
+	if (!test_bit(RTL8152_UNPLUG, &tp->flags))
+		napi_disable(&tp->napi);
 	clear_bit(WORK_ENABLE, &tp->flags);
 	usb_kill_urb(tp->intr_urb);
 	cancel_delayed_work_sync(&tp->schedule);
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 5f565bd574da..48ba80a8ca5c 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -681,7 +681,7 @@ static void rtl8150_set_multicast(struct net_device *netdev)
 		   (netdev->flags & IFF_ALLMULTI)) {
 		rx_creg &= 0xfffe;
 		rx_creg |= 0x0002;
-		dev_info(&netdev->dev, "%s: allmulti set\n", netdev->name);
+		dev_dbg(&netdev->dev, "%s: allmulti set\n", netdev->name);
 	} else {
 		/* ~RX_MULTICAST, ~RX_PROMISCUOUS */
 		rx_creg &= 0x00fc;
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 7a6a1fe79309..05553d252446 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -82,6 +82,9 @@ static bool turbo_mode = true;
 module_param(turbo_mode, bool, 0644);
 MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction");
 
+static int smsc75xx_link_ok_nopm(struct usbnet *dev);
+static int smsc75xx_phy_gig_workaround(struct usbnet *dev);
+
 static int __must_check __smsc75xx_read_reg(struct usbnet *dev, u32 index,
 					    u32 *data, int in_pm)
 {
@@ -852,6 +855,9 @@ static int smsc75xx_phy_initialize(struct usbnet *dev)
 		return -EIO;
 	}
 
+	/* phy workaround for gig link */
+	smsc75xx_phy_gig_workaround(dev);
+
 	smsc75xx_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE,
 		ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP |
 		ADVERTISE_PAUSE_ASYM);
@@ -987,6 +993,62 @@ static int smsc75xx_wait_ready(struct usbnet *dev, int in_pm)
 	return -EIO;
 }
 
+static int smsc75xx_phy_gig_workaround(struct usbnet *dev)
+{
+	struct mii_if_info *mii = &dev->mii;
+	int ret = 0, timeout = 0;
+	u32 buf, link_up = 0;
+
+	/* Set the phy in Gig loopback */
+	smsc75xx_mdio_write(dev->net, mii->phy_id, MII_BMCR, 0x4040);
+
+	/* Wait for the link up */
+	do {
+		link_up = smsc75xx_link_ok_nopm(dev);
+		usleep_range(10000, 20000);
+		timeout++;
+	} while ((!link_up) && (timeout < 1000));
+
+	if (timeout >= 1000) {
+		netdev_warn(dev->net, "Timeout waiting for PHY link up\n");
+		return -EIO;
+	}
+
+	/* phy reset */
+	ret = smsc75xx_read_reg(dev, PMT_CTL, &buf);
+	if (ret < 0) {
+		netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n", ret);
+		return ret;
+	}
+
+	buf |= PMT_CTL_PHY_RST;
+
+	ret = smsc75xx_write_reg(dev, PMT_CTL, buf);
+	if (ret < 0) {
+		netdev_warn(dev->net, "Failed to write PMT_CTL: %d\n", ret);
+		return ret;
+	}
+
+	timeout = 0;
+	do {
+		usleep_range(10000, 20000);
+		ret = smsc75xx_read_reg(dev, PMT_CTL, &buf);
+		if (ret < 0) {
+			netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n",
+				    ret);
+			return ret;
+		}
+		timeout++;
+	} while ((buf & PMT_CTL_PHY_RST) && (timeout < 100));
+
+	if (timeout >= 100) {
+		netdev_warn(dev->net, "timeout waiting for PHY Reset\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int smsc75xx_reset(struct usbnet *dev)
 {
 	struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b6c9a2af3732..2b6ec927809e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -53,6 +53,10 @@ module_param(napi_tx, bool, 0644);
 /* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */
 #define VIRTIO_XDP_HEADROOM 256
 
+/* Separating two types of XDP xmit */
+#define VIRTIO_XDP_TX		BIT(0)
+#define VIRTIO_XDP_REDIR	BIT(1)
+
 /* RX packet size EWMA. The average packet size is used to determine the packet
  * buffer size when refilling RX rings. As the entire RX ring may be refilled
  * at once, the weight is chosen so that the EWMA will be insensitive to short-
@@ -582,7 +586,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     struct receive_queue *rq,
 				     void *buf, void *ctx,
 				     unsigned int len,
-				     bool *xdp_xmit)
+				     unsigned int *xdp_xmit,
+				     unsigned int *rbytes)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -597,6 +602,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	int err;
 
 	len -= vi->hdr_len;
+	*rbytes += len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -654,14 +660,14 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				goto err_xdp;
 			}
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_TX;
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
 			if (err)
 				goto err_xdp;
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_REDIR;
 			rcu_read_unlock();
 			goto xdp_xmit;
 		default:
@@ -701,11 +707,13 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   struct virtnet_info *vi,
 				   struct receive_queue *rq,
 				   void *buf,
-				   unsigned int len)
+				   unsigned int len,
+				   unsigned int *rbytes)
 {
 	struct page *page = buf;
 	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
 
+	*rbytes += len - vi->hdr_len;
 	if (unlikely(!skb))
 		goto err;
 
@@ -723,7 +731,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 void *buf,
 					 void *ctx,
 					 unsigned int len,
-					 bool *xdp_xmit)
+					 unsigned int *xdp_xmit,
+					 unsigned int *rbytes)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -736,6 +745,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	int err;
 
 	head_skb = NULL;
+	*rbytes += len - vi->hdr_len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -818,7 +828,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					put_page(xdp_page);
 				goto err_xdp;
 			}
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_TX;
 			if (unlikely(xdp_page != page))
 				put_page(page);
 			rcu_read_unlock();
@@ -830,7 +840,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					put_page(xdp_page);
 				goto err_xdp;
 			}
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_REDIR;
 			if (unlikely(xdp_page != page))
 				put_page(page);
 			rcu_read_unlock();
@@ -873,6 +883,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto err_buf;
 		}
 
+		*rbytes += len;
 		page = virt_to_head_page(buf);
 
 		truesize = mergeable_ctx_to_truesize(ctx);
@@ -928,6 +939,7 @@ err_skb:
 			dev->stats.rx_length_errors++;
 			break;
 		}
+		*rbytes += len;
 		page = virt_to_head_page(buf);
 		put_page(page);
 	}
@@ -938,13 +950,13 @@ xdp_xmit:
 	return NULL;
 }
 
-static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
-		       void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
+static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
+			void *buf, unsigned int len, void **ctx,
+			unsigned int *xdp_xmit, unsigned int *rbytes)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
-	int ret;
 
 	if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
@@ -956,23 +968,22 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 		} else {
 			put_page(virt_to_head_page(buf));
 		}
-		return 0;
+		return;
 	}
 
 	if (vi->mergeable_rx_bufs)
-		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit);
+		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit,
+					rbytes);
 	else if (vi->big_packets)
-		skb = receive_big(dev, vi, rq, buf, len);
+		skb = receive_big(dev, vi, rq, buf, len, rbytes);
 	else
-		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit);
+		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, rbytes);
 
 	if (unlikely(!skb))
-		return 0;
+		return;
 
 	hdr = skb_vnet_hdr(skb);
 
-	ret = skb->len;
-
 	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
@@ -989,12 +1000,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 		 ntohs(skb->protocol), skb->len, skb->pkt_type);
 
 	napi_gro_receive(&rq->napi, skb);
-	return ret;
+	return;
 
 frame_err:
 	dev->stats.rx_frame_errors++;
 	dev_kfree_skb(skb);
-	return 0;
 }
 
 /* Unlike mergeable buffers, all buffers are allocated to the
@@ -1232,7 +1242,8 @@ static void refill_work(struct work_struct *work)
 	}
 }
 
-static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
+static int virtnet_receive(struct receive_queue *rq, int budget,
+			   unsigned int *xdp_xmit)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	unsigned int len, received = 0, bytes = 0;
@@ -1243,13 +1254,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
 
 		while (received < budget &&
 		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
-			bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit);
+			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &bytes);
 			received++;
 		}
 	} else {
 		while (received < budget &&
 		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
-			bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit);
+			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &bytes);
 			received++;
 		}
 	}
@@ -1321,7 +1332,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	struct send_queue *sq;
 	unsigned int received, qp;
-	bool xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
 
 	virtnet_poll_cleantx(rq);
 
@@ -1331,12 +1342,14 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	if (received < budget)
 		virtqueue_napi_complete(napi, rq->vq, received);
 
-	if (xdp_xmit) {
+	if (xdp_xmit & VIRTIO_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & VIRTIO_XDP_TX) {
 		qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
 		     smp_processor_id();
 		sq = &vi->sq[qp];
 		virtqueue_kick(sq->vq);
-		xdp_do_flush_map();
 	}
 
 	return received;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index aee0e60471f1..e857cb3335f6 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -623,9 +623,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk,
 	flush = 0;
 
 out:
-	skb_gro_remcsum_cleanup(skb, &grc);
-	skb->remcsum_offload = 0;
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
 
 	return pp;
 }
@@ -638,9 +636,62 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
-/* Add new entry to forwarding table -- assumes lock held */
+static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
+					 const u8 *mac, __u16 state,
+					 __be32 src_vni, __u8 ndm_flags)
+{
+	struct vxlan_fdb *f;
+
+	f = kmalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return NULL;
+	f->state = state;
+	f->flags = ndm_flags;
+	f->updated = f->used = jiffies;
+	f->vni = src_vni;
+	INIT_LIST_HEAD(&f->remotes);
+	memcpy(f->eth_addr, mac, ETH_ALEN);
+
+	return f;
+}
+
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
+			    __u16 state, __be16 port, __be32 src_vni,
+			    __be32 vni, __u32 ifindex, __u8 ndm_flags,
+			    struct vxlan_fdb **fdb)
+{
+	struct vxlan_rdst *rd = NULL;
+	struct vxlan_fdb *f;
+	int rc;
+
+	if (vxlan->cfg.addrmax &&
+	    vxlan->addrcnt >= vxlan->cfg.addrmax)
+		return -ENOSPC;
+
+	netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
+	f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags);
+	if (!f)
+		return -ENOMEM;
+
+	rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
+	if (rc < 0) {
+		kfree(f);
+		return rc;
+	}
+
+	++vxlan->addrcnt;
+	hlist_add_head_rcu(&f->hlist,
+			   vxlan_fdb_head(vxlan, mac, src_vni));
+
+	*fdb = f;
+
+	return 0;
+}
+
+/* Add new entry to forwarding table -- assumes lock held */
+static int vxlan_fdb_update(struct vxlan_dev *vxlan,
+			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __u16 flags,
 			    __be16 port, __be32 src_vni, __be32 vni,
 			    __u32 ifindex, __u8 ndm_flags)
@@ -689,37 +740,17 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		if (!(flags & NLM_F_CREATE))
 			return -ENOENT;
 
-		if (vxlan->cfg.addrmax &&
-		    vxlan->addrcnt >= vxlan->cfg.addrmax)
-			return -ENOSPC;
-
 		/* Disallow replace to add a multicast entry */
 		if ((flags & NLM_F_REPLACE) &&
 		    (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
 			return -EOPNOTSUPP;
 
 		netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
-		f = kmalloc(sizeof(*f), GFP_ATOMIC);
-		if (!f)
-			return -ENOMEM;
-
-		notify = 1;
-		f->state = state;
-		f->flags = ndm_flags;
-		f->updated = f->used = jiffies;
-		f->vni = src_vni;
-		INIT_LIST_HEAD(&f->remotes);
-		memcpy(f->eth_addr, mac, ETH_ALEN);
-
-		rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
-		if (rc < 0) {
-			kfree(f);
+		rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni,
+				      vni, ifindex, ndm_flags, &f);
+		if (rc < 0)
 			return rc;
-		}
-
-		++vxlan->addrcnt;
-		hlist_add_head_rcu(&f->hlist,
-				   vxlan_fdb_head(vxlan, mac, src_vni));
+		notify = 1;
 	}
 
 	if (notify) {
@@ -743,13 +774,15 @@ static void vxlan_fdb_free(struct rcu_head *head)
 	kfree(f);
 }
 
-static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
+static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+			      bool do_notify)
 {
 	netdev_dbg(vxlan->dev,
 		    "delete %pM\n", f->eth_addr);
 
 	--vxlan->addrcnt;
-	vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
+	if (do_notify)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
 
 	hlist_del_rcu(&f->hlist);
 	call_rcu(&f->rcu, vxlan_fdb_free);
@@ -865,7 +898,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EAFNOSUPPORT;
 
 	spin_lock_bh(&vxlan->hash_lock);
-	err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
+	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, src_vni, vni, ifindex, ndm->ndm_flags);
 	spin_unlock_bh(&vxlan->hash_lock);
 
@@ -899,7 +932,7 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 		goto out;
 	}
 
-	vxlan_fdb_destroy(vxlan, f);
+	vxlan_fdb_destroy(vxlan, f, true);
 
 out:
 	return 0;
@@ -1008,7 +1041,7 @@ static bool vxlan_snoop(struct net_device *dev,
 
 		/* close off race between vxlan_flush and incoming packets */
 		if (netif_running(dev))
-			vxlan_fdb_create(vxlan, src_mac, src_ip,
+			vxlan_fdb_update(vxlan, src_mac, src_ip,
 					 NUD_REACHABLE,
 					 NLM_F_EXCL|NLM_F_CREATE,
 					 vxlan->cfg.dst_port,
@@ -2366,7 +2399,7 @@ static void vxlan_cleanup(struct timer_list *t)
 					   "garbage collect %pM\n",
 					   f->eth_addr);
 				f->state = NUD_STALE;
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 			} else if (time_before(timeout, next_timer))
 				next_timer = timeout;
 		}
@@ -2417,7 +2450,7 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
 	spin_lock_bh(&vxlan->hash_lock);
 	f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
 	if (f)
-		vxlan_fdb_destroy(vxlan, f);
+		vxlan_fdb_destroy(vxlan, f, true);
 	spin_unlock_bh(&vxlan->hash_lock);
 }
 
@@ -2471,7 +2504,7 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 				continue;
 			/* the all_zeros_mac entry is deleted at vxlan_uninit */
 			if (!is_zero_ether_addr(f->eth_addr))
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 		}
 	}
 	spin_unlock_bh(&vxlan->hash_lock);
@@ -3162,6 +3195,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_dev_configure(net, dev, conf, false, extack);
@@ -3175,24 +3209,35 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 		err = vxlan_fdb_create(vxlan, all_zeros_mac,
 				       &vxlan->default_dst.remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
-				       NLM_F_EXCL | NLM_F_CREATE,
 				       vxlan->cfg.dst_port,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_ifindex,
-				       NTF_SELF);
+				       NTF_SELF, &f);
 		if (err)
 			return err;
 	}
 
 	err = register_netdevice(dev);
+	if (err)
+		goto errout;
+
+	err = rtnl_configure_link(dev, NULL);
 	if (err) {
-		vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
-		return err;
+		unregister_netdevice(dev);
+		goto errout;
 	}
 
+	/* notify default fdb entry */
+	if (f)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
+
 	list_add(&vxlan->next, &vn->vxlan_list);
 	return 0;
+errout:
+	if (f)
+		vxlan_fdb_destroy(vxlan, f, false);
+	return err;
 }
 
 static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
@@ -3427,6 +3472,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	struct vxlan_rdst old_dst;
 	struct vxlan_config conf;
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_nl2conf(tb, data,
@@ -3455,16 +3501,16 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 			err = vxlan_fdb_create(vxlan, all_zeros_mac,
 					       &dst->remote_ip,
 					       NUD_REACHABLE | NUD_PERMANENT,
-					       NLM_F_CREATE | NLM_F_APPEND,
 					       vxlan->cfg.dst_port,
 					       dst->remote_vni,
 					       dst->remote_vni,
 					       dst->remote_ifindex,
-					       NTF_SELF);
+					       NTF_SELF, &f);
 			if (err) {
 				spin_unlock_bh(&vxlan->hash_lock);
 				return err;
 			}
+			vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
 		}
 		spin_unlock_bh(&vxlan->hash_lock);
 	}
diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c
index 90a4ad9a2d08..b3a1b6f5c406 100644
--- a/drivers/net/wan/lmc/lmc_main.c
+++ b/drivers/net/wan/lmc/lmc_main.c
@@ -1362,7 +1362,7 @@ static irqreturn_t lmc_interrupt (int irq, void *dev_instance) /*fold00*/
             case 0x001:
                 printk(KERN_WARNING "%s: Master Abort (naughty)\n", dev->name);
                 break;
-            case 0x010:
+            case 0x002:
                 printk(KERN_WARNING "%s: Target Abort (not so naughty)\n", dev->name);
                 break;
             default:
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index e9c2fb318c03..836e0a47b94a 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -6058,8 +6058,19 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk)
 			   ath10k_mac_max_vht_nss(vht_mcs_mask)));
 
 	if (changed & IEEE80211_RC_BW_CHANGED) {
-		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d\n",
-			   sta->addr, bw);
+		enum wmi_phy_mode mode;
+
+		mode = chan_to_phymode(&def);
+		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d phymode %d\n",
+				sta->addr, bw, mode);
+
+		err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr,
+				WMI_PEER_PHYMODE, mode);
+		if (err) {
+			ath10k_warn(ar, "failed to update STA %pM peer phymode %d: %d\n",
+					sta->addr, mode, err);
+			goto exit;
+		}
 
 		err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr,
 						WMI_PEER_CHAN_WIDTH, bw);
@@ -6100,6 +6111,7 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk)
 				    sta->addr);
 	}
 
+exit:
 	mutex_unlock(&ar->conf_mutex);
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index b48db54e9865..d68afb65402a 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -6144,6 +6144,7 @@ enum wmi_peer_param {
 	WMI_PEER_NSS        = 0x5,
 	WMI_PEER_USE_4ADDR  = 0x6,
 	WMI_PEER_DEBUG      = 0xa,
+	WMI_PEER_PHYMODE    = 0xd,
 	WMI_PEER_DUMMY_VAR  = 0xff, /* dummy parameter for STA PS workaround */
 };
 
diff --git a/drivers/net/wireless/ath/wcn36xx/testmode.c b/drivers/net/wireless/ath/wcn36xx/testmode.c
index 1279064a3b71..51a038022c8b 100644
--- a/drivers/net/wireless/ath/wcn36xx/testmode.c
+++ b/drivers/net/wireless/ath/wcn36xx/testmode.c
@@ -1,4 +1,4 @@
-/*
+/*
  * Copyright (c) 2018, The Linux Foundation. All rights reserved.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
diff --git a/drivers/net/wireless/broadcom/brcm80211/Kconfig b/drivers/net/wireless/broadcom/brcm80211/Kconfig
index 9d99eb42d917..6acba67bca07 100644
--- a/drivers/net/wireless/broadcom/brcm80211/Kconfig
+++ b/drivers/net/wireless/broadcom/brcm80211/Kconfig
@@ -60,7 +60,6 @@ config BRCMFMAC_PCIE
 	bool "PCIE bus interface support for FullMAC driver"
 	depends on BRCMFMAC
 	depends on PCI
-	depends on HAS_DMA
 	select BRCMFMAC_PROTO_MSGBUF
 	select FW_LOADER
 	---help---
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 45928b5b8d97..4fffa6988087 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -1785,7 +1785,8 @@ brcmf_pcie_prepare_fw_request(struct brcmf_pciedev_info *devinfo)
 	fwreq->items[BRCMF_PCIE_FW_CODE].type = BRCMF_FW_TYPE_BINARY;
 	fwreq->items[BRCMF_PCIE_FW_NVRAM].type = BRCMF_FW_TYPE_NVRAM;
 	fwreq->items[BRCMF_PCIE_FW_NVRAM].flags = BRCMF_FW_REQF_OPTIONAL;
-	fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus);
+	/* NVRAM reserves PCI domain 0 for Broadcom's SDK faked bus */
+	fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus) + 1;
 	fwreq->bus_nr = devinfo->pdev->bus->number;
 
 	return fwreq;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index c99a191e8d69..a907d7b065fa 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4296,6 +4296,13 @@ void brcmf_sdio_remove(struct brcmf_sdio *bus)
 	brcmf_dbg(TRACE, "Enter\n");
 
 	if (bus) {
+		/* Stop watchdog task */
+		if (bus->watchdog_tsk) {
+			send_sig(SIGTERM, bus->watchdog_tsk, 1);
+			kthread_stop(bus->watchdog_tsk);
+			bus->watchdog_tsk = NULL;
+		}
+
 		/* De-register interrupt handler */
 		brcmf_sdiod_intr_unregister(bus->sdiodev);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index e20c30b29c03..c8ea63d02619 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -178,6 +178,17 @@ const struct iwl_cfg iwl9260_2ac_cfg = {
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
+const struct iwl_cfg iwl9260_killer_2ac_cfg = {
+	.name = "Killer (R) Wireless-AC 1550 Wireless Network Adapter (9260NGW)",
+	.fw_name_pre = IWL9260A_FW_PRE,
+	.fw_name_pre_b_or_c_step = IWL9260B_FW_PRE,
+	IWL_DEVICE_9000,
+	.ht_params = &iwl9000_ht_params,
+	.nvm_ver = IWL9000_NVM_VERSION,
+	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+};
+
 const struct iwl_cfg iwl9270_2ac_cfg = {
 	.name = "Intel(R) Dual Band Wireless AC 9270",
 	.fw_name_pre = IWL9260A_FW_PRE,
@@ -267,6 +278,34 @@ const struct iwl_cfg iwl9560_2ac_cfg_soc = {
 	.soc_latency = 5000,
 };
 
+const struct iwl_cfg iwl9560_killer_2ac_cfg_soc = {
+	.name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)",
+	.fw_name_pre = IWL9000A_FW_PRE,
+	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
+	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
+	IWL_DEVICE_9000,
+	.ht_params = &iwl9000_ht_params,
+	.nvm_ver = IWL9000_NVM_VERSION,
+	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.integrated = true,
+	.soc_latency = 5000,
+};
+
+const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc = {
+	.name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)",
+	.fw_name_pre = IWL9000A_FW_PRE,
+	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
+	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
+	IWL_DEVICE_9000,
+	.ht_params = &iwl9000_ht_params,
+	.nvm_ver = IWL9000_NVM_VERSION,
+	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.integrated = true,
+	.soc_latency = 5000,
+};
+
 const struct iwl_cfg iwl9460_2ac_cfg_shared_clk = {
 	.name = "Intel(R) Dual Band Wireless AC 9460",
 	.fw_name_pre = IWL9000A_FW_PRE,
@@ -327,6 +366,36 @@ const struct iwl_cfg iwl9560_2ac_cfg_shared_clk = {
 	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
 };
 
+const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk = {
+	.name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)",
+	.fw_name_pre = IWL9000A_FW_PRE,
+	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
+	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
+	IWL_DEVICE_9000,
+	.ht_params = &iwl9000_ht_params,
+	.nvm_ver = IWL9000_NVM_VERSION,
+	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.integrated = true,
+	.soc_latency = 5000,
+	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
+};
+
+const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk = {
+	.name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)",
+	.fw_name_pre = IWL9000A_FW_PRE,
+	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
+	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
+	IWL_DEVICE_9000,
+	.ht_params = &iwl9000_ht_params,
+	.nvm_ver = IWL9000_NVM_VERSION,
+	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.integrated = true,
+	.soc_latency = 5000,
+	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
+};
+
 MODULE_FIRMWARE(IWL9000A_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL9000B_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL9000RFB_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index c503b26793f6..84a816809723 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -551,6 +551,7 @@ extern const struct iwl_cfg iwl8275_2ac_cfg;
 extern const struct iwl_cfg iwl4165_2ac_cfg;
 extern const struct iwl_cfg iwl9160_2ac_cfg;
 extern const struct iwl_cfg iwl9260_2ac_cfg;
+extern const struct iwl_cfg iwl9260_killer_2ac_cfg;
 extern const struct iwl_cfg iwl9270_2ac_cfg;
 extern const struct iwl_cfg iwl9460_2ac_cfg;
 extern const struct iwl_cfg iwl9560_2ac_cfg;
@@ -558,10 +559,14 @@ extern const struct iwl_cfg iwl9460_2ac_cfg_soc;
 extern const struct iwl_cfg iwl9461_2ac_cfg_soc;
 extern const struct iwl_cfg iwl9462_2ac_cfg_soc;
 extern const struct iwl_cfg iwl9560_2ac_cfg_soc;
+extern const struct iwl_cfg iwl9560_killer_2ac_cfg_soc;
+extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc;
 extern const struct iwl_cfg iwl9460_2ac_cfg_shared_clk;
 extern const struct iwl_cfg iwl9461_2ac_cfg_shared_clk;
 extern const struct iwl_cfg iwl9462_2ac_cfg_shared_clk;
 extern const struct iwl_cfg iwl9560_2ac_cfg_shared_clk;
+extern const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk;
+extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk;
 extern const struct iwl_cfg iwl22000_2ac_cfg_hr;
 extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb;
 extern const struct iwl_cfg iwl22000_2ac_cfg_jf;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 38234bda9017..8520523b91b4 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -545,6 +545,9 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x2526, 0x1210, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x1410, iwl9270_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x1420, iwl9460_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x2526, 0x1550, iwl9260_killer_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x2526, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x2526, 0x1552, iwl9560_killer_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x1610, iwl9270_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x2030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x2034, iwl9560_2ac_cfg_soc)},
@@ -554,6 +557,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)},
@@ -578,6 +582,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x2720, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2720, 0x1030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2720, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x2720, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x2720, 0x1552, iwl9560_killer_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_cfg)},
@@ -604,6 +610,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x30DC, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_cfg_soc)},
@@ -630,6 +638,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x31DC, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x31DC, 0x1030, iwl9560_2ac_cfg_shared_clk)},
 	{IWL_PCI_DEVICE(0x31DC, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x31DC, 0x1551, iwl9560_killer_s_2ac_cfg_shared_clk)},
+	{IWL_PCI_DEVICE(0x31DC, 0x1552, iwl9560_killer_2ac_cfg_shared_clk)},
 	{IWL_PCI_DEVICE(0x31DC, 0x2030, iwl9560_2ac_cfg_shared_clk)},
 	{IWL_PCI_DEVICE(0x31DC, 0x2034, iwl9560_2ac_cfg_shared_clk)},
 	{IWL_PCI_DEVICE(0x31DC, 0x4030, iwl9560_2ac_cfg_shared_clk)},
@@ -656,6 +666,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x34F0, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x34F0, 0x1030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x34F0, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x34F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x34F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x34F0, 0x2030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x34F0, 0x2034, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x34F0, 0x4030, iwl9560_2ac_cfg_soc)},
@@ -682,6 +694,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x3DF0, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x3DF0, 0x1030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x3DF0, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_cfg_soc)},
@@ -708,6 +722,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x43F0, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x43F0, 0x1030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x43F0, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x43F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x43F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_cfg_soc)},
@@ -743,6 +759,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x9DF0, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x9DF0, 0x1030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x9DF0, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x9DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x9DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x9DF0, 0x2010, iwl9460_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x9DF0, 0x2030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x9DF0, 0x2034, iwl9560_2ac_cfg_soc)},
@@ -771,6 +789,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0xA0F0, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0xA0F0, 0x1030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA0F0, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_cfg_soc)},
@@ -797,6 +817,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0xA370, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0xA370, 0x1030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA370, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0xA370, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0xA370, 0x1552, iwl9560_killer_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA370, 0x2030, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA370, 0x2034, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA370, 0x4030, iwl9560_2ac_cfg_soc)},
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index 6e3cf9817730..88f4c89f89ba 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -644,11 +644,6 @@ static void mwifiex_usb_disconnect(struct usb_interface *intf)
 					 MWIFIEX_FUNC_SHUTDOWN);
 	}
 
-	if (adapter->workqueue)
-		flush_workqueue(adapter->workqueue);
-
-	mwifiex_usb_free(card);
-
 	mwifiex_dbg(adapter, FATAL,
 		    "%s: removing card\n", __func__);
 	mwifiex_remove_card(adapter);
@@ -1356,6 +1351,8 @@ static void mwifiex_unregister_dev(struct mwifiex_adapter *adapter)
 {
 	struct usb_card_rec *card = (struct usb_card_rec *)adapter->card;
 
+	mwifiex_usb_free(card);
+
 	mwifiex_usb_cleanup_tx_aggr(adapter);
 
 	card->adapter = NULL;
diff --git a/drivers/net/wireless/mediatek/mt7601u/phy.c b/drivers/net/wireless/mediatek/mt7601u/phy.c
index 9d2f9a776ef1..b804abd464ae 100644
--- a/drivers/net/wireless/mediatek/mt7601u/phy.c
+++ b/drivers/net/wireless/mediatek/mt7601u/phy.c
@@ -986,13 +986,15 @@ static void mt7601u_agc_tune(struct mt7601u_dev *dev)
 	 */
 	spin_lock_bh(&dev->con_mon_lock);
 	avg_rssi = ewma_rssi_read(&dev->avg_rssi);
-	WARN_ON_ONCE(avg_rssi == 0);
+	spin_unlock_bh(&dev->con_mon_lock);
+	if (avg_rssi == 0)
+		return;
+
 	avg_rssi = -avg_rssi;
 	if (avg_rssi <= -70)
 		val -= 0x20;
 	else if (avg_rssi <= -60)
 		val -= 0x10;
-	spin_unlock_bh(&dev->con_mon_lock);
 
 	if (val != mt7601u_bbp_rr(dev, 66))
 		mt7601u_bbp_wr(dev, 66, val);
diff --git a/drivers/net/wireless/quantenna/qtnfmac/Kconfig b/drivers/net/wireless/quantenna/qtnfmac/Kconfig
index 025fa6018550..8d1492a90bd1 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/Kconfig
+++ b/drivers/net/wireless/quantenna/qtnfmac/Kconfig
@@ -7,7 +7,7 @@ config QTNFMAC
 config QTNFMAC_PEARL_PCIE
 	tristate "Quantenna QSR10g PCIe support"
 	default n
-	depends on HAS_DMA && PCI && CFG80211
+	depends on PCI && CFG80211
 	select QTNFMAC
 	select FW_LOADER
 	select CRC32
diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index 220e2b710208..ae0ca8006849 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -654,8 +654,7 @@ qtnf_disconnect(struct wiphy *wiphy, struct net_device *dev,
 	vif = qtnf_mac_get_base_vif(mac);
 	if (!vif) {
 		pr_err("MAC%u: primary VIF is not configured\n", mac->macid);
-		ret = -EFAULT;
-		goto out;
+		return -EFAULT;
 	}
 
 	if (vif->wdev.iftype != NL80211_IFTYPE_STATION) {
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index 39c817eddd78..54c9f6ab0c8c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -484,18 +484,21 @@ static void _rtl_init_deferred_work(struct ieee80211_hw *hw)
 
 }
 
-void rtl_deinit_deferred_work(struct ieee80211_hw *hw)
+void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	del_timer_sync(&rtlpriv->works.watchdog_timer);
 
-	cancel_delayed_work(&rtlpriv->works.watchdog_wq);
-	cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq);
-	cancel_delayed_work(&rtlpriv->works.ps_work);
-	cancel_delayed_work(&rtlpriv->works.ps_rfon_wq);
-	cancel_delayed_work(&rtlpriv->works.fwevt_wq);
-	cancel_delayed_work(&rtlpriv->works.c2hcmd_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.watchdog_wq);
+	if (ips_wq)
+		cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq);
+	else
+		cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.ps_work);
+	cancel_delayed_work_sync(&rtlpriv->works.ps_rfon_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.fwevt_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.c2hcmd_wq);
 }
 EXPORT_SYMBOL_GPL(rtl_deinit_deferred_work);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h
index 912f205779c3..a7ae40eaa3cd 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.h
+++ b/drivers/net/wireless/realtek/rtlwifi/base.h
@@ -121,7 +121,7 @@ void rtl_init_rfkill(struct ieee80211_hw *hw);
 void rtl_deinit_rfkill(struct ieee80211_hw *hw);
 
 void rtl_watch_dog_timer_callback(struct timer_list *t);
-void rtl_deinit_deferred_work(struct ieee80211_hw *hw);
+void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq);
 
 bool rtl_action_proc(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx);
 int rtlwifi_rate_mapping(struct ieee80211_hw *hw, bool isht,
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index cfea57efa7f4..4bf7967590ca 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -130,7 +130,6 @@ found_alt:
 		       firmware->size);
 		rtlpriv->rtlhal.wowlan_fwsize = firmware->size;
 	}
-	rtlpriv->rtlhal.fwsize = firmware->size;
 	release_firmware(firmware);
 }
 
@@ -196,7 +195,7 @@ static void rtl_op_stop(struct ieee80211_hw *hw)
 		/* reset sec info */
 		rtl_cam_reset_sec_info(hw);
 
-		rtl_deinit_deferred_work(hw);
+		rtl_deinit_deferred_work(hw, false);
 	}
 	rtlpriv->intf_ops->adapter_stop(hw);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index ae13bcfb3bf0..5d1fda16fc8c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -2377,7 +2377,7 @@ void rtl_pci_disconnect(struct pci_dev *pdev)
 		ieee80211_unregister_hw(hw);
 		rtlmac->mac80211_registered = 0;
 	} else {
-		rtl_deinit_deferred_work(hw);
+		rtl_deinit_deferred_work(hw, false);
 		rtlpriv->intf_ops->adapter_stop(hw);
 	}
 	rtlpriv->cfg->ops->disable_interrupt(hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c
index 71af24e2e051..479a4cfc245d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/ps.c
+++ b/drivers/net/wireless/realtek/rtlwifi/ps.c
@@ -71,7 +71,7 @@ bool rtl_ps_disable_nic(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	/*<1> Stop all timer */
-	rtl_deinit_deferred_work(hw);
+	rtl_deinit_deferred_work(hw, true);
 
 	/*<2> Disable Interrupt */
 	rtlpriv->cfg->ops->disable_interrupt(hw);
@@ -292,7 +292,7 @@ void rtl_ips_nic_on(struct ieee80211_hw *hw)
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	enum rf_pwrstate rtstate;
 
-	cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq);
 
 	mutex_lock(&rtlpriv->locks.ips_mutex);
 	if (ppsc->inactiveps) {
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index f9faffc498bc..2ac5004d7a40 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -1132,7 +1132,7 @@ void rtl_usb_disconnect(struct usb_interface *intf)
 		ieee80211_unregister_hw(hw);
 		rtlmac->mac80211_registered = 0;
 	} else {
-		rtl_deinit_deferred_work(hw);
+		rtl_deinit_deferred_work(hw, false);
 		rtlpriv->intf_ops->adapter_stop(hw);
 	}
 	/*deinit rfkill */
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 922ce0abf5cf..9dd2ca62d84a 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -87,6 +87,7 @@ struct netfront_cb {
 /* IRQ name is queue name with "-tx" or "-rx" appended */
 #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
 
+static DECLARE_WAIT_QUEUE_HEAD(module_load_q);
 static DECLARE_WAIT_QUEUE_HEAD(module_unload_q);
 
 struct netfront_stats {
@@ -893,7 +894,6 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 				  struct sk_buff *skb,
 				  struct sk_buff_head *list)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *nskb;
 
@@ -902,15 +902,16 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 			RING_GET_RESPONSE(&queue->rx, ++cons);
 		skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
 
-		if (shinfo->nr_frags == MAX_SKB_FRAGS) {
+		if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
 			unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 
 			BUG_ON(pull_to <= skb_headlen(skb));
 			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 		}
-		BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
+		BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS);
 
-		skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag),
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				skb_frag_page(nfrag),
 				rx->offset, rx->status, PAGE_SIZE);
 
 		skb_shinfo(nskb)->nr_frags = 0;
@@ -1330,6 +1331,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	netif_carrier_off(netdev);
 
 	xenbus_switch_state(dev, XenbusStateInitialising);
+	wait_event(module_load_q,
+			   xenbus_read_driver_state(dev->otherend) !=
+			   XenbusStateClosed &&
+			   xenbus_read_driver_state(dev->otherend) !=
+			   XenbusStateUnknown);
 	return netdev;
 
  exit:
@@ -1810,7 +1816,7 @@ static int talk_to_netback(struct xenbus_device *dev,
 	err = xen_net_read_mac(dev, info->netdev->dev_addr);
 	if (err) {
 		xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
-		goto out;
+		goto out_unlocked;
 	}
 
 	rtnl_lock();
@@ -1925,6 +1931,7 @@ abort_transaction_no_dev_fatal:
 	xennet_destroy_queues(info);
  out:
 	rtnl_unlock();
+out_unlocked:
 	device_unregister(&dev->dev);
 	return err;
 }
@@ -1950,10 +1957,6 @@ static int xennet_connect(struct net_device *dev)
 	/* talk_to_netback() sets the correct number of queues */
 	num_queues = dev->real_num_tx_queues;
 
-	rtnl_lock();
-	netdev_update_features(dev);
-	rtnl_unlock();
-
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
 		err = register_netdev(dev);
 		if (err) {
@@ -1963,6 +1966,10 @@ static int xennet_connect(struct net_device *dev)
 		}
 	}
 
+	rtnl_lock();
+	netdev_update_features(dev);
+	rtnl_unlock();
+
 	/*
 	 * All public and private state should now be sane.  Get
 	 * ready to start sending and receiving packets and give the driver
diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index d5553c47014f..5d823e965883 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -74,7 +74,7 @@ static void pn533_recv_response(struct urb *urb)
 	struct sk_buff *skb = NULL;
 
 	if (!urb->status) {
-		skb = alloc_skb(urb->actual_length, GFP_KERNEL);
+		skb = alloc_skb(urb->actual_length, GFP_ATOMIC);
 		if (!skb) {
 			nfc_err(&phy->udev->dev, "failed to alloc memory\n");
 		} else {
@@ -186,7 +186,7 @@ static int pn533_usb_send_frame(struct pn533 *dev,
 
 	if (dev->protocol_type == PN533_PROTO_REQ_RESP) {
 		/* request for response for sent packet directly */
-		rc = pn533_submit_urb_for_response(phy, GFP_ATOMIC);
+		rc = pn533_submit_urb_for_response(phy, GFP_KERNEL);
 		if (rc)
 			goto error;
 	} else if (dev->protocol_type == PN533_PROTO_REQ_ACK_RESP) {
diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c
index a59b6c4bb5b8..ad3d17c42e23 100644
--- a/drivers/nubus/bus.c
+++ b/drivers/nubus/bus.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2017 Finn Thain
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/nubus.h>
 #include <linux/seq_file.h>
@@ -93,6 +94,8 @@ int nubus_device_register(struct nubus_board *board)
 	board->dev.release = nubus_device_release;
 	board->dev.bus = &nubus_bus_type;
 	dev_set_name(&board->dev, "slot.%X", board->slot);
+	board->dev.dma_mask = &board->dev.coherent_dma_mask;
+	dma_set_mask(&board->dev, DMA_BIT_MASK(32));
 	return device_register(&board->dev);
 }
 
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 85de8053aa34..0360c015f658 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1423,11 +1423,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 
 static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 			struct page *page, unsigned int len, unsigned int off,
-			bool is_write, sector_t sector)
+			unsigned int op, sector_t sector)
 {
 	int ret;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		ret = btt_read_pg(btt, bip, page, off, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -1464,7 +1464,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 		}
 
 		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
-				  op_is_write(bio_op(bio)), iter.bi_sector);
+				  bio_op(bio), iter.bi_sector);
 		if (err) {
 			dev_err(&btt->nd_btt->dev,
 					"io error in %s sector %lld, len %d,\n",
@@ -1483,16 +1483,16 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,
-		struct page *page, bool is_write)
+		struct page *page, unsigned int op)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 	int rc;
 	unsigned int len;
 
 	len = hpage_nr_pages(page) * PAGE_SIZE;
-	rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector);
+	rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector);
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return rc;
 }
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 2e96b34bc936..fb667bf469c7 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -278,6 +278,7 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 			return -EIO;
 		if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0)
 			return -EIO;
+		return 0;
 	}
 
 	if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 32e0364b48b9..6ee7fd7e4bbd 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -396,16 +396,15 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
 		return false;
 
 	*start = jiffies;
-	generic_start_io_acct(disk->queue, bio_data_dir(bio),
-			      bio_sectors(bio), &disk->part0);
+	generic_start_io_acct(disk->queue, bio_op(bio), bio_sectors(bio),
+			      &disk->part0);
 	return true;
 }
 static inline void nd_iostat_end(struct bio *bio, unsigned long start)
 {
 	struct gendisk *disk = bio->bi_disk;
 
-	generic_end_io_acct(disk->queue, bio_data_dir(bio), &disk->part0,
-				start);
+	generic_end_io_acct(disk->queue, bio_op(bio), &disk->part0, start);
 }
 static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector,
 		unsigned int len)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 68940356cad3..dd17acd8fe68 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -120,7 +120,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 }
 
 static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	blk_status_t rc = BLK_STS_OK;
@@ -131,7 +131,7 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		if (unlikely(bad_pmem))
 			rc = BLK_STS_IOERR;
 		else {
@@ -180,8 +180,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, op_is_write(bio_op(bio)),
-				iter.bi_sector);
+				bvec.bv_offset, bio_op(bio), iter.bi_sector);
 		if (rc) {
 			bio->bi_status = rc;
 			break;
@@ -198,13 +197,13 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	blk_status_t rc;
 
 	rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
-			  0, is_write, sector);
+			  0, op, sector);
 
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
@@ -213,7 +212,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	 * caused by double completion.
 	 */
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return blk_status_to_errno(rc);
 }
@@ -414,7 +413,8 @@ static int pmem_attach_disk(struct device *dev,
 	blk_queue_logical_block_size(q, pmem_sector_size(ndns));
 	blk_queue_max_hw_sectors(q, UINT_MAX);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+	if (pmem->pfn_flags & PFN_MAP)
+		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
 	q->queuedata = pmem;
 
 	disk = alloc_disk_node(0, nid);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 46df030b2c3f..dd8ec1dd9219 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -100,6 +100,22 @@ static struct class *nvme_subsys_class;
 static void nvme_ns_remove(struct nvme_ns *ns);
 static int nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
+static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
+					   unsigned nsid);
+
+static void nvme_set_queue_dying(struct nvme_ns *ns)
+{
+	/*
+	 * Revalidating a dead namespace sets capacity to 0. This will end
+	 * buffered writers dirtying pages that can't be synced.
+	 */
+	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+		return;
+	revalidate_disk(ns->disk);
+	blk_set_queue_dying(ns->queue);
+	/* Forcibly unquiesce queues to avoid blocking dispatch */
+	blk_mq_unquiesce_queue(ns->queue);
+}
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
 {
@@ -236,7 +252,8 @@ void nvme_complete_rq(struct request *req)
 	trace_nvme_complete_rq(req);
 
 	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
-		if (nvme_req_needs_failover(req, status)) {
+		if ((req->cmd_flags & REQ_NVME_MPATH) &&
+		    blk_path_error(status)) {
 			nvme_failover_req(req);
 			return;
 		}
@@ -601,6 +618,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))
 				return BLK_STS_NOTSUPP;
 			control |= NVME_RW_PRINFO_PRACT;
+		} else if (req_op(req) == REQ_OP_WRITE) {
+			t10_pi_prepare(req, ns->pi_type);
 		}
 
 		switch (ns->pi_type) {
@@ -611,8 +630,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					NVME_RW_PRINFO_PRCHK_REF;
-			cmnd->rw.reftag = cpu_to_le32(
-					nvme_block_nr(ns, blk_rq_pos(req)));
+			cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
 			break;
 		}
 	}
@@ -622,6 +640,22 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	return 0;
 }
 
+void nvme_cleanup_cmd(struct request *req)
+{
+	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
+	    nvme_req(req)->status == 0) {
+		struct nvme_ns *ns = req->rq_disk->private_data;
+
+		t10_pi_complete(req, ns->pi_type,
+				blk_rq_bytes(req) >> ns->lba_shift);
+	}
+	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		kfree(page_address(req->special_vec.bv_page) +
+		      req->special_vec.bv_offset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
+
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd)
 {
@@ -652,10 +686,7 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 	}
 
 	cmd->common.command_id = req->tag;
-	if (ns)
-		trace_nvme_setup_nvm_cmd(req->q->id, cmd);
-	else
-		trace_nvme_setup_admin_cmd(cmd);
+	trace_nvme_setup_cmd(req, cmd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_setup_cmd);
@@ -848,9 +879,6 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
-	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
-	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 
@@ -1040,18 +1068,21 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 #define NVME_AEN_SUPPORTED \
-	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT)
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | NVME_AEN_CFG_ANA_CHANGE)
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
-	u32 result;
+	u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED;
 	int status;
 
-	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
-			ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+	if (!supported_aens)
+		return;
+
+	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens,
+			NULL, 0, &result);
 	if (status)
 		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
-			 ctrl->oaes & NVME_AEN_SUPPORTED);
+			 supported_aens);
 }
 
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
@@ -1151,19 +1182,15 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 static void nvme_update_formats(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns, *next;
-	LIST_HEAD(rm_list);
+	struct nvme_ns *ns;
 
-	down_write(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		if (ns->disk && nvme_revalidate_disk(ns->disk)) {
-			list_move_tail(&ns->list, &rm_list);
-		}
-	}
-	up_write(&ctrl->namespaces_rwsem);
+	down_read(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		if (ns->disk && nvme_revalidate_disk(ns->disk))
+			nvme_set_queue_dying(ns);
+	up_read(&ctrl->namespaces_rwsem);
 
-	list_for_each_entry_safe(ns, next, &rm_list, list)
-		nvme_ns_remove(ns);
+	nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
 }
 
 static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
@@ -1218,7 +1245,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata,
+			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len,
 			0, &cmd.result, timeout);
 	nvme_passthru_end(ctrl, effects);
 
@@ -1457,6 +1484,12 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 	set_capacity(disk, capacity);
 	nvme_config_discard(ns);
+
+	if (id->nsattr & (1 << 0))
+		set_disk_ro(disk, true);
+	else
+		set_disk_ro(disk, false);
+
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
@@ -2255,21 +2288,16 @@ out_unlock:
 	return ret;
 }
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		     u8 log_page, void *log,
-		     size_t size, u64 offset)
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset)
 {
 	struct nvme_command c = { };
 	unsigned long dwlen = size / 4 - 1;
 
 	c.get_log_page.opcode = nvme_admin_get_log_page;
-
-	if (ns)
-		c.get_log_page.nsid = cpu_to_le32(ns->head->ns_id);
-	else
-		c.get_log_page.nsid = cpu_to_le32(NVME_NSID_ALL);
-
+	c.get_log_page.nsid = cpu_to_le32(nsid);
 	c.get_log_page.lid = log_page;
+	c.get_log_page.lsp = lsp;
 	c.get_log_page.numdl = cpu_to_le16(dwlen & ((1 << 16) - 1));
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
 	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
@@ -2278,12 +2306,6 @@ int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static int nvme_get_log(struct nvme_ctrl *ctrl, u8 log_page, void *log,
-			size_t size)
-{
-	return nvme_get_log_ext(ctrl, NULL, log_page, log, size, 0);
-}
-
 static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 {
 	int ret;
@@ -2294,8 +2316,8 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 	if (!ctrl->effects)
 		return 0;
 
-	ret = nvme_get_log(ctrl, NVME_LOG_CMD_EFFECTS, ctrl->effects,
-					sizeof(*ctrl->effects));
+	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
+			ctrl->effects, sizeof(*ctrl->effects), 0);
 	if (ret) {
 		kfree(ctrl->effects);
 		ctrl->effects = NULL;
@@ -2386,6 +2408,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	nvme_set_queue_limits(ctrl, ctrl->admin_q);
 	ctrl->sgls = le32_to_cpu(id->sgls);
 	ctrl->kas = le16_to_cpu(id->kas);
+	ctrl->max_namespaces = le32_to_cpu(id->mnan);
 
 	if (id->rtd3e) {
 		/* us -> s */
@@ -2445,8 +2468,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
 	}
 
+	ret = nvme_mpath_init(ctrl, id);
 	kfree(id);
 
+	if (ret < 0)
+		return ret;
+
 	if (ctrl->apst_enabled && !prev_apst_enabled)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
@@ -2665,6 +2692,10 @@ static struct attribute *nvme_ns_id_attrs[] = {
 	&dev_attr_nguid.attr,
 	&dev_attr_eui.attr,
 	&dev_attr_nsid.attr,
+#ifdef CONFIG_NVME_MULTIPATH
+	&dev_attr_ana_grpid.attr,
+	&dev_attr_ana_state.attr,
+#endif
 	NULL,
 };
 
@@ -2687,6 +2718,14 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 		if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
 			return 0;
 	}
+#ifdef CONFIG_NVME_MULTIPATH
+	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
+		if (dev_to_disk(dev)->fops != &nvme_fops) /* per-path attr */
+			return 0;
+		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
+			return 0;
+	}
+#endif
 	return a->mode;
 }
 
@@ -3060,8 +3099,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	nvme_get_ctrl(ctrl);
 
-	kfree(id);
-
 	device_add_disk(ctrl->device, ns->disk);
 	if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_id_attr_group))
@@ -3071,8 +3108,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
 			ns->disk->disk_name);
 
-	nvme_mpath_add_disk(ns->head);
+	nvme_mpath_add_disk(ns, id);
 	nvme_fault_inject_init(ns);
+	kfree(id);
+
 	return;
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
@@ -3138,7 +3177,7 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 
 	down_write(&ctrl->namespaces_rwsem);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->head->ns_id > nsid)
+		if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags))
 			list_move_tail(&ns->list, &rm_list);
 	}
 	up_write(&ctrl->namespaces_rwsem);
@@ -3214,7 +3253,8 @@ static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 	 * raced with us in reading the log page, which could cause us to miss
 	 * updates.
 	 */
-	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
+			log_size, 0);
 	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
@@ -3331,9 +3371,9 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_LOG_FW_SLOT, log, sizeof(*log)))
-		dev_warn(ctrl->device,
-				"Get FW SLOT INFO log error\n");
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log,
+			sizeof(*log), 0))
+		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
 }
 
@@ -3379,6 +3419,13 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
 		queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
+#ifdef CONFIG_NVME_MULTIPATH
+	case NVME_AER_NOTICE_ANA:
+		if (!ctrl->ana_log_buf)
+			break;
+		queue_work(nvme_wq, &ctrl->ana_work);
+		break;
+#endif
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);
 	}
@@ -3411,6 +3458,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 
 void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 {
+	nvme_mpath_stop(ctrl);
 	nvme_stop_keep_alive(ctrl);
 	flush_work(&ctrl->async_event_work);
 	flush_work(&ctrl->scan_work);
@@ -3448,6 +3496,7 @@ static void nvme_free_ctrl(struct device *dev)
 
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 	kfree(ctrl->effects);
+	nvme_mpath_uninit(ctrl);
 
 	if (subsys) {
 		mutex_lock(&subsys->lock);
@@ -3484,6 +3533,10 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
 	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
 
+	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
+	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
+
 	ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto out;
@@ -3542,19 +3595,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 	if (ctrl->admin_q)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		/*
-		 * Revalidating a dead namespace sets capacity to 0. This will
-		 * end buffered writers dirtying pages that can't be synced.
-		 */
-		if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
-			continue;
-		revalidate_disk(ns->disk);
-		blk_set_queue_dying(ns->queue);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		nvme_set_queue_dying(ns);
 
-		/* Forcibly unquiesce queues to avoid blocking dispatch */
-		blk_mq_unquiesce_queue(ns->queue);
-	}
 	up_read(&ctrl->namespaces_rwsem);
 }
 EXPORT_SYMBOL_GPL(nvme_kill_queues);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 903eb4545e26..206d63cb1afc 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -474,7 +474,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
 
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
 {
-	if (ctrl->opts->max_reconnects != -1 &&
+	if (ctrl->opts->max_reconnects == -1 ||
 	    ctrl->nr_reconnects < ctrl->opts->max_reconnects)
 		return true;
 
@@ -539,14 +539,18 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 /*
  * For something we're not in a state to send to the device the default action
  * is to busy it and retry it after the controller state is recovered.  However,
- * anything marked for failfast or nvme multipath is immediately failed.
+ * if the controller is deleting or if anything is marked for failfast or
+ * nvme multipath it is immediately failed.
  *
  * Note: commands used to initialize the controller will be marked for failfast.
  * Note: nvme cli/ioctl commands are marked for failfast.
  */
-blk_status_t nvmf_fail_nonready_command(struct request *rq)
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq)
 {
-	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+	if (ctrl->state != NVME_CTRL_DELETING &&
+	    ctrl->state != NVME_CTRL_DEAD &&
+	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
 	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
 	return BLK_STS_IOERR;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index e1818a27aa2d..aa2fdb2a2e8f 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -162,7 +162,8 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
-blk_status_t nvmf_fail_nonready_command(struct request *rq);
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq);
 bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live);
 
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 41d45a1b5c62..611e70cae754 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1737,6 +1737,7 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq,
 	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;
 	struct nvme_fc_queue *queue = &ctrl->queues[queue_idx];
 
+	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	return __nvme_fc_init_request(ctrl, queue, op, rq, queue->rqcnt++);
 }
 
@@ -2272,7 +2273,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE ||
 	    !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(rq);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	ret = nvme_setup_cmd(ns, rq, sqe);
 	if (ret)
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 41279da799ed..6fe5923c95d4 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -414,12 +414,6 @@ static int nvme_nvm_setup_20(struct nvme_nvm_id20 *id,
 	/* Set compacted version for upper layers */
 	geo->version = NVM_OCSSD_SPEC_20;
 
-	if (!(geo->major_ver_id == 2 && geo->minor_ver_id == 0)) {
-		pr_err("nvm: OCSSD version not supported (v%d.%d)\n",
-				geo->major_ver_id, geo->minor_ver_id);
-		return -EINVAL;
-	}
-
 	geo->num_ch = le16_to_cpu(id->num_grp);
 	geo->num_lun = le16_to_cpu(id->num_pu);
 	geo->all_luns = geo->num_ch * geo->num_lun;
@@ -583,7 +577,13 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	struct ppa_addr ppa;
 	size_t left = nchks * sizeof(struct nvme_nvm_chk_meta);
 	size_t log_pos, offset, len;
-	int ret, i;
+	int ret, i, max_len;
+
+	/*
+	 * limit requests to maximum 256K to avoid issuing arbitrary large
+	 * requests when the device does not specific a maximum transfer size.
+	 */
+	max_len = min_t(unsigned int, ctrl->max_hw_sectors << 9, 256 * 1024);
 
 	/* Normalize lba address space to obtain log offset */
 	ppa.ppa = slba;
@@ -596,10 +596,11 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	offset = log_pos * sizeof(struct nvme_nvm_chk_meta);
 
 	while (left) {
-		len = min_t(unsigned int, left, ctrl->max_hw_sectors << 9);
+		len = min_t(unsigned int, left, max_len);
 
-		ret = nvme_get_log_ext(ctrl, ns, NVME_NVM_LOG_REPORT_CHUNK,
-				dev_meta, len, offset);
+		ret = nvme_get_log(ctrl, ns->head->ns_id,
+				NVME_NVM_LOG_REPORT_CHUNK, 0, dev_meta, len,
+				offset);
 		if (ret) {
 			dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
 			break;
@@ -662,12 +663,10 @@ static struct request *nvme_nvm_alloc_request(struct request_queue *q,
 
 	rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
 
-	if (rqd->bio) {
+	if (rqd->bio)
 		blk_init_request_from_bio(rq, rqd->bio);
-	} else {
+	else
 		rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
-		rq->__data_len = 0;
-	}
 
 	return rq;
 }
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 1ffd3e8b13a1..5a9562881d4e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017 Christoph Hellwig.
+ * Copyright (c) 2017-2018 Christoph Hellwig.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,11 @@ module_param(multipath, bool, 0444);
 MODULE_PARM_DESC(multipath,
 	"turn on native support for multiple controllers per subsystem");
 
+inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+	return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
+}
+
 /*
  * If multipathing is enabled we need to always use the subsystem instance
  * number for numbering our devices to avoid conflicts between subsystems that
@@ -45,6 +50,7 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
+	u16 status = nvme_req(req)->status;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ns->head->requeue_lock, flags);
@@ -52,15 +58,35 @@ void nvme_failover_req(struct request *req)
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
 	blk_mq_end_request(req, 0);
 
-	nvme_reset_ctrl(ns->ctrl);
-	kblockd_schedule_work(&ns->head->requeue_work);
-}
+	switch (status & 0x7ff) {
+	case NVME_SC_ANA_TRANSITION:
+	case NVME_SC_ANA_INACCESSIBLE:
+	case NVME_SC_ANA_PERSISTENT_LOSS:
+		/*
+		 * If we got back an ANA error we know the controller is alive,
+		 * but not ready to serve this namespaces.  The spec suggests
+		 * we should update our general state here, but due to the fact
+		 * that the admin and I/O queues are not serialized that is
+		 * fundamentally racy.  So instead just clear the current path,
+		 * mark the the path as pending and kick of a re-read of the ANA
+		 * log page ASAP.
+		 */
+		nvme_mpath_clear_current_path(ns);
+		if (ns->ctrl->ana_log_buf) {
+			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+			queue_work(nvme_wq, &ns->ctrl->ana_work);
+		}
+		break;
+	default:
+		/*
+		 * Reset the controller for any non-ANA error as we don't know
+		 * what caused the error.
+		 */
+		nvme_reset_ctrl(ns->ctrl);
+		break;
+	}
 
-bool nvme_req_needs_failover(struct request *req, blk_status_t error)
-{
-	if (!(req->cmd_flags & REQ_NVME_MPATH))
-		return false;
-	return blk_path_error(error);
+	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
@@ -75,25 +101,51 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 	up_read(&ctrl->namespaces_rwsem);
 }
 
+static const char *nvme_ana_state_names[] = {
+	[0]				= "invalid state",
+	[NVME_ANA_OPTIMIZED]		= "optimized",
+	[NVME_ANA_NONOPTIMIZED]		= "non-optimized",
+	[NVME_ANA_INACCESSIBLE]		= "inaccessible",
+	[NVME_ANA_PERSISTENT_LOSS]	= "persistent-loss",
+	[NVME_ANA_CHANGE]		= "change",
+};
+
 static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head)
 {
-	struct nvme_ns *ns;
+	struct nvme_ns *ns, *fallback = NULL;
 
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
-		if (ns->ctrl->state == NVME_CTRL_LIVE) {
+		if (ns->ctrl->state != NVME_CTRL_LIVE ||
+		    test_bit(NVME_NS_ANA_PENDING, &ns->flags))
+			continue;
+		switch (ns->ana_state) {
+		case NVME_ANA_OPTIMIZED:
 			rcu_assign_pointer(head->current_path, ns);
 			return ns;
+		case NVME_ANA_NONOPTIMIZED:
+			fallback = ns;
+			break;
+		default:
+			break;
 		}
 	}
 
-	return NULL;
+	if (fallback)
+		rcu_assign_pointer(head->current_path, fallback);
+	return fallback;
+}
+
+static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
+{
+	return ns->ctrl->state == NVME_CTRL_LIVE &&
+		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
 inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 {
 	struct nvme_ns *ns = srcu_dereference(head->current_path, &head->srcu);
 
-	if (unlikely(!ns || ns->ctrl->state != NVME_CTRL_LIVE))
+	if (unlikely(!ns || !nvme_path_is_optimized(ns)))
 		ns = __nvme_find_path(head);
 	return ns;
 }
@@ -142,7 +194,7 @@ static bool nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc)
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = srcu_dereference(head->current_path, &head->srcu);
-	if (likely(ns && ns->ctrl->state == NVME_CTRL_LIVE))
+	if (likely(ns && nvme_path_is_optimized(ns)))
 		found = ns->queue->poll_fn(q, qc);
 	srcu_read_unlock(&head->srcu, srcu_idx);
 	return found;
@@ -176,6 +228,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	struct request_queue *q;
 	bool vwc = false;
 
+	mutex_init(&head->lock);
 	bio_list_init(&head->requeue_list);
 	spin_lock_init(&head->requeue_lock);
 	INIT_WORK(&head->requeue_work, nvme_requeue_work);
@@ -220,29 +273,232 @@ out:
 	return -ENOMEM;
 }
 
-void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static void nvme_mpath_set_live(struct nvme_ns *ns)
 {
+	struct nvme_ns_head *head = ns->head;
+
+	lockdep_assert_held(&ns->head->lock);
+
 	if (!head->disk)
 		return;
 
-	mutex_lock(&head->subsys->lock);
 	if (!(head->disk->flags & GENHD_FL_UP)) {
 		device_add_disk(&head->subsys->dev, head->disk);
 		if (sysfs_create_group(&disk_to_dev(head->disk)->kobj,
 				&nvme_ns_id_attr_group))
-			pr_warn("%s: failed to create sysfs group for identification\n",
-				head->disk->disk_name);
+			dev_warn(&head->subsys->dev,
+				 "failed to create id group.\n");
+	}
+
+	kblockd_schedule_work(&ns->head->requeue_work);
+}
+
+static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
+		int (*cb)(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *,
+			void *))
+{
+	void *base = ctrl->ana_log_buf;
+	size_t offset = sizeof(struct nvme_ana_rsp_hdr);
+	int error, i;
+
+	lockdep_assert_held(&ctrl->ana_lock);
+
+	for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) {
+		struct nvme_ana_group_desc *desc = base + offset;
+		u32 nr_nsids = le32_to_cpu(desc->nnsids);
+		size_t nsid_buf_size = nr_nsids * sizeof(__le32);
+
+		if (WARN_ON_ONCE(desc->grpid == 0))
+			return -EINVAL;
+		if (WARN_ON_ONCE(le32_to_cpu(desc->grpid) > ctrl->anagrpmax))
+			return -EINVAL;
+		if (WARN_ON_ONCE(desc->state == 0))
+			return -EINVAL;
+		if (WARN_ON_ONCE(desc->state > NVME_ANA_CHANGE))
+			return -EINVAL;
+
+		offset += sizeof(*desc);
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - nsid_buf_size))
+			return -EINVAL;
+
+		error = cb(ctrl, desc, data);
+		if (error)
+			return error;
+
+		offset += nsid_buf_size;
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static inline bool nvme_state_is_live(enum nvme_ana_state state)
+{
+	return state == NVME_ANA_OPTIMIZED || state == NVME_ANA_NONOPTIMIZED;
+}
+
+static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
+		struct nvme_ns *ns)
+{
+	enum nvme_ana_state old;
+
+	mutex_lock(&ns->head->lock);
+	old = ns->ana_state;
+	ns->ana_grpid = le32_to_cpu(desc->grpid);
+	ns->ana_state = desc->state;
+	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
+
+	if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old))
+		nvme_mpath_set_live(ns);
+	mutex_unlock(&ns->head->lock);
+}
+
+static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
+		struct nvme_ana_group_desc *desc, void *data)
+{
+	u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
+	unsigned *nr_change_groups = data;
+	struct nvme_ns *ns;
+
+	dev_info(ctrl->device, "ANA group %d: %s.\n",
+			le32_to_cpu(desc->grpid),
+			nvme_ana_state_names[desc->state]);
+
+	if (desc->state == NVME_ANA_CHANGE)
+		(*nr_change_groups)++;
+
+	if (!nr_nsids)
+		return 0;
+
+	down_write(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		if (ns->head->ns_id != le32_to_cpu(desc->nsids[n]))
+			continue;
+		nvme_update_ns_ana_state(desc, ns);
+		if (++n == nr_nsids)
+			break;
+	}
+	up_write(&ctrl->namespaces_rwsem);
+	WARN_ON_ONCE(n < nr_nsids);
+	return 0;
+}
+
+static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only)
+{
+	u32 nr_change_groups = 0;
+	int error;
+
+	mutex_lock(&ctrl->ana_lock);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA,
+			groups_only ? NVME_ANA_LOG_RGO : 0,
+			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
+	if (error) {
+		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
+		goto out_unlock;
+	}
+
+	error = nvme_parse_ana_log(ctrl, &nr_change_groups,
+			nvme_update_ana_state);
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * In theory we should have an ANATT timer per group as they might enter
+	 * the change state at different times.  But that is a lot of overhead
+	 * just to protect against a target that keeps entering new changes
+	 * states while never finishing previous ones.  But we'll still
+	 * eventually time out once all groups are in change state, so this
+	 * isn't a big deal.
+	 *
+	 * We also double the ANATT value to provide some slack for transports
+	 * or AEN processing overhead.
+	 */
+	if (nr_change_groups)
+		mod_timer(&ctrl->anatt_timer, ctrl->anatt * HZ * 2 + jiffies);
+	else
+		del_timer_sync(&ctrl->anatt_timer);
+out_unlock:
+	mutex_unlock(&ctrl->ana_lock);
+	return error;
+}
+
+static void nvme_ana_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
+
+	nvme_read_ana_log(ctrl, false);
+}
+
+static void nvme_anatt_timeout(struct timer_list *t)
+{
+	struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
+
+	dev_info(ctrl->device, "ANATT timeout, resetting controller.\n");
+	nvme_reset_ctrl(ctrl);
+}
+
+void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+	if (!nvme_ctrl_use_ana(ctrl))
+		return;
+	del_timer_sync(&ctrl->anatt_timer);
+	cancel_work_sync(&ctrl->ana_work);
+}
+
+static ssize_t ana_grpid_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	return sprintf(buf, "%d\n", nvme_get_ns_from_dev(dev)->ana_grpid);
+}
+DEVICE_ATTR_RO(ana_grpid);
+
+static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+
+	return sprintf(buf, "%s\n", nvme_ana_state_names[ns->ana_state]);
+}
+DEVICE_ATTR_RO(ana_state);
+
+static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
+		struct nvme_ana_group_desc *desc, void *data)
+{
+	struct nvme_ns *ns = data;
+
+	if (ns->ana_grpid == le32_to_cpu(desc->grpid)) {
+		nvme_update_ns_ana_state(desc, ns);
+		return -ENXIO; /* just break out of the loop */
+	}
+
+	return 0;
+}
+
+void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	if (nvme_ctrl_use_ana(ns->ctrl)) {
+		mutex_lock(&ns->ctrl->ana_lock);
+		ns->ana_grpid = le32_to_cpu(id->anagrpid);
+		nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state);
+		mutex_unlock(&ns->ctrl->ana_lock);
+	} else {
+		mutex_lock(&ns->head->lock);
+		ns->ana_state = NVME_ANA_OPTIMIZED; 
+		nvme_mpath_set_live(ns);
+		mutex_unlock(&ns->head->lock);
 	}
-	mutex_unlock(&head->subsys->lock);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
-			   &nvme_ns_id_attr_group);
-	del_gendisk(head->disk);
+	if (head->disk->flags & GENHD_FL_UP) {
+		sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
+				   &nvme_ns_id_attr_group);
+		del_gendisk(head->disk);
+	}
 	blk_set_queue_dying(head->disk->queue);
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
@@ -250,3 +506,52 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	blk_cleanup_queue(head->disk->queue);
 	put_disk(head->disk);
 }
+
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+	int error;
+
+	if (!nvme_ctrl_use_ana(ctrl))
+		return 0;
+
+	ctrl->anacap = id->anacap;
+	ctrl->anatt = id->anatt;
+	ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);
+	ctrl->anagrpmax = le32_to_cpu(id->anagrpmax);
+
+	mutex_init(&ctrl->ana_lock);
+	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
+	ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
+		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc);
+	if (!(ctrl->anacap & (1 << 6)))
+		ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
+
+	if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
+		dev_err(ctrl->device,
+			"ANA log page size (%zd) larger than MDTS (%d).\n",
+			ctrl->ana_log_size,
+			ctrl->max_hw_sectors << SECTOR_SHIFT);
+		dev_err(ctrl->device, "disabling ANA support.\n");
+		return 0;
+	}
+
+	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
+	if (!ctrl->ana_log_buf)
+		goto out;
+
+	error = nvme_read_ana_log(ctrl, true);
+	if (error)
+		goto out_free_ana_log_buf;
+	return 0;
+out_free_ana_log_buf:
+	kfree(ctrl->ana_log_buf);
+out:
+	return -ENOMEM;
+}
+
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+	kfree(ctrl->ana_log_buf);
+}
+
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 0c4a33df3b2f..bb4a2003c097 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -102,6 +102,7 @@ struct nvme_request {
 	u8			retries;
 	u8			flags;
 	u16			status;
+	struct nvme_ctrl	*ctrl;
 };
 
 /*
@@ -119,6 +120,13 @@ static inline struct nvme_request *nvme_req(struct request *req)
 	return blk_mq_rq_to_pdu(req);
 }
 
+static inline u16 nvme_req_qid(struct request *req)
+{
+	if (!req->rq_disk)
+		return 0;
+	return blk_mq_unique_tag_to_hwq(blk_mq_unique_tag(req)) + 1;
+}
+
 /* The below value is the specific amount of delay needed before checking
  * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the
  * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
@@ -175,6 +183,7 @@ struct nvme_ctrl {
 	u16 oacs;
 	u16 nssa;
 	u16 nr_streams;
+	u32 max_namespaces;
 	atomic_t abort_limit;
 	u8 vwc;
 	u32 vs;
@@ -197,6 +206,19 @@ struct nvme_ctrl {
 	struct work_struct fw_act_work;
 	unsigned long events;
 
+#ifdef CONFIG_NVME_MULTIPATH
+	/* asymmetric namespace access: */
+	u8 anacap;
+	u8 anatt;
+	u32 anagrpmax;
+	u32 nanagrpid;
+	struct mutex ana_lock;
+	struct nvme_ana_rsp_hdr *ana_log_buf;
+	size_t ana_log_size;
+	struct timer_list anatt_timer;
+	struct work_struct ana_work;
+#endif
+
 	/* Power saving configuration */
 	u64 ps_max_latency_us;
 	bool apst_enabled;
@@ -261,6 +283,7 @@ struct nvme_ns_head {
 	struct bio_list		requeue_list;
 	spinlock_t		requeue_lock;
 	struct work_struct	requeue_work;
+	struct mutex		lock;
 #endif
 	struct list_head	list;
 	struct srcu_struct      srcu;
@@ -287,6 +310,10 @@ struct nvme_ns {
 	struct nvme_ctrl *ctrl;
 	struct request_queue *queue;
 	struct gendisk *disk;
+#ifdef CONFIG_NVME_MULTIPATH
+	enum nvme_ana_state ana_state;
+	u32 ana_grpid;
+#endif
 	struct list_head siblings;
 	struct nvm_dev *ndev;
 	struct kref kref;
@@ -299,8 +326,9 @@ struct nvme_ns {
 	bool ext;
 	u8 pi_type;
 	unsigned long flags;
-#define NVME_NS_REMOVING 0
-#define NVME_NS_DEAD     1
+#define NVME_NS_REMOVING	0
+#define NVME_NS_DEAD     	1
+#define NVME_NS_ANA_PENDING	2
 	u16 noiob;
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
@@ -356,14 +384,6 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
 	return (sector >> (ns->lba_shift - 9));
 }
 
-static inline void nvme_cleanup_cmd(struct request *req)
-{
-	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
-		kfree(page_address(req->special_vec.bv_page) +
-		      req->special_vec.bv_offset);
-	}
-}
-
 static inline void nvme_end_request(struct request *req, __le16 status,
 		union nvme_result result)
 {
@@ -420,6 +440,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl);
 #define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid);
+void nvme_cleanup_cmd(struct request *req);
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd);
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
@@ -435,21 +456,24 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl);
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		u8 log_page, void *log, size_t size, u64 offset);
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset);
 
 extern const struct attribute_group nvme_ns_id_attr_group;
 extern const struct block_device_operations nvme_ns_head_ops;
 
 #ifdef CONFIG_NVME_MULTIPATH
+bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl);
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
 void nvme_failover_req(struct request *req);
-bool nvme_req_needs_failover(struct request *req, blk_status_t error);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
-void nvme_mpath_add_disk(struct nvme_ns_head *head);
+void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
 void nvme_mpath_remove_disk(struct nvme_ns_head *head);
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
+void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 
 static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
@@ -468,7 +492,14 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 		kblockd_schedule_work(&head->requeue_work);
 }
 
+extern struct device_attribute dev_attr_ana_grpid;
+extern struct device_attribute dev_attr_ana_state;
+
 #else
+static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+	return false;
+}
 /*
  * Without the multipath code enabled, multiple controller per subsystems are
  * visible as devices and thus we cannot use the subsystem instance.
@@ -482,11 +513,6 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 static inline void nvme_failover_req(struct request *req)
 {
 }
-static inline bool nvme_req_needs_failover(struct request *req,
-					   blk_status_t error)
-{
-	return false;
-}
 static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 }
@@ -495,7 +521,8 @@ static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,
 {
 	return 0;
 }
-static inline void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static inline void nvme_mpath_add_disk(struct nvme_ns *ns,
+		struct nvme_id_ns *id)
 {
 }
 static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
@@ -507,6 +534,17 @@ static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 {
 }
+static inline int nvme_mpath_init(struct nvme_ctrl *ctrl,
+		struct nvme_id_ctrl *id)
+{
+	return 0;
+}
+static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+}
+static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 #ifdef CONFIG_NVM
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ba943f211687..1b9951d2067e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -418,6 +418,8 @@ static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req,
 
 	BUG_ON(!nvmeq);
 	iod->nvmeq = nvmeq;
+
+	nvme_req(req)->ctrl = &dev->ctrl;
 	return 0;
 }
 
@@ -535,73 +537,6 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
 		mempool_free(iod->sg, dev->iod_mempool);
 }
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-	if (be32_to_cpu(pi->ref_tag) == v)
-		pi->ref_tag = cpu_to_be32(p);
-}
-
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-	if (be32_to_cpu(pi->ref_tag) == p)
-		pi->ref_tag = cpu_to_be32(v);
-}
-
-/**
- * nvme_dif_remap - remaps ref tags to bip seed and physical lba
- *
- * The virtual start sector is the one that was originally submitted by the
- * block layer.	Due to partitioning, MD/DM cloning, etc. the actual physical
- * start sector may be different. Remap protection information to match the
- * physical LBA on writes, and back to the original seed on reads.
- *
- * Type 0 and 3 do not have a ref tag, so no remapping required.
- */
-static void nvme_dif_remap(struct request *req,
-			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
-	struct nvme_ns *ns = req->rq_disk->private_data;
-	struct bio_integrity_payload *bip;
-	struct t10_pi_tuple *pi;
-	void *p, *pmap;
-	u32 i, nlb, ts, phys, virt;
-
-	if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3)
-		return;
-
-	bip = bio_integrity(req->bio);
-	if (!bip)
-		return;
-
-	pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset;
-
-	p = pmap;
-	virt = bip_get_seed(bip);
-	phys = nvme_block_nr(ns, blk_rq_pos(req));
-	nlb = (blk_rq_bytes(req) >> ns->lba_shift);
-	ts = ns->disk->queue->integrity.tuple_size;
-
-	for (i = 0; i < nlb; i++, virt++, phys++) {
-		pi = (struct t10_pi_tuple *)p;
-		dif_swap(phys, virt, pi);
-		p += ts;
-	}
-	kunmap_atomic(pmap);
-}
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-static void nvme_dif_remap(struct request *req,
-			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
-}
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-#endif
-
 static void nvme_print_sgl(struct scatterlist *sgl, int nents)
 {
 	int i;
@@ -827,9 +762,6 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1)
 			goto out_unmap;
 
-		if (req_op(req) == REQ_OP_WRITE)
-			nvme_dif_remap(req, nvme_dif_prep);
-
 		if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir))
 			goto out_unmap;
 	}
@@ -852,11 +784,8 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 
 	if (iod->nents) {
 		dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
-		if (blk_integrity_rq(req)) {
-			if (req_op(req) == REQ_OP_READ)
-				nvme_dif_remap(req, nvme_dif_complete);
+		if (blk_integrity_rq(req))
 			dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir);
-		}
 	}
 
 	nvme_cleanup_cmd(req);
@@ -2556,11 +2485,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	quirks |= check_vendor_combination_bug(pdev);
 
-	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
-			quirks);
-	if (result)
-		goto release_pools;
-
 	/*
 	 * Double check that our mempool alloc size will cover the biggest
 	 * command we support.
@@ -2578,6 +2502,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto release_pools;
 	}
 
+	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
+			quirks);
+	if (result)
+		goto release_mempool;
+
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
 	nvme_get_ctrl(&dev->ctrl);
@@ -2585,6 +2514,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+ release_mempool:
+	mempool_destroy(dev->iod_mempool);
  release_pools:
 	nvme_release_prp_pools(dev);
  unmap:
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 9544625c0b7d..0805fa6215ee 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -40,13 +40,14 @@
 
 #define NVME_RDMA_MAX_SEGMENTS		256
 
-#define NVME_RDMA_MAX_INLINE_SEGMENTS	1
+#define NVME_RDMA_MAX_INLINE_SEGMENTS	4
 
 struct nvme_rdma_device {
 	struct ib_device	*dev;
 	struct ib_pd		*pd;
 	struct kref		ref;
 	struct list_head	entry;
+	unsigned int		num_inline_segments;
 };
 
 struct nvme_rdma_qe {
@@ -117,6 +118,7 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
+	bool			use_inline_data;
 };
 
 static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
@@ -249,7 +251,7 @@ static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor)
 	/* +1 for drain */
 	init_attr.cap.max_recv_wr = queue->queue_size + 1;
 	init_attr.cap.max_recv_sge = 1;
-	init_attr.cap.max_send_sge = 1 + NVME_RDMA_MAX_INLINE_SEGMENTS;
+	init_attr.cap.max_send_sge = 1 + dev->num_inline_segments;
 	init_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
 	init_attr.qp_type = IB_QPT_RC;
 	init_attr.send_cq = queue->ib_cq;
@@ -286,6 +288,7 @@ static int nvme_rdma_init_request(struct blk_mq_tag_set *set,
 	struct ib_device *ibdev = dev->dev;
 	int ret;
 
+	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
 			DMA_TO_DEVICE);
 	if (ret)
@@ -374,6 +377,8 @@ nvme_rdma_find_get_device(struct rdma_cm_id *cm_id)
 		goto out_free_pd;
 	}
 
+	ndev->num_inline_segments = min(NVME_RDMA_MAX_INLINE_SEGMENTS,
+					ndev->dev->attrs.max_sge - 1);
 	list_add(&ndev->entry, &device_list);
 out_unlock:
 	mutex_unlock(&device_list_mutex);
@@ -732,8 +737,11 @@ static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		blk_cleanup_queue(ctrl->ctrl.admin_q);
 		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
 	}
-	nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
-		sizeof(struct nvme_command), DMA_TO_DEVICE);
+	if (ctrl->async_event_sqe.data) {
+		nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+				sizeof(struct nvme_command), DMA_TO_DEVICE);
+		ctrl->async_event_sqe.data = NULL;
+	}
 	nvme_rdma_free_queue(&ctrl->queues[0]);
 }
 
@@ -865,6 +873,31 @@ out_free_io_queues:
 	return ret;
 }
 
+static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
+		bool remove)
+{
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_cancel_request,
+			&ctrl->ctrl);
+	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_destroy_admin_queue(ctrl, remove);
+}
+
+static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
+		bool remove)
+{
+	if (ctrl->ctrl.queue_count > 1) {
+		nvme_stop_queues(&ctrl->ctrl);
+		nvme_rdma_stop_io_queues(ctrl);
+		blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_cancel_request,
+				&ctrl->ctrl);
+		if (remove)
+			nvme_start_queues(&ctrl->ctrl);
+		nvme_rdma_destroy_io_queues(ctrl, remove);
+	}
+}
+
 static void nvme_rdma_stop_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
@@ -909,21 +942,44 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 	}
 }
 
-static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 {
-	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
-			struct nvme_rdma_ctrl, reconnect_work);
+	int ret = -EINVAL;
 	bool changed;
-	int ret;
 
-	++ctrl->ctrl.nr_reconnects;
-
-	ret = nvme_rdma_configure_admin_queue(ctrl, false);
+	ret = nvme_rdma_configure_admin_queue(ctrl, new);
 	if (ret)
-		goto requeue;
+		return ret;
+
+	if (ctrl->ctrl.icdoff) {
+		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
+		goto destroy_admin;
+	}
+
+	if (!(ctrl->ctrl.sgls & (1 << 2))) {
+		dev_err(ctrl->ctrl.device,
+			"Mandatory keyed sgls are not supported!\n");
+		goto destroy_admin;
+	}
+
+	if (ctrl->ctrl.opts->queue_size > ctrl->ctrl.sqsize + 1) {
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl sqsize %u, clamping down\n",
+			ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
+	}
+
+	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
+		dev_warn(ctrl->ctrl.device,
+			"sqsize %u > ctrl maxcmd %u, clamping down\n",
+			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
+		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
+	}
+
+	if (ctrl->ctrl.sgls & (1 << 20))
+		ctrl->use_inline_data = true;
 
 	if (ctrl->ctrl.queue_count > 1) {
-		ret = nvme_rdma_configure_io_queues(ctrl, false);
+		ret = nvme_rdma_configure_io_queues(ctrl, new);
 		if (ret)
 			goto destroy_admin;
 	}
@@ -932,10 +988,31 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	if (!changed) {
 		/* state change failure is ok if we're in DELETING state */
 		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
-		return;
+		ret = -EINVAL;
+		goto destroy_io;
 	}
 
 	nvme_start_ctrl(&ctrl->ctrl);
+	return 0;
+
+destroy_io:
+	if (ctrl->ctrl.queue_count > 1)
+		nvme_rdma_destroy_io_queues(ctrl, new);
+destroy_admin:
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	nvme_rdma_destroy_admin_queue(ctrl, new);
+	return ret;
+}
+
+static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvme_rdma_ctrl, reconnect_work);
+
+	++ctrl->ctrl.nr_reconnects;
+
+	if (nvme_rdma_setup_ctrl(ctrl, false))
+		goto requeue;
 
 	dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n",
 			ctrl->ctrl.nr_reconnects);
@@ -944,9 +1021,6 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 
 	return;
 
-destroy_admin:
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	nvme_rdma_destroy_admin_queue(ctrl, false);
 requeue:
 	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
 			ctrl->ctrl.nr_reconnects);
@@ -959,27 +1033,9 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 			struct nvme_rdma_ctrl, err_work);
 
 	nvme_stop_keep_alive(&ctrl->ctrl);
-
-	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		nvme_rdma_stop_io_queues(ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-					nvme_cancel_request, &ctrl->ctrl);
-		nvme_rdma_destroy_io_queues(ctrl, false);
-	}
-
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_cancel_request, &ctrl->ctrl);
-	nvme_rdma_destroy_admin_queue(ctrl, false);
-
-	/*
-	 * queues are not a live anymore, so restart the queues to fail fast
-	 * new IO
-	 */
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_teardown_io_queues(ctrl, false);
 	nvme_start_queues(&ctrl->ctrl);
+	nvme_rdma_teardown_admin_queue(ctrl, false);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we're in DELETING state */
@@ -1087,19 +1143,27 @@ static int nvme_rdma_set_sg_null(struct nvme_command *c)
 }
 
 static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue,
-		struct nvme_rdma_request *req, struct nvme_command *c)
+		struct nvme_rdma_request *req, struct nvme_command *c,
+		int count)
 {
 	struct nvme_sgl_desc *sg = &c->common.dptr.sgl;
+	struct scatterlist *sgl = req->sg_table.sgl;
+	struct ib_sge *sge = &req->sge[1];
+	u32 len = 0;
+	int i;
 
-	req->sge[1].addr = sg_dma_address(req->sg_table.sgl);
-	req->sge[1].length = sg_dma_len(req->sg_table.sgl);
-	req->sge[1].lkey = queue->device->pd->local_dma_lkey;
+	for (i = 0; i < count; i++, sgl++, sge++) {
+		sge->addr = sg_dma_address(sgl);
+		sge->length = sg_dma_len(sgl);
+		sge->lkey = queue->device->pd->local_dma_lkey;
+		len += sge->length;
+	}
 
 	sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff);
-	sg->length = cpu_to_le32(sg_dma_len(req->sg_table.sgl));
+	sg->length = cpu_to_le32(len);
 	sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET;
 
-	req->num_sge++;
+	req->num_sge += count;
 	return 0;
 }
 
@@ -1192,15 +1256,16 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 		goto out_free_table;
 	}
 
-	if (count == 1) {
+	if (count <= dev->num_inline_segments) {
 		if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) &&
+		    queue->ctrl->use_inline_data &&
 		    blk_rq_payload_bytes(rq) <=
 				nvme_rdma_inline_data_size(queue)) {
-			ret = nvme_rdma_map_sg_inline(queue, req, c);
+			ret = nvme_rdma_map_sg_inline(queue, req, c, count);
 			goto out;
 		}
 
-		if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
+		if (count == 1 && dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
 			ret = nvme_rdma_map_sg_single(queue, req, c);
 			goto out;
 		}
@@ -1571,6 +1636,7 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	case RDMA_CM_EVENT_UNREACHABLE:
 		nvme_rdma_destroy_queue_ib(queue);
+		/* fall through */
 	case RDMA_CM_EVENT_ADDR_ERROR:
 		dev_dbg(queue->ctrl->ctrl.device,
 			"CM error event %d\n", ev->event);
@@ -1636,7 +1702,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	WARN_ON_ONCE(rq->tag < 0);
 
 	if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(rq);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	dev = queue->device->dev;
 	ib_dma_sync_single_for_cpu(dev, sqe->dma,
@@ -1733,25 +1799,12 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
 
 static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
 {
-	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		nvme_rdma_stop_io_queues(ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-					nvme_cancel_request, &ctrl->ctrl);
-		nvme_rdma_destroy_io_queues(ctrl, shutdown);
-	}
-
+	nvme_rdma_teardown_io_queues(ctrl, shutdown);
 	if (shutdown)
 		nvme_shutdown_ctrl(&ctrl->ctrl);
 	else
 		nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
-
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_cancel_request, &ctrl->ctrl);
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_destroy_admin_queue(ctrl, shutdown);
+	nvme_rdma_teardown_admin_queue(ctrl, shutdown);
 }
 
 static void nvme_rdma_delete_ctrl(struct nvme_ctrl *ctrl)
@@ -1763,8 +1816,6 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 {
 	struct nvme_rdma_ctrl *ctrl =
 		container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);
-	int ret;
-	bool changed;
 
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_rdma_shutdown_ctrl(ctrl, false);
@@ -1775,25 +1826,9 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 		return;
 	}
 
-	ret = nvme_rdma_configure_admin_queue(ctrl, false);
-	if (ret)
+	if (nvme_rdma_setup_ctrl(ctrl, false))
 		goto out_fail;
 
-	if (ctrl->ctrl.queue_count > 1) {
-		ret = nvme_rdma_configure_io_queues(ctrl, false);
-		if (ret)
-			goto out_fail;
-	}
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	if (!changed) {
-		/* state change failure is ok if we're in DELETING state */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
-		return;
-	}
-
-	nvme_start_ctrl(&ctrl->ctrl);
-
 	return;
 
 out_fail:
@@ -1956,49 +1991,10 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
 	WARN_ON_ONCE(!changed);
 
-	ret = nvme_rdma_configure_admin_queue(ctrl, true);
+	ret = nvme_rdma_setup_ctrl(ctrl, true);
 	if (ret)
 		goto out_uninit_ctrl;
 
-	/* sanity check icdoff */
-	if (ctrl->ctrl.icdoff) {
-		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
-		ret = -EINVAL;
-		goto out_remove_admin_queue;
-	}
-
-	/* sanity check keyed sgls */
-	if (!(ctrl->ctrl.sgls & (1 << 2))) {
-		dev_err(ctrl->ctrl.device,
-			"Mandatory keyed sgls are not supported!\n");
-		ret = -EINVAL;
-		goto out_remove_admin_queue;
-	}
-
-	/* only warn if argument is too large here, will clamp later */
-	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
-		dev_warn(ctrl->ctrl.device,
-			"queue_size %zu > ctrl sqsize %u, clamping down\n",
-			opts->queue_size, ctrl->ctrl.sqsize + 1);
-	}
-
-	/* warn if maxcmd is lower than sqsize+1 */
-	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
-		dev_warn(ctrl->ctrl.device,
-			"sqsize %u > ctrl maxcmd %u, clamping down\n",
-			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
-		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
-	}
-
-	if (opts->nr_io_queues) {
-		ret = nvme_rdma_configure_io_queues(ctrl, true);
-		if (ret)
-			goto out_remove_admin_queue;
-	}
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	WARN_ON_ONCE(!changed);
-
 	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
 		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
 
@@ -2008,13 +2004,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
 	mutex_unlock(&nvme_rdma_ctrl_mutex);
 
-	nvme_start_ctrl(&ctrl->ctrl);
-
 	return &ctrl->ctrl;
 
-out_remove_admin_queue:
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	nvme_rdma_destroy_admin_queue(ctrl, true);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 	nvme_put_ctrl(&ctrl->ctrl);
diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 41944bbef835..25b0e310f4a8 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -128,3 +128,14 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p,
 		return nvme_trace_common(p, cdw10);
 	}
 }
+
+const char *nvme_trace_disk_name(struct trace_seq *p, char *name)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+
+	if (*name)
+		trace_seq_printf(p, "disk=%s, ", name);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index 01390f0e1671..a490790d6691 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -50,13 +50,8 @@
 		nvme_admin_opcode_name(nvme_admin_security_recv),	\
 		nvme_admin_opcode_name(nvme_admin_sanitize_nvm))
 
-const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
-				       u8 *cdw10);
-#define __parse_nvme_admin_cmd(opcode, cdw10) \
-	nvme_trace_parse_admin_cmd(p, opcode, cdw10)
-
 #define nvme_opcode_name(opcode)	{ opcode, #opcode }
-#define show_opcode_name(val)					\
+#define show_nvm_opcode_name(val)				\
 	__print_symbolic(val,					\
 		nvme_opcode_name(nvme_cmd_flush),		\
 		nvme_opcode_name(nvme_cmd_write),		\
@@ -70,85 +65,92 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
 		nvme_opcode_name(nvme_cmd_resv_acquire),	\
 		nvme_opcode_name(nvme_cmd_resv_release))
 
-const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode,
-				     u8 *cdw10);
-#define __parse_nvme_cmd(opcode, cdw10) \
-	nvme_trace_parse_nvm_cmd(p, opcode, cdw10)
-
-TRACE_EVENT(nvme_setup_admin_cmd,
-	    TP_PROTO(struct nvme_command *cmd),
-	    TP_ARGS(cmd),
-	    TP_STRUCT__entry(
-		    __field(u8, opcode)
-		    __field(u8, flags)
-		    __field(u16, cid)
-		    __field(u64, metadata)
-		    __array(u8, cdw10, 24)
-	    ),
-	    TP_fast_assign(
-		    __entry->opcode = cmd->common.opcode;
-		    __entry->flags = cmd->common.flags;
-		    __entry->cid = cmd->common.command_id;
-		    __entry->metadata = le64_to_cpu(cmd->common.metadata);
-		    memcpy(__entry->cdw10, cmd->common.cdw10,
-			   sizeof(__entry->cdw10));
-	    ),
-	    TP_printk(" cmdid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->cid, __entry->flags, __entry->metadata,
-		      show_admin_opcode_name(__entry->opcode),
-		      __parse_nvme_admin_cmd(__entry->opcode, __entry->cdw10))
-);
-
+#define show_opcode_name(qid, opcode)					\
+	(qid ? show_nvm_opcode_name(opcode) : show_admin_opcode_name(opcode))
 
-TRACE_EVENT(nvme_setup_nvm_cmd,
-	    TP_PROTO(int qid, struct nvme_command *cmd),
-	    TP_ARGS(qid, cmd),
+const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
+		u8 *cdw10);
+const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode,
+		u8 *cdw10);
+
+#define parse_nvme_cmd(qid, opcode, cdw10) 			\
+	(qid ?							\
+	 nvme_trace_parse_nvm_cmd(p, opcode, cdw10) : 		\
+	 nvme_trace_parse_admin_cmd(p, opcode, cdw10))
+
+const char *nvme_trace_disk_name(struct trace_seq *p, char *name);
+#define __print_disk_name(name)				\
+	nvme_trace_disk_name(p, name)
+
+#ifndef TRACE_HEADER_MULTI_READ
+static inline void __assign_disk_name(char *name, struct gendisk *disk)
+{
+	if (disk)
+		memcpy(name, disk->disk_name, DISK_NAME_LEN);
+	else
+		memset(name, 0, DISK_NAME_LEN);
+}
+#endif
+
+TRACE_EVENT(nvme_setup_cmd,
+	    TP_PROTO(struct request *req, struct nvme_command *cmd),
+	    TP_ARGS(req, cmd),
 	    TP_STRUCT__entry(
-		    __field(int, qid)
-		    __field(u8, opcode)
-		    __field(u8, flags)
-		    __field(u16, cid)
-		    __field(u32, nsid)
-		    __field(u64, metadata)
-		    __array(u8, cdw10, 24)
+		__array(char, disk, DISK_NAME_LEN)
+		__field(int, ctrl_id)
+		__field(int, qid)
+		__field(u8, opcode)
+		__field(u8, flags)
+		__field(u16, cid)
+		__field(u32, nsid)
+		__field(u64, metadata)
+		__array(u8, cdw10, 24)
 	    ),
 	    TP_fast_assign(
-		    __entry->qid = qid;
-		    __entry->opcode = cmd->common.opcode;
-		    __entry->flags = cmd->common.flags;
-		    __entry->cid = cmd->common.command_id;
-		    __entry->nsid = le32_to_cpu(cmd->common.nsid);
-		    __entry->metadata = le64_to_cpu(cmd->common.metadata);
-		    memcpy(__entry->cdw10, cmd->common.cdw10,
-			   sizeof(__entry->cdw10));
+		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
+		__entry->qid = nvme_req_qid(req);
+		__entry->opcode = cmd->common.opcode;
+		__entry->flags = cmd->common.flags;
+		__entry->cid = cmd->common.command_id;
+		__entry->nsid = le32_to_cpu(cmd->common.nsid);
+		__entry->metadata = le64_to_cpu(cmd->common.metadata);
+		__assign_disk_name(__entry->disk, req->rq_disk);
+		memcpy(__entry->cdw10, cmd->common.cdw10,
+		       sizeof(__entry->cdw10));
 	    ),
-	    TP_printk("qid=%d, nsid=%u, cmdid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->qid, __entry->nsid, __entry->cid,
+	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
+		      __entry->ctrl_id, __print_disk_name(__entry->disk),
+		      __entry->qid, __entry->cid, __entry->nsid,
 		      __entry->flags, __entry->metadata,
-		      show_opcode_name(__entry->opcode),
-		      __parse_nvme_cmd(__entry->opcode, __entry->cdw10))
+		      show_opcode_name(__entry->qid, __entry->opcode),
+		      parse_nvme_cmd(__entry->qid, __entry->opcode, __entry->cdw10))
 );
 
 TRACE_EVENT(nvme_complete_rq,
 	    TP_PROTO(struct request *req),
 	    TP_ARGS(req),
 	    TP_STRUCT__entry(
-		    __field(int, qid)
-		    __field(int, cid)
-		    __field(u64, result)
-		    __field(u8, retries)
-		    __field(u8, flags)
-		    __field(u16, status)
+		__array(char, disk, DISK_NAME_LEN)
+		__field(int, ctrl_id)
+		__field(int, qid)
+		__field(int, cid)
+		__field(u64, result)
+		__field(u8, retries)
+		__field(u8, flags)
+		__field(u16, status)
 	    ),
 	    TP_fast_assign(
-		    __entry->qid = req->q->id;
-		    __entry->cid = req->tag;
-		    __entry->result = le64_to_cpu(nvme_req(req)->result.u64);
-		    __entry->retries = nvme_req(req)->retries;
-		    __entry->flags = nvme_req(req)->flags;
-		    __entry->status = nvme_req(req)->status;
+		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
+		__entry->qid = nvme_req_qid(req);
+		__entry->cid = req->tag;
+		__entry->result = le64_to_cpu(nvme_req(req)->result.u64);
+		__entry->retries = nvme_req(req)->retries;
+		__entry->flags = nvme_req(req)->flags;
+		__entry->status = nvme_req(req)->status;
+		__assign_disk_name(__entry->disk, req->rq_disk);
 	    ),
-	    TP_printk("qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+		      __entry->ctrl_id, __print_disk_name(__entry->disk),
 		      __entry->qid, __entry->cid, __entry->result,
 		      __entry->retries, __entry->flags, __entry->status)
 
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 38803576d5e1..a21caea1e080 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -19,6 +19,19 @@
 #include <asm/unaligned.h>
 #include "nvmet.h"
 
+/*
+ * This helper allows us to clear the AEN based on the RAE bit,
+ * Please use this helper when processing the log pages which are
+ * associated with the AEN.
+ */
+static inline void nvmet_clear_aen(struct nvmet_req *req, u32 aen_bit)
+{
+	int rae = le32_to_cpu(req->cmd->common.cdw10[0]) & 1 << 15;
+
+	if (!rae)
+		clear_bit(aen_bit, &req->sq->ctrl->aen_masked);
+}
+
 u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 {
 	u32 len = le16_to_cpu(cmd->get_log_page.numdu);
@@ -128,6 +141,36 @@ out:
 	nvmet_req_complete(req, status);
 }
 
+static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
+{
+	u16 status = NVME_SC_INTERNAL;
+	struct nvme_effects_log *log;
+
+	log = kzalloc(sizeof(*log), GFP_KERNEL);
+	if (!log)
+		goto out;
+
+	log->acs[nvme_admin_get_log_page]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_identify]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_abort_cmd]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_set_features]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_get_features]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_async_event]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_keep_alive]		= cpu_to_le32(1 << 0);
+
+	log->iocs[nvme_cmd_read]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_write]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_flush]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_dsm]			= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_write_zeroes]	= cpu_to_le32(1 << 0);
+
+	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+
+	kfree(log);
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -146,12 +189,76 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 	if (!status)
 		status = nvmet_zero_sgl(req, len, req->data_len - len);
 	ctrl->nr_changed_ns = 0;
-	clear_bit(NVME_AEN_CFG_NS_ATTR, &ctrl->aen_masked);
+	nvmet_clear_aen(req, NVME_AEN_CFG_NS_ATTR);
 	mutex_unlock(&ctrl->lock);
 out:
 	nvmet_req_complete(req, status);
 }
 
+static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
+		struct nvme_ana_group_desc *desc)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvmet_ns *ns;
+	u32 count = 0;
+
+	if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) {
+		rcu_read_lock();
+		list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+			if (ns->anagrpid == grpid)
+				desc->nsids[count++] = cpu_to_le32(ns->nsid);
+		rcu_read_unlock();
+	}
+
+	desc->grpid = cpu_to_le32(grpid);
+	desc->nnsids = cpu_to_le32(count);
+	desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	desc->state = req->port->ana_state[grpid];
+	memset(desc->rsvd17, 0, sizeof(desc->rsvd17));
+	return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32);
+}
+
+static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
+{
+	struct nvme_ana_rsp_hdr hdr = { 0, };
+	struct nvme_ana_group_desc *desc;
+	size_t offset = sizeof(struct nvme_ana_rsp_hdr); /* start beyond hdr */
+	size_t len;
+	u32 grpid;
+	u16 ngrps = 0;
+	u16 status;
+
+	status = NVME_SC_INTERNAL;
+	desc = kmalloc(sizeof(struct nvme_ana_group_desc) +
+			NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL);
+	if (!desc)
+		goto out;
+
+	down_read(&nvmet_ana_sem);
+	for (grpid = 1; grpid <= NVMET_MAX_ANAGRPS; grpid++) {
+		if (!nvmet_ana_group_enabled[grpid])
+			continue;
+		len = nvmet_format_ana_group(req, grpid, desc);
+		status = nvmet_copy_to_sgl(req, offset, desc, len);
+		if (status)
+			break;
+		offset += len;
+		ngrps++;
+	}
+
+	hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	hdr.ngrps = cpu_to_le16(ngrps);
+	nvmet_clear_aen(req, NVME_AEN_CFG_ANA_CHANGE);
+	up_read(&nvmet_ana_sem);
+
+	kfree(desc);
+
+	/* copy the header last once we know the number of groups */
+	status = nvmet_copy_to_sgl(req, 0, &hdr, sizeof(hdr));
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -183,8 +290,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	 * the safest is to leave it as zeroes.
 	 */
 
-	/* we support multiple ports and multiples hosts: */
-	id->cmic = (1 << 0) | (1 << 1);
+	/* we support multiple ports, multiples hosts and ANA: */
+	id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
 
 	/* no limit on data transfer sizes for now */
 	id->mdts = 0;
@@ -208,7 +315,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 
 	/* first slot is read-only, only one slot supported */
 	id->frmw = (1 << 0) | (1 << 1);
-	id->lpa = (1 << 0) | (1 << 2);
+	id->lpa = (1 << 0) | (1 << 1) | (1 << 2);
 	id->elpe = NVMET_ERROR_LOG_SLOTS - 1;
 	id->npss = 0;
 
@@ -222,6 +329,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
 
 	id->nn = cpu_to_le32(ctrl->subsys->max_nsid);
+	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
 			NVME_CTRL_ONCS_WRITE_ZEROES);
 
@@ -238,19 +346,24 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->has_keyed_sgls)
 		id->sgls |= cpu_to_le32(1 << 2);
-	if (ctrl->ops->sqe_inline_size)
+	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);
 
 	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
 
 	/* Max command capsule size is sqe + single page of in-capsule data */
 	id->ioccsz = cpu_to_le32((sizeof(struct nvme_command) +
-				  ctrl->ops->sqe_inline_size) / 16);
+				  req->port->inline_data_size) / 16);
 	/* Max response capsule size is cqe */
 	id->iorcsz = cpu_to_le32(sizeof(struct nvme_completion) / 16);
 
 	id->msdbd = ctrl->ops->msdbd;
 
+	id->anacap = (1 << 0) | (1 << 1) | (1 << 2) | (1 << 3) | (1 << 4);
+	id->anatt = 10; /* random value */
+	id->anagrpmax = cpu_to_le32(NVMET_MAX_ANAGRPS);
+	id->nanagrpid = cpu_to_le32(NVMET_MAX_ANAGRPS);
+
 	/*
 	 * Meh, we don't really support any power state.  Fake up the same
 	 * values that qemu does.
@@ -259,6 +372,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->psd[0].entry_lat = cpu_to_le32(0x10);
 	id->psd[0].exit_lat = cpu_to_le32(0x4);
 
+	id->nwpc = 1 << 0; /* write protect and no write protect */
+
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
 
 	kfree(id);
@@ -292,8 +407,15 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * nuse = ncap = nsze isn't always true, but we have no way to find
 	 * that out from the underlying device.
 	 */
-	id->ncap = id->nuse = id->nsze =
-		cpu_to_le64(ns->size >> ns->blksize_shift);
+	id->ncap = id->nsze = cpu_to_le64(ns->size >> ns->blksize_shift);
+	switch (req->port->ana_state[ns->anagrpid]) {
+	case NVME_ANA_INACCESSIBLE:
+	case NVME_ANA_PERSISTENT_LOSS:
+		break;
+	default:
+		id->nuse = id->nsze;
+		break;
+        }
 
 	/*
 	 * We just provide a single LBA format that matches what the
@@ -307,11 +429,14 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * controllers, but also with any other user of the block device.
 	 */
 	id->nmic = (1 << 0);
+	id->anagrpid = cpu_to_le32(ns->anagrpid);
 
-	memcpy(&id->nguid, &ns->nguid, sizeof(uuid_le));
+	memcpy(&id->nguid, &ns->nguid, sizeof(id->nguid));
 
 	id->lbaf[0].ds = ns->blksize_shift;
 
+	if (ns->readonly)
+		id->nsattr |= (1 << 0);
 	nvmet_put_namespace(ns);
 done:
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
@@ -424,6 +549,52 @@ static void nvmet_execute_abort(struct nvmet_req *req)
 	nvmet_req_complete(req, 0);
 }
 
+static u16 nvmet_write_protect_flush_sync(struct nvmet_req *req)
+{
+	u16 status;
+
+	if (req->ns->file)
+		status = nvmet_file_flush(req);
+	else
+		status = nvmet_bdev_flush(req);
+
+	if (status)
+		pr_err("write protect flush failed nsid: %u\n", req->ns->nsid);
+	return status;
+}
+
+static u16 nvmet_set_feat_write_protect(struct nvmet_req *req)
+{
+	u32 write_protect = le32_to_cpu(req->cmd->common.cdw10[1]);
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u16 status = NVME_SC_FEATURE_NOT_CHANGEABLE;
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->rw.nsid);
+	if (unlikely(!req->ns))
+		return status;
+
+	mutex_lock(&subsys->lock);
+	switch (write_protect) {
+	case NVME_NS_WRITE_PROTECT:
+		req->ns->readonly = true;
+		status = nvmet_write_protect_flush_sync(req);
+		if (status)
+			req->ns->readonly = false;
+		break;
+	case NVME_NS_NO_WRITE_PROTECT:
+		req->ns->readonly = false;
+		status = 0;
+		break;
+	default:
+		break;
+	}
+
+	if (!status)
+		nvmet_ns_changed(subsys, req->ns->nsid);
+	mutex_unlock(&subsys->lock);
+	return status;
+}
+
 static void nvmet_execute_set_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
@@ -454,6 +625,9 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 	case NVME_FEAT_HOST_ID:
 		status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 		break;
+	case NVME_FEAT_WRITE_PROTECT:
+		status = nvmet_set_feat_write_protect(req);
+		break;
 	default:
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
@@ -462,6 +636,26 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 	nvmet_req_complete(req, status);
 }
 
+static u16 nvmet_get_feat_write_protect(struct nvmet_req *req)
+{
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u32 result;
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->common.nsid);
+	if (!req->ns)
+		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+
+	mutex_lock(&subsys->lock);
+	if (req->ns->readonly == true)
+		result = NVME_NS_WRITE_PROTECT;
+	else
+		result = NVME_NS_NO_WRITE_PROTECT;
+	nvmet_set_result(req, result);
+	mutex_unlock(&subsys->lock);
+
+	return 0;
+}
+
 static void nvmet_execute_get_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
@@ -513,6 +707,9 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		status = nvmet_copy_to_sgl(req, 0, &req->sq->ctrl->hostid,
 				sizeof(req->sq->ctrl->hostid));
 		break;
+	case NVME_FEAT_WRITE_PROTECT:
+		status = nvmet_get_feat_write_protect(req);
+		break;
 	default:
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
@@ -586,6 +783,12 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 		case NVME_LOG_CHANGED_NS:
 			req->execute = nvmet_execute_get_log_changed_ns;
 			return 0;
+		case NVME_LOG_CMD_EFFECTS:
+			req->execute = nvmet_execute_get_log_cmd_effects_ns;
+			return 0;
+		case NVME_LOG_ANA:
+			req->execute = nvmet_execute_get_log_page_ana;
+			return 0;
 		}
 		break;
 	case nvme_admin_identify:
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index d3f3b3ec4d1a..b37a8e3e3f80 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -218,6 +218,35 @@ static ssize_t nvmet_addr_trsvcid_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_, addr_trsvcid);
 
+static ssize_t nvmet_param_inline_data_size_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%d\n", port->inline_data_size);
+}
+
+static ssize_t nvmet_param_inline_data_size_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	int ret;
+
+	if (port->enabled) {
+		pr_err("Cannot modify inline_data_size while port enabled\n");
+		pr_err("Disable the port before modifying\n");
+		return -EACCES;
+	}
+	ret = kstrtoint(page, 0, &port->inline_data_size);
+	if (ret) {
+		pr_err("Invalid value '%s' for inline_data_size\n", page);
+		return -EINVAL;
+	}
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, param_inline_data_size);
+
 static ssize_t nvmet_addr_trtype_show(struct config_item *item,
 		char *page)
 {
@@ -282,6 +311,7 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item,
 {
 	struct nvmet_ns *ns = to_nvmet_ns(item);
 	struct nvmet_subsys *subsys = ns->subsys;
+	size_t len;
 	int ret;
 
 	mutex_lock(&subsys->lock);
@@ -289,10 +319,14 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item,
 	if (ns->enabled)
 		goto out_unlock;
 
-	kfree(ns->device_path);
+	ret = -EINVAL;
+	len = strcspn(page, "\n");
+	if (!len)
+		goto out_unlock;
 
+	kfree(ns->device_path);
 	ret = -ENOMEM;
-	ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL);
+	ns->device_path = kstrndup(page, len, GFP_KERNEL);
 	if (!ns->device_path)
 		goto out_unlock;
 
@@ -382,6 +416,39 @@ out_unlock:
 
 CONFIGFS_ATTR(nvmet_ns_, device_nguid);
 
+static ssize_t nvmet_ns_ana_grpid_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%u\n", to_nvmet_ns(item)->anagrpid);
+}
+
+static ssize_t nvmet_ns_ana_grpid_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	u32 oldgrpid, newgrpid;
+	int ret;
+
+	ret = kstrtou32(page, 0, &newgrpid);
+	if (ret)
+		return ret;
+
+	if (newgrpid < 1 || newgrpid > NVMET_MAX_ANAGRPS)
+		return -EINVAL;
+
+	down_write(&nvmet_ana_sem);
+	oldgrpid = ns->anagrpid;
+	nvmet_ana_group_enabled[newgrpid]++;
+	ns->anagrpid = newgrpid;
+	nvmet_ana_group_enabled[oldgrpid]--;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_send_ana_event(ns->subsys, NULL);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, ana_grpid);
+
 static ssize_t nvmet_ns_enable_show(struct config_item *item, char *page)
 {
 	return sprintf(page, "%d\n", to_nvmet_ns(item)->enabled);
@@ -407,11 +474,41 @@ static ssize_t nvmet_ns_enable_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_ns_, enable);
 
+static ssize_t nvmet_ns_buffered_io_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%d\n", to_nvmet_ns(item)->buffered_io);
+}
+
+static ssize_t nvmet_ns_buffered_io_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	bool val;
+
+	if (strtobool(page, &val))
+		return -EINVAL;
+
+	mutex_lock(&ns->subsys->lock);
+	if (ns->enabled) {
+		pr_err("disable ns before setting buffered_io value.\n");
+		mutex_unlock(&ns->subsys->lock);
+		return -EINVAL;
+	}
+
+	ns->buffered_io = val;
+	mutex_unlock(&ns->subsys->lock);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, buffered_io);
+
 static struct configfs_attribute *nvmet_ns_attrs[] = {
 	&nvmet_ns_attr_device_path,
 	&nvmet_ns_attr_device_nguid,
 	&nvmet_ns_attr_device_uuid,
+	&nvmet_ns_attr_ana_grpid,
 	&nvmet_ns_attr_enable,
+	&nvmet_ns_attr_buffered_io,
 	NULL,
 };
 
@@ -858,6 +955,134 @@ static const struct config_item_type nvmet_referrals_type = {
 	.ct_group_ops	= &nvmet_referral_group_ops,
 };
 
+static struct {
+	enum nvme_ana_state	state;
+	const char		*name;
+} nvmet_ana_state_names[] = {
+	{ NVME_ANA_OPTIMIZED,		"optimized" },
+	{ NVME_ANA_NONOPTIMIZED,	"non-optimized" },
+	{ NVME_ANA_INACCESSIBLE,	"inaccessible" },
+	{ NVME_ANA_PERSISTENT_LOSS,	"persistent-loss" },
+	{ NVME_ANA_CHANGE,		"change" },
+};
+
+static ssize_t nvmet_ana_group_ana_state_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	enum nvme_ana_state state = grp->port->ana_state[grp->grpid];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (state != nvmet_ana_state_names[i].state)
+			continue;
+		return sprintf(page, "%s\n", nvmet_ana_state_names[i].name);
+	}
+
+	return sprintf(page, "\n");
+}
+
+static ssize_t nvmet_ana_group_ana_state_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (sysfs_streq(page, nvmet_ana_state_names[i].name))
+			goto found;
+	}
+
+	pr_err("Invalid value '%s' for ana_state\n", page);
+	return -EINVAL;
+
+found:
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = nvmet_ana_state_names[i].state;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ana_group_, ana_state);
+
+static struct configfs_attribute *nvmet_ana_group_attrs[] = {
+	&nvmet_ana_group_attr_ana_state,
+	NULL,
+};
+
+static void nvmet_ana_group_release(struct config_item *item)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+
+	if (grp == &grp->port->ana_default_group)
+		return;
+
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = NVME_ANA_INACCESSIBLE;
+	nvmet_ana_group_enabled[grp->grpid]--;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	kfree(grp);
+}
+
+static struct configfs_item_operations nvmet_ana_group_item_ops = {
+	.release		= nvmet_ana_group_release,
+};
+
+static const struct config_item_type nvmet_ana_group_type = {
+	.ct_item_ops		= &nvmet_ana_group_item_ops,
+	.ct_attrs		= nvmet_ana_group_attrs,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group *nvmet_ana_groups_make_group(
+		struct config_group *group, const char *name)
+{
+	struct nvmet_port *port = ana_groups_to_port(&group->cg_item);
+	struct nvmet_ana_group *grp;
+	u32 grpid;
+	int ret;
+
+	ret = kstrtou32(name, 0, &grpid);
+	if (ret)
+		goto out;
+
+	ret = -EINVAL;
+	if (grpid <= 1 || grpid > NVMET_MAX_ANAGRPS)
+		goto out;
+
+	ret = -ENOMEM;
+	grp = kzalloc(sizeof(*grp), GFP_KERNEL);
+	if (!grp)
+		goto out;
+	grp->port = port;
+	grp->grpid = grpid;
+
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[grpid]++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+
+	config_group_init_type_name(&grp->group, name, &nvmet_ana_group_type);
+	return &grp->group;
+out:
+	return ERR_PTR(ret);
+}
+
+static struct configfs_group_operations nvmet_ana_groups_group_ops = {
+	.make_group		= nvmet_ana_groups_make_group,
+};
+
+static const struct config_item_type nvmet_ana_groups_type = {
+	.ct_group_ops		= &nvmet_ana_groups_group_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
 /*
  * Ports definitions.
  */
@@ -865,6 +1090,7 @@ static void nvmet_port_release(struct config_item *item)
 {
 	struct nvmet_port *port = to_nvmet_port(item);
 
+	kfree(port->ana_state);
 	kfree(port);
 }
 
@@ -874,6 +1100,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_traddr,
 	&nvmet_attr_addr_trsvcid,
 	&nvmet_attr_addr_trtype,
+	&nvmet_attr_param_inline_data_size,
 	NULL,
 };
 
@@ -892,6 +1119,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 {
 	struct nvmet_port *port;
 	u16 portid;
+	u32 i;
 
 	if (kstrtou16(name, 0, &portid))
 		return ERR_PTR(-EINVAL);
@@ -900,9 +1128,24 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	if (!port)
 		return ERR_PTR(-ENOMEM);
 
+	port->ana_state = kcalloc(NVMET_MAX_ANAGRPS + 1,
+			sizeof(*port->ana_state), GFP_KERNEL);
+	if (!port->ana_state) {
+		kfree(port);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 1; i <= NVMET_MAX_ANAGRPS; i++) {
+		if (i == NVMET_DEFAULT_ANA_GRPID)
+			port->ana_state[1] = NVME_ANA_OPTIMIZED;
+		else
+			port->ana_state[i] = NVME_ANA_INACCESSIBLE;
+	}
+
 	INIT_LIST_HEAD(&port->entry);
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
+	port->inline_data_size = -1;	/* < 0 == let the transport choose */
 
 	port->disc_addr.portid = cpu_to_le16(portid);
 	config_group_init_type_name(&port->group, name, &nvmet_port_type);
@@ -915,6 +1158,18 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 			"referrals", &nvmet_referrals_type);
 	configfs_add_default_group(&port->referrals_group, &port->group);
 
+	config_group_init_type_name(&port->ana_groups_group,
+			"ana_groups", &nvmet_ana_groups_type);
+	configfs_add_default_group(&port->ana_groups_group, &port->group);
+
+	port->ana_default_group.port = port;
+	port->ana_default_group.grpid = NVMET_DEFAULT_ANA_GRPID;
+	config_group_init_type_name(&port->ana_default_group.group,
+			__stringify(NVMET_DEFAULT_ANA_GRPID),
+			&nvmet_ana_group_type);
+	configfs_add_default_group(&port->ana_default_group.group,
+			&port->ana_groups_group);
+
 	return &port->group;
 }
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 74d4b785d2da..ebf3e7a6c49e 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -18,6 +18,7 @@
 
 #include "nvmet.h"
 
+struct workqueue_struct *buffered_io_wq;
 static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
 static DEFINE_IDA(cntlid_ida);
 
@@ -39,6 +40,10 @@ static DEFINE_IDA(cntlid_ida);
  */
 DECLARE_RWSEM(nvmet_config_sem);
 
+u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+u64 nvmet_ana_chgcnt;
+DECLARE_RWSEM(nvmet_ana_sem);
+
 static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
 		const char *subsysnqn);
 
@@ -175,7 +180,7 @@ out_unlock:
 	mutex_unlock(&ctrl->lock);
 }
 
-static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
+void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 {
 	struct nvmet_ctrl *ctrl;
 
@@ -189,6 +194,33 @@ static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 	}
 }
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port)
+{
+	struct nvmet_ctrl *ctrl;
+
+	mutex_lock(&subsys->lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		if (port && ctrl->port != port)
+			continue;
+		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_ANA_CHANGE))
+			continue;
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+				NVME_AER_NOTICE_ANA, NVME_LOG_ANA);
+	}
+	mutex_unlock(&subsys->lock);
+}
+
+void nvmet_port_send_ana_event(struct nvmet_port *port)
+{
+	struct nvmet_subsys_link *p;
+
+	down_read(&nvmet_config_sem);
+	list_for_each_entry(p, &port->subsystems, entry)
+		nvmet_send_ana_event(p->subsys, port);
+	up_read(&nvmet_config_sem);
+}
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops)
 {
 	int ret = 0;
@@ -241,6 +273,10 @@ int nvmet_enable_port(struct nvmet_port *port)
 		return ret;
 	}
 
+	/* If the transport didn't set inline_data_size, then disable it. */
+	if (port->inline_data_size < 0)
+		port->inline_data_size = 0;
+
 	port->enabled = true;
 	return 0;
 }
@@ -332,14 +368,18 @@ static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
 int nvmet_ns_enable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&subsys->lock);
+	ret = -EMFILE;
+	if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES)
+		goto out_unlock;
+	ret = 0;
 	if (ns->enabled)
 		goto out_unlock;
 
 	ret = nvmet_bdev_ns_enable(ns);
-	if (ret)
+	if (ret == -ENOTBLK)
 		ret = nvmet_file_ns_enable(ns);
 	if (ret)
 		goto out_unlock;
@@ -369,6 +409,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 
 		list_add_tail_rcu(&ns->dev_link, &old->dev_link);
 	}
+	subsys->nr_namespaces++;
 
 	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
@@ -409,6 +450,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	percpu_ref_exit(&ns->ref);
 
 	mutex_lock(&subsys->lock);
+	subsys->nr_namespaces--;
 	nvmet_ns_changed(subsys, ns->nsid);
 	nvmet_ns_dev_disable(ns);
 out_unlock:
@@ -419,6 +461,10 @@ void nvmet_ns_free(struct nvmet_ns *ns)
 {
 	nvmet_ns_disable(ns);
 
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[ns->anagrpid]--;
+	up_write(&nvmet_ana_sem);
+
 	kfree(ns->device_path);
 	kfree(ns);
 }
@@ -436,7 +482,14 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 
 	ns->nsid = nsid;
 	ns->subsys = subsys;
+
+	down_write(&nvmet_ana_sem);
+	ns->anagrpid = NVMET_DEFAULT_ANA_GRPID;
+	nvmet_ana_group_enabled[ns->anagrpid]++;
+	up_write(&nvmet_ana_sem);
+
 	uuid_gen(&ns->uuid);
+	ns->buffered_io = false;
 
 	return ns;
 }
@@ -542,6 +595,35 @@ int nvmet_sq_init(struct nvmet_sq *sq)
 }
 EXPORT_SYMBOL_GPL(nvmet_sq_init);
 
+static inline u16 nvmet_check_ana_state(struct nvmet_port *port,
+		struct nvmet_ns *ns)
+{
+	enum nvme_ana_state state = port->ana_state[ns->anagrpid];
+
+	if (unlikely(state == NVME_ANA_INACCESSIBLE))
+		return NVME_SC_ANA_INACCESSIBLE;
+	if (unlikely(state == NVME_ANA_PERSISTENT_LOSS))
+		return NVME_SC_ANA_PERSISTENT_LOSS;
+	if (unlikely(state == NVME_ANA_CHANGE))
+		return NVME_SC_ANA_TRANSITION;
+	return 0;
+}
+
+static inline u16 nvmet_io_cmd_check_access(struct nvmet_req *req)
+{
+	if (unlikely(req->ns->readonly)) {
+		switch (req->cmd->common.opcode) {
+		case nvme_cmd_read:
+		case nvme_cmd_flush:
+			break;
+		default:
+			return NVME_SC_NS_WRITE_PROTECTED;
+		}
+	}
+
+	return 0;
+}
+
 static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
@@ -554,6 +636,12 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
 	if (unlikely(!req->ns))
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+	ret = nvmet_check_ana_state(req->port, req->ns);
+	if (unlikely(ret))
+		return ret;
+	ret = nvmet_io_cmd_check_access(req);
+	if (unlikely(ret))
+		return ret;
 
 	if (req->ns->file)
 		return nvmet_file_parse_io_cmd(req);
@@ -870,6 +958,8 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	nvmet_init_cap(ctrl);
 
+	ctrl->port = req->port;
+
 	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
 	INIT_LIST_HEAD(&ctrl->async_events);
 
@@ -1109,6 +1199,15 @@ static int __init nvmet_init(void)
 {
 	int error;
 
+	nvmet_ana_group_enabled[NVMET_DEFAULT_ANA_GRPID] = 1;
+
+	buffered_io_wq = alloc_workqueue("nvmet-buffered-io-wq",
+			WQ_MEM_RECLAIM, 0);
+	if (!buffered_io_wq) {
+		error = -ENOMEM;
+		goto out;
+	}
+
 	error = nvmet_init_discovery();
 	if (error)
 		goto out;
@@ -1129,6 +1228,7 @@ static void __exit nvmet_exit(void)
 	nvmet_exit_configfs();
 	nvmet_exit_discovery();
 	ida_destroy(&cntlid_ida);
+	destroy_workqueue(buffered_io_wq);
 
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024);
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024);
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 08656b849bd6..eae29f493a07 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -171,7 +171,7 @@ static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req)
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->has_keyed_sgls)
 		id->sgls |= cpu_to_le32(1 << 2);
-	if (ctrl->ops->sqe_inline_size)
+	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);
 
 	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 408279cb6f2c..29b4b236afd8 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -58,8 +58,8 @@ struct nvmet_fc_ls_iod {
 	struct work_struct		work;
 } __aligned(sizeof(unsigned long long));
 
+/* desired maximum for a single sequence - if sg list allows it */
 #define NVMET_FC_MAX_SEQ_LENGTH		(256 * 1024)
-#define NVMET_FC_MAX_XFR_SGENTS		(NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE)
 
 enum nvmet_fcp_datadir {
 	NVMET_FCP_NODATA,
@@ -74,6 +74,7 @@ struct nvmet_fc_fcp_iod {
 	struct nvme_fc_cmd_iu		cmdiubuf;
 	struct nvme_fc_ersp_iu		rspiubuf;
 	dma_addr_t			rspdma;
+	struct scatterlist		*next_sg;
 	struct scatterlist		*data_sg;
 	int				data_sg_cnt;
 	u32				offset;
@@ -1025,8 +1026,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 	INIT_LIST_HEAD(&newrec->assoc_list);
 	kref_init(&newrec->ref);
 	ida_init(&newrec->assoc_cnt);
-	newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS,
-					template->max_sgl_segments);
+	newrec->max_sg_cnt = template->max_sgl_segments;
 
 	ret = nvmet_fc_alloc_ls_iodlist(newrec);
 	if (ret) {
@@ -1722,6 +1722,7 @@ nvmet_fc_alloc_tgt_pgs(struct nvmet_fc_fcp_iod *fod)
 				((fod->io_dir == NVMET_FCP_WRITE) ?
 					DMA_FROM_DEVICE : DMA_TO_DEVICE));
 				/* note: write from initiator perspective */
+	fod->next_sg = fod->data_sg;
 
 	return 0;
 
@@ -1866,24 +1867,49 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 				struct nvmet_fc_fcp_iod *fod, u8 op)
 {
 	struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+	struct scatterlist *sg = fod->next_sg;
 	unsigned long flags;
-	u32 tlen;
+	u32 remaininglen = fod->req.transfer_len - fod->offset;
+	u32 tlen = 0;
 	int ret;
 
 	fcpreq->op = op;
 	fcpreq->offset = fod->offset;
 	fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC;
 
-	tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE,
-			(fod->req.transfer_len - fod->offset));
+	/*
+	 * for next sequence:
+	 *  break at a sg element boundary
+	 *  attempt to keep sequence length capped at
+	 *    NVMET_FC_MAX_SEQ_LENGTH but allow sequence to
+	 *    be longer if a single sg element is larger
+	 *    than that amount. This is done to avoid creating
+	 *    a new sg list to use for the tgtport api.
+	 */
+	fcpreq->sg = sg;
+	fcpreq->sg_cnt = 0;
+	while (tlen < remaininglen &&
+	       fcpreq->sg_cnt < tgtport->max_sg_cnt &&
+	       tlen + sg_dma_len(sg) < NVMET_FC_MAX_SEQ_LENGTH) {
+		fcpreq->sg_cnt++;
+		tlen += sg_dma_len(sg);
+		sg = sg_next(sg);
+	}
+	if (tlen < remaininglen && fcpreq->sg_cnt == 0) {
+		fcpreq->sg_cnt++;
+		tlen += min_t(u32, sg_dma_len(sg), remaininglen);
+		sg = sg_next(sg);
+	}
+	if (tlen < remaininglen)
+		fod->next_sg = sg;
+	else
+		fod->next_sg = NULL;
+
 	fcpreq->transfer_length = tlen;
 	fcpreq->transferred_length = 0;
 	fcpreq->fcp_error = 0;
 	fcpreq->rsplen = 0;
 
-	fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE];
-	fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE);
-
 	/*
 	 * If the last READDATA request: check if LLDD supports
 	 * combined xfr with response.
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index e0b0f7df70c2..7bc9f6240432 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -124,6 +124,13 @@ static void nvmet_bdev_execute_flush(struct nvmet_req *req)
 	submit_bio(bio);
 }
 
+u16 nvmet_bdev_flush(struct nvmet_req *req)
+{
+	if (blkdev_issue_flush(req->ns->bdev, GFP_KERNEL, NULL))
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
+	return 0;
+}
+
 static u16 nvmet_bdev_discard_range(struct nvmet_ns *ns,
 		struct nvme_dsm_range *range, struct bio **bio)
 {
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 8c42b3a8c420..81a9dc5290a8 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -16,6 +16,8 @@
 void nvmet_file_ns_disable(struct nvmet_ns *ns)
 {
 	if (ns->file) {
+		if (ns->buffered_io)
+			flush_workqueue(buffered_io_wq);
 		mempool_destroy(ns->bvec_pool);
 		ns->bvec_pool = NULL;
 		kmem_cache_destroy(ns->bvec_cache);
@@ -27,11 +29,14 @@ void nvmet_file_ns_disable(struct nvmet_ns *ns)
 
 int nvmet_file_ns_enable(struct nvmet_ns *ns)
 {
-	int ret;
+	int flags = O_RDWR | O_LARGEFILE;
 	struct kstat stat;
+	int ret;
+
+	if (!ns->buffered_io)
+		flags |= O_DIRECT;
 
-	ns->file = filp_open(ns->device_path,
-			O_RDWR | O_LARGEFILE | O_DIRECT, 0);
+	ns->file = filp_open(ns->device_path, flags, 0);
 	if (IS_ERR(ns->file)) {
 		pr_err("failed to open file %s: (%ld)\n",
 				ns->device_path, PTR_ERR(ns->file));
@@ -100,7 +105,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
 
 	iocb->ki_pos = pos;
 	iocb->ki_filp = req->ns->file;
-	iocb->ki_flags = IOCB_DIRECT | ki_flags;
+	iocb->ki_flags = ki_flags | iocb_flags(req->ns->file);
 
 	ret = call_iter(iocb, &iter);
 
@@ -140,6 +145,12 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 		return;
 	}
 
+	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
+	if (unlikely(pos + req->data_len > req->ns->size)) {
+		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		return;
+	}
+
 	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
 		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
 				GFP_KERNEL);
@@ -155,8 +166,6 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 			is_sync = true;
 	}
 
-	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
-
 	memset(&req->f.iocb, 0, sizeof(struct kiocb));
 	for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) {
 		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter);
@@ -189,14 +198,31 @@ out:
 	nvmet_file_submit_bvec(req, pos, bv_cnt, total_len);
 }
 
-static void nvmet_file_flush_work(struct work_struct *w)
+static void nvmet_file_buffered_io_work(struct work_struct *w)
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
-	int ret;
 
-	ret = vfs_fsync(req->ns->file, 1);
+	nvmet_file_execute_rw(req);
+}
 
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+static void nvmet_file_execute_rw_buffered_io(struct nvmet_req *req)
+{
+	INIT_WORK(&req->f.work, nvmet_file_buffered_io_work);
+	queue_work(buffered_io_wq, &req->f.work);
+}
+
+u16 nvmet_file_flush(struct nvmet_req *req)
+{
+	if (vfs_fsync(req->ns->file, 1) < 0)
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
+	return 0;
+}
+
+static void nvmet_file_flush_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+
+	nvmet_req_complete(req, nvmet_file_flush(req));
 }
 
 static void nvmet_file_execute_flush(struct nvmet_req *req)
@@ -209,22 +235,30 @@ static void nvmet_file_execute_discard(struct nvmet_req *req)
 {
 	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	struct nvme_dsm_range range;
-	loff_t offset;
-	loff_t len;
-	int i, ret;
+	loff_t offset, len;
+	u16 ret;
+	int i;
 
 	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
-		if (nvmet_copy_from_sgl(req, i * sizeof(range), &range,
-					sizeof(range)))
+		ret = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+					sizeof(range));
+		if (ret)
 			break;
+
 		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
 		len = le32_to_cpu(range.nlb) << req->ns->blksize_shift;
-		ret = vfs_fallocate(req->ns->file, mode, offset, len);
-		if (ret)
+		if (offset + len > req->ns->size) {
+			ret = NVME_SC_LBA_RANGE | NVME_SC_DNR;
 			break;
+		}
+
+		if (vfs_fallocate(req->ns->file, mode, offset, len)) {
+			ret = NVME_SC_INTERNAL | NVME_SC_DNR;
+			break;
+		}
 	}
 
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	nvmet_req_complete(req, ret);
 }
 
 static void nvmet_file_dsm_work(struct work_struct *w)
@@ -263,6 +297,11 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w)
 	len = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
 			req->ns->blksize_shift);
 
+	if (unlikely(offset + len > req->ns->size)) {
+		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		return;
+	}
+
 	ret = vfs_fallocate(req->ns->file, mode, offset, len);
 	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
 }
@@ -280,7 +319,10 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	switch (cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
-		req->execute = nvmet_file_execute_rw;
+		if (req->ns->buffered_io)
+			req->execute = nvmet_file_execute_rw_buffered_io;
+		else
+			req->execute = nvmet_file_execute_rw;
 		req->data_len = nvmet_rw_len(req);
 		return 0;
 	case nvme_cmd_flush:
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index d8d91f04bd7e..9908082b32c4 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -162,7 +162,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_status_t ret;
 
 	if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready))
-		return nvmf_fail_nonready_command(req);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req);
 
 	ret = nvme_setup_cmd(ns, req, &iod->cmd);
 	if (ret)
@@ -227,6 +227,7 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set,
 {
 	struct nvme_loop_ctrl *ctrl = set->driver_data;
 
+	nvme_req(req)->ctrl = &ctrl->ctrl;
 	return nvme_loop_init_iod(ctrl, blk_mq_rq_to_pdu(req),
 			(set == &ctrl->tag_set) ? hctx_idx + 1 : 0);
 }
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 480dfe10fad9..ec9af4ee03b6 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -30,12 +30,11 @@
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
 
-
 /*
  * Supported optional AENs:
  */
 #define NVMET_AEN_CFG_OPTIONAL \
-	NVME_AEN_CFG_NS_ATTR
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_ANA_CHANGE)
 
 /*
  * Plus mandatory SMART AENs (we'll never send them, but allow enabling them):
@@ -59,12 +58,15 @@ struct nvmet_ns {
 	struct percpu_ref	ref;
 	struct block_device	*bdev;
 	struct file		*file;
+	bool			readonly;
 	u32			nsid;
 	u32			blksize_shift;
 	loff_t			size;
 	u8			nguid[16];
 	uuid_t			uuid;
+	u32			anagrpid;
 
+	bool			buffered_io;
 	bool			enabled;
 	struct nvmet_subsys	*subsys;
 	const char		*device_path;
@@ -97,6 +99,18 @@ struct nvmet_sq {
 	struct completion	confirm_done;
 };
 
+struct nvmet_ana_group {
+	struct config_group	group;
+	struct nvmet_port	*port;
+	u32			grpid;
+};
+
+static inline struct nvmet_ana_group *to_ana_group(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_ana_group,
+			group);
+}
+
 /**
  * struct nvmet_port -	Common structure to keep port
  *				information for the target.
@@ -114,8 +128,12 @@ struct nvmet_port {
 	struct list_head		subsystems;
 	struct config_group		referrals_group;
 	struct list_head		referrals;
+	struct config_group		ana_groups_group;
+	struct nvmet_ana_group		ana_default_group;
+	enum nvme_ana_state		*ana_state;
 	void				*priv;
 	bool				enabled;
+	int				inline_data_size;
 };
 
 static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
@@ -124,6 +142,13 @@ static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
 			group);
 }
 
+static inline struct nvmet_port *ana_groups_to_port(
+		struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_port,
+			ana_groups_group);
+}
+
 struct nvmet_ctrl {
 	struct nvmet_subsys	*subsys;
 	struct nvmet_cq		**cqs;
@@ -138,6 +163,8 @@ struct nvmet_ctrl {
 	u16			cntlid;
 	u32			kato;
 
+	struct nvmet_port	*port;
+
 	u32			aen_enabled;
 	unsigned long		aen_masked;
 	struct nvmet_req	*async_event_cmds[NVMET_ASYNC_EVENTS];
@@ -166,6 +193,7 @@ struct nvmet_subsys {
 	struct kref		ref;
 
 	struct list_head	namespaces;
+	unsigned int		nr_namespaces;
 	unsigned int		max_nsid;
 
 	struct list_head	ctrls;
@@ -225,7 +253,6 @@ struct nvmet_req;
 struct nvmet_fabrics_ops {
 	struct module *owner;
 	unsigned int type;
-	unsigned int sqe_inline_size;
 	unsigned int msdbd;
 	bool has_keyed_sgls : 1;
 	void (*queue_response)(struct nvmet_req *req);
@@ -269,6 +296,8 @@ struct nvmet_req {
 	const struct nvmet_fabrics_ops *ops;
 };
 
+extern struct workqueue_struct *buffered_io_wq;
+
 static inline void nvmet_set_status(struct nvmet_req *req, u16 status)
 {
 	req->rsp->status = cpu_to_le16(status << 1);
@@ -337,6 +366,10 @@ void nvmet_ns_disable(struct nvmet_ns *ns);
 struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid);
 void nvmet_ns_free(struct nvmet_ns *ns);
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port);
+void nvmet_port_send_ana_event(struct nvmet_port *port);
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops);
 void nvmet_unregister_transport(const struct nvmet_fabrics_ops *ops);
 
@@ -357,6 +390,22 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 #define NVMET_QUEUE_SIZE	1024
 #define NVMET_NR_QUEUES		128
 #define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
+
+/*
+ * Nice round number that makes a list of nsids fit into a page.
+ * Should become tunable at some point in the future.
+ */
+#define NVMET_MAX_NAMESPACES	1024
+
+/*
+ * 0 is not a valid ANA group ID, so we start numbering at 1.
+ *
+ * ANA Group 1 exists without manual intervention, has namespaces assigned to it
+ * by default, and is available in an optimized state through all ports.
+ */
+#define NVMET_MAX_ANAGRPS	128
+#define NVMET_DEFAULT_ANA_GRPID	1
+
 #define NVMET_KAS		10
 #define NVMET_DISC_KATO		120
 
@@ -370,6 +419,10 @@ extern struct nvmet_subsys *nvmet_disc_subsys;
 extern u64 nvmet_genctr;
 extern struct rw_semaphore nvmet_config_sem;
 
+extern u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+extern u64 nvmet_ana_chgcnt;
+extern struct rw_semaphore nvmet_ana_sem;
+
 bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
 		const char *hostnqn);
 
@@ -377,6 +430,9 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns);
 int nvmet_file_ns_enable(struct nvmet_ns *ns);
 void nvmet_bdev_ns_disable(struct nvmet_ns *ns);
 void nvmet_file_ns_disable(struct nvmet_ns *ns);
+u16 nvmet_bdev_flush(struct nvmet_req *req);
+u16 nvmet_file_flush(struct nvmet_req *req);
+void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid);
 
 static inline u32 nvmet_rw_len(struct nvmet_req *req)
 {
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 52e0c5d579a7..e7f43d1e1779 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -33,16 +33,17 @@
 #include "nvmet.h"
 
 /*
- * We allow up to a page of inline data to go with the SQE
+ * We allow at least 1 page, up to 4 SGEs, and up to 16KB of inline data
  */
-#define NVMET_RDMA_INLINE_DATA_SIZE	PAGE_SIZE
+#define NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE	PAGE_SIZE
+#define NVMET_RDMA_MAX_INLINE_SGE		4
+#define NVMET_RDMA_MAX_INLINE_DATA_SIZE		max_t(int, SZ_16K, PAGE_SIZE)
 
 struct nvmet_rdma_cmd {
-	struct ib_sge		sge[2];
+	struct ib_sge		sge[NVMET_RDMA_MAX_INLINE_SGE + 1];
 	struct ib_cqe		cqe;
 	struct ib_recv_wr	wr;
-	struct scatterlist	inline_sg;
-	struct page		*inline_page;
+	struct scatterlist	inline_sg[NVMET_RDMA_MAX_INLINE_SGE];
 	struct nvme_command     *nvme_cmd;
 	struct nvmet_rdma_queue	*queue;
 };
@@ -116,6 +117,8 @@ struct nvmet_rdma_device {
 	size_t			srq_size;
 	struct kref		ref;
 	struct list_head	entry;
+	int			inline_data_size;
+	int			inline_page_count;
 };
 
 static bool nvmet_rdma_use_srq;
@@ -138,6 +141,11 @@ static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);
 
 static const struct nvmet_fabrics_ops nvmet_rdma_ops;
 
+static int num_pages(int len)
+{
+	return 1 + (((len - 1) & PAGE_MASK) >> PAGE_SHIFT);
+}
+
 /* XXX: really should move to a generic header sooner or later.. */
 static inline u32 get_unaligned_le24(const u8 *p)
 {
@@ -184,6 +192,71 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
 	spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags);
 }
 
+static void nvmet_rdma_free_inline_pages(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_cmd *c)
+{
+	struct scatterlist *sg;
+	struct ib_sge *sge;
+	int i;
+
+	if (!ndev->inline_data_size)
+		return;
+
+	sg = c->inline_sg;
+	sge = &c->sge[1];
+
+	for (i = 0; i < ndev->inline_page_count; i++, sg++, sge++) {
+		if (sge->length)
+			ib_dma_unmap_page(ndev->device, sge->addr,
+					sge->length, DMA_FROM_DEVICE);
+		if (sg_page(sg))
+			__free_page(sg_page(sg));
+	}
+}
+
+static int nvmet_rdma_alloc_inline_pages(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_cmd *c)
+{
+	struct scatterlist *sg;
+	struct ib_sge *sge;
+	struct page *pg;
+	int len;
+	int i;
+
+	if (!ndev->inline_data_size)
+		return 0;
+
+	sg = c->inline_sg;
+	sg_init_table(sg, ndev->inline_page_count);
+	sge = &c->sge[1];
+	len = ndev->inline_data_size;
+
+	for (i = 0; i < ndev->inline_page_count; i++, sg++, sge++) {
+		pg = alloc_page(GFP_KERNEL);
+		if (!pg)
+			goto out_err;
+		sg_assign_page(sg, pg);
+		sge->addr = ib_dma_map_page(ndev->device,
+			pg, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+		if (ib_dma_mapping_error(ndev->device, sge->addr))
+			goto out_err;
+		sge->length = min_t(int, len, PAGE_SIZE);
+		sge->lkey = ndev->pd->local_dma_lkey;
+		len -= sge->length;
+	}
+
+	return 0;
+out_err:
+	for (; i >= 0; i--, sg--, sge--) {
+		if (sge->length)
+			ib_dma_unmap_page(ndev->device, sge->addr,
+					sge->length, DMA_FROM_DEVICE);
+		if (sg_page(sg))
+			__free_page(sg_page(sg));
+	}
+	return -ENOMEM;
+}
+
 static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
 			struct nvmet_rdma_cmd *c, bool admin)
 {
@@ -200,33 +273,17 @@ static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
 	c->sge[0].length = sizeof(*c->nvme_cmd);
 	c->sge[0].lkey = ndev->pd->local_dma_lkey;
 
-	if (!admin) {
-		c->inline_page = alloc_pages(GFP_KERNEL,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-		if (!c->inline_page)
-			goto out_unmap_cmd;
-		c->sge[1].addr = ib_dma_map_page(ndev->device,
-				c->inline_page, 0, NVMET_RDMA_INLINE_DATA_SIZE,
-				DMA_FROM_DEVICE);
-		if (ib_dma_mapping_error(ndev->device, c->sge[1].addr))
-			goto out_free_inline_page;
-		c->sge[1].length = NVMET_RDMA_INLINE_DATA_SIZE;
-		c->sge[1].lkey = ndev->pd->local_dma_lkey;
-	}
+	if (!admin && nvmet_rdma_alloc_inline_pages(ndev, c))
+		goto out_unmap_cmd;
 
 	c->cqe.done = nvmet_rdma_recv_done;
 
 	c->wr.wr_cqe = &c->cqe;
 	c->wr.sg_list = c->sge;
-	c->wr.num_sge = admin ? 1 : 2;
+	c->wr.num_sge = admin ? 1 : ndev->inline_page_count + 1;
 
 	return 0;
 
-out_free_inline_page:
-	if (!admin) {
-		__free_pages(c->inline_page,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-	}
 out_unmap_cmd:
 	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
 			sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
@@ -240,12 +297,8 @@ out:
 static void nvmet_rdma_free_cmd(struct nvmet_rdma_device *ndev,
 		struct nvmet_rdma_cmd *c, bool admin)
 {
-	if (!admin) {
-		ib_dma_unmap_page(ndev->device, c->sge[1].addr,
-				NVMET_RDMA_INLINE_DATA_SIZE, DMA_FROM_DEVICE);
-		__free_pages(c->inline_page,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-	}
+	if (!admin)
+		nvmet_rdma_free_inline_pages(ndev, c);
 	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
 				sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
 	kfree(c->nvme_cmd);
@@ -383,14 +436,21 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
 		struct nvmet_rdma_cmd *cmd)
 {
 	struct ib_recv_wr *bad_wr;
+	int ret;
 
 	ib_dma_sync_single_for_device(ndev->device,
 		cmd->sge[0].addr, cmd->sge[0].length,
 		DMA_FROM_DEVICE);
 
 	if (ndev->srq)
-		return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
-	return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
+		ret = ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
+	else
+		ret = ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
+
+	if (unlikely(ret))
+		pr_err("post_recv cmd failed\n");
+
+	return ret;
 }
 
 static void nvmet_rdma_process_wr_wait_list(struct nvmet_rdma_queue *queue)
@@ -429,7 +489,7 @@ static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp)
 				rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
 	}
 
-	if (rsp->req.sg != &rsp->cmd->inline_sg)
+	if (rsp->req.sg != rsp->cmd->inline_sg)
 		sgl_free(rsp->req.sg);
 
 	if (unlikely(!list_empty_careful(&queue->rsp_wr_wait_list)))
@@ -493,7 +553,7 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req)
 		rsp->send_sge.addr, rsp->send_sge.length,
 		DMA_TO_DEVICE);
 
-	if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) {
+	if (unlikely(ib_post_send(cm_id->qp, first_wr, &bad_wr))) {
 		pr_err("sending cmd response failed\n");
 		nvmet_rdma_release_rsp(rsp);
 	}
@@ -529,10 +589,25 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc)
 static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len,
 		u64 off)
 {
-	sg_init_table(&rsp->cmd->inline_sg, 1);
-	sg_set_page(&rsp->cmd->inline_sg, rsp->cmd->inline_page, len, off);
-	rsp->req.sg = &rsp->cmd->inline_sg;
-	rsp->req.sg_cnt = 1;
+	int sg_count = num_pages(len);
+	struct scatterlist *sg;
+	int i;
+
+	sg = rsp->cmd->inline_sg;
+	for (i = 0; i < sg_count; i++, sg++) {
+		if (i < sg_count - 1)
+			sg_unmark_end(sg);
+		else
+			sg_mark_end(sg);
+		sg->offset = off;
+		sg->length = min_t(int, len, PAGE_SIZE - off);
+		len -= sg->length;
+		if (!i)
+			off = 0;
+	}
+
+	rsp->req.sg = rsp->cmd->inline_sg;
+	rsp->req.sg_cnt = sg_count;
 }
 
 static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
@@ -544,7 +619,7 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
 	if (!nvme_is_write(rsp->req.cmd))
 		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 
-	if (off + len > NVMET_RDMA_INLINE_DATA_SIZE) {
+	if (off + len > rsp->queue->dev->inline_data_size) {
 		pr_err("invalid inline data offset!\n");
 		return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
 	}
@@ -743,7 +818,7 @@ static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
 	srq_size = 4095;	/* XXX: tune */
 
 	srq_attr.attr.max_wr = srq_size;
-	srq_attr.attr.max_sge = 2;
+	srq_attr.attr.max_sge = 1 + ndev->inline_page_count;
 	srq_attr.attr.srq_limit = 0;
 	srq_attr.srq_type = IB_SRQT_BASIC;
 	srq = ib_create_srq(ndev->pd, &srq_attr);
@@ -765,11 +840,16 @@ static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
 	ndev->srq = srq;
 	ndev->srq_size = srq_size;
 
-	for (i = 0; i < srq_size; i++)
-		nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
+	for (i = 0; i < srq_size; i++) {
+		ret = nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
+		if (ret)
+			goto out_free_cmds;
+	}
 
 	return 0;
 
+out_free_cmds:
+	nvmet_rdma_free_cmds(ndev, ndev->srq_cmds, ndev->srq_size, false);
 out_destroy_srq:
 	ib_destroy_srq(srq);
 	return ret;
@@ -793,7 +873,10 @@ static void nvmet_rdma_free_dev(struct kref *ref)
 static struct nvmet_rdma_device *
 nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 {
+	struct nvmet_port *port = cm_id->context;
 	struct nvmet_rdma_device *ndev;
+	int inline_page_count;
+	int inline_sge_count;
 	int ret;
 
 	mutex_lock(&device_list_mutex);
@@ -807,6 +890,18 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 	if (!ndev)
 		goto out_err;
 
+	inline_page_count = num_pages(port->inline_data_size);
+	inline_sge_count = max(cm_id->device->attrs.max_sge_rd,
+				cm_id->device->attrs.max_sge) - 1;
+	if (inline_page_count > inline_sge_count) {
+		pr_warn("inline_data_size %d cannot be supported by device %s. Reducing to %lu.\n",
+			port->inline_data_size, cm_id->device->name,
+			inline_sge_count * PAGE_SIZE);
+		port->inline_data_size = inline_sge_count * PAGE_SIZE;
+		inline_page_count = inline_sge_count;
+	}
+	ndev->inline_data_size = port->inline_data_size;
+	ndev->inline_page_count = inline_page_count;
 	ndev->device = cm_id->device;
 	kref_init(&ndev->ref);
 
@@ -881,7 +976,7 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 	} else {
 		/* +1 for drain */
 		qp_attr.cap.max_recv_wr = 1 + queue->recv_queue_size;
-		qp_attr.cap.max_recv_sge = 2;
+		qp_attr.cap.max_recv_sge = 1 + ndev->inline_page_count;
 	}
 
 	ret = rdma_create_qp(queue->cm_id, ndev->pd, &qp_attr);
@@ -899,13 +994,17 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 	if (!ndev->srq) {
 		for (i = 0; i < queue->recv_queue_size; i++) {
 			queue->cmds[i].queue = queue;
-			nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
+			ret = nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
+			if (ret)
+				goto err_destroy_qp;
 		}
 	}
 
 out:
 	return ret;
 
+err_destroy_qp:
+	rdma_destroy_qp(queue->cm_id);
 err_destroy_cq:
 	ib_free_cq(queue->cq);
 	goto out;
@@ -1379,6 +1478,15 @@ static int nvmet_rdma_add_port(struct nvmet_port *port)
 		return -EINVAL;
 	}
 
+	if (port->inline_data_size < 0) {
+		port->inline_data_size = NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE;
+	} else if (port->inline_data_size > NVMET_RDMA_MAX_INLINE_DATA_SIZE) {
+		pr_warn("inline_data_size %u is too large, reducing to %u\n",
+			port->inline_data_size,
+			NVMET_RDMA_MAX_INLINE_DATA_SIZE);
+		port->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
+	}
+
 	ret = inet_pton_with_scope(&init_net, af, port->disc_addr.traddr,
 			port->disc_addr.trsvcid, &addr);
 	if (ret) {
@@ -1456,7 +1564,6 @@ static void nvmet_rdma_disc_port_addr(struct nvmet_req *req,
 static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.owner			= THIS_MODULE,
 	.type			= NVMF_TRTYPE_RDMA,
-	.sqe_inline_size	= NVMET_RDMA_INLINE_DATA_SIZE,
 	.msdbd			= 1,
 	.has_keyed_sgls		= 1,
 	.add_port		= nvmet_rdma_add_port,
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index b5b0cdc21d01..514d1dfc5630 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -936,6 +936,10 @@ struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *cell_id)
 			return cell;
 	}
 
+	/* NULL cell_id only allowed for device tree; invalid otherwise */
+	if (!cell_id)
+		return ERR_PTR(-EINVAL);
+
 	return nvmem_cell_get_from_list(cell_id);
 }
 EXPORT_SYMBOL_GPL(nvmem_cell_get);
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 53349912ac75..7ddbf0a1ab86 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -846,7 +846,7 @@ EXPORT_SYMBOL(of_iomap);
  *			   for a given device_node
  * @device:	the device whose io range will be mapped
  * @index:	index of the io range
- * @name:	name of the resource
+ * @name:	name "override" for the memory region request or NULL
  *
  * Returns a pointer to the requested and mapped memory or an ERR_PTR() encoded
  * error code on failure. Usage example:
@@ -856,7 +856,7 @@ EXPORT_SYMBOL(of_iomap);
  *		return PTR_ERR(base);
  */
 void __iomem *of_io_request_and_map(struct device_node *np, int index,
-					const char *name)
+				    const char *name)
 {
 	struct resource res;
 	void __iomem *mem;
@@ -864,6 +864,8 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
 	if (of_address_to_resource(np, index, &res))
 		return IOMEM_ERR_PTR(-EINVAL);
 
+	if (!name)
+		name = res.name;
 	if (!request_mem_region(res.start, resource_size(&res), name))
 		return IOMEM_ERR_PTR(-EBUSY);
 
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 848f549164cd..466e3c8582f0 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -102,7 +102,7 @@ static u32 phandle_cache_mask;
  *   - the phandle lookup overhead reduction provided by the cache
  *     will likely be less
  */
-static void of_populate_phandle_cache(void)
+void of_populate_phandle_cache(void)
 {
 	unsigned long flags;
 	u32 cache_entries;
@@ -134,8 +134,7 @@ out:
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 }
 
-#ifndef CONFIG_MODULES
-static int __init of_free_phandle_cache(void)
+int of_free_phandle_cache(void)
 {
 	unsigned long flags;
 
@@ -148,6 +147,7 @@ static int __init of_free_phandle_cache(void)
 
 	return 0;
 }
+#if !defined(CONFIG_MODULES)
 late_initcall_sync(of_free_phandle_cache);
 #endif
 
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 33d85511d790..5957cd4fa262 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -127,20 +127,20 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	}
 
 	/*
-	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to
-	 * setup the correct supported mask.
+	 * If @dev is expected to be DMA-capable then the bus code that created
+	 * it should have initialised its dma_mask pointer by this point. For
+	 * now, we'll continue the legacy behaviour of coercing it to the
+	 * coherent mask if not, but we'll no longer do so quietly.
 	 */
-	if (!dev->coherent_dma_mask)
-		dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	/*
-	 * Set it to coherent_dma_mask by default if the architecture
-	 * code has not set it.
-	 */
-	if (!dev->dma_mask)
+	if (!dev->dma_mask) {
+		dev_warn(dev, "DMA mask not set\n");
 		dev->dma_mask = &dev->coherent_dma_mask;
+	}
 
-	if (!size)
+	if (!size && dev->coherent_dma_mask)
 		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	else if (!size)
+		size = 1ULL << 32;
 
 	dev->dma_pfn_offset = offset;
 
@@ -149,6 +149,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	 * set by the driver.
 	 */
 	mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1);
+	dev->bus_dma_mask = mask;
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
 
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 6da20b9688f7..800ad252cf9c 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1034,14 +1034,7 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 	bool hotpluggable;
 
 	/* We are scanning "memory" nodes only */
-	if (type == NULL) {
-		/*
-		 * The longtrail doesn't have a device_type on the
-		 * /memory node, so look for the node called /memory@0.
-		 */
-		if (!IS_ENABLED(CONFIG_PPC32) || depth != 1 || strcmp(uname, "memory@0") != 0)
-			return 0;
-	} else if (strcmp(type, "memory") != 0)
+	if (type == NULL || strcmp(type, "memory") != 0)
 		return 0;
 
 	reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l);
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index 891d780c076a..216175d11d3d 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -79,6 +79,8 @@ int of_resolve_phandles(struct device_node *tree);
 #if defined(CONFIG_OF_OVERLAY)
 void of_overlay_mutex_lock(void);
 void of_overlay_mutex_unlock(void);
+int of_free_phandle_cache(void);
+void of_populate_phandle_cache(void);
 #else
 static inline void of_overlay_mutex_lock(void) {};
 static inline void of_overlay_mutex_unlock(void) {};
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 7baa53e5b1d7..eda57ef12fd0 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -804,6 +804,8 @@ static int of_overlay_apply(const void *fdt, struct device_node *tree,
 		goto err_free_overlay_changeset;
 	}
 
+	of_populate_phandle_cache();
+
 	ret = __of_changeset_apply_notify(&ovcs->cset);
 	if (ret)
 		pr_err("overlay changeset entry notify error %d\n", ret);
@@ -1046,8 +1048,17 @@ int of_overlay_remove(int *ovcs_id)
 
 	list_del(&ovcs->ovcs_list);
 
+	/*
+	 * Disable phandle cache.  Avoids race condition that would arise
+	 * from removing cache entry when the associated node is deleted.
+	 */
+	of_free_phandle_cache();
+
 	ret_apply = 0;
 	ret = __of_changeset_revert_entries(&ovcs->cset, &ret_apply);
+
+	of_populate_phandle_cache();
+
 	if (ret) {
 		if (ret_apply)
 			devicetree_state_flags |= DTSF_REVERT_FAIL;
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 6925d993e1f0..7ba90c290a42 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -185,6 +185,9 @@ static struct platform_device *of_platform_device_create_pdata(
 	if (!dev)
 		goto err_clear_flag;
 
+	dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	if (!dev->dev.dma_mask)
+		dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
 	dev->dev.bus = &platform_bus_type;
 	dev->dev.platform_data = platform_data;
 	of_msi_configure(&dev->dev, dev->dev.of_node);
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 535201984b8b..1b2cfe51e8d7 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -28,10 +28,10 @@ obj-$(CONFIG_PCI_PF_STUB)	+= pci-pf-stub.o
 obj-$(CONFIG_PCI_ECAM)		+= ecam.o
 obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
 
-obj-y				+= controller/
-obj-y				+= switch/
-
 # Endpoint library must be initialized before its users
 obj-$(CONFIG_PCI_ENDPOINT)	+= endpoint/
 
+obj-y				+= controller/
+obj-y				+= switch/
+
 ccflags-$(CONFIG_PCI_DEBUG) := -DDEBUG
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 35b7fc87eac5..5cb40b2518f9 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -330,7 +330,7 @@ void pci_bus_add_device(struct pci_dev *dev)
 		return;
 	}
 
-	dev->is_added = 1;
+	pci_dev_assign_added(dev, true);
 }
 EXPORT_SYMBOL_GPL(pci_bus_add_device);
 
@@ -347,14 +347,14 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/* Skip already-added devices */
-		if (dev->is_added)
+		if (pci_dev_is_added(dev))
 			continue;
 		pci_bus_add_device(dev);
 	}
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/* Skip if device attach failed */
-		if (!dev->is_added)
+		if (!pci_dev_is_added(dev))
 			continue;
 		child = dev->subordinate;
 		if (child)
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 18fa09b3ac8f..cc9fa02d32a0 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -96,7 +96,6 @@ config PCI_HOST_GENERIC
 	depends on OF
 	select PCI_HOST_COMMON
 	select IRQ_DOMAIN
-	select PCI_DOMAINS
 	help
 	  Say Y here if you want to support a simple generic PCI host
 	  controller, such as the one emulated by kvmtool.
@@ -138,7 +137,6 @@ config PCI_VERSATILE
 
 config PCIE_IPROC
 	tristate
-	select PCI_DOMAINS
 	help
 	  This enables the iProc PCIe core controller support for Broadcom's
 	  iProc family of SoCs. An appropriate bus interface driver needs
@@ -176,7 +174,6 @@ config PCIE_IPROC_MSI
 config PCIE_ALTERA
 	bool "Altera PCIe controller"
 	depends on ARM || NIOS2 || COMPILE_TEST
-	select PCI_DOMAINS
 	help
 	  Say Y here if you want to enable PCIe controller support on Altera
 	  FPGA.
diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index 16f52c626b4b..91b0194240a5 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -58,7 +58,6 @@ config PCIE_DW_PLAT_HOST
 	depends on PCI && PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW_HOST
 	select PCIE_DW_PLAT
-	default y
 	help
 	  Enables support for the PCIe controller in the Designware IP to
 	  work in host mode. There are two instances of PCIe controller in
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 781aa03aeede..29a05759a294 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -363,7 +363,8 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	resource_list_for_each_entry_safe(win, tmp, &bridge->windows) {
 		switch (resource_type(win->res)) {
 		case IORESOURCE_IO:
-			ret = pci_remap_iospace(win->res, pp->io_base);
+			ret = devm_pci_remap_iospace(dev, win->res,
+						     pp->io_base);
 			if (ret) {
 				dev_warn(dev, "Error %d: failed to map resource %pR\n",
 					 ret, win->res);
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index d3172d5d3d35..0fae816fba39 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -849,7 +849,7 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)
 					     0,	0xF8000000, 0,
 					     lower_32_bits(res->start),
 					     OB_PCIE_IO);
-			err = pci_remap_iospace(res, iobase);
+			err = devm_pci_remap_iospace(dev, res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);
diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c
index a1ebe9ed441f..bf5ece5d9291 100644
--- a/drivers/pci/controller/pci-ftpci100.c
+++ b/drivers/pci/controller/pci-ftpci100.c
@@ -355,11 +355,13 @@ static int faraday_pci_setup_cascaded_irq(struct faraday_pci *p)
 	irq = of_irq_get(intc, 0);
 	if (irq <= 0) {
 		dev_err(p->dev, "failed to get parent IRQ\n");
+		of_node_put(intc);
 		return irq ?: -EINVAL;
 	}
 
 	p->irqdomain = irq_domain_add_linear(intc, PCI_NUM_INTX,
 					     &faraday_pci_irqdomain_ops, p);
+	of_node_put(intc);
 	if (!p->irqdomain) {
 		dev_err(p->dev, "failed to create Gemini PCI IRQ domain\n");
 		return -EINVAL;
@@ -501,7 +503,7 @@ static int faraday_pci_probe(struct platform_device *pdev)
 				dev_err(dev, "illegal IO mem size\n");
 				return -EINVAL;
 			}
-			ret = pci_remap_iospace(io, io_base);
+			ret = devm_pci_remap_iospace(dev, io, io_base);
 			if (ret) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 ret, io);
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 6cc5036ac83c..d4d4a55f09f8 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -45,6 +45,7 @@
 #include <linux/irqdomain.h>
 #include <asm/irqdomain.h>
 #include <asm/apic.h>
+#include <linux/irq.h>
 #include <linux/msi.h>
 #include <linux/hyperv.h>
 #include <linux/refcount.h>
@@ -1073,6 +1074,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	struct pci_bus *pbus;
 	struct pci_dev *pdev;
 	struct cpumask *dest;
+	unsigned long flags;
 	struct compose_comp_ctxt comp;
 	struct tran_int_desc *int_desc;
 	struct {
@@ -1164,14 +1166,15 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		 * the channel callback directly when channel->target_cpu is
 		 * the current CPU. When the higher level interrupt code
 		 * calls us with interrupt enabled, let's add the
-		 * local_bh_disable()/enable() to avoid race.
+		 * local_irq_save()/restore() to avoid race:
+		 * hv_pci_onchannelcallback() can also run in tasklet.
 		 */
-		local_bh_disable();
+		local_irq_save(flags);
 
 		if (hbus->hdev->channel->target_cpu == smp_processor_id())
 			hv_pci_onchannelcallback(hbus);
 
-		local_bh_enable();
+		local_irq_restore(flags);
 
 		if (hpdev->state == hv_pcichild_ejecting) {
 			dev_err_once(&hbus->hdev->device,
diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c
index 68b8bfbdb867..d219404bad92 100644
--- a/drivers/pci/controller/pci-v3-semi.c
+++ b/drivers/pci/controller/pci-v3-semi.c
@@ -537,7 +537,7 @@ static int v3_pci_setup_resource(struct v3_pci *v3,
 		v3->io_bus_addr = io->start - win->offset;
 		dev_dbg(dev, "I/O window %pR, bus addr %pap\n",
 			io, &v3->io_bus_addr);
-		ret = pci_remap_iospace(io, io_base);
+		ret = devm_pci_remap_iospace(dev, io, io_base);
 		if (ret) {
 			dev_warn(dev,
 				 "error %d: failed to map resource %pR\n",
diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c
index 994f32061b32..f59ad2728c0b 100644
--- a/drivers/pci/controller/pci-versatile.c
+++ b/drivers/pci/controller/pci-versatile.c
@@ -82,7 +82,7 @@ static int versatile_pci_parse_request_of_pci_ranges(struct device *dev,
 
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
-			err = pci_remap_iospace(res, iobase);
+			err = devm_pci_remap_iospace(dev, res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);
diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c
index d854d67e873c..ffda3e8b4742 100644
--- a/drivers/pci/controller/pci-xgene.c
+++ b/drivers/pci/controller/pci-xgene.c
@@ -423,7 +423,7 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port,
 		case IORESOURCE_IO:
 			xgene_pcie_setup_ob_reg(port, res, OMR3BARL, io_base,
 						res->start - window->offset);
-			ret = pci_remap_iospace(res, io_base);
+			ret = devm_pci_remap_iospace(dev, res, io_base);
 			if (ret < 0)
 				return ret;
 			break;
diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index 0baabe30858f..861dda69f366 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -1109,7 +1109,7 @@ static int mtk_pcie_request_resources(struct mtk_pcie *pcie)
 	if (err < 0)
 		return err;
 
-	pci_remap_iospace(&pcie->pio, pcie->io.start);
+	devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start);
 
 	return 0;
 }
diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c
index 4d6c20e47bed..cf0aa7cee5b0 100644
--- a/drivers/pci/controller/pcie-mobiveil.c
+++ b/drivers/pci/controller/pcie-mobiveil.c
@@ -107,7 +107,7 @@
 #define CFG_WINDOW_TYPE	0
 #define IO_WINDOW_TYPE		1
 #define MEM_WINDOW_TYPE	2
-#define IB_WIN_SIZE		(256 * 1024 * 1024 * 1024)
+#define IB_WIN_SIZE		((u64)256 * 1024 * 1024 * 1024)
 #define MAX_PIO_WINDOWS	8
 
 /* Parameters for the waiting for link up routine */
diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c
index 874d75c9ee4a..c8febb009454 100644
--- a/drivers/pci/controller/pcie-rcar.c
+++ b/drivers/pci/controller/pcie-rcar.c
@@ -680,7 +680,11 @@ static int rcar_pcie_phy_init_gen3(struct rcar_pcie *pcie)
 	if (err)
 		return err;
 
-	return phy_power_on(pcie->phy);
+	err = phy_power_on(pcie->phy);
+	if (err)
+		phy_exit(pcie->phy);
+
+	return err;
 }
 
 static int rcar_msi_alloc(struct rcar_msi *chip)
@@ -1165,7 +1169,7 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 	if (rcar_pcie_hw_init(pcie)) {
 		dev_info(dev, "PCIe link down\n");
 		err = -ENODEV;
-		goto err_clk_disable;
+		goto err_phy_shutdown;
 	}
 
 	data = rcar_pci_read_reg(pcie, MACSR);
@@ -1177,7 +1181,7 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 			dev_err(dev,
 				"failed to enable MSI support: %d\n",
 				err);
-			goto err_clk_disable;
+			goto err_phy_shutdown;
 		}
 	}
 
@@ -1191,6 +1195,12 @@ err_msi_teardown:
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		rcar_pcie_teardown_msi(pcie);
 
+err_phy_shutdown:
+	if (pcie->phy) {
+		phy_power_off(pcie->phy);
+		phy_exit(pcie->phy);
+	}
+
 err_clk_disable:
 	clk_disable_unprepare(pcie->bus_clk);
 
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index 6a4bbb5b3de0..fb32840ce8e6 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -559,7 +559,7 @@ static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie)
 							PCI_NUM_INTX,
 							&legacy_domain_ops,
 							pcie);
-
+	of_node_put(legacy_intc_node);
 	if (!pcie->legacy_irq_domain) {
 		dev_err(dev, "failed to create IRQ domain\n");
 		return -ENOMEM;
diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c
index b110a3a814e3..7b1389d8e2a5 100644
--- a/drivers/pci/controller/pcie-xilinx.c
+++ b/drivers/pci/controller/pcie-xilinx.c
@@ -509,6 +509,7 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
 	port->leg_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX,
 						 &intx_domain_ops,
 						 port);
+	of_node_put(pcie_intc_node);
 	if (!port->leg_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
 		return -ENODEV;
diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c
index 523a8cab3bfb..825fa24427a3 100644
--- a/drivers/pci/endpoint/pci-epf-core.c
+++ b/drivers/pci/endpoint/pci-epf-core.c
@@ -137,6 +137,20 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar)
 }
 EXPORT_SYMBOL_GPL(pci_epf_alloc_space);
 
+static void pci_epf_remove_cfs(struct pci_epf_driver *driver)
+{
+	struct config_group *group, *tmp;
+
+	if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS))
+		return;
+
+	mutex_lock(&pci_epf_mutex);
+	list_for_each_entry_safe(group, tmp, &driver->epf_group, group_entry)
+		pci_ep_cfs_remove_epf_group(group);
+	list_del(&driver->epf_group);
+	mutex_unlock(&pci_epf_mutex);
+}
+
 /**
  * pci_epf_unregister_driver() - unregister the PCI EPF driver
  * @driver: the PCI EPF driver that has to be unregistered
@@ -145,17 +159,38 @@ EXPORT_SYMBOL_GPL(pci_epf_alloc_space);
  */
 void pci_epf_unregister_driver(struct pci_epf_driver *driver)
 {
-	struct config_group *group;
-
-	mutex_lock(&pci_epf_mutex);
-	list_for_each_entry(group, &driver->epf_group, group_entry)
-		pci_ep_cfs_remove_epf_group(group);
-	list_del(&driver->epf_group);
-	mutex_unlock(&pci_epf_mutex);
+	pci_epf_remove_cfs(driver);
 	driver_unregister(&driver->driver);
 }
 EXPORT_SYMBOL_GPL(pci_epf_unregister_driver);
 
+static int pci_epf_add_cfs(struct pci_epf_driver *driver)
+{
+	struct config_group *group;
+	const struct pci_epf_device_id *id;
+
+	if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS))
+		return 0;
+
+	INIT_LIST_HEAD(&driver->epf_group);
+
+	id = driver->id_table;
+	while (id->name[0]) {
+		group = pci_ep_cfs_add_epf_group(id->name);
+		if (IS_ERR(group)) {
+			pci_epf_remove_cfs(driver);
+			return PTR_ERR(group);
+		}
+
+		mutex_lock(&pci_epf_mutex);
+		list_add_tail(&group->group_entry, &driver->epf_group);
+		mutex_unlock(&pci_epf_mutex);
+		id++;
+	}
+
+	return 0;
+}
+
 /**
  * __pci_epf_register_driver() - register a new PCI EPF driver
  * @driver: structure representing PCI EPF driver
@@ -167,8 +202,6 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver,
 			      struct module *owner)
 {
 	int ret;
-	struct config_group *group;
-	const struct pci_epf_device_id *id;
 
 	if (!driver->ops)
 		return -EINVAL;
@@ -183,16 +216,7 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver,
 	if (ret)
 		return ret;
 
-	INIT_LIST_HEAD(&driver->epf_group);
-
-	id = driver->id_table;
-	while (id->name[0]) {
-		group = pci_ep_cfs_add_epf_group(id->name);
-		mutex_lock(&pci_epf_mutex);
-		list_add_tail(&group->group_entry, &driver->epf_group);
-		mutex_unlock(&pci_epf_mutex);
-		id++;
-	}
+	pci_epf_add_cfs(driver);
 
 	return 0;
 }
diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c
index 3979f89b250a..5bd6c1573295 100644
--- a/drivers/pci/hotplug/acpi_pcihp.c
+++ b/drivers/pci/hotplug/acpi_pcihp.c
@@ -7,7 +7,6 @@
  * All rights reserved.
  *
  * Send feedback to <kristen.c.accardi@intel.com>
- *
  */
 
 #include <linux/module.h>
@@ -87,8 +86,17 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev)
 		return 0;
 
 	/* If _OSC exists, we should not evaluate OSHP */
+
+	/*
+	 * If there's no ACPI host bridge (i.e., ACPI support is compiled
+	 * into the kernel but the hardware platform doesn't support ACPI),
+	 * there's nothing to do here.
+	 */
 	host = pci_find_host_bridge(pdev->bus);
 	root = acpi_pci_find_root(ACPI_HANDLE(&host->dev));
+	if (!root)
+		return 0;
+
 	if (root->osc_support_set)
 		goto no_control;
 
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 3a17b290df5d..ef0b1b6ba86f 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -509,7 +509,7 @@ static void enable_slot(struct acpiphp_slot *slot)
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/* Assume that newly added devices are powered on already. */
-		if (!dev->is_added)
+		if (!pci_dev_is_added(dev))
 			dev->current_state = PCI_D0;
 	}
 
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index d0d73dbbd5ca..0f04ae648cf1 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -575,6 +575,22 @@ void pci_iov_release(struct pci_dev *dev)
 }
 
 /**
+ * pci_iov_remove - clean up SR-IOV state after PF driver is detached
+ * @dev: the PCI device
+ */
+void pci_iov_remove(struct pci_dev *dev)
+{
+	struct pci_sriov *iov = dev->sriov;
+
+	if (!dev->is_physfn)
+		return;
+
+	iov->driver_max_VFs = iov->total_VFs;
+	if (iov->num_VFs)
+		pci_warn(dev, "driver left SR-IOV enabled after remove\n");
+}
+
+/**
  * pci_iov_update_resource - update a VF BAR
  * @dev: the PCI device
  * @resno: the resource number
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index d088c9147f10..69a60d6ebd73 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -612,7 +612,7 @@ int pci_parse_request_of_pci_ranges(struct device *dev,
 
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
-			err = pci_remap_iospace(res, iobase);
+			err = devm_pci_remap_iospace(dev, res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 65113b6eed14..89ee6a2b6eb8 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -629,6 +629,18 @@ static bool acpi_pci_need_resume(struct pci_dev *dev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(&dev->dev);
 
+	/*
+	 * In some cases (eg. Samsung 305V4A) leaving a bridge in suspend over
+	 * system-wide suspend/resume confuses the platform firmware, so avoid
+	 * doing that, unless the bridge has a driver that should take care of
+	 * the PM handling.  According to Section 16.1.6 of ACPI 6.2, endpoint
+	 * devices are expected to be in D3 before invoking the S3 entry path
+	 * from the firmware, so they should not be affected by this issue.
+	 */
+	if (pci_is_bridge(dev) && !dev->driver &&
+	    acpi_target_system_state() != ACPI_STATE_S0)
+		return true;
+
 	if (!adev || !acpi_device_power_manageable(adev))
 		return false;
 
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index c125d53033c6..6792292b5fc7 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -445,6 +445,7 @@ static int pci_device_remove(struct device *dev)
 		}
 		pcibios_free_irq(pci_dev);
 		pci_dev->driver = NULL;
+		pci_iov_remove(pci_dev);
 	}
 
 	/* Undo the runtime PM settings in local_pci_probe() */
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..316496e99da9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3579,6 +3579,44 @@ void pci_unmap_iospace(struct resource *res)
 }
 EXPORT_SYMBOL(pci_unmap_iospace);
 
+static void devm_pci_unmap_iospace(struct device *dev, void *ptr)
+{
+	struct resource **res = ptr;
+
+	pci_unmap_iospace(*res);
+}
+
+/**
+ * devm_pci_remap_iospace - Managed pci_remap_iospace()
+ * @dev: Generic device to remap IO address for
+ * @res: Resource describing the I/O space
+ * @phys_addr: physical address of range to be mapped
+ *
+ * Managed pci_remap_iospace().  Map is automatically unmapped on driver
+ * detach.
+ */
+int devm_pci_remap_iospace(struct device *dev, const struct resource *res,
+			   phys_addr_t phys_addr)
+{
+	const struct resource **ptr;
+	int error;
+
+	ptr = devres_alloc(devm_pci_unmap_iospace, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	error = pci_remap_iospace(res, phys_addr);
+	if (error) {
+		devres_free(ptr);
+	} else	{
+		*ptr = res;
+		devres_add(dev, ptr);
+	}
+
+	return error;
+}
+EXPORT_SYMBOL(devm_pci_remap_iospace);
+
 /**
  * devm_pci_remap_cfgspace - Managed pci_remap_cfgspace()
  * @dev: Generic device to remap IO address for
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index c358e7a07f3f..08817253c8a2 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -288,6 +288,7 @@ struct pci_sriov {
 
 /* pci_dev priv_flags */
 #define PCI_DEV_DISCONNECTED 0
+#define PCI_DEV_ADDED 1
 
 static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused)
 {
@@ -300,6 +301,16 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev)
 	return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags);
 }
 
+static inline void pci_dev_assign_added(struct pci_dev *dev, bool added)
+{
+	assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added);
+}
+
+static inline bool pci_dev_is_added(const struct pci_dev *dev)
+{
+	return test_bit(PCI_DEV_ADDED, &dev->priv_flags);
+}
+
 #ifdef CONFIG_PCI_ATS
 void pci_restore_ats_state(struct pci_dev *dev);
 #else
@@ -311,6 +322,7 @@ static inline void pci_restore_ats_state(struct pci_dev *dev)
 #ifdef CONFIG_PCI_IOV
 int pci_iov_init(struct pci_dev *dev);
 void pci_iov_release(struct pci_dev *dev);
+void pci_iov_remove(struct pci_dev *dev);
 void pci_iov_update_resource(struct pci_dev *dev, int resno);
 resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
 void pci_restore_iov_state(struct pci_dev *dev);
@@ -325,6 +337,9 @@ static inline void pci_iov_release(struct pci_dev *dev)
 
 {
 }
+static inline void pci_iov_remove(struct pci_dev *dev)
+{
+}
 static inline void pci_restore_iov_state(struct pci_dev *dev)
 {
 }
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index f7ce0cb0b0b7..f02e334beb45 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -295,6 +295,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service)
 
 	parent = udev->subordinate;
 	pci_lock_rescan_remove();
+	pci_dev_get(dev);
 	list_for_each_entry_safe_reverse(pdev, temp, &parent->devices,
 					 bus_list) {
 		pci_dev_get(pdev);
@@ -328,6 +329,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service)
 		pci_info(dev, "Device recovery from fatal error failed\n");
 	}
 
+	pci_dev_put(dev);
 	pci_unlock_rescan_remove();
 }
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ac876e32de4b..611adcd9c169 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2433,13 +2433,13 @@ int pci_scan_slot(struct pci_bus *bus, int devfn)
 	dev = pci_scan_single_device(bus, devfn);
 	if (!dev)
 		return 0;
-	if (!dev->is_added)
+	if (!pci_dev_is_added(dev))
 		nr++;
 
 	for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) {
 		dev = pci_scan_single_device(bus, devfn + fn);
 		if (dev) {
-			if (!dev->is_added)
+			if (!pci_dev_is_added(dev))
 				nr++;
 			dev->multifunction = 1;
 		}
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 6f072eae4f7a..5e3d0dced2b8 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -19,11 +19,12 @@ static void pci_stop_dev(struct pci_dev *dev)
 {
 	pci_pme_active(dev, false);
 
-	if (dev->is_added) {
+	if (pci_dev_is_added(dev)) {
 		device_release_driver(&dev->dev);
 		pci_proc_detach_device(dev);
 		pci_remove_sysfs_dev_files(dev);
-		dev->is_added = 0;
+
+		pci_dev_assign_added(dev, false);
 	}
 
 	if (dev->bus->self)
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 0d09d8e669cd..1bfeb160c5b1 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -53,6 +53,16 @@ enum {
 	CCI_IF_MAX,
 };
 
+#define NUM_HW_CNTRS_CII_4XX	4
+#define NUM_HW_CNTRS_CII_5XX	8
+#define NUM_HW_CNTRS_MAX	NUM_HW_CNTRS_CII_5XX
+
+#define FIXED_HW_CNTRS_CII_4XX	1
+#define FIXED_HW_CNTRS_CII_5XX	0
+#define FIXED_HW_CNTRS_MAX	FIXED_HW_CNTRS_CII_4XX
+
+#define HW_CNTRS_MAX		(NUM_HW_CNTRS_MAX + FIXED_HW_CNTRS_MAX)
+
 struct event_range {
 	u32 min;
 	u32 max;
@@ -633,8 +643,7 @@ static void cci_pmu_sync_counters(struct cci_pmu *cci_pmu)
 {
 	int i;
 	struct cci_pmu_hw_events *cci_hw = &cci_pmu->hw_events;
-
-	DECLARE_BITMAP(mask, cci_pmu->num_cntrs);
+	DECLARE_BITMAP(mask, HW_CNTRS_MAX);
 
 	bitmap_zero(mask, cci_pmu->num_cntrs);
 	for_each_set_bit(i, cci_pmu->hw_events.used_mask, cci_pmu->num_cntrs) {
@@ -940,7 +949,7 @@ static void pmu_write_counters(struct cci_pmu *cci_pmu, unsigned long *mask)
 static void cci5xx_pmu_write_counters(struct cci_pmu *cci_pmu, unsigned long *mask)
 {
 	int i;
-	DECLARE_BITMAP(saved_mask, cci_pmu->num_cntrs);
+	DECLARE_BITMAP(saved_mask, HW_CNTRS_MAX);
 
 	bitmap_zero(saved_mask, cci_pmu->num_cntrs);
 	pmu_save_counters(cci_pmu, saved_mask);
@@ -1245,7 +1254,7 @@ static int validate_group(struct perf_event *event)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
 	struct cci_pmu *cci_pmu = to_cci_pmu(event->pmu);
-	unsigned long mask[BITS_TO_LONGS(cci_pmu->num_cntrs)];
+	unsigned long mask[BITS_TO_LONGS(HW_CNTRS_MAX)];
 	struct cci_pmu_hw_events fake_pmu = {
 		/*
 		 * Initialise the fake PMU. We only need to populate the
@@ -1403,6 +1412,11 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 	char *name = model->name;
 	u32 num_cntrs;
 
+	if (WARN_ON(model->num_hw_cntrs > NUM_HW_CNTRS_MAX))
+		return -EINVAL;
+	if (WARN_ON(model->fixed_hw_cntrs > FIXED_HW_CNTRS_MAX))
+		return -EINVAL;
+
 	pmu_event_attr_group.attrs = model->event_attrs;
 	pmu_format_attr_group.attrs = model->format_attrs;
 
@@ -1455,8 +1469,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 #ifdef CONFIG_ARM_CCI400_PMU
 	[CCI400_R0] = {
 		.name = "CCI_400",
-		.fixed_hw_cntrs = 1,	/* Cycle counter */
-		.num_hw_cntrs = 4,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_4XX, /* Cycle counter */
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_4XX,
 		.cntr_size = SZ_4K,
 		.format_attrs = cci400_pmu_format_attrs,
 		.event_attrs = cci400_r0_pmu_event_attrs,
@@ -1475,8 +1489,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 	},
 	[CCI400_R1] = {
 		.name = "CCI_400_r1",
-		.fixed_hw_cntrs = 1,	/* Cycle counter */
-		.num_hw_cntrs = 4,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_4XX, /* Cycle counter */
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_4XX,
 		.cntr_size = SZ_4K,
 		.format_attrs = cci400_pmu_format_attrs,
 		.event_attrs = cci400_r1_pmu_event_attrs,
@@ -1497,8 +1511,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 #ifdef CONFIG_ARM_CCI5xx_PMU
 	[CCI500_R0] = {
 		.name = "CCI_500",
-		.fixed_hw_cntrs = 0,
-		.num_hw_cntrs = 8,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_5XX,
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_5XX,
 		.cntr_size = SZ_64K,
 		.format_attrs = cci5xx_pmu_format_attrs,
 		.event_attrs = cci5xx_pmu_event_attrs,
@@ -1521,8 +1535,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 	},
 	[CCI550_R0] = {
 		.name = "CCI_550",
-		.fixed_hw_cntrs = 0,
-		.num_hw_cntrs = 8,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_5XX,
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_5XX,
 		.cntr_size = SZ_64K,
 		.format_attrs = cci5xx_pmu_format_attrs,
 		.event_attrs = cci5xx_pmu_event_attrs,
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index b416ee18e6bb..4b15c36f4631 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1485,17 +1485,9 @@ static int arm_ccn_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ccn);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -EINVAL;
-
-	if (!devm_request_mem_region(ccn->dev, res->start,
-			resource_size(res), pdev->name))
-		return -EBUSY;
-
-	ccn->base = devm_ioremap(ccn->dev, res->start,
-				resource_size(res));
-	if (!ccn->base)
-		return -EFAULT;
+	ccn->base = devm_ioremap_resource(ccn->dev, res);
+	if (IS_ERR(ccn->base))
+		return PTR_ERR(ccn->base);
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!res)
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index a6347d487635..7f01f6f60b87 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -28,6 +28,14 @@
 static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu);
 static DEFINE_PER_CPU(int, cpu_irq);
 
+static inline u64 arm_pmu_event_max_period(struct perf_event *event)
+{
+	if (event->hw.flags & ARMPMU_EVT_64BIT)
+		return GENMASK_ULL(63, 0);
+	else
+		return GENMASK_ULL(31, 0);
+}
+
 static int
 armpmu_map_cache_event(const unsigned (*cache_map)
 				      [PERF_COUNT_HW_CACHE_MAX]
@@ -114,8 +122,10 @@ int armpmu_event_set_period(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	s64 left = local64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
+	u64 max_period;
 	int ret = 0;
 
+	max_period = arm_pmu_event_max_period(event);
 	if (unlikely(left <= -period)) {
 		left = period;
 		local64_set(&hwc->period_left, left);
@@ -136,12 +146,12 @@ int armpmu_event_set_period(struct perf_event *event)
 	 * effect we are reducing max_period to account for
 	 * interrupt latency (and we are being very conservative).
 	 */
-	if (left > (armpmu->max_period >> 1))
-		left = armpmu->max_period >> 1;
+	if (left > (max_period >> 1))
+		left = (max_period >> 1);
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
-	armpmu->write_counter(event, (u64)(-left) & 0xffffffff);
+	armpmu->write_counter(event, (u64)(-left) & max_period);
 
 	perf_event_update_userpage(event);
 
@@ -153,6 +163,7 @@ u64 armpmu_event_update(struct perf_event *event)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 delta, prev_raw_count, new_raw_count;
+	u64 max_period = arm_pmu_event_max_period(event);
 
 again:
 	prev_raw_count = local64_read(&hwc->prev_count);
@@ -162,7 +173,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
+	delta = (new_raw_count - prev_raw_count) & max_period;
 
 	local64_add(delta, &event->count);
 	local64_sub(delta, &hwc->period_left);
@@ -227,11 +238,10 @@ armpmu_del(struct perf_event *event, int flags)
 
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
-	clear_bit(idx, hw_events->used_mask);
-	if (armpmu->clear_event_idx)
-		armpmu->clear_event_idx(hw_events, event);
-
+	armpmu->clear_event_idx(hw_events, event);
 	perf_event_update_userpage(event);
+	/* Clear the allocated counter */
+	hwc->idx = -1;
 }
 
 static int
@@ -360,6 +370,7 @@ __hw_perf_event_init(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int mapping;
 
+	hwc->flags = 0;
 	mapping = armpmu->map_event(event);
 
 	if (mapping < 0) {
@@ -402,7 +413,7 @@ __hw_perf_event_init(struct perf_event *event)
 		 * is far less likely to overtake the previous one unless
 		 * you have some serious IRQ latency issues.
 		 */
-		hwc->sample_period  = armpmu->max_period >> 1;
+		hwc->sample_period  = arm_pmu_event_max_period(event) >> 1;
 		hwc->last_period    = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
@@ -654,14 +665,9 @@ static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd)
 	int idx;
 
 	for (idx = 0; idx < armpmu->num_events; idx++) {
-		/*
-		 * If the counter is not used skip it, there is no
-		 * need of stopping/restarting it.
-		 */
-		if (!test_bit(idx, hw_events->used_mask))
-			continue;
-
 		event = hw_events->events[idx];
+		if (!event)
+			continue;
 
 		switch (cmd) {
 		case CPU_PM_ENTER:
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 971ff336494a..96075cecb0ae 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -160,7 +160,7 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 static int armpmu_request_irqs(struct arm_pmu *armpmu)
 {
 	struct pmu_hw_events __percpu *hw_events = armpmu->hw_events;
-	int cpu, err;
+	int cpu, err = 0;
 
 	for_each_cpu(cpu, &armpmu->supported_cpus) {
 		int irq = per_cpu(hw_events->irq, cpu);
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 44df61397a38..9efd2413240c 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -350,19 +350,21 @@ void hisi_uncore_pmu_disable(struct pmu *pmu)
 
 /*
  * Read Super CPU cluster and CPU cluster ID from MPIDR_EL1.
- * If multi-threading is supported, SCCL_ID is in MPIDR[aff3] and CCL_ID
- * is in MPIDR[aff2]; if not, SCCL_ID is in MPIDR[aff2] and CCL_ID is
- * in MPIDR[aff1]. If this changes in future, this shall be updated.
+ * If multi-threading is supported, CCL_ID is the low 3-bits in MPIDR[Aff2]
+ * and SCCL_ID is the upper 5-bits of Aff2 field; if not, SCCL_ID
+ * is in MPIDR[Aff2] and CCL_ID is in MPIDR[Aff1].
  */
 static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id)
 {
 	u64 mpidr = read_cpuid_mpidr();
 
 	if (mpidr & MPIDR_MT_BITMASK) {
+		int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+
 		if (sccl_id)
-			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 3);
+			*sccl_id = aff2 >> 3;
 		if (ccl_id)
-			*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+			*ccl_id = aff2 & 0x7;
 	} else {
 		if (sccl_id)
 			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 6bdb1dad805f..0e31f1392a53 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1463,7 +1463,7 @@ static char *xgene_pmu_dev_name(struct device *dev, u32 type, int id)
 	case PMU_TYPE_IOB:
 		return devm_kasprintf(dev, GFP_KERNEL, "iob%d", id);
 	case PMU_TYPE_IOB_SLOW:
-		return devm_kasprintf(dev, GFP_KERNEL, "iob-slow%d", id);
+		return devm_kasprintf(dev, GFP_KERNEL, "iob_slow%d", id);
 	case PMU_TYPE_MCB:
 		return devm_kasprintf(dev, GFP_KERNEL, "mcb%d", id);
 	case PMU_TYPE_MC:
diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.c b/drivers/phy/broadcom/phy-brcm-usb-init.c
index 1b7febc43da9..29d2c3b1913a 100644
--- a/drivers/phy/broadcom/phy-brcm-usb-init.c
+++ b/drivers/phy/broadcom/phy-brcm-usb-init.c
@@ -962,6 +962,10 @@ void brcm_usb_init_xhci(struct brcm_usb_init_params *params)
 {
 	void __iomem *ctrl = params->ctrl_regs;
 
+	USB_CTRL_UNSET(ctrl, USB30_PCTL, PHY3_IDDQ_OVERRIDE);
+	/* 1 millisecond - for USB clocks to settle down */
+	usleep_range(1000, 2000);
+
 	if (BRCM_ID(params->family_id) == 0x7366) {
 		/*
 		 * The PHY3_SOFT_RESETB bits default to the wrong state.
diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c
index 23705e1a0023..0075fb0bef8c 100644
--- a/drivers/phy/motorola/phy-mapphone-mdm6600.c
+++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c
@@ -182,13 +182,13 @@ static void phy_mdm6600_status(struct work_struct *work)
 	ddata = container_of(work, struct phy_mdm6600, status_work.work);
 	dev = ddata->dev;
 
-	error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_CMD_LINES,
+	error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_STATUS_LINES,
 					       ddata->status_gpios->desc,
 					       values);
 	if (error)
 		return;
 
-	for (i = 0; i < PHY_MDM6600_NR_CMD_LINES; i++) {
+	for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) {
 		val |= values[i] << i;
 		dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n",
 			__func__, i, values[i], val);
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index dd50371225bc..8d4b7e999f02 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -161,10 +161,10 @@ config PINCTRL_MCP23S08
 	select REGMAP_SPI if SPI_MASTER
 	select GENERIC_PINCONF
 	help
-	  SPI/I2C driver for Microchip MCP23S08/MCP23S17/MCP23008/MCP23017
-	  I/O expanders.
-	  This provides a GPIO interface supporting inputs and outputs.
-	  The I2C versions of the chips can be used as interrupt-controller.
+	  SPI/I2C driver for Microchip MCP23S08 / MCP23S17 / MCP23S18 /
+	  MCP23008 / MCP23017 / MCP23018 I/O expanders.
+	  This provides a GPIO interface supporting inputs and outputs and a
+	  corresponding interrupt-controller.
 
 config PINCTRL_OXNAS
 	bool
@@ -332,6 +332,7 @@ config PINCTRL_OCELOT
 	depends on OF
 	depends on MSCC_OCELOT || COMPILE_TEST
 	select GPIOLIB
+	select GPIOLIB_IRQCHIP
 	select GENERIC_PINCONF
 	select GENERIC_PINCTRL_GROUPS
 	select GENERIC_PINMUX_FUNCTIONS
diff --git a/drivers/pinctrl/actions/Kconfig b/drivers/pinctrl/actions/Kconfig
index 490927b4ea76..2397cb0f6011 100644
--- a/drivers/pinctrl/actions/Kconfig
+++ b/drivers/pinctrl/actions/Kconfig
@@ -5,6 +5,7 @@ config PINCTRL_OWL
 	select PINCONF
 	select GENERIC_PINCONF
 	select GPIOLIB
+	select GPIOLIB_IRQCHIP
 	help
 	  Say Y here to enable Actions Semi OWL pinctrl driver
 
diff --git a/drivers/pinctrl/actions/pinctrl-owl.c b/drivers/pinctrl/actions/pinctrl-owl.c
index b5c880b50bb3..9d18c02f192b 100644
--- a/drivers/pinctrl/actions/pinctrl-owl.c
+++ b/drivers/pinctrl/actions/pinctrl-owl.c
@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <linux/gpio/driver.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -45,6 +46,9 @@ struct owl_pinctrl {
 	struct clk *clk;
 	const struct owl_pinctrl_soc_data *soc;
 	void __iomem *base;
+	struct irq_chip irq_chip;
+	unsigned int num_irq;
+	unsigned int *irq;
 };
 
 static void owl_update_bits(void __iomem *base, u32 mask, u32 val)
@@ -701,10 +705,213 @@ static int owl_gpio_direction_output(struct gpio_chip *chip,
 	return 0;
 }
 
+static void irq_set_type(struct owl_pinctrl *pctrl, int gpio, unsigned int type)
+{
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int offset, value, irq_type = 0;
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_BOTH:
+		/*
+		 * Since the hardware doesn't support interrupts on both edges,
+		 * emulate it in the software by setting the single edge
+		 * interrupt and switching to the opposite edge while ACKing
+		 * the interrupt
+		 */
+		if (owl_gpio_get(&pctrl->chip, gpio))
+			irq_type = OWL_GPIO_INT_EDGE_FALLING;
+		else
+			irq_type = OWL_GPIO_INT_EDGE_RISING;
+		break;
+
+	case IRQ_TYPE_EDGE_RISING:
+		irq_type = OWL_GPIO_INT_EDGE_RISING;
+		break;
+
+	case IRQ_TYPE_EDGE_FALLING:
+		irq_type = OWL_GPIO_INT_EDGE_FALLING;
+		break;
+
+	case IRQ_TYPE_LEVEL_HIGH:
+		irq_type = OWL_GPIO_INT_LEVEL_HIGH;
+		break;
+
+	case IRQ_TYPE_LEVEL_LOW:
+		irq_type = OWL_GPIO_INT_LEVEL_LOW;
+		break;
+
+	default:
+		break;
+	}
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	offset = (gpio < 16) ? 4 : 0;
+	value = readl_relaxed(gpio_base + port->intc_type + offset);
+	value &= ~(OWL_GPIO_INT_MASK << ((gpio % 16) * 2));
+	value |= irq_type << ((gpio % 16) * 2);
+	writel_relaxed(value, gpio_base + port->intc_type + offset);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static void owl_gpio_irq_mask(struct irq_data *data)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int gpio = data->hwirq;
+	u32 val;
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	owl_gpio_update_reg(gpio_base + port->intc_msk, gpio, false);
+
+	/* disable port interrupt if no interrupt pending bit is active */
+	val = readl_relaxed(gpio_base + port->intc_msk);
+	if (val == 0)
+		owl_gpio_update_reg(gpio_base + port->intc_ctl,
+					OWL_GPIO_CTLR_ENABLE, false);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static void owl_gpio_irq_unmask(struct irq_data *data)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int gpio = data->hwirq;
+	u32 value;
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	/* enable port interrupt */
+	value = readl_relaxed(gpio_base + port->intc_ctl);
+	value |= BIT(OWL_GPIO_CTLR_ENABLE) | BIT(OWL_GPIO_CTLR_SAMPLE_CLK_24M);
+	writel_relaxed(value, gpio_base + port->intc_ctl);
+
+	/* enable GPIO interrupt */
+	owl_gpio_update_reg(gpio_base + port->intc_msk, gpio, true);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static void owl_gpio_irq_ack(struct irq_data *data)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int gpio = data->hwirq;
+
+	/*
+	 * Switch the interrupt edge to the opposite edge of the interrupt
+	 * which got triggered for the case of emulating both edges
+	 */
+	if (irqd_get_trigger_type(data) == IRQ_TYPE_EDGE_BOTH) {
+		if (owl_gpio_get(gc, gpio))
+			irq_set_type(pctrl, gpio, IRQ_TYPE_EDGE_FALLING);
+		else
+			irq_set_type(pctrl, gpio, IRQ_TYPE_EDGE_RISING);
+	}
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	owl_gpio_update_reg(gpio_base + port->intc_ctl,
+				OWL_GPIO_CTLR_PENDING, true);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static int owl_gpio_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+
+	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
+		irq_set_handler_locked(data, handle_level_irq);
+	else
+		irq_set_handler_locked(data, handle_edge_irq);
+
+	irq_set_type(pctrl, data->hwirq, type);
+
+	return 0;
+}
+
+static void owl_gpio_irq_handler(struct irq_desc *desc)
+{
+	struct owl_pinctrl *pctrl = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irq_domain *domain = pctrl->chip.irq.domain;
+	unsigned int parent = irq_desc_get_irq(desc);
+	const struct owl_gpio_port *port;
+	void __iomem *base;
+	unsigned int pin, irq, offset = 0, i;
+	unsigned long pending_irq;
+
+	chained_irq_enter(chip, desc);
+
+	for (i = 0; i < pctrl->soc->nports; i++) {
+		port = &pctrl->soc->ports[i];
+		base = pctrl->base + port->offset;
+
+		/* skip ports that are not associated with this irq */
+		if (parent != pctrl->irq[i])
+			goto skip;
+
+		pending_irq = readl_relaxed(base + port->intc_pd);
+
+		for_each_set_bit(pin, &pending_irq, port->pins) {
+			irq = irq_find_mapping(domain, offset + pin);
+			generic_handle_irq(irq);
+
+			/* clear pending interrupt */
+			owl_gpio_update_reg(base + port->intc_pd, pin, true);
+		}
+
+skip:
+		offset += port->pins;
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
 static int owl_gpio_init(struct owl_pinctrl *pctrl)
 {
 	struct gpio_chip *chip;
-	int ret;
+	struct gpio_irq_chip *gpio_irq;
+	int ret, i, j, offset;
 
 	chip = &pctrl->chip;
 	chip->base = -1;
@@ -714,6 +921,35 @@ static int owl_gpio_init(struct owl_pinctrl *pctrl)
 	chip->owner = THIS_MODULE;
 	chip->of_node = pctrl->dev->of_node;
 
+	pctrl->irq_chip.name = chip->of_node->name;
+	pctrl->irq_chip.irq_ack = owl_gpio_irq_ack;
+	pctrl->irq_chip.irq_mask = owl_gpio_irq_mask;
+	pctrl->irq_chip.irq_unmask = owl_gpio_irq_unmask;
+	pctrl->irq_chip.irq_set_type = owl_gpio_irq_set_type;
+
+	gpio_irq = &chip->irq;
+	gpio_irq->chip = &pctrl->irq_chip;
+	gpio_irq->handler = handle_simple_irq;
+	gpio_irq->default_type = IRQ_TYPE_NONE;
+	gpio_irq->parent_handler = owl_gpio_irq_handler;
+	gpio_irq->parent_handler_data = pctrl;
+	gpio_irq->num_parents = pctrl->num_irq;
+	gpio_irq->parents = pctrl->irq;
+
+	gpio_irq->map = devm_kcalloc(pctrl->dev, chip->ngpio,
+				sizeof(*gpio_irq->map), GFP_KERNEL);
+	if (!gpio_irq->map)
+		return -ENOMEM;
+
+	for (i = 0, offset = 0; i < pctrl->soc->nports; i++) {
+		const struct owl_gpio_port *port = &pctrl->soc->ports[i];
+
+		for (j = 0; j < port->pins; j++)
+			gpio_irq->map[offset + j] = gpio_irq->parents[i];
+
+		offset += port->pins;
+	}
+
 	ret = gpiochip_add_data(&pctrl->chip, pctrl);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to register gpiochip\n");
@@ -728,7 +964,7 @@ int owl_pinctrl_probe(struct platform_device *pdev,
 {
 	struct resource *res;
 	struct owl_pinctrl *pctrl;
-	int ret;
+	int ret, i;
 
 	pctrl = devm_kzalloc(&pdev->dev, sizeof(*pctrl), GFP_KERNEL);
 	if (!pctrl)
@@ -772,14 +1008,40 @@ int owl_pinctrl_probe(struct platform_device *pdev,
 					&owl_pinctrl_desc, pctrl);
 	if (IS_ERR(pctrl->pctrldev)) {
 		dev_err(&pdev->dev, "could not register Actions OWL pinmux driver\n");
-		return PTR_ERR(pctrl->pctrldev);
+		ret = PTR_ERR(pctrl->pctrldev);
+		goto err_exit;
+	}
+
+	ret = platform_irq_count(pdev);
+	if (ret < 0)
+		goto err_exit;
+
+	pctrl->num_irq = ret;
+
+	pctrl->irq = devm_kcalloc(&pdev->dev, pctrl->num_irq,
+					sizeof(*pctrl->irq), GFP_KERNEL);
+	if (!pctrl->irq) {
+		ret = -ENOMEM;
+		goto err_exit;
+	}
+
+	for (i = 0; i < pctrl->num_irq ; i++) {
+		ret = platform_get_irq(pdev, i);
+		if (ret < 0)
+			goto err_exit;
+		pctrl->irq[i] = ret;
 	}
 
 	ret = owl_gpio_init(pctrl);
 	if (ret)
-		return ret;
+		goto err_exit;
 
 	platform_set_drvdata(pdev, pctrl);
 
 	return 0;
+
+err_exit:
+	clk_disable_unprepare(pctrl->clk);
+
+	return ret;
 }
diff --git a/drivers/pinctrl/actions/pinctrl-owl.h b/drivers/pinctrl/actions/pinctrl-owl.h
index 74342378937c..a724d1d406d4 100644
--- a/drivers/pinctrl/actions/pinctrl-owl.h
+++ b/drivers/pinctrl/actions/pinctrl-owl.h
@@ -29,6 +29,18 @@ enum owl_pinconf_drv {
 	OWL_PINCONF_DRV_12MA,
 };
 
+/* GPIO CTRL Bit Definition */
+#define OWL_GPIO_CTLR_PENDING		0
+#define OWL_GPIO_CTLR_ENABLE		1
+#define OWL_GPIO_CTLR_SAMPLE_CLK_24M	2
+
+/* GPIO TYPE Bit Definition */
+#define OWL_GPIO_INT_LEVEL_HIGH		0
+#define OWL_GPIO_INT_LEVEL_LOW		1
+#define OWL_GPIO_INT_EDGE_RISING	2
+#define OWL_GPIO_INT_EDGE_FALLING	3
+#define OWL_GPIO_INT_MASK		3
+
 /**
  * struct owl_pullctl - Actions pad pull control register
  * @reg: offset to the pull control register
@@ -121,6 +133,10 @@ struct owl_pinmux_func {
  * @outen: offset of the output enable register.
  * @inen: offset of the input enable register.
  * @dat: offset of the data register.
+ * @intc_ctl: offset of the interrupt control register.
+ * @intc_pd: offset of the interrupt pending register.
+ * @intc_msk: offset of the interrupt mask register.
+ * @intc_type: offset of the interrupt type register.
  */
 struct owl_gpio_port {
 	unsigned int offset;
@@ -128,6 +144,10 @@ struct owl_gpio_port {
 	unsigned int outen;
 	unsigned int inen;
 	unsigned int dat;
+	unsigned int intc_ctl;
+	unsigned int intc_pd;
+	unsigned int intc_msk;
+	unsigned int intc_type;
 };
 
 /**
@@ -140,7 +160,7 @@ struct owl_gpio_port {
  * @ngroups: number of entries in @groups.
  * @padinfo: array describing the pad info of this SoC.
  * @ngpios: number of pingroups the driver should expose as GPIOs.
- * @port: array describing all GPIO ports of this SoC.
+ * @ports: array describing all GPIO ports of this SoC.
  * @nports: number of GPIO ports in this SoC.
  */
 struct owl_pinctrl_soc_data {
diff --git a/drivers/pinctrl/actions/pinctrl-s900.c b/drivers/pinctrl/actions/pinctrl-s900.c
index 5503c7945764..ea67b14ef93b 100644
--- a/drivers/pinctrl/actions/pinctrl-s900.c
+++ b/drivers/pinctrl/actions/pinctrl-s900.c
@@ -1821,22 +1821,27 @@ static struct owl_padinfo s900_padinfo[NUM_PADS] = {
 	[SGPIO3] = PAD_INFO_PULLCTL_ST(SGPIO3)
 };
 
-#define OWL_GPIO_PORT(port, base, count, _outen, _inen, _dat)	\
-	[OWL_GPIO_PORT_##port] = {				\
-		.offset = base,					\
-		.pins = count,					\
-		.outen = _outen,				\
-		.inen = _inen,					\
-		.dat = _dat,					\
+#define OWL_GPIO_PORT(port, base, count, _outen, _inen, _dat,		\
+			_intc_ctl, _intc_pd, _intc_msk, _intc_type)	\
+	[OWL_GPIO_PORT_##port] = {					\
+		.offset = base,						\
+		.pins = count,						\
+		.outen = _outen,					\
+		.inen = _inen,						\
+		.dat = _dat,						\
+		.intc_ctl = _intc_ctl,					\
+		.intc_pd = _intc_pd,					\
+		.intc_msk = _intc_msk,					\
+		.intc_type = _intc_type,				\
 	}
 
 static const struct owl_gpio_port s900_gpio_ports[] = {
-	OWL_GPIO_PORT(A, 0x0000, 32, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(B, 0x000C, 32, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(C, 0x0018, 12, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(D, 0x0024, 30, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(E, 0x0030, 32, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(F, 0x00F0, 8, 0x0, 0x4, 0x8)
+	OWL_GPIO_PORT(A, 0x0000, 32, 0x0, 0x4, 0x8, 0x204, 0x208, 0x20C, 0x240),
+	OWL_GPIO_PORT(B, 0x000C, 32, 0x0, 0x4, 0x8, 0x534, 0x204, 0x208, 0x23C),
+	OWL_GPIO_PORT(C, 0x0018, 12, 0x0, 0x4, 0x8, 0x52C, 0x200, 0x204, 0x238),
+	OWL_GPIO_PORT(D, 0x0024, 30, 0x0, 0x4, 0x8, 0x524, 0x1FC, 0x200, 0x234),
+	OWL_GPIO_PORT(E, 0x0030, 32, 0x0, 0x4, 0x8, 0x51C, 0x1F8, 0x1FC, 0x230),
+	OWL_GPIO_PORT(F, 0x00F0, 8, 0x0, 0x4, 0x8, 0x460, 0x140, 0x144, 0x178)
 };
 
 static struct owl_pinctrl_soc_data s900_pinctrl_data = {
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
index 7f13ce8450a3..aefe3c33dffd 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
@@ -95,7 +95,7 @@ static inline void aspeed_sig_desc_print_val(
  *
  * @desc: The signal descriptor of interest
  * @enabled: True to query the enabled state, false to query disabled state
- * @regmap: The IP block's regmap instance
+ * @map: The IP block's regmap instance
  *
  * Return: 1 if the descriptor's bitfield is configured to the state
  * selected by @enabled, 0 if not, and less than zero if an unrecoverable
@@ -594,7 +594,7 @@ static inline const struct aspeed_pin_config *find_pinconf_config(
 /**
  * @param: pinconf configuration parameter
  * @arg: The supported argument for @param, or -1 if any value is supported
- * @value: The register value to write to configure @arg for @param
+ * @val: The register value to write to configure @arg for @param
  *
  * The map is to be used in conjunction with the configuration array supplied
  * by the driver implementation.
diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-mux.c b/drivers/pinctrl/bcm/pinctrl-nsp-mux.c
index 35c17653c694..87618a4e90e4 100644
--- a/drivers/pinctrl/bcm/pinctrl-nsp-mux.c
+++ b/drivers/pinctrl/bcm/pinctrl-nsp-mux.c
@@ -460,8 +460,8 @@ static int nsp_pinmux_enable(struct pinctrl_dev *pctrl_dev,
 	const struct nsp_pin_function *func;
 	const struct nsp_pin_group *grp;
 
-	if (grp_select > pinctrl->num_groups ||
-		func_select > pinctrl->num_functions)
+	if (grp_select >= pinctrl->num_groups ||
+	    func_select >= pinctrl->num_functions)
 		return -EINVAL;
 
 	func = &pinctrl->functions[func_select];
@@ -577,6 +577,8 @@ static int nsp_pinmux_probe(struct platform_device *pdev)
 		return PTR_ERR(pinctrl->base0);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res)
+		return -EINVAL;
 	pinctrl->base1 = devm_ioremap_nocache(&pdev->dev, res->start,
 					      resource_size(res));
 	if (!pinctrl->base1) {
diff --git a/drivers/pinctrl/berlin/Kconfig b/drivers/pinctrl/berlin/Kconfig
index 8fe6ad7795dc..0dd60278e973 100644
--- a/drivers/pinctrl/berlin/Kconfig
+++ b/drivers/pinctrl/berlin/Kconfig
@@ -5,6 +5,11 @@ config PINCTRL_BERLIN
 	select PINMUX
 	select REGMAP_MMIO
 
+config PINCTRL_AS370
+	bool "Synaptics as370 pin controller driver"
+	depends on OF
+	select PINCTRL_BERLIN
+
 config PINCTRL_BERLIN_BG2
 	def_bool MACH_BERLIN_BG2
 	depends on OF
diff --git a/drivers/pinctrl/berlin/Makefile b/drivers/pinctrl/berlin/Makefile
index 6f641ce2c830..00c53ca3676d 100644
--- a/drivers/pinctrl/berlin/Makefile
+++ b/drivers/pinctrl/berlin/Makefile
@@ -3,3 +3,4 @@ obj-$(CONFIG_PINCTRL_BERLIN_BG2)	+= berlin-bg2.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG2CD)	+= berlin-bg2cd.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG2Q)	+= berlin-bg2q.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG4CT)	+= berlin-bg4ct.o
+obj-$(CONFIG_PINCTRL_AS370)		+= pinctrl-as370.o
diff --git a/drivers/pinctrl/berlin/berlin.c b/drivers/pinctrl/berlin/berlin.c
index d6d183e9db17..b5903fffb3d0 100644
--- a/drivers/pinctrl/berlin/berlin.c
+++ b/drivers/pinctrl/berlin/berlin.c
@@ -216,10 +216,8 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 	}
 
 	/* we will reallocate later */
-	pctrl->functions = devm_kcalloc(&pdev->dev,
-					max_functions,
-					sizeof(*pctrl->functions),
-					GFP_KERNEL);
+	pctrl->functions = kcalloc(max_functions,
+				   sizeof(*pctrl->functions), GFP_KERNEL);
 	if (!pctrl->functions)
 		return -ENOMEM;
 
@@ -257,8 +255,10 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 				function++;
 			}
 
-			if (!found)
+			if (!found) {
+				kfree(pctrl->functions);
 				return -EINVAL;
+			}
 
 			if (!function->groups) {
 				function->groups =
@@ -267,8 +267,10 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 						     sizeof(char *),
 						     GFP_KERNEL);
 
-				if (!function->groups)
+				if (!function->groups) {
+					kfree(pctrl->functions);
 					return -ENOMEM;
+				}
 			}
 
 			groups = function->groups;
diff --git a/drivers/pinctrl/berlin/pinctrl-as370.c b/drivers/pinctrl/berlin/pinctrl-as370.c
new file mode 100644
index 000000000000..d2bb811fc5fa
--- /dev/null
+++ b/drivers/pinctrl/berlin/pinctrl-as370.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Synaptics AS370 pinctrl driver
+ *
+ * Copyright (C) 2018 Synaptics Incorporated
+ *
+ * Author: Jisheng Zhang <jszhang@kernel.org>
+ */
+
+#include <linux/init.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "berlin.h"
+
+static const struct berlin_desc_group as370_soc_pinctrl_groups[] = {
+	BERLIN_PINCTRL_GROUP("I2S1_BCLKIO", 0x0, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO0 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* BCLKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG0 */
+	BERLIN_PINCTRL_GROUP("I2S1_LRCKIO", 0x0, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO1 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* LRCKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG1 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO0", 0x0, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* 1P8V RSTB*/
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO0 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio"), /* GPIO2 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG2 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO1", 0x0, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* 3P3V RSTB */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO1 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio"), /* GPIO3 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG3 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO2", 0x0, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* CORE RSTB */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm4"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio"), /* GPIO4 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG4 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO3", 0x0, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO5 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm5"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spififib"), /* SPDIFIB */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG5 */
+	BERLIN_PINCTRL_GROUP("I2S1_MCLK", 0x0, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO6 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* MCLK */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG6 */
+	BERLIN_PINCTRL_GROUP("I2S2_BCLKIO", 0x0, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO7 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* BCLKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG7 */
+	BERLIN_PINCTRL_GROUP("I2S2_LRCKIO", 0x0, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO8 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* LRCKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG8 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI0", 0x0, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO9 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI0 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm2"),
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG9 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI1", 0x4, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO10 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI1 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm3"),
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG10 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI2", 0x4, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO11 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm6"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdific"), /* SPDIFIC */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG11 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI3", 0x4, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO12 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm7"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifia"), /* SPDIFIA */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG12 */
+	BERLIN_PINCTRL_GROUP("PDM_CLKO", 0x4, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO13 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* CLKO */
+			BERLIN_PINCTRL_FUNCTION(0x2, "i2s2"), /* MCLK */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG13 */
+	BERLIN_PINCTRL_GROUP("PDM_DI0", 0x4, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO14 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI0 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG14 */
+	BERLIN_PINCTRL_GROUP("PDM_DI1", 0x4, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO15 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI1 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG15 */
+	BERLIN_PINCTRL_GROUP("PDM_DI2", 0x4, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO16 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm4"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifid"), /* SPDIFID */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG16 */
+	BERLIN_PINCTRL_GROUP("PDM_DI3", 0x4, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO17 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm5"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifi"), /* SPDIFI */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG17 */
+	BERLIN_PINCTRL_GROUP("NAND_IO0", 0x4, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO0 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA0 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie0")), /* MDIO */
+	BERLIN_PINCTRL_GROUP("NAND_IO1", 0x4, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO1 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA1 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie0")), /* MDC */
+	BERLIN_PINCTRL_GROUP("NAND_IO2", 0x8, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO2 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA2 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie1")), /* MDIO */
+	BERLIN_PINCTRL_GROUP("NAND_IO3", 0x8, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO3 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA3 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie1")), /* MDC */
+	BERLIN_PINCTRL_GROUP("NAND_IO4", 0x8, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO4 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA4 */
+	BERLIN_PINCTRL_GROUP("NAND_IO5", 0x8, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO5 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA5 */
+	BERLIN_PINCTRL_GROUP("NAND_IO6", 0x8, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO6 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA6 */
+	BERLIN_PINCTRL_GROUP("NAND_IO7", 0x8, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO7 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA7 */
+	BERLIN_PINCTRL_GROUP("NAND_ALE", 0x8, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* ALE */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm6"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO18 */
+	BERLIN_PINCTRL_GROUP("NAND_CLE", 0x8, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* CLE */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm7"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO19 */
+	BERLIN_PINCTRL_GROUP("NAND_WEn", 0x8, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* WEn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO20 */
+	BERLIN_PINCTRL_GROUP("NAND_REn", 0x8, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* REn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO21 */
+	BERLIN_PINCTRL_GROUP("NAND_WPn", 0xc, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* WPn */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* CLK */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO22 */
+	BERLIN_PINCTRL_GROUP("NAND_CEn", 0xc, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* CEn */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* RSTn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO23 */
+	BERLIN_PINCTRL_GROUP("NAND_RDY", 0xc, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* RDY */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* CMD */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO24 */
+	BERLIN_PINCTRL_GROUP("SPI1_SS0n", 0xc, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS0n */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio")), /* GPIO25 */
+	BERLIN_PINCTRL_GROUP("SPI1_SS1n", 0xc, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS1n */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio"), /* GPIO26 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm2")),
+	BERLIN_PINCTRL_GROUP("SPI1_SS2n", 0xc, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "uart0"), /* RXD */
+			BERLIN_PINCTRL_FUNCTION(0x1, "spi1"), /* SS2n */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio"), /* GPIO27 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm3")),
+	BERLIN_PINCTRL_GROUP("SPI1_SS3n", 0xc, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "uart0"), /* TXD */
+			BERLIN_PINCTRL_FUNCTION(0x1, "spi1"), /* SS3n */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO28 */
+	BERLIN_PINCTRL_GROUP("SPI1_SCLK", 0xc, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SCLK */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO29 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm4")),
+	BERLIN_PINCTRL_GROUP("SPI1_SDO", 0xc, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SDO */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO30 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm5")),
+	BERLIN_PINCTRL_GROUP("SPI1_SDI", 0xc, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SDI */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio")), /* GPIO31 */
+	BERLIN_PINCTRL_GROUP("USB0_DRV_VBUS", 0x10, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "usb0"), /* VBUS */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO32 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "refclko")), /* 25M */
+	BERLIN_PINCTRL_GROUP("TW1_SCL", 0x10, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO33 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw1")), /* SCL */
+	BERLIN_PINCTRL_GROUP("TW1_SDA", 0x10, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO34 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw1")), /* SDA */
+	BERLIN_PINCTRL_GROUP("TW0_SCL", 0x10, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO35 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw0")), /* SCL */
+	BERLIN_PINCTRL_GROUP("TW0_SDA", 0x10, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO36 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw0")), /* SDA */
+	BERLIN_PINCTRL_GROUP("TMS", 0x10, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "jtag"), /* TMS */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO37 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pwm0")),
+	BERLIN_PINCTRL_GROUP("TDI", 0x10, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "jtag"), /* TDI */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO38 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pwm1")),
+	BERLIN_PINCTRL_GROUP("TDO", 0x10, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "jtag"), /* TDO */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO39 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pwm0")),
+	BERLIN_PINCTRL_GROUP("PWM6", 0x10, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO40 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm6")),
+	BERLIN_PINCTRL_GROUP("PWM7", 0x10, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO41 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm7")),
+	BERLIN_PINCTRL_GROUP("PWM0", 0x14, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* VDDCPUSOC RSTB */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm0"),
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO42 */
+	BERLIN_PINCTRL_GROUP("PWM1", 0x14, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO43 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm1")),
+	BERLIN_PINCTRL_GROUP("PWM2", 0x14, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO44 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm2")),
+	BERLIN_PINCTRL_GROUP("PWM3", 0x14, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO45 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm3")),
+	BERLIN_PINCTRL_GROUP("PWM4", 0x14, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO46 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm4")),
+	BERLIN_PINCTRL_GROUP("PWM5", 0x14, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO47 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm5")),
+	BERLIN_PINCTRL_GROUP("URT1_RTSn", 0x14, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO48 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* RTSn */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm6"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "tw1a"), /* SCL */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG0 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG18 */
+	BERLIN_PINCTRL_GROUP("URT1_CTSn", 0x14, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO49 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* CTSn */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm7"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "tw1a"), /* SDA */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG1 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG19 */
+	BERLIN_PINCTRL_GROUP("URT1_RXD", 0x14, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO50 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* RXD */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG2 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG20 */
+	BERLIN_PINCTRL_GROUP("URT1_TXD", 0x14, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO51 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* TXD */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG3 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG21 */
+	BERLIN_PINCTRL_GROUP("I2S3_DI", 0x18, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO52 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3"), /* DI */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG22 */
+	BERLIN_PINCTRL_GROUP("I2S3_DO", 0x18, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO53 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3"), /* DO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG23 */
+	BERLIN_PINCTRL_GROUP("I2S3_BCLKIO", 0x18, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO54 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3"), /* BCLKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "clk")), /* DBG */
+	BERLIN_PINCTRL_GROUP("I2S3_LRCKIO", 0x18, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO55 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3")), /* LRCKIO */
+	BERLIN_PINCTRL_GROUP("SD0_DAT0", 0x18, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "cpupll"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT0 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO56 */
+	BERLIN_PINCTRL_GROUP("SD0_DAT1", 0x18, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "syspll"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT1 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO57 */
+	BERLIN_PINCTRL_GROUP("SD0_CLK", 0x18, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO58 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0")), /* CLK */
+	BERLIN_PINCTRL_GROUP("SD0_DAT2", 0x18, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "mempll"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO59 */
+	BERLIN_PINCTRL_GROUP("SD0_DAT3", 0x18, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "apll0"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO60 */
+	BERLIN_PINCTRL_GROUP("SD0_CMD", 0x18, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "apll1"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* CMD */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO61 */
+	BERLIN_PINCTRL_GROUP("SD0_CDn", 0x1c, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO62 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* CDn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm2")),
+	BERLIN_PINCTRL_GROUP("SD0_WP", 0x1c, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO63 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* WP */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm3")),
+};
+
+static const struct berlin_pinctrl_desc as370_soc_pinctrl_data = {
+	.groups = as370_soc_pinctrl_groups,
+	.ngroups = ARRAY_SIZE(as370_soc_pinctrl_groups),
+};
+
+static const struct of_device_id as370_pinctrl_match[] = {
+	{
+		.compatible = "syna,as370-soc-pinctrl",
+		.data = &as370_soc_pinctrl_data,
+	},
+	{}
+};
+
+static int as370_pinctrl_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match =
+		of_match_device(as370_pinctrl_match, &pdev->dev);
+	struct regmap_config *rmconfig;
+	struct regmap *regmap;
+	struct resource *res;
+	void __iomem *base;
+
+	rmconfig = devm_kzalloc(&pdev->dev, sizeof(*rmconfig), GFP_KERNEL);
+	if (!rmconfig)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	rmconfig->reg_bits = 32,
+	rmconfig->val_bits = 32,
+	rmconfig->reg_stride = 4,
+	rmconfig->max_register = resource_size(res);
+
+	regmap = devm_regmap_init_mmio(&pdev->dev, base, rmconfig);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	return berlin_pinctrl_probe_regmap(pdev, match->data, regmap);
+}
+
+static struct platform_driver as370_pinctrl_driver = {
+	.probe	= as370_pinctrl_probe,
+	.driver	= {
+		.name = "as370-pinctrl",
+		.of_match_table = as370_pinctrl_match,
+	},
+};
+builtin_platform_driver(as370_pinctrl_driver);
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index e5a303002021..a3dd777e3ce8 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -21,7 +21,6 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/list.h>
-#include <linux/sysfs.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/pinctrl/consumer.h>
@@ -617,6 +616,26 @@ struct group_desc *pinctrl_generic_get_group(struct pinctrl_dev *pctldev,
 }
 EXPORT_SYMBOL_GPL(pinctrl_generic_get_group);
 
+static int pinctrl_generic_group_name_to_selector(struct pinctrl_dev *pctldev,
+						  const char *function)
+{
+	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
+	int ngroups = ops->get_groups_count(pctldev);
+	int selector = 0;
+
+	/* See if this pctldev has this group */
+	while (selector < ngroups) {
+		const char *gname = ops->get_group_name(pctldev, selector);
+
+		if (!strcmp(function, gname))
+			return selector;
+
+		selector++;
+	}
+
+	return -EINVAL;
+}
+
 /**
  * pinctrl_generic_add_group() - adds a new pin group
  * @pctldev: pin controller device
@@ -631,6 +650,16 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 			      int *pins, int num_pins, void *data)
 {
 	struct group_desc *group;
+	int selector;
+
+	if (!name)
+		return -EINVAL;
+
+	selector = pinctrl_generic_group_name_to_selector(pctldev, name);
+	if (selector >= 0)
+		return selector;
+
+	selector = pctldev->num_groups;
 
 	group = devm_kzalloc(pctldev->dev, sizeof(*group), GFP_KERNEL);
 	if (!group)
@@ -641,12 +670,11 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 	group->num_pins = num_pins;
 	group->data = data;
 
-	radix_tree_insert(&pctldev->pin_group_tree, pctldev->num_groups,
-			  group);
+	radix_tree_insert(&pctldev->pin_group_tree, selector, group);
 
 	pctldev->num_groups++;
 
-	return 0;
+	return selector;
 }
 EXPORT_SYMBOL_GPL(pinctrl_generic_add_group);
 
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 8cf2eba17c8c..4a0526e567df 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -218,12 +218,6 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 int pinctrl_generic_remove_group(struct pinctrl_dev *pctldev,
 				 unsigned int group_selector);
 
-static inline int
-pinctrl_generic_remove_last_group(struct pinctrl_dev *pctldev)
-{
-	return pinctrl_generic_remove_group(pctldev, pctldev->num_groups - 1);
-}
-
 #endif	/* CONFIG_GENERIC_PINCTRL_GROUPS */
 
 struct pinctrl_dev *get_pinctrl_dev_from_devname(const char *dev_name);
diff --git a/drivers/pinctrl/freescale/Kconfig b/drivers/pinctrl/freescale/Kconfig
index 0d8ba1ef5329..dccf64c55498 100644
--- a/drivers/pinctrl/freescale/Kconfig
+++ b/drivers/pinctrl/freescale/Kconfig
@@ -117,6 +117,13 @@ config PINCTRL_IMX7ULP
 	help
 	  Say Y here to enable the imx7ulp pinctrl driver
 
+config PINCTRL_IMX8MQ
+	bool "IMX8MQ pinctrl driver"
+	depends on SOC_IMX8MQ
+	select PINCTRL_IMX
+	help
+	  Say Y here to enable the imx8mq pinctrl driver
+
 config PINCTRL_VF610
 	bool "Freescale Vybrid VF610 pinctrl driver"
 	depends on SOC_VF610
diff --git a/drivers/pinctrl/freescale/Makefile b/drivers/pinctrl/freescale/Makefile
index 368be8cfc9b1..73175b3e7c9c 100644
--- a/drivers/pinctrl/freescale/Makefile
+++ b/drivers/pinctrl/freescale/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_PINCTRL_IMX6SX)	+= pinctrl-imx6sx.o
 obj-$(CONFIG_PINCTRL_IMX6UL)	+= pinctrl-imx6ul.o
 obj-$(CONFIG_PINCTRL_IMX7D)	+= pinctrl-imx7d.o
 obj-$(CONFIG_PINCTRL_IMX7ULP)	+= pinctrl-imx7ulp.o
+obj-$(CONFIG_PINCTRL_IMX8MQ)	+= pinctrl-imx8mq.o
 obj-$(CONFIG_PINCTRL_VF610)	+= pinctrl-vf610.o
 obj-$(CONFIG_PINCTRL_MXS)	+= pinctrl-mxs.o
 obj-$(CONFIG_PINCTRL_IMX23)	+= pinctrl-imx23.o
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 1c6bb15579e1..b04edc22dad7 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -383,7 +383,7 @@ static void imx_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 	const char *name;
 	int i, ret;
 
-	if (group > pctldev->num_groups)
+	if (group >= pctldev->num_groups)
 		return;
 
 	seq_puts(s, "\n");
diff --git a/drivers/pinctrl/freescale/pinctrl-imx1-core.c b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
index c3bdd90b1422..deb7870b3d1a 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
@@ -429,7 +429,7 @@ static void imx1_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 	const char *name;
 	int i, ret;
 
-	if (group > info->ngroups)
+	if (group >= info->ngroups)
 		return;
 
 	seq_puts(s, "\n");
diff --git a/drivers/pinctrl/freescale/pinctrl-imx8mq.c b/drivers/pinctrl/freescale/pinctrl-imx8mq.c
new file mode 100644
index 000000000000..8d39af541d5f
--- /dev/null
+++ b/drivers/pinctrl/freescale/pinctrl-imx8mq.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016 Freescale Semiconductor, Inc.
+ * Copyright 2017-2018 NXP
+ * Copyright (C) 2018 Pengutronix, Lucas Stach <kernel@pengutronix.de>
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-imx.h"
+
+enum imx8mq_pads {
+	MX8MQ_PAD_RESERVE0 = 0,
+	MX8MQ_PAD_RESERVE1 = 1,
+	MX8MQ_PAD_RESERVE2 = 2,
+	MX8MQ_PAD_RESERVE3 = 3,
+	MX8MQ_PAD_RESERVE4 = 4,
+	MX8MQ_IOMUXC_PMIC_STBY_REQ_CCMSRCGPCMIX = 5,
+	MX8MQ_IOMUXC_PMIC_ON_REQ_SNVSMIX = 6,
+	MX8MQ_IOMUXC_ONOFF_SNVSMIX = 7,
+	MX8MQ_IOMUXC_POR_B_SNVSMIX = 8,
+	MX8MQ_IOMUXC_RTC_RESET_B_SNVSMIX = 9,
+	MX8MQ_IOMUXC_GPIO1_IO00 = 10,
+	MX8MQ_IOMUXC_GPIO1_IO01 = 11,
+	MX8MQ_IOMUXC_GPIO1_IO02 = 12,
+	MX8MQ_IOMUXC_GPIO1_IO03 = 13,
+	MX8MQ_IOMUXC_GPIO1_IO04 = 14,
+	MX8MQ_IOMUXC_GPIO1_IO05 = 15,
+	MX8MQ_IOMUXC_GPIO1_IO06 = 16,
+	MX8MQ_IOMUXC_GPIO1_IO07 = 17,
+	MX8MQ_IOMUXC_GPIO1_IO08 = 18,
+	MX8MQ_IOMUXC_GPIO1_IO09 = 19,
+	MX8MQ_IOMUXC_GPIO1_IO10 = 20,
+	MX8MQ_IOMUXC_GPIO1_IO11 = 21,
+	MX8MQ_IOMUXC_GPIO1_IO12 = 22,
+	MX8MQ_IOMUXC_GPIO1_IO13 = 23,
+	MX8MQ_IOMUXC_GPIO1_IO14 = 24,
+	MX8MQ_IOMUXC_GPIO1_IO15 = 25,
+	MX8MQ_IOMUXC_ENET_MDC = 26,
+	MX8MQ_IOMUXC_ENET_MDIO = 27,
+	MX8MQ_IOMUXC_ENET_TD3 = 28,
+	MX8MQ_IOMUXC_ENET_TD2 = 29,
+	MX8MQ_IOMUXC_ENET_TD1 = 30,
+	MX8MQ_IOMUXC_ENET_TD0 = 31,
+	MX8MQ_IOMUXC_ENET_TX_CTL = 32,
+	MX8MQ_IOMUXC_ENET_TXC = 33,
+	MX8MQ_IOMUXC_ENET_RX_CTL = 34,
+	MX8MQ_IOMUXC_ENET_RXC = 35,
+	MX8MQ_IOMUXC_ENET_RD0 = 36,
+	MX8MQ_IOMUXC_ENET_RD1 = 37,
+	MX8MQ_IOMUXC_ENET_RD2 = 38,
+	MX8MQ_IOMUXC_ENET_RD3 = 39,
+	MX8MQ_IOMUXC_SD1_CLK = 40,
+	MX8MQ_IOMUXC_SD1_CMD = 41,
+	MX8MQ_IOMUXC_SD1_DATA0 = 42,
+	MX8MQ_IOMUXC_SD1_DATA1 = 43,
+	MX8MQ_IOMUXC_SD1_DATA2 = 44,
+	MX8MQ_IOMUXC_SD1_DATA3 = 45,
+	MX8MQ_IOMUXC_SD1_DATA4 = 46,
+	MX8MQ_IOMUXC_SD1_DATA5 = 47,
+	MX8MQ_IOMUXC_SD1_DATA6 = 48,
+	MX8MQ_IOMUXC_SD1_DATA7 = 49,
+	MX8MQ_IOMUXC_SD1_RESET_B = 50,
+	MX8MQ_IOMUXC_SD1_STROBE = 51,
+	MX8MQ_IOMUXC_SD2_CD_B = 52,
+	MX8MQ_IOMUXC_SD2_CLK = 53,
+	MX8MQ_IOMUXC_SD2_CMD = 54,
+	MX8MQ_IOMUXC_SD2_DATA0 = 55,
+	MX8MQ_IOMUXC_SD2_DATA1 = 56,
+	MX8MQ_IOMUXC_SD2_DATA2 = 57,
+	MX8MQ_IOMUXC_SD2_DATA3 = 58,
+	MX8MQ_IOMUXC_SD2_RESET_B = 59,
+	MX8MQ_IOMUXC_SD2_WP = 60,
+	MX8MQ_IOMUXC_NAND_ALE = 61,
+	MX8MQ_IOMUXC_NAND_CE0_B = 62,
+	MX8MQ_IOMUXC_NAND_CE1_B = 63,
+	MX8MQ_IOMUXC_NAND_CE2_B = 64,
+	MX8MQ_IOMUXC_NAND_CE3_B = 65,
+	MX8MQ_IOMUXC_NAND_CLE = 66,
+	MX8MQ_IOMUXC_NAND_DATA00 = 67,
+	MX8MQ_IOMUXC_NAND_DATA01 = 68,
+	MX8MQ_IOMUXC_NAND_DATA02 = 69,
+	MX8MQ_IOMUXC_NAND_DATA03 = 70,
+	MX8MQ_IOMUXC_NAND_DATA04 = 71,
+	MX8MQ_IOMUXC_NAND_DATA05 = 72,
+	MX8MQ_IOMUXC_NAND_DATA06 = 73,
+	MX8MQ_IOMUXC_NAND_DATA07 = 74,
+	MX8MQ_IOMUXC_NAND_DQS = 75,
+	MX8MQ_IOMUXC_NAND_RE_B = 76,
+	MX8MQ_IOMUXC_NAND_READY_B = 77,
+	MX8MQ_IOMUXC_NAND_WE_B = 78,
+	MX8MQ_IOMUXC_NAND_WP_B = 79,
+	MX8MQ_IOMUXC_SAI5_RXFS = 80,
+	MX8MQ_IOMUXC_SAI5_RXC = 81,
+	MX8MQ_IOMUXC_SAI5_RXD0 = 82,
+	MX8MQ_IOMUXC_SAI5_RXD1 = 83,
+	MX8MQ_IOMUXC_SAI5_RXD2 = 84,
+	MX8MQ_IOMUXC_SAI5_RXD3 = 85,
+	MX8MQ_IOMUXC_SAI5_MCLK = 86,
+	MX8MQ_IOMUXC_SAI1_RXFS = 87,
+	MX8MQ_IOMUXC_SAI1_RXC = 88,
+	MX8MQ_IOMUXC_SAI1_RXD0 = 89,
+	MX8MQ_IOMUXC_SAI1_RXD1 = 90,
+	MX8MQ_IOMUXC_SAI1_RXD2 = 91,
+	MX8MQ_IOMUXC_SAI1_RXD3 = 92,
+	MX8MQ_IOMUXC_SAI1_RXD4 = 93,
+	MX8MQ_IOMUXC_SAI1_RXD5 = 94,
+	MX8MQ_IOMUXC_SAI1_RXD6 = 95,
+	MX8MQ_IOMUXC_SAI1_RXD7 = 96,
+	MX8MQ_IOMUXC_SAI1_TXFS = 97,
+	MX8MQ_IOMUXC_SAI1_TXC = 98,
+	MX8MQ_IOMUXC_SAI1_TXD0 = 99,
+	MX8MQ_IOMUXC_SAI1_TXD1 = 100,
+	MX8MQ_IOMUXC_SAI1_TXD2 = 101,
+	MX8MQ_IOMUXC_SAI1_TXD3 = 102,
+	MX8MQ_IOMUXC_SAI1_TXD4 = 103,
+	MX8MQ_IOMUXC_SAI1_TXD5 = 104,
+	MX8MQ_IOMUXC_SAI1_TXD6 = 105,
+	MX8MQ_IOMUXC_SAI1_TXD7 = 106,
+	MX8MQ_IOMUXC_SAI1_MCLK = 107,
+	MX8MQ_IOMUXC_SAI2_RXFS = 108,
+	MX8MQ_IOMUXC_SAI2_RXC = 109,
+	MX8MQ_IOMUXC_SAI2_RXD0 = 110,
+	MX8MQ_IOMUXC_SAI2_TXFS = 111,
+	MX8MQ_IOMUXC_SAI2_TXC = 112,
+	MX8MQ_IOMUXC_SAI2_TXD0 = 113,
+	MX8MQ_IOMUXC_SAI2_MCLK = 114,
+	MX8MQ_IOMUXC_SAI3_RXFS = 115,
+	MX8MQ_IOMUXC_SAI3_RXC = 116,
+	MX8MQ_IOMUXC_SAI3_RXD = 117,
+	MX8MQ_IOMUXC_SAI3_TXFS = 118,
+	MX8MQ_IOMUXC_SAI3_TXC = 119,
+	MX8MQ_IOMUXC_SAI3_TXD = 120,
+	MX8MQ_IOMUXC_SAI3_MCLK = 121,
+	MX8MQ_IOMUXC_SPDIF_TX = 122,
+	MX8MQ_IOMUXC_SPDIF_RX = 123,
+	MX8MQ_IOMUXC_SPDIF_EXT_CLK = 124,
+	MX8MQ_IOMUXC_ECSPI1_SCLK = 125,
+	MX8MQ_IOMUXC_ECSPI1_MOSI = 126,
+	MX8MQ_IOMUXC_ECSPI1_MISO = 127,
+	MX8MQ_IOMUXC_ECSPI1_SS0 = 128,
+	MX8MQ_IOMUXC_ECSPI2_SCLK = 129,
+	MX8MQ_IOMUXC_ECSPI2_MOSI = 130,
+	MX8MQ_IOMUXC_ECSPI2_MISO = 131,
+	MX8MQ_IOMUXC_ECSPI2_SS0 = 132,
+	MX8MQ_IOMUXC_I2C1_SCL = 133,
+	MX8MQ_IOMUXC_I2C1_SDA = 134,
+	MX8MQ_IOMUXC_I2C2_SCL = 135,
+	MX8MQ_IOMUXC_I2C2_SDA = 136,
+	MX8MQ_IOMUXC_I2C3_SCL = 137,
+	MX8MQ_IOMUXC_I2C3_SDA = 138,
+	MX8MQ_IOMUXC_I2C4_SCL = 139,
+	MX8MQ_IOMUXC_I2C4_SDA = 140,
+	MX8MQ_IOMUXC_UART1_RXD = 141,
+	MX8MQ_IOMUXC_UART1_TXD = 142,
+	MX8MQ_IOMUXC_UART2_RXD = 143,
+	MX8MQ_IOMUXC_UART2_TXD = 144,
+	MX8MQ_IOMUXC_UART3_RXD = 145,
+	MX8MQ_IOMUXC_UART3_TXD = 146,
+	MX8MQ_IOMUXC_UART4_RXD = 147,
+	MX8MQ_IOMUXC_UART4_TXD = 148,
+};
+
+/* Pad names for the pinmux subsystem */
+static const struct pinctrl_pin_desc imx8mq_pinctrl_pads[] = {
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE0),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE1),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE2),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE3),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_PMIC_STBY_REQ_CCMSRCGPCMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_PMIC_ON_REQ_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ONOFF_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_POR_B_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_RTC_RESET_B_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO00),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO01),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO02),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO03),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO04),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO05),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO06),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO07),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO08),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO09),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO10),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO11),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO12),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO13),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO14),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO15),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_MDC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_MDIO),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TX_CTL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RX_CTL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_CLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_CMD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA5),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA6),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA7),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_RESET_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_STROBE),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_CD_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_CLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_CMD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_RESET_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_WP),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_ALE),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE0_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE1_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE2_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE3_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CLE),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA00),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA01),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA02),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA03),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA04),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA05),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA06),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA07),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DQS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_RE_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_READY_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_WE_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_WP_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD5),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD6),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD7),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD5),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD6),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD7),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_RXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_TXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_TXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_TXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SPDIF_TX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SPDIF_RX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SPDIF_EXT_CLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_SCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_MOSI),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_MISO),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_SS0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_SCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_MOSI),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_MISO),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_SS0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C1_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C1_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C2_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C2_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C3_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C3_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C4_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C4_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART1_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART1_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART2_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART2_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART3_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART3_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART4_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART4_TXD),
+};
+
+static const struct imx_pinctrl_soc_info imx8mq_pinctrl_info = {
+	.pins = imx8mq_pinctrl_pads,
+	.npins = ARRAY_SIZE(imx8mq_pinctrl_pads),
+	.gpr_compatible = "fsl,imx8mq-iomuxc-gpr",
+};
+
+static const struct of_device_id imx8mq_pinctrl_of_match[] = {
+	{ .compatible = "fsl,imx8mq-iomuxc", .data = &imx8mq_pinctrl_info, },
+	{ /* sentinel */ }
+};
+
+static int imx8mq_pinctrl_probe(struct platform_device *pdev)
+{
+	return imx_pinctrl_probe(pdev, &imx8mq_pinctrl_info);
+}
+
+static struct platform_driver imx8mq_pinctrl_driver = {
+	.driver = {
+		.name = "imx8mq-pinctrl",
+		.of_match_table = of_match_ptr(imx8mq_pinctrl_of_match),
+		.suppress_bind_attrs = true,
+	},
+	.probe = imx8mq_pinctrl_probe,
+};
+
+static int __init imx8mq_pinctrl_init(void)
+{
+	return platform_driver_register(&imx8mq_pinctrl_driver);
+}
+arch_initcall(imx8mq_pinctrl_init);
diff --git a/drivers/pinctrl/intel/Kconfig b/drivers/pinctrl/intel/Kconfig
index 4aea1b8504f7..452a14f78707 100644
--- a/drivers/pinctrl/intel/Kconfig
+++ b/drivers/pinctrl/intel/Kconfig
@@ -1,6 +1,6 @@
-#
+# SPDX-License-Identifier: GPL-2.0
 # Intel pin control drivers
-#
+
 if (X86 || COMPILE_TEST)
 
 config PINCTRL_BAYTRAIL
@@ -90,6 +90,14 @@ config PINCTRL_GEMINILAKE
 	  This pinctrl driver provides an interface that allows configuring
 	  of Intel Gemini Lake SoC pins and using them as GPIOs.
 
+config PINCTRL_ICELAKE
+	tristate "Intel Ice Lake PCH pinctrl and GPIO driver"
+	depends on ACPI
+	select PINCTRL_INTEL
+	help
+	  This pinctrl driver provides an interface that allows configuring
+	  of Intel Ice Lake PCH pins and using them as GPIOs.
+
 config PINCTRL_LEWISBURG
 	tristate "Intel Lewisburg pinctrl and GPIO driver"
 	depends on ACPI
diff --git a/drivers/pinctrl/intel/Makefile b/drivers/pinctrl/intel/Makefile
index fadfe3ea2b04..cb491e655749 100644
--- a/drivers/pinctrl/intel/Makefile
+++ b/drivers/pinctrl/intel/Makefile
@@ -10,5 +10,6 @@ obj-$(CONFIG_PINCTRL_CANNONLAKE)	+= pinctrl-cannonlake.o
 obj-$(CONFIG_PINCTRL_CEDARFORK)		+= pinctrl-cedarfork.o
 obj-$(CONFIG_PINCTRL_DENVERTON)		+= pinctrl-denverton.o
 obj-$(CONFIG_PINCTRL_GEMINILAKE)	+= pinctrl-geminilake.o
+obj-$(CONFIG_PINCTRL_ICELAKE)		+= pinctrl-icelake.o
 obj-$(CONFIG_PINCTRL_LEWISBURG)		+= pinctrl-lewisburg.o
 obj-$(CONFIG_PINCTRL_SUNRISEPOINT)	+= pinctrl-sunrisepoint.o
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 6b52ea1440a6..f38d596efa05 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Pinctrl GPIO driver for Intel Baytrail
- * Copyright (c) 2012-2013, Intel Corporation.
  *
+ * Copyright (c) 2012-2013, Intel Corporation
  * Author: Mathias Nyman <mathias.nyman@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
 #include <linux/kernel.h>
@@ -1542,11 +1534,13 @@ static void byt_irq_unmask(struct irq_data *d)
 	switch (irqd_get_trigger_type(d)) {
 	case IRQ_TYPE_LEVEL_HIGH:
 		value |= BYT_TRIG_LVL;
+		/* fall through */
 	case IRQ_TYPE_EDGE_RISING:
 		value |= BYT_TRIG_POS;
 		break;
 	case IRQ_TYPE_LEVEL_LOW:
 		value |= BYT_TRIG_LVL;
+		/* fall through */
 	case IRQ_TYPE_EDGE_FALLING:
 		value |= BYT_TRIG_NEG;
 		break;
@@ -1691,7 +1685,8 @@ static void byt_gpio_irq_init_hw(struct byt_gpio *vg)
 		value = readl(reg);
 		if (value)
 			dev_err(&vg->pdev->dev,
-				"GPIO interrupt error, pins misconfigured\n");
+				"GPIO interrupt error, pins misconfigured. INT_STAT%u: 0x%08x\n",
+				base / 32, value);
 	}
 }
 
diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c
index e6e6fd112585..8b1c7b59ad3e 100644
--- a/drivers/pinctrl/intel/pinctrl-broxton.c
+++ b/drivers/pinctrl/intel/pinctrl-broxton.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Broxton SoC pinctrl/GPIO driver
  *
  * Copyright (C) 2015, 2016 Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c
index 6243e7d95e7e..fb1afe55bf53 100644
--- a/drivers/pinctrl/intel/pinctrl-cannonlake.c
+++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Cannon Lake PCH pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Authors: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
@@ -447,12 +444,8 @@ static const struct intel_function cnlh_functions[] = {
 static const struct intel_community cnlh_communities[] = {
 	CNL_COMMUNITY(0, 0, 50, cnlh_community0_gpps),
 	CNL_COMMUNITY(1, 51, 154, cnlh_community1_gpps),
-	/*
-	 * ACPI MMIO resources are returned in reverse order for
-	 * communities 3 and 4.
-	 */
-	CNL_COMMUNITY(3, 155, 248, cnlh_community3_gpps),
-	CNL_COMMUNITY(2, 249, 298, cnlh_community4_gpps),
+	CNL_COMMUNITY(2, 155, 248, cnlh_community3_gpps),
+	CNL_COMMUNITY(3, 249, 298, cnlh_community4_gpps),
 };
 
 static const struct intel_pinctrl_soc_data cnlh_soc_data = {
diff --git a/drivers/pinctrl/intel/pinctrl-cedarfork.c b/drivers/pinctrl/intel/pinctrl-cedarfork.c
index 59216b0533d9..c788e37e338e 100644
--- a/drivers/pinctrl/intel/pinctrl-cedarfork.c
+++ b/drivers/pinctrl/intel/pinctrl-cedarfork.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Cedar Fork PCH pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
@@ -240,51 +237,51 @@ static const struct pinctrl_pin_desc cdf_pins[] = {
 	PINCTRL_PIN(179, "GBE_GPIO10"),
 	PINCTRL_PIN(180, "GBE_GPIO11"),
 	PINCTRL_PIN(181, "GBE_GPIO12"),
-	PINCTRL_PIN(182, "SATA0_LED_N"),
-	PINCTRL_PIN(183, "SATA1_LED_N"),
-	PINCTRL_PIN(184, "SATA_PDETECT0"),
-	PINCTRL_PIN(185, "SATA_PDETECT1"),
-	PINCTRL_PIN(186, "SATA0_SDOUT"),
-	PINCTRL_PIN(187, "SATA1_SDOUT"),
-	PINCTRL_PIN(188, "SATA2_LED_N"),
-	PINCTRL_PIN(189, "SATA_PDETECT2"),
-	PINCTRL_PIN(190, "SATA2_SDOUT"),
+	PINCTRL_PIN(182, "PECI_SMB_DATA"),
+	PINCTRL_PIN(183, "SATA0_LED_N"),
+	PINCTRL_PIN(184, "SATA1_LED_N"),
+	PINCTRL_PIN(185, "SATA_PDETECT0"),
+	PINCTRL_PIN(186, "SATA_PDETECT1"),
+	PINCTRL_PIN(187, "SATA0_SDOUT"),
+	PINCTRL_PIN(188, "SATA1_SDOUT"),
+	PINCTRL_PIN(189, "SATA2_LED_N"),
+	PINCTRL_PIN(190, "SATA_PDETECT2"),
+	PINCTRL_PIN(191, "SATA2_SDOUT"),
 	/* EAST3 */
-	PINCTRL_PIN(191, "ESPI_IO0"),
-	PINCTRL_PIN(192, "ESPI_IO1"),
-	PINCTRL_PIN(193, "ESPI_IO2"),
-	PINCTRL_PIN(194, "ESPI_IO3"),
-	PINCTRL_PIN(195, "ESPI_CLK"),
-	PINCTRL_PIN(196, "ESPI_RST_N"),
-	PINCTRL_PIN(197, "ESPI_CS0_N"),
-	PINCTRL_PIN(198, "ESPI_ALRT0_N"),
-	PINCTRL_PIN(199, "ESPI_CS1_N"),
-	PINCTRL_PIN(200, "ESPI_ALRT1_N"),
-	PINCTRL_PIN(201, "ESPI_CLK_LOOPBK"),
+	PINCTRL_PIN(192, "ESPI_IO0"),
+	PINCTRL_PIN(193, "ESPI_IO1"),
+	PINCTRL_PIN(194, "ESPI_IO2"),
+	PINCTRL_PIN(195, "ESPI_IO3"),
+	PINCTRL_PIN(196, "ESPI_CLK"),
+	PINCTRL_PIN(197, "ESPI_RST_N"),
+	PINCTRL_PIN(198, "ESPI_CS0_N"),
+	PINCTRL_PIN(199, "ESPI_ALRT0_N"),
+	PINCTRL_PIN(200, "ESPI_CS1_N"),
+	PINCTRL_PIN(201, "ESPI_ALRT1_N"),
+	PINCTRL_PIN(202, "ESPI_CLK_LOOPBK"),
 	/* EAST0 */
-	PINCTRL_PIN(202, "SPI_CS0_N"),
-	PINCTRL_PIN(203, "SPI_CS1_N"),
-	PINCTRL_PIN(204, "SPI_MOSI_IO0"),
-	PINCTRL_PIN(205, "SPI_MISO_IO1"),
-	PINCTRL_PIN(206, "SPI_IO2"),
-	PINCTRL_PIN(207, "SPI_IO3"),
-	PINCTRL_PIN(208, "SPI_CLK"),
-	PINCTRL_PIN(209, "SPI_CLK_LOOPBK"),
-	PINCTRL_PIN(210, "SUSPWRDNACK"),
-	PINCTRL_PIN(211, "PMU_SUSCLK"),
-	PINCTRL_PIN(212, "ADR_COMPLETE"),
-	PINCTRL_PIN(213, "ADR_TRIGGER_N"),
-	PINCTRL_PIN(214, "PMU_SLP_S45_N"),
-	PINCTRL_PIN(215, "PMU_SLP_S3_N"),
-	PINCTRL_PIN(216, "PMU_WAKE_N"),
-	PINCTRL_PIN(217, "PMU_PWRBTN_N"),
-	PINCTRL_PIN(218, "PMU_RESETBUTTON_N"),
-	PINCTRL_PIN(219, "PMU_PLTRST_N"),
-	PINCTRL_PIN(220, "SUS_STAT_N"),
-	PINCTRL_PIN(221, "PMU_I2C_CLK"),
-	PINCTRL_PIN(222, "PMU_I2C_DATA"),
-	PINCTRL_PIN(223, "PECI_SMB_CLK"),
-	PINCTRL_PIN(224, "PECI_SMB_DATA"),
+	PINCTRL_PIN(203, "SPI_CS0_N"),
+	PINCTRL_PIN(204, "SPI_CS1_N"),
+	PINCTRL_PIN(205, "SPI_MOSI_IO0"),
+	PINCTRL_PIN(206, "SPI_MISO_IO1"),
+	PINCTRL_PIN(207, "SPI_IO2"),
+	PINCTRL_PIN(208, "SPI_IO3"),
+	PINCTRL_PIN(209, "SPI_CLK"),
+	PINCTRL_PIN(210, "SPI_CLK_LOOPBK"),
+	PINCTRL_PIN(211, "SUSPWRDNACK"),
+	PINCTRL_PIN(212, "PMU_SUSCLK"),
+	PINCTRL_PIN(213, "ADR_COMPLETE"),
+	PINCTRL_PIN(214, "ADR_TRIGGER_N"),
+	PINCTRL_PIN(215, "PMU_SLP_S45_N"),
+	PINCTRL_PIN(216, "PMU_SLP_S3_N"),
+	PINCTRL_PIN(217, "PMU_WAKE_N"),
+	PINCTRL_PIN(218, "PMU_PWRBTN_N"),
+	PINCTRL_PIN(219, "PMU_RESETBUTTON_N"),
+	PINCTRL_PIN(220, "PMU_PLTRST_N"),
+	PINCTRL_PIN(221, "SUS_STAT_N"),
+	PINCTRL_PIN(222, "PMU_I2C_CLK"),
+	PINCTRL_PIN(223, "PMU_I2C_DATA"),
+	PINCTRL_PIN(224, "PECI_SMB_CLK"),
 	PINCTRL_PIN(225, "PECI_SMB_ALRT_N"),
 	/* EMMC */
 	PINCTRL_PIN(226, "EMMC_CMD"),
@@ -315,9 +312,9 @@ static const struct intel_padgroup cdf_community0_gpps[] = {
 };
 
 static const struct intel_padgroup cdf_community1_gpps[] = {
-	CDF_GPP(0, 168, 190),	/* EAST2 */
-	CDF_GPP(1, 191, 201),	/* EAST3 */
-	CDF_GPP(2, 202, 225),	/* EAST0 */
+	CDF_GPP(0, 168, 191),	/* EAST2 */
+	CDF_GPP(1, 192, 202),	/* EAST3 */
+	CDF_GPP(2, 203, 225),	/* EAST0 */
 	CDF_GPP(3, 226, 236),	/* EMMC */
 };
 
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 0f1019ae3993..6d31ad799987 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Cherryview/Braswell pinctrl driver
  *
@@ -7,10 +8,6 @@
  * This driver is based on the original Cherryview GPIO driver by
  *   Ning Li <ning.li@intel.com>
  *   Alan Cox <alan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/dmi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-denverton.c b/drivers/pinctrl/intel/pinctrl-denverton.c
index 6572550cfe78..f321ab0d76e5 100644
--- a/drivers/pinctrl/intel/pinctrl-denverton.c
+++ b/drivers/pinctrl/intel/pinctrl-denverton.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Denverton SoC pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-geminilake.c b/drivers/pinctrl/intel/pinctrl-geminilake.c
index a6b94c930007..5c4c96752fc1 100644
--- a/drivers/pinctrl/intel/pinctrl-geminilake.c
+++ b/drivers/pinctrl/intel/pinctrl-geminilake.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Gemini Lake SoC pinctrl/GPIO driver
  *
  * Copyright (C) 2017 Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-icelake.c b/drivers/pinctrl/intel/pinctrl-icelake.c
new file mode 100644
index 000000000000..630b966ce081
--- /dev/null
+++ b/drivers/pinctrl/intel/pinctrl-icelake.c
@@ -0,0 +1,436 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Ice Lake PCH pinctrl/GPIO driver
+ *
+ * Copyright (C) 2018, Intel Corporation
+ * Authors: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *	    Mika Westerberg <mika.westerberg@linux.intel.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-intel.h"
+
+#define ICL_PAD_OWN	0x020
+#define ICL_PADCFGLOCK	0x080
+#define ICL_HOSTSW_OWN	0x0b0
+#define ICL_GPI_IE	0x110
+
+#define ICL_GPP(r, s, e, g)				\
+	{						\
+		.reg_num = (r),				\
+		.base = (s),				\
+		.size = ((e) - (s) + 1),		\
+		.gpio_base = (g),			\
+	}
+
+#define ICL_NO_GPIO	-1
+
+#define ICL_COMMUNITY(b, s, e, g)			\
+	{						\
+		.barno = (b),				\
+		.padown_offset = ICL_PAD_OWN,		\
+		.padcfglock_offset = ICL_PADCFGLOCK,	\
+		.hostown_offset = ICL_HOSTSW_OWN,	\
+		.ie_offset = ICL_GPI_IE,		\
+		.pin_base = (s),			\
+		.npins = ((e) - (s) + 1),		\
+		.gpps = (g),				\
+		.ngpps = ARRAY_SIZE(g),			\
+	}
+
+/* Ice Lake-LP */
+static const struct pinctrl_pin_desc icllp_pins[] = {
+	/* GPP_G */
+	PINCTRL_PIN(0, "SD3_CMD"),
+	PINCTRL_PIN(1, "SD3_D0"),
+	PINCTRL_PIN(2, "SD3_D1"),
+	PINCTRL_PIN(3, "SD3_D2"),
+	PINCTRL_PIN(4, "SD3_D3"),
+	PINCTRL_PIN(5, "SD3_CDB"),
+	PINCTRL_PIN(6, "SD3_CLK"),
+	PINCTRL_PIN(7, "SD3_WP"),
+	/* GPP_B */
+	PINCTRL_PIN(8, "CORE_VID_0"),
+	PINCTRL_PIN(9, "CORE_VID_1"),
+	PINCTRL_PIN(10, "VRALERTB"),
+	PINCTRL_PIN(11, "CPU_GP_2"),
+	PINCTRL_PIN(12, "CPU_GP_3"),
+	PINCTRL_PIN(13, "ISH_I2C0_SDA"),
+	PINCTRL_PIN(14, "ISH_I2C0_SCL"),
+	PINCTRL_PIN(15, "ISH_I2C1_SDA"),
+	PINCTRL_PIN(16, "ISH_I2C1_SCL"),
+	PINCTRL_PIN(17, "I2C5_SDA"),
+	PINCTRL_PIN(18, "I2C5_SCL"),
+	PINCTRL_PIN(19, "PMCALERTB"),
+	PINCTRL_PIN(20, "SLP_S0B"),
+	PINCTRL_PIN(21, "PLTRSTB"),
+	PINCTRL_PIN(22, "SPKR"),
+	PINCTRL_PIN(23, "GSPI0_CS0B"),
+	PINCTRL_PIN(24, "GSPI0_CLK"),
+	PINCTRL_PIN(25, "GSPI0_MISO"),
+	PINCTRL_PIN(26, "GSPI0_MOSI"),
+	PINCTRL_PIN(27, "GSPI1_CS0B"),
+	PINCTRL_PIN(28, "GSPI1_CLK"),
+	PINCTRL_PIN(29, "GSPI1_MISO"),
+	PINCTRL_PIN(30, "GSPI1_MOSI"),
+	PINCTRL_PIN(31, "SML1ALERTB"),
+	PINCTRL_PIN(32, "GSPI0_CLK_LOOPBK"),
+	PINCTRL_PIN(33, "GSPI1_CLK_LOOPBK"),
+	/* GPP_A */
+	PINCTRL_PIN(34, "ESPI_IO_0"),
+	PINCTRL_PIN(35, "ESPI_IO_1"),
+	PINCTRL_PIN(36, "ESPI_IO_2"),
+	PINCTRL_PIN(37, "ESPI_IO_3"),
+	PINCTRL_PIN(38, "ESPI_CSB"),
+	PINCTRL_PIN(39, "ESPI_CLK"),
+	PINCTRL_PIN(40, "ESPI_RESETB"),
+	PINCTRL_PIN(41, "I2S2_SCLK"),
+	PINCTRL_PIN(42, "I2S2_SFRM"),
+	PINCTRL_PIN(43, "I2S2_TXD"),
+	PINCTRL_PIN(44, "I2S2_RXD"),
+	PINCTRL_PIN(45, "SATA_DEVSLP_2"),
+	PINCTRL_PIN(46, "SATAXPCIE_1"),
+	PINCTRL_PIN(47, "SATAXPCIE_2"),
+	PINCTRL_PIN(48, "USB2_OCB_1"),
+	PINCTRL_PIN(49, "USB2_OCB_2"),
+	PINCTRL_PIN(50, "USB2_OCB_3"),
+	PINCTRL_PIN(51, "DDSP_HPD_C"),
+	PINCTRL_PIN(52, "DDSP_HPD_B"),
+	PINCTRL_PIN(53, "DDSP_HPD_1"),
+	PINCTRL_PIN(54, "DDSP_HPD_2"),
+	PINCTRL_PIN(55, "I2S5_TXD"),
+	PINCTRL_PIN(56, "I2S5_RXD"),
+	PINCTRL_PIN(57, "I2S1_SCLK"),
+	PINCTRL_PIN(58, "ESPI_CLK_LOOPBK"),
+	/* GPP_H */
+	PINCTRL_PIN(59, "SD_1P8_SEL"),
+	PINCTRL_PIN(60, "SD_PWR_EN_B"),
+	PINCTRL_PIN(61, "GPPC_H_2"),
+	PINCTRL_PIN(62, "SX_EXIT_HOLDOFFB"),
+	PINCTRL_PIN(63, "I2C2_SDA"),
+	PINCTRL_PIN(64, "I2C2_SCL"),
+	PINCTRL_PIN(65, "I2C3_SDA"),
+	PINCTRL_PIN(66, "I2C3_SCL"),
+	PINCTRL_PIN(67, "I2C4_SDA"),
+	PINCTRL_PIN(68, "I2C4_SCL"),
+	PINCTRL_PIN(69, "SRCCLKREQB_4"),
+	PINCTRL_PIN(70, "SRCCLKREQB_5"),
+	PINCTRL_PIN(71, "M2_SKT2_CFG_0"),
+	PINCTRL_PIN(72, "M2_SKT2_CFG_1"),
+	PINCTRL_PIN(73, "M2_SKT2_CFG_2"),
+	PINCTRL_PIN(74, "M2_SKT2_CFG_3"),
+	PINCTRL_PIN(75, "DDPB_CTRLCLK"),
+	PINCTRL_PIN(76, "DDPB_CTRLDATA"),
+	PINCTRL_PIN(77, "CPU_VCCIO_PWR_GATEB"),
+	PINCTRL_PIN(78, "TIME_SYNC_0"),
+	PINCTRL_PIN(79, "IMGCLKOUT_1"),
+	PINCTRL_PIN(80, "IMGCLKOUT_2"),
+	PINCTRL_PIN(81, "IMGCLKOUT_3"),
+	PINCTRL_PIN(82, "IMGCLKOUT_4"),
+	/* GPP_D */
+	PINCTRL_PIN(83, "ISH_GP_0"),
+	PINCTRL_PIN(84, "ISH_GP_1"),
+	PINCTRL_PIN(85, "ISH_GP_2"),
+	PINCTRL_PIN(86, "ISH_GP_3"),
+	PINCTRL_PIN(87, "IMGCLKOUT_0"),
+	PINCTRL_PIN(88, "SRCCLKREQB_0"),
+	PINCTRL_PIN(89, "SRCCLKREQB_1"),
+	PINCTRL_PIN(90, "SRCCLKREQB_2"),
+	PINCTRL_PIN(91, "SRCCLKREQB_3"),
+	PINCTRL_PIN(92, "ISH_SPI_CSB"),
+	PINCTRL_PIN(93, "ISH_SPI_CLK"),
+	PINCTRL_PIN(94, "ISH_SPI_MISO"),
+	PINCTRL_PIN(95, "ISH_SPI_MOSI"),
+	PINCTRL_PIN(96, "ISH_UART0_RXD"),
+	PINCTRL_PIN(97, "ISH_UART0_TXD"),
+	PINCTRL_PIN(98, "ISH_UART0_RTSB"),
+	PINCTRL_PIN(99, "ISH_UART0_CTSB"),
+	PINCTRL_PIN(100, "ISH_GP_4"),
+	PINCTRL_PIN(101, "ISH_GP_5"),
+	PINCTRL_PIN(102, "I2S_MCLK"),
+	PINCTRL_PIN(103, "GSPI2_CLK_LOOPBK"),
+	/* GPP_F */
+	PINCTRL_PIN(104, "CNV_BRI_DT"),
+	PINCTRL_PIN(105, "CNV_BRI_RSP"),
+	PINCTRL_PIN(106, "CNV_RGI_DT"),
+	PINCTRL_PIN(107, "CNV_RGI_RSP"),
+	PINCTRL_PIN(108, "CNV_RF_RESET_B"),
+	PINCTRL_PIN(109, "EMMC_HIP_MON"),
+	PINCTRL_PIN(110, "CNV_PA_BLANKING"),
+	PINCTRL_PIN(111, "EMMC_CMD"),
+	PINCTRL_PIN(112, "EMMC_DATA0"),
+	PINCTRL_PIN(113, "EMMC_DATA1"),
+	PINCTRL_PIN(114, "EMMC_DATA2"),
+	PINCTRL_PIN(115, "EMMC_DATA3"),
+	PINCTRL_PIN(116, "EMMC_DATA4"),
+	PINCTRL_PIN(117, "EMMC_DATA5"),
+	PINCTRL_PIN(118, "EMMC_DATA6"),
+	PINCTRL_PIN(119, "EMMC_DATA7"),
+	PINCTRL_PIN(120, "EMMC_RCLK"),
+	PINCTRL_PIN(121, "EMMC_CLK"),
+	PINCTRL_PIN(122, "EMMC_RESETB"),
+	PINCTRL_PIN(123, "A4WP_PRESENT"),
+	/* vGPIO */
+	PINCTRL_PIN(124, "CNV_BTEN"),
+	PINCTRL_PIN(125, "CNV_WCEN"),
+	PINCTRL_PIN(126, "CNV_BT_HOST_WAKEB"),
+	PINCTRL_PIN(127, "CNV_BT_IF_SELECT"),
+	PINCTRL_PIN(128, "vCNV_BT_UART_TXD"),
+	PINCTRL_PIN(129, "vCNV_BT_UART_RXD"),
+	PINCTRL_PIN(130, "vCNV_BT_UART_CTS_B"),
+	PINCTRL_PIN(131, "vCNV_BT_UART_RTS_B"),
+	PINCTRL_PIN(132, "vCNV_MFUART1_TXD"),
+	PINCTRL_PIN(133, "vCNV_MFUART1_RXD"),
+	PINCTRL_PIN(134, "vCNV_MFUART1_CTS_B"),
+	PINCTRL_PIN(135, "vCNV_MFUART1_RTS_B"),
+	PINCTRL_PIN(136, "vUART0_TXD"),
+	PINCTRL_PIN(137, "vUART0_RXD"),
+	PINCTRL_PIN(138, "vUART0_CTS_B"),
+	PINCTRL_PIN(139, "vUART0_RTS_B"),
+	PINCTRL_PIN(140, "vISH_UART0_TXD"),
+	PINCTRL_PIN(141, "vISH_UART0_RXD"),
+	PINCTRL_PIN(142, "vISH_UART0_CTS_B"),
+	PINCTRL_PIN(143, "vISH_UART0_RTS_B"),
+	PINCTRL_PIN(144, "vCNV_BT_I2S_BCLK"),
+	PINCTRL_PIN(145, "vCNV_BT_I2S_WS_SYNC"),
+	PINCTRL_PIN(146, "vCNV_BT_I2S_SDO"),
+	PINCTRL_PIN(147, "vCNV_BT_I2S_SDI"),
+	PINCTRL_PIN(148, "vI2S2_SCLK"),
+	PINCTRL_PIN(149, "vI2S2_SFRM"),
+	PINCTRL_PIN(150, "vI2S2_TXD"),
+	PINCTRL_PIN(151, "vI2S2_RXD"),
+	PINCTRL_PIN(152, "vSD3_CD_B"),
+	/* GPP_C */
+	PINCTRL_PIN(153, "SMBCLK"),
+	PINCTRL_PIN(154, "SMBDATA"),
+	PINCTRL_PIN(155, "SMBALERTB"),
+	PINCTRL_PIN(156, "SML0CLK"),
+	PINCTRL_PIN(157, "SML0DATA"),
+	PINCTRL_PIN(158, "SML0ALERTB"),
+	PINCTRL_PIN(159, "SML1CLK"),
+	PINCTRL_PIN(160, "SML1DATA"),
+	PINCTRL_PIN(161, "UART0_RXD"),
+	PINCTRL_PIN(162, "UART0_TXD"),
+	PINCTRL_PIN(163, "UART0_RTSB"),
+	PINCTRL_PIN(164, "UART0_CTSB"),
+	PINCTRL_PIN(165, "UART1_RXD"),
+	PINCTRL_PIN(166, "UART1_TXD"),
+	PINCTRL_PIN(167, "UART1_RTSB"),
+	PINCTRL_PIN(168, "UART1_CTSB"),
+	PINCTRL_PIN(169, "I2C0_SDA"),
+	PINCTRL_PIN(170, "I2C0_SCL"),
+	PINCTRL_PIN(171, "I2C1_SDA"),
+	PINCTRL_PIN(172, "I2C1_SCL"),
+	PINCTRL_PIN(173, "UART2_RXD"),
+	PINCTRL_PIN(174, "UART2_TXD"),
+	PINCTRL_PIN(175, "UART2_RTSB"),
+	PINCTRL_PIN(176, "UART2_CTSB"),
+	/* HVCMOS */
+	PINCTRL_PIN(177, "L_BKLTEN"),
+	PINCTRL_PIN(178, "L_BKLTCTL"),
+	PINCTRL_PIN(179, "L_VDDEN"),
+	PINCTRL_PIN(180, "SYS_PWROK"),
+	PINCTRL_PIN(181, "SYS_RESETB"),
+	PINCTRL_PIN(182, "MLK_RSTB"),
+	/* GPP_E */
+	PINCTRL_PIN(183, "SATAXPCIE_0"),
+	PINCTRL_PIN(184, "SPI1_IO_2"),
+	PINCTRL_PIN(185, "SPI1_IO_3"),
+	PINCTRL_PIN(186, "CPU_GP_0"),
+	PINCTRL_PIN(187, "SATA_DEVSLP_0"),
+	PINCTRL_PIN(188, "SATA_DEVSLP_1"),
+	PINCTRL_PIN(189, "GPPC_E_6"),
+	PINCTRL_PIN(190, "CPU_GP_1"),
+	PINCTRL_PIN(191, "SATA_LEDB"),
+	PINCTRL_PIN(192, "USB2_OCB_0"),
+	PINCTRL_PIN(193, "SPI1_CSB"),
+	PINCTRL_PIN(194, "SPI1_CLK"),
+	PINCTRL_PIN(195, "SPI1_MISO_IO_1"),
+	PINCTRL_PIN(196, "SPI1_MOSI_IO_0"),
+	PINCTRL_PIN(197, "DDSP_HPD_A"),
+	PINCTRL_PIN(198, "ISH_GP_6"),
+	PINCTRL_PIN(199, "ISH_GP_7"),
+	PINCTRL_PIN(200, "DISP_MISC_4"),
+	PINCTRL_PIN(201, "DDP1_CTRLCLK"),
+	PINCTRL_PIN(202, "DDP1_CTRLDATA"),
+	PINCTRL_PIN(203, "DDP2_CTRLCLK"),
+	PINCTRL_PIN(204, "DDP2_CTRLDATA"),
+	PINCTRL_PIN(205, "DDPA_CTRLCLK"),
+	PINCTRL_PIN(206, "DDPA_CTRLDATA"),
+	/* JTAG */
+	PINCTRL_PIN(207, "JTAG_TDO"),
+	PINCTRL_PIN(208, "JTAGX"),
+	PINCTRL_PIN(209, "PRDYB"),
+	PINCTRL_PIN(210, "PREQB"),
+	PINCTRL_PIN(211, "CPU_TRSTB"),
+	PINCTRL_PIN(212, "JTAG_TDI"),
+	PINCTRL_PIN(213, "JTAG_TMS"),
+	PINCTRL_PIN(214, "JTAG_TCK"),
+	PINCTRL_PIN(215, "ITP_PMODE"),
+	/* GPP_R */
+	PINCTRL_PIN(216, "HDA_BCLK"),
+	PINCTRL_PIN(217, "HDA_SYNC"),
+	PINCTRL_PIN(218, "HDA_SDO"),
+	PINCTRL_PIN(219, "HDA_SDI_0"),
+	PINCTRL_PIN(220, "HDA_RSTB"),
+	PINCTRL_PIN(221, "HDA_SDI_1"),
+	PINCTRL_PIN(222, "I2S1_TXD"),
+	PINCTRL_PIN(223, "I2S1_RXD"),
+	/* GPP_S */
+	PINCTRL_PIN(224, "SNDW1_CLK"),
+	PINCTRL_PIN(225, "SNDW1_DATA"),
+	PINCTRL_PIN(226, "SNDW2_CLK"),
+	PINCTRL_PIN(227, "SNDW2_DATA"),
+	PINCTRL_PIN(228, "SNDW3_CLK"),
+	PINCTRL_PIN(229, "SNDW3_DATA"),
+	PINCTRL_PIN(230, "SNDW4_CLK"),
+	PINCTRL_PIN(231, "SNDW4_DATA"),
+	/* SPI */
+	PINCTRL_PIN(232, "SPI0_IO_2"),
+	PINCTRL_PIN(233, "SPI0_IO_3"),
+	PINCTRL_PIN(234, "SPI0_MOSI_IO_0"),
+	PINCTRL_PIN(235, "SPI0_MISO_IO_1"),
+	PINCTRL_PIN(236, "SPI0_TPM_CSB"),
+	PINCTRL_PIN(237, "SPI0_FLASH_0_CSB"),
+	PINCTRL_PIN(238, "SPI0_FLASH_1_CSB"),
+	PINCTRL_PIN(239, "SPI0_CLK"),
+	PINCTRL_PIN(240, "SPI0_CLK_LOOPBK"),
+};
+
+static const struct intel_padgroup icllp_community0_gpps[] = {
+	ICL_GPP(0, 0, 7, 0),			/* GPP_G */
+	ICL_GPP(1, 8, 33, 32),			/* GPP_B */
+	ICL_GPP(2, 34, 58, 64),			/* GPP_A */
+};
+
+static const struct intel_padgroup icllp_community1_gpps[] = {
+	ICL_GPP(0, 59, 82, 96),			/* GPP_H */
+	ICL_GPP(1, 83, 103, 128),		/* GPP_D */
+	ICL_GPP(2, 104, 123, 160),		/* GPP_F */
+	ICL_GPP(3, 124, 152, 192),		/* vGPIO */
+};
+
+static const struct intel_padgroup icllp_community4_gpps[] = {
+	ICL_GPP(0, 153, 176, 224),		/* GPP_C */
+	ICL_GPP(1, 177, 182, ICL_NO_GPIO),	/* HVCMOS */
+	ICL_GPP(2, 183, 206, 256),		/* GPP_E */
+	ICL_GPP(3, 207, 215, ICL_NO_GPIO),	/* JTAG */
+};
+
+static const struct intel_padgroup icllp_community5_gpps[] = {
+	ICL_GPP(0, 216, 223, 288),		/* GPP_R */
+	ICL_GPP(1, 224, 231, 320),		/* GPP_S */
+	ICL_GPP(2, 232, 240, ICL_NO_GPIO),	/* SPI */
+};
+
+static const struct intel_community icllp_communities[] = {
+	ICL_COMMUNITY(0, 0, 58, icllp_community0_gpps),
+	ICL_COMMUNITY(1, 59, 152, icllp_community1_gpps),
+	ICL_COMMUNITY(2, 153, 215, icllp_community4_gpps),
+	ICL_COMMUNITY(3, 216, 240, icllp_community5_gpps),
+};
+
+static const unsigned int icllp_spi0_pins[] = { 22, 23, 24, 25, 26 };
+static const unsigned int icllp_spi0_modes[] = { 3, 1, 1, 1, 1 };
+static const unsigned int icllp_spi1_pins[] = { 27, 28, 29, 30, 31 };
+static const unsigned int icllp_spi1_modes[] = { 1, 1, 1, 1, 3 };
+static const unsigned int icllp_spi2_pins[] = { 92, 93, 94, 95, 98 };
+static const unsigned int icllp_spi2_modes[] = { 3, 3, 3, 3, 2 };
+
+static const unsigned int icllp_i2c0_pins[] = { 169, 170 };
+static const unsigned int icllp_i2c1_pins[] = { 171, 172 };
+static const unsigned int icllp_i2c2_pins[] = { 63, 64 };
+static const unsigned int icllp_i2c3_pins[] = { 65, 66 };
+static const unsigned int icllp_i2c4_pins[] = { 67, 68 };
+
+static const unsigned int icllp_uart0_pins[] = { 161, 162, 163, 164 };
+static const unsigned int icllp_uart1_pins[] = { 165, 166, 167, 168 };
+static const unsigned int icllp_uart2_pins[] = { 173, 174, 175, 176 };
+
+static const struct intel_pingroup icllp_groups[] = {
+	PIN_GROUP("spi0_grp", icllp_spi0_pins, icllp_spi0_modes),
+	PIN_GROUP("spi1_grp", icllp_spi1_pins, icllp_spi1_modes),
+	PIN_GROUP("spi2_grp", icllp_spi2_pins, icllp_spi2_modes),
+	PIN_GROUP("i2c0_grp", icllp_i2c0_pins, 1),
+	PIN_GROUP("i2c1_grp", icllp_i2c1_pins, 1),
+	PIN_GROUP("i2c2_grp", icllp_i2c2_pins, 1),
+	PIN_GROUP("i2c3_grp", icllp_i2c3_pins, 1),
+	PIN_GROUP("i2c4_grp", icllp_i2c4_pins, 1),
+	PIN_GROUP("uart0_grp", icllp_uart0_pins, 1),
+	PIN_GROUP("uart1_grp", icllp_uart1_pins, 1),
+	PIN_GROUP("uart2_grp", icllp_uart2_pins, 1),
+};
+
+static const char * const icllp_spi0_groups[] = { "spi0_grp" };
+static const char * const icllp_spi1_groups[] = { "spi1_grp" };
+static const char * const icllp_spi2_groups[] = { "spi2_grp" };
+static const char * const icllp_i2c0_groups[] = { "i2c0_grp" };
+static const char * const icllp_i2c1_groups[] = { "i2c1_grp" };
+static const char * const icllp_i2c2_groups[] = { "i2c2_grp" };
+static const char * const icllp_i2c3_groups[] = { "i2c3_grp" };
+static const char * const icllp_i2c4_groups[] = { "i2c4_grp" };
+static const char * const icllp_uart0_groups[] = { "uart0_grp" };
+static const char * const icllp_uart1_groups[] = { "uart1_grp" };
+static const char * const icllp_uart2_groups[] = { "uart2_grp" };
+
+static const struct intel_function icllp_functions[] = {
+	FUNCTION("spi0", icllp_spi0_groups),
+	FUNCTION("spi1", icllp_spi1_groups),
+	FUNCTION("spi2", icllp_spi2_groups),
+	FUNCTION("i2c0", icllp_i2c0_groups),
+	FUNCTION("i2c1", icllp_i2c1_groups),
+	FUNCTION("i2c2", icllp_i2c2_groups),
+	FUNCTION("i2c3", icllp_i2c3_groups),
+	FUNCTION("i2c4", icllp_i2c4_groups),
+	FUNCTION("uart0", icllp_uart0_groups),
+	FUNCTION("uart1", icllp_uart1_groups),
+	FUNCTION("uart2", icllp_uart2_groups),
+};
+
+static const struct intel_pinctrl_soc_data icllp_soc_data = {
+	.pins = icllp_pins,
+	.npins = ARRAY_SIZE(icllp_pins),
+	.groups = icllp_groups,
+	.ngroups = ARRAY_SIZE(icllp_groups),
+	.functions = icllp_functions,
+	.nfunctions = ARRAY_SIZE(icllp_functions),
+	.communities = icllp_communities,
+	.ncommunities = ARRAY_SIZE(icllp_communities),
+};
+
+static int icl_pinctrl_probe(struct platform_device *pdev)
+{
+	return intel_pinctrl_probe(pdev, &icllp_soc_data);
+}
+
+static const struct dev_pm_ops icl_pinctrl_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(intel_pinctrl_suspend,
+				     intel_pinctrl_resume)
+};
+
+static const struct acpi_device_id icl_pinctrl_acpi_match[] = {
+	{ "INT3455" },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, icl_pinctrl_acpi_match);
+
+static struct platform_driver icl_pinctrl_driver = {
+	.probe = icl_pinctrl_probe,
+	.driver = {
+		.name = "icelake-pinctrl",
+		.acpi_match_table = icl_pinctrl_acpi_match,
+		.pm = &icl_pinctrl_pm_ops,
+	},
+};
+
+module_platform_driver(icl_pinctrl_driver);
+
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_DESCRIPTION("Intel Ice Lake PCH pinctrl/GPIO driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 1e24a6b8a64e..62b009b27eda 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel pinctrl/GPIO core driver.
  *
  * Copyright (C) 2015, Intel Corporation
  * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -875,6 +872,36 @@ static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned offset,
 	return -EINVAL;
 }
 
+static int intel_gpio_irq_reqres(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct intel_pinctrl *pctrl = gpiochip_get_data(gc);
+	int pin;
+	int ret;
+
+	pin = intel_gpio_to_pin(pctrl, irqd_to_hwirq(d), NULL, NULL);
+	if (pin >= 0) {
+		ret = gpiochip_lock_as_irq(gc, pin);
+		if (ret) {
+			dev_err(pctrl->dev, "unable to lock HW IRQ %d for IRQ\n",
+				pin);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+static void intel_gpio_irq_relres(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct intel_pinctrl *pctrl = gpiochip_get_data(gc);
+	int pin;
+
+	pin = intel_gpio_to_pin(pctrl, irqd_to_hwirq(d), NULL, NULL);
+	if (pin >= 0)
+		gpiochip_unlock_as_irq(gc, pin);
+}
+
 static void intel_gpio_irq_ack(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -1090,6 +1117,8 @@ static irqreturn_t intel_gpio_irq(int irq, void *data)
 
 static struct irq_chip intel_gpio_irqchip = {
 	.name = "intel-gpio",
+	.irq_request_resources = intel_gpio_irq_reqres,
+	.irq_release_resources = intel_gpio_irq_relres,
 	.irq_enable = intel_gpio_irq_enable,
 	.irq_ack = intel_gpio_irq_ack,
 	.irq_mask = intel_gpio_irq_mask,
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index 98fdf9adf623..1785abf157e4 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Core pinctrl/GPIO driver for Intel GPIO controllers
  *
  * Copyright (C) 2015, Intel Corporation
  * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef PINCTRL_INTEL_H
diff --git a/drivers/pinctrl/intel/pinctrl-lewisburg.c b/drivers/pinctrl/intel/pinctrl-lewisburg.c
index 14d56ea6cfdc..99894647eddd 100644
--- a/drivers/pinctrl/intel/pinctrl-lewisburg.c
+++ b/drivers/pinctrl/intel/pinctrl-lewisburg.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Lewisburg pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c
index d9357054d41d..4a916be44f4f 100644
--- a/drivers/pinctrl/intel/pinctrl-merrifield.c
+++ b/drivers/pinctrl/intel/pinctrl-merrifield.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Merrifield SoC pinctrl driver
  *
  * Copyright (C) 2016, Intel Corporation
  * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index fee3435a6f15..7984392104fe 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Sunrisepoint PCH pinctrl/GPIO driver
  *
  * Copyright (C) 2015, Intel Corporation
  * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/mediatek/mtk-eint.c b/drivers/pinctrl/mediatek/mtk-eint.c
index 30f3316747e2..a613e546717a 100644
--- a/drivers/pinctrl/mediatek/mtk-eint.c
+++ b/drivers/pinctrl/mediatek/mtk-eint.c
@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <linux/gpio.h>
 #include <linux/io.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7622.c b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
index e3f1ab2290fc..6f931b85701b 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt7622.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
@@ -1263,6 +1263,7 @@ static int mtk_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 					       MTK_DISABLE);
 			if (err)
 				goto err;
+			/* else: fall through */
 		case PIN_CONFIG_INPUT_ENABLE:
 		case PIN_CONFIG_SLEW_RATE:
 			reg = (param == PIN_CONFIG_SLEW_RATE) ?
@@ -1424,7 +1425,7 @@ static struct pinctrl_desc mtk_desc = {
 
 static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio)
 {
-	struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent);
+	struct mtk_pinctrl *hw = gpiochip_get_data(chip);
 	int value, err;
 
 	err = mtk_hw_get_value(hw, gpio, PINCTRL_PIN_REG_DI, &value);
@@ -1436,7 +1437,7 @@ static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio)
 
 static void mtk_gpio_set(struct gpio_chip *chip, unsigned int gpio, int value)
 {
-	struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent);
+	struct mtk_pinctrl *hw = gpiochip_get_data(chip);
 
 	mtk_hw_set_value(hw, gpio, PINCTRL_PIN_REG_DO, !!value);
 }
@@ -1508,11 +1509,20 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw, struct device_node *np)
 	if (ret < 0)
 		return ret;
 
-	ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0,
-				     chip->ngpio);
-	if (ret < 0) {
-		gpiochip_remove(chip);
-		return ret;
+	/* Just for backward compatible for these old pinctrl nodes without
+	 * "gpio-ranges" property. Otherwise, called directly from a
+	 * DeviceTree-supported pinctrl driver is DEPRECATED.
+	 * Please see Section 2.1 of
+	 * Documentation/devicetree/bindings/gpio/gpio.txt on how to
+	 * bind pinctrl and gpio drivers via the "gpio-ranges" property.
+	 */
+	if (!of_find_property(np, "gpio-ranges", NULL)) {
+		ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0,
+					     chip->ngpio);
+		if (ret < 0) {
+			gpiochip_remove(chip);
+			return ret;
+		}
 	}
 
 	return 0;
@@ -1528,7 +1538,7 @@ static int mtk_build_groups(struct mtk_pinctrl *hw)
 		err = pinctrl_generic_add_group(hw->pctrl, group->name,
 						group->pins, group->num_pins,
 						group->data);
-		if (err) {
+		if (err < 0) {
 			dev_err(hw->dev, "Failed to register group %s\n",
 				group->name);
 			return err;
@@ -1549,7 +1559,7 @@ static int mtk_build_functions(struct mtk_pinctrl *hw)
 						  func->group_names,
 						  func->num_group_names,
 						  func->data);
-		if (err) {
+		if (err < 0) {
 			dev_err(hw->dev, "Failed to register function %s\n",
 				func->name);
 			return err;
@@ -1695,15 +1705,16 @@ static int mtk_pinctrl_probe(struct platform_device *pdev)
 	mtk_desc.custom_conf_items = mtk_conf_items;
 #endif
 
-	hw->pctrl = devm_pinctrl_register(&pdev->dev, &mtk_desc, hw);
-	if (IS_ERR(hw->pctrl))
-		return PTR_ERR(hw->pctrl);
+	err = devm_pinctrl_register_and_init(&pdev->dev, &mtk_desc, hw,
+					     &hw->pctrl);
+	if (err)
+		return err;
 
 	/* Setup groups descriptions per SoC types */
 	err = mtk_build_groups(hw);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to build groups\n");
-		return 0;
+		return err;
 	}
 
 	/* Setup functions descriptions per SoC types */
@@ -1713,17 +1724,25 @@ static int mtk_pinctrl_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = mtk_build_gpiochip(hw, pdev->dev.of_node);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to add gpio_chip\n");
+	/* For able to make pinctrl_claim_hogs, we must not enable pinctrl
+	 * until all groups and functions are being added one.
+	 */
+	err = pinctrl_enable(hw->pctrl);
+	if (err)
 		return err;
-	}
 
 	err = mtk_build_eint(hw, pdev);
 	if (err)
 		dev_warn(&pdev->dev,
 			 "Failed to add EINT, but pinctrl still can work\n");
 
+	/* Build gpiochip should be after pinctrl_enable is done */
+	err = mtk_build_gpiochip(hw, pdev->dev.of_node);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to add gpio_chip\n");
+		return err;
+	}
+
 	platform_set_drvdata(pdev, hw);
 
 	return 0;
diff --git a/drivers/pinctrl/meson/pinctrl-meson-axg.c b/drivers/pinctrl/meson/pinctrl-meson-axg.c
index 46a0918bd284..ad502eda4afa 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-axg.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-axg.c
@@ -672,6 +672,9 @@ static const unsigned int jtag_ao_tdo_pins[] = {GPIOAO_4};
 static const unsigned int jtag_ao_clk_pins[] = {GPIOAO_5};
 static const unsigned int jtag_ao_tms_pins[] = {GPIOAO_7};
 
+/* gen_clk */
+static const unsigned int gen_clk_ee_pins[] = {GPIOAO_13};
+
 static struct meson_pmx_group meson_axg_aobus_groups[] = {
 	GPIO_GROUP(GPIOAO_0),
 	GPIO_GROUP(GPIOAO_1),
@@ -718,6 +721,7 @@ static struct meson_pmx_group meson_axg_aobus_groups[] = {
 	GROUP(jtag_ao_tdo, 4),
 	GROUP(jtag_ao_clk, 4),
 	GROUP(jtag_ao_tms, 4),
+	GROUP(gen_clk_ee, 4),
 };
 
 static const char * const gpio_periphs_groups[] = {
@@ -947,6 +951,10 @@ static const char * const tdmb_groups[] = {
 	"tdmb_din2", "tdmb_dout2", "tdmb_din3",	"tdmb_dout3",
 };
 
+static const char * const gen_clk_ee_groups[] = {
+	"gen_clk_ee",
+};
+
 static struct meson_pmx_func meson_axg_periphs_functions[] = {
 	FUNCTION(gpio_periphs),
 	FUNCTION(emmc),
@@ -992,6 +1000,7 @@ static struct meson_pmx_func meson_axg_aobus_functions[] = {
 	FUNCTION(pwm_ao_c),
 	FUNCTION(pwm_ao_d),
 	FUNCTION(jtag_ao),
+	FUNCTION(gen_clk_ee),
 };
 
 static struct meson_bank meson_axg_periphs_banks[] = {
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
index 2c97a2e07a5f..4ceb06f8a33c 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
@@ -243,6 +243,8 @@ static const unsigned int i2s_out_ch67_y_pins[]	= { GPIOY_10 };
 
 static const unsigned int spdif_out_y_pins[]	= { GPIOY_12 };
 
+static const unsigned int gen_clk_out_pins[]	= { GPIOY_15 };
+
 static const struct pinctrl_pin_desc meson_gxbb_aobus_pins[] = {
 	MESON_PIN(GPIOAO_0),
 	MESON_PIN(GPIOAO_1),
@@ -453,6 +455,7 @@ static struct meson_pmx_group meson_gxbb_periphs_groups[] = {
 	GROUP(i2s_out_ch45_y,	1,	6),
 	GROUP(i2s_out_ch67_y,	1,	7),
 	GROUP(spdif_out_y,	1,	9),
+	GROUP(gen_clk_out,	6,	15),
 
 	/* Bank Z */
 	GROUP(eth_mdio,		6,	1),
@@ -706,6 +709,10 @@ static const char * const spdif_out_groups[] = {
 	"spdif_out_y",
 };
 
+static const char * const gen_clk_out_groups[] = {
+	"gen_clk_out",
+};
+
 static const char * const gpio_aobus_groups[] = {
 	"GPIOAO_0", "GPIOAO_1", "GPIOAO_2", "GPIOAO_3", "GPIOAO_4",
 	"GPIOAO_5", "GPIOAO_6", "GPIOAO_7", "GPIOAO_8", "GPIOAO_9",
@@ -790,6 +797,7 @@ static struct meson_pmx_func meson_gxbb_periphs_functions[] = {
 	FUNCTION(hdmi_i2c),
 	FUNCTION(i2s_out),
 	FUNCTION(spdif_out),
+	FUNCTION(gen_clk_out),
 };
 
 static struct meson_pmx_func meson_gxbb_aobus_functions[] = {
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
index 53cf800688e9..aa48b3f23c7f 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
@@ -80,6 +80,18 @@ struct armada_37xx_pmx_func {
 	unsigned int		ngroups;
 };
 
+struct armada_37xx_pm_state {
+	u32 out_en_l;
+	u32 out_en_h;
+	u32 out_val_l;
+	u32 out_val_h;
+	u32 irq_en_l;
+	u32 irq_en_h;
+	u32 irq_pol_l;
+	u32 irq_pol_h;
+	u32 selection;
+};
+
 struct armada_37xx_pinctrl {
 	struct regmap			*regmap;
 	void __iomem			*base;
@@ -94,6 +106,7 @@ struct armada_37xx_pinctrl {
 	unsigned int			ngroups;
 	struct armada_37xx_pmx_func	*funcs;
 	unsigned int			nfuncs;
+	struct armada_37xx_pm_state	pm;
 };
 
 #define PIN_GRP(_name, _start, _nr, _mask, _func1, _func2)	\
@@ -996,6 +1009,110 @@ static int armada_37xx_pinctrl_register(struct platform_device *pdev,
 	return 0;
 }
 
+#if defined(CONFIG_PM)
+static int armada_3700_pinctrl_suspend(struct device *dev)
+{
+	struct armada_37xx_pinctrl *info = dev_get_drvdata(dev);
+
+	/* Save GPIO state */
+	regmap_read(info->regmap, OUTPUT_EN, &info->pm.out_en_l);
+	regmap_read(info->regmap, OUTPUT_EN + sizeof(u32), &info->pm.out_en_h);
+	regmap_read(info->regmap, OUTPUT_VAL, &info->pm.out_val_l);
+	regmap_read(info->regmap, OUTPUT_VAL + sizeof(u32),
+		    &info->pm.out_val_h);
+
+	info->pm.irq_en_l = readl(info->base + IRQ_EN);
+	info->pm.irq_en_h = readl(info->base + IRQ_EN + sizeof(u32));
+	info->pm.irq_pol_l = readl(info->base + IRQ_POL);
+	info->pm.irq_pol_h = readl(info->base + IRQ_POL + sizeof(u32));
+
+	/* Save pinctrl state */
+	regmap_read(info->regmap, SELECTION, &info->pm.selection);
+
+	return 0;
+}
+
+static int armada_3700_pinctrl_resume(struct device *dev)
+{
+	struct armada_37xx_pinctrl *info = dev_get_drvdata(dev);
+	struct gpio_chip *gc;
+	struct irq_domain *d;
+	int i;
+
+	/* Restore GPIO state */
+	regmap_write(info->regmap, OUTPUT_EN, info->pm.out_en_l);
+	regmap_write(info->regmap, OUTPUT_EN + sizeof(u32),
+		     info->pm.out_en_h);
+	regmap_write(info->regmap, OUTPUT_VAL, info->pm.out_val_l);
+	regmap_write(info->regmap, OUTPUT_VAL + sizeof(u32),
+		     info->pm.out_val_h);
+
+	/*
+	 * Input levels may change during suspend, which is not monitored at
+	 * that time. GPIOs used for both-edge IRQs may not be synchronized
+	 * anymore with their polarities (rising/falling edge) and must be
+	 * re-configured manually.
+	 */
+	gc = &info->gpio_chip;
+	d = gc->irq.domain;
+	for (i = 0; i < gc->ngpio; i++) {
+		u32 irq_bit = BIT(i % GPIO_PER_REG);
+		u32 mask, *irq_pol, input_reg, virq, type, level;
+
+		if (i < GPIO_PER_REG) {
+			mask = info->pm.irq_en_l;
+			irq_pol = &info->pm.irq_pol_l;
+			input_reg = INPUT_VAL;
+		} else {
+			mask = info->pm.irq_en_h;
+			irq_pol = &info->pm.irq_pol_h;
+			input_reg = INPUT_VAL + sizeof(u32);
+		}
+
+		if (!(mask & irq_bit))
+			continue;
+
+		virq = irq_find_mapping(d, i);
+		type = irq_get_trigger_type(virq);
+
+		/*
+		 * Synchronize level and polarity for both-edge irqs:
+		 *     - a high input level expects a falling edge,
+		 *     - a low input level exepects a rising edge.
+		 */
+		if ((type & IRQ_TYPE_SENSE_MASK) ==
+		    IRQ_TYPE_EDGE_BOTH) {
+			regmap_read(info->regmap, input_reg, &level);
+			if ((*irq_pol ^ level) & irq_bit)
+				*irq_pol ^= irq_bit;
+		}
+	}
+
+	writel(info->pm.irq_en_l, info->base + IRQ_EN);
+	writel(info->pm.irq_en_h, info->base + IRQ_EN + sizeof(u32));
+	writel(info->pm.irq_pol_l, info->base + IRQ_POL);
+	writel(info->pm.irq_pol_h, info->base + IRQ_POL + sizeof(u32));
+
+	/* Restore pinctrl state */
+	regmap_write(info->regmap, SELECTION, info->pm.selection);
+
+	return 0;
+}
+
+/*
+ * Since pinctrl is an infrastructure module, its resume should be issued prior
+ * to other IO drivers.
+ */
+static const struct dev_pm_ops armada_3700_pinctrl_pm_ops = {
+	.suspend_late = armada_3700_pinctrl_suspend,
+	.resume_early = armada_3700_pinctrl_resume,
+};
+
+#define PINCTRL_ARMADA_37XX_DEV_PM_OPS (&armada_3700_pinctrl_pm_ops)
+#else
+#define PINCTRL_ARMADA_37XX_DEV_PM_OPS NULL
+#endif /* CONFIG_PM */
+
 static const struct of_device_id armada_37xx_pinctrl_of_match[] = {
 	{
 		.compatible = "marvell,armada3710-sb-pinctrl",
@@ -1049,6 +1166,7 @@ static struct platform_driver armada_37xx_pinctrl_driver = {
 	.driver = {
 		.name = "armada-37xx-pinctrl",
 		.of_match_table = armada_37xx_pinctrl_of_match,
+		.pm = PINCTRL_ARMADA_37XX_DEV_PM_OPS,
 	},
 };
 
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index aa592ef23a29..e3689cc62a41 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -101,15 +101,16 @@ static int abx500_gpio_get_bit(struct gpio_chip *chip, u8 reg,
 	reg += offset / 8;
 	ret = abx500_get_register_interruptible(pct->dev,
 						AB8500_MISC, reg, &val);
-
-	*bit = !!(val & BIT(pos));
-
-	if (ret < 0)
+	if (ret < 0) {
 		dev_err(pct->dev,
 			"%s read reg =%x, offset=%x failed (%d)\n",
 			__func__, reg, offset, ret);
+		return ret;
+	}
 
-	return ret;
+	*bit = !!(val & BIT(pos));
+
+	return 0;
 }
 
 static int abx500_gpio_set_bits(struct gpio_chip *chip, u8 reg,
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 04ae139671c8..41ccc759b8b8 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -247,16 +247,16 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc)
 			raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 			if (pin_reg & BIT(INTERRUPT_ENABLE_OFF)) {
+				u8 level = (pin_reg >> ACTIVE_LEVEL_OFF) &
+						ACTIVE_LEVEL_MASK;
 				interrupt_enable = "interrupt is enabled|";
 
-				if (!(pin_reg & BIT(ACTIVE_LEVEL_OFF)) &&
-				    !(pin_reg & BIT(ACTIVE_LEVEL_OFF + 1)))
-					active_level = "Active low|";
-				else if (pin_reg & BIT(ACTIVE_LEVEL_OFF) &&
-					 !(pin_reg & BIT(ACTIVE_LEVEL_OFF + 1)))
+				if (level == ACTIVE_LEVEL_HIGH)
 					active_level = "Active high|";
-				else if (!(pin_reg & BIT(ACTIVE_LEVEL_OFF)) &&
-					 pin_reg & BIT(ACTIVE_LEVEL_OFF + 1))
+				else if (level == ACTIVE_LEVEL_LOW)
+					active_level = "Active low|";
+				else if (!(pin_reg & BIT(LEVEL_TRIG_OFF)) &&
+					 level == ACTIVE_LEVEL_BOTH)
 					active_level = "Active on both|";
 				else
 					active_level = "Unknown Active level|";
@@ -552,7 +552,8 @@ static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
 		/* Each status bit covers four pins */
 		for (i = 0; i < 4; i++) {
 			regval = readl(regs + i);
-			if (!(regval & PIN_IRQ_PENDING))
+			if (!(regval & PIN_IRQ_PENDING) ||
+			    !(regval & BIT(INTERRUPT_MASK_OFF)))
 				continue;
 			irq = irq_find_mapping(gc->irq.domain, irqnr + i);
 			generic_handle_irq(irq);
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index 8fa453a59da5..22af7edfdb38 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -54,6 +54,10 @@
 #define ACTIVE_LEVEL_MASK	0x3UL
 #define DRV_STRENGTH_SEL_MASK	0x3UL
 
+#define ACTIVE_LEVEL_HIGH	0x0UL
+#define ACTIVE_LEVEL_LOW	0x1UL
+#define ACTIVE_LEVEL_BOTH	0x2UL
+
 #define DB_TYPE_NO_DEBOUNCE               0x0UL
 #define DB_TYPE_PRESERVE_LOW_GLITCH       0x1UL
 #define DB_TYPE_PRESERVE_HIGH_GLITCH      0x2UL
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 67e4d9ffa6b1..ef7ab208b951 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -14,6 +14,7 @@
  * GNU General Public License for more details.
  */
 
+#include <dt-bindings/pinctrl/at91.h>
 #include <linux/clk.h>
 #include <linux/gpio/driver.h>
 /* FIXME: needed for gpio_to_irq(), get rid of this */
@@ -49,6 +50,8 @@
 #define		ATMEL_PIO_IFSCEN_MASK		BIT(13)
 #define		ATMEL_PIO_OPD_MASK		BIT(14)
 #define		ATMEL_PIO_SCHMITT_MASK		BIT(15)
+#define		ATMEL_PIO_DRVSTR_MASK		GENMASK(17, 16)
+#define		ATMEL_PIO_DRVSTR_OFFSET		16
 #define		ATMEL_PIO_CFGR_EVTSEL_MASK	GENMASK(26, 24)
 #define		ATMEL_PIO_CFGR_EVTSEL_FALLING	(0 << 24)
 #define		ATMEL_PIO_CFGR_EVTSEL_RISING	(1 << 24)
@@ -75,6 +78,9 @@
 #define ATMEL_GET_PIN_FUNC(pinfunc)	((pinfunc >> 16) & 0xf)
 #define ATMEL_GET_PIN_IOSET(pinfunc)	((pinfunc >> 20) & 0xf)
 
+/* Custom pinconf parameters */
+#define ATMEL_PIN_CONFIG_DRIVE_STRENGTH	(PIN_CONFIG_END + 1)
+
 struct atmel_pioctrl_data {
 	unsigned nbanks;
 };
@@ -139,6 +145,10 @@ static const char * const atmel_functions[] = {
 	"GPIO", "A", "B", "C", "D", "E", "F", "G"
 };
 
+static const struct pinconf_generic_params atmel_custom_bindings[] = {
+	{"atmel,drive-strength", ATMEL_PIN_CONFIG_DRIVE_STRENGTH, 0},
+};
+
 /* --- GPIO --- */
 static unsigned int atmel_gpio_read(struct atmel_pioctrl *atmel_pioctrl,
 				    unsigned int bank, unsigned int reg)
@@ -692,6 +702,11 @@ static int atmel_conf_pin_config_group_get(struct pinctrl_dev *pctldev,
 			return -EINVAL;
 		arg = 1;
 		break;
+	case ATMEL_PIN_CONFIG_DRIVE_STRENGTH:
+		if (!(res & ATMEL_PIO_DRVSTR_MASK))
+			return -EINVAL;
+		arg = (res & ATMEL_PIO_DRVSTR_MASK) >> ATMEL_PIO_DRVSTR_OFFSET;
+		break;
 	default:
 		return -ENOTSUPP;
 	}
@@ -777,6 +792,18 @@ static int atmel_conf_pin_config_group_set(struct pinctrl_dev *pctldev,
 					ATMEL_PIO_SODR);
 			}
 			break;
+		case ATMEL_PIN_CONFIG_DRIVE_STRENGTH:
+			switch (arg) {
+			case ATMEL_PIO_DRVSTR_LO:
+			case ATMEL_PIO_DRVSTR_ME:
+			case ATMEL_PIO_DRVSTR_HI:
+				conf &= (~ATMEL_PIO_DRVSTR_MASK);
+				conf |= arg << ATMEL_PIO_DRVSTR_OFFSET;
+				break;
+			default:
+				dev_warn(pctldev->dev, "drive strength not updated (incorrect value)\n");
+			}
+			break;
 		default:
 			dev_warn(pctldev->dev,
 				 "unsupported configuration parameter: %u\n",
@@ -816,6 +843,19 @@ static void atmel_conf_pin_config_dbg_show(struct pinctrl_dev *pctldev,
 		seq_printf(s, "%s ", "open-drain");
 	if (conf & ATMEL_PIO_SCHMITT_MASK)
 		seq_printf(s, "%s ", "schmitt");
+	if (conf & ATMEL_PIO_DRVSTR_MASK) {
+		switch ((conf & ATMEL_PIO_DRVSTR_MASK) >> ATMEL_PIO_DRVSTR_OFFSET) {
+		case ATMEL_PIO_DRVSTR_ME:
+			seq_printf(s, "%s ", "medium-drive");
+			break;
+		case ATMEL_PIO_DRVSTR_HI:
+			seq_printf(s, "%s ", "high-drive");
+			break;
+		/* ATMEL_PIO_DRVSTR_LO and 0 which is the default value at reset */
+		default:
+			seq_printf(s, "%s ", "low-drive");
+		}
+	}
 }
 
 static const struct pinconf_ops atmel_confops = {
@@ -931,10 +971,6 @@ static int atmel_pinctrl_probe(struct platform_device *pdev)
 	atmel_pioctrl->npins = atmel_pioctrl->nbanks * ATMEL_PIO_NPINS_PER_BANK;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "unable to get atmel pinctrl resource\n");
-		return -EINVAL;
-	}
 	atmel_pioctrl->reg_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(atmel_pioctrl->reg_base))
 		return -EINVAL;
@@ -958,6 +994,8 @@ static int atmel_pinctrl_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	atmel_pinctrl_desc.pins = pin_desc;
 	atmel_pinctrl_desc.npins = atmel_pioctrl->npins;
+	atmel_pinctrl_desc.num_custom_params = ARRAY_SIZE(atmel_custom_bindings);
+	atmel_pinctrl_desc.custom_params = atmel_custom_bindings;
 
 	/* One pin is one group since a pin can achieve all functions. */
 	group_names = devm_kcalloc(dev,
diff --git a/drivers/pinctrl/pinctrl-axp209.c b/drivers/pinctrl/pinctrl-axp209.c
index a52779f33ad4..afd0b533c40a 100644
--- a/drivers/pinctrl/pinctrl-axp209.c
+++ b/drivers/pinctrl/pinctrl-axp209.c
@@ -316,7 +316,7 @@ static const struct pinctrl_ops axp20x_pctrl_ops = {
 	.get_group_pins		= axp20x_group_pins,
 };
 
-static void axp20x_funcs_groups_from_mask(struct device *dev, unsigned int mask,
+static int axp20x_funcs_groups_from_mask(struct device *dev, unsigned int mask,
 					  unsigned int mask_len,
 					  struct axp20x_pinctrl_function *func,
 					  const struct pinctrl_pin_desc *pins)
@@ -331,18 +331,22 @@ static void axp20x_funcs_groups_from_mask(struct device *dev, unsigned int mask,
 		func->groups = devm_kcalloc(dev,
 					    ngroups, sizeof(const char *),
 					    GFP_KERNEL);
+		if (!func->groups)
+			return -ENOMEM;
 		group = func->groups;
 		for_each_set_bit(bit, &mask_cpy, mask_len) {
 			*group = pins[bit].name;
 			group++;
 		}
 	}
+
+	return 0;
 }
 
-static void axp20x_build_funcs_groups(struct platform_device *pdev)
+static int axp20x_build_funcs_groups(struct platform_device *pdev)
 {
 	struct axp20x_pctl *pctl = platform_get_drvdata(pdev);
-	int i, pin, npins = pctl->desc->npins;
+	int i, ret, pin, npins = pctl->desc->npins;
 
 	pctl->funcs[AXP20X_FUNC_GPIO_OUT].name = "gpio_out";
 	pctl->funcs[AXP20X_FUNC_GPIO_OUT].muxval = AXP20X_MUX_GPIO_OUT;
@@ -366,13 +370,19 @@ static void axp20x_build_funcs_groups(struct platform_device *pdev)
 			pctl->funcs[i].groups[pin] = pctl->desc->pins[pin].name;
 	}
 
-	axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->ldo_mask,
+	ret = axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->ldo_mask,
 				      npins, &pctl->funcs[AXP20X_FUNC_LDO],
 				      pctl->desc->pins);
+	if (ret)
+		return ret;
 
-	axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->adc_mask,
+	ret = axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->adc_mask,
 				      npins, &pctl->funcs[AXP20X_FUNC_ADC],
 				      pctl->desc->pins);
+	if (ret)
+		return ret;
+
+	return 0;
 }
 
 static const struct of_device_id axp20x_pctl_match[] = {
@@ -424,7 +434,11 @@ static int axp20x_pctl_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pctl);
 
-	axp20x_build_funcs_groups(pdev);
+	ret = axp20x_build_funcs_groups(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to build groups\n");
+		return ret;
+	}
 
 	pctrl_desc = devm_kzalloc(&pdev->dev, sizeof(*pctrl_desc), GFP_KERNEL);
 	if (!pctrl_desc)
diff --git a/drivers/pinctrl/pinctrl-gemini.c b/drivers/pinctrl/pinctrl-gemini.c
index 8c9970ae8505..fa7d998e1d5a 100644
--- a/drivers/pinctrl/pinctrl-gemini.c
+++ b/drivers/pinctrl/pinctrl-gemini.c
@@ -1696,6 +1696,7 @@ static const struct gemini_pin_group gemini_3516_pin_groups[] = {
 		.name = "gmii_gmac0_grp",
 		.pins = gmii_gmac0_3516_pins,
 		.num_pins = ARRAY_SIZE(gmii_gmac0_3516_pins),
+		.mask = GEMINI_GMAC_IOSEL_MASK,
 		.driving_mask = GENMASK(17, 16),
 	},
 	{
@@ -1703,6 +1704,7 @@ static const struct gemini_pin_group gemini_3516_pin_groups[] = {
 		.pins = gmii_gmac1_3516_pins,
 		.num_pins = ARRAY_SIZE(gmii_gmac1_3516_pins),
 		/* Bring out RGMII on the GMAC1 pins */
+		.mask = GEMINI_GMAC_IOSEL_MASK,
 		.value = GEMINI_GMAC_IOSEL_GMAC0_GMAC1_RGMII,
 		.driving_mask = GENMASK(19, 18),
 	},
diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index a1d7156d0a43..6a1b6058b991 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -536,7 +536,7 @@ static int ingenic_pinmux_gpio_set_direction(struct pinctrl_dev *pctldev,
 		ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PAT1, input);
 	} else {
 		ingenic_config_pin(jzpc, pin, JZ4740_GPIO_SELECT, false);
-		ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, input);
+		ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, !input);
 		ingenic_config_pin(jzpc, pin, JZ4740_GPIO_FUNC, false);
 	}
 
diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c
index 022307dd4b54..4a8a8efadefa 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08.c
@@ -666,7 +666,7 @@ static int mcp23s08_irq_setup(struct mcp23s08 *mcp)
  * can be used to fix state for MCP23xxx, that temporary
  * lost its power supply.
  */
-#define MCP23S08_CONFIG_REGS 8
+#define MCP23S08_CONFIG_REGS 7
 static int __check_mcp23s08_reg_cache(struct mcp23s08 *mcp)
 {
 	int cached[MCP23S08_CONFIG_REGS];
diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c
index 15bb1cb8729b..f9fc2b3a8731 100644
--- a/drivers/pinctrl/pinctrl-ocelot.c
+++ b/drivers/pinctrl/pinctrl-ocelot.c
@@ -11,6 +11,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/pinctrl/pinmux.h>
@@ -132,7 +133,7 @@ OCELOT_P(0,  SG0,       NONE,      NONE);
 OCELOT_P(1,  SG0,       NONE,      NONE);
 OCELOT_P(2,  SG0,       NONE,      NONE);
 OCELOT_P(3,  SG0,       NONE,      NONE);
-OCELOT_P(4,  IRQ0_IN,   IRQ0_OUT,  TWI);
+OCELOT_P(4,  IRQ0_IN,   IRQ0_OUT,  TWI_SCL_M);
 OCELOT_P(5,  IRQ1_IN,   IRQ1_OUT,  PCI_WAKE);
 OCELOT_P(6,  UART,      TWI_SCL_M, NONE);
 OCELOT_P(7,  UART,      TWI_SCL_M, NONE);
@@ -427,11 +428,98 @@ static const struct gpio_chip ocelot_gpiolib_chip = {
 	.owner = THIS_MODULE,
 };
 
+static void ocelot_irq_mask(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	regmap_update_bits(info->map, OCELOT_GPIO_INTR_ENA, BIT(gpio), 0);
+}
+
+static void ocelot_irq_unmask(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	regmap_update_bits(info->map, OCELOT_GPIO_INTR_ENA, BIT(gpio),
+			   BIT(gpio));
+}
+
+static void ocelot_irq_ack(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	regmap_write_bits(info->map, OCELOT_GPIO_INTR, BIT(gpio), BIT(gpio));
+}
+
+static int ocelot_irq_set_type(struct irq_data *data, unsigned int type);
+
+static struct irq_chip ocelot_eoi_irqchip = {
+	.name		= "gpio",
+	.irq_mask	= ocelot_irq_mask,
+	.irq_eoi	= ocelot_irq_ack,
+	.irq_unmask	= ocelot_irq_unmask,
+	.flags          = IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED,
+	.irq_set_type	= ocelot_irq_set_type,
+};
+
+static struct irq_chip ocelot_irqchip = {
+	.name		= "gpio",
+	.irq_mask	= ocelot_irq_mask,
+	.irq_ack	= ocelot_irq_ack,
+	.irq_unmask	= ocelot_irq_unmask,
+	.irq_set_type	= ocelot_irq_set_type,
+};
+
+static int ocelot_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	type &= IRQ_TYPE_SENSE_MASK;
+
+	if (!(type & (IRQ_TYPE_EDGE_BOTH | IRQ_TYPE_LEVEL_HIGH)))
+		return -EINVAL;
+
+	if (type & IRQ_TYPE_LEVEL_HIGH)
+		irq_set_chip_handler_name_locked(data, &ocelot_eoi_irqchip,
+						 handle_fasteoi_irq, NULL);
+	if (type & IRQ_TYPE_EDGE_BOTH)
+		irq_set_chip_handler_name_locked(data, &ocelot_irqchip,
+						 handle_edge_irq, NULL);
+
+	return 0;
+}
+
+static void ocelot_irq_handler(struct irq_desc *desc)
+{
+	struct irq_chip *parent_chip = irq_desc_get_chip(desc);
+	struct gpio_chip *chip = irq_desc_get_handler_data(desc);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int reg = 0, irq;
+	unsigned long irqs;
+
+	regmap_read(info->map, OCELOT_GPIO_INTR_IDENT, &reg);
+	if (!reg)
+		return;
+
+	chained_irq_enter(parent_chip, desc);
+
+	irqs = reg;
+
+	for_each_set_bit(irq, &irqs, OCELOT_PINS) {
+		generic_handle_irq(irq_linear_revmap(chip->irq.domain, irq));
+	}
+
+	chained_irq_exit(parent_chip, desc);
+}
+
 static int ocelot_gpiochip_register(struct platform_device *pdev,
 				    struct ocelot_pinctrl *info)
 {
 	struct gpio_chip *gc;
-	int ret;
+	int ret, irq;
 
 	info->gpio_chip = ocelot_gpiolib_chip;
 
@@ -446,7 +534,17 @@ static int ocelot_gpiochip_register(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
-	/* TODO: this can be used as an irqchip but no board is using that */
+	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+	if (irq <= 0)
+		return irq;
+
+	ret = gpiochip_irqchip_add(gc, &ocelot_irqchip, 0, handle_edge_irq,
+				   IRQ_TYPE_NONE);
+	if (ret)
+		return ret;
+
+	gpiochip_set_chained_irqchip(gc, &ocelot_irqchip, irq,
+				     ocelot_irq_handler);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/pinctrl-rza1.c b/drivers/pinctrl/pinctrl-rza1.c
index 717c0f4449a0..f76edf664539 100644
--- a/drivers/pinctrl/pinctrl-rza1.c
+++ b/drivers/pinctrl/pinctrl-rza1.c
@@ -1006,6 +1006,7 @@ static int rza1_dt_node_to_map(struct pinctrl_dev *pctldev,
 	const char *grpname;
 	const char **fngrps;
 	int ret, npins;
+	int gsel, fsel;
 
 	npins = rza1_dt_node_pin_count(np);
 	if (npins < 0) {
@@ -1055,18 +1056,19 @@ static int rza1_dt_node_to_map(struct pinctrl_dev *pctldev,
 	fngrps[0] = grpname;
 
 	mutex_lock(&rza1_pctl->mutex);
-	ret = pinctrl_generic_add_group(pctldev, grpname, grpins, npins,
-					NULL);
-	if (ret) {
+	gsel = pinctrl_generic_add_group(pctldev, grpname, grpins, npins,
+					 NULL);
+	if (gsel < 0) {
 		mutex_unlock(&rza1_pctl->mutex);
-		return ret;
+		return gsel;
 	}
 
-	ret = pinmux_generic_add_function(pctldev, grpname, fngrps, 1,
-					  mux_confs);
-	if (ret)
+	fsel = pinmux_generic_add_function(pctldev, grpname, fngrps, 1,
+					   mux_confs);
+	if (fsel < 0) {
+		ret = fsel;
 		goto remove_group;
-	mutex_unlock(&rza1_pctl->mutex);
+	}
 
 	dev_info(rza1_pctl->dev, "Parsed function and group %s with %d pins\n",
 				 grpname, npins);
@@ -1083,15 +1085,15 @@ static int rza1_dt_node_to_map(struct pinctrl_dev *pctldev,
 	(*map)->data.mux.group = np->name;
 	(*map)->data.mux.function = np->name;
 	*num_maps = 1;
+	mutex_unlock(&rza1_pctl->mutex);
 
 	return 0;
 
 remove_function:
-	mutex_lock(&rza1_pctl->mutex);
-	pinmux_generic_remove_last_function(pctldev);
+	pinmux_generic_remove_function(pctldev, fsel);
 
 remove_group:
-	pinctrl_generic_remove_last_group(pctldev);
+	pinctrl_generic_remove_group(pctldev, gsel);
 	mutex_unlock(&rza1_pctl->mutex);
 
 	dev_info(rza1_pctl->dev, "Unable to parse function and group %s\n",
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index e5647dac0818..7ec72ff2419a 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -747,38 +747,44 @@ static int pcs_allocate_pin_table(struct pcs_device *pcs)
 /**
  * pcs_add_function() - adds a new function to the function list
  * @pcs: pcs driver instance
- * @np: device node of the mux entry
+ * @fcn: new function allocated
  * @name: name of the function
  * @vals: array of mux register value pairs used by the function
  * @nvals: number of mux register value pairs
  * @pgnames: array of pingroup names for the function
  * @npgnames: number of pingroup names
+ *
+ * Caller must take care of locking.
  */
-static struct pcs_function *pcs_add_function(struct pcs_device *pcs,
-					struct device_node *np,
-					const char *name,
-					struct pcs_func_vals *vals,
-					unsigned nvals,
-					const char **pgnames,
-					unsigned npgnames)
+static int pcs_add_function(struct pcs_device *pcs,
+			    struct pcs_function **fcn,
+			    const char *name,
+			    struct pcs_func_vals *vals,
+			    unsigned int nvals,
+			    const char **pgnames,
+			    unsigned int npgnames)
 {
 	struct pcs_function *function;
-	int res;
+	int selector;
 
 	function = devm_kzalloc(pcs->dev, sizeof(*function), GFP_KERNEL);
 	if (!function)
-		return NULL;
+		return -ENOMEM;
 
 	function->vals = vals;
 	function->nvals = nvals;
 
-	res = pinmux_generic_add_function(pcs->pctl, name,
-					  pgnames, npgnames,
-					  function);
-	if (res)
-		return NULL;
+	selector = pinmux_generic_add_function(pcs->pctl, name,
+					       pgnames, npgnames,
+					       function);
+	if (selector < 0) {
+		devm_kfree(pcs->dev, function);
+		*fcn = NULL;
+	} else {
+		*fcn = function;
+	}
 
-	return function;
+	return selector;
 }
 
 /**
@@ -979,8 +985,8 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 {
 	const char *name = "pinctrl-single,pins";
 	struct pcs_func_vals *vals;
-	int rows, *pins, found = 0, res = -ENOMEM, i;
-	struct pcs_function *function;
+	int rows, *pins, found = 0, res = -ENOMEM, i, fsel, gsel;
+	struct pcs_function *function = NULL;
 
 	rows = pinctrl_count_index_with_args(np, name);
 	if (rows <= 0) {
@@ -1030,21 +1036,25 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 	}
 
 	pgnames[0] = np->name;
-	function = pcs_add_function(pcs, np, np->name, vals, found, pgnames, 1);
-	if (!function) {
-		res = -ENOMEM;
+	mutex_lock(&pcs->mutex);
+	fsel = pcs_add_function(pcs, &function, np->name, vals, found,
+				pgnames, 1);
+	if (fsel < 0) {
+		res = fsel;
 		goto free_pins;
 	}
 
-	res = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
-	if (res < 0)
+	gsel = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
+	if (gsel < 0) {
+		res = gsel;
 		goto free_function;
+	}
 
 	(*map)->type = PIN_MAP_TYPE_MUX_GROUP;
 	(*map)->data.mux.group = np->name;
 	(*map)->data.mux.function = np->name;
 
-	if (PCS_HAS_PINCONF) {
+	if (PCS_HAS_PINCONF && function) {
 		res = pcs_parse_pinconf(pcs, np, function, map);
 		if (res)
 			goto free_pingroups;
@@ -1052,15 +1062,17 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 	} else {
 		*num_maps = 1;
 	}
+	mutex_unlock(&pcs->mutex);
+
 	return 0;
 
 free_pingroups:
-	pinctrl_generic_remove_last_group(pcs->pctl);
+	pinctrl_generic_remove_group(pcs->pctl, gsel);
 	*num_maps = 1;
 free_function:
-	pinmux_generic_remove_last_function(pcs->pctl);
-
+	pinmux_generic_remove_function(pcs->pctl, fsel);
 free_pins:
+	mutex_unlock(&pcs->mutex);
 	devm_kfree(pcs->dev, pins);
 
 free_vals:
@@ -1077,9 +1089,9 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 {
 	const char *name = "pinctrl-single,bits";
 	struct pcs_func_vals *vals;
-	int rows, *pins, found = 0, res = -ENOMEM, i;
+	int rows, *pins, found = 0, res = -ENOMEM, i, fsel, gsel;
 	int npins_in_row;
-	struct pcs_function *function;
+	struct pcs_function *function = NULL;
 
 	rows = pinctrl_count_index_with_args(np, name);
 	if (rows <= 0) {
@@ -1166,15 +1178,19 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 	}
 
 	pgnames[0] = np->name;
-	function = pcs_add_function(pcs, np, np->name, vals, found, pgnames, 1);
-	if (!function) {
-		res = -ENOMEM;
+	mutex_lock(&pcs->mutex);
+	fsel = pcs_add_function(pcs, &function, np->name, vals, found,
+				pgnames, 1);
+	if (fsel < 0) {
+		res = fsel;
 		goto free_pins;
 	}
 
-	res = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
-	if (res < 0)
+	gsel = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
+	if (gsel < 0) {
+		res = gsel;
 		goto free_function;
+	}
 
 	(*map)->type = PIN_MAP_TYPE_MUX_GROUP;
 	(*map)->data.mux.group = np->name;
@@ -1186,14 +1202,17 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 	}
 
 	*num_maps = 1;
+	mutex_unlock(&pcs->mutex);
+
 	return 0;
 
 free_pingroups:
-	pinctrl_generic_remove_last_group(pcs->pctl);
+	pinctrl_generic_remove_group(pcs->pctl, gsel);
 	*num_maps = 1;
 free_function:
-	pinmux_generic_remove_last_function(pcs->pctl);
+	pinmux_generic_remove_function(pcs->pctl, fsel);
 free_pins:
+	mutex_unlock(&pcs->mutex);
 	devm_kfree(pcs->dev, pins);
 
 free_vals:
@@ -1598,19 +1617,19 @@ static int pcs_save_context(struct pcs_device *pcs)
 
 	switch (pcs->width) {
 	case 64:
-		regsl = (u64 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			regsl[i] = pcs->read(pcs->base + i * mux_bytes);
+		regsl = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			*regsl++ = pcs->read(pcs->base + i);
 		break;
 	case 32:
-		regsw = (u32 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			regsw[i] = pcs->read(pcs->base + i * mux_bytes);
+		regsw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			*regsw++ = pcs->read(pcs->base + i);
 		break;
 	case 16:
-		regshw = (u16 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			regshw[i] = pcs->read(pcs->base + i * mux_bytes);
+		regshw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			*regshw++ = pcs->read(pcs->base + i);
 		break;
 	}
 
@@ -1628,19 +1647,19 @@ static void pcs_restore_context(struct pcs_device *pcs)
 
 	switch (pcs->width) {
 	case 64:
-		regsl = (u64 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			pcs->write(regsl[i], pcs->base + i * mux_bytes);
+		regsl = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			pcs->write(*regsl++, pcs->base + i);
 		break;
 	case 32:
-		regsw = (u32 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			pcs->write(regsw[i], pcs->base + i * mux_bytes);
+		regsw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			pcs->write(*regsw++, pcs->base + i);
 		break;
 	case 16:
-		regshw = (u16 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			pcs->write(regshw[i], pcs->base + i * mux_bytes);
+		regshw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			pcs->write(*regshw++, pcs->base + i);
 		break;
 	}
 }
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index b8e9bda8ec98..5780442c068b 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -22,7 +22,6 @@
 #include <linux/err.h>
 #include <linux/list.h>
 #include <linux/string.h>
-#include <linux/sysfs.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/pinctrl/machine.h>
@@ -308,7 +307,6 @@ static int pinmux_func_name_to_selector(struct pinctrl_dev *pctldev,
 		selector++;
 	}
 
-	dev_err(pctldev->dev, "function '%s' not supported\n", function);
 	return -EINVAL;
 }
 
@@ -775,6 +773,16 @@ int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 				void *data)
 {
 	struct function_desc *function;
+	int selector;
+
+	if (!name)
+		return -EINVAL;
+
+	selector = pinmux_func_name_to_selector(pctldev, name);
+	if (selector >= 0)
+		return selector;
+
+	selector = pctldev->num_functions;
 
 	function = devm_kzalloc(pctldev->dev, sizeof(*function), GFP_KERNEL);
 	if (!function)
@@ -785,12 +793,11 @@ int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 	function->num_group_names = num_groups;
 	function->data = data;
 
-	radix_tree_insert(&pctldev->pin_function_tree, pctldev->num_functions,
-			  function);
+	radix_tree_insert(&pctldev->pin_function_tree, selector, function);
 
 	pctldev->num_functions++;
 
-	return 0;
+	return selector;
 }
 EXPORT_SYMBOL_GPL(pinmux_generic_add_function);
 
diff --git a/drivers/pinctrl/pinmux.h b/drivers/pinctrl/pinmux.h
index a331fcdbedd9..3319535c76cb 100644
--- a/drivers/pinctrl/pinmux.h
+++ b/drivers/pinctrl/pinmux.h
@@ -150,13 +150,6 @@ int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 int pinmux_generic_remove_function(struct pinctrl_dev *pctldev,
 				   unsigned int selector);
 
-static inline int
-pinmux_generic_remove_last_function(struct pinctrl_dev *pctldev)
-{
-	return pinmux_generic_remove_function(pctldev,
-					      pctldev->num_functions - 1);
-}
-
 void pinmux_generic_free_functions(struct pinctrl_dev *pctldev);
 
 #else
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 0e22f52b2a19..2155a30c282b 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -250,22 +250,30 @@ static int msm_config_group_get(struct pinctrl_dev *pctldev,
 	/* Convert register value to pinconf value */
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
-		arg = arg == MSM_NO_PULL;
+		if (arg != MSM_NO_PULL)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_DOWN:
-		arg = arg == MSM_PULL_DOWN;
+		if (arg != MSM_PULL_DOWN)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_BUS_HOLD:
 		if (pctrl->soc->pull_no_keeper)
 			return -ENOTSUPP;
 
-		arg = arg == MSM_KEEPER;
+		if (arg != MSM_KEEPER)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_UP:
 		if (pctrl->soc->pull_no_keeper)
 			arg = arg == MSM_PULL_UP_NO_KEEPER;
 		else
 			arg = arg == MSM_PULL_UP;
+		if (!arg)
+			return -EINVAL;
 		break;
 	case PIN_CONFIG_DRIVE_STRENGTH:
 		arg = msm_regval_to_drive(arg);
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index 3e66e0d10010..cf82db78e69e 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -390,31 +390,47 @@ static int pmic_gpio_config_get(struct pinctrl_dev *pctldev,
 
 	switch (param) {
 	case PIN_CONFIG_DRIVE_PUSH_PULL:
-		arg = pad->buffer_type == PMIC_GPIO_OUT_BUF_CMOS;
+		if (pad->buffer_type != PMIC_GPIO_OUT_BUF_CMOS)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
-		arg = pad->buffer_type == PMIC_GPIO_OUT_BUF_OPEN_DRAIN_NMOS;
+		if (pad->buffer_type != PMIC_GPIO_OUT_BUF_OPEN_DRAIN_NMOS)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_DRIVE_OPEN_SOURCE:
-		arg = pad->buffer_type == PMIC_GPIO_OUT_BUF_OPEN_DRAIN_PMOS;
+		if (pad->buffer_type != PMIC_GPIO_OUT_BUF_OPEN_DRAIN_PMOS)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_DOWN:
-		arg = pad->pullup == PMIC_GPIO_PULL_DOWN;
+		if (pad->pullup != PMIC_GPIO_PULL_DOWN)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_DISABLE:
-		arg = pad->pullup = PMIC_GPIO_PULL_DISABLE;
+		if (pad->pullup != PMIC_GPIO_PULL_DISABLE)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_UP:
-		arg = pad->pullup == PMIC_GPIO_PULL_UP_30;
+		if (pad->pullup != PMIC_GPIO_PULL_UP_30)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_HIGH_IMPEDANCE:
-		arg = !pad->is_enabled;
+		if (pad->is_enabled)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_POWER_SOURCE:
 		arg = pad->power_source;
 		break;
 	case PIN_CONFIG_INPUT_ENABLE:
-		arg = pad->input_enabled;
+		if (!pad->input_enabled)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_OUTPUT:
 		arg = pad->out_value;
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c
index d82820fc349a..44c6b753f692 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c
@@ -616,16 +616,22 @@ static const struct samsung_pin_ctrl exynos5260_pin_ctrl[] __initconst = {
 		.nr_banks	= ARRAY_SIZE(exynos5260_pin_banks0),
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 	}, {
 		/* pin-controller instance 1 data */
 		.pin_banks	= exynos5260_pin_banks1,
 		.nr_banks	= ARRAY_SIZE(exynos5260_pin_banks1),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 	}, {
 		/* pin-controller instance 2 data */
 		.pin_banks	= exynos5260_pin_banks2,
 		.nr_banks	= ARRAY_SIZE(exynos5260_pin_banks2),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 	},
 };
 
@@ -842,30 +848,40 @@ static const struct samsung_pin_ctrl exynos5420_pin_ctrl[] __initconst = {
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks0),
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 1 data */
 		.pin_banks	= exynos5420_pin_banks1,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks1),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 2 data */
 		.pin_banks	= exynos5420_pin_banks2,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks2),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 3 data */
 		.pin_banks	= exynos5420_pin_banks3,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks3),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 4 data */
 		.pin_banks	= exynos5420_pin_banks4,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks4),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos4_audio_retention_data,
 	},
 };
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index a263ddd94945..f49ea3d92aa1 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -25,6 +25,7 @@
 #include <linux/regmap.h>
 #include <linux/err.h>
 #include <linux/soc/samsung/exynos-pmu.h>
+#include <linux/soc/samsung/exynos-regs-pmu.h>
 
 #include <dt-bindings/pinctrl/samsung.h>
 
@@ -37,6 +38,8 @@ struct exynos_irq_chip {
 	u32 eint_con;
 	u32 eint_mask;
 	u32 eint_pend;
+	u32 eint_wake_mask_value;
+	u32 eint_wake_mask_reg;
 };
 
 static inline struct exynos_irq_chip *to_exynos_irq_chip(struct irq_chip *chip)
@@ -215,6 +218,7 @@ static struct exynos_irq_chip exynos_gpio_irq_chip = {
 	.eint_con = EXYNOS_GPIO_ECON_OFFSET,
 	.eint_mask = EXYNOS_GPIO_EMASK_OFFSET,
 	.eint_pend = EXYNOS_GPIO_EPEND_OFFSET,
+	/* eint_wake_mask_value not used */
 };
 
 static int exynos_eint_irq_map(struct irq_domain *h, unsigned int virq,
@@ -330,6 +334,8 @@ u32 exynos_get_eint_wake_mask(void)
 
 static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 {
+	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
+	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
 	unsigned long bit = 1UL << (2 * bank->eint_offset + irqd->hwirq);
 
@@ -339,6 +345,7 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 		exynos_eint_wake_mask |= bit;
 	else
 		exynos_eint_wake_mask &= ~bit;
+	our_chip->eint_wake_mask_value = exynos_eint_wake_mask;
 
 	return 0;
 }
@@ -346,6 +353,25 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 /*
  * irq_chip for wakeup interrupts
  */
+static const struct exynos_irq_chip s5pv210_wkup_irq_chip __initconst = {
+	.chip = {
+		.name = "s5pv210_wkup_irq_chip",
+		.irq_unmask = exynos_irq_unmask,
+		.irq_mask = exynos_irq_mask,
+		.irq_ack = exynos_irq_ack,
+		.irq_set_type = exynos_irq_set_type,
+		.irq_set_wake = exynos_wkup_irq_set_wake,
+		.irq_request_resources = exynos_irq_request_resources,
+		.irq_release_resources = exynos_irq_release_resources,
+	},
+	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
+	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
+	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
+	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+	/* Only difference with exynos4210_wkup_irq_chip: */
+	.eint_wake_mask_reg = S5PV210_EINT_WAKEUP_MASK,
+};
+
 static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
 	.chip = {
 		.name = "exynos4210_wkup_irq_chip",
@@ -360,6 +386,8 @@ static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
+	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+	.eint_wake_mask_reg = EXYNOS_EINT_WAKEUP_MASK,
 };
 
 static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
@@ -376,10 +404,14 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS7_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS7_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS7_WKUP_EPEND_OFFSET,
+	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+	.eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK,
 };
 
 /* list of external wakeup controllers supported */
 static const struct of_device_id exynos_wkup_irq_ids[] = {
+	{ .compatible = "samsung,s5pv210-wakeup-eint",
+			.data = &s5pv210_wkup_irq_chip },
 	{ .compatible = "samsung,exynos4210-wakeup-eint",
 			.data = &exynos4210_wkup_irq_chip },
 	{ .compatible = "samsung,exynos7-wakeup-eint",
@@ -542,6 +574,27 @@ int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d)
 	return 0;
 }
 
+static void
+exynos_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
+				    struct exynos_irq_chip *irq_chip)
+{
+	struct regmap *pmu_regs;
+
+	if (!drvdata->retention_ctrl || !drvdata->retention_ctrl->priv) {
+		dev_warn(drvdata->dev,
+			 "No retention data configured bank with external wakeup interrupt. Wake-up mask will not be set.\n");
+		return;
+	}
+
+	pmu_regs = drvdata->retention_ctrl->priv;
+	dev_info(drvdata->dev,
+		 "Setting external wakeup interrupt mask: 0x%x\n",
+		 irq_chip->eint_wake_mask_value);
+
+	regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg,
+		     irq_chip->eint_wake_mask_value);
+}
+
 static void exynos_pinctrl_suspend_bank(
 				struct samsung_pinctrl_drv_data *drvdata,
 				struct samsung_pin_bank *bank)
@@ -564,11 +617,24 @@ static void exynos_pinctrl_suspend_bank(
 void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
 {
 	struct samsung_pin_bank *bank = drvdata->pin_banks;
+	struct exynos_irq_chip *irq_chip = NULL;
 	int i;
 
-	for (i = 0; i < drvdata->nr_banks; ++i, ++bank)
+	for (i = 0; i < drvdata->nr_banks; ++i, ++bank) {
 		if (bank->eint_type == EINT_TYPE_GPIO)
 			exynos_pinctrl_suspend_bank(drvdata, bank);
+		else if (bank->eint_type == EINT_TYPE_WKUP) {
+			if (!irq_chip) {
+				irq_chip = bank->irq_chip;
+				exynos_pinctrl_set_eint_wakeup_mask(drvdata,
+								    irq_chip);
+			} else if (bank->irq_chip != irq_chip) {
+				dev_warn(drvdata->dev,
+					 "More than one external wakeup interrupt chip configured (bank: %s). This is not supported by hardware nor by driver.\n",
+					 bank->name);
+			}
+		}
+	}
 }
 
 static void exynos_pinctrl_resume_bank(
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index f0cda9424dfe..e571bbd7139b 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -223,6 +223,13 @@ struct samsung_retention_data {
  *	interrupts for the controller.
  * @eint_wkup_init: platform specific callback to setup the external wakeup
  *	interrupts for the controller.
+ * @suspend: platform specific suspend callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_suspend()
+ * @resume: platform specific resume callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_resume()
+ *
+ * External wakeup interrupts must define at least eint_wkup_init,
+ * retention_data and suspend in order for proper suspend/resume to work.
  */
 struct samsung_pin_ctrl {
 	const struct samsung_pin_bank_data *pin_banks;
@@ -255,6 +262,10 @@ struct samsung_pin_ctrl {
  * @pin_base: starting system wide pin number.
  * @nr_pins: number of pins supported by the controller.
  * @retention_ctrl: retention control runtime data.
+ * @suspend: platform specific suspend callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_suspend()
+ * @resume: platform specific resume callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_resume()
  */
 struct samsung_pinctrl_drv_data {
 	struct list_head		node;
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77965.c b/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
index d2bbee656381..cfd7de67e3e3 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
@@ -1758,6 +1758,263 @@ static const unsigned int du_disp_mux[] = {
 	DU_DISP_MARK,
 };
 
+/* - HSCIF0 ----------------------------------------------------------------- */
+static const unsigned int hscif0_data_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 13), RCAR_GP_PIN(5, 14),
+};
+
+static const unsigned int hscif0_data_mux[] = {
+	HRX0_MARK, HTX0_MARK,
+};
+
+static const unsigned int hscif0_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 12),
+};
+
+static const unsigned int hscif0_clk_mux[] = {
+	HSCK0_MARK,
+};
+
+static const unsigned int hscif0_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 16), RCAR_GP_PIN(5, 15),
+};
+
+static const unsigned int hscif0_ctrl_mux[] = {
+	HRTS0_N_MARK, HCTS0_N_MARK,
+};
+
+/* - HSCIF1 ----------------------------------------------------------------- */
+static const unsigned int hscif1_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 6),
+};
+
+static const unsigned int hscif1_data_a_mux[] = {
+	HRX1_A_MARK, HTX1_A_MARK,
+};
+
+static const unsigned int hscif1_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+
+static const unsigned int hscif1_clk_a_mux[] = {
+	HSCK1_A_MARK,
+};
+
+static const unsigned int hscif1_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 7),
+};
+
+static const unsigned int hscif1_ctrl_a_mux[] = {
+	HRTS1_N_A_MARK, HCTS1_N_A_MARK,
+};
+
+static const unsigned int hscif1_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
+};
+
+static const unsigned int hscif1_data_b_mux[] = {
+	HRX1_B_MARK, HTX1_B_MARK,
+};
+
+static const unsigned int hscif1_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 0),
+};
+
+static const unsigned int hscif1_clk_b_mux[] = {
+	HSCK1_B_MARK,
+};
+
+static const unsigned int hscif1_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 3),
+};
+
+static const unsigned int hscif1_ctrl_b_mux[] = {
+	HRTS1_N_B_MARK, HCTS1_N_B_MARK,
+};
+
+/* - HSCIF2 ----------------------------------------------------------------- */
+static const unsigned int hscif2_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
+};
+
+static const unsigned int hscif2_data_a_mux[] = {
+	HRX2_A_MARK, HTX2_A_MARK,
+};
+
+static const unsigned int hscif2_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 10),
+};
+
+static const unsigned int hscif2_clk_a_mux[] = {
+	HSCK2_A_MARK,
+};
+
+static const unsigned int hscif2_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 7), RCAR_GP_PIN(6, 6),
+};
+
+static const unsigned int hscif2_ctrl_a_mux[] = {
+	HRTS2_N_A_MARK, HCTS2_N_A_MARK,
+};
+
+static const unsigned int hscif2_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
+};
+
+static const unsigned int hscif2_data_b_mux[] = {
+	HRX2_B_MARK, HTX2_B_MARK,
+};
+
+static const unsigned int hscif2_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+
+static const unsigned int hscif2_clk_b_mux[] = {
+	HSCK2_B_MARK,
+};
+
+static const unsigned int hscif2_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 20), RCAR_GP_PIN(6, 19),
+};
+
+static const unsigned int hscif2_ctrl_b_mux[] = {
+	HRTS2_N_B_MARK, HCTS2_N_B_MARK,
+};
+
+static const unsigned int hscif2_data_c_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 25), RCAR_GP_PIN(6, 26),
+};
+
+static const unsigned int hscif2_data_c_mux[] = {
+	HRX2_C_MARK, HTX2_C_MARK,
+};
+
+static const unsigned int hscif2_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 24),
+};
+
+static const unsigned int hscif2_clk_c_mux[] = {
+	HSCK2_C_MARK,
+};
+
+static const unsigned int hscif2_ctrl_c_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 28), RCAR_GP_PIN(6, 27),
+};
+
+static const unsigned int hscif2_ctrl_c_mux[] = {
+	HRTS2_N_C_MARK, HCTS2_N_C_MARK,
+};
+
+/* - HSCIF3 ----------------------------------------------------------------- */
+static const unsigned int hscif3_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24),
+};
+
+static const unsigned int hscif3_data_a_mux[] = {
+	HRX3_A_MARK, HTX3_A_MARK,
+};
+
+static const unsigned int hscif3_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 22),
+};
+
+static const unsigned int hscif3_clk_mux[] = {
+	HSCK3_MARK,
+};
+
+static const unsigned int hscif3_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25),
+};
+
+static const unsigned int hscif3_ctrl_mux[] = {
+	HRTS3_N_MARK, HCTS3_N_MARK,
+};
+
+static const unsigned int hscif3_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 10), RCAR_GP_PIN(0, 11),
+};
+
+static const unsigned int hscif3_data_b_mux[] = {
+	HRX3_B_MARK, HTX3_B_MARK,
+};
+
+static const unsigned int hscif3_data_c_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 15),
+};
+
+static const unsigned int hscif3_data_c_mux[] = {
+	HRX3_C_MARK, HTX3_C_MARK,
+};
+
+static const unsigned int hscif3_data_d_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(2, 7), RCAR_GP_PIN(2, 8),
+};
+
+static const unsigned int hscif3_data_d_mux[] = {
+	HRX3_D_MARK, HTX3_D_MARK,
+};
+
+/* - HSCIF4 ----------------------------------------------------------------- */
+static const unsigned int hscif4_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 13),
+};
+
+static const unsigned int hscif4_data_a_mux[] = {
+	HRX4_A_MARK, HTX4_A_MARK,
+};
+
+static const unsigned int hscif4_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 11),
+};
+
+static const unsigned int hscif4_clk_mux[] = {
+	HSCK4_MARK,
+};
+
+static const unsigned int hscif4_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14),
+};
+
+static const unsigned int hscif4_ctrl_mux[] = {
+	HRTS4_N_MARK, HCTS4_N_MARK,
+};
+
+static const unsigned int hscif4_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11),
+};
+
+static const unsigned int hscif4_data_b_mux[] = {
+	HRX4_B_MARK, HTX4_B_MARK,
+};
+
 /* - I2C -------------------------------------------------------------------- */
 static const unsigned int i2c1_a_pins[] = {
 	/* SDA, SCL */
@@ -3169,6 +3426,34 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(du_oddf),
 	SH_PFC_PIN_GROUP(du_cde),
 	SH_PFC_PIN_GROUP(du_disp),
+	SH_PFC_PIN_GROUP(hscif0_data),
+	SH_PFC_PIN_GROUP(hscif0_clk),
+	SH_PFC_PIN_GROUP(hscif0_ctrl),
+	SH_PFC_PIN_GROUP(hscif1_data_a),
+	SH_PFC_PIN_GROUP(hscif1_clk_a),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif1_data_b),
+	SH_PFC_PIN_GROUP(hscif1_clk_b),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif2_data_a),
+	SH_PFC_PIN_GROUP(hscif2_clk_a),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif2_data_b),
+	SH_PFC_PIN_GROUP(hscif2_clk_b),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif2_data_c),
+	SH_PFC_PIN_GROUP(hscif2_clk_c),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_c),
+	SH_PFC_PIN_GROUP(hscif3_data_a),
+	SH_PFC_PIN_GROUP(hscif3_clk),
+	SH_PFC_PIN_GROUP(hscif3_ctrl),
+	SH_PFC_PIN_GROUP(hscif3_data_b),
+	SH_PFC_PIN_GROUP(hscif3_data_c),
+	SH_PFC_PIN_GROUP(hscif3_data_d),
+	SH_PFC_PIN_GROUP(hscif4_data_a),
+	SH_PFC_PIN_GROUP(hscif4_clk),
+	SH_PFC_PIN_GROUP(hscif4_ctrl),
+	SH_PFC_PIN_GROUP(hscif4_data_b),
 	SH_PFC_PIN_GROUP(i2c1_a),
 	SH_PFC_PIN_GROUP(i2c1_b),
 	SH_PFC_PIN_GROUP(i2c2_a),
@@ -3379,6 +3664,49 @@ static const char * const du_groups[] = {
 	"du_disp",
 };
 
+static const char * const hscif0_groups[] = {
+	"hscif0_data",
+	"hscif0_clk",
+	"hscif0_ctrl",
+};
+
+static const char * const hscif1_groups[] = {
+	"hscif1_data_a",
+	"hscif1_clk_a",
+	"hscif1_ctrl_a",
+	"hscif1_data_b",
+	"hscif1_clk_b",
+	"hscif1_ctrl_b",
+};
+
+static const char * const hscif2_groups[] = {
+	"hscif2_data_a",
+	"hscif2_clk_a",
+	"hscif2_ctrl_a",
+	"hscif2_data_b",
+	"hscif2_clk_b",
+	"hscif2_ctrl_b",
+	"hscif2_data_c",
+	"hscif2_clk_c",
+	"hscif2_ctrl_c",
+};
+
+static const char * const hscif3_groups[] = {
+	"hscif3_data_a",
+	"hscif3_clk",
+	"hscif3_ctrl",
+	"hscif3_data_b",
+	"hscif3_data_c",
+	"hscif3_data_d",
+};
+
+static const char * const hscif4_groups[] = {
+	"hscif4_data_a",
+	"hscif4_clk",
+	"hscif4_ctrl",
+	"hscif4_data_b",
+};
+
 static const char * const i2c1_groups[] = {
 	"i2c1_a",
 	"i2c1_b",
@@ -3651,6 +3979,11 @@ static const char * const usb30_groups[] = {
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(avb),
 	SH_PFC_FUNCTION(du),
+	SH_PFC_FUNCTION(hscif0),
+	SH_PFC_FUNCTION(hscif1),
+	SH_PFC_FUNCTION(hscif2),
+	SH_PFC_FUNCTION(hscif3),
+	SH_PFC_FUNCTION(hscif4),
 	SH_PFC_FUNCTION(i2c1),
 	SH_PFC_FUNCTION(i2c2),
 	SH_PFC_FUNCTION(i2c6),
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c
index b02caf316711..eeb58b3bbc9a 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c
@@ -21,15 +21,13 @@
 #include "core.h"
 #include "sh_pfc.h"
 
-#define CFG_FLAGS SH_PFC_PIN_CFG_DRIVE_STRENGTH
-
 #define CPU_ALL_PORT(fn, sfx)						\
-	PORT_GP_CFG_22(0, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \
-	PORT_GP_CFG_28(1, fn, sfx, CFG_FLAGS),				\
-	PORT_GP_CFG_17(2, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \
-	PORT_GP_CFG_17(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \
-	PORT_GP_CFG_6(4,  fn, sfx, CFG_FLAGS),				\
-	PORT_GP_CFG_15(5, fn, sfx, CFG_FLAGS)
+	PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE),		\
+	PORT_GP_28(1, fn, sfx),						\
+	PORT_GP_CFG_17(2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE),		\
+	PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE),		\
+	PORT_GP_6(4,  fn, sfx),						\
+	PORT_GP_15(5, fn, sfx)
 /*
  * F_() : just information
  * FM() : macro for FN_xxx / xxx_MARK
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
index a68fd658aada..b81c807ac54d 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
@@ -277,7 +277,7 @@
 #define IP11_15_12	FM(TX0_A)		FM(HTX1_A)		FM(SSI_WS2_A)		FM(RIF1_D0)		F_(0, 0)		F_(0, 0)	F_(0, 0)	FM(TS_SDAT1)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP11_19_16	FM(CTS0_N_A)		FM(NFDATA14_A)		FM(AUDIO_CLKOUT_A)	FM(RIF1_D1)		FM(SCIF_CLK_A)		FM(FMCLK_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP11_23_20	FM(RTS0_N_TANS_A)	FM(NFDATA15_A)		FM(AUDIO_CLKOUT1_A)	FM(RIF1_CLK)		FM(SCL2_A)		FM(FMIN_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_27_24	FM(SCK0_A)		FM(HSCK1_A)		FM(USB3HS0_ID)		FM(RTS1_N_TANS)		FM(SDA2_A)		FM(FMCLK_C)	F_(0, 0)	F_(0, 0)	FM(USB1_ID)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_27_24	FM(SCK0_A)		FM(HSCK1_A)		FM(USB3HS0_ID)		FM(RTS1_N_TANS)		FM(SDA2_A)		FM(FMCLK_C)	F_(0, 0)	F_(0, 0)	FM(USB0_ID)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP11_31_28	FM(RX1)			FM(HRX2_B)		FM(SSI_SCK9_B)		FM(AUDIO_CLKOUT1_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 
 /* IPSRx */		/* 0 */			/* 1 */			/* 2 */			/* 3 */			/* 4 */			/* 5 */		/* 6 */		/* 7 */		/* 8 */		/* 9 - F */
@@ -1082,7 +1082,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_GPSR(IP11_27_24,		RTS1_N_TANS),
 	PINMUX_IPSR_MSEL(IP11_27_24,		SDA2_A,		SEL_I2C2_0),
 	PINMUX_IPSR_MSEL(IP11_27_24,		FMCLK_C,	SEL_FM_2),
-	PINMUX_IPSR_GPSR(IP11_27_24,		USB1_ID),
+	PINMUX_IPSR_GPSR(IP11_27_24,		USB0_ID),
 
 	PINMUX_IPSR_GPSR(IP11_31_28,		RX1),
 	PINMUX_IPSR_MSEL(IP11_31_28,		HRX2_B,		SEL_HSCIF2_1),
@@ -1784,6 +1784,53 @@ static const unsigned int scif_clk_b_mux[] = {
 	SCIF_CLK_B_MARK,
 };
 
+/* - USB0 ------------------------------------------------------------------- */
+static const unsigned int usb0_a_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 9),
+};
+
+static const unsigned int usb0_a_mux[] = {
+	USB0_PWEN_A_MARK, USB0_OVC_A_MARK,
+};
+
+static const unsigned int usb0_b_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 11), RCAR_GP_PIN(6, 12),
+};
+
+static const unsigned int usb0_b_mux[] = {
+	USB0_PWEN_B_MARK, USB0_OVC_B_MARK,
+};
+
+static const unsigned int usb0_id_pins[] = {
+	/* ID */
+	RCAR_GP_PIN(5, 0)
+};
+
+static const unsigned int usb0_id_mux[] = {
+	USB0_ID_MARK,
+};
+
+/* - USB30 ------------------------------------------------------------------ */
+static const unsigned int usb30_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 9),
+};
+
+static const unsigned int usb30_mux[] = {
+	USB30_PWEN_MARK, USB30_OVC_MARK,
+};
+
+static const unsigned int usb30_id_pins[] = {
+	/* ID */
+	RCAR_GP_PIN(5, 0),
+};
+
+static const unsigned int usb30_id_mux[] = {
+	USB3HS0_ID_MARK,
+};
+
 static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(avb_link),
 	SH_PFC_PIN_GROUP(avb_magic),
@@ -1837,6 +1884,11 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(scif5_data_c),
 	SH_PFC_PIN_GROUP(scif_clk_a),
 	SH_PFC_PIN_GROUP(scif_clk_b),
+	SH_PFC_PIN_GROUP(usb0_a),
+	SH_PFC_PIN_GROUP(usb0_b),
+	SH_PFC_PIN_GROUP(usb0_id),
+	SH_PFC_PIN_GROUP(usb30),
+	SH_PFC_PIN_GROUP(usb30_id),
 };
 
 static const char * const avb_groups[] = {
@@ -1933,6 +1985,17 @@ static const char * const scif_clk_groups[] = {
 	"scif_clk_b",
 };
 
+static const char * const usb0_groups[] = {
+	"usb0_a",
+	"usb0_b",
+	"usb0_id",
+};
+
+static const char * const usb30_groups[] = {
+	"usb30",
+	"usb30_id",
+};
+
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(avb),
 	SH_PFC_FUNCTION(i2c1),
@@ -1948,6 +2011,8 @@ static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(scif4),
 	SH_PFC_FUNCTION(scif5),
 	SH_PFC_FUNCTION(scif_clk),
+	SH_PFC_FUNCTION(usb0),
+	SH_PFC_FUNCTION(usb30),
 };
 
 static const struct pinmux_cfg_reg pinmux_config_regs[] = {
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index dfed60982a8a..a9bec6e6fdd1 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -46,6 +46,8 @@
 #define STM32_GPIO_PINS_PER_BANK 16
 #define STM32_GPIO_IRQ_LINE	 16
 
+#define SYSCFG_IRQMUX_MASK GENMASK(3, 0)
+
 #define gpio_range_to_bank(chip) \
 		container_of(chip, struct stm32_gpio_bank, range)
 
@@ -73,6 +75,7 @@ struct stm32_gpio_bank {
 	struct fwnode_handle *fwnode;
 	struct irq_domain *domain;
 	u32 bank_nr;
+	u32 bank_ioport_nr;
 };
 
 struct stm32_pinctrl {
@@ -298,7 +301,7 @@ static int stm32_gpio_domain_activate(struct irq_domain *d,
 	struct stm32_gpio_bank *bank = d->host_data;
 	struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent);
 
-	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_nr);
+	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_ioport_nr);
 	return 0;
 }
 
@@ -638,6 +641,11 @@ static int stm32_pmx_set_mux(struct pinctrl_dev *pctldev,
 	}
 
 	range = pinctrl_find_gpio_range_from_pin(pctldev, g->pin);
+	if (!range) {
+		dev_err(pctl->dev, "No gpio range defined.\n");
+		return -EINVAL;
+	}
+
 	bank = gpiochip_get_data(range->gc);
 	pin = stm32_gpio_pin(g->pin);
 
@@ -806,11 +814,17 @@ static int stm32_pconf_parse_conf(struct pinctrl_dev *pctldev,
 		unsigned int pin, enum pin_config_param param,
 		enum pin_config_param arg)
 {
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
 	struct pinctrl_gpio_range *range;
 	struct stm32_gpio_bank *bank;
 	int offset, ret = 0;
 
 	range = pinctrl_find_gpio_range_from_pin(pctldev, pin);
+	if (!range) {
+		dev_err(pctl->dev, "No gpio range defined.\n");
+		return -EINVAL;
+	}
+
 	bank = gpiochip_get_data(range->gc);
 	offset = stm32_gpio_pin(pin);
 
@@ -892,6 +906,9 @@ static void stm32_pconf_dbg_show(struct pinctrl_dev *pctldev,
 	bool val;
 
 	range = pinctrl_find_gpio_range_from_pin_nolock(pctldev, pin);
+	if (!range)
+		return;
+
 	bank = gpiochip_get_data(range->gc);
 	offset = stm32_gpio_pin(pin);
 
@@ -948,6 +965,7 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 	struct device_node *np)
 {
 	struct stm32_gpio_bank *bank = &pctl->banks[pctl->nbanks];
+	int bank_ioport_nr;
 	struct pinctrl_gpio_range *range = &bank->range;
 	struct of_phandle_args args;
 	struct device *dev = pctl->dev;
@@ -998,12 +1016,17 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 		pinctrl_add_gpio_range(pctl->pctl_dev,
 				       &pctl->banks[bank_nr].range);
 	}
+
+	if (of_property_read_u32(np, "st,bank-ioport", &bank_ioport_nr))
+		bank_ioport_nr = bank_nr;
+
 	bank->gpio_chip.base = bank_nr * STM32_GPIO_PINS_PER_BANK;
 
 	bank->gpio_chip.ngpio = npins;
 	bank->gpio_chip.of_node = np;
 	bank->gpio_chip.parent = dev;
 	bank->bank_nr = bank_nr;
+	bank->bank_ioport_nr = bank_ioport_nr;
 	spin_lock_init(&bank->lock);
 
 	/* create irq hierarchical domain */
@@ -1033,6 +1056,7 @@ static int stm32_pctrl_dt_setup_irq(struct platform_device *pdev,
 	struct device *dev = &pdev->dev;
 	struct regmap *rm;
 	int offset, ret, i;
+	int mask, mask_width;
 
 	parent = of_irq_find_parent(np);
 	if (!parent)
@@ -1052,12 +1076,21 @@ static int stm32_pctrl_dt_setup_irq(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
+	ret = of_property_read_u32_index(np, "st,syscfg", 2, &mask);
+	if (ret)
+		mask = SYSCFG_IRQMUX_MASK;
+
+	mask_width = fls(mask);
+
 	for (i = 0; i < STM32_GPIO_PINS_PER_BANK; i++) {
 		struct reg_field mux;
 
 		mux.reg = offset + (i / 4) * 4;
-		mux.lsb = (i % 4) * 4;
-		mux.msb = mux.lsb + 3;
+		mux.lsb = (i % 4) * mask_width;
+		mux.msb = mux.lsb + mask_width - 1;
+
+		dev_dbg(dev, "irqmux%d: reg:%#x, lsb:%d, msb:%d\n",
+			i, mux.reg, mux.lsb, mux.msb);
 
 		pctl->irqmux[i] = devm_regmap_field_alloc(dev, rm, mux);
 		if (IS_ERR(pctl->irqmux[i]))
@@ -1166,7 +1199,7 @@ int stm32_pctl_probe(struct platform_device *pdev)
 		return PTR_ERR(pctl->pctl_dev);
 	}
 
-	for_each_child_of_node(np, child)
+	for_each_available_child_of_node(np, child)
 		if (of_property_read_bool(child, "gpio-controller"))
 			banks++;
 
@@ -1179,7 +1212,7 @@ int stm32_pctl_probe(struct platform_device *pdev)
 	if (!pctl->banks)
 		return -ENOMEM;
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		if (of_property_read_bool(child, "gpio-controller")) {
 			ret = stm32_gpiolib_register_bank(pctl, child);
 			if (ret)
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index f974eee29a19..1aba75897d14 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -629,12 +629,12 @@ static void tegra_pinctrl_clear_parked_bits(struct tegra_pmx *pmx)
 	}
 }
 
-static bool gpio_node_has_range(void)
+static bool gpio_node_has_range(const char *compatible)
 {
 	struct device_node *np;
 	bool has_prop = false;
 
-	np = of_find_compatible_node(NULL, NULL, "nvidia,tegra30-gpio");
+	np = of_find_compatible_node(NULL, NULL, compatible);
 	if (!np)
 		return has_prop;
 
@@ -728,7 +728,7 @@ int tegra_pinctrl_probe(struct platform_device *pdev,
 
 	tegra_pinctrl_clear_parked_bits(pmx);
 
-	if (!gpio_node_has_range())
+	if (!gpio_node_has_range(pmx->soc->gpio_compatible))
 		pinctrl_add_gpio_range(pmx->pctl, &tegra_pinctrl_gpio_range);
 
 	platform_set_drvdata(pdev, pmx);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.h b/drivers/pinctrl/tegra/pinctrl-tegra.h
index aa33c20766c4..44c71941b5f8 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.h
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.h
@@ -189,6 +189,7 @@ struct tegra_pingroup {
  */
 struct tegra_pinctrl_soc_data {
 	unsigned ngpios;
+	const char *gpio_compatible;
 	const struct pinctrl_pin_desc *pins;
 	unsigned npins;
 	struct tegra_function *functions;
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra114.c b/drivers/pinctrl/tegra/pinctrl-tegra114.c
index 56b33fca1bfc..d43c209e9c30 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra114.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra114.c
@@ -1839,6 +1839,7 @@ static const struct tegra_pingroup tegra114_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra114_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra114_pins,
 	.npins = ARRAY_SIZE(tegra114_pins),
 	.functions = tegra114_functions,
@@ -1867,4 +1868,9 @@ static struct platform_driver tegra114_pinctrl_driver = {
 	},
 	.probe = tegra114_pinctrl_probe,
 };
-builtin_platform_driver(tegra114_pinctrl_driver);
+
+static int __init tegra114_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra114_pinctrl_driver);
+}
+arch_initcall(tegra114_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra124.c b/drivers/pinctrl/tegra/pinctrl-tegra124.c
index 7bc998ace0d5..5b07a5834d15 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra124.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra124.c
@@ -2051,6 +2051,7 @@ static const struct tegra_pingroup tegra124_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra124_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra124_pins,
 	.npins = ARRAY_SIZE(tegra124_pins),
 	.functions = tegra124_functions,
@@ -2079,4 +2080,9 @@ static struct platform_driver tegra124_pinctrl_driver = {
 	},
 	.probe = tegra124_pinctrl_probe,
 };
-builtin_platform_driver(tegra124_pinctrl_driver);
+
+static int __init tegra124_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra124_pinctrl_driver);
+}
+arch_initcall(tegra124_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra20.c b/drivers/pinctrl/tegra/pinctrl-tegra20.c
index b6dd939d32cc..1fc82a9576e0 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra20.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra20.c
@@ -2221,6 +2221,7 @@ static const struct tegra_pingroup tegra20_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra20_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra20-gpio",
 	.pins = tegra20_pins,
 	.npins = ARRAY_SIZE(tegra20_pins),
 	.functions = tegra20_functions,
@@ -2276,4 +2277,9 @@ static struct platform_driver tegra20_pinctrl_driver = {
 	},
 	.probe = tegra20_pinctrl_probe,
 };
-builtin_platform_driver(tegra20_pinctrl_driver);
+
+static int __init tegra20_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra20_pinctrl_driver);
+}
+arch_initcall(tegra20_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra210.c b/drivers/pinctrl/tegra/pinctrl-tegra210.c
index c244e5b17bd6..3e77f5474dd8 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra210.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra210.c
@@ -1553,6 +1553,7 @@ static const struct tegra_pingroup tegra210_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra210_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra210_pins,
 	.npins = ARRAY_SIZE(tegra210_pins),
 	.functions = tegra210_functions,
@@ -1581,4 +1582,9 @@ static struct platform_driver tegra210_pinctrl_driver = {
 	},
 	.probe = tegra210_pinctrl_probe,
 };
-builtin_platform_driver(tegra210_pinctrl_driver);
+
+static int __init tegra210_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra210_pinctrl_driver);
+}
+arch_initcall(tegra210_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra30.c b/drivers/pinctrl/tegra/pinctrl-tegra30.c
index 1f180a20f2ab..10e617003e9c 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra30.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra30.c
@@ -2474,6 +2474,7 @@ static const struct tegra_pingroup tegra30_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra30_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra30_pins,
 	.npins = ARRAY_SIZE(tegra30_pins),
 	.functions = tegra30_functions,
@@ -2502,4 +2503,9 @@ static struct platform_driver tegra30_pinctrl_driver = {
 	},
 	.probe = tegra30_pinctrl_probe,
 };
-builtin_platform_driver(tegra30_pinctrl_driver);
+
+static int __init tegra30_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra30_pinctrl_driver);
+}
+arch_initcall(tegra30_pinctrl_init);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
index 58825f68b58b..bce533f85420 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
@@ -517,6 +517,10 @@ static const int i2c4_muxvals[] = {1, 1};
 static const unsigned nand_pins[] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
 				     15, 16, 17};
 static const int nand_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {56, 57, 58, 59};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {169, 170, 171, 172};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {1, 2, 6, 7, 8, 9, 10, 11, 12, 13,
 					   14, 15, 16, 17};
 static const int system_bus_muxvals[] = {0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
@@ -596,6 +600,8 @@ static const struct uniphier_pinctrl_group uniphier_ld11_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c3),
 	UNIPHIER_PINCTRL_GROUP(i2c4),
 	UNIPHIER_PINCTRL_GROUP(nand),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -632,6 +638,8 @@ static const char * const i2c1_groups[] = {"i2c1"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const i2c4_groups[] = {"i2c4"};
 static const char * const nand_groups[] = {"nand"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0"};
@@ -657,6 +665,8 @@ static const struct uniphier_pinmux_function uniphier_ld11_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(i2c4),
 	UNIPHIER_PINMUX_FUNCTION(nand),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
index 9f449b35e300..99f06fe8e1cb 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
@@ -606,6 +606,14 @@ static const unsigned nand_pins[] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
 static const int nand_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
 static const unsigned sd_pins[] = {10, 11, 12, 13, 14, 15, 16, 17};
 static const int sd_muxvals[] = {3, 3, 3, 3, 3, 3, 3, 3};  /* No SDVOLC */
+static const unsigned spi0_pins[] = {56, 57, 58, 59};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {169, 170, 171, 172};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
+static const unsigned spi2_pins[] = {86, 87, 88, 89};
+static const int spi2_muxvals[] = {1, 1, 1, 1};
+static const unsigned spi3_pins[] = {74, 75, 76, 77};
+static const int spi3_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {1, 2, 6, 7, 8, 9, 10, 11, 12, 13,
 					   14, 15, 16, 17};
 static const int system_bus_muxvals[] = {0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
@@ -685,6 +693,10 @@ static const struct uniphier_pinctrl_group uniphier_ld20_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c4),
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
+	UNIPHIER_PINCTRL_GROUP(spi2),
+	UNIPHIER_PINCTRL_GROUP(spi3),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -722,6 +734,10 @@ static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const i2c4_groups[] = {"i2c4"};
 static const char * const nand_groups[] = {"nand"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
+static const char * const spi2_groups[] = {"spi2"};
+static const char * const spi3_groups[] = {"spi3"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0"};
@@ -751,6 +767,10 @@ static const struct uniphier_pinmux_function uniphier_ld20_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c4),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
+	UNIPHIER_PINMUX_FUNCTION(spi2),
+	UNIPHIER_PINMUX_FUNCTION(spi3),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
index 0b10ebc07eb8..b247011524bf 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
@@ -576,6 +576,8 @@ static const unsigned nand_cs1_pins[] = {22, 23};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {44, 45, 46, 47, 48, 49, 50, 51, 52};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {135, 136, 137, 138};
+static const int spi0_muxvals[] = {12, 12, 12, 12};
 static const unsigned system_bus_pins[] = {16, 17, 18, 19, 20, 165, 166, 167,
 					   168, 169, 170, 171, 172, 173};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, -1, -1, -1, -1, -1, -1,
@@ -640,6 +642,7 @@ static const struct uniphier_pinctrl_group uniphier_ld4_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs0),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
@@ -667,6 +670,7 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs0",
 						 "system_bus_cs1",
@@ -690,6 +694,7 @@ static const struct uniphier_pinmux_function uniphier_ld4_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
index 8e4d45fea885..cb58797adaee 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
@@ -769,6 +769,10 @@ static const unsigned nand_cs1_pins[] = {37, 38};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {47, 48, 49, 50, 51, 52, 53, 54, 55};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {199, 200, 201, 202};
+static const int spi0_muxvals[] = {8, 8, 8, 8};
+static const unsigned spi1_pins[] = {93, 94, 95, 96};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 					   11, 12, 13};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -851,6 +855,8 @@ static const struct uniphier_pinctrl_group uniphier_ld6b_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs2),
@@ -882,6 +888,8 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1",
 						 "system_bus_cs2",
@@ -907,6 +915,8 @@ static const struct uniphier_pinmux_function uniphier_ld6b_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
index 24788a74c254..89148f81d5e0 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
@@ -1050,6 +1050,10 @@ static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
 static const unsigned sd1_pins[] = {319, 320, 321, 322, 323, 324, 325, 326,
 				    327};
 static const int sd1_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {199, 200, 201, 202};
+static const int spi0_muxvals[] = {11, 11, 11, 11};
+static const unsigned spi1_pins[] = {195, 196, 197, 198, 235, 238, 239};
+static const int spi1_muxvals[] = {11, 11, 11, 11, 11, 11, 11};
 static const unsigned system_bus_pins[] = {25, 26, 27, 28, 29, 30, 31, 32, 33,
 					   34, 35, 36, 37, 38};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -1138,6 +1142,8 @@ static const struct uniphier_pinctrl_group uniphier_pro4_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
 	UNIPHIER_PINCTRL_GROUP(sd1),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs0),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
@@ -1171,6 +1177,8 @@ static const char * const i2c6_groups[] = {"i2c6"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
 static const char * const sd1_groups[] = {"sd1"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs0",
 						 "system_bus_cs1",
@@ -1202,6 +1210,8 @@ static const struct uniphier_pinmux_function uniphier_pro4_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
 	UNIPHIER_PINMUX_FUNCTION(sd1),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
index d5d5e579cb08..d77d6b37aabe 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
@@ -818,6 +818,12 @@ static const unsigned nand_cs1_pins[] = {26, 27};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {250, 251, 252, 253, 254, 255, 256, 257, 258};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {120, 121, 122, 123};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {134, 139, 85, 86};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
+static const unsigned spi2_pins[] = {55, 56, 57, 58, 82, 83, 84};
+static const int spi2_muxvals[] = {0, 0, 0, 0, 1, 1, 1};
 static const unsigned system_bus_pins[] = {4, 5, 6, 7, 8, 9, 10, 11, 12, 13,
 					   14, 15, 16, 17};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -904,6 +910,9 @@ static const struct uniphier_pinctrl_group uniphier_pro5_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c5c),
 	UNIPHIER_PINCTRL_GROUP(i2c6),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
+	UNIPHIER_PINCTRL_GROUP(spi2),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs0),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
@@ -934,6 +943,9 @@ static const char * const i2c5_groups[] = {"i2c5", "i2c5b", "i2c5c"};
 static const char * const i2c6_groups[] = {"i2c6"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
+static const char * const spi2_groups[] = {"spi2"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs0",
 						 "system_bus_cs1",
@@ -961,6 +973,9 @@ static const struct uniphier_pinmux_function uniphier_pro5_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c6),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
+	UNIPHIER_PINMUX_FUNCTION(spi2),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
index 032619ad0e73..90199da87eb9 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
@@ -778,6 +778,10 @@ static const unsigned nand_cs1_pins[] = {37, 38};
 static const int nand_cs1_muxvals[] = {8, 8};
 static const unsigned sd_pins[] = {47, 48, 49, 50, 51, 52, 53, 54, 55};
 static const int sd_muxvals[] = {8, 8, 8, 8, 8, 8, 8, 8, 8};
+static const unsigned spi0_pins[] = {199, 200, 201, 202};
+static const int spi0_muxvals[] = {8, 8, 8, 8};
+static const unsigned spi1_pins[] = {93, 94, 95, 96};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 					   11, 12, 13};
 static const int system_bus_muxvals[] = {8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
@@ -861,6 +865,8 @@ static const struct uniphier_pinctrl_group uniphier_pxs2_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -897,6 +903,8 @@ static const char * const i2c5_groups[] = {"i2c5"};
 static const char * const i2c6_groups[] = {"i2c6"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0", "uart0b", "uart0b_ctsrts"};
@@ -928,6 +936,8 @@ static const struct uniphier_pinmux_function uniphier_pxs2_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c6),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c
index 535bb2e935e4..3b860da47733 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c
@@ -808,6 +808,10 @@ static const unsigned int nand_pins[] = {16, 17, 18, 19, 20, 21, 22, 23, 24, 25,
 static const int nand_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
 static const unsigned int sd_pins[] = {43, 44, 45, 46, 47, 48, 49, 50, 51};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {100, 101, 102, 103};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {112, 113, 114, 115};
+static const int spi1_muxvals[] = {2, 2, 2, 2};
 static const unsigned int system_bus_pins[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 					       11, 12, 13, 14};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -886,6 +890,8 @@ static const struct uniphier_pinctrl_group uniphier_pxs3_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c3),
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -913,6 +919,8 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0", "uart0_ctsrts"};
@@ -936,6 +944,8 @@ static const struct uniphier_pinmux_function uniphier_pxs3_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
index 0f921a653164..f086083368a7 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
@@ -504,6 +504,8 @@ static const unsigned nand_cs1_pins[] = {22, 23};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {32, 33, 34, 35, 36, 37, 38, 39, 40};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {118, 119, 120, 121};
+static const int spi0_muxvals[] = {3, 3, 3, 3};
 static const unsigned system_bus_pins[] = {136, 137, 138, 139, 140, 141, 142,
 					   143, 144, 145, 146, 147, 148, 149};
 static const int system_bus_muxvals[] = {-1, -1, -1, -1, -1, -1, -1, -1, -1,
@@ -570,6 +572,7 @@ static const struct uniphier_pinctrl_group uniphier_sld8_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs2),
@@ -598,6 +601,7 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1",
 						 "system_bus_cs2",
@@ -622,6 +626,7 @@ static const struct uniphier_pinmux_function uniphier_sld8_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c
index 322de58eebaf..f66521c7f846 100644
--- a/drivers/platform/mips/cpu_hwmon.c
+++ b/drivers/platform/mips/cpu_hwmon.c
@@ -30,7 +30,8 @@ int loongson3_cpu_temp(int cpu)
 	case PRID_REV_LOONGSON3B_R2:
 		reg = ((reg >> 8) & 0xff) - 100;
 		break;
-	case PRID_REV_LOONGSON3A_R3:
+	case PRID_REV_LOONGSON3A_R3_0:
+	case PRID_REV_LOONGSON3A_R3_1:
 		reg = (reg & 0xffff)*731/0x4000 - 273;
 		break;
 	}
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index ac4d48830415..107d336453b2 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -1218,6 +1218,17 @@ config INTEL_CHTDC_TI_PWRBTN
 	  To compile this driver as a module, choose M here: the module
 	  will be called intel_chtdc_ti_pwrbtn.
 
+config I2C_MULTI_INSTANTIATE
+	tristate "I2C multi instantiate pseudo device driver"
+	depends on I2C && ACPI
+	help
+	  Some ACPI-based systems list multiple i2c-devices in a single ACPI
+	  firmware-node. This driver will instantiate separate i2c-clients
+	  for each device in the firmware-node.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called i2c-multi-instantiate.
+
 endif # X86_PLATFORM_DEVICES
 
 config PMC_ATOM
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index 2ba6cb795338..50dc8f280914 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -91,3 +91,4 @@ obj-$(CONFIG_PMC_ATOM)		+= pmc_atom.o
 obj-$(CONFIG_MLX_PLATFORM)	+= mlx-platform.o
 obj-$(CONFIG_INTEL_TURBO_MAX_3) += intel_turbo_max_3.o
 obj-$(CONFIG_INTEL_CHTDC_TI_PWRBTN)	+= intel_chtdc_ti_pwrbtn.o
+obj-$(CONFIG_I2C_MULTI_INSTANTIATE)	+= i2c-multi-instantiate.o
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index f1fa8612db40..06978c14c83b 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -2185,7 +2185,7 @@ static int __init dell_init(void)
 		dell_fill_request(&buffer, token->location, 0, 0, 0);
 		ret = dell_send_request(&buffer,
 					CLASS_TOKEN_READ, SELECT_TOKEN_AC);
-		if (ret)
+		if (ret == 0)
 			max_intensity = buffer.output[3];
 	}
 
diff --git a/drivers/platform/x86/i2c-multi-instantiate.c b/drivers/platform/x86/i2c-multi-instantiate.c
new file mode 100644
index 000000000000..5456581b473c
--- /dev/null
+++ b/drivers/platform/x86/i2c-multi-instantiate.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * I2C multi-instantiate driver, pseudo driver to instantiate multiple
+ * i2c-clients from a single fwnode.
+ *
+ * Copyright 2018 Hans de Goede <hdegoede@redhat.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+struct i2c_inst_data {
+	const char *type;
+	int gpio_irq_idx;
+};
+
+struct i2c_multi_inst_data {
+	int num_clients;
+	struct i2c_client *clients[0];
+};
+
+static int i2c_multi_inst_probe(struct platform_device *pdev)
+{
+	struct i2c_multi_inst_data *multi;
+	const struct acpi_device_id *match;
+	const struct i2c_inst_data *inst_data;
+	struct i2c_board_info board_info = {};
+	struct device *dev = &pdev->dev;
+	struct acpi_device *adev;
+	char name[32];
+	int i, ret;
+
+	match = acpi_match_device(dev->driver->acpi_match_table, dev);
+	if (!match) {
+		dev_err(dev, "Error ACPI match data is missing\n");
+		return -ENODEV;
+	}
+	inst_data = (const struct i2c_inst_data *)match->driver_data;
+
+	adev = ACPI_COMPANION(dev);
+
+	/* Count number of clients to instantiate */
+	for (i = 0; inst_data[i].type; i++) {}
+
+	multi = devm_kmalloc(dev,
+			offsetof(struct i2c_multi_inst_data, clients[i]),
+			GFP_KERNEL);
+	if (!multi)
+		return -ENOMEM;
+
+	multi->num_clients = i;
+
+	for (i = 0; i < multi->num_clients; i++) {
+		memset(&board_info, 0, sizeof(board_info));
+		strlcpy(board_info.type, inst_data[i].type, I2C_NAME_SIZE);
+		snprintf(name, sizeof(name), "%s-%s", match->id,
+			 inst_data[i].type);
+		board_info.dev_name = name;
+		board_info.irq = 0;
+		if (inst_data[i].gpio_irq_idx != -1) {
+			ret = acpi_dev_gpio_irq_get(adev,
+						    inst_data[i].gpio_irq_idx);
+			if (ret < 0) {
+				dev_err(dev, "Error requesting irq at index %d: %d\n",
+					inst_data[i].gpio_irq_idx, ret);
+				goto error;
+			}
+			board_info.irq = ret;
+		}
+		multi->clients[i] = i2c_acpi_new_device(dev, i, &board_info);
+		if (!multi->clients[i]) {
+			dev_err(dev, "Error creating i2c-client, idx %d\n", i);
+			ret = -ENODEV;
+			goto error;
+		}
+	}
+
+	platform_set_drvdata(pdev, multi);
+	return 0;
+
+error:
+	while (--i >= 0)
+		i2c_unregister_device(multi->clients[i]);
+
+	return ret;
+}
+
+static int i2c_multi_inst_remove(struct platform_device *pdev)
+{
+	struct i2c_multi_inst_data *multi = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < multi->num_clients; i++)
+		i2c_unregister_device(multi->clients[i]);
+
+	return 0;
+}
+
+static const struct i2c_inst_data bsg1160_data[]  = {
+	{ "bmc150_accel", 0 },
+	{ "bmc150_magn", -1 },
+	{ "bmg160", -1 },
+	{}
+};
+
+/*
+ * Note new device-ids must also be added to i2c_multi_instantiate_ids in
+ * drivers/acpi/scan.c: acpi_device_enumeration_by_parent().
+ */
+static const struct acpi_device_id i2c_multi_inst_acpi_ids[] = {
+	{ "BSG1160", (unsigned long)bsg1160_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, i2c_multi_inst_acpi_ids);
+
+static struct platform_driver i2c_multi_inst_driver = {
+	.driver	= {
+		.name = "I2C multi instantiate pseudo device driver",
+		.acpi_match_table = ACPI_PTR(i2c_multi_inst_acpi_ids),
+	},
+	.probe = i2c_multi_inst_probe,
+	.remove = i2c_multi_inst_remove,
+};
+module_platform_driver(i2c_multi_inst_driver);
+
+MODULE_DESCRIPTION("I2C multi instantiate pseudo device driver");
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig
index 85727ef6ce8e..6ac27e5908f5 100644
--- a/drivers/powercap/Kconfig
+++ b/drivers/powercap/Kconfig
@@ -29,4 +29,14 @@ config INTEL_RAPL
 	  controller, CPU core (Power Plance 0), graphics uncore (Power Plane
 	  1), etc.
 
+config IDLE_INJECT
+	bool "Idle injection framework"
+	depends on CPU_IDLE
+	default n
+	help
+	  This enables support for the idle injection framework. It
+	  provides a way to force idle periods on a set of specified
+	  CPUs for power capping. Idle period can be injected
+	  synchronously on a set of specified CPUs or alternatively
+	  on a per CPU basis.
 endif
diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile
index 0a21ef31372b..1b328854b36e 100644
--- a/drivers/powercap/Makefile
+++ b/drivers/powercap/Makefile
@@ -1,2 +1,3 @@
 obj-$(CONFIG_POWERCAP)	+= powercap_sys.o
 obj-$(CONFIG_INTEL_RAPL) += intel_rapl.o
+obj-$(CONFIG_IDLE_INJECT) += idle_inject.o
diff --git a/drivers/powercap/idle_inject.c b/drivers/powercap/idle_inject.c
new file mode 100644
index 000000000000..24ff2a068978
--- /dev/null
+++ b/drivers/powercap/idle_inject.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * The idle injection framework provides a way to force CPUs to enter idle
+ * states for a specified fraction of time over a specified period.
+ *
+ * It relies on the smpboot kthreads feature providing common code for CPU
+ * hotplug and thread [un]parking.
+ *
+ * All of the kthreads used for idle injection are created at init time.
+ *
+ * Next, the users of the the idle injection framework provide a cpumask via
+ * its register function. The kthreads will be synchronized with respect to
+ * this cpumask.
+ *
+ * The idle + run duration is specified via separate helpers and that allows
+ * idle injection to be started.
+ *
+ * The idle injection kthreads will call play_idle() with the idle duration
+ * specified as per the above.
+ *
+ * After all of them have been woken up, a timer is set to start the next idle
+ * injection cycle.
+ *
+ * The timer interrupt handler will wake up the idle injection kthreads for
+ * all of the CPUs in the cpumask provided by the user.
+ *
+ * Idle injection is stopped synchronously and no leftover idle injection
+ * kthread activity after its completion is guaranteed.
+ *
+ * It is up to the user of this framework to provide a lock for higher-level
+ * synchronization to prevent race conditions like starting idle injection
+ * while unregistering from the framework.
+ */
+#define pr_fmt(fmt) "ii_dev: " fmt
+
+#include <linux/cpu.h>
+#include <linux/hrtimer.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smpboot.h>
+
+#include <uapi/linux/sched/types.h>
+
+/**
+ * struct idle_inject_thread - task on/off switch structure
+ * @tsk: task injecting the idle cycles
+ * @should_run: whether or not to run the task (for the smpboot kthread API)
+ */
+struct idle_inject_thread {
+	struct task_struct *tsk;
+	int should_run;
+};
+
+/**
+ * struct idle_inject_device - idle injection data
+ * @timer: idle injection period timer
+ * @idle_duration_ms: duration of CPU idle time to inject
+ * @run_duration_ms: duration of CPU run time to allow
+ * @cpumask: mask of CPUs affected by idle injection
+ */
+struct idle_inject_device {
+	struct hrtimer timer;
+	unsigned int idle_duration_ms;
+	unsigned int run_duration_ms;
+	unsigned long int cpumask[0];
+};
+
+static DEFINE_PER_CPU(struct idle_inject_thread, idle_inject_thread);
+static DEFINE_PER_CPU(struct idle_inject_device *, idle_inject_device);
+
+/**
+ * idle_inject_wakeup - Wake up idle injection threads
+ * @ii_dev: target idle injection device
+ *
+ * Every idle injection task associated with the given idle injection device
+ * and running on an online CPU will be woken up.
+ */
+static void idle_inject_wakeup(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	for_each_cpu_and(cpu, to_cpumask(ii_dev->cpumask), cpu_online_mask) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 1;
+		wake_up_process(iit->tsk);
+	}
+}
+
+/**
+ * idle_inject_timer_fn - idle injection timer function
+ * @timer: idle injection hrtimer
+ *
+ * This function is called when the idle injection timer expires.  It wakes up
+ * idle injection tasks associated with the timer and they, in turn, invoke
+ * play_idle() to inject a specified amount of CPU idle time.
+ *
+ * Return: HRTIMER_RESTART.
+ */
+static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
+{
+	unsigned int duration_ms;
+	struct idle_inject_device *ii_dev =
+		container_of(timer, struct idle_inject_device, timer);
+
+	duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	duration_ms += READ_ONCE(ii_dev->idle_duration_ms);
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_forward_now(timer, ms_to_ktime(duration_ms));
+
+	return HRTIMER_RESTART;
+}
+
+/**
+ * idle_inject_fn - idle injection work function
+ * @cpu: the CPU owning the task
+ *
+ * This function calls play_idle() to inject a specified amount of CPU idle
+ * time.
+ */
+static void idle_inject_fn(unsigned int cpu)
+{
+	struct idle_inject_device *ii_dev;
+	struct idle_inject_thread *iit;
+
+	ii_dev = per_cpu(idle_inject_device, cpu);
+	iit = per_cpu_ptr(&idle_inject_thread, cpu);
+
+	/*
+	 * Let the smpboot main loop know that the task should not run again.
+	 */
+	iit->should_run = 0;
+
+	play_idle(READ_ONCE(ii_dev->idle_duration_ms));
+}
+
+/**
+ * idle_inject_set_duration - idle and run duration update helper
+ * @run_duration_ms: CPU run time to allow in milliseconds
+ * @idle_duration_ms: CPU idle time to inject in milliseconds
+ */
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+			      unsigned int run_duration_ms,
+			      unsigned int idle_duration_ms)
+{
+	if (run_duration_ms && idle_duration_ms) {
+		WRITE_ONCE(ii_dev->run_duration_ms, run_duration_ms);
+		WRITE_ONCE(ii_dev->idle_duration_ms, idle_duration_ms);
+	}
+}
+
+/**
+ * idle_inject_get_duration - idle and run duration retrieval helper
+ * @run_duration_ms: memory location to store the current CPU run time
+ * @idle_duration_ms: memory location to store the current CPU idle time
+ */
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+			      unsigned int *run_duration_ms,
+			      unsigned int *idle_duration_ms)
+{
+	*run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	*idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+}
+
+/**
+ * idle_inject_start - start idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function starts idle injection by first waking up all of the idle
+ * injection kthreads associated with @ii_dev to let them inject CPU idle time
+ * sets up a timer to start the next idle injection period.
+ *
+ * Return: -EINVAL if the CPU idle or CPU run time is not set or 0 on success.
+ */
+int idle_inject_start(struct idle_inject_device *ii_dev)
+{
+	unsigned int idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+	unsigned int run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+
+	if (!idle_duration_ms || !run_duration_ms)
+		return -EINVAL;
+
+	pr_debug("Starting injecting idle cycles on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_start(&ii_dev->timer,
+		      ms_to_ktime(idle_duration_ms + run_duration_ms),
+		      HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+/**
+ * idle_inject_stop - stops idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function stops idle injection and waits for the threads to finish work.
+ * If CPU idle time is being injected when this function runs, then it will
+ * wait until the end of the cycle.
+ *
+ * When it returns, there is no more idle injection kthread activity.  The
+ * kthreads are scheduled out and the periodic timer is off.
+ */
+void idle_inject_stop(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	pr_debug("Stopping idle injection on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	hrtimer_cancel(&ii_dev->timer);
+
+	/*
+	 * Stopping idle injection requires all of the idle injection kthreads
+	 * associated with the given cpumask to be parked and stay that way, so
+	 * prevent CPUs from going online at this point.  Any CPUs going online
+	 * after the loop below will be covered by clearing the should_run flag
+	 * that will cause the smpboot main loop to schedule them out.
+	 */
+	cpu_hotplug_disable();
+
+	/*
+	 * Iterate over all (online + offline) CPUs here in case one of them
+	 * goes offline with the should_run flag set so as to prevent its idle
+	 * injection kthread from running when the CPU goes online again after
+	 * the ii_dev has been freed.
+	 */
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 0;
+
+		wait_task_inactive(iit->tsk, 0);
+	}
+
+	cpu_hotplug_enable();
+}
+
+/**
+ * idle_inject_setup - prepare the current task for idle injection
+ * @cpu: not used
+ *
+ * Called once, this function is in charge of setting the current task's
+ * scheduler parameters to make it an RT task.
+ */
+static void idle_inject_setup(unsigned int cpu)
+{
+	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+
+	sched_setscheduler(current, SCHED_FIFO, &param);
+}
+
+/**
+ * idle_inject_should_run - function helper for the smpboot API
+ * @cpu: CPU the kthread is running on
+ *
+ * Return: whether or not the thread can run.
+ */
+static int idle_inject_should_run(unsigned int cpu)
+{
+	struct idle_inject_thread *iit =
+		per_cpu_ptr(&idle_inject_thread, cpu);
+
+	return iit->should_run;
+}
+
+/**
+ * idle_inject_register - initialize idle injection on a set of CPUs
+ * @cpumask: CPUs to be affected by idle injection
+ *
+ * This function creates an idle injection control device structure for the
+ * given set of CPUs and initializes the timer associated with it.  It does not
+ * start any injection cycles.
+ *
+ * Return: NULL if memory allocation fails, idle injection control device
+ * pointer on success.
+ */
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask)
+{
+	struct idle_inject_device *ii_dev;
+	int cpu, cpu_rb;
+
+	ii_dev = kzalloc(sizeof(*ii_dev) + cpumask_size(), GFP_KERNEL);
+	if (!ii_dev)
+		return NULL;
+
+	cpumask_copy(to_cpumask(ii_dev->cpumask), cpumask);
+	hrtimer_init(&ii_dev->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	ii_dev->timer.function = idle_inject_timer_fn;
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+
+		if (per_cpu(idle_inject_device, cpu)) {
+			pr_err("cpu%d is already registered\n", cpu);
+			goto out_rollback;
+		}
+
+		per_cpu(idle_inject_device, cpu) = ii_dev;
+	}
+
+	return ii_dev;
+
+out_rollback:
+	for_each_cpu(cpu_rb, to_cpumask(ii_dev->cpumask)) {
+		if (cpu == cpu_rb)
+			break;
+		per_cpu(idle_inject_device, cpu_rb) = NULL;
+	}
+
+	kfree(ii_dev);
+
+	return NULL;
+}
+
+/**
+ * idle_inject_unregister - unregister idle injection control device
+ * @ii_dev: idle injection control device to unregister
+ *
+ * The function stops idle injection for the given control device,
+ * unregisters its kthreads and frees memory allocated when that device was
+ * created.
+ */
+void idle_inject_unregister(struct idle_inject_device *ii_dev)
+{
+	unsigned int cpu;
+
+	idle_inject_stop(ii_dev);
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask))
+		per_cpu(idle_inject_device, cpu) = NULL;
+
+	kfree(ii_dev);
+}
+
+static struct smp_hotplug_thread idle_inject_threads = {
+	.store = &idle_inject_thread.tsk,
+	.setup = idle_inject_setup,
+	.thread_fn = idle_inject_fn,
+	.thread_comm = "idle_inject/%u",
+	.thread_should_run = idle_inject_should_run,
+};
+
+static int __init idle_inject_init(void)
+{
+	return smpboot_register_percpu_thread(&idle_inject_threads);
+}
+early_initcall(idle_inject_init);
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 547dbdac9d54..01b0e2bb3319 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -89,6 +89,7 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin,
 	case PTP_PF_PHYSYNC:
 		if (chan != 0)
 			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 5dbccf5f3037..329cdd33ed62 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -180,9 +180,9 @@ config REGULATOR_BCM590XX
 	  BCM590xx PMUs. This will enable support for the software
 	  controllable LDO/Switching regulators.
 
-config REGULATOR_BD71837
+config REGULATOR_BD718XX
 	tristate "ROHM BD71837 Power Regulator"
-	depends on MFD_BD71837
+	depends on MFD_ROHM_BD718XX
 	help
 	  This driver supports voltage regulators on ROHM BD71837 PMIC.
 	  This will enable support for the software controllable buck
@@ -633,12 +633,12 @@ config REGULATOR_PCF50633
 	 on PCF50633
 
 config REGULATOR_PFUZE100
-	tristate "Freescale PFUZE100/200/3000 regulator driver"
+	tristate "Freescale PFUZE100/200/3000/3001 regulator driver"
 	depends on I2C
 	select REGMAP_I2C
 	help
 	  Say y here to support the regulators found on the Freescale
-	  PFUZE100/200/3000 PMIC.
+	  PFUZE100/200/3000/3001 PMIC.
 
 config REGULATOR_PV88060
 	tristate "Powerventure Semiconductor PV88060 regulator"
@@ -682,6 +682,15 @@ config REGULATOR_QCOM_RPM
 	  Qualcomm RPM as a module. The module will be named
 	  "qcom_rpm-regulator".
 
+config REGULATOR_QCOM_RPMH
+	tristate "Qualcomm Technologies, Inc. RPMh regulator driver"
+	depends on QCOM_RPMH || COMPILE_TEST
+	help
+	  This driver supports control of PMIC regulators via the RPMh hardware
+	  block found on Qualcomm Technologies Inc. SoCs.  RPMh regulator
+	  control allows for voting on regulator state between multiple
+	  processors within the SoC.
+
 config REGULATOR_QCOM_SMD_RPM
 	tristate "Qualcomm SMD based RPM regulator driver"
 	depends on QCOM_SMD_RPM
@@ -950,6 +959,14 @@ config REGULATOR_TWL4030
 	  This driver supports the voltage regulators provided by
 	  this family of companion chips.
 
+config REGULATOR_UNIPHIER
+	tristate "UniPhier regulator driver"
+	depends on ARCH_UNIPHIER || COMPILE_TEST
+	depends on OF && MFD_SYSCON
+	default ARCH_UNIPHIER
+	help
+	  Support for regulators implemented on Socionext UniPhier SoCs.
+
 config REGULATOR_VCTRL
 	tristate "Voltage controlled regulators"
 	depends on OF
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index bd818ceb7c72..801d9a34a203 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -27,7 +27,7 @@ obj-$(CONFIG_REGULATOR_AS3711) += as3711-regulator.o
 obj-$(CONFIG_REGULATOR_AS3722) += as3722-regulator.o
 obj-$(CONFIG_REGULATOR_AXP20X) += axp20x-regulator.o
 obj-$(CONFIG_REGULATOR_BCM590XX) += bcm590xx-regulator.o
-obj-$(CONFIG_REGULATOR_BD71837) += bd71837-regulator.o
+obj-$(CONFIG_REGULATOR_BD718XX) += bd71837-regulator.o
 obj-$(CONFIG_REGULATOR_BD9571MWV) += bd9571mwv-regulator.o
 obj-$(CONFIG_REGULATOR_DA903X)	+= da903x.o
 obj-$(CONFIG_REGULATOR_DA9052)	+= da9052-regulator.o
@@ -78,6 +78,7 @@ obj-$(CONFIG_REGULATOR_MT6323)	+= mt6323-regulator.o
 obj-$(CONFIG_REGULATOR_MT6380)	+= mt6380-regulator.o
 obj-$(CONFIG_REGULATOR_MT6397)	+= mt6397-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_RPM) += qcom_rpm-regulator.o
+obj-$(CONFIG_REGULATOR_QCOM_RPMH) += qcom-rpmh-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_SMD_RPM) += qcom_smd-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_SPMI) += qcom_spmi-regulator.o
 obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o
@@ -118,6 +119,7 @@ obj-$(CONFIG_REGULATOR_TPS65912) += tps65912-regulator.o
 obj-$(CONFIG_REGULATOR_TPS80031) += tps80031-regulator.o
 obj-$(CONFIG_REGULATOR_TPS65132) += tps65132-regulator.o
 obj-$(CONFIG_REGULATOR_TWL4030) += twl-regulator.o twl6030-regulator.o
+obj-$(CONFIG_REGULATOR_UNIPHIER) += uniphier-regulator.o
 obj-$(CONFIG_REGULATOR_VCTRL) += vctrl-regulator.o
 obj-$(CONFIG_REGULATOR_VEXPRESS) += vexpress-regulator.o
 obj-$(CONFIG_REGULATOR_WM831X) += wm831x-dcdc.o
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index f6d6a4ad9e8a..e976d073f28d 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -36,6 +36,8 @@ struct arizona_ldo1 {
 
 	struct regulator_consumer_supply supply;
 	struct regulator_init_data init_data;
+
+	struct gpio_desc *ena_gpiod;
 };
 
 static int arizona_ldo1_hc_list_voltage(struct regulator_dev *rdev,
@@ -253,12 +255,17 @@ static int arizona_ldo1_common_init(struct platform_device *pdev,
 		}
 	}
 
-	/* We assume that high output = regulator off */
-	config.ena_gpiod = devm_gpiod_get_optional(&pdev->dev, "wlf,ldoena",
-						   GPIOD_OUT_HIGH);
+	/* We assume that high output = regulator off
+	 * Don't use devm, since we need to get against the parent device
+	 * so clean up would happen at the wrong time
+	 */
+	config.ena_gpiod = gpiod_get_optional(parent_dev, "wlf,ldoena",
+					      GPIOD_OUT_LOW);
 	if (IS_ERR(config.ena_gpiod))
 		return PTR_ERR(config.ena_gpiod);
 
+	ldo1->ena_gpiod = config.ena_gpiod;
+
 	if (pdata->init_data)
 		config.init_data = pdata->init_data;
 	else
@@ -276,6 +283,9 @@ static int arizona_ldo1_common_init(struct platform_device *pdev,
 	of_node_put(config.of_node);
 
 	if (IS_ERR(ldo1->regulator)) {
+		if (config.ena_gpiod)
+			gpiod_put(config.ena_gpiod);
+
 		ret = PTR_ERR(ldo1->regulator);
 		dev_err(&pdev->dev, "Failed to register LDO1 supply: %d\n",
 			ret);
@@ -334,8 +344,19 @@ static int arizona_ldo1_probe(struct platform_device *pdev)
 	return ret;
 }
 
+static int arizona_ldo1_remove(struct platform_device *pdev)
+{
+	struct arizona_ldo1 *ldo1 = platform_get_drvdata(pdev);
+
+	if (ldo1->ena_gpiod)
+		gpiod_put(ldo1->ena_gpiod);
+
+	return 0;
+}
+
 static struct platform_driver arizona_ldo1_driver = {
 	.probe = arizona_ldo1_probe,
+	.remove = arizona_ldo1_remove,
 	.driver		= {
 		.name	= "arizona-ldo1",
 	},
diff --git a/drivers/regulator/bd71837-regulator.c b/drivers/regulator/bd71837-regulator.c
index 6eae4d0432a2..0f8ac8dec3e1 100644
--- a/drivers/regulator/bd71837-regulator.c
+++ b/drivers/regulator/bd71837-regulator.c
@@ -2,19 +2,18 @@
 // Copyright (C) 2018 ROHM Semiconductors
 // bd71837-regulator.c ROHM BD71837MWV regulator driver
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
+#include <linux/delay.h>
 #include <linux/err.h>
+#include <linux/gpio.h>
 #include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/rohm-bd718x7.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
-#include <linux/delay.h>
-#include <linux/slab.h>
-#include <linux/gpio.h>
-#include <linux/mfd/bd71837.h>
 #include <linux/regulator/of_regulator.h>
+#include <linux/slab.h>
 
 struct bd71837_pmic {
 	struct regulator_desc descs[BD71837_REGULATOR_CNT];
@@ -39,7 +38,7 @@ static int bd71837_buck1234_set_ramp_delay(struct regulator_dev *rdev,
 	int id = rdev->desc->id;
 	unsigned int ramp_value = BUCK_RAMPRATE_10P00MV;
 
-	dev_dbg(&(pmic->pdev->dev), "Buck[%d] Set Ramp = %d\n", id + 1,
+	dev_dbg(&pmic->pdev->dev, "Buck[%d] Set Ramp = %d\n", id + 1,
 		ramp_delay);
 	switch (ramp_delay) {
 	case 1 ... 1250:
@@ -73,14 +72,10 @@ static int bd71837_buck1234_set_ramp_delay(struct regulator_dev *rdev,
 static int bd71837_set_voltage_sel_restricted(struct regulator_dev *rdev,
 						    unsigned int sel)
 {
-	int ret;
-
-	ret = regulator_is_enabled_regmap(rdev);
-	if (!ret)
-		ret = regulator_set_voltage_sel_regmap(rdev, sel);
-	else if (ret == 1)
-		ret = -EBUSY;
-	return ret;
+	if (regulator_is_enabled_regmap(rdev))
+		return -EBUSY;
+
+	return regulator_set_voltage_sel_regmap(rdev, sel);
 }
 
 static struct regulator_ops bd71837_ldo_regulator_ops = {
@@ -195,7 +190,7 @@ static const struct regulator_linear_range bd71837_ldo1_voltage_ranges[] = {
  * LDO2
  * 0.8 or 0.9V
  */
-const unsigned int ldo_2_volts[] = {
+static const unsigned int ldo_2_volts[] = {
 	900000, 800000
 };
 
@@ -495,7 +490,6 @@ struct reg_init {
 static int bd71837_probe(struct platform_device *pdev)
 {
 	struct bd71837_pmic *pmic;
-	struct bd71837_board *pdata;
 	struct regulator_config config = { 0 };
 	struct reg_init pmic_regulator_inits[] = {
 		{
@@ -548,8 +542,7 @@ static int bd71837_probe(struct platform_device *pdev)
 
 	int i, err;
 
-	pmic = devm_kzalloc(&pdev->dev, sizeof(struct bd71837_pmic),
-			    GFP_KERNEL);
+	pmic = devm_kzalloc(&pdev->dev, sizeof(*pmic), GFP_KERNEL);
 	if (!pmic)
 		return -ENOMEM;
 
@@ -564,7 +557,6 @@ static int bd71837_probe(struct platform_device *pdev)
 		goto err;
 	}
 	platform_set_drvdata(pdev, pmic);
-	pdata = dev_get_platdata(pmic->mfd->dev);
 
 	/* Register LOCK release */
 	err = regmap_update_bits(pmic->mfd->regmap, BD71837_REG_REGLOCK,
@@ -573,8 +565,8 @@ static int bd71837_probe(struct platform_device *pdev)
 		dev_err(&pmic->pdev->dev, "Failed to unlock PMIC (%d)\n", err);
 		goto err;
 	} else {
-		dev_dbg(&pmic->pdev->dev, "%s: Unlocked lock register 0x%x\n",
-			__func__, BD71837_REG_REGLOCK);
+		dev_dbg(&pmic->pdev->dev, "Unlocked lock register 0x%x\n",
+			BD71837_REG_REGLOCK);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(pmic_regulator_inits); i++) {
@@ -584,9 +576,6 @@ static int bd71837_probe(struct platform_device *pdev)
 
 		desc = &pmic->descs[i];
 
-		if (pdata)
-			config.init_data = pdata->init_data[i];
-
 		config.dev = pdev->dev.parent;
 		config.driver_data = pmic;
 		config.regmap = pmic->mfd->regmap;
@@ -619,8 +608,6 @@ static int bd71837_probe(struct platform_device *pdev)
 		pmic->rdev[i] = rdev;
 	}
 
-	return 0;
-
 err:
 	return err;
 }
@@ -628,7 +615,6 @@ err:
 static struct platform_driver bd71837_regulator = {
 	.driver = {
 		.name = "bd71837-pmic",
-		.owner = THIS_MODULE,
 	},
 	.probe = bd71837_probe,
 };
diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c
index be574eb444eb..274c5ed7cd73 100644
--- a/drivers/regulator/bd9571mwv-regulator.c
+++ b/drivers/regulator/bd9571mwv-regulator.c
@@ -30,6 +30,7 @@ struct bd9571mwv_reg {
 	/* DDR Backup Power */
 	u8 bkup_mode_cnt_keepon;	/* from "rohm,ddr-backup-power" */
 	u8 bkup_mode_cnt_saved;
+	bool bkup_mode_enabled;
 
 	/* Power switch type */
 	bool rstbmode_level;
@@ -171,13 +172,60 @@ static int bd9571mwv_bkup_mode_write(struct bd9571mwv *bd, unsigned int mode)
 	return 0;
 }
 
+static ssize_t backup_mode_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off");
+}
+
+static ssize_t backup_mode_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
+	unsigned int mode;
+	int ret;
+
+	if (!count)
+		return 0;
+
+	ret = kstrtobool(buf, &bdreg->bkup_mode_enabled);
+	if (ret)
+		return ret;
+
+	if (!bdreg->rstbmode_level)
+		return count;
+
+	/*
+	 * Configure DDR Backup Mode, to change the role of the accessory power
+	 * switch from a power switch to a wake-up switch, or vice versa
+	 */
+	ret = bd9571mwv_bkup_mode_read(bdreg->bd, &mode);
+	if (ret)
+		return ret;
+
+	mode &= ~BD9571MWV_BKUP_MODE_CNT_KEEPON_MASK;
+	if (bdreg->bkup_mode_enabled)
+		mode |= bdreg->bkup_mode_cnt_keepon;
+
+	ret = bd9571mwv_bkup_mode_write(bdreg->bd, mode);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(backup_mode);
+
 static int bd9571mwv_suspend(struct device *dev)
 {
 	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
 	unsigned int mode;
 	int ret;
 
-	if (!device_may_wakeup(dev))
+	if (!bdreg->bkup_mode_enabled)
 		return 0;
 
 	/* Save DDR Backup Mode */
@@ -204,7 +252,7 @@ static int bd9571mwv_resume(struct device *dev)
 {
 	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
 
-	if (!device_may_wakeup(dev))
+	if (!bdreg->bkup_mode_enabled)
 		return 0;
 
 	/* Restore DDR Backup Mode */
@@ -215,9 +263,15 @@ static const struct dev_pm_ops bd9571mwv_pm  = {
 	SET_SYSTEM_SLEEP_PM_OPS(bd9571mwv_suspend, bd9571mwv_resume)
 };
 
+static int bd9571mwv_regulator_remove(struct platform_device *pdev)
+{
+	device_remove_file(&pdev->dev, &dev_attr_backup_mode);
+	return 0;
+}
 #define DEV_PM_OPS	&bd9571mwv_pm
 #else
 #define DEV_PM_OPS	NULL
+#define bd9571mwv_regulator_remove	NULL
 #endif /* CONFIG_PM_SLEEP */
 
 static int bd9571mwv_regulator_probe(struct platform_device *pdev)
@@ -270,14 +324,21 @@ static int bd9571mwv_regulator_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+#ifdef CONFIG_PM_SLEEP
 	if (bdreg->bkup_mode_cnt_keepon) {
-		device_set_wakeup_capable(&pdev->dev, true);
+		int ret;
+
 		/*
-		 * Wakeup is enabled by default in pulse mode, but needs
+		 * Backup mode is enabled by default in pulse mode, but needs
 		 * explicit user setup in level mode.
 		 */
-		device_set_wakeup_enable(&pdev->dev, bdreg->rstbmode_pulse);
+		bdreg->bkup_mode_enabled = bdreg->rstbmode_pulse;
+
+		ret = device_create_file(&pdev->dev, &dev_attr_backup_mode);
+		if (ret)
+			return ret;
 	}
+#endif /* CONFIG_PM_SLEEP */
 
 	return 0;
 }
@@ -294,6 +355,7 @@ static struct platform_driver bd9571mwv_regulator_driver = {
 		.pm = DEV_PM_OPS,
 	},
 	.probe = bd9571mwv_regulator_probe,
+	.remove = bd9571mwv_regulator_remove,
 	.id_table = bd9571mwv_regulator_id_table,
 };
 module_platform_driver(bd9571mwv_regulator_driver);
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 6ed568b96c0e..bb1324f93143 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1740,6 +1740,8 @@ struct regulator *_regulator_get(struct device *dev, const char *id,
 			rdev->use_count = 0;
 	}
 
+	device_link_add(dev, &rdev->dev, DL_FLAG_STATELESS);
+
 	return regulator;
 }
 
@@ -1829,9 +1831,21 @@ static void _regulator_put(struct regulator *regulator)
 
 	debugfs_remove_recursive(regulator->debugfs);
 
-	/* remove any sysfs entries */
-	if (regulator->dev)
+	if (regulator->dev) {
+		int count = 0;
+		struct regulator *r;
+
+		list_for_each_entry(r, &rdev->consumer_list, list)
+			if (r->dev == regulator->dev)
+				count++;
+
+		if (count == 1)
+			device_link_remove(regulator->dev, &rdev->dev);
+
+		/* remove any sysfs entries */
 		sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name);
+	}
+
 	regulator_lock(rdev);
 	list_del(&regulator->list);
 
@@ -4441,7 +4455,7 @@ void regulator_unregister(struct regulator_dev *rdev)
 EXPORT_SYMBOL_GPL(regulator_unregister);
 
 #ifdef CONFIG_SUSPEND
-static int _regulator_suspend_late(struct device *dev, void *data)
+static int _regulator_suspend(struct device *dev, void *data)
 {
 	struct regulator_dev *rdev = dev_to_rdev(dev);
 	suspend_state_t *state = data;
@@ -4455,20 +4469,20 @@ static int _regulator_suspend_late(struct device *dev, void *data)
 }
 
 /**
- * regulator_suspend_late - prepare regulators for system wide suspend
+ * regulator_suspend - prepare regulators for system wide suspend
  * @state: system suspend state
  *
  * Configure each regulator with it's suspend operating parameters for state.
  */
-static int regulator_suspend_late(struct device *dev)
+static int regulator_suspend(struct device *dev)
 {
 	suspend_state_t state = pm_suspend_target_state;
 
 	return class_for_each_device(&regulator_class, NULL, &state,
-				     _regulator_suspend_late);
+				     _regulator_suspend);
 }
 
-static int _regulator_resume_early(struct device *dev, void *data)
+static int _regulator_resume(struct device *dev, void *data)
 {
 	int ret = 0;
 	struct regulator_dev *rdev = dev_to_rdev(dev);
@@ -4481,35 +4495,35 @@ static int _regulator_resume_early(struct device *dev, void *data)
 
 	regulator_lock(rdev);
 
-	if (rdev->desc->ops->resume_early &&
+	if (rdev->desc->ops->resume &&
 	    (rstate->enabled == ENABLE_IN_SUSPEND ||
 	     rstate->enabled == DISABLE_IN_SUSPEND))
-		ret = rdev->desc->ops->resume_early(rdev);
+		ret = rdev->desc->ops->resume(rdev);
 
 	regulator_unlock(rdev);
 
 	return ret;
 }
 
-static int regulator_resume_early(struct device *dev)
+static int regulator_resume(struct device *dev)
 {
 	suspend_state_t state = pm_suspend_target_state;
 
 	return class_for_each_device(&regulator_class, NULL, &state,
-				     _regulator_resume_early);
+				     _regulator_resume);
 }
 
 #else /* !CONFIG_SUSPEND */
 
-#define regulator_suspend_late	NULL
-#define regulator_resume_early	NULL
+#define regulator_suspend	NULL
+#define regulator_resume	NULL
 
 #endif /* !CONFIG_SUSPEND */
 
 #ifdef CONFIG_PM
 static const struct dev_pm_ops __maybe_unused regulator_pm_ops = {
-	.suspend_late	= regulator_suspend_late,
-	.resume_early	= regulator_resume_early,
+	.suspend	= regulator_suspend,
+	.resume		= regulator_resume,
 };
 #endif
 
diff --git a/drivers/regulator/cpcap-regulator.c b/drivers/regulator/cpcap-regulator.c
index bd910fe123d9..2131457937b7 100644
--- a/drivers/regulator/cpcap-regulator.c
+++ b/drivers/regulator/cpcap-regulator.c
@@ -271,6 +271,29 @@ static struct regulator_ops cpcap_regulator_ops = {
 };
 
 static const unsigned int unknown_val_tbl[] = { 0, };
+static const unsigned int sw2_sw4_val_tbl[] = { 612500, 625000, 637500,
+						650000, 662500, 675000,
+						687500, 700000, 712500,
+						725000, 737500, 750000,
+						762500, 775000, 787500,
+						800000, 812500, 825000,
+						837500, 850000, 862500,
+						875000, 887500, 900000,
+						912500, 925000, 937500,
+						950000, 962500, 975000,
+						987500, 1000000, 1012500,
+						1025000, 1037500, 1050000,
+						1062500, 1075000, 1087500,
+						1100000, 1112500, 1125000,
+						1137500, 1150000, 1162500,
+						1175000, 1187500, 1200000,
+						1212500, 1225000, 1237500,
+						1250000, 1262500, 1275000,
+						1287500, 1300000, 1312500,
+						1325000, 1337500, 1350000,
+						1362500, 1375000, 1387500,
+						1400000, 1412500, 1425000,
+						1437500, 1450000, 1462500, };
 static const unsigned int sw5_val_tbl[] = { 0, 5050000, };
 static const unsigned int vcam_val_tbl[] = { 2600000, 2700000, 2800000,
 					     2900000, };
@@ -389,6 +412,82 @@ static struct cpcap_regulator omap4_regulators[] = {
 	{ /* sentinel */ },
 };
 
+static struct cpcap_regulator xoom_regulators[] = {
+	CPCAP_REG(SW1, CPCAP_REG_S1C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW1_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW2, CPCAP_REG_S2C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW2_SEL, sw2_sw4_val_tbl,
+		  0xf00, 0x7f, 0, 0x800, 0, 120),
+	CPCAP_REG(SW3, CPCAP_REG_S3C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW3_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW4, CPCAP_REG_S4C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW4_SEL, sw2_sw4_val_tbl,
+		  0xf00, 0x7f, 0, 0x900, 0, 100),
+	CPCAP_REG(SW5, CPCAP_REG_S5C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW5_SEL, sw5_val_tbl,
+		  0x2a, 0, 0, 0x22, 0, 0),
+	CPCAP_REG(SW6, CPCAP_REG_S6C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW6_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(VCAM, CPCAP_REG_VCAMC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VCAM_SEL, vcam_val_tbl,
+		  0x87, 0x30, 4, 0x7, 0, 420),
+	CPCAP_REG(VCSI, CPCAP_REG_VCSIC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VCSI_SEL, vcsi_val_tbl,
+		  0x47, 0x10, 4, 0x7, 0, 350),
+	CPCAP_REG(VDAC, CPCAP_REG_VDACC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VDAC_SEL, vdac_val_tbl,
+		  0x87, 0x30, 4, 0x3, 0, 420),
+	CPCAP_REG(VDIG, CPCAP_REG_VDIGC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VDIG_SEL, vdig_val_tbl,
+		  0x87, 0x30, 4, 0x5, 0, 420),
+	CPCAP_REG(VFUSE, CPCAP_REG_VFUSEC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VFUSE_SEL, vfuse_val_tbl,
+		  0x80, 0xf, 0, 0x80, 0, 420),
+	CPCAP_REG(VHVIO, CPCAP_REG_VHVIOC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VHVIO_SEL, vhvio_val_tbl,
+		  0x17, 0, 0, 0x2, 0, 0),
+	CPCAP_REG(VSDIO, CPCAP_REG_VSDIOC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VSDIO_SEL, vsdio_val_tbl,
+		  0x87, 0x38, 3, 0x2, 0, 420),
+	CPCAP_REG(VPLL, CPCAP_REG_VPLLC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VPLL_SEL, vpll_val_tbl,
+		  0x43, 0x18, 3, 0x1, 0, 420),
+	CPCAP_REG(VRF1, CPCAP_REG_VRF1C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRF1_SEL, vrf1_val_tbl,
+		  0xac, 0x2, 1, 0xc, 0, 10),
+	CPCAP_REG(VRF2, CPCAP_REG_VRF2C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRF2_SEL, vrf2_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 10),
+	CPCAP_REG(VRFREF, CPCAP_REG_VRFREFC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRFREF_SEL, vrfref_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 420),
+	CPCAP_REG(VWLAN1, CPCAP_REG_VWLAN1C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VWLAN1_SEL, vwlan1_val_tbl,
+		  0x47, 0x10, 4, 0x5, 0, 420),
+	CPCAP_REG(VWLAN2, CPCAP_REG_VWLAN2C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VWLAN2_SEL, vwlan2_val_tbl,
+		  0x20c, 0xc0, 6, 0x8, 0, 420),
+	CPCAP_REG(VSIM, CPCAP_REG_VSIMC, CPCAP_REG_ASSIGN3,
+		  0xffff, vsim_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 420),
+	CPCAP_REG(VSIMCARD, CPCAP_REG_VSIMC, CPCAP_REG_ASSIGN3,
+		  0xffff, vsimcard_val_tbl,
+		  0x1e80, 0x8, 3, 0x1e00, 0, 420),
+	CPCAP_REG(VVIB, CPCAP_REG_VVIBC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VVIB_SEL, vvib_val_tbl,
+		  0x1, 0xc, 2, 0, 0x1, 500),
+	CPCAP_REG(VUSB, CPCAP_REG_VUSBC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VUSB_SEL, vusb_val_tbl,
+		  0x11c, 0x40, 6, 0xc, 0, 0),
+	CPCAP_REG(VAUDIO, CPCAP_REG_VAUDIOC, CPCAP_REG_ASSIGN4,
+		  CPCAP_BIT_VAUDIO_SEL, vaudio_val_tbl,
+		  0x16, 0x1, 0, 0x4, 0, 0),
+	{ /* sentinel */ },
+};
+
 static const struct of_device_id cpcap_regulator_id_table[] = {
 	{
 		.compatible = "motorola,cpcap-regulator",
@@ -397,6 +496,10 @@ static const struct of_device_id cpcap_regulator_id_table[] = {
 		.compatible = "motorola,mapphone-cpcap-regulator",
 		.data = omap4_regulators,
 	},
+	{
+		.compatible = "motorola,xoom-cpcap-regulator",
+		.data = xoom_regulators,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, cpcap_regulator_id_table);
diff --git a/drivers/regulator/max14577-regulator.c b/drivers/regulator/max14577-regulator.c
index 0db288ce319c..bc7f4751bf9c 100644
--- a/drivers/regulator/max14577-regulator.c
+++ b/drivers/regulator/max14577-regulator.c
@@ -1,19 +1,9 @@
-/*
- * max14577.c - Regulator driver for the Maxim 14577/77836
- *
- * Copyright (C) 2013,2014 Samsung Electronics
- * Krzysztof Kozlowski <krzk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max14577.c - Regulator driver for the Maxim 14577/77836
+//
+// Copyright (C) 2013,2014 Samsung Electronics
+// Krzysztof Kozlowski <krzk@kernel.org>
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
diff --git a/drivers/regulator/max77686-regulator.c b/drivers/regulator/max77686-regulator.c
index c301f3733475..bee060937f56 100644
--- a/drivers/regulator/max77686-regulator.c
+++ b/drivers/regulator/max77686-regulator.c
@@ -1,26 +1,12 @@
-/*
- * max77686.c - Regulator driver for the Maxim 77686
- *
- * Copyright (C) 2012 Samsung Electronics
- * Chiwoong Byun <woong.byun@samsung.com>
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * This driver is based on max8997.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max77686.c - Regulator driver for the Maxim 77686
+//
+// Copyright (C) 2012 Samsung Electronics
+// Chiwoong Byun <woong.byun@samsung.com>
+// Jonghwa Lee <jonghwa3.lee@samsung.com>
+//
+// This driver is based on max8997.c
 
 #include <linux/kernel.h>
 #include <linux/bug.h>
diff --git a/drivers/regulator/max77693-regulator.c b/drivers/regulator/max77693-regulator.c
index e7000e777292..077ecbbfdf76 100644
--- a/drivers/regulator/max77693-regulator.c
+++ b/drivers/regulator/max77693-regulator.c
@@ -1,26 +1,12 @@
-/*
- * max77693.c - Regulator driver for the Maxim 77693 and 77843
- *
- * Copyright (C) 2013-2015 Samsung Electronics
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- * Krzysztof Kozlowski <krzk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * This driver is based on max77686.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max77693.c - Regulator driver for the Maxim 77693 and 77843
+//
+// Copyright (C) 2013-2015 Samsung Electronics
+// Jonghwa Lee <jonghwa3.lee@samsung.com>
+// Krzysztof Kozlowski <krzk@kernel.org>
+//
+// This driver is based on max77686.c
 
 #include <linux/err.h>
 #include <linux/slab.h>
diff --git a/drivers/regulator/max77802-regulator.c b/drivers/regulator/max77802-regulator.c
index b6261903818c..c30cf5c9f2de 100644
--- a/drivers/regulator/max77802-regulator.c
+++ b/drivers/regulator/max77802-regulator.c
@@ -1,25 +1,15 @@
-/*
- * max77802.c - Regulator driver for the Maxim 77802
- *
- * Copyright (C) 2013-2014 Google, Inc
- * Simon Glass <sjg@chromium.org>
- *
- * Copyright (C) 2012 Samsung Electronics
- * Chiwoong Byun <woong.byun@samsung.com>
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * This driver is based on max8997.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max77802.c - Regulator driver for the Maxim 77802
+//
+// Copyright (C) 2013-2014 Google, Inc
+// Simon Glass <sjg@chromium.org>
+//
+// Copyright (C) 2012 Samsung Electronics
+// Chiwoong Byun <woong.byun@samsung.com>
+// Jonghwa Lee <jonghwa3.lee@samsung.com>
+//
+// This driver is based on max8997.c
 
 #include <linux/kernel.h>
 #include <linux/bug.h>
diff --git a/drivers/regulator/max8997-regulator.c b/drivers/regulator/max8997-regulator.c
index a8ea30ee18a6..ad0c806b0737 100644
--- a/drivers/regulator/max8997-regulator.c
+++ b/drivers/regulator/max8997-regulator.c
@@ -1,25 +1,11 @@
-/*
- * max8997.c - Regulator driver for the Maxim 8997/8966
- *
- * Copyright (C) 2011 Samsung Electronics
- * MyungJoo Ham <myungjoo.ham@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * This driver is based on max8998.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max8997.c - Regulator driver for the Maxim 8997/8966
+//
+// Copyright (C) 2011 Samsung Electronics
+// MyungJoo Ham <myungjoo.ham@samsung.com>
+//
+// This driver is based on max8998.c
 
 #include <linux/bug.h>
 #include <linux/err.h>
@@ -165,8 +151,7 @@ static int max8997_list_voltage(struct regulator_dev *rdev,
 	int rid = rdev_get_id(rdev);
 	int val;
 
-	if (rid >= ARRAY_SIZE(reg_voltage_map) ||
-			rid < 0)
+	if (rid < 0 || rid >= ARRAY_SIZE(reg_voltage_map))
 		return -EINVAL;
 
 	desc = reg_voltage_map[rid];
diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c
index 6b9f262ebbb0..271bb736f3f5 100644
--- a/drivers/regulator/max8998.c
+++ b/drivers/regulator/max8998.c
@@ -1,24 +1,10 @@
-/*
- * max8998.c - Voltage regulator driver for the Maxim 8998
- *
- *  Copyright (C) 2009-2010 Samsung Electronics
- *  Kyungmin Park <kyungmin.park@samsung.com>
- *  Marek Szyprowski <m.szyprowski@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max8998.c - Voltage regulator driver for the Maxim 8998
+//
+//  Copyright (C) 2009-2010 Samsung Electronics
+//  Kyungmin Park <kyungmin.park@samsung.com>
+//  Marek Szyprowski <m.szyprowski@samsung.com>
 
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 8d9dbcc775ea..31c3a236120a 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -17,6 +17,8 @@
 #include <linux/slab.h>
 #include <linux/regmap.h>
 
+#define PFUZE_FLAG_DISABLE_SW	BIT(1)
+
 #define PFUZE_NUMREGS		128
 #define PFUZE100_VOL_OFFSET	0
 #define PFUZE100_STANDBY_OFFSET	1
@@ -44,16 +46,18 @@
 #define PFUZE100_VGEN5VOL	0x70
 #define PFUZE100_VGEN6VOL	0x71
 
-enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3 };
+enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3, PFUZE3001 = 0x31, };
 
 struct pfuze_regulator {
 	struct regulator_desc desc;
 	unsigned char stby_reg;
 	unsigned char stby_mask;
+	bool sw_reg;
 };
 
 struct pfuze_chip {
 	int	chip_id;
+	int     flags;
 	struct regmap *regmap;
 	struct device *dev;
 	struct pfuze_regulator regulator_descs[PFUZE100_MAX_REGULATOR];
@@ -92,6 +96,7 @@ static const struct i2c_device_id pfuze_device_id[] = {
 	{.name = "pfuze100", .driver_data = PFUZE100},
 	{.name = "pfuze200", .driver_data = PFUZE200},
 	{.name = "pfuze3000", .driver_data = PFUZE3000},
+	{.name = "pfuze3001", .driver_data = PFUZE3001},
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, pfuze_device_id);
@@ -100,6 +105,7 @@ static const struct of_device_id pfuze_dt_ids[] = {
 	{ .compatible = "fsl,pfuze100", .data = (void *)PFUZE100},
 	{ .compatible = "fsl,pfuze200", .data = (void *)PFUZE200},
 	{ .compatible = "fsl,pfuze3000", .data = (void *)PFUZE3000},
+	{ .compatible = "fsl,pfuze3001", .data = (void *)PFUZE3001},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, pfuze_dt_ids);
@@ -108,10 +114,28 @@ static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay)
 {
 	struct pfuze_chip *pfuze100 = rdev_get_drvdata(rdev);
 	int id = rdev_get_id(rdev);
+	bool reg_has_ramp_delay;
 	unsigned int ramp_bits;
 	int ret;
 
-	if (id < PFUZE100_SWBST) {
+	switch (pfuze100->chip_id) {
+	case PFUZE3001:
+		/* no dynamic voltage scaling for PF3001 */
+		reg_has_ramp_delay = false;
+		break;
+	case PFUZE3000:
+		reg_has_ramp_delay = (id < PFUZE3000_SWBST);
+		break;
+	case PFUZE200:
+		reg_has_ramp_delay = (id < PFUZE200_SWBST);
+		break;
+	case PFUZE100:
+	default:
+		reg_has_ramp_delay = (id < PFUZE100_SWBST);
+		break;
+	}
+
+	if (reg_has_ramp_delay) {
 		ramp_delay = 12500 / ramp_delay;
 		ramp_bits = (ramp_delay >> 1) - (ramp_delay >> 3);
 		ret = regmap_update_bits(pfuze100->regmap,
@@ -119,8 +143,9 @@ static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay)
 					 0xc0, ramp_bits << 6);
 		if (ret < 0)
 			dev_err(pfuze100->dev, "ramp failed, err %d\n", ret);
-	} else
+	} else {
 		ret = -EACCES;
+	}
 
 	return ret;
 }
@@ -142,6 +167,14 @@ static const struct regulator_ops pfuze100_fixed_regulator_ops = {
 };
 
 static const struct regulator_ops pfuze100_sw_regulator_ops = {
+	.list_voltage = regulator_list_voltage_linear,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.set_ramp_delay = pfuze100_set_ramp_delay,
+};
+
+static const struct regulator_ops pfuze100_sw_disable_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
@@ -192,13 +225,11 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = {
 			.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
 			.vsel_mask = 0x3f,	\
 			.enable_reg = (base) + PFUZE100_MODE_OFFSET,	\
-			.enable_val = 0xc,	\
-			.disable_val = 0x0,	\
 			.enable_mask = 0xf,	\
-			.enable_time = 500,	\
 		},	\
 		.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
 		.stby_mask = 0x3f,	\
+		.sw_reg = true,		\
 	}
 
 #define PFUZE100_SWB_REG(_chip, _name, base, mask, voltages)	\
@@ -361,6 +392,19 @@ static struct pfuze_regulator pfuze3000_regulators[] = {
 	PFUZE100_VGEN_REG(PFUZE3000, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
 };
 
+static struct pfuze_regulator pfuze3001_regulators[] = {
+	PFUZE100_SWB_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
+	PFUZE100_SWB_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
+	PFUZE3000_SW3_REG(PFUZE3001, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000),
+	PFUZE100_SWB_REG(PFUZE3001, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000),
+	PFUZE3000_VCC_REG(PFUZE3001, VCCSD, PFUZE100_VGEN3VOL, 2850000, 3300000, 150000),
+	PFUZE3000_VCC_REG(PFUZE3001, V33, PFUZE100_VGEN4VOL, 2850000, 3300000, 150000),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO3, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
+};
+
 #ifdef CONFIG_OF
 /* PFUZE100 */
 static struct of_regulator_match pfuze100_matches[] = {
@@ -418,6 +462,21 @@ static struct of_regulator_match pfuze3000_matches[] = {
 	{ .name = "vldo4",	},
 };
 
+/* PFUZE3001 */
+static struct of_regulator_match pfuze3001_matches[] = {
+
+	{ .name = "sw1",	},
+	{ .name = "sw2",	},
+	{ .name = "sw3",	},
+	{ .name = "vsnvs",	},
+	{ .name = "vldo1",	},
+	{ .name = "vldo2",	},
+	{ .name = "vccsd",	},
+	{ .name = "v33",	},
+	{ .name = "vldo3",	},
+	{ .name = "vldo4",	},
+};
+
 static struct of_regulator_match *pfuze_matches;
 
 static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
@@ -430,6 +489,9 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 	if (!np)
 		return -EINVAL;
 
+	if (of_property_read_bool(np, "fsl,pfuze-support-disable-sw"))
+		chip->flags |= PFUZE_FLAG_DISABLE_SW;
+
 	parent = of_get_child_by_name(np, "regulators");
 	if (!parent) {
 		dev_err(dev, "regulators node not found\n");
@@ -437,6 +499,11 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 	}
 
 	switch (chip->chip_id) {
+	case PFUZE3001:
+		pfuze_matches = pfuze3001_matches;
+		ret = of_regulator_match(dev, parent, pfuze3001_matches,
+					 ARRAY_SIZE(pfuze3001_matches));
+		break;
 	case PFUZE3000:
 		pfuze_matches = pfuze3000_matches;
 		ret = of_regulator_match(dev, parent, pfuze3000_matches,
@@ -508,7 +575,8 @@ static int pfuze_identify(struct pfuze_chip *pfuze_chip)
 		 */
 		dev_info(pfuze_chip->dev, "Assuming misprogrammed ID=0x8");
 	} else if ((value & 0x0f) != pfuze_chip->chip_id &&
-		   (value & 0xf0) >> 4 != pfuze_chip->chip_id) {
+		   (value & 0xf0) >> 4 != pfuze_chip->chip_id &&
+		   (value != pfuze_chip->chip_id)) {
 		/* device id NOT match with your setting */
 		dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value);
 		return -ENODEV;
@@ -588,6 +656,13 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 
 	/* use the right regulators after identify the right device */
 	switch (pfuze_chip->chip_id) {
+	case PFUZE3001:
+		pfuze_chip->pfuze_regulators = pfuze3001_regulators;
+		regulator_num = ARRAY_SIZE(pfuze3001_regulators);
+		sw_check_start = PFUZE3001_SW2;
+		sw_check_end = PFUZE3001_SW2;
+		sw_hi = 1 << 3;
+		break;
 	case PFUZE3000:
 		pfuze_chip->pfuze_regulators = pfuze3000_regulators;
 		regulator_num = ARRAY_SIZE(pfuze3000_regulators);
@@ -611,7 +686,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 	}
 	dev_info(&client->dev, "pfuze%s found.\n",
 		(pfuze_chip->chip_id == PFUZE100) ? "100" :
-		((pfuze_chip->chip_id == PFUZE200) ? "200" : "3000"));
+		(((pfuze_chip->chip_id == PFUZE200) ? "200" :
+		((pfuze_chip->chip_id == PFUZE3000) ? "3000" : "3001"))));
 
 	memcpy(pfuze_chip->regulator_descs, pfuze_chip->pfuze_regulators,
 		sizeof(pfuze_chip->regulator_descs));
@@ -636,7 +712,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 		if (i >= sw_check_start && i <= sw_check_end) {
 			regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val);
 			if (val & sw_hi) {
-				if (pfuze_chip->chip_id == PFUZE3000) {
+				if (pfuze_chip->chip_id == PFUZE3000 ||
+					pfuze_chip->chip_id == PFUZE3001) {
 					desc->volt_table = pfuze3000_sw2hi;
 					desc->n_voltages = ARRAY_SIZE(pfuze3000_sw2hi);
 				} else {
@@ -647,6 +724,21 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 			}
 		}
 
+		/*
+		 * Allow SW regulators to turn off. Checking it trough a flag is
+		 * a workaround to keep the backward compatibility with existing
+		 * old dtb's which may relay on the fact that we didn't disable
+		 * the switched regulator till yet.
+		 */
+		if (pfuze_chip->flags & PFUZE_FLAG_DISABLE_SW) {
+			if (pfuze_chip->regulator_descs[i].sw_reg) {
+				desc->ops = &pfuze100_sw_disable_regulator_ops;
+				desc->enable_val = 0x8;
+				desc->disable_val = 0x0;
+				desc->enable_time = 500;
+			}
+		}
+
 		config.dev = &client->dev;
 		config.init_data = init_data;
 		config.driver_data = pfuze_chip;
@@ -675,5 +767,5 @@ static struct i2c_driver pfuze_driver = {
 module_i2c_driver(pfuze_driver);
 
 MODULE_AUTHOR("Robin Gong <b38343@freescale.com>");
-MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/200/3000 PMIC");
+MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/200/3000/3001 PMIC");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
new file mode 100644
index 000000000000..9f27daebd8c8
--- /dev/null
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -0,0 +1,769 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/of_regulator.h>
+
+#include <soc/qcom/cmd-db.h>
+#include <soc/qcom/rpmh.h>
+
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+
+/**
+ * enum rpmh_regulator_type - supported RPMh accelerator types
+ * %VRM:	RPMh VRM accelerator which supports voting on enable, voltage,
+ *		and mode of LDO, SMPS, and BOB type PMIC regulators.
+ * %XOB:	RPMh XOB accelerator which supports voting on the enable state
+ *		of PMIC regulators.
+ */
+enum rpmh_regulator_type {
+	VRM,
+	XOB,
+};
+
+#define RPMH_REGULATOR_REG_VRM_VOLTAGE		0x0
+#define RPMH_REGULATOR_REG_ENABLE		0x4
+#define RPMH_REGULATOR_REG_VRM_MODE		0x8
+
+#define PMIC4_LDO_MODE_RETENTION		4
+#define PMIC4_LDO_MODE_LPM			5
+#define PMIC4_LDO_MODE_HPM			7
+
+#define PMIC4_SMPS_MODE_RETENTION		4
+#define PMIC4_SMPS_MODE_PFM			5
+#define PMIC4_SMPS_MODE_AUTO			6
+#define PMIC4_SMPS_MODE_PWM			7
+
+#define PMIC4_BOB_MODE_PASS			0
+#define PMIC4_BOB_MODE_PFM			1
+#define PMIC4_BOB_MODE_AUTO			2
+#define PMIC4_BOB_MODE_PWM			3
+
+/**
+ * struct rpmh_vreg_hw_data - RPMh regulator hardware configurations
+ * @regulator_type:		RPMh accelerator type used to manage this
+ *				regulator
+ * @ops:			Pointer to regulator ops callback structure
+ * @voltage_range:		The single range of voltages supported by this
+ *				PMIC regulator type
+ * @n_voltages:			The number of unique voltage set points defined
+ *				by voltage_range
+ * @hpm_min_load_uA:		Minimum load current in microamps that requires
+ *				high power mode (HPM) operation.  This is used
+ *				for LDO hardware type regulators only.
+ * @pmic_mode_map:		Array indexed by regulator framework mode
+ *				containing PMIC hardware modes.  Must be large
+ *				enough to index all framework modes supported
+ *				by this regulator hardware type.
+ * @of_map_mode:		Maps an RPMH_REGULATOR_MODE_* mode value defined
+ *				in device tree to a regulator framework mode
+ */
+struct rpmh_vreg_hw_data {
+	enum rpmh_regulator_type		regulator_type;
+	const struct regulator_ops		*ops;
+	const struct regulator_linear_range	voltage_range;
+	int					n_voltages;
+	int					hpm_min_load_uA;
+	const int				*pmic_mode_map;
+	unsigned int			      (*of_map_mode)(unsigned int mode);
+};
+
+/**
+ * struct rpmh_vreg - individual RPMh regulator data structure encapsulating a
+ *		single regulator device
+ * @dev:			Device pointer for the top-level PMIC RPMh
+ *				regulator parent device.  This is used as a
+ *				handle in RPMh write requests.
+ * @addr:			Base address of the regulator resource within
+ *				an RPMh accelerator
+ * @rdesc:			Regulator descriptor
+ * @hw_data:			PMIC regulator configuration data for this RPMh
+ *				regulator
+ * @always_wait_for_ack:	Boolean flag indicating if a request must always
+ *				wait for an ACK from RPMh before continuing even
+ *				if it corresponds to a strictly lower power
+ *				state (e.g. enabled --> disabled).
+ * @enabled:			Flag indicating if the regulator is enabled or
+ *				not
+ * @bypassed:			Boolean indicating if the regulator is in
+ *				bypass (pass-through) mode or not.  This is
+ *				only used by BOB rpmh-regulator resources.
+ * @voltage_selector:		Selector used for get_voltage_sel() and
+ *				set_voltage_sel() callbacks
+ * @mode:			RPMh VRM regulator current framework mode
+ */
+struct rpmh_vreg {
+	struct device			*dev;
+	u32				addr;
+	struct regulator_desc		rdesc;
+	const struct rpmh_vreg_hw_data	*hw_data;
+	bool				always_wait_for_ack;
+
+	int				enabled;
+	bool				bypassed;
+	int				voltage_selector;
+	unsigned int			mode;
+};
+
+/**
+ * struct rpmh_vreg_init_data - initialization data for an RPMh regulator
+ * @name:			Name for the regulator which also corresponds
+ *				to the device tree subnode name of the regulator
+ * @resource_name:		RPMh regulator resource name format string.
+ *				This must include exactly one field: '%s' which
+ *				is filled at run-time with the PMIC ID provided
+ *				by device tree property qcom,pmic-id.  Example:
+ *				"ldo%s1" for RPMh resource "ldoa1".
+ * @supply_name:		Parent supply regulator name
+ * @hw_data:			Configuration data for this PMIC regulator type
+ */
+struct rpmh_vreg_init_data {
+	const char			*name;
+	const char			*resource_name;
+	const char			*supply_name;
+	const struct rpmh_vreg_hw_data	*hw_data;
+};
+
+/**
+ * rpmh_regulator_send_request() - send the request to RPMh
+ * @vreg:		Pointer to the RPMh regulator
+ * @cmd:		Pointer to the RPMh command to send
+ * @wait_for_ack:	Boolean indicating if execution must wait until the
+ *			request has been acknowledged as complete
+ *
+ * Return: 0 on success, errno on failure
+ */
+static int rpmh_regulator_send_request(struct rpmh_vreg *vreg,
+			struct tcs_cmd *cmd, bool wait_for_ack)
+{
+	int ret;
+
+	if (wait_for_ack || vreg->always_wait_for_ack)
+		ret = rpmh_write(vreg->dev, RPMH_ACTIVE_ONLY_STATE, cmd, 1);
+	else
+		ret = rpmh_write_async(vreg->dev, RPMH_ACTIVE_ONLY_STATE, cmd,
+					1);
+
+	return ret;
+}
+
+static int _rpmh_regulator_vrm_set_voltage_sel(struct regulator_dev *rdev,
+				unsigned int selector, bool wait_for_ack)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	struct tcs_cmd cmd = {
+		.addr = vreg->addr + RPMH_REGULATOR_REG_VRM_VOLTAGE,
+	};
+	int ret;
+
+	/* VRM voltage control register is set with voltage in millivolts. */
+	cmd.data = DIV_ROUND_UP(regulator_list_voltage_linear_range(rdev,
+							selector), 1000);
+
+	ret = rpmh_regulator_send_request(vreg, &cmd, wait_for_ack);
+	if (!ret)
+		vreg->voltage_selector = selector;
+
+	return ret;
+}
+
+static int rpmh_regulator_vrm_set_voltage_sel(struct regulator_dev *rdev,
+					unsigned int selector)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	if (vreg->enabled == -EINVAL) {
+		/*
+		 * Cache the voltage and send it later when the regulator is
+		 * enabled or disabled.
+		 */
+		vreg->voltage_selector = selector;
+		return 0;
+	}
+
+	return _rpmh_regulator_vrm_set_voltage_sel(rdev, selector,
+					selector > vreg->voltage_selector);
+}
+
+static int rpmh_regulator_vrm_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	return vreg->voltage_selector;
+}
+
+static int rpmh_regulator_is_enabled(struct regulator_dev *rdev)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	return vreg->enabled;
+}
+
+static int rpmh_regulator_set_enable_state(struct regulator_dev *rdev,
+					bool enable)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	struct tcs_cmd cmd = {
+		.addr = vreg->addr + RPMH_REGULATOR_REG_ENABLE,
+		.data = enable,
+	};
+	int ret;
+
+	if (vreg->enabled == -EINVAL &&
+	    vreg->voltage_selector != -ENOTRECOVERABLE) {
+		ret = _rpmh_regulator_vrm_set_voltage_sel(rdev,
+						vreg->voltage_selector, true);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = rpmh_regulator_send_request(vreg, &cmd, enable);
+	if (!ret)
+		vreg->enabled = enable;
+
+	return ret;
+}
+
+static int rpmh_regulator_enable(struct regulator_dev *rdev)
+{
+	return rpmh_regulator_set_enable_state(rdev, true);
+}
+
+static int rpmh_regulator_disable(struct regulator_dev *rdev)
+{
+	return rpmh_regulator_set_enable_state(rdev, false);
+}
+
+static int rpmh_regulator_vrm_set_mode_bypass(struct rpmh_vreg *vreg,
+					unsigned int mode, bool bypassed)
+{
+	struct tcs_cmd cmd = {
+		.addr = vreg->addr + RPMH_REGULATOR_REG_VRM_MODE,
+	};
+	int pmic_mode;
+
+	if (mode > REGULATOR_MODE_STANDBY)
+		return -EINVAL;
+
+	pmic_mode = vreg->hw_data->pmic_mode_map[mode];
+	if (pmic_mode < 0)
+		return pmic_mode;
+
+	if (bypassed)
+		cmd.data = PMIC4_BOB_MODE_PASS;
+	else
+		cmd.data = pmic_mode;
+
+	return rpmh_regulator_send_request(vreg, &cmd, true);
+}
+
+static int rpmh_regulator_vrm_set_mode(struct regulator_dev *rdev,
+					unsigned int mode)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	int ret;
+
+	if (mode == vreg->mode)
+		return 0;
+
+	ret = rpmh_regulator_vrm_set_mode_bypass(vreg, mode, vreg->bypassed);
+	if (!ret)
+		vreg->mode = mode;
+
+	return ret;
+}
+
+static unsigned int rpmh_regulator_vrm_get_mode(struct regulator_dev *rdev)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	return vreg->mode;
+}
+
+/**
+ * rpmh_regulator_vrm_set_load() - set the regulator mode based upon the load
+ *		current requested
+ * @rdev:		Regulator device pointer for the rpmh-regulator
+ * @load_uA:		Aggregated load current in microamps
+ *
+ * This function is used in the regulator_ops for VRM type RPMh regulator
+ * devices.
+ *
+ * Return: 0 on success, errno on failure
+ */
+static int rpmh_regulator_vrm_set_load(struct regulator_dev *rdev, int load_uA)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	unsigned int mode;
+
+	if (load_uA >= vreg->hw_data->hpm_min_load_uA)
+		mode = REGULATOR_MODE_NORMAL;
+	else
+		mode = REGULATOR_MODE_IDLE;
+
+	return rpmh_regulator_vrm_set_mode(rdev, mode);
+}
+
+static int rpmh_regulator_vrm_set_bypass(struct regulator_dev *rdev,
+				bool enable)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	int ret;
+
+	if (vreg->bypassed == enable)
+		return 0;
+
+	ret = rpmh_regulator_vrm_set_mode_bypass(vreg, vreg->mode, enable);
+	if (!ret)
+		vreg->bypassed = enable;
+
+	return ret;
+}
+
+static int rpmh_regulator_vrm_get_bypass(struct regulator_dev *rdev,
+				bool *enable)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	*enable = vreg->bypassed;
+
+	return 0;
+}
+
+static const struct regulator_ops rpmh_regulator_vrm_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+	.set_voltage_sel	= rpmh_regulator_vrm_set_voltage_sel,
+	.get_voltage_sel	= rpmh_regulator_vrm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_mode		= rpmh_regulator_vrm_set_mode,
+	.get_mode		= rpmh_regulator_vrm_get_mode,
+};
+
+static const struct regulator_ops rpmh_regulator_vrm_drms_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+	.set_voltage_sel	= rpmh_regulator_vrm_set_voltage_sel,
+	.get_voltage_sel	= rpmh_regulator_vrm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_mode		= rpmh_regulator_vrm_set_mode,
+	.get_mode		= rpmh_regulator_vrm_get_mode,
+	.set_load		= rpmh_regulator_vrm_set_load,
+};
+
+static const struct regulator_ops rpmh_regulator_vrm_bypass_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+	.set_voltage_sel	= rpmh_regulator_vrm_set_voltage_sel,
+	.get_voltage_sel	= rpmh_regulator_vrm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_mode		= rpmh_regulator_vrm_set_mode,
+	.get_mode		= rpmh_regulator_vrm_get_mode,
+	.set_bypass		= rpmh_regulator_vrm_set_bypass,
+	.get_bypass		= rpmh_regulator_vrm_get_bypass,
+};
+
+static const struct regulator_ops rpmh_regulator_xob_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+};
+
+/**
+ * rpmh_regulator_init_vreg() - initialize all attributes of an rpmh-regulator
+ * vreg:		Pointer to the individual rpmh-regulator resource
+ * dev:			Pointer to the top level rpmh-regulator PMIC device
+ * node:		Pointer to the individual rpmh-regulator resource
+ *			device node
+ * pmic_id:		String used to identify the top level rpmh-regulator
+ *			PMIC device on the board
+ * pmic_rpmh_data:	Pointer to a null-terminated array of rpmh-regulator
+ *			resources defined for the top level PMIC device
+ *
+ * Return: 0 on success, errno on failure
+ */
+static int rpmh_regulator_init_vreg(struct rpmh_vreg *vreg, struct device *dev,
+			struct device_node *node, const char *pmic_id,
+			const struct rpmh_vreg_init_data *pmic_rpmh_data)
+{
+	struct regulator_config reg_config = {};
+	char rpmh_resource_name[20] = "";
+	const struct rpmh_vreg_init_data *rpmh_data;
+	struct regulator_init_data *init_data;
+	struct regulator_dev *rdev;
+	int ret;
+
+	vreg->dev = dev;
+
+	for (rpmh_data = pmic_rpmh_data; rpmh_data->name; rpmh_data++)
+		if (!strcmp(rpmh_data->name, node->name))
+			break;
+
+	if (!rpmh_data->name) {
+		dev_err(dev, "Unknown regulator %s\n", node->name);
+		return -EINVAL;
+	}
+
+	scnprintf(rpmh_resource_name, sizeof(rpmh_resource_name),
+		rpmh_data->resource_name, pmic_id);
+
+	vreg->addr = cmd_db_read_addr(rpmh_resource_name);
+	if (!vreg->addr) {
+		dev_err(dev, "%s: could not find RPMh address for resource %s\n",
+			node->name, rpmh_resource_name);
+		return -ENODEV;
+	}
+
+	vreg->rdesc.name = rpmh_data->name;
+	vreg->rdesc.supply_name = rpmh_data->supply_name;
+	vreg->hw_data = rpmh_data->hw_data;
+
+	vreg->enabled = -EINVAL;
+	vreg->voltage_selector = -ENOTRECOVERABLE;
+	vreg->mode = REGULATOR_MODE_INVALID;
+
+	if (rpmh_data->hw_data->n_voltages) {
+		vreg->rdesc.linear_ranges = &rpmh_data->hw_data->voltage_range;
+		vreg->rdesc.n_linear_ranges = 1;
+		vreg->rdesc.n_voltages = rpmh_data->hw_data->n_voltages;
+	}
+
+	vreg->always_wait_for_ack = of_property_read_bool(node,
+						"qcom,always-wait-for-ack");
+
+	vreg->rdesc.owner	= THIS_MODULE;
+	vreg->rdesc.type	= REGULATOR_VOLTAGE;
+	vreg->rdesc.ops		= vreg->hw_data->ops;
+	vreg->rdesc.of_map_mode	= vreg->hw_data->of_map_mode;
+
+	init_data = of_get_regulator_init_data(dev, node, &vreg->rdesc);
+	if (!init_data)
+		return -ENOMEM;
+
+	if (rpmh_data->hw_data->regulator_type == XOB &&
+	    init_data->constraints.min_uV &&
+	    init_data->constraints.min_uV == init_data->constraints.max_uV) {
+		vreg->rdesc.fixed_uV = init_data->constraints.min_uV;
+		vreg->rdesc.n_voltages = 1;
+	}
+
+	reg_config.dev		= dev;
+	reg_config.init_data	= init_data;
+	reg_config.of_node	= node;
+	reg_config.driver_data	= vreg;
+
+	rdev = devm_regulator_register(dev, &vreg->rdesc, &reg_config);
+	if (IS_ERR(rdev)) {
+		ret = PTR_ERR(rdev);
+		dev_err(dev, "%s: devm_regulator_register() failed, ret=%d\n",
+			node->name, ret);
+		return ret;
+	}
+
+	dev_dbg(dev, "%s regulator registered for RPMh resource %s @ 0x%05X\n",
+		node->name, rpmh_resource_name, vreg->addr);
+
+	return 0;
+}
+
+static const int pmic_mode_map_pmic4_ldo[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = PMIC4_LDO_MODE_RETENTION,
+	[REGULATOR_MODE_IDLE]    = PMIC4_LDO_MODE_LPM,
+	[REGULATOR_MODE_NORMAL]  = PMIC4_LDO_MODE_HPM,
+	[REGULATOR_MODE_FAST]    = -EINVAL,
+};
+
+static unsigned int rpmh_regulator_pmic4_ldo_of_map_mode(unsigned int rpmh_mode)
+{
+	unsigned int mode;
+
+	switch (rpmh_mode) {
+	case RPMH_REGULATOR_MODE_HPM:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case RPMH_REGULATOR_MODE_LPM:
+		mode = REGULATOR_MODE_IDLE;
+		break;
+	case RPMH_REGULATOR_MODE_RET:
+		mode = REGULATOR_MODE_STANDBY;
+		break;
+	default:
+		mode = REGULATOR_MODE_INVALID;
+	}
+
+	return mode;
+}
+
+static const int pmic_mode_map_pmic4_smps[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = PMIC4_SMPS_MODE_RETENTION,
+	[REGULATOR_MODE_IDLE]    = PMIC4_SMPS_MODE_PFM,
+	[REGULATOR_MODE_NORMAL]  = PMIC4_SMPS_MODE_AUTO,
+	[REGULATOR_MODE_FAST]    = PMIC4_SMPS_MODE_PWM,
+};
+
+static unsigned int
+rpmh_regulator_pmic4_smps_of_map_mode(unsigned int rpmh_mode)
+{
+	unsigned int mode;
+
+	switch (rpmh_mode) {
+	case RPMH_REGULATOR_MODE_HPM:
+		mode = REGULATOR_MODE_FAST;
+		break;
+	case RPMH_REGULATOR_MODE_AUTO:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case RPMH_REGULATOR_MODE_LPM:
+		mode = REGULATOR_MODE_IDLE;
+		break;
+	case RPMH_REGULATOR_MODE_RET:
+		mode = REGULATOR_MODE_STANDBY;
+		break;
+	default:
+		mode = REGULATOR_MODE_INVALID;
+	}
+
+	return mode;
+}
+
+static const int pmic_mode_map_pmic4_bob[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = -EINVAL,
+	[REGULATOR_MODE_IDLE]    = PMIC4_BOB_MODE_PFM,
+	[REGULATOR_MODE_NORMAL]  = PMIC4_BOB_MODE_AUTO,
+	[REGULATOR_MODE_FAST]    = PMIC4_BOB_MODE_PWM,
+};
+
+static unsigned int rpmh_regulator_pmic4_bob_of_map_mode(unsigned int rpmh_mode)
+{
+	unsigned int mode;
+
+	switch (rpmh_mode) {
+	case RPMH_REGULATOR_MODE_HPM:
+		mode = REGULATOR_MODE_FAST;
+		break;
+	case RPMH_REGULATOR_MODE_AUTO:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case RPMH_REGULATOR_MODE_LPM:
+		mode = REGULATOR_MODE_IDLE;
+		break;
+	default:
+		mode = REGULATOR_MODE_INVALID;
+	}
+
+	return mode;
+}
+
+static const struct rpmh_vreg_hw_data pmic4_pldo = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(1664000, 0, 255, 8000),
+	.n_voltages = 256,
+	.hpm_min_load_uA = 10000,
+	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_pldo_lv = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(1256000, 0, 127, 8000),
+	.n_voltages = 128,
+	.hpm_min_load_uA = 10000,
+	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_nldo = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(312000, 0, 127, 8000),
+	.n_voltages = 128,
+	.hpm_min_load_uA = 30000,
+	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_hfsmps3 = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
+	.n_voltages = 216,
+	.pmic_mode_map = pmic_mode_map_pmic4_smps,
+	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_ftsmps426 = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 258, 4000),
+	.n_voltages = 259,
+	.pmic_mode_map = pmic_mode_map_pmic4_smps,
+	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_bob = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_bypass_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(1824000, 0, 83, 32000),
+	.n_voltages = 84,
+	.pmic_mode_map = pmic_mode_map_pmic4_bob,
+	.of_map_mode = rpmh_regulator_pmic4_bob_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_lvs = {
+	.regulator_type = XOB,
+	.ops = &rpmh_regulator_xob_ops,
+	/* LVS hardware does not support voltage or mode configuration. */
+};
+
+#define RPMH_VREG(_name, _resource_name, _hw_data, _supply_name) \
+{ \
+	.name		= _name, \
+	.resource_name	= _resource_name, \
+	.hw_data	= _hw_data, \
+	.supply_name	= _supply_name, \
+}
+
+static const struct rpmh_vreg_init_data pm8998_vreg_data[] = {
+	RPMH_VREG("smps1",  "smp%s1",  &pmic4_ftsmps426, "vdd-s1"),
+	RPMH_VREG("smps2",  "smp%s2",  &pmic4_ftsmps426, "vdd-s2"),
+	RPMH_VREG("smps3",  "smp%s3",  &pmic4_hfsmps3,   "vdd-s3"),
+	RPMH_VREG("smps4",  "smp%s4",  &pmic4_hfsmps3,   "vdd-s4"),
+	RPMH_VREG("smps5",  "smp%s5",  &pmic4_hfsmps3,   "vdd-s5"),
+	RPMH_VREG("smps6",  "smp%s6",  &pmic4_ftsmps426, "vdd-s6"),
+	RPMH_VREG("smps7",  "smp%s7",  &pmic4_ftsmps426, "vdd-s7"),
+	RPMH_VREG("smps8",  "smp%s8",  &pmic4_ftsmps426, "vdd-s8"),
+	RPMH_VREG("smps9",  "smp%s9",  &pmic4_ftsmps426, "vdd-s9"),
+	RPMH_VREG("smps10", "smp%s10", &pmic4_ftsmps426, "vdd-s10"),
+	RPMH_VREG("smps11", "smp%s11", &pmic4_ftsmps426, "vdd-s11"),
+	RPMH_VREG("smps12", "smp%s12", &pmic4_ftsmps426, "vdd-s12"),
+	RPMH_VREG("smps13", "smp%s13", &pmic4_ftsmps426, "vdd-s13"),
+	RPMH_VREG("ldo1",   "ldo%s1",  &pmic4_nldo,      "vdd-l1-l27"),
+	RPMH_VREG("ldo2",   "ldo%s2",  &pmic4_nldo,      "vdd-l2-l8-l17"),
+	RPMH_VREG("ldo3",   "ldo%s3",  &pmic4_nldo,      "vdd-l3-l11"),
+	RPMH_VREG("ldo4",   "ldo%s4",  &pmic4_nldo,      "vdd-l4-l5"),
+	RPMH_VREG("ldo5",   "ldo%s5",  &pmic4_nldo,      "vdd-l4-l5"),
+	RPMH_VREG("ldo6",   "ldo%s6",  &pmic4_pldo,      "vdd-l6"),
+	RPMH_VREG("ldo7",   "ldo%s7",  &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo8",   "ldo%s8",  &pmic4_nldo,      "vdd-l2-l8-l17"),
+	RPMH_VREG("ldo9",   "ldo%s9",  &pmic4_pldo,      "vdd-l9"),
+	RPMH_VREG("ldo10",  "ldo%s10", &pmic4_pldo,      "vdd-l10-l23-l25"),
+	RPMH_VREG("ldo11",  "ldo%s11", &pmic4_nldo,      "vdd-l3-l11"),
+	RPMH_VREG("ldo12",  "ldo%s12", &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo13",  "ldo%s13", &pmic4_pldo,      "vdd-l13-l19-l21"),
+	RPMH_VREG("ldo14",  "ldo%s14", &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo15",  "ldo%s15", &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo16",  "ldo%s16", &pmic4_pldo,      "vdd-l16-l28"),
+	RPMH_VREG("ldo17",  "ldo%s17", &pmic4_nldo,      "vdd-l2-l8-l17"),
+	RPMH_VREG("ldo18",  "ldo%s18", &pmic4_pldo,      "vdd-l18-l22"),
+	RPMH_VREG("ldo19",  "ldo%s19", &pmic4_pldo,      "vdd-l13-l19-l21"),
+	RPMH_VREG("ldo20",  "ldo%s20", &pmic4_pldo,      "vdd-l20-l24"),
+	RPMH_VREG("ldo21",  "ldo%s21", &pmic4_pldo,      "vdd-l13-l19-l21"),
+	RPMH_VREG("ldo22",  "ldo%s22", &pmic4_pldo,      "vdd-l18-l22"),
+	RPMH_VREG("ldo23",  "ldo%s23", &pmic4_pldo,      "vdd-l10-l23-l25"),
+	RPMH_VREG("ldo24",  "ldo%s24", &pmic4_pldo,      "vdd-l20-l24"),
+	RPMH_VREG("ldo25",  "ldo%s25", &pmic4_pldo,      "vdd-l10-l23-l25"),
+	RPMH_VREG("ldo26",  "ldo%s26", &pmic4_nldo,      "vdd-l26"),
+	RPMH_VREG("ldo27",  "ldo%s27", &pmic4_nldo,      "vdd-l1-l27"),
+	RPMH_VREG("ldo28",  "ldo%s28", &pmic4_pldo,      "vdd-l16-l28"),
+	RPMH_VREG("lvs1",   "vs%s1",   &pmic4_lvs,       "vin-lvs-1-2"),
+	RPMH_VREG("lvs2",   "vs%s2",   &pmic4_lvs,       "vin-lvs-1-2"),
+	{},
+};
+
+static const struct rpmh_vreg_init_data pmi8998_vreg_data[] = {
+	RPMH_VREG("bob",    "bob%s1",  &pmic4_bob,       "vdd-bob"),
+	{},
+};
+
+static const struct rpmh_vreg_init_data pm8005_vreg_data[] = {
+	RPMH_VREG("smps1",  "smp%s1",  &pmic4_ftsmps426, "vdd-s1"),
+	RPMH_VREG("smps2",  "smp%s2",  &pmic4_ftsmps426, "vdd-s2"),
+	RPMH_VREG("smps3",  "smp%s3",  &pmic4_ftsmps426, "vdd-s3"),
+	RPMH_VREG("smps4",  "smp%s4",  &pmic4_ftsmps426, "vdd-s4"),
+	{},
+};
+
+static int rpmh_regulator_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct rpmh_vreg_init_data *vreg_data;
+	struct device_node *node;
+	struct rpmh_vreg *vreg;
+	const char *pmic_id;
+	int ret;
+
+	vreg_data = of_device_get_match_data(dev);
+	if (!vreg_data)
+		return -ENODEV;
+
+	ret = of_property_read_string(dev->of_node, "qcom,pmic-id", &pmic_id);
+	if (ret < 0) {
+		dev_err(dev, "qcom,pmic-id missing in DT node\n");
+		return ret;
+	}
+
+	for_each_available_child_of_node(dev->of_node, node) {
+		vreg = devm_kzalloc(dev, sizeof(*vreg), GFP_KERNEL);
+		if (!vreg) {
+			of_node_put(node);
+			return -ENOMEM;
+		}
+
+		ret = rpmh_regulator_init_vreg(vreg, dev, node, pmic_id,
+						vreg_data);
+		if (ret < 0) {
+			of_node_put(node);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static const struct of_device_id rpmh_regulator_match_table[] = {
+	{
+		.compatible = "qcom,pm8998-rpmh-regulators",
+		.data = pm8998_vreg_data,
+	},
+	{
+		.compatible = "qcom,pmi8998-rpmh-regulators",
+		.data = pmi8998_vreg_data,
+	},
+	{
+		.compatible = "qcom,pm8005-rpmh-regulators",
+		.data = pm8005_vreg_data,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, rpmh_regulator_match_table);
+
+static struct platform_driver rpmh_regulator_driver = {
+	.driver = {
+		.name = "qcom-rpmh-regulator",
+		.of_match_table	= of_match_ptr(rpmh_regulator_match_table),
+	},
+	.probe = rpmh_regulator_probe,
+};
+module_platform_driver(rpmh_regulator_driver);
+
+MODULE_DESCRIPTION("Qualcomm RPMh regulator driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/qcom_spmi-regulator.c b/drivers/regulator/qcom_spmi-regulator.c
index 9817f1a75342..53a61fb65642 100644
--- a/drivers/regulator/qcom_spmi-regulator.c
+++ b/drivers/regulator/qcom_spmi-regulator.c
@@ -1060,7 +1060,7 @@ static irqreturn_t spmi_regulator_vs_ocp_isr(int irq, void *data)
 #define SAW3_AVS_CTL_TGGL_MASK	0x8000000
 #define SAW3_AVS_CTL_CLEAR_MASK	0x7efc00
 
-static struct regmap *saw_regmap = NULL;
+static struct regmap *saw_regmap;
 
 static void spmi_saw_set_vdd(void *data)
 {
@@ -1728,7 +1728,7 @@ static const struct spmi_regulator_data pmi8994_regulators[] = {
 	{ "s2", 0x1700, "vdd_s2", },
 	{ "s3", 0x1a00, "vdd_s3", },
 	{ "l1", 0x4000, "vdd_l1", },
-        { }
+	{ }
 };
 
 static const struct of_device_id qcom_spmi_regulator_match[] = {
@@ -1752,7 +1752,8 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 	const char *name;
 	struct device *dev = &pdev->dev;
 	struct device_node *node = pdev->dev.of_node;
-	struct device_node *syscon;
+	struct device_node *syscon, *reg_node;
+	struct property *reg_prop;
 	int ret, lenp;
 	struct list_head *vreg_list;
 
@@ -1774,16 +1775,19 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 		syscon = of_parse_phandle(node, "qcom,saw-reg", 0);
 		saw_regmap = syscon_node_to_regmap(syscon);
 		of_node_put(syscon);
-		if (IS_ERR(regmap))
+		if (IS_ERR(saw_regmap))
 			dev_err(dev, "ERROR reading SAW regmap\n");
 	}
 
 	for (reg = match->data; reg->name; reg++) {
 
-		if (saw_regmap && \
-		    of_find_property(of_find_node_by_name(node, reg->name), \
-				     "qcom,saw-slave", &lenp)) {
-			continue;
+		if (saw_regmap) {
+			reg_node = of_get_child_by_name(node, reg->name);
+			reg_prop = of_find_property(reg_node, "qcom,saw-slave",
+						    &lenp);
+			of_node_put(reg_node);
+			if (reg_prop)
+				continue;
 		}
 
 		vreg = devm_kzalloc(dev, sizeof(*vreg), GFP_KERNEL);
@@ -1816,13 +1820,17 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 		if (ret)
 			continue;
 
-		if (saw_regmap && \
-		    of_find_property(of_find_node_by_name(node, reg->name), \
-				     "qcom,saw-leader", &lenp)) {
-			spmi_saw_ops = *(vreg->desc.ops);
-			spmi_saw_ops.set_voltage_sel = \
-				spmi_regulator_saw_set_voltage;
-			vreg->desc.ops = &spmi_saw_ops;
+		if (saw_regmap) {
+			reg_node = of_get_child_by_name(node, reg->name);
+			reg_prop = of_find_property(reg_node, "qcom,saw-leader",
+						    &lenp);
+			of_node_put(reg_node);
+			if (reg_prop) {
+				spmi_saw_ops = *(vreg->desc.ops);
+				spmi_saw_ops.set_voltage_sel =
+					spmi_regulator_saw_set_voltage;
+				vreg->desc.ops = &spmi_saw_ops;
+			}
 		}
 
 		config.dev = dev;
diff --git a/drivers/regulator/s2mpa01.c b/drivers/regulator/s2mpa01.c
index 48f0ca90743c..095d25f3d2ea 100644
--- a/drivers/regulator/s2mpa01.c
+++ b/drivers/regulator/s2mpa01.c
@@ -1,13 +1,7 @@
-/*
- * Copyright (c) 2013 Samsung Electronics Co., Ltd
- *		http://www.samsung.com
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2013 Samsung Electronics Co., Ltd
+//		http://www.samsung.com
 
 #include <linux/bug.h>
 #include <linux/err.h>
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index d1207ec683db..5bb6f4ca48db 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -1,20 +1,7 @@
-/*
- * s2mps11.c
- *
- * Copyright (c) 2012-2014 Samsung Electronics Co., Ltd
- *              http://www.samsung.com
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2012-2014 Samsung Electronics Co., Ltd
+//              http://www.samsung.com
 
 #include <linux/bug.h>
 #include <linux/err.h>
diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index 0cbc980753c2..667d16dc83ce 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -1,15 +1,7 @@
-/*
- * s5m8767.c
- *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd
- *              http://www.samsung.com
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2011 Samsung Electronics Co., Ltd
+//              http://www.samsung.com
 
 #include <linux/err.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index fc12badf3805..d84fab616abf 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -232,6 +232,8 @@ static int tps65217_regulator_probe(struct platform_device *pdev)
 	tps->strobes = devm_kcalloc(&pdev->dev,
 				    TPS65217_NUM_REGULATOR, sizeof(u8),
 				    GFP_KERNEL);
+	if (!tps->strobes)
+		return -ENOMEM;
 
 	platform_set_drvdata(pdev, tps);
 
diff --git a/drivers/regulator/uniphier-regulator.c b/drivers/regulator/uniphier-regulator.c
new file mode 100644
index 000000000000..abf22acbd13e
--- /dev/null
+++ b/drivers/regulator/uniphier-regulator.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Regulator controller driver for UniPhier SoC
+// Copyright 2018 Socionext Inc.
+// Author: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
+
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/of_regulator.h>
+#include <linux/reset.h>
+
+#define MAX_CLKS	2
+#define MAX_RSTS	2
+
+struct uniphier_regulator_soc_data {
+	int nclks;
+	const char * const *clock_names;
+	int nrsts;
+	const char * const *reset_names;
+	const struct regulator_desc *desc;
+	const struct regmap_config *regconf;
+};
+
+struct uniphier_regulator_priv {
+	struct clk_bulk_data clk[MAX_CLKS];
+	struct reset_control *rst[MAX_RSTS];
+	const struct uniphier_regulator_soc_data *data;
+};
+
+static struct regulator_ops uniphier_regulator_ops = {
+	.enable     = regulator_enable_regmap,
+	.disable    = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+};
+
+static int uniphier_regulator_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct uniphier_regulator_priv *priv;
+	struct regulator_config config = { };
+	struct regulator_dev *rdev;
+	struct regmap *regmap;
+	struct resource *res;
+	void __iomem *base;
+	const char *name;
+	int i, ret, nr;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->data = of_device_get_match_data(dev);
+	if (WARN_ON(!priv->data))
+		return -EINVAL;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	for (i = 0; i < priv->data->nclks; i++)
+		priv->clk[i].id = priv->data->clock_names[i];
+	ret = devm_clk_bulk_get(dev, priv->data->nclks, priv->clk);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < priv->data->nrsts; i++) {
+		name = priv->data->reset_names[i];
+		priv->rst[i] = devm_reset_control_get_shared(dev, name);
+		if (IS_ERR(priv->rst[i]))
+			return PTR_ERR(priv->rst[i]);
+	}
+
+	ret = clk_bulk_prepare_enable(priv->data->nclks, priv->clk);
+	if (ret)
+		return ret;
+
+	for (nr = 0; nr < priv->data->nrsts; nr++) {
+		ret = reset_control_deassert(priv->rst[nr]);
+		if (ret)
+			goto out_rst_assert;
+	}
+
+	regmap = devm_regmap_init_mmio(dev, base, priv->data->regconf);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	config.dev = dev;
+	config.driver_data = priv;
+	config.of_node = dev->of_node;
+	config.regmap = regmap;
+	config.init_data = of_get_regulator_init_data(dev, dev->of_node,
+						      priv->data->desc);
+	rdev = devm_regulator_register(dev, priv->data->desc, &config);
+	if (IS_ERR(rdev)) {
+		ret = PTR_ERR(rdev);
+		goto out_rst_assert;
+	}
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+out_rst_assert:
+	while (nr--)
+		reset_control_assert(priv->rst[nr]);
+
+	clk_bulk_disable_unprepare(priv->data->nclks, priv->clk);
+
+	return ret;
+}
+
+static int uniphier_regulator_remove(struct platform_device *pdev)
+{
+	struct uniphier_regulator_priv *priv = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < priv->data->nrsts; i++)
+		reset_control_assert(priv->rst[i]);
+
+	clk_bulk_disable_unprepare(priv->data->nclks, priv->clk);
+
+	return 0;
+}
+
+/* USB3 controller data */
+#define USB3VBUS_OFFSET		0x0
+#define USB3VBUS_REG		BIT(4)
+#define USB3VBUS_REG_EN		BIT(3)
+static const struct regulator_desc uniphier_usb3_regulator_desc = {
+	.name = "vbus",
+	.of_match = of_match_ptr("vbus"),
+	.ops = &uniphier_regulator_ops,
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+	.enable_reg  = USB3VBUS_OFFSET,
+	.enable_mask = USB3VBUS_REG_EN | USB3VBUS_REG,
+	.enable_val  = USB3VBUS_REG_EN | USB3VBUS_REG,
+	.disable_val = USB3VBUS_REG_EN,
+};
+
+static const struct regmap_config uniphier_usb3_regulator_regconf = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = 1,
+};
+
+static const char * const uniphier_pro4_clock_reset_names[] = {
+	"gio", "link",
+};
+
+static const struct uniphier_regulator_soc_data uniphier_pro4_usb3_data = {
+	.nclks = ARRAY_SIZE(uniphier_pro4_clock_reset_names),
+	.clock_names = uniphier_pro4_clock_reset_names,
+	.nrsts = ARRAY_SIZE(uniphier_pro4_clock_reset_names),
+	.reset_names = uniphier_pro4_clock_reset_names,
+	.desc = &uniphier_usb3_regulator_desc,
+	.regconf = &uniphier_usb3_regulator_regconf,
+};
+
+static const char * const uniphier_pxs2_clock_reset_names[] = {
+	"link",
+};
+
+static const struct uniphier_regulator_soc_data uniphier_pxs2_usb3_data = {
+	.nclks = ARRAY_SIZE(uniphier_pxs2_clock_reset_names),
+	.clock_names = uniphier_pxs2_clock_reset_names,
+	.nrsts = ARRAY_SIZE(uniphier_pxs2_clock_reset_names),
+	.reset_names = uniphier_pxs2_clock_reset_names,
+	.desc = &uniphier_usb3_regulator_desc,
+	.regconf = &uniphier_usb3_regulator_regconf,
+};
+
+static const struct of_device_id uniphier_regulator_match[] = {
+	/* USB VBUS */
+	{
+		.compatible = "socionext,uniphier-pro4-usb3-regulator",
+		.data = &uniphier_pro4_usb3_data,
+	},
+	{
+		.compatible = "socionext,uniphier-pxs2-usb3-regulator",
+		.data = &uniphier_pxs2_usb3_data,
+	},
+	{
+		.compatible = "socionext,uniphier-ld20-usb3-regulator",
+		.data = &uniphier_pxs2_usb3_data,
+	},
+	{
+		.compatible = "socionext,uniphier-pxs3-usb3-regulator",
+		.data = &uniphier_pxs2_usb3_data,
+	},
+	{ /* Sentinel */ },
+};
+
+static struct platform_driver uniphier_regulator_driver = {
+	.probe = uniphier_regulator_probe,
+	.remove = uniphier_regulator_remove,
+	.driver = {
+		.name  = "uniphier-regulator",
+		.of_match_table = uniphier_regulator_match,
+	},
+};
+module_platform_driver(uniphier_regulator_driver);
+
+MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>");
+MODULE_DESCRIPTION("UniPhier Regulator Controller Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 6d4012dd6922..bac1eeb3d312 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -265,8 +265,10 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 			return err;
 
 		/* full-function RTCs won't have such missing fields */
-		if (rtc_valid_tm(&alarm->time) == 0)
+		if (rtc_valid_tm(&alarm->time) == 0) {
+			rtc_add_offset(rtc, &alarm->time);
 			return 0;
+		}
 
 		/* get the "after" timestamp, to detect wrapped fields */
 		err = rtc_read_time(rtc, &now);
@@ -409,7 +411,6 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 	if (err)
 		return err;
 
-	rtc_subtract_offset(rtc, &alarm->time);
 	scheduled = rtc_tm_to_time64(&alarm->time);
 
 	/* Make sure we're not setting alarms in the past */
@@ -426,6 +427,8 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 	 * over right here, before we set the alarm.
 	 */
 
+	rtc_subtract_offset(rtc, &alarm->time);
+
 	if (!rtc->ops)
 		err = -ENODEV;
 	else if (!rtc->ops->set_alarm)
@@ -467,7 +470,6 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 
 	mutex_unlock(&rtc->ops_lock);
 
-	rtc_add_offset(rtc, &alarm->time);
 	return err;
 }
 EXPORT_SYMBOL_GPL(rtc_set_alarm);
diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c
index 097a4d4e2aba..1925aaf09093 100644
--- a/drivers/rtc/rtc-mrst.c
+++ b/drivers/rtc/rtc-mrst.c
@@ -367,10 +367,8 @@ static int vrtc_mrst_do_probe(struct device *dev, struct resource *iomem,
 	}
 
 	retval = rtc_register_device(mrst_rtc.rtc);
-	if (retval) {
-		retval = PTR_ERR(mrst_rtc.rtc);
+	if (retval)
 		goto cleanup0;
-	}
 
 	dev_dbg(dev, "initialised\n");
 	return 0;
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index d3a38c421503..a23e7d394a0a 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -41,6 +41,15 @@
 
 #define DASD_DIAG_MOD		"dasd_diag_mod"
 
+static unsigned int queue_depth = 32;
+static unsigned int nr_hw_queues = 4;
+
+module_param(queue_depth, uint, 0444);
+MODULE_PARM_DESC(queue_depth, "Default queue depth for new DASD devices");
+
+module_param(nr_hw_queues, uint, 0444);
+MODULE_PARM_DESC(nr_hw_queues, "Default number of hardware queues for new DASD devices");
+
 /*
  * SECTION: exported variables of dasd.c
  */
@@ -64,8 +73,8 @@ static int  dasd_alloc_queue(struct dasd_block *);
 static void dasd_setup_queue(struct dasd_block *);
 static void dasd_free_queue(struct dasd_block *);
 static int dasd_flush_block_queue(struct dasd_block *);
-static void dasd_device_tasklet(struct dasd_device *);
-static void dasd_block_tasklet(struct dasd_block *);
+static void dasd_device_tasklet(unsigned long);
+static void dasd_block_tasklet(unsigned long);
 static void do_kick_device(struct work_struct *);
 static void do_restore_device(struct work_struct *);
 static void do_reload_device(struct work_struct *);
@@ -116,8 +125,7 @@ struct dasd_device *dasd_alloc_device(void)
 	dasd_init_chunklist(&device->erp_chunks, device->erp_mem, PAGE_SIZE);
 	spin_lock_init(&device->mem_lock);
 	atomic_set(&device->tasklet_scheduled, 0);
-	tasklet_init(&device->tasklet,
-		     (void (*)(unsigned long)) dasd_device_tasklet,
+	tasklet_init(&device->tasklet, dasd_device_tasklet,
 		     (unsigned long) device);
 	INIT_LIST_HEAD(&device->ccw_queue);
 	timer_setup(&device->timer, dasd_device_timeout, 0);
@@ -157,8 +165,7 @@ struct dasd_block *dasd_alloc_block(void)
 	atomic_set(&block->open_count, -1);
 
 	atomic_set(&block->tasklet_scheduled, 0);
-	tasklet_init(&block->tasklet,
-		     (void (*)(unsigned long)) dasd_block_tasklet,
+	tasklet_init(&block->tasklet, dasd_block_tasklet,
 		     (unsigned long) block);
 	INIT_LIST_HEAD(&block->ccw_queue);
 	spin_lock_init(&block->queue_lock);
@@ -2055,8 +2062,9 @@ EXPORT_SYMBOL_GPL(dasd_flush_device_queue);
 /*
  * Acquire the device lock and process queues for the device.
  */
-static void dasd_device_tasklet(struct dasd_device *device)
+static void dasd_device_tasklet(unsigned long data)
 {
+	struct dasd_device *device = (struct dasd_device *) data;
 	struct list_head final_queue;
 
 	atomic_set (&device->tasklet_scheduled, 0);
@@ -2774,8 +2782,9 @@ static void __dasd_block_start_head(struct dasd_block *block)
  * block layer request queue, creates ccw requests, enqueues them on
  * a dasd_device and processes ccw requests that have been returned.
  */
-static void dasd_block_tasklet(struct dasd_block *block)
+static void dasd_block_tasklet(unsigned long data)
 {
+	struct dasd_block *block = (struct dasd_block *) data;
 	struct list_head final_queue;
 	struct list_head *l, *n;
 	struct dasd_ccw_req *cqr;
@@ -3115,9 +3124,10 @@ static int dasd_alloc_queue(struct dasd_block *block)
 
 	block->tag_set.ops = &dasd_mq_ops;
 	block->tag_set.cmd_size = sizeof(struct dasd_ccw_req);
-	block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES;
-	block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV;
+	block->tag_set.nr_hw_queues = nr_hw_queues;
+	block->tag_set.queue_depth = queue_depth;
 	block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	block->tag_set.numa_node = NUMA_NO_NODE;
 
 	rc = blk_mq_alloc_tag_set(&block->tag_set);
 	if (rc)
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index e36a114354fc..b9ce93e9df89 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -708,7 +708,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu,
 	struct ccw1 *ccw;
 
 	cqr = lcu->rsu_cqr;
-	strncpy((char *) &cqr->magic, "ECKD", 4);
+	memcpy((char *) &cqr->magic, "ECKD", 4);
 	ASCEBC((char *) &cqr->magic, 4);
 	ccw = cqr->cpaddr;
 	ccw->cmd_code = DASD_ECKD_CCW_RSCK;
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index b9ebb565ee2c..fab35c6170cc 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -426,7 +426,7 @@ dasd_add_busid(const char *bus_id, int features)
 	if (!devmap) {
 		/* This bus_id is new. */
 		new->devindex = dasd_max_devindex++;
-		strncpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
+		strlcpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
 		new->features = features;
 		new->device = NULL;
 		list_add(&new->list, &dasd_hashlists[hash]);
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index bbf95b78ef5d..4e7b55a14b1a 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1780,6 +1780,9 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device)
 	struct dasd_eckd_private *private = device->private;
 	int i;
 
+	if (!private)
+		return;
+
 	dasd_alias_disconnect_device_from_lcu(device);
 	private->ned = NULL;
 	private->sneq = NULL;
@@ -2035,8 +2038,11 @@ static int dasd_eckd_basic_to_ready(struct dasd_device *device)
 
 static int dasd_eckd_online_to_ready(struct dasd_device *device)
 {
-	cancel_work_sync(&device->reload_device);
-	cancel_work_sync(&device->kick_validate);
+	if (cancel_work_sync(&device->reload_device))
+		dasd_put_device(device);
+	if (cancel_work_sync(&device->kick_validate))
+		dasd_put_device(device);
+
 	return 0;
 };
 
@@ -3535,7 +3541,7 @@ static int prepare_itcw(struct itcw *itcw,
 
 	dcw = itcw_add_dcw(itcw, pfx_cmd, 0,
 		     &pfxdata, sizeof(pfxdata), total_data_size);
-	return PTR_RET(dcw);
+	return PTR_ERR_OR_ZERO(dcw);
 }
 
 static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index 6ef8714dc693..93bb09da7fdc 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -313,7 +313,7 @@ static void dasd_eer_write_standard_trigger(struct dasd_device *device,
 	ktime_get_real_ts64(&ts);
 	header.tv_sec = ts.tv_sec;
 	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-	strncpy(header.busid, dev_name(&device->cdev->dev),
+	strlcpy(header.busid, dev_name(&device->cdev->dev),
 		DASD_EER_BUSID_SIZE);
 
 	spin_lock_irqsave(&bufferlock, flags);
@@ -356,7 +356,7 @@ static void dasd_eer_write_snss_trigger(struct dasd_device *device,
 	ktime_get_real_ts64(&ts);
 	header.tv_sec = ts.tv_sec;
 	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-	strncpy(header.busid, dev_name(&device->cdev->dev),
+	strlcpy(header.busid, dev_name(&device->cdev->dev),
 		DASD_EER_BUSID_SIZE);
 
 	spin_lock_irqsave(&bufferlock, flags);
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 976b6bd4fb05..de6b96036aa4 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -228,14 +228,6 @@ struct dasd_ccw_req {
 #define DASD_CQR_SUPPRESS_IL	6	/* Suppress 'Incorrect Length' error */
 #define DASD_CQR_SUPPRESS_CR	7	/* Suppress 'Command Reject' error */
 
-/*
- * There is no reliable way to determine the number of available CPUs on
- * LPAR but there is no big performance difference between 1 and the
- * maximum CPU number.
- * 64 is a good trade off performance wise.
- */
-#define DASD_NR_HW_QUEUES 64
-#define DASD_MAX_LCU_DEV 256
 #define DASD_REQ_PER_DEV 4
 
 /* Signature for error recovery functions. */
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index b1fcb76dd272..98f66b7b6794 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -455,6 +455,7 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 	bdev->tag_set.nr_hw_queues = nr_requests;
 	bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests;
 	bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	bdev->tag_set.numa_node = NUMA_NO_NODE;
 
 	ret = blk_mq_alloc_tag_set(&bdev->tag_set);
 	if (ret)
diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile
index 0a4c13e1e76e..c6ab34f94b1b 100644
--- a/drivers/s390/char/Makefile
+++ b/drivers/s390/char/Makefile
@@ -12,11 +12,6 @@ GCOV_PROFILE_sclp_early_core.o		:= n
 KCOV_INSTRUMENT_sclp_early_core.o	:= n
 UBSAN_SANITIZE_sclp_early_core.o	:= n
 
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_sclp_early_core.o		+= -march=z900
-endif
-
 CFLAGS_sclp_early_core.o		+= -D__NO_FORTIFY
 
 CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_EXPOLINE)
diff --git a/drivers/s390/char/keyboard.c b/drivers/s390/char/keyboard.c
index 79eb60958015..bbb3001b0961 100644
--- a/drivers/s390/char/keyboard.c
+++ b/drivers/s390/char/keyboard.c
@@ -334,37 +334,41 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 	      int cmd, int perm)
 {
 	struct kbentry tmp;
+	unsigned long kb_index, kb_table;
 	ushort *key_map, val, ov;
 
 	if (copy_from_user(&tmp, user_kbe, sizeof(struct kbentry)))
 		return -EFAULT;
+	kb_index = (unsigned long) tmp.kb_index;
 #if NR_KEYS < 256
-	if (tmp.kb_index >= NR_KEYS)
+	if (kb_index >= NR_KEYS)
 		return -EINVAL;
 #endif
+	kb_table = (unsigned long) tmp.kb_table;
 #if MAX_NR_KEYMAPS < 256
-	if (tmp.kb_table >= MAX_NR_KEYMAPS)
+	if (kb_table >= MAX_NR_KEYMAPS)
 		return -EINVAL;	
+	kb_table = array_index_nospec(kb_table , MAX_NR_KEYMAPS);
 #endif
 
 	switch (cmd) {
 	case KDGKBENT:
-		key_map = kbd->key_maps[tmp.kb_table];
+		key_map = kbd->key_maps[kb_table];
 		if (key_map) {
-		    val = U(key_map[tmp.kb_index]);
+		    val = U(key_map[kb_index]);
 		    if (KTYP(val) >= KBD_NR_TYPES)
 			val = K_HOLE;
 		} else
-		    val = (tmp.kb_index ? K_HOLE : K_NOSUCHMAP);
+		    val = (kb_index ? K_HOLE : K_NOSUCHMAP);
 		return put_user(val, &user_kbe->kb_value);
 	case KDSKBENT:
 		if (!perm)
 			return -EPERM;
-		if (!tmp.kb_index && tmp.kb_value == K_NOSUCHMAP) {
+		if (!kb_index && tmp.kb_value == K_NOSUCHMAP) {
 			/* disallocate map */
-			key_map = kbd->key_maps[tmp.kb_table];
+			key_map = kbd->key_maps[kb_table];
 			if (key_map) {
-			    kbd->key_maps[tmp.kb_table] = NULL;
+			    kbd->key_maps[kb_table] = NULL;
 			    kfree(key_map);
 			}
 			break;
@@ -375,18 +379,18 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 		if (KVAL(tmp.kb_value) > kbd_max_vals[KTYP(tmp.kb_value)])
 			return -EINVAL;
 
-		if (!(key_map = kbd->key_maps[tmp.kb_table])) {
+		if (!(key_map = kbd->key_maps[kb_table])) {
 			int j;
 
 			key_map = kmalloc(sizeof(plain_map),
 						     GFP_KERNEL);
 			if (!key_map)
 				return -ENOMEM;
-			kbd->key_maps[tmp.kb_table] = key_map;
+			kbd->key_maps[kb_table] = key_map;
 			for (j = 0; j < NR_KEYS; j++)
 				key_map[j] = U(K_HOLE);
 		}
-		ov = U(key_map[tmp.kb_index]);
+		ov = U(key_map[kb_index]);
 		if (tmp.kb_value == ov)
 			break;	/* nothing to do */
 		/*
@@ -395,7 +399,7 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 		if (((ov == K_SAK) || (tmp.kb_value == K_SAK)) &&
 		    !capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		key_map[tmp.kb_index] = U(tmp.kb_value);
+		key_map[kb_index] = U(tmp.kb_value);
 		break;
 	}
 	return 0;
diff --git a/drivers/s390/char/monwriter.c b/drivers/s390/char/monwriter.c
index 76c158c41510..4f1a69c9d81d 100644
--- a/drivers/s390/char/monwriter.c
+++ b/drivers/s390/char/monwriter.c
@@ -61,7 +61,7 @@ static int monwrite_diag(struct monwrite_hdr *myhdr, char *buffer, int fcn)
 	struct appldata_product_id id;
 	int rc;
 
-	strncpy(id.prod_nr, "LNXAPPL", 7);
+	memcpy(id.prod_nr, "LNXAPPL", 7);
 	id.prod_fn = myhdr->applid;
 	id.record_nr = myhdr->record_num;
 	id.version_nr = myhdr->version;
diff --git a/drivers/s390/char/sclp_async.c b/drivers/s390/char/sclp_async.c
index ee6f3b563728..e69b12a40636 100644
--- a/drivers/s390/char/sclp_async.c
+++ b/drivers/s390/char/sclp_async.c
@@ -64,42 +64,18 @@ static struct notifier_block call_home_panic_nb = {
 	.priority = INT_MAX,
 };
 
-static int proc_handler_callhome(struct ctl_table *ctl, int write,
-				 void __user *buffer, size_t *count,
-				 loff_t *ppos)
-{
-	unsigned long val;
-	int len, rc;
-	char buf[3];
-
-	if (!*count || (*ppos && !write)) {
-		*count = 0;
-		return 0;
-	}
-	if (!write) {
-		len = snprintf(buf, sizeof(buf), "%d\n", callhome_enabled);
-		rc = copy_to_user(buffer, buf, sizeof(buf));
-		if (rc != 0)
-			return -EFAULT;
-	} else {
-		len = *count;
-		rc = kstrtoul_from_user(buffer, len, 0, &val);
-		if (rc)
-			return rc;
-		if (val != 0 && val != 1)
-			return -EINVAL;
-		callhome_enabled = val;
-	}
-	*count = len;
-	*ppos += len;
-	return 0;
-}
+static int zero;
+static int one = 1;
 
 static struct ctl_table callhome_table[] = {
 	{
 		.procname	= "callhome",
+		.data		= &callhome_enabled,
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_handler_callhome,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 	{}
 };
diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c
index 37e65a05517f..cdcde18e7220 100644
--- a/drivers/s390/char/tape_3590.c
+++ b/drivers/s390/char/tape_3590.c
@@ -113,16 +113,16 @@ static int crypt_enabled(struct tape_device *device)
 static void ext_to_int_kekl(struct tape390_kekl *in,
 			    struct tape3592_kekl *out)
 {
-	int i;
+	int len;
 
 	memset(out, 0, sizeof(*out));
 	if (in->type == TAPE390_KEKL_TYPE_HASH)
 		out->flags |= 0x40;
 	if (in->type_on_tape == TAPE390_KEKL_TYPE_HASH)
 		out->flags |= 0x80;
-	strncpy(out->label, in->label, 64);
-	for (i = strlen(in->label); i < sizeof(out->label); i++)
-		out->label[i] = ' ';
+	len = min(sizeof(out->label), strlen(in->label));
+	memcpy(out->label, in->label, len);
+	memset(out->label + len, ' ', sizeof(out->label) - len);
 	ASCEBC(out->label, sizeof(out->label));
 }
 
diff --git a/drivers/s390/char/tape_class.c b/drivers/s390/char/tape_class.c
index a07102472ce9..b58df0dd0039 100644
--- a/drivers/s390/char/tape_class.c
+++ b/drivers/s390/char/tape_class.c
@@ -54,10 +54,10 @@ struct tape_class_device *register_tape_dev(
 	if (!tcd)
 		return ERR_PTR(-ENOMEM);
 
-	strncpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
+	strlcpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
 	for (s = strchr(tcd->device_name, '/'); s; s = strchr(s, '/'))
 		*s = '!';
-	strncpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
+	strlcpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
 	for (s = strchr(tcd->mode_name, '/'); s; s = strchr(s, '/'))
 		*s = '!';
 
@@ -77,7 +77,7 @@ struct tape_class_device *register_tape_dev(
 	tcd->class_device = device_create(tape_class, device,
 					  tcd->char_device->dev, NULL,
 					  "%s", tcd->device_name);
-	rc = PTR_RET(tcd->class_device);
+	rc = PTR_ERR_OR_ZERO(tcd->class_device);
 	if (rc)
 		goto fail_with_cdev;
 	rc = sysfs_create_link(
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index afbdee74147d..51038ec309c1 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -471,14 +471,17 @@ int chp_new(struct chp_id chpid)
 {
 	struct channel_subsystem *css = css_by_id(chpid.cssid);
 	struct channel_path *chp;
-	int ret;
+	int ret = 0;
 
+	mutex_lock(&css->mutex);
 	if (chp_is_registered(chpid))
-		return 0;
-	chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
-	if (!chp)
-		return -ENOMEM;
+		goto out;
 
+	chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
+	if (!chp) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	/* fill in status, etc. */
 	chp->chpid = chpid;
 	chp->state = 1;
@@ -505,21 +508,20 @@ int chp_new(struct chp_id chpid)
 		put_device(&chp->dev);
 		goto out;
 	}
-	mutex_lock(&css->mutex);
+
 	if (css->cm_enabled) {
 		ret = chp_add_cmg_attr(chp);
 		if (ret) {
 			device_unregister(&chp->dev);
-			mutex_unlock(&css->mutex);
 			goto out;
 		}
 	}
 	css->chps[chpid.id] = chp;
-	mutex_unlock(&css->mutex);
 	goto out;
 out_free:
 	kfree(chp);
 out:
+	mutex_unlock(&css->mutex);
 	return ret;
 }
 
@@ -585,8 +587,7 @@ static void chp_process_crw(struct crw *crw0, struct crw *crw1,
 	switch (crw0->erc) {
 	case CRW_ERC_IPARM: /* Path has come. */
 	case CRW_ERC_INIT:
-		if (!chp_is_registered(chpid))
-			chp_new(chpid);
+		chp_new(chpid);
 		chsc_chp_online(chpid);
 		break;
 	case CRW_ERC_PERRI: /* Path has gone. */
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 9029804dcd22..a0baee25134c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -91,7 +91,7 @@ struct chsc_ssd_area {
 	u16 sch;	  /* subchannel */
 	u8 chpid[8];	  /* chpids 0-7 */
 	u16 fla[8];	  /* full link addresses 0-7 */
-} __attribute__ ((packed));
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_get_ssd_info(struct subchannel_id schid, struct chsc_ssd_info *ssd)
 {
@@ -319,7 +319,7 @@ struct chsc_sei {
 		struct chsc_sei_nt2_area nt2_area;
 		u8 nt_area[PAGE_SIZE - 24];
 	} u;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 /*
  * Node Descriptor as defined in SA22-7204, "Common I/O-Device Commands"
@@ -841,7 +841,7 @@ int __chsc_do_secm(struct channel_subsystem *css, int enable)
 		u32 : 4;
 		u32 fmt : 4;
 		u32 : 16;
-	} __attribute__ ((packed)) *secm_area;
+	} *secm_area;
 	unsigned long flags;
 	int ret, ccode;
 
@@ -1014,7 +1014,7 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp)
 		u32 cmg : 8;
 		u32 zeroes3;
 		u32 data[NR_MEASUREMENT_CHARS];
-	} __attribute__ ((packed)) *scmc_area;
+	} *scmc_area;
 
 	chp->shared = -1;
 	chp->cmg = -1;
@@ -1142,7 +1142,7 @@ int __init chsc_get_cssid(int idx)
 			u8 cssid;
 			u32 : 24;
 		} list[0];
-	} __packed *sdcal_area;
+	} *sdcal_area;
 	int ret;
 
 	spin_lock_irq(&chsc_page_lock);
@@ -1192,7 +1192,7 @@ chsc_determine_css_characteristics(void)
 		u32 reserved4;
 		u32 general_char[510];
 		u32 chsc_char[508];
-	} __attribute__ ((packed)) *scsc_area;
+	} *scsc_area;
 
 	spin_lock_irqsave(&chsc_page_lock, flags);
 	memset(chsc_page, 0, PAGE_SIZE);
@@ -1236,7 +1236,7 @@ int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta)
 		unsigned int rsvd3[3];
 		u64 clock_delta;
 		unsigned int rsvd4[2];
-	} __attribute__ ((packed)) *rr;
+	} *rr;
 	int rc;
 
 	memset(page, 0, PAGE_SIZE);
@@ -1261,7 +1261,7 @@ int chsc_sstpi(void *page, void *result, size_t size)
 		unsigned int rsvd0[3];
 		struct chsc_header response;
 		char data[];
-	} __attribute__ ((packed)) *rr;
+	} *rr;
 	int rc;
 
 	memset(page, 0, PAGE_SIZE);
@@ -1284,7 +1284,7 @@ int chsc_siosl(struct subchannel_id schid)
 		u32 word3;
 		struct chsc_header response;
 		u32 word[11];
-	} __attribute__ ((packed)) *siosl_area;
+	} *siosl_area;
 	unsigned long flags;
 	int ccode;
 	int rc;
diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h
index 5c9f0dd33f4e..78aba8d94eec 100644
--- a/drivers/s390/cio/chsc.h
+++ b/drivers/s390/cio/chsc.h
@@ -15,12 +15,12 @@
 #define NR_MEASUREMENT_CHARS 5
 struct cmg_chars {
 	u32 values[NR_MEASUREMENT_CHARS];
-} __attribute__ ((packed));
+};
 
 #define NR_MEASUREMENT_ENTRIES 8
 struct cmg_entry {
 	u32 values[NR_MEASUREMENT_ENTRIES];
-} __attribute__ ((packed));
+};
 
 struct channel_path_desc_fmt1 {
 	u8 flags;
@@ -38,7 +38,7 @@ struct channel_path_desc_fmt1 {
 	u8 s:1;
 	u8 f:1;
 	u32 zeros[2];
-} __attribute__ ((packed));
+};
 
 struct channel_path_desc_fmt3 {
 	struct channel_path_desc_fmt1 fmt1_desc;
@@ -59,7 +59,7 @@ struct css_chsc_char {
 	u32:7;
 	u32 pnso:1; /* bit 116 */
 	u32:11;
-}__attribute__((packed));
+} __packed;
 
 extern struct css_chsc_char css_chsc_characteristics;
 
@@ -82,7 +82,7 @@ struct chsc_ssqd_area {
 	struct chsc_header response;
 	u32:32;
 	struct qdio_ssqd_desc qdio_ssqd;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_scssc_area {
 	struct chsc_header request;
@@ -102,7 +102,7 @@ struct chsc_scssc_area {
 	u32 reserved[1004];
 	struct chsc_header response;
 	u32:32;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_scpd {
 	struct chsc_header request;
@@ -120,7 +120,7 @@ struct chsc_scpd {
 	struct chsc_header response;
 	u32:32;
 	u8 data[0];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_sda_area {
 	struct chsc_header request;
@@ -199,7 +199,7 @@ struct chsc_scm_info {
 	u32 reserved2[10];
 	u64 restok;
 	struct sale scmal[248];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_scm_info(struct chsc_scm_info *scm_area, u64 token);
 
@@ -243,7 +243,7 @@ struct chsc_pnso_area {
 		struct qdio_brinfo_entry_l3_ipv4 l3_ipv4[0];
 		struct qdio_brinfo_entry_l2	 l2[0];
 	} entries;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_pnso_brinfo(struct subchannel_id schid,
 		struct chsc_pnso_area *brinfo_area,
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 5130d7c67239..de744ca158fd 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -526,76 +526,6 @@ int cio_disable_subchannel(struct subchannel *sch)
 }
 EXPORT_SYMBOL_GPL(cio_disable_subchannel);
 
-static int cio_check_devno_blacklisted(struct subchannel *sch)
-{
-	if (is_blacklisted(sch->schid.ssid, sch->schib.pmcw.dev)) {
-		/*
-		 * This device must not be known to Linux. So we simply
-		 * say that there is no device and return ENODEV.
-		 */
-		CIO_MSG_EVENT(6, "Blacklisted device detected "
-			      "at devno %04X, subchannel set %x\n",
-			      sch->schib.pmcw.dev, sch->schid.ssid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
-/**
- * cio_validate_subchannel - basic validation of subchannel
- * @sch: subchannel structure to be filled out
- * @schid: subchannel id
- *
- * Find out subchannel type and initialize struct subchannel.
- * Return codes:
- *   0 on success
- *   -ENXIO for non-defined subchannels
- *   -ENODEV for invalid subchannels or blacklisted devices
- *   -EIO for subchannels in an invalid subchannel set
- */
-int cio_validate_subchannel(struct subchannel *sch, struct subchannel_id schid)
-{
-	char dbf_txt[15];
-	int ccode;
-	int err;
-
-	sprintf(dbf_txt, "valsch%x", schid.sch_no);
-	CIO_TRACE_EVENT(4, dbf_txt);
-
-	/*
-	 * The first subchannel that is not-operational (ccode==3)
-	 * indicates that there aren't any more devices available.
-	 * If stsch gets an exception, it means the current subchannel set
-	 * is not valid.
-	 */
-	ccode = stsch(schid, &sch->schib);
-	if (ccode) {
-		err = (ccode == 3) ? -ENXIO : ccode;
-		goto out;
-	}
-	sch->st = sch->schib.pmcw.st;
-	sch->schid = schid;
-
-	switch (sch->st) {
-	case SUBCHANNEL_TYPE_IO:
-	case SUBCHANNEL_TYPE_MSG:
-		if (!css_sch_is_valid(&sch->schib))
-			err = -ENODEV;
-		else
-			err = cio_check_devno_blacklisted(sch);
-		break;
-	default:
-		err = 0;
-	}
-	if (err)
-		goto out;
-
-	CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
-		      sch->schid.ssid, sch->schid.sch_no, sch->st);
-out:
-	return err;
-}
-
 /*
  * do_cio_interrupt() handles all normal I/O device IRQ's
  */
@@ -719,6 +649,7 @@ struct subchannel *cio_probe_console(void)
 {
 	struct subchannel_id schid;
 	struct subchannel *sch;
+	struct schib schib;
 	int sch_no, ret;
 
 	sch_no = cio_get_console_sch_no();
@@ -728,7 +659,11 @@ struct subchannel *cio_probe_console(void)
 	}
 	init_subchannel_id(&schid);
 	schid.sch_no = sch_no;
-	sch = css_alloc_subchannel(schid);
+	ret = stsch(schid, &schib);
+	if (ret)
+		return ERR_PTR(-ENODEV);
+
+	sch = css_alloc_subchannel(schid, &schib);
 	if (IS_ERR(sch))
 		return sch;
 
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index 94cd813bdcfe..9811fd8a0c73 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -119,7 +119,6 @@ DECLARE_PER_CPU(struct irb, cio_irb);
 
 #define to_subchannel(n) container_of(n, struct subchannel, dev)
 
-extern int cio_validate_subchannel (struct subchannel *, struct subchannel_id);
 extern int cio_enable_subchannel(struct subchannel *, u32);
 extern int cio_disable_subchannel (struct subchannel *);
 extern int cio_cancel (struct subchannel *);
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 9263a0fb3858..aea502922646 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -25,6 +25,7 @@
 
 #include "css.h"
 #include "cio.h"
+#include "blacklist.h"
 #include "cio_debug.h"
 #include "ioasm.h"
 #include "chsc.h"
@@ -168,18 +169,53 @@ static void css_subchannel_release(struct device *dev)
 	kfree(sch);
 }
 
-struct subchannel *css_alloc_subchannel(struct subchannel_id schid)
+static int css_validate_subchannel(struct subchannel_id schid,
+				   struct schib *schib)
+{
+	int err;
+
+	switch (schib->pmcw.st) {
+	case SUBCHANNEL_TYPE_IO:
+	case SUBCHANNEL_TYPE_MSG:
+		if (!css_sch_is_valid(schib))
+			err = -ENODEV;
+		else if (is_blacklisted(schid.ssid, schib->pmcw.dev)) {
+			CIO_MSG_EVENT(6, "Blacklisted device detected "
+				      "at devno %04X, subchannel set %x\n",
+				      schib->pmcw.dev, schid.ssid);
+			err = -ENODEV;
+		} else
+			err = 0;
+		break;
+	default:
+		err = 0;
+	}
+	if (err)
+		goto out;
+
+	CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
+		      schid.ssid, schid.sch_no, schib->pmcw.st);
+out:
+	return err;
+}
+
+struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
+					struct schib *schib)
 {
 	struct subchannel *sch;
 	int ret;
 
+	ret = css_validate_subchannel(schid, schib);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
 	sch = kzalloc(sizeof(*sch), GFP_KERNEL | GFP_DMA);
 	if (!sch)
 		return ERR_PTR(-ENOMEM);
 
-	ret = cio_validate_subchannel(sch, schid);
-	if (ret < 0)
-		goto err;
+	sch->schid = schid;
+	sch->schib = *schib;
+	sch->st = schib->pmcw.st;
 
 	ret = css_sch_create_locks(sch);
 	if (ret)
@@ -244,8 +280,7 @@ static void ssd_register_chpids(struct chsc_ssd_info *ssd)
 	for (i = 0; i < 8; i++) {
 		mask = 0x80 >> i;
 		if (ssd->path_mask & mask)
-			if (!chp_is_registered(ssd->chpid[i]))
-				chp_new(ssd->chpid[i]);
+			chp_new(ssd->chpid[i]);
 	}
 }
 
@@ -382,12 +417,12 @@ int css_register_subchannel(struct subchannel *sch)
 	return ret;
 }
 
-static int css_probe_device(struct subchannel_id schid)
+static int css_probe_device(struct subchannel_id schid, struct schib *schib)
 {
 	struct subchannel *sch;
 	int ret;
 
-	sch = css_alloc_subchannel(schid);
+	sch = css_alloc_subchannel(schid, schib);
 	if (IS_ERR(sch))
 		return PTR_ERR(sch);
 
@@ -436,23 +471,23 @@ EXPORT_SYMBOL_GPL(css_sch_is_valid);
 static int css_evaluate_new_subchannel(struct subchannel_id schid, int slow)
 {
 	struct schib schib;
+	int ccode;
 
 	if (!slow) {
 		/* Will be done on the slow path. */
 		return -EAGAIN;
 	}
-	if (stsch(schid, &schib)) {
-		/* Subchannel is not provided. */
-		return -ENXIO;
-	}
-	if (!css_sch_is_valid(&schib)) {
-		/* Unusable - ignore. */
-		return 0;
-	}
-	CIO_MSG_EVENT(4, "event: sch 0.%x.%04x, new\n", schid.ssid,
-		      schid.sch_no);
+	/*
+	 * The first subchannel that is not-operational (ccode==3)
+	 * indicates that there aren't any more devices available.
+	 * If stsch gets an exception, it means the current subchannel set
+	 * is not valid.
+	 */
+	ccode = stsch(schid, &schib);
+	if (ccode)
+		return (ccode == 3) ? -ENXIO : ccode;
 
-	return css_probe_device(schid);
+	return css_probe_device(schid, &schib);
 }
 
 static int css_evaluate_known_subchannel(struct subchannel *sch, int slow)
@@ -1081,6 +1116,11 @@ static int __init channel_subsystem_init(void)
 	if (ret)
 		goto out_wq;
 
+	/* Register subchannels which are already in use. */
+	cio_register_early_subchannels();
+	/* Start initial subchannel evaluation. */
+	css_schedule_eval_all();
+
 	return ret;
 out_wq:
 	destroy_workqueue(cio_work_q);
@@ -1120,10 +1160,6 @@ int css_complete_work(void)
  */
 static int __init channel_subsystem_init_sync(void)
 {
-	/* Register subchannels which are already in use. */
-	cio_register_early_subchannels();
-	/* Start initial subchannel evaluation. */
-	css_schedule_eval_all();
 	css_complete_work();
 	return 0;
 }
diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h
index 30357cbf350a..8d832900a63d 100644
--- a/drivers/s390/cio/css.h
+++ b/drivers/s390/cio/css.h
@@ -103,7 +103,8 @@ extern void css_driver_unregister(struct css_driver *);
 
 extern void css_sch_device_unregister(struct subchannel *);
 extern int css_register_subchannel(struct subchannel *);
-extern struct subchannel *css_alloc_subchannel(struct subchannel_id);
+extern struct subchannel *css_alloc_subchannel(struct subchannel_id,
+					       struct schib *schib);
 extern struct subchannel *get_subchannel_by_schid(struct subchannel_id);
 extern int css_init_done;
 extern int max_ssid;
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index f4ca72dd862f..9c7d9da42ba0 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -631,21 +631,20 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q,
 	unsigned long phys_aob = 0;
 
 	if (!q->use_cq)
-		goto out;
+		return 0;
 
 	if (!q->aobs[bufnr]) {
 		struct qaob *aob = qdio_allocate_aob();
 		q->aobs[bufnr] = aob;
 	}
 	if (q->aobs[bufnr]) {
-		q->sbal_state[bufnr].flags = QDIO_OUTBUF_STATE_FLAG_NONE;
 		q->sbal_state[bufnr].aob = q->aobs[bufnr];
 		q->aobs[bufnr]->user1 = (u64) q->sbal_state[bufnr].user;
 		phys_aob = virt_to_phys(q->aobs[bufnr]);
 		WARN_ON_ONCE(phys_aob & 0xFF);
 	}
 
-out:
+	q->sbal_state[bufnr].flags = 0;
 	return phys_aob;
 }
 
diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h
index 1f8d1c1e566d..0ebb29b6fd6d 100644
--- a/drivers/s390/cio/trace.h
+++ b/drivers/s390/cio/trace.h
@@ -30,6 +30,17 @@ DECLARE_EVENT_CLASS(s390_class_schib,
 		__field(u16, schno)
 		__field(u16, devno)
 		__field_struct(struct schib, schib)
+		__field(u8, pmcw_ena)
+		__field(u8, pmcw_st)
+		__field(u8, pmcw_dnv)
+		__field(u16, pmcw_dev)
+		__field(u8, pmcw_lpm)
+		__field(u8, pmcw_pnom)
+		__field(u8, pmcw_lpum)
+		__field(u8, pmcw_pim)
+		__field(u8, pmcw_pam)
+		__field(u8, pmcw_pom)
+		__field(u64, pmcw_chpid)
 		__field(int, cc)
 	),
 	TP_fast_assign(
@@ -38,18 +49,29 @@ DECLARE_EVENT_CLASS(s390_class_schib,
 		__entry->schno = schid.sch_no;
 		__entry->devno = schib->pmcw.dev;
 		__entry->schib = *schib;
+		__entry->pmcw_ena = schib->pmcw.ena;
+		__entry->pmcw_st = schib->pmcw.ena;
+		__entry->pmcw_dnv = schib->pmcw.dnv;
+		__entry->pmcw_dev = schib->pmcw.dev;
+		__entry->pmcw_lpm = schib->pmcw.lpm;
+		__entry->pmcw_pnom = schib->pmcw.pnom;
+		__entry->pmcw_lpum = schib->pmcw.lpum;
+		__entry->pmcw_pim = schib->pmcw.pim;
+		__entry->pmcw_pam = schib->pmcw.pam;
+		__entry->pmcw_pom = schib->pmcw.pom;
+		memcpy(&__entry->pmcw_chpid, &schib->pmcw.chpid, 8);
 		__entry->cc = cc;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d ena=%d st=%d dnv=%d dev=%04x "
 		  "lpm=0x%02x pnom=0x%02x lpum=0x%02x pim=0x%02x pam=0x%02x "
 		  "pom=0x%02x chpids=%016llx",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  __entry->schib.pmcw.ena, __entry->schib.pmcw.st,
-		  __entry->schib.pmcw.dnv, __entry->schib.pmcw.dev,
-		  __entry->schib.pmcw.lpm, __entry->schib.pmcw.pnom,
-		  __entry->schib.pmcw.lpum, __entry->schib.pmcw.pim,
-		  __entry->schib.pmcw.pam, __entry->schib.pmcw.pom,
-		  *((u64 *) __entry->schib.pmcw.chpid)
+		  __entry->pmcw_ena, __entry->pmcw_st,
+		  __entry->pmcw_dnv, __entry->pmcw_dev,
+		  __entry->pmcw_lpm, __entry->pmcw_pnom,
+		  __entry->pmcw_lpum, __entry->pmcw_pim,
+		  __entry->pmcw_pam, __entry->pmcw_pom,
+		  __entry->pmcw_chpid
 	)
 );
 
@@ -89,6 +111,13 @@ TRACE_EVENT(s390_cio_tsch,
 		__field(u8, ssid)
 		__field(u16, schno)
 		__field_struct(struct irb, irb)
+		__field(u8, scsw_dcc)
+		__field(u8, scsw_pno)
+		__field(u8, scsw_fctl)
+		__field(u8, scsw_actl)
+		__field(u8, scsw_stctl)
+		__field(u8, scsw_dstat)
+		__field(u8, scsw_cstat)
 		__field(int, cc)
 	),
 	TP_fast_assign(
@@ -96,15 +125,22 @@ TRACE_EVENT(s390_cio_tsch,
 		__entry->ssid = schid.ssid;
 		__entry->schno = schid.sch_no;
 		__entry->irb = *irb;
+		__entry->scsw_dcc = scsw_cc(&irb->scsw);
+		__entry->scsw_pno = scsw_pno(&irb->scsw);
+		__entry->scsw_fctl = scsw_fctl(&irb->scsw);
+		__entry->scsw_actl = scsw_actl(&irb->scsw);
+		__entry->scsw_stctl = scsw_stctl(&irb->scsw);
+		__entry->scsw_dstat = scsw_dstat(&irb->scsw);
+		__entry->scsw_cstat = scsw_cstat(&irb->scsw);
 		__entry->cc = cc;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d dcc=%d pno=%d fctl=0x%x actl=0x%x "
 		  "stctl=0x%x dstat=0x%x cstat=0x%x",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  scsw_cc(&__entry->irb.scsw), scsw_pno(&__entry->irb.scsw),
-		  scsw_fctl(&__entry->irb.scsw), scsw_actl(&__entry->irb.scsw),
-		  scsw_stctl(&__entry->irb.scsw),
-		  scsw_dstat(&__entry->irb.scsw), scsw_cstat(&__entry->irb.scsw)
+		  __entry->scsw_dcc, __entry->scsw_pno,
+		  __entry->scsw_fctl, __entry->scsw_actl,
+		  __entry->scsw_stctl,
+		  __entry->scsw_dstat, __entry->scsw_cstat
 	)
 );
 
@@ -122,6 +158,9 @@ TRACE_EVENT(s390_cio_tpi,
 		__field(u8, cssid)
 		__field(u8, ssid)
 		__field(u16, schno)
+		__field(u8, adapter_IO)
+		__field(u8, isc)
+		__field(u8, type)
 	),
 	TP_fast_assign(
 		__entry->cc = cc;
@@ -136,11 +175,14 @@ TRACE_EVENT(s390_cio_tpi,
 		__entry->cssid = __entry->tpi_info.schid.cssid;
 		__entry->ssid = __entry->tpi_info.schid.ssid;
 		__entry->schno = __entry->tpi_info.schid.sch_no;
+		__entry->adapter_IO = __entry->tpi_info.adapter_IO;
+		__entry->isc = __entry->tpi_info.isc;
+		__entry->type = __entry->tpi_info.type;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d a=%d isc=%d type=%d",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  __entry->tpi_info.adapter_IO, __entry->tpi_info.isc,
-		  __entry->tpi_info.type
+		  __entry->adapter_IO, __entry->isc,
+		  __entry->type
 	)
 );
 
@@ -299,16 +341,20 @@ TRACE_EVENT(s390_cio_interrupt,
 		__field(u8, cssid)
 		__field(u8, ssid)
 		__field(u16, schno)
+		__field(u8, isc)
+		__field(u8, type)
 	),
 	TP_fast_assign(
 		__entry->tpi_info = *tpi_info;
-		__entry->cssid = __entry->tpi_info.schid.cssid;
-		__entry->ssid = __entry->tpi_info.schid.ssid;
-		__entry->schno = __entry->tpi_info.schid.sch_no;
+		__entry->cssid = tpi_info->schid.cssid;
+		__entry->ssid = tpi_info->schid.ssid;
+		__entry->schno = tpi_info->schid.sch_no;
+		__entry->isc = tpi_info->isc;
+		__entry->type = tpi_info->type;
 	),
 	TP_printk("schid=%x.%x.%04x isc=%d type=%d",
 		  __entry->cssid, __entry->ssid, __entry->schno,
-		  __entry->tpi_info.isc, __entry->tpi_info.type
+		  __entry->isc, __entry->type
 	)
 );
 
@@ -321,11 +367,13 @@ TRACE_EVENT(s390_cio_adapter_int,
 	TP_ARGS(tpi_info),
 	TP_STRUCT__entry(
 		__field_struct(struct tpi_info, tpi_info)
+		__field(u8, isc)
 	),
 	TP_fast_assign(
 		__entry->tpi_info = *tpi_info;
+		__entry->isc = tpi_info->isc;
 	),
-	TP_printk("isc=%d", __entry->tpi_info.isc)
+	TP_printk("isc=%d", __entry->isc)
 );
 
 /**
@@ -339,16 +387,30 @@ TRACE_EVENT(s390_cio_stcrw,
 	TP_STRUCT__entry(
 		__field_struct(struct crw, crw)
 		__field(int, cc)
+		__field(u8, slct)
+		__field(u8, oflw)
+		__field(u8, chn)
+		__field(u8, rsc)
+		__field(u8, anc)
+		__field(u8, erc)
+		__field(u16, rsid)
 	),
 	TP_fast_assign(
 		__entry->crw = *crw;
 		__entry->cc = cc;
+		__entry->slct = crw->slct;
+		__entry->oflw = crw->oflw;
+		__entry->chn = crw->chn;
+		__entry->rsc = crw->rsc;
+		__entry->anc = crw->anc;
+		__entry->erc = crw->erc;
+		__entry->rsid = crw->rsid;
 	),
 	TP_printk("cc=%d slct=%d oflw=%d chn=%d rsc=%d anc=%d erc=0x%x "
 		  "rsid=0x%x",
-		  __entry->cc, __entry->crw.slct, __entry->crw.oflw,
-		  __entry->crw.chn, __entry->crw.rsc,  __entry->crw.anc,
-		  __entry->crw.erc, __entry->crw.rsid
+		  __entry->cc, __entry->slct, __entry->oflw,
+		  __entry->chn, __entry->rsc,  __entry->anc,
+		  __entry->erc, __entry->rsid
 	)
 );
 
diff --git a/drivers/s390/crypto/ap_asm.h b/drivers/s390/crypto/ap_asm.h
deleted file mode 100644
index 16b59ce5e01d..000000000000
--- a/drivers/s390/crypto/ap_asm.h
+++ /dev/null
@@ -1,236 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright IBM Corp. 2016
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- *
- * Adjunct processor bus inline assemblies.
- */
-
-#ifndef _AP_ASM_H_
-#define _AP_ASM_H_
-
-#include <asm/isc.h>
-
-/**
- * ap_intructions_available() - Test if AP instructions are available.
- *
- * Returns 0 if the AP instructions are installed.
- */
-static inline int ap_instructions_available(void)
-{
-	register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
-	register unsigned long reg1 asm ("1") = -ENODEV;
-	register unsigned long reg2 asm ("2") = 0UL;
-
-	asm volatile(
-		"   .long 0xb2af0000\n"		/* PQAP(TAPQ) */
-		"0: la    %1,0\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+d" (reg0), "+d" (reg1), "+d" (reg2) : : "cc");
-	return reg1;
-}
-
-/**
- * ap_tapq(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
-{
-	register unsigned long reg0 asm ("0") = qid;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
-
-	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
-		     : "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
-	if (info)
-		*info = reg2;
-	return reg1;
-}
-
-/**
- * ap_pqap_rapq(): Reset adjunct processor queue.
- * @qid: The AP queue number
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
-{
-	register unsigned long reg0 asm ("0") = qid | 0x01000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(RAPQ) */
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
-	return reg1;
-}
-
-/**
- * ap_aqic(): Control interruption for a specific AP.
- * @qid: The AP queue number
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- */
-static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
-					     struct ap_qirq_ctrl qirqctrl,
-					     void *ind)
-{
-	register unsigned long reg0 asm ("0") = qid | (3UL << 24);
-	register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
-	register struct ap_queue_status reg1_out asm ("1");
-	register void *reg2 asm ("2") = ind;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(AQIC) */
-		: "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
-		:
-		: "cc");
-	return reg1_out;
-}
-
-/**
- * ap_qci(): Get AP configuration data
- *
- * Returns 0 on success, or -EOPNOTSUPP.
- */
-static inline int ap_qci(void *config)
-{
-	register unsigned long reg0 asm ("0") = 0x04000000UL;
-	register unsigned long reg1 asm ("1") = -EINVAL;
-	register void *reg2 asm ("2") = (void *) config;
-
-	asm volatile(
-		".long 0xb2af0000\n"		/* PQAP(QCI) */
-		"0: la    %1,0\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+d" (reg0), "+d" (reg1), "+d" (reg2)
-		:
-		: "cc", "memory");
-
-	return reg1;
-}
-
-/*
- * union ap_qact_ap_info - used together with the
- * ap_aqic() function to provide a convenient way
- * to handle the ap info needed by the qact function.
- */
-union ap_qact_ap_info {
-	unsigned long val;
-	struct {
-		unsigned int	  : 3;
-		unsigned int mode : 3;
-		unsigned int	  : 26;
-		unsigned int cat  : 8;
-		unsigned int	  : 8;
-		unsigned char ver[2];
-	};
-};
-
-/**
- * ap_qact(): Query AP combatibility type.
- * @qid: The AP queue number
- * @apinfo: On input the info about the AP queue. On output the
- *	    alternate AP queue info provided by the qact function
- *	    in GR2 is stored in.
- *
- * Returns AP queue status. Check response_code field for failures.
- */
-static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
-					     union ap_qact_ap_info *apinfo)
-{
-	register unsigned long reg0 asm ("0") = qid | (5UL << 24)
-		| ((ifbit & 0x01) << 22);
-	register unsigned long reg1_in asm ("1") = apinfo->val;
-	register struct ap_queue_status reg1_out asm ("1");
-	register unsigned long reg2 asm ("2") = 0;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(QACT) */
-		: "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
-		: : "cc");
-	apinfo->val = reg2;
-	return reg1_out;
-}
-
-/**
- * ap_nqap(): Send message to adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: The program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on NQAP can't happen because the L bit is 1.
- * Condition code 2 on NQAP also means the send is incomplete,
- * because a segment boundary was reached. The NQAP is repeated.
- */
-static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
-					     unsigned long long psmid,
-					     void *msg, size_t length)
-{
-	register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = (unsigned long) msg;
-	register unsigned long reg3 asm ("3") = (unsigned long) length;
-	register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
-	register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
-
-	asm volatile (
-		"0: .long 0xb2ad0042\n"		/* NQAP */
-		"   brc   2,0b"
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
-		: "d" (reg4), "d" (reg5)
-		: "cc", "memory");
-	return reg1;
-}
-
-/**
- * ap_dqap(): Receive message from adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: Pointer to program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on DQAP means the receive has taken place
- * but only partially.	The response is incomplete, hence the
- * DQAP is repeated.
- * Condition code 2 on DQAP also means the receive is incomplete,
- * this time because a segment boundary was reached. Again, the
- * DQAP is repeated.
- * Note that gpr2 is used by the DQAP instruction to keep track of
- * any 'residual' length, in case the instruction gets interrupted.
- * Hence it gets zeroed before the instruction.
- */
-static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
-					     unsigned long long *psmid,
-					     void *msg, size_t length)
-{
-	register unsigned long reg0 asm("0") = qid | 0x80000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm("2") = 0UL;
-	register unsigned long reg4 asm("4") = (unsigned long) msg;
-	register unsigned long reg5 asm("5") = (unsigned long) length;
-	register unsigned long reg6 asm("6") = 0UL;
-	register unsigned long reg7 asm("7") = 0UL;
-
-
-	asm volatile(
-		"0: .long 0xb2ae0064\n"		/* DQAP */
-		"   brc   6,0b\n"
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2),
-		  "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7)
-		: : "cc", "memory");
-	*psmid = (((unsigned long long) reg6) << 32) + reg7;
-	return reg1;
-}
-
-#endif /* _AP_ASM_H_ */
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 35a0c2b52f82..bf27fc4d1335 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -36,7 +36,6 @@
 #include <linux/debugfs.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
 #include "ap_debug.h"
 
 /*
@@ -174,24 +173,6 @@ static inline int ap_qact_available(void)
 	return 0;
 }
 
-/**
- * ap_test_queue(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @tbit: Test facilities bit
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-struct ap_queue_status ap_test_queue(ap_qid_t qid,
-				     int tbit,
-				     unsigned long *info)
-{
-	if (tbit)
-		qid |= 1UL << 23; /* set T bit*/
-	return ap_tapq(qid, info);
-}
-EXPORT_SYMBOL(ap_test_queue);
-
 /*
  * ap_query_configuration(): Fetch cryptographic config info
  *
@@ -200,7 +181,7 @@ EXPORT_SYMBOL(ap_test_queue);
  * is returned, e.g. if the PQAP(QCI) instruction is not
  * available, the return value will be -EOPNOTSUPP.
  */
-int ap_query_configuration(struct ap_config_info *info)
+static inline int ap_query_configuration(struct ap_config_info *info)
 {
 	if (!ap_configuration_available())
 		return -EOPNOTSUPP;
@@ -493,7 +474,7 @@ static int ap_poll_thread_start(void)
 		return 0;
 	mutex_lock(&ap_poll_thread_mutex);
 	ap_poll_kthread = kthread_run(ap_poll_thread, NULL, "appoll");
-	rc = PTR_RET(ap_poll_kthread);
+	rc = PTR_ERR_OR_ZERO(ap_poll_kthread);
 	if (rc)
 		ap_poll_kthread = NULL;
 	mutex_unlock(&ap_poll_thread_mutex);
@@ -1261,7 +1242,7 @@ static int __init ap_module_init(void)
 
 	/* Create /sys/devices/ap. */
 	ap_root_device = root_device_register("ap");
-	rc = PTR_RET(ap_root_device);
+	rc = PTR_ERR_OR_ZERO(ap_root_device);
 	if (rc)
 		goto out_bus;
 
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 6a273c5ebca5..936541937e15 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -15,6 +15,7 @@
 
 #include <linux/device.h>
 #include <linux/types.h>
+#include <asm/isc.h>
 #include <asm/ap.h>
 
 #define AP_DEVICES 256		/* Number of AP devices. */
diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c
index 2c726df210f6..c13e43292cb7 100644
--- a/drivers/s390/crypto/ap_card.c
+++ b/drivers/s390/crypto/ap_card.c
@@ -14,7 +14,6 @@
 #include <asm/facility.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
 
 /*
  * AP card related attributes.
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index ba3a2e13b0eb..e365171fe28f 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -14,26 +14,6 @@
 #include <asm/facility.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
-
-/**
- * ap_queue_irq_ctrl(): Control interruption on a AP queue.
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- *
- * Control interruption on the given AP queue.
- * Just a simple wrapper function for the low level PQAP(AQIC)
- * instruction available for other kernel modules.
- */
-struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid,
-					 struct ap_qirq_ctrl qirqctrl,
-					 void *ind)
-{
-	return ap_aqic(qid, qirqctrl, ind);
-}
-EXPORT_SYMBOL(ap_queue_irq_ctrl);
 
 /**
  * ap_queue_enable_interruption(): Enable interruption on an AP queue.
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 3929c8be8098..e663432395c1 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -699,7 +699,7 @@ static int query_crypto_facility(u16 cardnr, u16 domain,
 	/* fill request cprb param block with FQ request */
 	preqparm = (struct fqreqparm *) preqcblk->req_parmb;
 	memcpy(preqparm->subfunc_code, "FQ", 2);
-	strncpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
+	memcpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
 	preqparm->rule_array_len =
 		sizeof(preqparm->rule_array_len) + sizeof(preqparm->rule_array);
 	preqparm->lv1.len = sizeof(preqparm->lv1);
diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c
index 233e1e695208..da2c8dfd4d74 100644
--- a/drivers/s390/crypto/zcrypt_card.c
+++ b/drivers/s390/crypto/zcrypt_card.c
@@ -83,9 +83,21 @@ static ssize_t zcrypt_card_online_store(struct device *dev,
 static DEVICE_ATTR(online, 0644, zcrypt_card_online_show,
 		   zcrypt_card_online_store);
 
+static ssize_t zcrypt_card_load_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct zcrypt_card *zc = to_ap_card(dev)->private;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zc->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_card_load_show, NULL);
+
 static struct attribute *zcrypt_card_attrs[] = {
 	&dev_attr_type.attr,
 	&dev_attr_online.attr,
+	&dev_attr_load.attr,
 	NULL,
 };
 
diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h
index 011d61d8a4ae..1752622b95f7 100644
--- a/drivers/s390/crypto/zcrypt_cca_key.h
+++ b/drivers/s390/crypto/zcrypt_cca_key.h
@@ -99,7 +99,7 @@ struct cca_pvt_ext_CRT_sec {
  * @mex: pointer to user input data
  * @p: pointer to memory area for the key
  *
- * Returns the size of the key area or -EFAULT
+ * Returns the size of the key area or negative errno value.
  */
 static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
 {
@@ -118,6 +118,15 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
 	unsigned char *temp;
 	int i;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_modexpo(). However, do a plausibility check
+	 * here to make sure the following copy_from_user() can't be utilized
+	 * to compromise the system.
+	 */
+	if (WARN_ON_ONCE(mex->inputdatalength > 512))
+		return -EINVAL;
+
 	memset(key, 0, sizeof(*key));
 
 	key->pubHdr = static_pub_hdr;
@@ -178,6 +187,15 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p)
 	struct cca_public_sec *pub;
 	int short_len, long_len, pad_len, key_len, size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_crt(). However, do a plausibility check
+	 * here to make sure the following copy_from_user() can't be utilized
+	 * to compromise the system.
+	 */
+	if (WARN_ON_ONCE(crt->inputdatalength > 512))
+		return -EINVAL;
+
 	memset(key, 0, sizeof(*key));
 
 	short_len = (crt->inputdatalength + 1) / 2;
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index 97d4bacbc442..e70ae078c86b 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -246,7 +246,7 @@ int speed_idx_ep11(int req_type)
  * @ap_msg: pointer to AP message
  * @mex: pointer to user input data
  *
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
  */
 static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
 				       struct ap_message *ap_msg,
@@ -272,6 +272,14 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
 	} __packed * msg = ap_msg->message;
 	int size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_modexpo(). However, make sure the following
+	 * copy_from_user() never exceeds the allocated buffer space.
+	 */
+	if (WARN_ON_ONCE(mex->inputdatalength > PAGE_SIZE))
+		return -EINVAL;
+
 	/* VUD.ciphertext */
 	msg->length = mex->inputdatalength + 2;
 	if (copy_from_user(msg->text, mex->inputdata, mex->inputdatalength))
@@ -307,7 +315,7 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
  * @ap_msg: pointer to AP message
  * @crt: pointer to user input data
  *
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
  */
 static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
 				       struct ap_message *ap_msg,
@@ -334,6 +342,14 @@ static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
 	} __packed * msg = ap_msg->message;
 	int size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_crt(). However, make sure the following
+	 * copy_from_user() never exceeds the allocated buffer space.
+	 */
+	if (WARN_ON_ONCE(crt->inputdatalength > PAGE_SIZE))
+		return -EINVAL;
+
 	/* VUD.ciphertext */
 	msg->length = crt->inputdatalength + 2;
 	if (copy_from_user(msg->text, crt->inputdata, crt->inputdatalength))
diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c
index 720434e18007..91a52f268353 100644
--- a/drivers/s390/crypto/zcrypt_queue.c
+++ b/drivers/s390/crypto/zcrypt_queue.c
@@ -75,8 +75,20 @@ static ssize_t zcrypt_queue_online_store(struct device *dev,
 static DEVICE_ATTR(online, 0644, zcrypt_queue_online_show,
 		   zcrypt_queue_online_store);
 
+static ssize_t zcrypt_queue_load_show(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct zcrypt_queue *zq = to_ap_queue(dev)->private;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zq->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_queue_load_show, NULL);
+
 static struct attribute *zcrypt_queue_attrs[] = {
 	&dev_attr_online.attr,
+	&dev_attr_load.attr,
 	NULL,
 };
 
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 2a5fec55bf60..a246a618f9a4 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -829,6 +829,17 @@ struct qeth_trap_id {
 /*some helper functions*/
 #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "")
 
+static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf,
+					  unsigned int elements)
+{
+	unsigned int i;
+
+	for (i = 0; i < elements; i++)
+		memset(&buf->element[i], 0, sizeof(struct qdio_buffer_element));
+	buf->element[14].sflags = 0;
+	buf->element[15].sflags = 0;
+}
+
 /**
  * qeth_get_elements_for_range() -	find number of SBALEs to cover range.
  * @start:				Start of the address range.
@@ -1029,7 +1040,7 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *,
 						 __u16, __u16,
 						 enum qeth_prot_versions);
 int qeth_set_features(struct net_device *, netdev_features_t);
-void qeth_recover_features(struct net_device *dev);
+void qeth_enable_hw_features(struct net_device *dev);
 netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
 netdev_features_t qeth_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 8e1474f1ffac..d01ac29fd986 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -73,9 +73,6 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue,
 		struct qeth_qdio_out_buffer *buf,
 		enum iucv_tx_notify notification);
 static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf);
-static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
-		struct qeth_qdio_out_buffer *buf,
-		enum qeth_qdio_buffer_states newbufstate);
 static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int);
 
 struct workqueue_struct *qeth_wq;
@@ -489,6 +486,7 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	struct qaob *aob;
 	struct qeth_qdio_out_buffer *buffer;
 	enum iucv_tx_notify notification;
+	unsigned int i;
 
 	aob = (struct qaob *) phys_to_virt(phys_aob_addr);
 	QETH_CARD_TEXT(card, 5, "haob");
@@ -513,10 +511,18 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	qeth_notify_skbs(buffer->q, buffer, notification);
 
 	buffer->aob = NULL;
-	qeth_clear_output_buffer(buffer->q, buffer,
-				 QETH_QDIO_BUF_HANDLED_DELAYED);
+	/* Free dangling allocations. The attached skbs are handled by
+	 * qeth_cleanup_handled_pending().
+	 */
+	for (i = 0;
+	     i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
+	     i++) {
+		if (aob->sba[i] && buffer->is_header[i])
+			kmem_cache_free(qeth_core_header_cache,
+					(void *) aob->sba[i]);
+	}
+	atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED);
 
-	/* from here on: do not touch buffer anymore */
 	qdio_release_aob(aob);
 }
 
@@ -3759,6 +3765,10 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 			QETH_CARD_TEXT(queue->card, 5, "aob");
 			QETH_CARD_TEXT_(queue->card, 5, "%lx",
 					virt_to_phys(buffer->aob));
+
+			/* prepare the queue slot for re-use: */
+			qeth_scrub_qdio_buffer(buffer->buffer,
+					       QETH_MAX_BUFFER_ELEMENTS(card));
 			if (qeth_init_qdio_out_buf(queue, bidx)) {
 				QETH_CARD_TEXT(card, 2, "outofbuf");
 				qeth_schedule_recovery(card);
@@ -4834,7 +4844,7 @@ int qeth_vm_request_mac(struct qeth_card *card)
 		goto out;
 	}
 
-	ccw_device_get_id(CARD_RDEV(card), &id);
+	ccw_device_get_id(CARD_DDEV(card), &id);
 	request->resp_buf_len = sizeof(*response);
 	request->resp_version = DIAG26C_VERSION2;
 	request->op_code = DIAG26C_GET_MAC;
@@ -6459,28 +6469,27 @@ static int qeth_set_ipa_rx_csum(struct qeth_card *card, bool on)
 #define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO | \
 			  NETIF_F_IPV6_CSUM)
 /**
- * qeth_recover_features() - Restore device features after recovery
- * @dev:	the recovering net_device
- *
- * Caller must hold rtnl lock.
+ * qeth_enable_hw_features() - (Re-)Enable HW functions for device features
+ * @dev:	a net_device
  */
-void qeth_recover_features(struct net_device *dev)
+void qeth_enable_hw_features(struct net_device *dev)
 {
-	netdev_features_t features = dev->features;
 	struct qeth_card *card = dev->ml_priv;
+	netdev_features_t features;
 
+	rtnl_lock();
+	features = dev->features;
 	/* force-off any feature that needs an IPA sequence.
 	 * netdev_update_features() will restart them.
 	 */
 	dev->features &= ~QETH_HW_FEATURES;
 	netdev_update_features(dev);
-
-	if (features == dev->features)
-		return;
-	dev_warn(&card->gdev->dev,
-		 "Device recovery failed to restore all offload features\n");
+	if (features != dev->features)
+		dev_warn(&card->gdev->dev,
+			 "Device recovery failed to restore all offload features\n");
+	rtnl_unlock();
 }
-EXPORT_SYMBOL_GPL(qeth_recover_features);
+EXPORT_SYMBOL_GPL(qeth_enable_hw_features);
 
 int qeth_set_features(struct net_device *dev, netdev_features_t features)
 {
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index a7cb37da6a21..2487f0aeb165 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -140,7 +140,7 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac)
 
 static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
 {
-	enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+	enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
 					IPA_CMD_SETGMAC : IPA_CMD_SETVMAC;
 	int rc;
 
@@ -157,7 +157,7 @@ static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
 
 static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac)
 {
-	enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+	enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
 					IPA_CMD_DELGMAC : IPA_CMD_DELVMAC;
 	int rc;
 
@@ -501,27 +501,34 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p)
 		return -ERESTARTSYS;
 	}
 
+	/* avoid racing against concurrent state change: */
+	if (!mutex_trylock(&card->conf_mutex))
+		return -EAGAIN;
+
 	if (!qeth_card_hw_is_reachable(card)) {
 		ether_addr_copy(dev->dev_addr, addr->sa_data);
-		return 0;
+		goto out_unlock;
 	}
 
 	/* don't register the same address twice */
 	if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
 	    (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
-		return 0;
+		goto out_unlock;
 
 	/* add the new address, switch over, drop the old */
 	rc = qeth_l2_send_setmac(card, addr->sa_data);
 	if (rc)
-		return rc;
+		goto out_unlock;
 	ether_addr_copy(old_addr, dev->dev_addr);
 	ether_addr_copy(dev->dev_addr, addr->sa_data);
 
 	if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
 		qeth_l2_remove_mac(card, old_addr);
 	card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
-	return 0;
+
+out_unlock:
+	mutex_unlock(&card->conf_mutex);
+	return rc;
 }
 
 static void qeth_promisc_to_bridge(struct qeth_card *card)
@@ -1112,6 +1119,8 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		netif_carrier_off(card->dev);
 
 	qeth_set_allowed_threads(card, 0xffffffff, 0);
+
+	qeth_enable_hw_features(card->dev);
 	if (recover_flag == CARD_STATE_RECOVER) {
 		if (recovery_mode &&
 		    card->info.type != QETH_CARD_TYPE_OSN) {
@@ -1123,9 +1132,6 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		}
 		/* this also sets saved unicast addresses */
 		qeth_l2_set_rx_mode(card->dev);
-		rtnl_lock();
-		qeth_recover_features(card->dev);
-		rtnl_unlock();
 	}
 	/* let user_space know that device is online */
 	kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index e7fa479adf47..5905dc63e256 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2662,6 +2662,8 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		netif_carrier_on(card->dev);
 	else
 		netif_carrier_off(card->dev);
+
+	qeth_enable_hw_features(card->dev);
 	if (recover_flag == CARD_STATE_RECOVER) {
 		rtnl_lock();
 		if (recovery_mode)
@@ -2669,7 +2671,6 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		else
 			dev_open(card->dev);
 		qeth_l3_set_rx_mode(card->dev);
-		qeth_recover_features(card->dev);
 		rtnl_unlock();
 	}
 	qeth_trace_features(card);
diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c
index a3a8c8d9d717..94f4d8fe85e0 100644
--- a/drivers/s390/scsi/zfcp_aux.c
+++ b/drivers/s390/scsi/zfcp_aux.c
@@ -101,7 +101,7 @@ static void __init zfcp_init_device_setup(char *devstr)
 	token = strsep(&str, ",");
 	if (!token || strlen(token) >= ZFCP_BUS_ID_SIZE)
 		goto err_out;
-	strncpy(busid, token, ZFCP_BUS_ID_SIZE);
+	strlcpy(busid, token, ZFCP_BUS_ID_SIZE);
 
 	token = strsep(&str, ",");
 	if (!token || kstrtoull(token, 0, (unsigned long long *) &wwpn))
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 80aca2456353..768953881c9e 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -21,6 +21,7 @@ CFLAGS_gdth.o    = # -DDEBUG_GDTH=2 -D__SERIAL__ -D__COM2__ -DGDTH_STATISTICS
 obj-$(CONFIG_PCMCIA)		+= pcmcia/
 
 obj-$(CONFIG_SCSI)		+= scsi_mod.o
+obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_common.o
 
 obj-$(CONFIG_RAID_ATTRS)	+= raid_class.o
 
@@ -156,7 +157,6 @@ obj-$(CONFIG_SCSI_HISI_SAS) += hisi_sas/
 obj-$(CONFIG_SCSI_DEBUG)	+= scsi_debug.o
 scsi_mod-y			+= scsi.o hosts.o scsi_ioctl.o \
 				   scsicam.o scsi_error.o scsi_lib.o
-scsi_mod-y			+= scsi_common.o
 scsi_mod-$(CONFIG_SCSI_CONSTANTS) += constants.o
 scsi_mod-$(CONFIG_SCSI_DMA)	+= scsi_lib_dma.o
 scsi_mod-y			+= scsi_scan.o scsi_sysfs.o scsi_devinfo.o
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index a9831bd37a73..a57f3a7d4748 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -1974,7 +1974,6 @@ static void aac_set_safw_attr_all_targets(struct aac_dev *dev)
 	u32 lun_count, nexus;
 	u32 i, bus, target;
 	u8 expose_flag, attribs;
-	u8 devtype;
 
 	lun_count = aac_get_safw_phys_lun_count(dev);
 
@@ -1992,23 +1991,23 @@ static void aac_set_safw_attr_all_targets(struct aac_dev *dev)
 			continue;
 
 		if (expose_flag != 0) {
-			devtype = AAC_DEVTYPE_RAID_MEMBER;
-			goto update_devtype;
+			dev->hba_map[bus][target].devtype =
+				AAC_DEVTYPE_RAID_MEMBER;
+			continue;
 		}
 
 		if (nexus != 0 && (attribs & 8)) {
-			devtype = AAC_DEVTYPE_NATIVE_RAW;
+			dev->hba_map[bus][target].devtype =
+				AAC_DEVTYPE_NATIVE_RAW;
 			dev->hba_map[bus][target].rmw_nexus =
 					nexus;
 		} else
-			devtype = AAC_DEVTYPE_ARC_RAW;
+			dev->hba_map[bus][target].devtype =
+				AAC_DEVTYPE_ARC_RAW;
 
 		dev->hba_map[bus][target].scan_counter = dev->scan_counter;
 
 		aac_set_safw_target_qd(dev, bus, target);
-
-update_devtype:
-		dev->hba_map[bus][target].devtype = devtype;
 	}
 }
 
diff --git a/drivers/scsi/cxlflash/main.h b/drivers/scsi/cxlflash/main.h
index 2a3977823812..a39be94d110c 100644
--- a/drivers/scsi/cxlflash/main.h
+++ b/drivers/scsi/cxlflash/main.h
@@ -107,12 +107,12 @@ cxlflash_assign_ops(struct dev_dependent_vals *ddv)
 {
 	const struct cxlflash_backend_ops *ops = NULL;
 
-#ifdef CONFIG_OCXL
+#ifdef CONFIG_OCXL_BASE
 	if (ddv->flags & CXLFLASH_OCXL_DEV)
 		ops = &cxlflash_ocxl_ops;
 #endif
 
-#ifdef CONFIG_CXL
+#ifdef CONFIG_CXL_BASE
 	if (!(ddv->flags & CXLFLASH_OCXL_DEV))
 		ops = &cxlflash_cxl_ops;
 #endif
diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 0a95b5f25380..a43d44e7e7dd 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -88,10 +88,8 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 				      const struct file_operations *fops,
 				      void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	if (fops->owner && !try_module_get(fops->owner)) {
@@ -116,33 +114,18 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		goto err3;
 	}
 
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(ocxlflash_vfs_mount->mnt_sb, &this);
-	if (!path.dentry) {
-		dev_err(dev, "%s: d_alloc_pseudo failed\n", __func__);
-		rc = -ENOMEM;
-		goto err4;
-	}
-
-	path.mnt = mntget(ocxlflash_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file_pseudo(inode, ocxlflash_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		dev_err(dev, "%s: alloc_file failed rc=%d\n",
 			__func__, rc);
-		goto err5;
+		goto err4;
 	}
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 out:
 	return file;
-err5:
-	path_put(&path);
 err4:
 	iput(inode);
 err3:
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index e489d89cbb45..379890c4500b 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -339,7 +339,6 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 	struct scsi_sense_hdr sshdr;
 	u8 *cmd_buf = NULL;
 	u8 *scsi_cmd = NULL;
-	u8 *sense_buf = NULL;
 	int rc = 0;
 	int result = 0;
 	int retry_cnt = 0;
@@ -348,8 +347,7 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 retry:
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
 	scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
-	sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-	if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
+	if (unlikely(!cmd_buf || !scsi_cmd)) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -364,7 +362,7 @@ retry:
 	/* Drop the ioctl read semahpore across lengthy call */
 	up_read(&cfg->ioctl_rwsem);
 	result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf,
-			      CMD_BUFSIZE, sense_buf, &sshdr, to, CMD_RETRIES,
+			      CMD_BUFSIZE, NULL, &sshdr, to, CMD_RETRIES,
 			      0, 0, NULL);
 	down_read(&cfg->ioctl_rwsem);
 	rc = check_state(cfg);
@@ -395,7 +393,6 @@ retry:
 					if (retry_cnt++ < 1) {
 						kfree(cmd_buf);
 						kfree(scsi_cmd);
-						kfree(sense_buf);
 						goto retry;
 					}
 				}
@@ -426,7 +423,6 @@ retry:
 out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
-	kfree(sense_buf);
 
 	dev_dbg(dev, "%s: maxlba=%lld blklen=%d rc=%d\n",
 		__func__, gli->max_lba, gli->blk_len, rc);
diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c
index 66e445a17d6c..2c904bf16b65 100644
--- a/drivers/scsi/cxlflash/vlun.c
+++ b/drivers/scsi/cxlflash/vlun.c
@@ -426,7 +426,6 @@ static int write_same16(struct scsi_device *sdev,
 {
 	u8 *cmd_buf = NULL;
 	u8 *scsi_cmd = NULL;
-	u8 *sense_buf = NULL;
 	int rc = 0;
 	int result = 0;
 	u64 offset = lba;
@@ -440,8 +439,7 @@ static int write_same16(struct scsi_device *sdev,
 
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
 	scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
-	sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-	if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
+	if (unlikely(!cmd_buf || !scsi_cmd)) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -457,7 +455,7 @@ static int write_same16(struct scsi_device *sdev,
 		/* Drop the ioctl read semahpore across lengthy call */
 		up_read(&cfg->ioctl_rwsem);
 		result = scsi_execute(sdev, scsi_cmd, DMA_TO_DEVICE, cmd_buf,
-				      CMD_BUFSIZE, sense_buf, NULL, to,
+				      CMD_BUFSIZE, NULL, NULL, to,
 				      CMD_RETRIES, 0, 0, NULL);
 		down_read(&cfg->ioctl_rwsem);
 		rc = check_state(cfg);
@@ -482,7 +480,6 @@ static int write_same16(struct scsi_device *sdev,
 out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
-	kfree(sense_buf);
 	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index ea23c8dffc25..ffec695e0bfb 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -754,9 +754,9 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 	case ELS_LOGO:
 		if (fip->mode == FIP_MODE_VN2VN) {
 			if (fip->state != FIP_ST_VNMP_UP)
-				return -EINVAL;
+				goto drop;
 			if (ntoh24(fh->fh_d_id) == FC_FID_FLOGI)
-				return -EINVAL;
+				goto drop;
 		} else {
 			if (fip->state != FIP_ST_ENABLED)
 				return 0;
@@ -799,9 +799,9 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 	fip->send(fip, skb);
 	return -EINPROGRESS;
 drop:
-	kfree_skb(skb);
 	LIBFCOE_FIP_DBG(fip, "drop els_send op %u d_id %x\n",
 			op, ntoh24(fh->fh_d_id));
+	kfree_skb(skb);
 	return -EINVAL;
 }
 EXPORT_SYMBOL(fcoe_ctlr_els_send);
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 15c7f3b6f35e..58bb70b886d7 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -3440,11 +3440,11 @@ static void hpsa_get_enclosure_info(struct ctlr_info *h,
 	struct ext_report_lun_entry *rle = &rlep->LUN[rle_index];
 	u16 bmic_device_index = 0;
 
-	bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]);
-
-	encl_dev->sas_address =
+	encl_dev->eli =
 		hpsa_get_enclosure_logical_identifier(h, scsi3addr);
 
+	bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]);
+
 	if (encl_dev->target == -1 || encl_dev->lun == -1) {
 		rc = IO_OK;
 		goto out;
@@ -9697,7 +9697,24 @@ hpsa_sas_get_linkerrors(struct sas_phy *phy)
 static int
 hpsa_sas_get_enclosure_identifier(struct sas_rphy *rphy, u64 *identifier)
 {
-	*identifier = rphy->identify.sas_address;
+	struct Scsi_Host *shost = phy_to_shost(rphy);
+	struct ctlr_info *h;
+	struct hpsa_scsi_dev_t *sd;
+
+	if (!shost)
+		return -ENXIO;
+
+	h = shost_to_hba(shost);
+
+	if (!h)
+		return -ENXIO;
+
+	sd = hpsa_find_device_by_sas_rphy(h, rphy);
+	if (!sd)
+		return -ENXIO;
+
+	*identifier = sd->eli;
+
 	return 0;
 }
 
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index fb9f5e7f8209..59e023696fff 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -68,6 +68,7 @@ struct hpsa_scsi_dev_t {
 #define RAID_CTLR_LUNID "\0\0\0\0\0\0\0\0"
 	unsigned char device_id[16];    /* from inquiry pg. 0x83 */
 	u64 sas_address;
+	u64 eli;			/* from report diags. */
 	unsigned char vendor[8];        /* bytes 8-15 of inquiry data */
 	unsigned char model[16];        /* bytes 16-31 of inquiry data */
 	unsigned char rev;		/* byte 2 of inquiry data */
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 0a9b8b387bd2..02d65dce74e5 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -760,7 +760,6 @@ static void ipr_mask_and_clear_interrupts(struct ipr_ioa_cfg *ioa_cfg,
 		ioa_cfg->hrrq[i].allow_interrupts = 0;
 		spin_unlock(&ioa_cfg->hrrq[i]._lock);
 	}
-	wmb();
 
 	/* Set interrupt mask to stop all new interrupts */
 	if (ioa_cfg->sis64)
@@ -8403,7 +8402,6 @@ static int ipr_reset_enable_ioa(struct ipr_cmnd *ipr_cmd)
 		ioa_cfg->hrrq[i].allow_interrupts = 1;
 		spin_unlock(&ioa_cfg->hrrq[i]._lock);
 	}
-	wmb();
 	if (ioa_cfg->sis64) {
 		/* Set the adapter to the correct endian mode. */
 		writel(IPR_ENDIAN_SWAP_KEY, ioa_cfg->regs.endian_swap_reg);
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 31d31aad3de1..89b1f1af2fd4 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -2164,6 +2164,7 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 		FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n",
 			     fc_rport_state(rdata));
 
+		rdata->flags &= ~FC_RP_STARTED;
 		fc_rport_enter_delete(rdata, RPORT_EV_STOP);
 		mutex_unlock(&rdata->rp_mutex);
 		kref_put(&rdata->kref, fc_rport_destroy);
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index d6093838f5f2..c972cc2b3d5b 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -284,11 +284,11 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode)
 		 */
 		if (opcode != ISCSI_OP_SCSI_DATA_OUT) {
 			iscsi_conn_printk(KERN_INFO, conn,
-					  "task [op %x/%x itt "
+					  "task [op %x itt "
 					  "0x%x/0x%x] "
 					  "rejected.\n",
-					  task->hdr->opcode, opcode,
-					  task->itt, task->hdr_itt);
+					  opcode, task->itt,
+					  task->hdr_itt);
 			return -EACCES;
 		}
 		/*
@@ -297,10 +297,10 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode)
 		 */
 		if (conn->session->fast_abort) {
 			iscsi_conn_printk(KERN_INFO, conn,
-					  "task [op %x/%x itt "
+					  "task [op %x itt "
 					  "0x%x/0x%x] fast abort.\n",
-					  task->hdr->opcode, opcode,
-					  task->itt, task->hdr_itt);
+					  opcode, task->itt,
+					  task->hdr_itt);
 			return -EACCES;
 		}
 		break;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 569392d0d4c9..e44c91edf92d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3343,11 +3343,10 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 					spinlock_t *writeq_lock)
 {
 	unsigned long flags;
-	__u64 data_out = b;
 
 	spin_lock_irqsave(writeq_lock, flags);
-	writel((u32)(data_out), addr);
-	writel((u32)(data_out >> 32), (addr + 4));
+	__raw_writel((u32)(b), addr);
+	__raw_writel((u32)(b >> 32), (addr + 4));
 	mmiowb();
 	spin_unlock_irqrestore(writeq_lock, flags);
 }
@@ -3367,7 +3366,8 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 static inline void
 _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
 {
-	writeq(b, addr);
+	__raw_writeq(b, addr);
+	mmiowb();
 }
 #else
 static inline void
@@ -5268,7 +5268,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 
 	/* send message 32-bits at a time */
 	for (i = 0, failed = 0; i < request_bytes/4 && !failed; i++) {
-		writel((u32)(request[i]), &ioc->chip->Doorbell);
+		writel(cpu_to_le32(request[i]), &ioc->chip->Doorbell);
 		if ((_base_wait_for_doorbell_ack(ioc, 5)))
 			failed = 1;
 	}
@@ -5289,7 +5289,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 	}
 
 	/* read the first two 16-bits, it gives the total length of the reply */
-	reply[0] = (u16)(readl(&ioc->chip->Doorbell)
+	reply[0] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 	if ((_base_wait_for_doorbell_int(ioc, 5))) {
@@ -5298,7 +5298,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 			ioc->name, __LINE__);
 		return -EFAULT;
 	}
-	reply[1] = (u16)(readl(&ioc->chip->Doorbell)
+	reply[1] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 
@@ -5312,7 +5312,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 		if (i >=  reply_bytes/2) /* overflow case */
 			readl(&ioc->chip->Doorbell);
 		else
-			reply[i] = (u16)(readl(&ioc->chip->Doorbell)
+			reply[i] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 			    & MPI2_DOORBELL_DATA_MASK);
 		writel(0, &ioc->chip->HostInterruptStatus);
 	}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b8d131a455d0..dd738ae5c75b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -4568,7 +4568,7 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
 		    MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG |
 		    MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD;
 		mpi_request->CDB.EEDP32.PrimaryReferenceTag =
-		    cpu_to_be32(scsi_prot_ref_tag(scmd));
+		    cpu_to_be32(t10_pi_ref_tag(scmd->request));
 		break;
 
 	case SCSI_PROT_DIF_TYPE3:
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 90394cef0f41..0a5dd5595dd3 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -3295,6 +3295,11 @@ static int __qedf_probe(struct pci_dev *pdev, int mode)
 
 	init_completion(&qedf->flogi_compl);
 
+	status = qed_ops->common->update_drv_state(qedf->cdev, true);
+	if (status)
+		QEDF_ERR(&(qedf->dbg_ctx),
+			"Failed to send drv state to MFW.\n");
+
 	memset(&link_params, 0, sizeof(struct qed_link_params));
 	link_params.link_up = true;
 	status = qed_ops->common->set_link(qedf->cdev, &link_params);
@@ -3343,6 +3348,7 @@ static int qedf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 static void __qedf_remove(struct pci_dev *pdev, int mode)
 {
 	struct qedf_ctx *qedf;
+	int rc;
 
 	if (!pdev) {
 		QEDF_ERR(NULL, "pdev is NULL.\n");
@@ -3437,6 +3443,12 @@ static void __qedf_remove(struct pci_dev *pdev, int mode)
 		qed_ops->common->set_power_state(qedf->cdev, PCI_D0);
 		pci_set_drvdata(pdev, NULL);
 	}
+
+	rc = qed_ops->common->update_drv_state(qedf->cdev, false);
+	if (rc)
+		QEDF_ERR(&(qedf->dbg_ctx),
+			"Failed to send drv state to MFW.\n");
+
 	qed_ops->common->slowpath_stop(qedf->cdev);
 	qed_ops->common->remove(qedf->cdev);
 
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index cf274a79e77a..cff83b9457f7 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -888,7 +888,7 @@ static void qedi_get_boot_tgt_info(struct nvm_iscsi_block *block,
 	ipv6_en = !!(block->generic.ctrl_flags &
 		     NVM_ISCSI_CFG_GEN_IPV6_ENABLED);
 
-	snprintf(tgt->iscsi_name, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n",
+	snprintf(tgt->iscsi_name, sizeof(tgt->iscsi_name), "%s\n",
 		 block->target[index].target_name.byte);
 
 	tgt->ipv6_en = ipv6_en;
@@ -2273,6 +2273,7 @@ kset_free:
 static void __qedi_remove(struct pci_dev *pdev, int mode)
 {
 	struct qedi_ctx *qedi = pci_get_drvdata(pdev);
+	int rval;
 
 	if (qedi->tmf_thread) {
 		flush_workqueue(qedi->tmf_thread);
@@ -2302,6 +2303,10 @@ static void __qedi_remove(struct pci_dev *pdev, int mode)
 	if (mode == QEDI_MODE_NORMAL)
 		qedi_free_iscsi_pf_param(qedi);
 
+	rval = qedi_ops->common->update_drv_state(qedi->cdev, false);
+	if (rval)
+		QEDI_ERR(&qedi->dbg_ctx, "Failed to send drv state to MFW\n");
+
 	if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags)) {
 		qedi_ops->common->slowpath_stop(qedi->cdev);
 		qedi_ops->common->remove(qedi->cdev);
@@ -2576,6 +2581,12 @@ static int __qedi_probe(struct pci_dev *pdev, int mode)
 		if (qedi_setup_boot_info(qedi))
 			QEDI_ERR(&qedi->dbg_ctx,
 				 "No iSCSI boot target configured\n");
+
+		rc = qedi_ops->common->update_drv_state(qedi->cdev, true);
+		if (rc)
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Failed to send drv state to MFW\n");
+
 	}
 
 	return 0;
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 89a4999fa631..c8731568f9c4 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -2141,6 +2141,7 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 		msleep(1000);
 
 	qla24xx_disable_vp(vha);
+	qla2x00_wait_for_sess_deletion(vha);
 
 	vha->flags.delete_progress = 1;
 
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 9442e18aef6f..0f94b1d62d3f 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -361,6 +361,8 @@ struct ct_arg {
 	dma_addr_t	rsp_dma;
 	u32		req_size;
 	u32		rsp_size;
+	u32		req_allocated_size;
+	u32		rsp_allocated_size;
 	void		*req;
 	void		*rsp;
 	port_id_t	id;
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index f68eb6096559..2660a48d918a 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -214,6 +214,7 @@ void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *,
 int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *);
 int qla24xx_async_abort_cmd(srb_t *);
 int qla24xx_post_relogin_work(struct scsi_qla_host *vha);
+void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *);
 
 /*
  * Global Functions in qla_mid.c source file.
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 4bc2b66b299f..7a3744006419 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -556,7 +556,7 @@ err2:
 		/* please ignore kernel warning. otherwise, we have mem leak. */
 		if (sp->u.iocb_cmd.u.ctarg.req) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 			    sp->u.iocb_cmd.u.ctarg.req,
 			    sp->u.iocb_cmd.u.ctarg.req_dma);
 			sp->u.iocb_cmd.u.ctarg.req = NULL;
@@ -564,7 +564,7 @@ err2:
 
 		if (sp->u.iocb_cmd.u.ctarg.rsp) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 			    sp->u.iocb_cmd.u.ctarg.rsp,
 			    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -617,6 +617,7 @@ static int qla_async_rftid(scsi_qla_host_t *vha, port_id_t *d_id)
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -627,6 +628,7 @@ static int qla_async_rftid(scsi_qla_host_t *vha, port_id_t *d_id)
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -712,6 +714,7 @@ static int qla_async_rffid(scsi_qla_host_t *vha, port_id_t *d_id,
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -722,6 +725,7 @@ static int qla_async_rffid(scsi_qla_host_t *vha, port_id_t *d_id,
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -802,6 +806,7 @@ static int qla_async_rnnid(scsi_qla_host_t *vha, port_id_t *d_id,
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -812,6 +817,7 @@ static int qla_async_rnnid(scsi_qla_host_t *vha, port_id_t *d_id,
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -909,6 +915,7 @@ static int qla_async_rsnn_nn(scsi_qla_host_t *vha)
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -919,6 +926,7 @@ static int qla_async_rsnn_nn(scsi_qla_host_t *vha)
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -3388,14 +3396,14 @@ void qla24xx_sp_unmap(scsi_qla_host_t *vha, srb_t *sp)
 {
 	if (sp->u.iocb_cmd.u.ctarg.req) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-			sizeof(struct ct_sns_pkt),
+			sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 			sp->u.iocb_cmd.u.ctarg.req,
 			sp->u.iocb_cmd.u.ctarg.req_dma);
 		sp->u.iocb_cmd.u.ctarg.req = NULL;
 	}
 	if (sp->u.iocb_cmd.u.ctarg.rsp) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-			sizeof(struct ct_sns_pkt),
+			sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 			sp->u.iocb_cmd.u.ctarg.rsp,
 			sp->u.iocb_cmd.u.ctarg.rsp_dma);
 		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -3596,14 +3604,14 @@ static void qla2x00_async_gpnid_sp_done(void *s, int res)
 		/* please ignore kernel warning. otherwise, we have mem leak. */
 		if (sp->u.iocb_cmd.u.ctarg.req) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-				sizeof(struct ct_sns_pkt),
+				sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 				sp->u.iocb_cmd.u.ctarg.req,
 				sp->u.iocb_cmd.u.ctarg.req_dma);
 			sp->u.iocb_cmd.u.ctarg.req = NULL;
 		}
 		if (sp->u.iocb_cmd.u.ctarg.rsp) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-				sizeof(struct ct_sns_pkt),
+				sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 				sp->u.iocb_cmd.u.ctarg.rsp,
 				sp->u.iocb_cmd.u.ctarg.rsp_dma);
 			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -3654,6 +3662,7 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id)
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 		sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 		GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "Failed to allocate ct_sns request.\n");
@@ -3663,6 +3672,7 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id)
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 		sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 		GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "Failed to allocate ct_sns request.\n");
@@ -3698,6 +3708,10 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id)
 	return rval;
 
 done_free_sp:
+	spin_lock_irqsave(&vha->hw->vport_slock, flags);
+	list_del(&sp->elem);
+	spin_unlock_irqrestore(&vha->hw->vport_slock, flags);
+
 	if (sp->u.iocb_cmd.u.ctarg.req) {
 		dma_free_coherent(&vha->hw->pdev->dev,
 			sizeof(struct ct_sns_pkt),
@@ -4142,14 +4156,14 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res)
 			 */
 			if (sp->u.iocb_cmd.u.ctarg.req) {
 				dma_free_coherent(&vha->hw->pdev->dev,
-				    sizeof(struct ct_sns_pkt),
+				    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 				    sp->u.iocb_cmd.u.ctarg.req,
 				    sp->u.iocb_cmd.u.ctarg.req_dma);
 				sp->u.iocb_cmd.u.ctarg.req = NULL;
 			}
 			if (sp->u.iocb_cmd.u.ctarg.rsp) {
 				dma_free_coherent(&vha->hw->pdev->dev,
-				    sizeof(struct ct_sns_pkt),
+				    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 				    sp->u.iocb_cmd.u.ctarg.rsp,
 				    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 				sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -4179,14 +4193,14 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res)
 		/* please ignore kernel warning. Otherwise, we have mem leak. */
 		if (sp->u.iocb_cmd.u.ctarg.req) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 			    sp->u.iocb_cmd.u.ctarg.req,
 			    sp->u.iocb_cmd.u.ctarg.req_dma);
 			sp->u.iocb_cmd.u.ctarg.req = NULL;
 		}
 		if (sp->u.iocb_cmd.u.ctarg.rsp) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 			    sp->u.iocb_cmd.u.ctarg.rsp,
 			    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -4281,14 +4295,14 @@ static int qla24xx_async_gnnft(scsi_qla_host_t *vha, struct srb *sp,
 done_free_sp:
 	if (sp->u.iocb_cmd.u.ctarg.req) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-		    sizeof(struct ct_sns_pkt),
+		    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 		    sp->u.iocb_cmd.u.ctarg.req,
 		    sp->u.iocb_cmd.u.ctarg.req_dma);
 		sp->u.iocb_cmd.u.ctarg.req = NULL;
 	}
 	if (sp->u.iocb_cmd.u.ctarg.rsp) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-		    sizeof(struct ct_sns_pkt),
+		    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 		    sp->u.iocb_cmd.u.ctarg.rsp,
 		    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -4349,6 +4363,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
 		sp->u.iocb_cmd.u.ctarg.req = dma_zalloc_coherent(
 			&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt),
 			&sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL);
+		sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 		if (!sp->u.iocb_cmd.u.ctarg.req) {
 			ql_log(ql_log_warn, vha, 0xffff,
 			    "Failed to allocate ct_sns request.\n");
@@ -4366,6 +4381,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
 		sp->u.iocb_cmd.u.ctarg.rsp = dma_zalloc_coherent(
 			&vha->hw->pdev->dev, rspsz,
 			&sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL);
+		sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 		if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 			ql_log(ql_log_warn, vha, 0xffff,
 			    "Failed to allocate ct_sns request.\n");
@@ -4425,14 +4441,14 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
 done_free_sp:
 	if (sp->u.iocb_cmd.u.ctarg.req) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-		    sizeof(struct ct_sns_pkt),
+		    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 		    sp->u.iocb_cmd.u.ctarg.req,
 		    sp->u.iocb_cmd.u.ctarg.req_dma);
 		sp->u.iocb_cmd.u.ctarg.req = NULL;
 	}
 	if (sp->u.iocb_cmd.u.ctarg.rsp) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-		    sizeof(struct ct_sns_pkt),
+		    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 		    sp->u.iocb_cmd.u.ctarg.rsp,
 		    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 7b675243bd16..1b19b954bbae 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -591,12 +591,14 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 				conflict_fcport =
 					qla2x00_find_fcport_by_wwpn(vha,
 					    e->port_name, 0);
-				ql_dbg(ql_dbg_disc, vha, 0x20e6,
-				    "%s %d %8phC post del sess\n",
-				    __func__, __LINE__,
-				    conflict_fcport->port_name);
-				qlt_schedule_sess_for_deletion
-					(conflict_fcport);
+				if (conflict_fcport) {
+					qlt_schedule_sess_for_deletion
+						(conflict_fcport);
+					ql_dbg(ql_dbg_disc, vha, 0x20e6,
+					    "%s %d %8phC post del sess\n",
+					    __func__, __LINE__,
+					    conflict_fcport->port_name);
+				}
 			}
 
 			/* FW already picked this loop id for another fcport */
@@ -1487,11 +1489,10 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun,
 
 	wait_for_completion(&tm_iocb->u.tmf.comp);
 
-	rval = tm_iocb->u.tmf.comp_status == CS_COMPLETE ?
-	    QLA_SUCCESS : QLA_FUNCTION_FAILED;
+	rval = tm_iocb->u.tmf.data;
 
-	if ((rval != QLA_SUCCESS) || tm_iocb->u.tmf.data) {
-		ql_dbg(ql_dbg_taskm, vha, 0x8030,
+	if (rval != QLA_SUCCESS) {
+		ql_log(ql_log_warn, vha, 0x8030,
 		    "TM IOCB failed (%x).\n", rval);
 	}
 
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 37ae0f6d8ae5..59fd5a9dfeb8 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -222,6 +222,8 @@ qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag)
 	sp->fcport = fcport;
 	sp->iocbs = 1;
 	sp->vha = qpair->vha;
+	INIT_LIST_HEAD(&sp->elem);
+
 done:
 	if (!sp)
 		QLA_QPAIR_MARK_NOT_BUSY(qpair);
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index a91cca52b5d5..dd93a22fe843 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2130,34 +2130,11 @@ __qla2x00_alloc_iocbs(struct qla_qpair *qpair, srb_t *sp)
 	req_cnt = 1;
 	handle = 0;
 
-	if (!sp)
-		goto skip_cmd_array;
-
-	/* Check for room in outstanding command list. */
-	handle = req->current_outstanding_cmd;
-	for (index = 1; index < req->num_outstanding_cmds; index++) {
-		handle++;
-		if (handle == req->num_outstanding_cmds)
-			handle = 1;
-		if (!req->outstanding_cmds[handle])
-			break;
-	}
-	if (index == req->num_outstanding_cmds) {
-		ql_log(ql_log_warn, vha, 0x700b,
-		    "No room on outstanding cmd array.\n");
-		goto queuing_error;
-	}
-
-	/* Prep command array. */
-	req->current_outstanding_cmd = handle;
-	req->outstanding_cmds[handle] = sp;
-	sp->handle = handle;
-
-	/* Adjust entry-counts as needed. */
-	if (sp->type != SRB_SCSI_CMD)
+	if (sp && (sp->type != SRB_SCSI_CMD)) {
+		/* Adjust entry-counts as needed. */
 		req_cnt = sp->iocbs;
+	}
 
-skip_cmd_array:
 	/* Check for room on request queue. */
 	if (req->cnt < req_cnt + 2) {
 		if (qpair->use_shadow_reg)
@@ -2183,6 +2160,28 @@ skip_cmd_array:
 	if (req->cnt < req_cnt + 2)
 		goto queuing_error;
 
+	if (sp) {
+		/* Check for room in outstanding command list. */
+		handle = req->current_outstanding_cmd;
+		for (index = 1; index < req->num_outstanding_cmds; index++) {
+			handle++;
+			if (handle == req->num_outstanding_cmds)
+				handle = 1;
+			if (!req->outstanding_cmds[handle])
+				break;
+		}
+		if (index == req->num_outstanding_cmds) {
+			ql_log(ql_log_warn, vha, 0x700b,
+			    "No room on outstanding cmd array.\n");
+			goto queuing_error;
+		}
+
+		/* Prep command array. */
+		req->current_outstanding_cmd = handle;
+		req->outstanding_cmds[handle] = sp;
+		sp->handle = handle;
+	}
+
 	/* Prep packet */
 	req->cnt -= req_cnt;
 	pkt = req->ring_ptr;
@@ -2195,6 +2194,8 @@ skip_cmd_array:
 		pkt->handle = handle;
 	}
 
+	return pkt;
+
 queuing_error:
 	qpair->tgt_counters.num_alloc_iocb_failed++;
 	return pkt;
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 9fa5a2557f2c..7756106d4555 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -631,6 +631,9 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
 	unsigned long	flags;
 	fc_port_t	*fcport = NULL;
 
+	if (!vha->hw->flags.fw_started)
+		return;
+
 	/* Setup to process RIO completion. */
 	handle_cnt = 0;
 	if (IS_CNA_CAPABLE(ha))
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 7e875f575229..f0ec13d48bf3 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -4220,6 +4220,9 @@ qla25xx_init_req_que(struct scsi_qla_host *vha, struct req_que *req)
 	mbx_cmd_t *mcp = &mc;
 	struct qla_hw_data *ha = vha->hw;
 
+	if (!ha->flags.fw_started)
+		return QLA_SUCCESS;
+
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d3,
 	    "Entered %s.\n", __func__);
 
@@ -4289,6 +4292,9 @@ qla25xx_init_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp)
 	mbx_cmd_t *mcp = &mc;
 	struct qla_hw_data *ha = vha->hw;
 
+	if (!ha->flags.fw_started)
+		return QLA_SUCCESS;
+
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d6,
 	    "Entered %s.\n", __func__);
 
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index f6f0a759a7c2..aa727d07b702 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -152,11 +152,18 @@ int
 qla24xx_disable_vp(scsi_qla_host_t *vha)
 {
 	unsigned long flags;
-	int ret;
+	int ret = QLA_SUCCESS;
+	fc_port_t *fcport;
+
+	if (vha->hw->flags.fw_started)
+		ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL);
 
-	ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL);
 	atomic_set(&vha->loop_state, LOOP_DOWN);
 	atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
+	list_for_each_entry(fcport, &vha->vp_fcports, list)
+		fcport->logout_on_delete = 0;
+
+	qla2x00_mark_all_devices_lost(vha, 0);
 
 	/* Remove port id from vp target map */
 	spin_lock_irqsave(&vha->hw->hardware_lock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index e881fce7477a..1fbd16c8c9a7 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -303,6 +303,7 @@ static void qla2x00_free_device(scsi_qla_host_t *);
 static int qla2xxx_map_queues(struct Scsi_Host *shost);
 static void qla2x00_destroy_deferred_work(struct qla_hw_data *);
 
+
 struct scsi_host_template qla2xxx_driver_template = {
 	.module			= THIS_MODULE,
 	.name			= QLA2XXX_DRIVER_NAME,
@@ -1147,7 +1148,7 @@ static inline int test_fcport_count(scsi_qla_host_t *vha)
  * qla2x00_wait_for_sess_deletion can only be called from remove_one.
  * it has dependency on UNLOADING flag to stop device discovery
  */
-static void
+void
 qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha)
 {
 	qla2x00_mark_all_devices_lost(vha, 0);
@@ -3180,6 +3181,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    "req->req_q_in=%p req->req_q_out=%p rsp->rsp_q_in=%p rsp->rsp_q_out=%p.\n",
 	    req->req_q_in, req->req_q_out, rsp->rsp_q_in, rsp->rsp_q_out);
 
+	ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0);
+
 	if (ha->isp_ops->initialize_adapter(base_vha)) {
 		ql_log(ql_log_fatal, base_vha, 0x00d6,
 		    "Failed to initialize adapter - Adapter flags %x.\n",
@@ -3216,8 +3219,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    host->can_queue, base_vha->req,
 	    base_vha->mgmt_svr_loop_id, host->sg_tablesize);
 
-	ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0);
-
 	if (ha->mqenable) {
 		bool mq = false;
 		bool startit = false;
@@ -3603,6 +3604,8 @@ qla2x00_remove_one(struct pci_dev *pdev)
 
 	base_vha = pci_get_drvdata(pdev);
 	ha = base_vha->hw;
+	ql_log(ql_log_info, base_vha, 0xb079,
+	    "Removing driver\n");
 
 	/* Indicate device removal to prevent future board_disable and wait
 	 * until any pending board_disable has completed. */
@@ -3625,6 +3628,21 @@ qla2x00_remove_one(struct pci_dev *pdev)
 	}
 	qla2x00_wait_for_hba_ready(base_vha);
 
+	if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha)) {
+		if (ha->flags.fw_started)
+			qla2x00_abort_isp_cleanup(base_vha);
+	} else if (!IS_QLAFX00(ha)) {
+		if (IS_QLA8031(ha)) {
+			ql_dbg(ql_dbg_p3p, base_vha, 0xb07e,
+			    "Clearing fcoe driver presence.\n");
+			if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS)
+				ql_dbg(ql_dbg_p3p, base_vha, 0xb079,
+				    "Error while clearing DRV-Presence.\n");
+		}
+
+		qla2x00_try_to_stop_firmware(base_vha);
+	}
+
 	qla2x00_wait_for_sess_deletion(base_vha);
 
 	/*
@@ -3648,14 +3666,6 @@ qla2x00_remove_one(struct pci_dev *pdev)
 
 	qla2x00_delete_all_vps(ha, base_vha);
 
-	if (IS_QLA8031(ha)) {
-		ql_dbg(ql_dbg_p3p, base_vha, 0xb07e,
-		    "Clearing fcoe driver presence.\n");
-		if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS)
-			ql_dbg(ql_dbg_p3p, base_vha, 0xb079,
-			    "Error while clearing DRV-Presence.\n");
-	}
-
 	qla2x00_abort_all_cmds(base_vha, DID_NO_CONNECT << 16);
 
 	qla2x00_dfs_remove(base_vha);
@@ -3715,24 +3725,6 @@ qla2x00_free_device(scsi_qla_host_t *vha)
 		qla2x00_stop_timer(vha);
 
 	qla25xx_delete_queues(vha);
-
-	if (ha->flags.fce_enabled)
-		qla2x00_disable_fce_trace(vha, NULL, NULL);
-
-	if (ha->eft)
-		qla2x00_disable_eft_trace(vha);
-
-	if (IS_QLA25XX(ha) ||  IS_QLA2031(ha) || IS_QLA27XX(ha)) {
-		if (ha->flags.fw_started)
-			qla2x00_abort_isp_cleanup(vha);
-	} else {
-		if (ha->flags.fw_started) {
-			/* Stop currently executing firmware. */
-			qla2x00_try_to_stop_firmware(vha);
-			ha->flags.fw_started = 0;
-		}
-	}
-
 	vha->flags.online = 0;
 
 	/* turn-off interrupts on the card */
@@ -6028,8 +6020,9 @@ qla2x00_do_dpc(void *data)
 				set_bit(ISP_ABORT_NEEDED, &base_vha->dpc_flags);
 		}
 
-		if (test_and_clear_bit(ISP_ABORT_NEEDED,
-						&base_vha->dpc_flags)) {
+		if (test_and_clear_bit
+		    (ISP_ABORT_NEEDED, &base_vha->dpc_flags) &&
+		    !test_bit(UNLOADING, &base_vha->dpc_flags)) {
 
 			ql_dbg(ql_dbg_dpc, base_vha, 0x4007,
 			    "ISP abort scheduled.\n");
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index 04458eb19d38..4499c787165f 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -1880,6 +1880,9 @@ qla24xx_beacon_off(struct scsi_qla_host *vha)
 	if (IS_P3P_TYPE(ha))
 		return QLA_SUCCESS;
 
+	if (!ha->flags.fw_started)
+		return QLA_SUCCESS;
+
 	ha->beacon_blink_led = 0;
 
 	if (IS_QLA2031(ha) || IS_QLA27XX(ha))
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 0fea2e2326be..1027b0cb7fa3 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1224,7 +1224,6 @@ static void qla24xx_chk_fcp_state(struct fc_port *sess)
 void qlt_schedule_sess_for_deletion(struct fc_port *sess)
 {
 	struct qla_tgt *tgt = sess->tgt;
-	struct qla_hw_data *ha = sess->vha->hw;
 	unsigned long flags;
 
 	if (sess->disc_state == DSC_DELETE_PEND)
@@ -1241,16 +1240,16 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess)
 			return;
 	}
 
-	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 	if (sess->deleted == QLA_SESS_DELETED)
 		sess->logout_on_delete = 0;
 
+	spin_lock_irqsave(&sess->vha->work_lock, flags);
 	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
-		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+		spin_unlock_irqrestore(&sess->vha->work_lock, flags);
 		return;
 	}
 	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
-	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+	spin_unlock_irqrestore(&sess->vha->work_lock, flags);
 
 	sess->disc_state = DSC_DELETE_PEND;
 
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 24d7496cd9e2..364e71861bfd 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -5507,9 +5507,9 @@ static void __exit scsi_debug_exit(void)
 	int k = sdebug_add_host;
 
 	stop_all_queued();
-	free_all_queued();
 	for (; k; k--)
 		sdebug_remove_adapter();
+	free_all_queued();
 	driver_unregister(&sdebug_driverfs_driver);
 	bus_unregister(&pseudo_lld_bus);
 	root_device_unregister(pseudo_primary);
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 8932ae81a15a..2715cdaa669c 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -296,6 +296,20 @@ enum blk_eh_timer_return scsi_times_out(struct request *req)
 		rtn = host->hostt->eh_timed_out(scmd);
 
 	if (rtn == BLK_EH_DONE) {
+		/*
+		 * For blk-mq, we must set the request state to complete now
+		 * before sending the request to the scsi error handler. This
+		 * will prevent a use-after-free in the event the LLD manages
+		 * to complete the request before the error handler finishes
+		 * processing this timed out request.
+		 *
+		 * If the request was already completed, then the LLD beat the
+		 * time out handler from transferring the request to the scsi
+		 * error handler. In that case we can return immediately as no
+		 * further action is required.
+		 */
+		if (req->q->mq_ops && !blk_mq_mark_complete(req))
+			return rtn;
 		if (scsi_abort_command(scmd) != SUCCESS) {
 			set_host_byte(scmd, DID_TIME_OUT);
 			scsi_eh_scmd_add(scmd);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 41e9ac9fc138..9cb9a166fa0c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -238,7 +238,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 
 
 /**
- * scsi_execute - insert request and wait for the result
+ * __scsi_execute - insert request and wait for the result
  * @sdev:	scsi device
  * @cmd:	scsi command
  * @data_direction: data direction
@@ -255,7 +255,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
  * Returns the scsi_cmnd result field if a command was executed, or a negative
  * Linux error code if we didn't get that far.
  */
-int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
 		 unsigned char *sense, struct scsi_sense_hdr *sshdr,
 		 int timeout, int retries, u64 flags, req_flags_t rq_flags,
@@ -309,7 +309,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 
 	return ret;
 }
-EXPORT_SYMBOL(scsi_execute);
+EXPORT_SYMBOL(__scsi_execute);
 
 /*
  * Function:    scsi_init_cmd_errh()
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 9421d9877730..bbebdc3769b0 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1119,7 +1119,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 		SCpnt->cmnd[0] = WRITE_6;
 
 		if (blk_integrity_rq(rq))
-			sd_dif_prepare(SCpnt);
+			t10_pi_prepare(SCpnt->request, sdkp->protection_type);
 
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
@@ -2047,8 +2047,10 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 					   "sd_done: completed %d of %d bytes\n",
 					   good_bytes, scsi_bufflen(SCpnt)));
 
-	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt))
-		sd_dif_complete(SCpnt, good_bytes);
+	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt) &&
+	    good_bytes)
+		t10_pi_complete(SCpnt->request, sdkp->protection_type,
+				good_bytes / scsi_prot_interval(SCpnt));
 
 	return good_bytes;
 }
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 392c7d078ae3..a7d4f50b67d4 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -254,21 +254,12 @@ static inline unsigned int sd_prot_flag_mask(unsigned int prot_op)
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 
 extern void sd_dif_config_host(struct scsi_disk *);
-extern void sd_dif_prepare(struct scsi_cmnd *scmd);
-extern void sd_dif_complete(struct scsi_cmnd *, unsigned int);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 static inline void sd_dif_config_host(struct scsi_disk *disk)
 {
 }
-static inline int sd_dif_prepare(struct scsi_cmnd *scmd)
-{
-	return 0;
-}
-static inline void sd_dif_complete(struct scsi_cmnd *cmd, unsigned int a)
-{
-}
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 9035380c0dda..db72c82486e3 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -95,116 +95,3 @@ out:
 	blk_integrity_register(disk, &bi);
 }
 
-/*
- * The virtual start sector is the one that was originally submitted
- * by the block layer.	Due to partitioning, MD/DM cloning, etc. the
- * actual physical start sector is likely to be different.  Remap
- * protection information to match the physical LBA.
- *
- * From a protocol perspective there's a slight difference between
- * Type 1 and 2.  The latter uses 32-byte CDBs exclusively, and the
- * reference tag is seeded in the CDB.  This gives us the potential to
- * avoid virt->phys remapping during write.  However, at read time we
- * don't know whether the virt sector is the same as when we wrote it
- * (we could be reading from real disk as opposed to MD/DM device.  So
- * we always remap Type 2 making it identical to Type 1.
- *
- * Type 3 does not have a reference tag so no remapping is required.
- */
-void sd_dif_prepare(struct scsi_cmnd *scmd)
-{
-	const int tuple_sz = sizeof(struct t10_pi_tuple);
-	struct bio *bio;
-	struct scsi_disk *sdkp;
-	struct t10_pi_tuple *pi;
-	u32 phys, virt;
-
-	sdkp = scsi_disk(scmd->request->rq_disk);
-
-	if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION)
-		return;
-
-	phys = scsi_prot_ref_tag(scmd);
-
-	__rq_for_each_bio(bio, scmd->request) {
-		struct bio_integrity_payload *bip = bio_integrity(bio);
-		struct bio_vec iv;
-		struct bvec_iter iter;
-		unsigned int j;
-
-		/* Already remapped? */
-		if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
-			break;
-
-		virt = bip_get_seed(bip) & 0xffffffff;
-
-		bip_for_each_vec(iv, bip, iter) {
-			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
-
-			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
-
-				if (be32_to_cpu(pi->ref_tag) == virt)
-					pi->ref_tag = cpu_to_be32(phys);
-
-				virt++;
-				phys++;
-			}
-
-			kunmap_atomic(pi);
-		}
-
-		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
-	}
-}
-
-/*
- * Remap physical sector values in the reference tag to the virtual
- * values expected by the block layer.
- */
-void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
-{
-	const int tuple_sz = sizeof(struct t10_pi_tuple);
-	struct scsi_disk *sdkp;
-	struct bio *bio;
-	struct t10_pi_tuple *pi;
-	unsigned int j, intervals;
-	u32 phys, virt;
-
-	sdkp = scsi_disk(scmd->request->rq_disk);
-
-	if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION || good_bytes == 0)
-		return;
-
-	intervals = good_bytes / scsi_prot_interval(scmd);
-	phys = scsi_prot_ref_tag(scmd);
-
-	__rq_for_each_bio(bio, scmd->request) {
-		struct bio_integrity_payload *bip = bio_integrity(bio);
-		struct bio_vec iv;
-		struct bvec_iter iter;
-
-		virt = bip_get_seed(bip) & 0xffffffff;
-
-		bip_for_each_vec(iv, bip, iter) {
-			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
-
-			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
-
-				if (intervals == 0) {
-					kunmap_atomic(pi);
-					return;
-				}
-
-				if (be32_to_cpu(pi->ref_tag) == phys)
-					pi->ref_tag = cpu_to_be32(virt);
-
-				virt++;
-				phys++;
-				intervals--;
-			}
-
-			kunmap_atomic(pi);
-		}
-	}
-}
-
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index a14fef11776e..2bf3bf73886e 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -391,7 +391,8 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf)
  * Check that all zones of the device are equal. The last zone can however
  * be smaller. The zone size must also be a power of two number of LBAs.
  *
- * Returns the zone size in bytes upon success or an error code upon failure.
+ * Returns the zone size in number of blocks upon success or an error code
+ * upon failure.
  */
 static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 {
@@ -401,7 +402,7 @@ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 	unsigned char *rec;
 	unsigned int buf_len;
 	unsigned int list_length;
-	int ret;
+	s64 ret;
 	u8 same;
 
 	/* Get a buffer */
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 53ae52dbff84..139e13c73b41 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -51,6 +51,7 @@ static int sg_version_num = 30536;	/* 2 digits for each component */
 #include <linux/atomic.h>
 #include <linux/ratelimit.h>
 #include <linux/uio.h>
+#include <linux/cred.h> /* for sg_check_file_access() */
 
 #include "scsi.h"
 #include <scsi/scsi_dbg.h>
@@ -209,6 +210,33 @@ static void sg_device_destroy(struct kref *kref);
 	sdev_prefix_printk(prefix, (sdp)->device,		\
 			   (sdp)->disk->disk_name, fmt, ##a)
 
+/*
+ * The SCSI interfaces that use read() and write() as an asynchronous variant of
+ * ioctl(..., SG_IO, ...) are fundamentally unsafe, since there are lots of ways
+ * to trigger read() and write() calls from various contexts with elevated
+ * privileges. This can lead to kernel memory corruption (e.g. if these
+ * interfaces are called through splice()) and privilege escalation inside
+ * userspace (e.g. if a process with access to such a device passes a file
+ * descriptor to a SUID binary as stdin/stdout/stderr).
+ *
+ * This function provides protection for the legacy API by restricting the
+ * calling context.
+ */
+static int sg_check_file_access(struct file *filp, const char *caller)
+{
+	if (filp->f_cred != current_real_cred()) {
+		pr_err_once("%s: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n",
+			caller, task_tgid_vnr(current), current->comm);
+		return -EPERM;
+	}
+	if (uaccess_kernel()) {
+		pr_err_once("%s: process %d (%s) called from kernel context, this is not allowed.\n",
+			caller, task_tgid_vnr(current), current->comm);
+		return -EACCES;
+	}
+	return 0;
+}
+
 static int sg_allow_access(struct file *filp, unsigned char *cmd)
 {
 	struct sg_fd *sfp = filp->private_data;
@@ -393,6 +421,14 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
 	struct sg_header *old_hdr = NULL;
 	int retval = 0;
 
+	/*
+	 * This could cause a response to be stranded. Close the associated
+	 * file descriptor to free up any resources being held.
+	 */
+	retval = sg_check_file_access(filp, __func__);
+	if (retval)
+		return retval;
+
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
 		return -ENXIO;
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
@@ -580,9 +616,11 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	struct sg_header old_hdr;
 	sg_io_hdr_t *hp;
 	unsigned char cmnd[SG_MAX_CDB_SIZE];
+	int retval;
 
-	if (unlikely(uaccess_kernel()))
-		return -EINVAL;
+	retval = sg_check_file_access(filp, __func__);
+	if (retval)
+		return retval;
 
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
 		return -ENXIO;
@@ -1065,15 +1103,6 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 	case SCSI_IOCTL_SEND_COMMAND:
 		if (atomic_read(&sdp->detaching))
 			return -ENODEV;
-		if (read_only) {
-			unsigned char opcode = WRITE_6;
-			Scsi_Ioctl_Command __user *siocp = p;
-
-			if (copy_from_user(&opcode, siocp->data, 1))
-				return -EFAULT;
-			if (sg_allow_access(filp, &opcode))
-				return -EPERM;
-		}
 		return sg_scsi_ioctl(sdp->device->request_queue, NULL, filp->f_mode, p);
 	case SG_SET_DEBUG:
 		result = get_user(val, ip);
@@ -1703,15 +1732,11 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 	 *
 	 * With scsi-mq enabled, there are a fixed number of preallocated
 	 * requests equal in number to shost->can_queue.  If all of the
-	 * preallocated requests are already in use, then using GFP_ATOMIC with
-	 * blk_get_request() will return -EWOULDBLOCK, whereas using GFP_KERNEL
-	 * will cause blk_get_request() to sleep until an active command
-	 * completes, freeing up a request.  Neither option is ideal, but
-	 * GFP_KERNEL is the better choice to prevent userspace from getting an
-	 * unexpected EWOULDBLOCK.
-	 *
-	 * With scsi-mq disabled, blk_get_request() with GFP_KERNEL usually
-	 * does not sleep except under memory pressure.
+	 * preallocated requests are already in use, then blk_get_request()
+	 * will sleep until an active command completes, freeing up a request.
+	 * Although waiting in an asynchronous interface is less than ideal, we
+	 * do not want to use BLK_MQ_REQ_NOWAIT here because userspace might
+	 * not expect an EWOULDBLOCK from this condition.
 	 */
 	rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ?
 			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
@@ -2147,6 +2172,7 @@ sg_add_sfp(Sg_device * sdp)
 	write_lock_irqsave(&sdp->sfd_lock, iflags);
 	if (atomic_read(&sdp->detaching)) {
 		write_unlock_irqrestore(&sdp->sfd_lock, iflags);
+		kfree(sfp);
 		return ERR_PTR(-ENODEV);
 	}
 	list_add_tail(&sfp->sfd_siblings, &sdp->sfds);
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 3f3cb72e0c0c..d0389b20574d 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -523,18 +523,26 @@ static int sr_init_command(struct scsi_cmnd *SCpnt)
 static int sr_block_open(struct block_device *bdev, fmode_t mode)
 {
 	struct scsi_cd *cd;
+	struct scsi_device *sdev;
 	int ret = -ENXIO;
 
+	cd = scsi_cd_get(bdev->bd_disk);
+	if (!cd)
+		goto out;
+
+	sdev = cd->device;
+	scsi_autopm_get_device(sdev);
 	check_disk_change(bdev);
 
 	mutex_lock(&sr_mutex);
-	cd = scsi_cd_get(bdev->bd_disk);
-	if (cd) {
-		ret = cdrom_open(&cd->cdi, bdev, mode);
-		if (ret)
-			scsi_cd_put(cd);
-	}
+	ret = cdrom_open(&cd->cdi, bdev, mode);
 	mutex_unlock(&sr_mutex);
+
+	scsi_autopm_put_device(sdev);
+	if (ret)
+		scsi_cd_put(cd);
+
+out:
 	return ret;
 }
 
@@ -562,6 +570,8 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	if (ret)
 		goto out;
 
+	scsi_autopm_get_device(sdev);
+
 	/*
 	 * Send SCSI addressing ioctls directly to mid level, send other
 	 * ioctls to cdrom/block level.
@@ -570,15 +580,18 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case SCSI_IOCTL_GET_IDLUN:
 	case SCSI_IOCTL_GET_BUS_NUMBER:
 		ret = scsi_ioctl(sdev, cmd, argp);
-		goto out;
+		goto put;
 	}
 
 	ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg);
 	if (ret != -ENOSYS)
-		goto out;
+		goto put;
 
 	ret = scsi_ioctl(sdev, cmd, argp);
 
+put:
+	scsi_autopm_put_device(sdev);
+
 out:
 	mutex_unlock(&sr_mutex);
 	return ret;
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 35fab1e18adc..ffcf902da390 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -186,14 +186,13 @@ static int sr_play_trkind(struct cdrom_device_info *cdi,
 int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 {
 	struct scsi_device *SDev;
-	struct scsi_sense_hdr sshdr;
+	struct scsi_sense_hdr local_sshdr, *sshdr = &local_sshdr;
 	int result, err = 0, retries = 0;
-	unsigned char sense_buffer[SCSI_SENSE_BUFFERSIZE], *senseptr = NULL;
 
 	SDev = cd->device;
 
-	if (cgc->sense)
-		senseptr = sense_buffer;
+	if (cgc->sshdr)
+		sshdr = cgc->sshdr;
 
       retry:
 	if (!scsi_block_when_processing_errors(SDev)) {
@@ -202,15 +201,12 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 	}
 
 	result = scsi_execute(SDev, cgc->cmd, cgc->data_direction,
-			      cgc->buffer, cgc->buflen, senseptr, &sshdr,
+			      cgc->buffer, cgc->buflen, NULL, sshdr,
 			      cgc->timeout, IOCTL_RETRIES, 0, 0, NULL);
 
-	if (cgc->sense)
-		memcpy(cgc->sense, sense_buffer, sizeof(*cgc->sense));
-
 	/* Minimal error checking.  Ignore cases we know about, and report the rest. */
 	if (driver_byte(result) != 0) {
-		switch (sshdr.sense_key) {
+		switch (sshdr->sense_key) {
 		case UNIT_ATTENTION:
 			SDev->changed = 1;
 			if (!cgc->quiet)
@@ -221,8 +217,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 			err = -ENOMEDIUM;
 			break;
 		case NOT_READY:	/* This happens if there is no disc in drive */
-			if (sshdr.asc == 0x04 &&
-			    sshdr.ascq == 0x01) {
+			if (sshdr->asc == 0x04 &&
+			    sshdr->ascq == 0x01) {
 				/* sense: Logical unit is in process of becoming ready */
 				if (!cgc->quiet)
 					sr_printk(KERN_INFO, cd,
@@ -245,8 +241,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 			break;
 		case ILLEGAL_REQUEST:
 			err = -EIO;
-			if (sshdr.asc == 0x20 &&
-			    sshdr.ascq == 0x00)
+			if (sshdr->asc == 0x20 &&
+			    sshdr->ascq == 0x00)
 				/* sense: Invalid command operation code */
 				err = -EDRIVE_CANT_DO_THIS;
 			break;
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 6dc8891ccb74..1c72db94270e 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -513,12 +513,12 @@ static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
 
 	if (sc->sc_data_direction == DMA_TO_DEVICE)
 		cmd_pi->pi_bytesout = cpu_to_virtio32(vdev,
-							blk_rq_sectors(rq) *
-							bi->tuple_size);
+						      bio_integrity_bytes(bi,
+							blk_rq_sectors(rq)));
 	else if (sc->sc_data_direction == DMA_FROM_DEVICE)
 		cmd_pi->pi_bytesin = cpu_to_virtio32(vdev,
-						       blk_rq_sectors(rq) *
-						       bi->tuple_size);
+						     bio_integrity_bytes(bi,
+							blk_rq_sectors(rq)));
 }
 #endif
 
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 777e5f1e52d1..0cd947f78b5b 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -561,9 +561,14 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter,
 	    (btstat == BTSTAT_SUCCESS ||
 	     btstat == BTSTAT_LINKED_COMMAND_COMPLETED ||
 	     btstat == BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG)) {
-		cmd->result = (DID_OK << 16) | sdstat;
-		if (sdstat == SAM_STAT_CHECK_CONDITION && cmd->sense_buffer)
-			cmd->result |= (DRIVER_SENSE << 24);
+		if (sdstat == SAM_STAT_COMMAND_TERMINATED) {
+			cmd->result = (DID_RESET << 16);
+		} else {
+			cmd->result = (DID_OK << 16) | sdstat;
+			if (sdstat == SAM_STAT_CHECK_CONDITION &&
+			    cmd->sense_buffer)
+				cmd->result |= (DRIVER_SENSE << 24);
+		}
 	} else
 		switch (btstat) {
 		case BTSTAT_SUCCESS:
diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index 2e45988d1259..e5d7fb81ad66 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -300,8 +300,8 @@ static void maple_send(void)
 	mutex_unlock(&maple_wlist_lock);
 	if (maple_packets > 0) {
 		for (i = 0; i < (1 << MAPLE_DMA_PAGES); i++)
-			sh_sync_dma_for_device(maple_sendbuf + i * PAGE_SIZE,
-				       PAGE_SIZE, DMA_BIDIRECTIONAL);
+			__flush_purge_region(maple_sendbuf + i * PAGE_SIZE,
+					PAGE_SIZE);
 	}
 
 finish:
@@ -642,7 +642,8 @@ static void maple_dma_handler(struct work_struct *work)
 		list_for_each_entry_safe(mq, nmq, &maple_sentq, list) {
 			mdev = mq->dev;
 			recvbuf = mq->recvbuf->buf;
-			sh_sync_dma_for_device(recvbuf, 0x400, DMA_FROM_DEVICE);
+			__flush_invalidate_region(sh_cacheop_vaddr(recvbuf),
+					0x400);
 			code = recvbuf[0];
 			kfree(mq->sendbuf);
 			list_del_init(&mq->list);
diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c
index 32f0748fd067..546960a18d60 100644
--- a/drivers/soc/imx/gpc.c
+++ b/drivers/soc/imx/gpc.c
@@ -27,9 +27,16 @@
 #define GPC_PGC_SW2ISO_SHIFT	0x8
 #define GPC_PGC_SW_SHIFT	0x0
 
+#define GPC_PGC_PCI_PDN		0x200
+#define GPC_PGC_PCI_SR		0x20c
+
 #define GPC_PGC_GPU_PDN		0x260
 #define GPC_PGC_GPU_PUPSCR	0x264
 #define GPC_PGC_GPU_PDNSCR	0x268
+#define GPC_PGC_GPU_SR		0x26c
+
+#define GPC_PGC_DISP_PDN	0x240
+#define GPC_PGC_DISP_SR		0x24c
 
 #define GPU_VPU_PUP_REQ		BIT(1)
 #define GPU_VPU_PDN_REQ		BIT(0)
@@ -202,7 +209,7 @@ static int imx_pgc_power_domain_probe(struct platform_device *pdev)
 			goto genpd_err;
 	}
 
-	device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE);
+	device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE_CONSUMER);
 
 	return 0;
 
@@ -318,10 +325,24 @@ static const struct of_device_id imx_gpc_dt_ids[] = {
 	{ }
 };
 
+static const struct regmap_range yes_ranges[] = {
+	regmap_reg_range(GPC_CNTR, GPC_CNTR),
+	regmap_reg_range(GPC_PGC_PCI_PDN, GPC_PGC_PCI_SR),
+	regmap_reg_range(GPC_PGC_GPU_PDN, GPC_PGC_GPU_SR),
+	regmap_reg_range(GPC_PGC_DISP_PDN, GPC_PGC_DISP_SR),
+};
+
+static const struct regmap_access_table access_table = {
+	.yes_ranges	= yes_ranges,
+	.n_yes_ranges	= ARRAY_SIZE(yes_ranges),
+};
+
 static const struct regmap_config imx_gpc_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
 	.reg_stride = 4,
+	.rd_table = &access_table,
+	.wr_table = &access_table,
 	.max_register = 0x2ac,
 };
 
diff --git a/drivers/soc/imx/gpcv2.c b/drivers/soc/imx/gpcv2.c
index f4e3bd40c72e..6ef18cf8f243 100644
--- a/drivers/soc/imx/gpcv2.c
+++ b/drivers/soc/imx/gpcv2.c
@@ -39,10 +39,15 @@
 
 #define GPC_M4_PU_PDN_FLG		0x1bc
 
-
-#define PGC_MIPI			4
-#define PGC_PCIE			5
-#define PGC_USB_HSIC			8
+/*
+ * The PGC offset values in Reference Manual
+ * (Rev. 1, 01/2018 and the older ones) GPC chapter's
+ * GPC_PGC memory map are incorrect, below offset
+ * values are from design RTL.
+ */
+#define PGC_MIPI			16
+#define PGC_PCIE			17
+#define PGC_USB_HSIC			20
 #define GPC_PGC_CTRL(n)			(0x800 + (n) * 0x40)
 #define GPC_PGC_SR(n)			(GPC_PGC_CTRL(n) + 0xc)
 
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 9dc02f390ba3..ba79b609aca2 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -5,7 +5,8 @@ menu "Qualcomm SoC drivers"
 
 config QCOM_COMMAND_DB
 	bool "Qualcomm Command DB"
-	depends on (ARCH_QCOM && OF) || COMPILE_TEST
+	depends on ARCH_QCOM || COMPILE_TEST
+	depends on OF_RESERVED_MEM
 	help
 	  Command DB queries shared memory by key string for shared system
 	  resources. Platform drivers that require to set state of a shared
@@ -39,6 +40,23 @@ config QCOM_GSBI
           functions for connecting the underlying serial UART, SPI, and I2C
           devices to the output pins.
 
+config QCOM_LLCC
+	tristate "Qualcomm Technologies, Inc. LLCC driver"
+	depends on ARCH_QCOM
+	help
+	  Qualcomm Technologies, Inc. platform specific
+	  Last Level Cache Controller(LLCC) driver. This provides interfaces
+	  to clients that use the LLCC. Say yes here to enable LLCC slice
+	  driver.
+
+config QCOM_SDM845_LLCC
+	tristate "Qualcomm Technologies, Inc. SDM845 LLCC driver"
+	depends on QCOM_LLCC
+	help
+	  Say yes here to enable the LLCC driver for SDM845. This provides
+	  data required to configure LLCC so that clients can start using the
+	  LLCC slices.
+
 config QCOM_MDT_LOADER
 	tristate
 	select QCOM_SCM
@@ -74,6 +92,16 @@ config QCOM_RMTFS_MEM
 
 	  Say y here if you intend to boot the modem remoteproc.
 
+config QCOM_RPMH
+	bool "Qualcomm RPM-Hardened (RPMH) Communication"
+	depends on ARCH_QCOM && ARM64 && OF || COMPILE_TEST
+	help
+	  Support for communication with the hardened-RPM blocks in
+	  Qualcomm Technologies Inc (QTI) SoCs. RPMH communication uses an
+	  internal bus to transmit state requests for shared resources. A set
+	  of hardware components aggregate requests for these resources and
+	  help apply the aggregated state on the resource.
+
 config QCOM_SMEM
 	tristate "Qualcomm Shared Memory Manager (SMEM)"
 	depends on ARCH_QCOM
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 19dcf957cb3a..f25b54cd6cf8 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
+CFLAGS_rpmh-rsc.o := -I$(src)
 obj-$(CONFIG_QCOM_GENI_SE) +=	qcom-geni-se.o
 obj-$(CONFIG_QCOM_COMMAND_DB) += cmd-db.o
 obj-$(CONFIG_QCOM_GLINK_SSR) +=	glink_ssr.o
@@ -8,6 +9,9 @@ obj-$(CONFIG_QCOM_PM)	+=	spm.o
 obj-$(CONFIG_QCOM_QMI_HELPERS)	+= qmi_helpers.o
 qmi_helpers-y	+= qmi_encdec.o qmi_interface.o
 obj-$(CONFIG_QCOM_RMTFS_MEM)	+= rmtfs_mem.o
+obj-$(CONFIG_QCOM_RPMH)		+= qcom_rpmh.o
+qcom_rpmh-y			+= rpmh-rsc.o
+qcom_rpmh-y			+= rpmh.o
 obj-$(CONFIG_QCOM_SMD_RPM)	+= smd-rpm.o
 obj-$(CONFIG_QCOM_SMEM) +=	smem.o
 obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o
@@ -15,3 +19,5 @@ obj-$(CONFIG_QCOM_SMP2P)	+= smp2p.o
 obj-$(CONFIG_QCOM_SMSM)	+= smsm.o
 obj-$(CONFIG_QCOM_WCNSS_CTRL) += wcnss_ctrl.o
 obj-$(CONFIG_QCOM_APR) += apr.o
+obj-$(CONFIG_QCOM_LLCC) += llcc-slice.o
+obj-$(CONFIG_QCOM_SDM845_LLCC) += llcc-sdm845.o
diff --git a/drivers/soc/qcom/llcc-sdm845.c b/drivers/soc/qcom/llcc-sdm845.c
new file mode 100644
index 000000000000..2e1e4f0a5db8
--- /dev/null
+++ b/drivers/soc/qcom/llcc-sdm845.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/soc/qcom/llcc-qcom.h>
+
+/*
+ * SCT(System Cache Table) entry contains of the following members:
+ * usecase_id: Unique id for the client's use case
+ * slice_id: llcc slice id for each client
+ * max_cap: The maximum capacity of the cache slice provided in KB
+ * priority: Priority of the client used to select victim line for replacement
+ * fixed_size: Boolean indicating if the slice has a fixed capacity
+ * bonus_ways: Bonus ways are additional ways to be used for any slice,
+ *		if client ends up using more than reserved cache ways. Bonus
+ *		ways are allocated only if they are not reserved for some
+ *		other client.
+ * res_ways: Reserved ways for the cache slice, the reserved ways cannot
+ *		be used by any other client than the one its assigned to.
+ * cache_mode: Each slice operates as a cache, this controls the mode of the
+ *             slice: normal or TCM(Tightly Coupled Memory)
+ * probe_target_ways: Determines what ways to probe for access hit. When
+ *                    configured to 1 only bonus and reserved ways are probed.
+ *                    When configured to 0 all ways in llcc are probed.
+ * dis_cap_alloc: Disable capacity based allocation for a client
+ * retain_on_pc: If this bit is set and client has maintained active vote
+ *               then the ways assigned to this client are not flushed on power
+ *               collapse.
+ * activate_on_init: Activate the slice immediately after the SCT is programmed
+ */
+#define SCT_ENTRY(uid, sid, mc, p, fs, bway, rway, cmod, ptw, dca, rp, a) \
+	{					\
+		.usecase_id = uid,		\
+		.slice_id = sid,		\
+		.max_cap = mc,			\
+		.priority = p,			\
+		.fixed_size = fs,		\
+		.bonus_ways = bway,		\
+		.res_ways = rway,		\
+		.cache_mode = cmod,		\
+		.probe_target_ways = ptw,	\
+		.dis_cap_alloc = dca,		\
+		.retain_on_pc = rp,		\
+		.activate_on_init = a,		\
+	}
+
+static struct llcc_slice_config sdm845_data[] =  {
+	SCT_ENTRY(LLCC_CPUSS,    1,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 1),
+	SCT_ENTRY(LLCC_VIDSC0,   2,  512,  2, 1, 0x0,   0x0f0, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_VIDSC1,   3,  512,  2, 1, 0x0,   0x0f0, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_ROTATOR,  4,  563,  2, 1, 0x0,   0x00e, 2, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_VOICE,    5,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_AUDIO,    6,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDMHPGRW, 7,  1024, 2, 0, 0xfc,  0xf00, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDM,      8,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_CMPT,     10, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_GPUHTW,   11, 512,  1, 1, 0xc,   0x0,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_GPU,      12, 2304, 1, 0, 0xff0, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MMUHWT,   13, 256,  2, 0, 0x0,   0x1,   0, 0, 1, 0, 1),
+	SCT_ENTRY(LLCC_CMPTDMA,  15, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_DISP,     16, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_VIDFW,    17, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDMHPFX,  20, 1024, 2, 1, 0x0,   0xf00, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDMPNG,   21, 1024, 0, 1, 0x1e,  0x0,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_AUDHW,    22, 1024, 1, 1, 0xffc, 0x2,   0, 0, 1, 1, 0),
+};
+
+static int sdm845_qcom_llcc_probe(struct platform_device *pdev)
+{
+	return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data));
+}
+
+static const struct of_device_id sdm845_qcom_llcc_of_match[] = {
+	{ .compatible = "qcom,sdm845-llcc", },
+	{ }
+};
+
+static struct platform_driver sdm845_qcom_llcc_driver = {
+	.driver = {
+		.name = "sdm845-llcc",
+		.of_match_table = sdm845_qcom_llcc_of_match,
+	},
+	.probe = sdm845_qcom_llcc_probe,
+};
+module_platform_driver(sdm845_qcom_llcc_driver);
+
+MODULE_DESCRIPTION("QCOM sdm845 LLCC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c
new file mode 100644
index 000000000000..54063a31132f
--- /dev/null
+++ b/drivers/soc/qcom/llcc-slice.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/soc/qcom/llcc-qcom.h>
+
+#define ACTIVATE                      BIT(0)
+#define DEACTIVATE                    BIT(1)
+#define ACT_CTRL_OPCODE_ACTIVATE      BIT(0)
+#define ACT_CTRL_OPCODE_DEACTIVATE    BIT(1)
+#define ACT_CTRL_ACT_TRIG             BIT(0)
+#define ACT_CTRL_OPCODE_SHIFT         0x01
+#define ATTR1_PROBE_TARGET_WAYS_SHIFT 0x02
+#define ATTR1_FIXED_SIZE_SHIFT        0x03
+#define ATTR1_PRIORITY_SHIFT          0x04
+#define ATTR1_MAX_CAP_SHIFT           0x10
+#define ATTR0_RES_WAYS_MASK           GENMASK(11, 0)
+#define ATTR0_BONUS_WAYS_MASK         GENMASK(27, 16)
+#define ATTR0_BONUS_WAYS_SHIFT        0x10
+#define LLCC_STATUS_READ_DELAY        100
+
+#define CACHE_LINE_SIZE_SHIFT         6
+
+#define LLCC_COMMON_STATUS0           0x0003000c
+#define LLCC_LB_CNT_MASK              GENMASK(31, 28)
+#define LLCC_LB_CNT_SHIFT             28
+
+#define MAX_CAP_TO_BYTES(n)           (n * SZ_1K)
+#define LLCC_TRP_ACT_CTRLn(n)         (n * SZ_4K)
+#define LLCC_TRP_STATUSn(n)           (4 + n * SZ_4K)
+#define LLCC_TRP_ATTR0_CFGn(n)        (0x21000 + SZ_8 * n)
+#define LLCC_TRP_ATTR1_CFGn(n)        (0x21004 + SZ_8 * n)
+
+#define BANK_OFFSET_STRIDE	      0x80000
+
+static struct llcc_drv_data *drv_data;
+
+static const struct regmap_config llcc_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+};
+
+/**
+ * llcc_slice_getd - get llcc slice descriptor
+ * @uid: usecase_id for the client
+ *
+ * A pointer to llcc slice descriptor will be returned on success and
+ * and error pointer is returned on failure
+ */
+struct llcc_slice_desc *llcc_slice_getd(u32 uid)
+{
+	const struct llcc_slice_config *cfg;
+	struct llcc_slice_desc *desc;
+	u32 sz, count;
+
+	cfg = drv_data->cfg;
+	sz = drv_data->cfg_size;
+
+	for (count = 0; cfg && count < sz; count++, cfg++)
+		if (cfg->usecase_id == uid)
+			break;
+
+	if (count == sz || !cfg)
+		return ERR_PTR(-ENODEV);
+
+	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return ERR_PTR(-ENOMEM);
+
+	desc->slice_id = cfg->slice_id;
+	desc->slice_size = cfg->max_cap;
+
+	return desc;
+}
+EXPORT_SYMBOL_GPL(llcc_slice_getd);
+
+/**
+ * llcc_slice_putd - llcc slice descritpor
+ * @desc: Pointer to llcc slice descriptor
+ */
+void llcc_slice_putd(struct llcc_slice_desc *desc)
+{
+	kfree(desc);
+}
+EXPORT_SYMBOL_GPL(llcc_slice_putd);
+
+static int llcc_update_act_ctrl(u32 sid,
+				u32 act_ctrl_reg_val, u32 status)
+{
+	u32 act_ctrl_reg;
+	u32 status_reg;
+	u32 slice_status;
+	int ret;
+
+	act_ctrl_reg = drv_data->bcast_off + LLCC_TRP_ACT_CTRLn(sid);
+	status_reg = drv_data->bcast_off + LLCC_TRP_STATUSn(sid);
+
+	/* Set the ACTIVE trigger */
+	act_ctrl_reg_val |= ACT_CTRL_ACT_TRIG;
+	ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val);
+	if (ret)
+		return ret;
+
+	/* Clear the ACTIVE trigger */
+	act_ctrl_reg_val &= ~ACT_CTRL_ACT_TRIG;
+	ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val);
+	if (ret)
+		return ret;
+
+	ret = regmap_read_poll_timeout(drv_data->regmap, status_reg,
+				      slice_status, !(slice_status & status),
+				      0, LLCC_STATUS_READ_DELAY);
+	return ret;
+}
+
+/**
+ * llcc_slice_activate - Activate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ *
+ * A value of zero will be returned on success and a negative errno will
+ * be returned in error cases
+ */
+int llcc_slice_activate(struct llcc_slice_desc *desc)
+{
+	int ret;
+	u32 act_ctrl_val;
+
+	mutex_lock(&drv_data->lock);
+	if (test_bit(desc->slice_id, drv_data->bitmap)) {
+		mutex_unlock(&drv_data->lock);
+		return 0;
+	}
+
+	act_ctrl_val = ACT_CTRL_OPCODE_ACTIVATE << ACT_CTRL_OPCODE_SHIFT;
+
+	ret = llcc_update_act_ctrl(desc->slice_id, act_ctrl_val,
+				  DEACTIVATE);
+	if (ret) {
+		mutex_unlock(&drv_data->lock);
+		return ret;
+	}
+
+	__set_bit(desc->slice_id, drv_data->bitmap);
+	mutex_unlock(&drv_data->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(llcc_slice_activate);
+
+/**
+ * llcc_slice_deactivate - Deactivate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ *
+ * A value of zero will be returned on success and a negative errno will
+ * be returned in error cases
+ */
+int llcc_slice_deactivate(struct llcc_slice_desc *desc)
+{
+	u32 act_ctrl_val;
+	int ret;
+
+	mutex_lock(&drv_data->lock);
+	if (!test_bit(desc->slice_id, drv_data->bitmap)) {
+		mutex_unlock(&drv_data->lock);
+		return 0;
+	}
+	act_ctrl_val = ACT_CTRL_OPCODE_DEACTIVATE << ACT_CTRL_OPCODE_SHIFT;
+
+	ret = llcc_update_act_ctrl(desc->slice_id, act_ctrl_val,
+				  ACTIVATE);
+	if (ret) {
+		mutex_unlock(&drv_data->lock);
+		return ret;
+	}
+
+	__clear_bit(desc->slice_id, drv_data->bitmap);
+	mutex_unlock(&drv_data->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(llcc_slice_deactivate);
+
+/**
+ * llcc_get_slice_id - return the slice id
+ * @desc: Pointer to llcc slice descriptor
+ */
+int llcc_get_slice_id(struct llcc_slice_desc *desc)
+{
+	return desc->slice_id;
+}
+EXPORT_SYMBOL_GPL(llcc_get_slice_id);
+
+/**
+ * llcc_get_slice_size - return the slice id
+ * @desc: Pointer to llcc slice descriptor
+ */
+size_t llcc_get_slice_size(struct llcc_slice_desc *desc)
+{
+	return desc->slice_size;
+}
+EXPORT_SYMBOL_GPL(llcc_get_slice_size);
+
+static int qcom_llcc_cfg_program(struct platform_device *pdev)
+{
+	int i;
+	u32 attr1_cfg;
+	u32 attr0_cfg;
+	u32 attr1_val;
+	u32 attr0_val;
+	u32 max_cap_cacheline;
+	u32 sz;
+	int ret;
+	const struct llcc_slice_config *llcc_table;
+	struct llcc_slice_desc desc;
+	u32 bcast_off = drv_data->bcast_off;
+
+	sz = drv_data->cfg_size;
+	llcc_table = drv_data->cfg;
+
+	for (i = 0; i < sz; i++) {
+		attr1_cfg = bcast_off +
+				LLCC_TRP_ATTR1_CFGn(llcc_table[i].slice_id);
+		attr0_cfg = bcast_off +
+				LLCC_TRP_ATTR0_CFGn(llcc_table[i].slice_id);
+
+		attr1_val = llcc_table[i].cache_mode;
+		attr1_val |= llcc_table[i].probe_target_ways <<
+				ATTR1_PROBE_TARGET_WAYS_SHIFT;
+		attr1_val |= llcc_table[i].fixed_size <<
+				ATTR1_FIXED_SIZE_SHIFT;
+		attr1_val |= llcc_table[i].priority <<
+				ATTR1_PRIORITY_SHIFT;
+
+		max_cap_cacheline = MAX_CAP_TO_BYTES(llcc_table[i].max_cap);
+
+		/* LLCC instances can vary for each target.
+		 * The SW writes to broadcast register which gets propagated
+		 * to each llcc instace (llcc0,.. llccN).
+		 * Since the size of the memory is divided equally amongst the
+		 * llcc instances, we need to configure the max cap accordingly.
+		 */
+		max_cap_cacheline = max_cap_cacheline / drv_data->num_banks;
+		max_cap_cacheline >>= CACHE_LINE_SIZE_SHIFT;
+		attr1_val |= max_cap_cacheline << ATTR1_MAX_CAP_SHIFT;
+
+		attr0_val = llcc_table[i].res_ways & ATTR0_RES_WAYS_MASK;
+		attr0_val |= llcc_table[i].bonus_ways << ATTR0_BONUS_WAYS_SHIFT;
+
+		ret = regmap_write(drv_data->regmap, attr1_cfg, attr1_val);
+		if (ret)
+			return ret;
+		ret = regmap_write(drv_data->regmap, attr0_cfg, attr0_val);
+		if (ret)
+			return ret;
+		if (llcc_table[i].activate_on_init) {
+			desc.slice_id = llcc_table[i].slice_id;
+			ret = llcc_slice_activate(&desc);
+		}
+	}
+	return ret;
+}
+
+int qcom_llcc_probe(struct platform_device *pdev,
+		      const struct llcc_slice_config *llcc_cfg, u32 sz)
+{
+	u32 num_banks;
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	void __iomem *base;
+	int ret, i;
+
+	drv_data = devm_kzalloc(dev, sizeof(*drv_data), GFP_KERNEL);
+	if (!drv_data)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drv_data->regmap = devm_regmap_init_mmio(dev, base,
+					&llcc_regmap_config);
+	if (IS_ERR(drv_data->regmap))
+		return PTR_ERR(drv_data->regmap);
+
+	ret = regmap_read(drv_data->regmap, LLCC_COMMON_STATUS0,
+						&num_banks);
+	if (ret)
+		return ret;
+
+	num_banks &= LLCC_LB_CNT_MASK;
+	num_banks >>= LLCC_LB_CNT_SHIFT;
+	drv_data->num_banks = num_banks;
+
+	for (i = 0; i < sz; i++)
+		if (llcc_cfg[i].slice_id > drv_data->max_slices)
+			drv_data->max_slices = llcc_cfg[i].slice_id;
+
+	drv_data->offsets = devm_kcalloc(dev, num_banks, sizeof(u32),
+							GFP_KERNEL);
+	if (!drv_data->offsets)
+		return -ENOMEM;
+
+	for (i = 0; i < num_banks; i++)
+		drv_data->offsets[i] = i * BANK_OFFSET_STRIDE;
+
+	drv_data->bcast_off = num_banks * BANK_OFFSET_STRIDE;
+
+	drv_data->bitmap = devm_kcalloc(dev,
+	BITS_TO_LONGS(drv_data->max_slices), sizeof(unsigned long),
+						GFP_KERNEL);
+	if (!drv_data->bitmap)
+		return -ENOMEM;
+
+	drv_data->cfg = llcc_cfg;
+	drv_data->cfg_size = sz;
+	mutex_init(&drv_data->lock);
+	platform_set_drvdata(pdev, drv_data);
+
+	return qcom_llcc_cfg_program(pdev);
+}
+EXPORT_SYMBOL_GPL(qcom_llcc_probe);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/rmtfs_mem.c b/drivers/soc/qcom/rmtfs_mem.c
index c8999e38b005..8a3678c2e83c 100644
--- a/drivers/soc/qcom/rmtfs_mem.c
+++ b/drivers/soc/qcom/rmtfs_mem.c
@@ -184,6 +184,7 @@ static int qcom_rmtfs_mem_probe(struct platform_device *pdev)
 	device_initialize(&rmtfs_mem->dev);
 	rmtfs_mem->dev.parent = &pdev->dev;
 	rmtfs_mem->dev.groups = qcom_rmtfs_mem_groups;
+	rmtfs_mem->dev.release = qcom_rmtfs_mem_release_device;
 
 	rmtfs_mem->base = devm_memremap(&rmtfs_mem->dev, rmtfs_mem->addr,
 					rmtfs_mem->size, MEMREMAP_WC);
@@ -206,8 +207,6 @@ static int qcom_rmtfs_mem_probe(struct platform_device *pdev)
 		goto put_device;
 	}
 
-	rmtfs_mem->dev.release = qcom_rmtfs_mem_release_device;
-
 	ret = of_property_read_u32(node, "qcom,vmid", &vmid);
 	if (ret < 0 && ret != -EINVAL) {
 		dev_err(&pdev->dev, "failed to parse qcom,vmid\n");
diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h
new file mode 100644
index 000000000000..a7bbbb67991c
--- /dev/null
+++ b/drivers/soc/qcom/rpmh-internal.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+
+#ifndef __RPM_INTERNAL_H__
+#define __RPM_INTERNAL_H__
+
+#include <linux/bitmap.h>
+#include <soc/qcom/tcs.h>
+
+#define TCS_TYPE_NR			4
+#define MAX_CMDS_PER_TCS		16
+#define MAX_TCS_PER_TYPE		3
+#define MAX_TCS_NR			(MAX_TCS_PER_TYPE * TCS_TYPE_NR)
+#define MAX_TCS_SLOTS			(MAX_CMDS_PER_TCS * MAX_TCS_PER_TYPE)
+
+struct rsc_drv;
+
+/**
+ * struct tcs_group: group of Trigger Command Sets (TCS) to send state requests
+ * to the controller
+ *
+ * @drv:       the controller
+ * @type:      type of the TCS in this group - active, sleep, wake
+ * @mask:      mask of the TCSes relative to all the TCSes in the RSC
+ * @offset:    start of the TCS group relative to the TCSes in the RSC
+ * @num_tcs:   number of TCSes in this type
+ * @ncpt:      number of commands in each TCS
+ * @lock:      lock for synchronizing this TCS writes
+ * @req:       requests that are sent from the TCS
+ * @cmd_cache: flattened cache of cmds in sleep/wake TCS
+ * @slots:     indicates which of @cmd_addr are occupied
+ */
+struct tcs_group {
+	struct rsc_drv *drv;
+	int type;
+	u32 mask;
+	u32 offset;
+	int num_tcs;
+	int ncpt;
+	spinlock_t lock;
+	const struct tcs_request *req[MAX_TCS_PER_TYPE];
+	u32 *cmd_cache;
+	DECLARE_BITMAP(slots, MAX_TCS_SLOTS);
+};
+
+/**
+ * struct rpmh_request: the message to be sent to rpmh-rsc
+ *
+ * @msg: the request
+ * @cmd: the payload that will be part of the @msg
+ * @completion: triggered when request is done
+ * @dev: the device making the request
+ * @err: err return from the controller
+ * @needs_free: check to free dynamically allocated request object
+ */
+struct rpmh_request {
+	struct tcs_request msg;
+	struct tcs_cmd cmd[MAX_RPMH_PAYLOAD];
+	struct completion *completion;
+	const struct device *dev;
+	int err;
+	bool needs_free;
+};
+
+/**
+ * struct rpmh_ctrlr: our representation of the controller
+ *
+ * @cache: the list of cached requests
+ * @cache_lock: synchronize access to the cache data
+ * @dirty: was the cache updated since flush
+ * @batch_cache: Cache sleep and wake requests sent as batch
+ */
+struct rpmh_ctrlr {
+	struct list_head cache;
+	spinlock_t cache_lock;
+	bool dirty;
+	struct list_head batch_cache;
+};
+
+/**
+ * struct rsc_drv: the Direct Resource Voter (DRV) of the
+ * Resource State Coordinator controller (RSC)
+ *
+ * @name:       controller identifier
+ * @tcs_base:   start address of the TCS registers in this controller
+ * @id:         instance id in the controller (Direct Resource Voter)
+ * @num_tcs:    number of TCSes in this DRV
+ * @tcs:        TCS groups
+ * @tcs_in_use: s/w state of the TCS
+ * @lock:       synchronize state of the controller
+ * @client:     handle to the DRV's client.
+ */
+struct rsc_drv {
+	const char *name;
+	void __iomem *tcs_base;
+	int id;
+	int num_tcs;
+	struct tcs_group tcs[TCS_TYPE_NR];
+	DECLARE_BITMAP(tcs_in_use, MAX_TCS_NR);
+	spinlock_t lock;
+	struct rpmh_ctrlr client;
+};
+
+int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg);
+int rpmh_rsc_write_ctrl_data(struct rsc_drv *drv,
+			     const struct tcs_request *msg);
+int rpmh_rsc_invalidate(struct rsc_drv *drv);
+
+void rpmh_tx_done(const struct tcs_request *msg, int r);
+
+#endif /* __RPM_INTERNAL_H__ */
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
new file mode 100644
index 000000000000..ee75da66d64b
--- /dev/null
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -0,0 +1,693 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#define pr_fmt(fmt) "%s " fmt, KBUILD_MODNAME
+
+#include <linux/atomic.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <soc/qcom/cmd-db.h>
+#include <soc/qcom/tcs.h>
+#include <dt-bindings/soc/qcom,rpmh-rsc.h>
+
+#include "rpmh-internal.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace-rpmh.h"
+
+#define RSC_DRV_TCS_OFFSET		672
+#define RSC_DRV_CMD_OFFSET		20
+
+/* DRV Configuration Information Register */
+#define DRV_PRNT_CHLD_CONFIG		0x0C
+#define DRV_NUM_TCS_MASK		0x3F
+#define DRV_NUM_TCS_SHIFT		6
+#define DRV_NCPT_MASK			0x1F
+#define DRV_NCPT_SHIFT			27
+
+/* Register offsets */
+#define RSC_DRV_IRQ_ENABLE		0x00
+#define RSC_DRV_IRQ_STATUS		0x04
+#define RSC_DRV_IRQ_CLEAR		0x08
+#define RSC_DRV_CMD_WAIT_FOR_CMPL	0x10
+#define RSC_DRV_CONTROL			0x14
+#define RSC_DRV_STATUS			0x18
+#define RSC_DRV_CMD_ENABLE		0x1C
+#define RSC_DRV_CMD_MSGID		0x30
+#define RSC_DRV_CMD_ADDR		0x34
+#define RSC_DRV_CMD_DATA		0x38
+#define RSC_DRV_CMD_STATUS		0x3C
+#define RSC_DRV_CMD_RESP_DATA		0x40
+
+#define TCS_AMC_MODE_ENABLE		BIT(16)
+#define TCS_AMC_MODE_TRIGGER		BIT(24)
+
+/* TCS CMD register bit mask */
+#define CMD_MSGID_LEN			8
+#define CMD_MSGID_RESP_REQ		BIT(8)
+#define CMD_MSGID_WRITE			BIT(16)
+#define CMD_STATUS_ISSUED		BIT(8)
+#define CMD_STATUS_COMPL		BIT(16)
+
+static u32 read_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id)
+{
+	return readl_relaxed(drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id +
+			     RSC_DRV_CMD_OFFSET * cmd_id);
+}
+
+static void write_tcs_cmd(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id,
+			  u32 data)
+{
+	writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id +
+		       RSC_DRV_CMD_OFFSET * cmd_id);
+}
+
+static void write_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, u32 data)
+{
+	writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id);
+}
+
+static void write_tcs_reg_sync(struct rsc_drv *drv, int reg, int tcs_id,
+			       u32 data)
+{
+	writel(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id);
+	for (;;) {
+		if (data == readl(drv->tcs_base + reg +
+				  RSC_DRV_TCS_OFFSET * tcs_id))
+			break;
+		udelay(1);
+	}
+}
+
+static bool tcs_is_free(struct rsc_drv *drv, int tcs_id)
+{
+	return !test_bit(tcs_id, drv->tcs_in_use) &&
+	       read_tcs_reg(drv, RSC_DRV_STATUS, tcs_id, 0);
+}
+
+static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type)
+{
+	return &drv->tcs[type];
+}
+
+static int tcs_invalidate(struct rsc_drv *drv, int type)
+{
+	int m;
+	struct tcs_group *tcs;
+
+	tcs = get_tcs_of_type(drv, type);
+
+	spin_lock(&tcs->lock);
+	if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS)) {
+		spin_unlock(&tcs->lock);
+		return 0;
+	}
+
+	for (m = tcs->offset; m < tcs->offset + tcs->num_tcs; m++) {
+		if (!tcs_is_free(drv, m)) {
+			spin_unlock(&tcs->lock);
+			return -EAGAIN;
+		}
+		write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, m, 0);
+	}
+	bitmap_zero(tcs->slots, MAX_TCS_SLOTS);
+	spin_unlock(&tcs->lock);
+
+	return 0;
+}
+
+/**
+ * rpmh_rsc_invalidate - Invalidate sleep and wake TCSes
+ *
+ * @drv: the RSC controller
+ */
+int rpmh_rsc_invalidate(struct rsc_drv *drv)
+{
+	int ret;
+
+	ret = tcs_invalidate(drv, SLEEP_TCS);
+	if (!ret)
+		ret = tcs_invalidate(drv, WAKE_TCS);
+
+	return ret;
+}
+
+static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
+					 const struct tcs_request *msg)
+{
+	int type, ret;
+	struct tcs_group *tcs;
+
+	switch (msg->state) {
+	case RPMH_ACTIVE_ONLY_STATE:
+		type = ACTIVE_TCS;
+		break;
+	case RPMH_WAKE_ONLY_STATE:
+		type = WAKE_TCS;
+		break;
+	case RPMH_SLEEP_STATE:
+		type = SLEEP_TCS;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * If we are making an active request on a RSC that does not have a
+	 * dedicated TCS for active state use, then re-purpose a wake TCS to
+	 * send active votes.
+	 * NOTE: The driver must be aware that this RSC does not have a
+	 * dedicated AMC, and therefore would invalidate the sleep and wake
+	 * TCSes before making an active state request.
+	 */
+	tcs = get_tcs_of_type(drv, type);
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE && !tcs->num_tcs) {
+		tcs = get_tcs_of_type(drv, WAKE_TCS);
+		if (tcs->num_tcs) {
+			ret = rpmh_rsc_invalidate(drv);
+			if (ret)
+				return ERR_PTR(ret);
+		}
+	}
+
+	return tcs;
+}
+
+static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
+						  int tcs_id)
+{
+	struct tcs_group *tcs;
+	int i;
+
+	for (i = 0; i < TCS_TYPE_NR; i++) {
+		tcs = &drv->tcs[i];
+		if (tcs->mask & BIT(tcs_id))
+			return tcs->req[tcs_id - tcs->offset];
+	}
+
+	return NULL;
+}
+
+/**
+ * tcs_tx_done: TX Done interrupt handler
+ */
+static irqreturn_t tcs_tx_done(int irq, void *p)
+{
+	struct rsc_drv *drv = p;
+	int i, j, err = 0;
+	unsigned long irq_status;
+	const struct tcs_request *req;
+	struct tcs_cmd *cmd;
+
+	irq_status = read_tcs_reg(drv, RSC_DRV_IRQ_STATUS, 0, 0);
+
+	for_each_set_bit(i, &irq_status, BITS_PER_LONG) {
+		req = get_req_from_tcs(drv, i);
+		if (!req) {
+			WARN_ON(1);
+			goto skip;
+		}
+
+		err = 0;
+		for (j = 0; j < req->num_cmds; j++) {
+			u32 sts;
+
+			cmd = &req->cmds[j];
+			sts = read_tcs_reg(drv, RSC_DRV_CMD_STATUS, i, j);
+			if (!(sts & CMD_STATUS_ISSUED) ||
+			   ((req->wait_for_compl || cmd->wait) &&
+			   !(sts & CMD_STATUS_COMPL))) {
+				pr_err("Incomplete request: %s: addr=%#x data=%#x",
+				       drv->name, cmd->addr, cmd->data);
+				err = -EIO;
+			}
+		}
+
+		trace_rpmh_tx_done(drv, i, req, err);
+skip:
+		/* Reclaim the TCS */
+		write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0);
+		write_tcs_reg(drv, RSC_DRV_IRQ_CLEAR, 0, BIT(i));
+		spin_lock(&drv->lock);
+		clear_bit(i, drv->tcs_in_use);
+		spin_unlock(&drv->lock);
+		if (req)
+			rpmh_tx_done(req, err);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
+			       const struct tcs_request *msg)
+{
+	u32 msgid, cmd_msgid;
+	u32 cmd_enable = 0;
+	u32 cmd_complete;
+	struct tcs_cmd *cmd;
+	int i, j;
+
+	cmd_msgid = CMD_MSGID_LEN;
+	cmd_msgid |= msg->wait_for_compl ? CMD_MSGID_RESP_REQ : 0;
+	cmd_msgid |= CMD_MSGID_WRITE;
+
+	cmd_complete = read_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0);
+
+	for (i = 0, j = cmd_id; i < msg->num_cmds; i++, j++) {
+		cmd = &msg->cmds[i];
+		cmd_enable |= BIT(j);
+		cmd_complete |= cmd->wait << j;
+		msgid = cmd_msgid;
+		msgid |= cmd->wait ? CMD_MSGID_RESP_REQ : 0;
+
+		write_tcs_cmd(drv, RSC_DRV_CMD_MSGID, tcs_id, j, msgid);
+		write_tcs_cmd(drv, RSC_DRV_CMD_ADDR, tcs_id, j, cmd->addr);
+		write_tcs_cmd(drv, RSC_DRV_CMD_DATA, tcs_id, j, cmd->data);
+		trace_rpmh_send_msg(drv, tcs_id, j, msgid, cmd);
+	}
+
+	write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, cmd_complete);
+	cmd_enable |= read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+	write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, cmd_enable);
+}
+
+static void __tcs_trigger(struct rsc_drv *drv, int tcs_id)
+{
+	u32 enable;
+
+	/*
+	 * HW req: Clear the DRV_CONTROL and enable TCS again
+	 * While clearing ensure that the AMC mode trigger is cleared
+	 * and then the mode enable is cleared.
+	 */
+	enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id, 0);
+	enable &= ~TCS_AMC_MODE_TRIGGER;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	enable &= ~TCS_AMC_MODE_ENABLE;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+
+	/* Enable the AMC mode on the TCS and then trigger the TCS */
+	enable = TCS_AMC_MODE_ENABLE;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	enable |= TCS_AMC_MODE_TRIGGER;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+}
+
+static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs,
+				  const struct tcs_request *msg)
+{
+	unsigned long curr_enabled;
+	u32 addr;
+	int i, j, k;
+	int tcs_id = tcs->offset;
+
+	for (i = 0; i < tcs->num_tcs; i++, tcs_id++) {
+		if (tcs_is_free(drv, tcs_id))
+			continue;
+
+		curr_enabled = read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+
+		for_each_set_bit(j, &curr_enabled, MAX_CMDS_PER_TCS) {
+			addr = read_tcs_reg(drv, RSC_DRV_CMD_ADDR, tcs_id, j);
+			for (k = 0; k < msg->num_cmds; k++) {
+				if (addr == msg->cmds[k].addr)
+					return -EBUSY;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int find_free_tcs(struct tcs_group *tcs)
+{
+	int i;
+
+	for (i = 0; i < tcs->num_tcs; i++) {
+		if (tcs_is_free(tcs->drv, tcs->offset + i))
+			return tcs->offset + i;
+	}
+
+	return -EBUSY;
+}
+
+static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	struct tcs_group *tcs;
+	int tcs_id;
+	unsigned long flags;
+	int ret;
+
+	tcs = get_tcs_for_msg(drv, msg);
+	if (IS_ERR(tcs))
+		return PTR_ERR(tcs);
+
+	spin_lock_irqsave(&tcs->lock, flags);
+	spin_lock(&drv->lock);
+	/*
+	 * The h/w does not like if we send a request to the same address,
+	 * when one is already in-flight or being processed.
+	 */
+	ret = check_for_req_inflight(drv, tcs, msg);
+	if (ret) {
+		spin_unlock(&drv->lock);
+		goto done_write;
+	}
+
+	tcs_id = find_free_tcs(tcs);
+	if (tcs_id < 0) {
+		ret = tcs_id;
+		spin_unlock(&drv->lock);
+		goto done_write;
+	}
+
+	tcs->req[tcs_id - tcs->offset] = msg;
+	set_bit(tcs_id, drv->tcs_in_use);
+	spin_unlock(&drv->lock);
+
+	__tcs_buffer_write(drv, tcs_id, 0, msg);
+	__tcs_trigger(drv, tcs_id);
+
+done_write:
+	spin_unlock_irqrestore(&tcs->lock, flags);
+	return ret;
+}
+
+/**
+ * rpmh_rsc_send_data: Validate the incoming message and write to the
+ * appropriate TCS block.
+ *
+ * @drv: the controller
+ * @msg: the data to be sent
+ *
+ * Return: 0 on success, -EINVAL on error.
+ * Note: This call blocks until a valid data is written to the TCS.
+ */
+int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	int ret;
+
+	if (!msg || !msg->cmds || !msg->num_cmds ||
+	    msg->num_cmds > MAX_RPMH_PAYLOAD) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	do {
+		ret = tcs_write(drv, msg);
+		if (ret == -EBUSY) {
+			pr_info_ratelimited("TCS Busy, retrying RPMH message send: addr=%#x\n",
+					    msg->cmds[0].addr);
+			udelay(10);
+		}
+	} while (ret == -EBUSY);
+
+	return ret;
+}
+
+static int find_match(const struct tcs_group *tcs, const struct tcs_cmd *cmd,
+		      int len)
+{
+	int i, j;
+
+	/* Check for already cached commands */
+	for_each_set_bit(i, tcs->slots, MAX_TCS_SLOTS) {
+		if (tcs->cmd_cache[i] != cmd[0].addr)
+			continue;
+		if (i + len >= tcs->num_tcs * tcs->ncpt)
+			goto seq_err;
+		for (j = 0; j < len; j++) {
+			if (tcs->cmd_cache[i + j] != cmd[j].addr)
+				goto seq_err;
+		}
+		return i;
+	}
+
+	return -ENODATA;
+
+seq_err:
+	WARN(1, "Message does not match previous sequence.\n");
+	return -EINVAL;
+}
+
+static int find_slots(struct tcs_group *tcs, const struct tcs_request *msg,
+		      int *tcs_id, int *cmd_id)
+{
+	int slot, offset;
+	int i = 0;
+
+	/* Find if we already have the msg in our TCS */
+	slot = find_match(tcs, msg->cmds, msg->num_cmds);
+	if (slot >= 0)
+		goto copy_data;
+
+	/* Do over, until we can fit the full payload in a TCS */
+	do {
+		slot = bitmap_find_next_zero_area(tcs->slots, MAX_TCS_SLOTS,
+						  i, msg->num_cmds, 0);
+		if (slot == tcs->num_tcs * tcs->ncpt)
+			return -ENOMEM;
+		i += tcs->ncpt;
+	} while (slot + msg->num_cmds - 1 >= i);
+
+copy_data:
+	bitmap_set(tcs->slots, slot, msg->num_cmds);
+	/* Copy the addresses of the resources over to the slots */
+	for (i = 0; i < msg->num_cmds; i++)
+		tcs->cmd_cache[slot + i] = msg->cmds[i].addr;
+
+	offset = slot / tcs->ncpt;
+	*tcs_id = offset + tcs->offset;
+	*cmd_id = slot % tcs->ncpt;
+
+	return 0;
+}
+
+static int tcs_ctrl_write(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	struct tcs_group *tcs;
+	int tcs_id = 0, cmd_id = 0;
+	unsigned long flags;
+	int ret;
+
+	tcs = get_tcs_for_msg(drv, msg);
+	if (IS_ERR(tcs))
+		return PTR_ERR(tcs);
+
+	spin_lock_irqsave(&tcs->lock, flags);
+	/* find the TCS id and the command in the TCS to write to */
+	ret = find_slots(tcs, msg, &tcs_id, &cmd_id);
+	if (!ret)
+		__tcs_buffer_write(drv, tcs_id, cmd_id, msg);
+	spin_unlock_irqrestore(&tcs->lock, flags);
+
+	return ret;
+}
+
+/**
+ * rpmh_rsc_write_ctrl_data: Write request to the controller
+ *
+ * @drv: the controller
+ * @msg: the data to be written to the controller
+ *
+ * There is no response returned for writing the request to the controller.
+ */
+int rpmh_rsc_write_ctrl_data(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	if (!msg || !msg->cmds || !msg->num_cmds ||
+	    msg->num_cmds > MAX_RPMH_PAYLOAD) {
+		pr_err("Payload error\n");
+		return -EINVAL;
+	}
+
+	/* Data sent to this API will not be sent immediately */
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE)
+		return -EINVAL;
+
+	return tcs_ctrl_write(drv, msg);
+}
+
+static int rpmh_probe_tcs_config(struct platform_device *pdev,
+				 struct rsc_drv *drv)
+{
+	struct tcs_type_config {
+		u32 type;
+		u32 n;
+	} tcs_cfg[TCS_TYPE_NR] = { { 0 } };
+	struct device_node *dn = pdev->dev.of_node;
+	u32 config, max_tcs, ncpt, offset;
+	int i, ret, n, st = 0;
+	struct tcs_group *tcs;
+	struct resource *res;
+	void __iomem *base;
+	char drv_id[10] = {0};
+
+	snprintf(drv_id, ARRAY_SIZE(drv_id), "drv-%d", drv->id);
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, drv_id);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	ret = of_property_read_u32(dn, "qcom,tcs-offset", &offset);
+	if (ret)
+		return ret;
+	drv->tcs_base = base + offset;
+
+	config = readl_relaxed(base + DRV_PRNT_CHLD_CONFIG);
+
+	max_tcs = config;
+	max_tcs &= DRV_NUM_TCS_MASK << (DRV_NUM_TCS_SHIFT * drv->id);
+	max_tcs = max_tcs >> (DRV_NUM_TCS_SHIFT * drv->id);
+
+	ncpt = config & (DRV_NCPT_MASK << DRV_NCPT_SHIFT);
+	ncpt = ncpt >> DRV_NCPT_SHIFT;
+
+	n = of_property_count_u32_elems(dn, "qcom,tcs-config");
+	if (n != 2 * TCS_TYPE_NR)
+		return -EINVAL;
+
+	for (i = 0; i < TCS_TYPE_NR; i++) {
+		ret = of_property_read_u32_index(dn, "qcom,tcs-config",
+						 i * 2, &tcs_cfg[i].type);
+		if (ret)
+			return ret;
+		if (tcs_cfg[i].type >= TCS_TYPE_NR)
+			return -EINVAL;
+
+		ret = of_property_read_u32_index(dn, "qcom,tcs-config",
+						 i * 2 + 1, &tcs_cfg[i].n);
+		if (ret)
+			return ret;
+		if (tcs_cfg[i].n > MAX_TCS_PER_TYPE)
+			return -EINVAL;
+	}
+
+	for (i = 0; i < TCS_TYPE_NR; i++) {
+		tcs = &drv->tcs[tcs_cfg[i].type];
+		if (tcs->drv)
+			return -EINVAL;
+		tcs->drv = drv;
+		tcs->type = tcs_cfg[i].type;
+		tcs->num_tcs = tcs_cfg[i].n;
+		tcs->ncpt = ncpt;
+		spin_lock_init(&tcs->lock);
+
+		if (!tcs->num_tcs || tcs->type == CONTROL_TCS)
+			continue;
+
+		if (st + tcs->num_tcs > max_tcs ||
+		    st + tcs->num_tcs >= BITS_PER_BYTE * sizeof(tcs->mask))
+			return -EINVAL;
+
+		tcs->mask = ((1 << tcs->num_tcs) - 1) << st;
+		tcs->offset = st;
+		st += tcs->num_tcs;
+
+		/*
+		 * Allocate memory to cache sleep and wake requests to
+		 * avoid reading TCS register memory.
+		 */
+		if (tcs->type == ACTIVE_TCS)
+			continue;
+
+		tcs->cmd_cache = devm_kcalloc(&pdev->dev,
+					      tcs->num_tcs * ncpt, sizeof(u32),
+					      GFP_KERNEL);
+		if (!tcs->cmd_cache)
+			return -ENOMEM;
+	}
+
+	drv->num_tcs = st;
+
+	return 0;
+}
+
+static int rpmh_rsc_probe(struct platform_device *pdev)
+{
+	struct device_node *dn = pdev->dev.of_node;
+	struct rsc_drv *drv;
+	int ret, irq;
+
+	/*
+	 * Even though RPMh doesn't directly use cmd-db, all of its children
+	 * do. To avoid adding this check to our children we'll do it now.
+	 */
+	ret = cmd_db_ready();
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "Command DB not available (%d)\n",
+									ret);
+		return ret;
+	}
+
+	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
+	if (!drv)
+		return -ENOMEM;
+
+	ret = of_property_read_u32(dn, "qcom,drv-id", &drv->id);
+	if (ret)
+		return ret;
+
+	drv->name = of_get_property(dn, "label", NULL);
+	if (!drv->name)
+		drv->name = dev_name(&pdev->dev);
+
+	ret = rpmh_probe_tcs_config(pdev, drv);
+	if (ret)
+		return ret;
+
+	spin_lock_init(&drv->lock);
+	bitmap_zero(drv->tcs_in_use, MAX_TCS_NR);
+
+	irq = platform_get_irq(pdev, drv->id);
+	if (irq < 0)
+		return irq;
+
+	ret = devm_request_irq(&pdev->dev, irq, tcs_tx_done,
+			       IRQF_TRIGGER_HIGH | IRQF_NO_SUSPEND,
+			       drv->name, drv);
+	if (ret)
+		return ret;
+
+	/* Enable the active TCS to send requests immediately */
+	write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, drv->tcs[ACTIVE_TCS].mask);
+
+	spin_lock_init(&drv->client.cache_lock);
+	INIT_LIST_HEAD(&drv->client.cache);
+	INIT_LIST_HEAD(&drv->client.batch_cache);
+
+	dev_set_drvdata(&pdev->dev, drv);
+
+	return devm_of_platform_populate(&pdev->dev);
+}
+
+static const struct of_device_id rpmh_drv_match[] = {
+	{ .compatible = "qcom,rpmh-rsc", },
+	{ }
+};
+
+static struct platform_driver rpmh_driver = {
+	.probe = rpmh_rsc_probe,
+	.driver = {
+		  .name = "rpmh",
+		  .of_match_table = rpmh_drv_match,
+	},
+};
+
+static int __init rpmh_driver_init(void)
+{
+	return platform_driver_register(&rpmh_driver);
+}
+arch_initcall(rpmh_driver_init);
diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
new file mode 100644
index 000000000000..c7beb6841289
--- /dev/null
+++ b/drivers/soc/qcom/rpmh.c
@@ -0,0 +1,513 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/interrupt.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#include <soc/qcom/rpmh.h>
+
+#include "rpmh-internal.h"
+
+#define RPMH_TIMEOUT_MS			msecs_to_jiffies(10000)
+
+#define DEFINE_RPMH_MSG_ONSTACK(dev, s, q, name)	\
+	struct rpmh_request name = {			\
+		.msg = {				\
+			.state = s,			\
+			.cmds = name.cmd,		\
+			.num_cmds = 0,			\
+			.wait_for_compl = true,		\
+		},					\
+		.cmd = { { 0 } },			\
+		.completion = q,			\
+		.dev = dev,				\
+		.needs_free = false,				\
+	}
+
+#define ctrlr_to_drv(ctrlr) container_of(ctrlr, struct rsc_drv, client)
+
+/**
+ * struct cache_req: the request object for caching
+ *
+ * @addr: the address of the resource
+ * @sleep_val: the sleep vote
+ * @wake_val: the wake vote
+ * @list: linked list obj
+ */
+struct cache_req {
+	u32 addr;
+	u32 sleep_val;
+	u32 wake_val;
+	struct list_head list;
+};
+
+/**
+ * struct batch_cache_req - An entry in our batch catch
+ *
+ * @list: linked list obj
+ * @count: number of messages
+ * @rpm_msgs: the messages
+ */
+
+struct batch_cache_req {
+	struct list_head list;
+	int count;
+	struct rpmh_request rpm_msgs[];
+};
+
+static struct rpmh_ctrlr *get_rpmh_ctrlr(const struct device *dev)
+{
+	struct rsc_drv *drv = dev_get_drvdata(dev->parent);
+
+	return &drv->client;
+}
+
+void rpmh_tx_done(const struct tcs_request *msg, int r)
+{
+	struct rpmh_request *rpm_msg = container_of(msg, struct rpmh_request,
+						    msg);
+	struct completion *compl = rpm_msg->completion;
+
+	rpm_msg->err = r;
+
+	if (r)
+		dev_err(rpm_msg->dev, "RPMH TX fail in msg addr=%#x, err=%d\n",
+			rpm_msg->msg.cmds[0].addr, r);
+
+	if (!compl)
+		goto exit;
+
+	/* Signal the blocking thread we are done */
+	complete(compl);
+
+exit:
+	if (rpm_msg->needs_free)
+		kfree(rpm_msg);
+}
+
+static struct cache_req *__find_req(struct rpmh_ctrlr *ctrlr, u32 addr)
+{
+	struct cache_req *p, *req = NULL;
+
+	list_for_each_entry(p, &ctrlr->cache, list) {
+		if (p->addr == addr) {
+			req = p;
+			break;
+		}
+	}
+
+	return req;
+}
+
+static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr,
+					   enum rpmh_state state,
+					   struct tcs_cmd *cmd)
+{
+	struct cache_req *req;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	req = __find_req(ctrlr, cmd->addr);
+	if (req)
+		goto existing;
+
+	req = kzalloc(sizeof(*req), GFP_ATOMIC);
+	if (!req) {
+		req = ERR_PTR(-ENOMEM);
+		goto unlock;
+	}
+
+	req->addr = cmd->addr;
+	req->sleep_val = req->wake_val = UINT_MAX;
+	INIT_LIST_HEAD(&req->list);
+	list_add_tail(&req->list, &ctrlr->cache);
+
+existing:
+	switch (state) {
+	case RPMH_ACTIVE_ONLY_STATE:
+		if (req->sleep_val != UINT_MAX)
+			req->wake_val = cmd->data;
+		break;
+	case RPMH_WAKE_ONLY_STATE:
+		req->wake_val = cmd->data;
+		break;
+	case RPMH_SLEEP_STATE:
+		req->sleep_val = cmd->data;
+		break;
+	default:
+		break;
+	}
+
+	ctrlr->dirty = true;
+unlock:
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+
+	return req;
+}
+
+/**
+ * __rpmh_write: Cache and send the RPMH request
+ *
+ * @dev: The device making the request
+ * @state: Active/Sleep request type
+ * @rpm_msg: The data that needs to be sent (cmds).
+ *
+ * Cache the RPMH request and send if the state is ACTIVE_ONLY.
+ * SLEEP/WAKE_ONLY requests are not sent to the controller at
+ * this time. Use rpmh_flush() to send them to the controller.
+ */
+static int __rpmh_write(const struct device *dev, enum rpmh_state state,
+			struct rpmh_request *rpm_msg)
+{
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	int ret = -EINVAL;
+	struct cache_req *req;
+	int i;
+
+	rpm_msg->msg.state = state;
+
+	/* Cache the request in our store and link the payload */
+	for (i = 0; i < rpm_msg->msg.num_cmds; i++) {
+		req = cache_rpm_request(ctrlr, state, &rpm_msg->msg.cmds[i]);
+		if (IS_ERR(req))
+			return PTR_ERR(req);
+	}
+
+	rpm_msg->msg.state = state;
+
+	if (state == RPMH_ACTIVE_ONLY_STATE) {
+		WARN_ON(irqs_disabled());
+		ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg);
+	} else {
+		ret = rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr),
+				&rpm_msg->msg);
+		/* Clean up our call by spoofing tx_done */
+		rpmh_tx_done(&rpm_msg->msg, ret);
+	}
+
+	return ret;
+}
+
+static int __fill_rpmh_msg(struct rpmh_request *req, enum rpmh_state state,
+		const struct tcs_cmd *cmd, u32 n)
+{
+	if (!cmd || !n || n > MAX_RPMH_PAYLOAD)
+		return -EINVAL;
+
+	memcpy(req->cmd, cmd, n * sizeof(*cmd));
+
+	req->msg.state = state;
+	req->msg.cmds = req->cmd;
+	req->msg.num_cmds = n;
+
+	return 0;
+}
+
+/**
+ * rpmh_write_async: Write a set of RPMH commands
+ *
+ * @dev: The device making the request
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The number of elements in payload
+ *
+ * Write a set of RPMH commands, the order of commands is maintained
+ * and will be sent as a single shot.
+ */
+int rpmh_write_async(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 n)
+{
+	struct rpmh_request *rpm_msg;
+	int ret;
+
+	rpm_msg = kzalloc(sizeof(*rpm_msg), GFP_ATOMIC);
+	if (!rpm_msg)
+		return -ENOMEM;
+	rpm_msg->needs_free = true;
+
+	ret = __fill_rpmh_msg(rpm_msg, state, cmd, n);
+	if (ret) {
+		kfree(rpm_msg);
+		return ret;
+	}
+
+	return __rpmh_write(dev, state, rpm_msg);
+}
+EXPORT_SYMBOL(rpmh_write_async);
+
+/**
+ * rpmh_write: Write a set of RPMH commands and block until response
+ *
+ * @rc: The RPMH handle got from rpmh_get_client
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The number of elements in @cmd
+ *
+ * May sleep. Do not call from atomic contexts.
+ */
+int rpmh_write(const struct device *dev, enum rpmh_state state,
+	       const struct tcs_cmd *cmd, u32 n)
+{
+	DECLARE_COMPLETION_ONSTACK(compl);
+	DEFINE_RPMH_MSG_ONSTACK(dev, state, &compl, rpm_msg);
+	int ret;
+
+	if (!cmd || !n || n > MAX_RPMH_PAYLOAD)
+		return -EINVAL;
+
+	memcpy(rpm_msg.cmd, cmd, n * sizeof(*cmd));
+	rpm_msg.msg.num_cmds = n;
+
+	ret = __rpmh_write(dev, state, &rpm_msg);
+	if (ret)
+		return ret;
+
+	ret = wait_for_completion_timeout(&compl, RPMH_TIMEOUT_MS);
+	WARN_ON(!ret);
+	return (ret > 0) ? 0 : -ETIMEDOUT;
+}
+EXPORT_SYMBOL(rpmh_write);
+
+static void cache_batch(struct rpmh_ctrlr *ctrlr, struct batch_cache_req *req)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_add_tail(&req->list, &ctrlr->batch_cache);
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+}
+
+static int flush_batch(struct rpmh_ctrlr *ctrlr)
+{
+	struct batch_cache_req *req;
+	const struct rpmh_request *rpm_msg;
+	unsigned long flags;
+	int ret = 0;
+	int i;
+
+	/* Send Sleep/Wake requests to the controller, expect no response */
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_for_each_entry(req, &ctrlr->batch_cache, list) {
+		for (i = 0; i < req->count; i++) {
+			rpm_msg = req->rpm_msgs + i;
+			ret = rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr),
+						       &rpm_msg->msg);
+			if (ret)
+				break;
+		}
+	}
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+
+	return ret;
+}
+
+static void invalidate_batch(struct rpmh_ctrlr *ctrlr)
+{
+	struct batch_cache_req *req, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list)
+		kfree(req);
+	INIT_LIST_HEAD(&ctrlr->batch_cache);
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+}
+
+/**
+ * rpmh_write_batch: Write multiple sets of RPMH commands and wait for the
+ * batch to finish.
+ *
+ * @dev: the device making the request
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The array of count of elements in each batch, 0 terminated.
+ *
+ * Write a request to the RSC controller without caching. If the request
+ * state is ACTIVE, then the requests are treated as completion request
+ * and sent to the controller immediately. The function waits until all the
+ * commands are complete. If the request was to SLEEP or WAKE_ONLY, then the
+ * request is sent as fire-n-forget and no ack is expected.
+ *
+ * May sleep. Do not call from atomic contexts for ACTIVE_ONLY requests.
+ */
+int rpmh_write_batch(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 *n)
+{
+	struct batch_cache_req *req;
+	struct rpmh_request *rpm_msgs;
+	DECLARE_COMPLETION_ONSTACK(compl);
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	unsigned long time_left;
+	int count = 0;
+	int ret, i, j;
+
+	if (!cmd || !n)
+		return -EINVAL;
+
+	while (n[count] > 0)
+		count++;
+	if (!count)
+		return -EINVAL;
+
+	req = kzalloc(sizeof(*req) + count * sizeof(req->rpm_msgs[0]),
+		      GFP_ATOMIC);
+	if (!req)
+		return -ENOMEM;
+	req->count = count;
+	rpm_msgs = req->rpm_msgs;
+
+	for (i = 0; i < count; i++) {
+		__fill_rpmh_msg(rpm_msgs + i, state, cmd, n[i]);
+		cmd += n[i];
+	}
+
+	if (state != RPMH_ACTIVE_ONLY_STATE) {
+		cache_batch(ctrlr, req);
+		return 0;
+	}
+
+	for (i = 0; i < count; i++) {
+		rpm_msgs[i].completion = &compl;
+		ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msgs[i].msg);
+		if (ret) {
+			pr_err("Error(%d) sending RPMH message addr=%#x\n",
+			       ret, rpm_msgs[i].msg.cmds[0].addr);
+			for (j = i; j < count; j++)
+				rpmh_tx_done(&rpm_msgs[j].msg, ret);
+			break;
+		}
+	}
+
+	time_left = RPMH_TIMEOUT_MS;
+	for (i = 0; i < count; i++) {
+		time_left = wait_for_completion_timeout(&compl, time_left);
+		if (!time_left) {
+			/*
+			 * Better hope they never finish because they'll signal
+			 * the completion on our stack and that's bad once
+			 * we've returned from the function.
+			 */
+			WARN_ON(1);
+			ret = -ETIMEDOUT;
+			goto exit;
+		}
+	}
+
+exit:
+	kfree(req);
+
+	return ret;
+}
+EXPORT_SYMBOL(rpmh_write_batch);
+
+static int is_req_valid(struct cache_req *req)
+{
+	return (req->sleep_val != UINT_MAX &&
+		req->wake_val != UINT_MAX &&
+		req->sleep_val != req->wake_val);
+}
+
+static int send_single(const struct device *dev, enum rpmh_state state,
+		       u32 addr, u32 data)
+{
+	DEFINE_RPMH_MSG_ONSTACK(dev, state, NULL, rpm_msg);
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+
+	/* Wake sets are always complete and sleep sets are not */
+	rpm_msg.msg.wait_for_compl = (state == RPMH_WAKE_ONLY_STATE);
+	rpm_msg.cmd[0].addr = addr;
+	rpm_msg.cmd[0].data = data;
+	rpm_msg.msg.num_cmds = 1;
+
+	return rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr), &rpm_msg.msg);
+}
+
+/**
+ * rpmh_flush: Flushes the buffered active and sleep sets to TCS
+ *
+ * @dev: The device making the request
+ *
+ * Return: -EBUSY if the controller is busy, probably waiting on a response
+ * to a RPMH request sent earlier.
+ *
+ * This function is always called from the sleep code from the last CPU
+ * that is powering down the entire system. Since no other RPMH API would be
+ * executing at this time, it is safe to run lockless.
+ */
+int rpmh_flush(const struct device *dev)
+{
+	struct cache_req *p;
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	int ret;
+
+	if (!ctrlr->dirty) {
+		pr_debug("Skipping flush, TCS has latest data.\n");
+		return 0;
+	}
+
+	/* First flush the cached batch requests */
+	ret = flush_batch(ctrlr);
+	if (ret)
+		return ret;
+
+	/*
+	 * Nobody else should be calling this function other than system PM,
+	 * hence we can run without locks.
+	 */
+	list_for_each_entry(p, &ctrlr->cache, list) {
+		if (!is_req_valid(p)) {
+			pr_debug("%s: skipping RPMH req: a:%#x s:%#x w:%#x",
+				 __func__, p->addr, p->sleep_val, p->wake_val);
+			continue;
+		}
+		ret = send_single(dev, RPMH_SLEEP_STATE, p->addr, p->sleep_val);
+		if (ret)
+			return ret;
+		ret = send_single(dev, RPMH_WAKE_ONLY_STATE,
+				  p->addr, p->wake_val);
+		if (ret)
+			return ret;
+	}
+
+	ctrlr->dirty = false;
+
+	return 0;
+}
+EXPORT_SYMBOL(rpmh_flush);
+
+/**
+ * rpmh_invalidate: Invalidate all sleep and active sets
+ * sets.
+ *
+ * @dev: The device making the request
+ *
+ * Invalidate the sleep and active values in the TCS blocks.
+ */
+int rpmh_invalidate(const struct device *dev)
+{
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	int ret;
+
+	invalidate_batch(ctrlr);
+	ctrlr->dirty = true;
+
+	do {
+		ret = rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr));
+	} while (ret == -EAGAIN);
+
+	return ret;
+}
+EXPORT_SYMBOL(rpmh_invalidate);
diff --git a/drivers/soc/qcom/smem.c b/drivers/soc/qcom/smem.c
index 70b2ee80d6bd..bf4bd71ab53f 100644
--- a/drivers/soc/qcom/smem.c
+++ b/drivers/soc/qcom/smem.c
@@ -364,11 +364,6 @@ static int qcom_smem_alloc_private(struct qcom_smem *smem,
 	end = phdr_to_last_uncached_entry(phdr);
 	cached = phdr_to_last_cached_entry(phdr);
 
-	if (smem->global_partition) {
-		dev_err(smem->dev, "Already found the global partition\n");
-		return -EINVAL;
-	}
-
 	while (hdr < end) {
 		if (hdr->canary != SMEM_PRIVATE_CANARY)
 			goto bad_canary;
@@ -736,6 +731,11 @@ static int qcom_smem_set_global_partition(struct qcom_smem *smem)
 	bool found = false;
 	int i;
 
+	if (smem->global_partition) {
+		dev_err(smem->dev, "Already found the global partition\n");
+		return -EINVAL;
+	}
+
 	ptable = qcom_smem_get_ptable(smem);
 	if (IS_ERR(ptable))
 		return PTR_ERR(ptable);
diff --git a/drivers/soc/qcom/trace-rpmh.h b/drivers/soc/qcom/trace-rpmh.h
new file mode 100644
index 000000000000..feb0cb455e37
--- /dev/null
+++ b/drivers/soc/qcom/trace-rpmh.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#if !defined(_TRACE_RPMH_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RPMH_H
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rpmh
+
+#include <linux/tracepoint.h>
+#include "rpmh-internal.h"
+
+TRACE_EVENT(rpmh_tx_done,
+
+	TP_PROTO(struct rsc_drv *d, int m, const struct tcs_request *r, int e),
+
+	TP_ARGS(d, m, r, e),
+
+	TP_STRUCT__entry(
+			 __string(name, d->name)
+			 __field(int, m)
+			 __field(u32, addr)
+			 __field(u32, data)
+			 __field(int, err)
+	),
+
+	TP_fast_assign(
+		       __assign_str(name, d->name);
+		       __entry->m = m;
+		       __entry->addr = r->cmds[0].addr;
+		       __entry->data = r->cmds[0].data;
+		       __entry->err = e;
+	),
+
+	TP_printk("%s: ack: tcs-m: %d addr: %#x data: %#x errno: %d",
+		  __get_str(name), __entry->m, __entry->addr, __entry->data,
+		  __entry->err)
+);
+
+TRACE_EVENT(rpmh_send_msg,
+
+	TP_PROTO(struct rsc_drv *d, int m, int n, u32 h,
+		 const struct tcs_cmd *c),
+
+	TP_ARGS(d, m, n, h, c),
+
+	TP_STRUCT__entry(
+			 __string(name, d->name)
+			 __field(int, m)
+			 __field(int, n)
+			 __field(u32, hdr)
+			 __field(u32, addr)
+			 __field(u32, data)
+			 __field(bool, wait)
+	),
+
+	TP_fast_assign(
+		       __assign_str(name, d->name);
+		       __entry->m = m;
+		       __entry->n = n;
+		       __entry->hdr = h;
+		       __entry->addr = c->addr;
+		       __entry->data = c->data;
+		       __entry->wait = c->wait;
+	),
+
+	TP_printk("%s: send-msg: tcs(m): %d cmd(n): %d msgid: %#x addr: %#x data: %#x complete: %d",
+		  __get_str(name), __entry->m, __entry->n, __entry->hdr,
+		  __entry->addr, __entry->data, __entry->wait)
+);
+
+#endif /* _TRACE_RPMH_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace-rpmh
+
+#include <trace/define_trace.h>
diff --git a/drivers/soc/renesas/rcar-sysc.c b/drivers/soc/renesas/rcar-sysc.c
index 95120acc4d80..50d03d8b4f9a 100644
--- a/drivers/soc/renesas/rcar-sysc.c
+++ b/drivers/soc/renesas/rcar-sysc.c
@@ -194,11 +194,12 @@ static int rcar_sysc_pd_power_on(struct generic_pm_domain *genpd)
 
 static bool has_cpg_mstp;
 
-static void __init rcar_sysc_pd_setup(struct rcar_sysc_pd *pd)
+static int __init rcar_sysc_pd_setup(struct rcar_sysc_pd *pd)
 {
 	struct generic_pm_domain *genpd = &pd->genpd;
 	const char *name = pd->genpd.name;
 	struct dev_power_governor *gov = &simple_qos_governor;
+	int error;
 
 	if (pd->flags & PD_CPU) {
 		/*
@@ -251,7 +252,11 @@ static void __init rcar_sysc_pd_setup(struct rcar_sysc_pd *pd)
 	rcar_sysc_power_up(&pd->ch);
 
 finalize:
-	pm_genpd_init(genpd, gov, false);
+	error = pm_genpd_init(genpd, gov, false);
+	if (error)
+		pr_err("Failed to init PM domain %s: %d\n", name, error);
+
+	return error;
 }
 
 static const struct of_device_id rcar_sysc_matches[] __initconst = {
@@ -375,6 +380,9 @@ static int __init rcar_sysc_pd_init(void)
 	pr_debug("%pOF: syscier = 0x%08x\n", np, syscier);
 	iowrite32(syscier, base + SYSCIER);
 
+	/*
+	 * First, create all PM domains
+	 */
 	for (i = 0; i < info->num_areas; i++) {
 		const struct rcar_sysc_area *area = &info->areas[i];
 		struct rcar_sysc_pd *pd;
@@ -397,14 +405,29 @@ static int __init rcar_sysc_pd_init(void)
 		pd->ch.isr_bit = area->isr_bit;
 		pd->flags = area->flags;
 
-		rcar_sysc_pd_setup(pd);
-		if (area->parent >= 0)
-			pm_genpd_add_subdomain(domains->domains[area->parent],
-					       &pd->genpd);
+		error = rcar_sysc_pd_setup(pd);
+		if (error)
+			goto out_put;
 
 		domains->domains[area->isr_bit] = &pd->genpd;
 	}
 
+	/*
+	 * Second, link all PM domains to their parents
+	 */
+	for (i = 0; i < info->num_areas; i++) {
+		const struct rcar_sysc_area *area = &info->areas[i];
+
+		if (!area->name || area->parent < 0)
+			continue;
+
+		error = pm_genpd_add_subdomain(domains->domains[area->parent],
+					       domains->domains[area->isr_bit]);
+		if (error)
+			pr_warn("Failed to add PM subdomain %s to parent %u\n",
+				area->name, area->parent);
+	}
+
 	error = of_genpd_add_provider_onecell(np, &domains->onecell_data);
 
 out_put:
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index ad5d68e1dab7..671d078349cc 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -688,6 +688,19 @@ config SPI_TXX9
 	help
 	  SPI driver for Toshiba TXx9 MIPS SoCs
 
+config SPI_UNIPHIER
+	tristate "Socionext UniPhier SPI Controller"
+	depends on (ARCH_UNIPHIER || COMPILE_TEST) && OF
+	help
+	  This enables a driver for the Socionext UniPhier SoC SCSSI SPI controller.
+
+	  UniPhier SoCs have SCSSI and MCSSI SPI controllers.
+	  Every UniPhier SoC has SCSSI which supports single channel.
+	  Older UniPhier Pro4/Pro5 also has MCSSI which support multiple channels.
+	  This driver supports SCSSI only.
+
+	  If your SoC supports SCSSI, say Y here.
+
 config SPI_XCOMM
 	tristate "Analog Devices AD-FMCOMMS1-EBZ SPI-I2C-bridge driver"
 	depends on I2C
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index cb1f4378b87c..a90d55970036 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -101,6 +101,7 @@ spi-thunderx-objs			:= spi-cavium.o spi-cavium-thunderx.o
 obj-$(CONFIG_SPI_THUNDERX)		+= spi-thunderx.o
 obj-$(CONFIG_SPI_TOPCLIFF_PCH)		+= spi-topcliff-pch.o
 obj-$(CONFIG_SPI_TXX9)			+= spi-txx9.o
+obj-$(CONFIG_SPI_UNIPHIER)		+= spi-uniphier.o
 obj-$(CONFIG_SPI_XCOMM)		+= spi-xcomm.o
 obj-$(CONFIG_SPI_XILINX)		+= spi-xilinx.o
 obj-$(CONFIG_SPI_XLP)			+= spi-xlp.o
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index 0719bd484891..3f6b657394de 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -176,7 +176,7 @@ static void ath79_spi_cleanup(struct spi_device *spi)
 }
 
 static u32 ath79_spi_txrx_mode0(struct spi_device *spi, unsigned int nsecs,
-			       u32 word, u8 bits)
+			       u32 word, u8 bits, unsigned flags)
 {
 	struct ath79_spi *sp = ath79_spidev_to_sp(spi);
 	u32 ioc = sp->ioc_base;
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index 3aa9e6e3dac8..f29176000b8d 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -49,22 +49,26 @@
 struct spi_bitbang_cs {
 	unsigned	nsecs;	/* (clock cycle time)/2 */
 	u32		(*txrx_word)(struct spi_device *spi, unsigned nsecs,
-					u32 word, u8 bits);
+					u32 word, u8 bits, unsigned flags);
 	unsigned	(*txrx_bufs)(struct spi_device *,
 					u32 (*txrx_word)(
 						struct spi_device *spi,
 						unsigned nsecs,
-						u32 word, u8 bits),
-					unsigned, struct spi_transfer *);
+						u32 word, u8 bits,
+						unsigned flags),
+					unsigned, struct spi_transfer *,
+					unsigned);
 };
 
 static unsigned bitbang_txrx_8(
 	struct spi_device	*spi,
 	u32			(*txrx_word)(struct spi_device *spi,
 					unsigned nsecs,
-					u32 word, u8 bits),
+					u32 word, u8 bits,
+					unsigned flags),
 	unsigned		ns,
-	struct spi_transfer	*t
+	struct spi_transfer	*t,
+	unsigned flags
 ) {
 	unsigned		bits = t->bits_per_word;
 	unsigned		count = t->len;
@@ -76,7 +80,7 @@ static unsigned bitbang_txrx_8(
 
 		if (tx)
 			word = *tx++;
-		word = txrx_word(spi, ns, word, bits);
+		word = txrx_word(spi, ns, word, bits, flags);
 		if (rx)
 			*rx++ = word;
 		count -= 1;
@@ -88,9 +92,11 @@ static unsigned bitbang_txrx_16(
 	struct spi_device	*spi,
 	u32			(*txrx_word)(struct spi_device *spi,
 					unsigned nsecs,
-					u32 word, u8 bits),
+					u32 word, u8 bits,
+					unsigned flags),
 	unsigned		ns,
-	struct spi_transfer	*t
+	struct spi_transfer	*t,
+	unsigned flags
 ) {
 	unsigned		bits = t->bits_per_word;
 	unsigned		count = t->len;
@@ -102,7 +108,7 @@ static unsigned bitbang_txrx_16(
 
 		if (tx)
 			word = *tx++;
-		word = txrx_word(spi, ns, word, bits);
+		word = txrx_word(spi, ns, word, bits, flags);
 		if (rx)
 			*rx++ = word;
 		count -= 2;
@@ -114,9 +120,11 @@ static unsigned bitbang_txrx_32(
 	struct spi_device	*spi,
 	u32			(*txrx_word)(struct spi_device *spi,
 					unsigned nsecs,
-					u32 word, u8 bits),
+					u32 word, u8 bits,
+					unsigned flags),
 	unsigned		ns,
-	struct spi_transfer	*t
+	struct spi_transfer	*t,
+	unsigned flags
 ) {
 	unsigned		bits = t->bits_per_word;
 	unsigned		count = t->len;
@@ -128,7 +136,7 @@ static unsigned bitbang_txrx_32(
 
 		if (tx)
 			word = *tx++;
-		word = txrx_word(spi, ns, word, bits);
+		word = txrx_word(spi, ns, word, bits, flags);
 		if (rx)
 			*rx++ = word;
 		count -= 4;
@@ -235,8 +243,24 @@ static int spi_bitbang_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct spi_bitbang_cs	*cs = spi->controller_state;
 	unsigned		nsecs = cs->nsecs;
+	struct spi_bitbang	*bitbang;
+
+	bitbang = spi_master_get_devdata(spi->master);
+	if (bitbang->set_line_direction) {
+		int err;
 
-	return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t);
+		err = bitbang->set_line_direction(spi, !!(t->tx_buf));
+		if (err < 0)
+			return err;
+	}
+
+	if (spi->mode & SPI_3WIRE) {
+		unsigned flags;
+
+		flags = t->tx_buf ? SPI_MASTER_NO_RX : SPI_MASTER_NO_TX;
+		return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, flags);
+	}
+	return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, 0);
 }
 
 /*----------------------------------------------------------------------*/
diff --git a/drivers/spi/spi-butterfly.c b/drivers/spi/spi-butterfly.c
index 22a31e4a1a11..1a3510215841 100644
--- a/drivers/spi/spi-butterfly.c
+++ b/drivers/spi/spi-butterfly.c
@@ -144,9 +144,9 @@ static void butterfly_chipselect(struct spi_device *spi, int value)
 
 static u32
 butterfly_txrx_word_mode0(struct spi_device *spi, unsigned nsecs, u32 word,
-			  u8 bits)
+			  u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 /*----------------------------------------------------------------------*/
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index f3dad6fcdc35..7c88f74f7f47 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -319,7 +319,7 @@ static void cdns_spi_fill_tx_fifo(struct cdns_spi *xspi)
 		 */
 		if (cdns_spi_read(xspi, CDNS_SPI_ISR) &
 		    CDNS_SPI_IXR_TXFULL)
-			usleep_range(10, 20);
+			udelay(10);
 
 		if (xspi->txbuf)
 			cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
@@ -739,7 +739,7 @@ static int __maybe_unused cnds_runtime_resume(struct device *dev)
 	ret = clk_prepare_enable(xspi->ref_clk);
 	if (ret) {
 		dev_err(dev, "Cannot enable device clock.\n");
-		clk_disable(xspi->pclk);
+		clk_disable_unprepare(xspi->pclk);
 		return ret;
 	}
 	return 0;
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index 577084bb911b..a02099c90c5c 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -217,7 +217,7 @@ static void davinci_spi_chipselect(struct spi_device *spi, int value)
 	pdata = &dspi->pdata;
 
 	/* program delay transfers if tx_delay is non zero */
-	if (spicfg->wdelay)
+	if (spicfg && spicfg->wdelay)
 		spidat1 |= SPIDAT1_WDEL;
 
 	/*
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index d25cc4037e23..e80f60ed6fdf 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -15,11 +15,13 @@
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
 #include <linux/scatterlist.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/of_platform.h>
 #include <linux/property.h>
+#include <linux/regmap.h>
 
 #include "spi-dw.h"
 
@@ -28,10 +30,90 @@
 struct dw_spi_mmio {
 	struct dw_spi  dws;
 	struct clk     *clk;
+	void           *priv;
 };
 
+#define MSCC_CPU_SYSTEM_CTRL_GENERAL_CTRL	0x24
+#define OCELOT_IF_SI_OWNER_MASK			GENMASK(5, 4)
+#define OCELOT_IF_SI_OWNER_OFFSET		4
+#define MSCC_IF_SI_OWNER_SISL			0
+#define MSCC_IF_SI_OWNER_SIBM			1
+#define MSCC_IF_SI_OWNER_SIMC			2
+
+#define MSCC_SPI_MST_SW_MODE			0x14
+#define MSCC_SPI_MST_SW_MODE_SW_PIN_CTRL_MODE	BIT(13)
+#define MSCC_SPI_MST_SW_MODE_SW_SPI_CS(x)	(x << 5)
+
+struct dw_spi_mscc {
+	struct regmap       *syscon;
+	void __iomem        *spi_mst;
+};
+
+/*
+ * The Designware SPI controller (referred to as master in the documentation)
+ * automatically deasserts chip select when the tx fifo is empty. The chip
+ * selects then needs to be either driven as GPIOs or, for the first 4 using the
+ * the SPI boot controller registers. the final chip select is an OR gate
+ * between the Designware SPI controller and the SPI boot controller.
+ */
+static void dw_spi_mscc_set_cs(struct spi_device *spi, bool enable)
+{
+	struct dw_spi *dws = spi_master_get_devdata(spi->master);
+	struct dw_spi_mmio *dwsmmio = container_of(dws, struct dw_spi_mmio, dws);
+	struct dw_spi_mscc *dwsmscc = dwsmmio->priv;
+	u32 cs = spi->chip_select;
+
+	if (cs < 4) {
+		u32 sw_mode = MSCC_SPI_MST_SW_MODE_SW_PIN_CTRL_MODE;
+
+		if (!enable)
+			sw_mode |= MSCC_SPI_MST_SW_MODE_SW_SPI_CS(BIT(cs));
+
+		writel(sw_mode, dwsmscc->spi_mst + MSCC_SPI_MST_SW_MODE);
+	}
+
+	dw_spi_set_cs(spi, enable);
+}
+
+static int dw_spi_mscc_init(struct platform_device *pdev,
+			    struct dw_spi_mmio *dwsmmio)
+{
+	struct dw_spi_mscc *dwsmscc;
+	struct resource *res;
+
+	dwsmscc = devm_kzalloc(&pdev->dev, sizeof(*dwsmscc), GFP_KERNEL);
+	if (!dwsmscc)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	dwsmscc->spi_mst = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dwsmscc->spi_mst)) {
+		dev_err(&pdev->dev, "SPI_MST region map failed\n");
+		return PTR_ERR(dwsmscc->spi_mst);
+	}
+
+	dwsmscc->syscon = syscon_regmap_lookup_by_compatible("mscc,ocelot-cpu-syscon");
+	if (IS_ERR(dwsmscc->syscon))
+		return PTR_ERR(dwsmscc->syscon);
+
+	/* Deassert all CS */
+	writel(0, dwsmscc->spi_mst + MSCC_SPI_MST_SW_MODE);
+
+	/* Select the owner of the SI interface */
+	regmap_update_bits(dwsmscc->syscon, MSCC_CPU_SYSTEM_CTRL_GENERAL_CTRL,
+			   OCELOT_IF_SI_OWNER_MASK,
+			   MSCC_IF_SI_OWNER_SIMC << OCELOT_IF_SI_OWNER_OFFSET);
+
+	dwsmmio->dws.set_cs = dw_spi_mscc_set_cs;
+	dwsmmio->priv = dwsmscc;
+
+	return 0;
+}
+
 static int dw_spi_mmio_probe(struct platform_device *pdev)
 {
+	int (*init_func)(struct platform_device *pdev,
+			 struct dw_spi_mmio *dwsmmio);
 	struct dw_spi_mmio *dwsmmio;
 	struct dw_spi *dws;
 	struct resource *mem;
@@ -99,6 +181,13 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 		}
 	}
 
+	init_func = device_get_match_data(&pdev->dev);
+	if (init_func) {
+		ret = init_func(pdev, dwsmmio);
+		if (ret)
+			goto out;
+	}
+
 	ret = dw_spi_add_host(&pdev->dev, dws);
 	if (ret)
 		goto out;
@@ -123,6 +212,7 @@ static int dw_spi_mmio_remove(struct platform_device *pdev)
 
 static const struct of_device_id dw_spi_mmio_of_match[] = {
 	{ .compatible = "snps,dw-apb-ssi", },
+	{ .compatible = "mscc,ocelot-spi", .data = dw_spi_mscc_init},
 	{ /* end of table */}
 };
 MODULE_DEVICE_TABLE(of, dw_spi_mmio_of_match);
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index f693bfe95ab9..ac2eb89ef7a5 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -133,7 +133,7 @@ static inline void dw_spi_debugfs_remove(struct dw_spi *dws)
 }
 #endif /* CONFIG_DEBUG_FS */
 
-static void dw_spi_set_cs(struct spi_device *spi, bool enable)
+void dw_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	struct dw_spi *dws = spi_controller_get_devdata(spi->controller);
 	struct chip_data *chip = spi_get_ctldata(spi);
@@ -145,6 +145,7 @@ static void dw_spi_set_cs(struct spi_device *spi, bool enable)
 	if (!enable)
 		dw_writel(dws, DW_SPI_SER, BIT(spi->chip_select));
 }
+EXPORT_SYMBOL_GPL(dw_spi_set_cs);
 
 /* Return the max entries we can fill into tx fifo */
 static inline u32 tx_max(struct dw_spi *dws)
@@ -485,6 +486,8 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	dws->dma_inited = 0;
 	dws->dma_addr = (dma_addr_t)(dws->paddr + DW_SPI_DR);
 
+	spi_controller_set_devdata(master, dws);
+
 	ret = request_irq(dws->irq, dw_spi_irq, IRQF_SHARED, dev_name(dev),
 			  master);
 	if (ret < 0) {
@@ -505,6 +508,9 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	master->dev.of_node = dev->of_node;
 	master->flags = SPI_MASTER_GPIO_SS;
 
+	if (dws->set_cs)
+		master->set_cs = dws->set_cs;
+
 	/* Basic HW init */
 	spi_hw_init(dev, dws);
 
@@ -518,7 +524,6 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 		}
 	}
 
-	spi_controller_set_devdata(master, dws);
 	ret = devm_spi_register_controller(dev, master);
 	if (ret) {
 		dev_err(&master->dev, "problem registering spi master\n");
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index 2cde2473b3e9..0168b08364d5 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -112,6 +112,7 @@ struct dw_spi {
 	u32			reg_io_width;	/* DR I/O width in bytes */
 	u16			bus_num;
 	u16			num_cs;		/* supported slave numbers */
+	void (*set_cs)(struct spi_device *spi, bool enable);
 
 	/* Current message transfer state info */
 	size_t			len;
@@ -244,6 +245,7 @@ struct dw_spi_chip {
 	void (*cs_control)(u32 command);
 };
 
+extern void dw_spi_set_cs(struct spi_device *spi, bool enable);
 extern int dw_spi_add_host(struct device *dev, struct dw_spi *dws);
 extern void dw_spi_remove_host(struct dw_spi *dws);
 extern int dw_spi_suspend_host(struct dw_spi *dws);
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 0630962ce442..7cb3ab0a35a0 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1,17 +1,9 @@
-/*
- * drivers/spi/spi-fsl-dspi.c
- *
- * Copyright 2013 Freescale Semiconductor, Inc.
- *
- * Freescale DSPI driver
- * This file contains a driver for the Freescale DSPI
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2013 Freescale Semiconductor, Inc.
+//
+// Freescale DSPI driver
+// This file contains a driver for the Freescale DSPI
 
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -38,10 +30,6 @@
 
 #define DRIVER_NAME "fsl-dspi"
 
-#define TRAN_STATE_RX_VOID		0x01
-#define TRAN_STATE_TX_VOID		0x02
-#define TRAN_STATE_WORD_ODD_NUM	0x04
-
 #define DSPI_FIFO_SIZE			4
 #define DSPI_DMA_BUFSIZE		(DSPI_FIFO_SIZE * 1024)
 
@@ -50,6 +38,7 @@
 #define SPI_MCR_PCSIS		(0x3F << 16)
 #define SPI_MCR_CLR_TXF	(1 << 11)
 #define SPI_MCR_CLR_RXF	(1 << 10)
+#define SPI_MCR_XSPI		(1 << 3)
 
 #define SPI_TCR			0x08
 #define SPI_TCR_GET_TCNT(x)	(((x) & 0xffff0000) >> 16)
@@ -86,11 +75,16 @@
 #define SPI_RSER_TCFQE		0x80000000
 
 #define SPI_PUSHR		0x34
-#define SPI_PUSHR_CONT		(1 << 31)
-#define SPI_PUSHR_CTAS(x)	(((x) & 0x00000003) << 28)
-#define SPI_PUSHR_EOQ		(1 << 27)
-#define SPI_PUSHR_CTCNT	(1 << 26)
-#define SPI_PUSHR_PCS(x)	(((1 << x) & 0x0000003f) << 16)
+#define SPI_PUSHR_CMD_CONT	(1 << 15)
+#define SPI_PUSHR_CONT		(SPI_PUSHR_CMD_CONT << 16)
+#define SPI_PUSHR_CMD_CTAS(x)	(((x) & 0x0003) << 12)
+#define SPI_PUSHR_CTAS(x)	(SPI_PUSHR_CMD_CTAS(x) << 16)
+#define SPI_PUSHR_CMD_EOQ	(1 << 11)
+#define SPI_PUSHR_EOQ		(SPI_PUSHR_CMD_EOQ << 16)
+#define SPI_PUSHR_CMD_CTCNT	(1 << 10)
+#define SPI_PUSHR_CTCNT		(SPI_PUSHR_CMD_CTCNT << 16)
+#define SPI_PUSHR_CMD_PCS(x)	((1 << x) & 0x003f)
+#define SPI_PUSHR_PCS(x)	(SPI_PUSHR_CMD_PCS(x) << 16)
 #define SPI_PUSHR_TXDATA(x)	((x) & 0x0000ffff)
 
 #define SPI_PUSHR_SLAVE	0x34
@@ -107,21 +101,31 @@
 #define SPI_RXFR2		0x84
 #define SPI_RXFR3		0x88
 
+#define SPI_CTARE(x)		(0x11c + (((x) & 0x3) * 4))
+#define SPI_CTARE_FMSZE(x)	(((x) & 0x1) << 16)
+#define SPI_CTARE_DTCP(x)	((x) & 0x7ff)
+
+#define SPI_SREX		0x13c
+
 #define SPI_FRAME_BITS(bits)	SPI_CTAR_FMSZ((bits) - 1)
 #define SPI_FRAME_BITS_MASK	SPI_CTAR_FMSZ(0xf)
 #define SPI_FRAME_BITS_16	SPI_CTAR_FMSZ(0xf)
 #define SPI_FRAME_BITS_8	SPI_CTAR_FMSZ(0x7)
 
+#define SPI_FRAME_EBITS(bits)	SPI_CTARE_FMSZE(((bits) - 1) >> 4)
+#define SPI_FRAME_EBITS_MASK	SPI_CTARE_FMSZE(1)
+
+/* Register offsets for regmap_pushr */
+#define PUSHR_CMD		0x0
+#define PUSHR_TX		0x2
+
 #define SPI_CS_INIT		0x01
 #define SPI_CS_ASSERT		0x02
 #define SPI_CS_DROP		0x04
 
-#define SPI_TCR_TCNT_MAX	0x10000
-
 #define DMA_COMPLETION_TIMEOUT	msecs_to_jiffies(3000)
 
 struct chip_data {
-	u32 mcr_val;
 	u32 ctar_val;
 	u16 void_write_data;
 };
@@ -135,6 +139,7 @@ enum dspi_trans_mode {
 struct fsl_dspi_devtype_data {
 	enum dspi_trans_mode trans_mode;
 	u8 max_clock_factor;
+	bool xspi_mode;
 };
 
 static const struct fsl_dspi_devtype_data vf610_data = {
@@ -145,6 +150,7 @@ static const struct fsl_dspi_devtype_data vf610_data = {
 static const struct fsl_dspi_devtype_data ls1021a_v1_data = {
 	.trans_mode = DSPI_TCFQ_MODE,
 	.max_clock_factor = 8,
+	.xspi_mode = true,
 };
 
 static const struct fsl_dspi_devtype_data ls2085a_data = {
@@ -179,6 +185,7 @@ struct fsl_dspi {
 	struct platform_device	*pdev;
 
 	struct regmap		*regmap;
+	struct regmap		*regmap_pushr;
 	int			irq;
 	struct clk		*clk;
 
@@ -186,32 +193,62 @@ struct fsl_dspi {
 	struct spi_message	*cur_msg;
 	struct chip_data	*cur_chip;
 	size_t			len;
-	void			*tx;
-	void			*tx_end;
+	const void		*tx;
 	void			*rx;
 	void			*rx_end;
-	char			dataflags;
-	u8			cs;
 	u16			void_write_data;
-	u32			cs_change;
+	u16			tx_cmd;
+	u8			bits_per_word;
+	u8			bytes_per_word;
 	const struct fsl_dspi_devtype_data *devtype_data;
 
 	wait_queue_head_t	waitq;
 	u32			waitflags;
 
-	u32			spi_tcnt;
 	struct fsl_dspi_dma	*dma;
 };
 
-static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word);
+static u32 dspi_pop_tx(struct fsl_dspi *dspi)
+{
+	u32 txdata = 0;
+
+	if (dspi->tx) {
+		if (dspi->bytes_per_word == 1)
+			txdata = *(u8 *)dspi->tx;
+		else if (dspi->bytes_per_word == 2)
+			txdata = *(u16 *)dspi->tx;
+		else  /* dspi->bytes_per_word == 4 */
+			txdata = *(u32 *)dspi->tx;
+		dspi->tx += dspi->bytes_per_word;
+	}
+	dspi->len -= dspi->bytes_per_word;
+	return txdata;
+}
 
-static inline int is_double_byte_mode(struct fsl_dspi *dspi)
+static u32 dspi_pop_tx_pushr(struct fsl_dspi *dspi)
 {
-	unsigned int val;
+	u16 cmd = dspi->tx_cmd, data = dspi_pop_tx(dspi);
 
-	regmap_read(dspi->regmap, SPI_CTAR(0), &val);
+	if (dspi->len > 0)
+		cmd |= SPI_PUSHR_CMD_CONT;
+	return cmd << 16 | data;
+}
 
-	return ((val & SPI_FRAME_BITS_MASK) == SPI_FRAME_BITS(8)) ? 0 : 1;
+static void dspi_push_rx(struct fsl_dspi *dspi, u32 rxdata)
+{
+	if (!dspi->rx)
+		return;
+
+	/* Mask of undefined bits */
+	rxdata &= (1 << dspi->bits_per_word) - 1;
+
+	if (dspi->bytes_per_word == 1)
+		*(u8 *)dspi->rx = rxdata;
+	else if (dspi->bytes_per_word == 2)
+		*(u16 *)dspi->rx = rxdata;
+	else /* dspi->bytes_per_word == 4 */
+		*(u32 *)dspi->rx = rxdata;
+	dspi->rx += dspi->bytes_per_word;
 }
 
 static void dspi_tx_dma_callback(void *arg)
@@ -226,19 +263,11 @@ static void dspi_rx_dma_callback(void *arg)
 {
 	struct fsl_dspi *dspi = arg;
 	struct fsl_dspi_dma *dma = dspi->dma;
-	int rx_word;
 	int i;
-	u16 d;
-
-	rx_word = is_double_byte_mode(dspi);
 
-	if (!(dspi->dataflags & TRAN_STATE_RX_VOID)) {
-		for (i = 0; i < dma->curr_xfer_len; i++) {
-			d = dspi->dma->rx_dma_buf[i];
-			rx_word ? (*(u16 *)dspi->rx = d) :
-						(*(u8 *)dspi->rx = d);
-			dspi->rx += rx_word + 1;
-		}
+	if (dspi->rx) {
+		for (i = 0; i < dma->curr_xfer_len; i++)
+			dspi_push_rx(dspi, dspi->dma->rx_dma_buf[i]);
 	}
 
 	complete(&dma->cmd_rx_complete);
@@ -249,16 +278,10 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 	struct fsl_dspi_dma *dma = dspi->dma;
 	struct device *dev = &dspi->pdev->dev;
 	int time_left;
-	int tx_word;
 	int i;
 
-	tx_word = is_double_byte_mode(dspi);
-
-	for (i = 0; i < dma->curr_xfer_len; i++) {
-		dspi->dma->tx_dma_buf[i] = dspi_data_to_pushr(dspi, tx_word);
-		if ((dspi->cs_change) && (!dspi->len))
-			dspi->dma->tx_dma_buf[i] &= ~SPI_PUSHR_CONT;
-	}
+	for (i = 0; i < dma->curr_xfer_len; i++)
+		dspi->dma->tx_dma_buf[i] = dspi_pop_tx_pushr(dspi);
 
 	dma->tx_desc = dmaengine_prep_slave_single(dma->chan_tx,
 					dma->tx_dma_phys,
@@ -327,18 +350,17 @@ static int dspi_dma_xfer(struct fsl_dspi *dspi)
 {
 	struct fsl_dspi_dma *dma = dspi->dma;
 	struct device *dev = &dspi->pdev->dev;
+	struct spi_message *message = dspi->cur_msg;
 	int curr_remaining_bytes;
 	int bytes_per_buffer;
-	int word = 1;
 	int ret = 0;
 
-	if (is_double_byte_mode(dspi))
-		word = 2;
 	curr_remaining_bytes = dspi->len;
 	bytes_per_buffer = DSPI_DMA_BUFSIZE / DSPI_FIFO_SIZE;
 	while (curr_remaining_bytes) {
 		/* Check if current transfer fits the DMA buffer */
-		dma->curr_xfer_len = curr_remaining_bytes / word;
+		dma->curr_xfer_len = curr_remaining_bytes
+			/ dspi->bytes_per_word;
 		if (dma->curr_xfer_len > bytes_per_buffer)
 			dma->curr_xfer_len = bytes_per_buffer;
 
@@ -348,7 +370,10 @@ static int dspi_dma_xfer(struct fsl_dspi *dspi)
 			goto exit;
 
 		} else {
-			curr_remaining_bytes -= dma->curr_xfer_len * word;
+			const int len =
+				dma->curr_xfer_len * dspi->bytes_per_word;
+			curr_remaining_bytes -= len;
+			message->actual_length += len;
 			if (curr_remaining_bytes < 0)
 				curr_remaining_bytes = 0;
 		}
@@ -534,125 +559,91 @@ static void ns_delay_scale(char *psc, char *sc, int delay_ns,
 	}
 }
 
-static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word)
+static void fifo_write(struct fsl_dspi *dspi)
 {
-	u16 d16;
-
-	if (!(dspi->dataflags & TRAN_STATE_TX_VOID))
-		d16 = tx_word ? *(u16 *)dspi->tx : *(u8 *)dspi->tx;
-	else
-		d16 = dspi->void_write_data;
-
-	dspi->tx += tx_word + 1;
-	dspi->len -= tx_word + 1;
-
-	return	SPI_PUSHR_TXDATA(d16) |
-		SPI_PUSHR_PCS(dspi->cs) |
-		SPI_PUSHR_CTAS(0) |
-		SPI_PUSHR_CONT;
+	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pop_tx_pushr(dspi));
 }
 
-static void dspi_data_from_popr(struct fsl_dspi *dspi, int rx_word)
+static void cmd_fifo_write(struct fsl_dspi *dspi)
 {
-	u16 d;
-	unsigned int val;
-
-	regmap_read(dspi->regmap, SPI_POPR, &val);
-	d = SPI_POPR_RXDATA(val);
+	u16 cmd = dspi->tx_cmd;
 
-	if (!(dspi->dataflags & TRAN_STATE_RX_VOID))
-		rx_word ? (*(u16 *)dspi->rx = d) : (*(u8 *)dspi->rx = d);
-
-	dspi->rx += rx_word + 1;
+	if (dspi->len > 0)
+		cmd |= SPI_PUSHR_CMD_CONT;
+	regmap_write(dspi->regmap_pushr, PUSHR_CMD, cmd);
 }
 
-static int dspi_eoq_write(struct fsl_dspi *dspi)
+static void tx_fifo_write(struct fsl_dspi *dspi, u16 txdata)
 {
-	int tx_count = 0;
-	int tx_word;
-	u32 dspi_pushr = 0;
+	regmap_write(dspi->regmap_pushr, PUSHR_TX, txdata);
+}
 
-	tx_word = is_double_byte_mode(dspi);
+static void dspi_tcfq_write(struct fsl_dspi *dspi)
+{
+	/* Clear transfer count */
+	dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
 
-	while (dspi->len && (tx_count < DSPI_FIFO_SIZE)) {
-		/* If we are in word mode, only have a single byte to transfer
-		 * switch to byte mode temporarily.  Will switch back at the
-		 * end of the transfer.
+	if (dspi->devtype_data->xspi_mode && dspi->bits_per_word > 16) {
+		/* Write two TX FIFO entries first, and then the corresponding
+		 * CMD FIFO entry.
 		 */
-		if (tx_word && (dspi->len == 1)) {
-			dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM;
-			regmap_update_bits(dspi->regmap, SPI_CTAR(0),
-					SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8));
-			tx_word = 0;
-		}
-
-		dspi_pushr = dspi_data_to_pushr(dspi, tx_word);
-
-		if (dspi->len == 0 || tx_count == DSPI_FIFO_SIZE - 1) {
-			/* last transfer in the transfer */
-			dspi_pushr |= SPI_PUSHR_EOQ;
-			if ((dspi->cs_change) && (!dspi->len))
-				dspi_pushr &= ~SPI_PUSHR_CONT;
-		} else if (tx_word && (dspi->len == 1))
-			dspi_pushr |= SPI_PUSHR_EOQ;
+		u32 data = dspi_pop_tx(dspi);
 
-		regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
-
-		tx_count++;
+		if (dspi->cur_chip->ctar_val & SPI_CTAR_LSBFE(1)) {
+			/* LSB */
+			tx_fifo_write(dspi, data & 0xFFFF);
+			tx_fifo_write(dspi, data >> 16);
+		} else {
+			/* MSB */
+			tx_fifo_write(dspi, data >> 16);
+			tx_fifo_write(dspi, data & 0xFFFF);
+		}
+		cmd_fifo_write(dspi);
+	} else {
+		/* Write one entry to both TX FIFO and CMD FIFO
+		 * simultaneously.
+		 */
+		fifo_write(dspi);
 	}
-
-	return tx_count * (tx_word + 1);
 }
 
-static int dspi_eoq_read(struct fsl_dspi *dspi)
+static u32 fifo_read(struct fsl_dspi *dspi)
 {
-	int rx_count = 0;
-	int rx_word = is_double_byte_mode(dspi);
-
-	while ((dspi->rx < dspi->rx_end)
-			&& (rx_count < DSPI_FIFO_SIZE)) {
-		if (rx_word && (dspi->rx_end - dspi->rx) == 1)
-			rx_word = 0;
+	u32 rxdata = 0;
 
-		dspi_data_from_popr(dspi, rx_word);
-		rx_count++;
-	}
-
-	return rx_count;
+	regmap_read(dspi->regmap, SPI_POPR, &rxdata);
+	return rxdata;
 }
 
-static int dspi_tcfq_write(struct fsl_dspi *dspi)
+static void dspi_tcfq_read(struct fsl_dspi *dspi)
 {
-	int tx_word;
-	u32 dspi_pushr = 0;
-
-	tx_word = is_double_byte_mode(dspi);
+	dspi_push_rx(dspi, fifo_read(dspi));
+}
 
-	if (tx_word && (dspi->len == 1)) {
-		dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM;
-		regmap_update_bits(dspi->regmap, SPI_CTAR(0),
-				SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8));
-		tx_word = 0;
+static void dspi_eoq_write(struct fsl_dspi *dspi)
+{
+	int fifo_size = DSPI_FIFO_SIZE;
+
+	/* Fill TX FIFO with as many transfers as possible */
+	while (dspi->len && fifo_size--) {
+		/* Request EOQF for last transfer in FIFO */
+		if (dspi->len == dspi->bytes_per_word || fifo_size == 0)
+			dspi->tx_cmd |= SPI_PUSHR_CMD_EOQ;
+		/* Clear transfer count for first transfer in FIFO */
+		if (fifo_size == (DSPI_FIFO_SIZE - 1))
+			dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
+		/* Write combined TX FIFO and CMD FIFO entry */
+		fifo_write(dspi);
 	}
-
-	dspi_pushr = dspi_data_to_pushr(dspi, tx_word);
-
-	if ((dspi->cs_change) && (!dspi->len))
-		dspi_pushr &= ~SPI_PUSHR_CONT;
-
-	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
-
-	return tx_word + 1;
 }
 
-static void dspi_tcfq_read(struct fsl_dspi *dspi)
+static void dspi_eoq_read(struct fsl_dspi *dspi)
 {
-	int rx_word = is_double_byte_mode(dspi);
-
-	if (rx_word && (dspi->rx_end - dspi->rx) == 1)
-		rx_word = 0;
+	int fifo_size = DSPI_FIFO_SIZE;
 
-	dspi_data_from_popr(dspi, rx_word);
+	/* Read one FIFO entry at and push to rx buffer */
+	while ((dspi->rx < dspi->rx_end) && fifo_size--)
+		dspi_push_rx(dspi, fifo_read(dspi));
 }
 
 static int dspi_transfer_one_message(struct spi_master *master,
@@ -663,10 +654,6 @@ static int dspi_transfer_one_message(struct spi_master *master,
 	struct spi_transfer *transfer;
 	int status = 0;
 	enum dspi_trans_mode trans_mode;
-	u32 spi_tcr;
-
-	regmap_read(dspi->regmap, SPI_TCR, &spi_tcr);
-	dspi->spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr);
 
 	message->actual_length = 0;
 
@@ -674,32 +661,51 @@ static int dspi_transfer_one_message(struct spi_master *master,
 		dspi->cur_transfer = transfer;
 		dspi->cur_msg = message;
 		dspi->cur_chip = spi_get_ctldata(spi);
-		dspi->cs = spi->chip_select;
-		dspi->cs_change = 0;
+		/* Prepare command word for CMD FIFO */
+		dspi->tx_cmd = SPI_PUSHR_CMD_CTAS(0) |
+			SPI_PUSHR_CMD_PCS(spi->chip_select);
 		if (list_is_last(&dspi->cur_transfer->transfer_list,
-				 &dspi->cur_msg->transfers) || transfer->cs_change)
-			dspi->cs_change = 1;
+				 &dspi->cur_msg->transfers)) {
+			/* Leave PCS activated after last transfer when
+			 * cs_change is set.
+			 */
+			if (transfer->cs_change)
+				dspi->tx_cmd |= SPI_PUSHR_CMD_CONT;
+		} else {
+			/* Keep PCS active between transfers in same message
+			 * when cs_change is not set, and de-activate PCS
+			 * between transfers in the same message when
+			 * cs_change is set.
+			 */
+			if (!transfer->cs_change)
+				dspi->tx_cmd |= SPI_PUSHR_CMD_CONT;
+		}
+
 		dspi->void_write_data = dspi->cur_chip->void_write_data;
 
-		dspi->dataflags = 0;
-		dspi->tx = (void *)transfer->tx_buf;
-		dspi->tx_end = dspi->tx + transfer->len;
+		dspi->tx = transfer->tx_buf;
 		dspi->rx = transfer->rx_buf;
 		dspi->rx_end = dspi->rx + transfer->len;
 		dspi->len = transfer->len;
+		/* Validated transfer specific frame size (defaults applied) */
+		dspi->bits_per_word = transfer->bits_per_word;
+		if (transfer->bits_per_word <= 8)
+			dspi->bytes_per_word = 1;
+		else if (transfer->bits_per_word <= 16)
+			dspi->bytes_per_word = 2;
+		else
+			dspi->bytes_per_word = 4;
 
-		if (!dspi->rx)
-			dspi->dataflags |= TRAN_STATE_RX_VOID;
-
-		if (!dspi->tx)
-			dspi->dataflags |= TRAN_STATE_TX_VOID;
-
-		regmap_write(dspi->regmap, SPI_MCR, dspi->cur_chip->mcr_val);
 		regmap_update_bits(dspi->regmap, SPI_MCR,
-				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
-				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
+				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
+				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
 		regmap_write(dspi->regmap, SPI_CTAR(0),
-				dspi->cur_chip->ctar_val);
+			     dspi->cur_chip->ctar_val |
+			     SPI_FRAME_BITS(transfer->bits_per_word));
+		if (dspi->devtype_data->xspi_mode)
+			regmap_write(dspi->regmap, SPI_CTARE(0),
+				     SPI_FRAME_EBITS(transfer->bits_per_word)
+				     | SPI_CTARE_DTCP(1));
 
 		trans_mode = dspi->devtype_data->trans_mode;
 		switch (trans_mode) {
@@ -750,16 +756,9 @@ static int dspi_setup(struct spi_device *spi)
 	struct fsl_dspi_platform_data *pdata;
 	u32 cs_sck_delay = 0, sck_cs_delay = 0;
 	unsigned char br = 0, pbr = 0, pcssck = 0, cssck = 0;
-	unsigned char pasc = 0, asc = 0, fmsz = 0;
+	unsigned char pasc = 0, asc = 0;
 	unsigned long clkrate;
 
-	if ((spi->bits_per_word >= 4) && (spi->bits_per_word <= 16)) {
-		fmsz = spi->bits_per_word - 1;
-	} else {
-		pr_err("Invalid wordsize\n");
-		return -ENODEV;
-	}
-
 	/* Only alloc on first setup */
 	chip = spi_get_ctldata(spi);
 	if (chip == NULL) {
@@ -781,9 +780,6 @@ static int dspi_setup(struct spi_device *spi)
 		sck_cs_delay = pdata->sck_cs_delay;
 	}
 
-	chip->mcr_val = SPI_MCR_MASTER | SPI_MCR_PCSIS |
-		SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF;
-
 	chip->void_write_data = 0;
 
 	clkrate = clk_get_rate(dspi->clk);
@@ -795,8 +791,7 @@ static int dspi_setup(struct spi_device *spi)
 	/* Set After SCK delay scale values */
 	ns_delay_scale(&pasc, &asc, sck_cs_delay, clkrate);
 
-	chip->ctar_val =  SPI_CTAR_FMSZ(fmsz)
-		| SPI_CTAR_CPOL(spi->mode & SPI_CPOL ? 1 : 0)
+	chip->ctar_val = SPI_CTAR_CPOL(spi->mode & SPI_CPOL ? 1 : 0)
 		| SPI_CTAR_CPHA(spi->mode & SPI_CPHA ? 1 : 0)
 		| SPI_CTAR_LSBFE(spi->mode & SPI_LSB_FIRST ? 1 : 0)
 		| SPI_CTAR_PCSSCK(pcssck)
@@ -827,36 +822,20 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 	struct spi_message *msg = dspi->cur_msg;
 	enum dspi_trans_mode trans_mode;
 	u32 spi_sr, spi_tcr;
-	u32 spi_tcnt, tcnt_diff;
-	int tx_word;
+	u16 spi_tcnt;
 
 	regmap_read(dspi->regmap, SPI_SR, &spi_sr);
 	regmap_write(dspi->regmap, SPI_SR, spi_sr);
 
 
 	if (spi_sr & (SPI_SR_EOQF | SPI_SR_TCFQF)) {
-		tx_word = is_double_byte_mode(dspi);
-
+		/* Get transfer counter (in number of SPI transfers). It was
+		 * reset to 0 when transfer(s) were started.
+		 */
 		regmap_read(dspi->regmap, SPI_TCR, &spi_tcr);
 		spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr);
-		/*
-		 * The width of SPI Transfer Counter in SPI_TCR is 16bits,
-		 * so the max couner is 65535. When the counter reach 65535,
-		 * it will wrap around, counter reset to zero.
-		 * spi_tcnt my be less than dspi->spi_tcnt, it means the
-		 * counter already wrapped around.
-		 * SPI Transfer Counter is a counter of transmitted frames.
-		 * The size of frame maybe two bytes.
-		 */
-		tcnt_diff = ((spi_tcnt + SPI_TCR_TCNT_MAX) - dspi->spi_tcnt)
-			% SPI_TCR_TCNT_MAX;
-		tcnt_diff *= (tx_word + 1);
-		if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM)
-			tcnt_diff--;
-
-		msg->actual_length += tcnt_diff;
-
-		dspi->spi_tcnt = spi_tcnt;
+		/* Update total number of bytes that were transferred */
+		msg->actual_length += spi_tcnt * dspi->bytes_per_word;
 
 		trans_mode = dspi->devtype_data->trans_mode;
 		switch (trans_mode) {
@@ -873,14 +852,6 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 		}
 
 		if (!dspi->len) {
-			if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM) {
-				regmap_update_bits(dspi->regmap,
-						   SPI_CTAR(0),
-						   SPI_FRAME_BITS_MASK,
-						   SPI_FRAME_BITS(16));
-				dspi->dataflags &= ~TRAN_STATE_WORD_ODD_NUM;
-			}
-
 			dspi->waitflags = 1;
 			wake_up_interruptible(&dspi->waitq);
 		} else {
@@ -943,16 +914,62 @@ static int dspi_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(dspi_pm, dspi_suspend, dspi_resume);
 
+static const struct regmap_range dspi_volatile_ranges[] = {
+	regmap_reg_range(SPI_MCR, SPI_TCR),
+	regmap_reg_range(SPI_SR, SPI_SR),
+	regmap_reg_range(SPI_PUSHR, SPI_RXFR3),
+};
+
+static const struct regmap_access_table dspi_volatile_table = {
+	.yes_ranges     = dspi_volatile_ranges,
+	.n_yes_ranges   = ARRAY_SIZE(dspi_volatile_ranges),
+};
+
 static const struct regmap_config dspi_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
 	.reg_stride = 4,
 	.max_register = 0x88,
+	.volatile_table = &dspi_volatile_table,
+};
+
+static const struct regmap_range dspi_xspi_volatile_ranges[] = {
+	regmap_reg_range(SPI_MCR, SPI_TCR),
+	regmap_reg_range(SPI_SR, SPI_SR),
+	regmap_reg_range(SPI_PUSHR, SPI_RXFR3),
+	regmap_reg_range(SPI_SREX, SPI_SREX),
+};
+
+static const struct regmap_access_table dspi_xspi_volatile_table = {
+	.yes_ranges     = dspi_xspi_volatile_ranges,
+	.n_yes_ranges   = ARRAY_SIZE(dspi_xspi_volatile_ranges),
+};
+
+static const struct regmap_config dspi_xspi_regmap_config[] = {
+	{
+		.reg_bits = 32,
+		.val_bits = 32,
+		.reg_stride = 4,
+		.max_register = 0x13c,
+		.volatile_table = &dspi_xspi_volatile_table,
+	},
+	{
+		.name = "pushr",
+		.reg_bits = 16,
+		.val_bits = 16,
+		.reg_stride = 2,
+		.max_register = 0x2,
+	},
 };
 
 static void dspi_init(struct fsl_dspi *dspi)
 {
+	regmap_write(dspi->regmap, SPI_MCR, SPI_MCR_MASTER | SPI_MCR_PCSIS |
+		     (dspi->devtype_data->xspi_mode ? SPI_MCR_XSPI : 0));
 	regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
+	if (dspi->devtype_data->xspi_mode)
+		regmap_write(dspi->regmap, SPI_CTARE(0),
+			     SPI_CTARE_FMSZE(0) | SPI_CTARE_DTCP(1));
 }
 
 static int dspi_probe(struct platform_device *pdev)
@@ -961,6 +978,7 @@ static int dspi_probe(struct platform_device *pdev)
 	struct spi_master *master;
 	struct fsl_dspi *dspi;
 	struct resource *res;
+	const struct regmap_config *regmap_config;
 	void __iomem *base;
 	struct fsl_dspi_platform_data *pdata;
 	int ret = 0, cs_num, bus_num;
@@ -980,8 +998,6 @@ static int dspi_probe(struct platform_device *pdev)
 
 	master->cleanup = dspi_cleanup;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
-	master->bits_per_word_mask = SPI_BPW_MASK(4) | SPI_BPW_MASK(8) |
-					SPI_BPW_MASK(16);
 
 	pdata = dev_get_platdata(&pdev->dev);
 	if (pdata) {
@@ -1013,6 +1029,11 @@ static int dspi_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (dspi->devtype_data->xspi_mode)
+		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
+	else
+		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base)) {
@@ -1020,8 +1041,11 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_master_put;
 	}
 
-	dspi->regmap = devm_regmap_init_mmio_clk(&pdev->dev, NULL, base,
-						&dspi_regmap_config);
+	if (dspi->devtype_data->xspi_mode)
+		regmap_config = &dspi_xspi_regmap_config[0];
+	else
+		regmap_config = &dspi_regmap_config;
+	dspi->regmap = devm_regmap_init_mmio(&pdev->dev, base, regmap_config);
 	if (IS_ERR(dspi->regmap)) {
 		dev_err(&pdev->dev, "failed to init regmap: %ld\n",
 				PTR_ERR(dspi->regmap));
@@ -1029,30 +1053,43 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_master_put;
 	}
 
+	if (dspi->devtype_data->xspi_mode) {
+		dspi->regmap_pushr = devm_regmap_init_mmio(
+			&pdev->dev, base + SPI_PUSHR,
+			&dspi_xspi_regmap_config[1]);
+		if (IS_ERR(dspi->regmap_pushr)) {
+			dev_err(&pdev->dev,
+				"failed to init pushr regmap: %ld\n",
+				PTR_ERR(dspi->regmap_pushr));
+			ret = PTR_ERR(dspi->regmap_pushr);
+			goto out_master_put;
+		}
+	}
+
+	dspi->clk = devm_clk_get(&pdev->dev, "dspi");
+	if (IS_ERR(dspi->clk)) {
+		ret = PTR_ERR(dspi->clk);
+		dev_err(&pdev->dev, "unable to get clock\n");
+		goto out_master_put;
+	}
+	ret = clk_prepare_enable(dspi->clk);
+	if (ret)
+		goto out_master_put;
+
 	dspi_init(dspi);
 	dspi->irq = platform_get_irq(pdev, 0);
 	if (dspi->irq < 0) {
 		dev_err(&pdev->dev, "can't get platform irq\n");
 		ret = dspi->irq;
-		goto out_master_put;
+		goto out_clk_put;
 	}
 
 	ret = devm_request_irq(&pdev->dev, dspi->irq, dspi_interrupt, 0,
 			pdev->name, dspi);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Unable to attach DSPI interrupt\n");
-		goto out_master_put;
-	}
-
-	dspi->clk = devm_clk_get(&pdev->dev, "dspi");
-	if (IS_ERR(dspi->clk)) {
-		ret = PTR_ERR(dspi->clk);
-		dev_err(&pdev->dev, "unable to get clock\n");
-		goto out_master_put;
+		goto out_clk_put;
 	}
-	ret = clk_prepare_enable(dspi->clk);
-	if (ret)
-		goto out_master_put;
 
 	if (dspi->devtype_data->trans_mode == DSPI_DMA_MODE) {
 		ret = dspi_request_dma(dspi, res->start);
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index 1d332e23f6ed..1e8ff6256079 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -547,8 +547,11 @@ static void fsl_espi_cpu_irq(struct fsl_espi *espi, u32 events)
 		dev_err(espi->dev,
 			"Transfer done but SPIE_DON isn't set!\n");
 
-	if (SPIE_RXCNT(events) || SPIE_TXCNT(events) != FSL_ESPI_FIFO_SIZE)
+	if (SPIE_RXCNT(events) || SPIE_TXCNT(events) != FSL_ESPI_FIFO_SIZE) {
 		dev_err(espi->dev, "Transfer done but rx/tx fifo's aren't empty!\n");
+		dev_err(espi->dev, "SPIE_RXCNT = %d, SPIE_TXCNT = %d\n",
+			SPIE_RXCNT(events), SPIE_TXCNT(events));
+	}
 
 	complete(&espi->done);
 }
diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c
index 6ae92d4dca19..0626e6e3ea0c 100644
--- a/drivers/spi/spi-gpio.c
+++ b/drivers/spi/spi-gpio.c
@@ -121,7 +121,10 @@ static inline int getmiso(const struct spi_device *spi)
 {
 	struct spi_gpio *spi_gpio = spi_to_spi_gpio(spi);
 
-	return !!gpiod_get_value_cansleep(spi_gpio->miso);
+	if (spi->mode & SPI_3WIRE)
+		return !!gpiod_get_value_cansleep(spi_gpio->mosi);
+	else
+		return !!gpiod_get_value_cansleep(spi_gpio->miso);
 }
 
 /*
@@ -149,27 +152,27 @@ static inline int getmiso(const struct spi_device *spi)
  */
 
 static u32 spi_gpio_txrx_word_mode0(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_txrx_word_mode1(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_txrx_word_mode2(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits);
 }
 
 static u32 spi_gpio_txrx_word_mode3(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits);
 }
 
 /*
@@ -183,30 +186,30 @@ static u32 spi_gpio_txrx_word_mode3(struct spi_device *spi,
  */
 
 static u32 spi_gpio_spec_txrx_word_mode0(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_spec_txrx_word_mode1(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_spec_txrx_word_mode2(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits);
 }
 
 static u32 spi_gpio_spec_txrx_word_mode3(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits);
 }
 
@@ -250,6 +253,16 @@ static int spi_gpio_setup(struct spi_device *spi)
 	return status;
 }
 
+static int spi_gpio_set_direction(struct spi_device *spi, bool output)
+{
+	struct spi_gpio *spi_gpio = spi_to_spi_gpio(spi);
+
+	if (output)
+		return gpiod_direction_output(spi_gpio->mosi, 1);
+	else
+		return gpiod_direction_input(spi_gpio->mosi);
+}
+
 static void spi_gpio_cleanup(struct spi_device *spi)
 {
 	spi_bitbang_cleanup(spi);
@@ -395,6 +408,7 @@ static int spi_gpio_probe(struct platform_device *pdev)
 		return status;
 
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
+	master->mode_bits = SPI_3WIRE | SPI_CPHA | SPI_CPOL;
 	master->flags = master_flags;
 	master->bus_num = pdev->id;
 	/* The master needs to think there is a chipselect even if not connected */
@@ -407,6 +421,7 @@ static int spi_gpio_probe(struct platform_device *pdev)
 
 	spi_gpio->bitbang.master = master;
 	spi_gpio->bitbang.chipselect = spi_gpio_chipselect;
+	spi_gpio->bitbang.set_line_direction = spi_gpio_set_direction;
 
 	if ((master_flags & (SPI_MASTER_NO_TX | SPI_MASTER_NO_RX)) == 0) {
 		spi_gpio->bitbang.txrx_word[SPI_MODE_0] = spi_gpio_txrx_word_mode0;
diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c
index 7a37090dabbe..e6eb979f1b8a 100644
--- a/drivers/spi/spi-img-spfi.c
+++ b/drivers/spi/spi-img-spfi.c
@@ -419,6 +419,9 @@ static int img_spfi_prepare(struct spi_master *master, struct spi_message *msg)
 	u32 val;
 
 	val = spfi_readl(spfi, SPFI_PORT_STATE);
+	val &= ~(SPFI_PORT_STATE_DEV_SEL_MASK <<
+		 SPFI_PORT_STATE_DEV_SEL_SHIFT);
+	val |= msg->spi->chip_select << SPFI_PORT_STATE_DEV_SEL_SHIFT;
 	if (msg->spi->mode & SPI_CPHA)
 		val |= SPFI_PORT_STATE_CK_PHASE(msg->spi->chip_select);
 	else
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index d3b21faf6b1f..08dd3a31a3e5 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -94,8 +94,7 @@ struct spi_imx_data {
 	void *rx_buf;
 	const void *tx_buf;
 	unsigned int txfifo; /* number of words pushed in tx FIFO */
-	unsigned int dynamic_burst, read_u32;
-	unsigned int word_mask;
+	unsigned int dynamic_burst;
 
 	/* Slave mode */
 	bool slave_mode;
@@ -140,6 +139,8 @@ static void spi_imx_buf_rx_##type(struct spi_imx_data *spi_imx)		\
 		*(type *)spi_imx->rx_buf = val;				\
 		spi_imx->rx_buf += sizeof(type);			\
 	}								\
+									\
+	spi_imx->remainder -= sizeof(type);				\
 }
 
 #define MXC_SPI_BUF_TX(type)						\
@@ -203,7 +204,12 @@ out:
 
 static int spi_imx_bytes_per_word(const int bits_per_word)
 {
-	return DIV_ROUND_UP(bits_per_word, BITS_PER_BYTE);
+	if (bits_per_word <= 8)
+		return 1;
+	else if (bits_per_word <= 16)
+		return 2;
+	else
+		return 4;
 }
 
 static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
@@ -220,17 +226,11 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 
 	bytes_per_word = spi_imx_bytes_per_word(transfer->bits_per_word);
 
-	if (bytes_per_word != 1 && bytes_per_word != 2 && bytes_per_word != 4)
-		return false;
-
 	for (i = spi_imx->devtype_data->fifo_size / 2; i > 0; i--) {
 		if (!(transfer->len % (i * bytes_per_word)))
 			break;
 	}
 
-	if (i == 0)
-		return false;
-
 	spi_imx->wml = i;
 	spi_imx->dynamic_burst = 0;
 
@@ -291,26 +291,39 @@ static void spi_imx_buf_rx_swap_u32(struct spi_imx_data *spi_imx)
 		else if (bytes_per_word == 2)
 			val = (val << 16) | (val >> 16);
 #endif
-		val &= spi_imx->word_mask;
 		*(u32 *)spi_imx->rx_buf = val;
 		spi_imx->rx_buf += sizeof(u32);
 	}
+
+	spi_imx->remainder -= sizeof(u32);
 }
 
 static void spi_imx_buf_rx_swap(struct spi_imx_data *spi_imx)
 {
-	unsigned int bytes_per_word;
+	int unaligned;
+	u32 val;
 
-	bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word);
-	if (spi_imx->read_u32) {
+	unaligned = spi_imx->remainder % 4;
+
+	if (!unaligned) {
 		spi_imx_buf_rx_swap_u32(spi_imx);
 		return;
 	}
 
-	if (bytes_per_word == 1)
-		spi_imx_buf_rx_u8(spi_imx);
-	else if (bytes_per_word == 2)
+	if (spi_imx_bytes_per_word(spi_imx->bits_per_word) == 2) {
 		spi_imx_buf_rx_u16(spi_imx);
+		return;
+	}
+
+	val = readl(spi_imx->base + MXC_CSPIRXDATA);
+
+	while (unaligned--) {
+		if (spi_imx->rx_buf) {
+			*(u8 *)spi_imx->rx_buf = (val >> (8 * unaligned)) & 0xff;
+			spi_imx->rx_buf++;
+		}
+		spi_imx->remainder--;
+	}
 }
 
 static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx)
@@ -322,7 +335,6 @@ static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx)
 
 	if (spi_imx->tx_buf) {
 		val = *(u32 *)spi_imx->tx_buf;
-		val &= spi_imx->word_mask;
 		spi_imx->tx_buf += sizeof(u32);
 	}
 
@@ -340,40 +352,30 @@ static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx)
 
 static void spi_imx_buf_tx_swap(struct spi_imx_data *spi_imx)
 {
-	u32 ctrl, val;
-	unsigned int bytes_per_word;
+	int unaligned;
+	u32 val = 0;
 
-	if (spi_imx->count == spi_imx->remainder) {
-		ctrl = readl(spi_imx->base + MX51_ECSPI_CTRL);
-		ctrl &= ~MX51_ECSPI_CTRL_BL_MASK;
-		if (spi_imx->count > MX51_ECSPI_CTRL_MAX_BURST) {
-			spi_imx->remainder = spi_imx->count %
-					     MX51_ECSPI_CTRL_MAX_BURST;
-			val = MX51_ECSPI_CTRL_MAX_BURST * 8 - 1;
-		} else if (spi_imx->count >= sizeof(u32)) {
-			spi_imx->remainder = spi_imx->count % sizeof(u32);
-			val = (spi_imx->count - spi_imx->remainder) * 8 - 1;
-		} else {
-			spi_imx->remainder = 0;
-			val = spi_imx->bits_per_word - 1;
-			spi_imx->read_u32 = 0;
-		}
+	unaligned = spi_imx->count % 4;
 
-		ctrl |= (val << MX51_ECSPI_CTRL_BL_OFFSET);
-		writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
+	if (!unaligned) {
+		spi_imx_buf_tx_swap_u32(spi_imx);
+		return;
 	}
 
-	if (spi_imx->count >= sizeof(u32)) {
-		spi_imx_buf_tx_swap_u32(spi_imx);
+	if (spi_imx_bytes_per_word(spi_imx->bits_per_word) == 2) {
+		spi_imx_buf_tx_u16(spi_imx);
 		return;
 	}
 
-	bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word);
+	while (unaligned--) {
+		if (spi_imx->tx_buf) {
+			val |= *(u8 *)spi_imx->tx_buf << (8 * unaligned);
+			spi_imx->tx_buf++;
+		}
+		spi_imx->count--;
+	}
 
-	if (bytes_per_word == 1)
-		spi_imx_buf_tx_u8(spi_imx);
-	else if (bytes_per_word == 2)
-		spi_imx_buf_tx_u16(spi_imx);
+	writel(val, spi_imx->base + MXC_CSPITXDATA);
 }
 
 static void mx53_ecspi_rx_slave(struct spi_imx_data *spi_imx)
@@ -392,6 +394,8 @@ static void mx53_ecspi_rx_slave(struct spi_imx_data *spi_imx)
 		spi_imx->rx_buf += n_bytes;
 		spi_imx->slave_burst -= n_bytes;
 	}
+
+	spi_imx->remainder -= sizeof(u32);
 }
 
 static void mx53_ecspi_tx_slave(struct spi_imx_data *spi_imx)
@@ -1001,12 +1005,52 @@ static void spi_imx_chipselect(struct spi_device *spi, int is_active)
 	gpio_set_value(spi->cs_gpio, dev_is_lowactive ^ active);
 }
 
+static void spi_imx_set_burst_len(struct spi_imx_data *spi_imx, int n_bits)
+{
+	u32 ctrl;
+
+	ctrl = readl(spi_imx->base + MX51_ECSPI_CTRL);
+	ctrl &= ~MX51_ECSPI_CTRL_BL_MASK;
+	ctrl |= ((n_bits - 1) << MX51_ECSPI_CTRL_BL_OFFSET);
+	writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
+}
+
 static void spi_imx_push(struct spi_imx_data *spi_imx)
 {
+	unsigned int burst_len, fifo_words;
+
+	if (spi_imx->dynamic_burst)
+		fifo_words = 4;
+	else
+		fifo_words = spi_imx_bytes_per_word(spi_imx->bits_per_word);
+	/*
+	 * Reload the FIFO when the remaining bytes to be transferred in the
+	 * current burst is 0. This only applies when bits_per_word is a
+	 * multiple of 8.
+	 */
+	if (!spi_imx->remainder) {
+		if (spi_imx->dynamic_burst) {
+
+			/* We need to deal unaligned data first */
+			burst_len = spi_imx->count % MX51_ECSPI_CTRL_MAX_BURST;
+
+			if (!burst_len)
+				burst_len = MX51_ECSPI_CTRL_MAX_BURST;
+
+			spi_imx_set_burst_len(spi_imx, burst_len * 8);
+
+			spi_imx->remainder = burst_len;
+		} else {
+			spi_imx->remainder = fifo_words;
+		}
+	}
+
 	while (spi_imx->txfifo < spi_imx->devtype_data->fifo_size) {
 		if (!spi_imx->count)
 			break;
-		if (spi_imx->txfifo && (spi_imx->count == spi_imx->remainder))
+		if (spi_imx->dynamic_burst &&
+		    spi_imx->txfifo >=  DIV_ROUND_UP(spi_imx->remainder,
+						     fifo_words))
 			break;
 		spi_imx->tx(spi_imx);
 		spi_imx->txfifo++;
@@ -1102,27 +1146,20 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 	spi_imx->bits_per_word = t->bits_per_word;
 	spi_imx->speed_hz  = t->speed_hz;
 
-	/* Initialize the functions for transfer */
-	if (spi_imx->devtype_data->dynamic_burst && !spi_imx->slave_mode) {
-		u32 mask;
-
-		spi_imx->dynamic_burst = 0;
-		spi_imx->remainder = 0;
-		spi_imx->read_u32  = 1;
+	/*
+	 * Initialize the functions for transfer. To transfer non byte-aligned
+	 * words, we have to use multiple word-size bursts, we can't use
+	 * dynamic_burst in that case.
+	 */
+	if (spi_imx->devtype_data->dynamic_burst && !spi_imx->slave_mode &&
+	    (spi_imx->bits_per_word == 8 ||
+	    spi_imx->bits_per_word == 16 ||
+	    spi_imx->bits_per_word == 32)) {
 
-		mask = (1 << spi_imx->bits_per_word) - 1;
 		spi_imx->rx = spi_imx_buf_rx_swap;
 		spi_imx->tx = spi_imx_buf_tx_swap;
 		spi_imx->dynamic_burst = 1;
-		spi_imx->remainder = t->len;
-
-		if (spi_imx->bits_per_word <= 8)
-			spi_imx->word_mask = mask << 24 | mask << 16
-					     | mask << 8 | mask;
-		else if (spi_imx->bits_per_word <= 16)
-			spi_imx->word_mask = mask << 16 | mask;
-		else
-			spi_imx->word_mask = mask;
+
 	} else {
 		if (spi_imx->bits_per_word <= 8) {
 			spi_imx->rx = spi_imx_buf_rx_u8;
@@ -1134,6 +1171,7 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 			spi_imx->rx = spi_imx_buf_rx_u32;
 			spi_imx->tx = spi_imx_buf_tx_u32;
 		}
+		spi_imx->dynamic_burst = 0;
 	}
 
 	if (spi_imx_can_dma(spi_imx->bitbang.master, spi, t))
@@ -1317,6 +1355,7 @@ static int spi_imx_pio_transfer(struct spi_device *spi,
 	spi_imx->rx_buf = transfer->rx_buf;
 	spi_imx->count = transfer->len;
 	spi_imx->txfifo = 0;
+	spi_imx->remainder = 0;
 
 	reinit_completion(&spi_imx->xfer_done);
 
@@ -1354,6 +1393,7 @@ static int spi_imx_pio_transfer_slave(struct spi_device *spi,
 	spi_imx->rx_buf = transfer->rx_buf;
 	spi_imx->count = transfer->len;
 	spi_imx->txfifo = 0;
+	spi_imx->remainder = 0;
 
 	reinit_completion(&spi_imx->xfer_done);
 	spi_imx->slave_aborted = false;
diff --git a/drivers/spi/spi-lm70llp.c b/drivers/spi/spi-lm70llp.c
index 61ee0f4269ae..4549efd792da 100644
--- a/drivers/spi/spi-lm70llp.c
+++ b/drivers/spi/spi-lm70llp.c
@@ -188,9 +188,10 @@ static void lm70_chipselect(struct spi_device *spi, int value)
 /*
  * Our actual bitbanger routine.
  */
-static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits)
+static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits,
+		     unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static void spi_lm70llp_attach(struct parport *p)
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 990770dfa5cf..e43842c7a31a 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -311,6 +311,24 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 EXPORT_SYMBOL_GPL(spi_mem_exec_op);
 
 /**
+ * spi_mem_get_name() - Return the SPI mem device name to be used by the
+ *			upper layer if necessary
+ * @mem: the SPI memory
+ *
+ * This function allows SPI mem users to retrieve the SPI mem device name.
+ * It is useful if the upper layer needs to expose a custom name for
+ * compatibility reasons.
+ *
+ * Return: a string containing the name of the memory device to be used
+ *	   by the SPI mem user
+ */
+const char *spi_mem_get_name(struct spi_mem *mem)
+{
+	return mem->name;
+}
+EXPORT_SYMBOL_GPL(spi_mem_get_name);
+
+/**
  * spi_mem_adjust_op_size() - Adjust the data size of a SPI mem operation to
  *			      match controller limitations
  * @mem: the SPI memory
@@ -344,6 +362,7 @@ static inline struct spi_mem_driver *to_spi_mem_drv(struct device_driver *drv)
 static int spi_mem_probe(struct spi_device *spi)
 {
 	struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
+	struct spi_controller *ctlr = spi->controller;
 	struct spi_mem *mem;
 
 	mem = devm_kzalloc(&spi->dev, sizeof(*mem), GFP_KERNEL);
@@ -351,6 +370,15 @@ static int spi_mem_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	mem->spi = spi;
+
+	if (ctlr->mem_ops && ctlr->mem_ops->get_name)
+		mem->name = ctlr->mem_ops->get_name(mem);
+	else
+		mem->name = dev_name(&spi->dev);
+
+	if (IS_ERR_OR_NULL(mem->name))
+		return PTR_ERR(mem->name);
+
 	spi_set_drvdata(spi, mem);
 
 	return memdrv->probe(mem);
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 6c628a54e946..508c61c669e7 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -398,11 +398,9 @@ static void omap2_mcspi_tx_dma(struct spi_device *spi,
 {
 	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_dma  *mcspi_dma;
-	unsigned int		count;
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-	count = xfer->len;
 
 	if (mcspi_dma->dma_tx) {
 		struct dma_async_tx_descriptor *tx;
@@ -582,7 +580,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 	struct omap2_mcspi_cs	*cs = spi->controller_state;
 	struct omap2_mcspi_dma  *mcspi_dma;
 	unsigned int		count;
-	u32			l;
 	u8			*rx;
 	const u8		*tx;
 	struct dma_slave_config	cfg;
@@ -595,8 +592,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-	l = mcspi_cached_chconf0(spi);
-
 
 	if (cs->word_len <= 8) {
 		width = DMA_SLAVE_BUSWIDTH_1_BYTE;
@@ -676,7 +671,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 static unsigned
 omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer)
 {
-	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_cs	*cs = spi->controller_state;
 	unsigned int		count, c;
 	u32			l;
@@ -686,7 +680,6 @@ omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer)
 	void __iomem		*chstat_reg;
 	int			word_len;
 
-	mcspi = spi_master_get_devdata(spi->master);
 	count = xfer->len;
 	c = count;
 	word_len = cs->word_len;
@@ -883,13 +876,11 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi,
 {
 	struct omap2_mcspi_cs *cs = spi->controller_state;
 	struct omap2_mcspi *mcspi;
-	struct spi_master *spi_cntrl;
 	u32 l = 0, clkd = 0, div, extclk = 0, clkg = 0;
 	u8 word_len = spi->bits_per_word;
 	u32 speed_hz = spi->max_speed_hz;
 
 	mcspi = spi_master_get_devdata(spi->master);
-	spi_cntrl = mcspi->master;
 
 	if (t != NULL && t->bits_per_word)
 		word_len = t->bits_per_word;
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index d01a6adc726e..47ef6b1a2e76 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/of_gpio.h>
 #include <linux/clk.h>
 #include <linux/sizes.h>
 #include <linux/gpio.h>
@@ -681,9 +682,9 @@ static int orion_spi_probe(struct platform_device *pdev)
 		goto out_rel_axi_clk;
 	}
 
-	/* Scan all SPI devices of this controller for direct mapped devices */
 	for_each_available_child_of_node(pdev->dev.of_node, np) {
 		u32 cs;
+		int cs_gpio;
 
 		/* Get chip-select number from the "reg" property */
 		status = of_property_read_u32(np, "reg", &cs);
@@ -695,6 +696,44 @@ static int orion_spi_probe(struct platform_device *pdev)
 		}
 
 		/*
+		 * Initialize the CS GPIO:
+		 * - properly request the actual GPIO signal
+		 * - de-assert the logical signal so that all GPIO CS lines
+		 *   are inactive when probing for slaves
+		 * - find an unused physical CS which will be driven for any
+		 *   slave which uses a CS GPIO
+		 */
+		cs_gpio = of_get_named_gpio(pdev->dev.of_node, "cs-gpios", cs);
+		if (cs_gpio > 0) {
+			char *gpio_name;
+			int cs_flags;
+
+			if (spi->unused_hw_gpio == -1) {
+				dev_info(&pdev->dev,
+					"Selected unused HW CS#%d for any GPIO CSes\n",
+					cs);
+				spi->unused_hw_gpio = cs;
+			}
+
+			gpio_name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+					"%s-CS%d", dev_name(&pdev->dev), cs);
+			if (!gpio_name) {
+				status = -ENOMEM;
+				goto out_rel_axi_clk;
+			}
+
+			cs_flags = of_property_read_bool(np, "spi-cs-high") ?
+				GPIOF_OUT_INIT_LOW : GPIOF_OUT_INIT_HIGH;
+			status = devm_gpio_request_one(&pdev->dev, cs_gpio,
+					cs_flags, gpio_name);
+			if (status) {
+				dev_err(&pdev->dev,
+					"Can't request GPIO for CS %d\n", cs);
+				goto out_rel_axi_clk;
+			}
+		}
+
+		/*
 		 * Check if an address is configured for this SPI device. If
 		 * not, the MBus mapping via the 'ranges' property in the 'soc'
 		 * node is not configured and this device should not use the
@@ -740,44 +779,8 @@ static int orion_spi_probe(struct platform_device *pdev)
 	if (status < 0)
 		goto out_rel_pm;
 
-	if (master->cs_gpios) {
-		int i;
-		for (i = 0; i < master->num_chipselect; ++i) {
-			char *gpio_name;
-
-			if (!gpio_is_valid(master->cs_gpios[i])) {
-				continue;
-			}
-
-			gpio_name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-					"%s-CS%d", dev_name(&pdev->dev), i);
-			if (!gpio_name) {
-				status = -ENOMEM;
-				goto out_rel_master;
-			}
-
-			status = devm_gpio_request(&pdev->dev,
-					master->cs_gpios[i], gpio_name);
-			if (status) {
-				dev_err(&pdev->dev,
-					"Can't request GPIO for CS %d\n",
-					master->cs_gpios[i]);
-				goto out_rel_master;
-			}
-			if (spi->unused_hw_gpio == -1) {
-				dev_info(&pdev->dev,
-					"Selected unused HW CS#%d for any GPIO CSes\n",
-					i);
-				spi->unused_hw_gpio = i;
-			}
-		}
-	}
-
-
 	return status;
 
-out_rel_master:
-	spi_unregister_master(master);
 out_rel_pm:
 	pm_runtime_disable(&pdev->dev);
 out_rel_axi_clk:
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 0b2d60d30f69..14f4ea59caff 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1391,6 +1391,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	{ PCI_VDEVICE(INTEL, 0x31c2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x31c4), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x31c6), LPSS_BXT_SSP },
+	/* ICL-LP */
+	{ PCI_VDEVICE(INTEL, 0x34aa), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x34ab), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x34fb), LPSS_CNL_SSP },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP },
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 0e74cbf9929d..539d6d1a277a 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -49,6 +49,7 @@ struct sh_msiof_spi_priv {
 	struct platform_device *pdev;
 	struct sh_msiof_spi_info *info;
 	struct completion done;
+	struct completion done_txdma;
 	unsigned int tx_fifo_size;
 	unsigned int rx_fifo_size;
 	unsigned int min_div_pow;
@@ -649,19 +650,21 @@ static int sh_msiof_slave_abort(struct spi_master *master)
 
 	p->slave_aborted = true;
 	complete(&p->done);
+	complete(&p->done_txdma);
 	return 0;
 }
 
-static int sh_msiof_wait_for_completion(struct sh_msiof_spi_priv *p)
+static int sh_msiof_wait_for_completion(struct sh_msiof_spi_priv *p,
+					struct completion *x)
 {
 	if (spi_controller_is_slave(p->master)) {
-		if (wait_for_completion_interruptible(&p->done) ||
+		if (wait_for_completion_interruptible(x) ||
 		    p->slave_aborted) {
 			dev_dbg(&p->pdev->dev, "interrupted\n");
 			return -EINTR;
 		}
 	} else {
-		if (!wait_for_completion_timeout(&p->done, HZ)) {
+		if (!wait_for_completion_timeout(x, HZ)) {
 			dev_err(&p->pdev->dev, "timeout\n");
 			return -ETIMEDOUT;
 		}
@@ -711,7 +714,7 @@ static int sh_msiof_spi_txrx_once(struct sh_msiof_spi_priv *p,
 	}
 
 	/* wait for tx fifo to be emptied / rx fifo to be filled */
-	ret = sh_msiof_wait_for_completion(p);
+	ret = sh_msiof_wait_for_completion(p, &p->done);
 	if (ret)
 		goto stop_reset;
 
@@ -740,10 +743,7 @@ stop_ier:
 
 static void sh_msiof_dma_complete(void *arg)
 {
-	struct sh_msiof_spi_priv *p = arg;
-
-	sh_msiof_write(p, IER, 0);
-	complete(&p->done);
+	complete(arg);
 }
 
 static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
@@ -764,7 +764,7 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 			return -EAGAIN;
 
 		desc_rx->callback = sh_msiof_dma_complete;
-		desc_rx->callback_param = p;
+		desc_rx->callback_param = &p->done;
 		cookie = dmaengine_submit(desc_rx);
 		if (dma_submit_error(cookie))
 			return cookie;
@@ -782,13 +782,8 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 			goto no_dma_tx;
 		}
 
-		if (rx) {
-			/* No callback */
-			desc_tx->callback = NULL;
-		} else {
-			desc_tx->callback = sh_msiof_dma_complete;
-			desc_tx->callback_param = p;
-		}
+		desc_tx->callback = sh_msiof_dma_complete;
+		desc_tx->callback_param = &p->done_txdma;
 		cookie = dmaengine_submit(desc_tx);
 		if (dma_submit_error(cookie)) {
 			ret = cookie;
@@ -805,6 +800,8 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 	sh_msiof_write(p, IER, ier_bits);
 
 	reinit_completion(&p->done);
+	if (tx)
+		reinit_completion(&p->done_txdma);
 	p->slave_aborted = false;
 
 	/* Now start DMA */
@@ -819,17 +816,24 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 		goto stop_dma;
 	}
 
-	/* wait for tx/rx DMA completion */
-	ret = sh_msiof_wait_for_completion(p);
-	if (ret)
-		goto stop_reset;
+	if (tx) {
+		/* wait for tx DMA completion */
+		ret = sh_msiof_wait_for_completion(p, &p->done_txdma);
+		if (ret)
+			goto stop_reset;
+	}
 
-	if (!rx) {
-		reinit_completion(&p->done);
-		sh_msiof_write(p, IER, IER_TEOFE);
+	if (rx) {
+		/* wait for rx DMA completion */
+		ret = sh_msiof_wait_for_completion(p, &p->done);
+		if (ret)
+			goto stop_reset;
 
+		sh_msiof_write(p, IER, 0);
+	} else {
 		/* wait for tx fifo to be emptied */
-		ret = sh_msiof_wait_for_completion(p);
+		sh_msiof_write(p, IER, IER_TEOFE);
+		ret = sh_msiof_wait_for_completion(p, &p->done);
 		if (ret)
 			goto stop_reset;
 	}
@@ -1327,6 +1331,7 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	p->min_div_pow = chipdata->min_div_pow;
 
 	init_completion(&p->done);
+	init_completion(&p->done_txdma);
 
 	p->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(p->clk)) {
diff --git a/drivers/spi/spi-sh-sci.c b/drivers/spi/spi-sh-sci.c
index a9beeeed812c..393701cfca3c 100644
--- a/drivers/spi/spi-sh-sci.c
+++ b/drivers/spi/spi-sh-sci.c
@@ -80,27 +80,31 @@ static inline u32 getmiso(struct spi_device *dev)
 #include "spi-bitbang-txrx.h"
 
 static u32 sh_sci_spi_txrx_mode0(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 sh_sci_spi_txrx_mode1(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 sh_sci_spi_txrx_mode2(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits);
 }
 
 static u32 sh_sci_spi_txrx_mode3(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits);
 }
 
 static void sh_sci_spi_chipselect(struct spi_device *dev, int value)
diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c
new file mode 100644
index 000000000000..5a6137fe172d
--- /dev/null
+++ b/drivers/spi/spi-uniphier.c
@@ -0,0 +1,523 @@
+// SPDX-License-Identifier: GPL-2.0
+// spi-uniphier.c - Socionext UniPhier SPI controller driver
+// Copyright 2012      Panasonic Corporation
+// Copyright 2016-2018 Socionext Inc.
+
+#include <linux/kernel.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+
+#include <asm/unaligned.h>
+
+#define SSI_TIMEOUT_MS		2000
+#define SSI_MAX_CLK_DIVIDER	254
+#define SSI_MIN_CLK_DIVIDER	4
+
+struct uniphier_spi_priv {
+	void __iomem *base;
+	struct clk *clk;
+	struct spi_master *master;
+	struct completion xfer_done;
+
+	int error;
+	unsigned int tx_bytes;
+	unsigned int rx_bytes;
+	const u8 *tx_buf;
+	u8 *rx_buf;
+
+	bool is_save_param;
+	u8 bits_per_word;
+	u16 mode;
+	u32 speed_hz;
+};
+
+#define SSI_CTL			0x00
+#define   SSI_CTL_EN		BIT(0)
+
+#define SSI_CKS			0x04
+#define   SSI_CKS_CKRAT_MASK	GENMASK(7, 0)
+#define   SSI_CKS_CKPHS		BIT(14)
+#define   SSI_CKS_CKINIT	BIT(13)
+#define   SSI_CKS_CKDLY		BIT(12)
+
+#define SSI_TXWDS		0x08
+#define   SSI_TXWDS_WDLEN_MASK	GENMASK(13, 8)
+#define   SSI_TXWDS_TDTF_MASK	GENMASK(7, 6)
+#define   SSI_TXWDS_DTLEN_MASK	GENMASK(5, 0)
+
+#define SSI_RXWDS		0x0c
+#define   SSI_RXWDS_DTLEN_MASK	GENMASK(5, 0)
+
+#define SSI_FPS			0x10
+#define   SSI_FPS_FSPOL		BIT(15)
+#define   SSI_FPS_FSTRT		BIT(14)
+
+#define SSI_SR			0x14
+#define   SSI_SR_RNE		BIT(0)
+
+#define SSI_IE			0x18
+#define   SSI_IE_RCIE		BIT(3)
+#define   SSI_IE_RORIE		BIT(0)
+
+#define SSI_IS			0x1c
+#define   SSI_IS_RXRS		BIT(9)
+#define   SSI_IS_RCID		BIT(3)
+#define   SSI_IS_RORID		BIT(0)
+
+#define SSI_IC			0x1c
+#define   SSI_IC_TCIC		BIT(4)
+#define   SSI_IC_RCIC		BIT(3)
+#define   SSI_IC_RORIC		BIT(0)
+
+#define SSI_FC			0x20
+#define   SSI_FC_TXFFL		BIT(12)
+#define   SSI_FC_TXFTH_MASK	GENMASK(11, 8)
+#define   SSI_FC_RXFFL		BIT(4)
+#define   SSI_FC_RXFTH_MASK	GENMASK(3, 0)
+
+#define SSI_TXDR		0x24
+#define SSI_RXDR		0x24
+
+#define SSI_FIFO_DEPTH		8U
+
+static inline unsigned int bytes_per_word(unsigned int bits)
+{
+	return bits <= 8 ? 1 : (bits <= 16 ? 2 : 4);
+}
+
+static inline void uniphier_spi_irq_enable(struct spi_device *spi, u32 mask)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_IE);
+	val |= mask;
+	writel(val, priv->base + SSI_IE);
+}
+
+static inline void uniphier_spi_irq_disable(struct spi_device *spi, u32 mask)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_IE);
+	val &= ~mask;
+	writel(val, priv->base + SSI_IE);
+}
+
+static void uniphier_spi_set_mode(struct spi_device *spi)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val1, val2;
+
+	/*
+	 * clock setting
+	 * CKPHS    capture timing. 0:rising edge, 1:falling edge
+	 * CKINIT   clock initial level. 0:low, 1:high
+	 * CKDLY    clock delay. 0:no delay, 1:delay depending on FSTRT
+	 *          (FSTRT=0: 1 clock, FSTRT=1: 0.5 clock)
+	 *
+	 * frame setting
+	 * FSPOL    frame signal porarity. 0: low, 1: high
+	 * FSTRT    start frame timing
+	 *          0: rising edge of clock, 1: falling edge of clock
+	 */
+	switch (spi->mode & (SPI_CPOL | SPI_CPHA)) {
+	case SPI_MODE_0:
+		/* CKPHS=1, CKINIT=0, CKDLY=1, FSTRT=0 */
+		val1 = SSI_CKS_CKPHS | SSI_CKS_CKDLY;
+		val2 = 0;
+		break;
+	case SPI_MODE_1:
+		/* CKPHS=0, CKINIT=0, CKDLY=0, FSTRT=1 */
+		val1 = 0;
+		val2 = SSI_FPS_FSTRT;
+		break;
+	case SPI_MODE_2:
+		/* CKPHS=0, CKINIT=1, CKDLY=1, FSTRT=1 */
+		val1 = SSI_CKS_CKINIT | SSI_CKS_CKDLY;
+		val2 = SSI_FPS_FSTRT;
+		break;
+	case SPI_MODE_3:
+		/* CKPHS=1, CKINIT=1, CKDLY=0, FSTRT=0 */
+		val1 = SSI_CKS_CKPHS | SSI_CKS_CKINIT;
+		val2 = 0;
+		break;
+	}
+
+	if (!(spi->mode & SPI_CS_HIGH))
+		val2 |= SSI_FPS_FSPOL;
+
+	writel(val1, priv->base + SSI_CKS);
+	writel(val2, priv->base + SSI_FPS);
+
+	val1 = 0;
+	if (spi->mode & SPI_LSB_FIRST)
+		val1 |= FIELD_PREP(SSI_TXWDS_TDTF_MASK, 1);
+	writel(val1, priv->base + SSI_TXWDS);
+	writel(val1, priv->base + SSI_RXWDS);
+}
+
+static void uniphier_spi_set_transfer_size(struct spi_device *spi, int size)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_TXWDS);
+	val &= ~(SSI_TXWDS_WDLEN_MASK | SSI_TXWDS_DTLEN_MASK);
+	val |= FIELD_PREP(SSI_TXWDS_WDLEN_MASK, size);
+	val |= FIELD_PREP(SSI_TXWDS_DTLEN_MASK, size);
+	writel(val, priv->base + SSI_TXWDS);
+
+	val = readl(priv->base + SSI_RXWDS);
+	val &= ~SSI_RXWDS_DTLEN_MASK;
+	val |= FIELD_PREP(SSI_RXWDS_DTLEN_MASK, size);
+	writel(val, priv->base + SSI_RXWDS);
+}
+
+static void uniphier_spi_set_baudrate(struct spi_device *spi,
+				      unsigned int speed)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val, ckdiv;
+
+	/*
+	 * the supported rates are even numbers from 4 to 254. (4,6,8...254)
+	 * round up as we look for equal or less speed
+	 */
+	ckdiv = DIV_ROUND_UP(clk_get_rate(priv->clk), speed);
+	ckdiv = round_up(ckdiv, 2);
+
+	val = readl(priv->base + SSI_CKS);
+	val &= ~SSI_CKS_CKRAT_MASK;
+	val |= ckdiv & SSI_CKS_CKRAT_MASK;
+	writel(val, priv->base + SSI_CKS);
+}
+
+static void uniphier_spi_setup_transfer(struct spi_device *spi,
+				       struct spi_transfer *t)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	priv->error = 0;
+	priv->tx_buf = t->tx_buf;
+	priv->rx_buf = t->rx_buf;
+	priv->tx_bytes = priv->rx_bytes = t->len;
+
+	if (!priv->is_save_param || priv->mode != spi->mode) {
+		uniphier_spi_set_mode(spi);
+		priv->mode = spi->mode;
+	}
+
+	if (!priv->is_save_param || priv->bits_per_word != t->bits_per_word) {
+		uniphier_spi_set_transfer_size(spi, t->bits_per_word);
+		priv->bits_per_word = t->bits_per_word;
+	}
+
+	if (!priv->is_save_param || priv->speed_hz != t->speed_hz) {
+		uniphier_spi_set_baudrate(spi, t->speed_hz);
+		priv->speed_hz = t->speed_hz;
+	}
+
+	if (!priv->is_save_param)
+		priv->is_save_param = true;
+
+	/* reset FIFOs */
+	val = SSI_FC_TXFFL | SSI_FC_RXFFL;
+	writel(val, priv->base + SSI_FC);
+}
+
+static void uniphier_spi_send(struct uniphier_spi_priv *priv)
+{
+	int wsize;
+	u32 val = 0;
+
+	wsize = min(bytes_per_word(priv->bits_per_word), priv->tx_bytes);
+	priv->tx_bytes -= wsize;
+
+	if (priv->tx_buf) {
+		switch (wsize) {
+		case 1:
+			val = *priv->tx_buf;
+			break;
+		case 2:
+			val = get_unaligned_le16(priv->tx_buf);
+			break;
+		case 4:
+			val = get_unaligned_le32(priv->tx_buf);
+			break;
+		}
+
+		priv->tx_buf += wsize;
+	}
+
+	writel(val, priv->base + SSI_TXDR);
+}
+
+static void uniphier_spi_recv(struct uniphier_spi_priv *priv)
+{
+	int rsize;
+	u32 val;
+
+	rsize = min(bytes_per_word(priv->bits_per_word), priv->rx_bytes);
+	priv->rx_bytes -= rsize;
+
+	val = readl(priv->base + SSI_RXDR);
+
+	if (priv->rx_buf) {
+		switch (rsize) {
+		case 1:
+			*priv->rx_buf = val;
+			break;
+		case 2:
+			put_unaligned_le16(val, priv->rx_buf);
+			break;
+		case 4:
+			put_unaligned_le32(val, priv->rx_buf);
+			break;
+		}
+
+		priv->rx_buf += rsize;
+	}
+}
+
+static void uniphier_spi_fill_tx_fifo(struct uniphier_spi_priv *priv)
+{
+	unsigned int tx_count;
+	u32 val;
+
+	tx_count = DIV_ROUND_UP(priv->tx_bytes,
+				bytes_per_word(priv->bits_per_word));
+	tx_count = min(tx_count, SSI_FIFO_DEPTH);
+
+	/* set fifo threshold */
+	val = readl(priv->base + SSI_FC);
+	val &= ~(SSI_FC_TXFTH_MASK | SSI_FC_RXFTH_MASK);
+	val |= FIELD_PREP(SSI_FC_TXFTH_MASK, tx_count);
+	val |= FIELD_PREP(SSI_FC_RXFTH_MASK, tx_count);
+	writel(val, priv->base + SSI_FC);
+
+	while (tx_count--)
+		uniphier_spi_send(priv);
+}
+
+static void uniphier_spi_set_cs(struct spi_device *spi, bool enable)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_FPS);
+
+	if (enable)
+		val |= SSI_FPS_FSPOL;
+	else
+		val &= ~SSI_FPS_FSPOL;
+
+	writel(val, priv->base + SSI_FPS);
+}
+
+static int uniphier_spi_transfer_one(struct spi_master *master,
+				     struct spi_device *spi,
+				     struct spi_transfer *t)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	int status;
+
+	uniphier_spi_setup_transfer(spi, t);
+
+	reinit_completion(&priv->xfer_done);
+
+	uniphier_spi_fill_tx_fifo(priv);
+
+	uniphier_spi_irq_enable(spi, SSI_IE_RCIE | SSI_IE_RORIE);
+
+	status = wait_for_completion_timeout(&priv->xfer_done,
+					     msecs_to_jiffies(SSI_TIMEOUT_MS));
+
+	uniphier_spi_irq_disable(spi, SSI_IE_RCIE | SSI_IE_RORIE);
+
+	if (status < 0)
+		return status;
+
+	return priv->error;
+}
+
+static int uniphier_spi_prepare_transfer_hardware(struct spi_master *master)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+
+	writel(SSI_CTL_EN, priv->base + SSI_CTL);
+
+	return 0;
+}
+
+static int uniphier_spi_unprepare_transfer_hardware(struct spi_master *master)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+
+	writel(0, priv->base + SSI_CTL);
+
+	return 0;
+}
+
+static irqreturn_t uniphier_spi_handler(int irq, void *dev_id)
+{
+	struct uniphier_spi_priv *priv = dev_id;
+	u32 val, stat;
+
+	stat = readl(priv->base + SSI_IS);
+	val = SSI_IC_TCIC | SSI_IC_RCIC | SSI_IC_RORIC;
+	writel(val, priv->base + SSI_IC);
+
+	/* rx fifo overrun */
+	if (stat & SSI_IS_RORID) {
+		priv->error = -EIO;
+		goto done;
+	}
+
+	/* rx complete */
+	if ((stat & SSI_IS_RCID) && (stat & SSI_IS_RXRS)) {
+		while ((readl(priv->base + SSI_SR) & SSI_SR_RNE) &&
+				(priv->rx_bytes - priv->tx_bytes) > 0)
+			uniphier_spi_recv(priv);
+
+		if ((readl(priv->base + SSI_SR) & SSI_SR_RNE) ||
+				(priv->rx_bytes != priv->tx_bytes)) {
+			priv->error = -EIO;
+			goto done;
+		} else if (priv->rx_bytes == 0)
+			goto done;
+
+		/* next tx transfer */
+		uniphier_spi_fill_tx_fifo(priv);
+
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+
+done:
+	complete(&priv->xfer_done);
+	return IRQ_HANDLED;
+}
+
+static int uniphier_spi_probe(struct platform_device *pdev)
+{
+	struct uniphier_spi_priv *priv;
+	struct spi_master *master;
+	struct resource *res;
+	unsigned long clk_rate;
+	int irq;
+	int ret;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*priv));
+	if (!master)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, master);
+
+	priv = spi_master_get_devdata(master);
+	priv->master = master;
+	priv->is_save_param = false;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->base)) {
+		ret = PTR_ERR(priv->base);
+		goto out_master_put;
+	}
+
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		dev_err(&pdev->dev, "failed to get clock\n");
+		ret = PTR_ERR(priv->clk);
+		goto out_master_put;
+	}
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		goto out_master_put;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "failed to get IRQ\n");
+		ret = irq;
+		goto out_disable_clk;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, uniphier_spi_handler,
+			       0, "uniphier-spi", priv);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to request IRQ\n");
+		goto out_disable_clk;
+	}
+
+	init_completion(&priv->xfer_done);
+
+	clk_rate = clk_get_rate(priv->clk);
+
+	master->max_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MIN_CLK_DIVIDER);
+	master->min_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MAX_CLK_DIVIDER);
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST;
+	master->dev.of_node = pdev->dev.of_node;
+	master->bus_num = pdev->id;
+	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
+
+	master->set_cs = uniphier_spi_set_cs;
+	master->transfer_one = uniphier_spi_transfer_one;
+	master->prepare_transfer_hardware
+				= uniphier_spi_prepare_transfer_hardware;
+	master->unprepare_transfer_hardware
+				= uniphier_spi_unprepare_transfer_hardware;
+	master->num_chipselect = 1;
+
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret)
+		goto out_disable_clk;
+
+	return 0;
+
+out_disable_clk:
+	clk_disable_unprepare(priv->clk);
+
+out_master_put:
+	spi_master_put(master);
+	return ret;
+}
+
+static int uniphier_spi_remove(struct platform_device *pdev)
+{
+	struct uniphier_spi_priv *priv = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(priv->clk);
+
+	return 0;
+}
+
+static const struct of_device_id uniphier_spi_match[] = {
+	{ .compatible = "socionext,uniphier-scssi" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, uniphier_spi_match);
+
+static struct platform_driver uniphier_spi_driver = {
+	.probe = uniphier_spi_probe,
+	.remove = uniphier_spi_remove,
+	.driver = {
+		.name = "uniphier-spi",
+		.of_match_table = uniphier_spi_match,
+	},
+};
+module_platform_driver(uniphier_spi_driver);
+
+MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>");
+MODULE_AUTHOR("Keiji Hayashibara <hayashibara.keiji@socionext.com>");
+MODULE_DESCRIPTION("Socionext UniPhier SPI controller driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-xtensa-xtfpga.c b/drivers/spi/spi-xtensa-xtfpga.c
index be6155cba9de..8ce04f829a80 100644
--- a/drivers/spi/spi-xtensa-xtfpga.c
+++ b/drivers/spi/spi-xtensa-xtfpga.c
@@ -54,7 +54,7 @@ static inline void xtfpga_spi_wait_busy(struct xtfpga_spi *xspi)
 }
 
 static u32 xtfpga_spi_txrx_word(struct spi_device *spi, unsigned nsecs,
-				u32 v, u8 bits)
+				u32 v, u8 bits, unsigned flags)
 {
 	struct xtfpga_spi *xspi = spi_master_get_devdata(spi->master);
 
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index a1a0025b59e0..d5d33e12e952 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -402,6 +402,8 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 			fput(asma->file);
 			goto out;
 		}
+	} else {
+		vma_set_anonymous(vma);
 	}
 
 	if (vma->vm_file)
diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c
index e8c440329708..31db510018a9 100644
--- a/drivers/staging/android/ion/ion_heap.c
+++ b/drivers/staging/android/ion/ion_heap.c
@@ -30,7 +30,7 @@ void *ion_heap_map_kernel(struct ion_heap *heap,
 	struct page **tmp = pages;
 
 	if (!pages)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (buffer->flags & ION_FLAG_CACHED)
 		pgprot = PAGE_KERNEL;
diff --git a/drivers/staging/comedi/drivers/quatech_daqp_cs.c b/drivers/staging/comedi/drivers/quatech_daqp_cs.c
index ea194aa01a64..257b0daff01f 100644
--- a/drivers/staging/comedi/drivers/quatech_daqp_cs.c
+++ b/drivers/staging/comedi/drivers/quatech_daqp_cs.c
@@ -642,7 +642,7 @@ static int daqp_ao_insn_write(struct comedi_device *dev,
 	/* Make sure D/A update mode is direct update */
 	outb(0, dev->iobase + DAQP_AUX_REG);
 
-	for (i = 0; i > insn->n; i++) {
+	for (i = 0; i < insn->n; i++) {
 		unsigned int val = data[i];
 		int ret;
 
diff --git a/drivers/staging/ks7010/ks_hostif.c b/drivers/staging/ks7010/ks_hostif.c
index 0ecffab52ec2..abdaf7cf8162 100644
--- a/drivers/staging/ks7010/ks_hostif.c
+++ b/drivers/staging/ks7010/ks_hostif.c
@@ -1842,15 +1842,15 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv)
 	memset(set_address, 0, NIC_MAX_MCAST_LIST * ETH_ALEN);
 
 	if (dev->flags & IFF_PROMISC) {
-		hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER,
-					    MCAST_FILTER_PROMISC);
+		hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER,
+					   MCAST_FILTER_PROMISC);
 		goto spin_unlock;
 	}
 
 	if ((netdev_mc_count(dev) > NIC_MAX_MCAST_LIST) ||
 	    (dev->flags & IFF_ALLMULTI)) {
-		hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER,
-					    MCAST_FILTER_MCASTALL);
+		hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER,
+					   MCAST_FILTER_MCASTALL);
 		goto spin_unlock;
 	}
 
@@ -1866,8 +1866,8 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv)
 					       ETH_ALEN * mc_count);
 	} else {
 		priv->sme_i.sme_flag |= SME_MULTICAST;
-		hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER,
-					    MCAST_FILTER_MCAST);
+		hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER,
+					   MCAST_FILTER_MCAST);
 	}
 
 spin_unlock:
diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c
index a3a83424a926..16478fe9e3f8 100644
--- a/drivers/staging/media/omap4iss/iss_video.c
+++ b/drivers/staging/media/omap4iss/iss_video.c
@@ -11,7 +11,6 @@
  * (at your option) any later version.
  */
 
-#include <asm/cacheflush.h>
 #include <linux/clk.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
@@ -24,6 +23,8 @@
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-mc.h>
 
+#include <asm/cacheflush.h>
+
 #include "iss_video.h"
 #include "iss.h"
 
diff --git a/drivers/staging/most/sound/sound.c b/drivers/staging/most/sound/sound.c
index 04c18323c2ea..89b02fc305b8 100644
--- a/drivers/staging/most/sound/sound.c
+++ b/drivers/staging/most/sound/sound.c
@@ -457,7 +457,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.trigger    = pcm_trigger,
 	.pointer    = pcm_pointer,
 	.page       = snd_pcm_lib_get_vmalloc_page,
-	.mmap       = snd_pcm_lib_mmap_vmalloc,
 };
 
 static int split_arg_list(char *buf, char **card_name, u16 *ch_num,
diff --git a/drivers/staging/rtl8188eu/Kconfig b/drivers/staging/rtl8188eu/Kconfig
index 673fdce25530..ff7832798a77 100644
--- a/drivers/staging/rtl8188eu/Kconfig
+++ b/drivers/staging/rtl8188eu/Kconfig
@@ -7,7 +7,6 @@ config R8188EU
 	select LIB80211
 	select LIB80211_CRYPT_WEP
 	select LIB80211_CRYPT_CCMP
-	select LIB80211_CRYPT_TKIP
 	---help---
 	This option adds the Realtek RTL8188EU USB device such as TP-Link TL-WN725N.
 	If built as a module, it will be called r8188eu.
diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c
index 05936a45eb93..c6857a5be12a 100644
--- a/drivers/staging/rtl8188eu/core/rtw_recv.c
+++ b/drivers/staging/rtl8188eu/core/rtw_recv.c
@@ -23,7 +23,6 @@
 #include <mon.h>
 #include <wifi.h>
 #include <linux/vmalloc.h>
-#include <net/lib80211.h>
 
 #define ETHERNET_HEADER_SIZE	14	/*  Ethernet Header Length */
 #define LLC_HEADER_SIZE			6	/*  LLC Header Length */
@@ -221,20 +220,31 @@ u32 rtw_free_uc_swdec_pending_queue(struct adapter *adapter)
 static int recvframe_chkmic(struct adapter *adapter,
 			    struct recv_frame *precvframe)
 {
-	int res = _SUCCESS;
-	struct rx_pkt_attrib *prxattrib = &precvframe->attrib;
-	struct sta_info *stainfo = rtw_get_stainfo(&adapter->stapriv, prxattrib->ta);
+	int	i, res = _SUCCESS;
+	u32	datalen;
+	u8	miccode[8];
+	u8	bmic_err = false, brpt_micerror = true;
+	u8	*pframe, *payload, *pframemic;
+	u8	*mickey;
+	struct	sta_info		*stainfo;
+	struct	rx_pkt_attrib	*prxattrib = &precvframe->attrib;
+	struct	security_priv	*psecuritypriv = &adapter->securitypriv;
+
+	struct mlme_ext_priv	*pmlmeext = &adapter->mlmeextpriv;
+	struct mlme_ext_info	*pmlmeinfo = &(pmlmeext->mlmext_info);
+
+	stainfo = rtw_get_stainfo(&adapter->stapriv, &prxattrib->ta[0]);
 
 	if (prxattrib->encrypt == _TKIP_) {
+		RT_TRACE(_module_rtl871x_recv_c_, _drv_info_,
+			 ("\n %s: prxattrib->encrypt==_TKIP_\n", __func__));
+		RT_TRACE(_module_rtl871x_recv_c_, _drv_info_,
+			 ("\n %s: da=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n",
+			  __func__, prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2],
+			  prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5]));
+
+		/* calculate mic code */
 		if (stainfo) {
-			int key_idx;
-			const int iv_len = 8, icv_len = 4, key_length = 32;
-			struct sk_buff *skb = precvframe->pkt;
-			u8 key[32], iv[8], icv[4], *pframe = skb->data;
-			void *crypto_private = NULL;
-			struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip");
-			struct security_priv *psecuritypriv = &adapter->securitypriv;
-
 			if (IS_MCAST(prxattrib->ra)) {
 				if (!psecuritypriv) {
 					res = _FAIL;
@@ -243,58 +253,115 @@ static int recvframe_chkmic(struct adapter *adapter,
 					DBG_88E("\n %s: didn't install group key!!!!!!!!!!\n", __func__);
 					goto exit;
 				}
-				key_idx = prxattrib->key_index;
-				memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16);
-				memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16);
+				mickey = &psecuritypriv->dot118021XGrprxmickey[prxattrib->key_index].skey[0];
+
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_info_,
+					 ("\n %s: bcmc key\n", __func__));
 			} else {
-				key_idx = 0;
-				memcpy(key, stainfo->dot118021x_UncstKey.skey, 16);
-				memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16);
+				mickey = &stainfo->dot11tkiprxmickey.skey[0];
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+					 ("\n %s: unicast key\n", __func__));
 			}
 
-			if (!crypto_ops) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
+			/* icv_len included the mic code */
+			datalen = precvframe->pkt->len-prxattrib->hdrlen -
+				  prxattrib->iv_len-prxattrib->icv_len-8;
+			pframe = precvframe->pkt->data;
+			payload = pframe+prxattrib->hdrlen+prxattrib->iv_len;
 
-			memcpy(iv, pframe + prxattrib->hdrlen, iv_len);
-			memcpy(icv, pframe + skb->len - icv_len, icv_len);
-			memmove(pframe + iv_len, pframe, prxattrib->hdrlen);
+			RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, ("\n prxattrib->iv_len=%d prxattrib->icv_len=%d\n", prxattrib->iv_len, prxattrib->icv_len));
+			rtw_seccalctkipmic(mickey, pframe, payload, datalen, &miccode[0],
+					   (unsigned char)prxattrib->priority); /* care the length of the data */
 
-			skb_pull(skb, iv_len);
-			skb_trim(skb, skb->len - icv_len);
+			pframemic = payload+datalen;
 
-			crypto_private = crypto_ops->init(key_idx);
-			if (!crypto_private) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
-			if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
-			if (crypto_ops->decrypt_msdu(skb, key_idx, prxattrib->hdrlen, crypto_private)) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
+			bmic_err = false;
+
+			for (i = 0; i < 8; i++) {
+				if (miccode[i] != *(pframemic+i)) {
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+						 ("%s: miccode[%d](%02x)!=*(pframemic+%d)(%02x) ",
+						  __func__, i, miccode[i], i, *(pframemic + i)));
+					bmic_err = true;
+				}
 			}
 
-			memmove(pframe, pframe + iv_len, prxattrib->hdrlen);
-			skb_push(skb, iv_len);
-			skb_put(skb, icv_len);
+			if (bmic_err) {
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+					 ("\n *(pframemic-8)-*(pframemic-1)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n",
+					 *(pframemic-8), *(pframemic-7), *(pframemic-6),
+					 *(pframemic-5), *(pframemic-4), *(pframemic-3),
+					 *(pframemic-2), *(pframemic-1)));
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+					 ("\n *(pframemic-16)-*(pframemic-9)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n",
+					 *(pframemic-16), *(pframemic-15), *(pframemic-14),
+					 *(pframemic-13), *(pframemic-12), *(pframemic-11),
+					 *(pframemic-10), *(pframemic-9)));
+				{
+					uint i;
 
-			memcpy(pframe + prxattrib->hdrlen, iv, iv_len);
-			memcpy(pframe + skb->len - icv_len, icv, icv_len);
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+						 ("\n ======demp packet (len=%d)======\n",
+						 precvframe->pkt->len));
+					for (i = 0; i < precvframe->pkt->len; i += 8) {
+						RT_TRACE(_module_rtl871x_recv_c_,
+							 _drv_err_,
+							 ("0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x",
+							 *(precvframe->pkt->data+i),
+							 *(precvframe->pkt->data+i+1),
+							 *(precvframe->pkt->data+i+2),
+							 *(precvframe->pkt->data+i+3),
+							 *(precvframe->pkt->data+i+4),
+							 *(precvframe->pkt->data+i+5),
+							 *(precvframe->pkt->data+i+6),
+							 *(precvframe->pkt->data+i+7)));
+					}
+					RT_TRACE(_module_rtl871x_recv_c_,
+						 _drv_err_,
+						 ("\n ====== demp packet end [len=%d]======\n",
+						 precvframe->pkt->len));
+					RT_TRACE(_module_rtl871x_recv_c_,
+						 _drv_err_,
+						 ("\n hrdlen=%d,\n",
+						 prxattrib->hdrlen));
+				}
 
-exit_lib80211_tkip:
-			if (crypto_ops && crypto_private)
-				crypto_ops->deinit(crypto_private);
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+					 ("ra=0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x psecuritypriv->binstallGrpkey=%d ",
+					 prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2],
+					 prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5], psecuritypriv->binstallGrpkey));
+
+				/*  double check key_index for some timing issue , */
+				/*  cannot compare with psecuritypriv->dot118021XGrpKeyid also cause timing issue */
+				if ((IS_MCAST(prxattrib->ra) == true)  && (prxattrib->key_index != pmlmeinfo->key_index))
+					brpt_micerror = false;
+
+				if ((prxattrib->bdecrypted) && (brpt_micerror)) {
+					rtw_handle_tkip_mic_err(adapter, (u8)IS_MCAST(prxattrib->ra));
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted));
+					DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted);
+				} else {
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted));
+					DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted);
+				}
+				res = _FAIL;
+			} else {
+				/* mic checked ok */
+				if ((!psecuritypriv->bcheck_grpkey) && (IS_MCAST(prxattrib->ra))) {
+					psecuritypriv->bcheck_grpkey = true;
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("psecuritypriv->bcheck_grpkey = true"));
+				}
+			}
 		} else {
 			RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
 				 ("%s: rtw_get_stainfo==NULL!!!\n", __func__));
 		}
+
+		skb_trim(precvframe->pkt, precvframe->pkt->len - 8);
 	}
 
 exit:
+
 	return res;
 }
 
diff --git a/drivers/staging/rtl8188eu/core/rtw_security.c b/drivers/staging/rtl8188eu/core/rtw_security.c
index bfe0b217e679..67a2490f055e 100644
--- a/drivers/staging/rtl8188eu/core/rtw_security.c
+++ b/drivers/staging/rtl8188eu/core/rtw_security.c
@@ -650,71 +650,71 @@ u32	rtw_tkip_encrypt(struct adapter *padapter, u8 *pxmitframe)
 	return res;
 }
 
+/* The hlen isn't include the IV */
 u32 rtw_tkip_decrypt(struct adapter *padapter, u8 *precvframe)
-{
-	struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib;
-	u32 res = _SUCCESS;
+{																	/*  exclude ICV */
+	u16 pnl;
+	u32 pnh;
+	u8   rc4key[16];
+	u8   ttkey[16];
+	u8	crc[4];
+	struct arc4context mycontext;
+	int			length;
+
+	u8	*pframe, *payload, *iv, *prwskey;
+	union pn48 dot11txpn;
+	struct	sta_info		*stainfo;
+	struct	rx_pkt_attrib	 *prxattrib = &((struct recv_frame *)precvframe)->attrib;
+	struct	security_priv	*psecuritypriv = &padapter->securitypriv;
+	u32		res = _SUCCESS;
+
+
+	pframe = (unsigned char *)((struct recv_frame *)precvframe)->pkt->data;
 
 	/* 4 start to decrypt recvframe */
 	if (prxattrib->encrypt == _TKIP_) {
-		struct sta_info *stainfo = rtw_get_stainfo(&padapter->stapriv, prxattrib->ta);
-
+		stainfo = rtw_get_stainfo(&padapter->stapriv, &prxattrib->ta[0]);
 		if (stainfo) {
-			int key_idx;
-			const int iv_len = 8, icv_len = 4, key_length = 32;
-			void *crypto_private = NULL;
-			struct sk_buff *skb = ((struct recv_frame *)precvframe)->pkt;
-			u8 key[32], iv[8], icv[4], *pframe = skb->data;
-			struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip");
-			struct security_priv *psecuritypriv = &padapter->securitypriv;
-
 			if (IS_MCAST(prxattrib->ra)) {
 				if (!psecuritypriv->binstallGrpkey) {
 					res = _FAIL;
 					DBG_88E("%s:rx bc/mc packets, but didn't install group key!!!!!!!!!!\n", __func__);
 					goto exit;
 				}
-				key_idx = prxattrib->key_index;
-				memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16);
-				memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16);
+				prwskey = psecuritypriv->dot118021XGrpKey[prxattrib->key_index].skey;
 			} else {
-				key_idx = 0;
-				memcpy(key, stainfo->dot118021x_UncstKey.skey, 16);
-				memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16);
+				RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("%s: stainfo!= NULL!!!\n", __func__));
+				prwskey = &stainfo->dot118021x_UncstKey.skey[0];
 			}
 
-			if (!crypto_ops) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
+			iv = pframe+prxattrib->hdrlen;
+			payload = pframe+prxattrib->iv_len+prxattrib->hdrlen;
+			length = ((struct recv_frame *)precvframe)->pkt->len-prxattrib->hdrlen-prxattrib->iv_len;
 
-			memcpy(iv, pframe + prxattrib->hdrlen, iv_len);
-			memcpy(icv, pframe + skb->len - icv_len, icv_len);
+			GET_TKIP_PN(iv, dot11txpn);
 
-			crypto_private = crypto_ops->init(key_idx);
-			if (!crypto_private) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
-			if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
-			if (crypto_ops->decrypt_mpdu(skb, prxattrib->hdrlen, crypto_private)) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
+			pnl = (u16)(dot11txpn.val);
+			pnh = (u32)(dot11txpn.val>>16);
 
-			memmove(pframe, pframe + iv_len, prxattrib->hdrlen);
-			skb_push(skb, iv_len);
-			skb_put(skb, icv_len);
+			phase1((u16 *)&ttkey[0], prwskey, &prxattrib->ta[0], pnh);
+			phase2(&rc4key[0], prwskey, (unsigned short *)&ttkey[0], pnl);
 
-			memcpy(pframe + prxattrib->hdrlen, iv, iv_len);
-			memcpy(pframe + skb->len - icv_len, icv, icv_len);
+			/* 4 decrypt payload include icv */
 
-exit_lib80211_tkip:
-			if (crypto_ops && crypto_private)
-				crypto_ops->deinit(crypto_private);
+			arcfour_init(&mycontext, rc4key, 16);
+			arcfour_encrypt(&mycontext, payload, payload, length);
+
+			*((__le32 *)crc) = getcrc32(payload, length-4);
+
+			if (crc[3] != payload[length-1] ||
+			    crc[2] != payload[length-2] ||
+			    crc[1] != payload[length-3] ||
+			    crc[0] != payload[length-4]) {
+				RT_TRACE(_module_rtl871x_security_c_, _drv_err_,
+					 ("rtw_wep_decrypt:icv error crc (%4ph)!=payload (%4ph)\n",
+					 &crc, &payload[length-4]));
+				res = _FAIL;
+			}
 		} else {
 			RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("rtw_tkip_decrypt: stainfo==NULL!!!\n"));
 			res = _FAIL;
diff --git a/drivers/staging/rtl8723bs/core/rtw_ap.c b/drivers/staging/rtl8723bs/core/rtw_ap.c
index 45c05527a57a..faf4b4158cfa 100644
--- a/drivers/staging/rtl8723bs/core/rtw_ap.c
+++ b/drivers/staging/rtl8723bs/core/rtw_ap.c
@@ -1051,7 +1051,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 		return _FAIL;
 
 
-	if (len > MAX_IE_SZ)
+	if (len < 0 || len > MAX_IE_SZ)
 		return _FAIL;
 
 	pbss_network->IELength = len;
diff --git a/drivers/staging/rtlwifi/rtl8822be/hw.c b/drivers/staging/rtlwifi/rtl8822be/hw.c
index 7947edb239a1..88ba5b2fea6a 100644
--- a/drivers/staging/rtlwifi/rtl8822be/hw.c
+++ b/drivers/staging/rtlwifi/rtl8822be/hw.c
@@ -803,7 +803,7 @@ static void _rtl8822be_enable_aspm_back_door(struct ieee80211_hw *hw)
 		return;
 
 	pci_read_config_byte(rtlpci->pdev, 0x70f, &tmp);
-	pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | BIT(7));
+	pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | ASPM_L1_LATENCY << 3);
 
 	pci_read_config_byte(rtlpci->pdev, 0x719, &tmp);
 	pci_write_config_byte(rtlpci->pdev, 0x719, tmp | BIT(3) | BIT(4));
diff --git a/drivers/staging/rtlwifi/wifi.h b/drivers/staging/rtlwifi/wifi.h
index 012fb618840b..a45f0eb69d3f 100644
--- a/drivers/staging/rtlwifi/wifi.h
+++ b/drivers/staging/rtlwifi/wifi.h
@@ -88,6 +88,7 @@
 #define RTL_USB_MAX_RX_COUNT			100
 #define QBSS_LOAD_SIZE				5
 #define MAX_WMMELE_LENGTH			64
+#define ASPM_L1_LATENCY				7
 
 #define TOTAL_CAM_ENTRY				32
 
diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c
index a61bc41b82d7..947c79532e10 100644
--- a/drivers/staging/speakup/speakup_soft.c
+++ b/drivers/staging/speakup/speakup_soft.c
@@ -198,11 +198,15 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count,
 	int chars_sent = 0;
 	char __user *cp;
 	char *init;
+	size_t bytes_per_ch = unicode ? 3 : 1;
 	u16 ch;
 	int empty;
 	unsigned long flags;
 	DEFINE_WAIT(wait);
 
+	if (count < bytes_per_ch)
+		return -EINVAL;
+
 	spin_lock_irqsave(&speakup_info.spinlock, flags);
 	while (1) {
 		prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE);
@@ -228,7 +232,7 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count,
 	init = get_initstring();
 
 	/* Keep 3 bytes available for a 16bit UTF-8-encoded character */
-	while (chars_sent <= count - 3) {
+	while (chars_sent <= count - bytes_per_ch) {
 		if (speakup_info.flushing) {
 			speakup_info.flushing = 0;
 			ch = '\x18';
diff --git a/drivers/staging/typec/Kconfig b/drivers/staging/typec/Kconfig
index 3aa981fbc8f5..e45ed08a5166 100644
--- a/drivers/staging/typec/Kconfig
+++ b/drivers/staging/typec/Kconfig
@@ -11,6 +11,7 @@ config TYPEC_TCPCI
 
 config TYPEC_RT1711H
 	tristate "Richtek RT1711H Type-C chip driver"
+	depends on I2C
 	select TYPEC_TCPCI
 	help
 	  Richtek RT1711H Type-C chip driver that works with
diff --git a/drivers/target/Kconfig b/drivers/target/Kconfig
index 4c44d7bed01a..cb6f32ce7de8 100644
--- a/drivers/target/Kconfig
+++ b/drivers/target/Kconfig
@@ -1,10 +1,10 @@
 
 menuconfig TARGET_CORE
 	tristate "Generic Target Core Mod (TCM) and ConfigFS Infrastructure"
-	depends on SCSI && BLOCK
+	depends on BLOCK
 	select CONFIGFS_FS
 	select CRC_T10DIF
-	select BLK_SCSI_REQUEST # only for scsi_command_size_tbl..
+	select BLK_SCSI_REQUEST
 	select SGL_ALLOC
 	default n
 	help
@@ -29,6 +29,7 @@ config TCM_FILEIO
 
 config TCM_PSCSI
 	tristate "TCM/pSCSI Subsystem Plugin for Linux/SCSI"
+	depends on SCSI
 	help
 	Say Y here to enable the TCM/pSCSI subsystem plugin for non-buffered
 	passthrough access to Linux/SCSI device
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c
index 514986b57c2d..25eb3891e34b 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_target.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c
@@ -652,6 +652,7 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk)
 	struct iscsi_param *param;
 	u32 mrdsl, mbl;
 	u32 max_npdu, max_iso_npdu;
+	u32 max_iso_payload;
 
 	if (conn->login->leading_connection) {
 		param = iscsi_find_param_from_key(MAXBURSTLENGTH,
@@ -670,8 +671,10 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk)
 	mrdsl = conn_ops->MaxRecvDataSegmentLength;
 	max_npdu = mbl / mrdsl;
 
-	max_iso_npdu = CXGBIT_MAX_ISO_PAYLOAD /
-			(ISCSI_HDR_LEN + mrdsl +
+	max_iso_payload = rounddown(CXGBIT_MAX_ISO_PAYLOAD, csk->emss);
+
+	max_iso_npdu = max_iso_payload /
+		       (ISCSI_HDR_LEN + mrdsl +
 			cxgbit_digest_len[csk->submode]);
 
 	csk->max_iso_npdu = min(max_npdu, max_iso_npdu);
@@ -741,6 +744,9 @@ static int cxgbit_set_params(struct iscsi_conn *conn)
 	if (conn_ops->MaxRecvDataSegmentLength > cdev->mdsl)
 		conn_ops->MaxRecvDataSegmentLength = cdev->mdsl;
 
+	if (cxgbit_set_digest(csk))
+		return -1;
+
 	if (conn->login->leading_connection) {
 		param = iscsi_find_param_from_key(ERRORRECOVERYLEVEL,
 						  conn->param_list);
@@ -764,7 +770,7 @@ static int cxgbit_set_params(struct iscsi_conn *conn)
 			if (is_t5(cdev->lldi.adapter_type))
 				goto enable_ddp;
 			else
-				goto enable_digest;
+				return 0;
 		}
 
 		if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) {
@@ -781,10 +787,6 @@ enable_ddp:
 		}
 	}
 
-enable_digest:
-	if (cxgbit_set_digest(csk))
-		return -1;
-
 	return 0;
 }
 
diff --git a/drivers/target/loopback/Kconfig b/drivers/target/loopback/Kconfig
index abe8ecbcdf06..158ee9d522f7 100644
--- a/drivers/target/loopback/Kconfig
+++ b/drivers/target/loopback/Kconfig
@@ -1,5 +1,6 @@
 config LOOPBACK_TARGET
 	tristate "TCM Virtual SAS target and Linux/SCSI LDD fabric loopback module"
+	depends on SCSI
 	help
 	  Say Y here to enable the TCM Virtual SAS target and Linux/SCSI LLD
 	  fabric loopback module.
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 01ac306131c1..10db5656fd5d 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -3727,11 +3727,16 @@ core_scsi3_pri_read_keys(struct se_cmd *cmd)
 		 * Check for overflow of 8byte PRI READ_KEYS payload and
 		 * next reservation key list descriptor.
 		 */
-		if ((add_len + 8) > (cmd->data_length - 8))
-			break;
-
-		put_unaligned_be64(pr_reg->pr_res_key, &buf[off]);
-		off += 8;
+		if (off + 8 <= cmd->data_length) {
+			put_unaligned_be64(pr_reg->pr_res_key, &buf[off]);
+			off += 8;
+		}
+		/*
+		 * SPC5r17: 6.16.2 READ KEYS service action
+		 * The ADDITIONAL LENGTH field indicates the number of bytes in
+		 * the Reservation key list. The contents of the ADDITIONAL
+		 * LENGTH field are not altered based on the allocation length
+		 */
 		add_len += 8;
 	}
 	spin_unlock(&dev->t10_pr.registration_lock);
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 7f96dfa32b9c..d8dc3d22051f 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -656,7 +656,7 @@ static void scatter_data_area(struct tcmu_dev *udev,
 }
 
 static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
-			     bool bidi)
+			     bool bidi, uint32_t read_len)
 {
 	struct se_cmd *se_cmd = cmd->se_cmd;
 	int i, dbi;
@@ -689,7 +689,7 @@ static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
 	for_each_sg(data_sg, sg, data_nents, i) {
 		int sg_remaining = sg->length;
 		to = kmap_atomic(sg_page(sg)) + sg->offset;
-		while (sg_remaining > 0) {
+		while (sg_remaining > 0 && read_len > 0) {
 			if (block_remaining == 0) {
 				if (from)
 					kunmap_atomic(from);
@@ -701,6 +701,8 @@ static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
 			}
 			copy_bytes = min_t(size_t, sg_remaining,
 					block_remaining);
+			if (read_len < copy_bytes)
+				copy_bytes = read_len;
 			offset = DATA_BLOCK_SIZE - block_remaining;
 			tcmu_flush_dcache_range(from, copy_bytes);
 			memcpy(to + sg->length - sg_remaining, from + offset,
@@ -708,8 +710,11 @@ static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
 
 			sg_remaining -= copy_bytes;
 			block_remaining -= copy_bytes;
+			read_len -= copy_bytes;
 		}
 		kunmap_atomic(to - sg->offset);
+		if (read_len == 0)
+			break;
 	}
 	if (from)
 		kunmap_atomic(from);
@@ -1042,6 +1047,8 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *
 {
 	struct se_cmd *se_cmd = cmd->se_cmd;
 	struct tcmu_dev *udev = cmd->tcmu_dev;
+	bool read_len_valid = false;
+	uint32_t read_len = se_cmd->data_length;
 
 	/*
 	 * cmd has been completed already from timeout, just reclaim
@@ -1056,13 +1063,28 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *
 		pr_warn("TCMU: Userspace set UNKNOWN_OP flag on se_cmd %p\n",
 			cmd->se_cmd);
 		entry->rsp.scsi_status = SAM_STAT_CHECK_CONDITION;
-	} else if (entry->rsp.scsi_status == SAM_STAT_CHECK_CONDITION) {
+		goto done;
+	}
+
+	if (se_cmd->data_direction == DMA_FROM_DEVICE &&
+	    (entry->hdr.uflags & TCMU_UFLAG_READ_LEN) && entry->rsp.read_len) {
+		read_len_valid = true;
+		if (entry->rsp.read_len < read_len)
+			read_len = entry->rsp.read_len;
+	}
+
+	if (entry->rsp.scsi_status == SAM_STAT_CHECK_CONDITION) {
 		transport_copy_sense_to_cmd(se_cmd, entry->rsp.sense_buffer);
-	} else if (se_cmd->se_cmd_flags & SCF_BIDI) {
+		if (!read_len_valid )
+			goto done;
+		else
+			se_cmd->se_cmd_flags |= SCF_TREAT_READ_AS_NORMAL;
+	}
+	if (se_cmd->se_cmd_flags & SCF_BIDI) {
 		/* Get Data-In buffer before clean up */
-		gather_data_area(udev, cmd, true);
+		gather_data_area(udev, cmd, true, read_len);
 	} else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
-		gather_data_area(udev, cmd, false);
+		gather_data_area(udev, cmd, false, read_len);
 	} else if (se_cmd->data_direction == DMA_TO_DEVICE) {
 		/* TODO: */
 	} else if (se_cmd->data_direction != DMA_NONE) {
@@ -1070,7 +1092,13 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *
 			se_cmd->data_direction);
 	}
 
-	target_complete_cmd(cmd->se_cmd, entry->rsp.scsi_status);
+done:
+	if (read_len_valid) {
+		pr_debug("read_len = %d\n", read_len);
+		target_complete_cmd_with_length(cmd->se_cmd,
+					entry->rsp.scsi_status, read_len);
+	} else
+		target_complete_cmd(cmd->se_cmd, entry->rsp.scsi_status);
 
 out:
 	cmd->se_cmd = NULL;
@@ -1740,7 +1768,7 @@ static int tcmu_configure_device(struct se_device *dev)
 	/* Initialise the mailbox of the ring buffer */
 	mb = udev->mb_addr;
 	mb->version = TCMU_MAILBOX_VERSION;
-	mb->flags = TCMU_MAILBOX_FLAG_CAP_OOOC;
+	mb->flags = TCMU_MAILBOX_FLAG_CAP_OOOC | TCMU_MAILBOX_FLAG_CAP_READ_LEN;
 	mb->cmdr_off = CMDR_OFF;
 	mb->cmdr_size = udev->cmdr_size;
 
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index 334d98be03b9..cbfcca828cd7 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -3,6 +3,7 @@
 // Copyright 2013 Freescale Semiconductor, Inc.
 
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpu_cooling.h>
 #include <linux/delay.h>
@@ -644,6 +645,27 @@ static const struct of_device_id of_imx_thermal_match[] = {
 };
 MODULE_DEVICE_TABLE(of, of_imx_thermal_match);
 
+/*
+ * Create cooling device in case no #cooling-cells property is available in
+ * CPU node
+ */
+static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data)
+{
+	struct device_node *np = of_get_cpu_node(data->policy->cpu, NULL);
+	int ret;
+
+	if (!np || !of_find_property(np, "#cooling-cells", NULL)) {
+		data->cdev = cpufreq_cooling_register(data->policy);
+		if (IS_ERR(data->cdev)) {
+			ret = PTR_ERR(data->cdev);
+			cpufreq_cpu_put(data->policy);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static int imx_thermal_probe(struct platform_device *pdev)
 {
 	struct imx_thermal_data *data;
@@ -724,12 +746,10 @@ static int imx_thermal_probe(struct platform_device *pdev)
 		return -EPROBE_DEFER;
 	}
 
-	data->cdev = cpufreq_cooling_register(data->policy);
-	if (IS_ERR(data->cdev)) {
-		ret = PTR_ERR(data->cdev);
+	ret = imx_thermal_register_legacy_cooling(data);
+	if (ret) {
 		dev_err(&pdev->dev,
 			"failed to register cpufreq cooling device: %d\n", ret);
-		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index 6281266b8ec0..a923ebdeb73c 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -213,6 +213,10 @@ static ssize_t boot_acl_store(struct device *dev, struct device_attribute *attr,
 		goto err_free_acl;
 	}
 	ret = tb->cm_ops->set_boot_acl(tb, acl, tb->nboot_acl);
+	if (!ret) {
+		/* Notify userspace about the change */
+		kobject_uevent(&tb->dev.kobj, KOBJ_CHANGE);
+	}
 	mutex_unlock(&tb->lock);
 
 err_free_acl:
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index cbe98bc2b998..431742201709 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -124,6 +124,8 @@ struct n_tty_data {
 	struct mutex output_lock;
 };
 
+#define MASK(x) ((x) & (N_TTY_BUF_SIZE - 1))
+
 static inline size_t read_cnt(struct n_tty_data *ldata)
 {
 	return ldata->read_head - ldata->read_tail;
@@ -141,6 +143,7 @@ static inline unsigned char *read_buf_addr(struct n_tty_data *ldata, size_t i)
 
 static inline unsigned char echo_buf(struct n_tty_data *ldata, size_t i)
 {
+	smp_rmb(); /* Matches smp_wmb() in add_echo_byte(). */
 	return ldata->echo_buf[i & (N_TTY_BUF_SIZE - 1)];
 }
 
@@ -316,9 +319,7 @@ static inline void put_tty_queue(unsigned char c, struct n_tty_data *ldata)
 static void reset_buffer_flags(struct n_tty_data *ldata)
 {
 	ldata->read_head = ldata->canon_head = ldata->read_tail = 0;
-	ldata->echo_head = ldata->echo_tail = ldata->echo_commit = 0;
 	ldata->commit_head = 0;
-	ldata->echo_mark = 0;
 	ldata->line_start = 0;
 
 	ldata->erasing = 0;
@@ -617,13 +618,20 @@ static size_t __process_echoes(struct tty_struct *tty)
 	old_space = space = tty_write_room(tty);
 
 	tail = ldata->echo_tail;
-	while (ldata->echo_commit != tail) {
+	while (MASK(ldata->echo_commit) != MASK(tail)) {
 		c = echo_buf(ldata, tail);
 		if (c == ECHO_OP_START) {
 			unsigned char op;
 			int no_space_left = 0;
 
 			/*
+			 * Since add_echo_byte() is called without holding
+			 * output_lock, we might see only portion of multi-byte
+			 * operation.
+			 */
+			if (MASK(ldata->echo_commit) == MASK(tail + 1))
+				goto not_yet_stored;
+			/*
 			 * If the buffer byte is the start of a multi-byte
 			 * operation, get the next byte, which is either the
 			 * op code or a control character value.
@@ -634,6 +642,8 @@ static size_t __process_echoes(struct tty_struct *tty)
 				unsigned int num_chars, num_bs;
 
 			case ECHO_OP_ERASE_TAB:
+				if (MASK(ldata->echo_commit) == MASK(tail + 2))
+					goto not_yet_stored;
 				num_chars = echo_buf(ldata, tail + 2);
 
 				/*
@@ -728,7 +738,8 @@ static size_t __process_echoes(struct tty_struct *tty)
 	/* If the echo buffer is nearly full (so that the possibility exists
 	 * of echo overrun before the next commit), then discard enough
 	 * data at the tail to prevent a subsequent overrun */
-	while (ldata->echo_commit - tail >= ECHO_DISCARD_WATERMARK) {
+	while (ldata->echo_commit > tail &&
+	       ldata->echo_commit - tail >= ECHO_DISCARD_WATERMARK) {
 		if (echo_buf(ldata, tail) == ECHO_OP_START) {
 			if (echo_buf(ldata, tail + 1) == ECHO_OP_ERASE_TAB)
 				tail += 3;
@@ -738,6 +749,7 @@ static size_t __process_echoes(struct tty_struct *tty)
 			tail++;
 	}
 
+ not_yet_stored:
 	ldata->echo_tail = tail;
 	return old_space - space;
 }
@@ -748,6 +760,7 @@ static void commit_echoes(struct tty_struct *tty)
 	size_t nr, old, echoed;
 	size_t head;
 
+	mutex_lock(&ldata->output_lock);
 	head = ldata->echo_head;
 	ldata->echo_mark = head;
 	old = ldata->echo_commit - ldata->echo_tail;
@@ -756,10 +769,12 @@ static void commit_echoes(struct tty_struct *tty)
 	 * is over the threshold (and try again each time another
 	 * block is accumulated) */
 	nr = head - ldata->echo_tail;
-	if (nr < ECHO_COMMIT_WATERMARK || (nr % ECHO_BLOCK > old % ECHO_BLOCK))
+	if (nr < ECHO_COMMIT_WATERMARK ||
+	    (nr % ECHO_BLOCK > old % ECHO_BLOCK)) {
+		mutex_unlock(&ldata->output_lock);
 		return;
+	}
 
-	mutex_lock(&ldata->output_lock);
 	ldata->echo_commit = head;
 	echoed = __process_echoes(tty);
 	mutex_unlock(&ldata->output_lock);
@@ -810,7 +825,9 @@ static void flush_echoes(struct tty_struct *tty)
 
 static inline void add_echo_byte(unsigned char c, struct n_tty_data *ldata)
 {
-	*echo_buf_addr(ldata, ldata->echo_head++) = c;
+	*echo_buf_addr(ldata, ldata->echo_head) = c;
+	smp_wmb(); /* Matches smp_rmb() in echo_buf(). */
+	ldata->echo_head++;
 }
 
 /**
@@ -978,14 +995,15 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 	}
 
 	seen_alnums = 0;
-	while (ldata->read_head != ldata->canon_head) {
+	while (MASK(ldata->read_head) != MASK(ldata->canon_head)) {
 		head = ldata->read_head;
 
 		/* erase a single possibly multibyte character */
 		do {
 			head--;
 			c = read_buf(ldata, head);
-		} while (is_continuation(c, tty) && head != ldata->canon_head);
+		} while (is_continuation(c, tty) &&
+			 MASK(head) != MASK(ldata->canon_head));
 
 		/* do not partially erase */
 		if (is_continuation(c, tty))
@@ -1027,7 +1045,7 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 				 * This info is used to go back the correct
 				 * number of columns.
 				 */
-				while (tail != ldata->canon_head) {
+				while (MASK(tail) != MASK(ldata->canon_head)) {
 					tail--;
 					c = read_buf(ldata, tail);
 					if (c == '\t') {
@@ -1302,7 +1320,7 @@ n_tty_receive_char_special(struct tty_struct *tty, unsigned char c)
 			finish_erasing(ldata);
 			echo_char(c, tty);
 			echo_char_raw('\n', ldata);
-			while (tail != ldata->read_head) {
+			while (MASK(tail) != MASK(ldata->read_head)) {
 				echo_char(read_buf(ldata, tail), tty);
 				tail++;
 			}
@@ -1878,30 +1896,21 @@ static int n_tty_open(struct tty_struct *tty)
 	struct n_tty_data *ldata;
 
 	/* Currently a malloc failure here can panic */
-	ldata = vmalloc(sizeof(*ldata));
+	ldata = vzalloc(sizeof(*ldata));
 	if (!ldata)
-		goto err;
+		return -ENOMEM;
 
 	ldata->overrun_time = jiffies;
 	mutex_init(&ldata->atomic_read_lock);
 	mutex_init(&ldata->output_lock);
 
 	tty->disc_data = ldata;
-	reset_buffer_flags(tty->disc_data);
-	ldata->column = 0;
-	ldata->canon_column = 0;
-	ldata->num_overrun = 0;
-	ldata->no_room = 0;
-	ldata->lnext = 0;
 	tty->closing = 0;
 	/* indicate buffer work may resume */
 	clear_bit(TTY_LDISC_HALTED, &tty->flags);
 	n_tty_set_termios(tty, NULL);
 	tty_unthrottle(tty);
-
 	return 0;
-err:
-	return -ENOMEM;
 }
 
 static inline int input_available_p(struct tty_struct *tty, int poll)
@@ -2411,7 +2420,7 @@ static unsigned long inq_canon(struct n_tty_data *ldata)
 	tail = ldata->read_tail;
 	nr = head - tail;
 	/* Skip EOF-chars.. */
-	while (head != tail) {
+	while (MASK(head) != MASK(tail)) {
 		if (test_bit(tail & (N_TTY_BUF_SIZE - 1), ldata->read_flags) &&
 		    read_buf(ldata, tail) == __DISABLED_CHAR)
 			nr--;
diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index df93b727e984..9e59f4788589 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -617,6 +617,7 @@ EXPORT_SYMBOL_GPL(__serdev_device_driver_register);
 static void __exit serdev_exit(void)
 {
 	bus_unregister(&serdev_bus_type);
+	ida_destroy(&ctrl_ida);
 }
 module_exit(serdev_exit);
 
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 3296a05cda2d..f80a300b5d68 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -3339,9 +3339,7 @@ static const struct pci_device_id blacklist[] = {
 	/* multi-io cards handled by parport_serial */
 	{ PCI_DEVICE(0x4348, 0x7053), }, /* WCH CH353 2S1P */
 	{ PCI_DEVICE(0x4348, 0x5053), }, /* WCH CH353 1S1P */
-	{ PCI_DEVICE(0x4348, 0x7173), }, /* WCH CH355 4S */
 	{ PCI_DEVICE(0x1c00, 0x3250), }, /* WCH CH382 2S1P */
-	{ PCI_DEVICE(0x1c00, 0x3470), }, /* WCH CH384 4S */
 
 	/* Moxa Smartio MUE boards handled by 8250_moxa */
 	{ PCI_VDEVICE(MOXA, 0x1024), },
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index d5b4a2b44ab8..de310621b8e7 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -959,7 +959,7 @@ struct kbd_led_trigger {
 	unsigned int mask;
 };
 
-static void kbd_led_trigger_activate(struct led_classdev *cdev)
+static int kbd_led_trigger_activate(struct led_classdev *cdev)
 {
 	struct kbd_led_trigger *trigger =
 		container_of(cdev->trigger, struct kbd_led_trigger, trigger);
@@ -970,6 +970,8 @@ static void kbd_led_trigger_activate(struct led_classdev *cdev)
 				  ledstate & trigger->mask ?
 					LED_FULL : LED_OFF);
 	tasklet_enable(&keyboard_tasklet);
+
+	return 0;
 }
 
 #define KBD_LED_TRIGGER(_led_bit, _name) {			\
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 1eb1a376a041..15eb6c829d39 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -784,7 +784,7 @@ int vc_allocate(unsigned int currcons)	/* return 0 on success */
 	if (!*vc->vc_uni_pagedir_loc)
 		con_set_default_unimap(vc);
 
-	vc->vc_screenbuf = kmalloc(vc->vc_screenbuf_size, GFP_KERNEL);
+	vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL);
 	if (!vc->vc_screenbuf)
 		goto err_free;
 
@@ -871,7 +871,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 
 	if (new_screen_size > (4 << 20))
 		return -EINVAL;
-	newscreen = kmalloc(new_screen_size, GFP_USER);
+	newscreen = kzalloc(new_screen_size, GFP_USER);
 	if (!newscreen)
 		return -ENOMEM;
 
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index e8f4ac9400ea..5d421d7e8904 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -215,7 +215,20 @@ static ssize_t name_show(struct device *dev,
 			 struct device_attribute *attr, char *buf)
 {
 	struct uio_device *idev = dev_get_drvdata(dev);
-	return sprintf(buf, "%s\n", idev->info->name);
+	int ret;
+
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		ret = -EINVAL;
+		dev_err(dev, "the device has been unregistered\n");
+		goto out;
+	}
+
+	ret = sprintf(buf, "%s\n", idev->info->name);
+
+out:
+	mutex_unlock(&idev->info_lock);
+	return ret;
 }
 static DEVICE_ATTR_RO(name);
 
@@ -223,7 +236,20 @@ static ssize_t version_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	struct uio_device *idev = dev_get_drvdata(dev);
-	return sprintf(buf, "%s\n", idev->info->version);
+	int ret;
+
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		ret = -EINVAL;
+		dev_err(dev, "the device has been unregistered\n");
+		goto out;
+	}
+
+	ret = sprintf(buf, "%s\n", idev->info->version);
+
+out:
+	mutex_unlock(&idev->info_lock);
+	return ret;
 }
 static DEVICE_ATTR_RO(version);
 
@@ -415,11 +441,15 @@ EXPORT_SYMBOL_GPL(uio_event_notify);
 static irqreturn_t uio_interrupt(int irq, void *dev_id)
 {
 	struct uio_device *idev = (struct uio_device *)dev_id;
-	irqreturn_t ret = idev->info->handler(irq, idev->info);
+	irqreturn_t ret;
 
+	mutex_lock(&idev->info_lock);
+
+	ret = idev->info->handler(irq, idev->info);
 	if (ret == IRQ_HANDLED)
 		uio_event_notify(idev->info);
 
+	mutex_unlock(&idev->info_lock);
 	return ret;
 }
 
@@ -433,7 +463,6 @@ static int uio_open(struct inode *inode, struct file *filep)
 	struct uio_device *idev;
 	struct uio_listener *listener;
 	int ret = 0;
-	unsigned long flags;
 
 	mutex_lock(&minor_lock);
 	idev = idr_find(&uio_idr, iminor(inode));
@@ -460,10 +489,16 @@ static int uio_open(struct inode *inode, struct file *filep)
 	listener->event_count = atomic_read(&idev->event);
 	filep->private_data = listener;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		mutex_unlock(&idev->info_lock);
+		ret = -EINVAL;
+		goto err_alloc_listener;
+	}
+
 	if (idev->info && idev->info->open)
 		ret = idev->info->open(idev->info, inode);
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 	if (ret)
 		goto err_infoopen;
 
@@ -495,12 +530,11 @@ static int uio_release(struct inode *inode, struct file *filep)
 	int ret = 0;
 	struct uio_listener *listener = filep->private_data;
 	struct uio_device *idev = listener->dev;
-	unsigned long flags;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
 	if (idev->info && idev->info->release)
 		ret = idev->info->release(idev->info, inode);
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 
 	module_put(idev->owner);
 	kfree(listener);
@@ -513,12 +547,11 @@ static __poll_t uio_poll(struct file *filep, poll_table *wait)
 	struct uio_listener *listener = filep->private_data;
 	struct uio_device *idev = listener->dev;
 	__poll_t ret = 0;
-	unsigned long flags;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
 	if (!idev->info || !idev->info->irq)
 		ret = -EIO;
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 
 	if (ret)
 		return ret;
@@ -537,12 +570,11 @@ static ssize_t uio_read(struct file *filep, char __user *buf,
 	DECLARE_WAITQUEUE(wait, current);
 	ssize_t retval = 0;
 	s32 event_count;
-	unsigned long flags;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
 	if (!idev->info || !idev->info->irq)
 		retval = -EIO;
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 
 	if (retval)
 		return retval;
@@ -592,9 +624,13 @@ static ssize_t uio_write(struct file *filep, const char __user *buf,
 	struct uio_device *idev = listener->dev;
 	ssize_t retval;
 	s32 irq_on;
-	unsigned long flags;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		retval = -EINVAL;
+		goto out;
+	}
+
 	if (!idev->info || !idev->info->irq) {
 		retval = -EIO;
 		goto out;
@@ -618,7 +654,7 @@ static ssize_t uio_write(struct file *filep, const char __user *buf,
 	retval = idev->info->irqcontrol(idev->info, irq_on);
 
 out:
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 	return retval ? retval : sizeof(s32);
 }
 
@@ -640,10 +676,20 @@ static vm_fault_t uio_vma_fault(struct vm_fault *vmf)
 	struct page *page;
 	unsigned long offset;
 	void *addr;
+	int ret = 0;
+	int mi;
 
-	int mi = uio_find_mem_index(vmf->vma);
-	if (mi < 0)
-		return VM_FAULT_SIGBUS;
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		ret = VM_FAULT_SIGBUS;
+		goto out;
+	}
+
+	mi = uio_find_mem_index(vmf->vma);
+	if (mi < 0) {
+		ret = VM_FAULT_SIGBUS;
+		goto out;
+	}
 
 	/*
 	 * We need to subtract mi because userspace uses offset = N*PAGE_SIZE
@@ -658,7 +704,11 @@ static vm_fault_t uio_vma_fault(struct vm_fault *vmf)
 		page = vmalloc_to_page(addr);
 	get_page(page);
 	vmf->page = page;
-	return 0;
+
+out:
+	mutex_unlock(&idev->info_lock);
+
+	return ret;
 }
 
 static const struct vm_operations_struct uio_logical_vm_ops = {
@@ -683,6 +733,7 @@ static int uio_mmap_physical(struct vm_area_struct *vma)
 	struct uio_device *idev = vma->vm_private_data;
 	int mi = uio_find_mem_index(vma);
 	struct uio_mem *mem;
+
 	if (mi < 0)
 		return -EINVAL;
 	mem = idev->info->mem + mi;
@@ -724,30 +775,46 @@ static int uio_mmap(struct file *filep, struct vm_area_struct *vma)
 
 	vma->vm_private_data = idev;
 
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	mi = uio_find_mem_index(vma);
-	if (mi < 0)
-		return -EINVAL;
+	if (mi < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	requested_pages = vma_pages(vma);
 	actual_pages = ((idev->info->mem[mi].addr & ~PAGE_MASK)
 			+ idev->info->mem[mi].size + PAGE_SIZE -1) >> PAGE_SHIFT;
-	if (requested_pages > actual_pages)
-		return -EINVAL;
+	if (requested_pages > actual_pages) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	if (idev->info->mmap) {
 		ret = idev->info->mmap(idev->info, vma);
-		return ret;
+		goto out;
 	}
 
 	switch (idev->info->mem[mi].memtype) {
 		case UIO_MEM_PHYS:
-			return uio_mmap_physical(vma);
+			ret = uio_mmap_physical(vma);
+			break;
 		case UIO_MEM_LOGICAL:
 		case UIO_MEM_VIRTUAL:
-			return uio_mmap_logical(vma);
+			ret = uio_mmap_logical(vma);
+			break;
 		default:
-			return -EINVAL;
+			ret = -EINVAL;
 	}
+
+out:
+	mutex_unlock(&idev->info_lock);
+	return 0;
 }
 
 static const struct file_operations uio_fops = {
@@ -865,7 +932,7 @@ int __uio_register_device(struct module *owner,
 
 	idev->owner = owner;
 	idev->info = info;
-	spin_lock_init(&idev->info_lock);
+	mutex_init(&idev->info_lock);
 	init_waitqueue_head(&idev->wait);
 	atomic_set(&idev->event, 0);
 
@@ -902,8 +969,9 @@ int __uio_register_device(struct module *owner,
 		 * FDs at the time of unregister and therefore may not be
 		 * freed until they are released.
 		 */
-		ret = request_irq(info->irq, uio_interrupt,
-				  info->irq_flags, info->name, idev);
+		ret = request_threaded_irq(info->irq, NULL, uio_interrupt,
+					   info->irq_flags, info->name, idev);
+
 		if (ret)
 			goto err_request_irq;
 	}
@@ -928,7 +996,6 @@ EXPORT_SYMBOL_GPL(__uio_register_device);
 void uio_unregister_device(struct uio_info *info)
 {
 	struct uio_device *idev;
-	unsigned long flags;
 
 	if (!info || !info->uio_dev)
 		return;
@@ -937,14 +1004,14 @@ void uio_unregister_device(struct uio_info *info)
 
 	uio_free_minor(idev);
 
+	mutex_lock(&idev->info_lock);
 	uio_dev_del_attributes(idev);
 
 	if (info->irq && info->irq != UIO_IRQ_CUSTOM)
 		free_irq(info->irq, idev);
 
-	spin_lock_irqsave(&idev->info_lock, flags);
 	idev->info = NULL;
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 
 	device_unregister(&idev->dev);
 
diff --git a/drivers/usb/chipidea/Kconfig b/drivers/usb/chipidea/Kconfig
index 785f0ed037f7..ee34e9046f7e 100644
--- a/drivers/usb/chipidea/Kconfig
+++ b/drivers/usb/chipidea/Kconfig
@@ -3,6 +3,7 @@ config USB_CHIPIDEA
 	depends on ((USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)) && HAS_DMA
 	select EXTCON
 	select RESET_CONTROLLER
+	select USB_ULPI_BUS
 	help
 	  Say Y here if your system has a dual role high speed USB
 	  controller based on ChipIdea silicon IP. It supports:
@@ -38,12 +39,4 @@ config USB_CHIPIDEA_HOST
 	help
 	  Say Y here to enable host controller functionality of the
 	  ChipIdea driver.
-
-config USB_CHIPIDEA_ULPI
-	bool "ChipIdea ULPI PHY support"
-	depends on USB_ULPI_BUS=y || USB_ULPI_BUS=USB_CHIPIDEA
-	help
-	  Say Y here if you have a ULPI PHY attached to your ChipIdea
-	  controller.
-
 endif
diff --git a/drivers/usb/chipidea/Makefile b/drivers/usb/chipidea/Makefile
index e3d5e728fa53..12df94f78f72 100644
--- a/drivers/usb/chipidea/Makefile
+++ b/drivers/usb/chipidea/Makefile
@@ -1,11 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_USB_CHIPIDEA)		+= ci_hdrc.o
 
-ci_hdrc-y				:= core.o otg.o debug.o
+ci_hdrc-y				:= core.o otg.o debug.o ulpi.o
 ci_hdrc-$(CONFIG_USB_CHIPIDEA_UDC)	+= udc.o
 ci_hdrc-$(CONFIG_USB_CHIPIDEA_HOST)	+= host.o
 ci_hdrc-$(CONFIG_USB_OTG_FSM)		+= otg_fsm.o
-ci_hdrc-$(CONFIG_USB_CHIPIDEA_ULPI)	+= ulpi.o
 
 # Glue/Bridge layers go here
 
diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h
index 0bf244d50544..6a2cc5cd0281 100644
--- a/drivers/usb/chipidea/ci.h
+++ b/drivers/usb/chipidea/ci.h
@@ -240,10 +240,8 @@ struct ci_hdrc {
 
 	struct ci_hdrc_platform_data	*platdata;
 	int				vbus_active;
-#ifdef CONFIG_USB_CHIPIDEA_ULPI
 	struct ulpi			*ulpi;
 	struct ulpi_ops 		ulpi_ops;
-#endif
 	struct phy			*phy;
 	/* old usb_phy interface */
 	struct usb_phy			*usb_phy;
@@ -426,15 +424,9 @@ static inline bool ci_otg_is_fsm_mode(struct ci_hdrc *ci)
 #endif
 }
 
-#if IS_ENABLED(CONFIG_USB_CHIPIDEA_ULPI)
 int ci_ulpi_init(struct ci_hdrc *ci);
 void ci_ulpi_exit(struct ci_hdrc *ci);
 int ci_ulpi_resume(struct ci_hdrc *ci);
-#else
-static inline int ci_ulpi_init(struct ci_hdrc *ci) { return 0; }
-static inline void ci_ulpi_exit(struct ci_hdrc *ci) { }
-static inline int ci_ulpi_resume(struct ci_hdrc *ci) { return 0; }
-#endif
 
 u32 hw_read_intr_enable(struct ci_hdrc *ci);
 
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index af45aa3222b5..4638d9b066be 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -124,8 +124,11 @@ static int host_start(struct ci_hdrc *ci)
 
 	hcd->power_budget = ci->platdata->power_budget;
 	hcd->tpl_support = ci->platdata->tpl_support;
-	if (ci->phy || ci->usb_phy)
+	if (ci->phy || ci->usb_phy) {
 		hcd->skip_phy_initialization = 1;
+		if (ci->usb_phy)
+			hcd->usb_phy = ci->usb_phy;
+	}
 
 	ehci = hcd_to_ehci(hcd);
 	ehci->caps = ci->hw_bank.cap;
diff --git a/drivers/usb/chipidea/ulpi.c b/drivers/usb/chipidea/ulpi.c
index 6da42dcd2888..dfec07e8ae1d 100644
--- a/drivers/usb/chipidea/ulpi.c
+++ b/drivers/usb/chipidea/ulpi.c
@@ -95,6 +95,9 @@ int ci_ulpi_resume(struct ci_hdrc *ci)
 {
 	int cnt = 100000;
 
+	if (ci->platdata->phy_mode != USBPHY_INTERFACE_MODE_ULPI)
+		return 0;
+
 	while (cnt-- > 0) {
 		if (hw_read(ci, OP_ULPI_VIEWPORT, ULPI_SYNC_STATE))
 			return 0;
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 7b366a6c0b49..75c4623ad779 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1758,6 +1758,9 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x11ca, 0x0201), /* VeriFone Mx870 Gadget Serial */
 	.driver_info = SINGLE_RX_URB,
 	},
+	{ USB_DEVICE(0x1965, 0x0018), /* Uniden UBC125XLT */
+	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
+	},
 	{ USB_DEVICE(0x22b8, 0x7000), /* Motorola Q Phone */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
@@ -1828,6 +1831,9 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */
 	.driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */
 	},
+	{ USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */
+	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
+	},
 
 	{ USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */
 	.driver_info = CLEAR_HALT_CONDITIONS,
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index fcae521df29b..1fb266809966 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1142,10 +1142,14 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 
 		if (!udev || udev->state == USB_STATE_NOTATTACHED) {
 			/* Tell hub_wq to disconnect the device or
-			 * check for a new connection
+			 * check for a new connection or over current condition.
+			 * Based on USB2.0 Spec Section 11.12.5,
+			 * C_PORT_OVER_CURRENT could be set while
+			 * PORT_OVER_CURRENT is not. So check for any of them.
 			 */
 			if (udev || (portstatus & USB_PORT_STAT_CONNECTION) ||
-			    (portstatus & USB_PORT_STAT_OVERCURRENT))
+			    (portstatus & USB_PORT_STAT_OVERCURRENT) ||
+			    (portchange & USB_PORT_STAT_C_OVERCURRENT))
 				set_bit(port1, hub->change_bits);
 
 		} else if (portstatus & USB_PORT_STAT_ENABLE) {
diff --git a/drivers/usb/core/ledtrig-usbport.c b/drivers/usb/core/ledtrig-usbport.c
index d775ffea20c3..dc7f7fd71684 100644
--- a/drivers/usb/core/ledtrig-usbport.c
+++ b/drivers/usb/core/ledtrig-usbport.c
@@ -113,11 +113,17 @@ static ssize_t usbport_trig_port_store(struct device *dev,
 static struct attribute *ports_attrs[] = {
 	NULL,
 };
+
 static const struct attribute_group ports_group = {
 	.name = "ports",
 	.attrs = ports_attrs,
 };
 
+static const struct attribute_group *ports_groups[] = {
+	&ports_group,
+	NULL
+};
+
 /***************************************
  * Adding & removing ports
  ***************************************/
@@ -298,61 +304,47 @@ static int usbport_trig_notify(struct notifier_block *nb, unsigned long action,
 	return NOTIFY_DONE;
 }
 
-static void usbport_trig_activate(struct led_classdev *led_cdev)
+static int usbport_trig_activate(struct led_classdev *led_cdev)
 {
 	struct usbport_trig_data *usbport_data;
-	int err;
 
 	usbport_data = kzalloc(sizeof(*usbport_data), GFP_KERNEL);
 	if (!usbport_data)
-		return;
+		return -ENOMEM;
 	usbport_data->led_cdev = led_cdev;
 
 	/* List of ports */
 	INIT_LIST_HEAD(&usbport_data->ports);
-	err = sysfs_create_group(&led_cdev->dev->kobj, &ports_group);
-	if (err)
-		goto err_free;
 	usb_for_each_dev(usbport_data, usbport_trig_add_usb_dev_ports);
 	usbport_trig_update_count(usbport_data);
 
 	/* Notifications */
-	usbport_data->nb.notifier_call = usbport_trig_notify,
-	led_cdev->trigger_data = usbport_data;
+	usbport_data->nb.notifier_call = usbport_trig_notify;
+	led_set_trigger_data(led_cdev, usbport_data);
 	usb_register_notify(&usbport_data->nb);
 
-	led_cdev->activated = true;
-	return;
-
-err_free:
-	kfree(usbport_data);
+	return 0;
 }
 
 static void usbport_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct usbport_trig_data *usbport_data = led_cdev->trigger_data;
+	struct usbport_trig_data *usbport_data = led_get_trigger_data(led_cdev);
 	struct usbport_trig_port *port, *tmp;
 
-	if (!led_cdev->activated)
-		return;
-
 	list_for_each_entry_safe(port, tmp, &usbport_data->ports, list) {
 		usbport_trig_remove_port(usbport_data, port);
 	}
 
 	usb_unregister_notify(&usbport_data->nb);
 
-	sysfs_remove_group(&led_cdev->dev->kobj, &ports_group);
-
 	kfree(usbport_data);
-
-	led_cdev->activated = false;
 }
 
 static struct led_trigger usbport_led_trigger = {
 	.name     = "usbport",
 	.activate = usbport_trig_activate,
 	.deactivate = usbport_trig_deactivate,
+	.groups = ports_groups,
 };
 
 static int __init usbport_trig_init(void)
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index c55def2f1320..097057d2eacf 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -378,6 +378,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Corsair K70 RGB */
 	{ USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT },
 
+	/* Corsair Strafe */
+	{ USB_DEVICE(0x1b1c, 0x1b15), .driver_info = USB_QUIRK_DELAY_INIT |
+	  USB_QUIRK_DELAY_CTRL_MSG },
+
 	/* Corsair Strafe RGB */
 	{ USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT |
 	  USB_QUIRK_DELAY_CTRL_MSG },
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index 4a56ac772a3c..71b3b08ad516 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -1004,6 +1004,7 @@ struct dwc2_hregs_backup {
  * @frame_list_sz:      Frame list size
  * @desc_gen_cache:     Kmem cache for generic descriptors
  * @desc_hsisoc_cache:  Kmem cache for hs isochronous descriptors
+ * @unaligned_cache:    Kmem cache for DMA mode to handle non-aligned buf
  *
  * These are for peripheral mode:
  *
@@ -1177,6 +1178,8 @@ struct dwc2_hsotg {
 	u32 frame_list_sz;
 	struct kmem_cache *desc_gen_cache;
 	struct kmem_cache *desc_hsisoc_cache;
+	struct kmem_cache *unaligned_cache;
+#define DWC2_KMEM_UNALIGNED_BUF_SIZE 1024
 
 #endif /* CONFIG_USB_DWC2_HOST || CONFIG_USB_DWC2_DUAL_ROLE */
 
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index f0d9ccf1d665..cefc99ae69b2 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -812,6 +812,7 @@ static int dwc2_gadget_fill_isoc_desc(struct dwc2_hsotg_ep *hs_ep,
 	u32 index;
 	u32 maxsize = 0;
 	u32 mask = 0;
+	u8 pid = 0;
 
 	maxsize = dwc2_gadget_get_desc_params(hs_ep, &mask);
 
@@ -840,7 +841,11 @@ static int dwc2_gadget_fill_isoc_desc(struct dwc2_hsotg_ep *hs_ep,
 			 ((len << DEV_DMA_NBYTES_SHIFT) & mask));
 
 	if (hs_ep->dir_in) {
-		desc->status |= ((hs_ep->mc << DEV_DMA_ISOC_PID_SHIFT) &
+		if (len)
+			pid = DIV_ROUND_UP(len, hs_ep->ep.maxpacket);
+		else
+			pid = 1;
+		desc->status |= ((pid << DEV_DMA_ISOC_PID_SHIFT) &
 				 DEV_DMA_ISOC_PID_MASK) |
 				((len % hs_ep->ep.maxpacket) ?
 				 DEV_DMA_SHORT : 0) |
@@ -884,6 +889,7 @@ static void dwc2_gadget_start_isoc_ddma(struct dwc2_hsotg_ep *hs_ep)
 	struct dwc2_dma_desc *desc;
 
 	if (list_empty(&hs_ep->queue)) {
+		hs_ep->target_frame = TARGET_FRAME_INITIAL;
 		dev_dbg(hsotg->dev, "%s: No requests in queue\n", __func__);
 		return;
 	}
@@ -2755,8 +2761,6 @@ static void dwc2_gadget_handle_out_token_ep_disabled(struct dwc2_hsotg_ep *ep)
 	 */
 	tmp = dwc2_hsotg_read_frameno(hsotg);
 
-	dwc2_hsotg_complete_request(hsotg, ep, get_ep_head(ep), 0);
-
 	if (using_desc_dma(hsotg)) {
 		if (ep->target_frame == TARGET_FRAME_INITIAL) {
 			/* Start first ISO Out */
@@ -2817,9 +2821,6 @@ static void dwc2_gadget_handle_nak(struct dwc2_hsotg_ep *hs_ep)
 
 		tmp = dwc2_hsotg_read_frameno(hsotg);
 		if (using_desc_dma(hsotg)) {
-			dwc2_hsotg_complete_request(hsotg, hs_ep,
-						    get_ep_head(hs_ep), 0);
-
 			hs_ep->target_frame = tmp;
 			dwc2_gadget_incr_frame_num(hs_ep);
 			dwc2_gadget_start_isoc_ddma(hs_ep);
@@ -3429,7 +3430,7 @@ static void dwc2_gadget_handle_incomplete_isoc_in(struct dwc2_hsotg *hsotg)
 	for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 		hs_ep = hsotg->eps_in[idx];
 		/* Proceed only unmasked ISOC EPs */
-		if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+		if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
 			continue;
 
 		epctrl = dwc2_readl(hsotg->regs + DIEPCTL(idx));
@@ -3475,7 +3476,7 @@ static void dwc2_gadget_handle_incomplete_isoc_out(struct dwc2_hsotg *hsotg)
 	for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 		hs_ep = hsotg->eps_out[idx];
 		/* Proceed only unmasked ISOC EPs */
-		if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+		if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
 			continue;
 
 		epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx));
@@ -3649,7 +3650,7 @@ irq_retry:
 		for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 			hs_ep = hsotg->eps_out[idx];
 			/* Proceed only unmasked ISOC EPs */
-			if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+			if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
 				continue;
 
 			epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx));
@@ -4739,9 +4740,11 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg)
 	}
 
 	ret = usb_add_gadget_udc(dev, &hsotg->gadget);
-	if (ret)
+	if (ret) {
+		dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep,
+					   hsotg->ctrl_req);
 		return ret;
-
+	}
 	dwc2_hsotg_dump(hsotg);
 
 	return 0;
@@ -4755,6 +4758,7 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg)
 int dwc2_hsotg_remove(struct dwc2_hsotg *hsotg)
 {
 	usb_del_gadget_udc(&hsotg->gadget);
+	dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep, hsotg->ctrl_req);
 
 	return 0;
 }
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index edaf0b6af4f0..6e2cdd7b93d4 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -1567,11 +1567,20 @@ static void dwc2_hc_start_transfer(struct dwc2_hsotg *hsotg,
 	}
 
 	if (hsotg->params.host_dma) {
-		dwc2_writel((u32)chan->xfer_dma,
-			    hsotg->regs + HCDMA(chan->hc_num));
+		dma_addr_t dma_addr;
+
+		if (chan->align_buf) {
+			if (dbg_hc(chan))
+				dev_vdbg(hsotg->dev, "align_buf\n");
+			dma_addr = chan->align_buf;
+		} else {
+			dma_addr = chan->xfer_dma;
+		}
+		dwc2_writel((u32)dma_addr, hsotg->regs + HCDMA(chan->hc_num));
+
 		if (dbg_hc(chan))
 			dev_vdbg(hsotg->dev, "Wrote %08lx to HCDMA(%d)\n",
-				 (unsigned long)chan->xfer_dma, chan->hc_num);
+				 (unsigned long)dma_addr, chan->hc_num);
 	}
 
 	/* Start the split */
@@ -2625,36 +2634,66 @@ static void dwc2_hc_init_xfer(struct dwc2_hsotg *hsotg,
 	}
 }
 
-#define DWC2_USB_DMA_ALIGN 4
+static int dwc2_alloc_split_dma_aligned_buf(struct dwc2_hsotg *hsotg,
+					    struct dwc2_qh *qh,
+					    struct dwc2_host_chan *chan)
+{
+	if (!hsotg->unaligned_cache ||
+	    chan->max_packet > DWC2_KMEM_UNALIGNED_BUF_SIZE)
+		return -ENOMEM;
 
-struct dma_aligned_buffer {
-	void *kmalloc_ptr;
-	void *old_xfer_buffer;
-	u8 data[0];
-};
+	if (!qh->dw_align_buf) {
+		qh->dw_align_buf = kmem_cache_alloc(hsotg->unaligned_cache,
+						    GFP_ATOMIC | GFP_DMA);
+		if (!qh->dw_align_buf)
+			return -ENOMEM;
+	}
+
+	qh->dw_align_buf_dma = dma_map_single(hsotg->dev, qh->dw_align_buf,
+					      DWC2_KMEM_UNALIGNED_BUF_SIZE,
+					      DMA_FROM_DEVICE);
+
+	if (dma_mapping_error(hsotg->dev, qh->dw_align_buf_dma)) {
+		dev_err(hsotg->dev, "can't map align_buf\n");
+		chan->align_buf = 0;
+		return -EINVAL;
+	}
+
+	chan->align_buf = qh->dw_align_buf_dma;
+	return 0;
+}
+
+#define DWC2_USB_DMA_ALIGN 4
 
 static void dwc2_free_dma_aligned_buffer(struct urb *urb)
 {
-	struct dma_aligned_buffer *temp;
+	void *stored_xfer_buffer;
+	size_t length;
 
 	if (!(urb->transfer_flags & URB_ALIGNED_TEMP_BUFFER))
 		return;
 
-	temp = container_of(urb->transfer_buffer,
-			    struct dma_aligned_buffer, data);
+	/* Restore urb->transfer_buffer from the end of the allocated area */
+	memcpy(&stored_xfer_buffer, urb->transfer_buffer +
+	       urb->transfer_buffer_length, sizeof(urb->transfer_buffer));
 
-	if (usb_urb_dir_in(urb))
-		memcpy(temp->old_xfer_buffer, temp->data,
-		       urb->transfer_buffer_length);
-	urb->transfer_buffer = temp->old_xfer_buffer;
-	kfree(temp->kmalloc_ptr);
+	if (usb_urb_dir_in(urb)) {
+		if (usb_pipeisoc(urb->pipe))
+			length = urb->transfer_buffer_length;
+		else
+			length = urb->actual_length;
+
+		memcpy(stored_xfer_buffer, urb->transfer_buffer, length);
+	}
+	kfree(urb->transfer_buffer);
+	urb->transfer_buffer = stored_xfer_buffer;
 
 	urb->transfer_flags &= ~URB_ALIGNED_TEMP_BUFFER;
 }
 
 static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
 {
-	struct dma_aligned_buffer *temp, *kmalloc_ptr;
+	void *kmalloc_ptr;
 	size_t kmalloc_size;
 
 	if (urb->num_sgs || urb->sg ||
@@ -2662,22 +2701,29 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
 	    !((uintptr_t)urb->transfer_buffer & (DWC2_USB_DMA_ALIGN - 1)))
 		return 0;
 
-	/* Allocate a buffer with enough padding for alignment */
+	/*
+	 * Allocate a buffer with enough padding for original transfer_buffer
+	 * pointer. This allocation is guaranteed to be aligned properly for
+	 * DMA
+	 */
 	kmalloc_size = urb->transfer_buffer_length +
-		sizeof(struct dma_aligned_buffer) + DWC2_USB_DMA_ALIGN - 1;
+		sizeof(urb->transfer_buffer);
 
 	kmalloc_ptr = kmalloc(kmalloc_size, mem_flags);
 	if (!kmalloc_ptr)
 		return -ENOMEM;
 
-	/* Position our struct dma_aligned_buffer such that data is aligned */
-	temp = PTR_ALIGN(kmalloc_ptr + 1, DWC2_USB_DMA_ALIGN) - 1;
-	temp->kmalloc_ptr = kmalloc_ptr;
-	temp->old_xfer_buffer = urb->transfer_buffer;
+	/*
+	 * Position value of original urb->transfer_buffer pointer to the end
+	 * of allocation for later referencing
+	 */
+	memcpy(kmalloc_ptr + urb->transfer_buffer_length,
+	       &urb->transfer_buffer, sizeof(urb->transfer_buffer));
+
 	if (usb_urb_dir_out(urb))
-		memcpy(temp->data, urb->transfer_buffer,
+		memcpy(kmalloc_ptr, urb->transfer_buffer,
 		       urb->transfer_buffer_length);
-	urb->transfer_buffer = temp->data;
+	urb->transfer_buffer = kmalloc_ptr;
 
 	urb->transfer_flags |= URB_ALIGNED_TEMP_BUFFER;
 
@@ -2802,6 +2848,32 @@ static int dwc2_assign_and_init_hc(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh)
 	/* Set the transfer attributes */
 	dwc2_hc_init_xfer(hsotg, chan, qtd);
 
+	/* For non-dword aligned buffers */
+	if (hsotg->params.host_dma && qh->do_split &&
+	    chan->ep_is_in && (chan->xfer_dma & 0x3)) {
+		dev_vdbg(hsotg->dev, "Non-aligned buffer\n");
+		if (dwc2_alloc_split_dma_aligned_buf(hsotg, qh, chan)) {
+			dev_err(hsotg->dev,
+				"Failed to allocate memory to handle non-aligned buffer\n");
+			/* Add channel back to free list */
+			chan->align_buf = 0;
+			chan->multi_count = 0;
+			list_add_tail(&chan->hc_list_entry,
+				      &hsotg->free_hc_list);
+			qtd->in_process = 0;
+			qh->channel = NULL;
+			return -ENOMEM;
+		}
+	} else {
+		/*
+		 * We assume that DMA is always aligned in non-split
+		 * case or split out case. Warn if not.
+		 */
+		WARN_ON_ONCE(hsotg->params.host_dma &&
+			     (chan->xfer_dma & 0x3));
+		chan->align_buf = 0;
+	}
+
 	if (chan->ep_type == USB_ENDPOINT_XFER_INT ||
 	    chan->ep_type == USB_ENDPOINT_XFER_ISOC)
 		/*
@@ -5246,6 +5318,19 @@ int dwc2_hcd_init(struct dwc2_hsotg *hsotg)
 		}
 	}
 
+	if (hsotg->params.host_dma) {
+		/*
+		 * Create kmem caches to handle non-aligned buffer
+		 * in Buffer DMA mode.
+		 */
+		hsotg->unaligned_cache = kmem_cache_create("dwc2-unaligned-dma",
+						DWC2_KMEM_UNALIGNED_BUF_SIZE, 4,
+						SLAB_CACHE_DMA, NULL);
+		if (!hsotg->unaligned_cache)
+			dev_err(hsotg->dev,
+				"unable to create dwc2 unaligned cache\n");
+	}
+
 	hsotg->otg_port = 1;
 	hsotg->frame_list = NULL;
 	hsotg->frame_list_dma = 0;
@@ -5280,8 +5365,9 @@ int dwc2_hcd_init(struct dwc2_hsotg *hsotg)
 	return 0;
 
 error4:
-	kmem_cache_destroy(hsotg->desc_gen_cache);
+	kmem_cache_destroy(hsotg->unaligned_cache);
 	kmem_cache_destroy(hsotg->desc_hsisoc_cache);
+	kmem_cache_destroy(hsotg->desc_gen_cache);
 error3:
 	dwc2_hcd_release(hsotg);
 error2:
@@ -5322,8 +5408,9 @@ void dwc2_hcd_remove(struct dwc2_hsotg *hsotg)
 	usb_remove_hcd(hcd);
 	hsotg->priv = NULL;
 
-	kmem_cache_destroy(hsotg->desc_gen_cache);
+	kmem_cache_destroy(hsotg->unaligned_cache);
 	kmem_cache_destroy(hsotg->desc_hsisoc_cache);
+	kmem_cache_destroy(hsotg->desc_gen_cache);
 
 	dwc2_hcd_release(hsotg);
 	usb_put_hcd(hcd);
@@ -5435,7 +5522,7 @@ int dwc2_host_enter_hibernation(struct dwc2_hsotg *hsotg)
 	dwc2_writel(hprt0, hsotg->regs + HPRT0);
 
 	/* Wait for the HPRT0.PrtSusp register field to be set */
-	if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 300))
+	if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 3000))
 		dev_warn(hsotg->dev, "Suspend wasn't generated\n");
 
 	/*
@@ -5616,6 +5703,8 @@ int dwc2_host_exit_hibernation(struct dwc2_hsotg *hsotg, int rem_wakeup,
 		return ret;
 	}
 
+	dwc2_hcd_rem_wakeup(hsotg);
+
 	hsotg->hibernated = 0;
 	hsotg->bus_suspended = 0;
 	hsotg->lx_state = DWC2_L0;
diff --git a/drivers/usb/dwc2/hcd.h b/drivers/usb/dwc2/hcd.h
index 7db1ee7e7a77..5502a501f516 100644
--- a/drivers/usb/dwc2/hcd.h
+++ b/drivers/usb/dwc2/hcd.h
@@ -76,6 +76,8 @@ struct dwc2_qh;
  *                      (micro)frame
  * @xfer_buf:           Pointer to current transfer buffer position
  * @xfer_dma:           DMA address of xfer_buf
+ * @align_buf:          In Buffer DMA mode this will be used if xfer_buf is not
+ *                      DWORD aligned
  * @xfer_len:           Total number of bytes to transfer
  * @xfer_count:         Number of bytes transferred so far
  * @start_pkt_count:    Packet count at start of transfer
@@ -133,6 +135,7 @@ struct dwc2_host_chan {
 
 	u8 *xfer_buf;
 	dma_addr_t xfer_dma;
+	dma_addr_t align_buf;
 	u32 xfer_len;
 	u32 xfer_count;
 	u16 start_pkt_count;
@@ -302,6 +305,9 @@ struct dwc2_hs_transfer_time {
  *                           speed.  Note that this is in "schedule slice" which
  *                           is tightly packed.
  * @ntd:                Actual number of transfer descriptors in a list
+ * @dw_align_buf:       Used instead of original buffer if its physical address
+ *                      is not dword-aligned
+ * @dw_align_buf_dma:   DMA address for dw_align_buf
  * @qtd_list:           List of QTDs for this QH
  * @channel:            Host channel currently processing transfers for this QH
  * @qh_list_entry:      Entry for QH in either the periodic or non-periodic
@@ -350,6 +356,8 @@ struct dwc2_qh {
 	struct dwc2_hs_transfer_time hs_transfers[DWC2_HS_SCHEDULE_UFRAMES];
 	u32 ls_start_schedule_slice;
 	u16 ntd;
+	u8 *dw_align_buf;
+	dma_addr_t dw_align_buf_dma;
 	struct list_head qtd_list;
 	struct dwc2_host_chan *channel;
 	struct list_head qh_list_entry;
diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c
index fbea5e3fb947..8ce10caf3e19 100644
--- a/drivers/usb/dwc2/hcd_intr.c
+++ b/drivers/usb/dwc2/hcd_intr.c
@@ -942,14 +942,21 @@ static int dwc2_xfercomp_isoc_split_in(struct dwc2_hsotg *hsotg,
 	frame_desc = &qtd->urb->iso_descs[qtd->isoc_frame_index];
 	len = dwc2_get_actual_xfer_length(hsotg, chan, chnum, qtd,
 					  DWC2_HC_XFER_COMPLETE, NULL);
-	if (!len) {
+	if (!len && !qtd->isoc_split_offset) {
 		qtd->complete_split = 0;
-		qtd->isoc_split_offset = 0;
 		return 0;
 	}
 
 	frame_desc->actual_length += len;
 
+	if (chan->align_buf) {
+		dev_vdbg(hsotg->dev, "non-aligned buffer\n");
+		dma_unmap_single(hsotg->dev, chan->qh->dw_align_buf_dma,
+				 DWC2_KMEM_UNALIGNED_BUF_SIZE, DMA_FROM_DEVICE);
+		memcpy(qtd->urb->buf + (chan->xfer_dma - qtd->urb->dma),
+		       chan->qh->dw_align_buf, len);
+	}
+
 	qtd->isoc_split_offset += len;
 
 	hctsiz = dwc2_readl(hsotg->regs + HCTSIZ(chnum));
@@ -1224,7 +1231,10 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg,
 	 * avoid interrupt storms we'll wait before retrying if we've got
 	 * several NAKs. If we didn't do this we'd retry directly from the
 	 * interrupt handler and could end up quickly getting another
-	 * interrupt (another NAK), which we'd retry.
+	 * interrupt (another NAK), which we'd retry. Note that we do not
+	 * delay retries for IN parts of control requests, as those are expected
+	 * to complete fairly quickly, and if we delay them we risk confusing
+	 * the device and cause it issue STALL.
 	 *
 	 * Note that in DMA mode software only gets involved to re-send NAKed
 	 * transfers for split transactions, so we only need to apply this
@@ -1237,7 +1247,9 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg,
 			qtd->error_count = 0;
 		qtd->complete_split = 0;
 		qtd->num_naks++;
-		qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY;
+		qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY &&
+				!(chan->ep_type == USB_ENDPOINT_XFER_CONTROL &&
+				  chan->ep_is_in);
 		dwc2_halt_channel(hsotg, chan, qtd, DWC2_HC_XFER_NAK);
 		goto handle_nak_done;
 	}
diff --git a/drivers/usb/dwc2/hcd_queue.c b/drivers/usb/dwc2/hcd_queue.c
index d7c3d6c776d8..301ced1618f8 100644
--- a/drivers/usb/dwc2/hcd_queue.c
+++ b/drivers/usb/dwc2/hcd_queue.c
@@ -383,7 +383,7 @@ static unsigned long *dwc2_get_ls_map(struct dwc2_hsotg *hsotg,
 	/* Get the map and adjust if this is a multi_tt hub */
 	map = qh->dwc_tt->periodic_bitmaps;
 	if (qh->dwc_tt->usb_tt->multi)
-		map += DWC2_ELEMENTS_PER_LS_BITMAP * qh->ttport;
+		map += DWC2_ELEMENTS_PER_LS_BITMAP * (qh->ttport - 1);
 
 	return map;
 }
@@ -1696,6 +1696,9 @@ void dwc2_hcd_qh_free(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh)
 
 	if (qh->desc_list)
 		dwc2_hcd_qh_free_ddma(hsotg, qh);
+	else if (hsotg->unaligned_cache && qh->dw_align_buf)
+		kmem_cache_free(hsotg->unaligned_cache, qh->dw_align_buf);
+
 	kfree(qh);
 }
 
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index ea91310113b9..103807587dc6 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1272,7 +1272,6 @@ static int dwc3_probe(struct platform_device *pdev)
 	if (!dwc->clks)
 		return -ENOMEM;
 
-	dwc->num_clks = ARRAY_SIZE(dwc3_core_clks);
 	dwc->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1307,15 +1306,19 @@ static int dwc3_probe(struct platform_device *pdev)
 	if (IS_ERR(dwc->reset))
 		return PTR_ERR(dwc->reset);
 
-	ret = clk_bulk_get(dev, dwc->num_clks, dwc->clks);
-	if (ret == -EPROBE_DEFER)
-		return ret;
-	/*
-	 * Clocks are optional, but new DT platforms should support all clocks
-	 * as required by the DT-binding.
-	 */
-	if (ret)
-		dwc->num_clks = 0;
+	if (dev->of_node) {
+		dwc->num_clks = ARRAY_SIZE(dwc3_core_clks);
+
+		ret = clk_bulk_get(dev, dwc->num_clks, dwc->clks);
+		if (ret == -EPROBE_DEFER)
+			return ret;
+		/*
+		 * Clocks are optional, but new DT platforms should support all
+		 * clocks as required by the DT-binding.
+		 */
+		if (ret)
+			dwc->num_clks = 0;
+	}
 
 	ret = reset_control_deassert(dwc->reset);
 	if (ret)
diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c
index 6b3ccd542bd7..dbeff5e6ad14 100644
--- a/drivers/usb/dwc3/dwc3-of-simple.c
+++ b/drivers/usb/dwc3/dwc3-of-simple.c
@@ -165,8 +165,9 @@ static int dwc3_of_simple_remove(struct platform_device *pdev)
 
 	reset_control_put(simple->resets);
 
-	pm_runtime_put_sync(dev);
 	pm_runtime_disable(dev);
+	pm_runtime_put_noidle(dev);
+	pm_runtime_set_suspended(dev);
 
 	return 0;
 }
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index c961a94d136b..f57e7c94b8e5 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -34,6 +34,7 @@
 #define PCI_DEVICE_ID_INTEL_GLK			0x31aa
 #define PCI_DEVICE_ID_INTEL_CNPLP		0x9dee
 #define PCI_DEVICE_ID_INTEL_CNPH		0xa36e
+#define PCI_DEVICE_ID_INTEL_ICLLP		0x34ee
 
 #define PCI_INTEL_BXT_DSM_GUID		"732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511"
 #define PCI_INTEL_BXT_FUNC_PMU_PWR	4
@@ -289,6 +290,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_GLK), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPLP), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPH), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICLLP), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), },
 	{  }	/* Terminating Entry */
 };
diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index b0e67ab2f98c..a6d0203e40b6 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -490,6 +490,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 	qcom->dwc3 = of_find_device_by_node(dwc3_np);
 	if (!qcom->dwc3) {
 		dev_err(&pdev->dev, "failed to get dwc3 platform device\n");
+		ret = -ENODEV;
 		goto depopulate;
 	}
 
@@ -547,8 +548,7 @@ static int dwc3_qcom_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int dwc3_qcom_pm_suspend(struct device *dev)
+static int __maybe_unused dwc3_qcom_pm_suspend(struct device *dev)
 {
 	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
 	int ret = 0;
@@ -560,7 +560,7 @@ static int dwc3_qcom_pm_suspend(struct device *dev)
 	return ret;
 }
 
-static int dwc3_qcom_pm_resume(struct device *dev)
+static int __maybe_unused dwc3_qcom_pm_resume(struct device *dev)
 {
 	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
 	int ret;
@@ -571,23 +571,20 @@ static int dwc3_qcom_pm_resume(struct device *dev)
 
 	return ret;
 }
-#endif
 
-#ifdef CONFIG_PM
-static int dwc3_qcom_runtime_suspend(struct device *dev)
+static int __maybe_unused dwc3_qcom_runtime_suspend(struct device *dev)
 {
 	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
 
 	return dwc3_qcom_suspend(qcom);
 }
 
-static int dwc3_qcom_runtime_resume(struct device *dev)
+static int __maybe_unused dwc3_qcom_runtime_resume(struct device *dev)
 {
 	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
 
 	return dwc3_qcom_resume(qcom);
 }
-#endif
 
 static const struct dev_pm_ops dwc3_qcom_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(dwc3_qcom_pm_suspend, dwc3_qcom_pm_resume)
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index c77ff50a88a2..8efde178eef4 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -973,15 +973,12 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc,
 		ret = dwc3_ep0_start_trans(dep);
 	} else if (IS_ALIGNED(req->request.length, dep->endpoint.maxpacket) &&
 		   req->request.length && req->request.zero) {
-		u32	maxpacket;
 
 		ret = usb_gadget_map_request_by_dev(dwc->sysdev,
 				&req->request, dep->number);
 		if (ret)
 			return;
 
-		maxpacket = dep->endpoint.maxpacket;
-
 		/* prepare normal TRB */
 		dwc3_ep0_prepare_one_trb(dep, req->request.dma,
 					 req->request.length,
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index f242c2bcea81..b8a15840b4ff 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1719,6 +1719,8 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 		 */
 		if (w_value && !f->get_alt)
 			break;
+
+		spin_lock(&cdev->lock);
 		value = f->set_alt(f, w_index, w_value);
 		if (value == USB_GADGET_DELAYED_STATUS) {
 			DBG(cdev,
@@ -1728,6 +1730,7 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 			DBG(cdev, "delayed_status count %d\n",
 					cdev->delayed_status);
 		}
+		spin_unlock(&cdev->lock);
 		break;
 	case USB_REQ_GET_INTERFACE:
 		if (ctrl->bRequestType != (USB_DIR_IN|USB_RECIP_INTERFACE))
@@ -1816,7 +1819,6 @@ unknown:
 		if (cdev->use_os_string && cdev->os_desc_config &&
 		    (ctrl->bRequestType & USB_TYPE_VENDOR) &&
 		    ctrl->bRequest == cdev->b_vendor_code) {
-			struct usb_request		*req;
 			struct usb_configuration	*os_desc_cfg;
 			u8				*buf;
 			int				interface;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index dce9d12c7981..3ada83d81bda 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -215,6 +215,7 @@ struct ffs_io_data {
 
 	struct mm_struct *mm;
 	struct work_struct work;
+	struct work_struct cancellation_work;
 
 	struct usb_ep *ep;
 	struct usb_request *req;
@@ -1072,22 +1073,31 @@ ffs_epfile_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static void ffs_aio_cancel_worker(struct work_struct *work)
+{
+	struct ffs_io_data *io_data = container_of(work, struct ffs_io_data,
+						   cancellation_work);
+
+	ENTER();
+
+	usb_ep_dequeue(io_data->ep, io_data->req);
+}
+
 static int ffs_aio_cancel(struct kiocb *kiocb)
 {
 	struct ffs_io_data *io_data = kiocb->private;
-	struct ffs_epfile *epfile = kiocb->ki_filp->private_data;
+	struct ffs_data *ffs = io_data->ffs;
 	int value;
 
 	ENTER();
 
-	spin_lock_irq(&epfile->ffs->eps_lock);
-
-	if (likely(io_data && io_data->ep && io_data->req))
-		value = usb_ep_dequeue(io_data->ep, io_data->req);
-	else
+	if (likely(io_data && io_data->ep && io_data->req)) {
+		INIT_WORK(&io_data->cancellation_work, ffs_aio_cancel_worker);
+		queue_work(ffs->io_completion_wq, &io_data->cancellation_work);
+		value = -EINPROGRESS;
+	} else {
 		value = -EINVAL;
-
-	spin_unlock_irq(&epfile->ffs->eps_lock);
+	}
 
 	return value;
 }
@@ -3253,7 +3263,7 @@ static int ffs_func_setup(struct usb_function *f,
 	__ffs_event_add(ffs, FUNCTIONFS_SETUP);
 	spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags);
 
-	return USB_GADGET_DELAYED_STATUS;
+	return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0;
 }
 
 static bool ffs_func_req_match(struct usb_function *f,
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index d2dc1f00180b..d582921f7257 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -438,14 +438,14 @@ static struct usb_descriptor_header *hs_audio_desc[] = {
 };
 
 struct cntrl_cur_lay3 {
-	__u32	dCUR;
+	__le32	dCUR;
 };
 
 struct cntrl_range_lay3 {
-	__u16	wNumSubRanges;
-	__u32	dMIN;
-	__u32	dMAX;
-	__u32	dRES;
+	__le16	wNumSubRanges;
+	__le32	dMIN;
+	__le32	dMAX;
+	__le32	dRES;
 } __packed;
 
 static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
@@ -559,13 +559,13 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn)
 	agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc);
 	if (!agdev->out_ep) {
 		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
-		return ret;
+		return -ENODEV;
 	}
 
 	agdev->in_ep = usb_ep_autoconfig(gadget, &fs_epin_desc);
 	if (!agdev->in_ep) {
 		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
-		return ret;
+		return -ENODEV;
 	}
 
 	agdev->in_ep_maxpsize = max_t(u16,
@@ -703,9 +703,9 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr)
 		memset(&c, 0, sizeof(struct cntrl_cur_lay3));
 
 		if (entity_id == USB_IN_CLK_ID)
-			c.dCUR = p_srate;
+			c.dCUR = cpu_to_le32(p_srate);
 		else if (entity_id == USB_OUT_CLK_ID)
-			c.dCUR = c_srate;
+			c.dCUR = cpu_to_le32(c_srate);
 
 		value = min_t(unsigned, w_length, sizeof c);
 		memcpy(req->buf, &c, value);
@@ -742,15 +742,15 @@ in_rq_range(struct usb_function *fn, const struct usb_ctrlrequest *cr)
 
 	if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) {
 		if (entity_id == USB_IN_CLK_ID)
-			r.dMIN = p_srate;
+			r.dMIN = cpu_to_le32(p_srate);
 		else if (entity_id == USB_OUT_CLK_ID)
-			r.dMIN = c_srate;
+			r.dMIN = cpu_to_le32(c_srate);
 		else
 			return -EOPNOTSUPP;
 
 		r.dMAX = r.dMIN;
 		r.dRES = 0;
-		r.wNumSubRanges = 1;
+		r.wNumSubRanges = cpu_to_le16(1);
 
 		value = min_t(unsigned, w_length, sizeof r);
 		memcpy(req->buf, &r, value);
diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c
index a72295c953bb..fb5ed97572e5 100644
--- a/drivers/usb/gadget/function/u_audio.c
+++ b/drivers/usb/gadget/function/u_audio.c
@@ -32,9 +32,6 @@ struct uac_req {
 struct uac_rtd_params {
 	struct snd_uac_chip *uac; /* parent chip */
 	bool ep_enabled; /* if the ep is enabled */
-	/* Size of the ring buffer */
-	size_t dma_bytes;
-	unsigned char *dma_area;
 
 	struct snd_pcm_substream *ss;
 
@@ -43,8 +40,6 @@ struct uac_rtd_params {
 
 	void *rbuf;
 
-	size_t period_size;
-
 	unsigned max_psize;	/* MaxPacketSize of endpoint */
 	struct uac_req *ureq;
 
@@ -84,12 +79,12 @@ static const struct snd_pcm_hardware uac_pcm_hardware = {
 static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
 {
 	unsigned pending;
-	unsigned long flags;
+	unsigned long flags, flags2;
 	unsigned int hw_ptr;
-	bool update_alsa = false;
 	int status = req->status;
 	struct uac_req *ur = req->context;
 	struct snd_pcm_substream *substream;
+	struct snd_pcm_runtime *runtime;
 	struct uac_rtd_params *prm = ur->pp;
 	struct snd_uac_chip *uac = prm->uac;
 
@@ -111,6 +106,14 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
 	if (!substream)
 		goto exit;
 
+	snd_pcm_stream_lock_irqsave(substream, flags2);
+
+	runtime = substream->runtime;
+	if (!runtime || !snd_pcm_running(substream)) {
+		snd_pcm_stream_unlock_irqrestore(substream, flags2);
+		goto exit;
+	}
+
 	spin_lock_irqsave(&prm->lock, flags);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
@@ -137,43 +140,46 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
 		req->actual = req->length;
 	}
 
-	pending = prm->hw_ptr % prm->period_size;
-	pending += req->actual;
-	if (pending >= prm->period_size)
-		update_alsa = true;
-
 	hw_ptr = prm->hw_ptr;
-	prm->hw_ptr = (prm->hw_ptr + req->actual) % prm->dma_bytes;
 
 	spin_unlock_irqrestore(&prm->lock, flags);
 
 	/* Pack USB load in ALSA ring buffer */
-	pending = prm->dma_bytes - hw_ptr;
+	pending = runtime->dma_bytes - hw_ptr;
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		if (unlikely(pending < req->actual)) {
-			memcpy(req->buf, prm->dma_area + hw_ptr, pending);
-			memcpy(req->buf + pending, prm->dma_area,
+			memcpy(req->buf, runtime->dma_area + hw_ptr, pending);
+			memcpy(req->buf + pending, runtime->dma_area,
 			       req->actual - pending);
 		} else {
-			memcpy(req->buf, prm->dma_area + hw_ptr, req->actual);
+			memcpy(req->buf, runtime->dma_area + hw_ptr,
+			       req->actual);
 		}
 	} else {
 		if (unlikely(pending < req->actual)) {
-			memcpy(prm->dma_area + hw_ptr, req->buf, pending);
-			memcpy(prm->dma_area, req->buf + pending,
+			memcpy(runtime->dma_area + hw_ptr, req->buf, pending);
+			memcpy(runtime->dma_area, req->buf + pending,
 			       req->actual - pending);
 		} else {
-			memcpy(prm->dma_area + hw_ptr, req->buf, req->actual);
+			memcpy(runtime->dma_area + hw_ptr, req->buf,
+			       req->actual);
 		}
 	}
 
+	spin_lock_irqsave(&prm->lock, flags);
+	/* update hw_ptr after data is copied to memory */
+	prm->hw_ptr = (hw_ptr + req->actual) % runtime->dma_bytes;
+	hw_ptr = prm->hw_ptr;
+	spin_unlock_irqrestore(&prm->lock, flags);
+	snd_pcm_stream_unlock_irqrestore(substream, flags2);
+
+	if ((hw_ptr % snd_pcm_lib_period_bytes(substream)) < req->actual)
+		snd_pcm_period_elapsed(substream);
+
 exit:
 	if (usb_ep_queue(ep, req, GFP_ATOMIC))
 		dev_err(uac->card->dev, "%d Error!\n", __LINE__);
-
-	if (update_alsa)
-		snd_pcm_period_elapsed(substream);
 }
 
 static int uac_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
@@ -236,40 +242,12 @@ static snd_pcm_uframes_t uac_pcm_pointer(struct snd_pcm_substream *substream)
 static int uac_pcm_hw_params(struct snd_pcm_substream *substream,
 			       struct snd_pcm_hw_params *hw_params)
 {
-	struct snd_uac_chip *uac = snd_pcm_substream_chip(substream);
-	struct uac_rtd_params *prm;
-	int err;
-
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		prm = &uac->p_prm;
-	else
-		prm = &uac->c_prm;
-
-	err = snd_pcm_lib_malloc_pages(substream,
+	return snd_pcm_lib_malloc_pages(substream,
 					params_buffer_bytes(hw_params));
-	if (err >= 0) {
-		prm->dma_bytes = substream->runtime->dma_bytes;
-		prm->dma_area = substream->runtime->dma_area;
-		prm->period_size = params_period_bytes(hw_params);
-	}
-
-	return err;
 }
 
 static int uac_pcm_hw_free(struct snd_pcm_substream *substream)
 {
-	struct snd_uac_chip *uac = snd_pcm_substream_chip(substream);
-	struct uac_rtd_params *prm;
-
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		prm = &uac->p_prm;
-	else
-		prm = &uac->c_prm;
-
-	prm->dma_area = NULL;
-	prm->dma_bytes = 0;
-	prm->period_size = 0;
-
 	return snd_pcm_lib_free_pages(substream);
 }
 
@@ -595,15 +573,15 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name,
 	if (err < 0)
 		goto snd_fail;
 
-	strcpy(pcm->name, pcm_name);
+	strlcpy(pcm->name, pcm_name, sizeof(pcm->name));
 	pcm->private_data = uac;
 	uac->pcm = pcm;
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &uac_pcm_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &uac_pcm_ops);
 
-	strcpy(card->driver, card_name);
-	strcpy(card->shortname, card_name);
+	strlcpy(card->driver, card_name, sizeof(card->driver));
+	strlcpy(card->shortname, card_name, sizeof(card->shortname));
 	sprintf(card->longname, "%s %i", card_name, card->dev->id);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/Kconfig b/drivers/usb/gadget/udc/aspeed-vhub/Kconfig
index f0cdf89b8503..83ba8a2eb6af 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/Kconfig
+++ b/drivers/usb/gadget/udc/aspeed-vhub/Kconfig
@@ -2,6 +2,7 @@
 config USB_ASPEED_VHUB
 	tristate "Aspeed vHub UDC driver"
 	depends on ARCH_ASPEED || COMPILE_TEST
+	depends on USB_LIBCOMPOSITE
 	help
 	  USB peripheral controller for the Aspeed AST2500 family
 	  SoCs supporting the "vHub" functionality and USB2.0
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
index 20ffb03ff6ac..e2927fb083cf 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
@@ -108,6 +108,13 @@ void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep)
 	/* Check our state, cancel pending requests if needed */
 	if (ep->ep0.state != ep0_state_token) {
 		EPDBG(ep, "wrong state\n");
+		ast_vhub_nuke(ep, -EIO);
+
+		/*
+		 * Accept the packet regardless, this seems to happen
+		 * when stalling a SETUP packet that has an OUT data
+		 * phase.
+		 */
 		ast_vhub_nuke(ep, 0);
 		goto stall;
 	}
@@ -212,6 +219,8 @@ static void ast_vhub_ep0_do_send(struct ast_vhub_ep *ep,
 	if (chunk && req->req.buf)
 		memcpy(ep->buf, req->req.buf + req->req.actual, chunk);
 
+	vhub_dma_workaround(ep->buf);
+
 	/* Remember chunk size and trigger send */
 	reg = VHUB_EP0_SET_TX_LEN(chunk);
 	writel(reg, ep->ep0.ctlstat);
@@ -224,7 +233,7 @@ static void ast_vhub_ep0_rx_prime(struct ast_vhub_ep *ep)
 	EPVDBG(ep, "rx prime\n");
 
 	/* Prime endpoint for receiving data */
-	writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL);
+	writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat);
 }
 
 static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c
index 80c9feac5147..5939eb1e97f2 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c
@@ -66,11 +66,16 @@ static void ast_vhub_epn_kick(struct ast_vhub_ep *ep, struct ast_vhub_req *req)
 	if (!req->req.dma) {
 
 		/* For IN transfers, copy data over first */
-		if (ep->epn.is_in)
+		if (ep->epn.is_in) {
 			memcpy(ep->buf, req->req.buf + act, chunk);
+			vhub_dma_workaround(ep->buf);
+		}
 		writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
-	} else
+	} else {
+		if (ep->epn.is_in)
+			vhub_dma_workaround(req->req.buf);
 		writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
+	}
 
 	/* Start DMA */
 	req->active = true;
@@ -161,6 +166,7 @@ static inline unsigned int ast_vhub_count_free_descs(struct ast_vhub_ep *ep)
 static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 				   struct ast_vhub_req *req)
 {
+	struct ast_vhub_desc *desc = NULL;
 	unsigned int act = req->act_count;
 	unsigned int len = req->req.length;
 	unsigned int chunk;
@@ -177,7 +183,6 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 
 	/* While we can create descriptors */
 	while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) {
-		struct ast_vhub_desc *desc;
 		unsigned int d_num;
 
 		/* Grab next free descriptor */
@@ -227,6 +232,9 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 		req->act_count = act = act + chunk;
 	}
 
+	if (likely(desc))
+		vhub_dma_workaround(desc);
+
 	/* Tell HW about new descriptors */
 	writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next),
 	       ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
index 2b040257bc1f..4ed03d33a5a9 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
+++ b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
@@ -462,6 +462,39 @@ enum std_req_rc {
 #define DDBG(d, fmt, ...)	do { } while(0)
 #endif
 
+static inline void vhub_dma_workaround(void *addr)
+{
+	/*
+	 * This works around a confirmed HW issue with the Aspeed chip.
+	 *
+	 * The core uses a different bus to memory than the AHB going to
+	 * the USB device controller. Due to the latter having a higher
+	 * priority than the core for arbitration on that bus, it's
+	 * possible for an MMIO to the device, followed by a DMA by the
+	 * device from memory to all be performed and services before
+	 * a previous store to memory gets completed.
+	 *
+	 * This the following scenario can happen:
+	 *
+	 *    - Driver writes to a DMA descriptor (Mbus)
+	 *    - Driver writes to the MMIO register to start the DMA (AHB)
+	 *    - The gadget sees the second write and sends a read of the
+	 *      descriptor to the memory controller (Mbus)
+	 *    - The gadget hits memory before the descriptor write
+	 *      causing it to read an obsolete value.
+	 *
+	 * Thankfully the problem is limited to the USB gadget device, other
+	 * masters in the SoC all have a lower priority than the core, thus
+	 * ensuring that the store by the core arrives first.
+	 *
+	 * The workaround consists of using a dummy read of the memory before
+	 * doing the MMIO writes. This will ensure that the previous writes
+	 * have been "pushed out".
+	 */
+	mb();
+	(void)__raw_readl((void __iomem *)addr);
+}
+
 /* core.c */
 void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
 		   int status);
diff --git a/drivers/usb/gadget/udc/r8a66597-udc.c b/drivers/usb/gadget/udc/r8a66597-udc.c
index a3ecce62662b..11e25a3f4f1f 100644
--- a/drivers/usb/gadget/udc/r8a66597-udc.c
+++ b/drivers/usb/gadget/udc/r8a66597-udc.c
@@ -832,11 +832,11 @@ static void init_controller(struct r8a66597 *r8a66597)
 
 		r8a66597_bset(r8a66597, XCKE, SYSCFG0);
 
-		msleep(3);
+		mdelay(3);
 
 		r8a66597_bset(r8a66597, PLLC, SYSCFG0);
 
-		msleep(1);
+		mdelay(1);
 
 		r8a66597_bset(r8a66597, SCKE, SYSCFG0);
 
@@ -1190,7 +1190,7 @@ __acquires(r8a66597->lock)
 	r8a66597->ep0_req->length = 2;
 	/* AV: what happens if we get called again before that gets through? */
 	spin_unlock(&r8a66597->lock);
-	r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_KERNEL);
+	r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_ATOMIC);
 	spin_lock(&r8a66597->lock);
 }
 
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 1fbfd89d0a0f..387f124a8334 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -508,16 +508,18 @@ static int xhci_do_dbc_start(struct xhci_hcd *xhci)
 	return 0;
 }
 
-static void xhci_do_dbc_stop(struct xhci_hcd *xhci)
+static int xhci_do_dbc_stop(struct xhci_hcd *xhci)
 {
 	struct xhci_dbc		*dbc = xhci->dbc;
 
 	if (dbc->state == DS_DISABLED)
-		return;
+		return -1;
 
 	writel(0, &dbc->regs->control);
 	xhci_dbc_mem_cleanup(xhci);
 	dbc->state = DS_DISABLED;
+
+	return 0;
 }
 
 static int xhci_dbc_start(struct xhci_hcd *xhci)
@@ -544,6 +546,7 @@ static int xhci_dbc_start(struct xhci_hcd *xhci)
 
 static void xhci_dbc_stop(struct xhci_hcd *xhci)
 {
+	int ret;
 	unsigned long		flags;
 	struct xhci_dbc		*dbc = xhci->dbc;
 	struct dbc_port		*port = &dbc->port;
@@ -556,10 +559,11 @@ static void xhci_dbc_stop(struct xhci_hcd *xhci)
 		xhci_dbc_tty_unregister_device(xhci);
 
 	spin_lock_irqsave(&dbc->lock, flags);
-	xhci_do_dbc_stop(xhci);
+	ret = xhci_do_dbc_stop(xhci);
 	spin_unlock_irqrestore(&dbc->lock, flags);
 
-	pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller);
+	if (!ret)
+		pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller);
 }
 
 static void
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index acbd3d7b8828..ef350c33dc4a 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -595,7 +595,7 @@ struct xhci_ring *xhci_stream_id_to_ring(
 	if (!ep->stream_info)
 		return NULL;
 
-	if (stream_id > ep->stream_info->num_streams)
+	if (stream_id >= ep->stream_info->num_streams)
 		return NULL;
 	return ep->stream_info->stream_rings[stream_id];
 }
@@ -886,12 +886,12 @@ void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id)
 
 	dev = xhci->devs[slot_id];
 
-	trace_xhci_free_virt_device(dev);
-
 	xhci->dcbaa->dev_context_ptrs[slot_id] = 0;
 	if (!dev)
 		return;
 
+	trace_xhci_free_virt_device(dev);
+
 	if (dev->tt_info)
 		old_active_eps = dev->tt_info->active_eps;
 
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index a8c1d073cba0..4b463e5202a4 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -481,7 +481,7 @@ static void tegra_xusb_mbox_handle(struct tegra_xusb *tegra,
 	unsigned long mask;
 	unsigned int port;
 	bool idle, enable;
-	int err;
+	int err = 0;
 
 	memset(&rsp, 0, sizeof(rsp));
 
@@ -1223,10 +1223,10 @@ disable_rpm:
 	pm_runtime_disable(&pdev->dev);
 	usb_put_hcd(tegra->hcd);
 disable_xusbc:
-	if (!&pdev->dev.pm_domain)
+	if (!pdev->dev.pm_domain)
 		tegra_powergate_power_off(TEGRA_POWERGATE_XUSBC);
 disable_xusba:
-	if (!&pdev->dev.pm_domain)
+	if (!pdev->dev.pm_domain)
 		tegra_powergate_power_off(TEGRA_POWERGATE_XUSBA);
 put_padctl:
 	tegra_xusb_padctl_put(tegra->padctl);
diff --git a/drivers/usb/host/xhci-trace.h b/drivers/usb/host/xhci-trace.h
index 410544ffe78f..88b427434bd8 100644
--- a/drivers/usb/host/xhci-trace.h
+++ b/drivers/usb/host/xhci-trace.h
@@ -171,6 +171,37 @@ DEFINE_EVENT(xhci_log_trb, xhci_dbc_gadget_ep_queue,
 	TP_ARGS(ring, trb)
 );
 
+DECLARE_EVENT_CLASS(xhci_log_free_virt_dev,
+	TP_PROTO(struct xhci_virt_device *vdev),
+	TP_ARGS(vdev),
+	TP_STRUCT__entry(
+		__field(void *, vdev)
+		__field(unsigned long long, out_ctx)
+		__field(unsigned long long, in_ctx)
+		__field(u8, fake_port)
+		__field(u8, real_port)
+		__field(u16, current_mel)
+
+	),
+	TP_fast_assign(
+		__entry->vdev = vdev;
+		__entry->in_ctx = (unsigned long long) vdev->in_ctx->dma;
+		__entry->out_ctx = (unsigned long long) vdev->out_ctx->dma;
+		__entry->fake_port = (u8) vdev->fake_port;
+		__entry->real_port = (u8) vdev->real_port;
+		__entry->current_mel = (u16) vdev->current_mel;
+		),
+	TP_printk("vdev %p ctx %llx | %llx fake_port %d real_port %d current_mel %d",
+		__entry->vdev, __entry->in_ctx, __entry->out_ctx,
+		__entry->fake_port, __entry->real_port, __entry->current_mel
+	)
+);
+
+DEFINE_EVENT(xhci_log_free_virt_dev, xhci_free_virt_device,
+	TP_PROTO(struct xhci_virt_device *vdev),
+	TP_ARGS(vdev)
+);
+
 DECLARE_EVENT_CLASS(xhci_log_virt_dev,
 	TP_PROTO(struct xhci_virt_device *vdev),
 	TP_ARGS(vdev),
@@ -208,11 +239,6 @@ DEFINE_EVENT(xhci_log_virt_dev, xhci_alloc_virt_device,
 	TP_ARGS(vdev)
 );
 
-DEFINE_EVENT(xhci_log_virt_dev, xhci_free_virt_device,
-	TP_PROTO(struct xhci_virt_device *vdev),
-	TP_ARGS(vdev)
-);
-
 DEFINE_EVENT(xhci_log_virt_dev, xhci_setup_device,
 	TP_PROTO(struct xhci_virt_device *vdev),
 	TP_ARGS(vdev)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 8c8da2d657fa..68e6132aa8b2 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -908,6 +908,41 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
 	spin_unlock_irqrestore(&xhci->lock, flags);
 }
 
+static bool xhci_pending_portevent(struct xhci_hcd *xhci)
+{
+	struct xhci_port	**ports;
+	int			port_index;
+	u32			status;
+	u32			portsc;
+
+	status = readl(&xhci->op_regs->status);
+	if (status & STS_EINT)
+		return true;
+	/*
+	 * Checking STS_EINT is not enough as there is a lag between a change
+	 * bit being set and the Port Status Change Event that it generated
+	 * being written to the Event Ring. See note in xhci 1.1 section 4.19.2.
+	 */
+
+	port_index = xhci->usb2_rhub.num_ports;
+	ports = xhci->usb2_rhub.ports;
+	while (port_index--) {
+		portsc = readl(ports[port_index]->addr);
+		if (portsc & PORT_CHANGE_MASK ||
+		    (portsc & PORT_PLS_MASK) == XDEV_RESUME)
+			return true;
+	}
+	port_index = xhci->usb3_rhub.num_ports;
+	ports = xhci->usb3_rhub.ports;
+	while (port_index--) {
+		portsc = readl(ports[port_index]->addr);
+		if (portsc & PORT_CHANGE_MASK ||
+		    (portsc & PORT_PLS_MASK) == XDEV_RESUME)
+			return true;
+	}
+	return false;
+}
+
 /*
  * Stop HC (not bus-specific)
  *
@@ -1009,7 +1044,7 @@ EXPORT_SYMBOL_GPL(xhci_suspend);
  */
 int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 {
-	u32			command, temp = 0, status;
+	u32			command, temp = 0;
 	struct usb_hcd		*hcd = xhci_to_hcd(xhci);
 	struct usb_hcd		*secondary_hcd;
 	int			retval = 0;
@@ -1043,8 +1078,13 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 		command = readl(&xhci->op_regs->command);
 		command |= CMD_CRS;
 		writel(command, &xhci->op_regs->command);
+		/*
+		 * Some controllers take up to 55+ ms to complete the controller
+		 * restore so setting the timeout to 100ms. Xhci specification
+		 * doesn't mention any timeout value.
+		 */
 		if (xhci_handshake(&xhci->op_regs->status,
-			      STS_RESTORE, 0, 10 * 1000)) {
+			      STS_RESTORE, 0, 100 * 1000)) {
 			xhci_warn(xhci, "WARN: xHC restore state timeout\n");
 			spin_unlock_irq(&xhci->lock);
 			return -ETIMEDOUT;
@@ -1134,8 +1174,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
  done:
 	if (retval == 0) {
 		/* Resume root hubs only when have pending events. */
-		status = readl(&xhci->op_regs->status);
-		if (status & STS_EINT) {
+		if (xhci_pending_portevent(xhci)) {
 			usb_hcd_resume_root_hub(xhci->shared_hcd);
 			usb_hcd_resume_root_hub(hcd);
 		}
@@ -3012,6 +3051,7 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 	if (!list_empty(&ep->ring->td_list)) {
 		dev_err(&udev->dev, "EP not empty, refuse reset\n");
 		spin_unlock_irqrestore(&xhci->lock, flags);
+		xhci_free_command(xhci, cfg_cmd);
 		goto cleanup;
 	}
 	xhci_queue_stop_endpoint(xhci, stop_cmd, udev->slot_id, ep_index, 0);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 939e2f86b595..841e89ffe2e9 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -382,6 +382,10 @@ struct xhci_op_regs {
 #define PORT_PLC	(1 << 22)
 /* port configure error change - port failed to configure its link partner */
 #define PORT_CEC	(1 << 23)
+#define PORT_CHANGE_MASK	(PORT_CSC | PORT_PEC | PORT_WRC | PORT_OCC | \
+				 PORT_RC | PORT_PLC | PORT_CEC)
+
+
 /* Cold Attach Status - xHC can set this bit to report device attached during
  * Sx state. Warm port reset should be perfomed to clear this bit and move port
  * to connected state.
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 8abb6cbbd98a..3be40eaa1ac9 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -396,8 +396,7 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 			  loff_t *ppos)
 {
 	struct usb_yurex *dev;
-	int retval = 0;
-	int bytes_read = 0;
+	int len = 0;
 	char in_buffer[20];
 	unsigned long flags;
 
@@ -405,26 +404,16 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 
 	mutex_lock(&dev->io_mutex);
 	if (!dev->interface) {		/* already disconnected */
-		retval = -ENODEV;
-		goto exit;
+		mutex_unlock(&dev->io_mutex);
+		return -ENODEV;
 	}
 
 	spin_lock_irqsave(&dev->lock, flags);
-	bytes_read = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
+	len = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
 	spin_unlock_irqrestore(&dev->lock, flags);
-
-	if (*ppos < bytes_read) {
-		if (copy_to_user(buffer, in_buffer + *ppos, bytes_read - *ppos))
-			retval = -EFAULT;
-		else {
-			retval = bytes_read - *ppos;
-			*ppos += bytes_read;
-		}
-	}
-
-exit:
 	mutex_unlock(&dev->io_mutex);
-	return retval;
+
+	return simple_read_from_buffer(buffer, count, ppos, in_buffer, len);
 }
 
 static ssize_t yurex_write(struct file *file, const char __user *user_buffer,
diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c
index 900875f326d7..f7c96d209eda 100644
--- a/drivers/usb/phy/phy-fsl-usb.c
+++ b/drivers/usb/phy/phy-fsl-usb.c
@@ -861,6 +861,7 @@ int usb_otg_start(struct platform_device *pdev)
 	if (pdata->init && pdata->init(pdev) != 0)
 		return -EINVAL;
 
+#ifdef CONFIG_PPC32
 	if (pdata->big_endian_mmio) {
 		_fsl_readl = _fsl_readl_be;
 		_fsl_writel = _fsl_writel_be;
@@ -868,6 +869,7 @@ int usb_otg_start(struct platform_device *pdev)
 		_fsl_readl = _fsl_readl_le;
 		_fsl_writel = _fsl_writel_le;
 	}
+#endif
 
 	/* request irq */
 	p_otg->irq = platform_get_irq(pdev, 0);
@@ -958,7 +960,7 @@ int usb_otg_start(struct platform_device *pdev)
 /*
  * state file in sysfs
  */
-static int show_fsl_usb2_otg_state(struct device *dev,
+static ssize_t show_fsl_usb2_otg_state(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct otg_fsm *fsm = &fsl_otg_dev->fsm;
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index bdd7a5ad3bf1..3bb1fff02bed 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -128,7 +128,7 @@ static int ch341_control_in(struct usb_device *dev,
 	r = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), request,
 			    USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
 			    value, index, buf, bufsize, DEFAULT_TIMEOUT);
-	if (r < bufsize) {
+	if (r < (int)bufsize) {
 		if (r >= 0) {
 			dev_err(&dev->dev,
 				"short control message received (%d < %u)\n",
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index eb6c26cbe579..626a29d9aa58 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -95,6 +95,9 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8156) }, /* B&G H3000 link cable */
 	{ USB_DEVICE(0x10C4, 0x815E) }, /* Helicomm IP-Link 1220-DVM */
 	{ USB_DEVICE(0x10C4, 0x815F) }, /* Timewave HamLinkUSB */
+	{ USB_DEVICE(0x10C4, 0x817C) }, /* CESINEL MEDCAL N Power Quality Monitor */
+	{ USB_DEVICE(0x10C4, 0x817D) }, /* CESINEL MEDCAL NT Power Quality Monitor */
+	{ USB_DEVICE(0x10C4, 0x817E) }, /* CESINEL MEDCAL S Power Quality Monitor */
 	{ USB_DEVICE(0x10C4, 0x818B) }, /* AVIT Research USB to TTL */
 	{ USB_DEVICE(0x10C4, 0x819F) }, /* MJS USB Toslink Switcher */
 	{ USB_DEVICE(0x10C4, 0x81A6) }, /* ThinkOptics WavIt */
@@ -112,6 +115,9 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */
 	{ USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */
 	{ USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */
+	{ USB_DEVICE(0x10C4, 0x82EF) }, /* CESINEL FALCO 6105 AC Power Supply */
+	{ USB_DEVICE(0x10C4, 0x82F1) }, /* CESINEL MEDCAL EFD Earth Fault Detector */
+	{ USB_DEVICE(0x10C4, 0x82F2) }, /* CESINEL MEDCAL ST Network Analyzer */
 	{ USB_DEVICE(0x10C4, 0x82F4) }, /* Starizona MicroTouch */
 	{ USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */
 	{ USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */
@@ -124,7 +130,9 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8470) }, /* Juniper Networks BX Series System Console */
 	{ USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */
 	{ USB_DEVICE(0x10C4, 0x84B6) }, /* Starizona Hyperion */
+	{ USB_DEVICE(0x10C4, 0x851E) }, /* CESINEL MEDCAL PT Network Analyzer */
 	{ USB_DEVICE(0x10C4, 0x85A7) }, /* LifeScan OneTouch Verio IQ */
+	{ USB_DEVICE(0x10C4, 0x85B8) }, /* CESINEL ReCon T Energy Logger */
 	{ USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */
 	{ USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */
 	{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
@@ -134,17 +142,24 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8857) },	/* CEL EM357 ZigBee USB Stick */
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
 	{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
+	{ USB_DEVICE(0x10C4, 0x88FB) }, /* CESINEL MEDCAL STII Network Analyzer */
+	{ USB_DEVICE(0x10C4, 0x8938) }, /* CESINEL MEDCAL S II Network Analyzer */
 	{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
 	{ USB_DEVICE(0x10C4, 0x8962) }, /* Brim Brothers charging dock */
 	{ USB_DEVICE(0x10C4, 0x8977) },	/* CEL MeshWorks DevKit Device */
 	{ USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
+	{ USB_DEVICE(0x10C4, 0x89A4) }, /* CESINEL FTBC Flexible Thyristor Bridge Controller */
+	{ USB_DEVICE(0x10C4, 0x89FB) }, /* Qivicon ZigBee USB Radio Stick */
 	{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
 	{ USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */
 	{ USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */
 	{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
+	{ USB_DEVICE(0x10C4, 0xEA63) }, /* Silicon Labs Windows Update (CP2101-4/CP2102N) */
 	{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA71) }, /* Infinity GPS-MIC-1 Radio Monophone */
+	{ USB_DEVICE(0x10C4, 0xEA7A) }, /* Silicon Labs Windows Update (CP2105) */
+	{ USB_DEVICE(0x10C4, 0xEA7B) }, /* Silicon Labs Windows Update (CP2108) */
 	{ USB_DEVICE(0x10C4, 0xF001) }, /* Elan Digital Systems USBscope50 */
 	{ USB_DEVICE(0x10C4, 0xF002) }, /* Elan Digital Systems USBwave12 */
 	{ USB_DEVICE(0x10C4, 0xF003) }, /* Elan Digital Systems USBpulse100 */
diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c
index 5169624d8b11..38d43c4b7ce5 100644
--- a/drivers/usb/serial/keyspan_pda.c
+++ b/drivers/usb/serial/keyspan_pda.c
@@ -369,8 +369,10 @@ static int keyspan_pda_get_modem_info(struct usb_serial *serial,
 			     3, /* get pins */
 			     USB_TYPE_VENDOR|USB_RECIP_INTERFACE|USB_DIR_IN,
 			     0, 0, data, 1, 2000);
-	if (rc >= 0)
+	if (rc == 1)
 		*value = *data;
+	else if (rc >= 0)
+		rc = -EIO;
 
 	kfree(data);
 	return rc;
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index fdceb46d9fc6..b580b4c7fa48 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -468,6 +468,9 @@ static void mos7840_control_callback(struct urb *urb)
 	}
 
 	dev_dbg(dev, "%s urb buffer size is %d\n", __func__, urb->actual_length);
+	if (urb->actual_length < 1)
+		goto out;
+
 	dev_dbg(dev, "%s mos7840_port->MsrLsr is %d port %d\n", __func__,
 		mos7840_port->MsrLsr, mos7840_port->port_num);
 	data = urb->transfer_buffer;
diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c
index 8a201dd53d36..d1d20252bad8 100644
--- a/drivers/usb/typec/tcpm.c
+++ b/drivers/usb/typec/tcpm.c
@@ -418,17 +418,18 @@ static void _tcpm_log(struct tcpm_port *port, const char *fmt, va_list args)
 	u64 ts_nsec = local_clock();
 	unsigned long rem_nsec;
 
+	mutex_lock(&port->logbuffer_lock);
 	if (!port->logbuffer[port->logbuffer_head]) {
 		port->logbuffer[port->logbuffer_head] =
 				kzalloc(LOG_BUFFER_ENTRY_SIZE, GFP_KERNEL);
-		if (!port->logbuffer[port->logbuffer_head])
+		if (!port->logbuffer[port->logbuffer_head]) {
+			mutex_unlock(&port->logbuffer_lock);
 			return;
+		}
 	}
 
 	vsnprintf(tmpbuffer, sizeof(tmpbuffer), fmt, args);
 
-	mutex_lock(&port->logbuffer_lock);
-
 	if (tcpm_log_full(port)) {
 		port->logbuffer_head = max(port->logbuffer_head - 1, 0);
 		strcpy(tmpbuffer, "overflow");
@@ -724,6 +725,9 @@ static int tcpm_set_current_limit(struct tcpm_port *port, u32 max_ma, u32 mv)
 
 	tcpm_log(port, "Setting voltage/current limit %u mV %u mA", mv, max_ma);
 
+	port->supply_voltage = mv;
+	port->current_limit = max_ma;
+
 	if (port->tcpc->set_current_limit)
 		ret = port->tcpc->set_current_limit(port->tcpc, max_ma, mv);
 
@@ -2136,7 +2140,7 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port)
 			 * PPS APDO. Again skip the first sink PDO as this will
 			 * always be 5V 3A.
 			 */
-			for (j = i; j < port->nr_snk_pdo; j++) {
+			for (j = 1; j < port->nr_snk_pdo; j++) {
 				pdo = port->snk_pdo[j];
 
 				switch (pdo_type(pdo)) {
@@ -2594,8 +2598,6 @@ static void tcpm_reset_port(struct tcpm_port *port)
 	tcpm_set_attached_state(port, false);
 	port->try_src_count = 0;
 	port->try_snk_count = 0;
-	port->supply_voltage = 0;
-	port->current_limit = 0;
 	port->usb_type = POWER_SUPPLY_USB_TYPE_C;
 
 	power_supply_changed(port->psy);
@@ -3043,7 +3045,8 @@ static void run_state_machine(struct tcpm_port *port)
 		    tcpm_port_is_sink(port) &&
 		    time_is_after_jiffies(port->delayed_runtime)) {
 			tcpm_set_state(port, SNK_DISCOVERY,
-				       port->delayed_runtime - jiffies);
+				       jiffies_to_msecs(port->delayed_runtime -
+							jiffies));
 			break;
 		}
 		tcpm_set_state(port, unattached_state(port), 0);
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index bd5cca5632b3..8d0a6fe748bd 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -350,6 +350,19 @@ static void ucsi_connector_change(struct work_struct *work)
 	}
 
 	if (con->status.change & UCSI_CONSTAT_CONNECT_CHANGE) {
+		typec_set_pwr_role(con->port, con->status.pwr_dir);
+
+		switch (con->status.partner_type) {
+		case UCSI_CONSTAT_PARTNER_TYPE_UFP:
+			typec_set_data_role(con->port, TYPEC_HOST);
+			break;
+		case UCSI_CONSTAT_PARTNER_TYPE_DFP:
+			typec_set_data_role(con->port, TYPEC_DEVICE);
+			break;
+		default:
+			break;
+		}
+
 		if (con->status.connected)
 			ucsi_register_partner(con);
 		else
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 44eb4e1ea817..a18112a83fae 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -79,6 +79,11 @@ static int ucsi_acpi_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	/* This will make sure we can use ioremap_nocache() */
+	status = acpi_release_memory(ACPI_HANDLE(&pdev->dev), res, 1);
+	if (ACPI_FAILURE(status))
+		return -ENOMEM;
+
 	/*
 	 * NOTE: The memory region for the data structures is used also in an
 	 * operation region, which means ACPI has already reserved it. Therefore
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 24ee2605b9f0..42dc1d3d71cf 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -28,5 +28,13 @@ config VFIO_PCI_INTX
 	def_bool y if !S390
 
 config VFIO_PCI_IGD
-	depends on VFIO_PCI
-	def_bool y if X86
+	bool "VFIO PCI extensions for Intel graphics (GVT-d)"
+	depends on VFIO_PCI && X86
+	default y
+	help
+	  Support for Intel IGD specific extensions to enable direct
+	  assignment to virtual machines.  This includes exposing an IGD
+	  specific firmware table and read-only copies of the host bridge
+	  and LPC bridge config space.
+
+	  To enable Intel IGD assignment through vfio-pci, say Y.
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index b423a309a6e0..125b58eff936 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -28,6 +28,7 @@
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
 #include <linux/vgaarb.h>
+#include <linux/nospec.h>
 
 #include "vfio_pci_private.h"
 
@@ -727,6 +728,9 @@ static long vfio_pci_ioctl(void *device_data,
 			if (info.index >=
 			    VFIO_PCI_NUM_REGIONS + vdev->num_regions)
 				return -EINVAL;
+			info.index = array_index_nospec(info.index,
+							VFIO_PCI_NUM_REGIONS +
+							vdev->num_regions);
 
 			i = info.index - VFIO_PCI_NUM_REGIONS;
 
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 759a5bdd40e1..7cd63b0c1a46 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -457,17 +457,17 @@ static void tce_iommu_unuse_page(struct tce_container *container,
 }
 
 static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
-		unsigned long tce, unsigned long size,
+		unsigned long tce, unsigned long shift,
 		unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
 {
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem;
 
-	mem = mm_iommu_lookup(container->mm, tce, size);
+	mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift);
 	if (!mem)
 		return -EINVAL;
 
-	ret = mm_iommu_ua_to_hpa(mem, tce, phpa);
+	ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa);
 	if (ret)
 		return -EINVAL;
 
@@ -487,7 +487,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container,
 	if (!pua)
 		return;
 
-	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl),
+	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, tbl->it_page_shift,
 			&hpa, &mem);
 	if (ret)
 		pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n",
@@ -611,7 +611,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 				entry + i);
 
 		ret = tce_iommu_prereg_ua_to_hpa(container,
-				tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
+				tce, tbl->it_page_shift, &hpa, &mem);
 		if (ret)
 			break;
 
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 2c75b33db4ac..3e5b17710a4f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -343,18 +343,16 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 	struct page *page[1];
 	struct vm_area_struct *vma;
 	struct vm_area_struct *vmas[1];
+	unsigned int flags = 0;
 	int ret;
 
+	if (prot & IOMMU_WRITE)
+		flags |= FOLL_WRITE;
+
+	down_read(&mm->mmap_sem);
 	if (mm == current->mm) {
-		ret = get_user_pages_longterm(vaddr, 1, !!(prot & IOMMU_WRITE),
-					      page, vmas);
+		ret = get_user_pages_longterm(vaddr, 1, flags, page, vmas);
 	} else {
-		unsigned int flags = 0;
-
-		if (prot & IOMMU_WRITE)
-			flags |= FOLL_WRITE;
-
-		down_read(&mm->mmap_sem);
 		ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
 					    vmas, NULL);
 		/*
@@ -368,8 +366,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 			ret = -EOPNOTSUPP;
 			put_page(page[0]);
 		}
-		up_read(&mm->mmap_sem);
 	}
+	up_read(&mm->mmap_sem);
 
 	if (ret == 1) {
 		*pfn = page_to_pfn(page[0]);
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 686dc670fd29..29756d88799b 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1226,7 +1226,8 @@ err_used:
 	if (ubufs)
 		vhost_net_ubuf_put_wait_and_free(ubufs);
 err_ubufs:
-	sockfd_put(sock);
+	if (sock)
+		sockfd_put(sock);
 err_vq:
 	mutex_unlock(&vq->mutex);
 err:
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a502f1af4a21..ed3114556fda 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1560,9 +1560,12 @@ int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
 	d->iotlb = niotlb;
 
 	for (i = 0; i < d->nvqs; ++i) {
-		mutex_lock(&d->vqs[i]->mutex);
-		d->vqs[i]->iotlb = niotlb;
-		mutex_unlock(&d->vqs[i]->mutex);
+		struct vhost_virtqueue *vq = d->vqs[i];
+
+		mutex_lock(&vq->mutex);
+		vq->iotlb = niotlb;
+		__vhost_vq_meta_reset(vq);
+		mutex_unlock(&vq->mutex);
 	}
 
 	vhost_umem_clean(oiotlb);
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index 46a4484e3da7..c6f78d27947b 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -20,7 +20,7 @@
 #include <drm/drm_connector.h>  /* For DRM_MODE_PANEL_ORIENTATION_* */
 
 static bool request_mem_succeeded = false;
-static bool nowc = false;
+static u64 mem_flags = EFI_MEMORY_WC | EFI_MEMORY_UC;
 
 static struct fb_var_screeninfo efifb_defined = {
 	.activate		= FB_ACTIVATE_NOW,
@@ -68,8 +68,12 @@ static int efifb_setcolreg(unsigned regno, unsigned red, unsigned green,
 
 static void efifb_destroy(struct fb_info *info)
 {
-	if (info->screen_base)
-		iounmap(info->screen_base);
+	if (info->screen_base) {
+		if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+			iounmap(info->screen_base);
+		else
+			memunmap(info->screen_base);
+	}
 	if (request_mem_succeeded)
 		release_mem_region(info->apertures->ranges[0].base,
 				   info->apertures->ranges[0].size);
@@ -104,7 +108,7 @@ static int efifb_setup(char *options)
 			else if (!strncmp(this_opt, "width:", 6))
 				screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0);
 			else if (!strcmp(this_opt, "nowc"))
-				nowc = true;
+				mem_flags &= ~EFI_MEMORY_WC;
 		}
 	}
 
@@ -164,6 +168,7 @@ static int efifb_probe(struct platform_device *dev)
 	unsigned int size_remap;
 	unsigned int size_total;
 	char *option = NULL;
+	efi_memory_desc_t md;
 
 	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
 		return -ENODEV;
@@ -272,12 +277,35 @@ static int efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	if (nowc)
-		info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len);
-	else
-		info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len);
+	if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
+		if ((efifb_fix.smem_start + efifb_fix.smem_len) >
+		    (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) {
+			pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n",
+			       efifb_fix.smem_start);
+			err = -EIO;
+			goto err_release_fb;
+		}
+		/*
+		 * If the UEFI memory map covers the efifb region, we may only
+		 * remap it using the attributes the memory map prescribes.
+		 */
+		mem_flags |= EFI_MEMORY_WT | EFI_MEMORY_WB;
+		mem_flags &= md.attribute;
+	}
+	if (mem_flags & EFI_MEMORY_WC)
+		info->screen_base = ioremap_wc(efifb_fix.smem_start,
+					       efifb_fix.smem_len);
+	else if (mem_flags & EFI_MEMORY_UC)
+		info->screen_base = ioremap(efifb_fix.smem_start,
+					    efifb_fix.smem_len);
+	else if (mem_flags & EFI_MEMORY_WT)
+		info->screen_base = memremap(efifb_fix.smem_start,
+					     efifb_fix.smem_len, MEMREMAP_WT);
+	else if (mem_flags & EFI_MEMORY_WB)
+		info->screen_base = memremap(efifb_fix.smem_start,
+					     efifb_fix.smem_len, MEMREMAP_WB);
 	if (!info->screen_base) {
-		pr_err("efifb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n",
+		pr_err("efifb: abort, cannot remap video memory 0x%x @ 0x%lx\n",
 			efifb_fix.smem_len, efifb_fix.smem_start);
 		err = -EIO;
 		goto err_release_fb;
@@ -371,7 +399,10 @@ err_fb_dealoc:
 err_groups:
 	sysfs_remove_groups(&dev->dev.kobj, efifb_groups);
 err_unmap:
-	iounmap(info->screen_base);
+	if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+		iounmap(info->screen_base);
+	else
+		memunmap(info->screen_base);
 err_release_fb:
 	framebuffer_release(info);
 err_release_mem:
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 6b237e3f4983..3988c0914322 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -513,7 +513,9 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
 	tell_host(vb, vb->inflate_vq);
 
 	/* balloon's page migration 2nd step -- deflate "page" */
+	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
 	balloon_page_delete(page);
+	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
 	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
 	set_page_pfns(vb, vb->pfns, page);
 	tell_host(vb, vb->deflate_vq);
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index e5d0c28372ea..b459edfacff3 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -152,6 +152,16 @@ config XEN_GNTDEV
 	help
 	  Allows userspace processes to use grants.
 
+config XEN_GNTDEV_DMABUF
+	bool "Add support for dma-buf grant access device driver extension"
+	depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC && DMA_SHARED_BUFFER
+	help
+	  Allows userspace processes and kernel modules to use Xen backed
+	  dma-buf implementation. With this extension grant references to
+	  the pages of an imported dma-buf can be exported for other domain
+	  use and grant references coming from a foreign domain can be
+	  converted into a local dma-buf for local export.
+
 config XEN_GRANT_DEV_ALLOC
 	tristate "User-space grant reference allocator driver"
 	depends on XEN
@@ -161,6 +171,20 @@ config XEN_GRANT_DEV_ALLOC
 	  to other domains. This can be used to implement frontend drivers
 	  or as part of an inter-domain shared memory channel.
 
+config XEN_GRANT_DMA_ALLOC
+	bool "Allow allocating DMA capable buffers with grant reference module"
+	depends on XEN && HAS_DMA
+	help
+	  Extends grant table module API to allow allocating DMA capable
+	  buffers and mapping foreign grant references on top of it.
+	  The resulting buffer is similar to one allocated by the balloon
+	  driver in that proper memory reservation is made by
+	  ({increase|decrease}_reservation and VA mappings are updated if
+	  needed).
+	  This is useful for sharing foreign buffers with HW drivers which
+	  cannot work with scattered buffers provided by the balloon driver,
+	  but require DMAable memory instead.
+
 config SWIOTLB_XEN
 	def_bool y
 	select SWIOTLB
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 48b154276179..3e542f60f29f 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -2,6 +2,7 @@
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 obj-$(CONFIG_X86)			+= fallback.o
 obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o time.o
+obj-y	+= mem-reservation.o
 obj-y	+= events/
 obj-y	+= xenbus/
 
@@ -40,5 +41,6 @@ obj-$(CONFIG_XEN_PVCALLS_BACKEND)	+= pvcalls-back.o
 obj-$(CONFIG_XEN_PVCALLS_FRONTEND)	+= pvcalls-front.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
+xen-gntdev-$(CONFIG_XEN_GNTDEV_DMABUF)	+= gntdev-dmabuf.o
 xen-gntalloc-y				:= gntalloc.o
 xen-privcmd-y				:= privcmd.o privcmd-buf.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 065f0b607373..e12bb256036f 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -71,6 +71,7 @@
 #include <xen/balloon.h>
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/mem-reservation.h>
 
 static int xen_hotplug_unpopulated;
 
@@ -157,13 +158,6 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
 #define GFP_BALLOON \
 	(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
 
-static void scrub_page(struct page *page)
-{
-#ifdef CONFIG_XEN_SCRUB_PAGES
-	clear_highpage(page);
-#endif
-}
-
 /* balloon_append: add the given page to the balloon. */
 static void __balloon_append(struct page *page)
 {
@@ -463,11 +457,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 	int rc;
 	unsigned long i;
 	struct page   *page;
-	struct xen_memory_reservation reservation = {
-		.address_bits = 0,
-		.extent_order = EXTENT_ORDER,
-		.domid        = DOMID_SELF
-	};
 
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
@@ -479,16 +468,11 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 			break;
 		}
 
-		/* XENMEM_populate_physmap requires a PFN based on Xen
-		 * granularity.
-		 */
 		frame_list[i] = page_to_xen_pfn(page);
 		page = balloon_next_page(page);
 	}
 
-	set_xen_guest_handle(reservation.extent_start, frame_list);
-	reservation.nr_extents = nr_pages;
-	rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
+	rc = xenmem_reservation_increase(nr_pages, frame_list);
 	if (rc <= 0)
 		return BP_EAGAIN;
 
@@ -496,29 +480,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 		page = balloon_retrieve(false);
 		BUG_ON(page == NULL);
 
-#ifdef CONFIG_XEN_HAVE_PVMMU
-		/*
-		 * We don't support PV MMU when Linux and Xen is using
-		 * different page granularity.
-		 */
-		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long pfn = page_to_pfn(page);
-
-			set_phys_to_machine(pfn, frame_list[i]);
-
-			/* Link back into the page tables if not highmem. */
-			if (!PageHighMem(page)) {
-				int ret;
-				ret = HYPERVISOR_update_va_mapping(
-						(unsigned long)__va(pfn << PAGE_SHIFT),
-						mfn_pte(frame_list[i], PAGE_KERNEL),
-						0);
-				BUG_ON(ret);
-			}
-		}
-#endif
+		xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]);
 
 		/* Relinquish the page back to the allocator. */
 		free_reserved_page(page);
@@ -535,11 +497,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	unsigned long i;
 	struct page *page, *tmp;
 	int ret;
-	struct xen_memory_reservation reservation = {
-		.address_bits = 0,
-		.extent_order = EXTENT_ORDER,
-		.domid        = DOMID_SELF
-	};
 	LIST_HEAD(pages);
 
 	if (nr_pages > ARRAY_SIZE(frame_list))
@@ -553,7 +510,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 			break;
 		}
 		adjust_managed_page_count(page, -1);
-		scrub_page(page);
+		xenmem_reservation_scrub_page(page);
 		list_add(&page->lru, &pages);
 	}
 
@@ -572,28 +529,10 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	 */
 	i = 0;
 	list_for_each_entry_safe(page, tmp, &pages, lru) {
-		/* XENMEM_decrease_reservation requires a GFN */
 		frame_list[i++] = xen_page_to_gfn(page);
 
-#ifdef CONFIG_XEN_HAVE_PVMMU
-		/*
-		 * We don't support PV MMU when Linux and Xen is using
-		 * different page granularity.
-		 */
-		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long pfn = page_to_pfn(page);
+		xenmem_reservation_va_mapping_reset(1, &page);
 
-			if (!PageHighMem(page)) {
-				ret = HYPERVISOR_update_va_mapping(
-						(unsigned long)__va(pfn << PAGE_SHIFT),
-						__pte_ma(0), 0);
-				BUG_ON(ret);
-			}
-			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
-		}
-#endif
 		list_del(&page->lru);
 
 		balloon_append(page);
@@ -601,9 +540,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 
 	flush_tlb_all();
 
-	set_xen_guest_handle(reservation.extent_start, frame_list);
-	reservation.nr_extents   = nr_pages;
-	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+	ret = xenmem_reservation_decrease(nr_pages, frame_list);
 	BUG_ON(ret != nr_pages);
 
 	balloon_stats.current_pages -= nr_pages;
diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c
index 30d7f52eb7ca..55ed80c3a17c 100644
--- a/drivers/xen/biomerge.c
+++ b/drivers/xen/biomerge.c
@@ -17,7 +17,7 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 	 * XXX: Add support for merging bio_vec when using different page
 	 * size in Xen and Linux.
 	 */
-	return 0;
+	return false;
 #endif
 }
 EXPORT_SYMBOL(xen_biovec_phys_mergeable);
diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h
new file mode 100644
index 000000000000..2f8b949c3eeb
--- /dev/null
+++ b/drivers/xen/gntdev-common.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Common functionality of grant device.
+ *
+ * Copyright (c) 2006-2007, D G Murray.
+ *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *           (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _GNTDEV_COMMON_H
+#define _GNTDEV_COMMON_H
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mmu_notifier.h>
+#include <linux/types.h>
+
+struct gntdev_dmabuf_priv;
+
+struct gntdev_priv {
+	/* Maps with visible offsets in the file descriptor. */
+	struct list_head maps;
+	/*
+	 * Maps that are not visible; will be freed on munmap.
+	 * Only populated if populate_freeable_maps == 1
+	 */
+	struct list_head freeable_maps;
+	/* lock protects maps and freeable_maps. */
+	struct mutex lock;
+	struct mm_struct *mm;
+	struct mmu_notifier mn;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/* Device for which DMA memory is allocated. */
+	struct device *dma_dev;
+#endif
+
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	struct gntdev_dmabuf_priv *dmabuf_priv;
+#endif
+};
+
+struct gntdev_unmap_notify {
+	int flags;
+	/* Address relative to the start of the gntdev_grant_map. */
+	int addr;
+	int event;
+};
+
+struct gntdev_grant_map {
+	struct list_head next;
+	struct vm_area_struct *vma;
+	int index;
+	int count;
+	int flags;
+	refcount_t users;
+	struct gntdev_unmap_notify notify;
+	struct ioctl_gntdev_grant_ref *grants;
+	struct gnttab_map_grant_ref   *map_ops;
+	struct gnttab_unmap_grant_ref *unmap_ops;
+	struct gnttab_map_grant_ref   *kmap_ops;
+	struct gnttab_unmap_grant_ref *kunmap_ops;
+	struct page **pages;
+	unsigned long pages_vm_start;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/*
+	 * If dmabuf_vaddr is not NULL then this mapping is backed by DMA
+	 * capable memory.
+	 */
+
+	struct device *dma_dev;
+	/* Flags used to create this DMA buffer: GNTDEV_DMA_FLAG_XXX. */
+	int dma_flags;
+	void *dma_vaddr;
+	dma_addr_t dma_bus_addr;
+	/* Needed to avoid allocation in gnttab_dma_free_pages(). */
+	xen_pfn_t *frames;
+#endif
+};
+
+struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+					  int dma_flags);
+
+void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add);
+
+void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map);
+
+bool gntdev_account_mapped_pages(int count);
+
+int gntdev_map_grant_pages(struct gntdev_grant_map *map);
+
+#endif
diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
new file mode 100644
index 000000000000..589fd923c550
--- /dev/null
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -0,0 +1,857 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Xen dma-buf functionality for gntdev.
+ *
+ * DMA buffer implementation is based on drivers/gpu/drm/drm_prime.c.
+ *
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/dma-buf.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+
+#include <xen/xen.h>
+#include <xen/grant_table.h>
+
+#include "gntdev-common.h"
+#include "gntdev-dmabuf.h"
+
+#ifndef GRANT_INVALID_REF
+/*
+ * Note on usage of grant reference 0 as invalid grant reference:
+ * grant reference 0 is valid, but never exposed to a driver,
+ * because of the fact it is already in use/reserved by the PV console.
+ */
+#define GRANT_INVALID_REF	0
+#endif
+
+struct gntdev_dmabuf {
+	struct gntdev_dmabuf_priv *priv;
+	struct dma_buf *dmabuf;
+	struct list_head next;
+	int fd;
+
+	union {
+		struct {
+			/* Exported buffers are reference counted. */
+			struct kref refcount;
+
+			struct gntdev_priv *priv;
+			struct gntdev_grant_map *map;
+		} exp;
+		struct {
+			/* Granted references of the imported buffer. */
+			grant_ref_t *refs;
+			/* Scatter-gather table of the imported buffer. */
+			struct sg_table *sgt;
+			/* dma-buf attachment of the imported buffer. */
+			struct dma_buf_attachment *attach;
+		} imp;
+	} u;
+
+	/* Number of pages this buffer has. */
+	int nr_pages;
+	/* Pages of this buffer. */
+	struct page **pages;
+};
+
+struct gntdev_dmabuf_wait_obj {
+	struct list_head next;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct completion completion;
+};
+
+struct gntdev_dmabuf_attachment {
+	struct sg_table *sgt;
+	enum dma_data_direction dir;
+};
+
+struct gntdev_dmabuf_priv {
+	/* List of exported DMA buffers. */
+	struct list_head exp_list;
+	/* List of wait objects. */
+	struct list_head exp_wait_list;
+	/* List of imported DMA buffers. */
+	struct list_head imp_list;
+	/* This is the lock which protects dma_buf_xxx lists. */
+	struct mutex lock;
+};
+
+/* DMA buffer export support. */
+
+/* Implementation of wait for exported DMA buffer to be released. */
+
+static void dmabuf_exp_release(struct kref *kref);
+
+static struct gntdev_dmabuf_wait_obj *
+dmabuf_exp_wait_obj_new(struct gntdev_dmabuf_priv *priv,
+			struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	struct gntdev_dmabuf_wait_obj *obj;
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	init_completion(&obj->completion);
+	obj->gntdev_dmabuf = gntdev_dmabuf;
+
+	mutex_lock(&priv->lock);
+	list_add(&obj->next, &priv->exp_wait_list);
+	/* Put our reference and wait for gntdev_dmabuf's release to fire. */
+	kref_put(&gntdev_dmabuf->u.exp.refcount, dmabuf_exp_release);
+	mutex_unlock(&priv->lock);
+	return obj;
+}
+
+static void dmabuf_exp_wait_obj_free(struct gntdev_dmabuf_priv *priv,
+				     struct gntdev_dmabuf_wait_obj *obj)
+{
+	mutex_lock(&priv->lock);
+	list_del(&obj->next);
+	mutex_unlock(&priv->lock);
+	kfree(obj);
+}
+
+static int dmabuf_exp_wait_obj_wait(struct gntdev_dmabuf_wait_obj *obj,
+				    u32 wait_to_ms)
+{
+	if (wait_for_completion_timeout(&obj->completion,
+			msecs_to_jiffies(wait_to_ms)) <= 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static void dmabuf_exp_wait_obj_signal(struct gntdev_dmabuf_priv *priv,
+				       struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	struct gntdev_dmabuf_wait_obj *obj;
+
+	list_for_each_entry(obj, &priv->exp_wait_list, next)
+		if (obj->gntdev_dmabuf == gntdev_dmabuf) {
+			pr_debug("Found gntdev_dmabuf in the wait list, wake\n");
+			complete_all(&obj->completion);
+			break;
+		}
+}
+
+static struct gntdev_dmabuf *
+dmabuf_exp_wait_obj_get_dmabuf(struct gntdev_dmabuf_priv *priv, int fd)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf, *ret = ERR_PTR(-ENOENT);
+
+	mutex_lock(&priv->lock);
+	list_for_each_entry(gntdev_dmabuf, &priv->exp_list, next)
+		if (gntdev_dmabuf->fd == fd) {
+			pr_debug("Found gntdev_dmabuf in the wait list\n");
+			kref_get(&gntdev_dmabuf->u.exp.refcount);
+			ret = gntdev_dmabuf;
+			break;
+		}
+	mutex_unlock(&priv->lock);
+	return ret;
+}
+
+static int dmabuf_exp_wait_released(struct gntdev_dmabuf_priv *priv, int fd,
+				    int wait_to_ms)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct gntdev_dmabuf_wait_obj *obj;
+	int ret;
+
+	pr_debug("Will wait for dma-buf with fd %d\n", fd);
+	/*
+	 * Try to find the DMA buffer: if not found means that
+	 * either the buffer has already been released or file descriptor
+	 * provided is wrong.
+	 */
+	gntdev_dmabuf = dmabuf_exp_wait_obj_get_dmabuf(priv, fd);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	/*
+	 * gntdev_dmabuf still exists and is reference count locked by us now,
+	 * so prepare to wait: allocate wait object and add it to the wait list,
+	 * so we can find it on release.
+	 */
+	obj = dmabuf_exp_wait_obj_new(priv, gntdev_dmabuf);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	ret = dmabuf_exp_wait_obj_wait(obj, wait_to_ms);
+	dmabuf_exp_wait_obj_free(priv, obj);
+	return ret;
+}
+
+/* DMA buffer export support. */
+
+static struct sg_table *
+dmabuf_pages_to_sgt(struct page **pages, unsigned int nr_pages)
+{
+	struct sg_table *sgt;
+	int ret;
+
+	sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
+	if (!sgt) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = sg_alloc_table_from_pages(sgt, pages, nr_pages, 0,
+					nr_pages << PAGE_SHIFT,
+					GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	return sgt;
+
+out:
+	kfree(sgt);
+	return ERR_PTR(ret);
+}
+
+static int dmabuf_exp_ops_attach(struct dma_buf *dma_buf,
+				 struct device *target_dev,
+				 struct dma_buf_attachment *attach)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach;
+
+	gntdev_dmabuf_attach = kzalloc(sizeof(*gntdev_dmabuf_attach),
+				       GFP_KERNEL);
+	if (!gntdev_dmabuf_attach)
+		return -ENOMEM;
+
+	gntdev_dmabuf_attach->dir = DMA_NONE;
+	attach->priv = gntdev_dmabuf_attach;
+	return 0;
+}
+
+static void dmabuf_exp_ops_detach(struct dma_buf *dma_buf,
+				  struct dma_buf_attachment *attach)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach = attach->priv;
+
+	if (gntdev_dmabuf_attach) {
+		struct sg_table *sgt = gntdev_dmabuf_attach->sgt;
+
+		if (sgt) {
+			if (gntdev_dmabuf_attach->dir != DMA_NONE)
+				dma_unmap_sg_attrs(attach->dev, sgt->sgl,
+						   sgt->nents,
+						   gntdev_dmabuf_attach->dir,
+						   DMA_ATTR_SKIP_CPU_SYNC);
+			sg_free_table(sgt);
+		}
+
+		kfree(sgt);
+		kfree(gntdev_dmabuf_attach);
+		attach->priv = NULL;
+	}
+}
+
+static struct sg_table *
+dmabuf_exp_ops_map_dma_buf(struct dma_buf_attachment *attach,
+			   enum dma_data_direction dir)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach = attach->priv;
+	struct gntdev_dmabuf *gntdev_dmabuf = attach->dmabuf->priv;
+	struct sg_table *sgt;
+
+	pr_debug("Mapping %d pages for dev %p\n", gntdev_dmabuf->nr_pages,
+		 attach->dev);
+
+	if (dir == DMA_NONE || !gntdev_dmabuf_attach)
+		return ERR_PTR(-EINVAL);
+
+	/* Return the cached mapping when possible. */
+	if (gntdev_dmabuf_attach->dir == dir)
+		return gntdev_dmabuf_attach->sgt;
+
+	/*
+	 * Two mappings with different directions for the same attachment are
+	 * not allowed.
+	 */
+	if (gntdev_dmabuf_attach->dir != DMA_NONE)
+		return ERR_PTR(-EBUSY);
+
+	sgt = dmabuf_pages_to_sgt(gntdev_dmabuf->pages,
+				  gntdev_dmabuf->nr_pages);
+	if (!IS_ERR(sgt)) {
+		if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+				      DMA_ATTR_SKIP_CPU_SYNC)) {
+			sg_free_table(sgt);
+			kfree(sgt);
+			sgt = ERR_PTR(-ENOMEM);
+		} else {
+			gntdev_dmabuf_attach->sgt = sgt;
+			gntdev_dmabuf_attach->dir = dir;
+		}
+	}
+	if (IS_ERR(sgt))
+		pr_debug("Failed to map sg table for dev %p\n", attach->dev);
+	return sgt;
+}
+
+static void dmabuf_exp_ops_unmap_dma_buf(struct dma_buf_attachment *attach,
+					 struct sg_table *sgt,
+					 enum dma_data_direction dir)
+{
+	/* Not implemented. The unmap is done at dmabuf_exp_ops_detach(). */
+}
+
+static void dmabuf_exp_release(struct kref *kref)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf =
+		container_of(kref, struct gntdev_dmabuf, u.exp.refcount);
+
+	dmabuf_exp_wait_obj_signal(gntdev_dmabuf->priv, gntdev_dmabuf);
+	list_del(&gntdev_dmabuf->next);
+	kfree(gntdev_dmabuf);
+}
+
+static void dmabuf_exp_remove_map(struct gntdev_priv *priv,
+				  struct gntdev_grant_map *map)
+{
+	mutex_lock(&priv->lock);
+	list_del(&map->next);
+	gntdev_put_map(NULL /* already removed */, map);
+	mutex_unlock(&priv->lock);
+}
+
+static void dmabuf_exp_ops_release(struct dma_buf *dma_buf)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf = dma_buf->priv;
+	struct gntdev_dmabuf_priv *priv = gntdev_dmabuf->priv;
+
+	dmabuf_exp_remove_map(gntdev_dmabuf->u.exp.priv,
+			      gntdev_dmabuf->u.exp.map);
+	mutex_lock(&priv->lock);
+	kref_put(&gntdev_dmabuf->u.exp.refcount, dmabuf_exp_release);
+	mutex_unlock(&priv->lock);
+}
+
+static void *dmabuf_exp_ops_kmap(struct dma_buf *dma_buf,
+				 unsigned long page_num)
+{
+	/* Not implemented. */
+	return NULL;
+}
+
+static void dmabuf_exp_ops_kunmap(struct dma_buf *dma_buf,
+				  unsigned long page_num, void *addr)
+{
+	/* Not implemented. */
+}
+
+static int dmabuf_exp_ops_mmap(struct dma_buf *dma_buf,
+			       struct vm_area_struct *vma)
+{
+	/* Not implemented. */
+	return 0;
+}
+
+static const struct dma_buf_ops dmabuf_exp_ops =  {
+	.attach = dmabuf_exp_ops_attach,
+	.detach = dmabuf_exp_ops_detach,
+	.map_dma_buf = dmabuf_exp_ops_map_dma_buf,
+	.unmap_dma_buf = dmabuf_exp_ops_unmap_dma_buf,
+	.release = dmabuf_exp_ops_release,
+	.map = dmabuf_exp_ops_kmap,
+	.unmap = dmabuf_exp_ops_kunmap,
+	.mmap = dmabuf_exp_ops_mmap,
+};
+
+struct gntdev_dmabuf_export_args {
+	struct gntdev_priv *priv;
+	struct gntdev_grant_map *map;
+	struct gntdev_dmabuf_priv *dmabuf_priv;
+	struct device *dev;
+	int count;
+	struct page **pages;
+	u32 fd;
+};
+
+static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args)
+{
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	int ret;
+
+	gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL);
+	if (!gntdev_dmabuf)
+		return -ENOMEM;
+
+	kref_init(&gntdev_dmabuf->u.exp.refcount);
+
+	gntdev_dmabuf->priv = args->dmabuf_priv;
+	gntdev_dmabuf->nr_pages = args->count;
+	gntdev_dmabuf->pages = args->pages;
+	gntdev_dmabuf->u.exp.priv = args->priv;
+	gntdev_dmabuf->u.exp.map = args->map;
+
+	exp_info.exp_name = KBUILD_MODNAME;
+	if (args->dev->driver && args->dev->driver->owner)
+		exp_info.owner = args->dev->driver->owner;
+	else
+		exp_info.owner = THIS_MODULE;
+	exp_info.ops = &dmabuf_exp_ops;
+	exp_info.size = args->count << PAGE_SHIFT;
+	exp_info.flags = O_RDWR;
+	exp_info.priv = gntdev_dmabuf;
+
+	gntdev_dmabuf->dmabuf = dma_buf_export(&exp_info);
+	if (IS_ERR(gntdev_dmabuf->dmabuf)) {
+		ret = PTR_ERR(gntdev_dmabuf->dmabuf);
+		gntdev_dmabuf->dmabuf = NULL;
+		goto fail;
+	}
+
+	ret = dma_buf_fd(gntdev_dmabuf->dmabuf, O_CLOEXEC);
+	if (ret < 0)
+		goto fail;
+
+	gntdev_dmabuf->fd = ret;
+	args->fd = ret;
+
+	pr_debug("Exporting DMA buffer with fd %d\n", ret);
+
+	mutex_lock(&args->dmabuf_priv->lock);
+	list_add(&gntdev_dmabuf->next, &args->dmabuf_priv->exp_list);
+	mutex_unlock(&args->dmabuf_priv->lock);
+	return 0;
+
+fail:
+	if (gntdev_dmabuf->dmabuf)
+		dma_buf_put(gntdev_dmabuf->dmabuf);
+	kfree(gntdev_dmabuf);
+	return ret;
+}
+
+static struct gntdev_grant_map *
+dmabuf_exp_alloc_backing_storage(struct gntdev_priv *priv, int dmabuf_flags,
+				 int count)
+{
+	struct gntdev_grant_map *map;
+
+	if (unlikely(count <= 0))
+		return ERR_PTR(-EINVAL);
+
+	if ((dmabuf_flags & GNTDEV_DMA_FLAG_WC) &&
+	    (dmabuf_flags & GNTDEV_DMA_FLAG_COHERENT)) {
+		pr_debug("Wrong dma-buf flags: 0x%x\n", dmabuf_flags);
+		return ERR_PTR(-EINVAL);
+	}
+
+	map = gntdev_alloc_map(priv, count, dmabuf_flags);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	if (unlikely(gntdev_account_mapped_pages(count))) {
+		pr_debug("can't map %d pages: over limit\n", count);
+		gntdev_put_map(NULL, map);
+		return ERR_PTR(-ENOMEM);
+	}
+	return map;
+}
+
+static int dmabuf_exp_from_refs(struct gntdev_priv *priv, int flags,
+				int count, u32 domid, u32 *refs, u32 *fd)
+{
+	struct gntdev_grant_map *map;
+	struct gntdev_dmabuf_export_args args;
+	int i, ret;
+
+	map = dmabuf_exp_alloc_backing_storage(priv, flags, count);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	for (i = 0; i < count; i++) {
+		map->grants[i].domid = domid;
+		map->grants[i].ref = refs[i];
+	}
+
+	mutex_lock(&priv->lock);
+	gntdev_add_map(priv, map);
+	mutex_unlock(&priv->lock);
+
+	map->flags |= GNTMAP_host_map;
+#if defined(CONFIG_X86)
+	map->flags |= GNTMAP_device_map;
+#endif
+
+	ret = gntdev_map_grant_pages(map);
+	if (ret < 0)
+		goto out;
+
+	args.priv = priv;
+	args.map = map;
+	args.dev = priv->dma_dev;
+	args.dmabuf_priv = priv->dmabuf_priv;
+	args.count = map->count;
+	args.pages = map->pages;
+	args.fd = -1; /* Shut up unnecessary gcc warning for i386 */
+
+	ret = dmabuf_exp_from_pages(&args);
+	if (ret < 0)
+		goto out;
+
+	*fd = args.fd;
+	return 0;
+
+out:
+	dmabuf_exp_remove_map(priv, map);
+	return ret;
+}
+
+/* DMA buffer import support. */
+
+static int
+dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs,
+				int count, int domid)
+{
+	grant_ref_t priv_gref_head;
+	int i, ret;
+
+	ret = gnttab_alloc_grant_references(count, &priv_gref_head);
+	if (ret < 0) {
+		pr_debug("Cannot allocate grant references, ret %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < count; i++) {
+		int cur_ref;
+
+		cur_ref = gnttab_claim_grant_reference(&priv_gref_head);
+		if (cur_ref < 0) {
+			ret = cur_ref;
+			pr_debug("Cannot claim grant reference, ret %d\n", ret);
+			goto out;
+		}
+
+		gnttab_grant_foreign_access_ref(cur_ref, domid,
+						xen_page_to_gfn(pages[i]), 0);
+		refs[i] = cur_ref;
+	}
+
+	return 0;
+
+out:
+	gnttab_free_grant_references(priv_gref_head);
+	return ret;
+}
+
+static void dmabuf_imp_end_foreign_access(u32 *refs, int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++)
+		if (refs[i] != GRANT_INVALID_REF)
+			gnttab_end_foreign_access(refs[i], 0, 0UL);
+}
+
+static void dmabuf_imp_free_storage(struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	kfree(gntdev_dmabuf->pages);
+	kfree(gntdev_dmabuf->u.imp.refs);
+	kfree(gntdev_dmabuf);
+}
+
+static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	int i;
+
+	gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL);
+	if (!gntdev_dmabuf)
+		goto fail_no_free;
+
+	gntdev_dmabuf->u.imp.refs = kcalloc(count,
+					    sizeof(gntdev_dmabuf->u.imp.refs[0]),
+					    GFP_KERNEL);
+	if (!gntdev_dmabuf->u.imp.refs)
+		goto fail;
+
+	gntdev_dmabuf->pages = kcalloc(count,
+				       sizeof(gntdev_dmabuf->pages[0]),
+				       GFP_KERNEL);
+	if (!gntdev_dmabuf->pages)
+		goto fail;
+
+	gntdev_dmabuf->nr_pages = count;
+
+	for (i = 0; i < count; i++)
+		gntdev_dmabuf->u.imp.refs[i] = GRANT_INVALID_REF;
+
+	return gntdev_dmabuf;
+
+fail:
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+fail_no_free:
+	return ERR_PTR(-ENOMEM);
+}
+
+static struct gntdev_dmabuf *
+dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
+		   int fd, int count, int domid)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf, *ret;
+	struct dma_buf *dma_buf;
+	struct dma_buf_attachment *attach;
+	struct sg_table *sgt;
+	struct sg_page_iter sg_iter;
+	int i;
+
+	dma_buf = dma_buf_get(fd);
+	if (IS_ERR(dma_buf))
+		return ERR_CAST(dma_buf);
+
+	gntdev_dmabuf = dmabuf_imp_alloc_storage(count);
+	if (IS_ERR(gntdev_dmabuf)) {
+		ret = gntdev_dmabuf;
+		goto fail_put;
+	}
+
+	gntdev_dmabuf->priv = priv;
+	gntdev_dmabuf->fd = fd;
+
+	attach = dma_buf_attach(dma_buf, dev);
+	if (IS_ERR(attach)) {
+		ret = ERR_CAST(attach);
+		goto fail_free_obj;
+	}
+
+	gntdev_dmabuf->u.imp.attach = attach;
+
+	sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
+	if (IS_ERR(sgt)) {
+		ret = ERR_CAST(sgt);
+		goto fail_detach;
+	}
+
+	/* Check number of pages that imported buffer has. */
+	if (attach->dmabuf->size != gntdev_dmabuf->nr_pages << PAGE_SHIFT) {
+		ret = ERR_PTR(-EINVAL);
+		pr_debug("DMA buffer has %zu pages, user-space expects %d\n",
+			 attach->dmabuf->size, gntdev_dmabuf->nr_pages);
+		goto fail_unmap;
+	}
+
+	gntdev_dmabuf->u.imp.sgt = sgt;
+
+	/* Now convert sgt to array of pages and check for page validity. */
+	i = 0;
+	for_each_sg_page(sgt->sgl, &sg_iter, sgt->nents, 0) {
+		struct page *page = sg_page_iter_page(&sg_iter);
+		/*
+		 * Check if page is valid: this can happen if we are given
+		 * a page from VRAM or other resources which are not backed
+		 * by a struct page.
+		 */
+		if (!pfn_valid(page_to_pfn(page))) {
+			ret = ERR_PTR(-EINVAL);
+			goto fail_unmap;
+		}
+
+		gntdev_dmabuf->pages[i++] = page;
+	}
+
+	ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gntdev_dmabuf->pages,
+						      gntdev_dmabuf->u.imp.refs,
+						      count, domid));
+	if (IS_ERR(ret))
+		goto fail_end_access;
+
+	pr_debug("Imported DMA buffer with fd %d\n", fd);
+
+	mutex_lock(&priv->lock);
+	list_add(&gntdev_dmabuf->next, &priv->imp_list);
+	mutex_unlock(&priv->lock);
+
+	return gntdev_dmabuf;
+
+fail_end_access:
+	dmabuf_imp_end_foreign_access(gntdev_dmabuf->u.imp.refs, count);
+fail_unmap:
+	dma_buf_unmap_attachment(attach, sgt, DMA_BIDIRECTIONAL);
+fail_detach:
+	dma_buf_detach(dma_buf, attach);
+fail_free_obj:
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+fail_put:
+	dma_buf_put(dma_buf);
+	return ret;
+}
+
+/*
+ * Find the hyper dma-buf by its file descriptor and remove
+ * it from the buffer's list.
+ */
+static struct gntdev_dmabuf *
+dmabuf_imp_find_unlink(struct gntdev_dmabuf_priv *priv, int fd)
+{
+	struct gntdev_dmabuf *q, *gntdev_dmabuf, *ret = ERR_PTR(-ENOENT);
+
+	mutex_lock(&priv->lock);
+	list_for_each_entry_safe(gntdev_dmabuf, q, &priv->imp_list, next) {
+		if (gntdev_dmabuf->fd == fd) {
+			pr_debug("Found gntdev_dmabuf in the import list\n");
+			ret = gntdev_dmabuf;
+			list_del(&gntdev_dmabuf->next);
+			break;
+		}
+	}
+	mutex_unlock(&priv->lock);
+	return ret;
+}
+
+static int dmabuf_imp_release(struct gntdev_dmabuf_priv *priv, u32 fd)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct dma_buf_attachment *attach;
+	struct dma_buf *dma_buf;
+
+	gntdev_dmabuf = dmabuf_imp_find_unlink(priv, fd);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	pr_debug("Releasing DMA buffer with fd %d\n", fd);
+
+	dmabuf_imp_end_foreign_access(gntdev_dmabuf->u.imp.refs,
+				      gntdev_dmabuf->nr_pages);
+
+	attach = gntdev_dmabuf->u.imp.attach;
+
+	if (gntdev_dmabuf->u.imp.sgt)
+		dma_buf_unmap_attachment(attach, gntdev_dmabuf->u.imp.sgt,
+					 DMA_BIDIRECTIONAL);
+	dma_buf = attach->dmabuf;
+	dma_buf_detach(attach->dmabuf, attach);
+	dma_buf_put(dma_buf);
+
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+	return 0;
+}
+
+/* DMA buffer IOCTL support. */
+
+long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod,
+				       struct ioctl_gntdev_dmabuf_exp_from_refs __user *u)
+{
+	struct ioctl_gntdev_dmabuf_exp_from_refs op;
+	u32 *refs;
+	long ret;
+
+	if (use_ptemod) {
+		pr_debug("Cannot provide dma-buf: use_ptemode %d\n",
+			 use_ptemod);
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	if (unlikely(op.count <= 0))
+		return -EINVAL;
+
+	refs = kcalloc(op.count, sizeof(*refs), GFP_KERNEL);
+	if (!refs)
+		return -ENOMEM;
+
+	if (copy_from_user(refs, u->refs, sizeof(*refs) * op.count) != 0) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = dmabuf_exp_from_refs(priv, op.flags, op.count,
+				   op.domid, refs, &op.fd);
+	if (ret)
+		goto out;
+
+	if (copy_to_user(u, &op, sizeof(op)) != 0)
+		ret = -EFAULT;
+
+out:
+	kfree(refs);
+	return ret;
+}
+
+long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv,
+					   struct ioctl_gntdev_dmabuf_exp_wait_released __user *u)
+{
+	struct ioctl_gntdev_dmabuf_exp_wait_released op;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	return dmabuf_exp_wait_released(priv->dmabuf_priv, op.fd,
+					op.wait_to_ms);
+}
+
+long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_to_refs __user *u)
+{
+	struct ioctl_gntdev_dmabuf_imp_to_refs op;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	long ret;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	if (unlikely(op.count <= 0))
+		return -EINVAL;
+
+	gntdev_dmabuf = dmabuf_imp_to_refs(priv->dmabuf_priv,
+					   priv->dma_dev, op.fd,
+					   op.count, op.domid);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	if (copy_to_user(u->refs, gntdev_dmabuf->u.imp.refs,
+			 sizeof(*u->refs) * op.count) != 0) {
+		ret = -EFAULT;
+		goto out_release;
+	}
+	return 0;
+
+out_release:
+	dmabuf_imp_release(priv->dmabuf_priv, op.fd);
+	return ret;
+}
+
+long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_release __user *u)
+{
+	struct ioctl_gntdev_dmabuf_imp_release op;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	return dmabuf_imp_release(priv->dmabuf_priv, op.fd);
+}
+
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void)
+{
+	struct gntdev_dmabuf_priv *priv;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&priv->lock);
+	INIT_LIST_HEAD(&priv->exp_list);
+	INIT_LIST_HEAD(&priv->exp_wait_list);
+	INIT_LIST_HEAD(&priv->imp_list);
+
+	return priv;
+}
+
+void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv)
+{
+	kfree(priv);
+}
diff --git a/drivers/xen/gntdev-dmabuf.h b/drivers/xen/gntdev-dmabuf.h
new file mode 100644
index 000000000000..7220a53d0fc5
--- /dev/null
+++ b/drivers/xen/gntdev-dmabuf.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Xen dma-buf functionality for gntdev.
+ *
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _GNTDEV_DMABUF_H
+#define _GNTDEV_DMABUF_H
+
+#include <xen/gntdev.h>
+
+struct gntdev_dmabuf_priv;
+struct gntdev_priv;
+
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void);
+
+void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv);
+
+long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod,
+				       struct ioctl_gntdev_dmabuf_exp_from_refs __user *u);
+
+long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv,
+					   struct ioctl_gntdev_dmabuf_exp_wait_released __user *u);
+
+long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_to_refs __user *u);
+
+long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_release __user *u);
+
+#endif
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index bd56653b9bbc..c866a62f766d 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -6,6 +6,7 @@
  *
  * Copyright (c) 2006-2007, D G Murray.
  *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *           (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -26,10 +27,6 @@
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/mmu_notifier.h>
-#include <linux/types.h>
 #include <linux/uaccess.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
@@ -37,6 +34,9 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/refcount.h>
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+#include <linux/of_device.h>
+#endif
 
 #include <xen/xen.h>
 #include <xen/grant_table.h>
@@ -47,6 +47,11 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
+#include "gntdev-common.h"
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+#include "gntdev-dmabuf.h"
+#endif
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
 	      "Gerd Hoffmann <kraxel@redhat.com>");
@@ -62,51 +67,23 @@ static atomic_t pages_mapped = ATOMIC_INIT(0);
 static int use_ptemod;
 #define populate_freeable_maps use_ptemod
 
-struct gntdev_priv {
-	/* maps with visible offsets in the file descriptor */
-	struct list_head maps;
-	/* maps that are not visible; will be freed on munmap.
-	 * Only populated if populate_freeable_maps == 1 */
-	struct list_head freeable_maps;
-	/* lock protects maps and freeable_maps */
-	struct mutex lock;
-	struct mm_struct *mm;
-	struct mmu_notifier mn;
-};
-
-struct unmap_notify {
-	int flags;
-	/* Address relative to the start of the grant_map */
-	int addr;
-	int event;
-};
-
-struct grant_map {
-	struct list_head next;
-	struct vm_area_struct *vma;
-	int index;
-	int count;
-	int flags;
-	refcount_t users;
-	struct unmap_notify notify;
-	struct ioctl_gntdev_grant_ref *grants;
-	struct gnttab_map_grant_ref   *map_ops;
-	struct gnttab_unmap_grant_ref *unmap_ops;
-	struct gnttab_map_grant_ref   *kmap_ops;
-	struct gnttab_unmap_grant_ref *kunmap_ops;
-	struct page **pages;
-	unsigned long pages_vm_start;
-};
+static int unmap_grant_pages(struct gntdev_grant_map *map,
+			     int offset, int pages);
 
-static int unmap_grant_pages(struct grant_map *map, int offset, int pages);
+static struct miscdevice gntdev_miscdev;
 
 /* ------------------------------------------------------------------ */
 
+bool gntdev_account_mapped_pages(int count)
+{
+	return atomic_add_return(count, &pages_mapped) > limit;
+}
+
 static void gntdev_print_maps(struct gntdev_priv *priv,
 			      char *text, int text_index)
 {
 #ifdef DEBUG
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	pr_debug("%s: maps list (priv %p)\n", __func__, priv);
 	list_for_each_entry(map, &priv->maps, next)
@@ -116,13 +93,32 @@ static void gntdev_print_maps(struct gntdev_priv *priv,
 #endif
 }
 
-static void gntdev_free_map(struct grant_map *map)
+static void gntdev_free_map(struct gntdev_grant_map *map)
 {
 	if (map == NULL)
 		return;
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	if (map->dma_vaddr) {
+		struct gnttab_dma_alloc_args args;
+
+		args.dev = map->dma_dev;
+		args.coherent = !!(map->dma_flags & GNTDEV_DMA_FLAG_COHERENT);
+		args.nr_pages = map->count;
+		args.pages = map->pages;
+		args.frames = map->frames;
+		args.vaddr = map->dma_vaddr;
+		args.dev_bus_addr = map->dma_bus_addr;
+
+		gnttab_dma_free_pages(&args);
+	} else
+#endif
 	if (map->pages)
 		gnttab_free_pages(map->count, map->pages);
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	kfree(map->frames);
+#endif
 	kfree(map->pages);
 	kfree(map->grants);
 	kfree(map->map_ops);
@@ -132,12 +128,13 @@ static void gntdev_free_map(struct grant_map *map)
 	kfree(map);
 }
 
-static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
+struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+					  int dma_flags)
 {
-	struct grant_map *add;
+	struct gntdev_grant_map *add;
 	int i;
 
-	add = kzalloc(sizeof(struct grant_map), GFP_KERNEL);
+	add = kzalloc(sizeof(*add), GFP_KERNEL);
 	if (NULL == add)
 		return NULL;
 
@@ -155,6 +152,37 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 	    NULL == add->pages)
 		goto err;
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	add->dma_flags = dma_flags;
+
+	/*
+	 * Check if this mapping is requested to be backed
+	 * by a DMA buffer.
+	 */
+	if (dma_flags & (GNTDEV_DMA_FLAG_WC | GNTDEV_DMA_FLAG_COHERENT)) {
+		struct gnttab_dma_alloc_args args;
+
+		add->frames = kcalloc(count, sizeof(add->frames[0]),
+				      GFP_KERNEL);
+		if (!add->frames)
+			goto err;
+
+		/* Remember the device, so we can free DMA memory. */
+		add->dma_dev = priv->dma_dev;
+
+		args.dev = priv->dma_dev;
+		args.coherent = !!(dma_flags & GNTDEV_DMA_FLAG_COHERENT);
+		args.nr_pages = count;
+		args.pages = add->pages;
+		args.frames = add->frames;
+
+		if (gnttab_dma_alloc_pages(&args))
+			goto err;
+
+		add->dma_vaddr = args.vaddr;
+		add->dma_bus_addr = args.dev_bus_addr;
+	} else
+#endif
 	if (gnttab_alloc_pages(count, add->pages))
 		goto err;
 
@@ -176,9 +204,9 @@ err:
 	return NULL;
 }
 
-static void gntdev_add_map(struct gntdev_priv *priv, struct grant_map *add)
+void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add)
 {
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	list_for_each_entry(map, &priv->maps, next) {
 		if (add->index + add->count < map->index) {
@@ -193,10 +221,10 @@ done:
 	gntdev_print_maps(priv, "[new]", add->index);
 }
 
-static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
-		int index, int count)
+static struct gntdev_grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
+						      int index, int count)
 {
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	list_for_each_entry(map, &priv->maps, next) {
 		if (map->index != index)
@@ -208,7 +236,7 @@ static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
 	return NULL;
 }
 
-static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
+void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
 {
 	if (!map)
 		return;
@@ -239,7 +267,7 @@ static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
 static int find_grant_ptes(pte_t *pte, pgtable_t token,
 		unsigned long addr, void *data)
 {
-	struct grant_map *map = data;
+	struct gntdev_grant_map *map = data;
 	unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT;
 	int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte;
 	u64 pte_maddr;
@@ -272,7 +300,7 @@ static int set_grant_ptes_as_special(pte_t *pte, pgtable_t token,
 }
 #endif
 
-static int map_grant_pages(struct grant_map *map)
+int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 {
 	int i, err = 0;
 
@@ -325,11 +353,20 @@ static int map_grant_pages(struct grant_map *map)
 		map->unmap_ops[i].handle = map->map_ops[i].handle;
 		if (use_ptemod)
 			map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+		else if (map->dma_vaddr) {
+			unsigned long bfn;
+
+			bfn = pfn_to_bfn(page_to_pfn(map->pages[i]));
+			map->unmap_ops[i].dev_bus_addr = __pfn_to_phys(bfn);
+		}
+#endif
 	}
 	return err;
 }
 
-static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
+static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+			       int pages)
 {
 	int i, err = 0;
 	struct gntab_unmap_queue_data unmap_data;
@@ -364,7 +401,8 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
 	return err;
 }
 
-static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
+static int unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+			     int pages)
 {
 	int range, err = 0;
 
@@ -396,7 +434,7 @@ static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
 
 static void gntdev_vma_open(struct vm_area_struct *vma)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 
 	pr_debug("gntdev_vma_open %p\n", vma);
 	refcount_inc(&map->users);
@@ -404,7 +442,7 @@ static void gntdev_vma_open(struct vm_area_struct *vma)
 
 static void gntdev_vma_close(struct vm_area_struct *vma)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 	struct file *file = vma->vm_file;
 	struct gntdev_priv *priv = file->private_data;
 
@@ -428,7 +466,7 @@ static void gntdev_vma_close(struct vm_area_struct *vma)
 static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma,
 						 unsigned long addr)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 
 	return map->pages[(addr - map->pages_vm_start) >> PAGE_SHIFT];
 }
@@ -441,7 +479,7 @@ static const struct vm_operations_struct gntdev_vmops = {
 
 /* ------------------------------------------------------------------ */
 
-static void unmap_if_in_range(struct grant_map *map,
+static void unmap_if_in_range(struct gntdev_grant_map *map,
 			      unsigned long start, unsigned long end)
 {
 	unsigned long mstart, mend;
@@ -470,7 +508,7 @@ static void mn_invl_range_start(struct mmu_notifier *mn,
 				unsigned long start, unsigned long end)
 {
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	mutex_lock(&priv->lock);
 	list_for_each_entry(map, &priv->maps, next) {
@@ -486,7 +524,7 @@ static void mn_release(struct mmu_notifier *mn,
 		       struct mm_struct *mm)
 {
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err;
 
 	mutex_lock(&priv->lock);
@@ -531,6 +569,15 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	INIT_LIST_HEAD(&priv->freeable_maps);
 	mutex_init(&priv->lock);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	priv->dmabuf_priv = gntdev_dmabuf_init();
+	if (IS_ERR(priv->dmabuf_priv)) {
+		ret = PTR_ERR(priv->dmabuf_priv);
+		kfree(priv);
+		return ret;
+	}
+#endif
+
 	if (use_ptemod) {
 		priv->mm = get_task_mm(current);
 		if (!priv->mm) {
@@ -548,6 +595,17 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	}
 
 	flip->private_data = priv;
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	priv->dma_dev = gntdev_miscdev.this_device;
+
+	/*
+	 * The device is not spawn from a device tree, so arch_setup_dma_ops
+	 * is not called, thus leaving the device with dummy DMA ops.
+	 * Fix this by calling of_dma_configure() with a NULL node to set
+	 * default DMA ops.
+	 */
+	of_dma_configure(priv->dma_dev, NULL, true);
+#endif
 	pr_debug("priv %p\n", priv);
 
 	return 0;
@@ -556,21 +614,27 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 static int gntdev_release(struct inode *inode, struct file *flip)
 {
 	struct gntdev_priv *priv = flip->private_data;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	pr_debug("priv %p\n", priv);
 
 	mutex_lock(&priv->lock);
 	while (!list_empty(&priv->maps)) {
-		map = list_entry(priv->maps.next, struct grant_map, next);
+		map = list_entry(priv->maps.next,
+				 struct gntdev_grant_map, next);
 		list_del(&map->next);
 		gntdev_put_map(NULL /* already removed */, map);
 	}
 	WARN_ON(!list_empty(&priv->freeable_maps));
 	mutex_unlock(&priv->lock);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	gntdev_dmabuf_fini(priv->dmabuf_priv);
+#endif
+
 	if (use_ptemod)
 		mmu_notifier_unregister(&priv->mn, priv->mm);
+
 	kfree(priv);
 	return 0;
 }
@@ -579,7 +643,7 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 				       struct ioctl_gntdev_map_grant_ref __user *u)
 {
 	struct ioctl_gntdev_map_grant_ref op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -589,11 +653,11 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 		return -EINVAL;
 
 	err = -ENOMEM;
-	map = gntdev_alloc_map(priv, op.count);
+	map = gntdev_alloc_map(priv, op.count, 0 /* This is not a dma-buf. */);
 	if (!map)
 		return err;
 
-	if (unlikely(atomic_add_return(op.count, &pages_mapped) > limit)) {
+	if (unlikely(gntdev_account_mapped_pages(op.count))) {
 		pr_debug("can't map: over limit\n");
 		gntdev_put_map(NULL, map);
 		return err;
@@ -620,7 +684,7 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
 					 struct ioctl_gntdev_unmap_grant_ref __user *u)
 {
 	struct ioctl_gntdev_unmap_grant_ref op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err = -ENOENT;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -646,7 +710,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 {
 	struct ioctl_gntdev_get_offset_for_vaddr op;
 	struct vm_area_struct *vma;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int rv = -EINVAL;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -677,7 +741,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 {
 	struct ioctl_gntdev_unmap_notify op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int rc;
 	int out_flags;
 	unsigned int out_event;
@@ -962,6 +1026,20 @@ static long gntdev_ioctl(struct file *flip,
 	case IOCTL_GNTDEV_GRANT_COPY:
 		return gntdev_ioctl_grant_copy(priv, ptr);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	case IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS:
+		return gntdev_ioctl_dmabuf_exp_from_refs(priv, use_ptemod, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED:
+		return gntdev_ioctl_dmabuf_exp_wait_released(priv, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_IMP_TO_REFS:
+		return gntdev_ioctl_dmabuf_imp_to_refs(priv, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_IMP_RELEASE:
+		return gntdev_ioctl_dmabuf_imp_release(priv, ptr);
+#endif
+
 	default:
 		pr_debug("priv %p, unknown cmd %x\n", priv, cmd);
 		return -ENOIOCTLCMD;
@@ -975,7 +1053,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	struct gntdev_priv *priv = flip->private_data;
 	int index = vma->vm_pgoff;
 	int count = vma_pages(vma);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int i, err = -EINVAL;
 
 	if ((vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_SHARED))
@@ -1032,7 +1110,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		}
 	}
 
-	err = map_grant_pages(map);
+	err = gntdev_map_grant_pages(map);
 	if (err)
 		goto out_put_map;
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index ba9f3eec2bd0..7bafa703a992 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -45,6 +45,9 @@
 #include <linux/workqueue.h>
 #include <linux/ratelimit.h>
 #include <linux/moduleparam.h>
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+#include <linux/dma-mapping.h>
+#endif
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -57,6 +60,7 @@
 #ifdef CONFIG_X86
 #include <asm/xen/cpuid.h>
 #endif
+#include <xen/mem-reservation.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -769,29 +773,18 @@ void gnttab_free_auto_xlat_frames(void)
 }
 EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames);
 
-/**
- * gnttab_alloc_pages - alloc pages suitable for grant mapping into
- * @nr_pages: number of pages to alloc
- * @pages: returns the pages
- */
-int gnttab_alloc_pages(int nr_pages, struct page **pages)
+int gnttab_pages_set_private(int nr_pages, struct page **pages)
 {
 	int i;
-	int ret;
-
-	ret = alloc_xenballooned_pages(nr_pages, pages);
-	if (ret < 0)
-		return ret;
 
 	for (i = 0; i < nr_pages; i++) {
 #if BITS_PER_LONG < 64
 		struct xen_page_foreign *foreign;
 
 		foreign = kzalloc(sizeof(*foreign), GFP_KERNEL);
-		if (!foreign) {
-			gnttab_free_pages(nr_pages, pages);
+		if (!foreign)
 			return -ENOMEM;
-		}
+
 		set_page_private(pages[i], (unsigned long)foreign);
 #endif
 		SetPagePrivate(pages[i]);
@@ -799,14 +792,30 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
+EXPORT_SYMBOL_GPL(gnttab_pages_set_private);
 
 /**
- * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
- * @nr_pages; number of pages to free
- * @pages: the pages
+ * gnttab_alloc_pages - alloc pages suitable for grant mapping into
+ * @nr_pages: number of pages to alloc
+ * @pages: returns the pages
  */
-void gnttab_free_pages(int nr_pages, struct page **pages)
+int gnttab_alloc_pages(int nr_pages, struct page **pages)
+{
+	int ret;
+
+	ret = alloc_xenballooned_pages(nr_pages, pages);
+	if (ret < 0)
+		return ret;
+
+	ret = gnttab_pages_set_private(nr_pages, pages);
+	if (ret < 0)
+		gnttab_free_pages(nr_pages, pages);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
+
+void gnttab_pages_clear_private(int nr_pages, struct page **pages)
 {
 	int i;
 
@@ -818,10 +827,114 @@ void gnttab_free_pages(int nr_pages, struct page **pages)
 			ClearPagePrivate(pages[i]);
 		}
 	}
+}
+EXPORT_SYMBOL_GPL(gnttab_pages_clear_private);
+
+/**
+ * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
+ * @nr_pages; number of pages to free
+ * @pages: the pages
+ */
+void gnttab_free_pages(int nr_pages, struct page **pages)
+{
+	gnttab_pages_clear_private(nr_pages, pages);
 	free_xenballooned_pages(nr_pages, pages);
 }
 EXPORT_SYMBOL_GPL(gnttab_free_pages);
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+/**
+ * gnttab_dma_alloc_pages - alloc DMAable pages suitable for grant mapping into
+ * @args: arguments to the function
+ */
+int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args)
+{
+	unsigned long pfn, start_pfn;
+	size_t size;
+	int i, ret;
+
+	size = args->nr_pages << PAGE_SHIFT;
+	if (args->coherent)
+		args->vaddr = dma_alloc_coherent(args->dev, size,
+						 &args->dev_bus_addr,
+						 GFP_KERNEL | __GFP_NOWARN);
+	else
+		args->vaddr = dma_alloc_wc(args->dev, size,
+					   &args->dev_bus_addr,
+					   GFP_KERNEL | __GFP_NOWARN);
+	if (!args->vaddr) {
+		pr_debug("Failed to allocate DMA buffer of size %zu\n", size);
+		return -ENOMEM;
+	}
+
+	start_pfn = __phys_to_pfn(args->dev_bus_addr);
+	for (pfn = start_pfn, i = 0; pfn < start_pfn + args->nr_pages;
+			pfn++, i++) {
+		struct page *page = pfn_to_page(pfn);
+
+		args->pages[i] = page;
+		args->frames[i] = xen_page_to_gfn(page);
+		xenmem_reservation_scrub_page(page);
+	}
+
+	xenmem_reservation_va_mapping_reset(args->nr_pages, args->pages);
+
+	ret = xenmem_reservation_decrease(args->nr_pages, args->frames);
+	if (ret != args->nr_pages) {
+		pr_debug("Failed to decrease reservation for DMA buffer\n");
+		ret = -EFAULT;
+		goto fail;
+	}
+
+	ret = gnttab_pages_set_private(args->nr_pages, args->pages);
+	if (ret < 0)
+		goto fail;
+
+	return 0;
+
+fail:
+	gnttab_dma_free_pages(args);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_dma_alloc_pages);
+
+/**
+ * gnttab_dma_free_pages - free DMAable pages
+ * @args: arguments to the function
+ */
+int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args)
+{
+	size_t size;
+	int i, ret;
+
+	gnttab_pages_clear_private(args->nr_pages, args->pages);
+
+	for (i = 0; i < args->nr_pages; i++)
+		args->frames[i] = page_to_xen_pfn(args->pages[i]);
+
+	ret = xenmem_reservation_increase(args->nr_pages, args->frames);
+	if (ret != args->nr_pages) {
+		pr_debug("Failed to decrease reservation for DMA buffer\n");
+		ret = -EFAULT;
+	} else {
+		ret = 0;
+	}
+
+	xenmem_reservation_va_mapping_update(args->nr_pages, args->pages,
+					     args->frames);
+
+	size = args->nr_pages << PAGE_SHIFT;
+	if (args->coherent)
+		dma_free_coherent(args->dev, size,
+				  args->vaddr, args->dev_bus_addr);
+	else
+		dma_free_wc(args->dev, size,
+			    args->vaddr, args->dev_bus_addr);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_dma_free_pages);
+#endif
+
 /* Handling of paged out grant targets (GNTST_eagain) */
 #define MAX_DELAY 256
 static inline void
diff --git a/drivers/xen/mem-reservation.c b/drivers/xen/mem-reservation.c
new file mode 100644
index 000000000000..084799c6180e
--- /dev/null
+++ b/drivers/xen/mem-reservation.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/******************************************************************************
+ * Xen memory reservation utilities.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ * Copyright (c) 2010 Daniel Kiper
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#include <asm/xen/hypercall.h>
+
+#include <xen/interface/memory.h>
+#include <xen/mem-reservation.h>
+
+/*
+ * Use one extent per PAGE_SIZE to avoid to break down the page into
+ * multiple frame.
+ */
+#define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1)
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+void __xenmem_reservation_va_mapping_update(unsigned long count,
+					    struct page **pages,
+					    xen_pfn_t *frames)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = pages[i];
+		unsigned long pfn = page_to_pfn(page);
+
+		BUG_ON(!page);
+
+		/*
+		 * We don't support PV MMU when Linux and Xen is using
+		 * different page granularity.
+		 */
+		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
+
+		set_phys_to_machine(pfn, frames[i]);
+
+		/* Link back into the page tables if not highmem. */
+		if (!PageHighMem(page)) {
+			int ret;
+
+			ret = HYPERVISOR_update_va_mapping(
+					(unsigned long)__va(pfn << PAGE_SHIFT),
+					mfn_pte(frames[i], PAGE_KERNEL),
+					0);
+			BUG_ON(ret);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_update);
+
+void __xenmem_reservation_va_mapping_reset(unsigned long count,
+					   struct page **pages)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = pages[i];
+		unsigned long pfn = page_to_pfn(page);
+
+		/*
+		 * We don't support PV MMU when Linux and Xen are using
+		 * different page granularity.
+		 */
+		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
+
+		if (!PageHighMem(page)) {
+			int ret;
+
+			ret = HYPERVISOR_update_va_mapping(
+					(unsigned long)__va(pfn << PAGE_SHIFT),
+					__pte_ma(0), 0);
+			BUG_ON(ret);
+		}
+		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	}
+}
+EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_reset);
+#endif /* CONFIG_XEN_HAVE_PVMMU */
+
+/* @frames is an array of PFNs */
+int xenmem_reservation_increase(int count, xen_pfn_t *frames)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = EXTENT_ORDER,
+		.domid        = DOMID_SELF
+	};
+
+	/* XENMEM_populate_physmap requires a PFN based on Xen granularity. */
+	set_xen_guest_handle(reservation.extent_start, frames);
+	reservation.nr_extents = count;
+	return HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
+}
+EXPORT_SYMBOL_GPL(xenmem_reservation_increase);
+
+/* @frames is an array of GFNs */
+int xenmem_reservation_decrease(int count, xen_pfn_t *frames)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = EXTENT_ORDER,
+		.domid        = DOMID_SELF
+	};
+
+	/* XENMEM_decrease_reservation requires a GFN */
+	set_xen_guest_handle(reservation.extent_start, frames);
+	reservation.nr_extents = count;
+	return HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+}
+EXPORT_SYMBOL_GPL(xenmem_reservation_decrease);
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index b437fccd4e62..294f35ce9e46 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -81,7 +81,7 @@ static void watch_target(struct xenbus_watch *watch,
 			static_max = new_target;
 		else
 			static_max >>= PAGE_SHIFT - 10;
-		target_diff = xen_pv_domain() ? 0
+		target_diff = (xen_pv_domain() || xen_initial_domain()) ? 0
 				: static_max - balloon_stats.target_pages;
 	}
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 42e102e2e74a..85ff859d3af5 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -859,8 +859,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 
 static int
 v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
-		     struct file *file, unsigned flags, umode_t mode,
-		     int *opened)
+		     struct file *file, unsigned flags, umode_t mode)
 {
 	int err;
 	u32 perm;
@@ -917,7 +916,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		v9inode->writeback_fid = (void *) inode_fid;
 	}
 	mutex_unlock(&v9inode->v_mutex);
-	err = finish_open(file, dentry, generic_file_open, opened);
+	err = finish_open(file, dentry, generic_file_open);
 	if (err)
 		goto error;
 
@@ -925,7 +924,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(d_inode(dentry), file);
 
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 out:
 	dput(res);
 	return err;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 7f6ae21a27b3..4823e1c46999 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -241,8 +241,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 
 static int
 v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
-			  struct file *file, unsigned flags, umode_t omode,
-			  int *opened)
+			  struct file *file, unsigned flags, umode_t omode)
 {
 	int err = 0;
 	kgid_t gid;
@@ -352,13 +351,13 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	}
 	mutex_unlock(&v9inode->v_mutex);
 	/* Since we are opening a file, assign the open fid to the file */
-	err = finish_open(file, dentry, generic_file_open, opened);
+	err = finish_open(file, dentry, generic_file_open);
 	if (err)
 		goto err_clunk_old_fid;
 	file->private_data = ofid;
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(inode, file);
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 out:
 	v9fs_put_acl(dacl, pacl);
 	dput(res);
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index c836c425ca94..e91028d4340a 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -287,7 +287,7 @@ adfs_iget(struct super_block *sb, struct object_info *obj)
 		ADFS_I(inode)->mmu_private = inode->i_size;
 	}
 
-	insert_inode_hash(inode);
+	inode_fake_hash(inode);
 
 out:
 	return inode;
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 71fa525d63a0..7e099a7a4eb1 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -291,6 +291,7 @@ static void destroy_inodecache(void)
 static const struct super_operations adfs_sops = {
 	.alloc_inode	= adfs_alloc_inode,
 	.destroy_inode	= adfs_destroy_inode,
+	.drop_inode	= generic_delete_inode,
 	.write_inode	= adfs_write_inode,
 	.put_super	= adfs_put_super,
 	.statfs		= adfs_statfs,
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 7d623008157f..855bf2b79fed 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -822,6 +822,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 {
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct inode *inode;
+	struct dentry *d;
 	struct key *key;
 	int ret;
 
@@ -862,43 +863,17 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 
 	afs_stat_v(dvnode, n_lookup);
 	inode = afs_do_lookup(dir, dentry, key);
-	if (IS_ERR(inode)) {
-		ret = PTR_ERR(inode);
-		if (ret == -ENOENT) {
-			inode = afs_try_auto_mntpt(dentry, dir);
-			if (!IS_ERR(inode)) {
-				key_put(key);
-				goto success;
-			}
-
-			ret = PTR_ERR(inode);
-		}
-
-		key_put(key);
-		if (ret == -ENOENT) {
-			d_add(dentry, NULL);
-			_leave(" = NULL [negative]");
-			return NULL;
-		}
-		_leave(" = %d [do]", ret);
-		return ERR_PTR(ret);
-	}
-	dentry->d_fsdata = (void *)(unsigned long)dvnode->status.data_version;
-
-	/* instantiate the dentry */
 	key_put(key);
-	if (IS_ERR(inode)) {
-		_leave(" = %ld", PTR_ERR(inode));
-		return ERR_CAST(inode);
+	if (inode == ERR_PTR(-ENOENT)) {
+		inode = afs_try_auto_mntpt(dentry, dir);
+	} else {
+		dentry->d_fsdata =
+			(void *)(unsigned long)dvnode->status.data_version;
 	}
-
-success:
-	d_add(dentry, inode);
-	_leave(" = 0 { ino=%lu v=%u }",
-	       d_inode(dentry)->i_ino,
-	       d_inode(dentry)->i_generation);
-
-	return NULL;
+	d = d_splice_alias(inode, dentry);
+	if (!IS_ERR_OR_NULL(d))
+		d->d_fsdata = dentry->d_fsdata;
+	return d;
 }
 
 /*
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 174e843f0633..1cde710a8013 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -83,7 +83,7 @@ struct inode *afs_try_auto_mntpt(struct dentry *dentry, struct inode *dir)
 
 out:
 	_leave("= %d", ret);
-	return ERR_PTR(ret);
+	return ret == -ENOENT ? NULL : ERR_PTR(ret);
 }
 
 /*
@@ -141,12 +141,6 @@ out_p:
 static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
 					 unsigned int flags)
 {
-	struct afs_vnode *vnode;
-	struct inode *inode;
-	int ret;
-
-	vnode = AFS_FS_I(dir);
-
 	_enter("%pd", dentry);
 
 	ASSERTCMP(d_inode(dentry), ==, NULL);
@@ -160,22 +154,7 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr
 	    memcmp(dentry->d_name.name, "@cell", 5) == 0)
 		return afs_lookup_atcell(dentry);
 
-	inode = afs_try_auto_mntpt(dentry, dir);
-	if (IS_ERR(inode)) {
-		ret = PTR_ERR(inode);
-		if (ret == -ENOENT) {
-			d_add(dentry, NULL);
-			_leave(" = NULL [negative]");
-			return NULL;
-		}
-		_leave(" = %d [do]", ret);
-		return ERR_PTR(ret);
-	}
-
-	d_add(dentry, inode);
-	_leave(" = 0 { ino=%lu v=%u }",
-	       d_inode(dentry)->i_ino, d_inode(dentry)->i_generation);
-	return NULL;
+	return d_splice_alias(afs_try_auto_mntpt(dentry, dir), dentry);
 }
 
 const struct inode_operations afs_dynroot_inode_operations = {
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index a1b18082991b..183cc5418722 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -648,7 +648,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
 	trace_afs_notify_call(rxcall, call);
 	call->need_attention = true;
 
-	u = __atomic_add_unless(&call->usage, 1, 0);
+	u = atomic_fetch_add_unless(&call->usage, 1, 0);
 	if (u != 0) {
 		trace_afs_call(call, afs_call_trace_wake, u,
 			       atomic_read(&call->net->nr_outstanding_calls),
diff --git a/fs/aio.c b/fs/aio.c
index e1d20124ec0e..b9350f3360c6 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -19,6 +19,7 @@
 #include <linux/export.h>
 #include <linux/syscalls.h>
 #include <linux/backing-dev.h>
+#include <linux/refcount.h>
 #include <linux/uio.h>
 
 #include <linux/sched/signal.h>
@@ -167,13 +168,12 @@ struct fsync_iocb {
 
 struct poll_iocb {
 	struct file		*file;
-	__poll_t		events;
 	struct wait_queue_head	*head;
-
-	union {
-		struct wait_queue_entry	wait;
-		struct work_struct	work;
-	};
+	__poll_t		events;
+	bool			woken;
+	bool			cancelled;
+	struct wait_queue_entry	wait;
+	struct work_struct	work;
 };
 
 struct aio_kiocb {
@@ -191,6 +191,7 @@ struct aio_kiocb {
 
 	struct list_head	ki_list;	/* the aio core uses this
 						 * for cancellation */
+	refcount_t		ki_refcnt;
 
 	/*
 	 * If the aio_resfd field of the userspace iocb is not zero,
@@ -215,9 +216,7 @@ static const struct address_space_operations aio_ctx_aops;
 
 static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 {
-	struct qstr this = QSTR_INIT("[aio]", 5);
 	struct file *file;
-	struct path path;
 	struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
@@ -226,31 +225,17 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 	inode->i_mapping->private_data = ctx;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
-	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
-	if (!path.dentry) {
+	file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
+				O_RDWR, &aio_ring_fops);
+	if (IS_ERR(file))
 		iput(inode);
-		return ERR_PTR(-ENOMEM);
-	}
-	path.mnt = mntget(aio_mnt);
-
-	d_instantiate(path.dentry, inode);
-	file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops);
-	if (IS_ERR(file)) {
-		path_put(&path);
-		return file;
-	}
-
-	file->f_flags = O_RDWR;
 	return file;
 }
 
 static struct dentry *aio_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
-	static const struct dentry_operations ops = {
-		.d_dname	= simple_dname,
-	};
-	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, NULL,
 					   AIO_RING_MAGIC);
 
 	if (!IS_ERR(root))
@@ -1028,6 +1013,7 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 
 	percpu_ref_get(&ctx->reqs);
 	INIT_LIST_HEAD(&req->ki_list);
+	refcount_set(&req->ki_refcnt, 0);
 	req->ki_ctx = ctx;
 	return req;
 out_put:
@@ -1062,6 +1048,15 @@ out:
 	return ret;
 }
 
+static inline void iocb_put(struct aio_kiocb *iocb)
+{
+	if (refcount_read(&iocb->ki_refcnt) == 0 ||
+	    refcount_dec_and_test(&iocb->ki_refcnt)) {
+		percpu_ref_put(&iocb->ki_ctx->reqs);
+		kmem_cache_free(kiocb_cachep, iocb);
+	}
+}
+
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
@@ -1131,8 +1126,6 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 		eventfd_ctx_put(iocb->ki_eventfd);
 	}
 
-	kmem_cache_free(kiocb_cachep, iocb);
-
 	/*
 	 * We have to order our ring_info tail store above and test
 	 * of the wait list below outside the wait lock.  This is
@@ -1143,8 +1136,7 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
-
-	percpu_ref_put(&ctx->reqs);
+	iocb_put(iocb);
 }
 
 /* aio_read_events_ring
@@ -1590,6 +1582,7 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
 	if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
 			iocb->aio_rw_flags))
 		return -EINVAL;
+
 	req->file = fget(iocb->aio_fildes);
 	if (unlikely(!req->file))
 		return -EBADF;
@@ -1604,46 +1597,58 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
 	return 0;
 }
 
-/* need to use list_del_init so we can check if item was present */
-static inline bool __aio_poll_remove(struct poll_iocb *req)
+static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
 {
-	if (list_empty(&req->wait.entry))
-		return false;
-	list_del_init(&req->wait.entry);
-	return true;
-}
+	struct file *file = iocb->poll.file;
 
-static inline void __aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
-{
-	fput(iocb->poll.file);
 	aio_complete(iocb, mangle_poll(mask), 0);
+	fput(file);
 }
 
-static void aio_poll_work(struct work_struct *work)
+static void aio_poll_complete_work(struct work_struct *work)
 {
-	struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, poll.work);
+	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
+	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+	struct poll_table_struct pt = { ._key = req->events };
+	struct kioctx *ctx = iocb->ki_ctx;
+	__poll_t mask = 0;
 
-	if (!list_empty_careful(&iocb->ki_list))
-		aio_remove_iocb(iocb);
-	__aio_poll_complete(iocb, iocb->poll.events);
+	if (!READ_ONCE(req->cancelled))
+		mask = vfs_poll(req->file, &pt) & req->events;
+
+	/*
+	 * Note that ->ki_cancel callers also delete iocb from active_reqs after
+	 * calling ->ki_cancel.  We need the ctx_lock roundtrip here to
+	 * synchronize with them.  In the cancellation case the list_del_init
+	 * itself is not actually needed, but harmless so we keep it in to
+	 * avoid further branches in the fast path.
+	 */
+	spin_lock_irq(&ctx->ctx_lock);
+	if (!mask && !READ_ONCE(req->cancelled)) {
+		add_wait_queue(req->head, &req->wait);
+		spin_unlock_irq(&ctx->ctx_lock);
+		return;
+	}
+	list_del_init(&iocb->ki_list);
+	spin_unlock_irq(&ctx->ctx_lock);
+
+	aio_poll_complete(iocb, mask);
 }
 
+/* assumes we are called with irqs disabled */
 static int aio_poll_cancel(struct kiocb *iocb)
 {
 	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
 	struct poll_iocb *req = &aiocb->poll;
-	struct wait_queue_head *head = req->head;
-	bool found = false;
-
-	spin_lock(&head->lock);
-	found = __aio_poll_remove(req);
-	spin_unlock(&head->lock);
 
-	if (found) {
-		req->events = 0;
-		INIT_WORK(&req->work, aio_poll_work);
-		schedule_work(&req->work);
+	spin_lock(&req->head->lock);
+	WRITE_ONCE(req->cancelled, true);
+	if (!list_empty(&req->wait.entry)) {
+		list_del_init(&req->wait.entry);
+		schedule_work(&aiocb->poll.work);
 	}
+	spin_unlock(&req->head->lock);
+
 	return 0;
 }
 
@@ -1652,44 +1657,59 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 {
 	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
 	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
-	struct file *file = req->file;
 	__poll_t mask = key_to_poll(key);
 
-	assert_spin_locked(&req->head->lock);
+	req->woken = true;
 
 	/* for instances that support it check for an event match first: */
-	if (mask && !(mask & req->events))
-		return 0;
+	if (mask) {
+		if (!(mask & req->events))
+			return 0;
+
+		/* try to complete the iocb inline if we can: */
+		if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
+			list_del(&iocb->ki_list);
+			spin_unlock(&iocb->ki_ctx->ctx_lock);
+
+			list_del_init(&req->wait.entry);
+			aio_poll_complete(iocb, mask);
+			return 1;
+		}
+	}
 
-	mask = file->f_op->poll_mask(file, req->events) & req->events;
-	if (!mask)
-		return 0;
+	list_del_init(&req->wait.entry);
+	schedule_work(&req->work);
+	return 1;
+}
 
-	__aio_poll_remove(req);
+struct aio_poll_table {
+	struct poll_table_struct	pt;
+	struct aio_kiocb		*iocb;
+	int				error;
+};
 
-	/*
-	 * Try completing without a context switch if we can acquire ctx_lock
-	 * without spinning.  Otherwise we need to defer to a workqueue to
-	 * avoid a deadlock due to the lock order.
-	 */
-	if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
-		list_del_init(&iocb->ki_list);
-		spin_unlock(&iocb->ki_ctx->ctx_lock);
+static void
+aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
+		struct poll_table_struct *p)
+{
+	struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt);
 
-		__aio_poll_complete(iocb, mask);
-	} else {
-		req->events = mask;
-		INIT_WORK(&req->work, aio_poll_work);
-		schedule_work(&req->work);
+	/* multiple wait queues per file are not supported */
+	if (unlikely(pt->iocb->poll.head)) {
+		pt->error = -EINVAL;
+		return;
 	}
 
-	return 1;
+	pt->error = 0;
+	pt->iocb->poll.head = head;
+	add_wait_queue(head, &pt->iocb->poll.wait);
 }
 
 static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
 {
 	struct kioctx *ctx = aiocb->ki_ctx;
 	struct poll_iocb *req = &aiocb->poll;
+	struct aio_poll_table apt;
 	__poll_t mask;
 
 	/* reject any unknown events outside the normal event mask. */
@@ -1699,40 +1719,58 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
 	if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
 		return -EINVAL;
 
+	INIT_WORK(&req->work, aio_poll_complete_work);
 	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
 	req->file = fget(iocb->aio_fildes);
 	if (unlikely(!req->file))
 		return -EBADF;
-	if (!file_has_poll_mask(req->file))
-		goto out_fail;
-
-	req->head = req->file->f_op->get_poll_head(req->file, req->events);
-	if (!req->head)
-		goto out_fail;
-	if (IS_ERR(req->head)) {
-		mask = EPOLLERR;
-		goto done;
-	}
 
+	apt.pt._qproc = aio_poll_queue_proc;
+	apt.pt._key = req->events;
+	apt.iocb = aiocb;
+	apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
+
+	/* initialized the list so that we can do list_empty checks */
+	INIT_LIST_HEAD(&req->wait.entry);
 	init_waitqueue_func_entry(&req->wait, aio_poll_wake);
-	aiocb->ki_cancel = aio_poll_cancel;
+
+	/* one for removal from waitqueue, one for this function */
+	refcount_set(&aiocb->ki_refcnt, 2);
+
+	mask = vfs_poll(req->file, &apt.pt) & req->events;
+	if (unlikely(!req->head)) {
+		/* we did not manage to set up a waitqueue, done */
+		goto out;
+	}
 
 	spin_lock_irq(&ctx->ctx_lock);
 	spin_lock(&req->head->lock);
-	mask = req->file->f_op->poll_mask(req->file, req->events) & req->events;
-	if (!mask) {
-		__add_wait_queue(req->head, &req->wait);
+	if (req->woken) {
+		/* wake_up context handles the rest */
+		mask = 0;
+		apt.error = 0;
+	} else if (mask || apt.error) {
+		/* if we get an error or a mask we are done */
+		WARN_ON_ONCE(list_empty(&req->wait.entry));
+		list_del_init(&req->wait.entry);
+	} else {
+		/* actually waiting for an event */
 		list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+		aiocb->ki_cancel = aio_poll_cancel;
 	}
 	spin_unlock(&req->head->lock);
 	spin_unlock_irq(&ctx->ctx_lock);
-done:
+
+out:
+	if (unlikely(apt.error)) {
+		fput(req->file);
+		return apt.error;
+	}
+
 	if (mask)
-		__aio_poll_complete(aiocb, mask);
+		aio_poll_complete(aiocb, mask);
+	iocb_put(aiocb);
 	return 0;
-out_fail:
-	fput(req->file);
-	return -EINVAL; /* same as no support for IOCB_CMD_POLL */
 }
 
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
@@ -2042,6 +2080,11 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
 	return ret;
 }
 
+struct __aio_sigset {
+	const sigset_t __user	*sigmask;
+	size_t		sigsetsize;
+};
+
 SYSCALL_DEFINE6(io_pgetevents,
 		aio_context_t, ctx_id,
 		long, min_nr,
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 3168ee4e77f4..91262c34b797 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -71,8 +71,6 @@ struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
 
 	if (IS_ERR(anon_inode_inode))
@@ -82,39 +80,23 @@ struct file *anon_inode_getfile(const char *name,
 		return ERR_PTR(-ENOENT);
 
 	/*
-	 * Link the inode to a directory entry by creating a unique name
-	 * using the inode sequence number.
-	 */
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
-	if (!path.dentry)
-		goto err_module;
-
-	path.mnt = mntget(anon_inode_mnt);
-	/*
 	 * We know the anon_inode inode count is always greater than zero,
 	 * so ihold() is safe.
 	 */
 	ihold(anon_inode_inode);
-
-	d_instantiate(path.dentry, anon_inode_inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file_pseudo(anon_inode_inode, anon_inode_mnt, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file))
-		goto err_dput;
+		goto err;
+
 	file->f_mapping = anon_inode_inode->i_mapping;
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
 
-err_dput:
-	path_put(&path);
-err_module:
+err:
+	iput(anon_inode_inode);
 	module_put(fops->owner);
 	return file;
 }
diff --git a/fs/attr.c b/fs/attr.c
index e3d53bf12240..d22e8187477f 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -120,7 +120,6 @@ EXPORT_SYMBOL(setattr_prepare);
  * inode_newsize_ok - may this inode be truncated to a given size
  * @inode:	the inode to be truncated
  * @offset:	the new size to assign to the inode
- * @Returns:	0 on success, -ve errno on failure
  *
  * inode_newsize_ok must be called with i_mutex held.
  *
@@ -130,6 +129,8 @@ EXPORT_SYMBOL(setattr_prepare);
  * returned. @inode must be a file (not directory), with appropriate
  * permissions to allow truncate (inode_newsize_ok does NOT check these
  * conditions).
+ *
+ * Return: 0 on success, -ve errno on failure
  */
 int inode_newsize_ok(const struct inode *inode, loff_t offset)
 {
@@ -205,7 +206,7 @@ EXPORT_SYMBOL(setattr_copy);
 /**
  * notify_change - modify attributes of a filesytem object
  * @dentry:	object affected
- * @iattr:	new attributes
+ * @attr:	new attributes
  * @delegated_inode: returns inode, if the inode is delegated
  *
  * The caller must hold the i_mutex on the affected object.
diff --git a/fs/autofs/Makefile b/fs/autofs/Makefile
index 43fedde15c26..1f85d35ec8b7 100644
--- a/fs/autofs/Makefile
+++ b/fs/autofs/Makefile
@@ -2,6 +2,6 @@
 # Makefile for the linux autofs-filesystem routines.
 #
 
-obj-$(CONFIG_AUTOFS_FS) += autofs.o
+obj-$(CONFIG_AUTOFS_FS) += autofs4.o
 
-autofs-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o
+autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o
diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c
index ea4ca1445ab7..86eafda4a652 100644
--- a/fs/autofs/dev-ioctl.c
+++ b/fs/autofs/dev-ioctl.c
@@ -135,6 +135,15 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
 				cmd);
 			goto out;
 		}
+	} else {
+		unsigned int inr = _IOC_NR(cmd);
+
+		if (inr == AUTOFS_DEV_IOCTL_OPENMOUNT_CMD ||
+		    inr == AUTOFS_DEV_IOCTL_REQUESTER_CMD ||
+		    inr == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) {
+			err = -EINVAL;
+			goto out;
+		}
 	}
 
 	err = 0;
@@ -271,7 +280,8 @@ static int autofs_dev_ioctl_openmount(struct file *fp,
 	dev_t devid;
 	int err, fd;
 
-	/* param->path has already been checked */
+	/* param->path has been checked in validate_dev_ioctl() */
+
 	if (!param->openmount.devid)
 		return -EINVAL;
 
@@ -433,10 +443,7 @@ static int autofs_dev_ioctl_requester(struct file *fp,
 	dev_t devid;
 	int err = -ENOENT;
 
-	if (param->size <= AUTOFS_DEV_IOCTL_SIZE) {
-		err = -EINVAL;
-		goto out;
-	}
+	/* param->path has been checked in validate_dev_ioctl() */
 
 	devid = sbi->sb->s_dev;
 
@@ -521,10 +528,7 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp,
 	unsigned int devid, magic;
 	int err = -ENOENT;
 
-	if (param->size <= AUTOFS_DEV_IOCTL_SIZE) {
-		err = -EINVAL;
-		goto out;
-	}
+	/* param->path has been checked in validate_dev_ioctl() */
 
 	name = param->path;
 	type = param->ismountpoint.in.type;
diff --git a/fs/autofs/init.c b/fs/autofs/init.c
index cc9447e1903f..79ae07d9592f 100644
--- a/fs/autofs/init.c
+++ b/fs/autofs/init.c
@@ -23,7 +23,7 @@ static struct file_system_type autofs_fs_type = {
 	.kill_sb	= autofs_kill_sb,
 };
 MODULE_ALIAS_FS("autofs");
-MODULE_ALIAS("autofs4");
+MODULE_ALIAS("autofs");
 
 static int __init init_autofs_fs(void)
 {
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 125e8bbd22a2..8035d2a44561 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -134,7 +134,7 @@ static int bad_inode_update_time(struct inode *inode, struct timespec64 *time,
 
 static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry,
 				 struct file *file, unsigned int open_flag,
-				 umode_t create_mode, int *opened)
+				 umode_t create_mode)
 {
 	return -EIO;
 }
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 0ac456b52bdd..efae2fb0930a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1259,9 +1259,8 @@ static int load_elf_library(struct file *file)
 		goto out_free_ph;
 	}
 
-	len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr +
-			    ELF_MIN_ALIGN - 1);
-	bss = eppnt->p_memsz + eppnt->p_vaddr;
+	len = ELF_PAGEALIGN(eppnt->p_filesz + eppnt->p_vaddr);
+	bss = ELF_PAGEALIGN(eppnt->p_memsz + eppnt->p_vaddr);
 	if (bss > len) {
 		error = vm_brk(len, bss - len);
 		if (error)
@@ -1752,7 +1751,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 		const struct user_regset *regset = &view->regsets[i];
 		do_thread_regset_writeback(t->task, regset);
 		if (regset->core_note_type && regset->get &&
-		    (!regset->active || regset->active(t->task, regset))) {
+		    (!regset->active || regset->active(t->task, regset) > 0)) {
 			int ret;
 			size_t size = regset_size(t->task, regset);
 			void *data = kmalloc(size, GFP_KERNEL);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 4b5fff31ef27..aa4a7a23ff99 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -205,7 +205,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		goto error;
 
 	if (fmt->flags & MISC_FMT_OPEN_FILE) {
-		interp_file = filp_clone_open(fmt->interp_file);
+		interp_file = file_clone_open(fmt->interp_file);
 		if (!IS_ERR(interp_file))
 			deny_write_access(interp_file);
 	} else {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0dd87aaeb39a..38b8ce05cbc7 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -221,7 +221,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 
 	ret = bio_iov_iter_get_pages(&bio, iter);
 	if (unlikely(ret))
-		return ret;
+		goto out;
 	ret = bio.bi_iter.bi_size;
 
 	if (iov_iter_rw(iter) == READ) {
@@ -250,12 +250,13 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 		put_page(bvec->bv_page);
 	}
 
-	if (vecs != inline_vecs)
-		kfree(vecs);
-
 	if (unlikely(bio.bi_status))
 		ret = blk_status_to_errno(bio.bi_status);
 
+out:
+	if (vecs != inline_vecs)
+		kfree(vecs);
+
 	bio_uninit(&bio);
 
 	return ret;
@@ -665,7 +666,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	result = blk_queue_enter(bdev->bd_queue, 0);
 	if (result)
 		return result;
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_READ);
 	blk_queue_exit(bdev->bd_queue);
 	return result;
 }
@@ -703,7 +705,8 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 		return result;
 
 	set_page_writeback(page);
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_WRITE);
 	if (result) {
 		end_page_writeback(page);
 	} else {
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 15e1dfef56a5..3b66c957ea6f 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -30,23 +30,22 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
-		BUG();
+		return ERR_PTR(-EINVAL);
 	}
 
-	size = btrfs_getxattr(inode, name, "", 0);
+	size = btrfs_getxattr(inode, name, NULL, 0);
 	if (size > 0) {
 		value = kzalloc(size, GFP_KERNEL);
 		if (!value)
 			return ERR_PTR(-ENOMEM);
 		size = btrfs_getxattr(inode, name, value, size);
 	}
-	if (size > 0) {
+	if (size > 0)
 		acl = posix_acl_from_xattr(&init_user_ns, value, size);
-	} else if (size == -ERANGE || size == -ENODATA || size == 0) {
+	else if (size == -ENODATA || size == 0)
 		acl = NULL;
-	} else {
-		acl = ERR_PTR(-EIO);
-	}
+	else
+		acl = ERR_PTR(size);
 	kfree(value);
 
 	return acl;
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 0a8e2e29a66b..ae750b1574a2 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -925,7 +925,7 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info,
 		type = btrfs_get_extent_inline_ref_type(leaf, iref,
 							BTRFS_REF_TYPE_ANY);
 		if (type == BTRFS_REF_TYPE_INVALID)
-			return -EINVAL;
+			return -EUCLEAN;
 
 		offset = btrfs_extent_inline_ref_offset(leaf, iref);
 
@@ -1793,7 +1793,7 @@ static int get_extent_inline_ref(unsigned long *ptr,
 	*out_type = btrfs_get_extent_inline_ref_type(eb, *out_eiref,
 						     BTRFS_REF_TYPE_ANY);
 	if (*out_type == BTRFS_REF_TYPE_INVALID)
-		return -EINVAL;
+		return -EUCLEAN;
 
 	*ptr += btrfs_extent_inline_ref_size(*out_type);
 	WARN_ON(*ptr > end);
@@ -2225,7 +2225,7 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 
 	fspath = init_data_container(total_bytes);
 	if (IS_ERR(fspath))
-		return (void *)fspath;
+		return ERR_CAST(fspath);
 
 	ifp = kmalloc(sizeof(*ifp), GFP_KERNEL);
 	if (!ifp) {
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 7e075343daa5..1343ac57b438 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -178,7 +178,7 @@ struct btrfs_inode {
 	struct btrfs_delayed_node *delayed_node;
 
 	/* File creation time. */
-	struct timespec i_otime;
+	struct timespec64 i_otime;
 
 	/* Hook into fs_info->delayed_iputs */
 	struct list_head delayed_iput;
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index a3fdb4fe967d..833cf3c35b4d 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1539,7 +1539,12 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
 	}
 
 	device = multi->stripes[0].dev;
-	block_ctx_out->dev = btrfsic_dev_state_lookup(device->bdev->bd_dev);
+	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state) ||
+	    !device->bdev || !device->name)
+		block_ctx_out->dev = NULL;
+	else
+		block_ctx_out->dev = btrfsic_dev_state_lookup(
+							device->bdev->bd_dev);
 	block_ctx_out->dev_bytenr = multi->stripes[0].physical;
 	block_ctx_out->start = bytenr;
 	block_ctx_out->len = len;
@@ -1624,7 +1629,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 		bio = btrfs_io_bio_alloc(num_pages - i);
 		bio_set_dev(bio, block_ctx->dev->bdev);
 		bio->bi_iter.bi_sector = dev_bytenr >> 9;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		for (j = i; j < num_pages; j++) {
 			ret = bio_add_page(bio, block_ctx->pagev[j],
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d3e447b45bf7..9bfa66592aa7 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -5,7 +5,6 @@
 
 #include <linux/kernel.h>
 #include <linux/bio.h>
-#include <linux/buffer_head.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
@@ -14,10 +13,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
-#include <linux/bit_spinlock.h>
 #include <linux/slab.h>
 #include <linux/sched/mm.h>
 #include <linux/log2.h>
@@ -303,7 +299,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	struct bio *bio = NULL;
 	struct compressed_bio *cb;
 	unsigned long bytes_left;
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	int pg_index = 0;
 	struct page *page;
 	u64 first_byte = disk_start;
@@ -342,9 +337,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		page = compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		if (bio->bi_iter.bi_size)
-			submit = io_tree->ops->merge_bio_hook(page, 0,
-							   PAGE_SIZE,
-							   bio, 0);
+			submit = btrfs_merge_bio_hook(page, 0, PAGE_SIZE, bio, 0);
 
 		page->mapping = NULL;
 		if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) <
@@ -613,7 +606,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	cb->len = bio->bi_iter.bi_size;
 
 	comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
-	bio_set_op_attrs (comp_bio, REQ_OP_READ, 0);
+	comp_bio->bi_opf = REQ_OP_READ;
 	comp_bio->bi_private = cb;
 	comp_bio->bi_end_io = end_compressed_bio_read;
 	refcount_set(&cb->pending_bios, 1);
@@ -626,9 +619,8 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		page->index = em_start >> PAGE_SHIFT;
 
 		if (comp_bio->bi_iter.bi_size)
-			submit = tree->ops->merge_bio_hook(page, 0,
-							PAGE_SIZE,
-							comp_bio, 0);
+			submit = btrfs_merge_bio_hook(page, 0, PAGE_SIZE,
+					comp_bio, 0);
 
 		page->mapping = NULL;
 		if (submit || bio_add_page(comp_bio, page, PAGE_SIZE, 0) <
@@ -660,7 +652,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			}
 
 			comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
-			bio_set_op_attrs(comp_bio, REQ_OP_READ, 0);
+			comp_bio->bi_opf = REQ_OP_READ;
 			comp_bio->bi_private = cb;
 			comp_bio->bi_end_io = end_compressed_bio_read;
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 4bc326df472e..d436fb4c002e 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -888,11 +888,7 @@ int btrfs_block_can_be_shared(struct btrfs_root *root,
 	     btrfs_root_last_snapshot(&root->root_item) ||
 	     btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
 		return 1;
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
-	    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
-		return 1;
-#endif
+
 	return 0;
 }
 
@@ -3128,8 +3124,7 @@ again:
  * higher levels
  *
  */
-static void fixup_low_keys(struct btrfs_fs_info *fs_info,
-			   struct btrfs_path *path,
+static void fixup_low_keys(struct btrfs_path *path,
 			   struct btrfs_disk_key *key, int level)
 {
 	int i;
@@ -3181,7 +3176,7 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
 	btrfs_set_item_key(eb, &disk_key, slot);
 	btrfs_mark_buffer_dirty(eb);
 	if (slot == 0)
-		fixup_low_keys(fs_info, path, &disk_key, 1);
+		fixup_low_keys(path, &disk_key, 1);
 }
 
 /*
@@ -3359,17 +3354,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 
 	root_add_used(root, fs_info->nodesize);
 
-	memzero_extent_buffer(c, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_nritems(c, 1);
-	btrfs_set_header_level(c, level);
-	btrfs_set_header_bytenr(c, c->start);
-	btrfs_set_header_generation(c, trans->transid);
-	btrfs_set_header_backref_rev(c, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(c, root->root_key.objectid);
-
-	write_extent_buffer_fsid(c, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(c, fs_info->chunk_tree_uuid);
-
 	btrfs_set_node_key(c, &lower_key, 0);
 	btrfs_set_node_blockptr(c, 0, lower->start);
 	lower_gen = btrfs_header_generation(lower);
@@ -3498,15 +3483,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 		return PTR_ERR(split);
 
 	root_add_used(root, fs_info->nodesize);
-
-	memzero_extent_buffer(split, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_level(split, btrfs_header_level(c));
-	btrfs_set_header_bytenr(split, split->start);
-	btrfs_set_header_generation(split, trans->transid);
-	btrfs_set_header_backref_rev(split, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(split, root->root_key.objectid);
-	write_extent_buffer_fsid(split, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(split, fs_info->chunk_tree_uuid);
+	ASSERT(btrfs_header_level(c) == level);
 
 	ret = tree_mod_log_eb_copy(fs_info, split, c, 0, mid, c_nritems - mid);
 	if (ret) {
@@ -3945,7 +3922,7 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info,
 		clean_tree_block(fs_info, right);
 
 	btrfs_item_key(right, &disk_key, 0);
-	fixup_low_keys(fs_info, path, &disk_key, 1);
+	fixup_low_keys(path, &disk_key, 1);
 
 	/* then fixup the leaf pointer in the path */
 	if (path->slots[0] < push_items) {
@@ -4292,15 +4269,6 @@ again:
 
 	root_add_used(root, fs_info->nodesize);
 
-	memzero_extent_buffer(right, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(right, right->start);
-	btrfs_set_header_generation(right, trans->transid);
-	btrfs_set_header_backref_rev(right, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(right, root->root_key.objectid);
-	btrfs_set_header_level(right, 0);
-	write_extent_buffer_fsid(right, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(right, fs_info->chunk_tree_uuid);
-
 	if (split == 0) {
 		if (mid <= slot) {
 			btrfs_set_header_nritems(right, 0);
@@ -4320,7 +4288,7 @@ again:
 			path->nodes[0] = right;
 			path->slots[0] = 0;
 			if (path->slots[1] == 0)
-				fixup_low_keys(fs_info, path, &disk_key, 1);
+				fixup_low_keys(path, &disk_key, 1);
 		}
 		/*
 		 * We create a new leaf 'right' for the required ins_len and
@@ -4642,7 +4610,7 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info,
 		btrfs_set_disk_key_offset(&disk_key, offset + size_diff);
 		btrfs_set_item_key(leaf, &disk_key, slot);
 		if (slot == 0)
-			fixup_low_keys(fs_info, path, &disk_key, 1);
+			fixup_low_keys(path, &disk_key, 1);
 	}
 
 	item = btrfs_item_nr(slot);
@@ -4744,7 +4712,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
 
 	if (path->slots[0] == 0) {
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
-		fixup_low_keys(fs_info, path, &disk_key, 1);
+		fixup_low_keys(path, &disk_key, 1);
 	}
 	btrfs_unlock_up_safe(path, 1);
 
@@ -4886,7 +4854,6 @@ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
 		    int level, int slot)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *parent = path->nodes[level];
 	u32 nritems;
 	int ret;
@@ -4919,7 +4886,7 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
 		struct btrfs_disk_key disk_key;
 
 		btrfs_node_key(parent, &disk_key, 0);
-		fixup_low_keys(fs_info, path, &disk_key, level + 1);
+		fixup_low_keys(path, &disk_key, level + 1);
 	}
 	btrfs_mark_buffer_dirty(parent);
 }
@@ -5022,7 +4989,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			struct btrfs_disk_key disk_key;
 
 			btrfs_item_key(leaf, &disk_key, 0);
-			fixup_low_keys(fs_info, path, &disk_key, 1);
+			fixup_low_keys(path, &disk_key, 1);
 		}
 
 		/* delete the leaf if it is mostly empty */
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 118346aceea9..318be7864072 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -55,8 +55,6 @@ struct btrfs_ordered_sum;
 
 #define BTRFS_OLDEST_GENERATION	0ULL
 
-#define BTRFS_COMPAT_EXTENT_TREE_V0
-
 /*
  * the max metadata block size.  This limit is somewhat artificial,
  * but the memmove costs go through the roof for larger blocks.
@@ -86,6 +84,14 @@ static const int btrfs_csum_sizes[] = { 4 };
 
 #define BTRFS_DIRTY_METADATA_THRESH	SZ_32M
 
+/*
+ * Use large batch size to reduce overhead of metadata updates.  On the reader
+ * side, we only read it when we are close to ENOSPC and the read overhead is
+ * mostly related to the number of CPUs, so it is OK to use arbitrary large
+ * value here.
+ */
+#define BTRFS_TOTAL_BYTES_PINNED_BATCH	SZ_128M
+
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
 
@@ -342,8 +348,8 @@ struct btrfs_path {
 					sizeof(struct btrfs_item))
 struct btrfs_dev_replace {
 	u64 replace_state;	/* see #define above */
-	u64 time_started;	/* seconds since 1-Jan-1970 */
-	u64 time_stopped;	/* seconds since 1-Jan-1970 */
+	time64_t time_started;	/* seconds since 1-Jan-1970 */
+	time64_t time_stopped;	/* seconds since 1-Jan-1970 */
 	atomic64_t num_write_errors;
 	atomic64_t num_uncorrectable_read_errors;
 
@@ -359,8 +365,6 @@ struct btrfs_dev_replace {
 	struct btrfs_device *srcdev;
 	struct btrfs_device *tgtdev;
 
-	pid_t lock_owner;
-	atomic_t nesting_level;
 	struct mutex lock_finishing_cancel_unmount;
 	rwlock_t lock;
 	atomic_t read_locks;
@@ -1213,7 +1217,6 @@ struct btrfs_root {
 	u64 defrag_trans_start;
 	struct btrfs_key defrag_progress;
 	struct btrfs_key defrag_max;
-	char *name;
 
 	/* the dirty list is only used by non-reference counted roots */
 	struct list_head dirty_list;
@@ -2428,32 +2431,6 @@ static inline u32 btrfs_file_extent_inline_item_len(
 	return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START;
 }
 
-/* this returns the number of file bytes represented by the inline item.
- * If an item is compressed, this is the uncompressed size
- */
-static inline u32 btrfs_file_extent_inline_len(const struct extent_buffer *eb,
-					int slot,
-					const struct btrfs_file_extent_item *fi)
-{
-	struct btrfs_map_token token;
-
-	btrfs_init_map_token(&token);
-	/*
-	 * return the space used on disk if this item isn't
-	 * compressed or encoded
-	 */
-	if (btrfs_token_file_extent_compression(eb, fi, &token) == 0 &&
-	    btrfs_token_file_extent_encryption(eb, fi, &token) == 0 &&
-	    btrfs_token_file_extent_other_encoding(eb, fi, &token) == 0) {
-		return btrfs_file_extent_inline_item_len(eb,
-							 btrfs_item_nr(slot));
-	}
-
-	/* otherwise use the ram bytes field */
-	return btrfs_token_file_extent_ram_bytes(eb, fi, &token);
-}
-
-
 /* btrfs_dev_stats_item */
 static inline u64 btrfs_dev_stats_value(const struct extent_buffer *eb,
 					const struct btrfs_dev_stats_item *ptr,
@@ -2676,7 +2653,6 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 				     u64 offset, u64 ram_bytes,
 				     struct btrfs_key *ins);
 int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   u64 root_objectid, u64 owner, u64 offset,
 				   struct btrfs_key *ins);
 int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes,
@@ -2716,15 +2692,14 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info);
 int btrfs_read_block_groups(struct btrfs_fs_info *info);
 int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr);
 int btrfs_make_block_group(struct btrfs_trans_handle *trans,
-			   struct btrfs_fs_info *fs_info, u64 bytes_used,
-			   u64 type, u64 chunk_offset, u64 size);
+			   u64 bytes_used, u64 type, u64 chunk_offset,
+			   u64 size);
 void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info);
 struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
 				const u64 chunk_offset);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info, u64 group_start,
-			     struct extent_map *em);
+			     u64 group_start, struct extent_map *em);
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
 void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
@@ -2786,7 +2761,6 @@ void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info,
 				   unsigned short type);
 void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
 			  struct btrfs_block_rsv *rsv);
-void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv);
 int btrfs_block_rsv_add(struct btrfs_root *root,
 			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
 			enum btrfs_reserve_flush_enum flush);
@@ -2803,8 +2777,7 @@ int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
 void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
 			     struct btrfs_block_rsv *block_rsv,
 			     u64 num_bytes);
-int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info,
-			     struct btrfs_block_group_cache *cache);
+int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
@@ -2812,8 +2785,7 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
 				   u64 start, u64 end);
 int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			 u64 num_bytes, u64 *actual_bytes);
-int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info, u64 type);
+int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
 int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
 
 int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
@@ -2822,10 +2794,10 @@ int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
 int btrfs_start_write_no_snapshotting(struct btrfs_root *root);
 void btrfs_end_write_no_snapshotting(struct btrfs_root *root);
 void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
-void check_system_chunk(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, const u64 type);
+void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
 u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 		       u64 start, u64 end);
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
 
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
@@ -3011,16 +2983,14 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq);
 
 /* root-item.c */
-int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 sequence,
-		       const char *name, int name_len);
-int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
-		       const char *name, int name_len);
+int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 sequence, const char *name,
+		       int name_len);
+int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 *sequence, const char *name,
+		       int name_len);
 int btrfs_del_root(struct btrfs_trans_handle *trans,
-		   struct btrfs_fs_info *fs_info, const struct btrfs_key *key);
+		   const struct btrfs_key *key);
 int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		      const struct btrfs_key *key,
 		      struct btrfs_root_item *item);
@@ -3196,7 +3166,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 			 size_t size, struct bio *bio,
 			 unsigned long bio_flags);
-void btrfs_set_range_writeback(void *private_data, u64 start, u64 end);
+void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end);
 vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
 int btrfs_readpage(struct file *file, struct page *page);
 void btrfs_evict_inode(struct inode *inode);
@@ -3452,7 +3422,7 @@ do {								\
 #ifdef CONFIG_BTRFS_ASSERT
 
 __cold
-static inline void assfail(char *expr, char *file, int line)
+static inline void assfail(const char *expr, const char *file, int line)
 {
 	pr_err("assertion failed: %s, file: %s, line: %d\n",
 	       expr, file, line);
@@ -3465,6 +3435,13 @@ static inline void assfail(char *expr, char *file, int line)
 #define ASSERT(expr)	((void)0)
 #endif
 
+__cold
+static inline void btrfs_print_v0_err(struct btrfs_fs_info *fs_info)
+{
+	btrfs_err(fs_info,
+"Unsupported V0 extent filesystem detected. Aborting. Please re-create your filesystem with a newer kernel");
+}
+
 __printf(5, 6)
 __cold
 void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index fe6caa7e698b..f51b509f2d9b 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1222,7 +1222,7 @@ int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
 
 int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
 	struct btrfs_path *path;
@@ -1418,7 +1418,6 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info)
 
 /* Will return 0 or -ENOMEM */
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
 				   struct btrfs_disk_key *disk_key, u8 type,
@@ -1458,11 +1457,10 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 	 */
 	BUG_ON(ret);
 
-
 	mutex_lock(&delayed_node->mutex);
 	ret = __btrfs_add_delayed_insertion_item(delayed_node, delayed_item);
 	if (unlikely(ret)) {
-		btrfs_err(fs_info,
+		btrfs_err(trans->fs_info,
 			  "err add delayed dir index item(name: %.*s) into the insertion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
 			  name_len, name, delayed_node->root->objectid,
 			  delayed_node->inode_id, ret);
@@ -1495,7 +1493,6 @@ static int btrfs_delete_delayed_insertion_item(struct btrfs_fs_info *fs_info,
 }
 
 int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   struct btrfs_inode *dir, u64 index)
 {
 	struct btrfs_delayed_node *node;
@@ -1511,7 +1508,8 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	item_key.type = BTRFS_DIR_INDEX_KEY;
 	item_key.offset = index;
 
-	ret = btrfs_delete_delayed_insertion_item(fs_info, node, &item_key);
+	ret = btrfs_delete_delayed_insertion_item(trans->fs_info, node,
+						  &item_key);
 	if (!ret)
 		goto end;
 
@@ -1533,7 +1531,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	mutex_lock(&node->mutex);
 	ret = __btrfs_add_delayed_deletion_item(node, item);
 	if (unlikely(ret)) {
-		btrfs_err(fs_info,
+		btrfs_err(trans->fs_info,
 			  "err add delayed dir index item(index: %llu) into the deletion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
 			  index, node->root->objectid, node->inode_id, ret);
 		BUG();
@@ -1837,7 +1835,7 @@ release_node:
 
 int btrfs_delayed_delete_inode_ref(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_delayed_node *delayed_node;
 
 	/*
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index ca7a97f3ab6b..33536cd681d4 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -86,14 +86,12 @@ static inline void btrfs_init_delayed_root(
 }
 
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
 				   struct btrfs_disk_key *disk_key, u8 type,
 				   u64 index);
 
 int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   struct btrfs_inode *dir, u64 index);
 
 int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 03dec673d12a..62ff545ba1f7 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -709,13 +709,13 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
  * to make sure the delayed ref is eventually processed before this
  * transaction commits.
  */
-int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root,  int level, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int *old_ref_mod, int *new_ref_mod)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_tree_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
@@ -730,27 +730,33 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	if (!ref)
 		return -ENOMEM;
 
+	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
+	if (!head_ref) {
+		kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+		return -ENOMEM;
+	}
+
+	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
+	    is_fstree(ref_root)) {
+		record = kmalloc(sizeof(*record), GFP_NOFS);
+		if (!record) {
+			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+			kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
+			return -ENOMEM;
+		}
+	}
+
 	if (parent)
 		ref_type = BTRFS_SHARED_BLOCK_REF_KEY;
 	else
 		ref_type = BTRFS_TREE_BLOCK_REF_KEY;
+
 	init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
 				ref_root, action, ref_type);
 	ref->root = ref_root;
 	ref->parent = parent;
 	ref->level = level;
 
-	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
-	if (!head_ref)
-		goto free_ref;
-
-	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
-	    is_fstree(ref_root)) {
-		record = kmalloc(sizeof(*record), GFP_NOFS);
-		if (!record)
-			goto free_head_ref;
-	}
-
 	init_delayed_ref_head(head_ref, record, bytenr, num_bytes,
 			      ref_root, 0, action, false, is_system);
 	head_ref->extent_op = extent_op;
@@ -779,25 +785,18 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 		btrfs_qgroup_trace_extent_post(fs_info, record);
 
 	return 0;
-
-free_head_ref:
-	kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
-free_ref:
-	kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
-
-	return -ENOMEM;
 }
 
 /*
  * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
  */
-int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, u64 reserved, int action,
 			       int *old_ref_mod, int *new_ref_mod)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_data_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index ea1aecb6a50d..d9f2a4ebd5db 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -234,14 +234,12 @@ static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *hea
 		kmem_cache_free(btrfs_delayed_ref_head_cachep, head);
 }
 
-int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root, int level, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int *old_ref_mod, int *new_ref_mod);
-int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, u64 reserved, int action,
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index e2ba0419297a..dec01970d8c5 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -6,14 +6,9 @@
 #include <linux/sched.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
-#include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/random.h>
-#include <linux/iocontext.h>
-#include <linux/capability.h>
 #include <linux/kthread.h>
 #include <linux/math64.h>
-#include <asm/div64.h>
 #include "ctree.h"
 #include "extent_map.h"
 #include "disk-io.h"
@@ -465,7 +460,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	 * go to the tgtdev as well (refer to btrfs_map_block()).
 	 */
 	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED;
-	dev_replace->time_started = get_seconds();
+	dev_replace->time_started = ktime_get_real_seconds();
 	dev_replace->cursor_left = 0;
 	dev_replace->committed_cursor_left = 0;
 	dev_replace->cursor_left_last_write_of_item = 0;
@@ -511,7 +506,7 @@ leave:
 	dev_replace->srcdev = NULL;
 	dev_replace->tgtdev = NULL;
 	btrfs_dev_replace_write_unlock(dev_replace);
-	btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+	btrfs_destroy_dev_replace_tgtdev(tgt_device);
 	return ret;
 }
 
@@ -618,7 +613,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 			  : BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED;
 	dev_replace->tgtdev = NULL;
 	dev_replace->srcdev = NULL;
-	dev_replace->time_stopped = get_seconds();
+	dev_replace->time_stopped = ktime_get_real_seconds();
 	dev_replace->item_needs_writeback = 1;
 
 	/* replace old device with new one in mapping tree */
@@ -637,7 +632,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		btrfs_rm_dev_replace_blocked(fs_info);
 		if (tgt_device)
-			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+			btrfs_destroy_dev_replace_tgtdev(tgt_device);
 		btrfs_rm_dev_replace_unblocked(fs_info);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 
@@ -663,7 +658,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	tgt_device->commit_total_bytes = src_device->commit_total_bytes;
 	tgt_device->commit_bytes_used = src_device->bytes_used;
 
-	btrfs_assign_next_active_device(fs_info, src_device, tgt_device);
+	btrfs_assign_next_active_device(src_device, tgt_device);
 
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 	fs_info->fs_devices->rw_devices++;
@@ -672,11 +667,17 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 
 	btrfs_rm_dev_replace_blocked(fs_info);
 
-	btrfs_rm_dev_replace_remove_srcdev(fs_info, src_device);
+	btrfs_rm_dev_replace_remove_srcdev(src_device);
 
 	btrfs_rm_dev_replace_unblocked(fs_info);
 
 	/*
+	 * Increment dev_stats_ccnt so that btrfs_run_dev_stats() will
+	 * update on-disk dev stats value during commit transaction
+	 */
+	atomic_inc(&tgt_device->dev_stats_ccnt);
+
+	/*
 	 * this is again a consistent state where no dev_replace procedure
 	 * is running, the target device is part of the filesystem, the
 	 * source device is not part of the filesystem anymore and its 1st
@@ -807,7 +808,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		break;
 	}
 	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED;
-	dev_replace->time_stopped = get_seconds();
+	dev_replace->time_stopped = ktime_get_real_seconds();
 	dev_replace->item_needs_writeback = 1;
 	btrfs_dev_replace_write_unlock(dev_replace);
 	btrfs_scrub_cancel(fs_info);
@@ -826,7 +827,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		btrfs_dev_name(tgt_device));
 
 	if (tgt_device)
-		btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+		btrfs_destroy_dev_replace_tgtdev(tgt_device);
 
 leave:
 	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
@@ -848,7 +849,7 @@ void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 		dev_replace->replace_state =
 			BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED;
-		dev_replace->time_stopped = get_seconds();
+		dev_replace->time_stopped = ktime_get_real_seconds();
 		dev_replace->item_needs_writeback = 1;
 		btrfs_info(fs_info, "suspending dev_replace for unmount");
 		break;
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 39e9766d1cbd..a678b07fcf01 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -160,8 +160,8 @@ second_insert:
 	}
 	btrfs_release_path(path);
 
-	ret2 = btrfs_insert_delayed_dir_index(trans, root->fs_info, name,
-			name_len, dir, &disk_key, type, index);
+	ret2 = btrfs_insert_delayed_dir_index(trans, name, name_len, dir,
+					      &disk_key, type, index);
 out_free:
 	btrfs_free_path(path);
 	if (ret)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 205092dc9390..5124c15705ce 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -5,8 +5,6 @@
 
 #include <linux/fs.h>
 #include <linux/blkdev.h>
-#include <linux/scatterlist.h>
-#include <linux/swap.h>
 #include <linux/radix-tree.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
@@ -54,7 +52,6 @@
 
 static const struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
-static void free_fs_root(struct btrfs_root *root);
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				      struct btrfs_fs_info *fs_info);
@@ -108,12 +105,9 @@ void __cold btrfs_end_io_wq_exit(void)
  */
 struct async_submit_bio {
 	void *private_data;
-	struct btrfs_fs_info *fs_info;
 	struct bio *bio;
 	extent_submit_bio_start_t *submit_bio_start;
-	extent_submit_bio_done_t *submit_bio_done;
 	int mirror_num;
-	unsigned long bio_flags;
 	/*
 	 * bio_offset is optional, can be used if the pages in the bio
 	 * can't tell us where in the file the bio should go
@@ -212,7 +206,7 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
@@ -615,8 +609,8 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != eb->start) {
-		btrfs_err_rl(fs_info, "bad tree block start %llu %llu",
-			     found_start, eb->start);
+		btrfs_err_rl(fs_info, "bad tree block start, want %llu have %llu",
+			     eb->start, found_start);
 		ret = -EIO;
 		goto err;
 	}
@@ -628,8 +622,8 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	}
 	found_level = btrfs_header_level(eb);
 	if (found_level >= BTRFS_MAX_LEVEL) {
-		btrfs_err(fs_info, "bad tree block level %d",
-			  (int)btrfs_header_level(eb));
+		btrfs_err(fs_info, "bad tree block level %d on %llu",
+			  (int)btrfs_header_level(eb), eb->start);
 		ret = -EIO;
 		goto err;
 	}
@@ -779,7 +773,7 @@ static void run_one_async_done(struct btrfs_work *work)
 		return;
 	}
 
-	async->submit_bio_done(async->private_data, async->bio, async->mirror_num);
+	btrfs_submit_bio_done(async->private_data, async->bio, async->mirror_num);
 }
 
 static void run_one_async_free(struct btrfs_work *work)
@@ -793,8 +787,7 @@ static void run_one_async_free(struct btrfs_work *work)
 blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags,
 				 u64 bio_offset, void *private_data,
-				 extent_submit_bio_start_t *submit_bio_start,
-				 extent_submit_bio_done_t *submit_bio_done)
+				 extent_submit_bio_start_t *submit_bio_start)
 {
 	struct async_submit_bio *async;
 
@@ -803,16 +796,13 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 		return BLK_STS_RESOURCE;
 
 	async->private_data = private_data;
-	async->fs_info = fs_info;
 	async->bio = bio;
 	async->mirror_num = mirror_num;
 	async->submit_bio_start = submit_bio_start;
-	async->submit_bio_done = submit_bio_done;
 
 	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
 			run_one_async_done, run_one_async_free);
 
-	async->bio_flags = bio_flags;
 	async->bio_offset = bio_offset;
 
 	async->status = 0;
@@ -851,24 +841,6 @@ static blk_status_t btree_submit_bio_start(void *private_data, struct bio *bio,
 	return btree_csum_one_bio(bio);
 }
 
-static blk_status_t btree_submit_bio_done(void *private_data, struct bio *bio,
-					    int mirror_num)
-{
-	struct inode *inode = private_data;
-	blk_status_t ret;
-
-	/*
-	 * when we're called for a write, we're already in the async
-	 * submission context.  Just jump into btrfs_map_bio
-	 */
-	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), bio, mirror_num, 1);
-	if (ret) {
-		bio->bi_status = ret;
-		bio_endio(bio);
-	}
-	return ret;
-}
-
 static int check_async_write(struct btrfs_inode *bi)
 {
 	if (atomic_read(&bi->sync_writers))
@@ -911,8 +883,7 @@ static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio,
 		 */
 		ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0,
 					  bio_offset, private_data,
-					  btree_submit_bio_start,
-					  btree_submit_bio_done);
+					  btree_submit_bio_start);
 	}
 
 	if (ret)
@@ -961,8 +932,9 @@ static int btree_writepages(struct address_space *mapping,
 
 		fs_info = BTRFS_I(mapping->host)->root->fs_info;
 		/* this is a bit racy, but that's ok */
-		ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes,
-					     BTRFS_DIRTY_METADATA_THRESH);
+		ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
+					     BTRFS_DIRTY_METADATA_THRESH,
+					     fs_info->dirty_metadata_batch);
 		if (ret < 0)
 			return 0;
 	}
@@ -1181,7 +1153,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->highest_objectid = 0;
 	root->nr_delalloc_inodes = 0;
 	root->nr_ordered_extents = 0;
-	root->name = NULL;
 	root->inode_tree = RB_ROOT;
 	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
 	root->block_rsv = NULL;
@@ -1292,15 +1263,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(leaf, leaf->start);
-	btrfs_set_header_generation(leaf, trans->transid);
-	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(leaf, objectid);
 	root->node = leaf;
-
-	write_extent_buffer_fsid(leaf, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(leaf, fs_info->chunk_tree_uuid);
 	btrfs_mark_buffer_dirty(leaf);
 
 	root->commit_root = btrfs_root_node(root);
@@ -1374,14 +1337,8 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 		return ERR_CAST(leaf);
 	}
 
-	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(leaf, leaf->start);
-	btrfs_set_header_generation(leaf, trans->transid);
-	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(leaf, BTRFS_TREE_LOG_OBJECTID);
 	root->node = leaf;
 
-	write_extent_buffer_fsid(root->node, fs_info->fsid);
 	btrfs_mark_buffer_dirty(root->node);
 	btrfs_tree_unlock(root->node);
 	return root;
@@ -1546,7 +1503,7 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 
 	return 0;
 fail:
-	/* the caller is responsible to call free_fs_root */
+	/* The caller is responsible to call btrfs_free_fs_root */
 	return ret;
 }
 
@@ -1651,14 +1608,14 @@ again:
 	ret = btrfs_insert_fs_root(fs_info, root);
 	if (ret) {
 		if (ret == -EEXIST) {
-			free_fs_root(root);
+			btrfs_free_fs_root(root);
 			goto again;
 		}
 		goto fail;
 	}
 	return root;
 fail:
-	free_fs_root(root);
+	btrfs_free_fs_root(root);
 	return ERR_PTR(ret);
 }
 
@@ -1803,7 +1760,7 @@ static int transaction_kthread(void *arg)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_transaction *cur;
 	u64 transid;
-	unsigned long now;
+	time64_t now;
 	unsigned long delay;
 	bool cannot_commit;
 
@@ -1819,7 +1776,7 @@ static int transaction_kthread(void *arg)
 			goto sleep;
 		}
 
-		now = get_seconds();
+		now = ktime_get_seconds();
 		if (cur->state < TRANS_STATE_BLOCKED &&
 		    !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
 		    (now < cur->start_time ||
@@ -2196,8 +2153,6 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
 
 static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
 {
-	fs_info->dev_replace.lock_owner = 0;
-	atomic_set(&fs_info->dev_replace.nesting_level, 0);
 	mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
 	rwlock_init(&fs_info->dev_replace.lock);
 	atomic_set(&fs_info->dev_replace.read_locks, 0);
@@ -3075,6 +3030,13 @@ retry_root_backup:
 	fs_info->generation = generation;
 	fs_info->last_trans_committed = generation;
 
+	ret = btrfs_verify_dev_extents(fs_info);
+	if (ret) {
+		btrfs_err(fs_info,
+			  "failed to verify dev extents against chunks: %d",
+			  ret);
+		goto fail_block_groups;
+	}
 	ret = btrfs_recover_balance(fs_info);
 	if (ret) {
 		btrfs_err(fs_info, "failed to recover balance: %d", ret);
@@ -3875,10 +3837,10 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 		__btrfs_remove_free_space_cache(root->free_ino_pinned);
 	if (root->free_ino_ctl)
 		__btrfs_remove_free_space_cache(root->free_ino_ctl);
-	free_fs_root(root);
+	btrfs_free_fs_root(root);
 }
 
-static void free_fs_root(struct btrfs_root *root)
+void btrfs_free_fs_root(struct btrfs_root *root)
 {
 	iput(root->ino_cache_inode);
 	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
@@ -3890,15 +3852,9 @@ static void free_fs_root(struct btrfs_root *root)
 	free_extent_buffer(root->commit_root);
 	kfree(root->free_ino_ctl);
 	kfree(root->free_ino_pinned);
-	kfree(root->name);
 	btrfs_put_fs_root(root);
 }
 
-void btrfs_free_fs_root(struct btrfs_root *root)
-{
-	free_fs_root(root);
-}
-
 int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 {
 	u64 root_objectid = 0;
@@ -4104,10 +4060,10 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	/*
 	 * This is a fast path so only do this check if we have sanity tests
-	 * enabled.  Normal people shouldn't be marking dummy buffers as dirty
+	 * enabled.  Normal people shouldn't be using umapped buffers as dirty
 	 * outside of the sanity tests.
 	 */
-	if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &buf->bflags)))
+	if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags)))
 		return;
 #endif
 	root = BTRFS_I(buf->pages[0]->mapping->host)->root;
@@ -4150,8 +4106,9 @@ static void __btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info,
 	if (flush_delayed)
 		btrfs_balance_delayed_items(fs_info);
 
-	ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes,
-				     BTRFS_DIRTY_METADATA_THRESH);
+	ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
+				     BTRFS_DIRTY_METADATA_THRESH,
+				     fs_info->dirty_metadata_batch);
 	if (ret > 0) {
 		balance_dirty_pages_ratelimited(fs_info->btree_inode->i_mapping);
 	}
@@ -4563,21 +4520,11 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
-static struct btrfs_fs_info *btree_fs_info(void *private_data)
-{
-	struct inode *inode = private_data;
-	return btrfs_sb(inode->i_sb);
-}
-
 static const struct extent_io_ops btree_extent_io_ops = {
 	/* mandatory callbacks */
 	.submit_bio_hook = btree_submit_bio_hook,
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
-	/* note we're sharing with inode.c for the merge bio hook */
-	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_io_failed_hook = btree_io_failed_hook,
-	.set_range_writeback = btrfs_set_range_writeback,
-	.tree_fs_info = btree_fs_info,
 
 	/* optional callbacks */
 };
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 1a3d277b027b..4cccba22640f 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -120,8 +120,9 @@ blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			int mirror_num, unsigned long bio_flags,
 			u64 bio_offset, void *private_data,
-			extent_submit_bio_start_t *submit_bio_start,
-			extent_submit_bio_done_t *submit_bio_done);
+			extent_submit_bio_start_t *submit_bio_start);
+blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
+			  int mirror_num);
 int btrfs_write_tree_block(struct extent_buffer *buf);
 void btrfs_wait_tree_block_writeback(struct extent_buffer *buf);
 int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3d9fe58c0080..de6f75f5547b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -52,24 +52,21 @@ enum {
 };
 
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info,
-				struct btrfs_delayed_ref_node *node, u64 parent,
-				u64 root_objectid, u64 owner_objectid,
-				u64 owner_offset, int refs_to_drop,
-				struct btrfs_delayed_extent_op *extra_op);
+			       struct btrfs_delayed_ref_node *node, u64 parent,
+			       u64 root_objectid, u64 owner_objectid,
+			       u64 owner_offset, int refs_to_drop,
+			       struct btrfs_delayed_extent_op *extra_op);
 static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
 				    struct extent_buffer *leaf,
 				    struct btrfs_extent_item *ei);
 static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
-				      struct btrfs_fs_info *fs_info,
 				      u64 parent, u64 root_objectid,
 				      u64 flags, u64 owner, u64 offset,
 				      struct btrfs_key *ins, int ref_mod);
 static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 				     struct btrfs_delayed_ref_node *node,
 				     struct btrfs_delayed_extent_op *extent_op);
-static int do_chunk_alloc(struct btrfs_trans_handle *trans,
-			  struct btrfs_fs_info *fs_info, u64 flags,
+static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 			  int force);
 static int find_next_key(struct btrfs_path *path, int level,
 			 struct btrfs_key *key);
@@ -220,9 +217,9 @@ static int add_excluded_extent(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-static void free_excluded_extents(struct btrfs_fs_info *fs_info,
-				  struct btrfs_block_group_cache *cache)
+static void free_excluded_extents(struct btrfs_block_group_cache *cache)
 {
+	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 start, end;
 
 	start = cache->key.objectid;
@@ -234,9 +231,9 @@ static void free_excluded_extents(struct btrfs_fs_info *fs_info,
 			  start, end, EXTENT_UPTODATE);
 }
 
-static int exclude_super_stripes(struct btrfs_fs_info *fs_info,
-				 struct btrfs_block_group_cache *cache)
+static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 {
+	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 bytenr;
 	u64 *logical;
 	int stripe_len;
@@ -558,7 +555,7 @@ static noinline void caching_thread(struct btrfs_work *work)
 	caching_ctl->progress = (u64)-1;
 
 	up_read(&fs_info->commit_root_sem);
-	free_excluded_extents(fs_info, block_group);
+	free_excluded_extents(block_group);
 	mutex_unlock(&caching_ctl->mutex);
 
 	wake_up(&caching_ctl->wait);
@@ -666,7 +663,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 		wake_up(&caching_ctl->wait);
 		if (ret == 1) {
 			put_caching_control(caching_ctl);
-			free_excluded_extents(fs_info, cache);
+			free_excluded_extents(cache);
 			return 0;
 		}
 	} else {
@@ -758,7 +755,8 @@ static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes,
 
 	space_info = __find_space_info(fs_info, flags);
 	ASSERT(space_info);
-	percpu_counter_add(&space_info->total_bytes_pinned, num_bytes);
+	percpu_counter_add_batch(&space_info->total_bytes_pinned, num_bytes,
+		    BTRFS_TOTAL_BYTES_PINNED_BATCH);
 }
 
 /*
@@ -870,18 +868,16 @@ search_again:
 			num_refs = btrfs_extent_refs(leaf, ei);
 			extent_flags = btrfs_extent_flags(leaf, ei);
 		} else {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-			struct btrfs_extent_item_v0 *ei0;
-			BUG_ON(item_size != sizeof(*ei0));
-			ei0 = btrfs_item_ptr(leaf, path->slots[0],
-					     struct btrfs_extent_item_v0);
-			num_refs = btrfs_extent_refs_v0(leaf, ei0);
-			/* FIXME: this isn't correct for data */
-			extent_flags = BTRFS_BLOCK_FLAG_FULL_BACKREF;
-#else
-			BUG();
-#endif
+			ret = -EINVAL;
+			btrfs_print_v0_err(fs_info);
+			if (trans)
+				btrfs_abort_transaction(trans, ret);
+			else
+				btrfs_handle_fs_error(fs_info, ret, NULL);
+
+			goto out_free;
 		}
+
 		BUG_ON(num_refs == 0);
 	} else {
 		num_refs = 0;
@@ -1039,89 +1035,6 @@ out_free:
  * tree block info structure.
  */
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
-				  struct btrfs_path *path,
-				  u64 owner, u32 extra_size)
-{
-	struct btrfs_root *root = fs_info->extent_root;
-	struct btrfs_extent_item *item;
-	struct btrfs_extent_item_v0 *ei0;
-	struct btrfs_extent_ref_v0 *ref0;
-	struct btrfs_tree_block_info *bi;
-	struct extent_buffer *leaf;
-	struct btrfs_key key;
-	struct btrfs_key found_key;
-	u32 new_size = sizeof(*item);
-	u64 refs;
-	int ret;
-
-	leaf = path->nodes[0];
-	BUG_ON(btrfs_item_size_nr(leaf, path->slots[0]) != sizeof(*ei0));
-
-	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-	ei0 = btrfs_item_ptr(leaf, path->slots[0],
-			     struct btrfs_extent_item_v0);
-	refs = btrfs_extent_refs_v0(leaf, ei0);
-
-	if (owner == (u64)-1) {
-		while (1) {
-			if (path->slots[0] >= btrfs_header_nritems(leaf)) {
-				ret = btrfs_next_leaf(root, path);
-				if (ret < 0)
-					return ret;
-				BUG_ON(ret > 0); /* Corruption */
-				leaf = path->nodes[0];
-			}
-			btrfs_item_key_to_cpu(leaf, &found_key,
-					      path->slots[0]);
-			BUG_ON(key.objectid != found_key.objectid);
-			if (found_key.type != BTRFS_EXTENT_REF_V0_KEY) {
-				path->slots[0]++;
-				continue;
-			}
-			ref0 = btrfs_item_ptr(leaf, path->slots[0],
-					      struct btrfs_extent_ref_v0);
-			owner = btrfs_ref_objectid_v0(leaf, ref0);
-			break;
-		}
-	}
-	btrfs_release_path(path);
-
-	if (owner < BTRFS_FIRST_FREE_OBJECTID)
-		new_size += sizeof(*bi);
-
-	new_size -= sizeof(*ei0);
-	ret = btrfs_search_slot(trans, root, &key, path,
-				new_size + extra_size, 1);
-	if (ret < 0)
-		return ret;
-	BUG_ON(ret); /* Corruption */
-
-	btrfs_extend_item(fs_info, path, new_size);
-
-	leaf = path->nodes[0];
-	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
-	btrfs_set_extent_refs(leaf, item, refs);
-	/* FIXME: get real generation */
-	btrfs_set_extent_generation(leaf, item, 0);
-	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		btrfs_set_extent_flags(leaf, item,
-				       BTRFS_EXTENT_FLAG_TREE_BLOCK |
-				       BTRFS_BLOCK_FLAG_FULL_BACKREF);
-		bi = (struct btrfs_tree_block_info *)(item + 1);
-		/* FIXME: get first key of the block */
-		memzero_extent_buffer(leaf, (unsigned long)bi, sizeof(*bi));
-		btrfs_set_tree_block_level(leaf, bi, (int)owner);
-	} else {
-		btrfs_set_extent_flags(leaf, item, BTRFS_EXTENT_FLAG_DATA);
-	}
-	btrfs_mark_buffer_dirty(leaf);
-	return 0;
-}
-#endif
-
 /*
  * is_data == BTRFS_REF_TYPE_BLOCK, tree block type is required,
  * is_data == BTRFS_REF_TYPE_DATA, data type is requried,
@@ -1216,13 +1129,12 @@ static int match_extent_data_ref(struct extent_buffer *leaf,
 }
 
 static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   u64 bytenr, u64 parent,
 					   u64 root_objectid,
 					   u64 owner, u64 offset)
 {
-	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *root = trans->fs_info->extent_root;
 	struct btrfs_key key;
 	struct btrfs_extent_data_ref *ref;
 	struct extent_buffer *leaf;
@@ -1251,17 +1163,6 @@ again:
 	if (parent) {
 		if (!ret)
 			return 0;
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		key.type = BTRFS_EXTENT_REF_V0_KEY;
-		btrfs_release_path(path);
-		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-		if (ret < 0) {
-			err = ret;
-			goto fail;
-		}
-		if (!ret)
-			return 0;
-#endif
 		goto fail;
 	}
 
@@ -1304,13 +1205,12 @@ fail:
 }
 
 static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   u64 bytenr, u64 parent,
 					   u64 root_objectid, u64 owner,
 					   u64 offset, int refs_to_add)
 {
-	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *root = trans->fs_info->extent_root;
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
 	u32 size;
@@ -1384,7 +1284,6 @@ fail:
 }
 
 static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   int refs_to_drop, int *last_ref)
 {
@@ -1406,13 +1305,10 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 		ref2 = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_shared_data_ref);
 		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
-		struct btrfs_extent_ref_v0 *ref0;
-		ref0 = btrfs_item_ptr(leaf, path->slots[0],
-				      struct btrfs_extent_ref_v0);
-		num_refs = btrfs_ref_count_v0(leaf, ref0);
-#endif
+	} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
+		btrfs_print_v0_err(trans->fs_info);
+		btrfs_abort_transaction(trans, -EINVAL);
+		return -EINVAL;
 	} else {
 		BUG();
 	}
@@ -1421,21 +1317,13 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 	num_refs -= refs_to_drop;
 
 	if (num_refs == 0) {
-		ret = btrfs_del_item(trans, fs_info->extent_root, path);
+		ret = btrfs_del_item(trans, trans->fs_info->extent_root, path);
 		*last_ref = 1;
 	} else {
 		if (key.type == BTRFS_EXTENT_DATA_REF_KEY)
 			btrfs_set_extent_data_ref_count(leaf, ref1, num_refs);
 		else if (key.type == BTRFS_SHARED_DATA_REF_KEY)
 			btrfs_set_shared_data_ref_count(leaf, ref2, num_refs);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		else {
-			struct btrfs_extent_ref_v0 *ref0;
-			ref0 = btrfs_item_ptr(leaf, path->slots[0],
-					struct btrfs_extent_ref_v0);
-			btrfs_set_ref_count_v0(leaf, ref0, num_refs);
-		}
-#endif
 		btrfs_mark_buffer_dirty(leaf);
 	}
 	return ret;
@@ -1453,6 +1341,8 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+
+	BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
 	if (iref) {
 		/*
 		 * If type is invalid, we should have bailed out earlier than
@@ -1475,13 +1365,6 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 		ref2 = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_shared_data_ref);
 		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
-		struct btrfs_extent_ref_v0 *ref0;
-		ref0 = btrfs_item_ptr(leaf, path->slots[0],
-				      struct btrfs_extent_ref_v0);
-		num_refs = btrfs_ref_count_v0(leaf, ref0);
-#endif
 	} else {
 		WARN_ON(1);
 	}
@@ -1489,12 +1372,11 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 }
 
 static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
-					  struct btrfs_fs_info *fs_info,
 					  struct btrfs_path *path,
 					  u64 bytenr, u64 parent,
 					  u64 root_objectid)
 {
-	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *root = trans->fs_info->extent_root;
 	struct btrfs_key key;
 	int ret;
 
@@ -1510,20 +1392,10 @@ static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret > 0)
 		ret = -ENOENT;
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (ret == -ENOENT && parent) {
-		btrfs_release_path(path);
-		key.type = BTRFS_EXTENT_REF_V0_KEY;
-		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-		if (ret > 0)
-			ret = -ENOENT;
-	}
-#endif
 	return ret;
 }
 
 static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
-					  struct btrfs_fs_info *fs_info,
 					  struct btrfs_path *path,
 					  u64 bytenr, u64 parent,
 					  u64 root_objectid)
@@ -1540,7 +1412,7 @@ static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
 		key.offset = root_objectid;
 	}
 
-	ret = btrfs_insert_empty_item(trans, fs_info->extent_root,
+	ret = btrfs_insert_empty_item(trans, trans->fs_info->extent_root,
 				      path, &key, 0);
 	btrfs_release_path(path);
 	return ret;
@@ -1599,13 +1471,13 @@ static int find_next_key(struct btrfs_path *path, int level,
  */
 static noinline_for_stack
 int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref **ref_ret,
 				 u64 bytenr, u64 num_bytes,
 				 u64 parent, u64 root_objectid,
 				 u64 owner, u64 offset, int insert)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
@@ -1635,8 +1507,8 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
 		extra_size = -1;
 
 	/*
-	 * Owner is our parent level, so we can just add one to get the level
-	 * for the block we are interested in.
+	 * Owner is our level, so we can just add one to get the level for the
+	 * block we are interested in.
 	 */
 	if (skinny_metadata && owner < BTRFS_FIRST_FREE_OBJECTID) {
 		key.type = BTRFS_METADATA_ITEM_KEY;
@@ -1684,23 +1556,12 @@ again:
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		if (!insert) {
-			err = -ENOENT;
-			goto out;
-		}
-		ret = convert_extent_item_v0(trans, fs_info, path, owner,
-					     extra_size);
-		if (ret < 0) {
-			err = ret;
-			goto out;
-		}
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+	if (unlikely(item_size < sizeof(*ei))) {
+		err = -EINVAL;
+		btrfs_print_v0_err(fs_info);
+		btrfs_abort_transaction(trans, err);
+		goto out;
 	}
-#endif
-	BUG_ON(item_size < sizeof(*ei));
 
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	flags = btrfs_extent_flags(leaf, ei);
@@ -1727,7 +1588,7 @@ again:
 		iref = (struct btrfs_extent_inline_ref *)ptr;
 		type = btrfs_get_extent_inline_ref_type(leaf, iref, needed);
 		if (type == BTRFS_REF_TYPE_INVALID) {
-			err = -EINVAL;
+			err = -EUCLEAN;
 			goto out;
 		}
 
@@ -1863,7 +1724,6 @@ void setup_inline_extent_backref(struct btrfs_fs_info *fs_info,
 }
 
 static int lookup_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref **ref_ret,
 				 u64 bytenr, u64 num_bytes, u64 parent,
@@ -1871,9 +1731,9 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 {
 	int ret;
 
-	ret = lookup_inline_extent_backref(trans, fs_info, path, ref_ret,
-					   bytenr, num_bytes, parent,
-					   root_objectid, owner, offset, 0);
+	ret = lookup_inline_extent_backref(trans, path, ref_ret, bytenr,
+					   num_bytes, parent, root_objectid,
+					   owner, offset, 0);
 	if (ret != -ENOENT)
 		return ret;
 
@@ -1881,12 +1741,11 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 	*ref_ret = NULL;
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = lookup_tree_block_ref(trans, fs_info, path, bytenr,
-					    parent, root_objectid);
+		ret = lookup_tree_block_ref(trans, path, bytenr, parent,
+					    root_objectid);
 	} else {
-		ret = lookup_extent_data_ref(trans, fs_info, path, bytenr,
-					     parent, root_objectid, owner,
-					     offset);
+		ret = lookup_extent_data_ref(trans, path, bytenr, parent,
+					     root_objectid, owner, offset);
 	}
 	return ret;
 }
@@ -1895,14 +1754,14 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
  * helper to update/remove inline back ref
  */
 static noinline_for_stack
-void update_inline_extent_backref(struct btrfs_fs_info *fs_info,
-				  struct btrfs_path *path,
+void update_inline_extent_backref(struct btrfs_path *path,
 				  struct btrfs_extent_inline_ref *iref,
 				  int refs_to_mod,
 				  struct btrfs_delayed_extent_op *extent_op,
 				  int *last_ref)
 {
-	struct extent_buffer *leaf;
+	struct extent_buffer *leaf = path->nodes[0];
+	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_extent_item *ei;
 	struct btrfs_extent_data_ref *dref = NULL;
 	struct btrfs_shared_data_ref *sref = NULL;
@@ -1913,7 +1772,6 @@ void update_inline_extent_backref(struct btrfs_fs_info *fs_info,
 	int type;
 	u64 refs;
 
-	leaf = path->nodes[0];
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	refs = btrfs_extent_refs(leaf, ei);
 	WARN_ON(refs_to_mod < 0 && refs + refs_to_mod <= 0);
@@ -1965,7 +1823,6 @@ void update_inline_extent_backref(struct btrfs_fs_info *fs_info,
 
 static noinline_for_stack
 int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 u64 bytenr, u64 num_bytes, u64 parent,
 				 u64 root_objectid, u64 owner,
@@ -1975,15 +1832,15 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 	struct btrfs_extent_inline_ref *iref;
 	int ret;
 
-	ret = lookup_inline_extent_backref(trans, fs_info, path, &iref,
-					   bytenr, num_bytes, parent,
-					   root_objectid, owner, offset, 1);
+	ret = lookup_inline_extent_backref(trans, path, &iref, bytenr,
+					   num_bytes, parent, root_objectid,
+					   owner, offset, 1);
 	if (ret == 0) {
 		BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
-		update_inline_extent_backref(fs_info, path, iref,
-					     refs_to_add, extent_op, NULL);
+		update_inline_extent_backref(path, iref, refs_to_add,
+					     extent_op, NULL);
 	} else if (ret == -ENOENT) {
-		setup_inline_extent_backref(fs_info, path, iref, parent,
+		setup_inline_extent_backref(trans->fs_info, path, iref, parent,
 					    root_objectid, owner, offset,
 					    refs_to_add, extent_op);
 		ret = 0;
@@ -1992,7 +1849,6 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 }
 
 static int insert_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 u64 bytenr, u64 parent, u64 root_objectid,
 				 u64 owner, u64 offset, int refs_to_add)
@@ -2000,18 +1856,17 @@ static int insert_extent_backref(struct btrfs_trans_handle *trans,
 	int ret;
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
 		BUG_ON(refs_to_add != 1);
-		ret = insert_tree_block_ref(trans, fs_info, path, bytenr,
-					    parent, root_objectid);
+		ret = insert_tree_block_ref(trans, path, bytenr, parent,
+					    root_objectid);
 	} else {
-		ret = insert_extent_data_ref(trans, fs_info, path, bytenr,
-					     parent, root_objectid,
-					     owner, offset, refs_to_add);
+		ret = insert_extent_data_ref(trans, path, bytenr, parent,
+					     root_objectid, owner, offset,
+					     refs_to_add);
 	}
 	return ret;
 }
 
 static int remove_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref *iref,
 				 int refs_to_drop, int is_data, int *last_ref)
@@ -2020,14 +1875,14 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 
 	BUG_ON(!is_data && refs_to_drop != 1);
 	if (iref) {
-		update_inline_extent_backref(fs_info, path, iref,
-					     -refs_to_drop, NULL, last_ref);
+		update_inline_extent_backref(path, iref, -refs_to_drop, NULL,
+					     last_ref);
 	} else if (is_data) {
-		ret = remove_extent_data_ref(trans, fs_info, path, refs_to_drop,
+		ret = remove_extent_data_ref(trans, path, refs_to_drop,
 					     last_ref);
 	} else {
 		*last_ref = 1;
-		ret = btrfs_del_item(trans, fs_info->extent_root, path);
+		ret = btrfs_del_item(trans, trans->fs_info->extent_root, path);
 	}
 	return ret;
 }
@@ -2185,13 +2040,13 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			   owner, offset, BTRFS_ADD_DELAYED_REF);
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_tree_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, (int)owner,
 						 BTRFS_ADD_DELAYED_REF, NULL,
 						 &old_ref_mod, &new_ref_mod);
 	} else {
-		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_data_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, owner, offset,
 						 0, BTRFS_ADD_DELAYED_REF,
@@ -2207,8 +2062,41 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+/*
+ * __btrfs_inc_extent_ref - insert backreference for a given extent
+ *
+ * @trans:	    Handle of transaction
+ *
+ * @node:	    The delayed ref node used to get the bytenr/length for
+ *		    extent whose references are incremented.
+ *
+ * @parent:	    If this is a shared extent (BTRFS_SHARED_DATA_REF_KEY/
+ *		    BTRFS_SHARED_BLOCK_REF_KEY) then it holds the logical
+ *		    bytenr of the parent block. Since new extents are always
+ *		    created with indirect references, this will only be the case
+ *		    when relocating a shared extent. In that case, root_objectid
+ *		    will be BTRFS_TREE_RELOC_OBJECTID. Otheriwse, parent must
+ *		    be 0
+ *
+ * @root_objectid:  The id of the root where this modification has originated,
+ *		    this can be either one of the well-known metadata trees or
+ *		    the subvolume id which references this extent.
+ *
+ * @owner:	    For data extents it is the inode number of the owning file.
+ *		    For metadata extents this parameter holds the level in the
+ *		    tree of the extent.
+ *
+ * @offset:	    For metadata extents the offset is ignored and is currently
+ *		    always passed as 0. For data extents it is the fileoffset
+ *		    this extent belongs to.
+ *
+ * @refs_to_add     Number of references to add
+ *
+ * @extent_op       Pointer to a structure, holding information necessary when
+ *                  updating a tree block's flags
+ *
+ */
 static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_delayed_ref_node *node,
 				  u64 parent, u64 root_objectid,
 				  u64 owner, u64 offset, int refs_to_add,
@@ -2230,10 +2118,9 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* this will setup the path even if it fails to insert the back ref */
-	ret = insert_inline_extent_backref(trans, fs_info, path, bytenr,
-					   num_bytes, parent, root_objectid,
-					   owner, offset,
-					   refs_to_add, extent_op);
+	ret = insert_inline_extent_backref(trans, path, bytenr, num_bytes,
+					   parent, root_objectid, owner,
+					   offset, refs_to_add, extent_op);
 	if ((ret < 0 && ret != -EAGAIN) || !ret)
 		goto out;
 
@@ -2256,8 +2143,8 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* now insert the actual backref */
-	ret = insert_extent_backref(trans, fs_info, path, bytenr, parent,
-				    root_objectid, owner, offset, refs_to_add);
+	ret = insert_extent_backref(trans, path, bytenr, parent, root_objectid,
+				    owner, offset, refs_to_add);
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
 out:
@@ -2266,7 +2153,6 @@ out:
 }
 
 static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_node *node,
 				struct btrfs_delayed_extent_op *extent_op,
 				int insert_reserved)
@@ -2283,7 +2169,7 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 	ins.type = BTRFS_EXTENT_ITEM_KEY;
 
 	ref = btrfs_delayed_node_to_data_ref(node);
-	trace_run_delayed_data_ref(fs_info, node, ref, node->action);
+	trace_run_delayed_data_ref(trans->fs_info, node, ref, node->action);
 
 	if (node->type == BTRFS_SHARED_DATA_REF_KEY)
 		parent = ref->parent;
@@ -2292,17 +2178,16 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
 		if (extent_op)
 			flags |= extent_op->flags_to_set;
-		ret = alloc_reserved_file_extent(trans, fs_info,
-						 parent, ref_root, flags,
-						 ref->objectid, ref->offset,
-						 &ins, node->ref_mod);
+		ret = alloc_reserved_file_extent(trans, parent, ref_root,
+						 flags, ref->objectid,
+						 ref->offset, &ins,
+						 node->ref_mod);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
-		ret = __btrfs_inc_extent_ref(trans, fs_info, node, parent,
-					     ref_root, ref->objectid,
-					     ref->offset, node->ref_mod,
-					     extent_op);
+		ret = __btrfs_inc_extent_ref(trans, node, parent, ref_root,
+					     ref->objectid, ref->offset,
+					     node->ref_mod, extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
-		ret = __btrfs_free_extent(trans, fs_info, node, parent,
+		ret = __btrfs_free_extent(trans, node, parent,
 					  ref_root, ref->objectid,
 					  ref->offset, node->ref_mod,
 					  extent_op);
@@ -2331,10 +2216,10 @@ static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
 }
 
 static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_delayed_ref_head *head,
 				 struct btrfs_delayed_extent_op *extent_op)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_key key;
 	struct btrfs_path *path;
 	struct btrfs_extent_item *ei;
@@ -2400,18 +2285,14 @@ again:
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		ret = convert_extent_item_v0(trans, fs_info, path, (u64)-1, 0);
-		if (ret < 0) {
-			err = ret;
-			goto out;
-		}
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+
+	if (unlikely(item_size < sizeof(*ei))) {
+		err = -EINVAL;
+		btrfs_print_v0_err(fs_info);
+		btrfs_abort_transaction(trans, err);
+		goto out;
 	}
-#endif
-	BUG_ON(item_size < sizeof(*ei));
+
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	__run_delayed_extent_op(extent_op, leaf, ei);
 
@@ -2422,7 +2303,6 @@ out:
 }
 
 static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_node *node,
 				struct btrfs_delayed_extent_op *extent_op,
 				int insert_reserved)
@@ -2433,14 +2313,14 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	u64 ref_root = 0;
 
 	ref = btrfs_delayed_node_to_tree_ref(node);
-	trace_run_delayed_tree_ref(fs_info, node, ref, node->action);
+	trace_run_delayed_tree_ref(trans->fs_info, node, ref, node->action);
 
 	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY)
 		parent = ref->parent;
 	ref_root = ref->root;
 
 	if (node->ref_mod != 1) {
-		btrfs_err(fs_info,
+		btrfs_err(trans->fs_info,
 	"btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu",
 			  node->bytenr, node->ref_mod, node->action, ref_root,
 			  parent);
@@ -2450,13 +2330,10 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		BUG_ON(!extent_op || !extent_op->update_flags);
 		ret = alloc_reserved_tree_block(trans, node, extent_op);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
-		ret = __btrfs_inc_extent_ref(trans, fs_info, node,
-					     parent, ref_root,
-					     ref->level, 0, 1,
-					     extent_op);
+		ret = __btrfs_inc_extent_ref(trans, node, parent, ref_root,
+					     ref->level, 0, 1, extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
-		ret = __btrfs_free_extent(trans, fs_info, node,
-					  parent, ref_root,
+		ret = __btrfs_free_extent(trans, node, parent, ref_root,
 					  ref->level, 0, 1, extent_op);
 	} else {
 		BUG();
@@ -2466,7 +2343,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 
 /* helper function to actually process a single delayed ref entry */
 static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info,
 			       struct btrfs_delayed_ref_node *node,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int insert_reserved)
@@ -2475,18 +2351,18 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 
 	if (trans->aborted) {
 		if (insert_reserved)
-			btrfs_pin_extent(fs_info, node->bytenr,
+			btrfs_pin_extent(trans->fs_info, node->bytenr,
 					 node->num_bytes, 1);
 		return 0;
 	}
 
 	if (node->type == BTRFS_TREE_BLOCK_REF_KEY ||
 	    node->type == BTRFS_SHARED_BLOCK_REF_KEY)
-		ret = run_delayed_tree_ref(trans, fs_info, node, extent_op,
+		ret = run_delayed_tree_ref(trans, node, extent_op,
 					   insert_reserved);
 	else if (node->type == BTRFS_EXTENT_DATA_REF_KEY ||
 		 node->type == BTRFS_SHARED_DATA_REF_KEY)
-		ret = run_delayed_data_ref(trans, fs_info, node, extent_op,
+		ret = run_delayed_data_ref(trans, node, extent_op,
 					   insert_reserved);
 	else
 		BUG();
@@ -2528,7 +2404,6 @@ static void unselect_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_ref
 }
 
 static int cleanup_extent_op(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info,
 			     struct btrfs_delayed_ref_head *head)
 {
 	struct btrfs_delayed_extent_op *extent_op = head->extent_op;
@@ -2542,21 +2417,22 @@ static int cleanup_extent_op(struct btrfs_trans_handle *trans,
 		return 0;
 	}
 	spin_unlock(&head->lock);
-	ret = run_delayed_extent_op(trans, fs_info, head, extent_op);
+	ret = run_delayed_extent_op(trans, head, extent_op);
 	btrfs_free_delayed_extent_op(extent_op);
 	return ret ? ret : 1;
 }
 
 static int cleanup_ref_head(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
 			    struct btrfs_delayed_ref_head *head)
 {
+
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int ret;
 
 	delayed_refs = &trans->transaction->delayed_refs;
 
-	ret = cleanup_extent_op(trans, fs_info, head);
+	ret = cleanup_extent_op(trans, head);
 	if (ret < 0) {
 		unselect_delayed_ref_head(delayed_refs, head);
 		btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret);
@@ -2598,8 +2474,9 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 			flags = BTRFS_BLOCK_GROUP_METADATA;
 		space_info = __find_space_info(fs_info, flags);
 		ASSERT(space_info);
-		percpu_counter_add(&space_info->total_bytes_pinned,
-				   -head->num_bytes);
+		percpu_counter_add_batch(&space_info->total_bytes_pinned,
+				   -head->num_bytes,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH);
 
 		if (head->is_data) {
 			spin_lock(&delayed_refs->lock);
@@ -2705,7 +2582,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		 * up and move on to the next ref_head.
 		 */
 		if (!ref) {
-			ret = cleanup_ref_head(trans, fs_info, locked_ref);
+			ret = cleanup_ref_head(trans, locked_ref);
 			if (ret > 0 ) {
 				/* We dropped our lock, we need to loop. */
 				ret = 0;
@@ -2752,7 +2629,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		locked_ref->extent_op = NULL;
 		spin_unlock(&locked_ref->lock);
 
-		ret = run_one_delayed_ref(trans, fs_info, ref, extent_op,
+		ret = run_one_delayed_ref(trans, ref, extent_op,
 					  must_insert_reserved);
 
 		btrfs_free_delayed_extent_op(extent_op);
@@ -3227,12 +3104,6 @@ static noinline int check_committed_ref(struct btrfs_root *root,
 
 	ret = 1;
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		WARN_ON(item_size != sizeof(struct btrfs_extent_item_v0));
-		goto out;
-	}
-#endif
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 
 	if (item_size != sizeof(*ei) +
@@ -4060,11 +3931,7 @@ static void update_space_info(struct btrfs_fs_info *info, u64 flags,
 	struct btrfs_space_info *found;
 	int factor;
 
-	if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
-		     BTRFS_BLOCK_GROUP_RAID10))
-		factor = 2;
-	else
-		factor = 1;
+	factor = btrfs_bg_type_to_factor(flags);
 
 	found = __find_space_info(info, flags);
 	ASSERT(found);
@@ -4289,7 +4156,7 @@ again:
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 
-			ret = do_chunk_alloc(trans, fs_info, alloc_target,
+			ret = do_chunk_alloc(trans, alloc_target,
 					     CHUNK_ALLOC_NO_FORCE);
 			btrfs_end_transaction(trans);
 			if (ret < 0) {
@@ -4309,9 +4176,10 @@ again:
 		 * allocation, and no removed chunk in current transaction,
 		 * don't bother committing the transaction.
 		 */
-		have_pinned_space = percpu_counter_compare(
+		have_pinned_space = __percpu_counter_compare(
 			&data_sinfo->total_bytes_pinned,
-			used + bytes - data_sinfo->total_bytes);
+			used + bytes - data_sinfo->total_bytes,
+			BTRFS_TOTAL_BYTES_PINNED_BATCH);
 		spin_unlock(&data_sinfo->lock);
 
 		/* commit the current transaction and try again */
@@ -4358,7 +4226,7 @@ commit_trans:
 				      data_sinfo->flags, bytes, 1);
 	spin_unlock(&data_sinfo->lock);
 
-	return ret;
+	return 0;
 }
 
 int btrfs_check_data_free_space(struct inode *inode,
@@ -4511,9 +4379,9 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
  * for allocating a chunk, otherwise if it's false, reserve space necessary for
  * removing a chunk.
  */
-void check_system_chunk(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 type)
+void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_space_info *info;
 	u64 left;
 	u64 thresh;
@@ -4552,7 +4420,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
 		 * the paths we visit in the chunk tree (they were already COWed
 		 * or created in the current transaction for example).
 		 */
-		ret = btrfs_alloc_chunk(trans, fs_info, flags);
+		ret = btrfs_alloc_chunk(trans, flags);
 	}
 
 	if (!ret) {
@@ -4573,11 +4441,13 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
  *    - return 1 if it successfully allocates a chunk,
  *    - return errors including -ENOSPC otherwise.
  */
-static int do_chunk_alloc(struct btrfs_trans_handle *trans,
-			  struct btrfs_fs_info *fs_info, u64 flags, int force)
+static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
+			  int force)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_space_info *space_info;
-	int wait_for_alloc = 0;
+	bool wait_for_alloc = false;
+	bool should_alloc = false;
 	int ret = 0;
 
 	/* Don't re-enter if we're already allocating a chunk */
@@ -4587,45 +4457,44 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 	space_info = __find_space_info(fs_info, flags);
 	ASSERT(space_info);
 
-again:
-	spin_lock(&space_info->lock);
-	if (force < space_info->force_alloc)
-		force = space_info->force_alloc;
-	if (space_info->full) {
-		if (should_alloc_chunk(fs_info, space_info, force))
-			ret = -ENOSPC;
-		else
-			ret = 0;
-		spin_unlock(&space_info->lock);
-		return ret;
-	}
-
-	if (!should_alloc_chunk(fs_info, space_info, force)) {
-		spin_unlock(&space_info->lock);
-		return 0;
-	} else if (space_info->chunk_alloc) {
-		wait_for_alloc = 1;
-	} else {
-		space_info->chunk_alloc = 1;
-	}
-
-	spin_unlock(&space_info->lock);
-
-	mutex_lock(&fs_info->chunk_mutex);
+	do {
+		spin_lock(&space_info->lock);
+		if (force < space_info->force_alloc)
+			force = space_info->force_alloc;
+		should_alloc = should_alloc_chunk(fs_info, space_info, force);
+		if (space_info->full) {
+			/* No more free physical space */
+			if (should_alloc)
+				ret = -ENOSPC;
+			else
+				ret = 0;
+			spin_unlock(&space_info->lock);
+			return ret;
+		} else if (!should_alloc) {
+			spin_unlock(&space_info->lock);
+			return 0;
+		} else if (space_info->chunk_alloc) {
+			/*
+			 * Someone is already allocating, so we need to block
+			 * until this someone is finished and then loop to
+			 * recheck if we should continue with our allocation
+			 * attempt.
+			 */
+			wait_for_alloc = true;
+			spin_unlock(&space_info->lock);
+			mutex_lock(&fs_info->chunk_mutex);
+			mutex_unlock(&fs_info->chunk_mutex);
+		} else {
+			/* Proceed with allocation */
+			space_info->chunk_alloc = 1;
+			wait_for_alloc = false;
+			spin_unlock(&space_info->lock);
+		}
 
-	/*
-	 * The chunk_mutex is held throughout the entirety of a chunk
-	 * allocation, so once we've acquired the chunk_mutex we know that the
-	 * other guy is done and we need to recheck and see if we should
-	 * allocate.
-	 */
-	if (wait_for_alloc) {
-		mutex_unlock(&fs_info->chunk_mutex);
-		wait_for_alloc = 0;
 		cond_resched();
-		goto again;
-	}
+	} while (wait_for_alloc);
 
+	mutex_lock(&fs_info->chunk_mutex);
 	trans->allocating_chunk = true;
 
 	/*
@@ -4651,9 +4520,9 @@ again:
 	 * Check if we have enough space in SYSTEM chunk because we may need
 	 * to update devices.
 	 */
-	check_system_chunk(trans, fs_info, flags);
+	check_system_chunk(trans, flags);
 
-	ret = btrfs_alloc_chunk(trans, fs_info, flags);
+	ret = btrfs_alloc_chunk(trans, flags);
 	trans->allocating_chunk = false;
 
 	spin_lock(&space_info->lock);
@@ -4703,6 +4572,7 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 	u64 space_size;
 	u64 avail;
 	u64 used;
+	int factor;
 
 	/* Don't overcommit when in mixed mode. */
 	if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
@@ -4737,10 +4607,8 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 	 * doesn't include the parity drive, so we don't have to
 	 * change the math
 	 */
-	if (profile & (BTRFS_BLOCK_GROUP_DUP |
-		       BTRFS_BLOCK_GROUP_RAID1 |
-		       BTRFS_BLOCK_GROUP_RAID10))
-		avail >>= 1;
+	factor = btrfs_bg_type_to_factor(profile);
+	avail = div_u64(avail, factor);
 
 	/*
 	 * If we aren't flushing all things, let us overcommit up to
@@ -4912,8 +4780,9 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 		return 0;
 
 	/* See if there is enough pinned space to make this reservation */
-	if (percpu_counter_compare(&space_info->total_bytes_pinned,
-				   bytes) >= 0)
+	if (__percpu_counter_compare(&space_info->total_bytes_pinned,
+				   bytes,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH) >= 0)
 		goto commit;
 
 	/*
@@ -4930,8 +4799,9 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 		bytes -= delayed_rsv->size;
 	spin_unlock(&delayed_rsv->lock);
 
-	if (percpu_counter_compare(&space_info->total_bytes_pinned,
-				   bytes) < 0) {
+	if (__percpu_counter_compare(&space_info->total_bytes_pinned,
+				   bytes,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH) < 0) {
 		return -ENOSPC;
 	}
 
@@ -4984,7 +4854,7 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 			ret = PTR_ERR(trans);
 			break;
 		}
-		ret = do_chunk_alloc(trans, fs_info,
+		ret = do_chunk_alloc(trans,
 				     btrfs_metadata_alloc_profile(fs_info),
 				     CHUNK_ALLOC_NO_FORCE);
 		btrfs_end_transaction(trans);
@@ -5659,11 +5529,6 @@ void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
 	kfree(rsv);
 }
 
-void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv)
-{
-	kfree(rsv);
-}
-
 int btrfs_block_rsv_add(struct btrfs_root *root,
 			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
 			enum btrfs_reserve_flush_enum flush)
@@ -6019,7 +5884,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	unsigned nr_extents;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
 	int ret = 0;
@@ -6092,7 +5957,7 @@ out_fail:
 void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 				     bool qgroup_free)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 	spin_lock(&inode->lock);
@@ -6121,7 +5986,7 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
 				    bool qgroup_free)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	unsigned num_extents;
 
 	spin_lock(&inode->lock);
@@ -6219,12 +6084,8 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		cache = btrfs_lookup_block_group(info, bytenr);
 		if (!cache)
 			return -ENOENT;
-		if (cache->flags & (BTRFS_BLOCK_GROUP_DUP |
-				    BTRFS_BLOCK_GROUP_RAID1 |
-				    BTRFS_BLOCK_GROUP_RAID10))
-			factor = 2;
-		else
-			factor = 1;
+		factor = btrfs_bg_type_to_factor(cache->flags);
+
 		/*
 		 * If this block group has free space cache written out, we
 		 * need to make sure to load it if we are removing space.  This
@@ -6268,8 +6129,9 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 			trace_btrfs_space_reservation(info, "pinned",
 						      cache->space_info->flags,
 						      num_bytes, 1);
-			percpu_counter_add(&cache->space_info->total_bytes_pinned,
-					   num_bytes);
+			percpu_counter_add_batch(&cache->space_info->total_bytes_pinned,
+					   num_bytes,
+					   BTRFS_TOTAL_BYTES_PINNED_BATCH);
 			set_extent_dirty(info->pinned_extents,
 					 bytenr, bytenr + num_bytes - 1,
 					 GFP_NOFS | __GFP_NOFAIL);
@@ -6279,7 +6141,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		if (list_empty(&cache->dirty_list)) {
 			list_add_tail(&cache->dirty_list,
 				      &trans->transaction->dirty_bgs);
-				trans->transaction->num_dirty_bgs++;
+			trans->transaction->num_dirty_bgs++;
 			btrfs_get_block_group(cache);
 		}
 		spin_unlock(&trans->transaction->dirty_bgs_lock);
@@ -6290,16 +6152,8 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		 * dirty list to avoid races between cleaner kthread and space
 		 * cache writeout.
 		 */
-		if (!alloc && old_val == 0) {
-			spin_lock(&info->unused_bgs_lock);
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &info->unused_bgs);
-			}
-			spin_unlock(&info->unused_bgs_lock);
-		}
+		if (!alloc && old_val == 0)
+			btrfs_mark_bg_unused(cache);
 
 		btrfs_put_block_group(cache);
 		total -= num_bytes;
@@ -6347,7 +6201,8 @@ static int pin_down_extent(struct btrfs_fs_info *fs_info,
 
 	trace_btrfs_space_reservation(fs_info, "pinned",
 				      cache->space_info->flags, num_bytes, 1);
-	percpu_counter_add(&cache->space_info->total_bytes_pinned, num_bytes);
+	percpu_counter_add_batch(&cache->space_info->total_bytes_pinned,
+		    num_bytes, BTRFS_TOTAL_BYTES_PINNED_BATCH);
 	set_extent_dirty(fs_info->pinned_extents, bytenr,
 			 bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL);
 	return 0;
@@ -6711,7 +6566,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 		trace_btrfs_space_reservation(fs_info, "pinned",
 					      space_info->flags, len, 0);
 		space_info->max_extent_size = 0;
-		percpu_counter_add(&space_info->total_bytes_pinned, -len);
+		percpu_counter_add_batch(&space_info->total_bytes_pinned,
+			    -len, BTRFS_TOTAL_BYTES_PINNED_BATCH);
 		if (cache->ro) {
 			space_info->bytes_readonly += len;
 			readonly = true;
@@ -6815,12 +6671,12 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 }
 
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *info,
-				struct btrfs_delayed_ref_node *node, u64 parent,
-				u64 root_objectid, u64 owner_objectid,
-				u64 owner_offset, int refs_to_drop,
-				struct btrfs_delayed_extent_op *extent_op)
+			       struct btrfs_delayed_ref_node *node, u64 parent,
+			       u64 root_objectid, u64 owner_objectid,
+			       u64 owner_offset, int refs_to_drop,
+			       struct btrfs_delayed_extent_op *extent_op)
 {
+	struct btrfs_fs_info *info = trans->fs_info;
 	struct btrfs_key key;
 	struct btrfs_path *path;
 	struct btrfs_root *extent_root = info->extent_root;
@@ -6852,9 +6708,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	if (is_data)
 		skinny_metadata = false;
 
-	ret = lookup_extent_backref(trans, info, path, &iref,
-				    bytenr, num_bytes, parent,
-				    root_objectid, owner_objectid,
+	ret = lookup_extent_backref(trans, path, &iref, bytenr, num_bytes,
+				    parent, root_objectid, owner_objectid,
 				    owner_offset);
 	if (ret == 0) {
 		extent_slot = path->slots[0];
@@ -6877,14 +6732,10 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				break;
 			extent_slot--;
 		}
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		item_size = btrfs_item_size_nr(path->nodes[0], extent_slot);
-		if (found_extent && item_size < sizeof(*ei))
-			found_extent = 0;
-#endif
+
 		if (!found_extent) {
 			BUG_ON(iref);
-			ret = remove_extent_backref(trans, info, path, NULL,
+			ret = remove_extent_backref(trans, path, NULL,
 						    refs_to_drop,
 						    is_data, &last_ref);
 			if (ret) {
@@ -6957,42 +6808,12 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, extent_slot);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		BUG_ON(found_extent || extent_slot != path->slots[0]);
-		ret = convert_extent_item_v0(trans, info, path, owner_objectid,
-					     0);
-		if (ret < 0) {
-			btrfs_abort_transaction(trans, ret);
-			goto out;
-		}
-
-		btrfs_release_path(path);
-		path->leave_spinning = 1;
-
-		key.objectid = bytenr;
-		key.type = BTRFS_EXTENT_ITEM_KEY;
-		key.offset = num_bytes;
-
-		ret = btrfs_search_slot(trans, extent_root, &key, path,
-					-1, 1);
-		if (ret) {
-			btrfs_err(info,
-				  "umm, got %d back from search, was looking for %llu",
-				ret, bytenr);
-			btrfs_print_leaf(path->nodes[0]);
-		}
-		if (ret < 0) {
-			btrfs_abort_transaction(trans, ret);
-			goto out;
-		}
-
-		extent_slot = path->slots[0];
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, extent_slot);
+	if (unlikely(item_size < sizeof(*ei))) {
+		ret = -EINVAL;
+		btrfs_print_v0_err(info);
+		btrfs_abort_transaction(trans, ret);
+		goto out;
 	}
-#endif
-	BUG_ON(item_size < sizeof(*ei));
 	ei = btrfs_item_ptr(leaf, extent_slot,
 			    struct btrfs_extent_item);
 	if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID &&
@@ -7028,9 +6849,9 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			btrfs_mark_buffer_dirty(leaf);
 		}
 		if (found_extent) {
-			ret = remove_extent_backref(trans, info, path,
-						    iref, refs_to_drop,
-						    is_data, &last_ref);
+			ret = remove_extent_backref(trans, path, iref,
+						    refs_to_drop, is_data,
+						    &last_ref);
 			if (ret) {
 				btrfs_abort_transaction(trans, ret);
 				goto out;
@@ -7172,7 +6993,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 				   root->root_key.objectid,
 				   btrfs_header_level(buf), 0,
 				   BTRFS_DROP_DELAYED_REF);
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, buf->start,
+		ret = btrfs_add_delayed_tree_ref(trans, buf->start,
 						 buf->len, parent,
 						 root->root_key.objectid,
 						 btrfs_header_level(buf),
@@ -7251,13 +7072,13 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		old_ref_mod = new_ref_mod = 0;
 		ret = 0;
 	} else if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_tree_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, (int)owner,
 						 BTRFS_DROP_DELAYED_REF, NULL,
 						 &old_ref_mod, &new_ref_mod);
 	} else {
-		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_data_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, owner, offset,
 						 0, BTRFS_DROP_DELAYED_REF,
@@ -7534,7 +7355,7 @@ search:
 		 * for the proper type.
 		 */
 		if (!block_group_bits(block_group, flags)) {
-		    u64 extra = BTRFS_BLOCK_GROUP_DUP |
+			u64 extra = BTRFS_BLOCK_GROUP_DUP |
 				BTRFS_BLOCK_GROUP_RAID1 |
 				BTRFS_BLOCK_GROUP_RAID5 |
 				BTRFS_BLOCK_GROUP_RAID6 |
@@ -7738,7 +7559,7 @@ unclustered_alloc:
 			goto loop;
 		}
 checks:
-		search_start = ALIGN(offset, fs_info->stripesize);
+		search_start = round_up(offset, fs_info->stripesize);
 
 		/* move on to the next group */
 		if (search_start + num_bytes >
@@ -7750,7 +7571,6 @@ checks:
 		if (offset < search_start)
 			btrfs_add_free_space(block_group, offset,
 					     search_start - offset);
-		BUG_ON(offset > search_start);
 
 		ret = btrfs_add_reserved_bytes(block_group, ram_bytes,
 				num_bytes, delalloc);
@@ -7826,8 +7646,7 @@ loop:
 				goto out;
 			}
 
-			ret = do_chunk_alloc(trans, fs_info, flags,
-					     CHUNK_ALLOC_FORCE);
+			ret = do_chunk_alloc(trans, flags, CHUNK_ALLOC_FORCE);
 
 			/*
 			 * If we can't allocate a new chunk we've already looped
@@ -8053,11 +7872,11 @@ int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
 }
 
 static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
-				      struct btrfs_fs_info *fs_info,
 				      u64 parent, u64 root_objectid,
 				      u64 flags, u64 owner, u64 offset,
 				      struct btrfs_key *ins, int ref_mod)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_extent_item *extent_item;
 	struct btrfs_extent_inline_ref *iref;
@@ -8231,7 +8050,6 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 				     u64 offset, u64 ram_bytes,
 				     struct btrfs_key *ins)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
 
 	BUG_ON(root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);
@@ -8240,7 +8058,7 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 			   root->root_key.objectid, owner, offset,
 			   BTRFS_ADD_DELAYED_EXTENT);
 
-	ret = btrfs_add_delayed_data_ref(fs_info, trans, ins->objectid,
+	ret = btrfs_add_delayed_data_ref(trans, ins->objectid,
 					 ins->offset, 0,
 					 root->root_key.objectid, owner,
 					 offset, ram_bytes,
@@ -8254,10 +8072,10 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
  * space cache bits as well
  */
 int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   u64 root_objectid, u64 owner, u64 offset,
 				   struct btrfs_key *ins)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_block_group_cache *block_group;
 	struct btrfs_space_info *space_info;
@@ -8285,15 +8103,15 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 	spin_unlock(&block_group->lock);
 	spin_unlock(&space_info->lock);
 
-	ret = alloc_reserved_file_extent(trans, fs_info, 0, root_objectid,
-					 0, owner, offset, ins, 1);
+	ret = alloc_reserved_file_extent(trans, 0, root_objectid, 0, owner,
+					 offset, ins, 1);
 	btrfs_put_block_group(block_group);
 	return ret;
 }
 
 static struct extent_buffer *
 btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		      u64 bytenr, int level)
+		      u64 bytenr, int level, u64 owner)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *buf;
@@ -8302,7 +8120,6 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	if (IS_ERR(buf))
 		return buf;
 
-	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
 	clean_tree_block(fs_info, buf);
@@ -8311,6 +8128,14 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	btrfs_set_lock_blocking(buf);
 	set_extent_buffer_uptodate(buf);
 
+	memzero_extent_buffer(buf, 0, sizeof(struct btrfs_header));
+	btrfs_set_header_level(buf, level);
+	btrfs_set_header_bytenr(buf, buf->start);
+	btrfs_set_header_generation(buf, trans->transid);
+	btrfs_set_header_backref_rev(buf, BTRFS_MIXED_BACKREF_REV);
+	btrfs_set_header_owner(buf, owner);
+	write_extent_buffer_fsid(buf, fs_info->fsid);
+	write_extent_buffer_chunk_tree_uuid(buf, fs_info->chunk_tree_uuid);
 	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
 		buf->log_index = root->log_transid % 2;
 		/*
@@ -8419,7 +8244,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	if (btrfs_is_testing(fs_info)) {
 		buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
-					    level);
+					    level, root_objectid);
 		if (!IS_ERR(buf))
 			root->alloc_bytenr += blocksize;
 		return buf;
@@ -8435,7 +8260,8 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out_unuse;
 
-	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level);
+	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level,
+				    root_objectid);
 	if (IS_ERR(buf)) {
 		ret = PTR_ERR(buf);
 		goto out_free_reserved;
@@ -8467,7 +8293,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		btrfs_ref_tree_mod(root, ins.objectid, ins.offset, parent,
 				   root_objectid, level, 0,
 				   BTRFS_ADD_DELAYED_EXTENT);
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, ins.objectid,
+		ret = btrfs_add_delayed_tree_ref(trans, ins.objectid,
 						 ins.offset, parent,
 						 root_objectid, level,
 						 BTRFS_ADD_DELAYED_EXTENT,
@@ -8499,7 +8325,6 @@ struct walk_control {
 	int keep_locks;
 	int reada_slot;
 	int reada_count;
-	int for_reloc;
 };
 
 #define DROP_REFERENCE	1
@@ -8819,7 +8644,7 @@ skip:
 		}
 
 		if (need_account) {
-			ret = btrfs_qgroup_trace_subtree(trans, root, next,
+			ret = btrfs_qgroup_trace_subtree(trans, next,
 							 generation, level - 1);
 			if (ret) {
 				btrfs_err_rl(fs_info,
@@ -8919,7 +8744,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			else
 				ret = btrfs_dec_ref(trans, root, eb, 0);
 			BUG_ON(ret); /* -ENOMEM */
-			ret = btrfs_qgroup_trace_leaf_items(trans, fs_info, eb);
+			ret = btrfs_qgroup_trace_leaf_items(trans, eb);
 			if (ret) {
 				btrfs_err_rl(fs_info,
 					     "error %d accounting leaf items. Quota is out of sync, rescan required.",
@@ -9136,7 +8961,6 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	wc->stage = DROP_REFERENCE;
 	wc->update_ref = update_ref;
 	wc->keep_locks = 0;
-	wc->for_reloc = for_reloc;
 	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info);
 
 	while (1) {
@@ -9199,7 +9023,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	if (err)
 		goto out_end_trans;
 
-	ret = btrfs_del_root(trans, fs_info, &root->root_key);
+	ret = btrfs_del_root(trans, &root->root_key);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		err = ret;
@@ -9302,7 +9126,6 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	wc->stage = DROP_REFERENCE;
 	wc->update_ref = 0;
 	wc->keep_locks = 1;
-	wc->for_reloc = 1;
 	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info);
 
 	while (1) {
@@ -9417,10 +9240,10 @@ out:
 	return ret;
 }
 
-int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info,
-			     struct btrfs_block_group_cache *cache)
+int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache)
 
 {
+	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_trans_handle *trans;
 	u64 alloc_flags;
 	int ret;
@@ -9454,7 +9277,7 @@ again:
 	 */
 	alloc_flags = update_block_group_flags(fs_info, cache->flags);
 	if (alloc_flags != cache->flags) {
-		ret = do_chunk_alloc(trans, fs_info, alloc_flags,
+		ret = do_chunk_alloc(trans, alloc_flags,
 				     CHUNK_ALLOC_FORCE);
 		/*
 		 * ENOSPC is allowed here, we may have enough space
@@ -9471,8 +9294,7 @@ again:
 	if (!ret)
 		goto out;
 	alloc_flags = get_alloc_profile(fs_info, cache->space_info->flags);
-	ret = do_chunk_alloc(trans, fs_info, alloc_flags,
-			     CHUNK_ALLOC_FORCE);
+	ret = do_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
 	if (ret < 0)
 		goto out;
 	ret = inc_block_group_ro(cache, 0);
@@ -9480,7 +9302,7 @@ out:
 	if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
 		alloc_flags = update_block_group_flags(fs_info, cache->flags);
 		mutex_lock(&fs_info->chunk_mutex);
-		check_system_chunk(trans, fs_info, alloc_flags);
+		check_system_chunk(trans, alloc_flags);
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
 	mutex_unlock(&fs_info->ro_block_group_mutex);
@@ -9489,12 +9311,11 @@ out:
 	return ret;
 }
 
-int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info, u64 type)
+int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type)
 {
-	u64 alloc_flags = get_alloc_profile(fs_info, type);
+	u64 alloc_flags = get_alloc_profile(trans->fs_info, type);
 
-	return do_chunk_alloc(trans, fs_info, alloc_flags, CHUNK_ALLOC_FORCE);
+	return do_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
 }
 
 /*
@@ -9520,13 +9341,7 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
 			continue;
 		}
 
-		if (block_group->flags & (BTRFS_BLOCK_GROUP_RAID1 |
-					  BTRFS_BLOCK_GROUP_RAID10 |
-					  BTRFS_BLOCK_GROUP_DUP))
-			factor = 2;
-		else
-			factor = 1;
-
+		factor = btrfs_bg_type_to_factor(block_group->flags);
 		free_bytes += (block_group->key.offset -
 			       btrfs_block_group_used(&block_group->item)) *
 			       factor;
@@ -9717,6 +9532,8 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
 	int ret = 0;
 	struct btrfs_key found_key;
 	struct extent_buffer *leaf;
+	struct btrfs_block_group_item bg;
+	u64 flags;
 	int slot;
 
 	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
@@ -9751,8 +9568,32 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
 			"logical %llu len %llu found bg but no related chunk",
 					  found_key.objectid, found_key.offset);
 				ret = -ENOENT;
+			} else if (em->start != found_key.objectid ||
+				   em->len != found_key.offset) {
+				btrfs_err(fs_info,
+		"block group %llu len %llu mismatch with chunk %llu len %llu",
+					  found_key.objectid, found_key.offset,
+					  em->start, em->len);
+				ret = -EUCLEAN;
 			} else {
-				ret = 0;
+				read_extent_buffer(leaf, &bg,
+					btrfs_item_ptr_offset(leaf, slot),
+					sizeof(bg));
+				flags = btrfs_block_group_flags(&bg) &
+					BTRFS_BLOCK_GROUP_TYPE_MASK;
+
+				if (flags != (em->map_lookup->type &
+					      BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+					btrfs_err(fs_info,
+"block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx",
+						found_key.objectid,
+						found_key.offset, flags,
+						(BTRFS_BLOCK_GROUP_TYPE_MASK &
+						 em->map_lookup->type));
+					ret = -EUCLEAN;
+				} else {
+					ret = 0;
+				}
 			}
 			free_extent_map(em);
 			goto out;
@@ -9847,7 +9688,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		 */
 		if (block_group->cached == BTRFS_CACHE_NO ||
 		    block_group->cached == BTRFS_CACHE_ERROR)
-			free_excluded_extents(info, block_group);
+			free_excluded_extents(block_group);
 
 		btrfs_remove_free_space_cache(block_group);
 		ASSERT(block_group->cached != BTRFS_CACHE_STARTED);
@@ -10003,6 +9844,62 @@ btrfs_create_block_group_cache(struct btrfs_fs_info *fs_info,
 	return cache;
 }
 
+
+/*
+ * Iterate all chunks and verify that each of them has the corresponding block
+ * group
+ */
+static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+	struct extent_map *em;
+	struct btrfs_block_group_cache *bg;
+	u64 start = 0;
+	int ret = 0;
+
+	while (1) {
+		read_lock(&map_tree->map_tree.lock);
+		/*
+		 * lookup_extent_mapping will return the first extent map
+		 * intersecting the range, so setting @len to 1 is enough to
+		 * get the first chunk.
+		 */
+		em = lookup_extent_mapping(&map_tree->map_tree, start, 1);
+		read_unlock(&map_tree->map_tree.lock);
+		if (!em)
+			break;
+
+		bg = btrfs_lookup_block_group(fs_info, em->start);
+		if (!bg) {
+			btrfs_err(fs_info,
+	"chunk start=%llu len=%llu doesn't have corresponding block group",
+				     em->start, em->len);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			break;
+		}
+		if (bg->key.objectid != em->start ||
+		    bg->key.offset != em->len ||
+		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
+		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+			btrfs_err(fs_info,
+"chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
+				em->start, em->len,
+				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
+				bg->key.objectid, bg->key.offset,
+				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			btrfs_put_block_group(bg);
+			break;
+		}
+		start = em->start + em->len;
+		free_extent_map(em);
+		btrfs_put_block_group(bg);
+	}
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_path *path;
@@ -10089,13 +9986,13 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		 * info has super bytes accounted for, otherwise we'll think
 		 * we have more space than we actually do.
 		 */
-		ret = exclude_super_stripes(info, cache);
+		ret = exclude_super_stripes(cache);
 		if (ret) {
 			/*
 			 * We may have excluded something, so call this just in
 			 * case.
 			 */
-			free_excluded_extents(info, cache);
+			free_excluded_extents(cache);
 			btrfs_put_block_group(cache);
 			goto error;
 		}
@@ -10110,14 +10007,14 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		if (found_key.offset == btrfs_block_group_used(&cache->item)) {
 			cache->last_byte_to_unpin = (u64)-1;
 			cache->cached = BTRFS_CACHE_FINISHED;
-			free_excluded_extents(info, cache);
+			free_excluded_extents(cache);
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
 			cache->last_byte_to_unpin = (u64)-1;
 			cache->cached = BTRFS_CACHE_FINISHED;
 			add_new_free_space(cache, found_key.objectid,
 					   found_key.objectid +
 					   found_key.offset);
-			free_excluded_extents(info, cache);
+			free_excluded_extents(cache);
 		}
 
 		ret = btrfs_add_block_group_cache(info, cache);
@@ -10140,15 +10037,8 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		if (btrfs_chunk_readonly(info, cache->key.objectid)) {
 			inc_block_group_ro(cache, 1);
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
-			spin_lock(&info->unused_bgs_lock);
-			/* Should always be true but just in case. */
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &info->unused_bgs);
-			}
-			spin_unlock(&info->unused_bgs_lock);
+			ASSERT(list_empty(&cache->bg_list));
+			btrfs_mark_bg_unused(cache);
 		}
 	}
 
@@ -10176,7 +10066,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 
 	btrfs_add_raid_kobjects(info);
 	init_global_block_rsv(info);
-	ret = 0;
+	ret = check_chunk_block_group_mappings(info);
 error:
 	btrfs_free_path(path);
 	return ret;
@@ -10206,8 +10096,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 					sizeof(item));
 		if (ret)
 			btrfs_abort_transaction(trans, ret);
-		ret = btrfs_finish_chunk_alloc(trans, fs_info, key.objectid,
-					       key.offset);
+		ret = btrfs_finish_chunk_alloc(trans, key.objectid, key.offset);
 		if (ret)
 			btrfs_abort_transaction(trans, ret);
 		add_block_group_free_space(trans, block_group);
@@ -10218,10 +10107,10 @@ next:
 	trans->can_flush_pending_bgs = can_flush_pending_bgs;
 }
 
-int btrfs_make_block_group(struct btrfs_trans_handle *trans,
-			   struct btrfs_fs_info *fs_info, u64 bytes_used,
+int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 			   u64 type, u64 chunk_offset, u64 size)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_block_group_cache *cache;
 	int ret;
 
@@ -10240,20 +10129,20 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
 	cache->needs_free_space = 1;
-	ret = exclude_super_stripes(fs_info, cache);
+	ret = exclude_super_stripes(cache);
 	if (ret) {
 		/*
 		 * We may have excluded something, so call this just in
 		 * case.
 		 */
-		free_excluded_extents(fs_info, cache);
+		free_excluded_extents(cache);
 		btrfs_put_block_group(cache);
 		return ret;
 	}
 
 	add_new_free_space(cache, chunk_offset, chunk_offset + size);
 
-	free_excluded_extents(fs_info, cache);
+	free_excluded_extents(cache);
 
 #ifdef CONFIG_BTRFS_DEBUG
 	if (btrfs_should_fragment_free_space(cache)) {
@@ -10311,9 +10200,9 @@ static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 }
 
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info, u64 group_start,
-			     struct extent_map *em)
+			     u64 group_start, struct extent_map *em)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_path *path;
 	struct btrfs_block_group_cache *block_group;
@@ -10337,18 +10226,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * Free the reserved super bytes from this block group before
 	 * remove it.
 	 */
-	free_excluded_extents(fs_info, block_group);
+	free_excluded_extents(block_group);
 	btrfs_free_ref_tree_range(fs_info, block_group->key.objectid,
 				  block_group->key.offset);
 
 	memcpy(&key, &block_group->key, sizeof(key));
 	index = btrfs_bg_flags_to_raid_index(block_group->flags);
-	if (block_group->flags & (BTRFS_BLOCK_GROUP_DUP |
-				  BTRFS_BLOCK_GROUP_RAID1 |
-				  BTRFS_BLOCK_GROUP_RAID10))
-		factor = 2;
-	else
-		factor = 1;
+	factor = btrfs_bg_type_to_factor(block_group->flags);
 
 	/* make sure this block group isn't part of an allocation cluster */
 	cluster = &fs_info->data_alloc_cluster;
@@ -10687,7 +10571,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		/* Don't want to race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
 		spin_lock(&block_group->lock);
-		if (block_group->reserved ||
+		if (block_group->reserved || block_group->pinned ||
 		    btrfs_block_group_used(&block_group->item) ||
 		    block_group->ro ||
 		    list_is_singular(&block_group->list)) {
@@ -10764,8 +10648,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 
 		space_info->bytes_pinned -= block_group->pinned;
 		space_info->bytes_readonly += block_group->pinned;
-		percpu_counter_add(&space_info->total_bytes_pinned,
-				   -block_group->pinned);
+		percpu_counter_add_batch(&space_info->total_bytes_pinned,
+				   -block_group->pinned,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH);
 		block_group->pinned = 0;
 
 		spin_unlock(&block_group->lock);
@@ -10782,8 +10667,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * Btrfs_remove_chunk will abort the transaction if things go
 		 * horribly wrong.
 		 */
-		ret = btrfs_remove_chunk(trans, fs_info,
-					 block_group->key.objectid);
+		ret = btrfs_remove_chunk(trans, block_group->key.objectid);
 
 		if (ret) {
 			if (trimming)
@@ -11066,3 +10950,16 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
 			       !atomic_read(&root->will_be_snapshotted));
 	}
 }
+
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+
+	spin_lock(&fs_info->unused_bgs_lock);
+	if (list_empty(&bg->bg_list)) {
+		btrfs_get_block_group(bg);
+		trace_btrfs_add_unused_block_group(bg);
+		list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
+	}
+	spin_unlock(&fs_info->unused_bgs_lock);
+}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cce6087d6880..628f1aef34b0 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -140,14 +140,6 @@ static int add_extent_changeset(struct extent_state *state, unsigned bits,
 
 static void flush_write_bio(struct extent_page_data *epd);
 
-static inline struct btrfs_fs_info *
-tree_fs_info(struct extent_io_tree *tree)
-{
-	if (tree->ops)
-		return tree->ops->tree_fs_info(tree->private_data);
-	return NULL;
-}
-
 int __init extent_io_init(void)
 {
 	extent_state_cache = kmem_cache_create("btrfs_extent_state",
@@ -564,8 +556,10 @@ alloc_extent_state_atomic(struct extent_state *prealloc)
 
 static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
 {
-	btrfs_panic(tree_fs_info(tree), err,
-		    "Locking error: Extent tree was modified by another thread while locked.");
+	struct inode *inode = tree->private_data;
+
+	btrfs_panic(btrfs_sb(inode->i_sb), err,
+	"locking error: extent tree was modified by another thread while locked");
 }
 
 /*
@@ -1386,14 +1380,6 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
 	}
 }
 
-/*
- * helper function to set both pages and extents in the tree writeback
- */
-static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	tree->ops->set_range_writeback(tree->private_data, start, end);
-}
-
 /* find the first state struct with 'bits' set after 'start', and
  * return it.  tree->lock must be held.  NULL will returned if
  * nothing was found after 'start'
@@ -2059,7 +2045,7 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
 			 struct extent_buffer *eb, int mirror_num)
 {
 	u64 start = eb->start;
-	unsigned long i, num_pages = num_extent_pages(eb->start, eb->len);
+	int i, num_pages = num_extent_pages(eb);
 	int ret = 0;
 
 	if (sb_rdonly(fs_info->sb))
@@ -2398,7 +2384,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 				      start - page_offset(page),
 				      (int)phy_offset, failed_bio->bi_end_io,
 				      NULL);
-	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
+	bio->bi_opf = REQ_OP_READ | read_mode;
 
 	btrfs_debug(btrfs_sb(inode->i_sb),
 		"Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d",
@@ -2790,8 +2776,8 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 		else
 			contig = bio_end_sector(bio) == sector;
 
-		if (tree->ops && tree->ops->merge_bio_hook(page, offset,
-					page_size, bio, bio_flags))
+		if (tree->ops && btrfs_merge_bio_hook(page, offset, page_size,
+						      bio, bio_flags))
 			can_merge = false;
 
 		if (prev_bio_flags != bio_flags || !contig || !can_merge ||
@@ -3422,7 +3408,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 			continue;
 		}
 
-		set_range_writeback(tree, cur, cur + iosize - 1);
+		btrfs_set_range_writeback(tree, cur, cur + iosize - 1);
 		if (!PageWriteback(page)) {
 			btrfs_err(BTRFS_I(inode)->root->fs_info,
 				   "page %lu not writeback, cur %llu end %llu",
@@ -3538,7 +3524,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 			  struct btrfs_fs_info *fs_info,
 			  struct extent_page_data *epd)
 {
-	unsigned long i, num_pages;
+	int i, num_pages;
 	int flush = 0;
 	int ret = 0;
 
@@ -3588,7 +3574,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 	if (!ret)
 		return ret;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
@@ -3712,13 +3698,13 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	u64 offset = eb->start;
 	u32 nritems;
-	unsigned long i, num_pages;
+	int i, num_pages;
 	unsigned long start, end;
 	unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
 	int ret = 0;
 
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	atomic_set(&eb->io_pages, num_pages);
 
 	/* set btree blocks beyond nritems with 0 to avoid stale content. */
@@ -4238,8 +4224,9 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 	struct extent_map *em;
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
-	struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree;
-	struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree;
+	struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host);
+	struct extent_io_tree *tree = &btrfs_inode->io_tree;
+	struct extent_map_tree *map = &btrfs_inode->extent_tree;
 
 	if (gfpflags_allow_blocking(mask) &&
 	    page->mapping->host->i_size > SZ_16M) {
@@ -4262,6 +4249,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 					    extent_map_end(em) - 1,
 					    EXTENT_LOCKED | EXTENT_WRITEBACK,
 					    0, NULL)) {
+				set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+					&btrfs_inode->runtime_flags);
 				remove_extent_mapping(map, em);
 				/* once for the rb tree */
 				free_extent_map(em);
@@ -4542,8 +4531,11 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			offset_in_extent = em_start - em->start;
 		em_end = extent_map_end(em);
 		em_len = em_end - em_start;
-		disko = em->block_start + offset_in_extent;
 		flags = 0;
+		if (em->block_start < EXTENT_MAP_LAST_BYTE)
+			disko = em->block_start + offset_in_extent;
+		else
+			disko = 0;
 
 		/*
 		 * bump off for our next call to get_extent
@@ -4637,23 +4629,20 @@ int extent_buffer_under_io(struct extent_buffer *eb)
 }
 
 /*
- * Helper for releasing extent buffer page.
+ * Release all pages attached to the extent buffer.
  */
-static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
+static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb)
 {
-	unsigned long index;
-	struct page *page;
-	int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+	int i;
+	int num_pages;
+	int mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
 	BUG_ON(extent_buffer_under_io(eb));
 
-	index = num_extent_pages(eb->start, eb->len);
-	if (index == 0)
-		return;
+	num_pages = num_extent_pages(eb);
+	for (i = 0; i < num_pages; i++) {
+		struct page *page = eb->pages[i];
 
-	do {
-		index--;
-		page = eb->pages[index];
 		if (!page)
 			continue;
 		if (mapped)
@@ -4685,7 +4674,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 
 		/* One for when we allocated the page */
 		put_page(page);
-	} while (index != 0);
+	}
 }
 
 /*
@@ -4693,7 +4682,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
  */
 static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
 {
-	btrfs_release_extent_buffer_page(eb);
+	btrfs_release_extent_buffer_pages(eb);
 	__free_extent_buffer(eb);
 }
 
@@ -4737,10 +4726,10 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
 
 struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 {
-	unsigned long i;
+	int i;
 	struct page *p;
 	struct extent_buffer *new;
-	unsigned long num_pages = num_extent_pages(src->start, src->len);
+	int num_pages = num_extent_pages(src);
 
 	new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
 	if (new == NULL)
@@ -4760,7 +4749,7 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 	}
 
 	set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
-	set_bit(EXTENT_BUFFER_DUMMY, &new->bflags);
+	set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
 
 	return new;
 }
@@ -4769,15 +4758,14 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 						  u64 start, unsigned long len)
 {
 	struct extent_buffer *eb;
-	unsigned long num_pages;
-	unsigned long i;
-
-	num_pages = num_extent_pages(start, len);
+	int num_pages;
+	int i;
 
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
 		return NULL;
 
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		eb->pages[i] = alloc_page(GFP_NOFS);
 		if (!eb->pages[i])
@@ -4785,7 +4773,7 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 	}
 	set_extent_buffer_uptodate(eb);
 	btrfs_set_header_nritems(eb, 0);
-	set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+	set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
 	return eb;
 err:
@@ -4837,11 +4825,11 @@ static void check_buffer_tree_ref(struct extent_buffer *eb)
 static void mark_extent_buffer_accessed(struct extent_buffer *eb,
 		struct page *accessed)
 {
-	unsigned long num_pages, i;
+	int num_pages, i;
 
 	check_buffer_tree_ref(eb);
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
@@ -4938,8 +4926,8 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 					  u64 start)
 {
 	unsigned long len = fs_info->nodesize;
-	unsigned long num_pages = num_extent_pages(start, len);
-	unsigned long i;
+	int num_pages;
+	int i;
 	unsigned long index = start >> PAGE_SHIFT;
 	struct extent_buffer *eb;
 	struct extent_buffer *exists = NULL;
@@ -4961,6 +4949,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	if (!eb)
 		return ERR_PTR(-ENOMEM);
 
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++, index++) {
 		p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
 		if (!p) {
@@ -5003,8 +4992,11 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 			uptodate = 0;
 
 		/*
-		 * see below about how we avoid a nasty race with release page
-		 * and why we unlock later
+		 * We can't unlock the pages just yet since the extent buffer
+		 * hasn't been properly inserted in the radix tree, this
+		 * opens a race with btree_releasepage which can free a page
+		 * while we are still filling in all pages for the buffer and
+		 * we could crash.
 		 */
 	}
 	if (uptodate)
@@ -5033,21 +5025,12 @@ again:
 	set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
 
 	/*
-	 * there is a race where release page may have
-	 * tried to find this extent buffer in the radix
-	 * but failed.  It will tell the VM it is safe to
-	 * reclaim the, and it will clear the page private bit.
-	 * We must make sure to set the page private bit properly
-	 * after the extent buffer is in the radix tree so
-	 * it doesn't get lost
+	 * Now it's safe to unlock the pages because any calls to
+	 * btree_releasepage will correctly detect that a page belongs to a
+	 * live buffer and won't free them prematurely.
 	 */
-	SetPageChecked(eb->pages[0]);
-	for (i = 1; i < num_pages; i++) {
-		p = eb->pages[i];
-		ClearPageChecked(p);
-		unlock_page(p);
-	}
-	unlock_page(eb->pages[0]);
+	for (i = 0; i < num_pages; i++)
+		unlock_page(eb->pages[i]);
 	return eb;
 
 free_eb:
@@ -5069,9 +5052,10 @@ static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
 	__free_extent_buffer(eb);
 }
 
-/* Expects to have eb->eb_lock already held */
 static int release_extent_buffer(struct extent_buffer *eb)
 {
+	lockdep_assert_held(&eb->refs_lock);
+
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	if (atomic_dec_and_test(&eb->refs)) {
 		if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
@@ -5088,9 +5072,9 @@ static int release_extent_buffer(struct extent_buffer *eb)
 		}
 
 		/* Should be safe to release our pages at this point */
-		btrfs_release_extent_buffer_page(eb);
+		btrfs_release_extent_buffer_pages(eb);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-		if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) {
+		if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))) {
 			__free_extent_buffer(eb);
 			return 1;
 		}
@@ -5121,7 +5105,7 @@ void free_extent_buffer(struct extent_buffer *eb)
 
 	spin_lock(&eb->refs_lock);
 	if (atomic_read(&eb->refs) == 2 &&
-	    test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))
+	    test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))
 		atomic_dec(&eb->refs);
 
 	if (atomic_read(&eb->refs) == 2 &&
@@ -5153,11 +5137,11 @@ void free_extent_buffer_stale(struct extent_buffer *eb)
 
 void clear_extent_buffer_dirty(struct extent_buffer *eb)
 {
-	unsigned long i;
-	unsigned long num_pages;
+	int i;
+	int num_pages;
 	struct page *page;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
@@ -5183,15 +5167,15 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
 
 int set_extent_buffer_dirty(struct extent_buffer *eb)
 {
-	unsigned long i;
-	unsigned long num_pages;
+	int i;
+	int num_pages;
 	int was_dirty = 0;
 
 	check_buffer_tree_ref(eb);
 
 	was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
 
@@ -5202,12 +5186,12 @@ int set_extent_buffer_dirty(struct extent_buffer *eb)
 
 void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 {
-	unsigned long i;
+	int i;
 	struct page *page;
-	unsigned long num_pages;
+	int num_pages;
 
 	clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		if (page)
@@ -5217,12 +5201,12 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 
 void set_extent_buffer_uptodate(struct extent_buffer *eb)
 {
-	unsigned long i;
+	int i;
 	struct page *page;
-	unsigned long num_pages;
+	int num_pages;
 
 	set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		SetPageUptodate(page);
@@ -5232,13 +5216,13 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     struct extent_buffer *eb, int wait, int mirror_num)
 {
-	unsigned long i;
+	int i;
 	struct page *page;
 	int err;
 	int ret = 0;
 	int locked_pages = 0;
 	int all_uptodate = 1;
-	unsigned long num_pages;
+	int num_pages;
 	unsigned long num_reads = 0;
 	struct bio *bio = NULL;
 	unsigned long bio_flags = 0;
@@ -5246,7 +5230,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 		return 0;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		if (wait == WAIT_NONE) {
@@ -5570,11 +5554,11 @@ void copy_extent_buffer_full(struct extent_buffer *dst,
 			     struct extent_buffer *src)
 {
 	int i;
-	unsigned num_pages;
+	int num_pages;
 
 	ASSERT(dst->len == src->len);
 
-	num_pages = num_extent_pages(dst->start, dst->len);
+	num_pages = num_extent_pages(dst);
 	for (i = 0; i < num_pages; i++)
 		copy_page(page_address(dst->pages[i]),
 				page_address(src->pages[i]));
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0bfd4aeb822d..b4d03e677e1d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -46,7 +46,7 @@
 #define EXTENT_BUFFER_STALE 6
 #define EXTENT_BUFFER_WRITEBACK 7
 #define EXTENT_BUFFER_READ_ERR 8        /* read IO error */
-#define EXTENT_BUFFER_DUMMY 9
+#define EXTENT_BUFFER_UNMAPPED 9
 #define EXTENT_BUFFER_IN_TREE 10
 #define EXTENT_BUFFER_WRITE_ERR 11    /* write IO error */
 
@@ -92,9 +92,6 @@ typedef	blk_status_t (extent_submit_bio_hook_t)(void *private_data, struct bio *
 typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
 		struct bio *bio, u64 bio_offset);
 
-typedef blk_status_t (extent_submit_bio_done_t)(void *private_data,
-		struct bio *bio, int mirror_num);
-
 struct extent_io_ops {
 	/*
 	 * The following callbacks must be allways defined, the function
@@ -104,12 +101,7 @@ struct extent_io_ops {
 	int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
 				    struct page *page, u64 start, u64 end,
 				    int mirror);
-	int (*merge_bio_hook)(struct page *page, unsigned long offset,
-			      size_t size, struct bio *bio,
-			      unsigned long bio_flags);
 	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
-	struct btrfs_fs_info *(*tree_fs_info)(void *private_data);
-	void (*set_range_writeback)(void *private_data, u64 start, u64 end);
 
 	/*
 	 * Optional hooks, called if the pointer is not NULL
@@ -440,10 +432,10 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     int mirror_num);
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
 
-static inline unsigned long num_extent_pages(u64 start, u64 len)
+static inline int num_extent_pages(const struct extent_buffer *eb)
 {
-	return ((start + len + PAGE_SIZE - 1) >> PAGE_SHIFT) -
-		(start >> PAGE_SHIFT);
+	return (round_up(eb->start + eb->len, PAGE_SIZE) >> PAGE_SHIFT) -
+	       (eb->start >> PAGE_SHIFT);
 }
 
 static inline void extent_buffer_get(struct extent_buffer *eb)
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index f9dd6d1836a3..ba74827beb32 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -922,7 +922,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     const bool new_inline,
 				     struct extent_map *em)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf = path->nodes[0];
 	const int slot = path->slots[0];
@@ -942,7 +942,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 			btrfs_file_extent_num_bytes(leaf, fi);
 	} else if (type == BTRFS_FILE_EXTENT_INLINE) {
 		size_t size;
-		size = btrfs_file_extent_inline_len(leaf, slot, fi);
+		size = btrfs_file_extent_ram_bytes(leaf, fi);
 		extent_end = ALIGN(extent_start + size,
 				   fs_info->sectorsize);
 	}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 51e77d72068a..2be00e873e92 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -5,14 +5,11 @@
 
 #include <linux/fs.h>
 #include <linux/pagemap.h>
-#include <linux/highmem.h>
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
 #include <linux/falloc.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
 #include <linux/slab.h>
@@ -83,7 +80,7 @@ static int __compare_inode_defrag(struct inode_defrag *defrag1,
 static int __btrfs_add_inode_defrag(struct btrfs_inode *inode,
 				    struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct inode_defrag *entry;
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -135,8 +132,8 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info)
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 			   struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct inode_defrag *defrag;
 	u64 transid;
 	int ret;
@@ -185,7 +182,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode,
 				       struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret;
 
 	if (!__need_auto_defrag(fs_info))
@@ -833,8 +830,7 @@ next_slot:
 				btrfs_file_extent_num_bytes(leaf, fi);
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = key.offset +
-				btrfs_file_extent_inline_len(leaf,
-						     path->slots[0], fi);
+				btrfs_file_extent_ram_bytes(leaf, fi);
 		} else {
 			/* can't happen */
 			BUG();
@@ -1133,7 +1129,7 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 			      struct btrfs_inode *inode, u64 start, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
@@ -1470,7 +1466,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 				u64 *lockstart, u64 *lockend,
 				struct extent_state **cached_state)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 start_pos;
 	u64 last_pos;
 	int i;
@@ -1526,7 +1522,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 				    size_t *write_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct btrfs_ordered_extent *ordered;
 	u64 lockstart, lockend;
@@ -1569,10 +1565,11 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 	return ret;
 }
 
-static noinline ssize_t __btrfs_buffered_write(struct file *file,
-					       struct iov_iter *i,
-					       loff_t pos)
+static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
+					       struct iov_iter *i)
 {
+	struct file *file = iocb->ki_filp;
+	loff_t pos = iocb->ki_pos;
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -1804,7 +1801,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	loff_t pos = iocb->ki_pos;
+	loff_t pos;
 	ssize_t written;
 	ssize_t written_buffered;
 	loff_t endbyte;
@@ -1815,8 +1812,8 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	if (written < 0 || !iov_iter_count(from))
 		return written;
 
-	pos += written;
-	written_buffered = __btrfs_buffered_write(file, from, pos);
+	pos = iocb->ki_pos;
+	written_buffered = btrfs_buffered_write(iocb, from);
 	if (written_buffered < 0) {
 		err = written_buffered;
 		goto out;
@@ -1953,7 +1950,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		num_written = __btrfs_direct_write(iocb, from);
 	} else {
-		num_written = __btrfs_buffered_write(file, from, pos);
+		num_written = btrfs_buffered_write(iocb, from);
 		if (num_written > 0)
 			iocb->ki_pos = pos + num_written;
 		if (clean_page)
@@ -2042,7 +2039,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_log_ctx ctx;
 	int ret = 0, err;
-	bool full_sync = false;
 	u64 len;
 
 	/*
@@ -2066,96 +2062,21 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	inode_lock(inode);
 	atomic_inc(&root->log_batch);
-	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			     &BTRFS_I(inode)->runtime_flags);
+
 	/*
-	 * We might have have had more pages made dirty after calling
-	 * start_ordered_ops and before acquiring the inode's i_mutex.
+	 * We have to do this here to avoid the priority inversion of waiting on
+	 * IO of a lower priority task while holding a transaciton open.
 	 */
-	if (full_sync) {
-		/*
-		 * For a full sync, we need to make sure any ordered operations
-		 * start and finish before we start logging the inode, so that
-		 * all extents are persisted and the respective file extent
-		 * items are in the fs/subvol btree.
-		 */
-		ret = btrfs_wait_ordered_range(inode, start, len);
-	} else {
-		/*
-		 * Start any new ordered operations before starting to log the
-		 * inode. We will wait for them to finish in btrfs_sync_log().
-		 *
-		 * Right before acquiring the inode's mutex, we might have new
-		 * writes dirtying pages, which won't immediately start the
-		 * respective ordered operations - that is done through the
-		 * fill_delalloc callbacks invoked from the writepage and
-		 * writepages address space operations. So make sure we start
-		 * all ordered operations before starting to log our inode. Not
-		 * doing this means that while logging the inode, writeback
-		 * could start and invoke writepage/writepages, which would call
-		 * the fill_delalloc callbacks (cow_file_range,
-		 * submit_compressed_extents). These callbacks add first an
-		 * extent map to the modified list of extents and then create
-		 * the respective ordered operation, which means in
-		 * tree-log.c:btrfs_log_inode() we might capture all existing
-		 * ordered operations (with btrfs_get_logged_extents()) before
-		 * the fill_delalloc callback adds its ordered operation, and by
-		 * the time we visit the modified list of extent maps (with
-		 * btrfs_log_changed_extents()), we see and process the extent
-		 * map they created. We then use the extent map to construct a
-		 * file extent item for logging without waiting for the
-		 * respective ordered operation to finish - this file extent
-		 * item points to a disk location that might not have yet been
-		 * written to, containing random data - so after a crash a log
-		 * replay will make our inode have file extent items that point
-		 * to disk locations containing invalid data, as we returned
-		 * success to userspace without waiting for the respective
-		 * ordered operation to finish, because it wasn't captured by
-		 * btrfs_get_logged_extents().
-		 */
-		ret = start_ordered_ops(inode, start, end);
-	}
+	ret = btrfs_wait_ordered_range(inode, start, len);
 	if (ret) {
 		inode_unlock(inode);
 		goto out;
 	}
 	atomic_inc(&root->log_batch);
 
-	/*
-	 * If the last transaction that changed this file was before the current
-	 * transaction and we have the full sync flag set in our inode, we can
-	 * bail out now without any syncing.
-	 *
-	 * Note that we can't bail out if the full sync flag isn't set. This is
-	 * because when the full sync flag is set we start all ordered extents
-	 * and wait for them to fully complete - when they complete they update
-	 * the inode's last_trans field through:
-	 *
-	 *     btrfs_finish_ordered_io() ->
-	 *         btrfs_update_inode_fallback() ->
-	 *             btrfs_update_inode() ->
-	 *                 btrfs_set_inode_last_trans()
-	 *
-	 * So we are sure that last_trans is up to date and can do this check to
-	 * bail out safely. For the fast path, when the full sync flag is not
-	 * set in our inode, we can not do it because we start only our ordered
-	 * extents and don't wait for them to complete (that is when
-	 * btrfs_finish_ordered_io runs), so here at this point their last_trans
-	 * value might be less than or equals to fs_info->last_trans_committed,
-	 * and setting a speculative last_trans for an inode when a buffered
-	 * write is made (such as fs_info->generation + 1 for example) would not
-	 * be reliable since after setting the value and before fsync is called
-	 * any number of transactions can start and commit (transaction kthread
-	 * commits the current transaction periodically), and a transaction
-	 * commit does not start nor waits for ordered extents to complete.
-	 */
 	smp_mb();
 	if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) ||
-	    (full_sync && BTRFS_I(inode)->last_trans <=
-	     fs_info->last_trans_committed) ||
-	    (!btrfs_have_ordered_extents_in_range(inode, start, len) &&
-	     BTRFS_I(inode)->last_trans
-	     <= fs_info->last_trans_committed)) {
+	    BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed) {
 		/*
 		 * We've had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
@@ -2239,13 +2160,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 				goto out;
 			}
 		}
-		if (!full_sync) {
-			ret = btrfs_wait_ordered_range(inode, start, len);
-			if (ret) {
-				btrfs_end_transaction(trans);
-				goto out;
-			}
-		}
 		ret = btrfs_commit_transaction(trans);
 	} else {
 		ret = btrfs_end_transaction(trans);
@@ -2310,7 +2224,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		struct btrfs_inode *inode,
 		struct btrfs_path *path, u64 offset, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_file_extent_item *fi;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d5f80cb300be..0adf38b00fa0 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -71,10 +71,6 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	inode = btrfs_iget(fs_info->sb, &location, root, NULL);
 	if (IS_ERR(inode))
 		return inode;
-	if (is_bad_inode(inode)) {
-		iput(inode);
-		return ERR_PTR(-ENOENT);
-	}
 
 	mapping_set_gfp_mask(inode->i_mapping,
 			mapping_gfp_constraint(inode->i_mapping,
@@ -300,9 +296,9 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
 	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FREE_INO_OBJECTID)
 		check_crcs = 1;
 
-	/* Make sure we can fit our crcs into the first page */
+	/* Make sure we can fit our crcs and generation into the first page */
 	if (write && check_crcs &&
-	    (num_pages * sizeof(u32)) >= PAGE_SIZE)
+	    (num_pages * sizeof(u32) + sizeof(u64)) > PAGE_SIZE)
 		return -ENOSPC;
 
 	memset(io_ctl, 0, sizeof(struct btrfs_io_ctl));
@@ -547,7 +543,7 @@ static int io_ctl_add_bitmap(struct btrfs_io_ctl *io_ctl, void *bitmap)
 		io_ctl_map_page(io_ctl, 0);
 	}
 
-	memcpy(io_ctl->cur, bitmap, PAGE_SIZE);
+	copy_page(io_ctl->cur, bitmap);
 	io_ctl_set_crc(io_ctl, io_ctl->index - 1);
 	if (io_ctl->index < io_ctl->num_pages)
 		io_ctl_map_page(io_ctl, 0);
@@ -607,7 +603,7 @@ static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl,
 	if (ret)
 		return ret;
 
-	memcpy(entry->bitmap, io_ctl->cur, PAGE_SIZE);
+	copy_page(entry->bitmap, io_ctl->cur);
 	io_ctl_unmap_page(io_ctl);
 
 	return 0;
@@ -655,7 +651,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 				   struct btrfs_free_space_ctl *ctl,
 				   struct btrfs_path *path, u64 offset)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_free_space_header *header;
 	struct extent_buffer *leaf;
 	struct btrfs_io_ctl io_ctl;
@@ -1123,13 +1119,10 @@ static int __btrfs_wait_cache_io(struct btrfs_root *root,
 {
 	int ret;
 	struct inode *inode = io_ctl->inode;
-	struct btrfs_fs_info *fs_info;
 
 	if (!inode)
 		return 0;
 
-	fs_info = btrfs_sb(inode->i_sb);
-
 	/* Flush the dirty pages in the cache file. */
 	ret = flush_dirty_cache(inode);
 	if (ret)
@@ -1145,7 +1138,7 @@ out:
 		BTRFS_I(inode)->generation = 0;
 		if (block_group) {
 #ifdef DEBUG
-			btrfs_err(fs_info,
+			btrfs_err(root->fs_info,
 				  "failed to write free space cache for block group %llu",
 				  block_group->key.objectid);
 #endif
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index b5950aacd697..d6736595ec57 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1236,7 +1236,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
 	if (ret)
 		goto abort;
 
-	ret = btrfs_del_root(trans, fs_info, &free_space_root->root_key);
+	ret = btrfs_del_root(trans, &free_space_root->root_key);
 	if (ret)
 		goto abort;
 
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 12fcd8897c33..ffca2abf13d0 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2007 Oracle.  All rights reserved.
  */
 
-#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/pagemap.h>
 
@@ -244,8 +243,6 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 		return;
 
 	while (1) {
-		bool add_to_ctl = true;
-
 		spin_lock(rbroot_lock);
 		n = rb_first(rbroot);
 		if (!n) {
@@ -257,15 +254,14 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 		BUG_ON(info->bitmap); /* Logic error */
 
 		if (info->offset > root->ino_cache_progress)
-			add_to_ctl = false;
-		else if (info->offset + info->bytes > root->ino_cache_progress)
-			count = root->ino_cache_progress - info->offset + 1;
+			count = 0;
 		else
-			count = info->bytes;
+			count = min(root->ino_cache_progress - info->offset + 1,
+				    info->bytes);
 
 		rb_erase(&info->offset_index, rbroot);
 		spin_unlock(rbroot_lock);
-		if (add_to_ctl)
+		if (count)
 			__btrfs_add_free_space(root->fs_info, ctl,
 					       info->offset, count);
 		kmem_cache_free(btrfs_free_space_cachep, info);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e9482f0db9d0..9357a19d2bff 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -14,17 +14,13 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
-#include <linux/bit_spinlock.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/falloc.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
-#include <linux/mount.h>
 #include <linux/btrfs.h>
 #include <linux/blkdev.h>
 #include <linux/posix_acl_xattr.h>
@@ -1443,8 +1439,7 @@ next_slot:
 			nocow = 1;
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = found_key.offset +
-				btrfs_file_extent_inline_len(leaf,
-						     path->slots[0], fi);
+				btrfs_file_extent_ram_bytes(leaf, fi);
 			extent_end = ALIGN(extent_end,
 					   fs_info->sectorsize);
 		} else {
@@ -1752,7 +1747,7 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
 void __btrfs_del_delalloc_inode(struct btrfs_root *root,
 				struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (!list_empty(&inode->delalloc_inodes)) {
 		list_del_init(&inode->delalloc_inodes);
@@ -1903,8 +1898,8 @@ static void btrfs_clear_bit_hook(void *private_data,
 }
 
 /*
- * extent_io.c merge_bio_hook, this must check the chunk tree to make sure
- * we don't create bios that span stripes or chunks
+ * Merge bio hook, this must check the chunk tree to make sure we don't create
+ * bios that span stripes or chunks
  *
  * return 1 if page cannot be merged to bio
  * return 0 if page can be merged to bio
@@ -1962,7 +1957,7 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
+blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
 			  int mirror_num)
 {
 	struct inode *inode = private_data;
@@ -2035,8 +2030,7 @@ static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio,
 		/* we're doing a write, do the async checksumming */
 		ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags,
 					  bio_offset, inode,
-					  btrfs_submit_bio_start,
-					  btrfs_submit_bio_done);
+					  btrfs_submit_bio_start);
 		goto out;
 	} else if (!skip_sum) {
 		ret = btrfs_csum_one_bio(inode, bio, 0, 0);
@@ -3610,18 +3604,15 @@ static int btrfs_read_locked_inode(struct inode *inode)
 		filled = true;
 
 	path = btrfs_alloc_path();
-	if (!path) {
-		ret = -ENOMEM;
-		goto make_bad;
-	}
+	if (!path)
+		return -ENOMEM;
 
 	memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
 
 	ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
 	if (ret) {
-		if (ret > 0)
-			ret = -ENOENT;
-		goto make_bad;
+		btrfs_free_path(path);
+		return ret;
 	}
 
 	leaf = path->nodes[0];
@@ -3774,11 +3765,6 @@ cache_acl:
 
 	btrfs_sync_inode_flags_to_i_flags(inode);
 	return 0;
-
-make_bad:
-	btrfs_free_path(path);
-	make_bad_inode(inode);
-	return ret;
 }
 
 /*
@@ -3984,7 +3970,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		goto err;
 	}
 skip_backref:
-	ret = btrfs_delete_delayed_dir_index(trans, fs_info, dir, index);
+	ret = btrfs_delete_delayed_dir_index(trans, dir, index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto err;
@@ -4087,11 +4073,10 @@ out:
 }
 
 static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root,
-			struct inode *dir, u64 objectid,
-			const char *name, int name_len)
+			       struct inode *dir, u64 objectid,
+			       const char *name, int name_len)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_dir_item *di;
@@ -4124,9 +4109,8 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_del_root_ref(trans, fs_info, objectid,
-				 root->root_key.objectid, dir_ino,
-				 &index, name, name_len);
+	ret = btrfs_del_root_ref(trans, objectid, root->root_key.objectid,
+				 dir_ino, &index, name, name_len);
 	if (ret < 0) {
 		if (ret != -ENOENT) {
 			btrfs_abort_transaction(trans, ret);
@@ -4145,12 +4129,11 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-		btrfs_release_path(path);
 		index = key.offset;
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_delete_delayed_dir_index(trans, fs_info, BTRFS_I(dir), index);
+	ret = btrfs_delete_delayed_dir_index(trans, BTRFS_I(dir), index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -4243,9 +4226,9 @@ again:
 		prev = node;
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
 
-		if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		if (objectid < btrfs_ino(entry))
 			node = node->rb_left;
-		else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		else if (objectid > btrfs_ino(entry))
 			node = node->rb_right;
 		else
 			break;
@@ -4253,7 +4236,7 @@ again:
 	if (!node) {
 		while (prev) {
 			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) {
+			if (objectid <= btrfs_ino(entry)) {
 				node = prev;
 				break;
 			}
@@ -4262,7 +4245,7 @@ again:
 	}
 	while (node) {
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
-		objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1;
+		objectid = btrfs_ino(entry) + 1;
 		inode = igrab(&entry->vfs_inode);
 		if (inode) {
 			spin_unlock(&root->inode_lock);
@@ -4343,10 +4326,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
 
 	btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
 
-	ret = btrfs_unlink_subvol(trans, root, dir,
-				dest->root_key.objectid,
-				dentry->d_name.name,
-				dentry->d_name.len);
+	ret = btrfs_unlink_subvol(trans, dir, dest->root_key.objectid,
+				  dentry->d_name.name, dentry->d_name.len);
 	if (ret) {
 		err = ret;
 		btrfs_abort_transaction(trans, ret);
@@ -4441,7 +4422,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 		return PTR_ERR(trans);
 
 	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
-		err = btrfs_unlink_subvol(trans, root, dir,
+		err = btrfs_unlink_subvol(trans, dir,
 					  BTRFS_I(inode)->location.objectid,
 					  dentry->d_name.name,
 					  dentry->d_name.len);
@@ -4643,8 +4624,8 @@ search_again:
 					BTRFS_I(inode), leaf, fi,
 					found_key.offset);
 			} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
-				item_end += btrfs_file_extent_inline_len(leaf,
-							 path->slots[0], fi);
+				item_end += btrfs_file_extent_ram_bytes(leaf,
+									fi);
 
 				trace_btrfs_truncate_show_fi_inline(
 					BTRFS_I(inode), leaf, fi, path->slots[0],
@@ -5615,9 +5596,9 @@ static void inode_tree_add(struct inode *inode)
 		parent = *p;
 		entry = rb_entry(parent, struct btrfs_inode, rb_node);
 
-		if (ino < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		if (ino < btrfs_ino(entry))
 			p = &parent->rb_left;
-		else if (ino > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		else if (ino > btrfs_ino(entry))
 			p = &parent->rb_right;
 		else {
 			WARN_ON(!(entry->vfs_inode.i_state &
@@ -5708,16 +5689,21 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 		int ret;
 
 		ret = btrfs_read_locked_inode(inode);
-		if (!is_bad_inode(inode)) {
+		if (!ret) {
 			inode_tree_add(inode);
 			unlock_new_inode(inode);
 			if (new)
 				*new = 1;
 		} else {
-			unlock_new_inode(inode);
-			iput(inode);
-			ASSERT(ret < 0);
-			inode = ERR_PTR(ret < 0 ? ret : -ESTALE);
+			iget_failed(inode);
+			/*
+			 * ret > 0 can come from btrfs_search_slot called by
+			 * btrfs_read_locked_inode, this means the inode item
+			 * was not found.
+			 */
+			if (ret > 0)
+				ret = -ENOENT;
+			inode = ERR_PTR(ret);
 		}
 	}
 
@@ -5745,7 +5731,7 @@ static struct inode *new_simple_dir(struct super_block *s,
 	inode->i_mtime = current_time(inode);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
-	BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime);
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
 
 	return inode;
 }
@@ -6027,32 +6013,6 @@ err:
 	return ret;
 }
 
-int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
-{
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_trans_handle *trans;
-	int ret = 0;
-	bool nolock = false;
-
-	if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags))
-		return 0;
-
-	if (btrfs_fs_closing(root->fs_info) &&
-			btrfs_is_free_space_inode(BTRFS_I(inode)))
-		nolock = true;
-
-	if (wbc->sync_mode == WB_SYNC_ALL) {
-		if (nolock)
-			trans = btrfs_join_transaction_nolock(root);
-		else
-			trans = btrfs_join_transaction(root);
-		if (IS_ERR(trans))
-			return PTR_ERR(trans);
-		ret = btrfs_commit_transaction(trans);
-	}
-	return ret;
-}
-
 /*
  * This is somewhat expensive, updating the tree every time the
  * inode changes.  But, it is most likely to find the inode in cache.
@@ -6335,8 +6295,10 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	location->type = BTRFS_INODE_ITEM_KEY;
 
 	ret = btrfs_insert_inode_locked(inode);
-	if (ret < 0)
+	if (ret < 0) {
+		iput(inode);
 		goto fail;
+	}
 
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems);
@@ -6349,7 +6311,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	inode->i_mtime = current_time(inode);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
-	BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime);
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
 
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				  struct btrfs_inode_item);
@@ -6395,12 +6357,11 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	return inode;
 
 fail_unlock:
-	unlock_new_inode(inode);
+	discard_new_inode(inode);
 fail:
 	if (dir && name)
 		BTRFS_I(dir)->index_cnt--;
 	btrfs_free_path(path);
-	iput(inode);
 	return ERR_PTR(ret);
 }
 
@@ -6419,7 +6380,6 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret = 0;
 	struct btrfs_key key;
 	struct btrfs_root *root = parent_inode->root;
@@ -6435,7 +6395,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 	}
 
 	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
-		ret = btrfs_add_root_ref(trans, fs_info, key.objectid,
+		ret = btrfs_add_root_ref(trans, key.objectid,
 					 root->root_key.objectid, parent_ino,
 					 index, name, name_len);
 	} else if (add_backref) {
@@ -6471,7 +6431,7 @@ fail_dir_item:
 	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		u64 local_index;
 		int err;
-		err = btrfs_del_root_ref(trans, fs_info, key.objectid,
+		err = btrfs_del_root_ref(trans, key.objectid,
 					 root->root_key.objectid, parent_ino,
 					 &local_index, name, name_len);
 
@@ -6505,7 +6465,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = NULL;
 	int err;
-	int drop_inode = 0;
 	u64 objectid;
 	u64 index = 0;
 
@@ -6527,6 +6486,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 			mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_unlock;
 	}
 
@@ -6541,31 +6501,24 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
 			0, index);
-	if (err) {
-		goto out_unlock_inode;
-	} else {
-		btrfs_update_inode(trans, root, inode);
-		d_instantiate_new(dentry, inode);
-	}
+	if (err)
+		goto out_unlock;
+
+	btrfs_update_inode(trans, root, inode);
+	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
-	if (drop_inode) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	return err;
-
-out_unlock_inode:
-	drop_inode = 1;
-	unlock_new_inode(inode);
-	goto out_unlock;
-
 }
 
 static int btrfs_create(struct inode *dir, struct dentry *dentry,
@@ -6575,7 +6528,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = NULL;
-	int drop_inode_on_err = 0;
 	int err;
 	u64 objectid;
 	u64 index = 0;
@@ -6598,9 +6550,9 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 			mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_unlock;
 	}
-	drop_inode_on_err = 1;
 	/*
 	* If the active LSM wants to access the inode during
 	* d_instantiate it needs these. Smack checks to see
@@ -6613,33 +6565,28 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	err = btrfs_update_inode(trans, root, inode);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
 			0, index);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
-	if (err && drop_inode_on_err) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
-
-out_unlock_inode:
-	unlock_new_inode(inode);
-	goto out_unlock;
-
 }
 
 static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
@@ -6748,6 +6695,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 			S_IFDIR | mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_fail;
 	}
 
@@ -6758,34 +6706,30 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_fail_inode;
+		goto out_fail;
 
 	btrfs_i_size_write(BTRFS_I(inode), 0);
 	err = btrfs_update_inode(trans, root, inode);
 	if (err)
-		goto out_fail_inode;
+		goto out_fail;
 
 	err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 			dentry->d_name.name,
 			dentry->d_name.len, 0, index);
 	if (err)
-		goto out_fail_inode;
+		goto out_fail;
 
 	d_instantiate_new(dentry, inode);
 	drop_on_err = 0;
 
 out_fail:
 	btrfs_end_transaction(trans);
-	if (drop_on_err) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
-
-out_fail_inode:
-	unlock_new_inode(inode);
-	goto out_fail;
 }
 
 static noinline int uncompress_inline(struct btrfs_path *path,
@@ -6847,7 +6791,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 	    size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret;
 	int err = 0;
 	u64 extent_start = 0;
@@ -6943,7 +6887,8 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 						       extent_start);
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		size_t size;
-		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
+
+		size = btrfs_file_extent_ram_bytes(leaf, item);
 		extent_end = ALIGN(extent_start + size,
 				   fs_info->sectorsize);
 
@@ -6994,7 +6939,7 @@ next:
 		if (new_inline)
 			goto out;
 
-		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
+		size = btrfs_file_extent_ram_bytes(leaf, item);
 		extent_offset = page_offset(page) + pg_offset - extent_start;
 		copy_size = min_t(u64, PAGE_SIZE - pg_offset,
 				  size - extent_offset);
@@ -7865,7 +7810,7 @@ static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio,
 	isector >>= inode->i_sb->s_blocksize_bits;
 	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
 				pgoff, isector, repair_endio, repair_arg);
-	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
+	bio->bi_opf = REQ_OP_READ | read_mode;
 
 	btrfs_debug(BTRFS_I(inode)->root->fs_info,
 		    "repair DIO read error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d",
@@ -8299,8 +8244,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
 	if (write && async_submit) {
 		ret = btrfs_wq_submit_bio(fs_info, bio, 0, 0,
 					  file_offset, inode,
-					  btrfs_submit_bio_start_direct_io,
-					  btrfs_submit_bio_done);
+					  btrfs_submit_bio_start_direct_io);
 		goto err;
 	} else if (write) {
 		/*
@@ -9005,13 +8949,14 @@ again:
 
 	unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
 
-out_unlock:
 	if (!ret2) {
 		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true);
 		sb_end_pagefault(inode->i_sb);
 		extent_changeset_free(data_reserved);
 		return VM_FAULT_LOCKED;
 	}
+
+out_unlock:
 	unlock_page(page);
 out:
 	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0));
@@ -9443,6 +9388,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	u64 new_idx = 0;
 	u64 root_objectid;
 	int ret;
+	int ret2;
 	bool root_log_pinned = false;
 	bool dest_log_pinned = false;
 
@@ -9538,8 +9484,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	/* src is a subvolume */
 	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
 		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, root, old_dir,
-					  root_objectid,
+		ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
 					  old_dentry->d_name.name,
 					  old_dentry->d_name.len);
 	} else { /* src is an inode */
@@ -9558,8 +9503,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	/* dest is a subvolume */
 	if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
 		root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, dest, new_dir,
-					  root_objectid,
+		ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
 					  new_dentry->d_name.name,
 					  new_dentry->d_name.len);
 	} else { /* dest is an inode */
@@ -9639,7 +9583,8 @@ out_fail:
 			dest_log_pinned = false;
 		}
 	}
-	ret = btrfs_end_transaction(trans);
+	ret2 = btrfs_end_transaction(trans);
+	ret = ret ? ret : ret2;
 out_notrans:
 	if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
 		up_read(&fs_info->subvol_sem);
@@ -9818,7 +9763,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, root, old_dir, root_objectid,
+		ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
 					old_dentry->d_name.name,
 					old_dentry->d_name.len);
 	} else {
@@ -9840,8 +9785,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (unlikely(btrfs_ino(BTRFS_I(new_inode)) ==
 			     BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 			root_objectid = BTRFS_I(new_inode)->location.objectid;
-			ret = btrfs_unlink_subvol(trans, dest, new_dir,
-						root_objectid,
+			ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
 						new_dentry->d_name.name,
 						new_dentry->d_name.len);
 			BUG_ON(new_inode->i_nlink == 0);
@@ -10112,7 +10056,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	struct btrfs_key key;
 	struct inode *inode = NULL;
 	int err;
-	int drop_inode = 0;
 	u64 objectid;
 	u64 index = 0;
 	int name_len;
@@ -10145,6 +10088,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 				objectid, S_IFLNK|S_IRWXUGO, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_unlock;
 	}
 
@@ -10161,12 +10105,12 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	path = btrfs_alloc_path();
 	if (!path) {
 		err = -ENOMEM;
-		goto out_unlock_inode;
+		goto out_unlock;
 	}
 	key.objectid = btrfs_ino(BTRFS_I(inode));
 	key.offset = 0;
@@ -10176,7 +10120,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 				      datasize);
 	if (err) {
 		btrfs_free_path(path);
-		goto out_unlock_inode;
+		goto out_unlock;
 	}
 	leaf = path->nodes[0];
 	ei = btrfs_item_ptr(leaf, path->slots[0],
@@ -10208,26 +10152,19 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	if (!err)
 		err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
 				BTRFS_I(inode), 0, index);
-	if (err) {
-		drop_inode = 1;
-		goto out_unlock_inode;
-	}
+	if (err)
+		goto out_unlock;
 
 	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
-	if (drop_inode) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
-
-out_unlock_inode:
-	drop_inode = 1;
-	unlock_new_inode(inode);
-	goto out_unlock;
 }
 
 static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -10436,14 +10373,14 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	ret = btrfs_init_inode_security(trans, inode, dir, NULL);
 	if (ret)
-		goto out_inode;
+		goto out;
 
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret)
-		goto out_inode;
+		goto out;
 	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 	if (ret)
-		goto out_inode;
+		goto out;
 
 	/*
 	 * We set number of links to 0 in btrfs_new_inode(), and here we set
@@ -10453,21 +10390,15 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	 *    d_tmpfile() -> inode_dec_link_count() -> drop_nlink()
 	 */
 	set_nlink(inode, 1);
-	unlock_new_inode(inode);
 	d_tmpfile(dentry, inode);
+	unlock_new_inode(inode);
 	mark_inode_dirty(inode);
-
 out:
 	btrfs_end_transaction(trans);
-	if (ret)
-		iput(inode);
+	if (ret && inode)
+		discard_new_inode(inode);
 	btrfs_btree_balance_dirty(fs_info);
 	return ret;
-
-out_inode:
-	unlock_new_inode(inode);
-	goto out;
-
 }
 
 __attribute__((const))
@@ -10476,12 +10407,6 @@ static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror)
 	return -EAGAIN;
 }
 
-static struct btrfs_fs_info *iotree_fs_info(void *private_data)
-{
-	struct inode *inode = private_data;
-	return btrfs_sb(inode->i_sb);
-}
-
 static void btrfs_check_extent_io_range(void *private_data, const char *caller,
 					u64 start, u64 end)
 {
@@ -10496,9 +10421,9 @@ static void btrfs_check_extent_io_range(void *private_data, const char *caller,
 	}
 }
 
-void btrfs_set_range_writeback(void *private_data, u64 start, u64 end)
+void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 {
-	struct inode *inode = private_data;
+	struct inode *inode = tree->private_data;
 	unsigned long index = start >> PAGE_SHIFT;
 	unsigned long end_index = end >> PAGE_SHIFT;
 	struct page *page;
@@ -10554,10 +10479,7 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
 	/* mandatory callbacks */
 	.submit_bio_hook = btrfs_submit_bio_hook,
 	.readpage_end_io_hook = btrfs_readpage_end_io_hook,
-	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
-	.tree_fs_info = iotree_fs_info,
-	.set_range_writeback = btrfs_set_range_writeback,
 
 	/* optional callbacks */
 	.fill_delalloc = run_delalloc_range,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c2837a32d689..d3a5d2a41e5f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5,23 +5,18 @@
 
 #include <linux/kernel.h>
 #include <linux/bio.h>
-#include <linux/buffer_head.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/fsnotify.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/time.h>
-#include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mount.h>
-#include <linux/mpage.h>
 #include <linux/namei.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
-#include <linux/bit_spinlock.h>
 #include <linux/security.h>
 #include <linux/xattr.h>
 #include <linux/mm.h>
@@ -606,7 +601,7 @@ static noinline int create_subvol(struct inode *dir,
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 
-	ret = btrfs_qgroup_inherit(trans, fs_info, 0, objectid, inherit);
+	ret = btrfs_qgroup_inherit(trans, 0, objectid, inherit);
 	if (ret)
 		goto fail;
 
@@ -616,14 +611,6 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 	}
 
-	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(leaf, leaf->start);
-	btrfs_set_header_generation(leaf, trans->transid);
-	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(leaf, objectid);
-
-	write_extent_buffer_fsid(leaf, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(leaf, fs_info->chunk_tree_uuid);
 	btrfs_mark_buffer_dirty(leaf);
 
 	inode_item = &root_item->inode;
@@ -711,8 +698,7 @@ static noinline int create_subvol(struct inode *dir,
 	ret = btrfs_update_inode(trans, root, dir);
 	BUG_ON(ret);
 
-	ret = btrfs_add_root_ref(trans, fs_info,
-				 objectid, root->root_key.objectid,
+	ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid,
 				 btrfs_ino(BTRFS_I(dir)), index, name, namelen);
 	BUG_ON(ret);
 
@@ -2507,8 +2493,8 @@ out:
 static noinline int btrfs_ioctl_ino_lookup(struct file *file,
 					   void __user *argp)
 {
-	 struct btrfs_ioctl_ino_lookup_args *args;
-	 struct inode *inode;
+	struct btrfs_ioctl_ino_lookup_args *args;
+	struct inode *inode;
 	int ret = 0;
 
 	args = memdup_user(argp, sizeof(*args));
@@ -2941,8 +2927,14 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 		ret = btrfs_defrag_root(root);
 		break;
 	case S_IFREG:
-		if (!(file->f_mode & FMODE_WRITE)) {
-			ret = -EINVAL;
+		/*
+		 * Note that this does not check the file descriptor for write
+		 * access. This prevents defragmenting executables that are
+		 * running and allows defrag on files open in read-only mode.
+		 */
+		if (!capable(CAP_SYS_ADMIN) &&
+		    inode_permission(inode, MAY_WRITE)) {
+			ret = -EPERM;
 			goto out;
 		}
 
@@ -3165,10 +3157,8 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info,
 	di_args->total_bytes = btrfs_device_get_total_bytes(dev);
 	memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
 	if (dev->name) {
-		struct rcu_string *name;
-
-		name = rcu_dereference(dev->name);
-		strncpy(di_args->path, name->str, sizeof(di_args->path) - 1);
+		strncpy(di_args->path, rcu_str_deref(dev->name),
+				sizeof(di_args->path) - 1);
 		di_args->path[sizeof(di_args->path) - 1] = 0;
 	} else {
 		di_args->path[0] = '\0';
@@ -3327,11 +3317,13 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
 		if (pg) {
 			unlock_page(pg);
 			put_page(pg);
+			cmp->src_pages[i] = NULL;
 		}
 		pg = cmp->dst_pages[i];
 		if (pg) {
 			unlock_page(pg);
 			put_page(pg);
+			cmp->dst_pages[i] = NULL;
 		}
 	}
 }
@@ -3577,7 +3569,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
 					      dst, dst_loff, &cmp);
 		if (ret)
-			goto out_unlock;
+			goto out_free;
 
 		loff += BTRFS_MAX_DEDUPE_LEN;
 		dst_loff += BTRFS_MAX_DEDUPE_LEN;
@@ -3587,16 +3579,16 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		ret = btrfs_extent_same_range(src, loff, tail_len, dst,
 					      dst_loff, &cmp);
 
+out_free:
+	kvfree(cmp.src_pages);
+	kvfree(cmp.dst_pages);
+
 out_unlock:
 	if (same_inode)
 		inode_unlock(src);
 	else
 		btrfs_double_inode_unlock(src, dst);
 
-out_free:
-	kvfree(cmp.src_pages);
-	kvfree(cmp.dst_pages);
-
 	return ret;
 }
 
@@ -5116,9 +5108,7 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_quota_ctl_args *sa;
-	struct btrfs_trans_handle *trans = NULL;
 	int ret;
-	int err;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -5134,28 +5124,19 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
 	}
 
 	down_write(&fs_info->subvol_sem);
-	trans = btrfs_start_transaction(fs_info->tree_root, 2);
-	if (IS_ERR(trans)) {
-		ret = PTR_ERR(trans);
-		goto out;
-	}
 
 	switch (sa->cmd) {
 	case BTRFS_QUOTA_CTL_ENABLE:
-		ret = btrfs_quota_enable(trans, fs_info);
+		ret = btrfs_quota_enable(fs_info);
 		break;
 	case BTRFS_QUOTA_CTL_DISABLE:
-		ret = btrfs_quota_disable(trans, fs_info);
+		ret = btrfs_quota_disable(fs_info);
 		break;
 	default:
 		ret = -EINVAL;
 		break;
 	}
 
-	err = btrfs_commit_transaction(trans);
-	if (err && !ret)
-		ret = err;
-out:
 	kfree(sa);
 	up_write(&fs_info->subvol_sem);
 drop_write:
@@ -5193,15 +5174,13 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 	}
 
 	if (sa->assign) {
-		ret = btrfs_add_qgroup_relation(trans, fs_info,
-						sa->src, sa->dst);
+		ret = btrfs_add_qgroup_relation(trans, sa->src, sa->dst);
 	} else {
-		ret = btrfs_del_qgroup_relation(trans, fs_info,
-						sa->src, sa->dst);
+		ret = btrfs_del_qgroup_relation(trans, sa->src, sa->dst);
 	}
 
 	/* update qgroup status and info */
-	err = btrfs_run_qgroups(trans, fs_info);
+	err = btrfs_run_qgroups(trans);
 	if (err < 0)
 		btrfs_handle_fs_error(fs_info, err,
 				      "failed to update qgroup status and info");
@@ -5219,7 +5198,6 @@ drop_write:
 static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ioctl_qgroup_create_args *sa;
 	struct btrfs_trans_handle *trans;
@@ -5251,9 +5229,9 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 	}
 
 	if (sa->create) {
-		ret = btrfs_create_qgroup(trans, fs_info, sa->qgroupid);
+		ret = btrfs_create_qgroup(trans, sa->qgroupid);
 	} else {
-		ret = btrfs_remove_qgroup(trans, fs_info, sa->qgroupid);
+		ret = btrfs_remove_qgroup(trans, sa->qgroupid);
 	}
 
 	err = btrfs_end_transaction(trans);
@@ -5270,7 +5248,6 @@ drop_write:
 static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ioctl_qgroup_limit_args *sa;
 	struct btrfs_trans_handle *trans;
@@ -5303,7 +5280,7 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 		qgroupid = root->root_key.objectid;
 	}
 
-	ret = btrfs_limit_qgroup(trans, fs_info, qgroupid, &sa->lim);
+	ret = btrfs_limit_qgroup(trans, qgroupid, &sa->lim);
 
 	err = btrfs_end_transaction(trans);
 	if (err && !ret)
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 2e1a1694a33d..0c4ef208b8b9 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -6,7 +6,6 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
-#include <linux/pagevec.h>
 #include "ctree.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
@@ -421,129 +420,6 @@ out:
 	return ret == 0;
 }
 
-/* Needs to either be called under a log transaction or the log_mutex */
-void btrfs_get_logged_extents(struct btrfs_inode *inode,
-			      struct list_head *logged_list,
-			      const loff_t start,
-			      const loff_t end)
-{
-	struct btrfs_ordered_inode_tree *tree;
-	struct btrfs_ordered_extent *ordered;
-	struct rb_node *n;
-	struct rb_node *prev;
-
-	tree = &inode->ordered_tree;
-	spin_lock_irq(&tree->lock);
-	n = __tree_search(&tree->tree, end, &prev);
-	if (!n)
-		n = prev;
-	for (; n; n = rb_prev(n)) {
-		ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
-		if (ordered->file_offset > end)
-			continue;
-		if (entry_end(ordered) <= start)
-			break;
-		if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
-			continue;
-		list_add(&ordered->log_list, logged_list);
-		refcount_inc(&ordered->refs);
-	}
-	spin_unlock_irq(&tree->lock);
-}
-
-void btrfs_put_logged_extents(struct list_head *logged_list)
-{
-	struct btrfs_ordered_extent *ordered;
-
-	while (!list_empty(logged_list)) {
-		ordered = list_first_entry(logged_list,
-					   struct btrfs_ordered_extent,
-					   log_list);
-		list_del_init(&ordered->log_list);
-		btrfs_put_ordered_extent(ordered);
-	}
-}
-
-void btrfs_submit_logged_extents(struct list_head *logged_list,
-				 struct btrfs_root *log)
-{
-	int index = log->log_transid % 2;
-
-	spin_lock_irq(&log->log_extents_lock[index]);
-	list_splice_tail(logged_list, &log->logged_list[index]);
-	spin_unlock_irq(&log->log_extents_lock[index]);
-}
-
-void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *log, u64 transid)
-{
-	struct btrfs_ordered_extent *ordered;
-	int index = transid % 2;
-
-	spin_lock_irq(&log->log_extents_lock[index]);
-	while (!list_empty(&log->logged_list[index])) {
-		struct inode *inode;
-		ordered = list_first_entry(&log->logged_list[index],
-					   struct btrfs_ordered_extent,
-					   log_list);
-		list_del_init(&ordered->log_list);
-		inode = ordered->inode;
-		spin_unlock_irq(&log->log_extents_lock[index]);
-
-		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
-			u64 start = ordered->file_offset;
-			u64 end = ordered->file_offset + ordered->len - 1;
-
-			WARN_ON(!inode);
-			filemap_fdatawrite_range(inode->i_mapping, start, end);
-		}
-		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
-						   &ordered->flags));
-
-		/*
-		 * In order to keep us from losing our ordered extent
-		 * information when committing the transaction we have to make
-		 * sure that any logged extents are completed when we go to
-		 * commit the transaction.  To do this we simply increase the
-		 * current transactions pending_ordered counter and decrement it
-		 * when the ordered extent completes.
-		 */
-		if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
-			struct btrfs_ordered_inode_tree *tree;
-
-			tree = &BTRFS_I(inode)->ordered_tree;
-			spin_lock_irq(&tree->lock);
-			if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
-				set_bit(BTRFS_ORDERED_PENDING, &ordered->flags);
-				atomic_inc(&trans->transaction->pending_ordered);
-			}
-			spin_unlock_irq(&tree->lock);
-		}
-		btrfs_put_ordered_extent(ordered);
-		spin_lock_irq(&log->log_extents_lock[index]);
-	}
-	spin_unlock_irq(&log->log_extents_lock[index]);
-}
-
-void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid)
-{
-	struct btrfs_ordered_extent *ordered;
-	int index = transid % 2;
-
-	spin_lock_irq(&log->log_extents_lock[index]);
-	while (!list_empty(&log->logged_list[index])) {
-		ordered = list_first_entry(&log->logged_list[index],
-					   struct btrfs_ordered_extent,
-					   log_list);
-		list_del_init(&ordered->log_list);
-		spin_unlock_irq(&log->log_extents_lock[index]);
-		btrfs_put_ordered_extent(ordered);
-		spin_lock_irq(&log->log_extents_lock[index]);
-	}
-	spin_unlock_irq(&log->log_extents_lock[index]);
-}
-
 /*
  * used to drop a reference on an ordered extent.  This will free
  * the extent if the last reference is dropped
@@ -913,20 +789,6 @@ out:
 	return entry;
 }
 
-bool btrfs_have_ordered_extents_in_range(struct inode *inode,
-					 u64 file_offset,
-					 u64 len)
-{
-	struct btrfs_ordered_extent *oe;
-
-	oe = btrfs_lookup_ordered_range(BTRFS_I(inode), file_offset, len);
-	if (oe) {
-		btrfs_put_ordered_extent(oe);
-		return true;
-	}
-	return false;
-}
-
 /*
  * lookup and return any extent before 'file_offset'.  NULL is returned
  * if none is found
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 3be443fb3001..02d813aaa261 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -54,15 +54,11 @@ struct btrfs_ordered_sum {
 #define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates whether this ordered extent
 				       * has done its due diligence in updating
 				       * the isize. */
-#define BTRFS_ORDERED_LOGGED_CSUM 8 /* We've logged the csums on this ordered
-				       ordered extent */
-#define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */
+#define BTRFS_ORDERED_TRUNCATED 8 /* Set when we have to truncate an extent */
 
-#define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent
-				 * in the logging code. */
-#define BTRFS_ORDERED_PENDING 11 /* We are waiting for this ordered extent to
+#define BTRFS_ORDERED_PENDING 9 /* We are waiting for this ordered extent to
 				  * complete in the current transaction. */
-#define BTRFS_ORDERED_REGULAR 12 /* Regular IO for COW */
+#define BTRFS_ORDERED_REGULAR 10 /* Regular IO for COW */
 
 struct btrfs_ordered_extent {
 	/* logical offset in the file */
@@ -182,9 +178,6 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
 		struct btrfs_inode *inode,
 		u64 file_offset,
 		u64 len);
-bool btrfs_have_ordered_extents_in_range(struct inode *inode,
-					 u64 file_offset,
-					 u64 len);
 int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 				struct btrfs_ordered_extent *ordered);
 int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
@@ -193,16 +186,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 			       const u64 range_start, const u64 range_len);
 u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 			      const u64 range_start, const u64 range_len);
-void btrfs_get_logged_extents(struct btrfs_inode *inode,
-			      struct list_head *logged_list,
-			      const loff_t start,
-			      const loff_t end);
-void btrfs_put_logged_extents(struct list_head *logged_list);
-void btrfs_submit_logged_extents(struct list_head *logged_list,
-				 struct btrfs_root *log);
-void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *log, u64 transid);
-void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid);
 int __init ordered_data_init(void);
 void __cold ordered_data_exit(void);
 
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index a4e11cf04671..df49931ffe92 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -52,17 +52,9 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 	u64 offset;
 	int ref_index = 0;
 
-	if (item_size < sizeof(*ei)) {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		struct btrfs_extent_item_v0 *ei0;
-		BUG_ON(item_size != sizeof(*ei0));
-		ei0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_item_v0);
-		pr_info("\t\textent refs %u\n",
-		       btrfs_extent_refs_v0(eb, ei0));
-		return;
-#else
-		BUG();
-#endif
+	if (unlikely(item_size < sizeof(*ei))) {
+		btrfs_print_v0_err(eb->fs_info);
+		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
 	}
 
 	ei = btrfs_item_ptr(eb, slot, struct btrfs_extent_item);
@@ -133,20 +125,6 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 	WARN_ON(ptr > end);
 }
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static void print_extent_ref_v0(struct extent_buffer *eb, int slot)
-{
-	struct btrfs_extent_ref_v0 *ref0;
-
-	ref0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_ref_v0);
-	printk("\t\textent back ref root %llu gen %llu owner %llu num_refs %lu\n",
-		btrfs_ref_root_v0(eb, ref0),
-		btrfs_ref_generation_v0(eb, ref0),
-		btrfs_ref_objectid_v0(eb, ref0),
-		(unsigned long)btrfs_ref_count_v0(eb, ref0));
-}
-#endif
-
 static void print_uuid_item(struct extent_buffer *l, unsigned long offset,
 			    u32 item_size)
 {
@@ -267,8 +245,8 @@ void btrfs_print_leaf(struct extent_buffer *l)
 					    struct btrfs_file_extent_item);
 			if (btrfs_file_extent_type(l, fi) ==
 			    BTRFS_FILE_EXTENT_INLINE) {
-				pr_info("\t\tinline extent data size %u\n",
-				       btrfs_file_extent_inline_len(l, i, fi));
+				pr_info("\t\tinline extent data size %llu\n",
+				       btrfs_file_extent_ram_bytes(l, fi));
 				break;
 			}
 			pr_info("\t\textent data disk bytenr %llu nr %llu\n",
@@ -280,11 +258,8 @@ void btrfs_print_leaf(struct extent_buffer *l)
 			       btrfs_file_extent_ram_bytes(l, fi));
 			break;
 		case BTRFS_EXTENT_REF_V0_KEY:
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-			print_extent_ref_v0(l, i);
-#else
-			BUG();
-#endif
+			btrfs_print_v0_err(fs_info);
+			btrfs_handle_fs_error(fs_info, -EINVAL, NULL);
 			break;
 		case BTRFS_BLOCK_GROUP_ITEM_KEY:
 			bi = btrfs_item_ptr(l, i,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 1874a6d2e6f5..4353bb69bb86 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -530,11 +530,11 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
 	fs_info->qgroup_ulist = NULL;
 }
 
-static int add_qgroup_relation_item(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *quota_root,
-				    u64 src, u64 dst)
+static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src,
+				    u64 dst)
 {
 	int ret;
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 
@@ -554,11 +554,11 @@ static int add_qgroup_relation_item(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static int del_qgroup_relation_item(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *quota_root,
-				    u64 src, u64 dst)
+static int del_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src,
+				    u64 dst)
 {
 	int ret;
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 
@@ -653,10 +653,10 @@ out:
 	return ret;
 }
 
-static int del_qgroup_item(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *quota_root, u64 qgroupid)
+static int del_qgroup_item(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
 	int ret;
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 
@@ -700,9 +700,9 @@ out:
 }
 
 static int update_qgroup_limit_item(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *root,
 				    struct btrfs_qgroup *qgroup)
 {
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct extent_buffer *l;
@@ -718,7 +718,7 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1);
 	if (ret > 0)
 		ret = -ENOENT;
 
@@ -742,9 +742,10 @@ out:
 }
 
 static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
-				   struct btrfs_root *root,
 				   struct btrfs_qgroup *qgroup)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct extent_buffer *l;
@@ -752,7 +753,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
 	int ret;
 	int slot;
 
-	if (btrfs_is_testing(root->fs_info))
+	if (btrfs_is_testing(fs_info))
 		return 0;
 
 	key.objectid = 0;
@@ -763,7 +764,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1);
 	if (ret > 0)
 		ret = -ENOENT;
 
@@ -786,10 +787,10 @@ out:
 	return ret;
 }
 
-static int update_qgroup_status_item(struct btrfs_trans_handle *trans,
-				     struct btrfs_fs_info *fs_info,
-				    struct btrfs_root *root)
+static int update_qgroup_status_item(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct extent_buffer *l;
@@ -805,7 +806,7 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1);
 	if (ret > 0)
 		ret = -ENOENT;
 
@@ -875,8 +876,7 @@ out:
 	return ret;
 }
 
-int btrfs_quota_enable(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info)
+int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *quota_root;
 	struct btrfs_root *tree_root = fs_info->tree_root;
@@ -886,6 +886,7 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	struct btrfs_key found_key;
 	struct btrfs_qgroup *qgroup = NULL;
+	struct btrfs_trans_handle *trans = NULL;
 	int ret = 0;
 	int slot;
 
@@ -893,9 +894,25 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	if (fs_info->quota_root)
 		goto out;
 
+	/*
+	 * 1 for quota root item
+	 * 1 for BTRFS_QGROUP_STATUS item
+	 *
+	 * Yet we also need 2*n items for a QGROUP_INFO/QGROUP_LIMIT items
+	 * per subvolume. However those are not currently reserved since it
+	 * would be a lot of overkill.
+	 */
+	trans = btrfs_start_transaction(tree_root, 2);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		trans = NULL;
+		goto out;
+	}
+
 	fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
 	if (!fs_info->qgroup_ulist) {
 		ret = -ENOMEM;
+		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
@@ -906,12 +923,14 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 				       BTRFS_QUOTA_TREE_OBJECTID);
 	if (IS_ERR(quota_root)) {
 		ret =  PTR_ERR(quota_root);
+		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_root;
 	}
 
@@ -921,8 +940,10 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_insert_empty_item(trans, quota_root, path, &key,
 				      sizeof(*ptr));
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
+	}
 
 	leaf = path->nodes[0];
 	ptr = btrfs_item_ptr(leaf, path->slots[0],
@@ -944,9 +965,10 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot_for_read(tree_root, &key, path, 1, 0);
 	if (ret > 0)
 		goto out_add_root;
-	if (ret < 0)
+	if (ret < 0) {
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
-
+	}
 
 	while (1) {
 		slot = path->slots[0];
@@ -956,18 +978,23 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 		if (found_key.type == BTRFS_ROOT_REF_KEY) {
 			ret = add_qgroup_item(trans, quota_root,
 					      found_key.offset);
-			if (ret)
+			if (ret) {
+				btrfs_abort_transaction(trans, ret);
 				goto out_free_path;
+			}
 
 			qgroup = add_qgroup_rb(fs_info, found_key.offset);
 			if (IS_ERR(qgroup)) {
 				ret = PTR_ERR(qgroup);
+				btrfs_abort_transaction(trans, ret);
 				goto out_free_path;
 			}
 		}
 		ret = btrfs_next_item(tree_root, path);
-		if (ret < 0)
+		if (ret < 0) {
+			btrfs_abort_transaction(trans, ret);
 			goto out_free_path;
+		}
 		if (ret)
 			break;
 	}
@@ -975,18 +1002,28 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 out_add_root:
 	btrfs_release_path(path);
 	ret = add_qgroup_item(trans, quota_root, BTRFS_FS_TREE_OBJECTID);
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
+	}
 
 	qgroup = add_qgroup_rb(fs_info, BTRFS_FS_TREE_OBJECTID);
 	if (IS_ERR(qgroup)) {
 		ret = PTR_ERR(qgroup);
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
 	}
 	spin_lock(&fs_info->qgroup_lock);
 	fs_info->quota_root = quota_root;
 	set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 	spin_unlock(&fs_info->qgroup_lock);
+
+	ret = btrfs_commit_transaction(trans);
+	if (ret) {
+		trans = NULL;
+		goto out_free_path;
+	}
+
 	ret = qgroup_rescan_init(fs_info, 0, 1);
 	if (!ret) {
 	        qgroup_rescan_zero_tracking(fs_info);
@@ -1006,20 +1043,35 @@ out:
 	if (ret) {
 		ulist_free(fs_info->qgroup_ulist);
 		fs_info->qgroup_ulist = NULL;
+		if (trans)
+			btrfs_end_transaction(trans);
 	}
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;
 }
 
-int btrfs_quota_disable(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info)
+int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *quota_root;
+	struct btrfs_trans_handle *trans = NULL;
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	if (!fs_info->quota_root)
 		goto out;
+
+	/*
+	 * 1 For the root item
+	 *
+	 * We should also reserve enough items for the quota tree deletion in
+	 * btrfs_clean_quota_tree but this is not done.
+	 */
+	trans = btrfs_start_transaction(fs_info->tree_root, 1);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out;
+	}
+
 	clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 	btrfs_qgroup_wait_for_completion(fs_info, false);
 	spin_lock(&fs_info->qgroup_lock);
@@ -1031,12 +1083,16 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 	btrfs_free_qgroup_config(fs_info);
 
 	ret = btrfs_clean_quota_tree(trans, quota_root);
-	if (ret)
-		goto out;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto end_trans;
+	}
 
-	ret = btrfs_del_root(trans, fs_info, &quota_root->root_key);
-	if (ret)
-		goto out;
+	ret = btrfs_del_root(trans, &quota_root->root_key);
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto end_trans;
+	}
 
 	list_del(&quota_root->dirty_list);
 
@@ -1048,6 +1104,9 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 	free_extent_buffer(quota_root->node);
 	free_extent_buffer(quota_root->commit_root);
 	kfree(quota_root);
+
+end_trans:
+	ret = btrfs_end_transaction(trans);
 out:
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;
@@ -1177,9 +1236,10 @@ out:
 	return ret;
 }
 
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *parent;
 	struct btrfs_qgroup *member;
@@ -1216,13 +1276,13 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	ret = add_qgroup_relation_item(trans, quota_root, src, dst);
+	ret = add_qgroup_relation_item(trans, src, dst);
 	if (ret)
 		goto out;
 
-	ret = add_qgroup_relation_item(trans, quota_root, dst, src);
+	ret = add_qgroup_relation_item(trans, dst, src);
 	if (ret) {
-		del_qgroup_relation_item(trans, quota_root, src, dst);
+		del_qgroup_relation_item(trans, src, dst);
 		goto out;
 	}
 
@@ -1240,9 +1300,10 @@ out:
 	return ret;
 }
 
-static int __del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
+static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+				 u64 dst)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *parent;
 	struct btrfs_qgroup *member;
@@ -1276,8 +1337,8 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans,
 	ret = -ENOENT;
 	goto out;
 exist:
-	ret = del_qgroup_relation_item(trans, quota_root, src, dst);
-	err = del_qgroup_relation_item(trans, quota_root, dst, src);
+	ret = del_qgroup_relation_item(trans, src, dst);
+	err = del_qgroup_relation_item(trans, dst, src);
 	if (err && !ret)
 		ret = err;
 
@@ -1290,21 +1351,22 @@ out:
 	return ret;
 }
 
-int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
+int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
-	ret = __del_qgroup_relation(trans, fs_info, src, dst);
+	ret = __del_qgroup_relation(trans, src, dst);
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 
 	return ret;
 }
 
-int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid)
+int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	int ret = 0;
@@ -1336,9 +1398,9 @@ out:
 	return ret;
 }
 
-int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid)
+int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_qgroup_list *list;
@@ -1362,16 +1424,15 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 	}
-	ret = del_qgroup_item(trans, quota_root, qgroupid);
+	ret = del_qgroup_item(trans, qgroupid);
 	if (ret && ret != -ENOENT)
 		goto out;
 
 	while (!list_empty(&qgroup->groups)) {
 		list = list_first_entry(&qgroup->groups,
 					struct btrfs_qgroup_list, next_group);
-		ret = __del_qgroup_relation(trans, fs_info,
-					   qgroupid,
-					   list->group->qgroupid);
+		ret = __del_qgroup_relation(trans, qgroupid,
+					    list->group->qgroupid);
 		if (ret)
 			goto out;
 	}
@@ -1384,10 +1445,10 @@ out:
 	return ret;
 }
 
-int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 qgroupid,
+int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	int ret = 0;
@@ -1451,7 +1512,7 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
 
 	spin_unlock(&fs_info->qgroup_lock);
 
-	ret = update_qgroup_limit_item(trans, quota_root, qgroup);
+	ret = update_qgroup_limit_item(trans, qgroup);
 	if (ret) {
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 		btrfs_info(fs_info, "unable to update quota limit for %llu",
@@ -1519,10 +1580,10 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
-		struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
-		gfp_t gfp_flag)
+int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+			      u64 num_bytes, gfp_t gfp_flag)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_qgroup_extent_record *record;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int ret;
@@ -1530,8 +1591,6 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)
 	    || bytenr == 0 || num_bytes == 0)
 		return 0;
-	if (WARN_ON(trans == NULL))
-		return -EINVAL;
 	record = kmalloc(sizeof(*record), gfp_flag);
 	if (!record)
 		return -ENOMEM;
@@ -1552,9 +1611,9 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
 }
 
 int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct extent_buffer *eb)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int nr = btrfs_header_nritems(eb);
 	int i, extent_type, ret;
 	struct btrfs_key key;
@@ -1584,8 +1643,8 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
 
 		num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
 
-		ret = btrfs_qgroup_trace_extent(trans, fs_info, bytenr,
-						num_bytes, GFP_NOFS);
+		ret = btrfs_qgroup_trace_extent(trans, bytenr, num_bytes,
+						GFP_NOFS);
 		if (ret)
 			return ret;
 	}
@@ -1655,11 +1714,10 @@ static int adjust_slots_upwards(struct btrfs_path *path, int root_level)
 }
 
 int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root,
 			       struct extent_buffer *root_eb,
 			       u64 root_gen, int root_level)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret = 0;
 	int level;
 	struct extent_buffer *eb = root_eb;
@@ -1678,7 +1736,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 	}
 
 	if (root_level == 0) {
-		ret = btrfs_qgroup_trace_leaf_items(trans, fs_info, root_eb);
+		ret = btrfs_qgroup_trace_leaf_items(trans, root_eb);
 		goto out;
 	}
 
@@ -1736,8 +1794,7 @@ walk_down:
 			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 			path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
 
-			ret = btrfs_qgroup_trace_extent(trans, fs_info,
-							child_bytenr,
+			ret = btrfs_qgroup_trace_extent(trans, child_bytenr,
 							fs_info->nodesize,
 							GFP_NOFS);
 			if (ret)
@@ -1745,8 +1802,8 @@ walk_down:
 		}
 
 		if (level == 0) {
-			ret = btrfs_qgroup_trace_leaf_items(trans,fs_info,
-							   path->nodes[level]);
+			ret = btrfs_qgroup_trace_leaf_items(trans,
+							    path->nodes[level]);
 			if (ret)
 				goto out;
 
@@ -1981,12 +2038,11 @@ static int maybe_fs_roots(struct ulist *roots)
 	return is_fstree(unode->val);
 }
 
-int
-btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
-			    u64 bytenr, u64 num_bytes,
-			    struct ulist *old_roots, struct ulist *new_roots)
+int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+				u64 num_bytes, struct ulist *old_roots,
+				struct ulist *new_roots)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct ulist *qgroups = NULL;
 	struct ulist *tmp = NULL;
 	u64 seq;
@@ -2116,9 +2172,10 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 				ulist_del(record->old_roots, qgroup_to_skip,
 					  0);
 			}
-			ret = btrfs_qgroup_account_extent(trans, fs_info,
-					record->bytenr, record->num_bytes,
-					record->old_roots, new_roots);
+			ret = btrfs_qgroup_account_extent(trans, record->bytenr,
+							  record->num_bytes,
+							  record->old_roots,
+							  new_roots);
 			record->old_roots = NULL;
 			new_roots = NULL;
 		}
@@ -2136,9 +2193,9 @@ cleanup:
 /*
  * called from commit_transaction. Writes all changed qgroups to disk.
  */
-int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info)
+int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root = fs_info->quota_root;
 	int ret = 0;
 
@@ -2152,11 +2209,11 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 					  struct btrfs_qgroup, dirty);
 		list_del_init(&qgroup->dirty);
 		spin_unlock(&fs_info->qgroup_lock);
-		ret = update_qgroup_info_item(trans, quota_root, qgroup);
+		ret = update_qgroup_info_item(trans, qgroup);
 		if (ret)
 			fs_info->qgroup_flags |=
 					BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
-		ret = update_qgroup_limit_item(trans, quota_root, qgroup);
+		ret = update_qgroup_limit_item(trans, qgroup);
 		if (ret)
 			fs_info->qgroup_flags |=
 					BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
@@ -2168,7 +2225,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
 	spin_unlock(&fs_info->qgroup_lock);
 
-	ret = update_qgroup_status_item(trans, fs_info, quota_root);
+	ret = update_qgroup_status_item(trans);
 	if (ret)
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 
@@ -2181,13 +2238,13 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
  * cause a transaction abort so we take extra care here to only error
  * when a readonly fs is a reasonable outcome.
  */
-int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
-			 struct btrfs_qgroup_inherit *inherit)
+int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
+			 u64 objectid, struct btrfs_qgroup_inherit *inherit)
 {
 	int ret = 0;
 	int i;
 	u64 *i_qgroups;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_qgroup *srcgroup;
 	struct btrfs_qgroup *dstgroup;
@@ -2229,22 +2286,6 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	if (srcid) {
-		struct btrfs_root *srcroot;
-		struct btrfs_key srckey;
-
-		srckey.objectid = srcid;
-		srckey.type = BTRFS_ROOT_ITEM_KEY;
-		srckey.offset = (u64)-1;
-		srcroot = btrfs_read_fs_root_no_name(fs_info, &srckey);
-		if (IS_ERR(srcroot)) {
-			ret = PTR_ERR(srcroot);
-			goto out;
-		}
-
-		level_size = fs_info->nodesize;
-	}
-
 	/*
 	 * add qgroup to all inherited groups
 	 */
@@ -2253,12 +2294,12 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		for (i = 0; i < inherit->num_qgroups; ++i, ++i_qgroups) {
 			if (*i_qgroups == 0)
 				continue;
-			ret = add_qgroup_relation_item(trans, quota_root,
-						       objectid, *i_qgroups);
+			ret = add_qgroup_relation_item(trans, objectid,
+						       *i_qgroups);
 			if (ret && ret != -EEXIST)
 				goto out;
-			ret = add_qgroup_relation_item(trans, quota_root,
-						       *i_qgroups, objectid);
+			ret = add_qgroup_relation_item(trans, *i_qgroups,
+						       objectid);
 			if (ret && ret != -EEXIST)
 				goto out;
 		}
@@ -2281,7 +2322,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		dstgroup->rsv_rfer = inherit->lim.rsv_rfer;
 		dstgroup->rsv_excl = inherit->lim.rsv_excl;
 
-		ret = update_qgroup_limit_item(trans, quota_root, dstgroup);
+		ret = update_qgroup_limit_item(trans, dstgroup);
 		if (ret) {
 			fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 			btrfs_info(fs_info,
@@ -2301,6 +2342,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		 * our counts don't go crazy, so at this point the only
 		 * difference between the two roots should be the root node.
 		 */
+		level_size = fs_info->nodesize;
 		dstgroup->rfer = srcgroup->rfer;
 		dstgroup->rfer_cmpr = srcgroup->rfer_cmpr;
 		dstgroup->excl = level_size;
@@ -2598,10 +2640,10 @@ static bool is_last_leaf(struct btrfs_path *path)
  * returns < 0 on error, 0 when more leafs are to be scanned.
  * returns 1 when done.
  */
-static int
-qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
-		   struct btrfs_trans_handle *trans)
+static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans,
+			      struct btrfs_path *path)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_key found;
 	struct extent_buffer *scratch_leaf = NULL;
 	struct ulist *roots = NULL;
@@ -2669,8 +2711,8 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 		if (ret < 0)
 			goto out;
 		/* For rescan, just pass old_roots as NULL */
-		ret = btrfs_qgroup_account_extent(trans, fs_info,
-				found.objectid, num_bytes, NULL, roots);
+		ret = btrfs_qgroup_account_extent(trans, found.objectid,
+						  num_bytes, NULL, roots);
 		if (ret < 0)
 			goto out;
 	}
@@ -2680,8 +2722,10 @@ out:
 		free_extent_buffer(scratch_leaf);
 	}
 
-	if (done && !ret)
+	if (done && !ret) {
 		ret = 1;
+		fs_info->qgroup_rescan_progress.objectid = (u64)-1;
+	}
 	return ret;
 }
 
@@ -2714,7 +2758,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 		if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
 			err = -EINTR;
 		} else {
-			err = qgroup_rescan_leaf(fs_info, path, trans);
+			err = qgroup_rescan_leaf(trans, path);
 		}
 		if (err > 0)
 			btrfs_commit_transaction(trans);
@@ -2749,7 +2793,7 @@ out:
 			  err);
 		goto done;
 	}
-	ret = update_qgroup_status_item(trans, fs_info, fs_info->quota_root);
+	ret = update_qgroup_status_item(trans);
 	if (ret < 0) {
 		err = ret;
 		btrfs_err(fs_info, "fail to update qgroup status: %d", err);
@@ -2784,13 +2828,20 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 
 	if (!init_flags) {
 		/* we're resuming qgroup rescan at mount time */
-		if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN))
+		if (!(fs_info->qgroup_flags &
+		      BTRFS_QGROUP_STATUS_FLAG_RESCAN)) {
 			btrfs_warn(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-		else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
+			ret = -EINVAL;
+		} else if (!(fs_info->qgroup_flags &
+			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
 			btrfs_warn(fs_info,
 			"qgroup rescan init failed, qgroup rescan is not queued");
-		return -EINVAL;
+			ret = -EINVAL;
+		}
+
+		if (ret)
+			return ret;
 	}
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index d60dd06445ce..54b8bb282c0e 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -141,24 +141,19 @@ struct btrfs_qgroup {
 #define QGROUP_RELEASE		(1<<1)
 #define QGROUP_FREE		(1<<2)
 
-int btrfs_quota_enable(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info);
-int btrfs_quota_disable(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info);
+int btrfs_quota_enable(struct btrfs_fs_info *fs_info);
+int btrfs_quota_disable(struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
 void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
 				     bool interruptible);
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
-int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
-int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid);
-int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 qgroupid);
-int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 qgroupid,
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst);
+int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst);
+int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
+int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
+int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit);
 int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);
 void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
@@ -217,9 +212,8 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
  * Return <0 for error, like memory allocation failure or invalid parameter
  * (NULL trans)
  */
-int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
-		struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
-		gfp_t gfp_flag);
+int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+			      u64 num_bytes, gfp_t gfp_flag);
 
 /*
  * Inform qgroup to trace all leaf items of data
@@ -228,7 +222,6 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
  * Return <0 for error(ENOMEM)
  */
 int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct extent_buffer *eb);
 /*
  * Inform qgroup to trace a whole subtree, including all its child tree
@@ -241,20 +234,15 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
  * Return <0 for error(ENOMEM or tree search error)
  */
 int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root,
 			       struct extent_buffer *root_eb,
 			       u64 root_gen, int root_level);
-int
-btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
-			    u64 bytenr, u64 num_bytes,
-			    struct ulist *old_roots, struct ulist *new_roots);
+int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+				u64 num_bytes, struct ulist *old_roots,
+				struct ulist *new_roots);
 int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans);
-int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
-			 struct btrfs_qgroup_inherit *inherit);
+int btrfs_run_qgroups(struct btrfs_trans_handle *trans);
+int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
+			 u64 objectid, struct btrfs_qgroup_inherit *inherit);
 void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 			       u64 ref_root, u64 num_bytes,
 			       enum btrfs_qgroup_rsv_type type);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 5e4ad134b9ad..df41d7049936 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -5,32 +5,19 @@
  */
 
 #include <linux/sched.h>
-#include <linux/wait.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
-#include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/random.h>
-#include <linux/iocontext.h>
-#include <linux/capability.h>
-#include <linux/ratelimit.h>
-#include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/hash.h>
 #include <linux/list_sort.h>
 #include <linux/raid/xor.h>
 #include <linux/mm.h>
-#include <asm/div64.h>
 #include "ctree.h"
-#include "extent_map.h"
 #include "disk-io.h"
-#include "transaction.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "raid56.h"
 #include "async-thread.h"
-#include "check-integrity.h"
-#include "rcu-string.h"
 
 /* set when additional merges to this rbio are not allowed */
 #define RBIO_RMW_LOCKED_BIT	1
@@ -175,8 +162,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
 static noinline void finish_rmw(struct btrfs_raid_bio *rbio);
 static void rmw_work(struct btrfs_work *work);
 static void read_rebuild_work(struct btrfs_work *work);
-static void async_rmw_stripe(struct btrfs_raid_bio *rbio);
-static void async_read_rebuild(struct btrfs_raid_bio *rbio);
 static int fail_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio);
 static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed);
 static void __free_raid_bio(struct btrfs_raid_bio *rbio);
@@ -185,7 +170,13 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio);
 
 static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 					 int need_check);
-static void async_scrub_parity(struct btrfs_raid_bio *rbio);
+static void scrub_parity_work(struct btrfs_work *work);
+
+static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func)
+{
+	btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL);
+	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
+}
 
 /*
  * the stripe hash table is used for locking, and to collect
@@ -260,7 +251,7 @@ static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
 		s = kmap(rbio->bio_pages[i]);
 		d = kmap(rbio->stripe_pages[i]);
 
-		memcpy(d, s, PAGE_SIZE);
+		copy_page(d, s);
 
 		kunmap(rbio->bio_pages[i]);
 		kunmap(rbio->stripe_pages[i]);
@@ -516,32 +507,21 @@ static void run_xor(void **pages, int src_cnt, ssize_t len)
 }
 
 /*
- * returns true if the bio list inside this rbio
- * covers an entire stripe (no rmw required).
- * Must be called with the bio list lock held, or
- * at a time when you know it is impossible to add
- * new bios into the list
+ * Returns true if the bio list inside this rbio covers an entire stripe (no
+ * rmw required).
  */
-static int __rbio_is_full(struct btrfs_raid_bio *rbio)
+static int rbio_is_full(struct btrfs_raid_bio *rbio)
 {
+	unsigned long flags;
 	unsigned long size = rbio->bio_list_bytes;
 	int ret = 1;
 
+	spin_lock_irqsave(&rbio->bio_list_lock, flags);
 	if (size != rbio->nr_data * rbio->stripe_len)
 		ret = 0;
-
 	BUG_ON(size > rbio->nr_data * rbio->stripe_len);
-	return ret;
-}
-
-static int rbio_is_full(struct btrfs_raid_bio *rbio)
-{
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&rbio->bio_list_lock, flags);
-	ret = __rbio_is_full(rbio);
 	spin_unlock_irqrestore(&rbio->bio_list_lock, flags);
+
 	return ret;
 }
 
@@ -812,16 +792,16 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
 			spin_unlock_irqrestore(&h->lock, flags);
 
 			if (next->operation == BTRFS_RBIO_READ_REBUILD)
-				async_read_rebuild(next);
+				start_async_work(next, read_rebuild_work);
 			else if (next->operation == BTRFS_RBIO_REBUILD_MISSING) {
 				steal_rbio(rbio, next);
-				async_read_rebuild(next);
+				start_async_work(next, read_rebuild_work);
 			} else if (next->operation == BTRFS_RBIO_WRITE) {
 				steal_rbio(rbio, next);
-				async_rmw_stripe(next);
+				start_async_work(next, rmw_work);
 			} else if (next->operation == BTRFS_RBIO_PARITY_SCRUB) {
 				steal_rbio(rbio, next);
-				async_scrub_parity(next);
+				start_async_work(next, scrub_parity_work);
 			}
 
 			goto done_nolock;
@@ -1275,7 +1255,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 						pointers);
 		} else {
 			/* raid5 */
-			memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
+			copy_page(pointers[nr_data], pointers[0]);
 			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
 		}
 
@@ -1343,7 +1323,7 @@ write_data:
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 
 		submit_bio(bio);
 	}
@@ -1508,20 +1488,6 @@ cleanup:
 	rbio_orig_end_io(rbio, BLK_STS_IOERR);
 }
 
-static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
-{
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper, rmw_work, NULL, NULL);
-	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
-}
-
-static void async_read_rebuild(struct btrfs_raid_bio *rbio)
-{
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
-			read_rebuild_work, NULL, NULL);
-
-	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
-}
-
 /*
  * the stripe must be locked by the caller.  It will
  * unlock after all the writes are done
@@ -1599,7 +1565,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_rmw_end_io;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -1652,7 +1618,7 @@ static int partial_stripe_write(struct btrfs_raid_bio *rbio)
 
 	ret = lock_stripe_add(rbio);
 	if (ret == 0)
-		async_rmw_stripe(rbio);
+		start_async_work(rbio, rmw_work);
 	return 0;
 }
 
@@ -1720,8 +1686,11 @@ static void run_plug(struct btrfs_plug_cb *plug)
 		list_del_init(&cur->plug_list);
 
 		if (rbio_is_full(cur)) {
+			int ret;
+
 			/* we have a full stripe, send it down */
-			full_stripe_write(cur);
+			ret = full_stripe_write(cur);
+			BUG_ON(ret);
 			continue;
 		}
 		if (last) {
@@ -1941,9 +1910,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 			BUG_ON(failb != -1);
 pstripe:
 			/* Copy parity block into failed block to start with */
-			memcpy(pointers[faila],
-			       pointers[rbio->nr_data],
-			       PAGE_SIZE);
+			copy_page(pointers[faila], pointers[rbio->nr_data]);
 
 			/* rearrange the pointer array */
 			p = pointers[faila];
@@ -2145,7 +2112,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_recover_end_io;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -2448,7 +2415,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 						pointers);
 		} else {
 			/* raid5 */
-			memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
+			copy_page(pointers[nr_data], pointers[0]);
 			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
 		}
 
@@ -2456,7 +2423,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 		p = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
 		parity = kmap(p);
 		if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE))
-			memcpy(parity, pointers[rbio->scrubp], PAGE_SIZE);
+			copy_page(parity, pointers[rbio->scrubp]);
 		else
 			/* Parity is right, needn't writeback */
 			bitmap_clear(rbio->dbitmap, pagenr, 1);
@@ -2517,7 +2484,7 @@ submit_write:
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 
 		submit_bio(bio);
 	}
@@ -2699,7 +2666,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid56_parity_scrub_end_io;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -2728,18 +2695,10 @@ static void scrub_parity_work(struct btrfs_work *work)
 	raid56_parity_scrub_stripe(rbio);
 }
 
-static void async_scrub_parity(struct btrfs_raid_bio *rbio)
-{
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
-			scrub_parity_work, NULL, NULL);
-
-	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
-}
-
 void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio)
 {
 	if (!lock_stripe_add(rbio))
-		async_scrub_parity(rbio);
+		start_async_work(rbio, scrub_parity_work);
 }
 
 /* The following code is used for dev replace of a missing RAID 5/6 device. */
@@ -2781,5 +2740,5 @@ raid56_alloc_missing_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
 void raid56_submit_missing_rbio(struct btrfs_raid_bio *rbio)
 {
 	if (!lock_stripe_add(rbio))
-		async_read_rebuild(rbio);
+		start_async_work(rbio, read_rebuild_work);
 }
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 40f1bcef394d..dec14b739b10 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -7,7 +7,6 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
-#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 #include "ctree.h"
@@ -355,7 +354,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 		dev = bbio->stripes[nzones].dev;
 
 		/* cannot read ahead on missing device. */
-		 if (!dev->bdev)
+		if (!dev->bdev)
 			continue;
 
 		zone = reada_find_zone(dev, logical, bbio);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 879b76fa881a..8783a1776540 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -586,29 +586,6 @@ static struct btrfs_root *read_fs_root(struct btrfs_fs_info *fs_info,
 	return btrfs_get_fs_root(fs_info, &key, false);
 }
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static noinline_for_stack
-struct btrfs_root *find_tree_root(struct reloc_control *rc,
-				  struct extent_buffer *leaf,
-				  struct btrfs_extent_ref_v0 *ref0)
-{
-	struct btrfs_root *root;
-	u64 root_objectid = btrfs_ref_root_v0(leaf, ref0);
-	u64 generation = btrfs_ref_generation_v0(leaf, ref0);
-
-	BUG_ON(root_objectid == BTRFS_TREE_RELOC_OBJECTID);
-
-	root = read_fs_root(rc->extent_root->fs_info, root_objectid);
-	BUG_ON(IS_ERR(root));
-
-	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
-	    generation != btrfs_root_generation(&root->root_item))
-		return NULL;
-
-	return root;
-}
-#endif
-
 static noinline_for_stack
 int find_inline_backref(struct extent_buffer *leaf, int slot,
 			unsigned long *ptr, unsigned long *end)
@@ -621,12 +598,11 @@ int find_inline_backref(struct extent_buffer *leaf, int slot,
 	btrfs_item_key_to_cpu(leaf, &key, slot);
 
 	item_size = btrfs_item_size_nr(leaf, slot);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
 	if (item_size < sizeof(*ei)) {
-		WARN_ON(item_size != sizeof(struct btrfs_extent_item_v0));
+		btrfs_print_v0_err(leaf->fs_info);
+		btrfs_handle_fs_error(leaf->fs_info, -EINVAL, NULL);
 		return 1;
 	}
-#endif
 	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
 	WARN_ON(!(btrfs_extent_flags(leaf, ei) &
 		  BTRFS_EXTENT_FLAG_TREE_BLOCK));
@@ -792,7 +768,7 @@ again:
 			type = btrfs_get_extent_inline_ref_type(eb, iref,
 							BTRFS_REF_TYPE_BLOCK);
 			if (type == BTRFS_REF_TYPE_INVALID) {
-				err = -EINVAL;
+				err = -EUCLEAN;
 				goto out;
 			}
 			key.type = type;
@@ -811,29 +787,7 @@ again:
 			goto next;
 		}
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY ||
-		    key.type == BTRFS_EXTENT_REF_V0_KEY) {
-			if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
-				struct btrfs_extent_ref_v0 *ref0;
-				ref0 = btrfs_item_ptr(eb, path1->slots[0],
-						struct btrfs_extent_ref_v0);
-				if (key.objectid == key.offset) {
-					root = find_tree_root(rc, eb, ref0);
-					if (root && !should_ignore_root(root))
-						cur->root = root;
-					else
-						list_add(&cur->list, &useless);
-					break;
-				}
-				if (is_cowonly_root(btrfs_ref_root_v0(eb,
-								      ref0)))
-					cur->cowonly = 1;
-			}
-#else
-		ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
-#endif
 			if (key.objectid == key.offset) {
 				/*
 				 * only root blocks of reloc trees use
@@ -876,6 +830,12 @@ again:
 			edge->node[UPPER] = upper;
 
 			goto next;
+		} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
+			err = -EINVAL;
+			btrfs_print_v0_err(rc->extent_root->fs_info);
+			btrfs_handle_fs_error(rc->extent_root->fs_info, err,
+					      NULL);
+			goto out;
 		} else if (key.type != BTRFS_TREE_BLOCK_REF_KEY) {
 			goto next;
 		}
@@ -1321,18 +1281,19 @@ static void __del_reloc_root(struct btrfs_root *root)
 	struct mapping_node *node = NULL;
 	struct reloc_control *rc = fs_info->reloc_ctl;
 
-	spin_lock(&rc->reloc_root_tree.lock);
-	rb_node = tree_search(&rc->reloc_root_tree.rb_root,
-			      root->node->start);
-	if (rb_node) {
-		node = rb_entry(rb_node, struct mapping_node, rb_node);
-		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
+	if (rc) {
+		spin_lock(&rc->reloc_root_tree.lock);
+		rb_node = tree_search(&rc->reloc_root_tree.rb_root,
+				      root->node->start);
+		if (rb_node) {
+			node = rb_entry(rb_node, struct mapping_node, rb_node);
+			rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
+		}
+		spin_unlock(&rc->reloc_root_tree.lock);
+		if (!node)
+			return;
+		BUG_ON((struct btrfs_root *)node->data != root);
 	}
-	spin_unlock(&rc->reloc_root_tree.lock);
-
-	if (!node)
-		return;
-	BUG_ON((struct btrfs_root *)node->data != root);
 
 	spin_lock(&fs_info->trans_lock);
 	list_del_init(&root->root_list);
@@ -1918,13 +1879,12 @@ again:
 		 *    and tree block numbers, if current trans doesn't free
 		 *    data reloc tree inode.
 		 */
-		ret = btrfs_qgroup_trace_subtree(trans, src, parent,
+		ret = btrfs_qgroup_trace_subtree(trans, parent,
 				btrfs_header_generation(parent),
 				btrfs_header_level(parent));
 		if (ret < 0)
 			break;
-		ret = btrfs_qgroup_trace_subtree(trans, dest,
-				path->nodes[level],
+		ret = btrfs_qgroup_trace_subtree(trans, path->nodes[level],
 				btrfs_header_generation(path->nodes[level]),
 				btrfs_header_level(path->nodes[level]));
 		if (ret < 0)
@@ -3333,48 +3293,6 @@ int relocate_data_extent(struct inode *inode, struct btrfs_key *extent_key,
 	return 0;
 }
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static int get_ref_objectid_v0(struct reloc_control *rc,
-			       struct btrfs_path *path,
-			       struct btrfs_key *extent_key,
-			       u64 *ref_objectid, int *path_change)
-{
-	struct btrfs_key key;
-	struct extent_buffer *leaf;
-	struct btrfs_extent_ref_v0 *ref0;
-	int ret;
-	int slot;
-
-	leaf = path->nodes[0];
-	slot = path->slots[0];
-	while (1) {
-		if (slot >= btrfs_header_nritems(leaf)) {
-			ret = btrfs_next_leaf(rc->extent_root, path);
-			if (ret < 0)
-				return ret;
-			BUG_ON(ret > 0);
-			leaf = path->nodes[0];
-			slot = path->slots[0];
-			if (path_change)
-				*path_change = 1;
-		}
-		btrfs_item_key_to_cpu(leaf, &key, slot);
-		if (key.objectid != extent_key->objectid)
-			return -ENOENT;
-
-		if (key.type != BTRFS_EXTENT_REF_V0_KEY) {
-			slot++;
-			continue;
-		}
-		ref0 = btrfs_item_ptr(leaf, slot,
-				struct btrfs_extent_ref_v0);
-		*ref_objectid = btrfs_ref_objectid_v0(leaf, ref0);
-		break;
-	}
-	return 0;
-}
-#endif
-
 /*
  * helper to add a tree block to the list.
  * the major work is getting the generation and level of the block
@@ -3407,23 +3325,12 @@ static int add_tree_block(struct reloc_control *rc,
 			level = (int)extent_key->offset;
 		}
 		generation = btrfs_extent_generation(eb, ei);
+	} else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
+		btrfs_print_v0_err(eb->fs_info);
+		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
+		return -EINVAL;
 	} else {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		u64 ref_owner;
-		int ret;
-
-		BUG_ON(item_size != sizeof(struct btrfs_extent_item_v0));
-		ret = get_ref_objectid_v0(rc, path, extent_key,
-					  &ref_owner, NULL);
-		if (ret < 0)
-			return ret;
-		BUG_ON(ref_owner >= BTRFS_MAX_LEVEL);
-		level = (int)ref_owner;
-		/* FIXME: get real generation */
-		generation = 0;
-#else
 		BUG();
-#endif
 	}
 
 	btrfs_release_path(path);
@@ -3563,11 +3470,8 @@ static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
 	key.offset = 0;
 
 	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
-	if (IS_ERR(inode) || is_bad_inode(inode)) {
-		if (!IS_ERR(inode))
-			iput(inode);
+	if (IS_ERR(inode))
 		return -ENOENT;
-	}
 
 truncate:
 	ret = btrfs_check_trunc_cache_free_space(fs_info,
@@ -3781,12 +3685,7 @@ int add_data_references(struct reloc_control *rc,
 	eb = path->nodes[0];
 	ptr = btrfs_item_ptr_offset(eb, path->slots[0]);
 	end = ptr + btrfs_item_size_nr(eb, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (ptr + sizeof(struct btrfs_extent_item_v0) == end)
-		ptr = end;
-	else
-#endif
-		ptr += sizeof(struct btrfs_extent_item);
+	ptr += sizeof(struct btrfs_extent_item);
 
 	while (ptr < end) {
 		iref = (struct btrfs_extent_inline_ref *)ptr;
@@ -3801,7 +3700,7 @@ int add_data_references(struct reloc_control *rc,
 			ret = find_data_references(rc, extent_key,
 						   eb, dref, blocks);
 		} else {
-			ret = -EINVAL;
+			ret = -EUCLEAN;
 			btrfs_err(rc->extent_root->fs_info,
 		     "extent %llu slot %d has an invalid inline ref type",
 			     eb->start, path->slots[0]);
@@ -3832,13 +3731,7 @@ int add_data_references(struct reloc_control *rc,
 		if (key.objectid != extent_key->objectid)
 			break;
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		if (key.type == BTRFS_SHARED_DATA_REF_KEY ||
-		    key.type == BTRFS_EXTENT_REF_V0_KEY) {
-#else
-		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
-#endif
 			ret = __add_tree_block(rc, key.offset, blocksize,
 					       blocks);
 		} else if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
@@ -3846,6 +3739,10 @@ int add_data_references(struct reloc_control *rc,
 					      struct btrfs_extent_data_ref);
 			ret = find_data_references(rc, extent_key,
 						   eb, dref, blocks);
+		} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
+			btrfs_print_v0_err(eb->fs_info);
+			btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
+			ret = -EINVAL;
 		} else {
 			ret = 0;
 		}
@@ -4084,41 +3981,13 @@ restart:
 			flags = btrfs_extent_flags(path->nodes[0], ei);
 			ret = check_extent_flags(flags);
 			BUG_ON(ret);
-
+		} else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
+			err = -EINVAL;
+			btrfs_print_v0_err(trans->fs_info);
+			btrfs_abort_transaction(trans, err);
+			break;
 		} else {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-			u64 ref_owner;
-			int path_change = 0;
-
-			BUG_ON(item_size !=
-			       sizeof(struct btrfs_extent_item_v0));
-			ret = get_ref_objectid_v0(rc, path, &key, &ref_owner,
-						  &path_change);
-			if (ret < 0) {
-				err = ret;
-				break;
-			}
-			if (ref_owner < BTRFS_FIRST_FREE_OBJECTID)
-				flags = BTRFS_EXTENT_FLAG_TREE_BLOCK;
-			else
-				flags = BTRFS_EXTENT_FLAG_DATA;
-
-			if (path_change) {
-				btrfs_release_path(path);
-
-				path->search_commit_root = 1;
-				path->skip_locking = 1;
-				ret = btrfs_search_slot(NULL, rc->extent_root,
-							&key, path, 0, 0);
-				if (ret < 0) {
-					err = ret;
-					break;
-				}
-				BUG_ON(ret > 0);
-			}
-#else
 			BUG();
-#endif
 		}
 
 		if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
@@ -4169,8 +4038,7 @@ restart:
 		}
 	}
 	if (trans && progress && err == -ENOSPC) {
-		ret = btrfs_force_chunk_alloc(trans, fs_info,
-					      rc->block_group->flags);
+		ret = btrfs_force_chunk_alloc(trans, rc->block_group->flags);
 		if (ret == 1) {
 			err = 0;
 			progress = 0;
@@ -4284,7 +4152,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
-	BUG_ON(IS_ERR(inode) || is_bad_inode(inode));
+	BUG_ON(IS_ERR(inode));
 	BTRFS_I(inode)->index_cnt = group->key.objectid;
 
 	err = btrfs_orphan_add(trans, BTRFS_I(inode));
@@ -4375,7 +4243,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 	rc->block_group = btrfs_lookup_block_group(fs_info, group_start);
 	BUG_ON(!rc->block_group);
 
-	ret = btrfs_inc_block_group_ro(fs_info, rc->block_group);
+	ret = btrfs_inc_block_group_ro(rc->block_group);
 	if (ret) {
 		err = ret;
 		goto out;
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index c451285976ac..65bda0682928 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -320,9 +320,9 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info)
 
 /* drop the root item for 'key' from the tree root */
 int btrfs_del_root(struct btrfs_trans_handle *trans,
-		   struct btrfs_fs_info *fs_info, const struct btrfs_key *key)
+		   const struct btrfs_key *key)
 {
-	struct btrfs_root *root = fs_info->tree_root;
+	struct btrfs_root *root = trans->fs_info->tree_root;
 	struct btrfs_path *path;
 	int ret;
 
@@ -341,13 +341,12 @@ out:
 	return ret;
 }
 
-int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
-		       const char *name, int name_len)
+int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 *sequence, const char *name,
+		       int name_len)
 
 {
-	struct btrfs_root *tree_root = fs_info->tree_root;
+	struct btrfs_root *tree_root = trans->fs_info->tree_root;
 	struct btrfs_path *path;
 	struct btrfs_root_ref *ref;
 	struct extent_buffer *leaf;
@@ -413,12 +412,11 @@ out:
  *
  * Will return 0, -ENOMEM, or anything from the CoW path
  */
-int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 sequence,
-		       const char *name, int name_len)
+int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 sequence, const char *name,
+		       int name_len)
 {
-	struct btrfs_root *tree_root = fs_info->tree_root;
+	struct btrfs_root *tree_root = trans->fs_info->tree_root;
 	struct btrfs_key key;
 	int ret;
 	struct btrfs_path *path;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 572306036477..3be1456b5116 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -188,32 +188,6 @@ struct scrub_ctx {
 	refcount_t              refs;
 };
 
-struct scrub_fixup_nodatasum {
-	struct scrub_ctx	*sctx;
-	struct btrfs_device	*dev;
-	u64			logical;
-	struct btrfs_root	*root;
-	struct btrfs_work	work;
-	int			mirror_num;
-};
-
-struct scrub_nocow_inode {
-	u64			inum;
-	u64			offset;
-	u64			root;
-	struct list_head	list;
-};
-
-struct scrub_copy_nocow_ctx {
-	struct scrub_ctx	*sctx;
-	u64			logical;
-	u64			len;
-	int			mirror_num;
-	u64			physical_for_dev_replace;
-	struct list_head	inodes;
-	struct btrfs_work	work;
-};
-
 struct scrub_warning {
 	struct btrfs_path	*path;
 	u64			extent_item_size;
@@ -232,8 +206,6 @@ struct full_stripe_lock {
 
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
 static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
-static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx);
-static void scrub_pending_trans_workers_dec(struct scrub_ctx *sctx);
 static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
 static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 				     struct scrub_block *sblocks_for_recheck);
@@ -277,13 +249,6 @@ static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
 static void scrub_wr_submit(struct scrub_ctx *sctx);
 static void scrub_wr_bio_end_io(struct bio *bio);
 static void scrub_wr_bio_end_io_worker(struct btrfs_work *work);
-static int write_page_nocow(struct scrub_ctx *sctx,
-			    u64 physical_for_dev_replace, struct page *page);
-static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
-				      struct scrub_copy_nocow_ctx *ctx);
-static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
-			    int mirror_num, u64 physical_for_dev_replace);
-static void copy_nocow_pages_worker(struct btrfs_work *work);
 static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_put_ctx(struct scrub_ctx *sctx);
@@ -555,60 +520,6 @@ out:
 	return ret;
 }
 
-/*
- * used for workers that require transaction commits (i.e., for the
- * NOCOW case)
- */
-static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx)
-{
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-
-	refcount_inc(&sctx->refs);
-	/*
-	 * increment scrubs_running to prevent cancel requests from
-	 * completing as long as a worker is running. we must also
-	 * increment scrubs_paused to prevent deadlocking on pause
-	 * requests used for transactions commits (as the worker uses a
-	 * transaction context). it is safe to regard the worker
-	 * as paused for all matters practical. effectively, we only
-	 * avoid cancellation requests from completing.
-	 */
-	mutex_lock(&fs_info->scrub_lock);
-	atomic_inc(&fs_info->scrubs_running);
-	atomic_inc(&fs_info->scrubs_paused);
-	mutex_unlock(&fs_info->scrub_lock);
-
-	/*
-	 * check if @scrubs_running=@scrubs_paused condition
-	 * inside wait_event() is not an atomic operation.
-	 * which means we may inc/dec @scrub_running/paused
-	 * at any time. Let's wake up @scrub_pause_wait as
-	 * much as we can to let commit transaction blocked less.
-	 */
-	wake_up(&fs_info->scrub_pause_wait);
-
-	atomic_inc(&sctx->workers_pending);
-}
-
-/* used for workers that require transaction commits */
-static void scrub_pending_trans_workers_dec(struct scrub_ctx *sctx)
-{
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-
-	/*
-	 * see scrub_pending_trans_workers_inc() why we're pretending
-	 * to be paused in the scrub counters
-	 */
-	mutex_lock(&fs_info->scrub_lock);
-	atomic_dec(&fs_info->scrubs_running);
-	atomic_dec(&fs_info->scrubs_paused);
-	mutex_unlock(&fs_info->scrub_lock);
-	atomic_dec(&sctx->workers_pending);
-	wake_up(&fs_info->scrub_pause_wait);
-	wake_up(&sctx->list_wait);
-	scrub_put_ctx(sctx);
-}
-
 static void scrub_free_csums(struct scrub_ctx *sctx)
 {
 	while (!list_empty(&sctx->csum_list)) {
@@ -882,194 +793,6 @@ out:
 	btrfs_free_path(path);
 }
 
-static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
-{
-	struct page *page = NULL;
-	unsigned long index;
-	struct scrub_fixup_nodatasum *fixup = fixup_ctx;
-	int ret;
-	int corrected = 0;
-	struct btrfs_key key;
-	struct inode *inode = NULL;
-	struct btrfs_fs_info *fs_info;
-	u64 end = offset + PAGE_SIZE - 1;
-	struct btrfs_root *local_root;
-	int srcu_index;
-
-	key.objectid = root;
-	key.type = BTRFS_ROOT_ITEM_KEY;
-	key.offset = (u64)-1;
-
-	fs_info = fixup->root->fs_info;
-	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
-
-	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-	if (IS_ERR(local_root)) {
-		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-		return PTR_ERR(local_root);
-	}
-
-	key.type = BTRFS_INODE_ITEM_KEY;
-	key.objectid = inum;
-	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
-	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-
-	index = offset >> PAGE_SHIFT;
-
-	page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
-	if (!page) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	if (PageUptodate(page)) {
-		if (PageDirty(page)) {
-			/*
-			 * we need to write the data to the defect sector. the
-			 * data that was in that sector is not in memory,
-			 * because the page was modified. we must not write the
-			 * modified page to that sector.
-			 *
-			 * TODO: what could be done here: wait for the delalloc
-			 *       runner to write out that page (might involve
-			 *       COW) and see whether the sector is still
-			 *       referenced afterwards.
-			 *
-			 * For the meantime, we'll treat this error
-			 * incorrectable, although there is a chance that a
-			 * later scrub will find the bad sector again and that
-			 * there's no dirty page in memory, then.
-			 */
-			ret = -EIO;
-			goto out;
-		}
-		ret = repair_io_failure(fs_info, inum, offset, PAGE_SIZE,
-					fixup->logical, page,
-					offset - page_offset(page),
-					fixup->mirror_num);
-		unlock_page(page);
-		corrected = !ret;
-	} else {
-		/*
-		 * we need to get good data first. the general readpage path
-		 * will call repair_io_failure for us, we just have to make
-		 * sure we read the bad mirror.
-		 */
-		ret = set_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
-					EXTENT_DAMAGED);
-		if (ret) {
-			/* set_extent_bits should give proper error */
-			WARN_ON(ret > 0);
-			if (ret > 0)
-				ret = -EFAULT;
-			goto out;
-		}
-
-		ret = extent_read_full_page(&BTRFS_I(inode)->io_tree, page,
-						btrfs_get_extent,
-						fixup->mirror_num);
-		wait_on_page_locked(page);
-
-		corrected = !test_range_bit(&BTRFS_I(inode)->io_tree, offset,
-						end, EXTENT_DAMAGED, 0, NULL);
-		if (!corrected)
-			clear_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
-						EXTENT_DAMAGED);
-	}
-
-out:
-	if (page)
-		put_page(page);
-
-	iput(inode);
-
-	if (ret < 0)
-		return ret;
-
-	if (ret == 0 && corrected) {
-		/*
-		 * we only need to call readpage for one of the inodes belonging
-		 * to this extent. so make iterate_extent_inodes stop
-		 */
-		return 1;
-	}
-
-	return -EIO;
-}
-
-static void scrub_fixup_nodatasum(struct btrfs_work *work)
-{
-	struct btrfs_fs_info *fs_info;
-	int ret;
-	struct scrub_fixup_nodatasum *fixup;
-	struct scrub_ctx *sctx;
-	struct btrfs_trans_handle *trans = NULL;
-	struct btrfs_path *path;
-	int uncorrectable = 0;
-
-	fixup = container_of(work, struct scrub_fixup_nodatasum, work);
-	sctx = fixup->sctx;
-	fs_info = fixup->root->fs_info;
-
-	path = btrfs_alloc_path();
-	if (!path) {
-		spin_lock(&sctx->stat_lock);
-		++sctx->stat.malloc_errors;
-		spin_unlock(&sctx->stat_lock);
-		uncorrectable = 1;
-		goto out;
-	}
-
-	trans = btrfs_join_transaction(fixup->root);
-	if (IS_ERR(trans)) {
-		uncorrectable = 1;
-		goto out;
-	}
-
-	/*
-	 * the idea is to trigger a regular read through the standard path. we
-	 * read a page from the (failed) logical address by specifying the
-	 * corresponding copynum of the failed sector. thus, that readpage is
-	 * expected to fail.
-	 * that is the point where on-the-fly error correction will kick in
-	 * (once it's finished) and rewrite the failed sector if a good copy
-	 * can be found.
-	 */
-	ret = iterate_inodes_from_logical(fixup->logical, fs_info, path,
-					  scrub_fixup_readpage, fixup, false);
-	if (ret < 0) {
-		uncorrectable = 1;
-		goto out;
-	}
-	WARN_ON(ret != 1);
-
-	spin_lock(&sctx->stat_lock);
-	++sctx->stat.corrected_errors;
-	spin_unlock(&sctx->stat_lock);
-
-out:
-	if (trans && !IS_ERR(trans))
-		btrfs_end_transaction(trans);
-	if (uncorrectable) {
-		spin_lock(&sctx->stat_lock);
-		++sctx->stat.uncorrectable_errors;
-		spin_unlock(&sctx->stat_lock);
-		btrfs_dev_replace_stats_inc(
-			&fs_info->dev_replace.num_uncorrectable_read_errors);
-		btrfs_err_rl_in_rcu(fs_info,
-		    "unable to fixup (nodatasum) error at logical %llu on dev %s",
-			fixup->logical, rcu_str_deref(fixup->dev->name));
-	}
-
-	btrfs_free_path(path);
-	kfree(fixup);
-
-	scrub_pending_trans_workers_dec(sctx);
-}
-
 static inline void scrub_get_recover(struct scrub_recover *recover)
 {
 	refcount_inc(&recover->refs);
@@ -1151,11 +874,6 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 		return ret;
 	}
 
-	if (sctx->is_dev_replace && !is_metadata && !have_csum) {
-		sblocks_for_recheck = NULL;
-		goto nodatasum_case;
-	}
-
 	/*
 	 * read all mirrors one after the other. This includes to
 	 * re-read the extent or metadata block that failed (that was
@@ -1268,36 +986,6 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 		goto out;
 	}
 
-	if (!is_metadata && !have_csum) {
-		struct scrub_fixup_nodatasum *fixup_nodatasum;
-
-		WARN_ON(sctx->is_dev_replace);
-
-nodatasum_case:
-
-		/*
-		 * !is_metadata and !have_csum, this means that the data
-		 * might not be COWed, that it might be modified
-		 * concurrently. The general strategy to work on the
-		 * commit root does not help in the case when COW is not
-		 * used.
-		 */
-		fixup_nodatasum = kzalloc(sizeof(*fixup_nodatasum), GFP_NOFS);
-		if (!fixup_nodatasum)
-			goto did_not_correct_error;
-		fixup_nodatasum->sctx = sctx;
-		fixup_nodatasum->dev = dev;
-		fixup_nodatasum->logical = logical;
-		fixup_nodatasum->root = fs_info->extent_root;
-		fixup_nodatasum->mirror_num = failed_mirror_index + 1;
-		scrub_pending_trans_workers_inc(sctx);
-		btrfs_init_work(&fixup_nodatasum->work, btrfs_scrub_helper,
-				scrub_fixup_nodatasum, NULL, NULL);
-		btrfs_queue_work(fs_info->scrub_workers,
-				 &fixup_nodatasum->work);
-		goto out;
-	}
-
 	/*
 	 * now build and submit the bios for the other mirrors, check
 	 * checksums.
@@ -1865,7 +1553,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 		bio = btrfs_io_bio_alloc(1);
 		bio_set_dev(bio, page_bad->dev->bdev);
 		bio->bi_iter.bi_sector = page_bad->physical >> 9;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 
 		ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
 		if (PAGE_SIZE != ret) {
@@ -1960,7 +1648,7 @@ again:
 		bio->bi_end_io = scrub_wr_bio_end_io;
 		bio_set_dev(bio, sbio->dev->bdev);
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 		sbio->status = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical_for_dev_replace ||
@@ -2360,7 +2048,7 @@ again:
 		bio->bi_end_io = scrub_bio_end_io;
 		bio_set_dev(bio, sbio->dev->bdev);
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 		sbio->status = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical ||
@@ -2799,17 +2487,10 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map,
 			have_csum = scrub_find_csum(sctx, logical, csum);
 			if (have_csum == 0)
 				++sctx->stat.no_csum;
-			if (0 && sctx->is_dev_replace && !have_csum) {
-				ret = copy_nocow_pages(sctx, logical, l,
-						       mirror_num,
-						      physical_for_dev_replace);
-				goto behind_scrub_pages;
-			}
 		}
 		ret = scrub_pages(sctx, logical, l, physical, dev, flags, gen,
 				  mirror_num, have_csum ? csum : NULL, 0,
 				  physical_for_dev_replace);
-behind_scrub_pages:
 		if (ret)
 			return ret;
 		len -= l;
@@ -3862,7 +3543,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 * -> btrfs_scrub_pause()
 		 */
 		scrub_pause_on(fs_info);
-		ret = btrfs_inc_block_group_ro(fs_info, cache);
+		ret = btrfs_inc_block_group_ro(cache);
 		if (!ret && is_dev_replace) {
 			/*
 			 * If we are doing a device replace wait for any tasks
@@ -3981,14 +3662,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
 		    btrfs_block_group_used(&cache->item) == 0) {
 			spin_unlock(&cache->lock);
-			spin_lock(&fs_info->unused_bgs_lock);
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &fs_info->unused_bgs);
-			}
-			spin_unlock(&fs_info->unused_bgs_lock);
+			btrfs_mark_bg_unused(cache);
 		} else {
 			spin_unlock(&cache->lock);
 		}
@@ -4071,10 +3745,6 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 		if (!fs_info->scrub_wr_completion_workers)
 			goto fail_scrub_wr_completion_workers;
 
-		fs_info->scrub_nocow_workers =
-			btrfs_alloc_workqueue(fs_info, "scrubnc", flags, 1, 0);
-		if (!fs_info->scrub_nocow_workers)
-			goto fail_scrub_nocow_workers;
 		fs_info->scrub_parity_workers =
 			btrfs_alloc_workqueue(fs_info, "scrubparity", flags,
 					      max_active, 2);
@@ -4085,8 +3755,6 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 	return 0;
 
 fail_scrub_parity_workers:
-	btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
-fail_scrub_nocow_workers:
 	btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
 fail_scrub_wr_completion_workers:
 	btrfs_destroy_workqueue(fs_info->scrub_workers);
@@ -4099,7 +3767,6 @@ static noinline_for_stack void scrub_workers_put(struct btrfs_fs_info *fs_info)
 	if (--fs_info->scrub_workers_refcnt == 0) {
 		btrfs_destroy_workqueue(fs_info->scrub_workers);
 		btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
-		btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
 		btrfs_destroy_workqueue(fs_info->scrub_parity_workers);
 	}
 	WARN_ON(fs_info->scrub_workers_refcnt < 0);
@@ -4112,7 +3779,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	struct scrub_ctx *sctx;
 	int ret;
 	struct btrfs_device *dev;
-	struct rcu_string *name;
 
 	if (btrfs_fs_closing(fs_info))
 		return -EINVAL;
@@ -4166,11 +3832,8 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	if (!is_dev_replace && !readonly &&
 	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		rcu_read_lock();
-		name = rcu_dereference(dev->name);
-		btrfs_err(fs_info, "scrub: device %s is not writable",
-			  name->str);
-		rcu_read_unlock();
+		btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable",
+				rcu_str_deref(dev->name));
 		return -EROFS;
 	}
 
@@ -4358,330 +4021,3 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
 	*extent_dev = bbio->stripes[0].dev;
 	btrfs_put_bbio(bbio);
 }
-
-static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
-			    int mirror_num, u64 physical_for_dev_replace)
-{
-	struct scrub_copy_nocow_ctx *nocow_ctx;
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-
-	nocow_ctx = kzalloc(sizeof(*nocow_ctx), GFP_NOFS);
-	if (!nocow_ctx) {
-		spin_lock(&sctx->stat_lock);
-		sctx->stat.malloc_errors++;
-		spin_unlock(&sctx->stat_lock);
-		return -ENOMEM;
-	}
-
-	scrub_pending_trans_workers_inc(sctx);
-
-	nocow_ctx->sctx = sctx;
-	nocow_ctx->logical = logical;
-	nocow_ctx->len = len;
-	nocow_ctx->mirror_num = mirror_num;
-	nocow_ctx->physical_for_dev_replace = physical_for_dev_replace;
-	btrfs_init_work(&nocow_ctx->work, btrfs_scrubnc_helper,
-			copy_nocow_pages_worker, NULL, NULL);
-	INIT_LIST_HEAD(&nocow_ctx->inodes);
-	btrfs_queue_work(fs_info->scrub_nocow_workers,
-			 &nocow_ctx->work);
-
-	return 0;
-}
-
-static int record_inode_for_nocow(u64 inum, u64 offset, u64 root, void *ctx)
-{
-	struct scrub_copy_nocow_ctx *nocow_ctx = ctx;
-	struct scrub_nocow_inode *nocow_inode;
-
-	nocow_inode = kzalloc(sizeof(*nocow_inode), GFP_NOFS);
-	if (!nocow_inode)
-		return -ENOMEM;
-	nocow_inode->inum = inum;
-	nocow_inode->offset = offset;
-	nocow_inode->root = root;
-	list_add_tail(&nocow_inode->list, &nocow_ctx->inodes);
-	return 0;
-}
-
-#define COPY_COMPLETE 1
-
-static void copy_nocow_pages_worker(struct btrfs_work *work)
-{
-	struct scrub_copy_nocow_ctx *nocow_ctx =
-		container_of(work, struct scrub_copy_nocow_ctx, work);
-	struct scrub_ctx *sctx = nocow_ctx->sctx;
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-	struct btrfs_root *root = fs_info->extent_root;
-	u64 logical = nocow_ctx->logical;
-	u64 len = nocow_ctx->len;
-	int mirror_num = nocow_ctx->mirror_num;
-	u64 physical_for_dev_replace = nocow_ctx->physical_for_dev_replace;
-	int ret;
-	struct btrfs_trans_handle *trans = NULL;
-	struct btrfs_path *path;
-	int not_written = 0;
-
-	path = btrfs_alloc_path();
-	if (!path) {
-		spin_lock(&sctx->stat_lock);
-		sctx->stat.malloc_errors++;
-		spin_unlock(&sctx->stat_lock);
-		not_written = 1;
-		goto out;
-	}
-
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans)) {
-		not_written = 1;
-		goto out;
-	}
-
-	ret = iterate_inodes_from_logical(logical, fs_info, path,
-			record_inode_for_nocow, nocow_ctx, false);
-	if (ret != 0 && ret != -ENOENT) {
-		btrfs_warn(fs_info,
-			   "iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d",
-			   logical, physical_for_dev_replace, len, mirror_num,
-			   ret);
-		not_written = 1;
-		goto out;
-	}
-
-	btrfs_end_transaction(trans);
-	trans = NULL;
-	while (!list_empty(&nocow_ctx->inodes)) {
-		struct scrub_nocow_inode *entry;
-		entry = list_first_entry(&nocow_ctx->inodes,
-					 struct scrub_nocow_inode,
-					 list);
-		list_del_init(&entry->list);
-		ret = copy_nocow_pages_for_inode(entry->inum, entry->offset,
-						 entry->root, nocow_ctx);
-		kfree(entry);
-		if (ret == COPY_COMPLETE) {
-			ret = 0;
-			break;
-		} else if (ret) {
-			break;
-		}
-	}
-out:
-	while (!list_empty(&nocow_ctx->inodes)) {
-		struct scrub_nocow_inode *entry;
-		entry = list_first_entry(&nocow_ctx->inodes,
-					 struct scrub_nocow_inode,
-					 list);
-		list_del_init(&entry->list);
-		kfree(entry);
-	}
-	if (trans && !IS_ERR(trans))
-		btrfs_end_transaction(trans);
-	if (not_written)
-		btrfs_dev_replace_stats_inc(&fs_info->dev_replace.
-					    num_uncorrectable_read_errors);
-
-	btrfs_free_path(path);
-	kfree(nocow_ctx);
-
-	scrub_pending_trans_workers_dec(sctx);
-}
-
-static int check_extent_to_block(struct btrfs_inode *inode, u64 start, u64 len,
-				 u64 logical)
-{
-	struct extent_state *cached_state = NULL;
-	struct btrfs_ordered_extent *ordered;
-	struct extent_io_tree *io_tree;
-	struct extent_map *em;
-	u64 lockstart = start, lockend = start + len - 1;
-	int ret = 0;
-
-	io_tree = &inode->io_tree;
-
-	lock_extent_bits(io_tree, lockstart, lockend, &cached_state);
-	ordered = btrfs_lookup_ordered_range(inode, lockstart, len);
-	if (ordered) {
-		btrfs_put_ordered_extent(ordered);
-		ret = 1;
-		goto out_unlock;
-	}
-
-	em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
-	if (IS_ERR(em)) {
-		ret = PTR_ERR(em);
-		goto out_unlock;
-	}
-
-	/*
-	 * This extent does not actually cover the logical extent anymore,
-	 * move on to the next inode.
-	 */
-	if (em->block_start > logical ||
-	    em->block_start + em->block_len < logical + len ||
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
-		free_extent_map(em);
-		ret = 1;
-		goto out_unlock;
-	}
-	free_extent_map(em);
-
-out_unlock:
-	unlock_extent_cached(io_tree, lockstart, lockend, &cached_state);
-	return ret;
-}
-
-static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
-				      struct scrub_copy_nocow_ctx *nocow_ctx)
-{
-	struct btrfs_fs_info *fs_info = nocow_ctx->sctx->fs_info;
-	struct btrfs_key key;
-	struct inode *inode;
-	struct page *page;
-	struct btrfs_root *local_root;
-	struct extent_io_tree *io_tree;
-	u64 physical_for_dev_replace;
-	u64 nocow_ctx_logical;
-	u64 len = nocow_ctx->len;
-	unsigned long index;
-	int srcu_index;
-	int ret = 0;
-	int err = 0;
-
-	key.objectid = root;
-	key.type = BTRFS_ROOT_ITEM_KEY;
-	key.offset = (u64)-1;
-
-	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
-
-	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-	if (IS_ERR(local_root)) {
-		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-		return PTR_ERR(local_root);
-	}
-
-	key.type = BTRFS_INODE_ITEM_KEY;
-	key.objectid = inum;
-	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
-	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-
-	/* Avoid truncate/dio/punch hole.. */
-	inode_lock(inode);
-	inode_dio_wait(inode);
-
-	physical_for_dev_replace = nocow_ctx->physical_for_dev_replace;
-	io_tree = &BTRFS_I(inode)->io_tree;
-	nocow_ctx_logical = nocow_ctx->logical;
-
-	ret = check_extent_to_block(BTRFS_I(inode), offset, len,
-			nocow_ctx_logical);
-	if (ret) {
-		ret = ret > 0 ? 0 : ret;
-		goto out;
-	}
-
-	while (len >= PAGE_SIZE) {
-		index = offset >> PAGE_SHIFT;
-again:
-		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
-		if (!page) {
-			btrfs_err(fs_info, "find_or_create_page() failed");
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		if (PageUptodate(page)) {
-			if (PageDirty(page))
-				goto next_page;
-		} else {
-			ClearPageError(page);
-			err = extent_read_full_page(io_tree, page,
-							   btrfs_get_extent,
-							   nocow_ctx->mirror_num);
-			if (err) {
-				ret = err;
-				goto next_page;
-			}
-
-			lock_page(page);
-			/*
-			 * If the page has been remove from the page cache,
-			 * the data on it is meaningless, because it may be
-			 * old one, the new data may be written into the new
-			 * page in the page cache.
-			 */
-			if (page->mapping != inode->i_mapping) {
-				unlock_page(page);
-				put_page(page);
-				goto again;
-			}
-			if (!PageUptodate(page)) {
-				ret = -EIO;
-				goto next_page;
-			}
-		}
-
-		ret = check_extent_to_block(BTRFS_I(inode), offset, len,
-					    nocow_ctx_logical);
-		if (ret) {
-			ret = ret > 0 ? 0 : ret;
-			goto next_page;
-		}
-
-		err = write_page_nocow(nocow_ctx->sctx,
-				       physical_for_dev_replace, page);
-		if (err)
-			ret = err;
-next_page:
-		unlock_page(page);
-		put_page(page);
-
-		if (ret)
-			break;
-
-		offset += PAGE_SIZE;
-		physical_for_dev_replace += PAGE_SIZE;
-		nocow_ctx_logical += PAGE_SIZE;
-		len -= PAGE_SIZE;
-	}
-	ret = COPY_COMPLETE;
-out:
-	inode_unlock(inode);
-	iput(inode);
-	return ret;
-}
-
-static int write_page_nocow(struct scrub_ctx *sctx,
-			    u64 physical_for_dev_replace, struct page *page)
-{
-	struct bio *bio;
-	struct btrfs_device *dev;
-
-	dev = sctx->wr_tgtdev;
-	if (!dev)
-		return -EIO;
-	if (!dev->bdev) {
-		btrfs_warn_rl(dev->fs_info,
-			"scrub write_page_nocow(bdev == NULL) is unexpected");
-		return -EIO;
-	}
-	bio = btrfs_io_bio_alloc(1);
-	bio->bi_iter.bi_size = 0;
-	bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
-	bio_set_dev(bio, dev->bdev);
-	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
-	/* bio_add_page won't fail on a freshly allocated bio */
-	bio_add_page(bio, page, PAGE_SIZE, 0);
-
-	if (btrfsic_submit_bio_wait(bio)) {
-		bio_put(bio);
-		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
-		return -EIO;
-	}
-
-	bio_put(bio);
-	return 0;
-}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index c47f62b19226..ba8950bfd9c7 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -100,6 +100,7 @@ struct send_ctx {
 	u64 cur_inode_rdev;
 	u64 cur_inode_last_extent;
 	u64 cur_inode_next_write_offset;
+	bool ignore_cur_inode;
 
 	u64 send_progress;
 
@@ -1500,7 +1501,7 @@ static int read_symlink(struct btrfs_root *root,
 	BUG_ON(compression);
 
 	off = btrfs_file_extent_inline_start(ei);
-	len = btrfs_file_extent_inline_len(path->nodes[0], path->slots[0], ei);
+	len = btrfs_file_extent_ram_bytes(path->nodes[0], ei);
 
 	ret = fs_path_add_from_extent_buffer(dest, path->nodes[0], off, len);
 
@@ -5006,6 +5007,15 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 	u64 len;
 	int ret = 0;
 
+	/*
+	 * A hole that starts at EOF or beyond it. Since we do not yet support
+	 * fallocate (for extent preallocation and hole punching), sending a
+	 * write of zeroes starting at EOF or beyond would later require issuing
+	 * a truncate operation which would undo the write and achieve nothing.
+	 */
+	if (offset >= sctx->cur_inode_size)
+		return 0;
+
 	if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
 		return send_update_extent(sctx, offset, end - offset);
 
@@ -5160,7 +5170,7 @@ static int clone_range(struct send_ctx *sctx,
 		ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 		type = btrfs_file_extent_type(leaf, ei);
 		if (type == BTRFS_FILE_EXTENT_INLINE) {
-			ext_len = btrfs_file_extent_inline_len(leaf, slot, ei);
+			ext_len = btrfs_file_extent_ram_bytes(leaf, ei);
 			ext_len = PAGE_ALIGN(ext_len);
 		} else {
 			ext_len = btrfs_file_extent_num_bytes(leaf, ei);
@@ -5236,8 +5246,7 @@ static int send_write_or_clone(struct send_ctx *sctx,
 			struct btrfs_file_extent_item);
 	type = btrfs_file_extent_type(path->nodes[0], ei);
 	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		len = btrfs_file_extent_inline_len(path->nodes[0],
-						   path->slots[0], ei);
+		len = btrfs_file_extent_ram_bytes(path->nodes[0], ei);
 		/*
 		 * it is possible the inline item won't cover the whole page,
 		 * but there may be items after this page.  Make
@@ -5375,7 +5384,7 @@ static int is_extent_unchanged(struct send_ctx *sctx,
 		}
 
 		if (right_type == BTRFS_FILE_EXTENT_INLINE) {
-			right_len = btrfs_file_extent_inline_len(eb, slot, ei);
+			right_len = btrfs_file_extent_ram_bytes(eb, ei);
 			right_len = PAGE_ALIGN(right_len);
 		} else {
 			right_len = btrfs_file_extent_num_bytes(eb, ei);
@@ -5496,8 +5505,7 @@ static int get_last_extent(struct send_ctx *sctx, u64 offset)
 			    struct btrfs_file_extent_item);
 	type = btrfs_file_extent_type(path->nodes[0], fi);
 	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		u64 size = btrfs_file_extent_inline_len(path->nodes[0],
-							path->slots[0], fi);
+		u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
 		extent_end = ALIGN(key.offset + size,
 				   sctx->send_root->fs_info->sectorsize);
 	} else {
@@ -5560,7 +5568,7 @@ static int range_is_hole_in_parent(struct send_ctx *sctx,
 		fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 		if (btrfs_file_extent_type(leaf, fi) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			u64 size = btrfs_file_extent_inline_len(leaf, slot, fi);
+			u64 size = btrfs_file_extent_ram_bytes(leaf, fi);
 
 			extent_end = ALIGN(key.offset + size,
 					   root->fs_info->sectorsize);
@@ -5606,8 +5614,7 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 			    struct btrfs_file_extent_item);
 	type = btrfs_file_extent_type(path->nodes[0], fi);
 	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		u64 size = btrfs_file_extent_inline_len(path->nodes[0],
-							path->slots[0], fi);
+		u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
 		extent_end = ALIGN(key->offset + size,
 				   sctx->send_root->fs_info->sectorsize);
 	} else {
@@ -5799,6 +5806,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 	int pending_move = 0;
 	int refs_processed = 0;
 
+	if (sctx->ignore_cur_inode)
+		return 0;
+
 	ret = process_recorded_refs_if_needed(sctx, at_end, &pending_move,
 					      &refs_processed);
 	if (ret < 0)
@@ -5917,6 +5927,93 @@ out:
 	return ret;
 }
 
+struct parent_paths_ctx {
+	struct list_head *refs;
+	struct send_ctx *sctx;
+};
+
+static int record_parent_ref(int num, u64 dir, int index, struct fs_path *name,
+			     void *ctx)
+{
+	struct parent_paths_ctx *ppctx = ctx;
+
+	return record_ref(ppctx->sctx->parent_root, dir, name, ppctx->sctx,
+			  ppctx->refs);
+}
+
+/*
+ * Issue unlink operations for all paths of the current inode found in the
+ * parent snapshot.
+ */
+static int btrfs_unlink_all_paths(struct send_ctx *sctx)
+{
+	LIST_HEAD(deleted_refs);
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct parent_paths_ctx ctx;
+	int ret;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = sctx->cur_ino;
+	key.type = BTRFS_INODE_REF_KEY;
+	key.offset = 0;
+	ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	ctx.refs = &deleted_refs;
+	ctx.sctx = sctx;
+
+	while (true) {
+		struct extent_buffer *eb = path->nodes[0];
+		int slot = path->slots[0];
+
+		if (slot >= btrfs_header_nritems(eb)) {
+			ret = btrfs_next_leaf(sctx->parent_root, path);
+			if (ret < 0)
+				goto out;
+			else if (ret > 0)
+				break;
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(eb, &key, slot);
+		if (key.objectid != sctx->cur_ino)
+			break;
+		if (key.type != BTRFS_INODE_REF_KEY &&
+		    key.type != BTRFS_INODE_EXTREF_KEY)
+			break;
+
+		ret = iterate_inode_ref(sctx->parent_root, path, &key, 1,
+					record_parent_ref, &ctx);
+		if (ret < 0)
+			goto out;
+
+		path->slots[0]++;
+	}
+
+	while (!list_empty(&deleted_refs)) {
+		struct recorded_ref *ref;
+
+		ref = list_first_entry(&deleted_refs, struct recorded_ref, list);
+		ret = send_unlink(sctx, ref->full_path);
+		if (ret < 0)
+			goto out;
+		fs_path_free(ref->full_path);
+		list_del(&ref->list);
+		kfree(ref);
+	}
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	if (ret)
+		__free_recorded_refs(&deleted_refs);
+	return ret;
+}
+
 static int changed_inode(struct send_ctx *sctx,
 			 enum btrfs_compare_tree_result result)
 {
@@ -5931,6 +6028,7 @@ static int changed_inode(struct send_ctx *sctx,
 	sctx->cur_inode_new_gen = 0;
 	sctx->cur_inode_last_extent = (u64)-1;
 	sctx->cur_inode_next_write_offset = 0;
+	sctx->ignore_cur_inode = false;
 
 	/*
 	 * Set send_progress to current inode. This will tell all get_cur_xxx
@@ -5971,6 +6069,33 @@ static int changed_inode(struct send_ctx *sctx,
 			sctx->cur_inode_new_gen = 1;
 	}
 
+	/*
+	 * Normally we do not find inodes with a link count of zero (orphans)
+	 * because the most common case is to create a snapshot and use it
+	 * for a send operation. However other less common use cases involve
+	 * using a subvolume and send it after turning it to RO mode just
+	 * after deleting all hard links of a file while holding an open
+	 * file descriptor against it or turning a RO snapshot into RW mode,
+	 * keep an open file descriptor against a file, delete it and then
+	 * turn the snapshot back to RO mode before using it for a send
+	 * operation. So if we find such cases, ignore the inode and all its
+	 * items completely if it's a new inode, or if it's a changed inode
+	 * make sure all its previous paths (from the parent snapshot) are all
+	 * unlinked and all other the inode items are ignored.
+	 */
+	if (result == BTRFS_COMPARE_TREE_NEW ||
+	    result == BTRFS_COMPARE_TREE_CHANGED) {
+		u32 nlinks;
+
+		nlinks = btrfs_inode_nlink(sctx->left_path->nodes[0], left_ii);
+		if (nlinks == 0) {
+			sctx->ignore_cur_inode = true;
+			if (result == BTRFS_COMPARE_TREE_CHANGED)
+				ret = btrfs_unlink_all_paths(sctx);
+			goto out;
+		}
+	}
+
 	if (result == BTRFS_COMPARE_TREE_NEW) {
 		sctx->cur_inode_gen = left_gen;
 		sctx->cur_inode_new = 1;
@@ -6309,15 +6434,17 @@ static int changed_cb(struct btrfs_path *left_path,
 	    key->objectid == BTRFS_FREE_SPACE_OBJECTID)
 		goto out;
 
-	if (key->type == BTRFS_INODE_ITEM_KEY)
+	if (key->type == BTRFS_INODE_ITEM_KEY) {
 		ret = changed_inode(sctx, result);
-	else if (key->type == BTRFS_INODE_REF_KEY ||
-		 key->type == BTRFS_INODE_EXTREF_KEY)
-		ret = changed_ref(sctx, result);
-	else if (key->type == BTRFS_XATTR_ITEM_KEY)
-		ret = changed_xattr(sctx, result);
-	else if (key->type == BTRFS_EXTENT_DATA_KEY)
-		ret = changed_extent(sctx, result);
+	} else if (!sctx->ignore_cur_inode) {
+		if (key->type == BTRFS_INODE_REF_KEY ||
+		    key->type == BTRFS_INODE_EXTREF_KEY)
+			ret = changed_ref(sctx, result);
+		else if (key->type == BTRFS_XATTR_ITEM_KEY)
+			ret = changed_xattr(sctx, result);
+		else if (key->type == BTRFS_EXTENT_DATA_KEY)
+			ret = changed_extent(sctx, result);
+	}
 
 out:
 	return ret;
@@ -6328,7 +6455,6 @@ static int full_send_tree(struct send_ctx *sctx)
 	int ret;
 	struct btrfs_root *send_root = sctx->send_root;
 	struct btrfs_key key;
-	struct btrfs_key found_key;
 	struct btrfs_path *path;
 	struct extent_buffer *eb;
 	int slot;
@@ -6350,17 +6476,13 @@ static int full_send_tree(struct send_ctx *sctx)
 	while (1) {
 		eb = path->nodes[0];
 		slot = path->slots[0];
-		btrfs_item_key_to_cpu(eb, &found_key, slot);
+		btrfs_item_key_to_cpu(eb, &key, slot);
 
-		ret = changed_cb(path, NULL, &found_key,
+		ret = changed_cb(path, NULL, &key,
 				 BTRFS_COMPARE_TREE_NEW, sctx);
 		if (ret < 0)
 			goto out;
 
-		key.objectid = found_key.objectid;
-		key.type = found_key.type;
-		key.offset = found_key.offset + 1;
-
 		ret = btrfs_next_item(send_root, path);
 		if (ret < 0)
 			goto out;
diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c
index b7b4acb12833..4c13b737f568 100644
--- a/fs/btrfs/struct-funcs.c
+++ b/fs/btrfs/struct-funcs.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2007 Oracle.  All rights reserved.
  */
 
-#include <linux/highmem.h>
 #include <asm/unaligned.h>
 
 #include "ctree.h"
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 81107ad49f3a..6601c9aa5e35 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -5,7 +5,6 @@
 
 #include <linux/blkdev.h>
 #include <linux/module.h>
-#include <linux/buffer_head.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
@@ -15,8 +14,6 @@
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mount.h>
-#include <linux/mpage.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/statfs.h>
 #include <linux/compat.h>
@@ -468,9 +465,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_subvolrootid:
 		case Opt_device:
 			/*
-			 * These are parsed by btrfs_parse_subvol_options
-			 * and btrfs_parse_early_options
-			 * and can be happily ignored here.
+			 * These are parsed by btrfs_parse_subvol_options or
+			 * btrfs_parse_device_options and can be ignored here.
 			 */
 			break;
 		case Opt_nodatasum:
@@ -760,6 +756,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_recovery:
 			btrfs_warn(info,
 				   "'recovery' is deprecated, use 'usebackuproot' instead");
+			/* fall through */
 		case Opt_usebackuproot:
 			btrfs_info(info,
 				   "trying to use backup root at mount time");
@@ -885,13 +882,16 @@ out:
  * All other options will be parsed on much later in the mount process and
  * only when we need to allocate a new super block.
  */
-static int btrfs_parse_early_options(const char *options, fmode_t flags,
-		void *holder, struct btrfs_fs_devices **fs_devices)
+static int btrfs_parse_device_options(const char *options, fmode_t flags,
+				      void *holder)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *device_name, *opts, *orig, *p;
+	struct btrfs_device *device = NULL;
 	int error = 0;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	if (!options)
 		return 0;
 
@@ -917,11 +917,13 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 				error = -ENOMEM;
 				goto out;
 			}
-			error = btrfs_scan_one_device(device_name,
-					flags, holder, fs_devices);
+			device = btrfs_scan_one_device(device_name, flags,
+					holder);
 			kfree(device_name);
-			if (error)
+			if (IS_ERR(device)) {
+				error = PTR_ERR(device);
 				goto out;
+			}
 		}
 	}
 
@@ -935,8 +937,8 @@ out:
  *
  * The value is later passed to mount_subvol()
  */
-static int btrfs_parse_subvol_options(const char *options, fmode_t flags,
-		char **subvol_name, u64 *subvol_objectid)
+static int btrfs_parse_subvol_options(const char *options, char **subvol_name,
+		u64 *subvol_objectid)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *opts, *orig, *p;
@@ -948,7 +950,7 @@ static int btrfs_parse_subvol_options(const char *options, fmode_t flags,
 
 	/*
 	 * strsep changes the string, duplicate it because
-	 * btrfs_parse_early_options gets called later
+	 * btrfs_parse_device_options gets called later
 	 */
 	opts = kstrdup(options, GFP_KERNEL);
 	if (!opts)
@@ -1517,6 +1519,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 {
 	struct block_device *bdev = NULL;
 	struct super_block *s;
+	struct btrfs_device *device = NULL;
 	struct btrfs_fs_devices *fs_devices = NULL;
 	struct btrfs_fs_info *fs_info = NULL;
 	struct security_mnt_opts new_sec_opts;
@@ -1526,12 +1529,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
 
-	error = btrfs_parse_early_options(data, mode, fs_type,
-					  &fs_devices);
-	if (error) {
-		return ERR_PTR(error);
-	}
-
 	security_init_mnt_opts(&new_sec_opts);
 	if (data) {
 		error = parse_security_options(data, &new_sec_opts);
@@ -1539,10 +1536,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 			return ERR_PTR(error);
 	}
 
-	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
-	if (error)
-		goto error_sec_opts;
-
 	/*
 	 * Setup a dummy root and fs_info for test/set super.  This is because
 	 * we don't actually fill this stuff out until open_ctree, but we need
@@ -1555,8 +1548,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 		goto error_sec_opts;
 	}
 
-	fs_info->fs_devices = fs_devices;
-
 	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
 	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
 	security_init_mnt_opts(&fs_info->security_opts);
@@ -1565,7 +1556,25 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 		goto error_fs_info;
 	}
 
+	mutex_lock(&uuid_mutex);
+	error = btrfs_parse_device_options(data, mode, fs_type);
+	if (error) {
+		mutex_unlock(&uuid_mutex);
+		goto error_fs_info;
+	}
+
+	device = btrfs_scan_one_device(device_name, mode, fs_type);
+	if (IS_ERR(device)) {
+		mutex_unlock(&uuid_mutex);
+		error = PTR_ERR(device);
+		goto error_fs_info;
+	}
+
+	fs_devices = device->fs_devices;
+	fs_info->fs_devices = fs_devices;
+
 	error = btrfs_open_devices(fs_devices, mode, fs_type);
+	mutex_unlock(&uuid_mutex);
 	if (error)
 		goto error_fs_info;
 
@@ -1650,8 +1659,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
 
-	error = btrfs_parse_subvol_options(data, mode,
-					  &subvol_name, &subvol_objectid);
+	error = btrfs_parse_subvol_options(data, &subvol_name,
+					&subvol_objectid);
 	if (error) {
 		kfree(subvol_name);
 		return ERR_PTR(error);
@@ -2098,14 +2107,9 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 				btrfs_account_ro_block_groups_free_space(found);
 
 			for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
-				if (!list_empty(&found->block_groups[i])) {
-					switch (i) {
-					case BTRFS_RAID_DUP:
-					case BTRFS_RAID_RAID1:
-					case BTRFS_RAID_RAID10:
-						factor = 2;
-					}
-				}
+				if (!list_empty(&found->block_groups[i]))
+					factor = btrfs_bg_type_to_factor(
+						btrfs_raid_array[i].bg_flag);
 			}
 		}
 
@@ -2222,7 +2226,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg)
 {
 	struct btrfs_ioctl_vol_args *vol;
-	struct btrfs_fs_devices *fs_devices;
+	struct btrfs_device *device = NULL;
 	int ret = -ENOTTY;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -2234,15 +2238,24 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
-		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
-					    &btrfs_root_fs_type, &fs_devices);
+		mutex_lock(&uuid_mutex);
+		device = btrfs_scan_one_device(vol->name, FMODE_READ,
+					       &btrfs_root_fs_type);
+		ret = PTR_ERR_OR_ZERO(device);
+		mutex_unlock(&uuid_mutex);
 		break;
 	case BTRFS_IOC_DEVICES_READY:
-		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
-					    &btrfs_root_fs_type, &fs_devices);
-		if (ret)
+		mutex_lock(&uuid_mutex);
+		device = btrfs_scan_one_device(vol->name, FMODE_READ,
+					       &btrfs_root_fs_type);
+		if (IS_ERR(device)) {
+			mutex_unlock(&uuid_mutex);
+			ret = PTR_ERR(device);
 			break;
-		ret = !(fs_devices->num_devices == fs_devices->total_devices);
+		}
+		ret = !(device->fs_devices->num_devices ==
+			device->fs_devices->total_devices);
+		mutex_unlock(&uuid_mutex);
 		break;
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
 		ret = btrfs_ioctl_get_supported_features((void __user*)arg);
@@ -2290,7 +2303,6 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 	struct btrfs_fs_devices *cur_devices;
 	struct btrfs_device *dev, *first_dev = NULL;
 	struct list_head *head;
-	struct rcu_string *name;
 
 	/*
 	 * Lightweight locking of the devices. We should not need
@@ -2314,12 +2326,10 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 		cur_devices = cur_devices->seed;
 	}
 
-	if (first_dev) {
-		name = rcu_dereference(first_dev->name);
-		seq_escape(m, name->str, " \t\n\\");
-	} else {
+	if (first_dev)
+		seq_escape(m, rcu_str_deref(first_dev->name), " \t\n\\");
+	else
 		WARN_ON(1);
-	}
 	rcu_read_unlock();
 	return 0;
 }
@@ -2331,7 +2341,6 @@ static const struct super_operations btrfs_super_ops = {
 	.sync_fs	= btrfs_sync_fs,
 	.show_options	= btrfs_show_options,
 	.show_devname	= btrfs_show_devname,
-	.write_inode	= btrfs_write_inode,
 	.alloc_inode	= btrfs_alloc_inode,
 	.destroy_inode	= btrfs_destroy_inode,
 	.statfs		= btrfs_statfs,
@@ -2369,7 +2378,7 @@ static __cold void btrfs_interface_exit(void)
 
 static void __init btrfs_print_mod_info(void)
 {
-	pr_info("Btrfs loaded, crc32c=%s"
+	static const char options[] = ""
 #ifdef CONFIG_BTRFS_DEBUG
 			", debug=on"
 #endif
@@ -2382,8 +2391,8 @@ static void __init btrfs_print_mod_info(void)
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 			", ref-verify=on"
 #endif
-			"\n",
-			crc32c_impl());
+			;
+	pr_info("Btrfs loaded, crc32c=%s%s\n", crc32c_impl(), options);
 }
 
 static int __init init_btrfs_fs(void)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 4a4e960c7c66..3717c864ba23 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -7,10 +7,8 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
-#include <linux/buffer_head.h>
 #include <linux/kobject.h>
 #include <linux/bug.h>
-#include <linux/genhd.h>
 #include <linux/debugfs.h>
 
 #include "ctree.h"
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index ace94db09d29..412b910b04cc 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -216,7 +216,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 	btrfs_init_dummy_trans(&trans, fs_info);
 
 	test_msg("qgroup basic add");
-	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FS_TREE_OBJECTID);
+	ret = btrfs_create_qgroup(&trans, BTRFS_FS_TREE_OBJECTID);
 	if (ret) {
 		test_err("couldn't create a qgroup %d", ret);
 		return ret;
@@ -249,8 +249,8 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
@@ -285,8 +285,8 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return -EINVAL;
@@ -322,7 +322,7 @@ static int test_multiple_refs(struct btrfs_root *root,
 	 * We have BTRFS_FS_TREE_OBJECTID created already from the
 	 * previous test.
 	 */
-	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FIRST_FREE_OBJECTID);
+	ret = btrfs_create_qgroup(&trans, BTRFS_FIRST_FREE_OBJECTID);
 	if (ret) {
 		test_err("couldn't create a qgroup %d", ret);
 		return ret;
@@ -350,8 +350,8 @@ static int test_multiple_refs(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
@@ -385,8 +385,8 @@ static int test_multiple_refs(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
@@ -426,8 +426,8 @@ static int test_multiple_refs(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index ff5f6c719976..3b84f5015029 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -241,7 +241,7 @@ loop:
 	refcount_set(&cur_trans->use_count, 2);
 	atomic_set(&cur_trans->pending_ordered, 0);
 	cur_trans->flags = 0;
-	cur_trans->start_time = get_seconds();
+	cur_trans->start_time = ktime_get_seconds();
 
 	memset(&cur_trans->delayed_refs, 0, sizeof(cur_trans->delayed_refs));
 
@@ -680,7 +680,7 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root)
 
 	trans = start_transaction(root, 0, TRANS_ATTACH,
 				  BTRFS_RESERVE_NO_FLUSH, true);
-	if (IS_ERR(trans) && PTR_ERR(trans) == -ENOENT)
+	if (trans == ERR_PTR(-ENOENT))
 		btrfs_wait_for_commit(root->fs_info, 0);
 
 	return trans;
@@ -1152,7 +1152,7 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans)
 	ret = btrfs_run_dev_replace(trans, fs_info);
 	if (ret)
 		return ret;
-	ret = btrfs_run_qgroups(trans, fs_info);
+	ret = btrfs_run_qgroups(trans);
 	if (ret)
 		return ret;
 
@@ -1355,8 +1355,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 		goto out;
 
 	/* Now qgroup are all updated, we can inherit it to new qgroups */
-	ret = btrfs_qgroup_inherit(trans, fs_info,
-				   src->root_key.objectid, dst_objectid,
+	ret = btrfs_qgroup_inherit(trans, src->root_key.objectid, dst_objectid,
 				   inherit);
 	if (ret < 0)
 		goto out;
@@ -1574,7 +1573,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	/*
 	 * insert root back/forward references
 	 */
-	ret = btrfs_add_root_ref(trans, fs_info, objectid,
+	ret = btrfs_add_root_ref(trans, objectid,
 				 parent_root->root_key.objectid,
 				 btrfs_ino(BTRFS_I(parent_inode)), index,
 				 dentry->d_name.name, dentry->d_name.len);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 94439482a0ec..4cbb1b55387d 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -48,7 +48,7 @@ struct btrfs_transaction {
 	int aborted;
 	struct list_head list;
 	struct extent_io_tree dirty_pages;
-	unsigned long start_time;
+	time64_t start_time;
 	wait_queue_head_t writer_wait;
 	wait_queue_head_t commit_wait;
 	wait_queue_head_t pending_wait;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 8d40e7dd8c30..db835635372f 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -19,6 +19,7 @@
 #include "tree-checker.h"
 #include "disk-io.h"
 #include "compression.h"
+#include "volumes.h"
 
 /*
  * Error message should follow the following format:
@@ -353,6 +354,102 @@ static int check_dir_item(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+__printf(4, 5)
+__cold
+static void block_group_err(const struct btrfs_fs_info *fs_info,
+			    const struct extent_buffer *eb, int slot,
+			    const char *fmt, ...)
+{
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(fs_info,
+	"corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node",
+		btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
+		key.objectid, key.offset, &vaf);
+	va_end(args);
+}
+
+static int check_block_group_item(struct btrfs_fs_info *fs_info,
+				  struct extent_buffer *leaf,
+				  struct btrfs_key *key, int slot)
+{
+	struct btrfs_block_group_item bgi;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+	u64 flags;
+	u64 type;
+
+	/*
+	 * Here we don't really care about alignment since extent allocator can
+	 * handle it.  We care more about the size, as if one block group is
+	 * larger than maximum size, it's must be some obvious corruption.
+	 */
+	if (key->offset > BTRFS_MAX_DATA_CHUNK_SIZE || key->offset == 0) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group size, have %llu expect (0, %llu]",
+				key->offset, BTRFS_MAX_DATA_CHUNK_SIZE);
+		return -EUCLEAN;
+	}
+
+	if (item_size != sizeof(bgi)) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid item size, have %u expect %zu",
+				item_size, sizeof(bgi));
+		return -EUCLEAN;
+	}
+
+	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+			   sizeof(bgi));
+	if (btrfs_block_group_chunk_objectid(&bgi) !=
+	    BTRFS_FIRST_CHUNK_TREE_OBJECTID) {
+		block_group_err(fs_info, leaf, slot,
+		"invalid block group chunk objectid, have %llu expect %llu",
+				btrfs_block_group_chunk_objectid(&bgi),
+				BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+		return -EUCLEAN;
+	}
+
+	if (btrfs_block_group_used(&bgi) > key->offset) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group used, have %llu expect [0, %llu)",
+				btrfs_block_group_used(&bgi), key->offset);
+		return -EUCLEAN;
+	}
+
+	flags = btrfs_block_group_flags(&bgi);
+	if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) {
+		block_group_err(fs_info, leaf, slot,
+"invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
+			flags & BTRFS_BLOCK_GROUP_PROFILE_MASK,
+			hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK));
+		return -EUCLEAN;
+	}
+
+	type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
+	if (type != BTRFS_BLOCK_GROUP_DATA &&
+	    type != BTRFS_BLOCK_GROUP_METADATA &&
+	    type != BTRFS_BLOCK_GROUP_SYSTEM &&
+	    type != (BTRFS_BLOCK_GROUP_METADATA |
+			   BTRFS_BLOCK_GROUP_DATA)) {
+		block_group_err(fs_info, leaf, slot,
+"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx",
+			type, hweight64(type),
+			BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA,
+			BTRFS_BLOCK_GROUP_SYSTEM,
+			BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA);
+		return -EUCLEAN;
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */
@@ -374,6 +471,9 @@ static int check_leaf_item(struct btrfs_fs_info *fs_info,
 	case BTRFS_XATTR_ITEM_KEY:
 		ret = check_dir_item(fs_info, leaf, key, slot);
 		break;
+	case BTRFS_BLOCK_GROUP_ITEM_KEY:
+		ret = check_block_group_item(fs_info, leaf, key, slot);
+		break;
 	}
 	return ret;
 }
@@ -396,9 +496,22 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf,
 	 * skip this check for relocation trees.
 	 */
 	if (nritems == 0 && !btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_RELOC)) {
+		u64 owner = btrfs_header_owner(leaf);
 		struct btrfs_root *check_root;
 
-		key.objectid = btrfs_header_owner(leaf);
+		/* These trees must never be empty */
+		if (owner == BTRFS_ROOT_TREE_OBJECTID ||
+		    owner == BTRFS_CHUNK_TREE_OBJECTID ||
+		    owner == BTRFS_EXTENT_TREE_OBJECTID ||
+		    owner == BTRFS_DEV_TREE_OBJECTID ||
+		    owner == BTRFS_FS_TREE_OBJECTID ||
+		    owner == BTRFS_DATA_RELOC_TREE_OBJECTID) {
+			generic_err(fs_info, leaf, 0,
+			"invalid root, root %llu must never be empty",
+				    owner);
+			return -EUCLEAN;
+		}
+		key.objectid = owner;
 		key.type = BTRFS_ROOT_ITEM_KEY;
 		key.offset = (u64)-1;
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f8220ec02036..1650dc44a5e3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -545,12 +545,8 @@ static noinline struct inode *read_one_inode(struct btrfs_root *root,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 	inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
-	if (IS_ERR(inode)) {
+	if (IS_ERR(inode))
 		inode = NULL;
-	} else if (is_bad_inode(inode)) {
-		iput(inode);
-		inode = NULL;
-	}
 	return inode;
 }
 
@@ -597,7 +593,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
 			nbytes = 0;
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
-		size = btrfs_file_extent_inline_len(eb, slot, item);
+		size = btrfs_file_extent_ram_bytes(eb, item);
 		nbytes = btrfs_file_extent_ram_bytes(eb, item);
 		extent_end = ALIGN(start + size,
 				   fs_info->sectorsize);
@@ -685,7 +681,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		 * as the owner of the file extent changed from log tree
 		 * (doesn't affect qgroup) to fs/file tree(affects qgroup)
 		 */
-		ret = btrfs_qgroup_trace_extent(trans, fs_info,
+		ret = btrfs_qgroup_trace_extent(trans,
 				btrfs_file_extent_disk_bytenr(eb, item),
 				btrfs_file_extent_disk_num_bytes(eb, item),
 				GFP_NOFS);
@@ -715,7 +711,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 				 * allocation tree
 				 */
 				ret = btrfs_alloc_logged_file_extent(trans,
-						fs_info,
 						root->root_key.objectid,
 						key->objectid, offset, &ins);
 				if (ret)
@@ -1291,6 +1286,46 @@ again:
 	return ret;
 }
 
+static int btrfs_inode_ref_exists(struct inode *inode, struct inode *dir,
+				  const u8 ref_type, const char *name,
+				  const int namelen)
+{
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	const u64 parent_id = btrfs_ino(BTRFS_I(dir));
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = btrfs_ino(BTRFS_I(inode));
+	key.type = ref_type;
+	if (key.type == BTRFS_INODE_REF_KEY)
+		key.offset = parent_id;
+	else
+		key.offset = btrfs_extref_hash(parent_id, name, namelen);
+
+	ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
+	if (key.type == BTRFS_INODE_EXTREF_KEY)
+		ret = btrfs_find_name_in_ext_backref(path->nodes[0],
+						     path->slots[0], parent_id,
+						     name, namelen, NULL);
+	else
+		ret = btrfs_find_name_in_backref(path->nodes[0], path->slots[0],
+						 name, namelen, NULL);
+
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 /*
  * replay one inode back reference item found in the log tree.
  * eb, slot and key refer to the buffer and key found in the log tree.
@@ -1400,6 +1435,32 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				}
 			}
 
+			/*
+			 * If a reference item already exists for this inode
+			 * with the same parent and name, but different index,
+			 * drop it and the corresponding directory index entries
+			 * from the parent before adding the new reference item
+			 * and dir index entries, otherwise we would fail with
+			 * -EEXIST returned from btrfs_add_link() below.
+			 */
+			ret = btrfs_inode_ref_exists(inode, dir, key->type,
+						     name, namelen);
+			if (ret > 0) {
+				ret = btrfs_unlink_inode(trans, root,
+							 BTRFS_I(dir),
+							 BTRFS_I(inode),
+							 name, namelen);
+				/*
+				 * If we dropped the link count to 0, bump it so
+				 * that later the iput() on the inode will not
+				 * free it. We will fixup the link count later.
+				 */
+				if (!ret && inode->i_nlink == 0)
+					inc_nlink(inode);
+			}
+			if (ret < 0)
+				goto out;
+
 			/* insert our name */
 			ret = btrfs_add_link(trans, BTRFS_I(dir),
 					BTRFS_I(inode),
@@ -2120,7 +2181,7 @@ again:
 						     dir_key->offset,
 						     name, name_len, 0);
 		}
-		if (!log_di || (IS_ERR(log_di) && PTR_ERR(log_di) == -ENOENT)) {
+		if (!log_di || log_di == ERR_PTR(-ENOENT)) {
 			btrfs_dir_item_key_to_cpu(eb, di, &location);
 			btrfs_release_path(path);
 			btrfs_release_path(log_path);
@@ -2933,7 +2994,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	/* bail out if we need to do a full commit */
 	if (btrfs_need_log_full_commit(fs_info, trans)) {
 		ret = -EAGAIN;
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&root->log_mutex);
 		goto out;
 	}
@@ -2951,7 +3011,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (ret) {
 		blk_finish_plug(&plug);
 		btrfs_abort_transaction(trans, ret);
-		btrfs_free_logged_extents(log, log_transid);
 		btrfs_set_log_full_commit(fs_info, trans);
 		mutex_unlock(&root->log_mutex);
 		goto out;
@@ -3002,7 +3061,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 		btrfs_wait_tree_log_extents(log, mark);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = -EAGAIN;
 		goto out;
@@ -3020,7 +3078,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (atomic_read(&log_root_tree->log_commit[index2])) {
 		blk_finish_plug(&plug);
 		ret = btrfs_wait_tree_log_extents(log, mark);
-		btrfs_wait_logged_extents(trans, log, log_transid);
 		wait_log_commit(log_root_tree,
 				root_log_ctx.log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
@@ -3045,7 +3102,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (btrfs_need_log_full_commit(fs_info, trans)) {
 		blk_finish_plug(&plug);
 		btrfs_wait_tree_log_extents(log, mark);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = -EAGAIN;
 		goto out_wake_log_root;
@@ -3058,7 +3114,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (ret) {
 		btrfs_set_log_full_commit(fs_info, trans);
 		btrfs_abort_transaction(trans, ret);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out_wake_log_root;
 	}
@@ -3068,11 +3123,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 						  EXTENT_NEW | EXTENT_DIRTY);
 	if (ret) {
 		btrfs_set_log_full_commit(fs_info, trans);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out_wake_log_root;
 	}
-	btrfs_wait_logged_extents(trans, log, log_transid);
 
 	btrfs_set_super_log_root(fs_info->super_for_commit,
 				 log_root_tree->node->start);
@@ -3159,14 +3212,6 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 				  EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
 	}
 
-	/*
-	 * We may have short-circuited the log tree with the full commit logic
-	 * and left ordered extents on our list, so clear these out to keep us
-	 * from leaking inodes and memory.
-	 */
-	btrfs_free_logged_extents(log, 0);
-	btrfs_free_logged_extents(log, 1);
-
 	free_extent_buffer(log->node);
 	kfree(log);
 }
@@ -3756,7 +3801,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       int start_slot, int nr, int inode_only,
 			       u64 logged_isize)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	unsigned long src_offset;
 	unsigned long dst_offset;
 	struct btrfs_root *log = inode->root->log_root;
@@ -3937,9 +3982,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 					struct btrfs_file_extent_item);
 		if (btrfs_file_extent_type(src, extent) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_inline_len(src,
-							   src_path->slots[0],
-							   extent);
+			len = btrfs_file_extent_ram_bytes(src, extent);
 			*last_extent = ALIGN(key.offset + len,
 					     fs_info->sectorsize);
 		} else {
@@ -4004,7 +4047,7 @@ fill_holes:
 		extent = btrfs_item_ptr(src, i, struct btrfs_file_extent_item);
 		if (btrfs_file_extent_type(src, extent) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_inline_len(src, i, extent);
+			len = btrfs_file_extent_ram_bytes(src, extent);
 			extent_end = ALIGN(key.offset + len,
 					   fs_info->sectorsize);
 		} else {
@@ -4078,131 +4121,32 @@ static int extent_cmp(void *priv, struct list_head *a, struct list_head *b)
 	return 0;
 }
 
-static int wait_ordered_extents(struct btrfs_trans_handle *trans,
-				struct inode *inode,
-				struct btrfs_root *root,
-				const struct extent_map *em,
-				const struct list_head *logged_list,
-				bool *ordered_io_error)
+static int log_extent_csums(struct btrfs_trans_handle *trans,
+			    struct btrfs_inode *inode,
+			    struct btrfs_root *log_root,
+			    const struct extent_map *em)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_ordered_extent *ordered;
-	struct btrfs_root *log = root->log_root;
-	u64 mod_start = em->mod_start;
-	u64 mod_len = em->mod_len;
-	const bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 	u64 csum_offset;
 	u64 csum_len;
 	LIST_HEAD(ordered_sums);
 	int ret = 0;
 
-	*ordered_io_error = false;
-
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	if (inode->flags & BTRFS_INODE_NODATASUM ||
+	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
 	    em->block_start == EXTENT_MAP_HOLE)
 		return 0;
 
-	/*
-	 * Wait far any ordered extent that covers our extent map. If it
-	 * finishes without an error, first check and see if our csums are on
-	 * our outstanding ordered extents.
-	 */
-	list_for_each_entry(ordered, logged_list, log_list) {
-		struct btrfs_ordered_sum *sum;
-
-		if (!mod_len)
-			break;
-
-		if (ordered->file_offset + ordered->len <= mod_start ||
-		    mod_start + mod_len <= ordered->file_offset)
-			continue;
-
-		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
-			const u64 start = ordered->file_offset;
-			const u64 end = ordered->file_offset + ordered->len - 1;
-
-			WARN_ON(ordered->inode != inode);
-			filemap_fdatawrite_range(inode->i_mapping, start, end);
-		}
-
-		wait_event(ordered->wait,
-			   (test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) ||
-			    test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)));
-
-		if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) {
-			/*
-			 * Clear the AS_EIO/AS_ENOSPC flags from the inode's
-			 * i_mapping flags, so that the next fsync won't get
-			 * an outdated io error too.
-			 */
-			filemap_check_errors(inode->i_mapping);
-			*ordered_io_error = true;
-			break;
-		}
-		/*
-		 * We are going to copy all the csums on this ordered extent, so
-		 * go ahead and adjust mod_start and mod_len in case this
-		 * ordered extent has already been logged.
-		 */
-		if (ordered->file_offset > mod_start) {
-			if (ordered->file_offset + ordered->len >=
-			    mod_start + mod_len)
-				mod_len = ordered->file_offset - mod_start;
-			/*
-			 * If we have this case
-			 *
-			 * |--------- logged extent ---------|
-			 *       |----- ordered extent ----|
-			 *
-			 * Just don't mess with mod_start and mod_len, we'll
-			 * just end up logging more csums than we need and it
-			 * will be ok.
-			 */
-		} else {
-			if (ordered->file_offset + ordered->len <
-			    mod_start + mod_len) {
-				mod_len = (mod_start + mod_len) -
-					(ordered->file_offset + ordered->len);
-				mod_start = ordered->file_offset +
-					ordered->len;
-			} else {
-				mod_len = 0;
-			}
-		}
-
-		if (skip_csum)
-			continue;
-
-		/*
-		 * To keep us from looping for the above case of an ordered
-		 * extent that falls inside of the logged extent.
-		 */
-		if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM,
-				     &ordered->flags))
-			continue;
-
-		list_for_each_entry(sum, &ordered->list, list) {
-			ret = btrfs_csum_file_blocks(trans, log, sum);
-			if (ret)
-				break;
-		}
-	}
-
-	if (*ordered_io_error || !mod_len || ret || skip_csum)
-		return ret;
-
+	/* If we're compressed we have to save the entire range of csums. */
 	if (em->compress_type) {
 		csum_offset = 0;
 		csum_len = max(em->block_len, em->orig_block_len);
 	} else {
-		csum_offset = mod_start - em->start;
-		csum_len = mod_len;
+		csum_offset = em->mod_start - em->start;
+		csum_len = em->mod_len;
 	}
 
 	/* block start is already adjusted for the file extent offset. */
-	ret = btrfs_lookup_csums_range(fs_info->csum_root,
+	ret = btrfs_lookup_csums_range(trans->fs_info->csum_root,
 				       em->block_start + csum_offset,
 				       em->block_start + csum_offset +
 				       csum_len - 1, &ordered_sums, 0);
@@ -4214,7 +4158,7 @@ static int wait_ordered_extents(struct btrfs_trans_handle *trans,
 						   struct btrfs_ordered_sum,
 						   list);
 		if (!ret)
-			ret = btrfs_csum_file_blocks(trans, log, sums);
+			ret = btrfs_csum_file_blocks(trans, log_root, sums);
 		list_del(&sums->list);
 		kfree(sums);
 	}
@@ -4226,7 +4170,6 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 			  struct btrfs_inode *inode, struct btrfs_root *root,
 			  const struct extent_map *em,
 			  struct btrfs_path *path,
-			  const struct list_head *logged_list,
 			  struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *log = root->log_root;
@@ -4238,18 +4181,11 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	u64 block_len;
 	int ret;
 	int extent_inserted = 0;
-	bool ordered_io_err = false;
 
-	ret = wait_ordered_extents(trans, &inode->vfs_inode, root, em,
-			logged_list, &ordered_io_err);
+	ret = log_extent_csums(trans, inode, log, em);
 	if (ret)
 		return ret;
 
-	if (ordered_io_err) {
-		ctx->io_err = -EIO;
-		return ctx->io_err;
-	}
-
 	btrfs_init_map_token(&token);
 
 	ret = __btrfs_drop_extents(trans, log, &inode->vfs_inode, path, em->start,
@@ -4424,7 +4360,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
 				     struct btrfs_inode *inode,
 				     struct btrfs_path *path,
-				     struct list_head *logged_list,
 				     struct btrfs_log_ctx *ctx,
 				     const u64 start,
 				     const u64 end)
@@ -4480,20 +4415,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	}
 
 	list_sort(NULL, &extents, extent_cmp);
-	btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
-	/*
-	 * Some ordered extents started by fsync might have completed
-	 * before we could collect them into the list logged_list, which
-	 * means they're gone, not in our logged_list nor in the inode's
-	 * ordered tree. We want the application/user space to know an
-	 * error happened while attempting to persist file data so that
-	 * it can take proper action. If such error happened, we leave
-	 * without writing to the log tree and the fsync must report the
-	 * file data write error and not commit the current transaction.
-	 */
-	ret = filemap_check_errors(inode->vfs_inode.i_mapping);
-	if (ret)
-		ctx->io_err = ret;
 process:
 	while (!list_empty(&extents)) {
 		em = list_entry(extents.next, struct extent_map, list);
@@ -4512,8 +4433,7 @@ process:
 
 		write_unlock(&tree->lock);
 
-		ret = log_one_extent(trans, inode, root, em, path, logged_list,
-				     ctx);
+		ret = log_one_extent(trans, inode, root, em, path, ctx);
 		write_lock(&tree->lock);
 		clear_em_logging(tree, em);
 		free_extent_map(em);
@@ -4712,9 +4632,7 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 
 		if (btrfs_file_extent_type(leaf, extent) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_inline_len(leaf,
-							   path->slots[0],
-							   extent);
+			len = btrfs_file_extent_ram_bytes(leaf, extent);
 			ASSERT(len == i_size ||
 			       (len == fs_info->sectorsize &&
 				btrfs_file_extent_compression(leaf, extent) !=
@@ -4898,7 +4816,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_key min_key;
 	struct btrfs_key max_key;
 	struct btrfs_root *log = root->log_root;
-	LIST_HEAD(logged_list);
 	u64 last_extent = 0;
 	int err = 0;
 	int ret;
@@ -5094,8 +5011,7 @@ again:
 				 * we don't need to do more work nor fallback to
 				 * a transaction commit.
 				 */
-				if (IS_ERR(other_inode) &&
-				    PTR_ERR(other_inode) == -ENOENT) {
+				if (other_inode == ERR_PTR(-ENOENT)) {
 					goto next_key;
 				} else if (IS_ERR(other_inode)) {
 					err = PTR_ERR(other_inode);
@@ -5235,7 +5151,7 @@ log_extents:
 	}
 	if (fast_search) {
 		ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
-						&logged_list, ctx, start, end);
+						ctx, start, end);
 		if (ret) {
 			err = ret;
 			goto out_unlock;
@@ -5286,10 +5202,6 @@ log_extents:
 	inode->last_log_commit = inode->last_sub_trans;
 	spin_unlock(&inode->lock);
 out_unlock:
-	if (unlikely(err))
-		btrfs_put_logged_extents(&logged_list);
-	else
-		btrfs_submit_logged_extents(&logged_list, log);
 	mutex_unlock(&inode->log_mutex);
 
 	btrfs_free_path(path);
@@ -5585,7 +5497,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 				 struct btrfs_inode *inode,
 				 struct btrfs_log_ctx *ctx)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_key key;
@@ -6120,7 +6032,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
 			struct dentry *parent)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 
 	/*
 	 * this will force the logging code to walk the dentry chain
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index e034ad9e23b4..da86706123ff 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -8,15 +8,12 @@
 #include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/iocontext.h>
-#include <linux/capability.h>
 #include <linux/ratelimit.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/semaphore.h>
 #include <linux/uuid.h>
 #include <linux/list_sort.h>
-#include <asm/div64.h>
 #include "ctree.h"
 #include "extent_map.h"
 #include "disk-io.h"
@@ -634,44 +631,48 @@ static void pending_bios_fn(struct btrfs_work *work)
  *		devices.
  */
 static void btrfs_free_stale_devices(const char *path,
-				     struct btrfs_device *skip_dev)
+				     struct btrfs_device *skip_device)
 {
-	struct btrfs_fs_devices *fs_devs, *tmp_fs_devs;
-	struct btrfs_device *dev, *tmp_dev;
+	struct btrfs_fs_devices *fs_devices, *tmp_fs_devices;
+	struct btrfs_device *device, *tmp_device;
 
-	list_for_each_entry_safe(fs_devs, tmp_fs_devs, &fs_uuids, fs_list) {
-
-		if (fs_devs->opened)
+	list_for_each_entry_safe(fs_devices, tmp_fs_devices, &fs_uuids, fs_list) {
+		mutex_lock(&fs_devices->device_list_mutex);
+		if (fs_devices->opened) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			continue;
+		}
 
-		list_for_each_entry_safe(dev, tmp_dev,
-					 &fs_devs->devices, dev_list) {
+		list_for_each_entry_safe(device, tmp_device,
+					 &fs_devices->devices, dev_list) {
 			int not_found = 0;
 
-			if (skip_dev && skip_dev == dev)
+			if (skip_device && skip_device == device)
 				continue;
-			if (path && !dev->name)
+			if (path && !device->name)
 				continue;
 
 			rcu_read_lock();
 			if (path)
-				not_found = strcmp(rcu_str_deref(dev->name),
+				not_found = strcmp(rcu_str_deref(device->name),
 						   path);
 			rcu_read_unlock();
 			if (not_found)
 				continue;
 
 			/* delete the stale device */
-			if (fs_devs->num_devices == 1) {
-				btrfs_sysfs_remove_fsid(fs_devs);
-				list_del(&fs_devs->fs_list);
-				free_fs_devices(fs_devs);
+			fs_devices->num_devices--;
+			list_del(&device->dev_list);
+			btrfs_free_device(device);
+
+			if (fs_devices->num_devices == 0)
 				break;
-			} else {
-				fs_devs->num_devices--;
-				list_del(&dev->dev_list);
-				btrfs_free_device(dev);
-			}
+		}
+		mutex_unlock(&fs_devices->device_list_mutex);
+		if (fs_devices->num_devices == 0) {
+			btrfs_sysfs_remove_fsid(fs_devices);
+			list_del(&fs_devices->fs_list);
+			free_fs_devices(fs_devices);
 		}
 	}
 }
@@ -750,7 +751,8 @@ error_brelse:
  * error pointer when failed
  */
 static noinline struct btrfs_device *device_list_add(const char *path,
-			   struct btrfs_super_block *disk_super)
+			   struct btrfs_super_block *disk_super,
+			   bool *new_device_added)
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *fs_devices;
@@ -764,21 +766,26 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		if (IS_ERR(fs_devices))
 			return ERR_CAST(fs_devices);
 
+		mutex_lock(&fs_devices->device_list_mutex);
 		list_add(&fs_devices->fs_list, &fs_uuids);
 
 		device = NULL;
 	} else {
+		mutex_lock(&fs_devices->device_list_mutex);
 		device = find_device(fs_devices, devid,
 				disk_super->dev_item.uuid);
 	}
 
 	if (!device) {
-		if (fs_devices->opened)
+		if (fs_devices->opened) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EBUSY);
+		}
 
 		device = btrfs_alloc_device(NULL, &devid,
 					    disk_super->dev_item.uuid);
 		if (IS_ERR(device)) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			/* we can safely leave the fs_devices entry around */
 			return device;
 		}
@@ -786,17 +793,16 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		name = rcu_string_strdup(path, GFP_NOFS);
 		if (!name) {
 			btrfs_free_device(device);
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-ENOMEM);
 		}
 		rcu_assign_pointer(device->name, name);
 
-		mutex_lock(&fs_devices->device_list_mutex);
 		list_add_rcu(&device->dev_list, &fs_devices->devices);
 		fs_devices->num_devices++;
-		mutex_unlock(&fs_devices->device_list_mutex);
 
 		device->fs_devices = fs_devices;
-		btrfs_free_stale_devices(path, device);
+		*new_device_added = true;
 
 		if (disk_super->label[0])
 			pr_info("BTRFS: device label %s devid %llu transid %llu %s\n",
@@ -840,12 +846,15 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 			 * with larger generation number or the last-in if
 			 * generation are equal.
 			 */
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EEXIST);
 		}
 
 		name = rcu_string_strdup(path, GFP_NOFS);
-		if (!name)
+		if (!name) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-ENOMEM);
+		}
 		rcu_string_free(device->name);
 		rcu_assign_pointer(device->name, name);
 		if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state)) {
@@ -865,6 +874,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 	fs_devices->total_devices = btrfs_super_num_devices(disk_super);
 
+	mutex_unlock(&fs_devices->device_list_mutex);
 	return device;
 }
 
@@ -1004,7 +1014,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 	blkdev_put(device->bdev, device->mode);
 }
 
-static void btrfs_prepare_close_one_device(struct btrfs_device *device)
+static void btrfs_close_one_device(struct btrfs_device *device)
 {
 	struct btrfs_fs_devices *fs_devices = device->fs_devices;
 	struct btrfs_device *new_device;
@@ -1022,6 +1032,8 @@ static void btrfs_prepare_close_one_device(struct btrfs_device *device)
 	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
 		fs_devices->missing_devices--;
 
+	btrfs_close_bdev(device);
+
 	new_device = btrfs_alloc_device(NULL, &device->devid,
 					device->uuid);
 	BUG_ON(IS_ERR(new_device)); /* -ENOMEM */
@@ -1035,39 +1047,23 @@ static void btrfs_prepare_close_one_device(struct btrfs_device *device)
 
 	list_replace_rcu(&device->dev_list, &new_device->dev_list);
 	new_device->fs_devices = device->fs_devices;
+
+	call_rcu(&device->rcu, free_device_rcu);
 }
 
 static int close_fs_devices(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *device, *tmp;
-	struct list_head pending_put;
-
-	INIT_LIST_HEAD(&pending_put);
 
 	if (--fs_devices->opened > 0)
 		return 0;
 
 	mutex_lock(&fs_devices->device_list_mutex);
 	list_for_each_entry_safe(device, tmp, &fs_devices->devices, dev_list) {
-		btrfs_prepare_close_one_device(device);
-		list_add(&device->dev_list, &pending_put);
+		btrfs_close_one_device(device);
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	/*
-	 * btrfs_show_devname() is using the device_list_mutex,
-	 * sometimes call to blkdev_put() leads vfs calling
-	 * into this func. So do put outside of device_list_mutex,
-	 * as of now.
-	 */
-	while (!list_empty(&pending_put)) {
-		device = list_first_entry(&pending_put,
-				struct btrfs_device, dev_list);
-		list_del(&device->dev_list);
-		btrfs_close_bdev(device);
-		call_rcu(&device->rcu, free_device_rcu);
-	}
-
 	WARN_ON(fs_devices->open_devices);
 	WARN_ON(fs_devices->rw_devices);
 	fs_devices->opened = 0;
@@ -1146,6 +1142,8 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 {
 	int ret;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	mutex_lock(&fs_devices->device_list_mutex);
 	if (fs_devices->opened) {
 		fs_devices->opened++;
@@ -1215,16 +1213,18 @@ static int btrfs_read_disk_super(struct block_device *bdev, u64 bytenr,
  * and we are not allowed to call set_blocksize during the scan. The superblock
  * is read via pagecache
  */
-int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
-			  struct btrfs_fs_devices **fs_devices_ret)
+struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
+					   void *holder)
 {
 	struct btrfs_super_block *disk_super;
-	struct btrfs_device *device;
+	bool new_device_added = false;
+	struct btrfs_device *device = NULL;
 	struct block_device *bdev;
 	struct page *page;
-	int ret = 0;
 	u64 bytenr;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	/*
 	 * we would like to check all the supers, but that would make
 	 * a btrfs mount succeed after a mkfs from a different FS.
@@ -1236,112 +1236,25 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 
 	bdev = blkdev_get_by_path(path, flags, holder);
 	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
+		return ERR_CAST(bdev);
 
 	if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super)) {
-		ret = -EINVAL;
+		device = ERR_PTR(-EINVAL);
 		goto error_bdev_put;
 	}
 
-	mutex_lock(&uuid_mutex);
-	device = device_list_add(path, disk_super);
-	if (IS_ERR(device))
-		ret = PTR_ERR(device);
-	else
-		*fs_devices_ret = device->fs_devices;
-	mutex_unlock(&uuid_mutex);
+	device = device_list_add(path, disk_super, &new_device_added);
+	if (!IS_ERR(device)) {
+		if (new_device_added)
+			btrfs_free_stale_devices(path, device);
+	}
 
 	btrfs_release_disk_super(page);
 
 error_bdev_put:
 	blkdev_put(bdev, flags);
 
-	return ret;
-}
-
-/* helper to account the used device space in the range */
-int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
-				   u64 end, u64 *length)
-{
-	struct btrfs_key key;
-	struct btrfs_root *root = device->fs_info->dev_root;
-	struct btrfs_dev_extent *dev_extent;
-	struct btrfs_path *path;
-	u64 extent_end;
-	int ret;
-	int slot;
-	struct extent_buffer *l;
-
-	*length = 0;
-
-	if (start >= device->total_bytes ||
-		test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
-		return 0;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-	path->reada = READA_FORWARD;
-
-	key.objectid = device->devid;
-	key.offset = start;
-	key.type = BTRFS_DEV_EXTENT_KEY;
-
-	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
-		goto out;
-	if (ret > 0) {
-		ret = btrfs_previous_item(root, path, key.objectid, key.type);
-		if (ret < 0)
-			goto out;
-	}
-
-	while (1) {
-		l = path->nodes[0];
-		slot = path->slots[0];
-		if (slot >= btrfs_header_nritems(l)) {
-			ret = btrfs_next_leaf(root, path);
-			if (ret == 0)
-				continue;
-			if (ret < 0)
-				goto out;
-
-			break;
-		}
-		btrfs_item_key_to_cpu(l, &key, slot);
-
-		if (key.objectid < device->devid)
-			goto next;
-
-		if (key.objectid > device->devid)
-			break;
-
-		if (key.type != BTRFS_DEV_EXTENT_KEY)
-			goto next;
-
-		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
-		extent_end = key.offset + btrfs_dev_extent_length(l,
-								  dev_extent);
-		if (key.offset <= start && extent_end > end) {
-			*length = end - start + 1;
-			break;
-		} else if (key.offset <= start && extent_end > start)
-			*length += extent_end - start;
-		else if (key.offset > start && extent_end <= end)
-			*length += extent_end - key.offset;
-		else if (key.offset > start && key.offset <= end) {
-			*length += end - key.offset + 1;
-			break;
-		} else if (key.offset > end)
-			break;
-
-next:
-		path->slots[0]++;
-	}
-	ret = 0;
-out:
-	btrfs_free_path(path);
-	return ret;
+	return device;
 }
 
 static int contains_pending_extent(struct btrfs_transaction *transaction,
@@ -1753,10 +1666,8 @@ error:
  * the btrfs_device struct should be fully filled in
  */
 static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
 			    struct btrfs_device *device)
 {
-	struct btrfs_root *root = fs_info->chunk_root;
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_dev_item *dev_item;
@@ -1772,8 +1683,8 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_DEV_ITEM_KEY;
 	key.offset = device->devid;
 
-	ret = btrfs_insert_empty_item(trans, root, path, &key,
-				      sizeof(*dev_item));
+	ret = btrfs_insert_empty_item(trans, trans->fs_info->chunk_root, path,
+				      &key, sizeof(*dev_item));
 	if (ret)
 		goto out;
 
@@ -1798,7 +1709,7 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 	ptr = btrfs_device_uuid(dev_item);
 	write_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
 	ptr = btrfs_device_fsid(dev_item);
-	write_extent_buffer(leaf, fs_info->fsid, ptr, BTRFS_FSID_SIZE);
+	write_extent_buffer(leaf, trans->fs_info->fsid, ptr, BTRFS_FSID_SIZE);
 	btrfs_mark_buffer_dirty(leaf);
 
 	ret = 0;
@@ -1922,9 +1833,10 @@ static struct btrfs_device * btrfs_find_next_active_device(
  * where this function called, there should be always be another device (or
  * this_dev) which is active.
  */
-void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
-		struct btrfs_device *device, struct btrfs_device *this_dev)
+void btrfs_assign_next_active_device(struct btrfs_device *device,
+				     struct btrfs_device *this_dev)
 {
+	struct btrfs_fs_info *fs_info = device->fs_info;
 	struct btrfs_device *next_device;
 
 	if (this_dev)
@@ -2027,11 +1939,14 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 
 	cur_devices->num_devices--;
 	cur_devices->total_devices--;
+	/* Update total_devices of the parent fs_devices if it's seed */
+	if (cur_devices != fs_devices)
+		fs_devices->total_devices--;
 
 	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
 		cur_devices->missing_devices--;
 
-	btrfs_assign_next_active_device(fs_info, device, NULL);
+	btrfs_assign_next_active_device(device, NULL);
 
 	if (device->bdev) {
 		cur_devices->open_devices--;
@@ -2082,12 +1997,11 @@ error_undo:
 	goto out;
 }
 
-void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
-					struct btrfs_device *srcdev)
+void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev)
 {
 	struct btrfs_fs_devices *fs_devices;
 
-	lockdep_assert_held(&fs_info->fs_devices->device_list_mutex);
+	lockdep_assert_held(&srcdev->fs_info->fs_devices->device_list_mutex);
 
 	/*
 	 * in case of fs with no seed, srcdev->fs_devices will point
@@ -2149,10 +2063,9 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 	}
 }
 
-void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				      struct btrfs_device *tgtdev)
+void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
 {
-	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_fs_devices *fs_devices = tgtdev->fs_info->fs_devices;
 
 	WARN_ON(!tgtdev);
 	mutex_lock(&fs_devices->device_list_mutex);
@@ -2164,7 +2077,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 
 	fs_devices->num_devices--;
 
-	btrfs_assign_next_active_device(fs_info, tgtdev, NULL);
+	btrfs_assign_next_active_device(tgtdev, NULL);
 
 	list_del_rcu(&tgtdev->dev_list);
 
@@ -2295,7 +2208,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&seed_devices->alloc_list);
 	mutex_init(&seed_devices->device_list_mutex);
 
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 	list_splice_init_rcu(&fs_devices->devices, &seed_devices->devices,
 			      synchronize_rcu);
 	list_for_each_entry(device, &seed_devices->devices, dev_list)
@@ -2315,7 +2228,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	generate_random_uuid(fs_devices->fsid);
 	memcpy(fs_info->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
 	memcpy(disk_super->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	super_flags = btrfs_super_flags(disk_super) &
 		      ~BTRFS_SUPER_FLAG_SEEDING;
@@ -2405,15 +2318,16 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
 	struct block_device *bdev;
-	struct list_head *devices;
 	struct super_block *sb = fs_info->sb;
 	struct rcu_string *name;
-	u64 tmp;
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	u64 orig_super_total_bytes;
+	u64 orig_super_num_devices;
 	int seeding_dev = 0;
 	int ret = 0;
 	bool unlocked = false;
 
-	if (sb_rdonly(sb) && !fs_info->fs_devices->seeding)
+	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
 	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
@@ -2421,7 +2335,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
-	if (fs_info->fs_devices->seeding) {
+	if (fs_devices->seeding) {
 		seeding_dev = 1;
 		down_write(&sb->s_umount);
 		mutex_lock(&uuid_mutex);
@@ -2429,18 +2343,16 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 	filemap_write_and_wait(bdev->bd_inode->i_mapping);
 
-	devices = &fs_info->fs_devices->devices;
-
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
-	list_for_each_entry(device, devices, dev_list) {
+	mutex_lock(&fs_devices->device_list_mutex);
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
 		if (device->bdev == bdev) {
 			ret = -EEXIST;
 			mutex_unlock(
-				&fs_info->fs_devices->device_list_mutex);
+				&fs_devices->device_list_mutex);
 			goto error;
 		}
 	}
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	device = btrfs_alloc_device(fs_info, NULL, NULL);
 	if (IS_ERR(device)) {
@@ -2489,33 +2401,34 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		}
 	}
 
-	device->fs_devices = fs_info->fs_devices;
+	device->fs_devices = fs_devices;
 
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 	mutex_lock(&fs_info->chunk_mutex);
-	list_add_rcu(&device->dev_list, &fs_info->fs_devices->devices);
-	list_add(&device->dev_alloc_list,
-		 &fs_info->fs_devices->alloc_list);
-	fs_info->fs_devices->num_devices++;
-	fs_info->fs_devices->open_devices++;
-	fs_info->fs_devices->rw_devices++;
-	fs_info->fs_devices->total_devices++;
-	fs_info->fs_devices->total_rw_bytes += device->total_bytes;
+	list_add_rcu(&device->dev_list, &fs_devices->devices);
+	list_add(&device->dev_alloc_list, &fs_devices->alloc_list);
+	fs_devices->num_devices++;
+	fs_devices->open_devices++;
+	fs_devices->rw_devices++;
+	fs_devices->total_devices++;
+	fs_devices->total_rw_bytes += device->total_bytes;
 
 	atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
 
 	if (!blk_queue_nonrot(q))
-		fs_info->fs_devices->rotating = 1;
+		fs_devices->rotating = 1;
 
-	tmp = btrfs_super_total_bytes(fs_info->super_copy);
+	orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
 	btrfs_set_super_total_bytes(fs_info->super_copy,
-		round_down(tmp + device->total_bytes, fs_info->sectorsize));
+		round_down(orig_super_total_bytes + device->total_bytes,
+			   fs_info->sectorsize));
 
-	tmp = btrfs_super_num_devices(fs_info->super_copy);
-	btrfs_set_super_num_devices(fs_info->super_copy, tmp + 1);
+	orig_super_num_devices = btrfs_super_num_devices(fs_info->super_copy);
+	btrfs_set_super_num_devices(fs_info->super_copy,
+				    orig_super_num_devices + 1);
 
 	/* add sysfs device entry */
-	btrfs_sysfs_add_device_link(fs_info->fs_devices, device);
+	btrfs_sysfs_add_device_link(fs_devices, device);
 
 	/*
 	 * we've got more storage, clear any full flags on the space
@@ -2524,7 +2437,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	btrfs_clear_space_info_full(fs_info);
 
 	mutex_unlock(&fs_info->chunk_mutex);
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	if (seeding_dev) {
 		mutex_lock(&fs_info->chunk_mutex);
@@ -2536,7 +2449,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		}
 	}
 
-	ret = btrfs_add_dev_item(trans, fs_info, device);
+	ret = btrfs_add_dev_item(trans, device);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto error_sysfs;
@@ -2556,7 +2469,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		 */
 		snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU",
 						fs_info->fsid);
-		if (kobject_rename(&fs_info->fs_devices->fsid_kobj, fsid_buf))
+		if (kobject_rename(&fs_devices->fsid_kobj, fsid_buf))
 			btrfs_warn(fs_info,
 				   "sysfs: failed to create fsid for sprout");
 	}
@@ -2591,7 +2504,23 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	return ret;
 
 error_sysfs:
-	btrfs_sysfs_rm_device_link(fs_info->fs_devices, device);
+	btrfs_sysfs_rm_device_link(fs_devices, device);
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_info->chunk_mutex);
+	list_del_rcu(&device->dev_list);
+	list_del(&device->dev_alloc_list);
+	fs_info->fs_devices->num_devices--;
+	fs_info->fs_devices->open_devices--;
+	fs_info->fs_devices->rw_devices--;
+	fs_info->fs_devices->total_devices--;
+	fs_info->fs_devices->total_rw_bytes -= device->total_bytes;
+	atomic64_sub(device->total_bytes, &fs_info->free_chunk_space);
+	btrfs_set_super_total_bytes(fs_info->super_copy,
+				    orig_super_total_bytes);
+	btrfs_set_super_num_devices(fs_info->super_copy,
+				    orig_super_num_devices);
+	mutex_unlock(&fs_info->chunk_mutex);
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 error_trans:
 	if (seeding_dev)
 		sb->s_flags |= SB_RDONLY;
@@ -2695,9 +2624,9 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 	return btrfs_update_device(trans, device);
 }
 
-static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info, u64 chunk_offset)
+static int btrfs_free_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->chunk_root;
 	int ret;
 	struct btrfs_path *path;
@@ -2806,9 +2735,9 @@ static struct extent_map *get_chunk_map(struct btrfs_fs_info *fs_info,
 	return em;
 }
 
-int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 chunk_offset)
+int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct extent_map *em;
 	struct map_lookup *map;
 	u64 dev_extent_len = 0;
@@ -2827,7 +2756,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	}
 	map = em->map_lookup;
 	mutex_lock(&fs_info->chunk_mutex);
-	check_system_chunk(trans, fs_info, map->type);
+	check_system_chunk(trans, map->type);
 	mutex_unlock(&fs_info->chunk_mutex);
 
 	/*
@@ -2867,7 +2796,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	ret = btrfs_free_chunk(trans, fs_info, chunk_offset);
+	ret = btrfs_free_chunk(trans, chunk_offset);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -2883,7 +2812,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	ret = btrfs_remove_block_group(trans, fs_info, chunk_offset, em);
+	ret = btrfs_remove_block_group(trans, chunk_offset, em);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -2948,7 +2877,7 @@ static int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 	 * step two, delete the device extents and the
 	 * chunk tree entries
 	 */
-	ret = btrfs_remove_chunk(trans, fs_info, chunk_offset);
+	ret = btrfs_remove_chunk(trans, chunk_offset);
 	btrfs_end_transaction(trans);
 	return ret;
 }
@@ -3057,7 +2986,7 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 
-			ret = btrfs_force_chunk_alloc(trans, fs_info,
+			ret = btrfs_force_chunk_alloc(trans,
 						      BTRFS_BLOCK_GROUP_DATA);
 			btrfs_end_transaction(trans);
 			if (ret < 0)
@@ -4690,7 +4619,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
 		max_stripe_size = SZ_1G;
-		max_chunk_size = 10 * max_stripe_size;
+		max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS(info);
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
@@ -4898,7 +4827,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	refcount_inc(&em->refs);
 	write_unlock(&em_tree->lock);
 
-	ret = btrfs_make_block_group(trans, info, 0, type, start, num_bytes);
+	ret = btrfs_make_block_group(trans, 0, type, start, num_bytes);
 	if (ret)
 		goto error_del_extent;
 
@@ -4932,9 +4861,9 @@ error:
 }
 
 int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
-				u64 chunk_offset, u64 chunk_size)
+			     u64 chunk_offset, u64 chunk_size)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct btrfs_root *chunk_root = fs_info->chunk_root;
 	struct btrfs_key key;
@@ -5036,13 +4965,12 @@ out:
  * require modifying the chunk tree. This division is important for the
  * bootstrap process of adding storage to a seed btrfs.
  */
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info, u64 type)
+int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type)
 {
 	u64 chunk_offset;
 
-	lockdep_assert_held(&fs_info->chunk_mutex);
-	chunk_offset = find_next_chunk(fs_info);
+	lockdep_assert_held(&trans->fs_info->chunk_mutex);
+	chunk_offset = find_next_chunk(trans->fs_info);
 	return __btrfs_alloc_chunk(trans, chunk_offset, type);
 }
 
@@ -5173,7 +5101,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		/*
 		 * There could be two corrupted data stripes, we need
 		 * to loop retry in order to rebuild the correct data.
-		 * 
+		 *
 		 * Fail a stripe at a time on every retry except the
 		 * stripe under reconstruction.
 		 */
@@ -6185,21 +6113,11 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
 	btrfs_io_bio(bio)->stripe_index = dev_nr;
 	bio->bi_end_io = btrfs_end_bio;
 	bio->bi_iter.bi_sector = physical >> 9;
-#ifdef DEBUG
-	{
-		struct rcu_string *name;
-
-		rcu_read_lock();
-		name = rcu_dereference(dev->name);
-		btrfs_debug(fs_info,
-			"btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
-			bio_op(bio), bio->bi_opf,
-			(u64)bio->bi_iter.bi_sector,
-			(u_long)dev->bdev->bd_dev, name->str, dev->devid,
-			bio->bi_iter.bi_size);
-		rcu_read_unlock();
-	}
-#endif
+	btrfs_debug_in_rcu(fs_info,
+	"btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
+		bio_op(bio), bio->bi_opf, (u64)bio->bi_iter.bi_sector,
+		(u_long)dev->bdev->bd_dev, rcu_str_deref(dev->name), dev->devid,
+		bio->bi_iter.bi_size);
 	bio_set_dev(bio, dev->bdev);
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
@@ -6401,6 +6319,8 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info,
 	u16 num_stripes;
 	u16 sub_stripes;
 	u64 type;
+	u64 features;
+	bool mixed = false;
 
 	length = btrfs_chunk_length(leaf, chunk);
 	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
@@ -6439,6 +6359,32 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info,
 			  btrfs_chunk_type(leaf, chunk));
 		return -EIO;
 	}
+
+	if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) {
+		btrfs_err(fs_info, "missing chunk type flag: 0x%llx", type);
+		return -EIO;
+	}
+
+	if ((type & BTRFS_BLOCK_GROUP_SYSTEM) &&
+	    (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) {
+		btrfs_err(fs_info,
+			"system chunk with data or metadata type: 0x%llx", type);
+		return -EIO;
+	}
+
+	features = btrfs_super_incompat_flags(fs_info->super_copy);
+	if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+		mixed = true;
+
+	if (!mixed) {
+		if ((type & BTRFS_BLOCK_GROUP_METADATA) &&
+		    (type & BTRFS_BLOCK_GROUP_DATA)) {
+			btrfs_err(fs_info,
+			"mixed chunk type in non-mixed mode: 0x%llx", type);
+			return -EIO;
+		}
+	}
+
 	if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||
@@ -6525,6 +6471,7 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	map->stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
 	map->type = btrfs_chunk_type(leaf, chunk);
 	map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
+	map->verified_stripes = 0;
 	for (i = 0; i < num_stripes; i++) {
 		map->stripes[i].physical =
 			btrfs_stripe_offset_nr(leaf, chunk, i);
@@ -6561,10 +6508,14 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	write_lock(&map_tree->map_tree.lock);
 	ret = add_extent_mapping(&map_tree->map_tree, em, 0);
 	write_unlock(&map_tree->map_tree.lock);
-	BUG_ON(ret); /* Tree corruption */
+	if (ret < 0) {
+		btrfs_err(fs_info,
+			  "failed to add chunk map, start=%llu len=%llu: %d",
+			  em->start, em->len, ret);
+	}
 	free_extent_map(em);
 
-	return 0;
+	return ret;
 }
 
 static void fill_device_from_item(struct extent_buffer *leaf,
@@ -7106,9 +7057,9 @@ out:
 }
 
 static int update_dev_stat_item(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				struct btrfs_device *device)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *dev_root = fs_info->dev_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
@@ -7201,7 +7152,7 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
 		 */
 		smp_rmb();
 
-		ret = update_dev_stat_item(trans, fs_info, device);
+		ret = update_dev_stat_item(trans, device);
 		if (!ret)
 			atomic_sub(stats_cnt, &device->dev_stats_ccnt);
 	}
@@ -7380,3 +7331,197 @@ void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info)
 		fs_devices = fs_devices->seed;
 	}
 }
+
+/*
+ * Multiplicity factor for simple profiles: DUP, RAID1-like and RAID10.
+ */
+int btrfs_bg_type_to_factor(u64 flags)
+{
+	if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
+		     BTRFS_BLOCK_GROUP_RAID10))
+		return 2;
+	return 1;
+}
+
+
+static u64 calc_stripe_length(u64 type, u64 chunk_len, int num_stripes)
+{
+	int index = btrfs_bg_flags_to_raid_index(type);
+	int ncopies = btrfs_raid_array[index].ncopies;
+	int data_stripes;
+
+	switch (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+	case BTRFS_BLOCK_GROUP_RAID5:
+		data_stripes = num_stripes - 1;
+		break;
+	case BTRFS_BLOCK_GROUP_RAID6:
+		data_stripes = num_stripes - 2;
+		break;
+	default:
+		data_stripes = num_stripes / ncopies;
+		break;
+	}
+	return div_u64(chunk_len, data_stripes);
+}
+
+static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
+				 u64 chunk_offset, u64 devid,
+				 u64 physical_offset, u64 physical_len)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+	struct extent_map *em;
+	struct map_lookup *map;
+	u64 stripe_len;
+	bool found = false;
+	int ret = 0;
+	int i;
+
+	read_lock(&em_tree->lock);
+	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
+	read_unlock(&em_tree->lock);
+
+	if (!em) {
+		btrfs_err(fs_info,
+"dev extent physical offset %llu on devid %llu doesn't have corresponding chunk",
+			  physical_offset, devid);
+		ret = -EUCLEAN;
+		goto out;
+	}
+
+	map = em->map_lookup;
+	stripe_len = calc_stripe_length(map->type, em->len, map->num_stripes);
+	if (physical_len != stripe_len) {
+		btrfs_err(fs_info,
+"dev extent physical offset %llu on devid %llu length doesn't match chunk %llu, have %llu expect %llu",
+			  physical_offset, devid, em->start, physical_len,
+			  stripe_len);
+		ret = -EUCLEAN;
+		goto out;
+	}
+
+	for (i = 0; i < map->num_stripes; i++) {
+		if (map->stripes[i].dev->devid == devid &&
+		    map->stripes[i].physical == physical_offset) {
+			found = true;
+			if (map->verified_stripes >= map->num_stripes) {
+				btrfs_err(fs_info,
+				"too many dev extents for chunk %llu found",
+					  em->start);
+				ret = -EUCLEAN;
+				goto out;
+			}
+			map->verified_stripes++;
+			break;
+		}
+	}
+	if (!found) {
+		btrfs_err(fs_info,
+	"dev extent physical offset %llu devid %llu has no corresponding chunk",
+			physical_offset, devid);
+		ret = -EUCLEAN;
+	}
+out:
+	free_extent_map(em);
+	return ret;
+}
+
+static int verify_chunk_dev_extent_mapping(struct btrfs_fs_info *fs_info)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+	struct extent_map *em;
+	struct rb_node *node;
+	int ret = 0;
+
+	read_lock(&em_tree->lock);
+	for (node = rb_first(&em_tree->map); node; node = rb_next(node)) {
+		em = rb_entry(node, struct extent_map, rb_node);
+		if (em->map_lookup->num_stripes !=
+		    em->map_lookup->verified_stripes) {
+			btrfs_err(fs_info,
+			"chunk %llu has missing dev extent, have %d expect %d",
+				  em->start, em->map_lookup->verified_stripes,
+				  em->map_lookup->num_stripes);
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+out:
+	read_unlock(&em_tree->lock);
+	return ret;
+}
+
+/*
+ * Ensure that all dev extents are mapped to correct chunk, otherwise
+ * later chunk allocation/free would cause unexpected behavior.
+ *
+ * NOTE: This will iterate through the whole device tree, which should be of
+ * the same size level as the chunk tree.  This slightly increases mount time.
+ */
+int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_path *path;
+	struct btrfs_root *root = fs_info->dev_root;
+	struct btrfs_key key;
+	int ret = 0;
+
+	key.objectid = 1;
+	key.type = BTRFS_DEV_EXTENT_KEY;
+	key.offset = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	path->reada = READA_FORWARD;
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
+		ret = btrfs_next_item(root, path);
+		if (ret < 0)
+			goto out;
+		/* No dev extents at all? Not good */
+		if (ret > 0) {
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+	while (1) {
+		struct extent_buffer *leaf = path->nodes[0];
+		struct btrfs_dev_extent *dext;
+		int slot = path->slots[0];
+		u64 chunk_offset;
+		u64 physical_offset;
+		u64 physical_len;
+		u64 devid;
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.type != BTRFS_DEV_EXTENT_KEY)
+			break;
+		devid = key.objectid;
+		physical_offset = key.offset;
+
+		dext = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
+		chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dext);
+		physical_len = btrfs_dev_extent_length(leaf, dext);
+
+		ret = verify_one_dev_extent(fs_info, chunk_offset, devid,
+					    physical_offset, physical_len);
+		if (ret < 0)
+			goto out;
+		ret = btrfs_next_item(root, path);
+		if (ret < 0)
+			goto out;
+		if (ret > 0) {
+			ret = 0;
+			break;
+		}
+	}
+
+	/* Ensure all chunks have corresponding dev extents */
+	ret = verify_chunk_dev_extent_mapping(fs_info);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 5139ec8daf4c..23e9285d88de 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -11,6 +11,8 @@
 #include <linux/btrfs.h>
 #include "async-thread.h"
 
+#define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
+
 extern struct mutex uuid_mutex;
 
 #define BTRFS_STRIPE_LEN	SZ_64K
@@ -343,6 +345,7 @@ struct map_lookup {
 	u64 stripe_len;
 	int num_stripes;
 	int sub_stripes;
+	int verified_stripes; /* For mount time dev extent verification */
 	struct btrfs_bio_stripe stripes[];
 };
 
@@ -382,8 +385,6 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio)
 	}
 }
 
-int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
-				   u64 end, u64 *length);
 void btrfs_get_bbio(struct btrfs_bio *bbio);
 void btrfs_put_bbio(struct btrfs_bio *bbio);
 int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
@@ -396,20 +397,19 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 		     u64 physical, u64 **logical, int *naddrs, int *stripe_len);
 int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info, u64 type);
+int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);
 void btrfs_mapping_init(struct btrfs_mapping_tree *tree);
 void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree);
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			   int mirror_num, int async_submit);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       fmode_t flags, void *holder);
-int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
-			  struct btrfs_fs_devices **fs_devices_ret);
+struct btrfs_device *btrfs_scan_one_device(const char *path,
+					   fmode_t flags, void *holder);
 int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
 void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step);
-void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
-		struct btrfs_device *device, struct btrfs_device *this_dev);
+void btrfs_assign_next_active_device(struct btrfs_device *device,
+				     struct btrfs_device *this_dev);
 int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
 					 const char *device_path,
 					 struct btrfs_device **device);
@@ -453,22 +453,18 @@ void btrfs_init_devices_late(struct btrfs_fs_info *fs_info);
 int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info);
 int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info);
-void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
-					struct btrfs_device *srcdev);
+void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev);
 void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 				      struct btrfs_device *srcdev);
-void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				      struct btrfs_device *tgtdev);
+void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev);
 void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path);
 int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
 			   u64 logical, u64 len);
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    u64 logical);
 int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
-				u64 chunk_offset, u64 chunk_size);
-int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 chunk_offset);
+			     u64 chunk_offset, u64 chunk_size);
+int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
 
 static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
 				      int index)
@@ -560,4 +556,7 @@ void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info);
 bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 					struct btrfs_device *failing_dev);
 
+int btrfs_bg_type_to_factor(u64 flags);
+int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info);
+
 #endif
diff --git a/fs/buffer.c b/fs/buffer.c
index cabc045f483d..c8c2b7d8b8d6 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1900,15 +1900,16 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
 		break;
 	case IOMAP_UNWRITTEN:
 		/*
-		 * For unwritten regions, we always need to ensure that
-		 * sub-block writes cause the regions in the block we are not
-		 * writing to are zeroed. Set the buffer as new to ensure this.
+		 * For unwritten regions, we always need to ensure that regions
+		 * in the block we are not writing to are zeroed. Mark the
+		 * buffer as new to ensure this.
 		 */
 		set_buffer_new(bh);
 		set_buffer_unwritten(bh);
 		/* FALLTHRU */
 	case IOMAP_MAPPED:
-		if (offset >= i_size_read(inode))
+		if ((iomap->flags & IOMAP_F_NEW) ||
+		    offset >= i_size_read(inode))
 			set_buffer_new(bh);
 		bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
 				inode->i_blkbits;
@@ -2076,6 +2077,40 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 }
 EXPORT_SYMBOL(block_write_begin);
 
+int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
+		struct page *page)
+{
+	loff_t old_size = inode->i_size;
+	bool i_size_changed = false;
+
+	/*
+	 * No need to use i_size_read() here, the i_size cannot change under us
+	 * because we hold i_rwsem.
+	 *
+	 * But it's important to update i_size while still holding page lock:
+	 * page writeout could otherwise come in and zero beyond i_size.
+	 */
+	if (pos + copied > inode->i_size) {
+		i_size_write(inode, pos + copied);
+		i_size_changed = true;
+	}
+
+	unlock_page(page);
+	put_page(page);
+
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (i_size_changed)
+		mark_inode_dirty(inode);
+	return copied;
+}
+
 int block_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
@@ -2116,39 +2151,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
 {
-	struct inode *inode = mapping->host;
-	loff_t old_size = inode->i_size;
-	int i_size_changed = 0;
-
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
-
-	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold i_mutex.
-	 *
-	 * But it's important to update i_size while still holding page lock:
-	 * page writeout could otherwise come in and zero beyond i_size.
-	 */
-	if (pos+copied > inode->i_size) {
-		i_size_write(inode, pos+copied);
-		i_size_changed = 1;
-	}
-
-	unlock_page(page);
-	put_page(page);
-
-	if (old_size < pos)
-		pagecache_isize_extended(inode, old_size, pos);
-	/*
-	 * Don't mark the inode dirty under page lock. First, it unnecessarily
-	 * makes the holding time of page lock longer. Second, it forces lock
-	 * ordering of page lock and transaction start for journaling
-	 * filesystems.
-	 */
-	if (i_size_changed)
-		mark_inode_dirty(inode);
-
-	return copied;
+	return __generic_write_end(mapping->host, pos, copied, page);
 }
 EXPORT_SYMBOL(generic_write_end);
 
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index d9f001078e08..4a717d400807 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -218,7 +218,8 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
 			   "%s",
 			   fsdef->dentry->d_sb->s_id);
 
-	fscache_object_init(&fsdef->fscache, NULL, &cache->cache);
+	fscache_object_init(&fsdef->fscache, &fscache_fsdef_index,
+			    &cache->cache);
 
 	ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag);
 	if (ret < 0)
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index ab0bbe93b398..af2b17b21b94 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -186,12 +186,12 @@ try_again:
 	 * need to wait for it to be destroyed */
 wait_for_old_object:
 	trace_cachefiles_wait_active(object, dentry, xobject);
+	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
 
 	if (fscache_object_is_live(&xobject->fscache)) {
 		pr_err("\n");
 		pr_err("Error: Unexpected object collision\n");
 		cachefiles_printk_object(object, xobject);
-		BUG();
 	}
 	atomic_inc(&xobject->usage);
 	write_unlock(&cache->active_lock);
@@ -248,7 +248,6 @@ wait_for_old_object:
 	goto try_again;
 
 requeue:
-	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
 	cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo);
 	_leave(" = -ETIMEDOUT");
 	return -ETIMEDOUT;
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 5082c8a49686..40f7595aad10 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -27,6 +27,7 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 	struct cachefiles_one_read *monitor =
 		container_of(wait, struct cachefiles_one_read, monitor);
 	struct cachefiles_object *object;
+	struct fscache_retrieval *op = monitor->op;
 	struct wait_bit_key *key = _key;
 	struct page *page = wait->private;
 
@@ -51,16 +52,22 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 	list_del(&wait->entry);
 
 	/* move onto the action list and queue for FS-Cache thread pool */
-	ASSERT(monitor->op);
+	ASSERT(op);
 
-	object = container_of(monitor->op->op.object,
-			      struct cachefiles_object, fscache);
+	/* We need to temporarily bump the usage count as we don't own a ref
+	 * here otherwise cachefiles_read_copier() may free the op between the
+	 * monitor being enqueued on the op->to_do list and the op getting
+	 * enqueued on the work queue.
+	 */
+	fscache_get_retrieval(op);
 
+	object = container_of(op->op.object, struct cachefiles_object, fscache);
 	spin_lock(&object->work_lock);
-	list_add_tail(&monitor->op_link, &monitor->op->to_do);
+	list_add_tail(&monitor->op_link, &op->to_do);
 	spin_unlock(&object->work_lock);
 
-	fscache_enqueue_retrieval(monitor->op);
+	fscache_enqueue_retrieval(op);
+	fscache_put_retrieval(op);
 	return 0;
 }
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ad0bed99b1d5..e2679e8a2535 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -429,8 +429,7 @@ out:
  * file or symlink, return 1 so the VFS can retry.
  */
 int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
-		     struct file *file, unsigned flags, umode_t mode,
-		     int *opened)
+		     struct file *file, unsigned flags, umode_t mode)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -507,9 +506,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		dout("atomic_open finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
 			ceph_init_inode_acls(d_inode(dentry), &acls);
-			*opened |= FILE_CREATED;
+			file->f_mode |= FMODE_CREATED;
 		}
-		err = finish_open(file, dentry, ceph_open, opened);
+		err = finish_open(file, dentry, ceph_open);
 	}
 out_req:
 	if (!req->r_err && req->r_target_inode)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index ee764ac352ab..a866be999216 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1135,6 +1135,7 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in)
 	if (IS_ERR(realdn)) {
 		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
 		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
+		dput(dn);
 		dn = realdn; /* note realdn contains the error */
 		goto out;
 	} else if (realdn) {
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index a7077a0c989f..971328b99ede 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1025,8 +1025,7 @@ extern const struct file_operations ceph_file_fops;
 extern int ceph_renew_caps(struct inode *inode);
 extern int ceph_open(struct inode *inode, struct file *file);
 extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
-			    struct file *file, unsigned flags, umode_t mode,
-			    int *opened);
+			    struct file *file, unsigned flags, umode_t mode);
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 5f132d59dfc2..35c83fe7dba0 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -16,24 +16,28 @@ config CIFS
 	select CRYPTO_DES
 	help
 	  This is the client VFS module for the SMB3 family of NAS protocols,
-	  as well as for earlier dialects such as SMB2.1, SMB2 and the
+	  (including support for the most recent, most secure dialect SMB3.1.1)
+	  as well as for earlier dialects such as SMB2.1, SMB2 and the older
 	  Common Internet File System (CIFS) protocol.  CIFS was the successor
 	  to the original dialect, the Server Message Block (SMB) protocol, the
 	  native file sharing mechanism for most early PC operating systems.
 
-	  The SMB3 protocol is supported by most modern operating systems and
-	  NAS appliances (e.g. Samba, Windows 8, Windows 2012, MacOS).
+	  The SMB3 protocol is supported by most modern operating systems
+	  and NAS appliances (e.g. Samba, Windows 10, Windows Server 2016,
+	  MacOS) and even in the cloud (e.g. Microsoft Azure).
 	  The older CIFS protocol was included in Windows NT4, 2000 and XP (and
 	  later) as well by Samba (which provides excellent CIFS and SMB3
-	  server support for Linux and many other operating systems). Limited
-	  support for OS/2 and Windows ME and similar very old servers is
-	  provided as well.
+	  server support for Linux and many other operating systems). Use of
+	  dialects older than SMB2.1 is often discouraged on public networks.
+	  This module also provides limited support for OS/2 and Windows ME
+	  and similar very old servers.
 
-	  The cifs module provides an advanced network file system client
+	  This module provides an advanced network file system client
 	  for mounting to SMB3 (and CIFS) compliant servers.  It includes
 	  support for DFS (hierarchical name space), secure per-user
-	  session establishment via Kerberos or NTLM or NTLMv2,
-	  safe distributed caching (oplock), optional packet
+	  session establishment via Kerberos or NTLM or NTLMv2, RDMA
+	  (smbdirect), advanced security features, per-share encryption,
+	  directory leases, safe distributed caching (oplock), optional packet
 	  signing, Unicode and other internationalization improvements.
 
 	  In general, the default dialects, SMB3 and later, enable better
@@ -43,18 +47,11 @@ config CIFS
 	  than SMB3 mounts. SMB2/SMB3 mount options are also
 	  slightly simpler (compared to CIFS) due to protocol improvements.
 
-	  If you need to mount to Samba, Macs or Windows from this machine, say Y.
-
-config CIFS_STATS
-        bool "CIFS statistics"
-        depends on CIFS
-        help
-          Enabling this option will cause statistics for each server share
-	  mounted by the cifs client to be displayed in /proc/fs/cifs/Stats
+	  If you need to mount to Samba, Azure, Macs or Windows from this machine, say Y.
 
 config CIFS_STATS2
 	bool "Extended statistics"
-	depends on CIFS_STATS
+	depends on CIFS
 	help
 	  Enabling this option will allow more detailed statistics on SMB
 	  request timing to be displayed in /proc/fs/cifs/DebugData and also
@@ -66,9 +63,24 @@ config CIFS_STATS2
 	  Unless you are a developer or are doing network performance analysis
 	  or tuning, say N.
 
+config CIFS_ALLOW_INSECURE_LEGACY
+	bool "Support legacy servers which use less secure dialects"
+	depends on CIFS
+	default y
+	help
+	  Modern dialects, SMB2.1 and later (including SMB3 and 3.1.1), have
+	  additional security features, including protection against
+	  man-in-the-middle attacks and stronger crypto hashes, so the use
+	  of legacy dialects (SMB1/CIFS and SMB2.0) is discouraged.
+
+	  Disabling this option prevents users from using vers=1.0 or vers=2.0
+	  on mounts with cifs.ko
+
+	  If unsure, say Y.
+
 config CIFS_WEAK_PW_HASH
 	bool "Support legacy servers which use weaker LANMAN security"
-	depends on CIFS
+	depends on CIFS && CIFS_ALLOW_INSECURE_LEGACY
 	help
 	  Modern CIFS servers including Samba and most Windows versions
 	  (since 1997) support stronger NTLM (and even NTLMv2 and Kerberos)
@@ -186,15 +198,6 @@ config CIFS_NFSD_EXPORT
 	  help
 	   Allows NFS server to export a CIFS mounted share (nfsd over cifs)
 
-config CIFS_SMB311
-	bool "SMB3.1.1 network file system support"
-	depends on CIFS
-	select CRYPTO_SHA512
-
-	help
-	  This enables support for the newest, and most secure dialect, SMB3.11.
-	  If unsure, say Y
-
 config CIFS_SMB_DIRECT
 	bool "SMB Direct support (Experimental)"
 	depends on CIFS=m && INFINIBAND && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND=y && INFINIBAND_ADDR_TRANS=y
diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c
index e1553d1e0e50..b7420e605b28 100644
--- a/fs/cifs/cache.c
+++ b/fs/cifs/cache.c
@@ -128,8 +128,10 @@ fscache_checkaux cifs_fscache_inode_check_aux(void *cookie_netfs_data,
 
 	memset(&auxdata, 0, sizeof(auxdata));
 	auxdata.eof = cifsi->server_eof;
-	auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
-	auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
+	auxdata.last_write_time_sec = cifsi->vfs_inode.i_mtime.tv_sec;
+	auxdata.last_change_time_sec = cifsi->vfs_inode.i_ctime.tv_sec;
+	auxdata.last_write_time_nsec = cifsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata.last_change_time_nsec = cifsi->vfs_inode.i_ctime.tv_nsec;
 
 	if (memcmp(data, &auxdata, datalen) != 0)
 		return FSCACHE_CHECKAUX_OBSOLETE;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index bfe999505815..f1fbea947fef 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -160,25 +160,41 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "CIFS Version %s\n", CIFS_VERSION);
 	seq_printf(m, "Features:");
 #ifdef CONFIG_CIFS_DFS_UPCALL
-	seq_printf(m, " dfs");
+	seq_printf(m, " DFS");
 #endif
 #ifdef CONFIG_CIFS_FSCACHE
-	seq_printf(m, " fscache");
+	seq_printf(m, ",FSCACHE");
+#endif
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	seq_printf(m, ",SMB_DIRECT");
+#endif
+#ifdef CONFIG_CIFS_STATS2
+	seq_printf(m, ",STATS2");
+#else
+	seq_printf(m, ",STATS");
+#endif
+#ifdef CONFIG_CIFS_DEBUG2
+	seq_printf(m, ",DEBUG2");
+#elif defined(CONFIG_CIFS_DEBUG)
+	seq_printf(m, ",DEBUG");
+#endif
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
+	seq_printf(m, ",ALLOW_INSECURE_LEGACY");
 #endif
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
-	seq_printf(m, " lanman");
+	seq_printf(m, ",WEAK_PW_HASH");
 #endif
 #ifdef CONFIG_CIFS_POSIX
-	seq_printf(m, " posix");
+	seq_printf(m, ",CIFS_POSIX");
 #endif
 #ifdef CONFIG_CIFS_UPCALL
-	seq_printf(m, " spnego");
+	seq_printf(m, ",UPCALL(SPNEGO)");
 #endif
 #ifdef CONFIG_CIFS_XATTR
-	seq_printf(m, " xattr");
+	seq_printf(m, ",XATTR");
 #endif
 #ifdef CONFIG_CIFS_ACL
-	seq_printf(m, " acl");
+	seq_printf(m, ",ACL");
 #endif
 	seq_putc(m, '\n');
 	seq_printf(m, "Active VFS Requests: %d\n", GlobalTotalActiveXid);
@@ -259,10 +275,9 @@ skip_rdma:
 			server->credits,  server->dialect);
 		if (server->sign)
 			seq_printf(m, " signed");
-#ifdef CONFIG_CIFS_SMB311
 		if (server->posix_ext_supported)
 			seq_printf(m, " posix");
-#endif /* 3.1.1 */
+
 		i++;
 		list_for_each(tmp2, &server->smb_ses_list) {
 			ses = list_entry(tmp2, struct cifs_ses,
@@ -350,7 +365,6 @@ skip_rdma:
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_STATS
 static ssize_t cifs_stats_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
@@ -364,13 +378,23 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 	rc = kstrtobool_from_user(buffer, count, &bv);
 	if (rc == 0) {
 #ifdef CONFIG_CIFS_STATS2
+		int i;
+
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
 #endif /* CONFIG_CIFS_STATS2 */
+		spin_lock(&GlobalMid_Lock);
+		GlobalMaxActiveXid = 0;
+		GlobalCurrentXid = 0;
+		spin_unlock(&GlobalMid_Lock);
 		spin_lock(&cifs_tcp_ses_lock);
 		list_for_each(tmp1, &cifs_tcp_ses_list) {
 			server = list_entry(tmp1, struct TCP_Server_Info,
 					    tcp_ses_list);
+#ifdef CONFIG_CIFS_STATS2
+			for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++)
+				atomic_set(&server->smb2slowcmd[i], 0);
+#endif /* CONFIG_CIFS_STATS2 */
 			list_for_each(tmp2, &server->smb_ses_list) {
 				ses = list_entry(tmp2, struct cifs_ses,
 						 smb_ses_list);
@@ -379,6 +403,10 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 							  struct cifs_tcon,
 							  tcon_list);
 					atomic_set(&tcon->num_smbs_sent, 0);
+					spin_lock(&tcon->stat_lock);
+					tcon->bytes_read = 0;
+					tcon->bytes_written = 0;
+					spin_unlock(&tcon->stat_lock);
 					if (server->ops->clear_stats)
 						server->ops->clear_stats(tcon);
 				}
@@ -395,13 +423,15 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 static int cifs_stats_proc_show(struct seq_file *m, void *v)
 {
 	int i;
+#ifdef CONFIG_CIFS_STATS2
+	int j;
+#endif /* STATS2 */
 	struct list_head *tmp1, *tmp2, *tmp3;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 
-	seq_printf(m,
-			"Resources in use\nCIFS Session: %d\n",
+	seq_printf(m, "Resources in use\nCIFS Session: %d\n",
 			sesInfoAllocCount.counter);
 	seq_printf(m, "Share (unique mount targets): %d\n",
 			tconInfoAllocCount.counter);
@@ -430,6 +460,13 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
 	list_for_each(tmp1, &cifs_tcp_ses_list) {
 		server = list_entry(tmp1, struct TCP_Server_Info,
 				    tcp_ses_list);
+#ifdef CONFIG_CIFS_STATS2
+		for (j = 0; j < NUMBER_OF_SMB2_COMMANDS; j++)
+			if (atomic_read(&server->smb2slowcmd[j]))
+				seq_printf(m, "%d slow responses from %s for command %d\n",
+					atomic_read(&server->smb2slowcmd[j]),
+					server->hostname, j);
+#endif /* STATS2 */
 		list_for_each(tmp2, &server->smb_ses_list) {
 			ses = list_entry(tmp2, struct cifs_ses,
 					 smb_ses_list);
@@ -466,7 +503,6 @@ static const struct file_operations cifs_stats_proc_fops = {
 	.release	= single_release,
 	.write		= cifs_stats_proc_write,
 };
-#endif /* STATS */
 
 #ifdef CONFIG_CIFS_SMB_DIRECT
 #define PROC_FILE_DEFINE(name) \
@@ -524,9 +560,7 @@ cifs_proc_init(void)
 	proc_create_single("DebugData", 0, proc_fs_cifs,
 			cifs_debug_data_proc_show);
 
-#ifdef CONFIG_CIFS_STATS
 	proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops);
-#endif /* STATS */
 	proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops);
 	proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops);
 	proc_create("LinuxExtensionsEnabled", 0644, proc_fs_cifs,
@@ -564,9 +598,7 @@ cifs_proc_clean(void)
 	remove_proc_entry("DebugData", proc_fs_cifs);
 	remove_proc_entry("cifsFYI", proc_fs_cifs);
 	remove_proc_entry("traceSMB", proc_fs_cifs);
-#ifdef CONFIG_CIFS_STATS
 	remove_proc_entry("Stats", proc_fs_cifs);
-#endif
 	remove_proc_entry("SecurityFlags", proc_fs_cifs);
 	remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs);
 	remove_proc_entry("LookupCacheEnabled", proc_fs_cifs);
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index ee2a8ec70056..85b31cfa2f3c 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -83,7 +83,13 @@ int __cifs_calc_signature(struct smb_rqst *rqst,
 
 		kaddr = (char *) kmap(rqst->rq_pages[i]) + offset;
 
-		crypto_shash_update(shash, kaddr, len);
+		rc = crypto_shash_update(shash, kaddr, len);
+		if (rc) {
+			cifs_dbg(VFS, "%s: Could not update with payload\n",
+				 __func__);
+			kunmap(rqst->rq_pages[i]);
+			return rc;
+		}
 
 		kunmap(rqst->rq_pages[i]);
 	}
@@ -452,7 +458,7 @@ find_timestamp(struct cifs_ses *ses)
 	unsigned char *blobptr;
 	unsigned char *blobend;
 	struct ntlmssp2_name *attrptr;
-	struct timespec ts;
+	struct timespec64 ts;
 
 	if (!ses->auth_key.len || !ses->auth_key.response)
 		return 0;
@@ -477,7 +483,7 @@ find_timestamp(struct cifs_ses *ses)
 		blobptr += attrsize; /* advance attr value */
 	}
 
-	ktime_get_real_ts(&ts);
+	ktime_get_real_ts64(&ts);
 	return cpu_to_le64(cifs_UnixTimeToNT(ts));
 }
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index d5aa7ae917bf..7065426b3280 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -139,6 +139,9 @@ cifs_read_super(struct super_block *sb)
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL)
 		sb->s_flags |= SB_POSIXACL;
 
+	if (tcon->snapshot_time)
+		sb->s_flags |= SB_RDONLY;
+
 	if (tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files)
 		sb->s_maxbytes = MAX_LFS_FILESIZE;
 	else
@@ -209,14 +212,16 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	xid = get_xid();
 
-	/*
-	 * PATH_MAX may be too long - it would presumably be total path,
-	 * but note that some servers (includinng Samba 3) have a shorter
-	 * maximum path.
-	 *
-	 * Instead could get the real value via SMB_QUERY_FS_ATTRIBUTE_INFO.
-	 */
-	buf->f_namelen = PATH_MAX;
+	if (le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength) > 0)
+		buf->f_namelen =
+		       le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength);
+	else
+		buf->f_namelen = PATH_MAX;
+
+	buf->f_fsid.val[0] = tcon->vol_serial_number;
+	/* are using part of create time for more randomness, see man statfs */
+	buf->f_fsid.val[1] =  (int)le64_to_cpu(tcon->vol_create_time);
+
 	buf->f_files = 0;	/* undefined */
 	buf->f_ffree = 0;	/* unlimited */
 
@@ -427,7 +432,7 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	else if (tcon->ses->user_name)
 		seq_show_option(s, "username", tcon->ses->user_name);
 
-	if (tcon->ses->domainName)
+	if (tcon->ses->domainName && tcon->ses->domainName[0] != 0)
 		seq_show_option(s, "domain", tcon->ses->domainName);
 
 	if (srcaddr->sa_family != AF_UNSPEC) {
@@ -481,20 +486,12 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",persistenthandles");
 	else if (tcon->use_resilient)
 		seq_puts(s, ",resilienthandles");
-
-#ifdef CONFIG_CIFS_SMB311
 	if (tcon->posix_extensions)
 		seq_puts(s, ",posix");
 	else if (tcon->unix_ext)
 		seq_puts(s, ",unix");
 	else
 		seq_puts(s, ",nounix");
-#else
-	if (tcon->unix_ext)
-		seq_puts(s, ",unix");
-	else
-		seq_puts(s, ",nounix");
-#endif /* SMB311 */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
 		seq_puts(s, ",posixpaths");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
@@ -546,6 +543,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	seq_printf(s, ",wsize=%u", cifs_sb->wsize);
 	seq_printf(s, ",echo_interval=%lu",
 			tcon->ses->server->echo_interval / HZ);
+	if (tcon->snapshot_time)
+		seq_printf(s, ",snapshot=%llu", tcon->snapshot_time);
 	/* convert actimeo and display it in seconds */
 	seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
 
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 5f0231803431..f3a78efc3109 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -65,8 +65,7 @@ extern struct inode *cifs_root_iget(struct super_block *);
 extern int cifs_create(struct inode *, struct dentry *, umode_t,
 		       bool excl);
 extern int cifs_atomic_open(struct inode *, struct dentry *,
-			    struct file *, unsigned, umode_t,
-			    int *);
+			    struct file *, unsigned, umode_t);
 extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
 				  unsigned int);
 extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index bd78da59a4fd..0c9ab62c3df4 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -76,6 +76,9 @@
 #define SMB_ECHO_INTERVAL_MAX 600
 #define SMB_ECHO_INTERVAL_DEFAULT 60
 
+/* maximum number of PDUs in one compound */
+#define MAX_COMPOUND 5
+
 /*
  * Default number of credits to keep available for SMB3.
  * This value is chosen somewhat arbitrarily. The Windows client
@@ -191,9 +194,7 @@ enum smb_version {
 	Smb_21,
 	Smb_30,
 	Smb_302,
-#ifdef CONFIG_CIFS_SMB311
 	Smb_311,
-#endif /* SMB311 */
 	Smb_3any,
 	Smb_default,
 	Smb_version_err
@@ -423,7 +424,7 @@ struct smb_version_operations {
 	void (*set_oplock_level)(struct cifsInodeInfo *, __u32, unsigned int,
 				 bool *);
 	/* create lease context buffer for CREATE request */
-	char * (*create_lease_buf)(u8 *, u8);
+	char * (*create_lease_buf)(u8 *lease_key, u8 oplock);
 	/* parse lease context buffer and return oplock/epoch info */
 	__u8 (*parse_lease_buf)(void *buf, unsigned int *epoch, char *lkey);
 	ssize_t (*copychunk_range)(const unsigned int,
@@ -456,13 +457,11 @@ struct smb_version_operations {
 	long (*fallocate)(struct file *, struct cifs_tcon *, int, loff_t,
 			  loff_t);
 	/* init transform request - used for encryption for now */
-	int (*init_transform_rq)(struct TCP_Server_Info *, struct smb_rqst *,
-				 struct smb_rqst *);
-	/* free transform request */
-	void (*free_transform_rq)(struct smb_rqst *);
+	int (*init_transform_rq)(struct TCP_Server_Info *, int num_rqst,
+				 struct smb_rqst *, struct smb_rqst *);
 	int (*is_transform_hdr)(void *buf);
 	int (*receive_transform)(struct TCP_Server_Info *,
-				 struct mid_q_entry **);
+				 struct mid_q_entry **, char **, int *);
 	enum securityEnum (*select_sectype)(struct TCP_Server_Info *,
 			    enum securityEnum);
 	int (*next_header)(char *);
@@ -684,15 +683,14 @@ struct TCP_Server_Info {
 #ifdef CONFIG_CIFS_STATS2
 	atomic_t in_send; /* requests trying to send */
 	atomic_t num_waiters;   /* blocked waiting to get in sendrecv */
-#endif
+	atomic_t smb2slowcmd[NUMBER_OF_SMB2_COMMANDS]; /* count resps > 1 sec */
+#endif /* STATS2 */
 	unsigned int	max_read;
 	unsigned int	max_write;
-#ifdef CONFIG_CIFS_SMB311
 	__le16	cipher_type;
 	 /* save initital negprot hash */
 	__u8	preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
 	bool	posix_ext_supported;
-#endif /* 3.1.1 */
 	struct delayed_work reconnect; /* reconnect workqueue job */
 	struct mutex reconnect_mutex; /* prevent simultaneous reconnects */
 	unsigned long echo_interval;
@@ -886,9 +884,7 @@ struct cifs_ses {
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
-#ifdef CONFIG_CIFS_SMB311
 	__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
-#endif /* 3.1.1 */
 
 	/*
 	 * Network interfaces available on the server this session is
@@ -913,6 +909,7 @@ cap_unix(struct cifs_ses *ses)
 
 struct cached_fid {
 	bool is_valid:1;	/* Do we have a useable root fid */
+	struct kref refcount;
 	struct cifs_fid *fid;
 	struct mutex fid_mutex;
 	struct cifs_tcon *tcon;
@@ -936,7 +933,6 @@ struct cifs_tcon {
 	__u32 tid;		/* The 4 byte tree id */
 	__u16 Flags;		/* optional support bits */
 	enum statusEnum tidStatus;
-#ifdef CONFIG_CIFS_STATS
 	atomic_t num_smbs_sent;
 	union {
 		struct {
@@ -967,24 +963,9 @@ struct cifs_tcon {
 			atomic_t smb2_com_failed[NUMBER_OF_SMB2_COMMANDS];
 		} smb2_stats;
 	} stats;
-#ifdef CONFIG_CIFS_STATS2
-	unsigned long long time_writes;
-	unsigned long long time_reads;
-	unsigned long long time_opens;
-	unsigned long long time_deletes;
-	unsigned long long time_closes;
-	unsigned long long time_mkdirs;
-	unsigned long long time_rmdirs;
-	unsigned long long time_renames;
-	unsigned long long time_t2renames;
-	unsigned long long time_ffirst;
-	unsigned long long time_fnext;
-	unsigned long long time_fclose;
-#endif /* CONFIG_CIFS_STATS2 */
 	__u64    bytes_read;
 	__u64    bytes_written;
 	spinlock_t stat_lock;  /* protects the two fields above */
-#endif /* CONFIG_CIFS_STATS */
 	FILE_SYSTEM_DEVICE_INFO fsDevInfo;
 	FILE_SYSTEM_ATTRIBUTE_INFO fsAttrInfo; /* ok if fs name truncated */
 	FILE_SYSTEM_UNIX_INFO fsUnixInfo;
@@ -997,9 +978,7 @@ struct cifs_tcon {
 	bool seal:1;      /* transport encryption for this mounted share */
 	bool unix_ext:1;  /* if false disable Linux extensions to CIFS protocol
 				for this mount even if server would support */
-#ifdef CONFIG_CIFS_SMB311
 	bool posix_extensions; /* if true SMB3.11 posix extensions enabled */
-#endif /* CIFS_311 */
 	bool local_lease:1; /* check leases (only) on local system not remote */
 	bool broken_posix_open; /* e.g. Samba server versions < 3.3.2, 3.2.9 */
 	bool broken_sparse_sup; /* if server or share does not support sparse */
@@ -1046,6 +1025,7 @@ struct tcon_link {
 };
 
 extern struct tcon_link *cifs_sb_tlink(struct cifs_sb_info *cifs_sb);
+extern void smb3_free_compound_rqst(int num_rqst, struct smb_rqst *rqst);
 
 static inline struct cifs_tcon *
 tlink_tcon(struct tcon_link *tlink)
@@ -1352,7 +1332,6 @@ convert_delimiter(char *path, char delim)
 		*pos = delim;
 }
 
-#ifdef CONFIG_CIFS_STATS
 #define cifs_stats_inc atomic_inc
 
 static inline void cifs_stats_bytes_written(struct cifs_tcon *tcon,
@@ -1372,13 +1351,6 @@ static inline void cifs_stats_bytes_read(struct cifs_tcon *tcon,
 	tcon->bytes_read += bytes;
 	spin_unlock(&tcon->stat_lock);
 }
-#else
-
-#define  cifs_stats_inc(field) do {} while (0)
-#define  cifs_stats_bytes_written(tcon, bytes) do {} while (0)
-#define  cifs_stats_bytes_read(tcon, bytes) do {} while (0)
-
-#endif
 
 
 /*
@@ -1416,6 +1388,7 @@ typedef int (mid_handle_t)(struct TCP_Server_Info *server,
 /* one of these for every pending CIFS request to the server */
 struct mid_q_entry {
 	struct list_head qhead;	/* mids waiting on reply from this server */
+	struct kref refcount;
 	struct TCP_Server_Info *server;	/* server corresponding to this mid */
 	__u64 mid;		/* multiplex id */
 	__u32 pid;		/* process id */
@@ -1543,9 +1516,9 @@ struct cifs_fattr {
 	dev_t		cf_rdev;
 	unsigned int	cf_nlink;
 	unsigned int	cf_dtype;
-	struct timespec	cf_atime;
-	struct timespec	cf_mtime;
-	struct timespec	cf_ctime;
+	struct timespec64 cf_atime;
+	struct timespec64 cf_mtime;
+	struct timespec64 cf_ctime;
 };
 
 static inline void free_dfs_info_param(struct dfs_info3_param *param)
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 03018be17283..20adda4de83b 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -82,6 +82,7 @@ extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer,
 					struct TCP_Server_Info *server);
 extern void DeleteMidQEntry(struct mid_q_entry *midEntry);
 extern void cifs_delete_mid(struct mid_q_entry *mid);
+extern void cifs_mid_q_entry_release(struct mid_q_entry *midEntry);
 extern void cifs_wake_up_task(struct mid_q_entry *mid);
 extern int cifs_handle_standard(struct TCP_Server_Info *server,
 				struct mid_q_entry *mid);
@@ -93,6 +94,10 @@ extern int cifs_call_async(struct TCP_Server_Info *server,
 extern int cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 			  struct smb_rqst *rqst, int *resp_buf_type,
 			  const int flags, struct kvec *resp_iov);
+extern int compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
+			      const int flags, const int num_rqst,
+			      struct smb_rqst *rqst, int *resp_buf_type,
+			      struct kvec *resp_iov);
 extern int SendReceive(const unsigned int /* xid */ , struct cifs_ses *,
 			struct smb_hdr * /* input */ ,
 			struct smb_hdr * /* out */ ,
@@ -142,9 +147,9 @@ extern enum securityEnum select_sectype(struct TCP_Server_Info *server,
 				enum securityEnum requested);
 extern int CIFS_SessSetup(const unsigned int xid, struct cifs_ses *ses,
 			  const struct nls_table *nls_cp);
-extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
-extern u64 cifs_UnixTimeToNT(struct timespec);
-extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
+extern struct timespec64 cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
+extern u64 cifs_UnixTimeToNT(struct timespec64);
+extern struct timespec64 cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
 				      int offset);
 extern void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock);
 extern int cifs_get_writer(struct cifsInodeInfo *cinode);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index d352da325de3..dc2f4cf08fe9 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -157,8 +157,14 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command)
 	 * greater than cifs socket timeout which is 7 seconds
 	 */
 	while (server->tcpStatus == CifsNeedReconnect) {
-		wait_event_interruptible_timeout(server->response_q,
-			(server->tcpStatus != CifsNeedReconnect), 10 * HZ);
+		rc = wait_event_interruptible_timeout(server->response_q,
+						      (server->tcpStatus != CifsNeedReconnect),
+						      10 * HZ);
+		if (rc < 0) {
+			cifs_dbg(FYI, "%s: aborting reconnect due to a received"
+				 " signal by the process\n", __func__);
+			return -ERESTARTSYS;
+		}
 
 		/* are we still trying to reconnect? */
 		if (server->tcpStatus != CifsNeedReconnect)
@@ -502,13 +508,13 @@ decode_lanman_negprot_rsp(struct TCP_Server_Info *server, NEGOTIATE_RSP *pSMBr)
 		 * this requirement.
 		 */
 		int val, seconds, remain, result;
-		struct timespec ts;
-		unsigned long utc = ktime_get_real_seconds();
+		struct timespec64 ts;
+		time64_t utc = ktime_get_real_seconds();
 		ts = cnvrtDosUnixTm(rsp->SrvTime.Date,
 				    rsp->SrvTime.Time, 0);
-		cifs_dbg(FYI, "SrvTime %d sec since 1970 (utc: %d) diff: %d\n",
-			 (int)ts.tv_sec, (int)utc,
-			 (int)(utc - ts.tv_sec));
+		cifs_dbg(FYI, "SrvTime %lld sec since 1970 (utc: %lld) diff: %lld\n",
+			 ts.tv_sec, utc,
+			 utc - ts.tv_sec);
 		val = (int)(utc - ts.tv_sec);
 		seconds = abs(val);
 		result = (seconds / MIN_TZ_ADJ) * MIN_TZ_ADJ;
@@ -4076,7 +4082,7 @@ QInfRetry:
 	if (rc) {
 		cifs_dbg(FYI, "Send error in QueryInfo = %d\n", rc);
 	} else if (data) {
-		struct timespec ts;
+		struct timespec64 ts;
 		__u32 time = le32_to_cpu(pSMBr->last_write_time);
 
 		/* decode response */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a57da1b88bdf..c832a8a1970a 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -303,10 +303,8 @@ static const match_table_t cifs_smb_version_tokens = {
 	{ Smb_21, SMB21_VERSION_STRING },
 	{ Smb_30, SMB30_VERSION_STRING },
 	{ Smb_302, SMB302_VERSION_STRING },
-#ifdef CONFIG_CIFS_SMB311
 	{ Smb_311, SMB311_VERSION_STRING },
 	{ Smb_311, ALT_SMB311_VERSION_STRING },
-#endif /* SMB311 */
 	{ Smb_3any, SMB3ANY_VERSION_STRING },
 	{ Smb_default, SMBDEFAULT_VERSION_STRING },
 	{ Smb_version_err, NULL }
@@ -350,6 +348,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	server->max_read = 0;
 
 	cifs_dbg(FYI, "Reconnecting tcp session\n");
+	trace_smb3_reconnect(server->CurrentMid, server->hostname);
 
 	/* before reconnecting the tcp session, mark the smb session (uid)
 		and the tid bad so they are not used until reconnected */
@@ -851,13 +850,14 @@ cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 static int
 cifs_demultiplex_thread(void *p)
 {
-	int length;
+	int i, num_mids, length;
 	struct TCP_Server_Info *server = p;
 	unsigned int pdu_length;
 	unsigned int next_offset;
 	char *buf = NULL;
 	struct task_struct *task_to_wake = NULL;
-	struct mid_q_entry *mid_entry;
+	struct mid_q_entry *mids[MAX_COMPOUND];
+	char *bufs[MAX_COMPOUND];
 
 	current->flags |= PF_MEMALLOC;
 	cifs_dbg(FYI, "Demultiplex PID: %d\n", task_pid_nr(current));
@@ -924,52 +924,75 @@ next_pdu:
 				server->pdu_size = next_offset;
 		}
 
+		memset(mids, 0, sizeof(mids));
+		memset(bufs, 0, sizeof(bufs));
+		num_mids = 0;
+
 		if (server->ops->is_transform_hdr &&
 		    server->ops->receive_transform &&
 		    server->ops->is_transform_hdr(buf)) {
 			length = server->ops->receive_transform(server,
-								&mid_entry);
+								mids,
+								bufs,
+								&num_mids);
 		} else {
-			mid_entry = server->ops->find_mid(server, buf);
+			mids[0] = server->ops->find_mid(server, buf);
+			bufs[0] = buf;
+			if (mids[0])
+				num_mids = 1;
 
-			if (!mid_entry || !mid_entry->receive)
-				length = standard_receive3(server, mid_entry);
+			if (!mids[0] || !mids[0]->receive)
+				length = standard_receive3(server, mids[0]);
 			else
-				length = mid_entry->receive(server, mid_entry);
+				length = mids[0]->receive(server, mids[0]);
 		}
 
-		if (length < 0)
+		if (length < 0) {
+			for (i = 0; i < num_mids; i++)
+				if (mids[i])
+					cifs_mid_q_entry_release(mids[i]);
 			continue;
+		}
 
 		if (server->large_buf)
 			buf = server->bigbuf;
 
+
 		server->lstrp = jiffies;
-		if (mid_entry != NULL) {
-			mid_entry->resp_buf_size = server->pdu_size;
-			if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
-			     mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
-					server->ops->handle_cancelled_mid)
-				server->ops->handle_cancelled_mid(
-							mid_entry->resp_buf,
+
+		for (i = 0; i < num_mids; i++) {
+			if (mids[i] != NULL) {
+				mids[i]->resp_buf_size = server->pdu_size;
+				if ((mids[i]->mid_flags & MID_WAIT_CANCELLED) &&
+				    mids[i]->mid_state == MID_RESPONSE_RECEIVED &&
+				    server->ops->handle_cancelled_mid)
+					server->ops->handle_cancelled_mid(
+							mids[i]->resp_buf,
 							server);
 
-			if (!mid_entry->multiRsp || mid_entry->multiEnd)
-				mid_entry->callback(mid_entry);
-		} else if (server->ops->is_oplock_break &&
-			   server->ops->is_oplock_break(buf, server)) {
-			cifs_dbg(FYI, "Received oplock break\n");
-		} else {
-			cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
-				 atomic_read(&midCount));
-			cifs_dump_mem("Received Data is: ", buf,
-				      HEADER_SIZE(server));
+				if (!mids[i]->multiRsp || mids[i]->multiEnd)
+					mids[i]->callback(mids[i]);
+
+				cifs_mid_q_entry_release(mids[i]);
+			} else if (server->ops->is_oplock_break &&
+				   server->ops->is_oplock_break(bufs[i],
+								server)) {
+				cifs_dbg(FYI, "Received oplock break\n");
+			} else {
+				cifs_dbg(VFS, "No task to wake, unknown frame "
+					 "received! NumMids %d\n",
+					 atomic_read(&midCount));
+				cifs_dump_mem("Received Data is: ", bufs[i],
+					      HEADER_SIZE(server));
 #ifdef CONFIG_CIFS_DEBUG2
-			if (server->ops->dump_detail)
-				server->ops->dump_detail(buf, server);
-			cifs_dump_mids(server);
+				if (server->ops->dump_detail)
+					server->ops->dump_detail(bufs[i],
+								 server);
+				cifs_dump_mids(server);
 #endif /* CIFS_DEBUG2 */
+			}
 		}
+
 		if (pdu_length > server->pdu_size) {
 			if (!allocate_buffers(server))
 				continue;
@@ -1168,6 +1191,7 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3)
 	substring_t args[MAX_OPT_ARGS];
 
 	switch (match_token(value, cifs_smb_version_tokens, args)) {
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	case Smb_1:
 		if (disable_legacy_dialects) {
 			cifs_dbg(VFS, "mount with legacy dialect disabled\n");
@@ -1192,6 +1216,14 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3)
 		vol->ops = &smb20_operations;
 		vol->vals = &smb20_values;
 		break;
+#else
+	case Smb_1:
+		cifs_dbg(VFS, "vers=1.0 (cifs) mount not permitted when legacy dialects disabled\n");
+		return 1;
+	case Smb_20:
+		cifs_dbg(VFS, "vers=2.0 mount not permitted when legacy dialects disabled\n");
+		return 1;
+#endif /* CIFS_ALLOW_INSECURE_LEGACY */
 	case Smb_21:
 		vol->ops = &smb21_operations;
 		vol->vals = &smb21_values;
@@ -1204,12 +1236,10 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3)
 		vol->ops = &smb30_operations; /* currently identical with 3.0 */
 		vol->vals = &smb302_values;
 		break;
-#ifdef CONFIG_CIFS_SMB311
 	case Smb_311:
 		vol->ops = &smb311_operations;
 		vol->vals = &smb311_values;
 		break;
-#endif /* SMB311 */
 	case Smb_3any:
 		vol->ops = &smb30_operations; /* currently identical with 3.0 */
 		vol->vals = &smb3any_values;
@@ -3024,15 +3054,17 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		}
 	}
 
-#ifdef CONFIG_CIFS_SMB311
-	if ((volume_info->linux_ext) && (ses->server->posix_ext_supported)) {
-		if (ses->server->vals->protocol_id == SMB311_PROT_ID) {
+	if (volume_info->linux_ext) {
+		if (ses->server->posix_ext_supported) {
 			tcon->posix_extensions = true;
 			printk_once(KERN_WARNING
 				"SMB3.11 POSIX Extensions are experimental\n");
+		} else {
+			cifs_dbg(VFS, "Server does not support mounting with posix SMB3.11 extensions.\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
 		}
 	}
-#endif /* 311 */
 
 	/*
 	 * BB Do we need to wrap session_mutex around this TCon call and Unix
@@ -3986,11 +4018,9 @@ try_mount_again:
 		goto remote_path_check;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
 	if (tcon->posix_extensions)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-#endif /* SMB3.11 */
 
 	/* tell server which Unix caps we support */
 	if (cap_unix(tcon->ses)) {
@@ -4453,11 +4483,10 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 		goto out;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
 	if (tcon->posix_extensions)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-#endif /* SMB3.11 */
+
 	if (cap_unix(ses))
 		reset_cifs_unix_caps(0, tcon, NULL, vol_info);
 
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index ddae52bd1993..3713d22b95a7 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -465,8 +465,7 @@ out_err:
 
 int
 cifs_atomic_open(struct inode *inode, struct dentry *direntry,
-		 struct file *file, unsigned oflags, umode_t mode,
-		 int *opened)
+		 struct file *file, unsigned oflags, umode_t mode)
 {
 	int rc;
 	unsigned int xid;
@@ -539,9 +538,9 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	}
 
 	if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
-		*opened |= FILE_CREATED;
+		file->f_mode |= FMODE_CREATED;
 
-	rc = finish_open(file, direntry, generic_file_open, opened);
+	rc = finish_open(file, direntry, generic_file_open);
 	if (rc) {
 		if (server->ops->close)
 			server->ops->close(xid, tcon, &fid);
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index 85145a763021..ea6ace9c2417 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -129,8 +129,10 @@ static void cifs_fscache_acquire_inode_cookie(struct cifsInodeInfo *cifsi,
 
 	memset(&auxdata, 0, sizeof(auxdata));
 	auxdata.eof = cifsi->server_eof;
-	auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
-	auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
+	auxdata.last_write_time_sec = cifsi->vfs_inode.i_mtime.tv_sec;
+	auxdata.last_change_time_sec = cifsi->vfs_inode.i_ctime.tv_sec;
+	auxdata.last_write_time_nsec = cifsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata.last_change_time_nsec = cifsi->vfs_inode.i_ctime.tv_nsec;
 
 	cifsi->fscache =
 		fscache_acquire_cookie(tcon->fscache,
@@ -166,8 +168,10 @@ void cifs_fscache_release_inode_cookie(struct inode *inode)
 	if (cifsi->fscache) {
 		memset(&auxdata, 0, sizeof(auxdata));
 		auxdata.eof = cifsi->server_eof;
-		auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
-		auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
+		auxdata.last_write_time_sec = cifsi->vfs_inode.i_mtime.tv_sec;
+		auxdata.last_change_time_sec = cifsi->vfs_inode.i_ctime.tv_sec;
+		auxdata.last_write_time_nsec = cifsi->vfs_inode.i_mtime.tv_nsec;
+		auxdata.last_change_time_nsec = cifsi->vfs_inode.i_ctime.tv_nsec;
 
 		cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cifsi->fscache);
 		fscache_relinquish_cookie(cifsi->fscache, &auxdata, false);
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index c7e3ac251e16..8c0862e41306 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -31,9 +31,11 @@
  * Auxiliary data attached to CIFS inode within the cache
  */
 struct cifs_fscache_inode_auxdata {
-	struct timespec	last_write_time;
-	struct timespec	last_change_time;
-	u64		eof;
+	u64 last_write_time_sec;
+	u64 last_change_time_sec;
+	u32 last_write_time_nsec;
+	u32 last_change_time_nsec;
+	u64 eof;
 };
 
 /*
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a2cfb33e85c1..d32eaa4b2437 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -95,7 +95,6 @@ static void
 cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 {
 	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
-	struct timespec ts;
 
 	cifs_dbg(FYI, "%s: revalidating inode %llu\n",
 		 __func__, cifs_i->uniqueid);
@@ -114,8 +113,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 	}
 
 	 /* revalidate if mtime or size have changed */
-	ts = timespec64_to_timespec(inode->i_mtime);
-	if (timespec_equal(&ts, &fattr->cf_mtime) &&
+	if (timespec64_equal(&inode->i_mtime, &fattr->cf_mtime) &&
 	    cifs_i->server_eof == fattr->cf_eof) {
 		cifs_dbg(FYI, "%s: inode %llu is unchanged\n",
 			 __func__, cifs_i->uniqueid);
@@ -164,9 +162,9 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 	cifs_revalidate_cache(inode, fattr);
 
 	spin_lock(&inode->i_lock);
-	inode->i_atime = timespec_to_timespec64(fattr->cf_atime);
-	inode->i_mtime = timespec_to_timespec64(fattr->cf_mtime);
-	inode->i_ctime = timespec_to_timespec64(fattr->cf_ctime);
+	inode->i_atime = fattr->cf_atime;
+	inode->i_mtime = fattr->cf_mtime;
+	inode->i_ctime = fattr->cf_ctime;
 	inode->i_rdev = fattr->cf_rdev;
 	cifs_nlink_fattr_to_inode(inode, fattr);
 	inode->i_uid = fattr->cf_uid;
@@ -327,8 +325,8 @@ cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb)
 	fattr->cf_mode = S_IFDIR | S_IXUGO | S_IRWXU;
 	fattr->cf_uid = cifs_sb->mnt_uid;
 	fattr->cf_gid = cifs_sb->mnt_gid;
-	ktime_get_real_ts(&fattr->cf_mtime);
-	fattr->cf_mtime = timespec_trunc(fattr->cf_mtime, sb->s_time_gran);
+	ktime_get_real_ts64(&fattr->cf_mtime);
+	fattr->cf_mtime = timespec64_trunc(fattr->cf_mtime, sb->s_time_gran);
 	fattr->cf_atime = fattr->cf_ctime = fattr->cf_mtime;
 	fattr->cf_nlink = 2;
 	fattr->cf_flags |= CIFS_FATTR_DFS_REFERRAL;
@@ -604,8 +602,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 	if (info->LastAccessTime)
 		fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
 	else {
-		ktime_get_real_ts(&fattr->cf_atime);
-		fattr->cf_atime = timespec_trunc(fattr->cf_atime, sb->s_time_gran);
+		ktime_get_real_ts64(&fattr->cf_atime);
+		fattr->cf_atime = timespec64_trunc(fattr->cf_atime, sb->s_time_gran);
 	}
 
 	fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime);
@@ -1122,17 +1120,19 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
 	if (!server->ops->set_file_info)
 		return -ENOSYS;
 
+	info_buf.Pad = 0;
+
 	if (attrs->ia_valid & ATTR_ATIME) {
 		set_time = true;
 		info_buf.LastAccessTime =
-			cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime)));
+			cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
 	} else
 		info_buf.LastAccessTime = 0;
 
 	if (attrs->ia_valid & ATTR_MTIME) {
 		set_time = true;
 		info_buf.LastWriteTime =
-		    cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime)));
+		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
 	} else
 		info_buf.LastWriteTime = 0;
 
@@ -1145,7 +1145,7 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
 	if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
 		cifs_dbg(FYI, "CIFS - CTIME changed\n");
 		info_buf.ChangeTime =
-		    cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime)));
+		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
 	} else
 		info_buf.ChangeTime = 0;
 
@@ -1577,14 +1577,12 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode)
 
 	server = tcon->ses->server;
 
-#ifdef CONFIG_CIFS_SMB311
 	if ((server->ops->posix_mkdir) && (tcon->posix_extensions)) {
 		rc = server->ops->posix_mkdir(xid, inode, mode, tcon, full_path,
 					      cifs_sb);
 		d_drop(direntry); /* for time being always refresh inode info */
 		goto mkdir_out;
 	}
-#endif /* SMB311 */
 
 	if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
 				le64_to_cpu(tcon->fsUnixInfo.Capability))) {
@@ -2071,8 +2069,8 @@ int cifs_getattr(const struct path *path, struct kstat *stat,
 	/* old CIFS Unix Extensions doesn't return create time */
 	if (CIFS_I(inode)->createtime) {
 		stat->result_mask |= STATX_BTIME;
-		stat->btime = timespec_to_timespec64(
-		      cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime)));
+		stat->btime =
+		      cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime));
 	}
 
 	stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED);
@@ -2278,17 +2276,17 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 		args->gid = INVALID_GID; /* no change */
 
 	if (attrs->ia_valid & ATTR_ATIME)
-		args->atime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime));
+		args->atime = cifs_UnixTimeToNT(attrs->ia_atime);
 	else
 		args->atime = NO_CHANGE_64;
 
 	if (attrs->ia_valid & ATTR_MTIME)
-		args->mtime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime));
+		args->mtime = cifs_UnixTimeToNT(attrs->ia_mtime);
 	else
 		args->mtime = NO_CHANGE_64;
 
 	if (attrs->ia_valid & ATTR_CTIME)
-		args->ctime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime));
+		args->ctime = cifs_UnixTimeToNT(attrs->ia_ctime);
 	else
 		args->ctime = NO_CHANGE_64;
 
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index de41f96aba49..2148b0f60e5e 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -396,7 +396,7 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_io_parms io_parms;
 	int buf_type = CIFS_NO_BUFFER;
 	__le16 *utf16_path;
-	__u8 oplock = SMB2_OPLOCK_LEVEL_II;
+	__u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct smb2_file_all_info *pfile_info = NULL;
 
 	oparms.tcon = tcon;
@@ -459,7 +459,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_io_parms io_parms;
 	int create_options = CREATE_NOT_DIR;
 	__le16 *utf16_path;
-	__u8 oplock = SMB2_OPLOCK_LEVEL_EXCLUSIVE;
+	__u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct kvec iov[2];
 
 	if (backup_cred(cifs_sb))
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 53e8362cbc4a..dacb2c05674c 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -122,9 +122,7 @@ tconInfoAlloc(void)
 		mutex_init(&ret_buf->crfid.fid_mutex);
 		ret_buf->crfid.fid = kzalloc(sizeof(struct cifs_fid),
 					     GFP_KERNEL);
-#ifdef CONFIG_CIFS_STATS
 		spin_lock_init(&ret_buf->stat_lock);
-#endif
 	}
 	return ret_buf;
 }
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index d7ad0dfe4e68..fdd908e4a26b 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -918,10 +918,10 @@ smbCalcSize(void *buf, struct TCP_Server_Info *server)
  * Convert the NT UTC (based 1601-01-01, in hundred nanosecond units)
  * into Unix UTC (based 1970-01-01, in seconds).
  */
-struct timespec
+struct timespec64
 cifs_NTtimeToUnix(__le64 ntutc)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 	/* BB what about the timezone? BB */
 
 	/* Subtract the NTFS time offset, then convert to 1s intervals. */
@@ -935,12 +935,12 @@ cifs_NTtimeToUnix(__le64 ntutc)
 	 */
 	if (t < 0) {
 		abs_t = -t;
-		ts.tv_nsec = (long)(do_div(abs_t, 10000000) * 100);
+		ts.tv_nsec = (time64_t)(do_div(abs_t, 10000000) * 100);
 		ts.tv_nsec = -ts.tv_nsec;
 		ts.tv_sec = -abs_t;
 	} else {
 		abs_t = t;
-		ts.tv_nsec = (long)do_div(abs_t, 10000000) * 100;
+		ts.tv_nsec = (time64_t)do_div(abs_t, 10000000) * 100;
 		ts.tv_sec = abs_t;
 	}
 
@@ -949,7 +949,7 @@ cifs_NTtimeToUnix(__le64 ntutc)
 
 /* Convert the Unix UTC into NT UTC. */
 u64
-cifs_UnixTimeToNT(struct timespec t)
+cifs_UnixTimeToNT(struct timespec64 t)
 {
 	/* Convert to 100ns intervals and then add the NTFS time offset. */
 	return (u64) t.tv_sec * 10000000 + t.tv_nsec/100 + NTFS_TIME_OFFSET;
@@ -959,10 +959,11 @@ static const int total_days_of_prev_months[] = {
 	0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334
 };
 
-struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
+struct timespec64 cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
 {
-	struct timespec ts;
-	int sec, min, days, month, year;
+	struct timespec64 ts;
+	time64_t sec;
+	int min, days, month, year;
 	u16 date = le16_to_cpu(le_date);
 	u16 time = le16_to_cpu(le_time);
 	SMB_TIME *st = (SMB_TIME *)&time;
@@ -973,7 +974,7 @@ struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
 	sec = 2 * st->TwoSeconds;
 	min = st->Minutes;
 	if ((sec > 59) || (min > 59))
-		cifs_dbg(VFS, "illegal time min %d sec %d\n", min, sec);
+		cifs_dbg(VFS, "illegal time min %d sec %lld\n", min, sec);
 	sec += (min * 60);
 	sec += 60 * 60 * st->Hours;
 	if (st->Hours > 24)
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index aff8ce8ba34d..378151e09e91 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -107,6 +107,7 @@ cifs_find_mid(struct TCP_Server_Info *server, char *buffer)
 		if (compare_mid(mid->mid, buf) &&
 		    mid->mid_state == MID_REQUEST_SUBMITTED &&
 		    le16_to_cpu(mid->command) == buf->Command) {
+			kref_get(&mid->refcount);
 			spin_unlock(&GlobalMid_Lock);
 			return mid;
 		}
@@ -623,7 +624,6 @@ cifs_query_file_info(const unsigned int xid, struct cifs_tcon *tcon,
 static void
 cifs_clear_stats(struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	atomic_set(&tcon->stats.cifs_stats.num_writes, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_reads, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_flushes, 0);
@@ -645,13 +645,11 @@ cifs_clear_stats(struct cifs_tcon *tcon)
 	atomic_set(&tcon->stats.cifs_stats.num_locks, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_acl_get, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_acl_set, 0);
-#endif
 }
 
 static void
 cifs_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	seq_printf(m, " Oplocks breaks: %d",
 		   atomic_read(&tcon->stats.cifs_stats.num_oplock_brks));
 	seq_printf(m, "\nReads:  %d Bytes: %llu",
@@ -683,7 +681,6 @@ cifs_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 		   atomic_read(&tcon->stats.cifs_stats.num_ffirst),
 		   atomic_read(&tcon->stats.cifs_stats.num_fnext),
 		   atomic_read(&tcon->stats.cifs_stats.num_fclose));
-#endif
 }
 
 static void
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 788412675723..4ed10dd086e6 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -41,7 +41,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 	int rc;
 	__le16 *smb2_path;
 	struct smb2_file_all_info *smb2_data = NULL;
-	__u8 smb2_oplock[17];
+	__u8 smb2_oplock;
 	struct cifs_fid *fid = oparms->fid;
 	struct network_resiliency_req nr_ioctl_req;
 
@@ -59,12 +59,9 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 	}
 
 	oparms->desired_access |= FILE_READ_ATTRIBUTES;
-	*smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH;
+	smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH;
 
-	if (oparms->tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING)
-		memcpy(smb2_oplock + 1, fid->lease_key, SMB2_LEASE_KEY_SIZE);
-
-	rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data, NULL,
+	rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL,
 		       NULL);
 	if (rc)
 		goto out;
@@ -101,7 +98,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 		move_smb2_info_to_cifs(buf, smb2_data);
 	}
 
-	*oplock = *smb2_oplock;
+	*oplock = smb2_oplock;
 out:
 	kfree(smb2_data);
 	kfree(smb2_path);
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index d01ad706d7fc..1eef1791d0c4 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -120,7 +120,9 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon,
 		break;
 	}
 
-	if (use_cached_root_handle == false)
+	if (use_cached_root_handle)
+		close_shroot(&tcon->crfid);
+	else
 		rc = SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	if (tmprc)
 		rc = tmprc;
@@ -281,7 +283,7 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	int rc;
 
 	if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) &&
-	    (buf->LastWriteTime == 0) && (buf->ChangeTime) &&
+	    (buf->LastWriteTime == 0) && (buf->ChangeTime == 0) &&
 	    (buf->Attributes == 0))
 		return 0; /* would be a no op, no sense sending this */
 
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 3ff7cec2da81..303d4592ebe7 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -93,7 +93,6 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 	/* SMB2_OPLOCK_BREAK */ cpu_to_le16(24)
 };
 
-#ifdef CONFIG_CIFS_SMB311
 static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
 			      __u32 non_ctxlen)
 {
@@ -127,7 +126,6 @@ static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
 	/* length of negcontexts including pad from end of sec blob to them */
 	return (len - nc_offset) + size_of_pad_before_neg_ctxts;
 }
-#endif /* CIFS_SMB311 */
 
 int
 smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
@@ -222,10 +220,9 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
 
 	clc_len = smb2_calc_size(buf, srvr);
 
-#ifdef CONFIG_CIFS_SMB311
 	if (shdr->Command == SMB2_NEGOTIATE)
 		clc_len += get_neg_ctxt_len(shdr, len, clc_len);
-#endif /* SMB311 */
+
 	if (len != clc_len) {
 		cifs_dbg(FYI, "Calculated size %u length %u mismatch mid %llu\n",
 			 clc_len, len, mid);
@@ -451,15 +448,13 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 	/* Windows doesn't allow paths beginning with \ */
 	if (from[0] == '\\')
 		start_of_path = from + 1;
-#ifdef CONFIG_CIFS_SMB311
+
 	/* SMB311 POSIX extensions paths do not include leading slash */
 	else if (cifs_sb_master_tlink(cifs_sb) &&
 		 cifs_sb_master_tcon(cifs_sb)->posix_extensions &&
 		 (from[0] == '/')) {
 		start_of_path = from + 1;
-	}
-#endif /* 311 */
-	else
+	} else
 		start_of_path = from;
 
 	to = cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
@@ -759,7 +754,6 @@ smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 /**
  * smb311_update_preauth_hash - update @ses hash with the packet data in @iov
  *
@@ -821,4 +815,3 @@ smb311_update_preauth_hash(struct cifs_ses *ses, struct kvec *iov, int nvec)
 
 	return 0;
 }
-#endif
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 0356b5559c71..541258447c4c 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -203,6 +203,7 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf)
 		if ((mid->mid == wire_mid) &&
 		    (mid->mid_state == MID_REQUEST_SUBMITTED) &&
 		    (mid->command == shdr->Command)) {
+			kref_get(&mid->refcount);
 			spin_unlock(&GlobalMid_Lock);
 			return mid;
 		}
@@ -443,7 +444,11 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 			FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
 			NULL /* no data input */, 0 /* no data input */,
 			(char **)&out_buf, &ret_data_len);
-	if (rc != 0) {
+	if (rc == -EOPNOTSUPP) {
+		cifs_dbg(FYI,
+			 "server does not support query network interfaces\n");
+		goto out;
+	} else if (rc != 0) {
 		cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc);
 		goto out;
 	}
@@ -465,21 +470,36 @@ out:
 	return rc;
 }
 
-void
-smb2_cached_lease_break(struct work_struct *work)
+static void
+smb2_close_cached_fid(struct kref *ref)
 {
-	struct cached_fid *cfid = container_of(work,
-				struct cached_fid, lease_break);
-	mutex_lock(&cfid->fid_mutex);
+	struct cached_fid *cfid = container_of(ref, struct cached_fid,
+					       refcount);
+
 	if (cfid->is_valid) {
 		cifs_dbg(FYI, "clear cached root file handle\n");
 		SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid,
 			   cfid->fid->volatile_fid);
 		cfid->is_valid = false;
 	}
+}
+
+void close_shroot(struct cached_fid *cfid)
+{
+	mutex_lock(&cfid->fid_mutex);
+	kref_put(&cfid->refcount, smb2_close_cached_fid);
 	mutex_unlock(&cfid->fid_mutex);
 }
 
+void
+smb2_cached_lease_break(struct work_struct *work)
+{
+	struct cached_fid *cfid = container_of(work,
+				struct cached_fid, lease_break);
+
+	close_shroot(cfid);
+}
+
 /*
  * Open the directory at the root of a share
  */
@@ -494,6 +514,7 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
 	if (tcon->crfid.is_valid) {
 		cifs_dbg(FYI, "found a cached root file handle\n");
 		memcpy(pfid, tcon->crfid.fid, sizeof(struct cifs_fid));
+		kref_get(&tcon->crfid.refcount);
 		mutex_unlock(&tcon->crfid.fid_mutex);
 		return 0;
 	}
@@ -510,6 +531,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
 		memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid));
 		tcon->crfid.tcon = tcon;
 		tcon->crfid.is_valid = true;
+		kref_init(&tcon->crfid.refcount);
+		kref_get(&tcon->crfid.refcount);
 	}
 	mutex_unlock(&tcon->crfid.fid_mutex);
 	return rc;
@@ -548,9 +571,14 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
 	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
 			FS_DEVICE_INFORMATION);
 	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
+			FS_VOLUME_INFORMATION);
+	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
 			FS_SECTOR_SIZE_INFORMATION); /* SMB3 specific */
 	if (no_cached_open)
 		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+	else
+		close_shroot(&tcon->crfid);
+
 	return;
 }
 
@@ -855,6 +883,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_set_ea(xid, tcon, fid.persistent_fid, fid.volatile_fid, ea,
 			 len);
+	kfree(ea);
+
 	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 
 	return rc;
@@ -870,13 +900,11 @@ smb2_can_echo(struct TCP_Server_Info *server)
 static void
 smb2_clear_stats(struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	int i;
 	for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++) {
 		atomic_set(&tcon->stats.smb2_stats.smb2_com_sent[i], 0);
 		atomic_set(&tcon->stats.smb2_stats.smb2_com_failed[i], 0);
 	}
-#endif
 }
 
 static void
@@ -915,67 +943,58 @@ smb2_dump_share_caps(struct seq_file *m, struct cifs_tcon *tcon)
 static void
 smb2_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	atomic_t *sent = tcon->stats.smb2_stats.smb2_com_sent;
 	atomic_t *failed = tcon->stats.smb2_stats.smb2_com_failed;
-	seq_printf(m, "\nNegotiates: %d sent %d failed",
-		   atomic_read(&sent[SMB2_NEGOTIATE_HE]),
-		   atomic_read(&failed[SMB2_NEGOTIATE_HE]));
-	seq_printf(m, "\nSessionSetups: %d sent %d failed",
-		   atomic_read(&sent[SMB2_SESSION_SETUP_HE]),
-		   atomic_read(&failed[SMB2_SESSION_SETUP_HE]));
-	seq_printf(m, "\nLogoffs: %d sent %d failed",
-		   atomic_read(&sent[SMB2_LOGOFF_HE]),
-		   atomic_read(&failed[SMB2_LOGOFF_HE]));
-	seq_printf(m, "\nTreeConnects: %d sent %d failed",
+
+	/*
+	 *  Can't display SMB2_NEGOTIATE, SESSION_SETUP, LOGOFF, CANCEL and ECHO
+	 *  totals (requests sent) since those SMBs are per-session not per tcon
+	 */
+	seq_printf(m, "\nBytes read: %llu  Bytes written: %llu",
+		   (long long)(tcon->bytes_read),
+		   (long long)(tcon->bytes_written));
+	seq_printf(m, "\nTreeConnects: %d total %d failed",
 		   atomic_read(&sent[SMB2_TREE_CONNECT_HE]),
 		   atomic_read(&failed[SMB2_TREE_CONNECT_HE]));
-	seq_printf(m, "\nTreeDisconnects: %d sent %d failed",
+	seq_printf(m, "\nTreeDisconnects: %d total %d failed",
 		   atomic_read(&sent[SMB2_TREE_DISCONNECT_HE]),
 		   atomic_read(&failed[SMB2_TREE_DISCONNECT_HE]));
-	seq_printf(m, "\nCreates: %d sent %d failed",
+	seq_printf(m, "\nCreates: %d total %d failed",
 		   atomic_read(&sent[SMB2_CREATE_HE]),
 		   atomic_read(&failed[SMB2_CREATE_HE]));
-	seq_printf(m, "\nCloses: %d sent %d failed",
+	seq_printf(m, "\nCloses: %d total %d failed",
 		   atomic_read(&sent[SMB2_CLOSE_HE]),
 		   atomic_read(&failed[SMB2_CLOSE_HE]));
-	seq_printf(m, "\nFlushes: %d sent %d failed",
+	seq_printf(m, "\nFlushes: %d total %d failed",
 		   atomic_read(&sent[SMB2_FLUSH_HE]),
 		   atomic_read(&failed[SMB2_FLUSH_HE]));
-	seq_printf(m, "\nReads: %d sent %d failed",
+	seq_printf(m, "\nReads: %d total %d failed",
 		   atomic_read(&sent[SMB2_READ_HE]),
 		   atomic_read(&failed[SMB2_READ_HE]));
-	seq_printf(m, "\nWrites: %d sent %d failed",
+	seq_printf(m, "\nWrites: %d total %d failed",
 		   atomic_read(&sent[SMB2_WRITE_HE]),
 		   atomic_read(&failed[SMB2_WRITE_HE]));
-	seq_printf(m, "\nLocks: %d sent %d failed",
+	seq_printf(m, "\nLocks: %d total %d failed",
 		   atomic_read(&sent[SMB2_LOCK_HE]),
 		   atomic_read(&failed[SMB2_LOCK_HE]));
-	seq_printf(m, "\nIOCTLs: %d sent %d failed",
+	seq_printf(m, "\nIOCTLs: %d total %d failed",
 		   atomic_read(&sent[SMB2_IOCTL_HE]),
 		   atomic_read(&failed[SMB2_IOCTL_HE]));
-	seq_printf(m, "\nCancels: %d sent %d failed",
-		   atomic_read(&sent[SMB2_CANCEL_HE]),
-		   atomic_read(&failed[SMB2_CANCEL_HE]));
-	seq_printf(m, "\nEchos: %d sent %d failed",
-		   atomic_read(&sent[SMB2_ECHO_HE]),
-		   atomic_read(&failed[SMB2_ECHO_HE]));
-	seq_printf(m, "\nQueryDirectories: %d sent %d failed",
+	seq_printf(m, "\nQueryDirectories: %d total %d failed",
 		   atomic_read(&sent[SMB2_QUERY_DIRECTORY_HE]),
 		   atomic_read(&failed[SMB2_QUERY_DIRECTORY_HE]));
-	seq_printf(m, "\nChangeNotifies: %d sent %d failed",
+	seq_printf(m, "\nChangeNotifies: %d total %d failed",
 		   atomic_read(&sent[SMB2_CHANGE_NOTIFY_HE]),
 		   atomic_read(&failed[SMB2_CHANGE_NOTIFY_HE]));
-	seq_printf(m, "\nQueryInfos: %d sent %d failed",
+	seq_printf(m, "\nQueryInfos: %d total %d failed",
 		   atomic_read(&sent[SMB2_QUERY_INFO_HE]),
 		   atomic_read(&failed[SMB2_QUERY_INFO_HE]));
-	seq_printf(m, "\nSetInfos: %d sent %d failed",
+	seq_printf(m, "\nSetInfos: %d total %d failed",
 		   atomic_read(&sent[SMB2_SET_INFO_HE]),
 		   atomic_read(&failed[SMB2_SET_INFO_HE]));
 	seq_printf(m, "\nOplockBreaks: %d sent %d failed",
 		   atomic_read(&sent[SMB2_OPLOCK_BREAK_HE]),
 		   atomic_read(&failed[SMB2_OPLOCK_BREAK_HE]));
-#endif
 }
 
 static void
@@ -1350,6 +1369,13 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 
 }
 
+/* GMT Token is @GMT-YYYY.MM.DD-HH.MM.SS Unicode which is 48 bytes + null */
+#define GMT_TOKEN_SIZE 50
+
+/*
+ * Input buffer contains (empty) struct smb_snapshot array with size filled in
+ * For output see struct SRV_SNAPSHOT_ARRAY in MS-SMB2 section 2.2.32.2
+ */
 static int
 smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 		   struct cifsFileInfo *cfile, void __user *ioc_buf)
@@ -1379,14 +1405,27 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 			kfree(retbuf);
 			return rc;
 		}
-		if (snapshot_in.snapshot_array_size < sizeof(struct smb_snapshot_array)) {
-			rc = -ERANGE;
-			kfree(retbuf);
-			return rc;
-		}
 
-		if (ret_data_len > snapshot_in.snapshot_array_size)
-			ret_data_len = snapshot_in.snapshot_array_size;
+		/*
+		 * Check for min size, ie not large enough to fit even one GMT
+		 * token (snapshot).  On the first ioctl some users may pass in
+		 * smaller size (or zero) to simply get the size of the array
+		 * so the user space caller can allocate sufficient memory
+		 * and retry the ioctl again with larger array size sufficient
+		 * to hold all of the snapshot GMT tokens on the second try.
+		 */
+		if (snapshot_in.snapshot_array_size < GMT_TOKEN_SIZE)
+			ret_data_len = sizeof(struct smb_snapshot_array);
+
+		/*
+		 * We return struct SRV_SNAPSHOT_ARRAY, followed by
+		 * the snapshot array (of 50 byte GMT tokens) each
+		 * representing an available previous version of the data
+		 */
+		if (ret_data_len > (snapshot_in.snapshot_array_size +
+					sizeof(struct smb_snapshot_array)))
+			ret_data_len = snapshot_in.snapshot_array_size +
+					sizeof(struct smb_snapshot_array);
 
 		if (copy_to_user(ioc_buf, retbuf, ret_data_len))
 			rc = -EFAULT;
@@ -1484,7 +1523,11 @@ smb2_is_session_expired(char *buf)
 	    shdr->Status != STATUS_USER_SESSION_DELETED)
 		return false;
 
+	trace_smb3_ses_expired(shdr->TreeId, shdr->SessionId,
+			       le16_to_cpu(shdr->Command),
+			       le64_to_cpu(shdr->MessageId));
 	cifs_dbg(FYI, "Session expired or deleted\n");
+
 	return true;
 }
 
@@ -1501,16 +1544,140 @@ smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid,
 				 CIFS_CACHE_READ(cinode) ? 1 : 0);
 }
 
+static void
+smb2_set_related(struct smb_rqst *rqst)
+{
+	struct smb2_sync_hdr *shdr;
+
+	shdr = (struct smb2_sync_hdr *)(rqst->rq_iov[0].iov_base);
+	shdr->Flags |= SMB2_FLAGS_RELATED_OPERATIONS;
+}
+
+char smb2_padding[7] = {0, 0, 0, 0, 0, 0, 0};
+
+static void
+smb2_set_next_command(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+{
+	struct smb2_sync_hdr *shdr;
+	unsigned long len = smb_rqst_len(server, rqst);
+
+	/* SMB headers in a compound are 8 byte aligned. */
+	if (len & 7) {
+		rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding;
+		rqst->rq_iov[rqst->rq_nvec].iov_len = 8 - (len & 7);
+		rqst->rq_nvec++;
+		len = smb_rqst_len(server, rqst);
+	}
+
+	shdr = (struct smb2_sync_hdr *)(rqst->rq_iov[0].iov_base);
+	shdr->NextCommand = cpu_to_le32(len);
+}
+
 static int
 smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	     struct kstatfs *buf)
 {
+	struct smb2_query_info_rsp *rsp;
+	struct smb2_fs_full_size_info *info = NULL;
+	struct smb_rqst rqst[3];
+	int resp_buftype[3];
+	struct kvec rsp_iov[3];
+	struct kvec open_iov[5]; /* 4 + potential padding. */
+	struct kvec qi_iov[1];
+	struct kvec close_iov[1];
+	struct cifs_ses *ses = tcon->ses;
+	struct TCP_Server_Info *server = ses->server;
+	__le16 srch_path = 0; /* Null - open root of share */
+	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+	struct cifs_open_parms oparms;
+	struct cifs_fid fid;
+	int flags = 0;
+	int rc;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	memset(rqst, 0, sizeof(rqst));
+	memset(resp_buftype, 0, sizeof(resp_buftype));
+	memset(rsp_iov, 0, sizeof(rsp_iov));
+
+	memset(&open_iov, 0, sizeof(open_iov));
+	rqst[0].rq_iov = open_iov;
+	rqst[0].rq_nvec = 4;
+
+	oparms.tcon = tcon;
+	oparms.desired_access = FILE_READ_ATTRIBUTES;
+	oparms.disposition = FILE_OPEN;
+	oparms.create_options = 0;
+	oparms.fid = &fid;
+	oparms.reconnect = false;
+
+	rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, &srch_path);
+	if (rc)
+		goto qfs_exit;
+	smb2_set_next_command(server, &rqst[0]);
+
+	memset(&qi_iov, 0, sizeof(qi_iov));
+	rqst[1].rq_iov = qi_iov;
+	rqst[1].rq_nvec = 1;
+
+	rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, COMPOUND_FID,
+				  FS_FULL_SIZE_INFORMATION,
+				  SMB2_O_INFO_FILESYSTEM, 0,
+				  sizeof(struct smb2_fs_full_size_info));
+	if (rc)
+		goto qfs_exit;
+	smb2_set_next_command(server, &rqst[1]);
+	smb2_set_related(&rqst[1]);
+
+	memset(&close_iov, 0, sizeof(close_iov));
+	rqst[2].rq_iov = close_iov;
+	rqst[2].rq_nvec = 1;
+
+	rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID);
+	if (rc)
+		goto qfs_exit;
+	smb2_set_related(&rqst[2]);
+
+	rc = compound_send_recv(xid, ses, flags, 3, rqst,
+				resp_buftype, rsp_iov);
+	if (rc)
+		goto qfs_exit;
+
+	rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base;
+	buf->f_type = SMB2_MAGIC_NUMBER;
+	info = (struct smb2_fs_full_size_info *)(
+		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength),
+			       &rsp_iov[1],
+			       sizeof(struct smb2_fs_full_size_info));
+	if (!rc)
+		smb2_copy_fs_info_to_kstatfs(info, buf);
+
+qfs_exit:
+	SMB2_open_free(&rqst[0]);
+	SMB2_query_info_free(&rqst[1]);
+	SMB2_close_free(&rqst[2]);
+	free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
+	free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
+	free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base);
+	return rc;
+}
+
+static int
+smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
+	     struct kstatfs *buf)
+{
 	int rc;
 	__le16 srch_path = 0; /* Null - open root of share */
 	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct cifs_open_parms oparms;
 	struct cifs_fid fid;
 
+	if (!tcon->posix_extensions)
+		return smb2_queryfs(xid, tcon, buf);
+
 	oparms.tcon = tcon;
 	oparms.desired_access = FILE_READ_ATTRIBUTES;
 	oparms.disposition = FILE_OPEN;
@@ -1521,9 +1688,10 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, NULL);
 	if (rc)
 		return rc;
+
+	rc = SMB311_posix_qfs_info(xid, tcon, fid.persistent_fid,
+				   fid.volatile_fid, buf);
 	buf->f_type = SMB2_MAGIC_NUMBER;
-	rc = SMB2_QFS_info(xid, tcon, fid.persistent_fid, fid.volatile_fid,
-			   buf);
 	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	return rc;
 }
@@ -1697,7 +1865,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 		       &resp_buftype);
 	if (!rc || !err_iov.iov_base) {
 		rc = -ENOENT;
-		goto querty_exit;
+		goto free_path;
 	}
 
 	err_buf = err_iov.iov_base;
@@ -1738,6 +1906,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 
  querty_exit:
 	free_rsp_buf(resp_buftype, err_buf);
+ free_path:
 	kfree(utf16_path);
 	return rc;
 }
@@ -2219,8 +2388,7 @@ smb2_create_lease_buf(u8 *lease_key, u8 oplock)
 	if (!buf)
 		return NULL;
 
-	buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key));
-	buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8)));
+	memcpy(&buf->lcontext.LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE);
 	buf->lcontext.LeaseState = map_oplock_to_lease(oplock);
 
 	buf->ccontext.DataOffset = cpu_to_le16(offsetof
@@ -2246,8 +2414,7 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock)
 	if (!buf)
 		return NULL;
 
-	buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key));
-	buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8)));
+	memcpy(&buf->lcontext.LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE);
 	buf->lcontext.LeaseState = map_oplock_to_lease(oplock);
 
 	buf->ccontext.DataOffset = cpu_to_le16(offsetof
@@ -2284,8 +2451,7 @@ smb3_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key)
 	if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS)
 		return SMB2_OPLOCK_LEVEL_NOCHANGE;
 	if (lease_key)
-		memcpy(lease_key, &lc->lcontext.LeaseKeyLow,
-		       SMB2_LEASE_KEY_SIZE);
+		memcpy(lease_key, &lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
 	return le32_to_cpu(lc->lcontext.LeaseState);
 }
 
@@ -2326,35 +2492,51 @@ static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf,
 	sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
 }
 
-/* Assumes:
- * rqst->rq_iov[0]  is transform header
- * rqst->rq_iov[1+] data to be encrypted/decrypted
+/* Assumes the first rqst has a transform header as the first iov.
+ * I.e.
+ * rqst[0].rq_iov[0]  is transform header
+ * rqst[0].rq_iov[1+] data to be encrypted/decrypted
+ * rqst[1+].rq_iov[0+] data to be encrypted/decrypted
  */
 static struct scatterlist *
-init_sg(struct smb_rqst *rqst, u8 *sign)
+init_sg(int num_rqst, struct smb_rqst *rqst, u8 *sign)
 {
-	unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages + 1;
-	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
+	unsigned int sg_len;
 	struct scatterlist *sg;
 	unsigned int i;
 	unsigned int j;
+	unsigned int idx = 0;
+	int skip;
+
+	sg_len = 1;
+	for (i = 0; i < num_rqst; i++)
+		sg_len += rqst[i].rq_nvec + rqst[i].rq_npages;
 
 	sg = kmalloc_array(sg_len, sizeof(struct scatterlist), GFP_KERNEL);
 	if (!sg)
 		return NULL;
 
 	sg_init_table(sg, sg_len);
-	smb2_sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 20, assoc_data_len);
-	for (i = 1; i < rqst->rq_nvec; i++)
-		smb2_sg_set_buf(&sg[i], rqst->rq_iov[i].iov_base,
-						rqst->rq_iov[i].iov_len);
-	for (j = 0; i < sg_len - 1; i++, j++) {
-		unsigned int len, offset;
+	for (i = 0; i < num_rqst; i++) {
+		for (j = 0; j < rqst[i].rq_nvec; j++) {
+			/*
+			 * The first rqst has a transform header where the
+			 * first 20 bytes are not part of the encrypted blob
+			 */
+			skip = (i == 0) && (j == 0) ? 20 : 0;
+			smb2_sg_set_buf(&sg[idx++],
+					rqst[i].rq_iov[j].iov_base + skip,
+					rqst[i].rq_iov[j].iov_len - skip);
+		}
+
+		for (j = 0; j < rqst[i].rq_npages; j++) {
+			unsigned int len, offset;
 
-		rqst_page_get_length(rqst, j, &len, &offset);
-		sg_set_page(&sg[i], rqst->rq_pages[j], len, offset);
+			rqst_page_get_length(&rqst[i], j, &len, &offset);
+			sg_set_page(&sg[idx++], rqst[i].rq_pages[j], len, offset);
+		}
 	}
-	smb2_sg_set_buf(&sg[sg_len - 1], sign, SMB2_SIGNATURE_SIZE);
+	smb2_sg_set_buf(&sg[idx], sign, SMB2_SIGNATURE_SIZE);
 	return sg;
 }
 
@@ -2386,10 +2568,11 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
  * untouched.
  */
 static int
-crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
+crypt_message(struct TCP_Server_Info *server, int num_rqst,
+	      struct smb_rqst *rqst, int enc)
 {
 	struct smb2_transform_hdr *tr_hdr =
-			(struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
+		(struct smb2_transform_hdr *)rqst[0].rq_iov[0].iov_base;
 	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
 	int rc = 0;
 	struct scatterlist *sg;
@@ -2440,7 +2623,7 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
 		crypt_len += SMB2_SIGNATURE_SIZE;
 	}
 
-	sg = init_sg(rqst, sign);
+	sg = init_sg(num_rqst, rqst, sign);
 	if (!sg) {
 		cifs_dbg(VFS, "%s: Failed to init sg", __func__);
 		rc = -ENOMEM;
@@ -2477,103 +2660,98 @@ free_req:
 	return rc;
 }
 
+void
+smb3_free_compound_rqst(int num_rqst, struct smb_rqst *rqst)
+{
+	int i, j;
+
+	for (i = 0; i < num_rqst; i++) {
+		if (rqst[i].rq_pages) {
+			for (j = rqst[i].rq_npages - 1; j >= 0; j--)
+				put_page(rqst[i].rq_pages[j]);
+			kfree(rqst[i].rq_pages);
+		}
+	}
+}
+
+/*
+ * This function will initialize new_rq and encrypt the content.
+ * The first entry, new_rq[0], only contains a single iov which contains
+ * a smb2_transform_hdr and is pre-allocated by the caller.
+ * This function then populates new_rq[1+] with the content from olq_rq[0+].
+ *
+ * The end result is an array of smb_rqst structures where the first structure
+ * only contains a single iov for the transform header which we then can pass
+ * to crypt_message().
+ *
+ * new_rq[0].rq_iov[0] :  smb2_transform_hdr pre-allocated by the caller
+ * new_rq[1+].rq_iov[*] == old_rq[0+].rq_iov[*] : SMB2/3 requests
+ */
 static int
-smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
-		       struct smb_rqst *old_rq)
+smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst,
+		       struct smb_rqst *new_rq, struct smb_rqst *old_rq)
 {
-	struct kvec *iov;
 	struct page **pages;
-	struct smb2_transform_hdr *tr_hdr;
-	unsigned int npages = old_rq->rq_npages;
-	unsigned int orig_len;
-	int i;
+	struct smb2_transform_hdr *tr_hdr = new_rq[0].rq_iov[0].iov_base;
+	unsigned int npages;
+	unsigned int orig_len = 0;
+	int i, j;
 	int rc = -ENOMEM;
 
-	pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
-	if (!pages)
-		return rc;
-
-	new_rq->rq_pages = pages;
-	new_rq->rq_offset = old_rq->rq_offset;
-	new_rq->rq_npages = old_rq->rq_npages;
-	new_rq->rq_pagesz = old_rq->rq_pagesz;
-	new_rq->rq_tailsz = old_rq->rq_tailsz;
-
-	for (i = 0; i < npages; i++) {
-		pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
-		if (!pages[i])
-			goto err_free_pages;
-	}
-
-	iov = kmalloc_array(old_rq->rq_nvec + 1, sizeof(struct kvec),
-			    GFP_KERNEL);
-	if (!iov)
-		goto err_free_pages;
+	for (i = 1; i < num_rqst; i++) {
+		npages = old_rq[i - 1].rq_npages;
+		pages = kmalloc_array(npages, sizeof(struct page *),
+				      GFP_KERNEL);
+		if (!pages)
+			goto err_free;
+
+		new_rq[i].rq_pages = pages;
+		new_rq[i].rq_npages = npages;
+		new_rq[i].rq_offset = old_rq[i - 1].rq_offset;
+		new_rq[i].rq_pagesz = old_rq[i - 1].rq_pagesz;
+		new_rq[i].rq_tailsz = old_rq[i - 1].rq_tailsz;
+		new_rq[i].rq_iov = old_rq[i - 1].rq_iov;
+		new_rq[i].rq_nvec = old_rq[i - 1].rq_nvec;
+
+		orig_len += smb_rqst_len(server, &old_rq[i - 1]);
+
+		for (j = 0; j < npages; j++) {
+			pages[j] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
+			if (!pages[j])
+				goto err_free;
+		}
 
-	/* copy all iovs from the old */
-	memcpy(&iov[1], &old_rq->rq_iov[0],
-				sizeof(struct kvec) * old_rq->rq_nvec);
+		/* copy pages form the old */
+		for (j = 0; j < npages; j++) {
+			char *dst, *src;
+			unsigned int offset, len;
 
-	new_rq->rq_iov = iov;
-	new_rq->rq_nvec = old_rq->rq_nvec + 1;
+			rqst_page_get_length(&new_rq[i], j, &len, &offset);
 
-	tr_hdr = kmalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL);
-	if (!tr_hdr)
-		goto err_free_iov;
+			dst = (char *) kmap(new_rq[i].rq_pages[j]) + offset;
+			src = (char *) kmap(old_rq[i - 1].rq_pages[j]) + offset;
 
-	orig_len = smb2_rqst_len(old_rq, false);
+			memcpy(dst, src, len);
+			kunmap(new_rq[i].rq_pages[j]);
+			kunmap(old_rq[i - 1].rq_pages[j]);
+		}
+	}
 
-	/* fill the 2nd iov with a transform header */
+	/* fill the 1st iov with a transform header */
 	fill_transform_hdr(tr_hdr, orig_len, old_rq);
-	new_rq->rq_iov[0].iov_base = tr_hdr;
-	new_rq->rq_iov[0].iov_len = sizeof(struct smb2_transform_hdr);
-
-	/* copy pages form the old */
-	for (i = 0; i < npages; i++) {
-		char *dst, *src;
-		unsigned int offset, len;
-
-		rqst_page_get_length(new_rq, i, &len, &offset);
-
-		dst = (char *) kmap(new_rq->rq_pages[i]) + offset;
-		src = (char *) kmap(old_rq->rq_pages[i]) + offset;
 
-		memcpy(dst, src, len);
-		kunmap(new_rq->rq_pages[i]);
-		kunmap(old_rq->rq_pages[i]);
-	}
-
-	rc = crypt_message(server, new_rq, 1);
+	rc = crypt_message(server, num_rqst, new_rq, 1);
 	cifs_dbg(FYI, "encrypt message returned %d", rc);
 	if (rc)
-		goto err_free_tr_hdr;
+		goto err_free;
 
 	return rc;
 
-err_free_tr_hdr:
-	kfree(tr_hdr);
-err_free_iov:
-	kfree(iov);
-err_free_pages:
-	for (i = i - 1; i >= 0; i--)
-		put_page(pages[i]);
-	kfree(pages);
+err_free:
+	smb3_free_compound_rqst(num_rqst - 1, &new_rq[1]);
 	return rc;
 }
 
-static void
-smb3_free_transform_rq(struct smb_rqst *rqst)
-{
-	int i = rqst->rq_npages - 1;
-
-	for (; i >= 0; i--)
-		put_page(rqst->rq_pages[i]);
-	kfree(rqst->rq_pages);
-	/* free transform header */
-	kfree(rqst->rq_iov[0].iov_base);
-	kfree(rqst->rq_iov);
-}
-
 static int
 smb3_is_transform_hdr(void *buf)
 {
@@ -2603,7 +2781,7 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
 	rqst.rq_pagesz = PAGE_SIZE;
 	rqst.rq_tailsz = (page_data_size % PAGE_SIZE) ? : PAGE_SIZE;
 
-	rc = crypt_message(server, &rqst, 0);
+	rc = crypt_message(server, 1, &rqst, 0);
 	cifs_dbg(FYI, "decrypt message returned %d\n", rc);
 
 	if (rc)
@@ -2878,13 +3056,20 @@ discard_data:
 
 static int
 receive_encrypted_standard(struct TCP_Server_Info *server,
-			   struct mid_q_entry **mid)
+			   struct mid_q_entry **mids, char **bufs,
+			   int *num_mids)
 {
-	int length;
+	int ret, length;
 	char *buf = server->smallbuf;
+	char *tmpbuf;
+	struct smb2_sync_hdr *shdr;
 	unsigned int pdu_length = server->pdu_size;
 	unsigned int buf_size;
 	struct mid_q_entry *mid_entry;
+	int next_is_large;
+	char *next_buffer = NULL;
+
+	*num_mids = 0;
 
 	/* switch to large buffer if too big for a small one */
 	if (pdu_length > MAX_CIFS_SMALL_BUFFER_SIZE) {
@@ -2905,24 +3090,61 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 	if (length)
 		return length;
 
+	next_is_large = server->large_buf;
+ one_more:
+	shdr = (struct smb2_sync_hdr *)buf;
+	if (shdr->NextCommand) {
+		if (next_is_large) {
+			tmpbuf = server->bigbuf;
+			next_buffer = (char *)cifs_buf_get();
+		} else {
+			tmpbuf = server->smallbuf;
+			next_buffer = (char *)cifs_small_buf_get();
+		}
+		memcpy(next_buffer,
+		       tmpbuf + le32_to_cpu(shdr->NextCommand),
+		       pdu_length - le32_to_cpu(shdr->NextCommand));
+	}
+
 	mid_entry = smb2_find_mid(server, buf);
 	if (mid_entry == NULL)
 		cifs_dbg(FYI, "mid not found\n");
 	else {
 		cifs_dbg(FYI, "mid found\n");
 		mid_entry->decrypted = true;
+		mid_entry->resp_buf_size = server->pdu_size;
 	}
 
-	*mid = mid_entry;
+	if (*num_mids >= MAX_COMPOUND) {
+		cifs_dbg(VFS, "too many PDUs in compound\n");
+		return -1;
+	}
+	bufs[*num_mids] = buf;
+	mids[(*num_mids)++] = mid_entry;
 
 	if (mid_entry && mid_entry->handle)
-		return mid_entry->handle(server, mid_entry);
+		ret = mid_entry->handle(server, mid_entry);
+	else
+		ret = cifs_handle_standard(server, mid_entry);
 
-	return cifs_handle_standard(server, mid_entry);
+	if (ret == 0 && shdr->NextCommand) {
+		pdu_length -= le32_to_cpu(shdr->NextCommand);
+		server->large_buf = next_is_large;
+		if (next_is_large)
+			server->bigbuf = next_buffer;
+		else
+			server->smallbuf = next_buffer;
+
+		buf += le32_to_cpu(shdr->NextCommand);
+		goto one_more;
+	}
+
+	return ret;
 }
 
 static int
-smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
+smb3_receive_transform(struct TCP_Server_Info *server,
+		       struct mid_q_entry **mids, char **bufs, int *num_mids)
 {
 	char *buf = server->smallbuf;
 	unsigned int pdu_length = server->pdu_size;
@@ -2945,10 +3167,11 @@ smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
 		return -ECONNABORTED;
 	}
 
+	/* TODO: add support for compounds containing READ. */
 	if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server))
-		return receive_encrypted_read(server, mid);
+		return receive_encrypted_read(server, &mids[0]);
 
-	return receive_encrypted_standard(server, mid);
+	return receive_encrypted_standard(server, mids, bufs, num_mids);
 }
 
 int
@@ -3250,7 +3473,6 @@ struct smb_version_operations smb30_operations = {
 	.fallocate = smb3_fallocate,
 	.enum_snapshots = smb3_enum_snapshots,
 	.init_transform_rq = smb3_init_transform_rq,
-	.free_transform_rq = smb3_free_transform_rq,
 	.is_transform_hdr = smb3_is_transform_hdr,
 	.receive_transform = smb3_receive_transform,
 	.get_dfs_refer = smb2_get_dfs_refer,
@@ -3267,7 +3489,6 @@ struct smb_version_operations smb30_operations = {
 	.next_header = smb2_next_header,
 };
 
-#ifdef CONFIG_CIFS_SMB311
 struct smb_version_operations smb311_operations = {
 	.compare_fids = smb2_compare_fids,
 	.setup_request = smb2_setup_request,
@@ -3335,7 +3556,7 @@ struct smb_version_operations smb311_operations = {
 	.is_status_pending = smb2_is_status_pending,
 	.is_session_expired = smb2_is_session_expired,
 	.oplock_response = smb2_oplock_response,
-	.queryfs = smb2_queryfs,
+	.queryfs = smb311_queryfs,
 	.mand_lock = smb2_mand_lock,
 	.mand_unlock_range = smb2_unlock_range,
 	.push_mand_locks = smb2_push_mandatory_locks,
@@ -3357,7 +3578,6 @@ struct smb_version_operations smb311_operations = {
 	.fallocate = smb3_fallocate,
 	.enum_snapshots = smb3_enum_snapshots,
 	.init_transform_rq = smb3_init_transform_rq,
-	.free_transform_rq = smb3_free_transform_rq,
 	.is_transform_hdr = smb3_is_transform_hdr,
 	.receive_transform = smb3_receive_transform,
 	.get_dfs_refer = smb2_get_dfs_refer,
@@ -3366,9 +3586,13 @@ struct smb_version_operations smb311_operations = {
 	.query_all_EAs = smb2_query_eas,
 	.set_EA = smb2_set_ea,
 #endif /* CIFS_XATTR */
+#ifdef CONFIG_CIFS_ACL
+	.get_acl = get_smb2_acl,
+	.get_acl_by_fid = get_smb2_acl_by_fid,
+	.set_acl = set_smb2_acl,
+#endif /* CIFS_ACL */
 	.next_header = smb2_next_header,
 };
-#endif /* CIFS_SMB311 */
 
 struct smb_version_values smb20_values = {
 	.version_string = SMB20_VERSION_STRING,
@@ -3496,7 +3720,6 @@ struct smb_version_values smb302_values = {
 	.create_lease_size = sizeof(struct create_lease_v2),
 };
 
-#ifdef CONFIG_CIFS_SMB311
 struct smb_version_values smb311_values = {
 	.version_string = SMB311_VERSION_STRING,
 	.protocol_id = SMB311_PROT_ID,
@@ -3517,4 +3740,3 @@ struct smb_version_values smb311_values = {
 	.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
 	.create_lease_size = sizeof(struct create_lease_v2),
 };
-#endif /* SMB311 */
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 810b85787c91..2f1938011395 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -80,7 +80,7 @@ static const int smb2_req_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 	/* SMB2_OPLOCK_BREAK */ 24 /* BB this is 36 for LEASE_BREAK variant */
 };
 
-static int smb3_encryption_required(const struct cifs_tcon *tcon)
+int smb3_encryption_required(const struct cifs_tcon *tcon)
 {
 	if (!tcon)
 		return 0;
@@ -155,7 +155,7 @@ out:
 static int
 smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 {
-	int rc = 0;
+	int rc;
 	struct nls_table *nls_codepage;
 	struct cifs_ses *ses;
 	struct TCP_Server_Info *server;
@@ -166,10 +166,10 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 	 * for those three - in the calling routine.
 	 */
 	if (tcon == NULL)
-		return rc;
+		return 0;
 
 	if (smb2_command == SMB2_TREE_CONNECT)
-		return rc;
+		return 0;
 
 	if (tcon->tidStatus == CifsExiting) {
 		/*
@@ -212,8 +212,14 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 			return -EAGAIN;
 		}
 
-		wait_event_interruptible_timeout(server->response_q,
-			(server->tcpStatus != CifsNeedReconnect), 10 * HZ);
+		rc = wait_event_interruptible_timeout(server->response_q,
+						      (server->tcpStatus != CifsNeedReconnect),
+						      10 * HZ);
+		if (rc < 0) {
+			cifs_dbg(FYI, "%s: aborting reconnect due to a received"
+				 " signal by the process\n", __func__);
+			return -ERESTARTSYS;
+		}
 
 		/* are we still trying to reconnect? */
 		if (server->tcpStatus != CifsNeedReconnect)
@@ -231,7 +237,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 	}
 
 	if (!tcon->ses->need_reconnect && !tcon->need_reconnect)
-		return rc;
+		return 0;
 
 	nls_codepage = load_nls_default();
 
@@ -340,7 +346,10 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		return rc;
 
 	/* BB eventually switch this to SMB2 specific small buf size */
-	*request_buf = cifs_small_buf_get();
+	if (smb2_command == SMB2_SET_INFO)
+		*request_buf = cifs_buf_get();
+	else
+		*request_buf = cifs_small_buf_get();
 	if (*request_buf == NULL) {
 		/* BB should we add a retry in here if not a writepage? */
 		return -ENOMEM;
@@ -351,17 +360,15 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		       total_len);
 
 	if (tcon != NULL) {
-#ifdef CONFIG_CIFS_STATS2
 		uint16_t com_code = le16_to_cpu(smb2_command);
 		cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_sent[com_code]);
-#endif
 		cifs_stats_inc(&tcon->num_smbs_sent);
 	}
 
 	return rc;
 }
 
-#ifdef CONFIG_CIFS_SMB311
+
 /* offset is sizeof smb2_negotiate_req but rounded up to 8 bytes */
 #define OFFSET_OF_NEG_CONTEXT 0x68  /* sizeof(struct smb2_negotiate_req) */
 
@@ -576,13 +583,6 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode)
 	return 0;
 }
 
-#else
-static void assemble_neg_contexts(struct smb2_negotiate_req *req,
-				  unsigned int *total_len)
-{
-	return;
-}
-#endif /* SMB311 */
 
 /*
  *
@@ -627,10 +627,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		return rc;
 
 	req->sync_hdr.SessionId = 0;
-#ifdef CONFIG_CIFS_SMB311
+
 	memset(server->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
 	memset(ses->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
-#endif
 
 	if (strcmp(ses->server->vals->version_string,
 		   SMB3ANY_VERSION_STRING) == 0) {
@@ -732,10 +731,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		cifs_dbg(FYI, "negotiated smb3.0 dialect\n");
 	else if (rsp->DialectRevision == cpu_to_le16(SMB302_PROT_ID))
 		cifs_dbg(FYI, "negotiated smb3.02 dialect\n");
-#ifdef CONFIG_CIFS_SMB311
 	else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID))
 		cifs_dbg(FYI, "negotiated smb3.1.1 dialect\n");
-#endif /* SMB311 */
 	else {
 		cifs_dbg(VFS, "Illegal dialect returned by server 0x%x\n",
 			 le16_to_cpu(rsp->DialectRevision));
@@ -744,9 +741,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	}
 	server->dialect = le16_to_cpu(rsp->DialectRevision);
 
-	/* BB: add check that dialect was valid given dialect(s) we asked for */
-
-#ifdef CONFIG_CIFS_SMB311
 	/*
 	 * Keep a copy of the hash after negprot. This hash will be
 	 * the starting hash value for all sessions made from this
@@ -754,7 +748,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	 */
 	memcpy(server->preauth_sha_hash, ses->preauth_sha_hash,
 	       SMB2_PREAUTH_HASH_SIZE);
-#endif
+
 	/* SMB2 only has an extended negflavor */
 	server->negflavor = CIFS_NEGFLAVOR_EXTENDED;
 	/* set it to the maximum buffer size value we can send with 1 credit */
@@ -795,7 +789,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 			rc = -EIO;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
 		if (rsp->NegotiateContextCount)
 			rc = smb311_decode_neg_context(rsp, server,
@@ -803,7 +796,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		else
 			cifs_dbg(VFS, "Missing expected negotiate contexts\n");
 	}
-#endif /* CONFIG_CIFS_SMB311 */
 neg_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -1364,13 +1356,11 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	sess_data->nls_cp = (struct nls_table *) nls_cp;
 	sess_data->previous_session = ses->Suid;
 
-#ifdef CONFIG_CIFS_SMB311
 	/*
 	 * Initialize the session hash with the server one.
 	 */
 	memcpy(ses->preauth_sha_hash, ses->server->preauth_sha_hash,
 	       SMB2_PREAUTH_HASH_SIZE);
-#endif
 
 	while (sess_data->func)
 		sess_data->func(sess_data);
@@ -1707,12 +1697,12 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
 
 static int
 add_lease_context(struct TCP_Server_Info *server, struct kvec *iov,
-		  unsigned int *num_iovec, __u8 *oplock)
+		  unsigned int *num_iovec, u8 *lease_key, __u8 *oplock)
 {
 	struct smb2_create_req *req = iov[0].iov_base;
 	unsigned int num = *num_iovec;
 
-	iov[num].iov_base = server->ops->create_lease_buf(oplock+1, *oplock);
+	iov[num].iov_base = server->ops->create_lease_buf(lease_key, *oplock);
 	if (iov[num].iov_base == NULL)
 		return -ENOMEM;
 	iov[num].iov_len = server->vals->create_lease_size;
@@ -1866,6 +1856,51 @@ add_durable_context(struct kvec *iov, unsigned int *num_iovec,
 	return 0;
 }
 
+/* See MS-SMB2 2.2.13.2.7 */
+static struct crt_twarp_ctxt *
+create_twarp_buf(__u64 timewarp)
+{
+	struct crt_twarp_ctxt *buf;
+
+	buf = kzalloc(sizeof(struct crt_twarp_ctxt), GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	buf->ccontext.DataOffset = cpu_to_le16(offsetof
+					(struct crt_twarp_ctxt, Timestamp));
+	buf->ccontext.DataLength = cpu_to_le32(8);
+	buf->ccontext.NameOffset = cpu_to_le16(offsetof
+				(struct crt_twarp_ctxt, Name));
+	buf->ccontext.NameLength = cpu_to_le16(4);
+	/* SMB2_CREATE_TIMEWARP_TOKEN is "TWrp" */
+	buf->Name[0] = 'T';
+	buf->Name[1] = 'W';
+	buf->Name[2] = 'r';
+	buf->Name[3] = 'p';
+	buf->Timestamp = cpu_to_le64(timewarp);
+	return buf;
+}
+
+/* See MS-SMB2 2.2.13.2.7 */
+static int
+add_twarp_context(struct kvec *iov, unsigned int *num_iovec, __u64 timewarp)
+{
+	struct smb2_create_req *req = iov[0].iov_base;
+	unsigned int num = *num_iovec;
+
+	iov[num].iov_base = create_twarp_buf(timewarp);
+	if (iov[num].iov_base == NULL)
+		return -ENOMEM;
+	iov[num].iov_len = sizeof(struct crt_twarp_ctxt);
+	if (!req->CreateContextsOffset)
+		req->CreateContextsOffset = cpu_to_le32(
+				sizeof(struct smb2_create_req) +
+				iov[num - 1].iov_len);
+	le32_add_cpu(&req->CreateContextsLength, sizeof(struct crt_twarp_ctxt));
+	*num_iovec = num + 1;
+	return 0;
+}
+
 static int
 alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len,
 			    const char *treename, const __le16 *path)
@@ -1911,7 +1946,6 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len,
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 			       umode_t mode, struct cifs_tcon *tcon,
 			       const char *full_path,
@@ -1919,7 +1953,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 {
 	struct smb_rqst rqst;
 	struct smb2_create_req *req;
-	struct smb2_create_rsp *rsp;
+	struct smb2_create_rsp *rsp = NULL;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[3]; /* make sure at least one for each open context */
@@ -1934,27 +1968,31 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	char *pc_buf = NULL;
 	int flags = 0;
 	unsigned int total_len;
-	__le16 *path = cifs_convert_path_to_utf16(full_path, cifs_sb);
-
-	if (!path)
-		return -ENOMEM;
+	__le16 *utf16_path = NULL;
 
 	cifs_dbg(FYI, "mkdir\n");
 
+	/* resource #1: path allocation */
+	utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
+	if (!utf16_path)
+		return -ENOMEM;
+
 	if (ses && (ses->server))
 		server = ses->server;
-	else
-		return -EIO;
+	else {
+		rc = -EIO;
+		goto err_free_path;
+	}
 
+	/* resource #2: request */
 	rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len);
-
 	if (rc)
-		return rc;
+		goto err_free_path;
+
 
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
-
 	req->ImpersonationLevel = IL_IMPERSONATION;
 	req->DesiredAccess = cpu_to_le32(FILE_WRITE_ATTRIBUTES);
 	/* File attributes ignored on open (used in create though) */
@@ -1983,50 +2021,44 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 		req->sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
 		rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
 						 &name_len,
-						 tcon->treeName, path);
-		if (rc) {
-			cifs_small_buf_release(req);
-			return rc;
-		}
+						 tcon->treeName, utf16_path);
+		if (rc)
+			goto err_free_req;
+
 		req->NameLength = cpu_to_le16(name_len * 2);
 		uni_path_len = copy_size;
-		path = copy_path;
+		/* free before overwriting resource */
+		kfree(utf16_path);
+		utf16_path = copy_path;
 	} else {
-		uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
+		uni_path_len = (2 * UniStrnlen((wchar_t *)utf16_path, PATH_MAX)) + 2;
 		/* MUST set path len (NameLength) to 0 opening root of share */
 		req->NameLength = cpu_to_le16(uni_path_len - 2);
 		if (uni_path_len % 8 != 0) {
 			copy_size = roundup(uni_path_len, 8);
 			copy_path = kzalloc(copy_size, GFP_KERNEL);
 			if (!copy_path) {
-				cifs_small_buf_release(req);
-				return -ENOMEM;
+				rc = -ENOMEM;
+				goto err_free_req;
 			}
-			memcpy((char *)copy_path, (const char *)path,
+			memcpy((char *)copy_path, (const char *)utf16_path,
 			       uni_path_len);
 			uni_path_len = copy_size;
-			path = copy_path;
+			/* free before overwriting resource */
+			kfree(utf16_path);
+			utf16_path = copy_path;
 		}
 	}
 
 	iov[1].iov_len = uni_path_len;
-	iov[1].iov_base = path;
+	iov[1].iov_base = utf16_path;
 	req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_NONE;
 
 	if (tcon->posix_extensions) {
-		if (n_iov > 2) {
-			struct create_context *ccontext =
-			    (struct create_context *)iov[n_iov-1].iov_base;
-			ccontext->Next =
-				cpu_to_le32(iov[n_iov-1].iov_len);
-		}
-
+		/* resource #3: posix buf */
 		rc = add_posix_context(iov, &n_iov, mode);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
-			return rc;
-		}
+		if (rc)
+			goto err_free_req;
 		pc_buf = iov[n_iov-1].iov_base;
 	}
 
@@ -2035,73 +2067,57 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = n_iov;
 
-	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
-			    &rsp_iov);
-
-	cifs_small_buf_release(req);
-	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
-
-	if (rc != 0) {
+	/* resource #4: response buffer */
+	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
+	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
 		trace_smb3_posix_mkdir_err(xid, tcon->tid, ses->Suid,
-				    CREATE_NOT_FILE, FILE_WRITE_ATTRIBUTES, rc);
-		goto smb311_mkdir_exit;
-	} else
-		trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid,
-				     ses->Suid, CREATE_NOT_FILE,
-				     FILE_WRITE_ATTRIBUTES);
+					   CREATE_NOT_FILE,
+					   FILE_WRITE_ATTRIBUTES, rc);
+		goto err_free_rsp_buf;
+	}
+
+	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
+	trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid,
+				    ses->Suid, CREATE_NOT_FILE,
+				    FILE_WRITE_ATTRIBUTES);
 
 	SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId);
 
 	/* Eventually save off posix specific response info and timestaps */
 
-smb311_mkdir_exit:
-	kfree(copy_path);
-	kfree(pc_buf);
+err_free_rsp_buf:
 	free_rsp_buf(resp_buftype, rsp);
+	kfree(pc_buf);
+err_free_req:
+	cifs_small_buf_release(req);
+err_free_path:
+	kfree(utf16_path);
 	return rc;
-
 }
-#endif /* SMB311 */
 
 int
-SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
-	  __u8 *oplock, struct smb2_file_all_info *buf,
-	  struct kvec *err_iov, int *buftype)
+SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock,
+	       struct cifs_open_parms *oparms, __le16 *path)
 {
-	struct smb_rqst rqst;
+	struct TCP_Server_Info *server = tcon->ses->server;
 	struct smb2_create_req *req;
-	struct smb2_create_rsp *rsp;
-	struct TCP_Server_Info *server;
-	struct cifs_tcon *tcon = oparms->tcon;
-	struct cifs_ses *ses = tcon->ses;
-	struct kvec iov[5]; /* make sure at least one for each open context */
-	struct kvec rsp_iov = {NULL, 0};
-	int resp_buftype;
-	int uni_path_len;
-	__le16 *copy_path = NULL;
-	int copy_size;
-	int rc = 0;
 	unsigned int n_iov = 2;
 	__u32 file_attributes = 0;
-	char *dhc_buf = NULL, *lc_buf = NULL, *pc_buf = NULL;
-	int flags = 0;
+	int copy_size;
+	int uni_path_len;
 	unsigned int total_len;
-
-	cifs_dbg(FYI, "create/open\n");
-
-	if (ses && (ses->server))
-		server = ses->server;
-	else
-		return -EIO;
+	struct kvec *iov = rqst->rq_iov;
+	__le16 *copy_path;
+	int rc;
 
 	rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len);
-
 	if (rc)
 		return rc;
 
-	if (smb3_encryption_required(tcon))
-		flags |= CIFS_TRANSFORM_REQ;
+	iov[0].iov_base = (char *)req;
+	/* -1 since last byte is buf[0] which is sent below (path) */
+	iov[0].iov_len = total_len - 1;
 
 	if (oparms->create_options & CREATE_OPTION_READONLY)
 		file_attributes |= ATTR_READONLY;
@@ -2115,11 +2131,6 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	req->ShareAccess = FILE_SHARE_ALL_LE;
 	req->CreateDisposition = cpu_to_le32(oparms->disposition);
 	req->CreateOptions = cpu_to_le32(oparms->create_options & CREATE_OPTIONS_MASK);
-
-	iov[0].iov_base = (char *)req;
-	/* -1 since last byte is buf[0] which is sent below (path) */
-	iov[0].iov_len = total_len - 1;
-
 	req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req));
 
 	/* [MS-SMB2] 2.2.13 NameOffset:
@@ -2137,10 +2148,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
 						 &name_len,
 						 tcon->treeName, path);
-		if (rc) {
-			cifs_small_buf_release(req);
+		if (rc)
 			return rc;
-		}
 		req->NameLength = cpu_to_le16(name_len * 2);
 		uni_path_len = copy_size;
 		path = copy_path;
@@ -2148,18 +2157,16 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
 		/* MUST set path len (NameLength) to 0 opening root of share */
 		req->NameLength = cpu_to_le16(uni_path_len - 2);
-		if (uni_path_len % 8 != 0) {
-			copy_size = roundup(uni_path_len, 8);
-			copy_path = kzalloc(copy_size, GFP_KERNEL);
-			if (!copy_path) {
-				cifs_small_buf_release(req);
-				return -ENOMEM;
-			}
-			memcpy((char *)copy_path, (const char *)path,
-			       uni_path_len);
-			uni_path_len = copy_size;
-			path = copy_path;
-		}
+		copy_size = uni_path_len;
+		if (copy_size % 8 != 0)
+			copy_size = roundup(copy_size, 8);
+		copy_path = kzalloc(copy_size, GFP_KERNEL);
+		if (!copy_path)
+			return -ENOMEM;
+		memcpy((char *)copy_path, (const char *)path,
+		       uni_path_len);
+		uni_path_len = copy_size;
+		path = copy_path;
 	}
 
 	iov[1].iov_len = uni_path_len;
@@ -2172,13 +2179,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	    *oplock == SMB2_OPLOCK_LEVEL_NONE)
 		req->RequestedOplockLevel = *oplock;
 	else {
-		rc = add_lease_context(server, iov, &n_iov, oplock);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
+		rc = add_lease_context(server, iov, &n_iov,
+				       oparms->fid->lease_key, oplock);
+		if (rc)
 			return rc;
-		}
-		lc_buf = iov[n_iov-1].iov_base;
 	}
 
 	if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
@@ -2192,16 +2196,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 
 		rc = add_durable_context(iov, &n_iov, oparms,
 					tcon->use_persistent);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
-			kfree(lc_buf);
+		if (rc)
 			return rc;
-		}
-		dhc_buf = iov[n_iov-1].iov_base;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	if (tcon->posix_extensions) {
 		if (n_iov > 2) {
 			struct create_context *ccontext =
@@ -2211,24 +2209,79 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		}
 
 		rc = add_posix_context(iov, &n_iov, oparms->mode);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
-			kfree(lc_buf);
-			kfree(dhc_buf);
+		if (rc)
 			return rc;
+	}
+
+	if (tcon->snapshot_time) {
+		cifs_dbg(FYI, "adding snapshot context\n");
+		if (n_iov > 2) {
+			struct create_context *ccontext =
+			    (struct create_context *)iov[n_iov-1].iov_base;
+			ccontext->Next =
+				cpu_to_le32(iov[n_iov-1].iov_len);
 		}
-		pc_buf = iov[n_iov-1].iov_base;
+
+		rc = add_twarp_context(iov, &n_iov, tcon->snapshot_time);
+		if (rc)
+			return rc;
 	}
-#endif /* SMB311 */
+
+
+	rqst->rq_nvec = n_iov;
+	return 0;
+}
+
+/* rq_iov[0] is the request and is released by cifs_small_buf_release().
+ * All other vectors are freed by kfree().
+ */
+void
+SMB2_open_free(struct smb_rqst *rqst)
+{
+	int i;
+
+	cifs_small_buf_release(rqst->rq_iov[0].iov_base);
+	for (i = 1; i < rqst->rq_nvec; i++)
+		if (rqst->rq_iov[i].iov_base != smb2_padding)
+			kfree(rqst->rq_iov[i].iov_base);
+}
+
+int
+SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
+	  __u8 *oplock, struct smb2_file_all_info *buf,
+	  struct kvec *err_iov, int *buftype)
+{
+	struct smb_rqst rqst;
+	struct smb2_create_rsp *rsp = NULL;
+	struct TCP_Server_Info *server;
+	struct cifs_tcon *tcon = oparms->tcon;
+	struct cifs_ses *ses = tcon->ses;
+	struct kvec iov[5]; /* make sure at least one for each open context */
+	struct kvec rsp_iov = {NULL, 0};
+	int resp_buftype;
+	int rc = 0;
+	int flags = 0;
+
+	cifs_dbg(FYI, "create/open\n");
+	if (ses && (ses->server))
+		server = ses->server;
+	else
+		return -EIO;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
 
 	memset(&rqst, 0, sizeof(struct smb_rqst));
+	memset(&iov, 0, sizeof(iov));
 	rqst.rq_iov = iov;
-	rqst.rq_nvec = n_iov;
+	rqst.rq_nvec = 5;
+
+	rc = SMB2_open_init(tcon, &rqst, oplock, oparms, path);
+	if (rc)
+		goto creat_exit;
 
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
 			    &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
@@ -2265,10 +2318,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	else
 		*oplock = rsp->OplockLevel;
 creat_exit:
-	kfree(copy_path);
-	kfree(lc_buf);
-	kfree(dhc_buf);
-	kfree(pc_buf);
+	SMB2_open_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
@@ -2459,43 +2509,62 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 }
 
 int
+SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+		u64 persistent_fid, u64 volatile_fid)
+{
+	struct smb2_close_req *req;
+	struct kvec *iov = rqst->rq_iov;
+	unsigned int total_len;
+	int rc;
+
+	rc = smb2_plain_req_init(SMB2_CLOSE, tcon, (void **) &req, &total_len);
+	if (rc)
+		return rc;
+
+	req->PersistentFileId = persistent_fid;
+	req->VolatileFileId = volatile_fid;
+	iov[0].iov_base = (char *)req;
+	iov[0].iov_len = total_len;
+
+	return 0;
+}
+
+void
+SMB2_close_free(struct smb_rqst *rqst)
+{
+	cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+}
+
+int
 SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
 		 u64 persistent_fid, u64 volatile_fid, int flags)
 {
 	struct smb_rqst rqst;
-	struct smb2_close_req *req;
-	struct smb2_close_rsp *rsp;
+	struct smb2_close_rsp *rsp = NULL;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[1];
 	struct kvec rsp_iov;
 	int resp_buftype;
 	int rc = 0;
-	unsigned int total_len;
 
 	cifs_dbg(FYI, "Close\n");
 
 	if (!ses || !(ses->server))
 		return -EIO;
 
-	rc = smb2_plain_req_init(SMB2_CLOSE, tcon, (void **) &req, &total_len);
-	if (rc)
-		return rc;
-
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
-	req->PersistentFileId = persistent_fid;
-	req->VolatileFileId = volatile_fid;
-
-	iov[0].iov_base = (char *)req;
-	iov[0].iov_len = total_len;
-
 	memset(&rqst, 0, sizeof(struct smb_rqst));
+	memset(&iov, 0, sizeof(iov));
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
+	rc = SMB2_close_init(tcon, &rqst, persistent_fid, volatile_fid);
+	if (rc)
+		goto close_exit;
+
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_close_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
@@ -2508,6 +2577,7 @@ SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
 	/* BB FIXME - decode close response, update inode for caching */
 
 close_exit:
+	SMB2_close_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
@@ -2519,9 +2589,9 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	return SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0);
 }
 
-static int
-validate_iov(unsigned int offset, unsigned int buffer_length,
-	     struct kvec *iov, unsigned int min_buf_size)
+int
+smb2_validate_iov(unsigned int offset, unsigned int buffer_length,
+		  struct kvec *iov, unsigned int min_buf_size)
 {
 	unsigned int smb_len = iov->iov_len;
 	char *end_of_smb = smb_len + (char *)iov->iov_base;
@@ -2565,7 +2635,7 @@ validate_and_copy_iov(unsigned int offset, unsigned int buffer_length,
 	if (!data)
 		return -EINVAL;
 
-	rc = validate_iov(offset, buffer_length, iov, minbufsize);
+	rc = smb2_validate_iov(offset, buffer_length, iov, minbufsize);
 	if (rc)
 		return rc;
 
@@ -2574,36 +2644,22 @@ validate_and_copy_iov(unsigned int offset, unsigned int buffer_length,
 	return 0;
 }
 
-static int
-query_info(const unsigned int xid, struct cifs_tcon *tcon,
-	   u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type,
-	   u32 additional_info, size_t output_len, size_t min_len, void **data,
-		u32 *dlen)
+int
+SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+		     u64 persistent_fid, u64 volatile_fid,
+		     u8 info_class, u8 info_type, u32 additional_info,
+		     size_t output_len)
 {
-	struct smb_rqst rqst;
 	struct smb2_query_info_req *req;
-	struct smb2_query_info_rsp *rsp = NULL;
-	struct kvec iov[2];
-	struct kvec rsp_iov;
-	int rc = 0;
-	int resp_buftype;
-	struct cifs_ses *ses = tcon->ses;
-	int flags = 0;
+	struct kvec *iov = rqst->rq_iov;
 	unsigned int total_len;
-
-	cifs_dbg(FYI, "Query Info\n");
-
-	if (!ses || !(ses->server))
-		return -EIO;
+	int rc;
 
 	rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, (void **) &req,
 			     &total_len);
 	if (rc)
 		return rc;
 
-	if (smb3_encryption_required(tcon))
-		flags |= CIFS_TRANSFORM_REQ;
-
 	req->InfoType = info_type;
 	req->FileInfoClass = info_class;
 	req->PersistentFileId = persistent_fid;
@@ -2620,13 +2676,50 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	iov[0].iov_base = (char *)req;
 	/* 1 for Buffer */
 	iov[0].iov_len = total_len - 1;
+	return 0;
+}
+
+void
+SMB2_query_info_free(struct smb_rqst *rqst)
+{
+	cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+}
+
+static int
+query_info(const unsigned int xid, struct cifs_tcon *tcon,
+	   u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type,
+	   u32 additional_info, size_t output_len, size_t min_len, void **data,
+		u32 *dlen)
+{
+	struct smb_rqst rqst;
+	struct smb2_query_info_rsp *rsp = NULL;
+	struct kvec iov[1];
+	struct kvec rsp_iov;
+	int rc = 0;
+	int resp_buftype;
+	struct cifs_ses *ses = tcon->ses;
+	int flags = 0;
+
+	cifs_dbg(FYI, "Query Info\n");
+
+	if (!ses || !(ses->server))
+		return -EIO;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
 
 	memset(&rqst, 0, sizeof(struct smb_rqst));
+	memset(&iov, 0, sizeof(iov));
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
+	rc = SMB2_query_info_init(tcon, &rqst, persistent_fid, volatile_fid,
+				  info_class, info_type, additional_info,
+				  output_len);
+	if (rc)
+		goto qinf_exit;
+
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
@@ -2655,6 +2748,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 				   &rsp_iov, min_len, *data);
 
 qinf_exit:
+	SMB2_query_info_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
@@ -3613,9 +3707,9 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 		goto qdir_exit;
 	}
 
-	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
-			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
-			  info_buf_size);
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			       info_buf_size);
 	if (rc)
 		goto qdir_exit;
 
@@ -3720,7 +3814,7 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
 			    &rsp_iov);
-	cifs_small_buf_release(req);
+	cifs_buf_release(req);
 	rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
@@ -3917,9 +4011,9 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 	return rc;
 }
 
-static void
-copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
-			struct kstatfs *kst)
+void
+smb2_copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
+			     struct kstatfs *kst)
 {
 	kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) *
 			  le32_to_cpu(pfs_inf->SectorsPerAllocationUnit);
@@ -3929,6 +4023,25 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
 	return;
 }
 
+static void
+copy_posix_fs_info_to_kstatfs(FILE_SYSTEM_POSIX_INFO *response_data,
+			struct kstatfs *kst)
+{
+	kst->f_bsize = le32_to_cpu(response_data->BlockSize);
+	kst->f_blocks = le64_to_cpu(response_data->TotalBlocks);
+	kst->f_bfree =  le64_to_cpu(response_data->BlocksAvail);
+	if (response_data->UserBlocksAvail == cpu_to_le64(-1))
+		kst->f_bavail = kst->f_bfree;
+	else
+		kst->f_bavail = le64_to_cpu(response_data->UserBlocksAvail);
+	if (response_data->TotalFileNodes != cpu_to_le64(-1))
+		kst->f_files = le64_to_cpu(response_data->TotalFileNodes);
+	if (response_data->FreeFileNodes != cpu_to_le64(-1))
+		kst->f_ffree = le64_to_cpu(response_data->FreeFileNodes);
+
+	return;
+}
+
 static int
 build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
 		   int outbuf_len, u64 persistent_fid, u64 volatile_fid)
@@ -3966,6 +4079,54 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
 }
 
 int
+SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
+	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
+{
+	struct smb_rqst rqst;
+	struct smb2_query_info_rsp *rsp = NULL;
+	struct kvec iov;
+	struct kvec rsp_iov;
+	int rc = 0;
+	int resp_buftype;
+	struct cifs_ses *ses = tcon->ses;
+	FILE_SYSTEM_POSIX_INFO *info = NULL;
+	int flags = 0;
+
+	rc = build_qfs_info_req(&iov, tcon, FS_POSIX_INFORMATION,
+				sizeof(FILE_SYSTEM_POSIX_INFO),
+				persistent_fid, volatile_fid);
+	if (rc)
+		return rc;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	memset(&rqst, 0, sizeof(struct smb_rqst));
+	rqst.rq_iov = &iov;
+	rqst.rq_nvec = 1;
+
+	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(iov.iov_base);
+	if (rc) {
+		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
+		goto posix_qfsinf_exit;
+	}
+	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
+
+	info = (FILE_SYSTEM_POSIX_INFO *)(
+		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			       sizeof(FILE_SYSTEM_POSIX_INFO));
+	if (!rc)
+		copy_posix_fs_info_to_kstatfs(info, fsdata);
+
+posix_qfsinf_exit:
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+	return rc;
+}
+
+int
 SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
 {
@@ -4002,11 +4163,11 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	info = (struct smb2_fs_full_size_info *)(
 		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
-	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
-			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
-			  sizeof(struct smb2_fs_full_size_info));
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			       sizeof(struct smb2_fs_full_size_info));
 	if (!rc)
-		copy_fs_info_to_kstatfs(info, fsdata);
+		smb2_copy_fs_info_to_kstatfs(info, fsdata);
 
 qfsinf_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
@@ -4036,6 +4197,9 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	} else if (level == FS_SECTOR_SIZE_INFORMATION) {
 		max_len = sizeof(struct smb3_fs_ss_info);
 		min_len = sizeof(struct smb3_fs_ss_info);
+	} else if (level == FS_VOLUME_INFORMATION) {
+		max_len = sizeof(struct smb3_fs_vol_info) + MAX_VOL_LABEL_LEN;
+		min_len = sizeof(struct smb3_fs_vol_info);
 	} else {
 		cifs_dbg(FYI, "Invalid qfsinfo level %d\n", level);
 		return -EINVAL;
@@ -4063,7 +4227,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rsp_len = le32_to_cpu(rsp->OutputBufferLength);
 	offset = le16_to_cpu(rsp->OutputBufferOffset);
-	rc = validate_iov(offset, rsp_len, &rsp_iov, min_len);
+	rc = smb2_validate_iov(offset, rsp_len, &rsp_iov, min_len);
 	if (rc)
 		goto qfsattr_exit;
 
@@ -4080,6 +4244,11 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 		tcon->ss_flags = le32_to_cpu(ss_info->Flags);
 		tcon->perf_sector_size =
 			le32_to_cpu(ss_info->PhysicalBytesPerSectorForPerf);
+	} else if (level == FS_VOLUME_INFORMATION) {
+		struct smb3_fs_vol_info *vol_info = (struct smb3_fs_vol_info *)
+			(offset + (char *)rsp);
+		tcon->vol_serial_number = vol_info->VolumeSerialNumber;
+		tcon->vol_create_time = vol_info->VolumeCreationTime;
 	}
 
 qfsattr_exit:
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 824dddeee3f2..a2eeae9e0432 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -153,6 +153,8 @@ struct smb2_transform_hdr {
  *
  */
 
+#define COMPOUND_FID 0xFFFFFFFFFFFFFFFFULL
+
 #define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
 
 struct smb2_err_rsp {
@@ -678,16 +680,14 @@ struct create_context {
 #define SMB2_LEASE_KEY_SIZE 16
 
 struct lease_context {
-	__le64 LeaseKeyLow;
-	__le64 LeaseKeyHigh;
+	u8 LeaseKey[SMB2_LEASE_KEY_SIZE];
 	__le32 LeaseState;
 	__le32 LeaseFlags;
 	__le64 LeaseDuration;
 } __packed;
 
 struct lease_context_v2 {
-	__le64 LeaseKeyLow;
-	__le64 LeaseKeyHigh;
+	u8 LeaseKey[SMB2_LEASE_KEY_SIZE];
 	__le32 LeaseState;
 	__le32 LeaseFlags;
 	__le64 LeaseDuration;
@@ -767,6 +767,14 @@ struct create_durable_handle_reconnect_v2 {
 	struct durable_reconnect_context_v2 dcontext;
 } __packed;
 
+/* See MS-SMB2 2.2.13.2.5 */
+struct crt_twarp_ctxt {
+	struct create_context ccontext;
+	__u8	Name[8];
+	__le64	Timestamp;
+
+} __packed;
+
 #define COPY_CHUNK_RES_KEY_SIZE	24
 struct resume_key_req {
 	char ResumeKey[COPY_CHUNK_RES_KEY_SIZE];
@@ -1225,6 +1233,7 @@ struct smb2_lease_ack {
 #define FS_DRIVER_PATH_INFORMATION	9 /* Local only */
 #define FS_VOLUME_FLAGS_INFORMATION	10 /* Local only */
 #define FS_SECTOR_SIZE_INFORMATION	11 /* SMB3 or later. Query */
+#define FS_POSIX_INFORMATION		100 /* SMB3.1.1 POSIX. Query */
 
 struct smb2_fs_full_size_info {
 	__le64 TotalAllocationUnits;
@@ -1250,6 +1259,17 @@ struct smb3_fs_ss_info {
 	__le32 ByteOffsetForPartitionAlignment;
 } __packed;
 
+/* volume info struct - see MS-FSCC 2.5.9 */
+#define MAX_VOL_LABEL_LEN	32
+struct smb3_fs_vol_info {
+	__le64	VolumeCreationTime;
+	__u32	VolumeSerialNumber;
+	__le32	VolumeLabelLength; /* includes trailing null */
+	__u8	SupportsObjects; /* True if eg like NTFS, supports objects */
+	__u8	Reserved;
+	__u8	VolumeLabel[0]; /* variable len */
+} __packed;
+
 /* partial list of QUERY INFO levels */
 #define FILE_DIRECTORY_INFORMATION	1
 #define FILE_FULL_DIRECTORY_INFORMATION 2
@@ -1363,4 +1383,6 @@ struct smb2_file_eof_info { /* encoding of request for level 10 */
 	__le64 EndOfFile; /* new end of file value */
 } __packed; /* level 20 Set */
 
+extern char smb2_padding[7];
+
 #endif				/* _SMB2PDU_H */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 3ae208ac2a77..b4076577eeb7 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -68,6 +68,7 @@ extern int smb3_handle_read_data(struct TCP_Server_Info *server,
 
 extern int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
 			struct cifs_fid *pfid);
+extern void close_shroot(struct cached_fid *cfid);
 extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst,
 				   struct smb2_file_all_info *src);
 extern int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
@@ -113,8 +114,8 @@ extern int smb2_unlock_range(struct cifsFileInfo *cfile,
 extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile);
 extern void smb2_reconnect_server(struct work_struct *work);
 extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server);
-extern unsigned long
-smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker);
+extern unsigned long smb_rqst_len(struct TCP_Server_Info *server,
+				  struct smb_rqst *rqst);
 
 /*
  * SMB2 Worker functions - most of protocol specific implementation details
@@ -132,6 +133,10 @@ extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms,
 		     __le16 *path, __u8 *oplock,
 		     struct smb2_file_all_info *buf,
 		     struct kvec *err_iov, int *resp_buftype);
+extern int SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+			  __u8 *oplock, struct cifs_open_parms *oparms,
+			  __le16 *path);
+extern void SMB2_open_free(struct smb_rqst *rqst);
 extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
 		     u64 persistent_fid, u64 volatile_fid, u32 opcode,
 		     bool is_fsctl, char *in_data, u32 indatalen,
@@ -140,6 +145,9 @@ extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
 extern int SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
 			    u64 persistent_fid, u64 volatile_fid, int flags);
+extern int SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+		      u64 persistent_file_id, u64 volatile_file_id);
+extern void SMB2_close_free(struct smb_rqst *rqst);
 extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
 extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
@@ -149,6 +157,11 @@ extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 			   u64 persistent_file_id, u64 volatile_file_id,
 			   struct smb2_file_all_info *data);
+extern int SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+				u64 persistent_fid, u64 volatile_fid,
+				u8 info_class, u8 info_type,
+				u32 additional_info, size_t output_len);
+extern void SMB2_query_info_free(struct smb_rqst *rqst);
 extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
 			   u64 persistent_file_id, u64 volatile_file_id,
 			   void **data, unsigned int *plen);
@@ -197,6 +210,9 @@ void smb2_cancelled_close_fid(struct work_struct *work);
 extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id,
 			 struct kstatfs *FSData);
+extern int SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
+			 u64 persistent_file_id, u64 volatile_file_id,
+			 struct kstatfs *FSData);
 extern int SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id, int lvl);
 extern int SMB2_lock(const unsigned int xid, struct cifs_tcon *tcon,
@@ -213,9 +229,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
 extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
 					enum securityEnum);
-#ifdef CONFIG_CIFS_SMB311
+extern int smb3_encryption_required(const struct cifs_tcon *tcon);
+extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length,
+			     struct kvec *iov, unsigned int min_buf_size);
+extern void smb2_copy_fs_info_to_kstatfs(
+	 struct smb2_fs_full_size_info *pfs_inf,
+	 struct kstatfs *kst);
 extern int smb311_crypto_shash_allocate(struct TCP_Server_Info *server);
 extern int smb311_update_preauth_hash(struct cifs_ses *ses,
 				      struct kvec *iov, int nvec);
-#endif
 #endif			/* _SMB2PROTO_H */
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 51b9437c3c7b..7b351c65ee46 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -70,7 +70,6 @@ err:
 	return rc;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int
 smb311_crypto_shash_allocate(struct TCP_Server_Info *server)
 {
@@ -98,7 +97,6 @@ err:
 	cifs_free_hash(&p->hmacsha256, &p->sdeschmacsha256);
 	return rc;
 }
-#endif
 
 static struct cifs_ses *
 smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
@@ -173,6 +171,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	struct kvec *iov = rqst->rq_iov;
 	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
 	struct cifs_ses *ses;
+	struct shash_desc *shash;
+	struct smb_rqst drqst;
 
 	ses = smb2_find_smb_ses(server, shdr->SessionId);
 	if (!ses) {
@@ -185,26 +185,45 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 
 	rc = smb2_crypto_shash_allocate(server);
 	if (rc) {
-		cifs_dbg(VFS, "%s: shah256 alloc failed\n", __func__);
+		cifs_dbg(VFS, "%s: sha256 alloc failed\n", __func__);
 		return rc;
 	}
 
 	rc = crypto_shash_setkey(server->secmech.hmacsha256,
-		ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
+				 ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not update with response\n", __func__);
 		return rc;
 	}
 
-	rc = crypto_shash_init(&server->secmech.sdeschmacsha256->shash);
+	shash = &server->secmech.sdeschmacsha256->shash;
+	rc = crypto_shash_init(shash);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not init sha256", __func__);
 		return rc;
 	}
 
-	rc = __cifs_calc_signature(rqst, server, sigptr,
-		&server->secmech.sdeschmacsha256->shash);
+	/*
+	 * For SMB2+, __cifs_calc_signature() expects to sign only the actual
+	 * data, that is, iov[0] should not contain a rfc1002 length.
+	 *
+	 * Sign the rfc1002 length prior to passing the data (iov[1-N]) down to
+	 * __cifs_calc_signature().
+	 */
+	drqst = *rqst;
+	if (drqst.rq_nvec >= 2 && iov[0].iov_len == 4) {
+		rc = crypto_shash_update(shash, iov[0].iov_base,
+					 iov[0].iov_len);
+		if (rc) {
+			cifs_dbg(VFS, "%s: Could not update with payload\n",
+				 __func__);
+			return rc;
+		}
+		drqst.rq_iov++;
+		drqst.rq_nvec--;
+	}
 
+	rc = __cifs_calc_signature(&drqst, server, sigptr, shash);
 	if (!rc)
 		memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
 
@@ -375,7 +394,6 @@ generate_smb30signingkey(struct cifs_ses *ses)
 	return generate_smb3signingkey(ses, &triplet);
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int
 generate_smb311signingkey(struct cifs_ses *ses)
 
@@ -403,17 +421,18 @@ generate_smb311signingkey(struct cifs_ses *ses)
 
 	return generate_smb3signingkey(ses, &triplet);
 }
-#endif /* 311 */
 
 int
 smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 {
-	int rc = 0;
+	int rc;
 	unsigned char smb3_signature[SMB2_CMACAES_SIZE];
 	unsigned char *sigptr = smb3_signature;
 	struct kvec *iov = rqst->rq_iov;
 	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
 	struct cifs_ses *ses;
+	struct shash_desc *shash = &server->secmech.sdesccmacaes->shash;
+	struct smb_rqst drqst;
 
 	ses = smb2_find_smb_ses(server, shdr->SessionId);
 	if (!ses) {
@@ -425,8 +444,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE);
 
 	rc = crypto_shash_setkey(server->secmech.cmacaes,
-		ses->smb3signingkey, SMB2_CMACAES_SIZE);
-
+				 ses->smb3signingkey, SMB2_CMACAES_SIZE);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not set key for cmac aes\n", __func__);
 		return rc;
@@ -437,15 +455,33 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	 * so unlike smb2 case we do not have to check here if secmech are
 	 * initialized
 	 */
-	rc = crypto_shash_init(&server->secmech.sdesccmacaes->shash);
+	rc = crypto_shash_init(shash);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not init cmac aes\n", __func__);
 		return rc;
 	}
 
-	rc = __cifs_calc_signature(rqst, server, sigptr,
-				   &server->secmech.sdesccmacaes->shash);
+	/*
+	 * For SMB2+, __cifs_calc_signature() expects to sign only the actual
+	 * data, that is, iov[0] should not contain a rfc1002 length.
+	 *
+	 * Sign the rfc1002 length prior to passing the data (iov[1-N]) down to
+	 * __cifs_calc_signature().
+	 */
+	drqst = *rqst;
+	if (drqst.rq_nvec >= 2 && iov[0].iov_len == 4) {
+		rc = crypto_shash_update(shash, iov[0].iov_base,
+					 iov[0].iov_len);
+		if (rc) {
+			cifs_dbg(VFS, "%s: Could not update with payload\n",
+				 __func__);
+			return rc;
+		}
+		drqst.rq_iov++;
+		drqst.rq_nvec--;
+	}
 
+	rc = __cifs_calc_signature(&drqst, server, sigptr, shash);
 	if (!rc)
 		memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
 
@@ -548,6 +584,7 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr,
 
 	temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
 	memset(temp, 0, sizeof(struct mid_q_entry));
+	kref_init(&temp->refcount);
 	temp->mid = le64_to_cpu(shdr->MessageId);
 	temp->pid = current->pid;
 	temp->command = shdr->Command; /* Always LE */
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index 6fd94d9ffac2..c55ea4e6201b 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -2083,8 +2083,9 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg)
  * rqst: the data to write
  * return value: 0 if successfully write, otherwise error code
  */
-int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
+int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
+	struct smbd_connection *info = server->smbd_conn;
 	struct kvec vec;
 	int nvecs;
 	int size;
@@ -2118,7 +2119,7 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
 	 * rq_tailsz to PAGE_SIZE when the buffer has multiple pages and
 	 * ends at page boundary
 	 */
-	buflen = smb2_rqst_len(rqst, true);
+	buflen = smb_rqst_len(server, rqst);
 
 	if (buflen + sizeof(struct smbd_data_transfer) >
 		info->max_fragmented_send_size) {
diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h
index 1e419c21dc60..a11096254f29 100644
--- a/fs/cifs/smbdirect.h
+++ b/fs/cifs/smbdirect.h
@@ -292,7 +292,7 @@ void smbd_destroy(struct smbd_connection *info);
 
 /* Interface for carrying upper layer I/O through send/recv */
 int smbd_recv(struct smbd_connection *info, struct msghdr *msg);
-int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst);
+int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst);
 
 enum mr_state {
 	MR_READY,
@@ -332,7 +332,7 @@ static inline void *smbd_get_connection(
 static inline int smbd_reconnect(struct TCP_Server_Info *server) {return -1; }
 static inline void smbd_destroy(struct smbd_connection *info) {}
 static inline int smbd_recv(struct smbd_connection *info, struct msghdr *msg) {return -1; }
-static inline int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) {return -1; }
+static inline int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) {return -1; }
 #endif
 
 #endif
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index 67e413f6ee4d..d4aed5217a56 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -281,6 +281,44 @@ DEFINE_EVENT(smb3_cmd_done_class, smb3_##name,    \
 	TP_ARGS(tid, sesid, cmd, mid))
 
 DEFINE_SMB3_CMD_DONE_EVENT(cmd_done);
+DEFINE_SMB3_CMD_DONE_EVENT(ses_expired);
+
+DECLARE_EVENT_CLASS(smb3_mid_class,
+	TP_PROTO(__u16	cmd,
+		__u64	mid,
+		__u32	pid,
+		unsigned long when_sent,
+		unsigned long when_received),
+	TP_ARGS(cmd, mid, pid, when_sent, when_received),
+	TP_STRUCT__entry(
+		__field(__u16, cmd)
+		__field(__u64, mid)
+		__field(__u32, pid)
+		__field(unsigned long, when_sent)
+		__field(unsigned long, when_received)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+		__entry->mid = mid;
+		__entry->pid = pid;
+		__entry->when_sent = when_sent;
+		__entry->when_received = when_received;
+	),
+	TP_printk("\tcmd=%u mid=%llu pid=%u, when_sent=%lu when_rcv=%lu",
+		__entry->cmd, __entry->mid, __entry->pid, __entry->when_sent,
+		__entry->when_received)
+)
+
+#define DEFINE_SMB3_MID_EVENT(name)          \
+DEFINE_EVENT(smb3_mid_class, smb3_##name,    \
+	TP_PROTO(__u16	cmd,			\
+		__u64	mid,			\
+		__u32	pid,			\
+		unsigned long when_sent,	\
+		unsigned long when_received),	\
+	TP_ARGS(cmd, mid, pid, when_sent, when_received))
+
+DEFINE_SMB3_MID_EVENT(slow_rsp);
 
 DECLARE_EVENT_CLASS(smb3_exit_err_class,
 	TP_PROTO(unsigned int xid,
@@ -422,6 +460,32 @@ DEFINE_EVENT(smb3_open_done_class, smb3_##name,  \
 DEFINE_SMB3_OPEN_DONE_EVENT(open_done);
 DEFINE_SMB3_OPEN_DONE_EVENT(posix_mkdir_done);
 
+DECLARE_EVENT_CLASS(smb3_reconnect_class,
+	TP_PROTO(__u64	currmid,
+		char *hostname),
+	TP_ARGS(currmid, hostname),
+	TP_STRUCT__entry(
+		__field(__u64, currmid)
+		__field(char *, hostname)
+	),
+	TP_fast_assign(
+		__entry->currmid = currmid;
+		__entry->hostname = hostname;
+	),
+	TP_printk("server=%s current_mid=0x%llx",
+		__entry->hostname,
+		__entry->currmid)
+)
+
+#define DEFINE_SMB3_RECONNECT_EVENT(name)        \
+DEFINE_EVENT(smb3_reconnect_class, smb3_##name,  \
+	TP_PROTO(__u64	currmid,		\
+		char *hostname),		\
+	TP_ARGS(currmid, hostname))
+
+DEFINE_SMB3_RECONNECT_EVENT(reconnect);
+DEFINE_SMB3_RECONNECT_EVENT(partial_send_reconnect);
+
 #endif /* _CIFS_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index fb57dfbfb749..78f96fa3d7d9 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -61,6 +61,7 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 
 	temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
 	memset(temp, 0, sizeof(struct mid_q_entry));
+	kref_init(&temp->refcount);
 	temp->mid = get_mid(smb_buffer);
 	temp->pid = current->pid;
 	temp->command = cpu_to_le16(smb_buffer->Command);
@@ -82,6 +83,21 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 	return temp;
 }
 
+static void _cifs_mid_q_entry_release(struct kref *refcount)
+{
+	struct mid_q_entry *mid = container_of(refcount, struct mid_q_entry,
+					       refcount);
+
+	mempool_free(mid, cifs_mid_poolp);
+}
+
+void cifs_mid_q_entry_release(struct mid_q_entry *midEntry)
+{
+	spin_lock(&GlobalMid_Lock);
+	kref_put(&midEntry->refcount, _cifs_mid_q_entry_release);
+	spin_unlock(&GlobalMid_Lock);
+}
+
 void
 DeleteMidQEntry(struct mid_q_entry *midEntry)
 {
@@ -99,8 +115,17 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 	now = jiffies;
 	/* commands taking longer than one second are indications that
 	   something is wrong, unless it is quite a slow link or server */
-	if (time_after(now, midEntry->when_alloc + HZ)) {
-		if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) {
+	if (time_after(now, midEntry->when_alloc + HZ) &&
+	    (midEntry->command != command)) {
+		/* smb2slowcmd[NUMBER_OF_SMB2_COMMANDS] counts by command */
+		if ((le16_to_cpu(midEntry->command) < NUMBER_OF_SMB2_COMMANDS) &&
+		    (le16_to_cpu(midEntry->command) >= 0))
+			cifs_stats_inc(&midEntry->server->smb2slowcmd[le16_to_cpu(midEntry->command)]);
+
+		trace_smb3_slow_rsp(le16_to_cpu(midEntry->command),
+			       midEntry->mid, midEntry->pid,
+			       midEntry->when_sent, midEntry->when_received);
+		if (cifsFYI & CIFS_TIMER) {
 			pr_debug(" CIFS slow rsp: cmd %d mid %llu",
 			       midEntry->command, midEntry->mid);
 			pr_info(" A: 0x%lx S: 0x%lx R: 0x%lx\n",
@@ -110,7 +135,7 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 		}
 	}
 #endif
-	mempool_free(midEntry, cifs_mid_poolp);
+	cifs_mid_q_entry_release(midEntry);
 }
 
 void
@@ -202,14 +227,15 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg,
 }
 
 unsigned long
-smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker)
+smb_rqst_len(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
 	unsigned int i;
 	struct kvec *iov;
 	int nvec;
 	unsigned long buflen = 0;
 
-	if (skip_rfc1002_marker && rqst->rq_iov[0].iov_len == 4) {
+	if (server->vals->header_preamble_size == 0 &&
+	    rqst->rq_nvec >= 2 && rqst->rq_iov[0].iov_len == 4) {
 		iov = &rqst->rq_iov[1];
 		nvec = rqst->rq_nvec - 1;
 	} else {
@@ -260,7 +286,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	__be32 rfc1002_marker;
 
 	if (cifs_rdma_enabled(server) && server->smbd_conn) {
-		rc = smbd_send(server->smbd_conn, rqst);
+		rc = smbd_send(server, rqst);
 		goto smbd_done;
 	}
 	if (ssocket == NULL)
@@ -271,7 +297,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 				(char *)&val, sizeof(val));
 
 	for (j = 0; j < num_rqst; j++)
-		send_length += smb2_rqst_len(&rqst[j], true);
+		send_length += smb_rqst_len(server, &rqst[j]);
 	rfc1002_marker = cpu_to_be32(send_length);
 
 	/* Generate a rfc1002 marker for SMB2+ */
@@ -344,6 +370,8 @@ uncork:
 		 * socket so the server throws away the partial SMB
 		 */
 		server->tcpStatus = CifsNeedReconnect;
+		trace_smb3_partial_send_reconnect(server->CurrentMid,
+						  server->hostname);
 	}
 smbd_done:
 	if (rc < 0 && rc != -EINTR)
@@ -356,26 +384,42 @@ smbd_done:
 }
 
 static int
-smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags)
+smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
+	      struct smb_rqst *rqst, int flags)
 {
-	struct smb_rqst cur_rqst;
+	struct kvec iov;
+	struct smb2_transform_hdr tr_hdr;
+	struct smb_rqst cur_rqst[MAX_COMPOUND];
 	int rc;
 
 	if (!(flags & CIFS_TRANSFORM_REQ))
-		return __smb_send_rqst(server, 1, rqst);
+		return __smb_send_rqst(server, num_rqst, rqst);
 
-	if (!server->ops->init_transform_rq ||
-	    !server->ops->free_transform_rq) {
-		cifs_dbg(VFS, "Encryption requested but transform callbacks are missed\n");
+	if (num_rqst > MAX_COMPOUND - 1)
+		return -ENOMEM;
+
+	memset(&cur_rqst[0], 0, sizeof(cur_rqst));
+	memset(&iov, 0, sizeof(iov));
+	memset(&tr_hdr, 0, sizeof(tr_hdr));
+
+	iov.iov_base = &tr_hdr;
+	iov.iov_len = sizeof(tr_hdr);
+	cur_rqst[0].rq_iov = &iov;
+	cur_rqst[0].rq_nvec = 1;
+
+	if (!server->ops->init_transform_rq) {
+		cifs_dbg(VFS, "Encryption requested but transform callback "
+			 "is missing\n");
 		return -EIO;
 	}
 
-	rc = server->ops->init_transform_rq(server, &cur_rqst, rqst);
+	rc = server->ops->init_transform_rq(server, num_rqst + 1,
+					    &cur_rqst[0], rqst);
 	if (rc)
 		return rc;
 
-	rc = __smb_send_rqst(server, 1, &cur_rqst);
-	server->ops->free_transform_rq(&cur_rqst);
+	rc = __smb_send_rqst(server, num_rqst + 1, &cur_rqst[0]);
+	smb3_free_compound_rqst(num_rqst, &cur_rqst[1]);
 	return rc;
 }
 
@@ -589,7 +633,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 	 */
 	cifs_save_when_sent(mid);
 	cifs_in_send_inc(server);
-	rc = smb_send_rqst(server, rqst, flags);
+	rc = smb_send_rqst(server, 1, rqst, flags);
 	cifs_in_send_dec(server);
 
 	if (rc < 0) {
@@ -729,20 +773,21 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
 }
 
 int
-cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
-	       struct smb_rqst *rqst, int *resp_buf_type, const int flags,
-	       struct kvec *resp_iov)
+compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
+		   const int flags, const int num_rqst, struct smb_rqst *rqst,
+		   int *resp_buf_type, struct kvec *resp_iov)
 {
-	int rc = 0;
+	int i, j, rc = 0;
 	int timeout, optype;
-	struct mid_q_entry *midQ;
+	struct mid_q_entry *midQ[MAX_COMPOUND];
 	unsigned int credits = 1;
 	char *buf;
 
 	timeout = flags & CIFS_TIMEOUT_MASK;
 	optype = flags & CIFS_OP_MASK;
 
-	*resp_buf_type = CIFS_NO_BUFFER;  /* no response buf yet */
+	for (i = 0; i < num_rqst; i++)
+		resp_buf_type[i] = CIFS_NO_BUFFER;  /* no response buf yet */
 
 	if ((ses == NULL) || (ses->server == NULL)) {
 		cifs_dbg(VFS, "Null session\n");
@@ -769,98 +814,117 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 
 	mutex_lock(&ses->server->srv_mutex);
 
-	midQ = ses->server->ops->setup_request(ses, rqst);
-	if (IS_ERR(midQ)) {
-		mutex_unlock(&ses->server->srv_mutex);
-		/* Update # of requests on wire to server */
-		add_credits(ses->server, 1, optype);
-		return PTR_ERR(midQ);
+	for (i = 0; i < num_rqst; i++) {
+		midQ[i] = ses->server->ops->setup_request(ses, &rqst[i]);
+		if (IS_ERR(midQ[i])) {
+			for (j = 0; j < i; j++)
+				cifs_delete_mid(midQ[j]);
+			mutex_unlock(&ses->server->srv_mutex);
+			/* Update # of requests on wire to server */
+			add_credits(ses->server, 1, optype);
+			return PTR_ERR(midQ[i]);
+		}
+
+		midQ[i]->mid_state = MID_REQUEST_SUBMITTED;
 	}
 
-	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
-	rc = smb_send_rqst(ses->server, rqst, flags);
+	rc = smb_send_rqst(ses->server, num_rqst, rqst, flags);
 	cifs_in_send_dec(ses->server);
-	cifs_save_when_sent(midQ);
+
+	for (i = 0; i < num_rqst; i++)
+		cifs_save_when_sent(midQ[i]);
 
 	if (rc < 0)
 		ses->server->sequence_number -= 2;
+
 	mutex_unlock(&ses->server->srv_mutex);
 
-	if (rc < 0)
-		goto out;
+	for (i = 0; i < num_rqst; i++) {
+		if (rc < 0)
+			goto out;
 
-#ifdef CONFIG_CIFS_SMB311
-	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
-		smb311_update_preauth_hash(ses, rqst->rq_iov,
-					   rqst->rq_nvec);
-#endif
+		if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
+			smb311_update_preauth_hash(ses, rqst[i].rq_iov,
+						   rqst[i].rq_nvec);
 
-	if (timeout == CIFS_ASYNC_OP)
-		goto out;
+		if (timeout == CIFS_ASYNC_OP)
+			goto out;
 
-	rc = wait_for_response(ses->server, midQ);
-	if (rc != 0) {
-		cifs_dbg(FYI, "Cancelling wait for mid %llu\n",	midQ->mid);
-		send_cancel(ses->server, rqst, midQ);
-		spin_lock(&GlobalMid_Lock);
-		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
-			midQ->mid_flags |= MID_WAIT_CANCELLED;
-			midQ->callback = DeleteMidQEntry;
+		rc = wait_for_response(ses->server, midQ[i]);
+		if (rc != 0) {
+			cifs_dbg(FYI, "Cancelling wait for mid %llu\n",
+				 midQ[i]->mid);
+			send_cancel(ses->server, &rqst[i], midQ[i]);
+			spin_lock(&GlobalMid_Lock);
+			if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) {
+				midQ[i]->mid_flags |= MID_WAIT_CANCELLED;
+				midQ[i]->callback = DeleteMidQEntry;
+				spin_unlock(&GlobalMid_Lock);
+				add_credits(ses->server, 1, optype);
+				return rc;
+			}
 			spin_unlock(&GlobalMid_Lock);
+		}
+
+		rc = cifs_sync_mid_result(midQ[i], ses->server);
+		if (rc != 0) {
 			add_credits(ses->server, 1, optype);
 			return rc;
 		}
-		spin_unlock(&GlobalMid_Lock);
-	}
 
-	rc = cifs_sync_mid_result(midQ, ses->server);
-	if (rc != 0) {
-		add_credits(ses->server, 1, optype);
-		return rc;
-	}
-
-	if (!midQ->resp_buf || midQ->mid_state != MID_RESPONSE_RECEIVED) {
-		rc = -EIO;
-		cifs_dbg(FYI, "Bad MID state?\n");
-		goto out;
-	}
-
-	buf = (char *)midQ->resp_buf;
-	resp_iov->iov_base = buf;
-	resp_iov->iov_len = midQ->resp_buf_size +
-		ses->server->vals->header_preamble_size;
-	if (midQ->large_buf)
-		*resp_buf_type = CIFS_LARGE_BUFFER;
-	else
-		*resp_buf_type = CIFS_SMALL_BUFFER;
+		if (!midQ[i]->resp_buf ||
+		    midQ[i]->mid_state != MID_RESPONSE_RECEIVED) {
+			rc = -EIO;
+			cifs_dbg(FYI, "Bad MID state?\n");
+			goto out;
+		}
 
-#ifdef CONFIG_CIFS_SMB311
-	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
-		struct kvec iov = {
-			.iov_base = resp_iov->iov_base,
-			.iov_len = resp_iov->iov_len
-		};
-		smb311_update_preauth_hash(ses, &iov, 1);
-	}
-#endif
+		buf = (char *)midQ[i]->resp_buf;
+		resp_iov[i].iov_base = buf;
+		resp_iov[i].iov_len = midQ[i]->resp_buf_size +
+			ses->server->vals->header_preamble_size;
+
+		if (midQ[i]->large_buf)
+			resp_buf_type[i] = CIFS_LARGE_BUFFER;
+		else
+			resp_buf_type[i] = CIFS_SMALL_BUFFER;
+
+		if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
+			struct kvec iov = {
+				.iov_base = resp_iov[i].iov_base,
+				.iov_len = resp_iov[i].iov_len
+			};
+			smb311_update_preauth_hash(ses, &iov, 1);
+		}
 
-	credits = ses->server->ops->get_credits(midQ);
+		credits = ses->server->ops->get_credits(midQ[i]);
 
-	rc = ses->server->ops->check_receive(midQ, ses->server,
-					     flags & CIFS_LOG_ERROR);
+		rc = ses->server->ops->check_receive(midQ[i], ses->server,
+						     flags & CIFS_LOG_ERROR);
 
-	/* mark it so buf will not be freed by cifs_delete_mid */
-	if ((flags & CIFS_NO_RESP) == 0)
-		midQ->resp_buf = NULL;
+		/* mark it so buf will not be freed by cifs_delete_mid */
+		if ((flags & CIFS_NO_RESP) == 0)
+			midQ[i]->resp_buf = NULL;
+	}
 out:
-	cifs_delete_mid(midQ);
+	for (i = 0; i < num_rqst; i++)
+		cifs_delete_mid(midQ[i]);
 	add_credits(ses->server, credits, optype);
 
 	return rc;
 }
 
 int
+cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
+	       struct smb_rqst *rqst, int *resp_buf_type, const int flags,
+	       struct kvec *resp_iov)
+{
+	return compound_send_recv(xid, ses, flags, 1, rqst, resp_buf_type,
+				  resp_iov);
+}
+
+int
 SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	     struct kvec *iov, int n_vec, int *resp_buf_type /* ret */,
 	     const int flags, struct kvec *resp_iov)
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 316af84674f1..50ddb795aaeb 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -35,6 +35,14 @@
 #define CIFS_XATTR_CIFS_ACL "system.cifs_acl"
 #define CIFS_XATTR_ATTRIB "cifs.dosattrib"  /* full name: user.cifs.dosattrib */
 #define CIFS_XATTR_CREATETIME "cifs.creationtime"  /* user.cifs.creationtime */
+/*
+ * Although these three are just aliases for the above, need to move away from
+ * confusing users and using the 20+ year old term 'cifs' when it is no longer
+ * secure, replaced by SMB2 (then even more highly secure SMB3) many years ago
+ */
+#define SMB3_XATTR_CIFS_ACL "system.smb3_acl"
+#define SMB3_XATTR_ATTRIB "smb3.dosattrib"  /* full name: user.smb3.dosattrib */
+#define SMB3_XATTR_CREATETIME "smb3.creationtime"  /* user.smb3.creationtime */
 /* BB need to add server (Samba e.g) support for security and trusted prefix */
 
 enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT };
@@ -220,10 +228,12 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
 	switch (handler->flags) {
 	case XATTR_USER:
 		cifs_dbg(FYI, "%s:querying user xattr %s\n", __func__, name);
-		if (strcmp(name, CIFS_XATTR_ATTRIB) == 0) {
+		if ((strcmp(name, CIFS_XATTR_ATTRIB) == 0) ||
+		    (strcmp(name, SMB3_XATTR_ATTRIB) == 0)) {
 			rc = cifs_attrib_get(dentry, inode, value, size);
 			break;
-		} else if (strcmp(name, CIFS_XATTR_CREATETIME) == 0) {
+		} else if ((strcmp(name, CIFS_XATTR_CREATETIME) == 0) ||
+		    (strcmp(name, SMB3_XATTR_CREATETIME) == 0)) {
 			rc = cifs_creation_time_get(dentry, inode, value, size);
 			break;
 		}
@@ -363,6 +373,19 @@ static const struct xattr_handler cifs_cifs_acl_xattr_handler = {
 	.set = cifs_xattr_set,
 };
 
+/*
+ * Although this is just an alias for the above, need to move away from
+ * confusing users and using the 20 year old term 'cifs' when it is no
+ * longer secure and was replaced by SMB2/SMB3 a long time ago, and
+ * SMB3 and later are highly secure.
+ */
+static const struct xattr_handler smb3_acl_xattr_handler = {
+	.name = SMB3_XATTR_CIFS_ACL,
+	.flags = XATTR_CIFS_ACL,
+	.get = cifs_xattr_get,
+	.set = cifs_xattr_set,
+};
+
 static const struct xattr_handler cifs_posix_acl_access_xattr_handler = {
 	.name = XATTR_NAME_POSIX_ACL_ACCESS,
 	.flags = XATTR_ACL_ACCESS,
@@ -381,6 +404,7 @@ const struct xattr_handler *cifs_xattr_handlers[] = {
 	&cifs_user_xattr_handler,
 	&cifs_os2_xattr_handler,
 	&cifs_cifs_acl_xattr_handler,
+	&smb3_acl_xattr_handler, /* alias for above since avoiding "cifs" */
 	&cifs_posix_acl_access_xattr_handler,
 	&cifs_posix_acl_default_xattr_handler,
 	NULL
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 577cff24707b..39843fa7e11b 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1777,6 +1777,16 @@ void configfs_unregister_group(struct config_group *group)
 	struct dentry *dentry = group->cg_item.ci_dentry;
 	struct dentry *parent = group->cg_item.ci_parent->ci_dentry;
 
+	mutex_lock(&subsys->su_mutex);
+	if (!group->cg_item.ci_parent->ci_group) {
+		/*
+		 * The parent has already been unlinked and detached
+		 * due to a rmdir.
+		 */
+		goto unlink_group;
+	}
+	mutex_unlock(&subsys->su_mutex);
+
 	inode_lock_nested(d_inode(parent), I_MUTEX_PARENT);
 	spin_lock(&configfs_dirent_lock);
 	configfs_detach_prep(dentry, NULL);
@@ -1791,6 +1801,7 @@ void configfs_unregister_group(struct config_group *group)
 	dput(dentry);
 
 	mutex_lock(&subsys->su_mutex);
+unlink_group:
 	unlink_group(group);
 	mutex_unlock(&subsys->su_mutex);
 }
diff --git a/fs/configfs/item.c b/fs/configfs/item.c
index 88f266efc09b..99d491cd01f9 100644
--- a/fs/configfs/item.c
+++ b/fs/configfs/item.c
@@ -64,7 +64,6 @@ static void config_item_init(struct config_item *item)
  */
 int config_item_set_name(struct config_item *item, const char *fmt, ...)
 {
-	int error = 0;
 	int limit = CONFIGFS_ITEM_NAME_LEN;
 	int need;
 	va_list args;
@@ -79,25 +78,11 @@ int config_item_set_name(struct config_item *item, const char *fmt, ...)
 	if (need < limit)
 		name = item->ci_namebuf;
 	else {
-		/*
-		 * Need more space? Allocate it and try again
-		 */
-		limit = need + 1;
-		name = kmalloc(limit, GFP_KERNEL);
-		if (!name) {
-			error = -ENOMEM;
-			goto Done;
-		}
 		va_start(args, fmt);
-		need = vsnprintf(name, limit, fmt, args);
+		name = kvasprintf(GFP_KERNEL, fmt, args);
 		va_end(args);
-
-		/* Still? Give up. */
-		if (need >= limit) {
-			kfree(name);
-			error = -EFAULT;
-			goto Done;
-		}
+		if (!name)
+			return -EFAULT;
 	}
 
 	/* Free the old name, if necessary. */
@@ -106,8 +91,7 @@ int config_item_set_name(struct config_item *item, const char *fmt, ...)
 
 	/* Now, set the new name */
 	item->ci_name = name;
- Done:
-	return error;
+	return 0;
 }
 EXPORT_SYMBOL(config_item_set_name);
 
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 78ffc2699993..a5c54af861f7 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -64,7 +64,7 @@ static void fill_item_path(struct config_item * item, char * buffer, int length)
 
 		/* back up enough to print this bus id with '/' */
 		length -= cur;
-		strncpy(buffer + length,config_item_name(p),cur);
+		memcpy(buffer + length, config_item_name(p), cur);
 		*(buffer + --length) = '/';
 	}
 }
diff --git a/fs/dax.c b/fs/dax.c
index 641192808bb6..897b51e41d8f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -566,7 +566,8 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 			if (index >= end)
 				break;
 
-			if (!radix_tree_exceptional_entry(pvec_ent))
+			if (WARN_ON_ONCE(
+			     !radix_tree_exceptional_entry(pvec_ent)))
 				continue;
 
 			xa_lock_irq(&mapping->i_pages);
@@ -578,6 +579,13 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 			if (page)
 				break;
 		}
+
+		/*
+		 * We don't expect normal struct page entries to exist in our
+		 * tree, but we keep these pagevec calls so that this code is
+		 * consistent with the common pattern for handling pagevecs
+		 * throughout the kernel.
+		 */
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		index++;
diff --git a/fs/dcache.c b/fs/dcache.c
index 0e8e5de3c48a..8d2ec4898c2b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -358,14 +358,11 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	__releases(dentry->d_inode->i_lock)
 {
 	struct inode *inode = dentry->d_inode;
-	bool hashed = !d_unhashed(dentry);
 
-	if (hashed)
-		raw_write_seqcount_begin(&dentry->d_seq);
+	raw_write_seqcount_begin(&dentry->d_seq);
 	__d_clear_type_and_inode(dentry);
 	hlist_del_init(&dentry->d_u.d_alias);
-	if (hashed)
-		raw_write_seqcount_end(&dentry->d_seq);
+	raw_write_seqcount_end(&dentry->d_seq);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
 	if (!inode->i_nlink)
@@ -732,16 +729,16 @@ static inline bool fast_dput(struct dentry *dentry)
 		if (dentry->d_lockref.count > 1) {
 			dentry->d_lockref.count--;
 			spin_unlock(&dentry->d_lock);
-			return 1;
+			return true;
 		}
-		return 0;
+		return false;
 	}
 
 	/*
 	 * If we weren't the last ref, we're done.
 	 */
 	if (ret)
-		return 1;
+		return true;
 
 	/*
 	 * Careful, careful. The reference count went down
@@ -770,7 +767,7 @@ static inline bool fast_dput(struct dentry *dentry)
 
 	/* Nothing to do? Dropping the reference was all we needed? */
 	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
-		return 1;
+		return true;
 
 	/*
 	 * Not the fast normal case? Get the lock. We've already decremented
@@ -787,7 +784,7 @@ static inline bool fast_dput(struct dentry *dentry)
 	 */
 	if (dentry->d_lockref.count) {
 		spin_unlock(&dentry->d_lock);
-		return 1;
+		return true;
 	}
 
 	/*
@@ -796,7 +793,7 @@ static inline bool fast_dput(struct dentry *dentry)
 	 * set it to 1.
 	 */
 	dentry->d_lockref.count = 1;
-	return 0;
+	return false;
 }
 
 
@@ -1892,50 +1889,25 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode)
 	spin_lock(&inode->i_lock);
 	__d_instantiate(entry, inode);
 	WARN_ON(!(inode->i_state & I_NEW));
-	inode->i_state &= ~I_NEW;
+	inode->i_state &= ~I_NEW & ~I_CREATING;
 	smp_mb();
 	wake_up_bit(&inode->i_state, __I_NEW);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(d_instantiate_new);
 
-/**
- * d_instantiate_no_diralias - instantiate a non-aliased dentry
- * @entry: dentry to complete
- * @inode: inode to attach to this dentry
- *
- * Fill in inode information in the entry.  If a directory alias is found, then
- * return an error (and drop inode).  Together with d_materialise_unique() this
- * guarantees that a directory inode may never have more than one alias.
- */
-int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
-{
-	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
-
-	security_d_instantiate(entry, inode);
-	spin_lock(&inode->i_lock);
-	if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
-		spin_unlock(&inode->i_lock);
-		iput(inode);
-		return -EBUSY;
-	}
-	__d_instantiate(entry, inode);
-	spin_unlock(&inode->i_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL(d_instantiate_no_diralias);
-
 struct dentry *d_make_root(struct inode *root_inode)
 {
 	struct dentry *res = NULL;
 
 	if (root_inode) {
 		res = d_alloc_anon(root_inode->i_sb);
-		if (res)
+		if (res) {
+			res->d_flags |= DCACHE_RCUACCESS;
 			d_instantiate(res, root_inode);
-		else
+		} else {
 			iput(root_inode);
+		}
 	}
 	return res;
 }
@@ -2676,33 +2648,6 @@ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode)
 }
 EXPORT_SYMBOL(d_exact_alias);
 
-/**
- * dentry_update_name_case - update case insensitive dentry with a new name
- * @dentry: dentry to be updated
- * @name: new name
- *
- * Update a case insensitive dentry with new case of name.
- *
- * dentry must have been returned by d_lookup with name @name. Old and new
- * name lengths must match (ie. no d_compare which allows mismatched name
- * lengths).
- *
- * Parent inode i_mutex must be held over d_lookup and into this call (to
- * keep renames and concurrent inserts, and readdir(2) away).
- */
-void dentry_update_name_case(struct dentry *dentry, const struct qstr *name)
-{
-	BUG_ON(!inode_is_locked(dentry->d_parent->d_inode));
-	BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */
-
-	spin_lock(&dentry->d_lock);
-	write_seqcount_begin(&dentry->d_seq);
-	memcpy((unsigned char *)dentry->d_name.name, name->name, name->len);
-	write_seqcount_end(&dentry->d_seq);
-	spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(dentry_update_name_case);
-
 static void swap_names(struct dentry *dentry, struct dentry *target)
 {
 	if (unlikely(dname_external(target))) {
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 71fccccf317e..8c6ab6c95727 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -86,7 +86,9 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 	/* length of the variable name itself: remove GUID and separator */
 	namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
 
-	uuid_le_to_bin(dentry->d_name.name + namelen + 1, &var->var.VendorGuid);
+	err = guid_parse(dentry->d_name.name + namelen + 1, &var->var.VendorGuid);
+	if (err)
+		goto out;
 
 	if (efivar_variable_is_removable(var->var.VendorGuid,
 					 dentry->d_name.name, namelen))
diff --git a/fs/eventfd.c b/fs/eventfd.c
index ceb1031f1cac..08d3bd602f73 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -101,20 +101,14 @@ static int eventfd_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static struct wait_queue_head *
-eventfd_get_poll_head(struct file *file, __poll_t events)
-{
-	struct eventfd_ctx *ctx = file->private_data;
-
-	return &ctx->wqh;
-}
-
-static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
+static __poll_t eventfd_poll(struct file *file, poll_table *wait)
 {
 	struct eventfd_ctx *ctx = file->private_data;
 	__poll_t events = 0;
 	u64 count;
 
+	poll_wait(file, &ctx->wqh, wait);
+
 	/*
 	 * All writes to ctx->count occur within ctx->wqh.lock.  This read
 	 * can be done outside ctx->wqh.lock because we know that poll_wait
@@ -156,11 +150,11 @@ static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
 	count = READ_ONCE(ctx->count);
 
 	if (count > 0)
-		events |= (EPOLLIN & eventmask);
+		events |= EPOLLIN;
 	if (count == ULLONG_MAX)
 		events |= EPOLLERR;
 	if (ULLONG_MAX - 1 > count)
-		events |= (EPOLLOUT & eventmask);
+		events |= EPOLLOUT;
 
 	return events;
 }
@@ -311,8 +305,7 @@ static const struct file_operations eventfd_fops = {
 	.show_fdinfo	= eventfd_show_fdinfo,
 #endif
 	.release	= eventfd_release,
-	.get_poll_head	= eventfd_get_poll_head,
-	.poll_mask	= eventfd_poll_mask,
+	.poll		= eventfd_poll,
 	.read		= eventfd_read,
 	.write		= eventfd_write,
 	.llseek		= noop_llseek,
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index ea4436f409fb..67db22fe99c5 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -922,18 +922,14 @@ static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head
 	return 0;
 }
 
-static struct wait_queue_head *ep_eventpoll_get_poll_head(struct file *file,
-		__poll_t eventmask)
-{
-	struct eventpoll *ep = file->private_data;
-	return &ep->poll_wait;
-}
-
-static __poll_t ep_eventpoll_poll_mask(struct file *file, __poll_t eventmask)
+static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait)
 {
 	struct eventpoll *ep = file->private_data;
 	int depth = 0;
 
+	/* Insert inside our poll wait queue */
+	poll_wait(file, &ep->poll_wait, wait);
+
 	/*
 	 * Proceed to find out if wanted events are really available inside
 	 * the ready list.
@@ -972,8 +968,7 @@ static const struct file_operations eventpoll_fops = {
 	.show_fdinfo	= ep_show_fdinfo,
 #endif
 	.release	= ep_eventpoll_release,
-	.get_poll_head	= ep_eventpoll_get_poll_head,
-	.poll_mask	= ep_eventpoll_poll_mask,
+	.poll		= ep_eventpoll_poll,
 	.llseek		= noop_llseek,
 };
 
diff --git a/fs/exec.c b/fs/exec.c
index 2d4e0075bd24..bdd0eacefdf5 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -290,15 +290,15 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	struct vm_area_struct *vma = NULL;
 	struct mm_struct *mm = bprm->mm;
 
-	bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	bprm->vma = vma = vm_area_alloc(mm);
 	if (!vma)
 		return -ENOMEM;
+	vma_set_anonymous(vma);
 
 	if (down_write_killable(&mm->mmap_sem)) {
 		err = -EINTR;
 		goto err_free;
 	}
-	vma->vm_mm = mm;
 
 	/*
 	 * Place the stack at the largest stack address the architecture
@@ -311,7 +311,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	vma->vm_start = vma->vm_end - PAGE_SIZE;
 	vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	err = insert_vm_struct(mm, vma);
 	if (err)
@@ -326,7 +325,7 @@ err:
 	up_write(&mm->mmap_sem);
 err_free:
 	bprm->vma = NULL;
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return err;
 }
 
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 1b8b44637e70..5331a15a61f1 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -873,8 +873,8 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp)
 			struct bio *bio;
 
 			if (per_dev != master_dev) {
-				bio = bio_clone_kmalloc(master_dev->bio,
-							GFP_KERNEL);
+				bio = bio_clone_fast(master_dev->bio,
+						     GFP_KERNEL, NULL);
 				if (unlikely(!bio)) {
 					ORE_DBGMSG(
 					      "Failed to allocate BIO size=%u\n",
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 6484199b35d1..5c3d7b7e4975 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -611,8 +611,7 @@ fail_drop:
 	dquot_drop(inode);
 	inode->i_flags |= S_NOQUOTA;
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return ERR_PTR(err);
 
 fail:
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 152453a91877..0c26dcc5d850 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -45,8 +45,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 		return 0;
 	}
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return err;
 }
 
@@ -192,8 +191,7 @@ out:
 
 out_fail:
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput (inode);
+	discard_new_inode(inode);
 	goto out;
 }
 
@@ -261,8 +259,7 @@ out:
 out_fail:
 	inode_dec_link_count(inode);
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 out_dir:
 	inode_dec_link_count(dir);
 	goto out;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index b00481c475cb..e5d6ee61ff48 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -184,7 +184,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	unsigned int bit, bit_max;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t start, tmp;
-	int flex_bg = 0;
 
 	J_ASSERT_BH(bh, buffer_locked(bh));
 
@@ -207,22 +206,19 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 
 	start = ext4_group_first_block_no(sb, block_group);
 
-	if (ext4_has_feature_flex_bg(sb))
-		flex_bg = 1;
-
 	/* Set bits for block and inode bitmaps, and inode table */
 	tmp = ext4_block_bitmap(sb, gdp);
-	if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+	if (ext4_block_in_group(sb, tmp, block_group))
 		ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
 
 	tmp = ext4_inode_bitmap(sb, gdp);
-	if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+	if (ext4_block_in_group(sb, tmp, block_group))
 		ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
 
 	tmp = ext4_inode_table(sb, gdp);
 	for (; tmp < ext4_inode_table(sb, gdp) +
 		     sbi->s_itb_per_group; tmp++) {
-		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+		if (ext4_block_in_group(sb, tmp, block_group))
 			ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
 	}
 
@@ -372,6 +368,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 		return -EFSCORRUPTED;
 
 	ext4_lock_group(sb, block_group);
+	if (buffer_verified(bh))
+		goto verified;
 	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
 			desc, bh))) {
 		ext4_unlock_group(sb, block_group);
@@ -390,6 +388,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 		return -EFSCORRUPTED;
 	}
 	set_buffer_verified(bh);
+verified:
 	ext4_unlock_group(sb, block_group);
 	return 0;
 }
@@ -427,9 +426,9 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	}
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, "Cannot get buffer for block bitmap - "
-			   "block_group = %u, block_bitmap = %llu",
-			   block_group, bitmap_blk);
+		ext4_warning(sb, "Cannot get buffer for block bitmap - "
+			     "block_group = %u, block_bitmap = %llu",
+			     block_group, bitmap_blk);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -442,7 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 		goto verify;
 	}
 	ext4_lock_group(sb, block_group);
-	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+	if (ext4_has_group_desc_csum(sb) &&
+	    (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+		if (block_group == 0) {
+			ext4_unlock_group(sb, block_group);
+			unlock_buffer(bh);
+			ext4_error(sb, "Block bitmap for bg 0 marked "
+				   "uninitialized");
+			err = -EFSCORRUPTED;
+			goto out;
+		}
 		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0b127853c584..1fc013f3d944 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -789,17 +789,16 @@ struct move_extent {
  * affected filesystem before 2242.
  */
 
-static inline __le32 ext4_encode_extra_time(struct timespec *time)
+static inline __le32 ext4_encode_extra_time(struct timespec64 *time)
 {
-	u32 extra = sizeof(time->tv_sec) > 4 ?
-		((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0;
+	u32 extra =((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK;
 	return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
 }
 
-static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
+static inline void ext4_decode_extra_time(struct timespec64 *time,
+					  __le32 extra)
 {
-	if (unlikely(sizeof(time->tv_sec) > 4 &&
-			(extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
+	if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK))) {
 
 #if 1
 		/* Handle legacy encoding of pre-1970 dates with epoch
@@ -821,9 +820,8 @@ static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
 do {										\
 	(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);		\
 	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     {\
-		struct timespec ts = timespec64_to_timespec((inode)->xtime);	\
 		(raw_inode)->xtime ## _extra =					\
-				ext4_encode_extra_time(&ts);			\
+				ext4_encode_extra_time(&(inode)->xtime);	\
 		}								\
 } while (0)
 
@@ -840,10 +838,8 @@ do {									       \
 do {										\
 	(inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime);	\
 	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {	\
-		struct timespec ts = timespec64_to_timespec((inode)->xtime);	\
-		ext4_decode_extra_time(&ts,					\
+		ext4_decode_extra_time(&(inode)->xtime,				\
 				       raw_inode->xtime ## _extra);		\
-		(inode)->xtime = timespec_to_timespec64(ts);			\
 		}								\
 	else									\
 		(inode)->xtime.tv_nsec = 0;					\
@@ -993,9 +989,9 @@ struct ext4_inode_info {
 
 	/*
 	 * File creation time. Its function is same as that of
-	 * struct timespec i_{a,c,m}time in the generic inode.
+	 * struct timespec64 i_{a,c,m}time in the generic inode.
 	 */
-	struct timespec i_crtime;
+	struct timespec64 i_crtime;
 
 	/* mballoc */
 	struct list_head i_prealloc_list;
@@ -1114,6 +1110,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
+#define EXT4_MOUNT_WARN_ON_ERROR	0x2000000 /* Trigger WARN_ON on error */
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
@@ -1298,7 +1295,14 @@ struct ext4_super_block {
 	__le32	s_lpf_ino;		/* Location of the lost+found inode */
 	__le32	s_prj_quota_inum;	/* inode for tracking project quota */
 	__le32	s_checksum_seed;	/* crc32c(uuid) if csum_seed set */
-	__le32	s_reserved[98];		/* Padding to the end of the block */
+	__u8	s_wtime_hi;
+	__u8	s_mtime_hi;
+	__u8	s_mkfs_time_hi;
+	__u8	s_lastcheck_hi;
+	__u8	s_first_error_time_hi;
+	__u8	s_last_error_time_hi;
+	__u8	s_pad[2];
+	__le32	s_reserved[96];		/* Padding to the end of the block */
 	__le32	s_checksum;		/* crc32c(superblock) */
 };
 
@@ -1507,11 +1511,6 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
 static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 {
 	return ino == EXT4_ROOT_INO ||
-		ino == EXT4_USR_QUOTA_INO ||
-		ino == EXT4_GRP_QUOTA_INO ||
-		ino == EXT4_BOOT_LOADER_INO ||
-		ino == EXT4_JOURNAL_INO ||
-		ino == EXT4_RESIZE_INO ||
 		(ino >= EXT4_FIRST_INO(sb) &&
 		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
 }
@@ -2460,6 +2459,7 @@ extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
 extern int ext4_truncate(struct inode *);
+extern int ext4_break_layouts(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
 extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
 extern void ext4_set_inode_flags(struct inode *);
@@ -3018,9 +3018,6 @@ extern int ext4_inline_data_fiemap(struct inode *inode,
 struct iomap;
 extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap);
 
-extern int ext4_try_to_evict_inline_data(handle_t *handle,
-					 struct inode *inode,
-					 int needed);
 extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
 
 extern int ext4_convert_inline_data(struct inode *inode);
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 98fb0c119c68..adf6668b596f 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -91,6 +91,7 @@ struct ext4_extent_header {
 };
 
 #define EXT4_EXT_MAGIC		cpu_to_le16(0xf30a)
+#define EXT4_MAX_EXTENT_DEPTH 5
 
 #define EXT4_EXTENT_TAIL_OFFSET(hdr) \
 	(sizeof(struct ext4_extent_header) + \
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0057fe3f248d..72a361d5ef74 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -869,6 +869,12 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block,
 
 	eh = ext_inode_hdr(inode);
 	depth = ext_depth(inode);
+	if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) {
+		EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d",
+				 depth);
+		ret = -EFSCORRUPTED;
+		goto err;
+	}
 
 	if (path) {
 		ext4_ext_drop_refs(path);
@@ -4820,6 +4826,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * released from page cache.
 		 */
 		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		ret = ext4_break_layouts(inode);
+		if (ret) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			goto out_mutex;
+		}
+
 		ret = ext4_update_disksize_before_punch(inode, offset, len);
 		if (ret) {
 			up_write(&EXT4_I(inode)->i_mmap_sem);
@@ -5493,6 +5506,11 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_mmap;
+
 	/*
 	 * Need to round down offset to be aligned with page size boundary
 	 * for page size > block size.
@@ -5641,6 +5659,11 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_mmap;
+
 	/*
 	 * Need to round down to align start offset to page size boundary
 	 * for page size > block size.
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f525f909b559..2addcb8730e1 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -90,6 +90,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 		return -EFSCORRUPTED;
 
 	ext4_lock_group(sb, block_group);
+	if (buffer_verified(bh))
+		goto verified;
 	blk = ext4_inode_bitmap(sb, desc);
 	if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
 					   EXT4_INODES_PER_GROUP(sb) / 8)) {
@@ -101,6 +103,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 		return -EFSBADCRC;
 	}
 	set_buffer_verified(bh);
+verified:
 	ext4_unlock_group(sb, block_group);
 	return 0;
 }
@@ -135,9 +138,9 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	}
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, "Cannot read inode bitmap - "
-			    "block_group = %u, inode_bitmap = %llu",
-			    block_group, bitmap_blk);
+		ext4_warning(sb, "Cannot read inode bitmap - "
+			     "block_group = %u, inode_bitmap = %llu",
+			     block_group, bitmap_blk);
 		return ERR_PTR(-ENOMEM);
 	}
 	if (bitmap_uptodate(bh))
@@ -150,7 +153,16 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	}
 
 	ext4_lock_group(sb, block_group);
-	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+	if (ext4_has_group_desc_csum(sb) &&
+	    (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) {
+		if (block_group == 0) {
+			ext4_unlock_group(sb, block_group);
+			unlock_buffer(bh);
+			ext4_error(sb, "Inode bitmap for bg 0 marked "
+				   "uninitialized");
+			err = -EFSCORRUPTED;
+			goto out;
+		}
 		memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
 		ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
 				     sb->s_blocksize * 8, bh->b_data);
@@ -994,7 +1006,8 @@ got:
 
 		/* recheck and clear flag under lock if we still need to */
 		ext4_lock_group(sb, group);
-		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+		if (ext4_has_group_desc_csum(sb) &&
+		    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
 			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 			ext4_free_group_clusters_set(sb, gdp,
 				ext4_free_clusters_after_init(sb, group, gdp));
@@ -1073,7 +1086,7 @@ got:
 	/* This is the optimal IO size (for stat), not the fs block size */
 	inode->i_blocks = 0;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
-	ei->i_crtime = timespec64_to_timespec(inode->i_mtime);
+	ei->i_crtime = inode->i_mtime;
 
 	memset(ei->i_data, 0, sizeof(ei->i_data));
 	ei->i_dir_start_lookup = 0;
@@ -1375,7 +1388,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 			    ext4_itable_unused_count(sb, gdp)),
 			    sbi->s_inodes_per_block);
 
-	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
+	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) ||
+	    ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) -
+			       ext4_itable_unused_count(sb, gdp)) <
+			      EXT4_FIRST_INO(sb)))) {
 		ext4_error(sb, "Something is wrong with group %u: "
 			   "used itable blocks: %d; "
 			   "itable unused count: %u",
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 285ed1588730..3543fe80a3c4 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -437,6 +437,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
 
 	memset((void *)ext4_raw_inode(&is.iloc)->i_block,
 		0, EXT4_MIN_INLINE_DATA_SIZE);
+	memset(ei->i_data, 0, EXT4_MIN_INLINE_DATA_SIZE);
 
 	if (ext4_has_feature_extents(inode->i_sb)) {
 		if (S_ISDIR(inode->i_mode) ||
@@ -681,6 +682,10 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 		goto convert;
 	}
 
+	ret = ext4_journal_get_write_access(handle, iloc.bh);
+	if (ret)
+		goto out;
+
 	flags |= AOP_FLAG_NOFS;
 
 	page = grab_cache_page_write_begin(mapping, 0, flags);
@@ -709,7 +714,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 out_up_read:
 	up_read(&EXT4_I(inode)->xattr_sem);
 out:
-	if (handle)
+	if (handle && (ret != 1))
 		ext4_journal_stop(handle);
 	brelse(iloc.bh);
 	return ret;
@@ -751,6 +756,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 
 	ext4_write_unlock_xattr(inode, &no_expand);
 	brelse(iloc.bh);
+	mark_inode_dirty(inode);
 out:
 	return copied;
 }
@@ -886,18 +892,17 @@ retry_journal:
 	flags |= AOP_FLAG_NOFS;
 
 	if (ret == -ENOSPC) {
+		ext4_journal_stop(handle);
 		ret = ext4_da_convert_inline_data_to_extent(mapping,
 							    inode,
 							    flags,
 							    fsdata);
-		ext4_journal_stop(handle);
 		if (ret == -ENOSPC &&
 		    ext4_should_retry_alloc(inode->i_sb, &retries))
 			goto retry_journal;
 		goto out;
 	}
 
-
 	page = grab_cache_page_write_begin(mapping, 0, flags);
 	if (!page) {
 		ret = -ENOMEM;
@@ -915,6 +920,9 @@ retry_journal:
 		if (ret < 0)
 			goto out_release_page;
 	}
+	ret = ext4_journal_get_write_access(handle, iloc.bh);
+	if (ret)
+		goto out_release_page;
 
 	up_read(&EXT4_I(inode)->xattr_sem);
 	*pagep = page;
@@ -935,7 +943,6 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 				  unsigned len, unsigned copied,
 				  struct page *page)
 {
-	int i_size_changed = 0;
 	int ret;
 
 	ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
@@ -953,10 +960,8 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 	 * But it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
 	 */
-	if (pos+copied > inode->i_size) {
+	if (pos+copied > inode->i_size)
 		i_size_write(inode, pos+copied);
-		i_size_changed = 1;
-	}
 	unlock_page(page);
 	put_page(page);
 
@@ -966,8 +971,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 	 * ordering of page lock and transaction start for journaling
 	 * filesystems.
 	 */
-	if (i_size_changed)
-		mark_inode_dirty(inode);
+	mark_inode_dirty(inode);
 
 	return copied;
 }
@@ -1890,42 +1894,6 @@ out:
 	return (error < 0 ? error : 0);
 }
 
-/*
- * Called during xattr set, and if we can sparse space 'needed',
- * just create the extent tree evict the data to the outer block.
- *
- * We use jbd2 instead of page cache to move data to the 1st block
- * so that the whole transaction can be committed as a whole and
- * the data isn't lost because of the delayed page cache write.
- */
-int ext4_try_to_evict_inline_data(handle_t *handle,
-				  struct inode *inode,
-				  int needed)
-{
-	int error;
-	struct ext4_xattr_entry *entry;
-	struct ext4_inode *raw_inode;
-	struct ext4_iloc iloc;
-
-	error = ext4_get_inode_loc(inode, &iloc);
-	if (error)
-		return error;
-
-	raw_inode = ext4_raw_inode(&iloc);
-	entry = (struct ext4_xattr_entry *)((void *)raw_inode +
-					    EXT4_I(inode)->i_inline_off);
-	if (EXT4_XATTR_LEN(entry->e_name_len) +
-	    EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) {
-		error = -ENOSPC;
-		goto out;
-	}
-
-	error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
-out:
-	brelse(iloc.bh);
-	return error;
-}
-
 int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 {
 	handle_t *handle;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2ea07efbe016..8f6ad7667974 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -317,7 +317,7 @@ stop_handle:
 	 * (Well, we could do this if we need to, but heck - it works)
 	 */
 	ext4_orphan_del(handle, inode);
-	EXT4_I(inode)->i_dtime	= get_seconds();
+	EXT4_I(inode)->i_dtime	= (__u32)ktime_get_real_seconds();
 
 	/*
 	 * One subtle ordering requirement: if anything has gone wrong
@@ -402,9 +402,9 @@ static int __check_block_validity(struct inode *inode, const char *func,
 	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
 				   map->m_len)) {
 		ext4_error_inode(inode, func, line, map->m_pblk,
-				 "lblock %lu mapped to illegal pblock "
+				 "lblock %lu mapped to illegal pblock %llu "
 				 "(length %d)", (unsigned long) map->m_lblk,
-				 map->m_len);
+				 map->m_pblk, map->m_len);
 		return -EFSCORRUPTED;
 	}
 	return 0;
@@ -1389,9 +1389,10 @@ static int ext4_write_end(struct file *file,
 	loff_t old_size = inode->i_size;
 	int ret = 0, ret2;
 	int i_size_changed = 0;
+	int inline_data = ext4_has_inline_data(inode);
 
 	trace_ext4_write_end(inode, pos, len, copied);
-	if (ext4_has_inline_data(inode)) {
+	if (inline_data) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
 		if (ret < 0) {
@@ -1419,7 +1420,7 @@ static int ext4_write_end(struct file *file,
 	 * ordering of page lock and transaction start for journaling
 	 * filesystems.
 	 */
-	if (i_size_changed)
+	if (i_size_changed || inline_data)
 		ext4_mark_inode_dirty(handle, inode);
 
 	if (pos + len > inode->i_size && ext4_can_truncate(inode))
@@ -1493,6 +1494,7 @@ static int ext4_journalled_write_end(struct file *file,
 	int partial = 0;
 	unsigned from, to;
 	int size_changed = 0;
+	int inline_data = ext4_has_inline_data(inode);
 
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
 	from = pos & (PAGE_SIZE - 1);
@@ -1500,7 +1502,7 @@ static int ext4_journalled_write_end(struct file *file,
 
 	BUG_ON(!ext4_handle_valid(handle));
 
-	if (ext4_has_inline_data(inode)) {
+	if (inline_data) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
 		if (ret < 0) {
@@ -1531,7 +1533,7 @@ static int ext4_journalled_write_end(struct file *file,
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
 
-	if (size_changed) {
+	if (size_changed || inline_data) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		if (!ret)
 			ret = ret2;
@@ -2028,11 +2030,7 @@ static int __ext4_journalled_writepage(struct page *page,
 	}
 
 	if (inline_data) {
-		BUFFER_TRACE(inode_bh, "get write access");
-		ret = ext4_journal_get_write_access(handle, inode_bh);
-
-		err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
-
+		ret = ext4_mark_inode_dirty(handle, inode);
 	} else {
 		ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL,
 					     do_journal_get_write_access);
@@ -4193,6 +4191,39 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 	return 0;
 }
 
+static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock)
+{
+	*did_unlock = true;
+	up_write(&ei->i_mmap_sem);
+	schedule();
+	down_write(&ei->i_mmap_sem);
+}
+
+int ext4_break_layouts(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct page *page;
+	bool retry;
+	int error;
+
+	if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+		return -EINVAL;
+
+	do {
+		retry = false;
+		page = dax_layout_busy_page(inode->i_mapping);
+		if (!page)
+			return 0;
+
+		error = ___wait_var_event(&page->_refcount,
+				atomic_read(&page->_refcount) == 1,
+				TASK_INTERRUPTIBLE, 0, 0,
+				ext4_wait_dax_page(ei, &retry));
+	} while (error == 0 && retry);
+
+	return error;
+}
+
 /*
  * ext4_punch_hole: punches a hole in a file by releasing the blocks
  * associated with the given offset and length
@@ -4266,6 +4297,11 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_dio;
+
 	first_block_offset = round_up(offset, sb->s_blocksize);
 	last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
@@ -4506,7 +4542,8 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	int			inodes_per_block, inode_offset;
 
 	iloc->bh = NULL;
-	if (!ext4_valid_inum(sb, inode->i_ino))
+	if (inode->i_ino < EXT4_ROOT_INO ||
+	    inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
 		return -EFSCORRUPTED;
 
 	iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
@@ -4945,17 +4982,14 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		ret = -EFSCORRUPTED;
 		goto bad_inode;
 	} else if (!ext4_has_inline_data(inode)) {
-		if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
-			if ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-			    (S_ISLNK(inode->i_mode) &&
-			     !ext4_inode_is_fast_symlink(inode))))
-				/* Validate extent which is part of inode */
+		/* validate the block references in the inode */
+		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		   (S_ISLNK(inode->i_mode) &&
+		    !ext4_inode_is_fast_symlink(inode))) {
+			if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 				ret = ext4_ext_check_inode(inode);
-		} else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-			   (S_ISLNK(inode->i_mode) &&
-			    !ext4_inode_is_fast_symlink(inode))) {
-			/* Validate block references which are part of inode */
-			ret = ext4_ind_check_inode(inode);
+			else
+				ret = ext4_ind_check_inode(inode);
 		}
 	}
 	if (ret)
@@ -5554,6 +5588,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				ext4_wait_for_tail_page_commit(inode);
 		}
 		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		rc = ext4_break_layouts(inode);
+		if (rc) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			error = rc;
+			goto err_out;
+		}
+
 		/*
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 6eae2b91aafa..e29fce2fbf25 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -14,6 +14,7 @@
 #include <linux/log2.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/nospec.h>
 #include <linux/backing-dev.h>
 #include <trace/events/ext4.h>
 
@@ -2140,7 +2141,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 		 * This should tell if fe_len is exactly power of 2
 		 */
 		if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0)
-			ac->ac_2order = i - 1;
+			ac->ac_2order = array_index_nospec(i - 1,
+							   sb->s_blocksize_bits + 2);
 	}
 
 	/* if stream allocation is enabled, use global goal */
@@ -2423,7 +2425,8 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 	 * initialize bb_free to be able to skip
 	 * empty groups without initialization
 	 */
-	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+	if (ext4_has_group_desc_csum(sb) &&
+	    (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
 		meta_group_info[i]->bb_free =
 			ext4_free_clusters_after_init(sb, group, desc);
 	} else {
@@ -2989,7 +2992,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 #endif
 	ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
 		      ac->ac_b_ex.fe_len);
-	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+	if (ext4_has_group_desc_csum(sb) &&
+	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
 		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 		ext4_free_group_clusters_set(sb, gdp,
 					     ext4_free_clusters_after_init(sb,
@@ -3797,7 +3801,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 	ext4_group_t group;
 	ext4_grpblk_t bit;
 	unsigned long long grp_blk_start;
-	int err = 0;
 	int free = 0;
 
 	BUG_ON(pa->pa_deleted == 0);
@@ -3838,7 +3841,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 	}
 	atomic_add(free, &sbi->s_mb_discarded);
 
-	return err;
+	return 0;
 }
 
 static noinline_for_stack int
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 27b9a76a0dfa..39b07c2d3384 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -147,7 +147,7 @@ static int kmmpd(void *data)
 
 	mmp_block = le64_to_cpu(es->s_mmp_block);
 	mmp = (struct mmp_struct *)(bh->b_data);
-	mmp->mmp_time = cpu_to_le64(get_seconds());
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 	/*
 	 * Start with the higher mmp_check_interval and reduce it if
 	 * the MMP block is being updated on time.
@@ -165,7 +165,7 @@ static int kmmpd(void *data)
 			seq = 1;
 
 		mmp->mmp_seq = cpu_to_le32(seq);
-		mmp->mmp_time = cpu_to_le64(get_seconds());
+		mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 		last_update_time = jiffies;
 
 		retval = write_mmp_block(sb, bh);
@@ -186,11 +186,8 @@ static int kmmpd(void *data)
 			goto exit_thread;
 		}
 
-		if (sb_rdonly(sb)) {
-			ext4_warning(sb, "kmmpd being stopped since filesystem "
-				     "has been remounted as readonly.");
-			goto exit_thread;
-		}
+		if (sb_rdonly(sb))
+			break;
 
 		diff = jiffies - last_update_time;
 		if (diff < mmp_update_interval * HZ)
@@ -244,7 +241,7 @@ static int kmmpd(void *data)
 	 * Unmount seems to be clean.
 	 */
 	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
-	mmp->mmp_time = cpu_to_le64(get_seconds());
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 
 	retval = write_mmp_block(sb, bh);
 
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 8e17efdcbf11..a409ff70d67b 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -134,9 +134,7 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2,
 		mapping[0] = inode1->i_mapping;
 		mapping[1] = inode2->i_mapping;
 	} else {
-		pgoff_t tmp = index1;
-		index1 = index2;
-		index2 = tmp;
+		swap(index1, index2);
 		mapping[0] = inode2->i_mapping;
 		mapping[1] = inode1->i_mapping;
 	}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2a4c25c4681d..116ff68c5bd4 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1398,6 +1398,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 			goto cleanup_and_exit;
 		dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
 			       "falling back\n"));
+		ret = NULL;
 	}
 	nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
 	if (!nblocks) {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0c4c2201b3aa..5863fd22e90b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -312,6 +312,24 @@ void ext4_itable_unused_set(struct super_block *sb,
 		bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
 }
 
+static void __ext4_update_tstamp(__le32 *lo, __u8 *hi)
+{
+	time64_t now = ktime_get_real_seconds();
+
+	now = clamp_val(now, 0, (1ull << 40) - 1);
+
+	*lo = cpu_to_le32(lower_32_bits(now));
+	*hi = upper_32_bits(now);
+}
+
+static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi)
+{
+	return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo);
+}
+#define ext4_update_tstamp(es, tstamp) \
+	__ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
+#define ext4_get_tstamp(es, tstamp) \
+	__ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
 
 static void __save_error_info(struct super_block *sb, const char *func,
 			    unsigned int line)
@@ -322,11 +340,12 @@ static void __save_error_info(struct super_block *sb, const char *func,
 	if (bdev_read_only(sb->s_bdev))
 		return;
 	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-	es->s_last_error_time = cpu_to_le32(get_seconds());
+	ext4_update_tstamp(es, s_last_error_time);
 	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
 	es->s_last_error_line = cpu_to_le32(line);
 	if (!es->s_first_error_time) {
 		es->s_first_error_time = es->s_last_error_time;
+		es->s_first_error_time_hi = es->s_last_error_time_hi;
 		strncpy(es->s_first_error_func, func,
 			sizeof(es->s_first_error_func));
 		es->s_first_error_line = cpu_to_le32(line);
@@ -405,6 +424,9 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 
 static void ext4_handle_error(struct super_block *sb)
 {
+	if (test_opt(sb, WARN_ON_ERROR))
+		WARN_ON_ONCE(1);
+
 	if (sb_rdonly(sb))
 		return;
 
@@ -740,6 +762,9 @@ __acquires(bitlock)
 		va_end(args);
 	}
 
+	if (test_opt(sb, WARN_ON_ERROR))
+		WARN_ON_ONCE(1);
+
 	if (test_opt(sb, ERRORS_CONT)) {
 		ext4_commit_super(sb, 0);
 		return;
@@ -770,26 +795,26 @@ void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
 	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+	int ret;
 
-	if ((flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) &&
-	    !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) {
-		percpu_counter_sub(&sbi->s_freeclusters_counter,
-					grp->bb_free);
-		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
-			&grp->bb_state);
+	if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) {
+		ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
+					    &grp->bb_state);
+		if (!ret)
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 	}
 
-	if ((flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) &&
-	    !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
-		if (gdp) {
+	if (flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) {
+		ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
+					    &grp->bb_state);
+		if (!ret && gdp) {
 			int count;
 
 			count = ext4_free_inodes_count(sb, gdp);
 			percpu_counter_sub(&sbi->s_freeinodes_counter,
 					   count);
 		}
-		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
-			&grp->bb_state);
 	}
 }
 
@@ -1371,7 +1396,8 @@ enum {
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
 	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
-	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
+	Opt_nowarn_on_error, Opt_mblk_io_submit,
 	Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
@@ -1438,6 +1464,8 @@ static const match_table_t tokens = {
 	{Opt_dax, "dax"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
+	{Opt_warn_on_error, "warn_on_error"},
+	{Opt_nowarn_on_error, "nowarn_on_error"},
 	{Opt_lazytime, "lazytime"},
 	{Opt_nolazytime, "nolazytime"},
 	{Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"},
@@ -1602,6 +1630,8 @@ static const struct mount_opts {
 	 MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
 	{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
 	 MOPT_EXT4_ONLY | MOPT_CLEAR},
+	{Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET},
+	{Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR},
 	{Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
 	 MOPT_EXT4_ONLY | MOPT_CLEAR},
 	{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
@@ -2163,8 +2193,8 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 			 "warning: maximal mount count reached, "
 			 "running e2fsck is recommended");
 	else if (le32_to_cpu(es->s_checkinterval) &&
-		(le32_to_cpu(es->s_lastcheck) +
-			le32_to_cpu(es->s_checkinterval) <= get_seconds()))
+		 (ext4_get_tstamp(es, s_lastcheck) +
+		  le32_to_cpu(es->s_checkinterval) <= ktime_get_real_seconds()))
 		ext4_msg(sb, KERN_WARNING,
 			 "warning: checktime reached, "
 			 "running e2fsck is recommended");
@@ -2173,7 +2203,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
 		es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
 	le16_add_cpu(&es->s_mnt_count, 1);
-	es->s_mtime = cpu_to_le32(get_seconds());
+	ext4_update_tstamp(es, s_mtime);
 	ext4_update_dynamic_rev(sb);
 	if (sbi->s_journal)
 		ext4_set_feature_journal_needs_recovery(sb);
@@ -2331,6 +2361,7 @@ static int ext4_check_descriptors(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
 	ext4_fsblk_t last_block;
+	ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0);
 	ext4_fsblk_t block_bitmap;
 	ext4_fsblk_t inode_bitmap;
 	ext4_fsblk_t inode_table;
@@ -2363,6 +2394,14 @@ static int ext4_check_descriptors(struct super_block *sb,
 			if (!sb_rdonly(sb))
 				return 0;
 		}
+		if (block_bitmap >= sb_block + 1 &&
+		    block_bitmap <= last_bg_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Block bitmap for group %u overlaps "
+				 "block group descriptors", i);
+			if (!sb_rdonly(sb))
+				return 0;
+		}
 		if (block_bitmap < first_block || block_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Block bitmap for group %u not in group "
@@ -2377,6 +2416,14 @@ static int ext4_check_descriptors(struct super_block *sb,
 			if (!sb_rdonly(sb))
 				return 0;
 		}
+		if (inode_bitmap >= sb_block + 1 &&
+		    inode_bitmap <= last_bg_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode bitmap for group %u overlaps "
+				 "block group descriptors", i);
+			if (!sb_rdonly(sb))
+				return 0;
+		}
 		if (inode_bitmap < first_block || inode_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Inode bitmap for group %u not in group "
@@ -2391,6 +2438,14 @@ static int ext4_check_descriptors(struct super_block *sb,
 			if (!sb_rdonly(sb))
 				return 0;
 		}
+		if (inode_table >= sb_block + 1 &&
+		    inode_table <= last_bg_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode table for group %u overlaps "
+				 "block group descriptors", i);
+			if (!sb_rdonly(sb))
+				return 0;
+		}
 		if (inode_table < first_block ||
 		    inode_table + sbi->s_itb_per_group - 1 > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -2839,8 +2894,9 @@ static void print_daily_error_info(struct timer_list *t)
 		ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
 			 le32_to_cpu(es->s_error_count));
 	if (es->s_first_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
-		       sb->s_id, le32_to_cpu(es->s_first_error_time),
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %llu: %.*s:%d",
+		       sb->s_id,
+		       ext4_get_tstamp(es, s_first_error_time),
 		       (int) sizeof(es->s_first_error_func),
 		       es->s_first_error_func,
 		       le32_to_cpu(es->s_first_error_line));
@@ -2853,8 +2909,9 @@ static void print_daily_error_info(struct timer_list *t)
 		printk(KERN_CONT "\n");
 	}
 	if (es->s_last_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
-		       sb->s_id, le32_to_cpu(es->s_last_error_time),
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %llu: %.*s:%d",
+		       sb->s_id,
+		       ext4_get_tstamp(es, s_last_error_time),
 		       (int) sizeof(es->s_last_error_func),
 		       es->s_last_error_func,
 		       le32_to_cpu(es->s_last_error_line));
@@ -3097,6 +3154,9 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
 	ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
 	struct ext4_group_desc *gdp = NULL;
 
+	if (!ext4_has_group_desc_csum(sb))
+		return ngroups;
+
 	for (group = 0; group < ngroups; group++) {
 		gdp = ext4_get_group_desc(sb, group, NULL);
 		if (!gdp)
@@ -3469,7 +3529,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_sb_block = sb_block;
 	if (sb->s_bdev->bd_part)
 		sbi->s_sectors_written_start =
-			part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+			part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]);
 
 	/* Cleanup superblock name */
 	strreplace(sb->s_id, '/', '!');
@@ -3742,6 +3802,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			 le32_to_cpu(es->s_log_block_size));
 		goto failed_mount;
 	}
+	if (le32_to_cpu(es->s_log_cluster_size) >
+	    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Invalid log cluster size: %u",
+			 le32_to_cpu(es->s_log_cluster_size));
+		goto failed_mount;
+	}
 
 	if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
 		ext4_msg(sb, KERN_ERR,
@@ -3806,6 +3873,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	} else {
 		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
 		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
+		if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) {
+			ext4_msg(sb, KERN_ERR, "invalid first ino: %u",
+				 sbi->s_first_ino);
+			goto failed_mount;
+		}
 		if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
 		    (!is_power_of_2(sbi->s_inode_size)) ||
 		    (sbi->s_inode_size > blocksize)) {
@@ -3882,13 +3954,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "block size (%d)", clustersize, blocksize);
 			goto failed_mount;
 		}
-		if (le32_to_cpu(es->s_log_cluster_size) >
-		    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
-			ext4_msg(sb, KERN_ERR,
-				 "Invalid log cluster size: %u",
-				 le32_to_cpu(es->s_log_cluster_size));
-			goto failed_mount;
-		}
 		sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
 			le32_to_cpu(es->s_log_block_size);
 		sbi->s_clusters_per_group =
@@ -3909,10 +3974,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		}
 	} else {
 		if (clustersize != blocksize) {
-			ext4_warning(sb, "fragment/cluster size (%d) != "
-				     "block size (%d)", clustersize,
-				     blocksize);
-			clustersize = blocksize;
+			ext4_msg(sb, KERN_ERR,
+				 "fragment/cluster size (%d) != "
+				 "block size (%d)", clustersize, blocksize);
+			goto failed_mount;
 		}
 		if (sbi->s_blocks_per_group > blocksize * 8) {
 			ext4_msg(sb, KERN_ERR,
@@ -3966,6 +4031,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			 ext4_blocks_count(es));
 		goto failed_mount;
 	}
+	if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) &&
+	    (sbi->s_cluster_ratio == 1)) {
+		ext4_msg(sb, KERN_WARNING, "bad geometry: first data "
+			 "block is 0 with a 1k block and cluster size");
+		goto failed_mount;
+	}
+
 	blocks_count = (ext4_blocks_count(es) -
 			le32_to_cpu(es->s_first_data_block) +
 			EXT4_BLOCKS_PER_GROUP(sb) - 1);
@@ -4001,6 +4073,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		ret = -ENOMEM;
 		goto failed_mount;
 	}
+	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
+	    le32_to_cpu(es->s_inodes_count)) {
+		ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
+			 le32_to_cpu(es->s_inodes_count),
+			 ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
+		ret = -EINVAL;
+		goto failed_mount;
+	}
 
 	bgl_lock_init(sbi->s_blockgroup_lock);
 
@@ -4020,14 +4100,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount2;
 		}
 	}
+	sbi->s_gdb_count = db_count;
 	if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
 		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
 		ret = -EFSCORRUPTED;
 		goto failed_mount2;
 	}
 
-	sbi->s_gdb_count = db_count;
-
 	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
 
 	/* Register extent status tree shrinker */
@@ -4736,6 +4815,14 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 
 	if (!sbh || block_device_ejected(sb))
 		return error;
+
+	/*
+	 * The superblock bh should be mapped, but it might not be if the
+	 * device was hot-removed. Not much we can do but fail the I/O.
+	 */
+	if (!buffer_mapped(sbh))
+		return error;
+
 	/*
 	 * If the file system is mounted read-only, don't update the
 	 * superblock write time.  This avoids updating the superblock
@@ -4747,11 +4834,12 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	 * to complain and force a full file system check.
 	 */
 	if (!(sb->s_flags & SB_RDONLY))
-		es->s_wtime = cpu_to_le32(get_seconds());
+		ext4_update_tstamp(es, s_wtime);
 	if (sb->s_bdev->bd_part)
 		es->s_kbytes_written =
 			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
-			    ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			    ((part_stat_read(sb->s_bdev->bd_part,
+					     sectors[STAT_WRITE]) -
 			      EXT4_SB(sb)->s_sectors_written_start) >> 1));
 	else
 		es->s_kbytes_written =
@@ -5014,6 +5102,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 #endif
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 
+	if (data && !orig_data)
+		return -ENOMEM;
+
 	/* Store the original options */
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;
@@ -5140,6 +5231,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 
 			if (sbi->s_journal)
 				ext4_mark_recovery_complete(sb, es);
+			if (sbi->s_mmp_tsk)
+				kthread_stop(sbi->s_mmp_tsk);
 		} else {
 			/* Make sure we can mount this feature set readwrite */
 			if (ext4_has_feature_readonly(sb) ||
@@ -5597,13 +5690,13 @@ static int ext4_enable_quotas(struct super_block *sb)
 				DQUOT_USAGE_ENABLED |
 				(quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
 			if (err) {
-				for (type--; type >= 0; type--)
-					dquot_quota_off(sb, type);
-
 				ext4_warning(sb,
 					"Failed to enable quota tracking "
 					"(type=%d, err=%d). Please run "
 					"e2fsck to fix.", type, err);
+				for (type--; type >= 0; type--)
+					dquot_quota_off(sb, type);
+
 				return err;
 			}
 		}
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index f34da0bb8f17..9212a026a1f1 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -25,6 +25,8 @@ typedef enum {
 	attr_reserved_clusters,
 	attr_inode_readahead,
 	attr_trigger_test_error,
+	attr_first_error_time,
+	attr_last_error_time,
 	attr_feature,
 	attr_pointer_ui,
 	attr_pointer_atomic,
@@ -56,7 +58,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 	if (!sb->s_bdev->bd_part)
 		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%lu\n",
-			(part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			(part_stat_read(sb->s_bdev->bd_part,
+					sectors[STAT_WRITE]) -
 			 sbi->s_sectors_written_start) >> 1);
 }
 
@@ -68,7 +71,8 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			(unsigned long long)(sbi->s_kbytes_written +
-			((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			((part_stat_read(sb->s_bdev->bd_part,
+					 sectors[STAT_WRITE]) -
 			  EXT4_SB(sb)->s_sectors_written_start) >> 1)));
 }
 
@@ -182,8 +186,8 @@ EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
 EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
-EXT4_RO_ATTR_ES_UI(first_error_time, s_first_error_time);
-EXT4_RO_ATTR_ES_UI(last_error_time, s_last_error_time);
+EXT4_ATTR(first_error_time, 0444, first_error_time);
+EXT4_ATTR(last_error_time, 0444, last_error_time);
 
 static unsigned int old_bump_val = 128;
 EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
@@ -249,6 +253,15 @@ static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi)
 	return NULL;
 }
 
+static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi)
+{
+	return snprintf(buf, PAGE_SIZE, "%lld",
+			((time64_t)hi << 32) + le32_to_cpu(lo));
+}
+
+#define print_tstamp(buf, es, tstamp) \
+	__print_tstamp(buf, (es)->tstamp, (es)->tstamp ## _hi)
+
 static ssize_t ext4_attr_show(struct kobject *kobj,
 			      struct attribute *attr, char *buf)
 {
@@ -274,8 +287,12 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 	case attr_pointer_ui:
 		if (!ptr)
 			return 0;
-		return snprintf(buf, PAGE_SIZE, "%u\n",
-				*((unsigned int *) ptr));
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			return snprintf(buf, PAGE_SIZE, "%u\n",
+					le32_to_cpup(ptr));
+		else
+			return snprintf(buf, PAGE_SIZE, "%u\n",
+					*((unsigned int *) ptr));
 	case attr_pointer_atomic:
 		if (!ptr)
 			return 0;
@@ -283,6 +300,10 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 				atomic_read((atomic_t *) ptr));
 	case attr_feature:
 		return snprintf(buf, PAGE_SIZE, "supported\n");
+	case attr_first_error_time:
+		return print_tstamp(buf, sbi->s_es, s_first_error_time);
+	case attr_last_error_time:
+		return print_tstamp(buf, sbi->s_es, s_last_error_time);
 	}
 
 	return 0;
@@ -308,7 +329,10 @@ static ssize_t ext4_attr_store(struct kobject *kobj,
 		ret = kstrtoul(skip_spaces(buf), 0, &t);
 		if (ret)
 			return ret;
-		*((unsigned int *) ptr) = t;
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			*((__le32 *) ptr) = cpu_to_le32(t);
+		else
+			*((unsigned int *) ptr) = t;
 		return len;
 	case attr_inode_readahead:
 		return inode_readahead_blks_store(sbi, buf, len);
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index 0cb13badf473..bcbe3668c1d4 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -11,6 +11,10 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	/*
+	 * We don't need to call ext4_break_layouts() because the blocks we
+	 * are truncating were never visible to userspace.
+	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
 	truncate_inode_pages(inode->i_mapping, inode->i_size);
 	ext4_truncate(inode);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index fc4ced59c565..f36fc5d5b257 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -190,6 +190,8 @@ ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end,
 		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
 		if ((void *)next >= end)
 			return -EFSCORRUPTED;
+		if (strnlen(e->e_name, e->e_name_len) != e->e_name_len)
+			return -EFSCORRUPTED;
 		e = next;
 	}
 
@@ -230,12 +232,12 @@ __ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh,
 {
 	int error = -EFSCORRUPTED;
 
-	if (buffer_verified(bh))
-		return 0;
-
 	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
 	    BHDR(bh)->h_blocks != cpu_to_le32(1))
 		goto errout;
+	if (buffer_verified(bh))
+		return 0;
+
 	error = -EFSBADCRC;
 	if (!ext4_xattr_block_csum_verify(inode, bh))
 		goto errout;
@@ -1560,7 +1562,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 				handle_t *handle, struct inode *inode,
 				bool is_block)
 {
-	struct ext4_xattr_entry *last;
+	struct ext4_xattr_entry *last, *next;
 	struct ext4_xattr_entry *here = s->here;
 	size_t min_offs = s->end - s->base, name_len = strlen(i->name);
 	int in_inode = i->in_inode;
@@ -1595,7 +1597,13 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 
 	/* Compute min_offs and last. */
 	last = s->first;
-	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+	for (; !IS_LAST_ENTRY(last); last = next) {
+		next = EXT4_XATTR_NEXT(last);
+		if ((void *)next >= s->end) {
+			EXT4_ERROR_INODE(inode, "corrupted xattr entries");
+			ret = -EFSCORRUPTED;
+			goto out;
+		}
 		if (!last->e_value_inum && last->e_value_size) {
 			size_t offs = le16_to_cpu(last->e_value_offs);
 			if (offs < min_offs)
@@ -2206,23 +2214,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 	if (EXT4_I(inode)->i_extra_isize == 0)
 		return -ENOSPC;
 	error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
-	if (error) {
-		if (error == -ENOSPC &&
-		    ext4_has_inline_data(inode)) {
-			error = ext4_try_to_evict_inline_data(handle, inode,
-					EXT4_XATTR_LEN(strlen(i->name) +
-					EXT4_XATTR_SIZE(i->value_len)));
-			if (error)
-				return error;
-			error = ext4_xattr_ibody_find(inode, i, is);
-			if (error)
-				return error;
-			error = ext4_xattr_set_entry(i, s, handle, inode,
-						     false /* is_block */);
-		}
-		if (error)
-			return error;
-	}
+	if (error)
+		return error;
 	header = IHDR(inode, ext4_raw_inode(&is->iloc));
 	if (!IS_LAST_ENTRY(s->first)) {
 		header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
@@ -2651,6 +2644,11 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode,
 		last = IFIRST(header);
 		/* Find the entry best suited to be pushed into EA block */
 		for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+			/* never move system.data out of the inode */
+			if ((last->e_name_len == 4) &&
+			    (last->e_name_index == EXT4_XATTR_INDEX_SYSTEM) &&
+			    !memcmp(last->e_name, "data", 4))
+				continue;
 			total_size = EXT4_XATTR_LEN(last->e_name_len);
 			if (!last->e_value_inum)
 				total_size += EXT4_XATTR_SIZE(
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 4d8b1de83143..6799c3fc44e3 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1304,7 +1304,7 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
  * and the return value is in kbytes. s is of struct f2fs_sb_info.
  */
 #define BD_PART_WRITTEN(s)						 \
-(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[1]) -		 \
+(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
 		(s)->sectors_written_start) >> 1)
 
 static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 3995e926ba3a..17bcff789c08 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2882,7 +2882,8 @@ try_onemore:
 	/* For write statistics */
 	if (sb->s_bdev->bd_part)
 		sbi->sectors_written_start =
-			(u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+			(u64)part_stat_read(sb->s_bdev->bd_part,
+					    sectors[STAT_WRITE]);
 
 	/* Read accumulated write IO statistics if exists */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 065dc919a0ce..bfd589ea74c0 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -707,13 +707,21 @@ static void fat_set_state(struct super_block *sb,
 	brelse(bh);
 }
 
+static void fat_reset_iocharset(struct fat_mount_options *opts)
+{
+	if (opts->iocharset != fat_default_iocharset) {
+		/* Note: opts->iocharset can be NULL here */
+		kfree(opts->iocharset);
+		opts->iocharset = fat_default_iocharset;
+	}
+}
+
 static void delayed_free(struct rcu_head *p)
 {
 	struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu);
 	unload_nls(sbi->nls_disk);
 	unload_nls(sbi->nls_io);
-	if (sbi->options.iocharset != fat_default_iocharset)
-		kfree(sbi->options.iocharset);
+	fat_reset_iocharset(&sbi->options);
 	kfree(sbi);
 }
 
@@ -1132,7 +1140,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 	opts->fs_fmask = opts->fs_dmask = current_umask();
 	opts->allow_utime = -1;
 	opts->codepage = fat_default_codepage;
-	opts->iocharset = fat_default_iocharset;
+	fat_reset_iocharset(opts);
 	if (is_vfat) {
 		opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95;
 		opts->rodir = 0;
@@ -1289,8 +1297,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 
 		/* vfat specific */
 		case Opt_charset:
-			if (opts->iocharset != fat_default_iocharset)
-				kfree(opts->iocharset);
+			fat_reset_iocharset(opts);
 			iocharset = match_strdup(&args[0]);
 			if (!iocharset)
 				return -ENOMEM;
@@ -1881,8 +1888,7 @@ out_fail:
 		iput(fat_inode);
 	unload_nls(sbi->nls_io);
 	unload_nls(sbi->nls_disk);
-	if (sbi->options.iocharset != fat_default_iocharset)
-		kfree(sbi->options.iocharset);
+	fat_reset_iocharset(&sbi->options);
 	sb->s_fs_info = NULL;
 	kfree(sbi);
 	return error;
diff --git a/fs/file_table.c b/fs/file_table.c
index 7ec0b3e5f05d..d6eccd04d703 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -51,6 +51,7 @@ static void file_free_rcu(struct rcu_head *head)
 
 static inline void file_free(struct file *f)
 {
+	security_file_free(f);
 	percpu_counter_dec(&nr_files);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
@@ -100,9 +101,8 @@ int proc_nr_files(struct ctl_table *table, int write,
  * done, you will imbalance int the mount's writer count
  * and a warning at __fput() time.
  */
-struct file *get_empty_filp(void)
+struct file *alloc_empty_file(int flags, const struct cred *cred)
 {
-	const struct cred *cred = current_cred();
 	static long old_max;
 	struct file *f;
 	int error;
@@ -123,11 +123,10 @@ struct file *get_empty_filp(void)
 	if (unlikely(!f))
 		return ERR_PTR(-ENOMEM);
 
-	percpu_counter_inc(&nr_files);
 	f->f_cred = get_cred(cred);
 	error = security_file_alloc(f);
 	if (unlikely(error)) {
-		file_free(f);
+		file_free_rcu(&f->f_u.fu_rcuhead);
 		return ERR_PTR(error);
 	}
 
@@ -136,7 +135,10 @@ struct file *get_empty_filp(void)
 	spin_lock_init(&f->f_lock);
 	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
+	f->f_flags = flags;
+	f->f_mode = OPEN_FMODE(flags);
 	/* f->f_version: 0 */
+	percpu_counter_inc(&nr_files);
 	return f;
 
 over:
@@ -152,15 +154,15 @@ over:
  * alloc_file - allocate and initialize a 'struct file'
  *
  * @path: the (dentry, vfsmount) pair for the new file
- * @mode: the mode with which the new file will be opened
+ * @flags: O_... flags with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
  */
-struct file *alloc_file(const struct path *path, fmode_t mode,
+static struct file *alloc_file(const struct path *path, int flags,
 		const struct file_operations *fop)
 {
 	struct file *file;
 
-	file = get_empty_filp();
+	file = alloc_empty_file(flags, current_cred());
 	if (IS_ERR(file))
 		return file;
 
@@ -168,19 +170,56 @@ struct file *alloc_file(const struct path *path, fmode_t mode,
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
 	file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
-	if ((mode & FMODE_READ) &&
+	if ((file->f_mode & FMODE_READ) &&
 	     likely(fop->read || fop->read_iter))
-		mode |= FMODE_CAN_READ;
-	if ((mode & FMODE_WRITE) &&
+		file->f_mode |= FMODE_CAN_READ;
+	if ((file->f_mode & FMODE_WRITE) &&
 	     likely(fop->write || fop->write_iter))
-		mode |= FMODE_CAN_WRITE;
-	file->f_mode = mode;
+		file->f_mode |= FMODE_CAN_WRITE;
+	file->f_mode |= FMODE_OPENED;
 	file->f_op = fop;
-	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
 	return file;
 }
-EXPORT_SYMBOL(alloc_file);
+
+struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
+				const char *name, int flags,
+				const struct file_operations *fops)
+{
+	static const struct dentry_operations anon_ops = {
+		.d_dname = simple_dname
+	};
+	struct qstr this = QSTR_INIT(name, strlen(name));
+	struct path path;
+	struct file *file;
+
+	path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
+	if (!path.dentry)
+		return ERR_PTR(-ENOMEM);
+	if (!mnt->mnt_sb->s_d_op)
+		d_set_d_op(path.dentry, &anon_ops);
+	path.mnt = mntget(mnt);
+	d_instantiate(path.dentry, inode);
+	file = alloc_file(&path, flags, fops);
+	if (IS_ERR(file)) {
+		ihold(inode);
+		path_put(&path);
+	}
+	return file;
+}
+EXPORT_SYMBOL(alloc_file_pseudo);
+
+struct file *alloc_file_clone(struct file *base, int flags,
+				const struct file_operations *fops)
+{
+	struct file *f = alloc_file(&base->f_path, flags, fops);
+	if (!IS_ERR(f)) {
+		path_get(&f->f_path);
+		f->f_mapping = base->f_mapping;
+	}
+	return f;
+}
 
 /* the real guts of fput() - releasing the last reference to file
  */
@@ -190,6 +229,9 @@ static void __fput(struct file *file)
 	struct vfsmount *mnt = file->f_path.mnt;
 	struct inode *inode = file->f_inode;
 
+	if (unlikely(!(file->f_mode & FMODE_OPENED)))
+		goto out;
+
 	might_sleep();
 
 	fsnotify_close(file);
@@ -207,7 +249,6 @@ static void __fput(struct file *file)
 	}
 	if (file->f_op->release)
 		file->f_op->release(inode, file);
-	security_file_free(file);
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
 		     !(file->f_mode & FMODE_PATH))) {
 		cdev_put(inode->i_cdev);
@@ -220,12 +261,10 @@ static void __fput(struct file *file)
 		put_write_access(inode);
 		__mnt_drop_write(mnt);
 	}
-	file->f_path.dentry = NULL;
-	file->f_path.mnt = NULL;
-	file->f_inode = NULL;
-	file_free(file);
 	dput(dentry);
 	mntput(mnt);
+out:
+	file_free(file);
 }
 
 static LLIST_HEAD(delayed_fput_list);
@@ -300,14 +339,6 @@ void __fput_sync(struct file *file)
 
 EXPORT_SYMBOL(fput);
 
-void put_filp(struct file *file)
-{
-	if (atomic_long_dec_and_test(&file->f_count)) {
-		security_file_free(file);
-		file_free(file);
-	}
-}
-
 void __init files_init(void)
 {
 	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c
index c184c5a356ff..cdcb376ef8df 100644
--- a/fs/fscache/cache.c
+++ b/fs/fscache/cache.c
@@ -220,6 +220,7 @@ int fscache_add_cache(struct fscache_cache *cache,
 {
 	struct fscache_cache_tag *tag;
 
+	ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index);
 	BUG_ON(!cache->ops);
 	BUG_ON(!ifsdef);
 
@@ -248,7 +249,6 @@ int fscache_add_cache(struct fscache_cache *cache,
 	if (!cache->kobj)
 		goto error;
 
-	ifsdef->cookie = &fscache_fsdef_index;
 	ifsdef->cache = cache;
 	cache->fsdef = ifsdef;
 
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 97137d7ec5ee..83bfe04456b6 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -516,6 +516,7 @@ static int fscache_alloc_object(struct fscache_cache *cache,
 		goto error;
 	}
 
+	ASSERTCMP(object->cookie, ==, cookie);
 	fscache_stat(&fscache_n_object_alloc);
 
 	object->debug_id = atomic_inc_return(&fscache_object_debug_id);
@@ -571,6 +572,8 @@ static int fscache_attach_object(struct fscache_cookie *cookie,
 
 	_enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id);
 
+	ASSERTCMP(object->cookie, ==, cookie);
+
 	spin_lock(&cookie->lock);
 
 	/* there may be multiple initial creations of this object, but we only
@@ -610,9 +613,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie,
 		spin_unlock(&cache->object_list_lock);
 	}
 
-	/* attach to the cookie */
-	object->cookie = cookie;
-	fscache_cookie_get(cookie, fscache_cookie_get_attach_object);
+	/* Attach to the cookie.  The object already has a ref on it. */
 	hlist_add_head(&object->cookie_link, &cookie->backing_objects);
 
 	fscache_objlist_add(object);
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 20e0d0a4dc8c..9edc920f651f 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -327,6 +327,7 @@ void fscache_object_init(struct fscache_object *object,
 	object->store_limit_l = 0;
 	object->cache = cache;
 	object->cookie = cookie;
+	fscache_cookie_get(cookie, fscache_cookie_get_attach_object);
 	object->parent = NULL;
 #ifdef CONFIG_FSCACHE_OBJECT_LIST
 	RB_CLEAR_NODE(&object->objlist_link);
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index e30c5975ea58..8d265790374c 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -70,7 +70,8 @@ void fscache_enqueue_operation(struct fscache_operation *op)
 	ASSERT(op->processor != NULL);
 	ASSERT(fscache_object_is_available(op->object));
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
-	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
+	ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS,
+		    op->state, ==,  FSCACHE_OP_ST_CANCELLED);
 
 	fscache_stat(&fscache_n_op_enqueue);
 	switch (op->flags & FSCACHE_OP_TYPE) {
@@ -499,7 +500,8 @@ void fscache_put_operation(struct fscache_operation *op)
 	struct fscache_cache *cache;
 
 	_enter("{OBJ%x OP%x,%d}",
-	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+	       op->object ? op->object->debug_id : 0,
+	       op->debug_id, atomic_read(&op->usage));
 
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 56231b31f806..d80aab0d5982 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -399,7 +399,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
  */
 static int fuse_create_open(struct inode *dir, struct dentry *entry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	int err;
 	struct inode *inode;
@@ -469,7 +469,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	d_instantiate(entry, inode);
 	fuse_change_entry_timeout(entry, &outentry);
 	fuse_invalidate_attr(dir);
-	err = finish_open(file, entry, generic_file_open, opened);
+	err = finish_open(file, entry, generic_file_open);
 	if (err) {
 		fuse_sync_release(ff, flags);
 	} else {
@@ -489,7 +489,7 @@ out_err:
 static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	int err;
 	struct fuse_conn *fc = get_fuse_conn(dir);
@@ -508,12 +508,12 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 		goto no_open;
 
 	/* Only creates */
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 
 	if (fc->no_create)
 		goto mknod;
 
-	err = fuse_create_open(dir, entry, file, flags, mode, opened);
+	err = fuse_create_open(dir, entry, file, flags, mode);
 	if (err == -ENOSYS) {
 		fc->no_create = 1;
 		goto mknod;
@@ -539,6 +539,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args,
 {
 	struct fuse_entry_out outarg;
 	struct inode *inode;
+	struct dentry *d;
 	int err;
 	struct fuse_forget_link *forget;
 
@@ -570,11 +571,17 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args,
 	}
 	kfree(forget);
 
-	err = d_instantiate_no_diralias(entry, inode);
-	if (err)
-		return err;
+	d_drop(entry);
+	d = d_splice_alias(inode, entry);
+	if (IS_ERR(d))
+		return PTR_ERR(d);
 
-	fuse_change_entry_timeout(entry, &outarg);
+	if (d) {
+		fuse_change_entry_timeout(d, &outarg);
+		dput(d);
+	} else {
+		fuse_change_entry_timeout(entry, &outarg);
+	}
 	fuse_invalidate_attr(dir);
 	return 0;
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index feda55f67050..648f0ca1ad57 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -580,7 +580,7 @@ static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 			     struct file *file,
 			     umode_t mode, dev_t dev, const char *symname,
-			     unsigned int size, int excl, int *opened)
+			     unsigned int size, int excl)
 {
 	const struct qstr *name = &dentry->d_name;
 	struct posix_acl *default_acl, *acl;
@@ -626,7 +626,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		error = 0;
 		if (file) {
 			if (S_ISREG(inode->i_mode))
-				error = finish_open(file, dentry, gfs2_open_common, opened);
+				error = finish_open(file, dentry, gfs2_open_common);
 			else
 				error = finish_no_open(file, NULL);
 		}
@@ -767,8 +767,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	mark_inode_dirty(inode);
 	d_instantiate(dentry, inode);
 	if (file) {
-		*opened |= FILE_CREATED;
-		error = finish_open(file, dentry, gfs2_open_common, opened);
+		file->f_mode |= FMODE_CREATED;
+		error = finish_open(file, dentry, gfs2_open_common);
 	}
 	gfs2_glock_dq_uninit(ghs);
 	gfs2_glock_dq_uninit(ghs + 1);
@@ -822,7 +822,7 @@ fail:
 static int gfs2_create(struct inode *dir, struct dentry *dentry,
 		       umode_t mode, bool excl)
 {
-	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /**
@@ -830,14 +830,13 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
  * @dir: The directory inode
  * @dentry: The dentry of the new inode
  * @file: File to be opened
- * @opened: atomic_open flags
  *
  *
  * Returns: errno
  */
 
 static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
-				    struct file *file, int *opened)
+				    struct file *file)
 {
 	struct inode *inode;
 	struct dentry *d;
@@ -866,7 +865,7 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
 		return d;
 	}
 	if (file && S_ISREG(inode->i_mode))
-		error = finish_open(file, dentry, gfs2_open_common, opened);
+		error = finish_open(file, dentry, gfs2_open_common);
 
 	gfs2_glock_dq_uninit(&gh);
 	if (error) {
@@ -879,7 +878,7 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
 static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
 				  unsigned flags)
 {
-	return __gfs2_lookup(dir, dentry, NULL, NULL);
+	return __gfs2_lookup(dir, dentry, NULL);
 }
 
 /**
@@ -1189,7 +1188,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 	if (size >= gfs2_max_stuffed_size(GFS2_I(dir)))
 		return -ENAMETOOLONG;
 
-	return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
 }
 
 /**
@@ -1204,7 +1203,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir));
-	return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0);
 }
 
 /**
@@ -1219,7 +1218,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 		      dev_t dev)
 {
-	return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0);
 }
 
 /**
@@ -1229,14 +1228,13 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
  * @file: The proposed new struct file
  * @flags: open flags
  * @mode: File mode
- * @opened: Flag to say whether the file has been opened or not
  *
  * Returns: error code or 0 for success
  */
 
 static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	struct dentry *d;
 	bool excl = !!(flags & O_EXCL);
@@ -1244,13 +1242,13 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (!d_in_lookup(dentry))
 		goto skip_lookup;
 
-	d = __gfs2_lookup(dir, dentry, file, opened);
+	d = __gfs2_lookup(dir, dentry, file);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
 	if (d != NULL)
 		dentry = d;
 	if (d_really_is_positive(dentry)) {
-		if (!(*opened & FILE_OPENED))
+		if (!(file->f_mode & FMODE_OPENED))
 			return finish_no_open(file, d);
 		dput(d);
 		return 0;
@@ -1262,7 +1260,7 @@ skip_lookup:
 	if (!(flags & O_CREAT))
 		return -ENOENT;
 
-	return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl, opened);
+	return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /*
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 2a16111d312f..a2dfa1b2a89c 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -541,7 +541,7 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
 	HFS_I(inode)->rsrc_inode = dir;
 	HFS_I(dir)->rsrc_inode = inode;
 	igrab(dir);
-	hlist_add_fake(&inode->i_hash);
+	inode_fake_hash(inode);
 	mark_inode_dirty(inode);
 	dont_mount(dentry);
 out:
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 2597b290c2a5..444c7b170359 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -610,33 +610,21 @@ static struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
 	int err;
 
 	inode = hostfs_iget(ino->i_sb);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
+	if (IS_ERR(inode))
 		goto out;
-	}
 
 	err = -ENOMEM;
 	name = dentry_name(dentry);
-	if (name == NULL)
-		goto out_put;
-
-	err = read_name(inode, name);
-
-	__putname(name);
-	if (err == -ENOENT) {
+	if (name) {
+		err = read_name(inode, name);
+		__putname(name);
+	}
+	if (err) {
 		iput(inode);
-		inode = NULL;
+		inode = (err == -ENOENT) ? NULL : ERR_PTR(err);
 	}
-	else if (err)
-		goto out_put;
-
-	d_add(dentry, inode);
-	return NULL;
-
- out_put:
-	iput(inode);
  out:
-	return ERR_PTR(err);
+	return d_splice_alias(inode, dentry);
 }
 
 static int hostfs_link(struct dentry *to, struct inode *ino,
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index c83ece7facc5..d85230c84ef2 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -244,6 +244,7 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in
 	result = iget_locked(dir->i_sb, ino);
 	if (!result) {
 		hpfs_error(dir->i_sb, "hpfs_lookup: can't get inode");
+		result = ERR_PTR(-ENOMEM);
 		goto bail1;
 	}
 	if (result->i_state & I_NEW) {
@@ -266,6 +267,8 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in
 
 	if (de->has_acl || de->has_xtd_perm) if (!sb_rdonly(dir->i_sb)) {
 		hpfs_error(result->i_sb, "ACLs or XPERM found. This is probably HPFS386. This driver doesn't support it now. Send me some info on these structures");
+		iput(result);
+		result = ERR_PTR(-EINVAL);
 		goto bail1;
 	}
 
@@ -301,29 +304,17 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in
 		}
 	}
 
+bail1:
 	hpfs_brelse4(&qbh);
 
 	/*
 	 * Made it.
 	 */
 
-	end:
-	end_add:
+end:
+end_add:
 	hpfs_unlock(dir->i_sb);
-	d_add(dentry, result);
-	return NULL;
-
-	/*
-	 * Didn't.
-	 */
-	bail1:
-	
-	hpfs_brelse4(&qbh);
-	
-	/*bail:*/
-
-	hpfs_unlock(dir->i_sb);
-	return ERR_PTR(-ENOENT);
+	return d_splice_alias(result, dentry);
 }
 
 const struct file_operations hpfs_dir_ops =
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d508c7844681..346a146c7617 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -411,6 +411,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	bool truncate_op = (lend == LLONG_MAX);
 
 	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	vma_init(&pseudo_vma, current->mm);
 	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pagevec_init(&pvec);
 	next = start;
@@ -595,6 +596,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	 * as input to create an allocation policy.
 	 */
 	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	vma_init(&pseudo_vma, mm);
 	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pseudo_vma.vm_file = file;
 
@@ -1308,10 +1310,6 @@ static int get_hstate_idx(int page_size_log)
 	return h - hstates;
 }
 
-static const struct dentry_operations anon_ops = {
-	.d_dname = simple_dname
-};
-
 /*
  * Note that size should be aligned to proper hugepage size in caller side,
  * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
@@ -1320,19 +1318,18 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 				vm_flags_t acctflag, struct user_struct **user,
 				int creat_flags, int page_size_log)
 {
-	struct file *file = ERR_PTR(-ENOMEM);
 	struct inode *inode;
-	struct path path;
-	struct super_block *sb;
-	struct qstr quick_string;
+	struct vfsmount *mnt;
 	int hstate_idx;
+	struct file *file;
 
 	hstate_idx = get_hstate_idx(page_size_log);
 	if (hstate_idx < 0)
 		return ERR_PTR(-ENODEV);
 
 	*user = NULL;
-	if (!hugetlbfs_vfsmount[hstate_idx])
+	mnt = hugetlbfs_vfsmount[hstate_idx];
+	if (!mnt)
 		return ERR_PTR(-ENOENT);
 
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
@@ -1348,45 +1345,28 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 		}
 	}
 
-	sb = hugetlbfs_vfsmount[hstate_idx]->mnt_sb;
-	quick_string.name = name;
-	quick_string.len = strlen(quick_string.name);
-	quick_string.hash = 0;
-	path.dentry = d_alloc_pseudo(sb, &quick_string);
-	if (!path.dentry)
-		goto out_shm_unlock;
-
-	d_set_d_op(path.dentry, &anon_ops);
-	path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
 	file = ERR_PTR(-ENOSPC);
-	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
-		goto out_dentry;
+		goto out;
 	if (creat_flags == HUGETLB_SHMFS_INODE)
 		inode->i_flags |= S_PRIVATE;
 
-	file = ERR_PTR(-ENOMEM);
-	if (hugetlb_reserve_pages(inode, 0,
-			size >> huge_page_shift(hstate_inode(inode)), NULL,
-			acctflag))
-		goto out_inode;
-
-	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
 	clear_nlink(inode);
 
-	file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
-			&hugetlbfs_file_operations);
-	if (IS_ERR(file))
-		goto out_dentry; /* inode is already attached */
-
-	return file;
+	if (hugetlb_reserve_pages(inode, 0,
+			size >> huge_page_shift(hstate_inode(inode)), NULL,
+			acctflag))
+		file = ERR_PTR(-ENOMEM);
+	else
+		file = alloc_file_pseudo(inode, mnt, name, O_RDWR,
+					&hugetlbfs_file_operations);
+	if (!IS_ERR(file))
+		return file;
 
-out_inode:
 	iput(inode);
-out_dentry:
-	path_put(&path);
-out_shm_unlock:
+out:
 	if (*user) {
 		user_shm_unlock(size, *user);
 		*user = NULL;
diff --git a/fs/inode.c b/fs/inode.c
index 2c300e981796..a06de4454232 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -804,6 +804,10 @@ repeat:
 			__wait_on_freeing_inode(inode);
 			goto repeat;
 		}
+		if (unlikely(inode->i_state & I_CREATING)) {
+			spin_unlock(&inode->i_lock);
+			return ERR_PTR(-ESTALE);
+		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
 		return inode;
@@ -831,6 +835,10 @@ repeat:
 			__wait_on_freeing_inode(inode);
 			goto repeat;
 		}
+		if (unlikely(inode->i_state & I_CREATING)) {
+			spin_unlock(&inode->i_lock);
+			return ERR_PTR(-ESTALE);
+		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
 		return inode;
@@ -961,13 +969,26 @@ void unlock_new_inode(struct inode *inode)
 	lockdep_annotate_inode_mutex_key(inode);
 	spin_lock(&inode->i_lock);
 	WARN_ON(!(inode->i_state & I_NEW));
-	inode->i_state &= ~I_NEW;
+	inode->i_state &= ~I_NEW & ~I_CREATING;
 	smp_mb();
 	wake_up_bit(&inode->i_state, __I_NEW);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(unlock_new_inode);
 
+void discard_new_inode(struct inode *inode)
+{
+	lockdep_annotate_inode_mutex_key(inode);
+	spin_lock(&inode->i_lock);
+	WARN_ON(!(inode->i_state & I_NEW));
+	inode->i_state &= ~I_NEW;
+	smp_mb();
+	wake_up_bit(&inode->i_state, __I_NEW);
+	spin_unlock(&inode->i_lock);
+	iput(inode);
+}
+EXPORT_SYMBOL(discard_new_inode);
+
 /**
  * lock_two_nondirectories - take two i_mutexes on non-directory objects
  *
@@ -1029,6 +1050,7 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
 {
 	struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
 	struct inode *old;
+	bool creating = inode->i_state & I_CREATING;
 
 again:
 	spin_lock(&inode_hash_lock);
@@ -1039,6 +1061,8 @@ again:
 		 * Use the old inode instead of the preallocated one.
 		 */
 		spin_unlock(&inode_hash_lock);
+		if (IS_ERR(old))
+			return NULL;
 		wait_on_inode(old);
 		if (unlikely(inode_unhashed(old))) {
 			iput(old);
@@ -1060,6 +1084,8 @@ again:
 	inode->i_state |= I_NEW;
 	hlist_add_head(&inode->i_hash, head);
 	spin_unlock(&inode->i_lock);
+	if (!creating)
+		inode_sb_list_add(inode);
 unlock:
 	spin_unlock(&inode_hash_lock);
 
@@ -1094,12 +1120,13 @@ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval,
 	struct inode *inode = ilookup5(sb, hashval, test, data);
 
 	if (!inode) {
-		struct inode *new = new_inode(sb);
+		struct inode *new = alloc_inode(sb);
 
 		if (new) {
+			new->i_state = 0;
 			inode = inode_insert5(new, hashval, test, set, data);
 			if (unlikely(inode != new))
-				iput(new);
+				destroy_inode(new);
 		}
 	}
 	return inode;
@@ -1128,6 +1155,8 @@ again:
 	inode = find_inode_fast(sb, head, ino);
 	spin_unlock(&inode_hash_lock);
 	if (inode) {
+		if (IS_ERR(inode))
+			return NULL;
 		wait_on_inode(inode);
 		if (unlikely(inode_unhashed(inode))) {
 			iput(inode);
@@ -1165,6 +1194,8 @@ again:
 		 */
 		spin_unlock(&inode_hash_lock);
 		destroy_inode(inode);
+		if (IS_ERR(old))
+			return NULL;
 		inode = old;
 		wait_on_inode(inode);
 		if (unlikely(inode_unhashed(inode))) {
@@ -1282,7 +1313,7 @@ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval,
 	inode = find_inode(sb, head, test, data);
 	spin_unlock(&inode_hash_lock);
 
-	return inode;
+	return IS_ERR(inode) ? NULL : inode;
 }
 EXPORT_SYMBOL(ilookup5_nowait);
 
@@ -1338,6 +1369,8 @@ again:
 	spin_unlock(&inode_hash_lock);
 
 	if (inode) {
+		if (IS_ERR(inode))
+			return NULL;
 		wait_on_inode(inode);
 		if (unlikely(inode_unhashed(inode))) {
 			iput(inode);
@@ -1421,12 +1454,17 @@ int insert_inode_locked(struct inode *inode)
 		}
 		if (likely(!old)) {
 			spin_lock(&inode->i_lock);
-			inode->i_state |= I_NEW;
+			inode->i_state |= I_NEW | I_CREATING;
 			hlist_add_head(&inode->i_hash, head);
 			spin_unlock(&inode->i_lock);
 			spin_unlock(&inode_hash_lock);
 			return 0;
 		}
+		if (unlikely(old->i_state & I_CREATING)) {
+			spin_unlock(&old->i_lock);
+			spin_unlock(&inode_hash_lock);
+			return -EBUSY;
+		}
 		__iget(old);
 		spin_unlock(&old->i_lock);
 		spin_unlock(&inode_hash_lock);
@@ -1443,7 +1481,10 @@ EXPORT_SYMBOL(insert_inode_locked);
 int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 		int (*test)(struct inode *, void *), void *data)
 {
-	struct inode *old = inode_insert5(inode, hashval, test, NULL, data);
+	struct inode *old;
+
+	inode->i_state |= I_CREATING;
+	old = inode_insert5(inode, hashval, test, NULL, data);
 
 	if (old != inode) {
 		iput(old);
@@ -1999,8 +2040,14 @@ void inode_init_owner(struct inode *inode, const struct inode *dir,
 	inode->i_uid = current_fsuid();
 	if (dir && dir->i_mode & S_ISGID) {
 		inode->i_gid = dir->i_gid;
+
+		/* Directories are special, and always inherit S_ISGID */
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
+		else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
+			 !in_group_p(inode->i_gid) &&
+			 !capable_wrt_inode_uidgid(dir, CAP_FSETID))
+			mode &= ~S_ISGID;
 	} else
 		inode->i_gid = current_fsgid();
 	inode->i_mode = mode;
diff --git a/fs/internal.h b/fs/internal.h
index 980d005b21b4..50a28fc71300 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -43,6 +43,8 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait)
 extern void guard_bio_eod(int rw, struct bio *bio);
 extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
 		get_block_t *get_block, struct iomap *iomap);
+int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
+		struct page *page);
 
 /*
  * char_dev.c
@@ -93,7 +95,7 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern struct file *get_empty_filp(void);
+extern struct file *alloc_empty_file(int, const struct cred *);
 
 /*
  * super.c
@@ -125,9 +127,7 @@ int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 
-extern int open_check_o_direct(struct file *f);
-extern int vfs_open(const struct path *, struct file *, const struct cred *);
-extern struct file *filp_clone_open(struct file *);
+extern int vfs_open(const struct path *, struct file *);
 
 /*
  * inode.c
diff --git a/fs/iomap.c b/fs/iomap.c
index 77397b5a96ef..009071e73bc0 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Red Hat, Inc.
- * Copyright (c) 2016 Christoph Hellwig.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -17,7 +17,9 @@
 #include <linux/iomap.h>
 #include <linux/uaccess.h>
 #include <linux/gfp.h>
+#include <linux/migrate.h>
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
@@ -103,6 +105,467 @@ iomap_sector(struct iomap *iomap, loff_t pos)
 	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
 }
 
+static struct iomap_page *
+iomap_page_create(struct inode *inode, struct page *page)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (iop || i_blocksize(inode) == PAGE_SIZE)
+		return iop;
+
+	iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL);
+	atomic_set(&iop->read_count, 0);
+	atomic_set(&iop->write_count, 0);
+	bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+	set_page_private(page, (unsigned long)iop);
+	SetPagePrivate(page);
+	return iop;
+}
+
+static void
+iomap_page_release(struct page *page)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (!iop)
+		return;
+	WARN_ON_ONCE(atomic_read(&iop->read_count));
+	WARN_ON_ONCE(atomic_read(&iop->write_count));
+	ClearPagePrivate(page);
+	set_page_private(page, 0);
+	kfree(iop);
+}
+
+/*
+ * Calculate the range inside the page that we actually need to read.
+ */
+static void
+iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
+		loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp)
+{
+	unsigned block_bits = inode->i_blkbits;
+	unsigned block_size = (1 << block_bits);
+	unsigned poff = offset_in_page(*pos);
+	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
+	unsigned first = poff >> block_bits;
+	unsigned last = (poff + plen - 1) >> block_bits;
+	unsigned end = offset_in_page(i_size_read(inode)) >> block_bits;
+
+	/*
+	 * If the block size is smaller than the page size we need to check the
+	 * per-block uptodate status and adjust the offset and length if needed
+	 * to avoid reading in already uptodate ranges.
+	 */
+	if (iop) {
+		unsigned int i;
+
+		/* move forward for each leading block marked uptodate */
+		for (i = first; i <= last; i++) {
+			if (!test_bit(i, iop->uptodate))
+				break;
+			*pos += block_size;
+			poff += block_size;
+			plen -= block_size;
+			first++;
+		}
+
+		/* truncate len if we find any trailing uptodate block(s) */
+		for ( ; i <= last; i++) {
+			if (test_bit(i, iop->uptodate)) {
+				plen -= (last - i + 1) * block_size;
+				last = i - 1;
+				break;
+			}
+		}
+	}
+
+	/*
+	 * If the extent spans the block that contains the i_size we need to
+	 * handle both halves separately so that we properly zero data in the
+	 * page cache for blocks that are entirely outside of i_size.
+	 */
+	if (first <= end && last > end)
+		plen -= (last - end) * block_size;
+
+	*offp = poff;
+	*lenp = plen;
+}
+
+static void
+iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+	struct inode *inode = page->mapping->host;
+	unsigned first = off >> inode->i_blkbits;
+	unsigned last = (off + len - 1) >> inode->i_blkbits;
+	unsigned int i;
+	bool uptodate = true;
+
+	if (iop) {
+		for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) {
+			if (i >= first && i <= last)
+				set_bit(i, iop->uptodate);
+			else if (!test_bit(i, iop->uptodate))
+				uptodate = false;
+		}
+	}
+
+	if (uptodate && !PageError(page))
+		SetPageUptodate(page);
+}
+
+static void
+iomap_read_finish(struct iomap_page *iop, struct page *page)
+{
+	if (!iop || atomic_dec_and_test(&iop->read_count))
+		unlock_page(page);
+}
+
+static void
+iomap_read_page_end_io(struct bio_vec *bvec, int error)
+{
+	struct page *page = bvec->bv_page;
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (unlikely(error)) {
+		ClearPageUptodate(page);
+		SetPageError(page);
+	} else {
+		iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len);
+	}
+
+	iomap_read_finish(iop, page);
+}
+
+static void
+iomap_read_inline_data(struct inode *inode, struct page *page,
+		struct iomap *iomap)
+{
+	size_t size = i_size_read(inode);
+	void *addr;
+
+	if (PageUptodate(page))
+		return;
+
+	BUG_ON(page->index);
+	BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data));
+
+	addr = kmap_atomic(page);
+	memcpy(addr, iomap->inline_data, size);
+	memset(addr + size, 0, PAGE_SIZE - size);
+	kunmap_atomic(addr);
+	SetPageUptodate(page);
+}
+
+static void
+iomap_read_end_io(struct bio *bio)
+{
+	int error = blk_status_to_errno(bio->bi_status);
+	struct bio_vec *bvec;
+	int i;
+
+	bio_for_each_segment_all(bvec, bio, i)
+		iomap_read_page_end_io(bvec, error);
+	bio_put(bio);
+}
+
+struct iomap_readpage_ctx {
+	struct page		*cur_page;
+	bool			cur_page_in_bio;
+	bool			is_readahead;
+	struct bio		*bio;
+	struct list_head	*pages;
+};
+
+static loff_t
+iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
+		struct iomap *iomap)
+{
+	struct iomap_readpage_ctx *ctx = data;
+	struct page *page = ctx->cur_page;
+	struct iomap_page *iop = iomap_page_create(inode, page);
+	bool is_contig = false;
+	loff_t orig_pos = pos;
+	unsigned poff, plen;
+	sector_t sector;
+
+	if (iomap->type == IOMAP_INLINE) {
+		WARN_ON_ONCE(poff);
+		iomap_read_inline_data(inode, page, iomap);
+		return PAGE_SIZE;
+	}
+
+	/* zero post-eof blocks as the page may be mapped */
+	iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen);
+	if (plen == 0)
+		goto done;
+
+	if (iomap->type != IOMAP_MAPPED || pos >= i_size_read(inode)) {
+		zero_user(page, poff, plen);
+		iomap_set_range_uptodate(page, poff, plen);
+		goto done;
+	}
+
+	ctx->cur_page_in_bio = true;
+
+	/*
+	 * Try to merge into a previous segment if we can.
+	 */
+	sector = iomap_sector(iomap, pos);
+	if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
+		if (__bio_try_merge_page(ctx->bio, page, plen, poff))
+			goto done;
+		is_contig = true;
+	}
+
+	/*
+	 * If we start a new segment we need to increase the read count, and we
+	 * need to do so before submitting any previous full bio to make sure
+	 * that we don't prematurely unlock the page.
+	 */
+	if (iop)
+		atomic_inc(&iop->read_count);
+
+	if (!ctx->bio || !is_contig || bio_full(ctx->bio)) {
+		gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
+		int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+		if (ctx->bio)
+			submit_bio(ctx->bio);
+
+		if (ctx->is_readahead) /* same as readahead_gfp_mask */
+			gfp |= __GFP_NORETRY | __GFP_NOWARN;
+		ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs));
+		ctx->bio->bi_opf = REQ_OP_READ;
+		if (ctx->is_readahead)
+			ctx->bio->bi_opf |= REQ_RAHEAD;
+		ctx->bio->bi_iter.bi_sector = sector;
+		bio_set_dev(ctx->bio, iomap->bdev);
+		ctx->bio->bi_end_io = iomap_read_end_io;
+	}
+
+	__bio_add_page(ctx->bio, page, plen, poff);
+done:
+	/*
+	 * Move the caller beyond our range so that it keeps making progress.
+	 * For that we have to include any leading non-uptodate ranges, but
+	 * we can skip trailing ones as they will be handled in the next
+	 * iteration.
+	 */
+	return pos - orig_pos + plen;
+}
+
+int
+iomap_readpage(struct page *page, const struct iomap_ops *ops)
+{
+	struct iomap_readpage_ctx ctx = { .cur_page = page };
+	struct inode *inode = page->mapping->host;
+	unsigned poff;
+	loff_t ret;
+
+	for (poff = 0; poff < PAGE_SIZE; poff += ret) {
+		ret = iomap_apply(inode, page_offset(page) + poff,
+				PAGE_SIZE - poff, 0, ops, &ctx,
+				iomap_readpage_actor);
+		if (ret <= 0) {
+			WARN_ON_ONCE(ret == 0);
+			SetPageError(page);
+			break;
+		}
+	}
+
+	if (ctx.bio) {
+		submit_bio(ctx.bio);
+		WARN_ON_ONCE(!ctx.cur_page_in_bio);
+	} else {
+		WARN_ON_ONCE(ctx.cur_page_in_bio);
+		unlock_page(page);
+	}
+
+	/*
+	 * Just like mpage_readpages and block_read_full_page we always
+	 * return 0 and just mark the page as PageError on errors.  This
+	 * should be cleaned up all through the stack eventually.
+	 */
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_readpage);
+
+static struct page *
+iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos,
+		loff_t length, loff_t *done)
+{
+	while (!list_empty(pages)) {
+		struct page *page = lru_to_page(pages);
+
+		if (page_offset(page) >= (u64)pos + length)
+			break;
+
+		list_del(&page->lru);
+		if (!add_to_page_cache_lru(page, inode->i_mapping, page->index,
+				GFP_NOFS))
+			return page;
+
+		/*
+		 * If we already have a page in the page cache at index we are
+		 * done.  Upper layers don't care if it is uptodate after the
+		 * readpages call itself as every page gets checked again once
+		 * actually needed.
+		 */
+		*done += PAGE_SIZE;
+		put_page(page);
+	}
+
+	return NULL;
+}
+
+static loff_t
+iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
+		void *data, struct iomap *iomap)
+{
+	struct iomap_readpage_ctx *ctx = data;
+	loff_t done, ret;
+
+	for (done = 0; done < length; done += ret) {
+		if (ctx->cur_page && offset_in_page(pos + done) == 0) {
+			if (!ctx->cur_page_in_bio)
+				unlock_page(ctx->cur_page);
+			put_page(ctx->cur_page);
+			ctx->cur_page = NULL;
+		}
+		if (!ctx->cur_page) {
+			ctx->cur_page = iomap_next_page(inode, ctx->pages,
+					pos, length, &done);
+			if (!ctx->cur_page)
+				break;
+			ctx->cur_page_in_bio = false;
+		}
+		ret = iomap_readpage_actor(inode, pos + done, length - done,
+				ctx, iomap);
+	}
+
+	return done;
+}
+
+int
+iomap_readpages(struct address_space *mapping, struct list_head *pages,
+		unsigned nr_pages, const struct iomap_ops *ops)
+{
+	struct iomap_readpage_ctx ctx = {
+		.pages		= pages,
+		.is_readahead	= true,
+	};
+	loff_t pos = page_offset(list_entry(pages->prev, struct page, lru));
+	loff_t last = page_offset(list_entry(pages->next, struct page, lru));
+	loff_t length = last - pos + PAGE_SIZE, ret = 0;
+
+	while (length > 0) {
+		ret = iomap_apply(mapping->host, pos, length, 0, ops,
+				&ctx, iomap_readpages_actor);
+		if (ret <= 0) {
+			WARN_ON_ONCE(ret == 0);
+			goto done;
+		}
+		pos += ret;
+		length -= ret;
+	}
+	ret = 0;
+done:
+	if (ctx.bio)
+		submit_bio(ctx.bio);
+	if (ctx.cur_page) {
+		if (!ctx.cur_page_in_bio)
+			unlock_page(ctx.cur_page);
+		put_page(ctx.cur_page);
+	}
+
+	/*
+	 * Check that we didn't lose a page due to the arcance calling
+	 * conventions..
+	 */
+	WARN_ON_ONCE(!ret && !list_empty(ctx.pages));
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iomap_readpages);
+
+int
+iomap_is_partially_uptodate(struct page *page, unsigned long from,
+		unsigned long count)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+	struct inode *inode = page->mapping->host;
+	unsigned first = from >> inode->i_blkbits;
+	unsigned last = (from + count - 1) >> inode->i_blkbits;
+	unsigned i;
+
+	if (iop) {
+		for (i = first; i <= last; i++)
+			if (!test_bit(i, iop->uptodate))
+				return 0;
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
+
+int
+iomap_releasepage(struct page *page, gfp_t gfp_mask)
+{
+	/*
+	 * mm accommodates an old ext3 case where clean pages might not have had
+	 * the dirty bit cleared. Thus, it can send actual dirty pages to
+	 * ->releasepage() via shrink_active_list(), skip those here.
+	 */
+	if (PageDirty(page) || PageWriteback(page))
+		return 0;
+	iomap_page_release(page);
+	return 1;
+}
+EXPORT_SYMBOL_GPL(iomap_releasepage);
+
+void
+iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len)
+{
+	/*
+	 * If we are invalidating the entire page, clear the dirty state from it
+	 * and release it to avoid unnecessary buildup of the LRU.
+	 */
+	if (offset == 0 && len == PAGE_SIZE) {
+		WARN_ON_ONCE(PageWriteback(page));
+		cancel_dirty_page(page);
+		iomap_page_release(page);
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_invalidatepage);
+
+#ifdef CONFIG_MIGRATION
+int
+iomap_migrate_page(struct address_space *mapping, struct page *newpage,
+		struct page *page, enum migrate_mode mode)
+{
+	int ret;
+
+	ret = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
+	if (ret != MIGRATEPAGE_SUCCESS)
+		return ret;
+
+	if (page_has_private(page)) {
+		ClearPagePrivate(page);
+		set_page_private(newpage, page_private(page));
+		set_page_private(page, 0);
+		SetPagePrivate(newpage);
+	}
+
+	if (mode != MIGRATE_SYNC_NO_COPY)
+		migrate_page_copy(newpage, page);
+	else
+		migrate_page_states(newpage, page);
+	return MIGRATEPAGE_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(iomap_migrate_page);
+#endif /* CONFIG_MIGRATION */
+
 static void
 iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 {
@@ -117,6 +580,61 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 }
 
 static int
+iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page,
+		unsigned poff, unsigned plen, unsigned from, unsigned to,
+		struct iomap *iomap)
+{
+	struct bio_vec bvec;
+	struct bio bio;
+
+	if (iomap->type != IOMAP_MAPPED || block_start >= i_size_read(inode)) {
+		zero_user_segments(page, poff, from, to, poff + plen);
+		iomap_set_range_uptodate(page, poff, plen);
+		return 0;
+	}
+
+	bio_init(&bio, &bvec, 1);
+	bio.bi_opf = REQ_OP_READ;
+	bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
+	bio_set_dev(&bio, iomap->bdev);
+	__bio_add_page(&bio, page, plen, poff);
+	return submit_bio_wait(&bio);
+}
+
+static int
+__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
+		struct page *page, struct iomap *iomap)
+{
+	struct iomap_page *iop = iomap_page_create(inode, page);
+	loff_t block_size = i_blocksize(inode);
+	loff_t block_start = pos & ~(block_size - 1);
+	loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
+	unsigned from = offset_in_page(pos), to = from + len, poff, plen;
+	int status = 0;
+
+	if (PageUptodate(page))
+		return 0;
+
+	do {
+		iomap_adjust_read_range(inode, iop, &block_start,
+				block_end - block_start, &poff, &plen);
+		if (plen == 0)
+			break;
+
+		if ((from > poff && from < poff + plen) ||
+		    (to > poff && to < poff + plen)) {
+			status = iomap_read_page_sync(inode, block_start, page,
+					poff, plen, from, to, iomap);
+			if (status)
+				break;
+		}
+
+	} while ((block_start += plen) < block_end);
+
+	return status;
+}
+
+static int
 iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, struct iomap *iomap)
 {
@@ -133,7 +651,12 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	if (!page)
 		return -ENOMEM;
 
-	status = __block_write_begin_int(page, pos, len, NULL, iomap);
+	if (iomap->type == IOMAP_INLINE)
+		iomap_read_inline_data(inode, page, iomap);
+	else if (iomap->flags & IOMAP_F_BUFFER_HEAD)
+		status = __block_write_begin_int(page, pos, len, NULL, iomap);
+	else
+		status = __iomap_write_begin(inode, pos, len, page, iomap);
 	if (unlikely(status)) {
 		unlock_page(page);
 		put_page(page);
@@ -146,14 +669,93 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	return status;
 }
 
+int
+iomap_set_page_dirty(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	int newly_dirty;
+
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	/*
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
+	 */
+	lock_page_memcg(page);
+	newly_dirty = !TestSetPageDirty(page);
+	if (newly_dirty)
+		__set_page_dirty(page, mapping, 0);
+	unlock_page_memcg(page);
+
+	if (newly_dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	return newly_dirty;
+}
+EXPORT_SYMBOL_GPL(iomap_set_page_dirty);
+
+static int
+__iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
+		unsigned copied, struct page *page, struct iomap *iomap)
+{
+	flush_dcache_page(page);
+
+	/*
+	 * The blocks that were entirely written will now be uptodate, so we
+	 * don't have to worry about a readpage reading them and overwriting a
+	 * partial write.  However if we have encountered a short write and only
+	 * partially written into a block, it will not be marked uptodate, so a
+	 * readpage might come in and destroy our partial write.
+	 *
+	 * Do the simplest thing, and just treat any short write to a non
+	 * uptodate page as a zero-length write, and force the caller to redo
+	 * the whole thing.
+	 */
+	if (unlikely(copied < len && !PageUptodate(page))) {
+		copied = 0;
+	} else {
+		iomap_set_range_uptodate(page, offset_in_page(pos), len);
+		iomap_set_page_dirty(page);
+	}
+	return __generic_write_end(inode, pos, copied, page);
+}
+
+static int
+iomap_write_end_inline(struct inode *inode, struct page *page,
+		struct iomap *iomap, loff_t pos, unsigned copied)
+{
+	void *addr;
+
+	WARN_ON_ONCE(!PageUptodate(page));
+	BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data));
+
+	addr = kmap_atomic(page);
+	memcpy(iomap->inline_data + pos, addr + pos, copied);
+	kunmap_atomic(addr);
+
+	mark_inode_dirty(inode);
+	__generic_write_end(inode, pos, copied, page);
+	return copied;
+}
+
 static int
 iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
-		unsigned copied, struct page *page)
+		unsigned copied, struct page *page, struct iomap *iomap)
 {
 	int ret;
 
-	ret = generic_write_end(NULL, inode->i_mapping, pos, len,
-			copied, page, NULL);
+	if (iomap->type == IOMAP_INLINE) {
+		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
+	} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
+		ret = generic_write_end(NULL, inode->i_mapping, pos, len,
+				copied, page, NULL);
+	} else {
+		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
+	}
+
+	if (iomap->page_done)
+		iomap->page_done(inode, pos, copied, page, iomap);
+
 	if (ret < len)
 		iomap_write_failed(inode, pos, len);
 	return ret;
@@ -174,7 +776,7 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		unsigned long bytes;	/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 
-		offset = (pos & (PAGE_SIZE - 1));
+		offset = offset_in_page(pos);
 		bytes = min_t(unsigned long, PAGE_SIZE - offset,
 						iov_iter_count(i));
 again:
@@ -208,7 +810,8 @@ again:
 
 		flush_dcache_page(page);
 
-		status = iomap_write_end(inode, pos, bytes, copied, page);
+		status = iomap_write_end(inode, pos, bytes, copied, page,
+				iomap);
 		if (unlikely(status < 0))
 			break;
 		copied = status;
@@ -287,7 +890,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		unsigned long offset;	/* Offset into pagecache page */
 		unsigned long bytes;	/* Bytes to write to page */
 
-		offset = (pos & (PAGE_SIZE - 1));
+		offset = offset_in_page(pos);
 		bytes = min_t(loff_t, PAGE_SIZE - offset, length);
 
 		rpage = __iomap_read_page(inode, pos);
@@ -302,7 +905,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 
 		WARN_ON_ONCE(!PageUptodate(page));
 
-		status = iomap_write_end(inode, pos, bytes, bytes, page);
+		status = iomap_write_end(inode, pos, bytes, bytes, page, iomap);
 		if (unlikely(status <= 0)) {
 			if (WARN_ON_ONCE(status == 0))
 				return -EIO;
@@ -354,7 +957,7 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 	zero_user(page, offset, bytes);
 	mark_page_accessed(page);
 
-	return iomap_write_end(inode, pos, bytes, bytes, page);
+	return iomap_write_end(inode, pos, bytes, bytes, page, iomap);
 }
 
 static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
@@ -379,7 +982,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 	do {
 		unsigned offset, bytes;
 
-		offset = pos & (PAGE_SIZE - 1); /* Within page */
+		offset = offset_in_page(pos);
 		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
 
 		if (IS_DAX(inode))
@@ -440,11 +1043,16 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct page *page = data;
 	int ret;
 
-	ret = __block_write_begin_int(page, pos, length, NULL, iomap);
-	if (ret)
-		return ret;
+	if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
+		ret = __block_write_begin_int(page, pos, length, NULL, iomap);
+		if (ret)
+			return ret;
+		block_commit_write(page, 0, length);
+	} else {
+		WARN_ON_ONCE(!PageUptodate(page));
+		iomap_page_create(inode, page);
+	}
 
-	block_commit_write(page, 0, length);
 	return length;
 }
 
@@ -467,7 +1075,7 @@ int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 
 	/* page is wholly or partially inside EOF */
 	if (((page->index + 1) << PAGE_SHIFT) > size)
-		length = size & ~PAGE_MASK;
+		length = offset_in_page(size);
 	else
 		length = PAGE_SIZE;
 
@@ -630,7 +1238,7 @@ page_seek_hole_data(struct inode *inode, struct page *page, loff_t *lastoff,
 		goto out_unlock_not_found;
 
 	for (off = 0; off < PAGE_SIZE; off += bsize) {
-		if ((*lastoff & ~PAGE_MASK) >= off + bsize)
+		if (offset_in_page(*lastoff) >= off + bsize)
 			continue;
 		if (ops->is_partially_uptodate(page, off, bsize) == seek_data) {
 			unlock_page(page);
@@ -811,6 +1419,7 @@ struct iomap_dio {
 	atomic_t		ref;
 	unsigned		flags;
 	int			error;
+	bool			wait_for_completion;
 
 	union {
 		/* used during submission and for synchronous completion: */
@@ -914,9 +1523,8 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 		iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status));
 
 	if (atomic_dec_and_test(&dio->ref)) {
-		if (is_sync_kiocb(dio->iocb)) {
+		if (dio->wait_for_completion) {
 			struct task_struct *waiter = dio->submit.waiter;
-
 			WRITE_ONCE(dio->submit.waiter, NULL);
 			wake_up_process(waiter);
 		} else if (dio->flags & IOMAP_DIO_WRITE) {
@@ -963,10 +1571,9 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 }
 
 static loff_t
-iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
-		void *data, struct iomap *iomap)
+iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
+		struct iomap_dio *dio, struct iomap *iomap)
 {
-	struct iomap_dio *dio = data;
 	unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
 	unsigned int fs_block_size = i_blocksize(inode), pad;
 	unsigned int align = iov_iter_alignment(dio->submit.iter);
@@ -980,41 +1587,27 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	if ((pos | length | align) & ((1 << blkbits) - 1))
 		return -EINVAL;
 
-	switch (iomap->type) {
-	case IOMAP_HOLE:
-		if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE))
-			return -EIO;
-		/*FALLTHRU*/
-	case IOMAP_UNWRITTEN:
-		if (!(dio->flags & IOMAP_DIO_WRITE)) {
-			length = iov_iter_zero(length, dio->submit.iter);
-			dio->size += length;
-			return length;
-		}
+	if (iomap->type == IOMAP_UNWRITTEN) {
 		dio->flags |= IOMAP_DIO_UNWRITTEN;
 		need_zeroout = true;
-		break;
-	case IOMAP_MAPPED:
-		if (iomap->flags & IOMAP_F_SHARED)
-			dio->flags |= IOMAP_DIO_COW;
-		if (iomap->flags & IOMAP_F_NEW) {
-			need_zeroout = true;
-		} else {
-			/*
-			 * Use a FUA write if we need datasync semantics, this
-			 * is a pure data IO that doesn't require any metadata
-			 * updates and the underlying device supports FUA. This
-			 * allows us to avoid cache flushes on IO completion.
-			 */
-			if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
-			    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
-			    blk_queue_fua(bdev_get_queue(iomap->bdev)))
-				use_fua = true;
-		}
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return -EIO;
+	}
+
+	if (iomap->flags & IOMAP_F_SHARED)
+		dio->flags |= IOMAP_DIO_COW;
+
+	if (iomap->flags & IOMAP_F_NEW) {
+		need_zeroout = true;
+	} else {
+		/*
+		 * Use a FUA write if we need datasync semantics, this
+		 * is a pure data IO that doesn't require any metadata
+		 * updates and the underlying device supports FUA. This
+		 * allows us to avoid cache flushes on IO completion.
+		 */
+		if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
+		    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
+		    blk_queue_fua(bdev_get_queue(iomap->bdev)))
+			use_fua = true;
 	}
 
 	/*
@@ -1093,6 +1686,66 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	return copied;
 }
 
+static loff_t
+iomap_dio_hole_actor(loff_t length, struct iomap_dio *dio)
+{
+	length = iov_iter_zero(length, dio->submit.iter);
+	dio->size += length;
+	return length;
+}
+
+static loff_t
+iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length,
+		struct iomap_dio *dio, struct iomap *iomap)
+{
+	struct iov_iter *iter = dio->submit.iter;
+	size_t copied;
+
+	BUG_ON(pos + length > PAGE_SIZE - offset_in_page(iomap->inline_data));
+
+	if (dio->flags & IOMAP_DIO_WRITE) {
+		loff_t size = inode->i_size;
+
+		if (pos > size)
+			memset(iomap->inline_data + size, 0, pos - size);
+		copied = copy_from_iter(iomap->inline_data + pos, length, iter);
+		if (copied) {
+			if (pos + copied > size)
+				i_size_write(inode, pos + copied);
+			mark_inode_dirty(inode);
+		}
+	} else {
+		copied = copy_to_iter(iomap->inline_data + pos, length, iter);
+	}
+	dio->size += copied;
+	return copied;
+}
+
+static loff_t
+iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
+		void *data, struct iomap *iomap)
+{
+	struct iomap_dio *dio = data;
+
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE))
+			return -EIO;
+		return iomap_dio_hole_actor(length, dio);
+	case IOMAP_UNWRITTEN:
+		if (!(dio->flags & IOMAP_DIO_WRITE))
+			return iomap_dio_hole_actor(length, dio);
+		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
+	case IOMAP_MAPPED:
+		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
+	case IOMAP_INLINE:
+		return iomap_dio_inline_actor(inode, pos, length, dio, iomap);
+	default:
+		WARN_ON_ONCE(1);
+		return -EIO;
+	}
+}
+
 /*
  * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO
  * is being issued as AIO or not.  This allows us to optimise pure data writes
@@ -1131,13 +1784,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->end_io = end_io;
 	dio->error = 0;
 	dio->flags = 0;
+	dio->wait_for_completion = is_sync_kiocb(iocb);
 
 	dio->submit.iter = iter;
-	if (is_sync_kiocb(iocb)) {
-		dio->submit.waiter = current;
-		dio->submit.cookie = BLK_QC_T_NONE;
-		dio->submit.last_queue = NULL;
-	}
+	dio->submit.waiter = current;
+	dio->submit.cookie = BLK_QC_T_NONE;
+	dio->submit.last_queue = NULL;
 
 	if (iov_iter_rw(iter) == READ) {
 		if (pos >= dio->i_size)
@@ -1187,7 +1839,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		dio_warn_stale_pagecache(iocb->ki_filp);
 	ret = 0;
 
-	if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
+	if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
 	    !inode->i_sb->s_dio_done_wq) {
 		ret = sb_init_dio_done_wq(inode->i_sb);
 		if (ret < 0)
@@ -1202,8 +1854,10 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 				iomap_dio_actor);
 		if (ret <= 0) {
 			/* magic error code to fall back to buffered I/O */
-			if (ret == -ENOTBLK)
+			if (ret == -ENOTBLK) {
+				dio->wait_for_completion = true;
 				ret = 0;
+			}
 			break;
 		}
 		pos += ret;
@@ -1224,7 +1878,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
 
 	if (!atomic_dec_and_test(&dio->ref)) {
-		if (!is_sync_kiocb(iocb))
+		if (!dio->wait_for_completion)
 			return -EIOCBQUEUED;
 
 		for (;;) {
@@ -1443,7 +2097,7 @@ iomap_bmap(struct address_space *mapping, sector_t bno,
 		const struct iomap_ops *ops)
 {
 	struct inode *inode = mapping->host;
-	loff_t pos = bno >> inode->i_blkbits;
+	loff_t pos = bno << inode->i_blkbits;
 	unsigned blocksize = i_blocksize(inode);
 
 	if (filemap_write_and_wait(mapping))
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8de0e7723316..150cc030b4d7 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -121,7 +121,7 @@ static int journal_submit_commit_record(journal_t *journal,
 	struct commit_header *tmp;
 	struct buffer_head *bh;
 	int ret;
-	struct timespec64 now = current_kernel_time64();
+	struct timespec64 now;
 
 	*cbh = NULL;
 
@@ -134,6 +134,7 @@ static int journal_submit_commit_record(journal_t *journal,
 		return 1;
 
 	tmp = (struct commit_header *)bh->b_data;
+	ktime_get_coarse_real_ts64(&now);
 	tmp->h_commit_sec = cpu_to_be64(now.tv_sec);
 	tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec);
 
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 51dd68e67b0f..c0b66a7a795b 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1361,6 +1361,13 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		if (jh->b_transaction == transaction &&
 		    jh->b_jlist != BJ_Metadata) {
 			jbd_lock_bh_state(bh);
+			if (jh->b_transaction == transaction &&
+			    jh->b_jlist != BJ_Metadata)
+				pr_err("JBD2: assertion failure: h_type=%u "
+				       "h_line_no=%u block_no=%llu jlist=%u\n",
+				       handle->h_type, handle->h_line_no,
+				       (unsigned long long) bh->b_blocknr,
+				       jh->b_jlist);
 			J_ASSERT_JH(jh, jh->b_transaction != transaction ||
 					jh->b_jlist == BJ_Metadata);
 			jbd_unlock_bh_state(bh);
@@ -1380,11 +1387,11 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		 * of the transaction. This needs to be done
 		 * once a transaction -bzzz
 		 */
-		jh->b_modified = 1;
 		if (handle->h_buffer_credits <= 0) {
 			ret = -ENOSPC;
 			goto out_unlock_bh;
 		}
+		jh->b_modified = 1;
 		handle->h_buffer_credits--;
 	}
 
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index b2944f9218f7..f20cff1194bb 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -201,7 +201,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
 	if (ret)
 		goto fail;
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(ri->ctime));
 
 	jffs2_free_raw_inode(ri);
 
@@ -227,14 +227,14 @@ static int jffs2_unlink(struct inode *dir_i, struct dentry *dentry)
 	struct jffs2_inode_info *dir_f = JFFS2_INODE_INFO(dir_i);
 	struct jffs2_inode_info *dead_f = JFFS2_INODE_INFO(d_inode(dentry));
 	int ret;
-	uint32_t now = get_seconds();
+	uint32_t now = JFFS2_NOW();
 
 	ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name,
 			      dentry->d_name.len, dead_f, now);
 	if (dead_f->inocache)
 		set_nlink(d_inode(dentry), dead_f->inocache->pino_nlink);
 	if (!ret)
-		dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
 	return ret;
 }
 /***********************************************************************/
@@ -260,7 +260,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de
 	type = (d_inode(old_dentry)->i_mode & S_IFMT) >> 12;
 	if (!type) type = DT_REG;
 
-	now = get_seconds();
+	now = JFFS2_NOW();
 	ret = jffs2_do_link(c, dir_f, f->inocache->ino, type, dentry->d_name.name, dentry->d_name.len, now);
 
 	if (!ret) {
@@ -268,7 +268,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de
 		set_nlink(d_inode(old_dentry), ++f->inocache->pino_nlink);
 		mutex_unlock(&f->sem);
 		d_instantiate(dentry, d_inode(old_dentry));
-		dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
 		ihold(d_inode(old_dentry));
 	}
 	return ret;
@@ -400,7 +400,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 	rd->pino = cpu_to_je32(dir_i->i_ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = cpu_to_je32(inode->i_ino);
-	rd->mctime = cpu_to_je32(get_seconds());
+	rd->mctime = cpu_to_je32(JFFS2_NOW());
 	rd->nsize = namelen;
 	rd->type = DT_LNK;
 	rd->node_crc = cpu_to_je32(crc32(0, rd, sizeof(*rd)-8));
@@ -418,7 +418,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 		goto fail;
 	}
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
 
 	jffs2_free_raw_dirent(rd);
 
@@ -543,7 +543,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	rd->pino = cpu_to_je32(dir_i->i_ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = cpu_to_je32(inode->i_ino);
-	rd->mctime = cpu_to_je32(get_seconds());
+	rd->mctime = cpu_to_je32(JFFS2_NOW());
 	rd->nsize = namelen;
 	rd->type = DT_DIR;
 	rd->node_crc = cpu_to_je32(crc32(0, rd, sizeof(*rd)-8));
@@ -561,7 +561,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
 		goto fail;
 	}
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
 	inc_nlink(dir_i);
 
 	jffs2_free_raw_dirent(rd);
@@ -588,7 +588,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(d_inode(dentry));
 	struct jffs2_full_dirent *fd;
 	int ret;
-	uint32_t now = get_seconds();
+	uint32_t now = JFFS2_NOW();
 
 	for (fd = f->dents ; fd; fd = fd->next) {
 		if (fd->ino)
@@ -598,7 +598,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
 	ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name,
 			      dentry->d_name.len, f, now);
 	if (!ret) {
-		dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
 		clear_nlink(d_inode(dentry));
 		drop_nlink(dir_i);
 	}
@@ -712,7 +712,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	rd->pino = cpu_to_je32(dir_i->i_ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = cpu_to_je32(inode->i_ino);
-	rd->mctime = cpu_to_je32(get_seconds());
+	rd->mctime = cpu_to_je32(JFFS2_NOW());
 	rd->nsize = namelen;
 
 	/* XXX: This is ugly. */
@@ -733,7 +733,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
 		goto fail;
 	}
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
 
 	jffs2_free_raw_dirent(rd);
 
@@ -797,7 +797,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 	type = (d_inode(old_dentry)->i_mode & S_IFMT) >> 12;
 	if (!type) type = DT_REG;
 
-	now = get_seconds();
+	now = JFFS2_NOW();
 	ret = jffs2_do_link(c, JFFS2_INODE_INFO(new_dir_i),
 			    d_inode(old_dentry)->i_ino, type,
 			    new_dentry->d_name.name, new_dentry->d_name.len, now);
@@ -853,14 +853,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 		 * caller won't do it on its own since we are returning an error.
 		 */
 		d_invalidate(new_dentry);
-		new_dir_i->i_mtime = new_dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
 		return ret;
 	}
 
 	if (d_is_dir(old_dentry))
 		drop_nlink(old_dir_i);
 
-	new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+	new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = ITIME(now);
 
 	return 0;
 }
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 481afd4c2e1a..7d8654a1472e 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -175,7 +175,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		ri.uid = cpu_to_je16(i_uid_read(inode));
 		ri.gid = cpu_to_je16(i_gid_read(inode));
 		ri.isize = cpu_to_je32(max((uint32_t)inode->i_size, pageofs));
-		ri.atime = ri.ctime = ri.mtime = cpu_to_je32(get_seconds());
+		ri.atime = ri.ctime = ri.mtime = cpu_to_je32(JFFS2_NOW());
 		ri.offset = cpu_to_je32(inode->i_size);
 		ri.dsize = cpu_to_je32(pageofs - inode->i_size);
 		ri.csize = cpu_to_je32(0);
@@ -283,7 +283,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	ri->uid = cpu_to_je16(i_uid_read(inode));
 	ri->gid = cpu_to_je16(i_gid_read(inode));
 	ri->isize = cpu_to_je32((uint32_t)inode->i_size);
-	ri->atime = ri->ctime = ri->mtime = cpu_to_je32(get_seconds());
+	ri->atime = ri->ctime = ri->mtime = cpu_to_je32(JFFS2_NOW());
 
 	/* In 2.4, it was already kmapped by generic_file_write(). Doesn't
 	   hurt to do it again. The alternative is ifdefs, which are ugly. */
@@ -308,7 +308,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 			inode->i_size = pos + writtenlen;
 			inode->i_blocks = (inode->i_size + 511) >> 9;
 
-			inode->i_ctime = inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
+			inode->i_ctime = inode->i_mtime = ITIME(je32_to_cpu(ri->ctime));
 		}
 	}
 
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 0ecfb8ea38cd..eab04eca95a3 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -146,9 +146,9 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr)
 		return PTR_ERR(new_metadata);
 	}
 	/* It worked. Update the inode */
-	inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->atime)));
-	inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
-	inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->mtime)));
+	inode->i_atime = ITIME(je32_to_cpu(ri->atime));
+	inode->i_ctime = ITIME(je32_to_cpu(ri->ctime));
+	inode->i_mtime = ITIME(je32_to_cpu(ri->mtime));
 	inode->i_mode = jemode_to_cpu(ri->mode);
 	i_uid_write(inode, je16_to_cpu(ri->uid));
 	i_gid_write(inode, je16_to_cpu(ri->gid));
@@ -280,9 +280,9 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino)
 	i_uid_write(inode, je16_to_cpu(latest_node.uid));
 	i_gid_write(inode, je16_to_cpu(latest_node.gid));
 	inode->i_size = je32_to_cpu(latest_node.isize);
-	inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.atime)));
-	inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.mtime)));
-	inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.ctime)));
+	inode->i_atime = ITIME(je32_to_cpu(latest_node.atime));
+	inode->i_mtime = ITIME(je32_to_cpu(latest_node.mtime));
+	inode->i_ctime = ITIME(je32_to_cpu(latest_node.ctime));
 
 	set_nlink(inode, f->inocache->pino_nlink);
 
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index c2fbec19c616..a2dbbb3f4c74 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -31,12 +31,13 @@ struct kvec;
 #define JFFS2_F_I_GID(f) (i_gid_read(OFNI_EDONI_2SFFJ(f)))
 #define JFFS2_F_I_RDEV(f) (OFNI_EDONI_2SFFJ(f)->i_rdev)
 
-#define ITIME(sec) ((struct timespec){sec, 0})
-#define I_SEC(tv) ((tv).tv_sec)
-#define JFFS2_F_I_CTIME(f) (OFNI_EDONI_2SFFJ(f)->i_ctime.tv_sec)
-#define JFFS2_F_I_MTIME(f) (OFNI_EDONI_2SFFJ(f)->i_mtime.tv_sec)
-#define JFFS2_F_I_ATIME(f) (OFNI_EDONI_2SFFJ(f)->i_atime.tv_sec)
-
+#define JFFS2_CLAMP_TIME(t) ((uint32_t)clamp_t(time64_t, (t), 0, U32_MAX))
+#define ITIME(sec) ((struct timespec64){sec, 0})
+#define JFFS2_NOW() JFFS2_CLAMP_TIME(ktime_get_real_seconds())
+#define I_SEC(tv) JFFS2_CLAMP_TIME((tv).tv_sec)
+#define JFFS2_F_I_CTIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_ctime)
+#define JFFS2_F_I_MTIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_mtime)
+#define JFFS2_F_I_ATIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_atime)
 #define sleep_on_spinunlock(wq, s)				\
 	do {							\
 		DECLARE_WAITQUEUE(__wait, current);		\
diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h
index 395c4c0d0f06..1682a87c00b2 100644
--- a/fs/jfs/jfs_dinode.h
+++ b/fs/jfs/jfs_dinode.h
@@ -115,6 +115,13 @@ struct dinode {
 					dxd_t _dxd;	/* 16: */
 					union {
 						__le32 _rdev;	/* 4: */
+						/*
+						 * The fast symlink area
+						 * is expected to overflow
+						 * into _inlineea when
+						 * needed (which will clear
+						 * INLINEEA).
+						 */
 						u8 _fastsymlink[128];
 					} _u;
 					u8 _inlineea[128];
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index f36ef68905a7..93e8c590ff5c 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -491,13 +491,7 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary)
 	/* release the page */
 	release_metapage(mp);
 
-	/*
-	 * __mark_inode_dirty expects inodes to be hashed.  Since we don't
-	 * want special inodes in the fileset inode space, we make them
-	 * appear hashed, but do not put on any lists.  hlist_del()
-	 * will work fine and require no locking.
-	 */
-	hlist_add_fake(&ip->i_hash);
+	inode_fake_hash(ip);
 
 	return (ip);
 }
diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h
index 1f26d1910409..9940a1e04cbf 100644
--- a/fs/jfs/jfs_incore.h
+++ b/fs/jfs/jfs_incore.h
@@ -87,6 +87,7 @@ struct jfs_inode_info {
 		struct {
 			unchar _unused[16];	/* 16: */
 			dxd_t _dxd;		/* 16: */
+			/* _inline may overflow into _inline_ea when needed */
 			unchar _inline[128];	/* 128: inline symlink */
 			/* _inline_ea may overlay the last part of
 			 * file._xtroot if maxentry = XTROOTINITSLOT
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index 5e9b7bb3aabf..4572b7cf183d 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -61,8 +61,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
 	inode = new_inode(sb);
 	if (!inode) {
 		jfs_warn("ialloc: new_inode returned NULL!");
-		rc = -ENOMEM;
-		goto fail;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	jfs_inode = JFS_IP(inode);
@@ -70,8 +69,6 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
 	rc = diAlloc(parent, S_ISDIR(mode), inode);
 	if (rc) {
 		jfs_warn("ialloc: diAlloc returned %d!", rc);
-		if (rc == -EIO)
-			make_bad_inode(inode);
 		goto fail_put;
 	}
 
@@ -141,9 +138,10 @@ fail_drop:
 	dquot_drop(inode);
 	inode->i_flags |= S_NOQUOTA;
 	clear_nlink(inode);
-	unlock_new_inode(inode);
+	discard_new_inode(inode);
+	return ERR_PTR(rc);
+
 fail_put:
 	iput(inode);
-fail:
 	return ERR_PTR(rc);
 }
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 56c3fcbfe80e..14528c0ffe63 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -175,8 +175,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
@@ -309,8 +308,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
@@ -1054,8 +1052,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
@@ -1441,8 +1438,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 1b9264fd54b6..09da5cf14e27 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -581,7 +581,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 	inode->i_ino = 0;
 	inode->i_size = i_size_read(sb->s_bdev->bd_inode);
 	inode->i_mapping->a_ops = &jfs_metapage_aops;
-	hlist_add_fake(&inode->i_hash);
+	inode_fake_hash(inode);
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 
 	sbi->direct_inode = inode;
@@ -967,8 +967,7 @@ static int __init init_jfs_fs(void)
 	jfs_inode_cachep =
 	    kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info),
 			0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
-			offsetof(struct jfs_inode_info, i_inline),
-			sizeof_field(struct jfs_inode_info, i_inline),
+			offsetof(struct jfs_inode_info, i_inline), IDATASIZE,
 			init_once);
 	if (jfs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/locks.c b/fs/locks.c
index db7b6917d9c5..bc047a7edc47 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -202,10 +202,6 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);
  * we often hold the flc_lock as well. In certain cases, when reading the fields
  * protected by this lock, we can skip acquiring it iff we already hold the
  * flc_lock.
- *
- * In particular, adding an entry to the fl_block list requires that you hold
- * both the flc_lock and the blocked_lock_lock (acquired in that order).
- * Deleting an entry from the list however only requires the file_lock_lock.
  */
 static DEFINE_SPINLOCK(blocked_lock_lock);
 
@@ -990,6 +986,7 @@ out:
 	if (new_fl)
 		locks_free_lock(new_fl);
 	locks_dispose_list(&dispose);
+	trace_flock_lock_inode(inode, request, error);
 	return error;
 }
 
@@ -2072,6 +2069,13 @@ static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns)
 		return -1;
 	if (IS_REMOTELCK(fl))
 		return fl->fl_pid;
+	/*
+	 * If the flock owner process is dead and its pid has been already
+	 * freed, the translation below won't work, but we still want to show
+	 * flock owner pid number in init pidns.
+	 */
+	if (ns == &init_pid_ns)
+		return (pid_t)fl->fl_pid;
 
 	rcu_read_lock();
 	pid = find_pid_ns(fl->fl_pid, &init_pid_ns);
@@ -2626,12 +2630,10 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 
 	fl_pid = locks_translate_pid(fl, proc_pidns);
 	/*
-	 * If there isn't a fl_pid don't display who is waiting on
-	 * the lock if we are called from locks_show, or if we are
-	 * called from __show_fd_info - skip lock entirely
+	 * If lock owner is dead (and pid is freed) or not visible in current
+	 * pidns, zero is shown as a pid value. Check lock info from
+	 * init_pid_ns to get saved lock pid value.
 	 */
-	if (fl_pid == 0)
-		return;
 
 	if (fl->fl_file != NULL)
 		inode = locks_inode(fl->fl_file);
diff --git a/fs/mpage.c b/fs/mpage.c
index b7e7f570733a..b73638db9866 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -51,8 +51,8 @@ static void mpage_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-		page_endio(page, op_is_write(bio_op(bio)),
-				blk_status_to_errno(bio->bi_status));
+		page_endio(page, bio_op(bio),
+			   blk_status_to_errno(bio->bi_status));
 	}
 
 	bio_put(bio);
diff --git a/fs/namei.c b/fs/namei.c
index 734cef54fdf8..3cd396277cd3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2028,6 +2028,8 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 {
 	int err;
 
+	if (IS_ERR(name))
+		return PTR_ERR(name);
 	while (*name=='/')
 		name++;
 	if (!*name)
@@ -2125,12 +2127,15 @@ OK:
 	}
 }
 
+/* must be paired with terminate_walk() */
 static const char *path_init(struct nameidata *nd, unsigned flags)
 {
 	const char *s = nd->name->name;
 
 	if (!*s)
 		flags &= ~LOOKUP_RCU;
+	if (flags & LOOKUP_RCU)
+		rcu_read_lock();
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
@@ -2143,7 +2148,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
-			rcu_read_lock();
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			nd->root_seq = nd->seq;
 			nd->m_seq = read_seqbegin(&mount_lock);
@@ -2159,21 +2163,15 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 
 	nd->m_seq = read_seqbegin(&mount_lock);
 	if (*s == '/') {
-		if (flags & LOOKUP_RCU)
-			rcu_read_lock();
 		set_root(nd);
 		if (likely(!nd_jump_root(nd)))
 			return s;
-		nd->root.mnt = NULL;
-		rcu_read_unlock();
 		return ERR_PTR(-ECHILD);
 	} else if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
 			unsigned seq;
 
-			rcu_read_lock();
-
 			do {
 				seq = read_seqcount_begin(&fs->seq);
 				nd->path = fs->pwd;
@@ -2195,16 +2193,13 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 
 		dentry = f.file->f_path.dentry;
 
-		if (*s) {
-			if (!d_can_lookup(dentry)) {
-				fdput(f);
-				return ERR_PTR(-ENOTDIR);
-			}
+		if (*s && unlikely(!d_can_lookup(dentry))) {
+			fdput(f);
+			return ERR_PTR(-ENOTDIR);
 		}
 
 		nd->path = f.file->f_path;
 		if (flags & LOOKUP_RCU) {
-			rcu_read_lock();
 			nd->inode = nd->path.dentry->d_inode;
 			nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 		} else {
@@ -2272,24 +2267,15 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	const char *s = path_init(nd, flags);
 	int err;
 
-	if (IS_ERR(s))
-		return PTR_ERR(s);
-
-	if (unlikely(flags & LOOKUP_DOWN)) {
+	if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
 		err = handle_lookup_down(nd);
-		if (unlikely(err < 0)) {
-			terminate_walk(nd);
-			return err;
-		}
+		if (unlikely(err < 0))
+			s = ERR_PTR(err);
 	}
 
 	while (!(err = link_path_walk(s, nd))
 		&& ((err = lookup_last(nd)) > 0)) {
 		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			err = PTR_ERR(s);
-			break;
-		}
 	}
 	if (!err)
 		err = complete_walk(nd);
@@ -2336,10 +2322,7 @@ static int path_parentat(struct nameidata *nd, unsigned flags,
 				struct path *parent)
 {
 	const char *s = path_init(nd, flags);
-	int err;
-	if (IS_ERR(s))
-		return PTR_ERR(s);
-	err = link_path_walk(s, nd);
+	int err = link_path_walk(s, nd);
 	if (!err)
 		err = complete_walk(nd);
 	if (!err) {
@@ -2666,15 +2649,10 @@ path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
 {
 	const char *s = path_init(nd, flags);
 	int err;
-	if (IS_ERR(s))
-		return PTR_ERR(s);
+
 	while (!(err = link_path_walk(s, nd)) &&
 		(err = mountpoint_last(nd)) > 0) {
 		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			err = PTR_ERR(s);
-			break;
-		}
 	}
 	if (!err) {
 		*path = nd->path;
@@ -3027,17 +3005,16 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m
  * Returns 0 if successful.  The file will have been created and attached to
  * @file by the filesystem calling finish_open().
  *
- * Returns 1 if the file was looked up only or didn't need creating.  The
- * caller will need to perform the open themselves.  @path will have been
- * updated to point to the new dentry.  This may be negative.
+ * If the file was looked up only or didn't need creating, FMODE_OPENED won't
+ * be set.  The caller will need to perform the open themselves.  @path will
+ * have been updated to point to the new dentry.  This may be negative.
  *
  * Returns an error code otherwise.
  */
 static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 			struct path *path, struct file *file,
 			const struct open_flags *op,
-			int open_flag, umode_t mode,
-			int *opened)
+			int open_flag, umode_t mode)
 {
 	struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
 	struct inode *dir =  nd->path.dentry->d_inode;
@@ -3052,39 +3029,38 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 	file->f_path.dentry = DENTRY_NOT_SET;
 	file->f_path.mnt = nd->path.mnt;
 	error = dir->i_op->atomic_open(dir, dentry, file,
-				       open_to_namei_flags(open_flag),
-				       mode, opened);
+				       open_to_namei_flags(open_flag), mode);
 	d_lookup_done(dentry);
 	if (!error) {
-		/*
-		 * We didn't have the inode before the open, so check open
-		 * permission here.
-		 */
-		int acc_mode = op->acc_mode;
-		if (*opened & FILE_CREATED) {
-			WARN_ON(!(open_flag & O_CREAT));
-			fsnotify_create(dir, dentry);
-			acc_mode = 0;
-		}
-		error = may_open(&file->f_path, acc_mode, open_flag);
-		if (WARN_ON(error > 0))
-			error = -EINVAL;
-	} else if (error > 0) {
-		if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
+		if (file->f_mode & FMODE_OPENED) {
+			/*
+			 * We didn't have the inode before the open, so check open
+			 * permission here.
+			 */
+			int acc_mode = op->acc_mode;
+			if (file->f_mode & FMODE_CREATED) {
+				WARN_ON(!(open_flag & O_CREAT));
+				fsnotify_create(dir, dentry);
+				acc_mode = 0;
+			}
+			error = may_open(&file->f_path, acc_mode, open_flag);
+			if (WARN_ON(error > 0))
+				error = -EINVAL;
+		} else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
 			error = -EIO;
 		} else {
 			if (file->f_path.dentry) {
 				dput(dentry);
 				dentry = file->f_path.dentry;
 			}
-			if (*opened & FILE_CREATED)
+			if (file->f_mode & FMODE_CREATED)
 				fsnotify_create(dir, dentry);
 			if (unlikely(d_is_negative(dentry))) {
 				error = -ENOENT;
 			} else {
 				path->dentry = dentry;
 				path->mnt = nd->path.mnt;
-				return 1;
+				return 0;
 			}
 		}
 	}
@@ -3095,25 +3071,22 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 /*
  * Look up and maybe create and open the last component.
  *
- * Must be called with i_mutex held on parent.
- *
- * Returns 0 if the file was successfully atomically created (if necessary) and
- * opened.  In this case the file will be returned attached to @file.
- *
- * Returns 1 if the file was not completely opened at this time, though lookups
- * and creations will have been performed and the dentry returned in @path will
- * be positive upon return if O_CREAT was specified.  If O_CREAT wasn't
- * specified then a negative dentry may be returned.
+ * Must be called with parent locked (exclusive in O_CREAT case).
  *
- * An error code is returned otherwise.
+ * Returns 0 on success, that is, if
+ *  the file was successfully atomically created (if necessary) and opened, or
+ *  the file was not completely opened at this time, though lookups and
+ *  creations were performed.
+ * These case are distinguished by presence of FMODE_OPENED on file->f_mode.
+ * In the latter case dentry returned in @path might be negative if O_CREAT
+ * hadn't been specified.
  *
- * FILE_CREATE will be set in @*opened if the dentry was created and will be
- * cleared otherwise prior to returning.
+ * An error code is returned on failure.
  */
 static int lookup_open(struct nameidata *nd, struct path *path,
 			struct file *file,
 			const struct open_flags *op,
-			bool got_write, int *opened)
+			bool got_write)
 {
 	struct dentry *dir = nd->path.dentry;
 	struct inode *dir_inode = dir->d_inode;
@@ -3126,7 +3099,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 	if (unlikely(IS_DEADDIR(dir_inode)))
 		return -ENOENT;
 
-	*opened &= ~FILE_CREATED;
+	file->f_mode &= ~FMODE_CREATED;
 	dentry = d_lookup(dir, &nd->last);
 	for (;;) {
 		if (!dentry) {
@@ -3188,7 +3161,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 
 	if (dir_inode->i_op->atomic_open) {
 		error = atomic_open(nd, dentry, path, file, op, open_flag,
-				    mode, opened);
+				    mode);
 		if (unlikely(error == -ENOENT) && create_error)
 			error = create_error;
 		return error;
@@ -3211,7 +3184,7 @@ no_open:
 
 	/* Negative dentry, just create the file */
 	if (!dentry->d_inode && (open_flag & O_CREAT)) {
-		*opened |= FILE_CREATED;
+		file->f_mode |= FMODE_CREATED;
 		audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
 		if (!dir_inode->i_op->create) {
 			error = -EACCES;
@@ -3230,7 +3203,7 @@ no_open:
 out_no_open:
 	path->dentry = dentry;
 	path->mnt = nd->path.mnt;
-	return 1;
+	return 0;
 
 out_dput:
 	dput(dentry);
@@ -3241,8 +3214,7 @@ out_dput:
  * Handle the last step of open()
  */
 static int do_last(struct nameidata *nd,
-		   struct file *file, const struct open_flags *op,
-		   int *opened)
+		   struct file *file, const struct open_flags *op)
 {
 	struct dentry *dir = nd->path.dentry;
 	int open_flag = op->open_flag;
@@ -3308,17 +3280,17 @@ static int do_last(struct nameidata *nd,
 		inode_lock(dir->d_inode);
 	else
 		inode_lock_shared(dir->d_inode);
-	error = lookup_open(nd, &path, file, op, got_write, opened);
+	error = lookup_open(nd, &path, file, op, got_write);
 	if (open_flag & O_CREAT)
 		inode_unlock(dir->d_inode);
 	else
 		inode_unlock_shared(dir->d_inode);
 
-	if (error <= 0) {
-		if (error)
-			goto out;
+	if (error)
+		goto out;
 
-		if ((*opened & FILE_CREATED) ||
+	if (file->f_mode & FMODE_OPENED) {
+		if ((file->f_mode & FMODE_CREATED) ||
 		    !S_ISREG(file_inode(file)->i_mode))
 			will_truncate = false;
 
@@ -3326,7 +3298,7 @@ static int do_last(struct nameidata *nd,
 		goto opened;
 	}
 
-	if (*opened & FILE_CREATED) {
+	if (file->f_mode & FMODE_CREATED) {
 		/* Don't check for write permission, don't truncate */
 		open_flag &= ~O_TRUNC;
 		will_truncate = false;
@@ -3395,20 +3367,15 @@ finish_open_created:
 	error = may_open(&nd->path, acc_mode, open_flag);
 	if (error)
 		goto out;
-	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
-	error = vfs_open(&nd->path, file, current_cred());
+	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
+	error = vfs_open(&nd->path, file);
 	if (error)
 		goto out;
-	*opened |= FILE_OPENED;
 opened:
-	error = open_check_o_direct(file);
-	if (!error)
-		error = ima_file_check(file, op->acc_mode, *opened);
+	error = ima_file_check(file, op->acc_mode);
 	if (!error && will_truncate)
 		error = handle_truncate(file);
 out:
-	if (unlikely(error) && (*opened & FILE_OPENED))
-		fput(file);
 	if (unlikely(error > 0)) {
 		WARN_ON(1);
 		error = -EINVAL;
@@ -3458,7 +3425,7 @@ EXPORT_SYMBOL(vfs_tmpfile);
 
 static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		const struct open_flags *op,
-		struct file *file, int *opened)
+		struct file *file)
 {
 	struct dentry *child;
 	struct path path;
@@ -3480,12 +3447,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	if (error)
 		goto out2;
 	file->f_path.mnt = path.mnt;
-	error = finish_open(file, child, NULL, opened);
-	if (error)
-		goto out2;
-	error = open_check_o_direct(file);
-	if (error)
-		fput(file);
+	error = finish_open(file, child, NULL);
 out2:
 	mnt_drop_write(path.mnt);
 out:
@@ -3499,7 +3461,7 @@ static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
 	int error = path_lookupat(nd, flags, &path);
 	if (!error) {
 		audit_inode(nd->name, path.dentry, 0);
-		error = vfs_open(&path, file, current_cred());
+		error = vfs_open(&path, file);
 		path_put(&path);
 	}
 	return error;
@@ -3508,59 +3470,40 @@ static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
 static struct file *path_openat(struct nameidata *nd,
 			const struct open_flags *op, unsigned flags)
 {
-	const char *s;
 	struct file *file;
-	int opened = 0;
 	int error;
 
-	file = get_empty_filp();
+	file = alloc_empty_file(op->open_flag, current_cred());
 	if (IS_ERR(file))
 		return file;
 
-	file->f_flags = op->open_flag;
-
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
-		error = do_tmpfile(nd, flags, op, file, &opened);
-		goto out2;
-	}
-
-	if (unlikely(file->f_flags & O_PATH)) {
+		error = do_tmpfile(nd, flags, op, file);
+	} else if (unlikely(file->f_flags & O_PATH)) {
 		error = do_o_path(nd, flags, file);
-		if (!error)
-			opened |= FILE_OPENED;
-		goto out2;
-	}
-
-	s = path_init(nd, flags);
-	if (IS_ERR(s)) {
-		put_filp(file);
-		return ERR_CAST(s);
-	}
-	while (!(error = link_path_walk(s, nd)) &&
-		(error = do_last(nd, file, op, &opened)) > 0) {
-		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
-		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			error = PTR_ERR(s);
-			break;
+	} else {
+		const char *s = path_init(nd, flags);
+		while (!(error = link_path_walk(s, nd)) &&
+			(error = do_last(nd, file, op)) > 0) {
+			nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
+			s = trailing_symlink(nd);
 		}
+		terminate_walk(nd);
 	}
-	terminate_walk(nd);
-out2:
-	if (!(opened & FILE_OPENED)) {
-		BUG_ON(!error);
-		put_filp(file);
+	if (likely(!error)) {
+		if (likely(file->f_mode & FMODE_OPENED))
+			return file;
+		WARN_ON(1);
+		error = -EINVAL;
 	}
-	if (unlikely(error)) {
-		if (error == -EOPENSTALE) {
-			if (flags & LOOKUP_RCU)
-				error = -ECHILD;
-			else
-				error = -ESTALE;
-		}
-		file = ERR_PTR(error);
+	fput(file);
+	if (error == -EOPENSTALE) {
+		if (flags & LOOKUP_RCU)
+			error = -ECHILD;
+		else
+			error = -ESTALE;
 	}
-	return file;
+	return ERR_PTR(error);
 }
 
 struct file *do_filp_open(int dfd, struct filename *pathname,
@@ -4712,29 +4655,6 @@ out:
 	return len;
 }
 
-/*
- * A helper for ->readlink().  This should be used *ONLY* for symlinks that
- * have ->get_link() not calling nd_jump_link().  Using (or not using) it
- * for any given inode is up to filesystem.
- */
-static int generic_readlink(struct dentry *dentry, char __user *buffer,
-			    int buflen)
-{
-	DEFINE_DELAYED_CALL(done);
-	struct inode *inode = d_inode(dentry);
-	const char *link = inode->i_link;
-	int res;
-
-	if (!link) {
-		link = inode->i_op->get_link(dentry, inode, &done);
-		if (IS_ERR(link))
-			return PTR_ERR(link);
-	}
-	res = readlink_copy(buffer, buflen, link);
-	do_delayed_call(&done);
-	return res;
-}
-
 /**
  * vfs_readlink - copy symlink body into userspace buffer
  * @dentry: dentry on which to get symbolic link
@@ -4748,6 +4668,9 @@ static int generic_readlink(struct dentry *dentry, char __user *buffer,
 int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
 	struct inode *inode = d_inode(dentry);
+	DEFINE_DELAYED_CALL(done);
+	const char *link;
+	int res;
 
 	if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) {
 		if (unlikely(inode->i_op->readlink))
@@ -4761,7 +4684,15 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 		spin_unlock(&inode->i_lock);
 	}
 
-	return generic_readlink(dentry, buffer, buflen);
+	link = inode->i_link;
+	if (!link) {
+		link = inode->i_op->get_link(dentry, inode, &done);
+		if (IS_ERR(link))
+			return PTR_ERR(link);
+	}
+	res = readlink_copy(buffer, buflen, link);
+	do_delayed_call(&done);
+	return res;
 }
 EXPORT_SYMBOL(vfs_readlink);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 8ddd14806799..bd2f4c68506a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -659,12 +659,21 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
 		return 0;
 	mnt = real_mount(bastard);
 	mnt_add_count(mnt, 1);
+	smp_mb();			// see mntput_no_expire()
 	if (likely(!read_seqretry(&mount_lock, seq)))
 		return 0;
 	if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
 		mnt_add_count(mnt, -1);
 		return 1;
 	}
+	lock_mount_hash();
+	if (unlikely(bastard->mnt_flags & MNT_DOOMED)) {
+		mnt_add_count(mnt, -1);
+		unlock_mount_hash();
+		return 1;
+	}
+	unlock_mount_hash();
+	/* caller will mntput() */
 	return -1;
 }
 
@@ -1195,12 +1204,27 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
 static void mntput_no_expire(struct mount *mnt)
 {
 	rcu_read_lock();
-	mnt_add_count(mnt, -1);
-	if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */
+	if (likely(READ_ONCE(mnt->mnt_ns))) {
+		/*
+		 * Since we don't do lock_mount_hash() here,
+		 * ->mnt_ns can change under us.  However, if it's
+		 * non-NULL, then there's a reference that won't
+		 * be dropped until after an RCU delay done after
+		 * turning ->mnt_ns NULL.  So if we observe it
+		 * non-NULL under rcu_read_lock(), the reference
+		 * we are dropping is not the final one.
+		 */
+		mnt_add_count(mnt, -1);
 		rcu_read_unlock();
 		return;
 	}
 	lock_mount_hash();
+	/*
+	 * make sure that if __legitimize_mnt() has not seen us grab
+	 * mount_lock, we'll see their refcount increment here.
+	 */
+	smp_mb();
+	mnt_add_count(mnt, -1);
 	if (mnt_get_count(mnt)) {
 		rcu_read_unlock();
 		unlock_mount_hash();
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 7a9c14426855..d7f158c3efc8 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1434,12 +1434,11 @@ static int do_open(struct inode *inode, struct file *filp)
 
 static int nfs_finish_open(struct nfs_open_context *ctx,
 			   struct dentry *dentry,
-			   struct file *file, unsigned open_flags,
-			   int *opened)
+			   struct file *file, unsigned open_flags)
 {
 	int err;
 
-	err = finish_open(file, dentry, do_open, opened);
+	err = finish_open(file, dentry, do_open);
 	if (err)
 		goto out;
 	if (S_ISREG(file->f_path.dentry->d_inode->i_mode))
@@ -1452,7 +1451,7 @@ out:
 
 int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		    struct file *file, unsigned open_flags,
-		    umode_t mode, int *opened)
+		    umode_t mode)
 {
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
 	struct nfs_open_context *ctx;
@@ -1461,6 +1460,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	unsigned int lookup_flags = 0;
 	bool switched = false;
+	int created = 0;
 	int err;
 
 	/* Expect a negative dentry */
@@ -1521,7 +1521,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		goto out;
 
 	trace_nfs_atomic_open_enter(dir, ctx, open_flags);
-	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened);
+	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, &created);
+	if (created)
+		file->f_mode |= FMODE_CREATED;
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
@@ -1546,7 +1548,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
-	err = nfs_finish_open(ctx, ctx->dentry, file, open_flags, opened);
+	err = nfs_finish_open(ctx, ctx->dentry, file, open_flags);
 	trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
 	put_nfs_open_context(ctx);
 out:
@@ -1641,6 +1643,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
 	struct dentry *parent = dget_parent(dentry);
 	struct inode *dir = d_inode(parent);
 	struct inode *inode;
+	struct dentry *d;
 	int error = -EACCES;
 
 	d_drop(dentry);
@@ -1662,10 +1665,12 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
 			goto out_error;
 	}
 	inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label);
-	error = PTR_ERR(inode);
-	if (IS_ERR(inode))
+	d = d_splice_alias(inode, dentry);
+	if (IS_ERR(d)) {
+		error = PTR_ERR(d);
 		goto out_error;
-	d_add(dentry, inode);
+	}
+	dput(d);
 out:
 	dput(parent);
 	return 0;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 137e18abb7e7..51beb6e38c90 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -258,7 +258,7 @@ extern const struct dentry_operations nfs4_dentry_operations;
 
 /* dir.c */
 int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
-		    unsigned, umode_t, int *);
+		    unsigned, umode_t);
 
 /* super.c */
 extern struct file_system_type nfs4_fs_type;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6dd146885da9..b790976d3913 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2951,7 +2951,7 @@ static int _nfs4_do_open(struct inode *dir,
 		}
 	}
 	if (opened && opendata->file_created)
-		*opened |= FILE_CREATED;
+		*opened = 1;
 
 	if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) {
 		*ctx_th = opendata->f_attr.mdsthreshold;
@@ -6466,34 +6466,34 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 		if (data->arg.new_lock && !data->cancelled) {
 			data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
 			if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0)
-				break;
+				goto out_restart;
 		}
-
 		if (data->arg.new_lock_owner != 0) {
 			nfs_confirm_seqid(&lsp->ls_seqid, 0);
 			nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid);
 			set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags);
-			goto out_done;
-		} else if (nfs4_update_lock_stateid(lsp, &data->res.stateid))
-			goto out_done;
-
+		} else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid))
+			goto out_restart;
 		break;
 	case -NFS4ERR_BAD_STATEID:
 	case -NFS4ERR_OLD_STATEID:
 	case -NFS4ERR_STALE_STATEID:
 	case -NFS4ERR_EXPIRED:
 		if (data->arg.new_lock_owner != 0) {
-			if (nfs4_stateid_match(&data->arg.open_stateid,
+			if (!nfs4_stateid_match(&data->arg.open_stateid,
 						&lsp->ls_state->open_stateid))
-				goto out_done;
-		} else if (nfs4_stateid_match(&data->arg.lock_stateid,
+				goto out_restart;
+		} else if (!nfs4_stateid_match(&data->arg.lock_stateid,
 						&lsp->ls_stateid))
-				goto out_done;
+				goto out_restart;
 	}
-	if (!data->cancelled)
-		rpc_restart_call_prepare(task);
 out_done:
 	dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status);
+	return;
+out_restart:
+	if (!data->cancelled)
+		rpc_restart_call_prepare(task);
+	goto out_done;
 }
 
 static void nfs4_lock_release(void *calldata)
@@ -6502,7 +6502,7 @@ static void nfs4_lock_release(void *calldata)
 
 	dprintk("%s: begin!\n", __func__);
 	nfs_free_seqid(data->arg.open_seqid);
-	if (data->cancelled) {
+	if (data->cancelled && data->rpc_status == 0) {
 		struct rpc_task *task;
 		task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp,
 				data->arg.lock_seqid);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index b0555d7d8200..55a099e47ba2 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -763,7 +763,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 		goto out_nfserr;
 	}
 
-	host_err = ima_file_check(file, may_flags, 0);
+	host_err = ima_file_check(file, may_flags);
 	if (host_err) {
 		fput(file);
 		goto out_nfserr;
diff --git a/fs/open.c b/fs/open.c
index d0e955b558ad..d98e19239bb7 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -724,27 +724,13 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 	return ksys_fchown(fd, user, group);
 }
 
-int open_check_o_direct(struct file *f)
-{
-	/* NB: we're sure to have correct a_ops only after f_op->open */
-	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
-			return -EINVAL;
-	}
-	return 0;
-}
-
 static int do_dentry_open(struct file *f,
 			  struct inode *inode,
-			  int (*open)(struct inode *, struct file *),
-			  const struct cred *cred)
+			  int (*open)(struct inode *, struct file *))
 {
 	static const struct file_operations empty_fops = {};
 	int error;
 
-	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
-				FMODE_PREAD | FMODE_PWRITE;
-
 	path_get(&f->f_path);
 	f->f_inode = inode;
 	f->f_mapping = inode->i_mapping;
@@ -753,7 +739,7 @@ static int do_dentry_open(struct file *f,
 	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
 
 	if (unlikely(f->f_flags & O_PATH)) {
-		f->f_mode = FMODE_PATH;
+		f->f_mode = FMODE_PATH | FMODE_OPENED;
 		f->f_op = &empty_fops;
 		return 0;
 	}
@@ -780,7 +766,7 @@ static int do_dentry_open(struct file *f,
 		goto cleanup_all;
 	}
 
-	error = security_file_open(f, cred);
+	error = security_file_open(f);
 	if (error)
 		goto cleanup_all;
 
@@ -788,6 +774,8 @@ static int do_dentry_open(struct file *f,
 	if (error)
 		goto cleanup_all;
 
+	/* normally all 3 are set; ->open() can clear them if needed */
+	f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
 	if (!open)
 		open = f->f_op->open;
 	if (open) {
@@ -795,6 +783,7 @@ static int do_dentry_open(struct file *f,
 		if (error)
 			goto cleanup_all;
 	}
+	f->f_mode |= FMODE_OPENED;
 	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(inode);
 	if ((f->f_mode & FMODE_READ) &&
@@ -809,9 +798,16 @@ static int do_dentry_open(struct file *f,
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
 
+	/* NB: we're sure to have correct a_ops only after f_op->open */
+	if (f->f_flags & O_DIRECT) {
+		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
+			return -EINVAL;
+	}
 	return 0;
 
 cleanup_all:
+	if (WARN_ON_ONCE(error > 0))
+		error = -EINVAL;
 	fops_put(f->f_op);
 	if (f->f_mode & FMODE_WRITER) {
 		put_write_access(inode);
@@ -847,19 +843,12 @@ cleanup_file:
  * Returns zero on success or -errno if the open failed.
  */
 int finish_open(struct file *file, struct dentry *dentry,
-		int (*open)(struct inode *, struct file *),
-		int *opened)
+		int (*open)(struct inode *, struct file *))
 {
-	int error;
-	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
+	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
 
 	file->f_path.dentry = dentry;
-	error = do_dentry_open(file, d_backing_inode(dentry), open,
-			       current_cred());
-	if (!error)
-		*opened |= FILE_OPENED;
-
-	return error;
+	return do_dentry_open(file, d_backing_inode(dentry), open);
 }
 EXPORT_SYMBOL(finish_open);
 
@@ -874,13 +863,13 @@ EXPORT_SYMBOL(finish_open);
  * NB: unlike finish_open() this function does consume the dentry reference and
  * the caller need not dput() it.
  *
- * Returns "1" which must be the return value of ->atomic_open() after having
+ * Returns "0" which must be the return value of ->atomic_open() after having
  * called this function.
  */
 int finish_no_open(struct file *file, struct dentry *dentry)
 {
 	file->f_path.dentry = dentry;
-	return 1;
+	return 0;
 }
 EXPORT_SYMBOL(finish_no_open);
 
@@ -896,8 +885,7 @@ EXPORT_SYMBOL(file_path);
  * @file: newly allocated file with f_flag initialized
  * @cred: credentials to use
  */
-int vfs_open(const struct path *path, struct file *file,
-	     const struct cred *cred)
+int vfs_open(const struct path *path, struct file *file)
 {
 	struct dentry *dentry = d_real(path->dentry, NULL, file->f_flags, 0);
 
@@ -905,7 +893,7 @@ int vfs_open(const struct path *path, struct file *file,
 		return PTR_ERR(dentry);
 
 	file->f_path = *path;
-	return do_dentry_open(file, d_backing_inode(dentry), NULL, cred);
+	return do_dentry_open(file, d_backing_inode(dentry), NULL);
 }
 
 struct file *dentry_open(const struct path *path, int flags,
@@ -919,19 +907,11 @@ struct file *dentry_open(const struct path *path, int flags,
 	/* We must always pass in a valid mount pointer. */
 	BUG_ON(!path->mnt);
 
-	f = get_empty_filp();
+	f = alloc_empty_file(flags, cred);
 	if (!IS_ERR(f)) {
-		f->f_flags = flags;
-		error = vfs_open(path, f, cred);
-		if (!error) {
-			/* from now on we need fput() to dispose of f */
-			error = open_check_o_direct(f);
-			if (error) {
-				fput(f);
-				f = ERR_PTR(error);
-			}
-		} else { 
-			put_filp(f);
+		error = vfs_open(path, f);
+		if (error) {
+			fput(f);
 			f = ERR_PTR(error);
 		}
 	}
@@ -1063,26 +1043,6 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 }
 EXPORT_SYMBOL(file_open_root);
 
-struct file *filp_clone_open(struct file *oldfile)
-{
-	struct file *file;
-	int retval;
-
-	file = get_empty_filp();
-	if (IS_ERR(file))
-		return file;
-
-	file->f_flags = oldfile->f_flags;
-	retval = vfs_open(&oldfile->f_path, file, oldfile->f_cred);
-	if (retval) {
-		put_filp(file);
-		return ERR_PTR(retval);
-	}
-
-	return file;
-}
-EXPORT_SYMBOL(filp_clone_open);
-
 long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
diff --git a/fs/pipe.c b/fs/pipe.c
index bb0840e234f3..bdc5d3c0977d 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -509,22 +509,19 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 }
 
-static struct wait_queue_head *
-pipe_get_poll_head(struct file *filp, __poll_t events)
-{
-	struct pipe_inode_info *pipe = filp->private_data;
-
-	return &pipe->wait;
-}
-
 /* No kernel lock held - fine */
-static __poll_t pipe_poll_mask(struct file *filp, __poll_t events)
+static __poll_t
+pipe_poll(struct file *filp, poll_table *wait)
 {
+	__poll_t mask;
 	struct pipe_inode_info *pipe = filp->private_data;
-	int nrbufs = pipe->nrbufs;
-	__poll_t mask = 0;
+	int nrbufs;
+
+	poll_wait(filp, &pipe->wait, wait);
 
 	/* Reading only -- no need for acquiring the semaphore.  */
+	nrbufs = pipe->nrbufs;
+	mask = 0;
 	if (filp->f_mode & FMODE_READ) {
 		mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
 		if (!pipe->writers && filp->f_version != pipe->w_counter)
@@ -744,54 +741,33 @@ fail_inode:
 
 int create_pipe_files(struct file **res, int flags)
 {
-	int err;
 	struct inode *inode = get_pipe_inode();
 	struct file *f;
-	struct path path;
 
 	if (!inode)
 		return -ENFILE;
 
-	err = -ENOMEM;
-	path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &empty_name);
-	if (!path.dentry)
-		goto err_inode;
-	path.mnt = mntget(pipe_mnt);
-
-	d_instantiate(path.dentry, inode);
-
-	f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops);
+	f = alloc_file_pseudo(inode, pipe_mnt, "",
+				O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
+				&pipefifo_fops);
 	if (IS_ERR(f)) {
-		err = PTR_ERR(f);
-		goto err_dentry;
+		free_pipe_info(inode->i_pipe);
+		iput(inode);
+		return PTR_ERR(f);
 	}
 
-	f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
 	f->private_data = inode->i_pipe;
 
-	res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);
+	res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK),
+				  &pipefifo_fops);
 	if (IS_ERR(res[0])) {
-		err = PTR_ERR(res[0]);
-		goto err_file;
+		put_pipe_info(inode, inode->i_pipe);
+		fput(f);
+		return PTR_ERR(res[0]);
 	}
-
-	path_get(&path);
 	res[0]->private_data = inode->i_pipe;
-	res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK);
 	res[1] = f;
 	return 0;
-
-err_file:
-	put_filp(f);
-err_dentry:
-	free_pipe_info(inode->i_pipe);
-	path_put(&path);
-	return err;
-
-err_inode:
-	free_pipe_info(inode->i_pipe);
-	iput(inode);
-	return err;
 }
 
 static int __do_pipe_flags(int *fd, struct file **files, int flags)
@@ -1023,8 +999,7 @@ const struct file_operations pipefifo_fops = {
 	.llseek		= no_llseek,
 	.read_iter	= pipe_read,
 	.write_iter	= pipe_write,
-	.get_poll_head	= pipe_get_poll_head,
-	.poll_mask	= pipe_poll_mask,
+	.poll		= pipe_poll,
 	.unlocked_ioctl	= pipe_ioctl,
 	.release	= pipe_release,
 	.fasync		= pipe_fasync,
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 6ac1c92997ea..bb1c1625b158 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -564,11 +564,20 @@ static int proc_seq_open(struct inode *inode, struct file *file)
 	return seq_open(file, de->seq_ops);
 }
 
+static int proc_seq_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+
+	if (de->state_size)
+		return seq_release_private(inode, file);
+	return seq_release(inode, file);
+}
+
 static const struct file_operations proc_seq_fops = {
 	.open		= proc_seq_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release	= proc_seq_release,
 };
 
 struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e9679016271f..dfd73a4616ce 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -831,7 +831,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		SEQ_PUT_DEC(" kB\nSwap:           ", mss->swap);
 		SEQ_PUT_DEC(" kB\nSwapPss:        ",
 						mss->swap_pss >> PSS_SHIFT);
-		SEQ_PUT_DEC(" kB\nLocked:         ", mss->pss >> PSS_SHIFT);
+		SEQ_PUT_DEC(" kB\nLocked:         ",
+						mss->pss_locked >> PSS_SHIFT);
 		seq_puts(m, " kB\n");
 	}
 	if (!rollup_mode) {
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index 09c19ef91526..503086f7f7c1 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -50,12 +50,19 @@ config PSTORE_842_COMPRESS
 	help
 	  This option enables 842 compression algorithm support.
 
+config PSTORE_ZSTD_COMPRESS
+	bool "zstd compression"
+	depends on PSTORE
+	select CRYPTO_ZSTD
+	help
+	  This option enables zstd compression algorithm support.
+
 config PSTORE_COMPRESS
 	def_bool y
 	depends on PSTORE
 	depends on PSTORE_DEFLATE_COMPRESS || PSTORE_LZO_COMPRESS ||	\
 		   PSTORE_LZ4_COMPRESS || PSTORE_LZ4HC_COMPRESS ||	\
-		   PSTORE_842_COMPRESS
+		   PSTORE_842_COMPRESS || PSTORE_ZSTD_COMPRESS
 
 choice
 	prompt "Default pstore compression algorithm"
@@ -65,8 +72,8 @@ choice
 	  This change be changed at boot with "pstore.compress=..." on
 	  the kernel command line.
 
-	  Currently, pstore has support for 5 compression algorithms:
-	  deflate, lzo, lz4, lz4hc and 842.
+	  Currently, pstore has support for 6 compression algorithms:
+	  deflate, lzo, lz4, lz4hc, 842 and zstd.
 
 	  The default compression algorithm is deflate.
 
@@ -85,6 +92,9 @@ choice
 	config PSTORE_842_COMPRESS_DEFAULT
 		bool "842" if PSTORE_842_COMPRESS
 
+	config PSTORE_ZSTD_COMPRESS_DEFAULT
+		bool "zstd" if PSTORE_ZSTD_COMPRESS
+
 endchoice
 
 config PSTORE_COMPRESS_DEFAULT
@@ -95,6 +105,7 @@ config PSTORE_COMPRESS_DEFAULT
 	default "lz4" if PSTORE_LZ4_COMPRESS_DEFAULT
 	default "lz4hc" if PSTORE_LZ4HC_COMPRESS_DEFAULT
 	default "842" if PSTORE_842_COMPRESS_DEFAULT
+	default "zstd" if PSTORE_ZSTD_COMPRESS_DEFAULT
 
 config PSTORE_CONSOLE
 	bool "Log kernel console messages"
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index c238ab8ba31d..15e99d5a681d 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -34,6 +34,9 @@
 #if IS_ENABLED(CONFIG_PSTORE_LZ4_COMPRESS) || IS_ENABLED(CONFIG_PSTORE_LZ4HC_COMPRESS)
 #include <linux/lz4.h>
 #endif
+#if IS_ENABLED(CONFIG_PSTORE_ZSTD_COMPRESS)
+#include <linux/zstd.h>
+#endif
 #include <linux/crypto.h>
 #include <linux/string.h>
 #include <linux/timer.h>
@@ -192,6 +195,13 @@ static int zbufsize_842(size_t size)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_PSTORE_ZSTD_COMPRESS)
+static int zbufsize_zstd(size_t size)
+{
+	return ZSTD_compressBound(size);
+}
+#endif
+
 static const struct pstore_zbackend *zbackend __ro_after_init;
 
 static const struct pstore_zbackend zbackends[] = {
@@ -225,6 +235,12 @@ static const struct pstore_zbackend zbackends[] = {
 		.name		= "842",
 	},
 #endif
+#if IS_ENABLED(CONFIG_PSTORE_ZSTD_COMPRESS)
+	{
+		.zbufsize	= zbufsize_zstd,
+		.name		= "zstd",
+	},
+#endif
 	{ }
 };
 
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index 7e288d97adcb..9fed1c05f1f4 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -76,83 +76,99 @@ static char *le_type(struct reiserfs_key *key)
 }
 
 /* %k */
-static void sprintf_le_key(char *buf, struct reiserfs_key *key)
+static int scnprintf_le_key(char *buf, size_t size, struct reiserfs_key *key)
 {
 	if (key)
-		sprintf(buf, "[%d %d %s %s]", le32_to_cpu(key->k_dir_id),
-			le32_to_cpu(key->k_objectid), le_offset(key),
-			le_type(key));
+		return scnprintf(buf, size, "[%d %d %s %s]",
+				 le32_to_cpu(key->k_dir_id),
+				 le32_to_cpu(key->k_objectid), le_offset(key),
+				 le_type(key));
 	else
-		sprintf(buf, "[NULL]");
+		return scnprintf(buf, size, "[NULL]");
 }
 
 /* %K */
-static void sprintf_cpu_key(char *buf, struct cpu_key *key)
+static int scnprintf_cpu_key(char *buf, size_t size, struct cpu_key *key)
 {
 	if (key)
-		sprintf(buf, "[%d %d %s %s]", key->on_disk_key.k_dir_id,
-			key->on_disk_key.k_objectid, reiserfs_cpu_offset(key),
-			cpu_type(key));
+		return scnprintf(buf, size, "[%d %d %s %s]",
+				 key->on_disk_key.k_dir_id,
+				 key->on_disk_key.k_objectid,
+				 reiserfs_cpu_offset(key), cpu_type(key));
 	else
-		sprintf(buf, "[NULL]");
+		return scnprintf(buf, size, "[NULL]");
 }
 
-static void sprintf_de_head(char *buf, struct reiserfs_de_head *deh)
+static int scnprintf_de_head(char *buf, size_t size,
+			     struct reiserfs_de_head *deh)
 {
 	if (deh)
-		sprintf(buf,
-			"[offset=%d dir_id=%d objectid=%d location=%d state=%04x]",
-			deh_offset(deh), deh_dir_id(deh), deh_objectid(deh),
-			deh_location(deh), deh_state(deh));
+		return scnprintf(buf, size,
+				 "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]",
+				 deh_offset(deh), deh_dir_id(deh),
+				 deh_objectid(deh), deh_location(deh),
+				 deh_state(deh));
 	else
-		sprintf(buf, "[NULL]");
+		return scnprintf(buf, size, "[NULL]");
 
 }
 
-static void sprintf_item_head(char *buf, struct item_head *ih)
+static int scnprintf_item_head(char *buf, size_t size, struct item_head *ih)
 {
 	if (ih) {
-		strcpy(buf,
-		       (ih_version(ih) == KEY_FORMAT_3_6) ? "*3.6* " : "*3.5*");
-		sprintf_le_key(buf + strlen(buf), &(ih->ih_key));
-		sprintf(buf + strlen(buf), ", item_len %d, item_location %d, "
-			"free_space(entry_count) %d",
-			ih_item_len(ih), ih_location(ih), ih_free_space(ih));
+		char *p = buf;
+		char * const end = buf + size;
+
+		p += scnprintf(p, end - p, "%s",
+			       (ih_version(ih) == KEY_FORMAT_3_6) ?
+			       "*3.6* " : "*3.5*");
+
+		p += scnprintf_le_key(p, end - p, &ih->ih_key);
+
+		p += scnprintf(p, end - p,
+			       ", item_len %d, item_location %d, free_space(entry_count) %d",
+			       ih_item_len(ih), ih_location(ih),
+			       ih_free_space(ih));
+		return p - buf;
 	} else
-		sprintf(buf, "[NULL]");
+		return scnprintf(buf, size, "[NULL]");
 }
 
-static void sprintf_direntry(char *buf, struct reiserfs_dir_entry *de)
+static int scnprintf_direntry(char *buf, size_t size,
+			      struct reiserfs_dir_entry *de)
 {
 	char name[20];
 
 	memcpy(name, de->de_name, de->de_namelen > 19 ? 19 : de->de_namelen);
 	name[de->de_namelen > 19 ? 19 : de->de_namelen] = 0;
-	sprintf(buf, "\"%s\"==>[%d %d]", name, de->de_dir_id, de->de_objectid);
+	return scnprintf(buf, size, "\"%s\"==>[%d %d]",
+			 name, de->de_dir_id, de->de_objectid);
 }
 
-static void sprintf_block_head(char *buf, struct buffer_head *bh)
+static int scnprintf_block_head(char *buf, size_t size, struct buffer_head *bh)
 {
-	sprintf(buf, "level=%d, nr_items=%d, free_space=%d rdkey ",
-		B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh));
+	return scnprintf(buf, size,
+			 "level=%d, nr_items=%d, free_space=%d rdkey ",
+			 B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh));
 }
 
-static void sprintf_buffer_head(char *buf, struct buffer_head *bh)
+static int scnprintf_buffer_head(char *buf, size_t size, struct buffer_head *bh)
 {
-	sprintf(buf,
-		"dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
-		bh->b_bdev, bh->b_size,
-		(unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)),
-		bh->b_state, bh->b_page,
-		buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE",
-		buffer_dirty(bh) ? "DIRTY" : "CLEAN",
-		buffer_locked(bh) ? "LOCKED" : "UNLOCKED");
+	return scnprintf(buf, size,
+			 "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
+			 bh->b_bdev, bh->b_size,
+			 (unsigned long long)bh->b_blocknr,
+			 atomic_read(&(bh->b_count)),
+			 bh->b_state, bh->b_page,
+			 buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE",
+			 buffer_dirty(bh) ? "DIRTY" : "CLEAN",
+			 buffer_locked(bh) ? "LOCKED" : "UNLOCKED");
 }
 
-static void sprintf_disk_child(char *buf, struct disk_child *dc)
+static int scnprintf_disk_child(char *buf, size_t size, struct disk_child *dc)
 {
-	sprintf(buf, "[dc_number=%d, dc_size=%u]", dc_block_number(dc),
-		dc_size(dc));
+	return scnprintf(buf, size, "[dc_number=%d, dc_size=%u]",
+			 dc_block_number(dc), dc_size(dc));
 }
 
 static char *is_there_reiserfs_struct(char *fmt, int *what)
@@ -189,55 +205,60 @@ static void prepare_error_buf(const char *fmt, va_list args)
 	char *fmt1 = fmt_buf;
 	char *k;
 	char *p = error_buf;
+	char * const end = &error_buf[sizeof(error_buf)];
 	int what;
 
 	spin_lock(&error_lock);
 
-	strcpy(fmt1, fmt);
+	if (WARN_ON(strscpy(fmt_buf, fmt, sizeof(fmt_buf)) < 0)) {
+		strscpy(error_buf, "format string too long", end - error_buf);
+		goto out_unlock;
+	}
 
 	while ((k = is_there_reiserfs_struct(fmt1, &what)) != NULL) {
 		*k = 0;
 
-		p += vsprintf(p, fmt1, args);
+		p += vscnprintf(p, end - p, fmt1, args);
 
 		switch (what) {
 		case 'k':
-			sprintf_le_key(p, va_arg(args, struct reiserfs_key *));
+			p += scnprintf_le_key(p, end - p,
+					      va_arg(args, struct reiserfs_key *));
 			break;
 		case 'K':
-			sprintf_cpu_key(p, va_arg(args, struct cpu_key *));
+			p += scnprintf_cpu_key(p, end - p,
+					       va_arg(args, struct cpu_key *));
 			break;
 		case 'h':
-			sprintf_item_head(p, va_arg(args, struct item_head *));
+			p += scnprintf_item_head(p, end - p,
+						 va_arg(args, struct item_head *));
 			break;
 		case 't':
-			sprintf_direntry(p,
-					 va_arg(args,
-						struct reiserfs_dir_entry *));
+			p += scnprintf_direntry(p, end - p,
+						va_arg(args, struct reiserfs_dir_entry *));
 			break;
 		case 'y':
-			sprintf_disk_child(p,
-					   va_arg(args, struct disk_child *));
+			p += scnprintf_disk_child(p, end - p,
+						  va_arg(args, struct disk_child *));
 			break;
 		case 'z':
-			sprintf_block_head(p,
-					   va_arg(args, struct buffer_head *));
+			p += scnprintf_block_head(p, end - p,
+						  va_arg(args, struct buffer_head *));
 			break;
 		case 'b':
-			sprintf_buffer_head(p,
-					    va_arg(args, struct buffer_head *));
+			p += scnprintf_buffer_head(p, end - p,
+						   va_arg(args, struct buffer_head *));
 			break;
 		case 'a':
-			sprintf_de_head(p,
-					va_arg(args,
-					       struct reiserfs_de_head *));
+			p += scnprintf_de_head(p, end - p,
+					       va_arg(args, struct reiserfs_de_head *));
 			break;
 		}
 
-		p += strlen(p);
 		fmt1 = k + 2;
 	}
-	vsprintf(p, fmt1, args);
+	p += vscnprintf(p, end - p, fmt1, args);
+out_unlock:
 	spin_unlock(&error_lock);
 
 }
diff --git a/fs/select.c b/fs/select.c
index 317891ff8165..4a6b6e4b21cb 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -34,29 +34,6 @@
 
 #include <linux/uaccess.h>
 
-__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
-{
-	if (file->f_op->poll) {
-		return file->f_op->poll(file, pt);
-	} else if (file_has_poll_mask(file)) {
-		unsigned int events = poll_requested_events(pt);
-		struct wait_queue_head *head;
-
-		if (pt && pt->_qproc) {
-			head = file->f_op->get_poll_head(file, events);
-			if (!head)
-				return DEFAULT_POLLMASK;
-			if (IS_ERR(head))
-				return EPOLLERR;
-			pt->_qproc(file, head, pt);
-		}
-
-		return file->f_op->poll_mask(file, events);
-	} else {
-		return DEFAULT_POLLMASK;
-	}
-}
-EXPORT_SYMBOL_GPL(vfs_poll);
 
 /*
  * Estimate expected accuracy in ns from a timeval.
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 2751476e6b6e..f098b9f1c396 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -167,6 +167,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 	}
 
 	if (compressed) {
+		if (!msblk->stream)
+			goto read_failure;
 		length = squashfs_decompress(msblk, bh, b, offset, length,
 			output);
 		if (length < 0)
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 23813c078cc9..0839efa720b3 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -350,6 +350,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer,
 
 	TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset);
 
+	if (unlikely(length < 0))
+		return -EIO;
+
 	while (length) {
 		entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0);
 		if (entry->error) {
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 13d80947bf9e..f1c1430ae721 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -194,7 +194,11 @@ static long long read_indexes(struct super_block *sb, int n,
 		}
 
 		for (i = 0; i < blocks; i++) {
-			int size = le32_to_cpu(blist[i]);
+			int size = squashfs_block_size(blist[i]);
+			if (size < 0) {
+				err = size;
+				goto failure;
+			}
 			block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size);
 		}
 		n -= blocks;
@@ -367,7 +371,24 @@ static int read_blocklist(struct inode *inode, int index, u64 *block)
 			sizeof(size));
 	if (res < 0)
 		return res;
-	return le32_to_cpu(size);
+	return squashfs_block_size(size);
+}
+
+void squashfs_fill_page(struct page *page, struct squashfs_cache_entry *buffer, int offset, int avail)
+{
+	int copied;
+	void *pageaddr;
+
+	pageaddr = kmap_atomic(page);
+	copied = squashfs_copy_data(pageaddr, buffer, offset, avail);
+	memset(pageaddr + copied, 0, PAGE_SIZE - copied);
+	kunmap_atomic(pageaddr);
+
+	flush_dcache_page(page);
+	if (copied == avail)
+		SetPageUptodate(page);
+	else
+		SetPageError(page);
 }
 
 /* Copy data into page cache  */
@@ -376,7 +397,6 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer,
 {
 	struct inode *inode = page->mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
-	void *pageaddr;
 	int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
 	int start_index = page->index & ~mask, end_index = start_index | mask;
 
@@ -402,12 +422,7 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer,
 		if (PageUptodate(push_page))
 			goto skip_page;
 
-		pageaddr = kmap_atomic(push_page);
-		squashfs_copy_data(pageaddr, buffer, offset, avail);
-		memset(pageaddr + avail, 0, PAGE_SIZE - avail);
-		kunmap_atomic(pageaddr);
-		flush_dcache_page(push_page);
-		SetPageUptodate(push_page);
+		squashfs_fill_page(push_page, buffer, offset, avail);
 skip_page:
 		unlock_page(push_page);
 		if (i != page->index)
@@ -416,10 +431,9 @@ skip_page:
 }
 
 /* Read datablock stored packed inside a fragment (tail-end packed block) */
-static int squashfs_readpage_fragment(struct page *page)
+static int squashfs_readpage_fragment(struct page *page, int expected)
 {
 	struct inode *inode = page->mapping->host;
-	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
 	struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb,
 		squashfs_i(inode)->fragment_block,
 		squashfs_i(inode)->fragment_size);
@@ -430,23 +444,16 @@ static int squashfs_readpage_fragment(struct page *page)
 			squashfs_i(inode)->fragment_block,
 			squashfs_i(inode)->fragment_size);
 	else
-		squashfs_copy_cache(page, buffer, i_size_read(inode) &
-			(msblk->block_size - 1),
+		squashfs_copy_cache(page, buffer, expected,
 			squashfs_i(inode)->fragment_offset);
 
 	squashfs_cache_put(buffer);
 	return res;
 }
 
-static int squashfs_readpage_sparse(struct page *page, int index, int file_end)
+static int squashfs_readpage_sparse(struct page *page, int expected)
 {
-	struct inode *inode = page->mapping->host;
-	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
-	int bytes = index == file_end ?
-			(i_size_read(inode) & (msblk->block_size - 1)) :
-			 msblk->block_size;
-
-	squashfs_copy_cache(page, NULL, bytes, 0);
+	squashfs_copy_cache(page, NULL, expected, 0);
 	return 0;
 }
 
@@ -456,6 +463,9 @@ static int squashfs_readpage(struct file *file, struct page *page)
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
 	int index = page->index >> (msblk->block_log - PAGE_SHIFT);
 	int file_end = i_size_read(inode) >> msblk->block_log;
+	int expected = index == file_end ?
+			(i_size_read(inode) & (msblk->block_size - 1)) :
+			 msblk->block_size;
 	int res;
 	void *pageaddr;
 
@@ -474,11 +484,11 @@ static int squashfs_readpage(struct file *file, struct page *page)
 			goto error_out;
 
 		if (bsize == 0)
-			res = squashfs_readpage_sparse(page, index, file_end);
+			res = squashfs_readpage_sparse(page, expected);
 		else
-			res = squashfs_readpage_block(page, block, bsize);
+			res = squashfs_readpage_block(page, block, bsize, expected);
 	} else
-		res = squashfs_readpage_fragment(page);
+		res = squashfs_readpage_fragment(page, expected);
 
 	if (!res)
 		return 0;
diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c
index f2310d2a2019..a9ba8d96776a 100644
--- a/fs/squashfs/file_cache.c
+++ b/fs/squashfs/file_cache.c
@@ -20,7 +20,7 @@
 #include "squashfs.h"
 
 /* Read separately compressed datablock and memcopy into page cache */
-int squashfs_readpage_block(struct page *page, u64 block, int bsize)
+int squashfs_readpage_block(struct page *page, u64 block, int bsize, int expected)
 {
 	struct inode *i = page->mapping->host;
 	struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
@@ -31,7 +31,7 @@ int squashfs_readpage_block(struct page *page, u64 block, int bsize)
 		ERROR("Unable to read page, block %llx, size %x\n", block,
 			bsize);
 	else
-		squashfs_copy_cache(page, buffer, buffer->length, 0);
+		squashfs_copy_cache(page, buffer, expected, 0);
 
 	squashfs_cache_put(buffer);
 	return res;
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index cb485d8e0e91..80db1b86a27c 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -21,10 +21,11 @@
 #include "page_actor.h"
 
 static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
-	int pages, struct page **page);
+	int pages, struct page **page, int bytes);
 
 /* Read separately compressed datablock directly into page cache */
-int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
+int squashfs_readpage_block(struct page *target_page, u64 block, int bsize,
+	int expected)
 
 {
 	struct inode *inode = target_page->mapping->host;
@@ -83,7 +84,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
 		 * using an intermediate buffer.
 		 */
 		res = squashfs_read_cache(target_page, block, bsize, pages,
-								page);
+							page, expected);
 		if (res < 0)
 			goto mark_errored;
 
@@ -95,6 +96,11 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
 	if (res < 0)
 		goto mark_errored;
 
+	if (res != expected) {
+		res = -EIO;
+		goto mark_errored;
+	}
+
 	/* Last page may have trailing bytes not filled */
 	bytes = res % PAGE_SIZE;
 	if (bytes) {
@@ -138,13 +144,12 @@ out:
 
 
 static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
-	int pages, struct page **page)
+	int pages, struct page **page, int bytes)
 {
 	struct inode *i = target_page->mapping->host;
 	struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
 						 block, bsize);
-	int bytes = buffer->length, res = buffer->error, n, offset = 0;
-	void *pageaddr;
+	int res = buffer->error, n, offset = 0;
 
 	if (res) {
 		ERROR("Unable to read page, block %llx, size %x\n", block,
@@ -159,12 +164,7 @@ static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
 		if (page[n] == NULL)
 			continue;
 
-		pageaddr = kmap_atomic(page[n]);
-		squashfs_copy_data(pageaddr, buffer, offset, avail);
-		memset(pageaddr + avail, 0, PAGE_SIZE - avail);
-		kunmap_atomic(pageaddr);
-		flush_dcache_page(page[n]);
-		SetPageUptodate(page[n]);
+		squashfs_fill_page(page[n], buffer, offset, avail);
 		unlock_page(page[n]);
 		if (page[n] != target_page)
 			put_page(page[n]);
diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c
index 0ed6edbc5c71..0681feab4a84 100644
--- a/fs/squashfs/fragment.c
+++ b/fs/squashfs/fragment.c
@@ -49,11 +49,16 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment,
 				u64 *fragment_block)
 {
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
-	int block = SQUASHFS_FRAGMENT_INDEX(fragment);
-	int offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment);
-	u64 start_block = le64_to_cpu(msblk->fragment_index[block]);
+	int block, offset, size;
 	struct squashfs_fragment_entry fragment_entry;
-	int size;
+	u64 start_block;
+
+	if (fragment >= msblk->fragments)
+		return -EIO;
+	block = SQUASHFS_FRAGMENT_INDEX(fragment);
+	offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment);
+
+	start_block = le64_to_cpu(msblk->fragment_index[block]);
 
 	size = squashfs_read_metadata(sb, &fragment_entry, &start_block,
 					&offset, sizeof(fragment_entry));
@@ -61,9 +66,7 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment,
 		return size;
 
 	*fragment_block = le64_to_cpu(fragment_entry.start_block);
-	size = le32_to_cpu(fragment_entry.size);
-
-	return size;
+	return squashfs_block_size(fragment_entry.size);
 }
 
 
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index 887d6d270080..f89f8a74c6ce 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -67,11 +67,12 @@ extern __le64 *squashfs_read_fragment_index_table(struct super_block *,
 				u64, u64, unsigned int);
 
 /* file.c */
+void squashfs_fill_page(struct page *, struct squashfs_cache_entry *, int, int);
 void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int,
 				int);
 
 /* file_xxx.c */
-extern int squashfs_readpage_block(struct page *, u64, int);
+extern int squashfs_readpage_block(struct page *, u64, int, int);
 
 /* id.c */
 extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *);
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 24d12fd14177..4e6853f084d0 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -129,6 +129,12 @@
 
 #define SQUASHFS_COMPRESSED_BLOCK(B)	(!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK))
 
+static inline int squashfs_block_size(__le32 raw)
+{
+	u32 size = le32_to_cpu(raw);
+	return (size >> 25) ? -EIO : size;
+}
+
 /*
  * Inode number ops.  Inodes consist of a compressed block number, and an
  * uncompressed offset within that block
diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h
index 1da565cb50c3..ef69c31947bf 100644
--- a/fs/squashfs/squashfs_fs_sb.h
+++ b/fs/squashfs/squashfs_fs_sb.h
@@ -75,6 +75,7 @@ struct squashfs_sb_info {
 	unsigned short				block_log;
 	long long				bytes_used;
 	unsigned int				inodes;
+	unsigned int				fragments;
 	int					xattr_ids;
 };
 #endif
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 8a73b97217c8..40e657386fa5 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -175,6 +175,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 	msblk->inode_table = le64_to_cpu(sblk->inode_table_start);
 	msblk->directory_table = le64_to_cpu(sblk->directory_table_start);
 	msblk->inodes = le32_to_cpu(sblk->inodes);
+	msblk->fragments = le32_to_cpu(sblk->fragments);
 	flags = le16_to_cpu(sblk->flags);
 
 	TRACE("Found valid superblock on %pg\n", sb->s_bdev);
@@ -185,7 +186,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 	TRACE("Filesystem size %lld bytes\n", msblk->bytes_used);
 	TRACE("Block size %d\n", msblk->block_size);
 	TRACE("Number of inodes %d\n", msblk->inodes);
-	TRACE("Number of fragments %d\n", le32_to_cpu(sblk->fragments));
+	TRACE("Number of fragments %d\n", msblk->fragments);
 	TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids));
 	TRACE("sblk->inode_table_start %llx\n", msblk->inode_table);
 	TRACE("sblk->directory_table_start %llx\n", msblk->directory_table);
@@ -272,7 +273,7 @@ allocate_id_index_table:
 	sb->s_export_op = &squashfs_export_ops;
 
 handle_fragments:
-	fragments = le32_to_cpu(sblk->fragments);
+	fragments = msblk->fragments;
 	if (fragments == 0)
 		goto check_directory_table;
 
diff --git a/fs/statfs.c b/fs/statfs.c
index 5b2a24f0f263..f0216629621d 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -335,7 +335,7 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat
 	return 0;
 }
 
-COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, struct compat_statfs64 __user * buf)
 {
 	struct kstatfs tmp;
 	int error;
@@ -349,7 +349,12 @@ COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, s
 	return error;
 }
 
-COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	return kcompat_sys_statfs64(pathname, sz, buf);
+}
+
+int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user * buf)
 {
 	struct kstatfs tmp;
 	int error;
@@ -363,6 +368,11 @@ COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct co
 	return error;
 }
 
+COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	return kcompat_sys_fstatfs64(fd, sz, buf);
+}
+
 /*
  * This is a copy of sys_ustat, just dealing with a structure layout.
  * Given how simple this syscall is that apporach is more maintainable
diff --git a/fs/timerfd.c b/fs/timerfd.c
index d84a2bee4f82..d69ad801eb80 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -66,7 +66,7 @@ static void timerfd_triggered(struct timerfd_ctx *ctx)
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
 	ctx->expired = 1;
 	ctx->ticks++;
-	wake_up_locked(&ctx->wqh);
+	wake_up_locked_poll(&ctx->wqh, EPOLLIN);
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 }
 
@@ -107,7 +107,7 @@ void timerfd_clock_was_set(void)
 		if (ctx->moffs != moffs) {
 			ctx->moffs = KTIME_MAX;
 			ctx->ticks++;
-			wake_up_locked(&ctx->wqh);
+			wake_up_locked_poll(&ctx->wqh, EPOLLIN);
 		}
 		spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 	}
@@ -226,20 +226,21 @@ static int timerfd_release(struct inode *inode, struct file *file)
 	kfree_rcu(ctx, rcu);
 	return 0;
 }
-	
-static struct wait_queue_head *timerfd_get_poll_head(struct file *file,
-		__poll_t eventmask)
+
+static __poll_t timerfd_poll(struct file *file, poll_table *wait)
 {
 	struct timerfd_ctx *ctx = file->private_data;
+	__poll_t events = 0;
+	unsigned long flags;
 
-	return &ctx->wqh;
-}
+	poll_wait(file, &ctx->wqh, wait);
 
-static __poll_t timerfd_poll_mask(struct file *file, __poll_t eventmask)
-{
-	struct timerfd_ctx *ctx = file->private_data;
+	spin_lock_irqsave(&ctx->wqh.lock, flags);
+	if (ctx->ticks)
+		events |= EPOLLIN;
+	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
-	return ctx->ticks ? EPOLLIN : 0;
+	return events;
 }
 
 static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
@@ -344,7 +345,7 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
 		spin_lock_irq(&ctx->wqh.lock);
 		if (!timerfd_canceled(ctx)) {
 			ctx->ticks = ticks;
-			wake_up_locked(&ctx->wqh);
+			wake_up_locked_poll(&ctx->wqh, EPOLLIN);
 		} else
 			ret = -ECANCELED;
 		spin_unlock_irq(&ctx->wqh.lock);
@@ -363,8 +364,7 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
 
 static const struct file_operations timerfd_fops = {
 	.release	= timerfd_release,
-	.get_poll_head	= timerfd_get_poll_head,
-	.poll_mask	= timerfd_poll_mask,
+	.poll		= timerfd_poll,
 	.read		= timerfd_read,
 	.llseek		= noop_llseek,
 	.show_fdinfo	= timerfd_show,
@@ -533,8 +533,8 @@ static int do_timerfd_gettime(int ufd, struct itimerspec64 *t)
 }
 
 SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
-		const struct itimerspec __user *, utmr,
-		struct itimerspec __user *, otmr)
+		const struct __kernel_itimerspec __user *, utmr,
+		struct __kernel_itimerspec __user *, otmr)
 {
 	struct itimerspec64 new, old;
 	int ret;
@@ -550,7 +550,7 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 	return ret;
 }
 
-SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
+SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, otmr)
 {
 	struct itimerspec64 kotmr;
 	int ret = do_timerfd_gettime(ufd, &kotmr);
@@ -559,7 +559,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
 	return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
 COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 		const struct compat_itimerspec __user *, utmr,
 		struct compat_itimerspec __user *, otmr)
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 06f37ddd2997..58cc2414992b 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -602,8 +602,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
 	fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err);
 	if (unlikely(!fi)) {
 		inode_dec_link_count(inode);
-		unlock_new_inode(inode);
-		iput(inode);
+		discard_new_inode(inode);
 		return err;
 	}
 	cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize);
@@ -694,8 +693,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	fi = udf_add_entry(inode, NULL, &fibh, &cfi, &err);
 	if (!fi) {
 		inode_dec_link_count(inode);
-		unlock_new_inode(inode);
-		iput(inode);
+		discard_new_inode(inode);
 		goto out;
 	}
 	set_nlink(inode, 2);
@@ -713,8 +711,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (!fi) {
 		clear_nlink(inode);
 		mark_inode_dirty(inode);
-		unlock_new_inode(inode);
-		iput(inode);
+		discard_new_inode(inode);
 		goto out;
 	}
 	cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize);
@@ -1041,8 +1038,7 @@ out:
 out_no_entry:
 	up_write(&iinfo->i_data_sem);
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	goto out;
 }
 
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index e1ef0f0a1353..02c0a4be4212 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -343,8 +343,7 @@ cg_found:
 fail_remove_inode:
 	mutex_unlock(&sbi->s_lock);
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
 	return ERR_PTR(err);
 failed:
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index d5f43ba76c59..9ef40f100415 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -43,8 +43,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode)
 		return 0;
 	}
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return err;
 }
 
@@ -142,8 +141,7 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry,
 
 out_fail:
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return err;
 }
 
@@ -198,8 +196,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 out_fail:
 	inode_dec_link_count(inode);
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput (inode);
+	discard_new_inode(inode);
 out_dir:
 	inode_dec_link_count(dir);
 	return err;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 123bf7d516fc..bad9cea37f12 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -222,24 +222,26 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 					 unsigned long reason)
 {
 	struct mm_struct *mm = ctx->mm;
-	pte_t *pte;
+	pte_t *ptep, pte;
 	bool ret = true;
 
 	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
-	pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
-	if (!pte)
+	ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
+
+	if (!ptep)
 		goto out;
 
 	ret = false;
+	pte = huge_ptep_get(ptep);
 
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
 	 * changes under us.
 	 */
-	if (huge_pte_none(*pte))
+	if (huge_pte_none(pte))
 		ret = true;
-	if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP))
+	if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
 		ret = true;
 out:
 	return ret;
@@ -631,8 +633,10 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 		/* the various vma->vm_userfaultfd_ctx still points to it */
 		down_write(&mm->mmap_sem);
 		for (vma = mm->mmap; vma; vma = vma->vm_next)
-			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx)
+			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+				vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+			}
 		up_write(&mm->mmap_sem);
 
 		userfaultfd_ctx_put(release_new_ctx);
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 2f3f75a7f180..7f96bdadc372 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -158,6 +158,7 @@ xfs-$(CONFIG_XFS_QUOTA)		+= scrub/quota.o
 ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
 xfs-y				+= $(addprefix scrub/, \
 				   agheader_repair.o \
+				   bitmap.o \
 				   repair.o \
 				   )
 endif
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 84db76e0e3e3..e701ebc36c06 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -157,6 +157,7 @@ __xfs_ag_resv_free(
 	error = xfs_mod_fdblocks(pag->pag_mount, oldresv, true);
 	resv->ar_reserved = 0;
 	resv->ar_asked = 0;
+	resv->ar_orig_reserved = 0;
 
 	if (error)
 		trace_xfs_ag_resv_free_error(pag->pag_mount, pag->pag_agno,
@@ -189,13 +190,34 @@ __xfs_ag_resv_init(
 	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_ag_resv		*resv;
 	int				error;
-	xfs_extlen_t			reserved;
+	xfs_extlen_t			hidden_space;
 
 	if (used > ask)
 		ask = used;
-	reserved = ask - used;
 
-	error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
+	switch (type) {
+	case XFS_AG_RESV_RMAPBT:
+		/*
+		 * Space taken by the rmapbt is not subtracted from fdblocks
+		 * because the rmapbt lives in the free space.  Here we must
+		 * subtract the entire reservation from fdblocks so that we
+		 * always have blocks available for rmapbt expansion.
+		 */
+		hidden_space = ask;
+		break;
+	case XFS_AG_RESV_METADATA:
+		/*
+		 * Space taken by all other metadata btrees are accounted
+		 * on-disk as used space.  We therefore only hide the space
+		 * that is reserved but not used by the trees.
+		 */
+		hidden_space = ask - used;
+		break;
+	default:
+		ASSERT(0);
+		return -EINVAL;
+	}
+	error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
 	if (error) {
 		trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
 				error, _RET_IP_);
@@ -216,7 +238,8 @@ __xfs_ag_resv_init(
 
 	resv = xfs_perag_resv(pag, type);
 	resv->ar_asked = ask;
-	resv->ar_reserved = resv->ar_orig_reserved = reserved;
+	resv->ar_orig_reserved = hidden_space;
+	resv->ar_reserved = ask - used;
 
 	trace_xfs_ag_resv_init(pag, type, ask);
 	return 0;
@@ -225,7 +248,8 @@ __xfs_ag_resv_init(
 /* Create a per-AG block reservation. */
 int
 xfs_ag_resv_init(
-	struct xfs_perag		*pag)
+	struct xfs_perag		*pag,
+	struct xfs_trans		*tp)
 {
 	struct xfs_mount		*mp = pag->pag_mount;
 	xfs_agnumber_t			agno = pag->pag_agno;
@@ -237,11 +261,11 @@ xfs_ag_resv_init(
 	if (pag->pag_meta_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_refcountbt_calc_reserves(mp, agno, &ask, &used);
+		error = xfs_refcountbt_calc_reserves(mp, tp, agno, &ask, &used);
 		if (error)
 			goto out;
 
-		error = xfs_finobt_calc_reserves(mp, agno, &ask, &used);
+		error = xfs_finobt_calc_reserves(mp, tp, agno, &ask, &used);
 		if (error)
 			goto out;
 
@@ -259,7 +283,7 @@ xfs_ag_resv_init(
 
 			mp->m_inotbt_nores = true;
 
-			error = xfs_refcountbt_calc_reserves(mp, agno, &ask,
+			error = xfs_refcountbt_calc_reserves(mp, tp, agno, &ask,
 					&used);
 			if (error)
 				goto out;
@@ -275,7 +299,7 @@ xfs_ag_resv_init(
 	if (pag->pag_rmapbt_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_rmapbt_calc_reserves(mp, agno, &ask, &used);
+		error = xfs_rmapbt_calc_reserves(mp, tp, agno, &ask, &used);
 		if (error)
 			goto out;
 
@@ -286,7 +310,7 @@ xfs_ag_resv_init(
 
 #ifdef DEBUG
 	/* need to read in the AGF for the ASSERT below to work */
-	error = xfs_alloc_pagf_init(pag->pag_mount, NULL, pag->pag_agno, 0);
+	error = xfs_alloc_pagf_init(pag->pag_mount, tp, pag->pag_agno, 0);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_ag_resv.h b/fs/xfs/libxfs/xfs_ag_resv.h
index 4619b554ee90..c0352edc8e41 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.h
+++ b/fs/xfs/libxfs/xfs_ag_resv.h
@@ -7,7 +7,7 @@
 #define	__XFS_AG_RESV_H__
 
 int xfs_ag_resv_free(struct xfs_perag *pag);
-int xfs_ag_resv_init(struct xfs_perag *pag);
+int xfs_ag_resv_init(struct xfs_perag *pag, struct xfs_trans *tp);
 
 bool xfs_ag_resv_critical(struct xfs_perag *pag, enum xfs_ag_resv_type type);
 xfs_extlen_t xfs_ag_resv_needed(struct xfs_perag *pag,
@@ -28,7 +28,7 @@ xfs_ag_resv_rmapbt_alloc(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
 {
-	struct xfs_alloc_arg	args = {0};
+	struct xfs_alloc_arg	args = { NULL };
 	struct xfs_perag	*pag;
 
 	args.len = 1;
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index eef466260d43..e1c0c0d2f1b0 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -223,12 +223,13 @@ xfs_alloc_get_rec(
 	error = xfs_btree_get_rec(cur, &rec, stat);
 	if (error || !(*stat))
 		return error;
-	if (rec->alloc.ar_blockcount == 0)
-		goto out_bad_rec;
 
 	*bno = be32_to_cpu(rec->alloc.ar_startblock);
 	*len = be32_to_cpu(rec->alloc.ar_blockcount);
 
+	if (*len == 0)
+		goto out_bad_rec;
+
 	/* check for valid extent range, including overflow */
 	if (!xfs_verify_agbno(mp, agno, *bno))
 		goto out_bad_rec;
@@ -2197,12 +2198,12 @@ xfs_agfl_reset(
  */
 STATIC void
 xfs_defer_agfl_block(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_agnumber_t			agno,
 	xfs_fsblock_t			agbno,
 	struct xfs_owner_info		*oinfo)
 {
+	struct xfs_mount		*mp = tp->t_mountp;
 	struct xfs_extent_free_item	*new;		/* new element */
 
 	ASSERT(xfs_bmap_free_item_zone != NULL);
@@ -2215,7 +2216,7 @@ xfs_defer_agfl_block(
 
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
 }
 
 /*
@@ -2322,16 +2323,8 @@ xfs_alloc_fix_freelist(
 		if (error)
 			goto out_agbp_relse;
 
-		/* defer agfl frees if dfops is provided */
-		if (tp->t_agfl_dfops) {
-			xfs_defer_agfl_block(mp, tp->t_agfl_dfops, args->agno,
-					     bno, &targs.oinfo);
-		} else {
-			error = xfs_free_agfl_block(tp, args->agno, bno, agbp,
-						    &targs.oinfo);
-			if (error)
-				goto out_agbp_relse;
-		}
+		/* defer agfl frees */
+		xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo);
 	}
 
 	targs.tp = tp;
@@ -2754,9 +2747,6 @@ xfs_alloc_read_agf(
 		pag->pagf_levels[XFS_BTNUM_RMAPi] =
 			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
 		pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
-		spin_lock_init(&pag->pagb_lock);
-		pag->pagb_count = 0;
-		pag->pagb_tree = RB_ROOT;
 		pag->pagf_init = 1;
 		pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
 	}
@@ -2783,16 +2773,16 @@ xfs_alloc_read_agf(
  */
 int				/* error */
 xfs_alloc_vextent(
-	xfs_alloc_arg_t	*args)	/* allocation argument structure */
+	struct xfs_alloc_arg	*args)	/* allocation argument structure */
 {
-	xfs_agblock_t	agsize;	/* allocation group size */
-	int		error;
-	int		flags;	/* XFS_ALLOC_FLAG_... locking flags */
-	xfs_mount_t	*mp;	/* mount structure pointer */
-	xfs_agnumber_t	sagno;	/* starting allocation group number */
-	xfs_alloctype_t	type;	/* input allocation type */
-	int		bump_rotor = 0;
-	xfs_agnumber_t	rotorstep = xfs_rotorstep; /* inode32 agf stepper */
+	xfs_agblock_t		agsize;	/* allocation group size */
+	int			error;
+	int			flags;	/* XFS_ALLOC_FLAG_... locking flags */
+	struct xfs_mount	*mp;	/* mount structure pointer */
+	xfs_agnumber_t		sagno;	/* starting allocation group number */
+	xfs_alloctype_t		type;	/* input allocation type */
+	int			bump_rotor = 0;
+	xfs_agnumber_t		rotorstep = xfs_rotorstep; /* inode32 agf stepper */
 
 	mp = args->mp;
 	type = args->otype = args->type;
@@ -2913,7 +2903,7 @@ xfs_alloc_vextent(
 			* locking of AGF, which might cause deadlock.
 			*/
 			if (++(args->agno) == mp->m_sb.sb_agcount) {
-				if (args->firstblock != NULLFSBLOCK)
+				if (args->tp->t_firstblock != NULLFSBLOCK)
 					args->agno = sagno;
 				else
 					args->agno = 0;
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index e716c993ac4c..00cd5ec4cb6b 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -74,7 +74,6 @@ typedef struct xfs_alloc_arg {
 	int		datatype;	/* mask defining data type treatment */
 	char		wasdel;		/* set if allocation was prev delayed */
 	char		wasfromfl;	/* set if allocation is from freelist */
-	xfs_fsblock_t	firstblock;	/* io first block allocated */
 	struct xfs_owner_info	oinfo;	/* owner of blocks being allocated */
 	enum xfs_ag_resv_type	resv;	/* block reservation to use */
 } xfs_alloc_arg_t;
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 99590f61d624..1e671d4eb6fa 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -202,9 +202,7 @@ xfs_attr_set(
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_buf		*leaf_bp = NULL;
 	struct xfs_da_args	args;
-	struct xfs_defer_ops	dfops;
 	struct xfs_trans_res	tres;
-	xfs_fsblock_t		firstblock;
 	int			rsvd = (flags & ATTR_ROOT) != 0;
 	int			error, err2, local;
 
@@ -219,8 +217,6 @@ xfs_attr_set(
 
 	args.value = value;
 	args.valuelen = valuelen;
-	args.firstblock = &firstblock;
-	args.dfops = &dfops;
 	args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 	args.total = xfs_attr_calc_size(&args, &local);
 
@@ -315,21 +311,18 @@ xfs_attr_set(
 		 * It won't fit in the shortform, transform to a leaf block.
 		 * GROT: another possible req'mt for a double-split btree op.
 		 */
-		xfs_defer_init(args.dfops, args.firstblock);
 		error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 		/*
 		 * Prevent the leaf buffer from being unlocked so that a
 		 * concurrent AIL push cannot grab the half-baked leaf
 		 * buffer and run into problems with the write verifier.
 		 */
 		xfs_trans_bhold(args.trans, leaf_bp);
-		xfs_defer_bjoin(args.dfops, leaf_bp);
-		xfs_defer_ijoin(args.dfops, dp);
-		error = xfs_defer_finish(&args.trans, args.dfops);
+		error = xfs_defer_finish(&args.trans);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 
 		/*
 		 * Commit the leaf transformation.  We'll need another (linked)
@@ -369,8 +362,6 @@ xfs_attr_set(
 
 	return error;
 
-out_defer_cancel:
-	xfs_defer_cancel(&dfops);
 out:
 	if (leaf_bp)
 		xfs_trans_brelse(args.trans, leaf_bp);
@@ -392,8 +383,6 @@ xfs_attr_remove(
 {
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_da_args	args;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		firstblock;
 	int			error;
 
 	XFS_STATS_INC(mp, xs_attr_remove);
@@ -405,9 +394,6 @@ xfs_attr_remove(
 	if (error)
 		return error;
 
-	args.firstblock = &firstblock;
-	args.dfops = &dfops;
-
 	/*
 	 * we have no control over the attribute names that userspace passes us
 	 * to remove, so we have to allow the name lookup prior to attribute
@@ -536,11 +522,12 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
  * if bmap_one_block() says there is only one block (ie: no remote blks).
  */
 STATIC int
-xfs_attr_leaf_addname(xfs_da_args_t *args)
+xfs_attr_leaf_addname(
+	struct xfs_da_args	*args)
 {
-	xfs_inode_t *dp;
-	struct xfs_buf *bp;
-	int retval, error, forkoff;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			retval, error, forkoff;
 
 	trace_xfs_attr_leaf_addname(args);
 
@@ -598,14 +585,12 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 		 * Commit that transaction so that the node_addname() call
 		 * can manage its own transactions.
 		 */
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 
 		/*
 		 * Commit the current trans (including the inode) and start
@@ -687,15 +672,13 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 		 * If the result is small enough, shrink it all into the inode.
 		 */
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->dfops, args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				return error;
 		}
 
 		/*
@@ -711,7 +694,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	}
 	return error;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans);
 	return error;
 }
 
@@ -722,11 +705,12 @@ out_defer_cancel:
  * if bmap_one_block() says there is only one block (ie: no remote blks).
  */
 STATIC int
-xfs_attr_leaf_removename(xfs_da_args_t *args)
+xfs_attr_leaf_removename(
+	struct xfs_da_args	*args)
 {
-	xfs_inode_t *dp;
-	struct xfs_buf *bp;
-	int error, forkoff;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			error, forkoff;
 
 	trace_xfs_attr_leaf_removename(args);
 
@@ -751,19 +735,17 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 	 * If the result is small enough, shrink it all into the inode.
 	 */
 	if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 	}
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans);
 	return error;
 }
 
@@ -814,13 +796,14 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
  * add a whole extra layer of confusion on top of that.
  */
 STATIC int
-xfs_attr_node_addname(xfs_da_args_t *args)
+xfs_attr_node_addname(
+	struct xfs_da_args	*args)
 {
-	xfs_da_state_t *state;
-	xfs_da_state_blk_t *blk;
-	xfs_inode_t *dp;
-	xfs_mount_t *mp;
-	int retval, error;
+	struct xfs_da_state	*state;
+	struct xfs_da_state_blk	*blk;
+	struct xfs_inode	*dp;
+	struct xfs_mount	*mp;
+	int			retval, error;
 
 	trace_xfs_attr_node_addname(args);
 
@@ -879,14 +862,12 @@ restart:
 			 */
 			xfs_da_state_free(state);
 			state = NULL;
-			xfs_defer_init(args->dfops, args->firstblock);
 			error = xfs_attr3_leaf_to_node(args);
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 
 			/*
 			 * Commit the node conversion and start the next
@@ -905,14 +886,12 @@ restart:
 		 * in the index/blkno/rmtblkno/rmtblkcnt fields and
 		 * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
 		 */
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_da3_split(state);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 	} else {
 		/*
 		 * Addition succeeded, update Btree hashvals.
@@ -1003,14 +982,12 @@ restart:
 		 * Check to see if the tree needs to be collapsed.
 		 */
 		if (retval && (state->path.active > 1)) {
-			xfs_defer_init(args->dfops, args->firstblock);
 			error = xfs_da3_join(state);
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 		}
 
 		/*
@@ -1037,7 +1014,7 @@ out:
 		return error;
 	return retval;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans);
 	goto out;
 }
 
@@ -1049,13 +1026,14 @@ out_defer_cancel:
  * the root node (a special case of an intermediate node).
  */
 STATIC int
-xfs_attr_node_removename(xfs_da_args_t *args)
+xfs_attr_node_removename(
+	struct xfs_da_args	*args)
 {
-	xfs_da_state_t *state;
-	xfs_da_state_blk_t *blk;
-	xfs_inode_t *dp;
-	struct xfs_buf *bp;
-	int retval, error, forkoff;
+	struct xfs_da_state	*state;
+	struct xfs_da_state_blk	*blk;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			retval, error, forkoff;
 
 	trace_xfs_attr_node_removename(args);
 
@@ -1127,14 +1105,12 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	 * Check to see if the tree needs to be collapsed.
 	 */
 	if (retval && (state->path.active > 1)) {
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_da3_join(state);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 		/*
 		 * Commit the Btree join operation and start a new trans.
 		 */
@@ -1159,15 +1135,13 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 			goto out;
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->dfops, args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 		} else
 			xfs_trans_brelse(args->trans, bp);
 	}
@@ -1177,7 +1151,7 @@ out:
 	xfs_da_state_free(state);
 	return error;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans);
 	goto out;
 }
 
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 76e90046731c..6fc5425b1474 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -242,8 +242,9 @@ xfs_attr3_leaf_verify(
 	struct xfs_attr3_icleaf_hdr	ichdr;
 	struct xfs_mount		*mp = bp->b_target->bt_mount;
 	struct xfs_attr_leafblock	*leaf = bp->b_addr;
-	struct xfs_perag		*pag = bp->b_pag;
 	struct xfs_attr_leaf_entry	*entries;
+	uint16_t			end;
+	int				i;
 
 	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
 
@@ -268,7 +269,7 @@ xfs_attr3_leaf_verify(
 	 * because we may have transitioned an empty shortform attr to a leaf
 	 * if the attr didn't fit in shortform.
 	 */
-	if (pag && pag->pagf_init && ichdr.count == 0)
+	if (!xfs_log_in_recovery(mp) && ichdr.count == 0)
 		return __this_address;
 
 	/*
@@ -289,6 +290,26 @@ xfs_attr3_leaf_verify(
 	/* XXX: need to range check rest of attr header values */
 	/* XXX: hash order check? */
 
+	/*
+	 * Quickly check the freemap information.  Attribute data has to be
+	 * aligned to 4-byte boundaries, and likewise for the free space.
+	 */
+	for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
+		if (ichdr.freemap[i].base > mp->m_attr_geo->blksize)
+			return __this_address;
+		if (ichdr.freemap[i].base & 0x3)
+			return __this_address;
+		if (ichdr.freemap[i].size > mp->m_attr_geo->blksize)
+			return __this_address;
+		if (ichdr.freemap[i].size & 0x3)
+			return __this_address;
+		end = ichdr.freemap[i].base + ichdr.freemap[i].size;
+		if (end < ichdr.freemap[i].base)
+			return __this_address;
+		if (end > mp->m_attr_geo->blksize)
+			return __this_address;
+	}
+
 	return NULL;
 }
 
@@ -506,7 +527,7 @@ xfs_attr_shortform_create(xfs_da_args_t *args)
 {
 	xfs_attr_sf_hdr_t *hdr;
 	xfs_inode_t *dp;
-	xfs_ifork_t *ifp;
+	struct xfs_ifork *ifp;
 
 	trace_xfs_attr_sf_create(args);
 
@@ -541,7 +562,7 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
 	int i, offset, size;
 	xfs_mount_t *mp;
 	xfs_inode_t *dp;
-	xfs_ifork_t *ifp;
+	struct xfs_ifork *ifp;
 
 	trace_xfs_attr_sf_add(args);
 
@@ -682,7 +703,7 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
 	xfs_attr_shortform_t *sf;
 	xfs_attr_sf_entry_t *sfe;
 	int i;
-	xfs_ifork_t *ifp;
+	struct xfs_ifork *ifp;
 
 	trace_xfs_attr_sf_lookup(args);
 
@@ -747,18 +768,18 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args)
  */
 int
 xfs_attr_shortform_to_leaf(
-	struct xfs_da_args	*args,
-	struct xfs_buf		**leaf_bp)
+	struct xfs_da_args		*args,
+	struct xfs_buf			**leaf_bp)
 {
-	xfs_inode_t *dp;
-	xfs_attr_shortform_t *sf;
-	xfs_attr_sf_entry_t *sfe;
-	xfs_da_args_t nargs;
-	char *tmpbuffer;
-	int error, i, size;
-	xfs_dablk_t blkno;
-	struct xfs_buf *bp;
-	xfs_ifork_t *ifp;
+	struct xfs_inode		*dp;
+	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_entry	*sfe;
+	struct xfs_da_args		nargs;
+	char				*tmpbuffer;
+	int				error, i, size;
+	xfs_dablk_t			blkno;
+	struct xfs_buf			*bp;
+	struct xfs_ifork		*ifp;
 
 	trace_xfs_attr_sf_to_leaf(args);
 
@@ -802,8 +823,6 @@ xfs_attr_shortform_to_leaf(
 	memset((char *)&nargs, 0, sizeof(nargs));
 	nargs.dp = dp;
 	nargs.geo = args->geo;
-	nargs.firstblock = args->firstblock;
-	nargs.dfops = args->dfops;
 	nargs.total = args->total;
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
@@ -1006,8 +1025,6 @@ xfs_attr3_leaf_to_shortform(
 	memset((char *)&nargs, 0, sizeof(nargs));
 	nargs.geo = args->geo;
 	nargs.dp = dp;
-	nargs.firstblock = args->firstblock;
-	nargs.dfops = args->dfops;
 	nargs.total = args->total;
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
@@ -1570,17 +1587,10 @@ xfs_attr3_leaf_rebalance(
 	 */
 	swap = 0;
 	if (xfs_attr3_leaf_order(blk1->bp, &ichdr1, blk2->bp, &ichdr2)) {
-		struct xfs_da_state_blk	*tmp_blk;
-		struct xfs_attr3_icleaf_hdr tmp_ichdr;
-
-		tmp_blk = blk1;
-		blk1 = blk2;
-		blk2 = tmp_blk;
+		swap(blk1, blk2);
 
-		/* struct copies to swap them rather than reconverting */
-		tmp_ichdr = ichdr1;
-		ichdr1 = ichdr2;
-		ichdr2 = tmp_ichdr;
+		/* swap structures rather than reconverting them */
+		swap(ichdr1, ichdr2);
 
 		leaf1 = blk1->bp->b_addr;
 		leaf2 = blk2->bp->b_addr;
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index bf2e0371149b..af094063e402 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -480,17 +480,15 @@ xfs_attr_rmtval_set(
 		 * extent and then crash then the block may not contain the
 		 * correct metadata after log recovery occurs.
 		 */
-		xfs_defer_init(args->dfops, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
-				  args->total, &map, &nmap, args->dfops);
+				  blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
+				  &nmap);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 
 		ASSERT(nmap == 1);
 		ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
@@ -522,7 +520,6 @@ xfs_attr_rmtval_set(
 
 		ASSERT(blkcnt > 0);
 
-		xfs_defer_init(args->dfops, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
 				       blkcnt, &map, &nmap,
@@ -557,8 +554,7 @@ xfs_attr_rmtval_set(
 	ASSERT(valuelen == 0);
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
-	args->trans = NULL;
+	xfs_defer_cancel(args->trans);
 	return error;
 }
 
@@ -626,16 +622,13 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	done = 0;
 	while (!done) {
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
-				    XFS_BMAPI_ATTRFORK, 1, args->firstblock,
-				    args->dfops, &done);
+				    XFS_BMAPI_ATTRFORK, 1, &done);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, args->dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 
 		/*
 		 * Close out trans and start the next one in the chain.
@@ -646,7 +639,6 @@ xfs_attr_rmtval_remove(
 	}
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
-	args->trans = NULL;
+	xfs_defer_cancel(args->trans);
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 01628f0c9a0c..2760314fdf7f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -326,7 +326,7 @@ xfs_bmap_check_leaf_extents(
 	xfs_buf_t		*bp;	/* buffer for "block" */
 	int			error;	/* error return value */
 	xfs_extnum_t		i=0, j;	/* index into the extents list */
-	xfs_ifork_t		*ifp;	/* fork structure */
+	struct xfs_ifork	*ifp;	/* fork structure */
 	int			level;	/* btree level, for checking */
 	xfs_mount_t		*mp;	/* file system mount structure */
 	__be64			*pp;	/* pointer to block address */
@@ -533,8 +533,7 @@ xfs_bmap_validate_ret(
  */
 void
 __xfs_bmap_add_free(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	struct xfs_owner_info		*oinfo,
@@ -542,8 +541,9 @@ __xfs_bmap_add_free(
 {
 	struct xfs_extent_free_item	*new;		/* new element */
 #ifdef DEBUG
-	xfs_agnumber_t		agno;
-	xfs_agblock_t		agbno;
+	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
 
 	ASSERT(bno != NULLFSBLOCK);
 	ASSERT(len > 0);
@@ -566,9 +566,10 @@ __xfs_bmap_add_free(
 	else
 		xfs_rmap_skip_owner_update(&new->xefi_oinfo);
 	new->xefi_skip_discard = skip_discard;
-	trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(mp, bno), 0,
-			XFS_FSB_TO_AGBNO(mp, bno), len);
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
+	trace_xfs_bmap_free_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
+			XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
 }
 
 /*
@@ -594,7 +595,7 @@ xfs_bmap_btree_to_extents(
 	xfs_fsblock_t		cbno;	/* child block number */
 	xfs_buf_t		*cbp;	/* child block's buffer */
 	int			error;	/* error return value */
-	xfs_ifork_t		*ifp;	/* inode fork data */
+	struct xfs_ifork	*ifp;	/* inode fork data */
 	xfs_mount_t		*mp;	/* mount point structure */
 	__be64			*pp;	/* ptr to block address */
 	struct xfs_btree_block	*rblock;/* root btree block */
@@ -624,7 +625,7 @@ xfs_bmap_btree_to_extents(
 	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
 		return error;
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, cbno, 1, &oinfo);
+	xfs_bmap_add_free(cur->bc_tp, cbno, 1, &oinfo);
 	ip->i_d.di_nblocks--;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
 	xfs_trans_binval(tp, cbp);
@@ -644,25 +645,23 @@ xfs_bmap_btree_to_extents(
  */
 STATIC int					/* error */
 xfs_bmap_extents_to_btree(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first-block-allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks freed in xaction */
-	xfs_btree_cur_t		**curp,		/* cursor returned to caller */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode pointer */
+	struct xfs_btree_cur	**curp,		/* cursor returned to caller */
 	int			wasdel,		/* converting a delayed alloc */
 	int			*logflagsp,	/* inode logging flags */
 	int			whichfork)	/* data or attr fork */
 {
 	struct xfs_btree_block	*ablock;	/* allocated (child) bt block */
-	xfs_buf_t		*abp;		/* buffer for ablock */
-	xfs_alloc_arg_t		args;		/* allocation arguments */
-	xfs_bmbt_rec_t		*arp;		/* child record pointer */
+	struct xfs_buf		*abp;		/* buffer for ablock */
+	struct xfs_alloc_arg	args;		/* allocation arguments */
+	struct xfs_bmbt_rec	*arp;		/* child record pointer */
 	struct xfs_btree_block	*block;		/* btree root block */
-	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
+	struct xfs_btree_cur	*cur;		/* bmap btree cursor */
 	int			error;		/* error return value */
-	xfs_ifork_t		*ifp;		/* inode fork pointer */
-	xfs_bmbt_key_t		*kp;		/* root block key pointer */
-	xfs_mount_t		*mp;		/* mount structure */
+	struct xfs_ifork	*ifp;		/* inode fork pointer */
+	struct xfs_bmbt_key	*kp;		/* root block key pointer */
+	struct xfs_mount	*mp;		/* mount structure */
 	xfs_bmbt_ptr_t		*pp;		/* root block address pointer */
 	struct xfs_iext_cursor	icur;
 	struct xfs_bmbt_irec	rec;
@@ -690,8 +689,6 @@ xfs_bmap_extents_to_btree(
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
 	cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-	cur->bc_private.b.firstblock = *firstblock;
-	cur->bc_private.b.dfops = dfops;
 	cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
 	/*
 	 * Convert to a btree with two levels, one record in root.
@@ -701,45 +698,43 @@ xfs_bmap_extents_to_btree(
 	args.tp = tp;
 	args.mp = mp;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);
-	args.firstblock = *firstblock;
-	if (*firstblock == NULLFSBLOCK) {
+	if (tp->t_firstblock == NULLFSBLOCK) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
-	} else if (dfops->dop_low) {
+	} else if (tp->t_flags & XFS_TRANS_LOWMODE) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
-		args.fsbno = *firstblock;
+		args.fsbno = tp->t_firstblock;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-		args.fsbno = *firstblock;
+		args.fsbno = tp->t_firstblock;
 	}
 	args.minlen = args.maxlen = args.prod = 1;
 	args.wasdel = wasdel;
 	*logflagsp = 0;
 	if ((error = xfs_alloc_vextent(&args))) {
-		xfs_iroot_realloc(ip, -1, whichfork);
 		ASSERT(ifp->if_broot == NULL);
-		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
-		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-		return error;
+		goto err1;
 	}
 
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
-		xfs_iroot_realloc(ip, -1, whichfork);
 		ASSERT(ifp->if_broot == NULL);
-		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
-		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-		return -ENOSPC;
+		error = -ENOSPC;
+		goto err1;
 	}
 	/*
 	 * Allocation can't fail, the space was reserved.
 	 */
-	ASSERT(*firstblock == NULLFSBLOCK ||
-	       args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
-	*firstblock = cur->bc_private.b.firstblock = args.fsbno;
+	ASSERT(tp->t_firstblock == NULLFSBLOCK ||
+	       args.agno >= XFS_FSB_TO_AGNO(mp, tp->t_firstblock));
+	tp->t_firstblock = args.fsbno;
 	cur->bc_private.b.allocated++;
 	ip->i_d.di_nblocks++;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
 	abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0);
+	if (!abp) {
+		error = -ENOSPC;
+		goto err2;
+	}
 	/*
 	 * Fill in the child block.
 	 */
@@ -779,6 +774,15 @@ xfs_bmap_extents_to_btree(
 	*curp = cur;
 	*logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork);
 	return 0;
+
+err2:
+	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
+err1:
+	xfs_iroot_realloc(ip, -1, whichfork);
+	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
+	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+
+	return error;
 }
 
 /*
@@ -812,7 +816,6 @@ STATIC int				/* error */
 xfs_bmap_local_to_extents(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_inode_t	*ip,		/* incore inode pointer */
-	xfs_fsblock_t	*firstblock,	/* first block allocated in xaction */
 	xfs_extlen_t	total,		/* total blocks needed by transaction */
 	int		*logflagsp,	/* inode logging flags */
 	int		whichfork,
@@ -823,7 +826,7 @@ xfs_bmap_local_to_extents(
 {
 	int		error = 0;
 	int		flags;		/* logging flags returned */
-	xfs_ifork_t	*ifp;		/* inode fork pointer */
+	struct xfs_ifork *ifp;		/* inode fork pointer */
 	xfs_alloc_arg_t	args;		/* allocation arguments */
 	xfs_buf_t	*bp;		/* buffer for extent block */
 	struct xfs_bmbt_irec rec;
@@ -850,16 +853,15 @@ xfs_bmap_local_to_extents(
 	args.tp = tp;
 	args.mp = ip->i_mount;
 	xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);
-	args.firstblock = *firstblock;
 	/*
 	 * Allocate a block.  We know we need only one, since the
 	 * file currently fits in an inode.
 	 */
-	if (*firstblock == NULLFSBLOCK) {
+	if (tp->t_firstblock == NULLFSBLOCK) {
 		args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
-		args.fsbno = *firstblock;
+		args.fsbno = tp->t_firstblock;
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
 	}
 	args.total = total;
@@ -871,7 +873,7 @@ xfs_bmap_local_to_extents(
 	/* Can't fail, the space was reserved. */
 	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(args.len == 1);
-	*firstblock = args.fsbno;
+	tp->t_firstblock = args.fsbno;
 	bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
 
 	/*
@@ -917,8 +919,6 @@ STATIC int					/* error */
 xfs_bmap_add_attrfork_btree(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* btree cursor */
@@ -931,8 +931,6 @@ xfs_bmap_add_attrfork_btree(
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
-		cur->bc_private.b.dfops = dfops;
-		cur->bc_private.b.firstblock = *firstblock;
 		error = xfs_bmbt_lookup_first(cur, &stat);
 		if (error)
 			goto error0;
@@ -944,7 +942,6 @@ xfs_bmap_add_attrfork_btree(
 			xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 			return -ENOSPC;
 		}
-		*firstblock = cur->bc_private.b.firstblock;
 		cur->bc_private.b.allocated = 0;
 		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 	}
@@ -959,10 +956,8 @@ error0:
  */
 STATIC int					/* error */
 xfs_bmap_add_attrfork_extents(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode pointer */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
@@ -971,12 +966,11 @@ xfs_bmap_add_attrfork_extents(
 	if (ip->i_d.di_nextents * sizeof(xfs_bmbt_rec_t) <= XFS_IFORK_DSIZE(ip))
 		return 0;
 	cur = NULL;
-	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops, &cur, 0,
-		flags, XFS_DATA_FORK);
+	error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, flags,
+					  XFS_DATA_FORK);
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	}
 	return error;
 }
@@ -994,13 +988,11 @@ xfs_bmap_add_attrfork_extents(
  */
 STATIC int					/* error */
 xfs_bmap_add_attrfork_local(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode pointer */
 	int			*flags)		/* inode logging flags */
 {
-	xfs_da_args_t		dargs;		/* args for dir/attr code */
+	struct xfs_da_args	dargs;		/* args for dir/attr code */
 
 	if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
 		return 0;
@@ -1009,8 +1001,6 @@ xfs_bmap_add_attrfork_local(
 		memset(&dargs, 0, sizeof(dargs));
 		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
-		dargs.firstblock = firstblock;
-		dargs.dfops = dfops;
 		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
@@ -1018,8 +1008,8 @@ xfs_bmap_add_attrfork_local(
 	}
 
 	if (S_ISLNK(VFS_I(ip)->i_mode))
-		return xfs_bmap_local_to_extents(tp, ip, firstblock, 1,
-						 flags, XFS_DATA_FORK,
+		return xfs_bmap_local_to_extents(tp, ip, 1, flags,
+						 XFS_DATA_FORK,
 						 xfs_symlink_local_to_remote);
 
 	/* should only be called for types that support local format data */
@@ -1037,8 +1027,6 @@ xfs_bmap_add_attrfork(
 	int			size,		/* space new attribute needs */
 	int			rsvd)		/* xact may use reserved blks */
 {
-	xfs_fsblock_t		firstblock;	/* 1st block/ag allocated */
-	struct xfs_defer_ops	dfops;		/* freed extent records */
 	xfs_mount_t		*mp;		/* mount structure */
 	xfs_trans_t		*tp;		/* transaction pointer */
 	int			blks;		/* space reservation */
@@ -1104,19 +1092,15 @@ xfs_bmap_add_attrfork(
 	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
 	ip->i_afp->if_flags = XFS_IFEXTENTS;
 	logflags = 0;
-	xfs_defer_init(&dfops, &firstblock);
 	switch (ip->i_d.di_format) {
 	case XFS_DINODE_FMT_LOCAL:
-		error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &dfops,
-			&logflags);
+		error = xfs_bmap_add_attrfork_local(tp, ip, &logflags);
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
-		error = xfs_bmap_add_attrfork_extents(tp, ip, &firstblock,
-			&dfops, &logflags);
+		error = xfs_bmap_add_attrfork_extents(tp, ip, &logflags);
 		break;
 	case XFS_DINODE_FMT_BTREE:
-		error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock, &dfops,
-			&logflags);
+		error = xfs_bmap_add_attrfork_btree(tp, ip, &logflags);
 		break;
 	default:
 		error = 0;
@@ -1125,7 +1109,7 @@ xfs_bmap_add_attrfork(
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	if (error)
-		goto bmap_cancel;
+		goto trans_cancel;
 	if (!xfs_sb_version_hasattr(&mp->m_sb) ||
 	   (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
 		bool log_sb = false;
@@ -1144,15 +1128,10 @@ xfs_bmap_add_attrfork(
 			xfs_log_sb(tp);
 	}
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto bmap_cancel;
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 
-bmap_cancel:
-	xfs_defer_cancel(&dfops);
 trans_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1501,7 +1480,7 @@ xfs_bmap_one_block(
 	xfs_inode_t	*ip,		/* incore inode */
 	int		whichfork)	/* data or attr fork */
 {
-	xfs_ifork_t	*ifp;		/* inode fork pointer */
+	struct xfs_ifork *ifp;		/* inode fork pointer */
 	int		rval;		/* return value */
 	xfs_bmbt_irec_t	s;		/* internal version of extent */
 	struct xfs_iext_cursor icur;
@@ -1539,7 +1518,7 @@ xfs_bmap_add_extent_delay_real(
 	struct xfs_bmbt_irec	*new = &bma->got;
 	int			error;	/* error return value */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_fileoff_t		new_endoff;	/* end offset of new entry */
 	xfs_bmbt_irec_t		r[3];	/* neighbor extent entries */
 					/* left is 0, right is 1, prev is 2 */
@@ -1809,7 +1788,6 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->dfops,
 					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -1887,8 +1865,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->dfops, &bma->cur, 1,
-				&tmp_rval, whichfork);
+				&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1968,8 +1945,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->dfops, &bma->cur,
-					1, &tmp_rval, whichfork);
+					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1994,8 +1970,7 @@ xfs_bmap_add_extent_delay_real(
 
 	/* add reverse mapping unless caller opted out */
 	if (!(bma->flags & XFS_BMAPI_NORMAP)) {
-		error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip,
-				whichfork, new);
+		error = xfs_rmap_map_extent(bma->tp, bma->ip, whichfork, new);
 		if (error)
 			goto done;
 	}
@@ -2006,8 +1981,8 @@ xfs_bmap_add_extent_delay_real(
 
 		ASSERT(bma->cur == NULL);
 		error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->dfops, &bma->cur,
-				da_old > 0, &tmp_logflags, whichfork);
+				&bma->cur, da_old > 0, &tmp_logflags,
+				whichfork);
 		bma->logflags |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2046,14 +2021,12 @@ xfs_bmap_add_extent_unwritten_real(
 	struct xfs_iext_cursor	*icur,
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
-	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
-	struct xfs_defer_ops	*dfops,	/* list of extents to be freed */
 	int			*logflagsp) /* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;	/* btree cursor */
 	int			error;	/* error return value */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_fileoff_t		new_endoff;	/* end offset of new entry */
 	xfs_bmbt_irec_t		r[3];	/* neighbor extent entries */
 					/* left is 0, right is 1, prev is 2 */
@@ -2479,7 +2452,7 @@ xfs_bmap_add_extent_unwritten_real(
 	}
 
 	/* update reverse mappings */
-	error = xfs_rmap_convert_extent(mp, dfops, ip, whichfork, new);
+	error = xfs_rmap_convert_extent(mp, tp, ip, whichfork, new);
 	if (error)
 		goto done;
 
@@ -2488,8 +2461,8 @@ xfs_bmap_add_extent_unwritten_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, &cur,
-				0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
+				&tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2520,7 +2493,7 @@ xfs_bmap_add_extent_hole_delay(
 	struct xfs_iext_cursor	*icur,
 	xfs_bmbt_irec_t		*new)	/* new data to add to file extents */
 {
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_bmbt_irec_t		left;	/* left neighbor extent entry */
 	xfs_filblks_t		newlen=0;	/* new indirect size */
 	xfs_filblks_t		oldlen=0;	/* old indirect size */
@@ -2660,8 +2633,6 @@ xfs_bmap_add_extent_hole_real(
 	struct xfs_iext_cursor	*icur,
 	struct xfs_btree_cur	**curp,
 	struct xfs_bmbt_irec	*new,
-	xfs_fsblock_t		*first,
-	struct xfs_defer_ops	*dfops,
 	int			*logflagsp,
 	int			flags)
 {
@@ -2842,7 +2813,7 @@ xfs_bmap_add_extent_hole_real(
 
 	/* add reverse mapping unless caller opted out */
 	if (!(flags & XFS_BMAPI_NORMAP)) {
-		error = xfs_rmap_map_extent(mp, dfops, ip, whichfork, new);
+		error = xfs_rmap_map_extent(tp, ip, whichfork, new);
 		if (error)
 			goto done;
 	}
@@ -2852,8 +2823,8 @@ xfs_bmap_add_extent_hole_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, curp,
-				0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, curp, 0,
+				&tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		cur = *curp;
 		if (error)
@@ -3071,10 +3042,11 @@ xfs_bmap_adjacent(
 		XFS_FSB_TO_AGBNO(mp, x) < mp->m_sb.sb_agblocks)
 
 	mp = ap->ip->i_mount;
-	nullfb = *ap->firstblock == NULLFSBLOCK;
+	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
 	rt = XFS_IS_REALTIME_INODE(ap->ip) &&
 		xfs_alloc_is_userdata(ap->datatype);
-	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
+	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
+							ap->tp->t_firstblock);
 	/*
 	 * If allocating at eof, and there's a previous real block,
 	 * try to use its last block as our starting point.
@@ -3432,8 +3404,9 @@ xfs_bmap_btalloc(
 	}
 
 
-	nullfb = *ap->firstblock == NULLFSBLOCK;
-	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
+	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
+	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
+							ap->tp->t_firstblock);
 	if (nullfb) {
 		if (xfs_alloc_is_userdata(ap->datatype) &&
 		    xfs_inode_is_filestream(ap->ip)) {
@@ -3444,7 +3417,7 @@ xfs_bmap_btalloc(
 			ap->blkno = XFS_INO_TO_FSB(mp, ap->ip->i_ino);
 		}
 	} else
-		ap->blkno = *ap->firstblock;
+		ap->blkno = ap->tp->t_firstblock;
 
 	xfs_bmap_adjacent(ap);
 
@@ -3455,7 +3428,7 @@ xfs_bmap_btalloc(
 	if (nullfb || XFS_FSB_TO_AGNO(mp, ap->blkno) == fb_agno)
 		;
 	else
-		ap->blkno = *ap->firstblock;
+		ap->blkno = ap->tp->t_firstblock;
 	/*
 	 * Normal allocation, done through xfs_alloc_vextent.
 	 */
@@ -3468,7 +3441,6 @@ xfs_bmap_btalloc(
 
 	/* Trim the allocation back to the maximum an AG can fit. */
 	args.maxlen = min(ap->length, mp->m_ag_max_usable);
-	args.firstblock = *ap->firstblock;
 	blen = 0;
 	if (nullfb) {
 		/*
@@ -3483,7 +3455,7 @@ xfs_bmap_btalloc(
 			error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
 		if (error)
 			return error;
-	} else if (ap->dfops->dop_low) {
+	} else if (ap->tp->t_flags & XFS_TRANS_LOWMODE) {
 		if (xfs_inode_is_filestream(ap->ip))
 			args.type = XFS_ALLOCTYPE_FIRST_AG;
 		else
@@ -3518,7 +3490,7 @@ xfs_bmap_btalloc(
 	 * is >= the stripe unit and the allocation offset is
 	 * at the end of file.
 	 */
-	if (!ap->dfops->dop_low && ap->aeof) {
+	if (!(ap->tp->t_flags & XFS_TRANS_LOWMODE) && ap->aeof) {
 		if (!ap->offset) {
 			args.alignment = stripe_align;
 			atype = args.type;
@@ -3610,20 +3582,20 @@ xfs_bmap_btalloc(
 		args.total = ap->minlen;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
-		ap->dfops->dop_low = true;
+		ap->tp->t_flags |= XFS_TRANS_LOWMODE;
 	}
 	if (args.fsbno != NULLFSBLOCK) {
 		/*
 		 * check the allocation happened at the same or higher AG than
 		 * the first block that was allocated.
 		 */
-		ASSERT(*ap->firstblock == NULLFSBLOCK ||
-		       XFS_FSB_TO_AGNO(mp, *ap->firstblock) <=
+		ASSERT(ap->tp->t_firstblock == NULLFSBLOCK ||
+		       XFS_FSB_TO_AGNO(mp, ap->tp->t_firstblock) <=
 		       XFS_FSB_TO_AGNO(mp, args.fsbno));
 
 		ap->blkno = args.fsbno;
-		if (*ap->firstblock == NULLFSBLOCK)
-			*ap->firstblock = args.fsbno;
+		if (ap->tp->t_firstblock == NULLFSBLOCK)
+			ap->tp->t_firstblock = args.fsbno;
 		ASSERT(nullfb || fb_agno <= args.agno);
 		ap->length = args.len;
 		/*
@@ -3788,8 +3760,7 @@ xfs_bmapi_update_map(
 		   mval[-1].br_startblock != HOLESTARTBLOCK &&
 		   mval->br_startblock == mval[-1].br_startblock +
 					  mval[-1].br_blockcount &&
-		   ((flags & XFS_BMAPI_IGSTATE) ||
-			mval[-1].br_state == mval->br_state)) {
+		   mval[-1].br_state == mval->br_state) {
 		ASSERT(mval->br_startoff ==
 		       mval[-1].br_startoff + mval[-1].br_blockcount);
 		mval[-1].br_blockcount += mval->br_blockcount;
@@ -3834,7 +3805,7 @@ xfs_bmapi_read(
 
 	ASSERT(*nmap >= 1);
 	ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK|XFS_BMAPI_ENTIRE|
-			   XFS_BMAPI_IGSTATE|XFS_BMAPI_COWFORK)));
+			   XFS_BMAPI_COWFORK)));
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL));
 
 	if (unlikely(XFS_TEST_ERROR(
@@ -4079,15 +4050,10 @@ xfs_bmapi_allocate(
 	if (error)
 		return error;
 
-	if (bma->cur)
-		bma->cur->bc_private.b.firstblock = *bma->firstblock;
 	if (bma->blkno == NULLFSBLOCK)
 		return 0;
-	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
+	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur)
 		bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork);
-		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.dfops = bma->dfops;
-	}
 	/*
 	 * Bump the number of extents we've allocated
 	 * in this call.
@@ -4122,8 +4088,7 @@ xfs_bmapi_allocate(
 	else
 		error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
 				whichfork, &bma->icur, &bma->cur, &bma->got,
-				bma->firstblock, bma->dfops, &bma->logflags,
-				bma->flags);
+				&bma->logflags, bma->flags);
 
 	bma->logflags |= tmp_logflags;
 	if (error)
@@ -4174,8 +4139,6 @@ xfs_bmapi_convert_unwritten(
 	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
 		bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp,
 					bma->ip, whichfork);
-		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.dfops = bma->dfops;
 	}
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
@@ -4192,8 +4155,7 @@ xfs_bmapi_convert_unwritten(
 	}
 
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork,
-			&bma->icur, &bma->cur, mval, bma->firstblock,
-			bma->dfops, &tmp_logflags);
+			&bma->icur, &bma->cur, mval, &tmp_logflags);
 	/*
 	 * Log the inode core unconditionally in the unwritten extent conversion
 	 * path because the conversion might not have done so (e.g., if the
@@ -4231,12 +4193,6 @@ xfs_bmapi_convert_unwritten(
  * extent state if necessary.  Details behaviour is controlled by the flags
  * parameter.  Only allocates blocks from a single allocation group, to avoid
  * locking problems.
- *
- * The returned value in "firstblock" from the first call in a transaction
- * must be remembered and presented to subsequent calls in "firstblock".
- * An upper bound for the number of blocks to be allocated is supplied to
- * the first call in "total"; if no allocation group has that many free
- * blocks then the call will fail (return NULLFSBLOCK in "firstblock").
  */
 int
 xfs_bmapi_write(
@@ -4245,12 +4201,9 @@ xfs_bmapi_write(
 	xfs_fileoff_t		bno,		/* starting file offs. mapped */
 	xfs_filblks_t		len,		/* length to map in file */
 	int			flags,		/* XFS_BMAPI_... */
-	xfs_fsblock_t		*firstblock,	/* first allocated block
-						   controls a.g. for allocs */
 	xfs_extlen_t		total,		/* total blocks needed */
 	struct xfs_bmbt_irec	*mval,		/* output: map values */
-	int			*nmap,		/* i/o: mval size/count */
-	struct xfs_defer_ops	*dfops)		/* i/o: list extents to free */
+	int			*nmap)		/* i/o: mval size/count */
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
@@ -4279,7 +4232,6 @@ xfs_bmapi_write(
 
 	ASSERT(*nmap >= 1);
 	ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
-	ASSERT(!(flags & XFS_BMAPI_IGSTATE));
 	ASSERT(tp != NULL ||
 	       (flags & (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)) ==
 			(XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK));
@@ -4315,7 +4267,7 @@ xfs_bmapi_write(
 
 	XFS_STATS_INC(mp, xs_blk_mapw);
 
-	if (*firstblock == NULLFSBLOCK) {
+	if (!tp || tp->t_firstblock == NULLFSBLOCK) {
 		if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE)
 			bma.minleft = be16_to_cpu(ifp->if_broot->bb_level) + 1;
 		else
@@ -4342,8 +4294,6 @@ xfs_bmapi_write(
 	bma.ip = ip;
 	bma.total = total;
 	bma.datatype = 0;
-	bma.dfops = dfops;
-	bma.firstblock = firstblock;
 
 	while (bno < end && n < *nmap) {
 		bool			need_alloc = false, wasdelay = false;
@@ -4419,7 +4369,7 @@ xfs_bmapi_write(
 			 * the refcount btree for orphan recovery.
 			 */
 			if (whichfork == XFS_COW_FORK) {
-				error = xfs_refcount_alloc_cow_extent(mp, dfops,
+				error = xfs_refcount_alloc_cow_extent(tp,
 						bma.blkno, bma.length);
 				if (error)
 					goto error0;
@@ -4493,15 +4443,7 @@ error0:
 		xfs_trans_log_inode(tp, ip, bma.logflags);
 
 	if (bma.cur) {
-		if (!error) {
-			ASSERT(*firstblock == NULLFSBLOCK ||
-			       XFS_FSB_TO_AGNO(mp, *firstblock) <=
-			       XFS_FSB_TO_AGNO(mp,
-				       bma.cur->bc_private.b.firstblock));
-			*firstblock = bma.cur->bc_private.b.firstblock;
-		}
-		xfs_btree_del_cursor(bma.cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(bma.cur, error);
 	}
 	if (!error)
 		xfs_bmap_validate_ret(orig_bno, orig_len, orig_flags, orig_mval,
@@ -4516,13 +4458,11 @@ xfs_bmapi_remap(
 	xfs_fileoff_t		bno,
 	xfs_filblks_t		len,
 	xfs_fsblock_t		startblock,
-	struct xfs_defer_ops	*dfops,
 	int			flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
 	struct xfs_btree_cur	*cur = NULL;
-	xfs_fsblock_t		firstblock = NULLFSBLOCK;
 	struct xfs_bmbt_irec	got;
 	struct xfs_iext_cursor	icur;
 	int			whichfork = xfs_bmapi_whichfork(flags);
@@ -4565,8 +4505,6 @@ xfs_bmapi_remap(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = firstblock;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -4579,7 +4517,7 @@ xfs_bmapi_remap(
 		got.br_state = XFS_EXT_NORM;
 
 	error = xfs_bmap_add_extent_hole_real(tp, ip, whichfork, &icur,
-			&cur, &got, &firstblock, dfops, &logflags, flags);
+			&cur, &got, &logflags, flags);
 	if (error)
 		goto error0;
 
@@ -4599,10 +4537,8 @@ error0:
 
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
-	if (cur) {
-		xfs_btree_del_cursor(cur,
-				error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
-	}
+	if (cur)
+		xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -4898,7 +4834,6 @@ xfs_bmap_del_extent_real(
 	xfs_inode_t		*ip,	/* incore inode pointer */
 	xfs_trans_t		*tp,	/* current transaction pointer */
 	struct xfs_iext_cursor	*icur,
-	struct xfs_defer_ops	*dfops,	/* list of extents to be freed */
 	xfs_btree_cur_t		*cur,	/* if null, not a btree */
 	xfs_bmbt_irec_t		*del,	/* data to remove from extents */
 	int			*logflagsp, /* inode logging flags */
@@ -4913,7 +4848,7 @@ xfs_bmap_del_extent_real(
 	struct xfs_bmbt_irec	got;	/* current extent entry */
 	xfs_fileoff_t		got_endoff;	/* first offset past got */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_mount_t		*mp;	/* mount structure */
 	xfs_filblks_t		nblks;	/* quota/sb block count */
 	xfs_bmbt_irec_t		new;	/* new record to be inserted */
@@ -5104,7 +5039,7 @@ xfs_bmap_del_extent_real(
 	}
 
 	/* remove reverse mapping */
-	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, del);
+	error = xfs_rmap_unmap_extent(tp, ip, whichfork, del);
 	if (error)
 		goto done;
 
@@ -5113,11 +5048,11 @@ xfs_bmap_del_extent_real(
 	 */
 	if (do_fx && !(bflags & XFS_BMAPI_REMAP)) {
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
-			error = xfs_refcount_decrease_extent(mp, dfops, del);
+			error = xfs_refcount_decrease_extent(tp, del);
 			if (error)
 				goto done;
 		} else {
-			__xfs_bmap_add_free(mp, dfops, del->br_startblock,
+			__xfs_bmap_add_free(tp, del->br_startblock,
 					del->br_blockcount, NULL,
 					(bflags & XFS_BMAPI_NODISCARD) ||
 					del->br_state == XFS_EXT_UNWRITTEN);
@@ -5148,26 +5083,23 @@ done:
  */
 int						/* error */
 __xfs_bunmapi(
-	xfs_trans_t		*tp,		/* transaction pointer */
+	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_inode	*ip,		/* incore inode */
 	xfs_fileoff_t		start,		/* first file offset deleted */
 	xfs_filblks_t		*rlen,		/* i/o: amount remaining */
 	int			flags,		/* misc flags */
-	xfs_extnum_t		nexts,		/* number of extents max */
-	xfs_fsblock_t		*firstblock,	/* first allocated block
-						   controls a.g. for allocs */
-	struct xfs_defer_ops	*dfops)		/* i/o: deferred updates */
+	xfs_extnum_t		nexts)		/* number of extents max */
 {
-	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
-	xfs_bmbt_irec_t		del;		/* extent being deleted */
+	struct xfs_btree_cur	*cur;		/* bmap btree cursor */
+	struct xfs_bmbt_irec	del;		/* extent being deleted */
 	int			error;		/* error return value */
 	xfs_extnum_t		extno;		/* extent number in list */
-	xfs_bmbt_irec_t		got;		/* current extent record */
-	xfs_ifork_t		*ifp;		/* inode fork pointer */
+	struct xfs_bmbt_irec	got;		/* current extent record */
+	struct xfs_ifork	*ifp;		/* inode fork pointer */
 	int			isrt;		/* freeing in rt area */
 	int			logflags;	/* transaction logging flags */
 	xfs_extlen_t		mod;		/* rt extent offset */
-	xfs_mount_t		*mp;		/* mount structure */
+	struct xfs_mount	*mp;		/* mount structure */
 	int			tmp_logflags;	/* partial logging flags */
 	int			wasdel;		/* was a delayed alloc extent */
 	int			whichfork;	/* data or attribute fork */
@@ -5230,8 +5162,6 @@ __xfs_bunmapi(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	} else
 		cur = NULL;
@@ -5347,7 +5277,7 @@ __xfs_bunmapi(
 			del.br_state = XFS_EXT_UNWRITTEN;
 			error = xfs_bmap_add_extent_unwritten_real(tp, ip,
 					whichfork, &icur, &cur, &del,
-					firstblock, dfops, &logflags);
+					&logflags);
 			if (error)
 				goto error0;
 			goto nodelete;
@@ -5404,8 +5334,7 @@ __xfs_bunmapi(
 				prev.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&prev, firstblock, dfops,
-						&logflags);
+						&prev, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5414,8 +5343,7 @@ __xfs_bunmapi(
 				del.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&del, firstblock, dfops,
-						&logflags);
+						&del, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5427,8 +5355,8 @@ delete:
 			error = xfs_bmap_del_extent_delay(ip, whichfork, &icur,
 					&got, &del);
 		} else {
-			error = xfs_bmap_del_extent_real(ip, tp, &icur, dfops,
-					cur, &del, &tmp_logflags, whichfork,
+			error = xfs_bmap_del_extent_real(ip, tp, &icur, cur,
+					&del, &tmp_logflags, whichfork,
 					flags);
 			logflags |= tmp_logflags;
 		}
@@ -5462,8 +5390,8 @@ nodelete:
 	 */
 	if (xfs_bmap_needs_btree(ip, whichfork)) {
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops,
-			&cur, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
+				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 		if (error)
 			goto error0;
@@ -5501,12 +5429,9 @@ error0:
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	if (cur) {
-		if (!error) {
-			*firstblock = cur->bc_private.b.firstblock;
+		if (!error)
 			cur->bc_private.b.allocated = 0;
-		}
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	}
 	return error;
 }
@@ -5520,14 +5445,11 @@ xfs_bunmapi(
 	xfs_filblks_t		len,
 	int			flags,
 	xfs_extnum_t		nexts,
-	xfs_fsblock_t		*firstblock,
-	struct xfs_defer_ops	*dfops,
 	int			*done)
 {
 	int			error;
 
-	error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts, firstblock,
-			dfops);
+	error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts);
 	*done = (len == 0);
 	return error;
 }
@@ -5570,6 +5492,7 @@ xfs_bmse_can_merge(
  */
 STATIC int
 xfs_bmse_merge(
+	struct xfs_trans		*tp,
 	struct xfs_inode		*ip,
 	int				whichfork,
 	xfs_fileoff_t			shift,		/* shift fsb */
@@ -5577,8 +5500,7 @@ xfs_bmse_merge(
 	struct xfs_bmbt_irec		*got,		/* extent to shift */
 	struct xfs_bmbt_irec		*left,		/* preceding extent */
 	struct xfs_btree_cur		*cur,
-	int				*logflags,	/* output */
-	struct xfs_defer_ops		*dfops)
+	int				*logflags)	/* output */
 {
 	struct xfs_bmbt_irec		new;
 	xfs_filblks_t			blockcount;
@@ -5634,23 +5556,23 @@ done:
 			&new);
 
 	/* update reverse mapping. rmap functions merge the rmaps for us */
-	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, got);
+	error = xfs_rmap_unmap_extent(tp, ip, whichfork, got);
 	if (error)
 		return error;
 	memcpy(&new, got, sizeof(new));
 	new.br_startoff = left->br_startoff + left->br_blockcount;
-	return xfs_rmap_map_extent(mp, dfops, ip, whichfork, &new);
+	return xfs_rmap_map_extent(tp, ip, whichfork, &new);
 }
 
 static int
 xfs_bmap_shift_update_extent(
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_iext_cursor	*icur,
 	struct xfs_bmbt_irec	*got,
 	struct xfs_btree_cur	*cur,
 	int			*logflags,
-	struct xfs_defer_ops	*dfops,
 	xfs_fileoff_t		startoff)
 {
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5678,10 +5600,10 @@ xfs_bmap_shift_update_extent(
 			got);
 
 	/* update reverse mapping */
-	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, &prev);
+	error = xfs_rmap_unmap_extent(tp, ip, whichfork, &prev);
 	if (error)
 		return error;
-	return xfs_rmap_map_extent(mp, dfops, ip, whichfork, got);
+	return xfs_rmap_map_extent(tp, ip, whichfork, got);
 }
 
 int
@@ -5690,9 +5612,7 @@ xfs_bmap_collapse_extents(
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		*next_fsb,
 	xfs_fileoff_t		offset_shift_fsb,
-	bool			*done,
-	xfs_fsblock_t		*firstblock,
-	struct xfs_defer_ops	*dfops)
+	bool			*done)
 {
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5725,8 +5645,6 @@ xfs_bmap_collapse_extents(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5745,9 +5663,9 @@ xfs_bmap_collapse_extents(
 		}
 
 		if (xfs_bmse_can_merge(&prev, &got, offset_shift_fsb)) {
-			error = xfs_bmse_merge(ip, whichfork, offset_shift_fsb,
-					&icur, &got, &prev, cur, &logflags,
-					dfops);
+			error = xfs_bmse_merge(tp, ip, whichfork,
+					offset_shift_fsb, &icur, &got, &prev,
+					cur, &logflags);
 			if (error)
 				goto del_cursor;
 			goto done;
@@ -5759,8 +5677,8 @@ xfs_bmap_collapse_extents(
 		}
 	}
 
-	error = xfs_bmap_shift_update_extent(ip, whichfork, &icur, &got, cur,
-			&logflags, dfops, new_startoff);
+	error = xfs_bmap_shift_update_extent(tp, ip, whichfork, &icur, &got,
+			cur, &logflags, new_startoff);
 	if (error)
 		goto del_cursor;
 
@@ -5773,13 +5691,38 @@ done:
 	*next_fsb = got.br_startoff;
 del_cursor:
 	if (cur)
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	return error;
 }
 
+/* Make sure we won't be right-shifting an extent past the maximum bound. */
+int
+xfs_bmap_can_insert_extents(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		off,
+	xfs_fileoff_t		shift)
+{
+	struct xfs_bmbt_irec	got;
+	int			is_empty;
+	int			error = 0;
+
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmap_last_extent(NULL, ip, XFS_DATA_FORK, &got, &is_empty);
+	if (!error && !is_empty && got.br_startoff >= off &&
+	    ((got.br_startoff + shift) & BMBT_STARTOFF_MASK) < got.br_startoff)
+		error = -EINVAL;
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	return error;
+}
+
 int
 xfs_bmap_insert_extents(
 	struct xfs_trans	*tp,
@@ -5787,9 +5730,7 @@ xfs_bmap_insert_extents(
 	xfs_fileoff_t		*next_fsb,
 	xfs_fileoff_t		offset_shift_fsb,
 	bool			*done,
-	xfs_fileoff_t		stop_fsb,
-	xfs_fsblock_t		*firstblock,
-	struct xfs_defer_ops	*dfops)
+	xfs_fileoff_t		stop_fsb)
 {
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5822,8 +5763,6 @@ xfs_bmap_insert_extents(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5865,8 +5804,8 @@ xfs_bmap_insert_extents(
 			WARN_ON_ONCE(1);
 	}
 
-	error = xfs_bmap_shift_update_extent(ip, whichfork, &icur, &got, cur,
-			&logflags, dfops, new_startoff);
+	error = xfs_bmap_shift_update_extent(tp, ip, whichfork, &icur, &got,
+			cur, &logflags, new_startoff);
 	if (error)
 		goto del_cursor;
 
@@ -5879,8 +5818,7 @@ xfs_bmap_insert_extents(
 	*next_fsb = got.br_startoff;
 del_cursor:
 	if (cur)
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	return error;
@@ -5896,9 +5834,7 @@ STATIC int
 xfs_bmap_split_extent_at(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
-	xfs_fileoff_t		split_fsb,
-	xfs_fsblock_t		*firstfsb,
-	struct xfs_defer_ops	*dfops)
+	xfs_fileoff_t		split_fsb)
 {
 	int				whichfork = XFS_DATA_FORK;
 	struct xfs_btree_cur		*cur = NULL;
@@ -5947,8 +5883,6 @@ xfs_bmap_split_extent_at(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstfsb;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
@@ -5992,16 +5926,15 @@ xfs_bmap_split_extent_at(
 		int tmp_logflags; /* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, dfops,
-				&cur, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
+				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 	}
 
 del_cursor:
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
-		xfs_btree_del_cursor(cur,
-				error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	}
 
 	if (logflags)
@@ -6016,8 +5949,6 @@ xfs_bmap_split_extent(
 {
 	struct xfs_mount        *mp = ip->i_mount;
 	struct xfs_trans        *tp;
-	struct xfs_defer_ops    dfops;
-	xfs_fsblock_t           firstfsb;
 	int                     error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write,
@@ -6028,21 +5959,13 @@ xfs_bmap_split_extent(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-	xfs_defer_init(&dfops, &firstfsb);
-
-	error = xfs_bmap_split_extent_at(tp, ip, split_fsb,
-			&firstfsb, &dfops);
-	if (error)
-		goto out;
-
-	error = xfs_defer_finish(&tp, &dfops);
+	error = xfs_bmap_split_extent_at(tp, ip, split_fsb);
 	if (error)
 		goto out;
 
 	return xfs_trans_commit(tp);
 
 out:
-	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -6059,20 +5982,18 @@ xfs_bmap_is_update_needed(
 /* Record a bmap intent. */
 static int
 __xfs_bmap_add(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	enum xfs_bmap_intent_type	type,
 	struct xfs_inode		*ip,
 	int				whichfork,
 	struct xfs_bmbt_irec		*bmap)
 {
-	int				error;
 	struct xfs_bmap_intent		*bi;
 
-	trace_xfs_bmap_defer(mp,
-			XFS_FSB_TO_AGNO(mp, bmap->br_startblock),
+	trace_xfs_bmap_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
 			type,
-			XFS_FSB_TO_AGBNO(mp, bmap->br_startblock),
+			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
 			ip->i_ino, whichfork,
 			bmap->br_startoff,
 			bmap->br_blockcount,
@@ -6085,44 +6006,34 @@ __xfs_bmap_add(
 	bi->bi_whichfork = whichfork;
 	bi->bi_bmap = *bmap;
 
-	error = xfs_defer_ijoin(dfops, bi->bi_owner);
-	if (error) {
-		kmem_free(bi);
-		return error;
-	}
-
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
 	return 0;
 }
 
 /* Map an extent into a file. */
 int
 xfs_bmap_map_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*PREV)
 {
 	if (!xfs_bmap_is_update_needed(PREV))
 		return 0;
 
-	return __xfs_bmap_add(mp, dfops, XFS_BMAP_MAP, ip,
-			XFS_DATA_FORK, PREV);
+	return __xfs_bmap_add(tp, XFS_BMAP_MAP, ip, XFS_DATA_FORK, PREV);
 }
 
 /* Unmap an extent out of a file. */
 int
 xfs_bmap_unmap_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*PREV)
 {
 	if (!xfs_bmap_is_update_needed(PREV))
 		return 0;
 
-	return __xfs_bmap_add(mp, dfops, XFS_BMAP_UNMAP, ip,
-			XFS_DATA_FORK, PREV);
+	return __xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, XFS_DATA_FORK, PREV);
 }
 
 /*
@@ -6132,7 +6043,6 @@ xfs_bmap_unmap_extent(
 int
 xfs_bmap_finish_one(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dfops,
 	struct xfs_inode		*ip,
 	enum xfs_bmap_intent_type	type,
 	int				whichfork,
@@ -6141,17 +6051,9 @@ xfs_bmap_finish_one(
 	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
-	xfs_fsblock_t			firstfsb;
 	int				error = 0;
 
-	/*
-	 * firstfsb is tied to the transaction lifetime and is used to
-	 * ensure correct AG locking order and schedule work item
-	 * continuations.  XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us
-	 * to only making one bmap call per transaction, so it should
-	 * be safe to have it as a local variable here.
-	 */
-	firstfsb = NULLFSBLOCK;
+	ASSERT(tp->t_firstblock == NULLFSBLOCK);
 
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
@@ -6168,12 +6070,12 @@ xfs_bmap_finish_one(
 	switch (type) {
 	case XFS_BMAP_MAP:
 		error = xfs_bmapi_remap(tp, ip, startoff, *blockcount,
-				startblock, dfops, 0);
+				startblock, 0);
 		*blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
 		error = __xfs_bunmapi(tp, ip, startoff, blockcount,
-				XFS_BMAPI_REMAP, 1, &firstfsb, dfops);
+				XFS_BMAPI_REMAP, 1);
 		break;
 	default:
 		ASSERT(0);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 99dddbd0fcc6..b6e9b639e731 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -19,8 +19,6 @@ extern kmem_zone_t	*xfs_bmap_free_item_zone;
  * Argument structure for xfs_bmap_alloc.
  */
 struct xfs_bmalloca {
-	xfs_fsblock_t		*firstblock; /* i/o first block allocated */
-	struct xfs_defer_ops	*dfops;	/* bmap freelist */
 	struct xfs_trans	*tp;	/* transaction pointer */
 	struct xfs_inode	*ip;	/* incore inode pointer */
 	struct xfs_bmbt_irec	prev;	/* extent before the new one */
@@ -68,8 +66,6 @@ struct xfs_extent_free_item
 #define XFS_BMAPI_METADATA	0x002	/* mapping metadata not user data */
 #define XFS_BMAPI_ATTRFORK	0x004	/* use attribute fork not data */
 #define XFS_BMAPI_PREALLOC	0x008	/* preallocation op: unwritten space */
-#define XFS_BMAPI_IGSTATE	0x010	/* Ignore state - */
-					/* combine contig. space */
 #define XFS_BMAPI_CONTIG	0x020	/* must allocate only one extent */
 /*
  * unwritten extent conversion - this needs write cache flushing and no additional
@@ -116,7 +112,6 @@ struct xfs_extent_free_item
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \
 	{ XFS_BMAPI_ATTRFORK,	"ATTRFORK" }, \
 	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \
-	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \
 	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \
 	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
 	{ XFS_BMAPI_ZERO,	"ZERO" }, \
@@ -189,9 +184,9 @@ void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
 void	xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
-void	__xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-			  xfs_fsblock_t bno, xfs_filblks_t len,
-			  struct xfs_owner_info *oinfo, bool skip_discard);
+void	__xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno,
+		xfs_filblks_t len, struct xfs_owner_info *oinfo,
+		bool skip_discard);
 void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
 int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
@@ -205,17 +200,13 @@ int	xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
 		int *nmap, int flags);
 int	xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
-		xfs_fsblock_t *firstblock, xfs_extlen_t total,
-		struct xfs_bmbt_irec *mval, int *nmap,
-		struct xfs_defer_ops *dfops);
+		xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap);
 int	__xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t *rlen, int flags,
-		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops);
+		xfs_extnum_t nexts);
 int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
-		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops, int *done);
+		xfs_extnum_t nexts, int *done);
 int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
 		struct xfs_bmbt_irec *del);
@@ -225,12 +216,12 @@ void	xfs_bmap_del_extent_cow(struct xfs_inode *ip,
 uint	xfs_default_attroffset(struct xfs_inode *ip);
 int	xfs_bmap_collapse_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
-		bool *done, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops);
+		bool *done);
+int	xfs_bmap_can_insert_extents(struct xfs_inode *ip, xfs_fileoff_t off,
+		xfs_fileoff_t shift);
 int	xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
-		bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops);
+		bool *done, xfs_fileoff_t stop_fsb);
 int	xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset);
 int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 		xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,
@@ -239,13 +230,12 @@ int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 
 static inline void
 xfs_bmap_add_free(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	struct xfs_owner_info		*oinfo)
 {
-	__xfs_bmap_add_free(mp, dfops, bno, len, oinfo, false);
+	__xfs_bmap_add_free(tp, bno, len, oinfo, false);
 }
 
 enum xfs_bmap_intent_type {
@@ -261,14 +251,14 @@ struct xfs_bmap_intent {
 	struct xfs_bmbt_irec			bi_bmap;
 };
 
-int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, enum xfs_bmap_intent_type type,
-		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
+int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_inode *ip,
+		enum xfs_bmap_intent_type type, int whichfork,
+		xfs_fileoff_t startoff, xfs_fsblock_t startblock,
 		xfs_filblks_t *blockcount, xfs_exntst_t state);
-int	xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
-int	xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
+int	xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap);
+int	xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap);
 
 static inline int xfs_bmap_fork_to_state(int whichfork)
 {
@@ -287,6 +277,6 @@ xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
 
 int	xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
-		struct xfs_defer_ops *dfops, int flags);
+		int flags);
 
 #endif	/* __XFS_BMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index e1a2d9ceb615..cdb74d2e2a43 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -175,8 +175,6 @@ xfs_bmbt_dup_cursor(
 	 * Copy the firstblock, dfops, and flags values,
 	 * since init cursor doesn't get them.
 	 */
-	new->bc_private.b.firstblock = cur->bc_private.b.firstblock;
-	new->bc_private.b.dfops = cur->bc_private.b.dfops;
 	new->bc_private.b.flags = cur->bc_private.b.flags;
 
 	return new;
@@ -187,12 +185,11 @@ xfs_bmbt_update_cursor(
 	struct xfs_btree_cur	*src,
 	struct xfs_btree_cur	*dst)
 {
-	ASSERT((dst->bc_private.b.firstblock != NULLFSBLOCK) ||
+	ASSERT((dst->bc_tp->t_firstblock != NULLFSBLOCK) ||
 	       (dst->bc_private.b.ip->i_d.di_flags & XFS_DIFLAG_REALTIME));
-	ASSERT(dst->bc_private.b.dfops == src->bc_private.b.dfops);
 
 	dst->bc_private.b.allocated += src->bc_private.b.allocated;
-	dst->bc_private.b.firstblock = src->bc_private.b.firstblock;
+	dst->bc_tp->t_firstblock = src->bc_tp->t_firstblock;
 
 	src->bc_private.b.allocated = 0;
 }
@@ -210,8 +207,7 @@ xfs_bmbt_alloc_block(
 	memset(&args, 0, sizeof(args));
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
-	args.fsbno = cur->bc_private.b.firstblock;
-	args.firstblock = args.fsbno;
+	args.fsbno = cur->bc_tp->t_firstblock;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_private.b.ip->i_ino,
 			cur->bc_private.b.whichfork);
 
@@ -230,7 +226,7 @@ xfs_bmbt_alloc_block(
 		 * block allocation here and corrupt the filesystem.
 		 */
 		args.minleft = args.tp->t_blk_res;
-	} else if (cur->bc_private.b.dfops->dop_low) {
+	} else if (cur->bc_tp->t_flags & XFS_TRANS_LOWMODE) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -257,7 +253,7 @@ xfs_bmbt_alloc_block(
 		error = xfs_alloc_vextent(&args);
 		if (error)
 			goto error0;
-		cur->bc_private.b.dfops->dop_low = true;
+		cur->bc_tp->t_flags |= XFS_TRANS_LOWMODE;
 	}
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		*stat = 0;
@@ -265,7 +261,7 @@ xfs_bmbt_alloc_block(
 	}
 
 	ASSERT(args.len == 1);
-	cur->bc_private.b.firstblock = args.fsbno;
+	cur->bc_tp->t_firstblock = args.fsbno;
 	cur->bc_private.b.allocated++;
 	cur->bc_private.b.ip->i_d.di_nblocks++;
 	xfs_trans_log_inode(args.tp, cur->bc_private.b.ip, XFS_ILOG_CORE);
@@ -293,7 +289,7 @@ xfs_bmbt_free_block(
 	struct xfs_owner_info	oinfo;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_private.b.whichfork);
-	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, fsbno, 1, &oinfo);
+	xfs_bmap_add_free(cur->bc_tp, fsbno, 1, &oinfo);
 	ip->i_d.di_nblocks--;
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -564,8 +560,6 @@ xfs_bmbt_init_cursor(
 
 	cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
 	cur->bc_private.b.ip = ip;
-	cur->bc_private.b.firstblock = NULLFSBLOCK;
-	cur->bc_private.b.dfops = NULL;
 	cur->bc_private.b.allocated = 0;
 	cur->bc_private.b.flags = 0;
 	cur->bc_private.b.whichfork = whichfork;
@@ -645,7 +639,7 @@ xfs_bmbt_change_owner(
 	cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER;
 
 	error = xfs_btree_change_owner(cur, new_owner, buffer_list);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 0a4fdf7f11a7..e3b3e9dce5da 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -7,7 +7,6 @@
 #define	__XFS_BTREE_H__
 
 struct xfs_buf;
-struct xfs_defer_ops;
 struct xfs_inode;
 struct xfs_mount;
 struct xfs_trans;
@@ -209,14 +208,11 @@ typedef struct xfs_btree_cur
 	union {
 		struct {			/* needed for BNO, CNT, INO */
 			struct xfs_buf	*agbp;	/* agf/agi buffer pointer */
-			struct xfs_defer_ops *dfops;	/* deferred updates */
 			xfs_agnumber_t	agno;	/* ag number */
 			union xfs_btree_cur_private	priv;
 		} a;
 		struct {			/* needed for BMAP */
 			struct xfs_inode *ip;	/* pointer to our inode */
-			struct xfs_defer_ops *dfops;	/* deferred updates */
-			xfs_fsblock_t	firstblock;	/* 1st blk allocated */
 			int		allocated;	/* count of alloced */
 			short		forksize;	/* fork's inode space */
 			char		whichfork;	/* data or attr fork */
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 8a301402bbc4..376bee94b5dd 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -1481,6 +1481,7 @@ xfs_da3_node_lookup_int(
 	int			error;
 	int			retval;
 	unsigned int		expected_level = 0;
+	uint16_t		magic;
 	struct xfs_inode	*dp = state->args->dp;
 
 	args = state->args;
@@ -1505,25 +1506,27 @@ xfs_da3_node_lookup_int(
 			return error;
 		}
 		curr = blk->bp->b_addr;
-		blk->magic = be16_to_cpu(curr->magic);
+		magic = be16_to_cpu(curr->magic);
 
-		if (blk->magic == XFS_ATTR_LEAF_MAGIC ||
-		    blk->magic == XFS_ATTR3_LEAF_MAGIC) {
+		if (magic == XFS_ATTR_LEAF_MAGIC ||
+		    magic == XFS_ATTR3_LEAF_MAGIC) {
 			blk->magic = XFS_ATTR_LEAF_MAGIC;
 			blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
 			break;
 		}
 
-		if (blk->magic == XFS_DIR2_LEAFN_MAGIC ||
-		    blk->magic == XFS_DIR3_LEAFN_MAGIC) {
+		if (magic == XFS_DIR2_LEAFN_MAGIC ||
+		    magic == XFS_DIR3_LEAFN_MAGIC) {
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
 							      blk->bp, NULL);
 			break;
 		}
 
-		blk->magic = XFS_DA_NODE_MAGIC;
+		if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC)
+			return -EFSCORRUPTED;
 
+		blk->magic = XFS_DA_NODE_MAGIC;
 
 		/*
 		 * Search an intermediate node for a match.
@@ -2059,11 +2062,9 @@ xfs_da_grow_inode_int(
 	 * Try mapping it in one filesystem block.
 	 */
 	nmap = 1;
-	ASSERT(args->firstblock != NULL);
 	error = xfs_bmapi_write(tp, dp, *bno, count,
 			xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG,
-			args->firstblock, args->total, &map, &nmap,
-			args->dfops);
+			args->total, &map, &nmap);
 	if (error)
 		return error;
 
@@ -2085,8 +2086,7 @@ xfs_da_grow_inode_int(
 			c = (int)(*bno + count - b);
 			error = xfs_bmapi_write(tp, dp, b, c,
 					xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA,
-					args->firstblock, args->total,
-					&mapp[mapi], &nmap, args->dfops);
+					args->total, &mapp[mapi], &nmap);
 			if (error)
 				goto out_free_map;
 			if (nmap < 1)
@@ -2375,13 +2375,13 @@ done:
  */
 int
 xfs_da_shrink_inode(
-	xfs_da_args_t	*args,
-	xfs_dablk_t	dead_blkno,
-	struct xfs_buf	*dead_buf)
+	struct xfs_da_args	*args,
+	xfs_dablk_t		dead_blkno,
+	struct xfs_buf		*dead_buf)
 {
-	xfs_inode_t *dp;
-	int done, error, w, count;
-	xfs_trans_t *tp;
+	struct xfs_inode	*dp;
+	int			done, error, w, count;
+	struct xfs_trans	*tp;
 
 	trace_xfs_da_shrink_inode(args);
 
@@ -2395,8 +2395,7 @@ xfs_da_shrink_inode(
 		 * the last block to the place we want to kill.
 		 */
 		error = xfs_bunmapi(tp, dp, dead_blkno, count,
-				    xfs_bmapi_aflag(w), 0, args->firstblock,
-				    args->dfops, &done);
+				    xfs_bmapi_aflag(w), 0, &done);
 		if (error == -ENOSPC) {
 			if (w != XFS_DATA_FORK)
 				break;
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 28260073ae71..84dd865b6c3d 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -7,7 +7,6 @@
 #ifndef __XFS_DA_BTREE_H__
 #define	__XFS_DA_BTREE_H__
 
-struct xfs_defer_ops;
 struct xfs_inode;
 struct xfs_trans;
 struct zone;
@@ -57,8 +56,6 @@ typedef struct xfs_da_args {
 	xfs_dahash_t	hashval;	/* hash value of name */
 	xfs_ino_t	inumber;	/* input/output inode number */
 	struct xfs_inode *dp;		/* directory inode to manipulate */
-	xfs_fsblock_t	*firstblock;	/* ptr to firstblock for bmap calls */
-	struct xfs_defer_ops *dfops;	/* ptr to freelist for bmap_finish */
 	struct xfs_trans *trans;	/* current trans (changes over time) */
 	xfs_extlen_t	total;		/* total blocks needed, for 1st bmap */
 	int		whichfork;	/* data or attribute fork */
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index c3e5bffda4f5..e792b167150a 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -14,6 +14,9 @@
 #include "xfs_mount.h"
 #include "xfs_defer.h"
 #include "xfs_trans.h"
+#include "xfs_buf_item.h"
+#include "xfs_inode.h"
+#include "xfs_inode_item.h"
 #include "xfs_trace.h"
 
 /*
@@ -177,146 +180,157 @@ static const struct xfs_defer_op_type *defer_op_types[XFS_DEFER_OPS_TYPE_MAX];
  * the pending list.
  */
 STATIC void
-xfs_defer_intake_work(
-	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop)
+xfs_defer_create_intents(
+	struct xfs_trans		*tp)
 {
 	struct list_head		*li;
 	struct xfs_defer_pending	*dfp;
 
-	list_for_each_entry(dfp, &dop->dop_intake, dfp_list) {
+	list_for_each_entry(dfp, &tp->t_dfops, dfp_list) {
 		dfp->dfp_intent = dfp->dfp_type->create_intent(tp,
 				dfp->dfp_count);
-		trace_xfs_defer_intake_work(tp->t_mountp, dfp);
+		trace_xfs_defer_create_intent(tp->t_mountp, dfp);
 		list_sort(tp->t_mountp, &dfp->dfp_work,
 				dfp->dfp_type->diff_items);
 		list_for_each(li, &dfp->dfp_work)
 			dfp->dfp_type->log_item(tp, dfp->dfp_intent, li);
 	}
-
-	list_splice_tail_init(&dop->dop_intake, &dop->dop_pending);
 }
 
 /* Abort all the intents that were committed. */
 STATIC void
 xfs_defer_trans_abort(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
-	int				error)
+	struct list_head		*dop_pending)
 {
 	struct xfs_defer_pending	*dfp;
 
-	trace_xfs_defer_trans_abort(tp->t_mountp, dop, _RET_IP_);
+	trace_xfs_defer_trans_abort(tp, _RET_IP_);
 
 	/* Abort intent items that don't have a done item. */
-	list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
+	list_for_each_entry(dfp, dop_pending, dfp_list) {
 		trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
 		if (dfp->dfp_intent && !dfp->dfp_done) {
 			dfp->dfp_type->abort_intent(dfp->dfp_intent);
 			dfp->dfp_intent = NULL;
 		}
 	}
-
-	/* Shut down FS. */
-	xfs_force_shutdown(tp->t_mountp, (error == -EFSCORRUPTED) ?
-			SHUTDOWN_CORRUPT_INCORE : SHUTDOWN_META_IO_ERROR);
 }
 
 /* Roll a transaction so we can do some deferred op processing. */
 STATIC int
 xfs_defer_trans_roll(
-	struct xfs_trans		**tp,
-	struct xfs_defer_ops		*dop)
+	struct xfs_trans		**tpp)
 {
+	struct xfs_trans		*tp = *tpp;
+	struct xfs_buf_log_item		*bli;
+	struct xfs_inode_log_item	*ili;
+	struct xfs_log_item		*lip;
+	struct xfs_buf			*bplist[XFS_DEFER_OPS_NR_BUFS];
+	struct xfs_inode		*iplist[XFS_DEFER_OPS_NR_INODES];
+	int				bpcount = 0, ipcount = 0;
 	int				i;
 	int				error;
 
-	/* Log all the joined inodes. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
-		xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE);
-
-	/* Hold the (previously bjoin'd) buffer locked across the roll. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++)
-		xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]);
+	list_for_each_entry(lip, &tp->t_items, li_trans) {
+		switch (lip->li_type) {
+		case XFS_LI_BUF:
+			bli = container_of(lip, struct xfs_buf_log_item,
+					   bli_item);
+			if (bli->bli_flags & XFS_BLI_HOLD) {
+				if (bpcount >= XFS_DEFER_OPS_NR_BUFS) {
+					ASSERT(0);
+					return -EFSCORRUPTED;
+				}
+				xfs_trans_dirty_buf(tp, bli->bli_buf);
+				bplist[bpcount++] = bli->bli_buf;
+			}
+			break;
+		case XFS_LI_INODE:
+			ili = container_of(lip, struct xfs_inode_log_item,
+					   ili_item);
+			if (ili->ili_lock_flags == 0) {
+				if (ipcount >= XFS_DEFER_OPS_NR_INODES) {
+					ASSERT(0);
+					return -EFSCORRUPTED;
+				}
+				xfs_trans_log_inode(tp, ili->ili_inode,
+						    XFS_ILOG_CORE);
+				iplist[ipcount++] = ili->ili_inode;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
-	trace_xfs_defer_trans_roll((*tp)->t_mountp, dop, _RET_IP_);
+	trace_xfs_defer_trans_roll(tp, _RET_IP_);
 
 	/* Roll the transaction. */
-	error = xfs_trans_roll(tp);
+	error = xfs_trans_roll(tpp);
+	tp = *tpp;
 	if (error) {
-		trace_xfs_defer_trans_roll_error((*tp)->t_mountp, dop, error);
-		xfs_defer_trans_abort(*tp, dop, error);
+		trace_xfs_defer_trans_roll_error(tp, error);
 		return error;
 	}
-	dop->dop_committed = true;
 
 	/* Rejoin the joined inodes. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
-		xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0);
+	for (i = 0; i < ipcount; i++)
+		xfs_trans_ijoin(tp, iplist[i], 0);
 
 	/* Rejoin the buffers and dirty them so the log moves forward. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) {
-		xfs_trans_bjoin(*tp, dop->dop_bufs[i]);
-		xfs_trans_bhold(*tp, dop->dop_bufs[i]);
+	for (i = 0; i < bpcount; i++) {
+		xfs_trans_bjoin(tp, bplist[i]);
+		xfs_trans_bhold(tp, bplist[i]);
 	}
 
 	return error;
 }
 
-/* Do we have any work items to finish? */
-bool
-xfs_defer_has_unfinished_work(
-	struct xfs_defer_ops		*dop)
-{
-	return !list_empty(&dop->dop_pending) || !list_empty(&dop->dop_intake);
-}
-
 /*
- * Add this inode to the deferred op.  Each joined inode is relogged
- * each time we roll the transaction.
+ * Reset an already used dfops after finish.
  */
-int
-xfs_defer_ijoin(
-	struct xfs_defer_ops		*dop,
-	struct xfs_inode		*ip)
+static void
+xfs_defer_reset(
+	struct xfs_trans	*tp)
 {
-	int				i;
-
-	for (i = 0; i < XFS_DEFER_OPS_NR_INODES; i++) {
-		if (dop->dop_inodes[i] == ip)
-			return 0;
-		else if (dop->dop_inodes[i] == NULL) {
-			dop->dop_inodes[i] = ip;
-			return 0;
-		}
-	}
+	ASSERT(list_empty(&tp->t_dfops));
 
-	ASSERT(0);
-	return -EFSCORRUPTED;
+	/*
+	 * Low mode state transfers across transaction rolls to mirror dfops
+	 * lifetime. Clear it now that dfops is reset.
+	 */
+	tp->t_flags &= ~XFS_TRANS_LOWMODE;
 }
 
 /*
- * Add this buffer to the deferred op.  Each joined buffer is relogged
- * each time we roll the transaction.
+ * Free up any items left in the list.
  */
-int
-xfs_defer_bjoin(
-	struct xfs_defer_ops		*dop,
-	struct xfs_buf			*bp)
+static void
+xfs_defer_cancel_list(
+	struct xfs_mount		*mp,
+	struct list_head		*dop_list)
 {
-	int				i;
+	struct xfs_defer_pending	*dfp;
+	struct xfs_defer_pending	*pli;
+	struct list_head		*pwi;
+	struct list_head		*n;
 
-	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS; i++) {
-		if (dop->dop_bufs[i] == bp)
-			return 0;
-		else if (dop->dop_bufs[i] == NULL) {
-			dop->dop_bufs[i] = bp;
-			return 0;
+	/*
+	 * Free the pending items.  Caller should already have arranged
+	 * for the intent items to be released.
+	 */
+	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) {
+		trace_xfs_defer_cancel_list(mp, dfp);
+		list_del(&dfp->dfp_list);
+		list_for_each_safe(pwi, n, &dfp->dfp_work) {
+			list_del(pwi);
+			dfp->dfp_count--;
+			dfp->dfp_type->cancel_item(pwi);
 		}
+		ASSERT(dfp->dfp_count == 0);
+		kmem_free(dfp);
 	}
-
-	ASSERT(0);
-	return -EFSCORRUPTED;
 }
 
 /*
@@ -328,9 +342,8 @@ xfs_defer_bjoin(
  * If an inode is provided, relog it to the new transaction.
  */
 int
-xfs_defer_finish(
-	struct xfs_trans		**tp,
-	struct xfs_defer_ops		*dop)
+xfs_defer_finish_noroll(
+	struct xfs_trans		**tp)
 {
 	struct xfs_defer_pending	*dfp;
 	struct list_head		*li;
@@ -338,35 +351,28 @@ xfs_defer_finish(
 	void				*state;
 	int				error = 0;
 	void				(*cleanup_fn)(struct xfs_trans *, void *, int);
-	struct xfs_defer_ops		*orig_dop;
+	LIST_HEAD(dop_pending);
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
-	trace_xfs_defer_finish((*tp)->t_mountp, dop, _RET_IP_);
-
-	/*
-	 * Attach dfops to the transaction during deferred ops processing. This
-	 * explicitly causes calls into the allocator to defer AGFL block frees.
-	 * Note that this code can go away once all dfops users attach to the
-	 * associated tp.
-	 */
-	ASSERT(!(*tp)->t_agfl_dfops || ((*tp)->t_agfl_dfops == dop));
-	orig_dop = (*tp)->t_agfl_dfops;
-	(*tp)->t_agfl_dfops = dop;
+	trace_xfs_defer_finish(*tp, _RET_IP_);
 
 	/* Until we run out of pending work to finish... */
-	while (xfs_defer_has_unfinished_work(dop)) {
-		/* Log intents for work items sitting in the intake. */
-		xfs_defer_intake_work(*tp, dop);
-
-		/* Roll the transaction. */
-		error = xfs_defer_trans_roll(tp, dop);
+	while (!list_empty(&dop_pending) || !list_empty(&(*tp)->t_dfops)) {
+		/* log intents and pull in intake items */
+		xfs_defer_create_intents(*tp);
+		list_splice_tail_init(&(*tp)->t_dfops, &dop_pending);
+
+		/*
+		 * Roll the transaction.
+		 */
+		error = xfs_defer_trans_roll(tp);
 		if (error)
 			goto out;
 
 		/* Log an intent-done item for the first pending item. */
-		dfp = list_first_entry(&dop->dop_pending,
-				struct xfs_defer_pending, dfp_list);
+		dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
+				       dfp_list);
 		trace_xfs_defer_pending_finish((*tp)->t_mountp, dfp);
 		dfp->dfp_done = dfp->dfp_type->create_done(*tp, dfp->dfp_intent,
 				dfp->dfp_count);
@@ -377,7 +383,7 @@ xfs_defer_finish(
 		list_for_each_safe(li, n, &dfp->dfp_work) {
 			list_del(li);
 			dfp->dfp_count--;
-			error = dfp->dfp_type->finish_item(*tp, dop, li,
+			error = dfp->dfp_type->finish_item(*tp, li,
 					dfp->dfp_done, &state);
 			if (error == -EAGAIN) {
 				/*
@@ -396,7 +402,6 @@ xfs_defer_finish(
 				 */
 				if (cleanup_fn)
 					cleanup_fn(*tp, state, error);
-				xfs_defer_trans_abort(*tp, dop, error);
 				goto out;
 			}
 		}
@@ -425,72 +430,72 @@ xfs_defer_finish(
 	}
 
 out:
-	(*tp)->t_agfl_dfops = orig_dop;
-	if (error)
-		trace_xfs_defer_finish_error((*tp)->t_mountp, dop, error);
-	else
-		trace_xfs_defer_finish_done((*tp)->t_mountp, dop, _RET_IP_);
-	return error;
+	if (error) {
+		xfs_defer_trans_abort(*tp, &dop_pending);
+		xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE);
+		trace_xfs_defer_finish_error(*tp, error);
+		xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending);
+		xfs_defer_cancel(*tp);
+		return error;
+	}
+
+	trace_xfs_defer_finish_done(*tp, _RET_IP_);
+	return 0;
 }
 
-/*
- * Free up any items left in the list.
- */
-void
-xfs_defer_cancel(
-	struct xfs_defer_ops		*dop)
+int
+xfs_defer_finish(
+	struct xfs_trans	**tp)
 {
-	struct xfs_defer_pending	*dfp;
-	struct xfs_defer_pending	*pli;
-	struct list_head		*pwi;
-	struct list_head		*n;
-
-	trace_xfs_defer_cancel(NULL, dop, _RET_IP_);
+	int			error;
 
 	/*
-	 * Free the pending items.  Caller should already have arranged
-	 * for the intent items to be released.
+	 * Finish and roll the transaction once more to avoid returning to the
+	 * caller with a dirty transaction.
 	 */
-	list_for_each_entry_safe(dfp, pli, &dop->dop_intake, dfp_list) {
-		trace_xfs_defer_intake_cancel(NULL, dfp);
-		list_del(&dfp->dfp_list);
-		list_for_each_safe(pwi, n, &dfp->dfp_work) {
-			list_del(pwi);
-			dfp->dfp_count--;
-			dfp->dfp_type->cancel_item(pwi);
-		}
-		ASSERT(dfp->dfp_count == 0);
-		kmem_free(dfp);
-	}
-	list_for_each_entry_safe(dfp, pli, &dop->dop_pending, dfp_list) {
-		trace_xfs_defer_pending_cancel(NULL, dfp);
-		list_del(&dfp->dfp_list);
-		list_for_each_safe(pwi, n, &dfp->dfp_work) {
-			list_del(pwi);
-			dfp->dfp_count--;
-			dfp->dfp_type->cancel_item(pwi);
+	error = xfs_defer_finish_noroll(tp);
+	if (error)
+		return error;
+	if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
+		error = xfs_defer_trans_roll(tp);
+		if (error) {
+			xfs_force_shutdown((*tp)->t_mountp,
+					   SHUTDOWN_CORRUPT_INCORE);
+			return error;
 		}
-		ASSERT(dfp->dfp_count == 0);
-		kmem_free(dfp);
 	}
+	xfs_defer_reset(*tp);
+	return 0;
+}
+
+void
+xfs_defer_cancel(
+	struct xfs_trans	*tp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+
+	trace_xfs_defer_cancel(tp, _RET_IP_);
+	xfs_defer_cancel_list(mp, &tp->t_dfops);
 }
 
 /* Add an item for later deferred processing. */
 void
 xfs_defer_add(
-	struct xfs_defer_ops		*dop,
+	struct xfs_trans		*tp,
 	enum xfs_defer_ops_type		type,
 	struct list_head		*li)
 {
 	struct xfs_defer_pending	*dfp = NULL;
 
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
 	/*
 	 * Add the item to a pending item at the end of the intake list.
 	 * If the last pending item has the same type, reuse it.  Else,
 	 * create a new pending item at the end of the intake list.
 	 */
-	if (!list_empty(&dop->dop_intake)) {
-		dfp = list_last_entry(&dop->dop_intake,
+	if (!list_empty(&tp->t_dfops)) {
+		dfp = list_last_entry(&tp->t_dfops,
 				struct xfs_defer_pending, dfp_list);
 		if (dfp->dfp_type->type != type ||
 		    (dfp->dfp_type->max_items &&
@@ -505,7 +510,7 @@ xfs_defer_add(
 		dfp->dfp_done = NULL;
 		dfp->dfp_count = 0;
 		INIT_LIST_HEAD(&dfp->dfp_work);
-		list_add_tail(&dfp->dfp_list, &dop->dop_intake);
+		list_add_tail(&dfp->dfp_list, &tp->t_dfops);
 	}
 
 	list_add_tail(li, &dfp->dfp_work);
@@ -520,15 +525,25 @@ xfs_defer_init_op_type(
 	defer_op_types[type->type] = type;
 }
 
-/* Initialize a deferred operation. */
+/*
+ * Move deferred ops from one transaction to another and reset the source to
+ * initial state. This is primarily used to carry state forward across
+ * transaction rolls with pending dfops.
+ */
 void
-xfs_defer_init(
-	struct xfs_defer_ops		*dop,
-	xfs_fsblock_t			*fbp)
+xfs_defer_move(
+	struct xfs_trans	*dtp,
+	struct xfs_trans	*stp)
 {
-	memset(dop, 0, sizeof(struct xfs_defer_ops));
-	*fbp = NULLFSBLOCK;
-	INIT_LIST_HEAD(&dop->dop_intake);
-	INIT_LIST_HEAD(&dop->dop_pending);
-	trace_xfs_defer_init(NULL, dop, _RET_IP_);
+	list_splice_init(&stp->t_dfops, &dtp->t_dfops);
+
+	/*
+	 * Low free space mode was historically controlled by a dfops field.
+	 * This meant that low mode state potentially carried across multiple
+	 * transaction rolls. Transfer low mode on a dfops move to preserve
+	 * that behavior.
+	 */
+	dtp->t_flags |= (stp->t_flags & XFS_TRANS_LOWMODE);
+
+	xfs_defer_reset(stp);
 }
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index a02b2b748b6d..2584a5b95b0d 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -24,17 +24,6 @@ struct xfs_defer_pending {
 
 /*
  * Header for deferred operation list.
- *
- * dop_low is used by the allocator to activate the lowspace algorithm -
- * when free space is running low the extent allocator may choose to
- * allocate an extent from an AG without leaving sufficient space for
- * a btree split when inserting the new extent.  In this case the allocator
- * will enable the lowspace algorithm which is supposed to allow further
- * allocations (such as btree splits and newroots) to allocate from
- * sequential AGs.  In order to avoid locking AGs out of order the lowspace
- * algorithm will start searching for free space from AG 0.  If the correct
- * transaction reservations have been made then this algorithm will eventually
- * find all the space it needs.
  */
 enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_BMAP,
@@ -45,28 +34,12 @@ enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_MAX,
 };
 
-#define XFS_DEFER_OPS_NR_INODES	2	/* join up to two inodes */
-#define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
-
-struct xfs_defer_ops {
-	bool			dop_committed;	/* did any trans commit? */
-	bool			dop_low;	/* alloc in low mode */
-	struct list_head	dop_intake;	/* unlogged pending work */
-	struct list_head	dop_pending;	/* logged pending work */
-
-	/* relog these with each roll */
-	struct xfs_inode	*dop_inodes[XFS_DEFER_OPS_NR_INODES];
-	struct xfs_buf		*dop_bufs[XFS_DEFER_OPS_NR_BUFS];
-};
-
-void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
+void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type,
 		struct list_head *h);
-int xfs_defer_finish(struct xfs_trans **tp, struct xfs_defer_ops *dop);
-void xfs_defer_cancel(struct xfs_defer_ops *dop);
-void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp);
-bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
-int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
-int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp);
+int xfs_defer_finish_noroll(struct xfs_trans **tp);
+int xfs_defer_finish(struct xfs_trans **tp);
+void xfs_defer_cancel(struct xfs_trans *);
+void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
 struct xfs_defer_op_type {
@@ -74,8 +47,8 @@ struct xfs_defer_op_type {
 	unsigned int		max_items;
 	void (*abort_intent)(void *);
 	void *(*create_done)(struct xfs_trans *, void *, unsigned int);
-	int (*finish_item)(struct xfs_trans *, struct xfs_defer_ops *,
-			struct list_head *, void *, void **);
+	int (*finish_item)(struct xfs_trans *, struct list_head *, void *,
+			void **);
 	void (*finish_cleanup)(struct xfs_trans *, void *, int);
 	void (*cancel_item)(struct list_head *);
 	int (*diff_items)(void *, struct list_head *, struct list_head *);
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 59169aff30fe..229152cd1a24 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -239,12 +239,10 @@ xfs_dir_init(
  */
 int
 xfs_dir_createname(
-	xfs_trans_t		*tp,
-	xfs_inode_t		*dp,
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_name		*name,
 	xfs_ino_t		inum,		/* new entry inode number */
-	xfs_fsblock_t		*first,		/* bmap's firstblock */
-	struct xfs_defer_ops	*dfops,		/* bmap's freeblock list */
 	xfs_extlen_t		total)		/* bmap's total block count */
 {
 	struct xfs_da_args	*args;
@@ -252,6 +250,7 @@ xfs_dir_createname(
 	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+
 	if (inum) {
 		rval = xfs_dir_ino_validate(tp->t_mountp, inum);
 		if (rval)
@@ -270,8 +269,6 @@ xfs_dir_createname(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = inum;
 	args->dp = dp;
-	args->firstblock = first;
-	args->dfops = dfops;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -416,17 +413,15 @@ out_free:
  */
 int
 xfs_dir_removename(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*dp,
-	struct xfs_name	*name,
-	xfs_ino_t	ino,
-	xfs_fsblock_t	*first,		/* bmap's firstblock */
-	struct xfs_defer_ops	*dfops,		/* bmap's freeblock list */
-	xfs_extlen_t	total)		/* bmap's total block count */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_name		*name,
+	xfs_ino_t		ino,
+	xfs_extlen_t		total)		/* bmap's total block count */
 {
-	struct xfs_da_args *args;
-	int		rval;
-	int		v;		/* type-checking value */
+	struct xfs_da_args	*args;
+	int			rval;
+	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	XFS_STATS_INC(dp->i_mount, xs_dir_remove);
@@ -442,8 +437,6 @@ xfs_dir_removename(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = ino;
 	args->dp = dp;
-	args->firstblock = first;
-	args->dfops = dfops;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -478,17 +471,15 @@ out_free:
  */
 int
 xfs_dir_replace(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*dp,
-	struct xfs_name	*name,		/* name of entry to replace */
-	xfs_ino_t	inum,		/* new inode number */
-	xfs_fsblock_t	*first,		/* bmap's firstblock */
-	struct xfs_defer_ops	*dfops,		/* bmap's freeblock list */
-	xfs_extlen_t	total)		/* bmap's total block count */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_name		*name,		/* name of entry to replace */
+	xfs_ino_t		inum,		/* new inode number */
+	xfs_extlen_t		total)		/* bmap's total block count */
 {
-	struct xfs_da_args *args;
-	int		rval;
-	int		v;		/* type-checking value */
+	struct xfs_da_args	*args;
+	int			rval;
+	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 
@@ -507,8 +498,6 @@ xfs_dir_replace(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = inum;
 	args->dp = dp;
-	args->firstblock = first;
-	args->dfops = dfops;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -547,7 +536,7 @@ xfs_dir_canenter(
 	xfs_inode_t	*dp,
 	struct xfs_name	*name)		/* name of entry to add */
 {
-	return xfs_dir_createname(tp, dp, name, 0, NULL, NULL, 0);
+	return xfs_dir_createname(tp, dp, name, 0, 0);
 }
 
 /*
@@ -645,17 +634,17 @@ xfs_dir2_isleaf(
  */
 int
 xfs_dir2_shrink_inode(
-	xfs_da_args_t	*args,
-	xfs_dir2_db_t	db,
-	struct xfs_buf	*bp)
+	struct xfs_da_args	*args,
+	xfs_dir2_db_t		db,
+	struct xfs_buf		*bp)
 {
-	xfs_fileoff_t	bno;		/* directory file offset */
-	xfs_dablk_t	da;		/* directory file offset */
-	int		done;		/* bunmap is finished */
-	xfs_inode_t	*dp;
-	int		error;
-	xfs_mount_t	*mp;
-	xfs_trans_t	*tp;
+	xfs_fileoff_t		bno;		/* directory file offset */
+	xfs_dablk_t		da;		/* directory file offset */
+	int			done;		/* bunmap is finished */
+	struct xfs_inode	*dp;
+	int			error;
+	struct xfs_mount	*mp;
+	struct xfs_trans	*tp;
 
 	trace_xfs_dir2_shrink_inode(args, db);
 
@@ -665,8 +654,7 @@ xfs_dir2_shrink_inode(
 	da = xfs_dir2_db_to_da(args->geo, db);
 
 	/* Unmap the fsblock(s). */
-	error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount, 0, 0,
-			    args->firstblock, args->dfops, &done);
+	error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount, 0, 0, &done);
 	if (error) {
 		/*
 		 * ENOSPC actually can happen if we're in a removename with no
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index ed385316c7dc..c3e3f6b813d8 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -9,7 +9,6 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 
-struct xfs_defer_ops;
 struct xfs_da_args;
 struct xfs_inode;
 struct xfs_mount;
@@ -118,19 +117,16 @@ extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_inode *pdp);
 extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t inum,
-				xfs_fsblock_t *first,
-				struct xfs_defer_ops *dfops, xfs_extlen_t tot);
+				xfs_extlen_t tot);
 extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t *inum,
 				struct xfs_name *ci_name);
 extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t ino,
-				xfs_fsblock_t *first,
-				struct xfs_defer_ops *dfops, xfs_extlen_t tot);
+				xfs_extlen_t tot);
 extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t inum,
-				xfs_fsblock_t *first,
-				struct xfs_defer_ops *dfops, xfs_extlen_t tot);
+				xfs_extlen_t tot);
 extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name);
 
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 2daf874969ab..f1bb3434f51c 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -1012,7 +1012,7 @@ xfs_dir2_leafn_rebalance(
 	int			oldstale;	/* old count of stale leaves */
 #endif
 	int			oldsum;		/* old total leaf count */
-	int			swap;		/* swapped leaf blocks */
+	int			swap_blocks;	/* swapped leaf blocks */
 	struct xfs_dir2_leaf_entry *ents1;
 	struct xfs_dir2_leaf_entry *ents2;
 	struct xfs_dir3_icleaf_hdr hdr1;
@@ -1023,13 +1023,10 @@ xfs_dir2_leafn_rebalance(
 	/*
 	 * If the block order is wrong, swap the arguments.
 	 */
-	if ((swap = xfs_dir2_leafn_order(dp, blk1->bp, blk2->bp))) {
-		xfs_da_state_blk_t	*tmp;	/* temp for block swap */
+	swap_blocks = xfs_dir2_leafn_order(dp, blk1->bp, blk2->bp);
+	if (swap_blocks)
+		swap(blk1, blk2);
 
-		tmp = blk1;
-		blk1 = blk2;
-		blk2 = tmp;
-	}
 	leaf1 = blk1->bp->b_addr;
 	leaf2 = blk2->bp->b_addr;
 	dp->d_ops->leaf_hdr_from_disk(&hdr1, leaf1);
@@ -1093,11 +1090,11 @@ xfs_dir2_leafn_rebalance(
 	 * Mark whether we're inserting into the old or new leaf.
 	 */
 	if (hdr1.count < hdr2.count)
-		state->inleaf = swap;
+		state->inleaf = swap_blocks;
 	else if (hdr1.count > hdr2.count)
-		state->inleaf = !swap;
+		state->inleaf = !swap_blocks;
 	else
-		state->inleaf = swap ^ (blk1->index <= hdr1.count);
+		state->inleaf = swap_blocks ^ (blk1->index <= hdr1.count);
 	/*
 	 * Adjust the expected index for insertion.
 	 */
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index b9974e7a8e6e..66077a105cbb 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -53,7 +53,8 @@
 #define XFS_ERRTAG_LOG_ITEM_PIN				30
 #define XFS_ERRTAG_BUF_LRU_REF				31
 #define XFS_ERRTAG_FORCE_SCRUB_REPAIR			32
-#define XFS_ERRTAG_MAX					33
+#define XFS_ERRTAG_FORCE_SUMMARY_RECALC			33
+#define XFS_ERRTAG_MAX					34
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -91,5 +92,6 @@
 #define XFS_RANDOM_LOG_ITEM_PIN				1
 #define XFS_RANDOM_BUF_LRU_REF				2
 #define XFS_RANDOM_FORCE_SCRUB_REPAIR			1
+#define XFS_RANDOM_FORCE_SUMMARY_RECALC			1
 
 #endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 1c5a8aaf2bfc..059bc44c27e8 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -962,6 +962,9 @@ typedef enum xfs_dinode_fmt {
 		XFS_DFORK_DSIZE(dip, mp) : \
 		XFS_DFORK_ASIZE(dip, mp))
 
+#define XFS_DFORK_MAXEXT(dip, mp, w) \
+	(XFS_DFORK_SIZE(dip, mp, w) / sizeof(struct xfs_bmbt_rec))
+
 /*
  * Return pointers to the data or attribute forks.
  */
@@ -1526,6 +1529,8 @@ typedef struct xfs_bmdr_block {
 #define BMBT_STARTBLOCK_BITLEN	52
 #define BMBT_BLOCKCOUNT_BITLEN	21
 
+#define BMBT_STARTOFF_MASK	((1ULL << BMBT_STARTOFF_BITLEN) - 1)
+
 typedef struct xfs_bmbt_rec {
 	__be64			l0, l1;
 } xfs_bmbt_rec_t;
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 0d968e8143aa..a8f6db735d5d 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1838,23 +1838,24 @@ out_error:
  */
 STATIC void
 xfs_difree_inode_chunk(
-	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
 	xfs_agnumber_t			agno,
-	struct xfs_inobt_rec_incore	*rec,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_inobt_rec_incore	*rec)
 {
-	xfs_agblock_t	sagbno = XFS_AGINO_TO_AGBNO(mp, rec->ir_startino);
-	int		startidx, endidx;
-	int		nextbit;
-	xfs_agblock_t	agbno;
-	int		contigblk;
-	struct xfs_owner_info	oinfo;
+	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_agblock_t			sagbno = XFS_AGINO_TO_AGBNO(mp,
+							rec->ir_startino);
+	int				startidx, endidx;
+	int				nextbit;
+	xfs_agblock_t			agbno;
+	int				contigblk;
+	struct xfs_owner_info		oinfo;
 	DECLARE_BITMAP(holemask, XFS_INOBT_HOLEMASK_BITS);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
 
 	if (!xfs_inobt_issparse(rec->ir_holemask)) {
 		/* not sparse, calculate extent info directly */
-		xfs_bmap_add_free(mp, dfops, XFS_AGB_TO_FSB(mp, agno, sagbno),
+		xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, sagbno),
 				  mp->m_ialloc_blks, &oinfo);
 		return;
 	}
@@ -1898,7 +1899,7 @@ xfs_difree_inode_chunk(
 
 		ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
-		xfs_bmap_add_free(mp, dfops, XFS_AGB_TO_FSB(mp, agno, agbno),
+		xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, agbno),
 				  contigblk, &oinfo);
 
 		/* reset range to current bit and carry on... */
@@ -1915,7 +1916,6 @@ xfs_difree_inobt(
 	struct xfs_trans		*tp,
 	struct xfs_buf			*agbp,
 	xfs_agino_t			agino,
-	struct xfs_defer_ops		*dfops,
 	struct xfs_icluster		*xic,
 	struct xfs_inobt_rec_incore	*orec)
 {
@@ -2003,7 +2003,7 @@ xfs_difree_inobt(
 			goto error0;
 		}
 
-		xfs_difree_inode_chunk(mp, agno, &rec, dfops);
+		xfs_difree_inode_chunk(tp, agno, &rec);
 	} else {
 		xic->deleted = false;
 
@@ -2148,7 +2148,6 @@ int
 xfs_difree(
 	struct xfs_trans	*tp,		/* transaction pointer */
 	xfs_ino_t		inode,		/* inode to be freed */
-	struct xfs_defer_ops	*dfops,		/* extents to free */
 	struct xfs_icluster	*xic)	/* cluster info if deleted */
 {
 	/* REFERENCED */
@@ -2200,7 +2199,7 @@ xfs_difree(
 	/*
 	 * Fix up the inode allocation btree.
 	 */
-	error = xfs_difree_inobt(mp, tp, agbp, agino, dfops, xic, &rec);
+	error = xfs_difree_inobt(mp, tp, agbp, agino, xic, &rec);
 	if (error)
 		goto error0;
 
@@ -2260,7 +2259,7 @@ xfs_imap_lookup(
 	}
 
 	xfs_trans_brelse(tp, agbp);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	if (error)
 		return error;
 
@@ -2539,7 +2538,7 @@ xfs_agi_verify(
 		return __this_address;
 
 	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
-		if (agi->agi_unlinked[i] == NULLAGINO)
+		if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO))
 			continue;
 		if (!xfs_verify_ino(mp, be32_to_cpu(agi->agi_unlinked[i])))
 			return __this_address;
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 90b09c5f163b..e936b7cc9389 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -82,7 +82,6 @@ int					/* error */
 xfs_difree(
 	struct xfs_trans *tp,		/* transaction pointer */
 	xfs_ino_t	inode,		/* inode to be freed */
-	struct xfs_defer_ops *dfops,	/* extents to free */
 	struct xfs_icluster *ifree);	/* cluster info if deleted */
 
 /*
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index a5237afec5ab..86c50208a143 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -552,6 +552,7 @@ xfs_inobt_max_size(
 static int
 xfs_inobt_count_blocks(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_btnum_t		btnum,
 	xfs_extlen_t		*tree_blocks)
@@ -560,14 +561,14 @@ xfs_inobt_count_blocks(
 	struct xfs_btree_cur	*cur;
 	int			error;
 
-	error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
+	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
 	if (error)
 		return error;
 
-	cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, btnum);
 	error = xfs_btree_count_blocks(cur, tree_blocks);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
-	xfs_buf_relse(agbp);
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(tp, agbp);
 
 	return error;
 }
@@ -578,6 +579,7 @@ xfs_inobt_count_blocks(
 int
 xfs_finobt_calc_reserves(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
@@ -588,7 +590,7 @@ xfs_finobt_calc_reserves(
 	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
 		return 0;
 
-	error = xfs_inobt_count_blocks(mp, agno, XFS_BTNUM_FINO, &tree_len);
+	error = xfs_inobt_count_blocks(mp, tp, agno, XFS_BTNUM_FINO, &tree_len);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index bf8f0c405e7d..ebdd0c6b8766 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -60,8 +60,8 @@ int xfs_inobt_rec_check_count(struct xfs_mount *,
 #define xfs_inobt_rec_check_count(mp, rec)	0
 #endif	/* DEBUG */
 
-int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno,
-		xfs_extlen_t *ask, xfs_extlen_t *used);
+int xfs_finobt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp,
+		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
 extern xfs_extlen_t xfs_iallocbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
 
diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index b80c63faace2..771dd072015d 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -14,6 +14,7 @@
 #include "xfs_inode_fork.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_bmap.h"
 #include "xfs_trace.h"
 
 /*
@@ -612,6 +613,19 @@ xfs_iext_realloc_root(
 	cur->leaf = new;
 }
 
+/*
+ * Increment the sequence counter if we are on a COW fork.  This allows
+ * the writeback code to skip looking for a COW extent if the COW fork
+ * hasn't changed.  We use WRITE_ONCE here to ensure the update to the
+ * sequence counter is seen before the modifications to the extent
+ * tree itself take effect.
+ */
+static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp, int state)
+{
+	if (state & BMAP_COWFORK)
+		WRITE_ONCE(ifp->if_seq, READ_ONCE(ifp->if_seq) + 1);
+}
+
 void
 xfs_iext_insert(
 	struct xfs_inode	*ip,
@@ -624,6 +638,8 @@ xfs_iext_insert(
 	struct xfs_iext_leaf	*new = NULL;
 	int			nr_entries, i;
 
+	xfs_iext_inc_seq(ifp, state);
+
 	if (ifp->if_height == 0)
 		xfs_iext_alloc_root(ifp, cur);
 	else if (ifp->if_height == 1)
@@ -864,6 +880,8 @@ xfs_iext_remove(
 	ASSERT(ifp->if_u1.if_root != NULL);
 	ASSERT(xfs_iext_valid(ifp, cur));
 
+	xfs_iext_inc_seq(ifp, state);
+
 	nr_entries = xfs_iext_leaf_nr_entries(ifp, leaf, cur->pos) - 1;
 	for (i = cur->pos; i < nr_entries; i++)
 		leaf->recs[i] = leaf->recs[i + 1];
@@ -970,6 +988,8 @@ xfs_iext_update_extent(
 {
 	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
 
+	xfs_iext_inc_seq(ifp, state);
+
 	if (cur->pos == 0) {
 		struct xfs_bmbt_irec	old;
 
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index d38d724534c4..30d1d60f1d46 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -374,6 +374,47 @@ xfs_log_dinode_to_disk(
 	}
 }
 
+static xfs_failaddr_t
+xfs_dinode_verify_fork(
+	struct xfs_dinode	*dip,
+	struct xfs_mount	*mp,
+	int			whichfork)
+{
+	uint32_t		di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+
+	switch (XFS_DFORK_FORMAT(dip, whichfork)) {
+	case XFS_DINODE_FMT_LOCAL:
+		/*
+		 * no local regular files yet
+		 */
+		if (whichfork == XFS_DATA_FORK) {
+			if (S_ISREG(be16_to_cpu(dip->di_mode)))
+				return __this_address;
+			if (be64_to_cpu(dip->di_size) >
+					XFS_DFORK_SIZE(dip, mp, whichfork))
+				return __this_address;
+		}
+		if (di_nextents)
+			return __this_address;
+		break;
+	case XFS_DINODE_FMT_EXTENTS:
+		if (di_nextents > XFS_DFORK_MAXEXT(dip, mp, whichfork))
+			return __this_address;
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		if (whichfork == XFS_ATTR_FORK) {
+			if (di_nextents > MAXAEXTNUM)
+				return __this_address;
+		} else if (di_nextents > MAXEXTNUM) {
+			return __this_address;
+		}
+		break;
+	default:
+		return __this_address;
+	}
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
@@ -441,24 +482,9 @@ xfs_dinode_verify(
 	case S_IFREG:
 	case S_IFLNK:
 	case S_IFDIR:
-		switch (dip->di_format) {
-		case XFS_DINODE_FMT_LOCAL:
-			/*
-			 * no local regular files yet
-			 */
-			if (S_ISREG(mode))
-				return __this_address;
-			if (di_size > XFS_DFORK_DSIZE(dip, mp))
-				return __this_address;
-			if (dip->di_nextents)
-				return __this_address;
-			/* fall through */
-		case XFS_DINODE_FMT_EXTENTS:
-		case XFS_DINODE_FMT_BTREE:
-			break;
-		default:
-			return __this_address;
-		}
+		fa = xfs_dinode_verify_fork(dip, mp, XFS_DATA_FORK);
+		if (fa)
+			return fa;
 		break;
 	case 0:
 		/* Uninitialized inode ok. */
@@ -468,17 +494,9 @@ xfs_dinode_verify(
 	}
 
 	if (XFS_DFORK_Q(dip)) {
-		switch (dip->di_aformat) {
-		case XFS_DINODE_FMT_LOCAL:
-			if (dip->di_anextents)
-				return __this_address;
-		/* fall through */
-		case XFS_DINODE_FMT_EXTENTS:
-		case XFS_DINODE_FMT_BTREE:
-			break;
-		default:
-			return __this_address;
-		}
+		fa = xfs_dinode_verify_fork(dip, mp, XFS_ATTR_FORK);
+		if (fa)
+			return fa;
 	} else {
 		/*
 		 * If there is no fork offset, this may be a freshly-made inode
@@ -713,7 +731,8 @@ xfs_inode_validate_extsize(
 	if ((hint_flag || inherit_flag) && extsize == 0)
 		return __this_address;
 
-	if (!(hint_flag || inherit_flag) && extsize != 0)
+	/* free inodes get flags set to zero but extsize remains */
+	if (mode && !(hint_flag || inherit_flag) && extsize != 0)
 		return __this_address;
 
 	if (extsize_bytes % blocksize_bytes)
@@ -759,7 +778,8 @@ xfs_inode_validate_cowextsize(
 	if (hint_flag && cowextsize == 0)
 		return __this_address;
 
-	if (!hint_flag && cowextsize != 0)
+	/* free inodes get flags set to zero but cowextsize remains */
+	if (mode && !hint_flag && cowextsize != 0)
 		return __this_address;
 
 	if (hint_flag && rt_flag)
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 183ec0cb8921..f9acf1d436f6 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -158,7 +158,6 @@ xfs_init_local_fork(
 	}
 
 	ifp->if_bytes = size;
-	ifp->if_real_bytes = real_size;
 	ifp->if_flags &= ~(XFS_IFEXTENTS | XFS_IFBROOT);
 	ifp->if_flags |= XFS_IFINLINE;
 }
@@ -226,7 +225,6 @@ xfs_iformat_extents(
 		return -EFSCORRUPTED;
 	}
 
-	ifp->if_real_bytes = 0;
 	ifp->if_bytes = 0;
 	ifp->if_u1.if_root = NULL;
 	ifp->if_height = 0;
@@ -271,7 +269,7 @@ xfs_iformat_btree(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_bmdr_block_t	*dfp;
-	xfs_ifork_t		*ifp;
+	struct xfs_ifork	*ifp;
 	/* REFERENCED */
 	int			nrecs;
 	int			size;
@@ -317,7 +315,6 @@ xfs_iformat_btree(
 	ifp->if_flags &= ~XFS_IFEXTENTS;
 	ifp->if_flags |= XFS_IFBROOT;
 
-	ifp->if_real_bytes = 0;
 	ifp->if_bytes = 0;
 	ifp->if_u1.if_root = NULL;
 	ifp->if_height = 0;
@@ -350,7 +347,7 @@ xfs_iroot_realloc(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	int			cur_max;
-	xfs_ifork_t		*ifp;
+	struct xfs_ifork	*ifp;
 	struct xfs_btree_block	*new_broot;
 	int			new_max;
 	size_t			new_size;
@@ -471,55 +468,34 @@ xfs_iroot_realloc(
  */
 void
 xfs_idata_realloc(
-	xfs_inode_t	*ip,
-	int		byte_diff,
-	int		whichfork)
+	struct xfs_inode	*ip,
+	int			byte_diff,
+	int			whichfork)
 {
-	xfs_ifork_t	*ifp;
-	int		new_size;
-	int		real_size;
-
-	if (byte_diff == 0) {
-		return;
-	}
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	int			new_size = (int)ifp->if_bytes + byte_diff;
 
-	ifp = XFS_IFORK_PTR(ip, whichfork);
-	new_size = (int)ifp->if_bytes + byte_diff;
 	ASSERT(new_size >= 0);
+	ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork));
+
+	if (byte_diff == 0)
+		return;
 
 	if (new_size == 0) {
 		kmem_free(ifp->if_u1.if_data);
 		ifp->if_u1.if_data = NULL;
-		real_size = 0;
-	} else {
-		/*
-		 * Stuck with malloc/realloc.
-		 * For inline data, the underlying buffer must be
-		 * a multiple of 4 bytes in size so that it can be
-		 * logged and stay on word boundaries.  We enforce
-		 * that here.
-		 */
-		real_size = roundup(new_size, 4);
-		if (ifp->if_u1.if_data == NULL) {
-			ASSERT(ifp->if_real_bytes == 0);
-			ifp->if_u1.if_data = kmem_alloc(real_size,
-							KM_SLEEP | KM_NOFS);
-		} else {
-			/*
-			 * Only do the realloc if the underlying size
-			 * is really changing.
-			 */
-			if (ifp->if_real_bytes != real_size) {
-				ifp->if_u1.if_data =
-					kmem_realloc(ifp->if_u1.if_data,
-							real_size,
-							KM_SLEEP | KM_NOFS);
-			}
-		}
+		ifp->if_bytes = 0;
+		return;
 	}
-	ifp->if_real_bytes = real_size;
+
+	/*
+	 * For inline data, the underlying buffer must be a multiple of 4 bytes
+	 * in size so that it can be logged and stay on word boundaries.
+	 * We enforce that here.
+	 */
+	ifp->if_u1.if_data = kmem_realloc(ifp->if_u1.if_data,
+			roundup(new_size, 4), KM_SLEEP | KM_NOFS);
 	ifp->if_bytes = new_size;
-	ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
 }
 
 void
@@ -527,7 +503,7 @@ xfs_idestroy_fork(
 	xfs_inode_t	*ip,
 	int		whichfork)
 {
-	xfs_ifork_t	*ifp;
+	struct xfs_ifork	*ifp;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	if (ifp->if_broot != NULL) {
@@ -543,17 +519,13 @@ xfs_idestroy_fork(
 	 */
 	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
 		if (ifp->if_u1.if_data != NULL) {
-			ASSERT(ifp->if_real_bytes != 0);
 			kmem_free(ifp->if_u1.if_data);
 			ifp->if_u1.if_data = NULL;
-			ifp->if_real_bytes = 0;
 		}
 	} else if ((ifp->if_flags & XFS_IFEXTENTS) && ifp->if_height) {
 		xfs_iext_destroy(ifp);
 	}
 
-	ASSERT(ifp->if_real_bytes == 0);
-
 	if (whichfork == XFS_ATTR_FORK) {
 		kmem_zone_free(xfs_ifork_zone, ip->i_afp);
 		ip->i_afp = NULL;
@@ -620,7 +592,7 @@ xfs_iflush_fork(
 	int			whichfork)
 {
 	char			*cp;
-	xfs_ifork_t		*ifp;
+	struct xfs_ifork	*ifp;
 	xfs_mount_t		*mp;
 	static const short	brootflag[2] =
 		{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 781b1603df5e..60361d2d74a1 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -12,9 +12,9 @@ struct xfs_dinode;
 /*
  * File incore extent information, present for each of data & attr forks.
  */
-typedef struct xfs_ifork {
+struct xfs_ifork {
 	int			if_bytes;	/* bytes in if_u1 */
-	int			if_real_bytes;	/* bytes allocated in if_u1 */
+	unsigned int		if_seq;		/* cow fork mod counter */
 	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	unsigned char		if_flags;	/* per-fork flags */
@@ -23,7 +23,7 @@ typedef struct xfs_ifork {
 		void		*if_root;	/* extent tree root */
 		char		*if_data;	/* inline file data */
 	} if_u1;
-} xfs_ifork_t;
+};
 
 /*
  * Per-fork incore inode flags.
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 79bb79853c9f..e5f97c69b320 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -77,6 +77,19 @@ static inline uint xlog_get_cycle(char *ptr)
 
 #define XLOG_UNMOUNT_TYPE	0x556e	/* Un for Unmount */
 
+/*
+ * Log item for unmount records.
+ *
+ * The unmount record used to have a string "Unmount filesystem--" in the
+ * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE).
+ * We just write the magic number now; see xfs_log_unmount_write.
+ */
+struct xfs_unmount_log_format {
+	uint16_t	magic;	/* XLOG_UNMOUNT_TYPE */
+	uint16_t	pad1;
+	uint32_t	pad2;	/* may as well make it 64 bits */
+};
+
 /* Region types for iovec's i_type */
 #define XLOG_REG_TYPE_BFORMAT		1
 #define XLOG_REG_TYPE_BCHUNK		2
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 9dda6fd0bb13..542aa1475b5f 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -34,11 +34,9 @@ enum xfs_refc_adjust_op {
 };
 
 STATIC int __xfs_refcount_cow_alloc(struct xfs_btree_cur *rcur,
-		xfs_agblock_t agbno, xfs_extlen_t aglen,
-		struct xfs_defer_ops *dfops);
+		xfs_agblock_t agbno, xfs_extlen_t aglen);
 STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur,
-		xfs_agblock_t agbno, xfs_extlen_t aglen,
-		struct xfs_defer_ops *dfops);
+		xfs_agblock_t agbno, xfs_extlen_t aglen);
 
 /*
  * Look up the first record less than or equal to [bno, len] in the btree
@@ -870,7 +868,6 @@ xfs_refcount_adjust_extents(
 	xfs_agblock_t		*agbno,
 	xfs_extlen_t		*aglen,
 	enum xfs_refc_adjust_op	adj,
-	struct xfs_defer_ops	*dfops,
 	struct xfs_owner_info	*oinfo)
 {
 	struct xfs_refcount_irec	ext, tmp;
@@ -925,8 +922,8 @@ xfs_refcount_adjust_extents(
 				fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
 						cur->bc_private.a.agno,
 						tmp.rc_startblock);
-				xfs_bmap_add_free(cur->bc_mp, dfops, fsbno,
-						tmp.rc_blockcount, oinfo);
+				xfs_bmap_add_free(cur->bc_tp, fsbno,
+						  tmp.rc_blockcount, oinfo);
 			}
 
 			(*agbno) += tmp.rc_blockcount;
@@ -968,8 +965,8 @@ xfs_refcount_adjust_extents(
 			fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
 					cur->bc_private.a.agno,
 					ext.rc_startblock);
-			xfs_bmap_add_free(cur->bc_mp, dfops, fsbno,
-					ext.rc_blockcount, oinfo);
+			xfs_bmap_add_free(cur->bc_tp, fsbno, ext.rc_blockcount,
+					  oinfo);
 		}
 
 skip:
@@ -998,7 +995,6 @@ xfs_refcount_adjust(
 	xfs_agblock_t		*new_agbno,
 	xfs_extlen_t		*new_aglen,
 	enum xfs_refc_adjust_op	adj,
-	struct xfs_defer_ops	*dfops,
 	struct xfs_owner_info	*oinfo)
 {
 	bool			shape_changed;
@@ -1043,7 +1039,7 @@ xfs_refcount_adjust(
 
 	/* Now that we've taken care of the ends, adjust the middle extents */
 	error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen,
-			adj, dfops, oinfo);
+			adj, oinfo);
 	if (error)
 		goto out_error;
 
@@ -1067,7 +1063,7 @@ xfs_refcount_finish_one_cleanup(
 	if (rcur == NULL)
 		return;
 	agbp = rcur->bc_private.a.agbp;
-	xfs_btree_del_cursor(rcur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(rcur, error);
 	if (error)
 		xfs_trans_brelse(tp, agbp);
 }
@@ -1082,7 +1078,6 @@ xfs_refcount_finish_one_cleanup(
 int
 xfs_refcount_finish_one(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dfops,
 	enum xfs_refcount_intent_type	type,
 	xfs_fsblock_t			startblock,
 	xfs_extlen_t			blockcount,
@@ -1132,7 +1127,7 @@ xfs_refcount_finish_one(
 		if (!agbp)
 			return -EFSCORRUPTED;
 
-		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, dfops);
+		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
 		if (!rcur) {
 			error = -ENOMEM;
 			goto out_cur;
@@ -1145,23 +1140,23 @@ xfs_refcount_finish_one(
 	switch (type) {
 	case XFS_REFCOUNT_INCREASE:
 		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
-			new_len, XFS_REFCOUNT_ADJUST_INCREASE, dfops, NULL);
+			new_len, XFS_REFCOUNT_ADJUST_INCREASE, NULL);
 		*new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno);
 		break;
 	case XFS_REFCOUNT_DECREASE:
 		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
-			new_len, XFS_REFCOUNT_ADJUST_DECREASE, dfops, NULL);
+			new_len, XFS_REFCOUNT_ADJUST_DECREASE, NULL);
 		*new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno);
 		break;
 	case XFS_REFCOUNT_ALLOC_COW:
 		*new_fsb = startblock + blockcount;
 		*new_len = 0;
-		error = __xfs_refcount_cow_alloc(rcur, bno, blockcount, dfops);
+		error = __xfs_refcount_cow_alloc(rcur, bno, blockcount);
 		break;
 	case XFS_REFCOUNT_FREE_COW:
 		*new_fsb = startblock + blockcount;
 		*new_len = 0;
-		error = __xfs_refcount_cow_free(rcur, bno, blockcount, dfops);
+		error = __xfs_refcount_cow_free(rcur, bno, blockcount);
 		break;
 	default:
 		ASSERT(0);
@@ -1183,16 +1178,16 @@ out_cur:
  */
 static int
 __xfs_refcount_add(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	enum xfs_refcount_intent_type	type,
 	xfs_fsblock_t			startblock,
 	xfs_extlen_t			blockcount)
 {
 	struct xfs_refcount_intent	*ri;
 
-	trace_xfs_refcount_defer(mp, XFS_FSB_TO_AGNO(mp, startblock),
-			type, XFS_FSB_TO_AGBNO(mp, startblock),
+	trace_xfs_refcount_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, startblock),
+			type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
 			blockcount);
 
 	ri = kmem_alloc(sizeof(struct xfs_refcount_intent),
@@ -1202,7 +1197,7 @@ __xfs_refcount_add(
 	ri->ri_startblock = startblock;
 	ri->ri_blockcount = blockcount;
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
 	return 0;
 }
 
@@ -1211,14 +1206,13 @@ __xfs_refcount_add(
  */
 int
 xfs_refcount_increase_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	struct xfs_bmbt_irec		*PREV)
 {
-	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+	if (!xfs_sb_version_hasreflink(&tp->t_mountp->m_sb))
 		return 0;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_INCREASE,
+	return __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE,
 			PREV->br_startblock, PREV->br_blockcount);
 }
 
@@ -1227,14 +1221,13 @@ xfs_refcount_increase_extent(
  */
 int
 xfs_refcount_decrease_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	struct xfs_bmbt_irec		*PREV)
 {
-	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+	if (!xfs_sb_version_hasreflink(&tp->t_mountp->m_sb))
 		return 0;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_DECREASE,
+	return __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE,
 			PREV->br_startblock, PREV->br_blockcount);
 }
 
@@ -1522,8 +1515,7 @@ STATIC int
 __xfs_refcount_cow_alloc(
 	struct xfs_btree_cur	*rcur,
 	xfs_agblock_t		agbno,
-	xfs_extlen_t		aglen,
-	struct xfs_defer_ops	*dfops)
+	xfs_extlen_t		aglen)
 {
 	trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_private.a.agno,
 			agbno, aglen);
@@ -1540,8 +1532,7 @@ STATIC int
 __xfs_refcount_cow_free(
 	struct xfs_btree_cur	*rcur,
 	xfs_agblock_t		agbno,
-	xfs_extlen_t		aglen,
-	struct xfs_defer_ops	*dfops)
+	xfs_extlen_t		aglen)
 {
 	trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_private.a.agno,
 			agbno, aglen);
@@ -1554,47 +1545,45 @@ __xfs_refcount_cow_free(
 /* Record a CoW staging extent in the refcount btree. */
 int
 xfs_refcount_alloc_cow_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			fsb,
 	xfs_extlen_t			len)
 {
+	struct xfs_mount		*mp = tp->t_mountp;
 	int				error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
-	error = __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW,
-			fsb, len);
+	error = __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len);
 	if (error)
 		return error;
 
 	/* Add rmap entry */
-	return xfs_rmap_alloc_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb),
+	return xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
 			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
 }
 
 /* Forget a CoW staging event in the refcount btree. */
 int
 xfs_refcount_free_cow_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			fsb,
 	xfs_extlen_t			len)
 {
+	struct xfs_mount		*mp = tp->t_mountp;
 	int				error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
 	/* Remove rmap entry */
-	error = xfs_rmap_free_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb),
+	error = xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
 			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
 	if (error)
 		return error;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_FREE_COW,
-			fsb, len);
+	return __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len);
 }
 
 struct xfs_refcount_recovery {
@@ -1635,7 +1624,6 @@ xfs_refcount_recover_cow_leftovers(
 	struct list_head		debris;
 	union xfs_btree_irec		low;
 	union xfs_btree_irec		high;
-	struct xfs_defer_ops		dfops;
 	xfs_fsblock_t			fsb;
 	xfs_agblock_t			agbno;
 	int				error;
@@ -1666,7 +1654,7 @@ xfs_refcount_recover_cow_leftovers(
 		error = -ENOMEM;
 		goto out_trans;
 	}
-	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
 
 	/* Find all the leftover CoW staging extents. */
 	memset(&low, 0, sizeof(low));
@@ -1675,11 +1663,11 @@ xfs_refcount_recover_cow_leftovers(
 	high.rc.rc_startblock = -1U;
 	error = xfs_btree_query_range(cur, &low, &high,
 			xfs_refcount_recover_extent, &debris);
-	if (error)
-		goto out_cursor;
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	xfs_trans_brelse(tp, agbp);
 	xfs_trans_cancel(tp);
+	if (error)
+		goto out_free;
 
 	/* Now iterate the list to free the leftovers */
 	list_for_each_entry_safe(rr, n, &debris, rr_list) {
@@ -1691,21 +1679,15 @@ xfs_refcount_recover_cow_leftovers(
 		trace_xfs_refcount_recover_extent(mp, agno, &rr->rr_rrec);
 
 		/* Free the orphan record */
-		xfs_defer_init(&dfops, &fsb);
 		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
 		fsb = XFS_AGB_TO_FSB(mp, agno, agbno);
-		error = xfs_refcount_free_cow_extent(mp, &dfops, fsb,
+		error = xfs_refcount_free_cow_extent(tp, fsb,
 				rr->rr_rrec.rc_blockcount);
 		if (error)
-			goto out_defer;
+			goto out_trans;
 
 		/* Free the block. */
-		xfs_bmap_add_free(mp, &dfops, fsb,
-				rr->rr_rrec.rc_blockcount, NULL);
-
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto out_defer;
+		xfs_bmap_add_free(tp, fsb, rr->rr_rrec.rc_blockcount, NULL);
 
 		error = xfs_trans_commit(tp);
 		if (error)
@@ -1716,8 +1698,6 @@ xfs_refcount_recover_cow_leftovers(
 	}
 
 	return error;
-out_defer:
-	xfs_defer_cancel(&dfops);
 out_trans:
 	xfs_trans_cancel(tp);
 out_free:
@@ -1727,11 +1707,6 @@ out_free:
 		kmem_free(rr);
 	}
 	return error;
-
-out_cursor:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-	xfs_trans_brelse(tp, agbp);
-	goto out_trans;
 }
 
 /* Is there a record covering a given extent? */
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 5fef74412727..1d9c518575e7 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -29,29 +29,26 @@ struct xfs_refcount_intent {
 	xfs_extlen_t				ri_blockcount;
 };
 
-extern int xfs_refcount_increase_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, struct xfs_bmbt_irec *irec);
-extern int xfs_refcount_decrease_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, struct xfs_bmbt_irec *irec);
+extern int xfs_refcount_increase_extent(struct xfs_trans *tp,
+		struct xfs_bmbt_irec *irec);
+extern int xfs_refcount_decrease_extent(struct xfs_trans *tp,
+		struct xfs_bmbt_irec *irec);
 
 extern void xfs_refcount_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
 extern int xfs_refcount_finish_one(struct xfs_trans *tp,
-		struct xfs_defer_ops *dfops, enum xfs_refcount_intent_type type,
-		xfs_fsblock_t startblock, xfs_extlen_t blockcount,
-		xfs_fsblock_t *new_fsb, xfs_extlen_t *new_len,
-		struct xfs_btree_cur **pcur);
+		enum xfs_refcount_intent_type type, xfs_fsblock_t startblock,
+		xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb,
+		xfs_extlen_t *new_len, struct xfs_btree_cur **pcur);
 
 extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur,
 		xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno,
 		xfs_extlen_t *flen, bool find_end_of_shared);
 
-extern int xfs_refcount_alloc_cow_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, xfs_fsblock_t fsb,
-		xfs_extlen_t len);
-extern int xfs_refcount_free_cow_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, xfs_fsblock_t fsb,
-		xfs_extlen_t len);
+extern int xfs_refcount_alloc_cow_extent(struct xfs_trans *tp,
+		xfs_fsblock_t fsb, xfs_extlen_t len);
+extern int xfs_refcount_free_cow_extent(struct xfs_trans *tp,
+		xfs_fsblock_t fsb, xfs_extlen_t len);
 extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
 		xfs_agnumber_t agno);
 
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index b71937982c5b..1aaa01c97517 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -27,8 +27,7 @@ xfs_refcountbt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_refcountbt_init_cursor(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agbp, cur->bc_private.a.agno,
-			cur->bc_private.a.dfops);
+			cur->bc_private.a.agbp, cur->bc_private.a.agno);
 }
 
 STATIC void
@@ -71,7 +70,6 @@ xfs_refcountbt_alloc_block(
 	args.type = XFS_ALLOCTYPE_NEAR_BNO;
 	args.fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno,
 			xfs_refc_block(args.mp));
-	args.firstblock = args.fsbno;
 	xfs_rmap_ag_owner(&args.oinfo, XFS_RMAP_OWN_REFC);
 	args.minlen = args.maxlen = args.prod = 1;
 	args.resv = XFS_AG_RESV_METADATA;
@@ -323,8 +321,7 @@ xfs_refcountbt_init_cursor(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
-	xfs_agnumber_t		agno,
-	struct xfs_defer_ops	*dfops)
+	xfs_agnumber_t		agno)
 {
 	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
 	struct xfs_btree_cur	*cur;
@@ -344,7 +341,6 @@ xfs_refcountbt_init_cursor(
 
 	cur->bc_private.a.agbp = agbp;
 	cur->bc_private.a.agno = agno;
-	cur->bc_private.a.dfops = dfops;
 	cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
 	cur->bc_private.a.priv.refc.nr_ops = 0;
@@ -408,6 +404,7 @@ xfs_refcountbt_max_size(
 int
 xfs_refcountbt_calc_reserves(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
@@ -422,14 +419,14 @@ xfs_refcountbt_calc_reserves(
 		return 0;
 
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
 	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_refcount_blocks);
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
 
 	*ask += xfs_refcountbt_max_size(mp, agblocks);
 	*used += tree_len;
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index d2852b6e1fa8..ba416f71c824 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -44,8 +44,8 @@ struct xfs_mount;
 		 ((index) - 1) * sizeof(xfs_refcount_ptr_t)))
 
 extern struct xfs_btree_cur *xfs_refcountbt_init_cursor(struct xfs_mount *mp,
-		struct xfs_trans *tp, struct xfs_buf *agbp, xfs_agnumber_t agno,
-		struct xfs_defer_ops *dfops);
+		struct xfs_trans *tp, struct xfs_buf *agbp,
+		xfs_agnumber_t agno);
 extern int xfs_refcountbt_maxrecs(int blocklen, bool leaf);
 extern void xfs_refcountbt_compute_maxlevels(struct xfs_mount *mp);
 
@@ -55,6 +55,7 @@ extern xfs_extlen_t xfs_refcountbt_max_size(struct xfs_mount *mp,
 		xfs_agblock_t agblocks);
 
 extern int xfs_refcountbt_calc_reserves(struct xfs_mount *mp,
-		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
+		struct xfs_trans *tp, xfs_agnumber_t agno, xfs_extlen_t *ask,
+		xfs_extlen_t *used);
 
 #endif	/* __XFS_REFCOUNT_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index d4460b0d2d81..245af452840e 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -670,14 +670,8 @@ xfs_rmap_free(
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);
 
 	error = xfs_rmap_unmap(cur, bno, len, false, oinfo);
-	if (error)
-		goto out_error;
 
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
-	return 0;
-
-out_error:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -753,19 +747,19 @@ xfs_rmap_map(
 			&have_lt);
 	if (error)
 		goto out_error;
-	XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
-
-	error = xfs_rmap_get_rec(cur, &ltrec, &have_lt);
-	if (error)
-		goto out_error;
-	XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
-	trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
-			cur->bc_private.a.agno, ltrec.rm_startblock,
-			ltrec.rm_blockcount, ltrec.rm_owner,
-			ltrec.rm_offset, ltrec.rm_flags);
+	if (have_lt) {
+		error = xfs_rmap_get_rec(cur, &ltrec, &have_lt);
+		if (error)
+			goto out_error;
+		XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
+		trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
+				cur->bc_private.a.agno, ltrec.rm_startblock,
+				ltrec.rm_blockcount, ltrec.rm_owner,
+				ltrec.rm_offset, ltrec.rm_flags);
 
-	if (!xfs_rmap_is_mergeable(&ltrec, owner, flags))
-		have_lt = 0;
+		if (!xfs_rmap_is_mergeable(&ltrec, owner, flags))
+			have_lt = 0;
+	}
 
 	XFS_WANT_CORRUPTED_GOTO(mp,
 		have_lt == 0 ||
@@ -912,14 +906,8 @@ xfs_rmap_alloc(
 
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);
 	error = xfs_rmap_map(cur, bno, len, false, oinfo);
-	if (error)
-		goto out_error;
-
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
-	return 0;
 
-out_error:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -2156,7 +2144,7 @@ xfs_rmap_finish_one_cleanup(
 	if (rcur == NULL)
 		return;
 	agbp = rcur->bc_private.a.agbp;
-	xfs_btree_del_cursor(rcur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(rcur, error);
 	if (error)
 		xfs_trans_brelse(tp, agbp);
 }
@@ -2289,18 +2277,18 @@ xfs_rmap_update_is_needed(
  */
 static int
 __xfs_rmap_add(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	enum xfs_rmap_intent_type	type,
 	uint64_t			owner,
 	int				whichfork,
 	struct xfs_bmbt_irec		*bmap)
 {
-	struct xfs_rmap_intent	*ri;
+	struct xfs_rmap_intent		*ri;
 
-	trace_xfs_rmap_defer(mp, XFS_FSB_TO_AGNO(mp, bmap->br_startblock),
+	trace_xfs_rmap_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
 			type,
-			XFS_FSB_TO_AGBNO(mp, bmap->br_startblock),
+			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
 			owner, whichfork,
 			bmap->br_startoff,
 			bmap->br_blockcount,
@@ -2313,23 +2301,22 @@ __xfs_rmap_add(
 	ri->ri_whichfork = whichfork;
 	ri->ri_bmap = *bmap;
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
 	return 0;
 }
 
 /* Map an extent into a file. */
 int
 xfs_rmap_map_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_rmap_update_is_needed(mp, whichfork))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return 0;
 
-	return __xfs_rmap_add(mp, dfops, xfs_is_reflink_inode(ip) ?
+	return __xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
 			XFS_RMAP_MAP_SHARED : XFS_RMAP_MAP, ip->i_ino,
 			whichfork, PREV);
 }
@@ -2337,25 +2324,29 @@ xfs_rmap_map_extent(
 /* Unmap an extent out of a file. */
 int
 xfs_rmap_unmap_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_rmap_update_is_needed(mp, whichfork))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return 0;
 
-	return __xfs_rmap_add(mp, dfops, xfs_is_reflink_inode(ip) ?
+	return __xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
 			XFS_RMAP_UNMAP_SHARED : XFS_RMAP_UNMAP, ip->i_ino,
 			whichfork, PREV);
 }
 
-/* Convert a data fork extent from unwritten to real or vice versa. */
+/*
+ * Convert a data fork extent from unwritten to real or vice versa.
+ *
+ * Note that tp can be NULL here as no transaction is used for COW fork
+ * unwritten conversion.
+ */
 int
 xfs_rmap_convert_extent(
 	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
@@ -2363,7 +2354,7 @@ xfs_rmap_convert_extent(
 	if (!xfs_rmap_update_is_needed(mp, whichfork))
 		return 0;
 
-	return __xfs_rmap_add(mp, dfops, xfs_is_reflink_inode(ip) ?
+	return __xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
 			XFS_RMAP_CONVERT_SHARED : XFS_RMAP_CONVERT, ip->i_ino,
 			whichfork, PREV);
 }
@@ -2371,8 +2362,7 @@ xfs_rmap_convert_extent(
 /* Schedule the creation of an rmap for non-file data. */
 int
 xfs_rmap_alloc_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
@@ -2380,23 +2370,21 @@ xfs_rmap_alloc_extent(
 {
 	struct xfs_bmbt_irec	bmap;
 
-	if (!xfs_rmap_update_is_needed(mp, XFS_DATA_FORK))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK))
 		return 0;
 
-	bmap.br_startblock = XFS_AGB_TO_FSB(mp, agno, bno);
+	bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno);
 	bmap.br_blockcount = len;
 	bmap.br_startoff = 0;
 	bmap.br_state = XFS_EXT_NORM;
 
-	return __xfs_rmap_add(mp, dfops, XFS_RMAP_ALLOC, owner,
-			XFS_DATA_FORK, &bmap);
+	return __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, XFS_DATA_FORK, &bmap);
 }
 
 /* Schedule the deletion of an rmap for non-file data. */
 int
 xfs_rmap_free_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
@@ -2404,16 +2392,15 @@ xfs_rmap_free_extent(
 {
 	struct xfs_bmbt_irec	bmap;
 
-	if (!xfs_rmap_update_is_needed(mp, XFS_DATA_FORK))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK))
 		return 0;
 
-	bmap.br_startblock = XFS_AGB_TO_FSB(mp, agno, bno);
+	bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno);
 	bmap.br_blockcount = len;
 	bmap.br_startoff = 0;
 	bmap.br_state = XFS_EXT_NORM;
 
-	return __xfs_rmap_add(mp, dfops, XFS_RMAP_FREE, owner,
-			XFS_DATA_FORK, &bmap);
+	return __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, XFS_DATA_FORK, &bmap);
 }
 
 /* Compare rmap records.  Returns -1 if a < b, 1 if a > b, and 0 if equal. */
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 9f19454768b2..157dc722ad35 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -185,21 +185,17 @@ struct xfs_rmap_intent {
 };
 
 /* functions for updating the rmapbt based on bmbt map/unmap operations */
-int xfs_rmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
+int xfs_rmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		int whichfork, struct xfs_bmbt_irec *imap);
+int xfs_rmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		int whichfork, struct xfs_bmbt_irec *imap);
+int xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_trans *tp,
 		struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *imap);
-int xfs_rmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, int whichfork,
-		struct xfs_bmbt_irec *imap);
-int xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, int whichfork,
-		struct xfs_bmbt_irec *imap);
-int xfs_rmap_alloc_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		uint64_t owner);
-int xfs_rmap_free_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		uint64_t owner);
+int xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
+		xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner);
+int xfs_rmap_free_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
+		xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner);
 
 void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 221a88ea60bb..f79cf040d745 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -554,6 +554,7 @@ xfs_rmapbt_max_size(
 int
 xfs_rmapbt_calc_reserves(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
@@ -567,14 +568,14 @@ xfs_rmapbt_calc_reserves(
 	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
 		return 0;
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
 	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_rmap_blocks);
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
 
 	/* Reserve 1% of the AG or enough for 1 block per record. */
 	*ask += max(agblocks / 100, xfs_rmapbt_max_size(mp, agblocks));
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index 50198b6c3bb2..820d668b063d 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -51,7 +51,7 @@ extern xfs_extlen_t xfs_rmapbt_calc_size(struct xfs_mount *mp,
 extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp,
 		xfs_agblock_t agblocks);
 
-extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp,
+extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp,
 		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
 
 #endif	/* __XFS_RMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 65fc4ed2e9a1..b228c821bae6 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1029,8 +1029,8 @@ xfs_rtalloc_query_range(
 	if (low_rec->ar_startext >= mp->m_sb.sb_rextents ||
 	    low_rec->ar_startext == high_rec->ar_startext)
 		return 0;
-	if (high_rec->ar_startext >= mp->m_sb.sb_rextents)
-		high_rec->ar_startext = mp->m_sb.sb_rextents - 1;
+	if (high_rec->ar_startext > mp->m_sb.sb_rextents)
+		high_rec->ar_startext = mp->m_sb.sb_rextents;
 
 	/* Iterate the bitmap, looking for discrepancies. */
 	rtstart = low_rec->ar_startext;
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 350119eeaecb..081f46e30556 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -96,80 +96,146 @@ xfs_perag_put(
 	trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
 }
 
-/*
- * Check the validity of the SB found.
- */
+/* Check all the superblock fields we care about when reading one in. */
 STATIC int
-xfs_mount_validate_sb(
-	xfs_mount_t	*mp,
-	xfs_sb_t	*sbp,
-	bool		check_inprogress,
-	bool		check_version)
+xfs_validate_sb_read(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp)
 {
-	uint32_t	agcount = 0;
-	uint32_t	rem;
-
-	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
-		xfs_warn(mp, "bad magic number");
-		return -EWRONGFS;
-	}
-
-
-	if (!xfs_sb_good_version(sbp)) {
-		xfs_warn(mp, "bad version");
-		return -EWRONGFS;
-	}
+	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
+		return 0;
 
 	/*
-	 * Version 5 superblock feature mask validation. Reject combinations the
-	 * kernel cannot support up front before checking anything else. For
-	 * write validation, we don't need to check feature masks.
+	 * Version 5 superblock feature mask validation. Reject combinations
+	 * the kernel cannot support up front before checking anything else.
 	 */
-	if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) {
-		if (xfs_sb_has_compat_feature(sbp,
-					XFS_SB_FEAT_COMPAT_UNKNOWN)) {
-			xfs_warn(mp,
+	if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) {
+		xfs_warn(mp,
 "Superblock has unknown compatible features (0x%x) enabled.",
-				(sbp->sb_features_compat &
-						XFS_SB_FEAT_COMPAT_UNKNOWN));
-			xfs_warn(mp,
+			(sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN));
+		xfs_warn(mp,
 "Using a more recent kernel is recommended.");
-		}
+	}
 
-		if (xfs_sb_has_ro_compat_feature(sbp,
-					XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
-			xfs_alert(mp,
+	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+		xfs_alert(mp,
 "Superblock has unknown read-only compatible features (0x%x) enabled.",
-				(sbp->sb_features_ro_compat &
-						XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
-			if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-				xfs_warn(mp,
+			(sbp->sb_features_ro_compat &
+					XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
+		if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+			xfs_warn(mp,
 "Attempted to mount read-only compatible filesystem read-write.");
-				xfs_warn(mp,
+			xfs_warn(mp,
 "Filesystem can only be safely mounted read only.");
 
-				return -EINVAL;
-			}
-		}
-		if (xfs_sb_has_incompat_feature(sbp,
-					XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
-			xfs_warn(mp,
-"Superblock has unknown incompatible features (0x%x) enabled.",
-				(sbp->sb_features_incompat &
-						XFS_SB_FEAT_INCOMPAT_UNKNOWN));
-			xfs_warn(mp,
-"Filesystem can not be safely mounted by this kernel.");
 			return -EINVAL;
 		}
-	} else if (xfs_sb_version_hascrc(sbp)) {
-		/*
-		 * We can't read verify the sb LSN because the read verifier is
-		 * called before the log is allocated and processed. We know the
-		 * log is set up before write verifier (!check_version) calls,
-		 * so just check it here.
-		 */
-		if (!xfs_log_check_lsn(mp, sbp->sb_lsn))
-			return -EFSCORRUPTED;
+	}
+	if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
+		xfs_warn(mp,
+"Superblock has unknown incompatible features (0x%x) enabled.",
+			(sbp->sb_features_incompat &
+					XFS_SB_FEAT_INCOMPAT_UNKNOWN));
+		xfs_warn(mp,
+"Filesystem cannot be safely mounted by this kernel.");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Check all the superblock fields we care about when writing one out. */
+STATIC int
+xfs_validate_sb_write(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct xfs_sb		*sbp)
+{
+	/*
+	 * Carry out additional sb summary counter sanity checks when we write
+	 * the superblock.  We skip this in the read validator because there
+	 * could be newer superblocks in the log and if the values are garbage
+	 * even after replay we'll recalculate them at the end of log mount.
+	 *
+	 * mkfs has traditionally written zeroed counters to inprogress and
+	 * secondary superblocks, so allow this usage to continue because
+	 * we never read counters from such superblocks.
+	 */
+	if (XFS_BUF_ADDR(bp) == XFS_SB_DADDR && !sbp->sb_inprogress &&
+	    (sbp->sb_fdblocks > sbp->sb_dblocks ||
+	     !xfs_verify_icount(mp, sbp->sb_icount) ||
+	     sbp->sb_ifree > sbp->sb_icount)) {
+		xfs_warn(mp, "SB summary counter sanity check failed");
+		return -EFSCORRUPTED;
+	}
+
+	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
+		return 0;
+
+	/*
+	 * Version 5 superblock feature mask validation. Reject combinations
+	 * the kernel cannot support since we checked for unsupported bits in
+	 * the read verifier, which means that memory is corrupt.
+	 */
+	if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) {
+		xfs_warn(mp,
+"Corruption detected in superblock compatible features (0x%x)!",
+			(sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+
+	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+		xfs_alert(mp,
+"Corruption detected in superblock read-only compatible features (0x%x)!",
+			(sbp->sb_features_ro_compat &
+					XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+	if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
+		xfs_warn(mp,
+"Corruption detected in superblock incompatible features (0x%x)!",
+			(sbp->sb_features_incompat &
+					XFS_SB_FEAT_INCOMPAT_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+	if (xfs_sb_has_incompat_log_feature(sbp,
+			XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN)) {
+		xfs_warn(mp,
+"Corruption detected in superblock incompatible log features (0x%x)!",
+			(sbp->sb_features_log_incompat &
+					XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * We can't read verify the sb LSN because the read verifier is called
+	 * before the log is allocated and processed. We know the log is set up
+	 * before write verifier calls, so check it here.
+	 */
+	if (!xfs_log_check_lsn(mp, sbp->sb_lsn))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Check the validity of the SB. */
+STATIC int
+xfs_validate_sb_common(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct xfs_sb		*sbp)
+{
+	uint32_t		agcount = 0;
+	uint32_t		rem;
+
+	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
+		xfs_warn(mp, "bad magic number");
+		return -EWRONGFS;
+	}
+
+	if (!xfs_sb_good_version(sbp)) {
+		xfs_warn(mp, "bad version");
+		return -EWRONGFS;
 	}
 
 	if (xfs_sb_version_has_pquotino(sbp)) {
@@ -321,7 +387,12 @@ xfs_mount_validate_sb(
 		return -EFBIG;
 	}
 
-	if (check_inprogress && sbp->sb_inprogress) {
+	/*
+	 * Don't touch the filesystem if a user tool thinks it owns the primary
+	 * superblock.  mkfs doesn't clear the flag from secondary supers, so
+	 * we don't check them at all.
+	 */
+	if (XFS_BUF_ADDR(bp) == XFS_SB_DADDR && sbp->sb_inprogress) {
 		xfs_warn(mp, "Offline file system operation in progress!");
 		return -EFSCORRUPTED;
 	}
@@ -596,29 +667,6 @@ xfs_sb_to_disk(
 	}
 }
 
-static int
-xfs_sb_verify(
-	struct xfs_buf	*bp,
-	bool		check_version)
-{
-	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_sb	sb;
-
-	/*
-	 * Use call variant which doesn't convert quota flags from disk 
-	 * format, because xfs_mount_validate_sb checks the on-disk flags.
-	 */
-	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
-
-	/*
-	 * Only check the in progress field for the primary superblock as
-	 * mkfs.xfs doesn't clear it from secondary superblocks.
-	 */
-	return xfs_mount_validate_sb(mp, &sb,
-				     bp->b_maps[0].bm_bn == XFS_SB_DADDR,
-				     check_version);
-}
-
 /*
  * If the superblock has the CRC feature bit set or the CRC field is non-null,
  * check that the CRC is valid.  We check the CRC field is non-null because a
@@ -633,11 +681,12 @@ xfs_sb_verify(
  */
 static void
 xfs_sb_read_verify(
-	struct xfs_buf	*bp)
+	struct xfs_buf		*bp)
 {
-	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_dsb	*dsb = XFS_BUF_TO_SBP(bp);
-	int		error;
+	struct xfs_sb		sb;
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	struct xfs_dsb		*dsb = XFS_BUF_TO_SBP(bp);
+	int			error;
 
 	/*
 	 * open code the version check to avoid needing to convert the entire
@@ -657,7 +706,16 @@ xfs_sb_read_verify(
 			}
 		}
 	}
-	error = xfs_sb_verify(bp, true);
+
+	/*
+	 * Check all the superblock fields.  Don't byteswap the xquota flags
+	 * because _verify_common checks the on-disk values.
+	 */
+	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
+	error = xfs_validate_sb_common(mp, bp, &sb);
+	if (error)
+		goto out_error;
+	error = xfs_validate_sb_read(mp, &sb);
 
 out_error:
 	if (error == -EFSCORRUPTED || error == -EFSBADCRC)
@@ -691,15 +749,22 @@ static void
 xfs_sb_write_verify(
 	struct xfs_buf		*bp)
 {
+	struct xfs_sb		sb;
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_buf_log_item	*bip = bp->b_log_item;
 	int			error;
 
-	error = xfs_sb_verify(bp, false);
-	if (error) {
-		xfs_verifier_error(bp, error, __this_address);
-		return;
-	}
+	/*
+	 * Check all the superblock fields.  Don't byteswap the xquota flags
+	 * because _verify_common checks the on-disk values.
+	 */
+	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
+	error = xfs_validate_sb_common(mp, bp, &sb);
+	if (error)
+		goto out_error;
+	error = xfs_validate_sb_write(mp, bp, &sb);
+	if (error)
+		goto out_error;
 
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
 		return;
@@ -708,6 +773,10 @@ xfs_sb_write_verify(
 		XFS_BUF_TO_SBP(bp)->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
 	xfs_buf_update_cksum(bp, XFS_SB_CRC_OFF);
+	return;
+
+out_error:
+	xfs_verifier_error(bp, error, __this_address);
 }
 
 const struct xfs_buf_ops xfs_sb_buf_ops = {
@@ -804,6 +873,7 @@ xfs_initialize_perag_data(
 	uint64_t	bfree = 0;
 	uint64_t	bfreelst = 0;
 	uint64_t	btree = 0;
+	uint64_t	fdblocks;
 	int		error;
 
 	for (index = 0; index < agcount; index++) {
@@ -827,17 +897,31 @@ xfs_initialize_perag_data(
 		btree += pag->pagf_btreeblks;
 		xfs_perag_put(pag);
 	}
+	fdblocks = bfree + bfreelst + btree;
+
+	/*
+	 * If the new summary counts are obviously incorrect, fail the
+	 * mount operation because that implies the AGFs are also corrupt.
+	 * Clear BAD_SUMMARY so that we don't unmount with a dirty log, which
+	 * will prevent xfs_repair from fixing anything.
+	 */
+	if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
+		xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+		error = -EFSCORRUPTED;
+		goto out;
+	}
 
 	/* Overwrite incore superblock counters with just-read data */
 	spin_lock(&mp->m_sb_lock);
 	sbp->sb_ifree = ifree;
 	sbp->sb_icount = ialloc;
-	sbp->sb_fdblocks = bfree + bfreelst + btree;
+	sbp->sb_fdblocks = fdblocks;
 	spin_unlock(&mp->m_sb_lock);
 
 	xfs_reinit_percpu_counters(mp);
-
-	return 0;
+out:
+	mp->m_flags &= ~XFS_MOUNT_BAD_SUMMARY;
+	return error;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 22089f1c880a..1c5debe748f0 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -64,6 +64,18 @@ void	xfs_log_get_max_trans_res(struct xfs_mount *mp,
 #define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
 #define XFS_TRANS_NO_WRITECOUNT 0x40	/* do not elevate SB writecount */
 #define XFS_TRANS_NOFS		0x80	/* pass KM_NOFS to kmem_alloc */
+/*
+ * LOWMODE is used by the allocator to activate the lowspace algorithm - when
+ * free space is running low the extent allocator may choose to allocate an
+ * extent from an AG without leaving sufficient space for a btree split when
+ * inserting the new extent. In this case the allocator will enable the
+ * lowspace algorithm which is supposed to allow further allocations (such as
+ * btree splits and newroots) to allocate from sequential AGs. In order to
+ * avoid locking AGs out of order the lowspace algorithm will start searching
+ * for free space from AG 0. If the correct transaction reservations have been
+ * made then this algorithm will eventually find all the space it needs.
+ */
+#define XFS_TRANS_LOWMODE	0x100	/* allocate in low space mode */
 
 /*
  * Field values for xfs_trans_mod_sb.
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index 2e2a243cef2e..33a5ca346baf 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -171,3 +171,37 @@ xfs_verify_rtbno(
 {
 	return rtbno < mp->m_sb.sb_rblocks;
 }
+
+/* Calculate the range of valid icount values. */
+static void
+xfs_icount_range(
+	struct xfs_mount	*mp,
+	unsigned long long	*min,
+	unsigned long long	*max)
+{
+	unsigned long long	nr_inos = 0;
+	xfs_agnumber_t		agno;
+
+	/* root, rtbitmap, rtsum all live in the first chunk */
+	*min = XFS_INODES_PER_CHUNK;
+
+	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
+		xfs_agino_t	first, last;
+
+		xfs_agino_range(mp, agno, &first, &last);
+		nr_inos += last - first + 1;
+	}
+	*max = nr_inos;
+}
+
+/* Sanity-checking of inode counts. */
+bool
+xfs_verify_icount(
+	struct xfs_mount	*mp,
+	unsigned long long	icount)
+{
+	unsigned long long	min, max;
+
+	xfs_icount_range(mp, &min, &max);
+	return icount >= min && icount <= max;
+}
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 4055d62f690c..b9e6c89284c3 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -165,5 +165,6 @@ bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
+bool xfs_verify_icount(struct xfs_mount *mp, unsigned long long icount);
 
 #endif	/* __XFS_TYPES_H__ */
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 9bb0745f1ad2..3068a9382feb 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -28,30 +28,30 @@
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_superblock_xref(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_superblock_xref(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agnumber_t			agno = sc->sm->sm_agno;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agnumber_t		agno = sc->sm->sm_agno;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_SB_BLOCK(mp);
 
-	error = xfs_scrub_ag_init(sc, agno, &sc->sa);
-	if (!xfs_scrub_xref_process_error(sc, agno, agbno, &error))
+	error = xchk_ag_init(sc, agno, &sc->sa);
+	if (!xchk_xref_process_error(sc, agno, agbno, &error))
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
@@ -65,17 +65,17 @@ xfs_scrub_superblock_xref(
  * sb 0 is ok and we can use its information to check everything else.
  */
 int
-xfs_scrub_superblock(
-	struct xfs_scrub_context	*sc)
+xchk_superblock(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_buf			*bp;
-	struct xfs_dsb			*sb;
-	xfs_agnumber_t			agno;
-	uint32_t			v2_ok;
-	__be32				features_mask;
-	int				error;
-	__be16				vernum_mask;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+	struct xfs_dsb		*sb;
+	xfs_agnumber_t		agno;
+	uint32_t		v2_ok;
+	__be32			features_mask;
+	int			error;
+	__be16			vernum_mask;
 
 	agno = sc->sm->sm_agno;
 	if (agno == 0)
@@ -98,7 +98,7 @@ xfs_scrub_superblock(
 	default:
 		break;
 	}
-	if (!xfs_scrub_process_error(sc, agno, XFS_SB_BLOCK(mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_SB_BLOCK(mp), &error))
 		return error;
 
 	sb = XFS_BUF_TO_SBP(bp);
@@ -110,46 +110,46 @@ xfs_scrub_superblock(
 	 * checked.
 	 */
 	if (sb->sb_blocksize != cpu_to_be32(mp->m_sb.sb_blocksize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_dblocks != cpu_to_be64(mp->m_sb.sb_dblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rblocks != cpu_to_be64(mp->m_sb.sb_rblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rextents != cpu_to_be64(mp->m_sb.sb_rextents))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (!uuid_equal(&sb->sb_uuid, &mp->m_sb.sb_uuid))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_logstart != cpu_to_be64(mp->m_sb.sb_logstart))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rootino != cpu_to_be64(mp->m_sb.sb_rootino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_rsumino != cpu_to_be64(mp->m_sb.sb_rsumino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_rextsize != cpu_to_be32(mp->m_sb.sb_rextsize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_agblocks != cpu_to_be32(mp->m_sb.sb_agblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_agcount != cpu_to_be32(mp->m_sb.sb_agcount))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rbmblocks != cpu_to_be32(mp->m_sb.sb_rbmblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logblocks != cpu_to_be32(mp->m_sb.sb_logblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Check sb_versionnum bits that are set at mkfs time. */
 	vernum_mask = cpu_to_be16(~XFS_SB_VERSION_OKBITS |
@@ -163,7 +163,7 @@ xfs_scrub_superblock(
 				  XFS_SB_VERSION_DIRV2BIT);
 	if ((sb->sb_versionnum & vernum_mask) !=
 	    (cpu_to_be16(mp->m_sb.sb_versionnum) & vernum_mask))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Check sb_versionnum bits that can be set after mkfs time. */
 	vernum_mask = cpu_to_be16(XFS_SB_VERSION_ATTRBIT |
@@ -171,40 +171,40 @@ xfs_scrub_superblock(
 				  XFS_SB_VERSION_QUOTABIT);
 	if ((sb->sb_versionnum & vernum_mask) !=
 	    (cpu_to_be16(mp->m_sb.sb_versionnum) & vernum_mask))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_sectsize != cpu_to_be16(mp->m_sb.sb_sectsize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inodesize != cpu_to_be16(mp->m_sb.sb_inodesize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inopblock != cpu_to_be16(mp->m_sb.sb_inopblock))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (memcmp(sb->sb_fname, mp->m_sb.sb_fname, sizeof(sb->sb_fname)))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_blocklog != mp->m_sb.sb_blocklog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_sectlog != mp->m_sb.sb_sectlog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inodelog != mp->m_sb.sb_inodelog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inopblog != mp->m_sb.sb_inopblog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_agblklog != mp->m_sb.sb_agblklog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rextslog != mp->m_sb.sb_rextslog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_imax_pct != mp->m_sb.sb_imax_pct)
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	/*
 	 * Skip the summary counters since we track them in memory anyway.
@@ -212,10 +212,10 @@ xfs_scrub_superblock(
 	 */
 
 	if (sb->sb_uquotino != cpu_to_be64(mp->m_sb.sb_uquotino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_gquotino != cpu_to_be64(mp->m_sb.sb_gquotino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	/*
 	 * Skip the quota flags since repair will force quotacheck.
@@ -223,46 +223,46 @@ xfs_scrub_superblock(
 	 */
 
 	if (sb->sb_flags != mp->m_sb.sb_flags)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_shared_vn != mp->m_sb.sb_shared_vn)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inoalignmt != cpu_to_be32(mp->m_sb.sb_inoalignmt))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_unit != cpu_to_be32(mp->m_sb.sb_unit))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_width != cpu_to_be32(mp->m_sb.sb_width))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_dirblklog != mp->m_sb.sb_dirblklog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logsectlog != mp->m_sb.sb_logsectlog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logsectsize != cpu_to_be16(mp->m_sb.sb_logsectsize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logsunit != cpu_to_be32(mp->m_sb.sb_logsunit))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Do we see any invalid bits in sb_features2? */
 	if (!xfs_sb_version_hasmorebits(&mp->m_sb)) {
 		if (sb->sb_features2 != 0)
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 	} else {
 		v2_ok = XFS_SB_VERSION2_OKBITS;
 		if (XFS_SB_VERSION_NUM(&mp->m_sb) >= XFS_SB_VERSION_5)
 			v2_ok |= XFS_SB_VERSION2_CRCBIT;
 
 		if (!!(sb->sb_features2 & cpu_to_be32(~v2_ok)))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		if (sb->sb_features2 != sb->sb_bad_features2)
-			xfs_scrub_block_set_preen(sc, bp);
+			xchk_block_set_preen(sc, bp);
 	}
 
 	/* Check sb_features2 flags that are set at mkfs time. */
@@ -272,26 +272,26 @@ xfs_scrub_superblock(
 				    XFS_SB_VERSION2_FTYPE);
 	if ((sb->sb_features2 & features_mask) !=
 	    (cpu_to_be32(mp->m_sb.sb_features2) & features_mask))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Check sb_features2 flags that can be set after mkfs time. */
 	features_mask = cpu_to_be32(XFS_SB_VERSION2_ATTR2BIT);
 	if ((sb->sb_features2 & features_mask) !=
 	    (cpu_to_be32(mp->m_sb.sb_features2) & features_mask))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (!xfs_sb_version_hascrc(&mp->m_sb)) {
 		/* all v5 fields must be zero */
 		if (memchr_inv(&sb->sb_features_compat, 0,
 				sizeof(struct xfs_dsb) -
 				offsetof(struct xfs_dsb, sb_features_compat)))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 	} else {
 		/* Check compat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_COMPAT_UNKNOWN);
 		if ((sb->sb_features_compat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_compat) & features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Check ro compat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_RO_COMPAT_UNKNOWN |
@@ -301,7 +301,7 @@ xfs_scrub_superblock(
 		if ((sb->sb_features_ro_compat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_ro_compat) &
 		     features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Check incompat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_INCOMPAT_UNKNOWN |
@@ -311,22 +311,22 @@ xfs_scrub_superblock(
 		if ((sb->sb_features_incompat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_incompat) &
 		     features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Check log incompat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN);
 		if ((sb->sb_features_log_incompat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_log_incompat) &
 		     features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Don't care about sb_crc */
 
 		if (sb->sb_spino_align != cpu_to_be32(mp->m_sb.sb_spino_align))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		if (sb->sb_pquotino != cpu_to_be64(mp->m_sb.sb_pquotino))
-			xfs_scrub_block_set_preen(sc, bp);
+			xchk_block_set_preen(sc, bp);
 
 		/* Don't care about sb_lsn */
 	}
@@ -334,15 +334,15 @@ xfs_scrub_superblock(
 	if (xfs_sb_version_hasmetauuid(&mp->m_sb)) {
 		/* The metadata UUID must be the same for all supers */
 		if (!uuid_equal(&sb->sb_meta_uuid, &mp->m_sb.sb_meta_uuid))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 	}
 
 	/* Everything else must be zero. */
 	if (memchr_inv(sb + 1, 0,
 			BBTOB(bp->b_length) - sizeof(struct xfs_dsb)))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
-	xfs_scrub_superblock_xref(sc, bp);
+	xchk_superblock_xref(sc, bp);
 
 	return error;
 }
@@ -351,7 +351,7 @@ xfs_scrub_superblock(
 
 /* Tally freespace record lengths. */
 STATIC int
-xfs_scrub_agf_record_bno_lengths(
+xchk_agf_record_bno_lengths(
 	struct xfs_btree_cur		*cur,
 	struct xfs_alloc_rec_incore	*rec,
 	void				*priv)
@@ -364,75 +364,75 @@ xfs_scrub_agf_record_bno_lengths(
 
 /* Check agf_freeblks */
 static inline void
-xfs_scrub_agf_xref_freeblks(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref_freeblks(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	xfs_extlen_t			blocks = 0;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	xfs_extlen_t		blocks = 0;
+	int			error;
 
 	if (!sc->sa.bno_cur)
 		return;
 
 	error = xfs_alloc_query_all(sc->sa.bno_cur,
-			xfs_scrub_agf_record_bno_lengths, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.bno_cur))
+			xchk_agf_record_bno_lengths, &blocks);
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
 	if (blocks != be32_to_cpu(agf->agf_freeblks))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Cross reference the AGF with the cntbt (freespace by length btree) */
 static inline void
-xfs_scrub_agf_xref_cntbt(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref_cntbt(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	xfs_agblock_t			agbno;
-	xfs_extlen_t			blocks;
-	int				have;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	xfs_agblock_t		agbno;
+	xfs_extlen_t		blocks;
+	int			have;
+	int			error;
 
 	if (!sc->sa.cnt_cur)
 		return;
 
 	/* Any freespace at all? */
 	error = xfs_alloc_lookup_le(sc->sa.cnt_cur, 0, -1U, &have);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.cnt_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.cnt_cur))
 		return;
 	if (!have) {
 		if (agf->agf_freeblks != be32_to_cpu(0))
-			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 		return;
 	}
 
 	/* Check agf_longest */
 	error = xfs_alloc_get_rec(sc->sa.cnt_cur, &agbno, &blocks, &have);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.cnt_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.cnt_cur))
 		return;
 	if (!have || blocks != be32_to_cpu(agf->agf_longest))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Check the btree block counts in the AGF against the btrees. */
 STATIC void
-xfs_scrub_agf_xref_btreeblks(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref_btreeblks(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			blocks;
-	xfs_agblock_t			btreeblks;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		blocks;
+	xfs_agblock_t		btreeblks;
+	int			error;
 
 	/* Check agf_rmap_blocks; set up for agf_btreeblks check */
 	if (sc->sa.rmap_cur) {
 		error = xfs_btree_count_blocks(sc->sa.rmap_cur, &blocks);
-		if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+		if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 			return;
 		btreeblks = blocks - 1;
 		if (blocks != be32_to_cpu(agf->agf_rmap_blocks))
-			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 	} else {
 		btreeblks = 0;
 	}
@@ -447,136 +447,136 @@ xfs_scrub_agf_xref_btreeblks(
 
 	/* Check agf_btreeblks */
 	error = xfs_btree_count_blocks(sc->sa.bno_cur, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.bno_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
 	btreeblks += blocks - 1;
 
 	error = xfs_btree_count_blocks(sc->sa.cnt_cur, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.cnt_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.cnt_cur))
 		return;
 	btreeblks += blocks - 1;
 
 	if (btreeblks != be32_to_cpu(agf->agf_btreeblks))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Check agf_refcount_blocks against tree size */
 static inline void
-xfs_scrub_agf_xref_refcblks(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref_refcblks(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	xfs_agblock_t			blocks;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	xfs_agblock_t		blocks;
+	int			error;
 
 	if (!sc->sa.refc_cur)
 		return;
 
 	error = xfs_btree_count_blocks(sc->sa.refc_cur, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (blocks != be32_to_cpu(agf->agf_refcount_blocks))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agf_xref(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_AGF_BLOCK(mp);
 
-	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	error = xchk_ag_btcur_init(sc, &sc->sa);
 	if (error)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_agf_xref_freeblks(sc);
-	xfs_scrub_agf_xref_cntbt(sc);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_agf_xref_freeblks(sc);
+	xchk_agf_xref_cntbt(sc);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_agf_xref_btreeblks(sc);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
-	xfs_scrub_agf_xref_refcblks(sc);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_agf_xref_btreeblks(sc);
+	xchk_xref_is_not_shared(sc, agbno, 1);
+	xchk_agf_xref_refcblks(sc);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
 
 /* Scrub the AGF. */
 int
-xfs_scrub_agf(
-	struct xfs_scrub_context	*sc)
+xchk_agf(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_agf			*agf;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_agblock_t			eoag;
-	xfs_agblock_t			agfl_first;
-	xfs_agblock_t			agfl_last;
-	xfs_agblock_t			agfl_count;
-	xfs_agblock_t			fl_count;
-	int				level;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agf		*agf;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_agblock_t		eoag;
+	xfs_agblock_t		agfl_first;
+	xfs_agblock_t		agfl_last;
+	xfs_agblock_t		agfl_count;
+	xfs_agblock_t		fl_count;
+	int			level;
+	int			error = 0;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sc->sa.agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
 			&sc->sa.agf_bp, &sc->sa.agfl_bp);
-	if (!xfs_scrub_process_error(sc, agno, XFS_AGF_BLOCK(sc->mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_AGF_BLOCK(sc->mp), &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, sc->sa.agf_bp);
+	xchk_buffer_recheck(sc, sc->sa.agf_bp);
 
 	agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 
 	/* Check the AG length */
 	eoag = be32_to_cpu(agf->agf_length);
 	if (eoag != xfs_ag_block_count(mp, agno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	/* Check the AGF btree roots and levels */
 	agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_BNO]);
 	if (!xfs_verify_agbno(mp, agno, agbno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_CNT]);
 	if (!xfs_verify_agbno(mp, agno, agbno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]);
 	if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]);
 	if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
 		agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_RMAP]);
 		if (!xfs_verify_agbno(mp, agno, agbno))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 		level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]);
 		if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 	}
 
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
 		agbno = be32_to_cpu(agf->agf_refcount_root);
 		if (!xfs_verify_agbno(mp, agno, agbno))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 		level = be32_to_cpu(agf->agf_refcount_level);
 		if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 	}
 
 	/* Check the AGFL counters */
@@ -588,57 +588,57 @@ xfs_scrub_agf(
 	else
 		fl_count = xfs_agfl_size(mp) - agfl_first + agfl_last + 1;
 	if (agfl_count != 0 && fl_count != agfl_count)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
-	xfs_scrub_agf_xref(sc);
+	xchk_agf_xref(sc);
 out:
 	return error;
 }
 
 /* AGFL */
 
-struct xfs_scrub_agfl_info {
-	struct xfs_owner_info		oinfo;
-	unsigned int			sz_entries;
-	unsigned int			nr_entries;
-	xfs_agblock_t			*entries;
-	struct xfs_scrub_context	*sc;
+struct xchk_agfl_info {
+	struct xfs_owner_info	oinfo;
+	unsigned int		sz_entries;
+	unsigned int		nr_entries;
+	xfs_agblock_t		*entries;
+	struct xfs_scrub	*sc;
 };
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agfl_block_xref(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	struct xfs_owner_info		*oinfo)
+xchk_agfl_block_xref(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	struct xfs_owner_info	*oinfo)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 }
 
 /* Scrub an AGFL block. */
 STATIC int
-xfs_scrub_agfl_block(
-	struct xfs_mount		*mp,
-	xfs_agblock_t			agbno,
-	void				*priv)
+xchk_agfl_block(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agbno,
+	void			*priv)
 {
-	struct xfs_scrub_agfl_info	*sai = priv;
-	struct xfs_scrub_context	*sc = sai->sc;
-	xfs_agnumber_t			agno = sc->sa.agno;
+	struct xchk_agfl_info	*sai = priv;
+	struct xfs_scrub	*sc = sai->sc;
+	xfs_agnumber_t		agno = sc->sa.agno;
 
 	if (xfs_verify_agbno(mp, agno, agbno) &&
 	    sai->nr_entries < sai->sz_entries)
 		sai->entries[sai->nr_entries++] = agbno;
 	else
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agfl_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agfl_bp);
 
-	xfs_scrub_agfl_block_xref(sc, agbno, priv);
+	xchk_agfl_block_xref(sc, agbno, priv);
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return XFS_BTREE_QUERY_RANGE_ABORT;
@@ -647,7 +647,7 @@ xfs_scrub_agfl_block(
 }
 
 static int
-xfs_scrub_agblock_cmp(
+xchk_agblock_cmp(
 	const void		*pa,
 	const void		*pb)
 {
@@ -659,28 +659,28 @@ xfs_scrub_agblock_cmp(
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agfl_xref(
-	struct xfs_scrub_context	*sc)
+xchk_agfl_xref(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_AGFL_BLOCK(mp);
 
-	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	error = xchk_ag_btcur_init(sc, &sc->sa);
 	if (error)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 
 	/*
 	 * Scrub teardown will take care of sc->sa for us.  Leave sc->sa
@@ -690,26 +690,26 @@ xfs_scrub_agfl_xref(
 
 /* Scrub the AGFL. */
 int
-xfs_scrub_agfl(
-	struct xfs_scrub_context	*sc)
+xchk_agfl(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_scrub_agfl_info	sai;
-	struct xfs_agf			*agf;
-	xfs_agnumber_t			agno;
-	unsigned int			agflcount;
-	unsigned int			i;
-	int				error;
+	struct xchk_agfl_info	sai;
+	struct xfs_agf		*agf;
+	xfs_agnumber_t		agno;
+	unsigned int		agflcount;
+	unsigned int		i;
+	int			error;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sc->sa.agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
 			&sc->sa.agf_bp, &sc->sa.agfl_bp);
-	if (!xfs_scrub_process_error(sc, agno, XFS_AGFL_BLOCK(sc->mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_AGFL_BLOCK(sc->mp), &error))
 		goto out;
 	if (!sc->sa.agf_bp)
 		return -EFSCORRUPTED;
-	xfs_scrub_buffer_recheck(sc, sc->sa.agfl_bp);
+	xchk_buffer_recheck(sc, sc->sa.agfl_bp);
 
-	xfs_scrub_agfl_xref(sc);
+	xchk_agfl_xref(sc);
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
@@ -718,7 +718,7 @@ xfs_scrub_agfl(
 	agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 	agflcount = be32_to_cpu(agf->agf_flcount);
 	if (agflcount > xfs_agfl_size(sc->mp)) {
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 		goto out;
 	}
 	memset(&sai, 0, sizeof(sai));
@@ -734,7 +734,7 @@ xfs_scrub_agfl(
 	/* Check the blocks in the AGFL. */
 	xfs_rmap_ag_owner(&sai.oinfo, XFS_RMAP_OWN_AG);
 	error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(sc->sa.agf_bp),
-			sc->sa.agfl_bp, xfs_scrub_agfl_block, &sai);
+			sc->sa.agfl_bp, xchk_agfl_block, &sai);
 	if (error == XFS_BTREE_QUERY_RANGE_ABORT) {
 		error = 0;
 		goto out_free;
@@ -743,16 +743,16 @@ xfs_scrub_agfl(
 		goto out_free;
 
 	if (agflcount != sai.nr_entries) {
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 		goto out_free;
 	}
 
 	/* Sort entries, check for duplicates. */
 	sort(sai.entries, sai.nr_entries, sizeof(sai.entries[0]),
-			xfs_scrub_agblock_cmp, NULL);
+			xchk_agblock_cmp, NULL);
 	for (i = 1; i < sai.nr_entries; i++) {
 		if (sai.entries[i] == sai.entries[i - 1]) {
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 			break;
 		}
 	}
@@ -767,103 +767,103 @@ out:
 
 /* Check agi_count/agi_freecount */
 static inline void
-xfs_scrub_agi_xref_icounts(
-	struct xfs_scrub_context	*sc)
+xchk_agi_xref_icounts(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agi			*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
-	xfs_agino_t			icount;
-	xfs_agino_t			freecount;
-	int				error;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
+	xfs_agino_t		icount;
+	xfs_agino_t		freecount;
+	int			error;
 
 	if (!sc->sa.ino_cur)
 		return;
 
 	error = xfs_ialloc_count_inodes(sc->sa.ino_cur, &icount, &freecount);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.ino_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.ino_cur))
 		return;
 	if (be32_to_cpu(agi->agi_count) != icount ||
 	    be32_to_cpu(agi->agi_freecount) != freecount)
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agi_bp);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agi_xref(
-	struct xfs_scrub_context	*sc)
+xchk_agi_xref(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_AGI_BLOCK(mp);
 
-	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	error = xchk_ag_btcur_init(sc, &sc->sa);
 	if (error)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
-	xfs_scrub_agi_xref_icounts(sc);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_agi_xref_icounts(sc);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
 
 /* Scrub the AGI. */
 int
-xfs_scrub_agi(
-	struct xfs_scrub_context	*sc)
+xchk_agi(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_agi			*agi;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_agblock_t			eoag;
-	xfs_agino_t			agino;
-	xfs_agino_t			first_agino;
-	xfs_agino_t			last_agino;
-	xfs_agino_t			icount;
-	int				i;
-	int				level;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agi		*agi;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_agblock_t		eoag;
+	xfs_agino_t		agino;
+	xfs_agino_t		first_agino;
+	xfs_agino_t		last_agino;
+	xfs_agino_t		icount;
+	int			i;
+	int			level;
+	int			error = 0;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sc->sa.agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
 			&sc->sa.agf_bp, &sc->sa.agfl_bp);
-	if (!xfs_scrub_process_error(sc, agno, XFS_AGI_BLOCK(sc->mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_AGI_BLOCK(sc->mp), &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, sc->sa.agi_bp);
+	xchk_buffer_recheck(sc, sc->sa.agi_bp);
 
 	agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
 
 	/* Check the AG length */
 	eoag = be32_to_cpu(agi->agi_length);
 	if (eoag != xfs_ag_block_count(mp, agno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check btree roots and levels */
 	agbno = be32_to_cpu(agi->agi_root);
 	if (!xfs_verify_agbno(mp, agno, agbno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	level = be32_to_cpu(agi->agi_level);
 	if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
 		agbno = be32_to_cpu(agi->agi_free_root);
 		if (!xfs_verify_agbno(mp, agno, agbno))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 		level = be32_to_cpu(agi->agi_free_level);
 		if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 	}
 
 	/* Check inode counters */
@@ -871,16 +871,16 @@ xfs_scrub_agi(
 	icount = be32_to_cpu(agi->agi_count);
 	if (icount > last_agino - first_agino + 1 ||
 	    icount < be32_to_cpu(agi->agi_freecount))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check inode pointers */
 	agino = be32_to_cpu(agi->agi_newino);
 	if (agino != NULLAGINO && !xfs_verify_agino(mp, agno, agino))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	agino = be32_to_cpu(agi->agi_dirino);
 	if (agino != NULLAGINO && !xfs_verify_agino(mp, agno, agino))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check unlinked inode buckets */
 	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
@@ -888,13 +888,13 @@ xfs_scrub_agi(
 		if (agino == NULLAGINO)
 			continue;
 		if (!xfs_verify_agino(mp, agno, agino))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 	}
 
 	if (agi->agi_pad32 != cpu_to_be32(0))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
-	xfs_scrub_agi_xref(sc);
+	xchk_agi_xref(sc);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 117eedac53df..f7568a4b5fe5 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -17,24 +17,31 @@
 #include "xfs_sb.h"
 #include "xfs_inode.h"
 #include "xfs_alloc.h"
+#include "xfs_alloc_btree.h"
 #include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
 #include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_refcount_btree.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
 
 /* Superblock */
 
 /* Repair the superblock. */
 int
-xfs_repair_superblock(
-	struct xfs_scrub_context	*sc)
+xrep_superblock(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_buf			*bp;
-	xfs_agnumber_t			agno;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+	xfs_agnumber_t		agno;
+	int			error;
 
 	/* Don't try to repair AG 0's sb; let xfs_repair deal with it. */
 	agno = sc->sm->sm_agno;
@@ -54,3 +61,873 @@ xfs_repair_superblock(
 	xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
 	return error;
 }
+
+/* AGF */
+
+struct xrep_agf_allocbt {
+	struct xfs_scrub	*sc;
+	xfs_agblock_t		freeblks;
+	xfs_agblock_t		longest;
+};
+
+/* Record free space shape information. */
+STATIC int
+xrep_agf_walk_allocbt(
+	struct xfs_btree_cur		*cur,
+	struct xfs_alloc_rec_incore	*rec,
+	void				*priv)
+{
+	struct xrep_agf_allocbt		*raa = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(raa->sc, &error))
+		return error;
+
+	raa->freeblks += rec->ar_blockcount;
+	if (rec->ar_blockcount > raa->longest)
+		raa->longest = rec->ar_blockcount;
+	return error;
+}
+
+/* Does this AGFL block look sane? */
+STATIC int
+xrep_agf_check_agfl_block(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agbno,
+	void			*priv)
+{
+	struct xfs_scrub	*sc = priv;
+
+	if (!xfs_verify_agbno(mp, sc->sa.agno, agbno))
+		return -EFSCORRUPTED;
+	return 0;
+}
+
+/*
+ * Offset within the xrep_find_ag_btree array for each btree type.  Avoid the
+ * XFS_BTNUM_ names here to avoid creating a sparse array.
+ */
+enum {
+	XREP_AGF_BNOBT = 0,
+	XREP_AGF_CNTBT,
+	XREP_AGF_RMAPBT,
+	XREP_AGF_REFCOUNTBT,
+	XREP_AGF_END,
+	XREP_AGF_MAX
+};
+
+/* Check a btree root candidate. */
+static inline bool
+xrep_check_btree_root(
+	struct xfs_scrub		*sc,
+	struct xrep_find_ag_btree	*fab)
+{
+	struct xfs_mount		*mp = sc->mp;
+	xfs_agnumber_t			agno = sc->sm->sm_agno;
+
+	return xfs_verify_agbno(mp, agno, fab->root) &&
+	       fab->height <= XFS_BTREE_MAXLEVELS;
+}
+
+/*
+ * Given the btree roots described by *fab, find the roots, check them for
+ * sanity, and pass the root data back out via *fab.
+ *
+ * This is /also/ a chicken and egg problem because we have to use the rmapbt
+ * (rooted in the AGF) to find the btrees rooted in the AGF.  We also have no
+ * idea if the btrees make any sense.  If we hit obvious corruptions in those
+ * btrees we'll bail out.
+ */
+STATIC int
+xrep_agf_find_btrees(
+	struct xfs_scrub		*sc,
+	struct xfs_buf			*agf_bp,
+	struct xrep_find_ag_btree	*fab,
+	struct xfs_buf			*agfl_bp)
+{
+	struct xfs_agf			*old_agf = XFS_BUF_TO_AGF(agf_bp);
+	int				error;
+
+	/* Go find the root data. */
+	error = xrep_find_ag_btree_roots(sc, agf_bp, fab, agfl_bp);
+	if (error)
+		return error;
+
+	/* We must find the bnobt, cntbt, and rmapbt roots. */
+	if (!xrep_check_btree_root(sc, &fab[XREP_AGF_BNOBT]) ||
+	    !xrep_check_btree_root(sc, &fab[XREP_AGF_CNTBT]) ||
+	    !xrep_check_btree_root(sc, &fab[XREP_AGF_RMAPBT]))
+		return -EFSCORRUPTED;
+
+	/*
+	 * We relied on the rmapbt to reconstruct the AGF.  If we get a
+	 * different root then something's seriously wrong.
+	 */
+	if (fab[XREP_AGF_RMAPBT].root !=
+	    be32_to_cpu(old_agf->agf_roots[XFS_BTNUM_RMAPi]))
+		return -EFSCORRUPTED;
+
+	/* We must find the refcountbt root if that feature is enabled. */
+	if (xfs_sb_version_hasreflink(&sc->mp->m_sb) &&
+	    !xrep_check_btree_root(sc, &fab[XREP_AGF_REFCOUNTBT]))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/*
+ * Reinitialize the AGF header, making an in-core copy of the old contents so
+ * that we know which in-core state needs to be reinitialized.
+ */
+STATIC void
+xrep_agf_init_header(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp,
+	struct xfs_agf		*old_agf)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+
+	memcpy(old_agf, agf, sizeof(*old_agf));
+	memset(agf, 0, BBTOB(agf_bp->b_length));
+	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
+	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
+	agf->agf_seqno = cpu_to_be32(sc->sa.agno);
+	agf->agf_length = cpu_to_be32(xfs_ag_block_count(mp, sc->sa.agno));
+	agf->agf_flfirst = old_agf->agf_flfirst;
+	agf->agf_fllast = old_agf->agf_fllast;
+	agf->agf_flcount = old_agf->agf_flcount;
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
+
+	/* Mark the incore AGF data stale until we're done fixing things. */
+	ASSERT(sc->sa.pag->pagf_init);
+	sc->sa.pag->pagf_init = 0;
+}
+
+/* Set btree root information in an AGF. */
+STATIC void
+xrep_agf_set_roots(
+	struct xfs_scrub		*sc,
+	struct xfs_agf			*agf,
+	struct xrep_find_ag_btree	*fab)
+{
+	agf->agf_roots[XFS_BTNUM_BNOi] =
+			cpu_to_be32(fab[XREP_AGF_BNOBT].root);
+	agf->agf_levels[XFS_BTNUM_BNOi] =
+			cpu_to_be32(fab[XREP_AGF_BNOBT].height);
+
+	agf->agf_roots[XFS_BTNUM_CNTi] =
+			cpu_to_be32(fab[XREP_AGF_CNTBT].root);
+	agf->agf_levels[XFS_BTNUM_CNTi] =
+			cpu_to_be32(fab[XREP_AGF_CNTBT].height);
+
+	agf->agf_roots[XFS_BTNUM_RMAPi] =
+			cpu_to_be32(fab[XREP_AGF_RMAPBT].root);
+	agf->agf_levels[XFS_BTNUM_RMAPi] =
+			cpu_to_be32(fab[XREP_AGF_RMAPBT].height);
+
+	if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
+		agf->agf_refcount_root =
+				cpu_to_be32(fab[XREP_AGF_REFCOUNTBT].root);
+		agf->agf_refcount_level =
+				cpu_to_be32(fab[XREP_AGF_REFCOUNTBT].height);
+	}
+}
+
+/* Update all AGF fields which derive from btree contents. */
+STATIC int
+xrep_agf_calc_from_btrees(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp)
+{
+	struct xrep_agf_allocbt	raa = { .sc = sc };
+	struct xfs_btree_cur	*cur = NULL;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		btreeblks;
+	xfs_agblock_t		blocks;
+	int			error;
+
+	/* Update the AGF counters from the bnobt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_BNO);
+	error = xfs_alloc_query_all(cur, xrep_agf_walk_allocbt, &raa);
+	if (error)
+		goto err;
+	error = xfs_btree_count_blocks(cur, &blocks);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+	btreeblks = blocks - 1;
+	agf->agf_freeblks = cpu_to_be32(raa.freeblks);
+	agf->agf_longest = cpu_to_be32(raa.longest);
+
+	/* Update the AGF counters from the cntbt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_CNT);
+	error = xfs_btree_count_blocks(cur, &blocks);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+	btreeblks += blocks - 1;
+
+	/* Update the AGF counters from the rmapbt. */
+	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
+	error = xfs_btree_count_blocks(cur, &blocks);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+	agf->agf_rmap_blocks = cpu_to_be32(blocks);
+	btreeblks += blocks - 1;
+
+	agf->agf_btreeblks = cpu_to_be32(btreeblks);
+
+	/* Update the AGF counters from the refcountbt. */
+	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+		cur = xfs_refcountbt_init_cursor(mp, sc->tp, agf_bp,
+				sc->sa.agno);
+		error = xfs_btree_count_blocks(cur, &blocks);
+		if (error)
+			goto err;
+		xfs_btree_del_cursor(cur, error);
+		agf->agf_refcount_blocks = cpu_to_be32(blocks);
+	}
+
+	return 0;
+err:
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/* Commit the new AGF and reinitialize the incore state. */
+STATIC int
+xrep_agf_commit_new(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp)
+{
+	struct xfs_perag	*pag;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+
+	/* Trigger fdblocks recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/* Write this to disk. */
+	xfs_trans_buf_set_type(sc->tp, agf_bp, XFS_BLFT_AGF_BUF);
+	xfs_trans_log_buf(sc->tp, agf_bp, 0, BBTOB(agf_bp->b_length) - 1);
+
+	/* Now reinitialize the in-core counters we changed. */
+	pag = sc->sa.pag;
+	pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
+	pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
+	pag->pagf_longest = be32_to_cpu(agf->agf_longest);
+	pag->pagf_levels[XFS_BTNUM_BNOi] =
+			be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]);
+	pag->pagf_levels[XFS_BTNUM_CNTi] =
+			be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]);
+	pag->pagf_levels[XFS_BTNUM_RMAPi] =
+			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
+	pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
+	pag->pagf_init = 1;
+
+	return 0;
+}
+
+/* Repair the AGF. v5 filesystems only. */
+int
+xrep_agf(
+	struct xfs_scrub		*sc)
+{
+	struct xrep_find_ag_btree	fab[XREP_AGF_MAX] = {
+		[XREP_AGF_BNOBT] = {
+			.rmap_owner = XFS_RMAP_OWN_AG,
+			.buf_ops = &xfs_allocbt_buf_ops,
+			.magic = XFS_ABTB_CRC_MAGIC,
+		},
+		[XREP_AGF_CNTBT] = {
+			.rmap_owner = XFS_RMAP_OWN_AG,
+			.buf_ops = &xfs_allocbt_buf_ops,
+			.magic = XFS_ABTC_CRC_MAGIC,
+		},
+		[XREP_AGF_RMAPBT] = {
+			.rmap_owner = XFS_RMAP_OWN_AG,
+			.buf_ops = &xfs_rmapbt_buf_ops,
+			.magic = XFS_RMAP_CRC_MAGIC,
+		},
+		[XREP_AGF_REFCOUNTBT] = {
+			.rmap_owner = XFS_RMAP_OWN_REFC,
+			.buf_ops = &xfs_refcountbt_buf_ops,
+			.magic = XFS_REFC_CRC_MAGIC,
+		},
+		[XREP_AGF_END] = {
+			.buf_ops = NULL,
+		},
+	};
+	struct xfs_agf			old_agf;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_buf			*agf_bp;
+	struct xfs_buf			*agfl_bp;
+	struct xfs_agf			*agf;
+	int				error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	xchk_perag_get(sc->mp, &sc->sa);
+	/*
+	 * Make sure we have the AGF buffer, as scrub might have decided it
+	 * was corrupt after xfs_alloc_read_agf failed with -EFSCORRUPTED.
+	 */
+	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGF_DADDR(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &agf_bp, NULL);
+	if (error)
+		return error;
+	agf_bp->b_ops = &xfs_agf_buf_ops;
+	agf = XFS_BUF_TO_AGF(agf_bp);
+
+	/*
+	 * Load the AGFL so that we can screen out OWN_AG blocks that are on
+	 * the AGFL now; these blocks might have once been part of the
+	 * bno/cnt/rmap btrees but are not now.  This is a chicken and egg
+	 * problem: the AGF is corrupt, so we have to trust the AGFL contents
+	 * because we can't do any serious cross-referencing with any of the
+	 * btrees rooted in the AGF.  If the AGFL contents are obviously bad
+	 * then we'll bail out.
+	 */
+	error = xfs_alloc_read_agfl(mp, sc->tp, sc->sa.agno, &agfl_bp);
+	if (error)
+		return error;
+
+	/*
+	 * Spot-check the AGFL blocks; if they're obviously corrupt then
+	 * there's nothing we can do but bail out.
+	 */
+	error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(agf_bp), agfl_bp,
+			xrep_agf_check_agfl_block, sc);
+	if (error)
+		return error;
+
+	/*
+	 * Find the AGF btree roots.  This is also a chicken-and-egg situation;
+	 * see the function for more details.
+	 */
+	error = xrep_agf_find_btrees(sc, agf_bp, fab, agfl_bp);
+	if (error)
+		return error;
+
+	/* Start rewriting the header and implant the btrees we found. */
+	xrep_agf_init_header(sc, agf_bp, &old_agf);
+	xrep_agf_set_roots(sc, agf, fab);
+	error = xrep_agf_calc_from_btrees(sc, agf_bp);
+	if (error)
+		goto out_revert;
+
+	/* Commit the changes and reinitialize incore state. */
+	return xrep_agf_commit_new(sc, agf_bp);
+
+out_revert:
+	/* Mark the incore AGF state stale and revert the AGF. */
+	sc->sa.pag->pagf_init = 0;
+	memcpy(agf, &old_agf, sizeof(old_agf));
+	return error;
+}
+
+/* AGFL */
+
+struct xrep_agfl {
+	/* Bitmap of other OWN_AG metadata blocks. */
+	struct xfs_bitmap	agmetablocks;
+
+	/* Bitmap of free space. */
+	struct xfs_bitmap	*freesp;
+
+	struct xfs_scrub	*sc;
+};
+
+/* Record all OWN_AG (free space btree) information from the rmap data. */
+STATIC int
+xrep_agfl_walk_rmap(
+	struct xfs_btree_cur	*cur,
+	struct xfs_rmap_irec	*rec,
+	void			*priv)
+{
+	struct xrep_agfl	*ra = priv;
+	xfs_fsblock_t		fsb;
+	int			error = 0;
+
+	if (xchk_should_terminate(ra->sc, &error))
+		return error;
+
+	/* Record all the OWN_AG blocks. */
+	if (rec->rm_owner == XFS_RMAP_OWN_AG) {
+		fsb = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno,
+				rec->rm_startblock);
+		error = xfs_bitmap_set(ra->freesp, fsb, rec->rm_blockcount);
+		if (error)
+			return error;
+	}
+
+	return xfs_bitmap_set_btcur_path(&ra->agmetablocks, cur);
+}
+
+/*
+ * Map out all the non-AGFL OWN_AG space in this AG so that we can deduce
+ * which blocks belong to the AGFL.
+ *
+ * Compute the set of old AGFL blocks by subtracting from the list of OWN_AG
+ * blocks the list of blocks owned by all other OWN_AG metadata (bnobt, cntbt,
+ * rmapbt).  These are the old AGFL blocks, so return that list and the number
+ * of blocks we're actually going to put back on the AGFL.
+ */
+STATIC int
+xrep_agfl_collect_blocks(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp,
+	struct xfs_bitmap	*agfl_extents,
+	xfs_agblock_t		*flcount)
+{
+	struct xrep_agfl	ra;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_btree_cur	*cur;
+	struct xfs_bitmap_range	*br;
+	struct xfs_bitmap_range	*n;
+	int			error;
+
+	ra.sc = sc;
+	ra.freesp = agfl_extents;
+	xfs_bitmap_init(&ra.agmetablocks);
+
+	/* Find all space used by the free space btrees & rmapbt. */
+	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
+	error = xfs_rmap_query_all(cur, xrep_agfl_walk_rmap, &ra);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+
+	/* Find all blocks currently being used by the bnobt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_BNO);
+	error = xfs_bitmap_set_btblocks(&ra.agmetablocks, cur);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+
+	/* Find all blocks currently being used by the cntbt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_CNT);
+	error = xfs_bitmap_set_btblocks(&ra.agmetablocks, cur);
+	if (error)
+		goto err;
+
+	xfs_btree_del_cursor(cur, error);
+
+	/*
+	 * Drop the freesp meta blocks that are in use by btrees.
+	 * The remaining blocks /should/ be AGFL blocks.
+	 */
+	error = xfs_bitmap_disunion(agfl_extents, &ra.agmetablocks);
+	xfs_bitmap_destroy(&ra.agmetablocks);
+	if (error)
+		return error;
+
+	/*
+	 * Calculate the new AGFL size.  If we found more blocks than fit in
+	 * the AGFL we'll free them later.
+	 */
+	*flcount = 0;
+	for_each_xfs_bitmap_extent(br, n, agfl_extents) {
+		*flcount += br->len;
+		if (*flcount > xfs_agfl_size(mp))
+			break;
+	}
+	if (*flcount > xfs_agfl_size(mp))
+		*flcount = xfs_agfl_size(mp);
+	return 0;
+
+err:
+	xfs_bitmap_destroy(&ra.agmetablocks);
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/* Update the AGF and reset the in-core state. */
+STATIC void
+xrep_agfl_update_agf(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp,
+	xfs_agblock_t		flcount)
+{
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+
+	ASSERT(flcount <= xfs_agfl_size(sc->mp));
+
+	/* Trigger fdblocks recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/* Update the AGF counters. */
+	if (sc->sa.pag->pagf_init)
+		sc->sa.pag->pagf_flcount = flcount;
+	agf->agf_flfirst = cpu_to_be32(0);
+	agf->agf_flcount = cpu_to_be32(flcount);
+	agf->agf_fllast = cpu_to_be32(flcount - 1);
+
+	xfs_alloc_log_agf(sc->tp, agf_bp,
+			XFS_AGF_FLFIRST | XFS_AGF_FLLAST | XFS_AGF_FLCOUNT);
+}
+
+/* Write out a totally new AGFL. */
+STATIC void
+xrep_agfl_init_header(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agfl_bp,
+	struct xfs_bitmap	*agfl_extents,
+	xfs_agblock_t		flcount)
+{
+	struct xfs_mount	*mp = sc->mp;
+	__be32			*agfl_bno;
+	struct xfs_bitmap_range	*br;
+	struct xfs_bitmap_range	*n;
+	struct xfs_agfl		*agfl;
+	xfs_agblock_t		agbno;
+	unsigned int		fl_off;
+
+	ASSERT(flcount <= xfs_agfl_size(mp));
+
+	/*
+	 * Start rewriting the header by setting the bno[] array to
+	 * NULLAGBLOCK, then setting AGFL header fields.
+	 */
+	agfl = XFS_BUF_TO_AGFL(agfl_bp);
+	memset(agfl, 0xFF, BBTOB(agfl_bp->b_length));
+	agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
+	agfl->agfl_seqno = cpu_to_be32(sc->sa.agno);
+	uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
+
+	/*
+	 * Fill the AGFL with the remaining blocks.  If agfl_extents has more
+	 * blocks than fit in the AGFL, they will be freed in a subsequent
+	 * step.
+	 */
+	fl_off = 0;
+	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, agfl_bp);
+	for_each_xfs_bitmap_extent(br, n, agfl_extents) {
+		agbno = XFS_FSB_TO_AGBNO(mp, br->start);
+
+		trace_xrep_agfl_insert(mp, sc->sa.agno, agbno, br->len);
+
+		while (br->len > 0 && fl_off < flcount) {
+			agfl_bno[fl_off] = cpu_to_be32(agbno);
+			fl_off++;
+			agbno++;
+
+			/*
+			 * We've now used br->start by putting it in the AGFL,
+			 * so bump br so that we don't reap the block later.
+			 */
+			br->start++;
+			br->len--;
+		}
+
+		if (br->len)
+			break;
+		list_del(&br->list);
+		kmem_free(br);
+	}
+
+	/* Write new AGFL to disk. */
+	xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF);
+	xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1);
+}
+
+/* Repair the AGFL. */
+int
+xrep_agfl(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_owner_info	oinfo;
+	struct xfs_bitmap	agfl_extents;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*agf_bp;
+	struct xfs_buf		*agfl_bp;
+	xfs_agblock_t		flcount;
+	int			error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	xchk_perag_get(sc->mp, &sc->sa);
+	xfs_bitmap_init(&agfl_extents);
+
+	/*
+	 * Read the AGF so that we can query the rmapbt.  We hope that there's
+	 * nothing wrong with the AGF, but all the AG header repair functions
+	 * have this chicken-and-egg problem.
+	 */
+	error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp);
+	if (error)
+		return error;
+	if (!agf_bp)
+		return -ENOMEM;
+
+	/*
+	 * Make sure we have the AGFL buffer, as scrub might have decided it
+	 * was corrupt after xfs_alloc_read_agfl failed with -EFSCORRUPTED.
+	 */
+	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGFL_DADDR(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL);
+	if (error)
+		return error;
+	agfl_bp->b_ops = &xfs_agfl_buf_ops;
+
+	/* Gather all the extents we're going to put on the new AGFL. */
+	error = xrep_agfl_collect_blocks(sc, agf_bp, &agfl_extents, &flcount);
+	if (error)
+		goto err;
+
+	/*
+	 * Update AGF and AGFL.  We reset the global free block counter when
+	 * we adjust the AGF flcount (which can fail) so avoid updating any
+	 * buffers until we know that part works.
+	 */
+	xrep_agfl_update_agf(sc, agf_bp, flcount);
+	xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount);
+
+	/*
+	 * Ok, the AGFL should be ready to go now.  Roll the transaction to
+	 * make the new AGFL permanent before we start using it to return
+	 * freespace overflow to the freespace btrees.
+	 */
+	sc->sa.agf_bp = agf_bp;
+	sc->sa.agfl_bp = agfl_bp;
+	error = xrep_roll_ag_trans(sc);
+	if (error)
+		goto err;
+
+	/* Dump any AGFL overflow. */
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
+	return xrep_reap_extents(sc, &agfl_extents, &oinfo, XFS_AG_RESV_AGFL);
+err:
+	xfs_bitmap_destroy(&agfl_extents);
+	return error;
+}
+
+/* AGI */
+
+/*
+ * Offset within the xrep_find_ag_btree array for each btree type.  Avoid the
+ * XFS_BTNUM_ names here to avoid creating a sparse array.
+ */
+enum {
+	XREP_AGI_INOBT = 0,
+	XREP_AGI_FINOBT,
+	XREP_AGI_END,
+	XREP_AGI_MAX
+};
+
+/*
+ * Given the inode btree roots described by *fab, find the roots, check them
+ * for sanity, and pass the root data back out via *fab.
+ */
+STATIC int
+xrep_agi_find_btrees(
+	struct xfs_scrub		*sc,
+	struct xrep_find_ag_btree	*fab)
+{
+	struct xfs_buf			*agf_bp;
+	struct xfs_mount		*mp = sc->mp;
+	int				error;
+
+	/* Read the AGF. */
+	error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp);
+	if (error)
+		return error;
+	if (!agf_bp)
+		return -ENOMEM;
+
+	/* Find the btree roots. */
+	error = xrep_find_ag_btree_roots(sc, agf_bp, fab, NULL);
+	if (error)
+		return error;
+
+	/* We must find the inobt root. */
+	if (!xrep_check_btree_root(sc, &fab[XREP_AGI_INOBT]))
+		return -EFSCORRUPTED;
+
+	/* We must find the finobt root if that feature is enabled. */
+	if (xfs_sb_version_hasfinobt(&mp->m_sb) &&
+	    !xrep_check_btree_root(sc, &fab[XREP_AGI_FINOBT]))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/*
+ * Reinitialize the AGI header, making an in-core copy of the old contents so
+ * that we know which in-core state needs to be reinitialized.
+ */
+STATIC void
+xrep_agi_init_header(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agi_bp,
+	struct xfs_agi		*old_agi)
+{
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
+	struct xfs_mount	*mp = sc->mp;
+
+	memcpy(old_agi, agi, sizeof(*old_agi));
+	memset(agi, 0, BBTOB(agi_bp->b_length));
+	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
+	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
+	agi->agi_seqno = cpu_to_be32(sc->sa.agno);
+	agi->agi_length = cpu_to_be32(xfs_ag_block_count(mp, sc->sa.agno));
+	agi->agi_newino = cpu_to_be32(NULLAGINO);
+	agi->agi_dirino = cpu_to_be32(NULLAGINO);
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
+
+	/* We don't know how to fix the unlinked list yet. */
+	memcpy(&agi->agi_unlinked, &old_agi->agi_unlinked,
+			sizeof(agi->agi_unlinked));
+
+	/* Mark the incore AGF data stale until we're done fixing things. */
+	ASSERT(sc->sa.pag->pagi_init);
+	sc->sa.pag->pagi_init = 0;
+}
+
+/* Set btree root information in an AGI. */
+STATIC void
+xrep_agi_set_roots(
+	struct xfs_scrub		*sc,
+	struct xfs_agi			*agi,
+	struct xrep_find_ag_btree	*fab)
+{
+	agi->agi_root = cpu_to_be32(fab[XREP_AGI_INOBT].root);
+	agi->agi_level = cpu_to_be32(fab[XREP_AGI_INOBT].height);
+
+	if (xfs_sb_version_hasfinobt(&sc->mp->m_sb)) {
+		agi->agi_free_root = cpu_to_be32(fab[XREP_AGI_FINOBT].root);
+		agi->agi_free_level = cpu_to_be32(fab[XREP_AGI_FINOBT].height);
+	}
+}
+
+/* Update the AGI counters. */
+STATIC int
+xrep_agi_calc_from_btrees(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agi_bp)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agino_t		count;
+	xfs_agino_t		freecount;
+	int			error;
+
+	cur = xfs_inobt_init_cursor(mp, sc->tp, agi_bp, sc->sa.agno,
+			XFS_BTNUM_INO);
+	error = xfs_ialloc_count_inodes(cur, &count, &freecount);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+
+	agi->agi_count = cpu_to_be32(count);
+	agi->agi_freecount = cpu_to_be32(freecount);
+	return 0;
+err:
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/* Trigger reinitialization of the in-core data. */
+STATIC int
+xrep_agi_commit_new(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agi_bp)
+{
+	struct xfs_perag	*pag;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
+
+	/* Trigger inode count recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/* Write this to disk. */
+	xfs_trans_buf_set_type(sc->tp, agi_bp, XFS_BLFT_AGI_BUF);
+	xfs_trans_log_buf(sc->tp, agi_bp, 0, BBTOB(agi_bp->b_length) - 1);
+
+	/* Now reinitialize the in-core counters if necessary. */
+	pag = sc->sa.pag;
+	pag->pagi_count = be32_to_cpu(agi->agi_count);
+	pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
+	pag->pagi_init = 1;
+
+	return 0;
+}
+
+/* Repair the AGI. */
+int
+xrep_agi(
+	struct xfs_scrub		*sc)
+{
+	struct xrep_find_ag_btree	fab[XREP_AGI_MAX] = {
+		[XREP_AGI_INOBT] = {
+			.rmap_owner = XFS_RMAP_OWN_INOBT,
+			.buf_ops = &xfs_inobt_buf_ops,
+			.magic = XFS_IBT_CRC_MAGIC,
+		},
+		[XREP_AGI_FINOBT] = {
+			.rmap_owner = XFS_RMAP_OWN_INOBT,
+			.buf_ops = &xfs_inobt_buf_ops,
+			.magic = XFS_FIBT_CRC_MAGIC,
+		},
+		[XREP_AGI_END] = {
+			.buf_ops = NULL
+		},
+	};
+	struct xfs_agi			old_agi;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_buf			*agi_bp;
+	struct xfs_agi			*agi;
+	int				error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	xchk_perag_get(sc->mp, &sc->sa);
+	/*
+	 * Make sure we have the AGI buffer, as scrub might have decided it
+	 * was corrupt after xfs_ialloc_read_agi failed with -EFSCORRUPTED.
+	 */
+	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGI_DADDR(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &agi_bp, NULL);
+	if (error)
+		return error;
+	agi_bp->b_ops = &xfs_agi_buf_ops;
+	agi = XFS_BUF_TO_AGI(agi_bp);
+
+	/* Find the AGI btree roots. */
+	error = xrep_agi_find_btrees(sc, fab);
+	if (error)
+		return error;
+
+	/* Start rewriting the header and implant the btrees we found. */
+	xrep_agi_init_header(sc, agi_bp, &old_agi);
+	xrep_agi_set_roots(sc, agi, fab);
+	error = xrep_agi_calc_from_btrees(sc, agi_bp);
+	if (error)
+		goto out_revert;
+
+	/* Reinitialize in-core state. */
+	return xrep_agi_commit_new(sc, agi_bp);
+
+out_revert:
+	/* Mark the incore AGI state stale and revert the AGI. */
+	sc->sa.pag->pagi_init = 0;
+	memcpy(agi, &old_agi, sizeof(old_agi));
+	return error;
+}
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 50e4f7fa06f0..036b5c7021eb 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -28,11 +28,11 @@
  * Set us up to scrub free space btrees.
  */
 int
-xfs_scrub_setup_ag_allocbt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_ag_allocbt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, ip, false);
 }
 
 /* Free space btree scrubber. */
@@ -41,71 +41,71 @@ xfs_scrub_setup_ag_allocbt(
  * bnobt/cntbt record, respectively.
  */
 STATIC void
-xfs_scrub_allocbt_xref_other(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_allocbt_xref_other(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	struct xfs_btree_cur		**pcur;
-	xfs_agblock_t			fbno;
-	xfs_extlen_t			flen;
-	int				has_otherrec;
-	int				error;
+	struct xfs_btree_cur	**pcur;
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	int			has_otherrec;
+	int			error;
 
 	if (sc->sm->sm_type == XFS_SCRUB_TYPE_BNOBT)
 		pcur = &sc->sa.cnt_cur;
 	else
 		pcur = &sc->sa.bno_cur;
-	if (!*pcur || xfs_scrub_skip_xref(sc->sm))
+	if (!*pcur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_alloc_lookup_le(*pcur, agbno, len, &has_otherrec);
-	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
+	if (!xchk_should_check_xref(sc, &error, pcur))
 		return;
 	if (!has_otherrec) {
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 		return;
 	}
 
 	error = xfs_alloc_get_rec(*pcur, &fbno, &flen, &has_otherrec);
-	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
+	if (!xchk_should_check_xref(sc, &error, pcur))
 		return;
 	if (!has_otherrec) {
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 		return;
 	}
 
 	if (fbno != agbno || flen != len)
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_allocbt_xref(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_allocbt_xref(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_allocbt_xref_other(sc, agbno, len);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
-	xfs_scrub_xref_has_no_owner(sc, agbno, len);
-	xfs_scrub_xref_is_not_shared(sc, agbno, len);
+	xchk_allocbt_xref_other(sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(sc, agbno, len);
+	xchk_xref_has_no_owner(sc, agbno, len);
+	xchk_xref_is_not_shared(sc, agbno, len);
 }
 
 /* Scrub a bnobt/cntbt record. */
 STATIC int
-xfs_scrub_allocbt_rec(
-	struct xfs_scrub_btree		*bs,
-	union xfs_btree_rec		*rec)
+xchk_allocbt_rec(
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
-	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
-	xfs_agblock_t			bno;
-	xfs_extlen_t			len;
-	int				error = 0;
+	struct xfs_mount	*mp = bs->cur->bc_mp;
+	xfs_agnumber_t		agno = bs->cur->bc_private.a.agno;
+	xfs_agblock_t		bno;
+	xfs_extlen_t		len;
+	int			error = 0;
 
 	bno = be32_to_cpu(rec->alloc.ar_startblock);
 	len = be32_to_cpu(rec->alloc.ar_blockcount);
@@ -113,57 +113,57 @@ xfs_scrub_allocbt_rec(
 	if (bno + len <= bno ||
 	    !xfs_verify_agbno(mp, agno, bno) ||
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xfs_scrub_allocbt_xref(bs->sc, bno, len);
+	xchk_allocbt_xref(bs->sc, bno, len);
 
 	return error;
 }
 
 /* Scrub the freespace btrees for some AG. */
 STATIC int
-xfs_scrub_allocbt(
-	struct xfs_scrub_context	*sc,
-	xfs_btnum_t			which)
+xchk_allocbt(
+	struct xfs_scrub	*sc,
+	xfs_btnum_t		which)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_btree_cur		*cur;
+	struct xfs_owner_info	oinfo;
+	struct xfs_btree_cur	*cur;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
 	cur = which == XFS_BTNUM_BNO ? sc->sa.bno_cur : sc->sa.cnt_cur;
-	return xfs_scrub_btree(sc, cur, xfs_scrub_allocbt_rec, &oinfo, NULL);
+	return xchk_btree(sc, cur, xchk_allocbt_rec, &oinfo, NULL);
 }
 
 int
-xfs_scrub_bnobt(
-	struct xfs_scrub_context	*sc)
+xchk_bnobt(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_allocbt(sc, XFS_BTNUM_BNO);
+	return xchk_allocbt(sc, XFS_BTNUM_BNO);
 }
 
 int
-xfs_scrub_cntbt(
-	struct xfs_scrub_context	*sc)
+xchk_cntbt(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_allocbt(sc, XFS_BTNUM_CNT);
+	return xchk_allocbt(sc, XFS_BTNUM_CNT);
 }
 
 /* xref check that the extent is not free */
 void
-xfs_scrub_xref_is_used_space(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_xref_is_used_space(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	bool				is_freesp;
-	int				error;
+	bool			is_freesp;
+	int			error;
 
-	if (!sc->sa.bno_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.bno_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_alloc_has_record(sc->sa.bno_cur, agbno, len, &is_freesp);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.bno_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
 	if (is_freesp)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.bno_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.bno_cur, 0);
 }
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index de51cf8a8516..81d5e90547a1 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -32,11 +32,11 @@
 
 /* Set us up to scrub an inode's extended attributes. */
 int
-xfs_scrub_setup_xattr(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_xattr(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	size_t				sz;
+	size_t			sz;
 
 	/*
 	 * Allocate the buffer without the inode lock held.  We need enough
@@ -50,14 +50,14 @@ xfs_scrub_setup_xattr(
 	if (!sc->buf)
 		return -ENOMEM;
 
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Extended Attributes */
 
-struct xfs_scrub_xattr {
+struct xchk_xattr {
 	struct xfs_attr_list_context	context;
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub		*sc;
 };
 
 /*
@@ -69,22 +69,22 @@ struct xfs_scrub_xattr {
  * or if we get more or less data than we expected.
  */
 static void
-xfs_scrub_xattr_listent(
+xchk_xattr_listent(
 	struct xfs_attr_list_context	*context,
 	int				flags,
 	unsigned char			*name,
 	int				namelen,
 	int				valuelen)
 {
-	struct xfs_scrub_xattr		*sx;
+	struct xchk_xattr		*sx;
 	struct xfs_da_args		args = { NULL };
 	int				error = 0;
 
-	sx = container_of(context, struct xfs_scrub_xattr, context);
+	sx = container_of(context, struct xchk_xattr, context);
 
 	if (flags & XFS_ATTR_INCOMPLETE) {
 		/* Incomplete attr key, just mark the inode for preening. */
-		xfs_scrub_ino_set_preen(sx->sc, context->dp->i_ino);
+		xchk_ino_set_preen(sx->sc, context->dp->i_ino);
 		return;
 	}
 
@@ -106,11 +106,11 @@ xfs_scrub_xattr_listent(
 	error = xfs_attr_get_ilocked(context->dp, &args);
 	if (error == -EEXIST)
 		error = 0;
-	if (!xfs_scrub_fblock_process_error(sx->sc, XFS_ATTR_FORK, args.blkno,
+	if (!xchk_fblock_process_error(sx->sc, XFS_ATTR_FORK, args.blkno,
 			&error))
 		goto fail_xref;
 	if (args.valuelen != valuelen)
-		xfs_scrub_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
+		xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
 					     args.blkno);
 fail_xref:
 	if (sx->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -126,14 +126,14 @@ fail_xref:
  * the smallest address
  */
 STATIC bool
-xfs_scrub_xattr_set_map(
-	struct xfs_scrub_context	*sc,
-	unsigned long			*map,
-	unsigned int			start,
-	unsigned int			len)
+xchk_xattr_set_map(
+	struct xfs_scrub	*sc,
+	unsigned long		*map,
+	unsigned int		start,
+	unsigned int		len)
 {
-	unsigned int			mapsize = sc->mp->m_attr_geo->blksize;
-	bool				ret = true;
+	unsigned int		mapsize = sc->mp->m_attr_geo->blksize;
+	bool			ret = true;
 
 	if (start >= mapsize)
 		return false;
@@ -154,8 +154,8 @@ xfs_scrub_xattr_set_map(
  * attr freemap has problems or points to used space.
  */
 STATIC bool
-xfs_scrub_xattr_check_freemap(
-	struct xfs_scrub_context	*sc,
+xchk_xattr_check_freemap(
+	struct xfs_scrub		*sc,
 	unsigned long			*map,
 	struct xfs_attr3_icleaf_hdr	*leafhdr)
 {
@@ -168,7 +168,7 @@ xfs_scrub_xattr_check_freemap(
 	freemap = (unsigned long *)sc->buf + BITS_TO_LONGS(mapsize);
 	bitmap_zero(freemap, mapsize);
 	for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
-		if (!xfs_scrub_xattr_set_map(sc, freemap,
+		if (!xchk_xattr_set_map(sc, freemap,
 				leafhdr->freemap[i].base,
 				leafhdr->freemap[i].size))
 			return false;
@@ -184,8 +184,8 @@ xfs_scrub_xattr_check_freemap(
  * Returns the number of bytes used for the name/value data.
  */
 STATIC void
-xfs_scrub_xattr_entry(
-	struct xfs_scrub_da_btree	*ds,
+xchk_xattr_entry(
+	struct xchk_da_btree		*ds,
 	int				level,
 	char				*buf_end,
 	struct xfs_attr_leafblock	*leaf,
@@ -204,17 +204,17 @@ xfs_scrub_xattr_entry(
 	unsigned int			namesize;
 
 	if (ent->pad2 != 0)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	/* Hash values in order? */
 	if (be32_to_cpu(ent->hashval) < *last_hashval)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	*last_hashval = be32_to_cpu(ent->hashval);
 
 	nameidx = be16_to_cpu(ent->nameidx);
 	if (nameidx < leafhdr->firstused ||
 	    nameidx >= mp->m_attr_geo->blksize) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		return;
 	}
 
@@ -225,27 +225,27 @@ xfs_scrub_xattr_entry(
 				be16_to_cpu(lentry->valuelen));
 		name_end = (char *)lentry + namesize;
 		if (lentry->namelen == 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	} else {
 		rentry = xfs_attr3_leaf_name_remote(leaf, idx);
 		namesize = xfs_attr_leaf_entsize_remote(rentry->namelen);
 		name_end = (char *)rentry + namesize;
 		if (rentry->namelen == 0 || rentry->valueblk == 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	}
 	if (name_end > buf_end)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
-	if (!xfs_scrub_xattr_set_map(ds->sc, usedmap, nameidx, namesize))
-		xfs_scrub_da_set_corrupt(ds, level);
+	if (!xchk_xattr_set_map(ds->sc, usedmap, nameidx, namesize))
+		xchk_da_set_corrupt(ds, level);
 	if (!(ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		*usedbytes += namesize;
 }
 
 /* Scrub an attribute leaf. */
 STATIC int
-xfs_scrub_xattr_block(
-	struct xfs_scrub_da_btree	*ds,
+xchk_xattr_block(
+	struct xchk_da_btree		*ds,
 	int				level)
 {
 	struct xfs_attr3_icleaf_hdr	leafhdr;
@@ -275,10 +275,10 @@ xfs_scrub_xattr_block(
 
 		if (leaf->hdr.pad1 != 0 || leaf->hdr.pad2 != 0 ||
 		    leaf->hdr.info.hdr.pad != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	} else {
 		if (leaf->hdr.pad1 != 0 || leaf->hdr.info.pad != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	}
 
 	/* Check the leaf header */
@@ -286,44 +286,44 @@ xfs_scrub_xattr_block(
 	hdrsize = xfs_attr3_leaf_hdr_size(leaf);
 
 	if (leafhdr.usedbytes > mp->m_attr_geo->blksize)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	if (leafhdr.firstused > mp->m_attr_geo->blksize)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	if (leafhdr.firstused < hdrsize)
-		xfs_scrub_da_set_corrupt(ds, level);
-	if (!xfs_scrub_xattr_set_map(ds->sc, usedmap, 0, hdrsize))
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
+	if (!xchk_xattr_set_map(ds->sc, usedmap, 0, hdrsize))
+		xchk_da_set_corrupt(ds, level);
 
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
 	entries = xfs_attr3_leaf_entryp(leaf);
 	if ((char *)&entries[leafhdr.count] > (char *)leaf + leafhdr.firstused)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	buf_end = (char *)bp->b_addr + mp->m_attr_geo->blksize;
 	for (i = 0, ent = entries; i < leafhdr.count; ent++, i++) {
 		/* Mark the leaf entry itself. */
 		off = (char *)ent - (char *)leaf;
-		if (!xfs_scrub_xattr_set_map(ds->sc, usedmap, off,
+		if (!xchk_xattr_set_map(ds->sc, usedmap, off,
 				sizeof(xfs_attr_leaf_entry_t))) {
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 			goto out;
 		}
 
 		/* Check the entry and nameval. */
-		xfs_scrub_xattr_entry(ds, level, buf_end, leaf, &leafhdr,
+		xchk_xattr_entry(ds, level, buf_end, leaf, &leafhdr,
 				usedmap, ent, i, &usedbytes, &last_hashval);
 
 		if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			goto out;
 	}
 
-	if (!xfs_scrub_xattr_check_freemap(ds->sc, usedmap, &leafhdr))
-		xfs_scrub_da_set_corrupt(ds, level);
+	if (!xchk_xattr_check_freemap(ds->sc, usedmap, &leafhdr))
+		xchk_da_set_corrupt(ds, level);
 
 	if (leafhdr.usedbytes != usedbytes)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 out:
 	return 0;
@@ -331,8 +331,8 @@ out:
 
 /* Scrub a attribute btree record. */
 STATIC int
-xfs_scrub_xattr_rec(
-	struct xfs_scrub_da_btree	*ds,
+xchk_xattr_rec(
+	struct xchk_da_btree		*ds,
 	int				level,
 	void				*rec)
 {
@@ -352,14 +352,14 @@ xfs_scrub_xattr_rec(
 	blk = &ds->state->path.blk[level];
 
 	/* Check the whole block, if necessary. */
-	error = xfs_scrub_xattr_block(ds, level);
+	error = xchk_xattr_block(ds, level);
 	if (error)
 		goto out;
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
 	/* Check the hash of the entry. */
-	error = xfs_scrub_da_btree_hash(ds, level, &ent->hashval);
+	error = xchk_da_btree_hash(ds, level, &ent->hashval);
 	if (error)
 		goto out;
 
@@ -368,7 +368,7 @@ xfs_scrub_xattr_rec(
 	hdrsize = xfs_attr3_leaf_hdr_size(bp->b_addr);
 	nameidx = be16_to_cpu(ent->nameidx);
 	if (nameidx < hdrsize || nameidx >= mp->m_attr_geo->blksize) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out;
 	}
 
@@ -377,12 +377,12 @@ xfs_scrub_xattr_rec(
 	badflags = ~(XFS_ATTR_LOCAL | XFS_ATTR_ROOT | XFS_ATTR_SECURE |
 			XFS_ATTR_INCOMPLETE);
 	if ((ent->flags & badflags) != 0)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	if (ent->flags & XFS_ATTR_LOCAL) {
 		lentry = (struct xfs_attr_leaf_name_local *)
 				(((char *)bp->b_addr) + nameidx);
 		if (lentry->namelen <= 0) {
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 			goto out;
 		}
 		calc_hash = xfs_da_hashname(lentry->nameval, lentry->namelen);
@@ -390,13 +390,13 @@ xfs_scrub_xattr_rec(
 		rentry = (struct xfs_attr_leaf_name_remote *)
 				(((char *)bp->b_addr) + nameidx);
 		if (rentry->namelen <= 0) {
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 			goto out;
 		}
 		calc_hash = xfs_da_hashname(rentry->name, rentry->namelen);
 	}
 	if (calc_hash != hash)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 out:
 	return error;
@@ -404,10 +404,10 @@ out:
 
 /* Scrub the extended attribute metadata. */
 int
-xfs_scrub_xattr(
-	struct xfs_scrub_context	*sc)
+xchk_xattr(
+	struct xfs_scrub		*sc)
 {
-	struct xfs_scrub_xattr		sx;
+	struct xchk_xattr		sx;
 	struct attrlist_cursor_kern	cursor = { 0 };
 	xfs_dablk_t			last_checked = -1U;
 	int				error = 0;
@@ -417,7 +417,7 @@ xfs_scrub_xattr(
 
 	memset(&sx, 0, sizeof(sx));
 	/* Check attribute tree structure */
-	error = xfs_scrub_da_btree(sc, XFS_ATTR_FORK, xfs_scrub_xattr_rec,
+	error = xchk_da_btree(sc, XFS_ATTR_FORK, xchk_xattr_rec,
 			&last_checked);
 	if (error)
 		goto out;
@@ -429,7 +429,7 @@ xfs_scrub_xattr(
 	sx.context.dp = sc->ip;
 	sx.context.cursor = &cursor;
 	sx.context.resynch = 1;
-	sx.context.put_listent = xfs_scrub_xattr_listent;
+	sx.context.put_listent = xchk_xattr_listent;
 	sx.context.tp = sc->tp;
 	sx.context.flags = ATTR_INCOMPLETE;
 	sx.sc = sc;
@@ -438,7 +438,7 @@ xfs_scrub_xattr(
 	 * Look up every xattr in this file by name.
 	 *
 	 * Use the backend implementation of xfs_attr_list to call
-	 * xfs_scrub_xattr_listent on every attribute key in this inode.
+	 * xchk_xattr_listent on every attribute key in this inode.
 	 * In other words, we use the same iterator/callback mechanism
 	 * that listattr uses to scrub extended attributes, though in our
 	 * _listent function, we check the value of the attribute.
@@ -451,7 +451,7 @@ xfs_scrub_xattr(
 	 * locking order.
 	 */
 	error = xfs_attr_list_int_ilocked(&sx.context);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error))
 		goto out;
 out:
 	return error;
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
new file mode 100644
index 000000000000..fdadc9e1dc49
--- /dev/null
+++ b/fs/xfs/scrub/bitmap.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+
+/*
+ * Set a range of this bitmap.  Caller must ensure the range is not set.
+ *
+ * This is the logical equivalent of bitmap |= mask(start, len).
+ */
+int
+xfs_bitmap_set(
+	struct xfs_bitmap	*bitmap,
+	uint64_t		start,
+	uint64_t		len)
+{
+	struct xfs_bitmap_range	*bmr;
+
+	bmr = kmem_alloc(sizeof(struct xfs_bitmap_range), KM_MAYFAIL);
+	if (!bmr)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&bmr->list);
+	bmr->start = start;
+	bmr->len = len;
+	list_add_tail(&bmr->list, &bitmap->list);
+
+	return 0;
+}
+
+/* Free everything related to this bitmap. */
+void
+xfs_bitmap_destroy(
+	struct xfs_bitmap	*bitmap)
+{
+	struct xfs_bitmap_range	*bmr;
+	struct xfs_bitmap_range	*n;
+
+	for_each_xfs_bitmap_extent(bmr, n, bitmap) {
+		list_del(&bmr->list);
+		kmem_free(bmr);
+	}
+}
+
+/* Set up a per-AG block bitmap. */
+void
+xfs_bitmap_init(
+	struct xfs_bitmap	*bitmap)
+{
+	INIT_LIST_HEAD(&bitmap->list);
+}
+
+/* Compare two btree extents. */
+static int
+xfs_bitmap_range_cmp(
+	void			*priv,
+	struct list_head	*a,
+	struct list_head	*b)
+{
+	struct xfs_bitmap_range	*ap;
+	struct xfs_bitmap_range	*bp;
+
+	ap = container_of(a, struct xfs_bitmap_range, list);
+	bp = container_of(b, struct xfs_bitmap_range, list);
+
+	if (ap->start > bp->start)
+		return 1;
+	if (ap->start < bp->start)
+		return -1;
+	return 0;
+}
+
+/*
+ * Remove all the blocks mentioned in @sub from the extents in @bitmap.
+ *
+ * The intent is that callers will iterate the rmapbt for all of its records
+ * for a given owner to generate @bitmap; and iterate all the blocks of the
+ * metadata structures that are not being rebuilt and have the same rmapbt
+ * owner to generate @sub.  This routine subtracts all the extents
+ * mentioned in sub from all the extents linked in @bitmap, which leaves
+ * @bitmap as the list of blocks that are not accounted for, which we assume
+ * are the dead blocks of the old metadata structure.  The blocks mentioned in
+ * @bitmap can be reaped.
+ *
+ * This is the logical equivalent of bitmap &= ~sub.
+ */
+#define LEFT_ALIGNED	(1 << 0)
+#define RIGHT_ALIGNED	(1 << 1)
+int
+xfs_bitmap_disunion(
+	struct xfs_bitmap	*bitmap,
+	struct xfs_bitmap	*sub)
+{
+	struct list_head	*lp;
+	struct xfs_bitmap_range	*br;
+	struct xfs_bitmap_range	*new_br;
+	struct xfs_bitmap_range	*sub_br;
+	uint64_t		sub_start;
+	uint64_t		sub_len;
+	int			state;
+	int			error = 0;
+
+	if (list_empty(&bitmap->list) || list_empty(&sub->list))
+		return 0;
+	ASSERT(!list_empty(&sub->list));
+
+	list_sort(NULL, &bitmap->list, xfs_bitmap_range_cmp);
+	list_sort(NULL, &sub->list, xfs_bitmap_range_cmp);
+
+	/*
+	 * Now that we've sorted both lists, we iterate bitmap once, rolling
+	 * forward through sub and/or bitmap as necessary until we find an
+	 * overlap or reach the end of either list.  We do not reset lp to the
+	 * head of bitmap nor do we reset sub_br to the head of sub.  The
+	 * list traversal is similar to merge sort, but we're deleting
+	 * instead.  In this manner we avoid O(n^2) operations.
+	 */
+	sub_br = list_first_entry(&sub->list, struct xfs_bitmap_range,
+			list);
+	lp = bitmap->list.next;
+	while (lp != &bitmap->list) {
+		br = list_entry(lp, struct xfs_bitmap_range, list);
+
+		/*
+		 * Advance sub_br and/or br until we find a pair that
+		 * intersect or we run out of extents.
+		 */
+		while (sub_br->start + sub_br->len <= br->start) {
+			if (list_is_last(&sub_br->list, &sub->list))
+				goto out;
+			sub_br = list_next_entry(sub_br, list);
+		}
+		if (sub_br->start >= br->start + br->len) {
+			lp = lp->next;
+			continue;
+		}
+
+		/* trim sub_br to fit the extent we have */
+		sub_start = sub_br->start;
+		sub_len = sub_br->len;
+		if (sub_br->start < br->start) {
+			sub_len -= br->start - sub_br->start;
+			sub_start = br->start;
+		}
+		if (sub_len > br->len)
+			sub_len = br->len;
+
+		state = 0;
+		if (sub_start == br->start)
+			state |= LEFT_ALIGNED;
+		if (sub_start + sub_len == br->start + br->len)
+			state |= RIGHT_ALIGNED;
+		switch (state) {
+		case LEFT_ALIGNED:
+			/* Coincides with only the left. */
+			br->start += sub_len;
+			br->len -= sub_len;
+			break;
+		case RIGHT_ALIGNED:
+			/* Coincides with only the right. */
+			br->len -= sub_len;
+			lp = lp->next;
+			break;
+		case LEFT_ALIGNED | RIGHT_ALIGNED:
+			/* Total overlap, just delete ex. */
+			lp = lp->next;
+			list_del(&br->list);
+			kmem_free(br);
+			break;
+		case 0:
+			/*
+			 * Deleting from the middle: add the new right extent
+			 * and then shrink the left extent.
+			 */
+			new_br = kmem_alloc(sizeof(struct xfs_bitmap_range),
+					KM_MAYFAIL);
+			if (!new_br) {
+				error = -ENOMEM;
+				goto out;
+			}
+			INIT_LIST_HEAD(&new_br->list);
+			new_br->start = sub_start + sub_len;
+			new_br->len = br->start + br->len - new_br->start;
+			list_add(&new_br->list, &br->list);
+			br->len = sub_start - br->start;
+			lp = lp->next;
+			break;
+		default:
+			ASSERT(0);
+			break;
+		}
+	}
+
+out:
+	return error;
+}
+#undef LEFT_ALIGNED
+#undef RIGHT_ALIGNED
+
+/*
+ * Record all btree blocks seen while iterating all records of a btree.
+ *
+ * We know that the btree query_all function starts at the left edge and walks
+ * towards the right edge of the tree.  Therefore, we know that we can walk up
+ * the btree cursor towards the root; if the pointer for a given level points
+ * to the first record/key in that block, we haven't seen this block before;
+ * and therefore we need to remember that we saw this block in the btree.
+ *
+ * So if our btree is:
+ *
+ *    4
+ *  / | \
+ * 1  2  3
+ *
+ * Pretend for this example that each leaf block has 100 btree records.  For
+ * the first btree record, we'll observe that bc_ptrs[0] == 1, so we record
+ * that we saw block 1.  Then we observe that bc_ptrs[1] == 1, so we record
+ * block 4.  The list is [1, 4].
+ *
+ * For the second btree record, we see that bc_ptrs[0] == 2, so we exit the
+ * loop.  The list remains [1, 4].
+ *
+ * For the 101st btree record, we've moved onto leaf block 2.  Now
+ * bc_ptrs[0] == 1 again, so we record that we saw block 2.  We see that
+ * bc_ptrs[1] == 2, so we exit the loop.  The list is now [1, 4, 2].
+ *
+ * For the 102nd record, bc_ptrs[0] == 2, so we continue.
+ *
+ * For the 201st record, we've moved on to leaf block 3.  bc_ptrs[0] == 1, so
+ * we add 3 to the list.  Now it is [1, 4, 2, 3].
+ *
+ * For the 300th record we just exit, with the list being [1, 4, 2, 3].
+ */
+
+/*
+ * Record all the buffers pointed to by the btree cursor.  Callers already
+ * engaged in a btree walk should call this function to capture the list of
+ * blocks going from the leaf towards the root.
+ */
+int
+xfs_bitmap_set_btcur_path(
+	struct xfs_bitmap	*bitmap,
+	struct xfs_btree_cur	*cur)
+{
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsb;
+	int			i;
+	int			error;
+
+	for (i = 0; i < cur->bc_nlevels && cur->bc_ptrs[i] == 1; i++) {
+		xfs_btree_get_block(cur, i, &bp);
+		if (!bp)
+			continue;
+		fsb = XFS_DADDR_TO_FSB(cur->bc_mp, bp->b_bn);
+		error = xfs_bitmap_set(bitmap, fsb, 1);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Collect a btree's block in the bitmap. */
+STATIC int
+xfs_bitmap_collect_btblock(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	void			*priv)
+{
+	struct xfs_bitmap	*bitmap = priv;
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsbno;
+
+	xfs_btree_get_block(cur, level, &bp);
+	if (!bp)
+		return 0;
+
+	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, bp->b_bn);
+	return xfs_bitmap_set(bitmap, fsbno, 1);
+}
+
+/* Walk the btree and mark the bitmap wherever a btree block is found. */
+int
+xfs_bitmap_set_btblocks(
+	struct xfs_bitmap	*bitmap,
+	struct xfs_btree_cur	*cur)
+{
+	return xfs_btree_visit_blocks(cur, xfs_bitmap_collect_btblock, bitmap);
+}
diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h
new file mode 100644
index 000000000000..ae8ecbce6fa6
--- /dev/null
+++ b/fs/xfs/scrub/bitmap.h
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#ifndef __XFS_SCRUB_BITMAP_H__
+#define __XFS_SCRUB_BITMAP_H__
+
+struct xfs_bitmap_range {
+	struct list_head	list;
+	uint64_t		start;
+	uint64_t		len;
+};
+
+struct xfs_bitmap {
+	struct list_head	list;
+};
+
+void xfs_bitmap_init(struct xfs_bitmap *bitmap);
+void xfs_bitmap_destroy(struct xfs_bitmap *bitmap);
+
+#define for_each_xfs_bitmap_extent(bex, n, bitmap) \
+	list_for_each_entry_safe((bex), (n), &(bitmap)->list, list)
+
+#define for_each_xfs_bitmap_block(b, bex, n, bitmap) \
+	list_for_each_entry_safe((bex), (n), &(bitmap)->list, list) \
+		for ((b) = bex->start; (b) < bex->start + bex->len; (b)++)
+
+int xfs_bitmap_set(struct xfs_bitmap *bitmap, uint64_t start, uint64_t len);
+int xfs_bitmap_disunion(struct xfs_bitmap *bitmap, struct xfs_bitmap *sub);
+int xfs_bitmap_set_btcur_path(struct xfs_bitmap *bitmap,
+		struct xfs_btree_cur *cur);
+int xfs_bitmap_set_btblocks(struct xfs_bitmap *bitmap,
+		struct xfs_btree_cur *cur);
+
+#endif	/* __XFS_SCRUB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 3d08589f5c60..e1d11f3223e3 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -33,13 +33,13 @@
 
 /* Set us up with an inode's bmap. */
 int
-xfs_scrub_setup_inode_bmap(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_inode_bmap(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	int				error;
+	int			error;
 
-	error = xfs_scrub_get_inode(sc, ip);
+	error = xchk_get_inode(sc, ip);
 	if (error)
 		goto out;
 
@@ -60,7 +60,7 @@ xfs_scrub_setup_inode_bmap(
 	}
 
 	/* Got the inode, lock it and we're ready to go. */
-	error = xfs_scrub_trans_alloc(sc, 0);
+	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -78,27 +78,27 @@ out:
  * is in btree format.
  */
 
-struct xfs_scrub_bmap_info {
-	struct xfs_scrub_context	*sc;
-	xfs_fileoff_t			lastoff;
-	bool				is_rt;
-	bool				is_shared;
-	int				whichfork;
+struct xchk_bmap_info {
+	struct xfs_scrub	*sc;
+	xfs_fileoff_t		lastoff;
+	bool			is_rt;
+	bool			is_shared;
+	int			whichfork;
 };
 
 /* Look for a corresponding rmap for this irec. */
 static inline bool
-xfs_scrub_bmap_get_rmap(
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_bmbt_irec		*irec,
-	xfs_agblock_t			agbno,
-	uint64_t			owner,
-	struct xfs_rmap_irec		*rmap)
+xchk_bmap_get_rmap(
+	struct xchk_bmap_info	*info,
+	struct xfs_bmbt_irec	*irec,
+	xfs_agblock_t		agbno,
+	uint64_t		owner,
+	struct xfs_rmap_irec	*rmap)
 {
-	xfs_fileoff_t			offset;
-	unsigned int			rflags = 0;
-	int				has_rmap;
-	int				error;
+	xfs_fileoff_t		offset;
+	unsigned int		rflags = 0;
+	int			has_rmap;
+	int			error;
 
 	if (info->whichfork == XFS_ATTR_FORK)
 		rflags |= XFS_RMAP_ATTR_FORK;
@@ -120,7 +120,7 @@ xfs_scrub_bmap_get_rmap(
 	if (info->is_shared) {
 		error = xfs_rmap_lookup_le_range(info->sc->sa.rmap_cur, agbno,
 				owner, offset, rflags, rmap, &has_rmap);
-		if (!xfs_scrub_should_check_xref(info->sc, &error,
+		if (!xchk_should_check_xref(info->sc, &error,
 				&info->sc->sa.rmap_cur))
 			return false;
 		goto out;
@@ -131,36 +131,36 @@ xfs_scrub_bmap_get_rmap(
 	 */
 	error = xfs_rmap_lookup_le(info->sc->sa.rmap_cur, agbno, 0, owner,
 			offset, rflags, &has_rmap);
-	if (!xfs_scrub_should_check_xref(info->sc, &error,
+	if (!xchk_should_check_xref(info->sc, &error,
 			&info->sc->sa.rmap_cur))
 		return false;
 	if (!has_rmap)
 		goto out;
 
 	error = xfs_rmap_get_rec(info->sc->sa.rmap_cur, rmap, &has_rmap);
-	if (!xfs_scrub_should_check_xref(info->sc, &error,
+	if (!xchk_should_check_xref(info->sc, &error,
 			&info->sc->sa.rmap_cur))
 		return false;
 
 out:
 	if (!has_rmap)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 			irec->br_startoff);
 	return has_rmap;
 }
 
 /* Make sure that we have rmapbt records for this extent. */
 STATIC void
-xfs_scrub_bmap_xref_rmap(
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_bmbt_irec		*irec,
-	xfs_agblock_t			agbno)
+xchk_bmap_xref_rmap(
+	struct xchk_bmap_info	*info,
+	struct xfs_bmbt_irec	*irec,
+	xfs_agblock_t		agbno)
 {
-	struct xfs_rmap_irec		rmap;
-	unsigned long long		rmap_end;
-	uint64_t			owner;
+	struct xfs_rmap_irec	rmap;
+	unsigned long long	rmap_end;
+	uint64_t		owner;
 
-	if (!info->sc->sa.rmap_cur || xfs_scrub_skip_xref(info->sc->sm))
+	if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm))
 		return;
 
 	if (info->whichfork == XFS_COW_FORK)
@@ -169,14 +169,14 @@ xfs_scrub_bmap_xref_rmap(
 		owner = info->sc->ip->i_ino;
 
 	/* Find the rmap record for this irec. */
-	if (!xfs_scrub_bmap_get_rmap(info, irec, agbno, owner, &rmap))
+	if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap))
 		return;
 
 	/* Check the rmap. */
 	rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount;
 	if (rmap.rm_startblock > agbno ||
 	    agbno + irec->br_blockcount > rmap_end)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/*
@@ -189,12 +189,12 @@ xfs_scrub_bmap_xref_rmap(
 				rmap.rm_blockcount;
 		if (rmap.rm_offset > irec->br_startoff ||
 		    irec->br_startoff + irec->br_blockcount > rmap_end)
-			xfs_scrub_fblock_xref_set_corrupt(info->sc,
+			xchk_fblock_xref_set_corrupt(info->sc,
 					info->whichfork, irec->br_startoff);
 	}
 
 	if (rmap.rm_owner != owner)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/*
@@ -207,46 +207,46 @@ xfs_scrub_bmap_xref_rmap(
 	if (owner != XFS_RMAP_OWN_COW &&
 	    irec->br_state == XFS_EXT_UNWRITTEN &&
 	    !(rmap.rm_flags & XFS_RMAP_UNWRITTEN))
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	if (info->whichfork == XFS_ATTR_FORK &&
 	    !(rmap.rm_flags & XFS_RMAP_ATTR_FORK))
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 }
 
 /* Cross-reference a single rtdev extent record. */
 STATIC void
-xfs_scrub_bmap_rt_extent_xref(
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_inode		*ip,
-	struct xfs_btree_cur		*cur,
-	struct xfs_bmbt_irec		*irec)
+xchk_bmap_rt_extent_xref(
+	struct xchk_bmap_info	*info,
+	struct xfs_inode	*ip,
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*irec)
 {
 	if (info->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_rt_space(info->sc, irec->br_startblock,
+	xchk_xref_is_used_rt_space(info->sc, irec->br_startblock,
 			irec->br_blockcount);
 }
 
 /* Cross-reference a single datadev extent record. */
 STATIC void
-xfs_scrub_bmap_extent_xref(
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_inode		*ip,
-	struct xfs_btree_cur		*cur,
-	struct xfs_bmbt_irec		*irec)
+xchk_bmap_extent_xref(
+	struct xchk_bmap_info	*info,
+	struct xfs_inode	*ip,
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_mount		*mp = info->sc->mp;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_extlen_t			len;
-	int				error;
+	struct xfs_mount	*mp = info->sc->mp;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_extlen_t		len;
+	int			error;
 
 	if (info->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -255,44 +255,44 @@ xfs_scrub_bmap_extent_xref(
 	agbno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock);
 	len = irec->br_blockcount;
 
-	error = xfs_scrub_ag_init(info->sc, agno, &info->sc->sa);
-	if (!xfs_scrub_fblock_process_error(info->sc, info->whichfork,
+	error = xchk_ag_init(info->sc, agno, &info->sc->sa);
+	if (!xchk_fblock_process_error(info->sc, info->whichfork,
 			irec->br_startoff, &error))
 		return;
 
-	xfs_scrub_xref_is_used_space(info->sc, agbno, len);
-	xfs_scrub_xref_is_not_inode_chunk(info->sc, agbno, len);
-	xfs_scrub_bmap_xref_rmap(info, irec, agbno);
+	xchk_xref_is_used_space(info->sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(info->sc, agbno, len);
+	xchk_bmap_xref_rmap(info, irec, agbno);
 	switch (info->whichfork) {
 	case XFS_DATA_FORK:
 		if (xfs_is_reflink_inode(info->sc->ip))
 			break;
 		/* fall through */
 	case XFS_ATTR_FORK:
-		xfs_scrub_xref_is_not_shared(info->sc, agbno,
+		xchk_xref_is_not_shared(info->sc, agbno,
 				irec->br_blockcount);
 		break;
 	case XFS_COW_FORK:
-		xfs_scrub_xref_is_cow_staging(info->sc, agbno,
+		xchk_xref_is_cow_staging(info->sc, agbno,
 				irec->br_blockcount);
 		break;
 	}
 
-	xfs_scrub_ag_free(info->sc, &info->sc->sa);
+	xchk_ag_free(info->sc, &info->sc->sa);
 }
 
 /* Scrub a single extent record. */
 STATIC int
-xfs_scrub_bmap_extent(
-	struct xfs_inode		*ip,
-	struct xfs_btree_cur		*cur,
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_bmbt_irec		*irec)
+xchk_bmap_extent(
+	struct xfs_inode	*ip,
+	struct xfs_btree_cur	*cur,
+	struct xchk_bmap_info	*info,
+	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_mount		*mp = info->sc->mp;
-	struct xfs_buf			*bp = NULL;
-	xfs_filblks_t			end;
-	int				error = 0;
+	struct xfs_mount	*mp = info->sc->mp;
+	struct xfs_buf		*bp = NULL;
+	xfs_filblks_t		end;
+	int			error = 0;
 
 	if (cur)
 		xfs_btree_get_block(cur, 0, &bp);
@@ -302,12 +302,12 @@ xfs_scrub_bmap_extent(
 	 * from the incore list, for which there is no ordering check.
 	 */
 	if (irec->br_startoff < info->lastoff)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/* There should never be a "hole" extent in either extent list. */
 	if (irec->br_startblock == HOLESTARTBLOCK)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/*
@@ -315,40 +315,40 @@ xfs_scrub_bmap_extent(
 	 * in-core extent scan, and we should never see these in the bmbt.
 	 */
 	if (isnullstartblock(irec->br_startblock))
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/* Make sure the extent points to a valid place. */
 	if (irec->br_blockcount > MAXEXTLEN)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	if (irec->br_startblock + irec->br_blockcount <= irec->br_startblock)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	end = irec->br_startblock + irec->br_blockcount - 1;
 	if (info->is_rt &&
 	    (!xfs_verify_rtbno(mp, irec->br_startblock) ||
 	     !xfs_verify_rtbno(mp, end)))
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	if (!info->is_rt &&
 	    (!xfs_verify_fsbno(mp, irec->br_startblock) ||
 	     !xfs_verify_fsbno(mp, end) ||
 	     XFS_FSB_TO_AGNO(mp, irec->br_startblock) !=
 				XFS_FSB_TO_AGNO(mp, end)))
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/* We don't allow unwritten extents on attr forks. */
 	if (irec->br_state == XFS_EXT_UNWRITTEN &&
 	    info->whichfork == XFS_ATTR_FORK)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	if (info->is_rt)
-		xfs_scrub_bmap_rt_extent_xref(info, ip, cur, irec);
+		xchk_bmap_rt_extent_xref(info, ip, cur, irec);
 	else
-		xfs_scrub_bmap_extent_xref(info, ip, cur, irec);
+		xchk_bmap_extent_xref(info, ip, cur, irec);
 
 	info->lastoff = irec->br_startoff + irec->br_blockcount;
 	return error;
@@ -356,17 +356,17 @@ xfs_scrub_bmap_extent(
 
 /* Scrub a bmbt record. */
 STATIC int
-xfs_scrub_bmapbt_rec(
-	struct xfs_scrub_btree		*bs,
-	union xfs_btree_rec		*rec)
+xchk_bmapbt_rec(
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xfs_scrub_bmap_info	*info = bs->private;
-	struct xfs_inode		*ip = bs->cur->bc_private.b.ip;
-	struct xfs_buf			*bp = NULL;
-	struct xfs_btree_block		*block;
-	uint64_t			owner;
-	int				i;
+	struct xfs_bmbt_irec	irec;
+	struct xchk_bmap_info	*info = bs->private;
+	struct xfs_inode	*ip = bs->cur->bc_private.b.ip;
+	struct xfs_buf		*bp = NULL;
+	struct xfs_btree_block	*block;
+	uint64_t		owner;
+	int			i;
 
 	/*
 	 * Check the owners of the btree blocks up to the level below
@@ -378,54 +378,53 @@ xfs_scrub_bmapbt_rec(
 			block = xfs_btree_get_block(bs->cur, i, &bp);
 			owner = be64_to_cpu(block->bb_u.l.bb_owner);
 			if (owner != ip->i_ino)
-				xfs_scrub_fblock_set_corrupt(bs->sc,
+				xchk_fblock_set_corrupt(bs->sc,
 						info->whichfork, 0);
 		}
 	}
 
 	/* Set up the in-core record and scrub it. */
 	xfs_bmbt_disk_get_all(&rec->bmbt, &irec);
-	return xfs_scrub_bmap_extent(ip, bs->cur, info, &irec);
+	return xchk_bmap_extent(ip, bs->cur, info, &irec);
 }
 
 /* Scan the btree records. */
 STATIC int
-xfs_scrub_bmap_btree(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	struct xfs_scrub_bmap_info	*info)
+xchk_bmap_btree(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	struct xchk_bmap_info	*info)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip = sc->ip;
-	struct xfs_btree_cur		*cur;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_btree_cur	*cur;
+	int			error;
 
 	cur = xfs_bmbt_init_cursor(mp, sc->tp, ip, whichfork);
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	error = xfs_scrub_btree(sc, cur, xfs_scrub_bmapbt_rec, &oinfo, info);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR :
-					  XFS_BTREE_NOERROR);
+	error = xchk_btree(sc, cur, xchk_bmapbt_rec, &oinfo, info);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
-struct xfs_scrub_bmap_check_rmap_info {
-	struct xfs_scrub_context	*sc;
-	int				whichfork;
-	struct xfs_iext_cursor		icur;
+struct xchk_bmap_check_rmap_info {
+	struct xfs_scrub	*sc;
+	int			whichfork;
+	struct xfs_iext_cursor	icur;
 };
 
 /* Can we find bmaps that fit this rmap? */
 STATIC int
-xfs_scrub_bmap_check_rmap(
+xchk_bmap_check_rmap(
 	struct xfs_btree_cur		*cur,
 	struct xfs_rmap_irec		*rec,
 	void				*priv)
 {
 	struct xfs_bmbt_irec		irec;
-	struct xfs_scrub_bmap_check_rmap_info	*sbcri = priv;
+	struct xchk_bmap_check_rmap_info	*sbcri = priv;
 	struct xfs_ifork		*ifp;
-	struct xfs_scrub_context	*sc = sbcri->sc;
+	struct xfs_scrub		*sc = sbcri->sc;
 	bool				have_map;
 
 	/* Is this even the right fork? */
@@ -440,14 +439,14 @@ xfs_scrub_bmap_check_rmap(
 	/* Now look up the bmbt record. */
 	ifp = XFS_IFORK_PTR(sc->ip, sbcri->whichfork);
 	if (!ifp) {
-		xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+		xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 				rec->rm_offset);
 		goto out;
 	}
 	have_map = xfs_iext_lookup_extent(sc->ip, ifp, rec->rm_offset,
 			&sbcri->icur, &irec);
 	if (!have_map)
-		xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+		xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 				rec->rm_offset);
 	/*
 	 * bmap extent record lengths are constrained to 2^21 blocks in length
@@ -458,14 +457,14 @@ xfs_scrub_bmap_check_rmap(
 	 */
 	while (have_map) {
 		if (irec.br_startoff != rec->rm_offset)
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 		if (irec.br_startblock != XFS_AGB_TO_FSB(sc->mp,
 				cur->bc_private.a.agno, rec->rm_startblock))
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 		if (irec.br_blockcount > rec->rm_blockcount)
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			break;
@@ -476,7 +475,7 @@ xfs_scrub_bmap_check_rmap(
 			break;
 		have_map = xfs_iext_next_extent(ifp, &sbcri->icur, &irec);
 		if (!have_map)
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 	}
 
@@ -488,12 +487,12 @@ out:
 
 /* Make sure each rmap has a corresponding bmbt entry. */
 STATIC int
-xfs_scrub_bmap_check_ag_rmaps(
-	struct xfs_scrub_context	*sc,
+xchk_bmap_check_ag_rmaps(
+	struct xfs_scrub		*sc,
 	int				whichfork,
 	xfs_agnumber_t			agno)
 {
-	struct xfs_scrub_bmap_check_rmap_info	sbcri;
+	struct xchk_bmap_check_rmap_info	sbcri;
 	struct xfs_btree_cur		*cur;
 	struct xfs_buf			*agf;
 	int				error;
@@ -510,11 +509,11 @@ xfs_scrub_bmap_check_ag_rmaps(
 
 	sbcri.sc = sc;
 	sbcri.whichfork = whichfork;
-	error = xfs_rmap_query_all(cur, xfs_scrub_bmap_check_rmap, &sbcri);
+	error = xfs_rmap_query_all(cur, xchk_bmap_check_rmap, &sbcri);
 	if (error == XFS_BTREE_QUERY_RANGE_ABORT)
 		error = 0;
 
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 out_agf:
 	xfs_trans_brelse(sc->tp, agf);
 	return error;
@@ -522,13 +521,13 @@ out_agf:
 
 /* Make sure each rmap has a corresponding bmbt entry. */
 STATIC int
-xfs_scrub_bmap_check_rmaps(
-	struct xfs_scrub_context	*sc,
-	int				whichfork)
+xchk_bmap_check_rmaps(
+	struct xfs_scrub	*sc,
+	int			whichfork)
 {
-	loff_t				size;
-	xfs_agnumber_t			agno;
-	int				error;
+	loff_t			size;
+	xfs_agnumber_t		agno;
+	int			error;
 
 	if (!xfs_sb_version_hasrmapbt(&sc->mp->m_sb) ||
 	    whichfork == XFS_COW_FORK ||
@@ -562,7 +561,7 @@ xfs_scrub_bmap_check_rmaps(
 		return 0;
 
 	for (agno = 0; agno < sc->mp->m_sb.sb_agcount; agno++) {
-		error = xfs_scrub_bmap_check_ag_rmaps(sc, whichfork, agno);
+		error = xchk_bmap_check_ag_rmaps(sc, whichfork, agno);
 		if (error)
 			return error;
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -579,18 +578,18 @@ xfs_scrub_bmap_check_rmaps(
  * Then we unconditionally scan the incore extent cache.
  */
 STATIC int
-xfs_scrub_bmap(
-	struct xfs_scrub_context	*sc,
-	int				whichfork)
+xchk_bmap(
+	struct xfs_scrub	*sc,
+	int			whichfork)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xfs_scrub_bmap_info	info = { NULL };
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip = sc->ip;
-	struct xfs_ifork		*ifp;
-	xfs_fileoff_t			endoff;
-	struct xfs_iext_cursor		icur;
-	int				error = 0;
+	struct xfs_bmbt_irec	irec;
+	struct xchk_bmap_info	info = { NULL };
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_ifork	*ifp;
+	xfs_fileoff_t		endoff;
+	struct xfs_iext_cursor	icur;
+	int			error = 0;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 
@@ -606,7 +605,7 @@ xfs_scrub_bmap(
 			goto out;
 		/* No CoW forks on non-reflink inodes/filesystems. */
 		if (!xfs_is_reflink_inode(ip)) {
-			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 			goto out;
 		}
 		break;
@@ -615,7 +614,7 @@ xfs_scrub_bmap(
 			goto out_check_rmap;
 		if (!xfs_sb_version_hasattr(&mp->m_sb) &&
 		    !xfs_sb_version_hasattr2(&mp->m_sb))
-			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		break;
 	default:
 		ASSERT(whichfork == XFS_DATA_FORK);
@@ -631,22 +630,22 @@ xfs_scrub_bmap(
 		goto out;
 	case XFS_DINODE_FMT_EXTENTS:
 		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-			xfs_scrub_fblock_set_corrupt(sc, whichfork, 0);
+			xchk_fblock_set_corrupt(sc, whichfork, 0);
 			goto out;
 		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (whichfork == XFS_COW_FORK) {
-			xfs_scrub_fblock_set_corrupt(sc, whichfork, 0);
+			xchk_fblock_set_corrupt(sc, whichfork, 0);
 			goto out;
 		}
 
-		error = xfs_scrub_bmap_btree(sc, whichfork, &info);
+		error = xchk_bmap_btree(sc, whichfork, &info);
 		if (error)
 			goto out;
 		break;
 	default:
-		xfs_scrub_fblock_set_corrupt(sc, whichfork, 0);
+		xchk_fblock_set_corrupt(sc, whichfork, 0);
 		goto out;
 	}
 
@@ -656,37 +655,37 @@ xfs_scrub_bmap(
 	/* Now try to scrub the in-memory extent list. */
         if (!(ifp->if_flags & XFS_IFEXTENTS)) {
 		error = xfs_iread_extents(sc->tp, ip, whichfork);
-		if (!xfs_scrub_fblock_process_error(sc, whichfork, 0, &error))
+		if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
 			goto out;
 	}
 
 	/* Find the offset of the last extent in the mapping. */
 	error = xfs_bmap_last_offset(ip, &endoff, whichfork);
-	if (!xfs_scrub_fblock_process_error(sc, whichfork, 0, &error))
+	if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
 		goto out;
 
 	/* Scrub extent records. */
 	info.lastoff = 0;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	for_each_xfs_iext(ifp, &icur, &irec) {
-		if (xfs_scrub_should_terminate(sc, &error) ||
+		if (xchk_should_terminate(sc, &error) ||
 		    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 			break;
 		if (isnullstartblock(irec.br_startblock))
 			continue;
 		if (irec.br_startoff >= endoff) {
-			xfs_scrub_fblock_set_corrupt(sc, whichfork,
+			xchk_fblock_set_corrupt(sc, whichfork,
 					irec.br_startoff);
 			goto out;
 		}
-		error = xfs_scrub_bmap_extent(ip, NULL, &info, &irec);
+		error = xchk_bmap_extent(ip, NULL, &info, &irec);
 		if (error)
 			goto out;
 	}
 
 out_check_rmap:
-	error = xfs_scrub_bmap_check_rmaps(sc, whichfork);
-	if (!xfs_scrub_fblock_xref_process_error(sc, whichfork, 0, &error))
+	error = xchk_bmap_check_rmaps(sc, whichfork);
+	if (!xchk_fblock_xref_process_error(sc, whichfork, 0, &error))
 		goto out;
 out:
 	return error;
@@ -694,27 +693,27 @@ out:
 
 /* Scrub an inode's data fork. */
 int
-xfs_scrub_bmap_data(
-	struct xfs_scrub_context	*sc)
+xchk_bmap_data(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_bmap(sc, XFS_DATA_FORK);
+	return xchk_bmap(sc, XFS_DATA_FORK);
 }
 
 /* Scrub an inode's attr fork. */
 int
-xfs_scrub_bmap_attr(
-	struct xfs_scrub_context	*sc)
+xchk_bmap_attr(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_bmap(sc, XFS_ATTR_FORK);
+	return xchk_bmap(sc, XFS_ATTR_FORK);
 }
 
 /* Scrub an inode's CoW fork. */
 int
-xfs_scrub_bmap_cow(
-	struct xfs_scrub_context	*sc)
+xchk_bmap_cow(
+	struct xfs_scrub	*sc)
 {
 	if (!xfs_is_reflink_inode(sc->ip))
 		return -ENOENT;
 
-	return xfs_scrub_bmap(sc, XFS_COW_FORK);
+	return xchk_bmap(sc, XFS_COW_FORK);
 }
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 5b472045f036..4ae959f7ad2c 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -29,13 +29,13 @@
  * operational errors in common.c.
  */
 static bool
-__xfs_scrub_btree_process_error(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	int				*error,
-	__u32				errflag,
-	void				*ret_ip)
+__xchk_btree_process_error(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*error,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	if (*error == 0)
 		return true;
@@ -43,7 +43,7 @@ __xfs_scrub_btree_process_error(
 	switch (*error) {
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -53,10 +53,10 @@ __xfs_scrub_btree_process_error(
 		/* fall through */
 	default:
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
-			trace_xfs_scrub_ifork_btree_op_error(sc, cur, level,
+			trace_xchk_ifork_btree_op_error(sc, cur, level,
 					*error, ret_ip);
 		else
-			trace_xfs_scrub_btree_op_error(sc, cur, level,
+			trace_xchk_btree_op_error(sc, cur, level,
 					*error, ret_ip);
 		break;
 	}
@@ -64,63 +64,63 @@ __xfs_scrub_btree_process_error(
 }
 
 bool
-xfs_scrub_btree_process_error(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	int				*error)
+xchk_btree_process_error(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*error)
 {
-	return __xfs_scrub_btree_process_error(sc, cur, level, error,
+	return __xchk_btree_process_error(sc, cur, level, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
 bool
-xfs_scrub_btree_xref_process_error(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	int				*error)
+xchk_btree_xref_process_error(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*error)
 {
-	return __xfs_scrub_btree_process_error(sc, cur, level, error,
+	return __xchk_btree_process_error(sc, cur, level, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
 }
 
 /* Record btree block corruption. */
 static void
-__xfs_scrub_btree_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	__u32				errflag,
-	void				*ret_ip)
+__xchk_btree_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	sc->sm->sm_flags |= errflag;
 
 	if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
-		trace_xfs_scrub_ifork_btree_error(sc, cur, level,
+		trace_xchk_ifork_btree_error(sc, cur, level,
 				ret_ip);
 	else
-		trace_xfs_scrub_btree_error(sc, cur, level,
+		trace_xchk_btree_error(sc, cur, level,
 				ret_ip);
 }
 
 void
-xfs_scrub_btree_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level)
+xchk_btree_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
-	__xfs_scrub_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_CORRUPT,
+	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_CORRUPT,
 			__return_address);
 }
 
 void
-xfs_scrub_btree_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level)
+xchk_btree_xref_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
-	__xfs_scrub_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_XCORRUPT,
+	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_XCORRUPT,
 			__return_address);
 }
 
@@ -129,8 +129,8 @@ xfs_scrub_btree_xref_set_corrupt(
  * keys.
  */
 STATIC void
-xfs_scrub_btree_rec(
-	struct xfs_scrub_btree	*bs)
+xchk_btree_rec(
+	struct xchk_btree	*bs)
 {
 	struct xfs_btree_cur	*cur = bs->cur;
 	union xfs_btree_rec	*rec;
@@ -144,11 +144,11 @@ xfs_scrub_btree_rec(
 	block = xfs_btree_get_block(cur, 0, &bp);
 	rec = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
 
-	trace_xfs_scrub_btree_rec(bs->sc, cur, 0);
+	trace_xchk_btree_rec(bs->sc, cur, 0);
 
 	/* If this isn't the first record, are they in order? */
 	if (!bs->firstrec && !cur->bc_ops->recs_inorder(cur, &bs->lastrec, rec))
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 0);
+		xchk_btree_set_corrupt(bs->sc, cur, 0);
 	bs->firstrec = false;
 	memcpy(&bs->lastrec, rec, cur->bc_ops->rec_len);
 
@@ -160,7 +160,7 @@ xfs_scrub_btree_rec(
 	keyblock = xfs_btree_get_block(cur, 1, &bp);
 	keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, &key, keyp) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 
 	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 		return;
@@ -169,7 +169,7 @@ xfs_scrub_btree_rec(
 	cur->bc_ops->init_high_key_from_rec(&hkey, rec);
 	keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, keyp, &hkey) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 }
 
 /*
@@ -177,8 +177,8 @@ xfs_scrub_btree_rec(
  * keys.
  */
 STATIC void
-xfs_scrub_btree_key(
-	struct xfs_scrub_btree	*bs,
+xchk_btree_key(
+	struct xchk_btree	*bs,
 	int			level)
 {
 	struct xfs_btree_cur	*cur = bs->cur;
@@ -191,12 +191,12 @@ xfs_scrub_btree_key(
 	block = xfs_btree_get_block(cur, level, &bp);
 	key = xfs_btree_key_addr(cur, cur->bc_ptrs[level], block);
 
-	trace_xfs_scrub_btree_key(bs->sc, cur, level);
+	trace_xchk_btree_key(bs->sc, cur, level);
 
 	/* If this isn't the first key, are they in order? */
 	if (!bs->firstkey[level] &&
 	    !cur->bc_ops->keys_inorder(cur, &bs->lastkey[level], key))
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 	bs->firstkey[level] = false;
 	memcpy(&bs->lastkey[level], key, cur->bc_ops->key_len);
 
@@ -207,7 +207,7 @@ xfs_scrub_btree_key(
 	keyblock = xfs_btree_get_block(cur, level + 1, &bp);
 	keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, key, keyp) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 
 	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 		return;
@@ -216,7 +216,7 @@ xfs_scrub_btree_key(
 	key = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level], block);
 	keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, keyp, key) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 }
 
 /*
@@ -224,12 +224,12 @@ xfs_scrub_btree_key(
  * Callers do not need to set the corrupt flag.
  */
 static bool
-xfs_scrub_btree_ptr_ok(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	union xfs_btree_ptr		*ptr)
+xchk_btree_ptr_ok(
+	struct xchk_btree	*bs,
+	int			level,
+	union xfs_btree_ptr	*ptr)
 {
-	bool				res;
+	bool			res;
 
 	/* A btree rooted in an inode has no block pointer to the root. */
 	if ((bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
@@ -242,29 +242,29 @@ xfs_scrub_btree_ptr_ok(
 	else
 		res = xfs_btree_check_sptr(bs->cur, be32_to_cpu(ptr->s), level);
 	if (!res)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 
 	return res;
 }
 
 /* Check that a btree block's sibling matches what we expect it. */
 STATIC int
-xfs_scrub_btree_block_check_sibling(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	int				direction,
-	union xfs_btree_ptr		*sibling)
+xchk_btree_block_check_sibling(
+	struct xchk_btree	*bs,
+	int			level,
+	int			direction,
+	union xfs_btree_ptr	*sibling)
 {
-	struct xfs_btree_cur		*cur = bs->cur;
-	struct xfs_btree_block		*pblock;
-	struct xfs_buf			*pbp;
-	struct xfs_btree_cur		*ncur = NULL;
-	union xfs_btree_ptr		*pp;
-	int				success;
-	int				error;
+	struct xfs_btree_cur	*cur = bs->cur;
+	struct xfs_btree_block	*pblock;
+	struct xfs_buf		*pbp;
+	struct xfs_btree_cur	*ncur = NULL;
+	union xfs_btree_ptr	*pp;
+	int			success;
+	int			error;
 
 	error = xfs_btree_dup_cursor(cur, &ncur);
-	if (!xfs_scrub_btree_process_error(bs->sc, cur, level + 1, &error) ||
+	if (!xchk_btree_process_error(bs->sc, cur, level + 1, &error) ||
 	    !ncur)
 		return error;
 
@@ -278,7 +278,7 @@ xfs_scrub_btree_block_check_sibling(
 		else
 			error = xfs_btree_decrement(ncur, level + 1, &success);
 		if (error == 0 && success)
-			xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+			xchk_btree_set_corrupt(bs->sc, cur, level);
 		error = 0;
 		goto out;
 	}
@@ -288,23 +288,23 @@ xfs_scrub_btree_block_check_sibling(
 		error = xfs_btree_increment(ncur, level + 1, &success);
 	else
 		error = xfs_btree_decrement(ncur, level + 1, &success);
-	if (!xfs_scrub_btree_process_error(bs->sc, cur, level + 1, &error))
+	if (!xchk_btree_process_error(bs->sc, cur, level + 1, &error))
 		goto out;
 	if (!success) {
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level + 1);
+		xchk_btree_set_corrupt(bs->sc, cur, level + 1);
 		goto out;
 	}
 
 	/* Compare upper level pointer to sibling pointer. */
 	pblock = xfs_btree_get_block(ncur, level + 1, &pbp);
 	pp = xfs_btree_ptr_addr(ncur, ncur->bc_ptrs[level + 1], pblock);
-	if (!xfs_scrub_btree_ptr_ok(bs, level + 1, pp))
+	if (!xchk_btree_ptr_ok(bs, level + 1, pp))
 		goto out;
 	if (pbp)
-		xfs_scrub_buffer_recheck(bs->sc, pbp);
+		xchk_buffer_recheck(bs->sc, pbp);
 
 	if (xfs_btree_diff_two_ptrs(cur, pp, sibling))
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 out:
 	xfs_btree_del_cursor(ncur, XFS_BTREE_ERROR);
 	return error;
@@ -312,15 +312,15 @@ out:
 
 /* Check the siblings of a btree block. */
 STATIC int
-xfs_scrub_btree_block_check_siblings(
-	struct xfs_scrub_btree		*bs,
-	struct xfs_btree_block		*block)
+xchk_btree_block_check_siblings(
+	struct xchk_btree	*bs,
+	struct xfs_btree_block	*block)
 {
-	struct xfs_btree_cur		*cur = bs->cur;
-	union xfs_btree_ptr		leftsib;
-	union xfs_btree_ptr		rightsib;
-	int				level;
-	int				error = 0;
+	struct xfs_btree_cur	*cur = bs->cur;
+	union xfs_btree_ptr	leftsib;
+	union xfs_btree_ptr	rightsib;
+	int			level;
+	int			error = 0;
 
 	xfs_btree_get_sibling(cur, block, &leftsib, XFS_BB_LEFTSIB);
 	xfs_btree_get_sibling(cur, block, &rightsib, XFS_BB_RIGHTSIB);
@@ -330,7 +330,7 @@ xfs_scrub_btree_block_check_siblings(
 	if (level == cur->bc_nlevels - 1) {
 		if (!xfs_btree_ptr_is_null(cur, &leftsib) ||
 		    !xfs_btree_ptr_is_null(cur, &rightsib))
-			xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+			xchk_btree_set_corrupt(bs->sc, cur, level);
 		goto out;
 	}
 
@@ -339,10 +339,10 @@ xfs_scrub_btree_block_check_siblings(
 	 * parent level pointers?
 	 * (These function absorbs error codes for us.)
 	 */
-	error = xfs_scrub_btree_block_check_sibling(bs, level, -1, &leftsib);
+	error = xchk_btree_block_check_sibling(bs, level, -1, &leftsib);
 	if (error)
 		return error;
-	error = xfs_scrub_btree_block_check_sibling(bs, level, 1, &rightsib);
+	error = xchk_btree_block_check_sibling(bs, level, 1, &rightsib);
 	if (error)
 		return error;
 out:
@@ -360,16 +360,16 @@ struct check_owner {
  * an rmap record for it.
  */
 STATIC int
-xfs_scrub_btree_check_block_owner(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	xfs_daddr_t			daddr)
+xchk_btree_check_block_owner(
+	struct xchk_btree	*bs,
+	int			level,
+	xfs_daddr_t		daddr)
 {
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_btnum_t			btnum;
-	bool				init_sa;
-	int				error = 0;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_btnum_t		btnum;
+	bool			init_sa;
+	int			error = 0;
 
 	if (!bs->cur)
 		return 0;
@@ -380,13 +380,13 @@ xfs_scrub_btree_check_block_owner(
 
 	init_sa = bs->cur->bc_flags & XFS_BTREE_LONG_PTRS;
 	if (init_sa) {
-		error = xfs_scrub_ag_init(bs->sc, agno, &bs->sc->sa);
-		if (!xfs_scrub_btree_xref_process_error(bs->sc, bs->cur,
+		error = xchk_ag_init(bs->sc, agno, &bs->sc->sa);
+		if (!xchk_btree_xref_process_error(bs->sc, bs->cur,
 				level, &error))
 			return error;
 	}
 
-	xfs_scrub_xref_is_used_space(bs->sc, agbno, 1);
+	xchk_xref_is_used_space(bs->sc, agbno, 1);
 	/*
 	 * The bnobt scrubber aliases bs->cur to bs->sc->sa.bno_cur, so we
 	 * have to nullify it (to shut down further block owner checks) if
@@ -395,25 +395,25 @@ xfs_scrub_btree_check_block_owner(
 	if (!bs->sc->sa.bno_cur && btnum == XFS_BTNUM_BNO)
 		bs->cur = NULL;
 
-	xfs_scrub_xref_is_owned_by(bs->sc, agbno, 1, bs->oinfo);
+	xchk_xref_is_owned_by(bs->sc, agbno, 1, bs->oinfo);
 	if (!bs->sc->sa.rmap_cur && btnum == XFS_BTNUM_RMAP)
 		bs->cur = NULL;
 
 	if (init_sa)
-		xfs_scrub_ag_free(bs->sc, &bs->sc->sa);
+		xchk_ag_free(bs->sc, &bs->sc->sa);
 
 	return error;
 }
 
 /* Check the owner of a btree block. */
 STATIC int
-xfs_scrub_btree_check_owner(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	struct xfs_buf			*bp)
+xchk_btree_check_owner(
+	struct xchk_btree	*bs,
+	int			level,
+	struct xfs_buf		*bp)
 {
-	struct xfs_btree_cur		*cur = bs->cur;
-	struct check_owner		*co;
+	struct xfs_btree_cur	*cur = bs->cur;
+	struct check_owner	*co;
 
 	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && bp == NULL)
 		return 0;
@@ -437,7 +437,7 @@ xfs_scrub_btree_check_owner(
 		return 0;
 	}
 
-	return xfs_scrub_btree_check_block_owner(bs, level, XFS_BUF_ADDR(bp));
+	return xchk_btree_check_block_owner(bs, level, XFS_BUF_ADDR(bp));
 }
 
 /*
@@ -445,8 +445,8 @@ xfs_scrub_btree_check_owner(
  * special blocks that don't require that.
  */
 STATIC void
-xfs_scrub_btree_check_minrecs(
-	struct xfs_scrub_btree	*bs,
+xchk_btree_check_minrecs(
+	struct xchk_btree	*bs,
 	int			level,
 	struct xfs_btree_block	*block)
 {
@@ -475,7 +475,7 @@ xfs_scrub_btree_check_minrecs(
 	if (level >= ok_level)
 		return;
 
-	xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+	xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 }
 
 /*
@@ -483,21 +483,21 @@ xfs_scrub_btree_check_minrecs(
  * and buffer pointers (if applicable) if they're ok to use.
  */
 STATIC int
-xfs_scrub_btree_get_block(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	union xfs_btree_ptr		*pp,
-	struct xfs_btree_block		**pblock,
-	struct xfs_buf			**pbp)
+xchk_btree_get_block(
+	struct xchk_btree	*bs,
+	int			level,
+	union xfs_btree_ptr	*pp,
+	struct xfs_btree_block	**pblock,
+	struct xfs_buf		**pbp)
 {
-	void				*failed_at;
-	int				error;
+	xfs_failaddr_t		failed_at;
+	int			error;
 
 	*pblock = NULL;
 	*pbp = NULL;
 
 	error = xfs_btree_lookup_get_block(bs->cur, level, pp, pblock);
-	if (!xfs_scrub_btree_process_error(bs->sc, bs->cur, level, &error) ||
+	if (!xchk_btree_process_error(bs->sc, bs->cur, level, &error) ||
 	    !*pblock)
 		return error;
 
@@ -509,19 +509,19 @@ xfs_scrub_btree_get_block(
 		failed_at = __xfs_btree_check_sblock(bs->cur, *pblock,
 				 level, *pbp);
 	if (failed_at) {
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 		return 0;
 	}
 	if (*pbp)
-		xfs_scrub_buffer_recheck(bs->sc, *pbp);
+		xchk_buffer_recheck(bs->sc, *pbp);
 
-	xfs_scrub_btree_check_minrecs(bs, level, *pblock);
+	xchk_btree_check_minrecs(bs, level, *pblock);
 
 	/*
 	 * Check the block's owner; this function absorbs error codes
 	 * for us.
 	 */
-	error = xfs_scrub_btree_check_owner(bs, level, *pbp);
+	error = xchk_btree_check_owner(bs, level, *pbp);
 	if (error)
 		return error;
 
@@ -529,7 +529,7 @@ xfs_scrub_btree_get_block(
 	 * Check the block's siblings; this function absorbs error codes
 	 * for us.
 	 */
-	return xfs_scrub_btree_block_check_siblings(bs, *pblock);
+	return xchk_btree_block_check_siblings(bs, *pblock);
 }
 
 /*
@@ -537,18 +537,18 @@ xfs_scrub_btree_get_block(
  * in the parent block.
  */
 STATIC void
-xfs_scrub_btree_block_keys(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	struct xfs_btree_block		*block)
+xchk_btree_block_keys(
+	struct xchk_btree	*bs,
+	int			level,
+	struct xfs_btree_block	*block)
 {
-	union xfs_btree_key		block_keys;
-	struct xfs_btree_cur		*cur = bs->cur;
-	union xfs_btree_key		*high_bk;
-	union xfs_btree_key		*parent_keys;
-	union xfs_btree_key		*high_pk;
-	struct xfs_btree_block		*parent_block;
-	struct xfs_buf			*bp;
+	union xfs_btree_key	block_keys;
+	struct xfs_btree_cur	*cur = bs->cur;
+	union xfs_btree_key	*high_bk;
+	union xfs_btree_key	*parent_keys;
+	union xfs_btree_key	*high_pk;
+	struct xfs_btree_block	*parent_block;
+	struct xfs_buf		*bp;
 
 	if (level >= cur->bc_nlevels - 1)
 		return;
@@ -562,7 +562,7 @@ xfs_scrub_btree_block_keys(
 			parent_block);
 
 	if (cur->bc_ops->diff_two_keys(cur, &block_keys, parent_keys) != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 
 	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 		return;
@@ -573,7 +573,7 @@ xfs_scrub_btree_block_keys(
 			parent_block);
 
 	if (cur->bc_ops->diff_two_keys(cur, high_bk, high_pk) != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 }
 
 /*
@@ -582,24 +582,24 @@ xfs_scrub_btree_block_keys(
  * so that the caller can verify individual records.
  */
 int
-xfs_scrub_btree(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	xfs_scrub_btree_rec_fn		scrub_fn,
-	struct xfs_owner_info		*oinfo,
-	void				*private)
+xchk_btree(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	xchk_btree_rec_fn	scrub_fn,
+	struct xfs_owner_info	*oinfo,
+	void			*private)
 {
-	struct xfs_scrub_btree		bs = { NULL };
-	union xfs_btree_ptr		ptr;
-	union xfs_btree_ptr		*pp;
-	union xfs_btree_rec		*recp;
-	struct xfs_btree_block		*block;
-	int				level;
-	struct xfs_buf			*bp;
-	struct check_owner		*co;
-	struct check_owner		*n;
-	int				i;
-	int				error = 0;
+	struct xchk_btree	bs = { NULL };
+	union xfs_btree_ptr	ptr;
+	union xfs_btree_ptr	*pp;
+	union xfs_btree_rec	*recp;
+	struct xfs_btree_block	*block;
+	int			level;
+	struct xfs_buf		*bp;
+	struct check_owner	*co;
+	struct check_owner	*n;
+	int			i;
+	int			error = 0;
 
 	/* Initialize scrub state */
 	bs.cur = cur;
@@ -614,7 +614,7 @@ xfs_scrub_btree(
 
 	/* Don't try to check a tree with a height we can't handle. */
 	if (cur->bc_nlevels > XFS_BTREE_MAXLEVELS) {
-		xfs_scrub_btree_set_corrupt(sc, cur, 0);
+		xchk_btree_set_corrupt(sc, cur, 0);
 		goto out;
 	}
 
@@ -624,9 +624,9 @@ xfs_scrub_btree(
 	 */
 	level = cur->bc_nlevels - 1;
 	cur->bc_ops->init_ptr_from_cur(cur, &ptr);
-	if (!xfs_scrub_btree_ptr_ok(&bs, cur->bc_nlevels, &ptr))
+	if (!xchk_btree_ptr_ok(&bs, cur->bc_nlevels, &ptr))
 		goto out;
-	error = xfs_scrub_btree_get_block(&bs, level, &ptr, &block, &bp);
+	error = xchk_btree_get_block(&bs, level, &ptr, &block, &bp);
 	if (error || !block)
 		goto out;
 
@@ -639,7 +639,7 @@ xfs_scrub_btree(
 			/* End of leaf, pop back towards the root. */
 			if (cur->bc_ptrs[level] >
 			    be16_to_cpu(block->bb_numrecs)) {
-				xfs_scrub_btree_block_keys(&bs, level, block);
+				xchk_btree_block_keys(&bs, level, block);
 				if (level < cur->bc_nlevels - 1)
 					cur->bc_ptrs[level + 1]++;
 				level++;
@@ -647,14 +647,14 @@ xfs_scrub_btree(
 			}
 
 			/* Records in order for scrub? */
-			xfs_scrub_btree_rec(&bs);
+			xchk_btree_rec(&bs);
 
 			/* Call out to the record checker. */
 			recp = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
 			error = bs.scrub_rec(&bs, recp);
 			if (error)
 				break;
-			if (xfs_scrub_should_terminate(sc, &error) ||
+			if (xchk_should_terminate(sc, &error) ||
 			    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 				break;
 
@@ -664,7 +664,7 @@ xfs_scrub_btree(
 
 		/* End of node, pop back towards the root. */
 		if (cur->bc_ptrs[level] > be16_to_cpu(block->bb_numrecs)) {
-			xfs_scrub_btree_block_keys(&bs, level, block);
+			xchk_btree_block_keys(&bs, level, block);
 			if (level < cur->bc_nlevels - 1)
 				cur->bc_ptrs[level + 1]++;
 			level++;
@@ -672,16 +672,16 @@ xfs_scrub_btree(
 		}
 
 		/* Keys in order for scrub? */
-		xfs_scrub_btree_key(&bs, level);
+		xchk_btree_key(&bs, level);
 
 		/* Drill another level deeper. */
 		pp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[level], block);
-		if (!xfs_scrub_btree_ptr_ok(&bs, level, pp)) {
+		if (!xchk_btree_ptr_ok(&bs, level, pp)) {
 			cur->bc_ptrs[level]++;
 			continue;
 		}
 		level--;
-		error = xfs_scrub_btree_get_block(&bs, level, pp, &block, &bp);
+		error = xchk_btree_get_block(&bs, level, pp, &block, &bp);
 		if (error || !block)
 			goto out;
 
@@ -692,7 +692,7 @@ out:
 	/* Process deferred owner checks on btree blocks. */
 	list_for_each_entry_safe(co, n, &bs.to_check, list) {
 		if (!error && bs.cur)
-			error = xfs_scrub_btree_check_block_owner(&bs,
+			error = xchk_btree_check_block_owner(&bs,
 					co->level, co->daddr);
 		list_del(&co->list);
 		kmem_free(co);
diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h
index 956627500f2c..aada763cd006 100644
--- a/fs/xfs/scrub/btree.h
+++ b/fs/xfs/scrub/btree.h
@@ -9,44 +9,43 @@
 /* btree scrub */
 
 /* Check for btree operation errors. */
-bool xfs_scrub_btree_process_error(struct xfs_scrub_context *sc,
+bool xchk_btree_process_error(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level, int *error);
 
 /* Check for btree xref operation errors. */
-bool xfs_scrub_btree_xref_process_error(struct xfs_scrub_context *sc,
-				struct xfs_btree_cur *cur, int level,
-				int *error);
+bool xchk_btree_xref_process_error(struct xfs_scrub *sc,
+		struct xfs_btree_cur *cur, int level, int *error);
 
 /* Check for btree corruption. */
-void xfs_scrub_btree_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_btree_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level);
 
 /* Check for btree xref discrepancies. */
-void xfs_scrub_btree_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_btree_xref_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level);
 
-struct xfs_scrub_btree;
-typedef int (*xfs_scrub_btree_rec_fn)(
-	struct xfs_scrub_btree	*bs,
+struct xchk_btree;
+typedef int (*xchk_btree_rec_fn)(
+	struct xchk_btree	*bs,
 	union xfs_btree_rec	*rec);
 
-struct xfs_scrub_btree {
+struct xchk_btree {
 	/* caller-provided scrub state */
-	struct xfs_scrub_context	*sc;
-	struct xfs_btree_cur		*cur;
-	xfs_scrub_btree_rec_fn		scrub_rec;
-	struct xfs_owner_info		*oinfo;
-	void				*private;
+	struct xfs_scrub	*sc;
+	struct xfs_btree_cur	*cur;
+	xchk_btree_rec_fn	scrub_rec;
+	struct xfs_owner_info	*oinfo;
+	void			*private;
 
 	/* internal scrub state */
-	union xfs_btree_rec		lastrec;
-	bool				firstrec;
-	union xfs_btree_key		lastkey[XFS_BTREE_MAXLEVELS];
-	bool				firstkey[XFS_BTREE_MAXLEVELS];
-	struct list_head		to_check;
+	union xfs_btree_rec	lastrec;
+	bool			firstrec;
+	union xfs_btree_key	lastkey[XFS_BTREE_MAXLEVELS];
+	bool			firstkey[XFS_BTREE_MAXLEVELS];
+	struct list_head	to_check;
 };
-int xfs_scrub_btree(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
-		    xfs_scrub_btree_rec_fn scrub_fn,
-		    struct xfs_owner_info *oinfo, void *private);
+int xchk_btree(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
+		xchk_btree_rec_fn scrub_fn, struct xfs_owner_info *oinfo,
+		void *private);
 
 #endif /* __XFS_SCRUB_BTREE_H__ */
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 70e70c69f83f..346b02abccf7 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -68,20 +68,20 @@
 
 /* Check for operational errors. */
 static bool
-__xfs_scrub_process_error(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	xfs_agblock_t			bno,
-	int				*error,
-	__u32				errflag,
-	void				*ret_ip)
+__xchk_process_error(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	int			*error,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	switch (*error) {
 	case 0:
 		return true;
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -90,7 +90,7 @@ __xfs_scrub_process_error(
 		*error = 0;
 		/* fall through */
 	default:
-		trace_xfs_scrub_op_error(sc, agno, bno, *error,
+		trace_xchk_op_error(sc, agno, bno, *error,
 				ret_ip);
 		break;
 	}
@@ -98,43 +98,43 @@ __xfs_scrub_process_error(
 }
 
 bool
-xfs_scrub_process_error(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	xfs_agblock_t			bno,
-	int				*error)
+xchk_process_error(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	int			*error)
 {
-	return __xfs_scrub_process_error(sc, agno, bno, error,
+	return __xchk_process_error(sc, agno, bno, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
 bool
-xfs_scrub_xref_process_error(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	xfs_agblock_t			bno,
-	int				*error)
+xchk_xref_process_error(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	int			*error)
 {
-	return __xfs_scrub_process_error(sc, agno, bno, error,
+	return __xchk_process_error(sc, agno, bno, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
 }
 
 /* Check for operational errors for a file offset. */
 static bool
-__xfs_scrub_fblock_process_error(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset,
-	int				*error,
-	__u32				errflag,
-	void				*ret_ip)
+__xchk_fblock_process_error(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset,
+	int			*error,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	switch (*error) {
 	case 0:
 		return true;
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -143,7 +143,7 @@ __xfs_scrub_fblock_process_error(
 		*error = 0;
 		/* fall through */
 	default:
-		trace_xfs_scrub_file_op_error(sc, whichfork, offset, *error,
+		trace_xchk_file_op_error(sc, whichfork, offset, *error,
 				ret_ip);
 		break;
 	}
@@ -151,24 +151,24 @@ __xfs_scrub_fblock_process_error(
 }
 
 bool
-xfs_scrub_fblock_process_error(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset,
-	int				*error)
+xchk_fblock_process_error(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset,
+	int			*error)
 {
-	return __xfs_scrub_fblock_process_error(sc, whichfork, offset, error,
+	return __xchk_fblock_process_error(sc, whichfork, offset, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
 bool
-xfs_scrub_fblock_xref_process_error(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset,
-	int				*error)
+xchk_fblock_xref_process_error(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset,
+	int			*error)
 {
-	return __xfs_scrub_fblock_process_error(sc, whichfork, offset, error,
+	return __xchk_fblock_process_error(sc, whichfork, offset, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
 }
 
@@ -186,12 +186,12 @@ xfs_scrub_fblock_xref_process_error(
 
 /* Record a block which could be optimized. */
 void
-xfs_scrub_block_set_preen(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_block_set_preen(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
-	trace_xfs_scrub_block_preen(sc, bp->b_bn, __return_address);
+	trace_xchk_block_preen(sc, bp->b_bn, __return_address);
 }
 
 /*
@@ -200,32 +200,32 @@ xfs_scrub_block_set_preen(
  * the block location of the inode record itself.
  */
 void
-xfs_scrub_ino_set_preen(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_ino_set_preen(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
-	trace_xfs_scrub_ino_preen(sc, ino, __return_address);
+	trace_xchk_ino_preen(sc, ino, __return_address);
 }
 
 /* Record a corrupt block. */
 void
-xfs_scrub_block_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_block_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_block_error(sc, bp->b_bn, __return_address);
+	trace_xchk_block_error(sc, bp->b_bn, __return_address);
 }
 
 /* Record a corruption while cross-referencing. */
 void
-xfs_scrub_block_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_block_xref_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
-	trace_xfs_scrub_block_error(sc, bp->b_bn, __return_address);
+	trace_xchk_block_error(sc, bp->b_bn, __return_address);
 }
 
 /*
@@ -234,44 +234,44 @@ xfs_scrub_block_xref_set_corrupt(
  * inode record itself.
  */
 void
-xfs_scrub_ino_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_ino_set_corrupt(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_ino_error(sc, ino, __return_address);
+	trace_xchk_ino_error(sc, ino, __return_address);
 }
 
 /* Record a corruption while cross-referencing with an inode. */
 void
-xfs_scrub_ino_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_ino_xref_set_corrupt(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
-	trace_xfs_scrub_ino_error(sc, ino, __return_address);
+	trace_xchk_ino_error(sc, ino, __return_address);
 }
 
 /* Record corruption in a block indexed by a file fork. */
 void
-xfs_scrub_fblock_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset)
+xchk_fblock_set_corrupt(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_fblock_error(sc, whichfork, offset, __return_address);
+	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
 }
 
 /* Record a corruption while cross-referencing a fork block. */
 void
-xfs_scrub_fblock_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset)
+xchk_fblock_xref_set_corrupt(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
-	trace_xfs_scrub_fblock_error(sc, whichfork, offset, __return_address);
+	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
 }
 
 /*
@@ -279,32 +279,32 @@ xfs_scrub_fblock_xref_set_corrupt(
  * incorrect.
  */
 void
-xfs_scrub_ino_set_warning(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_ino_set_warning(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
-	trace_xfs_scrub_ino_warning(sc, ino, __return_address);
+	trace_xchk_ino_warning(sc, ino, __return_address);
 }
 
 /* Warn about a block indexed by a file fork that needs review. */
 void
-xfs_scrub_fblock_set_warning(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset)
+xchk_fblock_set_warning(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
-	trace_xfs_scrub_fblock_warning(sc, whichfork, offset, __return_address);
+	trace_xchk_fblock_warning(sc, whichfork, offset, __return_address);
 }
 
 /* Signal an incomplete scrub. */
 void
-xfs_scrub_set_incomplete(
-	struct xfs_scrub_context	*sc)
+xchk_set_incomplete(
+	struct xfs_scrub	*sc)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_INCOMPLETE;
-	trace_xfs_scrub_incomplete(sc, __return_address);
+	trace_xchk_incomplete(sc, __return_address);
 }
 
 /*
@@ -312,20 +312,20 @@ xfs_scrub_set_incomplete(
  * at least according to the reverse mapping data.
  */
 
-struct xfs_scrub_rmap_ownedby_info {
+struct xchk_rmap_ownedby_info {
 	struct xfs_owner_info	*oinfo;
 	xfs_filblks_t		*blocks;
 };
 
 STATIC int
-xfs_scrub_count_rmap_ownedby_irec(
-	struct xfs_btree_cur			*cur,
-	struct xfs_rmap_irec			*rec,
-	void					*priv)
+xchk_count_rmap_ownedby_irec(
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*priv)
 {
-	struct xfs_scrub_rmap_ownedby_info	*sroi = priv;
-	bool					irec_attr;
-	bool					oinfo_attr;
+	struct xchk_rmap_ownedby_info	*sroi = priv;
+	bool				irec_attr;
+	bool				oinfo_attr;
 
 	irec_attr = rec->rm_flags & XFS_RMAP_ATTR_FORK;
 	oinfo_attr = sroi->oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK;
@@ -344,19 +344,19 @@ xfs_scrub_count_rmap_ownedby_irec(
  * The caller should pass us an rmapbt cursor.
  */
 int
-xfs_scrub_count_rmap_ownedby_ag(
-	struct xfs_scrub_context		*sc,
-	struct xfs_btree_cur			*cur,
-	struct xfs_owner_info			*oinfo,
-	xfs_filblks_t				*blocks)
+xchk_count_rmap_ownedby_ag(
+	struct xfs_scrub		*sc,
+	struct xfs_btree_cur		*cur,
+	struct xfs_owner_info		*oinfo,
+	xfs_filblks_t			*blocks)
 {
-	struct xfs_scrub_rmap_ownedby_info	sroi;
+	struct xchk_rmap_ownedby_info	sroi;
 
 	sroi.oinfo = oinfo;
 	*blocks = 0;
 	sroi.blocks = blocks;
 
-	return xfs_rmap_query_all(cur, xfs_scrub_count_rmap_ownedby_irec,
+	return xfs_rmap_query_all(cur, xchk_count_rmap_ownedby_irec,
 			&sroi);
 }
 
@@ -371,8 +371,8 @@ xfs_scrub_count_rmap_ownedby_ag(
 /* Decide if we want to return an AG header read failure. */
 static inline bool
 want_ag_read_header_failure(
-	struct xfs_scrub_context	*sc,
-	unsigned int			type)
+	struct xfs_scrub	*sc,
+	unsigned int		type)
 {
 	/* Return all AG header read failures when scanning btrees. */
 	if (sc->sm->sm_type != XFS_SCRUB_TYPE_AGF &&
@@ -392,20 +392,20 @@ want_ag_read_header_failure(
 /*
  * Grab all the headers for an AG.
  *
- * The headers should be released by xfs_scrub_ag_free, but as a fail
+ * The headers should be released by xchk_ag_free, but as a fail
  * safe we attach all the buffers we grab to the scrub transaction so
  * they'll all be freed when we cancel it.
  */
 int
-xfs_scrub_ag_read_headers(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	struct xfs_buf			**agi,
-	struct xfs_buf			**agf,
-	struct xfs_buf			**agfl)
-{
-	struct xfs_mount		*mp = sc->mp;
-	int				error;
+xchk_ag_read_headers(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	struct xfs_buf		**agi,
+	struct xfs_buf		**agf,
+	struct xfs_buf		**agfl)
+{
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
 
 	error = xfs_ialloc_read_agi(mp, sc->tp, agno, agi);
 	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
@@ -425,8 +425,8 @@ out:
 
 /* Release all the AG btree cursors. */
 void
-xfs_scrub_ag_btcur_free(
-	struct xfs_scrub_ag		*sa)
+xchk_ag_btcur_free(
+	struct xchk_ag		*sa)
 {
 	if (sa->refc_cur)
 		xfs_btree_del_cursor(sa->refc_cur, XFS_BTREE_ERROR);
@@ -451,12 +451,12 @@ xfs_scrub_ag_btcur_free(
 
 /* Initialize all the btree cursors for an AG. */
 int
-xfs_scrub_ag_btcur_init(
-	struct xfs_scrub_context	*sc,
-	struct xfs_scrub_ag		*sa)
+xchk_ag_btcur_init(
+	struct xfs_scrub	*sc,
+	struct xchk_ag		*sa)
 {
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agnumber_t			agno = sa->agno;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agnumber_t		agno = sa->agno;
 
 	if (sa->agf_bp) {
 		/* Set up a bnobt cursor for cross-referencing. */
@@ -499,7 +499,7 @@ xfs_scrub_ag_btcur_init(
 	/* Set up a refcountbt cursor for cross-referencing. */
 	if (sa->agf_bp && xfs_sb_version_hasreflink(&mp->m_sb)) {
 		sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp,
-				sa->agf_bp, agno, NULL);
+				sa->agf_bp, agno);
 		if (!sa->refc_cur)
 			goto err;
 	}
@@ -511,11 +511,11 @@ err:
 
 /* Release the AG header context and btree cursors. */
 void
-xfs_scrub_ag_free(
-	struct xfs_scrub_context	*sc,
-	struct xfs_scrub_ag		*sa)
+xchk_ag_free(
+	struct xfs_scrub	*sc,
+	struct xchk_ag		*sa)
 {
-	xfs_scrub_ag_btcur_free(sa);
+	xchk_ag_btcur_free(sa);
 	if (sa->agfl_bp) {
 		xfs_trans_brelse(sc->tp, sa->agfl_bp);
 		sa->agfl_bp = NULL;
@@ -543,30 +543,30 @@ xfs_scrub_ag_free(
  * transaction ourselves.
  */
 int
-xfs_scrub_ag_init(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	struct xfs_scrub_ag		*sa)
+xchk_ag_init(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	struct xchk_ag		*sa)
 {
-	int				error;
+	int			error;
 
 	sa->agno = agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sa->agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sa->agi_bp,
 			&sa->agf_bp, &sa->agfl_bp);
 	if (error)
 		return error;
 
-	return xfs_scrub_ag_btcur_init(sc, sa);
+	return xchk_ag_btcur_init(sc, sa);
 }
 
 /*
  * Grab the per-ag structure if we haven't already gotten it.  Teardown of the
- * xfs_scrub_ag will release it for us.
+ * xchk_ag will release it for us.
  */
 void
-xfs_scrub_perag_get(
+xchk_perag_get(
 	struct xfs_mount	*mp,
-	struct xfs_scrub_ag	*sa)
+	struct xchk_ag		*sa)
 {
 	if (!sa->pag)
 		sa->pag = xfs_perag_get(mp, sa->agno);
@@ -585,9 +585,9 @@ xfs_scrub_perag_get(
  * the metadata object.
  */
 int
-xfs_scrub_trans_alloc(
-	struct xfs_scrub_context	*sc,
-	uint				resblks)
+xchk_trans_alloc(
+	struct xfs_scrub	*sc,
+	uint			resblks)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
 		return xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
@@ -598,25 +598,25 @@ xfs_scrub_trans_alloc(
 
 /* Set us up with a transaction and an empty context. */
 int
-xfs_scrub_setup_fs(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_fs(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	uint				resblks;
+	uint			resblks;
 
-	resblks = xfs_repair_calc_ag_resblks(sc);
-	return xfs_scrub_trans_alloc(sc, resblks);
+	resblks = xrep_calc_ag_resblks(sc);
+	return xchk_trans_alloc(sc, resblks);
 }
 
 /* Set us up with AG headers and btree cursors. */
 int
-xfs_scrub_setup_ag_btree(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip,
-	bool				force_log)
+xchk_setup_ag_btree(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	bool			force_log)
 {
-	struct xfs_mount		*mp = sc->mp;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
 
 	/*
 	 * If the caller asks us to checkpont the log, do so.  This
@@ -625,21 +625,21 @@ xfs_scrub_setup_ag_btree(
 	 * document why they need to do so.
 	 */
 	if (force_log) {
-		error = xfs_scrub_checkpoint_log(mp);
+		error = xchk_checkpoint_log(mp);
 		if (error)
 			return error;
 	}
 
-	error = xfs_scrub_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc, ip);
 	if (error)
 		return error;
 
-	return xfs_scrub_ag_init(sc, sc->sm->sm_agno, &sc->sa);
+	return xchk_ag_init(sc, sc->sm->sm_agno, &sc->sa);
 }
 
 /* Push everything out of the log onto disk. */
 int
-xfs_scrub_checkpoint_log(
+xchk_checkpoint_log(
 	struct xfs_mount	*mp)
 {
 	int			error;
@@ -657,14 +657,14 @@ xfs_scrub_checkpoint_log(
  * The inode is not locked.
  */
 int
-xfs_scrub_get_inode(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip_in)
+xchk_get_inode(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip_in)
 {
-	struct xfs_imap			imap;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip = NULL;
-	int				error;
+	struct xfs_imap		imap;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = NULL;
+	int			error;
 
 	/* We want to scan the inode we already had opened. */
 	if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino) {
@@ -704,14 +704,14 @@ xfs_scrub_get_inode(
 		error = -EFSCORRUPTED;
 		/* fall through */
 	default:
-		trace_xfs_scrub_op_error(sc,
+		trace_xchk_op_error(sc,
 				XFS_INO_TO_AGNO(mp, sc->sm->sm_ino),
 				XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino),
 				error, __return_address);
 		return error;
 	}
 	if (VFS_I(ip)->i_generation != sc->sm->sm_gen) {
-		iput(VFS_I(ip));
+		xfs_irele(ip);
 		return -ENOENT;
 	}
 
@@ -721,21 +721,21 @@ xfs_scrub_get_inode(
 
 /* Set us up to scrub a file's contents. */
 int
-xfs_scrub_setup_inode_contents(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip,
-	unsigned int			resblks)
+xchk_setup_inode_contents(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	unsigned int		resblks)
 {
-	int				error;
+	int			error;
 
-	error = xfs_scrub_get_inode(sc, ip);
+	error = xchk_get_inode(sc, ip);
 	if (error)
 		return error;
 
 	/* Got the inode, lock it and we're ready to go. */
 	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	error = xfs_scrub_trans_alloc(sc, resblks);
+	error = xchk_trans_alloc(sc, resblks);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -752,13 +752,13 @@ out:
  * the cursor and skip the check.
  */
 bool
-xfs_scrub_should_check_xref(
-	struct xfs_scrub_context	*sc,
-	int				*error,
-	struct xfs_btree_cur		**curpp)
+xchk_should_check_xref(
+	struct xfs_scrub	*sc,
+	int			*error,
+	struct xfs_btree_cur	**curpp)
 {
 	/* No point in xref if we already know we're corrupt. */
-	if (xfs_scrub_skip_xref(sc->sm))
+	if (xchk_skip_xref(sc->sm))
 		return false;
 
 	if (*error == 0)
@@ -775,7 +775,7 @@ xfs_scrub_should_check_xref(
 	}
 
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XFAIL;
-	trace_xfs_scrub_xref_error(sc, *error, __return_address);
+	trace_xchk_xref_error(sc, *error, __return_address);
 
 	/*
 	 * Errors encountered during cross-referencing with another
@@ -787,25 +787,25 @@ xfs_scrub_should_check_xref(
 
 /* Run the structure verifiers on in-memory buffers to detect bad memory. */
 void
-xfs_scrub_buffer_recheck(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_buffer_recheck(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
-	xfs_failaddr_t			fa;
+	xfs_failaddr_t		fa;
 
 	if (bp->b_ops == NULL) {
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 		return;
 	}
 	if (bp->b_ops->verify_struct == NULL) {
-		xfs_scrub_set_incomplete(sc);
+		xchk_set_incomplete(sc);
 		return;
 	}
 	fa = bp->b_ops->verify_struct(bp);
 	if (!fa)
 		return;
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_block_error(sc, bp->b_bn, fa);
+	trace_xchk_block_error(sc, bp->b_bn, fa);
 }
 
 /*
@@ -813,38 +813,38 @@ xfs_scrub_buffer_recheck(
  * pointed to by sc->ip and the ILOCK must be held.
  */
 int
-xfs_scrub_metadata_inode_forks(
-	struct xfs_scrub_context	*sc)
+xchk_metadata_inode_forks(
+	struct xfs_scrub	*sc)
 {
-	__u32				smtype;
-	bool				shared;
-	int				error;
+	__u32			smtype;
+	bool			shared;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return 0;
 
 	/* Metadata inodes don't live on the rt device. */
 	if (sc->ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
 
 	/* They should never participate in reflink. */
 	if (xfs_is_reflink_inode(sc->ip)) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
 
 	/* They also should never have extended attributes. */
 	if (xfs_inode_hasattr(sc->ip)) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
 
 	/* Invoke the data fork scrubber. */
 	smtype = sc->sm->sm_type;
 	sc->sm->sm_type = XFS_SCRUB_TYPE_BMBTD;
-	error = xfs_scrub_bmap_data(sc);
+	error = xchk_bmap_data(sc);
 	sc->sm->sm_type = smtype;
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
@@ -853,11 +853,11 @@ xfs_scrub_metadata_inode_forks(
 	if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
 		error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
 				&shared);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0,
 				&error))
 			return error;
 		if (shared)
-			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 	}
 
 	return error;
@@ -871,7 +871,7 @@ xfs_scrub_metadata_inode_forks(
  * we can't.
  */
 int
-xfs_scrub_ilock_inverted(
+xchk_ilock_inverted(
 	struct xfs_inode	*ip,
 	uint			lock_mode)
 {
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 2172bd5361e2..2d4324d12f9a 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -12,8 +12,8 @@
  * Note that we're careful not to make any judgements about *error.
  */
 static inline bool
-xfs_scrub_should_terminate(
-	struct xfs_scrub_context	*sc,
+xchk_should_terminate(
+	struct xfs_scrub	*sc,
 	int				*error)
 {
 	if (fatal_signal_pending(current)) {
@@ -24,121 +24,118 @@ xfs_scrub_should_terminate(
 	return false;
 }
 
-int xfs_scrub_trans_alloc(struct xfs_scrub_context *sc, uint resblks);
-bool xfs_scrub_process_error(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+int xchk_trans_alloc(struct xfs_scrub *sc, uint resblks);
+bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		xfs_agblock_t bno, int *error);
-bool xfs_scrub_fblock_process_error(struct xfs_scrub_context *sc, int whichfork,
+bool xchk_fblock_process_error(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset, int *error);
 
-bool xfs_scrub_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_xref_process_error(struct xfs_scrub *sc,
 		xfs_agnumber_t agno, xfs_agblock_t bno, int *error);
-bool xfs_scrub_fblock_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_fblock_xref_process_error(struct xfs_scrub *sc,
 		int whichfork, xfs_fileoff_t offset, int *error);
 
-void xfs_scrub_block_set_preen(struct xfs_scrub_context *sc,
+void xchk_block_set_preen(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
-void xfs_scrub_ino_set_preen(struct xfs_scrub_context *sc, xfs_ino_t ino);
+void xchk_ino_set_preen(struct xfs_scrub *sc, xfs_ino_t ino);
 
-void xfs_scrub_block_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_block_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
-void xfs_scrub_ino_set_corrupt(struct xfs_scrub_context *sc, xfs_ino_t ino);
-void xfs_scrub_fblock_set_corrupt(struct xfs_scrub_context *sc, int whichfork,
+void xchk_ino_set_corrupt(struct xfs_scrub *sc, xfs_ino_t ino);
+void xchk_fblock_set_corrupt(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset);
 
-void xfs_scrub_block_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_block_xref_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
-void xfs_scrub_ino_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_ino_xref_set_corrupt(struct xfs_scrub *sc,
 		xfs_ino_t ino);
-void xfs_scrub_fblock_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_fblock_xref_set_corrupt(struct xfs_scrub *sc,
 		int whichfork, xfs_fileoff_t offset);
 
-void xfs_scrub_ino_set_warning(struct xfs_scrub_context *sc, xfs_ino_t ino);
-void xfs_scrub_fblock_set_warning(struct xfs_scrub_context *sc, int whichfork,
+void xchk_ino_set_warning(struct xfs_scrub *sc, xfs_ino_t ino);
+void xchk_fblock_set_warning(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset);
 
-void xfs_scrub_set_incomplete(struct xfs_scrub_context *sc);
-int xfs_scrub_checkpoint_log(struct xfs_mount *mp);
+void xchk_set_incomplete(struct xfs_scrub *sc);
+int xchk_checkpoint_log(struct xfs_mount *mp);
 
 /* Are we set up for a cross-referencing check? */
-bool xfs_scrub_should_check_xref(struct xfs_scrub_context *sc, int *error,
+bool xchk_should_check_xref(struct xfs_scrub *sc, int *error,
 			   struct xfs_btree_cur **curpp);
 
 /* Setup functions */
-int xfs_scrub_setup_fs(struct xfs_scrub_context *sc, struct xfs_inode *ip);
-int xfs_scrub_setup_ag_allocbt(struct xfs_scrub_context *sc,
+int xchk_setup_fs(struct xfs_scrub *sc, struct xfs_inode *ip);
+int xchk_setup_ag_allocbt(struct xfs_scrub *sc,
 			       struct xfs_inode *ip);
-int xfs_scrub_setup_ag_iallocbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_iallocbt(struct xfs_scrub *sc,
 				struct xfs_inode *ip);
-int xfs_scrub_setup_ag_rmapbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_rmapbt(struct xfs_scrub *sc,
 			      struct xfs_inode *ip);
-int xfs_scrub_setup_ag_refcountbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_refcountbt(struct xfs_scrub *sc,
 				  struct xfs_inode *ip);
-int xfs_scrub_setup_inode(struct xfs_scrub_context *sc,
+int xchk_setup_inode(struct xfs_scrub *sc,
 			  struct xfs_inode *ip);
-int xfs_scrub_setup_inode_bmap(struct xfs_scrub_context *sc,
+int xchk_setup_inode_bmap(struct xfs_scrub *sc,
 			       struct xfs_inode *ip);
-int xfs_scrub_setup_inode_bmap_data(struct xfs_scrub_context *sc,
+int xchk_setup_inode_bmap_data(struct xfs_scrub *sc,
 				    struct xfs_inode *ip);
-int xfs_scrub_setup_directory(struct xfs_scrub_context *sc,
+int xchk_setup_directory(struct xfs_scrub *sc,
 			      struct xfs_inode *ip);
-int xfs_scrub_setup_xattr(struct xfs_scrub_context *sc,
+int xchk_setup_xattr(struct xfs_scrub *sc,
 			  struct xfs_inode *ip);
-int xfs_scrub_setup_symlink(struct xfs_scrub_context *sc,
+int xchk_setup_symlink(struct xfs_scrub *sc,
 			    struct xfs_inode *ip);
-int xfs_scrub_setup_parent(struct xfs_scrub_context *sc,
+int xchk_setup_parent(struct xfs_scrub *sc,
 			   struct xfs_inode *ip);
 #ifdef CONFIG_XFS_RT
-int xfs_scrub_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip);
 #else
 static inline int
-xfs_scrub_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip)
+xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip)
 {
 	return -ENOENT;
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
-int xfs_scrub_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip);
 #else
 static inline int
-xfs_scrub_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip)
+xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip)
 {
 	return -ENOENT;
 }
 #endif
 
-void xfs_scrub_ag_free(struct xfs_scrub_context *sc, struct xfs_scrub_ag *sa);
-int xfs_scrub_ag_init(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
-		      struct xfs_scrub_ag *sa);
-void xfs_scrub_perag_get(struct xfs_mount *mp, struct xfs_scrub_ag *sa);
-int xfs_scrub_ag_read_headers(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
-			      struct xfs_buf **agi, struct xfs_buf **agf,
-			      struct xfs_buf **agfl);
-void xfs_scrub_ag_btcur_free(struct xfs_scrub_ag *sa);
-int xfs_scrub_ag_btcur_init(struct xfs_scrub_context *sc,
-			    struct xfs_scrub_ag *sa);
-int xfs_scrub_count_rmap_ownedby_ag(struct xfs_scrub_context *sc,
-				    struct xfs_btree_cur *cur,
-				    struct xfs_owner_info *oinfo,
-				    xfs_filblks_t *blocks);
+void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
+int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,
+		struct xchk_ag *sa);
+void xchk_perag_get(struct xfs_mount *mp, struct xchk_ag *sa);
+int xchk_ag_read_headers(struct xfs_scrub *sc, xfs_agnumber_t agno,
+		struct xfs_buf **agi, struct xfs_buf **agf,
+		struct xfs_buf **agfl);
+void xchk_ag_btcur_free(struct xchk_ag *sa);
+int xchk_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
+int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
+		struct xfs_owner_info *oinfo, xfs_filblks_t *blocks);
 
-int xfs_scrub_setup_ag_btree(struct xfs_scrub_context *sc,
-			     struct xfs_inode *ip, bool force_log);
-int xfs_scrub_get_inode(struct xfs_scrub_context *sc, struct xfs_inode *ip_in);
-int xfs_scrub_setup_inode_contents(struct xfs_scrub_context *sc,
-				   struct xfs_inode *ip, unsigned int resblks);
-void xfs_scrub_buffer_recheck(struct xfs_scrub_context *sc, struct xfs_buf *bp);
+int xchk_setup_ag_btree(struct xfs_scrub *sc, struct xfs_inode *ip,
+		bool force_log);
+int xchk_get_inode(struct xfs_scrub *sc, struct xfs_inode *ip_in);
+int xchk_setup_inode_contents(struct xfs_scrub *sc, struct xfs_inode *ip,
+		unsigned int resblks);
+void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
 
 /*
  * Don't bother cross-referencing if we already found corruption or cross
  * referencing discrepancies.
  */
-static inline bool xfs_scrub_skip_xref(struct xfs_scrub_metadata *sm)
+static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
 {
 	return sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
 			       XFS_SCRUB_OFLAG_XCORRUPT);
 }
 
-int xfs_scrub_metadata_inode_forks(struct xfs_scrub_context *sc);
-int xfs_scrub_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
+int xchk_metadata_inode_forks(struct xfs_scrub *sc);
+int xchk_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
 
 #endif	/* __XFS_SCRUB_COMMON_H__ */
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index d700c4d4d4ef..f1260b4bfdee 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -35,12 +35,12 @@
  * operational errors in common.c.
  */
 bool
-xfs_scrub_da_process_error(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	int				*error)
+xchk_da_process_error(
+	struct xchk_da_btree	*ds,
+	int			level,
+	int			*error)
 {
-	struct xfs_scrub_context	*sc = ds->sc;
+	struct xfs_scrub	*sc = ds->sc;
 
 	if (*error == 0)
 		return true;
@@ -48,7 +48,7 @@ xfs_scrub_da_process_error(
 	switch (*error) {
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -57,7 +57,7 @@ xfs_scrub_da_process_error(
 		*error = 0;
 		/* fall through */
 	default:
-		trace_xfs_scrub_file_op_error(sc, ds->dargs.whichfork,
+		trace_xchk_file_op_error(sc, ds->dargs.whichfork,
 				xfs_dir2_da_to_db(ds->dargs.geo,
 					ds->state->path.blk[level].blkno),
 				*error, __return_address);
@@ -71,15 +71,15 @@ xfs_scrub_da_process_error(
  * operational errors in common.c.
  */
 void
-xfs_scrub_da_set_corrupt(
-	struct xfs_scrub_da_btree	*ds,
-	int				level)
+xchk_da_set_corrupt(
+	struct xchk_da_btree	*ds,
+	int			level)
 {
-	struct xfs_scrub_context	*sc = ds->sc;
+	struct xfs_scrub	*sc = ds->sc;
 
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 
-	trace_xfs_scrub_fblock_error(sc, ds->dargs.whichfork,
+	trace_xchk_fblock_error(sc, ds->dargs.whichfork,
 			xfs_dir2_da_to_db(ds->dargs.geo,
 				ds->state->path.blk[level].blkno),
 			__return_address);
@@ -87,14 +87,14 @@ xfs_scrub_da_set_corrupt(
 
 /* Find an entry at a certain level in a da btree. */
 STATIC void *
-xfs_scrub_da_btree_entry(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	int				rec)
+xchk_da_btree_entry(
+	struct xchk_da_btree	*ds,
+	int			level,
+	int			rec)
 {
-	char				*ents;
-	struct xfs_da_state_blk		*blk;
-	void				*baddr;
+	char			*ents;
+	struct xfs_da_state_blk	*blk;
+	void			*baddr;
 
 	/* Dispatch the entry finding function. */
 	blk = &ds->state->path.blk[level];
@@ -123,8 +123,8 @@ xfs_scrub_da_btree_entry(
 
 /* Scrub a da btree hash (key). */
 int
-xfs_scrub_da_btree_hash(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_hash(
+	struct xchk_da_btree		*ds,
 	int				level,
 	__be32				*hashp)
 {
@@ -136,7 +136,7 @@ xfs_scrub_da_btree_hash(
 	/* Is this hash in order? */
 	hash = be32_to_cpu(*hashp);
 	if (hash < ds->hashes[level])
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	ds->hashes[level] = hash;
 
 	if (level == 0)
@@ -144,10 +144,10 @@ xfs_scrub_da_btree_hash(
 
 	/* Is this hash no larger than the parent hash? */
 	blks = ds->state->path.blk;
-	entry = xfs_scrub_da_btree_entry(ds, level - 1, blks[level - 1].index);
+	entry = xchk_da_btree_entry(ds, level - 1, blks[level - 1].index);
 	parent_hash = be32_to_cpu(entry->hashval);
 	if (parent_hash < hash)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	return 0;
 }
@@ -157,13 +157,13 @@ xfs_scrub_da_btree_hash(
  * pointer.
  */
 STATIC bool
-xfs_scrub_da_btree_ptr_ok(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	xfs_dablk_t			blkno)
+xchk_da_btree_ptr_ok(
+	struct xchk_da_btree	*ds,
+	int			level,
+	xfs_dablk_t		blkno)
 {
 	if (blkno < ds->lowest || (ds->highest != 0 && blkno >= ds->highest)) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		return false;
 	}
 
@@ -176,7 +176,7 @@ xfs_scrub_da_btree_ptr_ok(
  * leaf1, we must multiplex the verifiers.
  */
 static void
-xfs_scrub_da_btree_read_verify(
+xchk_da_btree_read_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -198,7 +198,7 @@ xfs_scrub_da_btree_read_verify(
 	}
 }
 static void
-xfs_scrub_da_btree_write_verify(
+xchk_da_btree_write_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -220,7 +220,7 @@ xfs_scrub_da_btree_write_verify(
 	}
 }
 static void *
-xfs_scrub_da_btree_verify(
+xchk_da_btree_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -236,23 +236,23 @@ xfs_scrub_da_btree_verify(
 	}
 }
 
-static const struct xfs_buf_ops xfs_scrub_da_btree_buf_ops = {
-	.name = "xfs_scrub_da_btree",
-	.verify_read = xfs_scrub_da_btree_read_verify,
-	.verify_write = xfs_scrub_da_btree_write_verify,
-	.verify_struct = xfs_scrub_da_btree_verify,
+static const struct xfs_buf_ops xchk_da_btree_buf_ops = {
+	.name = "xchk_da_btree",
+	.verify_read = xchk_da_btree_read_verify,
+	.verify_write = xchk_da_btree_write_verify,
+	.verify_struct = xchk_da_btree_verify,
 };
 
 /* Check a block's sibling. */
 STATIC int
-xfs_scrub_da_btree_block_check_sibling(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	int				direction,
-	xfs_dablk_t			sibling)
+xchk_da_btree_block_check_sibling(
+	struct xchk_da_btree	*ds,
+	int			level,
+	int			direction,
+	xfs_dablk_t		sibling)
 {
-	int				retval;
-	int				error;
+	int			retval;
+	int			error;
 
 	memcpy(&ds->state->altpath, &ds->state->path,
 			sizeof(ds->state->altpath));
@@ -265,7 +265,7 @@ xfs_scrub_da_btree_block_check_sibling(
 		error = xfs_da3_path_shift(ds->state, &ds->state->altpath,
 				direction, false, &retval);
 		if (error == 0 && retval == 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		error = 0;
 		goto out;
 	}
@@ -273,19 +273,19 @@ xfs_scrub_da_btree_block_check_sibling(
 	/* Move the alternate cursor one block in the direction given. */
 	error = xfs_da3_path_shift(ds->state, &ds->state->altpath,
 			direction, false, &retval);
-	if (!xfs_scrub_da_process_error(ds, level, &error))
+	if (!xchk_da_process_error(ds, level, &error))
 		return error;
 	if (retval) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		return error;
 	}
 	if (ds->state->altpath.blk[level].bp)
-		xfs_scrub_buffer_recheck(ds->sc,
+		xchk_buffer_recheck(ds->sc,
 				ds->state->altpath.blk[level].bp);
 
 	/* Compare upper level pointer to sibling pointer. */
 	if (ds->state->altpath.blk[level].blkno != sibling)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	xfs_trans_brelse(ds->dargs.trans, ds->state->altpath.blk[level].bp);
 out:
 	return error;
@@ -293,14 +293,14 @@ out:
 
 /* Check a block's sibling pointers. */
 STATIC int
-xfs_scrub_da_btree_block_check_siblings(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	struct xfs_da_blkinfo		*hdr)
+xchk_da_btree_block_check_siblings(
+	struct xchk_da_btree	*ds,
+	int			level,
+	struct xfs_da_blkinfo	*hdr)
 {
-	xfs_dablk_t			forw;
-	xfs_dablk_t			back;
-	int				error = 0;
+	xfs_dablk_t		forw;
+	xfs_dablk_t		back;
+	int			error = 0;
 
 	forw = be32_to_cpu(hdr->forw);
 	back = be32_to_cpu(hdr->back);
@@ -308,7 +308,7 @@ xfs_scrub_da_btree_block_check_siblings(
 	/* Top level blocks should not have sibling pointers. */
 	if (level == 0) {
 		if (forw != 0 || back != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		return 0;
 	}
 
@@ -316,10 +316,10 @@ xfs_scrub_da_btree_block_check_siblings(
 	 * Check back (left) and forw (right) pointers.  These functions
 	 * absorb error codes for us.
 	 */
-	error = xfs_scrub_da_btree_block_check_sibling(ds, level, 0, back);
+	error = xchk_da_btree_block_check_sibling(ds, level, 0, back);
 	if (error)
 		goto out;
-	error = xfs_scrub_da_btree_block_check_sibling(ds, level, 1, forw);
+	error = xchk_da_btree_block_check_sibling(ds, level, 1, forw);
 
 out:
 	memset(&ds->state->altpath, 0, sizeof(ds->state->altpath));
@@ -328,8 +328,8 @@ out:
 
 /* Load a dir/attribute block from a btree. */
 STATIC int
-xfs_scrub_da_btree_block(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_block(
+	struct xchk_da_btree		*ds,
 	int				level,
 	xfs_dablk_t			blkno)
 {
@@ -355,17 +355,17 @@ xfs_scrub_da_btree_block(
 
 	/* Check the pointer. */
 	blk->blkno = blkno;
-	if (!xfs_scrub_da_btree_ptr_ok(ds, level, blkno))
+	if (!xchk_da_btree_ptr_ok(ds, level, blkno))
 		goto out_nobuf;
 
 	/* Read the buffer. */
 	error = xfs_da_read_buf(dargs->trans, dargs->dp, blk->blkno, -2,
 			&blk->bp, dargs->whichfork,
-			&xfs_scrub_da_btree_buf_ops);
-	if (!xfs_scrub_da_process_error(ds, level, &error))
+			&xchk_da_btree_buf_ops);
+	if (!xchk_da_process_error(ds, level, &error))
 		goto out_nobuf;
 	if (blk->bp)
-		xfs_scrub_buffer_recheck(ds->sc, blk->bp);
+		xchk_buffer_recheck(ds->sc, blk->bp);
 
 	/*
 	 * We didn't find a dir btree root block, which means that
@@ -378,7 +378,7 @@ xfs_scrub_da_btree_block(
 
 	/* It's /not/ ok for attr trees not to have a da btree. */
 	if (blk->bp == NULL) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out_nobuf;
 	}
 
@@ -388,17 +388,17 @@ xfs_scrub_da_btree_block(
 
 	/* We only started zeroing the header on v5 filesystems. */
 	if (xfs_sb_version_hascrc(&ds->sc->mp->m_sb) && hdr3->hdr.pad)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	/* Check the owner. */
 	if (xfs_sb_version_hascrc(&ip->i_mount->m_sb)) {
 		owner = be64_to_cpu(hdr3->owner);
 		if (owner != ip->i_ino)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	}
 
 	/* Check the siblings. */
-	error = xfs_scrub_da_btree_block_check_siblings(ds, level, &hdr3->hdr);
+	error = xchk_da_btree_block_check_siblings(ds, level, &hdr3->hdr);
 	if (error)
 		goto out;
 
@@ -411,7 +411,7 @@ xfs_scrub_da_btree_block(
 		blk->magic = XFS_ATTR_LEAF_MAGIC;
 		blk->hashval = xfs_attr_leaf_lasthash(blk->bp, pmaxrecs);
 		if (ds->tree_level != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		break;
 	case XFS_DIR2_LEAFN_MAGIC:
 	case XFS_DIR3_LEAFN_MAGIC:
@@ -420,7 +420,7 @@ xfs_scrub_da_btree_block(
 		blk->magic = XFS_DIR2_LEAFN_MAGIC;
 		blk->hashval = xfs_dir2_leaf_lasthash(ip, blk->bp, pmaxrecs);
 		if (ds->tree_level != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		break;
 	case XFS_DIR2_LEAF1_MAGIC:
 	case XFS_DIR3_LEAF1_MAGIC:
@@ -429,7 +429,7 @@ xfs_scrub_da_btree_block(
 		blk->magic = XFS_DIR2_LEAF1_MAGIC;
 		blk->hashval = xfs_dir2_leaf_lasthash(ip, blk->bp, pmaxrecs);
 		if (ds->tree_level != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		break;
 	case XFS_DA_NODE_MAGIC:
 	case XFS_DA3_NODE_MAGIC:
@@ -443,13 +443,13 @@ xfs_scrub_da_btree_block(
 		blk->hashval = be32_to_cpu(btree[*pmaxrecs - 1].hashval);
 		if (level == 0) {
 			if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) {
-				xfs_scrub_da_set_corrupt(ds, level);
+				xchk_da_set_corrupt(ds, level);
 				goto out_freebp;
 			}
 			ds->tree_level = nodehdr.level;
 		} else {
 			if (ds->tree_level != nodehdr.level) {
-				xfs_scrub_da_set_corrupt(ds, level);
+				xchk_da_set_corrupt(ds, level);
 				goto out_freebp;
 			}
 		}
@@ -457,7 +457,7 @@ xfs_scrub_da_btree_block(
 		/* XXX: Check hdr3.pad32 once we know how to fix it. */
 		break;
 	default:
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out_freebp;
 	}
 
@@ -473,13 +473,13 @@ out_nobuf:
 
 /* Visit all nodes and leaves of a da btree. */
 int
-xfs_scrub_da_btree(
-	struct xfs_scrub_context	*sc,
+xchk_da_btree(
+	struct xfs_scrub		*sc,
 	int				whichfork,
-	xfs_scrub_da_btree_rec_fn	scrub_fn,
+	xchk_da_btree_rec_fn		scrub_fn,
 	void				*private)
 {
-	struct xfs_scrub_da_btree	ds = {};
+	struct xchk_da_btree		ds = {};
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_da_state_blk		*blks;
 	struct xfs_da_node_entry	*key;
@@ -517,7 +517,7 @@ xfs_scrub_da_btree(
 
 	/* Find the root of the da tree, if present. */
 	blks = ds.state->path.blk;
-	error = xfs_scrub_da_btree_block(&ds, level, blkno);
+	error = xchk_da_btree_block(&ds, level, blkno);
 	if (error)
 		goto out_state;
 	/*
@@ -542,12 +542,12 @@ xfs_scrub_da_btree(
 			}
 
 			/* Dispatch record scrubbing. */
-			rec = xfs_scrub_da_btree_entry(&ds, level,
+			rec = xchk_da_btree_entry(&ds, level,
 					blks[level].index);
 			error = scrub_fn(&ds, level, rec);
 			if (error)
 				break;
-			if (xfs_scrub_should_terminate(sc, &error) ||
+			if (xchk_should_terminate(sc, &error) ||
 			    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 				break;
 
@@ -566,8 +566,8 @@ xfs_scrub_da_btree(
 		}
 
 		/* Hashes in order for scrub? */
-		key = xfs_scrub_da_btree_entry(&ds, level, blks[level].index);
-		error = xfs_scrub_da_btree_hash(&ds, level, &key->hashval);
+		key = xchk_da_btree_entry(&ds, level, blks[level].index);
+		error = xchk_da_btree_hash(&ds, level, &key->hashval);
 		if (error)
 			goto out;
 
@@ -575,7 +575,7 @@ xfs_scrub_da_btree(
 		blkno = be32_to_cpu(key->before);
 		level++;
 		ds.tree_level--;
-		error = xfs_scrub_da_btree_block(&ds, level, blkno);
+		error = xchk_da_btree_block(&ds, level, blkno);
 		if (error)
 			goto out;
 		if (blks[level].bp == NULL)
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index 365f9f0019e6..cb3f0003245b 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -8,13 +8,13 @@
 
 /* dir/attr btree */
 
-struct xfs_scrub_da_btree {
-	struct xfs_da_args		dargs;
-	xfs_dahash_t			hashes[XFS_DA_NODE_MAXDEPTH];
-	int				maxrecs[XFS_DA_NODE_MAXDEPTH];
-	struct xfs_da_state		*state;
-	struct xfs_scrub_context	*sc;
-	void				*private;
+struct xchk_da_btree {
+	struct xfs_da_args	dargs;
+	xfs_dahash_t		hashes[XFS_DA_NODE_MAXDEPTH];
+	int			maxrecs[XFS_DA_NODE_MAXDEPTH];
+	struct xfs_da_state	*state;
+	struct xfs_scrub	*sc;
+	void			*private;
 
 	/*
 	 * Lowest and highest directory block address in which we expect
@@ -22,24 +22,23 @@ struct xfs_scrub_da_btree {
 	 * (presumably) means between LEAF_OFFSET and FREE_OFFSET; for
 	 * attributes there is no limit.
 	 */
-	xfs_dablk_t			lowest;
-	xfs_dablk_t			highest;
+	xfs_dablk_t		lowest;
+	xfs_dablk_t		highest;
 
-	int				tree_level;
+	int			tree_level;
 };
 
-typedef int (*xfs_scrub_da_btree_rec_fn)(struct xfs_scrub_da_btree *ds,
+typedef int (*xchk_da_btree_rec_fn)(struct xchk_da_btree *ds,
 		int level, void *rec);
 
 /* Check for da btree operation errors. */
-bool xfs_scrub_da_process_error(struct xfs_scrub_da_btree *ds, int level, int *error);
+bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error);
 
 /* Check for da btree corruption. */
-void xfs_scrub_da_set_corrupt(struct xfs_scrub_da_btree *ds, int level);
+void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
 
-int xfs_scrub_da_btree_hash(struct xfs_scrub_da_btree *ds, int level,
-			    __be32 *hashp);
-int xfs_scrub_da_btree(struct xfs_scrub_context *sc, int whichfork,
-		       xfs_scrub_da_btree_rec_fn scrub_fn, void *private);
+int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp);
+int xchk_da_btree(struct xfs_scrub *sc, int whichfork,
+		xchk_da_btree_rec_fn scrub_fn, void *private);
 
 #endif /* __XFS_SCRUB_DABTREE_H__ */
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 86324775fc9b..cd3e4d768a18 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -31,40 +31,40 @@
 
 /* Set us up to scrub directories. */
 int
-xfs_scrub_setup_directory(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_directory(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Directories */
 
 /* Scrub a directory entry. */
 
-struct xfs_scrub_dir_ctx {
+struct xchk_dir_ctx {
 	/* VFS fill-directory iterator */
-	struct dir_context		dir_iter;
+	struct dir_context	dir_iter;
 
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 };
 
 /* Check that an inode's mode matches a given DT_ type. */
 STATIC int
-xfs_scrub_dir_check_ftype(
-	struct xfs_scrub_dir_ctx	*sdc,
-	xfs_fileoff_t			offset,
-	xfs_ino_t			inum,
-	int				dtype)
+xchk_dir_check_ftype(
+	struct xchk_dir_ctx	*sdc,
+	xfs_fileoff_t		offset,
+	xfs_ino_t		inum,
+	int			dtype)
 {
-	struct xfs_mount		*mp = sdc->sc->mp;
-	struct xfs_inode		*ip;
-	int				ino_dtype;
-	int				error = 0;
+	struct xfs_mount	*mp = sdc->sc->mp;
+	struct xfs_inode	*ip;
+	int			ino_dtype;
+	int			error = 0;
 
 	if (!xfs_sb_version_hasftype(&mp->m_sb)) {
 		if (dtype != DT_UNKNOWN && dtype != DT_DIR)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 		goto out;
 	}
@@ -78,7 +78,7 @@ xfs_scrub_dir_check_ftype(
 	 * inodes can trigger immediate inactive cleanup of the inode.
 	 */
 	error = xfs_iget(mp, sdc->sc->tp, inum, 0, 0, &ip);
-	if (!xfs_scrub_fblock_xref_process_error(sdc->sc, XFS_DATA_FORK, offset,
+	if (!xchk_fblock_xref_process_error(sdc->sc, XFS_DATA_FORK, offset,
 			&error))
 		goto out;
 
@@ -86,8 +86,8 @@ xfs_scrub_dir_check_ftype(
 	ino_dtype = xfs_dir3_get_dtype(mp,
 			xfs_mode_to_ftype(VFS_I(ip)->i_mode));
 	if (ino_dtype != dtype)
-		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
-	iput(VFS_I(ip));
+		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
+	xfs_irele(ip);
 out:
 	return error;
 }
@@ -101,23 +101,23 @@ out:
  * we can look up this filename.  Finally, we check the ftype.
  */
 STATIC int
-xfs_scrub_dir_actor(
-	struct dir_context		*dir_iter,
-	const char			*name,
-	int				namelen,
-	loff_t				pos,
-	u64				ino,
-	unsigned			type)
+xchk_dir_actor(
+	struct dir_context	*dir_iter,
+	const char		*name,
+	int			namelen,
+	loff_t			pos,
+	u64			ino,
+	unsigned		type)
 {
-	struct xfs_mount		*mp;
-	struct xfs_inode		*ip;
-	struct xfs_scrub_dir_ctx	*sdc;
-	struct xfs_name			xname;
-	xfs_ino_t			lookup_ino;
-	xfs_dablk_t			offset;
-	int				error = 0;
-
-	sdc = container_of(dir_iter, struct xfs_scrub_dir_ctx, dir_iter);
+	struct xfs_mount	*mp;
+	struct xfs_inode	*ip;
+	struct xchk_dir_ctx	*sdc;
+	struct xfs_name		xname;
+	xfs_ino_t		lookup_ino;
+	xfs_dablk_t		offset;
+	int			error = 0;
+
+	sdc = container_of(dir_iter, struct xchk_dir_ctx, dir_iter);
 	ip = sdc->sc->ip;
 	mp = ip->i_mount;
 	offset = xfs_dir2_db_to_da(mp->m_dir_geo,
@@ -125,17 +125,17 @@ xfs_scrub_dir_actor(
 
 	/* Does this inode number make sense? */
 	if (!xfs_verify_dir_ino(mp, ino)) {
-		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
 		goto out;
 	}
 
 	if (!strncmp(".", name, namelen)) {
 		/* If this is "." then check that the inum matches the dir. */
 		if (xfs_sb_version_hasftype(&mp->m_sb) && type != DT_DIR)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 		if (ino != ip->i_ino)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 	} else if (!strncmp("..", name, namelen)) {
 		/*
@@ -143,10 +143,10 @@ xfs_scrub_dir_actor(
 		 * matches this dir.
 		 */
 		if (xfs_sb_version_hasftype(&mp->m_sb) && type != DT_DIR)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 		if (ip->i_ino == mp->m_sb.sb_rootino && ino != ip->i_ino)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 	}
 
@@ -156,23 +156,23 @@ xfs_scrub_dir_actor(
 	xname.type = XFS_DIR3_FT_UNKNOWN;
 
 	error = xfs_dir_lookup(sdc->sc->tp, ip, &xname, &lookup_ino, NULL);
-	if (!xfs_scrub_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset,
+	if (!xchk_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset,
 			&error))
 		goto out;
 	if (lookup_ino != ino) {
-		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
 		goto out;
 	}
 
 	/* Verify the file type.  This function absorbs error codes. */
-	error = xfs_scrub_dir_check_ftype(sdc, offset, lookup_ino, type);
+	error = xchk_dir_check_ftype(sdc, offset, lookup_ino, type);
 	if (error)
 		goto out;
 out:
 	/*
 	 * A negative error code returned here is supposed to cause the
 	 * dir_emit caller (xfs_readdir) to abort the directory iteration
-	 * and return zero to xfs_scrub_directory.
+	 * and return zero to xchk_directory.
 	 */
 	if (error == 0 && sdc->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return -EFSCORRUPTED;
@@ -181,8 +181,8 @@ out:
 
 /* Scrub a directory btree record. */
 STATIC int
-xfs_scrub_dir_rec(
-	struct xfs_scrub_da_btree	*ds,
+xchk_dir_rec(
+	struct xchk_da_btree		*ds,
 	int				level,
 	void				*rec)
 {
@@ -203,7 +203,7 @@ xfs_scrub_dir_rec(
 	int				error;
 
 	/* Check the hash of the entry. */
-	error = xfs_scrub_da_btree_hash(ds, level, &ent->hashval);
+	error = xchk_da_btree_hash(ds, level, &ent->hashval);
 	if (error)
 		goto out;
 
@@ -218,18 +218,18 @@ xfs_scrub_dir_rec(
 	rec_bno = xfs_dir2_db_to_da(mp->m_dir_geo, db);
 
 	if (rec_bno >= mp->m_dir_geo->leafblk) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out;
 	}
 	error = xfs_dir3_data_read(ds->dargs.trans, dp, rec_bno, -2, &bp);
-	if (!xfs_scrub_fblock_process_error(ds->sc, XFS_DATA_FORK, rec_bno,
+	if (!xchk_fblock_process_error(ds->sc, XFS_DATA_FORK, rec_bno,
 			&error))
 		goto out;
 	if (!bp) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out;
 	}
-	xfs_scrub_buffer_recheck(ds->sc, bp);
+	xchk_buffer_recheck(ds->sc, bp);
 
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out_relse;
@@ -240,7 +240,7 @@ xfs_scrub_dir_rec(
 	p = (char *)mp->m_dir_inode_ops->data_entry_p(bp->b_addr);
 	endp = xfs_dir3_data_endp(mp->m_dir_geo, bp->b_addr);
 	if (!endp) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out_relse;
 	}
 	while (p < endp) {
@@ -258,7 +258,7 @@ xfs_scrub_dir_rec(
 		p += mp->m_dir_inode_ops->data_entsize(dep->namelen);
 	}
 	if (p >= endp) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out_relse;
 	}
 
@@ -267,14 +267,14 @@ xfs_scrub_dir_rec(
 	hash = be32_to_cpu(ent->hashval);
 	tag = be16_to_cpup(dp->d_ops->data_entry_tag_p(dent));
 	if (!xfs_verify_dir_ino(mp, ino) || tag != off)
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 	if (dent->namelen == 0) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out_relse;
 	}
 	calc_hash = xfs_da_hashname(dent->name, dent->namelen);
 	if (calc_hash != hash)
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 
 out_relse:
 	xfs_trans_brelse(ds->dargs.trans, bp);
@@ -288,8 +288,8 @@ out:
  * shortest, and that there aren't any bogus entries.
  */
 STATIC void
-xfs_scrub_directory_check_free_entry(
-	struct xfs_scrub_context	*sc,
+xchk_directory_check_free_entry(
+	struct xfs_scrub		*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_dir2_data_free	*bf,
 	struct xfs_dir2_data_unused	*dup)
@@ -308,13 +308,13 @@ xfs_scrub_directory_check_free_entry(
 			return;
 
 	/* Unused entry should be in the bestfrees but wasn't found. */
-	xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+	xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 }
 
 /* Check free space info in a directory data block. */
 STATIC int
-xfs_scrub_directory_data_bestfree(
-	struct xfs_scrub_context	*sc,
+xchk_directory_data_bestfree(
+	struct xfs_scrub		*sc,
 	xfs_dablk_t			lblk,
 	bool				is_block)
 {
@@ -339,15 +339,15 @@ xfs_scrub_directory_data_bestfree(
 	if (is_block) {
 		/* dir block format */
 		if (lblk != XFS_B_TO_FSBT(mp, XFS_DIR2_DATA_OFFSET))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		error = xfs_dir3_block_read(sc->tp, sc->ip, &bp);
 	} else {
 		/* dir data format */
 		error = xfs_dir3_data_read(sc->tp, sc->ip, lblk, -1, &bp);
 	}
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, bp);
+	xchk_buffer_recheck(sc, bp);
 
 	/* XXX: Check xfs_dir3_data_hdr.pad is zero once we start setting it. */
 
@@ -362,7 +362,7 @@ xfs_scrub_directory_data_bestfree(
 		if (offset == 0)
 			continue;
 		if (offset >= mp->m_dir_geo->blksize) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 		dup = (struct xfs_dir2_data_unused *)(bp->b_addr + offset);
@@ -372,13 +372,13 @@ xfs_scrub_directory_data_bestfree(
 		if (dup->freetag != cpu_to_be16(XFS_DIR2_DATA_FREE_TAG) ||
 		    be16_to_cpu(dup->length) != be16_to_cpu(dfp->length) ||
 		    tag != ((char *)dup - (char *)bp->b_addr)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 
 		/* bestfree records should be ordered largest to smallest */
 		if (smallest_bestfree < be16_to_cpu(dfp->length)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 
@@ -400,7 +400,7 @@ xfs_scrub_directory_data_bestfree(
 			dep = (struct xfs_dir2_data_entry *)ptr;
 			newlen = d_ops->data_entsize(dep->namelen);
 			if (newlen <= 0) {
-				xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+				xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 						lblk);
 				goto out_buf;
 			}
@@ -411,7 +411,7 @@ xfs_scrub_directory_data_bestfree(
 		/* Spot check this free entry */
 		tag = be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup));
 		if (tag != ((char *)dup - (char *)bp->b_addr)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 
@@ -419,14 +419,14 @@ xfs_scrub_directory_data_bestfree(
 		 * Either this entry is a bestfree or it's smaller than
 		 * any of the bestfrees.
 		 */
-		xfs_scrub_directory_check_free_entry(sc, lblk, bf, dup);
+		xchk_directory_check_free_entry(sc, lblk, bf, dup);
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			goto out_buf;
 
 		/* Move on. */
 		newlen = be16_to_cpu(dup->length);
 		if (newlen <= 0) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 		ptr += newlen;
@@ -436,11 +436,11 @@ xfs_scrub_directory_data_bestfree(
 
 	/* We're required to fill all the space. */
 	if (ptr != endptr)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 
 	/* Did we see at least as many free slots as there are bestfrees? */
 	if (nr_frees < nr_bestfrees)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 out_buf:
 	xfs_trans_brelse(sc->tp, bp);
 out:
@@ -454,8 +454,8 @@ out:
  * array is in order.
  */
 STATIC void
-xfs_scrub_directory_check_freesp(
-	struct xfs_scrub_context	*sc,
+xchk_directory_check_freesp(
+	struct xfs_scrub		*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_buf			*dbp,
 	unsigned int			len)
@@ -465,16 +465,16 @@ xfs_scrub_directory_check_freesp(
 	dfp = sc->ip->d_ops->data_bestfree_p(dbp->b_addr);
 
 	if (len != be16_to_cpu(dfp->length))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 
 	if (len > 0 && be16_to_cpu(dfp->offset) == 0)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 }
 
 /* Check free space info in a directory leaf1 block. */
 STATIC int
-xfs_scrub_directory_leaf1_bestfree(
-	struct xfs_scrub_context	*sc,
+xchk_directory_leaf1_bestfree(
+	struct xfs_scrub		*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
 {
@@ -497,9 +497,9 @@ xfs_scrub_directory_leaf1_bestfree(
 
 	/* Read the free space block. */
 	error = xfs_dir3_leaf_read(sc->tp, sc->ip, lblk, -1, &bp);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, bp);
+	xchk_buffer_recheck(sc, bp);
 
 	leaf = bp->b_addr;
 	d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
@@ -512,7 +512,7 @@ xfs_scrub_directory_leaf1_bestfree(
 		struct xfs_dir3_leaf_hdr	*hdr3 = bp->b_addr;
 
 		if (hdr3->pad != cpu_to_be32(0))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 	}
 
 	/*
@@ -520,19 +520,19 @@ xfs_scrub_directory_leaf1_bestfree(
 	 * blocks that can fit under i_size.
 	 */
 	if (bestcount != xfs_dir2_byte_to_db(geo, sc->ip->i_d.di_size)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
 
 	/* Is the leaf count even remotely sane? */
 	if (leafhdr.count > d_ops->leaf_max_ents(geo)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
 
 	/* Leaves and bests don't overlap in leaf format. */
 	if ((char *)&ents[leafhdr.count] > (char *)bestp) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
 
@@ -540,13 +540,13 @@ xfs_scrub_directory_leaf1_bestfree(
 	for (i = 0; i < leafhdr.count; i++) {
 		hash = be32_to_cpu(ents[i].hashval);
 		if (i > 0 && lasthash > hash)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		lasthash = hash;
 		if (ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
 			stale++;
 	}
 	if (leafhdr.stale != stale)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
@@ -557,10 +557,10 @@ xfs_scrub_directory_leaf1_bestfree(
 			continue;
 		error = xfs_dir3_data_read(sc->tp, sc->ip,
 				i * args->geo->fsbcount, -1, &dbp);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
 				&error))
 			break;
-		xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
+		xchk_directory_check_freesp(sc, lblk, dbp, best);
 		xfs_trans_brelse(sc->tp, dbp);
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			goto out;
@@ -571,8 +571,8 @@ out:
 
 /* Check free space info in a directory freespace block. */
 STATIC int
-xfs_scrub_directory_free_bestfree(
-	struct xfs_scrub_context	*sc,
+xchk_directory_free_bestfree(
+	struct xfs_scrub		*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
 {
@@ -587,15 +587,15 @@ xfs_scrub_directory_free_bestfree(
 
 	/* Read the free space block */
 	error = xfs_dir2_free_read(sc->tp, sc->ip, lblk, &bp);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, bp);
+	xchk_buffer_recheck(sc, bp);
 
 	if (xfs_sb_version_hascrc(&sc->mp->m_sb)) {
 		struct xfs_dir3_free_hdr	*hdr3 = bp->b_addr;
 
 		if (hdr3->pad != cpu_to_be32(0))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 	}
 
 	/* Check all the entries. */
@@ -610,36 +610,36 @@ xfs_scrub_directory_free_bestfree(
 		error = xfs_dir3_data_read(sc->tp, sc->ip,
 				(freehdr.firstdb + i) * args->geo->fsbcount,
 				-1, &dbp);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
 				&error))
 			break;
-		xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
+		xchk_directory_check_freesp(sc, lblk, dbp, best);
 		xfs_trans_brelse(sc->tp, dbp);
 	}
 
 	if (freehdr.nused + stale != freehdr.nvalid)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 out:
 	return error;
 }
 
 /* Check free space information in directories. */
 STATIC int
-xfs_scrub_directory_blocks(
-	struct xfs_scrub_context	*sc)
+xchk_directory_blocks(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_bmbt_irec		got;
-	struct xfs_da_args		args;
-	struct xfs_ifork		*ifp;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_fileoff_t			leaf_lblk;
-	xfs_fileoff_t			free_lblk;
-	xfs_fileoff_t			lblk;
-	struct xfs_iext_cursor		icur;
-	xfs_dablk_t			dabno;
-	bool				found;
-	int				is_block = 0;
-	int				error;
+	struct xfs_bmbt_irec	got;
+	struct xfs_da_args	args;
+	struct xfs_ifork	*ifp;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_fileoff_t		leaf_lblk;
+	xfs_fileoff_t		free_lblk;
+	xfs_fileoff_t		lblk;
+	struct xfs_iext_cursor	icur;
+	xfs_dablk_t		dabno;
+	bool			found;
+	int			is_block = 0;
+	int			error;
 
 	/* Ignore local format directories. */
 	if (sc->ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
@@ -656,7 +656,7 @@ xfs_scrub_directory_blocks(
 	args.geo = mp->m_dir_geo;
 	args.trans = sc->tp;
 	error = xfs_dir2_isblock(&args, &is_block);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
 
 	/* Iterate all the data extents in the directory... */
@@ -666,7 +666,7 @@ xfs_scrub_directory_blocks(
 		if (is_block &&
 		    (got.br_startoff > 0 ||
 		     got.br_blockcount != args.geo->fsbcount)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					got.br_startoff);
 			break;
 		}
@@ -690,7 +690,7 @@ xfs_scrub_directory_blocks(
 				args.geo->fsbcount);
 		     lblk < got.br_startoff + got.br_blockcount;
 		     lblk += args.geo->fsbcount) {
-			error = xfs_scrub_directory_data_bestfree(sc, lblk,
+			error = xchk_directory_data_bestfree(sc, lblk,
 					is_block);
 			if (error)
 				goto out;
@@ -709,10 +709,10 @@ xfs_scrub_directory_blocks(
 	    got.br_blockcount == args.geo->fsbcount &&
 	    !xfs_iext_next_extent(ifp, &icur, &got)) {
 		if (is_block) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out;
 		}
-		error = xfs_scrub_directory_leaf1_bestfree(sc, &args,
+		error = xchk_directory_leaf1_bestfree(sc, &args,
 				leaf_lblk);
 		if (error)
 			goto out;
@@ -731,11 +731,11 @@ xfs_scrub_directory_blocks(
 		 */
 		lblk = got.br_startoff;
 		if (lblk & ~0xFFFFFFFFULL) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out;
 		}
 		if (is_block) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out;
 		}
 
@@ -754,7 +754,7 @@ xfs_scrub_directory_blocks(
 				args.geo->fsbcount);
 		     lblk < got.br_startoff + got.br_blockcount;
 		     lblk += args.geo->fsbcount) {
-			error = xfs_scrub_directory_free_bestfree(sc, &args,
+			error = xchk_directory_free_bestfree(sc, &args,
 					lblk);
 			if (error)
 				goto out;
@@ -769,29 +769,29 @@ out:
 
 /* Scrub a whole directory. */
 int
-xfs_scrub_directory(
-	struct xfs_scrub_context	*sc)
+xchk_directory(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_scrub_dir_ctx	sdc = {
-		.dir_iter.actor = xfs_scrub_dir_actor,
+	struct xchk_dir_ctx	sdc = {
+		.dir_iter.actor = xchk_dir_actor,
 		.dir_iter.pos = 0,
 		.sc = sc,
 	};
-	size_t				bufsize;
-	loff_t				oldpos;
-	int				error = 0;
+	size_t			bufsize;
+	loff_t			oldpos;
+	int			error = 0;
 
 	if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
 		return -ENOENT;
 
 	/* Plausible size? */
 	if (sc->ip->i_d.di_size < xfs_dir2_sf_hdr_size(0)) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		goto out;
 	}
 
 	/* Check directory tree structure */
-	error = xfs_scrub_da_btree(sc, XFS_DATA_FORK, xfs_scrub_dir_rec, NULL);
+	error = xchk_da_btree(sc, XFS_DATA_FORK, xchk_dir_rec, NULL);
 	if (error)
 		return error;
 
@@ -799,7 +799,7 @@ xfs_scrub_directory(
 		return error;
 
 	/* Check the freespace. */
-	error = xfs_scrub_directory_blocks(sc);
+	error = xchk_directory_blocks(sc);
 	if (error)
 		return error;
 
@@ -816,7 +816,7 @@ xfs_scrub_directory(
 	/*
 	 * Look up every name in this directory by hash.
 	 *
-	 * Use the xfs_readdir function to call xfs_scrub_dir_actor on
+	 * Use the xfs_readdir function to call xchk_dir_actor on
 	 * every directory entry in this directory.  In _actor, we check
 	 * the name, inode number, and ftype (if applicable) of the
 	 * entry.  xfs_readdir uses the VFS filldir functions to provide
@@ -834,7 +834,7 @@ xfs_scrub_directory(
 	xfs_iunlock(sc->ip, XFS_ILOCK_EXCL);
 	while (true) {
 		error = xfs_readdir(sc->tp, sc->ip, &sdc.dir_iter, bufsize);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0,
 				&error))
 			goto out;
 		if (oldpos == sdc.dir_iter.pos)
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 13d43d108574..224dba937492 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -35,11 +35,11 @@
  * try again after forcing logged inode cores out to disk.
  */
 int
-xfs_scrub_setup_ag_iallocbt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_ag_iallocbt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, sc->try_harder);
+	return xchk_setup_ag_btree(sc, ip, sc->try_harder);
 }
 
 /* Inode btree scrubber. */
@@ -50,8 +50,8 @@ xfs_scrub_setup_ag_iallocbt(
  * we have a record or not depending on freecount.
  */
 static inline void
-xfs_scrub_iallocbt_chunk_xref_other(
-	struct xfs_scrub_context	*sc,
+xchk_iallocbt_chunk_xref_other(
+	struct xfs_scrub		*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino)
 {
@@ -66,17 +66,17 @@ xfs_scrub_iallocbt_chunk_xref_other(
 	if (!(*pcur))
 		return;
 	error = xfs_ialloc_has_inode_record(*pcur, agino, agino, &has_irec);
-	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
+	if (!xchk_should_check_xref(sc, &error, pcur))
 		return;
 	if (((irec->ir_freecount > 0 && !has_irec) ||
 	     (irec->ir_freecount == 0 && has_irec)))
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_iallocbt_chunk_xref(
-	struct xfs_scrub_context	*sc,
+xchk_iallocbt_chunk_xref(
+	struct xfs_scrub		*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino,
 	xfs_agblock_t			agbno,
@@ -87,17 +87,17 @@ xfs_scrub_iallocbt_chunk_xref(
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, len);
-	xfs_scrub_iallocbt_chunk_xref_other(sc, irec, agino);
+	xchk_xref_is_used_space(sc, agbno, len);
+	xchk_iallocbt_chunk_xref_other(sc, irec, agino);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
-	xfs_scrub_xref_is_owned_by(sc, agbno, len, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, len);
+	xchk_xref_is_owned_by(sc, agbno, len, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, len);
 }
 
 /* Is this chunk worth checking? */
 STATIC bool
-xfs_scrub_iallocbt_chunk(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_chunk(
+	struct xchk_btree		*bs,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino,
 	xfs_extlen_t			len)
@@ -110,16 +110,16 @@ xfs_scrub_iallocbt_chunk(
 	if (bno + len <= bno ||
 	    !xfs_verify_agbno(mp, agno, bno) ||
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xfs_scrub_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);
+	xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);
 
 	return true;
 }
 
 /* Count the number of free inodes. */
 static unsigned int
-xfs_scrub_iallocbt_freecount(
+xchk_iallocbt_freecount(
 	xfs_inofree_t			freemask)
 {
 	BUILD_BUG_ON(sizeof(freemask) != sizeof(__u64));
@@ -128,8 +128,8 @@ xfs_scrub_iallocbt_freecount(
 
 /* Check a particular inode with ir_free. */
 STATIC int
-xfs_scrub_iallocbt_check_cluster_freemask(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_check_cluster_freemask(
+	struct xchk_btree		*bs,
 	xfs_ino_t			fsino,
 	xfs_agino_t			chunkino,
 	xfs_agino_t			clusterino,
@@ -143,14 +143,14 @@ xfs_scrub_iallocbt_check_cluster_freemask(
 	bool				inuse;
 	int				error = 0;
 
-	if (xfs_scrub_should_terminate(bs->sc, &error))
+	if (xchk_should_terminate(bs->sc, &error))
 		return error;
 
 	dip = xfs_buf_offset(bp, clusterino * mp->m_sb.sb_inodesize);
 	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
 	    (dip->di_version >= 3 &&
 	     be64_to_cpu(dip->di_ino) != fsino + clusterino)) {
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		goto out;
 	}
 
@@ -175,15 +175,15 @@ xfs_scrub_iallocbt_check_cluster_freemask(
 		freemask_ok = inode_is_free ^ inuse;
 	}
 	if (!freemask_ok)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 out:
 	return 0;
 }
 
 /* Make sure the free mask is consistent with what the inodes think. */
 STATIC int
-xfs_scrub_iallocbt_check_freemask(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_check_freemask(
+	struct xchk_btree		*bs,
 	struct xfs_inobt_rec_incore	*irec)
 {
 	struct xfs_owner_info		oinfo;
@@ -223,18 +223,18 @@ xfs_scrub_iallocbt_check_freemask(
 		/* The whole cluster must be a hole or not a hole. */
 		ir_holemask = (irec->ir_holemask & holemask);
 		if (ir_holemask != holemask && ir_holemask != 0) {
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 			continue;
 		}
 
 		/* If any part of this is a hole, skip it. */
 		if (ir_holemask) {
-			xfs_scrub_xref_is_not_owned_by(bs->sc, agbno,
+			xchk_xref_is_not_owned_by(bs->sc, agbno,
 					blks_per_cluster, &oinfo);
 			continue;
 		}
 
-		xfs_scrub_xref_is_owned_by(bs->sc, agbno, blks_per_cluster,
+		xchk_xref_is_owned_by(bs->sc, agbno, blks_per_cluster,
 				&oinfo);
 
 		/* Grab the inode cluster buffer. */
@@ -245,13 +245,13 @@ xfs_scrub_iallocbt_check_freemask(
 
 		error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap,
 				&dip, &bp, 0, 0);
-		if (!xfs_scrub_btree_xref_process_error(bs->sc, bs->cur, 0,
+		if (!xchk_btree_xref_process_error(bs->sc, bs->cur, 0,
 				&error))
 			continue;
 
 		/* Which inodes are free? */
 		for (clusterino = 0; clusterino < nr_inodes; clusterino++) {
-			error = xfs_scrub_iallocbt_check_cluster_freemask(bs,
+			error = xchk_iallocbt_check_cluster_freemask(bs,
 					fsino, chunkino, clusterino, irec, bp);
 			if (error) {
 				xfs_trans_brelse(bs->cur->bc_tp, bp);
@@ -267,8 +267,8 @@ xfs_scrub_iallocbt_check_freemask(
 
 /* Scrub an inobt/finobt record. */
 STATIC int
-xfs_scrub_iallocbt_rec(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_rec(
+	struct xchk_btree		*bs,
 	union xfs_btree_rec		*rec)
 {
 	struct xfs_mount		*mp = bs->cur->bc_mp;
@@ -289,18 +289,18 @@ xfs_scrub_iallocbt_rec(
 
 	if (irec.ir_count > XFS_INODES_PER_CHUNK ||
 	    irec.ir_freecount > XFS_INODES_PER_CHUNK)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	real_freecount = irec.ir_freecount +
 			(XFS_INODES_PER_CHUNK - irec.ir_count);
-	if (real_freecount != xfs_scrub_iallocbt_freecount(irec.ir_free))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+	if (real_freecount != xchk_iallocbt_freecount(irec.ir_free))
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	agino = irec.ir_startino;
 	/* Record has to be properly aligned within the AG. */
 	if (!xfs_verify_agino(mp, agno, agino) ||
 	    !xfs_verify_agino(mp, agno, agino + XFS_INODES_PER_CHUNK - 1)) {
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		goto out;
 	}
 
@@ -308,7 +308,7 @@ xfs_scrub_iallocbt_rec(
 	agbno = XFS_AGINO_TO_AGBNO(mp, irec.ir_startino);
 	if ((agbno & (xfs_ialloc_cluster_alignment(mp) - 1)) ||
 	    (agbno & (xfs_icluster_size_fsb(mp) - 1)))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	*inode_blocks += XFS_B_TO_FSB(mp,
 			irec.ir_count * mp->m_sb.sb_inodesize);
@@ -318,9 +318,9 @@ xfs_scrub_iallocbt_rec(
 		len = XFS_B_TO_FSB(mp,
 				XFS_INODES_PER_CHUNK * mp->m_sb.sb_inodesize);
 		if (irec.ir_count != XFS_INODES_PER_CHUNK)
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-		if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
+		if (!xchk_iallocbt_chunk(bs, &irec, agino, len))
 			goto out;
 		goto check_freemask;
 	}
@@ -333,12 +333,12 @@ xfs_scrub_iallocbt_rec(
 	holes = ~xfs_inobt_irec_to_allocmask(&irec);
 	if ((holes & irec.ir_free) != holes ||
 	    irec.ir_freecount > irec.ir_count)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; i++) {
 		if (holemask & 1)
 			holecount += XFS_INODES_PER_HOLEMASK_BIT;
-		else if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
+		else if (!xchk_iallocbt_chunk(bs, &irec, agino, len))
 			break;
 		holemask >>= 1;
 		agino += XFS_INODES_PER_HOLEMASK_BIT;
@@ -346,10 +346,10 @@ xfs_scrub_iallocbt_rec(
 
 	if (holecount > XFS_INODES_PER_CHUNK ||
 	    holecount + irec.ir_count != XFS_INODES_PER_CHUNK)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 check_freemask:
-	error = xfs_scrub_iallocbt_check_freemask(bs, &irec);
+	error = xchk_iallocbt_check_freemask(bs, &irec);
 	if (error)
 		goto out;
 
@@ -362,39 +362,39 @@ out:
  * Don't bother if we're missing btree cursors, as we're already corrupt.
  */
 STATIC void
-xfs_scrub_iallocbt_xref_rmap_btreeblks(
-	struct xfs_scrub_context	*sc,
-	int				which)
+xchk_iallocbt_xref_rmap_btreeblks(
+	struct xfs_scrub	*sc,
+	int			which)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_filblks_t			blocks;
-	xfs_extlen_t			inobt_blocks = 0;
-	xfs_extlen_t			finobt_blocks = 0;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_filblks_t		blocks;
+	xfs_extlen_t		inobt_blocks = 0;
+	xfs_extlen_t		finobt_blocks = 0;
+	int			error;
 
 	if (!sc->sa.ino_cur || !sc->sa.rmap_cur ||
 	    (xfs_sb_version_hasfinobt(&sc->mp->m_sb) && !sc->sa.fino_cur) ||
-	    xfs_scrub_skip_xref(sc->sm))
+	    xchk_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many inobt blocks as the rmap says. */
 	error = xfs_btree_count_blocks(sc->sa.ino_cur, &inobt_blocks);
-	if (!xfs_scrub_process_error(sc, 0, 0, &error))
+	if (!xchk_process_error(sc, 0, 0, &error))
 		return;
 
 	if (sc->sa.fino_cur) {
 		error = xfs_btree_count_blocks(sc->sa.fino_cur, &finobt_blocks);
-		if (!xfs_scrub_process_error(sc, 0, 0, &error))
+		if (!xchk_process_error(sc, 0, 0, &error))
 			return;
 	}
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != inobt_blocks + finobt_blocks)
-		xfs_scrub_btree_set_corrupt(sc, sc->sa.ino_cur, 0);
+		xchk_btree_set_corrupt(sc, sc->sa.ino_cur, 0);
 }
 
 /*
@@ -402,47 +402,47 @@ xfs_scrub_iallocbt_xref_rmap_btreeblks(
  * the rmap says are owned by inodes.
  */
 STATIC void
-xfs_scrub_iallocbt_xref_rmap_inodes(
-	struct xfs_scrub_context	*sc,
-	int				which,
-	xfs_filblks_t			inode_blocks)
+xchk_iallocbt_xref_rmap_inodes(
+	struct xfs_scrub	*sc,
+	int			which,
+	xfs_filblks_t		inode_blocks)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_filblks_t			blocks;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_filblks_t		blocks;
+	int			error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many inode blocks as the rmap knows about. */
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != inode_blocks)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* Scrub the inode btrees for some AG. */
 STATIC int
-xfs_scrub_iallocbt(
-	struct xfs_scrub_context	*sc,
-	xfs_btnum_t			which)
+xchk_iallocbt(
+	struct xfs_scrub	*sc,
+	xfs_btnum_t		which)
 {
-	struct xfs_btree_cur		*cur;
-	struct xfs_owner_info		oinfo;
-	xfs_filblks_t			inode_blocks = 0;
-	int				error;
+	struct xfs_btree_cur	*cur;
+	struct xfs_owner_info	oinfo;
+	xfs_filblks_t		inode_blocks = 0;
+	int			error;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
 	cur = which == XFS_BTNUM_INO ? sc->sa.ino_cur : sc->sa.fino_cur;
-	error = xfs_scrub_btree(sc, cur, xfs_scrub_iallocbt_rec, &oinfo,
+	error = xchk_btree(sc, cur, xchk_iallocbt_rec, &oinfo,
 			&inode_blocks);
 	if (error)
 		return error;
 
-	xfs_scrub_iallocbt_xref_rmap_btreeblks(sc, which);
+	xchk_iallocbt_xref_rmap_btreeblks(sc, which);
 
 	/*
 	 * If we're scrubbing the inode btree, inode_blocks is the number of
@@ -452,64 +452,64 @@ xfs_scrub_iallocbt(
 	 * to inode chunks with free inodes.
 	 */
 	if (which == XFS_BTNUM_INO)
-		xfs_scrub_iallocbt_xref_rmap_inodes(sc, which, inode_blocks);
+		xchk_iallocbt_xref_rmap_inodes(sc, which, inode_blocks);
 
 	return error;
 }
 
 int
-xfs_scrub_inobt(
-	struct xfs_scrub_context	*sc)
+xchk_inobt(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_iallocbt(sc, XFS_BTNUM_INO);
+	return xchk_iallocbt(sc, XFS_BTNUM_INO);
 }
 
 int
-xfs_scrub_finobt(
-	struct xfs_scrub_context	*sc)
+xchk_finobt(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_iallocbt(sc, XFS_BTNUM_FINO);
+	return xchk_iallocbt(sc, XFS_BTNUM_FINO);
 }
 
 /* See if an inode btree has (or doesn't have) an inode chunk record. */
 static inline void
-xfs_scrub_xref_inode_check(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len,
-	struct xfs_btree_cur		**icur,
-	bool				should_have_inodes)
+xchk_xref_inode_check(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len,
+	struct xfs_btree_cur	**icur,
+	bool			should_have_inodes)
 {
-	bool				has_inodes;
-	int				error;
+	bool			has_inodes;
+	int			error;
 
-	if (!(*icur) || xfs_scrub_skip_xref(sc->sm))
+	if (!(*icur) || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_ialloc_has_inodes_at_extent(*icur, agbno, len, &has_inodes);
-	if (!xfs_scrub_should_check_xref(sc, &error, icur))
+	if (!xchk_should_check_xref(sc, &error, icur))
 		return;
 	if (has_inodes != should_have_inodes)
-		xfs_scrub_btree_xref_set_corrupt(sc, *icur, 0);
+		xchk_btree_xref_set_corrupt(sc, *icur, 0);
 }
 
 /* xref check that the extent is not covered by inodes */
 void
-xfs_scrub_xref_is_not_inode_chunk(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_xref_is_not_inode_chunk(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, false);
-	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, false);
+	xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, false);
+	xchk_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, false);
 }
 
 /* xref check that the extent is covered by inodes */
 void
-xfs_scrub_xref_is_inode_chunk(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_xref_is_inode_chunk(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, true);
+	xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, true);
 }
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 7a6208505980..5b3b177c0fc9 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -37,23 +37,23 @@
  * the goal.
  */
 int
-xfs_scrub_setup_inode(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_inode(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	int				error;
+	int			error;
 
 	/*
 	 * Try to get the inode.  If the verifiers fail, we try again
 	 * in raw mode.
 	 */
-	error = xfs_scrub_get_inode(sc, ip);
+	error = xchk_get_inode(sc, ip);
 	switch (error) {
 	case 0:
 		break;
 	case -EFSCORRUPTED:
 	case -EFSBADCRC:
-		return xfs_scrub_trans_alloc(sc, 0);
+		return xchk_trans_alloc(sc, 0);
 	default:
 		return error;
 	}
@@ -61,7 +61,7 @@ xfs_scrub_setup_inode(
 	/* Got the inode, lock it and we're ready to go. */
 	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	error = xfs_scrub_trans_alloc(sc, 0);
+	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -76,19 +76,19 @@ out:
 
 /* Validate di_extsize hint. */
 STATIC void
-xfs_scrub_inode_extsize(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags)
+xchk_inode_extsize(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags)
 {
-	xfs_failaddr_t			fa;
+	xfs_failaddr_t		fa;
 
 	fa = xfs_inode_validate_extsize(sc->mp, be32_to_cpu(dip->di_extsize),
 			mode, flags);
 	if (fa)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 }
 
 /*
@@ -98,33 +98,33 @@ xfs_scrub_inode_extsize(
  * These functions must be kept in sync with each other.
  */
 STATIC void
-xfs_scrub_inode_cowextsize(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags,
-	uint64_t			flags2)
+xchk_inode_cowextsize(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags,
+	uint64_t		flags2)
 {
-	xfs_failaddr_t			fa;
+	xfs_failaddr_t		fa;
 
 	fa = xfs_inode_validate_cowextsize(sc->mp,
 			be32_to_cpu(dip->di_cowextsize), mode, flags,
 			flags2);
 	if (fa)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Make sure the di_flags make sense for the inode. */
 STATIC void
-xfs_scrub_inode_flags(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags)
+xchk_inode_flags(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags)
 {
-	struct xfs_mount		*mp = sc->mp;
+	struct xfs_mount	*mp = sc->mp;
 
 	if (flags & ~XFS_DIFLAG_ANY)
 		goto bad;
@@ -157,20 +157,20 @@ xfs_scrub_inode_flags(
 
 	return;
 bad:
-	xfs_scrub_ino_set_corrupt(sc, ino);
+	xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Make sure the di_flags2 make sense for the inode. */
 STATIC void
-xfs_scrub_inode_flags2(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags,
-	uint64_t			flags2)
+xchk_inode_flags2(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags,
+	uint64_t		flags2)
 {
-	struct xfs_mount		*mp = sc->mp;
+	struct xfs_mount	*mp = sc->mp;
 
 	if (flags2 & ~XFS_DIFLAG2_ANY)
 		goto bad;
@@ -200,23 +200,23 @@ xfs_scrub_inode_flags2(
 
 	return;
 bad:
-	xfs_scrub_ino_set_corrupt(sc, ino);
+	xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Scrub all the ondisk inode fields. */
 STATIC void
-xfs_scrub_dinode(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino)
+xchk_dinode(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino)
 {
-	struct xfs_mount		*mp = sc->mp;
-	size_t				fork_recs;
-	unsigned long long		isize;
-	uint64_t			flags2;
-	uint32_t			nextents;
-	uint16_t			flags;
-	uint16_t			mode;
+	struct xfs_mount	*mp = sc->mp;
+	size_t			fork_recs;
+	unsigned long long	isize;
+	uint64_t		flags2;
+	uint32_t		nextents;
+	uint16_t		flags;
+	uint16_t		mode;
 
 	flags = be16_to_cpu(dip->di_flags);
 	if (dip->di_version >= 3)
@@ -237,7 +237,7 @@ xfs_scrub_dinode(
 		/* mode is recognized */
 		break;
 	default:
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 		break;
 	}
 
@@ -248,22 +248,22 @@ xfs_scrub_dinode(
 		 * We autoconvert v1 inodes into v2 inodes on writeout,
 		 * so just mark this inode for preening.
 		 */
-		xfs_scrub_ino_set_preen(sc, ino);
+		xchk_ino_set_preen(sc, ino);
 		break;
 	case 2:
 	case 3:
 		if (dip->di_onlink != 0)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 
 		if (dip->di_mode == 0 && sc->ip)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 
 		if (dip->di_projid_hi != 0 &&
 		    !xfs_sb_version_hasprojid32bit(&mp->m_sb))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	default:
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 		return;
 	}
 
@@ -273,40 +273,40 @@ xfs_scrub_dinode(
 	 */
 	if (dip->di_uid == cpu_to_be32(-1U) ||
 	    dip->di_gid == cpu_to_be32(-1U))
-		xfs_scrub_ino_set_warning(sc, ino);
+		xchk_ino_set_warning(sc, ino);
 
 	/* di_format */
 	switch (dip->di_format) {
 	case XFS_DINODE_FMT_DEV:
 		if (!S_ISCHR(mode) && !S_ISBLK(mode) &&
 		    !S_ISFIFO(mode) && !S_ISSOCK(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_LOCAL:
 		if (!S_ISDIR(mode) && !S_ISLNK(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
 		if (!S_ISREG(mode) && !S_ISDIR(mode) && !S_ISLNK(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (!S_ISREG(mode) && !S_ISDIR(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_UUID:
 	default:
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 		break;
 	}
 
 	/* di_[amc]time.nsec */
 	if (be32_to_cpu(dip->di_atime.t_nsec) >= NSEC_PER_SEC)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (be32_to_cpu(dip->di_mtime.t_nsec) >= NSEC_PER_SEC)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (be32_to_cpu(dip->di_ctime.t_nsec) >= NSEC_PER_SEC)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/*
 	 * di_size.  xfs_dinode_verify checks for things that screw up
@@ -315,19 +315,19 @@ xfs_scrub_dinode(
 	 */
 	isize = be64_to_cpu(dip->di_size);
 	if (isize & (1ULL << 63))
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* Devices, fifos, and sockets must have zero size */
 	if (!S_ISDIR(mode) && !S_ISREG(mode) && !S_ISLNK(mode) && isize != 0)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* Directories can't be larger than the data section size (32G) */
 	if (S_ISDIR(mode) && (isize == 0 || isize >= XFS_DIR2_SPACE_SIZE))
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* Symlinks can't be larger than SYMLINK_MAXLEN */
 	if (S_ISLNK(mode) && (isize == 0 || isize >= XFS_SYMLINK_MAXLEN))
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/*
 	 * Warn if the running kernel can't handle the kinds of offsets
@@ -336,7 +336,7 @@ xfs_scrub_dinode(
 	 * overly large offsets, flag the inode for admin review.
 	 */
 	if (isize >= mp->m_super->s_maxbytes)
-		xfs_scrub_ino_set_warning(sc, ino);
+		xchk_ino_set_warning(sc, ino);
 
 	/* di_nblocks */
 	if (flags2 & XFS_DIFLAG2_REFLINK) {
@@ -351,15 +351,15 @@ xfs_scrub_dinode(
 		 */
 		if (be64_to_cpu(dip->di_nblocks) >=
 		    mp->m_sb.sb_dblocks + mp->m_sb.sb_rblocks)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 	} else {
 		if (be64_to_cpu(dip->di_nblocks) >= mp->m_sb.sb_dblocks)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 	}
 
-	xfs_scrub_inode_flags(sc, dip, ino, mode, flags);
+	xchk_inode_flags(sc, dip, ino, mode, flags);
 
-	xfs_scrub_inode_extsize(sc, dip, ino, mode, flags);
+	xchk_inode_extsize(sc, dip, ino, mode, flags);
 
 	/* di_nextents */
 	nextents = be32_to_cpu(dip->di_nextents);
@@ -367,31 +367,31 @@ xfs_scrub_dinode(
 	switch (dip->di_format) {
 	case XFS_DINODE_FMT_EXTENTS:
 		if (nextents > fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (nextents <= fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	default:
 		if (nextents != 0)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	}
 
 	/* di_forkoff */
 	if (XFS_DFORK_APTR(dip) >= (char *)dip + mp->m_sb.sb_inodesize)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (dip->di_anextents != 0 && dip->di_forkoff == 0)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (dip->di_forkoff == 0 && dip->di_aformat != XFS_DINODE_FMT_EXTENTS)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* di_aformat */
 	if (dip->di_aformat != XFS_DINODE_FMT_LOCAL &&
 	    dip->di_aformat != XFS_DINODE_FMT_EXTENTS &&
 	    dip->di_aformat != XFS_DINODE_FMT_BTREE)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* di_anextents */
 	nextents = be16_to_cpu(dip->di_anextents);
@@ -399,22 +399,22 @@ xfs_scrub_dinode(
 	switch (dip->di_aformat) {
 	case XFS_DINODE_FMT_EXTENTS:
 		if (nextents > fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (nextents <= fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	default:
 		if (nextents != 0)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 	}
 
 	if (dip->di_version >= 3) {
 		if (be32_to_cpu(dip->di_crtime.t_nsec) >= NSEC_PER_SEC)
-			xfs_scrub_ino_set_corrupt(sc, ino);
-		xfs_scrub_inode_flags2(sc, dip, ino, mode, flags, flags2);
-		xfs_scrub_inode_cowextsize(sc, dip, ino, mode, flags,
+			xchk_ino_set_corrupt(sc, ino);
+		xchk_inode_flags2(sc, dip, ino, mode, flags, flags2);
+		xchk_inode_cowextsize(sc, dip, ino, mode, flags,
 				flags2);
 	}
 }
@@ -425,8 +425,8 @@ xfs_scrub_dinode(
  * IGET_UNTRUSTED, which checks the inobt for us.
  */
 static void
-xfs_scrub_inode_xref_finobt(
-	struct xfs_scrub_context	*sc,
+xchk_inode_xref_finobt(
+	struct xfs_scrub		*sc,
 	xfs_ino_t			ino)
 {
 	struct xfs_inobt_rec_incore	rec;
@@ -434,7 +434,7 @@ xfs_scrub_inode_xref_finobt(
 	int				has_record;
 	int				error;
 
-	if (!sc->sa.fino_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.fino_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	agino = XFS_INO_TO_AGINO(sc->mp, ino);
@@ -445,12 +445,12 @@ xfs_scrub_inode_xref_finobt(
 	 */
 	error = xfs_inobt_lookup(sc->sa.fino_cur, agino, XFS_LOOKUP_LE,
 			&has_record);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
 	    !has_record)
 		return;
 
 	error = xfs_inobt_get_rec(sc->sa.fino_cur, &rec, &has_record);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
 	    !has_record)
 		return;
 
@@ -463,54 +463,54 @@ xfs_scrub_inode_xref_finobt(
 		return;
 
 	if (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino))
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.fino_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.fino_cur, 0);
 }
 
 /* Cross reference the inode fields with the forks. */
 STATIC void
-xfs_scrub_inode_xref_bmap(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip)
+xchk_inode_xref_bmap(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip)
 {
-	xfs_extnum_t			nextents;
-	xfs_filblks_t			count;
-	xfs_filblks_t			acount;
-	int				error;
+	xfs_extnum_t		nextents;
+	xfs_filblks_t		count;
+	xfs_filblks_t		acount;
+	int			error;
 
-	if (xfs_scrub_skip_xref(sc->sm))
+	if (xchk_skip_xref(sc->sm))
 		return;
 
 	/* Walk all the extents to check nextents/naextents/nblocks. */
 	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
 			&nextents, &count);
-	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
+	if (!xchk_should_check_xref(sc, &error, NULL))
 		return;
 	if (nextents < be32_to_cpu(dip->di_nextents))
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 
 	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
 			&nextents, &acount);
-	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
+	if (!xchk_should_check_xref(sc, &error, NULL))
 		return;
 	if (nextents != be16_to_cpu(dip->di_anextents))
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 
 	/* Check nblocks against the inode. */
 	if (count + acount != be64_to_cpu(dip->di_nblocks))
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_inode_xref(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino,
-	struct xfs_dinode		*dip)
+xchk_inode_xref(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino,
+	struct xfs_dinode	*dip)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -518,18 +518,18 @@ xfs_scrub_inode_xref(
 	agno = XFS_INO_TO_AGNO(sc->mp, ino);
 	agbno = XFS_INO_TO_AGBNO(sc->mp, ino);
 
-	error = xfs_scrub_ag_init(sc, agno, &sc->sa);
-	if (!xfs_scrub_xref_process_error(sc, agno, agbno, &error))
+	error = xchk_ag_init(sc, agno, &sc->sa);
+	if (!xchk_xref_process_error(sc, agno, agbno, &error))
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_inode_xref_finobt(sc, ino);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_inode_xref_finobt(sc, ino);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
-	xfs_scrub_inode_xref_bmap(sc, dip);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
+	xchk_inode_xref_bmap(sc, dip);
 
-	xfs_scrub_ag_free(sc, &sc->sa);
+	xchk_ag_free(sc, &sc->sa);
 }
 
 /*
@@ -539,35 +539,35 @@ xfs_scrub_inode_xref(
  * reflink filesystem.
  */
 static void
-xfs_scrub_inode_check_reflink_iflag(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_inode_check_reflink_iflag(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
-	struct xfs_mount		*mp = sc->mp;
-	bool				has_shared;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	bool			has_shared;
+	int			error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return;
 
 	error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
 			&has_shared);
-	if (!xfs_scrub_xref_process_error(sc, XFS_INO_TO_AGNO(mp, ino),
+	if (!xchk_xref_process_error(sc, XFS_INO_TO_AGNO(mp, ino),
 			XFS_INO_TO_AGBNO(mp, ino), &error))
 		return;
 	if (xfs_is_reflink_inode(sc->ip) && !has_shared)
-		xfs_scrub_ino_set_preen(sc, ino);
+		xchk_ino_set_preen(sc, ino);
 	else if (!xfs_is_reflink_inode(sc->ip) && has_shared)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Scrub an inode. */
 int
-xfs_scrub_inode(
-	struct xfs_scrub_context	*sc)
+xchk_inode(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_dinode		di;
-	int				error = 0;
+	struct xfs_dinode	di;
+	int			error = 0;
 
 	/*
 	 * If sc->ip is NULL, that means that the setup function called
@@ -575,13 +575,13 @@ xfs_scrub_inode(
 	 * and a NULL inode, so flag the corruption error and return.
 	 */
 	if (!sc->ip) {
-		xfs_scrub_ino_set_corrupt(sc, sc->sm->sm_ino);
+		xchk_ino_set_corrupt(sc, sc->sm->sm_ino);
 		return 0;
 	}
 
 	/* Scrub the inode core. */
 	xfs_inode_to_disk(sc->ip, &di, 0);
-	xfs_scrub_dinode(sc, &di, sc->ip->i_ino);
+	xchk_dinode(sc, &di, sc->ip->i_ino);
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
@@ -591,9 +591,9 @@ xfs_scrub_inode(
 	 * we scrubbed the dinode.
 	 */
 	if (S_ISREG(VFS_I(sc->ip)->i_mode))
-		xfs_scrub_inode_check_reflink_iflag(sc, sc->ip->i_ino);
+		xchk_inode_check_reflink_iflag(sc, sc->ip->i_ino);
 
-	xfs_scrub_inode_xref(sc, sc->ip->i_ino, &di);
+	xchk_inode_xref(sc, sc->ip->i_ino, &di);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index e2bda58c32f0..1c9d7c7f64f5 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -27,36 +27,36 @@
 
 /* Set us up to scrub parents. */
 int
-xfs_scrub_setup_parent(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_parent(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Parent pointers */
 
 /* Look for an entry in a parent pointing to this inode. */
 
-struct xfs_scrub_parent_ctx {
-	struct dir_context		dc;
-	xfs_ino_t			ino;
-	xfs_nlink_t			nlink;
+struct xchk_parent_ctx {
+	struct dir_context	dc;
+	xfs_ino_t		ino;
+	xfs_nlink_t		nlink;
 };
 
 /* Look for a single entry in a directory pointing to an inode. */
 STATIC int
-xfs_scrub_parent_actor(
-	struct dir_context		*dc,
-	const char			*name,
-	int				namelen,
-	loff_t				pos,
-	u64				ino,
-	unsigned			type)
+xchk_parent_actor(
+	struct dir_context	*dc,
+	const char		*name,
+	int			namelen,
+	loff_t			pos,
+	u64			ino,
+	unsigned		type)
 {
-	struct xfs_scrub_parent_ctx	*spc;
+	struct xchk_parent_ctx	*spc;
 
-	spc = container_of(dc, struct xfs_scrub_parent_ctx, dc);
+	spc = container_of(dc, struct xchk_parent_ctx, dc);
 	if (spc->ino == ino)
 		spc->nlink++;
 	return 0;
@@ -64,21 +64,21 @@ xfs_scrub_parent_actor(
 
 /* Count the number of dentries in the parent dir that point to this inode. */
 STATIC int
-xfs_scrub_parent_count_parent_dentries(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*parent,
-	xfs_nlink_t			*nlink)
+xchk_parent_count_parent_dentries(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*parent,
+	xfs_nlink_t		*nlink)
 {
-	struct xfs_scrub_parent_ctx	spc = {
-		.dc.actor = xfs_scrub_parent_actor,
+	struct xchk_parent_ctx	spc = {
+		.dc.actor = xchk_parent_actor,
 		.dc.pos = 0,
 		.ino = sc->ip->i_ino,
 		.nlink = 0,
 	};
-	size_t				bufsize;
-	loff_t				oldpos;
-	uint				lock_mode;
-	int				error = 0;
+	size_t			bufsize;
+	loff_t			oldpos;
+	uint			lock_mode;
+	int			error = 0;
 
 	/*
 	 * If there are any blocks, read-ahead block 0 as we're almost
@@ -120,16 +120,16 @@ out:
  * entry pointing back to the inode being scrubbed.
  */
 STATIC int
-xfs_scrub_parent_validate(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			dnum,
-	bool				*try_again)
+xchk_parent_validate(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		dnum,
+	bool			*try_again)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*dp = NULL;
-	xfs_nlink_t			expected_nlink;
-	xfs_nlink_t			nlink;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*dp = NULL;
+	xfs_nlink_t		expected_nlink;
+	xfs_nlink_t		nlink;
+	int			error = 0;
 
 	*try_again = false;
 
@@ -138,7 +138,7 @@ xfs_scrub_parent_validate(
 
 	/* '..' must not point to ourselves. */
 	if (sc->ip->i_ino == dnum) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -165,13 +165,13 @@ xfs_scrub_parent_validate(
 	error = xfs_iget(mp, sc->tp, dnum, XFS_IGET_UNTRUSTED, 0, &dp);
 	if (error == -EINVAL) {
 		error = -EFSCORRUPTED;
-		xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error);
+		xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error);
 		goto out;
 	}
-	if (!xfs_scrub_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 	if (dp == sc->ip || !S_ISDIR(VFS_I(dp)->i_mode)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out_rele;
 	}
 
@@ -183,12 +183,12 @@ xfs_scrub_parent_validate(
 	 * the child inodes.
 	 */
 	if (xfs_ilock_nowait(dp, XFS_IOLOCK_SHARED)) {
-		error = xfs_scrub_parent_count_parent_dentries(sc, dp, &nlink);
-		if (!xfs_scrub_fblock_xref_process_error(sc, XFS_DATA_FORK, 0,
+		error = xchk_parent_count_parent_dentries(sc, dp, &nlink);
+		if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0,
 				&error))
 			goto out_unlock;
 		if (nlink != expected_nlink)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out_unlock;
 	}
 
@@ -200,18 +200,18 @@ xfs_scrub_parent_validate(
 	 */
 	xfs_iunlock(sc->ip, sc->ilock_flags);
 	sc->ilock_flags = 0;
-	error = xfs_scrub_ilock_inverted(dp, XFS_IOLOCK_SHARED);
+	error = xchk_ilock_inverted(dp, XFS_IOLOCK_SHARED);
 	if (error)
 		goto out_rele;
 
 	/* Go looking for our dentry. */
-	error = xfs_scrub_parent_count_parent_dentries(sc, dp, &nlink);
-	if (!xfs_scrub_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
+	error = xchk_parent_count_parent_dentries(sc, dp, &nlink);
+	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out_unlock;
 
 	/* Drop the parent lock, relock this inode. */
 	xfs_iunlock(dp, XFS_IOLOCK_SHARED);
-	error = xfs_scrub_ilock_inverted(sc->ip, XFS_IOLOCK_EXCL);
+	error = xchk_ilock_inverted(sc->ip, XFS_IOLOCK_EXCL);
 	if (error)
 		goto out_rele;
 	sc->ilock_flags = XFS_IOLOCK_EXCL;
@@ -225,43 +225,43 @@ xfs_scrub_parent_validate(
 
 	/* Look up '..' to see if the inode changed. */
 	error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &dnum, NULL);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out_rele;
 
 	/* Drat, parent changed.  Try again! */
 	if (dnum != dp->i_ino) {
-		iput(VFS_I(dp));
+		xfs_irele(dp);
 		*try_again = true;
 		return 0;
 	}
-	iput(VFS_I(dp));
+	xfs_irele(dp);
 
 	/*
 	 * '..' didn't change, so check that there was only one entry
 	 * for us in the parent.
 	 */
 	if (nlink != expected_nlink)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 	return error;
 
 out_unlock:
 	xfs_iunlock(dp, XFS_IOLOCK_SHARED);
 out_rele:
-	iput(VFS_I(dp));
+	xfs_irele(dp);
 out:
 	return error;
 }
 
 /* Scrub a parent pointer. */
 int
-xfs_scrub_parent(
-	struct xfs_scrub_context	*sc)
+xchk_parent(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	xfs_ino_t			dnum;
-	bool				try_again;
-	int				tries = 0;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_ino_t		dnum;
+	bool			try_again;
+	int			tries = 0;
+	int			error = 0;
 
 	/*
 	 * If we're a directory, check that the '..' link points up to
@@ -272,7 +272,7 @@ xfs_scrub_parent(
 
 	/* We're not a special inode, are we? */
 	if (!xfs_verify_dir_ino(mp, sc->ip->i_ino)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -288,10 +288,10 @@ xfs_scrub_parent(
 
 	/* Look up '..' */
 	error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &dnum, NULL);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 	if (!xfs_verify_dir_ino(mp, dnum)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -299,12 +299,12 @@ xfs_scrub_parent(
 	if (sc->ip == mp->m_rootip) {
 		if (sc->ip->i_ino != mp->m_sb.sb_rootino ||
 		    sc->ip->i_ino != dnum)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
 	do {
-		error = xfs_scrub_parent_validate(sc, dnum, &try_again);
+		error = xchk_parent_validate(sc, dnum, &try_again);
 		if (error)
 			goto out;
 	} while (try_again && ++tries < 20);
@@ -314,7 +314,7 @@ xfs_scrub_parent(
 	 * incomplete.  Userspace can decide if it wants to try again.
 	 */
 	if (try_again && tries == 20)
-		xfs_scrub_set_incomplete(sc);
+		xchk_set_incomplete(sc);
 out:
 	/*
 	 * If we failed to lock the parent inode even after a retry, just mark
@@ -322,7 +322,7 @@ out:
 	 */
 	if (sc->try_harder && error == -EDEADLOCK) {
 		error = 0;
-		xfs_scrub_set_incomplete(sc);
+		xchk_set_incomplete(sc);
 	}
 	return error;
 }
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 6ff906aa0a3b..782d582d3edd 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -30,8 +30,8 @@
 
 /* Convert a scrub type code to a DQ flag, or return 0 if error. */
 static inline uint
-xfs_scrub_quota_to_dqtype(
-	struct xfs_scrub_context	*sc)
+xchk_quota_to_dqtype(
+	struct xfs_scrub	*sc)
 {
 	switch (sc->sm->sm_type) {
 	case XFS_SCRUB_TYPE_UQUOTA:
@@ -47,24 +47,24 @@ xfs_scrub_quota_to_dqtype(
 
 /* Set us up to scrub a quota. */
 int
-xfs_scrub_setup_quota(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_quota(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	uint				dqtype;
-	int				error;
+	uint			dqtype;
+	int			error;
 
 	if (!XFS_IS_QUOTA_RUNNING(sc->mp) || !XFS_IS_QUOTA_ON(sc->mp))
 		return -ENOENT;
 
-	dqtype = xfs_scrub_quota_to_dqtype(sc);
+	dqtype = xchk_quota_to_dqtype(sc);
 	if (dqtype == 0)
 		return -EINVAL;
 	sc->has_quotaofflock = true;
 	mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock);
 	if (!xfs_this_quota_on(sc->mp, dqtype))
 		return -ENOENT;
-	error = xfs_scrub_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc, ip);
 	if (error)
 		return error;
 	sc->ip = xfs_quota_inode(sc->mp, dqtype);
@@ -75,35 +75,35 @@ xfs_scrub_setup_quota(
 
 /* Quotas. */
 
-struct xfs_scrub_quota_info {
-	struct xfs_scrub_context	*sc;
-	xfs_dqid_t			last_id;
+struct xchk_quota_info {
+	struct xfs_scrub	*sc;
+	xfs_dqid_t		last_id;
 };
 
 /* Scrub the fields in an individual quota item. */
 STATIC int
-xfs_scrub_quota_item(
-	struct xfs_dquot		*dq,
-	uint				dqtype,
-	void				*priv)
+xchk_quota_item(
+	struct xfs_dquot	*dq,
+	uint			dqtype,
+	void			*priv)
 {
-	struct xfs_scrub_quota_info	*sqi = priv;
-	struct xfs_scrub_context	*sc = sqi->sc;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_disk_dquot		*d = &dq->q_core;
-	struct xfs_quotainfo		*qi = mp->m_quotainfo;
-	xfs_fileoff_t			offset;
-	unsigned long long		bsoft;
-	unsigned long long		isoft;
-	unsigned long long		rsoft;
-	unsigned long long		bhard;
-	unsigned long long		ihard;
-	unsigned long long		rhard;
-	unsigned long long		bcount;
-	unsigned long long		icount;
-	unsigned long long		rcount;
-	xfs_ino_t			fs_icount;
-	xfs_dqid_t			id = be32_to_cpu(d->d_id);
+	struct xchk_quota_info	*sqi = priv;
+	struct xfs_scrub	*sc = sqi->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_disk_dquot	*d = &dq->q_core;
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	xfs_fileoff_t		offset;
+	unsigned long long	bsoft;
+	unsigned long long	isoft;
+	unsigned long long	rsoft;
+	unsigned long long	bhard;
+	unsigned long long	ihard;
+	unsigned long long	rhard;
+	unsigned long long	bcount;
+	unsigned long long	icount;
+	unsigned long long	rcount;
+	xfs_ino_t		fs_icount;
+	xfs_dqid_t		id = be32_to_cpu(d->d_id);
 
 	/*
 	 * Except for the root dquot, the actual dquot we got must either have
@@ -111,16 +111,16 @@ xfs_scrub_quota_item(
 	 */
 	offset = id / qi->qi_dqperchunk;
 	if (id && id <= sqi->last_id)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	sqi->last_id = id;
 
 	/* Did we get the dquot type we wanted? */
 	if (dqtype != (d->d_flags & XFS_DQ_ALLTYPES))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	if (d->d_pad0 != cpu_to_be32(0) || d->d_pad != cpu_to_be16(0))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/* Check the limits. */
 	bhard = be64_to_cpu(d->d_blk_hardlimit);
@@ -140,19 +140,19 @@ xfs_scrub_quota_item(
 	 * the hard limit.
 	 */
 	if (bhard > mp->m_sb.sb_dblocks)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (bsoft > bhard)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	if (ihard > mp->m_maxicount)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (isoft > ihard)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	if (rhard > mp->m_sb.sb_rblocks)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (rsoft > rhard)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/* Check the resource counts. */
 	bcount = be64_to_cpu(d->d_bcount);
@@ -167,15 +167,15 @@ xfs_scrub_quota_item(
 	 */
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
 		if (mp->m_sb.sb_dblocks < bcount)
-			xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK,
+			xchk_fblock_set_warning(sc, XFS_DATA_FORK,
 					offset);
 	} else {
 		if (mp->m_sb.sb_dblocks < bcount)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					offset);
 	}
 	if (icount > fs_icount || rcount > mp->m_sb.sb_rblocks)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/*
 	 * We can violate the hard limits if the admin suddenly sets a
@@ -183,29 +183,29 @@ xfs_scrub_quota_item(
 	 * admin review.
 	 */
 	if (id != 0 && bhard != 0 && bcount > bhard)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (id != 0 && ihard != 0 && icount > ihard)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (id != 0 && rhard != 0 && rcount > rhard)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 
 	return 0;
 }
 
 /* Check the quota's data fork. */
 STATIC int
-xfs_scrub_quota_data_fork(
-	struct xfs_scrub_context	*sc)
+xchk_quota_data_fork(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_bmbt_irec		irec = { 0 };
-	struct xfs_iext_cursor		icur;
-	struct xfs_quotainfo		*qi = sc->mp->m_quotainfo;
-	struct xfs_ifork		*ifp;
-	xfs_fileoff_t			max_dqid_off;
-	int				error = 0;
+	struct xfs_bmbt_irec	irec = { 0 };
+	struct xfs_iext_cursor	icur;
+	struct xfs_quotainfo	*qi = sc->mp->m_quotainfo;
+	struct xfs_ifork	*ifp;
+	xfs_fileoff_t		max_dqid_off;
+	int			error = 0;
 
 	/* Invoke the fork scrubber. */
-	error = xfs_scrub_metadata_inode_forks(sc);
+	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 
@@ -213,7 +213,7 @@ xfs_scrub_quota_data_fork(
 	max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk;
 	ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK);
 	for_each_xfs_iext(ifp, &icur, &irec) {
-		if (xfs_scrub_should_terminate(sc, &error))
+		if (xchk_should_terminate(sc, &error))
 			break;
 		/*
 		 * delalloc extents or blocks mapped above the highest
@@ -222,7 +222,7 @@ xfs_scrub_quota_data_fork(
 		if (isnullstartblock(irec.br_startblock) ||
 		    irec.br_startoff > max_dqid_off ||
 		    irec.br_startoff + irec.br_blockcount - 1 > max_dqid_off) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					irec.br_startoff);
 			break;
 		}
@@ -233,19 +233,19 @@ xfs_scrub_quota_data_fork(
 
 /* Scrub all of a quota type's items. */
 int
-xfs_scrub_quota(
-	struct xfs_scrub_context	*sc)
+xchk_quota(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_scrub_quota_info	sqi;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_quotainfo		*qi = mp->m_quotainfo;
-	uint				dqtype;
-	int				error = 0;
+	struct xchk_quota_info	sqi;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	uint			dqtype;
+	int			error = 0;
 
-	dqtype = xfs_scrub_quota_to_dqtype(sc);
+	dqtype = xchk_quota_to_dqtype(sc);
 
 	/* Look for problem extents. */
-	error = xfs_scrub_quota_data_fork(sc);
+	error = xchk_quota_data_fork(sc);
 	if (error)
 		goto out;
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -260,10 +260,10 @@ xfs_scrub_quota(
 	sc->ilock_flags = 0;
 	sqi.sc = sc;
 	sqi.last_id = 0;
-	error = xfs_qm_dqiterate(mp, dqtype, xfs_scrub_quota_item, &sqi);
+	error = xfs_qm_dqiterate(mp, dqtype, xchk_quota_item, &sqi);
 	sc->ilock_flags = XFS_ILOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK,
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK,
 			sqi.last_id * qi->qi_dqperchunk, &error))
 		goto out;
 
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 607a9faa8ecc..e8c82b026083 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -28,11 +28,11 @@
  * Set us up to scrub reference count btrees.
  */
 int
-xfs_scrub_setup_ag_refcountbt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_ag_refcountbt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, ip, false);
 }
 
 /* Reference count btree scrubber. */
@@ -73,22 +73,22 @@ xfs_scrub_setup_ag_refcountbt(
  * If the refcount is correct, all the check conditions in the algorithm
  * should always hold true.  If not, the refcount is incorrect.
  */
-struct xfs_scrub_refcnt_frag {
-	struct list_head		list;
-	struct xfs_rmap_irec		rm;
+struct xchk_refcnt_frag {
+	struct list_head	list;
+	struct xfs_rmap_irec	rm;
 };
 
-struct xfs_scrub_refcnt_check {
-	struct xfs_scrub_context	*sc;
-	struct list_head		fragments;
+struct xchk_refcnt_check {
+	struct xfs_scrub	*sc;
+	struct list_head	fragments;
 
 	/* refcount extent we're examining */
-	xfs_agblock_t			bno;
-	xfs_extlen_t			len;
-	xfs_nlink_t			refcount;
+	xfs_agblock_t		bno;
+	xfs_extlen_t		len;
+	xfs_nlink_t		refcount;
 
 	/* number of owners seen */
-	xfs_nlink_t			seen;
+	xfs_nlink_t		seen;
 };
 
 /*
@@ -99,18 +99,18 @@ struct xfs_scrub_refcnt_check {
  * fragments as the refcountbt says we should have.
  */
 STATIC int
-xfs_scrub_refcountbt_rmap_check(
+xchk_refcountbt_rmap_check(
 	struct xfs_btree_cur		*cur,
 	struct xfs_rmap_irec		*rec,
 	void				*priv)
 {
-	struct xfs_scrub_refcnt_check	*refchk = priv;
-	struct xfs_scrub_refcnt_frag	*frag;
+	struct xchk_refcnt_check	*refchk = priv;
+	struct xchk_refcnt_frag		*frag;
 	xfs_agblock_t			rm_last;
 	xfs_agblock_t			rc_last;
 	int				error = 0;
 
-	if (xfs_scrub_should_terminate(refchk->sc, &error))
+	if (xchk_should_terminate(refchk->sc, &error))
 		return error;
 
 	rm_last = rec->rm_startblock + rec->rm_blockcount - 1;
@@ -118,7 +118,7 @@ xfs_scrub_refcountbt_rmap_check(
 
 	/* Confirm that a single-owner refc extent is a CoW stage. */
 	if (refchk->refcount == 1 && rec->rm_owner != XFS_RMAP_OWN_COW) {
-		xfs_scrub_btree_xref_set_corrupt(refchk->sc, cur, 0);
+		xchk_btree_xref_set_corrupt(refchk->sc, cur, 0);
 		return 0;
 	}
 
@@ -135,7 +135,7 @@ xfs_scrub_refcountbt_rmap_check(
 		 * is healthy each rmap_irec we see will be in agbno order
 		 * so we don't need insertion sort here.
 		 */
-		frag = kmem_alloc(sizeof(struct xfs_scrub_refcnt_frag),
+		frag = kmem_alloc(sizeof(struct xchk_refcnt_frag),
 				KM_MAYFAIL);
 		if (!frag)
 			return -ENOMEM;
@@ -154,12 +154,12 @@ xfs_scrub_refcountbt_rmap_check(
  * we have a refcountbt error.
  */
 STATIC void
-xfs_scrub_refcountbt_process_rmap_fragments(
-	struct xfs_scrub_refcnt_check	*refchk)
+xchk_refcountbt_process_rmap_fragments(
+	struct xchk_refcnt_check	*refchk)
 {
 	struct list_head		worklist;
-	struct xfs_scrub_refcnt_frag	*frag;
-	struct xfs_scrub_refcnt_frag	*n;
+	struct xchk_refcnt_frag		*frag;
+	struct xchk_refcnt_frag		*n;
 	xfs_agblock_t			bno;
 	xfs_agblock_t			rbno;
 	xfs_agblock_t			next_rbno;
@@ -277,13 +277,13 @@ done:
 
 /* Use the rmap entries covering this extent to verify the refcount. */
 STATIC void
-xfs_scrub_refcountbt_xref_rmap(
-	struct xfs_scrub_context	*sc,
+xchk_refcountbt_xref_rmap(
+	struct xfs_scrub		*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	xfs_nlink_t			refcount)
 {
-	struct xfs_scrub_refcnt_check	refchk = {
+	struct xchk_refcnt_check	refchk = {
 		.sc = sc,
 		.bno = bno,
 		.len = len,
@@ -292,11 +292,11 @@ xfs_scrub_refcountbt_xref_rmap(
 	};
 	struct xfs_rmap_irec		low;
 	struct xfs_rmap_irec		high;
-	struct xfs_scrub_refcnt_frag	*frag;
-	struct xfs_scrub_refcnt_frag	*n;
+	struct xchk_refcnt_frag		*frag;
+	struct xchk_refcnt_frag		*n;
 	int				error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Cross-reference with the rmapbt to confirm the refcount. */
@@ -307,13 +307,13 @@ xfs_scrub_refcountbt_xref_rmap(
 
 	INIT_LIST_HEAD(&refchk.fragments);
 	error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high,
-			&xfs_scrub_refcountbt_rmap_check, &refchk);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+			&xchk_refcountbt_rmap_check, &refchk);
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		goto out_free;
 
-	xfs_scrub_refcountbt_process_rmap_fragments(&refchk);
+	xchk_refcountbt_process_rmap_fragments(&refchk);
 	if (refcount != refchk.seen)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 
 out_free:
 	list_for_each_entry_safe(frag, n, &refchk.fragments, list) {
@@ -324,34 +324,34 @@ out_free:
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_refcountbt_xref(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len,
-	xfs_nlink_t			refcount)
+xchk_refcountbt_xref(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len,
+	xfs_nlink_t		refcount)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, len);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
-	xfs_scrub_refcountbt_xref_rmap(sc, agbno, len, refcount);
+	xchk_xref_is_used_space(sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(sc, agbno, len);
+	xchk_refcountbt_xref_rmap(sc, agbno, len, refcount);
 }
 
 /* Scrub a refcountbt record. */
 STATIC int
-xfs_scrub_refcountbt_rec(
-	struct xfs_scrub_btree		*bs,
-	union xfs_btree_rec		*rec)
+xchk_refcountbt_rec(
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
-	xfs_agblock_t			*cow_blocks = bs->private;
-	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
-	xfs_agblock_t			bno;
-	xfs_extlen_t			len;
-	xfs_nlink_t			refcount;
-	bool				has_cowflag;
-	int				error = 0;
+	struct xfs_mount	*mp = bs->cur->bc_mp;
+	xfs_agblock_t		*cow_blocks = bs->private;
+	xfs_agnumber_t		agno = bs->cur->bc_private.a.agno;
+	xfs_agblock_t		bno;
+	xfs_extlen_t		len;
+	xfs_nlink_t		refcount;
+	bool			has_cowflag;
+	int			error = 0;
 
 	bno = be32_to_cpu(rec->refc.rc_startblock);
 	len = be32_to_cpu(rec->refc.rc_blockcount);
@@ -360,7 +360,7 @@ xfs_scrub_refcountbt_rec(
 	/* Only CoW records can have refcount == 1. */
 	has_cowflag = (bno & XFS_REFC_COW_START);
 	if ((refcount == 1 && !has_cowflag) || (refcount != 1 && has_cowflag))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	if (has_cowflag)
 		(*cow_blocks) += len;
 
@@ -369,75 +369,75 @@ xfs_scrub_refcountbt_rec(
 	if (bno + len <= bno ||
 	    !xfs_verify_agbno(mp, agno, bno) ||
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (refcount == 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xfs_scrub_refcountbt_xref(bs->sc, bno, len, refcount);
+	xchk_refcountbt_xref(bs->sc, bno, len, refcount);
 
 	return error;
 }
 
 /* Make sure we have as many refc blocks as the rmap says. */
 STATIC void
-xfs_scrub_refcount_xref_rmap(
-	struct xfs_scrub_context	*sc,
-	struct xfs_owner_info		*oinfo,
-	xfs_filblks_t			cow_blocks)
+xchk_refcount_xref_rmap(
+	struct xfs_scrub	*sc,
+	struct xfs_owner_info	*oinfo,
+	xfs_filblks_t		cow_blocks)
 {
-	xfs_extlen_t			refcbt_blocks = 0;
-	xfs_filblks_t			blocks;
-	int				error;
+	xfs_extlen_t		refcbt_blocks = 0;
+	xfs_filblks_t		blocks;
+	int			error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many refcbt blocks as the rmap knows about. */
 	error = xfs_btree_count_blocks(sc->sa.refc_cur, &refcbt_blocks);
-	if (!xfs_scrub_btree_process_error(sc, sc->sa.refc_cur, 0, &error))
+	if (!xchk_btree_process_error(sc, sc->sa.refc_cur, 0, &error))
 		return;
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != refcbt_blocks)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 
 	/* Check that we saw as many cow blocks as the rmap knows about. */
 	xfs_rmap_ag_owner(oinfo, XFS_RMAP_OWN_COW);
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != cow_blocks)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* Scrub the refcount btree for some AG. */
 int
-xfs_scrub_refcountbt(
-	struct xfs_scrub_context	*sc)
+xchk_refcountbt(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_agblock_t			cow_blocks = 0;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_agblock_t		cow_blocks = 0;
+	int			error;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_REFC);
-	error = xfs_scrub_btree(sc, sc->sa.refc_cur, xfs_scrub_refcountbt_rec,
+	error = xchk_btree(sc, sc->sa.refc_cur, xchk_refcountbt_rec,
 			&oinfo, &cow_blocks);
 	if (error)
 		return error;
 
-	xfs_scrub_refcount_xref_rmap(sc, &oinfo, cow_blocks);
+	xchk_refcount_xref_rmap(sc, &oinfo, cow_blocks);
 
 	return 0;
 }
 
 /* xref check that a cow staging extent is marked in the refcountbt. */
 void
-xfs_scrub_xref_is_cow_staging(
-	struct xfs_scrub_context	*sc,
+xchk_xref_is_cow_staging(
+	struct xfs_scrub		*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
@@ -446,35 +446,35 @@ xfs_scrub_xref_is_cow_staging(
 	int				has_refcount;
 	int				error;
 
-	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Find the CoW staging extent. */
 	error = xfs_refcount_lookup_le(sc->sa.refc_cur,
 			agbno + XFS_REFC_COW_START, &has_refcount);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (!has_refcount) {
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 		return;
 	}
 
 	error = xfs_refcount_get_rec(sc->sa.refc_cur, &rc, &has_refcount);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (!has_refcount) {
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 		return;
 	}
 
 	/* CoW flag must be set, refcount must be 1. */
 	has_cowflag = (rc.rc_startblock & XFS_REFC_COW_START);
 	if (!has_cowflag || rc.rc_refcount != 1)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 
 	/* Must be at least as long as what was passed in */
 	if (rc.rc_blockcount < len)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
 
 /*
@@ -482,20 +482,20 @@ xfs_scrub_xref_is_cow_staging(
  * can have multiple owners.
  */
 void
-xfs_scrub_xref_is_not_shared(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_xref_is_not_shared(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	bool				shared;
-	int				error;
+	bool			shared;
+	int			error;
 
-	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (shared)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 326be4e8b71e..17cf48564390 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -34,6 +34,7 @@
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/repair.h"
+#include "scrub/bitmap.h"
 
 /*
  * Attempt to repair some metadata, if the metadata is corrupt and userspace
@@ -41,21 +42,21 @@
  * and will set *fixed to true if it thinks it repaired anything.
  */
 int
-xfs_repair_attempt(
-	struct xfs_inode		*ip,
-	struct xfs_scrub_context	*sc,
-	bool				*fixed)
+xrep_attempt(
+	struct xfs_inode	*ip,
+	struct xfs_scrub	*sc,
+	bool			*fixed)
 {
-	int				error = 0;
+	int			error = 0;
 
-	trace_xfs_repair_attempt(ip, sc->sm, error);
+	trace_xrep_attempt(ip, sc->sm, error);
 
-	xfs_scrub_ag_btcur_free(&sc->sa);
+	xchk_ag_btcur_free(&sc->sa);
 
 	/* Repair whatever's broken. */
 	ASSERT(sc->ops->repair);
 	error = sc->ops->repair(sc);
-	trace_xfs_repair_done(ip, sc->sm, error);
+	trace_xrep_done(ip, sc->sm, error);
 	switch (error) {
 	case 0:
 		/*
@@ -93,8 +94,8 @@ xfs_repair_attempt(
  * structure to track rate limiting information.
  */
 void
-xfs_repair_failure(
-	struct xfs_mount		*mp)
+xrep_failure(
+	struct xfs_mount	*mp)
 {
 	xfs_alert_ratelimited(mp,
 "Corruption not fixed during online repair.  Unmount and run xfs_repair.");
@@ -105,12 +106,12 @@ xfs_repair_failure(
  * given mountpoint.
  */
 int
-xfs_repair_probe(
-	struct xfs_scrub_context	*sc)
+xrep_probe(
+	struct xfs_scrub	*sc)
 {
-	int				error = 0;
+	int			error = 0;
 
-	if (xfs_scrub_should_terminate(sc, &error))
+	if (xchk_should_terminate(sc, &error))
 		return error;
 
 	return 0;
@@ -121,15 +122,18 @@ xfs_repair_probe(
  * the btree cursors.
  */
 int
-xfs_repair_roll_ag_trans(
-	struct xfs_scrub_context	*sc)
+xrep_roll_ag_trans(
+	struct xfs_scrub	*sc)
 {
-	int				error;
+	int			error;
 
 	/* Keep the AG header buffers locked so we can keep going. */
-	xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
-	xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
-	xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
+	if (sc->sa.agi_bp)
+		xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
+	if (sc->sa.agfl_bp)
+		xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
 
 	/* Roll the transaction. */
 	error = xfs_trans_roll(&sc->tp);
@@ -137,9 +141,12 @@ xfs_repair_roll_ag_trans(
 		goto out_release;
 
 	/* Join AG headers to the new transaction. */
-	xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
-	xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
-	xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
+	if (sc->sa.agi_bp)
+		xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
+	if (sc->sa.agfl_bp)
+		xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
 
 	return 0;
 
@@ -149,9 +156,12 @@ out_release:
 	 * buffers will be released during teardown on our way out
 	 * of the kernel.
 	 */
-	xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp);
-	xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp);
-	xfs_trans_bhold_release(sc->tp, sc->sa.agfl_bp);
+	if (sc->sa.agi_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp);
+	if (sc->sa.agfl_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agfl_bp);
 
 	return error;
 }
@@ -162,10 +172,10 @@ out_release:
  * in AG reservations) to construct a whole btree.
  */
 bool
-xfs_repair_ag_has_space(
-	struct xfs_perag		*pag,
-	xfs_extlen_t			nr_blocks,
-	enum xfs_ag_resv_type		type)
+xrep_ag_has_space(
+	struct xfs_perag	*pag,
+	xfs_extlen_t		nr_blocks,
+	enum xfs_ag_resv_type	type)
 {
 	return  !xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) &&
 		!xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA) &&
@@ -178,8 +188,8 @@ xfs_repair_ag_has_space(
  * any type of per-AG btree.
  */
 xfs_extlen_t
-xfs_repair_calc_ag_resblks(
-	struct xfs_scrub_context	*sc)
+xrep_calc_ag_resblks(
+	struct xfs_scrub		*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_scrub_metadata	*sm = sc->sm;
@@ -231,7 +241,7 @@ xfs_repair_calc_ag_resblks(
 	}
 	xfs_perag_put(pag);
 
-	trace_xfs_repair_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
+	trace_xrep_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
 			freelen, usedlen);
 
 	/*
@@ -270,7 +280,7 @@ xfs_repair_calc_ag_resblks(
 		rmapbt_sz = 0;
 	}
 
-	trace_xfs_repair_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
+	trace_xrep_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
 			inobt_sz, rmapbt_sz, refcbt_sz);
 
 	return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz));
@@ -278,15 +288,15 @@ xfs_repair_calc_ag_resblks(
 
 /* Allocate a block in an AG. */
 int
-xfs_repair_alloc_ag_block(
-	struct xfs_scrub_context	*sc,
-	struct xfs_owner_info		*oinfo,
-	xfs_fsblock_t			*fsbno,
-	enum xfs_ag_resv_type		resv)
+xrep_alloc_ag_block(
+	struct xfs_scrub	*sc,
+	struct xfs_owner_info	*oinfo,
+	xfs_fsblock_t		*fsbno,
+	enum xfs_ag_resv_type	resv)
 {
-	struct xfs_alloc_arg		args = {0};
-	xfs_agblock_t			bno;
-	int				error;
+	struct xfs_alloc_arg	args = {0};
+	xfs_agblock_t		bno;
+	int			error;
 
 	switch (resv) {
 	case XFS_AG_RESV_AGFL:
@@ -329,8 +339,8 @@ xfs_repair_alloc_ag_block(
 
 /* Initialize a new AG btree root block with zero entries. */
 int
-xfs_repair_init_btblock(
-	struct xfs_scrub_context	*sc,
+xrep_init_btblock(
+	struct xfs_scrub		*sc,
 	xfs_fsblock_t			fsb,
 	struct xfs_buf			**bpp,
 	xfs_btnum_t			btnum,
@@ -340,7 +350,7 @@ xfs_repair_init_btblock(
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_buf			*bp;
 
-	trace_xfs_repair_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb),
+	trace_xrep_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb),
 			XFS_FSB_TO_AGBNO(mp, fsb), btnum);
 
 	ASSERT(XFS_FSB_TO_AGNO(mp, fsb) == sc->sa.agno);
@@ -367,222 +377,29 @@ xfs_repair_init_btblock(
  *
  * However, that leaves the matter of removing all the metadata describing the
  * old broken structure.  For primary metadata we use the rmap data to collect
- * every extent with a matching rmap owner (exlist); we then iterate all other
+ * every extent with a matching rmap owner (bitmap); we then iterate all other
  * metadata structures with the same rmap owner to collect the extents that
- * cannot be removed (sublist).  We then subtract sublist from exlist to
+ * cannot be removed (sublist).  We then subtract sublist from bitmap to
  * derive the blocks that were used by the old btree.  These blocks can be
  * reaped.
  *
  * For rmapbt reconstructions we must use different tactics for extent
  * collection.  First we iterate all primary metadata (this excludes the old
  * rmapbt, obviously) to generate new rmap records.  The gaps in the rmap
- * records are collected as exlist.  The bnobt records are collected as
- * sublist.  As with the other btrees we subtract sublist from exlist, and the
+ * records are collected as bitmap.  The bnobt records are collected as
+ * sublist.  As with the other btrees we subtract sublist from bitmap, and the
  * result (since the rmapbt lives in the free space) are the blocks from the
  * old rmapbt.
- */
-
-/* Collect a dead btree extent for later disposal. */
-int
-xfs_repair_collect_btree_extent(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist,
-	xfs_fsblock_t			fsbno,
-	xfs_extlen_t			len)
-{
-	struct xfs_repair_extent	*rex;
-
-	trace_xfs_repair_collect_btree_extent(sc->mp,
-			XFS_FSB_TO_AGNO(sc->mp, fsbno),
-			XFS_FSB_TO_AGBNO(sc->mp, fsbno), len);
-
-	rex = kmem_alloc(sizeof(struct xfs_repair_extent), KM_MAYFAIL);
-	if (!rex)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&rex->list);
-	rex->fsbno = fsbno;
-	rex->len = len;
-	list_add_tail(&rex->list, &exlist->list);
-
-	return 0;
-}
-
-/*
- * An error happened during the rebuild so the transaction will be cancelled.
- * The fs will shut down, and the administrator has to unmount and run repair.
- * Therefore, free all the memory associated with the list so we can die.
- */
-void
-xfs_repair_cancel_btree_extents(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist)
-{
-	struct xfs_repair_extent	*rex;
-	struct xfs_repair_extent	*n;
-
-	for_each_xfs_repair_extent_safe(rex, n, exlist) {
-		list_del(&rex->list);
-		kmem_free(rex);
-	}
-}
-
-/* Compare two btree extents. */
-static int
-xfs_repair_btree_extent_cmp(
-	void				*priv,
-	struct list_head		*a,
-	struct list_head		*b)
-{
-	struct xfs_repair_extent	*ap;
-	struct xfs_repair_extent	*bp;
-
-	ap = container_of(a, struct xfs_repair_extent, list);
-	bp = container_of(b, struct xfs_repair_extent, list);
-
-	if (ap->fsbno > bp->fsbno)
-		return 1;
-	if (ap->fsbno < bp->fsbno)
-		return -1;
-	return 0;
-}
-
-/*
- * Remove all the blocks mentioned in @sublist from the extents in @exlist.
  *
- * The intent is that callers will iterate the rmapbt for all of its records
- * for a given owner to generate @exlist; and iterate all the blocks of the
- * metadata structures that are not being rebuilt and have the same rmapbt
- * owner to generate @sublist.  This routine subtracts all the extents
- * mentioned in sublist from all the extents linked in @exlist, which leaves
- * @exlist as the list of blocks that are not accounted for, which we assume
- * are the dead blocks of the old metadata structure.  The blocks mentioned in
- * @exlist can be reaped.
- */
-#define LEFT_ALIGNED	(1 << 0)
-#define RIGHT_ALIGNED	(1 << 1)
-int
-xfs_repair_subtract_extents(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist,
-	struct xfs_repair_extent_list	*sublist)
-{
-	struct list_head		*lp;
-	struct xfs_repair_extent	*ex;
-	struct xfs_repair_extent	*newex;
-	struct xfs_repair_extent	*subex;
-	xfs_fsblock_t			sub_fsb;
-	xfs_extlen_t			sub_len;
-	int				state;
-	int				error = 0;
-
-	if (list_empty(&exlist->list) || list_empty(&sublist->list))
-		return 0;
-	ASSERT(!list_empty(&sublist->list));
-
-	list_sort(NULL, &exlist->list, xfs_repair_btree_extent_cmp);
-	list_sort(NULL, &sublist->list, xfs_repair_btree_extent_cmp);
-
-	/*
-	 * Now that we've sorted both lists, we iterate exlist once, rolling
-	 * forward through sublist and/or exlist as necessary until we find an
-	 * overlap or reach the end of either list.  We do not reset lp to the
-	 * head of exlist nor do we reset subex to the head of sublist.  The
-	 * list traversal is similar to merge sort, but we're deleting
-	 * instead.  In this manner we avoid O(n^2) operations.
-	 */
-	subex = list_first_entry(&sublist->list, struct xfs_repair_extent,
-			list);
-	lp = exlist->list.next;
-	while (lp != &exlist->list) {
-		ex = list_entry(lp, struct xfs_repair_extent, list);
-
-		/*
-		 * Advance subex and/or ex until we find a pair that
-		 * intersect or we run out of extents.
-		 */
-		while (subex->fsbno + subex->len <= ex->fsbno) {
-			if (list_is_last(&subex->list, &sublist->list))
-				goto out;
-			subex = list_next_entry(subex, list);
-		}
-		if (subex->fsbno >= ex->fsbno + ex->len) {
-			lp = lp->next;
-			continue;
-		}
-
-		/* trim subex to fit the extent we have */
-		sub_fsb = subex->fsbno;
-		sub_len = subex->len;
-		if (subex->fsbno < ex->fsbno) {
-			sub_len -= ex->fsbno - subex->fsbno;
-			sub_fsb = ex->fsbno;
-		}
-		if (sub_len > ex->len)
-			sub_len = ex->len;
-
-		state = 0;
-		if (sub_fsb == ex->fsbno)
-			state |= LEFT_ALIGNED;
-		if (sub_fsb + sub_len == ex->fsbno + ex->len)
-			state |= RIGHT_ALIGNED;
-		switch (state) {
-		case LEFT_ALIGNED:
-			/* Coincides with only the left. */
-			ex->fsbno += sub_len;
-			ex->len -= sub_len;
-			break;
-		case RIGHT_ALIGNED:
-			/* Coincides with only the right. */
-			ex->len -= sub_len;
-			lp = lp->next;
-			break;
-		case LEFT_ALIGNED | RIGHT_ALIGNED:
-			/* Total overlap, just delete ex. */
-			lp = lp->next;
-			list_del(&ex->list);
-			kmem_free(ex);
-			break;
-		case 0:
-			/*
-			 * Deleting from the middle: add the new right extent
-			 * and then shrink the left extent.
-			 */
-			newex = kmem_alloc(sizeof(struct xfs_repair_extent),
-					KM_MAYFAIL);
-			if (!newex) {
-				error = -ENOMEM;
-				goto out;
-			}
-			INIT_LIST_HEAD(&newex->list);
-			newex->fsbno = sub_fsb + sub_len;
-			newex->len = ex->fsbno + ex->len - newex->fsbno;
-			list_add(&newex->list, &ex->list);
-			ex->len = sub_fsb - ex->fsbno;
-			lp = lp->next;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
-	}
-
-out:
-	return error;
-}
-#undef LEFT_ALIGNED
-#undef RIGHT_ALIGNED
-
-/*
  * Disposal of Blocks from Old per-AG Btrees
  *
  * Now that we've constructed a new btree to replace the damaged one, we want
  * to dispose of the blocks that (we think) the old btree was using.
- * Previously, we used the rmapbt to collect the extents (exlist) with the
+ * Previously, we used the rmapbt to collect the extents (bitmap) with the
  * rmap owner corresponding to the tree we rebuilt, collected extents for any
  * blocks with the same rmap owner that are owned by another data structure
- * (sublist), and subtracted sublist from exlist.  In theory the extents
- * remaining in exlist are the old btree's blocks.
+ * (sublist), and subtracted sublist from bitmap.  In theory the extents
+ * remaining in bitmap are the old btree's blocks.
  *
  * Unfortunately, it's possible that the btree was crosslinked with other
  * blocks on disk.  The rmap data can tell us if there are multiple owners, so
@@ -598,7 +415,7 @@ out:
  * If there are no rmap records at all, we also free the block.  If the btree
  * being rebuilt lives in the free space (bnobt/cntbt/rmapbt) then there isn't
  * supposed to be a rmap record and everything is ok.  For other btrees there
- * had to have been an rmap entry for the block to have ended up on @exlist,
+ * had to have been an rmap entry for the block to have ended up on @bitmap,
  * so if it's gone now there's something wrong and the fs will shut down.
  *
  * Note: If there are multiple rmap records with only the same rmap owner as
@@ -611,7 +428,7 @@ out:
  * The caller is responsible for locking the AG headers for the entire rebuild
  * operation so that nothing else can sneak in and change the AG state while
  * we're not looking.  We also assume that the caller already invalidated any
- * buffers associated with @exlist.
+ * buffers associated with @bitmap.
  */
 
 /*
@@ -619,15 +436,14 @@ out:
  * is not intended for use with file data repairs; we have bunmapi for that.
  */
 int
-xfs_repair_invalidate_blocks(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist)
+xrep_invalidate_blocks(
+	struct xfs_scrub	*sc,
+	struct xfs_bitmap	*bitmap)
 {
-	struct xfs_repair_extent	*rex;
-	struct xfs_repair_extent	*n;
-	struct xfs_buf			*bp;
-	xfs_fsblock_t			fsbno;
-	xfs_agblock_t			i;
+	struct xfs_bitmap_range	*bmr;
+	struct xfs_bitmap_range	*n;
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsbno;
 
 	/*
 	 * For each block in each extent, see if there's an incore buffer for
@@ -637,18 +453,16 @@ xfs_repair_invalidate_blocks(
 	 * because we never own those; and if we can't TRYLOCK the buffer we
 	 * assume it's owned by someone else.
 	 */
-	for_each_xfs_repair_extent_safe(rex, n, exlist) {
-		for (fsbno = rex->fsbno, i = rex->len; i > 0; fsbno++, i--) {
-			/* Skip AG headers and post-EOFS blocks */
-			if (!xfs_verify_fsbno(sc->mp, fsbno))
-				continue;
-			bp = xfs_buf_incore(sc->mp->m_ddev_targp,
-					XFS_FSB_TO_DADDR(sc->mp, fsbno),
-					XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
-			if (bp) {
-				xfs_trans_bjoin(sc->tp, bp);
-				xfs_trans_binval(sc->tp, bp);
-			}
+	for_each_xfs_bitmap_block(fsbno, bmr, n, bitmap) {
+		/* Skip AG headers and post-EOFS blocks */
+		if (!xfs_verify_fsbno(sc->mp, fsbno))
+			continue;
+		bp = xfs_buf_incore(sc->mp->m_ddev_targp,
+				XFS_FSB_TO_DADDR(sc->mp, fsbno),
+				XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
+		if (bp) {
+			xfs_trans_bjoin(sc->tp, bp);
+			xfs_trans_binval(sc->tp, bp);
 		}
 	}
 
@@ -657,11 +471,11 @@ xfs_repair_invalidate_blocks(
 
 /* Ensure the freelist is the correct size. */
 int
-xfs_repair_fix_freelist(
-	struct xfs_scrub_context	*sc,
-	bool				can_shrink)
+xrep_fix_freelist(
+	struct xfs_scrub	*sc,
+	bool			can_shrink)
 {
-	struct xfs_alloc_arg		args = {0};
+	struct xfs_alloc_arg	args = {0};
 
 	args.mp = sc->mp;
 	args.tp = sc->tp;
@@ -677,15 +491,15 @@ xfs_repair_fix_freelist(
  * Put a block back on the AGFL.
  */
 STATIC int
-xfs_repair_put_freelist(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno)
+xrep_put_freelist(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno)
 {
-	struct xfs_owner_info		oinfo;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	int			error;
 
 	/* Make sure there's space on the freelist. */
-	error = xfs_repair_fix_freelist(sc, true);
+	error = xrep_fix_freelist(sc, true);
 	if (error)
 		return error;
 
@@ -711,20 +525,20 @@ xfs_repair_put_freelist(
 	return 0;
 }
 
-/* Dispose of a single metadata block. */
+/* Dispose of a single block. */
 STATIC int
-xfs_repair_dispose_btree_block(
-	struct xfs_scrub_context	*sc,
-	xfs_fsblock_t			fsbno,
-	struct xfs_owner_info		*oinfo,
-	enum xfs_ag_resv_type		resv)
+xrep_reap_block(
+	struct xfs_scrub	*sc,
+	xfs_fsblock_t		fsbno,
+	struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type	resv)
 {
-	struct xfs_btree_cur		*cur;
-	struct xfs_buf			*agf_bp = NULL;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	bool				has_other_rmap;
-	int				error;
+	struct xfs_btree_cur	*cur;
+	struct xfs_buf		*agf_bp = NULL;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	bool			has_other_rmap;
+	int			error;
 
 	agno = XFS_FSB_TO_AGNO(sc->mp, fsbno);
 	agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno);
@@ -747,9 +561,9 @@ xfs_repair_dispose_btree_block(
 
 	/* Can we find any other rmappings? */
 	error = xfs_rmap_has_other_keys(cur, agbno, 1, oinfo, &has_other_rmap);
+	xfs_btree_del_cursor(cur, error);
 	if (error)
-		goto out_cur;
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+		goto out_free;
 
 	/*
 	 * If there are other rmappings, this block is cross linked and must
@@ -767,7 +581,7 @@ xfs_repair_dispose_btree_block(
 	if (has_other_rmap)
 		error = xfs_rmap_free(sc->tp, agf_bp, agno, agbno, 1, oinfo);
 	else if (resv == XFS_AG_RESV_AGFL)
-		error = xfs_repair_put_freelist(sc, agbno);
+		error = xrep_put_freelist(sc, agbno);
 	else
 		error = xfs_free_extent(sc->tp, fsbno, 1, oinfo, resv);
 	if (agf_bp != sc->sa.agf_bp)
@@ -777,50 +591,43 @@ xfs_repair_dispose_btree_block(
 
 	if (sc->ip)
 		return xfs_trans_roll_inode(&sc->tp, sc->ip);
-	return xfs_repair_roll_ag_trans(sc);
+	return xrep_roll_ag_trans(sc);
 
-out_cur:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+out_free:
 	if (agf_bp != sc->sa.agf_bp)
 		xfs_trans_brelse(sc->tp, agf_bp);
 	return error;
 }
 
-/* Dispose of btree blocks from an old per-AG btree. */
+/* Dispose of every block of every extent in the bitmap. */
 int
-xfs_repair_reap_btree_extents(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist,
-	struct xfs_owner_info		*oinfo,
-	enum xfs_ag_resv_type		type)
+xrep_reap_extents(
+	struct xfs_scrub	*sc,
+	struct xfs_bitmap	*bitmap,
+	struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type	type)
 {
-	struct xfs_repair_extent	*rex;
-	struct xfs_repair_extent	*n;
-	int				error = 0;
+	struct xfs_bitmap_range	*bmr;
+	struct xfs_bitmap_range	*n;
+	xfs_fsblock_t		fsbno;
+	int			error = 0;
 
 	ASSERT(xfs_sb_version_hasrmapbt(&sc->mp->m_sb));
 
-	/* Dispose of every block from the old btree. */
-	for_each_xfs_repair_extent_safe(rex, n, exlist) {
+	for_each_xfs_bitmap_block(fsbno, bmr, n, bitmap) {
 		ASSERT(sc->ip != NULL ||
-		       XFS_FSB_TO_AGNO(sc->mp, rex->fsbno) == sc->sa.agno);
+		       XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.agno);
+		trace_xrep_dispose_btree_extent(sc->mp,
+				XFS_FSB_TO_AGNO(sc->mp, fsbno),
+				XFS_FSB_TO_AGBNO(sc->mp, fsbno), 1);
 
-		trace_xfs_repair_dispose_btree_extent(sc->mp,
-				XFS_FSB_TO_AGNO(sc->mp, rex->fsbno),
-				XFS_FSB_TO_AGBNO(sc->mp, rex->fsbno), rex->len);
-
-		for (; rex->len > 0; rex->len--, rex->fsbno++) {
-			error = xfs_repair_dispose_btree_block(sc, rex->fsbno,
-					oinfo, type);
-			if (error)
-				goto out;
-		}
-		list_del(&rex->list);
-		kmem_free(rex);
+		error = xrep_reap_block(sc, fsbno, oinfo, type);
+		if (error)
+			goto out;
 	}
 
 out:
-	xfs_repair_cancel_btree_extents(sc, exlist);
+	xfs_bitmap_destroy(bitmap);
 	return error;
 }
 
@@ -832,12 +639,12 @@ out:
  * btree roots.  This is not guaranteed to work if the AG is heavily damaged
  * or the rmap data are corrupt.
  *
- * Callers of xfs_repair_find_ag_btree_roots must lock the AGF and AGFL
+ * Callers of xrep_find_ag_btree_roots must lock the AGF and AGFL
  * buffers if the AGF is being rebuilt; or the AGF and AGI buffers if the
  * AGI is being rebuilt.  It must maintain these locks until it's safe for
  * other threads to change the btrees' shapes.  The caller provides
  * information about the btrees to look for by passing in an array of
- * xfs_repair_find_ag_btree with the (rmap owner, buf_ops, magic) fields set.
+ * xrep_find_ag_btree with the (rmap owner, buf_ops, magic) fields set.
  * The (root, height) fields will be set on return if anything is found.  The
  * last element of the array should have a NULL buf_ops to mark the end of the
  * array.
@@ -851,30 +658,30 @@ out:
  * should be the roots.
  */
 
-struct xfs_repair_findroot {
-	struct xfs_scrub_context	*sc;
+struct xrep_findroot {
+	struct xfs_scrub		*sc;
 	struct xfs_buf			*agfl_bp;
 	struct xfs_agf			*agf;
-	struct xfs_repair_find_ag_btree	*btree_info;
+	struct xrep_find_ag_btree	*btree_info;
 };
 
 /* See if our block is in the AGFL. */
 STATIC int
-xfs_repair_findroot_agfl_walk(
-	struct xfs_mount		*mp,
-	xfs_agblock_t			bno,
-	void				*priv)
+xrep_findroot_agfl_walk(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		bno,
+	void			*priv)
 {
-	xfs_agblock_t			*agbno = priv;
+	xfs_agblock_t		*agbno = priv;
 
 	return (*agbno == bno) ? XFS_BTREE_QUERY_RANGE_ABORT : 0;
 }
 
 /* Does this block match the btree information passed in? */
 STATIC int
-xfs_repair_findroot_block(
-	struct xfs_repair_findroot	*ri,
-	struct xfs_repair_find_ag_btree	*fab,
+xrep_findroot_block(
+	struct xrep_findroot		*ri,
+	struct xrep_find_ag_btree	*fab,
 	uint64_t			owner,
 	xfs_agblock_t			agbno,
 	bool				*found_it)
@@ -895,7 +702,7 @@ xfs_repair_findroot_block(
 	 */
 	if (owner == XFS_RMAP_OWN_AG) {
 		error = xfs_agfl_walk(mp, ri->agf, ri->agfl_bp,
-				xfs_repair_findroot_agfl_walk, &agbno);
+				xrep_findroot_agfl_walk, &agbno);
 		if (error == XFS_BTREE_QUERY_RANGE_ABORT)
 			return 0;
 		if (error)
@@ -933,7 +740,7 @@ xfs_repair_findroot_block(
 	fab->height = xfs_btree_get_level(btblock) + 1;
 	*found_it = true;
 
-	trace_xfs_repair_findroot_block(mp, ri->sc->sa.agno, agbno,
+	trace_xrep_findroot_block(mp, ri->sc->sa.agno, agbno,
 			be32_to_cpu(btblock->bb_magic), fab->height - 1);
 out:
 	xfs_trans_brelse(ri->sc->tp, bp);
@@ -945,13 +752,13 @@ out:
  * looking for?
  */
 STATIC int
-xfs_repair_findroot_rmap(
+xrep_findroot_rmap(
 	struct xfs_btree_cur		*cur,
 	struct xfs_rmap_irec		*rec,
 	void				*priv)
 {
-	struct xfs_repair_findroot	*ri = priv;
-	struct xfs_repair_find_ag_btree	*fab;
+	struct xrep_findroot		*ri = priv;
+	struct xrep_find_ag_btree	*fab;
 	xfs_agblock_t			b;
 	bool				found_it;
 	int				error = 0;
@@ -966,7 +773,7 @@ xfs_repair_findroot_rmap(
 		for (fab = ri->btree_info; fab->buf_ops; fab++) {
 			if (rec->rm_owner != fab->rmap_owner)
 				continue;
-			error = xfs_repair_findroot_block(ri, fab,
+			error = xrep_findroot_block(ri, fab,
 					rec->rm_owner, rec->rm_startblock + b,
 					&found_it);
 			if (error)
@@ -981,15 +788,15 @@ xfs_repair_findroot_rmap(
 
 /* Find the roots of the per-AG btrees described in btree_info. */
 int
-xfs_repair_find_ag_btree_roots(
-	struct xfs_scrub_context	*sc,
+xrep_find_ag_btree_roots(
+	struct xfs_scrub		*sc,
 	struct xfs_buf			*agf_bp,
-	struct xfs_repair_find_ag_btree	*btree_info,
+	struct xrep_find_ag_btree	*btree_info,
 	struct xfs_buf			*agfl_bp)
 {
 	struct xfs_mount		*mp = sc->mp;
-	struct xfs_repair_findroot	ri;
-	struct xfs_repair_find_ag_btree	*fab;
+	struct xrep_findroot		ri;
+	struct xrep_find_ag_btree	*fab;
 	struct xfs_btree_cur		*cur;
 	int				error;
 
@@ -1008,19 +815,19 @@ xfs_repair_find_ag_btree_roots(
 	}
 
 	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
-	error = xfs_rmap_query_all(cur, xfs_repair_findroot_rmap, &ri);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	error = xfs_rmap_query_all(cur, xrep_findroot_rmap, &ri);
+	xfs_btree_del_cursor(cur, error);
 
 	return error;
 }
 
 /* Force a quotacheck the next time we mount. */
 void
-xfs_repair_force_quotacheck(
-	struct xfs_scrub_context	*sc,
-	uint				dqtype)
+xrep_force_quotacheck(
+	struct xfs_scrub	*sc,
+	uint			dqtype)
 {
-	uint				flag;
+	uint			flag;
 
 	flag = xfs_quota_chkd_flag(dqtype);
 	if (!(flag & sc->mp->m_qflags))
@@ -1044,10 +851,10 @@ xfs_repair_force_quotacheck(
  * repair corruptions in the quota metadata.
  */
 int
-xfs_repair_ino_dqattach(
-	struct xfs_scrub_context	*sc)
+xrep_ino_dqattach(
+	struct xfs_scrub	*sc)
 {
-	int				error;
+	int			error;
 
 	error = xfs_qm_dqattach_locked(sc->ip, false);
 	switch (error) {
@@ -1058,11 +865,11 @@ xfs_repair_ino_dqattach(
 "inode %llu repair encountered quota error %d, quotacheck forced.",
 				(unsigned long long)sc->ip->i_ino, error);
 		if (XFS_IS_UQUOTA_ON(sc->mp) && !sc->ip->i_udquot)
-			xfs_repair_force_quotacheck(sc, XFS_DQ_USER);
+			xrep_force_quotacheck(sc, XFS_DQ_USER);
 		if (XFS_IS_GQUOTA_ON(sc->mp) && !sc->ip->i_gdquot)
-			xfs_repair_force_quotacheck(sc, XFS_DQ_GROUP);
+			xrep_force_quotacheck(sc, XFS_DQ_GROUP);
 		if (XFS_IS_PQUOTA_ON(sc->mp) && !sc->ip->i_pdquot)
-			xfs_repair_force_quotacheck(sc, XFS_DQ_PROJ);
+			xrep_force_quotacheck(sc, XFS_DQ_PROJ);
 		/* fall through */
 	case -ESRCH:
 		error = 0;
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index ef47826b6725..9de321eee4ab 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -6,7 +6,7 @@
 #ifndef __XFS_SCRUB_REPAIR_H__
 #define __XFS_SCRUB_REPAIR_H__
 
-static inline int xfs_repair_notsupported(struct xfs_scrub_context *sc)
+static inline int xrep_notsupported(struct xfs_scrub *sc)
 {
 	return -EOPNOTSUPP;
 }
@@ -15,55 +15,26 @@ static inline int xfs_repair_notsupported(struct xfs_scrub_context *sc)
 
 /* Repair helpers */
 
-int xfs_repair_attempt(struct xfs_inode *ip, struct xfs_scrub_context *sc,
-		bool *fixed);
-void xfs_repair_failure(struct xfs_mount *mp);
-int xfs_repair_roll_ag_trans(struct xfs_scrub_context *sc);
-bool xfs_repair_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
+int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub *sc, bool *fixed);
+void xrep_failure(struct xfs_mount *mp);
+int xrep_roll_ag_trans(struct xfs_scrub *sc);
+bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
 		enum xfs_ag_resv_type type);
-xfs_extlen_t xfs_repair_calc_ag_resblks(struct xfs_scrub_context *sc);
-int xfs_repair_alloc_ag_block(struct xfs_scrub_context *sc,
-		struct xfs_owner_info *oinfo, xfs_fsblock_t *fsbno,
-		enum xfs_ag_resv_type resv);
-int xfs_repair_init_btblock(struct xfs_scrub_context *sc, xfs_fsblock_t fsb,
+xfs_extlen_t xrep_calc_ag_resblks(struct xfs_scrub *sc);
+int xrep_alloc_ag_block(struct xfs_scrub *sc, struct xfs_owner_info *oinfo,
+		xfs_fsblock_t *fsbno, enum xfs_ag_resv_type resv);
+int xrep_init_btblock(struct xfs_scrub *sc, xfs_fsblock_t fsb,
 		struct xfs_buf **bpp, xfs_btnum_t btnum,
 		const struct xfs_buf_ops *ops);
 
-struct xfs_repair_extent {
-	struct list_head		list;
-	xfs_fsblock_t			fsbno;
-	xfs_extlen_t			len;
-};
-
-struct xfs_repair_extent_list {
-	struct list_head		list;
-};
-
-static inline void
-xfs_repair_init_extent_list(
-	struct xfs_repair_extent_list	*exlist)
-{
-	INIT_LIST_HEAD(&exlist->list);
-}
+struct xfs_bitmap;
 
-#define for_each_xfs_repair_extent_safe(rbe, n, exlist) \
-	list_for_each_entry_safe((rbe), (n), &(exlist)->list, list)
-int xfs_repair_collect_btree_extent(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *btlist, xfs_fsblock_t fsbno,
-		xfs_extlen_t len);
-void xfs_repair_cancel_btree_extents(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *btlist);
-int xfs_repair_subtract_extents(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *exlist,
-		struct xfs_repair_extent_list *sublist);
-int xfs_repair_fix_freelist(struct xfs_scrub_context *sc, bool can_shrink);
-int xfs_repair_invalidate_blocks(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *btlist);
-int xfs_repair_reap_btree_extents(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *exlist,
+int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink);
+int xrep_invalidate_blocks(struct xfs_scrub *sc, struct xfs_bitmap *btlist);
+int xrep_reap_extents(struct xfs_scrub *sc, struct xfs_bitmap *exlist,
 		struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
 
-struct xfs_repair_find_ag_btree {
+struct xrep_find_ag_btree {
 	/* in: rmap owner of the btree we're looking for */
 	uint64_t			rmap_owner;
 
@@ -78,40 +49,44 @@ struct xfs_repair_find_ag_btree {
 	unsigned int			height;
 };
 
-int xfs_repair_find_ag_btree_roots(struct xfs_scrub_context *sc,
-		struct xfs_buf *agf_bp,
-		struct xfs_repair_find_ag_btree *btree_info,
-		struct xfs_buf *agfl_bp);
-void xfs_repair_force_quotacheck(struct xfs_scrub_context *sc, uint dqtype);
-int xfs_repair_ino_dqattach(struct xfs_scrub_context *sc);
+int xrep_find_ag_btree_roots(struct xfs_scrub *sc, struct xfs_buf *agf_bp,
+		struct xrep_find_ag_btree *btree_info, struct xfs_buf *agfl_bp);
+void xrep_force_quotacheck(struct xfs_scrub *sc, uint dqtype);
+int xrep_ino_dqattach(struct xfs_scrub *sc);
 
 /* Metadata repairers */
 
-int xfs_repair_probe(struct xfs_scrub_context *sc);
-int xfs_repair_superblock(struct xfs_scrub_context *sc);
+int xrep_probe(struct xfs_scrub *sc);
+int xrep_superblock(struct xfs_scrub *sc);
+int xrep_agf(struct xfs_scrub *sc);
+int xrep_agfl(struct xfs_scrub *sc);
+int xrep_agi(struct xfs_scrub *sc);
 
 #else
 
-static inline int xfs_repair_attempt(
-	struct xfs_inode		*ip,
-	struct xfs_scrub_context	*sc,
-	bool				*fixed)
+static inline int xrep_attempt(
+	struct xfs_inode	*ip,
+	struct xfs_scrub	*sc,
+	bool			*fixed)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline void xfs_repair_failure(struct xfs_mount *mp) {}
+static inline void xrep_failure(struct xfs_mount *mp) {}
 
 static inline xfs_extlen_t
-xfs_repair_calc_ag_resblks(
-	struct xfs_scrub_context	*sc)
+xrep_calc_ag_resblks(
+	struct xfs_scrub	*sc)
 {
 	ASSERT(!(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR));
 	return 0;
 }
 
-#define xfs_repair_probe		xfs_repair_notsupported
-#define xfs_repair_superblock		xfs_repair_notsupported
+#define xrep_probe			xrep_notsupported
+#define xrep_superblock			xrep_notsupported
+#define xrep_agf			xrep_notsupported
+#define xrep_agfl			xrep_notsupported
+#define xrep_agi			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index c6d763236ba7..5e293c129813 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -29,30 +29,30 @@
  * Set us up to scrub reverse mapping btrees.
  */
 int
-xfs_scrub_setup_ag_rmapbt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_ag_rmapbt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, ip, false);
 }
 
 /* Reverse-mapping scrubber. */
 
 /* Cross-reference a rmap against the refcount btree. */
 STATIC void
-xfs_scrub_rmapbt_xref_refc(
-	struct xfs_scrub_context	*sc,
-	struct xfs_rmap_irec		*irec)
+xchk_rmapbt_xref_refc(
+	struct xfs_scrub	*sc,
+	struct xfs_rmap_irec	*irec)
 {
-	xfs_agblock_t			fbno;
-	xfs_extlen_t			flen;
-	bool				non_inode;
-	bool				is_bmbt;
-	bool				is_attr;
-	bool				is_unwritten;
-	int				error;
-
-	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	bool			non_inode;
+	bool			is_bmbt;
+	bool			is_attr;
+	bool			is_unwritten;
+	int			error;
+
+	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	non_inode = XFS_RMAP_NON_INODE_OWNER(irec->rm_owner);
@@ -63,58 +63,58 @@ xfs_scrub_rmapbt_xref_refc(
 	/* If this is shared, must be a data fork extent. */
 	error = xfs_refcount_find_shared(sc->sa.refc_cur, irec->rm_startblock,
 			irec->rm_blockcount, &fbno, &flen, false);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (flen != 0 && (non_inode || is_attr || is_bmbt || is_unwritten))
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_rmapbt_xref(
-	struct xfs_scrub_context	*sc,
-	struct xfs_rmap_irec		*irec)
+xchk_rmapbt_xref(
+	struct xfs_scrub	*sc,
+	struct xfs_rmap_irec	*irec)
 {
-	xfs_agblock_t			agbno = irec->rm_startblock;
-	xfs_extlen_t			len = irec->rm_blockcount;
+	xfs_agblock_t		agbno = irec->rm_startblock;
+	xfs_extlen_t		len = irec->rm_blockcount;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, len);
+	xchk_xref_is_used_space(sc, agbno, len);
 	if (irec->rm_owner == XFS_RMAP_OWN_INODES)
-		xfs_scrub_xref_is_inode_chunk(sc, agbno, len);
+		xchk_xref_is_inode_chunk(sc, agbno, len);
 	else
-		xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
+		xchk_xref_is_not_inode_chunk(sc, agbno, len);
 	if (irec->rm_owner == XFS_RMAP_OWN_COW)
-		xfs_scrub_xref_is_cow_staging(sc, irec->rm_startblock,
+		xchk_xref_is_cow_staging(sc, irec->rm_startblock,
 				irec->rm_blockcount);
 	else
-		xfs_scrub_rmapbt_xref_refc(sc, irec);
+		xchk_rmapbt_xref_refc(sc, irec);
 }
 
 /* Scrub an rmapbt record. */
 STATIC int
-xfs_scrub_rmapbt_rec(
-	struct xfs_scrub_btree		*bs,
-	union xfs_btree_rec		*rec)
+xchk_rmapbt_rec(
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
-	struct xfs_rmap_irec		irec;
-	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
-	bool				non_inode;
-	bool				is_unwritten;
-	bool				is_bmbt;
-	bool				is_attr;
-	int				error;
+	struct xfs_mount	*mp = bs->cur->bc_mp;
+	struct xfs_rmap_irec	irec;
+	xfs_agnumber_t		agno = bs->cur->bc_private.a.agno;
+	bool			non_inode;
+	bool			is_unwritten;
+	bool			is_bmbt;
+	bool			is_attr;
+	int			error;
 
 	error = xfs_rmap_btrec_to_irec(rec, &irec);
-	if (!xfs_scrub_btree_process_error(bs->sc, bs->cur, 0, &error))
+	if (!xchk_btree_process_error(bs->sc, bs->cur, 0, &error))
 		goto out;
 
 	/* Check extent. */
 	if (irec.rm_startblock + irec.rm_blockcount <= irec.rm_startblock)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (irec.rm_owner == XFS_RMAP_OWN_FS) {
 		/*
@@ -124,7 +124,7 @@ xfs_scrub_rmapbt_rec(
 		 */
 		if (irec.rm_startblock != 0 ||
 		    irec.rm_blockcount != XFS_AGFL_BLOCK(mp) + 1)
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	} else {
 		/*
 		 * Otherwise we must point somewhere past the static metadata
@@ -133,7 +133,7 @@ xfs_scrub_rmapbt_rec(
 		if (!xfs_verify_agbno(mp, agno, irec.rm_startblock) ||
 		    !xfs_verify_agbno(mp, agno, irec.rm_startblock +
 				irec.rm_blockcount - 1))
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	}
 
 	/* Check flags. */
@@ -143,105 +143,105 @@ xfs_scrub_rmapbt_rec(
 	is_unwritten = irec.rm_flags & XFS_RMAP_UNWRITTEN;
 
 	if (is_bmbt && irec.rm_offset != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (non_inode && irec.rm_offset != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (is_unwritten && (is_bmbt || non_inode || is_attr))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (non_inode && (is_bmbt || is_unwritten || is_attr))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (!non_inode) {
 		if (!xfs_verify_ino(mp, irec.rm_owner))
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	} else {
 		/* Non-inode owner within the magic values? */
 		if (irec.rm_owner <= XFS_RMAP_OWN_MIN ||
 		    irec.rm_owner > XFS_RMAP_OWN_FS)
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	}
 
-	xfs_scrub_rmapbt_xref(bs->sc, &irec);
+	xchk_rmapbt_xref(bs->sc, &irec);
 out:
 	return error;
 }
 
 /* Scrub the rmap btree for some AG. */
 int
-xfs_scrub_rmapbt(
-	struct xfs_scrub_context	*sc)
+xchk_rmapbt(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
+	struct xfs_owner_info	oinfo;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
-	return xfs_scrub_btree(sc, sc->sa.rmap_cur, xfs_scrub_rmapbt_rec,
+	return xchk_btree(sc, sc->sa.rmap_cur, xchk_rmapbt_rec,
 			&oinfo, NULL);
 }
 
 /* xref check that the extent is owned by a given owner */
 static inline void
-xfs_scrub_xref_check_owner(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	struct xfs_owner_info		*oinfo,
-	bool				should_have_rmap)
+xchk_xref_check_owner(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo,
+	bool			should_have_rmap)
 {
-	bool				has_rmap;
-	int				error;
+	bool			has_rmap;
+	int			error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_rmap_record_exists(sc->sa.rmap_cur, bno, len, oinfo,
 			&has_rmap);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (has_rmap != should_have_rmap)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* xref check that the extent is owned by a given owner */
 void
-xfs_scrub_xref_is_owned_by(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	struct xfs_owner_info		*oinfo)
+xchk_xref_is_owned_by(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo)
 {
-	xfs_scrub_xref_check_owner(sc, bno, len, oinfo, true);
+	xchk_xref_check_owner(sc, bno, len, oinfo, true);
 }
 
 /* xref check that the extent is not owned by a given owner */
 void
-xfs_scrub_xref_is_not_owned_by(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	struct xfs_owner_info		*oinfo)
+xchk_xref_is_not_owned_by(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo)
 {
-	xfs_scrub_xref_check_owner(sc, bno, len, oinfo, false);
+	xchk_xref_check_owner(sc, bno, len, oinfo, false);
 }
 
 /* xref check that the extent has no reverse mapping at all */
 void
-xfs_scrub_xref_has_no_owner(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len)
+xchk_xref_has_no_owner(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len)
 {
-	bool				has_rmap;
-	int				error;
+	bool			has_rmap;
+	int			error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_rmap_has_record(sc->sa.rmap_cur, bno, len, &has_rmap);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (has_rmap)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 1f86e02a07ca..665d4bbb17cc 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -25,13 +25,13 @@
 
 /* Set us up with the realtime metadata locked. */
 int
-xfs_scrub_setup_rt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_rt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	int				error;
+	int			error;
 
-	error = xfs_scrub_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc, ip);
 	if (error)
 		return error;
 
@@ -46,14 +46,14 @@ xfs_scrub_setup_rt(
 
 /* Scrub a free extent record from the realtime bitmap. */
 STATIC int
-xfs_scrub_rtbitmap_rec(
-	struct xfs_trans		*tp,
-	struct xfs_rtalloc_rec		*rec,
-	void				*priv)
+xchk_rtbitmap_rec(
+	struct xfs_trans	*tp,
+	struct xfs_rtalloc_rec	*rec,
+	void			*priv)
 {
-	struct xfs_scrub_context	*sc = priv;
-	xfs_rtblock_t			startblock;
-	xfs_rtblock_t			blockcount;
+	struct xfs_scrub	*sc = priv;
+	xfs_rtblock_t		startblock;
+	xfs_rtblock_t		blockcount;
 
 	startblock = rec->ar_startext * tp->t_mountp->m_sb.sb_rextsize;
 	blockcount = rec->ar_extcount * tp->t_mountp->m_sb.sb_rextsize;
@@ -61,24 +61,24 @@ xfs_scrub_rtbitmap_rec(
 	if (startblock + blockcount <= startblock ||
 	    !xfs_verify_rtbno(sc->mp, startblock) ||
 	    !xfs_verify_rtbno(sc->mp, startblock + blockcount - 1))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 	return 0;
 }
 
 /* Scrub the realtime bitmap. */
 int
-xfs_scrub_rtbitmap(
-	struct xfs_scrub_context	*sc)
+xchk_rtbitmap(
+	struct xfs_scrub	*sc)
 {
-	int				error;
+	int			error;
 
 	/* Invoke the fork scrubber. */
-	error = xfs_scrub_metadata_inode_forks(sc);
+	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 
-	error = xfs_rtalloc_query_all(sc->tp, xfs_scrub_rtbitmap_rec, sc);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	error = xfs_rtalloc_query_all(sc->tp, xchk_rtbitmap_rec, sc);
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 
 out:
@@ -87,13 +87,13 @@ out:
 
 /* Scrub the realtime summary. */
 int
-xfs_scrub_rtsummary(
-	struct xfs_scrub_context	*sc)
+xchk_rtsummary(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_inode		*rsumip = sc->mp->m_rsumip;
-	struct xfs_inode		*old_ip = sc->ip;
-	uint				old_ilock_flags = sc->ilock_flags;
-	int				error = 0;
+	struct xfs_inode	*rsumip = sc->mp->m_rsumip;
+	struct xfs_inode	*old_ip = sc->ip;
+	uint			old_ilock_flags = sc->ilock_flags;
+	int			error = 0;
 
 	/*
 	 * We ILOCK'd the rt bitmap ip in the setup routine, now lock the
@@ -107,12 +107,12 @@ xfs_scrub_rtsummary(
 	xfs_ilock(sc->ip, sc->ilock_flags);
 
 	/* Invoke the fork scrubber. */
-	error = xfs_scrub_metadata_inode_forks(sc);
+	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		goto out;
 
 	/* XXX: implement this some day */
-	xfs_scrub_set_incomplete(sc);
+	xchk_set_incomplete(sc);
 out:
 	/* Switch back to the rtbitmap inode and lock flags. */
 	xfs_iunlock(sc->ip, sc->ilock_flags);
@@ -124,18 +124,18 @@ out:
 
 /* xref check that the extent is not free in the rtbitmap */
 void
-xfs_scrub_xref_is_used_rt_space(
-	struct xfs_scrub_context	*sc,
-	xfs_rtblock_t			fsbno,
-	xfs_extlen_t			len)
+xchk_xref_is_used_rt_space(
+	struct xfs_scrub	*sc,
+	xfs_rtblock_t		fsbno,
+	xfs_extlen_t		len)
 {
-	xfs_rtblock_t			startext;
-	xfs_rtblock_t			endext;
-	xfs_rtblock_t			extcount;
-	bool				is_free;
-	int				error;
+	xfs_rtblock_t		startext;
+	xfs_rtblock_t		endext;
+	xfs_rtblock_t		extcount;
+	bool			is_free;
+	int			error;
 
-	if (xfs_scrub_skip_xref(sc->sm))
+	if (xchk_skip_xref(sc->sm))
 		return;
 
 	startext = fsbno;
@@ -147,10 +147,10 @@ xfs_scrub_xref_is_used_rt_space(
 	xfs_ilock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 	error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, startext, extcount,
 			&is_free);
-	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
+	if (!xchk_should_check_xref(sc, &error, NULL))
 		goto out_unlock;
 	if (is_free)
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
 out_unlock:
 	xfs_iunlock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 }
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 58ae76b3a421..4bfae1e61d30 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -131,6 +131,12 @@
  * optimize the structure so that the rebuild knows what to do.  The
  * second check evaluates the completeness of the repair; that is what
  * is reported to userspace.
+ *
+ * A quick note on symbol prefixes:
+ * - "xfs_" are general XFS symbols.
+ * - "xchk_" are symbols related to metadata checking.
+ * - "xrep_" are symbols related to metadata repair.
+ * - "xfs_scrub_" are symbols that tie online fsck to the rest of XFS.
  */
 
 /*
@@ -144,12 +150,12 @@
  * supported by the running kernel.
  */
 static int
-xfs_scrub_probe(
-	struct xfs_scrub_context	*sc)
+xchk_probe(
+	struct xfs_scrub	*sc)
 {
-	int				error = 0;
+	int			error = 0;
 
-	if (xfs_scrub_should_terminate(sc, &error))
+	if (xchk_should_terminate(sc, &error))
 		return error;
 
 	return 0;
@@ -159,12 +165,12 @@ xfs_scrub_probe(
 
 /* Free all the resources and finish the transactions. */
 STATIC int
-xfs_scrub_teardown(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip_in,
-	int				error)
+xchk_teardown(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip_in,
+	int			error)
 {
-	xfs_scrub_ag_free(sc, &sc->sa);
+	xchk_ag_free(sc, &sc->sa);
 	if (sc->tp) {
 		if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
 			error = xfs_trans_commit(sc->tp);
@@ -177,7 +183,7 @@ xfs_scrub_teardown(
 			xfs_iunlock(sc->ip, sc->ilock_flags);
 		if (sc->ip != ip_in &&
 		    !xfs_internal_inum(sc->mp, sc->ip->i_ino))
-			iput(VFS_I(sc->ip));
+			xfs_irele(sc->ip);
 		sc->ip = NULL;
 	}
 	if (sc->has_quotaofflock)
@@ -191,165 +197,165 @@ xfs_scrub_teardown(
 
 /* Scrubbing dispatch. */
 
-static const struct xfs_scrub_meta_ops meta_scrub_ops[] = {
+static const struct xchk_meta_ops meta_scrub_ops[] = {
 	[XFS_SCRUB_TYPE_PROBE] = {	/* ioctl presence test */
 		.type	= ST_NONE,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_probe,
-		.repair = xfs_repair_probe,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_probe,
+		.repair = xrep_probe,
 	},
 	[XFS_SCRUB_TYPE_SB] = {		/* superblock */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_superblock,
-		.repair	= xfs_repair_superblock,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_superblock,
+		.repair	= xrep_superblock,
 	},
 	[XFS_SCRUB_TYPE_AGF] = {	/* agf */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_agf,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_agf,
+		.repair	= xrep_agf,
 	},
 	[XFS_SCRUB_TYPE_AGFL]= {	/* agfl */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_agfl,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_agfl,
+		.repair	= xrep_agfl,
 	},
 	[XFS_SCRUB_TYPE_AGI] = {	/* agi */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_agi,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_agi,
+		.repair	= xrep_agi,
 	},
 	[XFS_SCRUB_TYPE_BNOBT] = {	/* bnobt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_allocbt,
-		.scrub	= xfs_scrub_bnobt,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_ag_allocbt,
+		.scrub	= xchk_bnobt,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_CNTBT] = {	/* cntbt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_allocbt,
-		.scrub	= xfs_scrub_cntbt,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_ag_allocbt,
+		.scrub	= xchk_cntbt,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INOBT] = {	/* inobt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_iallocbt,
-		.scrub	= xfs_scrub_inobt,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_ag_iallocbt,
+		.scrub	= xchk_inobt,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_FINOBT] = {	/* finobt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_iallocbt,
-		.scrub	= xfs_scrub_finobt,
+		.setup	= xchk_setup_ag_iallocbt,
+		.scrub	= xchk_finobt,
 		.has	= xfs_sb_version_hasfinobt,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RMAPBT] = {	/* rmapbt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_rmapbt,
-		.scrub	= xfs_scrub_rmapbt,
+		.setup	= xchk_setup_ag_rmapbt,
+		.scrub	= xchk_rmapbt,
 		.has	= xfs_sb_version_hasrmapbt,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_REFCNTBT] = {	/* refcountbt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_refcountbt,
-		.scrub	= xfs_scrub_refcountbt,
+		.setup	= xchk_setup_ag_refcountbt,
+		.scrub	= xchk_refcountbt,
 		.has	= xfs_sb_version_hasreflink,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INODE] = {	/* inode record */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode,
-		.scrub	= xfs_scrub_inode,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_inode,
+		.scrub	= xchk_inode,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTD] = {	/* inode data fork */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode_bmap,
-		.scrub	= xfs_scrub_bmap_data,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_inode_bmap,
+		.scrub	= xchk_bmap_data,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTA] = {	/* inode attr fork */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode_bmap,
-		.scrub	= xfs_scrub_bmap_attr,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_inode_bmap,
+		.scrub	= xchk_bmap_attr,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTC] = {	/* inode CoW fork */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode_bmap,
-		.scrub	= xfs_scrub_bmap_cow,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_inode_bmap,
+		.scrub	= xchk_bmap_cow,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_DIR] = {	/* directory */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_directory,
-		.scrub	= xfs_scrub_directory,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_directory,
+		.scrub	= xchk_directory,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_XATTR] = {	/* extended attributes */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_xattr,
-		.scrub	= xfs_scrub_xattr,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_xattr,
+		.scrub	= xchk_xattr,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_SYMLINK] = {	/* symbolic link */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_symlink,
-		.scrub	= xfs_scrub_symlink,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_symlink,
+		.scrub	= xchk_symlink,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PARENT] = {	/* parent pointers */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_parent,
-		.scrub	= xfs_scrub_parent,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_parent,
+		.scrub	= xchk_parent,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_rt,
-		.scrub	= xfs_scrub_rtbitmap,
+		.setup	= xchk_setup_rt,
+		.scrub	= xchk_rtbitmap,
 		.has	= xfs_sb_version_hasrealtime,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_rt,
-		.scrub	= xfs_scrub_rtsummary,
+		.setup	= xchk_setup_rt,
+		.scrub	= xchk_rtsummary,
 		.has	= xfs_sb_version_hasrealtime,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_UQUOTA] = {	/* user quota */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_quota,
-		.scrub	= xfs_scrub_quota,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_quota,
+		.scrub	= xchk_quota,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_GQUOTA] = {	/* group quota */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_quota,
-		.scrub	= xfs_scrub_quota,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_quota,
+		.scrub	= xchk_quota,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PQUOTA] = {	/* project quota */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_quota,
-		.scrub	= xfs_scrub_quota,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_quota,
+		.scrub	= xchk_quota,
+		.repair	= xrep_notsupported,
 	},
 };
 
 /* This isn't a stable feature, warn once per day. */
 static inline void
-xfs_scrub_experimental_warning(
+xchk_experimental_warning(
 	struct xfs_mount	*mp)
 {
 	static struct ratelimit_state scrub_warning = RATELIMIT_STATE_INIT(
-			"xfs_scrub_warning", 86400 * HZ, 1);
+			"xchk_warning", 86400 * HZ, 1);
 	ratelimit_set_flags(&scrub_warning, RATELIMIT_MSG_ON_RELEASE);
 
 	if (__ratelimit(&scrub_warning))
@@ -358,12 +364,12 @@ xfs_scrub_experimental_warning(
 }
 
 static int
-xfs_scrub_validate_inputs(
+xchk_validate_inputs(
 	struct xfs_mount		*mp,
 	struct xfs_scrub_metadata	*sm)
 {
 	int				error;
-	const struct xfs_scrub_meta_ops	*ops;
+	const struct xchk_meta_ops	*ops;
 
 	error = -EINVAL;
 	/* Check our inputs. */
@@ -441,7 +447,7 @@ out:
 }
 
 #ifdef CONFIG_XFS_ONLINE_REPAIR
-static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+static inline void xchk_postmortem(struct xfs_scrub *sc)
 {
 	/*
 	 * Userspace asked us to repair something, we repaired it, rescanned
@@ -451,10 +457,10 @@ static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
 	if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
 	    (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
 				 XFS_SCRUB_OFLAG_XCORRUPT)))
-		xfs_repair_failure(sc->mp);
+		xrep_failure(sc->mp);
 }
 #else
-static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+static inline void xchk_postmortem(struct xfs_scrub *sc)
 {
 	/*
 	 * Userspace asked us to scrub something, it's broken, and we have no
@@ -473,16 +479,16 @@ xfs_scrub_metadata(
 	struct xfs_inode		*ip,
 	struct xfs_scrub_metadata	*sm)
 {
-	struct xfs_scrub_context	sc;
+	struct xfs_scrub		sc;
 	struct xfs_mount		*mp = ip->i_mount;
 	bool				try_harder = false;
 	bool				already_fixed = false;
 	int				error = 0;
 
 	BUILD_BUG_ON(sizeof(meta_scrub_ops) !=
-		(sizeof(struct xfs_scrub_meta_ops) * XFS_SCRUB_TYPE_NR));
+		(sizeof(struct xchk_meta_ops) * XFS_SCRUB_TYPE_NR));
 
-	trace_xfs_scrub_start(ip, sm, error);
+	trace_xchk_start(ip, sm, error);
 
 	/* Forbidden if we are shut down or mounted norecovery. */
 	error = -ESHUTDOWN;
@@ -492,11 +498,11 @@ xfs_scrub_metadata(
 	if (mp->m_flags & XFS_MOUNT_NORECOVERY)
 		goto out;
 
-	error = xfs_scrub_validate_inputs(mp, sm);
+	error = xchk_validate_inputs(mp, sm);
 	if (error)
 		goto out;
 
-	xfs_scrub_experimental_warning(mp);
+	xchk_experimental_warning(mp);
 
 retry_op:
 	/* Set up for the operation. */
@@ -518,7 +524,7 @@ retry_op:
 		 * Tear down everything we hold, then set up again with
 		 * preparation for worst-case scenarios.
 		 */
-		error = xfs_scrub_teardown(&sc, ip, 0);
+		error = xchk_teardown(&sc, ip, 0);
 		if (error)
 			goto out;
 		try_harder = true;
@@ -549,13 +555,13 @@ retry_op:
 		 * If it's broken, userspace wants us to fix it, and we haven't
 		 * already tried to fix it, then attempt a repair.
 		 */
-		error = xfs_repair_attempt(ip, &sc, &already_fixed);
+		error = xrep_attempt(ip, &sc, &already_fixed);
 		if (error == -EAGAIN) {
 			if (sc.try_harder)
 				try_harder = true;
-			error = xfs_scrub_teardown(&sc, ip, 0);
+			error = xchk_teardown(&sc, ip, 0);
 			if (error) {
-				xfs_repair_failure(mp);
+				xrep_failure(mp);
 				goto out;
 			}
 			goto retry_op;
@@ -563,11 +569,11 @@ retry_op:
 	}
 
 out_nofix:
-	xfs_scrub_postmortem(&sc);
+	xchk_postmortem(&sc);
 out_teardown:
-	error = xfs_scrub_teardown(&sc, ip, error);
+	error = xchk_teardown(&sc, ip, error);
 out:
-	trace_xfs_scrub_done(ip, sm, error);
+	trace_xchk_done(ip, sm, error);
 	if (error == -EFSCORRUPTED || error == -EFSBADCRC) {
 		sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 		error = 0;
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index b295edd5fc0e..af323b229c4b 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -6,58 +6,58 @@
 #ifndef __XFS_SCRUB_SCRUB_H__
 #define __XFS_SCRUB_SCRUB_H__
 
-struct xfs_scrub_context;
+struct xfs_scrub;
 
 /* Type info and names for the scrub types. */
-enum xfs_scrub_type {
+enum xchk_type {
 	ST_NONE = 1,	/* disabled */
 	ST_PERAG,	/* per-AG metadata */
 	ST_FS,		/* per-FS metadata */
 	ST_INODE,	/* per-inode metadata */
 };
 
-struct xfs_scrub_meta_ops {
+struct xchk_meta_ops {
 	/* Acquire whatever resources are needed for the operation. */
-	int		(*setup)(struct xfs_scrub_context *,
+	int		(*setup)(struct xfs_scrub *,
 				 struct xfs_inode *);
 
 	/* Examine metadata for errors. */
-	int		(*scrub)(struct xfs_scrub_context *);
+	int		(*scrub)(struct xfs_scrub *);
 
 	/* Repair or optimize the metadata. */
-	int		(*repair)(struct xfs_scrub_context *);
+	int		(*repair)(struct xfs_scrub *);
 
 	/* Decide if we even have this piece of metadata. */
 	bool		(*has)(struct xfs_sb *);
 
 	/* type describing required/allowed inputs */
-	enum xfs_scrub_type	type;
+	enum xchk_type	type;
 };
 
 /* Buffer pointers and btree cursors for an entire AG. */
-struct xfs_scrub_ag {
-	xfs_agnumber_t			agno;
-	struct xfs_perag		*pag;
+struct xchk_ag {
+	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag;
 
 	/* AG btree roots */
-	struct xfs_buf			*agf_bp;
-	struct xfs_buf			*agfl_bp;
-	struct xfs_buf			*agi_bp;
+	struct xfs_buf		*agf_bp;
+	struct xfs_buf		*agfl_bp;
+	struct xfs_buf		*agi_bp;
 
 	/* AG btrees */
-	struct xfs_btree_cur		*bno_cur;
-	struct xfs_btree_cur		*cnt_cur;
-	struct xfs_btree_cur		*ino_cur;
-	struct xfs_btree_cur		*fino_cur;
-	struct xfs_btree_cur		*rmap_cur;
-	struct xfs_btree_cur		*refc_cur;
+	struct xfs_btree_cur	*bno_cur;
+	struct xfs_btree_cur	*cnt_cur;
+	struct xfs_btree_cur	*ino_cur;
+	struct xfs_btree_cur	*fino_cur;
+	struct xfs_btree_cur	*rmap_cur;
+	struct xfs_btree_cur	*refc_cur;
 };
 
-struct xfs_scrub_context {
+struct xfs_scrub {
 	/* General scrub state. */
 	struct xfs_mount		*mp;
 	struct xfs_scrub_metadata	*sm;
-	const struct xfs_scrub_meta_ops	*ops;
+	const struct xchk_meta_ops	*ops;
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip;
 	void				*buf;
@@ -66,78 +66,76 @@ struct xfs_scrub_context {
 	bool				has_quotaofflock;
 
 	/* State tracking for single-AG operations. */
-	struct xfs_scrub_ag		sa;
+	struct xchk_ag			sa;
 };
 
 /* Metadata scrubbers */
-int xfs_scrub_tester(struct xfs_scrub_context *sc);
-int xfs_scrub_superblock(struct xfs_scrub_context *sc);
-int xfs_scrub_agf(struct xfs_scrub_context *sc);
-int xfs_scrub_agfl(struct xfs_scrub_context *sc);
-int xfs_scrub_agi(struct xfs_scrub_context *sc);
-int xfs_scrub_bnobt(struct xfs_scrub_context *sc);
-int xfs_scrub_cntbt(struct xfs_scrub_context *sc);
-int xfs_scrub_inobt(struct xfs_scrub_context *sc);
-int xfs_scrub_finobt(struct xfs_scrub_context *sc);
-int xfs_scrub_rmapbt(struct xfs_scrub_context *sc);
-int xfs_scrub_refcountbt(struct xfs_scrub_context *sc);
-int xfs_scrub_inode(struct xfs_scrub_context *sc);
-int xfs_scrub_bmap_data(struct xfs_scrub_context *sc);
-int xfs_scrub_bmap_attr(struct xfs_scrub_context *sc);
-int xfs_scrub_bmap_cow(struct xfs_scrub_context *sc);
-int xfs_scrub_directory(struct xfs_scrub_context *sc);
-int xfs_scrub_xattr(struct xfs_scrub_context *sc);
-int xfs_scrub_symlink(struct xfs_scrub_context *sc);
-int xfs_scrub_parent(struct xfs_scrub_context *sc);
+int xchk_tester(struct xfs_scrub *sc);
+int xchk_superblock(struct xfs_scrub *sc);
+int xchk_agf(struct xfs_scrub *sc);
+int xchk_agfl(struct xfs_scrub *sc);
+int xchk_agi(struct xfs_scrub *sc);
+int xchk_bnobt(struct xfs_scrub *sc);
+int xchk_cntbt(struct xfs_scrub *sc);
+int xchk_inobt(struct xfs_scrub *sc);
+int xchk_finobt(struct xfs_scrub *sc);
+int xchk_rmapbt(struct xfs_scrub *sc);
+int xchk_refcountbt(struct xfs_scrub *sc);
+int xchk_inode(struct xfs_scrub *sc);
+int xchk_bmap_data(struct xfs_scrub *sc);
+int xchk_bmap_attr(struct xfs_scrub *sc);
+int xchk_bmap_cow(struct xfs_scrub *sc);
+int xchk_directory(struct xfs_scrub *sc);
+int xchk_xattr(struct xfs_scrub *sc);
+int xchk_symlink(struct xfs_scrub *sc);
+int xchk_parent(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
-int xfs_scrub_rtbitmap(struct xfs_scrub_context *sc);
-int xfs_scrub_rtsummary(struct xfs_scrub_context *sc);
+int xchk_rtbitmap(struct xfs_scrub *sc);
+int xchk_rtsummary(struct xfs_scrub *sc);
 #else
 static inline int
-xfs_scrub_rtbitmap(struct xfs_scrub_context *sc)
+xchk_rtbitmap(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 static inline int
-xfs_scrub_rtsummary(struct xfs_scrub_context *sc)
+xchk_rtsummary(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
-int xfs_scrub_quota(struct xfs_scrub_context *sc);
+int xchk_quota(struct xfs_scrub *sc);
 #else
 static inline int
-xfs_scrub_quota(struct xfs_scrub_context *sc)
+xchk_quota(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 #endif
 
 /* cross-referencing helpers */
-void xfs_scrub_xref_is_used_space(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_not_inode_chunk(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_inode_chunk(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_owned_by(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len,
-		struct xfs_owner_info *oinfo);
-void xfs_scrub_xref_is_not_owned_by(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len,
-		struct xfs_owner_info *oinfo);
-void xfs_scrub_xref_has_no_owner(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_cow_staging(struct xfs_scrub_context *sc,
-		xfs_agblock_t bno, xfs_extlen_t len);
-void xfs_scrub_xref_is_not_shared(struct xfs_scrub_context *sc,
-		xfs_agblock_t bno, xfs_extlen_t len);
+void xchk_xref_is_used_space(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_not_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo);
+void xchk_xref_is_not_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo);
+void xchk_xref_has_no_owner(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_cow_staging(struct xfs_scrub *sc, xfs_agblock_t bno,
+		xfs_extlen_t len);
+void xchk_xref_is_not_shared(struct xfs_scrub *sc, xfs_agblock_t bno,
+		xfs_extlen_t len);
 #ifdef CONFIG_XFS_RT
-void xfs_scrub_xref_is_used_rt_space(struct xfs_scrub_context *sc,
-		xfs_rtblock_t rtbno, xfs_extlen_t len);
+void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno,
+		xfs_extlen_t len);
 #else
-# define xfs_scrub_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
+# define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
 #endif
 
 #endif	/* __XFS_SCRUB_SCRUB_H__ */
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 570a89812116..f7ebaa946999 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -25,28 +25,28 @@
 
 /* Set us up to scrub a symbolic link. */
 int
-xfs_scrub_setup_symlink(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_symlink(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
 	/* Allocate the buffer without the inode lock held. */
 	sc->buf = kmem_zalloc_large(XFS_SYMLINK_MAXLEN + 1, KM_SLEEP);
 	if (!sc->buf)
 		return -ENOMEM;
 
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Symbolic links. */
 
 int
-xfs_scrub_symlink(
-	struct xfs_scrub_context	*sc)
+xchk_symlink(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_inode		*ip = sc->ip;
-	struct xfs_ifork		*ifp;
-	loff_t				len;
-	int				error = 0;
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_ifork	*ifp;
+	loff_t			len;
+	int			error = 0;
 
 	if (!S_ISLNK(VFS_I(ip)->i_mode))
 		return -ENOENT;
@@ -55,7 +55,7 @@ xfs_scrub_symlink(
 
 	/* Plausible size? */
 	if (len > XFS_SYMLINK_MAXLEN || len <= 0) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -63,16 +63,16 @@ xfs_scrub_symlink(
 	if (ifp->if_flags & XFS_IFINLINE) {
 		if (len > XFS_IFORK_DSIZE(ip) ||
 		    len > strnlen(ifp->if_u1.if_data, XFS_IFORK_DSIZE(ip)))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
 	/* Remote symlink; must read the contents. */
 	error = xfs_readlink_bmap_ilocked(sc->ip, sc->buf);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 	if (strnlen(sc->buf, XFS_SYMLINK_MAXLEN) < len)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 7c76d8b5cb05..96feaf8dcdec 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -22,9 +22,9 @@
 
 /* Figure out which block the btree cursor was pointing to. */
 static inline xfs_fsblock_t
-xfs_scrub_btree_cur_fsbno(
-	struct xfs_btree_cur		*cur,
-	int				level)
+xchk_btree_cur_fsbno(
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
 	if (level < cur->bc_nlevels && cur->bc_bufs[level])
 		return XFS_DADDR_TO_FSB(cur->bc_mp, cur->bc_bufs[level]->b_bn);
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index cec3e5ece5a1..4e20f0e48232 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -12,7 +12,7 @@
 #include <linux/tracepoint.h>
 #include "xfs_bit.h"
 
-DECLARE_EVENT_CLASS(xfs_scrub_class,
+DECLARE_EVENT_CLASS(xchk_class,
 	TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm,
 		 int error),
 	TP_ARGS(ip, sm, error),
@@ -47,19 +47,19 @@ DECLARE_EVENT_CLASS(xfs_scrub_class,
 		  __entry->error)
 )
 #define DEFINE_SCRUB_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_class, name, \
+DEFINE_EVENT(xchk_class, name, \
 	TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm, \
 		 int error), \
 	TP_ARGS(ip, sm, error))
 
-DEFINE_SCRUB_EVENT(xfs_scrub_start);
-DEFINE_SCRUB_EVENT(xfs_scrub_done);
-DEFINE_SCRUB_EVENT(xfs_scrub_deadlock_retry);
-DEFINE_SCRUB_EVENT(xfs_repair_attempt);
-DEFINE_SCRUB_EVENT(xfs_repair_done);
+DEFINE_SCRUB_EVENT(xchk_start);
+DEFINE_SCRUB_EVENT(xchk_done);
+DEFINE_SCRUB_EVENT(xchk_deadlock_retry);
+DEFINE_SCRUB_EVENT(xrep_attempt);
+DEFINE_SCRUB_EVENT(xrep_done);
 
-TRACE_EVENT(xfs_scrub_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+TRACE_EVENT(xchk_op_error,
+	TP_PROTO(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		 xfs_agblock_t bno, int error, void *ret_ip),
 	TP_ARGS(sc, agno, bno, error, ret_ip),
 	TP_STRUCT__entry(
@@ -87,8 +87,8 @@ TRACE_EVENT(xfs_scrub_op_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_file_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, int whichfork,
+TRACE_EVENT(xchk_file_op_error,
+	TP_PROTO(struct xfs_scrub *sc, int whichfork,
 		 xfs_fileoff_t offset, int error, void *ret_ip),
 	TP_ARGS(sc, whichfork, offset, error, ret_ip),
 	TP_STRUCT__entry(
@@ -119,8 +119,8 @@ TRACE_EVENT(xfs_scrub_file_op_error,
 		  __entry->ret_ip)
 );
 
-DECLARE_EVENT_CLASS(xfs_scrub_block_error_class,
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_daddr_t daddr, void *ret_ip),
+DECLARE_EVENT_CLASS(xchk_block_error_class,
+	TP_PROTO(struct xfs_scrub *sc, xfs_daddr_t daddr, void *ret_ip),
 	TP_ARGS(sc, daddr, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -153,16 +153,16 @@ DECLARE_EVENT_CLASS(xfs_scrub_block_error_class,
 )
 
 #define DEFINE_SCRUB_BLOCK_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_block_error_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_daddr_t daddr, \
+DEFINE_EVENT(xchk_block_error_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, xfs_daddr_t daddr, \
 		 void *ret_ip), \
 	TP_ARGS(sc, daddr, ret_ip))
 
-DEFINE_SCRUB_BLOCK_ERROR_EVENT(xfs_scrub_block_error);
-DEFINE_SCRUB_BLOCK_ERROR_EVENT(xfs_scrub_block_preen);
+DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_error);
+DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_preen);
 
-DECLARE_EVENT_CLASS(xfs_scrub_ino_error_class,
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_ino_t ino, void *ret_ip),
+DECLARE_EVENT_CLASS(xchk_ino_error_class,
+	TP_PROTO(struct xfs_scrub *sc, xfs_ino_t ino, void *ret_ip),
 	TP_ARGS(sc, ino, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -184,17 +184,17 @@ DECLARE_EVENT_CLASS(xfs_scrub_ino_error_class,
 )
 
 #define DEFINE_SCRUB_INO_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_ino_error_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_ino_t ino, \
+DEFINE_EVENT(xchk_ino_error_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, xfs_ino_t ino, \
 		 void *ret_ip), \
 	TP_ARGS(sc, ino, ret_ip))
 
-DEFINE_SCRUB_INO_ERROR_EVENT(xfs_scrub_ino_error);
-DEFINE_SCRUB_INO_ERROR_EVENT(xfs_scrub_ino_preen);
-DEFINE_SCRUB_INO_ERROR_EVENT(xfs_scrub_ino_warning);
+DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_error);
+DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_preen);
+DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_warning);
 
-DECLARE_EVENT_CLASS(xfs_scrub_fblock_error_class,
-	TP_PROTO(struct xfs_scrub_context *sc, int whichfork,
+DECLARE_EVENT_CLASS(xchk_fblock_error_class,
+	TP_PROTO(struct xfs_scrub *sc, int whichfork,
 		 xfs_fileoff_t offset, void *ret_ip),
 	TP_ARGS(sc, whichfork, offset, ret_ip),
 	TP_STRUCT__entry(
@@ -223,16 +223,16 @@ DECLARE_EVENT_CLASS(xfs_scrub_fblock_error_class,
 );
 
 #define DEFINE_SCRUB_FBLOCK_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_fblock_error_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, int whichfork, \
+DEFINE_EVENT(xchk_fblock_error_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, int whichfork, \
 		 xfs_fileoff_t offset, void *ret_ip), \
 	TP_ARGS(sc, whichfork, offset, ret_ip))
 
-DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xfs_scrub_fblock_error);
-DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xfs_scrub_fblock_warning);
+DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_error);
+DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_warning);
 
-TRACE_EVENT(xfs_scrub_incomplete,
-	TP_PROTO(struct xfs_scrub_context *sc, void *ret_ip),
+TRACE_EVENT(xchk_incomplete,
+	TP_PROTO(struct xfs_scrub *sc, void *ret_ip),
 	TP_ARGS(sc, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -250,8 +250,8 @@ TRACE_EVENT(xfs_scrub_incomplete,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_btree_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+TRACE_EVENT(xchk_btree_op_error,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, int error, void *ret_ip),
 	TP_ARGS(sc, cur, level, error, ret_ip),
 	TP_STRUCT__entry(
@@ -266,7 +266,7 @@ TRACE_EVENT(xfs_scrub_btree_op_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->type = sc->sm->sm_type;
@@ -290,8 +290,8 @@ TRACE_EVENT(xfs_scrub_btree_op_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+TRACE_EVENT(xchk_ifork_btree_op_error,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, int error, void *ret_ip),
 	TP_ARGS(sc, cur, level, error, ret_ip),
 	TP_STRUCT__entry(
@@ -308,7 +308,7 @@ TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->ino = sc->ip->i_ino;
 		__entry->whichfork = cur->bc_private.b.whichfork;
@@ -335,8 +335,8 @@ TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_btree_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+TRACE_EVENT(xchk_btree_error,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, void *ret_ip),
 	TP_ARGS(sc, cur, level, ret_ip),
 	TP_STRUCT__entry(
@@ -350,7 +350,7 @@ TRACE_EVENT(xfs_scrub_btree_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->type = sc->sm->sm_type;
 		__entry->btnum = cur->bc_btnum;
@@ -371,8 +371,8 @@ TRACE_EVENT(xfs_scrub_btree_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_ifork_btree_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+TRACE_EVENT(xchk_ifork_btree_error,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, void *ret_ip),
 	TP_ARGS(sc, cur, level, ret_ip),
 	TP_STRUCT__entry(
@@ -388,7 +388,7 @@ TRACE_EVENT(xfs_scrub_ifork_btree_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->ino = sc->ip->i_ino;
 		__entry->whichfork = cur->bc_private.b.whichfork;
@@ -413,8 +413,8 @@ TRACE_EVENT(xfs_scrub_ifork_btree_error,
 		  __entry->ret_ip)
 );
 
-DECLARE_EVENT_CLASS(xfs_scrub_sbtree_class,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+DECLARE_EVENT_CLASS(xchk_sbtree_class,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level),
 	TP_ARGS(sc, cur, level),
 	TP_STRUCT__entry(
@@ -428,7 +428,7 @@ DECLARE_EVENT_CLASS(xfs_scrub_sbtree_class,
 		__field(int, ptr)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->type = sc->sm->sm_type;
@@ -450,16 +450,16 @@ DECLARE_EVENT_CLASS(xfs_scrub_sbtree_class,
 		  __entry->ptr)
 )
 #define DEFINE_SCRUB_SBTREE_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_sbtree_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur, \
+DEFINE_EVENT(xchk_sbtree_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur, \
 		 int level), \
 	TP_ARGS(sc, cur, level))
 
-DEFINE_SCRUB_SBTREE_EVENT(xfs_scrub_btree_rec);
-DEFINE_SCRUB_SBTREE_EVENT(xfs_scrub_btree_key);
+DEFINE_SCRUB_SBTREE_EVENT(xchk_btree_rec);
+DEFINE_SCRUB_SBTREE_EVENT(xchk_btree_key);
 
-TRACE_EVENT(xfs_scrub_xref_error,
-	TP_PROTO(struct xfs_scrub_context *sc, int error, void *ret_ip),
+TRACE_EVENT(xchk_xref_error,
+	TP_PROTO(struct xfs_scrub *sc, int error, void *ret_ip),
 	TP_ARGS(sc, error, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -483,7 +483,7 @@ TRACE_EVENT(xfs_scrub_xref_error,
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 
-DECLARE_EVENT_CLASS(xfs_repair_extent_class,
+DECLARE_EVENT_CLASS(xrep_extent_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len),
 	TP_ARGS(mp, agno, agbno, len),
@@ -506,15 +506,14 @@ DECLARE_EVENT_CLASS(xfs_repair_extent_class,
 		  __entry->len)
 );
 #define DEFINE_REPAIR_EXTENT_EVENT(name) \
-DEFINE_EVENT(xfs_repair_extent_class, name, \
+DEFINE_EVENT(xrep_extent_class, name, \
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
 		 xfs_agblock_t agbno, xfs_extlen_t len), \
 	TP_ARGS(mp, agno, agbno, len))
-DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_dispose_btree_extent);
-DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_collect_btree_extent);
-DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_agfl_insert);
+DEFINE_REPAIR_EXTENT_EVENT(xrep_dispose_btree_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert);
 
-DECLARE_EVENT_CLASS(xfs_repair_rmap_class,
+DECLARE_EVENT_CLASS(xrep_rmap_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len,
 		 uint64_t owner, uint64_t offset, unsigned int flags),
@@ -547,17 +546,17 @@ DECLARE_EVENT_CLASS(xfs_repair_rmap_class,
 		  __entry->flags)
 );
 #define DEFINE_REPAIR_RMAP_EVENT(name) \
-DEFINE_EVENT(xfs_repair_rmap_class, name, \
+DEFINE_EVENT(xrep_rmap_class, name, \
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
 		 xfs_agblock_t agbno, xfs_extlen_t len, \
 		 uint64_t owner, uint64_t offset, unsigned int flags), \
 	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_alloc_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_ialloc_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_rmap_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_bmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_alloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_ialloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_rmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_extent_fn);
 
-TRACE_EVENT(xfs_repair_refcount_extent_fn,
+TRACE_EVENT(xrep_refcount_extent_fn,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 struct xfs_refcount_irec *irec),
 	TP_ARGS(mp, agno, irec),
@@ -583,7 +582,7 @@ TRACE_EVENT(xfs_repair_refcount_extent_fn,
 		  __entry->refcount)
 )
 
-TRACE_EVENT(xfs_repair_init_btblock,
+TRACE_EVENT(xrep_init_btblock,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
 		 xfs_btnum_t btnum),
 	TP_ARGS(mp, agno, agbno, btnum),
@@ -605,7 +604,7 @@ TRACE_EVENT(xfs_repair_init_btblock,
 		  __entry->agbno,
 		  __entry->btnum)
 )
-TRACE_EVENT(xfs_repair_findroot_block,
+TRACE_EVENT(xrep_findroot_block,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
 		 uint32_t magic, uint16_t level),
 	TP_ARGS(mp, agno, agbno, magic, level),
@@ -630,7 +629,7 @@ TRACE_EVENT(xfs_repair_findroot_block,
 		  __entry->magic,
 		  __entry->level)
 )
-TRACE_EVENT(xfs_repair_calc_ag_resblks,
+TRACE_EVENT(xrep_calc_ag_resblks,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agino_t icount, xfs_agblock_t aglen, xfs_agblock_t freelen,
 		 xfs_agblock_t usedlen),
@@ -659,7 +658,7 @@ TRACE_EVENT(xfs_repair_calc_ag_resblks,
 		  __entry->freelen,
 		  __entry->usedlen)
 )
-TRACE_EVENT(xfs_repair_calc_ag_resblks_btsize,
+TRACE_EVENT(xrep_calc_ag_resblks_btsize,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t bnobt_sz, xfs_agblock_t inobt_sz,
 		 xfs_agblock_t rmapbt_sz, xfs_agblock_t refcbt_sz),
@@ -688,7 +687,7 @@ TRACE_EVENT(xfs_repair_calc_ag_resblks_btsize,
 		  __entry->rmapbt_sz,
 		  __entry->refcbt_sz)
 )
-TRACE_EVENT(xfs_repair_reset_counters,
+TRACE_EVENT(xrep_reset_counters,
 	TP_PROTO(struct xfs_mount *mp),
 	TP_ARGS(mp),
 	TP_STRUCT__entry(
@@ -701,7 +700,7 @@ TRACE_EVENT(xfs_repair_reset_counters,
 		  MAJOR(__entry->dev), MINOR(__entry->dev))
 )
 
-TRACE_EVENT(xfs_repair_ialloc_insert,
+TRACE_EVENT(xrep_ialloc_insert,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agino_t startino, uint16_t holemask, uint8_t count,
 		 uint8_t freecount, uint64_t freemask),
diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h
index 583a9f539bf1..f6ffb4f248f7 100644
--- a/fs/xfs/xfs.h
+++ b/fs/xfs/xfs.h
@@ -8,7 +8,6 @@
 
 #ifdef CONFIG_XFS_DEBUG
 #define DEBUG 1
-#define XFS_BUF_LOCK_TRACKING 1
 #endif
 
 #ifdef CONFIG_XFS_ASSERT_FATAL
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 8eb3ba3d4d00..49f5f5896a43 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  * All Rights Reserved.
  */
 #include "xfs.h"
@@ -20,9 +21,6 @@
 #include "xfs_bmap_util.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
-#include <linux/gfp.h>
-#include <linux/mpage.h>
-#include <linux/pagevec.h>
 #include <linux/writeback.h>
 
 /*
@@ -30,31 +28,11 @@
  */
 struct xfs_writepage_ctx {
 	struct xfs_bmbt_irec    imap;
-	bool			imap_valid;
 	unsigned int		io_type;
+	unsigned int		cow_seq;
 	struct xfs_ioend	*ioend;
-	sector_t		last_block;
 };
 
-void
-xfs_count_page_state(
-	struct page		*page,
-	int			*delalloc,
-	int			*unwritten)
-{
-	struct buffer_head	*bh, *head;
-
-	*delalloc = *unwritten = 0;
-
-	bh = head = page_buffers(page);
-	do {
-		if (buffer_unwritten(bh))
-			(*unwritten) = 1;
-		else if (buffer_delay(bh))
-			(*delalloc) = 1;
-	} while ((bh = bh->b_this_page) != head);
-}
-
 struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
@@ -81,60 +59,23 @@ xfs_find_daxdev_for_inode(
 		return mp->m_ddev_targp->bt_daxdev;
 }
 
-/*
- * We're now finished for good with this page.  Update the page state via the
- * associated buffer_heads, paying attention to the start and end offsets that
- * we need to process on the page.
- *
- * Note that we open code the action in end_buffer_async_write here so that we
- * only have to iterate over the buffers attached to the page once.  This is not
- * only more efficient, but also ensures that we only calls end_page_writeback
- * at the end of the iteration, and thus avoids the pitfall of having the page
- * and buffers potentially freed after every call to end_buffer_async_write.
- */
 static void
 xfs_finish_page_writeback(
 	struct inode		*inode,
 	struct bio_vec		*bvec,
 	int			error)
 {
-	struct buffer_head	*head = page_buffers(bvec->bv_page), *bh = head;
-	bool			busy = false;
-	unsigned int		off = 0;
-	unsigned long		flags;
-
-	ASSERT(bvec->bv_offset < PAGE_SIZE);
-	ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0);
-	ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE);
-	ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0);
-
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
-	do {
-		if (off >= bvec->bv_offset &&
-		    off < bvec->bv_offset + bvec->bv_len) {
-			ASSERT(buffer_async_write(bh));
-			ASSERT(bh->b_end_io == NULL);
-
-			if (error) {
-				mark_buffer_write_io_error(bh);
-				clear_buffer_uptodate(bh);
-				SetPageError(bvec->bv_page);
-			} else {
-				set_buffer_uptodate(bh);
-			}
-			clear_buffer_async_write(bh);
-			unlock_buffer(bh);
-		} else if (buffer_async_write(bh)) {
-			ASSERT(buffer_locked(bh));
-			busy = true;
-		}
-		off += bh->b_size;
-	} while ((bh = bh->b_this_page) != head);
-	bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
-	local_irq_restore(flags);
+	struct iomap_page	*iop = to_iomap_page(bvec->bv_page);
+
+	if (error) {
+		SetPageError(bvec->bv_page);
+		mapping_set_error(inode->i_mapping, -EIO);
+	}
+
+	ASSERT(iop || i_blocksize(inode) == PAGE_SIZE);
+	ASSERT(!iop || atomic_read(&iop->write_count) > 0);
 
-	if (!busy)
+	if (!iop || atomic_dec_and_test(&iop->write_count))
 		end_page_writeback(bvec->bv_page);
 }
 
@@ -170,7 +111,6 @@ xfs_destroy_ioend(
 		/* walk each page on bio, ending page IO on them */
 		bio_for_each_segment_all(bvec, bio, i)
 			xfs_finish_page_writeback(inode, bvec, error);
-
 		bio_put(bio);
 	}
 
@@ -363,39 +303,66 @@ xfs_end_bio(
 
 STATIC int
 xfs_map_blocks(
+	struct xfs_writepage_ctx *wpc,
 	struct inode		*inode,
-	loff_t			offset,
-	struct xfs_bmbt_irec	*imap,
-	int			type)
+	loff_t			offset)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	ssize_t			count = i_blocksize(inode);
-	xfs_fileoff_t		offset_fsb, end_fsb;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset), end_fsb;
+	xfs_fileoff_t		cow_fsb = NULLFILEOFF;
+	struct xfs_bmbt_irec	imap;
+	int			whichfork = XFS_DATA_FORK;
+	struct xfs_iext_cursor	icur;
+	bool			imap_valid;
 	int			error = 0;
-	int			bmapi_flags = XFS_BMAPI_ENTIRE;
-	int			nimaps = 1;
 
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
+	/*
+	 * We have to make sure the cached mapping is within EOF to protect
+	 * against eofblocks trimming on file release leaving us with a stale
+	 * mapping. Otherwise, a page for a subsequent file extending buffered
+	 * write could get picked up by this writeback cycle and written to the
+	 * wrong blocks.
+	 *
+	 * Note that what we really want here is a generic mapping invalidation
+	 * mechanism to protect us from arbitrary extent modifying contexts, not
+	 * just eofblocks.
+	 */
+	xfs_trim_extent_eof(&wpc->imap, ip);
 
 	/*
-	 * Truncate can race with writeback since writeback doesn't take the
-	 * iolock and truncate decreases the file size before it starts
-	 * truncating the pages between new_size and old_size.  Therefore, we
-	 * can end up in the situation where writeback gets a CoW fork mapping
-	 * but the truncate makes the mapping invalid and we end up in here
-	 * trying to get a new mapping.  Bail out here so that we simply never
-	 * get a valid mapping and so we drop the write altogether.  The page
-	 * truncation will kill the contents anyway.
+	 * COW fork blocks can overlap data fork blocks even if the blocks
+	 * aren't shared.  COW I/O always takes precedent, so we must always
+	 * check for overlap on reflink inodes unless the mapping is already a
+	 * COW one, or the COW fork hasn't changed from the last time we looked
+	 * at it.
+	 *
+	 * It's safe to check the COW fork if_seq here without the ILOCK because
+	 * we've indirectly protected against concurrent updates: writeback has
+	 * the page locked, which prevents concurrent invalidations by reflink
+	 * and directio and prevents concurrent buffered writes to the same
+	 * page.  Changes to if_seq always happen under i_lock, which protects
+	 * against concurrent updates and provides a memory barrier on the way
+	 * out that ensures that we always see the current value.
 	 */
-	if (type == XFS_IO_COW && offset > i_size_read(inode))
+	imap_valid = offset_fsb >= wpc->imap.br_startoff &&
+		     offset_fsb < wpc->imap.br_startoff + wpc->imap.br_blockcount;
+	if (imap_valid &&
+	    (!xfs_inode_has_cow_data(ip) ||
+	     wpc->io_type == XFS_IO_COW ||
+	     wpc->cow_seq == READ_ONCE(ip->i_cowfp->if_seq)))
 		return 0;
 
-	ASSERT(type != XFS_IO_COW);
-	if (type == XFS_IO_UNWRITTEN)
-		bmapi_flags |= XFS_BMAPI_IGSTATE;
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
 
+	/*
+	 * If we don't have a valid map, now it's time to get a new one for this
+	 * offset.  This will convert delayed allocations (including COW ones)
+	 * into real extents.  If we return without a valid map, it means we
+	 * landed in a hole and we skip the block.
+	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
@@ -404,109 +371,96 @@ xfs_map_blocks(
 	if (offset > mp->m_super->s_maxbytes - count)
 		count = mp->m_super->s_maxbytes - offset;
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
-	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
-				imap, &nimaps, bmapi_flags);
+
 	/*
-	 * Truncate an overwrite extent if there's a pending CoW
-	 * reservation before the end of this extent.  This forces us
-	 * to come back to writepage to take care of the CoW.
+	 * Check if this is offset is covered by a COW extents, and if yes use
+	 * it directly instead of looking up anything in the data fork.
 	 */
-	if (nimaps && type == XFS_IO_OVERWRITE)
-		xfs_reflink_trim_irec_to_next_cow(ip, offset_fsb, imap);
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	if (error)
-		return error;
-
-	if (type == XFS_IO_DELALLOC &&
-	    (!nimaps || isnullstartblock(imap->br_startblock))) {
-		error = xfs_iomap_write_allocate(ip, XFS_DATA_FORK, offset,
-				imap);
-		if (!error)
-			trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
-		return error;
-	}
-
-#ifdef DEBUG
-	if (type == XFS_IO_UNWRITTEN) {
-		ASSERT(nimaps);
-		ASSERT(imap->br_startblock != HOLESTARTBLOCK);
-		ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
+	if (xfs_inode_has_cow_data(ip) &&
+	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
+		cow_fsb = imap.br_startoff;
+	if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
+		wpc->cow_seq = READ_ONCE(ip->i_cowfp->if_seq);
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		/*
+		 * Truncate can race with writeback since writeback doesn't
+		 * take the iolock and truncate decreases the file size before
+		 * it starts truncating the pages between new_size and old_size.
+		 * Therefore, we can end up in the situation where writeback
+		 * gets a CoW fork mapping but the truncate makes the mapping
+		 * invalid and we end up in here trying to get a new mapping.
+		 * bail out here so that we simply never get a valid mapping
+		 * and so we drop the write altogether.  The page truncation
+		 * will kill the contents anyway.
+		 */
+		if (offset > i_size_read(inode)) {
+			wpc->io_type = XFS_IO_HOLE;
+			return 0;
+		}
+		whichfork = XFS_COW_FORK;
+		wpc->io_type = XFS_IO_COW;
+		goto allocate_blocks;
 	}
-#endif
-	if (nimaps)
-		trace_xfs_map_blocks_found(ip, offset, count, type, imap);
-	return 0;
-}
-
-STATIC bool
-xfs_imap_valid(
-	struct inode		*inode,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
-{
-	offset >>= inode->i_blkbits;
 
 	/*
-	 * We have to make sure the cached mapping is within EOF to protect
-	 * against eofblocks trimming on file release leaving us with a stale
-	 * mapping. Otherwise, a page for a subsequent file extending buffered
-	 * write could get picked up by this writeback cycle and written to the
-	 * wrong blocks.
-	 *
-	 * Note that what we really want here is a generic mapping invalidation
-	 * mechanism to protect us from arbitrary extent modifying contexts, not
-	 * just eofblocks.
+	 * Map valid and no COW extent in the way?  We're done.
 	 */
-	xfs_trim_extent_eof(imap, XFS_I(inode));
-
-	return offset >= imap->br_startoff &&
-		offset < imap->br_startoff + imap->br_blockcount;
-}
-
-STATIC void
-xfs_start_buffer_writeback(
-	struct buffer_head	*bh)
-{
-	ASSERT(buffer_mapped(bh));
-	ASSERT(buffer_locked(bh));
-	ASSERT(!buffer_delay(bh));
-	ASSERT(!buffer_unwritten(bh));
-
-	bh->b_end_io = NULL;
-	set_buffer_async_write(bh);
-	set_buffer_uptodate(bh);
-	clear_buffer_dirty(bh);
-}
-
-STATIC void
-xfs_start_page_writeback(
-	struct page		*page,
-	int			clear_dirty)
-{
-	ASSERT(PageLocked(page));
-	ASSERT(!PageWriteback(page));
+	if (imap_valid) {
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		return 0;
+	}
 
 	/*
-	 * if the page was not fully cleaned, we need to ensure that the higher
-	 * layers come back to it correctly. That means we need to keep the page
-	 * dirty, and for WB_SYNC_ALL writeback we need to ensure the
-	 * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to
-	 * write this page in this writeback sweep will be made.
+	 * If we don't have a valid map, now it's time to get a new one for this
+	 * offset.  This will convert delayed allocations (including COW ones)
+	 * into real extents.
 	 */
-	if (clear_dirty) {
-		clear_page_dirty_for_io(page);
-		set_page_writeback(page);
-	} else
-		set_page_writeback_keepwrite(page);
+	if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap))
+		imap.br_startoff = end_fsb;	/* fake a hole past EOF */
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
-	unlock_page(page);
-}
+	if (imap.br_startoff > offset_fsb) {
+		/* landed in a hole or beyond EOF */
+		imap.br_blockcount = imap.br_startoff - offset_fsb;
+		imap.br_startoff = offset_fsb;
+		imap.br_startblock = HOLESTARTBLOCK;
+		wpc->io_type = XFS_IO_HOLE;
+	} else {
+		/*
+		 * Truncate to the next COW extent if there is one.  This is the
+		 * only opportunity to do this because we can skip COW fork
+		 * lookups for the subsequent blocks in the mapping; however,
+		 * the requirement to treat the COW range separately remains.
+		 */
+		if (cow_fsb != NULLFILEOFF &&
+		    cow_fsb < imap.br_startoff + imap.br_blockcount)
+			imap.br_blockcount = cow_fsb - imap.br_startoff;
+
+		if (isnullstartblock(imap.br_startblock)) {
+			/* got a delalloc extent */
+			wpc->io_type = XFS_IO_DELALLOC;
+			goto allocate_blocks;
+		}
 
-static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
-{
-	return bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+		if (imap.br_state == XFS_EXT_UNWRITTEN)
+			wpc->io_type = XFS_IO_UNWRITTEN;
+		else
+			wpc->io_type = XFS_IO_OVERWRITE;
+	}
+
+	wpc->imap = imap;
+	trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap);
+	return 0;
+allocate_blocks:
+	error = xfs_iomap_write_allocate(ip, whichfork, offset, &imap,
+			&wpc->cow_seq);
+	if (error)
+		return error;
+	ASSERT(whichfork == XFS_COW_FORK || cow_fsb == NULLFILEOFF ||
+	       imap.br_startoff + imap.br_blockcount <= cow_fsb);
+	wpc->imap = imap;
+	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap);
+	return 0;
 }
 
 /*
@@ -574,27 +528,20 @@ xfs_submit_ioend(
 	return 0;
 }
 
-static void
-xfs_init_bio_from_bh(
-	struct bio		*bio,
-	struct buffer_head	*bh)
-{
-	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
-	bio_set_dev(bio, bh->b_bdev);
-}
-
 static struct xfs_ioend *
 xfs_alloc_ioend(
 	struct inode		*inode,
 	unsigned int		type,
 	xfs_off_t		offset,
-	struct buffer_head	*bh)
+	struct block_device	*bdev,
+	sector_t		sector)
 {
 	struct xfs_ioend	*ioend;
 	struct bio		*bio;
 
 	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset);
-	xfs_init_bio_from_bh(bio, bh);
+	bio_set_dev(bio, bdev);
+	bio->bi_iter.bi_sector = sector;
 
 	ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
 	INIT_LIST_HEAD(&ioend->io_list);
@@ -619,13 +566,14 @@ static void
 xfs_chain_bio(
 	struct xfs_ioend	*ioend,
 	struct writeback_control *wbc,
-	struct buffer_head	*bh)
+	struct block_device	*bdev,
+	sector_t		sector)
 {
 	struct bio *new;
 
 	new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
-	xfs_init_bio_from_bh(new, bh);
-
+	bio_set_dev(new, bdev);
+	new->bi_iter.bi_sector = sector;
 	bio_chain(ioend->io_bio, new);
 	bio_get(ioend->io_bio);		/* for xfs_destroy_ioend */
 	ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
@@ -635,122 +583,47 @@ xfs_chain_bio(
 }
 
 /*
- * Test to see if we've been building up a completion structure for
- * earlier buffers -- if so, we try to append to this ioend if we
- * can, otherwise we finish off any current ioend and start another.
- * Return the ioend we finished off so that the caller can submit it
- * once it has finished processing the dirty page.
+ * Test to see if we have an existing ioend structure that we could append to
+ * first, otherwise finish off the current ioend and start another.
  */
 STATIC void
 xfs_add_to_ioend(
 	struct inode		*inode,
-	struct buffer_head	*bh,
 	xfs_off_t		offset,
+	struct page		*page,
+	struct iomap_page	*iop,
 	struct xfs_writepage_ctx *wpc,
 	struct writeback_control *wbc,
 	struct list_head	*iolist)
 {
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct block_device	*bdev = xfs_find_bdev_for_inode(inode);
+	unsigned		len = i_blocksize(inode);
+	unsigned		poff = offset & (PAGE_SIZE - 1);
+	sector_t		sector;
+
+	sector = xfs_fsb_to_db(ip, wpc->imap.br_startblock) +
+		((offset - XFS_FSB_TO_B(mp, wpc->imap.br_startoff)) >> 9);
+
 	if (!wpc->ioend || wpc->io_type != wpc->ioend->io_type ||
-	    bh->b_blocknr != wpc->last_block + 1 ||
+	    sector != bio_end_sector(wpc->ioend->io_bio) ||
 	    offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
 		if (wpc->ioend)
 			list_add(&wpc->ioend->io_list, iolist);
-		wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset, bh);
+		wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset,
+				bdev, sector);
 	}
 
-	/*
-	 * If the buffer doesn't fit into the bio we need to allocate a new
-	 * one.  This shouldn't happen more than once for a given buffer.
-	 */
-	while (xfs_bio_add_buffer(wpc->ioend->io_bio, bh) != bh->b_size)
-		xfs_chain_bio(wpc->ioend, wbc, bh);
-
-	wpc->ioend->io_size += bh->b_size;
-	wpc->last_block = bh->b_blocknr;
-	xfs_start_buffer_writeback(bh);
-}
-
-STATIC void
-xfs_map_buffer(
-	struct inode		*inode,
-	struct buffer_head	*bh,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
-{
-	sector_t		bn;
-	struct xfs_mount	*m = XFS_I(inode)->i_mount;
-	xfs_off_t		iomap_offset = XFS_FSB_TO_B(m, imap->br_startoff);
-	xfs_daddr_t		iomap_bn = xfs_fsb_to_db(XFS_I(inode), imap->br_startblock);
-
-	ASSERT(imap->br_startblock != HOLESTARTBLOCK);
-	ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
-
-	bn = (iomap_bn >> (inode->i_blkbits - BBSHIFT)) +
-	      ((offset - iomap_offset) >> inode->i_blkbits);
-
-	ASSERT(bn || XFS_IS_REALTIME_INODE(XFS_I(inode)));
-
-	bh->b_blocknr = bn;
-	set_buffer_mapped(bh);
-}
-
-STATIC void
-xfs_map_at_offset(
-	struct inode		*inode,
-	struct buffer_head	*bh,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
-{
-	ASSERT(imap->br_startblock != HOLESTARTBLOCK);
-	ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
-
-	xfs_map_buffer(inode, bh, imap, offset);
-	set_buffer_mapped(bh);
-	clear_buffer_delay(bh);
-	clear_buffer_unwritten(bh);
-}
-
-/*
- * Test if a given page contains at least one buffer of a given @type.
- * If @check_all_buffers is true, then we walk all the buffers in the page to
- * try to find one of the type passed in. If it is not set, then the caller only
- * needs to check the first buffer on the page for a match.
- */
-STATIC bool
-xfs_check_page_type(
-	struct page		*page,
-	unsigned int		type,
-	bool			check_all_buffers)
-{
-	struct buffer_head	*bh;
-	struct buffer_head	*head;
-
-	if (PageWriteback(page))
-		return false;
-	if (!page->mapping)
-		return false;
-	if (!page_has_buffers(page))
-		return false;
-
-	bh = head = page_buffers(page);
-	do {
-		if (buffer_unwritten(bh)) {
-			if (type == XFS_IO_UNWRITTEN)
-				return true;
-		} else if (buffer_delay(bh)) {
-			if (type == XFS_IO_DELALLOC)
-				return true;
-		} else if (buffer_dirty(bh) && buffer_mapped(bh)) {
-			if (type == XFS_IO_OVERWRITE)
-				return true;
-		}
-
-		/* If we are only checking the first buffer, we are done now. */
-		if (!check_all_buffers)
-			break;
-	} while ((bh = bh->b_this_page) != head);
+	if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff)) {
+		if (iop)
+			atomic_inc(&iop->write_count);
+		if (bio_full(wpc->ioend->io_bio))
+			xfs_chain_bio(wpc->ioend, wbc, bdev, sector);
+		__bio_add_page(wpc->ioend->io_bio, page, len, poff);
+	}
 
-	return false;
+	wpc->ioend->io_size += len;
 }
 
 STATIC void
@@ -759,34 +632,20 @@ xfs_vm_invalidatepage(
 	unsigned int		offset,
 	unsigned int		length)
 {
-	trace_xfs_invalidatepage(page->mapping->host, page, offset,
-				 length);
-
-	/*
-	 * If we are invalidating the entire page, clear the dirty state from it
-	 * so that we can check for attempts to release dirty cached pages in
-	 * xfs_vm_releasepage().
-	 */
-	if (offset == 0 && length >= PAGE_SIZE)
-		cancel_dirty_page(page);
-	block_invalidatepage(page, offset, length);
+	trace_xfs_invalidatepage(page->mapping->host, page, offset, length);
+	iomap_invalidatepage(page, offset, length);
 }
 
 /*
- * If the page has delalloc buffers on it, we need to punch them out before we
- * invalidate the page. If we don't, we leave a stale delalloc mapping on the
- * inode that can trip a BUG() in xfs_get_blocks() later on if a direct IO read
- * is done on that same region - the delalloc extent is returned when none is
- * supposed to be there.
- *
- * We prevent this by truncating away the delalloc regions on the page before
- * invalidating it. Because they are delalloc, we can do this without needing a
- * transaction. Indeed - if we get ENOSPC errors, we have to be able to do this
- * truncation without a transaction as there is no space left for block
- * reservation (typically why we see a ENOSPC in writeback).
+ * If the page has delalloc blocks on it, we need to punch them out before we
+ * invalidate the page.  If we don't, we leave a stale delalloc mapping on the
+ * inode that can trip up a later direct I/O read operation on the same region.
  *
- * This is not a performance critical path, so for now just do the punching a
- * buffer head at a time.
+ * We prevent this by truncating away the delalloc regions on the page.  Because
+ * they are delalloc, we can do this without needing a transaction. Indeed - if
+ * we get ENOSPC errors, we have to be able to do this truncation without a
+ * transaction as there is no space left for block reservation (typically why we
+ * see a ENOSPC in writeback).
  */
 STATIC void
 xfs_aops_discard_page(
@@ -794,104 +653,31 @@ xfs_aops_discard_page(
 {
 	struct inode		*inode = page->mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	struct buffer_head	*bh, *head;
+	struct xfs_mount	*mp = ip->i_mount;
 	loff_t			offset = page_offset(page);
+	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, offset);
+	int			error;
 
-	if (!xfs_check_page_type(page, XFS_IO_DELALLOC, true))
-		goto out_invalidate;
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+	if (XFS_FORCED_SHUTDOWN(mp))
 		goto out_invalidate;
 
-	xfs_alert(ip->i_mount,
+	xfs_alert(mp,
 		"page discard on page "PTR_FMT", inode 0x%llx, offset %llu.",
 			page, ip->i_ino, offset);
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	bh = head = page_buffers(page);
-	do {
-		int		error;
-		xfs_fileoff_t	start_fsb;
-
-		if (!buffer_delay(bh))
-			goto next_buffer;
-
-		start_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
-		error = xfs_bmap_punch_delalloc_range(ip, start_fsb, 1);
-		if (error) {
-			/* something screwed, just bail */
-			if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-				xfs_alert(ip->i_mount,
-			"page discard unable to remove delalloc mapping.");
-			}
-			break;
-		}
-next_buffer:
-		offset += i_blocksize(inode);
-
-	} while ((bh = bh->b_this_page) != head);
-
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
+			PAGE_SIZE / i_blocksize(inode));
+	if (error && !XFS_FORCED_SHUTDOWN(mp))
+		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
 	xfs_vm_invalidatepage(page, 0, PAGE_SIZE);
-	return;
-}
-
-static int
-xfs_map_cow(
-	struct xfs_writepage_ctx *wpc,
-	struct inode		*inode,
-	loff_t			offset,
-	unsigned int		*new_type)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_bmbt_irec	imap;
-	bool			is_cow = false;
-	int			error;
-
-	/*
-	 * If we already have a valid COW mapping keep using it.
-	 */
-	if (wpc->io_type == XFS_IO_COW) {
-		wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap, offset);
-		if (wpc->imap_valid) {
-			*new_type = XFS_IO_COW;
-			return 0;
-		}
-	}
-
-	/*
-	 * Else we need to check if there is a COW mapping at this offset.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap);
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	if (!is_cow)
-		return 0;
-
-	/*
-	 * And if the COW mapping has a delayed extent here we need to
-	 * allocate real space for it now.
-	 */
-	if (isnullstartblock(imap.br_startblock)) {
-		error = xfs_iomap_write_allocate(ip, XFS_COW_FORK, offset,
-				&imap);
-		if (error)
-			return error;
-	}
-
-	wpc->io_type = *new_type = XFS_IO_COW;
-	wpc->imap_valid = true;
-	wpc->imap = imap;
-	return 0;
 }
 
 /*
  * We implement an immediate ioend submission policy here to avoid needing to
  * chain multiple ioends and hence nest mempool allocations which can violate
  * forward progress guarantees we need to provide. The current ioend we are
- * adding buffers to is cached on the writepage context, and if the new buffer
+ * adding blocks to is cached on the writepage context, and if the new block
  * does not append to the cached ioend it will create a new ioend and cache that
  * instead.
  *
@@ -912,138 +698,99 @@ xfs_writepage_map(
 	uint64_t		end_offset)
 {
 	LIST_HEAD(submit_list);
+	struct iomap_page	*iop = to_iomap_page(page);
+	unsigned		len = i_blocksize(inode);
 	struct xfs_ioend	*ioend, *next;
-	struct buffer_head	*bh, *head;
-	ssize_t			len = i_blocksize(inode);
-	uint64_t		offset;
-	int			error = 0;
-	int			count = 0;
-	int			uptodate = 1;
-	unsigned int		new_type;
-
-	bh = head = page_buffers(page);
-	offset = page_offset(page);
-	do {
-		if (offset >= end_offset)
-			break;
-		if (!buffer_uptodate(bh))
-			uptodate = 0;
+	uint64_t		file_offset;	/* file offset of page */
+	int			error = 0, count = 0, i;
 
-		/*
-		 * set_page_dirty dirties all buffers in a page, independent
-		 * of their state.  The dirty state however is entirely
-		 * meaningless for holes (!mapped && uptodate), so skip
-		 * buffers covering holes here.
-		 */
-		if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
-			wpc->imap_valid = false;
-			continue;
-		}
+	ASSERT(iop || i_blocksize(inode) == PAGE_SIZE);
+	ASSERT(!iop || atomic_read(&iop->write_count) == 0);
 
-		if (buffer_unwritten(bh))
-			new_type = XFS_IO_UNWRITTEN;
-		else if (buffer_delay(bh))
-			new_type = XFS_IO_DELALLOC;
-		else if (buffer_uptodate(bh))
-			new_type = XFS_IO_OVERWRITE;
-		else {
-			if (PageUptodate(page))
-				ASSERT(buffer_mapped(bh));
-			/*
-			 * This buffer is not uptodate and will not be
-			 * written to disk.  Ensure that we will put any
-			 * subsequent writeable buffers into a new
-			 * ioend.
-			 */
-			wpc->imap_valid = false;
+	/*
+	 * Walk through the page to find areas to write back. If we run off the
+	 * end of the current map or find the current map invalid, grab a new
+	 * one.
+	 */
+	for (i = 0, file_offset = page_offset(page);
+	     i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset;
+	     i++, file_offset += len) {
+		if (iop && !test_bit(i, iop->uptodate))
 			continue;
-		}
 
-		if (xfs_is_reflink_inode(XFS_I(inode))) {
-			error = xfs_map_cow(wpc, inode, offset, &new_type);
-			if (error)
-				goto out;
-		}
-
-		if (wpc->io_type != new_type) {
-			wpc->io_type = new_type;
-			wpc->imap_valid = false;
-		}
-
-		if (wpc->imap_valid)
-			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
-							 offset);
-		if (!wpc->imap_valid) {
-			error = xfs_map_blocks(inode, offset, &wpc->imap,
-					     wpc->io_type);
-			if (error)
-				goto out;
-			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
-							 offset);
-		}
-		if (wpc->imap_valid) {
-			lock_buffer(bh);
-			if (wpc->io_type != XFS_IO_OVERWRITE)
-				xfs_map_at_offset(inode, bh, &wpc->imap, offset);
-			xfs_add_to_ioend(inode, bh, offset, wpc, wbc, &submit_list);
-			count++;
-		}
-
-	} while (offset += len, ((bh = bh->b_this_page) != head));
-
-	if (uptodate && bh == head)
-		SetPageUptodate(page);
+		error = xfs_map_blocks(wpc, inode, file_offset);
+		if (error)
+			break;
+		if (wpc->io_type == XFS_IO_HOLE)
+			continue;
+		xfs_add_to_ioend(inode, file_offset, page, iop, wpc, wbc,
+				 &submit_list);
+		count++;
+	}
 
 	ASSERT(wpc->ioend || list_empty(&submit_list));
+	ASSERT(PageLocked(page));
+	ASSERT(!PageWriteback(page));
 
-out:
 	/*
-	 * On error, we have to fail the ioend here because we have locked
-	 * buffers in the ioend. If we don't do this, we'll deadlock
-	 * invalidating the page as that tries to lock the buffers on the page.
-	 * Also, because we may have set pages under writeback, we have to make
-	 * sure we run IO completion to mark the error state of the IO
-	 * appropriately, so we can't cancel the ioend directly here. That means
-	 * we have to mark this page as under writeback if we included any
-	 * buffers from it in the ioend chain so that completion treats it
-	 * correctly.
+	 * On error, we have to fail the ioend here because we may have set
+	 * pages under writeback, we have to make sure we run IO completion to
+	 * mark the error state of the IO appropriately, so we can't cancel the
+	 * ioend directly here.  That means we have to mark this page as under
+	 * writeback if we included any blocks from it in the ioend chain so
+	 * that completion treats it correctly.
 	 *
 	 * If we didn't include the page in the ioend, the on error we can
 	 * simply discard and unlock it as there are no other users of the page
-	 * or it's buffers right now. The caller will still need to trigger
-	 * submission of outstanding ioends on the writepage context so they are
-	 * treated correctly on error.
+	 * now.  The caller will still need to trigger submission of outstanding
+	 * ioends on the writepage context so they are treated correctly on
+	 * error.
 	 */
-	if (count) {
-		xfs_start_page_writeback(page, !error);
+	if (unlikely(error)) {
+		if (!count) {
+			xfs_aops_discard_page(page);
+			ClearPageUptodate(page);
+			unlock_page(page);
+			goto done;
+		}
 
 		/*
-		 * Preserve the original error if there was one, otherwise catch
-		 * submission errors here and propagate into subsequent ioend
-		 * submissions.
+		 * If the page was not fully cleaned, we need to ensure that the
+		 * higher layers come back to it correctly.  That means we need
+		 * to keep the page dirty, and for WB_SYNC_ALL writeback we need
+		 * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed
+		 * so another attempt to write this page in this writeback sweep
+		 * will be made.
 		 */
-		list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
-			int error2;
-
-			list_del_init(&ioend->io_list);
-			error2 = xfs_submit_ioend(wbc, ioend, error);
-			if (error2 && !error)
-				error = error2;
-		}
-	} else if (error) {
-		xfs_aops_discard_page(page);
-		ClearPageUptodate(page);
-		unlock_page(page);
+		set_page_writeback_keepwrite(page);
 	} else {
-		/*
-		 * We can end up here with no error and nothing to write if we
-		 * race with a partial page truncate on a sub-page block sized
-		 * filesystem. In that case we need to mark the page clean.
-		 */
-		xfs_start_page_writeback(page, 1);
-		end_page_writeback(page);
+		clear_page_dirty_for_io(page);
+		set_page_writeback(page);
 	}
 
+	unlock_page(page);
+
+	/*
+	 * Preserve the original error if there was one, otherwise catch
+	 * submission errors here and propagate into subsequent ioend
+	 * submissions.
+	 */
+	list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
+		int error2;
+
+		list_del_init(&ioend->io_list);
+		error2 = xfs_submit_ioend(wbc, ioend, error);
+		if (error2 && !error)
+			error = error2;
+	}
+
+	/*
+	 * We can end up here with no error and nothing to write only if we race
+	 * with a partial page truncate on a sub-page block sized filesystem.
+	 */
+	if (!count)
+		end_page_writeback(page);
+done:
 	mapping_set_error(page->mapping, error);
 	return error;
 }
@@ -1054,7 +801,6 @@ out:
  * For delalloc space on the page we need to allocate space and flush it.
  * For unwritten space on the page we need to start the conversion to
  * regular allocated space.
- * For any other dirty buffer heads on the page we should flush them.
  */
 STATIC int
 xfs_do_writepage(
@@ -1070,8 +816,6 @@ xfs_do_writepage(
 
 	trace_xfs_writepage(inode, page, 0, 0);
 
-	ASSERT(page_has_buffers(page));
-
 	/*
 	 * Refuse to write the page out if we are called from reclaim context.
 	 *
@@ -1210,166 +954,13 @@ xfs_dax_writepages(
 			xfs_find_bdev_for_inode(mapping->host), wbc);
 }
 
-/*
- * Called to move a page into cleanable state - and from there
- * to be released. The page should already be clean. We always
- * have buffer heads in this call.
- *
- * Returns 1 if the page is ok to release, 0 otherwise.
- */
 STATIC int
 xfs_vm_releasepage(
 	struct page		*page,
 	gfp_t			gfp_mask)
 {
-	int			delalloc, unwritten;
-
 	trace_xfs_releasepage(page->mapping->host, page, 0, 0);
-
-	/*
-	 * mm accommodates an old ext3 case where clean pages might not have had
-	 * the dirty bit cleared. Thus, it can send actual dirty pages to
-	 * ->releasepage() via shrink_active_list(). Conversely,
-	 * block_invalidatepage() can send pages that are still marked dirty but
-	 * otherwise have invalidated buffers.
-	 *
-	 * We want to release the latter to avoid unnecessary buildup of the
-	 * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages
-	 * that are entirely invalidated and need to be released.  Hence the
-	 * only time we should get dirty pages here is through
-	 * shrink_active_list() and so we can simply skip those now.
-	 *
-	 * warn if we've left any lingering delalloc/unwritten buffers on clean
-	 * or invalidated pages we are about to release.
-	 */
-	if (PageDirty(page))
-		return 0;
-
-	xfs_count_page_state(page, &delalloc, &unwritten);
-
-	if (WARN_ON_ONCE(delalloc))
-		return 0;
-	if (WARN_ON_ONCE(unwritten))
-		return 0;
-
-	return try_to_free_buffers(page);
-}
-
-/*
- * If this is O_DIRECT or the mpage code calling tell them how large the mapping
- * is, so that we can avoid repeated get_blocks calls.
- *
- * If the mapping spans EOF, then we have to break the mapping up as the mapping
- * for blocks beyond EOF must be marked new so that sub block regions can be
- * correctly zeroed. We can't do this for mappings within EOF unless the mapping
- * was just allocated or is unwritten, otherwise the callers would overwrite
- * existing data with zeros. Hence we have to split the mapping into a range up
- * to and including EOF, and a second mapping for beyond EOF.
- */
-static void
-xfs_map_trim_size(
-	struct inode		*inode,
-	sector_t		iblock,
-	struct buffer_head	*bh_result,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset,
-	ssize_t			size)
-{
-	xfs_off_t		mapping_size;
-
-	mapping_size = imap->br_startoff + imap->br_blockcount - iblock;
-	mapping_size <<= inode->i_blkbits;
-
-	ASSERT(mapping_size > 0);
-	if (mapping_size > size)
-		mapping_size = size;
-	if (offset < i_size_read(inode) &&
-	    (xfs_ufsize_t)offset + mapping_size >= i_size_read(inode)) {
-		/* limit mapping to block that spans EOF */
-		mapping_size = roundup_64(i_size_read(inode) - offset,
-					  i_blocksize(inode));
-	}
-	if (mapping_size > LONG_MAX)
-		mapping_size = LONG_MAX;
-
-	bh_result->b_size = mapping_size;
-}
-
-static int
-xfs_get_blocks(
-	struct inode		*inode,
-	sector_t		iblock,
-	struct buffer_head	*bh_result,
-	int			create)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		offset_fsb, end_fsb;
-	int			error = 0;
-	int			lockmode = 0;
-	struct xfs_bmbt_irec	imap;
-	int			nimaps = 1;
-	xfs_off_t		offset;
-	ssize_t			size;
-
-	BUG_ON(create);
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	offset = (xfs_off_t)iblock << inode->i_blkbits;
-	ASSERT(bh_result->b_size >= i_blocksize(inode));
-	size = bh_result->b_size;
-
-	if (offset >= i_size_read(inode))
-		return 0;
-
-	/*
-	 * Direct I/O is usually done on preallocated files, so try getting
-	 * a block mapping without an exclusive lock first.
-	 */
-	lockmode = xfs_ilock_data_map_shared(ip);
-
-	ASSERT(offset <= mp->m_super->s_maxbytes);
-	if (offset > mp->m_super->s_maxbytes - size)
-		size = mp->m_super->s_maxbytes - offset;
-	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size);
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
-
-	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
-			&nimaps, 0);
-	if (error)
-		goto out_unlock;
-	if (!nimaps) {
-		trace_xfs_get_blocks_notfound(ip, offset, size);
-		goto out_unlock;
-	}
-
-	trace_xfs_get_blocks_found(ip, offset, size,
-		imap.br_state == XFS_EXT_UNWRITTEN ?
-			XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, &imap);
-	xfs_iunlock(ip, lockmode);
-
-	/* trim mapping down to size requested */
-	xfs_map_trim_size(inode, iblock, bh_result, &imap, offset, size);
-
-	/*
-	 * For unwritten extents do not report a disk address in the buffered
-	 * read case (treat as if we're reading into a hole).
-	 */
-	if (xfs_bmap_is_real_extent(&imap))
-		xfs_map_buffer(inode, bh_result, &imap, offset);
-
-	/*
-	 * If this is a realtime file, data may be on a different device.
-	 * to that pointed to from the buffer_head b_bdev currently.
-	 */
-	bh_result->b_bdev = xfs_find_bdev_for_inode(inode);
-	return 0;
-
-out_unlock:
-	xfs_iunlock(ip, lockmode);
-	return error;
+	return iomap_releasepage(page, gfp_mask);
 }
 
 STATIC sector_t
@@ -1401,7 +992,7 @@ xfs_vm_readpage(
 	struct page		*page)
 {
 	trace_xfs_vm_readpage(page->mapping->host, 1);
-	return mpage_readpage(page, xfs_get_blocks);
+	return iomap_readpage(page, &xfs_iomap_ops);
 }
 
 STATIC int
@@ -1412,63 +1003,7 @@ xfs_vm_readpages(
 	unsigned		nr_pages)
 {
 	trace_xfs_vm_readpages(mapping->host, nr_pages);
-	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
-}
-
-/*
- * This is basically a copy of __set_page_dirty_buffers() with one
- * small tweak: buffers beyond EOF do not get marked dirty. If we mark them
- * dirty, we'll never be able to clean them because we don't write buffers
- * beyond EOF, and that means we can't invalidate pages that span EOF
- * that have been marked dirty. Further, the dirty state can leak into
- * the file interior if the file is extended, resulting in all sorts of
- * bad things happening as the state does not match the underlying data.
- *
- * XXX: this really indicates that bufferheads in XFS need to die. Warts like
- * this only exist because of bufferheads and how the generic code manages them.
- */
-STATIC int
-xfs_vm_set_page_dirty(
-	struct page		*page)
-{
-	struct address_space	*mapping = page->mapping;
-	struct inode		*inode = mapping->host;
-	loff_t			end_offset;
-	loff_t			offset;
-	int			newly_dirty;
-
-	if (unlikely(!mapping))
-		return !TestSetPageDirty(page);
-
-	end_offset = i_size_read(inode);
-	offset = page_offset(page);
-
-	spin_lock(&mapping->private_lock);
-	if (page_has_buffers(page)) {
-		struct buffer_head *head = page_buffers(page);
-		struct buffer_head *bh = head;
-
-		do {
-			if (offset < end_offset)
-				set_buffer_dirty(bh);
-			bh = bh->b_this_page;
-			offset += i_blocksize(inode);
-		} while (bh != head);
-	}
-	/*
-	 * Lock out page->mem_cgroup migration to keep PageDirty
-	 * synchronized with per-memcg dirty page counters.
-	 */
-	lock_page_memcg(page);
-	newly_dirty = !TestSetPageDirty(page);
-	spin_unlock(&mapping->private_lock);
-
-	if (newly_dirty)
-		__set_page_dirty(page, mapping, 1);
-	unlock_page_memcg(page);
-	if (newly_dirty)
-		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-	return newly_dirty;
+	return iomap_readpages(mapping, pages, nr_pages, &xfs_iomap_ops);
 }
 
 static int
@@ -1486,13 +1021,13 @@ const struct address_space_operations xfs_address_space_operations = {
 	.readpages		= xfs_vm_readpages,
 	.writepage		= xfs_vm_writepage,
 	.writepages		= xfs_vm_writepages,
-	.set_page_dirty		= xfs_vm_set_page_dirty,
+	.set_page_dirty		= iomap_set_page_dirty,
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
 	.bmap			= xfs_vm_bmap,
 	.direct_IO		= noop_direct_IO,
-	.migratepage		= buffer_migrate_page,
-	.is_partially_uptodate  = block_is_partially_uptodate,
+	.migratepage		= iomap_migrate_page,
+	.is_partially_uptodate  = iomap_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
 	.swap_activate		= xfs_iomap_swapfile_activate,
 };
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 25bc6d4a1231..9af867951a10 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -17,6 +17,7 @@ enum {
 	XFS_IO_UNWRITTEN,	/* covers allocated but uninitialized data */
 	XFS_IO_OVERWRITE,	/* covers already allocated extent */
 	XFS_IO_COW,		/* covers copy-on-write extent */
+	XFS_IO_HOLE,		/* covers region without any block allocation */
 };
 
 #define XFS_IO_TYPES \
@@ -24,7 +25,8 @@ enum {
 	{ XFS_IO_DELALLOC,		"delalloc" }, \
 	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
 	{ XFS_IO_OVERWRITE,		"overwrite" }, \
-	{ XFS_IO_COW,			"CoW" }
+	{ XFS_IO_COW,			"CoW" }, \
+	{ XFS_IO_HOLE,			"hole" }
 
 /*
  * Structure for buffered I/O completions.
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 7ce10055f275..228821b2ebe0 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -26,6 +26,7 @@
 #include "xfs_quota.h"
 #include "xfs_trace.h"
 #include "xfs_dir2.h"
+#include "xfs_defer.h"
 
 /*
  * Look at all the extents for this logical region,
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index f9ca80154c9c..a58034049995 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -87,7 +87,7 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
 	 */
 	if (context->bufsize == 0 ||
 	    (XFS_ISRESET_CURSOR(cursor) &&
-             (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) {
+	     (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) {
 		for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
 			context->put_listent(context,
 					     sfe->flags,
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 956ebd583e27..ce45f066995e 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -375,9 +375,8 @@ xfs_bud_init(
  */
 int
 xfs_bui_recover(
-	struct xfs_mount		*mp,
-	struct xfs_bui_log_item		*buip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_trans		*parent_tp,
+	struct xfs_bui_log_item		*buip)
 {
 	int				error = 0;
 	unsigned int			bui_type;
@@ -393,6 +392,7 @@ xfs_bui_recover(
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip = NULL;
 	struct xfs_bmbt_irec		irec;
+	struct xfs_mount		*mp = parent_tp->t_mountp;
 
 	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
 
@@ -441,6 +441,12 @@ xfs_bui_recover(
 			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
 	if (error)
 		return error;
+	/*
+	 * Recovery stashes all deferred ops during intent processing and
+	 * finishes them on completion. Transfer current dfops state to this
+	 * transaction and transfer the result back before we return.
+	 */
+	xfs_defer_move(tp, parent_tp);
 	budp = xfs_trans_get_bud(tp, buip);
 
 	/* Grab the inode. */
@@ -469,9 +475,8 @@ xfs_bui_recover(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	count = bmap->me_len;
-	error = xfs_trans_log_finish_bmap_update(tp, budp, dfops, type,
-			ip, whichfork, bmap->me_startoff,
-			bmap->me_startblock, &count, state);
+	error = xfs_trans_log_finish_bmap_update(tp, budp, type, ip, whichfork,
+			bmap->me_startoff, bmap->me_startblock, &count, state);
 	if (error)
 		goto err_inode;
 
@@ -481,23 +486,25 @@ xfs_bui_recover(
 		irec.br_blockcount = count;
 		irec.br_startoff = bmap->me_startoff;
 		irec.br_state = state;
-		error = xfs_bmap_unmap_extent(tp->t_mountp, dfops, ip, &irec);
+		error = xfs_bmap_unmap_extent(tp, ip, &irec);
 		if (error)
 			goto err_inode;
 	}
 
 	set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
+	xfs_defer_move(parent_tp, tp);
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	IRELE(ip);
+	xfs_irele(ip);
 
 	return error;
 
 err_inode:
+	xfs_defer_move(parent_tp, tp);
 	xfs_trans_cancel(tp);
 	if (ip) {
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 	return error;
 }
diff --git a/fs/xfs/xfs_bmap_item.h b/fs/xfs/xfs_bmap_item.h
index fd1a1b13df51..89e043a88bb8 100644
--- a/fs/xfs/xfs_bmap_item.h
+++ b/fs/xfs/xfs_bmap_item.h
@@ -79,7 +79,6 @@ struct xfs_bud_log_item *xfs_bud_init(struct xfs_mount *,
 		struct xfs_bui_log_item *);
 void xfs_bui_item_free(struct xfs_bui_log_item *);
 void xfs_bui_release(struct xfs_bui_log_item *);
-int xfs_bui_recover(struct xfs_mount *mp, struct xfs_bui_log_item *buip,
-		struct xfs_defer_ops *dfops);
+int xfs_bui_recover(struct xfs_trans *parent_tp, struct xfs_bui_log_item *buip);
 
 #endif	/* __XFS_BMAP_ITEM_H__ */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index c35009a86699..addbd74ecd8e 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -685,12 +685,10 @@ out_unlock_iolock:
 }
 
 /*
- * dead simple method of punching delalyed allocation blocks from a range in
- * the inode. Walks a block at a time so will be slow, but is only executed in
- * rare error cases so the overhead is not critical. This will always punch out
- * both the start and end blocks, even if the ranges only partially overlap
- * them, so it is up to the caller to ensure that partial blocks are not
- * passed in.
+ * Dead simple method of punching delalyed allocation blocks from a range in
+ * the inode.  This will always punch out both the start and end blocks, even
+ * if the ranges only partially overlap them, so it is up to the caller to
+ * ensure that partial blocks are not passed in.
  */
 int
 xfs_bmap_punch_delalloc_range(
@@ -698,64 +696,46 @@ xfs_bmap_punch_delalloc_range(
 	xfs_fileoff_t		start_fsb,
 	xfs_fileoff_t		length)
 {
-	xfs_fileoff_t		remaining = length;
+	struct xfs_ifork	*ifp = &ip->i_df;
+	xfs_fileoff_t		end_fsb = start_fsb + length;
+	struct xfs_bmbt_irec	got, del;
+	struct xfs_iext_cursor	icur;
 	int			error = 0;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+		if (error)
+			goto out_unlock;
+	}
 
-	do {
-		int		done;
-		xfs_bmbt_irec_t	imap;
-		int		nimaps = 1;
-		xfs_fsblock_t	firstblock;
-		struct xfs_defer_ops dfops;
+	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
+		goto out_unlock;
+
+	while (got.br_startoff + got.br_blockcount > start_fsb) {
+		del = got;
+		xfs_trim_extent(&del, start_fsb, length);
 
 		/*
-		 * Map the range first and check that it is a delalloc extent
-		 * before trying to unmap the range. Otherwise we will be
-		 * trying to remove a real extent (which requires a
-		 * transaction) or a hole, which is probably a bad idea...
+		 * A delete can push the cursor forward. Step back to the
+		 * previous extent on non-delalloc or extents outside the
+		 * target range.
 		 */
-		error = xfs_bmapi_read(ip, start_fsb, 1, &imap, &nimaps,
-				       XFS_BMAPI_ENTIRE);
-
-		if (error) {
-			/* something screwed, just bail */
-			if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-				xfs_alert(ip->i_mount,
-			"Failed delalloc mapping lookup ino %lld fsb %lld.",
-						ip->i_ino, start_fsb);
-			}
-			break;
-		}
-		if (!nimaps) {
-			/* nothing there */
-			goto next_block;
-		}
-		if (imap.br_startblock != DELAYSTARTBLOCK) {
-			/* been converted, ignore */
-			goto next_block;
+		if (!del.br_blockcount ||
+		    !isnullstartblock(del.br_startblock)) {
+			if (!xfs_iext_prev_extent(ifp, &icur, &got))
+				break;
+			continue;
 		}
-		WARN_ON(imap.br_blockcount == 0);
 
-		/*
-		 * Note: while we initialise the firstblock/dfops pair, they
-		 * should never be used because blocks should never be
-		 * allocated or freed for a delalloc extent and hence we need
-		 * don't cancel or finish them after the xfs_bunmapi() call.
-		 */
-		xfs_defer_init(&dfops, &firstblock);
-		error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock,
-					&dfops, &done);
-		if (error)
+		error = xfs_bmap_del_extent_delay(ip, XFS_DATA_FORK, &icur,
+						  &got, &del);
+		if (error || !xfs_iext_get_extent(ifp, &icur, &got))
 			break;
+	}
 
-		ASSERT(!xfs_defer_has_unfinished_work(&dfops));
-next_block:
-		start_fsb++;
-		remaining--;
-	} while(remaining > 0);
-
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
 
@@ -893,13 +873,11 @@ xfs_alloc_file_space(
 	xfs_filblks_t		allocatesize_fsb;
 	xfs_extlen_t		extsz, temp;
 	xfs_fileoff_t		startoffset_fsb;
-	xfs_fsblock_t		firstfsb;
 	int			nimaps;
 	int			quota_flag;
 	int			rt;
 	xfs_trans_t		*tp;
 	xfs_bmbt_irec_t		imaps[1], *imapp;
-	struct xfs_defer_ops	dfops;
 	uint			qblocks, resblks, resrtextents;
 	int			error;
 
@@ -992,20 +970,15 @@ xfs_alloc_file_space(
 
 		xfs_trans_ijoin(tp, ip, 0);
 
-		xfs_defer_init(&dfops, &firstfsb);
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-					allocatesize_fsb, alloc_type, &firstfsb,
-					resblks, imapp, &nimaps, &dfops);
+					allocatesize_fsb, alloc_type, resblks,
+					imapp, &nimaps);
 		if (error)
 			goto error0;
 
 		/*
 		 * Complete the transaction
 		 */
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto error0;
-
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
@@ -1024,8 +997,7 @@ xfs_alloc_file_space(
 
 	return error;
 
-error0:	/* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
-	xfs_defer_cancel(&dfops);
+error0:	/* unlock inode, unreserve quota blocks, cancel trans */
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
 
 error1:	/* Just cancel transaction */
@@ -1043,8 +1015,6 @@ xfs_unmap_extent(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		firstfsb;
 	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
 	int			error;
 
@@ -1062,24 +1032,15 @@ xfs_unmap_extent(
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(&dfops, &firstfsb);
-	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, &firstfsb,
-			&dfops, done);
-	if (error)
-		goto out_bmap_cancel;
-
-	xfs_defer_ijoin(&dfops, ip);
-	error = xfs_defer_finish(&tp, &dfops);
+	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
 	error = xfs_trans_commit(tp);
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	goto out_unlock;
@@ -1208,7 +1169,22 @@ xfs_free_file_space(
 		return 0;
 	if (offset + len > XFS_ISIZE(ip))
 		len = XFS_ISIZE(ip) - offset;
-	return iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+	error = iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+	if (error)
+		return error;
+
+	/*
+	 * If we zeroed right up to EOF and EOF straddles a page boundary we
+	 * must make sure that the post-EOF area is also zeroed because the
+	 * page could be mmap'd and iomap_zero_range doesn't do that for us.
+	 * Writeback of the eof page will do this, albeit clumsily.
+	 */
+	if (offset + len >= XFS_ISIZE(ip) && ((offset + len) & PAGE_MASK)) {
+		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+				(offset + len) & ~PAGE_MASK, LLONG_MAX);
+	}
+
+	return error;
 }
 
 /*
@@ -1285,7 +1261,7 @@ xfs_prepare_shift(
 	 * we've flushed all the dirty data out to disk to avoid having
 	 * CoW extents at the wrong offsets.
 	 */
-	if (xfs_is_reflink_inode(ip)) {
+	if (xfs_inode_has_cow_data(ip)) {
 		error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
 				true);
 		if (error)
@@ -1316,8 +1292,6 @@ xfs_collapse_file_space(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		next_fsb = XFS_B_TO_FSB(mp, offset + len);
 	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
 	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
@@ -1350,22 +1324,16 @@ xfs_collapse_file_space(
 			goto out_trans_cancel;
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(&dfops, &first_block);
 		error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, &first_block, &dfops);
+				&done);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
 	}
 
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
@@ -1392,8 +1360,6 @@ xfs_insert_file_space(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		stop_fsb = XFS_B_TO_FSB(mp, offset);
 	xfs_fileoff_t		next_fsb = NULLFSBLOCK;
 	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
@@ -1404,6 +1370,10 @@ xfs_insert_file_space(
 
 	trace_xfs_insert_file_space(ip);
 
+	error = xfs_bmap_can_insert_extents(ip, stop_fsb, shift_fsb);
+	if (error)
+		return error;
+
 	error = xfs_prepare_shift(ip, offset);
 	if (error)
 		return error;
@@ -1425,22 +1395,17 @@ xfs_insert_file_space(
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-		xfs_defer_init(&dfops, &first_block);
 		error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, stop_fsb, &first_block, &dfops);
+				&done, stop_fsb);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
 	}
 
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -1568,14 +1533,13 @@ xfs_swap_extent_rmap(
 	struct xfs_inode		*ip,
 	struct xfs_inode		*tip)
 {
+	struct xfs_trans		*tp = *tpp;
 	struct xfs_bmbt_irec		irec;
 	struct xfs_bmbt_irec		uirec;
 	struct xfs_bmbt_irec		tirec;
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
 	xfs_filblks_t			count_fsb;
-	xfs_fsblock_t			firstfsb;
-	struct xfs_defer_ops		dfops;
 	int				error;
 	xfs_filblks_t			ilen;
 	xfs_filblks_t			rlen;
@@ -1611,7 +1575,7 @@ xfs_swap_extent_rmap(
 
 		/* Unmap the old blocks in the source file. */
 		while (tirec.br_blockcount) {
-			xfs_defer_init(&dfops, &firstfsb);
+			ASSERT(tp->t_firstblock == NULLFSBLOCK);
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
 
 			/* Read extent from the source file */
@@ -1633,33 +1597,29 @@ xfs_swap_extent_rmap(
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec);
 
 			/* Remove the mapping from the donor file. */
-			error = xfs_bmap_unmap_extent((*tpp)->t_mountp, &dfops,
-					tip, &uirec);
+			error = xfs_bmap_unmap_extent(tp, tip, &uirec);
 			if (error)
 				goto out_defer;
 
 			/* Remove the mapping from the source file. */
-			error = xfs_bmap_unmap_extent((*tpp)->t_mountp, &dfops,
-					ip, &irec);
+			error = xfs_bmap_unmap_extent(tp, ip, &irec);
 			if (error)
 				goto out_defer;
 
 			/* Map the donor file's blocks into the source file. */
-			error = xfs_bmap_map_extent((*tpp)->t_mountp, &dfops,
-					ip, &uirec);
+			error = xfs_bmap_map_extent(tp, ip, &uirec);
 			if (error)
 				goto out_defer;
 
 			/* Map the source file's blocks into the donor file. */
-			error = xfs_bmap_map_extent((*tpp)->t_mountp, &dfops,
-					tip, &irec);
+			error = xfs_bmap_map_extent(tp, tip, &irec);
 			if (error)
 				goto out_defer;
 
-			xfs_defer_ijoin(&dfops, ip);
-			error = xfs_defer_finish(tpp, &dfops);
+			error = xfs_defer_finish(tpp);
+			tp = *tpp;
 			if (error)
-				goto out_defer;
+				goto out;
 
 			tirec.br_startoff += rlen;
 			if (tirec.br_startblock != HOLESTARTBLOCK &&
@@ -1677,7 +1637,7 @@ xfs_swap_extent_rmap(
 	return 0;
 
 out_defer:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp);
 out:
 	trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
 	tip->i_d.di_flags2 = tip_flags2;
@@ -1693,7 +1653,6 @@ xfs_swap_extent_forks(
 	int			*src_log_flags,
 	int			*target_log_flags)
 {
-	struct xfs_ifork	tempifp, *ifp, *tifp;
 	xfs_filblks_t		aforkblks = 0;
 	xfs_filblks_t		taforkblks = 0;
 	xfs_extnum_t		junk;
@@ -1735,11 +1694,7 @@ xfs_swap_extent_forks(
 	/*
 	 * Swap the data forks of the inodes
 	 */
-	ifp = &ip->i_df;
-	tifp = &tip->i_df;
-	tempifp = *ifp;		/* struct copy */
-	*ifp = *tifp;		/* struct copy */
-	*tifp = tempifp;	/* struct copy */
+	swap(ip->i_df, tip->i_df);
 
 	/*
 	 * Fix the on-disk inode values
@@ -1748,13 +1703,8 @@ xfs_swap_extent_forks(
 	ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
 	tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
 
-	tmp = (uint64_t) ip->i_d.di_nextents;
-	ip->i_d.di_nextents = tip->i_d.di_nextents;
-	tip->i_d.di_nextents = tmp;
-
-	tmp = (uint64_t) ip->i_d.di_format;
-	ip->i_d.di_format = tip->i_d.di_format;
-	tip->i_d.di_format = tmp;
+	swap(ip->i_d.di_nextents, tip->i_d.di_nextents);
+	swap(ip->i_d.di_format, tip->i_d.di_format);
 
 	/*
 	 * The extents in the source inode could still contain speculative
@@ -1848,7 +1798,6 @@ xfs_swap_extents(
 	int			src_log_flags, target_log_flags;
 	int			error = 0;
 	int			lock_flags;
-	struct xfs_ifork	*cowfp;
 	uint64_t		f;
 	int			resblks = 0;
 
@@ -1989,18 +1938,11 @@ xfs_swap_extents(
 
 	/* Swap the cow forks. */
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
-		xfs_extnum_t	extnum;
-
 		ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
 		ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);
 
-		extnum = ip->i_cnextents;
-		ip->i_cnextents = tip->i_cnextents;
-		tip->i_cnextents = extnum;
-
-		cowfp = ip->i_cowfp;
-		ip->i_cowfp = tip->i_cowfp;
-		tip->i_cowfp = cowfp;
+		swap(ip->i_cnextents, tip->i_cnextents);
+		swap(ip->i_cowfp, tip->i_cowfp);
 
 		if (ip->i_cowfp && ip->i_cowfp->if_bytes)
 			xfs_inode_set_cowblocks_tag(ip);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index e9c058e3761c..e839907e8492 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -34,16 +34,6 @@
 
 static kmem_zone_t *xfs_buf_zone;
 
-#ifdef XFS_BUF_LOCK_TRACKING
-# define XB_SET_OWNER(bp)	((bp)->b_last_holder = current->pid)
-# define XB_CLEAR_OWNER(bp)	((bp)->b_last_holder = -1)
-# define XB_GET_OWNER(bp)	((bp)->b_last_holder)
-#else
-# define XB_SET_OWNER(bp)	do { } while (0)
-# define XB_CLEAR_OWNER(bp)	do { } while (0)
-# define XB_GET_OWNER(bp)	do { } while (0)
-#endif
-
 #define xb_to_gfp(flags) \
 	((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN)
 
@@ -226,7 +216,6 @@ _xfs_buf_alloc(
 	INIT_LIST_HEAD(&bp->b_li_list);
 	sema_init(&bp->b_sema, 0); /* held, no waiters */
 	spin_lock_init(&bp->b_lock);
-	XB_SET_OWNER(bp);
 	bp->b_target = target;
 	bp->b_flags = flags;
 
@@ -757,11 +746,7 @@ _xfs_buf_read(
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
 
-	if (flags & XBF_ASYNC) {
-		xfs_buf_submit(bp);
-		return 0;
-	}
-	return xfs_buf_submit_wait(bp);
+	return xfs_buf_submit(bp);
 }
 
 xfs_buf_t *
@@ -846,7 +831,7 @@ xfs_buf_read_uncached(
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = ops;
 
-	xfs_buf_submit_wait(bp);
+	xfs_buf_submit(bp);
 	if (bp->b_error) {
 		int	error = bp->b_error;
 		xfs_buf_relse(bp);
@@ -1095,12 +1080,10 @@ xfs_buf_trylock(
 	int			locked;
 
 	locked = down_trylock(&bp->b_sema) == 0;
-	if (locked) {
-		XB_SET_OWNER(bp);
+	if (locked)
 		trace_xfs_buf_trylock(bp, _RET_IP_);
-	} else {
+	else
 		trace_xfs_buf_trylock_fail(bp, _RET_IP_);
-	}
 	return locked;
 }
 
@@ -1122,7 +1105,6 @@ xfs_buf_lock(
 	if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
 		xfs_log_force(bp->b_target->bt_mount, 0);
 	down(&bp->b_sema);
-	XB_SET_OWNER(bp);
 
 	trace_xfs_buf_lock_done(bp, _RET_IP_);
 }
@@ -1133,9 +1115,7 @@ xfs_buf_unlock(
 {
 	ASSERT(xfs_buf_islocked(bp));
 
-	XB_CLEAR_OWNER(bp);
 	up(&bp->b_sema);
-
 	trace_xfs_buf_unlock(bp, _RET_IP_);
 }
 
@@ -1249,7 +1229,7 @@ xfs_bwrite(
 	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q |
 			 XBF_WRITE_FAIL | XBF_DONE);
 
-	error = xfs_buf_submit_wait(bp);
+	error = xfs_buf_submit(bp);
 	if (error) {
 		xfs_force_shutdown(bp->b_target->bt_mount,
 				   SHUTDOWN_META_IO_ERROR);
@@ -1453,29 +1433,55 @@ _xfs_buf_ioapply(
 }
 
 /*
- * Asynchronous IO submission path. This transfers the buffer lock ownership and
- * the current reference to the IO. It is not safe to reference the buffer after
- * a call to this function unless the caller holds an additional reference
- * itself.
+ * Wait for I/O completion of a sync buffer and return the I/O error code.
  */
-void
-xfs_buf_submit(
+static int
+xfs_buf_iowait(
 	struct xfs_buf	*bp)
 {
+	ASSERT(!(bp->b_flags & XBF_ASYNC));
+
+	trace_xfs_buf_iowait(bp, _RET_IP_);
+	wait_for_completion(&bp->b_iowait);
+	trace_xfs_buf_iowait_done(bp, _RET_IP_);
+
+	return bp->b_error;
+}
+
+/*
+ * Buffer I/O submission path, read or write. Asynchronous submission transfers
+ * the buffer lock ownership and the current reference to the IO. It is not
+ * safe to reference the buffer after a call to this function unless the caller
+ * holds an additional reference itself.
+ */
+int
+__xfs_buf_submit(
+	struct xfs_buf	*bp,
+	bool		wait)
+{
+	int		error = 0;
+
 	trace_xfs_buf_submit(bp, _RET_IP_);
 
 	ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
-	ASSERT(bp->b_flags & XBF_ASYNC);
 
 	/* on shutdown we stale and complete the buffer immediately */
 	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
 		xfs_buf_ioerror(bp, -EIO);
 		bp->b_flags &= ~XBF_DONE;
 		xfs_buf_stale(bp);
-		xfs_buf_ioend(bp);
-		return;
+		if (bp->b_flags & XBF_ASYNC)
+			xfs_buf_ioend(bp);
+		return -EIO;
 	}
 
+	/*
+	 * Grab a reference so the buffer does not go away underneath us. For
+	 * async buffers, I/O completion drops the callers reference, which
+	 * could occur before submission returns.
+	 */
+	xfs_buf_hold(bp);
+
 	if (bp->b_flags & XBF_WRITE)
 		xfs_buf_wait_unpin(bp);
 
@@ -1483,22 +1489,13 @@ xfs_buf_submit(
 	bp->b_io_error = 0;
 
 	/*
-	 * The caller's reference is released during I/O completion.
-	 * This occurs some time after the last b_io_remaining reference is
-	 * released, so after we drop our Io reference we have to have some
-	 * other reference to ensure the buffer doesn't go away from underneath
-	 * us. Take a direct reference to ensure we have safe access to the
-	 * buffer until we are finished with it.
-	 */
-	xfs_buf_hold(bp);
-
-	/*
 	 * Set the count to 1 initially, this will stop an I/O completion
 	 * callout which happens before we have started all the I/O from calling
 	 * xfs_buf_ioend too early.
 	 */
 	atomic_set(&bp->b_io_remaining, 1);
-	xfs_buf_ioacct_inc(bp);
+	if (bp->b_flags & XBF_ASYNC)
+		xfs_buf_ioacct_inc(bp);
 	_xfs_buf_ioapply(bp);
 
 	/*
@@ -1507,74 +1504,19 @@ xfs_buf_submit(
 	 * that we don't return to the caller with completion still pending.
 	 */
 	if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
-		if (bp->b_error)
+		if (bp->b_error || !(bp->b_flags & XBF_ASYNC))
 			xfs_buf_ioend(bp);
 		else
 			xfs_buf_ioend_async(bp);
 	}
 
-	xfs_buf_rele(bp);
-	/* Note: it is not safe to reference bp now we've dropped our ref */
-}
-
-/*
- * Synchronous buffer IO submission path, read or write.
- */
-int
-xfs_buf_submit_wait(
-	struct xfs_buf	*bp)
-{
-	int		error;
-
-	trace_xfs_buf_submit_wait(bp, _RET_IP_);
-
-	ASSERT(!(bp->b_flags & (_XBF_DELWRI_Q | XBF_ASYNC)));
-
-	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
-		xfs_buf_ioerror(bp, -EIO);
-		xfs_buf_stale(bp);
-		bp->b_flags &= ~XBF_DONE;
-		return -EIO;
-	}
-
-	if (bp->b_flags & XBF_WRITE)
-		xfs_buf_wait_unpin(bp);
-
-	/* clear the internal error state to avoid spurious errors */
-	bp->b_io_error = 0;
+	if (wait)
+		error = xfs_buf_iowait(bp);
 
 	/*
-	 * For synchronous IO, the IO does not inherit the submitters reference
-	 * count, nor the buffer lock. Hence we cannot release the reference we
-	 * are about to take until we've waited for all IO completion to occur,
-	 * including any xfs_buf_ioend_async() work that may be pending.
-	 */
-	xfs_buf_hold(bp);
-
-	/*
-	 * Set the count to 1 initially, this will stop an I/O completion
-	 * callout which happens before we have started all the I/O from calling
-	 * xfs_buf_ioend too early.
-	 */
-	atomic_set(&bp->b_io_remaining, 1);
-	_xfs_buf_ioapply(bp);
-
-	/*
-	 * make sure we run completion synchronously if it raced with us and is
-	 * already complete.
-	 */
-	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
-		xfs_buf_ioend(bp);
-
-	/* wait for completion before gathering the error from the buffer */
-	trace_xfs_buf_iowait(bp, _RET_IP_);
-	wait_for_completion(&bp->b_iowait);
-	trace_xfs_buf_iowait_done(bp, _RET_IP_);
-	error = bp->b_error;
-
-	/*
-	 * all done now, we can release the hold that keeps the buffer
-	 * referenced for the entire IO.
+	 * Release the hold that keeps the buffer referenced for the entire
+	 * I/O. Note that if the buffer is async, it is not safe to reference
+	 * after this release.
 	 */
 	xfs_buf_rele(bp);
 	return error;
@@ -1972,16 +1914,11 @@ xfs_buf_cmp(
 }
 
 /*
- * submit buffers for write.
- *
- * When we have a large buffer list, we do not want to hold all the buffers
- * locked while we block on the request queue waiting for IO dispatch. To avoid
- * this problem, we lock and submit buffers in groups of 50, thereby minimising
- * the lock hold times for lists which may contain thousands of objects.
- *
- * To do this, we sort the buffer list before we walk the list to lock and
- * submit buffers, and we plug and unplug around each group of buffers we
- * submit.
+ * Submit buffers for write. If wait_list is specified, the buffers are
+ * submitted using sync I/O and placed on the wait list such that the caller can
+ * iowait each buffer. Otherwise async I/O is used and the buffers are released
+ * at I/O completion time. In either case, buffers remain locked until I/O
+ * completes and the buffer is released from the queue.
  */
 static int
 xfs_buf_delwri_submit_buffers(
@@ -2023,21 +1960,21 @@ xfs_buf_delwri_submit_buffers(
 		trace_xfs_buf_delwri_split(bp, _RET_IP_);
 
 		/*
-		 * We do all IO submission async. This means if we need
-		 * to wait for IO completion we need to take an extra
-		 * reference so the buffer is still valid on the other
-		 * side. We need to move the buffer onto the io_list
-		 * at this point so the caller can still access it.
+		 * If we have a wait list, each buffer (and associated delwri
+		 * queue reference) transfers to it and is submitted
+		 * synchronously. Otherwise, drop the buffer from the delwri
+		 * queue and submit async.
 		 */
 		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_WRITE_FAIL);
-		bp->b_flags |= XBF_WRITE | XBF_ASYNC;
+		bp->b_flags |= XBF_WRITE;
 		if (wait_list) {
-			xfs_buf_hold(bp);
+			bp->b_flags &= ~XBF_ASYNC;
 			list_move_tail(&bp->b_list, wait_list);
-		} else
+		} else {
+			bp->b_flags |= XBF_ASYNC;
 			list_del_init(&bp->b_list);
-
-		xfs_buf_submit(bp);
+		}
+		__xfs_buf_submit(bp, false);
 	}
 	blk_finish_plug(&plug);
 
@@ -2084,9 +2021,11 @@ xfs_buf_delwri_submit(
 
 		list_del_init(&bp->b_list);
 
-		/* locking the buffer will wait for async IO completion. */
-		xfs_buf_lock(bp);
-		error2 = bp->b_error;
+		/*
+		 * Wait on the locked buffer, check for errors and unlock and
+		 * release the delwri queue reference.
+		 */
+		error2 = xfs_buf_iowait(bp);
 		xfs_buf_relse(bp);
 		if (!error)
 			error = error2;
@@ -2132,23 +2071,18 @@ xfs_buf_delwri_pushbuf(
 
 	/*
 	 * Delwri submission clears the DELWRI_Q buffer flag and returns with
-	 * the buffer on the wait list with an associated reference. Rather than
+	 * the buffer on the wait list with the original reference. Rather than
 	 * bounce the buffer from a local wait list back to the original list
 	 * after I/O completion, reuse the original list as the wait list.
 	 */
 	xfs_buf_delwri_submit_buffers(&submit_list, buffer_list);
 
 	/*
-	 * The buffer is now under I/O and wait listed as during typical delwri
-	 * submission. Lock the buffer to wait for I/O completion. Rather than
-	 * remove the buffer from the wait list and release the reference, we
-	 * want to return with the buffer queued to the original list. The
-	 * buffer already sits on the original list with a wait list reference,
-	 * however. If we let the queue inherit that wait list reference, all we
-	 * need to do is reset the DELWRI_Q flag.
+	 * The buffer is now locked, under I/O and wait listed on the original
+	 * delwri queue. Wait for I/O completion, restore the DELWRI_Q flag and
+	 * return with the buffer unlocked and on the original queue.
 	 */
-	xfs_buf_lock(bp);
-	error = bp->b_error;
+	error = xfs_buf_iowait(bp);
 	bp->b_flags |= _XBF_DELWRI_Q;
 	xfs_buf_unlock(bp);
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index d24dbd4dac39..4e3171acd0f8 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -12,7 +12,6 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/dax.h>
-#include <linux/buffer_head.h>
 #include <linux/uio.h>
 #include <linux/list_lru.h>
 
@@ -199,10 +198,6 @@ typedef struct xfs_buf {
 	int			b_last_error;
 
 	const struct xfs_buf_ops	*b_ops;
-
-#ifdef XFS_BUF_LOCK_TRACKING
-	int			b_last_holder;
-#endif
 } xfs_buf_t;
 
 /* Finding and Reading Buffers */
@@ -298,8 +293,14 @@ extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error,
 		xfs_failaddr_t failaddr);
 #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address)
 extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
-extern void xfs_buf_submit(struct xfs_buf *bp);
-extern int xfs_buf_submit_wait(struct xfs_buf *bp);
+
+extern int __xfs_buf_submit(struct xfs_buf *bp, bool);
+static inline int xfs_buf_submit(struct xfs_buf *bp)
+{
+	bool wait = bp->b_flags & XBF_ASYNC ? false : true;
+	return __xfs_buf_submit(bp, wait);
+}
+
 extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 				xfs_buf_rw_t);
 #define xfs_buf_zero(bp, off, len) \
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 678a5fcd7576..93f07edafd81 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -128,7 +128,7 @@ next_extent:
 	}
 
 out_del_cursor:
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	xfs_buf_relse(agbp);
 out_put_perag:
 	xfs_perag_put(pag);
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 0973a0423bed..87e6dd5326d5 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -286,17 +286,15 @@ xfs_dquot_disk_alloc(
 	struct xfs_buf		**bpp)
 {
 	struct xfs_bmbt_irec	map;
-	struct xfs_defer_ops	dfops;
-	struct xfs_mount	*mp = (*tpp)->t_mountp;
+	struct xfs_trans	*tp = *tpp;
+	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_buf		*bp;
 	struct xfs_inode	*quotip = xfs_quota_inode(mp, dqp->dq_flags);
-	xfs_fsblock_t		firstblock;
 	int			nmaps = 1;
 	int			error;
 
 	trace_xfs_dqalloc(dqp);
 
-	xfs_defer_init(&dfops, &firstblock);
 	xfs_ilock(quotip, XFS_ILOCK_EXCL);
 	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
 		/*
@@ -308,13 +306,12 @@ xfs_dquot_disk_alloc(
 	}
 
 	/* Create the block mapping. */
-	xfs_trans_ijoin(*tpp, quotip, XFS_ILOCK_EXCL);
-	error = xfs_bmapi_write(*tpp, quotip, dqp->q_fileoffset,
+	xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
+	error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset,
 			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
-			&firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
-			&map, &nmaps, &dfops);
+			XFS_QM_DQALLOC_SPACE_RES(mp), &map, &nmaps);
 	if (error)
-		goto error0;
+		return error;
 	ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
 	ASSERT(nmaps == 1);
 	ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
@@ -326,19 +323,17 @@ xfs_dquot_disk_alloc(
 	dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
 
 	/* now we can just get the buffer (there's nothing to read yet) */
-	bp = xfs_trans_get_buf(*tpp, mp->m_ddev_targp, dqp->q_blkno,
+	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, dqp->q_blkno,
 			mp->m_quotainfo->qi_dqchunklen, 0);
-	if (!bp) {
-		error = -ENOMEM;
-		goto error1;
-	}
+	if (!bp)
+		return -ENOMEM;
 	bp->b_ops = &xfs_dquot_buf_ops;
 
 	/*
 	 * Make a chunk of dquots out of this buffer and log
 	 * the entire thing.
 	 */
-	xfs_qm_init_dquot_blk(*tpp, mp, be32_to_cpu(dqp->q_core.d_id),
+	xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
 			      dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
 	xfs_buf_set_ref(bp, XFS_DQUOT_REF);
 
@@ -352,10 +347,8 @@ xfs_dquot_disk_alloc(
 	 * the buffer locked across the _defer_finish call.  We can now do
 	 * this correctly with xfs_defer_bjoin.
 	 *
-	 * Above, we allocated a disk block for the dquot information and
-	 * used get_buf to initialize the dquot.  If the _defer_bjoin fails,
-	 * the buffer is still locked to *tpp, so we must _bhold_release and
-	 * then _trans_brelse the buffer.  If the _defer_finish fails, the old
+	 * Above, we allocated a disk block for the dquot information and used
+	 * get_buf to initialize the dquot. If the _defer_finish fails, the old
 	 * transaction is gone but the new buffer is not joined or held to any
 	 * transaction, so we must _buf_relse it.
 	 *
@@ -364,25 +357,15 @@ xfs_dquot_disk_alloc(
 	 * is responsible for unlocking any buffer passed back, either
 	 * manually or by committing the transaction.
 	 */
-	xfs_trans_bhold(*tpp, bp);
-	error = xfs_defer_bjoin(&dfops, bp);
-	if (error) {
-		xfs_trans_bhold_release(*tpp, bp);
-		xfs_trans_brelse(*tpp, bp);
-		goto error1;
-	}
-	error = xfs_defer_finish(tpp, &dfops);
+	xfs_trans_bhold(tp, bp);
+	error = xfs_defer_finish(tpp);
+	tp = *tpp;
 	if (error) {
 		xfs_buf_relse(bp);
-		goto error1;
+		return error;
 	}
 	*bpp = bp;
 	return 0;
-
-error1:
-	xfs_defer_cancel(&dfops);
-error0:
-	return error;
 }
 
 /*
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 0470114a8d80..9866f542e77b 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -50,6 +50,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_LOG_ITEM_PIN,
 	XFS_RANDOM_BUF_LRU_REF,
 	XFS_RANDOM_FORCE_SCRUB_REPAIR,
+	XFS_RANDOM_FORCE_SUMMARY_RECALC,
 };
 
 struct xfs_errortag_attr {
@@ -157,6 +158,7 @@ XFS_ERRORTAG_ATTR_RW(log_bad_crc,	XFS_ERRTAG_LOG_BAD_CRC);
 XFS_ERRORTAG_ATTR_RW(log_item_pin,	XFS_ERRTAG_LOG_ITEM_PIN);
 XFS_ERRORTAG_ATTR_RW(buf_lru_ref,	XFS_ERRTAG_BUF_LRU_REF);
 XFS_ERRORTAG_ATTR_RW(force_repair,	XFS_ERRTAG_FORCE_SCRUB_REPAIR);
+XFS_ERRORTAG_ATTR_RW(bad_summary,	XFS_ERRTAG_FORCE_SUMMARY_RECALC);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -192,6 +194,7 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(log_item_pin),
 	XFS_ERRORTAG_ATTR_LIST(buf_lru_ref),
 	XFS_ERRORTAG_ATTR_LIST(force_repair),
+	XFS_ERRORTAG_ATTR_LIST(bad_summary),
 	NULL,
 };
 
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 3cf4682e2510..f2284ceb129f 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -150,7 +150,7 @@ xfs_nfs_get_inode(
 	}
 
 	if (VFS_I(ip)->i_generation != generation) {
-		IRELE(ip);
+		xfs_irele(ip);
 		return ERR_PTR(-ESTALE);
 	}
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a3e7767a5715..181e9084519b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -721,12 +721,10 @@ xfs_file_write_iter(
 
 static void
 xfs_wait_dax_page(
-	struct inode		*inode,
-	bool			*did_unlock)
+	struct inode		*inode)
 {
 	struct xfs_inode        *ip = XFS_I(inode);
 
-	*did_unlock = true;
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	schedule();
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
@@ -735,8 +733,7 @@ xfs_wait_dax_page(
 static int
 xfs_break_dax_layouts(
 	struct inode		*inode,
-	uint			iolock,
-	bool			*did_unlock)
+	bool			*retry)
 {
 	struct page		*page;
 
@@ -746,9 +743,10 @@ xfs_break_dax_layouts(
 	if (!page)
 		return 0;
 
+	*retry = true;
 	return ___wait_var_event(&page->_refcount,
 			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
-			0, 0, xfs_wait_dax_page(inode, did_unlock));
+			0, 0, xfs_wait_dax_page(inode));
 }
 
 int
@@ -766,7 +764,7 @@ xfs_break_layouts(
 		retry = false;
 		switch (reason) {
 		case BREAK_UNMAP:
-			error = xfs_break_dax_layouts(inode, *iolock, &retry);
+			error = xfs_break_dax_layouts(inode, &retry);
 			if (error || retry)
 				break;
 			/* fall through */
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 2d2c5ab9143c..182501373af2 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -19,6 +19,8 @@
 #include "xfs_filestream.h"
 #include "xfs_trace.h"
 #include "xfs_ag_resv.h"
+#include "xfs_trans.h"
+#include "xfs_shared.h"
 
 struct xfs_fstrm_item {
 	struct xfs_mru_cache_elem	mru;
@@ -339,7 +341,7 @@ xfs_filestream_lookup_ag(
 	if (xfs_filestream_pick_ag(pip, startag, &ag, 0, 0))
 		ag = NULLAGNUMBER;
 out:
-	IRELE(pip);
+	xfs_irele(pip);
 	return ag;
 }
 
@@ -377,7 +379,7 @@ xfs_filestream_new_ag(
 
 	if (xfs_alloc_is_userdata(ap->datatype))
 		flags |= XFS_PICK_USERDATA;
-	if (ap->dfops->dop_low)
+	if (ap->tp->t_flags & XFS_TRANS_LOWMODE)
 		flags |= XFS_PICK_LOWSPACE;
 
 	err = xfs_filestream_pick_ag(pip, startag, agp, flags, minlen);
@@ -388,7 +390,7 @@ xfs_filestream_new_ag(
 	if (mru)
 		xfs_fstrm_free_func(mp, mru);
 
-	IRELE(pip);
+	xfs_irele(pip);
 exit:
 	if (*agp == NULLAGNUMBER)
 		*agp = 0;
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index c34fa9c342f2..3d76a9e35870 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -214,12 +214,12 @@ xfs_getfsmap_is_shared(
 	/* Are there any shared blocks here? */
 	flen = 0;
 	cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp,
-			info->agno, NULL);
+			info->agno);
 
 	error = xfs_refcount_find_shared(cur, rec->rm_startblock,
 			rec->rm_blockcount, &fbno, &flen, false);
 
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	if (error)
 		return error;
 
@@ -513,8 +513,8 @@ xfs_getfsmap_rtdev_rtbitmap_query(
 	struct xfs_trans		*tp,
 	struct xfs_getfsmap_info	*info)
 {
-	struct xfs_rtalloc_rec		alow;
-	struct xfs_rtalloc_rec		ahigh;
+	struct xfs_rtalloc_rec		alow = { 0 };
+	struct xfs_rtalloc_rec		ahigh = { 0 };
 	int				error;
 
 	xfs_ilock(tp->t_mountp->m_rbmip, XFS_ILOCK_SHARED);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a7afcad6b711..7c00b8bedfe3 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -387,7 +387,7 @@ xfs_reserve_blocks(
 	do {
 		free = percpu_counter_sum(&mp->m_fdblocks) -
 						mp->m_alloc_set_aside;
-		if (!free)
+		if (free <= 0)
 			break;
 
 		delta = request - mp->m_resblks;
@@ -536,7 +536,7 @@ xfs_fs_reserve_ag_blocks(
 
 	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
 		pag = xfs_perag_get(mp, agno);
-		err2 = xfs_ag_resv_init(pag);
+		err2 = xfs_ag_resv_init(pag, NULL);
 		xfs_perag_put(pag);
 		if (err2 && !error)
 			error = err2;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 47f417d20a30..245483cc282b 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -66,7 +66,7 @@ xfs_inode_alloc(
 	ip->i_cowfp = NULL;
 	ip->i_cnextents = 0;
 	ip->i_cformat = XFS_DINODE_FMT_EXTENTS;
-	memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
+	memset(&ip->i_df, 0, sizeof(ip->i_df));
 	ip->i_flags = 0;
 	ip->i_delayed_blks = 0;
 	memset(&ip->i_d, 0, sizeof(ip->i_d));
@@ -716,7 +716,7 @@ xfs_icache_inode_is_allocated(
 		return error;
 
 	*inuse = !!(VFS_I(ip)->i_mode);
-	IRELE(ip);
+	xfs_irele(ip);
 	return 0;
 }
 
@@ -856,7 +856,7 @@ restart:
 			    xfs_iflags_test(batch[i], XFS_INEW))
 				xfs_inew_wait(batch[i]);
 			error = execute(batch[i], flags, args);
-			IRELE(batch[i]);
+			xfs_irele(batch[i]);
 			if (error == -EAGAIN) {
 				skipped++;
 				continue;
@@ -1697,14 +1697,13 @@ xfs_inode_clear_eofblocks_tag(
  */
 static bool
 xfs_prep_free_cowblocks(
-	struct xfs_inode	*ip,
-	struct xfs_ifork	*ifp)
+	struct xfs_inode	*ip)
 {
 	/*
 	 * Just clear the tag if we have an empty cow fork or none at all. It's
 	 * possible the inode was fully unshared since it was originally tagged.
 	 */
-	if (!xfs_is_reflink_inode(ip) || !ifp->if_bytes) {
+	if (!xfs_inode_has_cow_data(ip)) {
 		trace_xfs_inode_free_cowblocks_invalid(ip);
 		xfs_inode_clear_cowblocks_tag(ip);
 		return false;
@@ -1742,11 +1741,10 @@ xfs_inode_free_cowblocks(
 	void			*args)
 {
 	struct xfs_eofblocks	*eofb = args;
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	int			match;
 	int			ret = 0;
 
-	if (!xfs_prep_free_cowblocks(ip, ifp))
+	if (!xfs_prep_free_cowblocks(ip))
 		return 0;
 
 	if (eofb) {
@@ -1771,7 +1769,7 @@ xfs_inode_free_cowblocks(
 	 * Check again, nobody else should be able to dirty blocks or change
 	 * the reflink iflag now that we have the first two locks held.
 	 */
-	if (xfs_prep_free_cowblocks(ip, ifp))
+	if (xfs_prep_free_cowblocks(ip))
 		ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 7a96c4e0ab5c..d957a46dc1cb 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -927,7 +927,7 @@ xfs_ialloc(
 	case S_IFLNK:
 		ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
 		ip->i_df.if_flags = XFS_IFEXTENTS;
-		ip->i_df.if_bytes = ip->i_df.if_real_bytes = 0;
+		ip->i_df.if_bytes = 0;
 		ip->i_df.if_u1.if_root = NULL;
 		break;
 	default:
@@ -1142,8 +1142,6 @@ xfs_create(
 	struct xfs_inode	*ip = NULL;
 	struct xfs_trans	*tp = NULL;
 	int			error;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	bool                    unlock_dp_on_error = false;
 	prid_t			prid;
 	struct xfs_dquot	*udqp = NULL;
@@ -1195,9 +1193,6 @@ xfs_create(
 	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
 	unlock_dp_on_error = true;
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-
 	/*
 	 * Reserve disk quota and the inode.
 	 */
@@ -1226,7 +1221,7 @@ xfs_create(
 	unlock_dp_on_error = false;
 
 	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
-					&first_block, &dfops, resblks ?
+				   resblks ?
 					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
 	if (error) {
 		ASSERT(error != -ENOSPC);
@@ -1238,11 +1233,11 @@ xfs_create(
 	if (is_dir) {
 		error = xfs_dir_init(tp, ip, dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		error = xfs_bumplink(tp, dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -1260,10 +1255,6 @@ xfs_create(
 	 */
 	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_release_inode;
@@ -1275,8 +1266,6 @@ xfs_create(
 	*ipp = ip;
 	return 0;
 
- out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
  out_trans_cancel:
 	xfs_trans_cancel(tp);
  out_release_inode:
@@ -1287,7 +1276,7 @@ xfs_create(
 	 */
 	if (ip) {
 		xfs_finish_inode_setup(ip);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 
 	xfs_qm_dqrele(udqp);
@@ -1382,7 +1371,7 @@ xfs_create_tmpfile(
 	 */
 	if (ip) {
 		xfs_finish_inode_setup(ip);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 
 	xfs_qm_dqrele(udqp);
@@ -1401,8 +1390,6 @@ xfs_link(
 	xfs_mount_t		*mp = tdp->i_mount;
 	xfs_trans_t		*tp;
 	int			error;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t           first_block;
 	int			resblks;
 
 	trace_xfs_link(tdp, target_name);
@@ -1451,9 +1438,6 @@ xfs_link(
 			goto error_return;
 	}
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-
 	/*
 	 * Handle initial link state of O_TMPFILE inode
 	 */
@@ -1464,7 +1448,7 @@ xfs_link(
 	}
 
 	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
-					&first_block, &dfops, resblks);
+				   resblks);
 	if (error)
 		goto error_return;
 	xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -1482,12 +1466,6 @@ xfs_link(
 	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error) {
-		xfs_defer_cancel(&dfops);
-		goto error_return;
-	}
-
 	return xfs_trans_commit(tp);
 
  error_return:
@@ -1545,8 +1523,6 @@ xfs_itruncate_extents_flags(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		first_unmap_block;
 	xfs_fileoff_t		last_block;
 	xfs_filblks_t		unmap_len;
@@ -1583,10 +1559,9 @@ xfs_itruncate_extents_flags(
 	ASSERT(first_unmap_block < last_block);
 	unmap_len = last_block - first_unmap_block + 1;
 	while (!done) {
-		xfs_defer_init(&dfops, &first_block);
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
-				    XFS_ITRUNC_MAX_EXTENTS, &first_block,
-				    &dfops, &done);
+				    XFS_ITRUNC_MAX_EXTENTS, &done);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1594,10 +1569,9 @@ xfs_itruncate_extents_flags(
 		 * Duplicate the transaction that has the permanent
 		 * reservation and commit the old transaction.
 		 */
-		xfs_defer_ijoin(&dfops, ip);
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out;
 
 		error = xfs_trans_roll_inode(&tp, ip);
 		if (error)
@@ -1631,7 +1605,7 @@ out_bmap_cancel:
 	 * the transaction can be properly aborted.  We just need to make sure
 	 * we're not holding any resources that we were not when we came in.
 	 */
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp);
 	goto out;
 }
 
@@ -1733,7 +1707,6 @@ xfs_inactive_truncate(
 		ASSERT(XFS_FORCED_SHUTDOWN(mp));
 		return error;
 	}
-
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
@@ -1774,8 +1747,6 @@ STATIC int
 xfs_inactive_ifree(
 	struct xfs_inode *ip)
 {
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
@@ -1812,9 +1783,7 @@ xfs_inactive_ifree(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-	error = xfs_ifree(tp, ip, &dfops);
+	error = xfs_ifree(tp, ip);
 	if (error) {
 		/*
 		 * If we fail to free the inode, shut down.  The cancel
@@ -1840,12 +1809,6 @@ xfs_inactive_ifree(
 	 * Just ignore errors at this point.  There is nothing we can do except
 	 * to try to keep going. Make sure it's not a silent error.
 	 */
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error) {
-		xfs_notice(mp, "%s: xfs_defer_finish returned error %d",
-			__func__, error);
-		xfs_defer_cancel(&dfops);
-	}
 	error = xfs_trans_commit(tp);
 	if (error)
 		xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
@@ -1868,7 +1831,6 @@ xfs_inactive(
 	xfs_inode_t	*ip)
 {
 	struct xfs_mount	*mp;
-	struct xfs_ifork	*cow_ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	int			error;
 	int			truncate = 0;
 
@@ -1877,7 +1839,6 @@ xfs_inactive(
 	 * to clean up here.
 	 */
 	if (VFS_I(ip)->i_mode == 0) {
-		ASSERT(ip->i_df.if_real_bytes == 0);
 		ASSERT(ip->i_df.if_broot_bytes == 0);
 		return;
 	}
@@ -1890,7 +1851,7 @@ xfs_inactive(
 		return;
 
 	/* Try to clean out the cow blocks if there are any. */
-	if (xfs_is_reflink_inode(ip) && cow_ifp->if_bytes > 0)
+	if (xfs_inode_has_cow_data(ip))
 		xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
 
 	if (VFS_I(ip)->i_nlink != 0) {
@@ -2445,9 +2406,8 @@ xfs_ifree_local_data(
  */
 int
 xfs_ifree(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
 {
 	int			error;
 	struct xfs_icluster	xic = { 0 };
@@ -2466,7 +2426,7 @@ xfs_ifree(
 	if (error)
 		return error;
 
-	error = xfs_difree(tp, ip->i_ino, dfops, &xic);
+	error = xfs_difree(tp, ip->i_ino, &xic);
 	if (error)
 		return error;
 
@@ -2577,8 +2537,6 @@ xfs_remove(
 	xfs_trans_t             *tp = NULL;
 	int			is_dir = S_ISDIR(VFS_I(ip)->i_mode);
 	int                     error = 0;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t           first_block;
 	uint			resblks;
 
 	trace_xfs_remove(dp, name);
@@ -2658,13 +2616,10 @@ xfs_remove(
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-	error = xfs_dir_removename(tp, dp, name, ip->i_ino,
-					&first_block, &dfops, resblks);
+	error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks);
 	if (error) {
 		ASSERT(error != -ENOENT);
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 	}
 
 	/*
@@ -2675,10 +2630,6 @@ xfs_remove(
 	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto std_return;
@@ -2688,8 +2639,6 @@ xfs_remove(
 
 	return 0;
 
- out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
  out_trans_cancel:
 	xfs_trans_cancel(tp);
  std_return:
@@ -2749,11 +2698,8 @@ xfs_sort_for_rename(
 
 static int
 xfs_finish_rename(
-	struct xfs_trans	*tp,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_trans	*tp)
 {
-	int			error;
-
 	/*
 	 * If this is a synchronous mount, make sure that the rename transaction
 	 * goes to disk before returning to the user.
@@ -2761,13 +2707,6 @@ xfs_finish_rename(
 	if (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_defer_finish(&tp, dfops);
-	if (error) {
-		xfs_defer_cancel(dfops);
-		xfs_trans_cancel(tp);
-		return error;
-	}
-
 	return xfs_trans_commit(tp);
 }
 
@@ -2785,8 +2724,6 @@ xfs_cross_rename(
 	struct xfs_inode	*dp2,
 	struct xfs_name		*name2,
 	struct xfs_inode	*ip2,
-	struct xfs_defer_ops	*dfops,
-	xfs_fsblock_t		*first_block,
 	int			spaceres)
 {
 	int		error = 0;
@@ -2795,16 +2732,12 @@ xfs_cross_rename(
 	int		dp2_flags = 0;
 
 	/* Swap inode number for dirent in first parent */
-	error = xfs_dir_replace(tp, dp1, name1,
-				ip2->i_ino,
-				first_block, dfops, spaceres);
+	error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, spaceres);
 	if (error)
 		goto out_trans_abort;
 
 	/* Swap inode number for dirent in second parent */
-	error = xfs_dir_replace(tp, dp2, name2,
-				ip1->i_ino,
-				first_block, dfops, spaceres);
+	error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, spaceres);
 	if (error)
 		goto out_trans_abort;
 
@@ -2818,8 +2751,7 @@ xfs_cross_rename(
 
 		if (S_ISDIR(VFS_I(ip2)->i_mode)) {
 			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
-						dp1->i_ino, first_block,
-						dfops, spaceres);
+						dp1->i_ino, spaceres);
 			if (error)
 				goto out_trans_abort;
 
@@ -2845,8 +2777,7 @@ xfs_cross_rename(
 
 		if (S_ISDIR(VFS_I(ip1)->i_mode)) {
 			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
-						dp2->i_ino, first_block,
-						dfops, spaceres);
+						dp2->i_ino, spaceres);
 			if (error)
 				goto out_trans_abort;
 
@@ -2885,10 +2816,9 @@ xfs_cross_rename(
 	}
 	xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
-	return xfs_finish_rename(tp, dfops);
+	return xfs_finish_rename(tp);
 
 out_trans_abort:
-	xfs_defer_cancel(dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -2943,8 +2873,6 @@ xfs_rename(
 {
 	struct xfs_mount	*mp = src_dp->i_mount;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	struct xfs_inode	*wip = NULL;		/* whiteout inode */
 	struct xfs_inode	*inodes[__XFS_SORT_INODES];
 	int			num_inodes = __XFS_SORT_INODES;
@@ -3026,14 +2954,11 @@ xfs_rename(
 		goto out_trans_cancel;
 	}
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-
 	/* RENAME_EXCHANGE is unique from here on. */
 	if (flags & RENAME_EXCHANGE)
 		return xfs_cross_rename(tp, src_dp, src_name, src_ip,
 					target_dp, target_name, target_ip,
-					&dfops, &first_block, spaceres);
+					spaceres);
 
 	/*
 	 * Set up the target.
@@ -3054,10 +2979,9 @@ xfs_rename(
 		 * to account for the ".." reference from the new entry.
 		 */
 		error = xfs_dir_createname(tp, target_dp, target_name,
-						src_ip->i_ino, &first_block,
-						&dfops, spaceres);
+					   src_ip->i_ino, spaceres);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		xfs_trans_ichgtime(tp, target_dp,
 					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -3065,7 +2989,7 @@ xfs_rename(
 		if (new_parent && src_is_directory) {
 			error = xfs_bumplink(tp, target_dp);
 			if (error)
-				goto out_bmap_cancel;
+				goto out_trans_cancel;
 		}
 	} else { /* target_ip != NULL */
 		/*
@@ -3094,10 +3018,9 @@ xfs_rename(
 		 * name at the destination directory, remove it first.
 		 */
 		error = xfs_dir_replace(tp, target_dp, target_name,
-					src_ip->i_ino,
-					&first_block, &dfops, spaceres);
+					src_ip->i_ino, spaceres);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		xfs_trans_ichgtime(tp, target_dp,
 					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -3108,7 +3031,7 @@ xfs_rename(
 		 */
 		error = xfs_droplink(tp, target_ip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		if (src_is_directory) {
 			/*
@@ -3116,7 +3039,7 @@ xfs_rename(
 			 */
 			error = xfs_droplink(tp, target_ip);
 			if (error)
-				goto out_bmap_cancel;
+				goto out_trans_cancel;
 		}
 	} /* target_ip != NULL */
 
@@ -3129,11 +3052,10 @@ xfs_rename(
 		 * directory.
 		 */
 		error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
-					target_dp->i_ino,
-					&first_block, &dfops, spaceres);
+					target_dp->i_ino, spaceres);
 		ASSERT(error != -EEXIST);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -3159,7 +3081,7 @@ xfs_rename(
 		 */
 		error = xfs_droplink(tp, src_dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -3169,12 +3091,12 @@ xfs_rename(
 	 */
 	if (wip) {
 		error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino,
-					&first_block, &dfops, spaceres);
+					spaceres);
 	} else
 		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
-					   &first_block, &dfops, spaceres);
+					   spaceres);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
 	/*
 	 * For whiteouts, we need to bump the link count on the whiteout inode.
@@ -3188,10 +3110,10 @@ xfs_rename(
 		ASSERT(VFS_I(wip)->i_nlink == 0);
 		error = xfs_bumplink(tp, wip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 		error = xfs_iunlink_remove(tp, wip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 		xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
 
 		/*
@@ -3207,18 +3129,16 @@ xfs_rename(
 	if (new_parent)
 		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
 
-	error = xfs_finish_rename(tp, &dfops);
+	error = xfs_finish_rename(tp);
 	if (wip)
-		IRELE(wip);
+		xfs_irele(wip);
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 out_release_wip:
 	if (wip)
-		IRELE(wip);
+		xfs_irele(wip);
 	return error;
 }
 
@@ -3236,7 +3156,6 @@ xfs_iflush_cluster(
 	struct xfs_inode	*cip;
 	int			nr_found;
 	int			clcount = 0;
-	int			bufwasdelwri;
 	int			i;
 
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
@@ -3360,37 +3279,22 @@ cluster_corrupt_out:
 	 * inode buffer and shut down the filesystem.
 	 */
 	rcu_read_unlock();
-	/*
-	 * Clean up the buffer.  If it was delwri, just release it --
-	 * brelse can handle it with no problems.  If not, shut down the
-	 * filesystem before releasing the buffer.
-	 */
-	bufwasdelwri = (bp->b_flags & _XBF_DELWRI_Q);
-	if (bufwasdelwri)
-		xfs_buf_relse(bp);
-
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 
-	if (!bufwasdelwri) {
-		/*
-		 * Just like incore_relse: if we have b_iodone functions,
-		 * mark the buffer as an error and call them.  Otherwise
-		 * mark it as stale and brelse.
-		 */
-		if (bp->b_iodone) {
-			bp->b_flags &= ~XBF_DONE;
-			xfs_buf_stale(bp);
-			xfs_buf_ioerror(bp, -EIO);
-			xfs_buf_ioend(bp);
-		} else {
-			xfs_buf_stale(bp);
-			xfs_buf_relse(bp);
-		}
-	}
-
 	/*
-	 * Unlocks the flush lock
+	 * We'll always have an inode attached to the buffer for completion
+	 * process by the time we are called from xfs_iflush(). Hence we have
+	 * always need to do IO completion processing to abort the inodes
+	 * attached to the buffer.  handle them just like the shutdown case in
+	 * xfs_buf_submit().
 	 */
+	ASSERT(bp->b_iodone);
+	bp->b_flags &= ~XBF_DONE;
+	xfs_buf_stale(bp);
+	xfs_buf_ioerror(bp, -EIO);
+	xfs_buf_ioend(bp);
+
+	/* abort the corrupt inode, as it was not attached to the buffer */
 	xfs_iflush_abort(cip, false);
 	kmem_free(cilist);
 	xfs_perag_put(pag);
@@ -3486,12 +3390,17 @@ xfs_iflush(
 		xfs_log_force(mp, 0);
 
 	/*
-	 * inode clustering:
-	 * see if other inodes can be gathered into this write
+	 * inode clustering: try to gather other inodes into this write
+	 *
+	 * Note: Any error during clustering will result in the filesystem
+	 * being shut down and completion callbacks run on the cluster buffer.
+	 * As we have already flushed and attached this inode to the buffer,
+	 * it has already been aborted and released by xfs_iflush_cluster() and
+	 * so we have no further error handling to do here.
 	 */
 	error = xfs_iflush_cluster(ip, bp);
 	if (error)
-		goto cluster_corrupt_out;
+		return error;
 
 	*bpp = bp;
 	return 0;
@@ -3500,12 +3409,8 @@ corrupt_out:
 	if (bp)
 		xfs_buf_relse(bp);
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-cluster_corrupt_out:
-	error = -EFSCORRUPTED;
 abort_out:
-	/*
-	 * Unlocks the flush lock
-	 */
+	/* abort the corrupt inode, as it was not attached to the buffer */
 	xfs_iflush_abort(ip, false);
 	return error;
 }
@@ -3689,3 +3594,12 @@ xfs_iflush_int(
 corrupt_out:
 	return -EFSCORRUPTED;
 }
+
+/* Release an inode. */
+void
+xfs_irele(
+	struct xfs_inode	*ip)
+{
+	trace_xfs_irele(ip, _RET_IP_);
+	iput(VFS_I(ip));
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 2ed63a49e890..be2014520155 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -15,7 +15,6 @@
 struct xfs_dinode;
 struct xfs_inode;
 struct xfs_buf;
-struct xfs_defer_ops;
 struct xfs_bmbt_irec;
 struct xfs_inode_log_item;
 struct xfs_mount;
@@ -34,9 +33,9 @@ typedef struct xfs_inode {
 	struct xfs_imap		i_imap;		/* location for xfs_imap() */
 
 	/* Extent information. */
-	xfs_ifork_t		*i_afp;		/* attribute fork pointer */
-	xfs_ifork_t		*i_cowfp;	/* copy on write extents */
-	xfs_ifork_t		i_df;		/* data fork */
+	struct xfs_ifork	*i_afp;		/* attribute fork pointer */
+	struct xfs_ifork	*i_cowfp;	/* copy on write extents */
+	struct xfs_ifork	i_df;		/* data fork */
 
 	/* operations vectors */
 	const struct xfs_dir_ops *d_ops;		/* directory ops vector */
@@ -199,6 +198,15 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
 }
 
 /*
+ * Check if an inode has any data in the COW fork.  This might be often false
+ * even for inodes with the reflink flag when there is no pending COW operation.
+ */
+static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
+{
+	return ip->i_cowfp && ip->i_cowfp->if_bytes;
+}
+
+/*
  * In-core inode flags.
  */
 #define XFS_IRECLAIM		(1 << 0) /* started reclaiming this inode */
@@ -415,8 +423,7 @@ uint		xfs_ilock_data_map_shared(struct xfs_inode *);
 uint		xfs_ilock_attr_map_shared(struct xfs_inode *);
 
 uint		xfs_ip2xflags(struct xfs_inode *);
-int		xfs_ifree(struct xfs_trans *, xfs_inode_t *,
-			   struct xfs_defer_ops *);
+int		xfs_ifree(struct xfs_trans *, struct xfs_inode *);
 int		xfs_itruncate_extents_flags(struct xfs_trans **,
 				struct xfs_inode *, int, xfs_fsize_t, int);
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
@@ -484,18 +491,7 @@ static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
 	xfs_finish_inode_setup(ip);
 }
 
-#define IHOLD(ip) \
-do { \
-	ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \
-	ihold(VFS_I(ip)); \
-	trace_xfs_ihold(ip, _THIS_IP_); \
-} while (0)
-
-#define IRELE(ip) \
-do { \
-	trace_xfs_irele(ip, _THIS_IP_); \
-	iput(VFS_I(ip)); \
-} while (0)
+void xfs_irele(struct xfs_inode *ip);
 
 extern struct kmem_zone	*xfs_inode_zone;
 
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 2389c34c172d..fa1c4fe2ffbf 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -194,8 +194,6 @@ xfs_inode_item_format_data_fork(
 			 * to be there by xfs_idata_realloc().
 			 */
 			data_bytes = roundup(ip->i_df.if_bytes, 4);
-			ASSERT(ip->i_df.if_real_bytes == 0 ||
-			       ip->i_df.if_real_bytes >= data_bytes);
 			ASSERT(ip->i_df.if_u1.if_data != NULL);
 			ASSERT(ip->i_d.di_size > 0);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
@@ -280,8 +278,6 @@ xfs_inode_item_format_attr_fork(
 			 * to be there by xfs_idata_realloc().
 			 */
 			data_bytes = roundup(ip->i_afp->if_bytes, 4);
-			ASSERT(ip->i_afp->if_real_bytes == 0 ||
-			       ip->i_afp->if_real_bytes >= data_bytes);
 			ASSERT(ip->i_afp->if_u1.if_data != NULL);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
 					ip->i_afp->if_u1.if_data,
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 49f5492eed3b..6320aca39f39 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2000-2006 Silicon Graphics, Inc.
- * Copyright (c) 2016 Christoph Hellwig.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  * All Rights Reserved.
  */
 #include <linux/iomap.h>
@@ -152,13 +152,11 @@ xfs_iomap_write_direct(
 	xfs_fileoff_t	offset_fsb;
 	xfs_fileoff_t	last_fsb;
 	xfs_filblks_t	count_fsb, resaligned;
-	xfs_fsblock_t	firstfsb;
 	xfs_extlen_t	extsz;
 	int		nimaps;
 	int		quota_flag;
 	int		rt;
 	xfs_trans_t	*tp;
-	struct xfs_defer_ops dfops;
 	uint		qblocks, resblks, resrtextents;
 	int		error;
 	int		lockmode;
@@ -254,21 +252,15 @@ xfs_iomap_write_direct(
 	 * From this point onwards we overwrite the imap pointer that the
 	 * caller gave to us.
 	 */
-	xfs_defer_init(&dfops, &firstfsb);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				bmapi_flags, &firstfsb, resblks, imap,
-				&nimaps, &dfops);
+				bmapi_flags, resblks, imap, &nimaps);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_res_cancel;
 
 	/*
 	 * Complete the transaction
 	 */
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_unlock;
@@ -288,8 +280,7 @@ out_unlock:
 	xfs_iunlock(ip, lockmode);
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+out_res_cancel:
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
@@ -626,7 +617,7 @@ retry:
 	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
 	 * them out if the write happens to fail.
 	 */
-	iomap->flags = IOMAP_F_NEW;
+	iomap->flags |= IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
 	if (isnullstartblock(got.br_startblock))
@@ -660,13 +651,13 @@ xfs_iomap_write_allocate(
 	xfs_inode_t	*ip,
 	int		whichfork,
 	xfs_off_t	offset,
-	xfs_bmbt_irec_t *imap)
+	xfs_bmbt_irec_t *imap,
+	unsigned int	*cow_seq)
 {
 	xfs_mount_t	*mp = ip->i_mount;
+	struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
 	xfs_fileoff_t	offset_fsb, last_block;
 	xfs_fileoff_t	end_fsb, map_start_fsb;
-	xfs_fsblock_t	first_block;
-	struct xfs_defer_ops	dfops;
 	xfs_filblks_t	count_fsb;
 	xfs_trans_t	*tp;
 	int		nimaps;
@@ -716,8 +707,6 @@ xfs_iomap_write_allocate(
 			xfs_ilock(ip, XFS_ILOCK_EXCL);
 			xfs_trans_ijoin(tp, ip, 0);
 
-			xfs_defer_init(&dfops, &first_block);
-
 			/*
 			 * it is possible that the extents have changed since
 			 * we did the read call as we dropped the ilock for a
@@ -770,13 +759,8 @@ xfs_iomap_write_allocate(
 			 * pointer that the caller gave to us.
 			 */
 			error = xfs_bmapi_write(tp, ip, map_start_fsb,
-						count_fsb, flags, &first_block,
-						nres, imap, &nimaps,
-						&dfops);
-			if (error)
-				goto trans_cancel;
-
-			error = xfs_defer_finish(&tp, &dfops);
+						count_fsb, flags, nres, imap,
+						&nimaps);
 			if (error)
 				goto trans_cancel;
 
@@ -784,6 +768,8 @@ xfs_iomap_write_allocate(
 			if (error)
 				goto error0;
 
+			if (whichfork == XFS_COW_FORK)
+				*cow_seq = READ_ONCE(ifp->if_seq);
 			xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		}
 
@@ -810,7 +796,6 @@ xfs_iomap_write_allocate(
 	}
 
 trans_cancel:
-	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 error0:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -828,11 +813,9 @@ xfs_iomap_write_unwritten(
 	xfs_fileoff_t	offset_fsb;
 	xfs_filblks_t	count_fsb;
 	xfs_filblks_t	numblks_fsb;
-	xfs_fsblock_t	firstfsb;
 	int		nimaps;
 	xfs_trans_t	*tp;
 	xfs_bmbt_irec_t imap;
-	struct xfs_defer_ops dfops;
 	struct inode	*inode = VFS_I(ip);
 	xfs_fsize_t	i_size;
 	uint		resblks;
@@ -877,11 +860,10 @@ xfs_iomap_write_unwritten(
 		/*
 		 * Modify the unwritten extent state of the buffer.
 		 */
-		xfs_defer_init(&dfops, &firstfsb);
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-					XFS_BMAPI_CONVERT, &firstfsb, resblks,
-					&imap, &nimaps, &dfops);
+					XFS_BMAPI_CONVERT, resblks, &imap,
+					&nimaps);
 		if (error)
 			goto error_on_bmapi_transaction;
 
@@ -901,10 +883,6 @@ xfs_iomap_write_unwritten(
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		}
 
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto error_on_bmapi_transaction;
-
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
@@ -928,7 +906,6 @@ xfs_iomap_write_unwritten(
 	return 0;
 
 error_on_bmapi_transaction:
-	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -963,12 +940,13 @@ xfs_ilock_for_iomap(
 	unsigned		*lockmode)
 {
 	unsigned		mode = XFS_ILOCK_SHARED;
+	bool			is_write = flags & (IOMAP_WRITE | IOMAP_ZERO);
 
 	/*
 	 * COW writes may allocate delalloc space or convert unwritten COW
 	 * extents, so we need to make sure to take the lock exclusively here.
 	 */
-	if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO))) {
+	if (xfs_is_reflink_inode(ip) && is_write) {
 		/*
 		 * FIXME: It could still overwrite on unshared extents and not
 		 * need allocation.
@@ -989,6 +967,7 @@ xfs_ilock_for_iomap(
 		mode = XFS_ILOCK_EXCL;
 	}
 
+relock:
 	if (flags & IOMAP_NOWAIT) {
 		if (!xfs_ilock_nowait(ip, mode))
 			return -EAGAIN;
@@ -996,6 +975,17 @@ xfs_ilock_for_iomap(
 		xfs_ilock(ip, mode);
 	}
 
+	/*
+	 * The reflink iflag could have changed since the earlier unlocked
+	 * check, so if we got ILOCK_SHARED for a write and but we're now a
+	 * reflink inode we have to switch to ILOCK_EXCL and relock.
+	 */
+	if (mode == XFS_ILOCK_SHARED && is_write && xfs_is_reflink_inode(ip)) {
+		xfs_iunlock(ip, mode);
+		mode = XFS_ILOCK_EXCL;
+		goto relock;
+	}
+
 	*lockmode = mode;
 	return 0;
 }
@@ -1119,7 +1109,7 @@ xfs_file_iomap_begin(
 	if (error)
 		return error;
 
-	iomap->flags = IOMAP_F_NEW;
+	iomap->flags |= IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
 
 out_finish:
@@ -1189,11 +1179,8 @@ xfs_file_iomap_end_delalloc(
 		truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
 					 XFS_FSB_TO_B(mp, end_fsb) - 1);
 
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
 					       end_fsb - start_fsb);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
 		if (error && !XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_alert(mp, "%s: unable to clean up ino %lld",
 				__func__, ip->i_ino);
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 83474c9cede9..c6170548831b 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -14,7 +14,7 @@ struct xfs_bmbt_irec;
 int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
 			struct xfs_bmbt_irec *, int);
 int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t,
-			struct xfs_bmbt_irec *);
+			struct xfs_bmbt_irec *, unsigned int *);
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 
 void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 0fa29f39d658..c3e74f9128e8 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -26,6 +26,7 @@
 #include "xfs_dir2.h"
 #include "xfs_trans_space.h"
 #include "xfs_iomap.h"
+#include "xfs_defer.h"
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
@@ -208,7 +209,7 @@ xfs_generic_create(
 	xfs_finish_inode_setup(ip);
 	if (!tmpfile)
 		xfs_cleanup_inode(dir, inode, dentry);
-	iput(inode);
+	xfs_irele(ip);
 	goto out_free_acl;
 }
 
@@ -390,7 +391,7 @@ xfs_vn_symlink(
  out_cleanup_inode:
 	xfs_finish_inode_setup(cip);
 	xfs_cleanup_inode(dir, inode, dentry);
-	iput(inode);
+	xfs_irele(cip);
  out:
 	return error;
 }
@@ -1253,7 +1254,7 @@ xfs_setup_inode(
 
 	inode_sb_list_add(inode);
 	/* make the inode look hashed for the writeback code */
-	hlist_add_fake(&inode->i_hash);
+	inode_fake_hash(inode);
 
 	inode->i_uid    = xfs_uid_to_kuid(ip->i_d.di_uid);
 	inode->i_gid    = xfs_gid_to_kgid(ip->i_d.di_gid);
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 24f4f1c555b5..e9508ba01ed1 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -114,7 +114,7 @@ xfs_bulkstat_one_int(
 		break;
 	}
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	IRELE(ip);
+	xfs_irele(ip);
 
 	error = formatter(buffer, ubsize, ubused, buf);
 	if (!error)
@@ -458,8 +458,7 @@ xfs_bulkstat(
 		 * pending error, then we are done.
 		 */
 del_cursor:
-		xfs_btree_del_cursor(cur, error ?
-					  XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 		xfs_buf_relse(agbp);
 		if (error)
 			break;
@@ -632,8 +631,7 @@ next_ag:
 
 	kmem_free(buffer);
 	if (cur)
-		xfs_btree_del_cursor(cur, (error ? XFS_BTREE_ERROR :
-					   XFS_BTREE_NOERROR));
+		xfs_btree_del_cursor(cur, error);
 	if (agbp)
 		xfs_buf_relse(agbp);
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 5e56f3b93d4b..c3b610b687d1 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -410,7 +410,7 @@ out_error:
 }
 
 /*
- * Reserve log space and return a ticket corresponding the reservation.
+ * Reserve log space and return a ticket corresponding to the reservation.
  *
  * Each reservation is going to reserve extra space for a log record header.
  * When writes happen to the on-disk log, we don't subtract the length of the
@@ -826,6 +826,88 @@ xfs_log_mount_cancel(
  * deallocation must not be done until source-end.
  */
 
+/* Actually write the unmount record to disk. */
+static void
+xfs_log_write_unmount_record(
+	struct xfs_mount	*mp)
+{
+	/* the data section must be 32 bit size aligned */
+	struct xfs_unmount_log_format magic = {
+		.magic = XLOG_UNMOUNT_TYPE,
+	};
+	struct xfs_log_iovec reg = {
+		.i_addr = &magic,
+		.i_len = sizeof(magic),
+		.i_type = XLOG_REG_TYPE_UNMOUNT,
+	};
+	struct xfs_log_vec vec = {
+		.lv_niovecs = 1,
+		.lv_iovecp = &reg,
+	};
+	struct xlog		*log = mp->m_log;
+	struct xlog_in_core	*iclog;
+	struct xlog_ticket	*tic = NULL;
+	xfs_lsn_t		lsn;
+	uint			flags = XLOG_UNMOUNT_TRANS;
+	int			error;
+
+	error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
+	if (error)
+		goto out_err;
+
+	/*
+	 * If we think the summary counters are bad, clear the unmount header
+	 * flag in the unmount record so that the summary counters will be
+	 * recalculated during log recovery at next mount.  Refer to
+	 * xlog_check_unmount_rec for more details.
+	 */
+	if (XFS_TEST_ERROR((mp->m_flags & XFS_MOUNT_BAD_SUMMARY), mp,
+			XFS_ERRTAG_FORCE_SUMMARY_RECALC)) {
+		xfs_alert(mp, "%s: will fix summary counters at next mount",
+				__func__);
+		flags &= ~XLOG_UNMOUNT_TRANS;
+	}
+
+	/* remove inited flag, and account for space used */
+	tic->t_flags = 0;
+	tic->t_curr_res -= sizeof(magic);
+	error = xlog_write(log, &vec, tic, &lsn, NULL, flags);
+	/*
+	 * At this point, we're umounting anyway, so there's no point in
+	 * transitioning log state to IOERROR. Just continue...
+	 */
+out_err:
+	if (error)
+		xfs_alert(mp, "%s: unmount record failed", __func__);
+
+	spin_lock(&log->l_icloglock);
+	iclog = log->l_iclog;
+	atomic_inc(&iclog->ic_refcnt);
+	xlog_state_want_sync(log, iclog);
+	spin_unlock(&log->l_icloglock);
+	error = xlog_state_release_iclog(log, iclog);
+
+	spin_lock(&log->l_icloglock);
+	switch (iclog->ic_state) {
+	default:
+		if (!XLOG_FORCED_SHUTDOWN(log)) {
+			xlog_wait(&iclog->ic_force_wait, &log->l_icloglock);
+			break;
+		}
+		/* fall through */
+	case XLOG_STATE_ACTIVE:
+	case XLOG_STATE_DIRTY:
+		spin_unlock(&log->l_icloglock);
+		break;
+	}
+
+	if (tic) {
+		trace_xfs_log_umount_write(log, tic);
+		xlog_ungrant_log_space(log, tic);
+		xfs_log_ticket_put(tic);
+	}
+}
+
 /*
  * Unmount record used to have a string "Unmount filesystem--" in the
  * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE).
@@ -842,8 +924,6 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 #ifdef DEBUG
 	xlog_in_core_t	 *first_iclog;
 #endif
-	xlog_ticket_t	*tic = NULL;
-	xfs_lsn_t	 lsn;
 	int		 error;
 
 	/*
@@ -870,66 +950,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 	} while (iclog != first_iclog);
 #endif
 	if (! (XLOG_FORCED_SHUTDOWN(log))) {
-		error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
-		if (!error) {
-			/* the data section must be 32 bit size aligned */
-			struct {
-			    uint16_t magic;
-			    uint16_t pad1;
-			    uint32_t pad2; /* may as well make it 64 bits */
-			} magic = {
-				.magic = XLOG_UNMOUNT_TYPE,
-			};
-			struct xfs_log_iovec reg = {
-				.i_addr = &magic,
-				.i_len = sizeof(magic),
-				.i_type = XLOG_REG_TYPE_UNMOUNT,
-			};
-			struct xfs_log_vec vec = {
-				.lv_niovecs = 1,
-				.lv_iovecp = &reg,
-			};
-
-			/* remove inited flag, and account for space used */
-			tic->t_flags = 0;
-			tic->t_curr_res -= sizeof(magic);
-			error = xlog_write(log, &vec, tic, &lsn,
-					   NULL, XLOG_UNMOUNT_TRANS);
-			/*
-			 * At this point, we're umounting anyway,
-			 * so there's no point in transitioning log state
-			 * to IOERROR. Just continue...
-			 */
-		}
-
-		if (error)
-			xfs_alert(mp, "%s: unmount record failed", __func__);
-
-
-		spin_lock(&log->l_icloglock);
-		iclog = log->l_iclog;
-		atomic_inc(&iclog->ic_refcnt);
-		xlog_state_want_sync(log, iclog);
-		spin_unlock(&log->l_icloglock);
-		error = xlog_state_release_iclog(log, iclog);
-
-		spin_lock(&log->l_icloglock);
-		if (!(iclog->ic_state == XLOG_STATE_ACTIVE ||
-		      iclog->ic_state == XLOG_STATE_DIRTY)) {
-			if (!XLOG_FORCED_SHUTDOWN(log)) {
-				xlog_wait(&iclog->ic_force_wait,
-							&log->l_icloglock);
-			} else {
-				spin_unlock(&log->l_icloglock);
-			}
-		} else {
-			spin_unlock(&log->l_icloglock);
-		}
-		if (tic) {
-			trace_xfs_log_umount_write(log, tic);
-			xlog_ungrant_log_space(log, tic);
-			xfs_log_ticket_put(tic);
-		}
+		xfs_log_write_unmount_record(mp);
 	} else {
 		/*
 		 * We're already in forced_shutdown mode, couldn't
@@ -4083,3 +4104,12 @@ xfs_log_check_lsn(
 
 	return valid;
 }
+
+bool
+xfs_log_in_recovery(
+	struct xfs_mount	*mp)
+{
+	struct xlog		*log = mp->m_log;
+
+	return log->l_flags & XLOG_ACTIVE_RECOVERY;
+}
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 3c1f6a8b4b70..73a64bf32f6f 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -153,5 +153,6 @@ bool	xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
 void	xfs_log_work_queue(struct xfs_mount *mp);
 void	xfs_log_quiesce(struct xfs_mount *mp);
 bool	xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
+bool	xfs_log_in_recovery(struct xfs_mount *);
 
 #endif	/* __XFS_LOG_H__ */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b181b5f57a19..a21dc61ec09e 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -196,7 +196,7 @@ xlog_bread_noalign(
 	bp->b_io_length = nbblks;
 	bp->b_error = 0;
 
-	error = xfs_buf_submit_wait(bp);
+	error = xfs_buf_submit(bp);
 	if (error && !XFS_FORCED_SHUTDOWN(log->l_mp))
 		xfs_buf_ioerror_alert(bp, __func__);
 	return error;
@@ -4733,10 +4733,9 @@ xlog_recover_cancel_rui(
 /* Recover the CUI if necessary. */
 STATIC int
 xlog_recover_process_cui(
-	struct xfs_mount		*mp,
+	struct xfs_trans		*parent_tp,
 	struct xfs_ail			*ailp,
-	struct xfs_log_item		*lip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_log_item		*lip)
 {
 	struct xfs_cui_log_item		*cuip;
 	int				error;
@@ -4749,7 +4748,7 @@ xlog_recover_process_cui(
 		return 0;
 
 	spin_unlock(&ailp->ail_lock);
-	error = xfs_cui_recover(mp, cuip, dfops);
+	error = xfs_cui_recover(parent_tp, cuip);
 	spin_lock(&ailp->ail_lock);
 
 	return error;
@@ -4774,10 +4773,9 @@ xlog_recover_cancel_cui(
 /* Recover the BUI if necessary. */
 STATIC int
 xlog_recover_process_bui(
-	struct xfs_mount		*mp,
+	struct xfs_trans		*parent_tp,
 	struct xfs_ail			*ailp,
-	struct xfs_log_item		*lip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_log_item		*lip)
 {
 	struct xfs_bui_log_item		*buip;
 	int				error;
@@ -4790,7 +4788,7 @@ xlog_recover_process_bui(
 		return 0;
 
 	spin_unlock(&ailp->ail_lock);
-	error = xfs_bui_recover(mp, buip, dfops);
+	error = xfs_bui_recover(parent_tp, buip);
 	spin_lock(&ailp->ail_lock);
 
 	return error;
@@ -4829,9 +4827,9 @@ static inline bool xlog_item_is_intent(struct xfs_log_item *lip)
 /* Take all the collected deferred ops and finish them in order. */
 static int
 xlog_finish_defer_ops(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_trans	*parent_tp)
 {
+	struct xfs_mount	*mp = parent_tp->t_mountp;
 	struct xfs_trans	*tp;
 	int64_t			freeblks;
 	uint			resblks;
@@ -4854,16 +4852,10 @@ xlog_finish_defer_ops(
 			0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
-
-	error = xfs_defer_finish(&tp, dfops);
-	if (error)
-		goto out_cancel;
+	/* transfer all collected dfops to this transaction */
+	xfs_defer_move(tp, parent_tp);
 
 	return xfs_trans_commit(tp);
-
-out_cancel:
-	xfs_trans_cancel(tp);
-	return error;
 }
 
 /*
@@ -4886,23 +4878,34 @@ STATIC int
 xlog_recover_process_intents(
 	struct xlog		*log)
 {
-	struct xfs_defer_ops	dfops;
+	struct xfs_trans	*parent_tp;
 	struct xfs_ail_cursor	cur;
 	struct xfs_log_item	*lip;
 	struct xfs_ail		*ailp;
-	xfs_fsblock_t		firstfsb;
-	int			error = 0;
+	int			error;
 #if defined(DEBUG) || defined(XFS_WARN)
 	xfs_lsn_t		last_lsn;
 #endif
 
+	/*
+	 * The intent recovery handlers commit transactions to complete recovery
+	 * for individual intents, but any new deferred operations that are
+	 * queued during that process are held off until the very end. The
+	 * purpose of this transaction is to serve as a container for deferred
+	 * operations. Each intent recovery handler must transfer dfops here
+	 * before its local transaction commits, and we'll finish the entire
+	 * list below.
+	 */
+	error = xfs_trans_alloc_empty(log->l_mp, &parent_tp);
+	if (error)
+		return error;
+
 	ailp = log->l_ailp;
 	spin_lock(&ailp->ail_lock);
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
 #if defined(DEBUG) || defined(XFS_WARN)
 	last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
 #endif
-	xfs_defer_init(&dfops, &firstfsb);
 	while (lip != NULL) {
 		/*
 		 * We're done when we see something other than an intent.
@@ -4937,12 +4940,10 @@ xlog_recover_process_intents(
 			error = xlog_recover_process_rui(log->l_mp, ailp, lip);
 			break;
 		case XFS_LI_CUI:
-			error = xlog_recover_process_cui(log->l_mp, ailp, lip,
-					&dfops);
+			error = xlog_recover_process_cui(parent_tp, ailp, lip);
 			break;
 		case XFS_LI_BUI:
-			error = xlog_recover_process_bui(log->l_mp, ailp, lip,
-					&dfops);
+			error = xlog_recover_process_bui(parent_tp, ailp, lip);
 			break;
 		}
 		if (error)
@@ -4952,10 +4953,9 @@ xlog_recover_process_intents(
 out:
 	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->ail_lock);
-	if (error)
-		xfs_defer_cancel(&dfops);
-	else
-		error = xlog_finish_defer_ops(log->l_mp, &dfops);
+	if (!error)
+		error = xlog_finish_defer_ops(parent_tp);
+	xfs_trans_cancel(parent_tp);
 
 	return error;
 }
@@ -5094,11 +5094,11 @@ xlog_recover_process_one_iunlink(
 	 */
 	ip->i_d.di_dmevmask = 0;
 
-	IRELE(ip);
+	xfs_irele(ip);
 	return agino;
 
  fail_iput:
-	IRELE(ip);
+	xfs_irele(ip);
  fail:
 	/*
 	 * We can't read in the inode this bucket points to, or this inode
@@ -5707,7 +5707,7 @@ xlog_do_recover(
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = &xfs_sb_buf_ops;
 
-	error = xfs_buf_submit_wait(bp);
+	error = xfs_buf_submit(bp);
 	if (error) {
 		if (!XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_buf_ioerror_alert(bp, __func__);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index a3378252baa1..99db27d6ac8a 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -207,6 +207,9 @@ xfs_initialize_perag(
 		if (xfs_buf_hash_init(pag))
 			goto out_free_pag;
 		init_waitqueue_head(&pag->pagb_wait);
+		spin_lock_init(&pag->pagb_lock);
+		pag->pagb_count = 0;
+		pag->pagb_tree = RB_ROOT;
 
 		if (radix_tree_preload(GFP_NOFS))
 			goto out_hash_destroy;
@@ -606,6 +609,56 @@ xfs_default_resblks(xfs_mount_t *mp)
 	return resblks;
 }
 
+/* Ensure the summary counts are correct. */
+STATIC int
+xfs_check_summary_counts(
+	struct xfs_mount	*mp)
+{
+	/*
+	 * The AG0 superblock verifier rejects in-progress filesystems,
+	 * so we should never see the flag set this far into mounting.
+	 */
+	if (mp->m_sb.sb_inprogress) {
+		xfs_err(mp, "sb_inprogress set after log recovery??");
+		WARN_ON(1);
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * Now the log is mounted, we know if it was an unclean shutdown or
+	 * not. If it was, with the first phase of recovery has completed, we
+	 * have consistent AG blocks on disk. We have not recovered EFIs yet,
+	 * but they are recovered transactionally in the second recovery phase
+	 * later.
+	 *
+	 * If the log was clean when we mounted, we can check the summary
+	 * counters.  If any of them are obviously incorrect, we can recompute
+	 * them from the AGF headers in the next step.
+	 */
+	if (XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
+	    (mp->m_sb.sb_fdblocks > mp->m_sb.sb_dblocks ||
+	     mp->m_sb.sb_ifree > mp->m_sb.sb_icount))
+		mp->m_flags |= XFS_MOUNT_BAD_SUMMARY;
+
+	/*
+	 * We can safely re-initialise incore superblock counters from the
+	 * per-ag data. These may not be correct if the filesystem was not
+	 * cleanly unmounted, so we waited for recovery to finish before doing
+	 * this.
+	 *
+	 * If the filesystem was cleanly unmounted or the previous check did
+	 * not flag anything weird, then we can trust the values in the
+	 * superblock to be correct and we don't need to do anything here.
+	 * Otherwise, recalculate the summary counters.
+	 */
+	if ((!xfs_sb_version_haslazysbcount(&mp->m_sb) ||
+	     XFS_LAST_UNMOUNT_WAS_CLEAN(mp)) &&
+	    !(mp->m_flags & XFS_MOUNT_BAD_SUMMARY))
+		return 0;
+
+	return xfs_initialize_perag_data(mp, mp->m_sb.sb_agcount);
+}
+
 /*
  * This function does the following on an initial mount of a file system:
  *	- reads the superblock from disk and init the mount struct
@@ -831,32 +884,10 @@ xfs_mountfs(
 		goto out_fail_wait;
 	}
 
-	/*
-	 * Now the log is mounted, we know if it was an unclean shutdown or
-	 * not. If it was, with the first phase of recovery has completed, we
-	 * have consistent AG blocks on disk. We have not recovered EFIs yet,
-	 * but they are recovered transactionally in the second recovery phase
-	 * later.
-	 *
-	 * Hence we can safely re-initialise incore superblock counters from
-	 * the per-ag data. These may not be correct if the filesystem was not
-	 * cleanly unmounted, so we need to wait for recovery to finish before
-	 * doing this.
-	 *
-	 * If the filesystem was cleanly unmounted, then we can trust the
-	 * values in the superblock to be correct and we don't need to do
-	 * anything here.
-	 *
-	 * If we are currently making the filesystem, the initialisation will
-	 * fail as the perag data is in an undefined state.
-	 */
-	if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
-	    !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
-	     !mp->m_sb.sb_inprogress) {
-		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
-		if (error)
-			goto out_log_dealloc;
-	}
+	/* Make sure the summary counts are ok. */
+	error = xfs_check_summary_counts(mp);
+	if (error)
+		goto out_log_dealloc;
 
 	/*
 	 * Get and sanity-check the root inode.
@@ -1011,7 +1042,7 @@ xfs_mountfs(
  out_rtunmount:
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
-	IRELE(rip);
+	xfs_irele(rip);
 	/* Clean out dquots that might be in memory after quotacheck. */
 	xfs_qm_unmount(mp);
 	/*
@@ -1067,7 +1098,7 @@ xfs_unmountfs(
 	xfs_fs_unreserve_ag_blocks(mp);
 	xfs_qm_unmount_quotas(mp);
 	xfs_rtunmount_inodes(mp);
-	IRELE(mp->m_rootip);
+	xfs_irele(mp->m_rootip);
 
 	/*
 	 * We can potentially deadlock here if we have an inode cluster
@@ -1395,3 +1426,16 @@ xfs_dev_is_read_only(
 	}
 	return 0;
 }
+
+/* Force the summary counters to be recalculated at next mount. */
+void
+xfs_force_summary_recalc(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
+		return;
+
+	spin_lock(&mp->m_sb_lock);
+	mp->m_flags |= XFS_MOUNT_BAD_SUMMARY;
+	spin_unlock(&mp->m_sb_lock);
+}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 245349d1e23f..7964513c3128 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -202,6 +202,7 @@ typedef struct xfs_mount {
 						   must be synchronous except
 						   for space allocations */
 #define XFS_MOUNT_UNMOUNTING	(1ULL << 1)	/* filesystem is unmounting */
+#define XFS_MOUNT_BAD_SUMMARY	(1ULL << 2)	/* summary counters are bad */
 #define XFS_MOUNT_WAS_CLEAN	(1ULL << 3)
 #define XFS_MOUNT_FS_SHUTDOWN	(1ULL << 4)	/* atomic stop of all filesystem
 						   operations, typically for
@@ -216,7 +217,6 @@ typedef struct xfs_mount {
 #define XFS_MOUNT_SMALL_INUMS	(1ULL << 14)	/* user wants 32bit inodes */
 #define XFS_MOUNT_32BITINODES	(1ULL << 15)	/* inode32 allocator active */
 #define XFS_MOUNT_NOUUID	(1ULL << 16)	/* ignore uuid during mount */
-#define XFS_MOUNT_BARRIER	(1ULL << 17)
 #define XFS_MOUNT_IKEEP		(1ULL << 18)	/* keep empty inode clusters*/
 #define XFS_MOUNT_SWALLOC	(1ULL << 19)	/* turn on stripe width
 						 * allocation */
@@ -434,5 +434,6 @@ int	xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
 
 struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp,
 		int error_class, int error);
+void xfs_force_summary_recalc(struct xfs_mount *mp);
 
 #endif	/* __XFS_MOUNT_H__ */
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 9ceb85cce33a..52ed7904df10 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -231,15 +231,15 @@ xfs_qm_unmount_quotas(
 	 */
 	if (mp->m_quotainfo) {
 		if (mp->m_quotainfo->qi_uquotaip) {
-			IRELE(mp->m_quotainfo->qi_uquotaip);
+			xfs_irele(mp->m_quotainfo->qi_uquotaip);
 			mp->m_quotainfo->qi_uquotaip = NULL;
 		}
 		if (mp->m_quotainfo->qi_gquotaip) {
-			IRELE(mp->m_quotainfo->qi_gquotaip);
+			xfs_irele(mp->m_quotainfo->qi_gquotaip);
 			mp->m_quotainfo->qi_gquotaip = NULL;
 		}
 		if (mp->m_quotainfo->qi_pquotaip) {
-			IRELE(mp->m_quotainfo->qi_pquotaip);
+			xfs_irele(mp->m_quotainfo->qi_pquotaip);
 			mp->m_quotainfo->qi_pquotaip = NULL;
 		}
 	}
@@ -1200,12 +1200,12 @@ xfs_qm_dqusage_adjust(
 			goto error0;
 	}
 
-	IRELE(ip);
+	xfs_irele(ip);
 	*res = BULKSTAT_RV_DIDONE;
 	return 0;
 
 error0:
-	IRELE(ip);
+	xfs_irele(ip);
 	*res = BULKSTAT_RV_GIVEUP;
 	return error;
 }
@@ -1575,11 +1575,11 @@ xfs_qm_init_quotainos(
 
 error_rele:
 	if (uip)
-		IRELE(uip);
+		xfs_irele(uip);
 	if (gip)
-		IRELE(gip);
+		xfs_irele(gip);
 	if (pip)
-		IRELE(pip);
+		xfs_irele(pip);
 	return error;
 }
 
@@ -1588,15 +1588,15 @@ xfs_qm_destroy_quotainos(
 	xfs_quotainfo_t	*qi)
 {
 	if (qi->qi_uquotaip) {
-		IRELE(qi->qi_uquotaip);
+		xfs_irele(qi->qi_uquotaip);
 		qi->qi_uquotaip = NULL; /* paranoia */
 	}
 	if (qi->qi_gquotaip) {
-		IRELE(qi->qi_gquotaip);
+		xfs_irele(qi->qi_gquotaip);
 		qi->qi_gquotaip = NULL;
 	}
 	if (qi->qi_pquotaip) {
-		IRELE(qi->qi_pquotaip);
+		xfs_irele(qi->qi_pquotaip);
 		qi->qi_pquotaip = NULL;
 	}
 }
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index abc8a21e3a82..b3190890f096 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -22,6 +22,7 @@
 #include "xfs_qm.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
+#include "xfs_defer.h"
 
 STATIC int	xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint);
 STATIC int	xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *,
@@ -189,15 +190,15 @@ xfs_qm_scall_quotaoff(
 	 * Release our quotainode references if we don't need them anymore.
 	 */
 	if ((dqtype & XFS_QMOPT_UQUOTA) && q->qi_uquotaip) {
-		IRELE(q->qi_uquotaip);
+		xfs_irele(q->qi_uquotaip);
 		q->qi_uquotaip = NULL;
 	}
 	if ((dqtype & XFS_QMOPT_GQUOTA) && q->qi_gquotaip) {
-		IRELE(q->qi_gquotaip);
+		xfs_irele(q->qi_gquotaip);
 		q->qi_gquotaip = NULL;
 	}
 	if ((dqtype & XFS_QMOPT_PQUOTA) && q->qi_pquotaip) {
-		IRELE(q->qi_pquotaip);
+		xfs_irele(q->qi_pquotaip);
 		q->qi_pquotaip = NULL;
 	}
 
@@ -250,7 +251,7 @@ xfs_qm_scall_trunc_qfile(
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 out_put:
-	IRELE(ip);
+	xfs_irele(ip);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 205fbb2a77e4..a7c0c657dfaf 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -45,7 +45,7 @@ xfs_qm_fill_state(
 	tstate->ino_warnlimit = q->qi_iwarnlimit;
 	tstate->rt_spc_warnlimit = q->qi_rtbwarnlimit;
 	if (tempqip)
-		IRELE(ip);
+		xfs_irele(ip);
 }
 
 /*
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 472a73e9d331..fce38b56b962 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -380,9 +380,8 @@ xfs_cud_init(
  */
 int
 xfs_cui_recover(
-	struct xfs_mount		*mp,
-	struct xfs_cui_log_item		*cuip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_trans		*parent_tp,
+	struct xfs_cui_log_item		*cuip)
 {
 	int				i;
 	int				error = 0;
@@ -398,6 +397,7 @@ xfs_cui_recover(
 	xfs_extlen_t			new_len;
 	struct xfs_bmbt_irec		irec;
 	bool				requeue_only = false;
+	struct xfs_mount		*mp = parent_tp->t_mountp;
 
 	ASSERT(!test_bit(XFS_CUI_RECOVERED, &cuip->cui_flags));
 
@@ -452,6 +452,12 @@ xfs_cui_recover(
 			mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
+	/*
+	 * Recovery stashes all deferred ops during intent processing and
+	 * finishes them on completion. Transfer current dfops state to this
+	 * transaction and transfer the result back before we return.
+	 */
+	xfs_defer_move(tp, parent_tp);
 	cudp = xfs_trans_get_cud(tp, cuip);
 
 	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
@@ -473,7 +479,7 @@ xfs_cui_recover(
 			new_len = refc->pe_len;
 		} else
 			error = xfs_trans_log_finish_refcount_update(tp, cudp,
-				dfops, type, refc->pe_startblock, refc->pe_len,
+				type, refc->pe_startblock, refc->pe_len,
 				&new_fsb, &new_len, &rcur);
 		if (error)
 			goto abort_error;
@@ -484,22 +490,18 @@ xfs_cui_recover(
 			irec.br_blockcount = new_len;
 			switch (type) {
 			case XFS_REFCOUNT_INCREASE:
-				error = xfs_refcount_increase_extent(
-						tp->t_mountp, dfops, &irec);
+				error = xfs_refcount_increase_extent(tp, &irec);
 				break;
 			case XFS_REFCOUNT_DECREASE:
-				error = xfs_refcount_decrease_extent(
-						tp->t_mountp, dfops, &irec);
+				error = xfs_refcount_decrease_extent(tp, &irec);
 				break;
 			case XFS_REFCOUNT_ALLOC_COW:
-				error = xfs_refcount_alloc_cow_extent(
-						tp->t_mountp, dfops,
+				error = xfs_refcount_alloc_cow_extent(tp,
 						irec.br_startblock,
 						irec.br_blockcount);
 				break;
 			case XFS_REFCOUNT_FREE_COW:
-				error = xfs_refcount_free_cow_extent(
-						tp->t_mountp, dfops,
+				error = xfs_refcount_free_cow_extent(tp,
 						irec.br_startblock,
 						irec.br_blockcount);
 				break;
@@ -514,11 +516,13 @@ xfs_cui_recover(
 
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
+	xfs_defer_move(parent_tp, tp);
 	error = xfs_trans_commit(tp);
 	return error;
 
 abort_error:
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
+	xfs_defer_move(parent_tp, tp);
 	xfs_trans_cancel(tp);
 	return error;
 }
diff --git a/fs/xfs/xfs_refcount_item.h b/fs/xfs/xfs_refcount_item.h
index dd830b69cd1e..3896dcc2368f 100644
--- a/fs/xfs/xfs_refcount_item.h
+++ b/fs/xfs/xfs_refcount_item.h
@@ -82,7 +82,6 @@ struct xfs_cud_log_item *xfs_cud_init(struct xfs_mount *,
 		struct xfs_cui_log_item *);
 void xfs_cui_item_free(struct xfs_cui_log_item *);
 void xfs_cui_release(struct xfs_cui_log_item *);
-int xfs_cui_recover(struct xfs_mount *mp, struct xfs_cui_log_item *cuip,
-		struct xfs_defer_ops *dfops);
+int xfs_cui_recover(struct xfs_trans *parent_tp, struct xfs_cui_log_item *cuip);
 
 #endif	/* __XFS_REFCOUNT_ITEM_H__ */
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 592fb2071a03..38f405415b88 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -157,12 +157,12 @@ xfs_reflink_find_shared(
 	if (!agbp)
 		return -ENOMEM;
 
-	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
 
 	error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
 			find_end_of_shared);
 
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 
 	xfs_trans_brelse(tp, agbp);
 	return error;
@@ -312,10 +312,8 @@ xfs_reflink_convert_cow_extent(
 	struct xfs_inode		*ip,
 	struct xfs_bmbt_irec		*imap,
 	xfs_fileoff_t			offset_fsb,
-	xfs_filblks_t			count_fsb,
-	struct xfs_defer_ops		*dfops)
+	xfs_filblks_t			count_fsb)
 {
-	xfs_fsblock_t			first_block = NULLFSBLOCK;
 	int				nimaps = 1;
 
 	if (imap->br_state == XFS_EXT_NORM)
@@ -326,8 +324,8 @@ xfs_reflink_convert_cow_extent(
 	if (imap->br_blockcount == 0)
 		return 0;
 	return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, &first_block,
-			0, imap, &nimaps, dfops);
+			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, 0, imap,
+			&nimaps);
 }
 
 /* Convert all of the unwritten CoW extents in a file's range to real ones. */
@@ -342,8 +340,6 @@ xfs_reflink_convert_cow(
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
 	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
 	struct xfs_bmbt_irec	imap;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block = NULLFSBLOCK;
 	int			nimaps = 1, error = 0;
 
 	ASSERT(count != 0);
@@ -351,8 +347,7 @@ xfs_reflink_convert_cow(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_write(NULL, ip, offset_fsb, count_fsb,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT |
-			XFS_BMAPI_CONVERT_ONLY, &first_block, 0, &imap, &nimaps,
-			&dfops);
+			XFS_BMAPI_CONVERT_ONLY, 0, &imap, &nimaps);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
@@ -369,9 +364,7 @@ xfs_reflink_allocate_cow(
 	xfs_fileoff_t		offset_fsb = imap->br_startoff;
 	xfs_filblks_t		count_fsb = imap->br_blockcount;
 	struct xfs_bmbt_irec	got;
-	struct xfs_defer_ops	dfops;
 	struct xfs_trans	*tp = NULL;
-	xfs_fsblock_t		first_block;
 	int			nimaps, error = 0;
 	bool			trimmed;
 	xfs_filblks_t		resaligned;
@@ -430,23 +423,18 @@ retry:
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(&dfops, &first_block);
 	nimaps = 1;
 
 	/* Allocate the entire reservation as unwritten blocks. */
 	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, &first_block,
-			resblks, imap, &nimaps, &dfops);
+			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC,
+			resblks, imap, &nimaps);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
 	xfs_inode_set_cowblocks_tag(ip);
 
 	/* Finish up. */
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		return error;
@@ -458,10 +446,8 @@ retry:
 	if (nimaps == 0)
 		return -ENOSPC;
 convert:
-	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb,
-			&dfops);
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb);
+out_trans_cancel:
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
 			XFS_QMOPT_RES_REGBLKS);
 out:
@@ -471,69 +457,6 @@ out:
 }
 
 /*
- * Find the CoW reservation for a given byte offset of a file.
- */
-bool
-xfs_reflink_find_cow_mapping(
-	struct xfs_inode		*ip,
-	xfs_off_t			offset,
-	struct xfs_bmbt_irec		*imap)
-{
-	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	xfs_fileoff_t			offset_fsb;
-	struct xfs_bmbt_irec		got;
-	struct xfs_iext_cursor		icur;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
-
-	if (!xfs_is_reflink_inode(ip))
-		return false;
-	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
-	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got))
-		return false;
-	if (got.br_startoff > offset_fsb)
-		return false;
-
-	trace_xfs_reflink_find_cow_mapping(ip, offset, 1, XFS_IO_OVERWRITE,
-			&got);
-	*imap = got;
-	return true;
-}
-
-/*
- * Trim an extent to end at the next CoW reservation past offset_fsb.
- */
-void
-xfs_reflink_trim_irec_to_next_cow(
-	struct xfs_inode		*ip,
-	xfs_fileoff_t			offset_fsb,
-	struct xfs_bmbt_irec		*imap)
-{
-	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	struct xfs_bmbt_irec		got;
-	struct xfs_iext_cursor		icur;
-
-	if (!xfs_is_reflink_inode(ip))
-		return;
-
-	/* Find the extent in the CoW fork. */
-	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got))
-		return;
-
-	/* This is the extent before; try sliding up one. */
-	if (got.br_startoff < offset_fsb) {
-		if (!xfs_iext_next_extent(ifp, &icur, &got))
-			return;
-	}
-
-	if (got.br_startoff >= imap->br_startoff + imap->br_blockcount)
-		return;
-
-	imap->br_blockcount = got.br_startoff - imap->br_startoff;
-	trace_xfs_reflink_trim_irec(ip, imap);
-}
-
-/*
  * Cancel CoW reservations for some block range of an inode.
  *
  * If cancel_real is true this function cancels all COW fork extents for the
@@ -553,11 +476,9 @@ xfs_reflink_cancel_cow_blocks(
 	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	struct xfs_bmbt_irec		got, del;
 	struct xfs_iext_cursor		icur;
-	xfs_fsblock_t			firstfsb;
-	struct xfs_defer_ops		dfops;
 	int				error = 0;
 
-	if (!xfs_is_reflink_inode(ip))
+	if (!xfs_inode_has_cow_data(ip))
 		return 0;
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
 		return 0;
@@ -581,26 +502,21 @@ xfs_reflink_cancel_cow_blocks(
 			if (error)
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
-			xfs_defer_init(&dfops, &firstfsb);
+			ASSERT((*tpp)->t_firstblock == NULLFSBLOCK);
 
 			/* Free the CoW orphan record. */
-			error = xfs_refcount_free_cow_extent(ip->i_mount,
-					&dfops, del.br_startblock,
-					del.br_blockcount);
+			error = xfs_refcount_free_cow_extent(*tpp,
+					del.br_startblock, del.br_blockcount);
 			if (error)
 				break;
 
-			xfs_bmap_add_free(ip->i_mount, &dfops,
-					del.br_startblock, del.br_blockcount,
-					NULL);
+			xfs_bmap_add_free(*tpp, del.br_startblock,
+					  del.br_blockcount, NULL);
 
 			/* Roll the transaction */
-			xfs_defer_ijoin(&dfops, ip);
-			error = xfs_defer_finish(tpp, &dfops);
-			if (error) {
-				xfs_defer_cancel(&dfops);
+			error = xfs_defer_finish(tpp);
+			if (error)
 				break;
-			}
 
 			/* Remove the mapping from the CoW fork. */
 			xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
@@ -623,7 +539,6 @@ next_extent:
 	/* clear tag if cow fork is emptied */
 	if (!ifp->if_bytes)
 		xfs_inode_clear_cowblocks_tag(ip);
-
 	return error;
 }
 
@@ -696,8 +611,6 @@ xfs_reflink_end_cow(
 	struct xfs_trans		*tp;
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
-	xfs_fsblock_t			firstfsb;
-	struct xfs_defer_ops		dfops;
 	int				error;
 	unsigned int			resblks;
 	xfs_filblks_t			rlen;
@@ -764,12 +677,11 @@ xfs_reflink_end_cow(
 			goto prev_extent;
 
 		/* Unmap the old blocks in the data fork. */
-		xfs_defer_init(&dfops, &firstfsb);
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
 		rlen = del.br_blockcount;
-		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
-				&firstfsb, &dfops);
+		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Trim the extent to whatever got unmapped. */
 		if (rlen) {
@@ -779,15 +691,15 @@ xfs_reflink_end_cow(
 		trace_xfs_reflink_cow_remap(ip, &del);
 
 		/* Free the CoW orphan record. */
-		error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
-				del.br_startblock, del.br_blockcount);
+		error = xfs_refcount_free_cow_extent(tp, del.br_startblock,
+				del.br_blockcount);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Map the new blocks into the data fork. */
-		error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
+		error = xfs_bmap_map_extent(tp, ip, &del);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Charge this new data fork mapping to the on-disk quota. */
 		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT,
@@ -796,10 +708,9 @@ xfs_reflink_end_cow(
 		/* Remove the mapping from the CoW fork. */
 		xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
 
-		xfs_defer_ijoin(&dfops, ip);
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 		if (!xfs_iext_get_extent(ifp, &icur, &got))
 			break;
 		continue;
@@ -814,8 +725,6 @@ prev_extent:
 		goto out;
 	return 0;
 
-out_defer:
-	xfs_defer_cancel(&dfops);
 out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1070,9 +979,7 @@ xfs_reflink_remap_extent(
 	struct xfs_mount	*mp = ip->i_mount;
 	bool			real_extent = xfs_bmap_is_real_extent(irec);
 	struct xfs_trans	*tp;
-	xfs_fsblock_t		firstfsb;
 	unsigned int		resblks;
-	struct xfs_defer_ops	dfops;
 	struct xfs_bmbt_irec	uirec;
 	xfs_filblks_t		rlen;
 	xfs_filblks_t		unmap_len;
@@ -1113,11 +1020,10 @@ xfs_reflink_remap_extent(
 	/* Unmap the old blocks in the data fork. */
 	rlen = unmap_len;
 	while (rlen) {
-		xfs_defer_init(&dfops, &firstfsb);
-		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1,
-				&firstfsb, &dfops);
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
+		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/*
 		 * Trim the extent to whatever got unmapped.
@@ -1136,14 +1042,14 @@ xfs_reflink_remap_extent(
 				uirec.br_blockcount, uirec.br_startblock);
 
 		/* Update the refcount tree */
-		error = xfs_refcount_increase_extent(mp, &dfops, &uirec);
+		error = xfs_refcount_increase_extent(tp, &uirec);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Map the new blocks into the data fork. */
-		error = xfs_bmap_map_extent(mp, &dfops, ip, &uirec);
+		error = xfs_bmap_map_extent(tp, ip, &uirec);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Update quota accounting. */
 		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT,
@@ -1162,10 +1068,9 @@ xfs_reflink_remap_extent(
 
 next_extent:
 		/* Process all the deferred stuff. */
-		xfs_defer_ijoin(&dfops, ip);
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 	}
 
 	error = xfs_trans_commit(tp);
@@ -1174,8 +1079,6 @@ next_extent:
 		goto out;
 	return 0;
 
-out_defer:
-	xfs_defer_cancel(&dfops);
 out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 1532827ba911..c585ad9552b2 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -18,10 +18,6 @@ extern int xfs_reflink_allocate_cow(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *imap, bool *shared, uint *lockmode);
 extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
-extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
-		struct xfs_bmbt_irec *imap);
-extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
-		xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap);
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
 		struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 329d4d26c13e..926ed314ffba 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -761,8 +761,6 @@ xfs_growfs_rt_alloc(
 	struct xfs_buf		*bp;	/* temporary buffer for zeroing */
 	xfs_daddr_t		d;		/* disk block address */
 	int			error;		/* error return value */
-	xfs_fsblock_t		firstblock;/* first block allocated in xaction */
-	struct xfs_defer_ops	dfops;		/* list of freed blocks */
 	xfs_fsblock_t		fsbno;		/* filesystem block for bno */
 	struct xfs_bmbt_irec	map;		/* block map output */
 	int			nmap;		/* number of block maps */
@@ -787,24 +785,20 @@ xfs_growfs_rt_alloc(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(&dfops, &firstblock);
 		/*
 		 * Allocate blocks to the bitmap file.
 		 */
 		nmap = 1;
 		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
-					XFS_BMAPI_METADATA, &firstblock,
-					resblks, &map, &nmap, &dfops);
+					XFS_BMAPI_METADATA, resblks, &map,
+					&nmap);
 		if (!error && nmap < 1)
 			error = -ENOSPC;
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 		/*
 		 * Free any blocks freed up in the transaction, then commit.
 		 */
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
 		if (error)
 			return error;
@@ -854,8 +848,6 @@ xfs_growfs_rt_alloc(
 
 	return 0;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
@@ -1215,7 +1207,7 @@ xfs_rtmount_inodes(
 	ASSERT(sbp->sb_rsumino != NULLFSINO);
 	error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip);
 	if (error) {
-		IRELE(mp->m_rbmip);
+		xfs_irele(mp->m_rbmip);
 		return error;
 	}
 	ASSERT(mp->m_rsumip != NULL);
@@ -1227,9 +1219,9 @@ xfs_rtunmount_inodes(
 	struct xfs_mount	*mp)
 {
 	if (mp->m_rbmip)
-		IRELE(mp->m_rbmip);
+		xfs_irele(mp->m_rbmip);
 	if (mp->m_rsumip)
-		IRELE(mp->m_rsumip);
+		xfs_irele(mp->m_rsumip);
 }
 
 /*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 9d791f158dfe..207ee302b1bb 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -65,11 +65,10 @@ enum {
 	Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_biosize,
 	Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid,
 	Opt_mtpt, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
-	Opt_allocsize, Opt_norecovery, Opt_barrier, Opt_nobarrier,
-	Opt_inode64, Opt_inode32, Opt_ikeep, Opt_noikeep,
-	Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2, Opt_filestreams,
-	Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota,
-	Opt_uquota, Opt_gquota, Opt_pquota,
+	Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, Opt_ikeep,
+	Opt_noikeep, Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2,
+	Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota,
+	Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota,
 	Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
 	Opt_discard, Opt_nodiscard, Opt_dax, Opt_err,
 };
@@ -118,14 +117,7 @@ static const match_table_t tokens = {
 	{Opt_qnoenforce, "qnoenforce"},	/* same as uqnoenforce */
 	{Opt_discard,	"discard"},	/* Discard unused blocks */
 	{Opt_nodiscard,	"nodiscard"},	/* Do not discard unused blocks */
-
 	{Opt_dax,	"dax"},		/* Enable direct access to bdev pages */
-
-	/* Deprecated mount options scheduled for removal */
-	{Opt_barrier,	"barrier"},	/* use writer barriers for log write and
-					 * unwritten extent conversion */
-	{Opt_nobarrier,	"nobarrier"},	/* .. disable */
-
 	{Opt_err,	NULL},
 };
 
@@ -209,7 +201,6 @@ xfs_parseargs(
 	 * Set some default flags that could be cleared by the mount option
 	 * parsing.
 	 */
-	mp->m_flags |= XFS_MOUNT_BARRIER;
 	mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
 
 	/*
@@ -362,14 +353,6 @@ xfs_parseargs(
 			mp->m_flags |= XFS_MOUNT_DAX;
 			break;
 #endif
-		case Opt_barrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags |= XFS_MOUNT_BARRIER;
-			break;
-		case Opt_nobarrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags &= ~XFS_MOUNT_BARRIER;
-			break;
 		default:
 			xfs_warn(mp, "unknown mount option [%s].", p);
 			return -EINVAL;
@@ -487,7 +470,6 @@ xfs_showargs(
 	static struct proc_xfs_info xfs_info_unset[] = {
 		/* the few simple ones we can get from the mount struct */
 		{ XFS_MOUNT_COMPAT_IOSIZE,	",largeio" },
-		{ XFS_MOUNT_BARRIER,		",nobarrier" },
 		{ XFS_MOUNT_SMALL_INUMS,	",inode64" },
 		{ 0, NULL }
 	};
@@ -1278,14 +1260,6 @@ xfs_fs_remount(
 
 		token = match_token(p, tokens, args);
 		switch (token) {
-		case Opt_barrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags |= XFS_MOUNT_BARRIER;
-			break;
-		case Opt_nobarrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags &= ~XFS_MOUNT_BARRIER;
-			break;
 		case Opt_inode64:
 			mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
 			mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
@@ -1860,7 +1834,7 @@ MODULE_ALIAS_FS("xfs");
 STATIC int __init
 xfs_init_zones(void)
 {
-	if (bioset_init(&xfs_ioend_bioset, 4 * MAX_BUF_PER_PAGE,
+	if (bioset_init(&xfs_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
 			offsetof(struct xfs_ioend, io_inline_bio),
 			BIOSET_NEED_BVECS))
 		goto out;
@@ -1886,7 +1860,7 @@ xfs_init_zones(void)
 	if (!xfs_da_state_zone)
 		goto out_destroy_btree_cur_zone;
 
-	xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
+	xfs_ifork_zone = kmem_zone_init(sizeof(struct xfs_ifork), "xfs_ifork");
 	if (!xfs_ifork_zone)
 		goto out_destroy_da_state_zone;
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 3783afcb68d2..a3e98c64b6e3 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -163,8 +163,6 @@ xfs_symlink(
 	struct xfs_inode	*ip = NULL;
 	int			error = 0;
 	int			pathlen;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	bool                    unlock_dp_on_error = false;
 	xfs_fileoff_t		first_fsb;
 	xfs_filblks_t		fs_blocks;
@@ -243,13 +241,6 @@ xfs_symlink(
 		goto out_trans_cancel;
 
 	/*
-	 * Initialize the bmap freelist prior to calling either
-	 * bmapi or the directory create code.
-	 */
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-
-	/*
 	 * Allocate an inode for the symlink.
 	 */
 	error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0,
@@ -290,10 +281,9 @@ xfs_symlink(
 		nmaps = XFS_SYMLINK_MAPS;
 
 		error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
-				  XFS_BMAPI_METADATA, &first_block, resblks,
-				  mval, &nmaps, &dfops);
+				  XFS_BMAPI_METADATA, resblks, mval, &nmaps);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		if (resblks)
 			resblks -= fs_blocks;
@@ -311,7 +301,7 @@ xfs_symlink(
 					       BTOBB(byte_cnt), 0);
 			if (!bp) {
 				error = -ENOMEM;
-				goto out_bmap_cancel;
+				goto out_trans_cancel;
 			}
 			bp->b_ops = &xfs_symlink_buf_ops;
 
@@ -338,10 +328,9 @@ xfs_symlink(
 	/*
 	 * Create the directory entry for the symlink.
 	 */
-	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino,
-					&first_block, &dfops, resblks);
+	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino, resblks);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
@@ -354,10 +343,6 @@ xfs_symlink(
 		xfs_trans_set_sync(tp);
 	}
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_release_inode;
@@ -369,8 +354,6 @@ xfs_symlink(
 	*ipp = ip;
 	return 0;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 out_release_inode:
@@ -381,7 +364,7 @@ out_release_inode:
 	 */
 	if (ip) {
 		xfs_finish_inode_setup(ip);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 
 	xfs_qm_dqrele(udqp);
@@ -403,8 +386,6 @@ xfs_inactive_symlink_rmt(
 	xfs_buf_t	*bp;
 	int		done;
 	int		error;
-	xfs_fsblock_t	first_block;
-	struct xfs_defer_ops	dfops;
 	int		i;
 	xfs_mount_t	*mp;
 	xfs_bmbt_irec_t	mval[XFS_SYMLINK_MAPS];
@@ -443,7 +424,6 @@ xfs_inactive_symlink_rmt(
 	 * Find the block(s) so we can inval and unmap them.
 	 */
 	done = 0;
-	xfs_defer_init(&dfops, &first_block);
 	nmaps = ARRAY_SIZE(mval);
 	error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
 				mval, &nmaps, 0);
@@ -458,28 +438,21 @@ xfs_inactive_symlink_rmt(
 			XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0);
 		if (!bp) {
 			error = -ENOMEM;
-			goto error_bmap_cancel;
+			goto error_trans_cancel;
 		}
 		xfs_trans_binval(tp, bp);
 	}
 	/*
 	 * Unmap the dead block(s) to the dfops.
 	 */
-	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps,
-			    &first_block, &dfops, &done);
+	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &done);
 	if (error)
-		goto error_bmap_cancel;
+		goto error_trans_cancel;
 	ASSERT(done);
-	/*
-	 * Commit the first transaction.  This logs the EFI and the inode.
-	 */
-	xfs_defer_ijoin(&dfops, ip);
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto error_bmap_cancel;
 
 	/*
-	 * Commit the transaction containing extent freeing and EFDs.
+	 * Commit the transaction. This first logs the EFI and the inode, then
+	 * rolls and commits the transaction that frees the extents.
 	 */
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	error = xfs_trans_commit(tp);
@@ -498,8 +471,6 @@ xfs_inactive_symlink_rmt(
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return 0;
 
-error_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 error_trans_cancel:
 	xfs_trans_cancel(tp);
 error_unlock:
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 972d45d28097..ad315e83bc02 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -310,7 +310,6 @@ DEFINE_BUF_EVENT(xfs_buf_hold);
 DEFINE_BUF_EVENT(xfs_buf_rele);
 DEFINE_BUF_EVENT(xfs_buf_iodone);
 DEFINE_BUF_EVENT(xfs_buf_submit);
-DEFINE_BUF_EVENT(xfs_buf_submit_wait);
 DEFINE_BUF_EVENT(xfs_buf_lock);
 DEFINE_BUF_EVENT(xfs_buf_lock_done);
 DEFINE_BUF_EVENT(xfs_buf_trylock_fail);
@@ -1153,33 +1152,23 @@ DECLARE_EVENT_CLASS(xfs_page_class,
 		__field(loff_t, size)
 		__field(unsigned long, offset)
 		__field(unsigned int, length)
-		__field(int, delalloc)
-		__field(int, unwritten)
 	),
 	TP_fast_assign(
-		int delalloc = -1, unwritten = -1;
-
-		if (page_has_buffers(page))
-			xfs_count_page_state(page, &delalloc, &unwritten);
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = XFS_I(inode)->i_ino;
 		__entry->pgoff = page_offset(page);
 		__entry->size = i_size_read(inode);
 		__entry->offset = off;
 		__entry->length = len;
-		__entry->delalloc = delalloc;
-		__entry->unwritten = unwritten;
 	),
 	TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx "
-		  "length %x delalloc %d unwritten %d",
+		  "length %x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->pgoff,
 		  __entry->size,
 		  __entry->offset,
-		  __entry->length,
-		  __entry->delalloc,
-		  __entry->unwritten)
+		  __entry->length)
 )
 
 #define DEFINE_PAGE_EVENT(name)		\
@@ -1263,9 +1252,6 @@ DEFINE_EVENT(xfs_imap_class, name,	\
 	TP_ARGS(ip, offset, count, type, irec))
 DEFINE_IOMAP_EVENT(xfs_map_blocks_found);
 DEFINE_IOMAP_EVENT(xfs_map_blocks_alloc);
-DEFINE_IOMAP_EVENT(xfs_get_blocks_found);
-DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc);
-DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct);
 DEFINE_IOMAP_EVENT(xfs_iomap_alloc);
 DEFINE_IOMAP_EVENT(xfs_iomap_found);
 
@@ -1304,7 +1290,6 @@ DEFINE_EVENT(xfs_simple_io_class, name,	\
 	TP_ARGS(ip, offset, count))
 DEFINE_SIMPLE_IO_EVENT(xfs_delalloc_enospc);
 DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert);
-DEFINE_SIMPLE_IO_EVENT(xfs_get_blocks_notfound);
 DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize);
 DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
@@ -1604,7 +1589,7 @@ DECLARE_EVENT_CLASS(xfs_alloc_class,
 		__entry->wasfromfl = args->wasfromfl;
 		__entry->resv = args->resv;
 		__entry->datatype = args->datatype;
-		__entry->firstblock = args->firstblock;
+		__entry->firstblock = args->tp->t_firstblock;
 	),
 	TP_printk("dev %d:%d agno %u agbno %u minlen %u maxlen %u mod %u "
 		  "prod %u minleft %u total %u alignment %u minalignslop %u "
@@ -2228,67 +2213,54 @@ DEFINE_BTREE_CUR_EVENT(xfs_btree_overlapped_query_range);
 
 /* deferred ops */
 struct xfs_defer_pending;
-struct xfs_defer_ops;
 
 DECLARE_EVENT_CLASS(xfs_defer_class,
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop,
-		 unsigned long caller_ip),
-	TP_ARGS(mp, dop, caller_ip),
+	TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip),
+	TP_ARGS(tp, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(void *, dop)
+		__field(struct xfs_trans *, tp)
 		__field(char, committed)
-		__field(char, low)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
-		__entry->dev = mp ? mp->m_super->s_dev : 0;
-		__entry->dop = dop;
-		__entry->committed = dop->dop_committed;
-		__entry->low = dop->dop_low;
+		__entry->dev = tp->t_mountp->m_super->s_dev;
+		__entry->tp = tp;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d ops %p committed %d low %d, caller %pS",
+	TP_printk("dev %d:%d tp %p caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->dop,
-		  __entry->committed,
-		  __entry->low,
+		  __entry->tp,
 		  (char *)__entry->caller_ip)
 )
 #define DEFINE_DEFER_EVENT(name) \
 DEFINE_EVENT(xfs_defer_class, name, \
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, \
-		 unsigned long caller_ip), \
-	TP_ARGS(mp, dop, caller_ip))
+	TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip), \
+	TP_ARGS(tp, caller_ip))
 
 DECLARE_EVENT_CLASS(xfs_defer_error_class,
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, int error),
-	TP_ARGS(mp, dop, error),
+	TP_PROTO(struct xfs_trans *tp, int error),
+	TP_ARGS(tp, error),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(void *, dop)
+		__field(struct xfs_trans *, tp)
 		__field(char, committed)
-		__field(char, low)
 		__field(int, error)
 	),
 	TP_fast_assign(
-		__entry->dev = mp ? mp->m_super->s_dev : 0;
-		__entry->dop = dop;
-		__entry->committed = dop->dop_committed;
-		__entry->low = dop->dop_low;
+		__entry->dev = tp->t_mountp->m_super->s_dev;
+		__entry->tp = tp;
 		__entry->error = error;
 	),
-	TP_printk("dev %d:%d ops %p committed %d low %d err %d",
+	TP_printk("dev %d:%d tp %p err %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->dop,
-		  __entry->committed,
-		  __entry->low,
+		  __entry->tp,
 		  __entry->error)
 )
 #define DEFINE_DEFER_ERROR_EVENT(name) \
 DEFINE_EVENT(xfs_defer_error_class, name, \
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, int error), \
-	TP_ARGS(mp, dop, error))
+	TP_PROTO(struct xfs_trans *tp, int error), \
+	TP_ARGS(tp, error))
 
 DECLARE_EVENT_CLASS(xfs_defer_pending_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp),
@@ -2407,7 +2379,6 @@ DEFINE_EVENT(xfs_map_extent_deferred_class, name, \
 		 xfs_exntst_t state), \
 	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state))
 
-DEFINE_DEFER_EVENT(xfs_defer_init);
 DEFINE_DEFER_EVENT(xfs_defer_cancel);
 DEFINE_DEFER_EVENT(xfs_defer_trans_roll);
 DEFINE_DEFER_EVENT(xfs_defer_trans_abort);
@@ -2417,9 +2388,8 @@ DEFINE_DEFER_EVENT(xfs_defer_finish_done);
 DEFINE_DEFER_ERROR_EVENT(xfs_defer_trans_roll_error);
 DEFINE_DEFER_ERROR_EVENT(xfs_defer_finish_error);
 
-DEFINE_DEFER_PENDING_EVENT(xfs_defer_intake_work);
-DEFINE_DEFER_PENDING_EVENT(xfs_defer_intake_cancel);
-DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_cancel);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_create_intent);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_cancel_list);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_finish);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort);
 
@@ -3215,8 +3185,6 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow);
 DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
 
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write);
-DEFINE_IOMAP_EVENT(xfs_reflink_find_cow_mapping);
-DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
 
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index e040af120b69..bedc5a5133a5 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -100,6 +100,8 @@ xfs_trans_dup(
 	ntp->t_mountp = tp->t_mountp;
 	INIT_LIST_HEAD(&ntp->t_items);
 	INIT_LIST_HEAD(&ntp->t_busy);
+	INIT_LIST_HEAD(&ntp->t_dfops);
+	ntp->t_firstblock = NULLFSBLOCK;
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(tp->t_ticket != NULL);
@@ -118,7 +120,9 @@ xfs_trans_dup(
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
 	tp->t_rtx_res = tp->t_rtx_res_used;
 	ntp->t_pflags = tp->t_pflags;
-	ntp->t_agfl_dfops = tp->t_agfl_dfops;
+
+	/* move deferred ops over to the new tp */
+	xfs_defer_move(ntp, tp);
 
 	xfs_trans_dup_dqinfo(tp, ntp);
 
@@ -258,7 +262,12 @@ xfs_trans_alloc(
 	if (!(flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_start_intwrite(mp->m_super);
 
-	WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
+	/*
+	 * Zero-reservation ("empty") transactions can't modify anything, so
+	 * they're allowed to run while we're frozen.
+	 */
+	WARN_ON(resp->tr_logres > 0 &&
+		mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
 	atomic_inc(&mp->m_active_trans);
 
 	tp = kmem_zone_zalloc(xfs_trans_zone,
@@ -268,6 +277,8 @@ xfs_trans_alloc(
 	tp->t_mountp = mp;
 	INIT_LIST_HEAD(&tp->t_items);
 	INIT_LIST_HEAD(&tp->t_busy);
+	INIT_LIST_HEAD(&tp->t_dfops);
+	tp->t_firstblock = NULLFSBLOCK;
 
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
 	if (error) {
@@ -909,12 +920,21 @@ __xfs_trans_commit(
 	int			error = 0;
 	int			sync = tp->t_flags & XFS_TRANS_SYNC;
 
-	ASSERT(!tp->t_agfl_dfops ||
-	       !xfs_defer_has_unfinished_work(tp->t_agfl_dfops) || regrant);
-
 	trace_xfs_trans_commit(tp, _RET_IP_);
 
 	/*
+	 * Finish deferred items on final commit. Only permanent transactions
+	 * should ever have deferred ops.
+	 */
+	WARN_ON_ONCE(!list_empty(&tp->t_dfops) &&
+		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
+	if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) {
+		error = xfs_defer_finish_noroll(&tp);
+		if (error)
+			goto out_unreserve;
+	}
+
+	/*
 	 * If there is nothing to be logged by the transaction,
 	 * then unlock all of the items associated with the
 	 * transaction and free the transaction structure.
@@ -1003,6 +1023,9 @@ xfs_trans_cancel(
 
 	trace_xfs_trans_cancel(tp, _RET_IP_);
 
+	if (tp->t_flags & XFS_TRANS_PERM_LOG_RES)
+		xfs_defer_cancel(tp);
+
 	/*
 	 * See if the caller is relying on us to shut down the
 	 * filesystem.  This happens in paths where we detect
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 6526314f0b8f..c3d278e96ad1 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -24,7 +24,6 @@ struct xfs_rui_log_item;
 struct xfs_btree_cur;
 struct xfs_cui_log_item;
 struct xfs_cud_log_item;
-struct xfs_defer_ops;
 struct xfs_bui_log_item;
 struct xfs_bud_log_item;
 
@@ -90,6 +89,11 @@ void	xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
 #define XFS_ITEM_LOCKED		2
 #define XFS_ITEM_FLUSHING	3
 
+/*
+ * Deferred operation item relogging limits.
+ */
+#define XFS_DEFER_OPS_NR_INODES	2	/* join up to two inodes */
+#define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
 
 /*
  * This is the structure maintained for every active transaction.
@@ -102,11 +106,11 @@ typedef struct xfs_trans {
 	unsigned int		t_blk_res_used;	/* # of resvd blocks used */
 	unsigned int		t_rtx_res;	/* # of rt extents resvd */
 	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
+	unsigned int		t_flags;	/* misc flags */
+	xfs_fsblock_t		t_firstblock;	/* first block allocated */
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
-	struct xfs_defer_ops	*t_agfl_dfops;	/* optional agfl fixup dfops */
-	unsigned int		t_flags;	/* misc flags */
 	int64_t			t_icount_delta;	/* superblock icount change */
 	int64_t			t_ifree_delta;	/* superblock ifree change */
 	int64_t			t_fdblocks_delta; /* superblock fdblocks chg */
@@ -128,6 +132,7 @@ typedef struct xfs_trans {
 	int64_t			t_rextslog_delta;/* superblocks rextslog chg */
 	struct list_head	t_items;	/* log item descriptors */
 	struct list_head	t_busy;		/* list of busy extents */
+	struct list_head	t_dfops;	/* deferred operations */
 	unsigned long		t_pflags;	/* saved process flags state */
 } xfs_trans_t;
 
@@ -258,7 +263,7 @@ void xfs_refcount_update_init_defer_op(void);
 struct xfs_cud_log_item *xfs_trans_get_cud(struct xfs_trans *tp,
 		struct xfs_cui_log_item *cuip);
 int xfs_trans_log_finish_refcount_update(struct xfs_trans *tp,
-		struct xfs_cud_log_item *cudp, struct xfs_defer_ops *dfops,
+		struct xfs_cud_log_item *cudp,
 		enum xfs_refcount_intent_type type, xfs_fsblock_t startblock,
 		xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb,
 		xfs_extlen_t *new_len, struct xfs_btree_cur **pcur);
@@ -270,9 +275,9 @@ void xfs_bmap_update_init_defer_op(void);
 struct xfs_bud_log_item *xfs_trans_get_bud(struct xfs_trans *tp,
 		struct xfs_bui_log_item *buip);
 int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp,
-		struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops,
-		enum xfs_bmap_intent_type type, struct xfs_inode *ip,
-		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t *blockcount, xfs_exntst_t state);
+		struct xfs_bud_log_item *rudp, enum xfs_bmap_intent_type type,
+		struct xfs_inode *ip, int whichfork, xfs_fileoff_t startoff,
+		xfs_fsblock_t startblock, xfs_filblks_t *blockcount,
+		xfs_exntst_t state);
 
 #endif	/* __XFS_TRANS_H__ */
diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c
index a15a5cd867f9..741c558b2179 100644
--- a/fs/xfs/xfs_trans_bmap.c
+++ b/fs/xfs/xfs_trans_bmap.c
@@ -43,7 +43,6 @@ int
 xfs_trans_log_finish_bmap_update(
 	struct xfs_trans		*tp,
 	struct xfs_bud_log_item		*budp,
-	struct xfs_defer_ops		*dop,
 	enum xfs_bmap_intent_type	type,
 	struct xfs_inode		*ip,
 	int				whichfork,
@@ -54,7 +53,7 @@ xfs_trans_log_finish_bmap_update(
 {
 	int				error;
 
-	error = xfs_bmap_finish_one(tp, dop, ip, type, whichfork, startoff,
+	error = xfs_bmap_finish_one(tp, ip, type, whichfork, startoff,
 			startblock, blockcount, state);
 
 	/*
@@ -176,7 +175,6 @@ xfs_bmap_update_create_done(
 STATIC int
 xfs_bmap_update_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
@@ -187,7 +185,7 @@ xfs_bmap_update_finish_item(
 
 	bmap = container_of(item, struct xfs_bmap_intent, bi_list);
 	count = bmap->bi_bmap.br_blockcount;
-	error = xfs_trans_log_finish_bmap_update(tp, done_item, dop,
+	error = xfs_trans_log_finish_bmap_update(tp, done_item,
 			bmap->bi_type,
 			bmap->bi_owner, bmap->bi_whichfork,
 			bmap->bi_bmap.br_startoff,
diff --git a/fs/xfs/xfs_trans_extfree.c b/fs/xfs/xfs_trans_extfree.c
index bd66c76f55e6..855c0b651fd4 100644
--- a/fs/xfs/xfs_trans_extfree.c
+++ b/fs/xfs/xfs_trans_extfree.c
@@ -171,7 +171,6 @@ xfs_extent_free_create_done(
 STATIC int
 xfs_extent_free_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
@@ -226,7 +225,6 @@ static const struct xfs_defer_op_type xfs_extent_free_defer_type = {
 STATIC int
 xfs_agfl_free_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
diff --git a/fs/xfs/xfs_trans_refcount.c b/fs/xfs/xfs_trans_refcount.c
index 46dd4fca8aa7..523c55663954 100644
--- a/fs/xfs/xfs_trans_refcount.c
+++ b/fs/xfs/xfs_trans_refcount.c
@@ -42,7 +42,6 @@ int
 xfs_trans_log_finish_refcount_update(
 	struct xfs_trans		*tp,
 	struct xfs_cud_log_item		*cudp,
-	struct xfs_defer_ops		*dop,
 	enum xfs_refcount_intent_type	type,
 	xfs_fsblock_t			startblock,
 	xfs_extlen_t			blockcount,
@@ -52,7 +51,7 @@ xfs_trans_log_finish_refcount_update(
 {
 	int				error;
 
-	error = xfs_refcount_finish_one(tp, dop, type, startblock,
+	error = xfs_refcount_finish_one(tp, type, startblock,
 			blockcount, new_fsb, new_len, pcur);
 
 	/*
@@ -169,7 +168,6 @@ xfs_refcount_update_create_done(
 STATIC int
 xfs_refcount_update_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
@@ -180,7 +178,7 @@ xfs_refcount_update_finish_item(
 	int				error;
 
 	refc = container_of(item, struct xfs_refcount_intent, ri_list);
-	error = xfs_trans_log_finish_refcount_update(tp, done_item, dop,
+	error = xfs_trans_log_finish_refcount_update(tp, done_item,
 			refc->ri_type,
 			refc->ri_startblock,
 			refc->ri_blockcount,
diff --git a/fs/xfs/xfs_trans_rmap.c b/fs/xfs/xfs_trans_rmap.c
index 726d8e2c0558..05b00e40251f 100644
--- a/fs/xfs/xfs_trans_rmap.c
+++ b/fs/xfs/xfs_trans_rmap.c
@@ -193,7 +193,6 @@ xfs_rmap_update_create_done(
 STATIC int
 xfs_rmap_update_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 48d84f0d9547..88072c92ace2 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -12,7 +12,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20180531
+#define ACPI_CA_VERSION                 0x20180629
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 1624e2be485c..82cb4eb225a4 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -118,6 +118,10 @@ static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata)
 	     (void *)section - (void *)(estatus + 1) < estatus->data_length; \
 	     section = acpi_hest_get_next(section))
 
+#ifdef CONFIG_ACPI_APEI_SEA
 int ghes_notify_sea(void);
+#else
+static inline int ghes_notify_sea(void) { return -ENOENT; }
+#endif
 
 #endif /* GHES_H */
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index ec07f23678ea..0d4b1d3dbc1e 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -84,42 +84,59 @@ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 ne
 }
 #endif
 
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+#ifdef arch_atomic_fetch_add_unless
+#define atomic_fetch_add_unless atomic_fetch_add_unless
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	kasan_check_write(v, sizeof(*v));
-	return __arch_atomic_add_unless(v, a, u);
+	return arch_atomic_fetch_add_unless(v, a, u);
 }
+#endif
 
-
-static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
+#ifdef arch_atomic64_fetch_add_unless
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
+static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	kasan_check_write(v, sizeof(*v));
-	return arch_atomic64_add_unless(v, a, u);
+	return arch_atomic64_fetch_add_unless(v, a, u);
 }
+#endif
 
+#ifdef arch_atomic_inc
+#define atomic_inc atomic_inc
 static __always_inline void atomic_inc(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic_inc(v);
 }
+#endif
 
+#ifdef arch_atomic64_inc
+#define atomic64_inc atomic64_inc
 static __always_inline void atomic64_inc(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_inc(v);
 }
+#endif
 
+#ifdef arch_atomic_dec
+#define atomic_dec atomic_dec
 static __always_inline void atomic_dec(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic_dec(v);
 }
+#endif
 
+#ifdef atch_atomic64_dec
+#define atomic64_dec
 static __always_inline void atomic64_dec(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_dec(v);
 }
+#endif
 
 static __always_inline void atomic_add(int i, atomic_t *v)
 {
@@ -181,65 +198,95 @@ static __always_inline void atomic64_xor(s64 i, atomic64_t *v)
 	arch_atomic64_xor(i, v);
 }
 
+#ifdef arch_atomic_inc_return
+#define atomic_inc_return atomic_inc_return
 static __always_inline int atomic_inc_return(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_return(v);
 }
+#endif
 
+#ifdef arch_atomic64_in_return
+#define atomic64_inc_return atomic64_inc_return
 static __always_inline s64 atomic64_inc_return(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_return(v);
 }
+#endif
 
+#ifdef arch_atomic_dec_return
+#define atomic_dec_return atomic_dec_return
 static __always_inline int atomic_dec_return(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_return(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_return
+#define atomic64_dec_return atomic64_dec_return
 static __always_inline s64 atomic64_dec_return(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_return(v);
 }
+#endif
 
-static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v)
+#ifdef arch_atomic64_inc_not_zero
+#define atomic64_inc_not_zero atomic64_inc_not_zero
+static __always_inline bool atomic64_inc_not_zero(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_not_zero(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_if_positive
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_if_positive(v);
 }
+#endif
 
+#ifdef arch_atomic_dec_and_test
+#define atomic_dec_and_test atomic_dec_and_test
 static __always_inline bool atomic_dec_and_test(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_and_test
+#define atomic64_dec_and_test atomic64_dec_and_test
 static __always_inline bool atomic64_dec_and_test(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic_inc_and_test
+#define atomic_inc_and_test atomic_inc_and_test
 static __always_inline bool atomic_inc_and_test(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic64_inc_and_test
+#define atomic64_inc_and_test atomic64_inc_and_test
 static __always_inline bool atomic64_inc_and_test(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_and_test(v);
 }
+#endif
 
 static __always_inline int atomic_add_return(int i, atomic_t *v)
 {
@@ -325,152 +372,96 @@ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v)
 	return arch_atomic64_fetch_xor(i, v);
 }
 
+#ifdef arch_atomic_sub_and_test
+#define atomic_sub_and_test atomic_sub_and_test
 static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_sub_and_test(i, v);
 }
+#endif
 
+#ifdef arch_atomic64_sub_and_test
+#define atomic64_sub_and_test atomic64_sub_and_test
 static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_sub_and_test(i, v);
 }
+#endif
 
+#ifdef arch_atomic_add_negative
+#define atomic_add_negative atomic_add_negative
 static __always_inline bool atomic_add_negative(int i, atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_add_negative(i, v);
 }
+#endif
 
+#ifdef arch_atomic64_add_negative
+#define atomic64_add_negative atomic64_add_negative
 static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_add_negative(i, v);
 }
+#endif
 
-static __always_inline unsigned long
-cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
+#define xchg(ptr, new)							\
+({									\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_xchg(__ai_ptr, (new));					\
+})
 
 #define cmpxchg(ptr, old, new)						\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg_size((ptr), (unsigned long)(old),	\
-		(unsigned long)(new), sizeof(*(ptr))));			\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg(__ai_ptr, (old), (new));				\
 })
 
-static __always_inline unsigned long
-sync_cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new,
-		  int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_sync_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_sync_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_sync_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_sync_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
-
 #define sync_cmpxchg(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))sync_cmpxchg_size((ptr),			\
-		(unsigned long)(old), (unsigned long)(new),		\
-		sizeof(*(ptr))));					\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_sync_cmpxchg(__ai_ptr, (old), (new));			\
 })
 
-static __always_inline unsigned long
-cmpxchg_local_size(volatile void *ptr, unsigned long old, unsigned long new,
-		   int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_cmpxchg_local((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_cmpxchg_local((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_cmpxchg_local((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_cmpxchg_local((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
-
 #define cmpxchg_local(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg_local_size((ptr),			\
-		(unsigned long)(old), (unsigned long)(new),		\
-		sizeof(*(ptr))));					\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg_local(__ai_ptr, (old), (new));			\
 })
 
-static __always_inline u64
-cmpxchg64_size(volatile u64 *ptr, u64 old, u64 new)
-{
-	kasan_check_write(ptr, sizeof(*ptr));
-	return arch_cmpxchg64(ptr, old, new);
-}
-
 #define cmpxchg64(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg64_size((ptr), (u64)(old),		\
-		(u64)(new)));						\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg64(__ai_ptr, (old), (new));				\
 })
 
-static __always_inline u64
-cmpxchg64_local_size(volatile u64 *ptr, u64 old, u64 new)
-{
-	kasan_check_write(ptr, sizeof(*ptr));
-	return arch_cmpxchg64_local(ptr, old, new);
-}
-
 #define cmpxchg64_local(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg64_local_size((ptr), (u64)(old),	\
-		(u64)(new)));						\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg64_local(__ai_ptr, (old), (new));			\
 })
 
-/*
- * Originally we had the following code here:
- *     __typeof__(p1) ____p1 = (p1);
- *     kasan_check_write(____p1, 2 * sizeof(*____p1));
- *     arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2));
- * But it leads to compilation failures (see gcc issue 72873).
- * So for now it's left non-instrumented.
- * There are few callers of cmpxchg_double(), so it's not critical.
- */
 #define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\
 ({									\
-	arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2));	\
+	typeof(p1) __ai_p1 = (p1);					\
+	kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1));		\
+	arch_cmpxchg_double(__ai_p1, (p2), (o1), (o2), (n1), (n2));	\
 })
 
-#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)			\
-({									\
-	arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2));	\
+#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)				\
+({										\
+	typeof(p1) __ai_p1 = (p1);						\
+	kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1));			\
+	arch_cmpxchg_double_local(__ai_p1, (p2), (o1), (o2), (n1), (n2));	\
 })
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index abe6dd9ca2a8..13324aa828eb 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -186,11 +186,6 @@ ATOMIC_OP(xor, ^)
 
 #include <linux/irqflags.h>
 
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
-	return atomic_add_return(i, v) < 0;
-}
-
 static inline void atomic_add(int i, atomic_t *v)
 {
 	atomic_add_return(i, v);
@@ -201,35 +196,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	atomic_sub_return(i, v);
 }
 
-static inline void atomic_inc(atomic_t *v)
-{
-	atomic_add_return(1, v);
-}
-
-static inline void atomic_dec(atomic_t *v)
-{
-	atomic_sub_return(1, v);
-}
-
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
-#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
-#ifndef __atomic_add_unless
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
-		c = old;
-	return c;
-}
-#endif
-
 #endif /* __ASM_GENERIC_ATOMIC_H */
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index 8d28eb010d0d..97b28b7f1f29 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -11,6 +11,7 @@
  */
 #ifndef _ASM_GENERIC_ATOMIC64_H
 #define _ASM_GENERIC_ATOMIC64_H
+#include <linux/types.h>
 
 typedef struct {
 	long long counter;
@@ -50,18 +51,10 @@ ATOMIC64_OPS(xor)
 #undef ATOMIC64_OP
 
 extern long long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
 extern long long atomic64_xchg(atomic64_t *v, long long new);
-extern int	 atomic64_add_unless(atomic64_t *v, long long a, long long u);
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v) 	atomic64_add_unless((v), 1LL, 0LL)
+extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif  /*  _ASM_GENERIC_ATOMIC64_H  */
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 04deffaf5f7d..dd90c9792909 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -2,189 +2,67 @@
 #ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_
 #define _ASM_GENERIC_BITOPS_ATOMIC_H_
 
-#include <asm/types.h>
-#include <linux/irqflags.h>
-
-#ifdef CONFIG_SMP
-#include <asm/spinlock.h>
-#include <asm/cache.h>		/* we use L1_CACHE_BYTES */
-
-/* Use an array of spinlocks for our atomic_ts.
- * Hash function to index into a different SPINLOCK.
- * Since "a" is usually an address, use one spinlock per cacheline.
- */
-#  define ATOMIC_HASH_SIZE 4
-#  define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
-
-extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
-
-/* Can't use raw_spin_lock_irq because of #include problems, so
- * this is the substitute */
-#define _atomic_spin_lock_irqsave(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);	\
-	local_irq_save(f);			\
-	arch_spin_lock(s);			\
-} while(0)
-
-#define _atomic_spin_unlock_irqrestore(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);		\
-	arch_spin_unlock(s);				\
-	local_irq_restore(f);				\
-} while(0)
-
-
-#else
-#  define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
-#  define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
-#endif
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
 
 /*
- * NMI events can occur at any time, including when interrupts have been
- * disabled by *_irqsave().  So you can get NMI events occurring while a
- * *_bit function is holding a spin lock.  If the NMI handler also wants
- * to do bit manipulation (and they do) then you can get a deadlock
- * between the original caller of *_bit() and the NMI handler.
- *
- * by Keith Owens
+ * Implementation of atomic bitops using atomic-fetch ops.
+ * See Documentation/atomic_bitops.txt for details.
  */
 
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note: there are no guarantees that this function will not be reordered
- * on non x86 architectures, so if you are writing portable code,
- * make sure not to rely on its reordering guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(int nr, volatile unsigned long *addr)
+static inline void set_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p  |= mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p &= ~mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered. It may be
- * reordered on other architectures than x86.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static inline void change_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p ^= mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It may be reordered on other architectures than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
 
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old | mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	if (READ_ONCE(*p) & mask)
+		return 1;
 
-	return (old & mask) != 0;
+	old = atomic_long_fetch_or(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It can be reorderdered on other architectures other than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
 
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old & ~mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	if (!(READ_ONCE(*p) & mask))
+		return 0;
 
-	return (old & mask) != 0;
+	old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old ^ mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
 
-	return (old & mask) != 0;
+	p += BIT_WORD(nr);
+	old = atomic_long_fetch_xor(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
 #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */
diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
index 67ab280ad134..3ae021368f48 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_GENERIC_BITOPS_LOCK_H_
 #define _ASM_GENERIC_BITOPS_LOCK_H_
 
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
 /**
  * test_and_set_bit_lock - Set a bit and return its old value, for lock
  * @nr: Bit to set
@@ -11,7 +15,20 @@
  * the returned value is 0.
  * It can be used to implement bit locks.
  */
-#define test_and_set_bit_lock(nr, addr)	test_and_set_bit(nr, addr)
+static inline int test_and_set_bit_lock(unsigned int nr,
+					volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	if (READ_ONCE(*p) & mask)
+		return 1;
+
+	old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
+	return !!(old & mask);
+}
+
 
 /**
  * clear_bit_unlock - Clear a bit in memory, for unlock
@@ -20,11 +37,11 @@
  *
  * This operation is atomic and provides release barrier semantics.
  */
-#define clear_bit_unlock(nr, addr)	\
-do {					\
-	smp_mb__before_atomic();	\
-	clear_bit(nr, addr);		\
-} while (0)
+static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
+{
+	p += BIT_WORD(nr);
+	atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
+}
 
 /**
  * __clear_bit_unlock - Clear a bit in memory, for unlock
@@ -37,11 +54,38 @@ do {					\
  *
  * See for example x86's implementation.
  */
-#define __clear_bit_unlock(nr, addr)	\
-do {					\
-	smp_mb__before_atomic();	\
-	clear_bit(nr, addr);		\
-} while (0)
+static inline void __clear_bit_unlock(unsigned int nr,
+				      volatile unsigned long *p)
+{
+	unsigned long old;
 
-#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
+	p += BIT_WORD(nr);
+	old = READ_ONCE(*p);
+	old &= ~BIT_MASK(nr);
+	atomic_long_set_release((atomic_long_t *)p, old);
+}
+
+/**
+ * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
+ *                                     byte is negative, for unlock.
+ * @nr: the bit to clear
+ * @addr: the address to start counting from
+ *
+ * This is a bit of a one-trick-pony for the filemap code, which clears
+ * PG_locked and tests PG_waiters,
+ */
+#ifndef clear_bit_unlock_is_negative_byte
+static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr,
+						     volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
+	return !!(old & BIT(7));
+}
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+#endif
 
+#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f59639afaa39..a75cb371cd19 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1019,8 +1019,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
 int pud_clear_huge(pud_t *pud);
 int pmd_clear_huge(pmd_t *pmd);
-int pud_free_pmd_page(pud_t *pud);
-int pmd_free_pte_page(pmd_t *pmd);
+int pud_free_pmd_page(pud_t *pud, unsigned long addr);
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
 static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
@@ -1046,11 +1046,11 @@ static inline int pmd_clear_huge(pmd_t *pmd)
 {
 	return 0;
 }
-static inline int pud_free_pmd_page(pud_t *pud)
+static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
 	return 0;
 }
-static inline int pmd_free_pte_page(pmd_t *pmd)
+static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	return 0;
 }
@@ -1083,6 +1083,18 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 static inline void init_espfix_bsp(void) { }
 #endif
 
+#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
+static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	return true;
+}
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return false;
+}
+#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */
+
 #endif /* !__ASSEMBLY__ */
 
 #ifndef io_remap_pfn_range
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index faddde44de8c..e811ef7b8350 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -265,34 +265,52 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
  * For now w.r.t page table cache, mark the range_size as PAGE_SIZE
  */
 
+#ifndef pte_free_tlb
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
+#endif
 
+#ifndef pmd_free_tlb
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
+#endif
 
 #ifndef __ARCH_HAS_4LEVEL_HACK
+#ifndef pud_free_tlb
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
+#endif
 
 #ifndef __ARCH_HAS_5LEVEL_HACK
+#ifndef p4d_free_tlb
 #define p4d_free_tlb(tlb, pudp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
 		__p4d_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
+#endif
 
 #define tlb_migrate_finish(mm) do {} while (0)
 
+/*
+ * Used to flush the TLB when page tables are removed, when lazy
+ * TLB mode may cause a CPU to retain intermediate translations
+ * pointing to about-to-be-freed page table memory.
+ */
+#ifndef HAVE_TLB_FLUSH_REMOVE_TABLES
+#define tlb_flush_remove_tables(mm) do {} while (0)
+#define tlb_flush_remove_tables_local(mm) do {} while (0)
+#endif
+
 #endif /* _ASM_GENERIC__TLB_H */
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index cc414db9da0a..482461d8931d 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -245,7 +245,8 @@ ssize_t af_alg_sendpage(struct socket *sock, struct page *page,
 			int offset, size_t size, int flags);
 void af_alg_free_resources(struct af_alg_async_req *areq);
 void af_alg_async_cb(struct crypto_async_request *_req, int err);
-__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events);
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
+			 poll_table *wait);
 struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
 					   unsigned int areqlen);
 int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
diff --git a/include/drm/drm_audio_component.h b/include/drm/drm_audio_component.h
new file mode 100644
index 000000000000..4923b00328c1
--- /dev/null
+++ b/include/drm/drm_audio_component.h
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: MIT
+// Copyright © 2014 Intel Corporation
+
+#ifndef _DRM_AUDIO_COMPONENT_H_
+#define _DRM_AUDIO_COMPONENT_H_
+
+struct drm_audio_component;
+
+/**
+ * struct drm_audio_component_ops - Ops implemented by DRM driver, called by hda driver
+ */
+struct drm_audio_component_ops {
+	/**
+	 * @owner: drm module to pin down
+	 */
+	struct module *owner;
+	/**
+	 * @get_power: get the POWER_DOMAIN_AUDIO power well
+	 *
+	 * Request the power well to be turned on.
+	 */
+	void (*get_power)(struct device *);
+	/**
+	 * @put_power: put the POWER_DOMAIN_AUDIO power well
+	 *
+	 * Allow the power well to be turned off.
+	 */
+	void (*put_power)(struct device *);
+	/**
+	 * @codec_wake_override: Enable/disable codec wake signal
+	 */
+	void (*codec_wake_override)(struct device *, bool enable);
+	/**
+	 * @get_cdclk_freq: Get the Core Display Clock in kHz
+	 */
+	int (*get_cdclk_freq)(struct device *);
+	/**
+	 * @sync_audio_rate: set n/cts based on the sample rate
+	 *
+	 * Called from audio driver. After audio driver sets the
+	 * sample rate, it will call this function to set n/cts
+	 */
+	int (*sync_audio_rate)(struct device *, int port, int pipe, int rate);
+	/**
+	 * @get_eld: fill the audio state and ELD bytes for the given port
+	 *
+	 * Called from audio driver to get the HDMI/DP audio state of the given
+	 * digital port, and also fetch ELD bytes to the given pointer.
+	 *
+	 * It returns the byte size of the original ELD (not the actually
+	 * copied size), zero for an invalid ELD, or a negative error code.
+	 *
+	 * Note that the returned size may be over @max_bytes.  Then it
+	 * implies that only a part of ELD has been copied to the buffer.
+	 */
+	int (*get_eld)(struct device *, int port, int pipe, bool *enabled,
+		       unsigned char *buf, int max_bytes);
+};
+
+/**
+ * struct drm_audio_component_audio_ops - Ops implemented by hda driver, called by DRM driver
+ */
+struct drm_audio_component_audio_ops {
+	/**
+	 * @audio_ptr: Pointer to be used in call to pin_eld_notify
+	 */
+	void *audio_ptr;
+	/**
+	 * @pin_eld_notify: Notify the HDA driver that pin sense and/or ELD information has changed
+	 *
+	 * Called when the DRM driver has set up audio pipeline or has just
+	 * begun to tear it down. This allows the HDA driver to update its
+	 * status accordingly (even when the HDA controller is in power save
+	 * mode).
+	 */
+	void (*pin_eld_notify)(void *audio_ptr, int port, int pipe);
+	/**
+	 * @pin2port: Check and convert from pin node to port number
+	 *
+	 * Called by HDA driver to check and convert from the pin widget node
+	 * number to a port number in the graphics side.
+	 */
+	int (*pin2port)(void *audio_ptr, int pin);
+	/**
+	 * @master_bind: (Optional) component master bind callback
+	 *
+	 * Called at binding master component, for HDA codec-specific
+	 * handling of dynamic binding.
+	 */
+	int (*master_bind)(struct device *dev, struct drm_audio_component *);
+	/**
+	 * @master_unbind: (Optional) component master unbind callback
+	 *
+	 * Called at unbinding master component, for HDA codec-specific
+	 * handling of dynamic unbinding.
+	 */
+	void (*master_unbind)(struct device *dev, struct drm_audio_component *);
+};
+
+/**
+ * struct drm_audio_component - Used for direct communication between DRM and hda drivers
+ */
+struct drm_audio_component {
+	/**
+	 * @dev: DRM device, used as parameter for ops
+	 */
+	struct device *dev;
+	/**
+	 * @ops: Ops implemented by DRM driver, called by hda driver
+	 */
+	const struct drm_audio_component_ops *ops;
+	/**
+	 * @audio_ops: Ops implemented by hda driver, called by DRM driver
+	 */
+	const struct drm_audio_component_audio_ops *audio_ops;
+};
+
+#endif /* _DRM_AUDIO_COMPONENT_H_ */
diff --git a/include/drm/i915_component.h b/include/drm/i915_component.h
index 346b1f5cb180..fca22d463e1b 100644
--- a/include/drm/i915_component.h
+++ b/include/drm/i915_component.h
@@ -24,101 +24,26 @@
 #ifndef _I915_COMPONENT_H_
 #define _I915_COMPONENT_H_
 
+#include "drm_audio_component.h"
+
 /* MAX_PORT is the number of port
  * It must be sync with I915_MAX_PORTS defined i915_drv.h
  */
 #define MAX_PORTS 6
 
 /**
- * struct i915_audio_component_ops - Ops implemented by i915 driver, called by hda driver
- */
-struct i915_audio_component_ops {
-	/**
-	 * @owner: i915 module
-	 */
-	struct module *owner;
-	/**
-	 * @get_power: get the POWER_DOMAIN_AUDIO power well
-	 *
-	 * Request the power well to be turned on.
-	 */
-	void (*get_power)(struct device *);
-	/**
-	 * @put_power: put the POWER_DOMAIN_AUDIO power well
-	 *
-	 * Allow the power well to be turned off.
-	 */
-	void (*put_power)(struct device *);
-	/**
-	 * @codec_wake_override: Enable/disable codec wake signal
-	 */
-	void (*codec_wake_override)(struct device *, bool enable);
-	/**
-	 * @get_cdclk_freq: Get the Core Display Clock in kHz
-	 */
-	int (*get_cdclk_freq)(struct device *);
-	/**
-	 * @sync_audio_rate: set n/cts based on the sample rate
-	 *
-	 * Called from audio driver. After audio driver sets the
-	 * sample rate, it will call this function to set n/cts
-	 */
-	int (*sync_audio_rate)(struct device *, int port, int pipe, int rate);
-	/**
-	 * @get_eld: fill the audio state and ELD bytes for the given port
-	 *
-	 * Called from audio driver to get the HDMI/DP audio state of the given
-	 * digital port, and also fetch ELD bytes to the given pointer.
-	 *
-	 * It returns the byte size of the original ELD (not the actually
-	 * copied size), zero for an invalid ELD, or a negative error code.
-	 *
-	 * Note that the returned size may be over @max_bytes.  Then it
-	 * implies that only a part of ELD has been copied to the buffer.
-	 */
-	int (*get_eld)(struct device *, int port, int pipe, bool *enabled,
-		       unsigned char *buf, int max_bytes);
-};
-
-/**
- * struct i915_audio_component_audio_ops - Ops implemented by hda driver, called by i915 driver
- */
-struct i915_audio_component_audio_ops {
-	/**
-	 * @audio_ptr: Pointer to be used in call to pin_eld_notify
-	 */
-	void *audio_ptr;
-	/**
-	 * @pin_eld_notify: Notify the HDA driver that pin sense and/or ELD information has changed
-	 *
-	 * Called when the i915 driver has set up audio pipeline or has just
-	 * begun to tear it down. This allows the HDA driver to update its
-	 * status accordingly (even when the HDA controller is in power save
-	 * mode).
-	 */
-	void (*pin_eld_notify)(void *audio_ptr, int port, int pipe);
-};
-
-/**
  * struct i915_audio_component - Used for direct communication between i915 and hda drivers
  */
 struct i915_audio_component {
 	/**
-	 * @dev: i915 device, used as parameter for ops
+	 * @base: the drm_audio_component base class
 	 */
-	struct device *dev;
+	struct drm_audio_component	base;
+
 	/**
 	 * @aud_sample_rate: the array of audio sample rate per port
 	 */
 	int aud_sample_rate[MAX_PORTS];
-	/**
-	 * @ops: Ops implemented by i915 driver, called by hda driver
-	 */
-	const struct i915_audio_component_ops *ops;
-	/**
-	 * @audio_ops: Ops implemented by hda driver, called by i915 driver
-	 */
-	const struct i915_audio_component_audio_ops *audio_ops;
 };
 
 #endif /* _I915_COMPONENT_H_ */
diff --git a/include/dt-bindings/clock/imx6ul-clock.h b/include/dt-bindings/clock/imx6ul-clock.h
index 9564597cbfac..0aa1d9c3e0b9 100644
--- a/include/dt-bindings/clock/imx6ul-clock.h
+++ b/include/dt-bindings/clock/imx6ul-clock.h
@@ -235,27 +235,25 @@
 #define IMX6UL_CLK_CSI_PODF		222
 #define IMX6UL_CLK_PLL3_120M		223
 #define IMX6UL_CLK_KPP			224
-#define IMX6UL_CLK_CKO1_SEL		225
-#define IMX6UL_CLK_CKO1_PODF		226
-#define IMX6UL_CLK_CKO1			227
-#define IMX6UL_CLK_CKO2_SEL		228
-#define IMX6UL_CLK_CKO2_PODF		229
-#define IMX6UL_CLK_CKO2			230
-#define IMX6UL_CLK_CKO			231
-
-/* For i.MX6ULL */
-#define IMX6ULL_CLK_ESAI_PRED		232
-#define IMX6ULL_CLK_ESAI_PODF		233
-#define IMX6ULL_CLK_ESAI_EXTAL		234
-#define IMX6ULL_CLK_ESAI_MEM		235
-#define IMX6ULL_CLK_ESAI_IPG		236
-#define IMX6ULL_CLK_DCP_CLK		237
-#define IMX6ULL_CLK_EPDC_PRE_SEL	238
-#define IMX6ULL_CLK_EPDC_SEL		239
-#define IMX6ULL_CLK_EPDC_PODF		240
-#define IMX6ULL_CLK_EPDC_ACLK		241
-#define IMX6ULL_CLK_EPDC_PIX		242
-#define IMX6ULL_CLK_ESAI_SEL		243
+#define IMX6ULL_CLK_ESAI_PRED		225
+#define IMX6ULL_CLK_ESAI_PODF		226
+#define IMX6ULL_CLK_ESAI_EXTAL		227
+#define IMX6ULL_CLK_ESAI_MEM		228
+#define IMX6ULL_CLK_ESAI_IPG		229
+#define IMX6ULL_CLK_DCP_CLK		230
+#define IMX6ULL_CLK_EPDC_PRE_SEL	231
+#define IMX6ULL_CLK_EPDC_SEL		232
+#define IMX6ULL_CLK_EPDC_PODF		233
+#define IMX6ULL_CLK_EPDC_ACLK		234
+#define IMX6ULL_CLK_EPDC_PIX		235
+#define IMX6ULL_CLK_ESAI_SEL		236
+#define IMX6UL_CLK_CKO1_SEL		237
+#define IMX6UL_CLK_CKO1_PODF		238
+#define IMX6UL_CLK_CKO1			239
+#define IMX6UL_CLK_CKO2_SEL		240
+#define IMX6UL_CLK_CKO2_PODF		241
+#define IMX6UL_CLK_CKO2			242
+#define IMX6UL_CLK_CKO			243
 #define IMX6UL_CLK_END			244
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6UL_H */
diff --git a/include/dt-bindings/clock/rk3399-ddr.h b/include/dt-bindings/clock/rk3399-ddr.h
new file mode 100644
index 000000000000..ed2280844963
--- /dev/null
+++ b/include/dt-bindings/clock/rk3399-ddr.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */
+
+#ifndef DT_BINDINGS_DDR_H
+#define DT_BINDINGS_DDR_H
+
+/*
+ * DDR3 SDRAM Standard Speed Bins include tCK, tRCD, tRP, tRAS and tRC for
+ * each corresponding bin.
+ */
+
+/* DDR3-800 (5-5-5) */
+#define DDR3_800D	0
+/* DDR3-800 (6-6-6) */
+#define DDR3_800E	1
+/* DDR3-1066 (6-6-6) */
+#define DDR3_1066E	2
+/* DDR3-1066 (7-7-7) */
+#define DDR3_1066F	3
+/* DDR3-1066 (8-8-8) */
+#define DDR3_1066G	4
+/* DDR3-1333 (7-7-7) */
+#define DDR3_1333F	5
+/* DDR3-1333 (8-8-8) */
+#define DDR3_1333G	6
+/* DDR3-1333 (9-9-9) */
+#define DDR3_1333H	7
+/* DDR3-1333 (10-10-10) */
+#define DDR3_1333J 	8
+/* DDR3-1600 (8-8-8) */
+#define DDR3_1600G	9
+/* DDR3-1600 (9-9-9) */
+#define DDR3_1600H	10
+/* DDR3-1600 (10-10-10) */
+#define DDR3_1600J	11
+/* DDR3-1600 (11-11-11) */
+#define DDR3_1600K	12
+/* DDR3-1600 (10-10-10) */
+#define DDR3_1866J	13
+/* DDR3-1866 (11-11-11) */
+#define DDR3_1866K	14
+/* DDR3-1866 (12-12-12) */
+#define DDR3_1866L	15
+/* DDR3-1866 (13-13-13) */
+#define DDR3_1866M	16
+/* DDR3-2133 (11-11-11) */
+#define DDR3_2133K	17
+/* DDR3-2133 (12-12-12) */
+#define DDR3_2133L	18
+/* DDR3-2133 (13-13-13) */
+#define DDR3_2133M	19
+/* DDR3-2133 (14-14-14) */
+#define DDR3_2133N	20
+/* DDR3 ATF default */
+#define DDR3_DEFAULT	21
+
+#endif
diff --git a/include/dt-bindings/pinctrl/at91.h b/include/dt-bindings/pinctrl/at91.h
index 2732d6c0fb39..eb81867eac77 100644
--- a/include/dt-bindings/pinctrl/at91.h
+++ b/include/dt-bindings/pinctrl/at91.h
@@ -39,4 +39,8 @@
 #define AT91_PERIPH_C		3
 #define AT91_PERIPH_D		4
 
+#define ATMEL_PIO_DRVSTR_LO	1
+#define ATMEL_PIO_DRVSTR_ME	2
+#define ATMEL_PIO_DRVSTR_HI	3
+
 #endif /* __DT_BINDINGS_AT91_PINCTRL_H__ */
diff --git a/include/dt-bindings/pinctrl/samsung.h b/include/dt-bindings/pinctrl/samsung.h
index ceb672305f59..b1832506b923 100644
--- a/include/dt-bindings/pinctrl/samsung.h
+++ b/include/dt-bindings/pinctrl/samsung.h
@@ -1,14 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Samsung's Exynos pinctrl bindings
  *
  * Copyright (c) 2016 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  * Author: Krzysztof Kozlowski <krzk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __DT_BINDINGS_PINCTRL_SAMSUNG_H__
 #define __DT_BINDINGS_PINCTRL_SAMSUNG_H__
diff --git a/include/dt-bindings/regulator/maxim,max77802.h b/include/dt-bindings/regulator/maxim,max77802.h
index cf28631d7109..d0baba1973d4 100644
--- a/include/dt-bindings/regulator/maxim,max77802.h
+++ b/include/dt-bindings/regulator/maxim,max77802.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2014 Google, Inc
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Device Tree binding constants for the Maxim 77802 PMIC regulators
  */
 
diff --git a/include/dt-bindings/regulator/qcom,rpmh-regulator.h b/include/dt-bindings/regulator/qcom,rpmh-regulator.h
new file mode 100644
index 000000000000..86713dcf9e02
--- /dev/null
+++ b/include/dt-bindings/regulator/qcom,rpmh-regulator.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, The Linux Foundation. All rights reserved. */
+
+#ifndef __QCOM_RPMH_REGULATOR_H
+#define __QCOM_RPMH_REGULATOR_H
+
+/*
+ * These mode constants may be used to specify modes for various RPMh regulator
+ * device tree properties (e.g. regulator-initial-mode).  Each type of regulator
+ * supports a subset of the possible modes.
+ *
+ * %RPMH_REGULATOR_MODE_RET:	Retention mode in which only an extremely small
+ *				load current is allowed.  This mode is supported
+ *				by LDO and SMPS type regulators.
+ * %RPMH_REGULATOR_MODE_LPM:	Low power mode in which a small load current is
+ *				allowed.  This mode corresponds to PFM for SMPS
+ *				and BOB type regulators.  This mode is supported
+ *				by LDO, HFSMPS, BOB, and PMIC4 FTSMPS type
+ *				regulators.
+ * %RPMH_REGULATOR_MODE_AUTO:	Auto mode in which the regulator hardware
+ *				automatically switches between LPM and HPM based
+ *				upon the real-time load current.  This mode is
+ *				supported by HFSMPS, BOB, and PMIC4 FTSMPS type
+ *				regulators.
+ * %RPMH_REGULATOR_MODE_HPM:	High power mode in which the full rated current
+ *				of the regulator is allowed.  This mode
+ *				corresponds to PWM for SMPS and BOB type
+ *				regulators.  This mode is supported by all types
+ *				of regulators.
+ */
+#define RPMH_REGULATOR_MODE_RET		0
+#define RPMH_REGULATOR_MODE_LPM		1
+#define RPMH_REGULATOR_MODE_AUTO	2
+#define RPMH_REGULATOR_MODE_HPM		3
+
+#endif
diff --git a/include/dt-bindings/soc/qcom,rpmh-rsc.h b/include/dt-bindings/soc/qcom,rpmh-rsc.h
new file mode 100644
index 000000000000..868f998ea998
--- /dev/null
+++ b/include/dt-bindings/soc/qcom,rpmh-rsc.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __DT_QCOM_RPMH_RSC_H__
+#define __DT_QCOM_RPMH_RSC_H__
+
+#define SLEEP_TCS	0
+#define WAKE_TCS	1
+#define ACTIVE_TCS	2
+#define CONTROL_TCS	3
+
+#endif /* __DT_QCOM_RPMH_RSC_H__ */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4b35a66383f9..de8d3d3fa651 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -443,6 +443,9 @@ int acpi_check_resource_conflict(const struct resource *res);
 int acpi_check_region(resource_size_t start, resource_size_t n,
 		      const char *name);
 
+acpi_status acpi_release_memory(acpi_handle handle, struct resource *res,
+				u32 level);
+
 int acpi_resources_are_enforced(void);
 
 #ifdef CONFIG_HIBERNATION
@@ -1055,27 +1058,20 @@ static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
 
 /* Device properties */
 
-#define MAX_ACPI_REFERENCE_ARGS	8
-struct acpi_reference_args {
-	struct acpi_device *adev;
-	size_t nargs;
-	u64 args[MAX_ACPI_REFERENCE_ARGS];
-};
-
 #ifdef CONFIG_ACPI
 int acpi_dev_get_property(const struct acpi_device *adev, const char *name,
 			  acpi_object_type type, const union acpi_object **obj);
 int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 				const char *name, size_t index, size_t num_args,
-				struct acpi_reference_args *args);
+				struct fwnode_reference_args *args);
 
 static inline int acpi_node_get_property_reference(
 				const struct fwnode_handle *fwnode,
 				const char *name, size_t index,
-				struct acpi_reference_args *args)
+				struct fwnode_reference_args *args)
 {
 	return __acpi_node_get_property_reference(fwnode, name, index,
-		MAX_ACPI_REFERENCE_ARGS, args);
+		NR_FWNODE_REFERENCE_ARGS, args);
 }
 
 int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname,
@@ -1093,14 +1089,6 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode,
 					    struct fwnode_handle *child);
 struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode);
 
-struct fwnode_handle *
-acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
-			     struct fwnode_handle *prev);
-int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode,
-				   struct fwnode_handle **remote,
-				   struct fwnode_handle **port,
-				   struct fwnode_handle **endpoint);
-
 struct acpi_probe_entry;
 typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *,
 						 struct acpi_probe_entry *);
@@ -1166,7 +1154,7 @@ static inline int acpi_dev_get_property(struct acpi_device *adev,
 static inline int
 __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 				const char *name, size_t index, size_t num_args,
-				struct acpi_reference_args *args)
+				struct fwnode_reference_args *args)
 {
 	return -ENXIO;
 }
@@ -1174,7 +1162,7 @@ __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 static inline int
 acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 				 const char *name, size_t index,
-				 struct acpi_reference_args *args)
+				 struct fwnode_reference_args *args)
 {
 	return -ENXIO;
 }
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 01ce3997cb42..1e8e88bdaf09 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -2,6 +2,8 @@
 /* Atomic operations usable in machine independent code */
 #ifndef _LINUX_ATOMIC_H
 #define _LINUX_ATOMIC_H
+#include <linux/types.h>
+
 #include <asm/atomic.h>
 #include <asm/barrier.h>
 
@@ -36,40 +38,46 @@
  * barriers on top of the relaxed variant. In the case where the relaxed
  * variant is already fully ordered, no additional barriers are needed.
  *
- * Besides, if an arch has a special barrier for acquire/release, it could
- * implement its own __atomic_op_* and use the same framework for building
- * variants
- *
- * If an architecture overrides __atomic_op_acquire() it will probably want
- * to define smp_mb__after_spinlock().
+ * If an architecture overrides __atomic_acquire_fence() it will probably
+ * want to define smp_mb__after_spinlock().
  */
-#ifndef __atomic_op_acquire
+#ifndef __atomic_acquire_fence
+#define __atomic_acquire_fence		smp_mb__after_atomic
+#endif
+
+#ifndef __atomic_release_fence
+#define __atomic_release_fence		smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_pre_full_fence
+#define __atomic_pre_full_fence		smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_post_full_fence
+#define __atomic_post_full_fence	smp_mb__after_atomic
+#endif
+
 #define __atomic_op_acquire(op, args...)				\
 ({									\
 	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	smp_mb__after_atomic();						\
+	__atomic_acquire_fence();					\
 	__ret;								\
 })
-#endif
 
-#ifndef __atomic_op_release
 #define __atomic_op_release(op, args...)				\
 ({									\
-	smp_mb__before_atomic();					\
+	__atomic_release_fence();					\
 	op##_relaxed(args);						\
 })
-#endif
 
-#ifndef __atomic_op_fence
 #define __atomic_op_fence(op, args...)					\
 ({									\
 	typeof(op##_relaxed(args)) __ret;				\
-	smp_mb__before_atomic();					\
+	__atomic_pre_full_fence();					\
 	__ret = op##_relaxed(args);					\
-	smp_mb__after_atomic();						\
+	__atomic_post_full_fence();					\
 	__ret;								\
 })
-#endif
 
 /* atomic_add_return_relaxed */
 #ifndef atomic_add_return_relaxed
@@ -95,11 +103,23 @@
 #endif
 #endif /* atomic_add_return_relaxed */
 
+#ifndef atomic_inc
+#define atomic_inc(v)			atomic_add(1, (v))
+#endif
+
 /* atomic_inc_return_relaxed */
 #ifndef atomic_inc_return_relaxed
+
+#ifndef atomic_inc_return
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+#define atomic_inc_return_relaxed(v)	atomic_add_return_relaxed(1, (v))
+#define atomic_inc_return_acquire(v)	atomic_add_return_acquire(1, (v))
+#define atomic_inc_return_release(v)	atomic_add_return_release(1, (v))
+#else /* atomic_inc_return */
 #define  atomic_inc_return_relaxed	atomic_inc_return
 #define  atomic_inc_return_acquire	atomic_inc_return
 #define  atomic_inc_return_release	atomic_inc_return
+#endif /* atomic_inc_return */
 
 #else /* atomic_inc_return_relaxed */
 
@@ -143,11 +163,23 @@
 #endif
 #endif /* atomic_sub_return_relaxed */
 
+#ifndef atomic_dec
+#define atomic_dec(v)			atomic_sub(1, (v))
+#endif
+
 /* atomic_dec_return_relaxed */
 #ifndef atomic_dec_return_relaxed
+
+#ifndef atomic_dec_return
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+#define atomic_dec_return_relaxed(v)	atomic_sub_return_relaxed(1, (v))
+#define atomic_dec_return_acquire(v)	atomic_sub_return_acquire(1, (v))
+#define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
+#else /* atomic_dec_return */
 #define  atomic_dec_return_relaxed	atomic_dec_return
 #define  atomic_dec_return_acquire	atomic_dec_return
 #define  atomic_dec_return_release	atomic_dec_return
+#endif /* atomic_dec_return */
 
 #else /* atomic_dec_return_relaxed */
 
@@ -328,12 +360,22 @@
 #endif
 #endif /* atomic_fetch_and_relaxed */
 
-#ifdef atomic_andnot
-/* atomic_fetch_andnot_relaxed */
+#ifndef atomic_andnot
+#define atomic_andnot(i, v)		atomic_and(~(int)(i), (v))
+#endif
+
 #ifndef atomic_fetch_andnot_relaxed
-#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot
-#define atomic_fetch_andnot_acquire	atomic_fetch_andnot
-#define atomic_fetch_andnot_release	atomic_fetch_andnot
+
+#ifndef atomic_fetch_andnot
+#define atomic_fetch_andnot(i, v)		atomic_fetch_and(~(int)(i), (v))
+#define atomic_fetch_andnot_relaxed(i, v)	atomic_fetch_and_relaxed(~(int)(i), (v))
+#define atomic_fetch_andnot_acquire(i, v)	atomic_fetch_and_acquire(~(int)(i), (v))
+#define atomic_fetch_andnot_release(i, v)	atomic_fetch_and_release(~(int)(i), (v))
+#else /* atomic_fetch_andnot */
+#define atomic_fetch_andnot_relaxed		atomic_fetch_andnot
+#define atomic_fetch_andnot_acquire		atomic_fetch_andnot
+#define atomic_fetch_andnot_release		atomic_fetch_andnot
+#endif /* atomic_fetch_andnot */
 
 #else /* atomic_fetch_andnot_relaxed */
 
@@ -352,7 +394,6 @@
 	__atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__)
 #endif
 #endif /* atomic_fetch_andnot_relaxed */
-#endif /* atomic_andnot */
 
 /* atomic_fetch_xor_relaxed */
 #ifndef atomic_fetch_xor_relaxed
@@ -520,112 +561,140 @@
 #endif /* xchg_relaxed */
 
 /**
+ * atomic_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic_fetch_add_unless
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
+{
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c == u))
+			break;
+	} while (!atomic_try_cmpxchg(v, &c, c + a));
+
+	return c;
+}
+#endif
+
+/**
  * atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
  */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
+static inline bool atomic_add_unless(atomic_t *v, int a, int u)
 {
-	return __atomic_add_unless(v, a, u) != u;
+	return atomic_fetch_add_unless(v, a, u) != u;
 }
 
 /**
  * atomic_inc_not_zero - increment unless the number is zero
  * @v: pointer of type atomic_t
  *
- * Atomically increments @v by 1, so long as @v is non-zero.
- * Returns non-zero if @v was non-zero, and zero otherwise.
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
  */
 #ifndef atomic_inc_not_zero
 #define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
 #endif
 
-#ifndef atomic_andnot
-static inline void atomic_andnot(int i, atomic_t *v)
-{
-	atomic_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot(int i, atomic_t *v)
-{
-	return atomic_fetch_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v)
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_inc_and_test
+static inline bool atomic_inc_and_test(atomic_t *v)
 {
-	return atomic_fetch_and_relaxed(~i, v);
+	return atomic_inc_return(v) == 0;
 }
+#endif
 
-static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v)
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic_dec_and_test
+static inline bool atomic_dec_and_test(atomic_t *v)
 {
-	return atomic_fetch_and_acquire(~i, v);
+	return atomic_dec_return(v) == 0;
 }
+#endif
 
-static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_sub_and_test
+static inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
-	return atomic_fetch_and_release(~i, v);
+	return atomic_sub_return(i, v) == 0;
 }
 #endif
 
 /**
- * atomic_inc_not_zero_hint - increment if not null
+ * atomic_add_negative - add and test if negative
+ * @i: integer value to add
  * @v: pointer of type atomic_t
- * @hint: probable value of the atomic before the increment
- *
- * This version of atomic_inc_not_zero() gives a hint of probable
- * value of the atomic. This helps processor to not read the memory
- * before doing the atomic read/modify/write cycle, lowering
- * number of bus transactions on some arches.
  *
- * Returns: 0 if increment was not done, 1 otherwise.
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
  */
-#ifndef atomic_inc_not_zero_hint
-static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
+#ifndef atomic_add_negative
+static inline bool atomic_add_negative(int i, atomic_t *v)
 {
-	int val, c = hint;
-
-	/* sanity test, should be removed by compiler if hint is a constant */
-	if (!hint)
-		return atomic_inc_not_zero(v);
-
-	do {
-		val = atomic_cmpxchg(v, c, c + 1);
-		if (val == c)
-			return 1;
-		c = val;
-	} while (c);
-
-	return 0;
+	return atomic_add_return(i, v) < 0;
 }
 #endif
 
 #ifndef atomic_inc_unless_negative
-static inline int atomic_inc_unless_negative(atomic_t *p)
+static inline bool atomic_inc_unless_negative(atomic_t *v)
 {
-	int v, v1;
-	for (v = 0; v >= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v + 1);
-		if (likely(v1 == v))
-			return 1;
-	}
-	return 0;
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c < 0))
+			return false;
+	} while (!atomic_try_cmpxchg(v, &c, c + 1));
+
+	return true;
 }
 #endif
 
 #ifndef atomic_dec_unless_positive
-static inline int atomic_dec_unless_positive(atomic_t *p)
+static inline bool atomic_dec_unless_positive(atomic_t *v)
 {
-	int v, v1;
-	for (v = 0; v <= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v - 1);
-		if (likely(v1 == v))
-			return 1;
-	}
-	return 0;
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c > 0))
+			return false;
+	} while (!atomic_try_cmpxchg(v, &c, c - 1));
+
+	return true;
 }
 #endif
 
@@ -639,17 +708,14 @@ static inline int atomic_dec_unless_positive(atomic_t *p)
 #ifndef atomic_dec_if_positive
 static inline int atomic_dec_if_positive(atomic_t *v)
 {
-	int c, old, dec;
-	c = atomic_read(v);
-	for (;;) {
+	int dec, c = atomic_read(v);
+
+	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-		old = atomic_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
+	} while (!atomic_try_cmpxchg(v, &c, dec));
+
 	return dec;
 }
 #endif
@@ -693,11 +759,23 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_add_return_relaxed */
 
+#ifndef atomic64_inc
+#define atomic64_inc(v)			atomic64_add(1, (v))
+#endif
+
 /* atomic64_inc_return_relaxed */
 #ifndef atomic64_inc_return_relaxed
+
+#ifndef atomic64_inc_return
+#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
+#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1, (v))
+#define atomic64_inc_return_acquire(v)	atomic64_add_return_acquire(1, (v))
+#define atomic64_inc_return_release(v)	atomic64_add_return_release(1, (v))
+#else /* atomic64_inc_return */
 #define  atomic64_inc_return_relaxed	atomic64_inc_return
 #define  atomic64_inc_return_acquire	atomic64_inc_return
 #define  atomic64_inc_return_release	atomic64_inc_return
+#endif /* atomic64_inc_return */
 
 #else /* atomic64_inc_return_relaxed */
 
@@ -742,11 +820,23 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_sub_return_relaxed */
 
+#ifndef atomic64_dec
+#define atomic64_dec(v)			atomic64_sub(1, (v))
+#endif
+
 /* atomic64_dec_return_relaxed */
 #ifndef atomic64_dec_return_relaxed
+
+#ifndef atomic64_dec_return
+#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
+#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1, (v))
+#define atomic64_dec_return_acquire(v)	atomic64_sub_return_acquire(1, (v))
+#define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
+#else /* atomic64_dec_return */
 #define  atomic64_dec_return_relaxed	atomic64_dec_return
 #define  atomic64_dec_return_acquire	atomic64_dec_return
 #define  atomic64_dec_return_release	atomic64_dec_return
+#endif /* atomic64_dec_return */
 
 #else /* atomic64_dec_return_relaxed */
 
@@ -927,12 +1017,22 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_fetch_and_relaxed */
 
-#ifdef atomic64_andnot
-/* atomic64_fetch_andnot_relaxed */
+#ifndef atomic64_andnot
+#define atomic64_andnot(i, v)		atomic64_and(~(long long)(i), (v))
+#endif
+
 #ifndef atomic64_fetch_andnot_relaxed
-#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot
-#define atomic64_fetch_andnot_acquire	atomic64_fetch_andnot
-#define atomic64_fetch_andnot_release	atomic64_fetch_andnot
+
+#ifndef atomic64_fetch_andnot
+#define atomic64_fetch_andnot(i, v)		atomic64_fetch_and(~(long long)(i), (v))
+#define atomic64_fetch_andnot_relaxed(i, v)	atomic64_fetch_and_relaxed(~(long long)(i), (v))
+#define atomic64_fetch_andnot_acquire(i, v)	atomic64_fetch_and_acquire(~(long long)(i), (v))
+#define atomic64_fetch_andnot_release(i, v)	atomic64_fetch_and_release(~(long long)(i), (v))
+#else /* atomic64_fetch_andnot */
+#define atomic64_fetch_andnot_relaxed		atomic64_fetch_andnot
+#define atomic64_fetch_andnot_acquire		atomic64_fetch_andnot
+#define atomic64_fetch_andnot_release		atomic64_fetch_andnot
+#endif /* atomic64_fetch_andnot */
 
 #else /* atomic64_fetch_andnot_relaxed */
 
@@ -951,7 +1051,6 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 	__atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__)
 #endif
 #endif /* atomic64_fetch_andnot_relaxed */
-#endif /* atomic64_andnot */
 
 /* atomic64_fetch_xor_relaxed */
 #ifndef atomic64_fetch_xor_relaxed
@@ -1049,30 +1148,164 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #define atomic64_try_cmpxchg_release	atomic64_try_cmpxchg
 #endif /* atomic64_try_cmpxchg */
 
-#ifndef atomic64_andnot
-static inline void atomic64_andnot(long long i, atomic64_t *v)
+/**
+ * atomic64_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic64_fetch_add_unless
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	atomic64_and(~i, v);
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c == u))
+			break;
+	} while (!atomic64_try_cmpxchg(v, &c, c + a));
+
+	return c;
 }
+#endif
 
-static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v)
+/**
+ * atomic64_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
+ */
+static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
-	return atomic64_fetch_and(~i, v);
+	return atomic64_fetch_add_unless(v, a, u) != u;
 }
 
-static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v)
+/**
+ * atomic64_inc_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
+ */
+#ifndef atomic64_inc_not_zero
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
+#endif
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_inc_and_test
+static inline bool atomic64_inc_and_test(atomic64_t *v)
 {
-	return atomic64_fetch_and_relaxed(~i, v);
+	return atomic64_inc_return(v) == 0;
 }
+#endif
 
-static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v)
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic64_dec_and_test
+static inline bool atomic64_dec_and_test(atomic64_t *v)
 {
-	return atomic64_fetch_and_acquire(~i, v);
+	return atomic64_dec_return(v) == 0;
 }
+#endif
 
-static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v)
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_sub_and_test
+static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
+{
+	return atomic64_sub_return(i, v) == 0;
+}
+#endif
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+#ifndef atomic64_add_negative
+static inline bool atomic64_add_negative(long long i, atomic64_t *v)
 {
-	return atomic64_fetch_and_release(~i, v);
+	return atomic64_add_return(i, v) < 0;
+}
+#endif
+
+#ifndef atomic64_inc_unless_negative
+static inline bool atomic64_inc_unless_negative(atomic64_t *v)
+{
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c < 0))
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &c, c + 1));
+
+	return true;
+}
+#endif
+
+#ifndef atomic64_dec_unless_positive
+static inline bool atomic64_dec_unless_positive(atomic64_t *v)
+{
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c > 0))
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &c, c - 1));
+
+	return true;
+}
+#endif
+
+/*
+ * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic64_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic64 variable, v, was not decremented.
+ */
+#ifndef atomic64_dec_if_positive
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long dec, c = atomic64_read(v);
+
+	do {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+	} while (!atomic64_try_cmpxchg(v, &c, dec));
+
+	return dec;
 }
 #endif
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index f08f5fe7bd08..51371740d2a8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -429,7 +429,6 @@ extern void bio_put(struct bio *);
 
 extern void __bio_clone_fast(struct bio *, struct bio *);
 extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
-extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
 extern struct bio_set fs_bio_set;
 
@@ -443,12 +442,6 @@ static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 	return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
 }
 
-static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
-{
-	return bio_clone_bioset(bio, gfp_mask, NULL);
-
-}
-
 extern blk_qc_t submit_bio(struct bio *);
 
 extern void bio_endio(struct bio *);
@@ -496,9 +489,9 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
-void generic_start_io_acct(struct request_queue *q, int rw,
+void generic_start_io_acct(struct request_queue *q, int op,
 				unsigned long sectors, struct hd_struct *part);
-void generic_end_io_acct(struct request_queue *q, int rw,
+void generic_end_io_acct(struct request_queue *q, int op,
 				struct hd_struct *part,
 				unsigned long start_time);
 
@@ -553,8 +546,16 @@ do {						\
 #define bio_dev(bio) \
 	disk_devt((bio)->bi_disk)
 
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+int bio_associate_blkcg_from_page(struct bio *bio, struct page *page);
+#else
+static inline int bio_associate_blkcg_from_page(struct bio *bio,
+						struct page *page) {  return 0; }
+#endif
+
 #ifdef CONFIG_BLK_CGROUP
 int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
+int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg);
 void bio_disassociate_task(struct bio *bio);
 void bio_clone_blkcg_association(struct bio *dst, struct bio *src);
 #else	/* CONFIG_BLK_CGROUP */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 4cac4e1a72ff..af419012d77d 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -2,29 +2,9 @@
 #ifndef _LINUX_BITOPS_H
 #define _LINUX_BITOPS_H
 #include <asm/types.h>
+#include <linux/bits.h>
 
-#ifdef	__KERNEL__
-#define BIT(nr)			(1UL << (nr))
-#define BIT_ULL(nr)		(1ULL << (nr))
-#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
-#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
-#define BITS_PER_BYTE		8
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#endif
-
-/*
- * Create a contiguous bitmask starting at bit position @l and ending at
- * position @h. For example
- * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
- */
-#define GENMASK(h, l) \
-	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
-
-#define GENMASK_ULL(h, l) \
-	(((~0ULL) - (1ULL << (l)) + 1) & \
-	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
 
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/include/linux/bits.h b/include/linux/bits.h
new file mode 100644
index 000000000000..2b7b532c1d51
--- /dev/null
+++ b/include/linux/bits.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+#include <asm/bitsperlong.h>
+
+#define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE		8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+	(((~0ULL) - (1ULL << (l)) + 1) & \
+	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif	/* __LINUX_BITS_H */
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 6c666fd7de3c..34aec30e06c7 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -35,6 +35,7 @@ enum blkg_rwstat_type {
 	BLKG_RWSTAT_WRITE,
 	BLKG_RWSTAT_SYNC,
 	BLKG_RWSTAT_ASYNC,
+	BLKG_RWSTAT_DISCARD,
 
 	BLKG_RWSTAT_NR,
 	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
@@ -136,6 +137,12 @@ struct blkcg_gq {
 	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
 
 	struct rcu_head			rcu_head;
+
+	atomic_t			use_delay;
+	atomic64_t			delay_nsec;
+	atomic64_t			delay_start;
+	u64				last_delay;
+	int				last_use;
 };
 
 typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
@@ -148,6 +155,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
+typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf,
+				      size_t size);
 
 struct blkcg_policy {
 	int				plid;
@@ -167,6 +176,7 @@ struct blkcg_policy {
 	blkcg_pol_offline_pd_fn		*pd_offline_fn;
 	blkcg_pol_free_pd_fn		*pd_free_fn;
 	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
+	blkcg_pol_stat_pd_fn		*pd_stat_fn;
 };
 
 extern struct blkcg blkcg_root;
@@ -238,6 +248,42 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 	return css_to_blkcg(task_css(current, io_cgrp_id));
 }
 
+static inline bool blk_cgroup_congested(void)
+{
+	struct cgroup_subsys_state *css;
+	bool ret = false;
+
+	rcu_read_lock();
+	css = kthread_blkcg();
+	if (!css)
+		css = task_css(current, io_cgrp_id);
+	while (css) {
+		if (atomic_read(&css->cgroup->congestion_count)) {
+			ret = true;
+			break;
+		}
+		css = css->parent;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg
+ * @return: true if this bio needs to be submitted with the root blkg context.
+ *
+ * In order to avoid priority inversions we sometimes need to issue a bio as if
+ * it were attached to the root blkg, and then backcharge to the actual owning
+ * blkg.  The idea is we do bio_blkcg() to look up the actual context for the
+ * bio and attach the appropriate blkg to the bio.  Then we call this helper and
+ * if it is true run with the root blkg for that queue and then do any
+ * backcharging to the originating cgroup once the io is complete.
+ */
+static inline bool bio_issue_as_root_blkg(struct bio *bio)
+{
+	return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0;
+}
+
 /**
  * blkcg_parent - get the parent of a blkcg
  * @blkcg: blkcg of interest
@@ -296,6 +342,17 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 }
 
 /**
+ * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair
+ * @q: request_queue of interest
+ *
+ * Lookup blkg for @q at the root level. See also blkg_lookup().
+ */
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{
+	return q->root_blkg;
+}
+
+/**
  * blkg_to_pdata - get policy private data
  * @blkg: blkg of interest
  * @pol: policy of interest
@@ -355,6 +412,21 @@ static inline void blkg_get(struct blkcg_gq *blkg)
 	atomic_inc(&blkg->refcnt);
 }
 
+/**
+ * blkg_try_get - try and get a blkg reference
+ * @blkg: blkg to get
+ *
+ * This is for use when doing an RCU lookup of the blkg.  We may be in the midst
+ * of freeing this blkg, so we can only use it if the refcnt is not zero.
+ */
+static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg)
+{
+	if (atomic_inc_not_zero(&blkg->refcnt))
+		return blkg;
+	return NULL;
+}
+
+
 void __blkg_release_rcu(struct rcu_head *rcu);
 
 /**
@@ -589,7 +661,9 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
 {
 	struct percpu_counter *cnt;
 
-	if (op_is_write(op))
+	if (op_is_discard(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
+	else if (op_is_write(op))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
@@ -706,8 +780,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 
 	if (!throtl) {
 		blkg = blkg ?: q->root_blkg;
-		blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
-				bio->bi_iter.bi_size);
+		/*
+		 * If the bio is flagged with BIO_QUEUE_ENTERED it means this
+		 * is a split bio and we would have already accounted for the
+		 * size of the bio.
+		 */
+		if (!bio_flagged(bio, BIO_QUEUE_ENTERED))
+			blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
+					bio->bi_iter.bi_size);
 		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
 	}
 
@@ -715,6 +795,59 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 	return !throtl;
 }
 
+static inline void blkcg_use_delay(struct blkcg_gq *blkg)
+{
+	if (atomic_add_return(1, &blkg->use_delay) == 1)
+		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+}
+
+static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+
+	if (old == 0)
+		return 0;
+
+	/*
+	 * We do this song and dance because we can race with somebody else
+	 * adding or removing delay.  If we just did an atomic_dec we'd end up
+	 * negative and we'd already be in trouble.  We need to subtract 1 and
+	 * then check to see if we were the last delay so we can drop the
+	 * congestion count on the cgroup.
+	 */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1);
+		if (cur == old)
+			break;
+		old = cur;
+	}
+
+	if (old == 0)
+		return 0;
+	if (old == 1)
+		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+	return 1;
+}
+
+static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+	if (!old)
+		return;
+	/* We only want 1 person clearing the congestion count for this blkg. */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, 0);
+		if (cur == old) {
+			atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+			break;
+		}
+		old = cur;
+	}
+}
+
+void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
+void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
+void blkcg_maybe_throttle_current(void);
 #else	/* CONFIG_BLK_CGROUP */
 
 struct blkcg {
@@ -734,9 +867,16 @@ struct blkcg_policy {
 
 #define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
 
+static inline void blkcg_maybe_throttle_current(void) { }
+static inline bool blk_cgroup_congested(void) { return false; }
+
 #ifdef CONFIG_BLOCK
 
+static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
+
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{ return NULL; }
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }
 static inline void blkcg_exit_queue(struct request_queue *q) { }
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index e3147eb74222..1da59c16f637 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -35,10 +35,12 @@ struct blk_mq_hw_ctx {
 	struct sbitmap		ctx_map;
 
 	struct blk_mq_ctx	*dispatch_from;
+	unsigned int		dispatch_busy;
 
-	struct blk_mq_ctx	**ctxs;
 	unsigned int		nr_ctx;
+	struct blk_mq_ctx	**ctxs;
 
+	spinlock_t		dispatch_wait_lock;
 	wait_queue_entry_t	dispatch_wait;
 	atomic_t		wait_index;
 
@@ -287,6 +289,20 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
 void blk_mq_quiesce_queue_nowait(struct request_queue *q);
 
+/**
+ * blk_mq_mark_complete() - Set request state to complete
+ * @rq: request to set to complete state
+ *
+ * Returns true if request state was successfully set to complete. If
+ * successful, the caller is responsibile for seeing this request is ended, as
+ * blk_mq_complete_request will not work again.
+ */
+static inline bool blk_mq_mark_complete(struct request *rq)
+{
+	return cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) ==
+			MQ_RQ_IN_FLIGHT;
+}
+
 /*
  * Driver command data is immediately after the request. So subtract request
  * size to get back to the original request, add request size to get the PDU.
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 3c4f390aea4b..f6dfb30737d8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -179,11 +179,9 @@ struct bio {
 	 */
 	struct io_context	*bi_ioc;
 	struct cgroup_subsys_state *bi_css;
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	void			*bi_cg_private;
+	struct blkcg_gq		*bi_blkg;
 	struct bio_issue	bi_issue;
 #endif
-#endif
 	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 		struct bio_integrity_payload *bi_integrity; /* data integrity */
@@ -329,7 +327,7 @@ enum req_flag_bits {
 
 	/* for driver use */
 	__REQ_DRV,
-
+	__REQ_SWAP,		/* swapping request. */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -351,6 +349,7 @@ enum req_flag_bits {
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
 
 #define REQ_DRV			(1ULL << __REQ_DRV)
+#define REQ_SWAP		(1ULL << __REQ_SWAP)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
@@ -358,6 +357,14 @@ enum req_flag_bits {
 #define REQ_NOMERGE_FLAGS \
 	(REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA)
 
+enum stat_group {
+	STAT_READ,
+	STAT_WRITE,
+	STAT_DISCARD,
+
+	NR_STAT_GROUPS
+};
+
 #define bio_op(bio) \
 	((bio)->bi_opf & REQ_OP_MASK)
 #define req_op(req) \
@@ -395,6 +402,18 @@ static inline bool op_is_sync(unsigned int op)
 		(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
 }
 
+static inline bool op_is_discard(unsigned int op)
+{
+	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
+}
+
+static inline int op_stat_group(unsigned int op)
+{
+	if (op_is_discard(op))
+		return STAT_DISCARD;
+	return op_is_write(op);
+}
+
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE		-1U
 #define BLK_QC_T_SHIFT		16
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9154570edf29..d6869e0e2b64 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -27,8 +27,6 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
-#include <linux/seqlock.h>
-#include <linux/u64_stats_sync.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -42,7 +40,7 @@ struct bsg_job;
 struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
-struct rq_wb;
+struct rq_qos;
 struct blk_queue_stats;
 struct blk_stat_callback;
 
@@ -442,10 +440,8 @@ struct request_queue {
 	int			nr_rqs[2];	/* # allocated [a]sync rqs */
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
-	atomic_t		shared_hctx_restart;
-
 	struct blk_queue_stats	*stats;
-	struct rq_wb		*rq_wb;
+	struct rq_qos		*rq_qos;
 
 	/*
 	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg
@@ -592,6 +588,7 @@ struct request_queue {
 
 	struct queue_limits	limits;
 
+#ifdef CONFIG_BLK_DEV_ZONED
 	/*
 	 * Zoned block device information for request dispatch control.
 	 * nr_zones is the total number of zones of the device. This is always
@@ -612,6 +609,7 @@ struct request_queue {
 	unsigned int		nr_zones;
 	unsigned long		*seq_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
 	 * sg stuff
@@ -800,11 +798,7 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
-static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
-{
-	return q->nr_zones;
-}
-
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 					     sector_t sector)
 {
@@ -820,6 +814,7 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return false;
 	return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap);
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
 {
@@ -1070,6 +1065,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_rq_zone_no(struct request *rq)
 {
 	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
@@ -1079,6 +1075,7 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
 {
 	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 /*
  * Some commands like WRITE SAME have a payload or data transfer size which
@@ -1119,8 +1116,8 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q,
 	if (!q->limits.chunk_sectors)
 		return q->limits.max_sectors;
 
-	return q->limits.chunk_sectors -
-			(offset & (q->limits.chunk_sectors - 1));
+	return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors -
+			(offset & (q->limits.chunk_sectors - 1))));
 }
 
 static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
@@ -1437,8 +1434,6 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
-
 static inline unsigned long queue_segment_boundary(struct request_queue *q)
 {
 	return q->limits.seg_boundary_mask;
@@ -1639,15 +1634,6 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
 	return 0;
 }
 
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return blk_queue_nr_zones(q);
-	return 0;
-}
-
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
@@ -1877,6 +1863,28 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 				bip_next->bip_vec[0].bv_offset);
 }
 
+/**
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
+ * @bi:		blk_integrity profile for device
+ * @sectors:	Size of the bio in 512-byte sectors
+ *
+ * Description: The block layer calculates everything in 512 byte
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device.  Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
+ */
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return sectors >> (bi->interval_exp - 9);
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct bio;
@@ -1950,12 +1958,24 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 	return false;
 }
 
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return 0;
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return 0;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
-	int (*rw_page)(struct block_device *, sector_t, struct page *, bool);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 7942a96b1a9d..42515195d7d8 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -27,9 +27,20 @@ extern unsigned long max_pfn;
 extern unsigned long long max_possible_pfn;
 
 #ifndef CONFIG_NO_BOOTMEM
-/*
- * node_bootmem_map is a map pointer - the bits represent all physical 
- * memory pages (including holes) on the node.
+/**
+ * struct bootmem_data - per-node information used by the bootmem allocator
+ * @node_min_pfn: the starting physical address of the node's memory
+ * @node_low_pfn: the end physical address of the directly addressable memory
+ * @node_bootmem_map: is a bitmap pointer - the bits represent all physical
+ *		      memory pages (including holes) on the node.
+ * @last_end_off: the offset within the page of the end of the last allocation;
+ *                if 0, the page used is full
+ * @hint_idx: the PFN of the page used with the last allocation;
+ *            together with using this with the @last_end_offset field,
+ *            a test can be made to see if allocations can be merged
+ *            with the page used for the last allocation rather than
+ *            using up a full new page.
+ * @list: list entry in the linked list ordered by the memory addresses
  */
 typedef struct bootmem_data {
 	unsigned long node_min_pfn;
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 975fb4cf1bb7..d50c2f0a655a 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -2,6 +2,7 @@
 #ifndef _BPF_CGROUP_H
 #define _BPF_CGROUP_H
 
+#include <linux/errno.h>
 #include <linux/jump_label.h>
 #include <uapi/linux/bpf.h>
 
@@ -188,12 +189,38 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 									      \
 	__ret;								      \
 })
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+			   enum bpf_prog_type ptype, struct bpf_prog *prog);
+int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+			   enum bpf_prog_type ptype);
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+			  union bpf_attr __user *uattr);
 #else
 
+struct bpf_prog;
 struct cgroup_bpf {};
 static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
 static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 
+static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+					 enum bpf_prog_type ptype,
+					 struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+					 enum bpf_prog_type ptype)
+{
+	return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
+					union bpf_attr __user *uattr)
+{
+	return -EINVAL;
+}
+
 #define cgroup_bpf_enabled (0)
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7df32a3200f7..8827e797ff97 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -696,6 +696,8 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
 struct sock  *__sock_hash_lookup_elem(struct bpf_map *map, void *key);
 int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+			struct bpf_prog *prog);
 #else
 static inline struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
 {
@@ -714,6 +716,12 @@ static inline int sock_map_prog(struct bpf_map *map,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+				      struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
 #endif
 
 #if defined(CONFIG_XDP_SOCKETS)
diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h
index 5f8a4283092d..9d9ff755ec29 100644
--- a/include/linux/bpf_lirc.h
+++ b/include/linux/bpf_lirc.h
@@ -5,11 +5,12 @@
 #include <uapi/linux/bpf.h>
 
 #ifdef CONFIG_BPF_LIRC_MODE2
-int lirc_prog_attach(const union bpf_attr *attr);
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int lirc_prog_detach(const union bpf_attr *attr);
 int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
 #else
-static inline int lirc_prog_attach(const union bpf_attr *attr)
+static inline int lirc_prog_attach(const union bpf_attr *attr,
+				   struct bpf_prog *prog)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
index 687b1760bb9f..f02cee0225d4 100644
--- a/include/linux/bpfilter.h
+++ b/include/linux/bpfilter.h
@@ -5,10 +5,10 @@
 #include <uapi/linux/bpfilter.h>
 
 struct sock;
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval,
+int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
 			    unsigned int optlen);
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval,
-			    int *optlen);
+int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
+			    int __user *optlen);
 extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname,
 				       char __user *optval,
 				       unsigned int optlen, bool is_set);
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index e75dfd1f1dec..528271c60018 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -13,6 +13,7 @@
 
 #include <linux/fs.h>		/* not really needed, later.. */
 #include <linux/list.h>
+#include <scsi/scsi_common.h>
 #include <uapi/linux/cdrom.h>
 
 struct packet_command
@@ -21,7 +22,7 @@ struct packet_command
 	unsigned char 		*buffer;
 	unsigned int 		buflen;
 	int			stat;
-	struct request_sense	*sense;
+	struct scsi_sense_hdr	*sshdr;
 	unsigned char		data_direction;
 	int			quiet;
 	int			timeout;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index c0e68f903011..ff20b677fb9f 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -438,6 +438,9 @@ struct cgroup {
 	/* used to store eBPF programs */
 	struct cgroup_bpf bpf;
 
+	/* If there is block congestion on this cgroup. */
+	atomic_t congestion_count;
+
 	/* ids of the ancestors at each level including self */
 	int ancestor_ids[];
 };
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index b7cfa037e593..08b1aa70a38d 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -38,6 +38,8 @@
 #define CLK_IS_CRITICAL		BIT(11) /* do not gate, ever */
 /* parents need enable during gate/ungate, set rate and re-parent */
 #define CLK_OPS_PARENT_ENABLE	BIT(12)
+/* duty cycle call may be forwarded to the parent clock */
+#define CLK_DUTY_CYCLE_PARENT	BIT(13)
 
 struct clk;
 struct clk_hw;
@@ -67,6 +69,17 @@ struct clk_rate_request {
 };
 
 /**
+ * struct clk_duty - Struture encoding the duty cycle ratio of a clock
+ *
+ * @num:	Numerator of the duty cycle ratio
+ * @den:	Denominator of the duty cycle ratio
+ */
+struct clk_duty {
+	unsigned int num;
+	unsigned int den;
+};
+
+/**
  * struct clk_ops -  Callback operations for hardware clocks; these are to
  * be provided by the clock implementation, and will be called by drivers
  * through the clk_* api.
@@ -169,6 +182,15 @@ struct clk_rate_request {
  *		by the second argument. Valid values for degrees are
  *		0-359. Return 0 on success, otherwise -EERROR.
  *
+ * @get_duty_cycle: Queries the hardware to get the current duty cycle ratio
+ *              of a clock. Returned values denominator cannot be 0 and must be
+ *              superior or equal to the numerator.
+ *
+ * @set_duty_cycle: Apply the duty cycle ratio to this clock signal specified by
+ *              the numerator (2nd argurment) and denominator (3rd  argument).
+ *              Argument must be a valid ratio (denominator > 0
+ *              and >= numerator) Return 0 on success, otherwise -EERROR.
+ *
  * @init:	Perform platform-specific initialization magic.
  *		This is not not used by any of the basic clock types.
  *		Please consider other ways of solving initialization problems
@@ -218,6 +240,10 @@ struct clk_ops {
 					   unsigned long parent_accuracy);
 	int		(*get_phase)(struct clk_hw *hw);
 	int		(*set_phase)(struct clk_hw *hw, int degrees);
+	int		(*get_duty_cycle)(struct clk_hw *hw,
+					  struct clk_duty *duty);
+	int		(*set_duty_cycle)(struct clk_hw *hw,
+					  struct clk_duty *duty);
 	void		(*init)(struct clk_hw *hw);
 	void		(*debug_init)(struct clk_hw *hw, struct dentry *dentry);
 };
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 0dbd0885b2c2..4f750c481b82 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -142,6 +142,27 @@ int clk_set_phase(struct clk *clk, int degrees);
 int clk_get_phase(struct clk *clk);
 
 /**
+ * clk_set_duty_cycle - adjust the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @num: numerator of the duty cycle ratio to be applied
+ * @den: denominator of the duty cycle ratio to be applied
+ *
+ * Adjust the duty cycle of a clock signal by the specified ratio. Returns 0 on
+ * success, -EERROR otherwise.
+ */
+int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den);
+
+/**
+ * clk_get_duty_cycle - return the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @scale: scaling factor to be applied to represent the ratio as an integer
+ *
+ * Returns the duty cycle ratio multiplied by the scale provided, otherwise
+ * returns -EERROR.
+ */
+int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale);
+
+/**
  * clk_is_match - check if two clk's point to the same hardware clock
  * @p: clk compared against q
  * @q: clk compared against p
@@ -183,6 +204,18 @@ static inline long clk_get_phase(struct clk *clk)
 	return -ENOTSUPP;
 }
 
+static inline int clk_set_duty_cycle(struct clk *clk, unsigned int num,
+				     unsigned int den)
+{
+	return -ENOTSUPP;
+}
+
+static inline unsigned int clk_get_scaled_duty_cycle(struct clk *clk,
+						     unsigned int scale)
+{
+	return 0;
+}
+
 static inline bool clk_is_match(const struct clk *p, const struct clk *q)
 {
 	return p == q;
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 7dff1963c185..308918928767 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -194,6 +194,9 @@ extern void clocksource_suspend(void);
 extern void clocksource_resume(void);
 extern struct clocksource * __init clocksource_default_clock(void);
 extern void clocksource_mark_unstable(struct clocksource *cs);
+extern void
+clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles);
+extern u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 now);
 
 extern u64
 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles);
diff --git a/include/linux/compat.h b/include/linux/compat.h
index b1a5562b3215..1a3c4f37e908 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -72,6 +72,9 @@
  */
 #ifndef COMPAT_SYSCALL_DEFINEx
 #define COMPAT_SYSCALL_DEFINEx(x, name, ...)					\
+	__diag_push();								\
+	__diag_ignore(GCC, 8, "-Wattribute-alias",				\
+		      "Type aliasing is used to sanitize syscall arguments");\
 	asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
 	asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
 		__attribute__((alias(__stringify(__se_compat_sys##name))));	\
@@ -80,8 +83,11 @@
 	asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
 	asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
 	{									\
-		return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
+		long ret = __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
+		__MAP(x,__SC_TEST,__VA_ARGS__);					\
+		return ret;							\
 	}									\
+	__diag_pop();								\
 	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 #endif /* COMPAT_SYSCALL_DEFINEx */
 
@@ -109,11 +115,6 @@ typedef	compat_ulong_t		compat_aio_context_t;
 struct compat_sel_arg_struct;
 struct rusage;
 
-struct compat_itimerspec {
-	struct compat_timespec it_interval;
-	struct compat_timespec it_value;
-};
-
 struct compat_utimbuf {
 	compat_time_t		actime;
 	compat_time_t		modtime;
@@ -294,10 +295,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *);
 extern int compat_put_timespec(const struct timespec *, void __user *);
 extern int compat_get_timeval(struct timeval *, const void __user *);
 extern int compat_put_timeval(const struct timeval *, void __user *);
-extern int get_compat_itimerspec64(struct itimerspec64 *its,
-			const struct compat_itimerspec __user *uits);
-extern int put_compat_itimerspec64(const struct itimerspec64 *its,
-			struct compat_itimerspec __user *uits);
 
 struct compat_iovec {
 	compat_uptr_t	iov_base;
@@ -1022,6 +1019,17 @@ static inline struct compat_timeval ns_to_compat_timeval(s64 nsec)
 	return ctv;
 }
 
+/*
+ * Kernel code should not call compat syscalls (i.e., compat_sys_xyzyyz())
+ * directly.  Instead, use one of the functions which work equivalently, such
+ * as the kcompat_sys_xyzyyz() functions prototyped below.
+ */
+
+int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz,
+		     struct compat_statfs64 __user * buf);
+int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz,
+			  struct compat_statfs64 __user * buf);
+
 #else /* !CONFIG_COMPAT */
 
 #define is_compat_task() (0)
diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h
index 31f2774f1994..e70bfd1d2c3f 100644
--- a/include/linux/compat_time.h
+++ b/include/linux/compat_time.h
@@ -17,7 +17,16 @@ struct compat_timeval {
 	s32		tv_usec;
 };
 
+struct compat_itimerspec {
+	struct compat_timespec it_interval;
+	struct compat_timespec it_value;
+};
+
 extern int compat_get_timespec64(struct timespec64 *, const void __user *);
 extern int compat_put_timespec64(const struct timespec64 *, void __user *);
+extern int get_compat_itimerspec64(struct itimerspec64 *its,
+			const struct compat_itimerspec __user *uits);
+extern int put_compat_itimerspec64(const struct itimerspec64 *its,
+			struct compat_itimerspec __user *uits);
 
 #endif /* _LINUX_COMPAT_TIME_H */
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index f1a7492a5cc8..573f5a7d42d4 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -66,25 +66,40 @@
 #endif
 
 /*
+ * Feature detection for gnu_inline (gnu89 extern inline semantics). Either
+ * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics,
+ * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not
+ * defined so the gnu89 semantics are the default.
+ */
+#ifdef __GNUC_STDC_INLINE__
+# define __gnu_inline	__attribute__((gnu_inline))
+#else
+# define __gnu_inline
+#endif
+
+/*
  * Force always-inline if the user requests it so via the .config,
  * or if gcc is too old.
  * GCC does not warn about unused static inline functions for
  * -Wunused-function.  This turns out to avoid the need for complex #ifdef
  * directives.  Suppress the warning in clang as well by using "unused"
  * function attribute, which is redundant but not harmful for gcc.
+ * Prefer gnu_inline, so that extern inline functions do not emit an
+ * externally visible function. This makes extern inline behave as per gnu89
+ * semantics rather than c99. This prevents multiple symbol definition errors
+ * of extern inline functions at link time.
+ * A lot of inline functions can cause havoc with function tracing.
  */
 #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) ||		\
     !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4)
-#define inline inline		__attribute__((always_inline,unused)) notrace
-#define __inline__ __inline__	__attribute__((always_inline,unused)) notrace
-#define __inline __inline	__attribute__((always_inline,unused)) notrace
+#define inline \
+	inline __attribute__((always_inline, unused)) notrace __gnu_inline
 #else
-/* A lot of inline functions can cause havoc with function tracing */
-#define inline inline		__attribute__((unused)) notrace
-#define __inline__ __inline__	__attribute__((unused)) notrace
-#define __inline __inline	__attribute__((unused)) notrace
+#define inline inline		__attribute__((unused)) notrace __gnu_inline
 #endif
 
+#define __inline__ inline
+#define __inline inline
 #define __always_inline	inline __attribute__((always_inline))
 #define  noinline	__attribute__((noinline))
 
@@ -347,3 +362,28 @@
 #if GCC_VERSION >= 50100
 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
 #endif
+
+/*
+ * Turn individual warnings and errors on and off locally, depending
+ * on version.
+ */
+#define __diag_GCC(version, severity, s) \
+	__diag_GCC_ ## version(__diag_GCC_ ## severity s)
+
+/* Severity used in pragma directives */
+#define __diag_GCC_ignore	ignored
+#define __diag_GCC_warn		warning
+#define __diag_GCC_error	error
+
+/* Compilers before gcc-4.6 do not understand "#pragma GCC diagnostic push" */
+#if GCC_VERSION >= 40600
+#define __diag_str1(s)		#s
+#define __diag_str(s)		__diag_str1(s)
+#define __diag(s)		_Pragma(__diag_str(GCC diagnostic s))
+#endif
+
+#if GCC_VERSION >= 80000
+#define __diag_GCC_8(s)		__diag(s)
+#else
+#define __diag_GCC_8(s)
+#endif
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 6b79a9bba9a7..a8ba6b04152c 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -271,4 +271,22 @@ struct ftrace_likely_data {
 # define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
 #endif
 
+#ifndef __diag
+#define __diag(string)
+#endif
+
+#ifndef __diag_GCC
+#define __diag_GCC(version, severity, string)
+#endif
+
+#define __diag_push()	__diag(push)
+#define __diag_pop()	__diag(pop)
+
+#define __diag_ignore(compiler, version, option, comment) \
+	__diag_ ## compiler(version, ignore, option)
+#define __diag_warn(compiler, version, option, comment) \
+	__diag_ ## compiler(version, warn, option)
+#define __diag_error(compiler, version, option, comment) \
+	__diag_ ## compiler(version, error, option)
+
 #endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index a97a63eef59f..218df7f4d3e1 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -30,7 +30,7 @@ struct cpu {
 };
 
 extern void boot_cpu_init(void);
-extern void boot_cpu_state_init(void);
+extern void boot_cpu_hotplug_init(void);
 extern void cpu_init(void);
 extern void trap_init(void);
 
@@ -55,6 +55,8 @@ extern ssize_t cpu_show_spectre_v2(struct device *dev,
 				   struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_spec_store_bypass(struct device *dev,
 					  struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_l1tf(struct device *dev,
+			     struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
@@ -103,6 +105,7 @@ extern void cpus_write_lock(void);
 extern void cpus_write_unlock(void);
 extern void cpus_read_lock(void);
 extern void cpus_read_unlock(void);
+extern int  cpus_read_trylock(void);
 extern void lockdep_assert_cpus_held(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
@@ -115,6 +118,7 @@ static inline void cpus_write_lock(void) { }
 static inline void cpus_write_unlock(void) { }
 static inline void cpus_read_lock(void) { }
 static inline void cpus_read_unlock(void) { }
+static inline int  cpus_read_trylock(void) { return true; }
 static inline void lockdep_assert_cpus_held(void) { }
 static inline void cpu_hotplug_disable(void) { }
 static inline void cpu_hotplug_enable(void) { }
@@ -166,4 +170,23 @@ void cpuhp_report_idle_dead(void);
 static inline void cpuhp_report_idle_dead(void) { }
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
+enum cpuhp_smt_control {
+	CPU_SMT_ENABLED,
+	CPU_SMT_DISABLED,
+	CPU_SMT_FORCE_DISABLED,
+	CPU_SMT_NOT_SUPPORTED,
+};
+
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
+extern enum cpuhp_smt_control cpu_smt_control;
+extern void cpu_smt_disable(bool force);
+extern void cpu_smt_check_topology_early(void);
+extern void cpu_smt_check_topology(void);
+#else
+# define cpu_smt_control		(CPU_SMT_ENABLED)
+static inline void cpu_smt_disable(bool force) { }
+static inline void cpu_smt_check_topology_early(void) { }
+static inline void cpu_smt_check_topology(void) { }
+#endif
+
 #endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 8796ba387152..4cf06a64bc02 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -164,6 +164,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
+	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 3855e3800f48..deb0f663252f 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -135,7 +135,7 @@ void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops);
-int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
 		    pfn_t *pfnp, int *errp, const struct iomap_ops *ops);
 vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 		enum page_entry_size pe_size, pfn_t pfn);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 66c6e17e61e5..d32957b423d5 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -227,7 +227,6 @@ extern void d_instantiate(struct dentry *, struct inode *);
 extern void d_instantiate_new(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
-extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
 extern void d_delete(struct dentry *);
@@ -271,8 +270,6 @@ extern void d_rehash(struct dentry *);
  
 extern void d_add(struct dentry *, struct inode *);
 
-extern void dentry_update_name_case(struct dentry *, const struct qstr *);
-
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
 extern void d_exchange(struct dentry *, struct dentry *);
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index e6c0448ebcc7..31c865d1842e 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -124,7 +124,7 @@ static inline void delayacct_blkio_start(void)
 
 static inline void delayacct_blkio_end(struct task_struct *p)
 {
-	if (current->delays)
+	if (p->delays)
 		__delayacct_blkio_end(p);
 	delayacct_clear_flag(DELAYACCT_PF_BLKIO);
 }
diff --git a/include/linux/device.h b/include/linux/device.h
index 055a69dbcd18..eb91127cc791 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -90,7 +90,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
  * @num_vf:	Called to find out how many virtual functions a device on this
  *		bus supports.
  * @dma_configure:	Called to setup DMA configuration on a device on
-			this bus.
+ *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
  * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
@@ -784,14 +784,16 @@ enum device_link_state {
  * Device link flags.
  *
  * STATELESS: The core won't track the presence of supplier/consumer drivers.
- * AUTOREMOVE: Remove this link automatically on consumer driver unbind.
+ * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind.
  * PM_RUNTIME: If set, the runtime PM framework will use this link.
  * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation.
+ * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind.
  */
-#define DL_FLAG_STATELESS	BIT(0)
-#define DL_FLAG_AUTOREMOVE	BIT(1)
-#define DL_FLAG_PM_RUNTIME	BIT(2)
-#define DL_FLAG_RPM_ACTIVE	BIT(3)
+#define DL_FLAG_STATELESS		BIT(0)
+#define DL_FLAG_AUTOREMOVE_CONSUMER	BIT(1)
+#define DL_FLAG_PM_RUNTIME		BIT(2)
+#define DL_FLAG_RPM_ACTIVE		BIT(3)
+#define DL_FLAG_AUTOREMOVE_SUPPLIER	BIT(4)
 
 /**
  * struct device_link - Device link representation.
@@ -886,6 +888,8 @@ struct dev_links_info {
  * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all
  * 		hardware supports 64-bit addresses for consistent allocations
  * 		such descriptors.
+ * @bus_dma_mask: Mask of an upstream bridge or bus which imposes a smaller DMA
+ *		limit than the device itself supports.
  * @dma_pfn_offset: offset of DMA memory range relatively of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
@@ -912,8 +916,6 @@ struct dev_links_info {
  * @offline:	Set after successful invocation of bus type's .offline().
  * @of_node_reused: Set if the device-tree node is shared with an ancestor
  *              device.
- * @dma_32bit_limit: bridge limited to 32bit DMA even if the device itself
- *		indicates support for a higher limit in the dma_mask field.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -967,6 +969,7 @@ struct device {
 					     not all hardware supports
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
+	u64		bus_dma_mask;	/* upstream dma_mask constraint */
 	unsigned long	dma_pfn_offset;
 
 	struct device_dma_parameters *dma_parms;
@@ -1002,7 +1005,6 @@ struct device {
 	bool			offline_disabled:1;
 	bool			offline:1;
 	bool			of_node_reused:1;
-	bool			dma_32bit_limit:1;
 };
 
 static inline struct device *kobj_to_dev(struct kobject *kobj)
@@ -1316,6 +1318,7 @@ extern const char *dev_driver_string(const struct device *dev);
 struct device_link *device_link_add(struct device *consumer,
 				    struct device *supplier, u32 flags);
 void device_link_del(struct device_link *link);
+void device_link_remove(void *consumer, struct device *supplier);
 
 #ifdef CONFIG_PRINTK
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index f9cc309507d9..1db6a6b46d0d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -538,10 +538,17 @@ static inline void dma_free_attrs(struct device *dev, size_t size,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!ops);
-	WARN_ON(irqs_disabled());
 
 	if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr))
 		return;
+	/*
+	 * On non-coherent platforms which implement DMA-coherent buffers via
+	 * non-cacheable remaps, ops->free() may call vunmap(). Thus getting
+	 * this far in IRQ context is a) at risk of a BUG_ON() or trying to
+	 * sleep on some machines, and b) an indication that the driver is
+	 * probably misusing the coherent API anyway.
+	 */
+	WARN_ON(irqs_disabled());
 
 	if (!ops->free || !cpu_addr)
 		return;
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 10b2654d549b..a0aa00cc909d 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -44,4 +44,12 @@ static inline void arch_sync_dma_for_cpu(struct device *dev,
 }
 #endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
 
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+void arch_sync_dma_for_cpu_all(struct device *dev);
+#else
+static inline void arch_sync_dma_for_cpu_all(struct device *dev)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
+
 #endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/include/linux/dma/pxa-dma.h b/include/linux/dma/pxa-dma.h
index e56ec7af4fd7..9fc594f69eff 100644
--- a/include/linux/dma/pxa-dma.h
+++ b/include/linux/dma/pxa-dma.h
@@ -9,6 +9,15 @@ enum pxad_chan_prio {
 	PXAD_PRIO_LOWEST,
 };
 
+/**
+ * struct pxad_param - dma channel request parameters
+ * @drcmr: requestor line number
+ * @prio: minimal mandatory priority of the channel
+ *
+ * If a requested channel is granted, its priority will be at least @prio,
+ * ie. if PXAD_PRIO_LOW is required, the requested channel will be either
+ * PXAD_PRIO_LOW, PXAD_PRIO_NORMAL or PXAD_PRIO_HIGHEST.
+ */
 struct pxad_param {
 	unsigned int drcmr;
 	enum pxad_chan_prio prio;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 56add823f190..401e4b254e30 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -894,6 +894,16 @@ typedef struct _efi_file_handle {
 	void *flush;
 } efi_file_handle_t;
 
+typedef struct {
+	u64 revision;
+	u32 open_volume;
+} efi_file_io_interface_32_t;
+
+typedef struct {
+	u64 revision;
+	u64 open_volume;
+} efi_file_io_interface_64_t;
+
 typedef struct _efi_file_io_interface {
 	u64 revision;
 	int (*open_volume)(struct _efi_file_io_interface *,
@@ -988,14 +998,12 @@ extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg);
 extern void efi_gettimeofday (struct timespec64 *ts);
 extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if possible */
 #ifdef CONFIG_X86
-extern void efi_late_init(void);
 extern void efi_free_boot_services(void);
 extern efi_status_t efi_query_variable_store(u32 attributes,
 					     unsigned long size,
 					     bool nonblocking);
 extern void efi_find_mirror(void);
 #else
-static inline void efi_late_init(void) {}
 static inline void efi_free_boot_services(void) {}
 
 static inline efi_status_t efi_query_variable_store(u32 attributes,
@@ -1651,4 +1659,7 @@ struct linux_efi_tpm_eventlog {
 
 extern int efi_tpm_eventlog_init(void);
 
+/* Workqueue to queue EFI Runtime Services */
+extern struct workqueue_struct *efi_rts_wq;
+
 #endif /* _LINUX_EFI_H */
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 7094718b653b..ffcc7724ca21 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -11,6 +11,7 @@
 
 #include <linux/fcntl.h>
 #include <linux/wait.h>
+#include <linux/err.h>
 
 /*
  * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
diff --git a/include/linux/file.h b/include/linux/file.h
index 279720db984a..6b2fb032416c 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -17,9 +17,12 @@ extern void fput(struct file *);
 struct file_operations;
 struct vfsmount;
 struct dentry;
+struct inode;
 struct path;
-extern struct file *alloc_file(const struct path *, fmode_t mode,
-	const struct file_operations *fop);
+extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
+	const char *, int flags, const struct file_operations *);
+extern struct file *alloc_file_clone(struct file *, int flags,
+	const struct file_operations *);
 
 static inline void fput_light(struct file *file, int fput_needed)
 {
@@ -78,7 +81,6 @@ extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);
 extern int replace_fd(unsigned fd, struct file *file, unsigned flags);
 extern void set_close_on_exec(unsigned int fd, int flag);
 extern bool get_close_on_exec(unsigned int fd);
-extern void put_filp(struct file *);
 extern int get_unused_fd_flags(unsigned flags);
 extern void put_unused_fd(unsigned int fd);
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index b615df57b7d5..c73dd7396886 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -470,16 +470,16 @@ struct sock_fprog_kern {
 };
 
 struct bpf_binary_header {
-	u16 pages;
-	u16 locked:1;
-	u8 image[];
+	u32 pages;
+	/* Some arches need word alignment for their instructions */
+	u8 image[] __aligned(4);
 };
 
 struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	u16			jited:1,	/* Is our filter JIT'ed? */
 				jit_requested:1,/* archs need to JIT the prog */
-				locked:1,	/* Program image locked? */
+				undo_set_mem:1,	/* Passed set_memory_ro() checkpoint */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
 				dst_needed:1,	/* Do we need dst entry? */
@@ -675,46 +675,24 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	fp->locked = 1;
-	if (set_memory_ro((unsigned long)fp, fp->pages))
-		fp->locked = 0;
-#endif
+	fp->undo_set_mem = 1;
+	set_memory_ro((unsigned long)fp, fp->pages);
 }
 
 static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	if (fp->locked) {
-		WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
-		/* In case set_memory_rw() fails, we want to be the first
-		 * to crash here instead of some random place later on.
-		 */
-		fp->locked = 0;
-	}
-#endif
+	if (fp->undo_set_mem)
+		set_memory_rw((unsigned long)fp, fp->pages);
 }
 
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	hdr->locked = 1;
-	if (set_memory_ro((unsigned long)hdr, hdr->pages))
-		hdr->locked = 0;
-#endif
+	set_memory_ro((unsigned long)hdr, hdr->pages);
 }
 
 static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	if (hdr->locked) {
-		WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
-		/* In case set_memory_rw() fails, we want to be the first
-		 * to crash here instead of some random place later on.
-		 */
-		hdr->locked = 0;
-	}
-#endif
+	set_memory_rw((unsigned long)hdr, hdr->pages);
 }
 
 static inline struct bpf_binary_header *
@@ -726,22 +704,6 @@ bpf_jit_binary_hdr(const struct bpf_prog *fp)
 	return (void *)addr;
 }
 
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp)
-{
-	if (!fp->locked)
-		return -ENOLCK;
-	if (fp->jited) {
-		const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
-
-		if (!hdr->locked)
-			return -ENOLCK;
-	}
-
-	return 0;
-}
-#endif
-
 int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
 static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
 {
@@ -803,8 +765,8 @@ static inline bool bpf_dump_raw_ok(void)
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 
-static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb,
-					   struct net_device *fwd)
+static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
+				 unsigned int pktlen)
 {
 	unsigned int len;
 
@@ -812,7 +774,7 @@ static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb,
 		return -ENETDOWN;
 
 	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
-	if (skb->len > len)
+	if (pktlen > len)
 		return -EMSGSIZE;
 
 	return 0;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5c91108846db..1ec33fd0423f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -148,6 +148,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* Has write method(s) */
 #define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
 
+#define FMODE_OPENED		((__force fmode_t)0x80000)
+#define FMODE_CREATED		((__force fmode_t)0x100000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
@@ -275,6 +278,7 @@ struct writeback_control;
 
 /*
  * Write life time hint values.
+ * Stored in struct inode as u8.
  */
 enum rw_hint {
 	WRITE_LIFE_NOT_SET	= 0,
@@ -609,8 +613,8 @@ struct inode {
 	struct timespec64	i_ctime;
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
-	unsigned int		i_blkbits;
-	enum rw_hint		i_write_hint;
+	u8			i_blkbits;
+	u8			i_write_hint;
 	blkcnt_t		i_blocks;
 
 #ifdef __NEED_I_SIZE_ORDERED
@@ -685,6 +689,17 @@ static inline int inode_unhashed(struct inode *inode)
 }
 
 /*
+ * __mark_inode_dirty expects inodes to be hashed.  Since we don't
+ * want special inodes in the fileset inode space, we make them
+ * appear hashed, but do not put on any lists.  hlist_del()
+ * will work fine and require no locking.
+ */
+static inline void inode_fake_hash(struct inode *inode)
+{
+	hlist_add_fake(&inode->i_hash);
+}
+
+/*
  * inode->i_mutex nesting subclasses for the lock validator:
  *
  * 0: the object of the current VFS operation
@@ -1720,8 +1735,6 @@ struct file_operations {
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
-	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
-	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -1778,7 +1791,7 @@ struct inode_operations {
 	int (*update_time)(struct inode *, struct timespec64 *, int);
 	int (*atomic_open)(struct inode *, struct dentry *,
 			   struct file *, unsigned open_flag,
-			   umode_t create_mode, int *opened);
+			   umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
 } ____cacheline_aligned;
@@ -2016,6 +2029,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
  * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
  *			and work dirs among overlayfs mounts.
  *
+ * I_CREATING		New object's inode in the middle of setting up.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -2036,7 +2051,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 #define __I_DIRTY_TIME_EXPIRED	12
 #define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
 #define I_WB_SWITCH		(1 << 13)
-#define I_OVL_INUSE			(1 << 14)
+#define I_OVL_INUSE		(1 << 14)
+#define I_CREATING		(1 << 15)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
@@ -2422,6 +2438,10 @@ extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int, umode_t);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
+static inline struct file *file_clone_open(struct file *file)
+{
+	return dentry_open(&file->f_path, file->f_flags, file->f_cred);
+}
 extern int filp_close(struct file *, fl_owner_t id);
 
 extern struct filename *getname_flags(const char __user *, int, int *);
@@ -2429,13 +2449,8 @@ extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 extern void putname(struct filename *name);
 
-enum {
-	FILE_CREATED = 1,
-	FILE_OPENED = 2
-};
 extern int finish_open(struct file *file, struct dentry *dentry,
-			int (*open)(struct inode *, struct file *),
-			int *opened);
+			int (*open)(struct inode *, struct file *));
 extern int finish_no_open(struct file *file, struct dentry *dentry);
 
 /* fs/ioctl.c */
@@ -2623,8 +2638,6 @@ static inline int filemap_fdatawait(struct address_space *mapping)
 
 extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
 				  loff_t lend);
-extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
-						loff_t lend);
 extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
@@ -2919,6 +2932,7 @@ extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
 static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
 #endif
 extern void unlock_new_inode(struct inode *);
+extern void discard_new_inode(struct inode *);
 extern unsigned int get_next_ino(void);
 extern void evict_inodes(struct super_block *sb);
 
diff --git a/include/linux/fsl/guts.h b/include/linux/fsl/guts.h
index 3efa3b861d44..941b11811f85 100644
--- a/include/linux/fsl/guts.h
+++ b/include/linux/fsl/guts.h
@@ -16,6 +16,7 @@
 #define __FSL_GUTS_H__
 
 #include <linux/types.h>
+#include <linux/io.h>
 
 /**
  * Global Utility Registers.
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8154f4920fcb..ebb77674be90 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -223,7 +223,6 @@ extern enum ftrace_tracing_type_t ftrace_tracing_type;
  */
 int register_ftrace_function(struct ftrace_ops *ops);
 int unregister_ftrace_function(struct ftrace_ops *ops);
-void clear_ftrace_function(void);
 
 extern void ftrace_stub(unsigned long a0, unsigned long a1,
 			struct ftrace_ops *op, struct pt_regs *regs);
@@ -239,7 +238,6 @@ static inline int ftrace_nr_registered_ops(void)
 {
 	return 0;
 }
-static inline void clear_ftrace_function(void) { }
 static inline void ftrace_kill(void) { }
 static inline void ftrace_free_init_mem(void) { }
 static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 4fe8f289b3f6..faebf0ca0686 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -45,7 +45,7 @@ struct fwnode_endpoint {
 struct fwnode_reference_args {
 	struct fwnode_handle *fwnode;
 	unsigned int nargs;
-	unsigned int args[NR_FWNODE_REFERENCE_ARGS];
+	u64 args[NR_FWNODE_REFERENCE_ARGS];
 };
 
 /**
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 6cb8a5789668..57864422a2c8 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/percpu-refcount.h>
 #include <linux/uuid.h>
+#include <linux/blk_types.h>
 
 #ifdef CONFIG_BLOCK
 
@@ -82,10 +83,10 @@ struct partition {
 } __attribute__((packed));
 
 struct disk_stats {
-	unsigned long sectors[2];	/* READs and WRITEs */
-	unsigned long ios[2];
-	unsigned long merges[2];
-	unsigned long ticks[2];
+	unsigned long sectors[NR_STAT_GROUPS];
+	unsigned long ios[NR_STAT_GROUPS];
+	unsigned long merges[NR_STAT_GROUPS];
+	unsigned long ticks[NR_STAT_GROUPS];
 	unsigned long io_ticks;
 	unsigned long time_in_queue;
 };
@@ -353,6 +354,11 @@ static inline void free_part_stats(struct hd_struct *part)
 
 #endif /* CONFIG_SMP */
 
+#define part_stat_read_accum(part, field)				\
+	(part_stat_read(part, field[STAT_READ]) +			\
+	 part_stat_read(part, field[STAT_WRITE]) +			\
+	 part_stat_read(part, field[STAT_DISCARD]))
+
 #define part_stat_add(cpu, part, field, addnd)	do {			\
 	__part_stat_add((cpu), (part), field, addnd);			\
 	if ((part)->partno)						\
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 91ed23468530..39745b8bdd65 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -14,7 +14,7 @@
 
 #include <linux/errno.h>
 
-/* see Documentation/gpio/gpio-legacy.txt */
+/* see Documentation/driver-api/gpio/legacy.rst */
 
 /* make these flag values available regardless of GPIO kconfig options */
 #define GPIOF_DIR_OUT	(0 << 0)
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 41a3d5775394..773bcb1d4044 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -511,6 +511,7 @@ struct hid_output_fifo {
 #define HID_STAT_ADDED		BIT(0)
 #define HID_STAT_PARSED		BIT(1)
 #define HID_STAT_DUP_DETECTED	BIT(2)
+#define HID_STAT_REPROBED	BIT(3)
 
 struct hid_input {
 	struct list_head list;
@@ -579,7 +580,7 @@ struct hid_device {							/* device report descriptor */
 	bool battery_avoid_query;
 #endif
 
-	unsigned int status;						/* see STAT flags above */
+	unsigned long status;						/* see STAT flags above */
 	unsigned claimed;						/* Claimed by hidinput, hiddev? */
 	unsigned quirks;						/* Various quirks the device can pull on us */
 	bool io_started;						/* If IO has started */
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 254cd34eeae2..465afb092fa7 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -140,9 +140,14 @@ extern int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
    and probably just as fast.
    Note that we use i2c_adapter here, because you do not need a specific
    smbus adapter to call this function. */
-extern s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
-			  unsigned short flags, char read_write, u8 command,
-			  int size, union i2c_smbus_data *data);
+s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		   unsigned short flags, char read_write, u8 command,
+		   int protocol, union i2c_smbus_data *data);
+
+/* Unlocked flavor */
+s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		     unsigned short flags, char read_write, u8 command,
+		     int protocol, union i2c_smbus_data *data);
 
 /* Now follow the 'nice' access routines. These also document the calling
    conventions of i2c_smbus_xfer. */
diff --git a/include/linux/idle_inject.h b/include/linux/idle_inject.h
new file mode 100644
index 000000000000..bdc0293fb6cb
--- /dev/null
+++ b/include/linux/idle_inject.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Linaro Ltd
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ */
+#ifndef __IDLE_INJECT_H__
+#define __IDLE_INJECT_H__
+
+/* private idle injection device structure */
+struct idle_inject_device;
+
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask);
+
+void idle_inject_unregister(struct idle_inject_device *ii_dev);
+
+int idle_inject_start(struct idle_inject_device *ii_dev);
+
+void idle_inject_stop(struct idle_inject_device *ii_dev);
+
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+				 unsigned int run_duration_ms,
+				 unsigned int idle_duration_ms);
+
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+				 unsigned int *run_duration_ms,
+				 unsigned int *idle_duration_ms);
+#endif /* __IDLE_INJECT_H__ */
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 7843b98e1c6e..c20c7e197d07 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -105,13 +105,13 @@ static inline bool br_vlan_enabled(const struct net_device *dev)
 
 static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
 {
-	return -1;
+	return -EINVAL;
 }
 
 static inline int br_vlan_get_info(const struct net_device *dev, u16 vid,
 				   struct bridge_vlan_info *p_vinfo)
 {
-	return -1;
+	return -EINVAL;
 }
 #endif
 
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index f8231854b5d6..119f53941c12 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -109,6 +109,8 @@ struct ip_mc_list {
 extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto);
 extern int igmp_rcv(struct sk_buff *);
 extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr);
+extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr,
+				unsigned int mode);
 extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr);
 extern void ip_mc_drop_socket(struct sock *sk);
 extern int ip_mc_source(int add, int omode, struct sock *sk,
diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h
index 767467d886de..67c75372b691 100644
--- a/include/linux/iio/buffer-dma.h
+++ b/include/linux/iio/buffer-dma.h
@@ -141,7 +141,7 @@ int iio_dma_buffer_read(struct iio_buffer *buffer, size_t n,
 	char __user *user_buffer);
 size_t iio_dma_buffer_data_available(struct iio_buffer *buffer);
 int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd);
-int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length);
+int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length);
 int iio_dma_buffer_request_update(struct iio_buffer *buffer);
 
 int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue,
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 84806b54b50a..97914a2833d1 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -17,7 +17,7 @@ struct linux_binprm;
 
 #ifdef CONFIG_IMA
 extern int ima_bprm_check(struct linux_binprm *bprm);
-extern int ima_file_check(struct file *file, int mask, int opened);
+extern int ima_file_check(struct file *file, int mask);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
 extern int ima_load_data(enum kernel_load_data_id id);
@@ -36,7 +36,7 @@ static inline int ima_bprm_check(struct linux_binprm *bprm)
 	return 0;
 }
 
-static inline int ima_file_check(struct file *file, int mask, int opened)
+static inline int ima_file_check(struct file *file, int mask)
 {
 	return 0;
 }
diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h
index d7188de4db96..3f4bf60b0bb5 100644
--- a/include/linux/input/mt.h
+++ b/include/linux/input/mt.h
@@ -100,7 +100,7 @@ static inline bool input_is_mt_axis(int axis)
 	return axis == ABS_MT_SLOT || input_is_mt_value(axis);
 }
 
-void input_mt_report_slot_state(struct input_dev *dev,
+bool input_mt_report_slot_state(struct input_dev *dev,
 				unsigned int tool_type, bool active);
 
 void input_mt_report_finger_count(struct input_dev *dev, int count);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 1df940196ab2..ef169d67df92 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -121,6 +121,7 @@
 #define ecap_srs(e)		((e >> 31) & 0x1)
 #define ecap_ers(e)		((e >> 30) & 0x1)
 #define ecap_prs(e)		((e >> 29) & 0x1)
+#define ecap_broken_pasid(e)	((e >> 28) & 0x1)
 #define ecap_dis(e)		((e >> 27) & 0x1)
 #define ecap_nest(e)		((e >> 26) & 0x1)
 #define ecap_mts(e)		((e >> 25) & 0x1)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index a044a824da85..3555d54bf79a 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -2,6 +2,9 @@
 #ifndef LINUX_IOMAP_H
 #define LINUX_IOMAP_H 1
 
+#include <linux/atomic.h>
+#include <linux/bitmap.h>
+#include <linux/mm.h>
 #include <linux/types.h>
 
 struct address_space;
@@ -9,6 +12,7 @@ struct fiemap_extent_info;
 struct inode;
 struct iov_iter;
 struct kiocb;
+struct page;
 struct vm_area_struct;
 struct vm_fault;
 
@@ -29,6 +33,7 @@ struct vm_fault;
  */
 #define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
 #define IOMAP_F_DIRTY		0x02	/* uncommitted metadata */
+#define IOMAP_F_BUFFER_HEAD	0x04	/* file system requires buffer heads */
 
 /*
  * Flags that only need to be reported for IOMAP_REPORT requests:
@@ -55,6 +60,16 @@ struct iomap {
 	u16			flags;	/* flags for mapping */
 	struct block_device	*bdev;	/* block device for I/O */
 	struct dax_device	*dax_dev; /* dax_dev for dax operations */
+	void			*inline_data;
+	void			*private; /* filesystem private */
+
+	/*
+	 * Called when finished processing a page in the mapping returned in
+	 * this iomap.  At least for now this is only supported in the buffered
+	 * write path.
+	 */
+	void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
+			struct page *page, struct iomap *iomap);
 };
 
 /*
@@ -86,8 +101,40 @@ struct iomap_ops {
 			ssize_t written, unsigned flags, struct iomap *iomap);
 };
 
+/*
+ * Structure allocate for each page when block size < PAGE_SIZE to track
+ * sub-page uptodate status and I/O completions.
+ */
+struct iomap_page {
+	atomic_t		read_count;
+	atomic_t		write_count;
+	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
+};
+
+static inline struct iomap_page *to_iomap_page(struct page *page)
+{
+	if (page_has_private(page))
+		return (struct iomap_page *)page_private(page);
+	return NULL;
+}
+
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
+int iomap_readpage(struct page *page, const struct iomap_ops *ops);
+int iomap_readpages(struct address_space *mapping, struct list_head *pages,
+		unsigned nr_pages, const struct iomap_ops *ops);
+int iomap_set_page_dirty(struct page *page);
+int iomap_is_partially_uptodate(struct page *page, unsigned long from,
+		unsigned long count);
+int iomap_releasepage(struct page *page, gfp_t gfp_mask);
+void iomap_invalidatepage(struct page *page, unsigned int offset,
+		unsigned int len);
+#ifdef CONFIG_MIGRATION
+int iomap_migrate_page(struct address_space *mapping, struct page *newpage,
+		struct page *page, enum migrate_mode mode);
+#else
+#define iomap_migrate_page NULL
+#endif
 int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index cbb872c1b607..9d2ea3e907d0 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -73,6 +73,7 @@
 #define GICD_TYPER_MBIS			(1U << 16)
 
 #define GICD_TYPER_ID_BITS(typer)	((((typer) >> 19) & 0x1f) + 1)
+#define GICD_TYPER_NUM_LPIS(typer)	((((typer) >> 11) & 0x1f) + 1)
 #define GICD_TYPER_IRQS(typer)		((((typer) & 0x1f) + 1) * 32)
 
 #define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
@@ -576,8 +577,8 @@ struct rdists {
 		phys_addr_t	phys_base;
 	} __percpu		*rdist;
 	struct page		*prop_page;
-	int			id_bits;
 	u64			flags;
+	u32			gicd_typer;
 	bool			has_vlpis;
 	bool			has_direct_lpi;
 };
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index b46b541c67c4..1a0b6f17a5d6 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -299,12 +299,18 @@ struct static_key_false {
 #define DEFINE_STATIC_KEY_TRUE(name)	\
 	struct static_key_true name = STATIC_KEY_TRUE_INIT
 
+#define DEFINE_STATIC_KEY_TRUE_RO(name)	\
+	struct static_key_true name __ro_after_init = STATIC_KEY_TRUE_INIT
+
 #define DECLARE_STATIC_KEY_TRUE(name)	\
 	extern struct static_key_true name
 
 #define DEFINE_STATIC_KEY_FALSE(name)	\
 	struct static_key_false name = STATIC_KEY_FALSE_INIT
 
+#define DEFINE_STATIC_KEY_FALSE_RO(name)	\
+	struct static_key_false name __ro_after_init = STATIC_KEY_FALSE_INIT
+
 #define DECLARE_STATIC_KEY_FALSE(name)	\
 	extern struct static_key_false name
 
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 9440a2fc8893..e909413e4e38 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -63,7 +63,6 @@ struct pt_regs;
 struct kretprobe;
 struct kretprobe_instance;
 typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *);
-typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *);
 typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *,
 				       unsigned long flags);
 typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *,
@@ -101,12 +100,6 @@ struct kprobe {
 	 */
 	kprobe_fault_handler_t fault_handler;
 
-	/*
-	 * ... called if breakpoint trap occurs in probe handler.
-	 * Return 1 if it handled break, otherwise kernel will see it.
-	 */
-	kprobe_break_handler_t break_handler;
-
 	/* Saved opcode (which has been replaced with breakpoint) */
 	kprobe_opcode_t opcode;
 
@@ -155,24 +148,6 @@ static inline int kprobe_ftrace(struct kprobe *p)
 }
 
 /*
- * Special probe type that uses setjmp-longjmp type tricks to resume
- * execution at a specified entry with a matching prototype corresponding
- * to the probed function - a trick to enable arguments to become
- * accessible seamlessly by probe handling logic.
- * Note:
- * Because of the way compilers allocate stack space for local variables
- * etc upfront, regardless of sub-scopes within a function, this mirroring
- * principle currently works only for probes placed on function entry points.
- */
-struct jprobe {
-	struct kprobe kp;
-	void *entry;	/* probe handling code to jump to */
-};
-
-/* For backward compatibility with old code using JPROBE_ENTRY() */
-#define JPROBE_ENTRY(handler)	(handler)
-
-/*
  * Function-return probe -
  * Note:
  * User needs to provide a handler function, and initialize maxactive.
@@ -389,9 +364,6 @@ int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
 int register_kprobes(struct kprobe **kps, int num);
 void unregister_kprobes(struct kprobe **kps, int num);
-int setjmp_pre_handler(struct kprobe *, struct pt_regs *);
-int longjmp_break_handler(struct kprobe *, struct pt_regs *);
-void jprobe_return(void);
 unsigned long arch_deref_entry_point(void *);
 
 int register_kretprobe(struct kretprobe *rp);
@@ -439,9 +411,6 @@ static inline void unregister_kprobe(struct kprobe *p)
 static inline void unregister_kprobes(struct kprobe **kps, int num)
 {
 }
-static inline void jprobe_return(void)
-{
-}
 static inline int register_kretprobe(struct kretprobe *rp)
 {
 	return -ENOSYS;
@@ -468,20 +437,6 @@ static inline int enable_kprobe(struct kprobe *kp)
 	return -ENOSYS;
 }
 #endif /* CONFIG_KPROBES */
-static inline int register_jprobe(struct jprobe *p)
-{
-	return -ENOSYS;
-}
-static inline int register_jprobes(struct jprobe **jps, int num)
-{
-	return -ENOSYS;
-}
-static inline void unregister_jprobe(struct jprobe *p)
-{
-}
-static inline void unregister_jprobes(struct jprobe **jps, int num)
-{
-}
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
 	return disable_kprobe(&rp->kp);
@@ -490,14 +445,6 @@ static inline int enable_kretprobe(struct kretprobe *rp)
 {
 	return enable_kprobe(&rp->kp);
 }
-static inline int disable_jprobe(struct jprobe *jp)
-{
-	return -ENOSYS;
-}
-static inline int enable_jprobe(struct jprobe *jp)
-{
-	return -ENOSYS;
-}
 
 #ifndef CONFIG_KPROBES
 static inline bool is_kprobe_insn_slot(unsigned long addr)
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 2803264c512f..c1961761311d 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -62,7 +62,6 @@ void *kthread_probe_data(struct task_struct *k);
 int kthread_park(struct task_struct *k);
 void kthread_unpark(struct task_struct *k);
 void kthread_parkme(void);
-void kthread_park_complete(struct task_struct *k);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 5b9fddbaac41..b2bb44f87f5a 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -93,8 +93,11 @@ static inline ktime_t timeval_to_ktime(struct timeval tv)
 /* Map the ktime_t to timeval conversion to ns_to_timeval function */
 #define ktime_to_timeval(kt)		ns_to_timeval((kt))
 
-/* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */
-#define ktime_to_ns(kt)			(kt)
+/* Convert ktime_t to nanoseconds */
+static inline s64 ktime_to_ns(const ktime_t kt)
+{
+	return kt;
+}
 
 /**
  * ktime_compare - Compares two ktime_t variables for less, greater or equal
diff --git a/include/linux/leds.h b/include/linux/leds.h
index b7e82550e655..834683d603f9 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -253,7 +253,7 @@ static inline bool led_sysfs_is_disabled(struct led_classdev *led_cdev)
 struct led_trigger {
 	/* Trigger Properties */
 	const char	 *name;
-	void		(*activate)(struct led_classdev *led_cdev);
+	int		(*activate)(struct led_classdev *led_cdev);
 	void		(*deactivate)(struct led_classdev *led_cdev);
 
 	/* LEDs under control by this trigger (for simple triggers) */
@@ -262,8 +262,19 @@ struct led_trigger {
 
 	/* Link to next registered trigger */
 	struct list_head  next_trig;
+
+	const struct attribute_group **groups;
 };
 
+/*
+ * Currently the attributes in struct led_trigger::groups are added directly to
+ * the LED device. As this might change in the future, the following
+ * macros abstract getting the LED device and its trigger_data from the dev
+ * parameter passed to the attribute accessor functions.
+ */
+#define led_trigger_get_led(dev)	((struct led_classdev *)dev_get_drvdata((dev)))
+#define led_trigger_get_drvdata(dev)	(led_get_trigger_data(led_trigger_get_led(dev)))
+
 ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
 			const char *buf, size_t count);
 ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr,
@@ -288,10 +299,16 @@ extern void led_trigger_blink_oneshot(struct led_trigger *trigger,
 				      unsigned long *delay_off,
 				      int invert);
 extern void led_trigger_set_default(struct led_classdev *led_cdev);
-extern void led_trigger_set(struct led_classdev *led_cdev,
-			struct led_trigger *trigger);
+extern int led_trigger_set(struct led_classdev *led_cdev,
+			   struct led_trigger *trigger);
 extern void led_trigger_remove(struct led_classdev *led_cdev);
 
+static inline void led_set_trigger_data(struct led_classdev *led_cdev,
+					void *trigger_data)
+{
+	led_cdev->trigger_data = trigger_data;
+}
+
 static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 {
 	return led_cdev->trigger_data;
@@ -315,6 +332,10 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 extern void led_trigger_rename_static(const char *name,
 				      struct led_trigger *trig);
 
+#define module_led_trigger(__led_trigger) \
+	module_driver(__led_trigger, led_trigger_register, \
+		      led_trigger_unregister)
+
 #else
 
 /* Trigger has no members */
@@ -334,9 +355,14 @@ static inline void led_trigger_blink_oneshot(struct led_trigger *trigger,
 				      unsigned long *delay_off,
 				      int invert) {}
 static inline void led_trigger_set_default(struct led_classdev *led_cdev) {}
-static inline void led_trigger_set(struct led_classdev *led_cdev,
-				struct led_trigger *trigger) {}
+static inline int led_trigger_set(struct led_classdev *led_cdev,
+				  struct led_trigger *trigger)
+{
+	return 0;
+}
+
 static inline void led_trigger_remove(struct led_classdev *led_cdev) {}
+static inline void led_set_trigger_data(struct led_classdev *led_cdev) {}
 static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 {
 	return NULL;
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 8b8946dd63b9..32f247cb5e9e 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -210,6 +210,7 @@ enum {
 	ATA_FLAG_SLAVE_POSS	= (1 << 0), /* host supports slave dev */
 					    /* (doesn't imply presence) */
 	ATA_FLAG_SATA		= (1 << 1),
+	ATA_FLAG_NO_LPM		= (1 << 2), /* host not happy with LPM */
 	ATA_FLAG_NO_LOG_PAGE	= (1 << 5), /* do not issue log page read */
 	ATA_FLAG_NO_ATAPI	= (1 << 6), /* No ATAPI support */
 	ATA_FLAG_PIO_DMA	= (1 << 7), /* PIO cmds via DMA */
@@ -1495,6 +1496,29 @@ static inline bool ata_tag_valid(unsigned int tag)
 	return tag < ATA_MAX_QUEUE || ata_tag_internal(tag);
 }
 
+#define __ata_qc_for_each(ap, qc, tag, max_tag, fn)		\
+	for ((tag) = 0; (tag) < (max_tag) &&			\
+	     ({ qc = fn((ap), (tag)); 1; }); (tag)++)		\
+
+/*
+ * Internal use only, iterate commands ignoring error handling and
+ * status of 'qc'.
+ */
+#define ata_qc_for_each_raw(ap, qc, tag)					\
+	__ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, __ata_qc_from_tag)
+
+/*
+ * Iterate all potential commands that can be queued
+ */
+#define ata_qc_for_each(ap, qc, tag)					\
+	__ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, ata_qc_from_tag)
+
+/*
+ * Like ata_qc_for_each, but with the internal tag included
+ */
+#define ata_qc_for_each_with_internal(ap, qc, tag)			\
+	__ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE + 1, ata_qc_from_tag)
+
 /*
  * device helpers
  */
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index a08bc2587b96..97a020c616ad 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1573,7 +1573,7 @@ union security_list_options {
 	int (*file_send_sigiotask)(struct task_struct *tsk,
 					struct fown_struct *fown, int sig);
 	int (*file_receive)(struct file *file);
-	int (*file_open)(struct file *file, const struct cred *cred);
+	int (*file_open)(struct file *file);
 
 	int (*task_alloc)(struct task_struct *task, unsigned long clone_flags);
 	void (*task_free)(struct task_struct *task);
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 4f5f8c21e283..1eb6f244588d 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -27,6 +27,8 @@
  */
 #define MARVELL_PHY_ID_88E6390		0x01410f90
 
+#define MARVELL_PHY_FAMILY_ID(id)	((id) >> 4)
+
 /* struct phy_device dev_flags definitions */
 #define MARVELL_PHY_M1145_FLAGS_RESISTANCE	0x00000001
 #define MARVELL_PHY_M1118_DNS323_LEDS		0x00000002
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index ca59883c8364..516920549378 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -20,31 +20,60 @@
 #define INIT_MEMBLOCK_REGIONS	128
 #define INIT_PHYSMEM_REGIONS	4
 
-/* Definition of memblock flags. */
-enum {
+/**
+ * enum memblock_flags - definition of memory region attributes
+ * @MEMBLOCK_NONE: no special request
+ * @MEMBLOCK_HOTPLUG: hotpluggable region
+ * @MEMBLOCK_MIRROR: mirrored region
+ * @MEMBLOCK_NOMAP: don't add to kernel direct mapping
+ */
+enum memblock_flags {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
 	MEMBLOCK_HOTPLUG	= 0x1,	/* hotpluggable region */
 	MEMBLOCK_MIRROR		= 0x2,	/* mirrored region */
 	MEMBLOCK_NOMAP		= 0x4,	/* don't add to kernel direct mapping */
 };
 
+/**
+ * struct memblock_region - represents a memory region
+ * @base: physical address of the region
+ * @size: size of the region
+ * @flags: memory region attributes
+ * @nid: NUMA node id
+ */
 struct memblock_region {
 	phys_addr_t base;
 	phys_addr_t size;
-	unsigned long flags;
+	enum memblock_flags flags;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	int nid;
 #endif
 };
 
+/**
+ * struct memblock_type - collection of memory regions of certain type
+ * @cnt: number of regions
+ * @max: size of the allocated array
+ * @total_size: size of all regions
+ * @regions: array of regions
+ * @name: the memory type symbolic name
+ */
 struct memblock_type {
-	unsigned long cnt;	/* number of regions */
-	unsigned long max;	/* size of the allocated array */
-	phys_addr_t total_size;	/* size of all regions */
+	unsigned long cnt;
+	unsigned long max;
+	phys_addr_t total_size;
 	struct memblock_region *regions;
 	char *name;
 };
 
+/**
+ * struct memblock - memblock allocator metadata
+ * @bottom_up: is bottom up direction?
+ * @current_limit: physical address of the current allocation limit
+ * @memory: usabe memory regions
+ * @reserved: reserved memory regions
+ * @physmem: all physical memory
+ */
 struct memblock {
 	bool bottom_up;  /* is bottom up direction? */
 	phys_addr_t current_limit;
@@ -72,7 +101,7 @@ void memblock_discard(void);
 
 phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align,
 					phys_addr_t start, phys_addr_t end,
-					int nid, ulong flags);
+					int nid, enum memblock_flags flags);
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
 void memblock_allow_resize(void);
@@ -89,19 +118,19 @@ int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
 int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
-ulong choose_memblock_flags(void);
+enum memblock_flags choose_memblock_flags(void);
 
 /* Low level functions */
 int memblock_add_range(struct memblock_type *type,
 		       phys_addr_t base, phys_addr_t size,
-		       int nid, unsigned long flags);
+		       int nid, enum memblock_flags flags);
 
-void __next_mem_range(u64 *idx, int nid, ulong flags,
+void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
 		      struct memblock_type *type_a,
 		      struct memblock_type *type_b, phys_addr_t *out_start,
 		      phys_addr_t *out_end, int *out_nid);
 
-void __next_mem_range_rev(u64 *idx, int nid, ulong flags,
+void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags,
 			  struct memblock_type *type_a,
 			  struct memblock_type *type_b, phys_addr_t *out_start,
 			  phys_addr_t *out_end, int *out_nid);
@@ -239,7 +268,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 /**
  * for_each_resv_unavail_range - iterate through reserved and unavailable memory
  * @i: u64 used as loop variable
- * @flags: pick from blocks based on memory attributes
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  *
@@ -253,13 +281,13 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 			   NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL)
 
 static inline void memblock_set_region_flags(struct memblock_region *r,
-					     unsigned long flags)
+					     enum memblock_flags flags)
 {
 	r->flags |= flags;
 }
 
 static inline void memblock_clear_region_flags(struct memblock_region *r,
-					       unsigned long flags)
+					       enum memblock_flags flags)
 {
 	r->flags &= ~flags;
 }
@@ -317,10 +345,10 @@ static inline bool memblock_bottom_up(void)
 
 phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
 					phys_addr_t start, phys_addr_t end,
-					ulong flags);
+					enum memblock_flags flags);
 phys_addr_t memblock_alloc_base_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t max_addr,
-					int nid, ulong flags);
+					int nid, enum memblock_flags flags);
 phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align,
 				phys_addr_t max_addr);
 phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align,
@@ -367,8 +395,10 @@ phys_addr_t memblock_get_current_limit(void);
  */
 
 /**
- * memblock_region_memory_base_pfn - Return the lowest pfn intersecting with the memory region
+ * memblock_region_memory_base_pfn - get the lowest pfn of the memory region
  * @reg: memblock_region structure
+ *
+ * Return: the lowest pfn intersecting with the memory region
  */
 static inline unsigned long memblock_region_memory_base_pfn(const struct memblock_region *reg)
 {
@@ -376,8 +406,10 @@ static inline unsigned long memblock_region_memory_base_pfn(const struct membloc
 }
 
 /**
- * memblock_region_memory_end_pfn - Return the end_pfn this region
+ * memblock_region_memory_end_pfn - get the end pfn of the memory region
  * @reg: memblock_region structure
+ *
+ * Return: the end_pfn of the reserved region
  */
 static inline unsigned long memblock_region_memory_end_pfn(const struct memblock_region *reg)
 {
@@ -385,8 +417,10 @@ static inline unsigned long memblock_region_memory_end_pfn(const struct memblock
 }
 
 /**
- * memblock_region_reserved_base_pfn - Return the lowest pfn intersecting with the reserved region
+ * memblock_region_reserved_base_pfn - get the lowest pfn of the reserved region
  * @reg: memblock_region structure
+ *
+ * Return: the lowest pfn intersecting with the reserved region
  */
 static inline unsigned long memblock_region_reserved_base_pfn(const struct memblock_region *reg)
 {
@@ -394,8 +428,10 @@ static inline unsigned long memblock_region_reserved_base_pfn(const struct membl
 }
 
 /**
- * memblock_region_reserved_end_pfn - Return the end_pfn this region
+ * memblock_region_reserved_end_pfn - get the end pfn of the reserved region
  * @reg: memblock_region structure
+ *
+ * Return: the end_pfn of the reserved region
  */
 static inline unsigned long memblock_region_reserved_end_pfn(const struct memblock_region *reg)
 {
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6c6fb116e925..680d3395fc83 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -317,6 +317,9 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
 			  bool compound);
+int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
+			  bool compound);
 void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
 			      bool lrucare, bool compound);
 void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
@@ -789,6 +792,16 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 	return 0;
 }
 
+static inline int mem_cgroup_try_charge_delay(struct page *page,
+					      struct mm_struct *mm,
+					      gfp_t gfp_mask,
+					      struct mem_cgroup **memcgp,
+					      bool compound)
+{
+	*memcgp = NULL;
+	return 0;
+}
+
 static inline void mem_cgroup_commit_charge(struct page *page,
 					    struct mem_cgroup *memcg,
 					    bool lrucare, bool compound)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 80cbb7fdce4a..83957920653a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -358,6 +358,7 @@ struct mlx5_frag_buf_ctrl {
 	struct mlx5_frag_buf	frag_buf;
 	u32			sz_m1;
 	u32			frag_sz_m1;
+	u32			strides_offset;
 	u8			log_sz;
 	u8			log_stride;
 	u8			log_frag_strides;
@@ -983,14 +984,22 @@ static inline u32 mlx5_base_mkey(const u32 key)
 	return key & 0xffffff00u;
 }
 
-static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
-				 struct mlx5_frag_buf_ctrl *fbc)
+static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz,
+					u32 strides_offset,
+					struct mlx5_frag_buf_ctrl *fbc)
 {
 	fbc->log_stride = log_stride;
 	fbc->log_sz     = log_sz;
 	fbc->sz_m1	= (1 << fbc->log_sz) - 1;
 	fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride;
 	fbc->frag_sz_m1	= (1 << fbc->log_frag_strides) - 1;
+	fbc->strides_offset = strides_offset;
+}
+
+static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
+				 struct mlx5_frag_buf_ctrl *fbc)
+{
+	mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc);
 }
 
 static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
@@ -1004,7 +1013,10 @@ static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
 static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc,
 					  u32 ix)
 {
-	unsigned int frag = (ix >> fbc->log_frag_strides);
+	unsigned int frag;
+
+	ix  += fbc->strides_offset;
+	frag = ix >> fbc->log_frag_strides;
 
 	return fbc->frag_buf.frags[frag].buf +
 		((fbc->frag_sz_m1 & ix) << fbc->log_stride);
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index d3c9db492b30..fab5121ffb8f 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -8,6 +8,8 @@
 
 #include <linux/mlx5/driver.h>
 
+#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
+
 enum {
 	SRIOV_NONE,
 	SRIOV_LEGACY,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 27134c4fcb76..ac281f5ec9b8 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -922,7 +922,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         vnic_env_queue_counters[0x1];
 	u8         ets[0x1];
 	u8         nic_flow_table[0x1];
-	u8         eswitch_flow_table[0x1];
+	u8         eswitch_manager[0x1];
 	u8         device_memory[0x1];
 	u8         mcam_reg[0x1];
 	u8         pcam_reg[0x1];
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a0fbb9ffe380..68a5121694ef 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -155,7 +155,9 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *,
  * mmap() functions).
  */
 
-extern struct kmem_cache *vm_area_cachep;
+struct vm_area_struct *vm_area_alloc(struct mm_struct *);
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
+void vm_area_free(struct vm_area_struct *);
 
 #ifndef CONFIG_MMU
 extern struct rb_root nommu_region_tree;
@@ -450,6 +452,23 @@ struct vm_operations_struct {
 					  unsigned long addr);
 };
 
+static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
+{
+	static const struct vm_operations_struct dummy_vm_ops = {};
+
+	vma->vm_mm = mm;
+	vma->vm_ops = &dummy_vm_ops;
+	INIT_LIST_HEAD(&vma->anon_vma_chain);
+}
+
+static inline void vma_set_anonymous(struct vm_area_struct *vma)
+{
+	vma->vm_ops = NULL;
+}
+
+/* flush_tlb_range() takes a vma, not a mm, and can care about flags */
+#define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) }
+
 struct mmu_gather;
 struct inode;
 
@@ -2132,7 +2151,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn,
 					struct mminit_pfnnid_cache *state);
 #endif
 
-#ifdef CONFIG_HAVE_MEMBLOCK
+#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
 void zero_resv_unavail(void);
 #else
 static inline void zero_resv_unavail(void) {}
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 99ce070e7dcb..efdc24dd9e97 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -335,176 +335,183 @@ struct core_state {
 
 struct kioctx_table;
 struct mm_struct {
-	struct vm_area_struct *mmap;		/* list of VMAs */
-	struct rb_root mm_rb;
-	u32 vmacache_seqnum;                   /* per-thread vmacache */
+	struct {
+		struct vm_area_struct *mmap;		/* list of VMAs */
+		struct rb_root mm_rb;
+		u32 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
-	unsigned long (*get_unmapped_area) (struct file *filp,
+		unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
 				unsigned long pgoff, unsigned long flags);
 #endif
-	unsigned long mmap_base;		/* base of mmap area */
-	unsigned long mmap_legacy_base;         /* base of mmap area in bottom-up allocations */
+		unsigned long mmap_base;	/* base of mmap area */
+		unsigned long mmap_legacy_base;	/* base of mmap area in bottom-up allocations */
 #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
-	/* Base adresses for compatible mmap() */
-	unsigned long mmap_compat_base;
-	unsigned long mmap_compat_legacy_base;
+		/* Base adresses for compatible mmap() */
+		unsigned long mmap_compat_base;
+		unsigned long mmap_compat_legacy_base;
 #endif
-	unsigned long task_size;		/* size of task vm space */
-	unsigned long highest_vm_end;		/* highest vma end address */
-	pgd_t * pgd;
-
-	/**
-	 * @mm_users: The number of users including userspace.
-	 *
-	 * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops
-	 * to 0 (i.e. when the task exits and there are no other temporary
-	 * reference holders), we also release a reference on @mm_count
-	 * (which may then free the &struct mm_struct if @mm_count also
-	 * drops to 0).
-	 */
-	atomic_t mm_users;
-
-	/**
-	 * @mm_count: The number of references to &struct mm_struct
-	 * (@mm_users count as 1).
-	 *
-	 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
-	 * &struct mm_struct is freed.
-	 */
-	atomic_t mm_count;
+		unsigned long task_size;	/* size of task vm space */
+		unsigned long highest_vm_end;	/* highest vma end address */
+		pgd_t * pgd;
+
+		/**
+		 * @mm_users: The number of users including userspace.
+		 *
+		 * Use mmget()/mmget_not_zero()/mmput() to modify. When this
+		 * drops to 0 (i.e. when the task exits and there are no other
+		 * temporary reference holders), we also release a reference on
+		 * @mm_count (which may then free the &struct mm_struct if
+		 * @mm_count also drops to 0).
+		 */
+		atomic_t mm_users;
+
+		/**
+		 * @mm_count: The number of references to &struct mm_struct
+		 * (@mm_users count as 1).
+		 *
+		 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
+		 * &struct mm_struct is freed.
+		 */
+		atomic_t mm_count;
 
 #ifdef CONFIG_MMU
-	atomic_long_t pgtables_bytes;		/* PTE page table pages */
+		atomic_long_t pgtables_bytes;	/* PTE page table pages */
 #endif
-	int map_count;				/* number of VMAs */
+		int map_count;			/* number of VMAs */
 
-	spinlock_t page_table_lock;		/* Protects page tables and some counters */
-	struct rw_semaphore mmap_sem;
+		spinlock_t page_table_lock; /* Protects page tables and some
+					     * counters
+					     */
+		struct rw_semaphore mmap_sem;
 
-	struct list_head mmlist;		/* List of maybe swapped mm's.	These are globally strung
-						 * together off init_mm.mmlist, and are protected
-						 * by mmlist_lock
-						 */
+		struct list_head mmlist; /* List of maybe swapped mm's.	These
+					  * are globally strung together off
+					  * init_mm.mmlist, and are protected
+					  * by mmlist_lock
+					  */
 
 
-	unsigned long hiwater_rss;	/* High-watermark of RSS usage */
-	unsigned long hiwater_vm;	/* High-water virtual memory usage */
+		unsigned long hiwater_rss; /* High-watermark of RSS usage */
+		unsigned long hiwater_vm;  /* High-water virtual memory usage */
 
-	unsigned long total_vm;		/* Total pages mapped */
-	unsigned long locked_vm;	/* Pages that have PG_mlocked set */
-	unsigned long pinned_vm;	/* Refcount permanently increased */
-	unsigned long data_vm;		/* VM_WRITE & ~VM_SHARED & ~VM_STACK */
-	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE & ~VM_STACK */
-	unsigned long stack_vm;		/* VM_STACK */
-	unsigned long def_flags;
+		unsigned long total_vm;	   /* Total pages mapped */
+		unsigned long locked_vm;   /* Pages that have PG_mlocked set */
+		unsigned long pinned_vm;   /* Refcount permanently increased */
+		unsigned long data_vm;	   /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
+		unsigned long exec_vm;	   /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
+		unsigned long stack_vm;	   /* VM_STACK */
+		unsigned long def_flags;
 
-	spinlock_t arg_lock; /* protect the below fields */
-	unsigned long start_code, end_code, start_data, end_data;
-	unsigned long start_brk, brk, start_stack;
-	unsigned long arg_start, arg_end, env_start, env_end;
+		spinlock_t arg_lock; /* protect the below fields */
+		unsigned long start_code, end_code, start_data, end_data;
+		unsigned long start_brk, brk, start_stack;
+		unsigned long arg_start, arg_end, env_start, env_end;
 
-	unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
+		unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
 
-	/*
-	 * Special counters, in some configurations protected by the
-	 * page_table_lock, in other configurations by being atomic.
-	 */
-	struct mm_rss_stat rss_stat;
-
-	struct linux_binfmt *binfmt;
+		/*
+		 * Special counters, in some configurations protected by the
+		 * page_table_lock, in other configurations by being atomic.
+		 */
+		struct mm_rss_stat rss_stat;
 
-	cpumask_var_t cpu_vm_mask_var;
+		struct linux_binfmt *binfmt;
 
-	/* Architecture-specific MM context */
-	mm_context_t context;
+		/* Architecture-specific MM context */
+		mm_context_t context;
 
-	unsigned long flags; /* Must use atomic bitops to access the bits */
+		unsigned long flags; /* Must use atomic bitops to access */
 
-	struct core_state *core_state; /* coredumping support */
+		struct core_state *core_state; /* coredumping support */
 #ifdef CONFIG_MEMBARRIER
-	atomic_t membarrier_state;
+		atomic_t membarrier_state;
 #endif
 #ifdef CONFIG_AIO
-	spinlock_t			ioctx_lock;
-	struct kioctx_table __rcu	*ioctx_table;
+		spinlock_t			ioctx_lock;
+		struct kioctx_table __rcu	*ioctx_table;
 #endif
 #ifdef CONFIG_MEMCG
-	/*
-	 * "owner" points to a task that is regarded as the canonical
-	 * user/owner of this mm. All of the following must be true in
-	 * order for it to be changed:
-	 *
-	 * current == mm->owner
-	 * current->mm != mm
-	 * new_owner->mm == mm
-	 * new_owner->alloc_lock is held
-	 */
-	struct task_struct __rcu *owner;
+		/*
+		 * "owner" points to a task that is regarded as the canonical
+		 * user/owner of this mm. All of the following must be true in
+		 * order for it to be changed:
+		 *
+		 * current == mm->owner
+		 * current->mm != mm
+		 * new_owner->mm == mm
+		 * new_owner->alloc_lock is held
+		 */
+		struct task_struct __rcu *owner;
 #endif
-	struct user_namespace *user_ns;
+		struct user_namespace *user_ns;
 
-	/* store ref to file /proc/<pid>/exe symlink points to */
-	struct file __rcu *exe_file;
+		/* store ref to file /proc/<pid>/exe symlink points to */
+		struct file __rcu *exe_file;
 #ifdef CONFIG_MMU_NOTIFIER
-	struct mmu_notifier_mm *mmu_notifier_mm;
+		struct mmu_notifier_mm *mmu_notifier_mm;
 #endif
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
-	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
-#endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	struct cpumask cpumask_allocation;
+		pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
 #ifdef CONFIG_NUMA_BALANCING
-	/*
-	 * numa_next_scan is the next time that the PTEs will be marked
-	 * pte_numa. NUMA hinting faults will gather statistics and migrate
-	 * pages to new nodes if necessary.
-	 */
-	unsigned long numa_next_scan;
+		/*
+		 * numa_next_scan is the next time that the PTEs will be marked
+		 * pte_numa. NUMA hinting faults will gather statistics and
+		 * migrate pages to new nodes if necessary.
+		 */
+		unsigned long numa_next_scan;
 
-	/* Restart point for scanning and setting pte_numa */
-	unsigned long numa_scan_offset;
+		/* Restart point for scanning and setting pte_numa */
+		unsigned long numa_scan_offset;
 
-	/* numa_scan_seq prevents two threads setting pte_numa */
-	int numa_scan_seq;
+		/* numa_scan_seq prevents two threads setting pte_numa */
+		int numa_scan_seq;
 #endif
-	/*
-	 * An operation with batched TLB flushing is going on. Anything that
-	 * can move process memory needs to flush the TLB when moving a
-	 * PROT_NONE or PROT_NUMA mapped page.
-	 */
-	atomic_t tlb_flush_pending;
+		/*
+		 * An operation with batched TLB flushing is going on. Anything
+		 * that can move process memory needs to flush the TLB when
+		 * moving a PROT_NONE or PROT_NUMA mapped page.
+		 */
+		atomic_t tlb_flush_pending;
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
-	/* See flush_tlb_batched_pending() */
-	bool tlb_flush_batched;
+		/* See flush_tlb_batched_pending() */
+		bool tlb_flush_batched;
 #endif
-	struct uprobes_state uprobes_state;
+		struct uprobes_state uprobes_state;
 #ifdef CONFIG_HUGETLB_PAGE
-	atomic_long_t hugetlb_usage;
+		atomic_long_t hugetlb_usage;
 #endif
-	struct work_struct async_put_work;
+		struct work_struct async_put_work;
 
 #if IS_ENABLED(CONFIG_HMM)
-	/* HMM needs to track a few things per mm */
-	struct hmm *hmm;
+		/* HMM needs to track a few things per mm */
+		struct hmm *hmm;
 #endif
-} __randomize_layout;
+	} __randomize_layout;
+
+	/*
+	 * The mm_cpumask needs to be at the end of mm_struct, because it
+	 * is dynamically sized based on nr_cpu_ids.
+	 */
+	unsigned long cpu_bitmap[];
+};
 
 extern struct mm_struct init_mm;
 
+/* Pointer magic because the dynamic array size confuses some compilers. */
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	mm->cpu_vm_mask_var = &mm->cpumask_allocation;
-#endif
-	cpumask_clear(mm->cpu_vm_mask_var);
+	unsigned long cpu_bitmap = (unsigned long)mm;
+
+	cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap);
+	cpumask_clear((struct cpumask *)cpu_bitmap);
 }
 
 /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
 static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 {
-	return mm->cpu_vm_mask_var;
+	return (struct cpumask *)&mm->cpu_bitmap;
 }
 
 struct mmu_gather;
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index a86c4fa93115..cd0be91bdefa 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -67,9 +67,11 @@ struct mtd_erase_region_info {
  * @datbuf:	data buffer - if NULL only oob data are read/written
  * @oobbuf:	oob data buffer
  *
- * Note, it is allowed to read more than one OOB area at one go, but not write.
- * The interface assumes that the OOB write requests program only one page's
- * OOB area.
+ * Note, some MTD drivers do not allow you to write more than one OOB area at
+ * one go. If you try to do that on such an MTD device, -EINVAL will be
+ * returned. If you want to make your implementation portable on all kind of MTD
+ * devices you should split the write request into several sub-requests when the
+ * request crosses a page boundary.
  */
 struct mtd_oob_ops {
 	unsigned int	mode;
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 3e8ec3b8a39c..efb2345359bb 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -21,11 +21,10 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/flashchip.h>
 #include <linux/mtd/bbm.h>
+#include <linux/of.h>
 #include <linux/types.h>
 
-struct mtd_info;
 struct nand_flash_dev;
-struct device_node;
 
 /* Scan and identify a NAND device */
 int nand_scan_with_ids(struct mtd_info *mtd, int max_chips,
@@ -36,17 +35,6 @@ static inline int nand_scan(struct mtd_info *mtd, int max_chips)
 	return nand_scan_with_ids(mtd, max_chips, NULL);
 }
 
-/*
- * Separate phases of nand_scan(), allowing board driver to intervene
- * and override command or ECC setup according to flash type.
- */
-int nand_scan_ident(struct mtd_info *mtd, int max_chips,
-			   struct nand_flash_dev *table);
-int nand_scan_tail(struct mtd_info *mtd);
-
-/* Unregister the MTD device and free resources held by the NAND device */
-void nand_release(struct mtd_info *mtd);
-
 /* Internal helper for board drivers which need to override command function */
 void nand_wait_ready(struct mtd_info *mtd);
 
@@ -121,6 +109,7 @@ enum nand_ecc_algo {
 	NAND_ECC_UNKNOWN,
 	NAND_ECC_HAMMING,
 	NAND_ECC_BCH,
+	NAND_ECC_RS,
 };
 
 /*
@@ -218,6 +207,12 @@ enum nand_ecc_algo {
  */
 #define NAND_WAIT_TCCS		0x00200000
 
+/*
+ * Whether the NAND chip is a boot medium. Drivers might use this information
+ * to select ECC algorithms supported by the boot ROM or similar restrictions.
+ */
+#define NAND_IS_BOOT_MEDIUM	0x00400000
+
 /* Options set by nand scan */
 /* Nand scan has allocated controller struct */
 #define NAND_CONTROLLER_ALLOC	0x80000000
@@ -230,6 +225,17 @@ enum nand_ecc_algo {
 /* Keep gcc happy */
 struct nand_chip;
 
+/* ONFI version bits */
+#define ONFI_VERSION_1_0		BIT(1)
+#define ONFI_VERSION_2_0		BIT(2)
+#define ONFI_VERSION_2_1		BIT(3)
+#define ONFI_VERSION_2_2		BIT(4)
+#define ONFI_VERSION_2_3		BIT(5)
+#define ONFI_VERSION_3_0		BIT(6)
+#define ONFI_VERSION_3_1		BIT(7)
+#define ONFI_VERSION_3_2		BIT(8)
+#define ONFI_VERSION_4_0		BIT(9)
+
 /* ONFI features */
 #define ONFI_FEATURE_16_BIT_BUS		(1 << 0)
 #define ONFI_FEATURE_EXT_PARAM_PAGE	(1 << 7)
@@ -470,13 +476,13 @@ struct onfi_params {
  */
 struct nand_parameters {
 	/* Generic parameters */
-	char model[100];
+	const char *model;
 	bool supports_set_get_features;
 	DECLARE_BITMAP(set_feature_list, ONFI_FEATURE_NUMBER);
 	DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER);
 
 	/* ONFI parameters */
-	struct onfi_params onfi;
+	struct onfi_params *onfi;
 };
 
 /* The maximum expected count of bytes in the NAND ID sequence */
@@ -493,20 +499,42 @@ struct nand_id {
 };
 
 /**
- * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices
+ * struct nand_controller_ops - Controller operations
+ *
+ * @attach_chip: this method is called after the NAND detection phase after
+ *		 flash ID and MTD fields such as erase size, page size and OOB
+ *		 size have been set up. ECC requirements are available if
+ *		 provided by the NAND chip or device tree. Typically used to
+ *		 choose the appropriate ECC configuration and allocate
+ *		 associated resources.
+ *		 This hook is optional.
+ * @detach_chip: free all resources allocated/claimed in
+ *		 nand_controller_ops->attach_chip().
+ *		 This hook is optional.
+ */
+struct nand_controller_ops {
+	int (*attach_chip)(struct nand_chip *chip);
+	void (*detach_chip)(struct nand_chip *chip);
+};
+
+/**
+ * struct nand_controller - Structure used to describe a NAND controller
+ *
  * @lock:               protection lock
  * @active:		the mtd device which holds the controller currently
  * @wq:			wait queue to sleep on if a NAND operation is in
  *			progress used instead of the per chip wait queue
  *			when a hw controller is available.
+ * @ops:		NAND controller operations.
  */
-struct nand_hw_control {
+struct nand_controller {
 	spinlock_t lock;
 	struct nand_chip *active;
 	wait_queue_head_t wq;
+	const struct nand_controller_ops *ops;
 };
 
-static inline void nand_hw_control_init(struct nand_hw_control *nfc)
+static inline void nand_controller_init(struct nand_controller *nfc)
 {
 	nfc->active = NULL;
 	spin_lock_init(&nfc->lock);
@@ -778,11 +806,15 @@ nand_get_sdr_timings(const struct nand_data_interface *conf)
  *	  implementation) if any.
  * @cleanup: the ->init() function may have allocated resources, ->cleanup()
  *	     is here to let vendor specific code release those resources.
+ * @fixup_onfi_param_page: apply vendor specific fixups to the ONFI parameter
+ *			   page. This is called after the checksum is verified.
  */
 struct nand_manufacturer_ops {
 	void (*detect)(struct nand_chip *chip);
 	int (*init)(struct nand_chip *chip);
 	void (*cleanup)(struct nand_chip *chip);
+	void (*fixup_onfi_param_page)(struct nand_chip *chip,
+				      struct nand_onfi_params *p);
 };
 
 /**
@@ -986,14 +1018,14 @@ struct nand_subop {
 	unsigned int last_instr_end_off;
 };
 
-int nand_subop_get_addr_start_off(const struct nand_subop *subop,
-				  unsigned int op_id);
-int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
-				unsigned int op_id);
-int nand_subop_get_data_start_off(const struct nand_subop *subop,
-				  unsigned int op_id);
-int nand_subop_get_data_len(const struct nand_subop *subop,
-			    unsigned int op_id);
+unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop,
+					   unsigned int op_id);
+unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
+					 unsigned int op_id);
+unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop,
+					   unsigned int op_id);
+unsigned int nand_subop_get_data_len(const struct nand_subop *subop,
+				     unsigned int op_id);
 
 /**
  * struct nand_op_parser_addr_constraints - Constraints for address instructions
@@ -1176,9 +1208,9 @@ int nand_op_parser_exec_op(struct nand_chip *chip,
  *			setting the read-retry mode. Mostly needed for MLC NAND.
  * @ecc:		[BOARDSPECIFIC] ECC control structure
  * @buf_align:		minimum buffer alignment required by a platform
- * @hwcontrol:		platform-specific hardware control structure
+ * @dummy_controller:	dummy controller implementation for drivers that can
+ *			only control a single chip
  * @erase:		[REPLACEABLE] erase function
- * @scan_bbt:		[REPLACEABLE] function to scan bad block table
  * @chip_delay:		[BOARDSPECIFIC] chip dependent delay for transferring
  *			data from array to read regs (tR).
  * @state:		[INTERN] the current state of the NAND device
@@ -1271,7 +1303,6 @@ struct nand_chip {
 		       const struct nand_operation *op,
 		       bool check_only);
 	int (*erase)(struct mtd_info *mtd, int page);
-	int (*scan_bbt)(struct mtd_info *mtd);
 	int (*set_features)(struct mtd_info *mtd, struct nand_chip *chip,
 			    int feature_addr, uint8_t *subfeature_para);
 	int (*get_features)(struct mtd_info *mtd, struct nand_chip *chip,
@@ -1314,11 +1345,11 @@ struct nand_chip {
 	flstate_t state;
 
 	uint8_t *oob_poi;
-	struct nand_hw_control *controller;
+	struct nand_controller *controller;
 
 	struct nand_ecc_ctrl ecc;
 	unsigned long buf_align;
-	struct nand_hw_control hwcontrol;
+	struct nand_controller dummy_controller;
 
 	uint8_t *bbt;
 	struct nand_bbt_descr *bbt_td;
@@ -1517,14 +1548,12 @@ extern const struct nand_manufacturer_ops micron_nand_manuf_ops;
 extern const struct nand_manufacturer_ops amd_nand_manuf_ops;
 extern const struct nand_manufacturer_ops macronix_nand_manuf_ops;
 
-int nand_default_bbt(struct mtd_info *mtd);
+int nand_create_bbt(struct nand_chip *chip);
 int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs);
 int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs);
 int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt);
 int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 		    int allowbbt);
-int nand_do_read(struct mtd_info *mtd, loff_t from, size_t len,
-		 size_t *retlen, uint8_t *buf);
 
 /**
  * struct platform_nand_chip - chip level device structure
@@ -1555,14 +1584,12 @@ struct platform_device;
  * struct platform_nand_ctrl - controller level device structure
  * @probe:		platform specific function to probe/setup hardware
  * @remove:		platform specific function to remove/teardown hardware
- * @hwcontrol:		platform specific hardware control structure
  * @dev_ready:		platform specific function to read ready/busy pin
  * @select_chip:	platform specific chip select function
  * @cmd_ctrl:		platform specific function for controlling
  *			ALE/CLE/nCE. Also used to write command and address
  * @write_buf:		platform specific function for write buffer
  * @read_buf:		platform specific function for read buffer
- * @read_byte:		platform specific function to read one byte from chip
  * @priv:		private data to transport driver specific settings
  *
  * All fields are optional and depend on the hardware driver requirements
@@ -1570,13 +1597,11 @@ struct platform_device;
 struct platform_nand_ctrl {
 	int (*probe)(struct platform_device *pdev);
 	void (*remove)(struct platform_device *pdev);
-	void (*hwcontrol)(struct mtd_info *mtd, int cmd);
 	int (*dev_ready)(struct mtd_info *mtd);
 	void (*select_chip)(struct mtd_info *mtd, int chip);
 	void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl);
 	void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len);
 	void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len);
-	unsigned char (*read_byte)(struct mtd_info *mtd);
 	void *priv;
 };
 
@@ -1593,10 +1618,10 @@ struct platform_nand_data {
 /* return the supported asynchronous timing mode. */
 static inline int onfi_get_async_timing_mode(struct nand_chip *chip)
 {
-	if (!chip->parameters.onfi.version)
+	if (!chip->parameters.onfi)
 		return ONFI_TIMING_MODE_UNKNOWN;
 
-	return chip->parameters.onfi.async_timing_mode;
+	return chip->parameters.onfi->async_timing_mode;
 }
 
 int onfi_fill_data_interface(struct nand_chip *chip,
@@ -1641,14 +1666,8 @@ int nand_check_erased_ecc_chunk(void *data, int datalen,
 				void *extraoob, int extraooblen,
 				int threshold);
 
-int nand_check_ecc_caps(struct nand_chip *chip,
-			const struct nand_ecc_caps *caps, int oobavail);
-
-int nand_match_ecc_req(struct nand_chip *chip,
-		       const struct nand_ecc_caps *caps,  int oobavail);
-
-int nand_maximize_ecc(struct nand_chip *chip,
-		      const struct nand_ecc_caps *caps, int oobavail);
+int nand_ecc_choose_conf(struct nand_chip *chip,
+			 const struct nand_ecc_caps *caps, int oobavail);
 
 /* Default write_oob implementation */
 int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page);
@@ -1674,10 +1693,14 @@ int nand_get_set_features_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
 /* Default read_page_raw implementation */
 int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 		       uint8_t *buf, int oob_required, int page);
+int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+			       u8 *buf, int oob_required, int page);
 
 /* Default write_page_raw implementation */
 int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 			const uint8_t *buf, int oob_required, int page);
+int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+				const u8 *buf, int oob_required, int page);
 
 /* Reset and initialize a NAND device */
 int nand_reset(struct nand_chip *chip, int chipnr);
@@ -1711,8 +1734,13 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len,
 int nand_write_data_op(struct nand_chip *chip, const void *buf,
 		       unsigned int len, bool force_8bit);
 
-/* Free resources held by the NAND device */
+/*
+ * Free resources held by the NAND device, must be called on error after a
+ * sucessful nand_scan().
+ */
 void nand_cleanup(struct nand_chip *chip);
+/* Unregister the MTD device and calls nand_cleanup() */
+void nand_release(struct mtd_info *mtd);
 
 /* Default extended ID decoding function */
 void nand_decode_ext_id(struct nand_chip *chip);
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index e60da0d34cc1..c922e97f205a 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -235,6 +235,7 @@ enum spi_nor_option_flags {
 	SNOR_F_S3AN_ADDR_DEFAULT = BIT(3),
 	SNOR_F_READY_XSR_RDY	= BIT(4),
 	SNOR_F_USE_CLSR		= BIT(5),
+	SNOR_F_BROKEN_RESET	= BIT(6),
 };
 
 /**
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
new file mode 100644
index 000000000000..088ff96c3eb6
--- /dev/null
+++ b/include/linux/mtd/spinand.h
@@ -0,0 +1,421 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2017 Micron Technology, Inc.
+ *
+ *  Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ */
+#ifndef __LINUX_MTD_SPINAND_H
+#define __LINUX_MTD_SPINAND_H
+
+#include <linux/mutex.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+/**
+ * Standard SPI NAND flash operations
+ */
+
+#define SPINAND_RESET_OP						\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xff, 1),				\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_WR_EN_DIS_OP(enable)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD((enable) ? 0x06 : 0x04, 1),		\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_READID_OP(ndummy, buf, len)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x9f, 1),				\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+
+#define SPINAND_SET_FEATURE_OP(reg, valptr)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x1f, 1),				\
+		   SPI_MEM_OP_ADDR(1, reg, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(1, valptr, 1))
+
+#define SPINAND_GET_FEATURE_OP(reg, valptr)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0f, 1),				\
+		   SPI_MEM_OP_ADDR(1, reg, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_IN(1, valptr, 1))
+
+#define SPINAND_BLK_ERASE_OP(addr)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xd8, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_PAGE_READ_OP(addr)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x13, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_PAGE_READ_FROM_CACHE_OP(fast, addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 2),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 4),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+
+#define SPINAND_PROG_EXEC_OP(addr)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_PROG_LOAD(reset, addr, buf, len)			\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x02 : 0x84, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(len, buf, 1))
+
+#define SPINAND_PROG_LOAD_X4(reset, addr, buf, len)			\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x32 : 0x34, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(len, buf, 4))
+
+/**
+ * Standard SPI NAND flash commands
+ */
+#define SPINAND_CMD_PROG_LOAD_X4		0x32
+#define SPINAND_CMD_PROG_LOAD_RDM_DATA_X4	0x34
+
+/* feature register */
+#define REG_BLOCK_LOCK		0xa0
+#define BL_ALL_UNLOCKED		0x00
+
+/* configuration register */
+#define REG_CFG			0xb0
+#define CFG_OTP_ENABLE		BIT(6)
+#define CFG_ECC_ENABLE		BIT(4)
+#define CFG_QUAD_ENABLE		BIT(0)
+
+/* status register */
+#define REG_STATUS		0xc0
+#define STATUS_BUSY		BIT(0)
+#define STATUS_ERASE_FAILED	BIT(2)
+#define STATUS_PROG_FAILED	BIT(3)
+#define STATUS_ECC_MASK		GENMASK(5, 4)
+#define STATUS_ECC_NO_BITFLIPS	(0 << 4)
+#define STATUS_ECC_HAS_BITFLIPS	(1 << 4)
+#define STATUS_ECC_UNCOR_ERROR	(2 << 4)
+
+struct spinand_op;
+struct spinand_device;
+
+#define SPINAND_MAX_ID_LEN	4
+
+/**
+ * struct spinand_id - SPI NAND id structure
+ * @data: buffer containing the id bytes. Currently 4 bytes large, but can
+ *	  be extended if required
+ * @len: ID length
+ *
+ * struct_spinand_id->data contains all bytes returned after a READ_ID command,
+ * including dummy bytes if the chip does not emit ID bytes right after the
+ * READ_ID command. The responsibility to extract real ID bytes is left to
+ * struct_manufacurer_ops->detect().
+ */
+struct spinand_id {
+	u8 data[SPINAND_MAX_ID_LEN];
+	int len;
+};
+
+/**
+ * struct manufacurer_ops - SPI NAND manufacturer specific operations
+ * @detect: detect a SPI NAND device. Every time a SPI NAND device is probed
+ *	    the core calls the struct_manufacurer_ops->detect() hook of each
+ *	    registered manufacturer until one of them return 1. Note that
+ *	    the first thing to check in this hook is that the manufacturer ID
+ *	    in struct_spinand_device->id matches the manufacturer whose
+ *	    ->detect() hook has been called. Should return 1 if there's a
+ *	    match, 0 if the manufacturer ID does not match and a negative
+ *	    error code otherwise. When true is returned, the core assumes
+ *	    that properties of the NAND chip (spinand->base.memorg and
+ *	    spinand->base.eccreq) have been filled
+ * @init: initialize a SPI NAND device
+ * @cleanup: cleanup a SPI NAND device
+ *
+ * Each SPI NAND manufacturer driver should implement this interface so that
+ * NAND chips coming from this vendor can be detected and initialized properly.
+ */
+struct spinand_manufacturer_ops {
+	int (*detect)(struct spinand_device *spinand);
+	int (*init)(struct spinand_device *spinand);
+	void (*cleanup)(struct spinand_device *spinand);
+};
+
+/**
+ * struct spinand_manufacturer - SPI NAND manufacturer instance
+ * @id: manufacturer ID
+ * @name: manufacturer name
+ * @ops: manufacturer operations
+ */
+struct spinand_manufacturer {
+	u8 id;
+	char *name;
+	const struct spinand_manufacturer_ops *ops;
+};
+
+/* SPI NAND manufacturers */
+extern const struct spinand_manufacturer macronix_spinand_manufacturer;
+extern const struct spinand_manufacturer micron_spinand_manufacturer;
+extern const struct spinand_manufacturer winbond_spinand_manufacturer;
+
+/**
+ * struct spinand_op_variants - SPI NAND operation variants
+ * @ops: the list of variants for a given operation
+ * @nops: the number of variants
+ *
+ * Some operations like read-from-cache/write-to-cache have several variants
+ * depending on the number of IO lines you use to transfer data or address
+ * cycles. This structure is a way to describe the different variants supported
+ * by a chip and let the core pick the best one based on the SPI mem controller
+ * capabilities.
+ */
+struct spinand_op_variants {
+	const struct spi_mem_op *ops;
+	unsigned int nops;
+};
+
+#define SPINAND_OP_VARIANTS(name, ...)					\
+	const struct spinand_op_variants name = {			\
+		.ops = (struct spi_mem_op[]) { __VA_ARGS__ },		\
+		.nops = sizeof((struct spi_mem_op[]){ __VA_ARGS__ }) /	\
+			sizeof(struct spi_mem_op),			\
+	}
+
+/**
+ * spinand_ecc_info - description of the on-die ECC implemented by a SPI NAND
+ *		      chip
+ * @get_status: get the ECC status. Should return a positive number encoding
+ *		the number of corrected bitflips if correction was possible or
+ *		-EBADMSG if there are uncorrectable errors. I can also return
+ *		other negative error codes if the error is not caused by
+ *		uncorrectable bitflips
+ * @ooblayout: the OOB layout used by the on-die ECC implementation
+ */
+struct spinand_ecc_info {
+	int (*get_status)(struct spinand_device *spinand, u8 status);
+	const struct mtd_ooblayout_ops *ooblayout;
+};
+
+#define SPINAND_HAS_QE_BIT		BIT(0)
+
+/**
+ * struct spinand_info - Structure used to describe SPI NAND chips
+ * @model: model name
+ * @devid: device ID
+ * @flags: OR-ing of the SPINAND_XXX flags
+ * @memorg: memory organization
+ * @eccreq: ECC requirements
+ * @eccinfo: on-die ECC info
+ * @op_variants: operations variants
+ * @op_variants.read_cache: variants of the read-cache operation
+ * @op_variants.write_cache: variants of the write-cache operation
+ * @op_variants.update_cache: variants of the update-cache operation
+ * @select_target: function used to select a target/die. Required only for
+ *		   multi-die chips
+ *
+ * Each SPI NAND manufacturer driver should have a spinand_info table
+ * describing all the chips supported by the driver.
+ */
+struct spinand_info {
+	const char *model;
+	u8 devid;
+	u32 flags;
+	struct nand_memory_organization memorg;
+	struct nand_ecc_req eccreq;
+	struct spinand_ecc_info eccinfo;
+	struct {
+		const struct spinand_op_variants *read_cache;
+		const struct spinand_op_variants *write_cache;
+		const struct spinand_op_variants *update_cache;
+	} op_variants;
+	int (*select_target)(struct spinand_device *spinand,
+			     unsigned int target);
+};
+
+#define SPINAND_INFO_OP_VARIANTS(__read, __write, __update)		\
+	{								\
+		.read_cache = __read,					\
+		.write_cache = __write,					\
+		.update_cache = __update,				\
+	}
+
+#define SPINAND_ECCINFO(__ooblayout, __get_status)			\
+	.eccinfo = {							\
+		.ooblayout = __ooblayout,				\
+		.get_status = __get_status,				\
+	}
+
+#define SPINAND_SELECT_TARGET(__func)					\
+	.select_target = __func,
+
+#define SPINAND_INFO(__model, __id, __memorg, __eccreq, __op_variants,	\
+		     __flags, ...)					\
+	{								\
+		.model = __model,					\
+		.devid = __id,						\
+		.memorg = __memorg,					\
+		.eccreq = __eccreq,					\
+		.op_variants = __op_variants,				\
+		.flags = __flags,					\
+		__VA_ARGS__						\
+	}
+
+/**
+ * struct spinand_device - SPI NAND device instance
+ * @base: NAND device instance
+ * @spimem: pointer to the SPI mem object
+ * @lock: lock used to serialize accesses to the NAND
+ * @id: NAND ID as returned by READ_ID
+ * @flags: NAND flags
+ * @op_templates: various SPI mem op templates
+ * @op_templates.read_cache: read cache op template
+ * @op_templates.write_cache: write cache op template
+ * @op_templates.update_cache: update cache op template
+ * @select_target: select a specific target/die. Usually called before sending
+ *		   a command addressing a page or an eraseblock embedded in
+ *		   this die. Only required if your chip exposes several dies
+ * @cur_target: currently selected target/die
+ * @eccinfo: on-die ECC information
+ * @cfg_cache: config register cache. One entry per die
+ * @databuf: bounce buffer for data
+ * @oobbuf: bounce buffer for OOB data
+ * @scratchbuf: buffer used for everything but page accesses. This is needed
+ *		because the spi-mem interface explicitly requests that buffers
+ *		passed in spi_mem_op be DMA-able, so we can't based the bufs on
+ *		the stack
+ * @manufacturer: SPI NAND manufacturer information
+ * @priv: manufacturer private data
+ */
+struct spinand_device {
+	struct nand_device base;
+	struct spi_mem *spimem;
+	struct mutex lock;
+	struct spinand_id id;
+	u32 flags;
+
+	struct {
+		const struct spi_mem_op *read_cache;
+		const struct spi_mem_op *write_cache;
+		const struct spi_mem_op *update_cache;
+	} op_templates;
+
+	int (*select_target)(struct spinand_device *spinand,
+			     unsigned int target);
+	unsigned int cur_target;
+
+	struct spinand_ecc_info eccinfo;
+
+	u8 *cfg_cache;
+	u8 *databuf;
+	u8 *oobbuf;
+	u8 *scratchbuf;
+	const struct spinand_manufacturer *manufacturer;
+	void *priv;
+};
+
+/**
+ * mtd_to_spinand() - Get the SPI NAND device attached to an MTD instance
+ * @mtd: MTD instance
+ *
+ * Return: the SPI NAND device attached to @mtd.
+ */
+static inline struct spinand_device *mtd_to_spinand(struct mtd_info *mtd)
+{
+	return container_of(mtd_to_nanddev(mtd), struct spinand_device, base);
+}
+
+/**
+ * spinand_to_mtd() - Get the MTD device embedded in a SPI NAND device
+ * @spinand: SPI NAND device
+ *
+ * Return: the MTD device embedded in @spinand.
+ */
+static inline struct mtd_info *spinand_to_mtd(struct spinand_device *spinand)
+{
+	return nanddev_to_mtd(&spinand->base);
+}
+
+/**
+ * nand_to_spinand() - Get the SPI NAND device embedding an NAND object
+ * @nand: NAND object
+ *
+ * Return: the SPI NAND device embedding @nand.
+ */
+static inline struct spinand_device *nand_to_spinand(struct nand_device *nand)
+{
+	return container_of(nand, struct spinand_device, base);
+}
+
+/**
+ * spinand_to_nand() - Get the NAND device embedded in a SPI NAND object
+ * @spinand: SPI NAND device
+ *
+ * Return: the NAND device embedded in @spinand.
+ */
+static inline struct nand_device *
+spinand_to_nand(struct spinand_device *spinand)
+{
+	return &spinand->base;
+}
+
+/**
+ * spinand_set_of_node - Attach a DT node to a SPI NAND device
+ * @spinand: SPI NAND device
+ * @np: DT node
+ *
+ * Attach a DT node to a SPI NAND device.
+ */
+static inline void spinand_set_of_node(struct spinand_device *spinand,
+				       struct device_node *np)
+{
+	nanddev_set_of_node(&spinand->base, np);
+}
+
+int spinand_match_and_init(struct spinand_device *dev,
+			   const struct spinand_info *table,
+			   unsigned int table_size, u8 devid);
+
+int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val);
+int spinand_select_target(struct spinand_device *spinand, unsigned int target);
+
+#endif /* __LINUX_MTD_SPINAND_H */
diff --git a/include/linux/net.h b/include/linux/net.h
index 08b6eb964dd6..6554d3ba4396 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -147,7 +147,6 @@ struct proto_ops {
 	int		(*getname)   (struct socket *sock,
 				      struct sockaddr *addr,
 				      int peer);
-	__poll_t	(*poll_mask) (struct socket *sock, __poll_t events);
 	__poll_t	(*poll)	     (struct file *file, struct socket *sock,
 				      struct poll_table_struct *wait);
 	int		(*ioctl)     (struct socket *sock, unsigned int cmd,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3ec9850c7936..3d0cc0b5cec2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2789,11 +2789,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp,
 	if (PTR_ERR(pp) != -EINPROGRESS)
 		NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	if (PTR_ERR(pp) != -EINPROGRESS) {
+		NAPI_GRO_CB(skb)->flush |= flush;
+		skb_gro_remcsum_cleanup(skb, grc);
+		skb->remcsum_offload = 0;
+	}
+}
 #else
 static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
 {
 	NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_remcsum_cleanup(skb, grc);
+	skb->remcsum_offload = 0;
+}
 #endif
 
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index b8d868d23e79..08f9247e9827 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -45,12 +45,18 @@ extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern unsigned int  softlockup_panic;
-#else
+
+extern int lockup_detector_online_cpu(unsigned int cpu);
+extern int lockup_detector_offline_cpu(unsigned int cpu);
+#else /* CONFIG_SOFTLOCKUP_DETECTOR */
 static inline void touch_softlockup_watchdog_sched(void) { }
 static inline void touch_softlockup_watchdog(void) { }
 static inline void touch_softlockup_watchdog_sync(void) { }
 static inline void touch_all_softlockup_watchdogs(void) { }
-#endif
+
+#define lockup_detector_online_cpu	NULL
+#define lockup_detector_offline_cpu	NULL
+#endif /* CONFIG_SOFTLOCKUP_DETECTOR */
 
 #ifdef CONFIG_DETECT_HUNG_TASK
 void reset_hung_task_detector(void);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 2950ce957656..68e91ef5494c 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -242,7 +242,12 @@ struct nvme_id_ctrl {
 	__le32			sanicap;
 	__le32			hmminds;
 	__le16			hmmaxd;
-	__u8			rsvd338[174];
+	__u8			rsvd338[4];
+	__u8			anatt;
+	__u8			anacap;
+	__le32			anagrpmax;
+	__le32			nanagrpid;
+	__u8			rsvd352[160];
 	__u8			sqes;
 	__u8			cqes;
 	__le16			maxcmd;
@@ -254,11 +259,12 @@ struct nvme_id_ctrl {
 	__le16			awun;
 	__le16			awupf;
 	__u8			nvscc;
-	__u8			rsvd531;
+	__u8			nwpc;
 	__le16			acwu;
 	__u8			rsvd534[2];
 	__le32			sgls;
-	__u8			rsvd540[228];
+	__le32			mnan;
+	__u8			rsvd544[224];
 	char			subnqn[256];
 	__u8			rsvd1024[768];
 	__le32			ioccsz;
@@ -312,7 +318,11 @@ struct nvme_id_ns {
 	__le16			nabspf;
 	__le16			noiob;
 	__u8			nvmcap[16];
-	__u8			rsvd64[40];
+	__u8			rsvd64[28];
+	__le32			anagrpid;
+	__u8			rsvd96[3];
+	__u8			nsattr;
+	__u8			rsvd100[4];
 	__u8			nguid[16];
 	__u8			eui64[8];
 	struct nvme_lbaf	lbaf[16];
@@ -425,6 +435,32 @@ struct nvme_effects_log {
 	__u8   resv[2048];
 };
 
+enum nvme_ana_state {
+	NVME_ANA_OPTIMIZED		= 0x01,
+	NVME_ANA_NONOPTIMIZED		= 0x02,
+	NVME_ANA_INACCESSIBLE		= 0x03,
+	NVME_ANA_PERSISTENT_LOSS	= 0x04,
+	NVME_ANA_CHANGE			= 0x0f,
+};
+
+struct nvme_ana_group_desc {
+	__le32	grpid;
+	__le32	nnsids;
+	__le64	chgcnt;
+	__u8	state;
+	__u8	rsvd17[15];
+	__le32	nsids[];
+};
+
+/* flag for the log specific field of the ANA log */
+#define NVME_ANA_LOG_RGO	(1 << 0)
+
+struct nvme_ana_rsp_hdr {
+	__le64	chgcnt;
+	__le16	ngrps;
+	__le16	rsvd10[3];
+};
+
 enum {
 	NVME_SMART_CRIT_SPARE		= 1 << 0,
 	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
@@ -444,11 +480,13 @@ enum {
 enum {
 	NVME_AER_NOTICE_NS_CHANGED	= 0x00,
 	NVME_AER_NOTICE_FW_ACT_STARTING = 0x01,
+	NVME_AER_NOTICE_ANA		= 0x03,
 };
 
 enum {
 	NVME_AEN_CFG_NS_ATTR		= 1 << 8,
 	NVME_AEN_CFG_FW_ACT		= 1 << 9,
+	NVME_AEN_CFG_ANA_CHANGE		= 1 << 11,
 };
 
 struct nvme_lba_range_type {
@@ -749,15 +787,22 @@ enum {
 	NVME_FEAT_HOST_MEM_BUF	= 0x0d,
 	NVME_FEAT_TIMESTAMP	= 0x0e,
 	NVME_FEAT_KATO		= 0x0f,
+	NVME_FEAT_HCTM		= 0x10,
+	NVME_FEAT_NOPSC		= 0x11,
+	NVME_FEAT_RRL		= 0x12,
+	NVME_FEAT_PLM_CONFIG	= 0x13,
+	NVME_FEAT_PLM_WINDOW	= 0x14,
 	NVME_FEAT_SW_PROGRESS	= 0x80,
 	NVME_FEAT_HOST_ID	= 0x81,
 	NVME_FEAT_RESV_MASK	= 0x82,
 	NVME_FEAT_RESV_PERSIST	= 0x83,
+	NVME_FEAT_WRITE_PROTECT	= 0x84,
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
 	NVME_LOG_CHANGED_NS	= 0x04,
 	NVME_LOG_CMD_EFFECTS	= 0x05,
+	NVME_LOG_ANA		= 0x0c,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
@@ -765,6 +810,14 @@ enum {
 	NVME_FWACT_ACTV		= (2 << 3),
 };
 
+/* NVMe Namespace Write Protect State */
+enum {
+	NVME_NS_NO_WRITE_PROTECT = 0,
+	NVME_NS_WRITE_PROTECT,
+	NVME_NS_WRITE_PROTECT_POWER_CYCLE,
+	NVME_NS_WRITE_PROTECT_PERMANENT,
+};
+
 #define NVME_MAX_CHANGED_NAMESPACES	1024
 
 struct nvme_identify {
@@ -880,7 +933,7 @@ struct nvme_get_log_page_command {
 	__u64			rsvd2[2];
 	union nvme_data_ptr	dptr;
 	__u8			lid;
-	__u8			rsvd10;
+	__u8			lsp; /* upper 4 bits reserved */
 	__le16			numdl;
 	__le16			numdu;
 	__u16			rsvd11;
@@ -1111,6 +1164,8 @@ enum {
 	NVME_SC_SGL_INVALID_OFFSET	= 0x16,
 	NVME_SC_SGL_INVALID_SUBTYPE	= 0x17,
 
+	NVME_SC_NS_WRITE_PROTECTED	= 0x20,
+
 	NVME_SC_LBA_RANGE		= 0x80,
 	NVME_SC_CAP_EXCEEDED		= 0x81,
 	NVME_SC_NS_NOT_READY		= 0x82,
@@ -1180,6 +1235,13 @@ enum {
 	NVME_SC_ACCESS_DENIED		= 0x286,
 	NVME_SC_UNWRITTEN_BLOCK		= 0x287,
 
+	/*
+	 * Path-related Errors:
+	 */
+	NVME_SC_ANA_PERSISTENT_LOSS	= 0x301,
+	NVME_SC_ANA_INACCESSIBLE	= 0x302,
+	NVME_SC_ANA_TRANSITION		= 0x303,
+
 	NVME_SC_DNR			= 0x4000,
 };
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 340029b2fb38..c133ccfa002e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -368,7 +368,6 @@ struct pci_dev {
 	unsigned int	transparent:1;		/* Subtractive decode bridge */
 	unsigned int	multifunction:1;	/* Multi-function device */
 
-	unsigned int	is_added:1;
 	unsigned int	is_busmaster:1;		/* Is busmaster */
 	unsigned int	no_msi:1;		/* May not use MSI */
 	unsigned int	no_64bit_msi:1; 	/* May only use 32-bit MSIs */
@@ -1240,6 +1239,8 @@ int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr,
 unsigned long pci_address_to_pio(phys_addr_t addr);
 phys_addr_t pci_pio_to_address(unsigned long pio);
 int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
+int devm_pci_remap_iospace(struct device *dev, const struct resource *res,
+			   phys_addr_t phys_addr);
 void pci_unmap_iospace(struct resource *res);
 void __iomem *devm_pci_remap_cfgspace(struct device *dev,
 				      resource_size_t offset,
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index ad5444491975..10f92e1d8e7b 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -25,6 +25,12 @@
  */
 #define ARMPMU_MAX_HWEVENTS		32
 
+/*
+ * ARM PMU hw_event flags
+ */
+/* Event uses a 64bit counter */
+#define ARMPMU_EVT_64BIT		1
+
 #define HW_OP_UNSUPPORTED		0xFFFF
 #define C(_x)				PERF_COUNT_HW_CACHE_##_x
 #define CACHE_OP_UNSUPPORTED		0xFFFF
@@ -87,14 +93,13 @@ struct arm_pmu {
 					 struct perf_event *event);
 	int		(*set_event_filter)(struct hw_perf_event *evt,
 					    struct perf_event_attr *attr);
-	u32		(*read_counter)(struct perf_event *event);
-	void		(*write_counter)(struct perf_event *event, u32 val);
+	u64		(*read_counter)(struct perf_event *event);
+	void		(*write_counter)(struct perf_event *event, u64 val);
 	void		(*start)(struct arm_pmu *);
 	void		(*stop)(struct arm_pmu *);
 	void		(*reset)(void *);
 	int		(*map_event)(struct perf_event *event);
 	int		num_events;
-	u64		max_period;
 	bool		secure_access; /* 32-bit ARM only */
 #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40
 	DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1fa12887ec02..53c500f0ca79 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -490,7 +490,7 @@ struct perf_addr_filters_head {
 };
 
 /**
- * enum perf_event_state - the states of a event
+ * enum perf_event_state - the states of an event:
  */
 enum perf_event_state {
 	PERF_EVENT_STATE_DEAD		= -4,
@@ -1130,6 +1130,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct
 extern struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark);
+extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
 
diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h
index 09eb80f2574a..8dd85d302b90 100644
--- a/include/linux/pinctrl/pinconf.h
+++ b/include/linux/pinctrl/pinconf.h
@@ -28,7 +28,8 @@ struct seq_file;
  *	is not available on this controller this should return -ENOTSUPP
  *	and if it is available but disabled it should return -EINVAL
  * @pin_config_set: configure an individual pin
- * @pin_config_group_get: get configurations for an entire pin group
+ * @pin_config_group_get: get configurations for an entire pin group; should
+ *	return -ENOTSUPP and -EINVAL using the same rules as pin_config_get.
  * @pin_config_group_set: configure all pins in a group
  * @pin_config_dbg_parse_modify: optional debugfs to modify a pin configuration
  * @pin_config_dbg_show: optional debugfs display hook that will provide
diff --git a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h b/include/linux/platform_data/jz4740/jz4740_nand.h
index f381d465e768..bc571f6d5ced 100644
--- a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
+++ b/include/linux/platform_data/jz4740/jz4740_nand.h
@@ -13,8 +13,8 @@
  *
  */
 
-#ifndef __ASM_MACH_JZ4740_JZ4740_NAND_H__
-#define __ASM_MACH_JZ4740_JZ4740_NAND_H__
+#ifndef __JZ4740_NAND_H__
+#define __JZ4740_NAND_H__
 
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
diff --git a/include/linux/platform_data/mmp_dma.h b/include/linux/platform_data/mmp_dma.h
index d1397c8ed94e..6397b9c8149a 100644
--- a/include/linux/platform_data/mmp_dma.h
+++ b/include/linux/platform_data/mmp_dma.h
@@ -12,9 +12,13 @@
 #ifndef MMP_DMA_H
 #define MMP_DMA_H
 
+struct dma_slave_map;
+
 struct mmp_dma_platdata {
 	int dma_channels;
 	int nb_requestors;
+	int slave_map_cnt;
+	const struct dma_slave_map *slave_map;
 };
 
 #endif /* MMP_DMA_H */
diff --git a/include/linux/platform_data/mtd-orion_nand.h b/include/linux/platform_data/mtd-orion_nand.h
index a7ce77c7c1a8..34828eb85982 100644
--- a/include/linux/platform_data/mtd-orion_nand.h
+++ b/include/linux/platform_data/mtd-orion_nand.h
@@ -12,7 +12,6 @@
  */
 struct orion_nand_data {
 	struct mtd_partition *parts;
-	int (*dev_ready)(struct mtd_info *mtd);
 	u32 nr_parts;
 	u8 ale;		/* address line number connected to ALE */
 	u8 cle;		/* address line number connected to CLE */
diff --git a/arch/mips/include/asm/txx9/ndfmc.h b/include/linux/platform_data/txx9/ndfmc.h
index fa67f3df78fc..fc172627d54e 100644
--- a/arch/mips/include/asm/txx9/ndfmc.h
+++ b/include/linux/platform_data/txx9/ndfmc.h
@@ -5,8 +5,8 @@
  *
  * (C) Copyright TOSHIBA CORPORATION 2007
  */
-#ifndef __ASM_TXX9_NDFMC_H
-#define __ASM_TXX9_NDFMC_H
+#ifndef __TXX9_NDFMC_H
+#define __TXX9_NDFMC_H
 
 #define NDFMC_PLAT_FLAG_USE_BSPRT	0x01
 #define NDFMC_PLAT_FLAG_NO_RSTR		0x02
@@ -27,4 +27,4 @@ struct txx9ndfmc_platform_data {
 void txx9_ndfmc_init(unsigned long baseaddr,
 		     const struct txx9ndfmc_platform_data *plat_data);
 
-#endif /* __ASM_TXX9_NDFMC_H */
+#endif /* __TXX9_NDFMC_H */
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 9206a4fef9ac..776c546d581a 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -234,11 +234,13 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np);
 int of_genpd_parse_idle_states(struct device_node *dn,
 			       struct genpd_power_state **states, int *n);
 unsigned int of_genpd_opp_to_performance_state(struct device *dev,
-				struct device_node *opp_node);
+				struct device_node *np);
 
 int genpd_dev_pm_attach(struct device *dev);
 struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 					 unsigned int index);
+struct device *genpd_dev_pm_attach_by_name(struct device *dev,
+					   char *name);
 #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
 static inline int of_genpd_add_provider_simple(struct device_node *np,
 					struct generic_pm_domain *genpd)
@@ -274,9 +276,9 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn,
 
 static inline unsigned int
 of_genpd_opp_to_performance_state(struct device *dev,
-				  struct device_node *opp_node)
+				  struct device_node *np)
 {
-	return -ENODEV;
+	return 0;
 }
 
 static inline int genpd_dev_pm_attach(struct device *dev)
@@ -290,6 +292,12 @@ static inline struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 	return NULL;
 }
 
+static inline struct device *genpd_dev_pm_attach_by_name(struct device *dev,
+							 char *name)
+{
+	return NULL;
+}
+
 static inline
 struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
 {
@@ -301,6 +309,8 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
 int dev_pm_domain_attach(struct device *dev, bool power_on);
 struct device *dev_pm_domain_attach_by_id(struct device *dev,
 					  unsigned int index);
+struct device *dev_pm_domain_attach_by_name(struct device *dev,
+					    char *name);
 void dev_pm_domain_detach(struct device *dev, bool power_off);
 void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd);
 #else
@@ -313,6 +323,11 @@ static inline struct device *dev_pm_domain_attach_by_id(struct device *dev,
 {
 	return NULL;
 }
+static inline struct device *dev_pm_domain_attach_by_name(struct device *dev,
+							  char *name)
+{
+	return NULL;
+}
 static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
 static inline void dev_pm_domain_set(struct device *dev,
 				     struct dev_pm_domain *pd) {}
diff --git a/include/linux/poll.h b/include/linux/poll.h
index fdf86b4cbc71..7e0fdcf905d2 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -74,18 +74,18 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
 	pt->_key   = ~(__poll_t)0; /* all events enabled */
 }
 
-static inline bool file_has_poll_mask(struct file *file)
+static inline bool file_can_poll(struct file *file)
 {
-	return file->f_op->get_poll_head && file->f_op->poll_mask;
+	return file->f_op->poll;
 }
 
-static inline bool file_can_poll(struct file *file)
+static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
 {
-	return file->f_op->poll || file_has_poll_mask(file);
+	if (unlikely(!file->f_op->poll))
+		return DEFAULT_POLLMASK;
+	return file->f_op->poll(file, pt);
 }
 
-__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
-
 struct poll_table_entry {
 	struct file *filp;
 	__poll_t key;
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index c85704fcdbd2..ee7e987ea1b4 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -95,8 +95,8 @@ struct k_itimer {
 	clockid_t		it_clock;
 	timer_t			it_id;
 	int			it_active;
-	int			it_overrun;
-	int			it_overrun_last;
+	s64			it_overrun;
+	s64			it_overrun_last;
 	int			it_requeue_pending;
 	int			it_sigev_notify;
 	ktime_t			it_interval;
diff --git a/include/linux/pti.h b/include/linux/pti.h
index 0174883a935a..1a941efcaa62 100644
--- a/include/linux/pti.h
+++ b/include/linux/pti.h
@@ -6,6 +6,7 @@
 #include <asm/pti.h>
 #else
 static inline void pti_init(void) { }
+static inline void pti_finalize(void) { }
 #endif
 
 #endif
diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 8461b18e4608..13b4244d44c1 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -171,6 +171,14 @@
 #define SSACD_SCDB		(1 << 3)	/* SSPSYSCLK Divider Bypass */
 #define SSACD_ACPS(x)		((x) << 4)	/* Audio clock PLL select */
 #define SSACD_ACDS(x)		((x) << 0)	/* Audio clock divider select */
+#define SSACD_ACDS_1		(0)
+#define SSACD_ACDS_2		(1)
+#define SSACD_ACDS_4		(2)
+#define SSACD_ACDS_8		(3)
+#define SSACD_ACDS_16		(4)
+#define SSACD_ACDS_32		(5)
+#define SSACD_SCDB_4X		(0)
+#define SSACD_SCDB_1X		(1)
 #define SSACD_SCDX8		(1 << 7)	/* SYSCLK division ratio select */
 
 /* LPSS SSP */
@@ -212,8 +220,6 @@ struct ssp_device {
 	int		type;
 	int		use_count;
 	int		irq;
-	int		drcmr_rx;
-	int		drcmr_tx;
 
 	struct device_node	*of_node;
 };
diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index b401b962afff..5d65521260b3 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -87,6 +87,10 @@ static inline int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr,
 static inline int
 qcom_scm_pas_auth_and_reset(u32 peripheral) { return -ENODEV; }
 static inline int qcom_scm_pas_shutdown(u32 peripheral) { return -ENODEV; }
+static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
+				      unsigned int *src,
+				      struct qcom_scm_vmperm *newvm,
+				      int dest_cnt) { return -ENODEV; }
 static inline void qcom_scm_cpu_power_down(u32 flags) {}
 static inline u32 qcom_scm_get_version(void) { return 0; }
 static inline u32
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 36df6ccbc874..4786c2235b98 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -396,7 +396,16 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * @member:	the name of the list_head within the struct.
  *
  * Continue to iterate over list of given type, continuing after
- * the current position.
+ * the current position which must have been in the list when the RCU read
+ * lock was taken.
+ * This would typically require either that you obtained the node from a
+ * previous walk of the list in the same RCU read-side critical section, or
+ * that you held some sort of non-RCU reference (such as a reference count)
+ * to keep the node alive *and* in the list.
+ *
+ * This iterator is similar to list_for_each_entry_from_rcu() except
+ * this starts after the given position and that one starts at the given
+ * position.
  */
 #define list_for_each_entry_continue_rcu(pos, head, member) 		\
 	for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \
@@ -411,6 +420,14 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  *
  * Iterate over the tail of a list starting from a given position,
  * which must have been in the list when the RCU read lock was taken.
+ * This would typically require either that you obtained the node from a
+ * previous walk of the list in the same RCU read-side critical section, or
+ * that you held some sort of non-RCU reference (such as a reference count)
+ * to keep the node alive *and* in the list.
+ *
+ * This iterator is similar to list_for_each_entry_continue_rcu() except
+ * this starts from the given position and that one starts from the position
+ * after the given position.
  */
 #define list_for_each_entry_from_rcu(pos, head, member)			\
 	for (; &(pos)->member != (head);					\
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 65163aa0bb04..75e5b393cf44 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -64,7 +64,6 @@ void rcu_barrier_tasks(void);
 
 void __rcu_read_lock(void);
 void __rcu_read_unlock(void);
-void rcu_read_unlock_special(struct task_struct *t);
 void synchronize_rcu(void);
 
 /*
@@ -159,11 +158,11 @@ static inline void rcu_init_nohz(void) { }
 	} while (0)
 
 /*
- * Note a voluntary context switch for RCU-tasks benefit.  This is a
- * macro rather than an inline function to avoid #include hell.
+ * Note a quasi-voluntary context switch for RCU-tasks's benefit.
+ * This is a macro rather than an inline function to avoid #include hell.
  */
 #ifdef CONFIG_TASKS_RCU
-#define rcu_note_voluntary_context_switch_lite(t) \
+#define rcu_tasks_qs(t) \
 	do { \
 		if (READ_ONCE((t)->rcu_tasks_holdout)) \
 			WRITE_ONCE((t)->rcu_tasks_holdout, false); \
@@ -171,14 +170,14 @@ static inline void rcu_init_nohz(void) { }
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
 		rcu_all_qs(); \
-		rcu_note_voluntary_context_switch_lite(t); \
+		rcu_tasks_qs(t); \
 	} while (0)
 void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
 void synchronize_rcu_tasks(void);
 void exit_tasks_rcu_start(void);
 void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU */
-#define rcu_note_voluntary_context_switch_lite(t)	do { } while (0)
+#define rcu_tasks_qs(t)	do { } while (0)
 #define rcu_note_voluntary_context_switch(t)		rcu_all_qs()
 #define call_rcu_tasks call_rcu_sched
 #define synchronize_rcu_tasks synchronize_sched
@@ -195,8 +194,8 @@ static inline void exit_tasks_rcu_finish(void) { }
  */
 #define cond_resched_tasks_rcu_qs() \
 do { \
-	if (!cond_resched()) \
-		rcu_note_voluntary_context_switch_lite(current); \
+	rcu_tasks_qs(current); \
+	cond_resched(); \
 } while (0)
 
 /*
@@ -567,8 +566,8 @@ static inline void rcu_preempt_sleep_check(void) { }
  * This is simply an identity function, but it documents where a pointer
  * is handed off from RCU to some other synchronization mechanism, for
  * example, reference counting or locking.  In C11, it would map to
- * kill_dependency().  It could be used as follows:
- * ``
+ * kill_dependency().  It could be used as follows::
+ *
  *	rcu_read_lock();
  *	p = rcu_dereference(gp);
  *	long_lived = is_long_lived(p);
@@ -579,7 +578,6 @@ static inline void rcu_preempt_sleep_check(void) { }
  *			p = rcu_pointer_handoff(p);
  *	}
  *	rcu_read_unlock();
- *``
  */
 #define rcu_pointer_handoff(p) (p)
 
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 7b3c82e8a625..8d9a0ea8f0b5 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -93,7 +93,7 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 #define rcu_note_context_switch(preempt) \
 	do { \
 		rcu_sched_qs(); \
-		rcu_note_voluntary_context_switch_lite(current); \
+		rcu_tasks_qs(current); \
 	} while (0)
 
 static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index a685da2c4522..e28cce21bad6 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -3,9 +3,10 @@
 #define _LINUX_REFCOUNT_H
 
 #include <linux/atomic.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/spinlock_types.h>
+
+struct mutex;
 
 /**
  * struct refcount_t - variant of atomic_t specialized for reference counts
@@ -42,17 +43,30 @@ static inline unsigned int refcount_read(const refcount_t *r)
 	return atomic_read(&r->refs);
 }
 
+extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r);
+extern void refcount_add_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r);
+extern void refcount_inc_checked(refcount_t *r);
+
+extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_dec_and_test_checked(refcount_t *r);
+extern void refcount_dec_checked(refcount_t *r);
+
 #ifdef CONFIG_REFCOUNT_FULL
-extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r);
-extern void refcount_add(unsigned int i, refcount_t *r);
 
-extern __must_check bool refcount_inc_not_zero(refcount_t *r);
-extern void refcount_inc(refcount_t *r);
+#define refcount_add_not_zero	refcount_add_not_zero_checked
+#define refcount_add		refcount_add_checked
+
+#define refcount_inc_not_zero	refcount_inc_not_zero_checked
+#define refcount_inc		refcount_inc_checked
+
+#define refcount_sub_and_test	refcount_sub_and_test_checked
 
-extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r);
+#define refcount_dec_and_test	refcount_dec_and_test_checked
+#define refcount_dec		refcount_dec_checked
 
-extern __must_check bool refcount_dec_and_test(refcount_t *r);
-extern void refcount_dec(refcount_t *r);
 #else
 # ifdef CONFIG_ARCH_HAS_REFCOUNT
 #  include <asm/refcount.h>
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 4f38068ffb71..379505a53722 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -268,6 +268,13 @@ typedef void (*regmap_unlock)(void *);
  *                field is NULL but precious_table (see below) is not, the
  *                check is performed on such table (a register is precious if
  *                it belongs to one of the ranges specified by precious_table).
+ * @readable_noinc_reg: Optional callback returning true if the register
+ *			supports multiple read operations without incrementing
+ *			the register number. If this field is NULL but
+ *			rd_noinc_table (see below) is not, the check is
+ *			performed on such table (a register is no increment
+ *			readable if it belongs to one of the ranges specified
+ *			by rd_noinc_table).
  * @disable_locking: This regmap is either protected by external means or
  *                   is guaranteed not be be accessed from multiple threads.
  *                   Don't use any locking mechanisms.
@@ -295,6 +302,7 @@ typedef void (*regmap_unlock)(void *);
  * @rd_table:     As above, for read access.
  * @volatile_table: As above, for volatile registers.
  * @precious_table: As above, for precious registers.
+ * @rd_noinc_table: As above, for no increment readable registers.
  * @reg_defaults: Power on reset values for registers (for use with
  *                register cache support).
  * @num_reg_defaults: Number of elements in reg_defaults.
@@ -344,6 +352,7 @@ struct regmap_config {
 	bool (*readable_reg)(struct device *dev, unsigned int reg);
 	bool (*volatile_reg)(struct device *dev, unsigned int reg);
 	bool (*precious_reg)(struct device *dev, unsigned int reg);
+	bool (*readable_noinc_reg)(struct device *dev, unsigned int reg);
 
 	bool disable_locking;
 	regmap_lock lock;
@@ -360,6 +369,7 @@ struct regmap_config {
 	const struct regmap_access_table *rd_table;
 	const struct regmap_access_table *volatile_table;
 	const struct regmap_access_table *precious_table;
+	const struct regmap_access_table *rd_noinc_table;
 	const struct reg_default *reg_defaults;
 	unsigned int num_reg_defaults;
 	enum regcache_type cache_type;
@@ -514,6 +524,10 @@ struct regmap *__regmap_init_i2c(struct i2c_client *i2c,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
 				 const char *lock_name);
+struct regmap *__regmap_init_sccb(struct i2c_client *i2c,
+				  const struct regmap_config *config,
+				  struct lock_class_key *lock_key,
+				  const char *lock_name);
 struct regmap *__regmap_init_slimbus(struct slim_device *slimbus,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
@@ -558,6 +572,10 @@ struct regmap *__devm_regmap_init_i2c(struct i2c_client *i2c,
 				      const struct regmap_config *config,
 				      struct lock_class_key *lock_key,
 				      const char *lock_name);
+struct regmap *__devm_regmap_init_sccb(struct i2c_client *i2c,
+				       const struct regmap_config *config,
+				       struct lock_class_key *lock_key,
+				       const char *lock_name);
 struct regmap *__devm_regmap_init_spi(struct spi_device *dev,
 				      const struct regmap_config *config,
 				      struct lock_class_key *lock_key,
@@ -646,6 +664,19 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 				i2c, config)
 
 /**
+ * regmap_init_sccb() - Initialise register map
+ *
+ * @i2c: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer to
+ * a struct regmap.
+ */
+#define regmap_init_sccb(i2c, config)					\
+	__regmap_lockdep_wrapper(__regmap_init_sccb, #config,		\
+				i2c, config)
+
+/**
  * regmap_init_slimbus() - Initialise register map
  *
  * @slimbus: Device that will be interacted with
@@ -798,6 +829,20 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 				i2c, config)
 
 /**
+ * devm_regmap_init_sccb() - Initialise managed register map
+ *
+ * @i2c: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+#define devm_regmap_init_sccb(i2c, config)				\
+	__regmap_lockdep_wrapper(__devm_regmap_init_sccb, #config,	\
+				i2c, config)
+
+/**
  * devm_regmap_init_spi() - Initialise register map
  *
  * @dev: Device that will be interacted with
@@ -946,6 +991,8 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg,
 int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val);
 int regmap_raw_read(struct regmap *map, unsigned int reg,
 		    void *val, size_t val_len);
+int regmap_noinc_read(struct regmap *map, unsigned int reg,
+		      void *val, size_t val_len);
 int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val,
 		     size_t val_count);
 int regmap_update_bits_base(struct regmap *map, unsigned int reg,
@@ -1196,6 +1243,13 @@ static inline int regmap_raw_read(struct regmap *map, unsigned int reg,
 	return -EINVAL;
 }
 
+static inline int regmap_noinc_read(struct regmap *map, unsigned int reg,
+				    void *val, size_t val_len)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
 static inline int regmap_bulk_read(struct regmap *map, unsigned int reg,
 				   void *val, size_t val_count)
 {
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index fc2dc8df476f..0fd8fbb74763 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -46,7 +46,7 @@ enum regulator_status {
 /**
  * struct regulator_linear_range - specify linear voltage ranges
  *
- * Specify a range of voltages for regulator_map_linar_range() and
+ * Specify a range of voltages for regulator_map_linear_range() and
  * regulator_list_linear_range().
  *
  * @min_uV:  Lowest voltage in range
@@ -220,7 +220,7 @@ struct regulator_ops {
 	/* set regulator suspend operating mode (defined in consumer.h) */
 	int (*set_suspend_mode) (struct regulator_dev *, unsigned int mode);
 
-	int (*resume_early)(struct regulator_dev *rdev);
+	int (*resume)(struct regulator_dev *rdev);
 
 	int (*set_pull_down) (struct regulator_dev *);
 };
diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h
index e0ccf46f66cf..cb5aecd40f07 100644
--- a/include/linux/regulator/pfuze100.h
+++ b/include/linux/regulator/pfuze100.h
@@ -64,6 +64,17 @@
 #define PFUZE3000_VLDO3		11
 #define PFUZE3000_VLDO4		12
 
+#define PFUZE3001_SW1		0
+#define PFUZE3001_SW2		1
+#define PFUZE3001_SW3		2
+#define PFUZE3001_VSNVS		3
+#define PFUZE3001_VLDO1		4
+#define PFUZE3001_VLDO2		5
+#define PFUZE3001_VCCSD		6
+#define PFUZE3001_V33		7
+#define PFUZE3001_VLDO3		8
+#define PFUZE3001_VLDO4		9
+
 struct regulator_init_data;
 
 struct pfuze_regulator_platform_data {
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index b72ebdff0b77..003d09ab308d 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer);
 void ring_buffer_record_off(struct ring_buffer *buffer);
 void ring_buffer_record_on(struct ring_buffer *buffer);
 int ring_buffer_record_is_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer);
 void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
 
diff --git a/include/linux/rmi.h b/include/linux/rmi.h
index 64125443f8a6..5ef5c7c412a7 100644
--- a/include/linux/rmi.h
+++ b/include/linux/rmi.h
@@ -354,6 +354,8 @@ struct rmi_driver_data {
 	struct mutex irq_mutex;
 	struct input_dev *input;
 
+	struct irq_domain *irqdomain;
+
 	u8 pdt_props;
 
 	u8 num_rx_electrodes;
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 1b92a28dd672..6fd615a0eea9 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -106,7 +106,14 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock)
 extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key);
 extern void rt_mutex_destroy(struct rt_mutex *lock);
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass);
+#define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0)
+#else
 extern void rt_mutex_lock(struct rt_mutex *lock);
+#define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock)
+#endif
+
 extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
 extern int rt_mutex_timed_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *timeout);
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 51f52020ad5f..093aa57120b0 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -9,9 +9,6 @@
 #include <asm/io.h>
 
 struct scatterlist {
-#ifdef CONFIG_DEBUG_SG
-	unsigned long	sg_magic;
-#endif
 	unsigned long	page_link;
 	unsigned int	offset;
 	unsigned int	length;
@@ -64,7 +61,6 @@ struct sg_table {
  *
  */
 
-#define SG_MAGIC	0x87654321
 #define SG_CHAIN	0x01UL
 #define SG_END		0x02UL
 
@@ -98,7 +94,6 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
 	 */
 	BUG_ON((unsigned long) page & (SG_CHAIN | SG_END));
 #ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
 	BUG_ON(sg_is_chain(sg));
 #endif
 	sg->page_link = page_link | (unsigned long) page;
@@ -129,7 +124,6 @@ static inline void sg_set_page(struct scatterlist *sg, struct page *page,
 static inline struct page *sg_page(struct scatterlist *sg)
 {
 #ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
 	BUG_ON(sg_is_chain(sg));
 #endif
 	return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END));
@@ -195,9 +189,6 @@ static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
  **/
 static inline void sg_mark_end(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	/*
 	 * Set termination bit, clear potential chain bit
 	 */
@@ -215,9 +206,6 @@ static inline void sg_mark_end(struct scatterlist *sg)
  **/
 static inline void sg_unmark_end(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	sg->page_link &= ~SG_END;
 }
 
@@ -260,12 +248,6 @@ static inline void *sg_virt(struct scatterlist *sg)
 static inline void sg_init_marker(struct scatterlist *sgl,
 				  unsigned int nents)
 {
-#ifdef CONFIG_DEBUG_SG
-	unsigned int i;
-
-	for (i = 0; i < nents; i++)
-		sgl[i].sg_magic = SG_MAGIC;
-#endif
 	sg_mark_end(&sgl[nents - 1]);
 }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9256118bd40c..95a5018c338e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -118,7 +118,7 @@ struct task_group;
  * the comment with set_special_state().
  */
 #define is_special_task_state(state)				\
-	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD))
+	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))
 
 #define __set_current_state(state_value)			\
 	do {							\
@@ -167,8 +167,8 @@ struct task_group;
  *   need_sleep = false;
  *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
- * Where wake_up_state() (and all other wakeup primitives) imply enough
- * barriers to order the store of the variable against wakeup.
+ * where wake_up_state() executes a full memory barrier before accessing the
+ * task state.
  *
  * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
@@ -734,6 +734,10 @@ struct task_struct {
 	/* disallow userland-initiated cgroup migration */
 	unsigned			no_cgroup_migration:1;
 #endif
+#ifdef CONFIG_BLK_CGROUP
+	/* to be used once the psi infrastructure lands upstream. */
+	unsigned			use_memdelay:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
@@ -1017,7 +1021,6 @@ struct task_struct {
 	u64				last_sum_exec_runtime;
 	struct callback_head		numa_work;
 
-	struct list_head		numa_entry;
 	struct numa_group		*numa_group;
 
 	/*
@@ -1151,6 +1154,10 @@ struct task_struct {
 	unsigned int			memcg_nr_pages_over_high;
 #endif
 
+#ifdef CONFIG_BLK_CGROUP
+	struct request_queue		*throttle_queue;
+#endif
+
 #ifdef CONFIG_UPROBES
 	struct uprobe_task		*utask;
 #endif
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 1c1a1512ec55..913488d828cb 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -40,7 +40,6 @@ extern unsigned int sysctl_numa_balancing_scan_size;
 #ifdef CONFIG_SCHED_DEBUG
 extern __read_mostly unsigned int sysctl_sched_migration_cost;
 extern __read_mostly unsigned int sysctl_sched_nr_migrate;
-extern __read_mostly unsigned int sysctl_sched_time_avg;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 5be31eb7b266..108ede99e533 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -75,7 +75,7 @@ extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *,
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-extern long kernel_wait4(pid_t, int *, int, struct rusage *);
+extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 
 extern void free_task(struct task_struct *tsk);
 
diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
index 411b52e424e1..abe28d5cb3f4 100644
--- a/include/linux/sched_clock.h
+++ b/include/linux/sched_clock.h
@@ -9,17 +9,16 @@
 #define LINUX_SCHED_CLOCK
 
 #ifdef CONFIG_GENERIC_SCHED_CLOCK
-extern void sched_clock_postinit(void);
+extern void generic_sched_clock_init(void);
 
 extern void sched_clock_register(u64 (*read)(void), int bits,
 				 unsigned long rate);
 #else
-static inline void sched_clock_postinit(void) { }
+static inline void generic_sched_clock_init(void) { }
 
 static inline void sched_clock_register(u64 (*read)(void), int bits,
 					unsigned long rate)
 {
-	;
 }
 #endif
 
diff --git a/include/linux/security.h b/include/linux/security.h
index 3410acfe139c..75f4156c84d7 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -330,7 +330,7 @@ void security_file_set_fowner(struct file *file);
 int security_file_send_sigiotask(struct task_struct *tsk,
 				 struct fown_struct *fown, int sig);
 int security_file_receive(struct file *file);
-int security_file_open(struct file *file, const struct cred *cred);
+int security_file_open(struct file *file);
 int security_task_alloc(struct task_struct *task, unsigned long clone_flags);
 void security_task_free(struct task_struct *task);
 int security_cred_alloc_blank(struct cred *cred, gfp_t gfp);
@@ -880,8 +880,7 @@ static inline int security_file_receive(struct file *file)
 	return 0;
 }
 
-static inline int security_file_open(struct file *file,
-				     const struct cred *cred)
+static inline int security_file_open(struct file *file)
 {
 	return 0;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c86885954994..610a201126ee 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -630,6 +630,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
  *	@xmit_more: More SKBs are pending for this queue
+ *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
  *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
@@ -735,7 +736,7 @@ struct sk_buff {
 				peeked:1,
 				head_frag:1,
 				xmit_more:1,
-				__unused:1; /* one bit hole */
+				pfmemalloc:1;
 
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
@@ -754,31 +755,30 @@ struct sk_buff {
 
 	__u8			__pkt_type_offset[0];
 	__u8			pkt_type:3;
-	__u8			pfmemalloc:1;
 	__u8			ignore_df:1;
-
 	__u8			nf_trace:1;
 	__u8			ip_summed:2;
 	__u8			ooo_okay:1;
+
 	__u8			l4_hash:1;
 	__u8			sw_hash:1;
 	__u8			wifi_acked_valid:1;
 	__u8			wifi_acked:1;
-
 	__u8			no_fcs:1;
 	/* Indicates the inner headers are valid in the skbuff. */
 	__u8			encapsulation:1;
 	__u8			encap_hdr_csum:1;
 	__u8			csum_valid:1;
+
 	__u8			csum_complete_sw:1;
 	__u8			csum_level:2;
 	__u8			csum_not_inet:1;
-
 	__u8			dst_pending_confirm:1;
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
 	__u8			ipvs_property:1;
+
 	__u8			inner_protocol_type:1;
 	__u8			remcsum_offload:1;
 #ifdef CONFIG_NET_SWITCHDEV
@@ -3252,7 +3252,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
 				    int *peeked, int *off, int *err);
 struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
 				  int *err);
-__poll_t datagram_poll_mask(struct socket *sock, __poll_t events);
+__poll_t datagram_poll(struct file *file, struct socket *sock,
+			   struct poll_table_struct *wait);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
 			   struct iov_iter *to, int size);
 static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 09fa2c6f0e68..3a1a1dbc6f49 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -155,8 +155,12 @@ struct kmem_cache {
 
 #ifdef CONFIG_SYSFS
 #define SLAB_SUPPORTS_SYSFS
+void sysfs_slab_unlink(struct kmem_cache *);
 void sysfs_slab_release(struct kmem_cache *);
 #else
+static inline void sysfs_slab_unlink(struct kmem_cache *s)
+{
+}
 static inline void sysfs_slab_release(struct kmem_cache *s)
 {
 }
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index c174844cf663..d0884b525001 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -25,8 +25,6 @@ struct smpboot_thread_data;
  *			parked (cpu offline)
  * @unpark:		Optional unpark function, called when the thread is
  *			unparked (cpu online)
- * @cpumask:		Internal state.  To update which threads are unparked,
- *			call smpboot_update_cpumask_percpu_thread().
  * @selfparking:	Thread is not parked by the park function.
  * @thread_comm:	The base name of the thread
  */
@@ -40,23 +38,12 @@ struct smp_hotplug_thread {
 	void				(*cleanup)(unsigned int cpu, bool online);
 	void				(*park)(unsigned int cpu);
 	void				(*unpark)(unsigned int cpu);
-	cpumask_var_t			cpumask;
 	bool				selfparking;
 	const char			*thread_comm;
 };
 
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
-					   const struct cpumask *cpumask);
-
-static inline int
-smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
-{
-	return smpboot_register_percpu_thread_cpumask(plug_thread,
-						      cpu_possible_mask);
-}
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
 
 void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					  const struct cpumask *);
 
 #endif
diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h
new file mode 100644
index 000000000000..7e3b9c605ab2
--- /dev/null
+++ b/include/linux/soc/qcom/llcc-qcom.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/platform_device.h>
+#ifndef __LLCC_QCOM__
+#define __LLCC_QCOM__
+
+#define LLCC_CPUSS       1
+#define LLCC_VIDSC0      2
+#define LLCC_VIDSC1      3
+#define LLCC_ROTATOR     4
+#define LLCC_VOICE       5
+#define LLCC_AUDIO       6
+#define LLCC_MDMHPGRW    7
+#define LLCC_MDM         8
+#define LLCC_CMPT        10
+#define LLCC_GPUHTW      11
+#define LLCC_GPU         12
+#define LLCC_MMUHWT      13
+#define LLCC_CMPTDMA     15
+#define LLCC_DISP        16
+#define LLCC_VIDFW       17
+#define LLCC_MDMHPFX     20
+#define LLCC_MDMPNG      21
+#define LLCC_AUDHW       22
+
+/**
+ * llcc_slice_desc - Cache slice descriptor
+ * @slice_id: llcc slice id
+ * @slice_size: Size allocated for the llcc slice
+ */
+struct llcc_slice_desc {
+	u32 slice_id;
+	size_t slice_size;
+};
+
+/**
+ * llcc_slice_config - Data associated with the llcc slice
+ * @usecase_id: usecase id for which the llcc slice is used
+ * @slice_id: llcc slice id assigned to each slice
+ * @max_cap: maximum capacity of the llcc slice
+ * @priority: priority of the llcc slice
+ * @fixed_size: whether the llcc slice can grow beyond its size
+ * @bonus_ways: bonus ways associated with llcc slice
+ * @res_ways: reserved ways associated with llcc slice
+ * @cache_mode: mode of the llcc slice
+ * @probe_target_ways: Probe only reserved and bonus ways on a cache miss
+ * @dis_cap_alloc: Disable capacity based allocation
+ * @retain_on_pc: Retain through power collapse
+ * @activate_on_init: activate the slice on init
+ */
+struct llcc_slice_config {
+	u32 usecase_id;
+	u32 slice_id;
+	u32 max_cap;
+	u32 priority;
+	bool fixed_size;
+	u32 bonus_ways;
+	u32 res_ways;
+	u32 cache_mode;
+	u32 probe_target_ways;
+	bool dis_cap_alloc;
+	bool retain_on_pc;
+	bool activate_on_init;
+};
+
+/**
+ * llcc_drv_data - Data associated with the llcc driver
+ * @regmap: regmap associated with the llcc device
+ * @cfg: pointer to the data structure for slice configuration
+ * @lock: mutex associated with each slice
+ * @cfg_size: size of the config data table
+ * @max_slices: max slices as read from device tree
+ * @bcast_off: Offset of the broadcast bank
+ * @num_banks: Number of llcc banks
+ * @bitmap: Bit map to track the active slice ids
+ * @offsets: Pointer to the bank offsets array
+ */
+struct llcc_drv_data {
+	struct regmap *regmap;
+	const struct llcc_slice_config *cfg;
+	struct mutex lock;
+	u32 cfg_size;
+	u32 max_slices;
+	u32 bcast_off;
+	u32 num_banks;
+	unsigned long *bitmap;
+	u32 *offsets;
+};
+
+#if IS_ENABLED(CONFIG_QCOM_LLCC)
+/**
+ * llcc_slice_getd - get llcc slice descriptor
+ * @uid: usecase_id of the client
+ */
+struct llcc_slice_desc *llcc_slice_getd(u32 uid);
+
+/**
+ * llcc_slice_putd - llcc slice descritpor
+ * @desc: Pointer to llcc slice descriptor
+ */
+void llcc_slice_putd(struct llcc_slice_desc *desc);
+
+/**
+ * llcc_get_slice_id - get slice id
+ * @desc: Pointer to llcc slice descriptor
+ */
+int llcc_get_slice_id(struct llcc_slice_desc *desc);
+
+/**
+ * llcc_get_slice_size - llcc slice size
+ * @desc: Pointer to llcc slice descriptor
+ */
+size_t llcc_get_slice_size(struct llcc_slice_desc *desc);
+
+/**
+ * llcc_slice_activate - Activate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ */
+int llcc_slice_activate(struct llcc_slice_desc *desc);
+
+/**
+ * llcc_slice_deactivate - Deactivate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ */
+int llcc_slice_deactivate(struct llcc_slice_desc *desc);
+
+/**
+ * qcom_llcc_probe - program the sct table
+ * @pdev: platform device pointer
+ * @table: soc sct table
+ * @sz: Size of the config table
+ */
+int qcom_llcc_probe(struct platform_device *pdev,
+		      const struct llcc_slice_config *table, u32 sz);
+#else
+static inline struct llcc_slice_desc *llcc_slice_getd(u32 uid)
+{
+	return NULL;
+}
+
+static inline void llcc_slice_putd(struct llcc_slice_desc *desc)
+{
+
+};
+
+static inline int llcc_get_slice_id(struct llcc_slice_desc *desc)
+{
+	return -EINVAL;
+}
+
+static inline size_t llcc_get_slice_size(struct llcc_slice_desc *desc)
+{
+	return 0;
+}
+static inline int llcc_slice_activate(struct llcc_slice_desc *desc)
+{
+	return -EINVAL;
+}
+
+static inline int llcc_slice_deactivate(struct llcc_slice_desc *desc)
+{
+	return -EINVAL;
+}
+static inline int qcom_llcc_probe(struct platform_device *pdev,
+		      const struct llcc_slice_config *table, u32 sz)
+{
+	return -ENODEV;
+}
+
+static inline int qcom_llcc_remove(struct platform_device *pdev)
+{
+	return -ENODEV;
+}
+#endif
+
+#endif
diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h
index 66dcb9ec273a..5addaf5ccbce 100644
--- a/include/linux/soc/samsung/exynos-regs-pmu.h
+++ b/include/linux/soc/samsung/exynos-regs-pmu.h
@@ -42,7 +42,9 @@
 #define EXYNOS_SWRESET				0x0400
 
 #define S5P_WAKEUP_STAT				0x0600
-#define S5P_EINT_WAKEUP_MASK			0x0604
+/* Value for EXYNOS_EINT_WAKEUP_MASK disabling all external wakeup interrupts */
+#define EXYNOS_EINT_WAKEUP_MASK_DISABLED	0xffffffff
+#define EXYNOS_EINT_WAKEUP_MASK			0x0604
 #define S5P_WAKEUP_MASK				0x0608
 #define S5P_WAKEUP_MASK2				0x0614
 
@@ -180,6 +182,9 @@
 #define S5P_CORE_WAKEUP_FROM_LOCAL_CFG		(0x3 << 8)
 #define S5P_CORE_AUTOWAKEUP_EN			(1 << 31)
 
+/* Only for S5Pv210 */
+#define S5PV210_EINT_WAKEUP_MASK	0xC004
+
 /* Only for EXYNOS4210 */
 #define S5P_CMU_CLKSTOP_LCD1_LOWPWR	0x1154
 #define S5P_CMU_RESET_LCD1_LOWPWR	0x1174
@@ -641,6 +646,7 @@
 					 | EXYNOS5420_KFC_USE_STANDBY_WFI3)
 
 /* For EXYNOS5433 */
+#define EXYNOS5433_EINT_WAKEUP_MASK				(0x060C)
 #define EXYNOS5433_USBHOST30_PHY_CONTROL			(0x0728)
 #define EXYNOS5433_PAD_RETENTION_AUD_OPTION			(0x3028)
 #define EXYNOS5433_PAD_RETENTION_MMC2_OPTION			(0x30C8)
diff --git a/include/linux/spi/adi_spi3.h b/include/linux/spi/adi_spi3.h
deleted file mode 100644
index c84123aa1d06..000000000000
--- a/include/linux/spi/adi_spi3.h
+++ /dev/null
@@ -1,254 +0,0 @@
-/*
- * Analog Devices SPI3 controller driver
- *
- * Copyright (c) 2014 Analog Devices Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef _ADI_SPI3_H_
-#define _ADI_SPI3_H_
-
-#include <linux/types.h>
-
-/* SPI_CONTROL */
-#define SPI_CTL_EN                  0x00000001    /* Enable */
-#define SPI_CTL_MSTR                0x00000002    /* Master/Slave */
-#define SPI_CTL_PSSE                0x00000004    /* controls modf error in master mode */
-#define SPI_CTL_ODM                 0x00000008    /* Open Drain Mode */
-#define SPI_CTL_CPHA                0x00000010    /* Clock Phase */
-#define SPI_CTL_CPOL                0x00000020    /* Clock Polarity */
-#define SPI_CTL_ASSEL               0x00000040    /* Slave Select Pin Control */
-#define SPI_CTL_SELST               0x00000080    /* Slave Select Polarity in-between transfers */
-#define SPI_CTL_EMISO               0x00000100    /* Enable MISO */
-#define SPI_CTL_SIZE                0x00000600    /* Word Transfer Size */
-#define SPI_CTL_SIZE08              0x00000000    /* SIZE: 8 bits */
-#define SPI_CTL_SIZE16              0x00000200    /* SIZE: 16 bits */
-#define SPI_CTL_SIZE32              0x00000400    /* SIZE: 32 bits */
-#define SPI_CTL_LSBF                0x00001000    /* LSB First */
-#define SPI_CTL_FCEN                0x00002000    /* Flow-Control Enable */
-#define SPI_CTL_FCCH                0x00004000    /* Flow-Control Channel Selection */
-#define SPI_CTL_FCPL                0x00008000    /* Flow-Control Polarity */
-#define SPI_CTL_FCWM                0x00030000    /* Flow-Control Water-Mark */
-#define SPI_CTL_FIFO0               0x00000000    /* FCWM: TFIFO empty or RFIFO Full */
-#define SPI_CTL_FIFO1               0x00010000    /* FCWM: TFIFO 75% or more empty or RFIFO 75% or more full */
-#define SPI_CTL_FIFO2               0x00020000    /* FCWM: TFIFO 50% or more empty or RFIFO 50% or more full */
-#define SPI_CTL_FMODE               0x00040000    /* Fast-mode Enable */
-#define SPI_CTL_MIOM                0x00300000    /* Multiple I/O Mode */
-#define SPI_CTL_MIO_DIS             0x00000000    /* MIOM: Disable */
-#define SPI_CTL_MIO_DUAL            0x00100000    /* MIOM: Enable DIOM (Dual I/O Mode) */
-#define SPI_CTL_MIO_QUAD            0x00200000    /* MIOM: Enable QUAD (Quad SPI Mode) */
-#define SPI_CTL_SOSI                0x00400000    /* Start on MOSI */
-/* SPI_RX_CONTROL */
-#define SPI_RXCTL_REN               0x00000001    /* Receive Channel Enable */
-#define SPI_RXCTL_RTI               0x00000004    /* Receive Transfer Initiate */
-#define SPI_RXCTL_RWCEN             0x00000008    /* Receive Word Counter Enable */
-#define SPI_RXCTL_RDR               0x00000070    /* Receive Data Request */
-#define SPI_RXCTL_RDR_DIS           0x00000000    /* RDR: Disabled */
-#define SPI_RXCTL_RDR_NE            0x00000010    /* RDR: RFIFO not empty */
-#define SPI_RXCTL_RDR_25            0x00000020    /* RDR: RFIFO 25% full */
-#define SPI_RXCTL_RDR_50            0x00000030    /* RDR: RFIFO 50% full */
-#define SPI_RXCTL_RDR_75            0x00000040    /* RDR: RFIFO 75% full */
-#define SPI_RXCTL_RDR_FULL          0x00000050    /* RDR: RFIFO full */
-#define SPI_RXCTL_RDO               0x00000100    /* Receive Data Over-Run */
-#define SPI_RXCTL_RRWM              0x00003000    /* FIFO Regular Water-Mark */
-#define SPI_RXCTL_RWM_0             0x00000000    /* RRWM: RFIFO Empty */
-#define SPI_RXCTL_RWM_25            0x00001000    /* RRWM: RFIFO 25% full */
-#define SPI_RXCTL_RWM_50            0x00002000    /* RRWM: RFIFO 50% full */
-#define SPI_RXCTL_RWM_75            0x00003000    /* RRWM: RFIFO 75% full */
-#define SPI_RXCTL_RUWM              0x00070000    /* FIFO Urgent Water-Mark */
-#define SPI_RXCTL_UWM_DIS           0x00000000    /* RUWM: Disabled */
-#define SPI_RXCTL_UWM_25            0x00010000    /* RUWM: RFIFO 25% full */
-#define SPI_RXCTL_UWM_50            0x00020000    /* RUWM: RFIFO 50% full */
-#define SPI_RXCTL_UWM_75            0x00030000    /* RUWM: RFIFO 75% full */
-#define SPI_RXCTL_UWM_FULL          0x00040000    /* RUWM: RFIFO full */
-/* SPI_TX_CONTROL */
-#define SPI_TXCTL_TEN               0x00000001    /* Transmit Channel Enable */
-#define SPI_TXCTL_TTI               0x00000004    /* Transmit Transfer Initiate */
-#define SPI_TXCTL_TWCEN             0x00000008    /* Transmit Word Counter Enable */
-#define SPI_TXCTL_TDR               0x00000070    /* Transmit Data Request */
-#define SPI_TXCTL_TDR_DIS           0x00000000    /* TDR: Disabled */
-#define SPI_TXCTL_TDR_NF            0x00000010    /* TDR: TFIFO not full */
-#define SPI_TXCTL_TDR_25            0x00000020    /* TDR: TFIFO 25% empty */
-#define SPI_TXCTL_TDR_50            0x00000030    /* TDR: TFIFO 50% empty */
-#define SPI_TXCTL_TDR_75            0x00000040    /* TDR: TFIFO 75% empty */
-#define SPI_TXCTL_TDR_EMPTY         0x00000050    /* TDR: TFIFO empty */
-#define SPI_TXCTL_TDU               0x00000100    /* Transmit Data Under-Run */
-#define SPI_TXCTL_TRWM              0x00003000    /* FIFO Regular Water-Mark */
-#define SPI_TXCTL_RWM_FULL          0x00000000    /* TRWM: TFIFO full */
-#define SPI_TXCTL_RWM_25            0x00001000    /* TRWM: TFIFO 25% empty */
-#define SPI_TXCTL_RWM_50            0x00002000    /* TRWM: TFIFO 50% empty */
-#define SPI_TXCTL_RWM_75            0x00003000    /* TRWM: TFIFO 75% empty */
-#define SPI_TXCTL_TUWM              0x00070000    /* FIFO Urgent Water-Mark */
-#define SPI_TXCTL_UWM_DIS           0x00000000    /* TUWM: Disabled */
-#define SPI_TXCTL_UWM_25            0x00010000    /* TUWM: TFIFO 25% empty */
-#define SPI_TXCTL_UWM_50            0x00020000    /* TUWM: TFIFO 50% empty */
-#define SPI_TXCTL_UWM_75            0x00030000    /* TUWM: TFIFO 75% empty */
-#define SPI_TXCTL_UWM_EMPTY         0x00040000    /* TUWM: TFIFO empty */
-/* SPI_CLOCK */
-#define SPI_CLK_BAUD                0x0000FFFF    /* Baud Rate */
-/* SPI_DELAY */
-#define SPI_DLY_STOP                0x000000FF    /* Transfer delay time in multiples of SCK period */
-#define SPI_DLY_LEADX               0x00000100    /* Extended (1 SCK) LEAD Control */
-#define SPI_DLY_LAGX                0x00000200    /* Extended (1 SCK) LAG control */
-/* SPI_SSEL */
-#define SPI_SLVSEL_SSE1             0x00000002    /* SPISSEL1 Enable */
-#define SPI_SLVSEL_SSE2             0x00000004    /* SPISSEL2 Enable */
-#define SPI_SLVSEL_SSE3             0x00000008    /* SPISSEL3 Enable */
-#define SPI_SLVSEL_SSE4             0x00000010    /* SPISSEL4 Enable */
-#define SPI_SLVSEL_SSE5             0x00000020    /* SPISSEL5 Enable */
-#define SPI_SLVSEL_SSE6             0x00000040    /* SPISSEL6 Enable */
-#define SPI_SLVSEL_SSE7             0x00000080    /* SPISSEL7 Enable */
-#define SPI_SLVSEL_SSEL1            0x00000200    /* SPISSEL1 Value */
-#define SPI_SLVSEL_SSEL2            0x00000400    /* SPISSEL2 Value */
-#define SPI_SLVSEL_SSEL3            0x00000800    /* SPISSEL3 Value */
-#define SPI_SLVSEL_SSEL4            0x00001000    /* SPISSEL4 Value */
-#define SPI_SLVSEL_SSEL5            0x00002000    /* SPISSEL5 Value */
-#define SPI_SLVSEL_SSEL6            0x00004000    /* SPISSEL6 Value */
-#define SPI_SLVSEL_SSEL7            0x00008000    /* SPISSEL7 Value */
-/* SPI_RWC */
-#define SPI_RWC_VALUE               0x0000FFFF    /* Received Word-Count */
-/* SPI_RWCR */
-#define SPI_RWCR_VALUE              0x0000FFFF    /* Received Word-Count Reload */
-/* SPI_TWC */
-#define SPI_TWC_VALUE               0x0000FFFF    /* Transmitted Word-Count */
-/* SPI_TWCR */
-#define SPI_TWCR_VALUE              0x0000FFFF    /* Transmitted Word-Count Reload */
-/* SPI_IMASK */
-#define SPI_IMSK_RUWM               0x00000002    /* Receive Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_TUWM               0x00000004    /* Transmit Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_ROM                0x00000010    /* Receive Over-Run Error Interrupt Mask */
-#define SPI_IMSK_TUM                0x00000020    /* Transmit Under-Run Error Interrupt Mask */
-#define SPI_IMSK_TCM                0x00000040    /* Transmit Collision Error Interrupt Mask */
-#define SPI_IMSK_MFM                0x00000080    /* Mode Fault Error Interrupt Mask */
-#define SPI_IMSK_RSM                0x00000100    /* Receive Start Interrupt Mask */
-#define SPI_IMSK_TSM                0x00000200    /* Transmit Start Interrupt Mask */
-#define SPI_IMSK_RFM                0x00000400    /* Receive Finish Interrupt Mask */
-#define SPI_IMSK_TFM                0x00000800    /* Transmit Finish Interrupt Mask */
-/* SPI_IMASKCL */
-#define SPI_IMSK_CLR_RUW            0x00000002    /* Receive Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_CLR_TUWM           0x00000004    /* Transmit Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_CLR_ROM            0x00000010    /* Receive Over-Run Error Interrupt Mask */
-#define SPI_IMSK_CLR_TUM            0x00000020    /* Transmit Under-Run Error Interrupt Mask */
-#define SPI_IMSK_CLR_TCM            0x00000040    /* Transmit Collision Error Interrupt Mask */
-#define SPI_IMSK_CLR_MFM            0x00000080    /* Mode Fault Error Interrupt Mask */
-#define SPI_IMSK_CLR_RSM            0x00000100    /* Receive Start Interrupt Mask */
-#define SPI_IMSK_CLR_TSM            0x00000200    /* Transmit Start Interrupt Mask */
-#define SPI_IMSK_CLR_RFM            0x00000400    /* Receive Finish Interrupt Mask */
-#define SPI_IMSK_CLR_TFM            0x00000800    /* Transmit Finish Interrupt Mask */
-/* SPI_IMASKST */
-#define SPI_IMSK_SET_RUWM           0x00000002    /* Receive Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_SET_TUWM           0x00000004    /* Transmit Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_SET_ROM            0x00000010    /* Receive Over-Run Error Interrupt Mask */
-#define SPI_IMSK_SET_TUM            0x00000020    /* Transmit Under-Run Error Interrupt Mask */
-#define SPI_IMSK_SET_TCM            0x00000040    /* Transmit Collision Error Interrupt Mask */
-#define SPI_IMSK_SET_MFM            0x00000080    /* Mode Fault Error Interrupt Mask */
-#define SPI_IMSK_SET_RSM            0x00000100    /* Receive Start Interrupt Mask */
-#define SPI_IMSK_SET_TSM            0x00000200    /* Transmit Start Interrupt Mask */
-#define SPI_IMSK_SET_RFM            0x00000400    /* Receive Finish Interrupt Mask */
-#define SPI_IMSK_SET_TFM            0x00000800    /* Transmit Finish Interrupt Mask */
-/* SPI_STATUS */
-#define SPI_STAT_SPIF               0x00000001    /* SPI Finished */
-#define SPI_STAT_RUWM               0x00000002    /* Receive Urgent Water-Mark Breached */
-#define SPI_STAT_TUWM               0x00000004    /* Transmit Urgent Water-Mark Breached */
-#define SPI_STAT_ROE                0x00000010    /* Receive Over-Run Error Indication */
-#define SPI_STAT_TUE                0x00000020    /* Transmit Under-Run Error Indication */
-#define SPI_STAT_TCE                0x00000040    /* Transmit Collision Error Indication */
-#define SPI_STAT_MODF               0x00000080    /* Mode Fault Error Indication */
-#define SPI_STAT_RS                 0x00000100    /* Receive Start Indication */
-#define SPI_STAT_TS                 0x00000200    /* Transmit Start Indication */
-#define SPI_STAT_RF                 0x00000400    /* Receive Finish Indication */
-#define SPI_STAT_TF                 0x00000800    /* Transmit Finish Indication */
-#define SPI_STAT_RFS                0x00007000    /* SPI_RFIFO status */
-#define SPI_STAT_RFIFO_EMPTY        0x00000000    /* RFS: RFIFO Empty */
-#define SPI_STAT_RFIFO_25           0x00001000    /* RFS: RFIFO 25% Full */
-#define SPI_STAT_RFIFO_50           0x00002000    /* RFS: RFIFO 50% Full */
-#define SPI_STAT_RFIFO_75           0x00003000    /* RFS: RFIFO 75% Full */
-#define SPI_STAT_RFIFO_FULL         0x00004000    /* RFS: RFIFO Full */
-#define SPI_STAT_TFS                0x00070000    /* SPI_TFIFO status */
-#define SPI_STAT_TFIFO_FULL         0x00000000    /* TFS: TFIFO full */
-#define SPI_STAT_TFIFO_25           0x00010000    /* TFS: TFIFO 25% empty */
-#define SPI_STAT_TFIFO_50           0x00020000    /* TFS: TFIFO 50% empty */
-#define SPI_STAT_TFIFO_75           0x00030000    /* TFS: TFIFO 75% empty */
-#define SPI_STAT_TFIFO_EMPTY        0x00040000    /* TFS: TFIFO empty */
-#define SPI_STAT_FCS                0x00100000    /* Flow-Control Stall Indication */
-#define SPI_STAT_RFE                0x00400000    /* SPI_RFIFO Empty */
-#define SPI_STAT_TFF                0x00800000    /* SPI_TFIFO Full */
-/* SPI_ILAT */
-#define SPI_ILAT_RUWMI              0x00000002    /* Receive Urgent Water Mark Interrupt */
-#define SPI_ILAT_TUWMI              0x00000004    /* Transmit Urgent Water Mark Interrupt */
-#define SPI_ILAT_ROI                0x00000010    /* Receive Over-Run Error Indication */
-#define SPI_ILAT_TUI                0x00000020    /* Transmit Under-Run Error Indication */
-#define SPI_ILAT_TCI                0x00000040    /* Transmit Collision Error Indication */
-#define SPI_ILAT_MFI                0x00000080    /* Mode Fault Error Indication */
-#define SPI_ILAT_RSI                0x00000100    /* Receive Start Indication */
-#define SPI_ILAT_TSI                0x00000200    /* Transmit Start Indication */
-#define SPI_ILAT_RFI                0x00000400    /* Receive Finish Indication */
-#define SPI_ILAT_TFI                0x00000800    /* Transmit Finish Indication */
-/* SPI_ILATCL */
-#define SPI_ILAT_CLR_RUWMI          0x00000002    /* Receive Urgent Water Mark Interrupt */
-#define SPI_ILAT_CLR_TUWMI          0x00000004    /* Transmit Urgent Water Mark Interrupt */
-#define SPI_ILAT_CLR_ROI            0x00000010    /* Receive Over-Run Error Indication */
-#define SPI_ILAT_CLR_TUI            0x00000020    /* Transmit Under-Run Error Indication */
-#define SPI_ILAT_CLR_TCI            0x00000040    /* Transmit Collision Error Indication */
-#define SPI_ILAT_CLR_MFI            0x00000080    /* Mode Fault Error Indication */
-#define SPI_ILAT_CLR_RSI            0x00000100    /* Receive Start Indication */
-#define SPI_ILAT_CLR_TSI            0x00000200    /* Transmit Start Indication */
-#define SPI_ILAT_CLR_RFI            0x00000400    /* Receive Finish Indication */
-#define SPI_ILAT_CLR_TFI            0x00000800    /* Transmit Finish Indication */
-
-/*
- * adi spi3 registers layout
- */
-struct adi_spi_regs {
-	u32 revid;
-	u32 control;
-	u32 rx_control;
-	u32 tx_control;
-	u32 clock;
-	u32 delay;
-	u32 ssel;
-	u32 rwc;
-	u32 rwcr;
-	u32 twc;
-	u32 twcr;
-	u32 reserved0;
-	u32 emask;
-	u32 emaskcl;
-	u32 emaskst;
-	u32 reserved1;
-	u32 status;
-	u32 elat;
-	u32 elatcl;
-	u32 reserved2;
-	u32 rfifo;
-	u32 reserved3;
-	u32 tfifo;
-};
-
-#define MAX_CTRL_CS          8  /* cs in spi controller */
-
-/* device.platform_data for SSP controller devices */
-struct adi_spi3_master {
-	u16 num_chipselect;
-	u16 pin_req[7];
-};
-
-/* spi_board_info.controller_data for SPI slave devices,
- * copied to spi_device.platform_data ... mostly for dma tuning
- */
-struct adi_spi3_chip {
-	u32 control;
-	u16 cs_chg_udelay; /* Some devices require 16-bit delays */
-	u32 tx_dummy_val; /* tx value for rx only transfer */
-	bool enable_dma;
-};
-
-#endif /* _ADI_SPI3_H_ */
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index bb4bd15ae1f6..b2bd4b4127c4 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -3,7 +3,9 @@
  * Copyright (C) 2018 Exceet Electronics GmbH
  * Copyright (C) 2018 Bootlin
  *
- * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ * Author:
+ *	Peter Pan <peterpandong@micron.com>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
  */
 
 #ifndef __LINUX_SPI_MEM_H
@@ -122,7 +124,8 @@ struct spi_mem_op {
 /**
  * struct spi_mem - describes a SPI memory device
  * @spi: the underlying SPI device
- * @drvpriv: spi_mem_drviver private data
+ * @drvpriv: spi_mem_driver private data
+ * @name: name of the SPI memory device
  *
  * Extra information that describe the SPI memory device and may be needed by
  * the controller to properly handle this device should be placed here.
@@ -133,6 +136,7 @@ struct spi_mem_op {
 struct spi_mem {
 	struct spi_device *spi;
 	void *drvpriv;
+	const char *name;
 };
 
 /**
@@ -165,6 +169,13 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem)
  *		    limitations)
  * @supports_op: check if an operation is supported by the controller
  * @exec_op: execute a SPI memory operation
+ * @get_name: get a custom name for the SPI mem device from the controller.
+ *	      This might be needed if the controller driver has been ported
+ *	      to use the SPI mem layer and a custom name is used to keep
+ *	      mtdparts compatible.
+ *	      Note that if the implementation of this function allocates memory
+ *	      dynamically, then it should do so with devm_xxx(), as we don't
+ *	      have a ->free_name() function.
  *
  * This interface should be implemented by SPI controllers providing an
  * high-level interface to execute SPI memory operation, which is usually the
@@ -176,6 +187,7 @@ struct spi_controller_mem_ops {
 			    const struct spi_mem_op *op);
 	int (*exec_op)(struct spi_mem *mem,
 		       const struct spi_mem_op *op);
+	const char *(*get_name)(struct spi_mem *mem);
 };
 
 /**
@@ -234,6 +246,8 @@ bool spi_mem_supports_op(struct spi_mem *mem,
 int spi_mem_exec_op(struct spi_mem *mem,
 		    const struct spi_mem_op *op);
 
+const char *spi_mem_get_name(struct spi_mem *mem);
+
 int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv,
 				       struct module *owner);
 
diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h
index 51d8c060e513..b7e021b274dc 100644
--- a/include/linux/spi/spi_bitbang.h
+++ b/include/linux/spi/spi_bitbang.h
@@ -8,7 +8,7 @@ struct spi_bitbang {
 	struct mutex		lock;
 	u8			busy;
 	u8			use_dma;
-	u8			flags;		/* extra spi->mode support */
+	u16			flags;		/* extra spi->mode support */
 
 	struct spi_master	*master;
 
@@ -30,7 +30,8 @@ struct spi_bitbang {
 	/* txrx_word[SPI_MODE_*]() just looks like a shift register */
 	u32	(*txrx_word[4])(struct spi_device *spi,
 			unsigned nsecs,
-			u32 word, u8 bits);
+			u32 word, u8 bits, unsigned flags);
+	int	(*set_line_direction)(struct spi_device *spi, bool output);
 };
 
 /* you can call these default bitbang->master methods from your custom
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index fd57888d4942..3190997df9ca 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -114,29 +114,48 @@ do {								\
 #endif /*arch_spin_is_contended*/
 
 /*
- * This barrier must provide two things:
+ * smp_mb__after_spinlock() provides the equivalent of a full memory barrier
+ * between program-order earlier lock acquisitions and program-order later
+ * memory accesses.
  *
- *   - it must guarantee a STORE before the spin_lock() is ordered against a
- *     LOAD after it, see the comments at its two usage sites.
+ * This guarantees that the following two properties hold:
  *
- *   - it must ensure the critical section is RCsc.
+ *   1) Given the snippet:
  *
- * The latter is important for cases where we observe values written by other
- * CPUs in spin-loops, without barriers, while being subject to scheduling.
+ *	  { X = 0;  Y = 0; }
  *
- * CPU0			CPU1			CPU2
+ *	  CPU0				CPU1
  *
- *			for (;;) {
- *			  if (READ_ONCE(X))
- *			    break;
- *			}
- * X=1
- *			<sched-out>
- *						<sched-in>
- *						r = X;
+ *	  WRITE_ONCE(X, 1);		WRITE_ONCE(Y, 1);
+ *	  spin_lock(S);			smp_mb();
+ *	  smp_mb__after_spinlock();	r1 = READ_ONCE(X);
+ *	  r0 = READ_ONCE(Y);
+ *	  spin_unlock(S);
  *
- * without transitivity it could be that CPU1 observes X!=0 breaks the loop,
- * we get migrated and CPU2 sees X==0.
+ *      it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0)
+ *      and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments
+ *      preceding the call to smp_mb__after_spinlock() in __schedule() and in
+ *      try_to_wake_up().
+ *
+ *   2) Given the snippet:
+ *
+ *  { X = 0;  Y = 0; }
+ *
+ *  CPU0		CPU1				CPU2
+ *
+ *  spin_lock(S);	spin_lock(S);			r1 = READ_ONCE(Y);
+ *  WRITE_ONCE(X, 1);	smp_mb__after_spinlock();	smp_rmb();
+ *  spin_unlock(S);	r0 = READ_ONCE(X);		r2 = READ_ONCE(X);
+ *			WRITE_ONCE(Y, 1);
+ *			spin_unlock(S);
+ *
+ *      it is forbidden that CPU0's critical section executes before CPU1's
+ *      critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1)
+ *      and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments
+ *      preceding the calls to smp_rmb() in try_to_wake_up() for similar
+ *      snippets but "projected" onto two CPUs.
+ *
+ * Property (2) upgrades the lock to an RCsc lock.
  *
  * Since most load-store architectures implement ACQUIRE with an smp_mb() after
  * the LL/SC loop, they need no further barriers. Similarly all our TSO
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 91494d7e8e41..3e72a291c401 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -195,6 +195,16 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
 	return retval;
 }
 
+/* Used by tracing, cannot be traced and cannot invoke lockdep. */
+static inline notrace int
+srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp)
+{
+	int retval;
+
+	retval = __srcu_read_lock(sp);
+	return retval;
+}
+
 /**
  * srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
  * @sp: srcu_struct in which to unregister the old reader.
@@ -209,6 +219,13 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
 	__srcu_read_unlock(sp, idx);
 }
 
+/* Used by tracing, cannot be traced and cannot call lockdep. */
+static inline notrace void
+srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp)
+{
+	__srcu_read_unlock(sp, idx);
+}
+
 /**
  * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock
  *
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 440b62f7502e..5a28ac9284f0 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -414,7 +414,7 @@ static inline bool hibernation_available(void) { return false; }
 #define PM_RESTORE_PREPARE	0x0005 /* Going to restore a saved image */
 #define PM_POST_RESTORE		0x0006 /* Restore failed */
 
-extern struct mutex pm_mutex;
+extern struct mutex system_transition_mutex;
 
 #ifdef CONFIG_PM_SLEEP
 void save_processor_state(void);
diff --git a/include/linux/swait.h b/include/linux/swait.h
index bf8cb0dee23c..73e06e9986d4 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -16,7 +16,7 @@
  * wait-queues, but the semantics are actually completely different, and
  * every single user we have ever had has been buggy (or pointless).
  *
- * A "swake_up()" only wakes up _one_ waiter, which is not at all what
+ * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what
  * "wake_up()" does, and has led to problems. In other cases, it has
  * been fine, because there's only ever one waiter (kvm), but in that
  * case gthe whole "simple" wait-queue is just pointless to begin with,
@@ -38,8 +38,8 @@
  *    all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
  *    sleeper state.
  *
- *  - the exclusive mode; because this requires preserving the list order
- *    and this is hard.
+ *  - the !exclusive mode; because that leads to O(n) wakeups, everything is
+ *    exclusive.
  *
  *  - custom wake callback functions; because you cannot give any guarantees
  *    about random code. This also allows swait to be used in RT, such that
@@ -115,7 +115,7 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name
  *      CPU0 - waker                    CPU1 - waiter
  *
  *                                      for (;;) {
- *      @cond = true;                     prepare_to_swait(&wq_head, &wait, state);
+ *      @cond = true;                     prepare_to_swait_exclusive(&wq_head, &wait, state);
  *      smp_mb();                         // smp_mb() from set_current_state()
  *      if (swait_active(wq_head))        if (@cond)
  *        wake_up(wq_head);                      break;
@@ -157,20 +157,20 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq)
 	return swait_active(wq);
 }
 
-extern void swake_up(struct swait_queue_head *q);
+extern void swake_up_one(struct swait_queue_head *q);
 extern void swake_up_all(struct swait_queue_head *q);
 extern void swake_up_locked(struct swait_queue_head *q);
 
-extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
-extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
+extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state);
 extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
 
 extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 
-/* as per ___wait_event() but for swait, therefore "exclusive == 0" */
+/* as per ___wait_event() but for swait, therefore "exclusive == 1" */
 #define ___swait_event(wq, condition, state, ret, cmd)			\
 ({									\
+	__label__ __out;						\
 	struct swait_queue __wait;					\
 	long __ret = ret;						\
 									\
@@ -183,20 +183,20 @@ extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 									\
 		if (___wait_is_interruptible(state) && __int) {		\
 			__ret = __int;					\
-			break;						\
+			goto __out;					\
 		}							\
 									\
 		cmd;							\
 	}								\
 	finish_swait(&wq, &__wait);					\
-	__ret;								\
+__out:	__ret;								\
 })
 
 #define __swait_event(wq, condition)					\
 	(void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,	\
 			    schedule())
 
-#define swait_event(wq, condition)					\
+#define swait_event_exclusive(wq, condition)				\
 do {									\
 	if (condition)							\
 		break;							\
@@ -208,7 +208,7 @@ do {									\
 		      TASK_UNINTERRUPTIBLE, timeout,			\
 		      __ret = schedule_timeout(__ret))
 
-#define swait_event_timeout(wq, condition, timeout)			\
+#define swait_event_timeout_exclusive(wq, condition, timeout)		\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
@@ -220,7 +220,7 @@ do {									\
 	___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0,		\
 		      schedule())
 
-#define swait_event_interruptible(wq, condition)			\
+#define swait_event_interruptible_exclusive(wq, condition)		\
 ({									\
 	int __ret = 0;							\
 	if (!(condition))						\
@@ -233,7 +233,7 @@ do {									\
 		      TASK_INTERRUPTIBLE, timeout,			\
 		      __ret = schedule_timeout(__ret))
 
-#define swait_event_interruptible_timeout(wq, condition, timeout)	\
+#define swait_event_interruptible_timeout_exclusive(wq, condition, timeout)\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
@@ -246,7 +246,7 @@ do {									\
 	(void)___swait_event(wq, condition, TASK_IDLE, 0, schedule())
 
 /**
- * swait_event_idle - wait without system load contribution
+ * swait_event_idle_exclusive - wait without system load contribution
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
@@ -257,7 +257,7 @@ do {									\
  * condition and doesn't want to contribute to system load. Signals are
  * ignored.
  */
-#define swait_event_idle(wq, condition)					\
+#define swait_event_idle_exclusive(wq, condition)			\
 do {									\
 	if (condition)							\
 		break;							\
@@ -270,7 +270,7 @@ do {									\
 		       __ret = schedule_timeout(__ret))
 
 /**
- * swait_event_idle_timeout - wait up to timeout without load contribution
+ * swait_event_idle_timeout_exclusive - wait up to timeout without load contribution
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout at which we'll give up in jiffies
@@ -288,7 +288,7 @@ do {									\
  * or the remaining jiffies (at least 1) if the @condition evaluated
  * to %true before the @timeout elapsed.
  */
-#define swait_event_idle_timeout(wq, condition, timeout)		\
+#define swait_event_idle_timeout_exclusive(wq, condition, timeout)	\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c063443d8638..1a8bd05a335e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -629,7 +629,6 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 
 	return memcg->swappiness;
 }
-
 #else
 static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 {
@@ -637,6 +636,16 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 }
 #endif
 
+#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
+					 gfp_t gfp_mask);
+#else
+static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg,
+						int node, gfp_t gfp_mask)
+{
+}
+#endif
+
 #ifdef CONFIG_MEMCG_SWAP
 extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
 extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h
index 06bd7b096167..e06febf62978 100644
--- a/include/linux/swapfile.h
+++ b/include/linux/swapfile.h
@@ -10,5 +10,7 @@ extern spinlock_t swap_lock;
 extern struct plist_head swap_active_head;
 extern struct swap_info_struct *swap_info[];
 extern int try_to_unuse(unsigned int, bool, unsigned long);
+extern unsigned long generic_max_swapfile_size(void);
+extern unsigned long max_swapfile_size(void);
 
 #endif /* _LINUX_SWAPFILE_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 73810808cdf2..2ff814c92f7f 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -11,6 +11,7 @@
 #ifndef _LINUX_SYSCALLS_H
 #define _LINUX_SYSCALLS_H
 
+struct __aio_sigset;
 struct epoll_event;
 struct iattr;
 struct inode;
@@ -80,6 +81,7 @@ union bpf_attr;
 #include <linux/unistd.h>
 #include <linux/quota.h>
 #include <linux/key.h>
+#include <linux/personality.h>
 #include <trace/syscall.h>
 
 #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
@@ -231,6 +233,9 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
  */
 #ifndef __SYSCALL_DEFINEx
 #define __SYSCALL_DEFINEx(x, name, ...)					\
+	__diag_push();							\
+	__diag_ignore(GCC, 8, "-Wattribute-alias",			\
+		      "Type aliasing is used to sanitize syscall arguments");\
 	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
 		__attribute__((alias(__stringify(__se_sys##name))));	\
 	ALLOW_ERROR_INJECTION(sys##name, ERRNO);			\
@@ -243,6 +248,7 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
 		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
 		return ret;						\
 	}								\
+	__diag_pop();							\
 	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 #endif /* __SYSCALL_DEFINEx */
 
@@ -501,9 +507,9 @@ asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
 /* fs/timerfd.c */
 asmlinkage long sys_timerfd_create(int clockid, int flags);
 asmlinkage long sys_timerfd_settime(int ufd, int flags,
-				    const struct itimerspec __user *utmr,
-				    struct itimerspec __user *otmr);
-asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr);
+				    const struct __kernel_itimerspec __user *utmr,
+				    struct __kernel_itimerspec __user *otmr);
+asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user *otmr);
 
 /* fs/utimes.c */
 asmlinkage long sys_utimensat(int dfd, const char __user *filename,
@@ -568,10 +574,10 @@ asmlinkage long sys_timer_create(clockid_t which_clock,
 				 struct sigevent __user *timer_event_spec,
 				 timer_t __user * created_timer_id);
 asmlinkage long sys_timer_gettime(timer_t timer_id,
-				struct itimerspec __user *setting);
+				struct __kernel_itimerspec __user *setting);
 asmlinkage long sys_timer_getoverrun(timer_t timer_id);
 asmlinkage long sys_timer_settime(timer_t timer_id, int flags,
-				const struct itimerspec __user *new_setting,
+				const struct __kernel_itimerspec __user *new_setting,
 				struct itimerspec __user *old_setting);
 asmlinkage long sys_timer_delete(timer_t timer_id);
 asmlinkage long sys_clock_settime(clockid_t which_clock,
@@ -1277,4 +1283,14 @@ static inline long ksys_truncate(const char __user *pathname, loff_t length)
 	return do_sys_truncate(pathname, length);
 }
 
+static inline unsigned int ksys_personality(unsigned int personality)
+{
+	unsigned int old = current->personality;
+
+	if (personality != 0xffffffff)
+		set_personality(personality);
+
+	return old;
+}
+
 #endif
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index c6aa8a3c42ed..b9626aa7e90c 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -37,9 +37,33 @@ struct t10_pi_tuple {
 #define T10_PI_APP_ESCAPE cpu_to_be16(0xffff)
 #define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff)
 
+static inline u32 t10_pi_ref_tag(struct request *rq)
+{
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+	return blk_rq_pos(rq) >>
+		(rq->q->integrity.interval_exp - 9) & 0xffffffff;
+#else
+	return -1U;
+#endif
+}
+
 extern const struct blk_integrity_profile t10_pi_type1_crc;
 extern const struct blk_integrity_profile t10_pi_type1_ip;
 extern const struct blk_integrity_profile t10_pi_type3_crc;
 extern const struct blk_integrity_profile t10_pi_type3_ip;
 
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+extern void t10_pi_prepare(struct request *rq, u8 protection_type);
+extern void t10_pi_complete(struct request *rq, u8 protection_type,
+			    unsigned int intervals);
+#else
+static inline void t10_pi_complete(struct request *rq, u8 protection_type,
+				   unsigned int intervals)
+{
+}
+static inline void t10_pi_prepare(struct request *rq, u8 protection_type)
+{
+}
+#endif
+
 #endif
diff --git a/include/linux/time.h b/include/linux/time.h
index aed74463592d..27d83fd2ae61 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -14,9 +14,9 @@ int get_timespec64(struct timespec64 *ts,
 int put_timespec64(const struct timespec64 *ts,
 		struct __kernel_timespec __user *uts);
 int get_itimerspec64(struct itimerspec64 *it,
-			const struct itimerspec __user *uit);
+			const struct __kernel_itimerspec __user *uit);
 int put_itimerspec64(const struct itimerspec64 *it,
-			struct itimerspec __user *uit);
+			struct __kernel_itimerspec __user *uit);
 
 extern time64_t mktime64(const unsigned int year, const unsigned int mon,
 			const unsigned int day, const unsigned int hour,
diff --git a/include/linux/time64.h b/include/linux/time64.h
index 0a7b2f79cec7..05634afba0db 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -12,6 +12,7 @@ typedef __u64 timeu64_t;
  */
 #ifndef CONFIG_64BIT_TIME
 #define __kernel_timespec timespec
+#define __kernel_itimerspec itimerspec
 #endif
 
 #include <uapi/linux/time.h>
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 86bc2026efce..5d738804e3d6 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -21,6 +21,21 @@ extern int do_sys_settimeofday64(const struct timespec64 *tv,
 				 const struct timezone *tz);
 
 /*
+ * ktime_get() family: read the current time in a multitude of ways,
+ *
+ * The default time reference is CLOCK_MONOTONIC, starting at
+ * boot time but not counting the time spent in suspend.
+ * For other references, use the functions with "real", "clocktai",
+ * "boottime" and "raw" suffixes.
+ *
+ * To get the time in a different format, use the ones wit
+ * "ns", "ts64" and "seconds" suffix.
+ *
+ * See Documentation/core-api/timekeeping.rst for more details.
+ */
+
+
+/*
  * timespec64 based interfaces
  */
 extern void ktime_get_raw_ts64(struct timespec64 *ts);
@@ -177,7 +192,7 @@ static inline time64_t ktime_get_clocktai_seconds(void)
 extern bool timekeeping_rtc_skipsuspend(void);
 extern bool timekeeping_rtc_skipresume(void);
 
-extern void timekeeping_inject_sleeptime64(struct timespec64 *delta);
+extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta);
 
 /*
  * struct system_time_snapshot - simultaneous raw/real time capture with
@@ -243,7 +258,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot);
 extern int persistent_clock_is_local;
 
 extern void read_persistent_clock64(struct timespec64 *ts);
-extern void read_boot_clock64(struct timespec64 *ts);
+void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock,
+					   struct timespec64 *boot_offset);
 extern int update_persistent_clock64(struct timespec64 now);
 
 /*
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 66272862070b..61dfd93b6ee4 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -64,6 +64,8 @@ struct torture_random_state {
 	long trs_count;
 };
 #define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 }
+#define DEFINE_TORTURE_RANDOM_PERCPU(name) \
+	DEFINE_PER_CPU(struct torture_random_state, name)
 unsigned long torture_random(struct torture_random_state *trsp);
 
 /* Task shuffler, which causes CPUs to occasionally go idle. */
@@ -79,7 +81,7 @@ void stutter_wait(const char *title);
 int torture_stutter_init(int s);
 
 /* Initialization and cleanup. */
-bool torture_init_begin(char *ttype, bool v);
+bool torture_init_begin(char *ttype, int v);
 void torture_init_end(void);
 bool torture_cleanup_begin(void);
 void torture_cleanup_end(void);
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 4a8841963c2e..05589a3e37f4 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -51,6 +51,7 @@
 #include <linux/security.h>
 #include <linux/task_work.h>
 #include <linux/memcontrol.h>
+#include <linux/blk-cgroup.h>
 struct linux_binprm;
 
 /*
@@ -192,6 +193,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 		task_work_run();
 
 	mem_cgroup_handle_over_high();
+	blkcg_maybe_throttle_current();
 }
 
 #endif	/* <linux/tracehook.h> */
diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h
index 6c5f2074e14f..6f8b68cd460f 100644
--- a/include/linux/uio_driver.h
+++ b/include/linux/uio_driver.h
@@ -75,7 +75,7 @@ struct uio_device {
         struct fasync_struct    *async_queue;
         wait_queue_head_t       wait;
         struct uio_info         *info;
-	spinlock_t		info_lock;
+	struct mutex		info_lock;
         struct kobject          *map_dir;
         struct kobject          *portio_dir;
 };
diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h
index a710e28b5215..6b708434b7f9 100644
--- a/include/linux/usb/audio-v3.h
+++ b/include/linux/usb/audio-v3.h
@@ -387,6 +387,12 @@ struct uac3_interrupt_data_msg {
 #define UAC3_CONNECTORS			0x0f
 #define UAC3_POWER_DOMAIN		0x10
 
+/* A.20 PROCESSING UNIT PROCESS TYPES */
+#define UAC3_PROCESS_UNDEFINED		0x00
+#define UAC3_PROCESS_UP_DOWNMIX		0x01
+#define UAC3_PROCESS_STEREO_EXTENDER	0x02
+#define UAC3_PROCESS_MULTI_FUNCTION	0x03
+
 /* A.22 AUDIO CLASS-SPECIFIC REQUEST CODES */
 /* see audio-v2.h for the rest, which is identical to v2 */
 #define UAC3_CS_REQ_INTEN			0x04
@@ -406,6 +412,15 @@ struct uac3_interrupt_data_msg {
 #define UAC3_TE_OVERFLOW			0x04
 #define UAC3_TE_LATENCY 			0x05
 
+/* A.23.10 PROCESSING UNITS CONTROL SELECTROS */
+
+/* Up/Down Mixer */
+#define UAC3_UD_MODE_SELECT			0x01
+
+/* Stereo Extender */
+#define UAC3_EXT_WIDTH_CONTROL			0x01
+
+
 /* BADD predefined Unit/Terminal values */
 #define UAC3_BADD_IT_ID1	1  /* Input Terminal ID1: bTerminalID = 1 */
 #define UAC3_BADD_FU_ID2	2  /* Feature Unit ID2: bUnitID = 2 */
@@ -432,4 +447,8 @@ struct uac3_interrupt_data_msg {
 /* BADD sample rate is always fixed to 48kHz */
 #define UAC3_BADD_SAMPLING_RATE				48000
 
+/* BADD power domains recovery times in 50us increments */
+#define UAC3_BADD_PD_RECOVER_D1D0			0x0258	/* 30ms */
+#define UAC3_BADD_PD_RECOVER_D2D0			0x1770	/* 300ms */
+
 #endif /* __LINUX_USB_AUDIO_V3_H */
diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h
index 77f0f0af3a71..a34539b7f750 100644
--- a/include/linux/vga_switcheroo.h
+++ b/include/linux/vga_switcheroo.h
@@ -84,8 +84,8 @@ enum vga_switcheroo_state {
  * Client identifier. Audio clients use the same identifier & 0x100.
  */
 enum vga_switcheroo_client_id {
-	VGA_SWITCHEROO_UNKNOWN_ID = -1,
-	VGA_SWITCHEROO_IGD,
+	VGA_SWITCHEROO_UNKNOWN_ID = 0x1000,
+	VGA_SWITCHEROO_IGD = 0,
 	VGA_SWITCHEROO_DIS,
 	VGA_SWITCHEROO_MAX_CLIENTS,
 };
@@ -151,7 +151,7 @@ int vga_switcheroo_register_client(struct pci_dev *dev,
 				   bool driver_power_control);
 int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 					 const struct vga_switcheroo_client_ops *ops,
-					 enum vga_switcheroo_client_id id);
+					 struct pci_dev *vga_dev);
 
 void vga_switcheroo_client_fb_set(struct pci_dev *dev,
 				  struct fb_info *info);
@@ -180,7 +180,7 @@ static inline int vga_switcheroo_register_handler(const struct vga_switcheroo_ha
 		enum vga_switcheroo_handler_flags_t handler_flags) { return 0; }
 static inline int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 	const struct vga_switcheroo_client_ops *ops,
-	enum vga_switcheroo_client_id id) { return 0; }
+	struct pci_dev *vga_dev) { return 0; }
 static inline void vga_switcheroo_unregister_handler(void) {}
 static inline enum vga_switcheroo_handler_flags_t vga_switcheroo_handler_flags(void) { return 0; }
 static inline int vga_switcheroo_lock_ddc(struct pci_dev *pdev) { return -ENODEV; }
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 9324ac2d9ff2..43913ae79f64 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -64,7 +64,8 @@ struct vsock_sock {
 	struct list_head pending_links;
 	struct list_head accept_queue;
 	bool rejected;
-	struct delayed_work dwork;
+	struct delayed_work connect_work;
+	struct delayed_work pending_work;
 	struct delayed_work close_work;
 	bool close_work_scheduled;
 	u32 peer_shutdown;
@@ -77,7 +78,6 @@ struct vsock_sock {
 
 s64 vsock_stream_has_data(struct vsock_sock *vsk);
 s64 vsock_stream_has_space(struct vsock_sock *vsk);
-void vsock_pending_work(struct work_struct *work);
 struct sock *__vsock_create(struct net *net,
 			    struct socket *sock,
 			    struct sock *parent,
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 53ce8176c313..ec9d6bc65855 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -271,7 +271,7 @@ int  bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		     int flags);
 int  bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 			    size_t len, int flags);
-__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events);
+__poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait);
 int  bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int  bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo);
 int  bt_sock_wait_ready(struct sock *sk, unsigned long flags);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5fbfe61f41c6..1beb3ead0385 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5835,10 +5835,11 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 /**
  * cfg80211_rx_control_port - notification about a received control port frame
  * @dev: The device the frame matched to
- * @buf: control port frame
- * @len: length of the frame data
- * @addr: The peer from which the frame was received
- * @proto: frame protocol, typically PAE or Pre-authentication
+ * @skb: The skbuf with the control port frame.  It is assumed that the skbuf
+ *	is 802.3 formatted (with 802.3 header).  The skb can be non-linear.
+ *	This function does not take ownership of the skb, so the caller is
+ *	responsible for any cleanup.  The caller must also ensure that
+ *	skb->protocol is set appropriately.
  * @unencrypted: Whether the frame was received unencrypted
  *
  * This function is used to inform userspace about a received control port
@@ -5851,8 +5852,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
  * Return: %true if the frame was passed to userspace
  */
 bool cfg80211_rx_control_port(struct net_device *dev,
-			      const u8 *buf, size_t len,
-			      const u8 *addr, u16 proto, bool unencrypted);
+			      struct sk_buff *skb, bool unencrypted);
 
 /**
  * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 71b9043aa0e7..3d4930528db0 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -281,6 +281,11 @@ static inline void fib6_info_hold(struct fib6_info *f6i)
 	atomic_inc(&f6i->fib6_ref);
 }
 
+static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
+{
+	return atomic_inc_not_zero(&f6i->fib6_ref);
+}
+
 static inline void fib6_info_release(struct fib6_info *f6i)
 {
 	if (f6i && atomic_dec_and_test(&f6i->fib6_ref))
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 59656fc580df..7b9c82de11cc 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -66,6 +66,12 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
 		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
 }
 
+static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
+{
+	return (f6i->fib6_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
+	       RTF_GATEWAY;
+}
+
 void ip6_route_input(struct sk_buff *skb);
 struct dst_entry *ip6_route_input_lookup(struct net *net,
 					 struct net_device *dev,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 16475c269749..8f73be494503 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -355,14 +355,7 @@ struct ipv6_txoptions *ipv6_dup_options(struct sock *sk,
 struct ipv6_txoptions *ipv6_renew_options(struct sock *sk,
 					  struct ipv6_txoptions *opt,
 					  int newtype,
-					  struct ipv6_opt_hdr __user *newopt,
-					  int newoptlen);
-struct ipv6_txoptions *
-ipv6_renew_options_kern(struct sock *sk,
-			struct ipv6_txoptions *opt,
-			int newtype,
-			struct ipv6_opt_hdr *newopt,
-			int newoptlen);
+					  struct ipv6_opt_hdr *newopt);
 struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
 					  struct ipv6_txoptions *opt);
 
@@ -830,7 +823,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 	 * to minimize possbility that any useful information to an
 	 * attacker is leaked. Only lower 20 bits are relevant.
 	 */
-	rol32(hash, 16);
+	hash = rol32(hash, 16);
 
 	flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 
@@ -1107,6 +1100,8 @@ void ipv6_sysctl_unregister(void);
 
 int ipv6_sock_mc_join(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
+int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex,
+			  const struct in6_addr *addr, unsigned int mode);
 int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 #endif /* _NET_IPV6_H */
diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h
index b0eaeb02d46d..f4c21b5a1242 100644
--- a/include/net/iucv/af_iucv.h
+++ b/include/net/iucv/af_iucv.h
@@ -153,6 +153,8 @@ struct iucv_sock_list {
 	atomic_t	  autobind_name;
 };
 
+__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
+			    poll_table *wait);
 void iucv_sock_link(struct iucv_sock_list *l, struct sock *s);
 void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s);
 void iucv_accept_enqueue(struct sock *parent, struct sock *sk);
diff --git a/include/net/llc.h b/include/net/llc.h
index dc35f25eb679..890a87318014 100644
--- a/include/net/llc.h
+++ b/include/net/llc.h
@@ -116,6 +116,11 @@ static inline void llc_sap_hold(struct llc_sap *sap)
 	refcount_inc(&sap->refcnt);
 }
 
+static inline bool llc_sap_hold_safe(struct llc_sap *sap)
+{
+	return refcount_inc_not_zero(&sap->refcnt);
+}
+
 void llc_sap_close(struct llc_sap *sap);
 
 static inline void llc_sap_put(struct llc_sap *sap)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 47e35cce3b64..a71264d75d7f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -128,6 +128,7 @@ struct net {
 #endif
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 	struct netns_nf_frag	nf_frag;
+	struct ctl_table_header *nf_frag_frags_hdr;
 #endif
 	struct sock		*nfnl;
 	struct sock		*nfnl_stash;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 08c005ce56e9..dc417ef0a0c5 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -150,6 +150,7 @@ static inline void nft_data_debug(const struct nft_data *data)
  *	@portid: netlink portID of the original message
  *	@seq: netlink sequence number
  *	@family: protocol family
+ *	@level: depth of the chains
  *	@report: notify via unicast netlink message
  */
 struct nft_ctx {
@@ -160,6 +161,7 @@ struct nft_ctx {
 	u32				portid;
 	u32				seq;
 	u8				family;
+	u8				level;
 	bool				report;
 };
 
@@ -865,7 +867,6 @@ enum nft_chain_flags {
  *	@table: table that this chain belongs to
  *	@handle: chain handle
  *	@use: number of jump references to this chain
- *	@level: length of longest path to this chain
  *	@flags: bitmask of enum nft_chain_flags
  *	@name: name of the chain
  */
@@ -878,7 +879,6 @@ struct nft_chain {
 	struct nft_table		*table;
 	u64				handle;
 	u32				use;
-	u16				level;
 	u8				flags:6,
 					genmask:2;
 	char				*name;
@@ -1124,7 +1124,6 @@ struct nft_flowtable {
 	u32				genmask:2,
 					use:30;
 	u64				handle;
-	char				*dev_name[NFT_FLOWTABLE_DEVICE_MAX];
 	/* runtime data below here */
 	struct nf_hook_ops		*ops ____cacheline_aligned;
 	struct nf_flowtable		data;
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index e0c0c2558ec4..a05134507e7b 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -65,4 +65,10 @@ extern const struct nft_expr_ops nft_payload_fast_ops;
 extern struct static_key_false nft_counters_enabled;
 extern struct static_key_false nft_trace_enabled;
 
+extern struct nft_set_type nft_set_rhash_type;
+extern struct nft_set_type nft_set_hash_type;
+extern struct nft_set_type nft_set_hash_fast_type;
+extern struct nft_set_type nft_set_rbtree_type;
+extern struct nft_set_type nft_set_bitmap_type;
+
 #endif /* _NET_NF_TABLES_CORE_H */
diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h
index 9754a50ecde9..4cc64c8446eb 100644
--- a/include/net/netfilter/nf_tproxy.h
+++ b/include/net/netfilter/nf_tproxy.h
@@ -64,7 +64,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
  * belonging to established connections going through that one.
  */
 struct sock *
-nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
 		      const u8 protocol,
 		      const __be32 saddr, const __be32 daddr,
 		      const __be16 sport, const __be16 dport,
@@ -103,7 +103,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
 			    struct sock *sk);
 
 struct sock *
-nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
+nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff,
 		      const u8 protocol,
 		      const struct in6_addr *saddr, const struct in6_addr *daddr,
 		      const __be16 sport, const __be16 dport,
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index c978a31b0f84..762ac9931b62 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -109,7 +109,6 @@ struct netns_ipv6 {
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 struct netns_nf_frag {
-	struct netns_sysctl_ipv6 sysctl;
 	struct netns_frags	frags;
 };
 #endif
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a3c1a2c47cd4..20b059574e60 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -111,6 +111,11 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 {
 }
 
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+	return false;
+}
+
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
 	return NULL;
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 30b3e2fe240a..8c2caa370e0f 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -109,7 +109,8 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 int sctp_inet_listen(struct socket *sock, int backlog);
 void sctp_write_space(struct sock *sk);
 void sctp_data_ready(struct sock *sk);
-__poll_t sctp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t sctp_poll(struct file *file, struct socket *sock,
+		poll_table *wait);
 void sctp_sock_rfree(struct sk_buff *skb);
 void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 		    struct sctp_association *asoc);
diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h
index 9470fd7e4350..32d2454c0479 100644
--- a/include/net/tc_act/tc_csum.h
+++ b/include/net/tc_act/tc_csum.h
@@ -7,7 +7,6 @@
 #include <linux/tc_act/tc_csum.h>
 
 struct tcf_csum_params {
-	int action;
 	u32 update_flags;
 	struct rcu_head rcu;
 };
diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h
index efef0b4b1b2b..46b8c7f1c8d5 100644
--- a/include/net/tc_act/tc_tunnel_key.h
+++ b/include/net/tc_act/tc_tunnel_key.h
@@ -18,7 +18,6 @@
 struct tcf_tunnel_key_params {
 	struct rcu_head		rcu;
 	int			tcft_action;
-	int			action;
 	struct metadata_dst     *tcft_enc_metadata;
 };
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0448e7c5d2b4..cd3ecda9386a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -342,6 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 			struct pipe_inode_info *pipe, size_t len,
 			unsigned int flags);
 
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
 {
@@ -388,7 +389,8 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
 void tcp_init_transfer(struct sock *sk, int bpf_op);
-__poll_t tcp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t tcp_poll(struct file *file, struct socket *sock,
+		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
 int tcp_setsockopt(struct sock *sk, int level, int optname,
@@ -538,6 +540,7 @@ void tcp_send_fin(struct sock *sk);
 void tcp_send_active_reset(struct sock *sk, gfp_t priority);
 int tcp_send_synack(struct sock *);
 void tcp_push_one(struct sock *, unsigned int mss_now);
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
 void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
@@ -827,6 +830,10 @@ struct tcp_skb_cb {
 
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
 
+static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
+{
+	TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
+}
 
 #if IS_ENABLED(CONFIG_IPV6)
 /* This is the variant of inet6_iif() that must be used by TCP,
@@ -834,6 +841,11 @@ struct tcp_skb_cb {
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
 {
+	return TCP_SKB_CB(skb)->header.h6.iif;
+}
+
+static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb)
+{
 	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 
 	return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
@@ -907,8 +919,6 @@ enum tcp_ca_event {
 	CA_EVENT_LOSS,		/* loss timeout */
 	CA_EVENT_ECN_NO_CE,	/* ECT set, but not CE marked */
 	CA_EVENT_ECN_IS_CE,	/* received CE marked IP packet */
-	CA_EVENT_DELAYED_ACK,	/* Delayed ack is sent */
-	CA_EVENT_NON_DELAYED_ACK,
 };
 
 /* Information about inbound ACK, passed to cong_ops->in_ack_event() */
diff --git a/include/net/tls.h b/include/net/tls.h
index 7f84ea3e217c..70c273777fe9 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -109,7 +109,8 @@ struct tls_sw_context_rx {
 
 	struct strparser strp;
 	void (*saved_data_ready)(struct sock *sk);
-	__poll_t (*sk_poll_mask)(struct socket *sock, __poll_t events);
+	unsigned int (*sk_poll)(struct file *file, struct socket *sock,
+				struct poll_table_struct *wait);
 	struct sk_buff *recv_pkt;
 	u8 control;
 	bool decrypted;
@@ -224,7 +225,8 @@ void tls_sw_free_resources_tx(struct sock *sk);
 void tls_sw_free_resources_rx(struct sock *sk);
 int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		   int nonblock, int flags, int *addr_len);
-__poll_t tls_sw_poll_mask(struct socket *sock, __poll_t events);
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+			 struct poll_table_struct *wait);
 ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
 			   struct pipe_inode_info *pipe,
 			   size_t len, unsigned int flags);
diff --git a/include/net/udp.h b/include/net/udp.h
index b1ea8b0f5e6a..81afdacd4fff 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -285,7 +285,7 @@ int udp_init_sock(struct sock *sk);
 int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int __udp_disconnect(struct sock *sk, int flags);
 int udp_disconnect(struct sock *sk, int flags);
-__poll_t udp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features,
 				       bool is_ipv6);
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 9fe472f2ac95..7161856bcf9c 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -60,6 +60,10 @@ struct xdp_sock {
 	bool zc;
 	/* Protects multiple processes in the control path */
 	struct mutex mutex;
+	/* Mutual exclusion of NAPI TX thread and sendmsg error paths
+	 * in the SKB destructor callback.
+	 */
+	spinlock_t tx_completion_lock;
 	u64 rx_dropped;
 };
 
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index aaf1e971c6a3..c891ada3c5c2 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -4,6 +4,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/blkdev.h>
+#include <linux/t10-pi.h>
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/timer.h>
@@ -14,8 +15,6 @@
 struct Scsi_Host;
 struct scsi_driver;
 
-#include <scsi/scsi_device.h>
-
 /*
  * MAX_COMMAND_SIZE is:
  * The longest fixed-length SCSI CDB as per the SCSI standard.
@@ -120,11 +119,11 @@ struct scsi_cmnd {
 	struct request *request;	/* The command we are
 				   	   working on */
 
-#define SCSI_SENSE_BUFFERSIZE 	96
 	unsigned char *sense_buffer;
 				/* obtained by REQUEST SENSE when
 				 * CHECK CONDITION is received on original
-				 * command (auto-sense) */
+				 * command (auto-sense). Length must be
+				 * SCSI_SENSE_BUFFERSIZE bytes. */
 
 	/* Low-level done function - can be used by low-level driver to point
 	 *        to completion function.  Not used by mid/upper level code. */
@@ -313,12 +312,6 @@ static inline unsigned int scsi_prot_interval(struct scsi_cmnd *scmd)
 	return scmd->device->sector_size;
 }
 
-static inline u32 scsi_prot_ref_tag(struct scsi_cmnd *scmd)
-{
-	return blk_rq_pos(scmd->request) >>
-		(ilog2(scsi_prot_interval(scmd)) - 9) & 0xffffffff;
-}
-
 static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd)
 {
 	return cmd->prot_sdb ? cmd->prot_sdb->table.nents : 0;
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 4c36af6edd79..202f4d6a4342 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -17,6 +17,8 @@ struct scsi_sense_hdr;
 
 typedef __u64 __bitwise blist_flags_t;
 
+#define SCSI_SENSE_BUFFERSIZE	96
+
 struct scsi_mode_data {
 	__u32	length;
 	__u16	block_descriptor_length;
@@ -426,11 +428,21 @@ extern const char *scsi_device_state_name(enum scsi_device_state);
 extern int scsi_is_sdev_device(const struct device *);
 extern int scsi_is_target_device(const struct device *);
 extern void scsi_sanitize_inquiry_string(unsigned char *s, int len);
-extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+extern int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 			int data_direction, void *buffer, unsigned bufflen,
 			unsigned char *sense, struct scsi_sense_hdr *sshdr,
 			int timeout, int retries, u64 flags,
 			req_flags_t rq_flags, int *resid);
+/* Make sure any sense buffer is the correct size. */
+#define scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense,	\
+		     sshdr, timeout, retries, flags, rq_flags, resid)	\
+({									\
+	BUILD_BUG_ON((sense) != NULL &&					\
+		     sizeof(sense) != SCSI_SENSE_BUFFERSIZE);		\
+	__scsi_execute(sdev, cmd, data_direction, buffer, bufflen,	\
+		       sense, sshdr, timeout, retries, flags, rq_flags,	\
+		       resid);						\
+})
 static inline int scsi_execute_req(struct scsi_device *sdev,
 	const unsigned char *cmd, int data_direction, void *buffer,
 	unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout,
diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h
new file mode 100644
index 000000000000..619e07c75da9
--- /dev/null
+++ b/include/soc/qcom/rpmh.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __SOC_QCOM_RPMH_H__
+#define __SOC_QCOM_RPMH_H__
+
+#include <soc/qcom/tcs.h>
+#include <linux/platform_device.h>
+
+
+#if IS_ENABLED(CONFIG_QCOM_RPMH)
+int rpmh_write(const struct device *dev, enum rpmh_state state,
+	       const struct tcs_cmd *cmd, u32 n);
+
+int rpmh_write_async(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 n);
+
+int rpmh_write_batch(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 *n);
+
+int rpmh_flush(const struct device *dev);
+
+int rpmh_invalidate(const struct device *dev);
+
+#else
+
+static inline int rpmh_write(const struct device *dev, enum rpmh_state state,
+			     const struct tcs_cmd *cmd, u32 n)
+{ return -ENODEV; }
+
+static inline int rpmh_write_async(const struct device *dev,
+				   enum rpmh_state state,
+				   const struct tcs_cmd *cmd, u32 n)
+{ return -ENODEV; }
+
+static inline int rpmh_write_batch(const struct device *dev,
+				   enum rpmh_state state,
+				   const struct tcs_cmd *cmd, u32 *n)
+{ return -ENODEV; }
+
+static inline int rpmh_flush(const struct device *dev)
+{ return -ENODEV; }
+
+static inline int rpmh_invalidate(const struct device *dev)
+{ return -ENODEV; }
+
+#endif /* CONFIG_QCOM_RPMH */
+
+#endif /* __SOC_QCOM_RPMH_H__ */
diff --git a/include/soc/qcom/tcs.h b/include/soc/qcom/tcs.h
new file mode 100644
index 000000000000..262876a59e86
--- /dev/null
+++ b/include/soc/qcom/tcs.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __SOC_QCOM_TCS_H__
+#define __SOC_QCOM_TCS_H__
+
+#define MAX_RPMH_PAYLOAD	16
+
+/**
+ * rpmh_state: state for the request
+ *
+ * RPMH_SLEEP_STATE:       State of the resource when the processor subsystem
+ *                         is powered down. There is no client using the
+ *                         resource actively.
+ * RPMH_WAKE_ONLY_STATE:   Resume resource state to the value previously
+ *                         requested before the processor was powered down.
+ * RPMH_ACTIVE_ONLY_STATE: Active or AMC mode requests. Resource state
+ *                         is aggregated immediately.
+ */
+enum rpmh_state {
+	RPMH_SLEEP_STATE,
+	RPMH_WAKE_ONLY_STATE,
+	RPMH_ACTIVE_ONLY_STATE,
+};
+
+/**
+ * struct tcs_cmd: an individual request to RPMH.
+ *
+ * @addr: the address of the resource slv_id:18:16 | offset:0:15
+ * @data: the resource state request
+ * @wait: wait for this request to be complete before sending the next
+ */
+struct tcs_cmd {
+	u32 addr;
+	u32 data;
+	u32 wait;
+};
+
+/**
+ * struct tcs_request: A set of tcs_cmds sent together in a TCS
+ *
+ * @state:          state for the request.
+ * @wait_for_compl: wait until we get a response from the h/w accelerator
+ * @num_cmds:       the number of @cmds in this request
+ * @cmds:           an array of tcs_cmds
+ */
+struct tcs_request {
+	enum rpmh_state state;
+	u32 wait_for_compl;
+	u32 num_cmds;
+	struct tcs_cmd *cmds;
+};
+
+#endif /* __SOC_QCOM_TCS_H__ */
diff --git a/include/sound/ac97/codec.h b/include/sound/ac97/codec.h
index ec04be9ab119..9792d25fa369 100644
--- a/include/sound/ac97/codec.h
+++ b/include/sound/ac97/codec.h
@@ -1,10 +1,8 @@
-/*
- *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
+/* SPDX-License-Identifier: GPL-2.0
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
  */
+
 #ifndef __SOUND_AC97_CODEC2_H
 #define __SOUND_AC97_CODEC2_H
 
diff --git a/include/sound/ac97/compat.h b/include/sound/ac97/compat.h
index 1351cba40048..57e19afa31ab 100644
--- a/include/sound/ac97/compat.h
+++ b/include/sound/ac97/compat.h
@@ -1,14 +1,11 @@
-/*
- *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
+/* SPDX-License-Identifier: GPL-2.0
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
  *
  * This file is for backward compatibility with snd_ac97 structure and its
  * multiple usages, such as the snd_ac97_bus and snd_ac97_build_ops.
- *
  */
+
 #ifndef AC97_COMPAT_H
 #define AC97_COMPAT_H
 
diff --git a/include/sound/ac97/controller.h b/include/sound/ac97/controller.h
index b36ecdd64f14..06b5afb7fa6b 100644
--- a/include/sound/ac97/controller.h
+++ b/include/sound/ac97/controller.h
@@ -1,10 +1,8 @@
-/*
- *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
+/* SPDX-License-Identifier: GPL-2.0
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
  */
+
 #ifndef AC97_CONTROLLER_H
 #define AC97_CONTROLLER_H
 
diff --git a/include/sound/ac97/regs.h b/include/sound/ac97/regs.h
index 9a4fa0c3264a..843f73f3705a 100644
--- a/include/sound/ac97/regs.h
+++ b/include/sound/ac97/regs.h
@@ -1,27 +1,11 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0+
+ *
  *  Copyright (c) by Jaroslav Kysela <perex@perex.cz>
  *  Universal interface for Audio Codec '97
  *
  *  For more details look to AC '97 component specification revision 2.1
  *  by Intel Corporation (http://developer.intel.com).
- *
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  */
-
 /*
  *  AC'97 codec registers
  */
diff --git a/include/sound/ac97_codec.h b/include/sound/ac97_codec.h
index 89d311a503d3..cc383991c0fe 100644
--- a/include/sound/ac97_codec.h
+++ b/include/sound/ac97_codec.h
@@ -1,30 +1,15 @@
-#ifndef __SOUND_AC97_CODEC_H
-#define __SOUND_AC97_CODEC_H
-
-/*
+/* SPDX-License-Identifier: GPL-2.0+
+ *
  *  Copyright (c) by Jaroslav Kysela <perex@perex.cz>
  *  Universal interface for Audio Codec '97
  *
  *  For more details look to AC '97 component specification revision 2.1
  *  by Intel Corporation (http://developer.intel.com).
- *
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  */
 
+#ifndef __SOUND_AC97_CODEC_H
+#define __SOUND_AC97_CODEC_H
+
 #include <linux/bitops.h>
 #include <linux/device.h>
 #include <linux/workqueue.h>
diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 9924bc9cbc7c..ea8c93bbb0e0 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -1,27 +1,12 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  *  compress_driver.h - compress offload driver definations
  *
  *  Copyright (C) 2011 Intel Corporation
  *  Authors:	Vinod Koul <vinod.koul@linux.intel.com>
  *		Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
- *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; version 2 of the License.
- *
- *  This program is distributed in the hope that it will be useful, but
- *  WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
  */
+
 #ifndef __COMPRESS_DRIVER_H
 #define __COMPRESS_DRIVER_H
 
diff --git a/include/sound/dmaengine_pcm.h b/include/sound/dmaengine_pcm.h
index e3481eebdd98..2c4cfaa135a6 100644
--- a/include/sound/dmaengine_pcm.h
+++ b/include/sound/dmaengine_pcm.h
@@ -1,17 +1,9 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0+
+ *
  *  Copyright (C) 2012, Analog Devices Inc.
  *	Author: Lars-Peter Clausen <lars@metafoo.de>
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under  the terms of the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the License, or (at your
- *  option) any later version.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  675 Mass Ave, Cambridge, MA 02139, USA.
- *
  */
+
 #ifndef __SOUND_DMAENGINE_PCM_H__
 #define __SOUND_DMAENGINE_PCM_H__
 
diff --git a/include/sound/hda_component.h b/include/sound/hda_component.h
new file mode 100644
index 000000000000..78626cde7081
--- /dev/null
+++ b/include/sound/hda_component.h
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+// HD-Audio helpers to sync with DRM driver
+
+#ifndef __SOUND_HDA_COMPONENT_H
+#define __SOUND_HDA_COMPONENT_H
+
+#include <drm/drm_audio_component.h>
+
+#ifdef CONFIG_SND_HDA_COMPONENT
+int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable);
+int snd_hdac_display_power(struct hdac_bus *bus, bool enable);
+int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid,
+			     int dev_id, int rate);
+int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
+			   bool *audio_enabled, char *buffer, int max_bytes);
+int snd_hdac_acomp_init(struct hdac_bus *bus,
+			const struct drm_audio_component_audio_ops *aops,
+			int (*match_master)(struct device *, void *),
+			size_t extra_size);
+int snd_hdac_acomp_exit(struct hdac_bus *bus);
+int snd_hdac_acomp_register_notifier(struct hdac_bus *bus,
+				    const struct drm_audio_component_audio_ops *ops);
+#else
+static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
+{
+	return 0;
+}
+static inline int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
+{
+	return 0;
+}
+static inline int snd_hdac_sync_audio_rate(struct hdac_device *codec,
+					   hda_nid_t nid, int dev_id, int rate)
+{
+	return 0;
+}
+static inline int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid,
+					 int dev_id, bool *audio_enabled,
+					 char *buffer, int max_bytes)
+{
+	return -ENODEV;
+}
+static inline int snd_hdac_acomp_init(struct hdac_bus *bus,
+				      const struct drm_audio_component_audio_ops *aops,
+				      int (*match_master)(struct device *, void *),
+				      size_t extra_size)
+{
+	return -ENODEV;
+}
+static inline int snd_hdac_acomp_exit(struct hdac_bus *bus)
+{
+	return 0;
+}
+static inline int snd_hdac_acomp_register_notifier(struct hdac_bus *bus,
+						  const struct drm_audio_component_audio_ops *ops)
+{
+	return -ENODEV;
+}
+#endif
+
+#endif /* __SOUND_HDA_COMPONENT_H */
diff --git a/include/sound/hda_i915.h b/include/sound/hda_i915.h
index a94f5b6f92ac..6b79614a893b 100644
--- a/include/sound/hda_i915.h
+++ b/include/sound/hda_i915.h
@@ -5,54 +5,23 @@
 #ifndef __SOUND_HDA_I915_H
 #define __SOUND_HDA_I915_H
 
-#include <drm/i915_component.h>
+#include "hda_component.h"
 
 #ifdef CONFIG_SND_HDA_I915
-int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable);
-int snd_hdac_display_power(struct hdac_bus *bus, bool enable);
 void snd_hdac_i915_set_bclk(struct hdac_bus *bus);
-int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid,
-			     int dev_id, int rate);
-int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
-			   bool *audio_enabled, char *buffer, int max_bytes);
 int snd_hdac_i915_init(struct hdac_bus *bus);
-int snd_hdac_i915_exit(struct hdac_bus *bus);
-int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *);
 #else
-static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
-{
-	return 0;
-}
-static inline int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
-{
-	return 0;
-}
 static inline void snd_hdac_i915_set_bclk(struct hdac_bus *bus)
 {
 }
-static inline int snd_hdac_sync_audio_rate(struct hdac_device *codec,
-					   hda_nid_t nid, int dev_id, int rate)
-{
-	return 0;
-}
-static inline int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid,
-					 int dev_id, bool *audio_enabled,
-					 char *buffer, int max_bytes)
-{
-	return -ENODEV;
-}
 static inline int snd_hdac_i915_init(struct hdac_bus *bus)
 {
 	return -ENODEV;
 }
+#endif
 static inline int snd_hdac_i915_exit(struct hdac_bus *bus)
 {
-	return 0;
+	return snd_hdac_acomp_exit(bus);
 }
-static inline int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *ops)
-{
-	return -ENODEV;
-}
-#endif
 
 #endif /* __SOUND_HDA_I915_H */
diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index c052afc27547..6f1e1f3b3063 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -8,8 +8,10 @@
 
 #include <linux/device.h>
 #include <linux/interrupt.h>
+#include <linux/pm_runtime.h>
 #include <linux/timecounter.h>
 #include <sound/core.h>
+#include <sound/pcm.h>
 #include <sound/memalloc.h>
 #include <sound/hda_verbs.h>
 #include <drm/i915_component.h>
@@ -132,7 +134,7 @@ int snd_hdac_get_sub_nodes(struct hdac_device *codec, hda_nid_t nid,
 			   hda_nid_t *start_id);
 unsigned int snd_hdac_calc_stream_format(unsigned int rate,
 					 unsigned int channels,
-					 unsigned int format,
+					 snd_pcm_format_t format,
 					 unsigned int maxbps,
 					 unsigned short spdif_ctls);
 int snd_hdac_query_supported_pcm(struct hdac_device *codec, hda_nid_t nid,
@@ -171,12 +173,38 @@ int snd_hdac_power_down(struct hdac_device *codec);
 int snd_hdac_power_up_pm(struct hdac_device *codec);
 int snd_hdac_power_down_pm(struct hdac_device *codec);
 int snd_hdac_keep_power_up(struct hdac_device *codec);
+
+/* call this at entering into suspend/resume callbacks in codec driver */
+static inline void snd_hdac_enter_pm(struct hdac_device *codec)
+{
+	atomic_inc(&codec->in_pm);
+}
+
+/* call this at leaving from suspend/resume callbacks in codec driver */
+static inline void snd_hdac_leave_pm(struct hdac_device *codec)
+{
+	atomic_dec(&codec->in_pm);
+}
+
+static inline bool snd_hdac_is_in_pm(struct hdac_device *codec)
+{
+	return atomic_read(&codec->in_pm);
+}
+
+static inline bool snd_hdac_is_power_on(struct hdac_device *codec)
+{
+	return !pm_runtime_suspended(&codec->dev);
+}
 #else
 static inline int snd_hdac_power_up(struct hdac_device *codec) { return 0; }
 static inline int snd_hdac_power_down(struct hdac_device *codec) { return 0; }
 static inline int snd_hdac_power_up_pm(struct hdac_device *codec) { return 0; }
 static inline int snd_hdac_power_down_pm(struct hdac_device *codec) { return 0; }
 static inline int snd_hdac_keep_power_up(struct hdac_device *codec) { return 0; }
+static inline void snd_hdac_enter_pm(struct hdac_device *codec) {}
+static inline void snd_hdac_leave_pm(struct hdac_device *codec) {}
+static inline bool snd_hdac_is_in_pm(struct hdac_device *codec) { return 0; }
+static inline bool snd_hdac_is_power_on(struct hdac_device *codec) { return 1; }
 #endif
 
 /*
@@ -188,6 +216,11 @@ struct hdac_driver {
 	const struct hda_device_id *id_table;
 	int (*match)(struct hdac_device *dev, struct hdac_driver *drv);
 	void (*unsol_event)(struct hdac_device *dev, unsigned int event);
+
+	/* fields used by ext bus APIs */
+	int (*probe)(struct hdac_device *dev);
+	int (*remove)(struct hdac_device *dev);
+	void (*shutdown)(struct hdac_device *dev);
 };
 
 #define drv_to_hdac_driver(_drv) container_of(_drv, struct hdac_driver, driver)
@@ -209,6 +242,14 @@ struct hdac_bus_ops {
 };
 
 /*
+ * ops used for ASoC HDA codec drivers
+ */
+struct hdac_ext_bus_ops {
+	int (*hdev_attach)(struct hdac_device *hdev);
+	int (*hdev_detach)(struct hdac_device *hdev);
+};
+
+/*
  * Lowlevel I/O operators
  */
 struct hdac_io_ops {
@@ -250,11 +291,17 @@ struct hdac_rb {
  * @mlcap: MultiLink capabilities pointer
  * @gtscap: gts capabilities pointer
  * @drsmcap: dma resume capabilities pointer
+ * @num_streams: streams supported
+ * @idx: HDA link index
+ * @hlink_list: link list of HDA links
+ * @lock: lock for link mgmt
+ * @cmd_dma_state: state of cmd DMAs: CORB and RIRB
  */
 struct hdac_bus {
 	struct device *dev;
 	const struct hdac_bus_ops *ops;
 	const struct hdac_io_ops *io_ops;
+	const struct hdac_ext_bus_ops *ext_ops;
 
 	/* h/w resources */
 	unsigned long addr;
@@ -314,9 +361,19 @@ struct hdac_bus {
 	spinlock_t reg_lock;
 	struct mutex cmd_mutex;
 
-	/* i915 component interface */
-	struct i915_audio_component *audio_component;
-	int i915_power_refcount;
+	/* DRM component interface */
+	struct drm_audio_component *audio_component;
+	int drm_power_refcount;
+
+	/* parameters required for enhanced capabilities */
+	int num_streams;
+	int idx;
+
+	struct list_head hlink_list;
+
+	struct mutex lock;
+	bool cmd_dma_state;
+
 };
 
 int snd_hdac_bus_init(struct hdac_bus *bus, struct device *dev,
diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h
index 9c14e21dda85..f34aced69ca8 100644
--- a/include/sound/hdaudio_ext.h
+++ b/include/sound/hdaudio_ext.h
@@ -4,38 +4,16 @@
 
 #include <sound/hdaudio.h>
 
-/**
- * hdac_ext_bus: HDAC extended bus for extended HDA caps
- *
- * @bus: hdac bus
- * @num_streams: streams supported
- * @hlink_list: link list of HDA links
- * @lock: lock for link mgmt
- * @cmd_dma_state: state of cmd DMAs: CORB and RIRB
- */
-struct hdac_ext_bus {
-	struct hdac_bus bus;
-	int num_streams;
-	int idx;
-
-	struct list_head hlink_list;
-
-	struct mutex lock;
-	bool cmd_dma_state;
-};
-
-int snd_hdac_ext_bus_init(struct hdac_ext_bus *sbus, struct device *dev,
+int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 		      const struct hdac_bus_ops *ops,
-		      const struct hdac_io_ops *io_ops);
+		      const struct hdac_io_ops *io_ops,
+		      const struct hdac_ext_bus_ops *ext_ops);
 
-void snd_hdac_ext_bus_exit(struct hdac_ext_bus *sbus);
-int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *sbus, int addr);
+void snd_hdac_ext_bus_exit(struct hdac_bus *bus);
+int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr,
+						struct hdac_device *hdev);
 void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev);
-void snd_hdac_ext_bus_device_remove(struct hdac_ext_bus *ebus);
-
-#define ebus_to_hbus(ebus)	(&(ebus)->bus)
-#define hbus_to_ebus(_bus) \
-	container_of(_bus, struct hdac_ext_bus, bus)
+void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus);
 
 #define HDA_CODEC_REV_EXT_ENTRY(_vid, _rev, _name, drv_data) \
 	{ .vendor_id = (_vid), .rev_id = (_rev), .name = (_name), \
@@ -44,14 +22,14 @@ void snd_hdac_ext_bus_device_remove(struct hdac_ext_bus *ebus);
 #define HDA_CODEC_EXT_ENTRY(_vid, _revid, _name, _drv_data) \
 	HDA_CODEC_REV_EXT_ENTRY(_vid, _revid, _name, _drv_data)
 
-void snd_hdac_ext_bus_ppcap_enable(struct hdac_ext_bus *chip, bool enable);
-void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_ext_bus *chip, bool enable);
+void snd_hdac_ext_bus_ppcap_enable(struct hdac_bus *chip, bool enable);
+void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_bus *chip, bool enable);
 
-void snd_hdac_ext_stream_spbcap_enable(struct hdac_ext_bus *chip,
+void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *chip,
 				 bool enable, int index);
 
-int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_ext_bus *bus);
-struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *bus,
+int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_bus *bus);
+struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_bus *bus,
 						const char *codec_name);
 
 enum hdac_ext_stream_type {
@@ -100,28 +78,28 @@ struct hdac_ext_stream {
 #define stream_to_hdac_ext_stream(s) \
 	container_of(s, struct hdac_ext_stream, hstream)
 
-void snd_hdac_ext_stream_init(struct hdac_ext_bus *bus,
+void snd_hdac_ext_stream_init(struct hdac_bus *bus,
 				struct hdac_ext_stream *stream, int idx,
 				int direction, int tag);
-int snd_hdac_ext_stream_init_all(struct hdac_ext_bus *ebus, int start_idx,
+int snd_hdac_ext_stream_init_all(struct hdac_bus *bus, int start_idx,
 		int num_stream, int dir);
-void snd_hdac_stream_free_all(struct hdac_ext_bus *ebus);
-void snd_hdac_link_free_all(struct hdac_ext_bus *ebus);
-struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_ext_bus *bus,
+void snd_hdac_stream_free_all(struct hdac_bus *bus);
+void snd_hdac_link_free_all(struct hdac_bus *bus);
+struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_bus *bus,
 					   struct snd_pcm_substream *substream,
 					   int type);
 void snd_hdac_ext_stream_release(struct hdac_ext_stream *azx_dev, int type);
-void snd_hdac_ext_stream_decouple(struct hdac_ext_bus *bus,
+void snd_hdac_ext_stream_decouple(struct hdac_bus *bus,
 				struct hdac_ext_stream *azx_dev, bool decouple);
-void snd_hdac_ext_stop_streams(struct hdac_ext_bus *sbus);
+void snd_hdac_ext_stop_streams(struct hdac_bus *bus);
 
-int snd_hdac_ext_stream_set_spib(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_set_spib(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream, u32 value);
-int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream);
-void snd_hdac_ext_stream_drsm_enable(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus,
 				bool enable, int index);
-int snd_hdac_ext_stream_set_dpibr(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_set_dpibr(struct hdac_bus *bus,
 				struct hdac_ext_stream *stream, u32 value);
 int snd_hdac_ext_stream_set_lpib(struct hdac_ext_stream *stream, u32 value);
 
@@ -144,17 +122,15 @@ struct hdac_ext_link {
 
 int snd_hdac_ext_bus_link_power_up(struct hdac_ext_link *link);
 int snd_hdac_ext_bus_link_power_down(struct hdac_ext_link *link);
-int snd_hdac_ext_bus_link_power_up_all(struct hdac_ext_bus *ebus);
-int snd_hdac_ext_bus_link_power_down_all(struct hdac_ext_bus *ebus);
+int snd_hdac_ext_bus_link_power_up_all(struct hdac_bus *bus);
+int snd_hdac_ext_bus_link_power_down_all(struct hdac_bus *bus);
 void snd_hdac_ext_link_set_stream_id(struct hdac_ext_link *link,
 				 int stream);
 void snd_hdac_ext_link_clear_stream_id(struct hdac_ext_link *link,
 				 int stream);
 
-int snd_hdac_ext_bus_link_get(struct hdac_ext_bus *ebus,
-				struct hdac_ext_link *link);
-int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus,
-				struct hdac_ext_link *link);
+int snd_hdac_ext_bus_link_get(struct hdac_bus *bus, struct hdac_ext_link *link);
+int snd_hdac_ext_bus_link_put(struct hdac_bus *bus, struct hdac_ext_link *link);
 
 /* update register macro */
 #define snd_hdac_updatel(addr, reg, mask, val)		\
@@ -181,53 +157,12 @@ struct hda_dai_map {
 	u32	maxbps;
 };
 
-#define HDA_MAX_NIDS 16
-
-/**
- * struct hdac_ext_device - HDAC Ext device
- *
- * @hdac: hdac core device
- * @nid_list - the dai map which matches the dai-name with the nid
- * @map_cur_idx - the idx in use in dai_map
- * @ops - the hda codec ops common to all codec drivers
- * @pvt_data - private data, for asoc contains asoc codec object
- */
-struct hdac_ext_device {
-	struct hdac_device hdev;
-	struct hdac_ext_bus *ebus;
-
-	/* soc-dai to nid map */
-	struct hda_dai_map nid_list[HDA_MAX_NIDS];
-	unsigned int map_cur_idx;
-
-	/* codec ops */
-	struct hdac_ext_codec_ops ops;
-
-	struct snd_card *card;
-	void *scodec;
-	void *private_data;
-};
-
 struct hdac_ext_dma_params {
 	u32 format;
 	u8 stream_tag;
 };
-#define to_ehdac_device(dev) (container_of((dev), \
-				 struct hdac_ext_device, hdev))
-/*
- * HD-audio codec base driver
- */
-struct hdac_ext_driver {
-	struct hdac_driver hdac;
-
-	int	(*probe)(struct hdac_ext_device *dev);
-	int	(*remove)(struct hdac_ext_device *dev);
-	void	(*shutdown)(struct hdac_ext_device *dev);
-};
-
-int snd_hda_ext_driver_register(struct hdac_ext_driver *drv);
-void snd_hda_ext_driver_unregister(struct hdac_ext_driver *drv);
 
-#define to_ehdac_driver(_drv) container_of(_drv, struct hdac_ext_driver, hdac)
+int snd_hda_ext_driver_register(struct hdac_driver *drv);
+void snd_hda_ext_driver_unregister(struct hdac_driver *drv);
 
 #endif /* __SOUND_HDAUDIO_EXT_H */
diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
index 9c3db3dce32b..67561b997915 100644
--- a/include/sound/memalloc.h
+++ b/include/sound/memalloc.h
@@ -24,6 +24,8 @@
 #ifndef __SOUND_MEMALLOC_H
 #define __SOUND_MEMALLOC_H
 
+#include <asm/page.h>
+
 struct device;
 
 /*
@@ -67,6 +69,14 @@ struct snd_dma_buffer {
 	void *private_data;	/* private for allocator; don't touch */
 };
 
+/*
+ * return the pages matching with the given byte size
+ */
+static inline unsigned int snd_sgbuf_aligned_pages(size_t size)
+{
+	return (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+}
+
 #ifdef CONFIG_SND_DMA_SGBUF
 /*
  * Scatter-Gather generic device pages
@@ -91,14 +101,6 @@ struct snd_sg_buf {
 };
 
 /*
- * return the pages matching with the given byte size
- */
-static inline unsigned int snd_sgbuf_aligned_pages(size_t size)
-{
-	return (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
-}
-
-/*
  * return the physical address at the corresponding offset
  */
 static inline dma_addr_t snd_sgbuf_get_addr(struct snd_dma_buffer *dmab,
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index e054c583d3b3..d6bd3caf6878 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -462,6 +462,7 @@ struct snd_pcm_substream {
         /* -- timer section -- */
 	struct snd_timer *timer;		/* timer */
 	unsigned timer_running: 1;	/* time is running */
+	long wait_time;	/* time in ms for R/W to wait for avail */
 	/* -- next substream -- */
 	struct snd_pcm_substream *next;
 	/* -- linked substreams -- */
@@ -1089,14 +1090,14 @@ static inline snd_pcm_sframes_t
 snd_pcm_lib_write(struct snd_pcm_substream *substream,
 		  const void __user *buf, snd_pcm_uframes_t frames)
 {
-	return __snd_pcm_lib_xfer(substream, (void *)buf, true, frames, false);
+	return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false);
 }
 
 static inline snd_pcm_sframes_t
 snd_pcm_lib_read(struct snd_pcm_substream *substream,
 		 void __user *buf, snd_pcm_uframes_t frames)
 {
-	return __snd_pcm_lib_xfer(substream, (void *)buf, true, frames, false);
+	return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false);
 }
 
 static inline snd_pcm_sframes_t
@@ -1341,8 +1342,6 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s
 #define snd_pcm_lib_mmap_iomem	NULL
 #endif
 
-#define snd_pcm_lib_mmap_vmalloc NULL
-
 /**
  * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer
  * @dma: DMA number
diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index c704357775fc..2dd37cada7c0 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -87,6 +87,13 @@ static inline void snd_mask_set(struct snd_mask *mask, unsigned int val)
 	mask->bits[MASK_OFS(val)] |= MASK_BIT(val);
 }
 
+/* Most of drivers need only this one */
+static inline void snd_mask_set_format(struct snd_mask *mask,
+				       snd_pcm_format_t format)
+{
+	snd_mask_set(mask, (__force unsigned int)format);
+}
+
 static inline void snd_mask_reset(struct snd_mask *mask, unsigned int val)
 {
 	mask->bits[MASK_OFS(val)] &= ~MASK_BIT(val);
@@ -369,8 +376,7 @@ static inline int params_physical_width(const struct snd_pcm_hw_params *p)
 static inline void
 params_set_format(struct snd_pcm_hw_params *p, snd_pcm_format_t fmt)
 {
-	snd_mask_set(hw_param_mask(p, SNDRV_PCM_HW_PARAM_FORMAT),
-		(__force int)fmt);
+	snd_mask_set_format(hw_param_mask(p, SNDRV_PCM_HW_PARAM_FORMAT), fmt);
 }
 
 #endif /* __SOUND_PCM_PARAMS_H */
diff --git a/include/sound/pxa2xx-lib.h b/include/sound/pxa2xx-lib.h
index 63f75450d3db..6758fc12fa84 100644
--- a/include/sound/pxa2xx-lib.h
+++ b/include/sound/pxa2xx-lib.h
@@ -8,20 +8,23 @@
 /* PCM */
 struct snd_pcm_substream;
 struct snd_pcm_hw_params;
+struct snd_soc_pcm_runtime;
 struct snd_pcm;
 
-extern int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
+extern int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *params);
-extern int __pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream);
+extern int pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream);
 extern int pxa2xx_pcm_trigger(struct snd_pcm_substream *substream, int cmd);
 extern snd_pcm_uframes_t pxa2xx_pcm_pointer(struct snd_pcm_substream *substream);
-extern int __pxa2xx_pcm_prepare(struct snd_pcm_substream *substream);
-extern int __pxa2xx_pcm_open(struct snd_pcm_substream *substream);
-extern int __pxa2xx_pcm_close(struct snd_pcm_substream *substream);
+extern int pxa2xx_pcm_prepare(struct snd_pcm_substream *substream);
+extern int pxa2xx_pcm_open(struct snd_pcm_substream *substream);
+extern int pxa2xx_pcm_close(struct snd_pcm_substream *substream);
 extern int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream,
 	struct vm_area_struct *vma);
 extern int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream);
 extern void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm);
+extern int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd);
+extern const struct snd_pcm_ops pxa2xx_pcm_ops;
 
 /* AC97 */
 
diff --git a/include/sound/rt5682.h b/include/sound/rt5682.h
new file mode 100644
index 000000000000..0251797ab438
--- /dev/null
+++ b/include/sound/rt5682.h
@@ -0,0 +1,40 @@
+/*
+ * linux/sound/rt5682.h -- Platform data for RT5682
+ *
+ * Copyright 2018 Realtek Microelectronics
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_SND_RT5682_H
+#define __LINUX_SND_RT5682_H
+
+enum rt5682_dmic1_data_pin {
+	RT5682_DMIC1_NULL,
+	RT5682_DMIC1_DATA_GPIO2,
+	RT5682_DMIC1_DATA_GPIO5,
+};
+
+enum rt5682_dmic1_clk_pin {
+	RT5682_DMIC1_CLK_GPIO1,
+	RT5682_DMIC1_CLK_GPIO3,
+};
+
+enum rt5682_jd_src {
+	RT5682_JD_NULL,
+	RT5682_JD1,
+};
+
+struct rt5682_platform_data {
+
+	int ldo1_en; /* GPIO for LDO1_EN */
+
+	enum rt5682_dmic1_data_pin dmic1_data_pin;
+	enum rt5682_dmic1_clk_pin dmic1_clk_pin;
+	enum rt5682_jd_src jd_src;
+};
+
+#endif
+
diff --git a/include/sound/sb16_csp.h b/include/sound/sb16_csp.h
index c7c7788005e4..7817e88bd08d 100644
--- a/include/sound/sb16_csp.h
+++ b/include/sound/sb16_csp.h
@@ -46,7 +46,7 @@ enum {
 struct snd_sb_csp_ops {
 	int (*csp_use) (struct snd_sb_csp * p);
 	int (*csp_unuse) (struct snd_sb_csp * p);
-	int (*csp_autoload) (struct snd_sb_csp * p, int pcm_sfmt, int play_rec_mode);
+	int (*csp_autoload) (struct snd_sb_csp * p, snd_pcm_format_t pcm_sfmt, int play_rec_mode);
 	int (*csp_start) (struct snd_sb_csp * p, int sample_width, int channels);
 	int (*csp_stop) (struct snd_sb_csp * p);
 	int (*csp_qsound_transfer) (struct snd_sb_csp * p);
diff --git a/include/sound/seq_midi_event.h b/include/sound/seq_midi_event.h
index e40f43e6fc7b..2f135bccf457 100644
--- a/include/sound/seq_midi_event.h
+++ b/include/sound/seq_midi_event.h
@@ -43,10 +43,8 @@ void snd_midi_event_free(struct snd_midi_event *dev);
 void snd_midi_event_reset_encode(struct snd_midi_event *dev);
 void snd_midi_event_reset_decode(struct snd_midi_event *dev);
 void snd_midi_event_no_status(struct snd_midi_event *dev, int on);
-/* encode from byte stream - return number of written bytes if success */
-long snd_midi_event_encode(struct snd_midi_event *dev, unsigned char *buf, long count,
-			   struct snd_seq_event *ev);
-int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c, struct snd_seq_event *ev);
+bool snd_midi_event_encode_byte(struct snd_midi_event *dev, unsigned char c,
+				struct snd_seq_event *ev);
 /* decode from event to bytes - return number of written bytes if success */
 long snd_midi_event_decode(struct snd_midi_event *dev, unsigned char *buf, long count,
 			   struct snd_seq_event *ev);
diff --git a/include/sound/seq_virmidi.h b/include/sound/seq_virmidi.h
index 695257ae64ac..796ce7772213 100644
--- a/include/sound/seq_virmidi.h
+++ b/include/sound/seq_virmidi.h
@@ -36,11 +36,12 @@ struct snd_virmidi {
 	int seq_mode;
 	int client;
 	int port;
-	unsigned int trigger: 1;
+	bool trigger;
 	struct snd_midi_event *parser;
 	struct snd_seq_event event;
 	struct snd_virmidi_dev *rdev;
 	struct snd_rawmidi_substream *substream;
+	struct work_struct output_work;
 };
 
 #define SNDRV_VIRMIDI_SUBSCRIBE		(1<<0)
diff --git a/include/sound/sh_fsi.h b/include/sound/sh_fsi.h
index 7a9710b4b799..89eafe23ef88 100644
--- a/include/sound/sh_fsi.h
+++ b/include/sound/sh_fsi.h
@@ -1,16 +1,13 @@
-#ifndef __SOUND_FSI_H
-#define __SOUND_FSI_H
-
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * Fifo-attached Serial Interface (FSI) support for SH7724
  *
  * Copyright (C) 2009 Renesas Solutions Corp.
  * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
+#ifndef __SOUND_FSI_H
+#define __SOUND_FSI_H
+
 #include <linux/clk.h>
 #include <sound/soc.h>
 
diff --git a/include/sound/simple_card.h b/include/sound/simple_card.h
index a6a2e1547092..d264e5463f22 100644
--- a/include/sound/simple_card.h
+++ b/include/sound/simple_card.h
@@ -1,12 +1,9 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * ASoC simple sound card support
  *
  * Copyright (C) 2012 Renesas Solutions Corp.
  * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __SIMPLE_CARD_H
diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
index 7e25afce6566..8bc5e2d8b13c 100644
--- a/include/sound/simple_card_utils.h
+++ b/include/sound/simple_card_utils.h
@@ -1,17 +1,20 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * simple_card_utils.h
  *
  * Copyright (c) 2016 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
+
 #ifndef __SIMPLE_CARD_UTILS_H
 #define __SIMPLE_CARD_UTILS_H
 
 #include <sound/soc.h>
 
+#define asoc_simple_card_init_hp(card, sjack, prefix) \
+	asoc_simple_card_init_jack(card, sjack, 1, prefix)
+#define asoc_simple_card_init_mic(card, sjack, prefix) \
+	asoc_simple_card_init_jack(card, sjack, 0, prefix)
+
 struct asoc_simple_dai {
 	const char *name;
 	unsigned int sysclk;
@@ -28,6 +31,12 @@ struct asoc_simple_card_data {
 	u32 convert_channels;
 };
 
+struct asoc_simple_jack {
+	struct snd_soc_jack jack;
+	struct snd_soc_jack_pin pin;
+	struct snd_soc_jack_gpio gpio;
+};
+
 int asoc_simple_card_parse_daifmt(struct device *dev,
 				  struct device_node *node,
 				  struct device_node *codec,
@@ -107,4 +116,8 @@ int asoc_simple_card_of_parse_routing(struct snd_soc_card *card,
 int asoc_simple_card_of_parse_widgets(struct snd_soc_card *card,
 				      char *prefix);
 
+int asoc_simple_card_init_jack(struct snd_soc_card *card,
+			       struct asoc_simple_jack *sjack,
+			       int is_hp, char *prefix);
+
 #endif /* __SIMPLE_CARD_UTILS_H */
diff --git a/include/sound/soc-acpi-intel-match.h b/include/sound/soc-acpi-intel-match.h
index 9da6388c20a1..bb1d24b703fb 100644
--- a/include/sound/soc-acpi-intel-match.h
+++ b/include/sound/soc-acpi-intel-match.h
@@ -1,16 +1,6 @@
-
-/*
- * Copyright (C) 2017, Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+/* SPDX-License-Identifier: GPL-2.0
  *
+ * Copyright (C) 2017, Intel Corporation. All rights reserved.
  */
 
 #ifndef __LINUX_SND_SOC_ACPI_INTEL_MATCH_H
@@ -29,5 +19,10 @@ extern struct snd_soc_acpi_mach snd_soc_acpi_intel_broadwell_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_legacy_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cherrytrail_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_skl_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_kbl_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_bxt_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[];
 
 #endif
diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h
index 082224275f52..e45b2330d16a 100644
--- a/include/sound/soc-acpi.h
+++ b/include/sound/soc-acpi.h
@@ -1,15 +1,6 @@
-/*
- * Copyright (C) 2013-15, Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+/* SPDX-License-Identifier: GPL-2.0
  *
+ * Copyright (C) 2013-15, Intel Corporation. All rights reserved.
  */
 
 #ifndef __LINUX_SND_SOC_ACPI_H
diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index e6f8c40ed43c..f5d70041108f 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -1,12 +1,9 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc-dai.h -- ALSA SoC Layer
  *
  * Copyright:	2005-2008 Wolfson Microelectronics. PLC.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Digital Audio Interface (DAI) API.
  */
 
@@ -141,6 +138,11 @@ int snd_soc_dai_set_tristate(struct snd_soc_dai *dai, int tristate);
 int snd_soc_dai_digital_mute(struct snd_soc_dai *dai, int mute,
 			     int direction);
 
+
+int snd_soc_dai_get_channel_map(struct snd_soc_dai *dai,
+		unsigned int *tx_num, unsigned int *tx_slot,
+		unsigned int *rx_num, unsigned int *rx_slot);
+
 int snd_soc_dai_is_dummy(struct snd_soc_dai *dai);
 
 struct snd_soc_dai_ops {
@@ -168,6 +170,9 @@ struct snd_soc_dai_ops {
 	int (*set_channel_map)(struct snd_soc_dai *dai,
 		unsigned int tx_num, unsigned int *tx_slot,
 		unsigned int rx_num, unsigned int *rx_slot);
+	int (*get_channel_map)(struct snd_soc_dai *dai,
+			unsigned int *tx_num, unsigned int *tx_slot,
+			unsigned int *rx_num, unsigned int *rx_slot);
 	int (*set_tristate)(struct snd_soc_dai *dai, int tristate);
 
 	int (*set_sdw_stream)(struct snd_soc_dai *dai,
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index a6ce2de4e20a..af9ef16cc34d 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -1,13 +1,10 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc-dapm.h -- ALSA SoC Dynamic Audio Power Management
  *
- * Author:		Liam Girdwood
- * Created:		Aug 11th 2005
+ * Author:	Liam Girdwood
+ * Created:	Aug 11th 2005
  * Copyright:	Wolfson Microelectronics. PLC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_SND_SOC_DAPM_H
diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h
index 806059052bfc..9bb92f187af8 100644
--- a/include/sound/soc-dpcm.h
+++ b/include/sound/soc-dpcm.h
@@ -1,11 +1,8 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc-dpcm.h -- ALSA SoC Dynamic PCM Support
  *
  * Author:		Liam Girdwood <lrg@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_SND_SOC_DPCM_H
diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h
index f552c3f56368..fa4b8413d2e2 100644
--- a/include/sound/soc-topology.h
+++ b/include/sound/soc-topology.h
@@ -1,13 +1,10 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc-topology.h -- ALSA SoC Firmware Controls and DAPM
  *
  * Copyright (C) 2012 Texas Instruments Inc.
  * Copyright (C) 2015 Intel Corporation.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Simple file API to load FW that includes mixers, coefficients, DAPM graphs,
  * algorithms, equalisers, DAIs, widgets, FE caps, BE caps, codec link caps etc.
  */
@@ -30,6 +27,9 @@ struct snd_soc_dapm_context;
 struct snd_soc_card;
 struct snd_kcontrol_new;
 struct snd_soc_dai_link;
+struct snd_soc_dai_driver;
+struct snd_soc_dai;
+struct snd_soc_dapm_route;
 
 /* object scan be loaded and unloaded in groups with identfying indexes */
 #define SND_SOC_TPLG_INDEX_ALL	0	/* ID that matches all FW objects */
@@ -109,35 +109,44 @@ struct snd_soc_tplg_widget_events {
 struct snd_soc_tplg_ops {
 
 	/* external kcontrol init - used for any driver specific init */
-	int (*control_load)(struct snd_soc_component *,
+	int (*control_load)(struct snd_soc_component *, int index,
 		struct snd_kcontrol_new *, struct snd_soc_tplg_ctl_hdr *);
 	int (*control_unload)(struct snd_soc_component *,
 		struct snd_soc_dobj *);
 
+	/* DAPM graph route element loading and unloading */
+	int (*dapm_route_load)(struct snd_soc_component *, int index,
+		struct snd_soc_dapm_route *route);
+	int (*dapm_route_unload)(struct snd_soc_component *,
+		struct snd_soc_dobj *);
+
 	/* external widget init - used for any driver specific init */
-	int (*widget_load)(struct snd_soc_component *,
+	int (*widget_load)(struct snd_soc_component *, int index,
 		struct snd_soc_dapm_widget *,
 		struct snd_soc_tplg_dapm_widget *);
-	int (*widget_ready)(struct snd_soc_component *,
+	int (*widget_ready)(struct snd_soc_component *, int index,
 		struct snd_soc_dapm_widget *,
 		struct snd_soc_tplg_dapm_widget *);
 	int (*widget_unload)(struct snd_soc_component *,
 		struct snd_soc_dobj *);
 
 	/* FE DAI - used for any driver specific init */
-	int (*dai_load)(struct snd_soc_component *,
-		struct snd_soc_dai_driver *dai_drv);
+	int (*dai_load)(struct snd_soc_component *, int index,
+		struct snd_soc_dai_driver *dai_drv,
+		struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai);
+
 	int (*dai_unload)(struct snd_soc_component *,
 		struct snd_soc_dobj *);
 
 	/* DAI link - used for any driver specific init */
-	int (*link_load)(struct snd_soc_component *,
-		struct snd_soc_dai_link *link);
+	int (*link_load)(struct snd_soc_component *, int index,
+		struct snd_soc_dai_link *link,
+		struct snd_soc_tplg_link_config *cfg);
 	int (*link_unload)(struct snd_soc_component *,
 		struct snd_soc_dobj *);
 
 	/* callback to handle vendor bespoke data */
-	int (*vendor_load)(struct snd_soc_component *,
+	int (*vendor_load)(struct snd_soc_component *, int index,
 		struct snd_soc_tplg_hdr *);
 	int (*vendor_unload)(struct snd_soc_component *,
 		struct snd_soc_tplg_hdr *);
@@ -146,7 +155,7 @@ struct snd_soc_tplg_ops {
 	void (*complete)(struct snd_soc_component *);
 
 	/* manifest - optional to inform component of manifest */
-	int (*manifest)(struct snd_soc_component *,
+	int (*manifest)(struct snd_soc_component *, int index,
 		struct snd_soc_tplg_manifest *);
 
 	/* vendor specific kcontrol handlers available for binding */
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 1378dcd2128a..41cec42fb456 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1,13 +1,10 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc.h -- ALSA SoC Layer
  *
- * Author:		Liam Girdwood
- * Created:		Aug 11th 2005
+ * Author:	Liam Girdwood
+ * Created:	Aug 11th 2005
  * Copyright:	Wolfson Microelectronics. PLC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_SND_SOC_H
@@ -806,6 +803,14 @@ struct snd_soc_component_driver {
 	unsigned int use_pmdown_time:1; /* care pmdown_time at stop */
 	unsigned int endianness:1;
 	unsigned int non_legacy_dai_naming:1;
+
+	/* this component uses topology and ignore machine driver FEs */
+	const char *ignore_machine;
+	const char *topology_name_prefix;
+	int (*be_hw_params_fixup)(struct snd_soc_pcm_runtime *rtd,
+				  struct snd_pcm_hw_params *params);
+	bool use_dai_pcm_id;	/* use the DAI link PCM ID as PCM device number */
+	int be_pcm_base;	/* base device ID for all BE PCMs */
 };
 
 struct snd_soc_component {
@@ -957,10 +962,17 @@ struct snd_soc_dai_link {
 
 	/* DPCM used FE & BE merged format */
 	unsigned int dpcm_merged_format:1;
+	/* DPCM used FE & BE merged channel */
+	unsigned int dpcm_merged_chan:1;
+	/* DPCM used FE & BE merged rate */
+	unsigned int dpcm_merged_rate:1;
 
 	/* pmdown_time is ignored at stop */
 	unsigned int ignore_pmdown_time:1;
 
+	/* Do not create a PCM for this DAI link (Backend link) */
+	unsigned int ignore:1;
+
 	struct list_head list; /* DAI link list of the soc card */
 	struct snd_soc_dobj dobj; /* For topology */
 };
@@ -1000,6 +1012,7 @@ struct snd_soc_card {
 	const char *long_name;
 	const char *driver_name;
 	char dmi_longname[80];
+	char topology_shortname[32];
 
 	struct device *dev;
 	struct snd_card *snd_card;
@@ -1009,6 +1022,7 @@ struct snd_soc_card {
 	struct mutex dapm_mutex;
 
 	bool instantiated;
+	bool topology_shortname_created;
 
 	int (*probe)(struct snd_soc_card *card);
 	int (*late_probe)(struct snd_soc_card *card);
@@ -1412,6 +1426,9 @@ int snd_soc_of_parse_card_name(struct snd_soc_card *card,
 			       const char *propname);
 int snd_soc_of_parse_audio_simple_widgets(struct snd_soc_card *card,
 					  const char *propname);
+int snd_soc_of_get_slot_mask(struct device_node *np,
+			     const char *prop_name,
+			     unsigned int *mask);
 int snd_soc_of_parse_tdm_slot(struct device_node *np,
 			      unsigned int *tx_mask,
 			      unsigned int *rx_mask,
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 39b94ec965be..b401c4e36394 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -374,7 +374,7 @@ DECLARE_EVENT_CLASS(
 		__entry->extent_type	= btrfs_file_extent_type(l, fi);
 		__entry->compression	= btrfs_file_extent_compression(l, fi);
 		__entry->extent_start	= start;
-		__entry->extent_end	= (start + btrfs_file_extent_inline_len(l, slot, fi));
+		__entry->extent_end	= (start + btrfs_file_extent_ram_bytes(l, fi));
 	),
 
 	TP_printk_btrfs(
@@ -433,7 +433,6 @@ DEFINE_EVENT(
 		{ (1 << BTRFS_ORDERED_DIRECT),	 	"DIRECT" 	}, \
 		{ (1 << BTRFS_ORDERED_IOERR), 		"IOERR" 	}, \
 		{ (1 << BTRFS_ORDERED_UPDATED_ISIZE), 	"UPDATED_ISIZE"	}, \
-		{ (1 << BTRFS_ORDERED_LOGGED_CSUM), 	"LOGGED_CSUM"	}, \
 		{ (1 << BTRFS_ORDERED_TRUNCATED), 	"TRUNCATED"	})
 
 
diff --git a/include/trace/events/clk.h b/include/trace/events/clk.h
index 2cd449328aee..9004ffff7f32 100644
--- a/include/trace/events/clk.h
+++ b/include/trace/events/clk.h
@@ -192,6 +192,42 @@ DEFINE_EVENT(clk_phase, clk_set_phase_complete,
 	TP_ARGS(core, phase)
 );
 
+DECLARE_EVENT_CLASS(clk_duty_cycle,
+
+	TP_PROTO(struct clk_core *core, struct clk_duty *duty),
+
+	TP_ARGS(core, duty),
+
+	TP_STRUCT__entry(
+		__string(        name,           core->name              )
+		__field( unsigned int,           num                     )
+		__field( unsigned int,           den                     )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, core->name);
+		__entry->num = duty->num;
+		__entry->den = duty->den;
+	),
+
+	TP_printk("%s %u/%u", __get_str(name), (unsigned int)__entry->num,
+		  (unsigned int)__entry->den)
+);
+
+DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle,
+
+	TP_PROTO(struct clk_core *core, struct clk_duty *duty),
+
+	TP_ARGS(core, duty)
+);
+
+DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle_complete,
+
+	TP_PROTO(struct clk_core *core, struct clk_duty *duty),
+
+	TP_ARGS(core, duty)
+);
+
 #endif /* _TRACE_CLK_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index d1faf3597b9d..68b17c116907 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -112,8 +112,11 @@ DEFINE_EVENT(filelock_lock, locks_remove_posix,
 		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
 		TP_ARGS(inode, fl, ret));
 
-DECLARE_EVENT_CLASS(filelock_lease,
+DEFINE_EVENT(filelock_lock, flock_lock_inode,
+		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
+		TP_ARGS(inode, fl, ret));
 
+DECLARE_EVENT_CLASS(filelock_lease,
 	TP_PROTO(struct inode *inode, struct file_lock *fl),
 
 	TP_ARGS(inode, fl),
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 908977d69783..f7aece721aed 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -5,6 +5,7 @@
 #if !defined(_TRACE_POWER_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_POWER_H
 
+#include <linux/cpufreq.h>
 #include <linux/ktime.h>
 #include <linux/pm_qos.h>
 #include <linux/tracepoint.h>
@@ -148,6 +149,30 @@ DEFINE_EVENT(cpu, cpu_frequency,
 	TP_ARGS(frequency, cpu_id)
 );
 
+TRACE_EVENT(cpu_frequency_limits,
+
+	TP_PROTO(struct cpufreq_policy *policy),
+
+	TP_ARGS(policy),
+
+	TP_STRUCT__entry(
+		__field(u32, min_freq)
+		__field(u32, max_freq)
+		__field(u32, cpu_id)
+	),
+
+	TP_fast_assign(
+		__entry->min_freq = policy->min;
+		__entry->max_freq = policy->max;
+		__entry->cpu_id = policy->cpu;
+	),
+
+	TP_printk("min=%lu max=%lu cpu_id=%lu",
+		  (unsigned long)__entry->min_freq,
+		  (unsigned long)__entry->max_freq,
+		  (unsigned long)__entry->cpu_id)
+);
+
 TRACE_EVENT(device_pm_callback_start,
 
 	TP_PROTO(struct device *dev, const char *pm_ops, int event),
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 5936aac357ab..a8d07feff6a0 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -52,6 +52,7 @@ TRACE_EVENT(rcu_utilization,
  *	"cpuqs": CPU passes through a quiescent state.
  *	"cpuonl": CPU comes online.
  *	"cpuofl": CPU goes offline.
+ *	"cpuofl-bgp": CPU goes offline while blocking a grace period.
  *	"reqwait": GP kthread sleeps waiting for grace-period request.
  *	"reqwaitsig": GP kthread awakened by signal from reqwait state.
  *	"fqswait": GP kthread waiting until time to force quiescent states.
@@ -63,24 +64,24 @@ TRACE_EVENT(rcu_utilization,
  */
 TRACE_EVENT(rcu_grace_period,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, const char *gpevent),
 
-	TP_ARGS(rcuname, gpnum, gpevent),
+	TP_ARGS(rcuname, gp_seq, gpevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(const char *, gpevent)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->gpevent = gpevent;
 	),
 
 	TP_printk("%s %lu %s",
-		  __entry->rcuname, __entry->gpnum, __entry->gpevent)
+		  __entry->rcuname, __entry->gp_seq, __entry->gpevent)
 );
 
 /*
@@ -90,8 +91,8 @@ TRACE_EVENT(rcu_grace_period,
  *
  * "Startleaf": Request a grace period based on leaf-node data.
  * "Prestarted": Someone beat us to the request
- * "Startedleaf": Leaf-node start proved sufficient.
- * "Startedleafroot": Leaf-node start proved sufficient after checking root.
+ * "Startedleaf": Leaf node marked for future GP.
+ * "Startedleafroot": All nodes from leaf to root marked for future GP.
  * "Startedroot": Requested a nocb grace period based on root-node data.
  * "NoGPkthread": The RCU grace-period kthread has not yet started.
  * "StartWait": Start waiting for the requested grace period.
@@ -102,17 +103,16 @@ TRACE_EVENT(rcu_grace_period,
  */
 TRACE_EVENT(rcu_future_grace_period,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed,
-		 unsigned long c, u8 level, int grplo, int grphi,
+	TP_PROTO(const char *rcuname, unsigned long gp_seq,
+		 unsigned long gp_seq_req, u8 level, int grplo, int grphi,
 		 const char *gpevent),
 
-	TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent),
+	TP_ARGS(rcuname, gp_seq, gp_seq_req, level, grplo, grphi, gpevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
-		__field(unsigned long, completed)
-		__field(unsigned long, c)
+		__field(unsigned long, gp_seq)
+		__field(unsigned long, gp_seq_req)
 		__field(u8, level)
 		__field(int, grplo)
 		__field(int, grphi)
@@ -121,19 +121,17 @@ TRACE_EVENT(rcu_future_grace_period,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
-		__entry->completed = completed;
-		__entry->c = c;
+		__entry->gp_seq = gp_seq;
+		__entry->gp_seq_req = gp_seq_req;
 		__entry->level = level;
 		__entry->grplo = grplo;
 		__entry->grphi = grphi;
 		__entry->gpevent = gpevent;
 	),
 
-	TP_printk("%s %lu %lu %lu %u %d %d %s",
-		  __entry->rcuname, __entry->gpnum, __entry->completed,
-		  __entry->c, __entry->level, __entry->grplo, __entry->grphi,
-		  __entry->gpevent)
+	TP_printk("%s %lu %lu %u %d %d %s",
+		  __entry->rcuname, __entry->gp_seq, __entry->gp_seq_req, __entry->level,
+		  __entry->grplo, __entry->grphi, __entry->gpevent)
 );
 
 /*
@@ -145,14 +143,14 @@ TRACE_EVENT(rcu_future_grace_period,
  */
 TRACE_EVENT(rcu_grace_period_init,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level,
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, u8 level,
 		 int grplo, int grphi, unsigned long qsmask),
 
-	TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask),
+	TP_ARGS(rcuname, gp_seq, level, grplo, grphi, qsmask),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(u8, level)
 		__field(int, grplo)
 		__field(int, grphi)
@@ -161,7 +159,7 @@ TRACE_EVENT(rcu_grace_period_init,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->level = level;
 		__entry->grplo = grplo;
 		__entry->grphi = grphi;
@@ -169,7 +167,7 @@ TRACE_EVENT(rcu_grace_period_init,
 	),
 
 	TP_printk("%s %lu %u %d %d %lx",
-		  __entry->rcuname, __entry->gpnum, __entry->level,
+		  __entry->rcuname, __entry->gp_seq, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->qsmask)
 );
 
@@ -301,24 +299,24 @@ TRACE_EVENT(rcu_nocb_wake,
  */
 TRACE_EVENT(rcu_preempt_task,
 
-	TP_PROTO(const char *rcuname, int pid, unsigned long gpnum),
+	TP_PROTO(const char *rcuname, int pid, unsigned long gp_seq),
 
-	TP_ARGS(rcuname, pid, gpnum),
+	TP_ARGS(rcuname, pid, gp_seq),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(int, pid)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->pid = pid;
 	),
 
 	TP_printk("%s %lu %d",
-		  __entry->rcuname, __entry->gpnum, __entry->pid)
+		  __entry->rcuname, __entry->gp_seq, __entry->pid)
 );
 
 /*
@@ -328,23 +326,23 @@ TRACE_EVENT(rcu_preempt_task,
  */
 TRACE_EVENT(rcu_unlock_preempted_task,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, int pid),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, int pid),
 
-	TP_ARGS(rcuname, gpnum, pid),
+	TP_ARGS(rcuname, gp_seq, pid),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(int, pid)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->pid = pid;
 	),
 
-	TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid)
+	TP_printk("%s %lu %d", __entry->rcuname, __entry->gp_seq, __entry->pid)
 );
 
 /*
@@ -357,15 +355,15 @@ TRACE_EVENT(rcu_unlock_preempted_task,
  */
 TRACE_EVENT(rcu_quiescent_state_report,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum,
+	TP_PROTO(const char *rcuname, unsigned long gp_seq,
 		 unsigned long mask, unsigned long qsmask,
 		 u8 level, int grplo, int grphi, int gp_tasks),
 
-	TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks),
+	TP_ARGS(rcuname, gp_seq, mask, qsmask, level, grplo, grphi, gp_tasks),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(unsigned long, mask)
 		__field(unsigned long, qsmask)
 		__field(u8, level)
@@ -376,7 +374,7 @@ TRACE_EVENT(rcu_quiescent_state_report,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->mask = mask;
 		__entry->qsmask = qsmask;
 		__entry->level = level;
@@ -386,41 +384,41 @@ TRACE_EVENT(rcu_quiescent_state_report,
 	),
 
 	TP_printk("%s %lu %lx>%lx %u %d %d %u",
-		  __entry->rcuname, __entry->gpnum,
+		  __entry->rcuname, __entry->gp_seq,
 		  __entry->mask, __entry->qsmask, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->gp_tasks)
 );
 
 /*
  * Tracepoint for quiescent states detected by force_quiescent_state().
- * These trace events include the type of RCU, the grace-period number that
- * was blocked by the CPU, the CPU itself, and the type of quiescent state,
- * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick"
- * when kicking a CPU that has been in dyntick-idle mode for too long, or
- * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr.
+ * These trace events include the type of RCU, the grace-period number
+ * that was blocked by the CPU, the CPU itself, and the type of quiescent
+ * state, which can be "dti" for dyntick-idle mode, "kick" when kicking
+ * a CPU that has been in dyntick-idle mode for too long, or "rqc" if the
+ * CPU got a quiescent state via its rcu_qs_ctr.
  */
 TRACE_EVENT(rcu_fqs,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, int cpu, const char *qsevent),
 
-	TP_ARGS(rcuname, gpnum, cpu, qsevent),
+	TP_ARGS(rcuname, gp_seq, cpu, qsevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(int, cpu)
 		__field(const char *, qsevent)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->cpu = cpu;
 		__entry->qsevent = qsevent;
 	),
 
 	TP_printk("%s %lu %d %s",
-		  __entry->rcuname, __entry->gpnum,
+		  __entry->rcuname, __entry->gp_seq,
 		  __entry->cpu, __entry->qsevent)
 );
 
@@ -753,23 +751,23 @@ TRACE_EVENT(rcu_barrier,
 
 #else /* #ifdef CONFIG_RCU_TRACE */
 
-#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
-#define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \
+#define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0)
+#define trace_rcu_future_grace_period(rcuname, gp_seq, gp_seq_req, \
 				      level, grplo, grphi, event) \
 				      do { } while (0)
-#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
+#define trace_rcu_grace_period_init(rcuname, gp_seq, level, grplo, grphi, \
 				    qsmask) do { } while (0)
 #define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \
 	do { } while (0)
 #define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \
 	do { } while (0)
 #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0)
-#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
-#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
-#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
+#define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0)
+#define trace_rcu_unlock_preempted_task(rcuname, gp_seq, pid) do { } while (0)
+#define trace_rcu_quiescent_state_report(rcuname, gp_seq, mask, qsmask, level, \
 					 grplo, grphi, gp_tasks) do { } \
 	while (0)
-#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
+#define trace_rcu_fqs(rcuname, gp_seq, cpu, qsevent) do { } while (0)
 #define trace_rcu_dyntick(polarity, oldnesting, newnesting, dyntick) do { } while (0)
 #define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0)
 #define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 42990676a55e..df4bedb9b01c 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -734,9 +734,11 @@ __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 __SYSCALL(__NR_statx,     sys_statx)
 #define __NR_io_pgetevents 292
 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+#define __NR_rseq 293
+__SYSCALL(__NR_rseq, sys_rseq)
 
 #undef __NR_syscalls
-#define __NR_syscalls 293
+#define __NR_syscalls 294
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index d00221345c19..ce43d340f010 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -29,7 +29,6 @@
 
 #include <linux/types.h>
 #include <linux/fs.h>
-#include <linux/signal.h>
 #include <asm/byteorder.h>
 
 typedef __kernel_ulong_t aio_context_t;
@@ -108,10 +107,5 @@ struct iocb {
 #undef IFBIG
 #undef IFLITTLE
 
-struct __aio_sigset {
-	const sigset_t __user	*sigmask;
-	size_t		sigsetsize;
-};
-
 #endif /* __LINUX__AIO_ABI_H */
 
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
index 821f71a2e48f..8d19e02d752a 100644
--- a/include/uapi/linux/bcache.h
+++ b/include/uapi/linux/bcache.h
@@ -195,7 +195,7 @@ struct cache_sb {
 	};
 	};
 
-	__u32			last_mount;	/* time_t */
+	__u32			last_mount;	/* time overflow in y2106 */
 
 	__u16			first_bucket;
 	union {
@@ -318,7 +318,7 @@ struct uuid_entry {
 		struct {
 			__u8	uuid[16];
 			__u8	label[32];
-			__u32	first_reg;
+			__u32	first_reg; /* time overflow in y2106 */
 			__u32	last_reg;
 			__u32	invalidated;
 
diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index e3c70fe6bf0f..ff5a5db8906a 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -117,7 +117,7 @@ struct blk_zone_report {
 	__u32		nr_zones;
 	__u8		reserved[4];
 	struct blk_zone zones[0];
-} __packed;
+};
 
 /**
  * struct blk_zone_range - BLKRESETZONE ioctl request
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 59b19b6a40d7..b7db3261c62d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1857,7 +1857,8 @@ union bpf_attr {
  *		is resolved), the nexthop address is returned in ipv4_dst
  *		or ipv6_dst based on family, smac is set to mac address of
  *		egress device, dmac is set to nexthop mac address, rt_metric
- *		is set to metric from route (IPv4/IPv6 only).
+ *		is set to metric from route (IPv4/IPv6 only), and ifindex
+ *		is set to the device index of the nexthop from the FIB lookup.
  *
  *             *plen* argument is the size of the passed in struct.
  *             *flags* argument can be a combination of one or more of the
@@ -1873,9 +1874,10 @@ union bpf_attr {
  *             *ctx* is either **struct xdp_md** for XDP programs or
  *             **struct sk_buff** tc cls_act programs.
  *     Return
- *             Egress device index on success, 0 if packet needs to continue
- *             up the stack for further processing or a negative error in case
- *             of failure.
+ *		* < 0 if any input argument is invalid
+ *		*   0 on success (packet is forwarded, nexthop neighbor exists)
+ *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ *		*     packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
@@ -2612,6 +2614,18 @@ struct bpf_raw_tracepoint_args {
 #define BPF_FIB_LOOKUP_DIRECT  BIT(0)
 #define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
 
+enum {
+	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
+	BPF_FIB_LKUP_RET_BLACKHOLE,    /* dest is blackholed; can be dropped */
+	BPF_FIB_LKUP_RET_UNREACHABLE,  /* dest is unreachable; can be dropped */
+	BPF_FIB_LKUP_RET_PROHIBIT,     /* dest not allowed; can be dropped */
+	BPF_FIB_LKUP_RET_NOT_FWDED,    /* packet is not forwarded */
+	BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
+	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
+	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+};
+
 struct bpf_fib_lookup {
 	/* input:  network family for lookup (AF_INET, AF_INET6)
 	 * output: network family of egress nexthop
@@ -2625,7 +2639,11 @@ struct bpf_fib_lookup {
 
 	/* total length of packet from network header - used for MTU check */
 	__u16	tot_len;
-	__u32	ifindex;  /* L3 device index for lookup */
+
+	/* input: L3 device index for lookup
+	 * output: device index from FIB lookup
+	 */
+	__u32	ifindex;
 
 	union {
 		/* inputs to lookup */
diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 0b5ddbe135a4..972265f32871 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -76,7 +76,7 @@ struct btf_type {
  */
 #define BTF_INT_ENCODING(VAL)	(((VAL) & 0x0f000000) >> 24)
 #define BTF_INT_OFFSET(VAL)	(((VAL  & 0x00ff0000)) >> 16)
-#define BTF_INT_BITS(VAL)	((VAL)  & 0x0000ffff)
+#define BTF_INT_BITS(VAL)	((VAL)  & 0x000000ff)
 
 /* Attributes stored in the BTF_INT_ENCODING */
 #define BTF_INT_SIGNED	(1 << 0)
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 4e12c423b9fe..c5358e0ae7c5 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -422,6 +422,8 @@ typedef struct elf64_shdr {
 #define NT_ARM_SVE	0x405		/* ARM Scalable Vector Extension registers */
 #define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
 #define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
+#define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
+#define NT_MIPS_FP_MODE	0x801		/* MIPS floating-point mode */
 
 /* Note header in a PT_NOTE section */
 typedef struct elf32_note {
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 4ca65b56084f..7363f18e65a5 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -226,7 +226,7 @@ enum tunable_id {
 	ETHTOOL_TX_COPYBREAK,
 	ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */
 	/*
-	 * Add your fresh new tubale attribute above and remember to update
+	 * Add your fresh new tunable attribute above and remember to update
 	 * tunable_strings[] in net/core/ethtool.c
 	 */
 	__ETHTOOL_TUNABLE_COUNT,
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index b6270a3b38e9..b955b986b341 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -949,6 +949,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
 #define KVM_CAP_HYPERV_TLBFLUSH 155
+#define KVM_CAP_S390_HPAGE_1M 156
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b8e288a1f740..eeb787b1c53c 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -143,6 +143,8 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
+
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
 };
 
 /*
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index d620fa43756c..9a402fdb60e9 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -10,13 +10,8 @@
  * Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
  */
 
-#ifdef __KERNEL__
-# include <linux/types.h>
-#else
-# include <stdint.h>
-#endif
-
-#include <linux/types_32_64.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
 
 enum rseq_cpu_id_state {
 	RSEQ_CPU_ID_UNINITIALIZED		= -1,
@@ -52,10 +47,10 @@ struct rseq_cs {
 	__u32 version;
 	/* enum rseq_cs_flags */
 	__u32 flags;
-	LINUX_FIELD_u32_u64(start_ip);
+	__u64 start_ip;
 	/* Offset from start_ip. */
-	LINUX_FIELD_u32_u64(post_commit_offset);
-	LINUX_FIELD_u32_u64(abort_ip);
+	__u64 post_commit_offset;
+	__u64 abort_ip;
 } __attribute__((aligned(4 * sizeof(__u64))));
 
 /*
@@ -67,28 +62,30 @@ struct rseq_cs {
 struct rseq {
 	/*
 	 * Restartable sequences cpu_id_start field. Updated by the
-	 * kernel, and read by user-space with single-copy atomicity
-	 * semantics. Aligned on 32-bit. Always contains a value in the
-	 * range of possible CPUs, although the value may not be the
-	 * actual current CPU (e.g. if rseq is not initialized). This
-	 * CPU number value should always be compared against the value
-	 * of the cpu_id field before performing a rseq commit or
-	 * returning a value read from a data structure indexed using
-	 * the cpu_id_start value.
+	 * kernel. Read by user-space with single-copy atomicity
+	 * semantics. This field should only be read by the thread which
+	 * registered this data structure. Aligned on 32-bit. Always
+	 * contains a value in the range of possible CPUs, although the
+	 * value may not be the actual current CPU (e.g. if rseq is not
+	 * initialized). This CPU number value should always be compared
+	 * against the value of the cpu_id field before performing a rseq
+	 * commit or returning a value read from a data structure indexed
+	 * using the cpu_id_start value.
 	 */
 	__u32 cpu_id_start;
 	/*
-	 * Restartable sequences cpu_id field. Updated by the kernel,
-	 * and read by user-space with single-copy atomicity semantics.
-	 * Aligned on 32-bit. Values RSEQ_CPU_ID_UNINITIALIZED and
-	 * RSEQ_CPU_ID_REGISTRATION_FAILED have a special semantic: the
-	 * former means "rseq uninitialized", and latter means "rseq
-	 * initialization failed". This value is meant to be read within
-	 * rseq critical sections and compared with the cpu_id_start
-	 * value previously read, before performing the commit instruction,
-	 * or read and compared with the cpu_id_start value before returning
-	 * a value loaded from a data structure indexed using the
-	 * cpu_id_start value.
+	 * Restartable sequences cpu_id field. Updated by the kernel.
+	 * Read by user-space with single-copy atomicity semantics. This
+	 * field should only be read by the thread which registered this
+	 * data structure. Aligned on 32-bit. Values
+	 * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED
+	 * have a special semantic: the former means "rseq uninitialized",
+	 * and latter means "rseq initialization failed". This value is
+	 * meant to be read within rseq critical sections and compared
+	 * with the cpu_id_start value previously read, before performing
+	 * the commit instruction, or read and compared with the
+	 * cpu_id_start value before returning a value loaded from a data
+	 * structure indexed using the cpu_id_start value.
 	 */
 	__u32 cpu_id;
 	/*
@@ -105,27 +102,44 @@ struct rseq {
 	 * targeted by the rseq_cs. Also needs to be set to NULL by user-space
 	 * before reclaiming memory that contains the targeted struct rseq_cs.
 	 *
-	 * Read and set by the kernel with single-copy atomicity semantics.
-	 * Set by user-space with single-copy atomicity semantics. Aligned
-	 * on 64-bit.
+	 * Read and set by the kernel. Set by user-space with single-copy
+	 * atomicity semantics. This field should only be updated by the
+	 * thread which registered this data structure. Aligned on 64-bit.
 	 */
-	LINUX_FIELD_u32_u64(rseq_cs);
+	union {
+		__u64 ptr64;
+#ifdef __LP64__
+		__u64 ptr;
+#else
+		struct {
+#if (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || defined(__BIG_ENDIAN)
+			__u32 padding;		/* Initialized to zero. */
+			__u32 ptr32;
+#else /* LITTLE */
+			__u32 ptr32;
+			__u32 padding;		/* Initialized to zero. */
+#endif /* ENDIAN */
+		} ptr;
+#endif
+	} rseq_cs;
+
 	/*
-	 * - RSEQ_DISABLE flag:
+	 * Restartable sequences flags field.
+	 *
+	 * This field should only be updated by the thread which
+	 * registered this data structure. Read by the kernel.
+	 * Mainly used for single-stepping through rseq critical sections
+	 * with debuggers.
 	 *
-	 * Fallback fast-track flag for single-stepping.
-	 * Set by user-space if lack of progress is detected.
-	 * Cleared by user-space after rseq finish.
-	 * Read by the kernel.
 	 * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT
-	 *     Inhibit instruction sequence block restart and event
-	 *     counter increment on preemption for this thread.
+	 *     Inhibit instruction sequence block restart on preemption
+	 *     for this thread.
 	 * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL
-	 *     Inhibit instruction sequence block restart and event
-	 *     counter increment on signal delivery for this thread.
+	 *     Inhibit instruction sequence block restart on signal
+	 *     delivery for this thread.
 	 * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE
-	 *     Inhibit instruction sequence block restart and event
-	 *     counter increment on migration for this thread.
+	 *     Inhibit instruction sequence block restart on migration for
+	 *     this thread.
 	 */
 	__u32 flags;
 } __attribute__((aligned(4 * sizeof(__u64))));
diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h
index 6e299349b158..b7b57967d90f 100644
--- a/include/uapi/linux/target_core_user.h
+++ b/include/uapi/linux/target_core_user.h
@@ -44,6 +44,7 @@
 #define TCMU_MAILBOX_VERSION 2
 #define ALIGN_SIZE 64 /* Should be enough for most CPUs */
 #define TCMU_MAILBOX_FLAG_CAP_OOOC (1 << 0) /* Out-of-order completions */
+#define TCMU_MAILBOX_FLAG_CAP_READ_LEN (1 << 1) /* Read data length */
 
 struct tcmu_mailbox {
 	__u16 version;
@@ -71,6 +72,7 @@ struct tcmu_cmd_entry_hdr {
 	__u16 cmd_id;
 	__u8 kflags;
 #define TCMU_UFLAG_UNKNOWN_OP 0x1
+#define TCMU_UFLAG_READ_LEN   0x2
 	__u8 uflags;
 
 } __packed;
@@ -119,7 +121,7 @@ struct tcmu_cmd_entry {
 			__u8 scsi_status;
 			__u8 __pad1;
 			__u16 __pad2;
-			__u32 __pad3;
+			__u32 read_len;
 			char sense_buffer[TCMU_SENSE_BUFFERSIZE];
 		} rsp;
 	};
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 29eb659aa77a..e3f6ed8a7064 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -127,6 +127,10 @@ enum {
 
 #define TCP_CM_INQ		TCP_INQ
 
+#define TCP_REPAIR_ON		1
+#define TCP_REPAIR_OFF		0
+#define TCP_REPAIR_OFF_NO_WP	-1	/* Turn off without window probes */
+
 struct tcp_repair_opt {
 	__u32	opt_code;
 	__u32	opt_val;
diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h
index fcf936656493..6b56a2208be7 100644
--- a/include/uapi/linux/time.h
+++ b/include/uapi/linux/time.h
@@ -49,6 +49,13 @@ struct __kernel_timespec {
 };
 #endif
 
+#ifndef __kernel_itimerspec
+struct __kernel_itimerspec {
+	struct __kernel_timespec it_interval;    /* timer period */
+	struct __kernel_timespec it_value;       /* timer expiration */
+};
+#endif
+
 /*
  * legacy timeval structure, only embedded in structures that
  * traditionally used 'timeval' to pass time intervals (not absolute
diff --git a/include/uapi/linux/types_32_64.h b/include/uapi/linux/types_32_64.h
deleted file mode 100644
index 0a87ace34a57..000000000000
--- a/include/uapi/linux/types_32_64.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_TYPES_32_64_H
-#define _UAPI_LINUX_TYPES_32_64_H
-
-/*
- * linux/types_32_64.h
- *
- * Integer type declaration for pointers across 32-bit and 64-bit systems.
- *
- * Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
- */
-
-#ifdef __KERNEL__
-# include <linux/types.h>
-#else
-# include <stdint.h>
-#endif
-
-#include <asm/byteorder.h>
-
-#ifdef __BYTE_ORDER
-# if (__BYTE_ORDER == __BIG_ENDIAN)
-#  define LINUX_BYTE_ORDER_BIG_ENDIAN
-# else
-#  define LINUX_BYTE_ORDER_LITTLE_ENDIAN
-# endif
-#else
-# ifdef __BIG_ENDIAN
-#  define LINUX_BYTE_ORDER_BIG_ENDIAN
-# else
-#  define LINUX_BYTE_ORDER_LITTLE_ENDIAN
-# endif
-#endif
-
-#ifdef __LP64__
-# define LINUX_FIELD_u32_u64(field)			__u64 field
-# define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v)	field = (intptr_t)v
-#else
-# ifdef LINUX_BYTE_ORDER_BIG_ENDIAN
-#  define LINUX_FIELD_u32_u64(field)	__u32 field ## _padding, field
-#  define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v)	\
-	field ## _padding = 0, field = (intptr_t)v
-# else
-#  define LINUX_FIELD_u32_u64(field)	__u32 field, field ## _padding
-#  define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v)	\
-	field = (intptr_t)v, field ## _padding = 0
-# endif
-#endif
-
-#endif /* _UAPI_LINUX_TYPES_32_64_H */
diff --git a/include/uapi/linux/usb/audio.h b/include/uapi/linux/usb/audio.h
index 74e520fb944f..ddc5396800aa 100644
--- a/include/uapi/linux/usb/audio.h
+++ b/include/uapi/linux/usb/audio.h
@@ -390,33 +390,64 @@ static inline __u8 uac_processing_unit_iChannelNames(struct uac_processing_unit_
 static inline __u8 uac_processing_unit_bControlSize(struct uac_processing_unit_descriptor *desc,
 						    int protocol)
 {
-	return (protocol == UAC_VERSION_1) ?
-		desc->baSourceID[desc->bNrInPins + 4] :
-		2; /* in UAC2, this value is constant */
+	switch (protocol) {
+	case UAC_VERSION_1:
+		return desc->baSourceID[desc->bNrInPins + 4];
+	case UAC_VERSION_2:
+		return 2; /* in UAC2, this value is constant */
+	case UAC_VERSION_3:
+		return 4; /* in UAC3, this value is constant */
+	default:
+		return 1;
+	}
 }
 
 static inline __u8 *uac_processing_unit_bmControls(struct uac_processing_unit_descriptor *desc,
 						   int protocol)
 {
-	return (protocol == UAC_VERSION_1) ?
-		&desc->baSourceID[desc->bNrInPins + 5] :
-		&desc->baSourceID[desc->bNrInPins + 6];
+	switch (protocol) {
+	case UAC_VERSION_1:
+		return &desc->baSourceID[desc->bNrInPins + 5];
+	case UAC_VERSION_2:
+		return &desc->baSourceID[desc->bNrInPins + 6];
+	case UAC_VERSION_3:
+		return &desc->baSourceID[desc->bNrInPins + 2];
+	default:
+		return NULL;
+	}
 }
 
 static inline __u8 uac_processing_unit_iProcessing(struct uac_processing_unit_descriptor *desc,
 						   int protocol)
 {
 	__u8 control_size = uac_processing_unit_bControlSize(desc, protocol);
-	return *(uac_processing_unit_bmControls(desc, protocol)
-			+ control_size);
+
+	switch (protocol) {
+	case UAC_VERSION_1:
+	case UAC_VERSION_2:
+	default:
+		return *(uac_processing_unit_bmControls(desc, protocol)
+			 + control_size);
+	case UAC_VERSION_3:
+		return 0; /* UAC3 does not have this field */
+	}
 }
 
 static inline __u8 *uac_processing_unit_specific(struct uac_processing_unit_descriptor *desc,
 						 int protocol)
 {
 	__u8 control_size = uac_processing_unit_bControlSize(desc, protocol);
-	return uac_processing_unit_bmControls(desc, protocol)
+
+	switch (protocol) {
+	case UAC_VERSION_1:
+	case UAC_VERSION_2:
+	default:
+		return uac_processing_unit_bmControls(desc, protocol)
 			+ control_size + 1;
+	case UAC_VERSION_3:
+		return uac_processing_unit_bmControls(desc, protocol)
+			+ control_size;
+	}
 }
 
 /* 4.5.2 Class-Specific AS Interface Descriptor */
diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h
index 6d1163456c03..fe4423e518c6 100644
--- a/include/uapi/xen/gntdev.h
+++ b/include/uapi/xen/gntdev.h
@@ -5,6 +5,7 @@
  * Interface to /dev/xen/gntdev.
  * 
  * Copyright (c) 2007, D G Murray
+ * Copyright (c) 2018, Oleksandr Andrushchenko, EPAM Systems Inc.
  * 
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2
@@ -200,4 +201,109 @@ struct ioctl_gntdev_grant_copy {
 /* Send an interrupt on the indicated event channel */
 #define UNMAP_NOTIFY_SEND_EVENT 0x2
 
+/*
+ * Flags to be used while requesting memory mapping's backing storage
+ * to be allocated with DMA API.
+ */
+
+/*
+ * The buffer is backed with memory allocated with dma_alloc_wc.
+ */
+#define GNTDEV_DMA_FLAG_WC		(1 << 0)
+
+/*
+ * The buffer is backed with memory allocated with dma_alloc_coherent.
+ */
+#define GNTDEV_DMA_FLAG_COHERENT	(1 << 1)
+
+/*
+ * Create a dma-buf [1] from grant references @refs of count @count provided
+ * by the foreign domain @domid with flags @flags.
+ *
+ * By default dma-buf is backed by system memory pages, but by providing
+ * one of the GNTDEV_DMA_FLAG_XXX flags it can also be created as
+ * a DMA write-combine or coherent buffer, e.g. allocated with dma_alloc_wc/
+ * dma_alloc_coherent.
+ *
+ * Returns 0 if dma-buf was successfully created and the corresponding
+ * dma-buf's file descriptor is returned in @fd.
+ *
+ * [1] Documentation/driver-api/dma-buf.rst
+ */
+
+#define IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS \
+	_IOC(_IOC_NONE, 'G', 9, \
+	     sizeof(struct ioctl_gntdev_dmabuf_exp_from_refs))
+struct ioctl_gntdev_dmabuf_exp_from_refs {
+	/* IN parameters. */
+	/* Specific options for this dma-buf: see GNTDEV_DMA_FLAG_XXX. */
+	__u32 flags;
+	/* Number of grant references in @refs array. */
+	__u32 count;
+	/* OUT parameters. */
+	/* File descriptor of the dma-buf. */
+	__u32 fd;
+	/* The domain ID of the grant references to be mapped. */
+	__u32 domid;
+	/* Variable IN parameter. */
+	/* Array of grant references of size @count. */
+	__u32 refs[1];
+};
+
+/*
+ * This will block until the dma-buf with the file descriptor @fd is
+ * released. This is only valid for buffers created with
+ * IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS.
+ *
+ * If within @wait_to_ms milliseconds the buffer is not released
+ * then -ETIMEDOUT error is returned.
+ * If the buffer with the file descriptor @fd does not exist or has already
+ * been released, then -ENOENT is returned. For valid file descriptors
+ * this must not be treated as error.
+ */
+#define IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED \
+	_IOC(_IOC_NONE, 'G', 10, \
+	     sizeof(struct ioctl_gntdev_dmabuf_exp_wait_released))
+struct ioctl_gntdev_dmabuf_exp_wait_released {
+	/* IN parameters */
+	__u32 fd;
+	__u32 wait_to_ms;
+};
+
+/*
+ * Import a dma-buf with file descriptor @fd and export granted references
+ * to the pages of that dma-buf into array @refs of size @count.
+ */
+#define IOCTL_GNTDEV_DMABUF_IMP_TO_REFS \
+	_IOC(_IOC_NONE, 'G', 11, \
+	     sizeof(struct ioctl_gntdev_dmabuf_imp_to_refs))
+struct ioctl_gntdev_dmabuf_imp_to_refs {
+	/* IN parameters. */
+	/* File descriptor of the dma-buf. */
+	__u32 fd;
+	/* Number of grant references in @refs array. */
+	__u32 count;
+	/* The domain ID for which references to be granted. */
+	__u32 domid;
+	/* Reserved - must be zero. */
+	__u32 reserved;
+	/* OUT parameters. */
+	/* Array of grant references of size @count. */
+	__u32 refs[1];
+};
+
+/*
+ * This will close all references to the imported buffer with file descriptor
+ * @fd, so it can be released by the owner. This is only valid for buffers
+ * created with IOCTL_GNTDEV_DMABUF_IMP_TO_REFS.
+ */
+#define IOCTL_GNTDEV_DMABUF_IMP_RELEASE \
+	_IOC(_IOC_NONE, 'G', 12, \
+	     sizeof(struct ioctl_gntdev_dmabuf_imp_release))
+struct ioctl_gntdev_dmabuf_imp_release {
+	/* IN parameters */
+	__u32 fd;
+	__u32 reserved;
+};
+
 #endif /* __LINUX_PUBLIC_GNTDEV_H__ */
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 2e37741f6b8d..9bc5bc07d4d3 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -198,6 +198,27 @@ void gnttab_free_auto_xlat_frames(void);
 int gnttab_alloc_pages(int nr_pages, struct page **pages);
 void gnttab_free_pages(int nr_pages, struct page **pages);
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+struct gnttab_dma_alloc_args {
+	/* Device for which DMA memory will be/was allocated. */
+	struct device *dev;
+	/* If set then DMA buffer is coherent and write-combine otherwise. */
+	bool coherent;
+
+	int nr_pages;
+	struct page **pages;
+	xen_pfn_t *frames;
+	void *vaddr;
+	dma_addr_t dev_bus_addr;
+};
+
+int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args);
+int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args);
+#endif
+
+int gnttab_pages_set_private(int nr_pages, struct page **pages);
+void gnttab_pages_clear_private(int nr_pages, struct page **pages);
+
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct gnttab_map_grant_ref *kmap_ops,
 		    struct page **pages, unsigned int count);
diff --git a/include/xen/mem-reservation.h b/include/xen/mem-reservation.h
new file mode 100644
index 000000000000..80b52b4945e9
--- /dev/null
+++ b/include/xen/mem-reservation.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Xen memory reservation utilities.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ * Copyright (c) 2010 Daniel Kiper
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _XENMEM_RESERVATION_H
+#define _XENMEM_RESERVATION_H
+
+#include <linux/highmem.h>
+
+#include <xen/page.h>
+
+static inline void xenmem_reservation_scrub_page(struct page *page)
+{
+#ifdef CONFIG_XEN_SCRUB_PAGES
+	clear_highpage(page);
+#endif
+}
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+void __xenmem_reservation_va_mapping_update(unsigned long count,
+					    struct page **pages,
+					    xen_pfn_t *frames);
+
+void __xenmem_reservation_va_mapping_reset(unsigned long count,
+					   struct page **pages);
+#endif
+
+static inline void xenmem_reservation_va_mapping_update(unsigned long count,
+							struct page **pages,
+							xen_pfn_t *frames)
+{
+#ifdef CONFIG_XEN_HAVE_PVMMU
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		__xenmem_reservation_va_mapping_update(count, pages, frames);
+#endif
+}
+
+static inline void xenmem_reservation_va_mapping_reset(unsigned long count,
+						       struct page **pages)
+{
+#ifdef CONFIG_XEN_HAVE_PVMMU
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		__xenmem_reservation_va_mapping_reset(count, pages);
+#endif
+}
+
+int xenmem_reservation_increase(int count, xen_pfn_t *frames);
+
+int xenmem_reservation_decrease(int count, xen_pfn_t *frames);
+
+#endif
diff --git a/init/Kconfig b/init/Kconfig
index fde3d09e8b27..8b1ab81ecda8 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -125,10 +125,13 @@ config HAVE_KERNEL_LZO
 config HAVE_KERNEL_LZ4
 	bool
 
+config HAVE_KERNEL_UNCOMPRESSED
+	bool
+
 choice
 	prompt "Kernel compression mode"
 	default KERNEL_GZIP
-	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4
+	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_UNCOMPRESSED
 	help
 	  The linux kernel is a kind of self-extracting executable.
 	  Several compression algorithms are available, which differ
@@ -207,6 +210,16 @@ config KERNEL_LZ4
 	  is about 8% bigger than LZO. But the decompression speed is
 	  faster than LZO.
 
+config KERNEL_UNCOMPRESSED
+	bool "None"
+	depends on HAVE_KERNEL_UNCOMPRESSED
+	help
+	  Produce uncompressed kernel image. This option is usually not what
+	  you want. It is useful for debugging the kernel in slow simulation
+	  environments, where decompressing and moving the kernel is awfully
+	  slow. This option allows early boot code to skip the decompressor
+	  and jump right at uncompressed kernel image.
+
 endchoice
 
 config DEFAULT_HOSTNAME
@@ -1051,10 +1064,9 @@ config LD_DEAD_CODE_DATA_ELIMINATION
 	depends on HAVE_LD_DEAD_CODE_DATA_ELIMINATION
 	depends on EXPERT
 	help
-	  Select this if the architecture wants to do dead code and
-	  data elimination with the linker by compiling with
-	  -ffunction-sections -fdata-sections, and linking with
-	  --gc-sections.
+	  Enable this if you want to do dead code and data elimination with
+	  the linker by compiling with -ffunction-sections -fdata-sections,
+	  and linking with --gc-sections.
 
 	  This can reduce on disk and in-memory size of the kernel
 	  code and static data, particularly for small configs and
diff --git a/init/main.c b/init/main.c
index 3b4ada11ed52..38c68b593d0d 100644
--- a/init/main.c
+++ b/init/main.c
@@ -79,7 +79,7 @@
 #include <linux/pti.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
-#include <linux/sched_clock.h>
+#include <linux/sched/clock.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/context_tracking.h>
@@ -561,8 +561,8 @@ asmlinkage __visible void __init start_kernel(void)
 	setup_command_line(command_line);
 	setup_nr_cpu_ids();
 	setup_per_cpu_areas();
-	boot_cpu_state_init();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
+	boot_cpu_hotplug_init();
 
 	build_all_zonelists(NULL);
 	page_alloc_init();
@@ -642,7 +642,6 @@ asmlinkage __visible void __init start_kernel(void)
 	softirq_init();
 	timekeeping_init();
 	time_init();
-	sched_clock_postinit();
 	printk_safe_init();
 	perf_event_init();
 	profile_init();
@@ -697,6 +696,7 @@ asmlinkage __visible void __init start_kernel(void)
 	acpi_early_init();
 	if (late_time_init)
 		late_time_init();
+	sched_clock_init();
 	calibrate_delay();
 	pid_idr_init();
 	anon_vma_init();
@@ -1065,6 +1065,13 @@ static int __ref kernel_init(void *unused)
 	jump_label_invalidate_initmem();
 	free_initmem();
 	mark_readonly();
+
+	/*
+	 * Kernel mappings are now finalized - update the userspace page-table
+	 * to finalize PTI.
+	 */
+	pti_finalize();
+
 	system_state = SYSTEM_RUNNING;
 	numa_default_policy();
 
diff --git a/ipc/sem.c b/ipc/sem.c
index 5af1943ad782..76e95e4f3aa2 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -2118,7 +2118,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops,
 	}
 
 	do {
-		queue.status = -EINTR;
+		WRITE_ONCE(queue.status, -EINTR);
 		queue.sleeper = current;
 
 		__set_current_state(TASK_INTERRUPTIBLE);
diff --git a/ipc/shm.c b/ipc/shm.c
index 051a3e1fb8df..d8a38b3be5dd 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -427,6 +427,17 @@ static int shm_split(struct vm_area_struct *vma, unsigned long addr)
 	return 0;
 }
 
+static unsigned long shm_pagesize(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+
+	if (sfd->vm_ops->pagesize)
+		return sfd->vm_ops->pagesize(vma);
+
+	return PAGE_SIZE;
+}
+
 #ifdef CONFIG_NUMA
 static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
 {
@@ -554,6 +565,7 @@ static const struct vm_operations_struct shm_vm_ops = {
 	.close	= shm_close,	/* callback for when the vm-area is released */
 	.fault	= shm_fault,
 	.split	= shm_split,
+	.pagesize = shm_pagesize,
 #if defined(CONFIG_NUMA)
 	.set_policy = shm_set_policy,
 	.get_policy = shm_get_policy,
@@ -1354,15 +1366,14 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	struct shmid_kernel *shp;
 	unsigned long addr = (unsigned long)shmaddr;
 	unsigned long size;
-	struct file *file;
+	struct file *file, *base;
 	int    err;
 	unsigned long flags = MAP_SHARED;
 	unsigned long prot;
 	int acc_mode;
 	struct ipc_namespace *ns;
 	struct shm_file_data *sfd;
-	struct path path;
-	fmode_t f_mode;
+	int f_flags;
 	unsigned long populate = 0;
 
 	err = -EINVAL;
@@ -1395,11 +1406,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	if (shmflg & SHM_RDONLY) {
 		prot = PROT_READ;
 		acc_mode = S_IRUGO;
-		f_mode = FMODE_READ;
+		f_flags = O_RDONLY;
 	} else {
 		prot = PROT_READ | PROT_WRITE;
 		acc_mode = S_IRUGO | S_IWUGO;
-		f_mode = FMODE_READ | FMODE_WRITE;
+		f_flags = O_RDWR;
 	}
 	if (shmflg & SHM_EXEC) {
 		prot |= PROT_EXEC;
@@ -1435,46 +1446,44 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 		goto out_unlock;
 	}
 
-	path = shp->shm_file->f_path;
-	path_get(&path);
+	/*
+	 * We need to take a reference to the real shm file to prevent the
+	 * pointer from becoming stale in cases where the lifetime of the outer
+	 * file extends beyond that of the shm segment.  It's not usually
+	 * possible, but it can happen during remap_file_pages() emulation as
+	 * that unmaps the memory, then does ->mmap() via file reference only.
+	 * We'll deny the ->mmap() if the shm segment was since removed, but to
+	 * detect shm ID reuse we need to compare the file pointers.
+	 */
+	base = get_file(shp->shm_file);
 	shp->shm_nattch++;
-	size = i_size_read(d_inode(path.dentry));
+	size = i_size_read(file_inode(base));
 	ipc_unlock_object(&shp->shm_perm);
 	rcu_read_unlock();
 
 	err = -ENOMEM;
 	sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
 	if (!sfd) {
-		path_put(&path);
+		fput(base);
 		goto out_nattch;
 	}
 
-	file = alloc_file(&path, f_mode,
-			  is_file_hugepages(shp->shm_file) ?
+	file = alloc_file_clone(base, f_flags,
+			  is_file_hugepages(base) ?
 				&shm_file_operations_huge :
 				&shm_file_operations);
 	err = PTR_ERR(file);
 	if (IS_ERR(file)) {
 		kfree(sfd);
-		path_put(&path);
+		fput(base);
 		goto out_nattch;
 	}
 
-	file->private_data = sfd;
-	file->f_mapping = shp->shm_file->f_mapping;
 	sfd->id = shp->shm_perm.id;
 	sfd->ns = get_ipc_ns(ns);
-	/*
-	 * We need to take a reference to the real shm file to prevent the
-	 * pointer from becoming stale in cases where the lifetime of the outer
-	 * file extends beyond that of the shm segment.  It's not usually
-	 * possible, but it can happen during remap_file_pages() emulation as
-	 * that unmaps the memory, then does ->mmap() via file reference only.
-	 * We'll deny the ->mmap() if the shm segment was since removed, but to
-	 * detect shm ID reuse we need to compare the file pointers.
-	 */
-	sfd->file = get_file(shp->shm_file);
+	sfd->file = base;
 	sfd->vm_ops = NULL;
+	file->private_data = sfd;
 
 	err = security_mmap_file(file, prot, flags);
 	if (err)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index ceb1c4596c51..80d672a11088 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1279,8 +1279,12 @@ static void show_special(struct audit_context *context, int *call_panic)
 		break;
 	case AUDIT_KERN_MODULE:
 		audit_log_format(ab, "name=");
-		audit_log_untrustedstring(ab, context->module.name);
-		kfree(context->module.name);
+		if (context->module.name) {
+			audit_log_untrustedstring(ab, context->module.name);
+			kfree(context->module.name);
+		} else
+			audit_log_format(ab, "(null)");
+
 		break;
 	}
 	audit_log_end(ab);
@@ -2411,8 +2415,9 @@ void __audit_log_kern_module(char *name)
 {
 	struct audit_context *context = audit_context();
 
-	context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL);
-	strcpy(context->module.name, name);
+	context->module.name = kstrdup(name, GFP_KERNEL);
+	if (!context->module.name)
+		audit_log_lost("out of memory in __audit_log_kern_module");
 	context->type = AUDIT_KERN_MODULE;
 }
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 544e58f5f642..2aa55d030c77 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -378,7 +378,7 @@ static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
 		return -EINVAL;
 
 	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
-	if (!value_type || value_size > map->value_size)
+	if (!value_type || value_size != map->value_size)
 		return -EINVAL;
 
 	return 0;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2d49d18b793a..2590700237c1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
  */
 static bool btf_type_int_is_regular(const struct btf_type *t)
 {
-	u16 nr_bits, nr_bytes;
+	u8 nr_bits, nr_bytes;
 	u32 int_data;
 
 	int_data = btf_type_int(t);
@@ -991,38 +991,38 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 				  void *data, u8 bits_offset,
 				  struct seq_file *m)
 {
+	u16 left_shift_bits, right_shift_bits;
 	u32 int_data = btf_type_int(t);
-	u16 nr_bits = BTF_INT_BITS(int_data);
-	u16 total_bits_offset;
-	u16 nr_copy_bytes;
-	u16 nr_copy_bits;
-	u8 nr_upper_bits;
-	union {
-		u64 u64_num;
-		u8  u8_nums[8];
-	} print_num;
+	u8 nr_bits = BTF_INT_BITS(int_data);
+	u8 total_bits_offset;
+	u8 nr_copy_bytes;
+	u8 nr_copy_bits;
+	u64 print_num;
 
+	/*
+	 * bits_offset is at most 7.
+	 * BTF_INT_OFFSET() cannot exceed 64 bits.
+	 */
 	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
 	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
 	bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
 	nr_copy_bits = nr_bits + bits_offset;
 	nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
 
-	print_num.u64_num = 0;
-	memcpy(&print_num.u64_num, data, nr_copy_bytes);
-
-	/* Ditch the higher order bits */
-	nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
-	if (nr_upper_bits) {
-		/* We need to mask out some bits of the upper byte. */
-		u8 mask = (1 << nr_upper_bits) - 1;
+	print_num = 0;
+	memcpy(&print_num, data, nr_copy_bytes);
 
-		print_num.u8_nums[nr_copy_bytes - 1] &= mask;
-	}
+#ifdef __BIG_ENDIAN_BITFIELD
+	left_shift_bits = bits_offset;
+#else
+	left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+	right_shift_bits = BITS_PER_U64 - nr_bits;
 
-	print_num.u64_num >>= bits_offset;
+	print_num <<= left_shift_bits;
+	print_num >>= right_shift_bits;
 
-	seq_printf(m, "0x%llx", print_num.u64_num);
+	seq_printf(m, "0x%llx", print_num);
 }
 
 static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
@@ -1032,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
 	u32 int_data = btf_type_int(t);
 	u8 encoding = BTF_INT_ENCODING(int_data);
 	bool sign = encoding & BTF_INT_SIGNED;
-	u32 nr_bits = BTF_INT_BITS(int_data);
+	u8 nr_bits = BTF_INT_BITS(int_data);
 
 	if (bits_offset || BTF_INT_OFFSET(int_data) ||
 	    BITS_PER_BYTE_MASKED(nr_bits)) {
@@ -1519,9 +1519,9 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 {
 	bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
 	const struct btf_member *member;
+	u32 meta_needed, last_offset;
 	struct btf *btf = env->btf;
 	u32 struct_size = t->size;
-	u32 meta_needed;
 	u16 i;
 
 	meta_needed = btf_type_vlen(t) * sizeof(*member);
@@ -1534,6 +1534,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 
 	btf_verifier_log_type(env, t, NULL);
 
+	last_offset = 0;
 	for_each_member(i, t, member) {
 		if (!btf_name_offset_valid(btf, member->name_off)) {
 			btf_verifier_log_member(env, t, member,
@@ -1555,6 +1556,16 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
+		/*
+		 * ">" instead of ">=" because the last member could be
+		 * "char a[0];"
+		 */
+		if (last_offset > member->offset) {
+			btf_verifier_log_member(env, t, member,
+						"Invalid member bits_offset");
+			return -EINVAL;
+		}
+
 		if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
 			btf_verifier_log_member(env, t, member,
 						"Memmber bits_offset exceeds its struct size");
@@ -1562,6 +1573,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 		}
 
 		btf_verifier_log_member(env, t, member, NULL);
+		last_offset = member->offset;
 	}
 
 	return meta_needed;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index f7c00bd6f8e4..3d83ee7df381 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -428,6 +428,60 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	return ret;
 }
 
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+			   enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+	struct cgroup *cgrp;
+	int ret;
+
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+				attr->attach_flags);
+	cgroup_put(cgrp);
+	return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+	struct bpf_prog *prog;
+	struct cgroup *cgrp;
+	int ret;
+
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		prog = NULL;
+
+	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+	if (prog)
+		bpf_prog_put(prog);
+
+	cgroup_put(cgrp);
+	return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+			  union bpf_attr __user *uattr)
+{
+	struct cgroup *cgrp;
+	int ret;
+
+	cgrp = cgroup_get_from_fd(attr->query.target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+	cgroup_put(cgrp);
+	return ret;
+}
+
 /**
  * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
  * @sk: The socket sending or receiving traffic
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a9e6c04d0f4a..1e5625d46414 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -598,8 +598,6 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 	bpf_fill_ill_insns(hdr, size);
 
 	hdr->pages = size / PAGE_SIZE;
-	hdr->locked = 0;
-
 	hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
 		     PAGE_SIZE - sizeof(*hdr));
 	start = (get_random_int() % hole) & ~(alignment - 1);
@@ -1450,22 +1448,6 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 	return 0;
 }
 
-static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp)
-{
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	int i, err;
-
-	for (i = 0; i < fp->aux->func_cnt; i++) {
-		err = bpf_prog_check_pages_ro_single(fp->aux->func[i]);
-		if (err)
-			return err;
-	}
-
-	return bpf_prog_check_pages_ro_single(fp);
-#endif
-	return 0;
-}
-
 static void bpf_prog_select_func(struct bpf_prog *fp)
 {
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
@@ -1524,17 +1506,7 @@ finalize:
 	 * all eBPF JITs might immediately support all features.
 	 */
 	*err = bpf_check_tail_call(fp);
-	if (*err)
-		return fp;
-
-	/* Checkpoint: at this point onwards any cBPF -> eBPF or
-	 * native eBPF program is read-only. If we failed to change
-	 * the page attributes (e.g. allocation failure from
-	 * splitting large pages), then reject the whole program
-	 * in order to guarantee not ending up with any W+X pages
-	 * from BPF side in kernel.
-	 */
-	*err = bpf_prog_check_pages_ro_locked(fp);
+
 	return fp;
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index e0918d180f08..46f5f29605d4 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -69,7 +69,7 @@ struct bpf_cpu_map {
 };
 
 static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
-			     struct xdp_bulk_queue *bq);
+			     struct xdp_bulk_queue *bq, bool in_napi_ctx);
 
 static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
 {
@@ -375,7 +375,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu)
 		struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
 
 		/* No concurrent bq_enqueue can run at this point */
-		bq_flush_to_queue(rcpu, bq);
+		bq_flush_to_queue(rcpu, bq, false);
 	}
 	free_percpu(rcpu->bulkq);
 	/* Cannot kthread_stop() here, last put free rcpu resources */
@@ -558,7 +558,7 @@ const struct bpf_map_ops cpu_map_ops = {
 };
 
 static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
-			     struct xdp_bulk_queue *bq)
+			     struct xdp_bulk_queue *bq, bool in_napi_ctx)
 {
 	unsigned int processed = 0, drops = 0;
 	const int to_cpu = rcpu->cpu;
@@ -578,7 +578,10 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
 		err = __ptr_ring_produce(q, xdpf);
 		if (err) {
 			drops++;
-			xdp_return_frame_rx_napi(xdpf);
+			if (likely(in_napi_ctx))
+				xdp_return_frame_rx_napi(xdpf);
+			else
+				xdp_return_frame(xdpf);
 		}
 		processed++;
 	}
@@ -598,7 +601,7 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
 
 	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
-		bq_flush_to_queue(rcpu, bq);
+		bq_flush_to_queue(rcpu, bq, true);
 
 	/* Notice, xdp_buff/page MUST be queued here, long enough for
 	 * driver to code invoking us to finished, due to driver
@@ -661,7 +664,7 @@ void __cpu_map_flush(struct bpf_map *map)
 
 		/* Flush all frames in bulkq to real queue */
 		bq = this_cpu_ptr(rcpu->bulkq);
-		bq_flush_to_queue(rcpu, bq);
+		bq_flush_to_queue(rcpu, bq, true);
 
 		/* If already running, costs spin_lock_irqsave + smb_mb */
 		wake_up_process(rcpu->kthread);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 642c97f6d1b8..750d45edae79 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -217,7 +217,8 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit)
 }
 
 static int bq_xmit_all(struct bpf_dtab_netdev *obj,
-		       struct xdp_bulk_queue *bq, u32 flags)
+		       struct xdp_bulk_queue *bq, u32 flags,
+		       bool in_napi_ctx)
 {
 	struct net_device *dev = obj->dev;
 	int sent = 0, drops = 0, err = 0;
@@ -254,7 +255,10 @@ error:
 		struct xdp_frame *xdpf = bq->q[i];
 
 		/* RX path under NAPI protection, can return frames faster */
-		xdp_return_frame_rx_napi(xdpf);
+		if (likely(in_napi_ctx))
+			xdp_return_frame_rx_napi(xdpf);
+		else
+			xdp_return_frame(xdpf);
 		drops++;
 	}
 	goto out;
@@ -286,7 +290,7 @@ void __dev_map_flush(struct bpf_map *map)
 		__clear_bit(bit, bitmap);
 
 		bq = this_cpu_ptr(dev->bulkq);
-		bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+		bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
 	}
 }
 
@@ -316,7 +320,7 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
 	struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
 
 	if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
-		bq_xmit_all(obj, bq, 0);
+		bq_xmit_all(obj, bq, 0, true);
 
 	/* Ingress dev_rx will be the same for all xdp_frame's in
 	 * bulk_queue, because bq stored per-CPU and must be flushed
@@ -334,10 +338,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 {
 	struct net_device *dev = dst->dev;
 	struct xdp_frame *xdpf;
+	int err;
 
 	if (!dev->netdev_ops->ndo_xdp_xmit)
 		return -EOPNOTSUPP;
 
+	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+	if (unlikely(err))
+		return err;
+
 	xdpf = convert_to_xdp_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
@@ -350,7 +359,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 {
 	int err;
 
-	err = __xdp_generic_ok_fwd_dev(skb, dst->dev);
+	err = xdp_ok_fwd_dev(dst->dev, skb->len);
 	if (unlikely(err))
 		return err;
 	skb->dev = dst->dev;
@@ -380,7 +389,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
 			__clear_bit(dev->bit, bitmap);
 
 			bq = per_cpu_ptr(dev->bulkq, cpu);
-			bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+			bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
 		}
 	}
 }
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ca2198a6d22..513d9dfcf4ee 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 				 * old element will be freed immediately.
 				 * Otherwise return an error
 				 */
-				atomic_dec(&htab->count);
-				return ERR_PTR(-E2BIG);
+				l_new = ERR_PTR(-E2BIG);
+				goto dec_count;
 			}
 		l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
 				     htab->map.numa_node);
-		if (!l_new)
-			return ERR_PTR(-ENOMEM);
+		if (!l_new) {
+			l_new = ERR_PTR(-ENOMEM);
+			goto dec_count;
+		}
 	}
 
 	memcpy(l_new->key, key, key_size);
@@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 						  GFP_ATOMIC | __GFP_NOWARN);
 			if (!pptr) {
 				kfree(l_new);
-				return ERR_PTR(-ENOMEM);
+				l_new = ERR_PTR(-ENOMEM);
+				goto dec_count;
 			}
 		}
 
@@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 
 	l_new->hash = hash;
 	return l_new;
+dec_count:
+	atomic_dec(&htab->count);
+	return l_new;
 }
 
 static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 52a91d816c0e..c4d75c52b4fc 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -72,6 +72,7 @@ struct bpf_htab {
 	u32 n_buckets;
 	u32 elem_size;
 	struct bpf_sock_progs progs;
+	struct rcu_head rcu;
 };
 
 struct htab_elem {
@@ -89,8 +90,8 @@ enum smap_psock_state {
 struct smap_psock_map_entry {
 	struct list_head list;
 	struct sock **entry;
-	struct htab_elem *hash_link;
-	struct bpf_htab *htab;
+	struct htab_elem __rcu *hash_link;
+	struct bpf_htab __rcu *htab;
 };
 
 struct smap_psock {
@@ -120,6 +121,7 @@ struct smap_psock {
 	struct bpf_prog *bpf_parse;
 	struct bpf_prog *bpf_verdict;
 	struct list_head maps;
+	spinlock_t maps_lock;
 
 	/* Back reference used when sock callback trigger sockmap operations */
 	struct sock *sock;
@@ -140,6 +142,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
 			    int offset, size_t size, int flags);
+static void bpf_tcp_close(struct sock *sk, long timeout);
 
 static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
 {
@@ -161,7 +164,42 @@ out:
 	return !empty;
 }
 
-static struct proto tcp_bpf_proto;
+enum {
+	SOCKMAP_IPV4,
+	SOCKMAP_IPV6,
+	SOCKMAP_NUM_PROTS,
+};
+
+enum {
+	SOCKMAP_BASE,
+	SOCKMAP_TX,
+	SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+			 struct proto *base)
+{
+	prot[SOCKMAP_BASE]			= *base;
+	prot[SOCKMAP_BASE].close		= bpf_tcp_close;
+	prot[SOCKMAP_BASE].recvmsg		= bpf_tcp_recvmsg;
+	prot[SOCKMAP_BASE].stream_memory_read	= bpf_tcp_stream_read;
+
+	prot[SOCKMAP_TX]			= prot[SOCKMAP_BASE];
+	prot[SOCKMAP_TX].sendmsg		= bpf_tcp_sendmsg;
+	prot[SOCKMAP_TX].sendpage		= bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+	int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+	int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+	sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
 static int bpf_tcp_init(struct sock *sk)
 {
 	struct smap_psock *psock;
@@ -181,14 +219,17 @@ static int bpf_tcp_init(struct sock *sk)
 	psock->save_close = sk->sk_prot->close;
 	psock->sk_proto = sk->sk_prot;
 
-	if (psock->bpf_tx_msg) {
-		tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
-		tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
-		tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
-		tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
+	/* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+	if (sk->sk_family == AF_INET6 &&
+	    unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+		spin_lock_bh(&tcpv6_prot_lock);
+		if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+			build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+			smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+		}
+		spin_unlock_bh(&tcpv6_prot_lock);
 	}
-
-	sk->sk_prot = &tcp_bpf_proto;
+	update_sk_prot(sk, psock);
 	rcu_read_unlock();
 	return 0;
 }
@@ -219,24 +260,64 @@ out:
 	rcu_read_unlock();
 }
 
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+					 u32 hash, void *key, u32 key_size)
+{
+	struct htab_elem *l;
+
+	hlist_for_each_entry_rcu(l, head, hash_node) {
+		if (l->hash == hash && !memcmp(&l->key, key, key_size))
+			return l;
+	}
+
+	return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+	return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+	return &__select_bucket(htab, hash)->head;
+}
+
 static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 {
 	atomic_dec(&htab->count);
 	kfree_rcu(l, rcu);
 }
 
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+						  struct smap_psock *psock)
+{
+	struct smap_psock_map_entry *e;
+
+	spin_lock_bh(&psock->maps_lock);
+	e = list_first_entry_or_null(&psock->maps,
+				     struct smap_psock_map_entry,
+				     list);
+	if (e)
+		list_del(&e->list);
+	spin_unlock_bh(&psock->maps_lock);
+	return e;
+}
+
 static void bpf_tcp_close(struct sock *sk, long timeout)
 {
 	void (*close_fun)(struct sock *sk, long timeout);
-	struct smap_psock_map_entry *e, *tmp;
+	struct smap_psock_map_entry *e;
 	struct sk_msg_buff *md, *mtmp;
 	struct smap_psock *psock;
 	struct sock *osk;
 
+	lock_sock(sk);
 	rcu_read_lock();
 	psock = smap_psock_sk(sk);
 	if (unlikely(!psock)) {
 		rcu_read_unlock();
+		release_sock(sk);
 		return sk->sk_prot->close(sk, timeout);
 	}
 
@@ -247,7 +328,6 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 	 */
 	close_fun = psock->save_close;
 
-	write_lock_bh(&sk->sk_callback_lock);
 	if (psock->cork) {
 		free_start_sg(psock->sock, psock->cork);
 		kfree(psock->cork);
@@ -260,21 +340,40 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 		kfree(md);
 	}
 
-	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+	e = psock_map_pop(sk, psock);
+	while (e) {
 		if (e->entry) {
 			osk = cmpxchg(e->entry, sk, NULL);
 			if (osk == sk) {
-				list_del(&e->list);
 				smap_release_sock(psock, sk);
 			}
 		} else {
-			hlist_del_rcu(&e->hash_link->hash_node);
-			smap_release_sock(psock, e->hash_link->sk);
-			free_htab_elem(e->htab, e->hash_link);
+			struct htab_elem *link = rcu_dereference(e->hash_link);
+			struct bpf_htab *htab = rcu_dereference(e->htab);
+			struct hlist_head *head;
+			struct htab_elem *l;
+			struct bucket *b;
+
+			b = __select_bucket(htab, link->hash);
+			head = &b->head;
+			raw_spin_lock_bh(&b->lock);
+			l = lookup_elem_raw(head,
+					    link->hash, link->key,
+					    htab->map.key_size);
+			/* If another thread deleted this object skip deletion.
+			 * The refcnt on psock may or may not be zero.
+			 */
+			if (l) {
+				hlist_del_rcu(&link->hash_node);
+				smap_release_sock(psock, link->sk);
+				free_htab_elem(htab, link);
+			}
+			raw_spin_unlock_bh(&b->lock);
 		}
+		e = psock_map_pop(sk, psock);
 	}
-	write_unlock_bh(&sk->sk_callback_lock);
 	rcu_read_unlock();
+	release_sock(sk);
 	close_fun(sk, timeout);
 }
 
@@ -472,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
 	while (sg[i].length) {
 		free += sg[i].length;
 		sk_mem_uncharge(sk, sg[i].length);
-		put_page(sg_page(&sg[i]));
+		if (!md->skb)
+			put_page(sg_page(&sg[i]));
 		sg[i].length = 0;
 		sg[i].page_link = 0;
 		sg[i].offset = 0;
@@ -481,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
 		if (i == MAX_SKB_FRAGS)
 			i = 0;
 	}
+	if (md->skb)
+		consume_skb(md->skb);
 
 	return free;
 }
@@ -946,12 +1048,12 @@ static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
 	while (msg_data_left(msg)) {
-		struct sk_msg_buff *m;
+		struct sk_msg_buff *m = NULL;
 		bool enospc = false;
 		int copy;
 
 		if (sk->sk_err) {
-			err = sk->sk_err;
+			err = -sk->sk_err;
 			goto out_err;
 		}
 
@@ -1014,8 +1116,11 @@ wait_for_sndbuf:
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
 		err = sk_stream_wait_memory(sk, &timeo);
-		if (err)
+		if (err) {
+			if (m && m != psock->cork)
+				free_start_sg(sk, m);
 			goto out_err;
+		}
 	}
 out_err:
 	if (err < 0)
@@ -1111,8 +1216,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock,
 
 static int bpf_tcp_ulp_register(void)
 {
-	tcp_bpf_proto = tcp_prot;
-	tcp_bpf_proto.close = bpf_tcp_close;
+	build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
 	/* Once BPF TX ULP is registered it is never unregistered. It
 	 * will be in the ULP list for the lifetime of the system. Doing
 	 * duplicate registers is not a problem.
@@ -1135,7 +1239,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 	 */
 	TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
 	skb->sk = psock->sock;
-	bpf_compute_data_pointers(skb);
+	bpf_compute_data_end_sk_skb(skb);
 	preempt_disable();
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	preempt_enable();
@@ -1357,7 +1461,9 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
 {
 	if (refcount_dec_and_test(&psock->refcnt)) {
 		tcp_cleanup_ulp(sock);
+		write_lock_bh(&sock->sk_callback_lock);
 		smap_stop_sock(psock, sock);
+		write_unlock_bh(&sock->sk_callback_lock);
 		clear_bit(SMAP_TX_RUNNING, &psock->state);
 		rcu_assign_sk_user_data(sock, NULL);
 		call_rcu_sched(&psock->rcu, smap_destroy_psock);
@@ -1388,7 +1494,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
 	 * any socket yet.
 	 */
 	skb->sk = psock->sock;
-	bpf_compute_data_pointers(skb);
+	bpf_compute_data_end_sk_skb(skb);
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	skb->sk = NULL;
 	rcu_read_unlock();
@@ -1508,6 +1614,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock, int node)
 	INIT_LIST_HEAD(&psock->maps);
 	INIT_LIST_HEAD(&psock->ingress);
 	refcount_set(&psock->refcnt, 1);
+	spin_lock_init(&psock->maps_lock);
 
 	rcu_assign_sk_user_data(sock, psock);
 	sock_hold(sock);
@@ -1564,18 +1671,32 @@ free_stab:
 	return ERR_PTR(err);
 }
 
-static void smap_list_remove(struct smap_psock *psock,
-			     struct sock **entry,
-			     struct htab_elem *hash_link)
+static void smap_list_map_remove(struct smap_psock *psock,
+				 struct sock **entry)
 {
 	struct smap_psock_map_entry *e, *tmp;
 
+	spin_lock_bh(&psock->maps_lock);
 	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
-		if (e->entry == entry || e->hash_link == hash_link) {
+		if (e->entry == entry)
 			list_del(&e->list);
-			break;
-		}
 	}
+	spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+				  struct htab_elem *hash_link)
+{
+	struct smap_psock_map_entry *e, *tmp;
+
+	spin_lock_bh(&psock->maps_lock);
+	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+		struct htab_elem *c = rcu_dereference(e->hash_link);
+
+		if (c == hash_link)
+			list_del(&e->list);
+	}
+	spin_unlock_bh(&psock->maps_lock);
 }
 
 static void sock_map_free(struct bpf_map *map)
@@ -1601,7 +1722,6 @@ static void sock_map_free(struct bpf_map *map)
 		if (!sock)
 			continue;
 
-		write_lock_bh(&sock->sk_callback_lock);
 		psock = smap_psock_sk(sock);
 		/* This check handles a racing sock event that can get the
 		 * sk_callback_lock before this case but after xchg happens
@@ -1609,10 +1729,9 @@ static void sock_map_free(struct bpf_map *map)
 		 * to be null and queued for garbage collection.
 		 */
 		if (likely(psock)) {
-			smap_list_remove(psock, &stab->sock_map[i], NULL);
+			smap_list_map_remove(psock, &stab->sock_map[i]);
 			smap_release_sock(psock, sock);
 		}
-		write_unlock_bh(&sock->sk_callback_lock);
 	}
 	rcu_read_unlock();
 
@@ -1661,17 +1780,15 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
 	if (!sock)
 		return -EINVAL;
 
-	write_lock_bh(&sock->sk_callback_lock);
 	psock = smap_psock_sk(sock);
 	if (!psock)
 		goto out;
 
 	if (psock->bpf_parse)
 		smap_stop_sock(psock, sock);
-	smap_list_remove(psock, &stab->sock_map[k], NULL);
+	smap_list_map_remove(psock, &stab->sock_map[k]);
 	smap_release_sock(psock, sock);
 out:
-	write_unlock_bh(&sock->sk_callback_lock);
 	return 0;
 }
 
@@ -1752,7 +1869,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
 		}
 	}
 
-	write_lock_bh(&sock->sk_callback_lock);
 	psock = smap_psock_sk(sock);
 
 	/* 2. Do not allow inheriting programs if psock exists and has
@@ -1789,7 +1905,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
 		e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
 		if (!e) {
 			err = -ENOMEM;
-			goto out_progs;
+			goto out_free;
 		}
 	}
 
@@ -1809,7 +1925,9 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
 		if (err)
 			goto out_free;
 		smap_init_progs(psock, verdict, parse);
+		write_lock_bh(&sock->sk_callback_lock);
 		smap_start_sock(psock, sock);
+		write_unlock_bh(&sock->sk_callback_lock);
 	}
 
 	/* 4. Place psock in sockmap for use and stop any programs on
@@ -1819,9 +1937,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
 	 */
 	if (map_link) {
 		e->entry = map_link;
+		spin_lock_bh(&psock->maps_lock);
 		list_add_tail(&e->list, &psock->maps);
+		spin_unlock_bh(&psock->maps_lock);
 	}
-	write_unlock_bh(&sock->sk_callback_lock);
 	return err;
 out_free:
 	smap_release_sock(psock, sock);
@@ -1832,7 +1951,6 @@ out_progs:
 	}
 	if (tx_msg)
 		bpf_prog_put(tx_msg);
-	write_unlock_bh(&sock->sk_callback_lock);
 	kfree(e);
 	return err;
 }
@@ -1869,10 +1987,8 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	if (osock) {
 		struct smap_psock *opsock = smap_psock_sk(osock);
 
-		write_lock_bh(&osock->sk_callback_lock);
-		smap_list_remove(opsock, &stab->sock_map[i], NULL);
+		smap_list_map_remove(opsock, &stab->sock_map[i]);
 		smap_release_sock(opsock, osock);
-		write_unlock_bh(&osock->sk_callback_lock);
 	}
 out:
 	return err;
@@ -1915,6 +2031,24 @@ int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
 	return 0;
 }
 
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+			struct bpf_prog *prog)
+{
+	int ufd = attr->target_fd;
+	struct bpf_map *map;
+	struct fd f;
+	int err;
+
+	f = fdget(ufd);
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = sock_map_prog(map, prog, attr->attach_type);
+	fdput(f);
+	return err;
+}
+
 static void *sock_map_lookup(struct bpf_map *map, void *key)
 {
 	return NULL;
@@ -1944,7 +2078,13 @@ static int sock_map_update_elem(struct bpf_map *map,
 		return -EOPNOTSUPP;
 	}
 
+	lock_sock(skops.sk);
+	preempt_disable();
+	rcu_read_lock();
 	err = sock_map_ctx_update_elem(&skops, map, key, flags);
+	rcu_read_unlock();
+	preempt_enable();
+	release_sock(skops.sk);
 	fput(socket->file);
 	return err;
 }
@@ -2043,14 +2183,13 @@ free_htab:
 	return ERR_PTR(err);
 }
 
-static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+static void __bpf_htab_free(struct rcu_head *rcu)
 {
-	return &htab->buckets[hash & (htab->n_buckets - 1)];
-}
+	struct bpf_htab *htab;
 
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
-{
-	return &__select_bucket(htab, hash)->head;
+	htab = container_of(rcu, struct bpf_htab, rcu);
+	bpf_map_area_free(htab->buckets);
+	kfree(htab);
 }
 
 static void sock_hash_free(struct bpf_map *map)
@@ -2069,16 +2208,18 @@ static void sock_hash_free(struct bpf_map *map)
 	 */
 	rcu_read_lock();
 	for (i = 0; i < htab->n_buckets; i++) {
-		struct hlist_head *head = select_bucket(htab, i);
+		struct bucket *b = __select_bucket(htab, i);
+		struct hlist_head *head;
 		struct hlist_node *n;
 		struct htab_elem *l;
 
+		raw_spin_lock_bh(&b->lock);
+		head = &b->head;
 		hlist_for_each_entry_safe(l, n, head, hash_node) {
 			struct sock *sock = l->sk;
 			struct smap_psock *psock;
 
 			hlist_del_rcu(&l->hash_node);
-			write_lock_bh(&sock->sk_callback_lock);
 			psock = smap_psock_sk(sock);
 			/* This check handles a racing sock event that can get
 			 * the sk_callback_lock before this case but after xchg
@@ -2086,16 +2227,15 @@ static void sock_hash_free(struct bpf_map *map)
 			 * (psock) to be null and queued for garbage collection.
 			 */
 			if (likely(psock)) {
-				smap_list_remove(psock, NULL, l);
+				smap_list_hash_remove(psock, l);
 				smap_release_sock(psock, sock);
 			}
-			write_unlock_bh(&sock->sk_callback_lock);
-			kfree(l);
+			free_htab_elem(htab, l);
 		}
+		raw_spin_unlock_bh(&b->lock);
 	}
 	rcu_read_unlock();
-	bpf_map_area_free(htab->buckets);
-	kfree(htab);
+	call_rcu(&htab->rcu, __bpf_htab_free);
 }
 
 static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
@@ -2122,19 +2262,6 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
 	return l_new;
 }
 
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
-					 u32 hash, void *key, u32 key_size)
-{
-	struct htab_elem *l;
-
-	hlist_for_each_entry_rcu(l, head, hash_node) {
-		if (l->hash == hash && !memcmp(&l->key, key, key_size))
-			return l;
-	}
-
-	return NULL;
-}
-
 static inline u32 htab_map_hash(const void *key, u32 key_len)
 {
 	return jhash(key, key_len, 0);
@@ -2230,7 +2357,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	if (err)
 		goto err;
 
-	/* bpf_map_update_elem() can be called in_irq() */
+	/* psock is valid here because otherwise above *ctx_update_elem would
+	 * have thrown an error. It is safe to skip error check.
+	 */
+	psock = smap_psock_sk(sock);
 	raw_spin_lock_bh(&b->lock);
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 	if (l_old && map_flags == BPF_NOEXIST) {
@@ -2248,15 +2378,12 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		goto bucket_err;
 	}
 
-	psock = smap_psock_sk(sock);
-	if (unlikely(!psock)) {
-		err = -EINVAL;
-		goto bucket_err;
-	}
-
-	e->hash_link = l_new;
-	e->htab = container_of(map, struct bpf_htab, map);
+	rcu_assign_pointer(e->hash_link, l_new);
+	rcu_assign_pointer(e->htab,
+			   container_of(map, struct bpf_htab, map));
+	spin_lock_bh(&psock->maps_lock);
 	list_add_tail(&e->list, &psock->maps);
+	spin_unlock_bh(&psock->maps_lock);
 
 	/* add new element to the head of the list, so that
 	 * concurrent search will find it before old elem
@@ -2266,19 +2393,17 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		psock = smap_psock_sk(l_old->sk);
 
 		hlist_del_rcu(&l_old->hash_node);
-		smap_list_remove(psock, NULL, l_old);
+		smap_list_hash_remove(psock, l_old);
 		smap_release_sock(psock, l_old->sk);
 		free_htab_elem(htab, l_old);
 	}
 	raw_spin_unlock_bh(&b->lock);
 	return 0;
 bucket_err:
+	smap_release_sock(psock, sock);
 	raw_spin_unlock_bh(&b->lock);
 err:
 	kfree(e);
-	psock = smap_psock_sk(sock);
-	if (psock)
-		smap_release_sock(psock, sock);
 	return err;
 }
 
@@ -2300,7 +2425,13 @@ static int sock_hash_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	lock_sock(skops.sk);
+	preempt_disable();
+	rcu_read_lock();
 	err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+	rcu_read_unlock();
+	preempt_enable();
+	release_sock(skops.sk);
 	fput(socket->file);
 	return err;
 }
@@ -2326,7 +2457,6 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
 		struct smap_psock *psock;
 
 		hlist_del_rcu(&l->hash_node);
-		write_lock_bh(&sock->sk_callback_lock);
 		psock = smap_psock_sk(sock);
 		/* This check handles a racing sock event that can get the
 		 * sk_callback_lock before this case but after xchg happens
@@ -2334,10 +2464,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
 		 * to be null and queued for garbage collection.
 		 */
 		if (likely(psock)) {
-			smap_list_remove(psock, NULL, l);
+			smap_list_hash_remove(psock, l);
 			smap_release_sock(psock, sock);
 		}
-		write_unlock_bh(&sock->sk_callback_lock);
 		free_htab_elem(htab, l);
 		ret = 0;
 	}
@@ -2359,10 +2488,8 @@ struct sock  *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	raw_spin_lock_bh(&b->lock);
 	l = lookup_elem_raw(head, hash, key, key_size);
 	sk = l ? l->sk : NULL;
-	raw_spin_unlock_bh(&b->lock);
 	return sk;
 }
 
@@ -2383,6 +2510,7 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_get_next_key = sock_hash_get_next_key,
 	.map_update_elem = sock_hash_update_elem,
 	.map_delete_elem = sock_hash_delete_elem,
+	.map_release_uref = sock_map_release,
 };
 
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 35dc466641f2..b41c6cf2eb88 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -575,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
 {
 	int refold;
 
-	refold = __atomic_add_unless(&map->refcnt, 1, 0);
+	refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
 
 	if (refold >= BPF_MAX_REFCNT) {
 		__bpf_map_put(map, false);
@@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr)
 	if (bpf_map_is_dev_bound(map)) {
 		err = bpf_map_offload_update_elem(map, key, value, attr->flags);
 		goto out;
-	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+		   map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+		   map->map_type == BPF_MAP_TYPE_SOCKMAP) {
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
 		goto out;
 	}
@@ -1142,7 +1144,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 {
 	int refold;
 
-	refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+	refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
 
 	if (refold >= BPF_MAX_REFCNT) {
 		__bpf_prog_put(prog, false);
@@ -1483,8 +1485,6 @@ out_free_tp:
 	return err;
 }
 
-#ifdef CONFIG_CGROUP_BPF
-
 static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 					     enum bpf_attach_type attach_type)
 {
@@ -1499,40 +1499,6 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 
 #define BPF_PROG_ATTACH_LAST_FIELD attach_flags
 
-static int sockmap_get_from_fd(const union bpf_attr *attr,
-			       int type, bool attach)
-{
-	struct bpf_prog *prog = NULL;
-	int ufd = attr->target_fd;
-	struct bpf_map *map;
-	struct fd f;
-	int err;
-
-	f = fdget(ufd);
-	map = __bpf_map_get(f);
-	if (IS_ERR(map))
-		return PTR_ERR(map);
-
-	if (attach) {
-		prog = bpf_prog_get_type(attr->attach_bpf_fd, type);
-		if (IS_ERR(prog)) {
-			fdput(f);
-			return PTR_ERR(prog);
-		}
-	}
-
-	err = sock_map_prog(map, prog, attr->attach_type);
-	if (err) {
-		fdput(f);
-		if (prog)
-			bpf_prog_put(prog);
-		return err;
-	}
-
-	fdput(f);
-	return 0;
-}
-
 #define BPF_F_ATTACH_MASK \
 	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
 
@@ -1540,7 +1506,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
-	struct cgroup *cgrp;
 	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
@@ -1577,12 +1542,15 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
 		break;
 	case BPF_SK_MSG_VERDICT:
-		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true);
+		ptype = BPF_PROG_TYPE_SK_MSG;
+		break;
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
-		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+		ptype = BPF_PROG_TYPE_SK_SKB;
+		break;
 	case BPF_LIRC_MODE2:
-		return lirc_prog_attach(attr);
+		ptype = BPF_PROG_TYPE_LIRC_MODE2;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1596,18 +1564,20 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		return -EINVAL;
 	}
 
-	cgrp = cgroup_get_from_fd(attr->target_fd);
-	if (IS_ERR(cgrp)) {
-		bpf_prog_put(prog);
-		return PTR_ERR(cgrp);
+	switch (ptype) {
+	case BPF_PROG_TYPE_SK_SKB:
+	case BPF_PROG_TYPE_SK_MSG:
+		ret = sockmap_get_from_fd(attr, ptype, prog);
+		break;
+	case BPF_PROG_TYPE_LIRC_MODE2:
+		ret = lirc_prog_attach(attr, prog);
+		break;
+	default:
+		ret = cgroup_bpf_prog_attach(attr, ptype, prog);
 	}
 
-	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
-				attr->attach_flags);
 	if (ret)
 		bpf_prog_put(prog);
-	cgroup_put(cgrp);
-
 	return ret;
 }
 
@@ -1616,9 +1586,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
-	struct bpf_prog *prog;
-	struct cgroup *cgrp;
-	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -1651,29 +1618,17 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
 		break;
 	case BPF_SK_MSG_VERDICT:
-		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false);
+		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
-		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
 	case BPF_LIRC_MODE2:
 		return lirc_prog_detach(attr);
 	default:
 		return -EINVAL;
 	}
 
-	cgrp = cgroup_get_from_fd(attr->target_fd);
-	if (IS_ERR(cgrp))
-		return PTR_ERR(cgrp);
-
-	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
-	if (IS_ERR(prog))
-		prog = NULL;
-
-	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
-	if (prog)
-		bpf_prog_put(prog);
-	cgroup_put(cgrp);
-	return ret;
+	return cgroup_bpf_prog_detach(attr, ptype);
 }
 
 #define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
@@ -1681,9 +1636,6 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 static int bpf_prog_query(const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
-	struct cgroup *cgrp;
-	int ret;
-
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 	if (CHECK_ATTR(BPF_PROG_QUERY))
@@ -1711,14 +1663,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	default:
 		return -EINVAL;
 	}
-	cgrp = cgroup_get_from_fd(attr->query.target_fd);
-	if (IS_ERR(cgrp))
-		return PTR_ERR(cgrp);
-	ret = cgroup_bpf_query(cgrp, attr, uattr);
-	cgroup_put(cgrp);
-	return ret;
+
+	return cgroup_bpf_prog_query(attr, uattr);
 }
-#endif /* CONFIG_CGROUP_BPF */
 
 #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
 
@@ -2365,7 +2312,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_OBJ_GET:
 		err = bpf_obj_get(&attr);
 		break;
-#ifdef CONFIG_CGROUP_BPF
 	case BPF_PROG_ATTACH:
 		err = bpf_prog_attach(&attr);
 		break;
@@ -2375,7 +2321,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_PROG_QUERY:
 		err = bpf_prog_query(&attr, uattr);
 		break;
-#endif
 	case BPF_PROG_TEST_RUN:
 		err = bpf_prog_test_run(&attr, uattr);
 		break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e2bf834f13a..63aaac52a265 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		if (insn->code != (BPF_JMP | BPF_CALL) ||
 		    insn->src_reg != BPF_PSEUDO_CALL)
 			continue;
+		/* Upon error here we cannot fall back to interpreter but
+		 * need a hard reject of the program. Thus -EFAULT is
+		 * propagated in any case.
+		 */
 		subprog = find_subprog(env, i + insn->imm + 1);
 		if (subprog < 0) {
 			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
@@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 
 	func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
 	if (!func)
-		return -ENOMEM;
+		goto out_undo_insn;
 
 	for (i = 0; i < env->subprog_cnt; i++) {
 		subprog_start = subprog_end;
@@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		tmp = bpf_int_jit_compile(func[i]);
 		if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
 			verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
-			err = -EFAULT;
+			err = -ENOTSUPP;
 			goto out_free;
 		}
 		cond_resched();
@@ -5552,6 +5556,7 @@ out_free:
 		if (func[i])
 			bpf_jit_free(func[i]);
 	kfree(func);
+out_undo_insn:
 	/* cleanup main prog to be interpreted */
 	prog->jit_requested = 0;
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
@@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 		err = jit_subprogs(env);
 		if (err == 0)
 			return 0;
+		if (err == -EFAULT)
+			return err;
 	}
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	for (i = 0; i < prog->len; i++, insn++) {
diff --git a/kernel/compat.c b/kernel/compat.c
index 702aa846ddac..8e40efc2928a 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -324,35 +324,6 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t,  pid, unsigned int, len,
 	return ret;
 }
 
-/* Todo: Delete these extern declarations when get/put_compat_itimerspec64()
- * are moved to kernel/time/time.c .
- */
-extern int __compat_get_timespec64(struct timespec64 *ts64,
-				   const struct compat_timespec __user *cts);
-extern int __compat_put_timespec64(const struct timespec64 *ts64,
-				   struct compat_timespec __user *cts);
-
-int get_compat_itimerspec64(struct itimerspec64 *its,
-			const struct compat_itimerspec __user *uits)
-{
-
-	if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
-	    __compat_get_timespec64(&its->it_value, &uits->it_value))
-		return -EFAULT;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
-
-int put_compat_itimerspec64(const struct itimerspec64 *its,
-			struct compat_itimerspec __user *uits)
-{
-	if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
-	    __compat_put_timespec64(&its->it_value, &uits->it_value))
-		return -EFAULT;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
-
 /*
  * We currently only need the following fields from the sigevent
  * structure: sigev_value, sigev_signo, sig_notify and (sometimes
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0db8938fbb23..ed44d7d34c2d 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -60,6 +60,7 @@ struct cpuhp_cpu_state {
 	bool			rollback;
 	bool			single;
 	bool			bringup;
+	bool			booted_once;
 	struct hlist_node	*node;
 	struct hlist_node	*last;
 	enum cpuhp_state	cb_state;
@@ -290,6 +291,12 @@ void cpus_read_lock(void)
 }
 EXPORT_SYMBOL_GPL(cpus_read_lock);
 
+int cpus_read_trylock(void)
+{
+	return percpu_down_read_trylock(&cpu_hotplug_lock);
+}
+EXPORT_SYMBOL_GPL(cpus_read_trylock);
+
 void cpus_read_unlock(void)
 {
 	percpu_up_read(&cpu_hotplug_lock);
@@ -342,6 +349,85 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
+#ifdef CONFIG_HOTPLUG_SMT
+enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+EXPORT_SYMBOL_GPL(cpu_smt_control);
+
+static bool cpu_smt_available __read_mostly;
+
+void __init cpu_smt_disable(bool force)
+{
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
+		cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		return;
+
+	if (force) {
+		pr_info("SMT: Force disabled\n");
+		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
+	} else {
+		cpu_smt_control = CPU_SMT_DISABLED;
+	}
+}
+
+/*
+ * The decision whether SMT is supported can only be done after the full
+ * CPU identification. Called from architecture code before non boot CPUs
+ * are brought up.
+ */
+void __init cpu_smt_check_topology_early(void)
+{
+	if (!topology_smt_supported())
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
+/*
+ * If SMT was disabled by BIOS, detect it here, after the CPUs have been
+ * brought online. This ensures the smt/l1tf sysfs entries are consistent
+ * with reality. cpu_smt_available is set to true during the bringup of non
+ * boot CPUs when a SMT sibling is detected. Note, this may overwrite
+ * cpu_smt_control's previous setting.
+ */
+void __init cpu_smt_check_topology(void)
+{
+	if (!cpu_smt_available)
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
+static int __init smt_cmdline_disable(char *str)
+{
+	cpu_smt_disable(str && !strcmp(str, "force"));
+	return 0;
+}
+early_param("nosmt", smt_cmdline_disable);
+
+static inline bool cpu_smt_allowed(unsigned int cpu)
+{
+	if (topology_is_primary_thread(cpu))
+		return true;
+
+	/*
+	 * If the CPU is not a 'primary' thread and the booted_once bit is
+	 * set then the processor has SMT support. Store this information
+	 * for the late check of SMT support in cpu_smt_check_topology().
+	 */
+	if (per_cpu(cpuhp_state, cpu).booted_once)
+		cpu_smt_available = true;
+
+	if (cpu_smt_control == CPU_SMT_ENABLED)
+		return true;
+
+	/*
+	 * On x86 it's required to boot all logical CPUs at least once so
+	 * that the init code can get a chance to set CR4.MCE on each
+	 * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
+	 * core will shutdown the machine.
+	 */
+	return !per_cpu(cpuhp_state, cpu).booted_once;
+}
+#else
+static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
+#endif
+
 static inline enum cpuhp_state
 cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
 {
@@ -422,6 +508,16 @@ static int bringup_wait_for_ap(unsigned int cpu)
 	stop_machine_unpark(cpu);
 	kthread_unpark(st->thread);
 
+	/*
+	 * SMT soft disabling on X86 requires to bring the CPU out of the
+	 * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit.  The
+	 * CPU marked itself as booted_once in cpu_notify_starting() so the
+	 * cpu_smt_allowed() check will now return false if this is not the
+	 * primary sibling.
+	 */
+	if (!cpu_smt_allowed(cpu))
+		return -ECANCELED;
+
 	if (st->target <= CPUHP_AP_ONLINE_IDLE)
 		return 0;
 
@@ -754,7 +850,6 @@ static int takedown_cpu(unsigned int cpu)
 
 	/* Park the smpboot threads */
 	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
-	smpboot_park_threads(cpu);
 
 	/*
 	 * Prevent irq alloc/free while the dying cpu reorganizes the
@@ -907,20 +1002,19 @@ out:
 	return ret;
 }
 
+static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
+{
+	if (cpu_hotplug_disabled)
+		return -EBUSY;
+	return _cpu_down(cpu, 0, target);
+}
+
 static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
 {
 	int err;
 
 	cpu_maps_update_begin();
-
-	if (cpu_hotplug_disabled) {
-		err = -EBUSY;
-		goto out;
-	}
-
-	err = _cpu_down(cpu, 0, target);
-
-out:
+	err = cpu_down_maps_locked(cpu, target);
 	cpu_maps_update_done();
 	return err;
 }
@@ -949,6 +1043,7 @@ void notify_cpu_starting(unsigned int cpu)
 	int ret;
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
+	st->booted_once = true;
 	while (st->state < target) {
 		st->state++;
 		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
@@ -1058,6 +1153,10 @@ static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
 		err = -EBUSY;
 		goto out;
 	}
+	if (!cpu_smt_allowed(cpu)) {
+		err = -EPERM;
+		goto out;
+	}
 
 	err = _cpu_up(cpu, 0, target);
 out:
@@ -1274,7 +1373,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	 * otherwise a RCU stall occurs.
 	 */
 	[CPUHP_TIMERS_PREPARE] = {
-		.name			= "timers:dead",
+		.name			= "timers:prepare",
 		.startup.single		= timers_prepare_cpu,
 		.teardown.single	= timers_dead_cpu,
 	},
@@ -1332,7 +1431,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_AP_SMPBOOT_THREADS] = {
 		.name			= "smpboot/threads:online",
 		.startup.single		= smpboot_unpark_threads,
-		.teardown.single	= NULL,
+		.teardown.single	= smpboot_park_threads,
 	},
 	[CPUHP_AP_IRQ_AFFINITY_ONLINE] = {
 		.name			= "irq/affinity:online",
@@ -1344,6 +1443,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= perf_event_init_cpu,
 		.teardown.single	= perf_event_exit_cpu,
 	},
+	[CPUHP_AP_WATCHDOG_ONLINE] = {
+		.name			= "lockup_detector:online",
+		.startup.single		= lockup_detector_online_cpu,
+		.teardown.single	= lockup_detector_offline_cpu,
+	},
 	[CPUHP_AP_WORKQUEUE_ONLINE] = {
 		.name			= "workqueue:online",
 		.startup.single		= workqueue_online_cpu,
@@ -1906,10 +2010,172 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
 	NULL
 };
 
+#ifdef CONFIG_HOTPLUG_SMT
+
+static const char *smt_states[] = {
+	[CPU_SMT_ENABLED]		= "on",
+	[CPU_SMT_DISABLED]		= "off",
+	[CPU_SMT_FORCE_DISABLED]	= "forceoff",
+	[CPU_SMT_NOT_SUPPORTED]		= "notsupported",
+};
+
+static ssize_t
+show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
+}
+
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = true;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = false;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	for_each_online_cpu(cpu) {
+		if (topology_is_primary_thread(cpu))
+			continue;
+		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+		if (ret)
+			break;
+		/*
+		 * As this needs to hold the cpu maps lock it's impossible
+		 * to call device_offline() because that ends up calling
+		 * cpu_down() which takes cpu maps lock. cpu maps lock
+		 * needs to be held as this might race against in kernel
+		 * abusers of the hotplug machinery (thermal management).
+		 *
+		 * So nothing would update device:offline state. That would
+		 * leave the sysfs entry stale and prevent onlining after
+		 * smt control has been changed to 'off' again. This is
+		 * called under the sysfs hotplug lock, so it is properly
+		 * serialized against the regular offline usage.
+		 */
+		cpuhp_offline_cpu_device(cpu);
+	}
+	if (!ret)
+		cpu_smt_control = ctrlval;
+	cpu_maps_update_done();
+	return ret;
+}
+
+static int cpuhp_smt_enable(void)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	cpu_smt_control = CPU_SMT_ENABLED;
+	for_each_present_cpu(cpu) {
+		/* Skip online CPUs and CPUs on offline nodes */
+		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+			continue;
+		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+		if (ret)
+			break;
+		/* See comment in cpuhp_smt_disable() */
+		cpuhp_online_cpu_device(cpu);
+	}
+	cpu_maps_update_done();
+	return ret;
+}
+
+static ssize_t
+store_smt_control(struct device *dev, struct device_attribute *attr,
+		  const char *buf, size_t count)
+{
+	int ctrlval, ret;
+
+	if (sysfs_streq(buf, "on"))
+		ctrlval = CPU_SMT_ENABLED;
+	else if (sysfs_streq(buf, "off"))
+		ctrlval = CPU_SMT_DISABLED;
+	else if (sysfs_streq(buf, "forceoff"))
+		ctrlval = CPU_SMT_FORCE_DISABLED;
+	else
+		return -EINVAL;
+
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
+		return -EPERM;
+
+	if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		return -ENODEV;
+
+	ret = lock_device_hotplug_sysfs();
+	if (ret)
+		return ret;
+
+	if (ctrlval != cpu_smt_control) {
+		switch (ctrlval) {
+		case CPU_SMT_ENABLED:
+			ret = cpuhp_smt_enable();
+			break;
+		case CPU_SMT_DISABLED:
+		case CPU_SMT_FORCE_DISABLED:
+			ret = cpuhp_smt_disable(ctrlval);
+			break;
+		}
+	}
+
+	unlock_device_hotplug();
+	return ret ? ret : count;
+}
+static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
+
+static ssize_t
+show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	bool active = topology_max_smt_threads() > 1;
+
+	return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
+}
+static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
+
+static struct attribute *cpuhp_smt_attrs[] = {
+	&dev_attr_control.attr,
+	&dev_attr_active.attr,
+	NULL
+};
+
+static const struct attribute_group cpuhp_smt_attr_group = {
+	.attrs = cpuhp_smt_attrs,
+	.name = "smt",
+	NULL
+};
+
+static int __init cpu_smt_state_init(void)
+{
+	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
+				  &cpuhp_smt_attr_group);
+}
+
+#else
+static inline int cpu_smt_state_init(void) { return 0; }
+#endif
+
 static int __init cpuhp_sysfs_init(void)
 {
 	int cpu, ret;
 
+	ret = cpu_smt_state_init();
+	if (ret)
+		return ret;
+
 	ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
 				 &cpuhp_cpu_root_attr_group);
 	if (ret)
@@ -2010,7 +2276,10 @@ void __init boot_cpu_init(void)
 /*
  * Must be called _AFTER_ setting up the per_cpu areas
  */
-void __init boot_cpu_state_init(void)
+void __init boot_cpu_hotplug_init(void)
 {
-	per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
+#ifdef CONFIG_SMP
+	this_cpu_write(cpuhp_state.booted_once, true);
+#endif
+	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 }
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8be8106270c2..c2860c5a9e96 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -180,10 +180,10 @@ int dma_direct_supported(struct device *dev, u64 mask)
 		return 0;
 #endif
 	/*
-	 * Various PCI/PCIe bridges have broken support for > 32bit DMA even
-	 * if the device itself might support it.
+	 * Upstream PCI/PCIe bridges or SoC interconnects may not carry
+	 * as many DMA address bits as the device itself supports.
 	 */
-	if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32))
+	if (dev->bus_dma_mask && mask > dev->bus_dma_mask)
 		return 0;
 	return 1;
 }
diff --git a/kernel/dma/noncoherent.c b/kernel/dma/noncoherent.c
index 79e9a757387f..031fe235d958 100644
--- a/kernel/dma/noncoherent.c
+++ b/kernel/dma/noncoherent.c
@@ -49,11 +49,13 @@ static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
 	return nents;
 }
 
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
 	arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
+	arch_sync_dma_for_cpu_all(dev);
 }
 
 static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
@@ -64,6 +66,7 @@ static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
 
 	for_each_sg(sgl, sg, nents, i)
 		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+	arch_sync_dma_for_cpu_all(dev);
 }
 
 static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
@@ -89,7 +92,8 @@ const struct dma_map_ops dma_noncoherent_ops = {
 	.sync_sg_for_device	= dma_noncoherent_sync_sg_for_device,
 	.map_page		= dma_noncoherent_map_page,
 	.map_sg			= dma_noncoherent_map_sg,
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 	.sync_single_for_cpu	= dma_noncoherent_sync_single_for_cpu,
 	.sync_sg_for_cpu	= dma_noncoherent_sync_sg_for_cpu,
 	.unmap_page		= dma_noncoherent_unmap_page,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 04b68d9dffac..4f8a6dbf0b60 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -17,6 +17,8 @@
  * 08/12/11 beckyb	Add highmem support
  */
 
+#define pr_fmt(fmt) "software IO TLB: " fmt
+
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
 #include <linux/mm.h>
@@ -162,20 +164,16 @@ static bool no_iotlb_memory;
 void swiotlb_print_info(void)
 {
 	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-	unsigned char *vstart, *vend;
 
 	if (no_iotlb_memory) {
-		pr_warn("software IO TLB: No low mem\n");
+		pr_warn("No low mem\n");
 		return;
 	}
 
-	vstart = phys_to_virt(io_tlb_start);
-	vend = phys_to_virt(io_tlb_end);
-
-	printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+	pr_info("mapped [mem %#010llx-%#010llx] (%luMB)\n",
 	       (unsigned long long)io_tlb_start,
 	       (unsigned long long)io_tlb_end,
-	       bytes >> 20, vstart, vend - 1);
+	       bytes >> 20);
 }
 
 /*
@@ -275,7 +273,7 @@ swiotlb_init(int verbose)
 	if (io_tlb_start)
 		memblock_free_early(io_tlb_start,
 				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
-	pr_warn("Cannot allocate SWIOTLB buffer");
+	pr_warn("Cannot allocate buffer");
 	no_iotlb_memory = true;
 }
 
@@ -317,8 +315,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
 		return -ENOMEM;
 	}
 	if (order != get_order(bytes)) {
-		printk(KERN_WARNING "Warning: only able to allocate %ld MB "
-		       "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+		pr_warn("only able to allocate %ld MB\n",
+			(PAGE_SIZE << order) >> 20);
 		io_tlb_nslabs = SLABS_PER_PAGE << order;
 	}
 	rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
@@ -1085,3 +1083,4 @@ const struct dma_map_ops swiotlb_dma_ops = {
 	.unmap_page		= swiotlb_unmap_page,
 	.dma_supported		= dma_direct_supported,
 };
+EXPORT_SYMBOL(swiotlb_dma_ops);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 80cca2b30c4f..80f456ec5d89 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1656,7 +1656,7 @@ perf_event_groups_next(struct perf_event *event)
 				typeof(*event), group_node))
 
 /*
- * Add a event from the lists for its context.
+ * Add an event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
  */
 static void
@@ -1844,7 +1844,7 @@ static void perf_group_attach(struct perf_event *event)
 }
 
 /*
- * Remove a event from the lists for its context.
+ * Remove an event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
  */
 static void
@@ -2148,7 +2148,7 @@ static void __perf_event_disable(struct perf_event *event,
 }
 
 /*
- * Disable a event.
+ * Disable an event.
  *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
@@ -2677,7 +2677,7 @@ static void __perf_event_enable(struct perf_event *event,
 }
 
 /*
- * Enable a event.
+ * Enable an event.
  *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
@@ -2755,7 +2755,7 @@ static int __perf_event_stop(void *info)
 	 * events will refuse to restart because of rb::aux_mmap_count==0,
 	 * see comments in perf_aux_output_begin().
 	 *
-	 * Since this is happening on a event-local CPU, no trace is lost
+	 * Since this is happening on an event-local CPU, no trace is lost
 	 * while restarting.
 	 */
 	if (sd->restart)
@@ -4827,7 +4827,7 @@ __perf_read(struct perf_event *event, char __user *buf, size_t count)
 	int ret;
 
 	/*
-	 * Return end-of-file for a read on a event that is in
+	 * Return end-of-file for a read on an event that is in
 	 * error state (i.e. because it was pinned but it couldn't be
 	 * scheduled on to the CPU at some point).
 	 */
@@ -5246,8 +5246,8 @@ void perf_event_update_userpage(struct perf_event *event)
 
 	userpg = rb->user_page;
 	/*
-	 * Disable preemption so as to not let the corresponding user-space
-	 * spin too long if we get preempted.
+	 * Disable preemption to guarantee consistent time stamps are stored to
+	 * the user page.
 	 */
 	preempt_disable();
 	++userpg->lock;
@@ -5273,11 +5273,11 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(perf_event_update_userpage);
 
-static int perf_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t perf_mmap_fault(struct vm_fault *vmf)
 {
 	struct perf_event *event = vmf->vma->vm_file->private_data;
 	struct ring_buffer *rb;
-	int ret = VM_FAULT_SIGBUS;
+	vm_fault_t ret = VM_FAULT_SIGBUS;
 
 	if (vmf->flags & FAULT_FLAG_MKWRITE) {
 		if (vmf->pgoff == 0)
@@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt)
 
 static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
 
-static struct perf_callchain_entry *
+struct perf_callchain_entry *
 perf_callchain(struct perf_event *event, struct pt_regs *regs)
 {
 	bool kernel = !event->attr.exclude_callchain_kernel;
@@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int size = 1;
 
-		data->callchain = perf_callchain(event, regs);
+		if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+			data->callchain = perf_callchain(event, regs);
+
 		size += data->callchain->nr;
 
 		header->size += size * sizeof(u64);
@@ -6482,7 +6484,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		data->phys_addr = perf_virt_to_phys(data->addr);
 }
 
-static void __always_inline
+static __always_inline void
 __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
 		    struct pt_regs *regs,
@@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 				     struct file *file, unsigned long offset,
 				     unsigned long size)
 {
+	/* d_inode(NULL) won't be equal to any mapped user-space file */
+	if (!filter->path.dentry)
+		return false;
+
 	if (d_inode(filter->path.dentry) != file_inode(file))
 		return false;
 
@@ -9898,7 +9904,7 @@ enabled:
 }
 
 /*
- * Allocate and initialize a event structure
+ * Allocate and initialize an event structure
  */
 static struct perf_event *
 perf_event_alloc(struct perf_event_attr *attr, int cpu,
@@ -11229,7 +11235,7 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
 }
 
 /*
- * Inherit a event from parent task to child task.
+ * Inherit an event from parent task to child task.
  *
  * Returns:
  *  - valid pointer on success
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 6e28d2866be5..b3814fce5ecb 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -345,13 +345,13 @@ void release_bp_slot(struct perf_event *bp)
 	mutex_unlock(&nr_bp_mutex);
 }
 
-static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 {
 	int err;
 
 	__release_bp_slot(bp, old_type);
 
-	err = __reserve_bp_slot(bp, bp->attr.bp_type);
+	err = __reserve_bp_slot(bp, new_type);
 	if (err) {
 		/*
 		 * Reserve the old_type slot back in case
@@ -367,12 +367,12 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
 	return err;
 }
 
-static int modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 {
 	int ret;
 
 	mutex_lock(&nr_bp_mutex);
-	ret = __modify_bp_slot(bp, old_type);
+	ret = __modify_bp_slot(bp, old_type, new_type);
 	mutex_unlock(&nr_bp_mutex);
 	return ret;
 }
@@ -400,16 +400,18 @@ int dbg_release_bp_slot(struct perf_event *bp)
 	return 0;
 }
 
-static int validate_hw_breakpoint(struct perf_event *bp)
+static int hw_breakpoint_parse(struct perf_event *bp,
+			       const struct perf_event_attr *attr,
+			       struct arch_hw_breakpoint *hw)
 {
-	int ret;
+	int err;
 
-	ret = arch_validate_hwbkpt_settings(bp);
-	if (ret)
-		return ret;
+	err = hw_breakpoint_arch_parse(bp, attr, hw);
+	if (err)
+		return err;
 
-	if (arch_check_bp_in_kernelspace(bp)) {
-		if (bp->attr.exclude_kernel)
+	if (arch_check_bp_in_kernelspace(hw)) {
+		if (attr->exclude_kernel)
 			return -EINVAL;
 		/*
 		 * Don't let unprivileged users set a breakpoint in the trap
@@ -424,19 +426,22 @@ static int validate_hw_breakpoint(struct perf_event *bp)
 
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
-	int ret;
-
-	ret = reserve_bp_slot(bp);
-	if (ret)
-		return ret;
+	struct arch_hw_breakpoint hw;
+	int err;
 
-	ret = validate_hw_breakpoint(bp);
+	err = reserve_bp_slot(bp);
+	if (err)
+		return err;
 
-	/* if arch_validate_hwbkpt_settings() fails then release bp slot */
-	if (ret)
+	err = hw_breakpoint_parse(bp, &bp->attr, &hw);
+	if (err) {
 		release_bp_slot(bp);
+		return err;
+	}
 
-	return ret;
+	bp->hw.info = hw;
+
+	return 0;
 }
 
 /**
@@ -456,35 +461,44 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
+static void hw_breakpoint_copy_attr(struct perf_event_attr *to,
+				    struct perf_event_attr *from)
+{
+	to->bp_addr = from->bp_addr;
+	to->bp_type = from->bp_type;
+	to->bp_len  = from->bp_len;
+	to->disabled = from->disabled;
+}
+
 int
 modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
 			        bool check)
 {
-	u64 old_addr = bp->attr.bp_addr;
-	u64 old_len  = bp->attr.bp_len;
-	int old_type = bp->attr.bp_type;
-	bool modify  = attr->bp_type != old_type;
-	int err = 0;
+	struct arch_hw_breakpoint hw;
+	int err;
 
-	bp->attr.bp_addr = attr->bp_addr;
-	bp->attr.bp_type = attr->bp_type;
-	bp->attr.bp_len  = attr->bp_len;
+	err = hw_breakpoint_parse(bp, attr, &hw);
+	if (err)
+		return err;
 
-	if (check && memcmp(&bp->attr, attr, sizeof(*attr)))
-		return -EINVAL;
+	if (check) {
+		struct perf_event_attr old_attr;
 
-	err = validate_hw_breakpoint(bp);
-	if (!err && modify)
-		err = modify_bp_slot(bp, old_type);
+		old_attr = bp->attr;
+		hw_breakpoint_copy_attr(&old_attr, attr);
+		if (memcmp(&old_attr, attr, sizeof(*attr)))
+			return -EINVAL;
+	}
 
-	if (err) {
-		bp->attr.bp_addr = old_addr;
-		bp->attr.bp_type = old_type;
-		bp->attr.bp_len  = old_len;
-		return err;
+	if (bp->attr.bp_type != attr->bp_type) {
+		err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type);
+		if (err)
+			return err;
 	}
 
-	bp->attr.disabled = attr->disabled;
+	hw_breakpoint_copy_attr(&bp->attr, attr);
+	bp->hw.info = hw;
+
 	return 0;
 }
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ccc579a7d32e..aed1ba569954 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -918,7 +918,7 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 EXPORT_SYMBOL_GPL(uprobe_register);
 
 /*
- * uprobe_apply - unregister a already registered probe.
+ * uprobe_apply - unregister an already registered probe.
  * @inode: the file in which the probe has to be removed.
  * @offset: offset from the start of the file.
  * @uc: consumer which wants to add more or remove some breakpoints
@@ -947,7 +947,7 @@ int uprobe_apply(struct inode *inode, loff_t offset,
 }
 
 /*
- * uprobe_unregister - unregister a already registered probe.
+ * uprobe_unregister - unregister an already registered probe.
  * @inode: the file in which the probe has to be removed.
  * @offset: offset from the start of the file.
  * @uc: identify which probe if multiple probes are colocated.
@@ -1403,7 +1403,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri)
 
 /*
  * Called with no locks held.
- * Called in context of a exiting or a exec-ing thread.
+ * Called in context of an exiting or an exec-ing thread.
  */
 void uprobe_free_utask(struct task_struct *t)
 {
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 5349c91c2298..bc80a4e268c0 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -184,9 +184,6 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
 	if (should_fail(&fei_fault_attr, 1)) {
 		regs_set_return_value(regs, attr->retval);
 		override_function_with_return(regs);
-		/* Kprobe specific fixup */
-		reset_current_kprobe();
-		preempt_enable_no_resched();
 		return 1;
 	}
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 9440d61b925c..33112315b5c0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -303,11 +303,36 @@ struct kmem_cache *files_cachep;
 struct kmem_cache *fs_cachep;
 
 /* SLAB cache for vm_area_struct structures */
-struct kmem_cache *vm_area_cachep;
+static struct kmem_cache *vm_area_cachep;
 
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
+struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+
+	if (vma)
+		vma_init(vma, mm);
+	return vma;
+}
+
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
+{
+	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+
+	if (new) {
+		*new = *orig;
+		INIT_LIST_HEAD(&new->anon_vma_chain);
+	}
+	return new;
+}
+
+void vm_area_free(struct vm_area_struct *vma)
+{
+	kmem_cache_free(vm_area_cachep, vma);
+}
+
 static void account_kernel_stack(struct task_struct *tsk, int account)
 {
 	void *stack = task_stack_page(tsk);
@@ -455,11 +480,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 				goto fail_nomem;
 			charge = len;
 		}
-		tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+		tmp = vm_area_dup(mpnt);
 		if (!tmp)
 			goto fail_nomem;
-		*tmp = *mpnt;
-		INIT_LIST_HEAD(&tmp->anon_vma_chain);
 		retval = vma_dup_policy(mpnt, tmp);
 		if (retval)
 			goto fail_nomem_policy;
@@ -539,7 +562,7 @@ fail_uprobe_end:
 fail_nomem_anon_vma_fork:
 	mpol_put(vma_policy(tmp));
 fail_nomem_policy:
-	kmem_cache_free(vm_area_cachep, tmp);
+	vm_area_free(tmp);
 fail_nomem:
 	retval = -ENOMEM;
 	vm_unacct_memory(charge);
@@ -843,6 +866,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->fail_nth = 0;
 #endif
 
+#ifdef CONFIG_BLK_CGROUP
+	tsk->throttle_queue = NULL;
+	tsk->use_memdelay = 0;
+#endif
+
 	return tsk;
 
 free_stack:
@@ -2253,6 +2281,8 @@ static void sighand_ctor(void *data)
 
 void __init proc_caches_init(void)
 {
+	unsigned int mm_size;
+
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -2269,15 +2299,16 @@ void __init proc_caches_init(void)
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			NULL);
+
 	/*
-	 * FIXME! The "sizeof(struct mm_struct)" currently includes the
-	 * whole struct cpumask for the OFFSTACK case. We could change
-	 * this to *only* allocate as much of it as required by the
-	 * maximum number of CPU's we can ever have.  The cpumask_allocation
-	 * is at the end of the structure, exactly for that reason.
+	 * The mm_cpumask is located at the end of mm_struct, and is
+	 * dynamically sized based on the maximum CPU number this system
+	 * can have, taking hotplug into account (nr_cpu_ids).
 	 */
+	mm_size = sizeof(struct mm_struct) + cpumask_size();
+
 	mm_cachep = kmem_cache_create_usercopy("mm_struct",
-			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
+			mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			offsetof(struct mm_struct, saved_auxv),
 			sizeof_field(struct mm_struct, saved_auxv),
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 6f56a9e219fa..b162b74611e4 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -15,7 +15,9 @@
 atomic_t system_freezing_cnt = ATOMIC_INIT(0);
 EXPORT_SYMBOL(system_freezing_cnt);
 
-/* indicate whether PM freezing is in effect, protected by pm_mutex */
+/* indicate whether PM freezing is in effect, protected by
+ * system_transition_mutex
+ */
 bool pm_freezing;
 bool pm_nosig_freezing;
 
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index c6766f326072..5f3e2baefca9 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -134,7 +134,6 @@ config GENERIC_IRQ_DEBUGFS
 endmenu
 
 config GENERIC_IRQ_MULTI_HANDLER
-	depends on !MULTI_IRQ_HANDLER
 	bool
 	help
 	  Allow to specify the low level IRQ handler at run time.
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index afc7f902d74a..578d0e5f1b5b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -443,6 +443,7 @@ static void free_desc(unsigned int irq)
 	 * We free the descriptor, masks and stat fields via RCU. That
 	 * allows demultiplex interrupts to do rcu based management of
 	 * the child interrupts.
+	 * This also allows us to use rcu in kstat_irqs_usr().
 	 */
 	call_rcu(&desc->rcu, delayed_free_desc);
 }
@@ -928,17 +929,17 @@ unsigned int kstat_irqs(unsigned int irq)
  * kstat_irqs_usr - Get the statistics for an interrupt
  * @irq:	The interrupt number
  *
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. Contrary to kstat_irqs() this can be called from any
- * preemptible context. It's protected against concurrent removal of
- * an interrupt descriptor when sparse irqs are enabled.
+ * Returns the sum of interrupt counts on all cpus since boot for @irq.
+ * Contrary to kstat_irqs() this can be called from any context.
+ * It uses rcu since a concurrent removal of an interrupt descriptor is
+ * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
 	unsigned int sum;
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	sum = kstat_irqs(irq);
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return sum;
 }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index daeabd791d58..fb86146037a7 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -790,9 +790,19 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
 
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
-	set_current_state(TASK_INTERRUPTIBLE);
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
 
-	while (!kthread_should_stop()) {
+		if (kthread_should_stop()) {
+			/* may need to run one last time */
+			if (test_and_clear_bit(IRQTF_RUNTHREAD,
+					       &action->thread_flags)) {
+				__set_current_state(TASK_RUNNING);
+				return 0;
+			}
+			__set_current_state(TASK_RUNNING);
+			return -1;
+		}
 
 		if (test_and_clear_bit(IRQTF_RUNTHREAD,
 				       &action->thread_flags)) {
@@ -800,10 +810,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 			return 0;
 		}
 		schedule();
-		set_current_state(TASK_INTERRUPTIBLE);
 	}
-	__set_current_state(TASK_RUNNING);
-	return -1;
 }
 
 /*
@@ -1024,11 +1031,8 @@ static int irq_thread(void *data)
 	/*
 	 * This is the regular exit path. __free_irq() is stopping the
 	 * thread via kthread_stop() after calling
-	 * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
-	 * oneshot mask bit can be set. We cannot verify that as we
-	 * cannot touch the oneshot mask at this point anymore as
-	 * __setup_irq() might have given out currents thread_mask
-	 * again.
+	 * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
+	 * oneshot mask bit can be set.
 	 */
 	task_work_cancel(current, irq_thread_dtor);
 	return 0;
@@ -1068,6 +1072,13 @@ static int irq_setup_forced_threading(struct irqaction *new)
 	if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
 		return 0;
 
+	/*
+	 * No further action required for interrupts which are requested as
+	 * threaded interrupts already
+	 */
+	if (new->handler == irq_default_primary_handler)
+		return 0;
+
 	new->flags |= IRQF_ONESHOT;
 
 	/*
@@ -1075,7 +1086,7 @@ static int irq_setup_forced_threading(struct irqaction *new)
 	 * thread handler. We force thread them as well by creating a
 	 * secondary action.
 	 */
-	if (new->handler != irq_default_primary_handler && new->thread_fn) {
+	if (new->handler && new->thread_fn) {
 		/* Allocate the secondary action */
 		new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
 		if (!new->secondary)
@@ -1244,8 +1255,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	/*
 	 * Protects against a concurrent __free_irq() call which might wait
-	 * for synchronize_irq() to complete without holding the optional
-	 * chip bus lock and desc->lock.
+	 * for synchronize_hardirq() to complete without holding the optional
+	 * chip bus lock and desc->lock. Also protects against handing out
+	 * a recycled oneshot thread_mask bit while it's still in use by
+	 * its previous owner.
 	 */
 	mutex_lock(&desc->request_mutex);
 
@@ -1564,9 +1577,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 
 	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
 
-	if (!desc)
-		return NULL;
-
 	mutex_lock(&desc->request_mutex);
 	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
@@ -1613,11 +1623,11 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	/*
 	 * Drop bus_lock here so the changes which were done in the chip
 	 * callbacks above are synced out to the irq chips which hang
-	 * behind a slow bus (I2C, SPI) before calling synchronize_irq().
+	 * behind a slow bus (I2C, SPI) before calling synchronize_hardirq().
 	 *
 	 * Aside of that the bus_lock can also be taken from the threaded
 	 * handler in irq_finalize_oneshot() which results in a deadlock
-	 * because synchronize_irq() would wait forever for the thread to
+	 * because kthread_stop() would wait forever for the thread to
 	 * complete, which is blocked on the bus lock.
 	 *
 	 * The still held desc->request_mutex() protects against a
@@ -1629,7 +1639,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	unregister_handler_proc(irq, action);
 
 	/* Make sure it's not being used on another CPU: */
-	synchronize_irq(irq);
+	synchronize_hardirq(irq);
 
 #ifdef CONFIG_DEBUG_SHIRQ
 	/*
@@ -1638,7 +1648,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	 * is so by doing an extra call to the handler ....
 	 *
 	 * ( We do this after actually deregistering it, to make sure that a
-	 *   'real' IRQ doesn't run in * parallel with our fake. )
+	 *   'real' IRQ doesn't run in parallel with our fake. )
 	 */
 	if (action->flags & IRQF_SHARED) {
 		local_irq_save(flags);
@@ -1647,6 +1657,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	}
 #endif
 
+	/*
+	 * The action has already been removed above, but the thread writes
+	 * its oneshot mask bit when it completes. Though request_mutex is
+	 * held across this which prevents __setup_irq() from handing out
+	 * the same bit to a newly requested action.
+	 */
 	if (action->thread) {
 		kthread_stop(action->thread);
 		put_task_struct(action->thread);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 37eda10f5c36..da9addb8d655 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -475,22 +475,24 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	desc = irq_to_desc(i);
 	if (!desc)
 		goto outsparse;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for_each_online_cpu(j)
-		any_count |= kstat_irqs_cpu(i, j);
-	action = desc->action;
-	if ((!action || irq_desc_is_chained(desc)) && !any_count)
-		goto out;
+	if (desc->kstat_irqs)
+		for_each_online_cpu(j)
+			any_count |= *per_cpu_ptr(desc->kstat_irqs, j);
+
+	if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
+		goto outsparse;
 
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+		seq_printf(p, "%10u ", desc->kstat_irqs ?
+					*per_cpu_ptr(desc->kstat_irqs, j) : 0);
 
+	raw_spin_lock_irqsave(&desc->lock, flags);
 	if (desc->irq_data.chip) {
 		if (desc->irq_data.chip->irq_print_chip)
 			desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
@@ -511,6 +513,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (desc->name)
 		seq_printf(p, "-%-8s", desc->name);
 
+	action = desc->action;
 	if (action) {
 		seq_printf(p, "  %s", action->name);
 		while ((action = action->next) != NULL)
@@ -518,10 +521,9 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	seq_putc(p, '\n');
-out:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 outsparse:
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return 0;
 }
 #endif
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ea619021d901..ab257be4d924 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -627,8 +627,8 @@ static void optimize_kprobe(struct kprobe *p)
 	    (kprobe_disabled(p) || kprobes_all_disarmed))
 		return;
 
-	/* Both of break_handler and post_handler are not supported. */
-	if (p->break_handler || p->post_handler)
+	/* kprobes with post_handler can not be optimized */
+	if (p->post_handler)
 		return;
 
 	op = container_of(p, struct optimized_kprobe, kp);
@@ -710,9 +710,7 @@ static void reuse_unused_kprobe(struct kprobe *ap)
 	 * there is still a relative jump) and disabled.
 	 */
 	op = container_of(ap, struct optimized_kprobe, kp);
-	if (unlikely(list_empty(&op->list)))
-		printk(KERN_WARNING "Warning: found a stray unused "
-			"aggrprobe@%p\n", ap->addr);
+	WARN_ON_ONCE(list_empty(&op->list));
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
@@ -985,7 +983,8 @@ static int arm_kprobe_ftrace(struct kprobe *p)
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 				   (unsigned long)p->addr, 0, 0);
 	if (ret) {
-		pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+		pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n",
+			 p->addr, ret);
 		return ret;
 	}
 
@@ -1025,7 +1024,8 @@ static int disarm_kprobe_ftrace(struct kprobe *p)
 
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 			   (unsigned long)p->addr, 1, 0);
-	WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+	WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n",
+		  p->addr, ret);
 	return ret;
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
@@ -1116,20 +1116,6 @@ static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
 }
 NOKPROBE_SYMBOL(aggr_fault_handler);
 
-static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe *cur = __this_cpu_read(kprobe_instance);
-	int ret = 0;
-
-	if (cur && cur->break_handler) {
-		if (cur->break_handler(cur, regs))
-			ret = 1;
-	}
-	reset_kprobe_instance();
-	return ret;
-}
-NOKPROBE_SYMBOL(aggr_break_handler);
-
 /* Walks the list and increments nmissed count for multiprobe case */
 void kprobes_inc_nmissed_count(struct kprobe *p)
 {
@@ -1270,24 +1256,15 @@ static void cleanup_rp_inst(struct kretprobe *rp)
 }
 NOKPROBE_SYMBOL(cleanup_rp_inst);
 
-/*
-* Add the new probe to ap->list. Fail if this is the
-* second jprobe at the address - two jprobes can't coexist
-*/
+/* Add the new probe to ap->list */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
 	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
 
-	if (p->break_handler || p->post_handler)
+	if (p->post_handler)
 		unoptimize_kprobe(ap, true);	/* Fall back to normal kprobe */
 
-	if (p->break_handler) {
-		if (ap->break_handler)
-			return -EEXIST;
-		list_add_tail_rcu(&p->list, &ap->list);
-		ap->break_handler = aggr_break_handler;
-	} else
-		list_add_rcu(&p->list, &ap->list);
+	list_add_rcu(&p->list, &ap->list);
 	if (p->post_handler && !ap->post_handler)
 		ap->post_handler = aggr_post_handler;
 
@@ -1310,8 +1287,6 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 	/* We don't care the kprobe which has gone. */
 	if (p->post_handler && !kprobe_gone(p))
 		ap->post_handler = aggr_post_handler;
-	if (p->break_handler && !kprobe_gone(p))
-		ap->break_handler = aggr_break_handler;
 
 	INIT_LIST_HEAD(&ap->list);
 	INIT_HLIST_NODE(&ap->hlist);
@@ -1706,8 +1681,6 @@ static int __unregister_kprobe_top(struct kprobe *p)
 		goto disarmed;
 	else {
 		/* If disabling probe has special handlers, update aggrprobe */
-		if (p->break_handler && !kprobe_gone(p))
-			ap->break_handler = NULL;
 		if (p->post_handler && !kprobe_gone(p)) {
 			list_for_each_entry_rcu(list_p, &ap->list, list) {
 				if ((list_p != p) && (list_p->post_handler))
@@ -1812,77 +1785,6 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 	return (unsigned long)entry;
 }
 
-#if 0
-int register_jprobes(struct jprobe **jps, int num)
-{
-	int ret = 0, i;
-
-	if (num <= 0)
-		return -EINVAL;
-
-	for (i = 0; i < num; i++) {
-		ret = register_jprobe(jps[i]);
-
-		if (ret < 0) {
-			if (i > 0)
-				unregister_jprobes(jps, i);
-			break;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(register_jprobes);
-
-int register_jprobe(struct jprobe *jp)
-{
-	unsigned long addr, offset;
-	struct kprobe *kp = &jp->kp;
-
-	/*
-	 * Verify probepoint as well as the jprobe handler are
-	 * valid function entry points.
-	 */
-	addr = arch_deref_entry_point(jp->entry);
-
-	if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 &&
-	    kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) {
-		kp->pre_handler = setjmp_pre_handler;
-		kp->break_handler = longjmp_break_handler;
-		return register_kprobe(kp);
-	}
-
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(register_jprobe);
-
-void unregister_jprobe(struct jprobe *jp)
-{
-	unregister_jprobes(&jp, 1);
-}
-EXPORT_SYMBOL_GPL(unregister_jprobe);
-
-void unregister_jprobes(struct jprobe **jps, int num)
-{
-	int i;
-
-	if (num <= 0)
-		return;
-	mutex_lock(&kprobe_mutex);
-	for (i = 0; i < num; i++)
-		if (__unregister_kprobe_top(&jps[i]->kp) < 0)
-			jps[i]->kp.addr = NULL;
-	mutex_unlock(&kprobe_mutex);
-
-	synchronize_sched();
-	for (i = 0; i < num; i++) {
-		if (jps[i]->kp.addr)
-			__unregister_kprobe_bottom(&jps[i]->kp);
-	}
-}
-EXPORT_SYMBOL_GPL(unregister_jprobes);
-#endif
-
 #ifdef CONFIG_KRETPROBES
 /*
  * This kprobe pre_handler is registered with every kretprobe. When probe
@@ -1982,7 +1884,6 @@ int register_kretprobe(struct kretprobe *rp)
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
 	rp->kp.fault_handler = NULL;
-	rp->kp.break_handler = NULL;
 
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {
@@ -2105,7 +2006,6 @@ static void kill_kprobe(struct kprobe *p)
 		list_for_each_entry_rcu(kp, &p->list, list)
 			kp->flags |= KPROBE_FLAG_GONE;
 		p->post_handler = NULL;
-		p->break_handler = NULL;
 		kill_optimized_kprobe(p);
 	}
 	/*
@@ -2169,11 +2069,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(enable_kprobe);
 
+/* Caller must NOT call this in usual path. This is only for critical case */
 void dump_kprobe(struct kprobe *kp)
 {
-	printk(KERN_WARNING "Dumping kprobe:\n");
-	printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
-	       kp->symbol_name, kp->addr, kp->offset);
+	pr_err("Dumping kprobe:\n");
+	pr_err("Name: %s\nOffset: %x\nAddress: %pS\n",
+	       kp->symbol_name, kp->offset, kp->addr);
 }
 NOKPROBE_SYMBOL(dump_kprobe);
 
@@ -2196,11 +2097,8 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
 		entry = arch_deref_entry_point((void *)*iter);
 
 		if (!kernel_text_address(entry) ||
-		    !kallsyms_lookup_size_offset(entry, &size, &offset)) {
-			pr_err("Failed to find blacklist at %p\n",
-				(void *)entry);
+		    !kallsyms_lookup_size_offset(entry, &size, &offset))
 			continue;
-		}
 
 		ent = kmalloc(sizeof(*ent), GFP_KERNEL);
 		if (!ent)
@@ -2326,21 +2224,23 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
 		const char *sym, int offset, char *modname, struct kprobe *pp)
 {
 	char *kprobe_type;
+	void *addr = p->addr;
 
 	if (p->pre_handler == pre_handler_kretprobe)
 		kprobe_type = "r";
-	else if (p->pre_handler == setjmp_pre_handler)
-		kprobe_type = "j";
 	else
 		kprobe_type = "k";
 
+	if (!kallsyms_show_value())
+		addr = NULL;
+
 	if (sym)
-		seq_printf(pi, "%p  %s  %s+0x%x  %s ",
-			p->addr, kprobe_type, sym, offset,
+		seq_printf(pi, "%px  %s  %s+0x%x  %s ",
+			addr, kprobe_type, sym, offset,
 			(modname ? modname : " "));
-	else
-		seq_printf(pi, "%p  %s  %p ",
-			p->addr, kprobe_type, p->addr);
+	else	/* try to use %pS */
+		seq_printf(pi, "%px  %s  %pS ",
+			addr, kprobe_type, p->addr);
 
 	if (!pp)
 		pp = p;
@@ -2428,8 +2328,16 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	struct kprobe_blacklist_entry *ent =
 		list_entry(v, struct kprobe_blacklist_entry, list);
 
-	seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
-		   (void *)ent->end_addr, (void *)ent->start_addr);
+	/*
+	 * If /proc/kallsyms is not showing kernel address, we won't
+	 * show them here either.
+	 */
+	if (!kallsyms_show_value())
+		seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
+			   (void *)ent->start_addr);
+	else
+		seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
+			   (void *)ent->end_addr, (void *)ent->start_addr);
 	return 0;
 }
 
@@ -2611,7 +2519,7 @@ static int __init debugfs_kprobe_init(void)
 	if (!dir)
 		return -ENOMEM;
 
-	file = debugfs_create_file("list", 0444, dir, NULL,
+	file = debugfs_create_file("list", 0400, dir, NULL,
 				&debugfs_kprobes_operations);
 	if (!file)
 		goto error;
@@ -2621,7 +2529,7 @@ static int __init debugfs_kprobe_init(void)
 	if (!file)
 		goto error;
 
-	file = debugfs_create_file("blacklist", 0444, dir, NULL,
+	file = debugfs_create_file("blacklist", 0400, dir, NULL,
 				&debugfs_kprobe_blacklist_ops);
 	if (!file)
 		goto error;
@@ -2637,6 +2545,3 @@ late_initcall(debugfs_kprobe_init);
 #endif /* CONFIG_DEBUG_FS */
 
 module_init(init_kprobes);
-
-/* defined in arch/.../kernel/kprobes.c */
-EXPORT_SYMBOL_GPL(jprobe_return);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 481951bf091d..087d18d771b5 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -177,9 +177,20 @@ void *kthread_probe_data(struct task_struct *task)
 static void __kthread_parkme(struct kthread *self)
 {
 	for (;;) {
-		set_current_state(TASK_PARKED);
+		/*
+		 * TASK_PARKED is a special state; we must serialize against
+		 * possible pending wakeups to avoid store-store collisions on
+		 * task->state.
+		 *
+		 * Such a collision might possibly result in the task state
+		 * changin from TASK_PARKED and us failing the
+		 * wait_task_inactive() in kthread_park().
+		 */
+		set_special_state(TASK_PARKED);
 		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
 			break;
+
+		complete(&self->parked);
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -191,11 +202,6 @@ void kthread_parkme(void)
 }
 EXPORT_SYMBOL_GPL(kthread_parkme);
 
-void kthread_park_complete(struct task_struct *k)
-{
-	complete_all(&to_kthread(k)->parked);
-}
-
 static int kthread(void *_create)
 {
 	/* Copy data: it's on kthread's stack */
@@ -319,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
 	task = create->result;
 	if (!IS_ERR(task)) {
 		static const struct sched_param param = { .sched_priority = 0 };
+		char name[TASK_COMM_LEN];
 
-		vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
+		/*
+		 * task is already visible to other tasks, so updating
+		 * COMM must be protected.
+		 */
+		vsnprintf(name, sizeof(name), namefmt, args);
+		set_task_comm(task, name);
 		/*
 		 * root may have changed our (kthreadd's) priority or CPU mask.
 		 * The kernel thread should not inherit these properties.
@@ -459,8 +471,10 @@ void kthread_unpark(struct task_struct *k)
 	if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
 		__kthread_bind(k, kthread->cpu, TASK_PARKED);
 
-	reinit_completion(&kthread->parked);
 	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+	/*
+	 * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
+	 */
 	wake_up_state(k, TASK_PARKED);
 }
 EXPORT_SYMBOL_GPL(kthread_unpark);
@@ -484,10 +498,22 @@ int kthread_park(struct task_struct *k)
 	if (WARN_ON(k->flags & PF_EXITING))
 		return -ENOSYS;
 
+	if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
+		return -EBUSY;
+
 	set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	if (k != current) {
 		wake_up_process(k);
+		/*
+		 * Wait for __kthread_parkme() to complete(), this means we
+		 * _will_ have TASK_PARKED and are about to call schedule().
+		 */
 		wait_for_completion(&kthread->parked);
+		/*
+		 * Now wait for that schedule() to complete and the task to
+		 * get scheduled out.
+		 */
+		WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED));
 	}
 
 	return 0;
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 8402b3349dca..57bef4fbfb31 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -21,6 +21,9 @@
  *          Davidlohr Bueso <dave@stgolabs.net>
  *	Based on kernel/rcu/torture.c.
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
@@ -57,7 +60,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
 torture_param(int, stat_interval, 60,
 	     "Number of seconds between stats printk()s");
 torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
 	     "Enable verbose debugging printk()s");
 
 static char *torture_type = "spin_lock";
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 4f014be7a4b8..2823d4163a37 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1465,6 +1465,29 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
 		rt_mutex_postunlock(&wake_q);
 }
 
+static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass)
+{
+	might_sleep();
+
+	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+/**
+ * rt_mutex_lock_nested - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ * @subclass: the lockdep subclass
+ */
+void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
+{
+	__rt_mutex_lock(lock, subclass);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
+#endif
+
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
 /**
  * rt_mutex_lock - lock a rt_mutex
  *
@@ -1472,12 +1495,10 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
  */
 void __sched rt_mutex_lock(struct rt_mutex *lock)
 {
-	might_sleep();
-
-	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+	__rt_mutex_lock(lock, 0);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock);
+#endif
 
 /**
  * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5857267a4af5..38283363da06 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
+	struct dev_pagemap *conflict_pgmap;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
 		- align_start;
+	align_end = align_start + align_size - 1;
+
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
+	if (conflict_pgmap) {
+		dev_WARN(dev, "Conflicting mapping in same section\n");
+		put_dev_pagemap(conflict_pgmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
+	if (conflict_pgmap) {
+		dev_WARN(dev, "Conflicting mapping in same section\n");
+		put_dev_pagemap(conflict_pgmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	is_ram = region_intersects(align_start, align_size,
 		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
@@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
-	align_end = align_start + align_size - 1;
 
 	foreach_order_pgoff(res, order, pgoff) {
 		error = __radix_tree_insert(&pgmap_radix,
@@ -305,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
 DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL_GPL(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
 static atomic_t devmap_enable;
 
 /*
@@ -346,5 +362,5 @@ void __put_devmap_managed_page(struct page *page)
 	} else if (!count)
 		__put_page(page);
 }
-EXPORT_SYMBOL_GPL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page);
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 9c85c7822383..abef759de7c8 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -338,7 +338,7 @@ static int create_image(int platform_mode)
  * hibernation_snapshot - Quiesce devices and create a hibernation image.
  * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- * This routine must be called with pm_mutex held.
+ * This routine must be called with system_transition_mutex held.
  */
 int hibernation_snapshot(int platform_mode)
 {
@@ -500,8 +500,9 @@ static int resume_target_kernel(bool platform_mode)
  * hibernation_restore - Quiesce devices and restore from a hibernation image.
  * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- * This routine must be called with pm_mutex held.  If it is successful, control
- * reappears in the restored target kernel in hibernation_snapshot().
+ * This routine must be called with system_transition_mutex held.  If it is
+ * successful, control reappears in the restored target kernel in
+ * hibernation_snapshot().
  */
 int hibernation_restore(int platform_mode)
 {
@@ -638,6 +639,7 @@ static void power_down(void)
 		break;
 	case HIBERNATION_PLATFORM:
 		hibernation_platform_enter();
+		/* Fall through */
 	case HIBERNATION_SHUTDOWN:
 		if (pm_power_off)
 			kernel_power_off();
@@ -805,13 +807,13 @@ static int software_resume(void)
 	 * name_to_dev_t() below takes a sysfs buffer mutex when sysfs
 	 * is configured into the kernel. Since the regular hibernate
 	 * trigger path is via sysfs which takes a buffer mutex before
-	 * calling hibernate functions (which take pm_mutex) this can
-	 * cause lockdep to complain about a possible ABBA deadlock
+	 * calling hibernate functions (which take system_transition_mutex)
+	 * this can cause lockdep to complain about a possible ABBA deadlock
 	 * which cannot happen since we're in the boot code here and
 	 * sysfs can't be invoked yet. Therefore, we use a subclass
 	 * here to avoid lockdep complaining.
 	 */
-	mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING);
+	mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING);
 
 	if (swsusp_resume_device)
 		goto Check_image;
@@ -899,7 +901,7 @@ static int software_resume(void)
 	atomic_inc(&snapshot_device_available);
 	/* For success case, the suspend path will release the lock */
  Unlock:
-	mutex_unlock(&pm_mutex);
+	mutex_unlock(&system_transition_mutex);
 	pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
 	return error;
  Close_Finish:
diff --git a/kernel/power/main.c b/kernel/power/main.c
index d9706da10930..35b50823d83b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -15,17 +15,16 @@
 #include <linux/workqueue.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/suspend.h>
 
 #include "power.h"
 
-DEFINE_MUTEX(pm_mutex);
-
 #ifdef CONFIG_PM_SLEEP
 
 void lock_system_sleep(void)
 {
 	current->flags |= PF_FREEZER_SKIP;
-	mutex_lock(&pm_mutex);
+	mutex_lock(&system_transition_mutex);
 }
 EXPORT_SYMBOL_GPL(lock_system_sleep);
 
@@ -37,8 +36,9 @@ void unlock_system_sleep(void)
 	 *
 	 * Reason:
 	 * Fundamentally, we just don't need it, because freezing condition
-	 * doesn't come into effect until we release the pm_mutex lock,
-	 * since the freezer always works with pm_mutex held.
+	 * doesn't come into effect until we release the
+	 * system_transition_mutex lock, since the freezer always works with
+	 * system_transition_mutex held.
 	 *
 	 * More importantly, in the case of hibernation,
 	 * unlock_system_sleep() gets called in snapshot_read() and
@@ -47,7 +47,7 @@ void unlock_system_sleep(void)
 	 * enter the refrigerator, thus causing hibernation to lockup.
 	 */
 	current->flags &= ~PF_FREEZER_SKIP;
-	mutex_unlock(&pm_mutex);
+	mutex_unlock(&system_transition_mutex);
 }
 EXPORT_SYMBOL_GPL(unlock_system_sleep);
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 87331565e505..5342f6fc022e 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -92,7 +92,7 @@ static void s2idle_enter(void)
 	/* Push all the CPUs into the idle loop. */
 	wake_up_all_idle_cpus();
 	/* Make the current CPU wait so it can enter the idle loop too. */
-	swait_event(s2idle_wait_head,
+	swait_event_exclusive(s2idle_wait_head,
 		    s2idle_state == S2IDLE_STATE_WAKE);
 
 	cpuidle_pause();
@@ -160,7 +160,7 @@ void s2idle_wake(void)
 	raw_spin_lock_irqsave(&s2idle_lock, flags);
 	if (s2idle_state > S2IDLE_STATE_NONE) {
 		s2idle_state = S2IDLE_STATE_WAKE;
-		swake_up(&s2idle_wait_head);
+		swake_up_one(&s2idle_wait_head);
 	}
 	raw_spin_unlock_irqrestore(&s2idle_lock, flags);
 }
@@ -556,7 +556,7 @@ static int enter_state(suspend_state_t state)
 	} else if (!valid_state(state)) {
 		return -EINVAL;
 	}
-	if (!mutex_trylock(&pm_mutex))
+	if (!mutex_trylock(&system_transition_mutex))
 		return -EBUSY;
 
 	if (state == PM_SUSPEND_TO_IDLE)
@@ -590,7 +590,7 @@ static int enter_state(suspend_state_t state)
 	pm_pr_dbg("Finishing wakeup.\n");
 	suspend_finish();
  Unlock:
-	mutex_unlock(&pm_mutex);
+	mutex_unlock(&system_transition_mutex);
 	return error;
 }
 
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index c2bcf97d24c8..d7f6c1a288d3 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -923,7 +923,7 @@ int swsusp_write(unsigned int flags)
 	}
 	memset(&snapshot, 0, sizeof(struct snapshot_handle));
 	error = snapshot_read_next(&snapshot);
-	if (error < PAGE_SIZE) {
+	if (error < (int)PAGE_SIZE) {
 		if (error >= 0)
 			error = -EFAULT;
 
@@ -1483,7 +1483,7 @@ int swsusp_read(unsigned int *flags_p)
 
 	memset(&snapshot, 0, sizeof(struct snapshot_handle));
 	error = snapshot_write_next(&snapshot);
-	if (error < PAGE_SIZE)
+	if (error < (int)PAGE_SIZE)
 		return error < 0 ? error : -EFAULT;
 	header = (struct swsusp_info *)data_of(snapshot);
 	error = get_swap_reader(&handle, flags_p);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index abd225550271..2d8b60a3c86b 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -216,7 +216,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!mutex_trylock(&pm_mutex))
+	if (!mutex_trylock(&system_transition_mutex))
 		return -EBUSY;
 
 	lock_device_hotplug();
@@ -394,7 +394,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 	}
 
 	unlock_device_hotplug();
-	mutex_unlock(&pm_mutex);
+	mutex_unlock(&system_transition_mutex);
 
 	return error;
 }
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 40cea6735c2d..4d04683c31b2 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -91,7 +91,17 @@ static inline void rcu_seq_end(unsigned long *sp)
 	WRITE_ONCE(*sp, rcu_seq_endval(sp));
 }
 
-/* Take a snapshot of the update side's sequence number. */
+/*
+ * rcu_seq_snap - Take a snapshot of the update side's sequence number.
+ *
+ * This function returns the earliest value of the grace-period sequence number
+ * that will indicate that a full grace period has elapsed since the current
+ * time.  Once the grace-period sequence number has reached this value, it will
+ * be safe to invoke all callbacks that have been registered prior to the
+ * current time. This value is the current grace-period number plus two to the
+ * power of the number of low-order bits reserved for state, then rounded up to
+ * the next value in which the state bits are all zero.
+ */
 static inline unsigned long rcu_seq_snap(unsigned long *sp)
 {
 	unsigned long s;
@@ -108,6 +118,15 @@ static inline unsigned long rcu_seq_current(unsigned long *sp)
 }
 
 /*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not the
+ * corresponding update-side operation has started.
+ */
+static inline bool rcu_seq_started(unsigned long *sp, unsigned long s)
+{
+	return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp));
+}
+
+/*
  * Given a snapshot from rcu_seq_snap(), determine whether or not a
  * full update-side operation has occurred.
  */
@@ -117,6 +136,45 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
 }
 
 /*
+ * Has a grace period completed since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new)
+{
+	return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK);
+}
+
+/*
+ * Has a grace period started since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new)
+{
+	return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK,
+			    new);
+}
+
+/*
+ * Roughly how many full grace periods have elapsed between the collection
+ * of the two specified grace periods?
+ */
+static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old)
+{
+	unsigned long rnd_diff;
+
+	if (old == new)
+		return 0;
+	/*
+	 * Compute the number of grace periods (still shifted up), plus
+	 * one if either of new and old is not an exact grace period.
+	 */
+	rnd_diff = (new & ~RCU_SEQ_STATE_MASK) -
+		   ((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) +
+		   ((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK));
+	if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff))
+		return 1; /* Definitely no grace period has elapsed. */
+	return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2;
+}
+
+/*
  * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
  * by call_rcu() and rcu callback execution, and are therefore not part of the
  * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
@@ -276,6 +334,9 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 /* Is this rcu_node a leaf? */
 #define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
 
+/* Is this rcu_node the last leaf? */
+#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1])
+
 /*
  * Do a full breadth-first scan of the rcu_node structures for the
  * specified rcu_state structure.
@@ -405,8 +466,7 @@ enum rcutorture_type {
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
-			    unsigned long *gpnum, unsigned long *completed);
-void rcutorture_record_test_transition(void);
+			    unsigned long *gp_seq);
 void rcutorture_record_progress(unsigned long vernum);
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
@@ -415,15 +475,11 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long c);
 #else
 static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
-					  int *flags,
-					  unsigned long *gpnum,
-					  unsigned long *completed)
+					  int *flags, unsigned long *gp_seq)
 {
 	*flags = 0;
-	*gpnum = 0;
-	*completed = 0;
+	*gp_seq = 0;
 }
-static inline void rcutorture_record_test_transition(void) { }
 static inline void rcutorture_record_progress(unsigned long vernum) { }
 #ifdef CONFIG_RCU_TRACE
 void do_trace_rcu_torture_read(const char *rcutorturename,
@@ -441,31 +497,26 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 
 static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
 					   struct srcu_struct *sp, int *flags,
-					   unsigned long *gpnum,
-					   unsigned long *completed)
+					   unsigned long *gp_seq)
 {
 	if (test_type != SRCU_FLAVOR)
 		return;
 	*flags = 0;
-	*completed = sp->srcu_idx;
-	*gpnum = *completed;
+	*gp_seq = sp->srcu_idx;
 }
 
 #elif defined(CONFIG_TREE_SRCU)
 
 void srcutorture_get_gp_data(enum rcutorture_type test_type,
 			     struct srcu_struct *sp, int *flags,
-			     unsigned long *gpnum, unsigned long *completed);
+			     unsigned long *gp_seq);
 
 #endif
 
 #ifdef CONFIG_TINY_RCU
-static inline unsigned long rcu_batches_started(void) { return 0; }
-static inline unsigned long rcu_batches_started_bh(void) { return 0; }
-static inline unsigned long rcu_batches_started_sched(void) { return 0; }
-static inline unsigned long rcu_batches_completed(void) { return 0; }
-static inline unsigned long rcu_batches_completed_bh(void) { return 0; }
-static inline unsigned long rcu_batches_completed_sched(void) { return 0; }
+static inline unsigned long rcu_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; }
 static inline unsigned long
@@ -474,19 +525,16 @@ static inline void rcu_force_quiescent_state(void) { }
 static inline void rcu_bh_force_quiescent_state(void) { }
 static inline void rcu_sched_force_quiescent_state(void) { }
 static inline void show_rcu_gp_kthreads(void) { }
+static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
 #else /* #ifdef CONFIG_TINY_RCU */
-extern unsigned long rcutorture_testseq;
-extern unsigned long rcutorture_vernum;
-unsigned long rcu_batches_started(void);
-unsigned long rcu_batches_started_bh(void);
-unsigned long rcu_batches_started_sched(void);
-unsigned long rcu_batches_completed(void);
-unsigned long rcu_batches_completed_bh(void);
-unsigned long rcu_batches_completed_sched(void);
+unsigned long rcu_get_gp_seq(void);
+unsigned long rcu_bh_get_gp_seq(void);
+unsigned long rcu_sched_get_gp_seq(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long rcu_exp_batches_completed_sched(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void show_rcu_gp_kthreads(void);
+int rcu_get_gp_kthreads_prio(void);
 void rcu_force_quiescent_state(void);
 void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index e232846516b3..34244523550e 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -19,6 +19,9 @@
  *
  * Authors: Paul E. McKenney <paulmck@us.ibm.com>
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -88,7 +91,7 @@ torture_param(int, nreaders, -1, "Number of RCU reader threads");
 torture_param(int, nwriters, -1, "Number of RCU updater threads");
 torture_param(bool, shutdown, !IS_ENABLED(MODULE),
 	      "Shutdown at end of performance tests.");
-torture_param(bool, verbose, true, "Enable verbose debugging printk()s");
+torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
 
 static char *perf_type = "rcu";
@@ -135,8 +138,8 @@ struct rcu_perf_ops {
 	void (*cleanup)(void);
 	int (*readlock)(void);
 	void (*readunlock)(int idx);
-	unsigned long (*started)(void);
-	unsigned long (*completed)(void);
+	unsigned long (*get_gp_seq)(void);
+	unsigned long (*gp_diff)(unsigned long new, unsigned long old);
 	unsigned long (*exp_completed)(void);
 	void (*async)(struct rcu_head *head, rcu_callback_t func);
 	void (*gp_barrier)(void);
@@ -176,8 +179,8 @@ static struct rcu_perf_ops rcu_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= rcu_perf_read_lock,
 	.readunlock	= rcu_perf_read_unlock,
-	.started	= rcu_batches_started,
-	.completed	= rcu_batches_completed,
+	.get_gp_seq	= rcu_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed,
 	.async		= call_rcu,
 	.gp_barrier	= rcu_barrier,
@@ -206,8 +209,8 @@ static struct rcu_perf_ops rcu_bh_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= rcu_bh_perf_read_lock,
 	.readunlock	= rcu_bh_perf_read_unlock,
-	.started	= rcu_batches_started_bh,
-	.completed	= rcu_batches_completed_bh,
+	.get_gp_seq	= rcu_bh_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed_sched,
 	.async		= call_rcu_bh,
 	.gp_barrier	= rcu_barrier_bh,
@@ -263,8 +266,8 @@ static struct rcu_perf_ops srcu_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= srcu_perf_read_lock,
 	.readunlock	= srcu_perf_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_perf_completed,
+	.get_gp_seq	= srcu_perf_completed,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= srcu_perf_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
@@ -292,8 +295,8 @@ static struct rcu_perf_ops srcud_ops = {
 	.cleanup	= srcu_sync_perf_cleanup,
 	.readlock	= srcu_perf_read_lock,
 	.readunlock	= srcu_perf_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_perf_completed,
+	.get_gp_seq	= srcu_perf_completed,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= srcu_perf_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
@@ -322,8 +325,8 @@ static struct rcu_perf_ops sched_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= sched_perf_read_lock,
 	.readunlock	= sched_perf_read_unlock,
-	.started	= rcu_batches_started_sched,
-	.completed	= rcu_batches_completed_sched,
+	.get_gp_seq	= rcu_sched_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed_sched,
 	.async		= call_rcu_sched,
 	.gp_barrier	= rcu_barrier_sched,
@@ -350,8 +353,8 @@ static struct rcu_perf_ops tasks_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= tasks_perf_read_lock,
 	.readunlock	= tasks_perf_read_unlock,
-	.started	= rcu_no_completed,
-	.completed	= rcu_no_completed,
+	.get_gp_seq	= rcu_no_completed,
+	.gp_diff	= rcu_seq_diff,
 	.async		= call_rcu_tasks,
 	.gp_barrier	= rcu_barrier_tasks,
 	.sync		= synchronize_rcu_tasks,
@@ -359,9 +362,11 @@ static struct rcu_perf_ops tasks_ops = {
 	.name		= "tasks"
 };
 
-static bool __maybe_unused torturing_tasks(void)
+static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
 {
-	return cur_ops == &tasks_ops;
+	if (!cur_ops->gp_diff)
+		return new - old;
+	return cur_ops->gp_diff(new, old);
 }
 
 /*
@@ -444,8 +449,7 @@ rcu_perf_writer(void *arg)
 			b_rcu_perf_writer_started =
 				cur_ops->exp_completed() / 2;
 		} else {
-			b_rcu_perf_writer_started =
-				cur_ops->completed();
+			b_rcu_perf_writer_started = cur_ops->get_gp_seq();
 		}
 	}
 
@@ -502,7 +506,7 @@ retry:
 						cur_ops->exp_completed() / 2;
 				} else {
 					b_rcu_perf_writer_finished =
-						cur_ops->completed();
+						cur_ops->get_gp_seq();
 				}
 				if (shutdown) {
 					smp_mb(); /* Assign before wake. */
@@ -527,7 +531,7 @@ retry:
 	return 0;
 }
 
-static inline void
+static void
 rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
 {
 	pr_alert("%s" PERF_FLAG
@@ -582,8 +586,8 @@ rcu_perf_cleanup(void)
 			 t_rcu_perf_writer_finished -
 			 t_rcu_perf_writer_started,
 			 ngps,
-			 b_rcu_perf_writer_finished -
-			 b_rcu_perf_writer_started);
+			 rcuperf_seq_diff(b_rcu_perf_writer_finished,
+					  b_rcu_perf_writer_started));
 		for (i = 0; i < nrealwriters; i++) {
 			if (!writer_durations)
 				break;
@@ -671,12 +675,11 @@ rcu_perf_init(void)
 			break;
 	}
 	if (i == ARRAY_SIZE(perf_ops)) {
-		pr_alert("rcu-perf: invalid perf type: \"%s\"\n",
-			 perf_type);
+		pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type);
 		pr_alert("rcu-perf types:");
 		for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
-			pr_alert(" %s", perf_ops[i]->name);
-		pr_alert("\n");
+			pr_cont(" %s", perf_ops[i]->name);
+		pr_cont("\n");
 		firsterr = -EINVAL;
 		goto unwind;
 	}
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 42fcb7f05fac..c596c6f1e457 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -22,6 +22,9 @@
  *
  * See also:  Documentation/RCU/torture.txt
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -52,6 +55,7 @@
 #include <linux/torture.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/sysctl.h>
 
 #include "rcu.h"
 
@@ -59,6 +63,19 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
 
+/* Bits for ->extendables field, extendables param, and related definitions. */
+#define RCUTORTURE_RDR_SHIFT	 8	/* Put SRCU index in upper bits. */
+#define RCUTORTURE_RDR_MASK	 ((1 << RCUTORTURE_RDR_SHIFT) - 1)
+#define RCUTORTURE_RDR_BH	 0x1	/* Extend readers by disabling bh. */
+#define RCUTORTURE_RDR_IRQ	 0x2	/*  ... disabling interrupts. */
+#define RCUTORTURE_RDR_PREEMPT	 0x4	/*  ... disabling preemption. */
+#define RCUTORTURE_RDR_RCU	 0x8	/*  ... entering another RCU reader. */
+#define RCUTORTURE_RDR_NBITS	 4	/* Number of bits defined above. */
+#define RCUTORTURE_MAX_EXTEND	 (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \
+				  RCUTORTURE_RDR_PREEMPT)
+#define RCUTORTURE_RDR_MAX_LOOPS 0x7	/* Maximum reader extensions. */
+					/* Must be power of two minus one. */
+
 torture_param(int, cbflood_inter_holdoff, HZ,
 	      "Holdoff between floods (jiffies)");
 torture_param(int, cbflood_intra_holdoff, 1,
@@ -66,6 +83,8 @@ torture_param(int, cbflood_intra_holdoff, 1,
 torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
 torture_param(int, cbflood_n_per_burst, 20000,
 	      "# callbacks per burst in flood");
+torture_param(int, extendables, RCUTORTURE_MAX_EXTEND,
+	      "Extend readers by disabling bh (1), irqs (2), or preempt (4)");
 torture_param(int, fqs_duration, 0,
 	      "Duration of fqs bursts (us), 0 to disable");
 torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
@@ -84,7 +103,7 @@ torture_param(int, object_debug, 0,
 	     "Enable debug-object double call_rcu() testing");
 torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
 torture_param(int, onoff_interval, 0,
-	     "Time between CPU hotplugs (s), 0=disable");
+	     "Time between CPU hotplugs (jiffies), 0=disable");
 torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
 torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
@@ -101,7 +120,7 @@ torture_param(int, test_boost_interval, 7,
 	     "Interval between boost tests, seconds.");
 torture_param(bool, test_no_idle_hz, true,
 	     "Test support for tickless idle CPUs");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
 	     "Enable verbose debugging printk()s");
 
 static char *torture_type = "rcu";
@@ -148,9 +167,9 @@ static long n_rcu_torture_boost_ktrerror;
 static long n_rcu_torture_boost_rterror;
 static long n_rcu_torture_boost_failure;
 static long n_rcu_torture_boosts;
-static long n_rcu_torture_timers;
+static atomic_long_t n_rcu_torture_timers;
 static long n_barrier_attempts;
-static long n_barrier_successes;
+static long n_barrier_successes; /* did rcu_barrier test succeed? */
 static atomic_long_t n_cbfloods;
 static struct list_head rcu_torture_removed;
 
@@ -261,8 +280,8 @@ struct rcu_torture_ops {
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
-	unsigned long (*started)(void);
-	unsigned long (*completed)(void);
+	unsigned long (*get_gp_seq)(void);
+	unsigned long (*gp_diff)(unsigned long new, unsigned long old);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*exp_sync)(void);
@@ -274,6 +293,8 @@ struct rcu_torture_ops {
 	void (*stats)(void);
 	int irq_capable;
 	int can_boost;
+	int extendables;
+	int ext_irq_conflict;
 	const char *name;
 };
 
@@ -302,10 +323,10 @@ static void rcu_read_delay(struct torture_random_state *rrsp)
 	 * force_quiescent_state. */
 
 	if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
-		started = cur_ops->completed();
+		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
 		mdelay(longdelay_ms);
-		completed = cur_ops->completed();
+		completed = cur_ops->get_gp_seq();
 		do_trace_rcu_torture_read(cur_ops->name, NULL, ts,
 					  started, completed);
 	}
@@ -397,8 +418,8 @@ static struct rcu_torture_ops rcu_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
-	.started	= rcu_batches_started,
-	.completed	= rcu_batches_completed,
+	.get_gp_seq	= rcu_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
@@ -439,8 +460,8 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
-	.started	= rcu_batches_started_bh,
-	.completed	= rcu_batches_completed_bh,
+	.get_gp_seq	= rcu_bh_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
 	.exp_sync	= synchronize_rcu_bh_expedited,
@@ -449,6 +470,8 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.fqs		= rcu_bh_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
+	.extendables	= (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ),
+	.ext_irq_conflict = RCUTORTURE_RDR_RCU,
 	.name		= "rcu_bh"
 };
 
@@ -483,8 +506,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_torture_read_unlock,
-	.started	= rcu_no_completed,
-	.completed	= rcu_no_completed,
+	.get_gp_seq	= rcu_no_completed,
 	.deferred_free	= rcu_busted_torture_deferred_free,
 	.sync		= synchronize_rcu_busted,
 	.exp_sync	= synchronize_rcu_busted,
@@ -572,8 +594,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_torture_completed,
+	.get_gp_seq	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
 	.exp_sync	= srcu_torture_synchronize_expedited,
@@ -610,8 +631,7 @@ static struct rcu_torture_ops srcud_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_torture_completed,
+	.get_gp_seq	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
 	.exp_sync	= srcu_torture_synchronize_expedited,
@@ -622,6 +642,26 @@ static struct rcu_torture_ops srcud_ops = {
 	.name		= "srcud"
 };
 
+/* As above, but broken due to inappropriate reader extension. */
+static struct rcu_torture_ops busted_srcud_ops = {
+	.ttype		= SRCU_FLAVOR,
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= rcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.get_gp_seq	= srcu_torture_completed,
+	.deferred_free	= srcu_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.exp_sync	= srcu_torture_synchronize_expedited,
+	.call		= srcu_torture_call,
+	.cb_barrier	= srcu_torture_barrier,
+	.stats		= srcu_torture_stats,
+	.irq_capable	= 1,
+	.extendables	= RCUTORTURE_MAX_EXTEND,
+	.name		= "busted_srcud"
+};
+
 /*
  * Definitions for sched torture testing.
  */
@@ -648,8 +688,8 @@ static struct rcu_torture_ops sched_ops = {
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
-	.started	= rcu_batches_started_sched,
-	.completed	= rcu_batches_completed_sched,
+	.get_gp_seq	= rcu_sched_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
 	.exp_sync	= synchronize_sched_expedited,
@@ -660,6 +700,7 @@ static struct rcu_torture_ops sched_ops = {
 	.fqs		= rcu_sched_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
+	.extendables	= RCUTORTURE_MAX_EXTEND,
 	.name		= "sched"
 };
 
@@ -687,8 +728,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.readlock	= tasks_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= tasks_torture_read_unlock,
-	.started	= rcu_no_completed,
-	.completed	= rcu_no_completed,
+	.get_gp_seq	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
 	.exp_sync	= synchronize_rcu_tasks,
@@ -700,6 +740,13 @@ static struct rcu_torture_ops tasks_ops = {
 	.name		= "tasks"
 };
 
+static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
+{
+	if (!cur_ops->gp_diff)
+		return new - old;
+	return cur_ops->gp_diff(new, old);
+}
+
 static bool __maybe_unused torturing_tasks(void)
 {
 	return cur_ops == &tasks_ops;
@@ -726,6 +773,44 @@ static void rcu_torture_boost_cb(struct rcu_head *head)
 	smp_store_release(&rbip->inflight, 0);
 }
 
+static int old_rt_runtime = -1;
+
+static void rcu_torture_disable_rt_throttle(void)
+{
+	/*
+	 * Disable RT throttling so that rcutorture's boost threads don't get
+	 * throttled. Only possible if rcutorture is built-in otherwise the
+	 * user should manually do this by setting the sched_rt_period_us and
+	 * sched_rt_runtime sysctls.
+	 */
+	if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime != -1)
+		return;
+
+	old_rt_runtime = sysctl_sched_rt_runtime;
+	sysctl_sched_rt_runtime = -1;
+}
+
+static void rcu_torture_enable_rt_throttle(void)
+{
+	if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime == -1)
+		return;
+
+	sysctl_sched_rt_runtime = old_rt_runtime;
+	old_rt_runtime = -1;
+}
+
+static bool rcu_torture_boost_failed(unsigned long start, unsigned long end)
+{
+	if (end - start > test_boost_duration * HZ - HZ / 2) {
+		VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
+		n_rcu_torture_boost_failure++;
+
+		return true; /* failed */
+	}
+
+	return false; /* passed */
+}
+
 static int rcu_torture_boost(void *arg)
 {
 	unsigned long call_rcu_time;
@@ -746,6 +831,21 @@ static int rcu_torture_boost(void *arg)
 	init_rcu_head_on_stack(&rbi.rcu);
 	/* Each pass through the following loop does one boost-test cycle. */
 	do {
+		/* Track if the test failed already in this test interval? */
+		bool failed = false;
+
+		/* Increment n_rcu_torture_boosts once per boost-test */
+		while (!kthread_should_stop()) {
+			if (mutex_trylock(&boost_mutex)) {
+				n_rcu_torture_boosts++;
+				mutex_unlock(&boost_mutex);
+				break;
+			}
+			schedule_timeout_uninterruptible(1);
+		}
+		if (kthread_should_stop())
+			goto checkwait;
+
 		/* Wait for the next test interval. */
 		oldstarttime = boost_starttime;
 		while (ULONG_CMP_LT(jiffies, oldstarttime)) {
@@ -764,11 +864,10 @@ static int rcu_torture_boost(void *arg)
 				/* RCU core before ->inflight = 1. */
 				smp_store_release(&rbi.inflight, 1);
 				call_rcu(&rbi.rcu, rcu_torture_boost_cb);
-				if (jiffies - call_rcu_time >
-					 test_boost_duration * HZ - HZ / 2) {
-					VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
-					n_rcu_torture_boost_failure++;
-				}
+				/* Check if the boost test failed */
+				failed = failed ||
+					 rcu_torture_boost_failed(call_rcu_time,
+								 jiffies);
 				call_rcu_time = jiffies;
 			}
 			stutter_wait("rcu_torture_boost");
@@ -777,6 +876,14 @@ static int rcu_torture_boost(void *arg)
 		}
 
 		/*
+		 * If boost never happened, then inflight will always be 1, in
+		 * this case the boost check would never happen in the above
+		 * loop so do another one here.
+		 */
+		if (!failed && smp_load_acquire(&rbi.inflight))
+			rcu_torture_boost_failed(call_rcu_time, jiffies);
+
+		/*
 		 * Set the start time of the next test interval.
 		 * Yes, this is vulnerable to long delays, but such
 		 * delays simply cause a false negative for the next
@@ -788,7 +895,6 @@ static int rcu_torture_boost(void *arg)
 			if (mutex_trylock(&boost_mutex)) {
 				boost_starttime = jiffies +
 						  test_boost_interval * HZ;
-				n_rcu_torture_boosts++;
 				mutex_unlock(&boost_mutex);
 				break;
 			}
@@ -1010,7 +1116,7 @@ rcu_torture_writer(void *arg)
 				break;
 			}
 		}
-		rcutorture_record_progress(++rcu_torture_current_version);
+		rcu_torture_current_version++;
 		/* Cycle through nesting levels of rcu_expedite_gp() calls. */
 		if (can_expedite &&
 		    !(torture_random(&rand) & 0xff & (!!expediting - 1))) {
@@ -1084,27 +1190,133 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp)
 }
 
 /*
- * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
- * incrementing the corresponding element of the pipeline array.  The
- * counter in the element should never be greater than 1, otherwise, the
- * RCU implementation is broken.
+ * Do one extension of an RCU read-side critical section using the
+ * current reader state in readstate (set to zero for initial entry
+ * to extended critical section), set the new state as specified by
+ * newstate (set to zero for final exit from extended critical section),
+ * and random-number-generator state in trsp.  If this is neither the
+ * beginning or end of the critical section and if there was actually a
+ * change, do a ->read_delay().
  */
-static void rcu_torture_timer(struct timer_list *unused)
+static void rcutorture_one_extend(int *readstate, int newstate,
+				  struct torture_random_state *trsp)
+{
+	int idxnew = -1;
+	int idxold = *readstate;
+	int statesnew = ~*readstate & newstate;
+	int statesold = *readstate & ~newstate;
+
+	WARN_ON_ONCE(idxold < 0);
+	WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1);
+
+	/* First, put new protection in place to avoid critical-section gap. */
+	if (statesnew & RCUTORTURE_RDR_BH)
+		local_bh_disable();
+	if (statesnew & RCUTORTURE_RDR_IRQ)
+		local_irq_disable();
+	if (statesnew & RCUTORTURE_RDR_PREEMPT)
+		preempt_disable();
+	if (statesnew & RCUTORTURE_RDR_RCU)
+		idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
+
+	/* Next, remove old protection, irq first due to bh conflict. */
+	if (statesold & RCUTORTURE_RDR_IRQ)
+		local_irq_enable();
+	if (statesold & RCUTORTURE_RDR_BH)
+		local_bh_enable();
+	if (statesold & RCUTORTURE_RDR_PREEMPT)
+		preempt_enable();
+	if (statesold & RCUTORTURE_RDR_RCU)
+		cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+
+	/* Delay if neither beginning nor end and there was a change. */
+	if ((statesnew || statesold) && *readstate && newstate)
+		cur_ops->read_delay(trsp);
+
+	/* Update the reader state. */
+	if (idxnew == -1)
+		idxnew = idxold & ~RCUTORTURE_RDR_MASK;
+	WARN_ON_ONCE(idxnew < 0);
+	WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1);
+	*readstate = idxnew | newstate;
+	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0);
+	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1);
+}
+
+/* Return the biggest extendables mask given current RCU and boot parameters. */
+static int rcutorture_extend_mask_max(void)
+{
+	int mask;
+
+	WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND);
+	mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables;
+	mask = mask | RCUTORTURE_RDR_RCU;
+	return mask;
+}
+
+/* Return a random protection state mask, but with at least one bit set. */
+static int
+rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
+{
+	int mask = rcutorture_extend_mask_max();
+	unsigned long randmask1 = torture_random(trsp) >> 8;
+	unsigned long randmask2 = randmask1 >> 1;
+
+	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
+	/* Half the time lots of bits, half the time only one bit. */
+	if (randmask1 & 0x1)
+		mask = mask & randmask2;
+	else
+		mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
+	if ((mask & RCUTORTURE_RDR_IRQ) &&
+	    !(mask & RCUTORTURE_RDR_BH) &&
+	    (oldmask & RCUTORTURE_RDR_BH))
+		mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */
+	if ((mask & RCUTORTURE_RDR_IRQ) &&
+	    !(mask & cur_ops->ext_irq_conflict) &&
+	    (oldmask & cur_ops->ext_irq_conflict))
+		mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */
+	return mask ?: RCUTORTURE_RDR_RCU;
+}
+
+/*
+ * Do a randomly selected number of extensions of an existing RCU read-side
+ * critical section.
+ */
+static void rcutorture_loop_extend(int *readstate,
+				   struct torture_random_state *trsp)
+{
+	int i;
+	int mask = rcutorture_extend_mask_max();
+
+	WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */
+	if (!((mask - 1) & mask))
+		return;  /* Current RCU flavor not extendable. */
+	i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS;
+	while (i--) {
+		mask = rcutorture_extend_mask(*readstate, trsp);
+		rcutorture_one_extend(readstate, mask, trsp);
+	}
+}
+
+/*
+ * Do one read-side critical section, returning false if there was
+ * no data to read.  Can be invoked both from process context and
+ * from a timer handler.
+ */
+static bool rcu_torture_one_read(struct torture_random_state *trsp)
 {
-	int idx;
 	unsigned long started;
 	unsigned long completed;
-	static DEFINE_TORTURE_RANDOM(rand);
-	static DEFINE_SPINLOCK(rand_lock);
+	int newstate;
 	struct rcu_torture *p;
 	int pipe_count;
+	int readstate = 0;
 	unsigned long long ts;
 
-	idx = cur_ops->readlock();
-	if (cur_ops->started)
-		started = cur_ops->started();
-	else
-		started = cur_ops->completed();
+	newstate = rcutorture_extend_mask(readstate, trsp);
+	rcutorture_one_extend(&readstate, newstate, trsp);
+	started = cur_ops->get_gp_seq();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
@@ -1112,39 +1324,50 @@ static void rcu_torture_timer(struct timer_list *unused)
 				  srcu_read_lock_held(srcu_ctlp) ||
 				  torturing_tasks());
 	if (p == NULL) {
-		/* Leave because rcu_torture_writer is not yet underway */
-		cur_ops->readunlock(idx);
-		return;
+		/* Wait for rcu_torture_writer to get underway */
+		rcutorture_one_extend(&readstate, 0, trsp);
+		return false;
 	}
 	if (p->rtort_mbtest == 0)
 		atomic_inc(&n_rcu_torture_mberror);
-	spin_lock(&rand_lock);
-	cur_ops->read_delay(&rand);
-	n_rcu_torture_timers++;
-	spin_unlock(&rand_lock);
+	rcutorture_loop_extend(&readstate, trsp);
 	preempt_disable();
 	pipe_count = p->rtort_pipe_count;
 	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	completed = cur_ops->completed();
+	completed = cur_ops->get_gp_seq();
 	if (pipe_count > 1) {
-		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
-					  started, completed);
+		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
+					  ts, started, completed);
 		rcu_ftrace_dump(DUMP_ALL);
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = completed - started;
-	if (cur_ops->started)
-		completed++;
+	completed = rcutorture_seq_diff(completed, started);
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
 	}
 	__this_cpu_inc(rcu_torture_batch[completed]);
 	preempt_enable();
-	cur_ops->readunlock(idx);
+	rcutorture_one_extend(&readstate, 0, trsp);
+	WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK);
+	return true;
+}
+
+static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand);
+
+/*
+ * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
+ * incrementing the corresponding element of the pipeline array.  The
+ * counter in the element should never be greater than 1, otherwise, the
+ * RCU implementation is broken.
+ */
+static void rcu_torture_timer(struct timer_list *unused)
+{
+	atomic_long_inc(&n_rcu_torture_timers);
+	(void)rcu_torture_one_read(this_cpu_ptr(&rcu_torture_timer_rand));
 
 	/* Test call_rcu() invocation from interrupt handler. */
 	if (cur_ops->call) {
@@ -1164,14 +1387,8 @@ static void rcu_torture_timer(struct timer_list *unused)
 static int
 rcu_torture_reader(void *arg)
 {
-	unsigned long started;
-	unsigned long completed;
-	int idx;
 	DEFINE_TORTURE_RANDOM(rand);
-	struct rcu_torture *p;
-	int pipe_count;
 	struct timer_list t;
-	unsigned long long ts;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_reader task started");
 	set_user_nice(current, MAX_NICE);
@@ -1183,49 +1400,8 @@ rcu_torture_reader(void *arg)
 			if (!timer_pending(&t))
 				mod_timer(&t, jiffies + 1);
 		}
-		idx = cur_ops->readlock();
-		if (cur_ops->started)
-			started = cur_ops->started();
-		else
-			started = cur_ops->completed();
-		ts = rcu_trace_clock_local();
-		p = rcu_dereference_check(rcu_torture_current,
-					  rcu_read_lock_bh_held() ||
-					  rcu_read_lock_sched_held() ||
-					  srcu_read_lock_held(srcu_ctlp) ||
-					  torturing_tasks());
-		if (p == NULL) {
-			/* Wait for rcu_torture_writer to get underway */
-			cur_ops->readunlock(idx);
+		if (!rcu_torture_one_read(&rand))
 			schedule_timeout_interruptible(HZ);
-			continue;
-		}
-		if (p->rtort_mbtest == 0)
-			atomic_inc(&n_rcu_torture_mberror);
-		cur_ops->read_delay(&rand);
-		preempt_disable();
-		pipe_count = p->rtort_pipe_count;
-		if (pipe_count > RCU_TORTURE_PIPE_LEN) {
-			/* Should not happen, but... */
-			pipe_count = RCU_TORTURE_PIPE_LEN;
-		}
-		completed = cur_ops->completed();
-		if (pipe_count > 1) {
-			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-						  ts, started, completed);
-			rcu_ftrace_dump(DUMP_ALL);
-		}
-		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = completed - started;
-		if (cur_ops->started)
-			completed++;
-		if (completed > RCU_TORTURE_PIPE_LEN) {
-			/* Should not happen, but... */
-			completed = RCU_TORTURE_PIPE_LEN;
-		}
-		__this_cpu_inc(rcu_torture_batch[completed]);
-		preempt_enable();
-		cur_ops->readunlock(idx);
 		stutter_wait("rcu_torture_reader");
 	} while (!torture_must_stop());
 	if (irqreader && cur_ops->irq_capable) {
@@ -1282,7 +1458,7 @@ rcu_torture_stats_print(void)
 	pr_cont("rtbf: %ld rtb: %ld nt: %ld ",
 		n_rcu_torture_boost_failure,
 		n_rcu_torture_boosts,
-		n_rcu_torture_timers);
+		atomic_long_read(&n_rcu_torture_timers));
 	torture_onoff_stats();
 	pr_cont("barrier: %ld/%ld:%ld ",
 		n_barrier_successes,
@@ -1324,18 +1500,16 @@ rcu_torture_stats_print(void)
 	if (rtcv_snap == rcu_torture_current_version &&
 	    rcu_torture_current != NULL) {
 		int __maybe_unused flags = 0;
-		unsigned long __maybe_unused gpnum = 0;
-		unsigned long __maybe_unused completed = 0;
+		unsigned long __maybe_unused gp_seq = 0;
 
 		rcutorture_get_gp_data(cur_ops->ttype,
-				       &flags, &gpnum, &completed);
+				       &flags, &gp_seq);
 		srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
-					&flags, &gpnum, &completed);
+					&flags, &gp_seq);
 		wtp = READ_ONCE(writer_task);
-		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n",
+		pr_alert("??? Writer stall state %s(%d) g%lu f%#x ->state %#lx cpu %d\n",
 			 rcu_torture_writer_state_getname(),
-			 rcu_torture_writer_state,
-			 gpnum, completed, flags,
+			 rcu_torture_writer_state, gp_seq, flags,
 			 wtp == NULL ? ~0UL : wtp->state,
 			 wtp == NULL ? -1 : (int)task_cpu(wtp));
 		if (!splatted && wtp) {
@@ -1365,7 +1539,7 @@ rcu_torture_stats(void *arg)
 	return 0;
 }
 
-static inline void
+static void
 rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 {
 	pr_alert("%s" TORTURE_FLAG
@@ -1397,6 +1571,7 @@ static int rcutorture_booster_cleanup(unsigned int cpu)
 	mutex_lock(&boost_mutex);
 	t = boost_tasks[cpu];
 	boost_tasks[cpu] = NULL;
+	rcu_torture_enable_rt_throttle();
 	mutex_unlock(&boost_mutex);
 
 	/* This must be outside of the mutex, otherwise deadlock! */
@@ -1413,6 +1588,7 @@ static int rcutorture_booster_init(unsigned int cpu)
 
 	/* Don't allow time recalculation while creating a new task. */
 	mutex_lock(&boost_mutex);
+	rcu_torture_disable_rt_throttle();
 	VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task");
 	boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL,
 						  cpu_to_node(cpu),
@@ -1446,7 +1622,7 @@ static int rcu_torture_stall(void *args)
 		VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
 	}
 	if (!kthread_should_stop()) {
-		stop_at = get_seconds() + stall_cpu;
+		stop_at = ktime_get_seconds() + stall_cpu;
 		/* RCU CPU stall is expected behavior in following code. */
 		rcu_read_lock();
 		if (stall_cpu_irqsoff)
@@ -1455,7 +1631,8 @@ static int rcu_torture_stall(void *args)
 			preempt_disable();
 		pr_alert("rcu_torture_stall start on CPU %d.\n",
 			 smp_processor_id());
-		while (ULONG_CMP_LT(get_seconds(), stop_at))
+		while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
+				    stop_at))
 			continue;  /* Induce RCU CPU stall warning. */
 		if (stall_cpu_irqsoff)
 			local_irq_enable();
@@ -1546,8 +1723,9 @@ static int rcu_torture_barrier(void *arg)
 			       atomic_read(&barrier_cbs_invoked),
 			       n_barrier_cbs);
 			WARN_ON_ONCE(1);
+		} else {
+			n_barrier_successes++;
 		}
-		n_barrier_successes++;
 		schedule_timeout_interruptible(HZ / 10);
 	} while (!torture_must_stop());
 	torture_kthread_stopping("rcu_torture_barrier");
@@ -1610,17 +1788,39 @@ static void rcu_torture_barrier_cleanup(void)
 	}
 }
 
+static bool rcu_torture_can_boost(void)
+{
+	static int boost_warn_once;
+	int prio;
+
+	if (!(test_boost == 1 && cur_ops->can_boost) && test_boost != 2)
+		return false;
+
+	prio = rcu_get_gp_kthreads_prio();
+	if (!prio)
+		return false;
+
+	if (prio < 2) {
+		if (boost_warn_once  == 1)
+			return false;
+
+		pr_alert("%s: WARN: RCU kthread priority too low to test boosting.  Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 on the kernel command line.\n", KBUILD_MODNAME);
+		boost_warn_once = 1;
+		return false;
+	}
+
+	return true;
+}
+
 static enum cpuhp_state rcutor_hp;
 
 static void
 rcu_torture_cleanup(void)
 {
 	int flags = 0;
-	unsigned long gpnum = 0;
-	unsigned long completed = 0;
+	unsigned long gp_seq = 0;
 	int i;
 
-	rcutorture_record_test_transition();
 	if (torture_cleanup_begin()) {
 		if (cur_ops->cb_barrier != NULL)
 			cur_ops->cb_barrier();
@@ -1648,17 +1848,15 @@ rcu_torture_cleanup(void)
 		fakewriter_tasks = NULL;
 	}
 
-	rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed);
-	srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
-				&flags, &gpnum, &completed);
-	pr_alert("%s:  End-test grace-period state: g%lu c%lu f%#x\n",
-		 cur_ops->name, gpnum, completed, flags);
+	rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq);
+	srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq);
+	pr_alert("%s:  End-test grace-period state: g%lu f%#x\n",
+		 cur_ops->name, gp_seq, flags);
 	torture_stop_kthread(rcu_torture_stats, stats_task);
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
 	for (i = 0; i < ncbflooders; i++)
 		torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
-	if ((test_boost == 1 && cur_ops->can_boost) ||
-	    test_boost == 2)
+	if (rcu_torture_can_boost())
 		cpuhp_remove_state(rcutor_hp);
 
 	/*
@@ -1746,7 +1944,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
-		&sched_ops, &tasks_ops,
+		&busted_srcud_ops, &sched_ops, &tasks_ops,
 	};
 
 	if (!torture_init_begin(torture_type, verbose))
@@ -1763,8 +1961,8 @@ rcu_torture_init(void)
 			 torture_type);
 		pr_alert("rcu-torture types:");
 		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
-			pr_alert(" %s", torture_ops[i]->name);
-		pr_alert("\n");
+			pr_cont(" %s", torture_ops[i]->name);
+		pr_cont("\n");
 		firsterr = -EINVAL;
 		goto unwind;
 	}
@@ -1882,8 +2080,7 @@ rcu_torture_init(void)
 		test_boost_interval = 1;
 	if (test_boost_duration < 2)
 		test_boost_duration = 2;
-	if ((test_boost == 1 && cur_ops->can_boost) ||
-	    test_boost == 2) {
+	if (rcu_torture_can_boost()) {
 
 		boost_starttime = jiffies + test_boost_interval * HZ;
 
@@ -1897,7 +2094,7 @@ rcu_torture_init(void)
 	firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
 	if (firsterr)
 		goto unwind;
-	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ);
+	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval);
 	if (firsterr)
 		goto unwind;
 	firsterr = rcu_torture_stall_init();
@@ -1926,7 +2123,6 @@ rcu_torture_init(void)
 				goto unwind;
 		}
 	}
-	rcutorture_record_test_transition();
 	torture_init_end();
 	return 0;
 
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 622792abe41a..04fc2ed71af8 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -110,7 +110,7 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 
 	WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
 	if (!newval && READ_ONCE(sp->srcu_gp_waiting))
-		swake_up(&sp->srcu_wq);
+		swake_up_one(&sp->srcu_wq);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -140,7 +140,7 @@ void srcu_drive_gp(struct work_struct *wp)
 	idx = sp->srcu_idx;
 	WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
 	WRITE_ONCE(sp->srcu_gp_waiting, true);  /* srcu_read_unlock() wakes! */
-	swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
+	swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
 	WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
 
 	/* Invoke the callbacks we removed above. */
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index b4123d7a2cec..6c9866a854b1 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -26,6 +26,8 @@
  *
  */
 
+#define pr_fmt(fmt) "rcu: " fmt
+
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/percpu.h>
@@ -390,7 +392,8 @@ void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
 		}
 	if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
 	    WARN_ON(srcu_readers_active(sp))) {
-		pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+		pr_info("%s: Active srcu_struct %p state: %d\n",
+			__func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
 		return; /* Caller forgot to stop doing call_srcu()? */
 	}
 	free_percpu(sp->sda);
@@ -641,6 +644,9 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
  * period s.  Losers must either ensure that their desired grace-period
  * number is recorded on at least their leaf srcu_node structure, or they
  * must take steps to invoke their own callbacks.
+ *
+ * Note that this function also does the work of srcu_funnel_exp_start(),
+ * in some cases by directly invoking it.
  */
 static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 				 unsigned long s, bool do_norm)
@@ -823,17 +829,17 @@ static void srcu_leak_callback(struct rcu_head *rhp)
  * more than one CPU, this means that when "func()" is invoked, each CPU
  * is guaranteed to have executed a full memory barrier since the end of
  * its last corresponding SRCU read-side critical section whose beginning
- * preceded the call to call_rcu().  It also means that each CPU executing
+ * preceded the call to call_srcu().  It also means that each CPU executing
  * an SRCU read-side critical section that continues beyond the start of
- * "func()" must have executed a memory barrier after the call_rcu()
+ * "func()" must have executed a memory barrier after the call_srcu()
  * but before the beginning of that SRCU read-side critical section.
  * Note that these guarantees include CPUs that are offline, idle, or
  * executing in user mode, as well as CPUs that are executing in the kernel.
  *
- * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * Furthermore, if CPU A invoked call_srcu() and CPU B invoked the
  * resulting SRCU callback function "func()", then both CPU A and CPU
  * B are guaranteed to execute a full memory barrier during the time
- * interval between the call to call_rcu() and the invocation of "func()".
+ * interval between the call to call_srcu() and the invocation of "func()".
  * This guarantee applies even if CPU A and CPU B are the same CPU (but
  * again only if the system has more than one CPU).
  *
@@ -1246,13 +1252,12 @@ static void process_srcu(struct work_struct *work)
 
 void srcutorture_get_gp_data(enum rcutorture_type test_type,
 			     struct srcu_struct *sp, int *flags,
-			     unsigned long *gpnum, unsigned long *completed)
+			     unsigned long *gp_seq)
 {
 	if (test_type != SRCU_FLAVOR)
 		return;
 	*flags = 0;
-	*completed = rcu_seq_ctr(sp->srcu_gp_seq);
-	*gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed);
+	*gp_seq = rcu_seq_current(&sp->srcu_gp_seq);
 }
 EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
 
@@ -1263,16 +1268,17 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
 	unsigned long s0 = 0, s1 = 0;
 
 	idx = sp->srcu_idx & 0x1;
-	pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", tt, tf, idx);
+	pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):",
+		 tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx);
 	for_each_possible_cpu(cpu) {
 		unsigned long l0, l1;
 		unsigned long u0, u1;
 		long c0, c1;
-		struct srcu_data *counts;
+		struct srcu_data *sdp;
 
-		counts = per_cpu_ptr(sp->sda, cpu);
-		u0 = counts->srcu_unlock_count[!idx];
-		u1 = counts->srcu_unlock_count[idx];
+		sdp = per_cpu_ptr(sp->sda, cpu);
+		u0 = sdp->srcu_unlock_count[!idx];
+		u1 = sdp->srcu_unlock_count[idx];
 
 		/*
 		 * Make sure that a lock is always counted if the corresponding
@@ -1280,12 +1286,13 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
 		 */
 		smp_rmb();
 
-		l0 = counts->srcu_lock_count[!idx];
-		l1 = counts->srcu_lock_count[idx];
+		l0 = sdp->srcu_lock_count[!idx];
+		l1 = sdp->srcu_lock_count[idx];
 
 		c0 = l0 - u0;
 		c1 = l1 - u1;
-		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
+		pr_cont(" %d(%ld,%ld %1p)",
+			cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist));
 		s0 += c0;
 		s1 += c1;
 	}
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index a64eee0db39e..befc9321a89c 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -122,10 +122,8 @@ void rcu_check_callbacks(int user)
 {
 	if (user)
 		rcu_sched_qs();
-	else if (!in_softirq())
+	if (user || !in_softirq())
 		rcu_bh_qs();
-	if (user)
-		rcu_note_voluntary_context_switch(current);
 }
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index aa7cade1b9f3..0b760c1369f7 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -27,6 +27,9 @@
  * For detailed explanation of Read-Copy Update mechanism see -
  *	Documentation/RCU
  */
+
+#define pr_fmt(fmt) "rcu: " fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -95,13 +98,13 @@ struct rcu_state sname##_state = { \
 	.rda = &sname##_data, \
 	.call = cr, \
 	.gp_state = RCU_GP_IDLE, \
-	.gpnum = 0UL - 300UL, \
-	.completed = 0UL - 300UL, \
+	.gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.name = RCU_STATE_NAME(sname), \
 	.abbr = sabbr, \
 	.exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \
 	.exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \
+	.ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \
 }
 
 RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
@@ -155,6 +158,9 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
  */
 static int rcu_scheduler_fully_active __read_mostly;
 
+static void
+rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
+		  struct rcu_node *rnp, unsigned long gps, unsigned long flags);
 static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
 static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
@@ -177,6 +183,13 @@ module_param(gp_init_delay, int, 0444);
 static int gp_cleanup_delay;
 module_param(gp_cleanup_delay, int, 0444);
 
+/* Retreive RCU kthreads priority for rcutorture */
+int rcu_get_gp_kthreads_prio(void)
+{
+	return kthread_prio;
+}
+EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio);
+
 /*
  * Number of grace periods between delays, normalized by the duration of
  * the delay.  The longer the delay, the more the grace periods between
@@ -189,18 +202,6 @@ module_param(gp_cleanup_delay, int, 0444);
 #define PER_RCU_NODE_PERIOD 3	/* Number of grace periods between delays. */
 
 /*
- * Track the rcutorture test sequence number and the update version
- * number within a given test.  The rcutorture_testseq is incremented
- * on every rcutorture module load and unload, so has an odd value
- * when a test is running.  The rcutorture_vernum is set to zero
- * when rcutorture starts and is incremented on each rcutorture update.
- * These variables enable correlating rcutorture output with the
- * RCU tracing information.
- */
-unsigned long rcutorture_testseq;
-unsigned long rcutorture_vernum;
-
-/*
  * Compute the mask of online CPUs for the specified rcu_node structure.
  * This will not be stable unless the rcu_node structure's ->lock is
  * held, but the bit corresponding to the current CPU will be stable
@@ -218,7 +219,7 @@ unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
  */
 static int rcu_gp_in_progress(struct rcu_state *rsp)
 {
-	return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
+	return rcu_seq_state(rcu_seq_current(&rsp->gp_seq));
 }
 
 /*
@@ -233,7 +234,7 @@ void rcu_sched_qs(void)
 	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s))
 		return;
 	trace_rcu_grace_period(TPS("rcu_sched"),
-			       __this_cpu_read(rcu_sched_data.gpnum),
+			       __this_cpu_read(rcu_sched_data.gp_seq),
 			       TPS("cpuqs"));
 	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
 	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
@@ -248,7 +249,7 @@ void rcu_bh_qs(void)
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!");
 	if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_bh"),
-				       __this_cpu_read(rcu_bh_data.gpnum),
+				       __this_cpu_read(rcu_bh_data.gp_seq),
 				       TPS("cpuqs"));
 		__this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
 	}
@@ -380,20 +381,6 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap)
 }
 
 /*
- * Do a double-increment of the ->dynticks counter to emulate a
- * momentary idle-CPU quiescent state.
- */
-static void rcu_dynticks_momentary_idle(void)
-{
-	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
-	int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
-					&rdtp->dynticks);
-
-	/* It is illegal to call this from idle state. */
-	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
-}
-
-/*
  * Set the special (bottom) bit of the specified CPU so that it
  * will take special action (such as flushing its TLB) on the
  * next exit from an extended quiescent state.  Returns true if
@@ -424,12 +411,17 @@ bool rcu_eqs_special_set(int cpu)
  *
  * We inform the RCU core by emulating a zero-duration dyntick-idle period.
  *
- * The caller must have disabled interrupts.
+ * The caller must have disabled interrupts and must not be idle.
  */
 static void rcu_momentary_dyntick_idle(void)
 {
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int special;
+
 	raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false);
-	rcu_dynticks_momentary_idle();
+	special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+	/* It is illegal to call this from idle state. */
+	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
 }
 
 /*
@@ -451,7 +443,7 @@ void rcu_note_context_switch(bool preempt)
 		rcu_momentary_dyntick_idle();
 	this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
 	if (!preempt)
-		rcu_note_voluntary_context_switch_lite(current);
+		rcu_tasks_qs(current);
 out:
 	trace_rcu_utilization(TPS("End context switch"));
 	barrier(); /* Avoid RCU read-side critical sections leaking up. */
@@ -513,8 +505,38 @@ static ulong jiffies_till_first_fqs = ULONG_MAX;
 static ulong jiffies_till_next_fqs = ULONG_MAX;
 static bool rcu_kick_kthreads;
 
-module_param(jiffies_till_first_fqs, ulong, 0644);
-module_param(jiffies_till_next_fqs, ulong, 0644);
+static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+	ulong j;
+	int ret = kstrtoul(val, 0, &j);
+
+	if (!ret)
+		WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j);
+	return ret;
+}
+
+static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+	ulong j;
+	int ret = kstrtoul(val, 0, &j);
+
+	if (!ret)
+		WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1));
+	return ret;
+}
+
+static struct kernel_param_ops first_fqs_jiffies_ops = {
+	.set = param_set_first_fqs_jiffies,
+	.get = param_get_ulong,
+};
+
+static struct kernel_param_ops next_fqs_jiffies_ops = {
+	.set = param_set_next_fqs_jiffies,
+	.get = param_get_ulong,
+};
+
+module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644);
+module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644);
 module_param(rcu_kick_kthreads, bool, 0644);
 
 /*
@@ -529,58 +551,31 @@ static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(void);
 
 /*
- * Return the number of RCU batches started thus far for debug & stats.
+ * Return the number of RCU GPs completed thus far for debug & stats.
  */
-unsigned long rcu_batches_started(void)
+unsigned long rcu_get_gp_seq(void)
 {
-	return rcu_state_p->gpnum;
+	return READ_ONCE(rcu_state_p->gp_seq);
 }
-EXPORT_SYMBOL_GPL(rcu_batches_started);
+EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
 
 /*
- * Return the number of RCU-sched batches started thus far for debug & stats.
+ * Return the number of RCU-sched GPs completed thus far for debug & stats.
  */
-unsigned long rcu_batches_started_sched(void)
+unsigned long rcu_sched_get_gp_seq(void)
 {
-	return rcu_sched_state.gpnum;
+	return READ_ONCE(rcu_sched_state.gp_seq);
 }
-EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
+EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq);
 
 /*
- * Return the number of RCU BH batches started thus far for debug & stats.
+ * Return the number of RCU-bh GPs completed thus far for debug & stats.
  */
-unsigned long rcu_batches_started_bh(void)
+unsigned long rcu_bh_get_gp_seq(void)
 {
-	return rcu_bh_state.gpnum;
+	return READ_ONCE(rcu_bh_state.gp_seq);
 }
-EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
-
-/*
- * Return the number of RCU batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed(void)
-{
-	return rcu_state_p->completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-/*
- * Return the number of RCU-sched batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_sched(void)
-{
-	return rcu_sched_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
-
-/*
- * Return the number of RCU BH batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_bh(void)
-{
-	return rcu_bh_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
+EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq);
 
 /*
  * Return the number of RCU expedited batches completed thus far for
@@ -636,35 +631,42 @@ EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
  */
 void show_rcu_gp_kthreads(void)
 {
+	int cpu;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp) {
 		pr_info("%s: wait state: %d ->state: %#lx\n",
 			rsp->name, rsp->gp_state, rsp->gp_kthread->state);
+		rcu_for_each_node_breadth_first(rsp, rnp) {
+			if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed))
+				continue;
+			pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n",
+				rnp->grplo, rnp->grphi, rnp->gp_seq,
+				rnp->gp_seq_needed);
+			if (!rcu_is_leaf_node(rnp))
+				continue;
+			for_each_leaf_node_possible_cpu(rnp, cpu) {
+				rdp = per_cpu_ptr(rsp->rda, cpu);
+				if (rdp->gpwrap ||
+				    ULONG_CMP_GE(rsp->gp_seq,
+						 rdp->gp_seq_needed))
+					continue;
+				pr_info("\tcpu %d ->gp_seq_needed %lu\n",
+					cpu, rdp->gp_seq_needed);
+			}
+		}
 		/* sched_show_task(rsp->gp_kthread); */
 	}
 }
 EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
 
 /*
- * Record the number of times rcutorture tests have been initiated and
- * terminated.  This information allows the debugfs tracing stats to be
- * correlated to the rcutorture messages, even when the rcutorture module
- * is being repeatedly loaded and unloaded.  In other words, we cannot
- * store this state in rcutorture itself.
- */
-void rcutorture_record_test_transition(void)
-{
-	rcutorture_testseq++;
-	rcutorture_vernum = 0;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
-
-/*
  * Send along grace-period-related data for rcutorture diagnostics.
  */
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
-			    unsigned long *gpnum, unsigned long *completed)
+			    unsigned long *gp_seq)
 {
 	struct rcu_state *rsp = NULL;
 
@@ -684,23 +686,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 	if (rsp == NULL)
 		return;
 	*flags = READ_ONCE(rsp->gp_flags);
-	*gpnum = READ_ONCE(rsp->gpnum);
-	*completed = READ_ONCE(rsp->completed);
+	*gp_seq = rcu_seq_current(&rsp->gp_seq);
 }
 EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
 
 /*
- * Record the number of writer passes through the current rcutorture test.
- * This is also used to correlate debugfs tracing stats with the rcutorture
- * messages.
- */
-void rcutorture_record_progress(unsigned long vernum)
-{
-	rcutorture_vernum++;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_progress);
-
-/*
  * Return the root node of the specified rcu_state structure.
  */
 static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
@@ -1059,41 +1049,41 @@ void rcu_request_urgent_qs_task(struct task_struct *t)
 #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
 
 /*
- * Is the current CPU online?  Disable preemption to avoid false positives
- * that could otherwise happen due to the current CPU number being sampled,
- * this task being preempted, its old CPU being taken offline, resuming
- * on some other CPU, then determining that its old CPU is now offline.
- * It is OK to use RCU on an offline processor during initial boot, hence
- * the check for rcu_scheduler_fully_active.  Note also that it is OK
- * for a CPU coming online to use RCU for one jiffy prior to marking itself
- * online in the cpu_online_mask.  Similarly, it is OK for a CPU going
- * offline to continue to use RCU for one jiffy after marking itself
- * offline in the cpu_online_mask.  This leniency is necessary given the
- * non-atomic nature of the online and offline processing, for example,
- * the fact that a CPU enters the scheduler after completing the teardown
- * of the CPU.
+ * Is the current CPU online as far as RCU is concerned?
  *
- * This is also why RCU internally marks CPUs online during in the
- * preparation phase and offline after the CPU has been taken down.
+ * Disable preemption to avoid false positives that could otherwise
+ * happen due to the current CPU number being sampled, this task being
+ * preempted, its old CPU being taken offline, resuming on some other CPU,
+ * then determining that its old CPU is now offline.  Because there are
+ * multiple flavors of RCU, and because this function can be called in the
+ * midst of updating the flavors while a given CPU coming online or going
+ * offline, it is necessary to check all flavors.  If any of the flavors
+ * believe that given CPU is online, it is considered to be online.
  *
- * Disable checking if in an NMI handler because we cannot safely report
- * errors from NMI handlers anyway.
+ * Disable checking if in an NMI handler because we cannot safely
+ * report errors from NMI handlers anyway.  In addition, it is OK to use
+ * RCU on an offline processor during initial boot, hence the check for
+ * rcu_scheduler_fully_active.
  */
 bool rcu_lockdep_current_cpu_online(void)
 {
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
-	bool ret;
+	struct rcu_state *rsp;
 
-	if (in_nmi())
+	if (in_nmi() || !rcu_scheduler_fully_active)
 		return true;
 	preempt_disable();
-	rdp = this_cpu_ptr(&rcu_sched_data);
-	rnp = rdp->mynode;
-	ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) ||
-	      !rcu_scheduler_fully_active;
+	for_each_rcu_flavor(rsp) {
+		rdp = this_cpu_ptr(rsp->rda);
+		rnp = rdp->mynode;
+		if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) {
+			preempt_enable();
+			return true;
+		}
+	}
 	preempt_enable();
-	return ret;
+	return false;
 }
 EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
 
@@ -1115,17 +1105,18 @@ static int rcu_is_cpu_rrupt_from_idle(void)
 /*
  * We are reporting a quiescent state on behalf of some other CPU, so
  * it is our responsibility to check for and handle potential overflow
- * of the rcu_node ->gpnum counter with respect to the rcu_data counters.
+ * of the rcu_node ->gp_seq counter with respect to the rcu_data counters.
  * After all, the CPU might be in deep idle state, and thus executing no
  * code whatsoever.
  */
 static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	raw_lockdep_assert_held_rcu_node(rnp);
-	if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum))
+	if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4,
+			 rnp->gp_seq))
 		WRITE_ONCE(rdp->gpwrap, true);
-	if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum))
-		rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4;
+	if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq))
+		rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4;
 }
 
 /*
@@ -1137,7 +1128,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
 	rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
 	if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
 		rcu_gpnum_ovf(rdp->mynode, rdp);
 		return 1;
 	}
@@ -1159,7 +1150,7 @@ static void rcu_iw_handler(struct irq_work *iwp)
 	rnp = rdp->mynode;
 	raw_spin_lock_rcu_node(rnp);
 	if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
-		rdp->rcu_iw_gpnum = rnp->gpnum;
+		rdp->rcu_iw_gp_seq = rnp->gp_seq;
 		rdp->rcu_iw_pending = false;
 	}
 	raw_spin_unlock_rcu_node(rnp);
@@ -1187,7 +1178,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * of the current RCU grace period.
 	 */
 	if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
 		rdp->dynticks_fqs++;
 		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
@@ -1203,8 +1194,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
 	if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
 	    READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) &&
-	    READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
+	    rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) {
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc"));
 		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
 	} else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) {
@@ -1212,12 +1203,25 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		smp_store_release(ruqp, true);
 	}
 
-	/* Check for the CPU being offline. */
-	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl"));
-		rdp->offline_fqs++;
-		rcu_gpnum_ovf(rnp, rdp);
-		return 1;
+	/* If waiting too long on an offline CPU, complain. */
+	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
+	    time_after(jiffies, rdp->rsp->gp_start + HZ)) {
+		bool onl;
+		struct rcu_node *rnp1;
+
+		WARN_ON(1);  /* Offline CPUs are supposed to report QS! */
+		pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+			__func__, rnp->grplo, rnp->grphi, rnp->level,
+			(long)rnp->gp_seq, (long)rnp->completedqs);
+		for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+			pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n",
+				__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask);
+		onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+		pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n",
+			__func__, rdp->cpu, ".o"[onl],
+			(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+			(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+		return 1; /* Break things loose after complaining. */
 	}
 
 	/*
@@ -1256,11 +1260,11 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) {
 		resched_cpu(rdp->cpu);
 		if (IS_ENABLED(CONFIG_IRQ_WORK) &&
-		    !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum &&
+		    !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
 		    (rnp->ffmask & rdp->grpmask)) {
 			init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
 			rdp->rcu_iw_pending = true;
-			rdp->rcu_iw_gpnum = rnp->gpnum;
+			rdp->rcu_iw_gp_seq = rnp->gp_seq;
 			irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
 		}
 	}
@@ -1274,9 +1278,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 	unsigned long j1;
 
 	rsp->gp_start = j;
-	smp_wmb(); /* Record start time before stall time. */
 	j1 = rcu_jiffies_till_stall_check();
-	WRITE_ONCE(rsp->jiffies_stall, j + j1);
+	/* Record ->gp_start before ->jiffies_stall. */
+	smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */
 	rsp->jiffies_resched = j + j1 / 2;
 	rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
 }
@@ -1302,9 +1306,9 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 	j = jiffies;
 	gpa = READ_ONCE(rsp->gp_activity);
 	if (j - gpa > 2 * HZ) {
-		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
+		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
 		       rsp->name, j - gpa,
-		       rsp->gpnum, rsp->completed,
+		       (long)rcu_seq_current(&rsp->gp_seq),
 		       rsp->gp_flags,
 		       gp_state_getname(rsp->gp_state), rsp->gp_state,
 		       rsp->gp_kthread ? rsp->gp_kthread->state : ~0,
@@ -1359,16 +1363,15 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp)
 	}
 }
 
-static inline void panic_on_rcu_stall(void)
+static void panic_on_rcu_stall(void)
 {
 	if (sysctl_panic_on_rcu_stall)
 		panic("RCU Stall\n");
 }
 
-static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
+static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq)
 {
 	int cpu;
-	long delta;
 	unsigned long flags;
 	unsigned long gpa;
 	unsigned long j;
@@ -1381,25 +1384,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	if (rcu_cpu_stall_suppress)
 		return;
 
-	/* Only let one CPU complain about others per time interval. */
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	delta = jiffies - READ_ONCE(rsp->jiffies_stall);
-	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	WRITE_ONCE(rsp->jiffies_stall,
-		   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
 	/*
 	 * OK, time to rat on our buddy...
 	 * See Documentation/RCU/stallwarn.txt for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
-	pr_err("INFO: %s detected stalls on CPUs/tasks:",
-	       rsp->name);
+	pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name);
 	print_cpu_stall_info_begin();
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -1418,17 +1408,16 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
 							    cpu)->cblist);
-	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
+	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start),
-	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
+	       (long)rcu_seq_current(&rsp->gp_seq), totqlen);
 	if (ndetected) {
 		rcu_dump_cpu_stacks(rsp);
 
 		/* Complain about tasks blocking the grace period. */
 		rcu_print_detail_task_stall(rsp);
 	} else {
-		if (READ_ONCE(rsp->gpnum) != gpnum ||
-		    READ_ONCE(rsp->completed) == gpnum) {
+		if (rcu_seq_current(&rsp->gp_seq) != gp_seq) {
 			pr_err("INFO: Stall ended before state dump start\n");
 		} else {
 			j = jiffies;
@@ -1441,6 +1430,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 			sched_show_task(current);
 		}
 	}
+	/* Rewrite if needed in case of slow consoles. */
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+		WRITE_ONCE(rsp->jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 
 	rcu_check_gp_kthread_starvation(rsp);
 
@@ -1476,15 +1469,16 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
 							    cpu)->cblist);
-	pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
+	pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
 		jiffies - rsp->gp_start,
-		(long)rsp->gpnum, (long)rsp->completed, totqlen);
+		(long)rcu_seq_current(&rsp->gp_seq), totqlen);
 
 	rcu_check_gp_kthread_starvation(rsp);
 
 	rcu_dump_cpu_stacks(rsp);
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	/* Rewrite if needed in case of slow consoles. */
 	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
 		WRITE_ONCE(rsp->jiffies_stall,
 			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
@@ -1504,10 +1498,11 @@ static void print_cpu_stall(struct rcu_state *rsp)
 
 static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	unsigned long completed;
-	unsigned long gpnum;
+	unsigned long gs1;
+	unsigned long gs2;
 	unsigned long gps;
 	unsigned long j;
+	unsigned long jn;
 	unsigned long js;
 	struct rcu_node *rnp;
 
@@ -1520,43 +1515,46 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	/*
 	 * Lots of memory barriers to reject false positives.
 	 *
-	 * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall,
-	 * then rsp->gp_start, and finally rsp->completed.  These values
-	 * are updated in the opposite order with memory barriers (or
-	 * equivalent) during grace-period initialization and cleanup.
-	 * Now, a false positive can occur if we get an new value of
-	 * rsp->gp_start and a old value of rsp->jiffies_stall.  But given
-	 * the memory barriers, the only way that this can happen is if one
-	 * grace period ends and another starts between these two fetches.
-	 * Detect this by comparing rsp->completed with the previous fetch
-	 * from rsp->gpnum.
+	 * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall,
+	 * then rsp->gp_start, and finally another copy of rsp->gp_seq.
+	 * These values are updated in the opposite order with memory
+	 * barriers (or equivalent) during grace-period initialization
+	 * and cleanup.  Now, a false positive can occur if we get an new
+	 * value of rsp->gp_start and a old value of rsp->jiffies_stall.
+	 * But given the memory barriers, the only way that this can happen
+	 * is if one grace period ends and another starts between these
+	 * two fetches.  This is detected by comparing the second fetch
+	 * of rsp->gp_seq with the previous fetch from rsp->gp_seq.
 	 *
 	 * Given this check, comparisons of jiffies, rsp->jiffies_stall,
 	 * and rsp->gp_start suffice to forestall false positives.
 	 */
-	gpnum = READ_ONCE(rsp->gpnum);
-	smp_rmb(); /* Pick up ->gpnum first... */
+	gs1 = READ_ONCE(rsp->gp_seq);
+	smp_rmb(); /* Pick up ->gp_seq first... */
 	js = READ_ONCE(rsp->jiffies_stall);
 	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
 	gps = READ_ONCE(rsp->gp_start);
-	smp_rmb(); /* ...and finally ->gp_start before ->completed. */
-	completed = READ_ONCE(rsp->completed);
-	if (ULONG_CMP_GE(completed, gpnum) ||
+	smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
+	gs2 = READ_ONCE(rsp->gp_seq);
+	if (gs1 != gs2 ||
 	    ULONG_CMP_LT(j, js) ||
 	    ULONG_CMP_GE(gps, js))
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
+	jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
 	if (rcu_gp_in_progress(rsp) &&
-	    (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
+	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+	    cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
 
 	} else if (rcu_gp_in_progress(rsp) &&
-		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
+		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+		   cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
 
 		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(rsp, gpnum);
+		print_other_cpu_stall(rsp, gs2);
 	}
 }
 
@@ -1577,123 +1575,99 @@ void rcu_cpu_stall_reset(void)
 		WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
 }
 
-/*
- * Determine the value that ->completed will have at the end of the
- * next subsequent grace period.  This is used to tag callbacks so that
- * a CPU can invoke callbacks in a timely fashion even if that CPU has
- * been dyntick-idle for an extended period with callbacks under the
- * influence of RCU_FAST_NO_HZ.
- *
- * The caller must hold rnp->lock with interrupts disabled.
- */
-static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
-				       struct rcu_node *rnp)
-{
-	raw_lockdep_assert_held_rcu_node(rnp);
-
-	/*
-	 * If RCU is idle, we just wait for the next grace period.
-	 * But we can only be sure that RCU is idle if we are looking
-	 * at the root rcu_node structure -- otherwise, a new grace
-	 * period might have started, but just not yet gotten around
-	 * to initializing the current non-root rcu_node structure.
-	 */
-	if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed)
-		return rnp->completed + 1;
-
-	/*
-	 * If the current rcu_node structure believes that RCU is
-	 * idle, and if the rcu_state structure does not yet reflect
-	 * the start of a new grace period, then the next grace period
-	 * will suffice.  The memory barrier is needed to accurately
-	 * sample the rsp->gpnum, and pairs with the second lock
-	 * acquisition in rcu_gp_init(), which is augmented with
-	 * smp_mb__after_unlock_lock() for this purpose.
-	 */
-	if (rnp->gpnum == rnp->completed) {
-		smp_mb(); /* See above block comment. */
-		if (READ_ONCE(rsp->gpnum) == rnp->completed)
-			return rnp->completed + 1;
-	}
-
-	/*
-	 * Otherwise, wait for a possible partial grace period and
-	 * then the subsequent full grace period.
-	 */
-	return rnp->completed + 2;
-}
-
 /* Trace-event wrapper function for trace_rcu_future_grace_period.  */
 static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
-			      unsigned long c, const char *s)
+			      unsigned long gp_seq_req, const char *s)
 {
-	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
-				      rnp->completed, c, rnp->level,
-				      rnp->grplo, rnp->grphi, s);
+	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req,
+				      rnp->level, rnp->grplo, rnp->grphi, s);
 }
 
 /*
+ * rcu_start_this_gp - Request the start of a particular grace period
+ * @rnp_start: The leaf node of the CPU from which to start.
+ * @rdp: The rcu_data corresponding to the CPU from which to start.
+ * @gp_seq_req: The gp_seq of the grace period to start.
+ *
  * Start the specified grace period, as needed to handle newly arrived
  * callbacks.  The required future grace periods are recorded in each
- * rcu_node structure's ->need_future_gp[] field.  Returns true if there
+ * rcu_node structure's ->gp_seq_needed field.  Returns true if there
  * is reason to awaken the grace-period kthread.
  *
  * The caller must hold the specified rcu_node structure's ->lock, which
  * is why the caller is responsible for waking the grace-period kthread.
+ *
+ * Returns true if the GP thread needs to be awakened else false.
  */
-static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
-			      unsigned long c)
+static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
+			      unsigned long gp_seq_req)
 {
 	bool ret = false;
 	struct rcu_state *rsp = rdp->rsp;
-	struct rcu_node *rnp_root;
+	struct rcu_node *rnp;
 
 	/*
 	 * Use funnel locking to either acquire the root rcu_node
 	 * structure's lock or bail out if the need for this grace period
-	 * has already been recorded -- or has already started.  If there
-	 * is already a grace period in progress in a non-leaf node, no
-	 * recording is needed because the end of the grace period will
-	 * scan the leaf rcu_node structures.  Note that rnp->lock must
-	 * not be released.
+	 * has already been recorded -- or if that grace period has in
+	 * fact already started.  If there is already a grace period in
+	 * progress in a non-leaf node, no recording is needed because the
+	 * end of the grace period will scan the leaf rcu_node structures.
+	 * Note that rnp_start->lock must not be released.
 	 */
-	raw_lockdep_assert_held_rcu_node(rnp);
-	trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
-	for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
-		if (rnp_root != rnp)
-			raw_spin_lock_rcu_node(rnp_root);
-		WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum +
-					  need_future_gp_mask(), c));
-		if (need_future_gp_element(rnp_root, c) ||
-		    ULONG_CMP_GE(rnp_root->gpnum, c) ||
-		    (rnp != rnp_root &&
-		     rnp_root->gpnum != rnp_root->completed)) {
-			trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
+	raw_lockdep_assert_held_rcu_node(rnp_start);
+	trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf"));
+	for (rnp = rnp_start; 1; rnp = rnp->parent) {
+		if (rnp != rnp_start)
+			raw_spin_lock_rcu_node(rnp);
+		if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) ||
+		    rcu_seq_started(&rnp->gp_seq, gp_seq_req) ||
+		    (rnp != rnp_start &&
+		     rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) {
+			trace_rcu_this_gp(rnp, rdp, gp_seq_req,
+					  TPS("Prestarted"));
 			goto unlock_out;
 		}
-		need_future_gp_element(rnp_root, c) = true;
-		if (rnp_root != rnp && rnp_root->parent != NULL)
-			raw_spin_unlock_rcu_node(rnp_root);
-		if (!rnp_root->parent)
+		rnp->gp_seq_needed = gp_seq_req;
+		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
+			/*
+			 * We just marked the leaf or internal node, and a
+			 * grace period is in progress, which means that
+			 * rcu_gp_cleanup() will see the marking.  Bail to
+			 * reduce contention.
+			 */
+			trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
+					  TPS("Startedleaf"));
+			goto unlock_out;
+		}
+		if (rnp != rnp_start && rnp->parent != NULL)
+			raw_spin_unlock_rcu_node(rnp);
+		if (!rnp->parent)
 			break;  /* At root, and perhaps also leaf. */
 	}
 
 	/* If GP already in progress, just leave, otherwise start one. */
-	if (rnp_root->gpnum != rnp_root->completed) {
-		trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot"));
+	if (rcu_gp_in_progress(rsp)) {
+		trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot"));
 		goto unlock_out;
 	}
-	trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot"));
+	trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
 	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
+	rsp->gp_req_activity = jiffies;
 	if (!rsp->gp_kthread) {
-		trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
+		trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
 		goto unlock_out;
 	}
-	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq"));
+	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq"));
 	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
-	if (rnp != rnp_root)
-		raw_spin_unlock_rcu_node(rnp_root);
+	/* Push furthest requested GP to leaf node and rcu_data structure. */
+	if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
+		rnp_start->gp_seq_needed = rnp->gp_seq_needed;
+		rdp->gp_seq_needed = rnp->gp_seq_needed;
+	}
+	if (rnp != rnp_start)
+		raw_spin_unlock_rcu_node(rnp);
 	return ret;
 }
 
@@ -1703,13 +1677,13 @@ unlock_out:
  */
 static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 {
-	unsigned long c = rnp->completed;
 	bool needmore;
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
-	need_future_gp_element(rnp, c) = false;
-	needmore = need_any_future_gp(rnp);
-	trace_rcu_this_gp(rnp, rdp, c,
+	needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed);
+	if (!needmore)
+		rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */
+	trace_rcu_this_gp(rnp, rdp, rnp->gp_seq,
 			  needmore ? TPS("CleanupMore") : TPS("Cleanup"));
 	return needmore;
 }
@@ -1727,25 +1701,25 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 	    !READ_ONCE(rsp->gp_flags) ||
 	    !rsp->gp_kthread)
 		return;
-	swake_up(&rsp->gp_wq);
+	swake_up_one(&rsp->gp_wq);
 }
 
 /*
- * If there is room, assign a ->completed number to any callbacks on
- * this CPU that have not already been assigned.  Also accelerate any
- * callbacks that were previously assigned a ->completed number that has
- * since proven to be too conservative, which can happen if callbacks get
- * assigned a ->completed number while RCU is idle, but with reference to
- * a non-root rcu_node structure.  This function is idempotent, so it does
- * not hurt to call it repeatedly.  Returns an flag saying that we should
- * awaken the RCU grace-period kthread.
+ * If there is room, assign a ->gp_seq number to any callbacks on this
+ * CPU that have not already been assigned.  Also accelerate any callbacks
+ * that were previously assigned a ->gp_seq number that has since proven
+ * to be too conservative, which can happen if callbacks get assigned a
+ * ->gp_seq number while RCU is idle, but with reference to a non-root
+ * rcu_node structure.  This function is idempotent, so it does not hurt
+ * to call it repeatedly.  Returns an flag saying that we should awaken
+ * the RCU grace-period kthread.
  *
  * The caller must hold rnp->lock with interrupts disabled.
  */
 static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 			       struct rcu_data *rdp)
 {
-	unsigned long c;
+	unsigned long gp_seq_req;
 	bool ret = false;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
@@ -1764,22 +1738,50 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 	 * accelerating callback invocation to an earlier grace-period
 	 * number.
 	 */
-	c = rcu_cbs_completed(rsp, rnp);
-	if (rcu_segcblist_accelerate(&rdp->cblist, c))
-		ret = rcu_start_this_gp(rnp, rdp, c);
+	gp_seq_req = rcu_seq_snap(&rsp->gp_seq);
+	if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req))
+		ret = rcu_start_this_gp(rnp, rdp, gp_seq_req);
 
 	/* Trace depending on how much we were able to accelerate. */
 	if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB"));
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB"));
 	else
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB"));
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB"));
 	return ret;
 }
 
 /*
+ * Similar to rcu_accelerate_cbs(), but does not require that the leaf
+ * rcu_node structure's ->lock be held.  It consults the cached value
+ * of ->gp_seq_needed in the rcu_data structure, and if that indicates
+ * that a new grace-period request be made, invokes rcu_accelerate_cbs()
+ * while holding the leaf rcu_node structure's ->lock.
+ */
+static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp,
+					struct rcu_node *rnp,
+					struct rcu_data *rdp)
+{
+	unsigned long c;
+	bool needwake;
+
+	lockdep_assert_irqs_disabled();
+	c = rcu_seq_snap(&rsp->gp_seq);
+	if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+		/* Old request still live, so mark recent callbacks. */
+		(void)rcu_segcblist_accelerate(&rdp->cblist, c);
+		return;
+	}
+	raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+	needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+	raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
+	if (needwake)
+		rcu_gp_kthread_wake(rsp);
+}
+
+/*
  * Move any callbacks whose grace period has completed to the
  * RCU_DONE_TAIL sublist, then compact the remaining sublists and
- * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
+ * assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL
  * sublist.  This function is idempotent, so it does not hurt to
  * invoke it repeatedly.  As long as it is not invoked -too- often...
  * Returns true if the RCU grace-period kthread needs to be awakened.
@@ -1796,10 +1798,10 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 		return false;
 
 	/*
-	 * Find all callbacks whose ->completed numbers indicate that they
+	 * Find all callbacks whose ->gp_seq numbers indicate that they
 	 * are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
 	 */
-	rcu_segcblist_advance(&rdp->cblist, rnp->completed);
+	rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq);
 
 	/* Classify any remaining callbacks. */
 	return rcu_accelerate_cbs(rsp, rnp, rdp);
@@ -1819,39 +1821,38 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 
 	raw_lockdep_assert_held_rcu_node(rnp);
 
-	/* Handle the ends of any preceding grace periods first. */
-	if (rdp->completed == rnp->completed &&
-	    !unlikely(READ_ONCE(rdp->gpwrap))) {
-
-		/* No grace period end, so just accelerate recent callbacks. */
-		ret = rcu_accelerate_cbs(rsp, rnp, rdp);
+	if (rdp->gp_seq == rnp->gp_seq)
+		return false; /* Nothing to do. */
 
+	/* Handle the ends of any preceding grace periods first. */
+	if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
+	    unlikely(READ_ONCE(rdp->gpwrap))) {
+		ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend"));
 	} else {
-
-		/* Advance callbacks. */
-		ret = rcu_advance_cbs(rsp, rnp, rdp);
-
-		/* Remember that we saw this grace-period completion. */
-		rdp->completed = rnp->completed;
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
+		ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */
 	}
 
-	if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
+	/* Now handle the beginnings of any new-to-this-CPU grace periods. */
+	if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) ||
+	    unlikely(READ_ONCE(rdp->gpwrap))) {
 		/*
 		 * If the current grace period is waiting for this CPU,
 		 * set up to detect a quiescent state, otherwise don't
 		 * go looking for one.
 		 */
-		rdp->gpnum = rnp->gpnum;
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
+		trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart"));
 		need_gp = !!(rnp->qsmask & rdp->grpmask);
 		rdp->cpu_no_qs.b.norm = need_gp;
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
 		rdp->core_needs_qs = need_gp;
 		zero_cpu_stall_ticks(rdp);
-		WRITE_ONCE(rdp->gpwrap, false);
-		rcu_gpnum_ovf(rnp, rdp);
 	}
+	rdp->gp_seq = rnp->gp_seq;  /* Remember new grace-period state. */
+	if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap)
+		rdp->gp_seq_needed = rnp->gp_seq_needed;
+	WRITE_ONCE(rdp->gpwrap, false);
+	rcu_gpnum_ovf(rnp, rdp);
 	return ret;
 }
 
@@ -1863,8 +1864,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	local_irq_save(flags);
 	rnp = rdp->mynode;
-	if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
-	     rdp->completed == READ_ONCE(rnp->completed) &&
+	if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) &&
 	     !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
 	    !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
@@ -1879,7 +1879,8 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 static void rcu_gp_slow(struct rcu_state *rsp, int delay)
 {
 	if (delay > 0 &&
-	    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
+	    !(rcu_seq_ctr(rsp->gp_seq) %
+	      (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
 		schedule_timeout_uninterruptible(delay);
 }
 
@@ -1888,7 +1889,9 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay)
  */
 static bool rcu_gp_init(struct rcu_state *rsp)
 {
+	unsigned long flags;
 	unsigned long oldmask;
+	unsigned long mask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
@@ -1912,9 +1915,9 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 
 	/* Advance to a new grace period and initialize state. */
 	record_gp_stall_check_time(rsp);
-	/* Record GP times before starting GP, hence smp_store_release(). */
-	smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
-	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
+	/* Record GP times before starting GP, hence rcu_seq_start(). */
+	rcu_seq_start(&rsp->gp_seq);
+	trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start"));
 	raw_spin_unlock_irq_rcu_node(rnp);
 
 	/*
@@ -1923,13 +1926,15 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 * for subsequent online CPUs, and that quiescent-state forcing
 	 * will handle subsequent offline CPUs.
 	 */
+	rsp->gp_state = RCU_GP_ONOFF;
 	rcu_for_each_leaf_node(rsp, rnp) {
-		rcu_gp_slow(rsp, gp_preinit_delay);
+		spin_lock(&rsp->ofl_lock);
 		raw_spin_lock_irq_rcu_node(rnp);
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
 		    !rnp->wait_blkd_tasks) {
 			/* Nothing to do on this leaf rcu_node structure. */
 			raw_spin_unlock_irq_rcu_node(rnp);
+			spin_unlock(&rsp->ofl_lock);
 			continue;
 		}
 
@@ -1939,12 +1944,14 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 
 		/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
 		if (!oldmask != !rnp->qsmaskinit) {
-			if (!oldmask) /* First online CPU for this rcu_node. */
-				rcu_init_new_rnp(rnp);
-			else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */
-				rnp->wait_blkd_tasks = true;
-			else /* Last offline CPU and can propagate. */
+			if (!oldmask) { /* First online CPU for rcu_node. */
+				if (!rnp->wait_blkd_tasks) /* Ever offline? */
+					rcu_init_new_rnp(rnp);
+			} else if (rcu_preempt_has_tasks(rnp)) {
+				rnp->wait_blkd_tasks = true; /* blocked tasks */
+			} else { /* Last offline CPU and can propagate. */
 				rcu_cleanup_dead_rnp(rnp);
+			}
 		}
 
 		/*
@@ -1953,18 +1960,19 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		 * still offline, propagate up the rcu_node tree and
 		 * clear ->wait_blkd_tasks.  Otherwise, if one of this
 		 * rcu_node structure's CPUs has since come back online,
-		 * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp()
-		 * checks for this, so just call it unconditionally).
+		 * simply clear ->wait_blkd_tasks.
 		 */
 		if (rnp->wait_blkd_tasks &&
-		    (!rcu_preempt_has_tasks(rnp) ||
-		     rnp->qsmaskinit)) {
+		    (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) {
 			rnp->wait_blkd_tasks = false;
-			rcu_cleanup_dead_rnp(rnp);
+			if (!rnp->qsmaskinit)
+				rcu_cleanup_dead_rnp(rnp);
 		}
 
 		raw_spin_unlock_irq_rcu_node(rnp);
+		spin_unlock(&rsp->ofl_lock);
 	}
+	rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */
 
 	/*
 	 * Set the quiescent-state-needed bits in all the rcu_node
@@ -1978,22 +1986,27 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 * The grace period cannot complete until the initialization
 	 * process finishes, because this kthread handles both.
 	 */
+	rsp->gp_state = RCU_GP_INIT;
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_init_delay);
-		raw_spin_lock_irq_rcu_node(rnp);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		rdp = this_cpu_ptr(rsp->rda);
-		rcu_preempt_check_blocked_tasks(rnp);
+		rcu_preempt_check_blocked_tasks(rsp, rnp);
 		rnp->qsmask = rnp->qsmaskinit;
-		WRITE_ONCE(rnp->gpnum, rsp->gpnum);
-		if (WARN_ON_ONCE(rnp->completed != rsp->completed))
-			WRITE_ONCE(rnp->completed, rsp->completed);
+		WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
 		if (rnp == rdp->mynode)
 			(void)__note_gp_changes(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
-		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
+		trace_rcu_grace_period_init(rsp->name, rnp->gp_seq,
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
-		raw_spin_unlock_irq_rcu_node(rnp);
+		/* Quiescent states for tasks on any now-offline CPUs. */
+		mask = rnp->qsmask & ~rnp->qsmaskinitnext;
+		rnp->rcu_gp_init_mask = mask;
+		if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+		else
+			raw_spin_unlock_irq_rcu_node(rnp);
 		cond_resched_tasks_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 	}
@@ -2002,7 +2015,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 }
 
 /*
- * Helper function for swait_event_idle() wakeup at force-quiescent-state
+ * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state
  * time.
  */
 static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
@@ -2053,6 +2066,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 {
 	unsigned long gp_duration;
 	bool needgp = false;
+	unsigned long new_gp_seq;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	struct swait_queue_head *sq;
@@ -2074,19 +2088,22 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	raw_spin_unlock_irq_rcu_node(rnp);
 
 	/*
-	 * Propagate new ->completed value to rcu_node structures so
-	 * that other CPUs don't have to wait until the start of the next
-	 * grace period to process their callbacks.  This also avoids
-	 * some nasty RCU grace-period initialization races by forcing
-	 * the end of the current grace period to be completely recorded in
-	 * all of the rcu_node structures before the beginning of the next
-	 * grace period is recorded in any of the rcu_node structures.
+	 * Propagate new ->gp_seq value to rcu_node structures so that
+	 * other CPUs don't have to wait until the start of the next grace
+	 * period to process their callbacks.  This also avoids some nasty
+	 * RCU grace-period initialization races by forcing the end of
+	 * the current grace period to be completely recorded in all of
+	 * the rcu_node structures before the beginning of the next grace
+	 * period is recorded in any of the rcu_node structures.
 	 */
+	new_gp_seq = rsp->gp_seq;
+	rcu_seq_end(&new_gp_seq);
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq_rcu_node(rnp);
-		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+		if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+			dump_blkd_tasks(rsp, rnp, 10);
 		WARN_ON_ONCE(rnp->qsmask);
-		WRITE_ONCE(rnp->completed, rsp->gpnum);
+		WRITE_ONCE(rnp->gp_seq, new_gp_seq);
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
 			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
@@ -2100,26 +2117,28 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
-	raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
+	raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */
 
 	/* Declare grace period done. */
-	WRITE_ONCE(rsp->completed, rsp->gpnum);
-	trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
+	rcu_seq_end(&rsp->gp_seq);
+	trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end"));
 	rsp->gp_state = RCU_GP_IDLE;
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(rsp->rda);
-	if (need_any_future_gp(rnp)) {
-		trace_rcu_this_gp(rnp, rdp, rsp->completed - 1,
+	if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
+		trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed,
 				  TPS("CleanupMore"));
 		needgp = true;
 	}
 	/* Advance CBs to reduce false positives below. */
 	if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
 		WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
-		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
+		rsp->gp_req_activity = jiffies;
+		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq),
 				       TPS("newreq"));
+	} else {
+		WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
 	}
-	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
 	raw_spin_unlock_irq_rcu_node(rnp);
 }
 
@@ -2141,10 +2160,10 @@ static int __noreturn rcu_gp_kthread(void *arg)
 		/* Handle grace-period start. */
 		for (;;) {
 			trace_rcu_grace_period(rsp->name,
-					       READ_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gp_seq),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
-			swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
+			swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
 						     RCU_GP_FLAG_INIT);
 			rsp->gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
@@ -2154,17 +2173,13 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			WRITE_ONCE(rsp->gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
 			trace_rcu_grace_period(rsp->name,
-					       READ_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gp_seq),
 					       TPS("reqwaitsig"));
 		}
 
 		/* Handle quiescent-state forcing. */
 		first_gp_fqs = true;
 		j = jiffies_till_first_fqs;
-		if (j > HZ) {
-			j = HZ;
-			jiffies_till_first_fqs = HZ;
-		}
 		ret = 0;
 		for (;;) {
 			if (!ret) {
@@ -2173,10 +2188,10 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					   jiffies + 3 * j);
 			}
 			trace_rcu_grace_period(rsp->name,
-					       READ_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gp_seq),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
-			ret = swait_event_idle_timeout(rsp->gp_wq,
+			ret = swait_event_idle_timeout_exclusive(rsp->gp_wq,
 					rcu_gp_fqs_check_wake(rsp, &gf), j);
 			rsp->gp_state = RCU_GP_DOING_FQS;
 			/* Locking provides needed memory barriers. */
@@ -2188,31 +2203,24 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
 			    (gf & RCU_GP_FLAG_FQS)) {
 				trace_rcu_grace_period(rsp->name,
-						       READ_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gp_seq),
 						       TPS("fqsstart"));
 				rcu_gp_fqs(rsp, first_gp_fqs);
 				first_gp_fqs = false;
 				trace_rcu_grace_period(rsp->name,
-						       READ_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gp_seq),
 						       TPS("fqsend"));
 				cond_resched_tasks_rcu_qs();
 				WRITE_ONCE(rsp->gp_activity, jiffies);
 				ret = 0; /* Force full wait till next FQS. */
 				j = jiffies_till_next_fqs;
-				if (j > HZ) {
-					j = HZ;
-					jiffies_till_next_fqs = HZ;
-				} else if (j < 1) {
-					j = 1;
-					jiffies_till_next_fqs = 1;
-				}
 			} else {
 				/* Deal with stray signal. */
 				cond_resched_tasks_rcu_qs();
 				WRITE_ONCE(rsp->gp_activity, jiffies);
 				WARN_ON(signal_pending(current));
 				trace_rcu_grace_period(rsp->name,
-						       READ_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gp_seq),
 						       TPS("fqswaitsig"));
 				ret = 1; /* Keep old FQS timing. */
 				j = jiffies;
@@ -2256,8 +2264,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
  * must be represented by the same rcu_node structure (which need not be a
  * leaf rcu_node structure, though it often will be).  The gps parameter
  * is the grace-period snapshot, which means that the quiescent states
- * are valid only if rnp->gpnum is equal to gps.  That structure's lock
+ * are valid only if rnp->gp_seq is equal to gps.  That structure's lock
  * must be held upon entry, and it is released before return.
+ *
+ * As a special case, if mask is zero, the bit-already-cleared check is
+ * disabled.  This allows propagating quiescent state due to resumed tasks
+ * during grace-period initialization.
  */
 static void
 rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
@@ -2271,7 +2283,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 
 	/* Walk up the rcu_node hierarchy. */
 	for (;;) {
-		if (!(rnp->qsmask & mask) || rnp->gpnum != gps) {
+		if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) {
 
 			/*
 			 * Our bit has already been cleared, or the
@@ -2284,7 +2296,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
 			     rcu_preempt_blocked_readers_cgp(rnp));
 		rnp->qsmask &= ~mask;
-		trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
+		trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq,
 						 mask, rnp->qsmask, rnp->level,
 						 rnp->grplo, rnp->grphi,
 						 !!rnp->gp_tasks);
@@ -2294,6 +2306,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			return;
 		}
+		rnp->completedqs = rnp->gp_seq;
 		mask = rnp->grpmask;
 		if (rnp->parent == NULL) {
 
@@ -2323,8 +2336,9 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
  * irqs disabled, and this lock is released upon return, but irqs remain
  * disabled.
  */
-static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
-				      struct rcu_node *rnp, unsigned long flags)
+static void __maybe_unused
+rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
+			  struct rcu_node *rnp, unsigned long flags)
 	__releases(rnp->lock)
 {
 	unsigned long gps;
@@ -2332,12 +2346,15 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 	struct rcu_node *rnp_p;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
-	if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p ||
-	    rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
+	if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) ||
+	    WARN_ON_ONCE(rsp != rcu_state_p) ||
+	    WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
+	    rnp->qsmask != 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;  /* Still need more quiescent states! */
 	}
 
+	rnp->completedqs = rnp->gp_seq;
 	rnp_p = rnp->parent;
 	if (rnp_p == NULL) {
 		/*
@@ -2348,8 +2365,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 		return;
 	}
 
-	/* Report up the rest of the hierarchy, tracking current ->gpnum. */
-	gps = rnp->gpnum;
+	/* Report up the rest of the hierarchy, tracking current ->gp_seq. */
+	gps = rnp->gp_seq;
 	mask = rnp->grpmask;
 	raw_spin_unlock_rcu_node(rnp);	/* irqs remain disabled. */
 	raw_spin_lock_rcu_node(rnp_p);	/* irqs already disabled. */
@@ -2370,8 +2387,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum ||
-	    rnp->completed == rnp->gpnum || rdp->gpwrap) {
+	if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
+	    rdp->gpwrap) {
 
 		/*
 		 * The grace period in which this quiescent state was
@@ -2396,7 +2413,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 */
 		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 
-		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
 		/* ^^^ Released rnp->lock */
 		if (needwake)
 			rcu_gp_kthread_wake(rsp);
@@ -2441,17 +2458,16 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
 {
-	RCU_TRACE(unsigned long mask;)
+	RCU_TRACE(bool blkd;)
 	RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);)
 	RCU_TRACE(struct rcu_node *rnp = rdp->mynode;)
 
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
 		return;
 
-	RCU_TRACE(mask = rdp->grpmask;)
-	trace_rcu_grace_period(rsp->name,
-			       rnp->gpnum + 1 - !!(rnp->qsmask & mask),
-			       TPS("cpuofl"));
+	RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);)
+	trace_rcu_grace_period(rsp->name, rnp->gp_seq,
+			       blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
 }
 
 /*
@@ -2463,7 +2479,7 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
  * This function therefore goes up the tree of rcu_node structures,
  * clearing the corresponding bits in the ->qsmaskinit fields.  Note that
  * the leaf rcu_node structure's ->qsmaskinit field has already been
- * updated
+ * updated.
  *
  * This function does check that the specified rcu_node structure has
  * all CPUs offline and no blocked tasks, so it is OK to invoke it
@@ -2476,9 +2492,10 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 	long mask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	raw_lockdep_assert_held_rcu_node(rnp);
+	raw_lockdep_assert_held_rcu_node(rnp_leaf);
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
-	    rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+	    WARN_ON_ONCE(rnp_leaf->qsmaskinit) ||
+	    WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf)))
 		return;
 	for (;;) {
 		mask = rnp->grpmask;
@@ -2487,7 +2504,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 			break;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		rnp->qsmaskinit &= ~mask;
-		rnp->qsmask &= ~mask;
+		/* Between grace periods, so better already be zero! */
+		WARN_ON_ONCE(rnp->qsmask);
 		if (rnp->qsmaskinit) {
 			raw_spin_unlock_rcu_node(rnp);
 			/* irqs remain disabled. */
@@ -2630,6 +2648,7 @@ void rcu_check_callbacks(int user)
 
 		rcu_sched_qs();
 		rcu_bh_qs();
+		rcu_note_voluntary_context_switch(current);
 
 	} else if (!in_softirq()) {
 
@@ -2645,8 +2664,7 @@ void rcu_check_callbacks(int user)
 	rcu_preempt_check_callbacks();
 	if (rcu_pending())
 		invoke_rcu_core();
-	if (user)
-		rcu_note_voluntary_context_switch(current);
+
 	trace_rcu_utilization(TPS("End scheduler-tick"));
 }
 
@@ -2681,17 +2699,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
 				/* rcu_initiate_boost() releases rnp->lock */
 				continue;
 			}
-			if (rnp->parent &&
-			    (rnp->parent->qsmask & rnp->grpmask)) {
-				/*
-				 * Race between grace-period
-				 * initialization and task exiting RCU
-				 * read-side critical section: Report.
-				 */
-				rcu_report_unblock_qs_rnp(rsp, rnp, flags);
-				/* rcu_report_unblock_qs_rnp() rlses ->lock */
-				continue;
-			}
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+			continue;
 		}
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
@@ -2701,8 +2710,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
 			}
 		}
 		if (mask != 0) {
-			/* Idle/offline CPUs, report (releases rnp->lock. */
-			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+			/* Idle/offline CPUs, report (releases rnp->lock). */
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
 		} else {
 			/* Nothing to do here, so just drop the lock. */
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2747,6 +2756,65 @@ static void force_quiescent_state(struct rcu_state *rsp)
 }
 
 /*
+ * This function checks for grace-period requests that fail to motivate
+ * RCU to come out of its idle mode.
+ */
+static void
+rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
+			 struct rcu_data *rdp)
+{
+	const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
+	unsigned long flags;
+	unsigned long j;
+	struct rcu_node *rnp_root = rcu_get_root(rsp);
+	static atomic_t warned = ATOMIC_INIT(0);
+
+	if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+		return;
+	j = jiffies; /* Expensive access, and in common case don't get here. */
+	if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
+	    atomic_read(&warned))
+		return;
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	j = jiffies;
+	if (rcu_gp_in_progress(rsp) ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
+	    atomic_read(&warned)) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	/* Hold onto the leaf lock to make others see warned==1. */
+
+	if (rnp_root != rnp)
+		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+	j = jiffies;
+	if (rcu_gp_in_progress(rsp) ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    time_before(j, rsp->gp_req_activity + gpssdelay) ||
+	    time_before(j, rsp->gp_activity + gpssdelay) ||
+	    atomic_xchg(&warned, 1)) {
+		raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
+		 __func__, (long)READ_ONCE(rsp->gp_seq),
+		 (long)READ_ONCE(rnp_root->gp_seq_needed),
+		 j - rsp->gp_req_activity, j - rsp->gp_activity,
+		 rsp->gp_flags, rsp->gp_state, rsp->name,
+		 rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL);
+	WARN_ON(1);
+	if (rnp_root != rnp)
+		raw_spin_unlock_rcu_node(rnp_root);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+}
+
+/*
  * This does the RCU core processing work for the specified rcu_state
  * and rcu_data structures.  This may be called only from the CPU to
  * whom the rdp belongs.
@@ -2755,9 +2823,8 @@ static void
 __rcu_process_callbacks(struct rcu_state *rsp)
 {
 	unsigned long flags;
-	bool needwake;
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
-	struct rcu_node *rnp;
+	struct rcu_node *rnp = rdp->mynode;
 
 	WARN_ON_ONCE(!rdp->beenonline);
 
@@ -2768,18 +2835,13 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	if (!rcu_gp_in_progress(rsp) &&
 	    rcu_segcblist_is_enabled(&rdp->cblist)) {
 		local_irq_save(flags);
-		if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
-			local_irq_restore(flags);
-		} else {
-			rnp = rdp->mynode;
-			raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
-			needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
-			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-			if (needwake)
-				rcu_gp_kthread_wake(rsp);
-		}
+		if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
+			rcu_accelerate_cbs_unlocked(rsp, rnp, rdp);
+		local_irq_restore(flags);
 	}
 
+	rcu_check_gp_start_stall(rsp, rnp, rdp);
+
 	/* If there are callbacks ready, invoke them. */
 	if (rcu_segcblist_ready_cbs(&rdp->cblist))
 		invoke_rcu_callbacks(rsp, rdp);
@@ -2833,8 +2895,6 @@ static void invoke_rcu_core(void)
 static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 			    struct rcu_head *head, unsigned long flags)
 {
-	bool needwake;
-
 	/*
 	 * If called from an extended quiescent state, invoke the RCU
 	 * core in order to force a re-evaluation of RCU's idleness.
@@ -2861,13 +2921,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 
 		/* Start a new grace period if one not already started. */
 		if (!rcu_gp_in_progress(rsp)) {
-			struct rcu_node *rnp = rdp->mynode;
-
-			raw_spin_lock_rcu_node(rnp);
-			needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
-			raw_spin_unlock_rcu_node(rnp);
-			if (needwake)
-				rcu_gp_kthread_wake(rsp);
+			rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp);
 		} else {
 			/* Give the grace period a kick. */
 			rdp->blimit = LONG_MAX;
@@ -3037,7 +3091,7 @@ EXPORT_SYMBOL_GPL(kfree_call_rcu);
  * when there was in fact only one the whole time, as this just adds
  * some overhead: RCU still operates correctly.
  */
-static inline int rcu_blocking_is_gp(void)
+static int rcu_blocking_is_gp(void)
 {
 	int ret;
 
@@ -3136,16 +3190,10 @@ unsigned long get_state_synchronize_rcu(void)
 {
 	/*
 	 * Any prior manipulation of RCU-protected data must happen
-	 * before the load from ->gpnum.
+	 * before the load from ->gp_seq.
 	 */
 	smp_mb();  /* ^^^ */
-
-	/*
-	 * Make sure this load happens before the purportedly
-	 * time-consuming work between get_state_synchronize_rcu()
-	 * and cond_synchronize_rcu().
-	 */
-	return smp_load_acquire(&rcu_state_p->gpnum);
+	return rcu_seq_snap(&rcu_state_p->gp_seq);
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
 
@@ -3165,15 +3213,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
  */
 void cond_synchronize_rcu(unsigned long oldstate)
 {
-	unsigned long newstate;
-
-	/*
-	 * Ensure that this load happens before any RCU-destructive
-	 * actions the caller might carry out after we return.
-	 */
-	newstate = smp_load_acquire(&rcu_state_p->completed);
-	if (ULONG_CMP_GE(oldstate, newstate))
+	if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate))
 		synchronize_rcu();
+	else
+		smp_mb(); /* Ensure GP ends before subsequent accesses. */
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
 
@@ -3188,16 +3231,10 @@ unsigned long get_state_synchronize_sched(void)
 {
 	/*
 	 * Any prior manipulation of RCU-protected data must happen
-	 * before the load from ->gpnum.
+	 * before the load from ->gp_seq.
 	 */
 	smp_mb();  /* ^^^ */
-
-	/*
-	 * Make sure this load happens before the purportedly
-	 * time-consuming work between get_state_synchronize_sched()
-	 * and cond_synchronize_sched().
-	 */
-	return smp_load_acquire(&rcu_sched_state.gpnum);
+	return rcu_seq_snap(&rcu_sched_state.gp_seq);
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
 
@@ -3217,15 +3254,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
  */
 void cond_synchronize_sched(unsigned long oldstate)
 {
-	unsigned long newstate;
-
-	/*
-	 * Ensure that this load happens before any RCU-destructive
-	 * actions the caller might carry out after we return.
-	 */
-	newstate = smp_load_acquire(&rcu_sched_state.completed);
-	if (ULONG_CMP_GE(oldstate, newstate))
+	if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate))
 		synchronize_sched();
+	else
+		smp_mb(); /* Ensure GP ends before subsequent accesses. */
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_sched);
 
@@ -3261,12 +3293,8 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	    !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
 		return 1;
 
-	/* Has another RCU grace period completed?  */
-	if (READ_ONCE(rnp->completed) != rdp->completed) /* outside lock */
-		return 1;
-
-	/* Has a new RCU grace period started? */
-	if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
+	/* Have RCU grace period completed or started?  */
+	if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq ||
 	    unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */
 		return 1;
 
@@ -3298,7 +3326,7 @@ static int rcu_pending(void)
  * non-NULL, store an indication of whether all callbacks are lazy.
  * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
+static bool rcu_cpu_has_callbacks(bool *all_lazy)
 {
 	bool al = true;
 	bool hc = false;
@@ -3484,17 +3512,22 @@ EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 {
 	long mask;
+	long oldmask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	raw_lockdep_assert_held_rcu_node(rnp);
+	raw_lockdep_assert_held_rcu_node(rnp_leaf);
+	WARN_ON_ONCE(rnp->wait_blkd_tasks);
 	for (;;) {
 		mask = rnp->grpmask;
 		rnp = rnp->parent;
 		if (rnp == NULL)
 			return;
 		raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
+		oldmask = rnp->qsmaskinit;
 		rnp->qsmaskinit |= mask;
 		raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */
+		if (oldmask)
+			return;
 	}
 }
 
@@ -3511,6 +3544,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1);
 	WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
+	rdp->rcu_ofl_gp_seq = rsp->gp_seq;
+	rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
+	rdp->rcu_onl_gp_seq = rsp->gp_seq;
+	rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	rcu_boot_init_nocb_percpu_data(rdp);
@@ -3518,9 +3555,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 
 /*
  * Initialize a CPU's per-CPU RCU data.  Note that only one online or
- * offline event can be happening at a given time.  Note also that we
- * can accept some slop in the rsp->completed access due to the fact
- * that this CPU cannot possibly have any RCU callbacks in flight yet.
+ * offline event can be happening at a given time.  Note also that we can
+ * accept some slop in the rsp->gp_seq access due to the fact that this
+ * CPU cannot possibly have any RCU callbacks in flight yet.
  */
 static void
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
@@ -3549,14 +3586,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rnp = rdp->mynode;
 	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	rdp->beenonline = true;	 /* We have now been online. */
-	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
-	rdp->completed = rnp->completed;
+	rdp->gp_seq = rnp->gp_seq;
+	rdp->gp_seq_needed = rnp->gp_seq;
 	rdp->cpu_no_qs.b.norm = true;
 	rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
 	rdp->core_needs_qs = false;
 	rdp->rcu_iw_pending = false;
-	rdp->rcu_iw_gpnum = rnp->gpnum - 1;
-	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
+	rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
+	trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
@@ -3705,7 +3742,15 @@ void rcu_cpu_starting(unsigned int cpu)
 		nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
 		/* Allow lockless access for expedited grace periods. */
 		smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
+		rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq);
+		rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags);
+		if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+			/* Report QS -after- changing ->qsmaskinitnext! */
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+		} else {
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		}
 	}
 	smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
 }
@@ -3713,7 +3758,7 @@ void rcu_cpu_starting(unsigned int cpu)
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
- * function.  We now remove it from the rcu_node tree's ->qsmaskinit
+ * function.  We now remove it from the rcu_node tree's ->qsmaskinitnext
  * bit masks.
  */
 static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
@@ -3725,9 +3770,18 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
+	spin_lock(&rsp->ofl_lock);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+	rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq);
+	rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags);
+	if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
+		/* Report quiescent state -before- changing ->qsmaskinitnext! */
+		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	}
 	rnp->qsmaskinitnext &= ~mask;
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	spin_unlock(&rsp->ofl_lock);
 }
 
 /*
@@ -3839,12 +3893,16 @@ static int __init rcu_spawn_gp_kthread(void)
 	struct task_struct *t;
 
 	/* Force priority into range. */
-	if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
+	if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2
+	    && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST))
+		kthread_prio = 2;
+	else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
 		kthread_prio = 1;
 	else if (kthread_prio < 0)
 		kthread_prio = 0;
 	else if (kthread_prio > 99)
 		kthread_prio = 99;
+
 	if (kthread_prio != kthread_prio_in)
 		pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n",
 			 kthread_prio, kthread_prio_in);
@@ -3928,8 +3986,9 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 			raw_spin_lock_init(&rnp->fqslock);
 			lockdep_set_class_and_name(&rnp->fqslock,
 						   &rcu_fqs_class[i], fqs[i]);
-			rnp->gpnum = rsp->gpnum;
-			rnp->completed = rsp->completed;
+			rnp->gp_seq = rsp->gp_seq;
+			rnp->gp_seq_needed = rsp->gp_seq;
+			rnp->completedqs = rsp->gp_seq;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
 			rnp->grplo = j * cpustride;
@@ -3997,7 +4056,7 @@ static void __init rcu_init_geometry(void)
 	if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
 		return;
-	pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
+	pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
 		rcu_fanout_leaf, nr_cpu_ids);
 
 	/*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 78e051dffc5b..4e74df768c57 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -81,18 +81,16 @@ struct rcu_node {
 	raw_spinlock_t __private lock;	/* Root rcu_node's lock protects */
 					/*  some rcu_state fields as well as */
 					/*  following. */
-	unsigned long gpnum;	/* Current grace period for this node. */
-				/*  This will either be equal to or one */
-				/*  behind the root rcu_node's gpnum. */
-	unsigned long completed; /* Last GP completed for this node. */
-				/*  This will either be equal to or one */
-				/*  behind the root rcu_node's gpnum. */
+	unsigned long gp_seq;	/* Track rsp->rcu_gp_seq. */
+	unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
+	unsigned long completedqs; /* All QSes done for this node. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
 				/*  order for current grace period to proceed.*/
 				/*  In leaf rcu_node, each bit corresponds to */
 				/*  an rcu_data structure, otherwise, each */
 				/*  bit corresponds to a child rcu_node */
 				/*  structure. */
+	unsigned long rcu_gp_init_mask;	/* Mask of offline CPUs at GP init. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask. */
 				/*  Initialized from ->qsmaskinitnext at the */
@@ -158,7 +156,6 @@ struct rcu_node {
 	struct swait_queue_head nocb_gp_wq[2];
 				/* Place for rcu_nocb_kthread() to wait GP. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-	u8 need_future_gp[4];	/* Counts of upcoming GP requests. */
 	raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
 
 	spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
@@ -168,22 +165,6 @@ struct rcu_node {
 	bool exp_need_flush;	/* Need to flush workitem? */
 } ____cacheline_internodealigned_in_smp;
 
-/* Accessors for ->need_future_gp[] array. */
-#define need_future_gp_mask() \
-	(ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1)
-#define need_future_gp_element(rnp, c) \
-	((rnp)->need_future_gp[(c) & need_future_gp_mask()])
-#define need_any_future_gp(rnp)						\
-({									\
-	int __i;							\
-	bool __nonzero = false;						\
-									\
-	for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++)	\
-		__nonzero = __nonzero ||				\
-			    READ_ONCE((rnp)->need_future_gp[__i]);	\
-	__nonzero;							\
-})
-
 /*
  * Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
  * are indexed relative to this interval rather than the global CPU ID space.
@@ -206,16 +187,14 @@ union rcu_noqs {
 /* Per-CPU data for read-copy update. */
 struct rcu_data {
 	/* 1) quiescent-state and grace-period handling : */
-	unsigned long	completed;	/* Track rsp->completed gp number */
-					/*  in order to detect GP end. */
-	unsigned long	gpnum;		/* Highest gp number that this CPU */
-					/*  is aware of having started. */
+	unsigned long	gp_seq;		/* Track rsp->rcu_gp_seq counter. */
+	unsigned long	gp_seq_needed;	/* Track rsp->rcu_gp_seq_needed ctr. */
 	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
 					/*  for rcu_all_qs() invocations. */
 	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
 	bool		core_needs_qs;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
-	bool		gpwrap;		/* Possible gpnum/completed wrap. */
+	bool		gpwrap;		/* Possible ->gp_seq wrap. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 	unsigned long	ticks_this_gp;	/* The number of scheduling-clock */
@@ -239,7 +218,6 @@ struct rcu_data {
 
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
 	unsigned long dynticks_fqs;	/* Kicked due to dynticks idle. */
-	unsigned long offline_fqs;	/* Kicked due to being offline. */
 	unsigned long cond_resched_completed;
 					/* Grace period that needs help */
 					/*  from cond_resched(). */
@@ -278,12 +256,16 @@ struct rcu_data {
 					/* Leader CPU takes GP-end wakeups. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
-	/* 7) RCU CPU stall data. */
+	/* 7) Diagnostic data, including RCU CPU stall warnings. */
 	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
 	/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
 	struct irq_work rcu_iw;		/* Check for non-irq activity. */
 	bool rcu_iw_pending;		/* Is ->rcu_iw pending? */
-	unsigned long rcu_iw_gpnum;	/* ->gpnum associated with ->rcu_iw. */
+	unsigned long rcu_iw_gp_seq;	/* ->gp_seq associated with ->rcu_iw. */
+	unsigned long rcu_ofl_gp_seq;	/* ->gp_seq at last offline. */
+	short rcu_ofl_gp_flags;		/* ->gp_flags at last offline. */
+	unsigned long rcu_onl_gp_seq;	/* ->gp_seq at last online. */
+	short rcu_onl_gp_flags;		/* ->gp_flags at last online. */
 
 	int cpu;
 	struct rcu_state *rsp;
@@ -340,8 +322,7 @@ struct rcu_state {
 
 	u8	boost ____cacheline_internodealigned_in_smp;
 						/* Subject to priority boost. */
-	unsigned long gpnum;			/* Current gp number. */
-	unsigned long completed;		/* # of last completed gp. */
+	unsigned long gp_seq;			/* Grace-period sequence #. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
 	struct swait_queue_head gp_wq;		/* Where GP task waits. */
 	short gp_flags;				/* Commands for GP task. */
@@ -373,6 +354,8 @@ struct rcu_state {
 						/*  but in jiffies. */
 	unsigned long gp_activity;		/* Time of last GP kthread */
 						/*  activity in jiffies. */
+	unsigned long gp_req_activity;		/* Time of last GP request */
+						/*  in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 	unsigned long jiffies_resched;		/* Time at which to resched */
@@ -384,6 +367,10 @@ struct rcu_state {
 	const char *name;			/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 	struct list_head flavors;		/* List of RCU flavors. */
+
+	spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
+						/* Synchronize offline with */
+						/*  GP pre-initialization. */
 };
 
 /* Values for rcu_state structure's gp_flags field. */
@@ -394,16 +381,20 @@ struct rcu_state {
 #define RCU_GP_IDLE	 0	/* Initial state and no GP in progress. */
 #define RCU_GP_WAIT_GPS  1	/* Wait for grace-period start. */
 #define RCU_GP_DONE_GPS  2	/* Wait done for grace-period start. */
-#define RCU_GP_WAIT_FQS  3	/* Wait for force-quiescent-state time. */
-#define RCU_GP_DOING_FQS 4	/* Wait done for force-quiescent-state time. */
-#define RCU_GP_CLEANUP   5	/* Grace-period cleanup started. */
-#define RCU_GP_CLEANED   6	/* Grace-period cleanup complete. */
+#define RCU_GP_ONOFF     3	/* Grace-period initialization hotplug. */
+#define RCU_GP_INIT      4	/* Grace-period initialization. */
+#define RCU_GP_WAIT_FQS  5	/* Wait for force-quiescent-state time. */
+#define RCU_GP_DOING_FQS 6	/* Wait done for force-quiescent-state time. */
+#define RCU_GP_CLEANUP   7	/* Grace-period cleanup started. */
+#define RCU_GP_CLEANED   8	/* Grace-period cleanup complete. */
 
 #ifndef RCU_TREE_NONCORE
 static const char * const gp_state_names[] = {
 	"RCU_GP_IDLE",
 	"RCU_GP_WAIT_GPS",
 	"RCU_GP_DONE_GPS",
+	"RCU_GP_ONOFF",
+	"RCU_GP_INIT",
 	"RCU_GP_WAIT_FQS",
 	"RCU_GP_DOING_FQS",
 	"RCU_GP_CLEANUP",
@@ -449,10 +440,13 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static int rcu_print_task_stall(struct rcu_node *rnp);
 static int rcu_print_task_exp_stall(struct rcu_node *rnp);
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
+static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp,
+					    struct rcu_node *rnp);
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void __init __rcu_init_preempt(void);
+static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp,
+			    int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static void invoke_rcu_callbacks_kthread(void);
@@ -489,7 +483,6 @@ static void __init rcu_spawn_nocb_kthreads(void);
 #ifdef CONFIG_RCU_NOCB_CPU
 static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
 static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d40708e8c5d6..0b2c2ad69629 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			if (wake) {
 				smp_mb(); /* EGP done before wake_up(). */
-				swake_up(&rsp->expedited_wq);
+				swake_up_one(&rsp->expedited_wq);
 			}
 			break;
 		}
@@ -472,6 +472,7 @@ retry_ipi:
 static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 				     smp_call_func_t func)
 {
+	int cpu;
 	struct rcu_node *rnp;
 
 	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
@@ -486,13 +487,20 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		rnp->rew.rew_func = func;
 		rnp->rew.rew_rsp = rsp;
 		if (!READ_ONCE(rcu_par_gp_wq) ||
-		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
-			/* No workqueues yet. */
+		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
+		    rcu_is_last_leaf_node(rsp, rnp)) {
+			/* No workqueues yet or last leaf, do direct call. */
 			sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
 			continue;
 		}
 		INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
-		queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work);
+		preempt_disable();
+		cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
+		/* If all offline, queue the work on an unbound CPU. */
+		if (unlikely(cpu > rnp->grphi))
+			cpu = WORK_CPU_UNBOUND;
+		queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
+		preempt_enable();
 		rnp->exp_need_flush = true;
 	}
 
@@ -518,7 +526,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	jiffies_start = jiffies;
 
 	for (;;) {
-		ret = swait_event_timeout(
+		ret = swait_event_timeout_exclusive(
 				rsp->expedited_wq,
 				sync_rcu_preempt_exp_done_unlocked(rnp_root),
 				jiffies_stall);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7fd12039e512..a97c20ea9bce 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -74,8 +74,8 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tRCU event tracing is enabled.\n");
 	if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
 	    (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
-		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
-		       RCU_FANOUT);
+		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d.\n",
+			RCU_FANOUT);
 	if (rcu_fanout_exact)
 		pr_info("\tHierarchical RCU autobalancing is disabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
@@ -88,11 +88,13 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
 			RCU_FANOUT_LEAF);
 	if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
-		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
+		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n",
+			rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%u.\n", NR_CPUS, nr_cpu_ids);
 #ifdef CONFIG_RCU_BOOST
-	pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY);
+	pr_info("\tRCU priority boosting: priority %d delay %d ms.\n",
+		kthread_prio, CONFIG_RCU_BOOST_DELAY);
 #endif
 	if (blimit != DEFAULT_RCU_BLIMIT)
 		pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit);
@@ -127,6 +129,7 @@ static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
 
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			       bool wake);
+static void rcu_read_unlock_special(struct task_struct *t);
 
 /*
  * Tell them what RCU they are running.
@@ -183,6 +186,9 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	raw_lockdep_assert_held_rcu_node(rnp);
 	WARN_ON_ONCE(rdp->mynode != rnp);
 	WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
+	/* RCU better not be waiting on newly onlined CPUs! */
+	WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask &
+		     rdp->grpmask);
 
 	/*
 	 * Decide where to queue the newly blocked task.  In theory,
@@ -260,8 +266,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * ->exp_tasks pointers, respectively, to reference the newly
 	 * blocked tasks.
 	 */
-	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD))
+	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) {
 		rnp->gp_tasks = &t->rcu_node_entry;
+		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
+	}
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
 		rnp->exp_tasks = &t->rcu_node_entry;
 	WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
@@ -286,20 +294,24 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 }
 
 /*
- * Record a preemptible-RCU quiescent state for the specified CPU.  Note
- * that this just means that the task currently running on the CPU is
- * not in a quiescent state.  There might be any number of tasks blocked
- * while in an RCU read-side critical section.
+ * Record a preemptible-RCU quiescent state for the specified CPU.
+ * Note that this does not necessarily mean that the task currently running
+ * on the CPU is in a quiescent state:  Instead, it means that the current
+ * grace period need not wait on any RCU read-side critical section that
+ * starts later on this CPU.  It also means that if the current task is
+ * in an RCU read-side critical section, it has already added itself to
+ * some leaf rcu_node structure's ->blkd_tasks list.  In addition to the
+ * current task, there might be any number of other tasks blocked while
+ * in an RCU read-side critical section.
  *
- * As with the other rcu_*_qs() functions, callers to this function
- * must disable preemption.
+ * Callers to this function must disable preemption.
  */
 static void rcu_preempt_qs(void)
 {
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n");
 	if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_preempt"),
-				       __this_cpu_read(rcu_data_p->gpnum),
+				       __this_cpu_read(rcu_data_p->gp_seq),
 				       TPS("cpuqs"));
 		__this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false);
 		barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
@@ -348,8 +360,8 @@ static void rcu_preempt_note_context_switch(bool preempt)
 		trace_rcu_preempt_task(rdp->rsp->name,
 				       t->pid,
 				       (rnp->qsmask & rdp->grpmask)
-				       ? rnp->gpnum
-				       : rnp->gpnum + 1);
+				       ? rnp->gp_seq
+				       : rcu_seq_snap(&rnp->gp_seq));
 		rcu_preempt_ctxt_queue(rnp, rdp);
 	} else if (t->rcu_read_lock_nesting < 0 &&
 		   t->rcu_read_unlock_special.s) {
@@ -456,7 +468,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
  */
-void rcu_read_unlock_special(struct task_struct *t)
+static void rcu_read_unlock_special(struct task_struct *t)
 {
 	bool empty_exp;
 	bool empty_norm;
@@ -535,13 +547,15 @@ void rcu_read_unlock_special(struct task_struct *t)
 		WARN_ON_ONCE(rnp != t->rcu_blocked_node);
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
+		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq &&
+			     (!empty_norm || rnp->qsmask));
 		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
 		np = rcu_next_node_entry(t, rnp);
 		list_del_init(&t->rcu_node_entry);
 		t->rcu_blocked_node = NULL;
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt"),
-						rnp->gpnum, t->pid);
+						rnp->gp_seq, t->pid);
 		if (&t->rcu_node_entry == rnp->gp_tasks)
 			rnp->gp_tasks = np;
 		if (&t->rcu_node_entry == rnp->exp_tasks)
@@ -562,7 +576,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		empty_exp_now = sync_rcu_preempt_exp_done(rnp);
 		if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
 			trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
-							 rnp->gpnum,
+							 rnp->gp_seq,
 							 0, rnp->qsmask,
 							 rnp->level,
 							 rnp->grplo,
@@ -686,24 +700,27 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * Check that the list of blocked tasks for the newly completed grace
  * period is in fact empty.  It is a serious bug to complete a grace
  * period that still has RCU readers blocked!  This function must be
- * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
+ * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock
  * must be held by the caller.
  *
  * Also, if there are blocked tasks on the list, they automatically
  * block the newly created grace period, so set up ->gp_tasks accordingly.
  */
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	struct task_struct *t;
 
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
-	WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
-	if (rcu_preempt_has_tasks(rnp)) {
+	if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+		dump_blkd_tasks(rsp, rnp, 10);
+	if (rcu_preempt_has_tasks(rnp) &&
+	    (rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
 		rnp->gp_tasks = rnp->blkd_tasks.next;
 		t = container_of(rnp->gp_tasks, struct task_struct,
 				 rcu_node_entry);
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"),
-						rnp->gpnum, t->pid);
+						rnp->gp_seq, t->pid);
 	}
 	WARN_ON_ONCE(rnp->qsmask);
 }
@@ -717,6 +734,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
  */
 static void rcu_preempt_check_callbacks(void)
 {
+	struct rcu_state *rsp = &rcu_preempt_state;
 	struct task_struct *t = current;
 
 	if (t->rcu_read_lock_nesting == 0) {
@@ -725,7 +743,9 @@ static void rcu_preempt_check_callbacks(void)
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
 	    __this_cpu_read(rcu_data_p->core_needs_qs) &&
-	    __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm))
+	    __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm) &&
+	    !t->rcu_read_unlock_special.b.need_qs &&
+	    time_after(jiffies, rsp->gp_start + HZ))
 		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
@@ -841,6 +861,47 @@ void exit_rcu(void)
 	__rcu_read_unlock();
 }
 
+/*
+ * Dump the blocked-tasks state, but limit the list dump to the
+ * specified number of elements.
+ */
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
+{
+	int cpu;
+	int i;
+	struct list_head *lhp;
+	bool onl;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp1;
+
+	raw_lockdep_assert_held_rcu_node(rnp);
+	pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+		__func__, rnp->grplo, rnp->grphi, rnp->level,
+		(long)rnp->gp_seq, (long)rnp->completedqs);
+	for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+		pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
+			__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
+	pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
+		__func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks);
+	pr_info("%s: ->blkd_tasks", __func__);
+	i = 0;
+	list_for_each(lhp, &rnp->blkd_tasks) {
+		pr_cont(" %p", lhp);
+		if (++i >= 10)
+			break;
+	}
+	pr_cont("\n");
+	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+		pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n",
+			cpu, ".o"[onl],
+			(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+			(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+	}
+}
+
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
 static struct rcu_state *const rcu_state_p = &rcu_sched_state;
@@ -911,7 +972,8 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * so there is no need to check for blocked tasks.  So check only for
  * bogus qsmask values.
  */
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	WARN_ON_ONCE(rnp->qsmask);
 }
@@ -949,6 +1011,15 @@ void exit_rcu(void)
 {
 }
 
+/*
+ * Dump the guaranteed-empty blocked-tasks state.  Trust but verify.
+ */
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
+{
+	WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks));
+}
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST
@@ -1433,7 +1504,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
 		 * completed since we last checked and there are
 		 * callbacks not yet ready to invoke.
 		 */
-		if ((rdp->completed != rnp->completed ||
+		if ((rcu_seq_completed_gp(rdp->gp_seq,
+					  rcu_seq_current(&rnp->gp_seq)) ||
 		     unlikely(READ_ONCE(rdp->gpwrap))) &&
 		    rcu_segcblist_pend_cbs(&rdp->cblist))
 			note_gp_changes(rsp, rdp);
@@ -1720,16 +1792,16 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 	 */
 	touch_nmi_watchdog();
 
-	if (rsp->gpnum == rdp->gpnum) {
+	ticks_value = rcu_seq_ctr(rsp->gp_seq - rdp->gp_seq);
+	if (ticks_value) {
+		ticks_title = "GPs behind";
+	} else {
 		ticks_title = "ticks this GP";
 		ticks_value = rdp->ticks_this_gp;
-	} else {
-		ticks_title = "GPs behind";
-		ticks_value = rsp->gpnum - rdp->gpnum;
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
-	delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum;
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%ld softirq=%u/%u fqs=%ld %s\n",
+	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -1817,7 +1889,7 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
 
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
 {
-	return &rnp->nocb_gp_wq[rnp->completed & 0x1];
+	return &rnp->nocb_gp_wq[rcu_seq_ctr(rnp->gp_seq) & 0x1];
 }
 
 static void rcu_init_one_nocb(struct rcu_node *rnp)
@@ -1854,8 +1926,8 @@ static void __wake_nocb_leader(struct rcu_data *rdp, bool force,
 		WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
 		del_timer(&rdp->nocb_timer);
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
-		smp_mb(); /* ->nocb_leader_sleep before swake_up(). */
-		swake_up(&rdp_leader->nocb_wq);
+		smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */
+		swake_up_one(&rdp_leader->nocb_wq);
 	} else {
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 	}
@@ -2069,12 +2141,17 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	bool needwake;
 	struct rcu_node *rnp = rdp->mynode;
 
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	c = rcu_cbs_completed(rdp->rsp, rnp);
-	needwake = rcu_start_this_gp(rnp, rdp, c);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	if (needwake)
-		rcu_gp_kthread_wake(rdp->rsp);
+	local_irq_save(flags);
+	c = rcu_seq_snap(&rdp->rsp->gp_seq);
+	if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+		local_irq_restore(flags);
+	} else {
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+		needwake = rcu_start_this_gp(rnp, rdp, c);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		if (needwake)
+			rcu_gp_kthread_wake(rdp->rsp);
+	}
 
 	/*
 	 * Wait for the grace period.  Do so interruptibly to avoid messing
@@ -2082,9 +2159,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	 */
 	trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
 	for (;;) {
-		swait_event_interruptible(
-			rnp->nocb_gp_wq[c & 0x1],
-			(d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
+		swait_event_interruptible_exclusive(
+			rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1],
+			(d = rcu_seq_done(&rnp->gp_seq, c)));
 		if (likely(d))
 			break;
 		WARN_ON(signal_pending(current));
@@ -2111,7 +2188,7 @@ wait_again:
 	/* Wait for callbacks to appear. */
 	if (!rcu_nocb_poll) {
 		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep"));
-		swait_event_interruptible(my_rdp->nocb_wq,
+		swait_event_interruptible_exclusive(my_rdp->nocb_wq,
 				!READ_ONCE(my_rdp->nocb_leader_sleep));
 		raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags);
 		my_rdp->nocb_leader_sleep = true;
@@ -2176,7 +2253,7 @@ wait_again:
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 		if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
 			/* List was empty, so wake up the follower.  */
-			swake_up(&rdp->nocb_wq);
+			swake_up_one(&rdp->nocb_wq);
 		}
 	}
 
@@ -2193,7 +2270,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
 {
 	for (;;) {
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep"));
-		swait_event_interruptible(rdp->nocb_wq,
+		swait_event_interruptible_exclusive(rdp->nocb_wq,
 					 READ_ONCE(rdp->nocb_follower_head));
 		if (smp_load_acquire(&rdp->nocb_follower_head)) {
 			/* ^^^ Ensure CB invocation follows _head test. */
@@ -2569,23 +2646,6 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
 /*
- * An adaptive-ticks CPU can potentially execute in kernel mode for an
- * arbitrarily long period of time with the scheduling-clock tick turned
- * off.  RCU will be paying attention to this CPU because it is in the
- * kernel, but the CPU cannot be guaranteed to be executing the RCU state
- * machine because the scheduling-clock tick has been disabled.  Therefore,
- * if an adaptive-ticks CPU is failing to respond to the current grace
- * period and has not be idle from an RCU perspective, kick it.
- */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
-{
-#ifdef CONFIG_NO_HZ_FULL
-	if (tick_nohz_full_cpu(cpu))
-		smp_send_reschedule(cpu);
-#endif /* #ifdef CONFIG_NO_HZ_FULL */
-}
-
-/*
  * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
  * grace-period kthread will do force_quiescent_state() processing?
  * The idea is to avoid waking up RCU core processing on such a
@@ -2610,8 +2670,6 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
  */
 static void rcu_bind_gp_kthread(void)
 {
-	int __maybe_unused cpu;
-
 	if (!tick_nohz_full_enabled())
 		return;
 	housekeeping_affine(current, HK_FLAG_RCU);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4c230a60ece4..39cb23d22109 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -507,14 +507,15 @@ early_initcall(check_cpu_stall_init);
 #ifdef CONFIG_TASKS_RCU
 
 /*
- * Simple variant of RCU whose quiescent states are voluntary context switch,
- * user-space execution, and idle.  As such, grace periods can take one good
- * long time.  There are no read-side primitives similar to rcu_read_lock()
- * and rcu_read_unlock() because this implementation is intended to get
- * the system into a safe state for some of the manipulations involved in
- * tracing and the like.  Finally, this implementation does not support
- * high call_rcu_tasks() rates from multiple CPUs.  If this is required,
- * per-CPU callback lists will be needed.
+ * Simple variant of RCU whose quiescent states are voluntary context
+ * switch, cond_resched_rcu_qs(), user-space execution, and idle.
+ * As such, grace periods can take one good long time.  There are no
+ * read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
+ * because this implementation is intended to get the system into a safe
+ * state for some of the manipulations involved in tracing and the like.
+ * Finally, this implementation does not support high call_rcu_tasks()
+ * rates from multiple CPUs.  If this is required, per-CPU callback lists
+ * will be needed.
  */
 
 /* Global list of callbacks and associated lock. */
@@ -542,11 +543,11 @@ static struct task_struct *rcu_tasks_kthread_ptr;
  * period elapses, in other words after all currently executing RCU
  * read-side critical sections have completed. call_rcu_tasks() assumes
  * that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), entry into idle, or transition to usermode
- * execution.  As such, there are no read-side primitives analogous to
- * rcu_read_lock() and rcu_read_unlock() because this primitive is intended
- * to determine that all tasks have passed through a safe state, not so
- * much for data-strcuture synchronization.
+ * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * or transition to usermode execution.  As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-strcuture synchronization.
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
@@ -667,6 +668,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	struct rcu_head *list;
 	struct rcu_head *next;
 	LIST_HEAD(rcu_tasks_holdouts);
+	int fract;
 
 	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
 	housekeeping_affine(current, HK_FLAG_RCU);
@@ -748,13 +750,25 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		 * holdouts.  When the list is empty, we are done.
 		 */
 		lastreport = jiffies;
-		while (!list_empty(&rcu_tasks_holdouts)) {
+
+		/* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
+		fract = 10;
+
+		for (;;) {
 			bool firstreport;
 			bool needreport;
 			int rtst;
 			struct task_struct *t1;
 
-			schedule_timeout_interruptible(HZ);
+			if (list_empty(&rcu_tasks_holdouts))
+				break;
+
+			/* Slowly back off waiting for holdouts */
+			schedule_timeout_interruptible(HZ/fract);
+
+			if (fract > 1)
+				fract--;
+
 			rtst = READ_ONCE(rcu_task_stall_timeout);
 			needreport = rtst > 0 &&
 				     time_after(jiffies, lastreport + rtst);
@@ -800,6 +814,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 			list = next;
 			cond_resched();
 		}
+		/* Paranoid sleep to keep this from entering a tight loop */
 		schedule_timeout_uninterruptible(HZ/10);
 	}
 }
diff --git a/kernel/reboot.c b/kernel/reboot.c
index e4ced883d8de..8fb44dec9ad7 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -294,7 +294,7 @@ void kernel_power_off(void)
 }
 EXPORT_SYMBOL_GPL(kernel_power_off);
 
-static DEFINE_MUTEX(reboot_mutex);
+DEFINE_MUTEX(system_transition_mutex);
 
 /*
  * Reboot system call: for obvious reasons only root may call it,
@@ -338,7 +338,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
 		cmd = LINUX_REBOOT_CMD_HALT;
 
-	mutex_lock(&reboot_mutex);
+	mutex_lock(&system_transition_mutex);
 	switch (cmd) {
 	case LINUX_REBOOT_CMD_RESTART:
 		kernel_restart(NULL);
@@ -389,7 +389,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 		ret = -EINVAL;
 		break;
 	}
-	mutex_unlock(&reboot_mutex);
+	mutex_unlock(&system_transition_mutex);
 	return ret;
 }
 
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 22b6acf1ad63..c6242d8594dc 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -85,9 +85,9 @@ static int rseq_update_cpu_id(struct task_struct *t)
 {
 	u32 cpu_id = raw_smp_processor_id();
 
-	if (__put_user(cpu_id, &t->rseq->cpu_id_start))
+	if (put_user(cpu_id, &t->rseq->cpu_id_start))
 		return -EFAULT;
-	if (__put_user(cpu_id, &t->rseq->cpu_id))
+	if (put_user(cpu_id, &t->rseq->cpu_id))
 		return -EFAULT;
 	trace_rseq_update(t);
 	return 0;
@@ -100,14 +100,14 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
 	/*
 	 * Reset cpu_id_start to its initial state (0).
 	 */
-	if (__put_user(cpu_id_start, &t->rseq->cpu_id_start))
+	if (put_user(cpu_id_start, &t->rseq->cpu_id_start))
 		return -EFAULT;
 	/*
 	 * Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
 	 * in after unregistration can figure out that rseq needs to be
 	 * registered again.
 	 */
-	if (__put_user(cpu_id, &t->rseq->cpu_id))
+	if (put_user(cpu_id, &t->rseq->cpu_id))
 		return -EFAULT;
 	return 0;
 }
@@ -115,29 +115,36 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
 static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 {
 	struct rseq_cs __user *urseq_cs;
-	unsigned long ptr;
+	u64 ptr;
 	u32 __user *usig;
 	u32 sig;
 	int ret;
 
-	ret = __get_user(ptr, &t->rseq->rseq_cs);
-	if (ret)
-		return ret;
+	if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
+		return -EFAULT;
 	if (!ptr) {
 		memset(rseq_cs, 0, sizeof(*rseq_cs));
 		return 0;
 	}
-	urseq_cs = (struct rseq_cs __user *)ptr;
+	if (ptr >= TASK_SIZE)
+		return -EINVAL;
+	urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr;
 	if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs)))
 		return -EFAULT;
-	if (rseq_cs->version > 0)
-		return -EINVAL;
 
+	if (rseq_cs->start_ip >= TASK_SIZE ||
+	    rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE ||
+	    rseq_cs->abort_ip >= TASK_SIZE ||
+	    rseq_cs->version > 0)
+		return -EINVAL;
+	/* Check for overflow. */
+	if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip)
+		return -EINVAL;
 	/* Ensure that abort_ip is not in the critical section. */
 	if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset)
 		return -EINVAL;
 
-	usig = (u32 __user *)(rseq_cs->abort_ip - sizeof(u32));
+	usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32));
 	ret = get_user(sig, usig);
 	if (ret)
 		return ret;
@@ -146,7 +153,7 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 		printk_ratelimited(KERN_WARNING
 			"Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n",
 			sig, current->rseq_sig, current->pid, usig);
-		return -EPERM;
+		return -EINVAL;
 	}
 	return 0;
 }
@@ -157,7 +164,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 	int ret;
 
 	/* Get thread flags. */
-	ret = __get_user(flags, &t->rseq->flags);
+	ret = get_user(flags, &t->rseq->flags);
 	if (ret)
 		return ret;
 
@@ -195,9 +202,11 @@ static int clear_rseq_cs(struct task_struct *t)
 	 * of code outside of the rseq assembly block. This performs
 	 * a lazy clear of the rseq_cs field.
 	 *
-	 * Set rseq_cs to NULL with single-copy atomicity.
+	 * Set rseq_cs to NULL.
 	 */
-	return __put_user(0UL, &t->rseq->rseq_cs);
+	if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
+		return -EFAULT;
+	return 0;
 }
 
 /*
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index d9a02b318108..7fe183404c38 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -20,7 +20,7 @@ obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle.o fair.o rt.o deadline.o
 obj-y += wait.o wait_bit.o swait.o completion.o
 
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 10c83e73837a..e3e3b979f9bd 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -53,6 +53,7 @@
  *
  */
 #include "sched.h"
+#include <linux/sched_clock.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -66,12 +67,7 @@ unsigned long long __weak sched_clock(void)
 }
 EXPORT_SYMBOL_GPL(sched_clock);
 
-__read_mostly int sched_clock_running;
-
-void sched_clock_init(void)
-{
-	sched_clock_running = 1;
-}
+static DEFINE_STATIC_KEY_FALSE(sched_clock_running);
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 /*
@@ -195,17 +191,40 @@ void clear_sched_clock_stable(void)
 
 	smp_mb(); /* matches sched_clock_init_late() */
 
-	if (sched_clock_running == 2)
+	if (static_key_count(&sched_clock_running.key) == 2)
 		__clear_sched_clock_stable();
 }
 
+static void __sched_clock_gtod_offset(void)
+{
+	struct sched_clock_data *scd = this_scd();
+
+	__scd_stamp(scd);
+	__gtod_offset = (scd->tick_raw + __sched_clock_offset) - scd->tick_gtod;
+}
+
+void __init sched_clock_init(void)
+{
+	/*
+	 * Set __gtod_offset such that once we mark sched_clock_running,
+	 * sched_clock_tick() continues where sched_clock() left off.
+	 *
+	 * Even if TSC is buggered, we're still UP at this point so it
+	 * can't really be out of sync.
+	 */
+	local_irq_disable();
+	__sched_clock_gtod_offset();
+	local_irq_enable();
+
+	static_branch_inc(&sched_clock_running);
+}
 /*
  * We run this as late_initcall() such that it runs after all built-in drivers,
  * notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
  */
 static int __init sched_clock_init_late(void)
 {
-	sched_clock_running = 2;
+	static_branch_inc(&sched_clock_running);
 	/*
 	 * Ensure that it is impossible to not do a static_key update.
 	 *
@@ -350,8 +369,8 @@ u64 sched_clock_cpu(int cpu)
 	if (sched_clock_stable())
 		return sched_clock() + __sched_clock_offset;
 
-	if (unlikely(!sched_clock_running))
-		return 0ull;
+	if (!static_branch_unlikely(&sched_clock_running))
+		return sched_clock();
 
 	preempt_disable_notrace();
 	scd = cpu_sdc(cpu);
@@ -373,7 +392,7 @@ void sched_clock_tick(void)
 	if (sched_clock_stable())
 		return;
 
-	if (unlikely(!sched_clock_running))
+	if (!static_branch_unlikely(&sched_clock_running))
 		return;
 
 	lockdep_assert_irqs_disabled();
@@ -385,8 +404,6 @@ void sched_clock_tick(void)
 
 void sched_clock_tick_stable(void)
 {
-	u64 gtod, clock;
-
 	if (!sched_clock_stable())
 		return;
 
@@ -398,9 +415,7 @@ void sched_clock_tick_stable(void)
 	 * TSC to be unstable, any computation will be computing crap.
 	 */
 	local_irq_disable();
-	gtod = ktime_get_ns();
-	clock = sched_clock();
-	__gtod_offset = (clock + __sched_clock_offset) - gtod;
+	__sched_clock_gtod_offset();
 	local_irq_enable();
 }
 
@@ -434,9 +449,17 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
+void __init sched_clock_init(void)
+{
+	static_branch_inc(&sched_clock_running);
+	local_irq_disable();
+	generic_sched_clock_init();
+	local_irq_enable();
+}
+
 u64 sched_clock_cpu(int cpu)
 {
-	if (unlikely(!sched_clock_running))
+	if (!static_branch_unlikely(&sched_clock_running))
 		return 0;
 
 	return sched_clock();
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index e426b0cb9ac6..a1ad5b7d5521 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -22,8 +22,8 @@
  *
  * See also complete_all(), wait_for_completion() and related routines.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void complete(struct completion *x)
 {
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete);
  *
  * This will wake up all threads waiting on this particular completion event.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  *
  * Since complete_all() sets the completion of @x permanently to done
  * to allow multiple waiters to finish, a call to reinit_completion()
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78d8facba456..454adf9f8180 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7,7 +7,6 @@
  */
 #include "sched.h"
 
-#include <linux/kthread.h>
 #include <linux/nospec.h>
 
 #include <linux/kcov.h>
@@ -18,6 +17,8 @@
 #include "../workqueue_internal.h"
 #include "../smpboot.h"
 
+#include "pelt.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
@@ -46,14 +47,6 @@ const_debug unsigned int sysctl_sched_features =
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
 /*
- * period over which we average the RT time consumption, measured
- * in ms.
- *
- * default: 1s
- */
-const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
-
-/*
  * period over which we measure -rt task CPU usage in us.
  * default: 1s
  */
@@ -184,9 +177,9 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->clock_task += delta;
 
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef HAVE_SCHED_AVG_IRQ
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
-		sched_rt_avg_update(rq, irq_delta + steal);
+		update_irq_load_avg(rq, irq_delta + steal);
 #endif
 }
 
@@ -413,8 +406,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * its already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
-	 * This cmpxchg() implies a full barrier, which pairs with the write
-	 * barrier implied by the wakeup in wake_up_q().
+	 * This cmpxchg() executes a full barrier, which pairs with the full
+	 * barrier executed by the wakeup in wake_up_q().
 	 */
 	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
 		return;
@@ -442,8 +435,8 @@ void wake_up_q(struct wake_q_head *head)
 		task->wake_q.next = NULL;
 
 		/*
-		 * wake_up_process() implies a wmb() to pair with the queueing
-		 * in wake_q_add() so as not to miss wakeups.
+		 * wake_up_process() executes a full barrier, which pairs with
+		 * the queueing in wake_q_add() so as not to miss wakeups.
 		 */
 		wake_up_process(task);
 		put_task_struct(task);
@@ -650,23 +643,6 @@ bool sched_can_stop_tick(struct rq *rq)
 	return true;
 }
 #endif /* CONFIG_NO_HZ_FULL */
-
-void sched_avg_update(struct rq *rq)
-{
-	s64 period = sched_avg_period();
-
-	while ((s64)(rq_clock(rq) - rq->age_stamp) > period) {
-		/*
-		 * Inline assembly required to prevent the compiler
-		 * optimising this loop into a divmod call.
-		 * See __iter_div_u64_rem() for another example of this.
-		 */
-		asm("" : "+rm" (rq->age_stamp));
-		rq->age_stamp += period;
-		rq->rt_avg /= 2;
-	}
-}
-
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
@@ -1200,6 +1176,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
 	if (task_on_rq_queued(p)) {
@@ -1281,16 +1258,17 @@ unlock:
 /*
  * Cross migrate two tasks
  */
-int migrate_swap(struct task_struct *cur, struct task_struct *p)
+int migrate_swap(struct task_struct *cur, struct task_struct *p,
+		int target_cpu, int curr_cpu)
 {
 	struct migration_swap_arg arg;
 	int ret = -EINVAL;
 
 	arg = (struct migration_swap_arg){
 		.src_task = cur,
-		.src_cpu = task_cpu(cur),
+		.src_cpu = curr_cpu,
 		.dst_task = p,
-		.dst_cpu = task_cpu(p),
+		.dst_cpu = target_cpu,
 	};
 
 	if (arg.src_cpu == arg.dst_cpu)
@@ -1315,6 +1293,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
 out:
 	return ret;
 }
+#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * wait_task_inactive - wait for a thread to unschedule.
@@ -1880,8 +1859,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *     rq(c1)->lock (if not at the same time, then in that order).
  *  C) LOCK of the rq(c1)->lock scheduling in task
  *
- * Transitivity guarantees that B happens after A and C after B.
- * Note: we only require RCpc transitivity.
+ * Release/acquire chaining guarantees that B happens after A and C after B.
  * Note: the CPU doing B need not be c0 or c1
  *
  * Example:
@@ -1943,16 +1921,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *   UNLOCK rq(0)->lock
  *
  *
- * However; for wakeups there is a second guarantee we must provide, namely we
- * must observe the state that lead to our wakeup. That is, not only must our
- * task observe its own prior state, it must also observe the stores prior to
- * its wakeup.
- *
- * This means that any means of doing remote wakeups must order the CPU doing
- * the wakeup against the CPU the task is going to end up running on. This,
- * however, is already required for the regular Program-Order guarantee above,
- * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
- *
+ * However, for wakeups there is a second guarantee we must provide, namely we
+ * must ensure that CONDITION=1 done by the caller can not be reordered with
+ * accesses to the task state; see try_to_wake_up() and set_current_state().
  */
 
 /**
@@ -1968,6 +1939,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * Atomic against schedule() which would dequeue a task, also see
  * set_current_state().
  *
+ * This function executes a full memory barrier before accessing the task
+ * state; see set_current_state().
+ *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
  */
@@ -1999,21 +1973,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
 	 * in smp_cond_load_acquire() below.
 	 *
-	 * sched_ttwu_pending()                 try_to_wake_up()
-	 *   [S] p->on_rq = 1;                  [L] P->state
-	 *       UNLOCK rq->lock  -----.
-	 *                              \
-	 *				 +---   RMB
-	 * schedule()                   /
-	 *       LOCK rq->lock    -----'
-	 *       UNLOCK rq->lock
+	 * sched_ttwu_pending()			try_to_wake_up()
+	 *   STORE p->on_rq = 1			  LOAD p->state
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   UNLOCK rq->lock
 	 *
 	 * [task p]
-	 *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+	 *   STORE p->state = UNINTERRUPTIBLE	  LOAD p->on_rq
 	 *
-	 * Pairs with the UNLOCK+LOCK on rq->lock from the
-	 * last wakeup of our task and the schedule that got our task
-	 * current.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
@@ -2027,15 +2000,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * One must be running (->on_cpu == 1) in order to remove oneself
 	 * from the runqueue.
 	 *
-	 *  [S] ->on_cpu = 1;	[L] ->on_rq
-	 *      UNLOCK rq->lock
-	 *			RMB
-	 *      LOCK   rq->lock
-	 *  [S] ->on_rq = 0;    [L] ->on_cpu
+	 * __schedule() (switch to task 'p')	try_to_wake_up()
+	 *   STORE p->on_cpu = 1		  LOAD p->on_rq
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (put 'p' to sleep)
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   STORE p->on_rq = 0			  LOAD p->on_cpu
 	 *
-	 * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
-	 * from the consecutive calls to schedule(); the first switching to our
-	 * task, the second putting it to sleep.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 
@@ -2141,8 +2116,7 @@ out:
  *
  * Return: 1 if the process was woken up, 0 if it was already running.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * This function executes a full memory barrier before accessing the task state.
  */
 int wake_up_process(struct task_struct *p)
 {
@@ -2318,7 +2292,6 @@ static inline void init_schedstats(void) {}
 int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
-	int cpu = get_cpu();
 
 	__sched_fork(clone_flags, p);
 	/*
@@ -2354,14 +2327,12 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->sched_reset_on_fork = 0;
 	}
 
-	if (dl_prio(p->prio)) {
-		put_cpu();
+	if (dl_prio(p->prio))
 		return -EAGAIN;
-	} else if (rt_prio(p->prio)) {
+	else if (rt_prio(p->prio))
 		p->sched_class = &rt_sched_class;
-	} else {
+	else
 		p->sched_class = &fair_sched_class;
-	}
 
 	init_entity_runnable_average(&p->se);
 
@@ -2377,7 +2348,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
 	 */
-	__set_task_cpu(p, cpu);
+	__set_task_cpu(p, smp_processor_id());
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
@@ -2394,8 +2365,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 	RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
-
-	put_cpu();
 	return 0;
 }
 
@@ -2724,28 +2693,20 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 		membarrier_mm_sync_core_before_usermode(mm);
 		mmdrop(mm);
 	}
-	if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
-		switch (prev_state) {
-		case TASK_DEAD:
-			if (prev->sched_class->task_dead)
-				prev->sched_class->task_dead(prev);
+	if (unlikely(prev_state == TASK_DEAD)) {
+		if (prev->sched_class->task_dead)
+			prev->sched_class->task_dead(prev);
 
-			/*
-			 * Remove function-return probe instances associated with this
-			 * task and put them back on the free list.
-			 */
-			kprobe_flush_task(prev);
+		/*
+		 * Remove function-return probe instances associated with this
+		 * task and put them back on the free list.
+		 */
+		kprobe_flush_task(prev);
 
-			/* Task is done with its stack. */
-			put_task_stack(prev);
+		/* Task is done with its stack. */
+		put_task_stack(prev);
 
-			put_task_struct(prev);
-			break;
-
-		case TASK_PARKED:
-			kthread_park_complete(prev);
-			break;
-		}
+		put_task_struct(prev);
 	}
 
 	tick_nohz_task_switch();
@@ -3113,7 +3074,9 @@ static void sched_tick_remote(struct work_struct *work)
 	struct tick_work *twork = container_of(dwork, struct tick_work, work);
 	int cpu = twork->cpu;
 	struct rq *rq = cpu_rq(cpu);
+	struct task_struct *curr;
 	struct rq_flags rf;
+	u64 delta;
 
 	/*
 	 * Handle the tick only if it appears the remote CPU is running in full
@@ -3122,25 +3085,29 @@ static void sched_tick_remote(struct work_struct *work)
 	 * statistics and checks timeslices in a time-independent way, regardless
 	 * of when exactly it is running.
 	 */
-	if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) {
-		struct task_struct *curr;
-		u64 delta;
+	if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+		goto out_requeue;
 
-		rq_lock_irq(rq, &rf);
-		update_rq_clock(rq);
-		curr = rq->curr;
-		delta = rq_clock_task(rq) - curr->se.exec_start;
+	rq_lock_irq(rq, &rf);
+	curr = rq->curr;
+	if (is_idle_task(curr))
+		goto out_unlock;
 
-		/*
-		 * Make sure the next tick runs within a reasonable
-		 * amount of time.
-		 */
-		WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
-		curr->sched_class->task_tick(rq, curr, 0);
-		rq_unlock_irq(rq, &rf);
-	}
+	update_rq_clock(rq);
+	delta = rq_clock_task(rq) - curr->se.exec_start;
 
 	/*
+	 * Make sure the next tick runs within a reasonable
+	 * amount of time.
+	 */
+	WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	curr->sched_class->task_tick(rq, curr, 0);
+
+out_unlock:
+	rq_unlock_irq(rq, &rf);
+
+out_requeue:
+	/*
 	 * Run the remote tick once per second (1Hz). This arbitrary
 	 * frequency is large enough to avoid overload but short enough
 	 * to keep scheduler internal stats reasonably up to date.
@@ -5717,13 +5684,6 @@ void set_rq_offline(struct rq *rq)
 	}
 }
 
-static void set_cpu_rq_start_time(unsigned int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-
-	rq->age_stamp = sched_clock_cpu(cpu);
-}
-
 /*
  * used to mark begin/end of suspend/resume:
  */
@@ -5777,6 +5737,18 @@ int sched_cpu_activate(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
+#ifdef CONFIG_SCHED_SMT
+	/*
+	 * The sched_smt_present static key needs to be evaluated on every
+	 * hotplug event because at boot time SMT might be disabled when
+	 * the number of booted CPUs is limited.
+	 *
+	 * If then later a sibling gets hotplugged, then the key would stay
+	 * off and SMT scheduling would never be functional.
+	 */
+	if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
+		static_branch_enable_cpuslocked(&sched_smt_present);
+#endif
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {
@@ -5841,7 +5813,6 @@ static void sched_rq_cpu_starting(unsigned int cpu)
 
 int sched_cpu_starting(unsigned int cpu)
 {
-	set_cpu_rq_start_time(cpu);
 	sched_rq_cpu_starting(cpu);
 	sched_tick_start(cpu);
 	return 0;
@@ -5874,22 +5845,6 @@ int sched_cpu_dying(unsigned int cpu)
 }
 #endif
 
-#ifdef CONFIG_SCHED_SMT
-DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-
-static void sched_init_smt(void)
-{
-	/*
-	 * We've enumerated all CPUs and will assume that if any CPU
-	 * has SMT siblings, CPU0 will too.
-	 */
-	if (cpumask_weight(cpu_smt_mask(0)) > 1)
-		static_branch_enable(&sched_smt_present);
-}
-#else
-static inline void sched_init_smt(void) { }
-#endif
-
 void __init sched_init_smp(void)
 {
 	sched_init_numa();
@@ -5911,8 +5866,6 @@ void __init sched_init_smp(void)
 	init_sched_rt_class();
 	init_sched_dl_class();
 
-	sched_init_smt();
-
 	sched_smp_initialized = true;
 }
 
@@ -5957,7 +5910,6 @@ void __init sched_init(void)
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
-	sched_clock_init();
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6109,7 +6061,6 @@ void __init sched_init(void)
 
 #ifdef CONFIG_SMP
 	idle_thread_set_boot_cpu();
-	set_cpu_rq_start_time(smp_processor_id());
 #endif
 	init_sched_fair_class();
 
@@ -6788,6 +6739,16 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
 	seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
 	seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
 
+	if (schedstat_enabled() && tg != &root_task_group) {
+		u64 ws = 0;
+		int i;
+
+		for_each_possible_cpu(i)
+			ws += schedstat_val(tg->se[i]->statistics.wait_sum);
+
+		seq_printf(sf, "wait_sum %llu\n", ws);
+	}
+
 	return 0;
 }
 #endif /* CONFIG_CFS_BANDWIDTH */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3cde46483f0a..3fffad3bc8a8 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -53,9 +53,7 @@ struct sugov_cpu {
 	unsigned int		iowait_boost_max;
 	u64			last_update;
 
-	/* The fields below are only needed when sharing a policy: */
-	unsigned long		util_cfs;
-	unsigned long		util_dl;
+	unsigned long		bw_dl;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -179,33 +177,90 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
-static void sugov_get_util(struct sugov_cpu *sg_cpu)
+/*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ *   cpu_util_{cfs,rt,dl,irq}()
+ *   cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the irq utilization.
+ *
+ * The DL bandwidth number otoh is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long util, irq, max;
 
-	sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
-	sg_cpu->util_cfs = cpu_util_cfs(rq);
-	sg_cpu->util_dl  = cpu_util_dl(rq);
-}
+	sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+	sg_cpu->bw_dl = cpu_bw_dl(rq);
 
-static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
-{
-	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	if (rt_rq_is_runnable(&rq->rt))
+		return max;
 
-	if (rq->rt.rt_nr_running)
-		return sg_cpu->max;
+	/*
+	 * Early check to see if IRQ/steal time saturates the CPU, can be
+	 * because of inaccuracies in how we track these -- see
+	 * update_irq_load_avg().
+	 */
+	irq = cpu_util_irq(rq);
+	if (unlikely(irq >= max))
+		return max;
+
+	/*
+	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
+	 * CFS tasks and we use the same metric to track the effective
+	 * utilization (PELT windows are synchronized) we can directly add them
+	 * to obtain the CPU's actual utilization.
+	 */
+	util = cpu_util_cfs(rq);
+	util += cpu_util_rt(rq);
+
+	/*
+	 * We do not make cpu_util_dl() a permanent part of this sum because we
+	 * want to use cpu_bw_dl() later on, but we need to check if the
+	 * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
+	 * f_max when there is no idle time.
+	 *
+	 * NOTE: numerical errors or stop class might cause us to not quite hit
+	 * saturation when we should -- something for later.
+	 */
+	if ((util + cpu_util_dl(rq)) >= max)
+		return max;
+
+	/*
+	 * There is still idle time; further improve the number by using the
+	 * irq metric. Because IRQ/steal time is hidden from the task clock we
+	 * need to scale the task numbers:
+	 *
+	 *              1 - irq
+	 *   U' = irq + ------- * U
+	 *                max
+	 */
+	util = scale_irq_capacity(util, irq, max);
+	util += irq;
 
 	/*
-	 * Utilization required by DEADLINE must always be granted while, for
-	 * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
-	 * gracefully reduce the frequency when no tasks show up for longer
+	 * Bandwidth required by DEADLINE must always be granted while, for
+	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
+	 * to gracefully reduce the frequency when no tasks show up for longer
 	 * periods of time.
 	 *
-	 * Ideally we would like to set util_dl as min/guaranteed freq and
-	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
-	 * ready for such an interface. So, we only do the latter for now.
+	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
+	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
+	 * an interface. So, we only do the latter for now.
 	 */
-	return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
+	return min(max, util + sg_cpu->bw_dl);
 }
 
 /**
@@ -360,7 +415,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
  */
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
 {
-	if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl)
+	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
 		sg_policy->need_freq_update = true;
 }
 
@@ -383,9 +438,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 
 	busy = sugov_cpu_is_busy(sg_cpu);
 
-	sugov_get_util(sg_cpu);
+	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
-	util = sugov_aggregate_util(sg_cpu);
 	sugov_iowait_apply(sg_cpu, time, &util, &max);
 	next_f = get_next_freq(sg_policy, util, max);
 	/*
@@ -424,9 +478,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
 		unsigned long j_util, j_max;
 
-		sugov_get_util(j_sg_cpu);
+		j_util = sugov_get_util(j_sg_cpu);
 		j_max = j_sg_cpu->max;
-		j_util = sugov_aggregate_util(j_sg_cpu);
 		sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
 
 		if (j_util * max > j_max * util) {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fbfc3f1d368a..997ea7b839fa 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,7 @@
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
 #include "sched.h"
+#include "pelt.h"
 
 struct dl_bandwidth def_dl_bandwidth;
 
@@ -1179,8 +1180,6 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (dl_entity_is_special(dl_se))
 		return;
 
@@ -1761,6 +1760,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	deadline_queue_push_tasks(rq);
 
+	if (rq->curr->sched_class != &dl_sched_class)
+		update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
 	return p;
 }
 
@@ -1768,6 +1770,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
 	update_curr_dl(rq);
 
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
 	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
 }
@@ -1784,6 +1787,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
 {
 	update_curr_dl(rq);
 
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
 	/*
 	 * Even when we have runtime, update_curr_dl() might have resulted in us
 	 * not being the leftmost task anymore. In that case NEED_RESCHED will
@@ -2090,8 +2094,14 @@ retry:
 	sub_rq_bw(&next_task->dl, &rq->dl);
 	set_task_cpu(next_task, later_rq->cpu);
 	add_rq_bw(&next_task->dl, &later_rq->dl);
+
+	/*
+	 * Update the later_rq clock here, because the clock is used
+	 * by the cpufreq_update_util() inside __add_running_bw().
+	 */
+	update_rq_clock(later_rq);
 	add_running_bw(&next_task->dl, &later_rq->dl);
-	activate_task(later_rq, next_task, 0);
+	activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
 	ret = 1;
 
 	resched_curr(later_rq);
@@ -2290,8 +2300,17 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	if (task_on_rq_queued(p) && p->dl.dl_runtime)
 		task_non_contending(p);
 
-	if (!task_on_rq_queued(p))
+	if (!task_on_rq_queued(p)) {
+		/*
+		 * Inactive timer is armed. However, p is leaving DEADLINE and
+		 * might migrate away from this rq while continuing to run on
+		 * some other class. We need to remove its contribution from
+		 * this rq running_bw now, or sub_rq_bw (below) will complain.
+		 */
+		if (p->dl.dl_non_contending)
+			sub_running_bw(&p->dl, &rq->dl);
 		sub_rq_bw(&p->dl, &rq->dl);
+	}
 
 	/*
 	 * We cannot use inactive_task_timer() to invoke sub_running_bw()
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e593b4118578..60caf1fb94e0 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -111,20 +111,19 @@ static int sched_feat_set(char *cmp)
 		cmp += 3;
 	}
 
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (strcmp(cmp, sched_feat_names[i]) == 0) {
-			if (neg) {
-				sysctl_sched_features &= ~(1UL << i);
-				sched_feat_disable(i);
-			} else {
-				sysctl_sched_features |= (1UL << i);
-				sched_feat_enable(i);
-			}
-			break;
-		}
+	i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp);
+	if (i < 0)
+		return i;
+
+	if (neg) {
+		sysctl_sched_features &= ~(1UL << i);
+		sched_feat_disable(i);
+	} else {
+		sysctl_sched_features |= (1UL << i);
+		sched_feat_enable(i);
 	}
 
-	return i;
+	return 0;
 }
 
 static ssize_t
@@ -133,7 +132,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 {
 	char buf[64];
 	char *cmp;
-	int i;
+	int ret;
 	struct inode *inode;
 
 	if (cnt > 63)
@@ -148,10 +147,10 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 	/* Ensure the static_key remains in a consistent state */
 	inode = file_inode(filp);
 	inode_lock(inode);
-	i = sched_feat_set(cmp);
+	ret = sched_feat_set(cmp);
 	inode_unlock(inode);
-	if (i == __SCHED_FEAT_NR)
-		return -EINVAL;
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
@@ -623,8 +622,6 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 #undef PU
 }
 
-extern __read_mostly int sched_clock_running;
-
 static void print_cpu(struct seq_file *m, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -843,8 +840,8 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
 		unsigned long tpf, unsigned long gsf, unsigned long gpf)
 {
 	SEQ_printf(m, "numa_faults node=%d ", node);
-	SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
-	SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+	SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf);
+	SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf);
 }
 #endif
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1866e64792a7..b39fb596f6c1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -255,9 +255,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 	return cfs_rq->rq;
 }
 
-/* An entity is a task if it doesn't "own" a runqueue */
-#define entity_is_task(se)	(!se->my_q)
-
 static inline struct task_struct *task_of(struct sched_entity *se)
 {
 	SCHED_WARN_ON(!entity_is_task(se));
@@ -419,7 +416,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 	return container_of(cfs_rq, struct rq, cfs);
 }
 
-#define entity_is_task(se)	1
 
 #define for_each_sched_entity(se) \
 		for (; se; se = NULL)
@@ -692,7 +688,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 #ifdef CONFIG_SMP
-
+#include "pelt.h"
 #include "sched-pelt.h"
 
 static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
@@ -735,11 +731,12 @@ static void attach_entity_cfs_rq(struct sched_entity *se);
  * To solve this problem, we also cap the util_avg of successive tasks to
  * only 1/2 of the left utilization budget:
  *
- *   util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
+ *   util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n
  *
- * where n denotes the nth task.
+ * where n denotes the nth task and cpu_scale the CPU capacity.
  *
- * For example, a simplest series from the beginning would be like:
+ * For example, for a CPU with 1024 of capacity, a simplest series from
+ * the beginning would be like:
  *
  *  task  util_avg: 512, 256, 128,  64,  32,   16,    8, ...
  * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
@@ -751,7 +748,8 @@ void post_init_entity_util_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	struct sched_avg *sa = &se->avg;
-	long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+	long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq)));
+	long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
 
 	if (cap > 0) {
 		if (cfs_rq->avg.util_avg != 0) {
@@ -1314,7 +1312,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 		 * of each group. Skip other nodes.
 		 */
 		if (sched_numa_topology_type == NUMA_BACKPLANE &&
-					dist > maxdist)
+					dist >= maxdist)
 			continue;
 
 		/* Add up the faults from nearby nodes. */
@@ -1452,15 +1450,12 @@ static unsigned long capacity_of(int cpu);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
-	unsigned long nr_running;
 	unsigned long load;
 
 	/* Total compute capacity of CPUs on a node */
 	unsigned long compute_capacity;
 
-	/* Approximate capacity in terms of runnable tasks on a node */
-	unsigned long task_capacity;
-	int has_free_capacity;
+	unsigned int nr_running;
 };
 
 /*
@@ -1487,8 +1482,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	 * the @ns structure is NULL'ed and task_numa_compare() will
 	 * not find this node attractive.
 	 *
-	 * We'll either bail at !has_free_capacity, or we'll detect a huge
-	 * imbalance and bail there.
+	 * We'll detect a huge imbalance and bail there.
 	 */
 	if (!cpus)
 		return;
@@ -1497,9 +1491,8 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
 	capacity = cpus / smt; /* cores */
 
-	ns->task_capacity = min_t(unsigned, capacity,
+	capacity = min_t(unsigned, capacity,
 		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
-	ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
 }
 
 struct task_numa_env {
@@ -1548,28 +1541,12 @@ static bool load_too_imbalanced(long src_load, long dst_load,
 	src_capacity = env->src_stats.compute_capacity;
 	dst_capacity = env->dst_stats.compute_capacity;
 
-	/* We care about the slope of the imbalance, not the direction. */
-	if (dst_load < src_load)
-		swap(dst_load, src_load);
+	imb = abs(dst_load * src_capacity - src_load * dst_capacity);
 
-	/* Is the difference below the threshold? */
-	imb = dst_load * src_capacity * 100 -
-	      src_load * dst_capacity * env->imbalance_pct;
-	if (imb <= 0)
-		return false;
-
-	/*
-	 * The imbalance is above the allowed threshold.
-	 * Compare it with the old imbalance.
-	 */
 	orig_src_load = env->src_stats.load;
 	orig_dst_load = env->dst_stats.load;
 
-	if (orig_dst_load < orig_src_load)
-		swap(orig_dst_load, orig_src_load);
-
-	old_imb = orig_dst_load * src_capacity * 100 -
-		  orig_src_load * dst_capacity * env->imbalance_pct;
+	old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity);
 
 	/* Would this change make things worse? */
 	return (imb > old_imb);
@@ -1582,9 +1559,8 @@ static bool load_too_imbalanced(long src_load, long dst_load,
  * be exchanged with the source task
  */
 static void task_numa_compare(struct task_numa_env *env,
-			      long taskimp, long groupimp)
+			      long taskimp, long groupimp, bool maymove)
 {
-	struct rq *src_rq = cpu_rq(env->src_cpu);
 	struct rq *dst_rq = cpu_rq(env->dst_cpu);
 	struct task_struct *cur;
 	long src_load, dst_load;
@@ -1605,97 +1581,73 @@ static void task_numa_compare(struct task_numa_env *env,
 	if (cur == env->p)
 		goto unlock;
 
+	if (!cur) {
+		if (maymove || imp > env->best_imp)
+			goto assign;
+		else
+			goto unlock;
+	}
+
 	/*
 	 * "imp" is the fault differential for the source task between the
 	 * source and destination node. Calculate the total differential for
 	 * the source task and potential destination task. The more negative
-	 * the value is, the more rmeote accesses that would be expected to
+	 * the value is, the more remote accesses that would be expected to
 	 * be incurred if the tasks were swapped.
 	 */
-	if (cur) {
-		/* Skip this swap candidate if cannot move to the source CPU: */
-		if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
-			goto unlock;
+	/* Skip this swap candidate if cannot move to the source cpu */
+	if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+		goto unlock;
 
+	/*
+	 * If dst and source tasks are in the same NUMA group, or not
+	 * in any group then look only at task weights.
+	 */
+	if (cur->numa_group == env->p->numa_group) {
+		imp = taskimp + task_weight(cur, env->src_nid, dist) -
+		      task_weight(cur, env->dst_nid, dist);
 		/*
-		 * If dst and source tasks are in the same NUMA group, or not
-		 * in any group then look only at task weights.
+		 * Add some hysteresis to prevent swapping the
+		 * tasks within a group over tiny differences.
 		 */
-		if (cur->numa_group == env->p->numa_group) {
-			imp = taskimp + task_weight(cur, env->src_nid, dist) -
-			      task_weight(cur, env->dst_nid, dist);
-			/*
-			 * Add some hysteresis to prevent swapping the
-			 * tasks within a group over tiny differences.
-			 */
-			if (cur->numa_group)
-				imp -= imp/16;
-		} else {
-			/*
-			 * Compare the group weights. If a task is all by
-			 * itself (not part of a group), use the task weight
-			 * instead.
-			 */
-			if (cur->numa_group)
-				imp += group_weight(cur, env->src_nid, dist) -
-				       group_weight(cur, env->dst_nid, dist);
-			else
-				imp += task_weight(cur, env->src_nid, dist) -
-				       task_weight(cur, env->dst_nid, dist);
-		}
+		if (cur->numa_group)
+			imp -= imp / 16;
+	} else {
+		/*
+		 * Compare the group weights. If a task is all by itself
+		 * (not part of a group), use the task weight instead.
+		 */
+		if (cur->numa_group && env->p->numa_group)
+			imp += group_weight(cur, env->src_nid, dist) -
+			       group_weight(cur, env->dst_nid, dist);
+		else
+			imp += task_weight(cur, env->src_nid, dist) -
+			       task_weight(cur, env->dst_nid, dist);
 	}
 
-	if (imp <= env->best_imp && moveimp <= env->best_imp)
+	if (imp <= env->best_imp)
 		goto unlock;
 
-	if (!cur) {
-		/* Is there capacity at our destination? */
-		if (env->src_stats.nr_running <= env->src_stats.task_capacity &&
-		    !env->dst_stats.has_free_capacity)
-			goto unlock;
-
-		goto balance;
-	}
-
-	/* Balance doesn't matter much if we're running a task per CPU: */
-	if (imp > env->best_imp && src_rq->nr_running == 1 &&
-			dst_rq->nr_running == 1)
+	if (maymove && moveimp > imp && moveimp > env->best_imp) {
+		imp = moveimp - 1;
+		cur = NULL;
 		goto assign;
+	}
 
 	/*
 	 * In the overloaded case, try and keep the load balanced.
 	 */
-balance:
-	load = task_h_load(env->p);
+	load = task_h_load(env->p) - task_h_load(cur);
+	if (!load)
+		goto assign;
+
 	dst_load = env->dst_stats.load + load;
 	src_load = env->src_stats.load - load;
 
-	if (moveimp > imp && moveimp > env->best_imp) {
-		/*
-		 * If the improvement from just moving env->p direction is
-		 * better than swapping tasks around, check if a move is
-		 * possible. Store a slightly smaller score than moveimp,
-		 * so an actually idle CPU will win.
-		 */
-		if (!load_too_imbalanced(src_load, dst_load, env)) {
-			imp = moveimp - 1;
-			cur = NULL;
-			goto assign;
-		}
-	}
-
-	if (imp <= env->best_imp)
-		goto unlock;
-
-	if (cur) {
-		load = task_h_load(cur);
-		dst_load -= load;
-		src_load += load;
-	}
-
 	if (load_too_imbalanced(src_load, dst_load, env))
 		goto unlock;
 
+assign:
 	/*
 	 * One idle CPU per node is evaluated for a task numa move.
 	 * Call select_idle_sibling to maybe find a better one.
@@ -1711,7 +1663,6 @@ balance:
 		local_irq_enable();
 	}
 
-assign:
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
@@ -1720,43 +1671,30 @@ unlock:
 static void task_numa_find_cpu(struct task_numa_env *env,
 				long taskimp, long groupimp)
 {
+	long src_load, dst_load, load;
+	bool maymove = false;
 	int cpu;
 
+	load = task_h_load(env->p);
+	dst_load = env->dst_stats.load + load;
+	src_load = env->src_stats.load - load;
+
+	/*
+	 * If the improvement from just moving env->p direction is better
+	 * than swapping tasks around, check if a move is possible.
+	 */
+	maymove = !load_too_imbalanced(src_load, dst_load, env);
+
 	for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
 		/* Skip this CPU if the source task cannot migrate */
 		if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
 			continue;
 
 		env->dst_cpu = cpu;
-		task_numa_compare(env, taskimp, groupimp);
+		task_numa_compare(env, taskimp, groupimp, maymove);
 	}
 }
 
-/* Only move tasks to a NUMA node less busy than the current node. */
-static bool numa_has_capacity(struct task_numa_env *env)
-{
-	struct numa_stats *src = &env->src_stats;
-	struct numa_stats *dst = &env->dst_stats;
-
-	if (src->has_free_capacity && !dst->has_free_capacity)
-		return false;
-
-	/*
-	 * Only consider a task move if the source has a higher load
-	 * than the destination, corrected for CPU capacity on each node.
-	 *
-	 *      src->load                dst->load
-	 * --------------------- vs ---------------------
-	 * src->compute_capacity    dst->compute_capacity
-	 */
-	if (src->load * dst->compute_capacity * env->imbalance_pct >
-
-	    dst->load * src->compute_capacity * 100)
-		return true;
-
-	return false;
-}
-
 static int task_numa_migrate(struct task_struct *p)
 {
 	struct task_numa_env env = {
@@ -1797,7 +1735,7 @@ static int task_numa_migrate(struct task_struct *p)
 	 * elsewhere, so there is no point in (re)trying.
 	 */
 	if (unlikely(!sd)) {
-		p->numa_preferred_nid = task_node(p);
+		sched_setnuma(p, task_node(p));
 		return -EINVAL;
 	}
 
@@ -1811,8 +1749,7 @@ static int task_numa_migrate(struct task_struct *p)
 	update_numa_stats(&env.dst_stats, env.dst_nid);
 
 	/* Try to find a spot on the preferred nid. */
-	if (numa_has_capacity(&env))
-		task_numa_find_cpu(&env, taskimp, groupimp);
+	task_numa_find_cpu(&env, taskimp, groupimp);
 
 	/*
 	 * Look at other nodes in these cases:
@@ -1842,8 +1779,7 @@ static int task_numa_migrate(struct task_struct *p)
 			env.dist = dist;
 			env.dst_nid = nid;
 			update_numa_stats(&env.dst_stats, env.dst_nid);
-			if (numa_has_capacity(&env))
-				task_numa_find_cpu(&env, taskimp, groupimp);
+			task_numa_find_cpu(&env, taskimp, groupimp);
 		}
 	}
 
@@ -1856,15 +1792,13 @@ static int task_numa_migrate(struct task_struct *p)
 	 * trying for a better one later. Do not set the preferred node here.
 	 */
 	if (p->numa_group) {
-		struct numa_group *ng = p->numa_group;
-
 		if (env.best_cpu == -1)
 			nid = env.src_nid;
 		else
-			nid = env.dst_nid;
+			nid = cpu_to_node(env.best_cpu);
 
-		if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
-			sched_setnuma(p, env.dst_nid);
+		if (nid != p->numa_preferred_nid)
+			sched_setnuma(p, nid);
 	}
 
 	/* No better CPU than the current one was found. */
@@ -1884,7 +1818,8 @@ static int task_numa_migrate(struct task_struct *p)
 		return ret;
 	}
 
-	ret = migrate_swap(p, env.best_task);
+	ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+
 	if (ret != 0)
 		trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
 	put_task_struct(env.best_task);
@@ -2144,8 +2079,8 @@ static int preferred_group_nid(struct task_struct *p, int nid)
 
 static void task_numa_placement(struct task_struct *p)
 {
-	int seq, nid, max_nid = -1, max_group_nid = -1;
-	unsigned long max_faults = 0, max_group_faults = 0;
+	int seq, nid, max_nid = -1;
+	unsigned long max_faults = 0;
 	unsigned long fault_types[2] = { 0, 0 };
 	unsigned long total_faults;
 	u64 runtime, period;
@@ -2224,33 +2159,30 @@ static void task_numa_placement(struct task_struct *p)
 			}
 		}
 
-		if (faults > max_faults) {
-			max_faults = faults;
+		if (!p->numa_group) {
+			if (faults > max_faults) {
+				max_faults = faults;
+				max_nid = nid;
+			}
+		} else if (group_faults > max_faults) {
+			max_faults = group_faults;
 			max_nid = nid;
 		}
-
-		if (group_faults > max_group_faults) {
-			max_group_faults = group_faults;
-			max_group_nid = nid;
-		}
 	}
 
-	update_task_scan_period(p, fault_types[0], fault_types[1]);
-
 	if (p->numa_group) {
 		numa_group_count_active_nodes(p->numa_group);
 		spin_unlock_irq(group_lock);
-		max_nid = preferred_group_nid(p, max_group_nid);
+		max_nid = preferred_group_nid(p, max_nid);
 	}
 
 	if (max_faults) {
 		/* Set the new preferred node */
 		if (max_nid != p->numa_preferred_nid)
 			sched_setnuma(p, max_nid);
-
-		if (task_node(p) != p->numa_preferred_nid)
-			numa_migrate_preferred(p);
 	}
+
+	update_task_scan_period(p, fault_types[0], fault_types[1]);
 }
 
 static inline int get_numa_group(struct numa_group *grp)
@@ -2450,14 +2382,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 				numa_is_active_node(mem_node, ng))
 		local = 1;
 
-	task_numa_placement(p);
-
 	/*
 	 * Retry task to preferred node migration periodically, in case it
 	 * case it previously failed, or the scheduler moved us.
 	 */
-	if (time_after(jiffies, p->numa_migrate_retry))
+	if (time_after(jiffies, p->numa_migrate_retry)) {
+		task_numa_placement(p);
 		numa_migrate_preferred(p);
+	}
 
 	if (migrated)
 		p->numa_pages_migrated += pages;
@@ -2749,19 +2681,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 } while (0)
 
 #ifdef CONFIG_SMP
-/*
- * XXX we want to get rid of these helpers and use the full load resolution.
- */
-static inline long se_weight(struct sched_entity *se)
-{
-	return scale_load_down(se->load.weight);
-}
-
-static inline long se_runnable(struct sched_entity *se)
-{
-	return scale_load_down(se->runnable_weight);
-}
-
 static inline void
 enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -3062,314 +2981,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 }
 
 #ifdef CONFIG_SMP
-/*
- * Approximate:
- *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
- */
-static u64 decay_load(u64 val, u64 n)
-{
-	unsigned int local_n;
-
-	if (unlikely(n > LOAD_AVG_PERIOD * 63))
-		return 0;
-
-	/* after bounds checking we can collapse to 32-bit */
-	local_n = n;
-
-	/*
-	 * As y^PERIOD = 1/2, we can combine
-	 *    y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
-	 * With a look-up table which covers y^n (n<PERIOD)
-	 *
-	 * To achieve constant time decay_load.
-	 */
-	if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
-		val >>= local_n / LOAD_AVG_PERIOD;
-		local_n %= LOAD_AVG_PERIOD;
-	}
-
-	val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
-	return val;
-}
-
-static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
-{
-	u32 c1, c2, c3 = d3; /* y^0 == 1 */
-
-	/*
-	 * c1 = d1 y^p
-	 */
-	c1 = decay_load((u64)d1, periods);
-
-	/*
-	 *            p-1
-	 * c2 = 1024 \Sum y^n
-	 *            n=1
-	 *
-	 *              inf        inf
-	 *    = 1024 ( \Sum y^n - \Sum y^n - y^0 )
-	 *              n=0        n=p
-	 */
-	c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
-
-	return c1 + c2 + c3;
-}
-
-/*
- * Accumulate the three separate parts of the sum; d1 the remainder
- * of the last (incomplete) period, d2 the span of full periods and d3
- * the remainder of the (incomplete) current period.
- *
- *           d1          d2           d3
- *           ^           ^            ^
- *           |           |            |
- *         |<->|<----------------->|<--->|
- * ... |---x---|------| ... |------|-----x (now)
- *
- *                           p-1
- * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
- *                           n=1
- *
- *    = u y^p +					(Step 1)
- *
- *                     p-1
- *      d1 y^p + 1024 \Sum y^n + d3 y^0		(Step 2)
- *                     n=1
- */
-static __always_inline u32
-accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
-	       unsigned long load, unsigned long runnable, int running)
-{
-	unsigned long scale_freq, scale_cpu;
-	u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
-	u64 periods;
-
-	scale_freq = arch_scale_freq_capacity(cpu);
-	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
-
-	delta += sa->period_contrib;
-	periods = delta / 1024; /* A period is 1024us (~1ms) */
-
-	/*
-	 * Step 1: decay old *_sum if we crossed period boundaries.
-	 */
-	if (periods) {
-		sa->load_sum = decay_load(sa->load_sum, periods);
-		sa->runnable_load_sum =
-			decay_load(sa->runnable_load_sum, periods);
-		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
-
-		/*
-		 * Step 2
-		 */
-		delta %= 1024;
-		contrib = __accumulate_pelt_segments(periods,
-				1024 - sa->period_contrib, delta);
-	}
-	sa->period_contrib = delta;
-
-	contrib = cap_scale(contrib, scale_freq);
-	if (load)
-		sa->load_sum += load * contrib;
-	if (runnable)
-		sa->runnable_load_sum += runnable * contrib;
-	if (running)
-		sa->util_sum += contrib * scale_cpu;
-
-	return periods;
-}
-
-/*
- * We can represent the historical contribution to runnable average as the
- * coefficients of a geometric series.  To do this we sub-divide our runnable
- * history into segments of approximately 1ms (1024us); label the segment that
- * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
- *
- * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
- *      p0            p1           p2
- *     (now)       (~1ms ago)  (~2ms ago)
- *
- * Let u_i denote the fraction of p_i that the entity was runnable.
- *
- * We then designate the fractions u_i as our co-efficients, yielding the
- * following representation of historical load:
- *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
- *
- * We choose y based on the with of a reasonably scheduling period, fixing:
- *   y^32 = 0.5
- *
- * This means that the contribution to load ~32ms ago (u_32) will be weighted
- * approximately half as much as the contribution to load within the last ms
- * (u_0).
- *
- * When a period "rolls over" and we have new u_0`, multiplying the previous
- * sum again by y is sufficient to update:
- *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
- *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
- */
-static __always_inline int
-___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
-		  unsigned long load, unsigned long runnable, int running)
-{
-	u64 delta;
-
-	delta = now - sa->last_update_time;
-	/*
-	 * This should only happen when time goes backwards, which it
-	 * unfortunately does during sched clock init when we swap over to TSC.
-	 */
-	if ((s64)delta < 0) {
-		sa->last_update_time = now;
-		return 0;
-	}
-
-	/*
-	 * Use 1024ns as the unit of measurement since it's a reasonable
-	 * approximation of 1us and fast to compute.
-	 */
-	delta >>= 10;
-	if (!delta)
-		return 0;
-
-	sa->last_update_time += delta << 10;
-
-	/*
-	 * running is a subset of runnable (weight) so running can't be set if
-	 * runnable is clear. But there are some corner cases where the current
-	 * se has been already dequeued but cfs_rq->curr still points to it.
-	 * This means that weight will be 0 but not running for a sched_entity
-	 * but also for a cfs_rq if the latter becomes idle. As an example,
-	 * this happens during idle_balance() which calls
-	 * update_blocked_averages()
-	 */
-	if (!load)
-		runnable = running = 0;
-
-	/*
-	 * Now we know we crossed measurement unit boundaries. The *_avg
-	 * accrues by two steps:
-	 *
-	 * Step 1: accumulate *_sum since last_update_time. If we haven't
-	 * crossed period boundaries, finish.
-	 */
-	if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
-		return 0;
-
-	return 1;
-}
-
-static __always_inline void
-___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
-{
-	u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
-
-	/*
-	 * Step 2: update *_avg.
-	 */
-	sa->load_avg = div_u64(load * sa->load_sum, divider);
-	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
-	sa->util_avg = sa->util_sum / divider;
-}
-
-/*
- * When a task is dequeued, its estimated utilization should not be update if
- * its util_avg has not been updated at least once.
- * This flag is used to synchronize util_avg updates with util_est updates.
- * We map this information into the LSB bit of the utilization saved at
- * dequeue time (i.e. util_est.dequeued).
- */
-#define UTIL_AVG_UNCHANGED 0x1
-
-static inline void cfs_se_util_change(struct sched_avg *avg)
-{
-	unsigned int enqueued;
-
-	if (!sched_feat(UTIL_EST))
-		return;
-
-	/* Avoid store if the flag has been already set */
-	enqueued = avg->util_est.enqueued;
-	if (!(enqueued & UTIL_AVG_UNCHANGED))
-		return;
-
-	/* Reset flag to report util_avg has been updated */
-	enqueued &= ~UTIL_AVG_UNCHANGED;
-	WRITE_ONCE(avg->util_est.enqueued, enqueued);
-}
-
-/*
- * sched_entity:
- *
- *   task:
- *     se_runnable() == se_weight()
- *
- *   group: [ see update_cfs_group() ]
- *     se_weight()   = tg->weight * grq->load_avg / tg->load_avg
- *     se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
- *
- *   load_sum := runnable_sum
- *   load_avg = se_weight(se) * runnable_avg
- *
- *   runnable_load_sum := runnable_sum
- *   runnable_load_avg = se_runnable(se) * runnable_avg
- *
- * XXX collapse load_sum and runnable_load_sum
- *
- * cfq_rs:
- *
- *   load_sum = \Sum se_weight(se) * se->avg.load_sum
- *   load_avg = \Sum se->avg.load_avg
- *
- *   runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
- *   runnable_load_avg = \Sum se->avg.runable_load_avg
- */
-
-static int
-__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
-{
-	if (entity_is_task(se))
-		se->runnable_weight = se->load.weight;
-
-	if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
-		return 1;
-	}
-
-	return 0;
-}
-
-static int
-__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	if (entity_is_task(se))
-		se->runnable_weight = se->load.weight;
-
-	if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
-				cfs_rq->curr == se)) {
-
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
-		cfs_se_util_change(&se->avg);
-		return 1;
-	}
-
-	return 0;
-}
-
-static int
-__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
-{
-	if (___update_load_sum(now, cpu, &cfs_rq->avg,
-				scale_load_down(cfs_rq->load.weight),
-				scale_load_down(cfs_rq->runnable_weight),
-				cfs_rq->curr != NULL)) {
-
-		___update_load_avg(&cfs_rq->avg, 1, 1);
-		return 1;
-	}
-
-	return 0;
-}
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /**
  * update_tg_load_avg - update the tg's load avg
@@ -3982,18 +3593,10 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	if (!sched_feat(UTIL_EST))
 		return;
 
-	/*
-	 * Update root cfs_rq's estimated utilization
-	 *
-	 * If *p is the last task then the root cfs_rq's estimated utilization
-	 * of a CPU is 0 by definition.
-	 */
-	ue.enqueued = 0;
-	if (cfs_rq->nr_running) {
-		ue.enqueued  = cfs_rq->avg.util_est.enqueued;
-		ue.enqueued -= min_t(unsigned int, ue.enqueued,
-				     (_task_util_est(p) | UTIL_AVG_UNCHANGED));
-	}
+	/* Update root cfs_rq's estimated utilization */
+	ue.enqueued  = cfs_rq->avg.util_est.enqueued;
+	ue.enqueued -= min_t(unsigned int, ue.enqueued,
+			     (_task_util_est(p) | UTIL_AVG_UNCHANGED));
 	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
 
 	/*
@@ -4045,12 +3648,6 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 
 #else /* CONFIG_SMP */
 
-static inline int
-update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
-{
-	return 0;
-}
-
 #define UPDATE_TG	0x0
 #define SKIP_AGE_LOAD	0x0
 #define DO_ATTACH	0x0
@@ -4590,6 +4187,7 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
 	now = sched_clock_cpu(smp_processor_id());
 	cfs_b->runtime = cfs_b->quota;
 	cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
+	cfs_b->expires_seq++;
 }
 
 static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -4612,6 +4210,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	struct task_group *tg = cfs_rq->tg;
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
 	u64 amount = 0, min_amount, expires;
+	int expires_seq;
 
 	/* note: this is a positive sum as runtime_remaining <= 0 */
 	min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
@@ -4628,6 +4227,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 			cfs_b->idle = 0;
 		}
 	}
+	expires_seq = cfs_b->expires_seq;
 	expires = cfs_b->runtime_expires;
 	raw_spin_unlock(&cfs_b->lock);
 
@@ -4637,8 +4237,10 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	 * spread between our sched_clock and the one on which runtime was
 	 * issued.
 	 */
-	if ((s64)(expires - cfs_rq->runtime_expires) > 0)
+	if (cfs_rq->expires_seq != expires_seq) {
+		cfs_rq->expires_seq = expires_seq;
 		cfs_rq->runtime_expires = expires;
+	}
 
 	return cfs_rq->runtime_remaining > 0;
 }
@@ -4664,12 +4266,9 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	 * has not truly expired.
 	 *
 	 * Fortunately we can check determine whether this the case by checking
-	 * whether the global deadline has advanced. It is valid to compare
-	 * cfs_b->runtime_expires without any locks since we only care about
-	 * exact equality, so a partial write will still work.
+	 * whether the global deadline(cfs_b->expires_seq) has advanced.
 	 */
-
-	if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
+	if (cfs_rq->expires_seq == cfs_b->expires_seq) {
 		/* extend local deadline, drift is bounded above by 2 ticks */
 		cfs_rq->runtime_expires += TICK_NSEC;
 	} else {
@@ -4732,7 +4331,6 @@ static inline int throttled_lb_pair(struct task_group *tg,
 	       throttled_hierarchy(dest_cfs_rq);
 }
 
-/* updated child weight may affect parent so we have to do this bottom up */
 static int tg_unthrottle_up(struct task_group *tg, void *data)
 {
 	struct rq *rq = data;
@@ -5202,13 +4800,18 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 
 void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
+	u64 overrun;
+
 	lockdep_assert_held(&cfs_b->lock);
 
-	if (!cfs_b->period_active) {
-		cfs_b->period_active = 1;
-		hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
-		hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
-	}
+	if (cfs_b->period_active)
+		return;
+
+	cfs_b->period_active = 1;
+	overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+	cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
+	cfs_b->expires_seq++;
+	hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
 }
 
 static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
@@ -5654,8 +5257,6 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
 
 		this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
 	}
-
-	sched_avg_update(this_rq);
 }
 
 /* Used instead of source_load when we know the type == 0 */
@@ -6238,6 +5839,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 }
 
 #ifdef CONFIG_SCHED_SMT
+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 
 static inline void set_idle_cores(int cpu, int val)
 {
@@ -7295,8 +6897,8 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 {
 	struct numa_group *numa_group = rcu_dereference(p->numa_group);
-	unsigned long src_faults, dst_faults;
-	int src_nid, dst_nid;
+	unsigned long src_weight, dst_weight;
+	int src_nid, dst_nid, dist;
 
 	if (!static_branch_likely(&sched_numa_balancing))
 		return -1;
@@ -7323,18 +6925,19 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 		return 0;
 
 	/* Leaving a core idle is often worse than degrading locality. */
-	if (env->idle != CPU_NOT_IDLE)
+	if (env->idle == CPU_IDLE)
 		return -1;
 
+	dist = node_distance(src_nid, dst_nid);
 	if (numa_group) {
-		src_faults = group_faults(p, src_nid);
-		dst_faults = group_faults(p, dst_nid);
+		src_weight = group_weight(p, src_nid, dist);
+		dst_weight = group_weight(p, dst_nid, dist);
 	} else {
-		src_faults = task_faults(p, src_nid);
-		dst_faults = task_faults(p, dst_nid);
+		src_weight = task_weight(p, src_nid, dist);
+		dst_weight = task_weight(p, dst_nid, dist);
 	}
 
-	return dst_faults < src_faults;
+	return dst_weight < src_weight;
 }
 
 #else
@@ -7621,6 +7224,22 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
 	return false;
 }
 
+static inline bool others_have_blocked(struct rq *rq)
+{
+	if (READ_ONCE(rq->avg_rt.util_avg))
+		return true;
+
+	if (READ_ONCE(rq->avg_dl.util_avg))
+		return true;
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	if (READ_ONCE(rq->avg_irq.util_avg))
+		return true;
+#endif
+
+	return false;
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
@@ -7680,6 +7299,12 @@ static void update_blocked_averages(int cpu)
 		if (cfs_rq_has_blocked(cfs_rq))
 			done = false;
 	}
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_irq_load_avg(rq, 0);
+	/* Don't need periodic decay once load/util_avg are null */
+	if (others_have_blocked(rq))
+		done = false;
 
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
@@ -7745,9 +7370,12 @@ static inline void update_blocked_averages(int cpu)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_irq_load_avg(rq, 0);
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
-	if (!cfs_rq_has_blocked(cfs_rq))
+	if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq))
 		rq->has_blocked_load = 0;
 #endif
 	rq_unlock_irqrestore(rq, &rf);
@@ -7857,39 +7485,32 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	u64 total, used, age_stamp, avg;
-	s64 delta;
+	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+	unsigned long used, free;
+	unsigned long irq;
 
-	/*
-	 * Since we're reading these variables without serialization make sure
-	 * we read them once before doing sanity checks on them.
-	 */
-	age_stamp = READ_ONCE(rq->age_stamp);
-	avg = READ_ONCE(rq->rt_avg);
-	delta = __rq_clock_broken(rq) - age_stamp;
+	irq = cpu_util_irq(rq);
 
-	if (unlikely(delta < 0))
-		delta = 0;
+	if (unlikely(irq >= max))
+		return 1;
 
-	total = sched_avg_period() + delta;
+	used = READ_ONCE(rq->avg_rt.util_avg);
+	used += READ_ONCE(rq->avg_dl.util_avg);
 
-	used = div_u64(avg, total);
+	if (unlikely(used >= max))
+		return 1;
 
-	if (likely(used < SCHED_CAPACITY_SCALE))
-		return SCHED_CAPACITY_SCALE - used;
+	free = max - used;
 
-	return 1;
+	return scale_irq_capacity(free, irq, max);
 }
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
+	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
 
-	cpu_rq(cpu)->cpu_capacity_orig = capacity;
-
-	capacity *= scale_rt_capacity(cpu);
-	capacity >>= SCHED_CAPACITY_SHIFT;
+	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
 
 	if (!capacity)
 		capacity = 1;
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
new file mode 100644
index 000000000000..35475c0c5419
--- /dev/null
+++ b/kernel/sched/pelt.c
@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Per Entity Load Tracking
+ *
+ *  Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ *  Interactivity improvements by Mike Galbraith
+ *  (C) 2007 Mike Galbraith <efault@gmx.de>
+ *
+ *  Various enhancements by Dmitry Adamushko.
+ *  (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
+ *
+ *  Group scheduling enhancements by Srivatsa Vaddagiri
+ *  Copyright IBM Corporation, 2007
+ *  Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
+ *
+ *  Scaled math optimizations by Thomas Gleixner
+ *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
+ *
+ *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
+ *
+ *  Move PELT related code from fair.c into this pelt.c file
+ *  Author: Vincent Guittot <vincent.guittot@linaro.org>
+ */
+
+#include <linux/sched.h>
+#include "sched.h"
+#include "sched-pelt.h"
+#include "pelt.h"
+
+/*
+ * Approximate:
+ *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
+ */
+static u64 decay_load(u64 val, u64 n)
+{
+	unsigned int local_n;
+
+	if (unlikely(n > LOAD_AVG_PERIOD * 63))
+		return 0;
+
+	/* after bounds checking we can collapse to 32-bit */
+	local_n = n;
+
+	/*
+	 * As y^PERIOD = 1/2, we can combine
+	 *    y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
+	 * With a look-up table which covers y^n (n<PERIOD)
+	 *
+	 * To achieve constant time decay_load.
+	 */
+	if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
+		val >>= local_n / LOAD_AVG_PERIOD;
+		local_n %= LOAD_AVG_PERIOD;
+	}
+
+	val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
+	return val;
+}
+
+static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
+{
+	u32 c1, c2, c3 = d3; /* y^0 == 1 */
+
+	/*
+	 * c1 = d1 y^p
+	 */
+	c1 = decay_load((u64)d1, periods);
+
+	/*
+	 *            p-1
+	 * c2 = 1024 \Sum y^n
+	 *            n=1
+	 *
+	 *              inf        inf
+	 *    = 1024 ( \Sum y^n - \Sum y^n - y^0 )
+	 *              n=0        n=p
+	 */
+	c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
+
+	return c1 + c2 + c3;
+}
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
+/*
+ * Accumulate the three separate parts of the sum; d1 the remainder
+ * of the last (incomplete) period, d2 the span of full periods and d3
+ * the remainder of the (incomplete) current period.
+ *
+ *           d1          d2           d3
+ *           ^           ^            ^
+ *           |           |            |
+ *         |<->|<----------------->|<--->|
+ * ... |---x---|------| ... |------|-----x (now)
+ *
+ *                           p-1
+ * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
+ *                           n=1
+ *
+ *    = u y^p +					(Step 1)
+ *
+ *                     p-1
+ *      d1 y^p + 1024 \Sum y^n + d3 y^0		(Step 2)
+ *                     n=1
+ */
+static __always_inline u32
+accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
+	       unsigned long load, unsigned long runnable, int running)
+{
+	unsigned long scale_freq, scale_cpu;
+	u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
+	u64 periods;
+
+	scale_freq = arch_scale_freq_capacity(cpu);
+	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+
+	delta += sa->period_contrib;
+	periods = delta / 1024; /* A period is 1024us (~1ms) */
+
+	/*
+	 * Step 1: decay old *_sum if we crossed period boundaries.
+	 */
+	if (periods) {
+		sa->load_sum = decay_load(sa->load_sum, periods);
+		sa->runnable_load_sum =
+			decay_load(sa->runnable_load_sum, periods);
+		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
+
+		/*
+		 * Step 2
+		 */
+		delta %= 1024;
+		contrib = __accumulate_pelt_segments(periods,
+				1024 - sa->period_contrib, delta);
+	}
+	sa->period_contrib = delta;
+
+	contrib = cap_scale(contrib, scale_freq);
+	if (load)
+		sa->load_sum += load * contrib;
+	if (runnable)
+		sa->runnable_load_sum += runnable * contrib;
+	if (running)
+		sa->util_sum += contrib * scale_cpu;
+
+	return periods;
+}
+
+/*
+ * We can represent the historical contribution to runnable average as the
+ * coefficients of a geometric series.  To do this we sub-divide our runnable
+ * history into segments of approximately 1ms (1024us); label the segment that
+ * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
+ *
+ * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
+ *      p0            p1           p2
+ *     (now)       (~1ms ago)  (~2ms ago)
+ *
+ * Let u_i denote the fraction of p_i that the entity was runnable.
+ *
+ * We then designate the fractions u_i as our co-efficients, yielding the
+ * following representation of historical load:
+ *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
+ *
+ * We choose y based on the with of a reasonably scheduling period, fixing:
+ *   y^32 = 0.5
+ *
+ * This means that the contribution to load ~32ms ago (u_32) will be weighted
+ * approximately half as much as the contribution to load within the last ms
+ * (u_0).
+ *
+ * When a period "rolls over" and we have new u_0`, multiplying the previous
+ * sum again by y is sufficient to update:
+ *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
+ *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
+ */
+static __always_inline int
+___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
+		  unsigned long load, unsigned long runnable, int running)
+{
+	u64 delta;
+
+	delta = now - sa->last_update_time;
+	/*
+	 * This should only happen when time goes backwards, which it
+	 * unfortunately does during sched clock init when we swap over to TSC.
+	 */
+	if ((s64)delta < 0) {
+		sa->last_update_time = now;
+		return 0;
+	}
+
+	/*
+	 * Use 1024ns as the unit of measurement since it's a reasonable
+	 * approximation of 1us and fast to compute.
+	 */
+	delta >>= 10;
+	if (!delta)
+		return 0;
+
+	sa->last_update_time += delta << 10;
+
+	/*
+	 * running is a subset of runnable (weight) so running can't be set if
+	 * runnable is clear. But there are some corner cases where the current
+	 * se has been already dequeued but cfs_rq->curr still points to it.
+	 * This means that weight will be 0 but not running for a sched_entity
+	 * but also for a cfs_rq if the latter becomes idle. As an example,
+	 * this happens during idle_balance() which calls
+	 * update_blocked_averages()
+	 */
+	if (!load)
+		runnable = running = 0;
+
+	/*
+	 * Now we know we crossed measurement unit boundaries. The *_avg
+	 * accrues by two steps:
+	 *
+	 * Step 1: accumulate *_sum since last_update_time. If we haven't
+	 * crossed period boundaries, finish.
+	 */
+	if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
+		return 0;
+
+	return 1;
+}
+
+static __always_inline void
+___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
+{
+	u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+
+	/*
+	 * Step 2: update *_avg.
+	 */
+	sa->load_avg = div_u64(load * sa->load_sum, divider);
+	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
+	WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
+}
+
+/*
+ * sched_entity:
+ *
+ *   task:
+ *     se_runnable() == se_weight()
+ *
+ *   group: [ see update_cfs_group() ]
+ *     se_weight()   = tg->weight * grq->load_avg / tg->load_avg
+ *     se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
+ *
+ *   load_sum := runnable_sum
+ *   load_avg = se_weight(se) * runnable_avg
+ *
+ *   runnable_load_sum := runnable_sum
+ *   runnable_load_avg = se_runnable(se) * runnable_avg
+ *
+ * XXX collapse load_sum and runnable_load_sum
+ *
+ * cfq_rq:
+ *
+ *   load_sum = \Sum se_weight(se) * se->avg.load_sum
+ *   load_avg = \Sum se->avg.load_avg
+ *
+ *   runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
+ *   runnable_load_avg = \Sum se->avg.runable_load_avg
+ */
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
+{
+	if (entity_is_task(se))
+		se->runnable_weight = se->load.weight;
+
+	if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
+		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		return 1;
+	}
+
+	return 0;
+}
+
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	if (entity_is_task(se))
+		se->runnable_weight = se->load.weight;
+
+	if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
+				cfs_rq->curr == se)) {
+
+		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		cfs_se_util_change(&se->avg);
+		return 1;
+	}
+
+	return 0;
+}
+
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
+{
+	if (___update_load_sum(now, cpu, &cfs_rq->avg,
+				scale_load_down(cfs_rq->load.weight),
+				scale_load_down(cfs_rq->runnable_weight),
+				cfs_rq->curr != NULL)) {
+
+		___update_load_avg(&cfs_rq->avg, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * rt_rq:
+ *
+ *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ *   util_sum = cpu_scale * load_sum
+ *   runnable_load_sum = load_sum
+ *
+ *   load_avg and runnable_load_avg are not supported and meaningless.
+ *
+ */
+
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	if (___update_load_sum(now, rq->cpu, &rq->avg_rt,
+				running,
+				running,
+				running)) {
+
+		___update_load_avg(&rq->avg_rt, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * dl_rq:
+ *
+ *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ *   util_sum = cpu_scale * load_sum
+ *   runnable_load_sum = load_sum
+ *
+ */
+
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	if (___update_load_sum(now, rq->cpu, &rq->avg_dl,
+				running,
+				running,
+				running)) {
+
+		___update_load_avg(&rq->avg_dl, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+/*
+ * irq:
+ *
+ *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ *   util_sum = cpu_scale * load_sum
+ *   runnable_load_sum = load_sum
+ *
+ */
+
+int update_irq_load_avg(struct rq *rq, u64 running)
+{
+	int ret = 0;
+	/*
+	 * We know the time that has been used by interrupt since last update
+	 * but we don't when. Let be pessimistic and assume that interrupt has
+	 * happened just before the update. This is not so far from reality
+	 * because interrupt will most probably wake up task and trig an update
+	 * of rq clock during which the metric si updated.
+	 * We start to decay with normal context time and then we add the
+	 * interrupt context time.
+	 * We can safely remove running from rq->clock because
+	 * rq->clock += delta with delta >= running
+	 */
+	ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq,
+				0,
+				0,
+				0);
+	ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq,
+				1,
+				1,
+				1);
+
+	if (ret)
+		___update_load_avg(&rq->avg_irq, 1, 1);
+
+	return ret;
+}
+#endif
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
new file mode 100644
index 000000000000..d2894db28955
--- /dev/null
+++ b/kernel/sched/pelt.h
@@ -0,0 +1,72 @@
+#ifdef CONFIG_SMP
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se);
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se);
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+int update_irq_load_avg(struct rq *rq, u64 running);
+#else
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+	return 0;
+}
+#endif
+
+/*
+ * When a task is dequeued, its estimated utilization should not be update if
+ * its util_avg has not been updated at least once.
+ * This flag is used to synchronize util_avg updates with util_est updates.
+ * We map this information into the LSB bit of the utilization saved at
+ * dequeue time (i.e. util_est.dequeued).
+ */
+#define UTIL_AVG_UNCHANGED 0x1
+
+static inline void cfs_se_util_change(struct sched_avg *avg)
+{
+	unsigned int enqueued;
+
+	if (!sched_feat(UTIL_EST))
+		return;
+
+	/* Avoid store if the flag has been already set */
+	enqueued = avg->util_est.enqueued;
+	if (!(enqueued & UTIL_AVG_UNCHANGED))
+		return;
+
+	/* Reset flag to report util_avg has been updated */
+	enqueued &= ~UTIL_AVG_UNCHANGED;
+	WRITE_ONCE(avg->util_est.enqueued, enqueued);
+}
+
+#else
+
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+{
+	return 0;
+}
+
+static inline int
+update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	return 0;
+}
+
+static inline int
+update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	return 0;
+}
+
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+	return 0;
+}
+#endif
+
+
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 47556b0c9a95..2e2955a8cf8f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -5,6 +5,8 @@
  */
 #include "sched.h"
 
+#include "pelt.h"
+
 int sched_rr_timeslice = RR_TIMESLICE;
 int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
 
@@ -508,8 +510,11 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 
 	rt_se = rt_rq->tg->rt_se[cpu];
 
-	if (!rt_se)
+	if (!rt_se) {
 		dequeue_top_rt_rq(rt_rq);
+		/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+		cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
+	}
 	else if (on_rt_rq(rt_se))
 		dequeue_rt_entity(rt_se, 0);
 }
@@ -833,6 +838,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 		 * can be time-consuming. Try to avoid it when possible.
 		 */
 		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF)
+			rt_rq->rt_runtime = rt_b->rt_runtime;
 		skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 		if (skip)
@@ -968,8 +975,6 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -1001,8 +1006,6 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq)
 	sub_nr_running(rq, rt_rq->rt_nr_running);
 	rt_rq->rt_queued = 0;
 
-	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
-	cpufreq_update_util(rq, 0);
 }
 
 static void
@@ -1014,11 +1017,14 @@ enqueue_top_rt_rq(struct rt_rq *rt_rq)
 
 	if (rt_rq->rt_queued)
 		return;
-	if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running)
+
+	if (rt_rq_throttled(rt_rq))
 		return;
 
-	add_nr_running(rq, rt_rq->rt_nr_running);
-	rt_rq->rt_queued = 1;
+	if (rt_rq->rt_nr_running) {
+		add_nr_running(rq, rt_rq->rt_nr_running);
+		rt_rq->rt_queued = 1;
+	}
 
 	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
 	cpufreq_update_util(rq, 0);
@@ -1572,6 +1578,14 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	rt_queue_push_tasks(rq);
 
+	/*
+	 * If prev task was rt, put_prev_task() has already updated the
+	 * utilization. We only care of the case where we start to schedule a
+	 * rt task
+	 */
+	if (rq->curr->sched_class != &rt_sched_class)
+		update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+
 	return p;
 }
 
@@ -1579,6 +1593,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 {
 	update_curr_rt(rq);
 
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
+
 	/*
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
@@ -2308,6 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	struct sched_rt_entity *rt_se = &p->rt;
 
 	update_curr_rt(rq);
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
 
 	watchdog(rq, p);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6601baf2361c..4a2e8cae63c4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -334,9 +334,10 @@ struct cfs_bandwidth {
 	u64			runtime;
 	s64			hierarchical_quota;
 	u64			runtime_expires;
+	int			expires_seq;
 
-	int			idle;
-	int			period_active;
+	short			idle;
+	short			period_active;
 	struct hrtimer		period_timer;
 	struct hrtimer		slack_timer;
 	struct list_head	throttled_cfs_rq;
@@ -551,6 +552,7 @@ struct cfs_rq {
 
 #ifdef CONFIG_CFS_BANDWIDTH
 	int			runtime_enabled;
+	int			expires_seq;
 	u64			runtime_expires;
 	s64			runtime_remaining;
 
@@ -592,6 +594,7 @@ struct rt_rq {
 	unsigned long		rt_nr_total;
 	int			overloaded;
 	struct plist_head	pushable_tasks;
+
 #endif /* CONFIG_SMP */
 	int			rt_queued;
 
@@ -609,6 +612,11 @@ struct rt_rq {
 #endif
 };
 
+static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq)
+{
+	return rt_rq->rt_queued && rt_rq->rt_nr_running;
+}
+
 /* Deadline class' related fields in a runqueue */
 struct dl_rq {
 	/* runqueue is an rbtree, ordered by deadline */
@@ -666,7 +674,26 @@ struct dl_rq {
 	u64			bw_ratio;
 };
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* An entity is a task if it doesn't "own" a runqueue */
+#define entity_is_task(se)	(!se->my_q)
+#else
+#define entity_is_task(se)	1
+#endif
+
 #ifdef CONFIG_SMP
+/*
+ * XXX we want to get rid of these helpers and use the full load resolution.
+ */
+static inline long se_weight(struct sched_entity *se)
+{
+	return scale_load_down(se->load.weight);
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+	return scale_load_down(se->runnable_weight);
+}
 
 static inline bool sched_asym_prefer(int a, int b)
 {
@@ -826,8 +853,12 @@ struct rq {
 
 	struct list_head cfs_tasks;
 
-	u64			rt_avg;
-	u64			age_stamp;
+	struct sched_avg	avg_rt;
+	struct sched_avg	avg_dl;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#define HAVE_SCHED_AVG_IRQ
+	struct sched_avg	avg_irq;
+#endif
 	u64			idle_stamp;
 	u64			avg_idle;
 
@@ -1068,7 +1099,8 @@ enum numa_faults_stats {
 };
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
-extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern int migrate_swap(struct task_struct *p, struct task_struct *t,
+			int cpu, int scpu);
 extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
 #else
 static inline void
@@ -1683,15 +1715,9 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
 extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
-extern const_debug unsigned int sysctl_sched_time_avg;
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
-static inline u64 sched_avg_period(void)
-{
-	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
-}
-
 #ifdef CONFIG_SCHED_HRTICK
 
 /*
@@ -1728,8 +1754,6 @@ unsigned long arch_scale_freq_capacity(int cpu)
 #endif
 
 #ifdef CONFIG_SMP
-extern void sched_avg_update(struct rq *rq);
-
 #ifndef arch_scale_cpu_capacity
 static __always_inline
 unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
@@ -1740,12 +1764,6 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 	return SCHED_CAPACITY_SCALE;
 }
 #endif
-
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
-{
-	rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq));
-	sched_avg_update(rq);
-}
 #else
 #ifndef arch_scale_cpu_capacity
 static __always_inline
@@ -1754,8 +1772,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
 	return SCHED_CAPACITY_SCALE;
 }
 #endif
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
-static inline void sched_avg_update(struct rq *rq) { }
 #endif
 
 struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
@@ -2170,11 +2186,16 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
-static inline unsigned long cpu_util_dl(struct rq *rq)
+static inline unsigned long cpu_bw_dl(struct rq *rq)
 {
 	return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
 }
 
+static inline unsigned long cpu_util_dl(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_dl.util_avg);
+}
+
 static inline unsigned long cpu_util_cfs(struct rq *rq)
 {
 	unsigned long util = READ_ONCE(rq->cfs.avg.util_avg);
@@ -2186,4 +2207,37 @@ static inline unsigned long cpu_util_cfs(struct rq *rq)
 
 	return util;
 }
+
+static inline unsigned long cpu_util_rt(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_rt.util_avg);
+}
+#endif
+
+#ifdef HAVE_SCHED_AVG_IRQ
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return rq->avg_irq.util_avg;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+	util *= (max - irq);
+	util /= max;
+
+	return util;
+
+}
+#else
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return 0;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+	return util;
+}
 #endif
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index b6fb2c3b3ff7..66b59ac77c22 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -32,7 +32,7 @@ void swake_up_locked(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_locked);
 
-void swake_up(struct swait_queue_head *q)
+void swake_up_one(struct swait_queue_head *q)
 {
 	unsigned long flags;
 
@@ -40,7 +40,7 @@ void swake_up(struct swait_queue_head *q)
 	swake_up_locked(q);
 	raw_spin_unlock_irqrestore(&q->lock, flags);
 }
-EXPORT_SYMBOL(swake_up);
+EXPORT_SYMBOL(swake_up_one);
 
 /*
  * Does not allow usage from IRQ disabled, since we must be able to
@@ -69,14 +69,14 @@ void swake_up_all(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_all);
 
-void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
 {
 	wait->task = current;
 	if (list_empty(&wait->task_list))
-		list_add(&wait->task_list, &q->task_list);
+		list_add_tail(&wait->task_list, &q->task_list);
 }
 
-void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
+void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state)
 {
 	unsigned long flags;
 
@@ -85,16 +85,28 @@ void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int
 	set_current_state(state);
 	raw_spin_unlock_irqrestore(&q->lock, flags);
 }
-EXPORT_SYMBOL(prepare_to_swait);
+EXPORT_SYMBOL(prepare_to_swait_exclusive);
 
 long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
 {
-	if (signal_pending_state(state, current))
-		return -ERESTARTSYS;
+	unsigned long flags;
+	long ret = 0;
 
-	prepare_to_swait(q, wait, state);
+	raw_spin_lock_irqsave(&q->lock, flags);
+	if (unlikely(signal_pending_state(state, current))) {
+		/*
+		 * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one()
+		 * must not see us.
+		 */
+		list_del_init(&wait->task_list);
+		ret = -ERESTARTSYS;
+	} else {
+		__prepare_to_swait(q, wait);
+		set_current_state(state);
+	}
+	raw_spin_unlock_irqrestore(&q->lock, flags);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(prepare_to_swait_event);
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 05a831427bc7..56a0fed30c0a 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -47,7 +47,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 		printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
 	}
-	if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
+	if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) {
 		printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
 	}
 
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 928be527477e..870f97b313e3 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -134,8 +134,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
  *
  * On UP it can prevent extra preemption.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -392,35 +392,36 @@ static inline bool is_kthread_should_stop(void)
  *     if (condition)
  *         break;
  *
- *     p->state = mode;				condition = true;
- *     smp_mb(); // A				smp_wmb(); // C
- *     if (!wq_entry->flags & WQ_FLAG_WOKEN)	wq_entry->flags |= WQ_FLAG_WOKEN;
- *         schedule()				try_to_wake_up();
- *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
- *     wq_entry->flags &= ~WQ_FLAG_WOKEN;		condition = true;
- *     smp_mb() // B				smp_wmb(); // C
- *						wq_entry->flags |= WQ_FLAG_WOKEN;
- * }
- * remove_wait_queue(&wq_head, &wait);
+ *     // in wait_woken()			// in woken_wake_function()
  *
+ *     p->state = mode;				wq_entry->flags |= WQ_FLAG_WOKEN;
+ *     smp_mb(); // A				try_to_wake_up():
+ *     if (!(wq_entry->flags & WQ_FLAG_WOKEN))	   <full barrier>
+ *         schedule()				   if (p->state & mode)
+ *     p->state = TASK_RUNNING;			      p->state = TASK_RUNNING;
+ *     wq_entry->flags &= ~WQ_FLAG_WOKEN;	~~~~~~~~~~~~~~~~~~
+ *     smp_mb(); // B				condition = true;
+ * }						smp_mb(); // C
+ * remove_wait_queue(&wq_head, &wait);		wq_entry->flags |= WQ_FLAG_WOKEN;
  */
 long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
 {
-	set_current_state(mode); /* A */
 	/*
-	 * The above implies an smp_mb(), which matches with the smp_wmb() from
-	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
-	 * also observe all state before the wakeup.
+	 * The below executes an smp_mb(), which matches with the full barrier
+	 * executed by the try_to_wake_up() in woken_wake_function() such that
+	 * either we see the store to wq_entry->flags in woken_wake_function()
+	 * or woken_wake_function() sees our store to current->state.
 	 */
+	set_current_state(mode); /* A */
 	if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
 		timeout = schedule_timeout(timeout);
 	__set_current_state(TASK_RUNNING);
 
 	/*
-	 * The below implies an smp_mb(), it too pairs with the smp_wmb() from
-	 * woken_wake_function() such that we must either observe the wait
-	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
-	 * an event.
+	 * The below executes an smp_mb(), which matches with the smp_mb() (C)
+	 * in woken_wake_function() such that either we see the wait condition
+	 * being true or the store to wq_entry->flags in woken_wake_function()
+	 * follows ours in the coherence order.
 	 */
 	smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
 
@@ -430,14 +431,8 @@ EXPORT_SYMBOL(wait_woken);
 
 int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
 {
-	/*
-	 * Although this function is called under waitqueue lock, LOCK
-	 * doesn't imply write barrier and the users expects write
-	 * barrier semantics on wakeup functions.  The following
-	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
-	 * and is paired with smp_store_mb() in wait_woken().
-	 */
-	smp_wmb(); /* C */
+	/* Pairs with the smp_store_mb() in wait_woken(). */
+	smp_mb(); /* C */
 	wq_entry->flags |= WQ_FLAG_WOKEN;
 
 	return default_wake_function(wq_entry, mode, sync, key);
diff --git a/kernel/smp.c b/kernel/smp.c
index 084c8b3a2681..d86eec5f51c1 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -584,6 +584,8 @@ void __init smp_init(void)
 		num_nodes, (num_nodes > 1 ? "s" : ""),
 		num_cpus,  (num_cpus  > 1 ? "s" : ""));
 
+	/* Final decision about SMT support */
+	cpu_smt_check_topology();
 	/* Any cleanup work */
 	smp_cpus_done(setup_max_cpus);
 }
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 5043e7433f4b..c230c2dd48e1 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -238,8 +238,7 @@ int smpboot_unpark_threads(unsigned int cpu)
 
 	mutex_lock(&smpboot_threads_lock);
 	list_for_each_entry(cur, &hotplug_threads, list)
-		if (cpumask_test_cpu(cpu, cur->cpumask))
-			smpboot_unpark_thread(cur, cpu);
+		smpboot_unpark_thread(cur, cpu);
 	mutex_unlock(&smpboot_threads_lock);
 	return 0;
 }
@@ -280,34 +279,26 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
 }
 
 /**
- * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related
+ * smpboot_register_percpu_thread - Register a per_cpu thread related
  * 					    to hotplug
  * @plug_thread:	Hotplug thread descriptor
- * @cpumask:		The cpumask where threads run
  *
  * Creates and starts the threads on all online cpus.
  */
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
-					   const struct cpumask *cpumask)
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
 {
 	unsigned int cpu;
 	int ret = 0;
 
-	if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL))
-		return -ENOMEM;
-	cpumask_copy(plug_thread->cpumask, cpumask);
-
 	get_online_cpus();
 	mutex_lock(&smpboot_threads_lock);
 	for_each_online_cpu(cpu) {
 		ret = __smpboot_create_thread(plug_thread, cpu);
 		if (ret) {
 			smpboot_destroy_threads(plug_thread);
-			free_cpumask_var(plug_thread->cpumask);
 			goto out;
 		}
-		if (cpumask_test_cpu(cpu, cpumask))
-			smpboot_unpark_thread(plug_thread, cpu);
+		smpboot_unpark_thread(plug_thread, cpu);
 	}
 	list_add(&plug_thread->list, &hotplug_threads);
 out:
@@ -315,7 +306,7 @@ out:
 	put_online_cpus();
 	return ret;
 }
-EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask);
+EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
 
 /**
  * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
@@ -331,44 +322,9 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	smpboot_destroy_threads(plug_thread);
 	mutex_unlock(&smpboot_threads_lock);
 	put_online_cpus();
-	free_cpumask_var(plug_thread->cpumask);
 }
 EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
 
-/**
- * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked
- * @plug_thread:	Hotplug thread descriptor
- * @new:		Revised mask to use
- *
- * The cpumask field in the smp_hotplug_thread must not be updated directly
- * by the client, but only by calling this function.
- * This function can only be called on a registered smp_hotplug_thread.
- */
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					  const struct cpumask *new)
-{
-	struct cpumask *old = plug_thread->cpumask;
-	static struct cpumask tmp;
-	unsigned int cpu;
-
-	lockdep_assert_cpus_held();
-	mutex_lock(&smpboot_threads_lock);
-
-	/* Park threads that were exclusively enabled on the old mask. */
-	cpumask_andnot(&tmp, old, new);
-	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
-		smpboot_park_thread(plug_thread, cpu);
-
-	/* Unpark threads that are exclusively enabled on the new mask. */
-	cpumask_andnot(&tmp, new, old);
-	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
-		smpboot_unpark_thread(plug_thread, cpu);
-
-	cpumask_copy(old, new);
-
-	mutex_unlock(&smpboot_threads_lock);
-}
-
 static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
 
 /*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 900dcfee542c..6f584861d329 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -79,12 +79,16 @@ static void wakeup_softirqd(void)
 
 /*
  * If ksoftirqd is scheduled, we do not want to process pending softirqs
- * right now. Let ksoftirqd handle this at its own rate, to get fairness.
+ * right now. Let ksoftirqd handle this at its own rate, to get fairness,
+ * unless we're doing some of the synchronous softirqs.
  */
-static bool ksoftirqd_running(void)
+#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ))
+static bool ksoftirqd_running(unsigned long pending)
 {
 	struct task_struct *tsk = __this_cpu_read(ksoftirqd);
 
+	if (pending & SOFTIRQ_NOW_MASK)
+		return false;
 	return tsk && (tsk->state == TASK_RUNNING);
 }
 
@@ -328,7 +332,7 @@ asmlinkage __visible void do_softirq(void)
 
 	pending = local_softirq_pending();
 
-	if (pending && !ksoftirqd_running())
+	if (pending && !ksoftirqd_running(pending))
 		do_softirq_own_stack();
 
 	local_irq_restore(flags);
@@ -355,7 +359,7 @@ void irq_enter(void)
 
 static inline void invoke_softirq(void)
 {
-	if (ksoftirqd_running())
+	if (ksoftirqd_running(local_softirq_pending()))
 		return;
 
 	if (!force_irqthreads) {
@@ -386,7 +390,7 @@ static inline void tick_irq_exit(void)
 
 	/* Make sure that timer wheel updates are propagated */
 	if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
-		if (!in_interrupt())
+		if (!in_irq())
 			tick_nohz_irq_exit();
 	}
 #endif
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index f89014a2c238..067cb83f37ea 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -81,6 +81,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	unsigned long flags;
 	bool enabled;
 
+	preempt_disable();
 	raw_spin_lock_irqsave(&stopper->lock, flags);
 	enabled = stopper->enabled;
 	if (enabled)
@@ -90,6 +91,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 
 	wake_up_q(&wakeq);
+	preempt_enable();
 
 	return enabled;
 }
@@ -236,13 +238,24 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
 	DEFINE_WAKE_Q(wakeq);
 	int err;
+
 retry:
+	/*
+	 * The waking up of stopper threads has to happen in the same
+	 * scheduling context as the queueing.  Otherwise, there is a
+	 * possibility of one of the above stoppers being woken up by another
+	 * CPU, and preempting us. This will cause us to not wake up the other
+	 * stopper forever.
+	 */
+	preempt_disable();
 	raw_spin_lock_irq(&stopper1->lock);
 	raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
 
-	err = -ENOENT;
-	if (!stopper1->enabled || !stopper2->enabled)
+	if (!stopper1->enabled || !stopper2->enabled) {
+		err = -ENOENT;
 		goto unlock;
+	}
+
 	/*
 	 * Ensure that if we race with __stop_cpus() the stoppers won't get
 	 * queued up in reverse order leading to system deadlock.
@@ -253,24 +266,30 @@ retry:
 	 * It can be falsely true but it is safe to spin until it is cleared,
 	 * queue_stop_cpus_work() does everything under preempt_disable().
 	 */
-	err = -EDEADLK;
-	if (unlikely(stop_cpus_in_progress))
-			goto unlock;
+	if (unlikely(stop_cpus_in_progress)) {
+		err = -EDEADLK;
+		goto unlock;
+	}
 
 	err = 0;
 	__cpu_stop_queue_work(stopper1, work1, &wakeq);
 	__cpu_stop_queue_work(stopper2, work2, &wakeq);
+
 unlock:
 	raw_spin_unlock(&stopper2->lock);
 	raw_spin_unlock_irq(&stopper1->lock);
 
 	if (unlikely(err == -EDEADLK)) {
+		preempt_enable();
+
 		while (stop_cpus_in_progress)
 			cpu_relax();
+
 		goto retry;
 	}
 
 	wake_up_q(&wakeq);
+	preempt_enable();
 
 	return err;
 }
diff --git a/kernel/sys.c b/kernel/sys.c
index 38509dc1f77b..e27b51d3facd 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2512,11 +2512,11 @@ static int do_sysinfo(struct sysinfo *info)
 {
 	unsigned long mem_total, sav_total;
 	unsigned int mem_unit, bitcount;
-	struct timespec tp;
+	struct timespec64 tp;
 
 	memset(info, 0, sizeof(struct sysinfo));
 
-	get_monotonic_boottime(&tp);
+	ktime_get_boottime_ts64(&tp);
 	info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
 
 	get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2d9837c0aff4..f22f76b7a138 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -368,14 +368,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "sched_time_avg_ms",
-		.data		= &sysctl_sched_time_avg,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-	},
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname	= "sched_schedstats",
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index dd53e354f630..7bca480151b0 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -162,90 +162,6 @@ static int test_kprobes(void)
 
 }
 
-#if 0
-static u32 jph_val;
-
-static u32 j_kprobe_target(u32 value)
-{
-	if (preemptible()) {
-		handler_errors++;
-		pr_err("jprobe-handler is preemptible\n");
-	}
-	if (value != rand1) {
-		handler_errors++;
-		pr_err("incorrect value in jprobe handler\n");
-	}
-
-	jph_val = rand1;
-	jprobe_return();
-	return 0;
-}
-
-static struct jprobe jp = {
-	.entry		= j_kprobe_target,
-	.kp.symbol_name = "kprobe_target"
-};
-
-static int test_jprobe(void)
-{
-	int ret;
-
-	ret = register_jprobe(&jp);
-	if (ret < 0) {
-		pr_err("register_jprobe returned %d\n", ret);
-		return ret;
-	}
-
-	ret = target(rand1);
-	unregister_jprobe(&jp);
-	if (jph_val == 0) {
-		pr_err("jprobe handler not called\n");
-		handler_errors++;
-	}
-
-	return 0;
-}
-
-static struct jprobe jp2 = {
-	.entry          = j_kprobe_target,
-	.kp.symbol_name = "kprobe_target2"
-};
-
-static int test_jprobes(void)
-{
-	int ret;
-	struct jprobe *jps[2] = {&jp, &jp2};
-
-	/* addr and flags should be cleard for reusing kprobe. */
-	jp.kp.addr = NULL;
-	jp.kp.flags = 0;
-	ret = register_jprobes(jps, 2);
-	if (ret < 0) {
-		pr_err("register_jprobes returned %d\n", ret);
-		return ret;
-	}
-
-	jph_val = 0;
-	ret = target(rand1);
-	if (jph_val == 0) {
-		pr_err("jprobe handler not called\n");
-		handler_errors++;
-	}
-
-	jph_val = 0;
-	ret = target2(rand1);
-	if (jph_val == 0) {
-		pr_err("jprobe handler2 not called\n");
-		handler_errors++;
-	}
-	unregister_jprobes(jps, 2);
-
-	return 0;
-}
-#else
-#define test_jprobe() (0)
-#define test_jprobes() (0)
-#endif
 #ifdef CONFIG_KRETPROBES
 static u32 krph_val;
 
@@ -383,16 +299,6 @@ int init_test_probes(void)
 	if (ret < 0)
 		errors++;
 
-	num_tests++;
-	ret = test_jprobe();
-	if (ret < 0)
-		errors++;
-
-	num_tests++;
-	ret = test_jprobes();
-	if (ret < 0)
-		errors++;
-
 #ifdef CONFIG_KRETPROBES
 	num_tests++;
 	ret = test_kretprobe();
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 639321bf2e39..fa5de5e8de61 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -581,11 +581,11 @@ static void alarm_timer_rearm(struct k_itimer *timr)
  * @timr:	Pointer to the posixtimer data struct
  * @now:	Current time to forward the timer against
  */
-static int alarm_timer_forward(struct k_itimer *timr, ktime_t now)
+static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now)
 {
 	struct alarm *alarm = &timr->it.alarm.alarmtimer;
 
-	return (int) alarm_forward(alarm, timr->it_interval, now);
+	return alarm_forward(alarm, timr->it_interval, now);
 }
 
 /**
@@ -808,7 +808,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	/* Convert (if necessary) to absolute time */
 	if (flags != TIMER_ABSTIME) {
 		ktime_t now = alarm_bases[type].gettime();
-		exp = ktime_add(now, exp);
+
+		exp = ktime_add_safe(now, exp);
 	}
 
 	ret = alarmtimer_do_nsleep(&alarm, exp, type);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 16c027e9cc73..8c0e4092f661 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -463,6 +463,12 @@ void clockevents_register_device(struct clock_event_device *dev)
 		dev->cpumask = cpumask_of(smp_processor_id());
 	}
 
+	if (dev->cpumask == cpu_all_mask) {
+		WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n",
+		     dev->name);
+		dev->cpumask = cpu_possible_mask;
+	}
+
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
 	list_add(&dev->list, &clockevent_devices);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index f89a78e2792b..f74fb00d8064 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -94,6 +94,8 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);
 /*[Clocksource internal variables]---------
  * curr_clocksource:
  *	currently selected clocksource.
+ * suspend_clocksource:
+ *	used to calculate the suspend time.
  * clocksource_list:
  *	linked list with the registered clocksources
  * clocksource_mutex:
@@ -102,10 +104,12 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);
  *	Name of the user-specified clocksource.
  */
 static struct clocksource *curr_clocksource;
+static struct clocksource *suspend_clocksource;
 static LIST_HEAD(clocksource_list);
 static DEFINE_MUTEX(clocksource_mutex);
 static char override_name[CS_NAME_LEN];
 static int finished_booting;
+static u64 suspend_start;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static void clocksource_watchdog_work(struct work_struct *work);
@@ -447,6 +451,140 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) { }
 
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
+static bool clocksource_is_suspend(struct clocksource *cs)
+{
+	return cs == suspend_clocksource;
+}
+
+static void __clocksource_suspend_select(struct clocksource *cs)
+{
+	/*
+	 * Skip the clocksource which will be stopped in suspend state.
+	 */
+	if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP))
+		return;
+
+	/*
+	 * The nonstop clocksource can be selected as the suspend clocksource to
+	 * calculate the suspend time, so it should not supply suspend/resume
+	 * interfaces to suspend the nonstop clocksource when system suspends.
+	 */
+	if (cs->suspend || cs->resume) {
+		pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n",
+			cs->name);
+	}
+
+	/* Pick the best rating. */
+	if (!suspend_clocksource || cs->rating > suspend_clocksource->rating)
+		suspend_clocksource = cs;
+}
+
+/**
+ * clocksource_suspend_select - Select the best clocksource for suspend timing
+ * @fallback:	if select a fallback clocksource
+ */
+static void clocksource_suspend_select(bool fallback)
+{
+	struct clocksource *cs, *old_suspend;
+
+	old_suspend = suspend_clocksource;
+	if (fallback)
+		suspend_clocksource = NULL;
+
+	list_for_each_entry(cs, &clocksource_list, list) {
+		/* Skip current if we were requested for a fallback. */
+		if (fallback && cs == old_suspend)
+			continue;
+
+		__clocksource_suspend_select(cs);
+	}
+}
+
+/**
+ * clocksource_start_suspend_timing - Start measuring the suspend timing
+ * @cs:			current clocksource from timekeeping
+ * @start_cycles:	current cycles from timekeeping
+ *
+ * This function will save the start cycle values of suspend timer to calculate
+ * the suspend time when resuming system.
+ *
+ * This function is called late in the suspend process from timekeeping_suspend(),
+ * that means processes are freezed, non-boot cpus and interrupts are disabled
+ * now. It is therefore possible to start the suspend timer without taking the
+ * clocksource mutex.
+ */
+void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles)
+{
+	if (!suspend_clocksource)
+		return;
+
+	/*
+	 * If current clocksource is the suspend timer, we should use the
+	 * tkr_mono.cycle_last value as suspend_start to avoid same reading
+	 * from suspend timer.
+	 */
+	if (clocksource_is_suspend(cs)) {
+		suspend_start = start_cycles;
+		return;
+	}
+
+	if (suspend_clocksource->enable &&
+	    suspend_clocksource->enable(suspend_clocksource)) {
+		pr_warn_once("Failed to enable the non-suspend-able clocksource.\n");
+		return;
+	}
+
+	suspend_start = suspend_clocksource->read(suspend_clocksource);
+}
+
+/**
+ * clocksource_stop_suspend_timing - Stop measuring the suspend timing
+ * @cs:		current clocksource from timekeeping
+ * @cycle_now:	current cycles from timekeeping
+ *
+ * This function will calculate the suspend time from suspend timer.
+ *
+ * Returns nanoseconds since suspend started, 0 if no usable suspend clocksource.
+ *
+ * This function is called early in the resume process from timekeeping_resume(),
+ * that means there is only one cpu, no processes are running and the interrupts
+ * are disabled. It is therefore possible to stop the suspend timer without
+ * taking the clocksource mutex.
+ */
+u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now)
+{
+	u64 now, delta, nsec = 0;
+
+	if (!suspend_clocksource)
+		return 0;
+
+	/*
+	 * If current clocksource is the suspend timer, we should use the
+	 * tkr_mono.cycle_last value from timekeeping as current cycle to
+	 * avoid same reading from suspend timer.
+	 */
+	if (clocksource_is_suspend(cs))
+		now = cycle_now;
+	else
+		now = suspend_clocksource->read(suspend_clocksource);
+
+	if (now > suspend_start) {
+		delta = clocksource_delta(now, suspend_start,
+					  suspend_clocksource->mask);
+		nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult,
+				       suspend_clocksource->shift);
+	}
+
+	/*
+	 * Disable the suspend timer to save power if current clocksource is
+	 * not the suspend timer.
+	 */
+	if (!clocksource_is_suspend(cs) && suspend_clocksource->disable)
+		suspend_clocksource->disable(suspend_clocksource);
+
+	return nsec;
+}
+
 /**
  * clocksource_suspend - suspend the clocksource(s)
  */
@@ -792,6 +930,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 
 	clocksource_select();
 	clocksource_select_watchdog(false);
+	__clocksource_suspend_select(cs);
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -820,6 +959,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
 
 	clocksource_select();
 	clocksource_select_watchdog(false);
+	clocksource_suspend_select(false);
 	mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
@@ -845,6 +985,15 @@ static int clocksource_unbind(struct clocksource *cs)
 			return -EBUSY;
 	}
 
+	if (clocksource_is_suspend(cs)) {
+		/*
+		 * Select and try to install a replacement suspend clocksource.
+		 * If no replacement suspend clocksource, we will just let the
+		 * clocksource go and have no suspend clocksource.
+		 */
+		clocksource_suspend_select(true);
+	}
+
 	clocksource_watchdog_lock(&flags);
 	clocksource_dequeue_watchdog(cs);
 	list_del_init(&cs->list);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 3e93c54bd3a1..e1a549c9e399 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -718,8 +718,8 @@ static void hrtimer_switch_to_hres(void)
 	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
 	if (tick_init_highres()) {
-		printk(KERN_WARNING "Could not switch to high resolution "
-				    "mode on CPU %d\n", base->cpu);
+		pr_warn("Could not switch to high resolution mode on CPU %u\n",
+			base->cpu);
 		return;
 	}
 	base->hres_active = 1;
@@ -1573,8 +1573,7 @@ retry:
 	else
 		expires_next = ktime_add(now, delta);
 	tick_program_event(expires_next, 1);
-	printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
-		    ktime_to_ns(delta));
+	pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta));
 }
 
 /* called with interrupts disabled */
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index a09ded765f6c..c5e0cba3b39c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -502,7 +502,7 @@ static void sched_sync_hw_clock(struct timespec64 now,
 {
 	struct timespec64 next;
 
-	getnstimeofday64(&next);
+	ktime_get_real_ts64(&next);
 	if (!fail)
 		next.tv_sec = 659;
 	else {
@@ -537,7 +537,7 @@ static void sync_rtc_clock(void)
 	if (!IS_ENABLED(CONFIG_RTC_SYSTOHC))
 		return;
 
-	getnstimeofday64(&now);
+	ktime_get_real_ts64(&now);
 
 	adjust = now;
 	if (persistent_clock_is_local)
@@ -591,7 +591,7 @@ static bool sync_cmos_clock(void)
 	 * Architectures are strongly encouraged to use rtclib and not
 	 * implement this legacy API.
 	 */
-	getnstimeofday64(&now);
+	ktime_get_real_ts64(&now);
 	if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) {
 		if (persistent_clock_is_local)
 			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
@@ -642,7 +642,7 @@ void ntp_notify_cmos_timer(void)
 /*
  * Propagate a new txc->status value into the NTP state:
  */
-static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
+static inline void process_adj_status(const struct timex *txc)
 {
 	if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
 		time_state = TIME_OK;
@@ -665,12 +665,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
 }
 
 
-static inline void process_adjtimex_modes(struct timex *txc,
-						struct timespec64 *ts,
-						s32 *time_tai)
+static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai)
 {
 	if (txc->modes & ADJ_STATUS)
-		process_adj_status(txc, ts);
+		process_adj_status(txc);
 
 	if (txc->modes & ADJ_NANO)
 		time_status |= STA_NANO;
@@ -718,7 +716,7 @@ static inline void process_adjtimex_modes(struct timex *txc,
  * adjtimex mainly allows reading (and writing, if superuser) of
  * kernel time-keeping variables. used by xntpd.
  */
-int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
+int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai)
 {
 	int result;
 
@@ -735,7 +733,7 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
 
 		/* If there are input parameters, then process them: */
 		if (txc->modes)
-			process_adjtimex_modes(txc, ts, time_tai);
+			process_adjtimex_modes(txc, time_tai);
 
 		txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
 				  NTP_SCALE_SHIFT);
@@ -1022,12 +1020,11 @@ void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_t
 
 static int __init ntp_tick_adj_setup(char *str)
 {
-	int rc = kstrtol(str, 0, (long *)&ntp_tick_adj);
-
+	int rc = kstrtos64(str, 0, &ntp_tick_adj);
 	if (rc)
 		return rc;
-	ntp_tick_adj <<= NTP_SCALE_SHIFT;
 
+	ntp_tick_adj <<= NTP_SCALE_SHIFT;
 	return 1;
 }
 
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index 909bd1f1bfb1..c24b0e13f011 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -8,6 +8,6 @@ extern void ntp_clear(void);
 extern u64 ntp_tick_length(void);
 extern ktime_t ntp_get_next_leap(void);
 extern int second_overflow(time64_t secs);
-extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
-extern void __hardpps(const struct timespec64 *, const struct timespec64 *);
+extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai);
+extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
 #endif /* _LINUX_NTP_INTERNAL_H */
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 9cdf54b04ca8..294d7b65af33 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -85,7 +85,7 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now)
 			continue;
 
 		timer->it.cpu.expires += incr;
-		timer->it_overrun += 1 << i;
+		timer->it_overrun += 1LL << i;
 		delta -= incr;
 	}
 }
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 26aa9569e24a..2c6847d5d69b 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -81,7 +81,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
 		ktime_get_ts64(tp);
 		break;
 	case CLOCK_BOOTTIME:
-		get_monotonic_boottime64(tp);
+		ktime_get_boottime_ts64(tp);
 		break;
 	default:
 		return -EINVAL;
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index e08ce3f27447..f23cc46ecf3e 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -86,15 +86,6 @@ static const struct k_clock clock_realtime, clock_monotonic;
 #endif
 
 /*
- * parisc wants ENOTSUP instead of EOPNOTSUPP
- */
-#ifndef ENOTSUP
-# define ENANOSLEEP_NOTSUP EOPNOTSUPP
-#else
-# define ENANOSLEEP_NOTSUP ENOTSUP
-#endif
-
-/*
  * The timer ID is turned into a timer address by idr_find().
  * Verifying a valid ID consists of:
  *
@@ -228,21 +219,21 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp)
  */
 static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
 {
-	getrawmonotonic64(tp);
+	ktime_get_raw_ts64(tp);
 	return 0;
 }
 
 
 static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp)
 {
-	*tp = current_kernel_time64();
+	ktime_get_coarse_real_ts64(tp);
 	return 0;
 }
 
 static int posix_get_monotonic_coarse(clockid_t which_clock,
 						struct timespec64 *tp)
 {
-	*tp = get_monotonic_coarse64();
+	ktime_get_coarse_ts64(tp);
 	return 0;
 }
 
@@ -254,13 +245,13 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
 
 static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
 {
-	get_monotonic_boottime64(tp);
+	ktime_get_boottime_ts64(tp);
 	return 0;
 }
 
 static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
 {
-	timekeeping_clocktai64(tp);
+	ktime_get_clocktai_ts64(tp);
 	return 0;
 }
 
@@ -283,6 +274,17 @@ static __init int init_posix_timers(void)
 }
 __initcall(init_posix_timers);
 
+/*
+ * The siginfo si_overrun field and the return value of timer_getoverrun(2)
+ * are of type int. Clamp the overrun value to INT_MAX
+ */
+static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
+{
+	s64 sum = timr->it_overrun_last + (s64)baseval;
+
+	return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
+}
+
 static void common_hrtimer_rearm(struct k_itimer *timr)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
@@ -290,9 +292,8 @@ static void common_hrtimer_rearm(struct k_itimer *timr)
 	if (!timr->it_interval)
 		return;
 
-	timr->it_overrun += (unsigned int) hrtimer_forward(timer,
-						timer->base->get_time(),
-						timr->it_interval);
+	timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
+					    timr->it_interval);
 	hrtimer_restart(timer);
 }
 
@@ -321,10 +322,10 @@ void posixtimer_rearm(struct siginfo *info)
 
 		timr->it_active = 1;
 		timr->it_overrun_last = timr->it_overrun;
-		timr->it_overrun = -1;
+		timr->it_overrun = -1LL;
 		++timr->it_requeue_pending;
 
-		info->si_overrun += timr->it_overrun_last;
+		info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
 	}
 
 	unlock_timer(timr, flags);
@@ -418,9 +419,8 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 					now = ktime_add(now, kj);
 			}
 #endif
-			timr->it_overrun += (unsigned int)
-				hrtimer_forward(timer, now,
-						timr->it_interval);
+			timr->it_overrun += hrtimer_forward(timer, now,
+							    timr->it_interval);
 			ret = HRTIMER_RESTART;
 			++timr->it_requeue_pending;
 			timr->it_active = 1;
@@ -524,7 +524,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event,
 	new_timer->it_id = (timer_t) new_timer_id;
 	new_timer->it_clock = which_clock;
 	new_timer->kclock = kc;
-	new_timer->it_overrun = -1;
+	new_timer->it_overrun = -1LL;
 
 	if (event) {
 		rcu_read_lock();
@@ -645,11 +645,11 @@ static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now)
 	return __hrtimer_expires_remaining_adjusted(timer, now);
 }
 
-static int common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
+static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
 
-	return (int)hrtimer_forward(timer, now, timr->it_interval);
+	return hrtimer_forward(timer, now, timr->it_interval);
 }
 
 /*
@@ -743,7 +743,7 @@ static int do_timer_gettime(timer_t timer_id,  struct itimerspec64 *setting)
 
 /* Get the time remaining on a POSIX.1b interval timer. */
 SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
-		struct itimerspec __user *, setting)
+		struct __kernel_itimerspec __user *, setting)
 {
 	struct itimerspec64 cur_setting;
 
@@ -755,7 +755,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 	return ret;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
 COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 		       struct compat_itimerspec __user *, setting)
 {
@@ -768,6 +769,7 @@ COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 	}
 	return ret;
 }
+
 #endif
 
 /*
@@ -789,7 +791,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 	if (!timr)
 		return -EINVAL;
 
-	overrun = timr->it_overrun_last;
+	overrun = timer_overrun_to_int(timr, 0);
 	unlock_timer(timr, flags);
 
 	return overrun;
@@ -906,8 +908,8 @@ retry:
 
 /* Set a POSIX.1b interval timer */
 SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
-		const struct itimerspec __user *, new_setting,
-		struct itimerspec __user *, old_setting)
+		const struct __kernel_itimerspec __user *, new_setting,
+		struct __kernel_itimerspec __user *, old_setting)
 {
 	struct itimerspec64 new_spec, old_spec;
 	struct itimerspec64 *rtn = old_setting ? &old_spec : NULL;
@@ -927,7 +929,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 	return error;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
 COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 		       struct compat_itimerspec __user *, new,
 		       struct compat_itimerspec __user *, old)
@@ -1220,7 +1222,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	if (!kc)
 		return -EINVAL;
 	if (!kc->nsleep)
-		return -ENANOSLEEP_NOTSUP;
+		return -EOPNOTSUPP;
 
 	if (get_timespec64(&t, rqtp))
 		return -EFAULT;
@@ -1247,7 +1249,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
 	if (!kc)
 		return -EINVAL;
 	if (!kc->nsleep)
-		return -ENANOSLEEP_NOTSUP;
+		return -EOPNOTSUPP;
 
 	if (compat_get_timespec64(&t, rqtp))
 		return -EFAULT;
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index 151e28f5bf30..ddb21145211a 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -19,7 +19,7 @@ struct k_clock {
 	void	(*timer_get)(struct k_itimer *timr,
 			     struct itimerspec64 *cur_setting);
 	void	(*timer_rearm)(struct k_itimer *timr);
-	int	(*timer_forward)(struct k_itimer *timr, ktime_t now);
+	s64	(*timer_forward)(struct k_itimer *timr, ktime_t now);
 	ktime_t	(*timer_remaining)(struct k_itimer *timr, ktime_t now);
 	int	(*timer_try_to_cancel)(struct k_itimer *timr);
 	void	(*timer_arm)(struct k_itimer *timr, ktime_t expires,
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 2d8f05aad442..cbc72c2c1fca 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -237,7 +237,7 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 	pr_debug("Registered %pF as sched_clock source\n", read);
 }
 
-void __init sched_clock_postinit(void)
+void __init generic_sched_clock_init(void)
 {
 	/*
 	 * If no sched_clock() function has been provided at that point,
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index 58045eb976c3..a59641fb88b6 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -90,7 +90,7 @@ static struct clock_event_device ce_broadcast_hrtimer = {
 	.max_delta_ticks	= ULONG_MAX,
 	.mult			= 1,
 	.shift			= 0,
-	.cpumask		= cpu_all_mask,
+	.cpumask		= cpu_possible_mask,
 };
 
 static enum hrtimer_restart bc_handler(struct hrtimer *t)
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index b7005dd21ec1..14de3727b18e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -277,8 +277,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
 	 */
 	return !curdev ||
 		newdev->rating > curdev->rating ||
-	       (!cpumask_equal(curdev->cpumask, newdev->cpumask) &&
-	        !tick_check_percpu(curdev, newdev, smp_processor_id()));
+	       !cpumask_equal(curdev->cpumask, newdev->cpumask);
 }
 
 /*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index da9455a6b42b..5b33e2f5c0ed 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -642,7 +642,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 
 static inline bool local_timer_softirq_pending(void)
 {
-	return local_softirq_pending() & TIMER_SOFTIRQ;
+	return local_softirq_pending() & BIT(TIMER_SOFTIRQ);
 }
 
 static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 2b41e8e2d31d..ccdb351277ee 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(sys_tz);
  */
 SYSCALL_DEFINE1(time, time_t __user *, tloc)
 {
-	time_t i = get_seconds();
+	time_t i = (time_t)ktime_get_real_seconds();
 
 	if (tloc) {
 		if (put_user(i,tloc))
@@ -107,11 +107,9 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr)
 /* compat_time_t is a 32 bit "long" and needs to get converted. */
 COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc)
 {
-	struct timeval tv;
 	compat_time_t i;
 
-	do_gettimeofday(&tv);
-	i = tv.tv_sec;
+	i = (compat_time_t)ktime_get_real_seconds();
 
 	if (tloc) {
 		if (put_user(i,tloc))
@@ -931,7 +929,7 @@ int compat_put_timespec64(const struct timespec64 *ts, void __user *uts)
 EXPORT_SYMBOL_GPL(compat_put_timespec64);
 
 int get_itimerspec64(struct itimerspec64 *it,
-			const struct itimerspec __user *uit)
+			const struct __kernel_itimerspec __user *uit)
 {
 	int ret;
 
@@ -946,7 +944,7 @@ int get_itimerspec64(struct itimerspec64 *it,
 EXPORT_SYMBOL_GPL(get_itimerspec64);
 
 int put_itimerspec64(const struct itimerspec64 *it,
-			struct itimerspec __user *uit)
+			struct __kernel_itimerspec __user *uit)
 {
 	int ret;
 
@@ -959,3 +957,24 @@ int put_itimerspec64(const struct itimerspec64 *it,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(put_itimerspec64);
+
+int get_compat_itimerspec64(struct itimerspec64 *its,
+			const struct compat_itimerspec __user *uits)
+{
+
+	if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
+	    __compat_get_timespec64(&its->it_value, &uits->it_value))
+		return -EFAULT;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
+
+int put_compat_itimerspec64(const struct itimerspec64 *its,
+			struct compat_itimerspec __user *uits)
+{
+	if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
+	    __compat_put_timespec64(&its->it_value, &uits->it_value))
+		return -EFAULT;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4786df904c22..f3b22f456fac 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -17,6 +17,7 @@
 #include <linux/nmi.h>
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/clock.h>
 #include <linux/syscore_ops.h>
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
@@ -34,6 +35,14 @@
 #define TK_MIRROR		(1 << 1)
 #define TK_CLOCK_WAS_SET	(1 << 2)
 
+enum timekeeping_adv_mode {
+	/* Update timekeeper when a tick has passed */
+	TK_ADV_TICK,
+
+	/* Update timekeeper on a direct frequency change */
+	TK_ADV_FREQ
+};
+
 /*
  * The most important data for readout fits into a single 64 byte
  * cache line.
@@ -97,7 +106,7 @@ static inline void tk_normalize_xtime(struct timekeeper *tk)
 	}
 }
 
-static inline struct timespec64 tk_xtime(struct timekeeper *tk)
+static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
 {
 	struct timespec64 ts;
 
@@ -154,7 +163,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
  * a read of the fast-timekeeper tkrs (which is protected by its own locking
  * and update logic).
  */
-static inline u64 tk_clock_read(struct tk_read_base *tkr)
+static inline u64 tk_clock_read(const struct tk_read_base *tkr)
 {
 	struct clocksource *clock = READ_ONCE(tkr->clock);
 
@@ -203,7 +212,7 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 	}
 }
 
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	u64 now, last, mask, max, delta;
@@ -247,7 +256,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
 static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 {
 }
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
 {
 	u64 cycle_now, delta;
 
@@ -344,7 +353,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
-static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
+static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta)
 {
 	u64 nsec;
 
@@ -355,7 +364,7 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
 	return nsec + arch_gettimeoffset();
 }
 
-static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr)
 {
 	u64 delta;
 
@@ -363,7 +372,7 @@ static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
 	return timekeeping_delta_to_ns(tkr, delta);
 }
 
-static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
+static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles)
 {
 	u64 delta;
 
@@ -386,7 +395,8 @@ static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
  * slightly wrong timestamp (a few nanoseconds). See
  * @ktime_get_mono_fast_ns.
  */
-static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf)
+static void update_fast_timekeeper(const struct tk_read_base *tkr,
+				   struct tk_fast *tkf)
 {
 	struct tk_read_base *base = tkf->base;
 
@@ -541,10 +551,10 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
  * number of cycles every time until timekeeping is resumed at which time the
  * proper readout base for the fast timekeeper will be restored automatically.
  */
-static void halt_fast_timekeeper(struct timekeeper *tk)
+static void halt_fast_timekeeper(const struct timekeeper *tk)
 {
 	static struct tk_read_base tkr_dummy;
-	struct tk_read_base *tkr = &tk->tkr_mono;
+	const struct tk_read_base *tkr = &tk->tkr_mono;
 
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
 	cycles_at_suspend = tk_clock_read(tkr);
@@ -1269,7 +1279,7 @@ EXPORT_SYMBOL(do_settimeofday64);
  *
  * Adds or subtracts an offset value from the current time.
  */
-static int timekeeping_inject_offset(struct timespec64 *ts)
+static int timekeeping_inject_offset(const struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
@@ -1496,22 +1506,39 @@ void __weak read_persistent_clock64(struct timespec64 *ts64)
 }
 
 /**
- * read_boot_clock64 -  Return time of the system start.
+ * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
+ *                                        from the boot.
  *
  * Weak dummy function for arches that do not yet support it.
- * Function to read the exact time the system has been started.
- * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
- *
- *  XXX - Do be sure to remove it once all arches implement it.
+ * wall_time	- current time as returned by persistent clock
+ * boot_offset	- offset that is defined as wall_time - boot_time
+ * The default function calculates offset based on the current value of
+ * local_clock(). This way architectures that support sched_clock() but don't
+ * support dedicated boot time clock will provide the best estimate of the
+ * boot time.
  */
-void __weak read_boot_clock64(struct timespec64 *ts)
+void __weak __init
+read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+				     struct timespec64 *boot_offset)
 {
-	ts->tv_sec = 0;
-	ts->tv_nsec = 0;
+	read_persistent_clock64(wall_time);
+	*boot_offset = ns_to_timespec64(local_clock());
 }
 
-/* Flag for if timekeeping_resume() has injected sleeptime */
-static bool sleeptime_injected;
+/*
+ * Flag reflecting whether timekeeping_resume() has injected sleeptime.
+ *
+ * The flag starts of false and is only set when a suspend reaches
+ * timekeeping_suspend(), timekeeping_resume() sets it to false when the
+ * timekeeper clocksource is not stopping across suspend and has been
+ * used to update sleep time. If the timekeeper clocksource has stopped
+ * then the flag stays true and is used by the RTC resume code to decide
+ * whether sleeptime must be injected and if so the flag gets false then.
+ *
+ * If a suspend fails before reaching timekeeping_resume() then the flag
+ * stays false and prevents erroneous sleeptime injection.
+ */
+static bool suspend_timing_needed;
 
 /* Flag for if there is a persistent clock on this platform */
 static bool persistent_clock_exists;
@@ -1521,28 +1548,29 @@ static bool persistent_clock_exists;
  */
 void __init timekeeping_init(void)
 {
+	struct timespec64 wall_time, boot_offset, wall_to_mono;
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct clocksource *clock;
 	unsigned long flags;
-	struct timespec64 now, boot, tmp;
-
-	read_persistent_clock64(&now);
-	if (!timespec64_valid_strict(&now)) {
-		pr_warn("WARNING: Persistent clock returned invalid value!\n"
-			"         Check your CMOS/BIOS settings.\n");
-		now.tv_sec = 0;
-		now.tv_nsec = 0;
-	} else if (now.tv_sec || now.tv_nsec)
-		persistent_clock_exists = true;
 
-	read_boot_clock64(&boot);
-	if (!timespec64_valid_strict(&boot)) {
-		pr_warn("WARNING: Boot clock returned invalid value!\n"
-			"         Check your CMOS/BIOS settings.\n");
-		boot.tv_sec = 0;
-		boot.tv_nsec = 0;
+	read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
+	if (timespec64_valid_strict(&wall_time) &&
+	    timespec64_to_ns(&wall_time) > 0) {
+		persistent_clock_exists = true;
+	} else if (timespec64_to_ns(&wall_time) != 0) {
+		pr_warn("Persistent clock returned invalid value");
+		wall_time = (struct timespec64){0};
 	}
 
+	if (timespec64_compare(&wall_time, &boot_offset) < 0)
+		boot_offset = (struct timespec64){0};
+
+	/*
+	 * We want set wall_to_mono, so the following is true:
+	 * wall time + wall_to_mono = boot time
+	 */
+	wall_to_mono = timespec64_sub(boot_offset, wall_time);
+
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	ntp_init();
@@ -1552,13 +1580,10 @@ void __init timekeeping_init(void)
 		clock->enable(clock);
 	tk_setup_internals(tk, clock);
 
-	tk_set_xtime(tk, &now);
+	tk_set_xtime(tk, &wall_time);
 	tk->raw_sec = 0;
-	if (boot.tv_sec == 0 && boot.tv_nsec == 0)
-		boot = tk_xtime(tk);
 
-	set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
-	tk_set_wall_to_mono(tk, tmp);
+	tk_set_wall_to_mono(tk, wall_to_mono);
 
 	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 
@@ -1577,7 +1602,7 @@ static struct timespec64 timekeeping_suspend_time;
  * adds the sleep offset to the timekeeping variables.
  */
 static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
-					   struct timespec64 *delta)
+					   const struct timespec64 *delta)
 {
 	if (!timespec64_valid_strict(delta)) {
 		printk_deferred(KERN_WARNING
@@ -1610,7 +1635,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
  */
 bool timekeeping_rtc_skipresume(void)
 {
-	return sleeptime_injected;
+	return !suspend_timing_needed;
 }
 
 /**
@@ -1638,7 +1663,7 @@ bool timekeeping_rtc_skipsuspend(void)
  * This function should only be called by rtc_resume(), and allows
  * a suspend offset to be injected into the timekeeping values.
  */
-void timekeeping_inject_sleeptime64(struct timespec64 *delta)
+void timekeeping_inject_sleeptime64(const struct timespec64 *delta)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
@@ -1646,6 +1671,8 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta)
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 
+	suspend_timing_needed = false;
+
 	timekeeping_forward_now(tk);
 
 	__timekeeping_inject_sleeptime(tk, delta);
@@ -1669,9 +1696,9 @@ void timekeeping_resume(void)
 	struct clocksource *clock = tk->tkr_mono.clock;
 	unsigned long flags;
 	struct timespec64 ts_new, ts_delta;
-	u64 cycle_now;
+	u64 cycle_now, nsec;
+	bool inject_sleeptime = false;
 
-	sleeptime_injected = false;
 	read_persistent_clock64(&ts_new);
 
 	clockevents_resume();
@@ -1693,22 +1720,19 @@ void timekeeping_resume(void)
 	 * usable source. The rtc part is handled separately in rtc core code.
 	 */
 	cycle_now = tk_clock_read(&tk->tkr_mono);
-	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
-		cycle_now > tk->tkr_mono.cycle_last) {
-		u64 nsec, cyc_delta;
-
-		cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last,
-					      tk->tkr_mono.mask);
-		nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift);
+	nsec = clocksource_stop_suspend_timing(clock, cycle_now);
+	if (nsec > 0) {
 		ts_delta = ns_to_timespec64(nsec);
-		sleeptime_injected = true;
+		inject_sleeptime = true;
 	} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
 		ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
-		sleeptime_injected = true;
+		inject_sleeptime = true;
 	}
 
-	if (sleeptime_injected)
+	if (inject_sleeptime) {
+		suspend_timing_needed = false;
 		__timekeeping_inject_sleeptime(tk, &ts_delta);
+	}
 
 	/* Re-base the last cycle value */
 	tk->tkr_mono.cycle_last = cycle_now;
@@ -1732,6 +1756,8 @@ int timekeeping_suspend(void)
 	unsigned long flags;
 	struct timespec64		delta, delta_delta;
 	static struct timespec64	old_delta;
+	struct clocksource *curr_clock;
+	u64 cycle_now;
 
 	read_persistent_clock64(&timekeeping_suspend_time);
 
@@ -1743,11 +1769,22 @@ int timekeeping_suspend(void)
 	if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
 		persistent_clock_exists = true;
 
+	suspend_timing_needed = true;
+
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	timekeeping_forward_now(tk);
 	timekeeping_suspended = 1;
 
+	/*
+	 * Since we've called forward_now, cycle_last stores the value
+	 * just read from the current clocksource. Save this to potentially
+	 * use in suspend timing.
+	 */
+	curr_clock = tk->tkr_mono.clock;
+	cycle_now = tk->tkr_mono.cycle_last;
+	clocksource_start_suspend_timing(curr_clock, cycle_now);
+
 	if (persistent_clock_exists) {
 		/*
 		 * To avoid drift caused by repeated suspend/resumes,
@@ -2021,11 +2058,11 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
 	return offset;
 }
 
-/**
- * update_wall_time - Uses the current clocksource to increment the wall time
- *
+/*
+ * timekeeping_advance - Updates the timekeeper to the current time and
+ * current NTP tick length
  */
-void update_wall_time(void)
+static void timekeeping_advance(enum timekeeping_adv_mode mode)
 {
 	struct timekeeper *real_tk = &tk_core.timekeeper;
 	struct timekeeper *tk = &shadow_timekeeper;
@@ -2042,14 +2079,17 @@ void update_wall_time(void)
 
 #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
 	offset = real_tk->cycle_interval;
+
+	if (mode != TK_ADV_TICK)
+		goto out;
 #else
 	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
 				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
-#endif
 
 	/* Check if there's really nothing to do */
-	if (offset < real_tk->cycle_interval)
+	if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
 		goto out;
+#endif
 
 	/* Do some additional sanity checking */
 	timekeeping_check_update(tk, offset);
@@ -2106,6 +2146,15 @@ out:
 }
 
 /**
+ * update_wall_time - Uses the current clocksource to increment the wall time
+ *
+ */
+void update_wall_time(void)
+{
+	timekeeping_advance(TK_ADV_TICK);
+}
+
+/**
  * getboottime64 - Return the real time of system boot.
  * @ts:		pointer to the timespec64 to be set
  *
@@ -2220,7 +2269,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
 /**
  * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex
  */
-static int timekeeping_validate_timex(struct timex *txc)
+static int timekeeping_validate_timex(const struct timex *txc)
 {
 	if (txc->modes & ADJ_ADJTIME) {
 		/* singleshot must not be used with any other mode bits */
@@ -2310,7 +2359,7 @@ int do_adjtimex(struct timex *txc)
 			return ret;
 	}
 
-	getnstimeofday64(&ts);
+	ktime_get_real_ts64(&ts);
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
@@ -2327,6 +2376,10 @@ int do_adjtimex(struct timex *txc)
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	/* Update the multiplier immediately if frequency was set directly */
+	if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK))
+		timekeeping_advance(TK_ADV_FREQ);
+
 	if (tai != orig_tai)
 		clock_was_set();
 
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 0754cadfa9e6..238e4be60229 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -70,7 +70,7 @@ static int __init tk_debug_sleep_time_init(void)
 }
 late_initcall(tk_debug_sleep_time_init);
 
-void tk_debug_account_sleep_time(struct timespec64 *t)
+void tk_debug_account_sleep_time(const struct timespec64 *t)
 {
 	/* Cap bin index so we don't overflow the array */
 	int bin = min(fls(t->tv_sec), NUM_BINS-1);
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index cf5c0828ee31..bcbb52db2256 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -8,7 +8,7 @@
 #include <linux/time.h>
 
 #ifdef CONFIG_DEBUG_FS
-extern void tk_debug_account_sleep_time(struct timespec64 *t);
+extern void tk_debug_account_sleep_time(const struct timespec64 *t);
 #else
 #define tk_debug_account_sleep_time(x)
 #endif
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index cc2d23e6ff61..fa49cd753dea 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -581,7 +581,7 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 	 * wheel:
 	 */
 	base->next_expiry = timer->expires;
-		wake_up_nohz_cpu(base->cpu);
+	wake_up_nohz_cpu(base->cpu);
 }
 
 static void
@@ -1657,6 +1657,22 @@ static inline void __run_timers(struct timer_base *base)
 
 	raw_spin_lock_irq(&base->lock);
 
+	/*
+	 * timer_base::must_forward_clk must be cleared before running
+	 * timers so that any timer functions that call mod_timer() will
+	 * not try to forward the base. Idle tracking / clock forwarding
+	 * logic is only used with BASE_STD timers.
+	 *
+	 * The must_forward_clk flag is cleared unconditionally also for
+	 * the deferrable base. The deferrable base is not affected by idle
+	 * tracking and never forwarded, so clearing the flag is a NOOP.
+	 *
+	 * The fact that the deferrable base is never forwarded can cause
+	 * large variations in granularity for deferrable timers, but they
+	 * can be deferred for long periods due to idle anyway.
+	 */
+	base->must_forward_clk = false;
+
 	while (time_after_eq(jiffies, base->clk)) {
 
 		levels = collect_expired_timers(base, heads);
@@ -1676,19 +1692,6 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
-	/*
-	 * must_forward_clk must be cleared before running timers so that any
-	 * timer functions that call mod_timer will not try to forward the
-	 * base. idle trcking / clock forwarding logic is only used with
-	 * BASE_STD timers.
-	 *
-	 * The deferrable base does not do idle tracking at all, so we do
-	 * not forward it. This can result in very large variations in
-	 * granularity for deferrable timers, but they can be deferred for
-	 * long periods due to idle.
-	 */
-	base->must_forward_clk = false;
-
 	__run_timers(base);
 	if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
diff --git a/kernel/torture.c b/kernel/torture.c
index 3de1efbecd6a..1ac24a826589 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -20,6 +20,9 @@
  * Author: Paul E. McKenney <paulmck@us.ibm.com>
  *	Based on kernel/rcu/torture.c.
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -53,7 +56,7 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
 
 static char *torture_type;
-static bool verbose;
+static int verbose;
 
 /* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
 #define FULLSTOP_DONTSTOP 0	/* Normal operation. */
@@ -98,7 +101,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 	if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
 		return false;
 
-	if (verbose)
+	if (verbose > 1)
 		pr_alert("%s" TORTURE_FLAG
 			 "torture_onoff task: offlining %d\n",
 			 torture_type, cpu);
@@ -111,7 +114,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 				 "torture_onoff task: offline %d failed: errno %d\n",
 				 torture_type, cpu, ret);
 	} else {
-		if (verbose)
+		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
 				 "torture_onoff task: offlined %d\n",
 				 torture_type, cpu);
@@ -147,7 +150,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 	if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
 		return false;
 
-	if (verbose)
+	if (verbose > 1)
 		pr_alert("%s" TORTURE_FLAG
 			 "torture_onoff task: onlining %d\n",
 			 torture_type, cpu);
@@ -160,7 +163,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 				 "torture_onoff task: online %d failed: errno %d\n",
 				 torture_type, cpu, ret);
 	} else {
-		if (verbose)
+		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
 				 "torture_onoff task: onlined %d\n",
 				 torture_type, cpu);
@@ -647,7 +650,7 @@ static void torture_stutter_cleanup(void)
  * The runnable parameter points to a flag that controls whether or not
  * the test is currently runnable.  If there is no such flag, pass in NULL.
  */
-bool torture_init_begin(char *ttype, bool v)
+bool torture_init_begin(char *ttype, int v)
 {
 	mutex_lock(&fullstop_mutex);
 	if (torture_type != NULL) {
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index dcc0166d1997..9a27f146fa1c 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -521,7 +521,7 @@ config FUNCTION_PROFILER
 	  in debugfs called function_profile_enabled which defaults to zero.
 	  When a 1 is echoed into this file profiling begins, and when a
 	  zero is entered, profiling stops. A "functions" file is created in
-	  the trace_stats directory; this file shows the list of functions that
+	  the trace_stat directory; this file shows the list of functions that
 	  have been hit and their counters.
 
 	  If in doubt, say N.
@@ -605,7 +605,7 @@ config HIST_TRIGGERS
 	  Inter-event tracing of quantities such as latencies is also
 	  supported using hist triggers under this option.
 
-	  See Documentation/trace/histogram.txt.
+	  See Documentation/trace/histogram.rst.
 	  If in doubt, say N.
 
 config MMIOTRACE_TEST
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 987d9a9ae283..b951aa1fac61 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -494,6 +494,9 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
+	if (!blk_debugfs_root)
+		return -ENOENT;
+
 	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
 	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
 
@@ -518,9 +521,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = -ENOENT;
 
-	if (!blk_debugfs_root)
-		goto err;
-
 	dir = debugfs_lookup(buts->name, blk_debugfs_root);
 	if (!dir)
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index efed9c1cfb7e..caf9cbf35816 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -192,17 +192,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 	op->saved_func(ip, parent_ip, op, regs);
 }
 
-/**
- * clear_ftrace_function - reset the ftrace function
- *
- * This NULLs the ftrace function and in essence stops
- * tracing.  There may be lag
- */
-void clear_ftrace_function(void)
-{
-	ftrace_trace_function = ftrace_stub;
-}
-
 static void ftrace_sync(struct work_struct *work)
 {
 	/*
@@ -6689,7 +6678,7 @@ void ftrace_kill(void)
 {
 	ftrace_disabled = 1;
 	ftrace_enabled = 0;
-	clear_ftrace_function();
+	ftrace_trace_function = ftrace_stub;
 }
 
 /**
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6a46af21765c..0b0b688ea166 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3227,6 +3227,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
 }
 
 /**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+	return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
+/**
  * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
  * @buffer: The ring buffer to stop writes to.
  * @cpu: The CPU buffer to stop
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a0079b4c7a49..823687997b01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	arch_spin_lock(&tr->max_lock);
 
+	/* Inherit the recordable setting from trace_buffer */
+	if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+		ring_buffer_record_on(tr->max_buffer.buffer);
+	else
+		ring_buffer_record_off(tr->max_buffer.buffer);
+
 	swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
 
 	__update_max_tr(tr, tsk, cpu);
@@ -2953,6 +2959,7 @@ out_nobuffer:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
+__printf(3, 0)
 static int
 __trace_array_vprintk(struct ring_buffer *buffer,
 		      unsigned long ip, const char *fmt, va_list args)
@@ -3007,12 +3014,14 @@ out_nobuffer:
 	return len;
 }
 
+__printf(3, 0)
 int trace_array_vprintk(struct trace_array *tr,
 			unsigned long ip, const char *fmt, va_list args)
 {
 	return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
 }
 
+__printf(3, 0)
 int trace_array_printk(struct trace_array *tr,
 		       unsigned long ip, const char *fmt, ...)
 {
@@ -3028,6 +3037,7 @@ int trace_array_printk(struct trace_array *tr,
 	return ret;
 }
 
+__printf(3, 4)
 int trace_array_printk_buf(struct ring_buffer *buffer,
 			   unsigned long ip, const char *fmt, ...)
 {
@@ -3043,6 +3053,7 @@ int trace_array_printk_buf(struct ring_buffer *buffer,
 	return ret;
 }
 
+__printf(2, 0)
 int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
 	return trace_array_vprintk(&global_trace, ip, fmt, args);
@@ -3360,8 +3371,8 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m,
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#           TASK-PID   CPU#   %s  TIMESTAMP  FUNCTION\n", tgid ? "TGID     " : "");
-	seq_printf(m, "#              | |       |    %s     |         |\n",	 tgid ? "  |      " : "");
+	seq_printf(m, "#           TASK-PID   %s  CPU#   TIMESTAMP  FUNCTION\n", tgid ? "TGID     " : "");
+	seq_printf(m, "#              | |     %s    |       |         |\n",	 tgid ? "  |      " : "");
 }
 
 static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m,
@@ -3381,9 +3392,9 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
 		   tgid ? tgid_space : space);
 	seq_printf(m, "#                          %s||| /     delay\n",
 		   tgid ? tgid_space : space);
-	seq_printf(m, "#           TASK-PID   CPU#%s||||    TIMESTAMP  FUNCTION\n",
+	seq_printf(m, "#           TASK-PID %sCPU#  ||||    TIMESTAMP  FUNCTION\n",
 		   tgid ? "   TGID   " : space);
-	seq_printf(m, "#              | |       | %s||||       |         |\n",
+	seq_printf(m, "#              | |   %s  |   ||||       |         |\n",
 		   tgid ? "     |    " : space);
 }
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 630c5a24b2b2..f8f86231ad90 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -583,9 +583,7 @@ static __always_inline void trace_clear_recursion(int bit)
 static inline struct ring_buffer_iter *
 trace_buffer_iter(struct trace_iterator *iter, int cpu)
 {
-	if (iter->buffer_iter && iter->buffer_iter[cpu])
-		return iter->buffer_iter[cpu];
-	return NULL;
+	return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL;
 }
 
 int tracer_init(struct tracer *t, struct trace_array *tr);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0dceb77d1d42..893a206bcba4 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1701,6 +1701,7 @@ static void create_filter_finish(struct filter_parse_error *pe)
  * @filter_str: filter string
  * @set_str: remember @filter_str and enable detailed error in filter
  * @filterp: out param for created filter (always updated on return)
+ *           Must be a pointer that references a NULL pointer.
  *
  * Creates a filter for @call with @filter_str.  If @set_str is %true,
  * @filter_str is copied and recorded in the new filter.
@@ -1718,6 +1719,10 @@ static int create_filter(struct trace_event_call *call,
 	struct filter_parse_error *pe = NULL;
 	int err;
 
+	/* filterp must point to NULL */
+	if (WARN_ON(*filterp))
+		*filterp = NULL;
+
 	err = create_filter_start(filter_string, set_str, &pe, filterp);
 	if (err)
 		return err;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 046c716a6536..aae18af94c94 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -393,7 +393,7 @@ static void hist_err_event(char *str, char *system, char *event, char *var)
 	else if (system)
 		snprintf(err, MAX_FILTER_STR_VAL, "%s.%s", system, event);
 	else
-		strncpy(err, var, MAX_FILTER_STR_VAL);
+		strscpy(err, var, MAX_FILTER_STR_VAL);
 
 	hist_err(str, err);
 }
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d18249683682..5dea177cef53 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -679,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops,
 		goto out_free;
 
  out_reg:
+	/* Up the trigger_data count to make sure reg doesn't free it on failure */
+	event_trigger_init(trigger_ops, trigger_data);
 	ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
 	/*
 	 * The above returns on success the # of functions enabled,
@@ -686,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops,
 	 * Consider no functions a failure too.
 	 */
 	if (!ret) {
+		cmd_ops->unreg(glob, trigger_ops, trigger_data, file);
 		ret = -ENOENT;
-		goto out_free;
-	} else if (ret < 0)
-		goto out_free;
-	ret = 0;
+	} else if (ret > 0)
+		ret = 0;
+
+	/* Down the counter of trigger_data or free it if not used anymore */
+	event_trigger_free(trigger_ops, trigger_data);
  out:
 	return ret;
 
@@ -1416,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 		goto out;
 	}
 
+	/* Up the trigger_data count to make sure nothing frees it on failure */
+	event_trigger_init(trigger_ops, trigger_data);
+
 	if (trigger) {
 		number = strsep(&trigger, ":");
 
@@ -1466,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 		goto out_disable;
 	/* Just return zero, not the number of enabled functions */
 	ret = 0;
+	event_trigger_free(trigger_ops, trigger_data);
  out:
 	return ret;
 
@@ -1476,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
  out_free:
 	if (cmd_ops->set_filter)
 		cmd_ops->set_filter(NULL, trigger_data, NULL);
-	kfree(trigger_data);
+	event_trigger_free(trigger_ops, trigger_data);
 	kfree(enable_data);
 	goto out;
 }
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 23c0b0cb5fb9..169b3c44ee97 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -831,6 +831,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 	struct ftrace_graph_ret *graph_ret;
 	struct ftrace_graph_ent *call;
 	unsigned long long duration;
+	int cpu = iter->cpu;
 	int i;
 
 	graph_ret = &ret_entry->ret;
@@ -839,7 +840,6 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 
 	if (data) {
 		struct fgraph_cpu_data *cpu_data;
-		int cpu = iter->cpu;
 
 		cpu_data = per_cpu_ptr(data->cpu_data, cpu);
 
@@ -869,6 +869,9 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 
 	trace_seq_printf(s, "%ps();\n", (void *)call->func);
 
+	print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
+			cpu, iter->ent->pid, flags);
+
 	return trace_handle_return(s);
 }
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index daa81571b22a..e9d99463e5df 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event,
 static int
 enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 {
+	struct event_file_link *link = NULL;
 	int ret = 0;
 
 	if (file) {
-		struct event_file_link *link;
-
 		link = kmalloc(sizeof(*link), GFP_KERNEL);
 		if (!link) {
 			ret = -ENOMEM;
@@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 		else
 			ret = enable_kprobe(&tk->rp.kp);
 	}
+
+	if (ret) {
+		if (file) {
+			/* Notice the if is true on not WARN() */
+			if (!WARN_ON_ONCE(!link))
+				list_del_rcu(&link->list);
+			kfree(link);
+			tk->tp.flags &= ~TP_FLAG_TRACE;
+		} else {
+			tk->tp.flags &= ~TP_FLAG_PROFILE;
+		}
+	}
  out:
 	return ret;
 }
@@ -1217,16 +1228,11 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 
 		/*
 		 * We need to check and see if we modified the pc of the
-		 * pt_regs, and if so clear the kprobe and return 1 so that we
-		 * don't do the single stepping.
-		 * The ftrace kprobe handler leaves it up to us to re-enable
-		 * preemption here before returning if we've modified the ip.
+		 * pt_regs, and if so return 1 so that we don't do the
+		 * single stepping.
 		 */
-		if (orig_ip != instruction_pointer(regs)) {
-			reset_current_kprobe();
-			preempt_enable_no_resched();
+		if (orig_ip != instruction_pointer(regs))
 			return 1;
-		}
 		if (!ret)
 			return 0;
 	}
@@ -1480,8 +1486,10 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
 	}
 
 	ret = __register_trace_kprobe(tk);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(tk->tp.call.print_fmt);
 		goto error;
+	}
 
 	return &tk->tp.call;
 error:
@@ -1501,6 +1509,8 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call)
 	}
 
 	__unregister_trace_kprobe(tk);
+
+	kfree(tk->tp.call.print_fmt);
 	free_trace_kprobe(tk);
 }
 #endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 90db994ac900..1c8e30fda46a 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -594,8 +594,7 @@ int trace_print_context(struct trace_iterator *iter)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%16s-%-5d [%03d] ",
-			       comm, entry->pid, iter->cpu);
+	trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
 
 	if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
 		unsigned int tgid = trace_find_tgid(entry->pid);
@@ -606,6 +605,8 @@ int trace_print_context(struct trace_iterator *iter)
 			trace_seq_printf(s, "(%5d) ", tgid);
 	}
 
+	trace_seq_printf(s, "[%03d] ", iter->cpu);
+
 	if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
 		trace_print_lat_fmt(s, entry);
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 576d18045811..5470dce212c0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -18,18 +18,14 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/sysctl.h>
-#include <linux/smpboot.h>
-#include <linux/sched/rt.h>
-#include <uapi/linux/sched/types.h>
 #include <linux/tick.h>
-#include <linux/workqueue.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/isolation.h>
+#include <linux/stop_machine.h>
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
-#include <linux/kthread.h>
 
 static DEFINE_MUTEX(watchdog_mutex);
 
@@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void)
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 
-static bool softlockup_threads_initialized __read_mostly;
+static bool softlockup_initialized __read_mostly;
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
-static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
 static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
 static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
@@ -335,6 +330,27 @@ static void watchdog_interrupt_count(void)
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
+static DEFINE_PER_CPU(struct completion, softlockup_completion);
+static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
+
+/*
+ * The watchdog thread function - touches the timestamp.
+ *
+ * It only runs once every sample_period seconds (4 seconds by
+ * default) to reset the softlockup timestamp. If this gets delayed
+ * for more than 2*watchdog_thresh seconds then the debug-printout
+ * triggers in watchdog_timer_fn().
+ */
+static int softlockup_fn(void *data)
+{
+	__this_cpu_write(soft_lockup_hrtimer_cnt,
+			 __this_cpu_read(hrtimer_interrupts));
+	__touch_watchdog();
+	complete(this_cpu_ptr(&softlockup_completion));
+
+	return 0;
+}
+
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -350,7 +366,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	watchdog_interrupt_count();
 
 	/* kick the softlockup detector */
-	wake_up_process(__this_cpu_read(softlockup_watchdog));
+	if (completion_done(this_cpu_ptr(&softlockup_completion))) {
+		reinit_completion(this_cpu_ptr(&softlockup_completion));
+		stop_one_cpu_nowait(smp_processor_id(),
+				softlockup_fn, NULL,
+				this_cpu_ptr(&softlockup_stop_work));
+	}
 
 	/* .. and repeat */
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
@@ -448,16 +469,15 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static void watchdog_set_prio(unsigned int policy, unsigned int prio)
-{
-	struct sched_param param = { .sched_priority = prio };
-
-	sched_setscheduler(current, policy, &param);
-}
-
 static void watchdog_enable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
+	struct completion *done = this_cpu_ptr(&softlockup_completion);
+
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
+	init_completion(done);
+	complete(done);
 
 	/*
 	 * Start the timer first to prevent the NMI watchdog triggering
@@ -473,15 +493,14 @@ static void watchdog_enable(unsigned int cpu)
 	/* Enable the perf event */
 	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
 		watchdog_nmi_enable(cpu);
-
-	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
 }
 
 static void watchdog_disable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
-	watchdog_set_prio(SCHED_NORMAL, 0);
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
 	/*
 	 * Disable the perf event first. That prevents that a large delay
 	 * between disabling the timer and disabling the perf event causes
@@ -489,79 +508,66 @@ static void watchdog_disable(unsigned int cpu)
 	 */
 	watchdog_nmi_disable(cpu);
 	hrtimer_cancel(hrtimer);
+	wait_for_completion(this_cpu_ptr(&softlockup_completion));
 }
 
-static void watchdog_cleanup(unsigned int cpu, bool online)
+static int softlockup_stop_fn(void *data)
 {
-	watchdog_disable(cpu);
+	watchdog_disable(smp_processor_id());
+	return 0;
 }
 
-static int watchdog_should_run(unsigned int cpu)
+static void softlockup_stop_all(void)
 {
-	return __this_cpu_read(hrtimer_interrupts) !=
-		__this_cpu_read(soft_lockup_hrtimer_cnt);
+	int cpu;
+
+	if (!softlockup_initialized)
+		return;
+
+	for_each_cpu(cpu, &watchdog_allowed_mask)
+		smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false);
+
+	cpumask_clear(&watchdog_allowed_mask);
 }
 
-/*
- * The watchdog thread function - touches the timestamp.
- *
- * It only runs once every sample_period seconds (4 seconds by
- * default) to reset the softlockup timestamp. If this gets delayed
- * for more than 2*watchdog_thresh seconds then the debug-printout
- * triggers in watchdog_timer_fn().
- */
-static void watchdog(unsigned int cpu)
+static int softlockup_start_fn(void *data)
 {
-	__this_cpu_write(soft_lockup_hrtimer_cnt,
-			 __this_cpu_read(hrtimer_interrupts));
-	__touch_watchdog();
+	watchdog_enable(smp_processor_id());
+	return 0;
 }
 
-static struct smp_hotplug_thread watchdog_threads = {
-	.store			= &softlockup_watchdog,
-	.thread_should_run	= watchdog_should_run,
-	.thread_fn		= watchdog,
-	.thread_comm		= "watchdog/%u",
-	.setup			= watchdog_enable,
-	.cleanup		= watchdog_cleanup,
-	.park			= watchdog_disable,
-	.unpark			= watchdog_enable,
-};
-
-static void softlockup_update_smpboot_threads(void)
+static void softlockup_start_all(void)
 {
-	lockdep_assert_held(&watchdog_mutex);
-
-	if (!softlockup_threads_initialized)
-		return;
+	int cpu;
 
-	smpboot_update_cpumask_percpu_thread(&watchdog_threads,
-					     &watchdog_allowed_mask);
+	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+	for_each_cpu(cpu, &watchdog_allowed_mask)
+		smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false);
 }
 
-/* Temporarily park all watchdog threads */
-static void softlockup_park_all_threads(void)
+int lockup_detector_online_cpu(unsigned int cpu)
 {
-	cpumask_clear(&watchdog_allowed_mask);
-	softlockup_update_smpboot_threads();
+	watchdog_enable(cpu);
+	return 0;
 }
 
-/* Unpark enabled threads */
-static void softlockup_unpark_threads(void)
+int lockup_detector_offline_cpu(unsigned int cpu)
 {
-	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
-	softlockup_update_smpboot_threads();
+	watchdog_disable(cpu);
+	return 0;
 }
 
 static void lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
 	watchdog_nmi_stop();
-	softlockup_park_all_threads();
+
+	softlockup_stop_all();
 	set_sample_period();
 	lockup_detector_update_enable();
 	if (watchdog_enabled && watchdog_thresh)
-		softlockup_unpark_threads();
+		softlockup_start_all();
+
 	watchdog_nmi_start();
 	cpus_read_unlock();
 	/*
@@ -580,8 +586,6 @@ static void lockup_detector_reconfigure(void)
  */
 static __init void lockup_detector_setup(void)
 {
-	int ret;
-
 	/*
 	 * If sysctl is off and watchdog got disabled on the command line,
 	 * nothing to do here.
@@ -592,24 +596,13 @@ static __init void lockup_detector_setup(void)
 	    !(watchdog_enabled && watchdog_thresh))
 		return;
 
-	ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
-						     &watchdog_allowed_mask);
-	if (ret) {
-		pr_err("Failed to initialize soft lockup detector threads\n");
-		return;
-	}
-
 	mutex_lock(&watchdog_mutex);
-	softlockup_threads_initialized = true;
 	lockup_detector_reconfigure();
+	softlockup_initialized = true;
 	mutex_unlock(&watchdog_mutex);
 }
 
 #else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static inline int watchdog_park_threads(void) { return 0; }
-static inline void watchdog_unpark_threads(void) { }
-static inline int watchdog_enable_all_cpus(void) { return 0; }
-static inline void watchdog_disable_all_cpus(void) { }
 static void lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index e449a23e9d59..1f7020d65d0a 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -175,8 +175,8 @@ static int hardlockup_detector_event_create(void)
 	evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
 					       watchdog_overflow_callback, NULL);
 	if (IS_ERR(evt)) {
-		pr_info("Perf event create on CPU %d failed with %ld\n", cpu,
-			PTR_ERR(evt));
+		pr_debug("Perf event create on CPU %d failed with %ld\n", cpu,
+			 PTR_ERR(evt));
 		return PTR_ERR(evt);
 	}
 	this_cpu_write(watchdog_ev, evt);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8838d1158d19..0b066b3c9284 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1718,7 +1718,7 @@ config KPROBES_SANITY_TEST
 	default n
 	help
 	  This option provides for testing basic kprobes functionality on
-	  boot. A sample kprobe, jprobe and kretprobe are inserted and
+	  boot. Samples of kprobe and kretprobe are inserted and
 	  verified for functionality.
 
 	  Say N if you are unsure.
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 3d35d062970d..befb127507c0 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -5,7 +5,8 @@ if HAVE_ARCH_KASAN
 
 config KASAN
 	bool "KASan: runtime memory debugger"
-	depends on SLUB || (SLAB && !DEBUG_SLAB)
+	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
+	select SLUB_DEBUG if SLUB
 	select CONSTRUCTORS
 	select STACKDEPOT
 	help
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index 19d42ea75ec2..98fa559ebd80 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -1,9 +1,6 @@
 config ARCH_HAS_UBSAN_SANITIZE_ALL
 	bool
 
-config ARCH_WANTS_UBSAN_NO_NULL
-	def_bool n
-
 config UBSAN
 	bool "Undefined behaviour sanity checker"
 	help
@@ -39,14 +36,6 @@ config UBSAN_ALIGNMENT
 	  Enabling this option on architectures that support unaligned
 	  accesses may produce a lot of false positives.
 
-config UBSAN_NULL
-	bool "Enable checking of null pointers"
-	depends on UBSAN
-	default y if !ARCH_WANTS_UBSAN_NO_NULL
-	help
-	  This option enables detection of memory accesses via a
-	  null pointer.
-
 config TEST_UBSAN
 	tristate "Module for testing for undefined behavior detection"
 	depends on m && UBSAN
diff --git a/lib/Makefile b/lib/Makefile
index 90dc5520b784..d4a3773ce4a6 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -116,6 +116,7 @@ obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
 obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
 obj-$(CONFIG_BCH) += bch.o
+CFLAGS_bch.o := $(call cc-option,-Wframe-larger-than=4500)
 obj-$(CONFIG_LZO_COMPRESS) += lzo/
 obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
 obj-$(CONFIG_LZ4_COMPRESS) += lz4/
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 53c2d5edc826..1d91e31eceec 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -178,18 +178,18 @@ long long atomic64_xchg(atomic64_t *v, long long new)
 }
 EXPORT_SYMBOL(atomic64_xchg);
 
-int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	int ret = 0;
+	long long val;
 
 	raw_spin_lock_irqsave(lock, flags);
-	if (v->counter != u) {
+	val = v->counter;
+	if (val != u)
 		v->counter += a;
-		ret = 1;
-	}
 	raw_spin_unlock_irqrestore(lock, flags);
-	return ret;
+
+	return val;
 }
-EXPORT_SYMBOL(atomic64_add_unless);
+EXPORT_SYMBOL(atomic64_fetch_add_unless);
diff --git a/lib/bch.c b/lib/bch.c
index bc89dfe4d1b3..7b0f2006698b 100644
--- a/lib/bch.c
+++ b/lib/bch.c
@@ -78,15 +78,22 @@
 #define GF_M(_p)               (CONFIG_BCH_CONST_M)
 #define GF_T(_p)               (CONFIG_BCH_CONST_T)
 #define GF_N(_p)               ((1 << (CONFIG_BCH_CONST_M))-1)
+#define BCH_MAX_M              (CONFIG_BCH_CONST_M)
 #else
 #define GF_M(_p)               ((_p)->m)
 #define GF_T(_p)               ((_p)->t)
 #define GF_N(_p)               ((_p)->n)
+#define BCH_MAX_M              15
 #endif
 
+#define BCH_MAX_T              (((1 << BCH_MAX_M) - 1) / BCH_MAX_M)
+
 #define BCH_ECC_WORDS(_p)      DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 32)
 #define BCH_ECC_BYTES(_p)      DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 8)
 
+#define BCH_ECC_MAX_WORDS      DIV_ROUND_UP(BCH_MAX_M * BCH_MAX_T, 32)
+#define BCH_ECC_MAX_BYTES      DIV_ROUND_UP(BCH_MAX_M * BCH_MAX_T, 8)
+
 #ifndef dbg
 #define dbg(_fmt, args...)     do {} while (0)
 #endif
@@ -187,7 +194,8 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	const unsigned int l = BCH_ECC_WORDS(bch)-1;
 	unsigned int i, mlen;
 	unsigned long m;
-	uint32_t w, r[l+1];
+	uint32_t w, r[BCH_ECC_MAX_WORDS];
+	const size_t r_bytes = BCH_ECC_WORDS(bch) * sizeof(*r);
 	const uint32_t * const tab0 = bch->mod8_tab;
 	const uint32_t * const tab1 = tab0 + 256*(l+1);
 	const uint32_t * const tab2 = tab1 + 256*(l+1);
@@ -198,7 +206,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 		/* load ecc parity bytes into internal 32-bit buffer */
 		load_ecc8(bch, bch->ecc_buf, ecc);
 	} else {
-		memset(bch->ecc_buf, 0, sizeof(r));
+		memset(bch->ecc_buf, 0, r_bytes);
 	}
 
 	/* process first unaligned data bytes */
@@ -215,7 +223,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	mlen  = len/4;
 	data += 4*mlen;
 	len  -= 4*mlen;
-	memcpy(r, bch->ecc_buf, sizeof(r));
+	memcpy(r, bch->ecc_buf, r_bytes);
 
 	/*
 	 * split each 32-bit word into 4 polynomials of weight 8 as follows:
@@ -241,7 +249,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 
 		r[l] = p0[l]^p1[l]^p2[l]^p3[l];
 	}
-	memcpy(bch->ecc_buf, r, sizeof(r));
+	memcpy(bch->ecc_buf, r, r_bytes);
 
 	/* process last unaligned bytes */
 	if (len)
@@ -434,7 +442,7 @@ static int solve_linear_system(struct bch_control *bch, unsigned int *rows,
 {
 	const int m = GF_M(bch);
 	unsigned int tmp, mask;
-	int rem, c, r, p, k, param[m];
+	int rem, c, r, p, k, param[BCH_MAX_M];
 
 	k = 0;
 	mask = 1 << m;
@@ -1114,7 +1122,7 @@ static int build_deg2_base(struct bch_control *bch)
 {
 	const int m = GF_M(bch);
 	int i, j, r;
-	unsigned int sum, x, y, remaining, ak = 0, xi[m];
+	unsigned int sum, x, y, remaining, ak = 0, xi[BCH_MAX_M];
 
 	/* find k s.t. Tr(a^k) = 1 and 0 <= k < m */
 	for (i = 0; i < m; i++) {
@@ -1254,7 +1262,6 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 	struct bch_control *bch = NULL;
 
 	const int min_m = 5;
-	const int max_m = 15;
 
 	/* default primitive polynomials */
 	static const unsigned int prim_poly_tab[] = {
@@ -1270,7 +1277,7 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 		goto fail;
 	}
 #endif
-	if ((m < min_m) || (m > max_m))
+	if ((m < min_m) || (m > BCH_MAX_M))
 		/*
 		 * values of m greater than 15 are not currently supported;
 		 * supporting m > 15 would require changing table base type
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 994be4805cec..70935ed91125 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -360,9 +360,12 @@ static void debug_object_is_on_stack(void *addr, int onstack)
 
 	limit++;
 	if (is_on_stack)
-		pr_warn("object is on stack, but not annotated\n");
+		pr_warn("object %p is on stack %p, but NOT annotated.\n", addr,
+			 task_stack_page(current));
 	else
-		pr_warn("object is not on stack, but annotated\n");
+		pr_warn("object %p is NOT on stack %p, but annotated.\n", addr,
+			 task_stack_page(current));
+
 	WARN_ON(1);
 }
 
@@ -1185,8 +1188,7 @@ void __init debug_objects_mem_init(void)
 
 	if (!obj_cache || debug_objects_replace_static_objects()) {
 		debug_objects_enabled = 0;
-		if (obj_cache)
-			kmem_cache_destroy(obj_cache);
+		kmem_cache_destroy(obj_cache);
 		pr_warn("out of memory.\n");
 	} else
 		debug_objects_selftest();
diff --git a/lib/ioremap.c b/lib/ioremap.c
index 54e5bbaa3200..517f5853ffed 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -92,7 +92,7 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
 		if (ioremap_pmd_enabled() &&
 		    ((next - addr) == PMD_SIZE) &&
 		    IS_ALIGNED(phys_addr + addr, PMD_SIZE) &&
-		    pmd_free_pte_page(pmd)) {
+		    pmd_free_pte_page(pmd, addr)) {
 			if (pmd_set_huge(pmd, phys_addr + addr, prot))
 				continue;
 		}
@@ -119,7 +119,7 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 		if (ioremap_pud_enabled() &&
 		    ((next - addr) == PUD_SIZE) &&
 		    IS_ALIGNED(phys_addr + addr, PUD_SIZE) &&
-		    pud_free_pmd_page(pud)) {
+		    pud_free_pmd_page(pud, addr)) {
 			if (pud_set_huge(pud, phys_addr + addr, prot))
 				continue;
 		}
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 7e43cd54c84c..8be175df3075 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -596,15 +596,70 @@ static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
 	return ret;
 }
 
+static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
+				struct iov_iter *i)
+{
+	struct pipe_inode_info *pipe = i->pipe;
+	size_t n, off, xfer = 0;
+	int idx;
+
+	if (!sanity(i))
+		return 0;
+
+	bytes = n = push_pipe(i, bytes, &idx, &off);
+	if (unlikely(!n))
+		return 0;
+	for ( ; n; idx = next_idx(idx, pipe), off = 0) {
+		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
+		unsigned long rem;
+
+		rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr,
+				chunk);
+		i->idx = idx;
+		i->iov_offset = off + chunk - rem;
+		xfer += chunk - rem;
+		if (rem)
+			break;
+		n -= chunk;
+		addr += chunk;
+	}
+	i->count -= xfer;
+	return xfer;
+}
+
+/**
+ * _copy_to_iter_mcsafe - copy to user with source-read error exception handling
+ * @addr: source kernel address
+ * @bytes: total transfer length
+ * @iter: destination iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_to_iter() for protecting read/write to persistent memory.
+ * Unless / until an architecture can guarantee identical performance
+ * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a
+ * performance regression to switch more users to the mcsafe version.
+ *
+ * Otherwise, the main differences between this and typical _copy_to_iter().
+ *
+ * * Typical tail/residue handling after a fault retries the copy
+ *   byte-by-byte until the fault happens again. Re-triggering machine
+ *   checks is potentially fatal so the implementation uses source
+ *   alignment and poison alignment assumptions to avoid re-triggering
+ *   hardware exceptions.
+ *
+ * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
+ *   Compare to copy_to_iter() where only ITER_IOVEC attempts might return
+ *   a short copy.
+ *
+ * See MCSAFE_TEST for self-test.
+ */
 size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
 	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
 
-	if (unlikely(i->type & ITER_PIPE)) {
-		WARN_ON(1);
-		return 0;
-	}
+	if (unlikely(i->type & ITER_PIPE))
+		return copy_pipe_to_iter_mcsafe(addr, bytes, i);
 	if (iter_is_iovec(i))
 		might_fault();
 	iterate_and_advance(i, bytes, v,
@@ -701,6 +756,20 @@ size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
 EXPORT_SYMBOL(_copy_from_iter_nocache);
 
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+/**
+ * _copy_from_iter_flushcache - write destination through cpu cache
+ * @addr: destination kernel address
+ * @bytes: total transfer length
+ * @iter: source iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_from_iter() for ensuring that writes to persistent memory
+ * are flushed through the CPU cache. It is differentiated from
+ * _copy_from_iter_nocache() in that guarantees all data is flushed for
+ * all iterator types. The _copy_from_iter_nocache() only attempts to
+ * bypass the cache for the ITER_IOVEC case, and on some archs may use
+ * instructions that strand dirty-data in the cache.
+ */
 size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 9bbd9c5d375a..beb14839b41a 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -141,7 +141,7 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
 	spin_lock_irqsave(&tags->lock, flags);
 
 	/* Fastpath */
-	if (likely(tags->nr_free >= 0)) {
+	if (likely(tags->nr_free)) {
 		tag = tags->freelist[--tags->nr_free];
 		spin_unlock_irqrestore(&tags->lock, flags);
 		return tag;
diff --git a/lib/raid6/s390vx.uc b/lib/raid6/s390vx.uc
index 140fa8bb5c23..914ebe98fc21 100644
--- a/lib/raid6/s390vx.uc
+++ b/lib/raid6/s390vx.uc
@@ -55,22 +55,24 @@ static inline void XOR(int x, int y, int z)
 	asm volatile ("VX %0,%1,%2" : : "i" (x), "i" (y), "i" (z));
 }
 
-static inline void LOAD_DATA(int x, int n, u8 *ptr)
+static inline void LOAD_DATA(int x, u8 *ptr)
 {
-	typedef struct { u8 _[16*n]; } addrtype;
+	typedef struct { u8 _[16 * $#]; } addrtype;
 	register addrtype *__ptr asm("1") = (addrtype *) ptr;
 
 	asm volatile ("VLM %2,%3,0,%r1"
-		      : : "m" (*__ptr), "a" (__ptr), "i" (x), "i" (x + n - 1));
+		      : : "m" (*__ptr), "a" (__ptr), "i" (x),
+			  "i" (x + $# - 1));
 }
 
-static inline void STORE_DATA(int x, int n, u8 *ptr)
+static inline void STORE_DATA(int x, u8 *ptr)
 {
-	typedef struct { u8 _[16*n]; } addrtype;
+	typedef struct { u8 _[16 * $#]; } addrtype;
 	register addrtype *__ptr asm("1") = (addrtype *) ptr;
 
 	asm volatile ("VSTM %2,%3,0,1"
-		      : "=m" (*__ptr) : "a" (__ptr), "i" (x), "i" (x + n - 1));
+		      : "=m" (*__ptr) : "a" (__ptr), "i" (x),
+			"i" (x + $# - 1));
 }
 
 static inline void COPY_VEC(int x, int y)
@@ -93,19 +95,19 @@ static void raid6_s390vx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
 	q = dptr[z0 + 2];	/* RS syndrome */
 
 	for (d = 0; d < bytes; d += $#*NSIZE) {
-		LOAD_DATA(0,$#,&dptr[z0][d]);
+		LOAD_DATA(0,&dptr[z0][d]);
 		COPY_VEC(8+$$,0+$$);
 		for (z = z0 - 1; z >= 0; z--) {
 			MASK(16+$$,8+$$);
 			AND(16+$$,16+$$,25);
 			SHLBYTE(8+$$,8+$$);
 			XOR(8+$$,8+$$,16+$$);
-			LOAD_DATA(16,$#,&dptr[z][d]);
+			LOAD_DATA(16,&dptr[z][d]);
 			XOR(0+$$,0+$$,16+$$);
 			XOR(8+$$,8+$$,16+$$);
 		}
-		STORE_DATA(0,$#,&p[d]);
-		STORE_DATA(8,$#,&q[d]);
+		STORE_DATA(0,&p[d]);
+		STORE_DATA(8,&q[d]);
 	}
 	kernel_fpu_end(&vxstate, KERNEL_VXR);
 }
@@ -127,14 +129,14 @@ static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop,
 
 	for (d = 0; d < bytes; d += $#*NSIZE) {
 		/* P/Q data pages */
-		LOAD_DATA(0,$#,&dptr[z0][d]);
+		LOAD_DATA(0,&dptr[z0][d]);
 		COPY_VEC(8+$$,0+$$);
 		for (z = z0 - 1; z >= start; z--) {
 			MASK(16+$$,8+$$);
 			AND(16+$$,16+$$,25);
 			SHLBYTE(8+$$,8+$$);
 			XOR(8+$$,8+$$,16+$$);
-			LOAD_DATA(16,$#,&dptr[z][d]);
+			LOAD_DATA(16,&dptr[z][d]);
 			XOR(0+$$,0+$$,16+$$);
 			XOR(8+$$,8+$$,16+$$);
 		}
@@ -145,12 +147,12 @@ static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop,
 			SHLBYTE(8+$$,8+$$);
 			XOR(8+$$,8+$$,16+$$);
 		}
-		LOAD_DATA(16,$#,&p[d]);
+		LOAD_DATA(16,&p[d]);
 		XOR(16+$$,16+$$,0+$$);
-		STORE_DATA(16,$#,&p[d]);
-		LOAD_DATA(16,$#,&q[d]);
+		STORE_DATA(16,&p[d]);
+		LOAD_DATA(16,&q[d]);
 		XOR(16+$$,16+$$,8+$$);
-		STORE_DATA(16,$#,&q[d]);
+		STORE_DATA(16,&q[d]);
 	}
 	kernel_fpu_end(&vxstate, KERNEL_VXR);
 }
diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c
index d8bb1a1eba72..e5fdc8b9e856 100644
--- a/lib/reed_solomon/reed_solomon.c
+++ b/lib/reed_solomon/reed_solomon.c
@@ -283,7 +283,7 @@ out:
  *		in index form
  *  @prim:	primitive element to generate polynomial roots
  *  @nroots:	RS code generator polynomial degree (number of roots)
- *  @gfp:	GFP_ flags for allocations
+ *  @gfp:	Memory allocation flags.
  */
 struct rs_control *init_rs_gfp(int symsize, int gfpoly, int fcr, int prim,
 			       int nroots, gfp_t gfp)
diff --git a/lib/refcount.c b/lib/refcount.c
index d3b81cefce91..ebcf8cd49e05 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -35,13 +35,13 @@
  *
  */
 
+#include <linux/mutex.h>
 #include <linux/refcount.h>
+#include <linux/spinlock.h>
 #include <linux/bug.h>
 
-#ifdef CONFIG_REFCOUNT_FULL
-
 /**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * refcount_add_not_zero_checked - add a value to a refcount unless it is 0
  * @i: the value to add to the refcount
  * @r: the refcount
  *
@@ -58,7 +58,7 @@
  *
  * Return: false if the passed refcount is 0, true otherwise
  */
-bool refcount_add_not_zero(unsigned int i, refcount_t *r)
+bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -79,10 +79,10 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 
 	return true;
 }
-EXPORT_SYMBOL(refcount_add_not_zero);
+EXPORT_SYMBOL(refcount_add_not_zero_checked);
 
 /**
- * refcount_add - add a value to a refcount
+ * refcount_add_checked - add a value to a refcount
  * @i: the value to add to the refcount
  * @r: the refcount
  *
@@ -97,14 +97,14 @@ EXPORT_SYMBOL(refcount_add_not_zero);
  * cases, refcount_inc(), or one of its variants, should instead be used to
  * increment a reference count.
  */
-void refcount_add(unsigned int i, refcount_t *r)
+void refcount_add_checked(unsigned int i, refcount_t *r)
 {
-	WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n");
 }
-EXPORT_SYMBOL(refcount_add);
+EXPORT_SYMBOL(refcount_add_checked);
 
 /**
- * refcount_inc_not_zero - increment a refcount unless it is 0
+ * refcount_inc_not_zero_checked - increment a refcount unless it is 0
  * @r: the refcount to increment
  *
  * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN.
@@ -115,7 +115,7 @@ EXPORT_SYMBOL(refcount_add);
  *
  * Return: true if the increment was successful, false otherwise
  */
-bool refcount_inc_not_zero(refcount_t *r)
+bool refcount_inc_not_zero_checked(refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -134,10 +134,10 @@ bool refcount_inc_not_zero(refcount_t *r)
 
 	return true;
 }
-EXPORT_SYMBOL(refcount_inc_not_zero);
+EXPORT_SYMBOL(refcount_inc_not_zero_checked);
 
 /**
- * refcount_inc - increment a refcount
+ * refcount_inc_checked - increment a refcount
  * @r: the refcount to increment
  *
  * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN.
@@ -148,14 +148,14 @@ EXPORT_SYMBOL(refcount_inc_not_zero);
  * Will WARN if the refcount is 0, as this represents a possible use-after-free
  * condition.
  */
-void refcount_inc(refcount_t *r)
+void refcount_inc_checked(refcount_t *r)
 {
-	WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n");
 }
-EXPORT_SYMBOL(refcount_inc);
+EXPORT_SYMBOL(refcount_inc_checked);
 
 /**
- * refcount_sub_and_test - subtract from a refcount and test if it is 0
+ * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0
  * @i: amount to subtract from the refcount
  * @r: the refcount
  *
@@ -174,7 +174,7 @@ EXPORT_SYMBOL(refcount_inc);
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -192,10 +192,10 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 
 	return !new;
 }
-EXPORT_SYMBOL(refcount_sub_and_test);
+EXPORT_SYMBOL(refcount_sub_and_test_checked);
 
 /**
- * refcount_dec_and_test - decrement a refcount and test if it is 0
+ * refcount_dec_and_test_checked - decrement a refcount and test if it is 0
  * @r: the refcount
  *
  * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
@@ -207,14 +207,14 @@ EXPORT_SYMBOL(refcount_sub_and_test);
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-bool refcount_dec_and_test(refcount_t *r)
+bool refcount_dec_and_test_checked(refcount_t *r)
 {
-	return refcount_sub_and_test(1, r);
+	return refcount_sub_and_test_checked(1, r);
 }
-EXPORT_SYMBOL(refcount_dec_and_test);
+EXPORT_SYMBOL(refcount_dec_and_test_checked);
 
 /**
- * refcount_dec - decrement a refcount
+ * refcount_dec_checked - decrement a refcount
  * @r: the refcount
  *
  * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
@@ -223,12 +223,11 @@ EXPORT_SYMBOL(refcount_dec_and_test);
  * Provides release memory ordering, such that prior loads and stores are done
  * before.
  */
-void refcount_dec(refcount_t *r)
+void refcount_dec_checked(refcount_t *r)
 {
-	WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+	WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n");
 }
-EXPORT_SYMBOL(refcount_dec);
-#endif /* CONFIG_REFCOUNT_FULL */
+EXPORT_SYMBOL(refcount_dec_checked);
 
 /**
  * refcount_dec_if_one - decrement a refcount if it is 1
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 9427b5766134..e5c8586cf717 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -774,7 +774,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter)
 				skip++;
 				if (list == iter->list) {
 					iter->p = p;
-					skip = skip;
+					iter->skip = skip;
 					goto found;
 				}
 			}
@@ -964,8 +964,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_stop);
 
 static size_t rounded_hashtable_size(const struct rhashtable_params *params)
 {
-	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
-		   (unsigned long)params->min_size);
+	size_t retsize;
+
+	if (params->nelem_hint)
+		retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
+			      (unsigned long)params->min_size);
+	else
+		retsize = max(HASH_DEFAULT_SIZE,
+			      (unsigned long)params->min_size);
+
+	return retsize;
 }
 
 static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
@@ -1022,8 +1030,6 @@ int rhashtable_init(struct rhashtable *ht,
 	struct bucket_table *tbl;
 	size_t size;
 
-	size = HASH_DEFAULT_SIZE;
-
 	if ((!params->key_len && !params->obj_hashfn) ||
 	    (params->obj_hashfn && !params->obj_cmpfn))
 		return -EINVAL;
@@ -1050,8 +1056,7 @@ int rhashtable_init(struct rhashtable *ht,
 
 	ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE);
 
-	if (params->nelem_hint)
-		size = rounded_hashtable_size(&ht->p);
+	size = rounded_hashtable_size(&ht->p);
 
 	if (params->locks_mul)
 		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
@@ -1143,13 +1148,14 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 				 void (*free_fn)(void *ptr, void *arg),
 				 void *arg)
 {
-	struct bucket_table *tbl;
+	struct bucket_table *tbl, *next_tbl;
 	unsigned int i;
 
 	cancel_work_sync(&ht->run_work);
 
 	mutex_lock(&ht->mutex);
 	tbl = rht_dereference(ht->tbl, ht);
+restart:
 	if (free_fn) {
 		for (i = 0; i < tbl->size; i++) {
 			struct rhash_head *pos, *next;
@@ -1166,7 +1172,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 		}
 	}
 
+	next_tbl = rht_dereference(tbl->future_tbl, ht);
 	bucket_table_free(tbl);
+	if (next_tbl) {
+		tbl = next_tbl;
+		goto restart;
+	}
 	mutex_unlock(&ht->mutex);
 }
 EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 1642fd507a96..7c6096a71704 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -24,9 +24,6 @@
  **/
 struct scatterlist *sg_next(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	if (sg_is_last(sg))
 		return NULL;
 
@@ -111,10 +108,7 @@ struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
 	for_each_sg(sgl, sg, nents, i)
 		ret = sg;
 
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sgl[0].sg_magic != SG_MAGIC);
 	BUG_ON(!sg_is_last(ret));
-#endif
 	return ret;
 }
 EXPORT_SYMBOL(sg_last);
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 60aedc879361..08d3d59dca17 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -5282,21 +5282,31 @@ static struct bpf_test tests[] = {
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Ctx heavy transformations",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC,
+#endif
 		{ },
 		{
 			{  1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
 			{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
 		},
 		.fill_helper = bpf_fill_maxinsns6,
+		.expected_errcode = -ENOTSUPP,
 	},
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Call heavy transformations",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC | FLAG_NO_DATA,
+#endif
 		{ },
 		{ { 1, 0 }, { 10, 0 } },
 		.fill_helper = bpf_fill_maxinsns7,
+		.expected_errcode = -ENOTSUPP,
 	},
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Jump heavy test",
@@ -5347,18 +5357,28 @@ static struct bpf_test tests[] = {
 	{
 		"BPF_MAXINSNS: exec all MSH",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC,
+#endif
 		{ 0xfa, 0xfb, 0xfc, 0xfd, },
 		{ { 4, 0xababab83 } },
 		.fill_helper = bpf_fill_maxinsns13,
+		.expected_errcode = -ENOTSUPP,
 	},
 	{
 		"BPF_MAXINSNS: ld_abs+get_processor_id",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC,
+#endif
 		{ },
 		{ { 1, 0xbee } },
 		.fill_helper = bpf_fill_ld_abs_get_processor_id,
+		.expected_errcode = -ENOTSUPP,
 	},
 	/*
 	 * LD_IND / LD_ABS on fragmented SKBs
diff --git a/lib/test_printf.c b/lib/test_printf.c
index b2aa8f514844..cea592f402ed 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -260,13 +260,6 @@ plain(void)
 {
 	int err;
 
-	/*
-	 * Make sure crng is ready. Otherwise we get "(ptrval)" instead
-	 * of a hashed address when printing '%p' in plain_hash() and
-	 * plain_format().
-	 */
-	wait_for_random_bytes();
-
 	err = plain_hash();
 	if (err) {
 		pr_warn("plain 'p' does not appear to be hashed\n");
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 9e197987b67d..97db0e8e362b 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -21,6 +21,53 @@
 
 #include "internal.h"
 
+/**
+ * DOC: bootmem overview
+ *
+ * Bootmem is a boot-time physical memory allocator and configurator.
+ *
+ * It is used early in the boot process before the page allocator is
+ * set up.
+ *
+ * Bootmem is based on the most basic of allocators, a First Fit
+ * allocator which uses a bitmap to represent memory. If a bit is 1,
+ * the page is allocated and 0 if unallocated. To satisfy allocations
+ * of sizes smaller than a page, the allocator records the Page Frame
+ * Number (PFN) of the last allocation and the offset the allocation
+ * ended at. Subsequent small allocations are merged together and
+ * stored on the same page.
+ *
+ * The information used by the bootmem allocator is represented by
+ * :c:type:`struct bootmem_data`. An array to hold up to %MAX_NUMNODES
+ * such structures is statically allocated and then it is discarded
+ * when the system initialization completes. Each entry in this array
+ * corresponds to a node with memory. For UMA systems only entry 0 is
+ * used.
+ *
+ * The bootmem allocator is initialized during early architecture
+ * specific setup. Each architecture is required to supply a
+ * :c:func:`setup_arch` function which, among other tasks, is
+ * responsible for acquiring the necessary parameters to initialise
+ * the boot memory allocator. These parameters define limits of usable
+ * physical memory:
+ *
+ * * @min_low_pfn - the lowest PFN that is available in the system
+ * * @max_low_pfn - the highest PFN that may be addressed by low
+ *   memory (%ZONE_NORMAL)
+ * * @max_pfn - the last PFN available to the system.
+ *
+ * After those limits are determined, the :c:func:`init_bootmem` or
+ * :c:func:`init_bootmem_node` function should be called to initialize
+ * the bootmem allocator. The UMA case should use the `init_bootmem`
+ * function. It will initialize ``contig_page_data`` structure that
+ * represents the only memory node in the system. In the NUMA case the
+ * `init_bootmem_node` function should be called to initialize the
+ * bootmem allocator for each node.
+ *
+ * Once the allocator is set up, it is possible to use either single
+ * node or NUMA variant of the allocation APIs.
+ */
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 struct pglist_data __refdata contig_page_data = {
 	.bdata = &bootmem_node_data[0]
@@ -62,6 +109,8 @@ static unsigned long __init bootmap_bytes(unsigned long pages)
 /**
  * bootmem_bootmap_pages - calculate bitmap size in pages
  * @pages: number of pages the bitmap has to represent
+ *
+ * Return: the number of pages needed to hold the bitmap.
  */
 unsigned long __init bootmem_bootmap_pages(unsigned long pages)
 {
@@ -121,7 +170,7 @@ static unsigned long __init init_bootmem_core(bootmem_data_t *bdata,
  * @startpfn: first pfn on the node
  * @endpfn: first pfn after the node
  *
- * Returns the number of bytes needed to hold the bitmap for this node.
+ * Return: the number of bytes needed to hold the bitmap for this node.
  */
 unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
 				unsigned long startpfn, unsigned long endpfn)
@@ -134,7 +183,7 @@ unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
  * @start: pfn where the bitmap is to be placed
  * @pages: number of available physical pages
  *
- * Returns the number of bytes needed to hold the bitmap.
+ * Return: the number of bytes needed to hold the bitmap.
  */
 unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 {
@@ -143,15 +192,6 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
 }
 
-/*
- * free_bootmem_late - free bootmem pages directly to page allocator
- * @addr: starting physical address of the range
- * @size: size of the range in bytes
- *
- * This is only useful when the bootmem allocator has already been torn
- * down, but we are still initializing the system.  Pages are given directly
- * to the page allocator, no bootmem metadata is updated because it is gone.
- */
 void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
 {
 	unsigned long cursor, end;
@@ -264,11 +304,6 @@ void __init reset_all_zones_managed_pages(void)
 	reset_managed_pages_done = 1;
 }
 
-/**
- * free_all_bootmem - release free pages to the buddy allocator
- *
- * Returns the number of pages actually released.
- */
 unsigned long __init free_all_bootmem(void)
 {
 	unsigned long total_pages = 0;
@@ -385,16 +420,6 @@ static int __init mark_bootmem(unsigned long start, unsigned long end,
 	BUG();
 }
 
-/**
- * free_bootmem_node - mark a page range as usable
- * @pgdat: node the range resides on
- * @physaddr: starting address of the range
- * @size: size of the range in bytes
- *
- * Partial pages will be considered reserved and left as they are.
- *
- * The range must reside completely on the specified node.
- */
 void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 			      unsigned long size)
 {
@@ -408,15 +433,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 	mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
 }
 
-/**
- * free_bootmem - mark a page range as usable
- * @physaddr: starting physical address of the range
- * @size: size of the range in bytes
- *
- * Partial pages will be considered reserved and left as they are.
- *
- * The range must be contiguous but may span node boundaries.
- */
 void __init free_bootmem(unsigned long physaddr, unsigned long size)
 {
 	unsigned long start, end;
@@ -439,6 +455,8 @@ void __init free_bootmem(unsigned long physaddr, unsigned long size)
  * Partial pages will be reserved.
  *
  * The range must reside completely on the specified node.
+ *
+ * Return: 0 on success, -errno on failure.
  */
 int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 				 unsigned long size, int flags)
@@ -460,6 +478,8 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
  * Partial pages will be reserved.
  *
  * The range must be contiguous but may span node boundaries.
+ *
+ * Return: 0 on success, -errno on failure.
  */
 int __init reserve_bootmem(unsigned long addr, unsigned long size,
 			    int flags)
@@ -646,19 +666,6 @@ restart:
 	return NULL;
 }
 
-/**
- * __alloc_bootmem_nopanic - allocate boot memory without panicking
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may happen on any node in the system.
- *
- * Returns NULL on failure.
- */
 void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
 					unsigned long goal)
 {
@@ -682,19 +689,6 @@ static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
 	return NULL;
 }
 
-/**
- * __alloc_bootmem - allocate boot memory
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may happen on any node in the system.
- *
- * The function panics if the request can not be satisfied.
- */
 void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 			      unsigned long goal)
 {
@@ -754,21 +748,6 @@ void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 	return NULL;
 }
 
-/**
- * __alloc_bootmem_node - allocate boot memory from a specific node
- * @pgdat: node to allocate from
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may fall back to any node in the system if the specified node
- * can not hold the requested memory.
- *
- * The function panics if the request can not be satisfied.
- */
 void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
@@ -807,19 +786,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 
 }
 
-/**
- * __alloc_bootmem_low - allocate low boot memory
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may happen on any node in the system.
- *
- * The function panics if the request can not be satisfied.
- */
 void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 				  unsigned long goal)
 {
@@ -834,21 +800,6 @@ void * __init __alloc_bootmem_low_nopanic(unsigned long size,
 					ARCH_LOW_ADDRESS_LIMIT);
 }
 
-/**
- * __alloc_bootmem_low_node - allocate low boot memory from a specific node
- * @pgdat: node to allocate from
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may fall back to any node in the system if the specified node
- * can not hold the requested memory.
- *
- * The function panics if the request can not be satisfied.
- */
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
 {
diff --git a/mm/debug.c b/mm/debug.c
index 56e2d9125ea5..38c926520c97 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -43,12 +43,25 @@ const struct trace_print_flags vmaflag_names[] = {
 
 void __dump_page(struct page *page, const char *reason)
 {
+	bool page_poisoned = PagePoisoned(page);
+	int mapcount;
+
+	/*
+	 * If struct page is poisoned don't access Page*() functions as that
+	 * leads to recursive loop. Page*() check for poisoned pages, and calls
+	 * dump_page() when detected.
+	 */
+	if (page_poisoned) {
+		pr_emerg("page:%px is uninitialized and poisoned", page);
+		goto hex_only;
+	}
+
 	/*
 	 * Avoid VM_BUG_ON() in page_mapcount().
 	 * page->_mapcount space in struct page is used by sl[aou]b pages to
 	 * encode own info.
 	 */
-	int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
+	mapcount = PageSlab(page) ? 0 : page_mapcount(page);
 
 	pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
 		  page, page_ref_count(page), mapcount,
@@ -60,6 +73,7 @@ void __dump_page(struct page *page, const char *reason)
 
 	pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags);
 
+hex_only:
 	print_hex_dump(KERN_ALERT, "raw: ", DUMP_PREFIX_NONE, 32,
 			sizeof(unsigned long), page,
 			sizeof(struct page), false);
@@ -68,7 +82,7 @@ void __dump_page(struct page *page, const char *reason)
 		pr_alert("page dumped because: %s\n", reason);
 
 #ifdef CONFIG_MEMCG
-	if (page->mem_cgroup)
+	if (!page_poisoned && page->mem_cgroup)
 		pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup);
 #endif
 }
diff --git a/mm/gup.c b/mm/gup.c
index b70d7ba7cc13..fc5f98069f4e 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1238,8 +1238,6 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 	int locked = 0;
 	long ret = 0;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
-	VM_BUG_ON(len != PAGE_ALIGN(len));
 	end = start + len;
 
 	for (nstart = start; nstart < end; nstart = nend) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1cd7c1a57a14..a9e1e093df51 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -552,7 +552,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) {
+	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1142,7 +1142,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd,
 		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, vma,
 					       vmf->address, page_to_nid(page));
 		if (unlikely(!pages[i] ||
-			     mem_cgroup_try_charge(pages[i], vma->vm_mm,
+			     mem_cgroup_try_charge_delay(pages[i], vma->vm_mm,
 				     GFP_KERNEL, &memcg, false))) {
 			if (pages[i])
 				put_page(pages[i]);
@@ -1312,7 +1312,7 @@ alloc:
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
+	if (unlikely(mem_cgroup_try_charge_delay(new_page, vma->vm_mm,
 					huge_gfp, &memcg, true))) {
 		put_page(new_page);
 		split_huge_pmd(vma, vmf->pmd, vmf->address);
@@ -2084,6 +2084,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		if (vma_is_dax(vma))
 			return;
 		page = pmd_page(_pmd);
+		if (!PageDirty(page) && pmd_dirty(_pmd))
+			set_page_dirty(page);
 		if (!PageReferenced(page) && pmd_young(_pmd))
 			SetPageReferenced(page);
 		page_remove_rmap(page, true);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3612fbb32e9d..3103099f64fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2163,6 +2163,7 @@ static void __init gather_bootmem_prealloc(void)
 		 */
 		if (hstate_is_gigantic(h))
 			adjust_managed_page_count(page, 1 << h->order);
+		cond_resched();
 	}
 }
 
@@ -3166,6 +3167,13 @@ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf)
 	return 0;
 }
 
+/*
+ * When a new function is introduced to vm_operations_struct and added
+ * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops.
+ * This is because under System V memory model, mappings created via
+ * shmget/shmat with "huge page" specified are backed by hugetlbfs files,
+ * their original vm_ops are overwritten with shm_vm_ops.
+ */
 const struct vm_operations_struct hugetlb_vm_ops = {
 	.fault = hugetlb_vm_op_fault,
 	.open = hugetlb_vm_op_open,
diff --git a/mm/init-mm.c b/mm/init-mm.c
index f0179c9c04c2..a787a319211e 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -15,6 +15,16 @@
 #define INIT_MM_CONTEXT(name)
 #endif
 
+/*
+ * For dynamically allocated mm_structs, there is a dynamically sized cpumask
+ * at the end of the structure, the size of which depends on the maximum CPU
+ * number the system can see. That way we allocate only as much memory for
+ * mm_cpumask() as needed for the hundreds, or thousands of processes that
+ * a system typically runs.
+ *
+ * Since there is only one init_mm in the entire system, keep it simple
+ * and size this cpu_bitmask to NR_CPUS.
+ */
 struct mm_struct init_mm = {
 	.mm_rb		= RB_ROOT,
 	.pgd		= swapper_pg_dir,
@@ -25,5 +35,6 @@ struct mm_struct init_mm = {
 	.arg_lock	=  __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
 	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
 	.user_ns	= &init_user_ns,
+	.cpu_bitmap	= { [BITS_TO_LONGS(NR_CPUS)] = 0},
 	INIT_MM_CONTEXT(init_mm)
 };
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index f185455b3406..c3bd5209da38 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -619,12 +619,13 @@ void kasan_kfree_large(void *ptr, unsigned long ip)
 int kasan_module_alloc(void *addr, size_t size)
 {
 	void *ret;
+	size_t scaled_size;
 	size_t shadow_size;
 	unsigned long shadow_start;
 
 	shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
-	shadow_size = round_up(size >> KASAN_SHADOW_SCALE_SHIFT,
-			PAGE_SIZE);
+	scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT;
+	shadow_size = round_up(scaled_size, PAGE_SIZE);
 
 	if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
 		return -EINVAL;
diff --git a/mm/memblock.c b/mm/memblock.c
index 03d48d8835ba..b4ad05764745 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -20,12 +20,68 @@
 #include <linux/kmemleak.h>
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 
 #include <asm/sections.h>
 #include <linux/io.h>
 
 #include "internal.h"
 
+/**
+ * DOC: memblock overview
+ *
+ * Memblock is a method of managing memory regions during the early
+ * boot period when the usual kernel memory allocators are not up and
+ * running.
+ *
+ * Memblock views the system memory as collections of contiguous
+ * regions. There are several types of these collections:
+ *
+ * * ``memory`` - describes the physical memory available to the
+ *   kernel; this may differ from the actual physical memory installed
+ *   in the system, for instance when the memory is restricted with
+ *   ``mem=`` command line parameter
+ * * ``reserved`` - describes the regions that were allocated
+ * * ``physmap`` - describes the actual physical memory regardless of
+ *   the possible restrictions; the ``physmap`` type is only available
+ *   on some architectures.
+ *
+ * Each region is represented by :c:type:`struct memblock_region` that
+ * defines the region extents, its attributes and NUMA node id on NUMA
+ * systems. Every memory type is described by the :c:type:`struct
+ * memblock_type` which contains an array of memory regions along with
+ * the allocator metadata. The memory types are nicely wrapped with
+ * :c:type:`struct memblock`. This structure is statically initialzed
+ * at build time. The region arrays for the "memory" and "reserved"
+ * types are initially sized to %INIT_MEMBLOCK_REGIONS and for the
+ * "physmap" type to %INIT_PHYSMEM_REGIONS.
+ * The :c:func:`memblock_allow_resize` enables automatic resizing of
+ * the region arrays during addition of new regions. This feature
+ * should be used with care so that memory allocated for the region
+ * array will not overlap with areas that should be reserved, for
+ * example initrd.
+ *
+ * The early architecture setup should tell memblock what the physical
+ * memory layout is by using :c:func:`memblock_add` or
+ * :c:func:`memblock_add_node` functions. The first function does not
+ * assign the region to a NUMA node and it is appropriate for UMA
+ * systems. Yet, it is possible to use it on NUMA systems as well and
+ * assign the region to a NUMA node later in the setup process using
+ * :c:func:`memblock_set_node`. The :c:func:`memblock_add_node`
+ * performs such an assignment directly.
+ *
+ * Once memblock is setup the memory can be allocated using either
+ * memblock or bootmem APIs.
+ *
+ * As the system boot progresses, the architecture specific
+ * :c:func:`mem_init` function frees all the memory to the buddy page
+ * allocator.
+ *
+ * If an architecure enables %CONFIG_ARCH_DISCARD_MEMBLOCK, the
+ * memblock data structures will be discarded after the system
+ * initialization compltes.
+ */
+
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
@@ -60,7 +116,7 @@ static int memblock_can_resize __initdata_memblock;
 static int memblock_memory_in_slab __initdata_memblock = 0;
 static int memblock_reserved_in_slab __initdata_memblock = 0;
 
-ulong __init_memblock choose_memblock_flags(void)
+enum memblock_flags __init_memblock choose_memblock_flags(void)
 {
 	return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE;
 }
@@ -92,10 +148,11 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
 	return i < type->cnt;
 }
 
-/*
+/**
  * __memblock_find_range_bottom_up - find free area utility in bottom-up
  * @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ *       %MEMBLOCK_ALLOC_ACCESSIBLE
  * @size: size of free area to find
  * @align: alignment of free area to find
  * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
@@ -103,13 +160,13 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
  *
  * Utility called from memblock_find_in_range_node(), find free area bottom-up.
  *
- * RETURNS:
+ * Return:
  * Found address on success, 0 on failure.
  */
 static phys_addr_t __init_memblock
 __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
 				phys_addr_t size, phys_addr_t align, int nid,
-				ulong flags)
+				enum memblock_flags flags)
 {
 	phys_addr_t this_start, this_end, cand;
 	u64 i;
@@ -129,7 +186,8 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
 /**
  * __memblock_find_range_top_down - find free area utility, in top-down
  * @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ *       %MEMBLOCK_ALLOC_ACCESSIBLE
  * @size: size of free area to find
  * @align: alignment of free area to find
  * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
@@ -137,13 +195,13 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
  *
  * Utility called from memblock_find_in_range_node(), find free area top-down.
  *
- * RETURNS:
+ * Return:
  * Found address on success, 0 on failure.
  */
 static phys_addr_t __init_memblock
 __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
 			       phys_addr_t size, phys_addr_t align, int nid,
-			       ulong flags)
+			       enum memblock_flags flags)
 {
 	phys_addr_t this_start, this_end, cand;
 	u64 i;
@@ -169,7 +227,8 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
  * @size: size of free area to find
  * @align: alignment of free area to find
  * @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ *       %MEMBLOCK_ALLOC_ACCESSIBLE
  * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
  * @flags: pick from blocks based on memory attributes
  *
@@ -183,12 +242,13 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
  *
  * If bottom-up allocation failed, will try to allocate memory top-down.
  *
- * RETURNS:
+ * Return:
  * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 					phys_addr_t align, phys_addr_t start,
-					phys_addr_t end, int nid, ulong flags)
+					phys_addr_t end, int nid,
+					enum memblock_flags flags)
 {
 	phys_addr_t kernel_end, ret;
 
@@ -227,7 +287,8 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 		 * so we use WARN_ONCE() here to see the stack trace if
 		 * fail happens.
 		 */
-		WARN_ONCE(1, "memblock: bottom-up allocation failed, memory hotunplug may be affected\n");
+		WARN_ONCE(IS_ENABLED(CONFIG_MEMORY_HOTREMOVE),
+			  "memblock: bottom-up allocation failed, memory hotremove may be affected\n");
 	}
 
 	return __memblock_find_range_top_down(start, end, size, align, nid,
@@ -237,13 +298,14 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 /**
  * memblock_find_in_range - find free area in given range
  * @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ *       %MEMBLOCK_ALLOC_ACCESSIBLE
  * @size: size of free area to find
  * @align: alignment of free area to find
  *
  * Find @size free area aligned to @align in the specified range.
  *
- * RETURNS:
+ * Return:
  * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
@@ -251,7 +313,7 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					phys_addr_t align)
 {
 	phys_addr_t ret;
-	ulong flags = choose_memblock_flags();
+	enum memblock_flags flags = choose_memblock_flags();
 
 again:
 	ret = memblock_find_in_range_node(size, align, start, end,
@@ -287,7 +349,7 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 
 #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
 /**
- * Discard memory and reserved arrays if they were allocated
+ * memblock_discard - discard memory and reserved arrays if they were allocated
  */
 void __init memblock_discard(void)
 {
@@ -317,11 +379,11 @@ void __init memblock_discard(void)
  *
  * Double the size of the @type regions array. If memblock is being used to
  * allocate memory for a new reserved regions array and there is a previously
- * allocated memory range [@new_area_start,@new_area_start+@new_area_size]
+ * allocated memory range [@new_area_start, @new_area_start + @new_area_size]
  * waiting to be reserved, ensure the memory used by the new array does
  * not overlap.
  *
- * RETURNS:
+ * Return:
  * 0 on success, -1 on failure.
  */
 static int __init_memblock memblock_double_array(struct memblock_type *type,
@@ -466,13 +528,14 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
  * @nid:	node id of the new region
  * @flags:	flags of the new region
  *
- * Insert new memblock region [@base,@base+@size) into @type at @idx.
+ * Insert new memblock region [@base, @base + @size) into @type at @idx.
  * @type must already have extra room to accommodate the new region.
  */
 static void __init_memblock memblock_insert_region(struct memblock_type *type,
 						   int idx, phys_addr_t base,
 						   phys_addr_t size,
-						   int nid, unsigned long flags)
+						   int nid,
+						   enum memblock_flags flags)
 {
 	struct memblock_region *rgn = &type->regions[idx];
 
@@ -494,17 +557,17 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
  * @nid: nid of the new region
  * @flags: flags of the new region
  *
- * Add new memblock region [@base,@base+@size) into @type.  The new region
+ * Add new memblock region [@base, @base + @size) into @type.  The new region
  * is allowed to overlap with existing ones - overlaps don't affect already
  * existing regions.  @type is guaranteed to be minimal (all neighbouring
  * compatible regions are merged) after the addition.
  *
- * RETURNS:
+ * Return:
  * 0 on success, -errno on failure.
  */
 int __init_memblock memblock_add_range(struct memblock_type *type,
 				phys_addr_t base, phys_addr_t size,
-				int nid, unsigned long flags)
+				int nid, enum memblock_flags flags)
 {
 	bool insert = false;
 	phys_addr_t obase = base;
@@ -588,12 +651,35 @@ repeat:
 	}
 }
 
+/**
+ * memblock_add_node - add new memblock region within a NUMA node
+ * @base: base address of the new region
+ * @size: size of the new region
+ * @nid: nid of the new region
+ *
+ * Add new memblock region [@base, @base + @size) to the "memory"
+ * type. See memblock_add_range() description for mode details
+ *
+ * Return:
+ * 0 on success, -errno on failure.
+ */
 int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
 				       int nid)
 {
 	return memblock_add_range(&memblock.memory, base, size, nid, 0);
 }
 
+/**
+ * memblock_add - add new memblock region
+ * @base: base address of the new region
+ * @size: size of the new region
+ *
+ * Add new memblock region [@base, @base + @size) to the "memory"
+ * type. See memblock_add_range() description for mode details
+ *
+ * Return:
+ * 0 on success, -errno on failure.
+ */
 int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
 	phys_addr_t end = base + size - 1;
@@ -613,11 +699,11 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
  * @end_rgn: out parameter for the end of isolated region
  *
  * Walk @type and ensure that regions don't cross the boundaries defined by
- * [@base,@base+@size).  Crossing regions are split at the boundaries,
+ * [@base, @base + @size).  Crossing regions are split at the boundaries,
  * which may create at most two more regions.  The index of the first
  * region inside the range is returned in *@start_rgn and end in *@end_rgn.
  *
- * RETURNS:
+ * Return:
  * 0 on success, -errno on failure.
  */
 static int __init_memblock memblock_isolate_range(struct memblock_type *type,
@@ -728,10 +814,15 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 }
 
 /**
+ * memblock_setclr_flag - set or clear flag for a memory region
+ * @base: base address of the region
+ * @size: size of the region
+ * @set: set or clear the flag
+ * @flag: the flag to udpate
  *
  * This function isolates region [@base, @base + @size), and sets/clears flag
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 static int __init_memblock memblock_setclr_flag(phys_addr_t base,
 				phys_addr_t size, int set, int flag)
@@ -758,7 +849,7 @@ static int __init_memblock memblock_setclr_flag(phys_addr_t base,
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
 {
@@ -770,7 +861,7 @@ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
 {
@@ -782,7 +873,7 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
 {
@@ -796,7 +887,7 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
 {
@@ -808,7 +899,7 @@ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
 {
@@ -873,7 +964,8 @@ void __init_memblock __next_reserved_mem_region(u64 *idx,
  * As both region arrays are sorted, the function advances the two indices
  * in lockstep and returns each intersection.
  */
-void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
+void __init_memblock __next_mem_range(u64 *idx, int nid,
+				      enum memblock_flags flags,
 				      struct memblock_type *type_a,
 				      struct memblock_type *type_b,
 				      phys_addr_t *out_start,
@@ -968,9 +1060,6 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
 /**
  * __next_mem_range_rev - generic next function for for_each_*_range_rev()
  *
- * Finds the next range from type_a which is not marked as unsuitable
- * in type_b.
- *
  * @idx: pointer to u64 loop variable
  * @nid: node selector, %NUMA_NO_NODE for all nodes
  * @flags: pick from blocks based on memory attributes
@@ -980,9 +1069,13 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
  * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @out_nid: ptr to int for nid of the range, can be %NULL
  *
+ * Finds the next range from type_a which is not marked as unsuitable
+ * in type_b.
+ *
  * Reverse of __next_mem_range().
  */
-void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags,
+void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
+					  enum memblock_flags flags,
 					  struct memblock_type *type_a,
 					  struct memblock_type *type_b,
 					  phys_addr_t *out_start,
@@ -1114,10 +1207,10 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid,
  * @type: memblock type to set node ID for
  * @nid: node ID to set
  *
- * Set the nid of memblock @type regions in [@base,@base+@size) to @nid.
+ * Set the nid of memblock @type regions in [@base, @base + @size) to @nid.
  * Regions which cross the area boundaries are split as necessary.
  *
- * RETURNS:
+ * Return:
  * 0 on success, -errno on failure.
  */
 int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
@@ -1140,7 +1233,8 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
 
 static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t start,
-					phys_addr_t end, int nid, ulong flags)
+					phys_addr_t end, int nid,
+					enum memblock_flags flags)
 {
 	phys_addr_t found;
 
@@ -1162,7 +1256,7 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 
 phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
 					phys_addr_t start, phys_addr_t end,
-					ulong flags)
+					enum memblock_flags flags)
 {
 	return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE,
 					flags);
@@ -1170,14 +1264,14 @@ phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
 
 phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t max_addr,
-					int nid, ulong flags)
+					int nid, enum memblock_flags flags)
 {
 	return memblock_alloc_range_nid(size, align, 0, max_addr, nid, flags);
 }
 
 phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	ulong flags = choose_memblock_flags();
+	enum memblock_flags flags = choose_memblock_flags();
 	phys_addr_t ret;
 
 again:
@@ -1224,6 +1318,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
 	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
+#if defined(CONFIG_NO_BOOTMEM)
 /**
  * memblock_virt_alloc_internal - allocate boot memory block
  * @size: size of memory block to be allocated in bytes
@@ -1240,7 +1335,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
  * The allocation is performed from memory region limited by
  * memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE.
  *
- * The memory block is aligned on SMP_CACHE_BYTES if @align == 0.
+ * The memory block is aligned on %SMP_CACHE_BYTES if @align == 0.
  *
  * The phys address of allocated boot memory block is converted to virtual and
  * allocated memory is reset to 0.
@@ -1248,7 +1343,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
  * In addition, function sets the min_count to 0 using kmemleak_alloc for
  * allocated boot memory block, so that it is never reported as leaks.
  *
- * RETURNS:
+ * Return:
  * Virtual address of allocated memory block on success, NULL on failure.
  */
 static void * __init memblock_virt_alloc_internal(
@@ -1258,7 +1353,7 @@ static void * __init memblock_virt_alloc_internal(
 {
 	phys_addr_t alloc;
 	void *ptr;
-	ulong flags = choose_memblock_flags();
+	enum memblock_flags flags = choose_memblock_flags();
 
 	if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
 		nid = NUMA_NO_NODE;
@@ -1333,7 +1428,7 @@ done:
  * info), if enabled. Does not zero allocated memory, does not panic if request
  * cannot be satisfied.
  *
- * RETURNS:
+ * Return:
  * Virtual address of allocated memory block on success, NULL on failure.
  */
 void * __init memblock_virt_alloc_try_nid_raw(
@@ -1370,7 +1465,7 @@ void * __init memblock_virt_alloc_try_nid_raw(
  * Public function, provides additional debug information (including caller
  * info), if enabled. This function zeroes the allocated memory.
  *
- * RETURNS:
+ * Return:
  * Virtual address of allocated memory block on success, NULL on failure.
  */
 void * __init memblock_virt_alloc_try_nid_nopanic(
@@ -1406,7 +1501,7 @@ void * __init memblock_virt_alloc_try_nid_nopanic(
  * which provides debug information (including caller info), if enabled,
  * and panics if the request can not be satisfied.
  *
- * RETURNS:
+ * Return:
  * Virtual address of allocated memory block on success, NULL on failure.
  */
 void * __init memblock_virt_alloc_try_nid(
@@ -1431,6 +1526,7 @@ void * __init memblock_virt_alloc_try_nid(
 	      (u64)max_addr);
 	return NULL;
 }
+#endif
 
 /**
  * __memblock_free_early - free boot memory block
@@ -1449,9 +1545,9 @@ void __init __memblock_free_early(phys_addr_t base, phys_addr_t size)
 	memblock_remove_range(&memblock.reserved, base, size);
 }
 
-/*
+/**
  * __memblock_free_late - free bootmem block pages directly to buddy allocator
- * @addr: phys starting address of the  boot memory block
+ * @base: phys starting address of the  boot memory block
  * @size: size of the boot memory block in bytes
  *
  * This is only useful when the bootmem allocator has already been torn
@@ -1663,9 +1759,9 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
  * @base: base of region to check
  * @size: size of region to check
  *
- * Check if the region [@base, @base+@size) is a subset of a memory block.
+ * Check if the region [@base, @base + @size) is a subset of a memory block.
  *
- * RETURNS:
+ * Return:
  * 0 if false, non-zero if true
  */
 bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
@@ -1684,9 +1780,10 @@ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t siz
  * @base: base of region to check
  * @size: size of region to check
  *
- * Check if the region [@base, @base+@size) intersects a reserved memory block.
+ * Check if the region [@base, @base + @size) intersects a reserved
+ * memory block.
  *
- * RETURNS:
+ * Return:
  * True if they intersect, false if not.
  */
 bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
@@ -1733,7 +1830,7 @@ phys_addr_t __init_memblock memblock_get_current_limit(void)
 static void __init_memblock memblock_dump(struct memblock_type *type)
 {
 	phys_addr_t base, end, size;
-	unsigned long flags;
+	enum memblock_flags flags;
 	int idx;
 	struct memblock_region *rgn;
 
@@ -1751,7 +1848,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type)
 			snprintf(nid_buf, sizeof(nid_buf), " on node %d",
 				 memblock_get_region_node(rgn));
 #endif
-		pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#lx\n",
+		pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n",
 			type->name, idx, &base, &end, &size, nid_buf, flags);
 	}
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e6f0d5ef320a..b836e7f00309 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -850,7 +850,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 	int nid;
 	int i;
 
-	while ((memcg = parent_mem_cgroup(memcg))) {
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
 		for_each_node(nid) {
 			mz = mem_cgroup_nodeinfo(memcg, nid);
 			for (i = 0; i <= DEF_PRIORITY; i++) {
@@ -4037,6 +4037,14 @@ static struct cftype mem_cgroup_legacy_files[] = {
 
 static DEFINE_IDR(mem_cgroup_idr);
 
+static void mem_cgroup_id_remove(struct mem_cgroup *memcg)
+{
+	if (memcg->id.id > 0) {
+		idr_remove(&mem_cgroup_idr, memcg->id.id);
+		memcg->id.id = 0;
+	}
+}
+
 static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
 {
 	VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0);
@@ -4047,8 +4055,7 @@ static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
 {
 	VM_BUG_ON(atomic_read(&memcg->id.ref) < n);
 	if (atomic_sub_and_test(n, &memcg->id.ref)) {
-		idr_remove(&mem_cgroup_idr, memcg->id.id);
-		memcg->id.id = 0;
+		mem_cgroup_id_remove(memcg);
 
 		/* Memcg ID pins CSS */
 		css_put(&memcg->css);
@@ -4185,8 +4192,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
 	return memcg;
 fail:
-	if (memcg->id.id > 0)
-		idr_remove(&mem_cgroup_idr, memcg->id.id);
+	mem_cgroup_id_remove(memcg);
 	__mem_cgroup_free(memcg);
 	return NULL;
 }
@@ -4245,6 +4251,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	return &memcg->css;
 fail:
+	mem_cgroup_id_remove(memcg);
 	mem_cgroup_free(memcg);
 	return ERR_PTR(-ENOMEM);
 }
@@ -5593,6 +5600,19 @@ out:
 	return ret;
 }
 
+int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
+			  bool compound)
+{
+	struct mem_cgroup *memcg;
+	int ret;
+
+	ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp, compound);
+	memcg = *memcgp;
+	mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask);
+	return ret;
+}
+
 /**
  * mem_cgroup_commit_charge - commit a page charge
  * @page: page to charge
diff --git a/mm/memfd.c b/mm/memfd.c
index 27069518e3c5..2bb5e257080e 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -326,7 +326,7 @@ SYSCALL_DEFINE2(memfd_create,
 		goto err_fd;
 	}
 	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
-	file->f_flags |= O_RDWR | O_LARGEFILE;
+	file->f_flags |= O_LARGEFILE;
 
 	if (flags & MFD_ALLOW_SEALING) {
 		file_seals = memfd_file_seals_ptr(file);
diff --git a/mm/memory.c b/mm/memory.c
index 7206a634270b..348279ff6e51 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -326,16 +326,20 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 
-/*
- * See the comment near struct mmu_table_batch.
- */
-
 static void tlb_remove_table_smp_sync(void *arg)
 {
-	/* Simply deliver the interrupt */
+	struct mm_struct __maybe_unused *mm = arg;
+	/*
+	 * On most architectures this does nothing. Simply delivering the
+	 * interrupt is enough to prevent races with software page table
+	 * walking like that done in get_user_pages_fast.
+	 *
+	 * See the comment near struct mmu_table_batch.
+	 */
+	tlb_flush_remove_tables_local(mm);
 }
 
-static void tlb_remove_table_one(void *table)
+static void tlb_remove_table_one(void *table, struct mmu_gather *tlb)
 {
 	/*
 	 * This isn't an RCU grace period and hence the page-tables cannot be
@@ -344,7 +348,7 @@ static void tlb_remove_table_one(void *table)
 	 * It is however sufficient for software page-table walkers that rely on
 	 * IRQ disabling. See the comment near struct mmu_table_batch.
 	 */
-	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+	smp_call_function(tlb_remove_table_smp_sync, tlb->mm, 1);
 	__tlb_remove_table(table);
 }
 
@@ -365,6 +369,8 @@ void tlb_table_flush(struct mmu_gather *tlb)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
+	tlb_flush_remove_tables(tlb->mm);
+
 	if (*batch) {
 		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
 		*batch = NULL;
@@ -387,7 +393,7 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 	if (*batch == NULL) {
 		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
 		if (*batch == NULL) {
-			tlb_remove_table_one(table);
+			tlb_remove_table_one(table, tlb);
 			return;
 		}
 		(*batch)->nr = 0;
@@ -1417,11 +1423,9 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 	do {
 		next = pmd_addr_end(addr, end);
 		if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
-			if (next - addr != HPAGE_PMD_SIZE) {
-				VM_BUG_ON_VMA(vma_is_anonymous(vma) &&
-				    !rwsem_is_locked(&tlb->mm->mmap_sem), vma);
+			if (next - addr != HPAGE_PMD_SIZE)
 				__split_huge_pmd(vma, pmd, addr, false, NULL);
-			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
+			else if (zap_huge_pmd(tlb, vma, pmd, addr))
 				goto next;
 			/* fall through */
 		}
@@ -1886,6 +1890,9 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
 
+	if (!pfn_modify_allowed(pfn, pgprot))
+		return -EACCES;
+
 	track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
 
 	ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
@@ -1921,6 +1928,9 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
+	if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
+		return -EACCES;
+
 	/*
 	 * If we don't have pte special, then we have to use the pfn_valid()
 	 * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
@@ -1982,6 +1992,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 {
 	pte_t *pte;
 	spinlock_t *ptl;
+	int err = 0;
 
 	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
@@ -1989,12 +2000,16 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	arch_enter_lazy_mmu_mode();
 	do {
 		BUG_ON(!pte_none(*pte));
+		if (!pfn_modify_allowed(pfn, prot)) {
+			err = -EACCES;
+			break;
+		}
 		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
-	return 0;
+	return err;
 }
 
 static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
@@ -2003,6 +2018,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 {
 	pmd_t *pmd;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pmd = pmd_alloc(mm, pud, addr);
@@ -2011,9 +2027,10 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 	VM_BUG_ON(pmd_trans_huge(*pmd));
 	do {
 		next = pmd_addr_end(addr, end);
-		if (remap_pte_range(mm, pmd, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pte_range(mm, pmd, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pmd++, addr = next, addr != end);
 	return 0;
 }
@@ -2024,6 +2041,7 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 {
 	pud_t *pud;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pud = pud_alloc(mm, p4d, addr);
@@ -2031,9 +2049,10 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 		return -ENOMEM;
 	do {
 		next = pud_addr_end(addr, end);
-		if (remap_pmd_range(mm, pud, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pmd_range(mm, pud, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pud++, addr = next, addr != end);
 	return 0;
 }
@@ -2044,6 +2063,7 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 {
 	p4d_t *p4d;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	p4d = p4d_alloc(mm, pgd, addr);
@@ -2051,9 +2071,10 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 		return -ENOMEM;
 	do {
 		next = p4d_addr_end(addr, end);
-		if (remap_pud_range(mm, p4d, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pud_range(mm, p4d, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (p4d++, addr = next, addr != end);
 	return 0;
 }
@@ -2503,7 +2524,7 @@ static int wp_page_copy(struct vm_fault *vmf)
 		cow_user_page(new_page, old_page, vmf->address, vma);
 	}
 
-	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false))
+	if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))
 		goto oom_free_new;
 
 	__SetPageUptodate(new_page);
@@ -3003,8 +3024,8 @@ int do_swap_page(struct vm_fault *vmf)
 		goto out_page;
 	}
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL,
-				&memcg, false)) {
+	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL,
+					&memcg, false)) {
 		ret = VM_FAULT_OOM;
 		goto out_page;
 	}
@@ -3165,7 +3186,8 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	if (!page)
 		goto oom;
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false))
+	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg,
+					false))
 		goto oom_free_page;
 
 	/*
@@ -3661,7 +3683,7 @@ static int do_cow_fault(struct vm_fault *vmf)
 	if (!vmf->cow_page)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_try_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL,
+	if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, GFP_KERNEL,
 				&vmf->memcg, false)) {
 		put_page(vmf->cow_page);
 		return VM_FAULT_OOM;
@@ -4397,6 +4419,9 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 		return -EINVAL;
 
 	maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
+	if (!maddr)
+		return -ENOMEM;
+
 	if (write)
 		memcpy_toio(maddr + offset, buf, len);
 	else
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 9ac49ef17b4e..01f1a14facc4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2505,6 +2505,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 
 		/* Create pseudo-vma that contains just the policy */
 		memset(&pvma, 0, sizeof(struct vm_area_struct));
+		vma_init(&pvma, NULL);
 		pvma.vm_end = TASK_SIZE;	/* policy covers entire file */
 		mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
 
diff --git a/mm/mmap.c b/mm/mmap.c
index d1eb87ef4b1a..17bbf4d3e24f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -182,12 +182,12 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	mpol_put(vma_policy(vma));
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return next;
 }
 
-static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf);
-
+static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags,
+		struct list_head *uf);
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
 	unsigned long retval;
@@ -245,7 +245,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 		goto out;
 
 	/* Ok, looks good - let it rip. */
-	if (do_brk(oldbrk, newbrk-oldbrk, &uf) < 0)
+	if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
 		goto out;
 
 set_brk:
@@ -911,7 +911,7 @@ again:
 			anon_vma_merge(vma, next);
 		mm->map_count--;
 		mpol_put(vma_policy(next));
-		kmem_cache_free(vm_area_cachep, next);
+		vm_area_free(next);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),
 		 * we must remove another next too. It would clutter
@@ -1729,19 +1729,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	 * specific mapper. the address has already been validated, but
 	 * not unmapped, but the maps are removed from the list.
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		error = -ENOMEM;
 		goto unacct_error;
 	}
 
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 	vma->vm_flags = vm_flags;
 	vma->vm_page_prot = vm_get_page_prot(vm_flags);
 	vma->vm_pgoff = pgoff;
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	if (file) {
 		if (vm_flags & VM_DENYWRITE) {
@@ -1780,6 +1778,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		error = shmem_zero_setup(vma);
 		if (error)
 			goto free_vma;
+	} else {
+		vma_set_anonymous(vma);
 	}
 
 	vma_link(mm, vma, prev, rb_link, rb_parent);
@@ -1832,7 +1832,7 @@ allow_write_and_free_vma:
 	if (vm_flags & VM_DENYWRITE)
 		allow_write_access(file);
 free_vma:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 unacct_error:
 	if (charged)
 		vm_unacct_memory(charged);
@@ -2620,15 +2620,10 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 			return err;
 	}
 
-	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	new = vm_area_dup(vma);
 	if (!new)
 		return -ENOMEM;
 
-	/* most fields are the same, copy all, and then fixup */
-	*new = *vma;
-
-	INIT_LIST_HEAD(&new->anon_vma_chain);
-
 	if (new_below)
 		new->vm_end = addr;
 	else {
@@ -2669,7 +2664,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
  out_free_mpol:
 	mpol_put(vma_policy(new));
  out_free_vma:
-	kmem_cache_free(vm_area_cachep, new);
+	vm_area_free(new);
 	return err;
 }
 
@@ -2929,21 +2924,14 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf)
+static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	unsigned long len;
 	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
-	len = PAGE_ALIGN(request);
-	if (len < request)
-		return -ENOMEM;
-	if (!len)
-		return 0;
-
 	/* Until we need other flags, refuse anything except VM_EXEC. */
 	if ((flags & (~VM_EXEC)) != 0)
 		return -EINVAL;
@@ -2991,14 +2979,13 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
 	/*
 	 * create a vma struct for an anonymous mapping
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		vm_unacct_memory(len >> PAGE_SHIFT);
 		return -ENOMEM;
 	}
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	vma->vm_mm = mm;
+	vma_set_anonymous(vma);
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 	vma->vm_pgoff = pgoff;
@@ -3015,18 +3002,20 @@ out:
 	return 0;
 }
 
-static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf)
-{
-	return do_brk_flags(addr, len, 0, uf);
-}
-
-int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags)
+int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
+	unsigned long len;
 	int ret;
 	bool populate;
 	LIST_HEAD(uf);
 
+	len = PAGE_ALIGN(request);
+	if (len < request)
+		return -ENOMEM;
+	if (!len)
+		return 0;
+
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
@@ -3207,16 +3196,14 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		}
 		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
 	} else {
-		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+		new_vma = vm_area_dup(vma);
 		if (!new_vma)
 			goto out;
-		*new_vma = *vma;
 		new_vma->vm_start = addr;
 		new_vma->vm_end = addr + len;
 		new_vma->vm_pgoff = pgoff;
 		if (vma_dup_policy(vma, new_vma))
 			goto out_free_vma;
-		INIT_LIST_HEAD(&new_vma->anon_vma_chain);
 		if (anon_vma_clone(new_vma, vma))
 			goto out_free_mempol;
 		if (new_vma->vm_file)
@@ -3231,7 +3218,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 out_free_mempol:
 	mpol_put(vma_policy(new_vma));
 out_free_vma:
-	kmem_cache_free(vm_area_cachep, new_vma);
+	vm_area_free(new_vma);
 out:
 	return NULL;
 }
@@ -3355,12 +3342,10 @@ static struct vm_area_struct *__install_special_mapping(
 	int ret;
 	struct vm_area_struct *vma;
 
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (unlikely(vma == NULL))
 		return ERR_PTR(-ENOMEM);
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 
@@ -3381,7 +3366,7 @@ static struct vm_area_struct *__install_special_mapping(
 	return vma;
 
 out:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return ERR_PTR(ret);
 }
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 625608bc8962..6d331620b9e5 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -306,6 +306,42 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 	return pages;
 }
 
+static int prot_none_pte_entry(pte_t *pte, unsigned long addr,
+			       unsigned long next, struct mm_walk *walk)
+{
+	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask,
+				   unsigned long addr, unsigned long next,
+				   struct mm_walk *walk)
+{
+	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+static int prot_none_test(unsigned long addr, unsigned long next,
+			  struct mm_walk *walk)
+{
+	return 0;
+}
+
+static int prot_none_walk(struct vm_area_struct *vma, unsigned long start,
+			   unsigned long end, unsigned long newflags)
+{
+	pgprot_t new_pgprot = vm_get_page_prot(newflags);
+	struct mm_walk prot_none_walk = {
+		.pte_entry = prot_none_pte_entry,
+		.hugetlb_entry = prot_none_hugetlb_entry,
+		.test_walk = prot_none_test,
+		.mm = current->mm,
+		.private = &new_pgprot,
+	};
+
+	return walk_page_range(start, end, &prot_none_walk);
+}
+
 int
 mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	unsigned long start, unsigned long end, unsigned long newflags)
@@ -324,6 +360,19 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	}
 
 	/*
+	 * Do PROT_NONE PFN permission checks here when we can still
+	 * bail out without undoing a lot of state. This is a rather
+	 * uncommon case, so doesn't need to be very optimized.
+	 */
+	if (arch_has_pfn_modify_check() &&
+	    (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
+	    (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) {
+		error = prot_none_walk(vma, start, end, newflags);
+		if (error)
+			return error;
+	}
+
+	/*
 	 * If we make a private mapping writable we increase our commit;
 	 * but (without finer accounting) cannot reduce our commit if we
 	 * make it unwritable again. hugetlb mapping were accounted for
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 9b02fda0886b..439af3b765a7 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -42,7 +42,7 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 {
 	void *ptr;
 	u64 addr;
-	ulong flags = choose_memblock_flags();
+	enum memblock_flags flags = choose_memblock_flags();
 
 	if (limit > memblock.current_limit)
 		limit = memblock.current_limit;
@@ -72,7 +72,7 @@ again:
 	return ptr;
 }
 
-/*
+/**
  * free_bootmem_late - free bootmem pages directly to page allocator
  * @addr: starting address of the range
  * @size: size of the range in bytes
@@ -176,7 +176,7 @@ void __init reset_all_zones_managed_pages(void)
 /**
  * free_all_bootmem - release free pages to the buddy allocator
  *
- * Returns the number of pages actually released.
+ * Return: the number of pages actually released.
  */
 unsigned long __init free_all_bootmem(void)
 {
@@ -193,7 +193,7 @@ unsigned long __init free_all_bootmem(void)
 /**
  * free_bootmem_node - mark a page range as usable
  * @pgdat: node the range resides on
- * @physaddr: starting address of the range
+ * @physaddr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * Partial pages will be considered reserved and left as they are.
@@ -208,7 +208,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 
 /**
  * free_bootmem - mark a page range as usable
- * @addr: starting address of the range
+ * @addr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * Partial pages will be considered reserved and left as they are.
@@ -256,7 +256,7 @@ restart:
  *
  * Allocation may happen on any node in the system.
  *
- * Returns NULL on failure.
+ * Return: address of the allocated region or %NULL on failure.
  */
 void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
 					unsigned long goal)
@@ -293,6 +293,8 @@ static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
  * Allocation may happen on any node in the system.
  *
  * The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
  */
 void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 			      unsigned long goal)
@@ -367,6 +369,8 @@ static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
  * can not hold the requested memory.
  *
  * The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
  */
 void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
@@ -396,6 +400,8 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
  * Allocation may happen on any node in the system.
  *
  * The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
  */
 void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 				  unsigned long goal)
@@ -425,6 +431,8 @@ void * __init __alloc_bootmem_low_nopanic(unsigned long size,
  * can not hold the requested memory.
  *
  * The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
  */
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
diff --git a/mm/nommu.c b/mm/nommu.c
index 4452d8bd9ae4..9fc9e43335b6 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -769,7 +769,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	put_nommu_region(vma->vm_region);
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 }
 
 /*
@@ -1145,6 +1145,8 @@ static int do_mmap_private(struct vm_area_struct *vma,
 		if (ret < len)
 			memset(base + ret, 0, len - ret);
 
+	} else {
+		vma_set_anonymous(vma);
 	}
 
 	return 0;
@@ -1204,7 +1206,7 @@ unsigned long do_mmap(struct file *file,
 	if (!region)
 		goto error_getting_region;
 
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(current->mm);
 	if (!vma)
 		goto error_getting_vma;
 
@@ -1212,7 +1214,6 @@ unsigned long do_mmap(struct file *file,
 	region->vm_flags = vm_flags;
 	region->vm_pgoff = pgoff;
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	vma->vm_flags = vm_flags;
 	vma->vm_pgoff = pgoff;
 
@@ -1368,7 +1369,7 @@ error:
 	kmem_cache_free(vm_region_jar, region);
 	if (vma->vm_file)
 		fput(vma->vm_file);
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return ret;
 
 sharing_violation:
@@ -1469,14 +1470,13 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!region)
 		return -ENOMEM;
 
-	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	new = vm_area_dup(vma);
 	if (!new) {
 		kmem_cache_free(vm_region_jar, region);
 		return -ENOMEM;
 	}
 
 	/* most fields are the same, copy all, and then fixup */
-	*new = *vma;
 	*region = *vma->vm_region;
 	new->vm_region = region;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1521100f1e63..0922ef5d2e46 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -155,16 +155,17 @@ static inline void set_pcppage_migratetype(struct page *page, int migratetype)
  * The following functions are used by the suspend/hibernate code to temporarily
  * change gfp_allowed_mask in order to avoid using I/O during memory allocations
  * while devices are suspended.  To avoid races with the suspend/hibernate code,
- * they should always be called with pm_mutex held (gfp_allowed_mask also should
- * only be modified with pm_mutex held, unless the suspend/hibernate code is
- * guaranteed not to run in parallel with that modification).
+ * they should always be called with system_transition_mutex held
+ * (gfp_allowed_mask also should only be modified with system_transition_mutex
+ * held, unless the suspend/hibernate code is guaranteed not to run in parallel
+ * with that modification).
  */
 
 static gfp_t saved_gfp_mask;
 
 void pm_restore_gfp_mask(void)
 {
-	WARN_ON(!mutex_is_locked(&pm_mutex));
+	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 	if (saved_gfp_mask) {
 		gfp_allowed_mask = saved_gfp_mask;
 		saved_gfp_mask = 0;
@@ -173,7 +174,7 @@ void pm_restore_gfp_mask(void)
 
 void pm_restrict_gfp_mask(void)
 {
-	WARN_ON(!mutex_is_locked(&pm_mutex));
+	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 	WARN_ON(saved_gfp_mask);
 	saved_gfp_mask = gfp_allowed_mask;
 	gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
@@ -6383,7 +6384,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	free_area_init_core(pgdat);
 }
 
-#ifdef CONFIG_HAVE_MEMBLOCK
+#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
 /*
  * Only struct pages that are backed by physical memory are zeroed and
  * initialized by going through __init_single_page(). But, there are some
@@ -6421,7 +6422,7 @@ void __paginginit zero_resv_unavail(void)
 	if (pgcnt)
 		pr_info("Reserved but unavailable: %lld pages", pgcnt);
 }
-#endif /* CONFIG_HAVE_MEMBLOCK */
+#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 
@@ -6847,6 +6848,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
 	setup_nr_node_ids();
+	zero_resv_unavail();
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 		free_area_init_node(nid, NULL,
@@ -6857,7 +6859,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 			node_set_state(nid, N_MEMORY);
 		check_for_memory(pgdat, nid);
 	}
-	zero_resv_unavail();
 }
 
 static int __init cmdline_parse_core(char *p, unsigned long *core,
@@ -6939,9 +6940,21 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
 	start = (void *)PAGE_ALIGN((unsigned long)start);
 	end = (void *)((unsigned long)end & PAGE_MASK);
 	for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
+		struct page *page = virt_to_page(pos);
+		void *direct_map_addr;
+
+		/*
+		 * 'direct_map_addr' might be different from 'pos'
+		 * because some architectures' virt_to_page()
+		 * work with aliases.  Getting the direct map
+		 * address ensures that we get a _writeable_
+		 * alias for the memset().
+		 */
+		direct_map_addr = page_address(page);
 		if ((unsigned int)poison <= 0xFF)
-			memset(pos, poison, PAGE_SIZE);
-		free_reserved_page(virt_to_page(pos));
+			memset(direct_map_addr, poison, PAGE_SIZE);
+
+		free_reserved_page(page);
 	}
 
 	if (pages && s)
@@ -7033,9 +7046,9 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 
 void __init free_area_init(unsigned long *zones_size)
 {
+	zero_resv_unavail();
 	free_area_init_node(0, zones_size,
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
-	zero_resv_unavail();
 }
 
 static int page_alloc_cpu_dead(unsigned int cpu)
diff --git a/mm/page_io.c b/mm/page_io.c
index b41cf9644585..aafd19ec1db4 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -338,7 +338,8 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		ret = -ENOMEM;
 		goto out;
 	}
-	bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
+	bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc);
+	bio_associate_blkcg_from_page(bio, page);
 	count_swpout_vm_event(page);
 	set_page_writeback(page);
 	unlock_page(page);
diff --git a/mm/readahead.c b/mm/readahead.c
index e273f0de3376..a59ea70527b9 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -19,6 +19,7 @@
 #include <linux/syscalls.h>
 #include <linux/file.h>
 #include <linux/mm_inline.h>
+#include <linux/blk-cgroup.h>
 
 #include "internal.h"
 
@@ -385,6 +386,7 @@ ondemand_readahead(struct address_space *mapping,
 {
 	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	unsigned long max_pages = ra->ra_pages;
+	unsigned long add_pages;
 	pgoff_t prev_offset;
 
 	/*
@@ -474,10 +476,17 @@ readit:
 	 * Will this read hit the readahead marker made by itself?
 	 * If so, trigger the readahead marker hit now, and merge
 	 * the resulted next readahead window into the current one.
+	 * Take care of maximum IO pages as above.
 	 */
 	if (offset == ra->start && ra->size == ra->async_size) {
-		ra->async_size = get_next_ra_size(ra, max_pages);
-		ra->size += ra->async_size;
+		add_pages = get_next_ra_size(ra, max_pages);
+		if (ra->size + add_pages <= max_pages) {
+			ra->async_size = add_pages;
+			ra->size += add_pages;
+		} else {
+			ra->size = max_pages;
+			ra->async_size = max_pages >> 1;
+		}
 	}
 
 	return ra_submit(ra, mapping, filp);
@@ -505,6 +514,9 @@ void page_cache_sync_readahead(struct address_space *mapping,
 	if (!ra->ra_pages)
 		return;
 
+	if (blk_cgroup_congested())
+		return;
+
 	/* be dumb */
 	if (filp && (filp->f_mode & FMODE_RANDOM)) {
 		force_page_cache_readahead(mapping, filp, offset, req_size);
@@ -555,6 +567,9 @@ page_cache_async_readahead(struct address_space *mapping,
 	if (inode_read_congested(mapping->host))
 		return;
 
+	if (blk_cgroup_congested())
+		return;
+
 	/* do read-ahead */
 	ondemand_readahead(mapping, ra, filp, true, offset, req_size);
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 6db729dc4c50..eb477809a5c0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -64,6 +64,7 @@
 #include <linux/backing-dev.h>
 #include <linux/page_idle.h>
 #include <linux/memremap.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/tlbflush.h>
 
@@ -1481,11 +1482,16 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				set_pte_at(mm, address, pvmw.pte, pteval);
 			}
 
-		} else if (pte_unused(pteval)) {
+		} else if (pte_unused(pteval) && !userfaultfd_armed(vma)) {
 			/*
 			 * The guest indicated that the page content is of no
 			 * interest anymore. Simply discard the pte, vmscan
 			 * will take care of the rest.
+			 * A future reference will then fault in a new zero
+			 * page. When userfaultfd is active, we must not drop
+			 * this page though, as its main user (postcopy
+			 * migration) will not expect userfaults on already
+			 * copied pages.
 			 */
 			dec_mm_counter(mm, mm_counter(page));
 			/* We have to invalidate as we cleared the pte */
diff --git a/mm/shmem.c b/mm/shmem.c
index 2cab84403055..06ebe17bb924 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1239,8 +1239,8 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
 	 * Charged back to the user (not to caller) when swap account is used.
 	 */
-	error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg,
-			false);
+	error = mem_cgroup_try_charge_delay(page, current->mm, GFP_KERNEL,
+					    &memcg, false);
 	if (error)
 		goto out;
 	/* No radix_tree_preload: swap entry keeps a place for page in tree */
@@ -1421,6 +1421,7 @@ static void shmem_pseudo_vma_init(struct vm_area_struct *vma,
 {
 	/* Create a pseudo vma that just contains the policy */
 	memset(vma, 0, sizeof(*vma));
+	vma_init(vma, NULL);
 	/* Bias interleave by inode number to distribute better across nodes */
 	vma->vm_pgoff = index + info->vfs_inode.i_ino;
 	vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index);
@@ -1712,7 +1713,7 @@ repeat:
 				goto failed;
 		}
 
-		error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg,
+		error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 				false);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
@@ -1818,7 +1819,7 @@ alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, inode,
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 
-		error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg,
+		error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 				PageTransHuge(page));
 		if (error)
 			goto unacct;
@@ -2291,7 +2292,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	__SetPageSwapBacked(page);
 	__SetPageUptodate(page);
 
-	ret = mem_cgroup_try_charge(page, dst_mm, gfp, &memcg, false);
+	ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false);
 	if (ret)
 		goto out_release;
 
@@ -3896,18 +3897,11 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
 /* common code */
 
-static const struct dentry_operations anon_ops = {
-	.d_dname = simple_dname
-};
-
 static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size,
 				       unsigned long flags, unsigned int i_flags)
 {
-	struct file *res;
 	struct inode *inode;
-	struct path path;
-	struct super_block *sb;
-	struct qstr this;
+	struct file *res;
 
 	if (IS_ERR(mnt))
 		return ERR_CAST(mnt);
@@ -3918,41 +3912,21 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
 	if (shmem_acct_size(flags, size))
 		return ERR_PTR(-ENOMEM);
 
-	res = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0; /* will go */
-	sb = mnt->mnt_sb;
-	path.mnt = mntget(mnt);
-	path.dentry = d_alloc_pseudo(sb, &this);
-	if (!path.dentry)
-		goto put_memory;
-	d_set_d_op(path.dentry, &anon_ops);
-
-	res = ERR_PTR(-ENOSPC);
-	inode = shmem_get_inode(sb, NULL, S_IFREG | 0777, 0, flags);
-	if (!inode)
-		goto put_memory;
-
+	inode = shmem_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0,
+				flags);
+	if (unlikely(!inode)) {
+		shmem_unacct_size(flags, size);
+		return ERR_PTR(-ENOSPC);
+	}
 	inode->i_flags |= i_flags;
-	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
 	clear_nlink(inode);	/* It is unlinked */
 	res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size));
+	if (!IS_ERR(res))
+		res = alloc_file_pseudo(inode, mnt, name, O_RDWR,
+				&shmem_file_operations);
 	if (IS_ERR(res))
-		goto put_path;
-
-	res = alloc_file(&path, FMODE_WRITE | FMODE_READ,
-		  &shmem_file_operations);
-	if (IS_ERR(res))
-		goto put_path;
-
-	return res;
-
-put_memory:
-	shmem_unacct_size(flags, size);
-put_path:
-	path_put(&path);
+		iput(inode);
 	return res;
 }
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 890b1f04a03a..2296caf87bfb 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -567,10 +567,14 @@ static int shutdown_cache(struct kmem_cache *s)
 	list_del(&s->list);
 
 	if (s->flags & SLAB_TYPESAFE_BY_RCU) {
+#ifdef SLAB_SUPPORTS_SYSFS
+		sysfs_slab_unlink(s);
+#endif
 		list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
 		schedule_work(&slab_caches_to_rcu_destroy_work);
 	} else {
 #ifdef SLAB_SUPPORTS_SYSFS
+		sysfs_slab_unlink(s);
 		sysfs_slab_release(s);
 #else
 		slab_kmem_cache_release(s);
diff --git a/mm/slub.c b/mm/slub.c
index a3b8467c14af..51258eff4178 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5667,7 +5667,6 @@ static void sysfs_slab_remove_workfn(struct work_struct *work)
 	kset_unregister(s->memcg_kset);
 #endif
 	kobject_uevent(&s->kobj, KOBJ_REMOVE);
-	kobject_del(&s->kobj);
 out:
 	kobject_put(&s->kobj);
 }
@@ -5752,6 +5751,12 @@ static void sysfs_slab_remove(struct kmem_cache *s)
 	schedule_work(&s->kobj_remove_work);
 }
 
+void sysfs_slab_unlink(struct kmem_cache *s)
+{
+	if (slab_state >= FULL)
+		kobject_del(&s->kobj);
+}
+
 void sysfs_slab_release(struct kmem_cache *s)
 {
 	if (slab_state >= FULL)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2cc2972eedaf..8837b22c848d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2909,6 +2909,35 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 	return 0;
 }
 
+
+/*
+ * Find out how many pages are allowed for a single swap device. There
+ * are two limiting factors:
+ * 1) the number of bits for the swap offset in the swp_entry_t type, and
+ * 2) the number of bits in the swap pte, as defined by the different
+ * architectures.
+ *
+ * In order to find the largest possible bit mask, a swap entry with
+ * swap type 0 and swap offset ~0UL is created, encoded to a swap pte,
+ * decoded to a swp_entry_t again, and finally the swap offset is
+ * extracted.
+ *
+ * This will mask all the bits from the initial ~0UL mask that can't
+ * be encoded in either the swp_entry_t or the architecture definition
+ * of a swap pte.
+ */
+unsigned long generic_max_swapfile_size(void)
+{
+	return swp_offset(pte_to_swp_entry(
+			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+}
+
+/* Can be overridden by an architecture for additional checks. */
+__weak unsigned long max_swapfile_size(void)
+{
+	return generic_max_swapfile_size();
+}
+
 static unsigned long read_swap_header(struct swap_info_struct *p,
 					union swap_header *swap_header,
 					struct inode *inode)
@@ -2944,22 +2973,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 	p->cluster_next = 1;
 	p->cluster_nr = 0;
 
-	/*
-	 * Find out how many pages are allowed for a single swap
-	 * device. There are two limiting factors: 1) the number
-	 * of bits for the swap offset in the swp_entry_t type, and
-	 * 2) the number of bits in the swap pte as defined by the
-	 * different architectures. In order to find the
-	 * largest possible bit mask, a swap entry with swap type 0
-	 * and swap offset ~0UL is created, encoded to a swap pte,
-	 * decoded to a swp_entry_t again, and finally the swap
-	 * offset is extracted. This will mask all the bits from
-	 * the initial ~0UL mask that can't be encoded in either
-	 * the swp_entry_t or the architecture definition of a
-	 * swap pte.
-	 */
-	maxpages = swp_offset(pte_to_swp_entry(
-			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+	maxpages = max_swapfile_size();
 	last_page = swap_header->info.last_page;
 	if (!last_page) {
 		pr_warn("Empty swap-file\n");
@@ -3731,6 +3745,37 @@ static void free_swap_count_continuations(struct swap_info_struct *si)
 	}
 }
 
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
+				  gfp_t gfp_mask)
+{
+	struct swap_info_struct *si, *next;
+	if (!(gfp_mask & __GFP_IO) || !memcg)
+		return;
+
+	if (!blk_cgroup_congested())
+		return;
+
+	/*
+	 * We've already scheduled a throttle, avoid taking the global swap
+	 * lock.
+	 */
+	if (current->throttle_queue)
+		return;
+
+	spin_lock(&swap_avail_lock);
+	plist_for_each_entry_safe(si, next, &swap_avail_heads[node],
+				  avail_lists[node]) {
+		if (si->bdev) {
+			blkcg_schedule_throttle(bdev_get_queue(si->bdev),
+						true);
+			break;
+		}
+	}
+	spin_unlock(&swap_avail_lock);
+}
+#endif
+
 static int __init swapfile_init(void)
 {
 	int nid;
diff --git a/mm/usercopy.c b/mm/usercopy.c
index e9e9325f7638..852eb4e53f06 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -20,6 +20,8 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/thread_info.h>
+#include <linux/atomic.h>
+#include <linux/jump_label.h>
 #include <asm/sections.h>
 
 /*
@@ -240,6 +242,8 @@ static inline void check_heap_object(const void *ptr, unsigned long n,
 	}
 }
 
+static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks);
+
 /*
  * Validates that the given object is:
  * - not bogus address
@@ -248,6 +252,9 @@ static inline void check_heap_object(const void *ptr, unsigned long n,
  */
 void __check_object_size(const void *ptr, unsigned long n, bool to_user)
 {
+	if (static_branch_unlikely(&bypass_usercopy_checks))
+		return;
+
 	/* Skip all tests if size is zero. */
 	if (!n)
 		return;
@@ -279,3 +286,21 @@ void __check_object_size(const void *ptr, unsigned long n, bool to_user)
 	check_kernel_text_object((const unsigned long)ptr, n, to_user);
 }
 EXPORT_SYMBOL(__check_object_size);
+
+static bool enable_checks __initdata = true;
+
+static int __init parse_hardened_usercopy(char *str)
+{
+	return strtobool(str, &enable_checks);
+}
+
+__setup("hardened_usercopy=", parse_hardened_usercopy);
+
+static int __init set_hardened_usercopy(void)
+{
+	if (enable_checks == false)
+		static_branch_enable(&bypass_usercopy_checks);
+	return 1;
+}
+
+late_initcall(set_hardened_usercopy);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 75eda9c2b260..8ba0870ecddd 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1796,11 +1796,9 @@ static void vmstat_update(struct work_struct *w)
 		 * to occur in the future. Keep on running the
 		 * update worker thread.
 		 */
-		preempt_disable();
 		queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
 				this_cpu_ptr(&vmstat_work),
 				round_jiffies_relative(sysctl_stat_interval));
-		preempt_enable();
 	}
 }
 
diff --git a/mm/zswap.c b/mm/zswap.c
index 7d34e69507e3..cd91fd9d96b8 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1026,6 +1026,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 			ret = -ENOMEM;
 			goto reject;
 		}
+
+		/* A second zswap_is_full() check after
+		 * zswap_shrink() to make sure it's now
+		 * under the max_pool_percent
+		 */
+		if (zswap_is_full()) {
+			ret = -ENOMEM;
+			goto reject;
+		}
 	}
 
 	/* allocate entry */
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 73a65789271b..8ccee3d01822 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -693,7 +693,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/net/9p/client.c b/net/9p/client.c
index 18c5271910dc..5c1343195292 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -225,7 +225,8 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 	}
 
 free_and_return:
-	v9fs_put_trans(clnt->trans_mod);
+	if (ret)
+		v9fs_put_trans(clnt->trans_mod);
 	kfree(tmp_options);
 	return ret;
 }
diff --git a/net/Makefile b/net/Makefile
index 13ec0d5415c7..bdaf53925acd 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -20,11 +20,7 @@ obj-$(CONFIG_TLS)		+= tls/
 obj-$(CONFIG_XFRM)		+= xfrm/
 obj-$(CONFIG_UNIX)		+= unix/
 obj-$(CONFIG_NET)		+= ipv6/
-ifneq ($(CC_CAN_LINK),y)
-$(warning CC cannot link executables. Skipping bpfilter.)
-else
 obj-$(CONFIG_BPFILTER)		+= bpfilter/
-endif
 obj-$(CONFIG_PACKET)		+= packet/
 obj-$(CONFIG_NET_KEY)		+= key/
 obj-$(CONFIG_BRIDGE)		+= bridge/
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 55fdba05d7d9..9b6bc5abe946 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1869,7 +1869,7 @@ static const struct proto_ops atalk_dgram_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= atalk_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.ioctl		= atalk_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= atalk_compat_ioctl,
diff --git a/net/atm/common.c b/net/atm/common.c
index ff5748b2190f..a7a68e509628 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -647,11 +647,16 @@ out:
 	return error;
 }
 
-__poll_t vcc_poll_mask(struct socket *sock, __poll_t events)
+__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
-	struct atm_vcc *vcc = ATM_SD(sock);
-	__poll_t mask = 0;
+	struct atm_vcc *vcc;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
+
+	vcc = ATM_SD(sock);
 
 	/* exceptional events */
 	if (sk->sk_err)
diff --git a/net/atm/common.h b/net/atm/common.h
index 526796ad230f..5850649068bb 100644
--- a/net/atm/common.h
+++ b/net/atm/common.h
@@ -17,7 +17,7 @@ int vcc_connect(struct socket *sock, int itf, short vpi, int vci);
 int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		int flags);
 int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len);
-__poll_t vcc_poll_mask(struct socket *sock, __poll_t events);
+__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait);
 int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int vcc_setsockopt(struct socket *sock, int level, int optname,
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index af8c4b38b746..d84227d75717 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -244,7 +244,7 @@ static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size)
 	 * the packet count limit, so...
 	 */
 	if (atm_may_send(pvcc->atmvcc, size) &&
-	    atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT))
+	    atomic_inc_not_zero(&pvcc->inflight))
 		return 1;
 
 	/*
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index 9f75092fe778..2cb10af16afc 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -113,7 +113,7 @@ static const struct proto_ops pvc_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	pvc_getname,
-	.poll_mask =	vcc_poll_mask,
+	.poll =		vcc_poll,
 	.ioctl =	vcc_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = vcc_compat_ioctl,
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 53f4ad7087b1..2f91b766ac42 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -636,7 +636,7 @@ static const struct proto_ops svc_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	svc_accept,
 	.getname =	svc_getname,
-	.poll_mask =	vcc_poll_mask,
+	.poll =		vcc_poll,
 	.ioctl =	svc_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl =	svc_compat_ioctl,
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index d1d2442ce573..c603d33d5410 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1941,7 +1941,7 @@ static const struct proto_ops ax25_proto_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= ax25_accept,
 	.getname	= ax25_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.ioctl		= ax25_ioctl,
 	.listen		= ax25_listen,
 	.shutdown	= ax25_shutdown,
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index be09a9883825..73bf6a93a3cf 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -2732,7 +2732,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 {
 	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
 	struct batadv_neigh_node *router;
-	struct batadv_gw_node *curr_gw;
+	struct batadv_gw_node *curr_gw = NULL;
 	int ret = 0;
 	void *hdr;
 
@@ -2780,6 +2780,8 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 	ret = 0;
 
 out:
+	if (curr_gw)
+		batadv_gw_node_put(curr_gw);
 	if (router_ifinfo)
 		batadv_neigh_ifinfo_put(router_ifinfo);
 	if (router)
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index ec93337ee259..6baec4e68898 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -927,7 +927,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 {
 	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
 	struct batadv_neigh_node *router;
-	struct batadv_gw_node *curr_gw;
+	struct batadv_gw_node *curr_gw = NULL;
 	int ret = 0;
 	void *hdr;
 
@@ -995,6 +995,8 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 	ret = 0;
 
 out:
+	if (curr_gw)
+		batadv_gw_node_put(curr_gw);
 	if (router_ifinfo)
 		batadv_neigh_ifinfo_put(router_ifinfo);
 	if (router)
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 4229b01ac7b5..87479c60670e 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -19,6 +19,7 @@
 #include "debugfs.h"
 #include "main.h"
 
+#include <linux/dcache.h>
 #include <linux/debugfs.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -344,6 +345,25 @@ out:
 }
 
 /**
+ * batadv_debugfs_rename_hardif() - Fix debugfs path for renamed hardif
+ * @hard_iface: hard interface which was renamed
+ */
+void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface)
+{
+	const char *name = hard_iface->net_dev->name;
+	struct dentry *dir;
+	struct dentry *d;
+
+	dir = hard_iface->debug_dir;
+	if (!dir)
+		return;
+
+	d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
+	if (!d)
+		pr_err("Can't rename debugfs dir to %s\n", name);
+}
+
+/**
  * batadv_debugfs_del_hardif() - delete the base directory for a hard interface
  *  in debugfs.
  * @hard_iface: hard interface which is deleted.
@@ -414,6 +434,26 @@ out:
 }
 
 /**
+ * batadv_debugfs_rename_meshif() - Fix debugfs path for renamed softif
+ * @dev: net_device which was renamed
+ */
+void batadv_debugfs_rename_meshif(struct net_device *dev)
+{
+	struct batadv_priv *bat_priv = netdev_priv(dev);
+	const char *name = dev->name;
+	struct dentry *dir;
+	struct dentry *d;
+
+	dir = bat_priv->debug_dir;
+	if (!dir)
+		return;
+
+	d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
+	if (!d)
+		pr_err("Can't rename debugfs dir to %s\n", name);
+}
+
+/**
  * batadv_debugfs_del_meshif() - Remove interface dependent debugfs entries
  * @dev: netdev struct of the soft interface
  */
diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h
index 37b069698b04..08a592ffbee5 100644
--- a/net/batman-adv/debugfs.h
+++ b/net/batman-adv/debugfs.h
@@ -30,8 +30,10 @@ struct net_device;
 void batadv_debugfs_init(void);
 void batadv_debugfs_destroy(void);
 int batadv_debugfs_add_meshif(struct net_device *dev);
+void batadv_debugfs_rename_meshif(struct net_device *dev);
 void batadv_debugfs_del_meshif(struct net_device *dev);
 int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface);
+void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface);
 void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface);
 
 #else
@@ -49,6 +51,10 @@ static inline int batadv_debugfs_add_meshif(struct net_device *dev)
 	return 0;
 }
 
+static inline void batadv_debugfs_rename_meshif(struct net_device *dev)
+{
+}
+
 static inline void batadv_debugfs_del_meshif(struct net_device *dev)
 {
 }
@@ -60,6 +66,11 @@ int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
 }
 
 static inline
+void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface)
+{
+}
+
+static inline
 void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface)
 {
 }
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index c405d15befd6..2f0d42f2f913 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -989,6 +989,32 @@ void batadv_hardif_remove_interfaces(void)
 	rtnl_unlock();
 }
 
+/**
+ * batadv_hard_if_event_softif() - Handle events for soft interfaces
+ * @event: NETDEV_* event to handle
+ * @net_dev: net_device which generated an event
+ *
+ * Return: NOTIFY_* result
+ */
+static int batadv_hard_if_event_softif(unsigned long event,
+				       struct net_device *net_dev)
+{
+	struct batadv_priv *bat_priv;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		batadv_sysfs_add_meshif(net_dev);
+		bat_priv = netdev_priv(net_dev);
+		batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS);
+		break;
+	case NETDEV_CHANGENAME:
+		batadv_debugfs_rename_meshif(net_dev);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
 static int batadv_hard_if_event(struct notifier_block *this,
 				unsigned long event, void *ptr)
 {
@@ -997,12 +1023,8 @@ static int batadv_hard_if_event(struct notifier_block *this,
 	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_priv *bat_priv;
 
-	if (batadv_softif_is_valid(net_dev) && event == NETDEV_REGISTER) {
-		batadv_sysfs_add_meshif(net_dev);
-		bat_priv = netdev_priv(net_dev);
-		batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS);
-		return NOTIFY_DONE;
-	}
+	if (batadv_softif_is_valid(net_dev))
+		return batadv_hard_if_event_softif(event, net_dev);
 
 	hard_iface = batadv_hardif_get_by_netdev(net_dev);
 	if (!hard_iface && (event == NETDEV_REGISTER ||
@@ -1051,6 +1073,9 @@ static int batadv_hard_if_event(struct notifier_block *this,
 		if (batadv_is_wifi_hardif(hard_iface))
 			hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS;
 		break;
+	case NETDEV_CHANGENAME:
+		batadv_debugfs_rename_hardif(hard_iface);
+		break;
 	default:
 		break;
 	}
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 3986551397ca..12a2b7d21376 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1705,7 +1705,9 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
 		ether_addr_copy(common->addr, tt_addr);
 		common->vid = vid;
 
-		common->flags = flags;
+		if (!is_multicast_ether_addr(common->addr))
+			common->flags = flags & (~BATADV_TT_SYNC_MASK);
+
 		tt_global_entry->roam_at = 0;
 		/* node must store current time in case of roaming. This is
 		 * needed to purge this entry out on timeout (if nobody claims
@@ -1768,7 +1770,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
 		 * TT_CLIENT_TEMP, therefore they have to be copied in the
 		 * client entry
 		 */
-		common->flags |= flags & (~BATADV_TT_SYNC_MASK);
+		if (!is_multicast_ether_addr(common->addr))
+			common->flags |= flags & (~BATADV_TT_SYNC_MASK);
 
 		/* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only
 		 * one originator left in the list and we previously received a
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 510ab4f55df5..3264e1873219 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -437,13 +437,16 @@ static inline __poll_t bt_accept_poll(struct sock *parent)
 	return 0;
 }
 
-__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
+__poll_t bt_sock_poll(struct file *file, struct socket *sock,
+			  poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
 	BT_DBG("sock %p, sk %p", sock, sk);
 
+	poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_state == BT_LISTEN)
 		return bt_accept_poll(sk);
 
@@ -475,7 +478,7 @@ __poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
 
 	return mask;
 }
-EXPORT_SYMBOL(bt_sock_poll_mask);
+EXPORT_SYMBOL(bt_sock_poll);
 
 int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index d6c099861538..1506e1632394 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1975,7 +1975,7 @@ static const struct proto_ops hci_sock_ops = {
 	.sendmsg	= hci_sock_sendmsg,
 	.recvmsg	= hci_sock_recvmsg,
 	.ioctl		= hci_sock_ioctl,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= hci_sock_setsockopt,
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 742a190034e6..686bdc6b35b0 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1653,7 +1653,7 @@ static const struct proto_ops l2cap_sock_ops = {
 	.getname	= l2cap_sock_getname,
 	.sendmsg	= l2cap_sock_sendmsg,
 	.recvmsg	= l2cap_sock_recvmsg,
-	.poll_mask	= bt_sock_poll_mask,
+	.poll		= bt_sock_poll,
 	.ioctl		= bt_sock_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,
diff --git a/net/bluetooth/leds.c b/net/bluetooth/leds.c
index cb670b5594eb..6d59a5023231 100644
--- a/net/bluetooth/leds.c
+++ b/net/bluetooth/leds.c
@@ -43,7 +43,7 @@ void hci_leds_update_powered(struct hci_dev *hdev, bool enabled)
 	led_trigger_event(bt_power_led_trigger, enabled ? LED_FULL : LED_OFF);
 }
 
-static void power_activate(struct led_classdev *led_cdev)
+static int power_activate(struct led_classdev *led_cdev)
 {
 	struct hci_basic_led_trigger *htrig;
 	bool powered;
@@ -52,10 +52,12 @@ static void power_activate(struct led_classdev *led_cdev)
 	powered = test_bit(HCI_UP, &htrig->hdev->flags);
 
 	led_trigger_event(led_cdev->trigger, powered ? LED_FULL : LED_OFF);
+
+	return 0;
 }
 
 static struct led_trigger *led_allocate_basic(struct hci_dev *hdev,
-			void (*activate)(struct led_classdev *led_cdev),
+			int (*activate)(struct led_classdev *led_cdev),
 			const char *name)
 {
 	struct hci_basic_led_trigger *htrig;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 1cf57622473a..d606e9212291 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -1049,7 +1049,7 @@ static const struct proto_ops rfcomm_sock_ops = {
 	.setsockopt	= rfcomm_sock_setsockopt,
 	.getsockopt	= rfcomm_sock_getsockopt,
 	.ioctl		= rfcomm_sock_ioctl,
-	.poll_mask	= bt_sock_poll_mask,
+	.poll		= bt_sock_poll,
 	.socketpair	= sock_no_socketpair,
 	.mmap		= sock_no_mmap
 };
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index d60dbc61d170..413b8ee49fec 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1197,7 +1197,7 @@ static const struct proto_ops sco_sock_ops = {
 	.getname	= sco_sock_getname,
 	.sendmsg	= sco_sock_sendmsg,
 	.recvmsg	= sco_sock_recvmsg,
-	.poll_mask	= bt_sock_poll_mask,
+	.poll		= bt_sock_poll,
 	.ioctl		= bt_sock_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 68c3578343b4..22a78eedf4b1 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -96,6 +96,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	u32 size = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
 	u32 retval, duration;
+	int hh_len = ETH_HLEN;
 	struct sk_buff *skb;
 	void *data;
 	int ret;
@@ -131,12 +132,22 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	skb_reset_network_header(skb);
 
 	if (is_l2)
-		__skb_push(skb, ETH_HLEN);
+		__skb_push(skb, hh_len);
 	if (is_direct_pkt_access)
 		bpf_compute_data_pointers(skb);
 	retval = bpf_test_run(prog, skb, repeat, &duration);
-	if (!is_l2)
-		__skb_push(skb, ETH_HLEN);
+	if (!is_l2) {
+		if (skb_headroom(skb) < hh_len) {
+			int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
+
+			if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
+				kfree_skb(skb);
+				return -ENOMEM;
+			}
+		}
+		memset(__skb_push(skb, hh_len), 0, hh_len);
+	}
+
 	size = skb->len;
 	/* bpf program can never convert linear skb to non-linear */
 	if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
index a948b072c28f..76deb6615883 100644
--- a/net/bpfilter/Kconfig
+++ b/net/bpfilter/Kconfig
@@ -1,6 +1,5 @@
 menuconfig BPFILTER
 	bool "BPF based packet filtering framework (BPFILTER)"
-	default n
 	depends on NET && BPF && INET
 	help
 	  This builds experimental bpfilter framework that is aiming to
@@ -9,6 +8,7 @@ menuconfig BPFILTER
 if BPFILTER
 config BPFILTER_UMH
 	tristate "bpfilter kernel module with user mode helper"
+	depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC))
 	default m
 	help
 	  This builds bpfilter kernel module with embedded user mode helper
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
index dd86b022eff0..39c6980b5d99 100644
--- a/net/bpfilter/Makefile
+++ b/net/bpfilter/Makefile
@@ -15,20 +15,7 @@ ifeq ($(CONFIG_BPFILTER_UMH), y)
 HOSTLDFLAGS += -static
 endif
 
-# a bit of elf magic to convert bpfilter_umh binary into a binary blob
-# inside bpfilter_umh.o elf file referenced by
-# _binary_net_bpfilter_bpfilter_umh_start symbol
-# which bpfilter_kern.c passes further into umh blob loader at run-time
-quiet_cmd_copy_umh = GEN $@
-      cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \
-      $(OBJCOPY) -I binary \
-          `LC_ALL=C objdump -f net/bpfilter/bpfilter_umh \
-          |awk -F' |,' '/file format/{print "-O",$$NF} \
-          /^architecture:/{print "-B",$$2}'` \
-      --rename-section .data=.init.rodata $< $@
-
-$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh
-	$(call cmd,copy_umh)
+$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
 
 obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
-bpfilter-objs += bpfilter_kern.o bpfilter_umh.o
+bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
index 09522573f611..f0fc182d3db7 100644
--- a/net/bpfilter/bpfilter_kern.c
+++ b/net/bpfilter/bpfilter_kern.c
@@ -10,11 +10,8 @@
 #include <linux/file.h>
 #include "msgfmt.h"
 
-#define UMH_start _binary_net_bpfilter_bpfilter_umh_start
-#define UMH_end _binary_net_bpfilter_bpfilter_umh_end
-
-extern char UMH_start;
-extern char UMH_end;
+extern char bpfilter_umh_start;
+extern char bpfilter_umh_end;
 
 static struct umh_info info;
 /* since ip_getsockopt() can run in parallel, serialize access to umh */
@@ -93,7 +90,9 @@ static int __init load_umh(void)
 	int err;
 
 	/* fork usermode process */
-	err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info);
+	err = fork_usermode_blob(&bpfilter_umh_start,
+				 &bpfilter_umh_end - &bpfilter_umh_start,
+				 &info);
 	if (err)
 		return err;
 	pr_info("Loaded bpfilter_umh pid %d\n", info.pid);
diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S
new file mode 100644
index 000000000000..40311d10d2f2
--- /dev/null
+++ b/net/bpfilter/bpfilter_umh_blob.S
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+	.section .init.rodata, "a"
+	.global bpfilter_umh_start
+bpfilter_umh_start:
+	.incbin "net/bpfilter/bpfilter_umh"
+	.global bpfilter_umh_end
+bpfilter_umh_end:
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index e0adcd123f48..711d7156efd8 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -131,8 +131,10 @@ static void caif_flow_cb(struct sk_buff *skb)
 	caifd = caif_get(skb->dev);
 
 	WARN_ON(caifd == NULL);
-	if (caifd == NULL)
+	if (!caifd) {
+		rcu_read_unlock();
 		return;
+	}
 
 	caifd_hold(caifd);
 	rcu_read_unlock();
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index c7991867d622..a6fb1b3bcad9 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -934,11 +934,15 @@ static int caif_release(struct socket *sock)
 }
 
 /* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
-static __poll_t caif_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t caif_poll(struct file *file,
+			      struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
+	__poll_t mask;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
-	__poll_t mask = 0;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err)
@@ -972,7 +976,7 @@ static const struct proto_ops caif_seqpacket_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = sock_no_getname,
-	.poll_mask = caif_poll_mask,
+	.poll = caif_poll,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = sock_no_shutdown,
@@ -993,7 +997,7 @@ static const struct proto_ops caif_stream_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = sock_no_getname,
-	.poll_mask = caif_poll_mask,
+	.poll = caif_poll,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = sock_no_shutdown,
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 9393f25df08d..0af8f0db892a 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1660,7 +1660,7 @@ static const struct proto_ops bcm_ops = {
 	.socketpair    = sock_no_socketpair,
 	.accept        = sock_no_accept,
 	.getname       = sock_no_getname,
-	.poll_mask     = datagram_poll_mask,
+	.poll          = datagram_poll,
 	.ioctl         = can_ioctl,	/* use can_ioctl() from af_can.c */
 	.listen        = sock_no_listen,
 	.shutdown      = sock_no_shutdown,
diff --git a/net/can/raw.c b/net/can/raw.c
index fd7e2f49ea6a..1051eee82581 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -843,7 +843,7 @@ static const struct proto_ops raw_ops = {
 	.socketpair    = sock_no_socketpair,
 	.accept        = sock_no_accept,
 	.getname       = raw_getname,
-	.poll_mask     = datagram_poll_mask,
+	.poll          = datagram_poll,
 	.ioctl         = can_ioctl,	/* use can_ioctl() from af_can.c */
 	.listen        = sock_no_listen,
 	.shutdown      = sock_no_shutdown,
diff --git a/net/core/datagram.c b/net/core/datagram.c
index f19bf3dc2bd6..9938952c5c78 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -819,8 +819,9 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
 
 /**
  * 	datagram_poll - generic datagram poll
+ *	@file: file struct
  *	@sock: socket
- *	@events to wait for
+ *	@wait: poll table
  *
  *	Datagram poll: Again totally generic. This also handles
  *	sequenced packet sockets providing the socket receive queue
@@ -830,10 +831,14 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
  *	and you use a different write policy from sock_writeable()
  *	then please supply your own write_space callback.
  */
-__poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
+__poll_t datagram_poll(struct file *file, struct socket *sock,
+			   poll_table *wait)
 {
 	struct sock *sk = sock->sk;
-	__poll_t mask = 0;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -866,4 +871,4 @@ __poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
 
 	return mask;
 }
-EXPORT_SYMBOL(datagram_poll_mask);
+EXPORT_SYMBOL(datagram_poll);
diff --git a/net/core/dev.c b/net/core/dev.c
index a5aa1c7444e6..559a91271f82 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7149,16 +7149,19 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
 		dev->tx_queue_len = new_len;
 		res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev);
 		res = notifier_to_errno(res);
-		if (res) {
-			netdev_err(dev,
-				   "refused to change device tx_queue_len\n");
-			dev->tx_queue_len = orig_len;
-			return res;
-		}
-		return dev_qdisc_change_tx_queue_len(dev);
+		if (res)
+			goto err_rollback;
+		res = dev_qdisc_change_tx_queue_len(dev);
+		if (res)
+			goto err_rollback;
 	}
 
 	return 0;
+
+err_rollback:
+	netdev_err(dev, "refused to change device tx_queue_len\n");
+	dev->tx_queue_len = orig_len;
+	return res;
 }
 
 /**
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index a04e1e88bf3a..50537ff961a7 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 		if (ifr->ifr_qlen < 0)
 			return -EINVAL;
 		if (dev->tx_queue_len ^ ifr->ifr_qlen) {
-			unsigned int orig_len = dev->tx_queue_len;
-
-			dev->tx_queue_len = ifr->ifr_qlen;
-			err = call_netdevice_notifiers(
-					NETDEV_CHANGE_TX_QUEUE_LEN, dev);
-			err = notifier_to_errno(err);
-			if (err) {
-				dev->tx_queue_len = orig_len;
+			err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+			if (err)
 				return err;
-			}
 		}
 		return 0;
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 126ffc5bc630..f64aa13811ea 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -416,6 +416,14 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
 		if (rule->mark && r->mark != rule->mark)
 			continue;
 
+		if (rule->suppress_ifgroup != -1 &&
+		    r->suppress_ifgroup != rule->suppress_ifgroup)
+			continue;
+
+		if (rule->suppress_prefixlen != -1 &&
+		    r->suppress_prefixlen != rule->suppress_prefixlen)
+			continue;
+
 		if (rule->mark_mask && r->mark_mask != rule->mark_mask)
 			continue;
 
@@ -436,6 +444,9 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
 		if (rule->ip_proto && r->ip_proto != rule->ip_proto)
 			continue;
 
+		if (rule->proto && r->proto != rule->proto)
+			continue;
+
 		if (fib_rule_port_range_set(&rule->sport_range) &&
 		    !fib_rule_port_range_compare(&r->sport_range,
 						 &rule->sport_range))
@@ -645,6 +656,73 @@ errout:
 	return err;
 }
 
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+		       struct nlattr **tb, struct fib_rule *rule)
+{
+	struct fib_rule *r;
+
+	list_for_each_entry(r, &ops->rules_list, list) {
+		if (r->action != rule->action)
+			continue;
+
+		if (r->table != rule->table)
+			continue;
+
+		if (r->pref != rule->pref)
+			continue;
+
+		if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+			continue;
+
+		if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+			continue;
+
+		if (r->mark != rule->mark)
+			continue;
+
+		if (r->suppress_ifgroup != rule->suppress_ifgroup)
+			continue;
+
+		if (r->suppress_prefixlen != rule->suppress_prefixlen)
+			continue;
+
+		if (r->mark_mask != rule->mark_mask)
+			continue;
+
+		if (r->tun_id != rule->tun_id)
+			continue;
+
+		if (r->fr_net != rule->fr_net)
+			continue;
+
+		if (r->l3mdev != rule->l3mdev)
+			continue;
+
+		if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+		    !uid_eq(r->uid_range.end, rule->uid_range.end))
+			continue;
+
+		if (r->ip_proto != rule->ip_proto)
+			continue;
+
+		if (r->proto != rule->proto)
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->sport_range,
+						 &rule->sport_range))
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->dport_range,
+						 &rule->dport_range))
+			continue;
+
+		if (!ops->compare(r, frh, tb))
+			continue;
+		return 1;
+	}
+	return 0;
+}
+
 int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		   struct netlink_ext_ack *extack)
 {
@@ -679,7 +757,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 
 	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
-	    rule_find(ops, frh, tb, rule, user_priority)) {
+	    rule_exists(ops, frh, tb, rule)) {
 		err = -EEXIST;
 		goto errout_free;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index e7f12e9f598c..9dfd145eedcc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -459,11 +459,21 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
 	     (!unaligned_ok && offset >= 0 &&
 	      offset + ip_align >= 0 &&
 	      offset + ip_align % size == 0))) {
+		bool ldx_off_ok = offset <= S16_MAX;
+
 		*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
 		*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
-		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian);
-		*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D,
-				      offset);
+		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
+				      size, 2 + endian + (!ldx_off_ok * 2));
+		if (ldx_off_ok) {
+			*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+					      BPF_REG_D, offset);
+		} else {
+			*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D);
+			*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset);
+			*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+					      BPF_REG_TMP, 0);
+		}
 		if (endian)
 			*insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8);
 		*insn++ = BPF_JMP_A(8);
@@ -1702,24 +1712,26 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
 BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
 	   u32, offset, void *, to, u32, len, u32, start_header)
 {
+	u8 *end = skb_tail_pointer(skb);
+	u8 *net = skb_network_header(skb);
+	u8 *mac = skb_mac_header(skb);
 	u8 *ptr;
 
-	if (unlikely(offset > 0xffff || len > skb_headlen(skb)))
+	if (unlikely(offset > 0xffff || len > (end - mac)))
 		goto err_clear;
 
 	switch (start_header) {
 	case BPF_HDR_START_MAC:
-		ptr = skb_mac_header(skb) + offset;
+		ptr = mac + offset;
 		break;
 	case BPF_HDR_START_NET:
-		ptr = skb_network_header(skb) + offset;
+		ptr = net + offset;
 		break;
 	default:
 		goto err_clear;
 	}
 
-	if (likely(ptr >= skb_mac_header(skb) &&
-		   ptr + len <= skb_tail_pointer(skb))) {
+	if (likely(ptr >= mac && ptr + len <= end)) {
 		memcpy(to, ptr, len);
 		return 0;
 	}
@@ -1762,6 +1774,37 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static inline int sk_skb_try_make_writable(struct sk_buff *skb,
+					   unsigned int write_len)
+{
+	int err = __bpf_try_make_writable(skb, write_len);
+
+	bpf_compute_data_end_sk_skb(skb);
+	return err;
+}
+
+BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len)
+{
+	/* Idea is the following: should the needed direct read/write
+	 * test fail during runtime, we can pull in more data and redo
+	 * again, since implicitly, we invalidate previous checks here.
+	 *
+	 * Or, since we know how much we need to make read/writeable,
+	 * this can be done once at the program beginning for direct
+	 * access case. By this we overcome limitations of only current
+	 * headroom being accessible.
+	 */
+	return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb));
+}
+
+static const struct bpf_func_proto sk_skb_pull_data_proto = {
+	.func		= sk_skb_pull_data,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset,
 	   u64, from, u64, to, u64, flags)
 {
@@ -2779,7 +2822,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
 
 static u32 __bpf_skb_max_len(const struct sk_buff *skb)
 {
-	return skb->dev->mtu + skb->dev->hard_header_len;
+	return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
+			  SKB_MAX_ALLOC;
 }
 
 static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
@@ -2863,8 +2907,8 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len)
 	return __skb_trim_rcsum(skb, new_len);
 }
 
-BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
-	   u64, flags)
+static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len,
+					u64 flags)
 {
 	u32 max_len = __bpf_skb_max_len(skb);
 	u32 min_len = __bpf_skb_min_len(skb);
@@ -2900,6 +2944,13 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
 		if (!ret && skb_is_gso(skb))
 			skb_gso_reset(skb);
 	}
+	return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
+	   u64, flags)
+{
+	int ret = __bpf_skb_change_tail(skb, new_len, flags);
 
 	bpf_compute_data_pointers(skb);
 	return ret;
@@ -2914,9 +2965,27 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len,
 	   u64, flags)
 {
+	int ret = __bpf_skb_change_tail(skb, new_len, flags);
+
+	bpf_compute_data_end_sk_skb(skb);
+	return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_tail_proto = {
+	.func		= sk_skb_change_tail,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
+					u64 flags)
+{
 	u32 max_len = __bpf_skb_max_len(skb);
 	u32 new_len = skb->len + head_room;
 	int ret;
@@ -2941,8 +3010,16 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
 		skb_reset_mac_header(skb);
 	}
 
+	return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+	   u64, flags)
+{
+	int ret = __bpf_skb_change_head(skb, head_room, flags);
+
 	bpf_compute_data_pointers(skb);
-	return 0;
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_skb_change_head_proto = {
@@ -2954,6 +3031,23 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room,
+	   u64, flags)
+{
+	int ret = __bpf_skb_change_head(skb, head_room, flags);
+
+	bpf_compute_data_end_sk_skb(skb);
+	return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_head_proto = {
+	.func		= sk_skb_change_head,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+};
 static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
 {
 	return xdp_data_meta_unsupported(xdp) ? 0 :
@@ -3046,12 +3140,16 @@ static int __bpf_tx_xdp(struct net_device *dev,
 			u32 index)
 {
 	struct xdp_frame *xdpf;
-	int sent;
+	int err, sent;
 
 	if (!dev->netdev_ops->ndo_xdp_xmit) {
 		return -EOPNOTSUPP;
 	}
 
+	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+	if (unlikely(err))
+		return err;
+
 	xdpf = convert_to_xdp_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
@@ -3285,7 +3383,8 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 		goto err;
 	}
 
-	if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+	err = xdp_ok_fwd_dev(fwd, skb->len);
+	if (unlikely(err))
 		goto err;
 
 	skb->dev = fwd;
@@ -4073,8 +4172,9 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
 	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
 	params->h_vlan_TCI = 0;
 	params->h_vlan_proto = 0;
+	params->ifindex = dev->ifindex;
 
-	return dev->ifindex;
+	return 0;
 }
 #endif
 
@@ -4098,7 +4198,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	/* verify forwarding is enabled on this interface */
 	in_dev = __in_dev_get_rcu(dev);
 	if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
-		return 0;
+		return BPF_FIB_LKUP_RET_FWD_DISABLED;
 
 	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
 		fl4.flowi4_iif = 1;
@@ -4123,7 +4223,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 		tb = fib_get_table(net, tbid);
 		if (unlikely(!tb))
-			return 0;
+			return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 		err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
 	} else {
@@ -4135,8 +4235,20 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
 	}
 
-	if (err || res.type != RTN_UNICAST)
-		return 0;
+	if (err) {
+		/* map fib lookup errors to RTN_ type */
+		if (err == -EINVAL)
+			return BPF_FIB_LKUP_RET_BLACKHOLE;
+		if (err == -EHOSTUNREACH)
+			return BPF_FIB_LKUP_RET_UNREACHABLE;
+		if (err == -EACCES)
+			return BPF_FIB_LKUP_RET_PROHIBIT;
+
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
+	}
+
+	if (res.type != RTN_UNICAST)
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 	if (res.fi->fib_nhs > 1)
 		fib_select_path(net, &res, &fl4, NULL);
@@ -4144,19 +4256,16 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (check_mtu) {
 		mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
 		if (params->tot_len > mtu)
-			return 0;
+			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
 	nh = &res.fi->fib_nh[res.nh_sel];
 
 	/* do not handle lwt encaps right now */
 	if (nh->nh_lwtstate)
-		return 0;
+		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
 	dev = nh->nh_dev;
-	if (unlikely(!dev))
-		return 0;
-
 	if (nh->nh_gw)
 		params->ipv4_dst = nh->nh_gw;
 
@@ -4166,10 +4275,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	 * rcu_read_lock_bh is not needed here
 	 */
 	neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
-	if (neigh)
-		return bpf_fib_set_fwd_params(params, neigh, dev);
+	if (!neigh)
+		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return 0;
+	return bpf_fib_set_fwd_params(params, neigh, dev);
 }
 #endif
 
@@ -4190,7 +4299,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	/* link local addresses are never forwarded */
 	if (rt6_need_strict(dst) || rt6_need_strict(src))
-		return 0;
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 	dev = dev_get_by_index_rcu(net, params->ifindex);
 	if (unlikely(!dev))
@@ -4198,7 +4307,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	idev = __in6_dev_get_safely(dev);
 	if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
-		return 0;
+		return BPF_FIB_LKUP_RET_FWD_DISABLED;
 
 	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
 		fl6.flowi6_iif = 1;
@@ -4225,7 +4334,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 		tb = ipv6_stub->fib6_get_table(net, tbid);
 		if (unlikely(!tb))
-			return 0;
+			return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 		f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
 	} else {
@@ -4238,11 +4347,23 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	}
 
 	if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
-		return 0;
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
+
+	if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
+		switch (f6i->fib6_type) {
+		case RTN_BLACKHOLE:
+			return BPF_FIB_LKUP_RET_BLACKHOLE;
+		case RTN_UNREACHABLE:
+			return BPF_FIB_LKUP_RET_UNREACHABLE;
+		case RTN_PROHIBIT:
+			return BPF_FIB_LKUP_RET_PROHIBIT;
+		default:
+			return BPF_FIB_LKUP_RET_NOT_FWDED;
+		}
+	}
 
-	if (unlikely(f6i->fib6_flags & RTF_REJECT ||
-	    f6i->fib6_type != RTN_UNICAST))
-		return 0;
+	if (f6i->fib6_type != RTN_UNICAST)
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 	if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
 		f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
@@ -4252,11 +4373,11 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (check_mtu) {
 		mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
 		if (params->tot_len > mtu)
-			return 0;
+			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
 	if (f6i->fib6_nh.nh_lwtstate)
-		return 0;
+		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
 	if (f6i->fib6_flags & RTF_GATEWAY)
 		*dst = f6i->fib6_nh.nh_gw;
@@ -4270,10 +4391,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	 */
 	neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
 				      ndisc_hashfn, dst, dev);
-	if (neigh)
-		return bpf_fib_set_fwd_params(params, neigh, dev);
+	if (!neigh)
+		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return 0;
+	return bpf_fib_set_fwd_params(params, neigh, dev);
 }
 #endif
 
@@ -4315,7 +4436,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
 {
 	struct net *net = dev_net(skb->dev);
-	int index = -EAFNOSUPPORT;
+	int rc = -EAFNOSUPPORT;
 
 	if (plen < sizeof(*params))
 		return -EINVAL;
@@ -4326,25 +4447,25 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 	switch (params->family) {
 #if IS_ENABLED(CONFIG_INET)
 	case AF_INET:
-		index = bpf_ipv4_fib_lookup(net, params, flags, false);
+		rc = bpf_ipv4_fib_lookup(net, params, flags, false);
 		break;
 #endif
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		index = bpf_ipv6_fib_lookup(net, params, flags, false);
+		rc = bpf_ipv6_fib_lookup(net, params, flags, false);
 		break;
 #endif
 	}
 
-	if (index > 0) {
+	if (!rc) {
 		struct net_device *dev;
 
-		dev = dev_get_by_index_rcu(net, index);
+		dev = dev_get_by_index_rcu(net, params->ifindex);
 		if (!is_skb_forwardable(dev, skb))
-			index = 0;
+			rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
-	return index;
+	return rc;
 }
 
 static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
@@ -4417,10 +4538,10 @@ static const struct bpf_func_proto bpf_lwt_push_encap_proto = {
 	.arg4_type	= ARG_CONST_SIZE
 };
 
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
 	   const void *, from, u32, len)
 {
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	void *srh_tlvs, *srh_end, *ptr;
@@ -4446,9 +4567,6 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
 
 	memcpy(skb->data + offset, from, len);
 	return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
-	return -EOPNOTSUPP;
-#endif
 }
 
 static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
@@ -4464,7 +4582,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
 BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
 	   u32, action, void *, param, u32, param_len)
 {
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	struct ipv6_sr_hdr *srh;
@@ -4512,9 +4629,6 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
 	default:
 		return -EINVAL;
 	}
-#else /* CONFIG_IPV6_SEG6_BPF */
-	return -EOPNOTSUPP;
-#endif
 }
 
 static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
@@ -4530,7 +4644,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
 BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
 	   s32, len)
 {
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	void *srh_end, *srh_tlvs, *ptr;
@@ -4574,9 +4687,6 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
 	srh_state->hdrlen += len;
 	srh_state->valid = 0;
 	return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
-	return -EOPNOTSUPP;
-#endif
 }
 
 static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
@@ -4587,6 +4697,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 	.arg2_type	= ARG_ANYTHING,
 	.arg3_type	= ARG_ANYTHING,
 };
+#endif /* CONFIG_IPV6_SEG6_BPF */
 
 bool bpf_helper_changes_pkt_data(void *func)
 {
@@ -4595,9 +4706,12 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_skb_store_bytes ||
 	    func == bpf_skb_change_proto ||
 	    func == bpf_skb_change_head ||
+	    func == sk_skb_change_head ||
 	    func == bpf_skb_change_tail ||
+	    func == sk_skb_change_tail ||
 	    func == bpf_skb_adjust_room ||
 	    func == bpf_skb_pull_data ||
+	    func == sk_skb_pull_data ||
 	    func == bpf_clone_redirect ||
 	    func == bpf_l3_csum_replace ||
 	    func == bpf_l4_csum_replace ||
@@ -4605,11 +4719,12 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_xdp_adjust_meta ||
 	    func == bpf_msg_pull_data ||
 	    func == bpf_xdp_adjust_tail ||
-	    func == bpf_lwt_push_encap ||
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	    func == bpf_lwt_seg6_store_bytes ||
 	    func == bpf_lwt_seg6_adjust_srh ||
-	    func == bpf_lwt_seg6_action
-	    )
+	    func == bpf_lwt_seg6_action ||
+#endif
+	    func == bpf_lwt_push_encap)
 		return true;
 
 	return false;
@@ -4849,11 +4964,11 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
 	case BPF_FUNC_skb_pull_data:
-		return &bpf_skb_pull_data_proto;
+		return &sk_skb_pull_data_proto;
 	case BPF_FUNC_skb_change_tail:
-		return &bpf_skb_change_tail_proto;
+		return &sk_skb_change_tail_proto;
 	case BPF_FUNC_skb_change_head:
-		return &bpf_skb_change_head_proto;
+		return &sk_skb_change_head_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
@@ -4944,12 +5059,14 @@ static const struct bpf_func_proto *
 lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	case BPF_FUNC_lwt_seg6_store_bytes:
 		return &bpf_lwt_seg6_store_bytes_proto;
 	case BPF_FUNC_lwt_seg6_action:
 		return &bpf_lwt_seg6_action_proto;
 	case BPF_FUNC_lwt_seg6_adjust_srh:
 		return &bpf_lwt_seg6_adjust_srh_proto;
+#endif
 	default:
 		return lwt_out_func_proto(func_id, prog);
 	}
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index b2b2323bdc84..188d693cb251 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -77,8 +77,20 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
 		d->lock = lock;
 		spin_lock_bh(lock);
 	}
-	if (d->tail)
-		return gnet_stats_copy(d, type, NULL, 0, padattr);
+	if (d->tail) {
+		int ret = gnet_stats_copy(d, type, NULL, 0, padattr);
+
+		/* The initial attribute added in gnet_stats_copy() may be
+		 * preceded by a padding attribute, in which case d->tail will
+		 * end up pointing at the padding instead of the real attribute.
+		 * Fix this so gnet_stats_finish_copy() adjusts the length of
+		 * the right attribute.
+		 */
+		if (ret == 0 && d->tail->nla_type == padattr)
+			d->tail = (struct nlattr *)((char *)d->tail +
+						    NLA_ALIGN(d->tail->nla_len));
+		return ret;
+	}
 
 	return 0;
 }
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index e7e626fb87bb..e45098593dc0 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -217,7 +217,7 @@ static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog,
 	if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME])
 		return -EINVAL;
 
-	prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL);
+	prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_ATOMIC);
 	if (!prog->name)
 		return -ENOMEM;
 
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 68bf07206744..43a932cb609b 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool)
 	struct page *page;
 
 	/* Empty recycle ring */
-	while ((page = ptr_ring_consume(&pool->ring))) {
+	while ((page = ptr_ring_consume_bh(&pool->ring))) {
 		/* Verify the refcnt invariant of cached pages */
 		if (!(page_ref_count(page) == 1))
 			pr_crit("%s() page_pool refcnt %d violation\n",
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ef61222fdef..e3f743c141b3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2759,9 +2759,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 			return err;
 	}
 
-	dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
-	__dev_notify_flags(dev, old_flags, ~0U);
+	if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+		__dev_notify_flags(dev, old_flags, 0U);
+	} else {
+		dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+		__dev_notify_flags(dev, old_flags, ~0U);
+	}
 	return 0;
 }
 EXPORT_SYMBOL(rtnl_configure_link);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c642304f178c..fb35b62af272 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -858,6 +858,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	n->cloned = 1;
 	n->nohdr = 0;
 	n->peeked = 0;
+	C(pfmemalloc);
 	n->destructor = NULL;
 	C(tail);
 	C(end);
@@ -3719,6 +3720,7 @@ normal:
 				net_warn_ratelimited(
 					"skb_segment: too many frags: %u %u\n",
 					pos, mss);
+				err = -EINVAL;
 				goto err;
 			}
 
@@ -3752,11 +3754,10 @@ skip_fraglist:
 
 perform_csum_check:
 		if (!csum) {
-			if (skb_has_shared_frag(nskb)) {
-				err = __skb_linearize(nskb);
-				if (err)
-					goto err;
-			}
+			if (skb_has_shared_frag(nskb) &&
+			    __skb_linearize(nskb))
+				goto err;
+
 			if (!nskb->remcsum_offload)
 				nskb->ip_summed = CHECKSUM_NONE;
 			SKB_GSO_CB(nskb)->csum =
@@ -5276,8 +5277,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 			if (npages >= 1 << order) {
 				page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
 						   __GFP_COMP |
-						   __GFP_NOWARN |
-						   __GFP_NORETRY,
+						   __GFP_NOWARN,
 						   order);
 				if (page)
 					goto fill_page;
diff --git a/net/core/sock.c b/net/core/sock.c
index bcc41829a16d..bc2d7a37297f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2277,9 +2277,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
 		pfrag->offset += use;
 
 		sge = sg + sg_curr - 1;
-		if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page &&
-		    sg->offset + sg->length == orig_offset) {
-			sg->length += use;
+		if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page &&
+		    sge->offset + sge->length == orig_offset) {
+			sge->length += use;
 		} else {
 			sge = sg + sg_curr;
 			sg_unmark_end(sge);
@@ -3243,7 +3243,8 @@ static int req_prot_init(const struct proto *prot)
 
 	rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
 					   rsk_prot->obj_size, 0,
-					   prot->slab_flags, NULL);
+					   SLAB_ACCOUNT | prot->slab_flags,
+					   NULL);
 
 	if (!rsk_prot->slab) {
 		pr_crit("%s: Can't create request sock SLAB cache!\n",
@@ -3258,7 +3259,8 @@ int proto_register(struct proto *prot, int alloc_slab)
 	if (alloc_slab) {
 		prot->slab = kmem_cache_create_usercopy(prot->name,
 					prot->obj_size, 0,
-					SLAB_HWCACHE_ALIGN | prot->slab_flags,
+					SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT |
+					prot->slab_flags,
 					prot->useroffset, prot->usersize,
 					NULL);
 
@@ -3281,6 +3283,7 @@ int proto_register(struct proto *prot, int alloc_slab)
 				kmem_cache_create(prot->twsk_prot->twsk_slab_name,
 						  prot->twsk_prot->twsk_obj_size,
 						  0,
+						  SLAB_ACCOUNT |
 						  prot->slab_flags,
 						  NULL);
 			if (prot->twsk_prot->twsk_slab == NULL)
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 9d1f22072d5d..6771f1855b96 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -345,7 +345,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		rcu_read_lock();
 		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
-		xa->zc_alloc->free(xa->zc_alloc, handle);
+		if (!WARN_ON_ONCE(!xa))
+			xa->zc_alloc->free(xa->zc_alloc, handle);
 		rcu_read_unlock();
 	default:
 		/* Not possible, checked in xdp_rxq_info_reg_mem_model() */
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 2b75df469220..842a9c7c73a3 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -229,14 +229,16 @@ static void ccid2_cwnd_restart(struct sock *sk, const u32 now)
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
 	u32 cwnd = hc->tx_cwnd, restart_cwnd,
 	    iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache);
+	s32 delta = now - hc->tx_lsndtime;
 
 	hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2));
 
 	/* don't reduce cwnd below the initial window (IW) */
 	restart_cwnd = min(cwnd, iwnd);
-	cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto;
-	hc->tx_cwnd = max(cwnd, restart_cwnd);
 
+	while ((delta -= hc->tx_rto) >= 0 && cwnd > restart_cwnd)
+		cwnd >>= 1;
+	hc->tx_cwnd = max(cwnd, restart_cwnd);
 	hc->tx_cwnd_stamp = now;
 	hc->tx_cwnd_used  = 0;
 
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 8b5ba6dffac7..12877a1514e7 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -600,7 +600,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
 {
 	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
-	ktime_t now = ktime_get_real();
+	ktime_t now = ktime_get();
 	s64 delta = 0;
 
 	switch (fbtype) {
@@ -625,15 +625,14 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
 	case CCID3_FBACK_PERIODIC:
 		delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback);
 		if (delta <= 0)
-			DCCP_BUG("delta (%ld) <= 0", (long)delta);
-		else
-			hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
+			delta = 1;
+		hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
 		break;
 	default:
 		return;
 	}
 
-	ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta,
+	ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta,
 		       hc->rx_x_recv, hc->rx_pinv);
 
 	hc->rx_tstamp_last_feedback = now;
@@ -680,7 +679,8 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb)
 static u32 ccid3_first_li(struct sock *sk)
 {
 	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-	u32 x_recv, p, delta;
+	u32 x_recv, p;
+	s64 delta;
 	u64 fval;
 
 	if (hc->rx_rtt == 0) {
@@ -688,7 +688,9 @@ static u32 ccid3_first_li(struct sock *sk)
 		hc->rx_rtt = DCCP_FALLBACK_RTT;
 	}
 
-	delta  = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback));
+	delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback);
+	if (delta <= 0)
+		delta = 1;
 	x_recv = scaled_div32(hc->rx_bytes_recv, delta);
 	if (x_recv == 0) {		/* would also trigger divide-by-zero */
 		DCCP_WARN("X_recv==0\n");
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 0ea2ee56ac1b..f91e3816806b 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -316,7 +316,8 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		 int flags, int *addr_len);
 void dccp_shutdown(struct sock *sk, int how);
 int inet_dccp_listen(struct socket *sock, int backlog);
-__poll_t dccp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t dccp_poll(struct file *file, struct socket *sock,
+		       poll_table *wait);
 int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 void dccp_req_err(struct sock *sk, u64 seq);
 
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index a9e478cd3787..b08feb219b44 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -984,7 +984,7 @@ static const struct proto_ops inet_dccp_ops = {
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,
 	/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
-	.poll_mask	   = dccp_poll_mask,
+	.poll		   = dccp_poll,
 	.ioctl		   = inet_ioctl,
 	/* FIXME: work on inet_listen to rename it to sock_common_listen */
 	.listen		   = inet_dccp_listen,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 17fc4e0166ba..6344f1b18a6a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1070,7 +1070,7 @@ static const struct proto_ops inet6_dccp_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet6_getname,
-	.poll_mask	   = dccp_poll_mask,
+	.poll		   = dccp_poll,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = inet_dccp_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index ca21c1c76da0..0d56e36a6db7 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -312,11 +312,20 @@ int dccp_disconnect(struct sock *sk, int flags)
 
 EXPORT_SYMBOL_GPL(dccp_disconnect);
 
-__poll_t dccp_poll_mask(struct socket *sock, __poll_t events)
+/*
+ *	Wait for a DCCP event.
+ *
+ *	Note that we don't need to lock the socket, as the upper poll layers
+ *	take care of normal races (between the test and the event) and we don't
+ *	go look at any of the socket buffers directly.
+ */
+__poll_t dccp_poll(struct file *file, struct socket *sock,
+		       poll_table *wait)
 {
 	__poll_t mask;
 	struct sock *sk = sock->sk;
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
 	if (sk->sk_state == DCCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
@@ -358,7 +367,7 @@ __poll_t dccp_poll_mask(struct socket *sock, __poll_t events)
 	return mask;
 }
 
-EXPORT_SYMBOL_GPL(dccp_poll_mask);
+EXPORT_SYMBOL_GPL(dccp_poll);
 
 int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 9a686d890bfa..7d6ff983ba2c 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1207,11 +1207,11 @@ static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int peer)
 }
 
 
-static __poll_t dn_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table  *wait)
 {
 	struct sock *sk = sock->sk;
 	struct dn_scp *scp = DN_SK(sk);
-	__poll_t mask = datagram_poll_mask(sock, events);
+	__poll_t mask = datagram_poll(file, sock, wait);
 
 	if (!skb_queue_empty(&scp->other_receive_queue))
 		mask |= EPOLLRDBAND;
@@ -2331,7 +2331,7 @@ static const struct proto_ops dn_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	dn_accept,
 	.getname =	dn_getname,
-	.poll_mask =	dn_poll_mask,
+	.poll =		dn_poll,
 	.ioctl =	dn_ioctl,
 	.listen =	dn_listen,
 	.shutdown =	dn_shutdown,
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 40c851693f77..0c9478b91fa5 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -86,35 +86,39 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 		opt++;
 		kdebug("options: '%s'", opt);
 		do {
+			int opt_len, opt_nlen;
 			const char *eq;
-			int opt_len, opt_nlen, opt_vlen, tmp;
+			char optval[128];
 
 			next_opt = memchr(opt, '#', end - opt) ?: end;
 			opt_len = next_opt - opt;
-			if (opt_len <= 0 || opt_len > 128) {
+			if (opt_len <= 0 || opt_len > sizeof(optval)) {
 				pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
 						    opt_len);
 				return -EINVAL;
 			}
 
-			eq = memchr(opt, '=', opt_len) ?: end;
-			opt_nlen = eq - opt;
-			eq++;
-			opt_vlen = next_opt - eq; /* will be -1 if no value */
+			eq = memchr(opt, '=', opt_len);
+			if (eq) {
+				opt_nlen = eq - opt;
+				eq++;
+				memcpy(optval, eq, next_opt - eq);
+				optval[next_opt - eq] = '\0';
+			} else {
+				opt_nlen = opt_len;
+				optval[0] = '\0';
+			}
 
-			tmp = opt_vlen >= 0 ? opt_vlen : 0;
-			kdebug("option '%*.*s' val '%*.*s'",
-			       opt_nlen, opt_nlen, opt, tmp, tmp, eq);
+			kdebug("option '%*.*s' val '%s'",
+			       opt_nlen, opt_nlen, opt, optval);
 
 			/* see if it's an error number representing a DNS error
 			 * that's to be recorded as the result in this key */
 			if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 &&
 			    memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) {
 				kdebug("dns error number option");
-				if (opt_vlen <= 0)
-					goto bad_option_value;
 
-				ret = kstrtoul(eq, 10, &derrno);
+				ret = kstrtoul(optval, 10, &derrno);
 				if (ret < 0)
 					goto bad_option_value;
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 1e3b6a6d8a40..9864bcd3d317 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -639,7 +639,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev)
+	if (!dev->phydev && !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->set_mac_eee)
@@ -659,7 +659,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev)
+	if (!dev->phydev && !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->get_mac_eee)
@@ -1248,6 +1248,9 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
 
+	if (!netif_running(slave_dev))
+		return 0;
+
 	netif_device_detach(slave_dev);
 
 	rtnl_lock();
@@ -1261,6 +1264,9 @@ int dsa_slave_resume(struct net_device *slave_dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
 
+	if (!netif_running(slave_dev))
+		return 0;
+
 	netif_device_attach(slave_dev);
 
 	rtnl_lock();
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 275449b0d633..3297e7fa9945 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -90,12 +90,18 @@ static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n)
 	return 0;
 }
 
+static int lowpan_get_iflink(const struct net_device *dev)
+{
+	return lowpan_802154_dev(dev)->wdev->ifindex;
+}
+
 static const struct net_device_ops lowpan_netdev_ops = {
 	.ndo_init		= lowpan_dev_init,
 	.ndo_start_xmit		= lowpan_xmit,
 	.ndo_open		= lowpan_open,
 	.ndo_stop		= lowpan_stop,
 	.ndo_neigh_construct    = lowpan_neigh_construct,
+	.ndo_get_iflink         = lowpan_get_iflink,
 };
 
 static void lowpan_setup(struct net_device *ldev)
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index a0768d2759b8..a60658c85a9a 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -423,7 +423,7 @@ static const struct proto_ops ieee802154_raw_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = sock_no_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = ieee802154_sock_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = sock_no_shutdown,
@@ -969,7 +969,7 @@ static const struct proto_ops ieee802154_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = sock_no_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = ieee802154_sock_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = sock_no_shutdown,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 15e125558c76..b403499fdabe 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -986,7 +986,7 @@ const struct proto_ops inet_stream_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,
-	.poll_mask	   = tcp_poll_mask,
+	.poll		   = tcp_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = inet_listen,
 	.shutdown	   = inet_shutdown,
@@ -1021,7 +1021,7 @@ const struct proto_ops inet_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = inet_getname,
-	.poll_mask	   = udp_poll_mask,
+	.poll		   = udp_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
@@ -1042,7 +1042,7 @@ EXPORT_SYMBOL(inet_dgram_ops);
 
 /*
  * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
- * udp_poll_mask
+ * udp_poll
  */
 static const struct proto_ops inet_sockraw_ops = {
 	.family		   = PF_INET,
@@ -1053,7 +1053,7 @@ static const struct proto_ops inet_sockraw_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = inet_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b21833651394..2998b0e47d4b 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -292,18 +292,19 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 		return ip_hdr(skb)->daddr;
 
 	in_dev = __in_dev_get_rcu(dev);
-	BUG_ON(!in_dev);
 
 	net = dev_net(dev);
 
 	scope = RT_SCOPE_UNIVERSE;
 	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
+		bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev);
 		struct flowi4 fl4 = {
 			.flowi4_iif = LOOPBACK_IFINDEX,
+			.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
 			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
 			.flowi4_scope = scope,
-			.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
+			.flowi4_mark = vmark ? skb->mark : 0,
 		};
 		if (!fib_lookup(net, &fl4, &res, 0))
 			return FIB_RES_PREFSRC(net, res);
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 1540db65241a..c9ec1603666b 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -448,9 +448,7 @@ next_proto:
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
-	skb_gro_remcsum_cleanup(skb, &grc);
-	skb->remcsum_offload = 0;
+	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
 
 	return pp;
 }
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 1859c473b21a..6a7d980105f6 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 85b617b655bc..75151be21413 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1200,13 +1200,13 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	spin_lock_bh(&im->lock);
 	if (pmc) {
 		im->interface = pmc->interface;
-		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
-		im->sfmode = pmc->sfmode;
-		if (pmc->sfmode == MCAST_INCLUDE) {
+		if (im->sfmode == MCAST_INCLUDE) {
 			im->tomb = pmc->tomb;
 			im->sources = pmc->sources;
 			for (psf = im->sources; psf; psf = psf->sf_next)
-				psf->sf_crcount = im->crcount;
+				psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+		} else {
+			im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
 		}
 		in_dev_put(pmc->interface);
 		kfree(pmc);
@@ -1288,7 +1288,7 @@ static void igmp_group_dropped(struct ip_mc_list *im)
 #endif
 }
 
-static void igmp_group_added(struct ip_mc_list *im)
+static void igmp_group_added(struct ip_mc_list *im, unsigned int mode)
 {
 	struct in_device *in_dev = im->interface;
 #ifdef CONFIG_IP_MULTICAST
@@ -1316,7 +1316,13 @@ static void igmp_group_added(struct ip_mc_list *im)
 	}
 	/* else, v3 */
 
-	im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+	/* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should
+	 * not send filter-mode change record as the mode should be from
+	 * IN() to IN(A).
+	 */
+	if (mode == MCAST_EXCLUDE)
+		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+
 	igmp_ifc_event(in_dev);
 #endif
 }
@@ -1381,8 +1387,8 @@ static void ip_mc_hash_remove(struct in_device *in_dev,
 /*
  *	A socket has joined a multicast group on device dev.
  */
-
-void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
+static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr,
+			      unsigned int mode)
 {
 	struct ip_mc_list *im;
 #ifdef CONFIG_IP_MULTICAST
@@ -1394,7 +1400,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 	for_each_pmc_rtnl(in_dev, im) {
 		if (im->multiaddr == addr) {
 			im->users++;
-			ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0);
+			ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0);
 			goto out;
 		}
 	}
@@ -1408,8 +1414,8 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 	in_dev_hold(in_dev);
 	im->multiaddr = addr;
 	/* initial mode is (EX, empty) */
-	im->sfmode = MCAST_EXCLUDE;
-	im->sfcount[MCAST_EXCLUDE] = 1;
+	im->sfmode = mode;
+	im->sfcount[mode] = 1;
 	refcount_set(&im->refcnt, 1);
 	spin_lock_init(&im->lock);
 #ifdef CONFIG_IP_MULTICAST
@@ -1426,12 +1432,17 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 #ifdef CONFIG_IP_MULTICAST
 	igmpv3_del_delrec(in_dev, im);
 #endif
-	igmp_group_added(im);
+	igmp_group_added(im, mode);
 	if (!in_dev->dead)
 		ip_rt_multicast_event(in_dev);
 out:
 	return;
 }
+
+void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
+{
+	__ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE);
+}
 EXPORT_SYMBOL(ip_mc_inc_group);
 
 static int ip_mc_check_iphdr(struct sk_buff *skb)
@@ -1688,7 +1699,7 @@ void ip_mc_remap(struct in_device *in_dev)
 #ifdef CONFIG_IP_MULTICAST
 		igmpv3_del_delrec(in_dev, pmc);
 #endif
-		igmp_group_added(pmc);
+		igmp_group_added(pmc, pmc->sfmode);
 	}
 }
 
@@ -1751,7 +1762,7 @@ void ip_mc_up(struct in_device *in_dev)
 #ifdef CONFIG_IP_MULTICAST
 		igmpv3_del_delrec(in_dev, pmc);
 #endif
-		igmp_group_added(pmc);
+		igmp_group_added(pmc, pmc->sfmode);
 	}
 }
 
@@ -2130,8 +2141,8 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc)
 
 /* Join a multicast group
  */
-
-int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
+static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr,
+			      unsigned int mode)
 {
 	__be32 addr = imr->imr_multiaddr.s_addr;
 	struct ip_mc_socklist *iml, *i;
@@ -2172,15 +2183,30 @@ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
 	memcpy(&iml->multi, imr, sizeof(*imr));
 	iml->next_rcu = inet->mc_list;
 	iml->sflist = NULL;
-	iml->sfmode = MCAST_EXCLUDE;
+	iml->sfmode = mode;
 	rcu_assign_pointer(inet->mc_list, iml);
-	ip_mc_inc_group(in_dev, addr);
+	__ip_mc_inc_group(in_dev, addr, mode);
 	err = 0;
 done:
 	return err;
 }
+
+/* Join ASM (Any-Source Multicast) group
+ */
+int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
+{
+	return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE);
+}
 EXPORT_SYMBOL(ip_mc_join_group);
 
+/* Join SSM (Source-Specific Multicast) group
+ */
+int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr,
+			 unsigned int mode)
+{
+	return __ip_mc_join_group(sk, imr, mode);
+}
+
 static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml,
 			   struct in_device *in_dev)
 {
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index c9e35b81d093..0d70608cc2e1 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -90,7 +90,7 @@ static void inet_frags_free_cb(void *ptr, void *arg)
 
 void inet_frags_exit_net(struct netns_frags *nf)
 {
-	nf->low_thresh = 0; /* prevent creation of new frags */
+	nf->high_thresh = 0; /* prevent creation of new frags */
 
 	rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
 }
@@ -157,9 +157,6 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 {
 	struct inet_frag_queue *q;
 
-	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
-		return NULL;
-
 	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
 	if (!q)
 		return NULL;
@@ -204,6 +201,9 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 {
 	struct inet_frag_queue *fq;
 
+	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
+		return NULL;
+
 	rcu_read_lock();
 
 	fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 8e9528ebaa8e..d14d741fb05e 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -383,11 +383,16 @@ found:
 		int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
 
 		if (i < next->len) {
+			int delta = -next->truesize;
+
 			/* Eat head of the next overlapped fragment
 			 * and leave the loop. The next ones cannot overlap.
 			 */
 			if (!pskb_pull(next, i))
 				goto err;
+			delta += next->truesize;
+			if (delta)
+				add_frag_mem_limit(qp->q.net, delta);
 			next->ip_defrag_offset += i;
 			qp->q.meat -= i;
 			if (next->ip_summed != CHECKSUM_UNNECESSARY)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b3308e9d9762..0e3edd25f881 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 	/* Copy the flags to each fragment. */
 	IPCB(to)->flags = IPCB(from)->flags;
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index fc32fdbeefa6..c0fe5ad996f2 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
 	struct sockaddr_in sin;
 	const struct iphdr *iph = ip_hdr(skb);
-	__be16 *ports = (__be16 *)skb_transport_header(skb);
+	__be16 *ports;
+	int end;
 
-	if (skb_transport_offset(skb) + 4 > (int)skb->len)
+	end = skb_transport_offset(skb) + 4;
+	if (end > 0 && !pskb_may_pull(skb, end))
 		return;
 
 	/* All current transport protocols have the port numbers in the
 	 * first four bytes of the transport header and this function is
 	 * written with this assumption in mind.
 	 */
+	ports = (__be16 *)skb_transport_header(skb);
 
 	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = iph->daddr;
@@ -984,7 +987,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 			mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
 			mreq.imr_address.s_addr = mreqs.imr_interface;
 			mreq.imr_ifindex = 0;
-			err = ip_mc_join_group(sk, &mreq);
+			err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
 			if (err && err != -EADDRINUSE)
 				break;
 			omode = MCAST_INCLUDE;
@@ -1061,7 +1064,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 			mreq.imr_multiaddr = psin->sin_addr;
 			mreq.imr_address.s_addr = 0;
 			mreq.imr_ifindex = greqs.gsr_interface;
-			err = ip_mc_join_group(sk, &mreq);
+			err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
 			if (err && err != -EADDRINUSE)
 				break;
 			greqs.gsr_interface = mreq.imr_ifindex;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index ca0dad90803a..e77872c93c20 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1898,6 +1898,7 @@ static struct xt_match ipt_builtin_mt[] __read_mostly = {
 		.checkentry = icmp_checkentry,
 		.proto      = IPPROTO_ICMP,
 		.family     = NFPROTO_IPV4,
+		.me	    = THIS_MODULE,
 	},
 };
 
diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c
index 805e83ec3ad9..164714104965 100644
--- a/net/ipv4/netfilter/nf_tproxy_ipv4.c
+++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c
@@ -37,7 +37,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
 		 * to a listener socket if there's one */
 		struct sock *sk2;
 
-		sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+		sk2 = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
 					    iph->saddr, laddr ? laddr : iph->daddr,
 					    hp->source, lport ? lport : hp->dest,
 					    skb->dev, NF_TPROXY_LOOKUP_LISTENER);
@@ -71,7 +71,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
 EXPORT_SYMBOL_GPL(nf_tproxy_laddr4);
 
 struct sock *
-nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
 		      const u8 protocol,
 		      const __be32 saddr, const __be32 daddr,
 		      const __be16 sport, const __be16 dport,
@@ -79,16 +79,21 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
 		      const enum nf_tproxy_lookup_t lookup_type)
 {
 	struct sock *sk;
-	struct tcphdr *tcph;
 
 	switch (protocol) {
-	case IPPROTO_TCP:
+	case IPPROTO_TCP: {
+		struct tcphdr _hdr, *hp;
+
+		hp = skb_header_pointer(skb, ip_hdrlen(skb),
+					sizeof(struct tcphdr), &_hdr);
+		if (hp == NULL)
+			return NULL;
+
 		switch (lookup_type) {
 		case NF_TPROXY_LOOKUP_LISTENER:
-			tcph = hp;
 			sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
 						    ip_hdrlen(skb) +
-						      __tcp_hdrlen(tcph),
+						      __tcp_hdrlen(hp),
 						    saddr, sport,
 						    daddr, dport,
 						    in->ifindex, 0);
@@ -110,6 +115,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
 			BUG();
 		}
 		break;
+		}
 	case IPPROTO_UDP:
 		sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
 				     in->ifindex);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d06247ba08b2..5fa335fd3852 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -189,8 +189,9 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 	if (write && ret == 0) {
 		low = make_kgid(user_ns, urange[0]);
 		high = make_kgid(user_ns, urange[1]);
-		if (!gid_valid(low) || !gid_valid(high) ||
-		    (urange[1] < urange[0]) || gid_lt(high, low)) {
+		if (!gid_valid(low) || !gid_valid(high))
+			return -EINVAL;
+		if (urange[1] < urange[0] || gid_lt(high, low)) {
 			low = make_kgid(&init_user_ns, 1);
 			high = make_kgid(&init_user_ns, 0);
 		}
@@ -265,8 +266,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 	    ipv4.sysctl_tcp_fastopen);
 	struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
 	struct tcp_fastopen_context *ctxt;
-	int ret;
 	u32  user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
+	__le32 key[4];
+	int ret, i;
 
 	tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
 	if (!tbl.data)
@@ -275,11 +277,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 	rcu_read_lock();
 	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
 	if (ctxt)
-		memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+		memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
 	else
-		memset(user_key, 0, sizeof(user_key));
+		memset(key, 0, sizeof(key));
 	rcu_read_unlock();
 
+	for (i = 0; i < ARRAY_SIZE(key); i++)
+		user_key[i] = le32_to_cpu(key[i]);
+
 	snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
 		user_key[0], user_key[1], user_key[2], user_key[3]);
 	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
@@ -290,13 +295,17 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 			ret = -EINVAL;
 			goto bad_key;
 		}
-		tcp_fastopen_reset_cipher(net, NULL, user_key,
+
+		for (i = 0; i < ARRAY_SIZE(user_key); i++)
+			key[i] = cpu_to_le32(user_key[i]);
+
+		tcp_fastopen_reset_cipher(net, NULL, key,
 					  TCP_FASTOPEN_KEY_LENGTH);
 	}
 
 bad_key:
 	pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
-	       user_key[0], user_key[1], user_key[2], user_key[3],
+		user_key[0], user_key[1], user_key[2], user_key[3],
 	       (char *)tbl.data, ret);
 	kfree(tbl.data);
 	return ret;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 141acd92e58a..4491faf83f4f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -494,21 +494,32 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 }
 
 /*
- * Socket is not locked. We are protected from async events by poll logic and
- * correct handling of state changes made by other threads is impossible in
- * any case.
+ *	Wait for a TCP event.
+ *
+ *	Note that we don't need to lock the socket, as the upper poll layers
+ *	take care of normal races (between the test and the event) and we don't
+ *	go look at any of the socket buffers directly.
  */
-__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
+	__poll_t mask;
 	struct sock *sk = sock->sk;
 	const struct tcp_sock *tp = tcp_sk(sk);
-	__poll_t mask = 0;
 	int state;
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
+
 	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
+	/* Socket is not locked. We are protected from async events
+	 * by poll logic and correct handling of state changes
+	 * made by other threads is impossible in any case.
+	 */
+
+	mask = 0;
+
 	/*
 	 * EPOLLHUP is certainly not done right. But poll() doesn't
 	 * have a notion of HUP in just one direction, and for a
@@ -589,7 +600,7 @@ __poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
 
 	return mask;
 }
-EXPORT_SYMBOL(tcp_poll_mask);
+EXPORT_SYMBOL(tcp_poll);
 
 int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
@@ -1987,7 +1998,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 			 * shouldn't happen.
 			 */
 			if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
-				 "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
+				 "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n",
 				 *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
 				 flags))
 				break;
@@ -2002,7 +2013,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 				goto found_fin_ok;
 			WARN(!(flags & MSG_PEEK),
-			     "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
+			     "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n",
 			     *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
 		}
 
@@ -2551,6 +2562,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	tcp_clear_xmit_timers(sk);
 	__skb_queue_purge(&sk->sk_receive_queue);
+	tp->copied_seq = tp->rcv_nxt;
+	tp->urg_data = 0;
 	tcp_write_queue_purge(sk);
 	tcp_fastopen_active_disable_ofo_check(sk);
 	skb_rbtree_purge(&tp->out_of_order_queue);
@@ -2810,14 +2823,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_REPAIR:
 		if (!tcp_can_repair_sock(sk))
 			err = -EPERM;
-		else if (val == 1) {
+		else if (val == TCP_REPAIR_ON) {
 			tp->repair = 1;
 			sk->sk_reuse = SK_FORCE_REUSE;
 			tp->repair_queue = TCP_NO_QUEUE;
-		} else if (val == 0) {
+		} else if (val == TCP_REPAIR_OFF) {
 			tp->repair = 0;
 			sk->sk_reuse = SK_NO_REUSE;
 			tcp_send_window_probe(sk);
+		} else if (val == TCP_REPAIR_OFF_NO_WP) {
+			tp->repair = 0;
+			sk->sk_reuse = SK_NO_REUSE;
 		} else
 			err = -EINVAL;
 
@@ -3709,8 +3725,7 @@ int tcp_abort(struct sock *sk, int err)
 			struct request_sock *req = inet_reqsk(sk);
 
 			local_bh_disable();
-			inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
-							  req);
+			inet_csk_reqsk_queue_drop(req->rsk_listener, req);
 			local_bh_enable();
 			return 0;
 		}
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 58e2f479ffb4..4bfff3c87e8e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -354,6 +354,10 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain)
 	/* Reduce delayed ACKs by rounding up cwnd to the next even number. */
 	cwnd = (cwnd + 1) & ~1U;
 
+	/* Ensure gain cycling gets inflight above BDP even for small BDPs. */
+	if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT)
+		cwnd += 2;
+
 	return cwnd;
 }
 
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5f5e5936760e..8b637f9f23a2 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -55,7 +55,6 @@ struct dctcp {
 	u32 dctcp_alpha;
 	u32 next_seq;
 	u32 ce_state;
-	u32 delayed_ack_reserved;
 	u32 loss_cwnd;
 };
 
@@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk)
 
 		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 
-		ca->delayed_ack_reserved = 0;
 		ca->loss_cwnd = 0;
 		ca->ce_state = 0;
 
@@ -131,23 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=0 to CE=1 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (!ca->ce_state && ca->delayed_ack_reserved) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=0. */
-		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
+	if (!ca->ce_state) {
+		/* State has changed from CE=0 to CE=1, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -161,23 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=1 to CE=0 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (ca->ce_state && ca->delayed_ack_reserved) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=1. */
-		tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
+	if (ca->ce_state) {
+		/* State has changed from CE=1 to CE=0, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -248,25 +228,6 @@ static void dctcp_state(struct sock *sk, u8 new_state)
 	}
 }
 
-static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
-{
-	struct dctcp *ca = inet_csk_ca(sk);
-
-	switch (ev) {
-	case CA_EVENT_DELAYED_ACK:
-		if (!ca->delayed_ack_reserved)
-			ca->delayed_ack_reserved = 1;
-		break;
-	case CA_EVENT_NON_DELAYED_ACK:
-		if (ca->delayed_ack_reserved)
-			ca->delayed_ack_reserved = 0;
-		break;
-	default:
-		/* Don't care for the rest. */
-		break;
-	}
-}
-
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 {
 	switch (ev) {
@@ -276,10 +237,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ce_state_1_to_0(sk);
 		break;
-	case CA_EVENT_DELAYED_ACK:
-	case CA_EVENT_NON_DELAYED_ACK:
-		dctcp_update_ack_reserved(sk, ev);
-		break;
 	default:
 		/* Don't care for the rest. */
 		break;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 355d3dffd021..f9dcb29be12d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -215,7 +215,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
 		icsk->icsk_ack.quick = quickacks;
 }
 
-static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -223,6 +223,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 	icsk->icsk_ack.pingpong = 0;
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
 
 /* Send ACKs quickly, if "quick" count is not exhausted
  * and the session is not interactive.
@@ -245,8 +246,15 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
 
 static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
 {
-	if (tcp_hdr(skb)->cwr)
+	if (tcp_hdr(skb)->cwr) {
 		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+
+		/* If the sender is telling us it has entered CWR, then its
+		 * cwnd may be very low (even just 1 packet), so we should ACK
+		 * immediately.
+		 */
+		tcp_enter_quickack_mode((struct sock *)tp, 2);
+	}
 }
 
 static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
@@ -265,7 +273,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode(sk, 1);
+			tcp_enter_quickack_mode(sk, 2);
 		break;
 	case INET_ECN_CE:
 		if (tcp_ca_needs_ecn(sk))
@@ -273,7 +281,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode(sk, 1);
+			tcp_enter_quickack_mode(sk, 2);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
@@ -3181,6 +3189,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 
 		if (tcp_is_reno(tp)) {
 			tcp_remove_reno_sacks(sk, pkts_acked);
+
+			/* If any of the cumulatively ACKed segments was
+			 * retransmitted, non-SACK case cannot confirm that
+			 * progress was due to original transmission due to
+			 * lack of TCPCB_SACKED_ACKED bits even if some of
+			 * the packets may have been never retransmitted.
+			 */
+			if (flag & FLAG_RETRANS_DATA_ACKED)
+				flag &= ~FLAG_ORIG_SACK_ACKED;
 		} else {
 			int delta;
 
@@ -4348,6 +4365,23 @@ static bool tcp_try_coalesce(struct sock *sk,
 	return true;
 }
 
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+			     struct sk_buff *to,
+			     struct sk_buff *from,
+			     bool *fragstolen)
+{
+	bool res = tcp_try_coalesce(sk, to, from, fragstolen);
+
+	/* In case tcp_drop() is called later, update to->gso_segs */
+	if (res) {
+		u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+			       max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+		skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+	}
+	return res;
+}
+
 static void tcp_drop(struct sock *sk, struct sk_buff *skb)
 {
 	sk_drops_add(sk, skb);
@@ -4471,8 +4505,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	/* In the typical case, we are adding an skb to the end of the list.
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (tcp_try_coalesce(sk, tp->ooo_last_skb,
-			     skb, &fragstolen)) {
+	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
+				 skb, &fragstolen)) {
 coalesce_done:
 		tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
@@ -4500,7 +4534,7 @@ coalesce_done:
 				/* All the bits are present. Drop. */
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb);
+				tcp_drop(sk, skb);
 				skb = NULL;
 				tcp_dsack_set(sk, seq, end_seq);
 				goto add_sack;
@@ -4519,11 +4553,11 @@ coalesce_done:
 						 TCP_SKB_CB(skb1)->end_seq);
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb1);
+				tcp_drop(sk, skb1);
 				goto merge_right;
 			}
-		} else if (tcp_try_coalesce(sk, skb1,
-					    skb, &fragstolen)) {
+		} else if (tcp_ooo_try_coalesce(sk, skb1,
+						skb, &fragstolen)) {
 			goto coalesce_done;
 		}
 		p = &parent->rb_right;
@@ -4892,6 +4926,7 @@ end:
 static void tcp_collapse_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 range_truesize, sum_tiny = 0;
 	struct sk_buff *skb, *head;
 	u32 start, end;
 
@@ -4903,6 +4938,7 @@ new_range:
 	}
 	start = TCP_SKB_CB(skb)->seq;
 	end = TCP_SKB_CB(skb)->end_seq;
+	range_truesize = skb->truesize;
 
 	for (head = skb;;) {
 		skb = skb_rb_next(skb);
@@ -4913,11 +4949,20 @@ new_range:
 		if (!skb ||
 		    after(TCP_SKB_CB(skb)->seq, end) ||
 		    before(TCP_SKB_CB(skb)->end_seq, start)) {
-			tcp_collapse(sk, NULL, &tp->out_of_order_queue,
-				     head, skb, start, end);
+			/* Do not attempt collapsing tiny skbs */
+			if (range_truesize != head->truesize ||
+			    end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+				tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+					     head, skb, start, end);
+			} else {
+				sum_tiny += range_truesize;
+				if (sum_tiny > sk->sk_rcvbuf >> 3)
+					return;
+			}
 			goto new_range;
 		}
 
+		range_truesize += skb->truesize;
 		if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
 			start = TCP_SKB_CB(skb)->seq;
 		if (after(TCP_SKB_CB(skb)->end_seq, end))
@@ -4932,6 +4977,7 @@ new_range:
  * 2) not add too big latencies if thousands of packets sit there.
  *    (But if application shrinks SO_RCVBUF, we could still end up
  *     freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
  *
  * Return true if queue has shrunk.
  */
@@ -4939,20 +4985,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct rb_node *node, *prev;
+	int goal;
 
 	if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
 		return false;
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+	goal = sk->sk_rcvbuf >> 3;
 	node = &tp->ooo_last_skb->rbnode;
 	do {
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
+		goal -= rb_to_skb(node)->truesize;
 		tcp_drop(sk, rb_to_skb(node));
-		sk_mem_reclaim(sk);
-		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
-		    !tcp_under_memory_pressure(sk))
-			break;
+		if (!prev || goal <= 0) {
+			sk_mem_reclaim(sk);
+			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+			    !tcp_under_memory_pressure(sk))
+				break;
+			goal = sk->sk_rcvbuf >> 3;
+		}
 		node = prev;
 	} while (node);
 	tp->ooo_last_skb = rb_to_skb(prev);
@@ -4987,6 +5039,9 @@ static int tcp_prune_queue(struct sock *sk)
 	else if (tcp_under_memory_pressure(sk))
 		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
 
+	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+		return 0;
+
 	tcp_collapse_ofo_queue(sk);
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		tcp_collapse(sk, &sk->sk_receive_queue, NULL,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bea17f1e8302..3b2711e33e4c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -156,11 +156,24 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	 */
 	if (tcptw->tw_ts_recent_stamp &&
 	    (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
-		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
-		if (tp->write_seq == 0)
-			tp->write_seq = 1;
-		tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
-		tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+		/* In case of repair and re-using TIME-WAIT sockets we still
+		 * want to be sure that it is safe as above but honor the
+		 * sequence numbers and time stamps set as part of the repair
+		 * process.
+		 *
+		 * Without this check re-using a TIME-WAIT socket with TCP
+		 * repair would accumulate a -1 on the repair assigned
+		 * sequence number. The first time it is reused the sequence
+		 * is -1, the second time -2, etc. This fixes that issue
+		 * without appearing to create any others.
+		 */
+		if (likely(!tp->repair)) {
+			tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
+			if (tp->write_seq == 0)
+				tp->write_seq = 1;
+			tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
+			tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+		}
 		sock_hold(sktw);
 		return 1;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8e08b409c71e..c4172c1fb198 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 }
 
 /* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+				      u32 rcv_nxt)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
 		if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
 			__sock_put(sk);
 	}
+
+	if (unlikely(rcv_nxt != tp->rcv_nxt))
+		return;  /* Special ACK sent by DCTCP to reflect ECN */
 	tcp_dec_quickack_mode(sk, pkts);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
@@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
  * We are working here with either a clone of the original
  * SKB, or a fresh unique copy made by the retransmit engine.
  */
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
-			    gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+			      int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet;
@@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	th->source		= inet->inet_sport;
 	th->dest		= inet->inet_dport;
 	th->seq			= htonl(tcb->seq);
-	th->ack_seq		= htonl(tp->rcv_nxt);
+	th->ack_seq		= htonl(rcv_nxt);
 	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
 					tcb->tcp_flags);
 
@@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	icsk->icsk_af_ops->send_check(sk, skb);
 
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
-		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+		tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
 
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
@@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	return err;
 }
 
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+			    gfp_t gfp_mask)
+{
+	return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+				  tcp_sk(sk)->rcv_nxt);
+}
+
 /* This routine just queues the buffer for sending.
  *
  * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -3523,8 +3534,6 @@ void tcp_send_delayed_ack(struct sock *sk)
 	int ato = icsk->icsk_ack.ato;
 	unsigned long timeout;
 
-	tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
-
 	if (ato > TCP_DELACK_MIN) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 		int max_ato = HZ / 2;
@@ -3573,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 }
 
 /* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 {
 	struct sk_buff *buff;
 
@@ -3581,8 +3590,6 @@ void tcp_send_ack(struct sock *sk)
 	if (sk->sk_state == TCP_CLOSE)
 		return;
 
-	tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
-
 	/* We are not putting this on the write queue, so
 	 * tcp_transmit_skb() will set the ownership to this
 	 * sock.
@@ -3608,9 +3615,14 @@ void tcp_send_ack(struct sock *sk)
 	skb_set_tcp_pure_ack(buff);
 
 	/* Send it off, this clears delayed acks for us. */
-	tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+	__tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
 }
-EXPORT_SYMBOL_GPL(tcp_send_ack);
 
 /* This routine sends a packet with an out of date sequence
  * number. It assumes the other end will try to ack it.
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9bb27df4dac5..24e116ddae79 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2591,7 +2591,7 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
  * 	udp_poll - wait for a UDP event.
  *	@file - file struct
  *	@sock - socket
- *	@events - events to wait for
+ *	@wait - poll table
  *
  *	This is same as datagram poll, except for the special case of
  *	blocking sockets. If application is using a blocking fd
@@ -2600,23 +2600,23 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
  *	but then block when reading it. Add special case code
  *	to work around these arguably broken applications.
  */
-__poll_t udp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
-	__poll_t mask = datagram_poll_mask(sock, events);
+	__poll_t mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 
 	if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Check for false positives due to checksum errors */
-	if ((mask & EPOLLRDNORM) && !(sock->file->f_flags & O_NONBLOCK) &&
+	if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
 	    !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
 		mask &= ~(EPOLLIN | EPOLLRDNORM);
 
 	return mask;
 
 }
-EXPORT_SYMBOL(udp_poll_mask);
+EXPORT_SYMBOL(udp_poll);
 
 int udp_abort(struct sock *sk, int err)
 {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 92dc9e5a7ff3..69c54540d5b4 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -394,7 +394,7 @@ unflush:
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 	return pp;
 }
 EXPORT_SYMBOL(udp_gro_receive);
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 0eff75525da1..b3885ca22d6f 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -108,6 +108,7 @@ config IPV6_MIP6
 config IPV6_ILA
 	tristate "IPv6: Identifier Locator Addressing (ILA)"
 	depends on NETFILTER
+	select DST_CACHE
 	select LWTUNNEL
 	---help---
 	  Support for IPv6 Identifier Locator Addressing (ILA).
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c134286d6a41..f66a1cae3366 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2374,7 +2374,8 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 			continue;
 		if ((rt->fib6_flags & noflags) != 0)
 			continue;
-		fib6_info_hold(rt);
+		if (!fib6_info_hold_safe(rt))
+			continue;
 		break;
 	}
 out:
@@ -4528,6 +4529,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 			       unsigned long expires, u32 flags)
 {
 	struct fib6_info *f6i;
+	u32 prio;
 
 	f6i = addrconf_get_prefix_route(&ifp->addr,
 					ifp->prefix_len,
@@ -4536,13 +4538,15 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 	if (!f6i)
 		return -ENOENT;
 
-	if (f6i->fib6_metric != ifp->rt_priority) {
+	prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF;
+	if (f6i->fib6_metric != prio) {
+		/* delete old one */
+		ip6_del_rt(dev_net(ifp->idev->dev), f6i);
+
 		/* add new one */
 		addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
 				      ifp->rt_priority, ifp->idev->dev,
 				      expires, flags, GFP_KERNEL);
-		/* delete old one */
-		ip6_del_rt(dev_net(ifp->idev->dev), f6i);
 	} else {
 		if (!expires)
 			fib6_clean_expires(f6i);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 74f2a261e8df..9ed0eae91758 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -570,7 +570,7 @@ const struct proto_ops inet6_stream_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = inet_accept,		/* ok		*/
 	.getname	   = inet6_getname,
-	.poll_mask	   = tcp_poll_mask,		/* ok		*/
+	.poll		   = tcp_poll,			/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = inet_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
@@ -603,7 +603,7 @@ const struct proto_ops inet6_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = sock_no_accept,		/* a do nothing	*/
 	.getname	   = inet6_getname,
-	.poll_mask	   = udp_poll_mask,		/* ok		*/
+	.poll		   = udp_poll,			/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = sock_no_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 1323b9679cf7..1c0bb9fb76e6 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -799,8 +799,7 @@ static int calipso_opt_update(struct sock *sk, struct ipv6_opt_hdr *hop)
 {
 	struct ipv6_txoptions *old = txopt_get(inet6_sk(sk)), *txopts;
 
-	txopts = ipv6_renew_options_kern(sk, old, IPV6_HOPOPTS,
-					 hop, hop ? ipv6_optlen(hop) : 0);
+	txopts = ipv6_renew_options(sk, old, IPV6_HOPOPTS, hop);
 	txopt_put(old);
 	if (IS_ERR(txopts))
 		return PTR_ERR(txopts);
@@ -1222,8 +1221,7 @@ static int calipso_req_setattr(struct request_sock *req,
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
-	txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS,
-					 new, new ? ipv6_optlen(new) : 0);
+	txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
 
 	kfree(new);
 
@@ -1260,8 +1258,7 @@ static void calipso_req_delattr(struct request_sock *req)
 	if (calipso_opt_del(req_inet->ipv6_opt->hopopt, &new))
 		return; /* Nothing to do */
 
-	txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS,
-					 new, new ? ipv6_optlen(new) : 0);
+	txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
 
 	if (!IS_ERR(txopts)) {
 		txopts = xchg(&req_inet->ipv6_opt, txopts);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2ee08b6a86a4..1a1f876f8e28 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -700,13 +700,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
-		__be16 *ports = (__be16 *) skb_transport_header(skb);
+		__be16 *ports;
+		int end;
 
-		if (skb_transport_offset(skb) + 4 <= (int)skb->len) {
+		end = skb_transport_offset(skb) + 4;
+		if (end <= 0 || pskb_may_pull(skb, end)) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
 			 */
+			ports = (__be16 *)skb_transport_header(skb);
 
 			sin6.sin6_family = AF_INET6;
 			sin6.sin6_addr = ipv6_hdr(skb)->daddr;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 97513f35bcc5..88a7579c23bd 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -669,8 +669,10 @@ skip_cow:
 
 	sg_init_table(sg, nfrags);
 	ret = skb_to_sgvec(skb, sg, 0, skb->len);
-	if (unlikely(ret < 0))
+	if (unlikely(ret < 0)) {
+		kfree(tmp);
 		goto out;
+	}
 
 	skb->ip_summed = CHECKSUM_NONE;
 
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 5bc2bf3733ab..20291c2036fc 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -1015,29 +1015,21 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
 }
 EXPORT_SYMBOL_GPL(ipv6_dup_options);
 
-static int ipv6_renew_option(void *ohdr,
-			     struct ipv6_opt_hdr __user *newopt, int newoptlen,
-			     int inherit,
-			     struct ipv6_opt_hdr **hdr,
-			     char **p)
+static void ipv6_renew_option(int renewtype,
+			      struct ipv6_opt_hdr **dest,
+			      struct ipv6_opt_hdr *old,
+			      struct ipv6_opt_hdr *new,
+			      int newtype, char **p)
 {
-	if (inherit) {
-		if (ohdr) {
-			memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr));
-			*hdr = (struct ipv6_opt_hdr *)*p;
-			*p += CMSG_ALIGN(ipv6_optlen(*hdr));
-		}
-	} else {
-		if (newopt) {
-			if (copy_from_user(*p, newopt, newoptlen))
-				return -EFAULT;
-			*hdr = (struct ipv6_opt_hdr *)*p;
-			if (ipv6_optlen(*hdr) > newoptlen)
-				return -EINVAL;
-			*p += CMSG_ALIGN(newoptlen);
-		}
-	}
-	return 0;
+	struct ipv6_opt_hdr *src;
+
+	src = (renewtype == newtype ? new : old);
+	if (!src)
+		return;
+
+	memcpy(*p, src, ipv6_optlen(src));
+	*dest = (struct ipv6_opt_hdr *)*p;
+	*p += CMSG_ALIGN(ipv6_optlen(*dest));
 }
 
 /**
@@ -1063,13 +1055,11 @@ static int ipv6_renew_option(void *ohdr,
  */
 struct ipv6_txoptions *
 ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
-		   int newtype,
-		   struct ipv6_opt_hdr __user *newopt, int newoptlen)
+		   int newtype, struct ipv6_opt_hdr *newopt)
 {
 	int tot_len = 0;
 	char *p;
 	struct ipv6_txoptions *opt2;
-	int err;
 
 	if (opt) {
 		if (newtype != IPV6_HOPOPTS && opt->hopopt)
@@ -1082,8 +1072,8 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 			tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt));
 	}
 
-	if (newopt && newoptlen)
-		tot_len += CMSG_ALIGN(newoptlen);
+	if (newopt)
+		tot_len += CMSG_ALIGN(ipv6_optlen(newopt));
 
 	if (!tot_len)
 		return NULL;
@@ -1098,29 +1088,19 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 	opt2->tot_len = tot_len;
 	p = (char *)(opt2 + 1);
 
-	err = ipv6_renew_option(opt ? opt->hopopt : NULL, newopt, newoptlen,
-				newtype != IPV6_HOPOPTS,
-				&opt2->hopopt, &p);
-	if (err)
-		goto out;
-
-	err = ipv6_renew_option(opt ? opt->dst0opt : NULL, newopt, newoptlen,
-				newtype != IPV6_RTHDRDSTOPTS,
-				&opt2->dst0opt, &p);
-	if (err)
-		goto out;
-
-	err = ipv6_renew_option(opt ? opt->srcrt : NULL, newopt, newoptlen,
-				newtype != IPV6_RTHDR,
-				(struct ipv6_opt_hdr **)&opt2->srcrt, &p);
-	if (err)
-		goto out;
-
-	err = ipv6_renew_option(opt ? opt->dst1opt : NULL, newopt, newoptlen,
-				newtype != IPV6_DSTOPTS,
-				&opt2->dst1opt, &p);
-	if (err)
-		goto out;
+	ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt,
+			  (opt ? opt->hopopt : NULL),
+			  newopt, newtype, &p);
+	ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt,
+			  (opt ? opt->dst0opt : NULL),
+			  newopt, newtype, &p);
+	ipv6_renew_option(IPV6_RTHDR,
+			  (struct ipv6_opt_hdr **)&opt2->srcrt,
+			  (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL),
+			  newopt, newtype, &p);
+	ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt,
+			  (opt ? opt->dst1opt : NULL),
+			  newopt, newtype, &p);
 
 	opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) +
 			  (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) +
@@ -1128,37 +1108,6 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 	opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0);
 
 	return opt2;
-out:
-	sock_kfree_s(sk, opt2, opt2->tot_len);
-	return ERR_PTR(err);
-}
-
-/**
- * ipv6_renew_options_kern - replace a specific ext hdr with a new one.
- *
- * @sk: sock from which to allocate memory
- * @opt: original options
- * @newtype: option type to replace in @opt
- * @newopt: new option of type @newtype to replace (kernel-mem)
- * @newoptlen: length of @newopt
- *
- * See ipv6_renew_options().  The difference is that @newopt is
- * kernel memory, rather than user memory.
- */
-struct ipv6_txoptions *
-ipv6_renew_options_kern(struct sock *sk, struct ipv6_txoptions *opt,
-			int newtype, struct ipv6_opt_hdr *newopt,
-			int newoptlen)
-{
-	struct ipv6_txoptions *ret_val;
-	const mm_segment_t old_fs = get_fs();
-
-	set_fs(KERNEL_DS);
-	ret_val = ipv6_renew_options(sk, opt, newtype,
-				     (struct ipv6_opt_hdr __user *)newopt,
-				     newoptlen);
-	set_fs(old_fs);
-	return ret_val;
 }
 
 struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index be491bf6ab6e..ef2505aefc15 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -402,9 +402,10 @@ static int icmp6_iif(const struct sk_buff *skb)
 
 	/* for local traffic to local address, skb dev is the loopback
 	 * device. Check if there is a dst attached to the skb and if so
-	 * get the real device index.
+	 * get the real device index. Same is needed for replies to a link
+	 * local address on a device enslaved to an L3 master device
 	 */
-	if (unlikely(iif == LOOPBACK_IFINDEX)) {
+	if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
 		const struct rt6_info *rt6 = skb_rt6_info(skb);
 
 		if (rt6)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1fb2f3118d60..d212738e9d10 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -935,20 +935,19 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 {
 	struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
 				    lockdep_is_held(&rt->fib6_table->tb6_lock));
-	enum fib_event_type event = FIB_EVENT_ENTRY_ADD;
-	struct fib6_info *iter = NULL, *match = NULL;
+	struct fib6_info *iter = NULL;
 	struct fib6_info __rcu **ins;
+	struct fib6_info __rcu **fallback_ins = NULL;
 	int replace = (info->nlh &&
 		       (info->nlh->nlmsg_flags & NLM_F_REPLACE));
-	int append = (info->nlh &&
-		       (info->nlh->nlmsg_flags & NLM_F_APPEND));
 	int add = (!info->nlh ||
 		   (info->nlh->nlmsg_flags & NLM_F_CREATE));
 	int found = 0;
+	bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
 	u16 nlflags = NLM_F_EXCL;
 	int err;
 
-	if (append)
+	if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND))
 		nlflags |= NLM_F_APPEND;
 
 	ins = &fn->leaf;
@@ -970,8 +969,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 
 			nlflags &= ~NLM_F_EXCL;
 			if (replace) {
-				found++;
-				break;
+				if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
+					found++;
+					break;
+				}
+				if (rt_can_ecmp)
+					fallback_ins = fallback_ins ?: ins;
+				goto next_iter;
 			}
 
 			if (rt6_duplicate_nexthop(iter, rt)) {
@@ -986,51 +990,71 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 				fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
 				return -EEXIST;
 			}
-
-			/* first route that matches */
-			if (!match)
-				match = iter;
+			/* If we have the same destination and the same metric,
+			 * but not the same gateway, then the route we try to
+			 * add is sibling to this route, increment our counter
+			 * of siblings, and later we will add our route to the
+			 * list.
+			 * Only static routes (which don't have flag
+			 * RTF_EXPIRES) are used for ECMPv6.
+			 *
+			 * To avoid long list, we only had siblings if the
+			 * route have a gateway.
+			 */
+			if (rt_can_ecmp &&
+			    rt6_qualify_for_ecmp(iter))
+				rt->fib6_nsiblings++;
 		}
 
 		if (iter->fib6_metric > rt->fib6_metric)
 			break;
 
+next_iter:
 		ins = &iter->fib6_next;
 	}
 
+	if (fallback_ins && !found) {
+		/* No ECMP-able route found, replace first non-ECMP one */
+		ins = fallback_ins;
+		iter = rcu_dereference_protected(*ins,
+				    lockdep_is_held(&rt->fib6_table->tb6_lock));
+		found++;
+	}
+
 	/* Reset round-robin state, if necessary */
 	if (ins == &fn->leaf)
 		fn->rr_ptr = NULL;
 
 	/* Link this route to others same route. */
-	if (append && match) {
+	if (rt->fib6_nsiblings) {
+		unsigned int fib6_nsiblings;
 		struct fib6_info *sibling, *temp_sibling;
 
-		if (rt->fib6_flags & RTF_REJECT) {
-			NL_SET_ERR_MSG(extack,
-				       "Can not append a REJECT route");
-			return -EINVAL;
-		} else if (match->fib6_flags & RTF_REJECT) {
-			NL_SET_ERR_MSG(extack,
-				       "Can not append to a REJECT route");
-			return -EINVAL;
+		/* Find the first route that have the same metric */
+		sibling = leaf;
+		while (sibling) {
+			if (sibling->fib6_metric == rt->fib6_metric &&
+			    rt6_qualify_for_ecmp(sibling)) {
+				list_add_tail(&rt->fib6_siblings,
+					      &sibling->fib6_siblings);
+				break;
+			}
+			sibling = rcu_dereference_protected(sibling->fib6_next,
+				    lockdep_is_held(&rt->fib6_table->tb6_lock));
 		}
-		event = FIB_EVENT_ENTRY_APPEND;
-		rt->fib6_nsiblings = match->fib6_nsiblings;
-		list_add_tail(&rt->fib6_siblings, &match->fib6_siblings);
-		match->fib6_nsiblings++;
-
 		/* For each sibling in the list, increment the counter of
 		 * siblings. BUG() if counters does not match, list of siblings
 		 * is broken!
 		 */
+		fib6_nsiblings = 0;
 		list_for_each_entry_safe(sibling, temp_sibling,
-					 &match->fib6_siblings, fib6_siblings) {
+					 &rt->fib6_siblings, fib6_siblings) {
 			sibling->fib6_nsiblings++;
-			BUG_ON(sibling->fib6_nsiblings != match->fib6_nsiblings);
+			BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings);
+			fib6_nsiblings++;
 		}
-
-		rt6_multipath_rebalance(match);
+		BUG_ON(fib6_nsiblings != rt->fib6_nsiblings);
+		rt6_multipath_rebalance(temp_sibling);
 	}
 
 	/*
@@ -1043,8 +1067,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 add:
 		nlflags |= NLM_F_CREATE;
 
-		err = call_fib6_entry_notifiers(info->nl_net, event, rt,
-						extack);
+		err = call_fib6_entry_notifiers(info->nl_net,
+						FIB_EVENT_ENTRY_ADD,
+						rt, extack);
 		if (err)
 			return err;
 
@@ -1062,7 +1087,7 @@ add:
 		}
 
 	} else {
-		struct fib6_info *tmp;
+		int nsiblings;
 
 		if (!found) {
 			if (add)
@@ -1077,57 +1102,48 @@ add:
 		if (err)
 			return err;
 
-		/* if route being replaced has siblings, set tmp to
-		 * last one, otherwise tmp is current route. this is
-		 * used to set fib6_next for new route
-		 */
-		if (iter->fib6_nsiblings)
-			tmp = list_last_entry(&iter->fib6_siblings,
-					      struct fib6_info,
-					      fib6_siblings);
-		else
-			tmp = iter;
-
-		/* insert new route */
 		atomic_inc(&rt->fib6_ref);
 		rcu_assign_pointer(rt->fib6_node, fn);
-		rt->fib6_next = tmp->fib6_next;
+		rt->fib6_next = iter->fib6_next;
 		rcu_assign_pointer(*ins, rt);
-
 		if (!info->skip_notify)
 			inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
 		if (!(fn->fn_flags & RTN_RTINFO)) {
 			info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
 			fn->fn_flags |= RTN_RTINFO;
 		}
+		nsiblings = iter->fib6_nsiblings;
+		iter->fib6_node = NULL;
+		fib6_purge_rt(iter, fn, info->nl_net);
+		if (rcu_access_pointer(fn->rr_ptr) == iter)
+			fn->rr_ptr = NULL;
+		fib6_info_release(iter);
 
-		/* delete old route */
-		rt = iter;
-
-		if (rt->fib6_nsiblings) {
-			struct fib6_info *tmp;
-
+		if (nsiblings) {
 			/* Replacing an ECMP route, remove all siblings */
-			list_for_each_entry_safe(iter, tmp, &rt->fib6_siblings,
-						 fib6_siblings) {
-				iter->fib6_node = NULL;
-				fib6_purge_rt(iter, fn, info->nl_net);
-				if (rcu_access_pointer(fn->rr_ptr) == iter)
-					fn->rr_ptr = NULL;
-				fib6_info_release(iter);
-
-				rt->fib6_nsiblings--;
-				info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
+			ins = &rt->fib6_next;
+			iter = rcu_dereference_protected(*ins,
+				    lockdep_is_held(&rt->fib6_table->tb6_lock));
+			while (iter) {
+				if (iter->fib6_metric > rt->fib6_metric)
+					break;
+				if (rt6_qualify_for_ecmp(iter)) {
+					*ins = iter->fib6_next;
+					iter->fib6_node = NULL;
+					fib6_purge_rt(iter, fn, info->nl_net);
+					if (rcu_access_pointer(fn->rr_ptr) == iter)
+						fn->rr_ptr = NULL;
+					fib6_info_release(iter);
+					nsiblings--;
+					info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
+				} else {
+					ins = &iter->fib6_next;
+				}
+				iter = rcu_dereference_protected(*ins,
+					lockdep_is_held(&rt->fib6_table->tb6_lock));
 			}
+			WARN_ON(nsiblings != 0);
 		}
-
-		WARN_ON(rt->fib6_nsiblings != 0);
-
-		rt->fib6_node = NULL;
-		fib6_purge_rt(rt, fn, info->nl_net);
-		if (rcu_access_pointer(fn->rr_ptr) == rt)
-			fn->rr_ptr = NULL;
-		fib6_info_release(rt);
 	}
 
 	return 0;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c8cf2fdbb13b..cd2cfb04e5d8 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -927,7 +927,6 @@ tx_err:
 static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 					 struct net_device *dev)
 {
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device_stats *stats;
@@ -1010,6 +1009,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 			goto tx_err;
 		}
 	} else {
+		struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+
 		switch (skb->protocol) {
 		case htons(ETH_P_IP):
 			memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a14fb4fcdf18..3168847c30d1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -570,6 +570,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 #ifdef CONFIG_NET_SCHED
 	to->tc_index = from->tc_index;
 #endif
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 00e138a44cbb..1cc9650af9fb 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1133,12 +1133,8 @@ route_lookup:
 		max_headroom += 8;
 		mtu -= 8;
 	}
-	if (skb->protocol == htons(ETH_P_IPV6)) {
-		if (mtu < IPV6_MIN_MTU)
-			mtu = IPV6_MIN_MTU;
-	} else if (mtu < 576) {
-		mtu = 576;
-	}
+	mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
+		       IPV6_MIN_MTU : IPV4_MIN_MTU);
 
 	skb_dst_update_pmtu(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index b7f28deddaea..c72ae3a4fe09 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -480,10 +480,6 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 		goto tx_err_dst_release;
 	}
 
-	skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
-	skb_dst_set(skb, dst);
-	skb->dev = skb_dst(skb)->dev;
-
 	mtu = dst_mtu(dst);
 	if (!skb->ignore_df && skb->len > mtu) {
 		skb_dst_update_pmtu(skb, mtu);
@@ -498,9 +494,14 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 				  htonl(mtu));
 		}
 
-		return -EMSGSIZE;
+		err = -EMSGSIZE;
+		goto tx_err_dst_release;
 	}
 
+	skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
+	skb_dst_set(skb, dst);
+	skb->dev = skb_dst(skb)->dev;
+
 	err = dst_output(t->net, skb->sk, skb);
 	if (net_xmit_eval(err) == 0) {
 		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 4d780c7f0130..568ca4187cd1 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -398,6 +398,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 	case IPV6_DSTOPTS:
 	{
 		struct ipv6_txoptions *opt;
+		struct ipv6_opt_hdr *new = NULL;
+
+		/* hop-by-hop / destination options are privileged option */
+		retv = -EPERM;
+		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
+			break;
 
 		/* remove any sticky options header with a zero option
 		 * length, per RFC3542.
@@ -409,17 +415,22 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		else if (optlen < sizeof(struct ipv6_opt_hdr) ||
 			 optlen & 0x7 || optlen > 8 * 255)
 			goto e_inval;
-
-		/* hop-by-hop / destination options are privileged option */
-		retv = -EPERM;
-		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
-			break;
+		else {
+			new = memdup_user(optval, optlen);
+			if (IS_ERR(new)) {
+				retv = PTR_ERR(new);
+				break;
+			}
+			if (unlikely(ipv6_optlen(new) > optlen)) {
+				kfree(new);
+				goto e_inval;
+			}
+		}
 
 		opt = rcu_dereference_protected(np->opt,
 						lockdep_sock_is_held(sk));
-		opt = ipv6_renew_options(sk, opt, optname,
-					 (struct ipv6_opt_hdr __user *)optval,
-					 optlen);
+		opt = ipv6_renew_options(sk, opt, optname, new);
+		kfree(new);
 		if (IS_ERR(opt)) {
 			retv = PTR_ERR(opt);
 			break;
@@ -718,8 +729,9 @@ done:
 			struct sockaddr_in6 *psin6;
 
 			psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
-			retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
-						 &psin6->sin6_addr);
+			retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface,
+						     &psin6->sin6_addr,
+						     MCAST_INCLUDE);
 			/* prior join w/ different source is ok */
 			if (retv && retv != -EADDRINUSE)
 				break;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 975021df7c1c..f60f310785fd 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -95,6 +95,8 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 			  int delta);
 static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 			    struct inet6_dev *idev);
+static int __ipv6_dev_mc_inc(struct net_device *dev,
+			     const struct in6_addr *addr, unsigned int mode);
 
 #define MLD_QRV_DEFAULT		2
 /* RFC3810, 9.2. Query Interval */
@@ -132,7 +134,8 @@ static int unsolicited_report_interval(struct inet6_dev *idev)
 	return iv > 0 ? iv : 1;
 }
 
-int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
+static int __ipv6_sock_mc_join(struct sock *sk, int ifindex,
+			       const struct in6_addr *addr, unsigned int mode)
 {
 	struct net_device *dev = NULL;
 	struct ipv6_mc_socklist *mc_lst;
@@ -179,7 +182,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	}
 
 	mc_lst->ifindex = dev->ifindex;
-	mc_lst->sfmode = MCAST_EXCLUDE;
+	mc_lst->sfmode = mode;
 	rwlock_init(&mc_lst->sflock);
 	mc_lst->sflist = NULL;
 
@@ -187,7 +190,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	 *	now add/increase the group membership on the device
 	 */
 
-	err = ipv6_dev_mc_inc(dev, addr);
+	err = __ipv6_dev_mc_inc(dev, addr, mode);
 
 	if (err) {
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
@@ -199,8 +202,19 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	return 0;
 }
+
+int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
+{
+	return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE);
+}
 EXPORT_SYMBOL(ipv6_sock_mc_join);
 
+int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex,
+			  const struct in6_addr *addr, unsigned int mode)
+{
+	return __ipv6_sock_mc_join(sk, ifindex, addr, mode);
+}
+
 /*
  *	socket leave on multicast group
  */
@@ -646,7 +660,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
 	return rv;
 }
 
-static void igmp6_group_added(struct ifmcaddr6 *mc)
+static void igmp6_group_added(struct ifmcaddr6 *mc, unsigned int mode)
 {
 	struct net_device *dev = mc->idev->dev;
 	char buf[MAX_ADDR_LEN];
@@ -672,7 +686,13 @@ static void igmp6_group_added(struct ifmcaddr6 *mc)
 	}
 	/* else v2 */
 
-	mc->mca_crcount = mc->idev->mc_qrv;
+	/* Based on RFC3810 6.1, for newly added INCLUDE SSM, we
+	 * should not send filter-mode change record as the mode
+	 * should be from IN() to IN(A).
+	 */
+	if (mode == MCAST_EXCLUDE)
+		mc->mca_crcount = mc->idev->mc_qrv;
+
 	mld_ifc_event(mc->idev);
 }
 
@@ -770,13 +790,13 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	spin_lock_bh(&im->mca_lock);
 	if (pmc) {
 		im->idev = pmc->idev;
-		im->mca_crcount = idev->mc_qrv;
-		im->mca_sfmode = pmc->mca_sfmode;
-		if (pmc->mca_sfmode == MCAST_INCLUDE) {
+		if (im->mca_sfmode == MCAST_INCLUDE) {
 			im->mca_tomb = pmc->mca_tomb;
 			im->mca_sources = pmc->mca_sources;
 			for (psf = im->mca_sources; psf; psf = psf->sf_next)
-				psf->sf_crcount = im->mca_crcount;
+				psf->sf_crcount = idev->mc_qrv;
+		} else {
+			im->mca_crcount = idev->mc_qrv;
 		}
 		in6_dev_put(pmc->idev);
 		kfree(pmc);
@@ -831,7 +851,8 @@ static void ma_put(struct ifmcaddr6 *mc)
 }
 
 static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
-				   const struct in6_addr *addr)
+				   const struct in6_addr *addr,
+				   unsigned int mode)
 {
 	struct ifmcaddr6 *mc;
 
@@ -849,9 +870,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
 	refcount_set(&mc->mca_refcnt, 1);
 	spin_lock_init(&mc->mca_lock);
 
-	/* initial mode is (EX, empty) */
-	mc->mca_sfmode = MCAST_EXCLUDE;
-	mc->mca_sfcount[MCAST_EXCLUDE] = 1;
+	mc->mca_sfmode = mode;
+	mc->mca_sfcount[mode] = 1;
 
 	if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) ||
 	    IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL)
@@ -863,7 +883,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
 /*
  *	device multicast group inc (add if not found)
  */
-int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
+static int __ipv6_dev_mc_inc(struct net_device *dev,
+			     const struct in6_addr *addr, unsigned int mode)
 {
 	struct ifmcaddr6 *mc;
 	struct inet6_dev *idev;
@@ -887,14 +908,13 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 		if (ipv6_addr_equal(&mc->mca_addr, addr)) {
 			mc->mca_users++;
 			write_unlock_bh(&idev->lock);
-			ip6_mc_add_src(idev, &mc->mca_addr, MCAST_EXCLUDE, 0,
-				NULL, 0);
+			ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0);
 			in6_dev_put(idev);
 			return 0;
 		}
 	}
 
-	mc = mca_alloc(idev, addr);
+	mc = mca_alloc(idev, addr, mode);
 	if (!mc) {
 		write_unlock_bh(&idev->lock);
 		in6_dev_put(idev);
@@ -911,11 +931,16 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 	write_unlock_bh(&idev->lock);
 
 	mld_del_delrec(idev, mc);
-	igmp6_group_added(mc);
+	igmp6_group_added(mc, mode);
 	ma_put(mc);
 	return 0;
 }
 
+int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
+{
+	return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE);
+}
+
 /*
  *	device multicast group del
  */
@@ -1751,7 +1776,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 
 		psf_next = psf->sf_next;
 
-		if (!is_in(pmc, psf, type, gdeleted, sdeleted)) {
+		if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) {
 			psf_prev = psf;
 			continue;
 		}
@@ -2066,7 +2091,7 @@ static void mld_send_initial_cr(struct inet6_dev *idev)
 		if (pmc->mca_sfcount[MCAST_EXCLUDE])
 			type = MLD2_CHANGE_TO_EXCLUDE;
 		else
-			type = MLD2_CHANGE_TO_INCLUDE;
+			type = MLD2_ALLOW_NEW_SOURCES;
 		skb = add_grec(skb, pmc, type, 0, 0, 1);
 		spin_unlock_bh(&pmc->mca_lock);
 	}
@@ -2082,7 +2107,8 @@ void ipv6_mc_dad_complete(struct inet6_dev *idev)
 		mld_send_initial_cr(idev);
 		idev->mc_dad_count--;
 		if (idev->mc_dad_count)
-			mld_dad_start_timer(idev, idev->mc_maxdelay);
+			mld_dad_start_timer(idev,
+					    unsolicited_report_interval(idev));
 	}
 }
 
@@ -2094,7 +2120,8 @@ static void mld_dad_timer_expire(struct timer_list *t)
 	if (idev->mc_dad_count) {
 		idev->mc_dad_count--;
 		if (idev->mc_dad_count)
-			mld_dad_start_timer(idev, idev->mc_maxdelay);
+			mld_dad_start_timer(idev,
+					    unsolicited_report_interval(idev));
 	}
 	in6_dev_put(idev);
 }
@@ -2452,7 +2479,8 @@ static void mld_ifc_timer_expire(struct timer_list *t)
 	if (idev->mc_ifc_count) {
 		idev->mc_ifc_count--;
 		if (idev->mc_ifc_count)
-			mld_ifc_start_timer(idev, idev->mc_maxdelay);
+			mld_ifc_start_timer(idev,
+					    unsolicited_report_interval(idev));
 	}
 	in6_dev_put(idev);
 }
@@ -2543,7 +2571,7 @@ void ipv6_mc_up(struct inet6_dev *idev)
 	ipv6_mc_reset(idev);
 	for (i = idev->mc_list; i; i = i->next) {
 		mld_del_delrec(idev, i);
-		igmp6_group_added(i);
+		igmp6_group_added(i, i->mca_sfmode);
 	}
 	read_unlock_bh(&idev->lock);
 }
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index e640d2f3c55c..0ec273997d1d 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -811,7 +811,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 			return;
 		}
 	}
-	if (ndopts.nd_opts_nonce)
+	if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1)
 		memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6);
 
 	inc = ipv6_addr_is_multicast(daddr);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 7eab959734bc..daf2e9e9193d 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1909,6 +1909,7 @@ static struct xt_match ip6t_builtin_mt[] __read_mostly = {
 		.checkentry = icmp6_checkentry,
 		.proto      = IPPROTO_ICMPV6,
 		.family     = NFPROTO_IPV6,
+		.me	    = THIS_MODULE,
 	},
 };
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 5e0332014c17..e4d9e6976d3c 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -107,7 +107,7 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
 	if (hdr == NULL)
 		goto err_reg;
 
-	net->nf_frag.sysctl.frags_hdr = hdr;
+	net->nf_frag_frags_hdr = hdr;
 	return 0;
 
 err_reg:
@@ -121,8 +121,8 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
 {
 	struct ctl_table *table;
 
-	table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg;
-	unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr);
+	table = net->nf_frag_frags_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->nf_frag_frags_hdr);
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
@@ -585,6 +585,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	    fq->q.meat == fq->q.len &&
 	    nf_ct_frag6_reasm(fq, skb, dev))
 		ret = 0;
+	else
+		skb_dst_drop(skb);
 
 out_unlock:
 	spin_unlock_bh(&fq->q.lock);
diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c
index bf1d6c421e3b..5dfd33af6451 100644
--- a/net/ipv6/netfilter/nf_tproxy_ipv6.c
+++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c
@@ -55,7 +55,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
 		 * to a listener socket if there's one */
 		struct sock *sk2;
 
-		sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, hp, tproto,
+		sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, tproto,
 					    &iph->saddr,
 					    nf_tproxy_laddr6(skb, laddr, &iph->daddr),
 					    hp->source,
@@ -72,7 +72,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
 EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait6);
 
 struct sock *
-nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
+nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff,
 		      const u8 protocol,
 		      const struct in6_addr *saddr, const struct in6_addr *daddr,
 		      const __be16 sport, const __be16 dport,
@@ -80,15 +80,20 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
 		      const enum nf_tproxy_lookup_t lookup_type)
 {
 	struct sock *sk;
-	struct tcphdr *tcph;
 
 	switch (protocol) {
-	case IPPROTO_TCP:
+	case IPPROTO_TCP: {
+		struct tcphdr _hdr, *hp;
+
+		hp = skb_header_pointer(skb, thoff,
+					sizeof(struct tcphdr), &_hdr);
+		if (hp == NULL)
+			return NULL;
+
 		switch (lookup_type) {
 		case NF_TPROXY_LOOKUP_LISTENER:
-			tcph = hp;
 			sk = inet6_lookup_listener(net, &tcp_hashinfo, skb,
-						   thoff + __tcp_hdrlen(tcph),
+						   thoff + __tcp_hdrlen(hp),
 						   saddr, sport,
 						   daddr, ntohs(dport),
 						   in->ifindex, 0);
@@ -110,6 +115,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
 			BUG();
 		}
 		break;
+		}
 	case IPPROTO_UDP:
 		sk = udp6_lib_lookup(net, saddr, sport, daddr, dport,
 				     in->ifindex);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ce6f0d15b5dd..afc307c89d1a 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1334,7 +1334,7 @@ void raw6_proc_exit(void)
 }
 #endif	/* CONFIG_PROC_FS */
 
-/* Same as inet6_dgram_ops, sans udp_poll_mask.  */
+/* Same as inet6_dgram_ops, sans udp_poll.  */
 const struct proto_ops inet6_sockraw_ops = {
 	.family		   = PF_INET6,
 	.owner		   = THIS_MODULE,
@@ -1344,7 +1344,7 @@ const struct proto_ops inet6_sockraw_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = sock_no_accept,		/* a do nothing	*/
 	.getname	   = inet6_getname,
-	.poll_mask	   = datagram_poll_mask,	/* ok		*/
+	.poll		   = datagram_poll,		/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = sock_no_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 86a0e4333d42..7208c16302f6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -972,18 +972,15 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
 	rt->dst.lastuse = jiffies;
 }
 
+/* Caller must already hold reference to @from */
 static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
 {
 	rt->rt6i_flags &= ~RTF_EXPIRES;
-	fib6_info_hold(from);
 	rcu_assign_pointer(rt->from, from);
 	dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
-	if (from->fib6_metrics != &dst_default_metrics) {
-		rt->dst._metrics |= DST_METRICS_REFCOUNTED;
-		refcount_inc(&from->fib6_metrics->refcnt);
-	}
 }
 
+/* Caller must already hold reference to @ort */
 static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
 {
 	struct net_device *dev = fib6_info_nh_dev(ort);
@@ -1044,9 +1041,14 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
 	struct net_device *dev = rt->fib6_nh.nh_dev;
 	struct rt6_info *nrt;
 
+	if (!fib6_info_hold_safe(rt))
+		return NULL;
+
 	nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
 	if (nrt)
 		ip6_rt_copy_init(nrt, rt);
+	else
+		fib6_info_release(rt);
 
 	return nrt;
 }
@@ -1178,10 +1180,15 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
 	 *	Clone the route.
 	 */
 
+	if (!fib6_info_hold_safe(ort))
+		return NULL;
+
 	dev = ip6_rt_get_dev_rcu(ort);
 	rt = ip6_dst_alloc(dev_net(dev), dev, 0);
-	if (!rt)
+	if (!rt) {
+		fib6_info_release(ort);
 		return NULL;
+	}
 
 	ip6_rt_copy_init(rt, ort);
 	rt->rt6i_flags |= RTF_CACHE;
@@ -1210,12 +1217,17 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt)
 	struct net_device *dev;
 	struct rt6_info *pcpu_rt;
 
+	if (!fib6_info_hold_safe(rt))
+		return NULL;
+
 	rcu_read_lock();
 	dev = ip6_rt_get_dev_rcu(rt);
 	pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags);
 	rcu_read_unlock();
-	if (!pcpu_rt)
+	if (!pcpu_rt) {
+		fib6_info_release(rt);
 		return NULL;
+	}
 	ip6_rt_copy_init(pcpu_rt, rt);
 	pcpu_rt->rt6i_flags |= RTF_PCPU;
 	return pcpu_rt;
@@ -2486,7 +2498,7 @@ restart:
 
 out:
 	if (ret)
-		dst_hold(&ret->dst);
+		ip6_hold_safe(net, &ret, true);
 	else
 		ret = ip6_create_rt_rcu(rt);
 
@@ -3303,7 +3315,8 @@ static int ip6_route_del(struct fib6_config *cfg,
 				continue;
 			if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol)
 				continue;
-			fib6_info_hold(rt);
+			if (!fib6_info_hold_safe(rt))
+				continue;
 			rcu_read_unlock();
 
 			/* if gateway was specified only delete the one hop */
@@ -3409,6 +3422,9 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
+	/* This fib6_info_hold() is safe here because we hold reference to rt
+	 * and rt already holds reference to fib6_info.
+	 */
 	fib6_info_hold(from);
 	rcu_read_unlock();
 
@@ -3470,7 +3486,8 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 			continue;
 		if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
 			continue;
-		fib6_info_hold(rt);
+		if (!fib6_info_hold_safe(rt))
+			continue;
 		break;
 	}
 out:
@@ -3530,8 +3547,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net,
 		    ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr))
 			break;
 	}
-	if (rt)
-		fib6_info_hold(rt);
+	if (rt && !fib6_info_hold_safe(rt))
+		rt = NULL;
 	rcu_read_unlock();
 	return rt;
 }
@@ -3579,8 +3596,8 @@ restart:
 		struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL;
 
 		if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
-		    (!idev || idev->cnf.accept_ra != 2)) {
-			fib6_info_hold(rt);
+		    (!idev || idev->cnf.accept_ra != 2) &&
+		    fib6_info_hold_safe(rt)) {
 			rcu_read_unlock();
 			ip6_del_rt(net, rt);
 			goto restart;
@@ -3842,7 +3859,7 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
 			lockdep_is_held(&rt->fib6_table->tb6_lock));
 	while (iter) {
 		if (iter->fib6_metric == rt->fib6_metric &&
-		    iter->fib6_nsiblings)
+		    rt6_qualify_for_ecmp(iter))
 			return iter;
 		iter = rcu_dereference_protected(iter->fib6_next,
 				lockdep_is_held(&rt->fib6_table->tb6_lock));
@@ -4388,6 +4405,13 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			rt = NULL;
 			goto cleanup;
 		}
+		if (!rt6_qualify_for_ecmp(rt)) {
+			err = -EINVAL;
+			NL_SET_ERR_MSG(extack,
+				       "Device only routes can not be added for IPv6 using the multipath API.");
+			fib6_info_release(rt);
+			goto cleanup;
+		}
 
 		rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1;
 
@@ -4439,7 +4463,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
-		cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_APPEND;
 		nhn++;
 	}
 
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 33fb35cbfac1..558fe8cc6d43 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void)
 			return -ENOMEM;
 
 		for_each_possible_cpu(cpu) {
-			tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+			tfm = crypto_alloc_shash(algo->name, 0, 0);
 			if (IS_ERR(tfm))
 				return PTR_ERR(tfm);
 			p_tfm = per_cpu_ptr(algo->tfms, cpu);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 19ccf0dc996c..a8854dd3e9c5 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -101,7 +101,7 @@ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb,
 
 	if (do_flowlabel > 0) {
 		hash = skb_get_hash(skb);
-		rol32(hash, 16);
+		hash = rol32(hash, 16);
 		flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 	} else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) {
 		flowlabel = ip6_flowlabel(inner_hdr);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7efa9fd7e109..03e6b7a2bc53 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -938,7 +938,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 					   &tcp_hashinfo, NULL, 0,
 					   &ipv6h->saddr,
 					   th->source, &ipv6h->daddr,
-					   ntohs(th->source), tcp_v6_iif(skb),
+					   ntohs(th->source),
+					   tcp_v6_iif_l3_slave(skb),
 					   tcp_v6_sdif(skb));
 		if (!sk1)
 			goto out;
@@ -1609,7 +1610,8 @@ do_time_wait:
 					    skb, __tcp_hdrlen(th),
 					    &ipv6_hdr(skb)->saddr, th->source,
 					    &ipv6_hdr(skb)->daddr,
-					    ntohs(th->dest), tcp_v6_iif(skb),
+					    ntohs(th->dest),
+					    tcp_v6_iif_l3_slave(skb),
 					    sdif);
 		if (sk2) {
 			struct inet_timewait_sock *tw = inet_twsk(sk);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 68e86257a549..893a022f9620 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1488,11 +1488,14 @@ static inline __poll_t iucv_accept_poll(struct sock *parent)
 	return 0;
 }
 
-static __poll_t iucv_sock_poll_mask(struct socket *sock, __poll_t events)
+__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
+			    poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_state == IUCV_LISTEN)
 		return iucv_accept_poll(sk);
 
@@ -2385,7 +2388,7 @@ static const struct proto_ops iucv_sock_ops = {
 	.getname	= iucv_sock_getname,
 	.sendmsg	= iucv_sock_sendmsg,
 	.recvmsg	= iucv_sock_recvmsg,
-	.poll_mask	= iucv_sock_poll_mask,
+	.poll		= iucv_sock_poll,
 	.ioctl		= sock_no_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 84b7d5c6fec8..d3601d421571 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1336,9 +1336,9 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux)
 	struct list_head *head;
 	int index = 0;
 
-	/* For SOCK_SEQPACKET sock type, datagram_poll_mask checks the sk_state,
-	 * so  we set sk_state, otherwise epoll_wait always returns right away
-	 * with EPOLLHUP
+	/* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so
+	 * we set sk_state, otherwise epoll_wait always returns right away with
+	 * EPOLLHUP
 	 */
 	kcm->sk.sk_state = TCP_ESTABLISHED;
 
@@ -1903,7 +1903,7 @@ static const struct proto_ops kcm_dgram_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	sock_no_getname,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	kcm_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -1924,7 +1924,7 @@ static const struct proto_ops kcm_seqpacket_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	sock_no_getname,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	kcm_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 8bdc1cbe490a..5e1d2946ffbf 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3751,7 +3751,7 @@ static const struct proto_ops pfkey_ops = {
 
 	/* Now the operations that really occur. */
 	.release	=	pfkey_release,
-	.poll_mask	=	datagram_poll_mask,
+	.poll		=	datagram_poll,
 	.sendmsg	=	pfkey_sendmsg,
 	.recvmsg	=	pfkey_recvmsg,
 };
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 181073bf6925..a9c05b2bc1b0 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -613,7 +613,7 @@ static const struct proto_ops l2tp_ip_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = l2tp_ip_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 336e4c00abbc..957369192ca1 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -754,7 +754,7 @@ static const struct proto_ops l2tp_ip6_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = l2tp_ip6_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 55188382845c..cf6cca260e7b 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1201,13 +1201,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
 				l2tp_session_get(sock_net(sk), tunnel,
 						 stats.session_id);
 
-			if (session && session->pwtype == L2TP_PWTYPE_PPP) {
-				err = pppol2tp_session_ioctl(session, cmd,
-							     arg);
+			if (!session) {
+				err = -EBADR;
+				break;
+			}
+			if (session->pwtype != L2TP_PWTYPE_PPP) {
 				l2tp_session_dec_refcount(session);
-			} else {
 				err = -EBADR;
+				break;
 			}
+
+			err = pppol2tp_session_ioctl(session, cmd, arg);
+			l2tp_session_dec_refcount(session);
 			break;
 		}
 #ifdef CONFIG_XFRM
@@ -1818,7 +1823,7 @@ static const struct proto_ops pppol2tp_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pppol2tp_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= pppol2tp_setsockopt,
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 804de8490186..1beeea9549fa 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -1192,7 +1192,7 @@ static const struct proto_ops llc_ui_ops = {
 	.socketpair  = sock_no_socketpair,
 	.accept      = llc_ui_accept,
 	.getname     = llc_ui_getname,
-	.poll_mask   = datagram_poll_mask,
+	.poll	     = datagram_poll,
 	.ioctl       = llc_ui_ioctl,
 	.listen      = llc_ui_listen,
 	.shutdown    = llc_ui_shutdown,
diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c
index 89041260784c..260b3dc1b4a2 100644
--- a/net/llc/llc_core.c
+++ b/net/llc/llc_core.c
@@ -73,8 +73,8 @@ struct llc_sap *llc_sap_find(unsigned char sap_value)
 
 	rcu_read_lock_bh();
 	sap = __llc_sap_find(sap_value);
-	if (sap)
-		llc_sap_hold(sap);
+	if (!sap || !llc_sap_hold_safe(sap))
+		sap = NULL;
 	rcu_read_unlock_bh();
 	return sap;
 }
diff --git a/net/mac80211/led.c b/net/mac80211/led.c
index ba0b507ea691..d6c66fc19716 100644
--- a/net/mac80211/led.c
+++ b/net/mac80211/led.c
@@ -52,13 +52,15 @@ void ieee80211_free_led_names(struct ieee80211_local *local)
 	kfree(local->radio_led.name);
 }
 
-static void ieee80211_tx_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_tx_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     tx_led);
 
 	atomic_inc(&local->tx_led_active);
+
+	return 0;
 }
 
 static void ieee80211_tx_led_deactivate(struct led_classdev *led_cdev)
@@ -70,13 +72,15 @@ static void ieee80211_tx_led_deactivate(struct led_classdev *led_cdev)
 	atomic_dec(&local->tx_led_active);
 }
 
-static void ieee80211_rx_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_rx_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     rx_led);
 
 	atomic_inc(&local->rx_led_active);
+
+	return 0;
 }
 
 static void ieee80211_rx_led_deactivate(struct led_classdev *led_cdev)
@@ -88,13 +92,15 @@ static void ieee80211_rx_led_deactivate(struct led_classdev *led_cdev)
 	atomic_dec(&local->rx_led_active);
 }
 
-static void ieee80211_assoc_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_assoc_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     assoc_led);
 
 	atomic_inc(&local->assoc_led_active);
+
+	return 0;
 }
 
 static void ieee80211_assoc_led_deactivate(struct led_classdev *led_cdev)
@@ -106,13 +112,15 @@ static void ieee80211_assoc_led_deactivate(struct led_classdev *led_cdev)
 	atomic_dec(&local->assoc_led_active);
 }
 
-static void ieee80211_radio_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_radio_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     radio_led);
 
 	atomic_inc(&local->radio_led_active);
+
+	return 0;
 }
 
 static void ieee80211_radio_led_deactivate(struct led_classdev *led_cdev)
@@ -124,13 +132,15 @@ static void ieee80211_radio_led_deactivate(struct led_classdev *led_cdev)
 	atomic_dec(&local->radio_led_active);
 }
 
-static void ieee80211_tpt_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_tpt_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     tpt_led);
 
 	atomic_inc(&local->tpt_led_active);
+
+	return 0;
 }
 
 static void ieee80211_tpt_led_deactivate(struct led_classdev *led_cdev)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 0a38cc1cbebc..932985ca4e66 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2254,11 +2254,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb,
 		     sdata->control_port_over_nl80211)) {
 		struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 		bool noencrypt = status->flag & RX_FLAG_DECRYPTED;
-		struct ethhdr *ehdr = eth_hdr(skb);
 
-		cfg80211_rx_control_port(dev, skb->data, skb->len,
-					 ehdr->h_source,
-					 be16_to_cpu(skb->protocol), noencrypt);
+		cfg80211_rx_control_port(dev, skb, noencrypt);
 		dev_kfree_skb(skb);
 	} else {
 		/* deliver to local stack */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 44b5dfe8727d..fa1f1e63a264 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4845,7 +4845,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 	skb_reset_network_header(skb);
 	skb_reset_mac_header(skb);
 
+	local_bh_disable();
 	__ieee80211_subif_start_xmit(skb, skb->dev, flags);
+	local_bh_enable();
 
 	return 0;
 }
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 5e2e511c4a6f..d02fbfec3783 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2111,7 +2111,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		if (!sta->uploaded)
 			continue;
 
-		if (sta->sdata->vif.type != NL80211_IFTYPE_AP)
+		if (sta->sdata->vif.type != NL80211_IFTYPE_AP &&
+		    sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN)
 			continue;
 
 		for (state = IEEE80211_STA_NOTEXIST;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index dbd7d1fad277..f0a1c536ef15 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -460,6 +460,13 @@ config NF_TABLES
 
 if NF_TABLES
 
+config NF_TABLES_SET
+	tristate "Netfilter nf_tables set infrastructure"
+	help
+	  This option enables the nf_tables set infrastructure that allows to
+	  look up for elements in a set and to build one-way mappings between
+	  matchings and actions.
+
 config NF_TABLES_INET
 	depends on IPV6
 	select NF_TABLES_IPV4
@@ -493,24 +500,6 @@ config NFT_FLOW_OFFLOAD
 	  This option adds the "flow_offload" expression that you can use to
 	  choose what flows are placed into the hardware.
 
-config NFT_SET_RBTREE
-	tristate "Netfilter nf_tables rbtree set module"
-	help
-	  This option adds the "rbtree" set type (Red Black tree) that is used
-	  to build interval-based sets.
-
-config NFT_SET_HASH
-	tristate "Netfilter nf_tables hash set module"
-	help
-	  This option adds the "hash" set type that is used to build one-way
-	  mappings between matchings and actions.
-
-config NFT_SET_BITMAP
-	tristate "Netfilter nf_tables bitmap set module"
-	help
-	  This option adds the "bitmap" set type that is used to build sets
-	  whose keys are smaller or equal to 16 bits.
-
 config NFT_COUNTER
 	tristate "Netfilter nf_tables counter module"
 	help
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 44449389e527..8a76dced974d 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -78,7 +78,11 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \
 		  nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
 		  nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o
 
+nf_tables_set-objs := nf_tables_set_core.o \
+		      nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o
+
 obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
+obj-$(CONFIG_NF_TABLES_SET)	+= nf_tables_set.o
 obj-$(CONFIG_NFT_COMPAT)	+= nft_compat.o
 obj-$(CONFIG_NFT_CONNLIMIT)	+= nft_connlimit.o
 obj-$(CONFIG_NFT_NUMGEN)	+= nft_numgen.o
@@ -91,9 +95,6 @@ obj-$(CONFIG_NFT_QUEUE)		+= nft_queue.o
 obj-$(CONFIG_NFT_QUOTA)		+= nft_quota.o
 obj-$(CONFIG_NFT_REJECT) 	+= nft_reject.o
 obj-$(CONFIG_NFT_REJECT_INET)	+= nft_reject_inet.o
-obj-$(CONFIG_NFT_SET_RBTREE)	+= nft_set_rbtree.o
-obj-$(CONFIG_NFT_SET_HASH)	+= nft_set_hash.o
-obj-$(CONFIG_NFT_SET_BITMAP)	+= nft_set_bitmap.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
 obj-$(CONFIG_NFT_MASQ)		+= nft_masq.o
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index d8383609fe28..510039862aa9 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -47,6 +47,8 @@ struct nf_conncount_tuple {
 	struct hlist_node		node;
 	struct nf_conntrack_tuple	tuple;
 	struct nf_conntrack_zone	zone;
+	int				cpu;
+	u32				jiffies32;
 };
 
 struct nf_conncount_rb {
@@ -91,11 +93,42 @@ bool nf_conncount_add(struct hlist_head *head,
 		return false;
 	conn->tuple = *tuple;
 	conn->zone = *zone;
+	conn->cpu = raw_smp_processor_id();
+	conn->jiffies32 = (u32)jiffies;
 	hlist_add_head(&conn->node, head);
 	return true;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_add);
 
+static const struct nf_conntrack_tuple_hash *
+find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
+{
+	const struct nf_conntrack_tuple_hash *found;
+	unsigned long a, b;
+	int cpu = raw_smp_processor_id();
+	__s32 age;
+
+	found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
+	if (found)
+		return found;
+	b = conn->jiffies32;
+	a = (u32)jiffies;
+
+	/* conn might have been added just before by another cpu and
+	 * might still be unconfirmed.  In this case, nf_conntrack_find()
+	 * returns no result.  Thus only evict if this cpu added the
+	 * stale entry or if the entry is older than two jiffies.
+	 */
+	age = a - b;
+	if (conn->cpu == cpu || age >= 2) {
+		hlist_del(&conn->node);
+		kmem_cache_free(conncount_conn_cachep, conn);
+		return ERR_PTR(-ENOENT);
+	}
+
+	return ERR_PTR(-EAGAIN);
+}
+
 unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 				 const struct nf_conntrack_tuple *tuple,
 				 const struct nf_conntrack_zone *zone,
@@ -103,18 +136,27 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn;
-	struct hlist_node *n;
 	struct nf_conn *found_ct;
+	struct hlist_node *n;
 	unsigned int length = 0;
 
 	*addit = tuple ? true : false;
 
 	/* check the saved connections */
 	hlist_for_each_entry_safe(conn, n, head, node) {
-		found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
-		if (found == NULL) {
-			hlist_del(&conn->node);
-			kmem_cache_free(conncount_conn_cachep, conn);
+		found = find_or_evict(net, conn);
+		if (IS_ERR(found)) {
+			/* Not found, but might be about to be confirmed */
+			if (PTR_ERR(found) == -EAGAIN) {
+				length++;
+				if (!tuple)
+					continue;
+
+				if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
+				    nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
+				    nf_ct_zone_id(zone, zone->dir))
+					*addit = false;
+			}
 			continue;
 		}
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3465da2a98bd..3d5280425027 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2043,7 +2043,7 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp)
 		return -EOPNOTSUPP;
 
 	/* On boot, we can set this without any fancy locking. */
-	if (!nf_conntrack_htable_size)
+	if (!nf_conntrack_hash)
 		return param_set_uint(val, kp);
 
 	rc = kstrtouint(val, 0, &hashsize);
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 551a1eddf0fa..a75b11c39312 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -465,6 +465,11 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 
 	nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
 	nf_ct_iterate_destroy(unhelp, me);
+
+	/* Maybe someone has gotten the helper already when unhelp above.
+	 * So need to wait it.
+	 */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
 
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index abe647d5b8c6..9ce6336d1e55 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -243,14 +243,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
 		 * We currently ignore Sync packets
 		 *
 		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
 		},
 		[DCCP_PKT_SYNCACK] = {
 		/*
 		 * We currently ignore SyncAck packets
 		 *
 		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
 		},
 	},
 	[CT_DCCP_ROLE_SERVER] = {
@@ -371,14 +371,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
 		 * We currently ignore Sync packets
 		 *
 		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
 		},
 		[DCCP_PKT_SYNCACK] = {
 		/*
 		 * We currently ignore SyncAck packets
 		 *
 		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
 		},
 	},
 };
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 426457047578..a61d6df6e5f6 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -424,6 +424,10 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
 	if (write) {
 		struct ctl_table tmp = *table;
 
+		/* proc_dostring() can append to existing strings, so we need to
+		 * initialize it as an empty string.
+		 */
+		buf[0] = '\0';
 		tmp.data = buf;
 		r = proc_dostring(&tmp, write, buffer, lenp, ppos);
 		if (r)
@@ -442,14 +446,17 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
 		rcu_assign_pointer(net->nf.nf_loggers[tindex], logger);
 		mutex_unlock(&nf_log_mutex);
 	} else {
+		struct ctl_table tmp = *table;
+
+		tmp.data = buf;
 		mutex_lock(&nf_log_mutex);
 		logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
 		if (!logger)
-			table->data = "NONE";
+			strlcpy(buf, "NONE", sizeof(buf));
 		else
-			table->data = logger->name;
-		r = proc_dostring(table, write, buffer, lenp, ppos);
+			strlcpy(buf, logger->name, sizeof(buf));
 		mutex_unlock(&nf_log_mutex);
+		r = proc_dostring(&tmp, write, buffer, lenp, ppos);
 	}
 
 	return r;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 896d4a36081d..f5745e4c6513 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -75,6 +75,7 @@ static void nft_ctx_init(struct nft_ctx *ctx,
 {
 	ctx->net	= net;
 	ctx->family	= family;
+	ctx->level	= 0;
 	ctx->table	= table;
 	ctx->chain	= chain;
 	ctx->nla   	= nla;
@@ -1597,7 +1598,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 	struct nft_base_chain *basechain;
 	struct nft_stats *stats = NULL;
 	struct nft_chain_hook hook;
-	const struct nlattr *name;
 	struct nf_hook_ops *ops;
 	struct nft_trans *trans;
 	int err;
@@ -1645,12 +1645,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 			return PTR_ERR(stats);
 	}
 
+	err = -ENOMEM;
 	trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN,
 				sizeof(struct nft_trans_chain));
-	if (trans == NULL) {
-		free_percpu(stats);
-		return -ENOMEM;
-	}
+	if (trans == NULL)
+		goto err;
 
 	nft_trans_chain_stats(trans) = stats;
 	nft_trans_chain_update(trans) = true;
@@ -1660,19 +1659,37 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 	else
 		nft_trans_chain_policy(trans) = -1;
 
-	name = nla[NFTA_CHAIN_NAME];
-	if (nla[NFTA_CHAIN_HANDLE] && name) {
-		nft_trans_chain_name(trans) =
-			nla_strdup(name, GFP_KERNEL);
-		if (!nft_trans_chain_name(trans)) {
-			kfree(trans);
-			free_percpu(stats);
-			return -ENOMEM;
+	if (nla[NFTA_CHAIN_HANDLE] &&
+	    nla[NFTA_CHAIN_NAME]) {
+		struct nft_trans *tmp;
+		char *name;
+
+		err = -ENOMEM;
+		name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL);
+		if (!name)
+			goto err;
+
+		err = -EEXIST;
+		list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) {
+			if (tmp->msg_type == NFT_MSG_NEWCHAIN &&
+			    tmp->ctx.table == table &&
+			    nft_trans_chain_update(tmp) &&
+			    nft_trans_chain_name(tmp) &&
+			    strcmp(name, nft_trans_chain_name(tmp)) == 0) {
+				kfree(name);
+				goto err;
+			}
 		}
+
+		nft_trans_chain_name(trans) = name;
 	}
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 
 	return 0;
+err:
+	free_percpu(stats);
+	kfree(trans);
+	return err;
 }
 
 static int nf_tables_newchain(struct net *net, struct sock *nlsk,
@@ -2254,6 +2271,39 @@ done:
 	return skb->len;
 }
 
+static int nf_tables_dump_rules_start(struct netlink_callback *cb)
+{
+	const struct nlattr * const *nla = cb->data;
+	struct nft_rule_dump_ctx *ctx = NULL;
+
+	if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) {
+		ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
+		if (!ctx)
+			return -ENOMEM;
+
+		if (nla[NFTA_RULE_TABLE]) {
+			ctx->table = nla_strdup(nla[NFTA_RULE_TABLE],
+							GFP_ATOMIC);
+			if (!ctx->table) {
+				kfree(ctx);
+				return -ENOMEM;
+			}
+		}
+		if (nla[NFTA_RULE_CHAIN]) {
+			ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN],
+						GFP_ATOMIC);
+			if (!ctx->chain) {
+				kfree(ctx->table);
+				kfree(ctx);
+				return -ENOMEM;
+			}
+		}
+	}
+
+	cb->data = ctx;
+	return 0;
+}
+
 static int nf_tables_dump_rules_done(struct netlink_callback *cb)
 {
 	struct nft_rule_dump_ctx *ctx = cb->data;
@@ -2283,38 +2333,13 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start= nf_tables_dump_rules_start,
 			.dump = nf_tables_dump_rules,
 			.done = nf_tables_dump_rules_done,
 			.module = THIS_MODULE,
+			.data = (void *)nla,
 		};
 
-		if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) {
-			struct nft_rule_dump_ctx *ctx;
-
-			ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
-			if (!ctx)
-				return -ENOMEM;
-
-			if (nla[NFTA_RULE_TABLE]) {
-				ctx->table = nla_strdup(nla[NFTA_RULE_TABLE],
-							GFP_ATOMIC);
-				if (!ctx->table) {
-					kfree(ctx);
-					return -ENOMEM;
-				}
-			}
-			if (nla[NFTA_RULE_CHAIN]) {
-				ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN],
-							GFP_ATOMIC);
-				if (!ctx->chain) {
-					kfree(ctx->table);
-					kfree(ctx);
-					return -ENOMEM;
-				}
-			}
-			c.data = ctx;
-		}
-
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
 
@@ -2384,6 +2409,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
 	struct nft_rule *rule;
 	int err;
 
+	if (ctx->level == NFT_JUMP_STACK_SIZE)
+		return -EMLINK;
+
 	list_for_each_entry(rule, &chain->rules, list) {
 		if (!nft_is_active_next(ctx->net, rule))
 			continue;
@@ -3161,6 +3189,18 @@ done:
 	return skb->len;
 }
 
+static int nf_tables_dump_sets_start(struct netlink_callback *cb)
+{
+	struct nft_ctx *ctx_dump = NULL;
+
+	ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC);
+	if (ctx_dump == NULL)
+		return -ENOMEM;
+
+	cb->data = ctx_dump;
+	return 0;
+}
+
 static int nf_tables_dump_sets_done(struct netlink_callback *cb)
 {
 	kfree(cb->data);
@@ -3188,18 +3228,12 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start = nf_tables_dump_sets_start,
 			.dump = nf_tables_dump_sets,
 			.done = nf_tables_dump_sets_done,
+			.data = &ctx,
 			.module = THIS_MODULE,
 		};
-		struct nft_ctx *ctx_dump;
-
-		ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC);
-		if (ctx_dump == NULL)
-			return -ENOMEM;
-
-		*ctx_dump = ctx;
-		c.data = ctx_dump;
 
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
@@ -3849,6 +3883,15 @@ nla_put_failure:
 	return -ENOSPC;
 }
 
+static int nf_tables_dump_set_start(struct netlink_callback *cb)
+{
+	struct nft_set_dump_ctx *dump_ctx = cb->data;
+
+	cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC);
+
+	return cb->data ? 0 : -ENOMEM;
+}
+
 static int nf_tables_dump_set_done(struct netlink_callback *cb)
 {
 	kfree(cb->data);
@@ -4002,20 +4045,17 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start = nf_tables_dump_set_start,
 			.dump = nf_tables_dump_set,
 			.done = nf_tables_dump_set_done,
 			.module = THIS_MODULE,
 		};
-		struct nft_set_dump_ctx *dump_ctx;
-
-		dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC);
-		if (!dump_ctx)
-			return -ENOMEM;
-
-		dump_ctx->set = set;
-		dump_ctx->ctx = ctx;
+		struct nft_set_dump_ctx dump_ctx = {
+			.set = set,
+			.ctx = ctx,
+		};
 
-		c.data = dump_ctx;
+		c.data = &dump_ctx;
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
 
@@ -4975,38 +5015,42 @@ done:
 	return skb->len;
 }
 
-static int nf_tables_dump_obj_done(struct netlink_callback *cb)
+static int nf_tables_dump_obj_start(struct netlink_callback *cb)
 {
-	struct nft_obj_filter *filter = cb->data;
+	const struct nlattr * const *nla = cb->data;
+	struct nft_obj_filter *filter = NULL;
 
-	if (filter) {
-		kfree(filter->table);
-		kfree(filter);
+	if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) {
+		filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
+		if (!filter)
+			return -ENOMEM;
+
+		if (nla[NFTA_OBJ_TABLE]) {
+			filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC);
+			if (!filter->table) {
+				kfree(filter);
+				return -ENOMEM;
+			}
+		}
+
+		if (nla[NFTA_OBJ_TYPE])
+			filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
 	}
 
+	cb->data = filter;
 	return 0;
 }
 
-static struct nft_obj_filter *
-nft_obj_filter_alloc(const struct nlattr * const nla[])
+static int nf_tables_dump_obj_done(struct netlink_callback *cb)
 {
-	struct nft_obj_filter *filter;
-
-	filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
-	if (!filter)
-		return ERR_PTR(-ENOMEM);
+	struct nft_obj_filter *filter = cb->data;
 
-	if (nla[NFTA_OBJ_TABLE]) {
-		filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC);
-		if (!filter->table) {
-			kfree(filter);
-			return ERR_PTR(-ENOMEM);
-		}
+	if (filter) {
+		kfree(filter->table);
+		kfree(filter);
 	}
-	if (nla[NFTA_OBJ_TYPE])
-		filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
 
-	return filter;
+	return 0;
 }
 
 /* called with rcu_read_lock held */
@@ -5027,21 +5071,13 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start = nf_tables_dump_obj_start,
 			.dump = nf_tables_dump_obj,
 			.done = nf_tables_dump_obj_done,
 			.module = THIS_MODULE,
+			.data = (void *)nla,
 		};
 
-		if (nla[NFTA_OBJ_TABLE] ||
-		    nla[NFTA_OBJ_TYPE]) {
-			struct nft_obj_filter *filter;
-
-			filter = nft_obj_filter_alloc(nla);
-			if (IS_ERR(filter))
-				return -ENOMEM;
-
-			c.data = filter;
-		}
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
 
@@ -5320,8 +5356,6 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
 		flowtable->ops[i].priv		= &flowtable->data;
 		flowtable->ops[i].hook		= flowtable->data.type->hook;
 		flowtable->ops[i].dev		= dev_array[i];
-		flowtable->dev_name[i]		= kstrdup(dev_array[i]->name,
-							  GFP_KERNEL);
 	}
 
 	return err;
@@ -5479,10 +5513,8 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 err6:
 	i = flowtable->ops_len;
 err5:
-	for (k = i - 1; k >= 0; k--) {
-		kfree(flowtable->dev_name[k]);
+	for (k = i - 1; k >= 0; k--)
 		nf_unregister_net_hook(net, &flowtable->ops[k]);
-	}
 
 	kfree(flowtable->ops);
 err4:
@@ -5581,9 +5613,10 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 		goto nla_put_failure;
 
 	for (i = 0; i < flowtable->ops_len; i++) {
-		if (flowtable->dev_name[i][0] &&
-		    nla_put_string(skb, NFTA_DEVICE_NAME,
-				   flowtable->dev_name[i]))
+		const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev);
+
+		if (dev &&
+		    nla_put_string(skb, NFTA_DEVICE_NAME, dev->name))
 			goto nla_put_failure;
 	}
 	nla_nest_end(skb, nest_devs);
@@ -5650,37 +5683,39 @@ done:
 	return skb->len;
 }
 
-static int nf_tables_dump_flowtable_done(struct netlink_callback *cb)
+static int nf_tables_dump_flowtable_start(struct netlink_callback *cb)
 {
-	struct nft_flowtable_filter *filter = cb->data;
+	const struct nlattr * const *nla = cb->data;
+	struct nft_flowtable_filter *filter = NULL;
 
-	if (!filter)
-		return 0;
+	if (nla[NFTA_FLOWTABLE_TABLE]) {
+		filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
+		if (!filter)
+			return -ENOMEM;
 
-	kfree(filter->table);
-	kfree(filter);
+		filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE],
+					   GFP_ATOMIC);
+		if (!filter->table) {
+			kfree(filter);
+			return -ENOMEM;
+		}
+	}
 
+	cb->data = filter;
 	return 0;
 }
 
-static struct nft_flowtable_filter *
-nft_flowtable_filter_alloc(const struct nlattr * const nla[])
+static int nf_tables_dump_flowtable_done(struct netlink_callback *cb)
 {
-	struct nft_flowtable_filter *filter;
+	struct nft_flowtable_filter *filter = cb->data;
 
-	filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
 	if (!filter)
-		return ERR_PTR(-ENOMEM);
+		return 0;
 
-	if (nla[NFTA_FLOWTABLE_TABLE]) {
-		filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE],
-					   GFP_ATOMIC);
-		if (!filter->table) {
-			kfree(filter);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
-	return filter;
+	kfree(filter->table);
+	kfree(filter);
+
+	return 0;
 }
 
 /* called with rcu_read_lock held */
@@ -5700,20 +5735,13 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start = nf_tables_dump_flowtable_start,
 			.dump = nf_tables_dump_flowtable,
 			.done = nf_tables_dump_flowtable_done,
 			.module = THIS_MODULE,
+			.data = (void *)nla,
 		};
 
-		if (nla[NFTA_FLOWTABLE_TABLE]) {
-			struct nft_flowtable_filter *filter;
-
-			filter = nft_flowtable_filter_alloc(nla);
-			if (IS_ERR(filter))
-				return -ENOMEM;
-
-			c.data = filter;
-		}
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
 
@@ -5783,6 +5811,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
 	kfree(flowtable->name);
 	flowtable->data.type->free(&flowtable->data);
 	module_put(flowtable->data.type->owner);
+	kfree(flowtable);
 }
 
 static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
@@ -5825,7 +5854,6 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev,
 			continue;
 
 		nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]);
-		flowtable->dev_name[i][0] = '\0';
 		flowtable->ops[i].dev = NULL;
 		break;
 	}
@@ -6086,6 +6114,9 @@ static void nft_commit_release(struct nft_trans *trans)
 	case NFT_MSG_DELTABLE:
 		nf_tables_table_destroy(&trans->ctx);
 		break;
+	case NFT_MSG_NEWCHAIN:
+		kfree(nft_trans_chain_name(trans));
+		break;
 	case NFT_MSG_DELCHAIN:
 		nf_tables_chain_destroy(&trans->ctx);
 		break;
@@ -6315,13 +6346,15 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 			nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE);
 			break;
 		case NFT_MSG_NEWCHAIN:
-			if (nft_trans_chain_update(trans))
+			if (nft_trans_chain_update(trans)) {
 				nft_chain_commit_update(trans);
-			else
+				nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+				/* trans destroyed after rcu grace period */
+			} else {
 				nft_clear(net, trans->ctx.chain);
-
-			nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
-			nft_trans_destroy(trans);
+				nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+				nft_trans_destroy(trans);
+			}
 			break;
 		case NFT_MSG_DELCHAIN:
 			nft_chain_del(trans->ctx.chain);
@@ -6471,7 +6504,7 @@ static int __nf_tables_abort(struct net *net)
 		case NFT_MSG_NEWCHAIN:
 			if (nft_trans_chain_update(trans)) {
 				free_percpu(nft_trans_chain_stats(trans));
-
+				kfree(nft_trans_chain_name(trans));
 				nft_trans_destroy(trans);
 			} else {
 				trans->ctx.table->use--;
@@ -6837,13 +6870,6 @@ int nft_validate_register_store(const struct nft_ctx *ctx,
 			err = nf_tables_check_loops(ctx, data->verdict.chain);
 			if (err < 0)
 				return err;
-
-			if (ctx->chain->level + 1 >
-			    data->verdict.chain->level) {
-				if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE)
-					return -EMLINK;
-				data->verdict.chain->level = ctx->chain->level + 1;
-			}
 		}
 
 		return 0;
diff --git a/net/netfilter/nf_tables_set_core.c b/net/netfilter/nf_tables_set_core.c
new file mode 100644
index 000000000000..814789644bd3
--- /dev/null
+++ b/net/netfilter/nf_tables_set_core.c
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <net/netfilter/nf_tables_core.h>
+
+static int __init nf_tables_set_module_init(void)
+{
+	nft_register_set(&nft_set_hash_fast_type);
+	nft_register_set(&nft_set_hash_type);
+	nft_register_set(&nft_set_rhash_type);
+	nft_register_set(&nft_set_bitmap_type);
+	nft_register_set(&nft_set_rbtree_type);
+
+	return 0;
+}
+
+static void __exit nf_tables_set_module_exit(void)
+{
+	nft_unregister_set(&nft_set_rbtree_type);
+	nft_unregister_set(&nft_set_bitmap_type);
+	nft_unregister_set(&nft_set_rhash_type);
+	nft_unregister_set(&nft_set_hash_type);
+	nft_unregister_set(&nft_set_hash_fast_type);
+}
+
+module_init(nf_tables_set_module_init);
+module_exit(nf_tables_set_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 4ccd2988f9db..ea4ba551abb2 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1243,6 +1243,9 @@ static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl,
 static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
 	[NFQA_CFG_CMD]		= { .len = sizeof(struct nfqnl_msg_config_cmd) },
 	[NFQA_CFG_PARAMS]	= { .len = sizeof(struct nfqnl_msg_config_params) },
+	[NFQA_CFG_QUEUE_MAXLEN]	= { .type = NLA_U32 },
+	[NFQA_CFG_MASK]		= { .type = NLA_U32 },
+	[NFQA_CFG_FLAGS]	= { .type = NLA_U32 },
 };
 
 static const struct nf_queue_handler nfqh = {
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 8d1ff654e5af..32535eea51b2 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -832,10 +832,18 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	rev = ntohl(nla_get_be32(tb[NFTA_TARGET_REV]));
 	family = ctx->family;
 
+	if (strcmp(tg_name, XT_ERROR_TARGET) == 0 ||
+	    strcmp(tg_name, XT_STANDARD_TARGET) == 0 ||
+	    strcmp(tg_name, "standard") == 0)
+		return ERR_PTR(-EINVAL);
+
 	/* Re-use the existing target if it's already loaded. */
 	list_for_each_entry(nft_target, &nft_target_list, head) {
 		struct xt_target *target = nft_target->ops.data;
 
+		if (!target->target)
+			continue;
+
 		if (nft_target_cmp(target, tg_name, rev, family))
 			return &nft_target->ops;
 	}
@@ -844,6 +852,11 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	if (IS_ERR(target))
 		return ERR_PTR(-ENOENT);
 
+	if (!target->target) {
+		err = -EINVAL;
+		goto err;
+	}
+
 	if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) {
 		err = -EINVAL;
 		goto err;
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 15adf8ca82c3..0777a93211e2 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -98,6 +98,7 @@ static int nft_immediate_validate(const struct nft_ctx *ctx,
 				  const struct nft_data **d)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+	struct nft_ctx *pctx = (struct nft_ctx *)ctx;
 	const struct nft_data *data;
 	int err;
 
@@ -109,9 +110,11 @@ static int nft_immediate_validate(const struct nft_ctx *ctx,
 	switch (data->verdict.code) {
 	case NFT_JUMP:
 	case NFT_GOTO:
+		pctx->level++;
 		err = nft_chain_validate(ctx, data->verdict.chain);
 		if (err < 0)
 			return err;
+		pctx->level--;
 		break;
 	default:
 		break;
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 42e6fadf1417..c2a1d84cdfc4 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -155,7 +155,9 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx,
 				       struct nft_set_elem *elem)
 {
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+	struct nft_ctx *pctx = (struct nft_ctx *)ctx;
 	const struct nft_data *data;
+	int err;
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
 	    *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
@@ -165,10 +167,17 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx,
 	switch (data->verdict.code) {
 	case NFT_JUMP:
 	case NFT_GOTO:
-		return nft_chain_validate(ctx, data->verdict.chain);
+		pctx->level++;
+		err = nft_chain_validate(ctx, data->verdict.chain);
+		if (err < 0)
+			return err;
+		pctx->level--;
+		break;
 	default:
-		return 0;
+		break;
 	}
+
+	return 0;
 }
 
 static int nft_lookup_validate(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index d6626e01c7ee..128bc16f52dd 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -296,7 +296,7 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features,
 	return true;
 }
 
-static struct nft_set_type nft_bitmap_type __read_mostly = {
+struct nft_set_type nft_set_bitmap_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.ops		= {
 		.privsize	= nft_bitmap_privsize,
@@ -314,20 +314,3 @@ static struct nft_set_type nft_bitmap_type __read_mostly = {
 		.get		= nft_bitmap_get,
 	},
 };
-
-static int __init nft_bitmap_module_init(void)
-{
-	return nft_register_set(&nft_bitmap_type);
-}
-
-static void __exit nft_bitmap_module_exit(void)
-{
-	nft_unregister_set(&nft_bitmap_type);
-}
-
-module_init(nft_bitmap_module_init);
-module_exit(nft_bitmap_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
-MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 6f9a1365a09f..90c3e7e6cacb 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -387,6 +387,7 @@ static void nft_rhash_destroy(const struct nft_set *set)
 	struct nft_rhash *priv = nft_set_priv(set);
 
 	cancel_delayed_work_sync(&priv->gc_work);
+	rcu_barrier();
 	rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy,
 				    (void *)set);
 }
@@ -654,7 +655,7 @@ static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features
 	return true;
 }
 
-static struct nft_set_type nft_rhash_type __read_mostly = {
+struct nft_set_type nft_set_rhash_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.features	= NFT_SET_MAP | NFT_SET_OBJECT |
 			  NFT_SET_TIMEOUT | NFT_SET_EVAL,
@@ -677,7 +678,7 @@ static struct nft_set_type nft_rhash_type __read_mostly = {
 	},
 };
 
-static struct nft_set_type nft_hash_type __read_mostly = {
+struct nft_set_type nft_set_hash_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.features	= NFT_SET_MAP | NFT_SET_OBJECT,
 	.ops		= {
@@ -697,7 +698,7 @@ static struct nft_set_type nft_hash_type __read_mostly = {
 	},
 };
 
-static struct nft_set_type nft_hash_fast_type __read_mostly = {
+struct nft_set_type nft_set_hash_fast_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.features	= NFT_SET_MAP | NFT_SET_OBJECT,
 	.ops		= {
@@ -716,26 +717,3 @@ static struct nft_set_type nft_hash_fast_type __read_mostly = {
 		.get		= nft_hash_get,
 	},
 };
-
-static int __init nft_hash_module_init(void)
-{
-	if (nft_register_set(&nft_hash_fast_type) ||
-	    nft_register_set(&nft_hash_type) ||
-	    nft_register_set(&nft_rhash_type))
-		return 1;
-	return 0;
-}
-
-static void __exit nft_hash_module_exit(void)
-{
-	nft_unregister_set(&nft_rhash_type);
-	nft_unregister_set(&nft_hash_type);
-	nft_unregister_set(&nft_hash_fast_type);
-}
-
-module_init(nft_hash_module_init);
-module_exit(nft_hash_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 7f3a9a211034..9873d734b494 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -381,7 +381,7 @@ static void nft_rbtree_gc(struct work_struct *work)
 
 		gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
 		if (!gcb)
-			goto out;
+			break;
 
 		atomic_dec(&set->nelems);
 		nft_set_gc_batch_add(gcb, rbe);
@@ -390,10 +390,12 @@ static void nft_rbtree_gc(struct work_struct *work)
 			rbe = rb_entry(prev, struct nft_rbtree_elem, node);
 			atomic_dec(&set->nelems);
 			nft_set_gc_batch_add(gcb, rbe);
+			prev = NULL;
 		}
 		node = rb_next(node);
+		if (!node)
+			break;
 	}
-out:
 	if (gcb) {
 		for (i = 0; i < gcb->head.cnt; i++) {
 			rbe = gcb->elems[i];
@@ -440,6 +442,7 @@ static void nft_rbtree_destroy(const struct nft_set *set)
 	struct rb_node *node;
 
 	cancel_delayed_work_sync(&priv->gc_work);
+	rcu_barrier();
 	while ((node = priv->root.rb_node) != NULL) {
 		rb_erase(node, &priv->root);
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
@@ -462,7 +465,7 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
 	return true;
 }
 
-static struct nft_set_type nft_rbtree_type __read_mostly = {
+struct nft_set_type nft_set_rbtree_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.features	= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT,
 	.ops		= {
@@ -481,20 +484,3 @@ static struct nft_set_type nft_rbtree_type __read_mostly = {
 		.get		= nft_rbtree_get,
 	},
 };
-
-static int __init nft_rbtree_module_init(void)
-{
-	return nft_register_set(&nft_rbtree_type);
-}
-
-static void __exit nft_rbtree_module_exit(void)
-{
-	nft_unregister_set(&nft_rbtree_type);
-}
-
-module_init(nft_rbtree_module_init);
-module_exit(nft_rbtree_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 58fce4e749a9..d76550a8b642 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -61,7 +61,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport,
 	 * addresses, this happens if the redirect already happened
 	 * and the current packet belongs to an already established
 	 * connection */
-	sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+	sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
 				   iph->saddr, iph->daddr,
 				   hp->source, hp->dest,
 				   skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED);
@@ -77,7 +77,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport,
 	else if (!sk)
 		/* no, there's no established connection, check if
 		 * there's a listener on the redirected addr/port */
-		sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+		sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
 					   iph->saddr, laddr,
 					   hp->source, lport,
 					   skb->dev, NF_TPROXY_LOOKUP_LISTENER);
@@ -150,7 +150,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
 	 * addresses, this happens if the redirect already happened
 	 * and the current packet belongs to an already established
 	 * connection */
-	sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto,
+	sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto,
 				   &iph->saddr, &iph->daddr,
 				   hp->source, hp->dest,
 				   xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED);
@@ -171,7 +171,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
 	else if (!sk)
 		/* no there's no established connection, check if
 		 * there's a listener on the redirected addr/port */
-		sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp,
+		sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff,
 					   tproto, &iph->saddr, laddr,
 					   hp->source, lport,
 					   xt_in(par), NF_TPROXY_LOOKUP_LISTENER);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 1189b84413d5..56704d95f82d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -63,6 +63,7 @@
 #include <linux/hash.h>
 #include <linux/genetlink.h>
 #include <linux/net_namespace.h>
+#include <linux/nospec.h>
 
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
@@ -679,6 +680,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 
 	if (protocol < 0 || protocol >= MAX_LINKS)
 		return -EPROTONOSUPPORT;
+	protocol = array_index_nospec(protocol, MAX_LINKS);
 
 	netlink_lock_table();
 #ifdef CONFIG_MODULES
@@ -1009,6 +1011,11 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			return err;
 	}
 
+	if (nlk->ngroups == 0)
+		groups = 0;
+	else if (nlk->ngroups < 8*sizeof(groups))
+		groups &= (1UL << nlk->ngroups) - 1;
+
 	bound = nlk->bound;
 	if (bound) {
 		/* Ensure nlk->portid is up-to-date. */
@@ -2658,7 +2665,7 @@ static const struct proto_ops netlink_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	netlink_getname,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	netlink_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 93fbcafbf388..03f37c4e64fe 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1355,7 +1355,7 @@ static const struct proto_ops nr_proto_ops = {
 	.socketpair	=	sock_no_socketpair,
 	.accept		=	nr_accept,
 	.getname	=	nr_getname,
-	.poll_mask	=	datagram_poll_mask,
+	.poll		=	datagram_poll,
 	.ioctl		=	nr_ioctl,
 	.listen		=	nr_listen,
 	.shutdown	=	sock_no_shutdown,
diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index 2ceefa183cee..6a196e438b6c 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -752,11 +752,14 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap,
 		pr_debug("Fragment %zd bytes remaining %zd",
 			 frag_len, remaining_len);
 
-		pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT,
+		pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0,
 					 frag_len + LLCP_HEADER_SIZE, &err);
 		if (pdu == NULL) {
-			pr_err("Could not allocate PDU\n");
-			continue;
+			pr_err("Could not allocate PDU (error=%d)\n", err);
+			len -= remaining_len;
+			if (len == 0)
+				len = err;
+			break;
 		}
 
 		pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index ab5bb14b49af..ea0c0c6f1874 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -548,13 +548,16 @@ static inline __poll_t llcp_accept_poll(struct sock *parent)
 	return 0;
 }
 
-static __poll_t llcp_sock_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
+				   poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
 	pr_debug("%p\n", sk);
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_state == LLCP_LISTEN)
 		return llcp_accept_poll(sk);
 
@@ -896,7 +899,7 @@ static const struct proto_ops llcp_sock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = llcp_sock_accept,
 	.getname        = llcp_sock_getname,
-	.poll_mask      = llcp_sock_poll_mask,
+	.poll           = llcp_sock_poll,
 	.ioctl          = sock_no_ioctl,
 	.listen         = llcp_sock_listen,
 	.shutdown       = sock_no_shutdown,
@@ -916,7 +919,7 @@ static const struct proto_ops llcp_rawsock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = llcp_sock_getname,
-	.poll_mask      = llcp_sock_poll_mask,
+	.poll           = llcp_sock_poll,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 60c322531c49..e2188deb08dc 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -284,7 +284,7 @@ static const struct proto_ops rawsock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = sock_no_getname,
-	.poll_mask      = datagram_poll_mask,
+	.poll           = datagram_poll,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,
@@ -304,7 +304,7 @@ static const struct proto_ops rawsock_raw_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = sock_no_getname,
-	.poll_mask      = datagram_poll_mask,
+	.poll           = datagram_poll,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,
diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c
index 9696ef96b719..1a30e165eeb4 100644
--- a/net/nsh/nsh.c
+++ b/net/nsh/nsh.c
@@ -104,7 +104,7 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb,
 	__skb_pull(skb, nsh_len);
 
 	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
+	skb->mac_len = proto == htons(ETH_P_TEB) ? ETH_HLEN : 0;
 	skb->protocol = proto;
 
 	features &= NETIF_F_SG;
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index b891a91577f8..c038e021a591 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -211,6 +211,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a)
 	if (!meter)
 		return ERR_PTR(-ENOMEM);
 
+	meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]);
 	meter->used = div_u64(ktime_get_ns(), 1000 * 1000);
 	meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0;
 	meter->keep_stats = !a[OVS_METER_ATTR_CLEAR];
@@ -280,6 +281,10 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	u32 meter_id;
 	bool failed;
 
+	if (!a[OVS_METER_ATTR_ID]) {
+		return -ENODEV;
+	}
+
 	meter = dp_meter_create(a);
 	if (IS_ERR_OR_NULL(meter))
 		return PTR_ERR(meter);
@@ -298,11 +303,6 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		goto exit_unlock;
 	}
 
-	if (!a[OVS_METER_ATTR_ID]) {
-		err = -ENODEV;
-		goto exit_unlock;
-	}
-
 	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
 
 	/* Cannot fail after this. */
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 50809748c127..e6445d8f3f57 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2262,6 +2262,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		if (po->stats.stats1.tp_drops)
 			status |= TP_STATUS_LOSING;
 	}
+
+	if (do_vnet &&
+	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
+				    sizeof(struct virtio_net_hdr),
+				    vio_le(), true, 0))
+		goto drop_n_account;
+
 	po->stats.stats1.tp_packets++;
 	if (copy_skb) {
 		status |= TP_STATUS_COPY;
@@ -2269,15 +2276,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	}
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	if (do_vnet) {
-		if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
-					    sizeof(struct virtio_net_hdr),
-					    vio_le(), true, 0)) {
-			spin_lock(&sk->sk_receive_queue.lock);
-			goto drop_n_account;
-		}
-	}
-
 	skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
 
 	if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
@@ -2880,6 +2878,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 			goto out_free;
 	} else if (reserve) {
 		skb_reserve(skb, -reserve);
+		if (len < reserve)
+			skb_reset_network_header(skb);
 	}
 
 	/* Returns -EFAULT on error */
@@ -4078,11 +4078,12 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd,
 	return 0;
 }
 
-static __poll_t packet_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t packet_poll(struct file *file, struct socket *sock,
+				poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
-	__poll_t mask = datagram_poll_mask(sock, events);
+	__poll_t mask = datagram_poll(file, sock, wait);
 
 	spin_lock_bh(&sk->sk_receive_queue.lock);
 	if (po->rx_ring.pg_vec) {
@@ -4225,6 +4226,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	}
 
 	if (req->tp_block_nr) {
+		unsigned int min_frame_size;
+
 		/* Sanity tests and some calculations */
 		err = -EBUSY;
 		if (unlikely(rb->pg_vec))
@@ -4247,12 +4250,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 		if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
 			goto out;
+		min_frame_size = po->tp_hdrlen + po->tp_reserve;
 		if (po->tp_version >= TPACKET_V3 &&
-		    req->tp_block_size <=
-		    BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr))
+		    req->tp_block_size <
+		    BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size)
 			goto out;
-		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
-					po->tp_reserve))
+		if (unlikely(req->tp_frame_size < min_frame_size))
 			goto out;
 		if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1)))
 			goto out;
@@ -4424,7 +4427,7 @@ static const struct proto_ops packet_ops_spkt = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	packet_getname_spkt,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	packet_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -4445,7 +4448,7 @@ static const struct proto_ops packet_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	packet_getname,
-	.poll_mask =	packet_poll_mask,
+	.poll =		packet_poll,
 	.ioctl =	packet_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index c295c4e20f01..30187990257f 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -340,12 +340,15 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr,
 	return sizeof(struct sockaddr_pn);
 }
 
-static __poll_t pn_socket_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
+					poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct pep_sock *pn = pep_sk(sk);
 	__poll_t mask = 0;
 
+	poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_state == TCP_CLOSE)
 		return EPOLLERR;
 	if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -445,7 +448,7 @@ const struct proto_ops phonet_dgram_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pn_socket_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.ioctl		= pn_socket_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
@@ -470,7 +473,7 @@ const struct proto_ops phonet_stream_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= pn_socket_accept,
 	.getname	= pn_socket_getname,
-	.poll_mask	= pn_socket_poll_mask,
+	.poll		= pn_socket_poll,
 	.ioctl		= pn_socket_ioctl,
 	.listen		= pn_socket_listen,
 	.shutdown	= sock_no_shutdown,
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 1b5025ea5b04..86e1e37eb4e8 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -191,8 +191,13 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	hdr->type = cpu_to_le32(type);
 	hdr->src_node_id = cpu_to_le32(from->sq_node);
 	hdr->src_port_id = cpu_to_le32(from->sq_port);
-	hdr->dst_node_id = cpu_to_le32(to->sq_node);
-	hdr->dst_port_id = cpu_to_le32(to->sq_port);
+	if (to->sq_port == QRTR_PORT_CTRL) {
+		hdr->dst_node_id = cpu_to_le32(node->nid);
+		hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST);
+	} else {
+		hdr->dst_node_id = cpu_to_le32(to->sq_node);
+		hdr->dst_port_id = cpu_to_le32(to->sq_port);
+	}
 
 	hdr->size = cpu_to_le32(len);
 	hdr->confirm_rx = 0;
@@ -764,6 +769,10 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	node = NULL;
 	if (addr->sq_node == QRTR_NODE_BCAST) {
 		enqueue_fn = qrtr_bcast_enqueue;
+		if (addr->sq_port != QRTR_PORT_CTRL) {
+			release_sock(sk);
+			return -ENOTCONN;
+		}
 	} else if (addr->sq_node == ipc->us.sq_node) {
 		enqueue_fn = qrtr_local_enqueue;
 	} else {
@@ -1023,7 +1032,7 @@ static const struct proto_ops qrtr_proto_ops = {
 	.recvmsg	= qrtr_recvmsg,
 	.getname	= qrtr_getname,
 	.ioctl		= qrtr_ioctl,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
 	.getsockopt	= sock_no_getsockopt,
diff --git a/net/rds/connection.c b/net/rds/connection.c
index abef75da89a7..cfb05953b0e5 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -659,11 +659,19 @@ static void rds_conn_info(struct socket *sock, unsigned int len,
 
 int rds_conn_init(void)
 {
+	int ret;
+
+	ret = rds_loop_net_init(); /* register pernet callback */
+	if (ret)
+		return ret;
+
 	rds_conn_slab = kmem_cache_create("rds_connection",
 					  sizeof(struct rds_connection),
 					  0, 0, NULL);
-	if (!rds_conn_slab)
+	if (!rds_conn_slab) {
+		rds_loop_net_exit();
 		return -ENOMEM;
+	}
 
 	rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info);
 	rds_info_register_func(RDS_INFO_SEND_MESSAGES,
@@ -676,6 +684,7 @@ int rds_conn_init(void)
 
 void rds_conn_exit(void)
 {
+	rds_loop_net_exit(); /* unregister pernet callback */
 	rds_loop_exit();
 
 	WARN_ON(!hlist_empty(rds_conn_hash));
diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index 48332a6ed738..d152e48ea371 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -344,6 +344,11 @@ struct rds_ib_mr *rds_ib_reg_frmr(struct rds_ib_device *rds_ibdev,
 	struct rds_ib_frmr *frmr;
 	int ret;
 
+	if (!ic) {
+		/* TODO: Add FRWR support for RDS_GET_MR using proxy qp*/
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	do {
 		if (ibmr)
 			rds_ib_free_frmr(ibmr, true);
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 0ea4ab017a8c..655f01d427fe 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -115,7 +115,8 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
 			struct rds_info_rdma_connection *iinfo);
 void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *);
 void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
-		    struct rds_sock *rs, u32 *key_ret);
+		    struct rds_sock *rs, u32 *key_ret,
+		    struct rds_connection *conn);
 void rds_ib_sync_mr(void *trans_private, int dir);
 void rds_ib_free_mr(void *trans_private, int invalidate);
 void rds_ib_flush_mrs(void);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index e678699268a2..2e49a40a5e11 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -537,11 +537,12 @@ void rds_ib_flush_mrs(void)
 }
 
 void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
-		    struct rds_sock *rs, u32 *key_ret)
+		    struct rds_sock *rs, u32 *key_ret,
+		    struct rds_connection *conn)
 {
 	struct rds_ib_device *rds_ibdev;
 	struct rds_ib_mr *ibmr = NULL;
-	struct rds_ib_connection *ic = rs->rs_conn->c_transport_data;
+	struct rds_ib_connection *ic = NULL;
 	int ret;
 
 	rds_ibdev = rds_ib_get_device(rs->rs_bound_addr);
@@ -550,6 +551,9 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 		goto out;
 	}
 
+	if (conn)
+		ic = conn->c_transport_data;
+
 	if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) {
 		ret = -ENODEV;
 		goto out;
@@ -559,17 +563,18 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 		ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret);
 	else
 		ibmr = rds_ib_reg_fmr(rds_ibdev, sg, nents, key_ret);
-	if (ibmr)
-		rds_ibdev = NULL;
-
- out:
-	if (!ibmr)
+	if (IS_ERR(ibmr)) {
+		ret = PTR_ERR(ibmr);
 		pr_warn("RDS/IB: rds_ib_get_mr failed (errno=%d)\n", ret);
+	} else {
+		return ibmr;
+	}
 
+ out:
 	if (rds_ibdev)
 		rds_ib_dev_put(rds_ibdev);
 
-	return ibmr;
+	return ERR_PTR(ret);
 }
 
 void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool)
diff --git a/net/rds/loop.c b/net/rds/loop.c
index dac6218a460e..feea1f96ee2a 100644
--- a/net/rds/loop.c
+++ b/net/rds/loop.c
@@ -33,6 +33,8 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/in.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #include "rds_single_path.h"
 #include "rds.h"
@@ -40,6 +42,17 @@
 
 static DEFINE_SPINLOCK(loop_conns_lock);
 static LIST_HEAD(loop_conns);
+static atomic_t rds_loop_unloading = ATOMIC_INIT(0);
+
+static void rds_loop_set_unloading(void)
+{
+	atomic_set(&rds_loop_unloading, 1);
+}
+
+static bool rds_loop_is_unloading(struct rds_connection *conn)
+{
+	return atomic_read(&rds_loop_unloading) != 0;
+}
 
 /*
  * This 'loopback' transport is a special case for flows that originate
@@ -165,6 +178,8 @@ void rds_loop_exit(void)
 	struct rds_loop_connection *lc, *_lc;
 	LIST_HEAD(tmp_list);
 
+	rds_loop_set_unloading();
+	synchronize_rcu();
 	/* avoid calling conn_destroy with irqs off */
 	spin_lock_irq(&loop_conns_lock);
 	list_splice(&loop_conns, &tmp_list);
@@ -177,6 +192,46 @@ void rds_loop_exit(void)
 	}
 }
 
+static void rds_loop_kill_conns(struct net *net)
+{
+	struct rds_loop_connection *lc, *_lc;
+	LIST_HEAD(tmp_list);
+
+	spin_lock_irq(&loop_conns_lock);
+	list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node)  {
+		struct net *c_net = read_pnet(&lc->conn->c_net);
+
+		if (net != c_net)
+			continue;
+		list_move_tail(&lc->loop_node, &tmp_list);
+	}
+	spin_unlock_irq(&loop_conns_lock);
+
+	list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) {
+		WARN_ON(lc->conn->c_passive);
+		rds_conn_destroy(lc->conn);
+	}
+}
+
+static void __net_exit rds_loop_exit_net(struct net *net)
+{
+	rds_loop_kill_conns(net);
+}
+
+static struct pernet_operations rds_loop_net_ops = {
+	.exit = rds_loop_exit_net,
+};
+
+int rds_loop_net_init(void)
+{
+	return register_pernet_device(&rds_loop_net_ops);
+}
+
+void rds_loop_net_exit(void)
+{
+	unregister_pernet_device(&rds_loop_net_ops);
+}
+
 /*
  * This is missing .xmit_* because loop doesn't go through generic
  * rds_send_xmit() and doesn't call rds_recv_incoming().  .listen_stop and
@@ -194,4 +249,5 @@ struct rds_transport rds_loop_transport = {
 	.inc_free		= rds_loop_inc_free,
 	.t_name			= "loopback",
 	.t_type			= RDS_TRANS_LOOP,
+	.t_unloading		= rds_loop_is_unloading,
 };
diff --git a/net/rds/loop.h b/net/rds/loop.h
index 469fa4b2da4f..bbc8cdd030df 100644
--- a/net/rds/loop.h
+++ b/net/rds/loop.h
@@ -5,6 +5,8 @@
 /* loop.c */
 extern struct rds_transport rds_loop_transport;
 
+int rds_loop_net_init(void);
+void rds_loop_net_exit(void);
 void rds_loop_exit(void);
 
 #endif
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 634cfcb7bba6..80920e47f2c7 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -170,7 +170,8 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages,
 }
 
 static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
-				u64 *cookie_ret, struct rds_mr **mr_ret)
+			  u64 *cookie_ret, struct rds_mr **mr_ret,
+			  struct rds_conn_path *cp)
 {
 	struct rds_mr *mr = NULL, *found;
 	unsigned int nr_pages;
@@ -269,7 +270,8 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 	 * Note that dma_map() implies that pending writes are
 	 * flushed to RAM, so no dma_sync is needed here. */
 	trans_private = rs->rs_transport->get_mr(sg, nents, rs,
-						 &mr->r_key);
+						 &mr->r_key,
+						 cp ? cp->cp_conn : NULL);
 
 	if (IS_ERR(trans_private)) {
 		for (i = 0 ; i < nents; i++)
@@ -330,7 +332,7 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen)
 			   sizeof(struct rds_get_mr_args)))
 		return -EFAULT;
 
-	return __rds_rdma_map(rs, &args, NULL, NULL);
+	return __rds_rdma_map(rs, &args, NULL, NULL, NULL);
 }
 
 int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
@@ -354,7 +356,7 @@ int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
 	new_args.cookie_addr = args.cookie_addr;
 	new_args.flags = args.flags;
 
-	return __rds_rdma_map(rs, &new_args, NULL, NULL);
+	return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL);
 }
 
 /*
@@ -782,7 +784,8 @@ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm,
 	    rm->m_rdma_cookie != 0)
 		return -EINVAL;
 
-	return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr);
+	return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie,
+			      &rm->rdma.op_rdma_mr, rm->m_conn_path);
 }
 
 /*
diff --git a/net/rds/rds.h b/net/rds/rds.h
index f2272fb8cd45..60b3b787fbdb 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -464,6 +464,8 @@ struct rds_message {
 			struct scatterlist	*op_sg;
 		} data;
 	};
+
+	struct rds_conn_path *m_conn_path;
 };
 
 /*
@@ -544,7 +546,8 @@ struct rds_transport {
 					unsigned int avail);
 	void (*exit)(void);
 	void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg,
-			struct rds_sock *rs, u32 *key_ret);
+			struct rds_sock *rs, u32 *key_ret,
+			struct rds_connection *conn);
 	void (*sync_mr)(void *trans_private, int direction);
 	void (*free_mr)(void *trans_private, int invalidate);
 	void (*flush_mrs)(void);
diff --git a/net/rds/send.c b/net/rds/send.c
index 94c7f74909be..59f17a2335f4 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1169,6 +1169,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		rs->rs_conn = conn;
 	}
 
+	if (conn->c_trans->t_mp_capable)
+		cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)];
+	else
+		cpath = &conn->c_path[0];
+
+	rm->m_conn_path = cpath;
+
 	/* Parse any control messages the user may have included. */
 	ret = rds_cmsg_send(rs, rm, msg, &allocated_mr);
 	if (ret) {
@@ -1192,11 +1199,6 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		goto out;
 	}
 
-	if (conn->c_trans->t_mp_capable)
-		cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)];
-	else
-		cpath = &conn->c_path[0];
-
 	if (rds_destroy_pending(conn)) {
 		ret = -EAGAIN;
 		goto out;
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index a7a4e6ff9be2..1355f5ca8d22 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -141,13 +141,15 @@ static void rfkill_led_trigger_event(struct rfkill *rfkill)
 		led_trigger_event(trigger, LED_FULL);
 }
 
-static void rfkill_led_trigger_activate(struct led_classdev *led)
+static int rfkill_led_trigger_activate(struct led_classdev *led)
 {
 	struct rfkill *rfkill;
 
 	rfkill = container_of(led->trigger, struct rfkill, led_trigger);
 
 	rfkill_led_trigger_event(rfkill);
+
+	return 0;
 }
 
 const char *rfkill_get_led_trigger_name(struct rfkill *rfkill)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index ebe42e7eb456..d00a0ef39a56 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1470,7 +1470,7 @@ static const struct proto_ops rose_proto_ops = {
 	.socketpair	=	sock_no_socketpair,
 	.accept		=	rose_accept,
 	.getname	=	rose_getname,
-	.poll_mask	=	datagram_poll_mask,
+	.poll		=	datagram_poll,
 	.ioctl		=	rose_ioctl,
 	.listen		=	rose_listen,
 	.shutdown	=	sock_no_shutdown,
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 3b1ac93efee2..2b463047dd7b 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -734,11 +734,15 @@ static int rxrpc_getsockopt(struct socket *sock, int level, int optname,
 /*
  * permit an RxRPC socket to be polled
  */
-static __poll_t rxrpc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
+			       poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct rxrpc_sock *rx = rxrpc_sk(sk);
-	__poll_t mask = 0;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	/* the socket is readable if there are any messages waiting on the Rx
 	 * queue */
@@ -945,7 +949,7 @@ static const struct proto_ops rxrpc_rpc_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= sock_no_getname,
-	.poll_mask	= rxrpc_poll_mask,
+	.poll		= rxrpc_poll,
 	.ioctl		= sock_no_ioctl,
 	.listen		= rxrpc_listen,
 	.shutdown	= rxrpc_shutdown,
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5fb7d3254d9e..707630ab4713 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -104,9 +104,9 @@ struct rxrpc_net {
 
 #define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */
 	u8			peer_keepalive_cursor;
-	ktime_t			peer_keepalive_base;
-	struct hlist_head	peer_keepalive[RXRPC_KEEPALIVE_TIME + 1];
-	struct hlist_head	peer_keepalive_new;
+	time64_t		peer_keepalive_base;
+	struct list_head	peer_keepalive[32];
+	struct list_head	peer_keepalive_new;
 	struct timer_list	peer_keepalive_timer;
 	struct work_struct	peer_keepalive_work;
 };
@@ -295,7 +295,7 @@ struct rxrpc_peer {
 	struct hlist_head	error_targets;	/* targets for net error distribution */
 	struct work_struct	error_distributor;
 	struct rb_root		service_conns;	/* Service connections */
-	struct hlist_node	keepalive_link;	/* Link in net->peer_keepalive[] */
+	struct list_head	keepalive_link;	/* Link in net->peer_keepalive[] */
 	time64_t		last_tx_at;	/* Last time packet sent here */
 	seqlock_t		service_conn_lock;
 	spinlock_t		lock;		/* access lock */
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index a9a9be5519b9..9d1e298b784c 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -116,9 +116,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 		while (*pp) {
 			parent = *pp;
 			xcall = rb_entry(parent, struct rxrpc_call, sock_node);
-			if (user_call_ID < call->user_call_ID)
+			if (user_call_ID < xcall->user_call_ID)
 				pp = &(*pp)->rb_left;
-			else if (user_call_ID > call->user_call_ID)
+			else if (user_call_ID > xcall->user_call_ID)
 				pp = &(*pp)->rb_right;
 			else
 				goto id_in_use;
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index f6734d8cb01a..9486293fef5c 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -415,7 +415,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
 bool rxrpc_queue_call(struct rxrpc_call *call)
 {
 	const void *here = __builtin_return_address(0);
-	int n = __atomic_add_unless(&call->usage, 1, 0);
+	int n = atomic_fetch_add_unless(&call->usage, 1, 0);
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&call->processor))
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 8229a52c2acd..3fde001fcc39 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -136,7 +136,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 	}
 
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_final_resend);
@@ -245,7 +245,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 
 	_leave(" = 0");
 	return 0;
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 4c77a78a252a..77440a356b14 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -266,7 +266,7 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn)
 bool rxrpc_queue_conn(struct rxrpc_connection *conn)
 {
 	const void *here = __builtin_return_address(0);
-	int n = __atomic_add_unless(&conn->usage, 1, 0);
+	int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&conn->processor))
@@ -309,7 +309,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn)
 	const void *here = __builtin_return_address(0);
 
 	if (conn) {
-		int n = __atomic_add_unless(&conn->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here);
 		else
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index b493e6b62740..777c3ed4cfc0 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -305,7 +305,7 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
 	const void *here = __builtin_return_address(0);
 
 	if (local) {
-		int n = __atomic_add_unless(&local->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&local->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_local(local, rxrpc_local_got, n + 1, here);
 		else
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index 5d6a773db973..417d80867c4f 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -85,12 +85,12 @@ static __net_init int rxrpc_init_net(struct net *net)
 	hash_init(rxnet->peer_hash);
 	spin_lock_init(&rxnet->peer_hash_lock);
 	for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++)
-		INIT_HLIST_HEAD(&rxnet->peer_keepalive[i]);
-	INIT_HLIST_HEAD(&rxnet->peer_keepalive_new);
+		INIT_LIST_HEAD(&rxnet->peer_keepalive[i]);
+	INIT_LIST_HEAD(&rxnet->peer_keepalive_new);
 	timer_setup(&rxnet->peer_keepalive_timer,
 		    rxrpc_peer_keepalive_timeout, 0);
 	INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker);
-	rxnet->peer_keepalive_base = ktime_add(ktime_get_real(), NSEC_PER_SEC);
+	rxnet->peer_keepalive_base = ktime_get_seconds();
 
 	ret = -ENOMEM;
 	rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index f03de1c59ba3..4774c8f5634d 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -209,7 +209,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	now = ktime_get_real();
 	if (ping)
 		call->ping_time = now;
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_ack);
@@ -296,7 +296,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 
 	ret = kernel_sendmsg(conn->params.local->socket,
 			     &msg, iov, 1, sizeof(pkt));
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_abort);
@@ -391,7 +391,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	 *     message and update the peer record
 	 */
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 
 	up_read(&conn->params.local->defrag_sem);
 	if (ret < 0)
@@ -457,7 +457,7 @@ send_fragmentable:
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
 					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_real();
+			conn->params.peer->last_tx_at = ktime_get_seconds();
 
 			opt = IP_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket, SOL_IP,
@@ -475,7 +475,7 @@ send_fragmentable:
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
 					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_real();
+			conn->params.peer->last_tx_at = ktime_get_seconds();
 
 			opt = IPV6_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket,
@@ -599,6 +599,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer)
 		trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
 				    rxrpc_tx_fail_version_keepalive);
 
-	peer->last_tx_at = ktime_get_real();
+	peer->last_tx_at = ktime_get_seconds();
 	_leave("");
 }
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 0ed8b651cec2..4f9da2f51c69 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -350,97 +350,117 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
 }
 
 /*
- * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ * Perform keep-alive pings.
  */
-void rxrpc_peer_keepalive_worker(struct work_struct *work)
+static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
+					  struct list_head *collector,
+					  time64_t base,
+					  u8 cursor)
 {
-	struct rxrpc_net *rxnet =
-		container_of(work, struct rxrpc_net, peer_keepalive_work);
 	struct rxrpc_peer *peer;
-	unsigned long delay;
-	ktime_t base, now = ktime_get_real();
-	s64 diff;
-	u8 cursor, slot;
+	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+	time64_t keepalive_at;
+	int slot;
 
-	base = rxnet->peer_keepalive_base;
-	cursor = rxnet->peer_keepalive_cursor;
+	spin_lock_bh(&rxnet->peer_hash_lock);
 
-	_enter("%u,%lld", cursor, ktime_sub(now, base));
+	while (!list_empty(collector)) {
+		peer = list_entry(collector->next,
+				  struct rxrpc_peer, keepalive_link);
 
-next_bucket:
-	diff = ktime_to_ns(ktime_sub(now, base));
-	if (diff < 0)
-		goto resched;
+		list_del_init(&peer->keepalive_link);
+		if (!rxrpc_get_peer_maybe(peer))
+			continue;
 
-	_debug("at %u", cursor);
-	spin_lock_bh(&rxnet->peer_hash_lock);
-next_peer:
-	if (!rxnet->live) {
 		spin_unlock_bh(&rxnet->peer_hash_lock);
-		goto out;
-	}
 
-	/* Everything in the bucket at the cursor is processed this second; the
-	 * bucket at cursor + 1 goes now + 1s and so on...
-	 */
-	if (hlist_empty(&rxnet->peer_keepalive[cursor])) {
-		if (hlist_empty(&rxnet->peer_keepalive_new)) {
-			spin_unlock_bh(&rxnet->peer_hash_lock);
-			goto emptied_bucket;
+		keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+		slot = keepalive_at - base;
+		_debug("%02x peer %u t=%d {%pISp}",
+		       cursor, peer->debug_id, slot, &peer->srx.transport);
+
+		if (keepalive_at <= base ||
+		    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+			rxrpc_send_keepalive(peer);
+			slot = RXRPC_KEEPALIVE_TIME;
 		}
 
-		hlist_move_list(&rxnet->peer_keepalive_new,
-				&rxnet->peer_keepalive[cursor]);
+		/* A transmission to this peer occurred since last we examined
+		 * it so put it into the appropriate future bucket.
+		 */
+		slot += cursor;
+		slot &= mask;
+		spin_lock_bh(&rxnet->peer_hash_lock);
+		list_add_tail(&peer->keepalive_link,
+			      &rxnet->peer_keepalive[slot & mask]);
+		rxrpc_put_peer(peer);
 	}
 
-	peer = hlist_entry(rxnet->peer_keepalive[cursor].first,
-			   struct rxrpc_peer, keepalive_link);
-	hlist_del_init(&peer->keepalive_link);
-	if (!rxrpc_get_peer_maybe(peer))
-		goto next_peer;
-
 	spin_unlock_bh(&rxnet->peer_hash_lock);
+}
 
-	_debug("peer %u {%pISp}", peer->debug_id, &peer->srx.transport);
+/*
+ * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ */
+void rxrpc_peer_keepalive_worker(struct work_struct *work)
+{
+	struct rxrpc_net *rxnet =
+		container_of(work, struct rxrpc_net, peer_keepalive_work);
+	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+	time64_t base, now, delay;
+	u8 cursor, stop;
+	LIST_HEAD(collector);
 
-recalc:
-	diff = ktime_divns(ktime_sub(peer->last_tx_at, base), NSEC_PER_SEC);
-	if (diff < -30 || diff > 30)
-		goto send; /* LSW of 64-bit time probably wrapped on 32-bit */
-	diff += RXRPC_KEEPALIVE_TIME - 1;
-	if (diff < 0)
-		goto send;
+	now = ktime_get_seconds();
+	base = rxnet->peer_keepalive_base;
+	cursor = rxnet->peer_keepalive_cursor;
+	_enter("%lld,%u", base - now, cursor);
 
-	slot = (diff > RXRPC_KEEPALIVE_TIME - 1) ? RXRPC_KEEPALIVE_TIME - 1 : diff;
-	if (slot == 0)
-		goto send;
+	if (!rxnet->live)
+		return;
 
-	/* A transmission to this peer occurred since last we examined it so
-	 * put it into the appropriate future bucket.
+	/* Remove to a temporary list all the peers that are currently lodged
+	 * in expired buckets plus all new peers.
+	 *
+	 * Everything in the bucket at the cursor is processed this
+	 * second; the bucket at cursor + 1 goes at now + 1s and so
+	 * on...
 	 */
-	slot = (slot + cursor) % ARRAY_SIZE(rxnet->peer_keepalive);
 	spin_lock_bh(&rxnet->peer_hash_lock);
-	hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive[slot]);
-	rxrpc_put_peer(peer);
-	goto next_peer;
-
-send:
-	rxrpc_send_keepalive(peer);
-	now = ktime_get_real();
-	goto recalc;
+	list_splice_init(&rxnet->peer_keepalive_new, &collector);
+
+	stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive);
+	while (base <= now && (s8)(cursor - stop) < 0) {
+		list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask],
+				      &collector);
+		base++;
+		cursor++;
+	}
 
-emptied_bucket:
-	cursor++;
-	if (cursor >= ARRAY_SIZE(rxnet->peer_keepalive))
-		cursor = 0;
-	base = ktime_add_ns(base, NSEC_PER_SEC);
-	goto next_bucket;
+	base = now;
+	spin_unlock_bh(&rxnet->peer_hash_lock);
 
-resched:
 	rxnet->peer_keepalive_base = base;
 	rxnet->peer_keepalive_cursor = cursor;
-	delay = nsecs_to_jiffies(-diff) + 1;
-	timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
-out:
+	rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor);
+	ASSERT(list_empty(&collector));
+
+	/* Schedule the timer for the next occupied timeslot. */
+	cursor = rxnet->peer_keepalive_cursor;
+	stop = cursor + RXRPC_KEEPALIVE_TIME - 1;
+	for (; (s8)(cursor - stop) < 0; cursor++) {
+		if (!list_empty(&rxnet->peer_keepalive[cursor & mask]))
+			break;
+		base++;
+	}
+
+	now = ktime_get_seconds();
+	delay = base - now;
+	if (delay < 1)
+		delay = 1;
+	delay *= HZ;
+	if (rxnet->live)
+		timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
+
 	_leave("");
 }
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 1b7e8107b3ae..1dc7648e3eff 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -322,7 +322,7 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local,
 	if (!peer) {
 		peer = prealloc;
 		hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
-		hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive_new);
+		list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
 	}
 
 	spin_unlock(&rxnet->peer_hash_lock);
@@ -367,8 +367,8 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
 		if (!peer) {
 			hash_add_rcu(rxnet->peer_hash,
 				     &candidate->hash_link, hash_key);
-			hlist_add_head(&candidate->keepalive_link,
-				       &rxnet->peer_keepalive_new);
+			list_add_tail(&candidate->keepalive_link,
+				      &rxnet->peer_keepalive_new);
 		}
 
 		spin_unlock_bh(&rxnet->peer_hash_lock);
@@ -406,7 +406,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
 	const void *here = __builtin_return_address(0);
 
 	if (peer) {
-		int n = __atomic_add_unless(&peer->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&peer->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here);
 		else
@@ -441,7 +441,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
 
 	spin_lock_bh(&rxnet->peer_hash_lock);
 	hash_del_rcu(&peer->hash_link);
-	hlist_del_init(&peer->keepalive_link);
+	list_del_init(&peer->keepalive_link);
 	spin_unlock_bh(&rxnet->peer_hash_lock);
 
 	kfree_rcu(peer, rcu);
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 278ac0807a60..47cb019c521a 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -669,7 +669,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	_leave(" = 0");
 	return 0;
 }
@@ -725,7 +725,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	_leave(" = 0");
 	return 0;
 }
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 526a8e491626..6e7124e57918 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -91,7 +91,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	}
 	params_old = rtnl_dereference(p->params);
 
-	params_new->action = parm->action;
+	p->tcf_action = parm->action;
 	params_new->update_flags = parm->update_flags;
 	rcu_assign_pointer(p->params, params_new);
 	if (params_old)
@@ -561,7 +561,7 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&p->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb);
 
-	action = params->action;
+	action = READ_ONCE(p->tcf_action);
 	if (unlikely(action == TC_ACT_SHOT))
 		goto drop_stats;
 
@@ -599,11 +599,11 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 		.index   = p->tcf_index,
 		.refcnt  = p->tcf_refcnt - ref,
 		.bindcnt = p->tcf_bindcnt - bind,
+		.action  = p->tcf_action,
 	};
 	struct tcf_t t;
 
 	params = rtnl_dereference(p->params);
-	opt.action = params->action;
 	opt.update_flags = params->update_flags;
 
 	if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt))
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 626dac81a48a..9bc6c2ae98a5 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -36,7 +36,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
 
 	tcf_lastuse_update(&t->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb);
-	action = params->action;
+	action = READ_ONCE(t->tcf_action);
 
 	switch (params->tcft_action) {
 	case TCA_TUNNEL_KEY_ACT_RELEASE:
@@ -182,7 +182,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 
 	params_old = rtnl_dereference(t->params);
 
-	params_new->action = parm->action;
+	t->tcf_action = parm->action;
 	params_new->tcft_action = parm->t_action;
 	params_new->tcft_enc_metadata = metadata;
 
@@ -254,13 +254,13 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 		.index    = t->tcf_index,
 		.refcnt   = t->tcf_refcnt - ref,
 		.bindcnt  = t->tcf_bindcnt - bind,
+		.action   = t->tcf_action,
 	};
 	struct tcf_t tm;
 
 	params = rtnl_dereference(t->params);
 
 	opt.t_action = params->tcft_action;
-	opt.action = params->action;
 
 	if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index cdc3c87c53e6..f74513a7c7a8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1053,7 +1053,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
 	for (tp = rtnl_dereference(chain->filter_chain);
 	     tp; tp = rtnl_dereference(tp->next))
 		tfilter_notify(net, oskb, n, tp, block,
-			       q, parent, 0, event, false);
+			       q, parent, NULL, event, false);
 }
 
 static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
@@ -1444,7 +1444,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
 			memset(&cb->args[1], 0,
 			       sizeof(cb->args) - sizeof(cb->args[0]));
 		if (cb->args[1] == 0) {
-			if (tcf_fill_node(net, skb, tp, block, q, parent, 0,
+			if (tcf_fill_node(net, skb, tp, block, q, parent, NULL,
 					  NETLINK_CB(cb->skb).portid,
 					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					  RTM_NEWTFILTER) <= 0)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 2b5be42a9f1c..9e8b26a80fb3 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -66,7 +66,7 @@ struct fl_flow_mask {
 	struct rhashtable_params filter_ht_params;
 	struct flow_dissector dissector;
 	struct list_head filters;
-	struct rcu_head rcu;
+	struct rcu_work rwork;
 	struct list_head list;
 };
 
@@ -203,6 +203,20 @@ static int fl_init(struct tcf_proto *tp)
 	return rhashtable_init(&head->ht, &mask_ht_params);
 }
 
+static void fl_mask_free(struct fl_flow_mask *mask)
+{
+	rhashtable_destroy(&mask->ht);
+	kfree(mask);
+}
+
+static void fl_mask_free_work(struct work_struct *work)
+{
+	struct fl_flow_mask *mask = container_of(to_rcu_work(work),
+						 struct fl_flow_mask, rwork);
+
+	fl_mask_free(mask);
+}
+
 static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask,
 			bool async)
 {
@@ -210,12 +224,11 @@ static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask,
 		return false;
 
 	rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params);
-	rhashtable_destroy(&mask->ht);
 	list_del_rcu(&mask->list);
 	if (async)
-		kfree_rcu(mask, rcu);
+		tcf_queue_work(&mask->rwork, fl_mask_free_work);
 	else
-		kfree(mask);
+		fl_mask_free(mask);
 
 	return true;
 }
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index cd2e0e342fb6..6c0a9d5dbf94 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -479,24 +479,28 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt,
 	q->cparams.mtu = psched_mtu(qdisc_dev(sch));
 
 	if (opt) {
-		int err = fq_codel_change(sch, opt, extack);
+		err = fq_codel_change(sch, opt, extack);
 		if (err)
-			return err;
+			goto init_failure;
 	}
 
 	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
 	if (err)
-		return err;
+		goto init_failure;
 
 	if (!q->flows) {
 		q->flows = kvcalloc(q->flows_cnt,
 				    sizeof(struct fq_codel_flow),
 				    GFP_KERNEL);
-		if (!q->flows)
-			return -ENOMEM;
+		if (!q->flows) {
+			err = -ENOMEM;
+			goto init_failure;
+		}
 		q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL);
-		if (!q->backlogs)
-			return -ENOMEM;
+		if (!q->backlogs) {
+			err = -ENOMEM;
+			goto alloc_failure;
+		}
 		for (i = 0; i < q->flows_cnt; i++) {
 			struct fq_codel_flow *flow = q->flows + i;
 
@@ -509,6 +513,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt,
 	else
 		sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
+
+alloc_failure:
+	kvfree(q->flows);
+	q->flows = NULL;
+init_failure:
+	q->flows_cnt = 0;
+	return err;
 }
 
 static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 3ae9877ea205..3278a76f6861 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1385,8 +1385,8 @@ hfsc_schedule_watchdog(struct Qdisc *sch)
 		if (next_time == 0 || next_time > q->root.cl_cfmin)
 			next_time = q->root.cl_cfmin;
 	}
-	WARN_ON(next_time == 0);
-	qdisc_watchdog_schedule(&q->watchdog, next_time);
+	if (next_time)
+		qdisc_watchdog_schedule(&q->watchdog, next_time);
 }
 
 static int
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 79daa98208c3..bfb9f812e2ef 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -237,7 +237,9 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 	/* Account for a different sized first fragment */
 	if (msg_len >= first_len) {
 		msg->can_delay = 0;
-		SCTP_INC_STATS(sock_net(asoc->base.sk), SCTP_MIB_FRAGUSRMSGS);
+		if (msg_len > first_len)
+			SCTP_INC_STATS(sock_net(asoc->base.sk),
+				       SCTP_MIB_FRAGUSRMSGS);
 	} else {
 		/* Which may be the only one... */
 		first_len = msg_len;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 7339918a805d..0cd2e764f47f 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -1010,7 +1010,7 @@ static const struct proto_ops inet6_seqpacket_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = sctp_getname,
-	.poll_mask	   = sctp_poll_mask,
+	.poll		   = sctp_poll,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 5dffbc493008..67f73d3a1356 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1016,7 +1016,7 @@ static const struct proto_ops inet_seqpacket_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,	/* Semantics are different.  */
-	.poll_mask	   = sctp_poll_mask,
+	.poll		   = sctp_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,	/* Looks harmless.  */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d20f7addee19..ce620e878538 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7717,12 +7717,14 @@ out:
  * here, again, by modeling the current TCP/UDP code.  We don't have
  * a good way to test with it yet.
  */
-__poll_t sctp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct sctp_sock *sp = sctp_sk(sk);
 	__poll_t mask;
 
+	poll_wait(file, sk_sleep(sk), wait);
+
 	sock_rps_record_flow(sk);
 
 	/* A TCP-style listening socket becomes readable when the accept queue
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 445b7ef61677..12cac85da994 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -282,7 +282,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 
 	if (dst) {
 		/* Re-fetch, as under layers may have a higher minimum size */
-		pmtu = SCTP_TRUNC4(dst_mtu(dst));
+		pmtu = sctp_dst_mtu(dst);
 		change = t->pathmtu != pmtu;
 	}
 	t->pathmtu = pmtu;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index da7f02edcd37..e7de5f282722 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -45,6 +45,7 @@ static DEFINE_MUTEX(smc_create_lgr_pending);	/* serialize link group
 						 */
 
 static void smc_tcp_listen_work(struct work_struct *);
+static void smc_connect_work(struct work_struct *);
 
 static void smc_set_keepalive(struct sock *sk, int val)
 {
@@ -122,6 +123,12 @@ static int smc_release(struct socket *sock)
 		goto out;
 
 	smc = smc_sk(sk);
+
+	/* cleanup for a dangling non-blocking connect */
+	flush_work(&smc->connect_work);
+	kfree(smc->connect_info);
+	smc->connect_info = NULL;
+
 	if (sk->sk_state == SMC_LISTEN)
 		/* smc_close_non_accepted() is called and acquires
 		 * sock lock for child sockets again
@@ -140,7 +147,8 @@ static int smc_release(struct socket *sock)
 		smc->clcsock = NULL;
 	}
 	if (smc->use_fallback) {
-		sock_put(sk); /* passive closing */
+		if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
+			sock_put(sk); /* passive closing */
 		sk->sk_state = SMC_CLOSED;
 		sk->sk_state_change(sk);
 	}
@@ -186,6 +194,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
 	sk->sk_protocol = protocol;
 	smc = smc_sk(sk);
 	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+	INIT_WORK(&smc->connect_work, smc_connect_work);
 	INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
 	INIT_LIST_HEAD(&smc->accept_q);
 	spin_lock_init(&smc->accept_q_lock);
@@ -409,12 +418,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 {
 	int rc;
 
-	if (reason_code < 0) /* error, fallback is not possible */
+	if (reason_code < 0) { /* error, fallback is not possible */
+		if (smc->sk.sk_state == SMC_INIT)
+			sock_put(&smc->sk); /* passive closing */
 		return reason_code;
+	}
 	if (reason_code != SMC_CLC_DECL_REPLY) {
 		rc = smc_clc_send_decline(smc, reason_code);
-		if (rc < 0)
+		if (rc < 0) {
+			if (smc->sk.sk_state == SMC_INIT)
+				sock_put(&smc->sk); /* passive closing */
 			return rc;
+		}
 	}
 	return smc_connect_fallback(smc);
 }
@@ -427,8 +442,6 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code,
 		smc_lgr_forget(smc->conn.lgr);
 	mutex_unlock(&smc_create_lgr_pending);
 	smc_conn_free(&smc->conn);
-	if (reason_code < 0 && smc->sk.sk_state == SMC_INIT)
-		sock_put(&smc->sk); /* passive closing */
 	return reason_code;
 }
 
@@ -576,6 +589,35 @@ static int __smc_connect(struct smc_sock *smc)
 	return 0;
 }
 
+static void smc_connect_work(struct work_struct *work)
+{
+	struct smc_sock *smc = container_of(work, struct smc_sock,
+					    connect_work);
+	int rc;
+
+	lock_sock(&smc->sk);
+	rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
+			    smc->connect_info->alen, smc->connect_info->flags);
+	if (smc->clcsock->sk->sk_err) {
+		smc->sk.sk_err = smc->clcsock->sk->sk_err;
+		goto out;
+	}
+	if (rc < 0) {
+		smc->sk.sk_err = -rc;
+		goto out;
+	}
+
+	rc = __smc_connect(smc);
+	if (rc < 0)
+		smc->sk.sk_err = -rc;
+
+out:
+	smc->sk.sk_state_change(&smc->sk);
+	kfree(smc->connect_info);
+	smc->connect_info = NULL;
+	release_sock(&smc->sk);
+}
+
 static int smc_connect(struct socket *sock, struct sockaddr *addr,
 		       int alen, int flags)
 {
@@ -605,15 +647,32 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
 
 	smc_copy_sock_settings_to_clc(smc);
 	tcp_sk(smc->clcsock->sk)->syn_smc = 1;
-	rc = kernel_connect(smc->clcsock, addr, alen, flags);
-	if (rc)
-		goto out;
+	if (flags & O_NONBLOCK) {
+		if (smc->connect_info) {
+			rc = -EALREADY;
+			goto out;
+		}
+		smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
+		if (!smc->connect_info) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		smc->connect_info->alen = alen;
+		smc->connect_info->flags = flags ^ O_NONBLOCK;
+		memcpy(&smc->connect_info->addr, addr, alen);
+		schedule_work(&smc->connect_work);
+		rc = -EINPROGRESS;
+	} else {
+		rc = kernel_connect(smc->clcsock, addr, alen, flags);
+		if (rc)
+			goto out;
 
-	rc = __smc_connect(smc);
-	if (rc < 0)
-		goto out;
-	else
-		rc = 0; /* success cases including fallback */
+		rc = __smc_connect(smc);
+		if (rc < 0)
+			goto out;
+		else
+			rc = 0; /* success cases including fallback */
+	}
 
 out:
 	release_sock(sk);
@@ -1063,6 +1122,8 @@ static void smc_tcp_listen_work(struct work_struct *work)
 		sock_hold(lsk); /* sock_put in smc_listen_work */
 		INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
 		smc_copy_sock_settings_to_smc(new_smc);
+		new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf;
+		new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf;
 		sock_hold(&new_smc->sk); /* sock_put in passive closing */
 		if (!schedule_work(&new_smc->smc_listen_work))
 			sock_put(&new_smc->sk);
@@ -1273,40 +1334,26 @@ static __poll_t smc_accept_poll(struct sock *parent)
 	return mask;
 }
 
-static __poll_t smc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t smc_poll(struct file *file, struct socket *sock,
+			     poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 	struct smc_sock *smc;
-	int rc;
 
 	if (!sk)
 		return EPOLLNVAL;
 
 	smc = smc_sk(sock->sk);
-	sock_hold(sk);
-	lock_sock(sk);
 	if ((sk->sk_state == SMC_INIT) || smc->use_fallback) {
 		/* delegate to CLC child sock */
-		release_sock(sk);
-		mask = smc->clcsock->ops->poll_mask(smc->clcsock, events);
-		lock_sock(sk);
+		mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
 		sk->sk_err = smc->clcsock->sk->sk_err;
-		if (sk->sk_err) {
+		if (sk->sk_err)
 			mask |= EPOLLERR;
-		} else {
-			/* if non-blocking connect finished ... */
-			if (sk->sk_state == SMC_INIT &&
-			    mask & EPOLLOUT &&
-			    smc->clcsock->sk->sk_state != TCP_CLOSE) {
-				rc = __smc_connect(smc);
-				if (rc < 0)
-					mask |= EPOLLERR;
-				/* success cases including fallback */
-				mask |= EPOLLOUT | EPOLLWRNORM;
-			}
-		}
 	} else {
+		if (sk->sk_state != SMC_CLOSED)
+			sock_poll_wait(file, sk_sleep(sk), wait);
 		if (sk->sk_err)
 			mask |= EPOLLERR;
 		if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
@@ -1332,10 +1379,7 @@ static __poll_t smc_poll_mask(struct socket *sock, __poll_t events)
 		}
 		if (smc->conn.urg_state == SMC_URG_VALID)
 			mask |= EPOLLPRI;
-
 	}
-	release_sock(sk);
-	sock_put(sk);
 
 	return mask;
 }
@@ -1355,8 +1399,7 @@ static int smc_shutdown(struct socket *sock, int how)
 	lock_sock(sk);
 
 	rc = -ENOTCONN;
-	if ((sk->sk_state != SMC_LISTEN) &&
-	    (sk->sk_state != SMC_ACTIVE) &&
+	if ((sk->sk_state != SMC_ACTIVE) &&
 	    (sk->sk_state != SMC_PEERCLOSEWAIT1) &&
 	    (sk->sk_state != SMC_PEERCLOSEWAIT2) &&
 	    (sk->sk_state != SMC_APPCLOSEWAIT1) &&
@@ -1415,7 +1458,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
-	get_user(val, (int __user *)optval);
+	if (get_user(val, (int __user *)optval))
+		return -EFAULT;
 
 	lock_sock(sk);
 	switch (optname) {
@@ -1478,15 +1522,22 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 
 	smc = smc_sk(sock->sk);
 	conn = &smc->conn;
+	lock_sock(&smc->sk);
 	if (smc->use_fallback) {
-		if (!smc->clcsock)
+		if (!smc->clcsock) {
+			release_sock(&smc->sk);
 			return -EBADF;
-		return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+		}
+		answ = smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+		release_sock(&smc->sk);
+		return answ;
 	}
 	switch (cmd) {
 	case SIOCINQ: /* same as FIONREAD */
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED)
 			answ = 0;
@@ -1495,8 +1546,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		break;
 	case SIOCOUTQ:
 		/* output queue size (not send + not acked) */
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED)
 			answ = 0;
@@ -1506,8 +1559,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		break;
 	case SIOCOUTQNSD:
 		/* output queue size (not send only) */
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED)
 			answ = 0;
@@ -1515,8 +1570,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 			answ = smc_tx_prepared_sends(&smc->conn);
 		break;
 	case SIOCATMARK:
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED) {
 			answ = 0;
@@ -1532,8 +1589,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		}
 		break;
 	default:
+		release_sock(&smc->sk);
 		return -ENOIOCTLCMD;
 	}
+	release_sock(&smc->sk);
 
 	return put_user(answ, (int __user *)arg);
 }
@@ -1619,7 +1678,7 @@ static const struct proto_ops smc_sock_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= smc_accept,
 	.getname	= smc_getname,
-	.poll_mask	= smc_poll_mask,
+	.poll		= smc_poll,
 	.ioctl		= smc_ioctl,
 	.listen		= smc_listen,
 	.shutdown	= smc_shutdown,
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 51ae1f10d81a..d7ca26570482 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -187,11 +187,19 @@ struct smc_connection {
 	struct work_struct	close_work;	/* peer sent some closing */
 };
 
+struct smc_connect_info {
+	int			flags;
+	int			alen;
+	struct sockaddr		addr;
+};
+
 struct smc_sock {				/* smc sock container */
 	struct sock		sk;
 	struct socket		*clcsock;	/* internal tcp socket */
 	struct smc_connection	conn;		/* smc connection */
 	struct smc_sock		*listen_smc;	/* listen parent */
+	struct smc_connect_info *connect_info;	/* connect address & flags */
+	struct work_struct	connect_work;	/* handle non-blocking connect*/
 	struct work_struct	tcp_listen_work;/* handle tcp socket accepts */
 	struct work_struct	smc_listen_work;/* prepare new accept socket */
 	struct list_head	accept_q;	/* sockets to be accepted */
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index a7e8d63fc8ae..9bde1e4ca288 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -233,7 +233,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 			/* force immediate tx of current consumer cursor, but
 			 * under send_lock to guarantee arrival in seqno-order
 			 */
-			smc_tx_sndbuf_nonempty(conn);
+			if (smc->sk.sk_state != SMC_INIT)
+				smc_tx_sndbuf_nonempty(conn);
 		}
 	}
 
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 717449b1da0b..ae5d168653ce 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -250,6 +250,7 @@ out:
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type)
 {
+	long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo;
 	struct sock *clc_sk = smc->clcsock->sk;
 	struct smc_clc_msg_hdr *clcm = buf;
 	struct msghdr msg = {NULL, 0};
@@ -306,7 +307,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	memset(&msg, 0, sizeof(struct msghdr));
 	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
 	krflags = MSG_WAITALL;
-	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
 	len = sock_recvmsg(smc->clcsock, &msg, krflags);
 	if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
 		smc->sk.sk_err = EPROTO;
@@ -322,6 +322,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	}
 
 out:
+	smc->clcsock->sk->sk_rcvtimeo = rcvtimeo;
 	return reason_code;
 }
 
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index fa41d9881741..ac961dfb1ea1 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -107,6 +107,8 @@ static void smc_close_active_abort(struct smc_sock *smc)
 	}
 	switch (sk->sk_state) {
 	case SMC_INIT:
+		sk->sk_state = SMC_PEERABORTWAIT;
+		break;
 	case SMC_ACTIVE:
 		sk->sk_state = SMC_PEERABORTWAIT;
 		release_sock(sk);
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index cee666400752..f82886b7d1d8 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -495,7 +495,8 @@ out:
 
 void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 {
-	union smc_host_cursor cfed, cons;
+	union smc_host_cursor cfed, cons, prod;
+	int sender_free = conn->rmb_desc->len;
 	int to_confirm;
 
 	smc_curs_write(&cons,
@@ -505,11 +506,18 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 		       smc_curs_read(&conn->rx_curs_confirmed, conn),
 		       conn);
 	to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
+	if (to_confirm > conn->rmbe_update_limit) {
+		smc_curs_write(&prod,
+			       smc_curs_read(&conn->local_rx_ctrl.prod, conn),
+			       conn);
+		sender_free = conn->rmb_desc->len -
+			      smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
+	}
 
 	if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
 	    force ||
 	    ((to_confirm > conn->rmbe_update_limit) &&
-	     ((to_confirm > (conn->rmb_desc->len / 2)) ||
+	     ((sender_free <= (conn->rmb_desc->len / 2)) ||
 	      conn->local_rx_ctrl.prod_flags.write_blocked))) {
 		if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
 		    conn->alert_token_local) { /* connection healthy */
diff --git a/net/socket.c b/net/socket.c
index 8a109012608a..792f0313ea91 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -89,6 +89,7 @@
 #include <linux/magic.h>
 #include <linux/slab.h>
 #include <linux/xattr.h>
+#include <linux/nospec.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -117,10 +118,8 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from);
 static int sock_mmap(struct file *file, struct vm_area_struct *vma);
 
 static int sock_close(struct inode *inode, struct file *file);
-static struct wait_queue_head *sock_get_poll_head(struct file *file,
-		__poll_t events);
-static __poll_t sock_poll_mask(struct file *file, __poll_t);
-static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait);
+static __poll_t sock_poll(struct file *file,
+			      struct poll_table_struct *wait);
 static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 #ifdef CONFIG_COMPAT
 static long compat_sock_ioctl(struct file *file,
@@ -143,8 +142,6 @@ static const struct file_operations socket_file_ops = {
 	.llseek =	no_llseek,
 	.read_iter =	sock_read_iter,
 	.write_iter =	sock_write_iter,
-	.get_poll_head = sock_get_poll_head,
-	.poll_mask =	sock_poll_mask,
 	.poll =		sock_poll,
 	.unlocked_ioctl = sock_ioctl,
 #ifdef CONFIG_COMPAT
@@ -391,39 +388,20 @@ static struct file_system_type sock_fs_type = {
 
 struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 {
-	struct qstr name = { .name = "" };
-	struct path path;
 	struct file *file;
 
-	if (dname) {
-		name.name = dname;
-		name.len = strlen(name.name);
-	} else if (sock->sk) {
-		name.name = sock->sk->sk_prot_creator->name;
-		name.len = strlen(name.name);
-	}
-	path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
-	if (unlikely(!path.dentry)) {
-		sock_release(sock);
-		return ERR_PTR(-ENOMEM);
-	}
-	path.mnt = mntget(sock_mnt);
+	if (!dname)
+		dname = sock->sk ? sock->sk->sk_prot_creator->name : "";
 
-	d_instantiate(path.dentry, SOCK_INODE(sock));
-
-	file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
-		  &socket_file_ops);
+	file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname,
+				O_RDWR | (flags & O_NONBLOCK),
+				&socket_file_ops);
 	if (IS_ERR(file)) {
-		/* drop dentry, keep inode for a bit */
-		ihold(d_inode(path.dentry));
-		path_put(&path);
-		/* ... and now kill it properly */
 		sock_release(sock);
 		return file;
 	}
 
 	sock->file = file;
-	file->f_flags = O_RDWR | (flags & O_NONBLOCK);
 	file->private_data = sock;
 	return file;
 }
@@ -1130,48 +1108,16 @@ out_release:
 }
 EXPORT_SYMBOL(sock_create_lite);
 
-static struct wait_queue_head *sock_get_poll_head(struct file *file,
-		__poll_t events)
-{
-	struct socket *sock = file->private_data;
-
-	if (!sock->ops->poll_mask)
-		return NULL;
-	sock_poll_busy_loop(sock, events);
-	return sk_sleep(sock->sk);
-}
-
-static __poll_t sock_poll_mask(struct file *file, __poll_t events)
-{
-	struct socket *sock = file->private_data;
-
-	/*
-	 * We need to be sure we are in sync with the socket flags modification.
-	 *
-	 * This memory barrier is paired in the wq_has_sleeper.
-	 */
-	smp_mb();
-
-	/* this socket can poll_ll so tell the system call */
-	return sock->ops->poll_mask(sock, events) |
-		(sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0);
-}
-
 /* No kernel lock held - perfect */
 static __poll_t sock_poll(struct file *file, poll_table *wait)
 {
 	struct socket *sock = file->private_data;
-	__poll_t events = poll_requested_events(wait), mask = 0;
-
-	if (sock->ops->poll) {
-		sock_poll_busy_loop(sock, events);
-		mask = sock->ops->poll(file, sock, wait);
-	} else if (sock->ops->poll_mask) {
-		sock_poll_wait(file, sock_get_poll_head(file, events), wait);
-		mask = sock->ops->poll_mask(sock, events);
-	}
+	__poll_t events = poll_requested_events(wait);
 
-	return mask | sock_poll_busy_flag(sock);
+	sock_poll_busy_loop(sock, events);
+	if (!sock->ops->poll)
+		return 0;
+	return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock);
 }
 
 static int sock_mmap(struct file *file, struct vm_area_struct *vma)
@@ -2558,6 +2504,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
 
 	if (call < 1 || call > SYS_SENDMMSG)
 		return -EINVAL;
+	call = array_index_nospec(call, SYS_SENDMMSG + 1);
 
 	len = nargs[call];
 	if (len > sizeof(a))
@@ -2724,7 +2671,8 @@ EXPORT_SYMBOL(sock_unregister);
 
 bool sock_is_registered(int family)
 {
-	return family < NPROTO && rcu_access_pointer(net_families[family]);
+	return family < NPROTO &&
+		rcu_access_pointer(net_families[array_index_nospec(family, NPROTO)]);
 }
 
 static int __init sock_init(void)
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 1a9695183599..625acb27efcc 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -35,7 +35,6 @@ struct _strp_msg {
 	 */
 	struct strp_msg strp;
 	int accum_len;
-	int early_eaten;
 };
 
 static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
@@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 	head = strp->skb_head;
 	if (head) {
 		/* Message already in progress */
-
-		stm = _strp_msg(head);
-		if (unlikely(stm->early_eaten)) {
-			/* Already some number of bytes on the receive sock
-			 * data saved in skb_head, just indicate they
-			 * are consumed.
-			 */
-			eaten = orig_len <= stm->early_eaten ?
-				orig_len : stm->early_eaten;
-			stm->early_eaten -= eaten;
-
-			return eaten;
-		}
-
 		if (unlikely(orig_offset)) {
 			/* Getting data with a non-zero offset when a message is
 			 * in progress is not expected. If it does happen, we
@@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 				}
 
 				stm->accum_len += cand_len;
+				eaten += cand_len;
 				strp->need_bytes = stm->strp.full_len -
 						       stm->accum_len;
-				stm->early_eaten = cand_len;
 				STRP_STATS_ADD(strp->stats.bytes, cand_len);
 				desc->count = 0; /* Stop reading socket */
 				break;
@@ -392,7 +377,7 @@ static int strp_read_sock(struct strparser *strp)
 /* Lower sock lock held */
 void strp_data_ready(struct strparser *strp)
 {
-	if (unlikely(strp->stopped))
+	if (unlikely(strp->stopped) || strp->paused)
 		return;
 
 	/* This check is needed to synchronize with do_strp_work.
@@ -407,9 +392,6 @@ void strp_data_ready(struct strparser *strp)
 		return;
 	}
 
-	if (strp->paused)
-		return;
-
 	if (strp->need_bytes) {
 		if (strp_peek_len(strp) < strp->need_bytes)
 			return;
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 9f666e0650e2..2830709957bd 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -133,6 +133,8 @@ static void disc_dupl_alert(struct tipc_bearer *b, u32 node_addr,
 }
 
 /* tipc_disc_addr_trial(): - handle an address uniqueness trial from peer
+ * Returns true if message should be dropped by caller, i.e., if it is a
+ * trial message or we are inside trial period. Otherwise false.
  */
 static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
 				     struct tipc_media_addr *maddr,
@@ -168,8 +170,9 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
 		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
 	}
 
+	/* Accept regular link requests/responses only after trial period */
 	if (mtyp != DSC_TRIAL_MSG)
-		return false;
+		return trial;
 
 	sugg_addr = tipc_node_try_addr(net, peer_id, src);
 	if (sugg_addr)
@@ -284,7 +287,6 @@ static void tipc_disc_timeout(struct timer_list *t)
 {
 	struct tipc_discoverer *d = from_timer(d, t, timer);
 	struct tipc_net *tn = tipc_net(d->net);
-	u32 self = tipc_own_addr(d->net);
 	struct tipc_media_addr maddr;
 	struct sk_buff *skb = NULL;
 	struct net *net = d->net;
@@ -298,12 +300,14 @@ static void tipc_disc_timeout(struct timer_list *t)
 		goto exit;
 	}
 
-	/* Did we just leave the address trial period ? */
-	if (!self && !time_before(jiffies, tn->addr_trial_end)) {
-		self = tn->trial_addr;
-		tipc_net_finalize(net, self);
-		msg_set_prevnode(buf_msg(d->skb), self);
+	/* Trial period over ? */
+	if (!time_before(jiffies, tn->addr_trial_end)) {
+		/* Did we just leave it ? */
+		if (!tipc_own_addr(net))
+			tipc_net_finalize(net, tn->trial_addr);
+
 		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+		msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net));
 	}
 
 	/* Adjust timeout interval according to discovery phase */
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 4fbaa0464405..62199cf5a56c 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -121,12 +121,15 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
 
 void tipc_net_finalize(struct net *net, u32 addr)
 {
-	tipc_set_node_addr(net, addr);
-	smp_mb();
-	tipc_named_reinit(net);
-	tipc_sk_reinit(net);
-	tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
-			     TIPC_CLUSTER_SCOPE, 0, addr);
+	struct tipc_net *tn = tipc_net(net);
+
+	if (!cmpxchg(&tn->node_addr, 0, addr)) {
+		tipc_set_node_addr(net, addr);
+		tipc_named_reinit(net);
+		tipc_sk_reinit(net);
+		tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
+				     TIPC_CLUSTER_SCOPE, 0, addr);
+	}
 }
 
 void tipc_net_stop(struct net *net)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 6a44eb812baf..0453bd451ce8 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -797,6 +797,7 @@ static u32 tipc_node_suggest_addr(struct net *net, u32 addr)
 }
 
 /* tipc_node_try_addr(): Check if addr can be used by peer, suggest other if not
+ * Returns suggested address if any, otherwise 0
  */
 u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr)
 {
@@ -819,12 +820,14 @@ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr)
 	if (n) {
 		addr = n->addr;
 		tipc_node_put(n);
+		return addr;
 	}
-	/* Even this node may be in trial phase */
+
+	/* Even this node may be in conflict */
 	if (tn->trial_addr == addr)
 		return tipc_node_suggest_addr(net, addr);
 
-	return addr;
+	return 0;
 }
 
 void tipc_node_check_dest(struct net *net, u32 addr,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 14a5d055717d..930852c54d7a 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -692,9 +692,10 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
 }
 
 /**
- * tipc_poll - read pollmask
+ * tipc_poll - read and possibly block on pollmask
  * @file: file structure associated with the socket
  * @sock: socket for which to calculate the poll bits
+ * @wait: ???
  *
  * Returns pollmask value
  *
@@ -708,12 +709,15 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
  * imply that the operation will succeed, merely that it should be performed
  * and will not block.
  */
-static __poll_t tipc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t tipc_poll(struct file *file, struct socket *sock,
+			      poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
 	__poll_t revents = 0;
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
 	if (sk->sk_shutdown == SHUTDOWN_MASK)
@@ -3033,7 +3037,7 @@ static const struct proto_ops msg_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= tipc_getname,
-	.poll_mask	= tipc_poll_mask,
+	.poll		= tipc_poll,
 	.ioctl		= tipc_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= tipc_shutdown,
@@ -3054,7 +3058,7 @@ static const struct proto_ops packet_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
-	.poll_mask	= tipc_poll_mask,
+	.poll		= tipc_poll,
 	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
@@ -3075,7 +3079,7 @@ static const struct proto_ops stream_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
-	.poll_mask	= tipc_poll_mask,
+	.poll		= tipc_poll,
 	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index a127d61e8af9..301f22430469 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -712,7 +712,7 @@ static int __init tls_register(void)
 	build_protos(tls_prots[TLSV4], &tcp_prot);
 
 	tls_sw_proto_ops = inet_stream_ops;
-	tls_sw_proto_ops.poll_mask = tls_sw_poll_mask;
+	tls_sw_proto_ops.poll = tls_sw_poll;
 	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
 
 #ifdef CONFIG_TLS_DEVICE
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index f127fac88acf..1f3d9789af30 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -440,7 +440,7 @@ alloc_encrypted:
 			ret = tls_push_record(sk, msg->msg_flags, record_type);
 			if (!ret)
 				continue;
-			if (ret == -EAGAIN)
+			if (ret < 0)
 				goto send_end;
 
 			copied -= try_to_copy;
@@ -646,6 +646,9 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags,
 			return NULL;
 		}
 
+		if (sk->sk_shutdown & RCV_SHUTDOWN)
+			return NULL;
+
 		if (sock_flag(sk, SOCK_DONE))
 			return NULL;
 
@@ -701,6 +704,10 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 	nsg = skb_to_sgvec(skb, &sgin[1],
 			   rxm->offset + tls_ctx->rx.prepend_size,
 			   rxm->full_len - tls_ctx->rx.prepend_size);
+	if (nsg < 0) {
+		ret = nsg;
+		goto out;
+	}
 
 	tls_make_aad(ctx->rx_aad_ciphertext,
 		     rxm->full_len - tls_ctx->rx.overhead_size,
@@ -712,6 +719,7 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 				rxm->full_len - tls_ctx->rx.overhead_size,
 				skb, sk->sk_allocation);
 
+out:
 	if (sgin != &sgin_arr[0])
 		kfree(sgin);
 
@@ -919,22 +927,23 @@ splice_read_end:
 	return copied ? : err;
 }
 
-__poll_t tls_sw_poll_mask(struct socket *sock, __poll_t events)
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+			 struct poll_table_struct *wait)
 {
+	unsigned int ret;
 	struct sock *sk = sock->sk;
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
-	__poll_t mask;
 
-	/* Grab EPOLLOUT and EPOLLHUP from the underlying socket */
-	mask = ctx->sk_poll_mask(sock, events);
+	/* Grab POLLOUT and POLLHUP from the underlying socket */
+	ret = ctx->sk_poll(file, sock, wait);
 
-	/* Clear EPOLLIN bits, and set based on recv_pkt */
-	mask &= ~(EPOLLIN | EPOLLRDNORM);
+	/* Clear POLLIN bits, and set based on recv_pkt */
+	ret &= ~(POLLIN | POLLRDNORM);
 	if (ctx->recv_pkt)
-		mask |= EPOLLIN | EPOLLRDNORM;
+		ret |= POLLIN | POLLRDNORM;
 
-	return mask;
+	return ret;
 }
 
 static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
@@ -1191,7 +1200,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		sk->sk_data_ready = tls_data_ready;
 		write_unlock_bh(&sk->sk_callback_lock);
 
-		sw_ctx_rx->sk_poll_mask = sk->sk_socket->ops->poll_mask;
+		sw_ctx_rx->sk_poll = sk->sk_socket->ops->poll;
 
 		strp_check_rcv(&sw_ctx_rx->strp);
 	}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 95b02a71fd47..e5473c03d667 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -638,8 +638,9 @@ static int unix_stream_connect(struct socket *, struct sockaddr *,
 static int unix_socketpair(struct socket *, struct socket *);
 static int unix_accept(struct socket *, struct socket *, int, bool);
 static int unix_getname(struct socket *, struct sockaddr *, int);
-static __poll_t unix_poll_mask(struct socket *, __poll_t);
-static __poll_t unix_dgram_poll_mask(struct socket *, __poll_t);
+static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
+static __poll_t unix_dgram_poll(struct file *, struct socket *,
+				    poll_table *);
 static int unix_ioctl(struct socket *, unsigned int, unsigned long);
 static int unix_shutdown(struct socket *, int);
 static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
@@ -680,7 +681,7 @@ static const struct proto_ops unix_stream_ops = {
 	.socketpair =	unix_socketpair,
 	.accept =	unix_accept,
 	.getname =	unix_getname,
-	.poll_mask =	unix_poll_mask,
+	.poll =		unix_poll,
 	.ioctl =	unix_ioctl,
 	.listen =	unix_listen,
 	.shutdown =	unix_shutdown,
@@ -703,7 +704,7 @@ static const struct proto_ops unix_dgram_ops = {
 	.socketpair =	unix_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	unix_getname,
-	.poll_mask =	unix_dgram_poll_mask,
+	.poll =		unix_dgram_poll,
 	.ioctl =	unix_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	unix_shutdown,
@@ -725,7 +726,7 @@ static const struct proto_ops unix_seqpacket_ops = {
 	.socketpair =	unix_socketpair,
 	.accept =	unix_accept,
 	.getname =	unix_getname,
-	.poll_mask =	unix_dgram_poll_mask,
+	.poll =		unix_dgram_poll,
 	.ioctl =	unix_ioctl,
 	.listen =	unix_listen,
 	.shutdown =	unix_shutdown,
@@ -2629,10 +2630,13 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	return err;
 }
 
-static __poll_t unix_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
-	__poll_t mask = 0;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err)
@@ -2661,11 +2665,15 @@ static __poll_t unix_poll_mask(struct socket *sock, __poll_t events)
 	return mask;
 }
 
-static __poll_t unix_dgram_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
+				    poll_table *wait)
 {
 	struct sock *sk = sock->sk, *other;
-	int writable;
-	__poll_t mask = 0;
+	unsigned int writable;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -2691,7 +2699,7 @@ static __poll_t unix_dgram_poll_mask(struct socket *sock, __poll_t events)
 	}
 
 	/* No write status requested, avoid expensive OUT tests. */
-	if (!(events & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
+	if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
 		return mask;
 
 	writable = unix_writable(sk);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index bb5d5fa68c35..ab27a2872935 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -451,14 +451,14 @@ static int vsock_send_shutdown(struct sock *sk, int mode)
 	return transport->shutdown(vsock_sk(sk), mode);
 }
 
-void vsock_pending_work(struct work_struct *work)
+static void vsock_pending_work(struct work_struct *work)
 {
 	struct sock *sk;
 	struct sock *listener;
 	struct vsock_sock *vsk;
 	bool cleanup;
 
-	vsk = container_of(work, struct vsock_sock, dwork.work);
+	vsk = container_of(work, struct vsock_sock, pending_work.work);
 	sk = sk_vsock(vsk);
 	listener = vsk->listener;
 	cleanup = true;
@@ -498,7 +498,6 @@ out:
 	sock_put(sk);
 	sock_put(listener);
 }
-EXPORT_SYMBOL_GPL(vsock_pending_work);
 
 /**** SOCKET OPERATIONS ****/
 
@@ -597,6 +596,8 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
 	return retval;
 }
 
+static void vsock_connect_timeout(struct work_struct *work);
+
 struct sock *__vsock_create(struct net *net,
 			    struct socket *sock,
 			    struct sock *parent,
@@ -638,6 +639,8 @@ struct sock *__vsock_create(struct net *net,
 	vsk->sent_request = false;
 	vsk->ignore_connecting_rst = false;
 	vsk->peer_shutdown = 0;
+	INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout);
+	INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work);
 
 	psk = parent ? vsock_sk(parent) : NULL;
 	if (parent) {
@@ -850,11 +853,18 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	return err;
 }
 
-static __poll_t vsock_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t vsock_poll(struct file *file, struct socket *sock,
+			       poll_table *wait)
 {
-	struct sock *sk = sock->sk;
-	struct vsock_sock *vsk = vsock_sk(sk);
-	__poll_t mask = 0;
+	struct sock *sk;
+	__poll_t mask;
+	struct vsock_sock *vsk;
+
+	sk = sock->sk;
+	vsk = vsock_sk(sk);
+
+	poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	if (sk->sk_err)
 		/* Signify that there has been an error on this socket. */
@@ -1084,7 +1094,7 @@ static const struct proto_ops vsock_dgram_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = vsock_getname,
-	.poll_mask = vsock_poll_mask,
+	.poll = vsock_poll,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = vsock_shutdown,
@@ -1110,7 +1120,7 @@ static void vsock_connect_timeout(struct work_struct *work)
 	struct vsock_sock *vsk;
 	int cancel = 0;
 
-	vsk = container_of(work, struct vsock_sock, dwork.work);
+	vsk = container_of(work, struct vsock_sock, connect_work.work);
 	sk = sk_vsock(vsk);
 
 	lock_sock(sk);
@@ -1214,9 +1224,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 			 * timeout fires.
 			 */
 			sock_hold(sk);
-			INIT_DELAYED_WORK(&vsk->dwork,
-					  vsock_connect_timeout);
-			schedule_delayed_work(&vsk->dwork, timeout);
+			schedule_delayed_work(&vsk->connect_work, timeout);
 
 			/* Skip ahead to preserve error code set above. */
 			goto out_wait;
@@ -1842,7 +1850,7 @@ static const struct proto_ops vsock_stream_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = vsock_accept,
 	.getname = vsock_getname,
-	.poll_mask = vsock_poll_mask,
+	.poll = vsock_poll,
 	.ioctl = sock_no_ioctl,
 	.listen = vsock_listen,
 	.shutdown = vsock_shutdown,
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 8e03bd3f3668..5d3cce9e8744 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -201,7 +201,7 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
 		return -ENODEV;
 	}
 
-	if (le32_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
+	if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
 		return virtio_transport_send_pkt_loopback(vsock, pkt);
 
 	if (pkt->reply)
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index a7a73ffe675b..cb332adb84cd 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1094,8 +1094,7 @@ static int vmci_transport_recv_listen(struct sock *sk,
 	vpending->listener = sk;
 	sock_hold(sk);
 	sock_hold(pending);
-	INIT_DELAYED_WORK(&vpending->dwork, vsock_pending_work);
-	schedule_delayed_work(&vpending->dwork, HZ);
+	schedule_delayed_work(&vpending->pending_work, HZ);
 
 out:
 	return err;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c7bbe5f0aae8..80bc986c79e5 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4409,6 +4409,7 @@ static int parse_station_flags(struct genl_info *info,
 		params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) |
 					 BIT(NL80211_STA_FLAG_MFP) |
 					 BIT(NL80211_STA_FLAG_AUTHORIZED);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -6231,7 +6232,7 @@ do {									    \
 				  nl80211_check_s32);
 	/*
 	 * Check HT operation mode based on
-	 * IEEE 802.11 2012 8.4.2.59 HT Operation element.
+	 * IEEE 802.11-2016 9.4.2.57 HT Operation element.
 	 */
 	if (tb[NL80211_MESHCONF_HT_OPMODE]) {
 		ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]);
@@ -6241,22 +6242,9 @@ do {									    \
 				  IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
 			return -EINVAL;
 
-		if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) &&
-		    (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
-			return -EINVAL;
+		/* NON_HT_STA bit is reserved, but some programs set it */
+		ht_opmode &= ~IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT;
 
-		switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) {
-		case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
-		case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
-			if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)
-				return -EINVAL;
-			break;
-		case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
-		case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
-			if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
-				return -EINVAL;
-			break;
-		}
 		cfg->ht_opmode = ht_opmode;
 		mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1));
 	}
@@ -10962,9 +10950,12 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 				    rem) {
 			u8 *mask_pat;
 
-			nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
-					 nl80211_packet_pattern_policy,
-					 info->extack);
+			err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+					       nl80211_packet_pattern_policy,
+					       info->extack);
+			if (err)
+				goto error;
+
 			err = -EINVAL;
 			if (!pat_tb[NL80211_PKTPAT_MASK] ||
 			    !pat_tb[NL80211_PKTPAT_PATTERN])
@@ -11213,8 +11204,11 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 			    rem) {
 		u8 *mask_pat;
 
-		nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
-				 nl80211_packet_pattern_policy, NULL);
+		err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+				       nl80211_packet_pattern_policy, NULL);
+		if (err)
+			return err;
+
 		if (!pat_tb[NL80211_PKTPAT_MASK] ||
 		    !pat_tb[NL80211_PKTPAT_PATTERN])
 			return -EINVAL;
@@ -14930,20 +14924,24 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 EXPORT_SYMBOL(cfg80211_mgmt_tx_status);
 
 static int __nl80211_rx_control_port(struct net_device *dev,
-				     const u8 *buf, size_t len,
-				     const u8 *addr, u16 proto,
+				     struct sk_buff *skb,
 				     bool unencrypted, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	struct ethhdr *ehdr = eth_hdr(skb);
+	const u8 *addr = ehdr->h_source;
+	u16 proto = be16_to_cpu(skb->protocol);
 	struct sk_buff *msg;
 	void *hdr;
+	struct nlattr *frame;
+
 	u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid);
 
 	if (!nlportid)
 		return -ENOENT;
 
-	msg = nlmsg_new(100 + len, gfp);
+	msg = nlmsg_new(100 + skb->len, gfp);
 	if (!msg)
 		return -ENOMEM;
 
@@ -14957,13 +14955,17 @@ static int __nl80211_rx_control_port(struct net_device *dev,
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
 	    nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev),
 			      NL80211_ATTR_PAD) ||
-	    nla_put(msg, NL80211_ATTR_FRAME, len, buf) ||
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) ||
 	    nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) ||
 	    (unencrypted && nla_put_flag(msg,
 					 NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT)))
 		goto nla_put_failure;
 
+	frame = nla_reserve(msg, NL80211_ATTR_FRAME, skb->len);
+	if (!frame)
+		goto nla_put_failure;
+
+	skb_copy_bits(skb, 0, nla_data(frame), skb->len);
 	genlmsg_end(msg, hdr);
 
 	return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid);
@@ -14974,14 +14976,12 @@ static int __nl80211_rx_control_port(struct net_device *dev,
 }
 
 bool cfg80211_rx_control_port(struct net_device *dev,
-			      const u8 *buf, size_t len,
-			      const u8 *addr, u16 proto, bool unencrypted)
+			      struct sk_buff *skb, bool unencrypted)
 {
 	int ret;
 
-	trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted);
-	ret = __nl80211_rx_control_port(dev, buf, len, addr, proto,
-					unencrypted, GFP_ATOMIC);
+	trace_cfg80211_rx_control_port(dev, skb, unencrypted);
+	ret = __nl80211_rx_control_port(dev, skb, unencrypted, GFP_ATOMIC);
 	trace_cfg80211_return_bool(ret == 0);
 	return ret == 0;
 }
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index bbe6298e4bb9..4fc66a117b7d 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2240,7 +2240,9 @@ static void wiphy_update_regulatory(struct wiphy *wiphy,
 		 * as some drivers used this to restore its orig_* reg domain.
 		 */
 		if (initiator == NL80211_REGDOM_SET_BY_CORE &&
-		    wiphy->regulatory_flags & REGULATORY_CUSTOM_REG)
+		    wiphy->regulatory_flags & REGULATORY_CUSTOM_REG &&
+		    !(wiphy->regulatory_flags &
+		      REGULATORY_WIPHY_SELF_MANAGED))
 			reg_call_notifier(wiphy, lr);
 		return;
 	}
@@ -2787,26 +2789,6 @@ static void notify_self_managed_wiphys(struct regulatory_request *request)
 	}
 }
 
-static bool reg_only_self_managed_wiphys(void)
-{
-	struct cfg80211_registered_device *rdev;
-	struct wiphy *wiphy;
-	bool self_managed_found = false;
-
-	ASSERT_RTNL();
-
-	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
-		wiphy = &rdev->wiphy;
-		if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
-			self_managed_found = true;
-		else
-			return false;
-	}
-
-	/* make sure at least one self-managed wiphy exists */
-	return self_managed_found;
-}
-
 /*
  * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_*
  * Regulatory hints come on a first come first serve basis and we
@@ -2839,10 +2821,6 @@ static void reg_process_pending_hints(void)
 	spin_unlock(&reg_requests_lock);
 
 	notify_self_managed_wiphys(reg_request);
-	if (reg_only_self_managed_wiphys()) {
-		reg_free_request(reg_request);
-		return;
-	}
 
 	reg_process_hint(reg_request);
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 2b417a2fe63f..7c73510b161f 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2627,23 +2627,25 @@ TRACE_EVENT(cfg80211_mgmt_tx_status,
 );
 
 TRACE_EVENT(cfg80211_rx_control_port,
-	TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len,
-		 const u8 *addr, u16 proto, bool unencrypted),
-	TP_ARGS(netdev, buf, len, addr, proto, unencrypted),
+	TP_PROTO(struct net_device *netdev, struct sk_buff *skb,
+		 bool unencrypted),
+	TP_ARGS(netdev, skb, unencrypted),
 	TP_STRUCT__entry(
 		NETDEV_ENTRY
-		MAC_ENTRY(addr)
+		__field(int, len)
+		MAC_ENTRY(from)
 		__field(u16, proto)
 		__field(bool, unencrypted)
 	),
 	TP_fast_assign(
 		NETDEV_ASSIGN;
-		MAC_ASSIGN(addr, addr);
-		__entry->proto = proto;
+		__entry->len = skb->len;
+		MAC_ASSIGN(from, eth_hdr(skb)->h_source);
+		__entry->proto = be16_to_cpu(skb->protocol);
 		__entry->unencrypted = unencrypted;
 	),
-	TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s",
-		  NETDEV_PR_ARG, MAC_PR_ARG(addr),
+	TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s",
+		  NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from),
 		  __entry->proto, BOOL_TO_STR(__entry->unencrypted))
 );
 
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index f93365ae0fdd..d49aa79b7997 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1750,7 +1750,7 @@ static const struct proto_ops x25_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	x25_accept,
 	.getname =	x25_getname,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	x25_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = compat_x25_ioctl,
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 3b3410ada097..4e937cd7c17d 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -84,10 +84,8 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
 	int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len);
 
-	if (err) {
-		xdp_return_buff(xdp);
+	if (err)
 		xs->rx_dropped++;
-	}
 
 	return err;
 }
@@ -199,8 +197,11 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 {
 	u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg;
 	struct xdp_sock *xs = xdp_sk(skb->sk);
+	unsigned long flags;
 
+	spin_lock_irqsave(&xs->tx_completion_lock, flags);
 	WARN_ON_ONCE(xskq_produce_addr(xs->umem->cq, addr));
+	spin_unlock_irqrestore(&xs->tx_completion_lock, flags);
 
 	sock_wfree(skb);
 }
@@ -215,9 +216,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 	struct sk_buff *skb;
 	int err = 0;
 
-	if (unlikely(!xs->tx))
-		return -ENOBUFS;
-
 	mutex_lock(&xs->mutex);
 
 	while (xskq_peek_desc(xs->tx, &desc)) {
@@ -230,22 +228,13 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 			goto out;
 		}
 
-		if (xskq_reserve_addr(xs->umem->cq)) {
-			err = -EAGAIN;
+		if (xskq_reserve_addr(xs->umem->cq))
 			goto out;
-		}
 
-		len = desc.len;
-		if (unlikely(len > xs->dev->mtu)) {
-			err = -EMSGSIZE;
+		if (xs->queue_id >= xs->dev->real_num_tx_queues)
 			goto out;
-		}
-
-		if (xs->queue_id >= xs->dev->real_num_tx_queues) {
-			err = -ENXIO;
-			goto out;
-		}
 
+		len = desc.len;
 		skb = sock_alloc_send_skb(sk, len, 1, &err);
 		if (unlikely(!skb)) {
 			err = -EAGAIN;
@@ -268,15 +257,15 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 		skb->destructor = xsk_destruct_skb;
 
 		err = dev_direct_xmit(skb, xs->queue_id);
+		xskq_discard_desc(xs->tx);
 		/* Ignore NET_XMIT_CN as packet might have been sent */
 		if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) {
-			err = -EAGAIN;
-			/* SKB consumed by dev_direct_xmit() */
+			/* SKB completed but not sent */
+			err = -EBUSY;
 			goto out;
 		}
 
 		sent_frame = true;
-		xskq_discard_desc(xs->tx);
 	}
 
 out:
@@ -297,15 +286,18 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 		return -ENXIO;
 	if (unlikely(!(xs->dev->flags & IFF_UP)))
 		return -ENETDOWN;
+	if (unlikely(!xs->tx))
+		return -ENOBUFS;
 	if (need_wait)
 		return -EOPNOTSUPP;
 
 	return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len);
 }
 
-static __poll_t xsk_poll_mask(struct socket *sock, __poll_t events)
+static unsigned int xsk_poll(struct file *file, struct socket *sock,
+			     struct poll_table_struct *wait)
 {
-	__poll_t mask = datagram_poll_mask(sock, events);
+	unsigned int mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 	struct xdp_sock *xs = xdp_sk(sk);
 
@@ -696,7 +688,7 @@ static const struct proto_ops xsk_proto_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= sock_no_getname,
-	.poll_mask	= xsk_poll_mask,
+	.poll		= xsk_poll,
 	.ioctl		= sock_no_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
@@ -754,6 +746,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 
 	xs = xdp_sk(sk);
 	mutex_init(&xs->mutex);
+	spin_lock_init(&xs->tx_completion_lock);
 
 	local_bh_disable();
 	sock_prot_inuse_add(net, &xsk_proto, 1);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index ef6a6f0ec949..8a64b150be54 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -62,14 +62,9 @@ static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt)
 	return (entries > dcnt) ? dcnt : entries;
 }
 
-static inline u32 xskq_nb_free_lazy(struct xsk_queue *q, u32 producer)
-{
-	return q->nentries - (producer - q->cons_tail);
-}
-
 static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt)
 {
-	u32 free_entries = xskq_nb_free_lazy(q, producer);
+	u32 free_entries = q->nentries - (producer - q->cons_tail);
 
 	if (free_entries >= dcnt)
 		return free_entries;
@@ -129,7 +124,7 @@ static inline int xskq_produce_addr(struct xsk_queue *q, u64 addr)
 {
 	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
 
-	if (xskq_nb_free(q, q->prod_tail, LAZY_UPDATE_THRESHOLD) == 0)
+	if (xskq_nb_free(q, q->prod_tail, 1) == 0)
 		return -ENOSPC;
 
 	ring->desc[q->prod_tail++ & q->ring_mask] = addr;
@@ -255,7 +250,7 @@ static inline bool xskq_full_desc(struct xsk_queue *q)
 
 static inline bool xskq_empty_desc(struct xsk_queue *q)
 {
-	return xskq_nb_free(q, q->prod_tail, 1) == q->nentries;
+	return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries;
 }
 
 void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5f48251c1319..7c5e8978aeaa 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2286,6 +2286,9 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
 	if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
 		return make_blackhole(net, dst_orig->ops->family, dst_orig);
 
+	if (IS_ERR(dst))
+		dst_release(dst_orig);
+
 	return dst;
 }
 EXPORT_SYMBOL(xfrm_lookup_route);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 080035f056d9..33878e6e0d0a 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1025,10 +1025,12 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
 {
 	struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
 
-	if (nlsk)
-		return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
-	else
-		return -1;
+	if (!nlsk) {
+		kfree_skb(skb);
+		return -EPIPE;
+	}
+
+	return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
 }
 
 static inline unsigned int xfrm_spdinfo_msgsize(void)
@@ -1671,9 +1673,11 @@ static inline unsigned int userpolicy_type_attrsize(void)
 #ifdef CONFIG_XFRM_SUB_POLICY
 static int copy_to_user_policy_type(u8 type, struct sk_buff *skb)
 {
-	struct xfrm_userpolicy_type upt = {
-		.type = type,
-	};
+	struct xfrm_userpolicy_type upt;
+
+	/* Sadly there are two holes in struct xfrm_userpolicy_type */
+	memset(&upt, 0, sizeof(upt));
+	upt.type = type;
 
 	return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt);
 }
diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore
new file mode 100644
index 000000000000..8ae4940025f8
--- /dev/null
+++ b/samples/bpf/.gitignore
@@ -0,0 +1,49 @@
+cpustat
+fds_example
+lathist
+load_sock_ops
+lwt_len_hist
+map_perf_test
+offwaketime
+per_socket_stats_example
+sampleip
+sock_example
+sockex1
+sockex2
+sockex3
+spintest
+syscall_nrs.h
+syscall_tp
+task_fd_query
+tc_l2_redirect
+test_cgrp2_array_pin
+test_cgrp2_attach
+test_cgrp2_attach2
+test_cgrp2_sock
+test_cgrp2_sock2
+test_current_task_under_cgroup
+test_lru_dist
+test_map_in_map
+test_overhead
+test_probe_write_user
+trace_event
+trace_output
+tracex1
+tracex2
+tracex3
+tracex4
+tracex5
+tracex6
+tracex7
+xdp1
+xdp2
+xdp_adjust_tail
+xdp_fwd
+xdp_monitor
+xdp_redirect
+xdp_redirect_cpu
+xdp_redirect_map
+xdp_router_ipv4
+xdp_rxq_info
+xdp_tx_iptunnel
+xdpsock
diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c
index 95c16324760c..0b6f22feb2c9 100644
--- a/samples/bpf/parse_varlen.c
+++ b/samples/bpf/parse_varlen.c
@@ -6,6 +6,7 @@
  */
 #define KBUILD_MODNAME "foo"
 #include <linux/if_ether.h>
+#include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/in.h>
@@ -108,11 +109,6 @@ static int parse_ipv6(void *data, uint64_t nh_off, void *data_end)
 	return 0;
 }
 
-struct vlan_hdr {
-	uint16_t h_vlan_TCI;
-	uint16_t h_vlan_encapsulated_proto;
-};
-
 SEC("varlen")
 int handle_ingress(struct __sk_buff *skb)
 {
diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c
index 6caf47afa635..9d6dcaa9db92 100644
--- a/samples/bpf/test_overhead_user.c
+++ b/samples/bpf/test_overhead_user.c
@@ -6,6 +6,7 @@
  */
 #define _GNU_SOURCE
 #include <sched.h>
+#include <errno.h>
 #include <stdio.h>
 #include <sys/types.h>
 #include <asm/unistd.h>
@@ -44,8 +45,13 @@ static void test_task_rename(int cpu)
 		exit(1);
 	}
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
-		write(fd, buf, sizeof(buf));
+	for (i = 0; i < MAX_CNT; i++) {
+		if (write(fd, buf, sizeof(buf)) < 0) {
+			printf("task rename failed: %s\n", strerror(errno));
+			close(fd);
+			return;
+		}
+	}
 	printf("task_rename:%d: %lld events per sec\n",
 	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
 	close(fd);
@@ -63,8 +69,13 @@ static void test_urandom_read(int cpu)
 		exit(1);
 	}
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
-		read(fd, buf, sizeof(buf));
+	for (i = 0; i < MAX_CNT; i++) {
+		if (read(fd, buf, sizeof(buf)) < 0) {
+			printf("failed to read from /dev/urandom: %s\n", strerror(errno));
+			close(fd);
+			return;
+		}
+	}
 	printf("urandom_read:%d: %lld events per sec\n",
 	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
 	close(fd);
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index 1fa1becfa641..d08046ab81f0 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -122,6 +122,16 @@ static void print_stacks(void)
 	}
 }
 
+static inline int generate_load(void)
+{
+	if (system("dd if=/dev/zero of=/dev/null count=5000k status=none") < 0) {
+		printf("failed to generate some load with dd: %s\n", strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
 static void test_perf_event_all_cpu(struct perf_event_attr *attr)
 {
 	int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
@@ -142,7 +152,11 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr)
 		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
 		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE) == 0);
 	}
-	system("dd if=/dev/zero of=/dev/null count=5000k status=none");
+
+	if (generate_load() < 0) {
+		error = 1;
+		goto all_cpu_err;
+	}
 	print_stacks();
 all_cpu_err:
 	for (i--; i >= 0; i--) {
@@ -156,7 +170,7 @@ all_cpu_err:
 
 static void test_perf_event_task(struct perf_event_attr *attr)
 {
-	int pmu_fd;
+	int pmu_fd, error = 0;
 
 	/* per task perf event, enable inherit so the "dd ..." command can be traced properly.
 	 * Enabling inherit will cause bpf_perf_prog_read_time helper failure.
@@ -171,10 +185,17 @@ static void test_perf_event_task(struct perf_event_attr *attr)
 	}
 	assert(ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
 	assert(ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE) == 0);
-	system("dd if=/dev/zero of=/dev/null count=5000k status=none");
+
+	if (generate_load() < 0) {
+		error = 1;
+		goto err;
+	}
 	print_stacks();
+err:
 	ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
 	close(pmu_fd);
+	if (error)
+		int_exit(0);
 }
 
 static void test_bpf_perf_event(void)
diff --git a/samples/bpf/xdp2skb_meta.sh b/samples/bpf/xdp2skb_meta.sh
index b9c9549c4c27..4bde9d066c46 100755
--- a/samples/bpf/xdp2skb_meta.sh
+++ b/samples/bpf/xdp2skb_meta.sh
@@ -16,8 +16,8 @@
 BPF_FILE=xdp2skb_meta_kern.o
 DIR=$(dirname $0)
 
-export TC=/usr/sbin/tc
-export IP=/usr/sbin/ip
+[ -z "$TC" ] && TC=tc
+[ -z "$IP" ] && IP=ip
 
 function usage() {
     echo ""
@@ -53,7 +53,7 @@ function _call_cmd() {
     local allow_fail="$2"
     shift 2
     if [[ -n "$VERBOSE" ]]; then
-	echo "$(basename $cmd) $@"
+	echo "$cmd $@"
     fi
     if [[ -n "$DRYRUN" ]]; then
 	return
diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c
index 6673cdb9f55c..a7e94e7ff87d 100644
--- a/samples/bpf/xdp_fwd_kern.c
+++ b/samples/bpf/xdp_fwd_kern.c
@@ -48,9 +48,9 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 	struct ethhdr *eth = data;
 	struct ipv6hdr *ip6h;
 	struct iphdr *iph;
-	int out_index;
 	u16 h_proto;
 	u64 nh_off;
+	int rc;
 
 	nh_off = sizeof(*eth);
 	if (data + nh_off > data_end)
@@ -101,7 +101,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 
 	fib_params.ifindex = ctx->ingress_ifindex;
 
-	out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
+	rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
 
 	/* verify egress index has xdp support
 	 * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
@@ -109,7 +109,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 	 * NOTE: without verification that egress index supports XDP
 	 *       forwarding packets are dropped.
 	 */
-	if (out_index > 0) {
+	if (rc == 0) {
 		if (h_proto == htons(ETH_P_IP))
 			ip_decrease_ttl(iph);
 		else if (h_proto == htons(ETH_P_IPV6))
@@ -117,7 +117,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 
 		memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
 		memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
-		return bpf_redirect_map(&tx_port, out_index, 0);
+		return bpf_redirect_map(&tx_port, fib_params.ifindex, 0);
 	}
 
 	return XDP_PASS;
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index 303e9e7161f3..4938dcbaecbf 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -14,7 +14,7 @@
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
 
-#define MAX_CPUS 12 /* WARNING - sync with _user.c */
+#define MAX_CPUS 64 /* WARNING - sync with _user.c */
 
 /* Special map type that can XDP_REDIRECT frames to another CPU */
 struct bpf_map_def SEC("maps") cpu_map = {
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index f6efaefd485b..4b4d78fffe30 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -19,7 +19,7 @@ static const char *__doc__ =
 #include <arpa/inet.h>
 #include <linux/if_link.h>
 
-#define MAX_CPUS 12 /* WARNING - sync with _kern.c */
+#define MAX_CPUS 64 /* WARNING - sync with _kern.c */
 
 /* How many xdp_progs are defined in _kern.c */
 #define MAX_PROG 5
@@ -527,7 +527,7 @@ static void stress_cpumap(void)
 	 * procedure.
 	 */
 	create_cpu_entry(1,  1024, 0, false);
-	create_cpu_entry(1,   128, 0, false);
+	create_cpu_entry(1,     8, 0, false);
 	create_cpu_entry(1, 16000, 0, false);
 }
 
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index d69c8d78d3fd..5904b1543831 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -729,7 +729,7 @@ static void kick_tx(int fd)
 	int ret;
 
 	ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0);
-	if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN)
+	if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY)
 		return;
 	lassert(0);
 }
diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c
index 2960e26c6ea4..2535c3677c7b 100644
--- a/samples/vfio-mdev/mbochs.c
+++ b/samples/vfio-mdev/mbochs.c
@@ -178,6 +178,8 @@ static const char *vbe_name(u32 index)
 	return "(invalid)";
 }
 
+static struct page *__mbochs_get_page(struct mdev_state *mdev_state,
+				      pgoff_t pgoff);
 static struct page *mbochs_get_page(struct mdev_state *mdev_state,
 				    pgoff_t pgoff);
 
@@ -394,7 +396,7 @@ static ssize_t mdev_access(struct mdev_device *mdev, char *buf, size_t count,
 		   MBOCHS_MEMORY_BAR_OFFSET + mdev_state->memsize) {
 		pos -= MBOCHS_MMIO_BAR_OFFSET;
 		poff = pos & ~PAGE_MASK;
-		pg = mbochs_get_page(mdev_state, pos >> PAGE_SHIFT);
+		pg = __mbochs_get_page(mdev_state, pos >> PAGE_SHIFT);
 		map = kmap(pg);
 		if (is_write)
 			memcpy(map + poff, buf, count);
@@ -657,7 +659,7 @@ static void mbochs_put_pages(struct mdev_state *mdev_state)
 	dev_dbg(dev, "%s: %d pages released\n", __func__, count);
 }
 
-static int mbochs_region_vm_fault(struct vm_fault *vmf)
+static vm_fault_t mbochs_region_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct mdev_state *mdev_state = vma->vm_private_data;
@@ -695,7 +697,7 @@ static int mbochs_mmap(struct mdev_device *mdev, struct vm_area_struct *vma)
 	return 0;
 }
 
-static int mbochs_dmabuf_vm_fault(struct vm_fault *vmf)
+static vm_fault_t mbochs_dmabuf_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct mbochs_dmabuf *dmabuf = vma->vm_private_data;
@@ -803,29 +805,26 @@ static void mbochs_release_dmabuf(struct dma_buf *buf)
 	mutex_unlock(&mdev_state->ops_lock);
 }
 
-static void *mbochs_kmap_atomic_dmabuf(struct dma_buf *buf,
-				       unsigned long page_num)
+static void *mbochs_kmap_dmabuf(struct dma_buf *buf, unsigned long page_num)
 {
 	struct mbochs_dmabuf *dmabuf = buf->priv;
 	struct page *page = dmabuf->pages[page_num];
 
-	return kmap_atomic(page);
+	return kmap(page);
 }
 
-static void *mbochs_kmap_dmabuf(struct dma_buf *buf, unsigned long page_num)
+static void mbochs_kunmap_dmabuf(struct dma_buf *buf, unsigned long page_num,
+				 void *vaddr)
 {
-	struct mbochs_dmabuf *dmabuf = buf->priv;
-	struct page *page = dmabuf->pages[page_num];
-
-	return kmap(page);
+	kunmap(vaddr);
 }
 
 static struct dma_buf_ops mbochs_dmabuf_ops = {
 	.map_dma_buf	  = mbochs_map_dmabuf,
 	.unmap_dma_buf	  = mbochs_unmap_dmabuf,
 	.release	  = mbochs_release_dmabuf,
-	.map_atomic	  = mbochs_kmap_atomic_dmabuf,
 	.map		  = mbochs_kmap_dmabuf,
+	.unmap		  = mbochs_kunmap_dmabuf,
 	.mmap		  = mbochs_mmap_dmabuf,
 };
 
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index c8156d61678c..d52db4279aa5 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -163,8 +163,8 @@ cc-ldoption = $(call try-run,\
 	$(CC) $(1) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
 
 # ld-option
-# Usage: LDFLAGS += $(call ld-option, -X)
-ld-option = $(call try-run, $(LD) $(LDFLAGS) $(1) -v,$(1),$(2))
+# Usage: LDFLAGS += $(call ld-option, -X, -Y)
+ld-option = $(call try-run, $(LD) $(LDFLAGS) $(1) -v,$(1),$(2),$(3))
 
 # ar-option
 # Usage: KBUILD_ARFLAGS := $(call ar-option,D)
@@ -214,7 +214,7 @@ hdr-inst := -f $(srctree)/scripts/Makefile.headersinst obj
 # Prefix -I with $(srctree) if it is not an absolute path.
 # skip if -I has no parameter
 addtree = $(if $(patsubst -I%,%,$(1)), \
-$(if $(filter-out -I/% -I./% -I../%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1)),$(1)))
+$(if $(filter-out -I/% -I./% -I../%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1)),$(1)),$(1))
 
 # Find all -I options and call addtree
 flags = $(foreach o,$($(1)),$(if $(filter -I%,$(o)),$(call addtree,$(o)),$(o)))
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index e7889f486ca1..514ed63ff571 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -590,7 +590,4 @@ endif
 # We never want them to be removed automatically.
 .SECONDARY: $(targets)
 
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean
index 808d09f27ad4..17ef94c635cd 100644
--- a/scripts/Makefile.clean
+++ b/scripts/Makefile.clean
@@ -88,7 +88,4 @@ PHONY += $(subdir-ymn)
 $(subdir-ymn):
 	$(Q)$(MAKE) $(clean)=$@
 
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.modbuiltin b/scripts/Makefile.modbuiltin
index a763b4775d06..40867a41615b 100644
--- a/scripts/Makefile.modbuiltin
+++ b/scripts/Makefile.modbuiltin
@@ -54,8 +54,4 @@ PHONY += $(subdir-ym)
 $(subdir-ym):
 	$(Q)$(MAKE) $(modbuiltin)=$@
 
-
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
index 51ca0244fc8a..ff5ca9817a85 100644
--- a/scripts/Makefile.modinst
+++ b/scripts/Makefile.modinst
@@ -35,8 +35,4 @@ modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
 $(modules):
 	$(call cmd,modules_install,$(MODLIB)/$(modinst_dir))
 
-
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable so we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index df4174405feb..dd92dbbbaa68 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -149,8 +149,4 @@ ifneq ($(cmd_files),)
   include $(cmd_files)
 endif
 
-
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.modsign b/scripts/Makefile.modsign
index 171483bc0538..da56aa78d245 100644
--- a/scripts/Makefile.modsign
+++ b/scripts/Makefile.modsign
@@ -27,7 +27,4 @@ modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
 $(modules):
 	$(call cmd,sign_ko,$(MODLIB)/$(modinst_dir))
 
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan
index b593b36ccff8..38b2b4818e8e 100644
--- a/scripts/Makefile.ubsan
+++ b/scripts/Makefile.ubsan
@@ -14,10 +14,6 @@ ifdef CONFIG_UBSAN_ALIGNMENT
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=alignment)
 endif
 
-ifdef CONFIG_UBSAN_NULL
-      CFLAGS_UBSAN += $(call cc-option, -fsanitize=null)
-endif
-
       # -fsanitize=* options makes GCC less smart than usual and
       # increase number of 'maybe-uninitialized false-positives
       CFLAGS_UBSAN += $(call cc-option, -Wno-maybe-uninitialized)
diff --git a/scripts/cc-can-link.sh b/scripts/cc-can-link.sh
index 208eb2825dab..6efcead31989 100755
--- a/scripts/cc-can-link.sh
+++ b/scripts/cc-can-link.sh
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 && echo "y"
+cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1
 #include <stdio.h>
 int main(void)
 {
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index e3b7362b0ee4..447857ffaf6b 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2606,12 +2606,6 @@ sub process {
 			     "A patch subject line should describe the change not the tool that found it\n" . $herecurr);
 		}
 
-# Check for old stable address
-		if ($line =~ /^\s*cc:\s*.*<?\bstable\@kernel\.org\b>?.*$/i) {
-			ERROR("STABLE_ADDRESS",
-			      "The 'stable' address should be 'stable\@vger.kernel.org'\n" . $herecurr);
-		}
-
 # Check for unwanted Gerrit info
 		if ($in_commit_log && $line =~ /^\s*change-id:/i) {
 			ERROR("GERRIT_CHANGE_ID",
@@ -5819,14 +5813,14 @@ sub process {
 		    defined $stat &&
 		    $stat =~ /^\+(?![^\{]*\{\s*).*\b(\w+)\s*\(.*$String\s*,/s &&
 		    $1 !~ /^_*volatile_*$/) {
-			my $specifier;
-			my $extension;
-			my $bad_specifier = "";
 			my $stat_real;
 
 			my $lc = $stat =~ tr@\n@@;
 			$lc = $lc + $linenr;
 		        for (my $count = $linenr; $count <= $lc; $count++) {
+				my $specifier;
+				my $extension;
+				my $bad_specifier = "";
 				my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0));
 				$fmt =~ s/%%//g;
 
diff --git a/scripts/documentation-file-ref-check b/scripts/documentation-file-ref-check
index 078999a3fdff..ad9db6821824 100755
--- a/scripts/documentation-file-ref-check
+++ b/scripts/documentation-file-ref-check
@@ -75,6 +75,12 @@ while (<IN>) {
 		# Remove URL false-positives
 		next if ($fulref =~ m/^http/);
 
+		# Remove sched-pelt false-positive
+		next if ($fulref =~ m,^Documentation/scheduler/sched-pelt$,);
+
+		# Discard some build examples from Documentation/target/tcm_mod_builder.txt
+		next if ($fulref =~ m,mnt/sdb/lio-core-2.6.git/Documentation/target,);
+
 		# Check if exists, evaluating wildcards
 		next if (grep -e, glob("$ref $fulref"));
 
diff --git a/scripts/extract-vmlinux b/scripts/extract-vmlinux
index 5061abcc2540..e6239f39abad 100755
--- a/scripts/extract-vmlinux
+++ b/scripts/extract-vmlinux
@@ -57,6 +57,8 @@ try_decompress '\3757zXZ\000' abcde unxz
 try_decompress 'BZh'          xy    bunzip2
 try_decompress '\135\0\0\0'   xxx   unlzma
 try_decompress '\211\114\132' xy    'lzop -d'
+try_decompress '\002!L\030'   xxx   'lz4 -d'
+try_decompress '(\265/\375'   xxx   unzstd
 
 # Bail out:
 echo "$me: Cannot find vmlinux." >&2
diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
index 3755af0cd9f7..75e4e22b986a 100755
--- a/scripts/gcc-x86_64-has-stack-protector.sh
+++ b/scripts/gcc-x86_64-has-stack-protector.sh
@@ -1,4 +1,4 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
+echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index 94a383b21df6..f63b41b0dd49 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -171,6 +171,9 @@ struct symbol {
  * config BAZ
  *         int "BAZ Value"
  *         range 1..255
+ *
+ * Please, also check zconf.y:print_symbol() when modifying the
+ * list of property types!
  */
 enum prop_type {
 	P_UNKNOWN,
diff --git a/scripts/kconfig/preprocess.c b/scripts/kconfig/preprocess.c
index 65da87fce907..5ca2df790d3c 100644
--- a/scripts/kconfig/preprocess.c
+++ b/scripts/kconfig/preprocess.c
@@ -156,7 +156,7 @@ static char *do_shell(int argc, char *argv[])
 		nread--;
 
 	/* remove trailing new lines */
-	while (buf[nread - 1] == '\n')
+	while (nread > 0 && buf[nread - 1] == '\n')
 		nread--;
 
 	buf[nread] = 0;
diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y
index 6f9b0aa32a82..4b68272ebdb9 100644
--- a/scripts/kconfig/zconf.y
+++ b/scripts/kconfig/zconf.y
@@ -31,7 +31,7 @@ struct symbol *symbol_hash[SYMBOL_HASHSIZE];
 static struct menu *current_menu, *current_entry;
 
 %}
-%expect 32
+%expect 31
 
 %union
 {
@@ -337,7 +337,7 @@ choice_block:
 
 /* if entry */
 
-if_entry: T_IF expr nl
+if_entry: T_IF expr T_EOL
 {
 	printd(DEBUG_PARSE, "%s:%d:if\n", zconf_curname(), zconf_lineno());
 	menu_add_entry(NULL);
@@ -717,6 +717,10 @@ static void print_symbol(FILE *out, struct menu *menu)
 			print_quoted_string(out, prop->text);
 			fputc('\n', out);
 			break;
+		case P_SYMBOL:
+			fputs( "  symbol ", out);
+			fprintf(out, "%s\n", prop->sym->name);
+			break;
 		default:
 			fprintf(out, "  unknown prop %d!\n", prop->type);
 			break;
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 0057d8eafcc1..8f0f508a78e9 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1062,7 +1062,7 @@ sub dump_struct($$) {
     my $x = shift;
     my $file = shift;
 
-    if ($x =~ /(struct|union)\s+(\w+)\s*{(.*)}/) {
+    if ($x =~ /(struct|union)\s+(\w+)\s*\{(.*)\}/) {
 	my $decl_type = $1;
 	$declaration_name = $2;
 	my $members = $3;
@@ -1148,20 +1148,20 @@ sub dump_struct($$) {
 				}
 			}
 		}
-		$members =~ s/(struct|union)([^\{\};]+)\{([^\{\}]*)}([^\{\}\;]*)\;/$newmember/;
+		$members =~ s/(struct|union)([^\{\};]+)\{([^\{\}]*)\}([^\{\}\;]*)\;/$newmember/;
 	}
 
 	# Ignore other nested elements, like enums
-	$members =~ s/({[^\{\}]*})//g;
+	$members =~ s/(\{[^\{\}]*\})//g;
 
 	create_parameterlist($members, ';', $file, $declaration_name);
 	check_sections($file, $declaration_name, $decl_type, $sectcheck, $struct_actual);
 
 	# Adjust declaration for better display
-	$declaration =~ s/([{;])/$1\n/g;
-	$declaration =~ s/}\s+;/};/g;
+	$declaration =~ s/([\{;])/$1\n/g;
+	$declaration =~ s/\}\s+;/};/g;
 	# Better handle inlined enums
-	do {} while ($declaration =~ s/(enum\s+{[^}]+),([^\n])/$1,\n$2/);
+	do {} while ($declaration =~ s/(enum\s+\{[^\}]+),([^\n])/$1,\n$2/);
 
 	my @def_args = split /\n/, $declaration;
 	my $level = 1;
@@ -1171,12 +1171,12 @@ sub dump_struct($$) {
 		$clause =~ s/\s+$//;
 		$clause =~ s/\s+/ /;
 		next if (!$clause);
-		$level-- if ($clause =~ m/(})/ && $level > 1);
+		$level-- if ($clause =~ m/(\})/ && $level > 1);
 		if (!($clause =~ m/^\s*#/)) {
 			$declaration .= "\t" x $level;
 		}
 		$declaration .= "\t" . $clause . "\n";
-		$level++ if ($clause =~ m/({)/ && !($clause =~m/}/));
+		$level++ if ($clause =~ m/(\{)/ && !($clause =~m/\}/));
 	}
 	output_declaration($declaration_name,
 			   'struct',
@@ -1244,7 +1244,7 @@ sub dump_enum($$) {
     # strip #define macros inside enums
     $x =~ s@#\s*((define|ifdef)\s+|endif)[^;]*;@@gos;
 
-    if ($x =~ /enum\s+(\w+)\s*{(.*)}/) {
+    if ($x =~ /enum\s+(\w+)\s*\{(.*)\}/) {
 	$declaration_name = $1;
 	my $members = $2;
 	my %_members;
@@ -1785,7 +1785,7 @@ sub process_proto_type($$) {
     }
 
     while (1) {
-	if ( $x =~ /([^{};]*)([{};])(.*)/ ) {
+	if ( $x =~ /([^\{\};]*)([\{\};])(.*)/ ) {
             if( length $prototype ) {
                 $prototype .= " "
             }
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 66f08bb1cce9..26de7d5aa5c8 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -152,6 +152,7 @@ regex_asm=(
 )
 regex_c=(
 	'/^SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/sys_\1/'
+	'/^BPF_CALL_[0-9](\([[:alnum:]_]*\).*/\1/'
 	'/^COMPAT_SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/compat_sys_\1/'
 	'/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1/'
 	'/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1_rcuidle/'
@@ -245,7 +246,7 @@ exuberant()
 {
 	setup_regex exuberant asm c
 	all_target_sources | xargs $1 -a                        \
-	-I __initdata,__exitdata,__initconst,			\
+	-I __initdata,__exitdata,__initconst,__ro_after_init	\
 	-I __initdata_memblock					\
 	-I __refdata,__attribute,__maybe_unused,__always_unused \
 	-I __acquires,__releases,__deprecated			\
diff --git a/security/Kconfig b/security/Kconfig
index c4302067a3ad..27d8b2688f75 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -57,7 +57,7 @@ config SECURITY_NETWORK
 config PAGE_TABLE_ISOLATION
 	bool "Remove the kernel mapping in user mode"
 	default y
-	depends on X86_64 && !UML
+	depends on X86 && !UML
 	help
 	  This feature reduces the number of hardware side channels by
 	  ensuring that the majority of kernel addresses are not mapped
@@ -153,7 +153,6 @@ config HAVE_HARDENED_USERCOPY_ALLOCATOR
 config HARDENED_USERCOPY
 	bool "Harden memory copies between kernel and userspace"
 	depends on HAVE_HARDENED_USERCOPY_ALLOCATOR
-	select BUG
 	imply STRICT_DEVMEM
 	help
 	  This option checks for obviously wrong memory regions when
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 74f17376202b..8b8b70620bbe 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -395,7 +395,7 @@ static int apparmor_inode_getattr(const struct path *path)
 	return common_perm_cond(OP_GETATTR, path, AA_MAY_GETATTR);
 }
 
-static int apparmor_file_open(struct file *file, const struct cred *cred)
+static int apparmor_file_open(struct file *file)
 {
 	struct aa_file_ctx *fctx = file_ctx(file);
 	struct aa_label *label;
@@ -414,7 +414,7 @@ static int apparmor_file_open(struct file *file, const struct cred *cred)
 		return 0;
 	}
 
-	label = aa_get_newest_cred_label(cred);
+	label = aa_get_newest_cred_label(file->f_cred);
 	if (!unconfined(label)) {
 		struct inode *inode = file_inode(file);
 		struct path_cond cond = { inode->i_uid, inode->i_mode };
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 78c15264b17b..a597b2795d2d 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -239,7 +239,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 			     struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len, int opened);
+			     int xattr_len);
 int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
 void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
 enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
@@ -255,7 +255,7 @@ static inline int ima_appraise_measurement(enum ima_hooks func,
 					   struct file *file,
 					   const unsigned char *filename,
 					   struct evm_ima_xattr_data *xattr_value,
-					   int xattr_len, int opened)
+					   int xattr_len)
 {
 	return INTEGRITY_UNKNOWN;
 }
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 8bd7a0733e51..deec1804a00a 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -212,7 +212,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 			     struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len, int opened)
+			     int xattr_len)
 {
 	static const char op[] = "appraise_data";
 	const char *cause = "unknown";
@@ -231,7 +231,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 		cause = iint->flags & IMA_DIGSIG_REQUIRED ?
 				"IMA-signature-required" : "missing-hash";
 		status = INTEGRITY_NOLABEL;
-		if (opened & FILE_CREATED)
+		if (file->f_mode & FMODE_CREATED)
 			iint->flags |= IMA_NEW_FILE;
 		if ((iint->flags & IMA_NEW_FILE) &&
 		    (!(iint->flags & IMA_DIGSIG_REQUIRED) ||
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index dce0a8a217bb..2d31921fbda4 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -168,7 +168,7 @@ void ima_file_free(struct file *file)
 
 static int process_measurement(struct file *file, const struct cred *cred,
 			       u32 secid, char *buf, loff_t size, int mask,
-			       enum ima_hooks func, int opened)
+			       enum ima_hooks func)
 {
 	struct inode *inode = file_inode(file);
 	struct integrity_iint_cache *iint = NULL;
@@ -294,7 +294,7 @@ static int process_measurement(struct file *file, const struct cred *cred,
 	if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) {
 		inode_lock(inode);
 		rc = ima_appraise_measurement(func, iint, file, pathname,
-					      xattr_value, xattr_len, opened);
+					      xattr_value, xattr_len);
 		inode_unlock(inode);
 	}
 	if (action & IMA_AUDIT)
@@ -338,7 +338,7 @@ int ima_file_mmap(struct file *file, unsigned long prot)
 	if (file && (prot & PROT_EXEC)) {
 		security_task_getsecid(current, &secid);
 		return process_measurement(file, current_cred(), secid, NULL,
-					   0, MAY_EXEC, MMAP_CHECK, 0);
+					   0, MAY_EXEC, MMAP_CHECK);
 	}
 
 	return 0;
@@ -364,13 +364,13 @@ int ima_bprm_check(struct linux_binprm *bprm)
 
 	security_task_getsecid(current, &secid);
 	ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0,
-				  MAY_EXEC, BPRM_CHECK, 0);
+				  MAY_EXEC, BPRM_CHECK);
 	if (ret)
 		return ret;
 
 	security_cred_getsecid(bprm->cred, &secid);
 	return process_measurement(bprm->file, bprm->cred, secid, NULL, 0,
-				   MAY_EXEC, CREDS_CHECK, 0);
+				   MAY_EXEC, CREDS_CHECK);
 }
 
 /**
@@ -383,14 +383,14 @@ int ima_bprm_check(struct linux_binprm *bprm)
  * On success return 0.  On integrity appraisal error, assuming the file
  * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
  */
-int ima_file_check(struct file *file, int mask, int opened)
+int ima_file_check(struct file *file, int mask)
 {
 	u32 secid;
 
 	security_task_getsecid(current, &secid);
 	return process_measurement(file, current_cred(), secid, NULL, 0,
 				   mask & (MAY_READ | MAY_WRITE | MAY_EXEC |
-					   MAY_APPEND), FILE_CHECK, opened);
+					   MAY_APPEND), FILE_CHECK);
 }
 EXPORT_SYMBOL_GPL(ima_file_check);
 
@@ -490,7 +490,7 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
 	func = read_idmap[read_id] ?: FILE_CHECK;
 	security_task_getsecid(current, &secid);
 	return process_measurement(file, current_cred(), secid, buf, size,
-				   MAY_READ, func, 0);
+				   MAY_READ, func);
 }
 
 /**
diff --git a/security/keys/dh.c b/security/keys/dh.c
index f7403821db7f..b203f7758f97 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -142,6 +142,8 @@ static void kdf_dealloc(struct kdf_sdesc *sdesc)
  * The src pointer is defined as Z || other info where Z is the shared secret
  * from DH and other info is an arbitrary string (see SP800-56A section
  * 5.8.1.2).
+ *
+ * 'dlen' must be a multiple of the digest size.
  */
 static int kdf_ctr(struct kdf_sdesc *sdesc, const u8 *src, unsigned int slen,
 		   u8 *dst, unsigned int dlen, unsigned int zlen)
@@ -205,8 +207,8 @@ static int keyctl_dh_compute_kdf(struct kdf_sdesc *sdesc,
 {
 	uint8_t *outbuf = NULL;
 	int ret;
-	size_t outbuf_len = round_up(buflen,
-			             crypto_shash_digestsize(sdesc->shash.tfm));
+	size_t outbuf_len = roundup(buflen,
+				    crypto_shash_digestsize(sdesc->shash.tfm));
 
 	outbuf = kmalloc(outbuf_len, GFP_KERNEL);
 	if (!outbuf) {
diff --git a/security/security.c b/security/security.c
index b49ee810371b..ab4f96347ebb 100644
--- a/security/security.c
+++ b/security/security.c
@@ -972,11 +972,11 @@ int security_file_receive(struct file *file)
 	return call_int_hook(file_receive, 0, file);
 }
 
-int security_file_open(struct file *file, const struct cred *cred)
+int security_file_open(struct file *file)
 {
 	int ret;
 
-	ret = call_int_hook(file_open, 0, file, cred);
+	ret = call_int_hook(file_open, 0, file);
 	if (ret)
 		return ret;
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a8bf324130f5..589c6b4023ce 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3862,7 +3862,7 @@ static int selinux_file_receive(struct file *file)
 	return file_has_perm(cred, file, file_to_av(file));
 }
 
-static int selinux_file_open(struct file *file, const struct cred *cred)
+static int selinux_file_open(struct file *file)
 {
 	struct file_security_struct *fsec;
 	struct inode_security_struct *isec;
@@ -3886,7 +3886,7 @@ static int selinux_file_open(struct file *file, const struct cred *cred)
 	 * new inode label or new policy.
 	 * This check is not redundant - do not remove.
 	 */
-	return file_path_has_perm(cred, file, open_file_to_av(file));
+	return file_path_has_perm(file->f_cred, file, open_file_to_av(file));
 }
 
 /* task security operations */
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index f3d374d2ca04..79d3709b0671 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -441,22 +441,16 @@ static int sel_release_policy(struct inode *inode, struct file *filp)
 static ssize_t sel_read_policy(struct file *filp, char __user *buf,
 			       size_t count, loff_t *ppos)
 {
-	struct selinux_fs_info *fsi = file_inode(filp)->i_sb->s_fs_info;
 	struct policy_load_memory *plm = filp->private_data;
 	int ret;
 
-	mutex_lock(&fsi->mutex);
-
 	ret = avc_has_perm(&selinux_state,
 			   current_sid(), SECINITSID_SECURITY,
 			  SECCLASS_SECURITY, SECURITY__READ_POLICY, NULL);
 	if (ret)
-		goto out;
+		return ret;
 
-	ret = simple_read_from_buffer(buf, count, ppos, plm->data, plm->len);
-out:
-	mutex_unlock(&fsi->mutex);
-	return ret;
+	return simple_read_from_buffer(buf, count, ppos, plm->data, plm->len);
 }
 
 static vm_fault_t sel_mmap_policy_fault(struct vm_fault *vmf)
@@ -1188,25 +1182,29 @@ static ssize_t sel_read_bool(struct file *filep, char __user *buf,
 	ret = -EINVAL;
 	if (index >= fsi->bool_num || strcmp(name,
 					     fsi->bool_pending_names[index]))
-		goto out;
+		goto out_unlock;
 
 	ret = -ENOMEM;
 	page = (char *)get_zeroed_page(GFP_KERNEL);
 	if (!page)
-		goto out;
+		goto out_unlock;
 
 	cur_enforcing = security_get_bool_value(fsi->state, index);
 	if (cur_enforcing < 0) {
 		ret = cur_enforcing;
-		goto out;
+		goto out_unlock;
 	}
 	length = scnprintf(page, PAGE_SIZE, "%d %d", cur_enforcing,
 			  fsi->bool_pending_values[index]);
-	ret = simple_read_from_buffer(buf, count, ppos, page, length);
-out:
 	mutex_unlock(&fsi->mutex);
+	ret = simple_read_from_buffer(buf, count, ppos, page, length);
+out_free:
 	free_page((unsigned long)page);
 	return ret;
+
+out_unlock:
+	mutex_unlock(&fsi->mutex);
+	goto out_free;
 }
 
 static ssize_t sel_write_bool(struct file *filep, const char __user *buf,
@@ -1219,6 +1217,17 @@ static ssize_t sel_write_bool(struct file *filep, const char __user *buf,
 	unsigned index = file_inode(filep)->i_ino & SEL_INO_MASK;
 	const char *name = filep->f_path.dentry->d_name.name;
 
+	if (count >= PAGE_SIZE)
+		return -ENOMEM;
+
+	/* No partial writes. */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
 	mutex_lock(&fsi->mutex);
 
 	length = avc_has_perm(&selinux_state,
@@ -1233,22 +1242,6 @@ static ssize_t sel_write_bool(struct file *filep, const char __user *buf,
 					     fsi->bool_pending_names[index]))
 		goto out;
 
-	length = -ENOMEM;
-	if (count >= PAGE_SIZE)
-		goto out;
-
-	/* No partial writes. */
-	length = -EINVAL;
-	if (*ppos != 0)
-		goto out;
-
-	page = memdup_user_nul(buf, count);
-	if (IS_ERR(page)) {
-		length = PTR_ERR(page);
-		page = NULL;
-		goto out;
-	}
-
 	length = -EINVAL;
 	if (sscanf(page, "%d", &new_value) != 1)
 		goto out;
@@ -1280,6 +1273,17 @@ static ssize_t sel_commit_bools_write(struct file *filep,
 	ssize_t length;
 	int new_value;
 
+	if (count >= PAGE_SIZE)
+		return -ENOMEM;
+
+	/* No partial writes. */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
 	mutex_lock(&fsi->mutex);
 
 	length = avc_has_perm(&selinux_state,
@@ -1289,22 +1293,6 @@ static ssize_t sel_commit_bools_write(struct file *filep,
 	if (length)
 		goto out;
 
-	length = -ENOMEM;
-	if (count >= PAGE_SIZE)
-		goto out;
-
-	/* No partial writes. */
-	length = -EINVAL;
-	if (*ppos != 0)
-		goto out;
-
-	page = memdup_user_nul(buf, count);
-	if (IS_ERR(page)) {
-		length = PTR_ERR(page);
-		page = NULL;
-		goto out;
-	}
-
 	length = -EINVAL;
 	if (sscanf(page, "%d", &new_value) != 1)
 		goto out;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 7ad226018f51..9ab8097dab7c 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1927,9 +1927,9 @@ static int smack_file_receive(struct file *file)
  *
  * Returns 0
  */
-static int smack_file_open(struct file *file, const struct cred *cred)
+static int smack_file_open(struct file *file)
 {
-	struct task_smack *tsp = cred->security;
+	struct task_smack *tsp = file->f_cred->security;
 	struct inode *inode = file_inode(file);
 	struct smk_audit_info ad;
 	int rc;
@@ -1937,7 +1937,7 @@ static int smack_file_open(struct file *file, const struct cred *cred)
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 	smk_ad_setfield_u_fs_path(&ad, file->f_path);
 	rc = smk_tskacc(tsp, smk_of_inode(inode), MAY_READ, &ad);
-	rc = smk_bu_credfile(cred, file, MAY_READ, rc);
+	rc = smk_bu_credfile(file->f_cred, file, MAY_READ, rc);
 
 	return rc;
 }
@@ -2296,6 +2296,7 @@ static void smack_task_to_inode(struct task_struct *p, struct inode *inode)
 	struct smack_known *skp = smk_of_task_struct(p);
 
 	isp->smk_inode = skp;
+	isp->smk_flags |= SMK_INODE_INSTANT;
 }
 
 /*
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index 213b8c593668..9f932e2d6852 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -320,7 +320,7 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd,
  *
  * Returns 0 on success, negative value otherwise.
  */
-static int tomoyo_file_open(struct file *f, const struct cred *cred)
+static int tomoyo_file_open(struct file *f)
 {
 	int flags = f->f_flags;
 	/* Don't check read permission here if called from do_execve(). */
diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c
index 31f858eceffc..7a0dfca03a57 100644
--- a/sound/ac97/bus.c
+++ b/sound/ac97/bus.c
@@ -13,6 +13,7 @@
 #include <linux/idr.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
+#include <linux/of.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
@@ -68,6 +69,27 @@ ac97_codec_find(struct ac97_controller *ac97_ctrl, unsigned int codec_num)
 	return ac97_ctrl->codecs[codec_num];
 }
 
+static struct device_node *
+ac97_of_get_child_device(struct ac97_controller *ac97_ctrl, int idx,
+			 unsigned int vendor_id)
+{
+	struct device_node *node;
+	u32 reg;
+	char compat[] = "ac97,0000,0000";
+
+	snprintf(compat, sizeof(compat), "ac97,%04x,%04x",
+		 vendor_id >> 16, vendor_id & 0xffff);
+
+	for_each_child_of_node(ac97_ctrl->parent->of_node, node) {
+		if ((idx != of_property_read_u32(node, "reg", &reg)) ||
+		    !of_device_is_compatible(node, compat))
+			continue;
+		return of_node_get(node);
+	}
+
+	return NULL;
+}
+
 static void ac97_codec_release(struct device *dev)
 {
 	struct ac97_codec_device *adev;
@@ -76,6 +98,7 @@ static void ac97_codec_release(struct device *dev)
 	adev = to_ac97_device(dev);
 	ac97_ctrl = adev->ac97_ctrl;
 	ac97_ctrl->codecs[adev->num] = NULL;
+	of_node_put(dev->of_node);
 	kfree(adev);
 }
 
@@ -98,6 +121,8 @@ static int ac97_codec_add(struct ac97_controller *ac97_ctrl, int idx,
 
 	device_initialize(&codec->dev);
 	dev_set_name(&codec->dev, "%s:%u", dev_name(ac97_ctrl->parent), idx);
+	codec->dev.of_node = ac97_of_get_child_device(ac97_ctrl, idx,
+						      vendor_id);
 
 	ret = device_add(&codec->dev);
 	if (ret)
@@ -105,6 +130,7 @@ static int ac97_codec_add(struct ac97_controller *ac97_ctrl, int idx,
 
 	return 0;
 err_free_codec:
+	of_node_put(codec->dev.of_node);
 	put_device(&codec->dev);
 	kfree(codec);
 	ac97_ctrl->codecs[idx] = NULL;
diff --git a/sound/aoa/core/gpio-feature.c b/sound/aoa/core/gpio-feature.c
index 71960089e207..65557421fe0b 100644
--- a/sound/aoa/core/gpio-feature.c
+++ b/sound/aoa/core/gpio-feature.c
@@ -88,8 +88,10 @@ static struct device_node *get_gpio(char *name,
 	}
 
 	reg = of_get_property(np, "reg", NULL);
-	if (!reg)
+	if (!reg) {
+		of_node_put(np);
 		return NULL;
+	}
 
 	*gpioptr = *reg;
 
diff --git a/sound/arm/Kconfig b/sound/arm/Kconfig
index 65171f6657a2..5fbd47a9177e 100644
--- a/sound/arm/Kconfig
+++ b/sound/arm/Kconfig
@@ -17,14 +17,9 @@ config SND_ARMAACI
 	select SND_PCM
 	select SND_AC97_CODEC
 
-config SND_PXA2XX_PCM
-	tristate
-	select SND_PCM
-
 config SND_PXA2XX_AC97
 	tristate "AC97 driver for the Intel PXA2xx chip"
 	depends on ARCH_PXA
-	select SND_PXA2XX_PCM
 	select SND_AC97_CODEC
 	select SND_PXA2XX_LIB
 	select SND_PXA2XX_LIB_AC97
diff --git a/sound/arm/Makefile b/sound/arm/Makefile
index e10d5b169565..34c769489877 100644
--- a/sound/arm/Makefile
+++ b/sound/arm/Makefile
@@ -6,9 +6,6 @@
 obj-$(CONFIG_SND_ARMAACI)	+= snd-aaci.o
 snd-aaci-objs			:= aaci.o
 
-obj-$(CONFIG_SND_PXA2XX_PCM)	+= snd-pxa2xx-pcm.o
-snd-pxa2xx-pcm-objs		:= pxa2xx-pcm.o
-
 obj-$(CONFIG_SND_PXA2XX_LIB)	+= snd-pxa2xx-lib.o
 snd-pxa2xx-lib-y		:= pxa2xx-pcm-lib.o
 snd-pxa2xx-lib-$(CONFIG_SND_PXA2XX_LIB_AC97)	+= pxa2xx-ac97-lib.o
diff --git a/sound/arm/pxa2xx-ac97-lib.c b/sound/arm/pxa2xx-ac97-lib.c
index 5950a9e218d9..8eafd3d3dff6 100644
--- a/sound/arm/pxa2xx-ac97-lib.c
+++ b/sound/arm/pxa2xx-ac97-lib.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
+#include <linux/of_gpio.h>
 
 #include <sound/pxa2xx-lib.h>
 
@@ -337,6 +338,17 @@ int pxa2xx_ac97_hw_probe(struct platform_device *dev)
 			dev_err(&dev->dev, "Invalid reset GPIO %d\n",
 				pdata->reset_gpio);
 		}
+	} else if (!pdata && dev->dev.of_node) {
+		pdata = devm_kzalloc(&dev->dev, sizeof(*pdata), GFP_KERNEL);
+		if (!pdata)
+			return -ENOMEM;
+		pdata->reset_gpio = of_get_named_gpio(dev->dev.of_node,
+						      "reset-gpios", 0);
+		if (pdata->reset_gpio == -ENOENT)
+			pdata->reset_gpio = -1;
+		else if (pdata->reset_gpio < 0)
+			return pdata->reset_gpio;
+		reset_gpio = pdata->reset_gpio;
 	} else {
 		if (cpu_is_pxa27x())
 			reset_gpio = 113;
diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index 4bc244c40f80..1f72672262d0 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/dmaengine.h>
-#include <linux/dma/pxa-dma.h>
+#include <linux/dma-mapping.h>
 
 #include <sound/core.h>
 #include <sound/pcm.h>
@@ -27,8 +27,6 @@
 #include <mach/regs-ac97.h>
 #include <mach/audio.h>
 
-#include "pxa2xx-pcm.h"
-
 static void pxa2xx_ac97_legacy_reset(struct snd_ac97 *ac97)
 {
 	if (!pxa2xx_ac97_try_cold_reset())
@@ -63,61 +61,46 @@ static struct snd_ac97_bus_ops pxa2xx_ac97_ops = {
 	.reset	= pxa2xx_ac97_legacy_reset,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_out_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 12,
-};
-
-static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_out = {
-	.addr		= __PREG(PCDR),
-	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
-	.maxburst	= 32,
-	.filter_data	= &pxa2xx_ac97_pcm_out_req,
-};
-
-static struct pxad_param pxa2xx_ac97_pcm_in_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 11,
-};
-
-static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_in = {
-	.addr		= __PREG(PCDR),
-	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
-	.maxburst	= 32,
-	.filter_data	= &pxa2xx_ac97_pcm_in_req,
-};
-
 static struct snd_pcm *pxa2xx_ac97_pcm;
 static struct snd_ac97 *pxa2xx_ac97_ac97;
 
-static int pxa2xx_ac97_pcm_startup(struct snd_pcm_substream *substream)
+static int pxa2xx_ac97_pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	pxa2xx_audio_ops_t *platform_ops;
-	int r;
+	int ret, i;
+
+	ret = pxa2xx_pcm_open(substream);
+	if (ret)
+		return ret;
 
 	runtime->hw.channels_min = 2;
 	runtime->hw.channels_max = 2;
 
-	r = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
-	    AC97_RATES_FRONT_DAC : AC97_RATES_ADC;
-	runtime->hw.rates = pxa2xx_ac97_ac97->rates[r];
+	i = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
+		AC97_RATES_FRONT_DAC : AC97_RATES_ADC;
+	runtime->hw.rates = pxa2xx_ac97_ac97->rates[i];
 	snd_pcm_limit_hw_rates(runtime);
 
-       	platform_ops = substream->pcm->card->dev->platform_data;
-	if (platform_ops && platform_ops->startup)
-		return platform_ops->startup(substream, platform_ops->priv);
-	else
-		return 0;
+	platform_ops = substream->pcm->card->dev->platform_data;
+	if (platform_ops && platform_ops->startup) {
+		ret = platform_ops->startup(substream, platform_ops->priv);
+		if (ret < 0)
+			pxa2xx_pcm_close(substream);
+	}
+
+	return ret;
 }
 
-static void pxa2xx_ac97_pcm_shutdown(struct snd_pcm_substream *substream)
+static int pxa2xx_ac97_pcm_close(struct snd_pcm_substream *substream)
 {
 	pxa2xx_audio_ops_t *platform_ops;
 
-       	platform_ops = substream->pcm->card->dev->platform_data;
+	platform_ops = substream->pcm->card->dev->platform_data;
 	if (platform_ops && platform_ops->shutdown)
 		platform_ops->shutdown(substream, platform_ops->priv);
+
+	return 0;
 }
 
 static int pxa2xx_ac97_pcm_prepare(struct snd_pcm_substream *substream)
@@ -125,17 +108,15 @@ static int pxa2xx_ac97_pcm_prepare(struct snd_pcm_substream *substream)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	int reg = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
 		  AC97_PCM_FRONT_DAC_RATE : AC97_PCM_LR_ADC_RATE;
+	int ret;
+
+	ret = pxa2xx_pcm_prepare(substream);
+	if (ret < 0)
+		return ret;
+
 	return snd_ac97_set_rate(pxa2xx_ac97_ac97, reg, runtime->rate);
 }
 
-static struct pxa2xx_pcm_client pxa2xx_ac97_pcm_client = {
-	.playback_params	= &pxa2xx_ac97_pcm_out,
-	.capture_params		= &pxa2xx_ac97_pcm_in,
-	.startup		= pxa2xx_ac97_pcm_startup,
-	.shutdown		= pxa2xx_ac97_pcm_shutdown,
-	.prepare		= pxa2xx_ac97_pcm_prepare,
-};
-
 #ifdef CONFIG_PM_SLEEP
 
 static int pxa2xx_ac97_do_suspend(struct snd_card *card)
@@ -193,6 +174,53 @@ static int pxa2xx_ac97_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(pxa2xx_ac97_pm_ops, pxa2xx_ac97_suspend, pxa2xx_ac97_resume);
 #endif
 
+static const struct snd_pcm_ops pxa2xx_ac97_pcm_ops = {
+	.open		= pxa2xx_ac97_pcm_open,
+	.close		= pxa2xx_ac97_pcm_close,
+	.ioctl		= snd_pcm_lib_ioctl,
+	.hw_params	= pxa2xx_pcm_hw_params,
+	.hw_free	= pxa2xx_pcm_hw_free,
+	.prepare	= pxa2xx_ac97_pcm_prepare,
+	.trigger	= pxa2xx_pcm_trigger,
+	.pointer	= pxa2xx_pcm_pointer,
+	.mmap		= pxa2xx_pcm_mmap,
+};
+
+
+static int pxa2xx_ac97_pcm_new(struct snd_card *card)
+{
+	struct snd_pcm *pcm;
+	int stream, ret;
+
+	ret = snd_pcm_new(card, "PXA2xx-PCM", 0, 1, 1, &pcm);
+	if (ret)
+		goto out;
+
+	pcm->private_free = pxa2xx_pcm_free_dma_buffers;
+
+	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
+	if (ret)
+		goto out;
+
+	stream = SNDRV_PCM_STREAM_PLAYBACK;
+	snd_pcm_set_ops(pcm, stream, &pxa2xx_ac97_pcm_ops);
+	ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
+	if (ret)
+		goto out;
+
+	stream = SNDRV_PCM_STREAM_CAPTURE;
+	snd_pcm_set_ops(pcm, stream, &pxa2xx_ac97_pcm_ops);
+	ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
+	if (ret)
+		goto out;
+
+	pxa2xx_ac97_pcm = pcm;
+	ret = 0;
+
+ out:
+	return ret;
+}
+
 static int pxa2xx_ac97_probe(struct platform_device *dev)
 {
 	struct snd_card *card;
@@ -214,7 +242,7 @@ static int pxa2xx_ac97_probe(struct platform_device *dev)
 
 	strlcpy(card->driver, dev->dev.driver->name, sizeof(card->driver));
 
-	ret = pxa2xx_pcm_new(card, &pxa2xx_ac97_pcm_client, &pxa2xx_ac97_pcm);
+	ret = pxa2xx_ac97_pcm_new(card);
 	if (ret)
 		goto err;
 
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index e8da3b8ee721..7931789d4a9f 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -16,8 +16,6 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-#include "pxa2xx-pcm.h"
-
 static const struct snd_pcm_hardware pxa2xx_pcm_hardware = {
 	.info			= SNDRV_PCM_INFO_MMAP |
 				  SNDRV_PCM_INFO_MMAP_VALID |
@@ -25,8 +23,8 @@ static const struct snd_pcm_hardware pxa2xx_pcm_hardware = {
 				  SNDRV_PCM_INFO_PAUSE |
 				  SNDRV_PCM_INFO_RESUME,
 	.formats		= SNDRV_PCM_FMTBIT_S16_LE |
-					SNDRV_PCM_FMTBIT_S24_LE |
-					SNDRV_PCM_FMTBIT_S32_LE,
+				  SNDRV_PCM_FMTBIT_S24_LE |
+				  SNDRV_PCM_FMTBIT_S32_LE,
 	.period_bytes_min	= 32,
 	.period_bytes_max	= 8192 - 32,
 	.periods_min		= 1,
@@ -35,8 +33,8 @@ static const struct snd_pcm_hardware pxa2xx_pcm_hardware = {
 	.fifo_size		= 32,
 };
 
-int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
-				struct snd_pcm_hw_params *params)
+int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
+			 struct snd_pcm_hw_params *params)
 {
 	struct dma_chan *chan = snd_dmaengine_pcm_get_chan(substream);
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -64,14 +62,14 @@ int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
 
 	return 0;
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_hw_params);
+EXPORT_SYMBOL(pxa2xx_pcm_hw_params);
 
-int __pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream)
+int pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream)
 {
 	snd_pcm_set_runtime_buffer(substream, NULL);
 	return 0;
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_hw_free);
+EXPORT_SYMBOL(pxa2xx_pcm_hw_free);
 
 int pxa2xx_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 {
@@ -86,13 +84,13 @@ pxa2xx_pcm_pointer(struct snd_pcm_substream *substream)
 }
 EXPORT_SYMBOL(pxa2xx_pcm_pointer);
 
-int __pxa2xx_pcm_prepare(struct snd_pcm_substream *substream)
+int pxa2xx_pcm_prepare(struct snd_pcm_substream *substream)
 {
 	return 0;
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_prepare);
+EXPORT_SYMBOL(pxa2xx_pcm_prepare);
 
-int __pxa2xx_pcm_open(struct snd_pcm_substream *substream)
+int pxa2xx_pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -125,17 +123,17 @@ int __pxa2xx_pcm_open(struct snd_pcm_substream *substream)
 	if (ret < 0)
 		return ret;
 
-	return snd_dmaengine_pcm_open_request_chan(substream,
-					pxad_filter_fn,
-					dma_params->filter_data);
+	return snd_dmaengine_pcm_open(
+		substream, dma_request_slave_channel(rtd->cpu_dai->dev,
+						     dma_params->chan_name));
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_open);
+EXPORT_SYMBOL(pxa2xx_pcm_open);
 
-int __pxa2xx_pcm_close(struct snd_pcm_substream *substream)
+int pxa2xx_pcm_close(struct snd_pcm_substream *substream)
 {
 	return snd_dmaengine_pcm_close_release_chan(substream);
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_close);
+EXPORT_SYMBOL(pxa2xx_pcm_close);
 
 int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream,
 	struct vm_area_struct *vma)
@@ -181,6 +179,47 @@ void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm)
 }
 EXPORT_SYMBOL(pxa2xx_pcm_free_dma_buffers);
 
+int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_card *card = rtd->card->snd_card;
+	struct snd_pcm *pcm = rtd->pcm;
+	int ret;
+
+	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
+		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
+			SNDRV_PCM_STREAM_PLAYBACK);
+		if (ret)
+			goto out;
+	}
+
+	if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
+		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
+			SNDRV_PCM_STREAM_CAPTURE);
+		if (ret)
+			goto out;
+	}
+ out:
+	return ret;
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_new);
+
+const struct snd_pcm_ops pxa2xx_pcm_ops = {
+	.open		= pxa2xx_pcm_open,
+	.close		= pxa2xx_pcm_close,
+	.ioctl		= snd_pcm_lib_ioctl,
+	.hw_params	= pxa2xx_pcm_hw_params,
+	.hw_free	= pxa2xx_pcm_hw_free,
+	.prepare	= pxa2xx_pcm_prepare,
+	.trigger	= pxa2xx_pcm_trigger,
+	.pointer	= pxa2xx_pcm_pointer,
+	.mmap		= pxa2xx_pcm_mmap,
+};
+EXPORT_SYMBOL(pxa2xx_pcm_ops);
+
 MODULE_AUTHOR("Nicolas Pitre");
 MODULE_DESCRIPTION("Intel PXA2xx sound library");
 MODULE_LICENSE("GPL");
diff --git a/sound/arm/pxa2xx-pcm.c b/sound/arm/pxa2xx-pcm.c
deleted file mode 100644
index 1c6f4b436de3..000000000000
--- a/sound/arm/pxa2xx-pcm.c
+++ /dev/null
@@ -1,129 +0,0 @@
-/*
- * linux/sound/arm/pxa2xx-pcm.c -- ALSA PCM interface for the Intel PXA2xx chip
- *
- * Author:	Nicolas Pitre
- * Created:	Nov 30, 2004
- * Copyright:	(C) 2004 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-#include <linux/dmaengine.h>
-
-#include <mach/dma.h>
-
-#include <sound/core.h>
-#include <sound/pxa2xx-lib.h>
-#include <sound/dmaengine_pcm.h>
-
-#include "pxa2xx-pcm.h"
-
-static int pxa2xx_pcm_prepare(struct snd_pcm_substream *substream)
-{
-	struct pxa2xx_pcm_client *client = substream->private_data;
-
-	__pxa2xx_pcm_prepare(substream);
-
-	return client->prepare(substream);
-}
-
-static int pxa2xx_pcm_open(struct snd_pcm_substream *substream)
-{
-	struct pxa2xx_pcm_client *client = substream->private_data;
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct pxa2xx_runtime_data *rtd;
-	int ret;
-
-	ret = __pxa2xx_pcm_open(substream);
-	if (ret)
-		goto out;
-
-	rtd = runtime->private_data;
-
-	rtd->params = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
-		      client->playback_params : client->capture_params;
-
-	ret = client->startup(substream);
-	if (!ret)
-		goto err2;
-
-	return 0;
-
- err2:
-	__pxa2xx_pcm_close(substream);
- out:
-	return ret;
-}
-
-static int pxa2xx_pcm_close(struct snd_pcm_substream *substream)
-{
-	struct pxa2xx_pcm_client *client = substream->private_data;
-
-	client->shutdown(substream);
-
-	return __pxa2xx_pcm_close(substream);
-}
-
-static const struct snd_pcm_ops pxa2xx_pcm_ops = {
-	.open		= pxa2xx_pcm_open,
-	.close		= pxa2xx_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= __pxa2xx_pcm_hw_params,
-	.hw_free	= __pxa2xx_pcm_hw_free,
-	.prepare	= pxa2xx_pcm_prepare,
-	.trigger	= pxa2xx_pcm_trigger,
-	.pointer	= pxa2xx_pcm_pointer,
-	.mmap		= pxa2xx_pcm_mmap,
-};
-
-int pxa2xx_pcm_new(struct snd_card *card, struct pxa2xx_pcm_client *client,
-		   struct snd_pcm **rpcm)
-{
-	struct snd_pcm *pcm;
-	int play = client->playback_params ? 1 : 0;
-	int capt = client->capture_params ? 1 : 0;
-	int ret;
-
-	ret = snd_pcm_new(card, "PXA2xx-PCM", 0, play, capt, &pcm);
-	if (ret)
-		goto out;
-
-	pcm->private_data = client;
-	pcm->private_free = pxa2xx_pcm_free_dma_buffers;
-
-	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
-	if (ret)
-		goto out;
-
-	if (play) {
-		int stream = SNDRV_PCM_STREAM_PLAYBACK;
-		snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops);
-		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
-		if (ret)
-			goto out;
-	}
-	if (capt) {
-		int stream = SNDRV_PCM_STREAM_CAPTURE;
-		snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops);
-		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
-		if (ret)
-			goto out;
-	}
-
-	if (rpcm)
-		*rpcm = pcm;
-	ret = 0;
-
- out:
-	return ret;
-}
-
-EXPORT_SYMBOL(pxa2xx_pcm_new);
-
-MODULE_AUTHOR("Nicolas Pitre");
-MODULE_DESCRIPTION("Intel PXA2xx PCM DMA module");
-MODULE_LICENSE("GPL");
diff --git a/sound/arm/pxa2xx-pcm.h b/sound/arm/pxa2xx-pcm.h
deleted file mode 100644
index 8fa2b7c9e6b8..000000000000
--- a/sound/arm/pxa2xx-pcm.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * linux/sound/arm/pxa2xx-pcm.h -- ALSA PCM interface for the Intel PXA2xx chip
- *
- * Author:	Nicolas Pitre
- * Created:	Nov 30, 2004
- * Copyright:	MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-struct pxa2xx_runtime_data {
-	int dma_ch;
-	struct snd_dmaengine_dai_dma_data *params;
-};
-
-struct pxa2xx_pcm_client {
-	struct snd_dmaengine_dai_dma_data *playback_params;
-	struct snd_dmaengine_dai_dma_data *capture_params;
-	int (*startup)(struct snd_pcm_substream *);
-	void (*shutdown)(struct snd_pcm_substream *);
-	int (*prepare)(struct snd_pcm_substream *);
-};
-
-extern int pxa2xx_pcm_new(struct snd_card *, struct pxa2xx_pcm_client *, struct snd_pcm **);
-
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 4b01a37c836e..26b5e245b074 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -1160,18 +1160,6 @@ int snd_compress_deregister(struct snd_compr *device)
 }
 EXPORT_SYMBOL_GPL(snd_compress_deregister);
 
-static int __init snd_compress_init(void)
-{
-	return 0;
-}
-
-static void __exit snd_compress_exit(void)
-{
-}
-
-module_init(snd_compress_init);
-module_exit(snd_compress_exit);
-
 MODULE_DESCRIPTION("ALSA Compressed offload framework");
 MODULE_AUTHOR("Vinod Koul <vinod.koul@linux.intel.com>");
 MODULE_LICENSE("GPL v2");
diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c
index 7f89d3c79a4b..753d5fc4b284 100644
--- a/sound/core/memalloc.c
+++ b/sound/core/memalloc.c
@@ -242,16 +242,12 @@ int snd_dma_alloc_pages_fallback(int type, struct device *device, size_t size,
 	int err;
 
 	while ((err = snd_dma_alloc_pages(type, device, size, dmab)) < 0) {
-		size_t aligned_size;
 		if (err != -ENOMEM)
 			return err;
 		if (size <= PAGE_SIZE)
 			return -ENOMEM;
-		aligned_size = PAGE_SIZE << get_order(size);
-		if (size != aligned_size)
-			size = aligned_size;
-		else
-			size >>= 1;
+		size >>= 1;
+		size = PAGE_SIZE << get_order(size);
 	}
 	if (! dmab->area)
 		return -ENOMEM;
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index 905a53c1cde5..f8d4a419f3af 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -1851,7 +1851,7 @@ static int snd_pcm_oss_get_formats(struct snd_pcm_oss_file *pcm_oss_file)
 	format_mask = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT);
 	for (fmt = 0; fmt < 32; ++fmt) {
 		if (snd_mask_test(format_mask, fmt)) {
-			int f = snd_pcm_oss_format_to(fmt);
+			int f = snd_pcm_oss_format_to((__force snd_pcm_format_t)fmt);
 			if (f >= 0)
 				formats |= f;
 		}
diff --git a/sound/core/oss/pcm_plugin.c b/sound/core/oss/pcm_plugin.c
index 85a56af104bd..0391cb1a4f19 100644
--- a/sound/core/oss/pcm_plugin.c
+++ b/sound/core/oss/pcm_plugin.c
@@ -281,10 +281,10 @@ static int snd_pcm_plug_formats(const struct snd_mask *mask,
 		       SNDRV_PCM_FMTBIT_U32_BE | SNDRV_PCM_FMTBIT_S32_BE);
 	snd_mask_set(&formats, (__force int)SNDRV_PCM_FORMAT_MU_LAW);
 	
-	if (formats.bits[0] & (u32)linfmts)
-		formats.bits[0] |= (u32)linfmts;
-	if (formats.bits[1] & (u32)(linfmts >> 32))
-		formats.bits[1] |= (u32)(linfmts >> 32);
+	if (formats.bits[0] & lower_32_bits(linfmts))
+		formats.bits[0] |= lower_32_bits(linfmts);
+	if (formats.bits[1] & upper_32_bits(linfmts))
+		formats.bits[1] |= upper_32_bits(linfmts);
 	return snd_mask_test(&formats, (__force int)format);
 }
 
@@ -353,6 +353,7 @@ snd_pcm_format_t snd_pcm_plug_slave_format(snd_pcm_format_t format,
 				if (snd_mask_test(format_mask, (__force int)format1))
 					return format1;
 			}
+			/* fall through */
 		default:
 			return (__force snd_pcm_format_t)-EINVAL;
 		}
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index c352bfb973cc..fdb9b92fc8d6 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -492,13 +492,8 @@ static void snd_pcm_xrun_injection_write(struct snd_info_entry *entry,
 					 struct snd_info_buffer *buffer)
 {
 	struct snd_pcm_substream *substream = entry->private_data;
-	struct snd_pcm_runtime *runtime;
 
-	snd_pcm_stream_lock_irq(substream);
-	runtime = substream->runtime;
-	if (runtime && runtime->status->state == SNDRV_PCM_STATE_RUNNING)
-		snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
-	snd_pcm_stream_unlock_irq(substream);
+	snd_pcm_stop_xrun(substream);
 }
 
 static void snd_pcm_xrun_debug_read(struct snd_info_entry *entry,
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 44b5ae833082..4e6110d778bd 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -153,7 +153,8 @@ EXPORT_SYMBOL(snd_pcm_debug_name);
 			dump_stack();				\
 	} while (0)
 
-static void xrun(struct snd_pcm_substream *substream)
+/* call with stream lock held */
+void __snd_pcm_xrun(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 
@@ -201,7 +202,7 @@ int snd_pcm_update_state(struct snd_pcm_substream *substream,
 		}
 	} else {
 		if (avail >= runtime->stop_threshold) {
-			xrun(substream);
+			__snd_pcm_xrun(substream);
 			return -EPIPE;
 		}
 	}
@@ -297,7 +298,7 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 	}
 
 	if (pos == SNDRV_PCM_POS_XRUN) {
-		xrun(substream);
+		__snd_pcm_xrun(substream);
 		return -EPIPE;
 	}
 	if (pos >= runtime->buffer_size) {
@@ -626,27 +627,33 @@ EXPORT_SYMBOL(snd_interval_refine);
 
 static int snd_interval_refine_first(struct snd_interval *i)
 {
+	const unsigned int last_max = i->max;
+
 	if (snd_BUG_ON(snd_interval_empty(i)))
 		return -EINVAL;
 	if (snd_interval_single(i))
 		return 0;
 	i->max = i->min;
-	i->openmax = i->openmin;
-	if (i->openmax)
+	if (i->openmin)
 		i->max++;
+	/* only exclude max value if also excluded before refine */
+	i->openmax = (i->openmax && i->max >= last_max);
 	return 1;
 }
 
 static int snd_interval_refine_last(struct snd_interval *i)
 {
+	const unsigned int last_min = i->min;
+
 	if (snd_BUG_ON(snd_interval_empty(i)))
 		return -EINVAL;
 	if (snd_interval_single(i))
 		return 0;
 	i->min = i->max;
-	i->openmin = i->openmax;
-	if (i->openmin)
+	if (i->openmax)
 		i->min--;
+	/* only exclude min value if also excluded before refine */
+	i->openmin = (i->openmin && i->min <= last_min);
 	return 1;
 }
 
@@ -1832,12 +1839,19 @@ static int wait_for_avail(struct snd_pcm_substream *substream,
 	if (runtime->no_period_wakeup)
 		wait_time = MAX_SCHEDULE_TIMEOUT;
 	else {
-		wait_time = 10;
-		if (runtime->rate) {
-			long t = runtime->period_size * 2 / runtime->rate;
-			wait_time = max(t, wait_time);
+		/* use wait time from substream if available */
+		if (substream->wait_time) {
+			wait_time = substream->wait_time;
+		} else {
+			wait_time = 10;
+
+			if (runtime->rate) {
+				long t = runtime->period_size * 2 /
+					 runtime->rate;
+				wait_time = max(t, wait_time);
+			}
+			wait_time = msecs_to_jiffies(wait_time * 1000);
 		}
-		wait_time = msecs_to_jiffies(wait_time * 1000);
 	}
 
 	for (;;) {
diff --git a/sound/core/pcm_local.h b/sound/core/pcm_local.h
index 7a499d02df6c..c515612969a4 100644
--- a/sound/core/pcm_local.h
+++ b/sound/core/pcm_local.h
@@ -65,4 +65,6 @@ static inline void snd_pcm_timer_init(struct snd_pcm_substream *substream) {}
 static inline void snd_pcm_timer_done(struct snd_pcm_substream *substream) {}
 #endif
 
+void __snd_pcm_xrun(struct snd_pcm_substream *substream);
+
 #endif	/* __SOUND_CORE_PCM_LOCAL_H */
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index cecc79772c94..66c90f486af9 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1337,13 +1337,12 @@ int snd_pcm_drain_done(struct snd_pcm_substream *substream)
 int snd_pcm_stop_xrun(struct snd_pcm_substream *substream)
 {
 	unsigned long flags;
-	int ret = 0;
 
 	snd_pcm_stream_lock_irqsave(substream, flags);
-	if (snd_pcm_running(substream))
-		ret = snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+	if (substream->runtime && snd_pcm_running(substream))
+		__snd_pcm_xrun(substream);
 	snd_pcm_stream_unlock_irqrestore(substream, flags);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stop_xrun);
 
@@ -1591,7 +1590,8 @@ static int snd_pcm_xrun(struct snd_pcm_substream *substream)
 		result = 0;	/* already there */
 		break;
 	case SNDRV_PCM_STATE_RUNNING:
-		result = snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+		__snd_pcm_xrun(substream);
+		result = 0;
 		break;
 	default:
 		result = -EBADFD;
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 69616d00481c..69517e18ef07 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -29,6 +29,7 @@
 #include <linux/mutex.h>
 #include <linux/module.h>
 #include <linux/delay.h>
+#include <linux/mm.h>
 #include <sound/rawmidi.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -88,6 +89,7 @@ static inline unsigned short snd_rawmidi_file_flags(struct file *file)
 static inline int snd_rawmidi_ready(struct snd_rawmidi_substream *substream)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
+
 	return runtime->avail >= runtime->avail_min;
 }
 
@@ -95,6 +97,7 @@ static inline int snd_rawmidi_ready_append(struct snd_rawmidi_substream *substre
 					   size_t count)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
+
 	return runtime->avail >= runtime->avail_min &&
 	       (!substream->append || runtime->avail >= count);
 }
@@ -103,6 +106,7 @@ static void snd_rawmidi_input_event_work(struct work_struct *work)
 {
 	struct snd_rawmidi_runtime *runtime =
 		container_of(work, struct snd_rawmidi_runtime, event_work);
+
 	if (runtime->event)
 		runtime->event(runtime->substream);
 }
@@ -111,7 +115,8 @@ static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream)
 {
 	struct snd_rawmidi_runtime *runtime;
 
-	if ((runtime = kzalloc(sizeof(*runtime), GFP_KERNEL)) == NULL)
+	runtime = kzalloc(sizeof(*runtime), GFP_KERNEL);
+	if (!runtime)
 		return -ENOMEM;
 	runtime->substream = substream;
 	spin_lock_init(&runtime->lock);
@@ -124,7 +129,8 @@ static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream)
 		runtime->avail = 0;
 	else
 		runtime->avail = runtime->buffer_size;
-	if ((runtime->buffer = kmalloc(runtime->buffer_size, GFP_KERNEL)) == NULL) {
+	runtime->buffer = kvmalloc(runtime->buffer_size, GFP_KERNEL);
+	if (!runtime->buffer) {
 		kfree(runtime);
 		return -ENOMEM;
 	}
@@ -137,13 +143,13 @@ static int snd_rawmidi_runtime_free(struct snd_rawmidi_substream *substream)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
-	kfree(runtime->buffer);
+	kvfree(runtime->buffer);
 	kfree(runtime);
 	substream->runtime = NULL;
 	return 0;
 }
 
-static inline void snd_rawmidi_output_trigger(struct snd_rawmidi_substream *substream,int up)
+static inline void snd_rawmidi_output_trigger(struct snd_rawmidi_substream *substream, int up)
 {
 	if (!substream->opened)
 		return;
@@ -159,17 +165,28 @@ static void snd_rawmidi_input_trigger(struct snd_rawmidi_substream *substream, i
 		cancel_work_sync(&substream->runtime->event_work);
 }
 
-int snd_rawmidi_drop_output(struct snd_rawmidi_substream *substream)
+static void __reset_runtime_ptrs(struct snd_rawmidi_runtime *runtime,
+				 bool is_input)
+{
+	runtime->drain = 0;
+	runtime->appl_ptr = runtime->hw_ptr = 0;
+	runtime->avail = is_input ? 0 : runtime->buffer_size;
+}
+
+static void reset_runtime_ptrs(struct snd_rawmidi_runtime *runtime,
+			       bool is_input)
 {
 	unsigned long flags;
-	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
-	snd_rawmidi_output_trigger(substream, 0);
-	runtime->drain = 0;
 	spin_lock_irqsave(&runtime->lock, flags);
-	runtime->appl_ptr = runtime->hw_ptr = 0;
-	runtime->avail = runtime->buffer_size;
+	__reset_runtime_ptrs(runtime, is_input);
 	spin_unlock_irqrestore(&runtime->lock, flags);
+}
+
+int snd_rawmidi_drop_output(struct snd_rawmidi_substream *substream)
+{
+	snd_rawmidi_output_trigger(substream, 0);
+	reset_runtime_ptrs(substream->runtime, false);
 	return 0;
 }
 EXPORT_SYMBOL(snd_rawmidi_drop_output);
@@ -208,15 +225,8 @@ EXPORT_SYMBOL(snd_rawmidi_drain_output);
 
 int snd_rawmidi_drain_input(struct snd_rawmidi_substream *substream)
 {
-	unsigned long flags;
-	struct snd_rawmidi_runtime *runtime = substream->runtime;
-
 	snd_rawmidi_input_trigger(substream, 0);
-	runtime->drain = 0;
-	spin_lock_irqsave(&runtime->lock, flags);
-	runtime->appl_ptr = runtime->hw_ptr = 0;
-	runtime->avail = 0;
-	spin_unlock_irqrestore(&runtime->lock, flags);
+	reset_runtime_ptrs(substream->runtime, true);
 	return 0;
 }
 EXPORT_SYMBOL(snd_rawmidi_drain_input);
@@ -330,25 +340,23 @@ static int rawmidi_open_priv(struct snd_rawmidi *rmidi, int subdevice, int mode,
 
 /* called from sound/core/seq/seq_midi.c */
 int snd_rawmidi_kernel_open(struct snd_card *card, int device, int subdevice,
-			    int mode, struct snd_rawmidi_file * rfile)
+			    int mode, struct snd_rawmidi_file *rfile)
 {
 	struct snd_rawmidi *rmidi;
-	int err;
+	int err = 0;
 
 	if (snd_BUG_ON(!rfile))
 		return -EINVAL;
 
 	mutex_lock(&register_mutex);
 	rmidi = snd_rawmidi_search(card, device);
-	if (rmidi == NULL) {
-		mutex_unlock(&register_mutex);
-		return -ENODEV;
-	}
-	if (!try_module_get(rmidi->card->module)) {
-		mutex_unlock(&register_mutex);
-		return -ENXIO;
-	}
+	if (!rmidi)
+		err = -ENODEV;
+	else if (!try_module_get(rmidi->card->module))
+		err = -ENXIO;
 	mutex_unlock(&register_mutex);
+	if (err < 0)
+		return err;
 
 	mutex_lock(&rmidi->open_mutex);
 	err = rawmidi_open_priv(rmidi, subdevice, mode, rfile);
@@ -370,7 +378,7 @@ static int snd_rawmidi_open(struct inode *inode, struct file *file)
 	struct snd_rawmidi_file *rawmidi_file = NULL;
 	wait_queue_entry_t wait;
 
-	if ((file->f_flags & O_APPEND) && !(file->f_flags & O_NONBLOCK)) 
+	if ((file->f_flags & O_APPEND) && !(file->f_flags & O_NONBLOCK))
 		return -EINVAL;		/* invalid combination */
 
 	err = nonseekable_open(inode, file);
@@ -520,7 +528,7 @@ int snd_rawmidi_kernel_release(struct snd_rawmidi_file *rfile)
 
 	if (snd_BUG_ON(!rfile))
 		return -ENXIO;
-	
+
 	rmidi = rfile->rmidi;
 	rawmidi_release_priv(rfile);
 	module_put(rmidi->card->module);
@@ -548,7 +556,7 @@ static int snd_rawmidi_info(struct snd_rawmidi_substream *substream,
 			    struct snd_rawmidi_info *info)
 {
 	struct snd_rawmidi *rmidi;
-	
+
 	if (substream == NULL)
 		return -ENODEV;
 	rmidi = substream->rmidi;
@@ -568,11 +576,13 @@ static int snd_rawmidi_info(struct snd_rawmidi_substream *substream,
 }
 
 static int snd_rawmidi_info_user(struct snd_rawmidi_substream *substream,
-				 struct snd_rawmidi_info __user * _info)
+				 struct snd_rawmidi_info __user *_info)
 {
 	struct snd_rawmidi_info info;
 	int err;
-	if ((err = snd_rawmidi_info(substream, &info)) < 0)
+
+	err = snd_rawmidi_info(substream, &info);
+	if (err < 0)
 		return err;
 	if (copy_to_user(_info, &info, sizeof(struct snd_rawmidi_info)))
 		return -EFAULT;
@@ -619,77 +629,68 @@ static int snd_rawmidi_info_select_user(struct snd_card *card,
 {
 	int err;
 	struct snd_rawmidi_info info;
+
 	if (get_user(info.device, &_info->device))
 		return -EFAULT;
 	if (get_user(info.stream, &_info->stream))
 		return -EFAULT;
 	if (get_user(info.subdevice, &_info->subdevice))
 		return -EFAULT;
-	if ((err = snd_rawmidi_info_select(card, &info)) < 0)
+	err = snd_rawmidi_info_select(card, &info);
+	if (err < 0)
 		return err;
 	if (copy_to_user(_info, &info, sizeof(struct snd_rawmidi_info)))
 		return -EFAULT;
 	return 0;
 }
 
-int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
-			      struct snd_rawmidi_params * params)
+static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime,
+				 struct snd_rawmidi_params *params,
+				 bool is_input)
 {
-	char *newbuf;
-	struct snd_rawmidi_runtime *runtime = substream->runtime;
-	
-	if (substream->append && substream->use_count > 1)
-		return -EBUSY;
-	snd_rawmidi_drain_output(substream);
-	if (params->buffer_size < 32 || params->buffer_size > 1024L * 1024L) {
+	char *newbuf, *oldbuf;
+
+	if (params->buffer_size < 32 || params->buffer_size > 1024L * 1024L)
 		return -EINVAL;
-	}
-	if (params->avail_min < 1 || params->avail_min > params->buffer_size) {
+	if (params->avail_min < 1 || params->avail_min > params->buffer_size)
 		return -EINVAL;
-	}
 	if (params->buffer_size != runtime->buffer_size) {
-		newbuf = krealloc(runtime->buffer, params->buffer_size,
-				  GFP_KERNEL);
+		newbuf = kvmalloc(params->buffer_size, GFP_KERNEL);
 		if (!newbuf)
 			return -ENOMEM;
+		spin_lock_irq(&runtime->lock);
+		oldbuf = runtime->buffer;
 		runtime->buffer = newbuf;
 		runtime->buffer_size = params->buffer_size;
-		runtime->avail = runtime->buffer_size;
+		__reset_runtime_ptrs(runtime, is_input);
+		spin_unlock_irq(&runtime->lock);
+		kvfree(oldbuf);
 	}
 	runtime->avail_min = params->avail_min;
-	substream->active_sensing = !params->no_active_sensing;
 	return 0;
 }
+
+int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
+			      struct snd_rawmidi_params *params)
+{
+	if (substream->append && substream->use_count > 1)
+		return -EBUSY;
+	snd_rawmidi_drain_output(substream);
+	substream->active_sensing = !params->no_active_sensing;
+	return resize_runtime_buffer(substream->runtime, params, false);
+}
 EXPORT_SYMBOL(snd_rawmidi_output_params);
 
 int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream,
-			     struct snd_rawmidi_params * params)
+			     struct snd_rawmidi_params *params)
 {
-	char *newbuf;
-	struct snd_rawmidi_runtime *runtime = substream->runtime;
-
 	snd_rawmidi_drain_input(substream);
-	if (params->buffer_size < 32 || params->buffer_size > 1024L * 1024L) {
-		return -EINVAL;
-	}
-	if (params->avail_min < 1 || params->avail_min > params->buffer_size) {
-		return -EINVAL;
-	}
-	if (params->buffer_size != runtime->buffer_size) {
-		newbuf = krealloc(runtime->buffer, params->buffer_size,
-				  GFP_KERNEL);
-		if (!newbuf)
-			return -ENOMEM;
-		runtime->buffer = newbuf;
-		runtime->buffer_size = params->buffer_size;
-	}
-	runtime->avail_min = params->avail_min;
-	return 0;
+	return resize_runtime_buffer(substream->runtime, params, true);
 }
 EXPORT_SYMBOL(snd_rawmidi_input_params);
 
 static int snd_rawmidi_output_status(struct snd_rawmidi_substream *substream,
-				     struct snd_rawmidi_status * status)
+				     struct snd_rawmidi_status *status)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
@@ -702,7 +703,7 @@ static int snd_rawmidi_output_status(struct snd_rawmidi_substream *substream,
 }
 
 static int snd_rawmidi_input_status(struct snd_rawmidi_substream *substream,
-				    struct snd_rawmidi_status * status)
+				    struct snd_rawmidi_status *status)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
@@ -731,6 +732,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	{
 		int stream;
 		struct snd_rawmidi_info __user *info = argp;
+
 		if (get_user(stream, &info->stream))
 			return -EFAULT;
 		switch (stream) {
@@ -745,6 +747,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	case SNDRV_RAWMIDI_IOCTL_PARAMS:
 	{
 		struct snd_rawmidi_params params;
+
 		if (copy_from_user(&params, argp, sizeof(struct snd_rawmidi_params)))
 			return -EFAULT;
 		switch (params.stream) {
@@ -764,6 +767,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	{
 		int err = 0;
 		struct snd_rawmidi_status status;
+
 		if (copy_from_user(&status, argp, sizeof(struct snd_rawmidi_status)))
 			return -EFAULT;
 		switch (status.stream) {
@@ -789,6 +793,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	case SNDRV_RAWMIDI_IOCTL_DROP:
 	{
 		int val;
+
 		if (get_user(val, (int __user *) argp))
 			return -EFAULT;
 		switch (val) {
@@ -803,6 +808,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	case SNDRV_RAWMIDI_IOCTL_DRAIN:
 	{
 		int val;
+
 		if (get_user(val, (int __user *) argp))
 			return -EFAULT;
 		switch (val) {
@@ -836,7 +842,7 @@ static int snd_rawmidi_control_ioctl(struct snd_card *card,
 	case SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE:
 	{
 		int device;
-		
+
 		if (get_user(device, (int __user *)argp))
 			return -EFAULT;
 		if (device >= SNDRV_RAWMIDI_DEVICES) /* next device is -1 */
@@ -858,7 +864,7 @@ static int snd_rawmidi_control_ioctl(struct snd_card *card,
 	case SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE:
 	{
 		int val;
-		
+
 		if (get_user(val, (int __user *)argp))
 			return -EFAULT;
 		control->preferred_subdevice[SND_CTL_SUBDEV_RAWMIDI] = val;
@@ -1012,6 +1018,7 @@ static ssize_t snd_rawmidi_read(struct file *file, char __user *buf, size_t coun
 		spin_lock_irq(&runtime->lock);
 		while (!snd_rawmidi_ready(substream)) {
 			wait_queue_entry_t wait;
+
 			if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) {
 				spin_unlock_irq(&runtime->lock);
 				return result > 0 ? result : -EAGAIN;
@@ -1064,7 +1071,7 @@ int snd_rawmidi_transmit_empty(struct snd_rawmidi_substream *substream)
 	spin_lock_irqsave(&runtime->lock, flags);
 	result = runtime->avail >= runtime->buffer_size;
 	spin_unlock_irqrestore(&runtime->lock, flags);
-	return result;		
+	return result;
 }
 EXPORT_SYMBOL(snd_rawmidi_transmit_empty);
 
@@ -1202,7 +1209,7 @@ EXPORT_SYMBOL(snd_rawmidi_transmit_ack);
  * @substream: the rawmidi substream
  * @buffer: the buffer pointer
  * @count: the data size to transfer
- * 
+ *
  * Copies data from the buffer to the device and advances the pointer.
  *
  * Return: The copied size if successful, or a negative error code on failure.
@@ -1316,6 +1323,7 @@ static ssize_t snd_rawmidi_write(struct file *file, const char __user *buf,
 		spin_lock_irq(&runtime->lock);
 		while (!snd_rawmidi_ready_append(substream, count)) {
 			wait_queue_entry_t wait;
+
 			if (file->f_flags & O_NONBLOCK) {
 				spin_unlock_irq(&runtime->lock);
 				return result > 0 ? result : -EAGAIN;
@@ -1349,6 +1357,7 @@ static ssize_t snd_rawmidi_write(struct file *file, const char __user *buf,
 		while (runtime->avail != runtime->buffer_size) {
 			wait_queue_entry_t wait;
 			unsigned int last_avail = runtime->avail;
+
 			init_waitqueue_entry(&wait, current);
 			add_wait_queue(&runtime->sleep, &wait);
 			set_current_state(TASK_INTERRUPTIBLE);
@@ -1366,7 +1375,7 @@ static ssize_t snd_rawmidi_write(struct file *file, const char __user *buf,
 	return result;
 }
 
-static __poll_t snd_rawmidi_poll(struct file *file, poll_table * wait)
+static __poll_t snd_rawmidi_poll(struct file *file, poll_table *wait)
 {
 	struct snd_rawmidi_file *rfile;
 	struct snd_rawmidi_runtime *runtime;
@@ -1403,7 +1412,6 @@ static __poll_t snd_rawmidi_poll(struct file *file, poll_table * wait)
 #endif
 
 /*
-
  */
 
 static void snd_rawmidi_proc_info_read(struct snd_info_entry *entry,
@@ -1471,8 +1479,7 @@ static void snd_rawmidi_proc_info_read(struct snd_info_entry *entry,
  *  Register functions
  */
 
-static const struct file_operations snd_rawmidi_f_ops =
-{
+static const struct file_operations snd_rawmidi_f_ops = {
 	.owner =	THIS_MODULE,
 	.read =		snd_rawmidi_read,
 	.write =	snd_rawmidi_write,
@@ -1527,7 +1534,7 @@ static void release_rawmidi_device(struct device *dev)
  */
 int snd_rawmidi_new(struct snd_card *card, char *id, int device,
 		    int output_count, int input_count,
-		    struct snd_rawmidi ** rrawmidi)
+		    struct snd_rawmidi **rrawmidi)
 {
 	struct snd_rawmidi *rmidi;
 	int err;
@@ -1558,27 +1565,29 @@ int snd_rawmidi_new(struct snd_card *card, char *id, int device,
 	rmidi->dev.release = release_rawmidi_device;
 	dev_set_name(&rmidi->dev, "midiC%iD%i", card->number, device);
 
-	if ((err = snd_rawmidi_alloc_substreams(rmidi,
-						&rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT],
-						SNDRV_RAWMIDI_STREAM_INPUT,
-						input_count)) < 0) {
-		snd_rawmidi_free(rmidi);
-		return err;
-	}
-	if ((err = snd_rawmidi_alloc_substreams(rmidi,
-						&rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT],
-						SNDRV_RAWMIDI_STREAM_OUTPUT,
-						output_count)) < 0) {
-		snd_rawmidi_free(rmidi);
-		return err;
-	}
-	if ((err = snd_device_new(card, SNDRV_DEV_RAWMIDI, rmidi, &ops)) < 0) {
-		snd_rawmidi_free(rmidi);
-		return err;
-	}
+	err = snd_rawmidi_alloc_substreams(rmidi,
+					   &rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT],
+					   SNDRV_RAWMIDI_STREAM_INPUT,
+					   input_count);
+	if (err < 0)
+		goto error;
+	err = snd_rawmidi_alloc_substreams(rmidi,
+					   &rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT],
+					   SNDRV_RAWMIDI_STREAM_OUTPUT,
+					   output_count);
+	if (err < 0)
+		goto error;
+	err = snd_device_new(card, SNDRV_DEV_RAWMIDI, rmidi, &ops);
+	if (err < 0)
+		goto error;
+
 	if (rrawmidi)
 		*rrawmidi = rmidi;
 	return 0;
+
+ error:
+	snd_rawmidi_free(rmidi);
+	return err;
 }
 EXPORT_SYMBOL(snd_rawmidi_new);
 
@@ -1616,6 +1625,7 @@ static int snd_rawmidi_free(struct snd_rawmidi *rmidi)
 static int snd_rawmidi_dev_free(struct snd_device *device)
 {
 	struct snd_rawmidi *rmidi = device->device_data;
+
 	return snd_rawmidi_free(rmidi);
 }
 
@@ -1623,6 +1633,7 @@ static int snd_rawmidi_dev_free(struct snd_device *device)
 static void snd_rawmidi_dev_seq_free(struct snd_seq_device *device)
 {
 	struct snd_rawmidi *rmidi = device->private_data;
+
 	rmidi->seq_dev = NULL;
 }
 #endif
@@ -1636,30 +1647,27 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 
 	if (rmidi->device >= SNDRV_RAWMIDI_DEVICES)
 		return -ENOMEM;
+	err = 0;
 	mutex_lock(&register_mutex);
-	if (snd_rawmidi_search(rmidi->card, rmidi->device)) {
-		mutex_unlock(&register_mutex);
-		return -EBUSY;
-	}
-	list_add_tail(&rmidi->list, &snd_rawmidi_devices);
+	if (snd_rawmidi_search(rmidi->card, rmidi->device))
+		err = -EBUSY;
+	else
+		list_add_tail(&rmidi->list, &snd_rawmidi_devices);
 	mutex_unlock(&register_mutex);
+	if (err < 0)
+		return err;
+
 	err = snd_register_device(SNDRV_DEVICE_TYPE_RAWMIDI,
 				  rmidi->card, rmidi->device,
 				  &snd_rawmidi_f_ops, rmidi, &rmidi->dev);
 	if (err < 0) {
 		rmidi_err(rmidi, "unable to register\n");
-		mutex_lock(&register_mutex);
-		list_del(&rmidi->list);
-		mutex_unlock(&register_mutex);
-		return err;
+		goto error;
 	}
-	if (rmidi->ops && rmidi->ops->dev_register &&
-	    (err = rmidi->ops->dev_register(rmidi)) < 0) {
-		snd_unregister_device(&rmidi->dev);
-		mutex_lock(&register_mutex);
-		list_del(&rmidi->list);
-		mutex_unlock(&register_mutex);
-		return err;
+	if (rmidi->ops && rmidi->ops->dev_register) {
+		err = rmidi->ops->dev_register(rmidi);
+		if (err < 0)
+			goto error_unregister;
 	}
 #ifdef CONFIG_SND_OSSEMUL
 	rmidi->ossreg = 0;
@@ -1711,6 +1719,14 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 	}
 #endif
 	return 0;
+
+ error_unregister:
+	snd_unregister_device(&rmidi->dev);
+ error:
+	mutex_lock(&register_mutex);
+	list_del(&rmidi->list);
+	mutex_unlock(&register_mutex);
+	return err;
 }
 
 static int snd_rawmidi_dev_disconnect(struct snd_device *device)
@@ -1724,6 +1740,7 @@ static int snd_rawmidi_dev_disconnect(struct snd_device *device)
 	list_del_init(&rmidi->list);
 	for (dir = 0; dir < 2; dir++) {
 		struct snd_rawmidi_substream *s;
+
 		list_for_each_entry(s, &rmidi->streams[dir].substreams, list) {
 			if (s->runtime)
 				wake_up(&s->runtime->sleep);
@@ -1761,7 +1778,7 @@ void snd_rawmidi_set_ops(struct snd_rawmidi *rmidi, int stream,
 			 const struct snd_rawmidi_ops *ops)
 {
 	struct snd_rawmidi_substream *substream;
-	
+
 	list_for_each_entry(substream, &rmidi->streams[stream].substreams, list)
 		substream->ops = ops;
 }
diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c
index 5f64d0d88320..e1f44fc86885 100644
--- a/sound/core/seq/oss/seq_oss.c
+++ b/sound/core/seq/oss/seq_oss.c
@@ -203,7 +203,7 @@ odev_poll(struct file *file, poll_table * wait)
 	struct seq_oss_devinfo *dp;
 	dp = file->private_data;
 	if (snd_BUG_ON(!dp))
-		return -ENXIO;
+		return EPOLLERR;
 	return snd_seq_oss_poll(dp, file, wait);
 }
 
diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c
index 9debd1b8fd28..0d5f8b16d057 100644
--- a/sound/core/seq/oss/seq_oss_midi.c
+++ b/sound/core/seq/oss/seq_oss_midi.c
@@ -637,7 +637,7 @@ snd_seq_oss_midi_putc(struct seq_oss_devinfo *dp, int dev, unsigned char c, stru
 
 	if ((mdev = get_mididev(dp, dev)) == NULL)
 		return -ENODEV;
-	if (snd_midi_event_encode_byte(mdev->coder, c, ev) > 0) {
+	if (snd_midi_event_encode_byte(mdev->coder, c, ev)) {
 		snd_seq_oss_fill_addr(dp, ev, mdev->client, mdev->port);
 		snd_use_lock_free(&mdev->use_lock);
 		return 0;
diff --git a/sound/core/seq/oss/seq_oss_timer.c b/sound/core/seq/oss/seq_oss_timer.c
index 4f24ea9fad93..ba127c22539a 100644
--- a/sound/core/seq/oss/seq_oss_timer.c
+++ b/sound/core/seq/oss/seq_oss_timer.c
@@ -92,7 +92,7 @@ snd_seq_oss_process_timer_event(struct seq_oss_timer *rec, union evrec *ev)
 		case TMR_WAIT_REL:
 			parm += rec->cur_tick;
 			rec->realtime = 0;
-			/* continue to next */
+			/* fall through and continue to next */
 		case TMR_WAIT_ABS:
 			if (parm == 0) {
 				rec->realtime = 1;
diff --git a/sound/core/seq/seq.c b/sound/core/seq/seq.c
index 639544b4fb04..7de98d71f2aa 100644
--- a/sound/core/seq/seq.c
+++ b/sound/core/seq/seq.c
@@ -84,30 +84,32 @@ static int __init alsa_seq_init(void)
 {
 	int err;
 
-	if ((err = client_init_data()) < 0)
-		goto error;
-
-	/* init memory, room for selected events */
-	if ((err = snd_sequencer_memory_init()) < 0)
-		goto error;
-
-	/* init event queues */
-	if ((err = snd_seq_queues_init()) < 0)
+	err = client_init_data();
+	if (err < 0)
 		goto error;
 
 	/* register sequencer device */
-	if ((err = snd_sequencer_device_init()) < 0)
+	err = snd_sequencer_device_init();
+	if (err < 0)
 		goto error;
 
 	/* register proc interface */
-	if ((err = snd_seq_info_init()) < 0)
-		goto error;
+	err = snd_seq_info_init();
+	if (err < 0)
+		goto error_device;
 
 	/* register our internal client */
-	if ((err = snd_seq_system_client_init()) < 0)
-		goto error;
+	err = snd_seq_system_client_init();
+	if (err < 0)
+		goto error_info;
 
 	snd_seq_autoload_init();
+	return 0;
+
+ error_info:
+	snd_seq_info_done();
+ error_device:
+	snd_sequencer_device_done();
  error:
 	return err;
 }
@@ -126,9 +128,6 @@ static void __exit alsa_seq_exit(void)
 	/* unregister sequencer device */
 	snd_sequencer_device_done();
 
-	/* release event memory */
-	snd_sequencer_memory_done();
-
 	snd_seq_autoload_exit();
 }
 
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 61a07fe34cd2..92e6524a3a9d 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -311,10 +311,9 @@ static int snd_seq_open(struct inode *inode, struct file *file)
 	if (err < 0)
 		return err;
 
-	if (mutex_lock_interruptible(&register_mutex))
-		return -ERESTARTSYS;
+	mutex_lock(&register_mutex);
 	client = seq_create_client1(-1, SNDRV_SEQ_DEFAULT_EVENTS);
-	if (client == NULL) {
+	if (!client) {
 		mutex_unlock(&register_mutex);
 		return -ENOMEM;	/* failure code */
 	}
@@ -1101,7 +1100,7 @@ static __poll_t snd_seq_poll(struct file *file, poll_table * wait)
 
 	/* check client structures are in place */
 	if (snd_BUG_ON(!client))
-		return -ENXIO;
+		return EPOLLERR;
 
 	if ((snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_INPUT) &&
 	    client->data.user.fifo) {
@@ -1704,10 +1703,7 @@ static int snd_seq_ioctl_get_queue_timer(struct snd_seq_client *client,
 	if (queue == NULL)
 		return -EINVAL;
 
-	if (mutex_lock_interruptible(&queue->timer_mutex)) {
-		queuefree(queue);
-		return -ERESTARTSYS;
-	}
+	mutex_lock(&queue->timer_mutex);
 	tmr = queue->timer;
 	memset(timer, 0, sizeof(*timer));
 	timer->queue = queue->queue;
@@ -1741,10 +1737,7 @@ static int snd_seq_ioctl_set_queue_timer(struct snd_seq_client *client,
 		q = queueptr(timer->queue);
 		if (q == NULL)
 			return -ENXIO;
-		if (mutex_lock_interruptible(&q->timer_mutex)) {
-			queuefree(q);
-			return -ERESTARTSYS;
-		}
+		mutex_lock(&q->timer_mutex);
 		tmr = q->timer;
 		snd_seq_queue_timer_close(timer->queue);
 		tmr->type = timer->type;
@@ -2004,7 +1997,8 @@ static int snd_seq_ioctl_query_next_client(struct snd_seq_client *client,
 	struct snd_seq_client *cptr = NULL;
 
 	/* search for next client */
-	info->client++;
+	if (info->client < INT_MAX)
+		info->client++;
 	if (info->client < 0)
 		info->client = 0;
 	for (; info->client < SNDRV_SEQ_MAX_CLIENTS; info->client++) {
@@ -2179,8 +2173,7 @@ int snd_seq_create_kernel_client(struct snd_card *card, int client_index,
 	if (card == NULL && client_index >= SNDRV_SEQ_GLOBAL_CLIENTS)
 		return -EINVAL;
 
-	if (mutex_lock_interruptible(&register_mutex))
-		return -ERESTARTSYS;
+	mutex_lock(&register_mutex);
 
 	if (card) {
 		client_index += SNDRV_SEQ_GLOBAL_CLIENTS
@@ -2521,19 +2514,15 @@ int __init snd_sequencer_device_init(void)
 	snd_device_initialize(&seq_dev, NULL);
 	dev_set_name(&seq_dev, "seq");
 
-	if (mutex_lock_interruptible(&register_mutex))
-		return -ERESTARTSYS;
-
+	mutex_lock(&register_mutex);
 	err = snd_register_device(SNDRV_DEVICE_TYPE_SEQUENCER, NULL, 0,
 				  &snd_seq_f_ops, NULL, &seq_dev);
+	mutex_unlock(&register_mutex);
 	if (err < 0) {
-		mutex_unlock(&register_mutex);
 		put_device(&seq_dev);
 		return err;
 	}
 	
-	mutex_unlock(&register_mutex);
-
 	return 0;
 }
 
@@ -2542,7 +2531,7 @@ int __init snd_sequencer_device_init(void)
 /* 
  * unregister sequencer device 
  */
-void __exit snd_sequencer_device_done(void)
+void snd_sequencer_device_done(void)
 {
 	snd_unregister_device(&seq_dev);
 	put_device(&seq_dev);
diff --git a/sound/core/seq/seq_info.c b/sound/core/seq/seq_info.c
index 97015447b9b3..b27fedd435b6 100644
--- a/sound/core/seq/seq_info.c
+++ b/sound/core/seq/seq_info.c
@@ -50,7 +50,7 @@ create_info_entry(char *name, void (*read)(struct snd_info_entry *,
 	return entry;
 }
 
-static void free_info_entries(void)
+void snd_seq_info_done(void)
 {
 	snd_info_free_entry(queues_entry);
 	snd_info_free_entry(clients_entry);
@@ -70,12 +70,6 @@ int __init snd_seq_info_init(void)
 	return 0;
 
  error:
-	free_info_entries();
+	snd_seq_info_done();
 	return -ENOMEM;
 }
-
-int __exit snd_seq_info_done(void)
-{
-	free_info_entries();
-	return 0;
-}
diff --git a/sound/core/seq/seq_info.h b/sound/core/seq/seq_info.h
index f8549f81a645..2cdf8f6e63f5 100644
--- a/sound/core/seq/seq_info.h
+++ b/sound/core/seq/seq_info.h
@@ -30,11 +30,11 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry, struct snd_info_buff
 
 
 #ifdef CONFIG_SND_PROC_FS
-int snd_seq_info_init( void );
-int snd_seq_info_done( void );
+int snd_seq_info_init(void);
+void snd_seq_info_done(void);
 #else
 static inline int snd_seq_info_init(void) { return 0; }
-static inline int snd_seq_info_done(void) { return 0; }
+static inline void snd_seq_info_done(void) {}
 #endif
 
 #endif
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index a4c8543176b2..5b0388202bac 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -504,18 +504,6 @@ int snd_seq_pool_delete(struct snd_seq_pool **ppool)
 	return 0;
 }
 
-/* initialize sequencer memory */
-int __init snd_sequencer_memory_init(void)
-{
-	return 0;
-}
-
-/* release sequencer memory */
-void __exit snd_sequencer_memory_done(void)
-{
-}
-
-
 /* exported to seq_clientmgr.c */
 void snd_seq_info_pool(struct snd_info_buffer *buffer,
 		       struct snd_seq_pool *pool, char *space)
diff --git a/sound/core/seq/seq_memory.h b/sound/core/seq/seq_memory.h
index 3abe306c394a..1292fe91f02e 100644
--- a/sound/core/seq/seq_memory.h
+++ b/sound/core/seq/seq_memory.h
@@ -94,12 +94,6 @@ struct snd_seq_pool *snd_seq_pool_new(int poolsize);
 /* remove pool */
 int snd_seq_pool_delete(struct snd_seq_pool **pool);
 
-/* init memory */
-int snd_sequencer_memory_init(void);
-            
-/* release event memory */
-void snd_sequencer_memory_done(void);
-
 /* polling */
 int snd_seq_pool_poll_wait(struct snd_seq_pool *pool, struct file *file, poll_table *wait);
 
diff --git a/sound/core/seq/seq_midi.c b/sound/core/seq/seq_midi.c
index 5dd0ee258359..9e0dabd3ce5f 100644
--- a/sound/core/seq/seq_midi.c
+++ b/sound/core/seq/seq_midi.c
@@ -78,7 +78,7 @@ static void snd_midi_input_event(struct snd_rawmidi_substream *substream)
 	struct seq_midisynth *msynth;
 	struct snd_seq_event ev;
 	char buf[16], *pbuf;
-	long res, count;
+	long res;
 
 	if (substream == NULL)
 		return;
@@ -94,19 +94,15 @@ static void snd_midi_input_event(struct snd_rawmidi_substream *substream)
 		if (msynth->parser == NULL)
 			continue;
 		pbuf = buf;
-		while (res > 0) {
-			count = snd_midi_event_encode(msynth->parser, pbuf, res, &ev);
-			if (count < 0)
-				break;
-			pbuf += count;
-			res -= count;
-			if (ev.type != SNDRV_SEQ_EVENT_NONE) {
-				ev.source.port = msynth->seq_port;
-				ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS;
-				snd_seq_kernel_client_dispatch(msynth->seq_client, &ev, 1, 0);
-				/* clear event and reset header */
-				memset(&ev, 0, sizeof(ev));
-			}
+		while (res-- > 0) {
+			if (!snd_midi_event_encode_byte(msynth->parser,
+							*pbuf++, &ev))
+				continue;
+			ev.source.port = msynth->seq_port;
+			ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS;
+			snd_seq_kernel_client_dispatch(msynth->seq_client, &ev, 1, 0);
+			/* clear event and reset header */
+			memset(&ev, 0, sizeof(ev));
 		}
 	}
 }
diff --git a/sound/core/seq/seq_midi_emul.c b/sound/core/seq/seq_midi_emul.c
index 288f839a554b..c1975dd31871 100644
--- a/sound/core/seq/seq_midi_emul.c
+++ b/sound/core/seq/seq_midi_emul.c
@@ -318,7 +318,7 @@ do_control(struct snd_midi_op *ops, void *drv, struct snd_midi_channel_set *chse
 		break;
 	case MIDI_CTL_MSB_DATA_ENTRY:
 		chan->control[MIDI_CTL_LSB_DATA_ENTRY] = 0;
-		/* go through here */
+		/* fall through */
 	case MIDI_CTL_LSB_DATA_ENTRY:
 		if (chan->param_type == SNDRV_MIDI_PARAM_TYPE_REGISTERED)
 			rpn(ops, drv, chan, chset);
@@ -728,15 +728,3 @@ void snd_midi_channel_free_set(struct snd_midi_channel_set *chset)
 	kfree(chset);
 }
 EXPORT_SYMBOL(snd_midi_channel_free_set);
-
-static int __init alsa_seq_midi_emul_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_seq_midi_emul_exit(void)
-{
-}
-
-module_init(alsa_seq_midi_emul_init)
-module_exit(alsa_seq_midi_emul_exit)
diff --git a/sound/core/seq/seq_midi_event.c b/sound/core/seq/seq_midi_event.c
index 90bbbdbeba03..b11419537062 100644
--- a/sound/core/seq/seq_midi_event.c
+++ b/sound/core/seq/seq_midi_event.c
@@ -175,14 +175,6 @@ void snd_midi_event_reset_decode(struct snd_midi_event *dev)
 }
 EXPORT_SYMBOL(snd_midi_event_reset_decode);
 
-#if 0
-void snd_midi_event_init(struct snd_midi_event *dev)
-{
-	snd_midi_event_reset_encode(dev);
-	snd_midi_event_reset_decode(dev);
-}
-#endif  /*  0  */
-
 void snd_midi_event_no_status(struct snd_midi_event *dev, int on)
 {
 	dev->nostat = on ? 1 : 0;
@@ -190,69 +182,16 @@ void snd_midi_event_no_status(struct snd_midi_event *dev, int on)
 EXPORT_SYMBOL(snd_midi_event_no_status);
 
 /*
- * resize buffer
- */
-#if 0
-int snd_midi_event_resize_buffer(struct snd_midi_event *dev, int bufsize)
-{
-	unsigned char *new_buf, *old_buf;
-	unsigned long flags;
-
-	if (bufsize == dev->bufsize)
-		return 0;
-	new_buf = kmalloc(bufsize, GFP_KERNEL);
-	if (new_buf == NULL)
-		return -ENOMEM;
-	spin_lock_irqsave(&dev->lock, flags);
-	old_buf = dev->buf;
-	dev->buf = new_buf;
-	dev->bufsize = bufsize;
-	reset_encode(dev);
-	spin_unlock_irqrestore(&dev->lock, flags);
-	kfree(old_buf);
-	return 0;
-}
-#endif  /*  0  */
-
-/*
- *  read bytes and encode to sequencer event if finished
- *  return the size of encoded bytes
- */
-long snd_midi_event_encode(struct snd_midi_event *dev, unsigned char *buf, long count,
-			   struct snd_seq_event *ev)
-{
-	long result = 0;
-	int rc;
-
-	ev->type = SNDRV_SEQ_EVENT_NONE;
-
-	while (count-- > 0) {
-		rc = snd_midi_event_encode_byte(dev, *buf++, ev);
-		result++;
-		if (rc < 0)
-			return rc;
-		else if (rc > 0)
-			return result;
-	}
-
-	return result;
-}
-EXPORT_SYMBOL(snd_midi_event_encode);
-
-/*
  *  read one byte and encode to sequencer event:
- *  return 1 if MIDI bytes are encoded to an event
- *         0 data is not finished
- *         negative for error
+ *  return true if MIDI bytes are encoded to an event
+ *         false data is not finished
  */
-int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c,
-			       struct snd_seq_event *ev)
+bool snd_midi_event_encode_byte(struct snd_midi_event *dev, unsigned char c,
+				struct snd_seq_event *ev)
 {
-	int rc = 0;
+	bool rc = false;
 	unsigned long flags;
 
-	c &= 0xff;
-
 	if (c >= MIDI_CMD_COMMON_CLOCK) {
 		/* real-time event */
 		ev->type = status_event[ST_SPECIAL + c - 0xf0].event;
@@ -293,7 +232,7 @@ int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c,
 			status_event[dev->type].encode(dev, ev);
 		if (dev->type >= ST_SPECIAL)
 			dev->type = ST_INVALID;
-		rc = 1;
+		rc = true;
 	} else 	if (dev->type == ST_SYSEX) {
 		if (c == MIDI_CMD_COMMON_SYSEX_END ||
 		    dev->read >= dev->bufsize) {
@@ -306,7 +245,7 @@ int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c,
 				dev->read = 0; /* continue to parse */
 			else
 				reset_encode(dev); /* all parsed */
-			rc = 1;
+			rc = true;
 		}
 	}
 
@@ -531,15 +470,3 @@ static int extra_decode_xrpn(struct snd_midi_event *dev, unsigned char *buf,
 	}
 	return idx;
 }
-
-static int __init alsa_seq_midi_event_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_seq_midi_event_exit(void)
-{
-}
-
-module_init(alsa_seq_midi_event_init)
-module_exit(alsa_seq_midi_event_exit)
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index b377f5048352..3b3ac96f1f5f 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -159,18 +159,8 @@ static void queue_delete(struct snd_seq_queue *q)
 
 /*----------------------------------------------------------------*/
 
-/* setup queues */
-int __init snd_seq_queues_init(void)
-{
-	/*
-	memset(queue_list, 0, sizeof(queue_list));
-	num_queues = 0;
-	*/
-	return 0;
-}
-
 /* delete all existing queues */
-void __exit snd_seq_queues_delete(void)
+void snd_seq_queues_delete(void)
 {
 	int i;
 
diff --git a/sound/core/seq/seq_queue.h b/sound/core/seq/seq_queue.h
index 719093489a2c..e006fc8e3a36 100644
--- a/sound/core/seq/seq_queue.h
+++ b/sound/core/seq/seq_queue.h
@@ -63,9 +63,6 @@ struct snd_seq_queue {
 /* get the number of current queues */
 int snd_seq_queue_get_cur_queues(void);
 
-/* init queues structure */
-int snd_seq_queues_init(void);
-
 /* delete queues */ 
 void snd_seq_queues_delete(void);
 
@@ -112,28 +109,4 @@ int snd_seq_queue_is_used(int queueid, int client);
 
 int snd_seq_control_queue(struct snd_seq_event *ev, int atomic, int hop);
 
-/*
- * 64bit division - for sync stuff..
- */
-#if defined(i386) || defined(i486)
-
-#define udiv_qrnnd(q, r, n1, n0, d) \
-  __asm__ ("divl %4"		\
-	   : "=a" ((u32)(q)),	\
-	     "=d" ((u32)(r))	\
-	   : "0" ((u32)(n0)),	\
-	     "1" ((u32)(n1)),	\
-	     "rm" ((u32)(d)))
-
-#define u64_div(x,y,q) do {u32 __tmp; udiv_qrnnd(q, __tmp, (x)>>32, x, y);} while (0)
-#define u64_mod(x,y,r) do {u32 __tmp; udiv_qrnnd(__tmp, q, (x)>>32, x, y);} while (0)
-#define u64_divmod(x,y,q,r) udiv_qrnnd(q, r, (x)>>32, x, y)
-
-#else
-#define u64_div(x,y,q)	((q) = (u32)((u64)(x) / (u64)(y)))
-#define u64_mod(x,y,r)	((r) = (u32)((u64)(x) % (u64)(y)))
-#define u64_divmod(x,y,q,r) (u64_div(x,y,q), u64_mod(x,y,r))
-#endif
-
-
 #endif
diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index 289ae6bb81d9..a2f1c6b58693 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -89,7 +89,7 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev,
 	else
 		down_read(&rdev->filelist_sem);
 	list_for_each_entry(vmidi, &rdev->filelist, list) {
-		if (!vmidi->trigger)
+		if (!READ_ONCE(vmidi->trigger))
 			continue;
 		if (ev->type == SNDRV_SEQ_EVENT_SYSEX) {
 			if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE)
@@ -110,23 +110,6 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev,
 }
 
 /*
- * receive an event from the remote virmidi port
- *
- * for rawmidi inputs, you can call this function from the event
- * handler of a remote port which is attached to the virmidi via
- * SNDRV_VIRMIDI_SEQ_ATTACH.
- */
-#if 0
-int snd_virmidi_receive(struct snd_rawmidi *rmidi, struct snd_seq_event *ev)
-{
-	struct snd_virmidi_dev *rdev;
-
-	rdev = rmidi->private_data;
-	return snd_virmidi_dev_receive_event(rdev, ev, true);
-}
-#endif  /*  0  */
-
-/*
  * event handler of virmidi port
  */
 static int snd_virmidi_event_input(struct snd_seq_event *ev, int direct,
@@ -147,68 +130,62 @@ static void snd_virmidi_input_trigger(struct snd_rawmidi_substream *substream, i
 {
 	struct snd_virmidi *vmidi = substream->runtime->private_data;
 
-	if (up) {
-		vmidi->trigger = 1;
-	} else {
-		vmidi->trigger = 0;
-	}
+	WRITE_ONCE(vmidi->trigger, !!up);
 }
 
-/*
- * trigger rawmidi stream for output
+/* process rawmidi bytes and send events;
+ * we need no lock here for vmidi->event since it's handled only in this work
  */
-static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, int up)
+static void snd_vmidi_output_work(struct work_struct *work)
 {
-	struct snd_virmidi *vmidi = substream->runtime->private_data;
-	int count, res;
-	unsigned char buf[32], *pbuf;
-	unsigned long flags;
-
-	if (up) {
-		vmidi->trigger = 1;
-		if (vmidi->seq_mode == SNDRV_VIRMIDI_SEQ_DISPATCH &&
-		    !(vmidi->rdev->flags & SNDRV_VIRMIDI_SUBSCRIBE)) {
-			while (snd_rawmidi_transmit(substream, buf,
-						    sizeof(buf)) > 0) {
-				/* ignored */
-			}
-			return;
-		}
-		spin_lock_irqsave(&substream->runtime->lock, flags);
+	struct snd_virmidi *vmidi;
+	struct snd_rawmidi_substream *substream;
+	unsigned char input;
+	int ret;
+
+	vmidi = container_of(work, struct snd_virmidi, output_work);
+	substream = vmidi->substream;
+
+	/* discard the outputs in dispatch mode unless subscribed */
+	if (vmidi->seq_mode == SNDRV_VIRMIDI_SEQ_DISPATCH &&
+	    !(vmidi->rdev->flags & SNDRV_VIRMIDI_SUBSCRIBE)) {
+		while (!snd_rawmidi_transmit_empty(substream))
+			snd_rawmidi_transmit_ack(substream, 1);
+		return;
+	}
+
+	while (READ_ONCE(vmidi->trigger)) {
+		if (snd_rawmidi_transmit(substream, &input, 1) != 1)
+			break;
+		if (!snd_midi_event_encode_byte(vmidi->parser, input,
+						&vmidi->event))
+			continue;
 		if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) {
-			if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0)
-				goto out;
+			ret = snd_seq_kernel_client_dispatch(vmidi->client,
+							     &vmidi->event,
+							     false, 0);
 			vmidi->event.type = SNDRV_SEQ_EVENT_NONE;
-		}
-		while (1) {
-			count = __snd_rawmidi_transmit_peek(substream, buf, sizeof(buf));
-			if (count <= 0)
+			if (ret < 0)
 				break;
-			pbuf = buf;
-			while (count > 0) {
-				res = snd_midi_event_encode(vmidi->parser, pbuf, count, &vmidi->event);
-				if (res < 0) {
-					snd_midi_event_reset_encode(vmidi->parser);
-					continue;
-				}
-				__snd_rawmidi_transmit_ack(substream, res);
-				pbuf += res;
-				count -= res;
-				if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) {
-					if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0)
-						goto out;
-					vmidi->event.type = SNDRV_SEQ_EVENT_NONE;
-				}
-			}
 		}
-	out:
-		spin_unlock_irqrestore(&substream->runtime->lock, flags);
-	} else {
-		vmidi->trigger = 0;
+		/* rawmidi input might be huge, allow to have a break */
+		cond_resched();
 	}
 }
 
 /*
+ * trigger rawmidi stream for output
+ */
+static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, int up)
+{
+	struct snd_virmidi *vmidi = substream->runtime->private_data;
+
+	WRITE_ONCE(vmidi->trigger, !!up);
+	if (up)
+		queue_work(system_highpri_wq, &vmidi->output_work);
+}
+
+/*
  * open rawmidi handle for input
  */
 static int snd_virmidi_input_open(struct snd_rawmidi_substream *substream)
@@ -260,6 +237,7 @@ static int snd_virmidi_output_open(struct snd_rawmidi_substream *substream)
 	vmidi->port = rdev->port;
 	snd_virmidi_init_event(vmidi, &vmidi->event);
 	vmidi->rdev = rdev;
+	INIT_WORK(&vmidi->output_work, snd_vmidi_output_work);
 	runtime->private_data = vmidi;
 	return 0;
 }
@@ -289,6 +267,9 @@ static int snd_virmidi_input_close(struct snd_rawmidi_substream *substream)
 static int snd_virmidi_output_close(struct snd_rawmidi_substream *substream)
 {
 	struct snd_virmidi *vmidi = substream->runtime->private_data;
+
+	WRITE_ONCE(vmidi->trigger, false); /* to be sure */
+	cancel_work_sync(&vmidi->output_work);
 	snd_midi_event_free(vmidi->parser);
 	substream->runtime->private_data = NULL;
 	kfree(vmidi);
@@ -546,19 +527,3 @@ int snd_virmidi_new(struct snd_card *card, int device, struct snd_rawmidi **rrmi
 	return 0;
 }
 EXPORT_SYMBOL(snd_virmidi_new);
-
-/*
- *  ENTRY functions
- */
-
-static int __init alsa_virmidi_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_virmidi_exit(void)
-{
-}
-
-module_init(alsa_virmidi_init)
-module_exit(alsa_virmidi_exit)
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 665089c45560..61a0cec6e1f6 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -883,6 +883,11 @@ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid,
 
 	if (snd_BUG_ON(!tid))
 		return -EINVAL;
+	if (tid->dev_class == SNDRV_TIMER_CLASS_CARD ||
+	    tid->dev_class == SNDRV_TIMER_CLASS_PCM) {
+		if (WARN_ON(!card))
+			return -EINVAL;
+	}
 	if (rtimer)
 		*rtimer = NULL;
 	timer = kzalloc(sizeof(*timer), GFP_KERNEL);
@@ -1520,7 +1525,7 @@ static int snd_timer_user_next_device(struct snd_timer_id __user *_tid)
 				} else {
 					if (id.subdevice < 0)
 						id.subdevice = 0;
-					else
+					else if (id.subdevice < INT_MAX)
 						id.subdevice++;
 				}
 			}
diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index 78a2fdc38531..1e34e6381baa 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -778,7 +778,6 @@ static const struct snd_pcm_ops loopback_pcm_ops = {
 	.trigger =	loopback_trigger,
 	.pointer =	loopback_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 static int loopback_pcm_new(struct loopback *loopback,
diff --git a/sound/drivers/mpu401/mpu401_uart.c b/sound/drivers/mpu401/mpu401_uart.c
index 3e745f47dd2f..dae26e856b26 100644
--- a/sound/drivers/mpu401/mpu401_uart.c
+++ b/sound/drivers/mpu401/mpu401_uart.c
@@ -617,19 +617,3 @@ free_device:
 }
 
 EXPORT_SYMBOL(snd_mpu401_uart_new);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_mpu401_uart_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_mpu401_uart_exit(void)
-{
-}
-
-module_init(alsa_mpu401_uart_init)
-module_exit(alsa_mpu401_uart_exit)
diff --git a/sound/drivers/opl3/opl3_drums.c b/sound/drivers/opl3/opl3_drums.c
index 73694380734a..14929822956c 100644
--- a/sound/drivers/opl3/opl3_drums.c
+++ b/sound/drivers/opl3/opl3_drums.c
@@ -21,8 +21,6 @@
 
 #include "opl3_voice.h"
 
-extern char snd_opl3_regmap[MAX_OPL2_VOICES][4];
-
 static char snd_opl3_drum_table[47] =
 {
 	OPL3_BASSDRUM_ON,  OPL3_BASSDRUM_ON,  OPL3_HIHAT_ON,	/* 35 - 37 */
diff --git a/sound/drivers/opl3/opl3_lib.c b/sound/drivers/opl3/opl3_lib.c
index 588963d6be28..cf86c36c7c3b 100644
--- a/sound/drivers/opl3/opl3_lib.c
+++ b/sound/drivers/opl3/opl3_lib.c
@@ -31,13 +31,12 @@
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <sound/minors.h>
+#include "opl3_voice.h"
 
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, Hannu Savolainen 1993-1996, Rob Hooft");
 MODULE_DESCRIPTION("Routines for control of AdLib FM cards (OPL2/OPL3/OPL4 chips)");
 MODULE_LICENSE("GPL");
 
-extern char snd_opl3_regmap[MAX_OPL2_VOICES][4];
-
 static void snd_opl2_command(struct snd_opl3 * opl3, unsigned short cmd, unsigned char val)
 {
 	unsigned long flags;
@@ -539,19 +538,3 @@ int snd_opl3_hwdep_new(struct snd_opl3 * opl3,
 }
 
 EXPORT_SYMBOL(snd_opl3_hwdep_new);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_opl3_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_opl3_exit(void)
-{
-}
-
-module_init(alsa_opl3_init)
-module_exit(alsa_opl3_exit)
diff --git a/sound/drivers/opl3/opl3_midi.c b/sound/drivers/opl3/opl3_midi.c
index bb3f3a5a6951..a33cb744e96c 100644
--- a/sound/drivers/opl3/opl3_midi.c
+++ b/sound/drivers/opl3/opl3_midi.c
@@ -25,10 +25,6 @@
 #include "opl3_voice.h"
 #include <sound/asoundef.h>
 
-extern char snd_opl3_regmap[MAX_OPL2_VOICES][4];
-
-extern bool use_internal_drums;
-
 static void snd_opl3_note_off_unsafe(void *p, int note, int vel,
 				     struct snd_midi_channel *chan);
 /*
@@ -372,6 +368,7 @@ void snd_opl3_note_on(void *p, int note, int vel, struct snd_midi_channel *chan)
 			instr_4op = 1;
 			break;
 		}
+		/* fall through */
 	default:
 		spin_unlock_irqrestore(&opl3->voice_lock, flags);
 		return;
@@ -721,9 +718,6 @@ void snd_opl3_note_off(void *p, int note, int vel,
  */
 void snd_opl3_key_press(void *p, int note, int vel, struct snd_midi_channel *chan)
 {
-  	struct snd_opl3 *opl3;
-
-	opl3 = p;
 #ifdef DEBUG_MIDI
 	snd_printk(KERN_DEBUG "Key pressure, ch#: %i, inst#: %i\n",
 		   chan->number, chan->midi_program);
@@ -735,9 +729,6 @@ void snd_opl3_key_press(void *p, int note, int vel, struct snd_midi_channel *cha
  */
 void snd_opl3_terminate_note(void *p, int note, struct snd_midi_channel *chan)
 {
-  	struct snd_opl3 *opl3;
-
-	opl3 = p;
 #ifdef DEBUG_MIDI
 	snd_printk(KERN_DEBUG "Terminate note, ch#: %i, inst#: %i\n",
 		   chan->number, chan->midi_program);
@@ -861,9 +852,6 @@ void snd_opl3_control(void *p, int type, struct snd_midi_channel *chan)
 void snd_opl3_nrpn(void *p, struct snd_midi_channel *chan,
 		   struct snd_midi_channel_set *chset)
 {
-  	struct snd_opl3 *opl3;
-
-	opl3 = p;
 #ifdef DEBUG_MIDI
 	snd_printk(KERN_DEBUG "NRPN, ch#: %i, inst#: %i\n",
 		   chan->number, chan->midi_program);
@@ -876,9 +864,6 @@ void snd_opl3_nrpn(void *p, struct snd_midi_channel *chan,
 void snd_opl3_sysex(void *p, unsigned char *buf, int len,
 		    int parsed, struct snd_midi_channel_set *chset)
 {
-  	struct snd_opl3 *opl3;
-
-	opl3 = p;
 #ifdef DEBUG_MIDI
 	snd_printk(KERN_DEBUG "SYSEX\n");
 #endif
diff --git a/sound/drivers/opl3/opl3_oss.c b/sound/drivers/opl3/opl3_oss.c
index 22c3e4bca220..869220ced4ed 100644
--- a/sound/drivers/opl3/opl3_oss.c
+++ b/sound/drivers/opl3/opl3_oss.c
@@ -29,8 +29,6 @@ static int snd_opl3_reset_seq_oss(struct snd_seq_oss_arg *arg);
 
 /* operators */
 
-extern struct snd_midi_op opl3_ops;
-
 static struct snd_seq_oss_callback oss_callback = {
 	.owner = 	THIS_MODULE,
 	.open =		snd_opl3_open_seq_oss,
@@ -233,11 +231,8 @@ static int snd_opl3_load_patch_seq_oss(struct snd_seq_oss_arg *arg, int format,
 static int snd_opl3_ioctl_seq_oss(struct snd_seq_oss_arg *arg, unsigned int cmd,
 				  unsigned long ioarg)
 {
-	struct snd_opl3 *opl3;
-
 	if (snd_BUG_ON(!arg))
 		return -ENXIO;
-	opl3 = arg->private_data;
 	switch (cmd) {
 		case SNDCTL_FM_LOAD_INSTR:
 			snd_printk(KERN_ERR "OPL3: "
@@ -261,11 +256,8 @@ static int snd_opl3_ioctl_seq_oss(struct snd_seq_oss_arg *arg, unsigned int cmd,
 /* reset device */
 static int snd_opl3_reset_seq_oss(struct snd_seq_oss_arg *arg)
 {
-	struct snd_opl3 *opl3;
-
 	if (snd_BUG_ON(!arg))
 		return -ENXIO;
-	opl3 = arg->private_data;
 
 	return 0;
 }
diff --git a/sound/drivers/opl3/opl3_synth.c b/sound/drivers/opl3/opl3_synth.c
index 42920a243328..d522925fc5c0 100644
--- a/sound/drivers/opl3/opl3_synth.c
+++ b/sound/drivers/opl3/opl3_synth.c
@@ -24,6 +24,7 @@
 #include <linux/nospec.h>
 #include <sound/opl3.h>
 #include <sound/asound_fm.h>
+#include "opl3_voice.h"
 
 #if IS_ENABLED(CONFIG_SND_SEQUENCER)
 #define OPL3_SUPPORT_SYNTH
diff --git a/sound/drivers/opl3/opl3_voice.h b/sound/drivers/opl3/opl3_voice.h
index a2445163008e..5b02bd49fde4 100644
--- a/sound/drivers/opl3/opl3_voice.h
+++ b/sound/drivers/opl3/opl3_voice.h
@@ -52,4 +52,8 @@ void snd_opl3_free_seq_oss(struct snd_opl3 *opl3);
 #define snd_opl3_free_seq_oss(opl3) /* NOP */
 #endif
 
+extern char snd_opl3_regmap[MAX_OPL2_VOICES][4];
+extern bool use_internal_drums;
+extern struct snd_midi_op opl3_ops;
+
 #endif
diff --git a/sound/drivers/opl4/opl4_lib.c b/sound/drivers/opl4/opl4_lib.c
index db76a5bf2bd2..819d2dce2a19 100644
--- a/sound/drivers/opl4/opl4_lib.c
+++ b/sound/drivers/opl4/opl4_lib.c
@@ -263,15 +263,3 @@ int snd_opl4_create(struct snd_card *card,
 }
 
 EXPORT_SYMBOL(snd_opl4_create);
-
-static int __init alsa_opl4_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_opl4_exit(void)
-{
-}
-
-module_init(alsa_opl4_init)
-module_exit(alsa_opl4_exit)
diff --git a/sound/drivers/vx/vx_core.c b/sound/drivers/vx/vx_core.c
index 121357397a6d..04368dd59a4c 100644
--- a/sound/drivers/vx/vx_core.c
+++ b/sound/drivers/vx/vx_core.c
@@ -815,18 +815,3 @@ struct vx_core *snd_vx_create(struct snd_card *card, struct snd_vx_hardware *hw,
 }
 
 EXPORT_SYMBOL(snd_vx_create);
-
-/*
- * module entries
- */
-static int __init alsa_vx_core_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_vx_core_exit(void)
-{
-}
-
-module_init(alsa_vx_core_init)
-module_exit(alsa_vx_core_exit)
diff --git a/sound/drivers/vx/vx_pcm.c b/sound/drivers/vx/vx_pcm.c
index 380a028469c4..ba80f459bdc5 100644
--- a/sound/drivers/vx/vx_pcm.c
+++ b/sound/drivers/vx/vx_pcm.c
@@ -883,7 +883,6 @@ static const struct snd_pcm_ops vx_pcm_playback_ops = {
 	.trigger =	vx_pcm_trigger,
 	.pointer =	vx_pcm_playback_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 
@@ -1105,7 +1104,6 @@ static const struct snd_pcm_ops vx_pcm_capture_ops = {
 	.trigger =	vx_pcm_trigger,
 	.pointer =	vx_pcm_capture_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 
diff --git a/sound/firewire/bebob/bebob_pcm.c b/sound/firewire/bebob/bebob_pcm.c
index e6adab3ef42e..ea9b86450580 100644
--- a/sound/firewire/bebob/bebob_pcm.c
+++ b/sound/firewire/bebob/bebob_pcm.c
@@ -373,7 +373,6 @@ int snd_bebob_create_pcm_devices(struct snd_bebob *bebob)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/dice/dice-alesis.c b/sound/firewire/dice/dice-alesis.c
index b2efb1c71a98..218292bdace6 100644
--- a/sound/firewire/dice/dice-alesis.c
+++ b/sound/firewire/dice/dice-alesis.c
@@ -37,7 +37,7 @@ int snd_dice_detect_alesis_formats(struct snd_dice *dice)
 				MAX_STREAMS * SND_DICE_RATE_MODE_COUNT *
 				sizeof(unsigned int));
 	} else {
-		memcpy(dice->rx_pcm_chs, alesis_io26_tx_pcm_chs,
+		memcpy(dice->tx_pcm_chs, alesis_io26_tx_pcm_chs,
 				MAX_STREAMS * SND_DICE_RATE_MODE_COUNT *
 				sizeof(unsigned int));
 	}
diff --git a/sound/firewire/dice/dice-pcm.c b/sound/firewire/dice/dice-pcm.c
index 80351b29fe0d..bb3ef5ff3488 100644
--- a/sound/firewire/dice/dice-pcm.c
+++ b/sound/firewire/dice/dice-pcm.c
@@ -412,7 +412,6 @@ int snd_dice_create_pcm(struct snd_dice *dice)
 		.pointer   = capture_pointer,
 		.ack       = capture_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open      = pcm_open,
@@ -425,7 +424,6 @@ int snd_dice_create_pcm(struct snd_dice *dice)
 		.pointer   = playback_pointer,
 		.ack       = playback_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	unsigned int capture, playback;
diff --git a/sound/firewire/digi00x/digi00x-pcm.c b/sound/firewire/digi00x/digi00x-pcm.c
index 796f4b4645f5..fdcff0460c53 100644
--- a/sound/firewire/digi00x/digi00x-pcm.c
+++ b/sound/firewire/digi00x/digi00x-pcm.c
@@ -352,7 +352,6 @@ int snd_dg00x_create_pcm_devices(struct snd_dg00x *dg00x)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/fireface/ff-pcm.c b/sound/firewire/fireface/ff-pcm.c
index e3c16308363d..bf47f9ec8703 100644
--- a/sound/firewire/fireface/ff-pcm.c
+++ b/sound/firewire/fireface/ff-pcm.c
@@ -383,7 +383,6 @@ int snd_ff_create_pcm_devices(struct snd_ff *ff)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/fireworks/fireworks_pcm.c b/sound/firewire/fireworks/fireworks_pcm.c
index 40faed5e6968..aed566d82726 100644
--- a/sound/firewire/fireworks/fireworks_pcm.c
+++ b/sound/firewire/fireworks/fireworks_pcm.c
@@ -397,7 +397,6 @@ int snd_efw_create_pcm_devices(struct snd_efw *efw)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c
index 3919e186a30b..30957477e005 100644
--- a/sound/firewire/isight.c
+++ b/sound/firewire/isight.c
@@ -454,7 +454,6 @@ static int isight_create_pcm(struct isight *isight)
 		.trigger   = isight_trigger,
 		.pointer   = isight_pointer,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/motu/motu-pcm.c b/sound/firewire/motu/motu-pcm.c
index 4330220890e8..ab69d7e6ac05 100644
--- a/sound/firewire/motu/motu-pcm.c
+++ b/sound/firewire/motu/motu-pcm.c
@@ -363,7 +363,6 @@ int snd_motu_create_pcm_devices(struct snd_motu *motu)
 		.pointer   = capture_pointer,
 		.ack       = capture_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open      = pcm_open,
@@ -376,7 +375,6 @@ int snd_motu_create_pcm_devices(struct snd_motu *motu)
 		.pointer   = playback_pointer,
 		.ack       = playback_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/motu/motu-protocol-v2.c b/sound/firewire/motu/motu-protocol-v2.c
index 525b746330be..453fc29fade7 100644
--- a/sound/firewire/motu/motu-protocol-v2.c
+++ b/sound/firewire/motu/motu-protocol-v2.c
@@ -13,6 +13,8 @@
 #define  V2_CLOCK_RATE_SHIFT			3
 #define  V2_CLOCK_SRC_MASK			0x00000007
 #define  V2_CLOCK_SRC_SHIFT			0
+#define  V2_CLOCK_TRAVELER_FETCH_DISABLE	0x04000000
+#define  V2_CLOCK_TRAVELER_FETCH_ENABLE		0x03000000
 
 #define V2_IN_OUT_CONF_OFFSET			0x0c04
 #define  V2_OPT_OUT_IFACE_MASK			0x00000c00
@@ -66,6 +68,11 @@ static int v2_set_clock_rate(struct snd_motu *motu, unsigned int rate)
 	data &= ~V2_CLOCK_RATE_MASK;
 	data |= i << V2_CLOCK_RATE_SHIFT;
 
+	if (motu->spec == &snd_motu_spec_traveler) {
+		data &= ~V2_CLOCK_TRAVELER_FETCH_ENABLE;
+		data |= V2_CLOCK_TRAVELER_FETCH_DISABLE;
+	}
+
 	reg = cpu_to_be32(data);
 	return snd_motu_transaction_write(motu, V2_CLOCK_STATUS_OFFSET, &reg,
 					  sizeof(reg));
@@ -121,8 +128,31 @@ static int v2_get_clock_source(struct snd_motu *motu,
 
 static int v2_switch_fetching_mode(struct snd_motu *motu, bool enable)
 {
-	/* V2 protocol doesn't have this feature. */
-	return 0;
+	__be32 reg;
+	u32 data;
+	int err = 0;
+
+	if (motu->spec == &snd_motu_spec_traveler) {
+		err = snd_motu_transaction_read(motu, V2_CLOCK_STATUS_OFFSET,
+						&reg, sizeof(reg));
+		if (err < 0)
+			return err;
+		data = be32_to_cpu(reg);
+
+		data &= ~(V2_CLOCK_TRAVELER_FETCH_DISABLE |
+			  V2_CLOCK_TRAVELER_FETCH_ENABLE);
+
+		if (enable)
+			data |= V2_CLOCK_TRAVELER_FETCH_ENABLE;
+		else
+			data |= V2_CLOCK_TRAVELER_FETCH_DISABLE;
+
+		reg = cpu_to_be32(data);
+		err = snd_motu_transaction_write(motu, V2_CLOCK_STATUS_OFFSET,
+						 &reg, sizeof(reg));
+	}
+
+	return err;
 }
 
 static void calculate_fixed_part(struct snd_motu_packet_format *formats,
@@ -149,11 +179,20 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 			pcm_chunks[1] += 2;
 		}
 	} else {
-		/*
-		 * Packets to v2 units transfer main-out-1/2 and phone-out-1/2.
-		 */
-		pcm_chunks[0] += 4;
-		pcm_chunks[1] += 4;
+		if (flags & SND_MOTU_SPEC_RX_SEPARETED_MAIN) {
+			pcm_chunks[0] += 2;
+			pcm_chunks[1] += 2;
+		}
+
+		// Packets to v2 units include 2 chunks for phone 1/2, except
+		// for 176.4/192.0 kHz.
+		pcm_chunks[0] += 2;
+		pcm_chunks[1] += 2;
+	}
+
+	if (flags & SND_MOTU_SPEC_HAS_AESEBU_IFACE) {
+		pcm_chunks[0] += 2;
+		pcm_chunks[1] += 2;
 	}
 
 	/*
@@ -164,19 +203,16 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 	pcm_chunks[0] += 2;
 	pcm_chunks[1] += 2;
 
-	/* This part should be multiples of 4. */
-	formats->fixed_part_pcm_chunks[0] = round_up(2 + pcm_chunks[0], 4) - 2;
-	formats->fixed_part_pcm_chunks[1] = round_up(2 + pcm_chunks[1], 4) - 2;
-	if (flags & SND_MOTU_SPEC_SUPPORT_CLOCK_X4)
-		formats->fixed_part_pcm_chunks[2] =
-					round_up(2 + pcm_chunks[2], 4) - 2;
+	formats->fixed_part_pcm_chunks[0] = pcm_chunks[0];
+	formats->fixed_part_pcm_chunks[1] = pcm_chunks[1];
+	formats->fixed_part_pcm_chunks[2] = pcm_chunks[2];
 }
 
 static void calculate_differed_part(struct snd_motu_packet_format *formats,
 				    enum snd_motu_spec_flags flags,
 				    u32 data, u32 mask, u32 shift)
 {
-	unsigned char pcm_chunks[3] = {0, 0};
+	unsigned char pcm_chunks[2] = {0, 0};
 
 	/*
 	 * When optical interfaces are configured for S/PDIF (TOSLINK),
diff --git a/sound/firewire/motu/motu-protocol-v3.c b/sound/firewire/motu/motu-protocol-v3.c
index c7cd9864dc4d..7cc80a05e91f 100644
--- a/sound/firewire/motu/motu-protocol-v3.c
+++ b/sound/firewire/motu/motu-protocol-v3.c
@@ -188,11 +188,20 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 			pcm_chunks[1] += 2;
 		}
 	} else {
-		/*
-		 * Packets to v2 units transfer main-out-1/2 and phone-out-1/2.
-		 */
-		pcm_chunks[0] += 4;
-		pcm_chunks[1] += 4;
+		if (flags & SND_MOTU_SPEC_RX_SEPARETED_MAIN) {
+			pcm_chunks[0] += 2;
+			pcm_chunks[1] += 2;
+		}
+
+		// Packets to v3 units include 2 chunks for phone 1/2, except
+		// for 176.4/192.0 kHz.
+		pcm_chunks[0] += 2;
+		pcm_chunks[1] += 2;
+	}
+
+	if (flags & SND_MOTU_SPEC_HAS_AESEBU_IFACE) {
+		pcm_chunks[0] += 2;
+		pcm_chunks[1] += 2;
 	}
 
 	/*
diff --git a/sound/firewire/motu/motu.c b/sound/firewire/motu/motu.c
index 0d6b526105ab..300d31b6f191 100644
--- a/sound/firewire/motu/motu.c
+++ b/sound/firewire/motu/motu.c
@@ -200,6 +200,22 @@ static const struct snd_motu_spec motu_828mk2 = {
 	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
+		 SND_MOTU_SPEC_RX_SEPARETED_MAIN |
+		 SND_MOTU_SPEC_HAS_OPT_IFACE_A |
+		 SND_MOTU_SPEC_RX_MIDI_2ND_Q |
+		 SND_MOTU_SPEC_TX_MIDI_2ND_Q,
+
+	.analog_in_ports = 8,
+	.analog_out_ports = 8,
+};
+
+const struct snd_motu_spec snd_motu_spec_traveler = {
+	.name = "Traveler",
+	.protocol = &snd_motu_protocol_v2,
+	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
+		 SND_MOTU_SPEC_SUPPORT_CLOCK_X4 |
+		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
+		 SND_MOTU_SPEC_HAS_AESEBU_IFACE |
 		 SND_MOTU_SPEC_HAS_OPT_IFACE_A |
 		 SND_MOTU_SPEC_RX_MIDI_2ND_Q |
 		 SND_MOTU_SPEC_TX_MIDI_2ND_Q,
@@ -216,6 +232,7 @@ static const struct snd_motu_spec motu_828mk3 = {
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
 		 SND_MOTU_SPEC_TX_REVERB_CHUNK |
+		 SND_MOTU_SPEC_RX_SEPARETED_MAIN |
 		 SND_MOTU_SPEC_HAS_OPT_IFACE_A |
 		 SND_MOTU_SPEC_HAS_OPT_IFACE_B |
 		 SND_MOTU_SPEC_RX_MIDI_3RD_Q |
@@ -231,6 +248,7 @@ static const struct snd_motu_spec motu_audio_express = {
 	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
+		 SND_MOTU_SPEC_RX_SEPARETED_MAIN |
 		 SND_MOTU_SPEC_RX_MIDI_2ND_Q |
 		 SND_MOTU_SPEC_TX_MIDI_3RD_Q,
 	.analog_in_ports = 2,
@@ -250,6 +268,7 @@ static const struct snd_motu_spec motu_audio_express = {
 
 static const struct ieee1394_device_id motu_id_table[] = {
 	SND_MOTU_DEV_ENTRY(0x101800, &motu_828mk2),
+	SND_MOTU_DEV_ENTRY(0x107800, &snd_motu_spec_traveler),
 	SND_MOTU_DEV_ENTRY(0x106800, &motu_828mk3),	/* FireWire only. */
 	SND_MOTU_DEV_ENTRY(0x100800, &motu_828mk3),	/* Hybrid. */
 	SND_MOTU_DEV_ENTRY(0x104800, &motu_audio_express),
diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h
index 4b23cf337c4b..fd5327d30ab1 100644
--- a/sound/firewire/motu/motu.h
+++ b/sound/firewire/motu/motu.h
@@ -79,13 +79,14 @@ enum snd_motu_spec_flags {
 	SND_MOTU_SPEC_TX_MICINST_CHUNK	= 0x0004,
 	SND_MOTU_SPEC_TX_RETURN_CHUNK	= 0x0008,
 	SND_MOTU_SPEC_TX_REVERB_CHUNK	= 0x0010,
-	SND_MOTU_SPEC_TX_AESEBU_CHUNK	= 0x0020,
+	SND_MOTU_SPEC_HAS_AESEBU_IFACE	= 0x0020,
 	SND_MOTU_SPEC_HAS_OPT_IFACE_A	= 0x0040,
 	SND_MOTU_SPEC_HAS_OPT_IFACE_B	= 0x0080,
 	SND_MOTU_SPEC_RX_MIDI_2ND_Q	= 0x0100,
 	SND_MOTU_SPEC_RX_MIDI_3RD_Q	= 0x0200,
 	SND_MOTU_SPEC_TX_MIDI_2ND_Q	= 0x0400,
 	SND_MOTU_SPEC_TX_MIDI_3RD_Q	= 0x0800,
+	SND_MOTU_SPEC_RX_SEPARETED_MAIN	= 0x1000,
 };
 
 #define SND_MOTU_CLOCK_RATE_COUNT	6
@@ -128,6 +129,8 @@ struct snd_motu_spec {
 extern const struct snd_motu_protocol snd_motu_protocol_v2;
 extern const struct snd_motu_protocol snd_motu_protocol_v3;
 
+extern const struct snd_motu_spec snd_motu_spec_traveler;
+
 int amdtp_motu_init(struct amdtp_stream *s, struct fw_unit *unit,
 		    enum amdtp_stream_direction dir,
 		    const struct snd_motu_protocol *const protocol);
diff --git a/sound/firewire/oxfw/oxfw-pcm.c b/sound/firewire/oxfw/oxfw-pcm.c
index 3dd46285c0e2..b3f6503dd34d 100644
--- a/sound/firewire/oxfw/oxfw-pcm.c
+++ b/sound/firewire/oxfw/oxfw-pcm.c
@@ -389,7 +389,6 @@ int snd_oxfw_create_pcm(struct snd_oxfw *oxfw)
 		.pointer   = pcm_capture_pointer,
 		.ack       = pcm_capture_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open      = pcm_open,
@@ -402,7 +401,6 @@ int snd_oxfw_create_pcm(struct snd_oxfw *oxfw)
 		.pointer   = pcm_playback_pointer,
 		.ack       = pcm_playback_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	unsigned int cap = 0;
diff --git a/sound/firewire/tascam/tascam-pcm.c b/sound/firewire/tascam/tascam-pcm.c
index 6ec8ec634d4d..e4cc8990e195 100644
--- a/sound/firewire/tascam/tascam-pcm.c
+++ b/sound/firewire/tascam/tascam-pcm.c
@@ -279,7 +279,6 @@ int snd_tscm_create_pcm_devices(struct snd_tscm *tscm)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/hda/Kconfig b/sound/hda/Kconfig
index 3129546398d0..2d90e11b3eaa 100644
--- a/sound/hda/Kconfig
+++ b/sound/hda/Kconfig
@@ -5,11 +5,12 @@ config SND_HDA_CORE
 config SND_HDA_DSP_LOADER
 	bool
 
+config SND_HDA_COMPONENT
+	bool
+
 config SND_HDA_I915
 	bool
-	default y
-	depends on DRM_I915
-	depends on SND_HDA_CORE
+	select SND_HDA_COMPONENT
 
 config SND_HDA_EXT_CORE
        tristate
diff --git a/sound/hda/Makefile b/sound/hda/Makefile
index e4e726f2ce98..2160202e2dc1 100644
--- a/sound/hda/Makefile
+++ b/sound/hda/Makefile
@@ -6,6 +6,7 @@ snd-hda-core-objs += trace.o
 CFLAGS_trace.o := -I$(src)
 
 # for sync with i915 gfx driver
+snd-hda-core-$(CONFIG_SND_HDA_COMPONENT) += hdac_component.o
 snd-hda-core-$(CONFIG_SND_HDA_I915) += hdac_i915.o
 
 obj-$(CONFIG_SND_HDA_CORE) += snd-hda-core.o
diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c
index 0daf31383084..9c37d9af3023 100644
--- a/sound/hda/ext/hdac_ext_bus.c
+++ b/sound/hda/ext/hdac_ext_bus.c
@@ -87,9 +87,10 @@ static const struct hdac_io_ops hdac_ext_default_io = {
  *
  * Returns 0 if successful, or a negative error code.
  */
-int snd_hdac_ext_bus_init(struct hdac_ext_bus *ebus, struct device *dev,
+int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 			const struct hdac_bus_ops *ops,
-			const struct hdac_io_ops *io_ops)
+			const struct hdac_io_ops *io_ops,
+			const struct hdac_ext_bus_ops *ext_ops)
 {
 	int ret;
 	static int idx;
@@ -98,15 +99,16 @@ int snd_hdac_ext_bus_init(struct hdac_ext_bus *ebus, struct device *dev,
 	if (io_ops == NULL)
 		io_ops = &hdac_ext_default_io;
 
-	ret = snd_hdac_bus_init(&ebus->bus, dev, ops, io_ops);
+	ret = snd_hdac_bus_init(bus, dev, ops, io_ops);
 	if (ret < 0)
 		return ret;
 
-	INIT_LIST_HEAD(&ebus->hlink_list);
-	ebus->idx = idx++;
+	bus->ext_ops = ext_ops;
+	INIT_LIST_HEAD(&bus->hlink_list);
+	bus->idx = idx++;
 
-	mutex_init(&ebus->lock);
-	ebus->cmd_dma_state = true;
+	mutex_init(&bus->lock);
+	bus->cmd_dma_state = true;
 
 	return 0;
 }
@@ -116,10 +118,10 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_init);
  * snd_hdac_ext_bus_exit - clean up a HD-audio extended bus
  * @ebus: the pointer to extended bus object
  */
-void snd_hdac_ext_bus_exit(struct hdac_ext_bus *ebus)
+void snd_hdac_ext_bus_exit(struct hdac_bus *bus)
 {
-	snd_hdac_bus_exit(&ebus->bus);
-	WARN_ON(!list_empty(&ebus->hlink_list));
+	snd_hdac_bus_exit(bus);
+	WARN_ON(!list_empty(&bus->hlink_list));
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_exit);
 
@@ -135,21 +137,15 @@ static void default_release(struct device *dev)
  *
  * Returns zero for success or a negative error code.
  */
-int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *ebus, int addr)
+int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr,
+					struct hdac_device *hdev)
 {
-	struct hdac_ext_device *edev;
-	struct hdac_device *hdev = NULL;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	char name[15];
 	int ret;
 
-	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
-	if (!edev)
-		return -ENOMEM;
-	hdev = &edev->hdev;
-	edev->ebus = ebus;
+	hdev->bus = bus;
 
-	snprintf(name, sizeof(name), "ehdaudio%dD%d", ebus->idx, addr);
+	snprintf(name, sizeof(name), "ehdaudio%dD%d", bus->idx, addr);
 
 	ret  = snd_hdac_device_init(hdev, bus, name, addr);
 	if (ret < 0) {
@@ -176,10 +172,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_init);
  */
 void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev)
 {
-	struct hdac_ext_device *edev = to_ehdac_device(hdev);
-
 	snd_hdac_device_exit(hdev);
-	kfree(edev);
+	kfree(hdev);
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_exit);
 
@@ -188,14 +182,14 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_exit);
  *
  * @ebus: HD-audio extended bus
  */
-void snd_hdac_ext_bus_device_remove(struct hdac_ext_bus *ebus)
+void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus)
 {
 	struct hdac_device *codec, *__codec;
 	/*
 	 * we need to remove all the codec devices objects created in the
 	 * snd_hdac_ext_bus_device_init
 	 */
-	list_for_each_entry_safe(codec, __codec, &ebus->bus.codec_list, list) {
+	list_for_each_entry_safe(codec, __codec, &bus->codec_list, list) {
 		snd_hdac_device_unregister(codec);
 		put_device(&codec->dev);
 	}
@@ -204,35 +198,31 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_remove);
 #define dev_to_hdac(dev) (container_of((dev), \
 			struct hdac_device, dev))
 
-static inline struct hdac_ext_driver *get_edrv(struct device *dev)
+static inline struct hdac_driver *get_hdrv(struct device *dev)
 {
 	struct hdac_driver *hdrv = drv_to_hdac_driver(dev->driver);
-	struct hdac_ext_driver *edrv = to_ehdac_driver(hdrv);
-
-	return edrv;
+	return hdrv;
 }
 
-static inline struct hdac_ext_device *get_edev(struct device *dev)
+static inline struct hdac_device *get_hdev(struct device *dev)
 {
 	struct hdac_device *hdev = dev_to_hdac_dev(dev);
-	struct hdac_ext_device *edev = to_ehdac_device(hdev);
-
-	return edev;
+	return hdev;
 }
 
 static int hda_ext_drv_probe(struct device *dev)
 {
-	return (get_edrv(dev))->probe(get_edev(dev));
+	return (get_hdrv(dev))->probe(get_hdev(dev));
 }
 
 static int hdac_ext_drv_remove(struct device *dev)
 {
-	return (get_edrv(dev))->remove(get_edev(dev));
+	return (get_hdrv(dev))->remove(get_hdev(dev));
 }
 
 static void hdac_ext_drv_shutdown(struct device *dev)
 {
-	return (get_edrv(dev))->shutdown(get_edev(dev));
+	return (get_hdrv(dev))->shutdown(get_hdev(dev));
 }
 
 /**
@@ -240,20 +230,20 @@ static void hdac_ext_drv_shutdown(struct device *dev)
  *
  * @drv: ext hda driver structure
  */
-int snd_hda_ext_driver_register(struct hdac_ext_driver *drv)
+int snd_hda_ext_driver_register(struct hdac_driver *drv)
 {
-	drv->hdac.type = HDA_DEV_ASOC;
-	drv->hdac.driver.bus = &snd_hda_bus_type;
+	drv->type = HDA_DEV_ASOC;
+	drv->driver.bus = &snd_hda_bus_type;
 	/* we use default match */
 
 	if (drv->probe)
-		drv->hdac.driver.probe = hda_ext_drv_probe;
+		drv->driver.probe = hda_ext_drv_probe;
 	if (drv->remove)
-		drv->hdac.driver.remove = hdac_ext_drv_remove;
+		drv->driver.remove = hdac_ext_drv_remove;
 	if (drv->shutdown)
-		drv->hdac.driver.shutdown = hdac_ext_drv_shutdown;
+		drv->driver.shutdown = hdac_ext_drv_shutdown;
 
-	return driver_register(&drv->hdac.driver);
+	return driver_register(&drv->driver);
 }
 EXPORT_SYMBOL_GPL(snd_hda_ext_driver_register);
 
@@ -262,8 +252,8 @@ EXPORT_SYMBOL_GPL(snd_hda_ext_driver_register);
  *
  * @drv: ext hda driver structure
  */
-void snd_hda_ext_driver_unregister(struct hdac_ext_driver *drv)
+void snd_hda_ext_driver_unregister(struct hdac_driver *drv)
 {
-	driver_unregister(&drv->hdac.driver);
+	driver_unregister(&drv->driver);
 }
 EXPORT_SYMBOL_GPL(snd_hda_ext_driver_unregister);
diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c
index 84f3b8168716..5bc4a1d587d4 100644
--- a/sound/hda/ext/hdac_ext_controller.c
+++ b/sound/hda/ext/hdac_ext_controller.c
@@ -39,9 +39,8 @@
  * @ebus: HD-audio extended core bus
  * @enable: flag to turn on/off the capability
  */
-void snd_hdac_ext_bus_ppcap_enable(struct hdac_ext_bus *ebus, bool enable)
+void snd_hdac_ext_bus_ppcap_enable(struct hdac_bus *bus, bool enable)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->ppcap) {
 		dev_err(bus->dev, "Address of PP capability is NULL");
@@ -60,9 +59,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_ppcap_enable);
  * @ebus: HD-audio extended core bus
  * @enable: flag to enable/disable interrupt
  */
-void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_ext_bus *ebus, bool enable)
+void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_bus *bus, bool enable)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->ppcap) {
 		dev_err(bus->dev, "Address of PP capability is NULL\n");
@@ -89,12 +87,11 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_ppcap_int_enable);
  * in hlink_list of extended hdac bus
  * Note: this will be freed on bus exit by driver
  */
-int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_ext_bus *ebus)
+int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_bus *bus)
 {
 	int idx;
 	u32 link_count;
 	struct hdac_ext_link *hlink;
-	struct hdac_bus *bus = &ebus->bus;
 
 	link_count = readl(bus->mlcap + AZX_REG_ML_MLCD) + 1;
 
@@ -114,7 +111,7 @@ int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_ext_bus *ebus)
 		/* since link in On, update the ref */
 		hlink->ref_count = 1;
 
-		list_add_tail(&hlink->list, &ebus->hlink_list);
+		list_add_tail(&hlink->list, &bus->hlink_list);
 	}
 
 	return 0;
@@ -127,12 +124,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_get_ml_capabilities);
  * @ebus: HD-audio ext core bus
  */
 
-void snd_hdac_link_free_all(struct hdac_ext_bus *ebus)
+void snd_hdac_link_free_all(struct hdac_bus *bus)
 {
 	struct hdac_ext_link *l;
 
-	while (!list_empty(&ebus->hlink_list)) {
-		l = list_first_entry(&ebus->hlink_list, struct hdac_ext_link, list);
+	while (!list_empty(&bus->hlink_list)) {
+		l = list_first_entry(&bus->hlink_list, struct hdac_ext_link, list);
 		list_del(&l->list);
 		kfree(l);
 	}
@@ -144,7 +141,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_link_free_all);
  * @ebus: HD-audio extended core bus
  * @codec_name: codec name
  */
-struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *ebus,
+struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_bus *bus,
 						 const char *codec_name)
 {
 	int i;
@@ -153,10 +150,10 @@ struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *ebus,
 
 	if (sscanf(codec_name, "ehdaudio%dD%d", &bus_idx, &addr) != 2)
 		return NULL;
-	if (ebus->idx != bus_idx)
+	if (bus->idx != bus_idx)
 		return NULL;
 
-	list_for_each_entry(hlink, &ebus->hlink_list, list) {
+	list_for_each_entry(hlink, &bus->hlink_list, list) {
 		for (i = 0; i < HDA_MAX_CODECS; i++) {
 			if (hlink->lsdiid & (0x1 << addr))
 				return hlink;
@@ -219,12 +216,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_down);
  * snd_hdac_ext_bus_link_power_up_all -power up all hda link
  * @ebus: HD-audio extended bus
  */
-int snd_hdac_ext_bus_link_power_up_all(struct hdac_ext_bus *ebus)
+int snd_hdac_ext_bus_link_power_up_all(struct hdac_bus *bus)
 {
 	struct hdac_ext_link *hlink = NULL;
 	int ret;
 
-	list_for_each_entry(hlink, &ebus->hlink_list, list) {
+	list_for_each_entry(hlink, &bus->hlink_list, list) {
 		snd_hdac_updatel(hlink->ml_addr,
 				AZX_REG_ML_LCTL, 0, AZX_MLCTL_SPA);
 		ret = check_hdac_link_power_active(hlink, true);
@@ -240,12 +237,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_up_all);
  * snd_hdac_ext_bus_link_power_down_all -power down all hda link
  * @ebus: HD-audio extended bus
  */
-int snd_hdac_ext_bus_link_power_down_all(struct hdac_ext_bus *ebus)
+int snd_hdac_ext_bus_link_power_down_all(struct hdac_bus *bus)
 {
 	struct hdac_ext_link *hlink = NULL;
 	int ret;
 
-	list_for_each_entry(hlink, &ebus->hlink_list, list) {
+	list_for_each_entry(hlink, &bus->hlink_list, list) {
 		snd_hdac_updatel(hlink->ml_addr, AZX_REG_ML_LCTL, AZX_MLCTL_SPA, 0);
 		ret = check_hdac_link_power_active(hlink, false);
 		if (ret < 0)
@@ -256,39 +253,48 @@ int snd_hdac_ext_bus_link_power_down_all(struct hdac_ext_bus *ebus)
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_down_all);
 
-int snd_hdac_ext_bus_link_get(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_bus_link_get(struct hdac_bus *bus,
 				struct hdac_ext_link *link)
 {
 	int ret = 0;
 
-	mutex_lock(&ebus->lock);
+	mutex_lock(&bus->lock);
 
 	/*
 	 * if we move from 0 to 1, count will be 1 so power up this link
 	 * as well, also check the dma status and trigger that
 	 */
 	if (++link->ref_count == 1) {
-		if (!ebus->cmd_dma_state) {
-			snd_hdac_bus_init_cmd_io(&ebus->bus);
-			ebus->cmd_dma_state = true;
+		if (!bus->cmd_dma_state) {
+			snd_hdac_bus_init_cmd_io(bus);
+			bus->cmd_dma_state = true;
 		}
 
 		ret = snd_hdac_ext_bus_link_power_up(link);
+
+		/*
+		 *  wait for 521usec for codec to report status
+		 *  HDA spec section 4.3 - Codec Discovery
+		 */
+		udelay(521);
+		bus->codec_mask = snd_hdac_chip_readw(bus, STATESTS);
+		dev_dbg(bus->dev, "codec_mask = 0x%lx\n", bus->codec_mask);
+		snd_hdac_chip_writew(bus, STATESTS, bus->codec_mask);
 	}
 
-	mutex_unlock(&ebus->lock);
+	mutex_unlock(&bus->lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_get);
 
-int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_bus_link_put(struct hdac_bus *bus,
 				struct hdac_ext_link *link)
 {
 	int ret = 0;
 	struct hdac_ext_link *hlink;
 	bool link_up = false;
 
-	mutex_lock(&ebus->lock);
+	mutex_lock(&bus->lock);
 
 	/*
 	 * if we move from 1 to 0, count will be 0
@@ -301,7 +307,7 @@ int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus,
 		 * now check if all links are off, if so turn off
 		 * cmd dma as well
 		 */
-		list_for_each_entry(hlink, &ebus->hlink_list, list) {
+		list_for_each_entry(hlink, &bus->hlink_list, list) {
 			if (hlink->ref_count) {
 				link_up = true;
 				break;
@@ -309,12 +315,12 @@ int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus,
 		}
 
 		if (!link_up) {
-			snd_hdac_bus_stop_cmd_io(&ebus->bus);
-			ebus->cmd_dma_state = false;
+			snd_hdac_bus_stop_cmd_io(bus);
+			bus->cmd_dma_state = false;
 		}
 	}
 
-	mutex_unlock(&ebus->lock);
+	mutex_unlock(&bus->lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_put);
diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c
index c96d7a7a36af..1bd27576db98 100644
--- a/sound/hda/ext/hdac_ext_stream.c
+++ b/sound/hda/ext/hdac_ext_stream.c
@@ -25,7 +25,7 @@
 
 /**
  * snd_hdac_ext_stream_init - initialize each stream (aka device)
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: HD-audio ext core stream object to initialize
  * @idx: stream index number
  * @direction: stream direction (SNDRV_PCM_STREAM_PLAYBACK or SNDRV_PCM_STREAM_CAPTURE)
@@ -34,18 +34,16 @@
  * initialize the stream, if ppcap is enabled then init those and then
  * invoke hdac stream initialization routine
  */
-void snd_hdac_ext_stream_init(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_init(struct hdac_bus *bus,
 				struct hdac_ext_stream *stream,
 				int idx, int direction, int tag)
 {
-	struct hdac_bus *bus = &ebus->bus;
-
 	if (bus->ppcap) {
 		stream->pphc_addr = bus->ppcap + AZX_PPHC_BASE +
 				AZX_PPHC_INTERVAL * idx;
 
 		stream->pplc_addr = bus->ppcap + AZX_PPLC_BASE +
-				AZX_PPLC_MULTI * ebus->num_streams +
+				AZX_PPLC_MULTI * bus->num_streams +
 				AZX_PPLC_INTERVAL * idx;
 	}
 
@@ -71,12 +69,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_init);
 /**
  * snd_hdac_ext_stream_init_all - create and initialize the stream objects
  *   for an extended hda bus
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @start_idx: start index for streams
  * @num_stream: number of streams to initialize
  * @dir: direction of streams
  */
-int snd_hdac_ext_stream_init_all(struct hdac_ext_bus *ebus, int start_idx,
+int snd_hdac_ext_stream_init_all(struct hdac_bus *bus, int start_idx,
 		int num_stream, int dir)
 {
 	int stream_tag = 0;
@@ -88,7 +86,7 @@ int snd_hdac_ext_stream_init_all(struct hdac_ext_bus *ebus, int start_idx,
 		if (!stream)
 			return -ENOMEM;
 		tag = ++stream_tag;
-		snd_hdac_ext_stream_init(ebus, stream, idx, dir, tag);
+		snd_hdac_ext_stream_init(bus, stream, idx, dir, tag);
 		idx++;
 	}
 
@@ -100,17 +98,16 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_init_all);
 /**
  * snd_hdac_stream_free_all - free hdac extended stream objects
  *
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  */
-void snd_hdac_stream_free_all(struct hdac_ext_bus *ebus)
+void snd_hdac_stream_free_all(struct hdac_bus *bus)
 {
 	struct hdac_stream *s, *_s;
 	struct hdac_ext_stream *stream;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 
 	list_for_each_entry_safe(s, _s, &bus->stream_list, list) {
 		stream = stream_to_hdac_ext_stream(s);
-		snd_hdac_ext_stream_decouple(ebus, stream, false);
+		snd_hdac_ext_stream_decouple(bus, stream, false);
 		list_del(&s->list);
 		kfree(stream);
 	}
@@ -119,15 +116,14 @@ EXPORT_SYMBOL_GPL(snd_hdac_stream_free_all);
 
 /**
  * snd_hdac_ext_stream_decouple - decouple the hdac stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: HD-audio ext core stream object to initialize
  * @decouple: flag to decouple
  */
-void snd_hdac_ext_stream_decouple(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_decouple(struct hdac_bus *bus,
 				struct hdac_ext_stream *stream, bool decouple)
 {
 	struct hdac_stream *hstream = &stream->hstream;
-	struct hdac_bus *bus = &ebus->bus;
 	u32 val;
 	int mask = AZX_PPCTL_PROCEN(hstream->index);
 
@@ -251,19 +247,18 @@ void snd_hdac_ext_link_clear_stream_id(struct hdac_ext_link *link,
 EXPORT_SYMBOL_GPL(snd_hdac_ext_link_clear_stream_id);
 
 static struct hdac_ext_stream *
-hdac_ext_link_stream_assign(struct hdac_ext_bus *ebus,
+hdac_ext_link_stream_assign(struct hdac_bus *bus,
 				struct snd_pcm_substream *substream)
 {
 	struct hdac_ext_stream *res = NULL;
 	struct hdac_stream *stream = NULL;
-	struct hdac_bus *hbus = &ebus->bus;
 
-	if (!hbus->ppcap) {
-		dev_err(hbus->dev, "stream type not supported\n");
+	if (!bus->ppcap) {
+		dev_err(bus->dev, "stream type not supported\n");
 		return NULL;
 	}
 
-	list_for_each_entry(stream, &hbus->stream_list, list) {
+	list_for_each_entry(stream, &bus->stream_list, list) {
 		struct hdac_ext_stream *hstream = container_of(stream,
 						struct hdac_ext_stream,
 						hstream);
@@ -277,34 +272,33 @@ hdac_ext_link_stream_assign(struct hdac_ext_bus *ebus,
 		}
 
 		if (!hstream->link_locked) {
-			snd_hdac_ext_stream_decouple(ebus, hstream, true);
+			snd_hdac_ext_stream_decouple(bus, hstream, true);
 			res = hstream;
 			break;
 		}
 	}
 	if (res) {
-		spin_lock_irq(&hbus->reg_lock);
+		spin_lock_irq(&bus->reg_lock);
 		res->link_locked = 1;
 		res->link_substream = substream;
-		spin_unlock_irq(&hbus->reg_lock);
+		spin_unlock_irq(&bus->reg_lock);
 	}
 	return res;
 }
 
 static struct hdac_ext_stream *
-hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus,
+hdac_ext_host_stream_assign(struct hdac_bus *bus,
 				struct snd_pcm_substream *substream)
 {
 	struct hdac_ext_stream *res = NULL;
 	struct hdac_stream *stream = NULL;
-	struct hdac_bus *hbus = &ebus->bus;
 
-	if (!hbus->ppcap) {
-		dev_err(hbus->dev, "stream type not supported\n");
+	if (!bus->ppcap) {
+		dev_err(bus->dev, "stream type not supported\n");
 		return NULL;
 	}
 
-	list_for_each_entry(stream, &hbus->stream_list, list) {
+	list_for_each_entry(stream, &bus->stream_list, list) {
 		struct hdac_ext_stream *hstream = container_of(stream,
 						struct hdac_ext_stream,
 						hstream);
@@ -313,17 +307,17 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus,
 
 		if (!stream->opened) {
 			if (!hstream->decoupled)
-				snd_hdac_ext_stream_decouple(ebus, hstream, true);
+				snd_hdac_ext_stream_decouple(bus, hstream, true);
 			res = hstream;
 			break;
 		}
 	}
 	if (res) {
-		spin_lock_irq(&hbus->reg_lock);
+		spin_lock_irq(&bus->reg_lock);
 		res->hstream.opened = 1;
 		res->hstream.running = 0;
 		res->hstream.substream = substream;
-		spin_unlock_irq(&hbus->reg_lock);
+		spin_unlock_irq(&bus->reg_lock);
 	}
 
 	return res;
@@ -331,7 +325,7 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus,
 
 /**
  * snd_hdac_ext_stream_assign - assign a stream for the PCM
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @substream: PCM substream to assign
  * @type: type of stream (coupled, host or link stream)
  *
@@ -346,27 +340,26 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus,
  * the same stream object when it's used beforehand.  when a stream is
  * decoupled, it becomes a host stream and link stream.
  */
-struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_ext_bus *ebus,
+struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_bus *bus,
 					   struct snd_pcm_substream *substream,
 					   int type)
 {
 	struct hdac_ext_stream *hstream = NULL;
 	struct hdac_stream *stream = NULL;
-	struct hdac_bus *hbus = &ebus->bus;
 
 	switch (type) {
 	case HDAC_EXT_STREAM_TYPE_COUPLED:
-		stream = snd_hdac_stream_assign(hbus, substream);
+		stream = snd_hdac_stream_assign(bus, substream);
 		if (stream)
 			hstream = container_of(stream,
 					struct hdac_ext_stream, hstream);
 		return hstream;
 
 	case HDAC_EXT_STREAM_TYPE_HOST:
-		return hdac_ext_host_stream_assign(ebus, substream);
+		return hdac_ext_host_stream_assign(bus, substream);
 
 	case HDAC_EXT_STREAM_TYPE_LINK:
-		return hdac_ext_link_stream_assign(ebus, substream);
+		return hdac_ext_link_stream_assign(bus, substream);
 
 	default:
 		return NULL;
@@ -384,7 +377,6 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_assign);
 void snd_hdac_ext_stream_release(struct hdac_ext_stream *stream, int type)
 {
 	struct hdac_bus *bus = stream->hstream.bus;
-	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 
 	switch (type) {
 	case HDAC_EXT_STREAM_TYPE_COUPLED:
@@ -393,13 +385,13 @@ void snd_hdac_ext_stream_release(struct hdac_ext_stream *stream, int type)
 
 	case HDAC_EXT_STREAM_TYPE_HOST:
 		if (stream->decoupled && !stream->link_locked)
-			snd_hdac_ext_stream_decouple(ebus, stream, false);
+			snd_hdac_ext_stream_decouple(bus, stream, false);
 		snd_hdac_stream_release(&stream->hstream);
 		break;
 
 	case HDAC_EXT_STREAM_TYPE_LINK:
 		if (stream->decoupled && !stream->hstream.opened)
-			snd_hdac_ext_stream_decouple(ebus, stream, false);
+			snd_hdac_ext_stream_decouple(bus, stream, false);
 		spin_lock_irq(&bus->reg_lock);
 		stream->link_locked = 0;
 		stream->link_substream = NULL;
@@ -415,16 +407,15 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_release);
 
 /**
  * snd_hdac_ext_stream_spbcap_enable - enable SPIB for a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @enable: flag to enable/disable SPIB
  * @index: stream index for which SPIB need to be enabled
  */
-void snd_hdac_ext_stream_spbcap_enable(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *bus,
 				 bool enable, int index)
 {
 	u32 mask = 0;
 	u32 register_mask = 0;
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->spbcap) {
 		dev_err(bus->dev, "Address of SPB capability is NULL\n");
@@ -446,14 +437,13 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_spbcap_enable);
 
 /**
  * snd_hdac_ext_stream_set_spib - sets the spib value of a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: hdac_ext_stream
  * @value: spib value to set
  */
-int snd_hdac_ext_stream_set_spib(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_set_spib(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream, u32 value)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->spbcap) {
 		dev_err(bus->dev, "Address of SPB capability is NULL\n");
@@ -468,15 +458,14 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_set_spib);
 
 /**
  * snd_hdac_ext_stream_get_spbmaxfifo - gets the spib value of a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: hdac_ext_stream
  *
  * Return maxfifo for the stream
  */
-int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->spbcap) {
 		dev_err(bus->dev, "Address of SPB capability is NULL\n");
@@ -490,11 +479,10 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_get_spbmaxfifo);
 
 /**
  * snd_hdac_ext_stop_streams - stop all stream if running
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  */
-void snd_hdac_ext_stop_streams(struct hdac_ext_bus *ebus)
+void snd_hdac_ext_stop_streams(struct hdac_bus *bus)
 {
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	struct hdac_stream *stream;
 
 	if (bus->chip_init) {
@@ -507,16 +495,15 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stop_streams);
 
 /**
  * snd_hdac_ext_stream_drsm_enable - enable DMA resume for a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @enable: flag to enable/disable DRSM
  * @index: stream index for which DRSM need to be enabled
  */
-void snd_hdac_ext_stream_drsm_enable(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus,
 				bool enable, int index)
 {
 	u32 mask = 0;
 	u32 register_mask = 0;
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->drsmcap) {
 		dev_err(bus->dev, "Address of DRSM capability is NULL\n");
@@ -538,14 +525,13 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_drsm_enable);
 
 /**
  * snd_hdac_ext_stream_set_dpibr - sets the dpibr value of a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: hdac_ext_stream
  * @value: dpib value to set
  */
-int snd_hdac_ext_stream_set_dpibr(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_set_dpibr(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream, u32 value)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->drsmcap) {
 		dev_err(bus->dev, "Address of DRSM capability is NULL\n");
@@ -560,7 +546,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_set_dpibr);
 
 /**
  * snd_hdac_ext_stream_set_lpib - sets the lpib value of a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: hdac_ext_stream
  * @value: lpib value to set
  */
diff --git a/sound/hda/hdac_component.c b/sound/hda/hdac_component.c
new file mode 100644
index 000000000000..6e46a9c73aed
--- /dev/null
+++ b/sound/hda/hdac_component.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0
+// hdac_component.c - routines for sync between HD-A core and DRM driver
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/component.h>
+#include <sound/core.h>
+#include <sound/hdaudio.h>
+#include <sound/hda_component.h>
+#include <sound/hda_register.h>
+
+static void hdac_acomp_release(struct device *dev, void *res)
+{
+}
+
+static struct drm_audio_component *hdac_get_acomp(struct device *dev)
+{
+	return devres_find(dev, hdac_acomp_release, NULL, NULL);
+}
+
+/**
+ * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup
+ * @bus: HDA core bus
+ * @enable: enable or disable the wakeup
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function should be called during the chip reset, also called at
+ * resume for updating STATESTS register read.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
+{
+	struct drm_audio_component *acomp = bus->audio_component;
+
+	if (!acomp || !acomp->ops)
+		return -ENODEV;
+
+	if (!acomp->ops->codec_wake_override)
+		return 0;
+
+	dev_dbg(bus->dev, "%s codec wakeup\n",
+		enable ? "enable" : "disable");
+
+	acomp->ops->codec_wake_override(acomp->dev, enable);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_set_codec_wakeup);
+
+/**
+ * snd_hdac_display_power - Power up / down the power refcount
+ * @bus: HDA core bus
+ * @enable: power up or down
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function manages a refcount and calls the get_power() and
+ * put_power() ops accordingly, toggling the codec wakeup, too.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
+{
+	struct drm_audio_component *acomp = bus->audio_component;
+
+	if (!acomp || !acomp->ops)
+		return -ENODEV;
+
+	dev_dbg(bus->dev, "display power %s\n",
+		enable ? "enable" : "disable");
+
+	if (enable) {
+		if (!bus->drm_power_refcount++) {
+			if (acomp->ops->get_power)
+				acomp->ops->get_power(acomp->dev);
+			snd_hdac_set_codec_wakeup(bus, true);
+			snd_hdac_set_codec_wakeup(bus, false);
+		}
+	} else {
+		WARN_ON(!bus->drm_power_refcount);
+		if (!--bus->drm_power_refcount)
+			if (acomp->ops->put_power)
+				acomp->ops->put_power(acomp->dev);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_display_power);
+
+/**
+ * snd_hdac_sync_audio_rate - Set N/CTS based on the sample rate
+ * @codec: HDA codec
+ * @nid: the pin widget NID
+ * @dev_id: device identifier
+ * @rate: the sample rate to set
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function sets N/CTS value based on the given sample rate.
+ * Returns zero for success, or a negative error code.
+ */
+int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid,
+			     int dev_id, int rate)
+{
+	struct hdac_bus *bus = codec->bus;
+	struct drm_audio_component *acomp = bus->audio_component;
+	int port, pipe;
+
+	if (!acomp || !acomp->ops || !acomp->ops->sync_audio_rate)
+		return -ENODEV;
+	port = nid;
+	if (acomp->audio_ops && acomp->audio_ops->pin2port) {
+		port = acomp->audio_ops->pin2port(codec, nid);
+		if (port < 0)
+			return -EINVAL;
+	}
+	pipe = dev_id;
+	return acomp->ops->sync_audio_rate(acomp->dev, port, pipe, rate);
+}
+EXPORT_SYMBOL_GPL(snd_hdac_sync_audio_rate);
+
+/**
+ * snd_hdac_acomp_get_eld - Get the audio state and ELD via component
+ * @codec: HDA codec
+ * @nid: the pin widget NID
+ * @dev_id: device identifier
+ * @audio_enabled: the pointer to store the current audio state
+ * @buffer: the buffer pointer to store ELD bytes
+ * @max_bytes: the max bytes to be stored on @buffer
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function queries the current state of the audio on the given
+ * digital port and fetches the ELD bytes onto the given buffer.
+ * It returns the number of bytes for the total ELD data, zero for
+ * invalid ELD, or a negative error code.
+ *
+ * The return size is the total bytes required for the whole ELD bytes,
+ * thus it may be over @max_bytes.  If it's over @max_bytes, it implies
+ * that only a part of ELD bytes have been fetched.
+ */
+int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
+			   bool *audio_enabled, char *buffer, int max_bytes)
+{
+	struct hdac_bus *bus = codec->bus;
+	struct drm_audio_component *acomp = bus->audio_component;
+	int port, pipe;
+
+	if (!acomp || !acomp->ops || !acomp->ops->get_eld)
+		return -ENODEV;
+
+	port = nid;
+	if (acomp->audio_ops && acomp->audio_ops->pin2port) {
+		port = acomp->audio_ops->pin2port(codec, nid);
+		if (port < 0)
+			return -EINVAL;
+	}
+	pipe = dev_id;
+	return acomp->ops->get_eld(acomp->dev, port, pipe, audio_enabled,
+				   buffer, max_bytes);
+}
+EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld);
+
+static int hdac_component_master_bind(struct device *dev)
+{
+	struct drm_audio_component *acomp = hdac_get_acomp(dev);
+	int ret;
+
+	if (WARN_ON(!acomp))
+		return -EINVAL;
+
+	ret = component_bind_all(dev, acomp);
+	if (ret < 0)
+		return ret;
+
+	if (WARN_ON(!(acomp->dev && acomp->ops))) {
+		ret = -EINVAL;
+		goto out_unbind;
+	}
+
+	/* pin the module to avoid dynamic unbinding, but only if given */
+	if (!try_module_get(acomp->ops->owner)) {
+		ret = -ENODEV;
+		goto out_unbind;
+	}
+
+	if (acomp->audio_ops && acomp->audio_ops->master_bind) {
+		ret = acomp->audio_ops->master_bind(dev, acomp);
+		if (ret < 0)
+			goto module_put;
+	}
+
+	return 0;
+
+ module_put:
+	module_put(acomp->ops->owner);
+out_unbind:
+	component_unbind_all(dev, acomp);
+
+	return ret;
+}
+
+static void hdac_component_master_unbind(struct device *dev)
+{
+	struct drm_audio_component *acomp = hdac_get_acomp(dev);
+
+	if (acomp->audio_ops && acomp->audio_ops->master_unbind)
+		acomp->audio_ops->master_unbind(dev, acomp);
+	module_put(acomp->ops->owner);
+	component_unbind_all(dev, acomp);
+	WARN_ON(acomp->ops || acomp->dev);
+}
+
+static const struct component_master_ops hdac_component_master_ops = {
+	.bind = hdac_component_master_bind,
+	.unbind = hdac_component_master_unbind,
+};
+
+/**
+ * snd_hdac_acomp_register_notifier - Register audio component ops
+ * @bus: HDA core bus
+ * @aops: audio component ops
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function sets the given ops to be called by the graphics driver.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_acomp_register_notifier(struct hdac_bus *bus,
+				    const struct drm_audio_component_audio_ops *aops)
+{
+	if (!bus->audio_component)
+		return -ENODEV;
+
+	bus->audio_component->audio_ops = aops;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_acomp_register_notifier);
+
+/**
+ * snd_hdac_acomp_init - Initialize audio component
+ * @bus: HDA core bus
+ * @match_master: match function for finding components
+ * @extra_size: Extra bytes to allocate
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function initializes and sets up the audio component to communicate
+ * with graphics driver.
+ *
+ * Unlike snd_hdac_i915_init(), this function doesn't synchronize with the
+ * binding with the DRM component.  Each caller needs to sync via master_bind
+ * audio_ops.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_acomp_init(struct hdac_bus *bus,
+			const struct drm_audio_component_audio_ops *aops,
+			int (*match_master)(struct device *, void *),
+			size_t extra_size)
+{
+	struct component_match *match = NULL;
+	struct device *dev = bus->dev;
+	struct drm_audio_component *acomp;
+	int ret;
+
+	if (WARN_ON(hdac_get_acomp(dev)))
+		return -EBUSY;
+
+	acomp = devres_alloc(hdac_acomp_release, sizeof(*acomp) + extra_size,
+			     GFP_KERNEL);
+	if (!acomp)
+		return -ENOMEM;
+	acomp->audio_ops = aops;
+	bus->audio_component = acomp;
+	devres_add(dev, acomp);
+
+	component_match_add(dev, &match, match_master, bus);
+	ret = component_master_add_with_match(dev, &hdac_component_master_ops,
+					      match);
+	if (ret < 0)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	bus->audio_component = NULL;
+	devres_destroy(dev, hdac_acomp_release, NULL, NULL);
+	dev_info(dev, "failed to add audio component master (%d)\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_acomp_init);
+
+/**
+ * snd_hdac_acomp_exit - Finalize audio component
+ * @bus: HDA core bus
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function releases the audio component that has been used.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_acomp_exit(struct hdac_bus *bus)
+{
+	struct device *dev = bus->dev;
+	struct drm_audio_component *acomp = bus->audio_component;
+
+	if (!acomp)
+		return 0;
+
+	WARN_ON(bus->drm_power_refcount);
+	if (bus->drm_power_refcount > 0 && acomp->ops)
+		acomp->ops->put_power(acomp->dev);
+
+	component_master_del(dev, &hdac_component_master_ops);
+
+	bus->audio_component = NULL;
+	devres_destroy(dev, hdac_acomp_release, NULL, NULL);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_acomp_exit);
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c
index 7ba100bb1c3f..dbf02a3a8d2f 100644
--- a/sound/hda/hdac_device.c
+++ b/sound/hda/hdac_device.c
@@ -738,7 +738,7 @@ static struct hda_rate_tbl rate_bits[] = {
  */
 unsigned int snd_hdac_calc_stream_format(unsigned int rate,
 					 unsigned int channels,
-					 unsigned int format,
+					 snd_pcm_format_t format,
 					 unsigned int maxbps,
 					 unsigned short spdif_ctls)
 {
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index cbe818eda336..b5282cbbe489 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -15,88 +15,12 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/component.h>
-#include <drm/i915_component.h>
 #include <sound/core.h>
 #include <sound/hdaudio.h>
 #include <sound/hda_i915.h>
 #include <sound/hda_register.h>
 
-static struct i915_audio_component *hdac_acomp;
-
-/**
- * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup
- * @bus: HDA core bus
- * @enable: enable or disable the wakeup
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function should be called during the chip reset, also called at
- * resume for updating STATESTS register read.
- *
- * Returns zero for success or a negative error code.
- */
-int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
-{
-	struct i915_audio_component *acomp = bus->audio_component;
-
-	if (!acomp || !acomp->ops)
-		return -ENODEV;
-
-	if (!acomp->ops->codec_wake_override) {
-		dev_warn(bus->dev,
-			"Invalid codec wake callback\n");
-		return 0;
-	}
-
-	dev_dbg(bus->dev, "%s codec wakeup\n",
-		enable ? "enable" : "disable");
-
-	acomp->ops->codec_wake_override(acomp->dev, enable);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_hdac_set_codec_wakeup);
-
-/**
- * snd_hdac_display_power - Power up / down the power refcount
- * @bus: HDA core bus
- * @enable: power up or down
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function manages a refcount and calls the i915 get_power() and
- * put_power() ops accordingly, toggling the codec wakeup, too.
- *
- * Returns zero for success or a negative error code.
- */
-int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
-{
-	struct i915_audio_component *acomp = bus->audio_component;
-
-	if (!acomp || !acomp->ops)
-		return -ENODEV;
-
-	dev_dbg(bus->dev, "display power %s\n",
-		enable ? "enable" : "disable");
-
-	if (enable) {
-		if (!bus->i915_power_refcount++) {
-			acomp->ops->get_power(acomp->dev);
-			snd_hdac_set_codec_wakeup(bus, true);
-			snd_hdac_set_codec_wakeup(bus, false);
-		}
-	} else {
-		WARN_ON(!bus->i915_power_refcount);
-		if (!--bus->i915_power_refcount)
-			acomp->ops->put_power(acomp->dev);
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_hdac_display_power);
+static struct completion bind_complete;
 
 #define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \
 				((pci)->device == 0x0c0c) || \
@@ -119,7 +43,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_display_power);
  */
 void snd_hdac_i915_set_bclk(struct hdac_bus *bus)
 {
-	struct i915_audio_component *acomp = bus->audio_component;
+	struct drm_audio_component *acomp = bus->audio_component;
 	struct pci_dev *pci = to_pci_dev(bus->dev);
 	int cdclk_freq;
 	unsigned int bclk_m, bclk_n;
@@ -158,181 +82,11 @@ void snd_hdac_i915_set_bclk(struct hdac_bus *bus)
 }
 EXPORT_SYMBOL_GPL(snd_hdac_i915_set_bclk);
 
-/* There is a fixed mapping between audio pin node and display port.
- * on SNB, IVY, HSW, BSW, SKL, BXT, KBL:
- * Pin Widget 5 - PORT B (port = 1 in i915 driver)
- * Pin Widget 6 - PORT C (port = 2 in i915 driver)
- * Pin Widget 7 - PORT D (port = 3 in i915 driver)
- *
- * on VLV, ILK:
- * Pin Widget 4 - PORT B (port = 1 in i915 driver)
- * Pin Widget 5 - PORT C (port = 2 in i915 driver)
- * Pin Widget 6 - PORT D (port = 3 in i915 driver)
- */
-static int pin2port(struct hdac_device *codec, hda_nid_t pin_nid)
-{
-	int base_nid;
-
-	switch (codec->vendor_id) {
-	case 0x80860054: /* ILK */
-	case 0x80862804: /* ILK */
-	case 0x80862882: /* VLV */
-		base_nid = 3;
-		break;
-	default:
-		base_nid = 4;
-		break;
-	}
-
-	if (WARN_ON(pin_nid <= base_nid || pin_nid > base_nid + 3))
-		return -1;
-	return pin_nid - base_nid;
-}
-
-/**
- * snd_hdac_sync_audio_rate - Set N/CTS based on the sample rate
- * @codec: HDA codec
- * @nid: the pin widget NID
- * @dev_id: device identifier
- * @rate: the sample rate to set
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function sets N/CTS value based on the given sample rate.
- * Returns zero for success, or a negative error code.
- */
-int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid,
-			     int dev_id, int rate)
-{
-	struct hdac_bus *bus = codec->bus;
-	struct i915_audio_component *acomp = bus->audio_component;
-	int port, pipe;
-
-	if (!acomp || !acomp->ops || !acomp->ops->sync_audio_rate)
-		return -ENODEV;
-	port = pin2port(codec, nid);
-	if (port < 0)
-		return -EINVAL;
-	pipe = dev_id;
-	return acomp->ops->sync_audio_rate(acomp->dev, port, pipe, rate);
-}
-EXPORT_SYMBOL_GPL(snd_hdac_sync_audio_rate);
-
-/**
- * snd_hdac_acomp_get_eld - Get the audio state and ELD via component
- * @codec: HDA codec
- * @nid: the pin widget NID
- * @dev_id: device identifier
- * @audio_enabled: the pointer to store the current audio state
- * @buffer: the buffer pointer to store ELD bytes
- * @max_bytes: the max bytes to be stored on @buffer
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function queries the current state of the audio on the given
- * digital port and fetches the ELD bytes onto the given buffer.
- * It returns the number of bytes for the total ELD data, zero for
- * invalid ELD, or a negative error code.
- *
- * The return size is the total bytes required for the whole ELD bytes,
- * thus it may be over @max_bytes.  If it's over @max_bytes, it implies
- * that only a part of ELD bytes have been fetched.
- */
-int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
-			   bool *audio_enabled, char *buffer, int max_bytes)
-{
-	struct hdac_bus *bus = codec->bus;
-	struct i915_audio_component *acomp = bus->audio_component;
-	int port, pipe;
-
-	if (!acomp || !acomp->ops || !acomp->ops->get_eld)
-		return -ENODEV;
-
-	port = pin2port(codec, nid);
-	if (port < 0)
-		return -EINVAL;
-
-	pipe = dev_id;
-	return acomp->ops->get_eld(acomp->dev, port, pipe, audio_enabled,
-				   buffer, max_bytes);
-}
-EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld);
-
-static int hdac_component_master_bind(struct device *dev)
-{
-	struct i915_audio_component *acomp = hdac_acomp;
-	int ret;
-
-	ret = component_bind_all(dev, acomp);
-	if (ret < 0)
-		return ret;
-
-	if (WARN_ON(!(acomp->dev && acomp->ops && acomp->ops->get_power &&
-		      acomp->ops->put_power && acomp->ops->get_cdclk_freq))) {
-		ret = -EINVAL;
-		goto out_unbind;
-	}
-
-	/*
-	 * Atm, we don't support dynamic unbinding initiated by the child
-	 * component, so pin its containing module until we unbind.
-	 */
-	if (!try_module_get(acomp->ops->owner)) {
-		ret = -ENODEV;
-		goto out_unbind;
-	}
-
-	return 0;
-
-out_unbind:
-	component_unbind_all(dev, acomp);
-
-	return ret;
-}
-
-static void hdac_component_master_unbind(struct device *dev)
-{
-	struct i915_audio_component *acomp = hdac_acomp;
-
-	module_put(acomp->ops->owner);
-	component_unbind_all(dev, acomp);
-	WARN_ON(acomp->ops || acomp->dev);
-}
-
-static const struct component_master_ops hdac_component_master_ops = {
-	.bind = hdac_component_master_bind,
-	.unbind = hdac_component_master_unbind,
-};
-
-static int hdac_component_master_match(struct device *dev, void *data)
+static int i915_component_master_match(struct device *dev, void *data)
 {
-	/* i915 is the only supported component */
 	return !strcmp(dev->driver->name, "i915");
 }
 
-/**
- * snd_hdac_i915_register_notifier - Register i915 audio component ops
- * @aops: i915 audio component ops
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function sets the given ops to be called by the i915 graphics driver.
- *
- * Returns zero for success or a negative error code.
- */
-int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops)
-{
-	if (!hdac_acomp)
-		return -ENODEV;
-
-	hdac_acomp->audio_ops = aops;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_hdac_i915_register_notifier);
-
 /* check whether intel graphics is present */
 static bool i915_gfx_present(void)
 {
@@ -345,6 +99,19 @@ static bool i915_gfx_present(void)
 	return pci_dev_present(ids);
 }
 
+static int i915_master_bind(struct device *dev,
+			    struct drm_audio_component *acomp)
+{
+	complete_all(&bind_complete);
+	/* clear audio_ops here as it was needed only for completion call */
+	acomp->audio_ops = NULL;
+	return 0;
+}
+
+static const struct drm_audio_component_audio_ops i915_init_ops = {
+	.master_bind = i915_master_bind
+};
+
 /**
  * snd_hdac_i915_init - Initialize i915 audio component
  * @bus: HDA core bus
@@ -359,83 +126,31 @@ static bool i915_gfx_present(void)
  */
 int snd_hdac_i915_init(struct hdac_bus *bus)
 {
-	struct component_match *match = NULL;
-	struct device *dev = bus->dev;
-	struct i915_audio_component *acomp;
-	int ret;
-
-	if (WARN_ON(hdac_acomp))
-		return -EBUSY;
+	struct drm_audio_component *acomp;
+	int err;
 
 	if (!i915_gfx_present())
 		return -ENODEV;
 
-	acomp = kzalloc(sizeof(*acomp), GFP_KERNEL);
-	if (!acomp)
-		return -ENOMEM;
-	bus->audio_component = acomp;
-	hdac_acomp = acomp;
-
-	component_match_add(dev, &match, hdac_component_master_match, bus);
-	ret = component_master_add_with_match(dev, &hdac_component_master_ops,
-					      match);
-	if (ret < 0)
-		goto out_err;
-
-	/*
-	 * Atm, we don't support deferring the component binding, so make sure
-	 * i915 is loaded and that the binding successfully completes.
-	 */
-	request_module("i915");
+	init_completion(&bind_complete);
 
+	err = snd_hdac_acomp_init(bus, &i915_init_ops,
+				  i915_component_master_match,
+				  sizeof(struct i915_audio_component) - sizeof(*acomp));
+	if (err < 0)
+		return err;
+	acomp = bus->audio_component;
+	if (!acomp)
+		return -ENODEV;
 	if (!acomp->ops) {
-		ret = -ENODEV;
-		goto out_master_del;
+		request_module("i915");
+		/* 10s timeout */
+		wait_for_completion_timeout(&bind_complete, 10 * 1000);
+	}
+	if (!acomp->ops) {
+		snd_hdac_acomp_exit(bus);
+		return -ENODEV;
 	}
-	dev_dbg(dev, "bound to i915 component master\n");
-
 	return 0;
-out_master_del:
-	component_master_del(dev, &hdac_component_master_ops);
-out_err:
-	kfree(acomp);
-	bus->audio_component = NULL;
-	hdac_acomp = NULL;
-	dev_info(dev, "failed to add i915 component master (%d)\n", ret);
-
-	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_i915_init);
-
-/**
- * snd_hdac_i915_exit - Finalize i915 audio component
- * @bus: HDA core bus
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function releases the i915 audio component that has been used.
- *
- * Returns zero for success or a negative error code.
- */
-int snd_hdac_i915_exit(struct hdac_bus *bus)
-{
-	struct device *dev = bus->dev;
-	struct i915_audio_component *acomp = bus->audio_component;
-
-	if (!acomp)
-		return 0;
-
-	WARN_ON(bus->i915_power_refcount);
-	if (bus->i915_power_refcount > 0 && acomp->ops)
-		acomp->ops->put_power(acomp->dev);
-
-	component_master_del(dev, &hdac_component_master_ops);
-
-	kfree(acomp);
-	bus->audio_component = NULL;
-	hdac_acomp = NULL;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_hdac_i915_exit);
diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c
index e1472c7ab6c1..eee422390d8e 100644
--- a/sound/hda/hdac_stream.c
+++ b/sound/hda/hdac_stream.c
@@ -621,7 +621,7 @@ int snd_hdac_dsp_prepare(struct hdac_stream *azx_dev, unsigned int format,
 			 unsigned int byte_size, struct snd_dma_buffer *bufp)
 {
 	struct hdac_bus *bus = azx_dev->bus;
-	u32 *bdl;
+	__le32 *bdl;
 	int err;
 
 	snd_hdac_dsp_lock(azx_dev);
@@ -651,7 +651,7 @@ int snd_hdac_dsp_prepare(struct hdac_stream *azx_dev, unsigned int format,
 	snd_hdac_stream_writel(azx_dev, SD_BDLPU, 0);
 
 	azx_dev->frags = 0;
-	bdl = (u32 *)azx_dev->bdl.area;
+	bdl = (__le32 *)azx_dev->bdl.area;
 	err = setup_bdle(bus, bufp, azx_dev, &bdl, 0, byte_size, 0);
 	if (err < 0)
 		goto error;
diff --git a/sound/i2c/cs8427.c b/sound/i2c/cs8427.c
index 7e21621e492a..2647309bc675 100644
--- a/sound/i2c/cs8427.c
+++ b/sound/i2c/cs8427.c
@@ -621,15 +621,3 @@ int snd_cs8427_iec958_pcm(struct snd_i2c_device *cs8427, unsigned int rate)
 }
 
 EXPORT_SYMBOL(snd_cs8427_iec958_pcm);
-
-static int __init alsa_cs8427_module_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_cs8427_module_exit(void)
-{
-}
-
-module_init(alsa_cs8427_module_init)
-module_exit(alsa_cs8427_module_exit)
diff --git a/sound/i2c/i2c.c b/sound/i2c/i2c.c
index ef2a9afe9e19..c4a232f18a79 100644
--- a/sound/i2c/i2c.c
+++ b/sound/i2c/i2c.c
@@ -338,16 +338,3 @@ static int snd_i2c_bit_probeaddr(struct snd_i2c_bus *bus, unsigned short addr)
 	snd_i2c_bit_stop(bus);
 	return err;
 }
-
-
-static int __init alsa_i2c_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_i2c_exit(void)
-{
-}
-
-module_init(alsa_i2c_init)
-module_exit(alsa_i2c_exit)
diff --git a/sound/i2c/other/ak4xxx-adda.c b/sound/i2c/other/ak4xxx-adda.c
index bf377dc192aa..7f2761a2e7c8 100644
--- a/sound/i2c/other/ak4xxx-adda.c
+++ b/sound/i2c/other/ak4xxx-adda.c
@@ -911,15 +911,3 @@ int snd_akm4xxx_build_controls(struct snd_akm4xxx *ak)
 	return 0;
 }
 EXPORT_SYMBOL(snd_akm4xxx_build_controls);
-
-static int __init alsa_akm4xxx_module_init(void)
-{
-	return 0;
-}
-        
-static void __exit alsa_akm4xxx_module_exit(void)
-{
-}
-        
-module_init(alsa_akm4xxx_module_init)
-module_exit(alsa_akm4xxx_module_exit)
diff --git a/sound/i2c/tea6330t.c b/sound/i2c/tea6330t.c
index 2d22310dce05..239c4822427f 100644
--- a/sound/i2c/tea6330t.c
+++ b/sound/i2c/tea6330t.c
@@ -368,19 +368,3 @@ int snd_tea6330t_update_mixer(struct snd_card *card,
 
 EXPORT_SYMBOL(snd_tea6330t_detect);
 EXPORT_SYMBOL(snd_tea6330t_update_mixer);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_tea6330t_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_tea6330t_exit(void)
-{
-}
-
-module_init(alsa_tea6330t_init)
-module_exit(alsa_tea6330t_exit)
diff --git a/sound/isa/Kconfig b/sound/isa/Kconfig
index 43b35a873d78..d7db1eeebc84 100644
--- a/sound/isa/Kconfig
+++ b/sound/isa/Kconfig
@@ -459,7 +459,7 @@ config SND_MSND_CLASSIC
 	  Say M here if you have a Turtle Beach MultiSound Classic, Tahiti or
 	  Monterey (not for the Pinnacle or Fiji).
 
-	  See <file:Documentation/sound/oss/MultiSound> for important information
+	  See <file:Documentation/sound/cards/multisound.sh> for important information
 	  about this driver.  Note that it has been discontinued, but the
 	  Voyetra Turtle Beach knowledge base entry for it is still available
 	  at <http://www.turtlebeach.com/site/kb_ftp/790.asp>.
diff --git a/sound/isa/ad1816a/ad1816a_lib.c b/sound/isa/ad1816a/ad1816a_lib.c
index 923201414469..fba6d22f7f4b 100644
--- a/sound/isa/ad1816a/ad1816a_lib.c
+++ b/sound/isa/ad1816a/ad1816a_lib.c
@@ -85,7 +85,8 @@ static void snd_ad1816a_write_mask(struct snd_ad1816a *chip, unsigned char reg,
 
 
 static unsigned char snd_ad1816a_get_format(struct snd_ad1816a *chip,
-					    unsigned int format, int channels)
+					    snd_pcm_format_t format,
+					    int channels)
 {
 	unsigned char retval = AD1816A_FMT_LINEAR_8;
 
diff --git a/sound/isa/es1688/es1688.c b/sound/isa/es1688/es1688.c
index a826c138e7f5..3dfe7e592c25 100644
--- a/sound/isa/es1688/es1688.c
+++ b/sound/isa/es1688/es1688.c
@@ -260,7 +260,6 @@ static int snd_es968_pnp_detect(struct pnp_card_link *pcard,
 	struct snd_card *card;
 	static unsigned int dev;
 	int error;
-	struct snd_es1688 *chip;
 
 	if (snd_es968_pnp_is_probed)
 		return -EBUSY;
@@ -276,7 +275,6 @@ static int snd_es968_pnp_detect(struct pnp_card_link *pcard,
 			     sizeof(struct snd_es1688), &card);
 	if (error < 0)
 		return error;
-	chip = card->private_data;
 
 	error = snd_card_es968_pnp(card, dev, pcard, pid);
 	if (error < 0) {
diff --git a/sound/isa/es1688/es1688_lib.c b/sound/isa/es1688/es1688_lib.c
index f9c0662e9a22..50cdce0e8946 100644
--- a/sound/isa/es1688/es1688_lib.c
+++ b/sound/isa/es1688/es1688_lib.c
@@ -1029,19 +1029,3 @@ EXPORT_SYMBOL(snd_es1688_mixer_write);
 EXPORT_SYMBOL(snd_es1688_create);
 EXPORT_SYMBOL(snd_es1688_pcm);
 EXPORT_SYMBOL(snd_es1688_mixer);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_es1688_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_es1688_exit(void)
-{
-}
-
-module_init(alsa_es1688_init)
-module_exit(alsa_es1688_exit)
diff --git a/sound/isa/es18xx.c b/sound/isa/es18xx.c
index 2a6960c3e2a4..0d103d6f805e 100644
--- a/sound/isa/es18xx.c
+++ b/sound/isa/es18xx.c
@@ -1024,6 +1024,7 @@ static int snd_es18xx_put_mux(struct snd_kcontrol *kcontrol, struct snd_ctl_elem
 			val = 3;
 		} else
 			retVal = snd_es18xx_mixer_bits(chip, 0x7a, 0x08, 0x00) != 0x00;
+		/* fall through */
  /* 4 source chips */
 	case 0x1868:
 	case 0x1878:
diff --git a/sound/isa/galaxy/galaxy.c b/sound/isa/galaxy/galaxy.c
index b9994cc9f5fb..af9eea41379f 100644
--- a/sound/isa/galaxy/galaxy.c
+++ b/sound/isa/galaxy/galaxy.c
@@ -260,6 +260,7 @@ static int snd_galaxy_match(struct device *dev, unsigned int n)
 		break;
 	case 2:
 		irq[n] = 9;
+		/* Fall through */
 	case 9:
 		wss_config[n] |= WSS_CONFIG_IRQ_9;
 		break;
@@ -304,6 +305,7 @@ static int snd_galaxy_match(struct device *dev, unsigned int n)
 	case 1:
 		if (dma1[n] == 0)
 			break;
+		/* Fall through */
 	default:
 		dev_err(dev, "invalid capture DMA %d\n", dma2[n]);
 		return 0;
@@ -333,6 +335,7 @@ mpu:
 		break;
 	case 2:
 		mpu_irq[n] = 9;
+		/* Fall through */
 	case 9:
 		config[n] |= GALAXY_CONFIG_MPUIRQ_2;
 		break;
diff --git a/sound/isa/gus/gus_io.c b/sound/isa/gus/gus_io.c
index ca79878d8d8c..2fd32ef22c30 100644
--- a/sound/isa/gus/gus_io.c
+++ b/sound/isa/gus/gus_io.c
@@ -461,7 +461,7 @@ void snd_gf1_print_voice_registers(struct snd_gus_card * gus)
 			printk(KERN_INFO " -%i- GFA1 effect address         = 0x%x\n", voice, snd_gf1_i_read_addr(gus, 0x11, ctrl & 4));
 			printk(KERN_INFO " -%i- GFA1 effect volume          = 0x%x\n", voice, snd_gf1_i_read16(gus, 0x16));
 			printk(KERN_INFO " -%i- GFA1 effect volume final    = 0x%x\n", voice, snd_gf1_i_read16(gus, 0x1d));
-			printk(KERN_INFO " -%i- GFA1 effect acumulator      = 0x%x\n", voice, snd_gf1_i_read8(gus, 0x14));
+			printk(KERN_INFO " -%i- GFA1 effect accumulator     = 0x%x\n", voice, snd_gf1_i_read8(gus, 0x14));
 		}
 		if (mode & 0x20) {
 			printk(KERN_INFO " -%i- GFA1 left offset            = 0x%x (%i)\n", voice, snd_gf1_i_read16(gus, 0x13), snd_gf1_i_read16(gus, 0x13) >> 4);
diff --git a/sound/isa/gus/gus_main.c b/sound/isa/gus/gus_main.c
index 3cf9b13c780a..3b8a0c880db5 100644
--- a/sound/isa/gus/gus_main.c
+++ b/sound/isa/gus/gus_main.c
@@ -465,19 +465,3 @@ EXPORT_SYMBOL(snd_gf1_mem_alloc);
 EXPORT_SYMBOL(snd_gf1_mem_xfree);
 EXPORT_SYMBOL(snd_gf1_mem_free);
 EXPORT_SYMBOL(snd_gf1_mem_lock);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_gus_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_gus_exit(void)
-{
-}
-
-module_init(alsa_gus_init)
-module_exit(alsa_gus_exit)
diff --git a/sound/isa/gus/gus_reset.c b/sound/isa/gus/gus_reset.c
index 3d1fed0c2620..59b3f683d49b 100644
--- a/sound/isa/gus/gus_reset.c
+++ b/sound/isa/gus/gus_reset.c
@@ -292,7 +292,6 @@ void snd_gf1_free_voice(struct snd_gus_card * gus, struct snd_gus_voice *voice)
 {
 	unsigned long flags;
 	void (*private_free)(struct snd_gus_voice *voice);
-	void *private_data;
 
 	if (voice == NULL || !voice->use)
 		return;
@@ -300,7 +299,6 @@ void snd_gf1_free_voice(struct snd_gus_card * gus, struct snd_gus_voice *voice)
 	snd_gf1_clear_voices(gus, voice->number, voice->number);
 	spin_lock_irqsave(&gus->voice_alloc, flags);
 	private_free = voice->private_free;
-	private_data = voice->private_data;
 	voice->private_free = NULL;
 	voice->private_data = NULL;
 	if (voice->pcm)
diff --git a/sound/isa/msnd/msnd.c b/sound/isa/msnd/msnd.c
index 569897f64fda..7c3203fe4869 100644
--- a/sound/isa/msnd/msnd.c
+++ b/sound/isa/msnd/msnd.c
@@ -54,7 +54,7 @@
 #define LOGNAME			"msnd"
 
 
-void snd_msnd_init_queue(void *base, int start, int size)
+void snd_msnd_init_queue(void __iomem *base, int start, int size)
 {
 	writew(PCTODSP_BASED(start), base + JQS_wStart);
 	writew(PCTODSP_OFFSET(size) - 1, base + JQS_wSize);
@@ -270,7 +270,7 @@ int snd_msnd_DARQ(struct snd_msnd *chip, int bank)
 		udelay(1);
 
 	if (chip->capturePeriods == 2) {
-		void *pDAQ = chip->mappedbase + DARQ_DATA_BUFF +
+		void __iomem *pDAQ = chip->mappedbase + DARQ_DATA_BUFF +
 			     bank * DAQDS__size + DAQDS_wStart;
 		unsigned short offset = 0x3000 + chip->capturePeriodBytes;
 
@@ -309,7 +309,7 @@ int snd_msnd_DAPQ(struct snd_msnd *chip, int start)
 {
 	u16	DAPQ_tail;
 	int	protect = start, nbanks = 0;
-	void	*DAQD;
+	void	__iomem *DAQD;
 	static int play_banks_submitted;
 	/* unsigned long flags;
 	spin_lock_irqsave(&chip->lock, flags); not necessary */
@@ -370,7 +370,7 @@ static void snd_msnd_play_reset_queue(struct snd_msnd *chip,
 				      unsigned int pcm_count)
 {
 	int	n;
-	void	*pDAQ = chip->mappedbase + DAPQ_DATA_BUFF;
+	void	__iomem *pDAQ = chip->mappedbase + DAPQ_DATA_BUFF;
 
 	chip->last_playbank = -1;
 	chip->playLimit = pcm_count * (pcm_periods - 1);
@@ -398,7 +398,7 @@ static void snd_msnd_capture_reset_queue(struct snd_msnd *chip,
 					 unsigned int pcm_count)
 {
 	int		n;
-	void		*pDAQ;
+	void		__iomem *pDAQ;
 	/* unsigned long	flags; */
 
 	/* snd_msnd_init_queue(chip->DARQ, DARQ_DATA_BUFF, DARQ_BUFF_SIZE); */
@@ -485,7 +485,7 @@ static int snd_msnd_playback_open(struct snd_pcm_substream *substream)
 	clear_bit(F_WRITING, &chip->flags);
 	snd_msnd_enable_irq(chip);
 
-	runtime->dma_area = chip->mappedbase;
+	runtime->dma_area = (__force void *)chip->mappedbase;
 	runtime->dma_bytes = 0x3000;
 
 	chip->playback_substream = substream;
@@ -508,7 +508,7 @@ static int snd_msnd_playback_hw_params(struct snd_pcm_substream *substream,
 {
 	int	i;
 	struct snd_msnd *chip = snd_pcm_substream_chip(substream);
-	void	*pDAQ =	chip->mappedbase + DAPQ_DATA_BUFF;
+	void	__iomem *pDAQ =	chip->mappedbase + DAPQ_DATA_BUFF;
 
 	chip->play_sample_size = snd_pcm_format_width(params_format(params));
 	chip->play_channels = params_channels(params);
@@ -589,7 +589,7 @@ static int snd_msnd_capture_open(struct snd_pcm_substream *substream)
 
 	set_bit(F_AUDIO_READ_INUSE, &chip->flags);
 	snd_msnd_enable_irq(chip);
-	runtime->dma_area = chip->mappedbase + 0x3000;
+	runtime->dma_area = (__force void *)chip->mappedbase + 0x3000;
 	runtime->dma_bytes = 0x3000;
 	memset(runtime->dma_area, 0, runtime->dma_bytes);
 	chip->capture_substream = substream;
@@ -654,7 +654,7 @@ static int snd_msnd_capture_hw_params(struct snd_pcm_substream *substream,
 {
 	int		i;
 	struct snd_msnd *chip = snd_pcm_substream_chip(substream);
-	void		*pDAQ = chip->mappedbase + DARQ_DATA_BUFF;
+	void		__iomem *pDAQ = chip->mappedbase + DARQ_DATA_BUFF;
 
 	chip->capture_sample_size = snd_pcm_format_width(params_format(params));
 	chip->capture_channels = params_channels(params);
diff --git a/sound/isa/msnd/msnd.h b/sound/isa/msnd/msnd.h
index 5f3c7dcd9f9d..80c718757eef 100644
--- a/sound/isa/msnd/msnd.h
+++ b/sound/isa/msnd/msnd.h
@@ -283,7 +283,7 @@ struct snd_msnd {
 
 };
 
-void snd_msnd_init_queue(void *base, int start, int size);
+void snd_msnd_init_queue(void __iomem *base, int start, int size);
 
 int snd_msnd_send_dsp_cmd(struct snd_msnd *chip, u8 cmd);
 int snd_msnd_send_word(struct snd_msnd *chip,
diff --git a/sound/isa/msnd/msnd_midi.c b/sound/isa/msnd/msnd_midi.c
index 013d8d1170fe..42876b0cb68b 100644
--- a/sound/isa/msnd/msnd_midi.c
+++ b/sound/isa/msnd/msnd_midi.c
@@ -119,7 +119,7 @@ void snd_msndmidi_input_read(void *mpuv)
 {
 	unsigned long flags;
 	struct snd_msndmidi *mpu = mpuv;
-	void *pwMIDQData = mpu->dev->mappedbase + MIDQ_DATA_BUFF;
+	void __iomem *pwMIDQData = mpu->dev->mappedbase + MIDQ_DATA_BUFF;
 	u16 head, tail, size;
 
 	spin_lock_irqsave(&mpu->input_lock, flags);
diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c
index 6c584d9b6c42..11af9c40bc05 100644
--- a/sound/isa/msnd/msnd_pinnacle.c
+++ b/sound/isa/msnd/msnd_pinnacle.c
@@ -82,10 +82,10 @@
 
 static void set_default_audio_parameters(struct snd_msnd *chip)
 {
-	chip->play_sample_size = DEFSAMPLESIZE;
+	chip->play_sample_size = snd_pcm_format_width(DEFSAMPLESIZE);
 	chip->play_sample_rate = DEFSAMPLERATE;
 	chip->play_channels = DEFCHANNELS;
-	chip->capture_sample_size = DEFSAMPLESIZE;
+	chip->capture_sample_size = snd_pcm_format_width(DEFSAMPLESIZE);
 	chip->capture_sample_rate = DEFSAMPLERATE;
 	chip->capture_channels = DEFCHANNELS;
 }
@@ -169,7 +169,7 @@ static void snd_msnd_eval_dsp_msg(struct snd_msnd *chip, u16 wMessage)
 static irqreturn_t snd_msnd_interrupt(int irq, void *dev_id)
 {
 	struct snd_msnd *chip = dev_id;
-	void *pwDSPQData = chip->mappedbase + DSPQ_DATA_BUFF;
+	void __iomem *pwDSPQData = chip->mappedbase + DSPQ_DATA_BUFF;
 	u16 head, tail, size;
 
 	/* Send ack to DSP */
@@ -810,7 +810,7 @@ module_param(calibrate_signal, int, 0444);
 #ifndef MSND_CLASSIC
 module_param_array(digital, int, NULL, 0444);
 module_param_hw_array(cfg, long, ioport, NULL, 0444);
-module_param_array(reset, int, 0, 0444);
+module_param_array(reset, int, NULL, 0444);
 module_param_hw_array(mpu_io, long, ioport, NULL, 0444);
 module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
 module_param_hw_array(ide_io0, long, ioport, NULL, 0444);
diff --git a/sound/isa/opti9xx/miro.c b/sound/isa/opti9xx/miro.c
index 8894c7c18ad6..c6136c6b0214 100644
--- a/sound/isa/opti9xx/miro.c
+++ b/sound/isa/opti9xx/miro.c
@@ -176,10 +176,13 @@ static int aci_busy_wait(struct snd_miro_aci *aci)
 			switch (timeout-ACI_MINTIME) {
 			case 0 ... 9:
 				out /= 10;
+				/* fall through */
 			case 10 ... 19:
 				out /= 10;
+				/* fall through */
 			case 20 ... 30:
 				out /= 10;
+				/* fall through */
 			default:
 				set_current_state(TASK_UNINTERRUPTIBLE);
 				schedule_timeout(out);
@@ -834,6 +837,7 @@ static unsigned char snd_miro_read(struct snd_miro *chip,
 			retval = inb(chip->mc_base + 9);
 			break;
 		}
+		/* fall through */
 
 	case OPTi9XX_HW_82C929:
 		retval = inb(chip->mc_base + reg);
@@ -863,6 +867,7 @@ static void snd_miro_write(struct snd_miro *chip, unsigned char reg,
 			outb(value, chip->mc_base + 9);
 			break;
 		}
+		/* fall through */
 
 	case OPTi9XX_HW_82C929:
 		outb(value, chip->mc_base + reg);
diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c
index 505cd81e19fa..ac0ab6eb40f0 100644
--- a/sound/isa/opti9xx/opti92x-ad1848.c
+++ b/sound/isa/opti9xx/opti92x-ad1848.c
@@ -261,6 +261,7 @@ static unsigned char snd_opti9xx_read(struct snd_opti9xx *chip,
 			retval = inb(chip->mc_base + 9);
 			break;
 		}
+		/* Fall through */
 
 	case OPTi9XX_HW_82C928:
 	case OPTi9XX_HW_82C929:
@@ -303,6 +304,7 @@ static void snd_opti9xx_write(struct snd_opti9xx *chip, unsigned char reg,
 			outb(value, chip->mc_base + 9);
 			break;
 		}
+		/* Fall through */
 
 	case OPTi9XX_HW_82C928:
 	case OPTi9XX_HW_82C929:
@@ -350,6 +352,7 @@ static int snd_opti9xx_configure(struct snd_opti9xx *chip,
 		snd_opti9xx_write_mask(chip, OPTi9XX_MC_REG(4), 0xf0, 0xfc);
 		/* enable wave audio */
 		snd_opti9xx_write_mask(chip, OPTi9XX_MC_REG(6), 0x02, 0x02);
+		/* Fall through */
 
 	case OPTi9XX_HW_82C925:
 		/* enable WSS mode */
diff --git a/sound/isa/sb/emu8000_patch.c b/sound/isa/sb/emu8000_patch.c
index c2e41d2762f7..d45a6b9d6437 100644
--- a/sound/isa/sb/emu8000_patch.c
+++ b/sound/isa/sb/emu8000_patch.c
@@ -165,11 +165,8 @@ snd_emu8000_sample_new(struct snd_emux *rec, struct snd_sf_sample *sp,
 		return 0;
 
 	/* be sure loop points start < end */
-	if (sp->v.loopstart > sp->v.loopend) {
-		int tmp = sp->v.loopstart;
-		sp->v.loopstart = sp->v.loopend;
-		sp->v.loopend = tmp;
-	}
+	if (sp->v.loopstart > sp->v.loopend)
+		swap(sp->v.loopstart, sp->v.loopend);
 
 	/* compute true data size to be loaded */
 	truesize = sp->v.size;
diff --git a/sound/isa/sb/emu8000_pcm.c b/sound/isa/sb/emu8000_pcm.c
index bc5af71d3bdb..f46f6ec3ea0c 100644
--- a/sound/isa/sb/emu8000_pcm.c
+++ b/sound/isa/sb/emu8000_pcm.c
@@ -470,7 +470,7 @@ static int emu8k_pcm_copy(struct snd_pcm_substream *subs,
 	/* convert to word unit */
 	pos = (pos << 1) + rec->loop_start[voice];
 	count <<= 1;
-	LOOP_WRITE(rec, pos, src, count, COPY_UESR);
+	LOOP_WRITE(rec, pos, src, count, COPY_USER);
 	return 0;
 }
 
diff --git a/sound/isa/sb/sb16_csp.c b/sound/isa/sb/sb16_csp.c
index fa5780bb0c68..bf3db0d2ea12 100644
--- a/sound/isa/sb/sb16_csp.c
+++ b/sound/isa/sb/sb16_csp.c
@@ -60,18 +60,18 @@ MODULE_FIRMWARE("sb16/ima_adpcm_capture.csp");
  * RIFF data format
  */
 struct riff_header {
-	__u32 name;
-	__u32 len;
+	__le32 name;
+	__le32 len;
 };
 
 struct desc_header {
 	struct riff_header info;
-	__u16 func_nr;
-	__u16 VOC_type;
-	__u16 flags_play_rec;
-	__u16 flags_16bit_8bit;
-	__u16 flags_stereo_mono;
-	__u16 flags_rates;
+	__le16 func_nr;
+	__le16 VOC_type;
+	__le16 flags_play_rec;
+	__le16 flags_16bit_8bit;
+	__le16 flags_stereo_mono;
+	__le16 flags_rates;
 };
 
 /*
@@ -93,7 +93,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 				struct snd_sb_csp_microcode __user * code);
 static int snd_sb_csp_unload(struct snd_sb_csp * p);
 static int snd_sb_csp_load_user(struct snd_sb_csp * p, const unsigned char __user *buf, int size, int load_flags);
-static int snd_sb_csp_autoload(struct snd_sb_csp * p, int pcm_sfmt, int play_rec_mode);
+static int snd_sb_csp_autoload(struct snd_sb_csp * p, snd_pcm_format_t pcm_sfmt, int play_rec_mode);
 static int snd_sb_csp_check_version(struct snd_sb_csp * p);
 
 static int snd_sb_csp_use(struct snd_sb_csp * p);
@@ -314,7 +314,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 	unsigned short func_nr = 0;
 
 	struct riff_header file_h, item_h, code_h;
-	__u32 item_type;
+	__le32 item_type;
 	struct desc_header funcdesc_h;
 
 	unsigned long flags;
@@ -326,7 +326,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 
 	if (copy_from_user(&file_h, data_ptr, sizeof(file_h)))
 		return -EFAULT;
-	if ((file_h.name != RIFF_HEADER) ||
+	if ((le32_to_cpu(file_h.name) != RIFF_HEADER) ||
 	    (le32_to_cpu(file_h.len) >= SNDRV_SB_CSP_MAX_MICROCODE_FILE_SIZE - sizeof(file_h))) {
 		snd_printd("%s: Invalid RIFF header\n", __func__);
 		return -EINVAL;
@@ -336,7 +336,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 
 	if (copy_from_user(&item_type, data_ptr, sizeof(item_type)))
 		return -EFAULT;
-	if (item_type != CSP__HEADER) {
+	if (le32_to_cpu(item_type) != CSP__HEADER) {
 		snd_printd("%s: Invalid RIFF file type\n", __func__);
 		return -EINVAL;
 	}
@@ -346,12 +346,12 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 		if (copy_from_user(&item_h, data_ptr, sizeof(item_h)))
 			return -EFAULT;
 		data_ptr += sizeof(item_h);
-		if (item_h.name != LIST_HEADER)
+		if (le32_to_cpu(item_h.name) != LIST_HEADER)
 			continue;
 
 		if (copy_from_user(&item_type, data_ptr, sizeof(item_type)))
 			 return -EFAULT;
-		switch (item_type) {
+		switch (le32_to_cpu(item_type)) {
 		case FUNC_HEADER:
 			if (copy_from_user(&funcdesc_h, data_ptr + sizeof(item_type), sizeof(funcdesc_h)))
 				return -EFAULT;
@@ -378,7 +378,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 					return -EFAULT;
 
 				/* init microcode blocks */
-				if (code_h.name != INIT_HEADER)
+				if (le32_to_cpu(code_h.name) != INIT_HEADER)
 					break;
 				data_ptr += sizeof(code_h);
 				err = snd_sb_csp_load_user(p, data_ptr, le32_to_cpu(code_h.len),
@@ -391,7 +391,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 			if (copy_from_user(&code_h, data_ptr, sizeof(code_h)))
 				return -EFAULT;
 
-			if (code_h.name != MAIN_HEADER) {
+			if (le32_to_cpu(code_h.name) != MAIN_HEADER) {
 				snd_printd("%s: Missing 'main' microcode\n", __func__);
 				return -EINVAL;
 			}
@@ -726,7 +726,7 @@ static int snd_sb_csp_firmware_load(struct snd_sb_csp *p, int index, int flags)
  * autoload hardware codec if necessary
  * return 0 if CSP is loaded and ready to run (p->running != 0)
  */
-static int snd_sb_csp_autoload(struct snd_sb_csp * p, int pcm_sfmt, int play_rec_mode)
+static int snd_sb_csp_autoload(struct snd_sb_csp * p, snd_pcm_format_t pcm_sfmt, int play_rec_mode)
 {
 	unsigned long flags;
 	int err = 0;
@@ -736,7 +736,7 @@ static int snd_sb_csp_autoload(struct snd_sb_csp * p, int pcm_sfmt, int play_rec
 		return -EBUSY;
 
 	/* autoload microcode only if requested hardware codec is not already loaded */
-	if (((1 << pcm_sfmt) & p->acc_format) && (play_rec_mode & p->mode)) {
+	if (((1U << (__force int)pcm_sfmt) & p->acc_format) && (play_rec_mode & p->mode)) {
 		p->running = SNDRV_SB_CSP_ST_AUTO;
 	} else {
 		switch (pcm_sfmt) {
@@ -1185,19 +1185,3 @@ static void info_read(struct snd_info_entry *entry, struct snd_info_buffer *buff
 /* */
 
 EXPORT_SYMBOL(snd_sb_csp_new);
-
-/*
- * INIT part
- */
-
-static int __init alsa_sb_csp_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_sb_csp_exit(void)
-{
-}
-
-module_init(alsa_sb_csp_init)
-module_exit(alsa_sb_csp_exit)
diff --git a/sound/isa/sb/sb16_main.c b/sound/isa/sb/sb16_main.c
index 3e39ba220c39..37e6ce7b0b13 100644
--- a/sound/isa/sb/sb16_main.c
+++ b/sound/isa/sb/sb16_main.c
@@ -49,6 +49,9 @@ MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Routines for control of 16-bit SoundBlaster cards and clones");
 MODULE_LICENSE("GPL");
 
+#define runtime_format_bits(runtime) \
+	((unsigned int)pcm_format_to_bits((runtime)->format))
+
 #ifdef CONFIG_SND_SB16_CSP
 static void snd_sb16_csp_playback_prepare(struct snd_sb *chip, struct snd_pcm_runtime *runtime)
 {
@@ -58,7 +61,7 @@ static void snd_sb16_csp_playback_prepare(struct snd_sb *chip, struct snd_pcm_ru
 		if (csp->running & SNDRV_SB_CSP_ST_LOADED) {
 			/* manually loaded codec */
 			if ((csp->mode & SNDRV_SB_CSP_MODE_DSP_WRITE) &&
-			    ((1U << runtime->format) == csp->acc_format)) {
+			    (runtime_format_bits(runtime) == csp->acc_format)) {
 				/* Supported runtime PCM format for playback */
 				if (csp->ops.csp_use(csp) == 0) {
 					/* If CSP was successfully acquired */
@@ -66,7 +69,7 @@ static void snd_sb16_csp_playback_prepare(struct snd_sb *chip, struct snd_pcm_ru
 				}
 			} else if ((csp->mode & SNDRV_SB_CSP_MODE_QSOUND) && (csp->q_enabled)) {
 				/* QSound decoder is loaded and enabled */
-				if ((1 << runtime->format) & (SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_U8 |
+				if (runtime_format_bits(runtime) & (SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_U8 |
 							      SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_U16_LE)) {
 					/* Only for simple PCM formats */
 					if (csp->ops.csp_use(csp) == 0) {
@@ -106,7 +109,7 @@ static void snd_sb16_csp_capture_prepare(struct snd_sb *chip, struct snd_pcm_run
 		if (csp->running & SNDRV_SB_CSP_ST_LOADED) {
 			/* manually loaded codec */
 			if ((csp->mode & SNDRV_SB_CSP_MODE_DSP_READ) &&
-			    ((1U << runtime->format) == csp->acc_format)) {
+			    (runtime_format_bits(runtime) == csp->acc_format)) {
 				/* Supported runtime PCM format for capture */
 				if (csp->ops.csp_use(csp) == 0) {
 					/* If CSP was successfully acquired */
@@ -897,19 +900,3 @@ EXPORT_SYMBOL(snd_sb16dsp_pcm);
 EXPORT_SYMBOL(snd_sb16dsp_get_pcm_ops);
 EXPORT_SYMBOL(snd_sb16dsp_configure);
 EXPORT_SYMBOL(snd_sb16dsp_interrupt);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_sb16_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_sb16_exit(void)
-{
-}
-
-module_init(alsa_sb16_init)
-module_exit(alsa_sb16_exit)
diff --git a/sound/isa/sb/sb8_main.c b/sound/isa/sb/sb8_main.c
index d45df5c54423..481797744b3c 100644
--- a/sound/isa/sb/sb8_main.c
+++ b/sound/isa/sb/sb8_main.c
@@ -381,7 +381,6 @@ static int snd_sb8_capture_trigger(struct snd_pcm_substream *substream,
 irqreturn_t snd_sb8dsp_interrupt(struct snd_sb *chip)
 {
 	struct snd_pcm_substream *substream;
-	struct snd_pcm_runtime *runtime;
 
 	snd_sb_ack_8bit(chip);
 	switch (chip->mode) {
@@ -391,7 +390,6 @@ irqreturn_t snd_sb8dsp_interrupt(struct snd_sb *chip)
 		/* fallthru */
 	case SB_MODE_PLAYBACK_8:
 		substream = chip->playback_substream;
-		runtime = substream->runtime;
 		if (chip->playback_format == SB_DSP_OUTPUT)
 		    	snd_sb8_playback_trigger(substream, SNDRV_PCM_TRIGGER_START);
 		snd_pcm_period_elapsed(substream);
@@ -402,7 +400,6 @@ irqreturn_t snd_sb8dsp_interrupt(struct snd_sb *chip)
 		/* fallthru */
 	case SB_MODE_CAPTURE_8:
 		substream = chip->capture_substream;
-		runtime = substream->runtime;
 		if (chip->capture_format == SB_DSP_INPUT)
 		    	snd_sb8_capture_trigger(substream, SNDRV_PCM_TRIGGER_START);
 		snd_pcm_period_elapsed(substream);
@@ -624,19 +621,3 @@ EXPORT_SYMBOL(snd_sb8dsp_interrupt);
   /* sb8_midi.c */
 EXPORT_SYMBOL(snd_sb8dsp_midi_interrupt);
 EXPORT_SYMBOL(snd_sb8dsp_midi);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_sb8_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_sb8_exit(void)
-{
-}
-
-module_init(alsa_sb8_init)
-module_exit(alsa_sb8_exit)
diff --git a/sound/isa/sb/sb_common.c b/sound/isa/sb/sb_common.c
index 787a4ade4afd..90b254aaef74 100644
--- a/sound/isa/sb/sb_common.c
+++ b/sound/isa/sb/sb_common.c
@@ -305,19 +305,3 @@ EXPORT_SYMBOL(snd_sbmixer_add_ctl);
 EXPORT_SYMBOL(snd_sbmixer_suspend);
 EXPORT_SYMBOL(snd_sbmixer_resume);
 #endif
-
-/*
- *  INIT part
- */
-
-static int __init alsa_sb_common_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_sb_common_exit(void)
-{
-}
-
-module_init(alsa_sb_common_init)
-module_exit(alsa_sb_common_exit)
diff --git a/sound/isa/wss/wss_lib.c b/sound/isa/wss/wss_lib.c
index 8a852042a066..32453f81b95a 100644
--- a/sound/isa/wss/wss_lib.c
+++ b/sound/isa/wss/wss_lib.c
@@ -541,7 +541,7 @@ static unsigned char snd_wss_get_rate(unsigned int rate)
 }
 
 static unsigned char snd_wss_get_format(struct snd_wss *chip,
-					int format,
+					snd_pcm_format_t format,
 					int channels)
 {
 	unsigned char rformat;
@@ -2279,19 +2279,3 @@ const struct snd_pcm_ops *snd_wss_get_pcm_ops(int direction)
 		&snd_wss_playback_ops : &snd_wss_capture_ops;
 }
 EXPORT_SYMBOL(snd_wss_get_pcm_ops);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_wss_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_wss_exit(void)
-{
-}
-
-module_init(alsa_wss_init);
-module_exit(alsa_wss_exit);
diff --git a/sound/mips/sgio2audio.c b/sound/mips/sgio2audio.c
index 9fb68b35de5a..3ec9391a4736 100644
--- a/sound/mips/sgio2audio.c
+++ b/sound/mips/sgio2audio.c
@@ -685,7 +685,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback1_ops = {
 	.trigger =     snd_sgio2audio_pcm_trigger,
 	.pointer =     snd_sgio2audio_pcm_pointer,
 	.page =        snd_pcm_lib_get_vmalloc_page,
-	.mmap =        snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = {
@@ -698,7 +697,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = {
 	.trigger =     snd_sgio2audio_pcm_trigger,
 	.pointer =     snd_sgio2audio_pcm_pointer,
 	.page =        snd_pcm_lib_get_vmalloc_page,
-	.mmap =        snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops snd_sgio2audio_capture_ops = {
@@ -711,7 +709,6 @@ static const struct snd_pcm_ops snd_sgio2audio_capture_ops = {
 	.trigger =     snd_sgio2audio_pcm_trigger,
 	.pointer =     snd_sgio2audio_pcm_pointer,
 	.page =        snd_pcm_lib_get_vmalloc_page,
-	.mmap =        snd_pcm_lib_mmap_vmalloc,
 };
 
 /*
diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c
index 1ef7cdf1d3e8..f4459d1a9d67 100644
--- a/sound/pci/ac97/ac97_codec.c
+++ b/sound/pci/ac97/ac97_codec.c
@@ -2941,19 +2941,3 @@ int snd_ac97_tune_hardware(struct snd_ac97 *ac97,
 }
 
 EXPORT_SYMBOL(snd_ac97_tune_hardware);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_ac97_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_ac97_exit(void)
-{
-}
-
-module_init(alsa_ac97_init)
-module_exit(alsa_ac97_exit)
diff --git a/sound/pci/ali5451/ali5451.c b/sound/pci/ali5451/ali5451.c
index 39547e32e584..9f569379b77e 100644
--- a/sound/pci/ali5451/ali5451.c
+++ b/sound/pci/ali5451/ali5451.c
@@ -1484,12 +1484,9 @@ static struct snd_pcm_hardware snd_ali_capture =
 static void snd_ali_pcm_free_substream(struct snd_pcm_runtime *runtime)
 {
 	struct snd_ali_voice *pvoice = runtime->private_data;
-	struct snd_ali *codec;
 
-	if (pvoice) {
-		codec = pvoice->codec;
+	if (pvoice)
 		snd_ali_free_voice(pvoice->codec, pvoice);
-	}
 }
 
 static int snd_ali_open(struct snd_pcm_substream *substream, int rec,
diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c
index 64e0961f93ba..a31fe1550903 100644
--- a/sound/pci/asihpi/asihpi.c
+++ b/sound/pci/asihpi/asihpi.c
@@ -311,27 +311,29 @@ static void print_hwparams(struct snd_pcm_substream *substream,
 		snd_pcm_format_width(params_format(p)) / 8);
 }
 
+#define INVALID_FORMAT	(__force snd_pcm_format_t)(-1)
+
 static snd_pcm_format_t hpi_to_alsa_formats[] = {
-	-1,			/* INVALID */
+	INVALID_FORMAT,		/* INVALID */
 	SNDRV_PCM_FORMAT_U8,	/* HPI_FORMAT_PCM8_UNSIGNED        1 */
 	SNDRV_PCM_FORMAT_S16,	/* HPI_FORMAT_PCM16_SIGNED         2 */
-	-1,			/* HPI_FORMAT_MPEG_L1              3 */
+	INVALID_FORMAT,		/* HPI_FORMAT_MPEG_L1              3 */
 	SNDRV_PCM_FORMAT_MPEG,	/* HPI_FORMAT_MPEG_L2              4 */
 	SNDRV_PCM_FORMAT_MPEG,	/* HPI_FORMAT_MPEG_L3              5 */
-	-1,			/* HPI_FORMAT_DOLBY_AC2            6 */
-	-1,			/* HPI_FORMAT_DOLBY_AC3            7 */
+	INVALID_FORMAT,		/* HPI_FORMAT_DOLBY_AC2            6 */
+	INVALID_FORMAT,		/* HPI_FORMAT_DOLBY_AC3            7 */
 	SNDRV_PCM_FORMAT_S16_BE,/* HPI_FORMAT_PCM16_BIGENDIAN      8 */
-	-1,			/* HPI_FORMAT_AA_TAGIT1_HITS       9 */
-	-1,			/* HPI_FORMAT_AA_TAGIT1_INSERTS   10 */
+	INVALID_FORMAT,		/* HPI_FORMAT_AA_TAGIT1_HITS       9 */
+	INVALID_FORMAT,		/* HPI_FORMAT_AA_TAGIT1_INSERTS   10 */
 	SNDRV_PCM_FORMAT_S32,	/* HPI_FORMAT_PCM32_SIGNED        11 */
-	-1,			/* HPI_FORMAT_RAW_BITSTREAM       12 */
-	-1,			/* HPI_FORMAT_AA_TAGIT1_HITS_EX1  13 */
+	INVALID_FORMAT,		/* HPI_FORMAT_RAW_BITSTREAM       12 */
+	INVALID_FORMAT,		/* HPI_FORMAT_AA_TAGIT1_HITS_EX1  13 */
 	SNDRV_PCM_FORMAT_FLOAT,	/* HPI_FORMAT_PCM32_FLOAT         14 */
 #if 1
 	/* ALSA can't handle 3 byte sample size together with power-of-2
 	 *  constraint on buffer_bytes, so disable this format
 	 */
-	-1
+	INVALID_FORMAT
 #else
 	/* SNDRV_PCM_FORMAT_S24_3LE */ /* HPI_FORMAT_PCM24_SIGNED 15 */
 #endif
@@ -1023,7 +1025,7 @@ static u64 snd_card_asihpi_playback_formats(struct snd_card_asihpi *asihpi,
 					format, sample_rate, 128000, 0);
 		if (!err)
 			err = hpi_outstream_query_format(h_stream, &hpi_format);
-		if (!err && (hpi_to_alsa_formats[format] != -1))
+		if (!err && (hpi_to_alsa_formats[format] != INVALID_FORMAT))
 			formats |= pcm_format_to_bits(hpi_to_alsa_formats[format]);
 	}
 	return formats;
@@ -1205,7 +1207,7 @@ static u64 snd_card_asihpi_capture_formats(struct snd_card_asihpi *asihpi,
 					format, sample_rate, 128000, 0);
 		if (!err)
 			err = hpi_instream_query_format(h_stream, &hpi_format);
-		if (!err && (hpi_to_alsa_formats[format] != -1))
+		if (!err && (hpi_to_alsa_formats[format] != INVALID_FORMAT))
 			formats |= pcm_format_to_bits(hpi_to_alsa_formats[format]);
 	}
 	return formats;
diff --git a/sound/pci/asihpi/hpi6205.c b/sound/pci/asihpi/hpi6205.c
index 8d5abfa4e24b..2864698436a5 100644
--- a/sound/pci/asihpi/hpi6205.c
+++ b/sound/pci/asihpi/hpi6205.c
@@ -635,7 +635,6 @@ static u16 create_adapter_obj(struct hpi_adapter_obj *pao,
 	{
 		struct hpi_message hm;
 		struct hpi_response hr;
-		u32 max_streams;
 
 		HPI_DEBUG_LOG(VERBOSE, "init ADAPTER_GET_INFO\n");
 		memset(&hm, 0, sizeof(hm));
@@ -660,10 +659,6 @@ static u16 create_adapter_obj(struct hpi_adapter_obj *pao,
 		pao->type = hr.u.ax.info.adapter_type;
 		pao->index = hr.u.ax.info.adapter_index;
 
-		max_streams =
-			hr.u.ax.info.num_outstreams +
-			hr.u.ax.info.num_instreams;
-
 		HPI_DEBUG_LOG(VERBOSE,
 			"got adapter info type %x index %d serial %d\n",
 			hr.u.ax.info.adapter_type, hr.u.ax.info.adapter_index,
diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c
index 7ae63d452bba..a1e4944dcfe8 100644
--- a/sound/pci/atiixp.c
+++ b/sound/pci/atiixp.c
@@ -207,10 +207,10 @@ struct atiixp;
  */
 
 struct atiixp_dma_desc {
-	u32 addr;	/* DMA buffer address */
+	__le32 addr;	/* DMA buffer address */
 	u16 status;	/* status bits */
 	u16 size;	/* size of the packet in dwords */
-	u32 next;	/* address of the next packet descriptor */
+	__le32 next;	/* address of the next packet descriptor */
 };
 
 /*
diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c
index a586635664e0..dc1de860cedf 100644
--- a/sound/pci/atiixp_modem.c
+++ b/sound/pci/atiixp_modem.c
@@ -183,10 +183,10 @@ struct atiixp_modem;
  */
 
 struct atiixp_dma_desc {
-	u32 addr;	/* DMA buffer address */
+	__le32 addr;	/* DMA buffer address */
 	u16 status;	/* status bits */
 	u16 size;	/* size of the packet in dwords */
-	u32 next;	/* address of the next packet descriptor */
+	__le32 next;	/* address of the next packet descriptor */
 };
 
 /*
diff --git a/sound/pci/au88x0/au88x0.h b/sound/pci/au88x0/au88x0.h
index bcc648bf6478..e3e31f07d766 100644
--- a/sound/pci/au88x0/au88x0.h
+++ b/sound/pci/au88x0/au88x0.h
@@ -241,7 +241,7 @@ static int vortex_core_init(vortex_t * card);
 static int vortex_core_shutdown(vortex_t * card);
 static void vortex_enable_int(vortex_t * card);
 static irqreturn_t vortex_interrupt(int irq, void *dev_id);
-static int vortex_alsafmt_aspfmt(int alsafmt, vortex_t *v);
+static int vortex_alsafmt_aspfmt(snd_pcm_format_t alsafmt, vortex_t *v);
 
 /* Connection  stuff. */
 static void vortex_connect_default(vortex_t * vortex, int en);
diff --git a/sound/pci/au88x0/au88x0_core.c b/sound/pci/au88x0/au88x0_core.c
index 4083c8b01619..2e5b460a847c 100644
--- a/sound/pci/au88x0/au88x0_core.c
+++ b/sound/pci/au88x0/au88x0_core.c
@@ -2770,7 +2770,7 @@ static int vortex_core_shutdown(vortex_t * vortex)
 
 /* Alsa support. */
 
-static int vortex_alsafmt_aspfmt(int alsafmt, vortex_t *v)
+static int vortex_alsafmt_aspfmt(snd_pcm_format_t alsafmt, vortex_t *v)
 {
 	int fmt;
 
diff --git a/sound/pci/bt87x.c b/sound/pci/bt87x.c
index d8ade8771a32..ba971042f871 100644
--- a/sound/pci/bt87x.c
+++ b/sound/pci/bt87x.c
@@ -228,14 +228,14 @@ static int snd_bt87x_create_risc(struct snd_bt87x *chip, struct snd_pcm_substrea
 			       	 unsigned int periods, unsigned int period_bytes)
 {
 	unsigned int i, offset;
-	u32 *risc;
+	__le32 *risc;
 
 	if (chip->dma_risc.area == NULL) {
 		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
 					PAGE_ALIGN(MAX_RISC_SIZE), &chip->dma_risc) < 0)
 			return -ENOMEM;
 	}
-	risc = (u32 *)chip->dma_risc.area;
+	risc = (__le32 *)chip->dma_risc.area;
 	offset = 0;
 	*risc++ = cpu_to_le32(RISC_SYNC | RISC_SYNC_FM1);
 	*risc++ = cpu_to_le32(0);
diff --git a/sound/pci/cs46xx/dsp_spos_scb_lib.c b/sound/pci/cs46xx/dsp_spos_scb_lib.c
index abb01ce66983..8d0a3d357345 100644
--- a/sound/pci/cs46xx/dsp_spos_scb_lib.c
+++ b/sound/pci/cs46xx/dsp_spos_scb_lib.c
@@ -73,13 +73,10 @@ static void cs46xx_dsp_proc_scb_info_read (struct snd_info_entry *entry,
 {
 	struct proc_scb_info * scb_info  = entry->private_data;
 	struct dsp_scb_descriptor * scb = scb_info->scb_desc;
-	struct dsp_spos_instance * ins;
 	struct snd_cs46xx *chip = scb_info->chip;
 	int j,col;
 	void __iomem *dst = chip->region.idx[1].remap_addr + DSP_PARAMETER_BYTE_OFFSET;
 
-	ins = chip->dsp_spos_instance;
-
 	mutex_lock(&chip->spos_mutex);
 	snd_iprintf(buffer,"%04x %s:\n",scb->address,scb->scb_name);
 
diff --git a/sound/pci/cs5535audio/cs5535audio.c b/sound/pci/cs5535audio/cs5535audio.c
index de409cda50aa..4590086d9cd8 100644
--- a/sound/pci/cs5535audio/cs5535audio.c
+++ b/sound/pci/cs5535audio/cs5535audio.c
@@ -192,8 +192,6 @@ static void process_bm0_irq(struct cs5535audio *cs5535au)
 	bm_stat = cs_readb(cs5535au, ACC_BM0_STATUS);
 	spin_unlock(&cs5535au->reg_lock);
 	if (bm_stat & EOP) {
-		struct cs5535audio_dma *dma;
-		dma = cs5535au->playback_substream->runtime->private_data;
 		snd_pcm_period_elapsed(cs5535au->playback_substream);
 	} else {
 		dev_err(cs5535au->card->dev,
@@ -208,11 +206,8 @@ static void process_bm1_irq(struct cs5535audio *cs5535au)
 	spin_lock(&cs5535au->reg_lock);
 	bm_stat = cs_readb(cs5535au, ACC_BM1_STATUS);
 	spin_unlock(&cs5535au->reg_lock);
-	if (bm_stat & EOP) {
-		struct cs5535audio_dma *dma;
-		dma = cs5535au->capture_substream->runtime->private_data;
+	if (bm_stat & EOP)
 		snd_pcm_period_elapsed(cs5535au->capture_substream);
-	}
 }
 
 static irqreturn_t snd_cs5535audio_interrupt(int irq, void *dev_id)
diff --git a/sound/pci/cs5535audio/cs5535audio.h b/sound/pci/cs5535audio/cs5535audio.h
index f4fcdf93f3c8..d84620a0c26c 100644
--- a/sound/pci/cs5535audio/cs5535audio.h
+++ b/sound/pci/cs5535audio/cs5535audio.h
@@ -67,9 +67,9 @@ struct cs5535audio_dma_ops {
 };
 
 struct cs5535audio_dma_desc {
-	u32 addr;
-	u16 size;
-	u16 ctlreserved;
+	__le32 addr;
+	__le16 size;
+	__le16 ctlreserved;
 };
 
 struct cs5535audio_dma {
diff --git a/sound/pci/cs5535audio/cs5535audio_pcm.c b/sound/pci/cs5535audio/cs5535audio_pcm.c
index ee7065f6e162..326caec854e1 100644
--- a/sound/pci/cs5535audio/cs5535audio_pcm.c
+++ b/sound/pci/cs5535audio/cs5535audio_pcm.c
@@ -158,8 +158,8 @@ static int cs5535audio_build_dma_packets(struct cs5535audio *cs5535au,
 	lastdesc->addr = cpu_to_le32((u32) dma->desc_buf.addr);
 	lastdesc->size = 0;
 	lastdesc->ctlreserved = cpu_to_le16(PRD_JMP);
-	jmpprd_addr = cpu_to_le32(lastdesc->addr +
-				  (sizeof(struct cs5535audio_dma_desc)*periods));
+	jmpprd_addr = (u32)dma->desc_buf.addr +
+		sizeof(struct cs5535audio_dma_desc) * periods;
 
 	dma->substream = substream;
 	dma->period_bytes = period_bytes;
diff --git a/sound/pci/ctxfi/cthw20k1.c b/sound/pci/ctxfi/cthw20k1.c
index 8e6eb9d7984b..6a051a1c3724 100644
--- a/sound/pci/ctxfi/cthw20k1.c
+++ b/sound/pci/ctxfi/cthw20k1.c
@@ -1319,7 +1319,7 @@ static int hw_pll_init(struct hw *hw, unsigned int rsr)
 			break;
 
 		hw_write_20kx(hw, PLLCTL, pllctl);
-		mdelay(40);
+		msleep(40);
 	}
 	if (i >= 3) {
 		dev_alert(hw->card->dev, "PLL initialization failed!!!\n");
@@ -1407,7 +1407,7 @@ static int hw_reset_dac(struct hw *hw)
 	/* To be effective, need to reset the DAC twice. */
 	for (i = 0; i < 2;  i++) {
 		/* set gpio */
-		mdelay(100);
+		msleep(100);
 		gpioorg = (u16)hw_read_20kx(hw, GPIO);
 		gpioorg &= 0xfffd;
 		hw_write_20kx(hw, GPIO, gpioorg);
@@ -2030,7 +2030,7 @@ static int hw_card_init(struct hw *hw, struct card_conf *info)
 	hw_write_20kx(hw, GIE, 0);
 	/* Reset all SRC pending interrupts */
 	hw_write_20kx(hw, SRCIP, 0);
-	mdelay(30);
+	msleep(30);
 
 	/* Detect the card ID and configure GPIO accordingly. */
 	switch (hw->model) {
diff --git a/sound/pci/ctxfi/cthw20k2.c b/sound/pci/ctxfi/cthw20k2.c
index b866d6b2c923..3c966fafc754 100644
--- a/sound/pci/ctxfi/cthw20k2.c
+++ b/sound/pci/ctxfi/cthw20k2.c
@@ -1316,12 +1316,12 @@ static int hw_pll_init(struct hw *hw, unsigned int rsr)
 	set_field(&pllctl, PLLCTL_FD, 48000 == rsr ? 16 - 4 : 147 - 4);
 	set_field(&pllctl, PLLCTL_RD, 48000 == rsr ? 1 - 1 : 10 - 1);
 	hw_write_20kx(hw, PLL_CTL, pllctl);
-	mdelay(40);
+	msleep(40);
 
 	pllctl = hw_read_20kx(hw, PLL_CTL);
 	set_field(&pllctl, PLLCTL_FD, 48000 == rsr ? 16 - 2 : 147 - 2);
 	hw_write_20kx(hw, PLL_CTL, pllctl);
-	mdelay(40);
+	msleep(40);
 
 	for (i = 0; i < 1000; i++) {
 		pllstat = hw_read_20kx(hw, PLL_STAT);
@@ -1584,7 +1584,7 @@ static void hw_dac_stop(struct hw *hw)
 	data = hw_read_20kx(hw, GPIO_DATA);
 	data &= 0xFFFFFFFD;
 	hw_write_20kx(hw, GPIO_DATA, data);
-	mdelay(10);
+	usleep_range(10000, 11000);
 }
 
 static void hw_dac_start(struct hw *hw)
@@ -1593,7 +1593,7 @@ static void hw_dac_start(struct hw *hw)
 	data = hw_read_20kx(hw, GPIO_DATA);
 	data |= 0x2;
 	hw_write_20kx(hw, GPIO_DATA, data);
-	mdelay(50);
+	msleep(50);
 }
 
 static void hw_dac_reset(struct hw *hw)
@@ -1864,11 +1864,11 @@ static int hw_adc_init(struct hw *hw, const struct adc_conf *info)
 		hw_write_20kx(hw, GPIO_DATA, data);
 	}
 
-	mdelay(10);
+	usleep_range(10000, 11000);
 	/* Return the ADC to normal operation. */
 	data |= (0x1 << 15);
 	hw_write_20kx(hw, GPIO_DATA, data);
-	mdelay(50);
+	msleep(50);
 
 	/* I2C write to register offset 0x0B to set ADC LRCLK polarity */
 	/* invert bit, interface format to I2S, word length to 24-bit, */
diff --git a/sound/pci/ctxfi/ctmixer.c b/sound/pci/ctxfi/ctmixer.c
index db710d0a609f..4777d50fbbf8 100644
--- a/sound/pci/ctxfi/ctmixer.c
+++ b/sound/pci/ctxfi/ctmixer.c
@@ -938,17 +938,18 @@ static int ct_mixer_topology_build(struct ct_mixer *mixer)
 	struct sum *sum;
 	struct amixer *amix_d, *amix_s;
 	enum CT_AMIXER_CTL i, j;
+	enum CT_SUM_CTL k;
 
 	/* Build topology from destination to source */
 
 	/* Set up Master mixer */
-	for (i = AMIXER_MASTER_F, j = SUM_IN_F;
-					i <= AMIXER_MASTER_S; i++, j++) {
+	for (i = AMIXER_MASTER_F, k = SUM_IN_F;
+					i <= AMIXER_MASTER_S; i++, k++) {
 		amix_d = mixer->amixers[i*CHN_NUM];
-		sum = mixer->sums[j*CHN_NUM];
+		sum = mixer->sums[k*CHN_NUM];
 		amix_d->ops->setup(amix_d, &sum->rsc, INIT_VOL, NULL);
 		amix_d = mixer->amixers[i*CHN_NUM+1];
-		sum = mixer->sums[j*CHN_NUM+1];
+		sum = mixer->sums[k*CHN_NUM+1];
 		amix_d->ops->setup(amix_d, &sum->rsc, INIT_VOL, NULL);
 	}
 
@@ -972,12 +973,12 @@ static int ct_mixer_topology_build(struct ct_mixer *mixer)
 	amix_d->ops->setup(amix_d, &amix_s->rsc, INIT_VOL, NULL);
 
 	/* Set up PCM-in mixer */
-	for (i = AMIXER_PCM_F, j = SUM_IN_F; i <= AMIXER_PCM_S; i++, j++) {
+	for (i = AMIXER_PCM_F, k = SUM_IN_F; i <= AMIXER_PCM_S; i++, k++) {
 		amix_d = mixer->amixers[i*CHN_NUM];
-		sum = mixer->sums[j*CHN_NUM];
+		sum = mixer->sums[k*CHN_NUM];
 		amix_d->ops->setup(amix_d, NULL, INIT_VOL, sum);
 		amix_d = mixer->amixers[i*CHN_NUM+1];
-		sum = mixer->sums[j*CHN_NUM+1];
+		sum = mixer->sums[k*CHN_NUM+1];
 		amix_d->ops->setup(amix_d, NULL, INIT_VOL, sum);
 	}
 
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index 358ef7dcf410..907cf1a46712 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -713,6 +713,7 @@ static int pcm_prepare(struct snd_pcm_substream *substream)
 		break;
 	case SNDRV_PCM_FORMAT_S32_BE:
 		format.data_are_bigendian = 1;
+		/* fall through */
 	case SNDRV_PCM_FORMAT_S32_LE:
 		format.bits_per_sample = 32;
 		break;
@@ -764,6 +765,7 @@ static int pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 					pipe->last_counter = 0;
 					pipe->position = 0;
 					*pipe->dma_counter = 0;
+					/* fall through */
 				case PIPE_STATE_PAUSED:
 					pipe->state = PIPE_STATE_STARTED;
 					break;
diff --git a/sound/pci/echoaudio/echoaudio.h b/sound/pci/echoaudio/echoaudio.h
index 44b390a667d5..be4d0489394a 100644
--- a/sound/pci/echoaudio/echoaudio.h
+++ b/sound/pci/echoaudio/echoaudio.h
@@ -294,7 +294,7 @@
 
 
 struct audiopipe {
-	volatile u32 *dma_counter;	/* Commpage register that contains
+	volatile __le32 *dma_counter;	/* Commpage register that contains
 					 * the current dma position
 					 * (lower 32 bits only)
 					 */
diff --git a/sound/pci/echoaudio/echoaudio_3g.c b/sound/pci/echoaudio/echoaudio_3g.c
index 22c786b8a889..cc3c79387194 100644
--- a/sound/pci/echoaudio/echoaudio_3g.c
+++ b/sound/pci/echoaudio/echoaudio_3g.c
@@ -73,19 +73,21 @@ register. write_control_reg sends the new control register value to the DSP. */
 static int write_control_reg(struct echoaudio *chip, u32 ctl, u32 frq,
 			     char force)
 {
+	__le32 ctl_reg, frq_reg;
+
 	if (wait_handshake(chip))
 		return -EIO;
 
 	dev_dbg(chip->card->dev,
 		"WriteControlReg: Setting 0x%x, 0x%x\n", ctl, frq);
 
-	ctl = cpu_to_le32(ctl);
-	frq = cpu_to_le32(frq);
+	ctl_reg = cpu_to_le32(ctl);
+	frq_reg = cpu_to_le32(frq);
 
-	if (ctl != chip->comm_page->control_register ||
-	    frq != chip->comm_page->e3g_frq_register || force) {
-		chip->comm_page->e3g_frq_register = frq;
-		chip->comm_page->control_register = ctl;
+	if (ctl_reg != chip->comm_page->control_register ||
+	    frq_reg != chip->comm_page->e3g_frq_register || force) {
+		chip->comm_page->e3g_frq_register = frq_reg;
+		chip->comm_page->control_register = ctl_reg;
 		clear_handshake(chip);
 		return send_vector(chip, DSP_VC_WRITE_CONTROL_REG);
 	}
diff --git a/sound/pci/echoaudio/echoaudio_dsp.c b/sound/pci/echoaudio/echoaudio_dsp.c
index 15aae2fad8e4..b181752b8481 100644
--- a/sound/pci/echoaudio/echoaudio_dsp.c
+++ b/sound/pci/echoaudio/echoaudio_dsp.c
@@ -679,7 +679,7 @@ static int restore_dsp_rettings(struct echoaudio *chip)
 	/* Gina20/Darla20 only. Should be harmless for other cards. */
 	chip->comm_page->gd_clock_state = GD_CLOCK_UNDEF;
 	chip->comm_page->gd_spdif_status = GD_SPDIF_STATUS_UNDEF;
-	chip->comm_page->handshake = 0xffffffff;
+	chip->comm_page->handshake = cpu_to_le32(0xffffffff);
 
 	/* Restore output busses */
 	for (i = 0; i < num_busses_out(chip); i++) {
@@ -989,7 +989,7 @@ static int init_dsp_comm_page(struct echoaudio *chip)
 	/* Init the comm page */
 	chip->comm_page->comm_size =
 		cpu_to_le32(sizeof(struct comm_page));
-	chip->comm_page->handshake = 0xffffffff;
+	chip->comm_page->handshake = cpu_to_le32(0xffffffff);
 	chip->comm_page->midi_out_free_count =
 		cpu_to_le32(DSP_MIDI_OUT_FIFO_SIZE);
 	chip->comm_page->sample_rate = cpu_to_le32(44100);
@@ -1087,7 +1087,7 @@ static int allocate_pipes(struct echoaudio *chip, struct audiopipe *pipe,
 	/* The counter register is where the DSP writes the 32 bit DMA
 	position for a pipe.  The DSP is constantly updating this value as
 	it moves data. The DMA counter is in units of bytes, not samples. */
-	pipe->dma_counter = &chip->comm_page->position[pipe_index];
+	pipe->dma_counter = (__le32 *)&chip->comm_page->position[pipe_index];
 	*pipe->dma_counter = 0;
 	return pipe_index;
 }
diff --git a/sound/pci/echoaudio/echoaudio_dsp.h b/sound/pci/echoaudio/echoaudio_dsp.h
index cb7d75a0a503..aa9129519795 100644
--- a/sound/pci/echoaudio/echoaudio_dsp.h
+++ b/sound/pci/echoaudio/echoaudio_dsp.h
@@ -627,8 +627,8 @@ sg_entry struct is read by the DSP, so all values must be little-endian. */
 #define MAX_SGLIST_ENTRIES 512
 
 struct sg_entry {
-	u32 addr;
-	u32 size;
+	__le32 addr;
+	__le32 size;
 };
 
 
@@ -643,18 +643,18 @@ struct sg_entry {
  ****************************************************************************/
 
 struct comm_page {		/*				Base	Length*/
-	u32 comm_size;		/* size of this object		0x000	4 */
-	u32 flags;		/* See Appendix A below		0x004	4 */
-	u32 unused;		/* Unused entry			0x008	4 */
-	u32 sample_rate;	/* Card sample rate in Hz	0x00c	4 */
-	u32 handshake;		/* DSP command handshake	0x010	4 */
-	u32 cmd_start;		/* Chs. to start mask		0x014	4 */
-	u32 cmd_stop;		/* Chs. to stop mask		0x018	4 */
-	u32 cmd_reset;		/* Chs. to reset mask		0x01c	4 */
-	u16 audio_format[DSP_MAXPIPES];	/* Chs. audio format	0x020	32*2 */
+	__le32 comm_size;	/* size of this object		0x000	4 */
+	__le32 flags;		/* See Appendix A below		0x004	4 */
+	__le32 unused;		/* Unused entry			0x008	4 */
+	__le32 sample_rate;	/* Card sample rate in Hz	0x00c	4 */
+	__le32 handshake;	/* DSP command handshake	0x010	4 */
+	__le32 cmd_start;	/* Chs. to start mask		0x014	4 */
+	__le32 cmd_stop;	/* Chs. to stop mask		0x018	4 */
+	__le32 cmd_reset;	/* Chs. to reset mask		0x01c	4 */
+	__le16 audio_format[DSP_MAXPIPES];	/* Chs. audio format	0x020	32*2 */
 	struct sg_entry sglist_addr[DSP_MAXPIPES];
 				/* Chs. Physical sglist addrs	0x060	32*8 */
-	u32 position[DSP_MAXPIPES];
+	__le32 position[DSP_MAXPIPES];
 				/* Positions for ea. ch.	0x160	32*4 */
 	s8 vu_meter[DSP_MAXPIPES];
 				/* VU meters			0x1e0	32*1 */
@@ -666,28 +666,28 @@ struct comm_page {		/*				Base	Length*/
 				/* Input gain			0x230	16*1 */
 	s8 monitors[MONITOR_ARRAY_SIZE];
 				/* Monitor map			0x240	0x180 */
-	u32 play_coeff[MAX_PLAY_TAPS];
+	__le32 play_coeff[MAX_PLAY_TAPS];
 			/* Gina/Darla play filters - obsolete	0x3c0	168*4 */
-	u32 rec_coeff[MAX_REC_TAPS];
+	__le32 rec_coeff[MAX_REC_TAPS];
 			/* Gina/Darla record filters - obsolete	0x660	192*4 */
-	u16 midi_input[MIDI_IN_BUFFER_SIZE];
+	__le16 midi_input[MIDI_IN_BUFFER_SIZE];
 			/* MIDI input data transfer buffer	0x960	256*2 */
 	u8 gd_clock_state;	/* Chg Gina/Darla clock state	0xb60	1 */
 	u8 gd_spdif_status;	/* Chg. Gina/Darla S/PDIF state	0xb61	1 */
 	u8 gd_resampler_state;	/* Should always be 3		0xb62	1 */
 	u8 filler2;		/*				0xb63	1 */
-	u32 nominal_level_mask;	/* -10 level enable mask	0xb64	4 */
-	u16 input_clock;	/* Chg. Input clock state	0xb68	2 */
-	u16 output_clock;	/* Chg. Output clock state	0xb6a	2 */
-	u32 status_clocks;	/* Current Input clock state	0xb6c	4 */
-	u32 ext_box_status;	/* External box status		0xb70	4 */
-	u32 cmd_add_buffer;	/* Pipes to add (obsolete)	0xb74	4 */
-	u32 midi_out_free_count;
+	__le32 nominal_level_mask;	/* -10 level enable mask	0xb64	4 */
+	__le16 input_clock;	/* Chg. Input clock state	0xb68	2 */
+	__le16 output_clock;	/* Chg. Output clock state	0xb6a	2 */
+	__le32 status_clocks;	/* Current Input clock state	0xb6c	4 */
+	__le32 ext_box_status;	/* External box status		0xb70	4 */
+	__le32 cmd_add_buffer;	/* Pipes to add (obsolete)	0xb74	4 */
+	__le32 midi_out_free_count;
 			/* # of bytes free in MIDI output FIFO	0xb78	4 */
-	u32 unused2;		/* Cyclic pipes			0xb7c	4 */
-	u32 control_register;
+	__le32 unused2;		/* Cyclic pipes			0xb7c	4 */
+	__le32 control_register;
 			/* Mona, Gina24, Layla24, 3G ctrl reg	0xb80	4 */
-	u32 e3g_frq_register;	/* 3G frequency register	0xb84	4 */
+	__le32 e3g_frq_register;	/* 3G frequency register	0xb84	4 */
 	u8 filler[24];		/* filler			0xb88	24*1 */
 	s8 vmixer[VMIXER_ARRAY_SIZE];
 				/* Vmixer levels		0xba0	64*1 */
diff --git a/sound/pci/echoaudio/echoaudio_gml.c b/sound/pci/echoaudio/echoaudio_gml.c
index 834b39e97db7..eea6fe530ab4 100644
--- a/sound/pci/echoaudio/echoaudio_gml.c
+++ b/sound/pci/echoaudio/echoaudio_gml.c
@@ -63,6 +63,8 @@ the control register.  write_control_reg sends the new control register
 value to the DSP. */
 static int write_control_reg(struct echoaudio *chip, u32 value, char force)
 {
+	__le32 reg_value;
+
 	/* Handle the digital input auto-mute */
 	if (chip->digital_in_automute)
 		value |= GML_DIGITAL_IN_AUTO_MUTE;
@@ -72,11 +74,11 @@ static int write_control_reg(struct echoaudio *chip, u32 value, char force)
 	dev_dbg(chip->card->dev, "write_control_reg: 0x%x\n", value);
 
 	/* Write the control register */
-	value = cpu_to_le32(value);
-	if (value != chip->comm_page->control_register || force) {
+	reg_value = cpu_to_le32(value);
+	if (reg_value != chip->comm_page->control_register || force) {
 		if (wait_handshake(chip))
 			return -EIO;
-		chip->comm_page->control_register = value;
+		chip->comm_page->control_register = reg_value;
 		clear_handshake(chip);
 		return send_vector(chip, DSP_VC_WRITE_CONTROL_REG);
 	}
diff --git a/sound/pci/emu10k1/emu10k1_patch.c b/sound/pci/emu10k1/emu10k1_patch.c
index 0e069aeab86d..c32eb7053715 100644
--- a/sound/pci/emu10k1/emu10k1_patch.c
+++ b/sound/pci/emu10k1/emu10k1_patch.c
@@ -70,11 +70,8 @@ snd_emu10k1_sample_new(struct snd_emux *rec, struct snd_sf_sample *sp,
 		loopend = sampleend;
 
 	/* be sure loop points start < end */
-	if (sp->v.loopstart >= sp->v.loopend) {
-		int tmp = sp->v.loopstart;
-		sp->v.loopstart = sp->v.loopend;
-		sp->v.loopend = tmp;
-	}
+	if (sp->v.loopstart >= sp->v.loopend)
+		swap(sp->v.loopstart, sp->v.loopend);
 
 	/* compute true data size to be loaded */
 	truesize = sp->v.size + BLANK_HEAD_SIZE;
diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c
index de2ecbe95d6c..90713741c2dc 100644
--- a/sound/pci/emu10k1/emufx.c
+++ b/sound/pci/emu10k1/emufx.c
@@ -526,7 +526,7 @@ static int snd_emu10k1_gpr_poke(struct snd_emu10k1 *emu,
 		if (!test_bit(gpr, icode->gpr_valid))
 			continue;
 		if (in_kernel)
-			val = *(u32 *)&icode->gpr_map[gpr];
+			val = *(__force u32 *)&icode->gpr_map[gpr];
 		else if (get_user(val, &icode->gpr_map[gpr]))
 			return -EFAULT;
 		snd_emu10k1_ptr_write(emu, emu->gpr_base + gpr, 0, val);
@@ -560,8 +560,8 @@ static int snd_emu10k1_tram_poke(struct snd_emu10k1 *emu,
 		if (!test_bit(tram, icode->tram_valid))
 			continue;
 		if (in_kernel) {
-			val = *(u32 *)&icode->tram_data_map[tram];
-			addr = *(u32 *)&icode->tram_addr_map[tram];
+			val = *(__force u32 *)&icode->tram_data_map[tram];
+			addr = *(__force u32 *)&icode->tram_addr_map[tram];
 		} else {
 			if (get_user(val, &icode->tram_data_map[tram]) ||
 			    get_user(addr, &icode->tram_addr_map[tram]))
@@ -611,8 +611,8 @@ static int snd_emu10k1_code_poke(struct snd_emu10k1 *emu,
 		if (!test_bit(pc / 2, icode->code_valid))
 			continue;
 		if (in_kernel) {
-			lo = *(u32 *)&icode->code[pc + 0];
-			hi = *(u32 *)&icode->code[pc + 1];
+			lo = *(__force u32 *)&icode->code[pc + 0];
+			hi = *(__force u32 *)&icode->code[pc + 1];
 		} else {
 			if (get_user(lo, &icode->code[pc + 0]) ||
 			    get_user(hi, &icode->code[pc + 1]))
@@ -666,7 +666,7 @@ static unsigned int *copy_tlv(const unsigned int __user *_tlv, bool in_kernel)
 	if (!_tlv)
 		return NULL;
 	if (in_kernel)
-		memcpy(data, (void *)_tlv, sizeof(data));
+		memcpy(data, (__force void *)_tlv, sizeof(data));
 	else if (copy_from_user(data, _tlv, sizeof(data)))
 		return NULL;
 	if (data[1] >= MAX_TLV_SIZE)
@@ -676,7 +676,7 @@ static unsigned int *copy_tlv(const unsigned int __user *_tlv, bool in_kernel)
 		return NULL;
 	memcpy(tlv, data, sizeof(data));
 	if (in_kernel) {
-		memcpy(tlv + 2, (void *)(_tlv + 2),  data[1]);
+		memcpy(tlv + 2, (__force void *)(_tlv + 2),  data[1]);
 	} else if (copy_from_user(tlv + 2, _tlv + 2, data[1])) {
 		kfree(tlv);
 		return NULL;
@@ -693,7 +693,7 @@ static int copy_gctl(struct snd_emu10k1 *emu,
 
 	if (emu->support_tlv) {
 		if (in_kernel)
-			memcpy(gctl, (void *)&_gctl[idx], sizeof(*gctl));
+			memcpy(gctl, (__force void *)&_gctl[idx], sizeof(*gctl));
 		else if (copy_from_user(gctl, &_gctl[idx], sizeof(*gctl)))
 			return -EFAULT;
 		return 0;
@@ -701,7 +701,7 @@ static int copy_gctl(struct snd_emu10k1 *emu,
 
 	octl = (struct snd_emu10k1_fx8010_control_old_gpr __user *)_gctl;
 	if (in_kernel)
-		memcpy(gctl, (void *)&octl[idx], sizeof(*octl));
+		memcpy(gctl, (__force void *)&octl[idx], sizeof(*octl));
 	else if (copy_from_user(gctl, &octl[idx], sizeof(*octl)))
 		return -EFAULT;
 	gctl->tlv = NULL;
@@ -735,7 +735,7 @@ static int snd_emu10k1_verify_controls(struct snd_emu10k1 *emu,
 	for (i = 0, _id = icode->gpr_del_controls;
 	     i < icode->gpr_del_control_count; i++, _id++) {
 		if (in_kernel)
-			id = *(struct snd_ctl_elem_id *)_id;
+			id = *(__force struct snd_ctl_elem_id *)_id;
 		else if (copy_from_user(&id, _id, sizeof(id)))
 	     		return -EFAULT;
 		if (snd_emu10k1_look_for_ctl(emu, &id) == NULL)
@@ -833,7 +833,7 @@ static int snd_emu10k1_add_controls(struct snd_emu10k1 *emu,
 		knew.device = gctl->id.device;
 		knew.subdevice = gctl->id.subdevice;
 		knew.info = snd_emu10k1_gpr_ctl_info;
-		knew.tlv.p = copy_tlv(gctl->tlv, in_kernel);
+		knew.tlv.p = copy_tlv((__force const unsigned int __user *)gctl->tlv, in_kernel);
 		if (knew.tlv.p)
 			knew.access = SNDRV_CTL_ELEM_ACCESS_READWRITE |
 				SNDRV_CTL_ELEM_ACCESS_TLV_READ;
@@ -897,7 +897,7 @@ static int snd_emu10k1_del_controls(struct snd_emu10k1 *emu,
 	for (i = 0, _id = icode->gpr_del_controls;
 	     i < icode->gpr_del_control_count; i++, _id++) {
 		if (in_kernel)
-			id = *(struct snd_ctl_elem_id *)_id;
+			id = *(__force struct snd_ctl_elem_id *)_id;
 		else if (copy_from_user(&id, _id, sizeof(id)))
 			return -EFAULT;
 		down_write(&card->controls_rwsem);
diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c
index 69f9b100bd24..9f2b6097f486 100644
--- a/sound/pci/emu10k1/emupcm.c
+++ b/sound/pci/emu10k1/emupcm.c
@@ -290,7 +290,7 @@ static void snd_emu10k1_pcm_init_voice(struct snd_emu10k1 *emu,
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	unsigned int silent_page, tmp;
 	int voice, stereo, w_16;
-	unsigned char attn, send_amount[8];
+	unsigned char send_amount[8];
 	unsigned char send_routing[8];
 	unsigned long flags;
 	unsigned int pitch_target;
@@ -313,7 +313,6 @@ static void snd_emu10k1_pcm_init_voice(struct snd_emu10k1 *emu,
 
 	/* volume parameters */
 	if (extra) {
-		attn = 0;
 		memset(send_routing, 0, sizeof(send_routing));
 		send_routing[0] = 0;
 		send_routing[1] = 1;
@@ -779,7 +778,7 @@ static int snd_emu10k1_playback_trigger(struct snd_pcm_substream *substream,
 	case SNDRV_PCM_TRIGGER_START:
 		snd_emu10k1_playback_invalidate_cache(emu, 1, epcm->extra);	/* do we need this? */
 		snd_emu10k1_playback_invalidate_cache(emu, 0, epcm->voices[0]);
-		/* follow thru */
+		/* fall through */
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 	case SNDRV_PCM_TRIGGER_RESUME:
 		if (cmd == SNDRV_PCM_TRIGGER_PAUSE_RELEASE)
@@ -929,7 +928,7 @@ static int snd_emu10k1_efx_playback_trigger(struct snd_pcm_substream *substream,
 		}
 		snd_emu10k1_playback_invalidate_cache(emu, 1, epcm->extra);
 
-		/* follow thru */
+		/* fall through */
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 	case SNDRV_PCM_TRIGGER_RESUME:
 		snd_emu10k1_playback_prepare_voice(emu, epcm->extra, 1, 1, NULL);
diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c
index 39f79a6b5283..727eb3da1fda 100644
--- a/sound/pci/ens1370.c
+++ b/sound/pci/ens1370.c
@@ -2392,7 +2392,7 @@ static int snd_audiopci_probe(struct pci_dev *pci,
 	static int dev;
 	struct snd_card *card;
 	struct ensoniq *ensoniq;
-	int err, pcm_devs[2];
+	int err;
 
 	if (dev >= SNDRV_CARDS)
 		return -ENODEV;
@@ -2412,7 +2412,6 @@ static int snd_audiopci_probe(struct pci_dev *pci,
 	}
 	card->private_data = ensoniq;
 
-	pcm_devs[0] = 0; pcm_devs[1] = 1;
 #ifdef CHIP1370
 	if ((err = snd_ensoniq_1370_mixer(ensoniq)) < 0) {
 		snd_card_free(card);
diff --git a/sound/pci/hda/dell_wmi_helper.c b/sound/pci/hda/dell_wmi_helper.c
index 1b48a8c19d28..8a7dbd1a7fbf 100644
--- a/sound/pci/hda/dell_wmi_helper.c
+++ b/sound/pci/hda/dell_wmi_helper.c
@@ -6,111 +6,18 @@
 #if IS_ENABLED(CONFIG_DELL_LAPTOP)
 #include <linux/dell-led.h>
 
-enum {
-	MICMUTE_LED_ON,
-	MICMUTE_LED_OFF,
-	MICMUTE_LED_FOLLOW_CAPTURE,
-	MICMUTE_LED_FOLLOW_MUTE,
-};
-
-static int dell_led_mode = MICMUTE_LED_FOLLOW_MUTE;
-static int dell_capture;
-static int dell_led_value;
 static int (*dell_micmute_led_set_func)(int);
-static void (*dell_old_cap_hook)(struct hda_codec *,
-			         struct snd_kcontrol *,
-				 struct snd_ctl_elem_value *);
-
-static void call_micmute_led_update(void)
-{
-	int val;
-
-	switch (dell_led_mode) {
-	case MICMUTE_LED_ON:
-		val = 1;
-		break;
-	case MICMUTE_LED_OFF:
-		val = 0;
-		break;
-	case MICMUTE_LED_FOLLOW_CAPTURE:
-		val = dell_capture;
-		break;
-	case MICMUTE_LED_FOLLOW_MUTE:
-	default:
-		val = !dell_capture;
-		break;
-	}
-
-	if (val == dell_led_value)
-		return;
-	dell_led_value = val;
-	dell_micmute_led_set_func(dell_led_value);
-}
-
-static void update_dell_wmi_micmute_led(struct hda_codec *codec,
-				        struct snd_kcontrol *kcontrol,
-					struct snd_ctl_elem_value *ucontrol)
-{
-	if (dell_old_cap_hook)
-		dell_old_cap_hook(codec, kcontrol, ucontrol);
-
-	if (!ucontrol || !dell_micmute_led_set_func)
-		return;
-	if (strcmp("Capture Switch", ucontrol->id.name) == 0 && ucontrol->id.index == 0) {
-		/* TODO: How do I verify if it's a mono or stereo here? */
-		dell_capture = (ucontrol->value.integer.value[0] ||
-				ucontrol->value.integer.value[1]);
-		call_micmute_led_update();
-	}
-}
 
-static int dell_mic_mute_led_mode_info(struct snd_kcontrol *kcontrol,
-				       struct snd_ctl_elem_info *uinfo)
+static void dell_micmute_update(struct hda_codec *codec)
 {
-	static const char * const texts[] = {
-		"On", "Off", "Follow Capture", "Follow Mute",
-	};
-
-	return snd_ctl_enum_info(uinfo, 1, ARRAY_SIZE(texts), texts);
-}
+	struct hda_gen_spec *spec = codec->spec;
 
-static int dell_mic_mute_led_mode_get(struct snd_kcontrol *kcontrol,
-				      struct snd_ctl_elem_value *ucontrol)
-{
-	ucontrol->value.enumerated.item[0] = dell_led_mode;
-	return 0;
+	dell_micmute_led_set_func(spec->micmute_led.led_value);
 }
 
-static int dell_mic_mute_led_mode_put(struct snd_kcontrol *kcontrol,
-				      struct snd_ctl_elem_value *ucontrol)
-{
-	unsigned int mode;
-
-	mode = ucontrol->value.enumerated.item[0];
-	if (mode > MICMUTE_LED_FOLLOW_MUTE)
-		mode = MICMUTE_LED_FOLLOW_MUTE;
-	if (mode == dell_led_mode)
-		return 0;
-	dell_led_mode = mode;
-	call_micmute_led_update();
-	return 1;
-}
-
-static const struct snd_kcontrol_new dell_mic_mute_mode_ctls[] = {
-	{
-		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
-		.name = "Mic Mute-LED Mode",
-		.info = dell_mic_mute_led_mode_info,
-		.get = dell_mic_mute_led_mode_get,
-		.put = dell_mic_mute_led_mode_put,
-	},
-	{}
-};
-
 static void alc_fixup_dell_wmi(struct hda_codec *codec,
 			       const struct hda_fixup *fix, int action)
 {
-	struct alc_spec *spec = codec->spec;
 	bool removefunc = false;
 
 	if (action == HDA_FIXUP_ACT_PROBE) {
@@ -121,25 +28,14 @@ static void alc_fixup_dell_wmi(struct hda_codec *codec,
 			return;
 		}
 
-		removefunc = true;
-		if (dell_micmute_led_set_func(false) >= 0) {
-			dell_led_value = 0;
-			if (spec->gen.num_adc_nids > 1 && !spec->gen.dyn_adc_switch)
-				codec_dbg(codec, "Skipping micmute LED control due to several ADCs");
-			else {
-				dell_old_cap_hook = spec->gen.cap_sync_hook;
-				spec->gen.cap_sync_hook = update_dell_wmi_micmute_led;
-				removefunc = false;
-				add_mixer(spec, dell_mic_mute_mode_ctls);
-			}
-		}
-
+		removefunc = (dell_micmute_led_set_func(false) < 0) ||
+			(snd_hda_gen_add_micmute_led(codec,
+						     dell_micmute_update) <= 0);
 	}
 
 	if (dell_micmute_led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) {
 		symbol_put(dell_micmute_led_set);
 		dell_micmute_led_set_func = NULL;
-		dell_old_cap_hook = NULL;
 	}
 }
 
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index d91c87e41756..0a5085537034 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -37,15 +37,8 @@
 #include "hda_jack.h"
 #include <sound/hda_hwdep.h>
 
-#ifdef CONFIG_PM
-#define codec_in_pm(codec)	atomic_read(&(codec)->core.in_pm)
-#define hda_codec_is_power_on(codec) \
-	(!pm_runtime_suspended(hda_codec_dev(codec)))
-#else
-#define codec_in_pm(codec)	0
-#define hda_codec_is_power_on(codec)	1
-#endif
-
+#define codec_in_pm(codec)		snd_hdac_is_in_pm(&codec->core)
+#define hda_codec_is_power_on(codec)	snd_hdac_is_power_on(&codec->core)
 #define codec_has_epss(codec) \
 	((codec)->core.power_caps & AC_PWRST_EPSS)
 #define codec_has_clkstop(codec) \
@@ -858,6 +851,39 @@ static void snd_hda_codec_dev_release(struct device *dev)
 	kfree(codec);
 }
 
+#define DEV_NAME_LEN 31
+
+static int snd_hda_codec_device_init(struct hda_bus *bus, struct snd_card *card,
+			unsigned int codec_addr, struct hda_codec **codecp)
+{
+	char name[DEV_NAME_LEN];
+	struct hda_codec *codec;
+	int err;
+
+	dev_dbg(card->dev, "%s: entry\n", __func__);
+
+	if (snd_BUG_ON(!bus))
+		return -EINVAL;
+	if (snd_BUG_ON(codec_addr > HDA_MAX_CODEC_ADDRESS))
+		return -EINVAL;
+
+	codec = kzalloc(sizeof(*codec), GFP_KERNEL);
+	if (!codec)
+		return -ENOMEM;
+
+	sprintf(name, "hdaudioC%dD%d", card->number, codec_addr);
+	err = snd_hdac_device_init(&codec->core, &bus->core, name, codec_addr);
+	if (err < 0) {
+		kfree(codec);
+		return err;
+	}
+
+	codec->core.type = HDA_DEV_LEGACY;
+	*codecp = codec;
+
+	return err;
+}
+
 /**
  * snd_hda_codec_new - create a HDA codec
  * @bus: the bus to assign
@@ -869,7 +895,19 @@ static void snd_hda_codec_dev_release(struct device *dev)
 int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card,
 		      unsigned int codec_addr, struct hda_codec **codecp)
 {
-	struct hda_codec *codec;
+	int ret;
+
+	ret = snd_hda_codec_device_init(bus, card, codec_addr, codecp);
+	if (ret < 0)
+		return ret;
+
+	return snd_hda_codec_device_new(bus, card, codec_addr, *codecp);
+}
+EXPORT_SYMBOL_GPL(snd_hda_codec_new);
+
+int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card,
+			unsigned int codec_addr, struct hda_codec *codec)
+{
 	char component[31];
 	hda_nid_t fg;
 	int err;
@@ -879,25 +917,14 @@ int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card,
 		.dev_free = snd_hda_codec_dev_free,
 	};
 
+	dev_dbg(card->dev, "%s: entry\n", __func__);
+
 	if (snd_BUG_ON(!bus))
 		return -EINVAL;
 	if (snd_BUG_ON(codec_addr > HDA_MAX_CODEC_ADDRESS))
 		return -EINVAL;
 
-	codec = kzalloc(sizeof(*codec), GFP_KERNEL);
-	if (!codec)
-		return -ENOMEM;
-
-	sprintf(component, "hdaudioC%dD%d", card->number, codec_addr);
-	err = snd_hdac_device_init(&codec->core, &bus->core, component,
-				   codec_addr);
-	if (err < 0) {
-		kfree(codec);
-		return err;
-	}
-
 	codec->core.dev.release = snd_hda_codec_dev_release;
-	codec->core.type = HDA_DEV_LEGACY;
 	codec->core.exec_verb = codec_exec_verb;
 
 	codec->bus = bus;
@@ -957,15 +984,13 @@ int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card,
 	if (err < 0)
 		goto error;
 
-	if (codecp)
-		*codecp = codec;
 	return 0;
 
  error:
 	put_device(hda_codec_dev(codec));
 	return err;
 }
-EXPORT_SYMBOL_GPL(snd_hda_codec_new);
+EXPORT_SYMBOL_GPL(snd_hda_codec_device_new);
 
 /**
  * snd_hda_codec_update_widgets - Refresh widget caps and pin defaults
@@ -2846,14 +2871,13 @@ static unsigned int hda_call_codec_suspend(struct hda_codec *codec)
 {
 	unsigned int state;
 
-	atomic_inc(&codec->core.in_pm);
-
+	snd_hdac_enter_pm(&codec->core);
 	if (codec->patch_ops.suspend)
 		codec->patch_ops.suspend(codec);
 	hda_cleanup_all_streams(codec);
 	state = hda_set_power_state(codec, AC_PWRST_D3);
 	update_power_acct(codec, true);
-	atomic_dec(&codec->core.in_pm);
+	snd_hdac_leave_pm(&codec->core);
 	return state;
 }
 
@@ -2862,8 +2886,7 @@ static unsigned int hda_call_codec_suspend(struct hda_codec *codec)
  */
 static void hda_call_codec_resume(struct hda_codec *codec)
 {
-	atomic_inc(&codec->core.in_pm);
-
+	snd_hdac_enter_pm(&codec->core);
 	if (codec->core.regmap)
 		regcache_mark_dirty(codec->core.regmap);
 
@@ -2886,7 +2909,7 @@ static void hda_call_codec_resume(struct hda_codec *codec)
 		hda_jackpoll_work(&codec->jackpoll_work.work);
 	else
 		snd_hda_jack_report_sync(codec);
-	atomic_dec(&codec->core.in_pm);
+	snd_hdac_leave_pm(&codec->core);
 }
 
 static int hda_codec_runtime_suspend(struct device *dev)
@@ -2899,8 +2922,9 @@ static int hda_codec_runtime_suspend(struct device *dev)
 	list_for_each_entry(pcm, &codec->pcm_list_head, list)
 		snd_pcm_suspend_all(pcm->pcm);
 	state = hda_call_codec_suspend(codec);
-	if (codec_has_clkstop(codec) && codec_has_epss(codec) &&
-	    (state & AC_PWRST_CLK_STOP_OK))
+	if (codec->link_down_at_suspend ||
+	    (codec_has_clkstop(codec) && codec_has_epss(codec) &&
+	     (state & AC_PWRST_CLK_STOP_OK)))
 		snd_hdac_codec_link_down(&codec->core);
 	snd_hdac_link_power(&codec->core, false);
 	return 0;
@@ -2991,6 +3015,7 @@ int snd_hda_codec_build_controls(struct hda_codec *codec)
 	sync_power_up_states(codec);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(snd_hda_codec_build_controls);
 
 /*
  * PCM stuff
@@ -3196,6 +3221,7 @@ int snd_hda_codec_parse_pcms(struct hda_codec *codec)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(snd_hda_codec_parse_pcms);
 
 /* assign all PCMs of the given codec */
 int snd_hda_codec_build_pcms(struct hda_codec *codec)
@@ -3251,8 +3277,8 @@ int snd_hda_add_new_ctls(struct hda_codec *codec,
 	for (; knew->name; knew++) {
 		struct snd_kcontrol *kctl;
 		int addr = 0, idx = 0;
-		if (knew->iface == -1)	/* skip this codec private value */
-			continue;
+		if (knew->iface == (__force snd_ctl_elem_iface_t)-1)
+			continue; /* skip this codec private value */
 		for (;;) {
 			kctl = snd_ctl_new1(knew, codec);
 			if (!kctl)
@@ -3842,7 +3868,7 @@ EXPORT_SYMBOL_GPL(snd_hda_correct_pin_ctl);
  * This function is a helper to set a pin ctl value more safely.
  * It corrects the pin ctl value via snd_hda_correct_pin_ctl(), stores the
  * value in pin target array via snd_hda_codec_set_pin_target(), then
- * actually writes the value via either snd_hda_codec_update_cache() or
+ * actually writes the value via either snd_hda_codec_write_cache() or
  * snd_hda_codec_write() depending on @cached flag.
  */
 int _snd_hda_set_pin_ctl(struct hda_codec *codec, hda_nid_t pin,
@@ -3851,7 +3877,7 @@ int _snd_hda_set_pin_ctl(struct hda_codec *codec, hda_nid_t pin,
 	val = snd_hda_correct_pin_ctl(codec, pin, val);
 	snd_hda_codec_set_pin_target(codec, pin, val);
 	if (cached)
-		return snd_hda_codec_update_cache(codec, pin, 0,
+		return snd_hda_codec_write_cache(codec, pin, 0,
 				AC_VERB_SET_PIN_WIDGET_CONTROL, val);
 	else
 		return snd_hda_codec_write(codec, pin, 0,
diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h
index 681c360f29f9..0d98bb9068b1 100644
--- a/sound/pci/hda/hda_codec.h
+++ b/sound/pci/hda/hda_codec.h
@@ -84,6 +84,7 @@ struct hda_bus {
  */
 typedef int (*hda_codec_patch_t)(struct hda_codec *);
 	
+#define HDA_CODEC_ID_SKIP_PROBE		0x00000001
 #define HDA_CODEC_ID_GENERIC_HDMI	0x00000101
 #define HDA_CODEC_ID_GENERIC		0x00000201
 
@@ -258,6 +259,7 @@ struct hda_codec {
 	unsigned int power_save_node:1; /* advanced PM for each widget */
 	unsigned int auto_runtime_pm:1; /* enable automatic codec runtime pm */
 	unsigned int force_pin_prefix:1; /* Add location prefix */
+	unsigned int link_down_at_suspend:1; /* link down at runtime suspend */
 #ifdef CONFIG_PM
 	unsigned long power_on_acct;
 	unsigned long power_off_acct;
@@ -307,6 +309,8 @@ struct hda_codec {
  */
 int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card,
 		      unsigned int codec_addr, struct hda_codec **codecp);
+int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card,
+		      unsigned int codec_addr, struct hda_codec *codec);
 int snd_hda_codec_configure(struct hda_codec *codec);
 int snd_hda_codec_update_widgets(struct hda_codec *codec);
 
@@ -381,9 +385,6 @@ snd_hda_codec_write_cache(struct hda_codec *codec, hda_nid_t nid,
 	return snd_hdac_regmap_write(&codec->core, nid, verb, parm);
 }
 
-#define snd_hda_codec_update_cache(codec, nid, flags, verb, parm) \
-	snd_hda_codec_write_cache(codec, nid, flags, verb, parm)
-
 /* the struct for codec->pin_configs */
 struct hda_pincfg {
 	hda_nid_t nid;
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index db773e219aaa..579984ecdec3 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -209,7 +209,7 @@ static void parse_user_hints(struct hda_codec *codec)
  */
 
 #define update_pin_ctl(codec, pin, val) \
-	snd_hda_codec_update_cache(codec, pin, 0, \
+	snd_hda_codec_write_cache(codec, pin, 0, \
 				   AC_VERB_SET_PIN_WIDGET_CONTROL, val)
 
 /* restore the pinctl based on the cached value */
@@ -898,7 +898,7 @@ void snd_hda_activate_path(struct hda_codec *codec, struct nid_path *path,
 		hda_nid_t nid = path->path[i];
 
 		if (enable && path->multi[i])
-			snd_hda_codec_update_cache(codec, nid, 0,
+			snd_hda_codec_write_cache(codec, nid, 0,
 					    AC_VERB_SET_CONNECT_SEL,
 					    path->idx[i]);
 		if (has_amp_in(codec, path, i))
@@ -930,7 +930,7 @@ static void set_pin_eapd(struct hda_codec *codec, hda_nid_t pin, bool enable)
 		return;
 	if (codec->inv_eapd)
 		enable = !enable;
-	snd_hda_codec_update_cache(codec, pin, 0,
+	snd_hda_codec_write_cache(codec, pin, 0,
 				   AC_VERB_SET_EAPD_BTLENABLE,
 				   enable ? 0x02 : 0x00);
 }
@@ -3900,6 +3900,142 @@ static int parse_mic_boost(struct hda_codec *codec)
 }
 
 /*
+ * mic mute LED hook helpers
+ */
+enum {
+	MICMUTE_LED_ON,
+	MICMUTE_LED_OFF,
+	MICMUTE_LED_FOLLOW_CAPTURE,
+	MICMUTE_LED_FOLLOW_MUTE,
+};
+
+static void call_micmute_led_update(struct hda_codec *codec)
+{
+	struct hda_gen_spec *spec = codec->spec;
+	unsigned int val;
+
+	switch (spec->micmute_led.led_mode) {
+	case MICMUTE_LED_ON:
+		val = 1;
+		break;
+	case MICMUTE_LED_OFF:
+		val = 0;
+		break;
+	case MICMUTE_LED_FOLLOW_CAPTURE:
+		val = !!spec->micmute_led.capture;
+		break;
+	case MICMUTE_LED_FOLLOW_MUTE:
+	default:
+		val = !spec->micmute_led.capture;
+		break;
+	}
+
+	if (val == spec->micmute_led.led_value)
+		return;
+	spec->micmute_led.led_value = val;
+	if (spec->micmute_led.update)
+		spec->micmute_led.update(codec);
+}
+
+static void update_micmute_led(struct hda_codec *codec,
+			       struct snd_kcontrol *kcontrol,
+			       struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_gen_spec *spec = codec->spec;
+	unsigned int mask;
+
+	if (spec->micmute_led.old_hook)
+		spec->micmute_led.old_hook(codec, kcontrol, ucontrol);
+
+	if (!ucontrol)
+		return;
+	mask = 1U << snd_ctl_get_ioffidx(kcontrol, &ucontrol->id);
+	if (!strcmp("Capture Switch", ucontrol->id.name)) {
+		/* TODO: How do I verify if it's a mono or stereo here? */
+		if (ucontrol->value.integer.value[0] ||
+		    ucontrol->value.integer.value[1])
+			spec->micmute_led.capture |= mask;
+		else
+			spec->micmute_led.capture &= ~mask;
+		call_micmute_led_update(codec);
+	}
+}
+
+static int micmute_led_mode_info(struct snd_kcontrol *kcontrol,
+				 struct snd_ctl_elem_info *uinfo)
+{
+	static const char * const texts[] = {
+		"On", "Off", "Follow Capture", "Follow Mute",
+	};
+
+	return snd_ctl_enum_info(uinfo, 1, ARRAY_SIZE(texts), texts);
+}
+
+static int micmute_led_mode_get(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct hda_gen_spec *spec = codec->spec;
+
+	ucontrol->value.enumerated.item[0] = spec->micmute_led.led_mode;
+	return 0;
+}
+
+static int micmute_led_mode_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct hda_gen_spec *spec = codec->spec;
+	unsigned int mode;
+
+	mode = ucontrol->value.enumerated.item[0];
+	if (mode > MICMUTE_LED_FOLLOW_MUTE)
+		mode = MICMUTE_LED_FOLLOW_MUTE;
+	if (mode == spec->micmute_led.led_mode)
+		return 0;
+	spec->micmute_led.led_mode = mode;
+	call_micmute_led_update(codec);
+	return 1;
+}
+
+static const struct snd_kcontrol_new micmute_led_mode_ctl = {
+	.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+	.name = "Mic Mute-LED Mode",
+	.info = micmute_led_mode_info,
+	.get = micmute_led_mode_get,
+	.put = micmute_led_mode_put,
+};
+
+/**
+ * snd_hda_gen_add_micmute_led - helper for setting up mic mute LED hook
+ * @codec: the HDA codec
+ * @hook: the callback for updating LED
+ *
+ * Called from the codec drivers for offering the mic mute LED controls.
+ * When established, it sets up cap_sync_hook and triggers the callback at
+ * each time when the capture mixer switch changes.  The callback is supposed
+ * to update the LED accordingly.
+ *
+ * Returns 0 if the hook is established or a negative error code.
+ */
+int snd_hda_gen_add_micmute_led(struct hda_codec *codec,
+				void (*hook)(struct hda_codec *))
+{
+	struct hda_gen_spec *spec = codec->spec;
+
+	spec->micmute_led.led_mode = MICMUTE_LED_FOLLOW_MUTE;
+	spec->micmute_led.capture = 0;
+	spec->micmute_led.led_value = 0;
+	spec->micmute_led.old_hook = spec->cap_sync_hook;
+	spec->micmute_led.update = hook;
+	spec->cap_sync_hook = update_micmute_led;
+	if (!snd_hda_gen_add_kctl(spec, NULL, &micmute_led_mode_ctl))
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_hda_gen_add_micmute_led);
+
+/*
  * parse digital I/Os and set up NIDs in BIOS auto-parse mode
  */
 static void parse_digital(struct hda_codec *codec)
@@ -5837,7 +5973,7 @@ static void clear_unsol_on_unused_pins(struct hda_codec *codec)
 		hda_nid_t nid = pin->nid;
 		if (is_jack_detectable(codec, nid) &&
 		    !snd_hda_jack_tbl_get(codec, nid))
-			snd_hda_codec_update_cache(codec, nid, 0,
+			snd_hda_codec_write_cache(codec, nid, 0,
 					AC_VERB_SET_UNSOLICITED_ENABLE, 0);
 	}
 }
diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h
index 61772317de46..10123664fa61 100644
--- a/sound/pci/hda/hda_generic.h
+++ b/sound/pci/hda/hda_generic.h
@@ -86,6 +86,16 @@ struct badness_table {
 extern const struct badness_table hda_main_out_badness;
 extern const struct badness_table hda_extra_out_badness;
 
+struct hda_micmute_hook {
+	unsigned int led_mode;
+	unsigned int capture;
+	unsigned int led_value;
+	void (*update)(struct hda_codec *codec);
+	void (*old_hook)(struct hda_codec *codec,
+			 struct snd_kcontrol *kcontrol,
+			 struct snd_ctl_elem_value *ucontrol);
+};
+
 struct hda_gen_spec {
 	char stream_name_analog[32];	/* analog PCM stream */
 	const struct hda_pcm_stream *stream_analog_playback;
@@ -276,6 +286,9 @@ struct hda_gen_spec {
 			      struct snd_kcontrol *kcontrol,
 			      struct snd_ctl_elem_value *ucontrol);
 
+	/* mic mute LED hook; called via cap_sync_hook */
+	struct hda_micmute_hook micmute_led;
+
 	/* PCM hooks */
 	void (*pcm_playback_hook)(struct hda_pcm_stream *hinfo,
 				  struct hda_codec *codec,
@@ -342,4 +355,7 @@ unsigned int snd_hda_gen_path_power_filter(struct hda_codec *codec,
 void snd_hda_gen_stream_pm(struct hda_codec *codec, hda_nid_t nid, bool on);
 int snd_hda_gen_fix_pin_power(struct hda_codec *codec, hda_nid_t pin);
 
+int snd_hda_gen_add_micmute_led(struct hda_codec *codec,
+				void (*hook)(struct hda_codec *));
+
 #endif /* __SOUND_HDA_GENERIC_H */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 1ae1850b3bfd..1b2ce304152a 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1319,15 +1319,16 @@ static const struct vga_switcheroo_client_ops azx_vs_ops = {
 static int register_vga_switcheroo(struct azx *chip)
 {
 	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
+	struct pci_dev *p;
 	int err;
 
 	if (!hda->use_vga_switcheroo)
 		return 0;
-	/* FIXME: currently only handling DIS controller
-	 * is there any machine with two switchable HDMI audio controllers?
-	 */
-	err = vga_switcheroo_register_audio_client(chip->pci, &azx_vs_ops,
-						   VGA_SWITCHEROO_DIS);
+
+	p = get_bound_vga(chip->pci);
+	err = vga_switcheroo_register_audio_client(chip->pci, &azx_vs_ops, p);
+	pci_dev_put(p);
+
 	if (err < 0)
 		return err;
 	hda->vga_switcheroo_registered = 1;
@@ -1429,7 +1430,7 @@ static struct pci_dev *get_bound_vga(struct pci_dev *pci)
 			p = pci_get_domain_bus_and_slot(pci_domain_nr(pci->bus),
 							pci->bus->number, 0);
 			if (p) {
-				if ((p->class >> 8) == PCI_CLASS_DISPLAY_VGA)
+				if ((p->class >> 16) == PCI_BASE_CLASS_DISPLAY)
 					return p;
 				pci_dev_put(p);
 			}
@@ -2207,7 +2208,7 @@ out_free:
  */
 static struct snd_pci_quirk power_save_blacklist[] = {
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
-	SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0),
+	SND_PCI_QUIRK(0x1849, 0xc892, "Asrock B85M-ITX", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	SND_PCI_QUIRK(0x1849, 0x7662, "Asrock H81M-HDS", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
@@ -2535,7 +2536,8 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
 	/* AMD Raven */
 	{ PCI_DEVICE(0x1022, 0x15e3),
-	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
+	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB |
+			 AZX_DCAPS_PM_RUNTIME },
 	/* ATI HDMI */
 	{ PCI_DEVICE(0x1002, 0x0002),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index 757857313426..fd476fb40e1b 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -148,7 +148,7 @@ static void ad_vmaster_eapd_hook(void *private_data, int enabled)
 		return;
 	if (codec->inv_eapd)
 		enabled = !enabled;
-	snd_hda_codec_update_cache(codec, spec->eapd_nid, 0,
+	snd_hda_codec_write_cache(codec, spec->eapd_nid, 0,
 				   AC_VERB_SET_EAPD_BTLENABLE,
 				   enabled ? 0x02 : 0x00);
 }
@@ -991,7 +991,7 @@ static void ad1884_vmaster_hp_gpio_hook(void *private_data, int enabled)
 
 	if (spec->eapd_nid)
 		ad_vmaster_eapd_hook(private_data, enabled);
-	snd_hda_codec_update_cache(codec, 0x01, 0,
+	snd_hda_codec_write_cache(codec, 0x01, 0,
 				   AC_VERB_SET_GPIO_DATA,
 				   enabled ? 0x00 : 0x02);
 }
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 04e949aa01ad..0166a3d7cd55 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -897,7 +897,7 @@ struct ca0132_spec {
 	const struct hda_verb *base_init_verbs;
 	const struct hda_verb *base_exit_verbs;
 	const struct hda_verb *chip_init_verbs;
-	const struct hda_verb *sbz_init_verbs;
+	const struct hda_verb *desktop_init_verbs;
 	struct hda_verb *spec_init_verbs;
 	struct auto_pin_cfg autocfg;
 
@@ -965,9 +965,11 @@ struct ca0132_spec {
 	long cur_ctl_vals[TUNING_CTLS_COUNT];
 #endif
 	/*
-	 * Sound Blaster Z PCI region 2 iomem, used for input and output
-	 * switching, and other unknown commands.
+	 * The Recon3D, Sound Blaster Z, Sound Blaster ZxR, and Sound Blaster
+	 * AE-5 all use PCI region 2 to toggle GPIO and other currently unknown
+	 * things.
 	 */
+	bool use_pci_mmio;
 	void __iomem *mem_base;
 
 	/*
@@ -991,8 +993,10 @@ struct ca0132_spec {
 enum {
 	QUIRK_NONE,
 	QUIRK_ALIENWARE,
+	QUIRK_ALIENWARE_M17XR4,
 	QUIRK_SBZ,
 	QUIRK_R3DI,
+	QUIRK_R3D,
 };
 
 static const struct hda_pintbl alienware_pincfgs[] = {
@@ -1024,6 +1028,21 @@ static const struct hda_pintbl sbz_pincfgs[] = {
 	{}
 };
 
+/* Recon3D pin configs taken from Windows Driver */
+static const struct hda_pintbl r3d_pincfgs[] = {
+	{ 0x0b, 0x01014110 }, /* Port G -- Lineout FRONT L/R */
+	{ 0x0c, 0x014510f0 }, /* SPDIF Out 1 */
+	{ 0x0d, 0x014510f0 }, /* Digital Out */
+	{ 0x0e, 0x01c520f0 }, /* SPDIF In */
+	{ 0x0f, 0x0221401f }, /* Port A -- BackPanel HP */
+	{ 0x10, 0x01016011 }, /* Port D -- Center/LFE or FP Hp */
+	{ 0x11, 0x01011014 }, /* Port B -- LineMicIn2 / Rear L/R */
+	{ 0x12, 0x02a090f0 }, /* Port C -- LineIn1 */
+	{ 0x13, 0x908700f0 }, /* What U Hear In*/
+	{ 0x18, 0x50d000f0 }, /* N/A */
+	{}
+};
+
 /* Recon3D integrated pin configs taken from Windows Driver */
 static const struct hda_pintbl r3di_pincfgs[] = {
 	{ 0x0b, 0x01014110 }, /* Port G -- Lineout FRONT L/R */
@@ -1040,13 +1059,16 @@ static const struct hda_pintbl r3di_pincfgs[] = {
 };
 
 static const struct snd_pci_quirk ca0132_quirks[] = {
+	SND_PCI_QUIRK(0x1028, 0x057b, "Alienware M17x R4", QUIRK_ALIENWARE_M17XR4),
 	SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15 2015", QUIRK_ALIENWARE),
 	SND_PCI_QUIRK(0x1028, 0x0688, "Alienware 17 2015", QUIRK_ALIENWARE),
 	SND_PCI_QUIRK(0x1028, 0x0708, "Alienware 15 R2 2016", QUIRK_ALIENWARE),
 	SND_PCI_QUIRK(0x1102, 0x0010, "Sound Blaster Z", QUIRK_SBZ),
 	SND_PCI_QUIRK(0x1102, 0x0023, "Sound Blaster Z", QUIRK_SBZ),
 	SND_PCI_QUIRK(0x1458, 0xA016, "Recon3Di", QUIRK_R3DI),
-	SND_PCI_QUIRK(0x1458, 0xA036, "Recon3Di", QUIRK_R3DI),
+	SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI),
+	SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI),
+	SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D),
 	{}
 };
 
@@ -3070,6 +3092,24 @@ static bool dspload_wait_loaded(struct hda_codec *codec)
  */
 
 /*
+ * For cards with PCI-E region2 (Sound Blaster Z/ZxR, Recon3D, and AE-5)
+ * the mmio address 0x320 is used to set GPIO pins. The format for the data
+ * The first eight bits are just the number of the pin. So far, I've only seen
+ * this number go to 7.
+ */
+static void ca0132_mmio_gpio_set(struct hda_codec *codec, unsigned int gpio_pin,
+		bool enable)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned short gpio_data;
+
+	gpio_data = gpio_pin & 0xF;
+	gpio_data |= ((enable << 8) & 0x100);
+
+	writew(gpio_data, spec->mem_base + 0x320);
+}
+
+/*
  * Sets up the GPIO pins so that they are discoverable. If this isn't done,
  * the card shows as having no GPIO pins.
  */
@@ -3944,15 +3984,19 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 		/*speaker out config*/
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0007, spec->mem_base + 0x320);
-			writew(0x0104, spec->mem_base + 0x320);
-			writew(0x0101, spec->mem_base + 0x320);
+			ca0132_mmio_gpio_set(codec, 7, false);
+			ca0132_mmio_gpio_set(codec, 4, true);
+			ca0132_mmio_gpio_set(codec, 1, true);
 			chipio_set_control_param(codec, 0x0D, 0x18);
 			break;
 		case QUIRK_R3DI:
 			chipio_set_control_param(codec, 0x0D, 0x24);
 			r3di_gpio_out_set(codec, R3DI_LINE_OUT);
 			break;
+		case QUIRK_R3D:
+			chipio_set_control_param(codec, 0x0D, 0x24);
+			ca0132_mmio_gpio_set(codec, 1, true);
+			break;
 		}
 
 		/* disable headphone node */
@@ -3980,15 +4024,19 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 		/* Headphone out config*/
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0107, spec->mem_base + 0x320);
-			writew(0x0104, spec->mem_base + 0x320);
-			writew(0x0001, spec->mem_base + 0x320);
+			ca0132_mmio_gpio_set(codec, 7, true);
+			ca0132_mmio_gpio_set(codec, 4, true);
+			ca0132_mmio_gpio_set(codec, 1, false);
 			chipio_set_control_param(codec, 0x0D, 0x12);
 			break;
 		case QUIRK_R3DI:
 			chipio_set_control_param(codec, 0x0D, 0x21);
 			r3di_gpio_out_set(codec, R3DI_HEADPHONE_OUT);
 			break;
+		case QUIRK_R3D:
+			chipio_set_control_param(codec, 0x0D, 0x21);
+			ca0132_mmio_gpio_set(codec, 0x1, false);
+			break;
 		}
 
 		snd_hda_codec_write(codec, spec->out_pins[0], 0,
@@ -4022,15 +4070,19 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 		/* Surround out config*/
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0007, spec->mem_base + 0x320);
-			writew(0x0104, spec->mem_base + 0x320);
-			writew(0x0101, spec->mem_base + 0x320);
+			ca0132_mmio_gpio_set(codec, 7, false);
+			ca0132_mmio_gpio_set(codec, 4, true);
+			ca0132_mmio_gpio_set(codec, 1, true);
 			chipio_set_control_param(codec, 0x0D, 0x18);
 			break;
 		case QUIRK_R3DI:
 			chipio_set_control_param(codec, 0x0D, 0x24);
 			r3di_gpio_out_set(codec, R3DI_LINE_OUT);
 			break;
+		case QUIRK_R3D:
+			ca0132_mmio_gpio_set(codec, 1, true);
+			chipio_set_control_param(codec, 0x0D, 0x24);
+			break;
 		}
 		/* enable line out node */
 		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[0], 0,
@@ -4288,7 +4340,8 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 	case REAR_MIC:
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0000, spec->mem_base + 0x320);
+		case QUIRK_R3D:
+			ca0132_mmio_gpio_set(codec, 0, false);
 			tmp = FLOAT_THREE;
 			break;
 		case QUIRK_R3DI:
@@ -4320,7 +4373,8 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 		ca0132_mic_boost_set(codec, 0);
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0000, spec->mem_base + 0x320);
+		case QUIRK_R3D:
+			ca0132_mmio_gpio_set(codec, 0, false);
 			break;
 		case QUIRK_R3DI:
 			r3di_gpio_mic_set(codec, R3DI_REAR_MIC);
@@ -4346,8 +4400,9 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 	case FRONT_MIC:
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0100, spec->mem_base + 0x320);
-			writew(0x0005, spec->mem_base + 0x320);
+		case QUIRK_R3D:
+			ca0132_mmio_gpio_set(codec, 0, true);
+			ca0132_mmio_gpio_set(codec, 5, false);
 			tmp = FLOAT_THREE;
 			break;
 		case QUIRK_R3DI:
@@ -5513,8 +5568,7 @@ static int ca0132_alt_add_effect_slider(struct hda_codec *codec, hda_nid_t nid,
 
 	sprintf(namestr, "FX: %s %s Volume", pfx, dirstr[dir]);
 
-	knew.tlv.c = 0;
-	knew.tlv.p = 0;
+	knew.tlv.c = NULL;
 
 	switch (nid) {
 	case XBASS_XOVER:
@@ -5663,7 +5717,7 @@ static const char * const ca0132_alt_slave_pfxs[] = {
  * I think this has to do with the pin for rear surround being 0x11,
  * and the center/lfe being 0x10. Usually the pin order is the opposite.
  */
-const struct snd_pcm_chmap_elem ca0132_alt_chmaps[] = {
+static const struct snd_pcm_chmap_elem ca0132_alt_chmaps[] = {
 	{ .channels = 2,
 	  .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR } },
 	{ .channels = 4,
@@ -5726,11 +5780,11 @@ static const struct snd_kcontrol_new ca0132_mixer[] = {
 };
 
 /*
- * SBZ specific control mixer. Removes auto-detect for mic, and adds surround
- * controls. Also sets both the Front Playback and Capture Volume controls to
- * alt so they set the DSP's decibel level.
+ * Desktop specific control mixer. Removes auto-detect for mic, and adds
+ * surround controls. Also sets both the Front Playback and Capture Volume
+ * controls to alt so they set the DSP's decibel level.
  */
-static const struct snd_kcontrol_new sbz_mixer[] = {
+static const struct snd_kcontrol_new desktop_mixer[] = {
 	CA0132_ALT_CODEC_VOL("Front Playback Volume", 0x02, HDA_OUTPUT),
 	CA0132_CODEC_MUTE("Front Playback Switch", VNID_SPK, HDA_OUTPUT),
 	HDA_CODEC_VOLUME("Surround Playback Volume", 0x04, 0, HDA_OUTPUT),
@@ -5801,8 +5855,8 @@ static int ca0132_build_controls(struct hda_codec *codec)
 	 */
 	num_fx = OUT_EFFECTS_COUNT + IN_EFFECTS_COUNT;
 	for (i = 0; i < num_fx; i++) {
-		/* SBZ breaks if Echo Cancellation is used */
-		if (spec->quirk == QUIRK_SBZ) {
+		/* SBZ and R3D break if Echo Cancellation is used. */
+		if (spec->quirk == QUIRK_SBZ || spec->quirk == QUIRK_R3D) {
 			if (i == (ECHO_CANCELLATION - IN_EFFECT_START_NID +
 						OUT_EFFECTS_COUNT))
 				continue;
@@ -5966,7 +6020,7 @@ static int ca0132_build_pcms(struct hda_codec *codec)
 	info->stream[SNDRV_PCM_STREAM_CAPTURE].nid = spec->adcs[0];
 
 	/* With the DSP enabled, desktops don't use this ADC. */
-	if (spec->use_alt_functions) {
+	if (!spec->use_alt_functions) {
 		info = snd_hda_codec_pcm_new(codec, "CA0132 Analog Mic-In2");
 		if (!info)
 			return -ENOMEM;
@@ -6130,7 +6184,10 @@ static void ca0132_init_dmic(struct hda_codec *codec)
 	 * Bit   6: set to select Data2, clear for Data1
 	 * Bit   7: set to enable DMic, clear for AMic
 	 */
-	val = 0x23;
+	if (spec->quirk == QUIRK_ALIENWARE_M17XR4)
+		val = 0x33;
+	else
+		val = 0x23;
 	/* keep a copy of dmic ctl val for enable/disable dmic purpuse */
 	spec->dmic_ctl = val;
 	snd_hda_codec_write(codec, spec->input_pins[0], 0,
@@ -6181,10 +6238,10 @@ static void ca0132_refresh_widget_caps(struct hda_codec *codec)
 }
 
 /*
- * Recon3Di r3di_setup_defaults sub functions.
+ * Recon3D r3d_setup_defaults sub functions.
  */
 
-static void r3di_dsp_scp_startup(struct hda_codec *codec)
+static void r3d_dsp_scp_startup(struct hda_codec *codec)
 {
 	unsigned int tmp;
 
@@ -6205,7 +6262,7 @@ static void r3di_dsp_scp_startup(struct hda_codec *codec)
 
 }
 
-static void r3di_dsp_initial_mic_setup(struct hda_codec *codec)
+static void r3d_dsp_initial_mic_setup(struct hda_codec *codec)
 {
 	unsigned int tmp;
 
@@ -6415,10 +6472,10 @@ static void ca0132_setup_defaults(struct hda_codec *codec)
 }
 
 /*
- * Setup default parameters for Recon3Di DSP.
+ * Setup default parameters for Recon3D/Recon3Di DSP.
  */
 
-static void r3di_setup_defaults(struct hda_codec *codec)
+static void r3d_setup_defaults(struct hda_codec *codec)
 {
 	struct ca0132_spec *spec = codec->spec;
 	unsigned int tmp;
@@ -6428,9 +6485,9 @@ static void r3di_setup_defaults(struct hda_codec *codec)
 	if (spec->dsp_state != DSP_DOWNLOADED)
 		return;
 
-	r3di_dsp_scp_startup(codec);
+	r3d_dsp_scp_startup(codec);
 
-	r3di_dsp_initial_mic_setup(codec);
+	r3d_dsp_initial_mic_setup(codec);
 
 	/*remove DSP headroom*/
 	tmp = FLOAT_ZERO;
@@ -6444,7 +6501,8 @@ static void r3di_setup_defaults(struct hda_codec *codec)
 	/* Set speaker source? */
 	dspio_set_uint_param(codec, 0x32, 0x00, tmp);
 
-	r3di_gpio_dsp_status_set(codec, R3DI_DSP_DOWNLOADED);
+	if (spec->quirk == QUIRK_R3DI)
+		r3di_gpio_dsp_status_set(codec, R3DI_DSP_DOWNLOADED);
 
 	/* Setup effect defaults */
 	num_fx = OUT_EFFECTS_COUNT + IN_EFFECTS_COUNT + 1;
@@ -6456,7 +6514,6 @@ static void r3di_setup_defaults(struct hda_codec *codec)
 					ca0132_effects[idx].def_vals[i]);
 		}
 	}
-
 }
 
 /*
@@ -6721,7 +6778,12 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 
 static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 {
-	ca0132_select_mic(codec);
+	struct ca0132_spec *spec = codec->spec;
+
+	if (spec->use_alt_functions)
+		ca0132_alt_select_in(codec);
+	else
+		ca0132_select_mic(codec);
 }
 
 static void ca0132_init_unsol(struct hda_codec *codec)
@@ -6792,8 +6854,8 @@ static struct hda_verb ca0132_init_verbs0[] = {
 	{}
 };
 
-/* Extra init verbs for SBZ */
-static struct hda_verb sbz_init_verbs[] = {
+/* Extra init verbs for desktop cards. */
+static struct hda_verb ca0132_init_verbs1[] = {
 	{0x15, 0x70D, 0x20},
 	{0x15, 0x70E, 0x19},
 	{0x15, 0x707, 0x00},
@@ -6885,16 +6947,12 @@ static void sbz_region2_exit(struct hda_codec *codec)
 		writeb(0x0, spec->mem_base + 0x100);
 	for (i = 0; i < 8; i++)
 		writeb(0xb3, spec->mem_base + 0x304);
-	/*
-	 * I believe these are GPIO, with the right most hex digit being the
-	 * gpio pin, and the second digit being on or off. We see this more in
-	 * the input/output select functions.
-	 */
-	writew(0x0000, spec->mem_base + 0x320);
-	writew(0x0001, spec->mem_base + 0x320);
-	writew(0x0104, spec->mem_base + 0x320);
-	writew(0x0005, spec->mem_base + 0x320);
-	writew(0x0007, spec->mem_base + 0x320);
+
+	ca0132_mmio_gpio_set(codec, 0, false);
+	ca0132_mmio_gpio_set(codec, 1, false);
+	ca0132_mmio_gpio_set(codec, 4, true);
+	ca0132_mmio_gpio_set(codec, 5, false);
+	ca0132_mmio_gpio_set(codec, 7, false);
 }
 
 static void sbz_set_pin_ctl_default(struct hda_codec *codec)
@@ -6910,7 +6968,7 @@ static void sbz_set_pin_ctl_default(struct hda_codec *codec)
 				AC_VERB_SET_PIN_WIDGET_CONTROL, 0x00);
 }
 
-static void sbz_clear_unsolicited(struct hda_codec *codec)
+static void ca0132_clear_unsolicited(struct hda_codec *codec)
 {
 	hda_nid_t pins[7] = {0x0B, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13};
 	unsigned int i;
@@ -6963,21 +7021,22 @@ static void sbz_exit_chip(struct hda_codec *codec)
 
 	chipio_set_control_param(codec, 0x0D, 0x24);
 
-	sbz_clear_unsolicited(codec);
+	ca0132_clear_unsolicited(codec);
 	sbz_set_pin_ctl_default(codec);
 
 	snd_hda_codec_write(codec, 0x0B, 0,
 		AC_VERB_SET_EAPD_BTLENABLE, 0x00);
 
-	if (dspload_is_loaded(codec))
-		dsp_reset(codec);
-
-	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
-		VENDOR_CHIPIO_CT_EXTENSIONS_ENABLE, 0x00);
-
 	sbz_region2_exit(codec);
 }
 
+static void r3d_exit_chip(struct hda_codec *codec)
+{
+	ca0132_clear_unsolicited(codec);
+	snd_hda_codec_write(codec, 0x01, 0, 0x793, 0x00);
+	snd_hda_codec_write(codec, 0x01, 0, 0x794, 0x5b);
+}
+
 static void ca0132_exit_chip(struct hda_codec *codec)
 {
 	/* put any chip cleanup stuffs here. */
@@ -7092,9 +7151,27 @@ static void sbz_pre_dsp_setup(struct hda_codec *codec)
 			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x44);
 }
 
-/*
- * Extra commands that don't really fit anywhere else.
- */
+static void r3d_pre_dsp_setup(struct hda_codec *codec)
+{
+
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xfc);
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xfd);
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xfe);
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xff);
+
+	chipio_write(codec, 0x18b0a4, 0x000000c2);
+
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_ADDRESS_LOW, 0x1E);
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_ADDRESS_HIGH, 0x1C);
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_DATA_WRITE, 0x5B);
+
+	snd_hda_codec_write(codec, 0x11, 0,
+			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x44);
+}
+
 static void r3di_pre_dsp_setup(struct hda_codec *codec)
 {
 	chipio_write(codec, 0x18b0a4, 0x000000c2);
@@ -7119,13 +7196,12 @@ static void r3di_pre_dsp_setup(struct hda_codec *codec)
 			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x04);
 }
 
-
 /*
  * These are sent before the DSP is downloaded. Not sure
  * what they do, or if they're necessary. Could possibly
  * be removed. Figure they're better to leave in.
  */
-static void sbz_region2_startup(struct hda_codec *codec)
+static void ca0132_mmio_init(struct hda_codec *codec)
 {
 	struct ca0132_spec *spec = codec->spec;
 
@@ -7165,7 +7241,7 @@ static void ca0132_alt_init(struct hda_codec *codec)
 		ca0132_gpio_init(codec);
 		sbz_pre_dsp_setup(codec);
 		snd_hda_sequence_write(codec, spec->chip_init_verbs);
-		snd_hda_sequence_write(codec, spec->sbz_init_verbs);
+		snd_hda_sequence_write(codec, spec->desktop_init_verbs);
 		break;
 	case QUIRK_R3DI:
 		codec_dbg(codec, "R3DI alt_init");
@@ -7176,6 +7252,11 @@ static void ca0132_alt_init(struct hda_codec *codec)
 		snd_hda_sequence_write(codec, spec->chip_init_verbs);
 		snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0, 0x6FF, 0xC4);
 		break;
+	case QUIRK_R3D:
+		r3d_pre_dsp_setup(codec);
+		snd_hda_sequence_write(codec, spec->chip_init_verbs);
+		snd_hda_sequence_write(codec, spec->desktop_init_verbs);
+		break;
 	}
 }
 
@@ -7212,8 +7293,8 @@ static int ca0132_init(struct hda_codec *codec)
 		spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->curr_chip_addx = INVALID_CHIP_ADDRESS;
 
-	if (spec->quirk == QUIRK_SBZ)
-		sbz_region2_startup(codec);
+	if (spec->use_pci_mmio)
+		ca0132_mmio_init(codec);
 
 	snd_hda_power_up_pm(codec);
 
@@ -7223,22 +7304,22 @@ static int ca0132_init(struct hda_codec *codec)
 
 	snd_hda_sequence_write(codec, spec->base_init_verbs);
 
-	if (spec->quirk != QUIRK_NONE)
+	if (spec->use_alt_functions)
 		ca0132_alt_init(codec);
 
 	ca0132_download_dsp(codec);
 
 	ca0132_refresh_widget_caps(codec);
 
-	if (spec->quirk == QUIRK_SBZ)
-		writew(0x0107, spec->mem_base + 0x320);
-
 	switch (spec->quirk) {
 	case QUIRK_R3DI:
-		r3di_setup_defaults(codec);
+	case QUIRK_R3D:
+		r3d_setup_defaults(codec);
 		break;
-	case QUIRK_NONE:
-	case QUIRK_ALIENWARE:
+	case QUIRK_SBZ:
+		sbz_setup_defaults(codec);
+		break;
+	default:
 		ca0132_setup_defaults(codec);
 		ca0132_init_analog_mic2(codec);
 		ca0132_init_dmic(codec);
@@ -7267,20 +7348,12 @@ static int ca0132_init(struct hda_codec *codec)
 		ca0132_gpio_setup(codec);
 
 	snd_hda_sequence_write(codec, spec->spec_init_verbs);
-	switch (spec->quirk) {
-	case QUIRK_SBZ:
-		sbz_setup_defaults(codec);
-		ca0132_alt_select_out(codec);
-		ca0132_alt_select_in(codec);
-		break;
-	case QUIRK_R3DI:
+	if (spec->use_alt_functions) {
 		ca0132_alt_select_out(codec);
 		ca0132_alt_select_in(codec);
-		break;
-	default:
+	} else {
 		ca0132_select_out(codec);
 		ca0132_select_mic(codec);
-		break;
 	}
 
 	snd_hda_jack_report_sync(codec);
@@ -7309,16 +7382,17 @@ static void ca0132_free(struct hda_codec *codec)
 	case QUIRK_SBZ:
 		sbz_exit_chip(codec);
 		break;
+	case QUIRK_R3D:
+		r3d_exit_chip(codec);
+		break;
 	case QUIRK_R3DI:
 		r3di_gpio_shutdown(codec);
-		snd_hda_sequence_write(codec, spec->base_exit_verbs);
-		ca0132_exit_chip(codec);
-		break;
-	default:
-		snd_hda_sequence_write(codec, spec->base_exit_verbs);
-		ca0132_exit_chip(codec);
 		break;
 	}
+
+	snd_hda_sequence_write(codec, spec->base_exit_verbs);
+	ca0132_exit_chip(codec);
+
 	snd_hda_power_down(codec);
 	if (spec->mem_base)
 		iounmap(spec->mem_base);
@@ -7343,7 +7417,6 @@ static const struct hda_codec_ops ca0132_patch_ops = {
 static void ca0132_config(struct hda_codec *codec)
 {
 	struct ca0132_spec *spec = codec->spec;
-	struct auto_pin_cfg *cfg = &spec->autocfg;
 
 	spec->dacs[0] = 0x2;
 	spec->dacs[1] = 0x3;
@@ -7380,8 +7453,15 @@ static void ca0132_config(struct hda_codec *codec)
 		spec->unsol_tag_amic1 = 0x11;
 		break;
 	case QUIRK_SBZ:
-		codec_dbg(codec, "%s: QUIRK_SBZ applied.\n", __func__);
-		snd_hda_apply_pincfgs(codec, sbz_pincfgs);
+	case QUIRK_R3D:
+		if (spec->quirk == QUIRK_SBZ) {
+			codec_dbg(codec, "%s: QUIRK_SBZ applied.\n", __func__);
+			snd_hda_apply_pincfgs(codec, sbz_pincfgs);
+		}
+		if (spec->quirk == QUIRK_R3D) {
+			codec_dbg(codec, "%s: QUIRK_R3D applied.\n", __func__);
+			snd_hda_apply_pincfgs(codec, r3d_pincfgs);
+		}
 
 		spec->num_outputs = 2;
 		spec->out_pins[0] = 0x0B; /* Line out */
@@ -7405,12 +7485,7 @@ static void ca0132_config(struct hda_codec *codec)
 		/* SPDIF I/O */
 		spec->dig_out = 0x05;
 		spec->multiout.dig_out_nid = spec->dig_out;
-		cfg->dig_out_pins[0] = 0x0c;
-		cfg->dig_outs = 1;
-		cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
 		spec->dig_in = 0x09;
-		cfg->dig_in_pin = 0x0e;
-		cfg->dig_in_type = HDA_PCM_TYPE_SPDIF;
 		break;
 	case QUIRK_R3DI:
 		codec_dbg(codec, "%s: QUIRK_R3DI applied.\n", __func__);
@@ -7438,9 +7513,6 @@ static void ca0132_config(struct hda_codec *codec)
 		/* SPDIF I/O */
 		spec->dig_out = 0x05;
 		spec->multiout.dig_out_nid = spec->dig_out;
-		cfg->dig_out_pins[0] = 0x0c;
-		cfg->dig_outs = 1;
-		cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
 		break;
 	default:
 		spec->num_outputs = 2;
@@ -7463,12 +7535,7 @@ static void ca0132_config(struct hda_codec *codec)
 		/* SPDIF I/O */
 		spec->dig_out = 0x05;
 		spec->multiout.dig_out_nid = spec->dig_out;
-		cfg->dig_out_pins[0] = 0x0c;
-		cfg->dig_outs = 1;
-		cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
 		spec->dig_in = 0x09;
-		cfg->dig_in_pin = 0x0e;
-		cfg->dig_in_type = HDA_PCM_TYPE_SPDIF;
 		break;
 	}
 }
@@ -7476,46 +7543,36 @@ static void ca0132_config(struct hda_codec *codec)
 static int ca0132_prepare_verbs(struct hda_codec *codec)
 {
 /* Verbs + terminator (an empty element) */
-#define NUM_SPEC_VERBS 4
+#define NUM_SPEC_VERBS 2
 	struct ca0132_spec *spec = codec->spec;
 
 	spec->chip_init_verbs = ca0132_init_verbs0;
-	if (spec->quirk == QUIRK_SBZ)
-		spec->sbz_init_verbs = sbz_init_verbs;
+	if (spec->quirk == QUIRK_SBZ || spec->quirk == QUIRK_R3D)
+		spec->desktop_init_verbs = ca0132_init_verbs1;
 	spec->spec_init_verbs = kcalloc(NUM_SPEC_VERBS,
 					sizeof(struct hda_verb),
 					GFP_KERNEL);
 	if (!spec->spec_init_verbs)
 		return -ENOMEM;
 
-	/* HP jack autodetection */
-	spec->spec_init_verbs[0].nid = spec->unsol_tag_hp;
-	spec->spec_init_verbs[0].param = AC_VERB_SET_UNSOLICITED_ENABLE;
-	spec->spec_init_verbs[0].verb = AC_USRSP_EN | spec->unsol_tag_hp;
-
-	/* MIC1 jack autodetection */
-	spec->spec_init_verbs[1].nid = spec->unsol_tag_amic1;
-	spec->spec_init_verbs[1].param = AC_VERB_SET_UNSOLICITED_ENABLE;
-	spec->spec_init_verbs[1].verb = AC_USRSP_EN | spec->unsol_tag_amic1;
-
 	/* config EAPD */
-	spec->spec_init_verbs[2].nid = 0x0b;
-	spec->spec_init_verbs[2].param = 0x78D;
-	spec->spec_init_verbs[2].verb = 0x00;
+	spec->spec_init_verbs[0].nid = 0x0b;
+	spec->spec_init_verbs[0].param = 0x78D;
+	spec->spec_init_verbs[0].verb = 0x00;
 
 	/* Previously commented configuration */
 	/*
-	spec->spec_init_verbs[3].nid = 0x0b;
-	spec->spec_init_verbs[3].param = AC_VERB_SET_EAPD_BTLENABLE;
+	spec->spec_init_verbs[2].nid = 0x0b;
+	spec->spec_init_verbs[2].param = AC_VERB_SET_EAPD_BTLENABLE;
+	spec->spec_init_verbs[2].verb = 0x02;
+
+	spec->spec_init_verbs[3].nid = 0x10;
+	spec->spec_init_verbs[3].param = 0x78D;
 	spec->spec_init_verbs[3].verb = 0x02;
 
 	spec->spec_init_verbs[4].nid = 0x10;
-	spec->spec_init_verbs[4].param = 0x78D;
+	spec->spec_init_verbs[4].param = AC_VERB_SET_EAPD_BTLENABLE;
 	spec->spec_init_verbs[4].verb = 0x02;
-
-	spec->spec_init_verbs[5].nid = 0x10;
-	spec->spec_init_verbs[5].param = AC_VERB_SET_EAPD_BTLENABLE;
-	spec->spec_init_verbs[5].verb = 0x02;
 	*/
 
 	/* Terminator: spec->spec_init_verbs[NUM_SPEC_VERBS-1] */
@@ -7547,25 +7604,19 @@ static int patch_ca0132(struct hda_codec *codec)
 	else
 		spec->quirk = QUIRK_NONE;
 
-	/* Setup BAR Region 2 for Sound Blaster Z */
-	if (spec->quirk == QUIRK_SBZ) {
-		spec->mem_base = pci_iomap(codec->bus->pci, 2, 0xC20);
-		if (spec->mem_base == NULL) {
-			codec_warn(codec, "pci_iomap failed!");
-			codec_info(codec, "perhaps this is not an SBZ?");
-			spec->quirk = QUIRK_NONE;
-		}
-	}
-
 	spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->num_mixers = 1;
 
 	/* Set which mixers each quirk uses. */
 	switch (spec->quirk) {
 	case QUIRK_SBZ:
-		spec->mixers[0] = sbz_mixer;
+		spec->mixers[0] = desktop_mixer;
 		snd_hda_codec_set_name(codec, "Sound Blaster Z");
 		break;
+	case QUIRK_R3D:
+		spec->mixers[0] = desktop_mixer;
+		snd_hda_codec_set_name(codec, "Recon3D");
+		break;
 	case QUIRK_R3DI:
 		spec->mixers[0] = r3di_mixer;
 		snd_hda_codec_set_name(codec, "Recon3Di");
@@ -7575,19 +7626,34 @@ static int patch_ca0132(struct hda_codec *codec)
 		break;
 	}
 
-	/* Setup whether or not to use alt functions/controls */
+	/* Setup whether or not to use alt functions/controls/pci_mmio */
 	switch (spec->quirk) {
 	case QUIRK_SBZ:
+	case QUIRK_R3D:
+		spec->use_alt_controls = true;
+		spec->use_alt_functions = true;
+		spec->use_pci_mmio = true;
+		break;
 	case QUIRK_R3DI:
 		spec->use_alt_controls = true;
 		spec->use_alt_functions = true;
+		spec->use_pci_mmio = false;
 		break;
 	default:
 		spec->use_alt_controls = false;
 		spec->use_alt_functions = false;
+		spec->use_pci_mmio = false;
 		break;
 	}
 
+	if (spec->use_pci_mmio) {
+		spec->mem_base = pci_iomap(codec->bus->pci, 2, 0xC20);
+		if (spec->mem_base == NULL) {
+			codec_warn(codec, "pci_iomap failed! Setting quirk to QUIRK_NONE.");
+			spec->quirk = QUIRK_NONE;
+		}
+	}
+
 	spec->base_init_verbs = ca0132_base_init_verbs;
 	spec->base_exit_verbs = ca0132_base_exit_verbs;
 
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index d6e079f4ec09..a7f91be45194 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -1096,25 +1096,6 @@ static int cs421x_init(struct hda_codec *codec)
 	return 0;
 }
 
-static int cs421x_build_controls(struct hda_codec *codec)
-{
-	struct cs_spec *spec = codec->spec;
-	int err;
-
-	err = snd_hda_gen_build_controls(codec);
-	if (err < 0)
-		return err;
-
-	if (spec->gen.autocfg.speaker_outs &&
-	    spec->vendor_nid == CS4210_VENDOR_NID) {
-		err = snd_hda_ctl_add(codec, 0,
-			snd_ctl_new1(&cs421x_speaker_boost_ctl, codec));
-		if (err < 0)
-			return err;
-	}
-	return 0;
-}
-
 static void fix_volume_caps(struct hda_codec *codec, hda_nid_t dac)
 {
 	unsigned int caps;
@@ -1144,6 +1125,14 @@ static int cs421x_parse_auto_config(struct hda_codec *codec)
 		return err;
 
 	parse_cs421x_digital(codec);
+
+	if (spec->gen.autocfg.speaker_outs &&
+	    spec->vendor_nid == CS4210_VENDOR_NID) {
+		if (!snd_hda_gen_add_kctl(&spec->gen, NULL,
+					  &cs421x_speaker_boost_ctl))
+			return -ENOMEM;
+	}
+
 	return 0;
 }
 
@@ -1175,7 +1164,7 @@ static int cs421x_suspend(struct hda_codec *codec)
 #endif
 
 static const struct hda_codec_ops cs421x_patch_ops = {
-	.build_controls = cs421x_build_controls,
+	.build_controls = snd_hda_gen_build_controls,
 	.build_pcms = snd_hda_gen_build_pcms,
 	.init = cs421x_init,
 	.free = cs_free,
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index e7fcfc3b8885..cfd4e4f97f8f 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -37,8 +37,6 @@
 struct conexant_spec {
 	struct hda_gen_spec gen;
 
-	unsigned int beep_amp;
-
 	/* extra EAPD pins */
 	unsigned int num_eapds;
 	hda_nid_t eapds[4];
@@ -62,65 +60,48 @@ struct conexant_spec {
 
 
 #ifdef CONFIG_SND_HDA_INPUT_BEEP
-static inline void set_beep_amp(struct conexant_spec *spec, hda_nid_t nid,
-				int idx, int dir)
-{
-	spec->gen.beep_nid = nid;
-	spec->beep_amp = HDA_COMPOSE_AMP_VAL(nid, 1, idx, dir);
-}
-/* additional beep mixers; the actual parameters are overwritten at build */
+/* additional beep mixers; private_value will be overwritten */
 static const struct snd_kcontrol_new cxt_beep_mixer[] = {
 	HDA_CODEC_VOLUME_MONO("Beep Playback Volume", 0, 1, 0, HDA_OUTPUT),
 	HDA_CODEC_MUTE_BEEP_MONO("Beep Playback Switch", 0, 1, 0, HDA_OUTPUT),
-	{ } /* end */
 };
 
-/* create beep controls if needed */
-static int add_beep_ctls(struct hda_codec *codec)
+static int set_beep_amp(struct conexant_spec *spec, hda_nid_t nid,
+			int idx, int dir)
 {
-	struct conexant_spec *spec = codec->spec;
-	int err;
+	struct snd_kcontrol_new *knew;
+	unsigned int beep_amp = HDA_COMPOSE_AMP_VAL(nid, 1, idx, dir);
+	int i;
 
-	if (spec->beep_amp) {
-		const struct snd_kcontrol_new *knew;
-		for (knew = cxt_beep_mixer; knew->name; knew++) {
-			struct snd_kcontrol *kctl;
-			kctl = snd_ctl_new1(knew, codec);
-			if (!kctl)
-				return -ENOMEM;
-			kctl->private_value = spec->beep_amp;
-			err = snd_hda_ctl_add(codec, 0, kctl);
-			if (err < 0)
-				return err;
-		}
+	spec->gen.beep_nid = nid;
+	for (i = 0; i < ARRAY_SIZE(cxt_beep_mixer); i++) {
+		knew = snd_hda_gen_add_kctl(&spec->gen, NULL,
+					    &cxt_beep_mixer[i]);
+		if (!knew)
+			return -ENOMEM;
+		knew->private_value = beep_amp;
 	}
 	return 0;
 }
-#else
-#define set_beep_amp(spec, nid, idx, dir) /* NOP */
-#define add_beep_ctls(codec)	0
-#endif
-
-/*
- * Automatic parser for CX20641 & co
- */
 
-#ifdef CONFIG_SND_HDA_INPUT_BEEP
-static void cx_auto_parse_beep(struct hda_codec *codec)
+static int cx_auto_parse_beep(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
 	hda_nid_t nid;
 
 	for_each_hda_codec_node(nid, codec)
-		if (get_wcaps_type(get_wcaps(codec, nid)) == AC_WID_BEEP) {
-			set_beep_amp(spec, nid, 0, HDA_OUTPUT);
-			break;
-		}
+		if (get_wcaps_type(get_wcaps(codec, nid)) == AC_WID_BEEP)
+			return set_beep_amp(spec, nid, 0, HDA_OUTPUT);
+	return 0;
 }
 #else
-#define cx_auto_parse_beep(codec)
+#define cx_auto_parse_beep(codec)	0
 #endif
 
+/*
+ * Automatic parser for CX20641 & co
+ */
+
 /* parse EAPDs */
 static void cx_auto_parse_eapd(struct hda_codec *codec)
 {
@@ -179,21 +160,6 @@ static void cx_auto_vmaster_hook_mute_led(void *private_data, int enabled)
 			    enabled ? 0x00 : 0x02);
 }
 
-static int cx_auto_build_controls(struct hda_codec *codec)
-{
-	int err;
-
-	err = snd_hda_gen_build_controls(codec);
-	if (err < 0)
-		return err;
-
-	err = add_beep_ctls(codec);
-	if (err < 0)
-		return err;
-
-	return 0;
-}
-
 static int cx_auto_init(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
@@ -211,6 +177,7 @@ static void cx_auto_reboot_notify(struct hda_codec *codec)
 	struct conexant_spec *spec = codec->spec;
 
 	switch (codec->core.vendor_id) {
+	case 0x14f12008: /* CX8200 */
 	case 0x14f150f2: /* CX20722 */
 	case 0x14f150f4: /* CX20724 */
 		break;
@@ -218,13 +185,14 @@ static void cx_auto_reboot_notify(struct hda_codec *codec)
 		return;
 	}
 
-	/* Turn the CX20722 codec into D3 to avoid spurious noises
+	/* Turn the problematic codec into D3 to avoid spurious noises
 	   from the internal speaker during (and after) reboot */
 	cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, false);
 
 	snd_hda_codec_set_power_to_all(codec, codec->core.afg, AC_PWRST_D3);
 	snd_hda_codec_write(codec, codec->core.afg, 0,
 			    AC_VERB_SET_POWER_STATE, AC_PWRST_D3);
+	msleep(10);
 }
 
 static void cx_auto_free(struct hda_codec *codec)
@@ -234,7 +202,7 @@ static void cx_auto_free(struct hda_codec *codec)
 }
 
 static const struct hda_codec_ops cx_auto_patch_ops = {
-	.build_controls = cx_auto_build_controls,
+	.build_controls = snd_hda_gen_build_controls,
 	.build_pcms = snd_hda_gen_build_pcms,
 	.init = cx_auto_init,
 	.reboot_notify = cx_auto_reboot_notify,
@@ -343,6 +311,7 @@ static void cxt_fixup_headphone_mic(struct hda_codec *codec,
 		snd_hdac_regmap_add_vendor_verb(&codec->core, 0x410);
 		break;
 	case HDA_FIXUP_ACT_PROBE:
+		WARN_ON(spec->gen.cap_sync_hook);
 		spec->gen.cap_sync_hook = cxt_update_headset_mode_hook;
 		spec->gen.automute_hook = cxt_update_headset_mode;
 		break;
@@ -374,7 +343,7 @@ static void cxt_fixup_headset_mic(struct hda_codec *codec,
  * control. */
 
 #define update_mic_pin(codec, nid, val)					\
-	snd_hda_codec_update_cache(codec, nid, 0,			\
+	snd_hda_codec_write_cache(codec, nid, 0,			\
 				   AC_VERB_SET_PIN_WIDGET_CONTROL, val)
 
 static const struct hda_input_mux olpc_xo_dc_bias = {
@@ -695,16 +664,12 @@ static void cxt_fixup_gpio_mute_hook(void *private_data, int enabled)
 }
 
 /* turn on/off mic-mute LED via GPIO per capture hook */
-static void cxt_fixup_gpio_mic_mute_hook(struct hda_codec *codec,
-					 struct snd_kcontrol *kcontrol,
-					 struct snd_ctl_elem_value *ucontrol)
+static void cxt_gpio_micmute_update(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
 
-	if (ucontrol)
-		cxt_update_gpio_led(codec, spec->gpio_mic_led_mask,
-				    ucontrol->value.integer.value[0] ||
-				    ucontrol->value.integer.value[1]);
+	cxt_update_gpio_led(codec, spec->gpio_mic_led_mask,
+			    spec->gen.micmute_led.led_value);
 }
 
 
@@ -721,11 +686,11 @@ static void cxt_fixup_mute_led_gpio(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = cxt_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = cxt_fixup_gpio_mic_mute_hook;
 		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x01;
 		spec->gpio_mic_led_mask = 0x02;
+		snd_hda_gen_add_micmute_led(codec, cxt_gpio_micmute_update);
 	}
 	snd_hda_add_verbs(codec, gpio_init);
 	if (spec->gpio_led)
@@ -964,6 +929,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO),
+	SND_PCI_QUIRK(0x103c, 0x836e, "HP ProBook 455 G5", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE),
@@ -1036,7 +1002,6 @@ static int patch_conexant_auto(struct hda_codec *codec)
 	codec->spec = spec;
 	codec->patch_ops = cx_auto_patch_ops;
 
-	cx_auto_parse_beep(codec);
 	cx_auto_parse_eapd(codec);
 	spec->gen.own_eapd_ctl = 1;
 	if (spec->dynamic_eapd)
@@ -1096,6 +1061,10 @@ static int patch_conexant_auto(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
+	err = cx_auto_parse_beep(codec);
+	if (err < 0)
+		goto error;
+
 	/* Some laptops with Conexant chips show stalls in S3 resume,
 	 * which falls into the single-cmd mode.
 	 * Better to make reset, then.
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 8840daf9c6a3..cb587dce67a9 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -33,6 +33,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <sound/core.h>
 #include <sound/jack.h>
 #include <sound/asoundef.h>
@@ -176,13 +177,13 @@ struct hdmi_spec {
 
 	/* i915/powerwell (Haswell+/Valleyview+) specific */
 	bool use_acomp_notifier; /* use i915 eld_notify callback for hotplug */
-	struct i915_audio_component_audio_ops i915_audio_ops;
+	struct drm_audio_component_audio_ops drm_audio_ops;
 
 	struct hdac_chmap chmap;
 	hda_nid_t vendor_nid;
 };
 
-#ifdef CONFIG_SND_HDA_I915
+#ifdef CONFIG_SND_HDA_COMPONENT
 static inline bool codec_has_acomp(struct hda_codec *codec)
 {
 	struct hdmi_spec *spec = codec->spec;
@@ -338,13 +339,13 @@ static int hdmi_eld_ctl_info(struct snd_kcontrol *kcontrol,
 	if (!per_pin) {
 		/* no pin is bound to the pcm */
 		uinfo->count = 0;
-		mutex_unlock(&spec->pcm_lock);
-		return 0;
+		goto unlock;
 	}
 	eld = &per_pin->sink_eld;
 	uinfo->count = eld->eld_valid ? eld->eld_size : 0;
-	mutex_unlock(&spec->pcm_lock);
 
+ unlock:
+	mutex_unlock(&spec->pcm_lock);
 	return 0;
 }
 
@@ -356,6 +357,7 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol,
 	struct hdmi_spec_per_pin *per_pin;
 	struct hdmi_eld *eld;
 	int pcm_idx;
+	int err = 0;
 
 	pcm_idx = kcontrol->private_value;
 	mutex_lock(&spec->pcm_lock);
@@ -364,16 +366,15 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol,
 		/* no pin is bound to the pcm */
 		memset(ucontrol->value.bytes.data, 0,
 		       ARRAY_SIZE(ucontrol->value.bytes.data));
-		mutex_unlock(&spec->pcm_lock);
-		return 0;
+		goto unlock;
 	}
-	eld = &per_pin->sink_eld;
 
+	eld = &per_pin->sink_eld;
 	if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data) ||
 	    eld->eld_size > ELD_MAX_SIZE) {
-		mutex_unlock(&spec->pcm_lock);
 		snd_BUG();
-		return -EINVAL;
+		err = -EINVAL;
+		goto unlock;
 	}
 
 	memset(ucontrol->value.bytes.data, 0,
@@ -381,9 +382,10 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol,
 	if (eld->eld_valid)
 		memcpy(ucontrol->value.bytes.data, eld->eld_buffer,
 		       eld->eld_size);
-	mutex_unlock(&spec->pcm_lock);
 
-	return 0;
+ unlock:
+	mutex_unlock(&spec->pcm_lock);
+	return err;
 }
 
 static const struct snd_kcontrol_new eld_bytes_ctl = {
@@ -764,8 +766,10 @@ static void check_presence_and_report(struct hda_codec *codec, hda_nid_t nid,
 
 	if (pin_idx < 0)
 		return;
+	mutex_lock(&spec->pcm_lock);
 	if (hdmi_present_sense(get_pin(spec, pin_idx), 1))
 		snd_hda_jack_report_sync(codec);
+	mutex_unlock(&spec->pcm_lock);
 }
 
 static void jack_callback(struct hda_codec *codec,
@@ -1206,8 +1210,8 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 	pin_idx = hinfo_to_pin_index(codec, hinfo);
 	if (!spec->dyn_pcm_assign) {
 		if (snd_BUG_ON(pin_idx < 0)) {
-			mutex_unlock(&spec->pcm_lock);
-			return -EINVAL;
+			err = -EINVAL;
+			goto unlock;
 		}
 	} else {
 		/* no pin is assigned to the PCM
@@ -1215,16 +1219,13 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 		 */
 		if (pin_idx < 0) {
 			err = hdmi_pcm_open_no_pin(hinfo, codec, substream);
-			mutex_unlock(&spec->pcm_lock);
-			return err;
+			goto unlock;
 		}
 	}
 
 	err = hdmi_choose_cvt(codec, pin_idx, &cvt_idx);
-	if (err < 0) {
-		mutex_unlock(&spec->pcm_lock);
-		return err;
-	}
+	if (err < 0)
+		goto unlock;
 
 	per_cvt = get_cvt(spec, cvt_idx);
 	/* Claim converter */
@@ -1261,12 +1262,11 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 			per_cvt->assigned = 0;
 			hinfo->nid = 0;
 			snd_hda_spdif_ctls_unassign(codec, pcm_idx);
-			mutex_unlock(&spec->pcm_lock);
-			return -ENODEV;
+			err = -ENODEV;
+			goto unlock;
 		}
 	}
 
-	mutex_unlock(&spec->pcm_lock);
 	/* Store the updated parameters */
 	runtime->hw.channels_min = hinfo->channels_min;
 	runtime->hw.channels_max = hinfo->channels_max;
@@ -1275,7 +1275,9 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 
 	snd_pcm_hw_constraint_step(substream->runtime, 0,
 				   SNDRV_PCM_HW_PARAM_CHANNELS, 2);
-	return 0;
+ unlock:
+	mutex_unlock(&spec->pcm_lock);
+	return err;
 }
 
 /*
@@ -1628,21 +1630,23 @@ static void sync_eld_via_acomp(struct hda_codec *codec,
 static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll)
 {
 	struct hda_codec *codec = per_pin->codec;
-	struct hdmi_spec *spec = codec->spec;
 	int ret;
 
 	/* no temporary power up/down needed for component notifier */
-	if (!codec_has_acomp(codec))
-		snd_hda_power_up_pm(codec);
+	if (!codec_has_acomp(codec)) {
+		ret = snd_hda_power_up_pm(codec);
+		if (ret < 0 && pm_runtime_suspended(hda_codec_dev(codec))) {
+			snd_hda_power_down_pm(codec);
+			return false;
+		}
+	}
 
-	mutex_lock(&spec->pcm_lock);
 	if (codec_has_acomp(codec)) {
 		sync_eld_via_acomp(codec, per_pin);
 		ret = false; /* don't call snd_hda_jack_report_sync() */
 	} else {
 		ret = hdmi_present_sense_via_verbs(per_pin, repoll);
 	}
-	mutex_unlock(&spec->pcm_lock);
 
 	if (!codec_has_acomp(codec))
 		snd_hda_power_down_pm(codec);
@@ -1654,12 +1658,16 @@ static void hdmi_repoll_eld(struct work_struct *work)
 {
 	struct hdmi_spec_per_pin *per_pin =
 	container_of(to_delayed_work(work), struct hdmi_spec_per_pin, work);
+	struct hda_codec *codec = per_pin->codec;
+	struct hdmi_spec *spec = codec->spec;
 
 	if (per_pin->repoll_count++ > 6)
 		per_pin->repoll_count = 0;
 
+	mutex_lock(&spec->pcm_lock);
 	if (hdmi_present_sense(per_pin, per_pin->repoll_count))
 		snd_hda_jack_report_sync(per_pin->codec);
+	mutex_unlock(&spec->pcm_lock);
 }
 
 static void intel_haswell_fixup_connect_list(struct hda_codec *codec,
@@ -1858,7 +1866,7 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	bool non_pcm;
 	int pinctl;
-	int err;
+	int err = 0;
 
 	mutex_lock(&spec->pcm_lock);
 	pin_idx = hinfo_to_pin_index(codec, hinfo);
@@ -1870,13 +1878,12 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 		pin_cvt_fixup(codec, NULL, cvt_nid);
 		snd_hda_codec_setup_stream(codec, cvt_nid,
 					stream_tag, 0, format);
-		mutex_unlock(&spec->pcm_lock);
-		return 0;
+		goto unlock;
 	}
 
 	if (snd_BUG_ON(pin_idx < 0)) {
-		mutex_unlock(&spec->pcm_lock);
-		return -EINVAL;
+		err = -EINVAL;
+		goto unlock;
 	}
 	per_pin = get_pin(spec, pin_idx);
 	pin_nid = per_pin->pin_nid;
@@ -1915,6 +1922,7 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 	/* snd_hda_set_dev_select() has been called before */
 	err = spec->ops.setup_stream(codec, cvt_nid, pin_nid,
 				 stream_tag, format);
+ unlock:
 	mutex_unlock(&spec->pcm_lock);
 	return err;
 }
@@ -1936,6 +1944,7 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo,
 	struct hdmi_spec_per_cvt *per_cvt;
 	struct hdmi_spec_per_pin *per_pin;
 	int pinctl;
+	int err = 0;
 
 	if (hinfo->nid) {
 		pcm_idx = hinfo_to_pcm_index(codec, hinfo);
@@ -1954,14 +1963,12 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo,
 		snd_hda_spdif_ctls_unassign(codec, pcm_idx);
 		clear_bit(pcm_idx, &spec->pcm_in_use);
 		pin_idx = hinfo_to_pin_index(codec, hinfo);
-		if (spec->dyn_pcm_assign && pin_idx < 0) {
-			mutex_unlock(&spec->pcm_lock);
-			return 0;
-		}
+		if (spec->dyn_pcm_assign && pin_idx < 0)
+			goto unlock;
 
 		if (snd_BUG_ON(pin_idx < 0)) {
-			mutex_unlock(&spec->pcm_lock);
-			return -EINVAL;
+			err = -EINVAL;
+			goto unlock;
 		}
 		per_pin = get_pin(spec, pin_idx);
 
@@ -1980,10 +1987,11 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo,
 		per_pin->setup = false;
 		per_pin->channels = 0;
 		mutex_unlock(&per_pin->lock);
+	unlock:
 		mutex_unlock(&spec->pcm_lock);
 	}
 
-	return 0;
+	return err;
 }
 
 static const struct hda_pcm_ops generic_ops = {
@@ -2279,7 +2287,7 @@ static void generic_hdmi_free(struct hda_codec *codec)
 	int pin_idx, pcm_idx;
 
 	if (codec_has_acomp(codec))
-		snd_hdac_i915_register_notifier(NULL);
+		snd_hdac_acomp_register_notifier(&codec->bus->core, NULL);
 
 	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
@@ -2462,6 +2470,38 @@ static void haswell_set_power_state(struct hda_codec *codec, hda_nid_t fg,
 	snd_hda_codec_set_power_to_all(codec, fg, power_state);
 }
 
+/* There is a fixed mapping between audio pin node and display port.
+ * on SNB, IVY, HSW, BSW, SKL, BXT, KBL:
+ * Pin Widget 5 - PORT B (port = 1 in i915 driver)
+ * Pin Widget 6 - PORT C (port = 2 in i915 driver)
+ * Pin Widget 7 - PORT D (port = 3 in i915 driver)
+ *
+ * on VLV, ILK:
+ * Pin Widget 4 - PORT B (port = 1 in i915 driver)
+ * Pin Widget 5 - PORT C (port = 2 in i915 driver)
+ * Pin Widget 6 - PORT D (port = 3 in i915 driver)
+ */
+static int intel_base_nid(struct hda_codec *codec)
+{
+	switch (codec->core.vendor_id) {
+	case 0x80860054: /* ILK */
+	case 0x80862804: /* ILK */
+	case 0x80862882: /* VLV */
+		return 4;
+	default:
+		return 5;
+	}
+}
+
+static int intel_pin2port(void *audio_ptr, int pin_nid)
+{
+	int base_nid = intel_base_nid(audio_ptr);
+
+	if (WARN_ON(pin_nid < base_nid || pin_nid >= base_nid + 3))
+		return -1;
+	return pin_nid - base_nid + 1; /* intel port is 1-based */
+}
+
 static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe)
 {
 	struct hda_codec *codec = audio_ptr;
@@ -2472,16 +2512,7 @@ static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe)
 	if (port < 1 || port > 3)
 		return;
 
-	switch (codec->core.vendor_id) {
-	case 0x80860054: /* ILK */
-	case 0x80862804: /* ILK */
-	case 0x80862882: /* VLV */
-		pin_nid = port + 0x03;
-		break;
-	default:
-		pin_nid = port + 0x04;
-		break;
-	}
+	pin_nid = port + intel_base_nid(codec) - 1; /* intel port is 1-based */
 
 	/* skip notification during system suspend (but not in runtime PM);
 	 * the state will be updated at resume
@@ -2489,7 +2520,7 @@ static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe)
 	if (snd_power_get_state(codec->card) != SNDRV_CTL_POWER_D0)
 		return;
 	/* ditto during suspend/resume process itself */
-	if (atomic_read(&(codec)->core.in_pm))
+	if (snd_hdac_is_in_pm(&codec->core))
 		return;
 
 	snd_hdac_i915_set_bclk(&codec->bus->core);
@@ -2502,14 +2533,16 @@ static void register_i915_notifier(struct hda_codec *codec)
 	struct hdmi_spec *spec = codec->spec;
 
 	spec->use_acomp_notifier = true;
-	spec->i915_audio_ops.audio_ptr = codec;
+	spec->drm_audio_ops.audio_ptr = codec;
 	/* intel_audio_codec_enable() or intel_audio_codec_disable()
 	 * will call pin_eld_notify with using audio_ptr pointer
 	 * We need make sure audio_ptr is really setup
 	 */
 	wmb();
-	spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify;
-	snd_hdac_i915_register_notifier(&spec->i915_audio_ops);
+	spec->drm_audio_ops.pin2port = intel_pin2port;
+	spec->drm_audio_ops.pin_eld_notify = intel_pin_eld_notify;
+	snd_hdac_acomp_register_notifier(&codec->bus->core,
+					&spec->drm_audio_ops);
 }
 
 /* setup_stream ops override for HSW+ */
@@ -2542,6 +2575,8 @@ static int alloc_intel_hdmi(struct hda_codec *codec)
 	/* requires i915 binding */
 	if (!codec->bus->core.audio_component) {
 		codec_info(codec, "No i915 binding for Intel HDMI/DP codec\n");
+		/* set probe_id here to prevent generic fallback binding */
+		codec->probe_id = HDA_CODEC_ID_SKIP_PROBE;
 		return -ENODEV;
 	}
 
@@ -3741,6 +3776,11 @@ static int patch_atihdmi(struct hda_codec *codec)
 
 	spec->chmap.channels_max = max(spec->chmap.channels_max, 8u);
 
+	/* AMD GPUs have neither EPSS nor CLKSTOP bits, hence preventing
+	 * the link-down as is.  Tell the core to allow it.
+	 */
+	codec->link_down_at_suspend = 1;
+
 	return 0;
 }
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e9bd33ea538f..b20974ef1e13 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -43,11 +43,9 @@
 
 /* extra amp-initialization sequence types */
 enum {
+	ALC_INIT_UNDEFINED,
 	ALC_INIT_NONE,
 	ALC_INIT_DEFAULT,
-	ALC_INIT_GPIO1,
-	ALC_INIT_GPIO2,
-	ALC_INIT_GPIO3,
 };
 
 enum {
@@ -85,19 +83,20 @@ struct alc_spec {
 	struct hda_gen_spec gen; /* must be at head */
 
 	/* codec parameterization */
-	const struct snd_kcontrol_new *mixers[5];	/* mixer arrays */
-	unsigned int num_mixers;
-	unsigned int beep_amp;	/* beep amp value, set via set_beep_amp() */
-
 	struct alc_customize_define cdefine;
 	unsigned int parse_flags; /* flag for snd_hda_parse_pin_defcfg() */
 
+	/* GPIO bits */
+	unsigned int gpio_mask;
+	unsigned int gpio_dir;
+	unsigned int gpio_data;
+	bool gpio_write_delay;	/* add a delay before writing gpio_data */
+
 	/* mute LED for HP laptops, see alc269_fixup_mic_mute_hook() */
 	int mute_led_polarity;
 	hda_nid_t mute_led_nid;
 	hda_nid_t cap_mute_led_nid;
 
-	unsigned int gpio_led; /* used for alc269_fixup_hp_gpio_led() */
 	unsigned int gpio_mute_led_mask;
 	unsigned int gpio_mic_led_mask;
 
@@ -205,41 +204,87 @@ static void alc_process_coef_fw(struct hda_codec *codec,
 }
 
 /*
- * Append the given mixer and verb elements for the later use
- * The mixer array is referred in build_controls(), and init_verbs are
- * called in init().
+ * GPIO setup tables, used in initialization
  */
-static void add_mixer(struct alc_spec *spec, const struct snd_kcontrol_new *mix)
+
+/* Enable GPIO mask and set output */
+static void alc_setup_gpio(struct hda_codec *codec, unsigned int mask)
 {
-	if (snd_BUG_ON(spec->num_mixers >= ARRAY_SIZE(spec->mixers)))
+	struct alc_spec *spec = codec->spec;
+
+	spec->gpio_mask |= mask;
+	spec->gpio_dir |= mask;
+	spec->gpio_data |= mask;
+}
+
+static void alc_write_gpio_data(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+
+	snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
+			    spec->gpio_data);
+}
+
+static void alc_update_gpio_data(struct hda_codec *codec, unsigned int mask,
+				 bool on)
+{
+	struct alc_spec *spec = codec->spec;
+	unsigned int oldval = spec->gpio_data;
+
+	if (on)
+		spec->gpio_data |= mask;
+	else
+		spec->gpio_data &= ~mask;
+	if (oldval != spec->gpio_data)
+		alc_write_gpio_data(codec);
+}
+
+static void alc_write_gpio(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (!spec->gpio_mask)
 		return;
-	spec->mixers[spec->num_mixers++] = mix;
+
+	snd_hda_codec_write(codec, codec->core.afg, 0,
+			    AC_VERB_SET_GPIO_MASK, spec->gpio_mask);
+	snd_hda_codec_write(codec, codec->core.afg, 0,
+			    AC_VERB_SET_GPIO_DIRECTION, spec->gpio_dir);
+	if (spec->gpio_write_delay)
+		msleep(1);
+	alc_write_gpio_data(codec);
 }
 
-/*
- * GPIO setup tables, used in initialization
- */
-/* Enable GPIO mask and set output */
-static const struct hda_verb alc_gpio1_init_verbs[] = {
-	{0x01, AC_VERB_SET_GPIO_MASK, 0x01},
-	{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x01},
-	{0x01, AC_VERB_SET_GPIO_DATA, 0x01},
-	{ }
-};
+static void alc_fixup_gpio(struct hda_codec *codec, int action,
+			   unsigned int mask)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		alc_setup_gpio(codec, mask);
+}
 
-static const struct hda_verb alc_gpio2_init_verbs[] = {
-	{0x01, AC_VERB_SET_GPIO_MASK, 0x02},
-	{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x02},
-	{0x01, AC_VERB_SET_GPIO_DATA, 0x02},
-	{ }
-};
+static void alc_fixup_gpio1(struct hda_codec *codec,
+			    const struct hda_fixup *fix, int action)
+{
+	alc_fixup_gpio(codec, action, 0x01);
+}
 
-static const struct hda_verb alc_gpio3_init_verbs[] = {
-	{0x01, AC_VERB_SET_GPIO_MASK, 0x03},
-	{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x03},
-	{0x01, AC_VERB_SET_GPIO_DATA, 0x03},
-	{ }
-};
+static void alc_fixup_gpio2(struct hda_codec *codec,
+			    const struct hda_fixup *fix, int action)
+{
+	alc_fixup_gpio(codec, action, 0x02);
+}
+
+static void alc_fixup_gpio3(struct hda_codec *codec,
+			    const struct hda_fixup *fix, int action)
+{
+	alc_fixup_gpio(codec, action, 0x03);
+}
+
+static void alc_fixup_gpio4(struct hda_codec *codec,
+			    const struct hda_fixup *fix, int action)
+{
+	alc_fixup_gpio(codec, action, 0x04);
+}
 
 /*
  * Fix hardware PLL issue
@@ -447,16 +492,8 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type)
 {
 	alc_fill_eapd_coef(codec);
 	alc_auto_setup_eapd(codec, true);
+	alc_write_gpio(codec);
 	switch (type) {
-	case ALC_INIT_GPIO1:
-		snd_hda_sequence_write(codec, alc_gpio1_init_verbs);
-		break;
-	case ALC_INIT_GPIO2:
-		snd_hda_sequence_write(codec, alc_gpio2_init_verbs);
-		break;
-	case ALC_INIT_GPIO3:
-		snd_hda_sequence_write(codec, alc_gpio3_init_verbs);
-		break;
 	case ALC_INIT_DEFAULT:
 		switch (codec->core.vendor_id) {
 		case 0x10ec0260:
@@ -656,20 +693,22 @@ do_sku:
 	 * 7~6 : Reserved
 	*/
 	tmp = (ass & 0x38) >> 3;	/* external Amp control */
-	switch (tmp) {
-	case 1:
-		spec->init_amp = ALC_INIT_GPIO1;
-		break;
-	case 3:
-		spec->init_amp = ALC_INIT_GPIO2;
-		break;
-	case 7:
-		spec->init_amp = ALC_INIT_GPIO3;
-		break;
-	case 5:
-	default:
-		spec->init_amp = ALC_INIT_DEFAULT;
-		break;
+	if (spec->init_amp == ALC_INIT_UNDEFINED) {
+		switch (tmp) {
+		case 1:
+			alc_setup_gpio(codec, 0x01);
+			break;
+		case 3:
+			alc_setup_gpio(codec, 0x02);
+			break;
+		case 7:
+			alc_setup_gpio(codec, 0x03);
+			break;
+		case 5:
+		default:
+			spec->init_amp = ALC_INIT_DEFAULT;
+			break;
+		}
 	}
 
 	/* is laptop or Desktop and enable the function "Mute internal speaker
@@ -722,47 +761,14 @@ static void alc_fixup_inv_dmic(struct hda_codec *codec,
 }
 
 
-#ifdef CONFIG_SND_HDA_INPUT_BEEP
-/* additional beep mixers; the actual parameters are overwritten at build */
-static const struct snd_kcontrol_new alc_beep_mixer[] = {
-	HDA_CODEC_VOLUME("Beep Playback Volume", 0, 0, HDA_INPUT),
-	HDA_CODEC_MUTE_BEEP("Beep Playback Switch", 0, 0, HDA_INPUT),
-	{ } /* end */
-};
-#endif
-
 static int alc_build_controls(struct hda_codec *codec)
 {
-	struct alc_spec *spec = codec->spec;
-	int i, err;
+	int err;
 
 	err = snd_hda_gen_build_controls(codec);
 	if (err < 0)
 		return err;
 
-	for (i = 0; i < spec->num_mixers; i++) {
-		err = snd_hda_add_new_ctls(codec, spec->mixers[i]);
-		if (err < 0)
-			return err;
-	}
-
-#ifdef CONFIG_SND_HDA_INPUT_BEEP
-	/* create beep controls if needed */
-	if (spec->beep_amp) {
-		const struct snd_kcontrol_new *knew;
-		for (knew = alc_beep_mixer; knew->name; knew++) {
-			struct snd_kcontrol *kctl;
-			kctl = snd_ctl_new1(knew, codec);
-			if (!kctl)
-				return -ENOMEM;
-			kctl->private_value = spec->beep_amp;
-			err = snd_hda_ctl_add(codec, 0, kctl);
-			if (err < 0)
-				return err;
-		}
-	}
-#endif
-
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_BUILD);
 	return 0;
 }
@@ -973,8 +979,30 @@ static int alc_codec_rename_from_preset(struct hda_codec *codec)
  * Digital-beep handlers
  */
 #ifdef CONFIG_SND_HDA_INPUT_BEEP
-#define set_beep_amp(spec, nid, idx, dir) \
-	((spec)->beep_amp = HDA_COMPOSE_AMP_VAL(nid, 3, idx, dir))
+
+/* additional beep mixers; private_value will be overwritten */
+static const struct snd_kcontrol_new alc_beep_mixer[] = {
+	HDA_CODEC_VOLUME("Beep Playback Volume", 0, 0, HDA_INPUT),
+	HDA_CODEC_MUTE_BEEP("Beep Playback Switch", 0, 0, HDA_INPUT),
+};
+
+/* set up and create beep controls */
+static int set_beep_amp(struct alc_spec *spec, hda_nid_t nid,
+			int idx, int dir)
+{
+	struct snd_kcontrol_new *knew;
+	unsigned int beep_amp = HDA_COMPOSE_AMP_VAL(nid, 3, idx, dir);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(alc_beep_mixer); i++) {
+		knew = snd_hda_gen_add_kctl(&spec->gen, NULL,
+					    &alc_beep_mixer[i]);
+		if (!knew)
+			return -ENOMEM;
+		knew->private_value = beep_amp;
+	}
+	return 0;
+}
 
 static const struct snd_pci_quirk beep_white_list[] = {
 	SND_PCI_QUIRK(0x1043, 0x103c, "ASUS", 1),
@@ -999,7 +1027,7 @@ static inline int has_cdefine_beep(struct hda_codec *codec)
 	return spec->cdefine.enable_pcbeep;
 }
 #else
-#define set_beep_amp(spec, nid, idx, dir) /* NOP */
+#define set_beep_amp(spec, nid, idx, dir)	0
 #define has_cdefine_beep(codec)		0
 #endif
 
@@ -1104,12 +1132,12 @@ static void alc880_fixup_vol_knob(struct hda_codec *codec,
 
 static const struct hda_fixup alc880_fixups[] = {
 	[ALC880_FIXUP_GPIO1] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio1_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio1,
 	},
 	[ALC880_FIXUP_GPIO2] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio2_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio2,
 	},
 	[ALC880_FIXUP_MEDION_RIM] = {
 		.type = HDA_FIXUP_VERBS,
@@ -1501,8 +1529,11 @@ static int patch_alc880(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog)
-		set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog) {
+		err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -1544,8 +1575,8 @@ enum {
 static void alc260_gpio1_automute(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
-	snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
-			    spec->gen.hp_jack_present);
+
+	alc_update_gpio_data(codec, 0x01, spec->gen.hp_jack_present);
 }
 
 static void alc260_fixup_gpio1_toggle(struct hda_codec *codec,
@@ -1562,7 +1593,7 @@ static void alc260_fixup_gpio1_toggle(struct hda_codec *codec,
 		spec->gen.autocfg.hp_pins[0] = 0x0f; /* copy it for automute */
 		snd_hda_jack_detect_enable_callback(codec, 0x0f,
 						    snd_hda_gen_hp_automute);
-		snd_hda_add_verbs(codec, alc_gpio1_init_verbs);
+		alc_setup_gpio(codec, 0x01);
 	}
 }
 
@@ -1589,8 +1620,6 @@ static void alc260_fixup_kn1(struct hda_codec *codec,
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
 		snd_hda_apply_pincfgs(codec, pincfgs);
-		break;
-	case HDA_FIXUP_ACT_PROBE:
 		spec->init_amp = ALC_INIT_NONE;
 		break;
 	}
@@ -1600,7 +1629,7 @@ static void alc260_fixup_fsc_s7020(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	if (action == HDA_FIXUP_ACT_PROBE)
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
 		spec->init_amp = ALC_INIT_NONE;
 }
 
@@ -1638,8 +1667,8 @@ static const struct hda_fixup alc260_fixups[] = {
 		},
 	},
 	[ALC260_FIXUP_GPIO1] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio1_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio1,
 	},
 	[ALC260_FIXUP_GPIO1_TOGGLE] = {
 		.type = HDA_FIXUP_FUNC,
@@ -1751,8 +1780,11 @@ static int patch_alc260(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog)
-		set_beep_amp(spec, 0x07, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog) {
+		err = set_beep_amp(spec, 0x07, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -1824,47 +1856,14 @@ static void alc889_fixup_coef(struct hda_codec *codec,
 	alc_update_coef_idx(codec, 7, 0, 0x2030);
 }
 
-/* toggle speaker-output according to the hp-jack state */
-static void alc882_gpio_mute(struct hda_codec *codec, int pin, int muted)
-{
-	unsigned int gpiostate, gpiomask, gpiodir;
-
-	gpiostate = snd_hda_codec_read(codec, codec->core.afg, 0,
-				       AC_VERB_GET_GPIO_DATA, 0);
-
-	if (!muted)
-		gpiostate |= (1 << pin);
-	else
-		gpiostate &= ~(1 << pin);
-
-	gpiomask = snd_hda_codec_read(codec, codec->core.afg, 0,
-				      AC_VERB_GET_GPIO_MASK, 0);
-	gpiomask |= (1 << pin);
-
-	gpiodir = snd_hda_codec_read(codec, codec->core.afg, 0,
-				     AC_VERB_GET_GPIO_DIRECTION, 0);
-	gpiodir |= (1 << pin);
-
-
-	snd_hda_codec_write(codec, codec->core.afg, 0,
-			    AC_VERB_SET_GPIO_MASK, gpiomask);
-	snd_hda_codec_write(codec, codec->core.afg, 0,
-			    AC_VERB_SET_GPIO_DIRECTION, gpiodir);
-
-	msleep(1);
-
-	snd_hda_codec_write(codec, codec->core.afg, 0,
-			    AC_VERB_SET_GPIO_DATA, gpiostate);
-}
-
 /* set up GPIO at initialization */
 static void alc885_fixup_macpro_gpio(struct hda_codec *codec,
 				     const struct hda_fixup *fix, int action)
 {
-	if (action != HDA_FIXUP_ACT_INIT)
-		return;
-	alc882_gpio_mute(codec, 0, 0);
-	alc882_gpio_mute(codec, 1, 0);
+	struct alc_spec *spec = codec->spec;
+
+	spec->gpio_write_delay = true;
+	alc_fixup_gpio3(codec, fix, action);
 }
 
 /* Fix the connection of some pins for ALC889:
@@ -2143,20 +2142,20 @@ static const struct hda_fixup alc882_fixups[] = {
 		}
 	},
 	[ALC882_FIXUP_GPIO1] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio1_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio1,
 	},
 	[ALC882_FIXUP_GPIO2] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio2_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio2,
 	},
 	[ALC882_FIXUP_GPIO3] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio3_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio3,
 	},
 	[ALC882_FIXUP_ASUS_W2JC] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio1_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio1,
 		.chained = true,
 		.chain_id = ALC882_FIXUP_EAPD,
 	},
@@ -2366,6 +2365,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
 	SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
 	SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
@@ -2375,12 +2375,37 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 };
 
 static const struct hda_model_fixup alc882_fixup_models[] = {
+	{.id = ALC882_FIXUP_ABIT_AW9D_MAX, .name = "abit-aw9d"},
+	{.id = ALC882_FIXUP_LENOVO_Y530, .name = "lenovo-y530"},
+	{.id = ALC882_FIXUP_ACER_ASPIRE_7736, .name = "acer-aspire-7736"},
+	{.id = ALC882_FIXUP_ASUS_W90V, .name = "asus-w90v"},
+	{.id = ALC889_FIXUP_CD, .name = "cd"},
+	{.id = ALC889_FIXUP_FRONT_HP_NO_PRESENCE, .name = "no-front-hp"},
+	{.id = ALC889_FIXUP_VAIO_TT, .name = "vaio-tt"},
+	{.id = ALC888_FIXUP_EEE1601, .name = "eee1601"},
+	{.id = ALC882_FIXUP_EAPD, .name = "alc882-eapd"},
+	{.id = ALC883_FIXUP_EAPD, .name = "alc883-eapd"},
+	{.id = ALC882_FIXUP_GPIO1, .name = "gpio1"},
+	{.id = ALC882_FIXUP_GPIO2, .name = "gpio2"},
+	{.id = ALC882_FIXUP_GPIO3, .name = "gpio3"},
+	{.id = ALC889_FIXUP_COEF, .name = "alc889-coef"},
+	{.id = ALC882_FIXUP_ASUS_W2JC, .name = "asus-w2jc"},
 	{.id = ALC882_FIXUP_ACER_ASPIRE_4930G, .name = "acer-aspire-4930g"},
 	{.id = ALC882_FIXUP_ACER_ASPIRE_8930G, .name = "acer-aspire-8930g"},
 	{.id = ALC883_FIXUP_ACER_EAPD, .name = "acer-aspire"},
+	{.id = ALC885_FIXUP_MACPRO_GPIO, .name = "macpro-gpio"},
+	{.id = ALC889_FIXUP_DAC_ROUTE, .name = "dac-route"},
+	{.id = ALC889_FIXUP_MBP_VREF, .name = "mbp-vref"},
+	{.id = ALC889_FIXUP_IMAC91_VREF, .name = "imac91-vref"},
+	{.id = ALC889_FIXUP_MBA11_VREF, .name = "mba11-vref"},
+	{.id = ALC889_FIXUP_MBA21_VREF, .name = "mba21-vref"},
+	{.id = ALC889_FIXUP_MP11_VREF, .name = "mp11-vref"},
+	{.id = ALC889_FIXUP_MP41_VREF, .name = "mp41-vref"},
 	{.id = ALC882_FIXUP_INV_DMIC, .name = "inv-dmic"},
 	{.id = ALC882_FIXUP_NO_PRIMARY_HP, .name = "no-primary-hp"},
+	{.id = ALC887_FIXUP_ASUS_BASS, .name = "asus-bass"},
 	{.id = ALC1220_FIXUP_GB_DUAL_CODECS, .name = "dual-codecs"},
+	{.id = ALC1220_FIXUP_CLEVO_P950, .name = "clevo-p950"},
 	{}
 };
 
@@ -2434,8 +2459,11 @@ static int patch_alc882(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog && spec->gen.beep_nid)
-		set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog && spec->gen.beep_nid) {
+		err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -2545,6 +2573,7 @@ static const struct snd_pci_quirk alc262_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x10cf, 0x1397, "Fujitsu Lifebook S7110", ALC262_FIXUP_FSC_S7110),
 	SND_PCI_QUIRK(0x10cf, 0x142d, "Fujitsu Lifebook E8410", ALC262_FIXUP_BENQ),
 	SND_PCI_QUIRK(0x10f1, 0x2915, "Tyan Thunder n6650W", ALC262_FIXUP_TYAN),
+	SND_PCI_QUIRK(0x1734, 0x1141, "FSC ESPRIMO U9210", ALC262_FIXUP_FSC_H270),
 	SND_PCI_QUIRK(0x1734, 0x1147, "FSC Celsius H270", ALC262_FIXUP_FSC_H270),
 	SND_PCI_QUIRK(0x17aa, 0x384e, "Lenovo 3000", ALC262_FIXUP_LENOVO_3000),
 	SND_PCI_QUIRK(0x17ff, 0x0560, "Benq ED8", ALC262_FIXUP_BENQ),
@@ -2555,6 +2584,14 @@ static const struct snd_pci_quirk alc262_fixup_tbl[] = {
 
 static const struct hda_model_fixup alc262_fixup_models[] = {
 	{.id = ALC262_FIXUP_INV_DMIC, .name = "inv-dmic"},
+	{.id = ALC262_FIXUP_FSC_H270, .name = "fsc-h270"},
+	{.id = ALC262_FIXUP_FSC_S7110, .name = "fsc-s7110"},
+	{.id = ALC262_FIXUP_HP_Z200, .name = "hp-z200"},
+	{.id = ALC262_FIXUP_TYAN, .name = "tyan"},
+	{.id = ALC262_FIXUP_LENOVO_3000, .name = "lenovo-3000"},
+	{.id = ALC262_FIXUP_BENQ, .name = "benq"},
+	{.id = ALC262_FIXUP_BENQ_T31, .name = "benq-t31"},
+	{.id = ALC262_FIXUP_INTEL_BAYLEYBAY, .name = "bayleybay"},
 	{}
 };
 
@@ -2596,8 +2633,11 @@ static int patch_alc262(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog && spec->gen.beep_nid)
-		set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog && spec->gen.beep_nid) {
+		err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -2643,7 +2683,6 @@ static const struct snd_kcontrol_new alc268_beep_mixer[] = {
 		.put = alc268_beep_switch_put,
 		.private_value = HDA_COMPOSE_AMP_VAL(0x0f, 3, 1, HDA_INPUT)
 	},
-	{ }
 };
 
 /* set PCBEEP vol = 0, mute connections */
@@ -2684,6 +2723,7 @@ static const struct hda_fixup alc268_fixups[] = {
 static const struct hda_model_fixup alc268_fixup_models[] = {
 	{.id = ALC268_FIXUP_INV_DMIC, .name = "inv-dmic"},
 	{.id = ALC268_FIXUP_HP_EAPD, .name = "hp-eapd"},
+	{.id = ALC268_FIXUP_SPDIF, .name = "spdif"},
 	{}
 };
 
@@ -2711,7 +2751,7 @@ static int alc268_parse_auto_config(struct hda_codec *codec)
 static int patch_alc268(struct hda_codec *codec)
 {
 	struct alc_spec *spec;
-	int err;
+	int i, err;
 
 	/* ALC268 has no aa-loopback mixer */
 	err = alc_alloc_spec(codec, 0);
@@ -2733,7 +2773,13 @@ static int patch_alc268(struct hda_codec *codec)
 
 	if (err > 0 && !spec->gen.no_analog &&
 	    spec->gen.autocfg.speaker_pins[0] != 0x1d) {
-		add_mixer(spec, alc268_beep_mixer);
+		for (i = 0; i < ARRAY_SIZE(alc268_beep_mixer); i++) {
+			if (!snd_hda_gen_add_kctl(&spec->gen, NULL,
+						  &alc268_beep_mixer[i])) {
+				err = -ENOMEM;
+				goto error;
+			}
+		}
 		snd_hda_add_verbs(codec, alc268_beep_init_verbs);
 		if (!query_amp_caps(codec, 0x1d, HDA_INPUT))
 			/* override the amp caps for beep generator */
@@ -3452,9 +3498,8 @@ static int alc269_resume(struct hda_codec *codec)
 	 * suspend, and won't restore the data after resume, so we restore it
 	 * in the driver.
 	 */
-	if (spec->gpio_led)
-		snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_DATA,
-			    spec->gpio_led);
+	if (spec->gpio_data)
+		alc_write_gpio_data(codec);
 
 	if (spec->has_alc5505_dsp)
 		alc5505_dsp_resume(codec);
@@ -3694,18 +3739,10 @@ static void alc_update_gpio_led(struct hda_codec *codec, unsigned int mask,
 				bool enabled)
 {
 	struct alc_spec *spec = codec->spec;
-	unsigned int oldval = spec->gpio_led;
 
 	if (spec->mute_led_polarity)
 		enabled = !enabled;
-
-	if (enabled)
-		spec->gpio_led &= ~mask;
-	else
-		spec->gpio_led |= mask;
-	if (spec->gpio_led != oldval)
-		snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
-				    spec->gpio_led);
+	alc_update_gpio_data(codec, mask, !enabled); /* muted -> LED on */
 }
 
 /* turn on/off mute LED via GPIO per vmaster hook */
@@ -3718,104 +3755,79 @@ static void alc_fixup_gpio_mute_hook(void *private_data, int enabled)
 }
 
 /* turn on/off mic-mute LED via GPIO per capture hook */
-static void alc_fixup_gpio_mic_mute_hook(struct hda_codec *codec,
-					 struct snd_kcontrol *kcontrol,
-					 struct snd_ctl_elem_value *ucontrol)
+static void alc_gpio_micmute_update(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
 
-	if (ucontrol)
-		alc_update_gpio_led(codec, spec->gpio_mic_led_mask,
-				    ucontrol->value.integer.value[0] ||
-				    ucontrol->value.integer.value[1]);
+	alc_update_gpio_led(codec, spec->gpio_mic_led_mask,
+			    spec->gen.micmute_led.led_value);
 }
 
-static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
-				const struct hda_fixup *fix, int action)
+/* setup mute and mic-mute GPIO bits, add hooks appropriately */
+static void alc_fixup_hp_gpio_led(struct hda_codec *codec,
+				  int action,
+				  unsigned int mute_mask,
+				  unsigned int micmute_mask)
 {
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x18 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x18 },
-		{}
-	};
 
-	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+	alc_fixup_gpio(codec, action, mute_mask | micmute_mask);
+
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+	if (mute_mask) {
+		spec->gpio_mute_led_mask = mute_mask;
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook;
-		spec->gpio_led = 0;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
-		spec->gpio_mic_led_mask = 0x10;
-		snd_hda_add_verbs(codec, gpio_init);
+	}
+	if (micmute_mask) {
+		spec->gpio_mic_led_mask = micmute_mask;
+		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
 	}
 }
 
-static void alc286_fixup_hp_gpio_led(struct hda_codec *codec,
+static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
-	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x22 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x22 },
-		{}
-	};
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0x10);
+}
 
-	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook;
-		spec->gpio_led = 0;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x02;
-		spec->gpio_mic_led_mask = 0x20;
-		snd_hda_add_verbs(codec, gpio_init);
-	}
+static void alc286_fixup_hp_gpio_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	alc_fixup_hp_gpio_led(codec, action, 0x02, 0x20);
 }
 
 /* turn on/off mic-mute LED per capture hook */
-static void alc269_fixup_hp_cap_mic_mute_hook(struct hda_codec *codec,
-					       struct snd_kcontrol *kcontrol,
-					       struct snd_ctl_elem_value *ucontrol)
+static void alc_cap_micmute_update(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
-	unsigned int pinval, enable, disable;
+	unsigned int pinval;
 
+	if (!spec->cap_mute_led_nid)
+		return;
 	pinval = snd_hda_codec_get_pin_target(codec, spec->cap_mute_led_nid);
 	pinval &= ~AC_PINCTL_VREFEN;
-	enable  = pinval | AC_PINCTL_VREF_80;
-	disable = pinval | AC_PINCTL_VREF_HIZ;
-
-	if (!ucontrol)
-		return;
-
-	if (ucontrol->value.integer.value[0] ||
-	    ucontrol->value.integer.value[1])
-		pinval = disable;
+	if (spec->gen.micmute_led.led_value)
+		pinval |= AC_PINCTL_VREF_80;
 	else
-		pinval = enable;
-
-	if (spec->cap_mute_led_nid)
-		snd_hda_set_pin_ctl_cache(codec, spec->cap_mute_led_nid, pinval);
+		pinval |= AC_PINCTL_VREF_HIZ;
+	snd_hda_set_pin_ctl_cache(codec, spec->cap_mute_led_nid, pinval);
 }
 
 static void alc269_fixup_hp_gpio_mic1_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x08 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x08 },
-		{}
-	};
 
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc269_fixup_hp_cap_mic_mute_hook;
-		spec->gpio_led = 0;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
+		/* Like hp_gpio_mic1_led, but also needs GPIO4 low to
+		 * enable headphone amp
+		 */
+		spec->gpio_mask |= 0x10;
+		spec->gpio_dir |= 0x10;
 		spec->cap_mute_led_nid = 0x18;
-		snd_hda_add_verbs(codec, gpio_init);
+		snd_hda_gen_add_micmute_led(codec, alc_cap_micmute_update);
 		codec->power_filter = led_power_filter;
 	}
 }
@@ -3823,22 +3835,12 @@ static void alc269_fixup_hp_gpio_mic1_led(struct hda_codec *codec,
 static void alc280_fixup_hp_gpio4(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
-	/* Like hp_gpio_mic1_led, but also needs GPIO4 low to enable headphone amp */
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x18 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x18 },
-		{}
-	};
 
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc269_fixup_hp_cap_mic_mute_hook;
-		spec->gpio_led = 0;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
 		spec->cap_mute_led_nid = 0x18;
-		snd_hda_add_verbs(codec, gpio_init);
+		snd_hda_gen_add_micmute_led(codec, alc_cap_micmute_update);
 		codec->power_filter = led_power_filter;
 	}
 }
@@ -3888,38 +3890,29 @@ static int alc_register_micmute_input_device(struct hda_codec *codec)
 	return 0;
 }
 
+/* GPIO1 = set according to SKU external amp
+ * GPIO2 = mic mute hotkey
+ * GPIO3 = mute LED
+ * GPIO4 = mic mute LED
+ */
 static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec,
 					     const struct hda_fixup *fix, int action)
 {
-	/* GPIO1 = set according to SKU external amp
-	   GPIO2 = mic mute hotkey
-	   GPIO3 = mute LED
-	   GPIO4 = mic mute LED */
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x1e },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x1a },
-		{ 0x01, AC_VERB_SET_GPIO_DATA, 0x02 },
-		{}
-	};
-
 	struct alc_spec *spec = codec->spec;
 
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0x10);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->init_amp = ALC_INIT_DEFAULT;
 		if (alc_register_micmute_input_device(codec) != 0)
 			return;
 
-		snd_hda_add_verbs(codec, gpio_init);
+		spec->gpio_mask |= 0x06;
+		spec->gpio_dir |= 0x02;
+		spec->gpio_data |= 0x02;
 		snd_hda_codec_write_cache(codec, codec->core.afg, 0,
 					  AC_VERB_SET_GPIO_UNSOLICITED_RSP_MASK, 0x04);
 		snd_hda_jack_detect_enable_callback(codec, codec->core.afg,
 						    gpio2_mic_hotkey_event);
-
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook;
-		spec->gpio_led = 0;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
-		spec->gpio_mic_led_mask = 0x10;
 		return;
 	}
 
@@ -3927,40 +3920,28 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec,
 		return;
 
 	switch (action) {
-	case HDA_FIXUP_ACT_PROBE:
-		spec->init_amp = ALC_INIT_DEFAULT;
-		break;
 	case HDA_FIXUP_ACT_FREE:
 		input_unregister_device(spec->kb_dev);
 		spec->kb_dev = NULL;
 	}
 }
 
+/* Line2 = mic mute hotkey
+ * GPIO2 = mic mute LED
+ */
 static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 					     const struct hda_fixup *fix, int action)
 {
-	/* Line2 = mic mute hotkey
-	   GPIO2 = mic mute LED */
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x04 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 },
-		{}
-	};
-
 	struct alc_spec *spec = codec->spec;
 
+	alc_fixup_hp_gpio_led(codec, action, 0, 0x04);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->init_amp = ALC_INIT_DEFAULT;
 		if (alc_register_micmute_input_device(codec) != 0)
 			return;
 
-		snd_hda_add_verbs(codec, gpio_init);
 		snd_hda_jack_detect_enable_callback(codec, 0x1b,
 						    gpio2_mic_hotkey_event);
-
-		spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook;
-		spec->gpio_led = 0;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mic_led_mask = 0x04;
 		return;
 	}
 
@@ -3968,9 +3949,6 @@ static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 		return;
 
 	switch (action) {
-	case HDA_FIXUP_ACT_PROBE:
-		spec->init_amp = ALC_INIT_DEFAULT;
-		break;
 	case HDA_FIXUP_ACT_FREE:
 		input_unregister_device(spec->kb_dev);
 		spec->kb_dev = NULL;
@@ -3986,14 +3964,10 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 {
 	struct alc_spec *spec = codec->spec;
 
+	alc269_fixup_hp_mute_led_micx(codec, fix, action, 0x1a);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
-		spec->gen.cap_sync_hook = alc269_fixup_hp_cap_mic_mute_hook;
-		spec->mute_led_polarity = 0;
-		spec->mute_led_nid = 0x1a;
 		spec->cap_mute_led_nid = 0x18;
-		spec->gen.vmaster_mute_enum = 1;
-		codec->power_filter = led_power_filter;
+		snd_hda_gen_add_micmute_led(codec, alc_cap_micmute_update);
 	}
 }
 
@@ -4841,6 +4815,7 @@ static void alc_probe_headset_mode(struct hda_codec *codec)
 			spec->headphone_mic_pin = cfg->inputs[i].pin;
 	}
 
+	WARN_ON(spec->gen.cap_sync_hook);
 	spec->gen.cap_sync_hook = alc_update_headset_mode_hook;
 	spec->gen.automute_hook = alc_update_headset_mode;
 	spec->gen.hp_automute_hook = alc_update_headset_jack_cb;
@@ -4932,13 +4907,10 @@ static void alc288_update_headset_jack_cb(struct hda_codec *codec,
 				       struct hda_jack_callback *jack)
 {
 	struct alc_spec *spec = codec->spec;
-	int present;
 
 	alc_update_headset_jack_cb(codec, jack);
 	/* Headset Mic enable or disable, only for Dell Dino */
-	present = spec->gen.hp_jack_present ? 0x40 : 0;
-	snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
-				present);
+	alc_update_gpio_data(codec, 0x40, spec->gen.hp_jack_present);
 }
 
 static void alc_fixup_headset_mode_dell_alc288(struct hda_codec *codec,
@@ -4947,6 +4919,9 @@ static void alc_fixup_headset_mode_dell_alc288(struct hda_codec *codec,
 	alc_fixup_headset_mode(codec, fix, action);
 	if (action == HDA_FIXUP_ACT_PROBE) {
 		struct alc_spec *spec = codec->spec;
+		/* toggled via hp_automute_hook */
+		spec->gpio_mask |= 0x40;
+		spec->gpio_dir |= 0x40;
 		spec->gen.hp_automute_hook = alc288_update_headset_jack_cb;
 	}
 }
@@ -4967,7 +4942,7 @@ static void alc_no_shutup(struct hda_codec *codec)
 static void alc_fixup_no_shutup(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
-	if (action == HDA_FIXUP_ACT_PROBE) {
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		struct alc_spec *spec = codec->spec;
 		spec->shutup = alc_no_shutup;
 	}
@@ -4995,7 +4970,6 @@ static void alc_fixup_tpt440_dock(struct hda_codec *codec,
 	struct alc_spec *spec = codec->spec;
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->shutup = alc_no_shutup; /* reduce click noise */
 		spec->reboot_notify = alc_d3_at_reboot; /* reduce noise */
 		spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP;
 		codec->power_save_node = 0; /* avoid click noises */
@@ -5050,10 +5024,9 @@ static void alc_fixup_dell_xps13(struct hda_codec *codec,
 		 * it causes a click noise at start up
 		 */
 		snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ);
+		spec->shutup = alc_shutup_dell_xps13;
 		break;
 	case HDA_FIXUP_ACT_PROBE:
-		spec->shutup = alc_shutup_dell_xps13;
-
 		/* Make the internal mic the default input source. */
 		for (i = 0; i < imux->num_items; i++) {
 			if (spec->gen.imux_pins[i] == 0x12) {
@@ -5230,13 +5203,6 @@ static void alc282_fixup_asus_tx300(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	/* TX300 needs to set up GPIO2 for the speaker amp */
-	static const struct hda_verb gpio2_verbs[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x04 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 },
-		{ 0x01, AC_VERB_SET_GPIO_DATA, 0x04 },
-		{}
-	};
 	static const struct hda_pintbl dock_pins[] = {
 		{ 0x1b, 0x21114000 }, /* dock speaker pin */
 		{}
@@ -5244,13 +5210,18 @@ static void alc282_fixup_asus_tx300(struct hda_codec *codec,
 
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
-		snd_hda_add_verbs(codec, gpio2_verbs);
+		spec->init_amp = ALC_INIT_DEFAULT;
+		/* TX300 needs to set up GPIO2 for the speaker amp */
+		alc_setup_gpio(codec, 0x04);
 		snd_hda_apply_pincfgs(codec, dock_pins);
 		spec->gen.auto_mute_via_amp = 1;
 		spec->gen.automute_hook = asus_tx300_automute;
 		snd_hda_jack_detect_enable_callback(codec, 0x1b,
 						    snd_hda_gen_hp_automute);
 		break;
+	case HDA_FIXUP_ACT_PROBE:
+		spec->init_amp = ALC_INIT_DEFAULT;
+		break;
 	case HDA_FIXUP_ACT_BUILD:
 		/* this is a bit tricky; give more sane names for the main
 		 * (tablet) speaker and the dock speaker, respectively
@@ -5324,30 +5295,26 @@ static void alc280_fixup_hp_9480m(struct hda_codec *codec,
 				  int action)
 {
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x18 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x18 },
-		{}
-	};
 
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		/* Set the hooks to turn the headphone amp on/off
-		 * as needed
-		 */
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
+		/* amp at GPIO4; toggled via alc280_hp_gpio4_automute_hook() */
+		spec->gpio_mask |= 0x10;
+		spec->gpio_dir |= 0x10;
 		spec->gen.hp_automute_hook = alc280_hp_gpio4_automute_hook;
+	}
+}
 
-		/* The GPIOs are currently off */
-		spec->gpio_led = 0;
-
-		/* GPIO3 is connected to the output mute LED,
-		 * high is on, low is off
-		 */
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
+static void alc275_fixup_gpio4_off(struct hda_codec *codec,
+				   const struct hda_fixup *fix,
+				   int action)
+{
+	struct alc_spec *spec = codec->spec;
 
-		/* Initialize GPIO configuration */
-		snd_hda_add_verbs(codec, gpio_init);
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->gpio_mask |= 0x04;
+		spec->gpio_dir |= 0x04;
+		/* set data bit low */
 	}
 }
 
@@ -5394,6 +5361,13 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec,
 /* for hda_fixup_thinkpad_acpi() */
 #include "thinkpad_helper.c"
 
+static void alc_fixup_thinkpad_acpi(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	alc_fixup_no_shutup(codec, fix, action); /* reduce click noise */
+	hda_fixup_thinkpad_acpi(codec, fix, action);
+}
+
 /* for dell wmi mic mute led */
 #include "dell_wmi_helper.c"
 
@@ -5484,7 +5458,6 @@ enum {
 	ALC280_FIXUP_HP_9480M,
 	ALC288_FIXUP_DELL_HEADSET_MODE,
 	ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
-	ALC288_FIXUP_DELL_XPS_13_GPIO6,
 	ALC288_FIXUP_DELL_XPS_13,
 	ALC288_FIXUP_DISABLE_AAMIX,
 	ALC292_FIXUP_DELL_E7X,
@@ -5532,13 +5505,8 @@ static const struct hda_fixup alc269_fixups[] = {
 		}
 	},
 	[ALC275_FIXUP_SONY_VAIO_GPIO2] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = (const struct hda_verb[]) {
-			{0x01, AC_VERB_SET_GPIO_MASK, 0x04},
-			{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04},
-			{0x01, AC_VERB_SET_GPIO_DATA, 0x00},
-			{ }
-		},
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc275_fixup_gpio4_off,
 		.chained = true,
 		.chain_id = ALC269_FIXUP_SONY_VAIO
 	},
@@ -5946,7 +5914,7 @@ static const struct hda_fixup alc269_fixups[] = {
 	},
 	[ALC269_FIXUP_THINKPAD_ACPI] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = hda_fixup_thinkpad_acpi,
+		.v.func = alc_fixup_thinkpad_acpi,
 		.chained = true,
 		.chain_id = ALC269_FIXUP_SKU_IGNORE,
 	},
@@ -6105,22 +6073,11 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC288_FIXUP_DELL_HEADSET_MODE
 	},
-	[ALC288_FIXUP_DELL_XPS_13_GPIO6] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = (const struct hda_verb[]) {
-			{0x01, AC_VERB_SET_GPIO_MASK, 0x40},
-			{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x40},
-			{0x01, AC_VERB_SET_GPIO_DATA, 0x00},
-			{ }
-		},
-		.chained = true,
-		.chain_id = ALC288_FIXUP_DELL1_MIC_NO_PRESENCE
-	},
 	[ALC288_FIXUP_DISABLE_AAMIX] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_disable_aamix,
 		.chained = true,
-		.chain_id = ALC288_FIXUP_DELL_XPS_13_GPIO6
+		.chain_id = ALC288_FIXUP_DELL1_MIC_NO_PRESENCE
 	},
 	[ALC288_FIXUP_DELL_XPS_13] = {
 		.type = HDA_FIXUP_FUNC,
@@ -6283,14 +6240,9 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
 	},
 	[ALC256_FIXUP_ASUS_AIO_GPIO2] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = (const struct hda_verb[]) {
-			/* Set up GPIO2 for the speaker amp */
-			{ 0x01, AC_VERB_SET_GPIO_MASK, 0x04 },
-			{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 },
-			{ 0x01, AC_VERB_SET_GPIO_DATA, 0x04 },
-			{}
-		},
+		.type = HDA_FIXUP_FUNC,
+		/* Set up GPIO2 for the speaker amp */
+		.v.func = alc_fixup_gpio4,
 	},
 	[ALC233_FIXUP_ASUS_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
@@ -6522,6 +6474,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360),
 	SND_PCI_QUIRK(0x103c, 0x82bf, "HP", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x82c0, "HP", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -6562,6 +6515,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC),
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
+	SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
@@ -6603,8 +6557,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+	SND_PCI_QUIRK(0x17aa, 0x312a, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
-	SND_PCI_QUIRK(0x17aa, 0x3138, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
@@ -6704,13 +6658,95 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"},
 	{.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
 	{.id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "dell-headset-dock"},
+	{.id = ALC269_FIXUP_DELL3_MIC_NO_PRESENCE, .name = "dell-headset3"},
+	{.id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, .name = "dell-headset4"},
 	{.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"},
 	{.id = ALC283_FIXUP_SENSE_COMBO_JACK, .name = "alc283-sense-combo"},
 	{.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"},
 	{.id = ALC292_FIXUP_TPT440, .name = "tpt440"},
 	{.id = ALC292_FIXUP_TPT460, .name = "tpt460"},
+	{.id = ALC298_FIXUP_TPT470_DOCK, .name = "tpt470-dock"},
 	{.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
 	{.id = ALC700_FIXUP_INTEL_REFERENCE, .name = "alc700-ref"},
+	{.id = ALC269_FIXUP_SONY_VAIO, .name = "vaio"},
+	{.id = ALC269_FIXUP_DELL_M101Z, .name = "dell-m101z"},
+	{.id = ALC269_FIXUP_ASUS_G73JW, .name = "asus-g73jw"},
+	{.id = ALC269_FIXUP_LENOVO_EAPD, .name = "lenovo-eapd"},
+	{.id = ALC275_FIXUP_SONY_HWEQ, .name = "sony-hweq"},
+	{.id = ALC269_FIXUP_PCM_44K, .name = "pcm44k"},
+	{.id = ALC269_FIXUP_LIFEBOOK, .name = "lifebook"},
+	{.id = ALC269_FIXUP_LIFEBOOK_EXTMIC, .name = "lifebook-extmic"},
+	{.id = ALC269_FIXUP_LIFEBOOK_HP_PIN, .name = "lifebook-hp-pin"},
+	{.id = ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC, .name = "lifebook-u7x7"},
+	{.id = ALC269VB_FIXUP_AMIC, .name = "alc269vb-amic"},
+	{.id = ALC269VB_FIXUP_DMIC, .name = "alc269vb-dmic"},
+	{.id = ALC269_FIXUP_HP_MUTE_LED_MIC1, .name = "hp-mute-led-mic1"},
+	{.id = ALC269_FIXUP_HP_MUTE_LED_MIC2, .name = "hp-mute-led-mic2"},
+	{.id = ALC269_FIXUP_HP_MUTE_LED_MIC3, .name = "hp-mute-led-mic3"},
+	{.id = ALC269_FIXUP_HP_GPIO_MIC1_LED, .name = "hp-gpio-mic1"},
+	{.id = ALC269_FIXUP_HP_LINE1_MIC1_LED, .name = "hp-line1-mic1"},
+	{.id = ALC269_FIXUP_NO_SHUTUP, .name = "noshutup"},
+	{.id = ALC286_FIXUP_SONY_MIC_NO_PRESENCE, .name = "sony-nomic"},
+	{.id = ALC269_FIXUP_ASPIRE_HEADSET_MIC, .name = "aspire-headset-mic"},
+	{.id = ALC269_FIXUP_ASUS_X101, .name = "asus-x101"},
+	{.id = ALC271_FIXUP_HP_GATE_MIC_JACK, .name = "acer-ao7xx"},
+	{.id = ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572, .name = "acer-aspire-e1"},
+	{.id = ALC269_FIXUP_ACER_AC700, .name = "acer-ac700"},
+	{.id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST, .name = "limit-mic-boost"},
+	{.id = ALC269VB_FIXUP_ASUS_ZENBOOK, .name = "asus-zenbook"},
+	{.id = ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A, .name = "asus-zenbook-ux31a"},
+	{.id = ALC269VB_FIXUP_ORDISSIMO_EVE2, .name = "ordissimo"},
+	{.id = ALC282_FIXUP_ASUS_TX300, .name = "asus-tx300"},
+	{.id = ALC283_FIXUP_INT_MIC, .name = "alc283-int-mic"},
+	{.id = ALC290_FIXUP_MONO_SPEAKERS_HSJACK, .name = "mono-speakers"},
+	{.id = ALC290_FIXUP_SUBWOOFER_HSJACK, .name = "alc290-subwoofer"},
+	{.id = ALC269_FIXUP_THINKPAD_ACPI, .name = "thinkpad"},
+	{.id = ALC269_FIXUP_DMIC_THINKPAD_ACPI, .name = "dmic-thinkpad"},
+	{.id = ALC255_FIXUP_ACER_MIC_NO_PRESENCE, .name = "alc255-acer"},
+	{.id = ALC255_FIXUP_ASUS_MIC_NO_PRESENCE, .name = "alc255-asus"},
+	{.id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc255-dell1"},
+	{.id = ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "alc255-dell2"},
+	{.id = ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc293-dell1"},
+	{.id = ALC283_FIXUP_HEADSET_MIC, .name = "alc283-headset"},
+	{.id = ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED, .name = "alc255-dell-mute"},
+	{.id = ALC282_FIXUP_ASPIRE_V5_PINS, .name = "aspire-v5"},
+	{.id = ALC280_FIXUP_HP_GPIO4, .name = "hp-gpio4"},
+	{.id = ALC286_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"},
+	{.id = ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY, .name = "hp-gpio2-hotkey"},
+	{.id = ALC280_FIXUP_HP_DOCK_PINS, .name = "hp-dock-pins"},
+	{.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic"},
+	{.id = ALC280_FIXUP_HP_9480M, .name = "hp-9480m"},
+	{.id = ALC288_FIXUP_DELL_HEADSET_MODE, .name = "alc288-dell-headset"},
+	{.id = ALC288_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc288-dell1"},
+	{.id = ALC288_FIXUP_DELL_XPS_13, .name = "alc288-dell-xps13"},
+	{.id = ALC292_FIXUP_DELL_E7X, .name = "dell-e7x"},
+	{.id = ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK, .name = "alc293-dell"},
+	{.id = ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc298-dell1"},
+	{.id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE, .name = "alc298-dell-aio"},
+	{.id = ALC275_FIXUP_DELL_XPS, .name = "alc275-dell-xps"},
+	{.id = ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, .name = "alc256-dell-xps13"},
+	{.id = ALC293_FIXUP_LENOVO_SPK_NOISE, .name = "lenovo-spk-noise"},
+	{.id = ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, .name = "lenovo-hotkey"},
+	{.id = ALC255_FIXUP_DELL_SPK_NOISE, .name = "dell-spk-noise"},
+	{.id = ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc255-dell1"},
+	{.id = ALC295_FIXUP_DISABLE_DAC3, .name = "alc295-disable-dac3"},
+	{.id = ALC280_FIXUP_HP_HEADSET_MIC, .name = "alc280-hp-headset"},
+	{.id = ALC221_FIXUP_HP_FRONT_MIC, .name = "alc221-hp-mic"},
+	{.id = ALC298_FIXUP_SPK_VOLUME, .name = "alc298-spk-volume"},
+	{.id = ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER, .name = "dell-inspiron-7559"},
+	{.id = ALC269_FIXUP_ATIV_BOOK_8, .name = "ativ-book"},
+	{.id = ALC221_FIXUP_HP_MIC_NO_PRESENCE, .name = "alc221-hp-mic"},
+	{.id = ALC256_FIXUP_ASUS_HEADSET_MODE, .name = "alc256-asus-headset"},
+	{.id = ALC256_FIXUP_ASUS_MIC, .name = "alc256-asus-mic"},
+	{.id = ALC256_FIXUP_ASUS_AIO_GPIO2, .name = "alc256-asus-aio"},
+	{.id = ALC233_FIXUP_ASUS_MIC_NO_PRESENCE, .name = "alc233-asus"},
+	{.id = ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE, .name = "alc233-eapd"},
+	{.id = ALC294_FIXUP_LENOVO_MIC_LOCATION, .name = "alc294-lenovo-mic"},
+	{.id = ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, .name = "alc225-wyse"},
+	{.id = ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, .name = "alc274-dell-aio"},
+	{.id = ALC255_FIXUP_DUMMY_LINEOUT_VERB, .name = "alc255-dummy-lineout"},
+	{.id = ALC255_FIXUP_DELL_HEADSET_MIC, .name = "alc255-dell-headset"},
+	{.id = ALC295_FIXUP_HP_X360, .name = "alc295-hp-x360"},
 	{}
 };
 #define ALC225_STANDARD_PINS \
@@ -6782,6 +6818,17 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x14, 0x90170110},
 		{0x19, 0x02a11030},
 		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", ALC294_FIXUP_LENOVO_MIC_LOCATION,
+		{0x14, 0x90170110},
+		{0x19, 0x02a11030},
+		{0x1a, 0x02a11040},
+		{0x1b, 0x01014020},
+		{0x21, 0x0221101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", ALC294_FIXUP_LENOVO_MIC_LOCATION,
+		{0x14, 0x90170110},
+		{0x19, 0x02a11020},
+		{0x1a, 0x02a11030},
+		{0x21, 0x0221101f}),
 	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60140},
 		{0x14, 0x90170110},
@@ -6963,7 +7010,7 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60130},
 		{0x19, 0x03a11020},
 		{0x21, 0x0321101f}),
-	SND_HDA_PIN_QUIRK(0x10ec0288, 0x1028, "Dell", ALC288_FIXUP_DELL_XPS_13_GPIO6,
+	SND_HDA_PIN_QUIRK(0x10ec0288, 0x1028, "Dell", ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60120},
 		{0x14, 0x90170110},
 		{0x21, 0x0321101f}),
@@ -7120,18 +7167,6 @@ static int patch_alc269(struct hda_codec *codec)
 	spec->shutup = alc_default_shutup;
 	spec->init_hook = alc_default_init;
 
-	snd_hda_pick_fixup(codec, alc269_fixup_models,
-		       alc269_fixup_tbl, alc269_fixups);
-	snd_hda_pick_pin_fixup(codec, alc269_pin_fixup_tbl, alc269_fixups);
-	snd_hda_pick_fixup(codec, NULL,	alc269_fixup_vendor_tbl,
-			   alc269_fixups);
-	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
-
-	alc_auto_parse_customize_define(codec);
-
-	if (has_cdefine_beep(codec))
-		spec->gen.beep_nid = 0x01;
-
 	switch (codec->core.vendor_id) {
 	case 0x10ec0269:
 		spec->codec_variant = ALC269_TYPE_ALC269VA;
@@ -7251,13 +7286,28 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->init_hook = alc5505_dsp_init;
 	}
 
+	snd_hda_pick_fixup(codec, alc269_fixup_models,
+		       alc269_fixup_tbl, alc269_fixups);
+	snd_hda_pick_pin_fixup(codec, alc269_pin_fixup_tbl, alc269_fixups);
+	snd_hda_pick_fixup(codec, NULL,	alc269_fixup_vendor_tbl,
+			   alc269_fixups);
+	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
+
+	alc_auto_parse_customize_define(codec);
+
+	if (has_cdefine_beep(codec))
+		spec->gen.beep_nid = 0x01;
+
 	/* automatic parse from the BIOS config */
 	err = alc269_parse_auto_config(codec);
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog && spec->gen.beep_nid && spec->gen.mixer_nid)
-		set_beep_amp(spec, spec->gen.mixer_nid, 0x04, HDA_INPUT);
+	if (!spec->gen.no_analog && spec->gen.beep_nid && spec->gen.mixer_nid) {
+		err = set_beep_amp(spec, spec->gen.mixer_nid, 0x04, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -7386,8 +7436,11 @@ static int patch_alc861(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog)
-		set_beep_amp(spec, 0x23, 0, HDA_OUTPUT);
+	if (!spec->gen.no_analog) {
+		err = set_beep_amp(spec, 0x23, 0, HDA_OUTPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -7427,16 +7480,21 @@ static void alc861vd_fixup_dallas(struct hda_codec *codec,
 	}
 }
 
+/* reset GPIO1 */
+static void alc660vd_fixup_asus_gpio1(struct hda_codec *codec,
+				      const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		spec->gpio_mask |= 0x02;
+	alc_fixup_gpio(codec, action, 0x01);
+}
+
 static const struct hda_fixup alc861vd_fixups[] = {
 	[ALC660VD_FIX_ASUS_GPIO1] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = (const struct hda_verb[]) {
-			/* reset GPIO1 */
-			{0x01, AC_VERB_SET_GPIO_MASK, 0x03},
-			{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x01},
-			{0x01, AC_VERB_SET_GPIO_DATA, 0x01},
-			{ }
-		}
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc660vd_fixup_asus_gpio1,
 	},
 	[ALC861VD_FIX_DALLAS] = {
 		.type = HDA_FIXUP_FUNC,
@@ -7475,8 +7533,11 @@ static int patch_alc861vd(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog)
-		set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog) {
+		err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -7557,7 +7618,7 @@ static unsigned int gpio_led_power_filter(struct hda_codec *codec,
 					  unsigned int power_state)
 {
 	struct alc_spec *spec = codec->spec;
-	if (nid == codec->core.afg && power_state == AC_PWRST_D3 && spec->gpio_led)
+	if (nid == codec->core.afg && power_state == AC_PWRST_D3 && spec->gpio_data)
 		return AC_PWRST_D0;
 	return power_state;
 }
@@ -7566,18 +7627,10 @@ static void alc662_fixup_led_gpio1(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x01 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x01 },
-		{}
-	};
 
+	alc_fixup_hp_gpio_led(codec, action, 0x01, 0);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gpio_led = 0;
 		spec->mute_led_polarity = 1;
-		spec->gpio_mute_led_mask = 0x01;
-		snd_hda_add_verbs(codec, gpio_init);
 		codec->power_filter = gpio_led_power_filter;
 	}
 }
@@ -8090,7 +8143,10 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 };
 
 static const struct hda_model_fixup alc662_fixup_models[] = {
+	{.id = ALC662_FIXUP_ASPIRE, .name = "aspire"},
+	{.id = ALC662_FIXUP_IDEAPAD, .name = "ideapad"},
 	{.id = ALC272_FIXUP_MARIO, .name = "mario"},
+	{.id = ALC662_FIXUP_HP_RP5800, .name = "hp-rp5800"},
 	{.id = ALC662_FIXUP_ASUS_MODE1, .name = "asus-mode1"},
 	{.id = ALC662_FIXUP_ASUS_MODE2, .name = "asus-mode2"},
 	{.id = ALC662_FIXUP_ASUS_MODE3, .name = "asus-mode3"},
@@ -8099,8 +8155,23 @@ static const struct hda_model_fixup alc662_fixup_models[] = {
 	{.id = ALC662_FIXUP_ASUS_MODE6, .name = "asus-mode6"},
 	{.id = ALC662_FIXUP_ASUS_MODE7, .name = "asus-mode7"},
 	{.id = ALC662_FIXUP_ASUS_MODE8, .name = "asus-mode8"},
+	{.id = ALC662_FIXUP_ZOTAC_Z68, .name = "zotac-z68"},
 	{.id = ALC662_FIXUP_INV_DMIC, .name = "inv-dmic"},
+	{.id = ALC662_FIXUP_DELL_MIC_NO_PRESENCE, .name = "alc662-headset-multi"},
 	{.id = ALC668_FIXUP_DELL_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
+	{.id = ALC662_FIXUP_HEADSET_MODE, .name = "alc662-headset"},
+	{.id = ALC668_FIXUP_HEADSET_MODE, .name = "alc668-headset"},
+	{.id = ALC662_FIXUP_BASS_16, .name = "bass16"},
+	{.id = ALC662_FIXUP_BASS_1A, .name = "bass1a"},
+	{.id = ALC668_FIXUP_AUTO_MUTE, .name = "automute"},
+	{.id = ALC668_FIXUP_DELL_XPS13, .name = "dell-xps13"},
+	{.id = ALC662_FIXUP_ASUS_Nx50, .name = "asus-nx50"},
+	{.id = ALC668_FIXUP_ASUS_Nx51, .name = "asus-nx51"},
+	{.id = ALC891_FIXUP_HEADSET_MODE, .name = "alc891-headset"},
+	{.id = ALC891_FIXUP_DELL_MIC_NO_PRESENCE, .name = "alc891-headset-multi"},
+	{.id = ALC662_FIXUP_ACER_VERITON, .name = "acer-veriton"},
+	{.id = ALC892_FIXUP_ASROCK_MOBO, .name = "asrock-mobo"},
+	{.id = ALC662_FIXUP_USI_HEADSET_MODE, .name = "usi-headset"},
 	{.id = ALC662_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
 	{}
 };
@@ -8194,18 +8265,20 @@ static int patch_alc662(struct hda_codec *codec)
 	if (!spec->gen.no_analog && spec->gen.beep_nid) {
 		switch (codec->core.vendor_id) {
 		case 0x10ec0662:
-			set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+			err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
 			break;
 		case 0x10ec0272:
 		case 0x10ec0663:
 		case 0x10ec0665:
 		case 0x10ec0668:
-			set_beep_amp(spec, 0x0b, 0x04, HDA_INPUT);
+			err = set_beep_amp(spec, 0x0b, 0x04, HDA_INPUT);
 			break;
 		case 0x10ec0273:
-			set_beep_amp(spec, 0x0b, 0x03, HDA_INPUT);
+			err = set_beep_amp(spec, 0x0b, 0x03, HDA_INPUT);
 			break;
 		}
+		if (err < 0)
+			goto error;
 	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 63d15b545b33..046705b4691a 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -332,33 +332,15 @@ static void stac_gpio_set(struct hda_codec *codec, unsigned int mask,
 }
 
 /* hook for controlling mic-mute LED GPIO */
-static void stac_capture_led_hook(struct hda_codec *codec,
-				  struct snd_kcontrol *kcontrol,
-				  struct snd_ctl_elem_value *ucontrol)
+static void stac_capture_led_update(struct hda_codec *codec)
 {
 	struct sigmatel_spec *spec = codec->spec;
-	unsigned int mask;
-	bool cur_mute, prev_mute;
 
-	if (!kcontrol || !ucontrol)
-		return;
-
-	mask = 1U << snd_ctl_get_ioffidx(kcontrol, &ucontrol->id);
-	prev_mute = !spec->mic_enabled;
-	if (ucontrol->value.integer.value[0] ||
-	    ucontrol->value.integer.value[1])
-		spec->mic_enabled |= mask;
+	if (spec->gen.micmute_led.led_value)
+		spec->gpio_data |= spec->mic_mute_led_gpio;
 	else
-		spec->mic_enabled &= ~mask;
-	cur_mute = !spec->mic_enabled;
-	if (cur_mute != prev_mute) {
-		if (cur_mute)
-			spec->gpio_data |= spec->mic_mute_led_gpio;
-		else
-			spec->gpio_data &= ~spec->mic_mute_led_gpio;
-		stac_gpio_set(codec, spec->gpio_mask,
-			      spec->gpio_dir, spec->gpio_data);
-	}
+		spec->gpio_data &= ~spec->mic_mute_led_gpio;
+	stac_gpio_set(codec, spec->gpio_mask, spec->gpio_dir, spec->gpio_data);
 }
 
 static int stac_vrefout_set(struct hda_codec *codec,
@@ -4656,8 +4638,7 @@ static void stac_setup_gpio(struct hda_codec *codec)
 		spec->gpio_dir |= spec->mic_mute_led_gpio;
 		spec->mic_enabled = 0;
 		spec->gpio_data |= spec->mic_mute_led_gpio;
-
-		spec->gen.cap_sync_hook = stac_capture_led_hook;
+		snd_hda_gen_add_micmute_led(codec, stac_capture_led_update);
 	}
 }
 
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index fc30d1e8aa76..6b9617aee0e6 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -90,13 +90,6 @@ enum VIA_HDA_CODEC {
 struct via_spec {
 	struct hda_gen_spec gen;
 
-	/* codec parameterization */
-	const struct snd_kcontrol_new *mixers[6];
-	unsigned int num_mixers;
-
-	const struct hda_verb *init_verbs[5];
-	unsigned int num_iverbs;
-
 	/* HP mode source */
 	unsigned int dmic_enabled;
 	enum VIA_HDA_CODEC codec_type;
@@ -107,8 +100,6 @@ struct via_spec {
 	/* work to check hp jack state */
 	int hp_work_active;
 	int vt1708_jack_detect;
-
-	unsigned int beep_amp;
 };
 
 static enum VIA_HDA_CODEC get_codec_type(struct hda_codec *codec);
@@ -262,69 +253,51 @@ static int via_pin_power_ctl_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const struct snd_kcontrol_new via_pin_power_ctl_enum[] = {
-	{
+static const struct snd_kcontrol_new via_pin_power_ctl_enum = {
 	.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
 	.name = "Dynamic Power-Control",
 	.info = via_pin_power_ctl_info,
 	.get = via_pin_power_ctl_get,
 	.put = via_pin_power_ctl_put,
-	},
-	{} /* terminator */
 };
 
 #ifdef CONFIG_SND_HDA_INPUT_BEEP
-static inline void set_beep_amp(struct via_spec *spec, hda_nid_t nid,
-				int idx, int dir)
-{
-	spec->gen.beep_nid = nid;
-	spec->beep_amp = HDA_COMPOSE_AMP_VAL(nid, 1, idx, dir);
-}
-
 /* additional beep mixers; the actual parameters are overwritten at build */
-static const struct snd_kcontrol_new cxt_beep_mixer[] = {
+static const struct snd_kcontrol_new via_beep_mixer[] = {
 	HDA_CODEC_VOLUME_MONO("Beep Playback Volume", 0, 1, 0, HDA_OUTPUT),
 	HDA_CODEC_MUTE_BEEP_MONO("Beep Playback Switch", 0, 1, 0, HDA_OUTPUT),
-	{ } /* end */
 };
 
-/* create beep controls if needed */
-static int add_beep_ctls(struct hda_codec *codec)
+static int set_beep_amp(struct via_spec *spec, hda_nid_t nid,
+			int idx, int dir)
 {
-	struct via_spec *spec = codec->spec;
-	int err;
+	struct snd_kcontrol_new *knew;
+	unsigned int beep_amp = HDA_COMPOSE_AMP_VAL(nid, 1, idx, dir);
+	int i;
 
-	if (spec->beep_amp) {
-		const struct snd_kcontrol_new *knew;
-		for (knew = cxt_beep_mixer; knew->name; knew++) {
-			struct snd_kcontrol *kctl;
-			kctl = snd_ctl_new1(knew, codec);
-			if (!kctl)
-				return -ENOMEM;
-			kctl->private_value = spec->beep_amp;
-			err = snd_hda_ctl_add(codec, 0, kctl);
-			if (err < 0)
-				return err;
-		}
+	spec->gen.beep_nid = nid;
+	for (i = 0; i < ARRAY_SIZE(via_beep_mixer); i++) {
+		knew = snd_hda_gen_add_kctl(&spec->gen, NULL,
+					    &via_beep_mixer[i]);
+		if (!knew)
+			return -ENOMEM;
+		knew->private_value = beep_amp;
 	}
 	return 0;
 }
 
-static void auto_parse_beep(struct hda_codec *codec)
+static int auto_parse_beep(struct hda_codec *codec)
 {
 	struct via_spec *spec = codec->spec;
 	hda_nid_t nid;
 
 	for_each_hda_codec_node(nid, codec)
-		if (get_wcaps_type(get_wcaps(codec, nid)) == AC_WID_BEEP) {
-			set_beep_amp(spec, nid, 0, HDA_OUTPUT);
-			break;
-		}
+		if (get_wcaps_type(get_wcaps(codec, nid)) == AC_WID_BEEP)
+			return set_beep_amp(spec, nid, 0, HDA_OUTPUT);
+	return 0;
 }
 #else
-#define set_beep_amp(spec, nid, idx, dir) /* NOP */
-#define add_beep_ctls(codec)	0
-#define auto_parse_beep(codec)
+#define auto_parse_beep(codec)	0
 #endif
 
 /* check AA path's mute status */
@@ -403,30 +376,6 @@ static void analog_low_current_mode(struct hda_codec *codec)
 	return __analog_low_current_mode(codec, false);
 }
 
-static int via_build_controls(struct hda_codec *codec)
-{
-	struct via_spec *spec = codec->spec;
-	int err, i;
-
-	err = snd_hda_gen_build_controls(codec);
-	if (err < 0)
-		return err;
-
-	err = add_beep_ctls(codec);
-	if (err < 0)
-		return err;
-
-	spec->mixers[spec->num_mixers++] = via_pin_power_ctl_enum;
-
-	for (i = 0; i < spec->num_mixers; i++) {
-		err = snd_hda_add_new_ctls(codec, spec->mixers[i]);
-		if (err < 0)
-			return err;
-	}
-
-	return 0;
-}
-
 static void via_playback_pcm_hook(struct hda_pcm_stream *hinfo,
 				  struct hda_codec *codec,
 				  struct snd_pcm_substream *substream,
@@ -481,7 +430,7 @@ static int via_check_power_status(struct hda_codec *codec, hda_nid_t nid)
 static int via_init(struct hda_codec *codec);
 
 static const struct hda_codec_ops via_patch_ops = {
-	.build_controls = via_build_controls,
+	.build_controls = snd_hda_gen_build_controls,
 	.build_pcms = snd_hda_gen_build_pcms,
 	.init = via_init,
 	.free = via_free,
@@ -545,16 +494,13 @@ static int vt1708_jack_detect_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const struct snd_kcontrol_new vt1708_jack_detect_ctl[] = {
-	{
+static const struct snd_kcontrol_new vt1708_jack_detect_ctl = {
 	.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
 	.name = "Jack Detect",
 	.count = 1,
 	.info = snd_ctl_boolean_mono_info,
 	.get = vt1708_jack_detect_get,
 	.put = vt1708_jack_detect_put,
-	},
-	{} /* terminator */
 };
 
 static const struct badness_table via_main_out_badness = {
@@ -586,12 +532,17 @@ static int via_parse_auto_config(struct hda_codec *codec)
 	if (err < 0)
 		return err;
 
-	auto_parse_beep(codec);
-
 	err = snd_hda_gen_parse_auto_config(codec, &spec->gen.autocfg);
 	if (err < 0)
 		return err;
 
+	err = auto_parse_beep(codec);
+	if (err < 0)
+		return err;
+
+	if (!snd_hda_gen_add_kctl(&spec->gen, NULL, &via_pin_power_ctl_enum))
+		return -ENOMEM;
+
 	/* disable widget PM at start for compatibility */
 	codec->power_save_node = 0;
 	spec->gen.power_down_unused = 0;
@@ -600,12 +551,6 @@ static int via_parse_auto_config(struct hda_codec *codec)
 
 static int via_init(struct hda_codec *codec)
 {
-	struct via_spec *spec = codec->spec;
-	int i;
-
-	for (i = 0; i < spec->num_iverbs; i++)
-		snd_hda_sequence_write(codec, spec->init_verbs[i]);
-
 	/* init power states */
 	__analog_low_current_mode(codec, true);
 
@@ -623,7 +568,7 @@ static int vt1708_build_controls(struct hda_codec *codec)
 	int err;
 	int old_interval = codec->jackpoll_interval;
 	codec->jackpoll_interval = msecs_to_jiffies(100);
-	err = via_build_controls(codec);
+	err = snd_hda_gen_build_controls(codec);
 	codec->jackpoll_interval = old_interval;
 	return err;
 }
@@ -684,22 +629,29 @@ static int patch_vt1708(struct hda_codec *codec)
 	vt1708_set_pinconfig_connect(codec, VT1708_HP_PIN_NID);
 	vt1708_set_pinconfig_connect(codec, VT1708_CD_PIN_NID);
 
+	err = snd_hda_add_verbs(codec, vt1708_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	/* add jack detect on/off control */
-	spec->mixers[spec->num_mixers++] = vt1708_jack_detect_ctl;
-
-	spec->init_verbs[spec->num_iverbs++] = vt1708_init_verbs;
+	if (!snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1708_jack_detect_ctl)) {
+		err = -ENOMEM;
+		goto error;
+	}
 
 	/* clear jackpoll_interval again; it's set dynamically */
 	codec->jackpoll_interval = 0;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 static int patch_vt1709(struct hda_codec *codec)
@@ -715,12 +667,14 @@ static int patch_vt1709(struct hda_codec *codec)
 	spec->gen.mixer_nid = 0x18;
 
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 static int patch_vt1708S(struct hda_codec *codec);
@@ -741,12 +695,14 @@ static int patch_vt1708B(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* Patch for VT1708S */
@@ -791,16 +747,20 @@ static int patch_vt1708S(struct hda_codec *codec)
 	if (codec->core.vendor_id == 0x11064397)
 		snd_hda_codec_set_name(codec, "VT1705");
 
+	err = snd_hda_add_verbs(codec, vt1708S_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
-
-	spec->init_verbs[spec->num_iverbs++] = vt1708S_init_verbs;
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* Patch for VT1702 */
@@ -832,16 +792,20 @@ static int patch_vt1702(struct hda_codec *codec)
 				  (0x5 << AC_AMPCAP_STEP_SIZE_SHIFT) |
 				  (1 << AC_AMPCAP_MUTE_SHIFT));
 
+	err = snd_hda_add_verbs(codec, vt1702_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
-
-	spec->init_verbs[spec->num_iverbs++] = vt1702_init_verbs;
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* Patch for VT1718S */
@@ -904,16 +868,20 @@ static int patch_vt1718S(struct hda_codec *codec)
 	override_mic_boost(codec, 0x29, 0, 3, 40);
 	add_secret_dac_path(codec);
 
+	err = snd_hda_add_verbs(codec, vt1718S_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
-
-	spec->init_verbs[spec->num_iverbs++] = vt1718S_init_verbs;
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* Patch for VT1716S */
@@ -955,9 +923,9 @@ static int vt1716s_dmic_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const struct snd_kcontrol_new vt1716s_dmic_mixer[] = {
-	HDA_CODEC_VOLUME("Digital Mic Capture Volume", 0x22, 0x0, HDA_INPUT),
-	{
+static const struct snd_kcontrol_new vt1716s_dmic_mixer_vol =
+	HDA_CODEC_VOLUME("Digital Mic Capture Volume", 0x22, 0x0, HDA_INPUT);
+static const struct snd_kcontrol_new vt1716s_dmic_mixer_sw = {
 	 .iface = SNDRV_CTL_ELEM_IFACE_MIXER,
 	 .name = "Digital Mic Capture Switch",
 	 .subdevice = HDA_SUBDEV_NID_FLAG | 0x26,
@@ -965,16 +933,12 @@ static const struct snd_kcontrol_new vt1716s_dmic_mixer[] = {
 	 .info = vt1716s_dmic_info,
 	 .get = vt1716s_dmic_get,
 	 .put = vt1716s_dmic_put,
-	 },
-	{}			/* end */
 };
 
 
 /* mono-out mixer elements */
-static const struct snd_kcontrol_new vt1716S_mono_out_mixer[] = {
-	HDA_CODEC_MUTE("Mono Playback Switch", 0x2a, 0x0, HDA_OUTPUT),
-	{ } /* end */
-};
+static const struct snd_kcontrol_new vt1716S_mono_out_mixer =
+	HDA_CODEC_MUTE("Mono Playback Switch", 0x2a, 0x0, HDA_OUTPUT);
 
 static const struct hda_verb vt1716S_init_verbs[] = {
 	/* Enable Boost Volume backdoor */
@@ -1000,19 +964,27 @@ static int patch_vt1716S(struct hda_codec *codec)
 	override_mic_boost(codec, 0x1a, 0, 3, 40);
 	override_mic_boost(codec, 0x1e, 0, 3, 40);
 
+	err = snd_hda_add_verbs(codec, vt1716S_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
-
-	spec->init_verbs[spec->num_iverbs++]  = vt1716S_init_verbs;
+	if (err < 0)
+		goto error;
 
-	spec->mixers[spec->num_mixers++] = vt1716s_dmic_mixer;
-	spec->mixers[spec->num_mixers++] = vt1716S_mono_out_mixer;
+	if (!snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1716s_dmic_mixer_vol) ||
+	    !snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1716s_dmic_mixer_sw) ||
+	    !snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1716S_mono_out_mixer)) {
+		err = -ENOMEM;
+		goto error;
+	}
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* for vt2002P */
@@ -1107,19 +1079,23 @@ static int patch_vt2002P(struct hda_codec *codec)
 	snd_hda_pick_fixup(codec, NULL, vt2002p_fixups, via_fixups);
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
 
-	/* automatic parse from the BIOS config */
-	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
-
 	if (spec->codec_type == VT1802)
-		spec->init_verbs[spec->num_iverbs++] = vt1802_init_verbs;
+		err = snd_hda_add_verbs(codec, vt1802_init_verbs);
 	else
-		spec->init_verbs[spec->num_iverbs++] = vt2002P_init_verbs;
+		err = snd_hda_add_verbs(codec, vt2002P_init_verbs);
+	if (err < 0)
+		goto error;
+
+	/* automatic parse from the BIOS config */
+	err = via_parse_auto_config(codec);
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* for vt1812 */
@@ -1148,16 +1124,20 @@ static int patch_vt1812(struct hda_codec *codec)
 	override_mic_boost(codec, 0x29, 0, 3, 40);
 	add_secret_dac_path(codec);
 
+	err = snd_hda_add_verbs(codec, vt1812_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
-
-	spec->init_verbs[spec->num_iverbs++]  = vt1812_init_verbs;
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* patch for vt3476 */
@@ -1185,16 +1165,20 @@ static int patch_vt3476(struct hda_codec *codec)
 	spec->gen.mixer_nid = 0x3f;
 	add_secret_dac_path(codec);
 
+	err = snd_hda_add_verbs(codec, vt3476_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
-
-	spec->init_verbs[spec->num_iverbs++] = vt3476_init_verbs;
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /*
diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index 65bb3ac6af4c..97f49b751e6e 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -27,17 +27,11 @@ static void update_tpacpi_mute_led(void *private_data, int enabled)
 		led_set_func(TPACPI_LED_MUTE, !enabled);
 }
 
-static void update_tpacpi_micmute_led(struct hda_codec *codec,
-				      struct snd_kcontrol *kcontrol,
-				      struct snd_ctl_elem_value *ucontrol)
+static void update_tpacpi_micmute(struct hda_codec *codec)
 {
-	if (!ucontrol || !led_set_func)
-		return;
-	if (strcmp("Capture Switch", ucontrol->id.name) == 0 && ucontrol->id.index == 0) {
-		/* TODO: How do I verify if it's a mono or stereo here? */
-		bool val = ucontrol->value.integer.value[0] || ucontrol->value.integer.value[1];
-		led_set_func(TPACPI_LED_MICMUTE, !val);
-	}
+	struct hda_gen_spec *spec = codec->spec;
+
+	led_set_func(TPACPI_LED_MICMUTE, spec->micmute_led.led_value);
 }
 
 static void hda_fixup_thinkpad_acpi(struct hda_codec *codec,
@@ -63,15 +57,10 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec,
 			spec->vmaster_mute.hook = update_tpacpi_mute_led;
 			removefunc = false;
 		}
-		if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) {
-			if (spec->num_adc_nids > 1 && !spec->dyn_adc_switch)
-				codec_dbg(codec,
-					  "Skipping micmute LED control due to several ADCs");
-			else {
-				spec->cap_sync_hook = update_tpacpi_micmute_led;
-				removefunc = false;
-			}
-		}
+		if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0 &&
+		    snd_hda_gen_add_micmute_led(codec,
+						update_tpacpi_micmute) > 0)
+			removefunc = false;
 	}
 
 	if (led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) {
diff --git a/sound/pci/ice1712/ak4xxx.c b/sound/pci/ice1712/ak4xxx.c
index 179ef7a5f0d1..a553897a4c4f 100644
--- a/sound/pci/ice1712/ak4xxx.c
+++ b/sound/pci/ice1712/ak4xxx.c
@@ -179,18 +179,6 @@ int snd_ice1712_akm4xxx_build_controls(struct snd_ice1712 *ice)
 	return 0;
 }
 
-static int __init alsa_ice1712_akm4xxx_module_init(void)
-{
-	return 0;
-}
-        
-static void __exit alsa_ice1712_akm4xxx_module_exit(void)
-{
-}
-        
-module_init(alsa_ice1712_akm4xxx_module_init)
-module_exit(alsa_ice1712_akm4xxx_module_exit)
-
 EXPORT_SYMBOL(snd_ice1712_akm4xxx_init);
 EXPORT_SYMBOL(snd_ice1712_akm4xxx_free);
 EXPORT_SYMBOL(snd_ice1712_akm4xxx_build_controls);
diff --git a/sound/pci/ice1712/prodigy_hifi.c b/sound/pci/ice1712/prodigy_hifi.c
index d7366ade5a25..c97b5528e4b8 100644
--- a/sound/pci/ice1712/prodigy_hifi.c
+++ b/sound/pci/ice1712/prodigy_hifi.c
@@ -314,26 +314,7 @@ static struct snd_kcontrol_new prodigy_hd2_controls[] = {
 
 /* --------------- */
 
-/*
- * Logarithmic volume values for WM87*6
- * Computed as 20 * Log10(255 / x)
- */
-static const unsigned char wm_vol[256] = {
-	127, 48, 42, 39, 36, 34, 33, 31, 30, 29, 28, 27, 27, 26, 25, 25, 24, 24, 23,
-	23, 22, 22, 21, 21, 21, 20, 20, 20, 19, 19, 19, 18, 18, 18, 18, 17, 17, 17,
-	17, 16, 16, 16, 16, 15, 15, 15, 15, 15, 15, 14, 14, 14, 14, 14, 13, 13, 13,
-	13, 13, 13, 13, 12, 12, 12, 12, 12, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11,
-	11, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 8, 8,
-	8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6,
-	6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-	5, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, 3, 3, 3, 3,
-	3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
-	2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
-	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0
-};
-
-#define WM_VOL_MAX	(sizeof(wm_vol) - 1)
+#define WM_VOL_MAX	255
 #define WM_VOL_MUTE	0x8000
 
 
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 4c24346340f4..5ee468d1aefe 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -351,7 +351,7 @@ enum {
 struct ichdev {
 	unsigned int ichd;			/* ich device number */
 	unsigned long reg_offset;		/* offset to bmaddr */
-	u32 *bdbar;				/* CPU address (32bit) */
+	__le32 *bdbar;				/* CPU address (32bit) */
 	unsigned int bdbar_addr;		/* PCI bus address (32bit) */
 	struct snd_pcm_substream *substream;
 	unsigned int physbuf;			/* physical address (32bit) */
@@ -677,7 +677,7 @@ static void snd_intel8x0_ali_codec_write(struct snd_ac97 *ac97, unsigned short r
 static void snd_intel8x0_setup_periods(struct intel8x0 *chip, struct ichdev *ichdev) 
 {
 	int idx;
-	u32 *bdbar = ichdev->bdbar;
+	__le32 *bdbar = ichdev->bdbar;
 	unsigned long port = ichdev->reg_offset;
 
 	iputdword(chip, port + ICH_REG_OFF_BDBAR, ichdev->bdbar_addr);
@@ -3143,7 +3143,7 @@ static int snd_intel8x0_create(struct snd_card *card,
 	int_sta_masks = 0;
 	for (i = 0; i < chip->bdbars_count; i++) {
 		ichdev = &chip->ichd[i];
-		ichdev->bdbar = ((u32 *)chip->bdbars.area) +
+		ichdev->bdbar = ((__le32 *)chip->bdbars.area) +
 			(i * ICH_MAX_FRAGS * 2);
 		ichdev->bdbar_addr = chip->bdbars.addr +
 			(i * sizeof(u32) * ICH_MAX_FRAGS * 2);
diff --git a/sound/pci/intel8x0m.c b/sound/pci/intel8x0m.c
index 3a4769a97d29..943a726b1c1b 100644
--- a/sound/pci/intel8x0m.c
+++ b/sound/pci/intel8x0m.c
@@ -168,7 +168,7 @@ enum { ALID_MDMIN, ALID_MDMOUT, ALID_MDMLAST = ALID_MDMOUT };
 struct ichdev {
 	unsigned int ichd;			/* ich device number */
 	unsigned long reg_offset;		/* offset to bmaddr */
-	u32 *bdbar;				/* CPU address (32bit) */
+	__le32 *bdbar;				/* CPU address (32bit) */
 	unsigned int bdbar_addr;		/* PCI bus address (32bit) */
 	struct snd_pcm_substream *substream;
 	unsigned int physbuf;			/* physical address (32bit) */
@@ -395,7 +395,7 @@ static unsigned short snd_intel8x0m_codec_read(struct snd_ac97 *ac97,
 static void snd_intel8x0m_setup_periods(struct intel8x0m *chip, struct ichdev *ichdev)
 {
 	int idx;
-	u32 *bdbar = ichdev->bdbar;
+	__le32 *bdbar = ichdev->bdbar;
 	unsigned long port = ichdev->reg_offset;
 
 	iputdword(chip, port + ICH_REG_OFF_BDBAR, ichdev->bdbar_addr);
@@ -1217,7 +1217,7 @@ static int snd_intel8x0m_create(struct snd_card *card,
 	int_sta_masks = 0;
 	for (i = 0; i < chip->bdbars_count; i++) {
 		ichdev = &chip->ichd[i];
-		ichdev->bdbar = ((u32 *)chip->bdbars.area) + (i * ICH_MAX_FRAGS * 2);
+		ichdev->bdbar = ((__le32 *)chip->bdbars.area) + (i * ICH_MAX_FRAGS * 2);
 		ichdev->bdbar_addr = chip->bdbars.addr + (i * sizeof(u32) * ICH_MAX_FRAGS * 2);
 		int_sta_masks |= ichdev->int_sta_mask;
 	}
diff --git a/sound/pci/korg1212/korg1212.c b/sound/pci/korg1212/korg1212.c
index 4206ba44d8bb..4e189a93f475 100644
--- a/sound/pci/korg1212/korg1212.c
+++ b/sound/pci/korg1212/korg1212.c
@@ -1326,7 +1326,7 @@ static int snd_korg1212_copy_to(struct snd_pcm_substream *substream,
 		}
 #endif
 		if (in_kernel)
-			memcpy((void *)dst, src, size);
+			memcpy((__force void *)dst, src, size);
 		else if (copy_to_user(dst, src, size))
 			return -EFAULT;
 		src++;
@@ -1365,7 +1365,7 @@ static int snd_korg1212_copy_from(struct snd_pcm_substream *substream,
 		}
 #endif
 		if (in_kernel)
-			memcpy((void *)dst, src, size);
+			memcpy(dst, (__force void *)src, size);
 		else if (copy_from_user(dst, src, size))
 			return -EFAULT;
 		dst++;
diff --git a/sound/pci/lola/lola.c b/sound/pci/lola/lola.c
index 9ff600084973..254f24366892 100644
--- a/sound/pci/lola/lola.c
+++ b/sound/pci/lola/lola.c
@@ -369,9 +369,9 @@ static int setup_corb_rirb(struct lola *chip)
 		return err;
 
 	chip->corb.addr = chip->rb.addr;
-	chip->corb.buf = (u32 *)chip->rb.area;
+	chip->corb.buf = (__le32 *)chip->rb.area;
 	chip->rirb.addr = chip->rb.addr + 2048;
-	chip->rirb.buf = (u32 *)(chip->rb.area + 2048);
+	chip->rirb.buf = (__le32 *)(chip->rb.area + 2048);
 
 	/* disable ringbuffer DMAs */
 	lola_writeb(chip, BAR0, RIRBCTL, 0);
diff --git a/sound/pci/lola/lola.h b/sound/pci/lola/lola.h
index f0b100059efd..bd852fed8bb6 100644
--- a/sound/pci/lola/lola.h
+++ b/sound/pci/lola/lola.h
@@ -220,7 +220,7 @@ struct lola_bar {
 
 /* CORB/RIRB */
 struct lola_rb {
-	u32 *buf;		/* CORB/RIRB buffer, 8 byte per each entry */
+	__le32 *buf;		/* CORB/RIRB buffer, 8 byte per each entry */
 	dma_addr_t addr;	/* physical address of CORB/RIRB buffer */
 	unsigned short rp, wp;	/* read/write pointers */
 	int cmds;		/* number of pending requests */
@@ -275,7 +275,7 @@ struct lola_mixer_array {
 struct lola_mixer_widget {
 	unsigned int nid;
 	unsigned int caps;
-	struct lola_mixer_array __user *array;
+	struct lola_mixer_array __iomem *array;
 	struct lola_mixer_array *array_saved;
 	unsigned int src_stream_outs;
 	unsigned int src_phys_ins;
diff --git a/sound/pci/lola/lola_pcm.c b/sound/pci/lola/lola_pcm.c
index 310b26a756c9..e70276c3ea20 100644
--- a/sound/pci/lola/lola_pcm.c
+++ b/sound/pci/lola/lola_pcm.c
@@ -316,10 +316,10 @@ static int lola_pcm_hw_free(struct snd_pcm_substream *substream)
  * set up a BDL entry
  */
 static int setup_bdle(struct snd_pcm_substream *substream,
-		      struct lola_stream *str, u32 **bdlp,
+		      struct lola_stream *str, __le32 **bdlp,
 		      int ofs, int size)
 {
-	u32 *bdl = *bdlp;
+	__le32 *bdl = *bdlp;
 
 	while (size > 0) {
 		dma_addr_t addr;
@@ -355,14 +355,14 @@ static int lola_setup_periods(struct lola *chip, struct lola_pcm *pcm,
 			      struct snd_pcm_substream *substream,
 			      struct lola_stream *str)
 {
-	u32 *bdl;
+	__le32 *bdl;
 	int i, ofs, periods, period_bytes;
 
 	period_bytes = str->period_bytes;
 	periods = str->bufsize / period_bytes;
 
 	/* program the initial BDL entries */
-	bdl = (u32 *)(pcm->bdl.area + LOLA_BDL_ENTRY_SIZE * str->index);
+	bdl = (__le32 *)(pcm->bdl.area + LOLA_BDL_ENTRY_SIZE * str->index);
 	ofs = 0;
 	str->frags = 0;
 	for (i = 0; i < periods; i++) {
diff --git a/sound/pci/lx6464es/lx6464es.c b/sound/pci/lx6464es/lx6464es.c
index 6c85f13ab23f..54f6252faca6 100644
--- a/sound/pci/lx6464es/lx6464es.c
+++ b/sound/pci/lx6464es/lx6464es.c
@@ -1018,6 +1018,7 @@ static int snd_lx6464es_create(struct snd_card *card,
 	chip->port_dsp_bar = pci_ioremap_bar(pci, 2);
 	if (!chip->port_dsp_bar) {
 		dev_err(card->dev, "cannot remap PCI memory region\n");
+		err = -ENOMEM;
 		goto remap_pci_failed;
 	}
 
diff --git a/sound/pci/maestro3.c b/sound/pci/maestro3.c
index 224e942f556d..62962178a9d7 100644
--- a/sound/pci/maestro3.c
+++ b/sound/pci/maestro3.c
@@ -2103,7 +2103,7 @@ static const u16 minisrc_lpf[MINISRC_LPF_LEN] = {
 static void snd_m3_assp_init(struct snd_m3 *chip)
 {
 	unsigned int i;
-	const u16 *data;
+	const __le16 *data;
 
 	/* zero kernel data */
 	for (i = 0; i < (REV_B_DATA_MEMORY_UNIT_LENGTH * NUM_UNITS_KERNEL_DATA) / 2; i++)
@@ -2121,7 +2121,7 @@ static void snd_m3_assp_init(struct snd_m3 *chip)
 			  KDATA_DMA_XFER0);
 
 	/* write kernel into code memory.. */
-	data = (const u16 *)chip->assp_kernel_image->data;
+	data = (const __le16 *)chip->assp_kernel_image->data;
 	for (i = 0 ; i * 2 < chip->assp_kernel_image->size; i++) {
 		snd_m3_assp_write(chip, MEMTYPE_INTERNAL_CODE, 
 				  REV_B_CODE_MEMORY_BEGIN + i,
@@ -2134,7 +2134,7 @@ static void snd_m3_assp_init(struct snd_m3 *chip)
 	 * drop it there.  It seems that the minisrc doesn't
 	 * need vectors, so we won't bother with them..
 	 */
-	data = (const u16 *)chip->assp_minisrc_image->data;
+	data = (const __le16 *)chip->assp_minisrc_image->data;
 	for (i = 0; i * 2 < chip->assp_minisrc_image->size; i++) {
 		snd_m3_assp_write(chip, MEMTYPE_INTERNAL_CODE, 
 				  0x400 + i, le16_to_cpu(data[i]));
diff --git a/sound/pci/mixart/mixart.c b/sound/pci/mixart/mixart.c
index a74f1ad7e7b8..9cd297a42f24 100644
--- a/sound/pci/mixart/mixart.c
+++ b/sound/pci/mixart/mixart.c
@@ -182,6 +182,7 @@ static int mixart_set_clock(struct mixart_mgr *mgr,
 	case PIPE_RUNNING:
 		if(rate != 0)
 			break;
+		/* fall through */
 	default:
 		if(rate == 0)
 			return 0; /* nothing to do */
diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c
index 8bf2ce32d4a8..71776bfe0485 100644
--- a/sound/pci/mixart/mixart_core.c
+++ b/sound/pci/mixart/mixart_core.c
@@ -107,7 +107,7 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp,
 #ifndef __BIG_ENDIAN
 	size /= 4; /* u32 size */
 	for(i=0; i < size; i++) {
-		((u32*)resp->data)[i] = be32_to_cpu(((u32*)resp->data)[i]);
+		((u32*)resp->data)[i] = be32_to_cpu(((__be32*)resp->data)[i]);
 	}
 #endif
 
@@ -519,7 +519,7 @@ irqreturn_t snd_mixart_threaded_irq(int irq, void *dev_id)
 					/* Traces are text: the swapped msg_data has to be swapped back ! */
 					int i;
 					for(i=0; i<(resp.size/4); i++) {
-						(mixart_msg_data)[i] = cpu_to_be32((mixart_msg_data)[i]);
+						((__be32*)mixart_msg_data)[i] = cpu_to_be32((mixart_msg_data)[i]);
 					}
 #endif
 					((char*)mixart_msg_data)[resp.size - 1] = 0;
@@ -540,7 +540,7 @@ irqreturn_t snd_mixart_threaded_irq(int irq, void *dev_id)
 				dev_err(&mgr->pci->dev,
 					"canceled notification %x !\n", msg);
 			}
-			/* no break, continue ! */
+			/* fall through */
 		case MSG_TYPE_ANSWER:
 			/* answer or notification to a message we are waiting for*/
 			mutex_lock(&mgr->msg_lock);
diff --git a/sound/pci/mixart/mixart_hwdep.c b/sound/pci/mixart/mixart_hwdep.c
index 5bfd3ac80db5..bc92758de82c 100644
--- a/sound/pci/mixart/mixart_hwdep.c
+++ b/sound/pci/mixart/mixart_hwdep.c
@@ -73,30 +73,30 @@ static int mixart_wait_nice_for_register_value(struct mixart_mgr *mgr,
  */
 struct snd_mixart_elf32_ehdr {
 	u8      e_ident[16];
-	u16     e_type;
-	u16     e_machine;
-	u32     e_version;
-	u32     e_entry;
-	u32     e_phoff;
-	u32     e_shoff;
-	u32     e_flags;
-	u16     e_ehsize;
-	u16     e_phentsize;
-	u16     e_phnum;
-	u16     e_shentsize;
-	u16     e_shnum;
-	u16     e_shstrndx;
+	__be16  e_type;
+	__be16  e_machine;
+	__be32  e_version;
+	__be32  e_entry;
+	__be32  e_phoff;
+	__be32  e_shoff;
+	__be32  e_flags;
+	__be16  e_ehsize;
+	__be16  e_phentsize;
+	__be16  e_phnum;
+	__be16  e_shentsize;
+	__be16  e_shnum;
+	__be16  e_shstrndx;
 };
 
 struct snd_mixart_elf32_phdr {
-	u32     p_type;
-	u32     p_offset;
-	u32     p_vaddr;
-	u32     p_paddr;
-	u32     p_filesz;
-	u32     p_memsz;
-	u32     p_flags;
-	u32     p_align;
+	__be32  p_type;
+	__be32  p_offset;
+	__be32  p_vaddr;
+	__be32  p_paddr;
+	__be32  p_filesz;
+	__be32  p_memsz;
+	__be32  p_flags;
+	__be32  p_align;
 };
 
 static int mixart_load_elf(struct mixart_mgr *mgr, const struct firmware *dsp )
diff --git a/sound/pci/mixart/mixart_hwdep.h b/sound/pci/mixart/mixart_hwdep.h
index 812e288ef2e7..2794cd385b8e 100644
--- a/sound/pci/mixart/mixart_hwdep.h
+++ b/sound/pci/mixart/mixart_hwdep.h
@@ -26,19 +26,19 @@
 #include <sound/hwdep.h>
 
 #ifndef readl_be
-#define readl_be(x) be32_to_cpu(__raw_readl(x))
+#define readl_be(x) be32_to_cpu((__force __be32)__raw_readl(x))
 #endif
 
 #ifndef writel_be
-#define writel_be(data,addr) __raw_writel(cpu_to_be32(data),addr)
+#define writel_be(data,addr) __raw_writel((__force u32)cpu_to_be32(data),addr)
 #endif
 
 #ifndef readl_le
-#define readl_le(x) le32_to_cpu(__raw_readl(x))
+#define readl_le(x) le32_to_cpu((__force __le32)__raw_readl(x))
 #endif
 
 #ifndef writel_le
-#define writel_le(data,addr) __raw_writel(cpu_to_le32(data),addr)
+#define writel_le(data,addr) __raw_writel((__force u32)cpu_to_le32(data),addr)
 #endif
 
 #define MIXART_MEM(mgr,x)	((mgr)->mem[0].virt + (x))
diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index 44f3b48d47b1..23017e3bc76c 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -470,10 +470,10 @@ struct snd_riptide {
 };
 
 struct sgd {			/* scatter gather desriptor */
-	u32 dwNextLink;
-	u32 dwSegPtrPhys;
-	u32 dwSegLen;
-	u32 dwStat_Ctl;
+	__le32 dwNextLink;
+	__le32 dwSegPtrPhys;
+	__le32 dwSegLen;
+	__le32 dwStat_Ctl;
 };
 
 struct pcmhw {			/* pcm descriptor */
@@ -1017,7 +1017,7 @@ getsamplerate(struct cmdif *cif, unsigned char *intdec, unsigned int *rate)
 static int
 setsampleformat(struct cmdif *cif,
 		unsigned char mixer, unsigned char id,
-		unsigned char channels, unsigned char format)
+		unsigned char channels, snd_pcm_format_t format)
 {
 	unsigned char w, ch, sig, order;
 
diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c
index 7fbdb703bfcd..7218f38b59db 100644
--- a/sound/pci/sonicvibes.c
+++ b/sound/pci/sonicvibes.c
@@ -1433,14 +1433,12 @@ static int snd_sonicvibes_midi(struct sonicvibes *sonic,
 {
 	struct snd_mpu401 * mpu = rmidi->private_data;
 	struct snd_card *card = sonic->card;
-	struct snd_rawmidi_str *dir;
 	unsigned int idx;
 	int err;
 
 	mpu->private_data = sonic;
 	mpu->open_input = snd_sonicvibes_midi_input_open;
 	mpu->close_input = snd_sonicvibes_midi_input_close;
-	dir = &rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT];
 	for (idx = 0; idx < ARRAY_SIZE(snd_sonicvibes_midi_controls); idx++)
 		if ((err = snd_ctl_add(card, snd_ctl_new1(&snd_sonicvibes_midi_controls[idx], sonic))) < 0)
 			return err;
diff --git a/sound/pci/trident/trident.c b/sound/pci/trident/trident.c
index cedf13b64803..2f18b1cdc2cd 100644
--- a/sound/pci/trident/trident.c
+++ b/sound/pci/trident/trident.c
@@ -123,7 +123,7 @@ static int snd_trident_probe(struct pci_dev *pci,
 	} else {
 		strcpy(card->shortname, "Trident ");
 	}
-	strcat(card->shortname, card->driver);
+	strcat(card->shortname, str);
 	sprintf(card->longname, "%s PCI Audio at 0x%lx, irq %d",
 		card->shortname, trident->port, trident->irq);
 
diff --git a/sound/pci/trident/trident.h b/sound/pci/trident/trident.h
index 9624e5937719..2d62c1921255 100644
--- a/sound/pci/trident/trident.h
+++ b/sound/pci/trident/trident.h
@@ -264,7 +264,7 @@ struct snd_trident_memblk_arg {
 };
 
 struct snd_trident_tlb {
-	unsigned int * entries;		/* 16k-aligned TLB table */
+	__le32 *entries;		/* 16k-aligned TLB table */
 	dma_addr_t entries_dmaaddr;	/* 16k-aligned PCI address to TLB table */
 	unsigned long * shadow_entries;	/* shadow entries with virtual addresses */
 	struct snd_dma_buffer buffer;
diff --git a/sound/pci/trident/trident_main.c b/sound/pci/trident/trident_main.c
index 49c64fae3466..5523e193d556 100644
--- a/sound/pci/trident/trident_main.c
+++ b/sound/pci/trident/trident_main.c
@@ -3359,7 +3359,7 @@ static int snd_trident_tlb_alloc(struct snd_trident *trident)
 		dev_err(trident->card->dev, "unable to allocate TLB buffer\n");
 		return -ENOMEM;
 	}
-	trident->tlb.entries = (unsigned int*)ALIGN((unsigned long)trident->tlb.buffer.area, SNDRV_TRIDENT_MAX_PAGES * 4);
+	trident->tlb.entries = (__le32 *)ALIGN((unsigned long)trident->tlb.buffer.area, SNDRV_TRIDENT_MAX_PAGES * 4);
 	trident->tlb.entries_dmaaddr = ALIGN(trident->tlb.buffer.addr, SNDRV_TRIDENT_MAX_PAGES * 4);
 	/* allocate shadow TLB page table (virtual addresses) */
 	trident->tlb.shadow_entries =
diff --git a/sound/pci/vx222/vx222_ops.c b/sound/pci/vx222/vx222_ops.c
index d4298af6d3ee..c0d0bf44f365 100644
--- a/sound/pci/vx222/vx222_ops.c
+++ b/sound/pci/vx222/vx222_ops.c
@@ -275,7 +275,7 @@ static void vx2_dma_write(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 		length >>= 2; /* in 32bit words */
 		/* Transfer using pseudo-dma. */
 		for (; length > 0; length--) {
-			outl(cpu_to_le32(*addr), port);
+			outl(*addr, port);
 			addr++;
 		}
 		addr = (u32 *)runtime->dma_area;
@@ -285,7 +285,7 @@ static void vx2_dma_write(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 	count >>= 2; /* in 32bit words */
 	/* Transfer using pseudo-dma. */
 	for (; count > 0; count--) {
-		outl(cpu_to_le32(*addr), port);
+		outl(*addr, port);
 		addr++;
 	}
 
@@ -313,7 +313,7 @@ static void vx2_dma_read(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 		length >>= 2; /* in 32bit words */
 		/* Transfer using pseudo-dma. */
 		for (; length > 0; length--)
-			*addr++ = le32_to_cpu(inl(port));
+			*addr++ = inl(port);
 		addr = (u32 *)runtime->dma_area;
 		pipe->hw_ptr = 0;
 	}
@@ -321,7 +321,7 @@ static void vx2_dma_read(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 	count >>= 2; /* in 32bit words */
 	/* Transfer using pseudo-dma. */
 	for (; count > 0; count--)
-		*addr++ = le32_to_cpu(inl(port));
+		*addr++ = inl(port);
 
 	vx2_release_pseudo_dma(chip);
 }
diff --git a/sound/pci/ymfpci/ymfpci.h b/sound/pci/ymfpci/ymfpci.h
index aa9bb065f385..e2fa7e360d79 100644
--- a/sound/pci/ymfpci/ymfpci.h
+++ b/sound/pci/ymfpci/ymfpci.h
@@ -185,50 +185,50 @@
  */
 
 struct snd_ymfpci_playback_bank {
-	u32 format;
-	u32 loop_default;
-	u32 base;			/* 32-bit address */
-	u32 loop_start;			/* 32-bit offset */
-	u32 loop_end;			/* 32-bit offset */
-	u32 loop_frac;			/* 8-bit fraction - loop_start */
-	u32 delta_end;			/* pitch delta end */
-	u32 lpfK_end;
-	u32 eg_gain_end;
-	u32 left_gain_end;
-	u32 right_gain_end;
-	u32 eff1_gain_end;
-	u32 eff2_gain_end;
-	u32 eff3_gain_end;
-	u32 lpfQ;
-	u32 status;
-	u32 num_of_frames;
-	u32 loop_count;
-	u32 start;
-	u32 start_frac;
-	u32 delta;
-	u32 lpfK;
-	u32 eg_gain;
-	u32 left_gain;
-	u32 right_gain;
-	u32 eff1_gain;
-	u32 eff2_gain;
-	u32 eff3_gain;
-	u32 lpfD1;
-	u32 lpfD2;
+	__le32 format;
+	__le32 loop_default;
+	__le32 base;			/* 32-bit address */
+	__le32 loop_start;		/* 32-bit offset */
+	__le32 loop_end;		/* 32-bit offset */
+	__le32 loop_frac;		/* 8-bit fraction - loop_start */
+	__le32 delta_end;		/* pitch delta end */
+	__le32 lpfK_end;
+	__le32 eg_gain_end;
+	__le32 left_gain_end;
+	__le32 right_gain_end;
+	__le32 eff1_gain_end;
+	__le32 eff2_gain_end;
+	__le32 eff3_gain_end;
+	__le32 lpfQ;
+	__le32 status;
+	__le32 num_of_frames;
+	__le32 loop_count;
+	__le32 start;
+	__le32 start_frac;
+	__le32 delta;
+	__le32 lpfK;
+	__le32 eg_gain;
+	__le32 left_gain;
+	__le32 right_gain;
+	__le32 eff1_gain;
+	__le32 eff2_gain;
+	__le32 eff3_gain;
+	__le32 lpfD1;
+	__le32 lpfD2;
  };
 
 struct snd_ymfpci_capture_bank {
-	u32 base;			/* 32-bit address */
-	u32 loop_end;			/* 32-bit offset */
-	u32 start;			/* 32-bit offset */
-	u32 num_of_loops;		/* counter */
+	__le32 base;			/* 32-bit address */
+	__le32 loop_end;		/* 32-bit offset */
+	__le32 start;			/* 32-bit offset */
+	__le32 num_of_loops;		/* counter */
 };
 
 struct snd_ymfpci_effect_bank {
-	u32 base;			/* 32-bit address */
-	u32 loop_end;			/* 32-bit offset */
-	u32 start;			/* 32-bit offset */
-	u32 temp;
+	__le32 base;			/* 32-bit address */
+	__le32 loop_end;		/* 32-bit offset */
+	__le32 start;			/* 32-bit offset */
+	__le32 temp;
 };
 
 struct snd_ymfpci_pcm;
@@ -316,7 +316,7 @@ struct snd_ymfpci {
 	dma_addr_t work_base_addr;
 	struct snd_dma_buffer ac3_tmp_base;
 
-	u32 *ctrl_playback;
+	__le32 *ctrl_playback;
 	struct snd_ymfpci_playback_bank *bank_playback[YDSXG_PLAYBACK_VOICES][2];
 	struct snd_ymfpci_capture_bank *bank_capture[YDSXG_CAPTURE_VOICES][2];
 	struct snd_ymfpci_effect_bank *bank_effect[YDSXG_EFFECT_VOICES][2];
diff --git a/sound/pci/ymfpci/ymfpci_main.c b/sound/pci/ymfpci/ymfpci_main.c
index 6f81396aadc9..a4926fb03991 100644
--- a/sound/pci/ymfpci/ymfpci_main.c
+++ b/sound/pci/ymfpci/ymfpci_main.c
@@ -336,7 +336,7 @@ static void snd_ymfpci_pcm_interrupt(struct snd_ymfpci *chip, struct snd_ymfpci_
 			unsigned int subs = ypcm->substream->number;
 			unsigned int next_bank = 1 - chip->active_bank;
 			struct snd_ymfpci_playback_bank *bank;
-			u32 volume;
+			__le32 volume;
 			
 			bank = &voice->bank[next_bank];
 			volume = cpu_to_le32(chip->pcm_mixer[subs].left << 15);
@@ -505,7 +505,7 @@ static void snd_ymfpci_pcm_init_voice(struct snd_ymfpci_pcm *ypcm, unsigned int
 	u32 lpfK = snd_ymfpci_calc_lpfK(runtime->rate);
 	struct snd_ymfpci_playback_bank *bank;
 	unsigned int nbank;
-	u32 vol_left, vol_right;
+	__le32 vol_left, vol_right;
 	u8 use_left, use_right;
 	unsigned long flags;
 
@@ -2135,7 +2135,7 @@ static int snd_ymfpci_memalloc(struct snd_ymfpci *chip)
 
 	chip->bank_base_playback = ptr;
 	chip->bank_base_playback_addr = ptr_addr;
-	chip->ctrl_playback = (u32 *)ptr;
+	chip->ctrl_playback = (__le32 *)ptr;
 	chip->ctrl_playback[0] = cpu_to_le32(YDSXG_PLAYBACK_VOICES);
 	ptr += ALIGN(playback_ctrl_size, 0x100);
 	ptr_addr += ALIGN(playback_ctrl_size, 0x100);
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
index 4a2354b5ae00..98a6863e933c 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
@@ -276,7 +276,6 @@ static const struct snd_pcm_ops pdacf_pcm_capture_ops = {
 	.trigger =	pdacf_pcm_trigger,
 	.pointer =	pdacf_pcm_capture_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 
diff --git a/sound/pcmcia/vx/vxp_ops.c b/sound/pcmcia/vx/vxp_ops.c
index 8cde40226355..4c4ef1fec69f 100644
--- a/sound/pcmcia/vx/vxp_ops.c
+++ b/sound/pcmcia/vx/vxp_ops.c
@@ -375,7 +375,7 @@ static void vxp_dma_write(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 		length >>= 1; /* in 16bit words */
 		/* Transfer using pseudo-dma. */
 		for (; length > 0; length--) {
-			outw(cpu_to_le16(*addr), port);
+			outw(*addr, port);
 			addr++;
 		}
 		addr = (unsigned short *)runtime->dma_area;
@@ -385,7 +385,7 @@ static void vxp_dma_write(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 	count >>= 1; /* in 16bit words */
 	/* Transfer using pseudo-dma. */
 	for (; count > 0; count--) {
-		outw(cpu_to_le16(*addr), port);
+		outw(*addr, port);
 		addr++;
 	}
 	vx_release_pseudo_dma(chip);
@@ -417,7 +417,7 @@ static void vxp_dma_read(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 		length >>= 1; /* in 16bit words */
 		/* Transfer using pseudo-dma. */
 		for (; length > 0; length--)
-			*addr++ = le16_to_cpu(inw(port));
+			*addr++ = inw(port);
 		addr = (unsigned short *)runtime->dma_area;
 		pipe->hw_ptr = 0;
 	}
@@ -425,12 +425,12 @@ static void vxp_dma_read(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 	count >>= 1; /* in 16bit words */
 	/* Transfer using pseudo-dma. */
 	for (; count > 1; count--)
-		*addr++ = le16_to_cpu(inw(port));
+		*addr++ = inw(port);
 	/* Disable DMA */
 	pchip->regDIALOG &= ~VXP_DLG_DMAREAD_SEL_MASK;
 	vx_outb(chip, DIALOG, pchip->regDIALOG);
 	/* Read the last word (16 bits) */
-	*addr = le16_to_cpu(inw(port));
+	*addr = inw(port);
 	/* Disable 16-bit accesses */
 	pchip->regDIALOG &= ~VXP_DLG_DMA16_SEL_MASK;
 	vx_outb(chip, DIALOG, pchip->regDIALOG);
diff --git a/sound/soc/Kconfig b/sound/soc/Kconfig
index 41af6b9cc350..1cf11cf51e1d 100644
--- a/sound/soc/Kconfig
+++ b/sound/soc/Kconfig
@@ -57,6 +57,7 @@ source "sound/soc/kirkwood/Kconfig"
 source "sound/soc/img/Kconfig"
 source "sound/soc/intel/Kconfig"
 source "sound/soc/mediatek/Kconfig"
+source "sound/soc/meson/Kconfig"
 source "sound/soc/mxs/Kconfig"
 source "sound/soc/pxa/Kconfig"
 source "sound/soc/qcom/Kconfig"
diff --git a/sound/soc/Makefile b/sound/soc/Makefile
index 06389a5385d7..62a5f87c3cfc 100644
--- a/sound/soc/Makefile
+++ b/sound/soc/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_SND_SOC)	+= jz4740/
 obj-$(CONFIG_SND_SOC)	+= img/
 obj-$(CONFIG_SND_SOC)	+= intel/
 obj-$(CONFIG_SND_SOC)	+= mediatek/
+obj-$(CONFIG_SND_SOC)	+= meson/
 obj-$(CONFIG_SND_SOC)	+= mxs/
 obj-$(CONFIG_SND_SOC)	+= nuc900/
 obj-$(CONFIG_SND_SOC)	+= omap/
diff --git a/sound/soc/amd/Kconfig b/sound/soc/amd/Kconfig
index 6cbf9cf4d1a4..58c1dcb4d255 100644
--- a/sound/soc/amd/Kconfig
+++ b/sound/soc/amd/Kconfig
@@ -8,6 +8,7 @@ config SND_SOC_AMD_CZ_DA7219MX98357_MACH
 	select SND_SOC_DA7219
 	select SND_SOC_MAX98357A
 	select SND_SOC_ADAU7002
+	select REGULATOR
 	depends on SND_SOC_AMD_ACP && I2C
 	help
 	 This option enables machine driver for DA7219 and MAX9835.
diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c
index ccddc6650b9c..8e3275a96a82 100644
--- a/sound/soc/amd/acp-da7219-max98357a.c
+++ b/sound/soc/amd/acp-da7219-max98357a.c
@@ -32,6 +32,8 @@
 #include <linux/clk.h>
 #include <linux/gpio.h>
 #include <linux/module.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/driver.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
 #include <linux/acpi.h>
@@ -148,7 +150,8 @@ static int cz_da7219_startup(struct snd_pcm_substream *substream)
 	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
 				   &constraints_rates);
 
-	machine->i2s_instance = I2S_BT_INSTANCE;
+	machine->i2s_instance = I2S_SP_INSTANCE;
+	machine->capture_channel = CAP_CHANNEL1;
 	return da7219_clk_enable(substream);
 }
 
@@ -163,7 +166,7 @@ static int cz_max_startup(struct snd_pcm_substream *substream)
 	struct snd_soc_card *card = rtd->card;
 	struct acp_platform_info *machine = snd_soc_card_get_drvdata(card);
 
-	machine->i2s_instance = I2S_SP_INSTANCE;
+	machine->i2s_instance = I2S_BT_INSTANCE;
 	return da7219_clk_enable(substream);
 }
 
@@ -172,13 +175,24 @@ static void cz_max_shutdown(struct snd_pcm_substream *substream)
 	da7219_clk_disable();
 }
 
-static int cz_dmic_startup(struct snd_pcm_substream *substream)
+static int cz_dmic0_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct acp_platform_info *machine = snd_soc_card_get_drvdata(card);
+
+	machine->i2s_instance = I2S_BT_INSTANCE;
+	return da7219_clk_enable(substream);
+}
+
+static int cz_dmic1_startup(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_card *card = rtd->card;
 	struct acp_platform_info *machine = snd_soc_card_get_drvdata(card);
 
 	machine->i2s_instance = I2S_SP_INSTANCE;
+	machine->capture_channel = CAP_CHANNEL0;
 	return da7219_clk_enable(substream);
 }
 
@@ -197,23 +211,39 @@ static const struct snd_soc_ops cz_max_play_ops = {
 	.shutdown = cz_max_shutdown,
 };
 
-static const struct snd_soc_ops cz_dmic_cap_ops = {
-	.startup = cz_dmic_startup,
+static const struct snd_soc_ops cz_dmic0_cap_ops = {
+	.startup = cz_dmic0_startup,
+	.shutdown = cz_dmic_shutdown,
+};
+
+static const struct snd_soc_ops cz_dmic1_cap_ops = {
+	.startup = cz_dmic1_startup,
 	.shutdown = cz_dmic_shutdown,
 };
 
 static struct snd_soc_dai_link cz_dai_7219_98357[] = {
 	{
-		.name = "amd-da7219-play-cap",
-		.stream_name = "Playback and Capture",
+		.name = "amd-da7219-play",
+		.stream_name = "Playback",
 		.platform_name = "acp_audio_dma.0.auto",
-		.cpu_dai_name = "designware-i2s.3.auto",
+		.cpu_dai_name = "designware-i2s.1.auto",
 		.codec_dai_name = "da7219-hifi",
 		.codec_name = "i2c-DLGS7219:00",
 		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
 				| SND_SOC_DAIFMT_CBM_CFM,
 		.init = cz_da7219_init,
 		.dpcm_playback = 1,
+		.ops = &cz_da7219_cap_ops,
+	},
+	{
+		.name = "amd-da7219-cap",
+		.stream_name = "Capture",
+		.platform_name = "acp_audio_dma.0.auto",
+		.cpu_dai_name = "designware-i2s.2.auto",
+		.codec_dai_name = "da7219-hifi",
+		.codec_name = "i2c-DLGS7219:00",
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
+				| SND_SOC_DAIFMT_CBM_CFM,
 		.dpcm_capture = 1,
 		.ops = &cz_da7219_cap_ops,
 	},
@@ -221,7 +251,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = {
 		.name = "amd-max98357-play",
 		.stream_name = "HiFi Playback",
 		.platform_name = "acp_audio_dma.0.auto",
-		.cpu_dai_name = "designware-i2s.1.auto",
+		.cpu_dai_name = "designware-i2s.3.auto",
 		.codec_dai_name = "HiFi",
 		.codec_name = "MX98357A:00",
 		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
@@ -230,8 +260,22 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = {
 		.ops = &cz_max_play_ops,
 	},
 	{
-		.name = "dmic",
-		.stream_name = "DMIC Capture",
+		/* C panel DMIC */
+		.name = "dmic0",
+		.stream_name = "DMIC0 Capture",
+		.platform_name = "acp_audio_dma.0.auto",
+		.cpu_dai_name = "designware-i2s.3.auto",
+		.codec_dai_name = "adau7002-hifi",
+		.codec_name = "ADAU7002:00",
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
+				| SND_SOC_DAIFMT_CBM_CFM,
+		.dpcm_capture = 1,
+		.ops = &cz_dmic0_cap_ops,
+	},
+	{
+		/* A/B panel DMIC */
+		.name = "dmic1",
+		.stream_name = "DMIC1 Capture",
 		.platform_name = "acp_audio_dma.0.auto",
 		.cpu_dai_name = "designware-i2s.2.auto",
 		.codec_dai_name = "adau7002-hifi",
@@ -239,7 +283,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = {
 		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
 				| SND_SOC_DAIFMT_CBM_CFM,
 		.dpcm_capture = 1,
-		.ops = &cz_dmic_cap_ops,
+		.ops = &cz_dmic1_cap_ops,
 	},
 };
 
@@ -278,11 +322,52 @@ static struct snd_soc_card cz_card = {
 	.num_controls = ARRAY_SIZE(cz_mc_controls),
 };
 
+static struct regulator_consumer_supply acp_da7219_supplies[] = {
+	REGULATOR_SUPPLY("VDD", "i2c-DLGS7219:00"),
+	REGULATOR_SUPPLY("VDDMIC", "i2c-DLGS7219:00"),
+	REGULATOR_SUPPLY("VDDIO", "i2c-DLGS7219:00"),
+	REGULATOR_SUPPLY("IOVDD", "ADAU7002:00"),
+};
+
+static struct regulator_init_data acp_da7219_data = {
+	.constraints = {
+		.always_on = 1,
+	},
+	.num_consumer_supplies = ARRAY_SIZE(acp_da7219_supplies),
+	.consumer_supplies = acp_da7219_supplies,
+};
+
+static struct regulator_config acp_da7219_cfg = {
+	.init_data = &acp_da7219_data,
+};
+
+static struct regulator_ops acp_da7219_ops = {
+};
+
+static struct regulator_desc acp_da7219_desc = {
+	.name = "reg-fixed-1.8V",
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+	.ops = &acp_da7219_ops,
+	.fixed_uV = 1800000, /* 1.8V */
+	.n_voltages = 1,
+};
+
 static int cz_probe(struct platform_device *pdev)
 {
 	int ret;
 	struct snd_soc_card *card;
 	struct acp_platform_info *machine;
+	struct regulator_dev *rdev;
+
+	acp_da7219_cfg.dev = &pdev->dev;
+	rdev = devm_regulator_register(&pdev->dev, &acp_da7219_desc,
+				       &acp_da7219_cfg);
+	if (IS_ERR(rdev)) {
+		dev_err(&pdev->dev, "Failed to register regulator: %d\n",
+			(int)PTR_ERR(rdev));
+		return -EINVAL;
+	}
 
 	machine = devm_kzalloc(&pdev->dev, sizeof(struct acp_platform_info),
 			       GFP_KERNEL);
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 77203841c535..e359938e3d7e 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -224,13 +224,11 @@ static void set_acp_sysmem_dma_descriptors(void __iomem *acp_mmio,
 			switch (asic_type) {
 			case CHIP_STONEY:
 				dmadscr[i].xfer_val |=
-				BIT(22) |
 				(ACP_DMA_ATTR_SHARED_MEM_TO_DAGB_GARLIC << 16) |
 				(size / 2);
 				break;
 			default:
 				dmadscr[i].xfer_val |=
-				BIT(22) |
 				(ACP_DMA_ATTR_SHAREDMEM_TO_DAGB_ONION << 16) |
 				(size / 2);
 			}
@@ -322,22 +320,87 @@ static void config_acp_dma(void __iomem *acp_mmio,
 			   struct audio_substream_data *rtd,
 			   u32 asic_type)
 {
+	u16 ch_acp_sysmem, ch_acp_i2s;
+
 	acp_pte_config(acp_mmio, rtd->pg, rtd->num_of_pages,
 		       rtd->pte_offset);
+
+	if (rtd->direction == SNDRV_PCM_STREAM_PLAYBACK) {
+		ch_acp_sysmem = rtd->ch1;
+		ch_acp_i2s = rtd->ch2;
+	} else {
+		ch_acp_i2s = rtd->ch1;
+		ch_acp_sysmem = rtd->ch2;
+	}
 	/* Configure System memory <-> ACP SRAM DMA descriptors */
 	set_acp_sysmem_dma_descriptors(acp_mmio, rtd->size,
 				       rtd->direction, rtd->pte_offset,
-				       rtd->ch1, rtd->sram_bank,
+				       ch_acp_sysmem, rtd->sram_bank,
 				       rtd->dma_dscr_idx_1, asic_type);
 	/* Configure ACP SRAM <-> I2S DMA descriptors */
 	set_acp_to_i2s_dma_descriptors(acp_mmio, rtd->size,
 				       rtd->direction, rtd->sram_bank,
-				       rtd->destination, rtd->ch2,
+				       rtd->destination, ch_acp_i2s,
 				       rtd->dma_dscr_idx_2, asic_type);
 }
 
+static void acp_dma_cap_channel_enable(void __iomem *acp_mmio,
+				       u16 cap_channel)
+{
+	u32 val, ch_reg, imr_reg, res_reg;
+
+	switch (cap_channel) {
+	case CAP_CHANNEL1:
+		ch_reg = mmACP_I2SMICSP_RER1;
+		res_reg = mmACP_I2SMICSP_RCR1;
+		imr_reg = mmACP_I2SMICSP_IMR1;
+		break;
+	case CAP_CHANNEL0:
+	default:
+		ch_reg = mmACP_I2SMICSP_RER0;
+		res_reg = mmACP_I2SMICSP_RCR0;
+		imr_reg = mmACP_I2SMICSP_IMR0;
+		break;
+	}
+	val = acp_reg_read(acp_mmio,
+			   mmACP_I2S_16BIT_RESOLUTION_EN);
+	if (val & ACP_I2S_MIC_16BIT_RESOLUTION_EN) {
+		acp_reg_write(0x0, acp_mmio, ch_reg);
+		/* Set 16bit resolution on capture */
+		acp_reg_write(0x2, acp_mmio, res_reg);
+	}
+	val = acp_reg_read(acp_mmio, imr_reg);
+	val &= ~ACP_I2SMICSP_IMR1__I2SMICSP_RXDAM_MASK;
+	val &= ~ACP_I2SMICSP_IMR1__I2SMICSP_RXFOM_MASK;
+	acp_reg_write(val, acp_mmio, imr_reg);
+	acp_reg_write(0x1, acp_mmio, ch_reg);
+}
+
+static void acp_dma_cap_channel_disable(void __iomem *acp_mmio,
+					u16 cap_channel)
+{
+	u32 val, ch_reg, imr_reg;
+
+	switch (cap_channel) {
+	case CAP_CHANNEL1:
+		imr_reg = mmACP_I2SMICSP_IMR1;
+		ch_reg = mmACP_I2SMICSP_RER1;
+		break;
+	case CAP_CHANNEL0:
+	default:
+		imr_reg = mmACP_I2SMICSP_IMR0;
+		ch_reg = mmACP_I2SMICSP_RER0;
+		break;
+	}
+	val = acp_reg_read(acp_mmio, imr_reg);
+	val |= ACP_I2SMICSP_IMR1__I2SMICSP_RXDAM_MASK;
+	val |= ACP_I2SMICSP_IMR1__I2SMICSP_RXFOM_MASK;
+	acp_reg_write(val, acp_mmio, imr_reg);
+	acp_reg_write(0x0, acp_mmio, ch_reg);
+}
+
 /* Start a given DMA channel transfer */
-static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num)
+static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num, bool is_circular)
 {
 	u32 dma_ctrl;
 
@@ -356,10 +419,8 @@ static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num)
 
 	switch (ch_num) {
 	case ACP_TO_I2S_DMA_CH_NUM:
-	case ACP_TO_SYSRAM_CH_NUM:
 	case I2S_TO_ACP_DMA_CH_NUM:
 	case ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM:
-	case ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM:
 	case I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM:
 		dma_ctrl |= ACP_DMA_CNTL_0__DMAChIOCEn_MASK;
 		break;
@@ -368,8 +429,11 @@ static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num)
 		break;
 	}
 
-	/* circular for both DMA channel */
-	dma_ctrl |= ACP_DMA_CNTL_0__Circular_DMA_En_MASK;
+	/* enable for ACP to SRAM DMA channel */
+	if (is_circular == true)
+		dma_ctrl |= ACP_DMA_CNTL_0__Circular_DMA_En_MASK;
+	else
+		dma_ctrl &= ~ACP_DMA_CNTL_0__Circular_DMA_En_MASK;
 
 	acp_reg_write(dma_ctrl, acp_mmio, mmACP_DMA_CNTL_0 + ch_num);
 }
@@ -613,6 +677,7 @@ static int acp_deinit(void __iomem *acp_mmio)
 /* ACP DMA irq handler routine for playback, capture usecases */
 static irqreturn_t dma_irq_handler(int irq, void *arg)
 {
+	u16 dscr_idx;
 	u32 intr_flag, ext_intr_status;
 	struct audio_drv_data *irq_data;
 	void __iomem *acp_mmio;
@@ -644,32 +709,39 @@ static irqreturn_t dma_irq_handler(int irq, void *arg)
 
 	if ((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) != 0) {
 		valid_irq = true;
+		if (acp_reg_read(acp_mmio, mmACP_DMA_CUR_DSCR_14) ==
+				CAPTURE_START_DMA_DESCR_CH15)
+			dscr_idx = CAPTURE_END_DMA_DESCR_CH14;
+		else
+			dscr_idx = CAPTURE_START_DMA_DESCR_CH14;
+		config_acp_dma_channel(acp_mmio, ACP_TO_SYSRAM_CH_NUM, dscr_idx,
+				       1, 0);
+		acp_dma_start(acp_mmio, ACP_TO_SYSRAM_CH_NUM, false);
+
 		snd_pcm_period_elapsed(irq_data->capture_i2ssp_stream);
 		acp_reg_write((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) << 16,
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) != 0) {
-		valid_irq = true;
-		acp_reg_write((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) << 16,
-			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
-	}
-
 	if ((intr_flag & BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) != 0) {
 		valid_irq = true;
+		if (acp_reg_read(acp_mmio, mmACP_DMA_CUR_DSCR_10) ==
+			CAPTURE_START_DMA_DESCR_CH11)
+			dscr_idx = CAPTURE_END_DMA_DESCR_CH10;
+		else
+			dscr_idx = CAPTURE_START_DMA_DESCR_CH10;
+		config_acp_dma_channel(acp_mmio,
+				       ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM,
+				       dscr_idx, 1, 0);
+		acp_dma_start(acp_mmio, ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM,
+			      false);
+
 		snd_pcm_period_elapsed(irq_data->capture_i2sbt_stream);
 		acp_reg_write((intr_flag &
 			      BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) << 16,
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) != 0) {
-		valid_irq = true;
-		acp_reg_write((intr_flag &
-			      BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) << 16,
-			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
-	}
-
 	if (valid_irq)
 		return IRQ_HANDLED;
 	else
@@ -773,7 +845,10 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 	if (WARN_ON(!rtd))
 		return -EINVAL;
 
-	rtd->i2s_instance = pinfo->i2s_instance;
+	if (pinfo) {
+		rtd->i2s_instance = pinfo->i2s_instance;
+		rtd->capture_channel = pinfo->capture_channel;
+	}
 	if (adata->asic_type == CHIP_STONEY) {
 		val = acp_reg_read(adata->acp_mmio,
 				   mmACP_I2S_16BIT_RESOLUTION_EN);
@@ -841,8 +916,8 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 		switch (rtd->i2s_instance) {
 		case I2S_BT_INSTANCE:
 			rtd->pte_offset = ACP_ST_BT_CAPTURE_PTE_OFFSET;
-			rtd->ch1 = ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM;
-			rtd->ch2 = I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM;
+			rtd->ch1 = I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM;
+			rtd->ch2 = ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM;
 			rtd->sram_bank = ACP_SRAM_BANK_4_ADDRESS;
 			rtd->destination = FROM_BLUETOOTH;
 			rtd->dma_dscr_idx_1 = CAPTURE_START_DMA_DESCR_CH10;
@@ -851,13 +926,14 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 					mmACP_I2S_BT_RECEIVE_BYTE_CNT_HIGH;
 			rtd->byte_cnt_low_reg_offset =
 					mmACP_I2S_BT_RECEIVE_BYTE_CNT_LOW;
+			rtd->dma_curr_dscr = mmACP_DMA_CUR_DSCR_11;
 			adata->capture_i2sbt_stream = substream;
 			break;
 		case I2S_SP_INSTANCE:
 		default:
 			rtd->pte_offset = ACP_CAPTURE_PTE_OFFSET;
-			rtd->ch1 = ACP_TO_SYSRAM_CH_NUM;
-			rtd->ch2 = I2S_TO_ACP_DMA_CH_NUM;
+			rtd->ch1 = I2S_TO_ACP_DMA_CH_NUM;
+			rtd->ch2 = ACP_TO_SYSRAM_CH_NUM;
 			switch (adata->asic_type) {
 			case CHIP_STONEY:
 				rtd->pte_offset = ACP_ST_CAPTURE_PTE_OFFSET;
@@ -874,6 +950,7 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 					mmACP_I2S_RECEIVED_BYTE_CNT_HIGH;
 			rtd->byte_cnt_low_reg_offset =
 					mmACP_I2S_RECEIVED_BYTE_CNT_LOW;
+			rtd->dma_curr_dscr = mmACP_DMA_CUR_DSCR_15;
 			adata->capture_i2ssp_stream = substream;
 		}
 	}
@@ -927,6 +1004,8 @@ static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
 	u32 buffersize;
 	u32 pos = 0;
 	u64 bytescount = 0;
+	u16 dscr;
+	u32 period_bytes, delay;
 
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
@@ -934,12 +1013,25 @@ static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
 	if (!rtd)
 		return -EINVAL;
 
-	buffersize = frames_to_bytes(runtime, runtime->buffer_size);
-	bytescount = acp_get_byte_count(rtd);
-
-	if (bytescount > rtd->bytescount)
-		bytescount -= rtd->bytescount;
-	pos = do_div(bytescount, buffersize);
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+		period_bytes = frames_to_bytes(runtime, runtime->period_size);
+		dscr = acp_reg_read(rtd->acp_mmio, rtd->dma_curr_dscr);
+		if (dscr == rtd->dma_dscr_idx_1)
+			pos = period_bytes;
+		else
+			pos = 0;
+		bytescount = acp_get_byte_count(rtd);
+		if (bytescount > rtd->bytescount)
+			bytescount -= rtd->bytescount;
+		delay = do_div(bytescount, period_bytes);
+		runtime->delay = bytes_to_frames(runtime, delay);
+	} else {
+		buffersize = frames_to_bytes(runtime, runtime->buffer_size);
+		bytescount = acp_get_byte_count(rtd);
+		if (bytescount > rtd->bytescount)
+			bytescount -= rtd->bytescount;
+		pos = do_div(bytescount, buffersize);
+	}
 	return bytes_to_frames(runtime, pos);
 }
 
@@ -953,16 +1045,24 @@ static int acp_dma_prepare(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
+	u16 ch_acp_sysmem, ch_acp_i2s;
 
 	if (!rtd)
 		return -EINVAL;
 
+	if (rtd->direction == SNDRV_PCM_STREAM_PLAYBACK) {
+		ch_acp_sysmem = rtd->ch1;
+		ch_acp_i2s = rtd->ch2;
+	} else {
+		ch_acp_i2s = rtd->ch1;
+		ch_acp_sysmem = rtd->ch2;
+	}
 	config_acp_dma_channel(rtd->acp_mmio,
-			       rtd->ch1,
+			       ch_acp_sysmem,
 			       rtd->dma_dscr_idx_1,
 			       NUM_DSCRS_PER_CHANNEL, 0);
 	config_acp_dma_channel(rtd->acp_mmio,
-			       rtd->ch2,
+			       ch_acp_i2s,
 			       rtd->dma_dscr_idx_2,
 			       NUM_DSCRS_PER_CHANNEL, 0);
 	return 0;
@@ -971,7 +1071,6 @@ static int acp_dma_prepare(struct snd_pcm_substream *substream)
 static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 {
 	int ret;
-	u64 bytescount = 0;
 
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
@@ -982,37 +1081,32 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 	case SNDRV_PCM_TRIGGER_RESUME:
-		bytescount = acp_get_byte_count(rtd);
-		if (rtd->bytescount == 0)
-			rtd->bytescount = bytescount;
-		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-			acp_dma_start(rtd->acp_mmio, rtd->ch1);
-			acp_dma_start(rtd->acp_mmio, rtd->ch2);
+		rtd->bytescount = acp_get_byte_count(rtd);
+		if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+			if (rtd->capture_channel == CAP_CHANNEL0) {
+				acp_dma_cap_channel_disable(rtd->acp_mmio,
+							    CAP_CHANNEL1);
+				acp_dma_cap_channel_enable(rtd->acp_mmio,
+							   CAP_CHANNEL0);
+			}
+			if (rtd->capture_channel == CAP_CHANNEL1) {
+				acp_dma_cap_channel_disable(rtd->acp_mmio,
+							    CAP_CHANNEL0);
+				acp_dma_cap_channel_enable(rtd->acp_mmio,
+							   CAP_CHANNEL1);
+			}
+			acp_dma_start(rtd->acp_mmio, rtd->ch1, true);
 		} else {
-			acp_dma_start(rtd->acp_mmio, rtd->ch2);
-			acp_dma_start(rtd->acp_mmio, rtd->ch1);
+			acp_dma_start(rtd->acp_mmio, rtd->ch1, true);
+			acp_dma_start(rtd->acp_mmio, rtd->ch2, true);
 		}
 		ret = 0;
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
-		/* For playback, non circular dma should be stopped first
-		 * i.e Sysram to acp dma transfer channel(rtd->ch1) should be
-		 * stopped before stopping cirular dma which is acp sram to i2s
-		 * fifo dma transfer channel(rtd->ch2). Where as in Capture
-		 * scenario, i2s fifo to acp sram dma channel(rtd->ch2) stopped
-		 * first before stopping acp sram to sysram which is circular
-		 * dma(rtd->ch1).
-		 */
-		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-			acp_dma_stop(rtd->acp_mmio, rtd->ch1);
-			ret =  acp_dma_stop(rtd->acp_mmio, rtd->ch2);
-		} else {
-			acp_dma_stop(rtd->acp_mmio, rtd->ch2);
-			ret = acp_dma_stop(rtd->acp_mmio, rtd->ch1);
-		}
-		rtd->bytescount = 0;
+		acp_dma_stop(rtd->acp_mmio, rtd->ch2);
+		ret = acp_dma_stop(rtd->acp_mmio, rtd->ch1);
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/sound/soc/amd/acp.h b/sound/soc/amd/acp.h
index 9cd3e96c84d4..be3963e8f4fa 100644
--- a/sound/soc/amd/acp.h
+++ b/sound/soc/amd/acp.h
@@ -55,6 +55,8 @@
 
 #define I2S_SP_INSTANCE                 0x01
 #define I2S_BT_INSTANCE                 0x02
+#define CAP_CHANNEL0			0x00
+#define CAP_CHANNEL1			0x01
 
 #define ACP_TILE_ON_MASK                0x03
 #define ACP_TILE_OFF_MASK               0x02
@@ -72,16 +74,16 @@
 #define ACP_TO_I2S_DMA_CH_NUM 13
 
 /* Capture DMA channels */
-#define ACP_TO_SYSRAM_CH_NUM 14
-#define I2S_TO_ACP_DMA_CH_NUM 15
+#define I2S_TO_ACP_DMA_CH_NUM 14
+#define ACP_TO_SYSRAM_CH_NUM 15
 
 /* Playback DMA Channels for I2S BT instance */
 #define SYSRAM_TO_ACP_BT_INSTANCE_CH_NUM  8
 #define ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM 9
 
 /* Capture DMA Channels for I2S BT Instance */
-#define ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM 10
-#define I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM 11
+#define I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM 10
+#define ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM 11
 
 #define NUM_DSCRS_PER_CHANNEL 2
 
@@ -125,6 +127,7 @@ struct audio_substream_data {
 	unsigned int order;
 	u16 num_of_pages;
 	u16 i2s_instance;
+	u16 capture_channel;
 	u16 direction;
 	u16 ch1;
 	u16 ch2;
@@ -135,6 +138,7 @@ struct audio_substream_data {
 	u32 sram_bank;
 	u32 byte_cnt_high_reg_offset;
 	u32 byte_cnt_low_reg_offset;
+	u32 dma_curr_dscr;
 	uint64_t size;
 	u64 bytescount;
 	void __iomem *acp_mmio;
@@ -155,6 +159,7 @@ struct audio_drv_data {
  */
 struct acp_platform_info {
 	u16 i2s_instance;
+	u16 capture_channel;
 };
 
 union acp_dma_count {
diff --git a/sound/soc/atmel/atmel-i2s.c b/sound/soc/atmel/atmel-i2s.c
index 5d3b5af9fd92..d88c1d995036 100644
--- a/sound/soc/atmel/atmel-i2s.c
+++ b/sound/soc/atmel/atmel-i2s.c
@@ -206,7 +206,6 @@ struct atmel_i2s_dev {
 	struct regmap				*regmap;
 	struct clk				*pclk;
 	struct clk				*gclk;
-	struct clk				*aclk;
 	struct snd_dmaengine_dai_dma_data	playback;
 	struct snd_dmaengine_dai_dma_data	capture;
 	unsigned int				fmt;
@@ -303,7 +302,7 @@ static int atmel_i2s_get_gck_param(struct atmel_i2s_dev *dev, int fs)
 {
 	int i, best;
 
-	if (!dev->gclk || !dev->aclk) {
+	if (!dev->gclk) {
 		dev_err(dev->dev, "cannot generate the I2S Master Clock\n");
 		return -EINVAL;
 	}
@@ -421,7 +420,7 @@ static int atmel_i2s_switch_mck_generator(struct atmel_i2s_dev *dev,
 					  bool enabled)
 {
 	unsigned int mr, mr_mask;
-	unsigned long aclk_rate;
+	unsigned long gclk_rate;
 	int ret;
 
 	mr = 0;
@@ -445,35 +444,18 @@ static int atmel_i2s_switch_mck_generator(struct atmel_i2s_dev *dev,
 		/* Disable/unprepare the PMC generated clock. */
 		clk_disable_unprepare(dev->gclk);
 
-		/* Disable/unprepare the PLL audio clock. */
-		clk_disable_unprepare(dev->aclk);
 		return 0;
 	}
 
 	if (!dev->gck_param)
 		return -EINVAL;
 
-	aclk_rate = dev->gck_param->mck * (dev->gck_param->imckdiv + 1);
+	gclk_rate = dev->gck_param->mck * (dev->gck_param->imckdiv + 1);
 
-	/* Fist change the PLL audio clock frequency ... */
-	ret = clk_set_rate(dev->aclk, aclk_rate);
+	ret = clk_set_rate(dev->gclk, gclk_rate);
 	if (ret)
 		return ret;
 
-	/*
-	 * ... then set the PMC generated clock rate to the very same frequency
-	 * to set the gclk parent to aclk.
-	 */
-	ret = clk_set_rate(dev->gclk, aclk_rate);
-	if (ret)
-		return ret;
-
-	/* Prepare and enable the PLL audio clock first ... */
-	ret = clk_prepare_enable(dev->aclk);
-	if (ret)
-		return ret;
-
-	/* ... then prepare and enable the PMC generated clock. */
 	ret = clk_prepare_enable(dev->gclk);
 	if (ret)
 		return ret;
@@ -668,28 +650,14 @@ static int atmel_i2s_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	/* Get audio clocks to generate the I2S Master Clock (I2S_MCK) */
-	dev->aclk = devm_clk_get(&pdev->dev, "aclk");
+	/* Get audio clock to generate the I2S Master Clock (I2S_MCK) */
 	dev->gclk = devm_clk_get(&pdev->dev, "gclk");
-	if (IS_ERR(dev->aclk) && IS_ERR(dev->gclk)) {
-		if (PTR_ERR(dev->aclk) == -EPROBE_DEFER ||
-		    PTR_ERR(dev->gclk) == -EPROBE_DEFER)
+	if (IS_ERR(dev->gclk)) {
+		if (PTR_ERR(dev->gclk) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
 		/* Master Mode not supported */
-		dev->aclk = NULL;
 		dev->gclk = NULL;
-	} else if (IS_ERR(dev->gclk)) {
-		err = PTR_ERR(dev->gclk);
-		dev_err(&pdev->dev,
-			"failed to get the PMC generated clock: %d\n", err);
-		return err;
-	} else if (IS_ERR(dev->aclk)) {
-		err = PTR_ERR(dev->aclk);
-		dev_err(&pdev->dev,
-			"failed to get the PLL audio clock: %d\n", err);
-		return err;
 	}
-
 	dev->dev = &pdev->dev;
 	dev->regmap = regmap;
 	platform_set_drvdata(pdev, dev);
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 63cf62e9c9aa..efb095dbcd71 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -74,12 +74,12 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_DA7219 if I2C
 	select SND_SOC_DA732X if I2C
 	select SND_SOC_DA9055 if I2C
-	select SND_SOC_DIO2125
 	select SND_SOC_DMIC if GPIOLIB
 	select SND_SOC_ES8316 if I2C
 	select SND_SOC_ES8328_SPI if SPI_MASTER
 	select SND_SOC_ES8328_I2C if I2C
 	select SND_SOC_ES7134
+	select SND_SOC_ES7241
 	select SND_SOC_GTM601
 	select SND_SOC_HDAC_HDMI
 	select SND_SOC_ICS43432
@@ -141,8 +141,10 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_RT5668 if I2C
 	select SND_SOC_RT5670 if I2C
 	select SND_SOC_RT5677 if I2C && SPI_MASTER
+	select SND_SOC_RT5682 if I2C
 	select SND_SOC_SGTL5000 if I2C
 	select SND_SOC_SI476X if MFD_SI476X_CORE
+	select SND_SOC_SIMPLE_AMPLIFIER
 	select SND_SOC_SIRF_AUDIO_CODEC
 	select SND_SOC_SPDIF
 	select SND_SOC_SSM2305
@@ -572,10 +574,6 @@ config SND_SOC_DA732X
 config SND_SOC_DA9055
 	tristate
 
-config SND_SOC_DIO2125
-	tristate "Dioo DIO2125 Amplifier"
-	select GPIOLIB
-
 config SND_SOC_DMIC
 	tristate
 
@@ -588,6 +586,9 @@ config SND_SOC_HDMI_CODEC
 config SND_SOC_ES7134
        tristate "Everest Semi ES7134 CODEC"
 
+config SND_SOC_ES7241
+       tristate "Everest Semi ES7241 CODEC"
+
 config SND_SOC_ES8316
 	tristate "Everest Semi ES8316 CODEC"
 	depends on I2C
@@ -778,6 +779,7 @@ config SND_SOC_RL6231
 	default y if SND_SOC_RT5668=y
 	default y if SND_SOC_RT5670=y
 	default y if SND_SOC_RT5677=y
+	default y if SND_SOC_RT5682=y
 	default y if SND_SOC_RT1305=y
 	default m if SND_SOC_RT5514=m
 	default m if SND_SOC_RT5616=m
@@ -791,6 +793,7 @@ config SND_SOC_RL6231
 	default m if SND_SOC_RT5668=m
 	default m if SND_SOC_RT5670=m
 	default m if SND_SOC_RT5677=m
+	default m if SND_SOC_RT5682=m
 	default m if SND_SOC_RT1305=m
 
 config SND_SOC_RL6347A
@@ -871,6 +874,9 @@ config SND_SOC_RT5677_SPI
 	tristate
 	default SND_SOC_RT5677 && SPI
 
+config SND_SOC_RT5682
+	tristate
+
 #Freescale sgtl5000 codec
 config SND_SOC_SGTL5000
 	tristate "Freescale SGTL5000 CODEC"
@@ -891,6 +897,10 @@ config SND_SOC_SIGMADSP_REGMAP
 	tristate
 	select SND_SOC_SIGMADSP
 
+config SND_SOC_SIMPLE_AMPLIFIER
+	tristate "Simple Audio Amplifier"
+	select GPIOLIB
+
 config SND_SOC_SIRF_AUDIO_CODEC
 	tristate "SiRF SoC internal audio codec"
 	select REGMAP_MMIO
@@ -953,8 +963,11 @@ config SND_SOC_TAS5086
 	depends on I2C
 
 config SND_SOC_TAS571X
-	tristate "Texas Instruments TAS5711/TAS5717/TAS5719/TAS5721 power amplifiers"
+	tristate "Texas Instruments TAS571x power amplifiers"
 	depends on I2C
+	help
+	  Enable support for Texas Instruments TAS5707, TAS5711, TAS5717,
+	  TAS5719 and TAS5721 power amplifiers
 
 config SND_SOC_TAS5720
 	tristate "Texas Instruments TAS5720 Mono Audio amplifier"
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index e023fdf85221..7ae7c85e8219 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -71,6 +71,7 @@ snd-soc-da732x-objs := da732x.o
 snd-soc-da9055-objs := da9055.o
 snd-soc-dmic-objs := dmic.o
 snd-soc-es7134-objs := es7134.o
+snd-soc-es7241-objs := es7241.o
 snd-soc-es8316-objs := es8316.o
 snd-soc-es8328-objs := es8328.o
 snd-soc-es8328-i2c-objs := es8328-i2c.o
@@ -146,6 +147,7 @@ snd-soc-rt5668-objs := rt5668.o
 snd-soc-rt5670-objs := rt5670.o
 snd-soc-rt5677-objs := rt5677.o
 snd-soc-rt5677-spi-objs := rt5677-spi.o
+snd-soc-rt5682-objs := rt5682.o
 snd-soc-sgtl5000-objs := sgtl5000.o
 snd-soc-alc5623-objs := alc5623.o
 snd-soc-alc5632-objs := alc5632.o
@@ -249,9 +251,9 @@ snd-soc-wm9713-objs := wm9713.o
 snd-soc-wm-hubs-objs := wm_hubs.o
 snd-soc-zx-aud96p22-objs := zx_aud96p22.o
 # Amp
-snd-soc-dio2125-objs := dio2125.o
 snd-soc-max9877-objs := max9877.o
 snd-soc-max98504-objs := max98504.o
+snd-soc-simple-amplifier-objs := simple-amplifier.o
 snd-soc-tpa6130a2-objs := tpa6130a2.o
 snd-soc-tas2552-objs := tas2552.o
 
@@ -329,6 +331,7 @@ obj-$(CONFIG_SND_SOC_DA732X)	+= snd-soc-da732x.o
 obj-$(CONFIG_SND_SOC_DA9055)	+= snd-soc-da9055.o
 obj-$(CONFIG_SND_SOC_DMIC)	+= snd-soc-dmic.o
 obj-$(CONFIG_SND_SOC_ES7134)	+= snd-soc-es7134.o
+obj-$(CONFIG_SND_SOC_ES7241)	+= snd-soc-es7241.o
 obj-$(CONFIG_SND_SOC_ES8316)    += snd-soc-es8316.o
 obj-$(CONFIG_SND_SOC_ES8328)	+= snd-soc-es8328.o
 obj-$(CONFIG_SND_SOC_ES8328_I2C)+= snd-soc-es8328-i2c.o
@@ -405,6 +408,7 @@ obj-$(CONFIG_SND_SOC_RT5668)	+= snd-soc-rt5668.o
 obj-$(CONFIG_SND_SOC_RT5670)	+= snd-soc-rt5670.o
 obj-$(CONFIG_SND_SOC_RT5677)	+= snd-soc-rt5677.o
 obj-$(CONFIG_SND_SOC_RT5677_SPI)	+= snd-soc-rt5677-spi.o
+obj-$(CONFIG_SND_SOC_RT5682)	+= snd-soc-rt5682.o
 obj-$(CONFIG_SND_SOC_SGTL5000)  += snd-soc-sgtl5000.o
 obj-$(CONFIG_SND_SOC_SIGMADSP)	+= snd-soc-sigmadsp.o
 obj-$(CONFIG_SND_SOC_SIGMADSP_I2C)	+= snd-soc-sigmadsp-i2c.o
@@ -507,7 +511,7 @@ obj-$(CONFIG_SND_SOC_WM_HUBS)	+= snd-soc-wm-hubs.o
 obj-$(CONFIG_SND_SOC_ZX_AUD96P22) += snd-soc-zx-aud96p22.o
 
 # Amp
-obj-$(CONFIG_SND_SOC_DIO2125)	+= snd-soc-dio2125.o
 obj-$(CONFIG_SND_SOC_MAX9877)	+= snd-soc-max9877.o
 obj-$(CONFIG_SND_SOC_MAX98504)	+= snd-soc-max98504.o
+obj-$(CONFIG_SND_SOC_SIMPLE_AMPLIFIER)	+= snd-soc-simple-amplifier.o
 obj-$(CONFIG_SND_SOC_TPA6130A2)	+= snd-soc-tpa6130a2.o
diff --git a/sound/soc/codecs/adau17x1.c b/sound/soc/codecs/adau17x1.c
index ae41edd1c406..57169b8ff14e 100644
--- a/sound/soc/codecs/adau17x1.c
+++ b/sound/soc/codecs/adau17x1.c
@@ -299,6 +299,7 @@ static const struct snd_soc_dapm_route adau17x1_dsp_dapm_routes[] = {
 
 	{ "DSP", NULL, "Left Decimator" },
 	{ "DSP", NULL, "Right Decimator" },
+	{ "DSP", NULL, "Playback" },
 };
 
 static const struct snd_soc_dapm_route adau17x1_no_dsp_dapm_routes[] = {
diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c
index db21ecbe0762..8b9ca7e7a682 100644
--- a/sound/soc/codecs/adav80x.c
+++ b/sound/soc/codecs/adav80x.c
@@ -648,6 +648,7 @@ static int adav80x_set_pll(struct snd_soc_component *component, int pll_id,
 			pll_ctrl1 |= ADAV80X_PLL_CTRL1_PLLDIV;
 			break;
 		}
+		/* fall through */
 	default:
 		return -EINVAL;
 	}
diff --git a/sound/soc/codecs/ak4458.c b/sound/soc/codecs/ak4458.c
index 31ec0ba2e639..299ada4dfaa0 100644
--- a/sound/soc/codecs/ak4458.c
+++ b/sound/soc/codecs/ak4458.c
@@ -558,7 +558,7 @@ static int __maybe_unused ak4458_runtime_resume(struct device *dev)
 }
 #endif /* CONFIG_PM */
 
-struct snd_soc_component_driver soc_codec_dev_ak4458 = {
+static const struct snd_soc_component_driver soc_codec_dev_ak4458 = {
 	.probe			= ak4458_probe,
 	.remove			= ak4458_remove,
 	.controls		= ak4458_snd_controls,
diff --git a/sound/soc/codecs/ak4554.c b/sound/soc/codecs/ak4554.c
index b7ee13406d93..2fa83a1a84cf 100644
--- a/sound/soc/codecs/ak4554.c
+++ b/sound/soc/codecs/ak4554.c
@@ -1,13 +1,8 @@
-/*
- * ak4554.c
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+// ak4554.c
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 #include <linux/module.h>
 #include <sound/soc.h>
@@ -97,6 +92,6 @@ static struct platform_driver ak4554_driver = {
 };
 module_platform_driver(ak4554_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("SoC AK4554 driver");
 MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
diff --git a/sound/soc/codecs/ak4613.c b/sound/soc/codecs/ak4613.c
index 8523ff9351cf..c1181a20714d 100644
--- a/sound/soc/codecs/ak4613.c
+++ b/sound/soc/codecs/ak4613.c
@@ -1,18 +1,14 @@
-/*
- * ak4613.c  --  Asahi Kasei ALSA Soc Audio driver
- *
- * Copyright (C) 2015 Renesas Electronics Corporation
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * Based on ak4642.c by Kuninori Morimoto
- * Based on wm8731.c by Richard Purdie
- * Based on ak4535.c by Richard Purdie
- * Based on wm8753.c by Liam Girdwood
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ak4613.c  --  Asahi Kasei ALSA Soc Audio driver
+//
+// Copyright (C) 2015 Renesas Electronics Corporation
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// Based on ak4642.c by Kuninori Morimoto
+// Based on wm8731.c by Richard Purdie
+// Based on ak4535.c by Richard Purdie
+// Based on wm8753.c by Liam Girdwood
 
 #include <linux/clk.h>
 #include <linux/delay.h>
diff --git a/sound/soc/codecs/ak4642.c b/sound/soc/codecs/ak4642.c
index 605055964529..353237025514 100644
--- a/sound/soc/codecs/ak4642.c
+++ b/sound/soc/codecs/ak4642.c
@@ -1,17 +1,13 @@
-/*
- * ak4642.c  --  AK4642/AK4643 ALSA Soc Audio driver
- *
- * Copyright (C) 2009 Renesas Solutions Corp.
- * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * Based on wm8731.c by Richard Purdie
- * Based on ak4535.c by Richard Purdie
- * Based on wm8753.c by Liam Girdwood
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ak4642.c  --  AK4642/AK4643 ALSA Soc Audio driver
+//
+// Copyright (C) 2009 Renesas Solutions Corp.
+// Kuninori Morimoto <morimoto.kuninori@renesas.com>
+//
+// Based on wm8731.c by Richard Purdie
+// Based on ak4535.c by Richard Purdie
+// Based on wm8753.c by Liam Girdwood
 
 /* ** CAUTION **
  *
@@ -709,4 +705,4 @@ module_i2c_driver(ak4642_i2c_driver);
 
 MODULE_DESCRIPTION("Soc AK4642 driver");
 MODULE_AUTHOR("Kuninori Morimoto <morimoto.kuninori@renesas.com>");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/ak5558.c b/sound/soc/codecs/ak5558.c
index f4ed5cc40661..448bb90c9c8e 100644
--- a/sound/soc/codecs/ak5558.c
+++ b/sound/soc/codecs/ak5558.c
@@ -322,13 +322,13 @@ static int __maybe_unused ak5558_runtime_resume(struct device *dev)
 	return regcache_sync(ak5558->regmap);
 }
 
-const struct dev_pm_ops ak5558_pm = {
+static const struct dev_pm_ops ak5558_pm = {
 	SET_RUNTIME_PM_OPS(ak5558_runtime_suspend, ak5558_runtime_resume, NULL)
 	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
 				pm_runtime_force_resume)
 };
 
-struct snd_soc_component_driver soc_codec_dev_ak5558 = {
+static const struct snd_soc_component_driver soc_codec_dev_ak5558 = {
 	.probe			= ak5558_probe,
 	.remove			= ak5558_remove,
 	.controls		= ak5558_snd_controls,
diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c
index 2a7a4168c072..3c266eeb89bf 100644
--- a/sound/soc/codecs/cs4270.c
+++ b/sound/soc/codecs/cs4270.c
@@ -219,7 +219,7 @@ static bool cs4270_reg_is_volatile(struct device *dev, unsigned int reg)
 {
 	/* Unreadable registers are considered volatile */
 	if ((reg < CS4270_FIRSTREG) || (reg > CS4270_LASTREG))
-		return 1;
+		return true;
 
 	return reg == CS4270_CHIPID;
 }
diff --git a/sound/soc/codecs/cs47l24.c b/sound/soc/codecs/cs47l24.c
index 196e9c343aeb..45e50fe3bf25 100644
--- a/sound/soc/codecs/cs47l24.c
+++ b/sound/soc/codecs/cs47l24.c
@@ -235,6 +235,9 @@ ARIZONA_MIXER_CONTROLS("AIF2TX6", ARIZONA_AIF2TX6MIX_INPUT_1_SOURCE),
 
 ARIZONA_MIXER_CONTROLS("AIF3TX1", ARIZONA_AIF3TX1MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("AIF3TX2", ARIZONA_AIF3TX2MIX_INPUT_1_SOURCE),
+
+WM_ADSP_FW_CONTROL("DSP2", 1),
+WM_ADSP_FW_CONTROL("DSP3", 2),
 };
 
 ARIZONA_MIXER_ENUMS(EQ1, ARIZONA_EQ1MIX_INPUT_1_SOURCE);
@@ -1283,6 +1286,12 @@ static int cs47l24_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 1);
+	if (ret != 0)
+		dev_warn(&pdev->dev,
+			 "Failed to set compressed IRQ as a wake source: %d\n",
+			 ret);
+
 	arizona_init_common(arizona);
 
 	ret = arizona_init_vol_limit(arizona);
@@ -1306,6 +1315,7 @@ static int cs47l24_probe(struct platform_device *pdev)
 err_spk_irqs:
 	arizona_free_spk_irqs(arizona);
 err_dsp_irq:
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, cs47l24);
 
 	return ret;
@@ -1323,6 +1333,7 @@ static int cs47l24_remove(struct platform_device *pdev)
 
 	arizona_free_spk_irqs(arizona);
 
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, cs47l24);
 
 	return 0;
diff --git a/sound/soc/codecs/cx20442.c b/sound/soc/codecs/cx20442.c
index 07dd33b09596..ab174b5114dc 100644
--- a/sound/soc/codecs/cx20442.c
+++ b/sound/soc/codecs/cx20442.c
@@ -362,8 +362,27 @@ static int cx20442_component_probe(struct snd_soc_component *component)
 		return -ENOMEM;
 
 	cx20442->por = regulator_get(component->dev, "POR");
-	if (IS_ERR(cx20442->por))
-		dev_warn(component->dev, "failed to get the regulator");
+	if (IS_ERR(cx20442->por)) {
+		int err = PTR_ERR(cx20442->por);
+
+		dev_warn(component->dev, "failed to get POR supply (%d)", err);
+		/*
+		 * When running on a non-dt platform and requested regulator
+		 * is not available, regulator_get() never returns
+		 * -EPROBE_DEFER as it is not able to justify if the regulator
+		 * may still appear later.  On the other hand, the board can
+		 * still set full constraints flag at late_initcall in order
+		 * to instruct regulator_get() to return a dummy one if
+		 * sufficient.  Hence, if we get -ENODEV here, let's convert
+		 * it to -EPROBE_DEFER and wait for the board to decide or
+		 * let Deferred Probe infrastructure handle this error.
+		 */
+		if (err == -ENODEV)
+			err = -EPROBE_DEFER;
+		kfree(cx20442);
+		return err;
+	}
+
 	cx20442->tty = NULL;
 
 	snd_soc_component_set_drvdata(component, cx20442);
diff --git a/sound/soc/codecs/da7210.c b/sound/soc/codecs/da7210.c
index a664111b7184..e172913d04a4 100644
--- a/sound/soc/codecs/da7210.c
+++ b/sound/soc/codecs/da7210.c
@@ -1,19 +1,14 @@
-/*
- * DA7210 ALSA Soc codec driver
- *
- * Copyright (c) 2009 Dialog Semiconductor
- * Written by David Chen <Dajun.chen@diasemi.com>
- *
- * Copyright (C) 2009 Renesas Solutions Corp.
- * Cleanups by Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * Tested on SuperH Ecovec24 board with S16/S24 LE in 48KHz using I2S
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// DA7210 ALSA Soc codec driver
+//
+// Copyright (c) 2009 Dialog Semiconductor
+// Written by David Chen <Dajun.chen@diasemi.com>
+//
+// Copyright (C) 2009 Renesas Solutions Corp.
+// Cleanups by Kuninori Morimoto <morimoto.kuninori@renesas.com>
+//
+// Tested on SuperH Ecovec24 board with S16/S24 LE in 48KHz using I2S
 
 #include <linux/delay.h>
 #include <linux/i2c.h>
diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c
index 54cb5f24969f..92d006a5283e 100644
--- a/sound/soc/codecs/da7213.c
+++ b/sound/soc/codecs/da7213.c
@@ -1140,9 +1140,9 @@ static bool da7213_volatile_register(struct device *dev, unsigned int reg)
 	case DA7213_ALC_OFFSET_AUTO_M_R:
 	case DA7213_ALC_OFFSET_AUTO_U_R:
 	case DA7213_ALC_CIC_OP_LVL_DATA:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c
index a49ab751a036..2c7d5088e6f2 100644
--- a/sound/soc/codecs/da7219-aad.c
+++ b/sound/soc/codecs/da7219-aad.c
@@ -59,6 +59,7 @@ static void da7219_aad_btn_det_work(struct work_struct *work)
 		container_of(work, struct da7219_aad_priv, btn_det_work);
 	struct snd_soc_component *component = da7219_aad->component;
 	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
+	struct da7219_priv *da7219 = snd_soc_component_get_drvdata(component);
 	u8 statusa, micbias_ctrl;
 	bool micbias_up = false;
 	int retries = 0;
@@ -86,6 +87,8 @@ static void da7219_aad_btn_det_work(struct work_struct *work)
 	if (retries >= DA7219_AAD_MICBIAS_CHK_RETRIES)
 		dev_warn(component->dev, "Mic bias status check timed out");
 
+	da7219->micbias_on_event = true;
+
 	/*
 	 * Mic bias pulse required to enable mic, must be done before enabling
 	 * button detection to prevent erroneous button readings.
@@ -439,6 +442,8 @@ static irqreturn_t da7219_aad_irq_thread(int irq, void *data)
 			snd_soc_component_update_bits(component, DA7219_ACCDET_CONFIG_1,
 					    DA7219_BUTTON_CONFIG_MASK, 0);
 
+			da7219->micbias_on_event = false;
+
 			/* Disable mic bias */
 			snd_soc_dapm_disable_pin(dapm, "Mic Bias");
 			snd_soc_dapm_sync(dapm);
diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c
index 980a6a8bf56d..e46e9f4bc994 100644
--- a/sound/soc/codecs/da7219.c
+++ b/sound/soc/codecs/da7219.c
@@ -768,6 +768,30 @@ static const struct snd_kcontrol_new da7219_st_out_filtr_mix_controls[] = {
  * DAPM Events
  */
 
+static int da7219_mic_pga_event(struct snd_soc_dapm_widget *w,
+				struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct da7219_priv *da7219 = snd_soc_component_get_drvdata(component);
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		if (da7219->micbias_on_event) {
+			/*
+			 * Delay only for first capture after bias enabled to
+			 * avoid possible DC offset related noise.
+			 */
+			da7219->micbias_on_event = false;
+			msleep(da7219->mic_pga_delay);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static int da7219_dai_event(struct snd_soc_dapm_widget *w,
 			    struct snd_kcontrol *kcontrol, int event)
 {
@@ -937,12 +961,12 @@ static const struct snd_soc_dapm_widget da7219_dapm_widgets[] = {
 	SND_SOC_DAPM_INPUT("MIC"),
 
 	/* Input PGAs */
-	SND_SOC_DAPM_PGA("Mic PGA", DA7219_MIC_1_CTRL,
-			 DA7219_MIC_1_AMP_EN_SHIFT, DA7219_NO_INVERT,
-			 NULL, 0),
-	SND_SOC_DAPM_PGA("Mixin PGA", DA7219_MIXIN_L_CTRL,
-			 DA7219_MIXIN_L_AMP_EN_SHIFT, DA7219_NO_INVERT,
-			 NULL, 0),
+	SND_SOC_DAPM_PGA_E("Mic PGA", DA7219_MIC_1_CTRL,
+			   DA7219_MIC_1_AMP_EN_SHIFT, DA7219_NO_INVERT,
+			   NULL, 0, da7219_mic_pga_event, SND_SOC_DAPM_POST_PMU),
+	SND_SOC_DAPM_PGA_E("Mixin PGA", DA7219_MIXIN_L_CTRL,
+			   DA7219_MIXIN_L_AMP_EN_SHIFT, DA7219_NO_INVERT,
+			   NULL, 0, da7219_settling_event, SND_SOC_DAPM_POST_PMU),
 
 	/* Input Filters */
 	SND_SOC_DAPM_ADC("ADC", NULL, DA7219_ADC_L_CTRL, DA7219_ADC_L_EN_SHIFT,
@@ -1847,6 +1871,14 @@ static void da7219_handle_pdata(struct snd_soc_component *component)
 
 		snd_soc_component_write(component, DA7219_MICBIAS_CTRL, micbias_lvl);
 
+		/*
+		 * Calculate delay required to compensate for DC offset in
+		 * Mic PGA, based on Mic Bias voltage.
+		 */
+		da7219->mic_pga_delay =  DA7219_MIC_PGA_BASE_DELAY +
+					(pdata->micbias_lvl *
+					 DA7219_MIC_PGA_OFFSET_DELAY);
+
 		/* Mic */
 		switch (pdata->mic_amp_in_sel) {
 		case DA7219_MIC_AMP_IN_SEL_DIFF:
@@ -2143,9 +2175,9 @@ static bool da7219_volatile_register(struct device *dev, unsigned int reg)
 	case DA7219_ACCDET_IRQ_EVENT_B:
 	case DA7219_ACCDET_CONFIG_8:
 	case DA7219_SYSTEM_STATUS:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
diff --git a/sound/soc/codecs/da7219.h b/sound/soc/codecs/da7219.h
index 1b00023e33cd..3a006862f0e7 100644
--- a/sound/soc/codecs/da7219.h
+++ b/sound/soc/codecs/da7219.h
@@ -781,8 +781,10 @@
 #define DA7219_SYS_STAT_CHECK_DELAY	50
 
 /* Power up/down Delays */
-#define DA7219_SETTLING_DELAY	40
-#define DA7219_MIN_GAIN_DELAY	30
+#define DA7219_SETTLING_DELAY		40
+#define DA7219_MIN_GAIN_DELAY		30
+#define DA7219_MIC_PGA_BASE_DELAY	100
+#define DA7219_MIC_PGA_OFFSET_DELAY	40
 
 enum da7219_clk_src {
 	DA7219_CLKSRC_MCLK = 0,
@@ -828,6 +830,8 @@ struct da7219_priv {
 
 	bool master;
 	bool alc_en;
+	bool micbias_on_event;
+	unsigned int mic_pga_delay;
 	u8 gain_ramp_ctrl;
 };
 
diff --git a/sound/soc/codecs/da9055.c b/sound/soc/codecs/da9055.c
index afdf90c78884..f6a7bf9560e7 100644
--- a/sound/soc/codecs/da9055.c
+++ b/sound/soc/codecs/da9055.c
@@ -1041,9 +1041,9 @@ static bool da9055_volatile_register(struct device *dev,
 	case DA9055_HP_R_GAIN_STATUS:
 	case DA9055_LINE_GAIN_STATUS:
 	case DA9055_ALC_CIC_OP_LVL_DATA:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
diff --git a/sound/soc/codecs/es7134.c b/sound/soc/codecs/es7134.c
index 58515bb1a303..6d7bca7b78ca 100644
--- a/sound/soc/codecs/es7134.c
+++ b/sound/soc/codecs/es7134.c
@@ -17,6 +17,7 @@
  * in the file called COPYING.
  */
 
+#include <linux/of_platform.h>
 #include <linux/module.h>
 #include <sound/soc.h>
 
@@ -24,6 +25,82 @@
  * The everest 7134 is a very simple DA converter with no register
  */
 
+struct es7134_clock_mode {
+	unsigned int rate_min;
+	unsigned int rate_max;
+	unsigned int *mclk_fs;
+	unsigned int mclk_fs_num;
+};
+
+struct es7134_chip {
+	struct snd_soc_dai_driver *dai_drv;
+	const struct es7134_clock_mode *modes;
+	unsigned int mode_num;
+	const struct snd_soc_dapm_widget *extra_widgets;
+	unsigned int extra_widget_num;
+	const struct snd_soc_dapm_route *extra_routes;
+	unsigned int extra_route_num;
+};
+
+struct es7134_data {
+	unsigned int mclk;
+	const struct es7134_chip *chip;
+};
+
+static int es7134_check_mclk(struct snd_soc_dai *dai,
+			     struct es7134_data *priv,
+			     unsigned int rate)
+{
+	unsigned int mfs = priv->mclk / rate;
+	int i, j;
+
+	for (i = 0; i < priv->chip->mode_num; i++) {
+		const struct es7134_clock_mode *mode = &priv->chip->modes[i];
+
+		if (rate < mode->rate_min || rate > mode->rate_max)
+			continue;
+
+		for (j = 0; j < mode->mclk_fs_num; j++) {
+			if (mode->mclk_fs[j] == mfs)
+				return 0;
+		}
+
+		dev_err(dai->dev, "unsupported mclk_fs %u for rate %u\n",
+			mfs, rate);
+		return -EINVAL;
+	}
+
+	/* should not happen */
+	dev_err(dai->dev, "unsupported rate: %u\n", rate);
+	return -EINVAL;
+}
+
+static int es7134_hw_params(struct snd_pcm_substream *substream,
+			    struct snd_pcm_hw_params *params,
+			    struct snd_soc_dai *dai)
+{
+	struct es7134_data *priv = snd_soc_dai_get_drvdata(dai);
+
+	/* mclk has not been provided, assume it is OK */
+	if (!priv->mclk)
+		return 0;
+
+	return es7134_check_mclk(dai, priv, params_rate(params));
+}
+
+static int es7134_set_sysclk(struct snd_soc_dai *dai, int clk_id,
+			     unsigned int freq, int dir)
+{
+	struct es7134_data *priv = snd_soc_dai_get_drvdata(dai);
+
+	if (dir == SND_SOC_CLOCK_IN && clk_id == 0) {
+		priv->mclk = freq;
+		return 0;
+	}
+
+	return -ENOTSUPP;
+}
+
 static int es7134_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 {
 	fmt &= (SND_SOC_DAIFMT_FORMAT_MASK | SND_SOC_DAIFMT_INV_MASK |
@@ -38,8 +115,38 @@ static int es7134_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 	return 0;
 }
 
+static int es7134_component_probe(struct snd_soc_component *c)
+{
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(c);
+	struct es7134_data *priv = snd_soc_component_get_drvdata(c);
+	const struct es7134_chip *chip = priv->chip;
+	int ret;
+
+	if (chip->extra_widget_num) {
+		ret = snd_soc_dapm_new_controls(dapm, chip->extra_widgets,
+						chip->extra_widget_num);
+		if (ret) {
+			dev_err(c->dev, "failed to add extra widgets\n");
+			return ret;
+		}
+	}
+
+	if (chip->extra_route_num) {
+		ret = snd_soc_dapm_add_routes(dapm, chip->extra_routes,
+					      chip->extra_route_num);
+		if (ret) {
+			dev_err(c->dev, "failed to add extra routes\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static const struct snd_soc_dai_ops es7134_dai_ops = {
 	.set_fmt	= es7134_set_fmt,
+	.hw_params	= es7134_hw_params,
+	.set_sysclk	= es7134_set_sysclk,
 };
 
 static struct snd_soc_dai_driver es7134_dai = {
@@ -48,7 +155,11 @@ static struct snd_soc_dai_driver es7134_dai = {
 		.stream_name = "Playback",
 		.channels_min = 2,
 		.channels_max = 2,
-		.rates = SNDRV_PCM_RATE_8000_192000,
+		.rates = (SNDRV_PCM_RATE_8000_48000 |
+			  SNDRV_PCM_RATE_88200      |
+			  SNDRV_PCM_RATE_96000      |
+			  SNDRV_PCM_RATE_176400     |
+			  SNDRV_PCM_RATE_192000),
 		.formats = (SNDRV_PCM_FMTBIT_S16_LE  |
 			    SNDRV_PCM_FMTBIT_S18_3LE |
 			    SNDRV_PCM_FMTBIT_S20_3LE |
@@ -58,18 +169,56 @@ static struct snd_soc_dai_driver es7134_dai = {
 	.ops = &es7134_dai_ops,
 };
 
+static const struct es7134_clock_mode es7134_modes[] = {
+	{
+		/* Single speed mode */
+		.rate_min = 8000,
+		.rate_max = 50000,
+		.mclk_fs = (unsigned int[]) { 256, 384, 512, 768, 1024 },
+		.mclk_fs_num = 5,
+	}, {
+		/* Double speed mode */
+		.rate_min = 84000,
+		.rate_max = 100000,
+		.mclk_fs = (unsigned int[]) { 128, 192, 256, 384, 512 },
+		.mclk_fs_num = 5,
+	}, {
+		/* Quad speed mode */
+		.rate_min = 167000,
+		.rate_max = 192000,
+		.mclk_fs = (unsigned int[]) { 128, 192, 256 },
+		.mclk_fs_num = 3,
+	},
+};
+
+/* Digital I/O are also supplied by VDD on the es7134 */
+static const struct snd_soc_dapm_route es7134_extra_routes[] = {
+	{ "Playback", NULL, "VDD", }
+};
+
+static const struct es7134_chip es7134_chip = {
+	.dai_drv = &es7134_dai,
+	.modes = es7134_modes,
+	.mode_num = ARRAY_SIZE(es7134_modes),
+	.extra_routes = es7134_extra_routes,
+	.extra_route_num = ARRAY_SIZE(es7134_extra_routes),
+};
+
 static const struct snd_soc_dapm_widget es7134_dapm_widgets[] = {
 	SND_SOC_DAPM_OUTPUT("AOUTL"),
 	SND_SOC_DAPM_OUTPUT("AOUTR"),
 	SND_SOC_DAPM_DAC("DAC", "Playback", SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("VDD", 0, 0),
 };
 
 static const struct snd_soc_dapm_route es7134_dapm_routes[] = {
 	{ "AOUTL", NULL, "DAC" },
 	{ "AOUTR", NULL, "DAC" },
+	{ "DAC", NULL, "VDD" },
 };
 
 static const struct snd_soc_component_driver es7134_component_driver = {
+	.probe			= es7134_component_probe,
 	.dapm_widgets		= es7134_dapm_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(es7134_dapm_widgets),
 	.dapm_routes		= es7134_dapm_routes,
@@ -80,17 +229,87 @@ static const struct snd_soc_component_driver es7134_component_driver = {
 	.non_legacy_dai_naming	= 1,
 };
 
+static struct snd_soc_dai_driver es7154_dai = {
+	.name = "es7154-hifi",
+	.playback = {
+		.stream_name = "Playback",
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = (SNDRV_PCM_RATE_8000_48000 |
+			  SNDRV_PCM_RATE_88200      |
+			  SNDRV_PCM_RATE_96000),
+		.formats = (SNDRV_PCM_FMTBIT_S16_LE  |
+			    SNDRV_PCM_FMTBIT_S18_3LE |
+			    SNDRV_PCM_FMTBIT_S20_3LE |
+			    SNDRV_PCM_FMTBIT_S24_3LE |
+			    SNDRV_PCM_FMTBIT_S24_LE),
+	},
+	.ops = &es7134_dai_ops,
+};
+
+static const struct es7134_clock_mode es7154_modes[] = {
+	{
+		/* Single speed mode */
+		.rate_min = 8000,
+		.rate_max = 50000,
+		.mclk_fs = (unsigned int[]) { 32, 64, 128, 192, 256,
+					      384, 512, 768, 1024 },
+		.mclk_fs_num = 9,
+	}, {
+		/* Double speed mode */
+		.rate_min = 84000,
+		.rate_max = 100000,
+		.mclk_fs = (unsigned int[]) { 128, 192, 256, 384, 512,
+					      768, 1024},
+		.mclk_fs_num = 7,
+	}
+};
+
+/* Es7154 has a separate supply for digital I/O  */
+static const struct snd_soc_dapm_widget es7154_extra_widgets[] = {
+	SND_SOC_DAPM_REGULATOR_SUPPLY("PVDD", 0, 0),
+};
+
+static const struct snd_soc_dapm_route es7154_extra_routes[] = {
+	{ "Playback", NULL, "PVDD", }
+};
+
+static const struct es7134_chip es7154_chip = {
+	.dai_drv = &es7154_dai,
+	.modes = es7154_modes,
+	.mode_num = ARRAY_SIZE(es7154_modes),
+	.extra_routes = es7154_extra_routes,
+	.extra_route_num = ARRAY_SIZE(es7154_extra_routes),
+	.extra_widgets = es7154_extra_widgets,
+	.extra_widget_num = ARRAY_SIZE(es7154_extra_widgets),
+};
+
 static int es7134_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
+	struct es7134_data *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, priv);
+
+	priv->chip = of_device_get_match_data(dev);
+	if (!priv->chip) {
+		dev_err(dev, "failed to match device\n");
+		return -ENODEV;
+	}
+
 	return devm_snd_soc_register_component(&pdev->dev,
 				      &es7134_component_driver,
-				      &es7134_dai, 1);
+				      priv->chip->dai_drv, 1);
 }
 
 #ifdef CONFIG_OF
 static const struct of_device_id es7134_ids[] = {
-	{ .compatible = "everest,es7134", },
-	{ .compatible = "everest,es7144", },
+	{ .compatible = "everest,es7134", .data = &es7134_chip },
+	{ .compatible = "everest,es7144", .data = &es7134_chip },
+	{ .compatible = "everest,es7154", .data = &es7154_chip },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, es7134_ids);
diff --git a/sound/soc/codecs/es7241.c b/sound/soc/codecs/es7241.c
new file mode 100644
index 000000000000..87991bd4acef
--- /dev/null
+++ b/sound/soc/codecs/es7241.c
@@ -0,0 +1,322 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/gpio/consumer.h>
+#include <linux/of_platform.h>
+#include <linux/module.h>
+#include <sound/soc.h>
+
+struct es7241_clock_mode {
+	unsigned int rate_min;
+	unsigned int rate_max;
+	unsigned int *slv_mfs;
+	unsigned int slv_mfs_num;
+	unsigned int mst_mfs;
+	unsigned int mst_m0:1;
+	unsigned int mst_m1:1;
+};
+
+struct es7241_chip {
+	const struct es7241_clock_mode *modes;
+	unsigned int mode_num;
+};
+
+struct es7241_data {
+	struct gpio_desc *reset;
+	struct gpio_desc *m0;
+	struct gpio_desc *m1;
+	unsigned int fmt;
+	unsigned int mclk;
+	bool is_slave;
+	const struct es7241_chip *chip;
+};
+
+static void es7241_set_mode(struct es7241_data *priv,  int m0, int m1)
+{
+	/* put the device in reset */
+	gpiod_set_value_cansleep(priv->reset, 0);
+
+	/* set the mode */
+	gpiod_set_value_cansleep(priv->m0, m0);
+	gpiod_set_value_cansleep(priv->m1, m1);
+
+	/* take the device out of reset - datasheet does not specify a delay */
+	gpiod_set_value_cansleep(priv->reset, 1);
+}
+
+static int es7241_set_slave_mode(struct es7241_data *priv,
+				 const struct es7241_clock_mode *mode,
+				 unsigned int mfs)
+{
+	int j;
+
+	if (!mfs)
+		goto out_ok;
+
+	for (j = 0; j < mode->slv_mfs_num; j++) {
+		if (mode->slv_mfs[j] == mfs)
+			goto out_ok;
+	}
+
+	return -EINVAL;
+
+out_ok:
+	es7241_set_mode(priv, 1, 1);
+	return 0;
+}
+
+static int es7241_set_master_mode(struct es7241_data *priv,
+				  const struct es7241_clock_mode *mode,
+				  unsigned int mfs)
+{
+	/*
+	 * We can't really set clock ratio, if the mclk/lrclk is different
+	 * from what we provide, then error out
+	 */
+	if (mfs && mfs != mode->mst_mfs)
+		return -EINVAL;
+
+	es7241_set_mode(priv, mode->mst_m0, mode->mst_m1);
+
+	return 0;
+}
+
+static int es7241_hw_params(struct snd_pcm_substream *substream,
+			    struct snd_pcm_hw_params *params,
+			    struct snd_soc_dai *dai)
+{
+	struct es7241_data *priv = snd_soc_dai_get_drvdata(dai);
+	unsigned int rate = params_rate(params);
+	unsigned int mfs = priv->mclk / rate;
+	int i;
+
+	for (i = 0; i < priv->chip->mode_num; i++) {
+		const struct es7241_clock_mode *mode = &priv->chip->modes[i];
+
+		if (rate < mode->rate_min || rate >= mode->rate_max)
+			continue;
+
+		if (priv->is_slave)
+			return es7241_set_slave_mode(priv, mode, mfs);
+		else
+			return es7241_set_master_mode(priv, mode, mfs);
+	}
+
+	/* should not happen */
+	dev_err(dai->dev, "unsupported rate: %u\n", rate);
+	return -EINVAL;
+}
+
+static int es7241_set_sysclk(struct snd_soc_dai *dai, int clk_id,
+			     unsigned int freq, int dir)
+{
+	struct es7241_data *priv = snd_soc_dai_get_drvdata(dai);
+
+	if (dir == SND_SOC_CLOCK_IN && clk_id == 0) {
+		priv->mclk = freq;
+		return 0;
+	}
+
+	return -ENOTSUPP;
+}
+
+static int es7241_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct es7241_data *priv = snd_soc_dai_get_drvdata(dai);
+
+	if ((fmt & SND_SOC_DAIFMT_INV_MASK) != SND_SOC_DAIFMT_NB_NF) {
+		dev_err(dai->dev, "Unsupported dai clock inversion\n");
+		return -EINVAL;
+	}
+
+	if ((fmt & SND_SOC_DAIFMT_FORMAT_MASK) != priv->fmt) {
+		dev_err(dai->dev, "Invalid dai format\n");
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		priv->is_slave = true;
+		break;
+	case SND_SOC_DAIFMT_CBM_CFM:
+		priv->is_slave = false;
+		break;
+
+	default:
+		dev_err(dai->dev, "Unsupported clock configuration\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops es7241_dai_ops = {
+	.set_fmt	= es7241_set_fmt,
+	.hw_params	= es7241_hw_params,
+	.set_sysclk	= es7241_set_sysclk,
+};
+
+static struct snd_soc_dai_driver es7241_dai = {
+	.name = "es7241-hifi",
+	.capture = {
+		.stream_name = "Capture",
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = SNDRV_PCM_RATE_8000_192000,
+		.formats = (SNDRV_PCM_FMTBIT_S16_LE  |
+			    SNDRV_PCM_FMTBIT_S24_3LE |
+			    SNDRV_PCM_FMTBIT_S24_LE),
+	},
+	.ops = &es7241_dai_ops,
+};
+
+static const struct es7241_clock_mode es7241_modes[] = {
+	{
+		/* Single speed mode */
+		.rate_min = 8000,
+		.rate_max = 50000,
+		.slv_mfs = (unsigned int[]) { 256, 384, 512, 768, 1024 },
+		.slv_mfs_num = 5,
+		.mst_mfs = 256,
+		.mst_m0 = 0,
+		.mst_m1 = 0,
+	}, {
+		/* Double speed mode */
+		.rate_min = 50000,
+		.rate_max = 100000,
+		.slv_mfs = (unsigned int[]) { 128, 192 },
+		.slv_mfs_num = 2,
+		.mst_mfs = 128,
+		.mst_m0 = 1,
+		.mst_m1 = 0,
+	}, {
+		/* Quad speed mode */
+		.rate_min = 100000,
+		.rate_max = 200000,
+		.slv_mfs = (unsigned int[]) { 64 },
+		.slv_mfs_num = 1,
+		.mst_mfs = 64,
+		.mst_m0 = 0,
+		.mst_m1 = 1,
+	},
+};
+
+static const struct es7241_chip es7241_chip = {
+	.modes = es7241_modes,
+	.mode_num = ARRAY_SIZE(es7241_modes),
+};
+
+static const struct snd_soc_dapm_widget es7241_dapm_widgets[] = {
+	SND_SOC_DAPM_INPUT("AINL"),
+	SND_SOC_DAPM_INPUT("AINR"),
+	SND_SOC_DAPM_DAC("ADC", "Capture", SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("VDDP", 0, 0),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("VDDD", 0, 0),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("VDDA", 0, 0),
+};
+
+static const struct snd_soc_dapm_route es7241_dapm_routes[] = {
+	{ "ADC", NULL, "AINL", },
+	{ "ADC", NULL, "AINR", },
+	{ "ADC", NULL, "VDDA", },
+	{ "Capture", NULL, "VDDP", },
+	{ "Capture", NULL, "VDDD", },
+};
+
+static const struct snd_soc_component_driver es7241_component_driver = {
+	.dapm_widgets		= es7241_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(es7241_dapm_widgets),
+	.dapm_routes		= es7241_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(es7241_dapm_routes),
+	.idle_bias_on		= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static void es7241_parse_fmt(struct device *dev, struct es7241_data *priv)
+{
+	bool is_leftj;
+
+	/*
+	 * The format is given by a pull resistor on the SDOUT pin:
+	 * pull-up for i2s, pull-down for left justified.
+	 */
+	is_leftj = of_property_read_bool(dev->of_node,
+					 "everest,sdout-pull-down");
+	if (is_leftj)
+		priv->fmt = SND_SOC_DAIFMT_LEFT_J;
+	else
+		priv->fmt = SND_SOC_DAIFMT_I2S;
+}
+
+static int es7241_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct es7241_data *priv;
+	int err;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, priv);
+
+	priv->chip = of_device_get_match_data(dev);
+	if (!priv->chip) {
+		dev_err(dev, "failed to match device\n");
+		return -ENODEV;
+	}
+
+	es7241_parse_fmt(dev, priv);
+
+	priv->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(priv->reset)) {
+		err = PTR_ERR(priv->reset);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get 'reset' gpio: %d", err);
+		return err;
+	}
+
+	priv->m0 = devm_gpiod_get_optional(dev, "m0", GPIOD_OUT_LOW);
+	if (IS_ERR(priv->m0)) {
+		err = PTR_ERR(priv->m0);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get 'm0' gpio: %d", err);
+		return err;
+	}
+
+	priv->m1 = devm_gpiod_get_optional(dev, "m1", GPIOD_OUT_LOW);
+	if (IS_ERR(priv->m1)) {
+		err = PTR_ERR(priv->m1);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get 'm1' gpio: %d", err);
+		return err;
+	}
+
+	return devm_snd_soc_register_component(&pdev->dev,
+				      &es7241_component_driver,
+				      &es7241_dai, 1);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id es7241_ids[] = {
+	{ .compatible = "everest,es7241", .data = &es7241_chip },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, es7241_ids);
+#endif
+
+static struct platform_driver es7241_driver = {
+	.driver = {
+		.name = "es7241",
+		.of_match_table = of_match_ptr(es7241_ids),
+	},
+	.probe = es7241_probe,
+};
+
+module_platform_driver(es7241_driver);
+
+MODULE_DESCRIPTION("ASoC ES7241 audio codec driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 84f7a7a36e4b..7b8533abf637 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -85,7 +85,7 @@ struct hdac_hdmi_pin {
 	bool mst_capable;
 	struct hdac_hdmi_port *ports;
 	int num_ports;
-	struct hdac_ext_device *edev;
+	struct hdac_device *hdev;
 };
 
 struct hdac_hdmi_port {
@@ -126,6 +126,9 @@ struct hdac_hdmi_drv_data {
 };
 
 struct hdac_hdmi_priv {
+	struct hdac_device *hdev;
+	struct snd_soc_component *component;
+	struct snd_card *card;
 	struct hdac_hdmi_dai_port_map dai_map[HDA_MAX_CVTS];
 	struct list_head pin_list;
 	struct list_head cvt_list;
@@ -139,7 +142,7 @@ struct hdac_hdmi_priv {
 	struct snd_soc_dai_driver *dai_drv;
 };
 
-#define hdev_to_hdmi_priv(_hdev) ((to_ehdac_device(_hdev))->private_data)
+#define hdev_to_hdmi_priv(_hdev) dev_get_drvdata(&(_hdev)->dev)
 
 static struct hdac_hdmi_pcm *
 hdac_hdmi_get_pcm_from_cvt(struct hdac_hdmi_priv *hdmi,
@@ -158,7 +161,7 @@ hdac_hdmi_get_pcm_from_cvt(struct hdac_hdmi_priv *hdmi,
 static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm,
 		struct hdac_hdmi_port *port, bool is_connect)
 {
-	struct hdac_ext_device *edev = port->pin->edev;
+	struct hdac_device *hdev = port->pin->hdev;
 
 	if (is_connect)
 		snd_soc_dapm_enable_pin(port->dapm, port->jack_pin);
@@ -172,7 +175,7 @@ static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm,
 		 * ports.
 		 */
 		if (pcm->jack_event == 0) {
-			dev_dbg(&edev->hdev.dev,
+			dev_dbg(&hdev->dev,
 					"jack report for pcm=%d\n",
 					pcm->pcm_id);
 			snd_soc_jack_report(pcm->jack, SND_JACK_AVOUT,
@@ -198,19 +201,18 @@ static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm,
 /*
  * Get the no devices that can be connected to a port on the Pin widget.
  */
-static int hdac_hdmi_get_port_len(struct hdac_ext_device *edev, hda_nid_t nid)
+static int hdac_hdmi_get_port_len(struct hdac_device *hdev, hda_nid_t nid)
 {
 	unsigned int caps;
 	unsigned int type, param;
 
-	caps = get_wcaps(&edev->hdev, nid);
+	caps = get_wcaps(hdev, nid);
 	type = get_wcaps_type(caps);
 
 	if (!(caps & AC_WCAP_DIGITAL) || (type != AC_WID_PIN))
 		return 0;
 
-	param = snd_hdac_read_parm_uncached(&edev->hdev, nid,
-					AC_PAR_DEVLIST_LEN);
+	param = snd_hdac_read_parm_uncached(hdev, nid, AC_PAR_DEVLIST_LEN);
 	if (param == -1)
 		return param;
 
@@ -222,10 +224,10 @@ static int hdac_hdmi_get_port_len(struct hdac_ext_device *edev, hda_nid_t nid)
  * id selected on the pin. Return 0 means the first port entry
  * is selected or MST is not supported.
  */
-static int hdac_hdmi_port_select_get(struct hdac_ext_device *edev,
+static int hdac_hdmi_port_select_get(struct hdac_device *hdev,
 					struct hdac_hdmi_port *port)
 {
-	return snd_hdac_codec_read(&edev->hdev, port->pin->nid,
+	return snd_hdac_codec_read(hdev, port->pin->nid,
 				0, AC_VERB_GET_DEVICE_SEL, 0);
 }
 
@@ -233,7 +235,7 @@ static int hdac_hdmi_port_select_get(struct hdac_ext_device *edev,
  * Sets the selected port entry for the configuring Pin widget verb.
  * returns error if port set is not equal to port get otherwise success
  */
-static int hdac_hdmi_port_select_set(struct hdac_ext_device *edev,
+static int hdac_hdmi_port_select_set(struct hdac_device *hdev,
 					struct hdac_hdmi_port *port)
 {
 	int num_ports;
@@ -242,8 +244,7 @@ static int hdac_hdmi_port_select_set(struct hdac_ext_device *edev,
 		return 0;
 
 	/* AC_PAR_DEVLIST_LEN is 0 based. */
-	num_ports = hdac_hdmi_get_port_len(edev, port->pin->nid);
-
+	num_ports = hdac_hdmi_get_port_len(hdev, port->pin->nid);
 	if (num_ports < 0)
 		return -EIO;
 	/*
@@ -253,13 +254,13 @@ static int hdac_hdmi_port_select_set(struct hdac_ext_device *edev,
 	if (num_ports + 1  < port->id)
 		return 0;
 
-	snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0,
+	snd_hdac_codec_write(hdev, port->pin->nid, 0,
 			AC_VERB_SET_DEVICE_SEL, port->id);
 
-	if (port->id != hdac_hdmi_port_select_get(edev, port))
+	if (port->id != hdac_hdmi_port_select_get(hdev, port))
 		return -EIO;
 
-	dev_dbg(&edev->hdev.dev, "Selected the port=%d\n", port->id);
+	dev_dbg(&hdev->dev, "Selected the port=%d\n", port->id);
 
 	return 0;
 }
@@ -277,13 +278,6 @@ static struct hdac_hdmi_pcm *get_hdmi_pcm_from_id(struct hdac_hdmi_priv *hdmi,
 	return NULL;
 }
 
-static inline struct hdac_ext_device *to_hda_ext_device(struct device *dev)
-{
-	struct hdac_device *hdev = dev_to_hdac_dev(dev);
-
-	return to_ehdac_device(hdev);
-}
-
 static unsigned int sad_format(const u8 *sad)
 {
 	return ((sad[0] >> 0x3) & 0x1f);
@@ -324,15 +318,13 @@ format_constraint:
 }
 
 static void
-hdac_hdmi_set_dip_index(struct hdac_ext_device *edev, hda_nid_t pin_nid,
+hdac_hdmi_set_dip_index(struct hdac_device *hdev, hda_nid_t pin_nid,
 				int packet_index, int byte_index)
 {
 	int val;
 
 	val = (packet_index << 5) | (byte_index & 0x1f);
-
-	snd_hdac_codec_write(&edev->hdev, pin_nid, 0,
-				AC_VERB_SET_HDMI_DIP_INDEX, val);
+	snd_hdac_codec_write(hdev, pin_nid, 0, AC_VERB_SET_HDMI_DIP_INDEX, val);
 }
 
 struct dp_audio_infoframe {
@@ -347,14 +339,14 @@ struct dp_audio_infoframe {
 	u8 LFEPBL01_LSV36_DM_INH7;
 };
 
-static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *edev,
+static int hdac_hdmi_setup_audio_infoframe(struct hdac_device *hdev,
 		   struct hdac_hdmi_pcm *pcm, struct hdac_hdmi_port *port)
 {
 	uint8_t buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AUDIO_INFOFRAME_SIZE];
 	struct hdmi_audio_infoframe frame;
 	struct hdac_hdmi_pin *pin = port->pin;
 	struct dp_audio_infoframe dp_ai;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_cvt *cvt = pcm->cvt;
 	u8 *dip;
 	int ret;
@@ -363,11 +355,11 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *edev,
 	u8 conn_type;
 	int channels, ca;
 
-	ca = snd_hdac_channel_allocation(&edev->hdev, port->eld.info.spk_alloc,
+	ca = snd_hdac_channel_allocation(hdev, port->eld.info.spk_alloc,
 			pcm->channels, pcm->chmap_set, true, pcm->chmap);
 
 	channels = snd_hdac_get_active_channels(ca);
-	hdmi->chmap.ops.set_channel_count(&edev->hdev, cvt->nid, channels);
+	hdmi->chmap.ops.set_channel_count(hdev, cvt->nid, channels);
 
 	snd_hdac_setup_channel_mapping(&hdmi->chmap, pin->nid, false, ca,
 				pcm->channels, pcm->chmap, pcm->chmap_set);
@@ -400,32 +392,31 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *edev,
 		break;
 
 	default:
-		dev_err(&edev->hdev.dev, "Invalid connection type: %d\n",
-						conn_type);
+		dev_err(&hdev->dev, "Invalid connection type: %d\n", conn_type);
 		return -EIO;
 	}
 
 	/* stop infoframe transmission */
-	hdac_hdmi_set_dip_index(edev, pin->nid, 0x0, 0x0);
-	snd_hdac_codec_write(&edev->hdev, pin->nid, 0,
+	hdac_hdmi_set_dip_index(hdev, pin->nid, 0x0, 0x0);
+	snd_hdac_codec_write(hdev, pin->nid, 0,
 			AC_VERB_SET_HDMI_DIP_XMIT, AC_DIPXMIT_DISABLE);
 
 
 	/*  Fill infoframe. Index auto-incremented */
-	hdac_hdmi_set_dip_index(edev, pin->nid, 0x0, 0x0);
+	hdac_hdmi_set_dip_index(hdev, pin->nid, 0x0, 0x0);
 	if (conn_type == DRM_ELD_CONN_TYPE_HDMI) {
 		for (i = 0; i < sizeof(buffer); i++)
-			snd_hdac_codec_write(&edev->hdev, pin->nid, 0,
+			snd_hdac_codec_write(hdev, pin->nid, 0,
 				AC_VERB_SET_HDMI_DIP_DATA, buffer[i]);
 	} else {
 		for (i = 0; i < sizeof(dp_ai); i++)
-			snd_hdac_codec_write(&edev->hdev, pin->nid, 0,
+			snd_hdac_codec_write(hdev, pin->nid, 0,
 				AC_VERB_SET_HDMI_DIP_DATA, dip[i]);
 	}
 
 	/* Start infoframe */
-	hdac_hdmi_set_dip_index(edev, pin->nid, 0x0, 0x0);
-	snd_hdac_codec_write(&edev->hdev, pin->nid, 0,
+	hdac_hdmi_set_dip_index(hdev, pin->nid, 0x0, 0x0);
+	snd_hdac_codec_write(hdev, pin->nid, 0,
 			AC_VERB_SET_HDMI_DIP_XMIT, AC_DIPXMIT_BEST);
 
 	return 0;
@@ -435,12 +426,12 @@ static int hdac_hdmi_set_tdm_slot(struct snd_soc_dai *dai,
 		unsigned int tx_mask, unsigned int rx_mask,
 		int slots, int slot_width)
 {
-	struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_pcm *pcm;
 
-	dev_dbg(&edev->hdev.dev, "%s: strm_tag: %d\n", __func__, tx_mask);
+	dev_dbg(&hdev->dev, "%s: strm_tag: %d\n", __func__, tx_mask);
 
 	dai_map = &hdmi->dai_map[dai->id];
 
@@ -455,8 +446,8 @@ static int hdac_hdmi_set_tdm_slot(struct snd_soc_dai *dai,
 static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_hw_params *hparams, struct snd_soc_dai *dai)
 {
-	struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_port *port;
 	struct hdac_hdmi_pcm *pcm;
@@ -469,7 +460,7 @@ static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream,
 		return -ENODEV;
 
 	if ((!port->eld.monitor_present) || (!port->eld.eld_valid)) {
-		dev_err(&edev->hdev.dev,
+		dev_err(&hdev->dev,
 			"device is not configured for this pin:port%d:%d\n",
 					port->pin->nid, port->id);
 		return -ENODEV;
@@ -489,28 +480,28 @@ static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int hdac_hdmi_query_port_connlist(struct hdac_ext_device *edev,
+static int hdac_hdmi_query_port_connlist(struct hdac_device *hdev,
 					struct hdac_hdmi_pin *pin,
 					struct hdac_hdmi_port *port)
 {
-	if (!(get_wcaps(&edev->hdev, pin->nid) & AC_WCAP_CONN_LIST)) {
-		dev_warn(&edev->hdev.dev,
+	if (!(get_wcaps(hdev, pin->nid) & AC_WCAP_CONN_LIST)) {
+		dev_warn(&hdev->dev,
 			"HDMI: pin %d wcaps %#x does not support connection list\n",
-			pin->nid, get_wcaps(&edev->hdev, pin->nid));
+			pin->nid, get_wcaps(hdev, pin->nid));
 		return -EINVAL;
 	}
 
-	if (hdac_hdmi_port_select_set(edev, port) < 0)
+	if (hdac_hdmi_port_select_set(hdev, port) < 0)
 		return -EIO;
 
-	port->num_mux_nids = snd_hdac_get_connections(&edev->hdev, pin->nid,
+	port->num_mux_nids = snd_hdac_get_connections(hdev, pin->nid,
 			port->mux_nids, HDA_MAX_CONNECTIONS);
 	if (port->num_mux_nids == 0)
-		dev_warn(&edev->hdev.dev,
+		dev_warn(&hdev->dev,
 			"No connections found for pin:port %d:%d\n",
 						pin->nid, port->id);
 
-	dev_dbg(&edev->hdev.dev, "num_mux_nids %d for pin:port %d:%d\n",
+	dev_dbg(&hdev->dev, "num_mux_nids %d for pin:port %d:%d\n",
 			port->num_mux_nids, pin->nid, port->id);
 
 	return port->num_mux_nids;
@@ -526,7 +517,7 @@ static int hdac_hdmi_query_port_connlist(struct hdac_ext_device *edev,
  * connected.
  */
 static struct hdac_hdmi_port *hdac_hdmi_get_port_from_cvt(
-			struct hdac_ext_device *edev,
+			struct hdac_device *hdev,
 			struct hdac_hdmi_priv *hdmi,
 			struct hdac_hdmi_cvt *cvt)
 {
@@ -541,7 +532,7 @@ static struct hdac_hdmi_port *hdac_hdmi_get_port_from_cvt(
 
 			list_for_each_entry(port, &pcm->port_list, head) {
 				mutex_lock(&pcm->lock);
-				ret = hdac_hdmi_query_port_connlist(edev,
+				ret = hdac_hdmi_query_port_connlist(hdev,
 							port->pin, port);
 				mutex_unlock(&pcm->lock);
 				if (ret < 0)
@@ -568,8 +559,8 @@ static struct hdac_hdmi_port *hdac_hdmi_get_port_from_cvt(
 static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 			struct snd_soc_dai *dai)
 {
-	struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_cvt *cvt;
 	struct hdac_hdmi_port *port;
@@ -578,7 +569,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 	dai_map = &hdmi->dai_map[dai->id];
 
 	cvt = dai_map->cvt;
-	port = hdac_hdmi_get_port_from_cvt(edev, hdmi, cvt);
+	port = hdac_hdmi_get_port_from_cvt(hdev, hdmi, cvt);
 
 	/*
 	 * To make PA and other userland happy.
@@ -589,7 +580,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 	if ((!port->eld.monitor_present) ||
 			(!port->eld.eld_valid)) {
 
-		dev_warn(&edev->hdev.dev,
+		dev_warn(&hdev->dev,
 			"Failed: present?:%d ELD valid?:%d pin:port: %d:%d\n",
 			port->eld.monitor_present, port->eld.eld_valid,
 			port->pin->nid, port->id);
@@ -611,8 +602,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 static void hdac_hdmi_pcm_close(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
-	struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai);
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_pcm *pcm;
 
@@ -695,10 +685,10 @@ static void hdac_hdmi_fill_route(struct snd_soc_dapm_route *route,
 	route->connected = handler;
 }
 
-static struct hdac_hdmi_pcm *hdac_hdmi_get_pcm(struct hdac_ext_device *edev,
+static struct hdac_hdmi_pcm *hdac_hdmi_get_pcm(struct hdac_device *hdev,
 					struct hdac_hdmi_port *port)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm = NULL;
 	struct hdac_hdmi_port *p;
 
@@ -715,33 +705,32 @@ static struct hdac_hdmi_pcm *hdac_hdmi_get_pcm(struct hdac_ext_device *edev,
 	return NULL;
 }
 
-static void hdac_hdmi_set_power_state(struct hdac_ext_device *edev,
+static void hdac_hdmi_set_power_state(struct hdac_device *hdev,
 			     hda_nid_t nid, unsigned int pwr_state)
 {
 	int count;
 	unsigned int state;
 
-	if (get_wcaps(&edev->hdev, nid) & AC_WCAP_POWER) {
-		if (!snd_hdac_check_power_state(&edev->hdev, nid, pwr_state)) {
+	if (get_wcaps(hdev, nid) & AC_WCAP_POWER) {
+		if (!snd_hdac_check_power_state(hdev, nid, pwr_state)) {
 			for (count = 0; count < 10; count++) {
-				snd_hdac_codec_read(&edev->hdev, nid, 0,
+				snd_hdac_codec_read(hdev, nid, 0,
 						AC_VERB_SET_POWER_STATE,
 						pwr_state);
-				state = snd_hdac_sync_power_state(&edev->hdev,
+				state = snd_hdac_sync_power_state(hdev,
 						nid, pwr_state);
 				if (!(state & AC_PWRST_ERROR))
 					break;
 			}
 		}
-
 	}
 }
 
-static void hdac_hdmi_set_amp(struct hdac_ext_device *edev,
+static void hdac_hdmi_set_amp(struct hdac_device *hdev,
 				   hda_nid_t nid, int val)
 {
-	if (get_wcaps(&edev->hdev, nid) & AC_WCAP_OUT_AMP)
-		snd_hdac_codec_write(&edev->hdev, nid, 0,
+	if (get_wcaps(hdev, nid) & AC_WCAP_OUT_AMP)
+		snd_hdac_codec_write(hdev, nid, 0,
 					AC_VERB_SET_AMP_GAIN_MUTE, val);
 }
 
@@ -750,40 +739,40 @@ static int hdac_hdmi_pin_output_widget_event(struct snd_soc_dapm_widget *w,
 					struct snd_kcontrol *kc, int event)
 {
 	struct hdac_hdmi_port *port = w->priv;
-	struct hdac_ext_device *edev = to_hda_ext_device(w->dapm->dev);
+	struct hdac_device *hdev = dev_to_hdac_dev(w->dapm->dev);
 	struct hdac_hdmi_pcm *pcm;
 
-	dev_dbg(&edev->hdev.dev, "%s: widget: %s event: %x\n",
+	dev_dbg(&hdev->dev, "%s: widget: %s event: %x\n",
 			__func__, w->name, event);
 
-	pcm = hdac_hdmi_get_pcm(edev, port);
+	pcm = hdac_hdmi_get_pcm(hdev, port);
 	if (!pcm)
 		return -EIO;
 
 	/* set the device if pin is mst_capable */
-	if (hdac_hdmi_port_select_set(edev, port) < 0)
+	if (hdac_hdmi_port_select_set(hdev, port) < 0)
 		return -EIO;
 
 	switch (event) {
 	case SND_SOC_DAPM_PRE_PMU:
-		hdac_hdmi_set_power_state(edev, port->pin->nid, AC_PWRST_D0);
+		hdac_hdmi_set_power_state(hdev, port->pin->nid, AC_PWRST_D0);
 
 		/* Enable out path for this pin widget */
-		snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0,
+		snd_hdac_codec_write(hdev, port->pin->nid, 0,
 				AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
 
-		hdac_hdmi_set_amp(edev, port->pin->nid, AMP_OUT_UNMUTE);
+		hdac_hdmi_set_amp(hdev, port->pin->nid, AMP_OUT_UNMUTE);
 
-		return hdac_hdmi_setup_audio_infoframe(edev, pcm, port);
+		return hdac_hdmi_setup_audio_infoframe(hdev, pcm, port);
 
 	case SND_SOC_DAPM_POST_PMD:
-		hdac_hdmi_set_amp(edev, port->pin->nid, AMP_OUT_MUTE);
+		hdac_hdmi_set_amp(hdev, port->pin->nid, AMP_OUT_MUTE);
 
 		/* Disable out path for this pin widget */
-		snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0,
+		snd_hdac_codec_write(hdev, port->pin->nid, 0,
 				AC_VERB_SET_PIN_WIDGET_CONTROL, 0);
 
-		hdac_hdmi_set_power_state(edev, port->pin->nid, AC_PWRST_D3);
+		hdac_hdmi_set_power_state(hdev, port->pin->nid, AC_PWRST_D3);
 		break;
 
 	}
@@ -795,11 +784,11 @@ static int hdac_hdmi_cvt_output_widget_event(struct snd_soc_dapm_widget *w,
 					struct snd_kcontrol *kc, int event)
 {
 	struct hdac_hdmi_cvt *cvt = w->priv;
-	struct hdac_ext_device *edev = to_hda_ext_device(w->dapm->dev);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = dev_to_hdac_dev(w->dapm->dev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm;
 
-	dev_dbg(&edev->hdev.dev, "%s: widget: %s event: %x\n",
+	dev_dbg(&hdev->dev, "%s: widget: %s event: %x\n",
 			__func__, w->name, event);
 
 	pcm = hdac_hdmi_get_pcm_from_cvt(hdmi, cvt);
@@ -808,29 +797,29 @@ static int hdac_hdmi_cvt_output_widget_event(struct snd_soc_dapm_widget *w,
 
 	switch (event) {
 	case SND_SOC_DAPM_PRE_PMU:
-		hdac_hdmi_set_power_state(edev, cvt->nid, AC_PWRST_D0);
+		hdac_hdmi_set_power_state(hdev, cvt->nid, AC_PWRST_D0);
 
 		/* Enable transmission */
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 			AC_VERB_SET_DIGI_CONVERT_1, 1);
 
 		/* Category Code (CC) to zero */
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 			AC_VERB_SET_DIGI_CONVERT_2, 0);
 
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 				AC_VERB_SET_CHANNEL_STREAMID, pcm->stream_tag);
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 				AC_VERB_SET_STREAM_FORMAT, pcm->format);
 		break;
 
 	case SND_SOC_DAPM_POST_PMD:
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 				AC_VERB_SET_CHANNEL_STREAMID, 0);
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 				AC_VERB_SET_STREAM_FORMAT, 0);
 
-		hdac_hdmi_set_power_state(edev, cvt->nid, AC_PWRST_D3);
+		hdac_hdmi_set_power_state(hdev, cvt->nid, AC_PWRST_D3);
 		break;
 
 	}
@@ -842,10 +831,10 @@ static int hdac_hdmi_pin_mux_widget_event(struct snd_soc_dapm_widget *w,
 					struct snd_kcontrol *kc, int event)
 {
 	struct hdac_hdmi_port *port = w->priv;
-	struct hdac_ext_device *edev = to_hda_ext_device(w->dapm->dev);
+	struct hdac_device *hdev = dev_to_hdac_dev(w->dapm->dev);
 	int mux_idx;
 
-	dev_dbg(&edev->hdev.dev, "%s: widget: %s event: %x\n",
+	dev_dbg(&hdev->dev, "%s: widget: %s event: %x\n",
 			__func__, w->name, event);
 
 	if (!kc)
@@ -854,11 +843,11 @@ static int hdac_hdmi_pin_mux_widget_event(struct snd_soc_dapm_widget *w,
 	mux_idx = dapm_kcontrol_get_value(kc);
 
 	/* set the device if pin is mst_capable */
-	if (hdac_hdmi_port_select_set(edev, port) < 0)
+	if (hdac_hdmi_port_select_set(hdev, port) < 0)
 		return -EIO;
 
 	if (mux_idx > 0) {
-		snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0,
+		snd_hdac_codec_write(hdev, port->pin->nid, 0,
 			AC_VERB_SET_CONNECT_SEL, (mux_idx - 1));
 	}
 
@@ -877,8 +866,8 @@ static int hdac_hdmi_set_pin_port_mux(struct snd_kcontrol *kcontrol,
 	struct snd_soc_dapm_widget *w = snd_soc_dapm_kcontrol_widget(kcontrol);
 	struct snd_soc_dapm_context *dapm = w->dapm;
 	struct hdac_hdmi_port *port = w->priv;
-	struct hdac_ext_device *edev = to_hda_ext_device(dapm->dev);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = dev_to_hdac_dev(dapm->dev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm = NULL;
 	const char *cvt_name =  e->texts[ucontrol->value.enumerated.item[0]];
 
@@ -931,12 +920,12 @@ static int hdac_hdmi_set_pin_port_mux(struct snd_kcontrol *kcontrol,
  * care of selecting the right one and leaving all other inputs selected to
  * "NONE"
  */
-static int hdac_hdmi_create_pin_port_muxs(struct hdac_ext_device *edev,
+static int hdac_hdmi_create_pin_port_muxs(struct hdac_device *hdev,
 				struct hdac_hdmi_port *port,
 				struct snd_soc_dapm_widget *widget,
 				const char *widget_name)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pin *pin = port->pin;
 	struct snd_kcontrol_new *kc;
 	struct hdac_hdmi_cvt *cvt;
@@ -948,17 +937,17 @@ static int hdac_hdmi_create_pin_port_muxs(struct hdac_ext_device *edev,
 	int i = 0;
 	int num_items = hdmi->num_cvt + 1;
 
-	kc = devm_kzalloc(&edev->hdev.dev, sizeof(*kc), GFP_KERNEL);
+	kc = devm_kzalloc(&hdev->dev, sizeof(*kc), GFP_KERNEL);
 	if (!kc)
 		return -ENOMEM;
 
-	se = devm_kzalloc(&edev->hdev.dev, sizeof(*se), GFP_KERNEL);
+	se = devm_kzalloc(&hdev->dev, sizeof(*se), GFP_KERNEL);
 	if (!se)
 		return -ENOMEM;
 
 	snprintf(kc_name, NAME_SIZE, "Pin %d port %d Input",
 						pin->nid, port->id);
-	kc->name = devm_kstrdup(&edev->hdev.dev, kc_name, GFP_KERNEL);
+	kc->name = devm_kstrdup(&hdev->dev, kc_name, GFP_KERNEL);
 	if (!kc->name)
 		return -ENOMEM;
 
@@ -976,35 +965,35 @@ static int hdac_hdmi_create_pin_port_muxs(struct hdac_ext_device *edev,
 	se->mask = roundup_pow_of_two(se->items) - 1;
 
 	sprintf(mux_items, "NONE");
-	items[i] = devm_kstrdup(&edev->hdev.dev, mux_items, GFP_KERNEL);
+	items[i] = devm_kstrdup(&hdev->dev, mux_items, GFP_KERNEL);
 	if (!items[i])
 		return -ENOMEM;
 
 	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
 		i++;
 		sprintf(mux_items, "cvt %d", cvt->nid);
-		items[i] = devm_kstrdup(&edev->hdev.dev, mux_items, GFP_KERNEL);
+		items[i] = devm_kstrdup(&hdev->dev, mux_items, GFP_KERNEL);
 		if (!items[i])
 			return -ENOMEM;
 	}
 
-	se->texts = devm_kmemdup(&edev->hdev.dev, items,
+	se->texts = devm_kmemdup(&hdev->dev, items,
 			(num_items  * sizeof(char *)), GFP_KERNEL);
 	if (!se->texts)
 		return -ENOMEM;
 
-	return hdac_hdmi_fill_widget_info(&edev->hdev.dev, widget,
+	return hdac_hdmi_fill_widget_info(&hdev->dev, widget,
 			snd_soc_dapm_mux, port, widget_name, NULL, kc, 1,
 			hdac_hdmi_pin_mux_widget_event,
 			SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_REG);
 }
 
 /* Add cvt <- input <- mux route map */
-static void hdac_hdmi_add_pinmux_cvt_route(struct hdac_ext_device *edev,
+static void hdac_hdmi_add_pinmux_cvt_route(struct hdac_device *hdev,
 			struct snd_soc_dapm_widget *widgets,
 			struct snd_soc_dapm_route *route, int rindex)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	const struct snd_kcontrol_new *kc;
 	struct soc_enum *se;
 	int mux_index = hdmi->num_cvt + hdmi->num_ports;
@@ -1046,8 +1035,8 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
 {
 	struct snd_soc_dapm_widget *widgets;
 	struct snd_soc_dapm_route *route;
-	struct hdac_ext_device *edev = to_hda_ext_device(dapm->dev);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = dev_to_hdac_dev(dapm->dev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct snd_soc_dai_driver *dai_drv = hdmi->dai_drv;
 	char widget_name[NAME_SIZE];
 	struct hdac_hdmi_cvt *cvt;
@@ -1099,7 +1088,7 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
 		for (j = 0; j < pin->num_ports; j++) {
 			sprintf(widget_name, "Pin%d-Port%d Mux",
 				pin->nid, pin->ports[j].id);
-			ret = hdac_hdmi_create_pin_port_muxs(edev,
+			ret = hdac_hdmi_create_pin_port_muxs(hdev,
 						&pin->ports[j], &widgets[i],
 						widget_name);
 			if (ret < 0)
@@ -1134,7 +1123,7 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
 		}
 	}
 
-	hdac_hdmi_add_pinmux_cvt_route(edev, widgets, route, i);
+	hdac_hdmi_add_pinmux_cvt_route(hdev, widgets, route, i);
 
 	snd_soc_dapm_new_controls(dapm, widgets,
 		((2 * hdmi->num_ports) + hdmi->num_cvt));
@@ -1146,9 +1135,9 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
 
 }
 
-static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev)
+static int hdac_hdmi_init_dai_map(struct hdac_device *hdev)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_cvt *cvt;
 	int dai_id = 0;
@@ -1164,7 +1153,7 @@ static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev)
 		dai_id++;
 
 		if (dai_id == HDA_MAX_CVTS) {
-			dev_warn(&edev->hdev.dev,
+			dev_warn(&hdev->dev,
 				"Max dais supported: %d\n", dai_id);
 			break;
 		}
@@ -1173,9 +1162,9 @@ static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev)
 	return 0;
 }
 
-static int hdac_hdmi_add_cvt(struct hdac_ext_device *edev, hda_nid_t nid)
+static int hdac_hdmi_add_cvt(struct hdac_device *hdev, hda_nid_t nid)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_cvt *cvt;
 	char name[NAME_SIZE];
 
@@ -1190,10 +1179,10 @@ static int hdac_hdmi_add_cvt(struct hdac_ext_device *edev, hda_nid_t nid)
 	list_add_tail(&cvt->head, &hdmi->cvt_list);
 	hdmi->num_cvt++;
 
-	return hdac_hdmi_query_cvt_params(&edev->hdev, cvt);
+	return hdac_hdmi_query_cvt_params(hdev, cvt);
 }
 
-static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev,
+static int hdac_hdmi_parse_eld(struct hdac_device *hdev,
 			struct hdac_hdmi_port *port)
 {
 	unsigned int ver, mnl;
@@ -1202,7 +1191,7 @@ static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev,
 						>> DRM_ELD_VER_SHIFT;
 
 	if (ver != ELD_VER_CEA_861D && ver != ELD_VER_PARTIAL) {
-		dev_err(&edev->hdev.dev, "HDMI: Unknown ELD version %d\n", ver);
+		dev_err(&hdev->dev, "HDMI: Unknown ELD version %d\n", ver);
 		return -EINVAL;
 	}
 
@@ -1210,7 +1199,7 @@ static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev,
 		DRM_ELD_MNL_MASK) >> DRM_ELD_MNL_SHIFT;
 
 	if (mnl > ELD_MAX_MNL) {
-		dev_err(&edev->hdev.dev, "HDMI: MNL Invalid %d\n", mnl);
+		dev_err(&hdev->dev, "HDMI: MNL Invalid %d\n", mnl);
 		return -EINVAL;
 	}
 
@@ -1222,8 +1211,8 @@ static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev,
 static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin,
 				    struct hdac_hdmi_port *port)
 {
-	struct hdac_ext_device *edev = pin->edev;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = pin->hdev;
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm;
 	int size = 0;
 	int port_id = -1;
@@ -1241,14 +1230,14 @@ static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin,
 	if (pin->mst_capable)
 		port_id = port->id;
 
-	size = snd_hdac_acomp_get_eld(&edev->hdev, pin->nid, port_id,
+	size = snd_hdac_acomp_get_eld(hdev, pin->nid, port_id,
 				&port->eld.monitor_present,
 				port->eld.eld_buffer,
 				ELD_MAX_SIZE);
 
 	if (size > 0) {
 		size = min(size, ELD_MAX_SIZE);
-		if (hdac_hdmi_parse_eld(edev, port) < 0)
+		if (hdac_hdmi_parse_eld(hdev, port) < 0)
 			size = -EINVAL;
 	}
 
@@ -1260,11 +1249,11 @@ static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin,
 		port->eld.eld_size = 0;
 	}
 
-	pcm = hdac_hdmi_get_pcm(edev, port);
+	pcm = hdac_hdmi_get_pcm(hdev, port);
 
 	if (!port->eld.monitor_present || !port->eld.eld_valid) {
 
-		dev_err(&edev->hdev.dev, "%s: disconnect for pin:port %d:%d\n",
+		dev_err(&hdev->dev, "%s: disconnect for pin:port %d:%d\n",
 						__func__, pin->nid, port->id);
 
 		/*
@@ -1316,9 +1305,9 @@ static int hdac_hdmi_add_ports(struct hdac_hdmi_priv *hdmi,
 	return 0;
 }
 
-static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid)
+static int hdac_hdmi_add_pin(struct hdac_device *hdev, hda_nid_t nid)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pin *pin;
 	int ret;
 
@@ -1328,7 +1317,7 @@ static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid)
 
 	pin->nid = nid;
 	pin->mst_capable = false;
-	pin->edev = edev;
+	pin->hdev = hdev;
 	ret = hdac_hdmi_add_ports(hdmi, pin);
 	if (ret < 0)
 		return ret;
@@ -1459,15 +1448,14 @@ static int hdac_hdmi_create_dais(struct hdac_device *hdev,
  * Parse all nodes and store the cvt/pin nids in array
  * Add one time initialization for pin and cvt widgets
  */
-static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev,
+static int hdac_hdmi_parse_and_map_nid(struct hdac_device *hdev,
 		struct snd_soc_dai_driver **dais, int *num_dais)
 {
 	hda_nid_t nid;
 	int i, num_nodes;
 	struct hdac_hdmi_cvt *temp_cvt, *cvt_next;
 	struct hdac_hdmi_pin *temp_pin, *pin_next;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	int ret;
 
 	hdac_hdmi_skl_enable_all_pins(hdev);
@@ -1492,13 +1480,13 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev,
 		switch (type) {
 
 		case AC_WID_AUD_OUT:
-			ret = hdac_hdmi_add_cvt(edev, nid);
+			ret = hdac_hdmi_add_cvt(hdev, nid);
 			if (ret < 0)
 				goto free_widgets;
 			break;
 
 		case AC_WID_PIN:
-			ret = hdac_hdmi_add_pin(edev, nid);
+			ret = hdac_hdmi_add_pin(hdev, nid);
 			if (ret < 0)
 				goto free_widgets;
 			break;
@@ -1518,7 +1506,7 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev,
 	}
 
 	*num_dais = hdmi->num_cvt;
-	ret = hdac_hdmi_init_dai_map(edev);
+	ret = hdac_hdmi_init_dai_map(hdev);
 	if (ret < 0)
 		goto free_widgets;
 
@@ -1542,19 +1530,24 @@ free_widgets:
 	return ret;
 }
 
+static int hdac_hdmi_pin2port(void *aptr, int pin)
+{
+	return pin - 4; /* map NID 0x05 -> port #1 */
+}
+
 static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
 {
-	struct hdac_ext_device *edev = aptr;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = aptr;
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pin *pin = NULL;
 	struct hdac_hdmi_port *hport = NULL;
-	struct snd_soc_component *component = edev->scodec;
+	struct snd_soc_component *component = hdmi->component;
 	int i;
 
 	/* Don't know how this mapping is derived */
 	hda_nid_t pin_nid = port + 0x04;
 
-	dev_dbg(&edev->hdev.dev, "%s: for pin:%d port=%d\n", __func__,
+	dev_dbg(&hdev->dev, "%s: for pin:%d port=%d\n", __func__,
 							pin_nid, pipe);
 
 	/*
@@ -1567,7 +1560,7 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
 			SNDRV_CTL_POWER_D0)
 		return;
 
-	if (atomic_read(&edev->hdev.in_pm))
+	if (atomic_read(&hdev->in_pm))
 		return;
 
 	list_for_each_entry(pin, &hdmi->pin_list, head) {
@@ -1595,7 +1588,8 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
 
 }
 
-static struct i915_audio_component_audio_ops aops = {
+static struct drm_audio_component_audio_ops aops = {
+	.pin2port	= hdac_hdmi_pin2port,
 	.pin_eld_notify	= hdac_hdmi_eld_notify_cb,
 };
 
@@ -1614,15 +1608,15 @@ static struct snd_pcm *hdac_hdmi_get_pcm_from_id(struct snd_soc_card *card,
 
 /* create jack pin kcontrols */
 static int create_fill_jack_kcontrols(struct snd_soc_card *card,
-				    struct hdac_ext_device *edev)
+				    struct hdac_device *hdev)
 {
 	struct hdac_hdmi_pin *pin;
 	struct snd_kcontrol_new *kc;
 	char kc_name[NAME_SIZE], xname[NAME_SIZE];
 	char *name;
 	int i = 0, j;
-	struct snd_soc_component *component = edev->scodec;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
+	struct snd_soc_component *component = hdmi->component;
 
 	kc = devm_kcalloc(component->dev, hdmi->num_ports,
 				sizeof(*kc), GFP_KERNEL);
@@ -1659,8 +1653,8 @@ static int create_fill_jack_kcontrols(struct snd_soc_card *card,
 int hdac_hdmi_jack_port_init(struct snd_soc_component *component,
 			struct snd_soc_dapm_context *dapm)
 {
-	struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_pin *pin;
 	struct snd_soc_dapm_widget *widgets;
 	struct snd_soc_dapm_route *route;
@@ -1715,7 +1709,7 @@ int hdac_hdmi_jack_port_init(struct snd_soc_component *component,
 		return ret;
 
 	/* Add Jack Pin switch Kcontrol */
-	ret = create_fill_jack_kcontrols(dapm->card, edev);
+	ret = create_fill_jack_kcontrols(dapm->card, hdev);
 
 	if (ret < 0)
 		return ret;
@@ -1735,8 +1729,8 @@ int hdac_hdmi_jack_init(struct snd_soc_dai *dai, int device,
 				struct snd_soc_jack *jack)
 {
 	struct snd_soc_component *component = dai->component;
-	struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_pcm *pcm;
 	struct snd_pcm *snd_pcm;
 	int err;
@@ -1758,7 +1752,7 @@ int hdac_hdmi_jack_init(struct snd_soc_dai *dai, int device,
 	if (snd_pcm) {
 		err = snd_hdac_add_chmap_ctls(snd_pcm, device, &hdmi->chmap);
 		if (err < 0) {
-			dev_err(&edev->hdev.dev,
+			dev_err(&hdev->dev,
 				"chmap control add failed with err: %d for pcm: %d\n",
 				err, device);
 			kfree(pcm);
@@ -1772,7 +1766,7 @@ int hdac_hdmi_jack_init(struct snd_soc_dai *dai, int device,
 }
 EXPORT_SYMBOL_GPL(hdac_hdmi_jack_init);
 
-static void hdac_hdmi_present_sense_all_pins(struct hdac_ext_device *edev,
+static void hdac_hdmi_present_sense_all_pins(struct hdac_device *hdev,
 			struct hdac_hdmi_priv *hdmi, bool detect_pin_caps)
 {
 	int i;
@@ -1781,7 +1775,7 @@ static void hdac_hdmi_present_sense_all_pins(struct hdac_ext_device *edev,
 	list_for_each_entry(pin, &hdmi->pin_list, head) {
 		if (detect_pin_caps) {
 
-			if (hdac_hdmi_get_port_len(edev, pin->nid)  == 0)
+			if (hdac_hdmi_get_port_len(hdev, pin->nid)  == 0)
 				pin->mst_capable = false;
 			else
 				pin->mst_capable = true;
@@ -1798,68 +1792,67 @@ static void hdac_hdmi_present_sense_all_pins(struct hdac_ext_device *edev,
 
 static int hdmi_codec_probe(struct snd_soc_component *component)
 {
-	struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct snd_soc_dapm_context *dapm =
 		snd_soc_component_get_dapm(component);
 	struct hdac_ext_link *hlink = NULL;
 	int ret;
 
-	edev->scodec = component;
+	hdmi->component = component;
 
 	/*
 	 * hold the ref while we probe, also no need to drop the ref on
 	 * exit, we call pm_runtime_suspend() so that will do for us
 	 */
-	hlink = snd_hdac_ext_bus_get_link(edev->ebus, dev_name(&edev->hdev.dev));
+	hlink = snd_hdac_ext_bus_get_link(hdev->bus, dev_name(&hdev->dev));
 	if (!hlink) {
-		dev_err(&edev->hdev.dev, "hdac link not found\n");
+		dev_err(&hdev->dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_get(edev->ebus, hlink);
+	snd_hdac_ext_bus_link_get(hdev->bus, hlink);
 
 	ret = create_fill_widget_route_map(dapm);
 	if (ret < 0)
 		return ret;
 
-	aops.audio_ptr = edev;
-	ret = snd_hdac_i915_register_notifier(&aops);
+	aops.audio_ptr = hdev;
+	ret = snd_hdac_acomp_register_notifier(hdev->bus, &aops);
 	if (ret < 0) {
-		dev_err(&edev->hdev.dev, "notifier register failed: err: %d\n",
-				ret);
+		dev_err(&hdev->dev, "notifier register failed: err: %d\n", ret);
 		return ret;
 	}
 
-	hdac_hdmi_present_sense_all_pins(edev, hdmi, true);
+	hdac_hdmi_present_sense_all_pins(hdev, hdmi, true);
 	/* Imp: Store the card pointer in hda_codec */
-	edev->card = dapm->card->snd_card;
+	hdmi->card = dapm->card->snd_card;
 
 	/*
 	 * hdac_device core already sets the state to active and calls
 	 * get_noresume. So enable runtime and set the device to suspend.
 	 */
-	pm_runtime_enable(&edev->hdev.dev);
-	pm_runtime_put(&edev->hdev.dev);
-	pm_runtime_suspend(&edev->hdev.dev);
+	pm_runtime_enable(&hdev->dev);
+	pm_runtime_put(&hdev->dev);
+	pm_runtime_suspend(&hdev->dev);
 
 	return 0;
 }
 
 static void hdmi_codec_remove(struct snd_soc_component *component)
 {
-	struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component);
+	struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component);
+	struct hdac_device *hdev = hdmi->hdev;
 
-	pm_runtime_disable(&edev->hdev.dev);
+	pm_runtime_disable(&hdev->dev);
 }
 
 #ifdef CONFIG_PM
 static int hdmi_codec_prepare(struct device *dev)
 {
-	struct hdac_ext_device *edev = to_hda_ext_device(dev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_device *hdev = dev_to_hdac_dev(dev);
 
-	pm_runtime_get_sync(&edev->hdev.dev);
+	pm_runtime_get_sync(&hdev->dev);
 
 	/*
 	 * Power down afg.
@@ -1876,16 +1869,15 @@ static int hdmi_codec_prepare(struct device *dev)
 
 static void hdmi_codec_complete(struct device *dev)
 {
-	struct hdac_ext_device *edev = to_hda_ext_device(dev);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_device *hdev = dev_to_hdac_dev(dev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 
 	/* Power up afg */
 	snd_hdac_codec_read(hdev, hdev->afg, 0,	AC_VERB_SET_POWER_STATE,
 							AC_PWRST_D0);
 
-	hdac_hdmi_skl_enable_all_pins(&edev->hdev);
-	hdac_hdmi_skl_enable_dp12(&edev->hdev);
+	hdac_hdmi_skl_enable_all_pins(hdev);
+	hdac_hdmi_skl_enable_dp12(hdev);
 
 	/*
 	 * As the ELD notify callback request is not entertained while the
@@ -1893,9 +1885,9 @@ static void hdmi_codec_complete(struct device *dev)
 	 * all pins here. pin capablity change is not support, so use the
 	 * already set pin caps.
 	 */
-	hdac_hdmi_present_sense_all_pins(edev, hdmi, false);
+	hdac_hdmi_present_sense_all_pins(hdev, hdmi, false);
 
-	pm_runtime_put_sync(&edev->hdev.dev);
+	pm_runtime_put_sync(&hdev->dev);
 }
 #else
 #define hdmi_codec_prepare NULL
@@ -1922,7 +1914,6 @@ static void hdac_hdmi_get_chmap(struct hdac_device *hdev, int pcm_idx,
 static void hdac_hdmi_set_chmap(struct hdac_device *hdev, int pcm_idx,
 				unsigned char *chmap, int prepared)
 {
-	struct hdac_ext_device *edev = to_ehdac_device(hdev);
 	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm = get_hdmi_pcm_from_id(hdmi, pcm_idx);
 	struct hdac_hdmi_port *port;
@@ -1938,7 +1929,7 @@ static void hdac_hdmi_set_chmap(struct hdac_device *hdev, int pcm_idx,
 	memcpy(pcm->chmap, chmap, ARRAY_SIZE(pcm->chmap));
 	list_for_each_entry(port, &pcm->port_list, head)
 		if (prepared)
-			hdac_hdmi_setup_audio_infoframe(edev, pcm, port);
+			hdac_hdmi_setup_audio_infoframe(hdev, pcm, port);
 	mutex_unlock(&pcm->lock);
 }
 
@@ -1987,10 +1978,9 @@ static struct hdac_hdmi_drv_data intel_drv_data  = {
 	.vendor_nid = INTEL_VENDOR_NID,
 };
 
-static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
+static int hdac_hdmi_dev_probe(struct hdac_device *hdev)
 {
-	struct hdac_device *hdev = &edev->hdev;
-	struct hdac_hdmi_priv *hdmi_priv;
+	struct hdac_hdmi_priv *hdmi_priv = NULL;
 	struct snd_soc_dai_driver *hdmi_dais = NULL;
 	struct hdac_ext_link *hlink = NULL;
 	int num_dais = 0;
@@ -1999,24 +1989,24 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	const struct hda_device_id *hdac_id = hdac_get_device_id(hdev, hdrv);
 
 	/* hold the ref while we probe */
-	hlink = snd_hdac_ext_bus_get_link(edev->ebus, dev_name(&edev->hdev.dev));
+	hlink = snd_hdac_ext_bus_get_link(hdev->bus, dev_name(&hdev->dev));
 	if (!hlink) {
-		dev_err(&edev->hdev.dev, "hdac link not found\n");
+		dev_err(&hdev->dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_get(edev->ebus, hlink);
+	snd_hdac_ext_bus_link_get(hdev->bus, hlink);
 
 	hdmi_priv = devm_kzalloc(&hdev->dev, sizeof(*hdmi_priv), GFP_KERNEL);
 	if (hdmi_priv == NULL)
 		return -ENOMEM;
 
-	edev->private_data = hdmi_priv;
 	snd_hdac_register_chmap_ops(hdev, &hdmi_priv->chmap);
 	hdmi_priv->chmap.ops.get_chmap = hdac_hdmi_get_chmap;
 	hdmi_priv->chmap.ops.set_chmap = hdac_hdmi_set_chmap;
 	hdmi_priv->chmap.ops.is_pcm_attached = is_hdac_hdmi_pcm_attached;
 	hdmi_priv->chmap.ops.get_spk_alloc = hdac_hdmi_get_spk_alloc;
+	hdmi_priv->hdev = hdev;
 
 	if (!hdac_id)
 		return -ENODEV;
@@ -2027,7 +2017,7 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	else
 		hdmi_priv->drv_data = &intel_drv_data;
 
-	dev_set_drvdata(&hdev->dev, edev);
+	dev_set_drvdata(&hdev->dev, hdmi_priv);
 
 	INIT_LIST_HEAD(&hdmi_priv->pin_list);
 	INIT_LIST_HEAD(&hdmi_priv->cvt_list);
@@ -2038,15 +2028,15 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	 * Turned off in the runtime_suspend during the first explicit
 	 * pm_runtime_suspend call.
 	 */
-	ret = snd_hdac_display_power(edev->hdev.bus, true);
+	ret = snd_hdac_display_power(hdev->bus, true);
 	if (ret < 0) {
-		dev_err(&edev->hdev.dev,
+		dev_err(&hdev->dev,
 			"Cannot turn on display power on i915 err: %d\n",
 			ret);
 		return ret;
 	}
 
-	ret = hdac_hdmi_parse_and_map_nid(edev, &hdmi_dais, &num_dais);
+	ret = hdac_hdmi_parse_and_map_nid(hdev, &hdmi_dais, &num_dais);
 	if (ret < 0) {
 		dev_err(&hdev->dev,
 			"Failed in parse and map nid with err: %d\n", ret);
@@ -2058,14 +2048,14 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	ret = devm_snd_soc_register_component(&hdev->dev, &hdmi_hda_codec,
 					hdmi_dais, num_dais);
 
-	snd_hdac_ext_bus_link_put(edev->ebus, hlink);
+	snd_hdac_ext_bus_link_put(hdev->bus, hlink);
 
 	return ret;
 }
 
-static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
+static int hdac_hdmi_dev_remove(struct hdac_device *hdev)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pin *pin, *pin_next;
 	struct hdac_hdmi_cvt *cvt, *cvt_next;
 	struct hdac_hdmi_pcm *pcm, *pcm_next;
@@ -2103,12 +2093,79 @@ static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
 }
 
 #ifdef CONFIG_PM
+/*
+ * Power management sequences
+ * ==========================
+ *
+ * The following explains the PM handling of HDAC HDMI with its parent
+ * device SKL and display power usage
+ *
+ * Probe
+ * -----
+ * In SKL probe,
+ * 1. skl_probe_work() powers up the display (refcount++ -> 1)
+ * 2. enumerates the codecs on the link
+ * 3. powers down the display  (refcount-- -> 0)
+ *
+ * In HDAC HDMI probe,
+ * 1. hdac_hdmi_dev_probe() powers up the display (refcount++ -> 1)
+ * 2. probe the codec
+ * 3. put the HDAC HDMI device to runtime suspend
+ * 4. hdac_hdmi_runtime_suspend() powers down the display (refcount-- -> 0)
+ *
+ * Once children are runtime suspended, SKL device also goes to runtime
+ * suspend
+ *
+ * HDMI Playback
+ * -------------
+ * Open HDMI device,
+ * 1. skl_runtime_resume() invoked
+ * 2. hdac_hdmi_runtime_resume() powers up the display (refcount++ -> 1)
+ *
+ * Close HDMI device,
+ * 1. hdac_hdmi_runtime_suspend() powers down the display (refcount-- -> 0)
+ * 2. skl_runtime_suspend() invoked
+ *
+ * S0/S3 Cycle with playback in progress
+ * -------------------------------------
+ * When the device is opened for playback, the device is runtime active
+ * already and the display refcount is 1 as explained above.
+ *
+ * Entering to S3,
+ * 1. hdmi_codec_prepare() invoke the runtime resume of codec which just
+ *    increments the PM runtime usage count of the codec since the device
+ *    is in use already
+ * 2. skl_suspend() powers down the display (refcount-- -> 0)
+ *
+ * Wakeup from S3,
+ * 1. skl_resume() powers up the display (refcount++ -> 1)
+ * 2. hdmi_codec_complete() invokes the runtime suspend of codec which just
+ *    decrements the PM runtime usage count of the codec since the device
+ *    is in use already
+ *
+ * Once playback is stopped, the display refcount is set to 0 as explained
+ * above in the HDMI playback sequence. The PM handlings are designed in
+ * such way that to balance the refcount of display power when the codec
+ * device put to S3 while playback is going on.
+ *
+ * S0/S3 Cycle without playback in progress
+ * ----------------------------------------
+ * Entering to S3,
+ * 1. hdmi_codec_prepare() invoke the runtime resume of codec
+ * 2. skl_runtime_resume() invoked
+ * 3. hdac_hdmi_runtime_resume() powers up the display (refcount++ -> 1)
+ * 4. skl_suspend() powers down the display (refcount-- -> 0)
+ *
+ * Wakeup from S3,
+ * 1. skl_resume() powers up the display (refcount++ -> 1)
+ * 2. hdmi_codec_complete() invokes the runtime suspend of codec
+ * 3. hdac_hdmi_runtime_suspend() powers down the display (refcount-- -> 0)
+ * 4. skl_runtime_suspend() invoked
+ */
 static int hdac_hdmi_runtime_suspend(struct device *dev)
 {
-	struct hdac_ext_device *edev = to_hda_ext_device(dev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_device *hdev = dev_to_hdac_dev(dev);
 	struct hdac_bus *bus = hdev->bus;
-	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 	struct hdac_ext_link *hlink = NULL;
 	int err;
 
@@ -2129,27 +2186,25 @@ static int hdac_hdmi_runtime_suspend(struct device *dev)
 							AC_PWRST_D3);
 	err = snd_hdac_display_power(bus, false);
 	if (err < 0) {
-		dev_err(bus->dev, "Cannot turn on display power on i915\n");
+		dev_err(dev, "Cannot turn on display power on i915\n");
 		return err;
 	}
 
-	hlink = snd_hdac_ext_bus_get_link(ebus, dev_name(dev));
+	hlink = snd_hdac_ext_bus_get_link(bus, dev_name(dev));
 	if (!hlink) {
 		dev_err(dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_put(ebus, hlink);
+	snd_hdac_ext_bus_link_put(bus, hlink);
 
 	return 0;
 }
 
 static int hdac_hdmi_runtime_resume(struct device *dev)
 {
-	struct hdac_ext_device *edev = to_hda_ext_device(dev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_device *hdev = dev_to_hdac_dev(dev);
 	struct hdac_bus *bus = hdev->bus;
-	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 	struct hdac_ext_link *hlink = NULL;
 	int err;
 
@@ -2159,22 +2214,22 @@ static int hdac_hdmi_runtime_resume(struct device *dev)
 	if (!bus)
 		return 0;
 
-	hlink = snd_hdac_ext_bus_get_link(ebus, dev_name(dev));
+	hlink = snd_hdac_ext_bus_get_link(bus, dev_name(dev));
 	if (!hlink) {
 		dev_err(dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_get(ebus, hlink);
+	snd_hdac_ext_bus_link_get(bus, hlink);
 
 	err = snd_hdac_display_power(bus, true);
 	if (err < 0) {
-		dev_err(bus->dev, "Cannot turn on display power on i915\n");
+		dev_err(dev, "Cannot turn on display power on i915\n");
 		return err;
 	}
 
-	hdac_hdmi_skl_enable_all_pins(&edev->hdev);
-	hdac_hdmi_skl_enable_dp12(&edev->hdev);
+	hdac_hdmi_skl_enable_all_pins(hdev);
+	hdac_hdmi_skl_enable_dp12(hdev);
 
 	/* Power up afg */
 	snd_hdac_codec_read(hdev, hdev->afg, 0,	AC_VERB_SET_POWER_STATE,
@@ -2206,14 +2261,12 @@ static const struct hda_device_id hdmi_list[] = {
 
 MODULE_DEVICE_TABLE(hdaudio, hdmi_list);
 
-static struct hdac_ext_driver hdmi_driver = {
-	. hdac = {
-		.driver = {
-			.name   = "HDMI HDA Codec",
-			.pm = &hdac_hdmi_pm,
-		},
-		.id_table       = hdmi_list,
+static struct hdac_driver hdmi_driver = {
+	.driver = {
+		.name   = "HDMI HDA Codec",
+		.pm = &hdac_hdmi_pm,
 	},
+	.id_table       = hdmi_list,
 	.probe          = hdac_hdmi_dev_probe,
 	.remove         = hdac_hdmi_dev_remove,
 };
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index 38e4a8515709..d00734d31e04 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -291,10 +291,6 @@ static const struct snd_soc_dapm_widget hdmi_widgets[] = {
 	SND_SOC_DAPM_OUTPUT("TX"),
 };
 
-static const struct snd_soc_dapm_route hdmi_routes[] = {
-	{ "TX", NULL, "Playback" },
-};
-
 enum {
 	DAI_ID_I2S = 0,
 	DAI_ID_SPDIF,
@@ -689,9 +685,23 @@ static int hdmi_codec_pcm_new(struct snd_soc_pcm_runtime *rtd,
 	return snd_ctl_add(rtd->card->snd_card, kctl);
 }
 
+static int hdmi_dai_probe(struct snd_soc_dai *dai)
+{
+	struct snd_soc_dapm_context *dapm;
+	struct snd_soc_dapm_route route = {
+		.sink = "TX",
+		.source = dai->driver->playback.stream_name,
+	};
+
+	dapm = snd_soc_component_get_dapm(dai->component);
+
+	return snd_soc_dapm_add_routes(dapm, &route, 1);
+}
+
 static const struct snd_soc_dai_driver hdmi_i2s_dai = {
 	.name = "i2s-hifi",
 	.id = DAI_ID_I2S,
+	.probe = hdmi_dai_probe,
 	.playback = {
 		.stream_name = "I2S Playback",
 		.channels_min = 2,
@@ -707,6 +717,7 @@ static const struct snd_soc_dai_driver hdmi_i2s_dai = {
 static const struct snd_soc_dai_driver hdmi_spdif_dai = {
 	.name = "spdif-hifi",
 	.id = DAI_ID_SPDIF,
+	.probe = hdmi_dai_probe,
 	.playback = {
 		.stream_name = "SPDIF Playback",
 		.channels_min = 2,
@@ -733,8 +744,6 @@ static int hdmi_of_xlate_dai_id(struct snd_soc_component *component,
 static const struct snd_soc_component_driver hdmi_driver = {
 	.dapm_widgets		= hdmi_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(hdmi_widgets),
-	.dapm_routes		= hdmi_routes,
-	.num_dapm_routes	= ARRAY_SIZE(hdmi_routes),
 	.of_xlate_dai_id	= hdmi_of_xlate_dai_id,
 	.idle_bias_on		= 1,
 	.use_pmdown_time	= 1,
diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c
index a92586106932..92b7125ea169 100644
--- a/sound/soc/codecs/max98373.c
+++ b/sound/soc/codecs/max98373.c
@@ -488,6 +488,7 @@ static const DECLARE_TLV_DB_RANGE(max98373_bde_gain_tlv,
 static bool max98373_readable_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
+	case MAX98373_R2000_SW_RESET:
 	case MAX98373_R2001_INT_RAW1 ... MAX98373_R200C_INT_EN3:
 	case MAX98373_R2010_IRQ_CTRL:
 	case MAX98373_R2014_THERM_WARN_THRESH
diff --git a/sound/soc/codecs/max9850.c b/sound/soc/codecs/max9850.c
index 74d7f52c7e73..6e6134589588 100644
--- a/sound/soc/codecs/max9850.c
+++ b/sound/soc/codecs/max9850.c
@@ -52,9 +52,9 @@ static bool max9850_volatile_register(struct device *dev, unsigned int reg)
 	switch (reg) {
 	case MAX9850_STATUSA:
 	case MAX9850_STATUSB:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
diff --git a/sound/soc/codecs/nau8540.c b/sound/soc/codecs/nau8540.c
index 17104f8dc1a9..e3c8cd17daf2 100644
--- a/sound/soc/codecs/nau8540.c
+++ b/sound/soc/codecs/nau8540.c
@@ -362,11 +362,8 @@ static const struct snd_soc_dapm_route nau8540_dapm_routes[] = {
 
 static int nau8540_clock_check(struct nau8540 *nau8540, int rate, int osr)
 {
-	int osrate;
-
 	if (osr >= ARRAY_SIZE(osr_adc_sel))
 		return -EINVAL;
-	osrate = osr_adc_sel[osr].osr;
 
 	if (rate * osr > CLK_ADC_MAX) {
 		dev_err(nau8540->dev, "exceed the maximum frequency of CLK_ADC\n");
diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c
index 6bd14453f06e..468d5143e2c4 100644
--- a/sound/soc/codecs/nau8824.c
+++ b/sound/soc/codecs/nau8824.c
@@ -1274,7 +1274,7 @@ static int nau8824_calc_fll_param(unsigned int fll_in,
 	fvco_max = 0;
 	fvco_sel = ARRAY_SIZE(mclk_src_scaling);
 	for (i = 0; i < ARRAY_SIZE(mclk_src_scaling); i++) {
-		fvco = 256 * fs * 2 * mclk_src_scaling[i].param;
+		fvco = 256ULL * fs * 2 * mclk_src_scaling[i].param;
 		if (fvco > NAU_FVCO_MIN && fvco < NAU_FVCO_MAX &&
 			fvco_max < fvco) {
 			fvco_max = fvco;
diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c
index dc6ea4987b7d..b9fed99d8b5e 100644
--- a/sound/soc/codecs/nau8825.c
+++ b/sound/soc/codecs/nau8825.c
@@ -2016,7 +2016,7 @@ static int nau8825_calc_fll_param(unsigned int fll_in, unsigned int fs,
 	fvco_max = 0;
 	fvco_sel = ARRAY_SIZE(mclk_src_scaling);
 	for (i = 0; i < ARRAY_SIZE(mclk_src_scaling); i++) {
-		fvco = 256 * fs * 2 * mclk_src_scaling[i].param;
+		fvco = 256ULL * fs * 2 * mclk_src_scaling[i].param;
 		if (fvco > NAU_FVCO_MIN && fvco < NAU_FVCO_MAX &&
 			fvco_max < fvco) {
 			fvco_max = fvco;
diff --git a/sound/soc/codecs/pcm1789.c b/sound/soc/codecs/pcm1789.c
index 21f15219b3ad..8df6447c76a6 100644
--- a/sound/soc/codecs/pcm1789.c
+++ b/sound/soc/codecs/pcm1789.c
@@ -262,8 +262,7 @@ int pcm1789_common_exit(struct device *dev)
 {
 	struct pcm1789_private *priv = dev_get_drvdata(dev);
 
-	if (&priv->work)
-		flush_work(&priv->work);
+	flush_work(&priv->work);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/pcm186x.c b/sound/soc/codecs/pcm186x.c
index 88fde70b1e9e..690c26e7389e 100644
--- a/sound/soc/codecs/pcm186x.c
+++ b/sound/soc/codecs/pcm186x.c
@@ -265,7 +265,7 @@ static int pcm186x_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component = dai->component;
 	struct pcm186x_priv *priv = snd_soc_component_get_drvdata(component);
 	unsigned int rate = params_rate(params);
-	unsigned int format = params_format(params);
+	snd_pcm_format_t format = params_format(params);
 	unsigned int width = params_width(params);
 	unsigned int channels = params_channels(params);
 	unsigned int div_lrck;
diff --git a/sound/soc/codecs/rt1305.c b/sound/soc/codecs/rt1305.c
index f4c8c45f4010..c4452efc7970 100644
--- a/sound/soc/codecs/rt1305.c
+++ b/sound/soc/codecs/rt1305.c
@@ -1066,7 +1066,7 @@ static void rt1305_calibrate(struct rt1305_priv *rt1305)
 	pr_debug("Left_rhl = 0x%x rh=0x%x rl=0x%x\n", rhl, rh, rl);
 	pr_info("Left channel %d.%dohm\n", (r0ohm/10), (r0ohm%10));
 
-	r0l = 562949953421312;
+	r0l = 562949953421312ULL;
 	if (rhl != 0)
 		do_div(r0l, rhl);
 	pr_debug("Left_r0 = 0x%llx\n", r0l);
@@ -1083,7 +1083,7 @@ static void rt1305_calibrate(struct rt1305_priv *rt1305)
 	pr_debug("Right_rhl = 0x%x rh=0x%x rl=0x%x\n", rhl, rh, rl);
 	pr_info("Right channel %d.%dohm\n", (r0ohm/10), (r0ohm%10));
 
-	r0r = 562949953421312;
+	r0r = 562949953421312ULL;
 	if (rhl != 0)
 		do_div(r0r, rhl);
 	pr_debug("Right_r0 = 0x%llx\n", r0r);
@@ -1150,17 +1150,11 @@ static int rt1305_i2c_probe(struct i2c_client *i2c,
 	rt1305_reset(rt1305->regmap);
 	rt1305_calibrate(rt1305);
 
-	return snd_soc_register_component(&i2c->dev, &soc_component_dev_rt1305,
+	return devm_snd_soc_register_component(&i2c->dev,
+			&soc_component_dev_rt1305,
 			rt1305_dai, ARRAY_SIZE(rt1305_dai));
 }
 
-static int rt1305_i2c_remove(struct i2c_client *i2c)
-{
-	snd_soc_unregister_component(&i2c->dev);
-
-	return 0;
-}
-
 static void rt1305_i2c_shutdown(struct i2c_client *client)
 {
 	struct rt1305_priv *rt1305 = i2c_get_clientdata(client);
@@ -1180,7 +1174,6 @@ static struct i2c_driver rt1305_i2c_driver = {
 #endif
 	},
 	.probe = rt1305_i2c_probe,
-	.remove   = rt1305_i2c_remove,
 	.shutdown = rt1305_i2c_shutdown,
 	.id_table = rt1305_i2c_id,
 };
diff --git a/sound/soc/codecs/rt5514-spi.c b/sound/soc/codecs/rt5514-spi.c
index 18686ffb0cd5..6478d10c4f4a 100644
--- a/sound/soc/codecs/rt5514-spi.c
+++ b/sound/soc/codecs/rt5514-spi.c
@@ -268,7 +268,6 @@ static const struct snd_pcm_ops rt5514_spi_pcm_ops = {
 	.hw_params	= rt5514_spi_hw_params,
 	.hw_free	= rt5514_spi_hw_free,
 	.pointer	= rt5514_spi_pcm_pointer,
-	.mmap		= snd_pcm_lib_mmap_vmalloc,
 	.page		= snd_pcm_lib_get_vmalloc_page,
 };
 
diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c
index 1570b91bf018..dca82dd6e3bf 100644
--- a/sound/soc/codecs/rt5514.c
+++ b/sound/soc/codecs/rt5514.c
@@ -64,8 +64,8 @@ static const struct reg_sequence rt5514_patch[] = {
 	{RT5514_ANA_CTRL_LDO10,		0x00028604},
 	{RT5514_ANA_CTRL_ADCFED,	0x00000800},
 	{RT5514_ASRC_IN_CTRL1,		0x00000003},
-	{RT5514_DOWNFILTER0_CTRL3,	0x10000362},
-	{RT5514_DOWNFILTER1_CTRL3,	0x10000362},
+	{RT5514_DOWNFILTER0_CTRL3,	0x10000352},
+	{RT5514_DOWNFILTER1_CTRL3,	0x10000352},
 };
 
 static const struct reg_default rt5514_reg[] = {
@@ -92,10 +92,10 @@ static const struct reg_default rt5514_reg[] = {
 	{RT5514_ASRC_IN_CTRL1,		0x00000003},
 	{RT5514_DOWNFILTER0_CTRL1,	0x00020c2f},
 	{RT5514_DOWNFILTER0_CTRL2,	0x00020c2f},
-	{RT5514_DOWNFILTER0_CTRL3,	0x10000362},
+	{RT5514_DOWNFILTER0_CTRL3,	0x10000352},
 	{RT5514_DOWNFILTER1_CTRL1,	0x00020c2f},
 	{RT5514_DOWNFILTER1_CTRL2,	0x00020c2f},
-	{RT5514_DOWNFILTER1_CTRL3,	0x10000362},
+	{RT5514_DOWNFILTER1_CTRL3,	0x10000352},
 	{RT5514_ANA_CTRL_LDO10,		0x00028604},
 	{RT5514_ANA_CTRL_LDO18_16,	0x02000345},
 	{RT5514_ANA_CTRL_ADC12,		0x0000a2a8},
diff --git a/sound/soc/codecs/rt5631.c b/sound/soc/codecs/rt5631.c
index cf6dce69eb2a..865f49ac38dd 100644
--- a/sound/soc/codecs/rt5631.c
+++ b/sound/soc/codecs/rt5631.c
@@ -105,9 +105,9 @@ static bool rt5631_volatile_register(struct device *dev, unsigned int reg)
 	case RT5631_INDEX_ADD:
 	case RT5631_INDEX_DATA:
 	case RT5631_EQ_CTRL:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -164,9 +164,9 @@ static bool rt5631_readable_register(struct device *dev, unsigned int reg)
 	case RT5631_VENDOR_ID:
 	case RT5631_VENDOR_ID1:
 	case RT5631_VENDOR_ID2:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -229,10 +229,10 @@ static SOC_ENUM_SINGLE_DECL(rt5631_spk_ratio_enum, RT5631_GEN_PUR_CTRL_REG,
 static const struct snd_kcontrol_new rt5631_snd_controls[] = {
 	/* MIC */
 	SOC_ENUM("MIC1 Mode Control",  rt5631_mic1_mode_enum),
-	SOC_SINGLE_TLV("MIC1 Boost", RT5631_MIC_CTRL_2,
+	SOC_SINGLE_TLV("MIC1 Boost Volume", RT5631_MIC_CTRL_2,
 		RT5631_MIC1_BOOST_SHIFT, 8, 0, mic_bst_tlv),
 	SOC_ENUM("MIC2 Mode Control", rt5631_mic2_mode_enum),
-	SOC_SINGLE_TLV("MIC2 Boost", RT5631_MIC_CTRL_2,
+	SOC_SINGLE_TLV("MIC2 Boost Volume", RT5631_MIC_CTRL_2,
 		RT5631_MIC2_BOOST_SHIFT, 8, 0, mic_bst_tlv),
 	/* MONO IN */
 	SOC_ENUM("MONOIN Mode Control", rt5631_monoin_mode_enum),
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index 8bf8d360c25f..27770143ae8f 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -1665,6 +1665,7 @@ static int get_sdp_info(struct snd_soc_component *component, int dai_id)
 			break;
 		case RT5640_IF_113:
 			ret |= RT5640_U_IF1;
+			/* fall through */
 		case RT5640_IF_312:
 		case RT5640_IF_213:
 			ret |= RT5640_U_IF2;
@@ -1680,6 +1681,7 @@ static int get_sdp_info(struct snd_soc_component *component, int dai_id)
 			break;
 		case RT5640_IF_223:
 			ret |= RT5640_U_IF1;
+			/* fall through */
 		case RT5640_IF_123:
 		case RT5640_IF_321:
 			ret |= RT5640_U_IF2;
diff --git a/sound/soc/codecs/rt5651.c b/sound/soc/codecs/rt5651.c
index 6b5669f3e85d..985852fd9723 100644
--- a/sound/soc/codecs/rt5651.c
+++ b/sound/soc/codecs/rt5651.c
@@ -331,11 +331,13 @@ static const struct snd_kcontrol_new rt5651_snd_controls[] = {
 	SOC_DOUBLE_TLV("Mono DAC Playback Volume", RT5651_DAC2_DIG_VOL,
 			RT5651_L_VOL_SFT, RT5651_R_VOL_SFT,
 			175, 0, dac_vol_tlv),
-	/* IN1/IN2 Control */
+	/* IN1/IN2/IN3 Control */
 	SOC_SINGLE_TLV("IN1 Boost", RT5651_IN1_IN2,
 		RT5651_BST_SFT1, 8, 0, bst_tlv),
 	SOC_SINGLE_TLV("IN2 Boost", RT5651_IN1_IN2,
 		RT5651_BST_SFT2, 8, 0, bst_tlv),
+	SOC_SINGLE_TLV("IN3 Boost", RT5651_IN3,
+		RT5651_BST_SFT1, 8, 0, bst_tlv),
 	/* INL/INR Volume Control */
 	SOC_DOUBLE_TLV("IN Capture Volume", RT5651_INL1_INR1_VOL,
 			RT5651_INL_VOL_SFT, RT5651_INR_VOL_SFT,
@@ -1581,6 +1583,24 @@ static void rt5651_disable_micbias1_for_ovcd(struct snd_soc_component *component
 	snd_soc_dapm_mutex_unlock(dapm);
 }
 
+static void rt5651_enable_micbias1_ovcd_irq(struct snd_soc_component *component)
+{
+	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
+
+	snd_soc_component_update_bits(component, RT5651_IRQ_CTRL2,
+		RT5651_IRQ_MB1_OC_MASK, RT5651_IRQ_MB1_OC_NOR);
+	rt5651->ovcd_irq_enabled = true;
+}
+
+static void rt5651_disable_micbias1_ovcd_irq(struct snd_soc_component *component)
+{
+	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
+
+	snd_soc_component_update_bits(component, RT5651_IRQ_CTRL2,
+		RT5651_IRQ_MB1_OC_MASK, RT5651_IRQ_MB1_OC_BP);
+	rt5651->ovcd_irq_enabled = false;
+}
+
 static void rt5651_clear_micbias1_ovcd(struct snd_soc_component *component)
 {
 	snd_soc_component_update_bits(component, RT5651_IRQ_CTRL2,
@@ -1622,10 +1642,80 @@ static bool rt5651_jack_inserted(struct snd_soc_component *component)
 	return val == 0;
 }
 
-/* Jack detect timings */
+/* Jack detect and button-press timings */
 #define JACK_SETTLE_TIME	100 /* milli seconds */
 #define JACK_DETECT_COUNT	5
 #define JACK_DETECT_MAXCOUNT	20  /* Aprox. 2 seconds worth of tries */
+#define JACK_UNPLUG_TIME	80  /* milli seconds */
+#define BP_POLL_TIME		10  /* milli seconds */
+#define BP_POLL_MAXCOUNT	200 /* assume something is wrong after this */
+#define BP_THRESHOLD		3
+
+static void rt5651_start_button_press_work(struct snd_soc_component *component)
+{
+	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
+
+	rt5651->poll_count = 0;
+	rt5651->press_count = 0;
+	rt5651->release_count = 0;
+	rt5651->pressed = false;
+	rt5651->press_reported = false;
+	rt5651_clear_micbias1_ovcd(component);
+	schedule_delayed_work(&rt5651->bp_work, msecs_to_jiffies(BP_POLL_TIME));
+}
+
+static void rt5651_button_press_work(struct work_struct *work)
+{
+	struct rt5651_priv *rt5651 =
+		container_of(work, struct rt5651_priv, bp_work.work);
+	struct snd_soc_component *component = rt5651->component;
+
+	/* Check the jack was not removed underneath us */
+	if (!rt5651_jack_inserted(component))
+		return;
+
+	if (rt5651_micbias1_ovcd(component)) {
+		rt5651->release_count = 0;
+		rt5651->press_count++;
+		/* Remember till after JACK_UNPLUG_TIME wait */
+		if (rt5651->press_count >= BP_THRESHOLD)
+			rt5651->pressed = true;
+		rt5651_clear_micbias1_ovcd(component);
+	} else {
+		rt5651->press_count = 0;
+		rt5651->release_count++;
+	}
+
+	/*
+	 * The pins get temporarily shorted on jack unplug, so we poll for
+	 * at least JACK_UNPLUG_TIME milli-seconds before reporting a press.
+	 */
+	rt5651->poll_count++;
+	if (rt5651->poll_count < (JACK_UNPLUG_TIME / BP_POLL_TIME)) {
+		schedule_delayed_work(&rt5651->bp_work,
+				      msecs_to_jiffies(BP_POLL_TIME));
+		return;
+	}
+
+	if (rt5651->pressed && !rt5651->press_reported) {
+		dev_dbg(component->dev, "headset button press\n");
+		snd_soc_jack_report(rt5651->hp_jack, SND_JACK_BTN_0,
+				    SND_JACK_BTN_0);
+		rt5651->press_reported = true;
+	}
+
+	if (rt5651->release_count >= BP_THRESHOLD) {
+		if (rt5651->press_reported) {
+			dev_dbg(component->dev, "headset button release\n");
+			snd_soc_jack_report(rt5651->hp_jack, 0, SND_JACK_BTN_0);
+		}
+		/* Re-enable OVCD IRQ to detect next press */
+		rt5651_enable_micbias1_ovcd_irq(component);
+		return; /* Stop polling */
+	}
+
+	schedule_delayed_work(&rt5651->bp_work, msecs_to_jiffies(BP_POLL_TIME));
+}
 
 static int rt5651_detect_headset(struct snd_soc_component *component)
 {
@@ -1676,15 +1766,58 @@ static void rt5651_jack_detect_work(struct work_struct *work)
 {
 	struct rt5651_priv *rt5651 =
 		container_of(work, struct rt5651_priv, jack_detect_work);
+	struct snd_soc_component *component = rt5651->component;
 	int report = 0;
 
-	if (rt5651_jack_inserted(rt5651->component)) {
-		rt5651_enable_micbias1_for_ovcd(rt5651->component);
-		report = rt5651_detect_headset(rt5651->component);
-		rt5651_disable_micbias1_for_ovcd(rt5651->component);
+	if (!rt5651_jack_inserted(component)) {
+		/* Jack removed, or spurious IRQ? */
+		if (rt5651->hp_jack->status & SND_JACK_HEADPHONE) {
+			if (rt5651->hp_jack->status & SND_JACK_MICROPHONE) {
+				cancel_delayed_work_sync(&rt5651->bp_work);
+				rt5651_disable_micbias1_ovcd_irq(component);
+				rt5651_disable_micbias1_for_ovcd(component);
+			}
+			snd_soc_jack_report(rt5651->hp_jack, 0,
+					    SND_JACK_HEADSET | SND_JACK_BTN_0);
+			dev_dbg(component->dev, "jack unplugged\n");
+		}
+	} else if (!(rt5651->hp_jack->status & SND_JACK_HEADPHONE)) {
+		/* Jack inserted */
+		WARN_ON(rt5651->ovcd_irq_enabled);
+		rt5651_enable_micbias1_for_ovcd(component);
+		report = rt5651_detect_headset(component);
+		if (report == SND_JACK_HEADSET) {
+			/* Enable ovcd IRQ for button press detect. */
+			rt5651_enable_micbias1_ovcd_irq(component);
+		} else {
+			/* No more need for overcurrent detect. */
+			rt5651_disable_micbias1_for_ovcd(component);
+		}
+		dev_dbg(component->dev, "detect report %#02x\n", report);
+		snd_soc_jack_report(rt5651->hp_jack, report, SND_JACK_HEADSET);
+	} else if (rt5651->ovcd_irq_enabled && rt5651_micbias1_ovcd(component)) {
+		dev_dbg(component->dev, "OVCD IRQ\n");
+
+		/*
+		 * The ovcd IRQ keeps firing while the button is pressed, so
+		 * we disable it and start polling the button until released.
+		 *
+		 * The disable will make the IRQ pin 0 again and since we get
+		 * IRQs on both edges (so as to detect both jack plugin and
+		 * unplug) this means we will immediately get another IRQ.
+		 * The ovcd_irq_enabled check above makes the 2ND IRQ a NOP.
+		 */
+		rt5651_disable_micbias1_ovcd_irq(component);
+		rt5651_start_button_press_work(component);
+
+		/*
+		 * If the jack-detect IRQ flag goes high (unplug) after our
+		 * above rt5651_jack_inserted() check and before we have
+		 * disabled the OVCD IRQ, the IRQ pin will stay high and as
+		 * we react to edges, we miss the unplug event -> recheck.
+		 */
+		queue_work(system_long_wq, &rt5651->jack_detect_work);
 	}
-
-	snd_soc_jack_report(rt5651->hp_jack, report, SND_JACK_HEADSET);
 }
 
 static irqreturn_t rt5651_irq(int irq, void *data)
@@ -1696,14 +1829,18 @@ static irqreturn_t rt5651_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int rt5651_set_jack(struct snd_soc_component *component,
-			   struct snd_soc_jack *hp_jack, void *data)
+static void rt5651_cancel_work(void *data)
 {
-	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
-	int ret;
+	struct rt5651_priv *rt5651 = data;
 
-	if (!rt5651->irq)
-		return -EINVAL;
+	cancel_work_sync(&rt5651->jack_detect_work);
+	cancel_delayed_work_sync(&rt5651->bp_work);
+}
+
+static void rt5651_enable_jack_detect(struct snd_soc_component *component,
+				      struct snd_soc_jack *hp_jack)
+{
+	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
 
 	/* IRQ output on GPIO1 */
 	snd_soc_component_update_bits(component, RT5651_GPIO_CTRL1,
@@ -1730,10 +1867,10 @@ static int rt5651_set_jack(struct snd_soc_component *component,
 			RT5651_JD2_IRQ_EN, RT5651_JD2_IRQ_EN);
 		break;
 	case RT5651_JD_NULL:
-		return 0;
+		return;
 	default:
 		dev_err(component->dev, "Currently only JD1_1 / JD1_2 / JD2 are supported\n");
-		return -EINVAL;
+		return;
 	}
 
 	/* Enable jack detect power */
@@ -1767,19 +1904,39 @@ static int rt5651_set_jack(struct snd_soc_component *component,
 		RT5651_MB1_OC_STKY_MASK, RT5651_MB1_OC_STKY_EN);
 
 	rt5651->hp_jack = hp_jack;
-
-	ret = devm_request_threaded_irq(component->dev, rt5651->irq, NULL,
-					rt5651_irq,
-					IRQF_TRIGGER_RISING |
-					IRQF_TRIGGER_FALLING |
-					IRQF_ONESHOT, "rt5651", rt5651);
-	if (ret) {
-		dev_err(component->dev, "Failed to reguest IRQ: %d\n", ret);
-		return ret;
+	if (rt5651->hp_jack->status & SND_JACK_MICROPHONE) {
+		rt5651_enable_micbias1_for_ovcd(component);
+		rt5651_enable_micbias1_ovcd_irq(component);
 	}
 
+	enable_irq(rt5651->irq);
 	/* sync initial jack state */
 	queue_work(system_power_efficient_wq, &rt5651->jack_detect_work);
+}
+
+static void rt5651_disable_jack_detect(struct snd_soc_component *component)
+{
+	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
+
+	disable_irq(rt5651->irq);
+	rt5651_cancel_work(rt5651);
+
+	if (rt5651->hp_jack->status & SND_JACK_MICROPHONE) {
+		rt5651_disable_micbias1_ovcd_irq(component);
+		rt5651_disable_micbias1_for_ovcd(component);
+		snd_soc_jack_report(rt5651->hp_jack, 0, SND_JACK_BTN_0);
+	}
+
+	rt5651->hp_jack = NULL;
+}
+
+static int rt5651_set_jack(struct snd_soc_component *component,
+			   struct snd_soc_jack *jack, void *data)
+{
+	if (jack)
+		rt5651_enable_jack_detect(component, jack);
+	else
+		rt5651_disable_jack_detect(component);
 
 	return 0;
 }
@@ -2034,8 +2191,26 @@ static int rt5651_i2c_probe(struct i2c_client *i2c,
 	rt5651->irq = i2c->irq;
 	rt5651->hp_mute = 1;
 
+	INIT_DELAYED_WORK(&rt5651->bp_work, rt5651_button_press_work);
 	INIT_WORK(&rt5651->jack_detect_work, rt5651_jack_detect_work);
 
+	/* Make sure work is stopped on probe-error / remove */
+	ret = devm_add_action_or_reset(&i2c->dev, rt5651_cancel_work, rt5651);
+	if (ret)
+		return ret;
+
+	ret = devm_request_irq(&i2c->dev, rt5651->irq, rt5651_irq,
+			       IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+			       | IRQF_ONESHOT, "rt5651", rt5651);
+	if (ret == 0) {
+		/* Gets re-enabled by rt5651_set_jack() */
+		disable_irq(rt5651->irq);
+	} else {
+		dev_warn(&i2c->dev, "Failed to reguest IRQ %d: %d\n",
+			 rt5651->irq, ret);
+		rt5651->irq = -ENXIO;
+	}
+
 	ret = devm_snd_soc_register_component(&i2c->dev,
 				&soc_component_dev_rt5651,
 				rt5651_dai, ARRAY_SIZE(rt5651_dai));
@@ -2043,15 +2218,6 @@ static int rt5651_i2c_probe(struct i2c_client *i2c,
 	return ret;
 }
 
-static int rt5651_i2c_remove(struct i2c_client *i2c)
-{
-	struct rt5651_priv *rt5651 = i2c_get_clientdata(i2c);
-
-	cancel_work_sync(&rt5651->jack_detect_work);
-
-	return 0;
-}
-
 static struct i2c_driver rt5651_i2c_driver = {
 	.driver = {
 		.name = "rt5651",
@@ -2059,7 +2225,6 @@ static struct i2c_driver rt5651_i2c_driver = {
 		.of_match_table = of_match_ptr(rt5651_of_match),
 	},
 	.probe = rt5651_i2c_probe,
-	.remove   = rt5651_i2c_remove,
 	.id_table = rt5651_i2c_id,
 };
 module_i2c_driver(rt5651_i2c_driver);
diff --git a/sound/soc/codecs/rt5651.h b/sound/soc/codecs/rt5651.h
index 3a0968c53fde..ac6de6fb5414 100644
--- a/sound/soc/codecs/rt5651.h
+++ b/sound/soc/codecs/rt5651.h
@@ -2071,8 +2071,16 @@ struct rt5651_pll_code {
 struct rt5651_priv {
 	struct snd_soc_component *component;
 	struct regmap *regmap;
+	/* Jack and button detect data */
 	struct snd_soc_jack *hp_jack;
 	struct work_struct jack_detect_work;
+	struct delayed_work bp_work;
+	bool ovcd_irq_enabled;
+	bool pressed;
+	bool press_reported;
+	int press_count;
+	int release_count;
+	int poll_count;
 	unsigned int jd_src;
 	unsigned int ovcd_th;
 	unsigned int ovcd_sf;
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 8a0181a2db08..9b7a1833d331 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -4417,6 +4417,7 @@ static int rt5677_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
 		break;
 	case 25:
 		slot_width_25 = 0x8080;
+		/* fall through */
 	case 24:
 		val |= (2 << 8);
 		break;
@@ -5007,7 +5008,7 @@ static const struct regmap_config rt5677_regmap = {
 };
 
 static const struct of_device_id rt5677_of_match[] = {
-	{ .compatible = "realtek,rt5677", RT5677 },
+	{ .compatible = "realtek,rt5677", .data = (const void *)RT5677 },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, rt5677_of_match);
diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
new file mode 100644
index 000000000000..640d400ca013
--- /dev/null
+++ b/sound/soc/codecs/rt5682.c
@@ -0,0 +1,2681 @@
+/*
+ * rt5682.c  --  RT5682 ALSA SoC audio component driver
+ *
+ * Copyright 2018 Realtek Semiconductor Corp.
+ * Author: Bard Liao <bardliao@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/pm.h>
+#include <linux/i2c.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/acpi.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/regulator/consumer.h>
+#include <linux/mutex.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/jack.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+#include <sound/rt5682.h>
+
+#include "rl6231.h"
+#include "rt5682.h"
+
+#define RT5682_NUM_SUPPLIES 3
+
+static const char *rt5682_supply_names[RT5682_NUM_SUPPLIES] = {
+	"AVDD",
+	"MICVDD",
+	"VBAT",
+};
+
+struct rt5682_priv {
+	struct snd_soc_component *component;
+	struct rt5682_platform_data pdata;
+	struct regmap *regmap;
+	struct snd_soc_jack *hs_jack;
+	struct regulator_bulk_data supplies[RT5682_NUM_SUPPLIES];
+	struct delayed_work jack_detect_work;
+	struct delayed_work jd_check_work;
+	struct mutex calibrate_mutex;
+
+	int sysclk;
+	int sysclk_src;
+	int lrck[RT5682_AIFS];
+	int bclk[RT5682_AIFS];
+	int master[RT5682_AIFS];
+
+	int pll_src;
+	int pll_in;
+	int pll_out;
+
+	int jack_type;
+};
+
+static const struct reg_sequence patch_list[] = {
+	{0x01c1, 0x1000},
+};
+
+static const struct reg_default rt5682_reg[] = {
+	{0x0002, 0x8080},
+	{0x0003, 0x8000},
+	{0x0005, 0x0000},
+	{0x0006, 0x0000},
+	{0x0008, 0x800f},
+	{0x000b, 0x0000},
+	{0x0010, 0x4040},
+	{0x0011, 0x0000},
+	{0x0012, 0x1404},
+	{0x0013, 0x1000},
+	{0x0014, 0xa00a},
+	{0x0015, 0x0404},
+	{0x0016, 0x0404},
+	{0x0019, 0xafaf},
+	{0x001c, 0x2f2f},
+	{0x001f, 0x0000},
+	{0x0022, 0x5757},
+	{0x0023, 0x0039},
+	{0x0024, 0x000b},
+	{0x0026, 0xc0c4},
+	{0x0029, 0x8080},
+	{0x002a, 0xa0a0},
+	{0x002b, 0x0300},
+	{0x0030, 0x0000},
+	{0x003c, 0x0080},
+	{0x0044, 0x0c0c},
+	{0x0049, 0x0000},
+	{0x0061, 0x0000},
+	{0x0062, 0x0000},
+	{0x0063, 0x003f},
+	{0x0064, 0x0000},
+	{0x0065, 0x0000},
+	{0x0066, 0x0030},
+	{0x0067, 0x0000},
+	{0x006b, 0x0000},
+	{0x006c, 0x0000},
+	{0x006d, 0x2200},
+	{0x006e, 0x0a10},
+	{0x0070, 0x8000},
+	{0x0071, 0x8000},
+	{0x0073, 0x0000},
+	{0x0074, 0x0000},
+	{0x0075, 0x0002},
+	{0x0076, 0x0001},
+	{0x0079, 0x0000},
+	{0x007a, 0x0000},
+	{0x007b, 0x0000},
+	{0x007c, 0x0100},
+	{0x007e, 0x0000},
+	{0x0080, 0x0000},
+	{0x0081, 0x0000},
+	{0x0082, 0x0000},
+	{0x0083, 0x0000},
+	{0x0084, 0x0000},
+	{0x0085, 0x0000},
+	{0x0086, 0x0005},
+	{0x0087, 0x0000},
+	{0x0088, 0x0000},
+	{0x008c, 0x0003},
+	{0x008d, 0x0000},
+	{0x008e, 0x0060},
+	{0x008f, 0x1000},
+	{0x0091, 0x0c26},
+	{0x0092, 0x0073},
+	{0x0093, 0x0000},
+	{0x0094, 0x0080},
+	{0x0098, 0x0000},
+	{0x009a, 0x0000},
+	{0x009b, 0x0000},
+	{0x009c, 0x0000},
+	{0x009d, 0x0000},
+	{0x009e, 0x100c},
+	{0x009f, 0x0000},
+	{0x00a0, 0x0000},
+	{0x00a3, 0x0002},
+	{0x00a4, 0x0001},
+	{0x00ae, 0x2040},
+	{0x00af, 0x0000},
+	{0x00b6, 0x0000},
+	{0x00b7, 0x0000},
+	{0x00b8, 0x0000},
+	{0x00b9, 0x0002},
+	{0x00be, 0x0000},
+	{0x00c0, 0x0160},
+	{0x00c1, 0x82a0},
+	{0x00c2, 0x0000},
+	{0x00d0, 0x0000},
+	{0x00d1, 0x2244},
+	{0x00d2, 0x3300},
+	{0x00d3, 0x2200},
+	{0x00d4, 0x0000},
+	{0x00d9, 0x0009},
+	{0x00da, 0x0000},
+	{0x00db, 0x0000},
+	{0x00dc, 0x00c0},
+	{0x00dd, 0x2220},
+	{0x00de, 0x3131},
+	{0x00df, 0x3131},
+	{0x00e0, 0x3131},
+	{0x00e2, 0x0000},
+	{0x00e3, 0x4000},
+	{0x00e4, 0x0aa0},
+	{0x00e5, 0x3131},
+	{0x00e6, 0x3131},
+	{0x00e7, 0x3131},
+	{0x00e8, 0x3131},
+	{0x00ea, 0xb320},
+	{0x00eb, 0x0000},
+	{0x00f0, 0x0000},
+	{0x00f1, 0x00d0},
+	{0x00f2, 0x00d0},
+	{0x00f6, 0x0000},
+	{0x00fa, 0x0000},
+	{0x00fb, 0x0000},
+	{0x00fc, 0x0000},
+	{0x00fd, 0x0000},
+	{0x00fe, 0x10ec},
+	{0x00ff, 0x6530},
+	{0x0100, 0xa0a0},
+	{0x010b, 0x0000},
+	{0x010c, 0xae00},
+	{0x010d, 0xaaa0},
+	{0x010e, 0x8aa2},
+	{0x010f, 0x02a2},
+	{0x0110, 0xc000},
+	{0x0111, 0x04a2},
+	{0x0112, 0x2800},
+	{0x0113, 0x0000},
+	{0x0117, 0x0100},
+	{0x0125, 0x0410},
+	{0x0132, 0x6026},
+	{0x0136, 0x5555},
+	{0x0138, 0x3700},
+	{0x013a, 0x2000},
+	{0x013b, 0x2000},
+	{0x013c, 0x2005},
+	{0x013f, 0x0000},
+	{0x0142, 0x0000},
+	{0x0145, 0x0002},
+	{0x0146, 0x0000},
+	{0x0147, 0x0000},
+	{0x0148, 0x0000},
+	{0x0149, 0x0000},
+	{0x0150, 0x79a1},
+	{0x0151, 0x0000},
+	{0x0160, 0x4ec0},
+	{0x0161, 0x0080},
+	{0x0162, 0x0200},
+	{0x0163, 0x0800},
+	{0x0164, 0x0000},
+	{0x0165, 0x0000},
+	{0x0166, 0x0000},
+	{0x0167, 0x000f},
+	{0x0168, 0x000f},
+	{0x0169, 0x0021},
+	{0x0190, 0x413d},
+	{0x0194, 0x0000},
+	{0x0195, 0x0000},
+	{0x0197, 0x0022},
+	{0x0198, 0x0000},
+	{0x0199, 0x0000},
+	{0x01af, 0x0000},
+	{0x01b0, 0x0400},
+	{0x01b1, 0x0000},
+	{0x01b2, 0x0000},
+	{0x01b3, 0x0000},
+	{0x01b4, 0x0000},
+	{0x01b5, 0x0000},
+	{0x01b6, 0x01c3},
+	{0x01b7, 0x02a0},
+	{0x01b8, 0x03e9},
+	{0x01b9, 0x1389},
+	{0x01ba, 0xc351},
+	{0x01bb, 0x0009},
+	{0x01bc, 0x0018},
+	{0x01bd, 0x002a},
+	{0x01be, 0x004c},
+	{0x01bf, 0x0097},
+	{0x01c0, 0x433d},
+	{0x01c2, 0x0000},
+	{0x01c3, 0x0000},
+	{0x01c4, 0x0000},
+	{0x01c5, 0x0000},
+	{0x01c6, 0x0000},
+	{0x01c7, 0x0000},
+	{0x01c8, 0x40af},
+	{0x01c9, 0x0702},
+	{0x01ca, 0x0000},
+	{0x01cb, 0x0000},
+	{0x01cc, 0x5757},
+	{0x01cd, 0x5757},
+	{0x01ce, 0x5757},
+	{0x01cf, 0x5757},
+	{0x01d0, 0x5757},
+	{0x01d1, 0x5757},
+	{0x01d2, 0x5757},
+	{0x01d3, 0x5757},
+	{0x01d4, 0x5757},
+	{0x01d5, 0x5757},
+	{0x01d6, 0x0000},
+	{0x01d7, 0x0008},
+	{0x01d8, 0x0029},
+	{0x01d9, 0x3333},
+	{0x01da, 0x0000},
+	{0x01db, 0x0004},
+	{0x01dc, 0x0000},
+	{0x01de, 0x7c00},
+	{0x01df, 0x0320},
+	{0x01e0, 0x06a1},
+	{0x01e1, 0x0000},
+	{0x01e2, 0x0000},
+	{0x01e3, 0x0000},
+	{0x01e4, 0x0000},
+	{0x01e6, 0x0001},
+	{0x01e7, 0x0000},
+	{0x01e8, 0x0000},
+	{0x01ea, 0x0000},
+	{0x01eb, 0x0000},
+	{0x01ec, 0x0000},
+	{0x01ed, 0x0000},
+	{0x01ee, 0x0000},
+	{0x01ef, 0x0000},
+	{0x01f0, 0x0000},
+	{0x01f1, 0x0000},
+	{0x01f2, 0x0000},
+	{0x01f3, 0x0000},
+	{0x01f4, 0x0000},
+	{0x0210, 0x6297},
+	{0x0211, 0xa005},
+	{0x0212, 0x824c},
+	{0x0213, 0xf7ff},
+	{0x0214, 0xf24c},
+	{0x0215, 0x0102},
+	{0x0216, 0x00a3},
+	{0x0217, 0x0048},
+	{0x0218, 0xa2c0},
+	{0x0219, 0x0400},
+	{0x021a, 0x00c8},
+	{0x021b, 0x00c0},
+	{0x021c, 0x0000},
+	{0x0250, 0x4500},
+	{0x0251, 0x40b3},
+	{0x0252, 0x0000},
+	{0x0253, 0x0000},
+	{0x0254, 0x0000},
+	{0x0255, 0x0000},
+	{0x0256, 0x0000},
+	{0x0257, 0x0000},
+	{0x0258, 0x0000},
+	{0x0259, 0x0000},
+	{0x025a, 0x0005},
+	{0x0270, 0x0000},
+	{0x02ff, 0x0110},
+	{0x0300, 0x001f},
+	{0x0301, 0x032c},
+	{0x0302, 0x5f21},
+	{0x0303, 0x4000},
+	{0x0304, 0x4000},
+	{0x0305, 0x06d5},
+	{0x0306, 0x8000},
+	{0x0307, 0x0700},
+	{0x0310, 0x4560},
+	{0x0311, 0xa4a8},
+	{0x0312, 0x7418},
+	{0x0313, 0x0000},
+	{0x0314, 0x0006},
+	{0x0315, 0xffff},
+	{0x0316, 0xc400},
+	{0x0317, 0x0000},
+	{0x03c0, 0x7e00},
+	{0x03c1, 0x8000},
+	{0x03c2, 0x8000},
+	{0x03c3, 0x8000},
+	{0x03c4, 0x8000},
+	{0x03c5, 0x8000},
+	{0x03c6, 0x8000},
+	{0x03c7, 0x8000},
+	{0x03c8, 0x8000},
+	{0x03c9, 0x8000},
+	{0x03ca, 0x8000},
+	{0x03cb, 0x8000},
+	{0x03cc, 0x8000},
+	{0x03d0, 0x0000},
+	{0x03d1, 0x0000},
+	{0x03d2, 0x0000},
+	{0x03d3, 0x0000},
+	{0x03d4, 0x2000},
+	{0x03d5, 0x2000},
+	{0x03d6, 0x0000},
+	{0x03d7, 0x0000},
+	{0x03d8, 0x2000},
+	{0x03d9, 0x2000},
+	{0x03da, 0x2000},
+	{0x03db, 0x2000},
+	{0x03dc, 0x0000},
+	{0x03dd, 0x0000},
+	{0x03de, 0x0000},
+	{0x03df, 0x2000},
+	{0x03e0, 0x0000},
+	{0x03e1, 0x0000},
+	{0x03e2, 0x0000},
+	{0x03e3, 0x0000},
+	{0x03e4, 0x0000},
+	{0x03e5, 0x0000},
+	{0x03e6, 0x0000},
+	{0x03e7, 0x0000},
+	{0x03e8, 0x0000},
+	{0x03e9, 0x0000},
+	{0x03ea, 0x0000},
+	{0x03eb, 0x0000},
+	{0x03ec, 0x0000},
+	{0x03ed, 0x0000},
+	{0x03ee, 0x0000},
+	{0x03ef, 0x0000},
+	{0x03f0, 0x0800},
+	{0x03f1, 0x0800},
+	{0x03f2, 0x0800},
+	{0x03f3, 0x0800},
+};
+
+static bool rt5682_volatile_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case RT5682_RESET:
+	case RT5682_CBJ_CTRL_2:
+	case RT5682_INT_ST_1:
+	case RT5682_4BTN_IL_CMD_1:
+	case RT5682_AJD1_CTRL:
+	case RT5682_HP_CALIB_CTRL_1:
+	case RT5682_DEVICE_ID:
+	case RT5682_I2C_MODE:
+	case RT5682_HP_CALIB_CTRL_10:
+	case RT5682_EFUSE_CTRL_2:
+	case RT5682_JD_TOP_VC_VTRL:
+	case RT5682_HP_IMP_SENS_CTRL_19:
+	case RT5682_IL_CMD_1:
+	case RT5682_SAR_IL_CMD_2:
+	case RT5682_SAR_IL_CMD_4:
+	case RT5682_SAR_IL_CMD_10:
+	case RT5682_SAR_IL_CMD_11:
+	case RT5682_EFUSE_CTRL_6...RT5682_EFUSE_CTRL_11:
+	case RT5682_HP_CALIB_STA_1...RT5682_HP_CALIB_STA_11:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool rt5682_readable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case RT5682_RESET:
+	case RT5682_VERSION_ID:
+	case RT5682_VENDOR_ID:
+	case RT5682_DEVICE_ID:
+	case RT5682_HP_CTRL_1:
+	case RT5682_HP_CTRL_2:
+	case RT5682_HPL_GAIN:
+	case RT5682_HPR_GAIN:
+	case RT5682_I2C_CTRL:
+	case RT5682_CBJ_BST_CTRL:
+	case RT5682_CBJ_CTRL_1:
+	case RT5682_CBJ_CTRL_2:
+	case RT5682_CBJ_CTRL_3:
+	case RT5682_CBJ_CTRL_4:
+	case RT5682_CBJ_CTRL_5:
+	case RT5682_CBJ_CTRL_6:
+	case RT5682_CBJ_CTRL_7:
+	case RT5682_DAC1_DIG_VOL:
+	case RT5682_STO1_ADC_DIG_VOL:
+	case RT5682_STO1_ADC_BOOST:
+	case RT5682_HP_IMP_GAIN_1:
+	case RT5682_HP_IMP_GAIN_2:
+	case RT5682_SIDETONE_CTRL:
+	case RT5682_STO1_ADC_MIXER:
+	case RT5682_AD_DA_MIXER:
+	case RT5682_STO1_DAC_MIXER:
+	case RT5682_A_DAC1_MUX:
+	case RT5682_DIG_INF2_DATA:
+	case RT5682_REC_MIXER:
+	case RT5682_CAL_REC:
+	case RT5682_ALC_BACK_GAIN:
+	case RT5682_PWR_DIG_1:
+	case RT5682_PWR_DIG_2:
+	case RT5682_PWR_ANLG_1:
+	case RT5682_PWR_ANLG_2:
+	case RT5682_PWR_ANLG_3:
+	case RT5682_PWR_MIXER:
+	case RT5682_PWR_VOL:
+	case RT5682_CLK_DET:
+	case RT5682_RESET_LPF_CTRL:
+	case RT5682_RESET_HPF_CTRL:
+	case RT5682_DMIC_CTRL_1:
+	case RT5682_I2S1_SDP:
+	case RT5682_I2S2_SDP:
+	case RT5682_ADDA_CLK_1:
+	case RT5682_ADDA_CLK_2:
+	case RT5682_I2S1_F_DIV_CTRL_1:
+	case RT5682_I2S1_F_DIV_CTRL_2:
+	case RT5682_TDM_CTRL:
+	case RT5682_TDM_ADDA_CTRL_1:
+	case RT5682_TDM_ADDA_CTRL_2:
+	case RT5682_DATA_SEL_CTRL_1:
+	case RT5682_TDM_TCON_CTRL:
+	case RT5682_GLB_CLK:
+	case RT5682_PLL_CTRL_1:
+	case RT5682_PLL_CTRL_2:
+	case RT5682_PLL_TRACK_1:
+	case RT5682_PLL_TRACK_2:
+	case RT5682_PLL_TRACK_3:
+	case RT5682_PLL_TRACK_4:
+	case RT5682_PLL_TRACK_5:
+	case RT5682_PLL_TRACK_6:
+	case RT5682_PLL_TRACK_11:
+	case RT5682_SDW_REF_CLK:
+	case RT5682_DEPOP_1:
+	case RT5682_DEPOP_2:
+	case RT5682_HP_CHARGE_PUMP_1:
+	case RT5682_HP_CHARGE_PUMP_2:
+	case RT5682_MICBIAS_1:
+	case RT5682_MICBIAS_2:
+	case RT5682_PLL_TRACK_12:
+	case RT5682_PLL_TRACK_14:
+	case RT5682_PLL2_CTRL_1:
+	case RT5682_PLL2_CTRL_2:
+	case RT5682_PLL2_CTRL_3:
+	case RT5682_PLL2_CTRL_4:
+	case RT5682_RC_CLK_CTRL:
+	case RT5682_I2S_M_CLK_CTRL_1:
+	case RT5682_I2S2_F_DIV_CTRL_1:
+	case RT5682_I2S2_F_DIV_CTRL_2:
+	case RT5682_EQ_CTRL_1:
+	case RT5682_EQ_CTRL_2:
+	case RT5682_IRQ_CTRL_1:
+	case RT5682_IRQ_CTRL_2:
+	case RT5682_IRQ_CTRL_3:
+	case RT5682_IRQ_CTRL_4:
+	case RT5682_INT_ST_1:
+	case RT5682_GPIO_CTRL_1:
+	case RT5682_GPIO_CTRL_2:
+	case RT5682_GPIO_CTRL_3:
+	case RT5682_HP_AMP_DET_CTRL_1:
+	case RT5682_HP_AMP_DET_CTRL_2:
+	case RT5682_MID_HP_AMP_DET:
+	case RT5682_LOW_HP_AMP_DET:
+	case RT5682_DELAY_BUF_CTRL:
+	case RT5682_SV_ZCD_1:
+	case RT5682_SV_ZCD_2:
+	case RT5682_IL_CMD_1:
+	case RT5682_IL_CMD_2:
+	case RT5682_IL_CMD_3:
+	case RT5682_IL_CMD_4:
+	case RT5682_IL_CMD_5:
+	case RT5682_IL_CMD_6:
+	case RT5682_4BTN_IL_CMD_1:
+	case RT5682_4BTN_IL_CMD_2:
+	case RT5682_4BTN_IL_CMD_3:
+	case RT5682_4BTN_IL_CMD_4:
+	case RT5682_4BTN_IL_CMD_5:
+	case RT5682_4BTN_IL_CMD_6:
+	case RT5682_4BTN_IL_CMD_7:
+	case RT5682_ADC_STO1_HP_CTRL_1:
+	case RT5682_ADC_STO1_HP_CTRL_2:
+	case RT5682_AJD1_CTRL:
+	case RT5682_JD1_THD:
+	case RT5682_JD2_THD:
+	case RT5682_JD_CTRL_1:
+	case RT5682_DUMMY_1:
+	case RT5682_DUMMY_2:
+	case RT5682_DUMMY_3:
+	case RT5682_DAC_ADC_DIG_VOL1:
+	case RT5682_BIAS_CUR_CTRL_2:
+	case RT5682_BIAS_CUR_CTRL_3:
+	case RT5682_BIAS_CUR_CTRL_4:
+	case RT5682_BIAS_CUR_CTRL_5:
+	case RT5682_BIAS_CUR_CTRL_6:
+	case RT5682_BIAS_CUR_CTRL_7:
+	case RT5682_BIAS_CUR_CTRL_8:
+	case RT5682_BIAS_CUR_CTRL_9:
+	case RT5682_BIAS_CUR_CTRL_10:
+	case RT5682_VREF_REC_OP_FB_CAP_CTRL:
+	case RT5682_CHARGE_PUMP_1:
+	case RT5682_DIG_IN_CTRL_1:
+	case RT5682_PAD_DRIVING_CTRL:
+	case RT5682_SOFT_RAMP_DEPOP:
+	case RT5682_CHOP_DAC:
+	case RT5682_CHOP_ADC:
+	case RT5682_CALIB_ADC_CTRL:
+	case RT5682_VOL_TEST:
+	case RT5682_SPKVDD_DET_STA:
+	case RT5682_TEST_MODE_CTRL_1:
+	case RT5682_TEST_MODE_CTRL_2:
+	case RT5682_TEST_MODE_CTRL_3:
+	case RT5682_TEST_MODE_CTRL_4:
+	case RT5682_TEST_MODE_CTRL_5:
+	case RT5682_PLL1_INTERNAL:
+	case RT5682_PLL2_INTERNAL:
+	case RT5682_STO_NG2_CTRL_1:
+	case RT5682_STO_NG2_CTRL_2:
+	case RT5682_STO_NG2_CTRL_3:
+	case RT5682_STO_NG2_CTRL_4:
+	case RT5682_STO_NG2_CTRL_5:
+	case RT5682_STO_NG2_CTRL_6:
+	case RT5682_STO_NG2_CTRL_7:
+	case RT5682_STO_NG2_CTRL_8:
+	case RT5682_STO_NG2_CTRL_9:
+	case RT5682_STO_NG2_CTRL_10:
+	case RT5682_STO1_DAC_SIL_DET:
+	case RT5682_SIL_PSV_CTRL1:
+	case RT5682_SIL_PSV_CTRL2:
+	case RT5682_SIL_PSV_CTRL3:
+	case RT5682_SIL_PSV_CTRL4:
+	case RT5682_SIL_PSV_CTRL5:
+	case RT5682_HP_IMP_SENS_CTRL_01:
+	case RT5682_HP_IMP_SENS_CTRL_02:
+	case RT5682_HP_IMP_SENS_CTRL_03:
+	case RT5682_HP_IMP_SENS_CTRL_04:
+	case RT5682_HP_IMP_SENS_CTRL_05:
+	case RT5682_HP_IMP_SENS_CTRL_06:
+	case RT5682_HP_IMP_SENS_CTRL_07:
+	case RT5682_HP_IMP_SENS_CTRL_08:
+	case RT5682_HP_IMP_SENS_CTRL_09:
+	case RT5682_HP_IMP_SENS_CTRL_10:
+	case RT5682_HP_IMP_SENS_CTRL_11:
+	case RT5682_HP_IMP_SENS_CTRL_12:
+	case RT5682_HP_IMP_SENS_CTRL_13:
+	case RT5682_HP_IMP_SENS_CTRL_14:
+	case RT5682_HP_IMP_SENS_CTRL_15:
+	case RT5682_HP_IMP_SENS_CTRL_16:
+	case RT5682_HP_IMP_SENS_CTRL_17:
+	case RT5682_HP_IMP_SENS_CTRL_18:
+	case RT5682_HP_IMP_SENS_CTRL_19:
+	case RT5682_HP_IMP_SENS_CTRL_20:
+	case RT5682_HP_IMP_SENS_CTRL_21:
+	case RT5682_HP_IMP_SENS_CTRL_22:
+	case RT5682_HP_IMP_SENS_CTRL_23:
+	case RT5682_HP_IMP_SENS_CTRL_24:
+	case RT5682_HP_IMP_SENS_CTRL_25:
+	case RT5682_HP_IMP_SENS_CTRL_26:
+	case RT5682_HP_IMP_SENS_CTRL_27:
+	case RT5682_HP_IMP_SENS_CTRL_28:
+	case RT5682_HP_IMP_SENS_CTRL_29:
+	case RT5682_HP_IMP_SENS_CTRL_30:
+	case RT5682_HP_IMP_SENS_CTRL_31:
+	case RT5682_HP_IMP_SENS_CTRL_32:
+	case RT5682_HP_IMP_SENS_CTRL_33:
+	case RT5682_HP_IMP_SENS_CTRL_34:
+	case RT5682_HP_IMP_SENS_CTRL_35:
+	case RT5682_HP_IMP_SENS_CTRL_36:
+	case RT5682_HP_IMP_SENS_CTRL_37:
+	case RT5682_HP_IMP_SENS_CTRL_38:
+	case RT5682_HP_IMP_SENS_CTRL_39:
+	case RT5682_HP_IMP_SENS_CTRL_40:
+	case RT5682_HP_IMP_SENS_CTRL_41:
+	case RT5682_HP_IMP_SENS_CTRL_42:
+	case RT5682_HP_IMP_SENS_CTRL_43:
+	case RT5682_HP_LOGIC_CTRL_1:
+	case RT5682_HP_LOGIC_CTRL_2:
+	case RT5682_HP_LOGIC_CTRL_3:
+	case RT5682_HP_CALIB_CTRL_1:
+	case RT5682_HP_CALIB_CTRL_2:
+	case RT5682_HP_CALIB_CTRL_3:
+	case RT5682_HP_CALIB_CTRL_4:
+	case RT5682_HP_CALIB_CTRL_5:
+	case RT5682_HP_CALIB_CTRL_6:
+	case RT5682_HP_CALIB_CTRL_7:
+	case RT5682_HP_CALIB_CTRL_9:
+	case RT5682_HP_CALIB_CTRL_10:
+	case RT5682_HP_CALIB_CTRL_11:
+	case RT5682_HP_CALIB_STA_1:
+	case RT5682_HP_CALIB_STA_2:
+	case RT5682_HP_CALIB_STA_3:
+	case RT5682_HP_CALIB_STA_4:
+	case RT5682_HP_CALIB_STA_5:
+	case RT5682_HP_CALIB_STA_6:
+	case RT5682_HP_CALIB_STA_7:
+	case RT5682_HP_CALIB_STA_8:
+	case RT5682_HP_CALIB_STA_9:
+	case RT5682_HP_CALIB_STA_10:
+	case RT5682_HP_CALIB_STA_11:
+	case RT5682_SAR_IL_CMD_1:
+	case RT5682_SAR_IL_CMD_2:
+	case RT5682_SAR_IL_CMD_3:
+	case RT5682_SAR_IL_CMD_4:
+	case RT5682_SAR_IL_CMD_5:
+	case RT5682_SAR_IL_CMD_6:
+	case RT5682_SAR_IL_CMD_7:
+	case RT5682_SAR_IL_CMD_8:
+	case RT5682_SAR_IL_CMD_9:
+	case RT5682_SAR_IL_CMD_10:
+	case RT5682_SAR_IL_CMD_11:
+	case RT5682_SAR_IL_CMD_12:
+	case RT5682_SAR_IL_CMD_13:
+	case RT5682_EFUSE_CTRL_1:
+	case RT5682_EFUSE_CTRL_2:
+	case RT5682_EFUSE_CTRL_3:
+	case RT5682_EFUSE_CTRL_4:
+	case RT5682_EFUSE_CTRL_5:
+	case RT5682_EFUSE_CTRL_6:
+	case RT5682_EFUSE_CTRL_7:
+	case RT5682_EFUSE_CTRL_8:
+	case RT5682_EFUSE_CTRL_9:
+	case RT5682_EFUSE_CTRL_10:
+	case RT5682_EFUSE_CTRL_11:
+	case RT5682_JD_TOP_VC_VTRL:
+	case RT5682_DRC1_CTRL_0:
+	case RT5682_DRC1_CTRL_1:
+	case RT5682_DRC1_CTRL_2:
+	case RT5682_DRC1_CTRL_3:
+	case RT5682_DRC1_CTRL_4:
+	case RT5682_DRC1_CTRL_5:
+	case RT5682_DRC1_CTRL_6:
+	case RT5682_DRC1_HARD_LMT_CTRL_1:
+	case RT5682_DRC1_HARD_LMT_CTRL_2:
+	case RT5682_DRC1_PRIV_1:
+	case RT5682_DRC1_PRIV_2:
+	case RT5682_DRC1_PRIV_3:
+	case RT5682_DRC1_PRIV_4:
+	case RT5682_DRC1_PRIV_5:
+	case RT5682_DRC1_PRIV_6:
+	case RT5682_DRC1_PRIV_7:
+	case RT5682_DRC1_PRIV_8:
+	case RT5682_EQ_AUTO_RCV_CTRL1:
+	case RT5682_EQ_AUTO_RCV_CTRL2:
+	case RT5682_EQ_AUTO_RCV_CTRL3:
+	case RT5682_EQ_AUTO_RCV_CTRL4:
+	case RT5682_EQ_AUTO_RCV_CTRL5:
+	case RT5682_EQ_AUTO_RCV_CTRL6:
+	case RT5682_EQ_AUTO_RCV_CTRL7:
+	case RT5682_EQ_AUTO_RCV_CTRL8:
+	case RT5682_EQ_AUTO_RCV_CTRL9:
+	case RT5682_EQ_AUTO_RCV_CTRL10:
+	case RT5682_EQ_AUTO_RCV_CTRL11:
+	case RT5682_EQ_AUTO_RCV_CTRL12:
+	case RT5682_EQ_AUTO_RCV_CTRL13:
+	case RT5682_ADC_L_EQ_LPF1_A1:
+	case RT5682_R_EQ_LPF1_A1:
+	case RT5682_L_EQ_LPF1_H0:
+	case RT5682_R_EQ_LPF1_H0:
+	case RT5682_L_EQ_BPF1_A1:
+	case RT5682_R_EQ_BPF1_A1:
+	case RT5682_L_EQ_BPF1_A2:
+	case RT5682_R_EQ_BPF1_A2:
+	case RT5682_L_EQ_BPF1_H0:
+	case RT5682_R_EQ_BPF1_H0:
+	case RT5682_L_EQ_BPF2_A1:
+	case RT5682_R_EQ_BPF2_A1:
+	case RT5682_L_EQ_BPF2_A2:
+	case RT5682_R_EQ_BPF2_A2:
+	case RT5682_L_EQ_BPF2_H0:
+	case RT5682_R_EQ_BPF2_H0:
+	case RT5682_L_EQ_BPF3_A1:
+	case RT5682_R_EQ_BPF3_A1:
+	case RT5682_L_EQ_BPF3_A2:
+	case RT5682_R_EQ_BPF3_A2:
+	case RT5682_L_EQ_BPF3_H0:
+	case RT5682_R_EQ_BPF3_H0:
+	case RT5682_L_EQ_BPF4_A1:
+	case RT5682_R_EQ_BPF4_A1:
+	case RT5682_L_EQ_BPF4_A2:
+	case RT5682_R_EQ_BPF4_A2:
+	case RT5682_L_EQ_BPF4_H0:
+	case RT5682_R_EQ_BPF4_H0:
+	case RT5682_L_EQ_HPF1_A1:
+	case RT5682_R_EQ_HPF1_A1:
+	case RT5682_L_EQ_HPF1_H0:
+	case RT5682_R_EQ_HPF1_H0:
+	case RT5682_L_EQ_PRE_VOL:
+	case RT5682_R_EQ_PRE_VOL:
+	case RT5682_L_EQ_POST_VOL:
+	case RT5682_R_EQ_POST_VOL:
+	case RT5682_I2C_MODE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const DECLARE_TLV_DB_SCALE(hp_vol_tlv, -2250, 150, 0);
+static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0);
+static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
+static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0);
+
+/* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */
+static const DECLARE_TLV_DB_RANGE(bst_tlv,
+	0, 0, TLV_DB_SCALE_ITEM(0, 0, 0),
+	1, 1, TLV_DB_SCALE_ITEM(2000, 0, 0),
+	2, 2, TLV_DB_SCALE_ITEM(2400, 0, 0),
+	3, 5, TLV_DB_SCALE_ITEM(3000, 500, 0),
+	6, 6, TLV_DB_SCALE_ITEM(4400, 0, 0),
+	7, 7, TLV_DB_SCALE_ITEM(5000, 0, 0),
+	8, 8, TLV_DB_SCALE_ITEM(5200, 0, 0)
+);
+
+/* Interface data select */
+static const char * const rt5682_data_select[] = {
+	"L/R", "R/L", "L/L", "R/R"
+};
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if2_adc_enum,
+	RT5682_DIG_INF2_DATA, RT5682_IF2_ADC_SEL_SFT, rt5682_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if1_01_adc_enum,
+	RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC1_SEL_SFT, rt5682_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if1_23_adc_enum,
+	RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC2_SEL_SFT, rt5682_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if1_45_adc_enum,
+	RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC3_SEL_SFT, rt5682_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if1_67_adc_enum,
+	RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC4_SEL_SFT, rt5682_data_select);
+
+static const struct snd_kcontrol_new rt5682_if2_adc_swap_mux =
+	SOC_DAPM_ENUM("IF2 ADC Swap Mux", rt5682_if2_adc_enum);
+
+static const struct snd_kcontrol_new rt5682_if1_01_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 01 ADC Swap Mux", rt5682_if1_01_adc_enum);
+
+static const struct snd_kcontrol_new rt5682_if1_23_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 23 ADC Swap Mux", rt5682_if1_23_adc_enum);
+
+static const struct snd_kcontrol_new rt5682_if1_45_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 45 ADC Swap Mux", rt5682_if1_45_adc_enum);
+
+static const struct snd_kcontrol_new rt5682_if1_67_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 67 ADC Swap Mux", rt5682_if1_67_adc_enum);
+
+static void rt5682_reset(struct regmap *regmap)
+{
+	regmap_write(regmap, RT5682_RESET, 0);
+	regmap_write(regmap, RT5682_I2C_MODE, 1);
+}
+/**
+ * rt5682_sel_asrc_clk_src - select ASRC clock source for a set of filters
+ * @component: SoC audio component device.
+ * @filter_mask: mask of filters.
+ * @clk_src: clock source
+ *
+ * The ASRC function is for asynchronous MCLK and LRCK. Also, since RT5682 can
+ * only support standard 32fs or 64fs i2s format, ASRC should be enabled to
+ * support special i2s clock format such as Intel's 100fs(100 * sampling rate).
+ * ASRC function will track i2s clock and generate a corresponding system clock
+ * for codec. This function provides an API to select the clock source for a
+ * set of filters specified by the mask. And the component driver will turn on
+ * ASRC for these filters if ASRC is selected as their clock source.
+ */
+int rt5682_sel_asrc_clk_src(struct snd_soc_component *component,
+		unsigned int filter_mask, unsigned int clk_src)
+{
+
+	switch (clk_src) {
+	case RT5682_CLK_SEL_SYS:
+	case RT5682_CLK_SEL_I2S1_ASRC:
+	case RT5682_CLK_SEL_I2S2_ASRC:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (filter_mask & RT5682_DA_STEREO1_FILTER) {
+		snd_soc_component_update_bits(component, RT5682_PLL_TRACK_2,
+			RT5682_FILTER_CLK_SEL_MASK,
+			clk_src << RT5682_FILTER_CLK_SEL_SFT);
+	}
+
+	if (filter_mask & RT5682_AD_STEREO1_FILTER) {
+		snd_soc_component_update_bits(component, RT5682_PLL_TRACK_3,
+			RT5682_FILTER_CLK_SEL_MASK,
+			clk_src << RT5682_FILTER_CLK_SEL_SFT);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rt5682_sel_asrc_clk_src);
+
+static int rt5682_button_detect(struct snd_soc_component *component)
+{
+	int btn_type, val;
+
+	val = snd_soc_component_read32(component, RT5682_4BTN_IL_CMD_1);
+	btn_type = val & 0xfff0;
+	snd_soc_component_write(component, RT5682_4BTN_IL_CMD_1, val);
+	pr_debug("%s btn_type=%x\n", __func__, btn_type);
+	snd_soc_component_update_bits(component,
+		RT5682_SAR_IL_CMD_2, 0x10, 0x10);
+
+	return btn_type;
+}
+
+static void rt5682_enable_push_button_irq(struct snd_soc_component *component,
+		bool enable)
+{
+	if (enable) {
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
+			RT5682_SAR_BUTT_DET_MASK, RT5682_SAR_BUTT_DET_EN);
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_13,
+			RT5682_SAR_SOUR_MASK, RT5682_SAR_SOUR_BTN);
+		snd_soc_component_write(component, RT5682_IL_CMD_1, 0x0040);
+		snd_soc_component_update_bits(component, RT5682_4BTN_IL_CMD_2,
+			RT5682_4BTN_IL_MASK | RT5682_4BTN_IL_RST_MASK,
+			RT5682_4BTN_IL_EN | RT5682_4BTN_IL_NOR);
+		snd_soc_component_update_bits(component, RT5682_IRQ_CTRL_3,
+			RT5682_IL_IRQ_MASK, RT5682_IL_IRQ_EN);
+	} else {
+		snd_soc_component_update_bits(component, RT5682_IRQ_CTRL_3,
+			RT5682_IL_IRQ_MASK, RT5682_IL_IRQ_DIS);
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
+			RT5682_SAR_BUTT_DET_MASK, RT5682_SAR_BUTT_DET_DIS);
+		snd_soc_component_update_bits(component, RT5682_4BTN_IL_CMD_2,
+			RT5682_4BTN_IL_MASK, RT5682_4BTN_IL_DIS);
+		snd_soc_component_update_bits(component, RT5682_4BTN_IL_CMD_2,
+			RT5682_4BTN_IL_RST_MASK, RT5682_4BTN_IL_RST);
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_13,
+			RT5682_SAR_SOUR_MASK, RT5682_SAR_SOUR_TYPE);
+	}
+}
+
+/**
+ * rt5682_headset_detect - Detect headset.
+ * @component: SoC audio component device.
+ * @jack_insert: Jack insert or not.
+ *
+ * Detect whether is headset or not when jack inserted.
+ *
+ * Returns detect status.
+ */
+static int rt5682_headset_detect(struct snd_soc_component *component,
+		int jack_insert)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	struct snd_soc_dapm_context *dapm =
+		snd_soc_component_get_dapm(component);
+	unsigned int val, count;
+
+	if (jack_insert) {
+		snd_soc_dapm_force_enable_pin(dapm, "CBJ Power");
+		snd_soc_dapm_sync(dapm);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
+			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH);
+
+		count = 0;
+		val = snd_soc_component_read32(component, RT5682_CBJ_CTRL_2)
+			& RT5682_JACK_TYPE_MASK;
+		while (val == 0 && count < 50) {
+			usleep_range(10000, 15000);
+			val = snd_soc_component_read32(component,
+				RT5682_CBJ_CTRL_2) & RT5682_JACK_TYPE_MASK;
+			count++;
+		}
+
+		switch (val) {
+		case 0x1:
+		case 0x2:
+			rt5682->jack_type = SND_JACK_HEADSET;
+			rt5682_enable_push_button_irq(component, true);
+			break;
+		default:
+			rt5682->jack_type = SND_JACK_HEADPHONE;
+		}
+
+	} else {
+		rt5682_enable_push_button_irq(component, false);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
+			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW);
+		snd_soc_dapm_disable_pin(dapm, "CBJ Power");
+		snd_soc_dapm_sync(dapm);
+
+		rt5682->jack_type = 0;
+	}
+
+	dev_dbg(component->dev, "jack_type = %d\n", rt5682->jack_type);
+	return rt5682->jack_type;
+}
+
+static irqreturn_t rt5682_irq(int irq, void *data)
+{
+	struct rt5682_priv *rt5682 = data;
+
+	mod_delayed_work(system_power_efficient_wq,
+			&rt5682->jack_detect_work, msecs_to_jiffies(250));
+
+	return IRQ_HANDLED;
+}
+
+static void rt5682_jd_check_handler(struct work_struct *work)
+{
+	struct rt5682_priv *rt5682 = container_of(work, struct rt5682_priv,
+		jd_check_work.work);
+
+	if (snd_soc_component_read32(rt5682->component, RT5682_AJD1_CTRL)
+		& RT5682_JDH_RS_MASK) {
+		/* jack out */
+		rt5682->jack_type = rt5682_headset_detect(rt5682->component, 0);
+
+		snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type,
+				SND_JACK_HEADSET |
+				SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+				SND_JACK_BTN_2 | SND_JACK_BTN_3);
+	} else {
+		schedule_delayed_work(&rt5682->jd_check_work, 500);
+	}
+}
+
+static int rt5682_set_jack_detect(struct snd_soc_component *component,
+	struct snd_soc_jack *hs_jack, void *data)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	switch (rt5682->pdata.jd_src) {
+	case RT5682_JD1:
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_2,
+			RT5682_EXT_JD_SRC, RT5682_EXT_JD_SRC_MANUAL);
+		snd_soc_component_write(component, RT5682_CBJ_CTRL_1, 0xd042);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_3,
+			RT5682_CBJ_IN_BUF_EN, RT5682_CBJ_IN_BUF_EN);
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
+			RT5682_SAR_POW_MASK, RT5682_SAR_POW_EN);
+		regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+			RT5682_GP1_PIN_MASK, RT5682_GP1_PIN_IRQ);
+		regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL,
+				RT5682_POW_IRQ | RT5682_POW_JDH |
+				RT5682_POW_ANA, RT5682_POW_IRQ |
+				RT5682_POW_JDH | RT5682_POW_ANA);
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_2,
+			RT5682_PWR_JDH | RT5682_PWR_JDL,
+			RT5682_PWR_JDH | RT5682_PWR_JDL);
+		regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2,
+			RT5682_JD1_EN_MASK | RT5682_JD1_POL_MASK,
+			RT5682_JD1_EN | RT5682_JD1_POL_NOR);
+		mod_delayed_work(system_power_efficient_wq,
+			   &rt5682->jack_detect_work, msecs_to_jiffies(250));
+		break;
+
+	case RT5682_JD_NULL:
+		regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2,
+			RT5682_JD1_EN_MASK, RT5682_JD1_DIS);
+		regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL,
+				RT5682_POW_JDH | RT5682_POW_JDL, 0);
+		break;
+
+	default:
+		dev_warn(component->dev, "Wrong JD source\n");
+		break;
+	}
+
+	rt5682->hs_jack = hs_jack;
+
+	return 0;
+}
+
+static void rt5682_jack_detect_handler(struct work_struct *work)
+{
+	struct rt5682_priv *rt5682 =
+		container_of(work, struct rt5682_priv, jack_detect_work.work);
+	int val, btn_type;
+
+	while (!rt5682->component)
+		usleep_range(10000, 15000);
+
+	while (!rt5682->component->card->instantiated)
+		usleep_range(10000, 15000);
+
+	mutex_lock(&rt5682->calibrate_mutex);
+
+	val = snd_soc_component_read32(rt5682->component, RT5682_AJD1_CTRL)
+		& RT5682_JDH_RS_MASK;
+	if (!val) {
+		/* jack in */
+		if (rt5682->jack_type == 0) {
+			/* jack was out, report jack type */
+			rt5682->jack_type =
+				rt5682_headset_detect(rt5682->component, 1);
+		} else {
+			/* jack is already in, report button event */
+			rt5682->jack_type = SND_JACK_HEADSET;
+			btn_type = rt5682_button_detect(rt5682->component);
+			/**
+			 * rt5682 can report three kinds of button behavior,
+			 * one click, double click and hold. However,
+			 * currently we will report button pressed/released
+			 * event. So all the three button behaviors are
+			 * treated as button pressed.
+			 */
+			switch (btn_type) {
+			case 0x8000:
+			case 0x4000:
+			case 0x2000:
+				rt5682->jack_type |= SND_JACK_BTN_0;
+				break;
+			case 0x1000:
+			case 0x0800:
+			case 0x0400:
+				rt5682->jack_type |= SND_JACK_BTN_1;
+				break;
+			case 0x0200:
+			case 0x0100:
+			case 0x0080:
+				rt5682->jack_type |= SND_JACK_BTN_2;
+				break;
+			case 0x0040:
+			case 0x0020:
+			case 0x0010:
+				rt5682->jack_type |= SND_JACK_BTN_3;
+				break;
+			case 0x0000: /* unpressed */
+				break;
+			default:
+				btn_type = 0;
+				dev_err(rt5682->component->dev,
+					"Unexpected button code 0x%04x\n",
+					btn_type);
+				break;
+			}
+		}
+	} else {
+		/* jack out */
+		rt5682->jack_type = rt5682_headset_detect(rt5682->component, 0);
+	}
+
+	snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type,
+			SND_JACK_HEADSET |
+			    SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+			    SND_JACK_BTN_2 | SND_JACK_BTN_3);
+
+	if (rt5682->jack_type & (SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+		SND_JACK_BTN_2 | SND_JACK_BTN_3))
+		schedule_delayed_work(&rt5682->jd_check_work, 0);
+	else
+		cancel_delayed_work_sync(&rt5682->jd_check_work);
+
+	mutex_unlock(&rt5682->calibrate_mutex);
+}
+
+static const struct snd_kcontrol_new rt5682_snd_controls[] = {
+	/* Headphone Output Volume */
+	SOC_DOUBLE_R_TLV("Headphone Playback Volume", RT5682_HPL_GAIN,
+		RT5682_HPR_GAIN, RT5682_G_HP_SFT, 15, 1, hp_vol_tlv),
+
+	/* DAC Digital Volume */
+	SOC_DOUBLE_TLV("DAC1 Playback Volume", RT5682_DAC1_DIG_VOL,
+		RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 175, 0, dac_vol_tlv),
+
+	/* IN Boost Volume */
+	SOC_SINGLE_TLV("CBJ Boost Volume", RT5682_CBJ_BST_CTRL,
+		RT5682_BST_CBJ_SFT, 8, 0, bst_tlv),
+
+	/* ADC Digital Volume Control */
+	SOC_DOUBLE("STO1 ADC Capture Switch", RT5682_STO1_ADC_DIG_VOL,
+		RT5682_L_MUTE_SFT, RT5682_R_MUTE_SFT, 1, 1),
+	SOC_DOUBLE_TLV("STO1 ADC Capture Volume", RT5682_STO1_ADC_DIG_VOL,
+		RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 127, 0, adc_vol_tlv),
+
+	/* ADC Boost Volume Control */
+	SOC_DOUBLE_TLV("STO1 ADC Boost Gain Volume", RT5682_STO1_ADC_BOOST,
+		RT5682_STO1_ADC_L_BST_SFT, RT5682_STO1_ADC_R_BST_SFT,
+		3, 0, adc_bst_tlv),
+};
+
+
+static int rt5682_div_sel(struct rt5682_priv *rt5682,
+			  int target, const int div[], int size)
+{
+	int i;
+
+	if (rt5682->sysclk < target) {
+		pr_err("sysclk rate %d is too low\n",
+			rt5682->sysclk);
+		return 0;
+	}
+
+	for (i = 0; i < size - 1; i++) {
+		pr_info("div[%d]=%d\n", i, div[i]);
+		if (target * div[i] == rt5682->sysclk)
+			return i;
+		if (target * div[i + 1] > rt5682->sysclk) {
+			pr_err("can't find div for sysclk %d\n",
+				rt5682->sysclk);
+			return i;
+		}
+	}
+
+	if (target * div[i] < rt5682->sysclk)
+		pr_err("sysclk rate %d is too high\n",
+			rt5682->sysclk);
+
+	return size - 1;
+
+}
+
+/**
+ * set_dmic_clk - Set parameter of dmic.
+ *
+ * @w: DAPM widget.
+ * @kcontrol: The kcontrol of this widget.
+ * @event: Event id.
+ *
+ * Choose dmic clock between 1MHz and 3MHz.
+ * It is better for clock to approximate 3MHz.
+ */
+static int set_dmic_clk(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	int idx = -EINVAL;
+	static const int div[] = {2, 4, 6, 8, 12, 16, 24, 32, 48, 64, 96, 128};
+
+	idx = rt5682_div_sel(rt5682, 1500000, div, ARRAY_SIZE(div));
+
+	snd_soc_component_update_bits(component, RT5682_DMIC_CTRL_1,
+		RT5682_DMIC_CLK_MASK, idx << RT5682_DMIC_CLK_SFT);
+
+	return 0;
+}
+
+static int set_filter_clk(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	int ref, val, reg, sft, mask, idx = -EINVAL;
+	static const int div_f[] = {1, 2, 3, 4, 6, 8, 12, 16, 24, 32, 48};
+	static const int div_o[] = {1, 2, 4, 6, 8, 12, 16, 24, 32, 48};
+
+	val = snd_soc_component_read32(component, RT5682_GPIO_CTRL_1) &
+		RT5682_GP4_PIN_MASK;
+	if (w->shift == RT5682_PWR_ADC_S1F_BIT &&
+		val == RT5682_GP4_PIN_ADCDAT2)
+		ref = 256 * rt5682->lrck[RT5682_AIF2];
+	else
+		ref = 256 * rt5682->lrck[RT5682_AIF1];
+
+	idx = rt5682_div_sel(rt5682, ref, div_f, ARRAY_SIZE(div_f));
+
+	if (w->shift == RT5682_PWR_ADC_S1F_BIT) {
+		reg = RT5682_PLL_TRACK_3;
+		sft = RT5682_ADC_OSR_SFT;
+		mask = RT5682_ADC_OSR_MASK;
+	} else {
+		reg = RT5682_PLL_TRACK_2;
+		sft = RT5682_DAC_OSR_SFT;
+		mask = RT5682_DAC_OSR_MASK;
+	}
+
+	snd_soc_component_update_bits(component, reg,
+		RT5682_FILTER_CLK_DIV_MASK, idx << RT5682_FILTER_CLK_DIV_SFT);
+
+	/* select over sample rate */
+	for (idx = 0; idx < ARRAY_SIZE(div_o); idx++) {
+		if (rt5682->sysclk <= 12288000 * div_o[idx])
+			break;
+	}
+
+	snd_soc_component_update_bits(component, RT5682_ADDA_CLK_1,
+		mask, idx << sft);
+
+	return 0;
+}
+
+static int is_sys_clk_from_pll1(struct snd_soc_dapm_widget *w,
+			 struct snd_soc_dapm_widget *sink)
+{
+	unsigned int val;
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	val = snd_soc_component_read32(component, RT5682_GLB_CLK);
+	val &= RT5682_SCLK_SRC_MASK;
+	if (val == RT5682_SCLK_SRC_PLL1)
+		return 1;
+	else
+		return 0;
+}
+
+static int is_using_asrc(struct snd_soc_dapm_widget *w,
+			 struct snd_soc_dapm_widget *sink)
+{
+	unsigned int reg, shift, val;
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (w->shift) {
+	case RT5682_ADC_STO1_ASRC_SFT:
+		reg = RT5682_PLL_TRACK_3;
+		shift = RT5682_FILTER_CLK_SEL_SFT;
+		break;
+	case RT5682_DAC_STO1_ASRC_SFT:
+		reg = RT5682_PLL_TRACK_2;
+		shift = RT5682_FILTER_CLK_SEL_SFT;
+		break;
+	default:
+		return 0;
+	}
+
+	val = (snd_soc_component_read32(component, reg) >> shift) & 0xf;
+	switch (val) {
+	case RT5682_CLK_SEL_I2S1_ASRC:
+	case RT5682_CLK_SEL_I2S2_ASRC:
+		return 1;
+	default:
+		return 0;
+	}
+
+}
+
+/* Digital Mixer */
+static const struct snd_kcontrol_new rt5682_sto1_adc_l_mix[] = {
+	SOC_DAPM_SINGLE("ADC1 Switch", RT5682_STO1_ADC_MIXER,
+			RT5682_M_STO1_ADC_L1_SFT, 1, 1),
+	SOC_DAPM_SINGLE("ADC2 Switch", RT5682_STO1_ADC_MIXER,
+			RT5682_M_STO1_ADC_L2_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_sto1_adc_r_mix[] = {
+	SOC_DAPM_SINGLE("ADC1 Switch", RT5682_STO1_ADC_MIXER,
+			RT5682_M_STO1_ADC_R1_SFT, 1, 1),
+	SOC_DAPM_SINGLE("ADC2 Switch", RT5682_STO1_ADC_MIXER,
+			RT5682_M_STO1_ADC_R2_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_dac_l_mix[] = {
+	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5682_AD_DA_MIXER,
+			RT5682_M_ADCMIX_L_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC1 Switch", RT5682_AD_DA_MIXER,
+			RT5682_M_DAC1_L_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_dac_r_mix[] = {
+	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5682_AD_DA_MIXER,
+			RT5682_M_ADCMIX_R_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC1 Switch", RT5682_AD_DA_MIXER,
+			RT5682_M_DAC1_R_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_sto1_dac_l_mix[] = {
+	SOC_DAPM_SINGLE("DAC L1 Switch", RT5682_STO1_DAC_MIXER,
+			RT5682_M_DAC_L1_STO_L_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC R1 Switch", RT5682_STO1_DAC_MIXER,
+			RT5682_M_DAC_R1_STO_L_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_sto1_dac_r_mix[] = {
+	SOC_DAPM_SINGLE("DAC L1 Switch", RT5682_STO1_DAC_MIXER,
+			RT5682_M_DAC_L1_STO_R_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC R1 Switch", RT5682_STO1_DAC_MIXER,
+			RT5682_M_DAC_R1_STO_R_SFT, 1, 1),
+};
+
+/* Analog Input Mixer */
+static const struct snd_kcontrol_new rt5682_rec1_l_mix[] = {
+	SOC_DAPM_SINGLE("CBJ Switch", RT5682_REC_MIXER,
+			RT5682_M_CBJ_RM1_L_SFT, 1, 1),
+};
+
+/* STO1 ADC1 Source */
+/* MX-26 [13] [5] */
+static const char * const rt5682_sto1_adc1_src[] = {
+	"DAC MIX", "ADC"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adc1l_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADC1L_SRC_SFT, rt5682_sto1_adc1_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adc1l_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC1L Source", rt5682_sto1_adc1l_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adc1r_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADC1R_SRC_SFT, rt5682_sto1_adc1_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adc1r_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC1L Source", rt5682_sto1_adc1r_enum);
+
+/* STO1 ADC Source */
+/* MX-26 [11:10] [3:2] */
+static const char * const rt5682_sto1_adc_src[] = {
+	"ADC1 L", "ADC1 R"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adcl_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADCL_SRC_SFT, rt5682_sto1_adc_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adcl_mux =
+	SOC_DAPM_ENUM("Stereo1 ADCL Source", rt5682_sto1_adcl_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adcr_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADCR_SRC_SFT, rt5682_sto1_adc_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adcr_mux =
+	SOC_DAPM_ENUM("Stereo1 ADCR Source", rt5682_sto1_adcr_enum);
+
+/* STO1 ADC2 Source */
+/* MX-26 [12] [4] */
+static const char * const rt5682_sto1_adc2_src[] = {
+	"DAC MIX", "DMIC"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adc2l_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADC2L_SRC_SFT, rt5682_sto1_adc2_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adc2l_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC2L Source", rt5682_sto1_adc2l_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adc2r_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADC2R_SRC_SFT, rt5682_sto1_adc2_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adc2r_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC2R Source", rt5682_sto1_adc2r_enum);
+
+/* MX-79 [6:4] I2S1 ADC data location */
+static const unsigned int rt5682_if1_adc_slot_values[] = {
+	0,
+	2,
+	4,
+	6,
+};
+
+static const char * const rt5682_if1_adc_slot_src[] = {
+	"Slot 0", "Slot 2", "Slot 4", "Slot 6"
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(rt5682_if1_adc_slot_enum,
+	RT5682_TDM_CTRL, RT5682_TDM_ADC_LCA_SFT, RT5682_TDM_ADC_LCA_MASK,
+	rt5682_if1_adc_slot_src, rt5682_if1_adc_slot_values);
+
+static const struct snd_kcontrol_new rt5682_if1_adc_slot_mux =
+	SOC_DAPM_ENUM("IF1 ADC Slot location", rt5682_if1_adc_slot_enum);
+
+/* Analog DAC L1 Source, Analog DAC R1 Source*/
+/* MX-2B [4], MX-2B [0]*/
+static const char * const rt5682_alg_dac1_src[] = {
+	"Stereo1 DAC Mixer", "DAC1"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_alg_dac_l1_enum, RT5682_A_DAC1_MUX,
+	RT5682_A_DACL1_SFT, rt5682_alg_dac1_src);
+
+static const struct snd_kcontrol_new rt5682_alg_dac_l1_mux =
+	SOC_DAPM_ENUM("Analog DAC L1 Source", rt5682_alg_dac_l1_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_alg_dac_r1_enum, RT5682_A_DAC1_MUX,
+	RT5682_A_DACR1_SFT, rt5682_alg_dac1_src);
+
+static const struct snd_kcontrol_new rt5682_alg_dac_r1_mux =
+	SOC_DAPM_ENUM("Analog DAC R1 Source", rt5682_alg_dac_r1_enum);
+
+/* Out Switch */
+static const struct snd_kcontrol_new hpol_switch =
+	SOC_DAPM_SINGLE_AUTODISABLE("Switch", RT5682_HP_CTRL_1,
+					RT5682_L_MUTE_SFT, 1, 1);
+static const struct snd_kcontrol_new hpor_switch =
+	SOC_DAPM_SINGLE_AUTODISABLE("Switch", RT5682_HP_CTRL_1,
+					RT5682_R_MUTE_SFT, 1, 1);
+
+static int rt5682_hp_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		snd_soc_component_write(component,
+			RT5682_HP_LOGIC_CTRL_2, 0x0012);
+		snd_soc_component_write(component,
+			RT5682_HP_CTRL_2, 0x6000);
+		snd_soc_component_update_bits(component, RT5682_STO_NG2_CTRL_1,
+			RT5682_NG2_EN_MASK, RT5682_NG2_EN);
+		snd_soc_component_update_bits(component,
+			RT5682_DEPOP_1, 0x60, 0x60);
+		break;
+
+	case SND_SOC_DAPM_POST_PMD:
+		snd_soc_component_update_bits(component,
+			RT5682_DEPOP_1, 0x60, 0x0);
+		snd_soc_component_write(component,
+			RT5682_HP_CTRL_2, 0x0000);
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+
+}
+
+static int set_dmic_power(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		/*Add delay to avoid pop noise*/
+		msleep(150);
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static int rt5655_set_verf(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		switch (w->shift) {
+		case RT5682_PWR_VREF1_BIT:
+			snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV1, 0);
+			break;
+
+		case RT5682_PWR_VREF2_BIT:
+			snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV2, 0);
+			break;
+
+		default:
+			break;
+		}
+		break;
+
+	case SND_SOC_DAPM_POST_PMU:
+		usleep_range(15000, 20000);
+		switch (w->shift) {
+		case RT5682_PWR_VREF1_BIT:
+			snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV1,
+				RT5682_PWR_FV1);
+			break;
+
+		case RT5682_PWR_VREF2_BIT:
+			snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV2,
+				RT5682_PWR_FV2);
+			break;
+
+		default:
+			break;
+		}
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static const unsigned int rt5682_adcdat_pin_values[] = {
+	1,
+	3,
+};
+
+static const char * const rt5682_adcdat_pin_select[] = {
+	"ADCDAT1",
+	"ADCDAT2",
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(rt5682_adcdat_pin_enum,
+	RT5682_GPIO_CTRL_1, RT5682_GP4_PIN_SFT, RT5682_GP4_PIN_MASK,
+	rt5682_adcdat_pin_select, rt5682_adcdat_pin_values);
+
+static const struct snd_kcontrol_new rt5682_adcdat_pin_ctrl =
+	SOC_DAPM_ENUM("ADCDAT", rt5682_adcdat_pin_enum);
+
+static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = {
+	SND_SOC_DAPM_SUPPLY("LDO2", RT5682_PWR_ANLG_3, RT5682_PWR_LDO2_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL1", RT5682_PWR_ANLG_3, RT5682_PWR_PLL_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL2B", RT5682_PWR_ANLG_3, RT5682_PWR_PLL2B_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL2F", RT5682_PWR_ANLG_3, RT5682_PWR_PLL2F_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Vref1", RT5682_PWR_ANLG_1, RT5682_PWR_VREF1_BIT, 0,
+		rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+	SND_SOC_DAPM_SUPPLY("Vref2", RT5682_PWR_ANLG_1, RT5682_PWR_VREF2_BIT, 0,
+		rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+
+	/* ASRC */
+	SND_SOC_DAPM_SUPPLY_S("DAC STO1 ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_DAC_STO1_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("ADC STO1 ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_ADC_STO1_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("AD ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_AD_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("DA ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_DA_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("DMIC ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_DMIC_ASRC_SFT, 0, NULL, 0),
+
+	/* Input Side */
+	SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5682_PWR_ANLG_2, RT5682_PWR_MB1_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("MICBIAS2", RT5682_PWR_ANLG_2, RT5682_PWR_MB2_BIT,
+		0, NULL, 0),
+
+	/* Input Lines */
+	SND_SOC_DAPM_INPUT("DMIC L1"),
+	SND_SOC_DAPM_INPUT("DMIC R1"),
+
+	SND_SOC_DAPM_INPUT("IN1P"),
+
+	SND_SOC_DAPM_SUPPLY("DMIC CLK", SND_SOC_NOPM, 0, 0,
+		set_dmic_clk, SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_SUPPLY("DMIC1 Power", RT5682_DMIC_CTRL_1,
+		RT5682_DMIC_1_EN_SFT, 0, set_dmic_power, SND_SOC_DAPM_POST_PMU),
+
+	/* Boost */
+	SND_SOC_DAPM_PGA("BST1 CBJ", SND_SOC_NOPM,
+		0, 0, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("CBJ Power", RT5682_PWR_ANLG_3,
+		RT5682_PWR_CBJ_BIT, 0, NULL, 0),
+
+	/* REC Mixer */
+	SND_SOC_DAPM_MIXER("RECMIX1L", SND_SOC_NOPM, 0, 0, rt5682_rec1_l_mix,
+		ARRAY_SIZE(rt5682_rec1_l_mix)),
+	SND_SOC_DAPM_SUPPLY("RECMIX1L Power", RT5682_PWR_ANLG_2,
+		RT5682_PWR_RM1_L_BIT, 0, NULL, 0),
+
+	/* ADCs */
+	SND_SOC_DAPM_ADC("ADC1 L", NULL, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_ADC("ADC1 R", NULL, SND_SOC_NOPM, 0, 0),
+
+	SND_SOC_DAPM_SUPPLY("ADC1 L Power", RT5682_PWR_DIG_1,
+		RT5682_PWR_ADC_L1_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC1 R Power", RT5682_PWR_DIG_1,
+		RT5682_PWR_ADC_R1_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC1 clock", RT5682_CHOP_ADC,
+		RT5682_CKGEN_ADC1_SFT, 0, NULL, 0),
+
+	/* ADC Mux */
+	SND_SOC_DAPM_MUX("Stereo1 ADC L1 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adc1l_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC R1 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adc1r_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC L2 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adc2l_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC R2 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adc2r_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC L Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adcl_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC R Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adcr_mux),
+	SND_SOC_DAPM_MUX("IF1_ADC Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_if1_adc_slot_mux),
+
+	/* ADC Mixer */
+	SND_SOC_DAPM_SUPPLY("ADC Stereo1 Filter", RT5682_PWR_DIG_2,
+		RT5682_PWR_ADC_S1F_BIT, 0, set_filter_clk,
+		SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_MIXER("Stereo1 ADC MIXL", RT5682_STO1_ADC_DIG_VOL,
+		RT5682_L_MUTE_SFT, 1, rt5682_sto1_adc_l_mix,
+		ARRAY_SIZE(rt5682_sto1_adc_l_mix)),
+	SND_SOC_DAPM_MIXER("Stereo1 ADC MIXR", RT5682_STO1_ADC_DIG_VOL,
+		RT5682_R_MUTE_SFT, 1, rt5682_sto1_adc_r_mix,
+		ARRAY_SIZE(rt5682_sto1_adc_r_mix)),
+	SND_SOC_DAPM_SUPPLY("BTN Detection Mode", RT5682_SAR_IL_CMD_1,
+		14, 1, NULL, 0),
+
+	/* ADC PGA */
+	SND_SOC_DAPM_PGA("Stereo1 ADC MIX", SND_SOC_NOPM, 0, 0, NULL, 0),
+
+	/* Digital Interface */
+	SND_SOC_DAPM_SUPPLY("I2S1", RT5682_PWR_DIG_1, RT5682_PWR_I2S1_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("I2S2", RT5682_PWR_DIG_1, RT5682_PWR_I2S2_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_PGA("IF1 DAC1", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("IF1 DAC1 L", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("IF1 DAC1 R", SND_SOC_NOPM, 0, 0, NULL, 0),
+
+	/* Digital Interface Select */
+	SND_SOC_DAPM_MUX("IF1 01 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if1_01_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF1 23 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if1_23_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF1 45 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if1_45_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF1 67 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if1_67_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF2 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if2_adc_swap_mux),
+
+	SND_SOC_DAPM_MUX("ADCDAT Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_adcdat_pin_ctrl),
+
+	/* Audio Interface */
+	SND_SOC_DAPM_AIF_OUT("AIF1TX", "AIF1 Capture", 0,
+		RT5682_I2S1_SDP, RT5682_SEL_ADCDAT_SFT, 1),
+	SND_SOC_DAPM_AIF_OUT("AIF2TX", "AIF2 Capture", 0,
+		RT5682_I2S2_SDP, RT5682_I2S2_PIN_CFG_SFT, 1),
+	SND_SOC_DAPM_AIF_IN("AIF1RX", "AIF1 Playback", 0, SND_SOC_NOPM, 0, 0),
+
+	/* Output Side */
+	/* DAC mixer before sound effect  */
+	SND_SOC_DAPM_MIXER("DAC1 MIXL", SND_SOC_NOPM, 0, 0,
+		rt5682_dac_l_mix, ARRAY_SIZE(rt5682_dac_l_mix)),
+	SND_SOC_DAPM_MIXER("DAC1 MIXR", SND_SOC_NOPM, 0, 0,
+		rt5682_dac_r_mix, ARRAY_SIZE(rt5682_dac_r_mix)),
+
+	/* DAC channel Mux */
+	SND_SOC_DAPM_MUX("DAC L1 Source", SND_SOC_NOPM, 0, 0,
+		&rt5682_alg_dac_l1_mux),
+	SND_SOC_DAPM_MUX("DAC R1 Source", SND_SOC_NOPM, 0, 0,
+		&rt5682_alg_dac_r1_mux),
+
+	/* DAC Mixer */
+	SND_SOC_DAPM_SUPPLY("DAC Stereo1 Filter", RT5682_PWR_DIG_2,
+		RT5682_PWR_DAC_S1F_BIT, 0, set_filter_clk,
+		SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_MIXER("Stereo1 DAC MIXL", SND_SOC_NOPM, 0, 0,
+		rt5682_sto1_dac_l_mix, ARRAY_SIZE(rt5682_sto1_dac_l_mix)),
+	SND_SOC_DAPM_MIXER("Stereo1 DAC MIXR", SND_SOC_NOPM, 0, 0,
+		rt5682_sto1_dac_r_mix, ARRAY_SIZE(rt5682_sto1_dac_r_mix)),
+
+	/* DACs */
+	SND_SOC_DAPM_DAC("DAC L1", NULL, RT5682_PWR_DIG_1,
+		RT5682_PWR_DAC_L1_BIT, 0),
+	SND_SOC_DAPM_DAC("DAC R1", NULL, RT5682_PWR_DIG_1,
+		RT5682_PWR_DAC_R1_BIT, 0),
+	SND_SOC_DAPM_SUPPLY_S("DAC 1 Clock", 3, RT5682_CHOP_DAC,
+		RT5682_CKGEN_DAC1_SFT, 0, NULL, 0),
+
+	/* HPO */
+	SND_SOC_DAPM_PGA_S("HP Amp", 1, SND_SOC_NOPM, 0, 0, rt5682_hp_event,
+		SND_SOC_DAPM_POST_PMD | SND_SOC_DAPM_PRE_PMU),
+
+	SND_SOC_DAPM_SUPPLY("HP Amp L", RT5682_PWR_ANLG_1,
+		RT5682_PWR_HA_L_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("HP Amp R", RT5682_PWR_ANLG_1,
+		RT5682_PWR_HA_R_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("Charge Pump", 1, RT5682_DEPOP_1,
+		RT5682_PUMP_EN_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("Capless", 2, RT5682_DEPOP_1,
+		RT5682_CAPLESS_EN_SFT, 0, NULL, 0),
+
+	SND_SOC_DAPM_SWITCH("HPOL Playback", SND_SOC_NOPM, 0, 0,
+		&hpol_switch),
+	SND_SOC_DAPM_SWITCH("HPOR Playback", SND_SOC_NOPM, 0, 0,
+		&hpor_switch),
+
+	/* CLK DET */
+	SND_SOC_DAPM_SUPPLY("CLKDET SYS", RT5682_CLK_DET,
+		RT5682_SYS_CLK_DET_SFT,	0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKDET PLL1", RT5682_CLK_DET,
+		RT5682_PLL1_CLK_DET_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKDET PLL2", RT5682_CLK_DET,
+		RT5682_PLL2_CLK_DET_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKDET", RT5682_CLK_DET,
+		RT5682_POW_CLK_DET_SFT, 0, NULL, 0),
+
+	/* Output Lines */
+	SND_SOC_DAPM_OUTPUT("HPOL"),
+	SND_SOC_DAPM_OUTPUT("HPOR"),
+
+};
+
+static const struct snd_soc_dapm_route rt5682_dapm_routes[] = {
+	/*PLL*/
+	{"ADC Stereo1 Filter", NULL, "PLL1", is_sys_clk_from_pll1},
+	{"DAC Stereo1 Filter", NULL, "PLL1", is_sys_clk_from_pll1},
+
+	/*ASRC*/
+	{"ADC Stereo1 Filter", NULL, "ADC STO1 ASRC", is_using_asrc},
+	{"DAC Stereo1 Filter", NULL, "DAC STO1 ASRC", is_using_asrc},
+	{"ADC STO1 ASRC", NULL, "AD ASRC"},
+	{"ADC STO1 ASRC", NULL, "CLKDET"},
+	{"DAC STO1 ASRC", NULL, "DA ASRC"},
+	{"DAC STO1 ASRC", NULL, "CLKDET"},
+
+	/*Vref*/
+	{"MICBIAS1", NULL, "Vref1"},
+	{"MICBIAS1", NULL, "Vref2"},
+	{"MICBIAS2", NULL, "Vref1"},
+	{"MICBIAS2", NULL, "Vref2"},
+
+	{"CLKDET SYS", NULL, "CLKDET"},
+
+	{"IN1P", NULL, "LDO2"},
+
+	{"BST1 CBJ", NULL, "IN1P"},
+	{"BST1 CBJ", NULL, "CBJ Power"},
+	{"CBJ Power", NULL, "Vref2"},
+
+	{"RECMIX1L", "CBJ Switch", "BST1 CBJ"},
+	{"RECMIX1L", NULL, "RECMIX1L Power"},
+
+	{"ADC1 L", NULL, "RECMIX1L"},
+	{"ADC1 L", NULL, "ADC1 L Power"},
+	{"ADC1 L", NULL, "ADC1 clock"},
+
+	{"DMIC L1", NULL, "DMIC CLK"},
+	{"DMIC L1", NULL, "DMIC1 Power"},
+	{"DMIC R1", NULL, "DMIC CLK"},
+	{"DMIC R1", NULL, "DMIC1 Power"},
+	{"DMIC CLK", NULL, "DMIC ASRC"},
+
+	{"Stereo1 ADC L Mux", "ADC1 L", "ADC1 L"},
+	{"Stereo1 ADC L Mux", "ADC1 R", "ADC1 R"},
+	{"Stereo1 ADC R Mux", "ADC1 L", "ADC1 L"},
+	{"Stereo1 ADC R Mux", "ADC1 R", "ADC1 R"},
+
+	{"Stereo1 ADC L1 Mux", "ADC", "Stereo1 ADC L Mux"},
+	{"Stereo1 ADC L1 Mux", "DAC MIX", "Stereo1 DAC MIXL"},
+	{"Stereo1 ADC L2 Mux", "DMIC", "DMIC L1"},
+	{"Stereo1 ADC L2 Mux", "DAC MIX", "Stereo1 DAC MIXL"},
+
+	{"Stereo1 ADC R1 Mux", "ADC", "Stereo1 ADC R Mux"},
+	{"Stereo1 ADC R1 Mux", "DAC MIX", "Stereo1 DAC MIXR"},
+	{"Stereo1 ADC R2 Mux", "DMIC", "DMIC R1"},
+	{"Stereo1 ADC R2 Mux", "DAC MIX", "Stereo1 DAC MIXR"},
+
+	{"Stereo1 ADC MIXL", "ADC1 Switch", "Stereo1 ADC L1 Mux"},
+	{"Stereo1 ADC MIXL", "ADC2 Switch", "Stereo1 ADC L2 Mux"},
+	{"Stereo1 ADC MIXL", NULL, "ADC Stereo1 Filter"},
+
+	{"Stereo1 ADC MIXR", "ADC1 Switch", "Stereo1 ADC R1 Mux"},
+	{"Stereo1 ADC MIXR", "ADC2 Switch", "Stereo1 ADC R2 Mux"},
+	{"Stereo1 ADC MIXR", NULL, "ADC Stereo1 Filter"},
+
+	{"ADC Stereo1 Filter", NULL, "BTN Detection Mode"},
+
+	{"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXL"},
+	{"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXR"},
+
+	{"IF1 01 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 01 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 01 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 01 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+
+	{"IF1_ADC Mux", "Slot 0", "IF1 01 ADC Swap Mux"},
+	{"IF1_ADC Mux", "Slot 2", "IF1 23 ADC Swap Mux"},
+	{"IF1_ADC Mux", "Slot 4", "IF1 45 ADC Swap Mux"},
+	{"IF1_ADC Mux", "Slot 6", "IF1 67 ADC Swap Mux"},
+	{"IF1_ADC Mux", NULL, "I2S1"},
+	{"ADCDAT Mux", "ADCDAT1", "IF1_ADC Mux"},
+	{"AIF1TX", NULL, "ADCDAT Mux"},
+	{"IF2 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF2 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF2 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF2 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"ADCDAT Mux", "ADCDAT2", "IF2 ADC Swap Mux"},
+	{"AIF2TX", NULL, "ADCDAT Mux"},
+
+	{"IF1 DAC1 L", NULL, "AIF1RX"},
+	{"IF1 DAC1 L", NULL, "I2S1"},
+	{"IF1 DAC1 L", NULL, "DAC Stereo1 Filter"},
+	{"IF1 DAC1 R", NULL, "AIF1RX"},
+	{"IF1 DAC1 R", NULL, "I2S1"},
+	{"IF1 DAC1 R", NULL, "DAC Stereo1 Filter"},
+
+	{"DAC1 MIXL", "Stereo ADC Switch", "Stereo1 ADC MIXL"},
+	{"DAC1 MIXL", "DAC1 Switch", "IF1 DAC1 L"},
+	{"DAC1 MIXR", "Stereo ADC Switch", "Stereo1 ADC MIXR"},
+	{"DAC1 MIXR", "DAC1 Switch", "IF1 DAC1 R"},
+
+	{"Stereo1 DAC MIXL", "DAC L1 Switch", "DAC1 MIXL"},
+	{"Stereo1 DAC MIXL", "DAC R1 Switch", "DAC1 MIXR"},
+
+	{"Stereo1 DAC MIXR", "DAC R1 Switch", "DAC1 MIXR"},
+	{"Stereo1 DAC MIXR", "DAC L1 Switch", "DAC1 MIXL"},
+
+	{"DAC L1 Source", "DAC1", "DAC1 MIXL"},
+	{"DAC L1 Source", "Stereo1 DAC Mixer", "Stereo1 DAC MIXL"},
+	{"DAC R1 Source", "DAC1", "DAC1 MIXR"},
+	{"DAC R1 Source", "Stereo1 DAC Mixer", "Stereo1 DAC MIXR"},
+
+	{"DAC L1", NULL, "DAC L1 Source"},
+	{"DAC R1", NULL, "DAC R1 Source"},
+
+	{"DAC L1", NULL, "DAC 1 Clock"},
+	{"DAC R1", NULL, "DAC 1 Clock"},
+
+	{"HP Amp", NULL, "DAC L1"},
+	{"HP Amp", NULL, "DAC R1"},
+	{"HP Amp", NULL, "HP Amp L"},
+	{"HP Amp", NULL, "HP Amp R"},
+	{"HP Amp", NULL, "Capless"},
+	{"HP Amp", NULL, "Charge Pump"},
+	{"HP Amp", NULL, "CLKDET SYS"},
+	{"HP Amp", NULL, "CBJ Power"},
+	{"HP Amp", NULL, "Vref2"},
+	{"HPOL Playback", "Switch", "HP Amp"},
+	{"HPOR Playback", "Switch", "HP Amp"},
+	{"HPOL", NULL, "HPOL Playback"},
+	{"HPOR", NULL, "HPOR Playback"},
+};
+
+static int rt5682_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
+			unsigned int rx_mask, int slots, int slot_width)
+{
+	struct snd_soc_component *component = dai->component;
+	unsigned int cl, val = 0;
+
+	if (tx_mask || rx_mask)
+		snd_soc_component_update_bits(component, RT5682_TDM_ADDA_CTRL_2,
+			RT5682_TDM_EN, RT5682_TDM_EN);
+	else
+		snd_soc_component_update_bits(component, RT5682_TDM_ADDA_CTRL_2,
+			RT5682_TDM_EN, 0);
+
+	switch (slots) {
+	case 4:
+		val |= RT5682_TDM_TX_CH_4;
+		val |= RT5682_TDM_RX_CH_4;
+		break;
+	case 6:
+		val |= RT5682_TDM_TX_CH_6;
+		val |= RT5682_TDM_RX_CH_6;
+		break;
+	case 8:
+		val |= RT5682_TDM_TX_CH_8;
+		val |= RT5682_TDM_RX_CH_8;
+		break;
+	case 2:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	snd_soc_component_update_bits(component, RT5682_TDM_CTRL,
+		RT5682_TDM_TX_CH_MASK | RT5682_TDM_RX_CH_MASK, val);
+
+	switch (slot_width) {
+	case 8:
+		if (tx_mask || rx_mask)
+			return -EINVAL;
+		cl = RT5682_I2S1_TX_CHL_8 | RT5682_I2S1_RX_CHL_8;
+		break;
+	case 16:
+		val = RT5682_TDM_CL_16;
+		cl = RT5682_I2S1_TX_CHL_16 | RT5682_I2S1_RX_CHL_16;
+		break;
+	case 20:
+		val = RT5682_TDM_CL_20;
+		cl = RT5682_I2S1_TX_CHL_20 | RT5682_I2S1_RX_CHL_20;
+		break;
+	case 24:
+		val = RT5682_TDM_CL_24;
+		cl = RT5682_I2S1_TX_CHL_24 | RT5682_I2S1_RX_CHL_24;
+		break;
+	case 32:
+		val = RT5682_TDM_CL_32;
+		cl = RT5682_I2S1_TX_CHL_32 | RT5682_I2S1_RX_CHL_32;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	snd_soc_component_update_bits(component, RT5682_TDM_TCON_CTRL,
+		RT5682_TDM_CL_MASK, val);
+	snd_soc_component_update_bits(component, RT5682_I2S1_SDP,
+		RT5682_I2S1_TX_CHL_MASK | RT5682_I2S1_RX_CHL_MASK, cl);
+
+	return 0;
+}
+
+
+static int rt5682_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params, struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	unsigned int len_1 = 0, len_2 = 0;
+	int pre_div, frame_size;
+
+	rt5682->lrck[dai->id] = params_rate(params);
+	pre_div = rl6231_get_clk_info(rt5682->sysclk, rt5682->lrck[dai->id]);
+
+	frame_size = snd_soc_params_to_frame_size(params);
+	if (frame_size < 0) {
+		dev_err(component->dev, "Unsupported frame size: %d\n",
+			frame_size);
+		return -EINVAL;
+	}
+
+	dev_dbg(dai->dev, "lrck is %dHz and pre_div is %d for iis %d\n",
+				rt5682->lrck[dai->id], pre_div, dai->id);
+
+	switch (params_width(params)) {
+	case 16:
+		break;
+	case 20:
+		len_1 |= RT5682_I2S1_DL_20;
+		len_2 |= RT5682_I2S2_DL_20;
+		break;
+	case 24:
+		len_1 |= RT5682_I2S1_DL_24;
+		len_2 |= RT5682_I2S2_DL_24;
+		break;
+	case 32:
+		len_1 |= RT5682_I2S1_DL_32;
+		len_2 |= RT5682_I2S2_DL_24;
+		break;
+	case 8:
+		len_1 |= RT5682_I2S2_DL_8;
+		len_2 |= RT5682_I2S2_DL_8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (dai->id) {
+	case RT5682_AIF1:
+		snd_soc_component_update_bits(component, RT5682_I2S1_SDP,
+			RT5682_I2S1_DL_MASK, len_1);
+		if (rt5682->master[RT5682_AIF1]) {
+			snd_soc_component_update_bits(component,
+				RT5682_ADDA_CLK_1, RT5682_I2S_M_DIV_MASK,
+				pre_div << RT5682_I2S_M_DIV_SFT);
+		}
+		if (params_channels(params) == 1) /* mono mode */
+			snd_soc_component_update_bits(component,
+				RT5682_I2S1_SDP, RT5682_I2S1_MONO_MASK,
+				RT5682_I2S1_MONO_EN);
+		else
+			snd_soc_component_update_bits(component,
+				RT5682_I2S1_SDP, RT5682_I2S1_MONO_MASK,
+				RT5682_I2S1_MONO_DIS);
+		break;
+	case RT5682_AIF2:
+		snd_soc_component_update_bits(component, RT5682_I2S2_SDP,
+			RT5682_I2S2_DL_MASK, len_2);
+		if (rt5682->master[RT5682_AIF2]) {
+			snd_soc_component_update_bits(component,
+				RT5682_I2S_M_CLK_CTRL_1, RT5682_I2S2_M_PD_MASK,
+				pre_div << RT5682_I2S2_M_PD_SFT);
+		}
+		if (params_channels(params) == 1) /* mono mode */
+			snd_soc_component_update_bits(component,
+				RT5682_I2S2_SDP, RT5682_I2S2_MONO_MASK,
+				RT5682_I2S2_MONO_EN);
+		else
+			snd_soc_component_update_bits(component,
+				RT5682_I2S2_SDP, RT5682_I2S2_MONO_MASK,
+				RT5682_I2S2_MONO_DIS);
+		break;
+	default:
+		dev_err(component->dev, "Invalid dai->id: %d\n", dai->id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rt5682_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	unsigned int reg_val = 0, tdm_ctrl = 0;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		rt5682->master[dai->id] = 1;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		rt5682->master[dai->id] = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		reg_val |= RT5682_I2S_BP_INV;
+		tdm_ctrl |= RT5682_TDM_S_BP_INV;
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		if (dai->id == RT5682_AIF1)
+			tdm_ctrl |= RT5682_TDM_S_LP_INV | RT5682_TDM_M_BP_INV;
+		else
+			return -EINVAL;
+		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		if (dai->id == RT5682_AIF1)
+			tdm_ctrl |= RT5682_TDM_S_BP_INV | RT5682_TDM_S_LP_INV |
+				    RT5682_TDM_M_BP_INV | RT5682_TDM_M_LP_INV;
+		else
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		reg_val |= RT5682_I2S_DF_LEFT;
+		tdm_ctrl |= RT5682_TDM_DF_LEFT;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		reg_val |= RT5682_I2S_DF_PCM_A;
+		tdm_ctrl |= RT5682_TDM_DF_PCM_A;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		reg_val |= RT5682_I2S_DF_PCM_B;
+		tdm_ctrl |= RT5682_TDM_DF_PCM_B;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (dai->id) {
+	case RT5682_AIF1:
+		snd_soc_component_update_bits(component, RT5682_I2S1_SDP,
+			RT5682_I2S_DF_MASK, reg_val);
+		snd_soc_component_update_bits(component, RT5682_TDM_TCON_CTRL,
+			RT5682_TDM_MS_MASK | RT5682_TDM_S_BP_MASK |
+			RT5682_TDM_DF_MASK | RT5682_TDM_M_BP_MASK |
+			RT5682_TDM_M_LP_MASK | RT5682_TDM_S_LP_MASK,
+			tdm_ctrl | rt5682->master[dai->id]);
+		break;
+	case RT5682_AIF2:
+		if (rt5682->master[dai->id] == 0)
+			reg_val |= RT5682_I2S2_MS_S;
+		snd_soc_component_update_bits(component, RT5682_I2S2_SDP,
+			RT5682_I2S2_MS_MASK | RT5682_I2S_BP_MASK |
+			RT5682_I2S_DF_MASK, reg_val);
+		break;
+	default:
+		dev_err(component->dev, "Invalid dai->id: %d\n", dai->id);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int rt5682_set_component_sysclk(struct snd_soc_component *component,
+		int clk_id, int source, unsigned int freq, int dir)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	unsigned int reg_val = 0, src = 0;
+
+	if (freq == rt5682->sysclk && clk_id == rt5682->sysclk_src)
+		return 0;
+
+	switch (clk_id) {
+	case RT5682_SCLK_S_MCLK:
+		reg_val |= RT5682_SCLK_SRC_MCLK;
+		src = RT5682_CLK_SRC_MCLK;
+		break;
+	case RT5682_SCLK_S_PLL1:
+		reg_val |= RT5682_SCLK_SRC_PLL1;
+		src = RT5682_CLK_SRC_PLL1;
+		break;
+	case RT5682_SCLK_S_PLL2:
+		reg_val |= RT5682_SCLK_SRC_PLL2;
+		src = RT5682_CLK_SRC_PLL2;
+		break;
+	case RT5682_SCLK_S_RCCLK:
+		reg_val |= RT5682_SCLK_SRC_RCCLK;
+		src = RT5682_CLK_SRC_RCCLK;
+		break;
+	default:
+		dev_err(component->dev, "Invalid clock id (%d)\n", clk_id);
+		return -EINVAL;
+	}
+	snd_soc_component_update_bits(component, RT5682_GLB_CLK,
+		RT5682_SCLK_SRC_MASK, reg_val);
+
+	if (rt5682->master[RT5682_AIF2]) {
+		snd_soc_component_update_bits(component,
+			RT5682_I2S_M_CLK_CTRL_1, RT5682_I2S2_SRC_MASK,
+			src << RT5682_I2S2_SRC_SFT);
+	}
+
+	rt5682->sysclk = freq;
+	rt5682->sysclk_src = clk_id;
+
+	dev_dbg(component->dev, "Sysclk is %dHz and clock id is %d\n",
+		freq, clk_id);
+
+	return 0;
+}
+
+static int rt5682_set_component_pll(struct snd_soc_component *component,
+		int pll_id, int source, unsigned int freq_in,
+		unsigned int freq_out)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	struct rl6231_pll_code pll_code;
+	int ret;
+
+	if (source == rt5682->pll_src && freq_in == rt5682->pll_in &&
+	    freq_out == rt5682->pll_out)
+		return 0;
+
+	if (!freq_in || !freq_out) {
+		dev_dbg(component->dev, "PLL disabled\n");
+
+		rt5682->pll_in = 0;
+		rt5682->pll_out = 0;
+		snd_soc_component_update_bits(component, RT5682_GLB_CLK,
+			RT5682_SCLK_SRC_MASK, RT5682_SCLK_SRC_MCLK);
+		return 0;
+	}
+
+	switch (source) {
+	case RT5682_PLL1_S_MCLK:
+		snd_soc_component_update_bits(component, RT5682_GLB_CLK,
+			RT5682_PLL1_SRC_MASK, RT5682_PLL1_SRC_MCLK);
+		break;
+	case RT5682_PLL1_S_BCLK1:
+		snd_soc_component_update_bits(component, RT5682_GLB_CLK,
+				RT5682_PLL1_SRC_MASK, RT5682_PLL1_SRC_BCLK1);
+		break;
+	default:
+		dev_err(component->dev, "Unknown PLL Source %d\n", source);
+		return -EINVAL;
+	}
+
+	ret = rl6231_pll_calc(freq_in, freq_out, &pll_code);
+	if (ret < 0) {
+		dev_err(component->dev, "Unsupport input clock %d\n", freq_in);
+		return ret;
+	}
+
+	dev_dbg(component->dev, "bypass=%d m=%d n=%d k=%d\n",
+		pll_code.m_bp, (pll_code.m_bp ? 0 : pll_code.m_code),
+		pll_code.n_code, pll_code.k_code);
+
+	snd_soc_component_write(component, RT5682_PLL_CTRL_1,
+		pll_code.n_code << RT5682_PLL_N_SFT | pll_code.k_code);
+	snd_soc_component_write(component, RT5682_PLL_CTRL_2,
+		(pll_code.m_bp ? 0 : pll_code.m_code) << RT5682_PLL_M_SFT |
+		pll_code.m_bp << RT5682_PLL_M_BP_SFT | RT5682_PLL_RST);
+
+	rt5682->pll_in = freq_in;
+	rt5682->pll_out = freq_out;
+	rt5682->pll_src = source;
+
+	return 0;
+}
+
+static int rt5682_set_bclk_ratio(struct snd_soc_dai *dai, unsigned int ratio)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	rt5682->bclk[dai->id] = ratio;
+
+	switch (ratio) {
+	case 64:
+		snd_soc_component_update_bits(component, RT5682_ADDA_CLK_2,
+			RT5682_I2S2_BCLK_MS2_MASK,
+			RT5682_I2S2_BCLK_MS2_64);
+		break;
+	case 32:
+		snd_soc_component_update_bits(component, RT5682_ADDA_CLK_2,
+			RT5682_I2S2_BCLK_MS2_MASK,
+			RT5682_I2S2_BCLK_MS2_32);
+		break;
+	default:
+		dev_err(dai->dev, "Invalid bclk ratio %d\n", ratio);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rt5682_set_bias_level(struct snd_soc_component *component,
+			enum snd_soc_bias_level level)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
+			RT5682_PWR_MB | RT5682_PWR_BG,
+			RT5682_PWR_MB | RT5682_PWR_BG);
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
+			RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO,
+			RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO);
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
+			RT5682_PWR_MB, RT5682_PWR_MB);
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
+			RT5682_DIG_GATE_CTRL, RT5682_DIG_GATE_CTRL);
+		break;
+	case SND_SOC_BIAS_OFF:
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
+			RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO, 0);
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
+			RT5682_PWR_MB | RT5682_PWR_BG, 0);
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int rt5682_probe(struct snd_soc_component *component)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	rt5682->component = component;
+
+	return 0;
+}
+
+static void rt5682_remove(struct snd_soc_component *component)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	rt5682_reset(rt5682->regmap);
+}
+
+#ifdef CONFIG_PM
+static int rt5682_suspend(struct snd_soc_component *component)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(rt5682->regmap, true);
+	regcache_mark_dirty(rt5682->regmap);
+	return 0;
+}
+
+static int rt5682_resume(struct snd_soc_component *component)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(rt5682->regmap, false);
+	regcache_sync(rt5682->regmap);
+
+	return 0;
+}
+#else
+#define rt5682_suspend NULL
+#define rt5682_resume NULL
+#endif
+
+#define RT5682_STEREO_RATES SNDRV_PCM_RATE_8000_192000
+#define RT5682_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE | \
+		SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S8)
+
+static const struct snd_soc_dai_ops rt5682_aif1_dai_ops = {
+	.hw_params = rt5682_hw_params,
+	.set_fmt = rt5682_set_dai_fmt,
+	.set_tdm_slot = rt5682_set_tdm_slot,
+};
+
+static const struct snd_soc_dai_ops rt5682_aif2_dai_ops = {
+	.hw_params = rt5682_hw_params,
+	.set_fmt = rt5682_set_dai_fmt,
+	.set_bclk_ratio = rt5682_set_bclk_ratio,
+};
+
+static struct snd_soc_dai_driver rt5682_dai[] = {
+	{
+		.name = "rt5682-aif1",
+		.id = RT5682_AIF1,
+		.playback = {
+			.stream_name = "AIF1 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT5682_STEREO_RATES,
+			.formats = RT5682_FORMATS,
+		},
+		.capture = {
+			.stream_name = "AIF1 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT5682_STEREO_RATES,
+			.formats = RT5682_FORMATS,
+		},
+		.ops = &rt5682_aif1_dai_ops,
+	},
+	{
+		.name = "rt5682-aif2",
+		.id = RT5682_AIF2,
+		.capture = {
+			.stream_name = "AIF2 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT5682_STEREO_RATES,
+			.formats = RT5682_FORMATS,
+		},
+		.ops = &rt5682_aif2_dai_ops,
+	},
+};
+
+static const struct snd_soc_component_driver soc_component_dev_rt5682 = {
+	.probe = rt5682_probe,
+	.remove = rt5682_remove,
+	.suspend = rt5682_suspend,
+	.resume = rt5682_resume,
+	.set_bias_level = rt5682_set_bias_level,
+	.controls = rt5682_snd_controls,
+	.num_controls = ARRAY_SIZE(rt5682_snd_controls),
+	.dapm_widgets = rt5682_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(rt5682_dapm_widgets),
+	.dapm_routes = rt5682_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(rt5682_dapm_routes),
+	.set_sysclk = rt5682_set_component_sysclk,
+	.set_pll = rt5682_set_component_pll,
+	.set_jack = rt5682_set_jack_detect,
+	.use_pmdown_time	= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static const struct regmap_config rt5682_regmap = {
+	.reg_bits = 16,
+	.val_bits = 16,
+	.max_register = RT5682_I2C_MODE,
+	.volatile_reg = rt5682_volatile_register,
+	.readable_reg = rt5682_readable_register,
+	.cache_type = REGCACHE_RBTREE,
+	.reg_defaults = rt5682_reg,
+	.num_reg_defaults = ARRAY_SIZE(rt5682_reg),
+	.use_single_rw = true,
+};
+
+static const struct i2c_device_id rt5682_i2c_id[] = {
+	{"rt5682", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, rt5682_i2c_id);
+
+static int rt5682_parse_dt(struct rt5682_priv *rt5682, struct device *dev)
+{
+
+	device_property_read_u32(dev, "realtek,dmic1-data-pin",
+		&rt5682->pdata.dmic1_data_pin);
+	device_property_read_u32(dev, "realtek,dmic1-clk-pin",
+		&rt5682->pdata.dmic1_clk_pin);
+	device_property_read_u32(dev, "realtek,jd-src",
+		&rt5682->pdata.jd_src);
+
+	rt5682->pdata.ldo1_en = of_get_named_gpio(dev->of_node,
+		"realtek,ldo1-en-gpios", 0);
+
+	return 0;
+}
+
+static void rt5682_calibrate(struct rt5682_priv *rt5682)
+{
+	int value, count;
+
+	mutex_lock(&rt5682->calibrate_mutex);
+
+	rt5682_reset(rt5682->regmap);
+	regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xa2bf);
+	usleep_range(15000, 20000);
+	regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xf2bf);
+	regmap_write(rt5682->regmap, RT5682_MICBIAS_2, 0x0380);
+	regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x8001);
+	regmap_write(rt5682->regmap, RT5682_TEST_MODE_CTRL_1, 0x0000);
+	regmap_write(rt5682->regmap, RT5682_STO1_DAC_MIXER, 0x2080);
+	regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0x4040);
+	regmap_write(rt5682->regmap, RT5682_DEPOP_1, 0x0069);
+	regmap_write(rt5682->regmap, RT5682_CHOP_DAC, 0x3000);
+	regmap_write(rt5682->regmap, RT5682_HP_CTRL_2, 0x6000);
+	regmap_write(rt5682->regmap, RT5682_HP_CHARGE_PUMP_1, 0x0f26);
+	regmap_write(rt5682->regmap, RT5682_CALIB_ADC_CTRL, 0x7f05);
+	regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0x686c);
+	regmap_write(rt5682->regmap, RT5682_CAL_REC, 0x0d0d);
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_9, 0x000f);
+	regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x8d01);
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_2, 0x0321);
+	regmap_write(rt5682->regmap, RT5682_HP_LOGIC_CTRL_2, 0x0004);
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_1, 0x7c00);
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_3, 0x06a1);
+	regmap_write(rt5682->regmap, RT5682_A_DAC1_MUX, 0x0311);
+	regmap_write(rt5682->regmap, RT5682_RESET_HPF_CTRL, 0x0000);
+	regmap_write(rt5682->regmap, RT5682_ADC_STO1_HP_CTRL_1, 0x3320);
+
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_1, 0xfc00);
+
+	for (count = 0; count < 60; count++) {
+		regmap_read(rt5682->regmap, RT5682_HP_CALIB_STA_1, &value);
+		if (!(value & 0x8000))
+			break;
+
+		usleep_range(10000, 10005);
+	}
+
+	if (count >= 60)
+		pr_err("HP Calibration Failure\n");
+
+	/* restore settings */
+	regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0xc0c4);
+	regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x0000);
+
+	mutex_unlock(&rt5682->calibrate_mutex);
+
+}
+
+static int rt5682_i2c_probe(struct i2c_client *i2c,
+		    const struct i2c_device_id *id)
+{
+	struct rt5682_platform_data *pdata = dev_get_platdata(&i2c->dev);
+	struct rt5682_priv *rt5682;
+	int i, ret;
+	unsigned int val;
+
+	rt5682 = devm_kzalloc(&i2c->dev, sizeof(struct rt5682_priv),
+		GFP_KERNEL);
+
+	if (rt5682 == NULL)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, rt5682);
+
+	if (pdata)
+		rt5682->pdata = *pdata;
+	else
+		rt5682_parse_dt(rt5682, &i2c->dev);
+
+	rt5682->regmap = devm_regmap_init_i2c(i2c, &rt5682_regmap);
+	if (IS_ERR(rt5682->regmap)) {
+		ret = PTR_ERR(rt5682->regmap);
+		dev_err(&i2c->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(rt5682->supplies); i++)
+		rt5682->supplies[i].supply = rt5682_supply_names[i];
+
+	ret = devm_regulator_bulk_get(&i2c->dev, ARRAY_SIZE(rt5682->supplies),
+				      rt5682->supplies);
+	if (ret != 0) {
+		dev_err(&i2c->dev, "Failed to request supplies: %d\n", ret);
+		return ret;
+	}
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(rt5682->supplies),
+				    rt5682->supplies);
+	if (ret != 0) {
+		dev_err(&i2c->dev, "Failed to enable supplies: %d\n", ret);
+		return ret;
+	}
+
+	if (gpio_is_valid(rt5682->pdata.ldo1_en)) {
+		if (devm_gpio_request_one(&i2c->dev, rt5682->pdata.ldo1_en,
+					  GPIOF_OUT_INIT_HIGH, "rt5682"))
+			dev_err(&i2c->dev, "Fail gpio_request gpio_ldo\n");
+	}
+
+	/* Sleep for 300 ms miniumum */
+	usleep_range(300000, 350000);
+
+	regmap_write(rt5682->regmap, RT5682_I2C_MODE, 0x1);
+	usleep_range(10000, 15000);
+
+	regmap_read(rt5682->regmap, RT5682_DEVICE_ID, &val);
+	if (val != DEVICE_ID) {
+		pr_err("Device with ID register %x is not rt5682\n", val);
+		return -ENODEV;
+	}
+
+	rt5682_reset(rt5682->regmap);
+
+	rt5682_calibrate(rt5682);
+
+	ret = regmap_register_patch(rt5682->regmap, patch_list,
+				    ARRAY_SIZE(patch_list));
+	if (ret != 0)
+		dev_warn(&i2c->dev, "Failed to apply regmap patch: %d\n", ret);
+
+	regmap_write(rt5682->regmap, RT5682_DEPOP_1, 0x0000);
+
+	/* DMIC pin*/
+	if (rt5682->pdata.dmic1_data_pin != RT5682_DMIC1_NULL) {
+		switch (rt5682->pdata.dmic1_data_pin) {
+		case RT5682_DMIC1_DATA_GPIO2: /* share with LRCK2 */
+			regmap_update_bits(rt5682->regmap, RT5682_DMIC_CTRL_1,
+				RT5682_DMIC_1_DP_MASK, RT5682_DMIC_1_DP_GPIO2);
+			regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+				RT5682_GP2_PIN_MASK, RT5682_GP2_PIN_DMIC_SDA);
+			break;
+
+		case RT5682_DMIC1_DATA_GPIO5: /* share with DACDAT1 */
+			regmap_update_bits(rt5682->regmap, RT5682_DMIC_CTRL_1,
+				RT5682_DMIC_1_DP_MASK, RT5682_DMIC_1_DP_GPIO5);
+			regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+				RT5682_GP5_PIN_MASK, RT5682_GP5_PIN_DMIC_SDA);
+			break;
+
+		default:
+			dev_warn(&i2c->dev, "invalid DMIC_DAT pin\n");
+			break;
+		}
+
+		switch (rt5682->pdata.dmic1_clk_pin) {
+		case RT5682_DMIC1_CLK_GPIO1: /* share with IRQ */
+			regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+				RT5682_GP1_PIN_MASK, RT5682_GP1_PIN_DMIC_CLK);
+			break;
+
+		case RT5682_DMIC1_CLK_GPIO3: /* share with BCLK2 */
+			regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+				RT5682_GP3_PIN_MASK, RT5682_GP3_PIN_DMIC_CLK);
+			break;
+
+		default:
+			dev_warn(&i2c->dev, "invalid DMIC_CLK pin\n");
+			break;
+		}
+	}
+
+	regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
+			RT5682_LDO1_DVO_MASK | RT5682_HP_DRIVER_MASK,
+			RT5682_LDO1_DVO_12 | RT5682_HP_DRIVER_5X);
+	regmap_write(rt5682->regmap, RT5682_MICBIAS_2, 0x0380);
+	regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+			RT5682_GP4_PIN_MASK | RT5682_GP5_PIN_MASK,
+			RT5682_GP4_PIN_ADCDAT1 | RT5682_GP5_PIN_DACDAT1);
+	regmap_write(rt5682->regmap, RT5682_TEST_MODE_CTRL_1, 0x0000);
+
+	INIT_DELAYED_WORK(&rt5682->jack_detect_work,
+				rt5682_jack_detect_handler);
+	INIT_DELAYED_WORK(&rt5682->jd_check_work,
+				rt5682_jd_check_handler);
+
+	mutex_init(&rt5682->calibrate_mutex);
+
+	if (i2c->irq) {
+		ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL,
+			rt5682_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+			| IRQF_ONESHOT, "rt5682", rt5682);
+		if (ret)
+			dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret);
+
+	}
+
+	return devm_snd_soc_register_component(&i2c->dev,
+			&soc_component_dev_rt5682,
+			rt5682_dai, ARRAY_SIZE(rt5682_dai));
+}
+
+static void rt5682_i2c_shutdown(struct i2c_client *client)
+{
+	struct rt5682_priv *rt5682 = i2c_get_clientdata(client);
+
+	rt5682_reset(rt5682->regmap);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id rt5682_of_match[] = {
+	{.compatible = "realtek,rt5682i"},
+	{},
+};
+MODULE_DEVICE_TABLE(of, rt5682_of_match);
+#endif
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id rt5682_acpi_match[] = {
+	{"10EC5682", 0,},
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, rt5682_acpi_match);
+#endif
+
+static struct i2c_driver rt5682_i2c_driver = {
+	.driver = {
+		.name = "rt5682",
+		.of_match_table = of_match_ptr(rt5682_of_match),
+		.acpi_match_table = ACPI_PTR(rt5682_acpi_match),
+	},
+	.probe = rt5682_i2c_probe,
+	.shutdown = rt5682_i2c_shutdown,
+	.id_table = rt5682_i2c_id,
+};
+module_i2c_driver(rt5682_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC RT5682 driver");
+MODULE_AUTHOR("Bard Liao <bardliao@realtek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h
new file mode 100644
index 000000000000..8068140ebe3f
--- /dev/null
+++ b/sound/soc/codecs/rt5682.h
@@ -0,0 +1,1324 @@
+/*
+ * rt5682.h  --  RT5682/RT5658 ALSA SoC audio driver
+ *
+ * Copyright 2018 Realtek Microelectronics
+ * Author: Bard Liao <bardliao@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __RT5682_H__
+#define __RT5682_H__
+
+#include <sound/rt5682.h>
+
+#define DEVICE_ID 0x6530
+
+/* Info */
+#define RT5682_RESET				0x0000
+#define RT5682_VERSION_ID			0x00fd
+#define RT5682_VENDOR_ID			0x00fe
+#define RT5682_DEVICE_ID			0x00ff
+/*  I/O - Output */
+#define RT5682_HP_CTRL_1			0x0002
+#define RT5682_HP_CTRL_2			0x0003
+#define RT5682_HPL_GAIN				0x0005
+#define RT5682_HPR_GAIN				0x0006
+
+#define RT5682_I2C_CTRL				0x0008
+
+/* I/O - Input */
+#define RT5682_CBJ_BST_CTRL			0x000b
+#define RT5682_CBJ_CTRL_1			0x0010
+#define RT5682_CBJ_CTRL_2			0x0011
+#define RT5682_CBJ_CTRL_3			0x0012
+#define RT5682_CBJ_CTRL_4			0x0013
+#define RT5682_CBJ_CTRL_5			0x0014
+#define RT5682_CBJ_CTRL_6			0x0015
+#define RT5682_CBJ_CTRL_7			0x0016
+/* I/O - ADC/DAC/DMIC */
+#define RT5682_DAC1_DIG_VOL			0x0019
+#define RT5682_STO1_ADC_DIG_VOL			0x001c
+#define RT5682_STO1_ADC_BOOST			0x001f
+#define RT5682_HP_IMP_GAIN_1			0x0022
+#define RT5682_HP_IMP_GAIN_2			0x0023
+/* Mixer - D-D */
+#define RT5682_SIDETONE_CTRL			0x0024
+#define RT5682_STO1_ADC_MIXER			0x0026
+#define RT5682_AD_DA_MIXER			0x0029
+#define RT5682_STO1_DAC_MIXER			0x002a
+#define RT5682_A_DAC1_MUX			0x002b
+#define RT5682_DIG_INF2_DATA			0x0030
+/* Mixer - ADC */
+#define RT5682_REC_MIXER			0x003c
+#define RT5682_CAL_REC				0x0044
+#define RT5682_ALC_BACK_GAIN			0x0049
+/* Power */
+#define RT5682_PWR_DIG_1			0x0061
+#define RT5682_PWR_DIG_2			0x0062
+#define RT5682_PWR_ANLG_1			0x0063
+#define RT5682_PWR_ANLG_2			0x0064
+#define RT5682_PWR_ANLG_3			0x0065
+#define RT5682_PWR_MIXER			0x0066
+#define RT5682_PWR_VOL				0x0067
+/* Clock Detect */
+#define RT5682_CLK_DET				0x006b
+/* Filter Auto Reset */
+#define RT5682_RESET_LPF_CTRL			0x006c
+#define RT5682_RESET_HPF_CTRL			0x006d
+/* DMIC */
+#define RT5682_DMIC_CTRL_1			0x006e
+/* Format - ADC/DAC */
+#define RT5682_I2S1_SDP				0x0070
+#define RT5682_I2S2_SDP				0x0071
+#define RT5682_ADDA_CLK_1			0x0073
+#define RT5682_ADDA_CLK_2			0x0074
+#define RT5682_I2S1_F_DIV_CTRL_1		0x0075
+#define RT5682_I2S1_F_DIV_CTRL_2		0x0076
+/* Format - TDM Control */
+#define RT5682_TDM_CTRL				0x0079
+#define RT5682_TDM_ADDA_CTRL_1			0x007a
+#define RT5682_TDM_ADDA_CTRL_2			0x007b
+#define RT5682_DATA_SEL_CTRL_1			0x007c
+#define RT5682_TDM_TCON_CTRL			0x007e
+/* Function - Analog */
+#define RT5682_GLB_CLK				0x0080
+#define RT5682_PLL_CTRL_1			0x0081
+#define RT5682_PLL_CTRL_2			0x0082
+#define RT5682_PLL_TRACK_1			0x0083
+#define RT5682_PLL_TRACK_2			0x0084
+#define RT5682_PLL_TRACK_3			0x0085
+#define RT5682_PLL_TRACK_4			0x0086
+#define RT5682_PLL_TRACK_5			0x0087
+#define RT5682_PLL_TRACK_6			0x0088
+#define RT5682_PLL_TRACK_11			0x008c
+#define RT5682_SDW_REF_CLK			0x008d
+#define RT5682_DEPOP_1				0x008e
+#define RT5682_DEPOP_2				0x008f
+#define RT5682_HP_CHARGE_PUMP_1			0x0091
+#define RT5682_HP_CHARGE_PUMP_2			0x0092
+#define RT5682_MICBIAS_1			0x0093
+#define RT5682_MICBIAS_2			0x0094
+#define RT5682_PLL_TRACK_12			0x0098
+#define RT5682_PLL_TRACK_14			0x009a
+#define RT5682_PLL2_CTRL_1			0x009b
+#define RT5682_PLL2_CTRL_2			0x009c
+#define RT5682_PLL2_CTRL_3			0x009d
+#define RT5682_PLL2_CTRL_4			0x009e
+#define RT5682_RC_CLK_CTRL			0x009f
+#define RT5682_I2S_M_CLK_CTRL_1			0x00a0
+#define RT5682_I2S2_F_DIV_CTRL_1		0x00a3
+#define RT5682_I2S2_F_DIV_CTRL_2		0x00a4
+/* Function - Digital */
+#define RT5682_EQ_CTRL_1			0x00ae
+#define RT5682_EQ_CTRL_2			0x00af
+#define RT5682_IRQ_CTRL_1			0x00b6
+#define RT5682_IRQ_CTRL_2			0x00b7
+#define RT5682_IRQ_CTRL_3			0x00b8
+#define RT5682_IRQ_CTRL_4			0x00b9
+#define RT5682_INT_ST_1				0x00be
+#define RT5682_GPIO_CTRL_1			0x00c0
+#define RT5682_GPIO_CTRL_2			0x00c1
+#define RT5682_GPIO_CTRL_3			0x00c2
+#define RT5682_HP_AMP_DET_CTRL_1		0x00d0
+#define RT5682_HP_AMP_DET_CTRL_2		0x00d1
+#define RT5682_MID_HP_AMP_DET			0x00d2
+#define RT5682_LOW_HP_AMP_DET			0x00d3
+#define RT5682_DELAY_BUF_CTRL			0x00d4
+#define RT5682_SV_ZCD_1				0x00d9
+#define RT5682_SV_ZCD_2				0x00da
+#define RT5682_IL_CMD_1				0x00db
+#define RT5682_IL_CMD_2				0x00dc
+#define RT5682_IL_CMD_3				0x00dd
+#define RT5682_IL_CMD_4				0x00de
+#define RT5682_IL_CMD_5				0x00df
+#define RT5682_IL_CMD_6				0x00e0
+#define RT5682_4BTN_IL_CMD_1			0x00e2
+#define RT5682_4BTN_IL_CMD_2			0x00e3
+#define RT5682_4BTN_IL_CMD_3			0x00e4
+#define RT5682_4BTN_IL_CMD_4			0x00e5
+#define RT5682_4BTN_IL_CMD_5			0x00e6
+#define RT5682_4BTN_IL_CMD_6			0x00e7
+#define RT5682_4BTN_IL_CMD_7			0x00e8
+
+#define RT5682_ADC_STO1_HP_CTRL_1		0x00ea
+#define RT5682_ADC_STO1_HP_CTRL_2		0x00eb
+#define RT5682_AJD1_CTRL			0x00f0
+#define RT5682_JD1_THD				0x00f1
+#define RT5682_JD2_THD				0x00f2
+#define RT5682_JD_CTRL_1			0x00f6
+/* General Control */
+#define RT5682_DUMMY_1				0x00fa
+#define RT5682_DUMMY_2				0x00fb
+#define RT5682_DUMMY_3				0x00fc
+
+#define RT5682_DAC_ADC_DIG_VOL1			0x0100
+#define RT5682_BIAS_CUR_CTRL_2			0x010b
+#define RT5682_BIAS_CUR_CTRL_3			0x010c
+#define RT5682_BIAS_CUR_CTRL_4			0x010d
+#define RT5682_BIAS_CUR_CTRL_5			0x010e
+#define RT5682_BIAS_CUR_CTRL_6			0x010f
+#define RT5682_BIAS_CUR_CTRL_7			0x0110
+#define RT5682_BIAS_CUR_CTRL_8			0x0111
+#define RT5682_BIAS_CUR_CTRL_9			0x0112
+#define RT5682_BIAS_CUR_CTRL_10			0x0113
+#define RT5682_VREF_REC_OP_FB_CAP_CTRL		0x0117
+#define RT5682_CHARGE_PUMP_1			0x0125
+#define RT5682_DIG_IN_CTRL_1			0x0132
+#define RT5682_PAD_DRIVING_CTRL			0x0136
+#define RT5682_SOFT_RAMP_DEPOP			0x0138
+#define RT5682_CHOP_DAC				0x013a
+#define RT5682_CHOP_ADC				0x013b
+#define RT5682_CALIB_ADC_CTRL			0x013c
+#define RT5682_VOL_TEST				0x013f
+#define RT5682_SPKVDD_DET_STA			0x0142
+#define RT5682_TEST_MODE_CTRL_1			0x0145
+#define RT5682_TEST_MODE_CTRL_2			0x0146
+#define RT5682_TEST_MODE_CTRL_3			0x0147
+#define RT5682_TEST_MODE_CTRL_4			0x0148
+#define RT5682_TEST_MODE_CTRL_5			0x0149
+#define RT5682_PLL1_INTERNAL			0x0150
+#define RT5682_PLL2_INTERNAL			0x0151
+#define RT5682_STO_NG2_CTRL_1			0x0160
+#define RT5682_STO_NG2_CTRL_2			0x0161
+#define RT5682_STO_NG2_CTRL_3			0x0162
+#define RT5682_STO_NG2_CTRL_4			0x0163
+#define RT5682_STO_NG2_CTRL_5			0x0164
+#define RT5682_STO_NG2_CTRL_6			0x0165
+#define RT5682_STO_NG2_CTRL_7			0x0166
+#define RT5682_STO_NG2_CTRL_8			0x0167
+#define RT5682_STO_NG2_CTRL_9			0x0168
+#define RT5682_STO_NG2_CTRL_10			0x0169
+#define RT5682_STO1_DAC_SIL_DET			0x0190
+#define RT5682_SIL_PSV_CTRL1			0x0194
+#define RT5682_SIL_PSV_CTRL2			0x0195
+#define RT5682_SIL_PSV_CTRL3			0x0197
+#define RT5682_SIL_PSV_CTRL4			0x0198
+#define RT5682_SIL_PSV_CTRL5			0x0199
+#define RT5682_HP_IMP_SENS_CTRL_01		0x01af
+#define RT5682_HP_IMP_SENS_CTRL_02		0x01b0
+#define RT5682_HP_IMP_SENS_CTRL_03		0x01b1
+#define RT5682_HP_IMP_SENS_CTRL_04		0x01b2
+#define RT5682_HP_IMP_SENS_CTRL_05		0x01b3
+#define RT5682_HP_IMP_SENS_CTRL_06		0x01b4
+#define RT5682_HP_IMP_SENS_CTRL_07		0x01b5
+#define RT5682_HP_IMP_SENS_CTRL_08		0x01b6
+#define RT5682_HP_IMP_SENS_CTRL_09		0x01b7
+#define RT5682_HP_IMP_SENS_CTRL_10		0x01b8
+#define RT5682_HP_IMP_SENS_CTRL_11		0x01b9
+#define RT5682_HP_IMP_SENS_CTRL_12		0x01ba
+#define RT5682_HP_IMP_SENS_CTRL_13		0x01bb
+#define RT5682_HP_IMP_SENS_CTRL_14		0x01bc
+#define RT5682_HP_IMP_SENS_CTRL_15		0x01bd
+#define RT5682_HP_IMP_SENS_CTRL_16		0x01be
+#define RT5682_HP_IMP_SENS_CTRL_17		0x01bf
+#define RT5682_HP_IMP_SENS_CTRL_18		0x01c0
+#define RT5682_HP_IMP_SENS_CTRL_19		0x01c1
+#define RT5682_HP_IMP_SENS_CTRL_20		0x01c2
+#define RT5682_HP_IMP_SENS_CTRL_21		0x01c3
+#define RT5682_HP_IMP_SENS_CTRL_22		0x01c4
+#define RT5682_HP_IMP_SENS_CTRL_23		0x01c5
+#define RT5682_HP_IMP_SENS_CTRL_24		0x01c6
+#define RT5682_HP_IMP_SENS_CTRL_25		0x01c7
+#define RT5682_HP_IMP_SENS_CTRL_26		0x01c8
+#define RT5682_HP_IMP_SENS_CTRL_27		0x01c9
+#define RT5682_HP_IMP_SENS_CTRL_28		0x01ca
+#define RT5682_HP_IMP_SENS_CTRL_29		0x01cb
+#define RT5682_HP_IMP_SENS_CTRL_30		0x01cc
+#define RT5682_HP_IMP_SENS_CTRL_31		0x01cd
+#define RT5682_HP_IMP_SENS_CTRL_32		0x01ce
+#define RT5682_HP_IMP_SENS_CTRL_33		0x01cf
+#define RT5682_HP_IMP_SENS_CTRL_34		0x01d0
+#define RT5682_HP_IMP_SENS_CTRL_35		0x01d1
+#define RT5682_HP_IMP_SENS_CTRL_36		0x01d2
+#define RT5682_HP_IMP_SENS_CTRL_37		0x01d3
+#define RT5682_HP_IMP_SENS_CTRL_38		0x01d4
+#define RT5682_HP_IMP_SENS_CTRL_39		0x01d5
+#define RT5682_HP_IMP_SENS_CTRL_40		0x01d6
+#define RT5682_HP_IMP_SENS_CTRL_41		0x01d7
+#define RT5682_HP_IMP_SENS_CTRL_42		0x01d8
+#define RT5682_HP_IMP_SENS_CTRL_43		0x01d9
+#define RT5682_HP_LOGIC_CTRL_1			0x01da
+#define RT5682_HP_LOGIC_CTRL_2			0x01db
+#define RT5682_HP_LOGIC_CTRL_3			0x01dc
+#define RT5682_HP_CALIB_CTRL_1			0x01de
+#define RT5682_HP_CALIB_CTRL_2			0x01df
+#define RT5682_HP_CALIB_CTRL_3			0x01e0
+#define RT5682_HP_CALIB_CTRL_4			0x01e1
+#define RT5682_HP_CALIB_CTRL_5			0x01e2
+#define RT5682_HP_CALIB_CTRL_6			0x01e3
+#define RT5682_HP_CALIB_CTRL_7			0x01e4
+#define RT5682_HP_CALIB_CTRL_9			0x01e6
+#define RT5682_HP_CALIB_CTRL_10			0x01e7
+#define RT5682_HP_CALIB_CTRL_11			0x01e8
+#define RT5682_HP_CALIB_STA_1			0x01ea
+#define RT5682_HP_CALIB_STA_2			0x01eb
+#define RT5682_HP_CALIB_STA_3			0x01ec
+#define RT5682_HP_CALIB_STA_4			0x01ed
+#define RT5682_HP_CALIB_STA_5			0x01ee
+#define RT5682_HP_CALIB_STA_6			0x01ef
+#define RT5682_HP_CALIB_STA_7			0x01f0
+#define RT5682_HP_CALIB_STA_8			0x01f1
+#define RT5682_HP_CALIB_STA_9			0x01f2
+#define RT5682_HP_CALIB_STA_10			0x01f3
+#define RT5682_HP_CALIB_STA_11			0x01f4
+#define RT5682_SAR_IL_CMD_1			0x0210
+#define RT5682_SAR_IL_CMD_2			0x0211
+#define RT5682_SAR_IL_CMD_3			0x0212
+#define RT5682_SAR_IL_CMD_4			0x0213
+#define RT5682_SAR_IL_CMD_5			0x0214
+#define RT5682_SAR_IL_CMD_6			0x0215
+#define RT5682_SAR_IL_CMD_7			0x0216
+#define RT5682_SAR_IL_CMD_8			0x0217
+#define RT5682_SAR_IL_CMD_9			0x0218
+#define RT5682_SAR_IL_CMD_10			0x0219
+#define RT5682_SAR_IL_CMD_11			0x021a
+#define RT5682_SAR_IL_CMD_12			0x021b
+#define RT5682_SAR_IL_CMD_13			0x021c
+#define RT5682_EFUSE_CTRL_1			0x0250
+#define RT5682_EFUSE_CTRL_2			0x0251
+#define RT5682_EFUSE_CTRL_3			0x0252
+#define RT5682_EFUSE_CTRL_4			0x0253
+#define RT5682_EFUSE_CTRL_5			0x0254
+#define RT5682_EFUSE_CTRL_6			0x0255
+#define RT5682_EFUSE_CTRL_7			0x0256
+#define RT5682_EFUSE_CTRL_8			0x0257
+#define RT5682_EFUSE_CTRL_9			0x0258
+#define RT5682_EFUSE_CTRL_10			0x0259
+#define RT5682_EFUSE_CTRL_11			0x025a
+#define RT5682_JD_TOP_VC_VTRL			0x0270
+#define RT5682_DRC1_CTRL_0			0x02ff
+#define RT5682_DRC1_CTRL_1			0x0300
+#define RT5682_DRC1_CTRL_2			0x0301
+#define RT5682_DRC1_CTRL_3			0x0302
+#define RT5682_DRC1_CTRL_4			0x0303
+#define RT5682_DRC1_CTRL_5			0x0304
+#define RT5682_DRC1_CTRL_6			0x0305
+#define RT5682_DRC1_HARD_LMT_CTRL_1		0x0306
+#define RT5682_DRC1_HARD_LMT_CTRL_2		0x0307
+#define RT5682_DRC1_PRIV_1			0x0310
+#define RT5682_DRC1_PRIV_2			0x0311
+#define RT5682_DRC1_PRIV_3			0x0312
+#define RT5682_DRC1_PRIV_4			0x0313
+#define RT5682_DRC1_PRIV_5			0x0314
+#define RT5682_DRC1_PRIV_6			0x0315
+#define RT5682_DRC1_PRIV_7			0x0316
+#define RT5682_DRC1_PRIV_8			0x0317
+#define RT5682_EQ_AUTO_RCV_CTRL1		0x03c0
+#define RT5682_EQ_AUTO_RCV_CTRL2		0x03c1
+#define RT5682_EQ_AUTO_RCV_CTRL3		0x03c2
+#define RT5682_EQ_AUTO_RCV_CTRL4		0x03c3
+#define RT5682_EQ_AUTO_RCV_CTRL5		0x03c4
+#define RT5682_EQ_AUTO_RCV_CTRL6		0x03c5
+#define RT5682_EQ_AUTO_RCV_CTRL7		0x03c6
+#define RT5682_EQ_AUTO_RCV_CTRL8		0x03c7
+#define RT5682_EQ_AUTO_RCV_CTRL9		0x03c8
+#define RT5682_EQ_AUTO_RCV_CTRL10		0x03c9
+#define RT5682_EQ_AUTO_RCV_CTRL11		0x03ca
+#define RT5682_EQ_AUTO_RCV_CTRL12		0x03cb
+#define RT5682_EQ_AUTO_RCV_CTRL13		0x03cc
+#define RT5682_ADC_L_EQ_LPF1_A1			0x03d0
+#define RT5682_R_EQ_LPF1_A1			0x03d1
+#define RT5682_L_EQ_LPF1_H0			0x03d2
+#define RT5682_R_EQ_LPF1_H0			0x03d3
+#define RT5682_L_EQ_BPF1_A1			0x03d4
+#define RT5682_R_EQ_BPF1_A1			0x03d5
+#define RT5682_L_EQ_BPF1_A2			0x03d6
+#define RT5682_R_EQ_BPF1_A2			0x03d7
+#define RT5682_L_EQ_BPF1_H0			0x03d8
+#define RT5682_R_EQ_BPF1_H0			0x03d9
+#define RT5682_L_EQ_BPF2_A1			0x03da
+#define RT5682_R_EQ_BPF2_A1			0x03db
+#define RT5682_L_EQ_BPF2_A2			0x03dc
+#define RT5682_R_EQ_BPF2_A2			0x03dd
+#define RT5682_L_EQ_BPF2_H0			0x03de
+#define RT5682_R_EQ_BPF2_H0			0x03df
+#define RT5682_L_EQ_BPF3_A1			0x03e0
+#define RT5682_R_EQ_BPF3_A1			0x03e1
+#define RT5682_L_EQ_BPF3_A2			0x03e2
+#define RT5682_R_EQ_BPF3_A2			0x03e3
+#define RT5682_L_EQ_BPF3_H0			0x03e4
+#define RT5682_R_EQ_BPF3_H0			0x03e5
+#define RT5682_L_EQ_BPF4_A1			0x03e6
+#define RT5682_R_EQ_BPF4_A1			0x03e7
+#define RT5682_L_EQ_BPF4_A2			0x03e8
+#define RT5682_R_EQ_BPF4_A2			0x03e9
+#define RT5682_L_EQ_BPF4_H0			0x03ea
+#define RT5682_R_EQ_BPF4_H0			0x03eb
+#define RT5682_L_EQ_HPF1_A1			0x03ec
+#define RT5682_R_EQ_HPF1_A1			0x03ed
+#define RT5682_L_EQ_HPF1_H0			0x03ee
+#define RT5682_R_EQ_HPF1_H0			0x03ef
+#define RT5682_L_EQ_PRE_VOL			0x03f0
+#define RT5682_R_EQ_PRE_VOL			0x03f1
+#define RT5682_L_EQ_POST_VOL			0x03f2
+#define RT5682_R_EQ_POST_VOL			0x03f3
+#define RT5682_I2C_MODE				0xffff
+
+
+/* global definition */
+#define RT5682_L_MUTE				(0x1 << 15)
+#define RT5682_L_MUTE_SFT			15
+#define RT5682_VOL_L_MUTE			(0x1 << 14)
+#define RT5682_VOL_L_SFT			14
+#define RT5682_R_MUTE				(0x1 << 7)
+#define RT5682_R_MUTE_SFT			7
+#define RT5682_VOL_R_MUTE			(0x1 << 6)
+#define RT5682_VOL_R_SFT			6
+#define RT5682_L_VOL_MASK			(0x3f << 8)
+#define RT5682_L_VOL_SFT			8
+#define RT5682_R_VOL_MASK			(0x3f)
+#define RT5682_R_VOL_SFT			0
+
+/*Headphone Amp L/R Analog Gain and Digital NG2 Gain Control (0x0005 0x0006)*/
+#define RT5682_G_HP				(0xf << 8)
+#define RT5682_G_HP_SFT				8
+#define RT5682_G_STO_DA_DMIX			(0xf)
+#define RT5682_G_STO_DA_SFT			0
+
+/* CBJ Control (0x000b) */
+#define RT5682_BST_CBJ_MASK			(0xf << 8)
+#define RT5682_BST_CBJ_SFT			8
+
+/* Embeeded Jack and Type Detection Control 1 (0x0010) */
+#define RT5682_EMB_JD_EN			(0x1 << 15)
+#define RT5682_EMB_JD_EN_SFT			15
+#define RT5682_EMB_JD_RST			(0x1 << 14)
+#define RT5682_JD_MODE				(0x1 << 13)
+#define RT5682_JD_MODE_SFT			13
+#define RT5682_DET_TYPE				(0x1 << 12)
+#define RT5682_DET_TYPE_SFT			12
+#define RT5682_POLA_EXT_JD_MASK			(0x1 << 11)
+#define RT5682_POLA_EXT_JD_LOW			(0x1 << 11)
+#define RT5682_POLA_EXT_JD_HIGH			(0x0 << 11)
+#define RT5682_EXT_JD_DIG			(0x1 << 9)
+#define RT5682_POL_FAST_OFF_MASK		(0x1 << 8)
+#define RT5682_POL_FAST_OFF_HIGH		(0x1 << 8)
+#define RT5682_POL_FAST_OFF_LOW			(0x0 << 8)
+#define RT5682_FAST_OFF_MASK			(0x1 << 7)
+#define RT5682_FAST_OFF_EN			(0x1 << 7)
+#define RT5682_FAST_OFF_DIS			(0x0 << 7)
+#define RT5682_VREF_POW_MASK			(0x1 << 6)
+#define RT5682_VREF_POW_FSM			(0x0 << 6)
+#define RT5682_VREF_POW_REG			(0x1 << 6)
+#define RT5682_MB1_PATH_MASK			(0x1 << 5)
+#define RT5682_CTRL_MB1_REG			(0x1 << 5)
+#define RT5682_CTRL_MB1_FSM			(0x0 << 5)
+#define RT5682_MB2_PATH_MASK			(0x1 << 4)
+#define RT5682_CTRL_MB2_REG			(0x1 << 4)
+#define RT5682_CTRL_MB2_FSM			(0x0 << 4)
+#define RT5682_TRIG_JD_MASK			(0x1 << 3)
+#define RT5682_TRIG_JD_HIGH			(0x1 << 3)
+#define RT5682_TRIG_JD_LOW			(0x0 << 3)
+#define RT5682_MIC_CAP_MASK			(0x1 << 1)
+#define RT5682_MIC_CAP_HS			(0x1 << 1)
+#define RT5682_MIC_CAP_HP			(0x0 << 1)
+#define RT5682_MIC_CAP_SRC_MASK			(0x1)
+#define RT5682_MIC_CAP_SRC_REG			(0x1)
+#define RT5682_MIC_CAP_SRC_ANA			(0x0)
+
+/* Embeeded Jack and Type Detection Control 2 (0x0011) */
+#define RT5682_EXT_JD_SRC			(0x7 << 4)
+#define RT5682_EXT_JD_SRC_SFT			4
+#define RT5682_EXT_JD_SRC_GPIO_JD1		(0x0 << 4)
+#define RT5682_EXT_JD_SRC_GPIO_JD2		(0x1 << 4)
+#define RT5682_EXT_JD_SRC_JDH			(0x2 << 4)
+#define RT5682_EXT_JD_SRC_JDL			(0x3 << 4)
+#define RT5682_EXT_JD_SRC_MANUAL		(0x4 << 4)
+#define RT5682_JACK_TYPE_MASK			(0x3)
+
+/* Combo Jack and Type Detection Control 3 (0x0012) */
+#define RT5682_CBJ_IN_BUF_EN			(0x1 << 7)
+
+/* Combo Jack and Type Detection Control 4 (0x0013) */
+#define RT5682_SEL_SHT_MID_TON_MASK		(0x3 << 12)
+#define RT5682_SEL_SHT_MID_TON_2		(0x0 << 12)
+#define RT5682_SEL_SHT_MID_TON_3		(0x1 << 12)
+#define RT5682_CBJ_JD_TEST_MASK			(0x1 << 6)
+#define RT5682_CBJ_JD_TEST_NORM			(0x0 << 6)
+#define RT5682_CBJ_JD_TEST_MODE			(0x1 << 6)
+
+/* DAC1 Digital Volume (0x0019) */
+#define RT5682_DAC_L1_VOL_MASK			(0xff << 8)
+#define RT5682_DAC_L1_VOL_SFT			8
+#define RT5682_DAC_R1_VOL_MASK			(0xff)
+#define RT5682_DAC_R1_VOL_SFT			0
+
+/* ADC Digital Volume Control (0x001c) */
+#define RT5682_ADC_L_VOL_MASK			(0x7f << 8)
+#define RT5682_ADC_L_VOL_SFT			8
+#define RT5682_ADC_R_VOL_MASK			(0x7f)
+#define RT5682_ADC_R_VOL_SFT			0
+
+/* Stereo1 ADC Boost Gain Control (0x001f) */
+#define RT5682_STO1_ADC_L_BST_MASK		(0x3 << 14)
+#define RT5682_STO1_ADC_L_BST_SFT		14
+#define RT5682_STO1_ADC_R_BST_MASK		(0x3 << 12)
+#define RT5682_STO1_ADC_R_BST_SFT		12
+
+/* Sidetone Control (0x0024) */
+#define RT5682_ST_SRC_SEL			(0x1 << 8)
+#define RT5682_ST_SRC_SFT			8
+#define RT5682_ST_EN_MASK			(0x1 << 6)
+#define RT5682_ST_DIS				(0x0 << 6)
+#define RT5682_ST_EN				(0x1 << 6)
+#define RT5682_ST_EN_SFT			6
+
+/* Stereo1 ADC Mixer Control (0x0026) */
+#define RT5682_M_STO1_ADC_L1			(0x1 << 15)
+#define RT5682_M_STO1_ADC_L1_SFT		15
+#define RT5682_M_STO1_ADC_L2			(0x1 << 14)
+#define RT5682_M_STO1_ADC_L2_SFT		14
+#define RT5682_STO1_ADC1L_SRC_MASK		(0x1 << 13)
+#define RT5682_STO1_ADC1L_SRC_SFT		13
+#define RT5682_STO1_ADC1_SRC_ADC		(0x1 << 13)
+#define RT5682_STO1_ADC1_SRC_DACMIX		(0x0 << 13)
+#define RT5682_STO1_ADC2L_SRC_MASK		(0x1 << 12)
+#define RT5682_STO1_ADC2L_SRC_SFT		12
+#define RT5682_STO1_ADCL_SRC_MASK		(0x3 << 10)
+#define RT5682_STO1_ADCL_SRC_SFT		10
+#define RT5682_STO1_DD_L_SRC_MASK		(0x1 << 9)
+#define RT5682_STO1_DD_L_SRC_SFT		9
+#define RT5682_STO1_DMIC_SRC_MASK		(0x1 << 8)
+#define RT5682_STO1_DMIC_SRC_SFT		8
+#define RT5682_STO1_DMIC_SRC_DMIC2		(0x1 << 8)
+#define RT5682_STO1_DMIC_SRC_DMIC1		(0x0 << 8)
+#define RT5682_M_STO1_ADC_R1			(0x1 << 7)
+#define RT5682_M_STO1_ADC_R1_SFT		7
+#define RT5682_M_STO1_ADC_R2			(0x1 << 6)
+#define RT5682_M_STO1_ADC_R2_SFT		6
+#define RT5682_STO1_ADC1R_SRC_MASK		(0x1 << 5)
+#define RT5682_STO1_ADC1R_SRC_SFT		5
+#define RT5682_STO1_ADC2R_SRC_MASK		(0x1 << 4)
+#define RT5682_STO1_ADC2R_SRC_SFT		4
+#define RT5682_STO1_ADCR_SRC_MASK		(0x3 << 2)
+#define RT5682_STO1_ADCR_SRC_SFT		2
+
+/* ADC Mixer to DAC Mixer Control (0x0029) */
+#define RT5682_M_ADCMIX_L			(0x1 << 15)
+#define RT5682_M_ADCMIX_L_SFT			15
+#define RT5682_M_DAC1_L				(0x1 << 14)
+#define RT5682_M_DAC1_L_SFT			14
+#define RT5682_DAC1_R_SEL_MASK			(0x1 << 10)
+#define RT5682_DAC1_R_SEL_SFT			10
+#define RT5682_DAC1_L_SEL_MASK			(0x1 << 8)
+#define RT5682_DAC1_L_SEL_SFT			8
+#define RT5682_M_ADCMIX_R			(0x1 << 7)
+#define RT5682_M_ADCMIX_R_SFT			7
+#define RT5682_M_DAC1_R				(0x1 << 6)
+#define RT5682_M_DAC1_R_SFT			6
+
+/* Stereo1 DAC Mixer Control (0x002a) */
+#define RT5682_M_DAC_L1_STO_L			(0x1 << 15)
+#define RT5682_M_DAC_L1_STO_L_SFT		15
+#define RT5682_G_DAC_L1_STO_L_MASK		(0x1 << 14)
+#define RT5682_G_DAC_L1_STO_L_SFT		14
+#define RT5682_M_DAC_R1_STO_L			(0x1 << 13)
+#define RT5682_M_DAC_R1_STO_L_SFT		13
+#define RT5682_G_DAC_R1_STO_L_MASK		(0x1 << 12)
+#define RT5682_G_DAC_R1_STO_L_SFT		12
+#define RT5682_M_DAC_L1_STO_R			(0x1 << 7)
+#define RT5682_M_DAC_L1_STO_R_SFT		7
+#define RT5682_G_DAC_L1_STO_R_MASK		(0x1 << 6)
+#define RT5682_G_DAC_L1_STO_R_SFT		6
+#define RT5682_M_DAC_R1_STO_R			(0x1 << 5)
+#define RT5682_M_DAC_R1_STO_R_SFT		5
+#define RT5682_G_DAC_R1_STO_R_MASK		(0x1 << 4)
+#define RT5682_G_DAC_R1_STO_R_SFT		4
+
+/* Analog DAC1 Input Source Control (0x002b) */
+#define RT5682_M_ST_STO_L			(0x1 << 9)
+#define RT5682_M_ST_STO_L_SFT			9
+#define RT5682_M_ST_STO_R			(0x1 << 8)
+#define RT5682_M_ST_STO_R_SFT			8
+#define RT5682_DAC_L1_SRC_MASK			(0x3 << 4)
+#define RT5682_A_DACL1_SFT			4
+#define RT5682_DAC_R1_SRC_MASK			(0x3)
+#define RT5682_A_DACR1_SFT			0
+
+/* Digital Interface Data Control (0x0030) */
+#define RT5682_IF2_ADC_SEL_MASK			(0x3 << 0)
+#define RT5682_IF2_ADC_SEL_SFT			0
+
+/* REC Left Mixer Control 2 (0x003c) */
+#define RT5682_G_CBJ_RM1_L			(0x7 << 10)
+#define RT5682_G_CBJ_RM1_L_SFT			10
+#define RT5682_M_CBJ_RM1_L			(0x1 << 7)
+#define RT5682_M_CBJ_RM1_L_SFT			7
+
+/* Power Management for Digital 1 (0x0061) */
+#define RT5682_PWR_I2S1				(0x1 << 15)
+#define RT5682_PWR_I2S1_BIT			15
+#define RT5682_PWR_I2S2				(0x1 << 14)
+#define RT5682_PWR_I2S2_BIT			14
+#define RT5682_PWR_DAC_L1			(0x1 << 11)
+#define RT5682_PWR_DAC_L1_BIT			11
+#define RT5682_PWR_DAC_R1			(0x1 << 10)
+#define RT5682_PWR_DAC_R1_BIT			10
+#define RT5682_PWR_LDO				(0x1 << 8)
+#define RT5682_PWR_LDO_BIT			8
+#define RT5682_PWR_ADC_L1			(0x1 << 4)
+#define RT5682_PWR_ADC_L1_BIT			4
+#define RT5682_PWR_ADC_R1			(0x1 << 3)
+#define RT5682_PWR_ADC_R1_BIT			3
+#define RT5682_DIG_GATE_CTRL			(0x1 << 0)
+#define RT5682_DIG_GATE_CTRL_SFT		0
+
+
+/* Power Management for Digital 2 (0x0062) */
+#define RT5682_PWR_ADC_S1F			(0x1 << 15)
+#define RT5682_PWR_ADC_S1F_BIT			15
+#define RT5682_PWR_DAC_S1F			(0x1 << 10)
+#define RT5682_PWR_DAC_S1F_BIT			10
+
+/* Power Management for Analog 1 (0x0063) */
+#define RT5682_PWR_VREF1			(0x1 << 15)
+#define RT5682_PWR_VREF1_BIT			15
+#define RT5682_PWR_FV1				(0x1 << 14)
+#define RT5682_PWR_FV1_BIT			14
+#define RT5682_PWR_VREF2			(0x1 << 13)
+#define RT5682_PWR_VREF2_BIT			13
+#define RT5682_PWR_FV2				(0x1 << 12)
+#define RT5682_PWR_FV2_BIT			12
+#define RT5682_LDO1_DBG_MASK			(0x3 << 10)
+#define RT5682_PWR_MB				(0x1 << 9)
+#define RT5682_PWR_MB_BIT			9
+#define RT5682_PWR_BG				(0x1 << 7)
+#define RT5682_PWR_BG_BIT			7
+#define RT5682_LDO1_BYPASS_MASK			(0x1 << 6)
+#define RT5682_LDO1_BYPASS			(0x1 << 6)
+#define RT5682_LDO1_NOT_BYPASS			(0x0 << 6)
+#define RT5682_PWR_MA_BIT			6
+#define RT5682_LDO1_DVO_MASK			(0x3 << 4)
+#define RT5682_LDO1_DVO_09			(0x0 << 4)
+#define RT5682_LDO1_DVO_10			(0x1 << 4)
+#define RT5682_LDO1_DVO_12			(0x2 << 4)
+#define RT5682_LDO1_DVO_14			(0x3 << 4)
+#define RT5682_HP_DRIVER_MASK			(0x3 << 2)
+#define RT5682_HP_DRIVER_1X			(0x0 << 2)
+#define RT5682_HP_DRIVER_3X			(0x1 << 2)
+#define RT5682_HP_DRIVER_5X			(0x3 << 2)
+#define RT5682_PWR_HA_L				(0x1 << 1)
+#define RT5682_PWR_HA_L_BIT			1
+#define RT5682_PWR_HA_R				(0x1 << 0)
+#define RT5682_PWR_HA_R_BIT			0
+
+/* Power Management for Analog 2 (0x0064) */
+#define RT5682_PWR_MB1				(0x1 << 11)
+#define RT5682_PWR_MB1_PWR_DOWN			(0x0 << 11)
+#define RT5682_PWR_MB1_BIT			11
+#define RT5682_PWR_MB2				(0x1 << 10)
+#define RT5682_PWR_MB2_PWR_DOWN			(0x0 << 10)
+#define RT5682_PWR_MB2_BIT			10
+#define RT5682_PWR_JDH				(0x1 << 3)
+#define RT5682_PWR_JDH_BIT			3
+#define RT5682_PWR_JDL				(0x1 << 2)
+#define RT5682_PWR_JDL_BIT			2
+#define RT5682_PWR_RM1_L			(0x1 << 1)
+#define RT5682_PWR_RM1_L_BIT			1
+
+/* Power Management for Analog 3 (0x0065) */
+#define RT5682_PWR_CBJ				(0x1 << 9)
+#define RT5682_PWR_CBJ_BIT			9
+#define RT5682_PWR_PLL				(0x1 << 6)
+#define RT5682_PWR_PLL_BIT			6
+#define RT5682_PWR_PLL2B			(0x1 << 5)
+#define RT5682_PWR_PLL2B_BIT			5
+#define RT5682_PWR_PLL2F			(0x1 << 4)
+#define RT5682_PWR_PLL2F_BIT			4
+#define RT5682_PWR_LDO2				(0x1 << 2)
+#define RT5682_PWR_LDO2_BIT			2
+#define RT5682_PWR_DET_SPKVDD			(0x1 << 1)
+#define RT5682_PWR_DET_SPKVDD_BIT		1
+
+/* Power Management for Mixer (0x0066) */
+#define RT5682_PWR_STO1_DAC_L			(0x1 << 5)
+#define RT5682_PWR_STO1_DAC_L_BIT		5
+#define RT5682_PWR_STO1_DAC_R			(0x1 << 4)
+#define RT5682_PWR_STO1_DAC_R_BIT		4
+
+/* MCLK and System Clock Detection Control (0x006b) */
+#define RT5682_SYS_CLK_DET			(0x1 << 15)
+#define RT5682_SYS_CLK_DET_SFT			15
+#define RT5682_PLL1_CLK_DET			(0x1 << 14)
+#define RT5682_PLL1_CLK_DET_SFT			14
+#define RT5682_PLL2_CLK_DET			(0x1 << 13)
+#define RT5682_PLL2_CLK_DET_SFT			13
+#define RT5682_POW_CLK_DET2_SFT			8
+#define RT5682_POW_CLK_DET_SFT			0
+
+/* Digital Microphone Control 1 (0x006e) */
+#define RT5682_DMIC_1_EN_MASK			(0x1 << 15)
+#define RT5682_DMIC_1_EN_SFT			15
+#define RT5682_DMIC_1_DIS			(0x0 << 15)
+#define RT5682_DMIC_1_EN			(0x1 << 15)
+#define RT5682_DMIC_1_DP_MASK			(0x3 << 4)
+#define RT5682_DMIC_1_DP_SFT			4
+#define RT5682_DMIC_1_DP_GPIO2			(0x0 << 4)
+#define RT5682_DMIC_1_DP_GPIO5			(0x1 << 4)
+#define RT5682_DMIC_CLK_MASK			(0xf << 0)
+#define RT5682_DMIC_CLK_SFT			0
+
+/* I2S1 Audio Serial Data Port Control (0x0070) */
+#define RT5682_SEL_ADCDAT_MASK			(0x1 << 15)
+#define RT5682_SEL_ADCDAT_OUT			(0x0 << 15)
+#define RT5682_SEL_ADCDAT_IN			(0x1 << 15)
+#define RT5682_SEL_ADCDAT_SFT			15
+#define RT5682_I2S1_TX_CHL_MASK			(0x7 << 12)
+#define RT5682_I2S1_TX_CHL_SFT			12
+#define RT5682_I2S1_TX_CHL_16			(0x0 << 12)
+#define RT5682_I2S1_TX_CHL_20			(0x1 << 12)
+#define RT5682_I2S1_TX_CHL_24			(0x2 << 12)
+#define RT5682_I2S1_TX_CHL_32			(0x3 << 12)
+#define RT5682_I2S1_TX_CHL_8			(0x4 << 12)
+#define RT5682_I2S1_RX_CHL_MASK			(0x7 << 8)
+#define RT5682_I2S1_RX_CHL_SFT			8
+#define RT5682_I2S1_RX_CHL_16			(0x0 << 8)
+#define RT5682_I2S1_RX_CHL_20			(0x1 << 8)
+#define RT5682_I2S1_RX_CHL_24			(0x2 << 8)
+#define RT5682_I2S1_RX_CHL_32			(0x3 << 8)
+#define RT5682_I2S1_RX_CHL_8			(0x4 << 8)
+#define RT5682_I2S1_MONO_MASK			(0x1 << 7)
+#define RT5682_I2S1_MONO_EN			(0x1 << 7)
+#define RT5682_I2S1_MONO_DIS			(0x0 << 7)
+#define RT5682_I2S2_MONO_MASK			(0x1 << 6)
+#define RT5682_I2S2_MONO_EN			(0x1 << 6)
+#define RT5682_I2S2_MONO_DIS			(0x0 << 6)
+#define RT5682_I2S1_DL_MASK			(0x7 << 4)
+#define RT5682_I2S1_DL_SFT			4
+#define RT5682_I2S1_DL_16			(0x0 << 4)
+#define RT5682_I2S1_DL_20			(0x1 << 4)
+#define RT5682_I2S1_DL_24			(0x2 << 4)
+#define RT5682_I2S1_DL_32			(0x3 << 4)
+#define RT5682_I2S1_DL_8			(0x4 << 4)
+
+/* I2S1/2 Audio Serial Data Port Control (0x0070)(0x0071) */
+#define RT5682_I2S2_MS_MASK			(0x1 << 15)
+#define RT5682_I2S2_MS_SFT			15
+#define RT5682_I2S2_MS_M			(0x0 << 15)
+#define RT5682_I2S2_MS_S			(0x1 << 15)
+#define RT5682_I2S2_PIN_CFG_MASK		(0x1 << 14)
+#define RT5682_I2S2_PIN_CFG_SFT			14
+#define RT5682_I2S2_CLK_SEL_MASK		(0x1 << 11)
+#define RT5682_I2S2_CLK_SEL_SFT			11
+#define RT5682_I2S2_OUT_MASK			(0x1 << 9)
+#define RT5682_I2S2_OUT_SFT			9
+#define RT5682_I2S2_OUT_UM			(0x0 << 9)
+#define RT5682_I2S2_OUT_M			(0x1 << 9)
+#define RT5682_I2S_BP_MASK			(0x1 << 8)
+#define RT5682_I2S_BP_SFT			8
+#define RT5682_I2S_BP_NOR			(0x0 << 8)
+#define RT5682_I2S_BP_INV			(0x1 << 8)
+#define RT5682_I2S2_MONO_EN			(0x1 << 6)
+#define RT5682_I2S2_MONO_DIS			(0x0 << 6)
+#define RT5682_I2S2_DL_MASK			(0x3 << 4)
+#define RT5682_I2S2_DL_SFT			4
+#define RT5682_I2S2_DL_16			(0x0 << 4)
+#define RT5682_I2S2_DL_20			(0x1 << 4)
+#define RT5682_I2S2_DL_24			(0x2 << 4)
+#define RT5682_I2S2_DL_8			(0x3 << 4)
+#define RT5682_I2S_DF_MASK			(0x7)
+#define RT5682_I2S_DF_SFT			0
+#define RT5682_I2S_DF_I2S			(0x0)
+#define RT5682_I2S_DF_LEFT			(0x1)
+#define RT5682_I2S_DF_PCM_A			(0x2)
+#define RT5682_I2S_DF_PCM_B			(0x3)
+#define RT5682_I2S_DF_PCM_A_N			(0x6)
+#define RT5682_I2S_DF_PCM_B_N			(0x7)
+
+/* ADC/DAC Clock Control 1 (0x0073) */
+#define RT5682_ADC_OSR_MASK			(0xf << 12)
+#define RT5682_ADC_OSR_SFT			12
+#define RT5682_ADC_OSR_D_1			(0x0 << 12)
+#define RT5682_ADC_OSR_D_2			(0x1 << 12)
+#define RT5682_ADC_OSR_D_4			(0x2 << 12)
+#define RT5682_ADC_OSR_D_6			(0x3 << 12)
+#define RT5682_ADC_OSR_D_8			(0x4 << 12)
+#define RT5682_ADC_OSR_D_12			(0x5 << 12)
+#define RT5682_ADC_OSR_D_16			(0x6 << 12)
+#define RT5682_ADC_OSR_D_24			(0x7 << 12)
+#define RT5682_ADC_OSR_D_32			(0x8 << 12)
+#define RT5682_ADC_OSR_D_48			(0x9 << 12)
+#define RT5682_I2S_M_DIV_MASK			(0xf << 12)
+#define RT5682_I2S_M_DIV_SFT			8
+#define RT5682_I2S_M_D_1			(0x0 << 8)
+#define RT5682_I2S_M_D_2			(0x1 << 8)
+#define RT5682_I2S_M_D_3			(0x2 << 8)
+#define RT5682_I2S_M_D_4			(0x3 << 8)
+#define RT5682_I2S_M_D_6			(0x4 << 8)
+#define RT5682_I2S_M_D_8			(0x5 << 8)
+#define RT5682_I2S_M_D_12			(0x6 << 8)
+#define RT5682_I2S_M_D_16			(0x7 << 8)
+#define RT5682_I2S_M_D_24			(0x8 << 8)
+#define RT5682_I2S_M_D_32			(0x9 << 8)
+#define RT5682_I2S_M_D_48			(0x10 << 8)
+#define RT5682_I2S_CLK_SRC_MASK			(0x7 << 4)
+#define RT5682_I2S_CLK_SRC_SFT			4
+#define RT5682_I2S_CLK_SRC_MCLK			(0x0 << 4)
+#define RT5682_I2S_CLK_SRC_PLL1			(0x1 << 4)
+#define RT5682_I2S_CLK_SRC_PLL2			(0x2 << 4)
+#define RT5682_I2S_CLK_SRC_SDW			(0x3 << 4)
+#define RT5682_I2S_CLK_SRC_RCCLK		(0x4 << 4) /* 25M */
+#define RT5682_DAC_OSR_MASK			(0xf << 0)
+#define RT5682_DAC_OSR_SFT			0
+#define RT5682_DAC_OSR_D_1			(0x0 << 0)
+#define RT5682_DAC_OSR_D_2			(0x1 << 0)
+#define RT5682_DAC_OSR_D_4			(0x2 << 0)
+#define RT5682_DAC_OSR_D_6			(0x3 << 0)
+#define RT5682_DAC_OSR_D_8			(0x4 << 0)
+#define RT5682_DAC_OSR_D_12			(0x5 << 0)
+#define RT5682_DAC_OSR_D_16			(0x6 << 0)
+#define RT5682_DAC_OSR_D_24			(0x7 << 0)
+#define RT5682_DAC_OSR_D_32			(0x8 << 0)
+#define RT5682_DAC_OSR_D_48			(0x9 << 0)
+
+/* ADC/DAC Clock Control 2 (0x0074) */
+#define RT5682_I2S2_BCLK_MS2_MASK		(0x1 << 11)
+#define RT5682_I2S2_BCLK_MS2_SFT		11
+#define RT5682_I2S2_BCLK_MS2_32			(0x0 << 11)
+#define RT5682_I2S2_BCLK_MS2_64			(0x1 << 11)
+
+
+/* TDM control 1 (0x0079) */
+#define RT5682_TDM_TX_CH_MASK			(0x3 << 12)
+#define RT5682_TDM_TX_CH_2			(0x0 << 12)
+#define RT5682_TDM_TX_CH_4			(0x1 << 12)
+#define RT5682_TDM_TX_CH_6			(0x2 << 12)
+#define RT5682_TDM_TX_CH_8			(0x3 << 12)
+#define RT5682_TDM_RX_CH_MASK			(0x3 << 8)
+#define RT5682_TDM_RX_CH_2			(0x0 << 8)
+#define RT5682_TDM_RX_CH_4			(0x1 << 8)
+#define RT5682_TDM_RX_CH_6			(0x2 << 8)
+#define RT5682_TDM_RX_CH_8			(0x3 << 8)
+#define RT5682_TDM_ADC_LCA_MASK			(0xf << 4)
+#define RT5682_TDM_ADC_LCA_SFT			4
+#define RT5682_TDM_ADC_DL_SFT			0
+
+/* TDM control 2 (0x007a) */
+#define RT5682_IF1_ADC1_SEL_SFT			14
+#define RT5682_IF1_ADC2_SEL_SFT			12
+#define RT5682_IF1_ADC3_SEL_SFT			10
+#define RT5682_IF1_ADC4_SEL_SFT			8
+#define RT5682_TDM_ADC_SEL_SFT			4
+
+/* TDM control 3 (0x007b) */
+#define RT5682_TDM_EN				(0x1 << 7)
+
+/* TDM/I2S control (0x007e) */
+#define RT5682_TDM_S_BP_MASK			(0x1 << 15)
+#define RT5682_TDM_S_BP_SFT			15
+#define RT5682_TDM_S_BP_NOR			(0x0 << 15)
+#define RT5682_TDM_S_BP_INV			(0x1 << 15)
+#define RT5682_TDM_S_LP_MASK			(0x1 << 14)
+#define RT5682_TDM_S_LP_SFT			14
+#define RT5682_TDM_S_LP_NOR			(0x0 << 14)
+#define RT5682_TDM_S_LP_INV			(0x1 << 14)
+#define RT5682_TDM_DF_MASK			(0x7 << 11)
+#define RT5682_TDM_DF_SFT			11
+#define RT5682_TDM_DF_I2S			(0x0 << 11)
+#define RT5682_TDM_DF_LEFT			(0x1 << 11)
+#define RT5682_TDM_DF_PCM_A			(0x2 << 11)
+#define RT5682_TDM_DF_PCM_B			(0x3 << 11)
+#define RT5682_TDM_DF_PCM_A_N			(0x6 << 11)
+#define RT5682_TDM_DF_PCM_B_N			(0x7 << 11)
+#define RT5682_TDM_CL_MASK			(0x3 << 4)
+#define RT5682_TDM_CL_16			(0x0 << 4)
+#define RT5682_TDM_CL_20			(0x1 << 4)
+#define RT5682_TDM_CL_24			(0x2 << 4)
+#define RT5682_TDM_CL_32			(0x3 << 4)
+#define RT5682_TDM_M_BP_MASK			(0x1 << 2)
+#define RT5682_TDM_M_BP_SFT			2
+#define RT5682_TDM_M_BP_NOR			(0x0 << 2)
+#define RT5682_TDM_M_BP_INV			(0x1 << 2)
+#define RT5682_TDM_M_LP_MASK			(0x1 << 1)
+#define RT5682_TDM_M_LP_SFT			1
+#define RT5682_TDM_M_LP_NOR			(0x0 << 1)
+#define RT5682_TDM_M_LP_INV			(0x1 << 1)
+#define RT5682_TDM_MS_MASK			(0x1 << 0)
+#define RT5682_TDM_MS_SFT			0
+#define RT5682_TDM_MS_M				(0x0 << 0)
+#define RT5682_TDM_MS_S				(0x1 << 0)
+
+/* Global Clock Control (0x0080) */
+#define RT5682_SCLK_SRC_MASK			(0x7 << 13)
+#define RT5682_SCLK_SRC_SFT			13
+#define RT5682_SCLK_SRC_MCLK			(0x0 << 13)
+#define RT5682_SCLK_SRC_PLL1			(0x1 << 13)
+#define RT5682_SCLK_SRC_PLL2			(0x2 << 13)
+#define RT5682_SCLK_SRC_SDW			(0x3 << 13)
+#define RT5682_SCLK_SRC_RCCLK			(0x4 << 13)
+#define RT5682_PLL1_SRC_MASK			(0x3 << 10)
+#define RT5682_PLL1_SRC_SFT			10
+#define RT5682_PLL1_SRC_MCLK			(0x0 << 10)
+#define RT5682_PLL1_SRC_BCLK1			(0x1 << 10)
+#define RT5682_PLL1_SRC_SDW			(0x2 << 10)
+#define RT5682_PLL1_SRC_RC			(0x3 << 10)
+#define RT5682_PLL2_SRC_MASK			(0x3 << 8)
+#define RT5682_PLL2_SRC_SFT			8
+#define RT5682_PLL2_SRC_MCLK			(0x0 << 8)
+#define RT5682_PLL2_SRC_BCLK1			(0x1 << 8)
+#define RT5682_PLL2_SRC_SDW			(0x2 << 8)
+#define RT5682_PLL2_SRC_RC			(0x3 << 8)
+
+
+
+#define RT5682_PLL_INP_MAX			40000000
+#define RT5682_PLL_INP_MIN			256000
+/* PLL M/N/K Code Control 1 (0x0081) */
+#define RT5682_PLL_N_MAX			0x001ff
+#define RT5682_PLL_N_MASK			(RT5682_PLL_N_MAX << 7)
+#define RT5682_PLL_N_SFT			7
+#define RT5682_PLL_K_MAX			0x001f
+#define RT5682_PLL_K_MASK			(RT5682_PLL_K_MAX)
+#define RT5682_PLL_K_SFT			0
+
+/* PLL M/N/K Code Control 2 (0x0082) */
+#define RT5682_PLL_M_MAX			0x00f
+#define RT5682_PLL_M_MASK			(RT5682_PLL_M_MAX << 12)
+#define RT5682_PLL_M_SFT			12
+#define RT5682_PLL_M_BP				(0x1 << 11)
+#define RT5682_PLL_M_BP_SFT			11
+#define RT5682_PLL_K_BP				(0x1 << 10)
+#define RT5682_PLL_K_BP_SFT			10
+#define RT5682_PLL_RST				(0x1 << 1)
+
+/* PLL tracking mode 1 (0x0083) */
+#define RT5682_DA_ASRC_MASK			(0x1 << 13)
+#define RT5682_DA_ASRC_SFT			13
+#define RT5682_DAC_STO1_ASRC_MASK		(0x1 << 12)
+#define RT5682_DAC_STO1_ASRC_SFT		12
+#define RT5682_AD_ASRC_MASK			(0x1 << 8)
+#define RT5682_AD_ASRC_SFT			8
+#define RT5682_AD_ASRC_SEL_MASK			(0x1 << 4)
+#define RT5682_AD_ASRC_SEL_SFT			4
+#define RT5682_DMIC_ASRC_MASK			(0x1 << 3)
+#define RT5682_DMIC_ASRC_SFT			3
+#define RT5682_ADC_STO1_ASRC_MASK		(0x1 << 2)
+#define RT5682_ADC_STO1_ASRC_SFT		2
+#define RT5682_DA_ASRC_SEL_MASK			(0x1 << 0)
+#define RT5682_DA_ASRC_SEL_SFT			0
+
+/* PLL tracking mode 2 3 (0x0084)(0x0085)*/
+#define RT5682_FILTER_CLK_SEL_MASK		(0x7 << 12)
+#define RT5682_FILTER_CLK_SEL_SFT		12
+#define RT5682_FILTER_CLK_DIV_MASK		(0xf << 8)
+#define RT5682_FILTER_CLK_DIV_SFT		8
+
+/* ASRC Control 4 (0x0086) */
+#define RT5682_ASRCIN_FTK_N1_MASK		(0x3 << 14)
+#define RT5682_ASRCIN_FTK_N1_SFT		14
+#define RT5682_ASRCIN_FTK_N2_MASK		(0x3 << 12)
+#define RT5682_ASRCIN_FTK_N2_SFT		12
+#define RT5682_ASRCIN_FTK_M1_MASK		(0x7 << 8)
+#define RT5682_ASRCIN_FTK_M1_SFT		8
+#define RT5682_ASRCIN_FTK_M2_MASK		(0x7 << 4)
+#define RT5682_ASRCIN_FTK_M2_SFT		4
+
+/* SoundWire reference clk (0x008d) */
+#define RT5682_PLL2_OUT_MASK			(0x1 << 8)
+#define RT5682_PLL2_OUT_98M			(0x0 << 8)
+#define RT5682_PLL2_OUT_49M			(0x1 << 8)
+#define RT5682_SDW_REF_2_MASK			(0xf << 4)
+#define RT5682_SDW_REF_2_SFT			4
+#define RT5682_SDW_REF_2_48K			(0x0 << 4)
+#define RT5682_SDW_REF_2_96K			(0x1 << 4)
+#define RT5682_SDW_REF_2_192K			(0x2 << 4)
+#define RT5682_SDW_REF_2_32K			(0x3 << 4)
+#define RT5682_SDW_REF_2_24K			(0x4 << 4)
+#define RT5682_SDW_REF_2_16K			(0x5 << 4)
+#define RT5682_SDW_REF_2_12K			(0x6 << 4)
+#define RT5682_SDW_REF_2_8K			(0x7 << 4)
+#define RT5682_SDW_REF_2_44K			(0x8 << 4)
+#define RT5682_SDW_REF_2_88K			(0x9 << 4)
+#define RT5682_SDW_REF_2_176K			(0xa << 4)
+#define RT5682_SDW_REF_2_353K			(0xb << 4)
+#define RT5682_SDW_REF_2_22K			(0xc << 4)
+#define RT5682_SDW_REF_2_384K			(0xd << 4)
+#define RT5682_SDW_REF_2_11K			(0xe << 4)
+#define RT5682_SDW_REF_1_MASK			(0xf << 0)
+#define RT5682_SDW_REF_1_SFT			0
+#define RT5682_SDW_REF_1_48K			(0x0 << 0)
+#define RT5682_SDW_REF_1_96K			(0x1 << 0)
+#define RT5682_SDW_REF_1_192K			(0x2 << 0)
+#define RT5682_SDW_REF_1_32K			(0x3 << 0)
+#define RT5682_SDW_REF_1_24K			(0x4 << 0)
+#define RT5682_SDW_REF_1_16K			(0x5 << 0)
+#define RT5682_SDW_REF_1_12K			(0x6 << 0)
+#define RT5682_SDW_REF_1_8K			(0x7 << 0)
+#define RT5682_SDW_REF_1_44K			(0x8 << 0)
+#define RT5682_SDW_REF_1_88K			(0x9 << 0)
+#define RT5682_SDW_REF_1_176K			(0xa << 0)
+#define RT5682_SDW_REF_1_353K			(0xb << 0)
+#define RT5682_SDW_REF_1_22K			(0xc << 0)
+#define RT5682_SDW_REF_1_384K			(0xd << 0)
+#define RT5682_SDW_REF_1_11K			(0xe << 0)
+
+/* Depop Mode Control 1 (0x008e) */
+#define RT5682_PUMP_EN				(0x1 << 3)
+#define RT5682_PUMP_EN_SFT				3
+#define RT5682_CAPLESS_EN			(0x1 << 0)
+#define RT5682_CAPLESS_EN_SFT			0
+
+/* Depop Mode Control 2 (0x8f) */
+#define RT5682_RAMP_MASK			(0x1 << 12)
+#define RT5682_RAMP_SFT				12
+#define RT5682_RAMP_DIS				(0x0 << 12)
+#define RT5682_RAMP_EN				(0x1 << 12)
+#define RT5682_BPS_MASK				(0x1 << 11)
+#define RT5682_BPS_SFT				11
+#define RT5682_BPS_DIS				(0x0 << 11)
+#define RT5682_BPS_EN				(0x1 << 11)
+#define RT5682_FAST_UPDN_MASK			(0x1 << 10)
+#define RT5682_FAST_UPDN_SFT			10
+#define RT5682_FAST_UPDN_DIS			(0x0 << 10)
+#define RT5682_FAST_UPDN_EN			(0x1 << 10)
+#define RT5682_VLO_MASK				(0x1 << 7)
+#define RT5682_VLO_SFT				7
+#define RT5682_VLO_3V				(0x0 << 7)
+#define RT5682_VLO_33V				(0x1 << 7)
+
+/* HPOUT charge pump 1 (0x0091) */
+#define RT5682_OSW_L_MASK			(0x1 << 11)
+#define RT5682_OSW_L_SFT			11
+#define RT5682_OSW_L_DIS			(0x0 << 11)
+#define RT5682_OSW_L_EN				(0x1 << 11)
+#define RT5682_OSW_R_MASK			(0x1 << 10)
+#define RT5682_OSW_R_SFT			10
+#define RT5682_OSW_R_DIS			(0x0 << 10)
+#define RT5682_OSW_R_EN				(0x1 << 10)
+#define RT5682_PM_HP_MASK			(0x3 << 8)
+#define RT5682_PM_HP_SFT			8
+#define RT5682_PM_HP_LV				(0x0 << 8)
+#define RT5682_PM_HP_MV				(0x1 << 8)
+#define RT5682_PM_HP_HV				(0x2 << 8)
+#define RT5682_IB_HP_MASK			(0x3 << 6)
+#define RT5682_IB_HP_SFT			6
+#define RT5682_IB_HP_125IL			(0x0 << 6)
+#define RT5682_IB_HP_25IL			(0x1 << 6)
+#define RT5682_IB_HP_5IL			(0x2 << 6)
+#define RT5682_IB_HP_1IL			(0x3 << 6)
+
+/* Micbias Control1 (0x93) */
+#define RT5682_MIC1_OV_MASK			(0x3 << 14)
+#define RT5682_MIC1_OV_SFT			14
+#define RT5682_MIC1_OV_2V7			(0x0 << 14)
+#define RT5682_MIC1_OV_2V4			(0x1 << 14)
+#define RT5682_MIC1_OV_2V25			(0x3 << 14)
+#define RT5682_MIC1_OV_1V8			(0x4 << 14)
+#define RT5682_MIC1_CLK_MASK			(0x1 << 13)
+#define RT5682_MIC1_CLK_SFT			13
+#define RT5682_MIC1_CLK_DIS			(0x0 << 13)
+#define RT5682_MIC1_CLK_EN			(0x1 << 13)
+#define RT5682_MIC1_OVCD_MASK			(0x1 << 12)
+#define RT5682_MIC1_OVCD_SFT			12
+#define RT5682_MIC1_OVCD_DIS			(0x0 << 12)
+#define RT5682_MIC1_OVCD_EN			(0x1 << 12)
+#define RT5682_MIC1_OVTH_MASK			(0x3 << 10)
+#define RT5682_MIC1_OVTH_SFT			10
+#define RT5682_MIC1_OVTH_768UA			(0x0 << 10)
+#define RT5682_MIC1_OVTH_960UA			(0x1 << 10)
+#define RT5682_MIC1_OVTH_1152UA			(0x2 << 10)
+#define RT5682_MIC1_OVTH_1960UA			(0x3 << 10)
+#define RT5682_MIC2_OV_MASK			(0x3 << 8)
+#define RT5682_MIC2_OV_SFT			8
+#define RT5682_MIC2_OV_2V7			(0x0 << 8)
+#define RT5682_MIC2_OV_2V4			(0x1 << 8)
+#define RT5682_MIC2_OV_2V25			(0x3 << 8)
+#define RT5682_MIC2_OV_1V8			(0x4 << 8)
+#define RT5682_MIC2_CLK_MASK			(0x1 << 7)
+#define RT5682_MIC2_CLK_SFT			7
+#define RT5682_MIC2_CLK_DIS			(0x0 << 7)
+#define RT5682_MIC2_CLK_EN			(0x1 << 7)
+#define RT5682_MIC2_OVTH_MASK			(0x3 << 4)
+#define RT5682_MIC2_OVTH_SFT			4
+#define RT5682_MIC2_OVTH_768UA			(0x0 << 4)
+#define RT5682_MIC2_OVTH_960UA			(0x1 << 4)
+#define RT5682_MIC2_OVTH_1152UA			(0x2 << 4)
+#define RT5682_MIC2_OVTH_1960UA			(0x3 << 4)
+#define RT5682_PWR_MB_MASK			(0x1 << 3)
+#define RT5682_PWR_MB_SFT			3
+#define RT5682_PWR_MB_PD			(0x0 << 3)
+#define RT5682_PWR_MB_PU			(0x1 << 3)
+
+/* Micbias Control2 (0x0094) */
+#define RT5682_PWR_CLK25M_MASK			(0x1 << 9)
+#define RT5682_PWR_CLK25M_SFT			9
+#define RT5682_PWR_CLK25M_PD			(0x0 << 9)
+#define RT5682_PWR_CLK25M_PU			(0x1 << 9)
+#define RT5682_PWR_CLK1M_MASK			(0x1 << 8)
+#define RT5682_PWR_CLK1M_SFT			8
+#define RT5682_PWR_CLK1M_PD			(0x0 << 8)
+#define RT5682_PWR_CLK1M_PU			(0x1 << 8)
+
+/* RC Clock Control (0x009f) */
+#define RT5682_POW_IRQ				(0x1 << 15)
+#define RT5682_POW_JDH				(0x1 << 14)
+#define RT5682_POW_JDL				(0x1 << 13)
+#define RT5682_POW_ANA				(0x1 << 12)
+
+/* I2S Master Mode Clock Control 1 (0x00a0) */
+#define RT5682_CLK_SRC_MCLK			(0x0)
+#define RT5682_CLK_SRC_PLL1			(0x1)
+#define RT5682_CLK_SRC_PLL2			(0x2)
+#define RT5682_CLK_SRC_SDW			(0x3)
+#define RT5682_CLK_SRC_RCCLK			(0x4)
+#define RT5682_I2S_PD_1				(0x0)
+#define RT5682_I2S_PD_2				(0x1)
+#define RT5682_I2S_PD_3				(0x2)
+#define RT5682_I2S_PD_4				(0x3)
+#define RT5682_I2S_PD_6				(0x4)
+#define RT5682_I2S_PD_8				(0x5)
+#define RT5682_I2S_PD_12			(0x6)
+#define RT5682_I2S_PD_16			(0x7)
+#define RT5682_I2S_PD_24			(0x8)
+#define RT5682_I2S_PD_32			(0x9)
+#define RT5682_I2S_PD_48			(0xa)
+#define RT5682_I2S2_SRC_MASK			(0x3 << 4)
+#define RT5682_I2S2_SRC_SFT			4
+#define RT5682_I2S2_M_PD_MASK			(0xf << 0)
+#define RT5682_I2S2_M_PD_SFT			0
+
+/* IRQ Control 1 (0x00b6) */
+#define RT5682_JD1_PULSE_EN_MASK		(0x1 << 10)
+#define RT5682_JD1_PULSE_EN_SFT			10
+#define RT5682_JD1_PULSE_DIS			(0x0 << 10)
+#define RT5682_JD1_PULSE_EN			(0x1 << 10)
+
+/* IRQ Control 2 (0x00b7) */
+#define RT5682_JD1_EN_MASK			(0x1 << 15)
+#define RT5682_JD1_EN_SFT			15
+#define RT5682_JD1_DIS				(0x0 << 15)
+#define RT5682_JD1_EN				(0x1 << 15)
+#define RT5682_JD1_POL_MASK			(0x1 << 13)
+#define RT5682_JD1_POL_NOR			(0x0 << 13)
+#define RT5682_JD1_POL_INV			(0x1 << 13)
+
+/* IRQ Control 3 (0x00b8) */
+#define RT5682_IL_IRQ_MASK			(0x1 << 7)
+#define RT5682_IL_IRQ_DIS			(0x0 << 7)
+#define RT5682_IL_IRQ_EN			(0x1 << 7)
+
+/* GPIO Control 1 (0x00c0) */
+#define RT5682_GP1_PIN_MASK			(0x3 << 14)
+#define RT5682_GP1_PIN_SFT			14
+#define RT5682_GP1_PIN_GPIO1			(0x0 << 14)
+#define RT5682_GP1_PIN_IRQ			(0x1 << 14)
+#define RT5682_GP1_PIN_DMIC_CLK			(0x2 << 14)
+#define RT5682_GP2_PIN_MASK			(0x3 << 12)
+#define RT5682_GP2_PIN_SFT			12
+#define RT5682_GP2_PIN_GPIO2			(0x0 << 12)
+#define RT5682_GP2_PIN_LRCK2			(0x1 << 12)
+#define RT5682_GP2_PIN_DMIC_SDA			(0x2 << 12)
+#define RT5682_GP3_PIN_MASK			(0x3 << 10)
+#define RT5682_GP3_PIN_SFT			10
+#define RT5682_GP3_PIN_GPIO3			(0x0 << 10)
+#define RT5682_GP3_PIN_BCLK2			(0x1 << 10)
+#define RT5682_GP3_PIN_DMIC_CLK			(0x2 << 10)
+#define RT5682_GP4_PIN_MASK			(0x3 << 8)
+#define RT5682_GP4_PIN_SFT			8
+#define RT5682_GP4_PIN_GPIO4			(0x0 << 8)
+#define RT5682_GP4_PIN_ADCDAT1			(0x1 << 8)
+#define RT5682_GP4_PIN_DMIC_CLK			(0x2 << 8)
+#define RT5682_GP4_PIN_ADCDAT2			(0x3 << 8)
+#define RT5682_GP5_PIN_MASK			(0x3 << 6)
+#define RT5682_GP5_PIN_SFT			6
+#define RT5682_GP5_PIN_GPIO5			(0x0 << 6)
+#define RT5682_GP5_PIN_DACDAT1			(0x1 << 6)
+#define RT5682_GP5_PIN_DMIC_SDA			(0x2 << 6)
+#define RT5682_GP6_PIN_MASK			(0x1 << 5)
+#define RT5682_GP6_PIN_SFT			5
+#define RT5682_GP6_PIN_GPIO6			(0x0 << 5)
+#define RT5682_GP6_PIN_LRCK1			(0x1 << 5)
+
+/* GPIO Control 2 (0x00c1)*/
+#define RT5682_GP1_PF_MASK			(0x1 << 15)
+#define RT5682_GP1_PF_IN			(0x0 << 15)
+#define RT5682_GP1_PF_OUT			(0x1 << 15)
+#define RT5682_GP1_OUT_MASK			(0x1 << 14)
+#define RT5682_GP1_OUT_L			(0x0 << 14)
+#define RT5682_GP1_OUT_H			(0x1 << 14)
+#define RT5682_GP2_PF_MASK			(0x1 << 13)
+#define RT5682_GP2_PF_IN			(0x0 << 13)
+#define RT5682_GP2_PF_OUT			(0x1 << 13)
+#define RT5682_GP2_OUT_MASK			(0x1 << 12)
+#define RT5682_GP2_OUT_L			(0x0 << 12)
+#define RT5682_GP2_OUT_H			(0x1 << 12)
+#define RT5682_GP3_PF_MASK			(0x1 << 11)
+#define RT5682_GP3_PF_IN			(0x0 << 11)
+#define RT5682_GP3_PF_OUT			(0x1 << 11)
+#define RT5682_GP3_OUT_MASK			(0x1 << 10)
+#define RT5682_GP3_OUT_L			(0x0 << 10)
+#define RT5682_GP3_OUT_H			(0x1 << 10)
+#define RT5682_GP4_PF_MASK			(0x1 << 9)
+#define RT5682_GP4_PF_IN			(0x0 << 9)
+#define RT5682_GP4_PF_OUT			(0x1 << 9)
+#define RT5682_GP4_OUT_MASK			(0x1 << 8)
+#define RT5682_GP4_OUT_L			(0x0 << 8)
+#define RT5682_GP4_OUT_H			(0x1 << 8)
+#define RT5682_GP5_PF_MASK			(0x1 << 7)
+#define RT5682_GP5_PF_IN			(0x0 << 7)
+#define RT5682_GP5_PF_OUT			(0x1 << 7)
+#define RT5682_GP5_OUT_MASK			(0x1 << 6)
+#define RT5682_GP5_OUT_L			(0x0 << 6)
+#define RT5682_GP5_OUT_H			(0x1 << 6)
+#define RT5682_GP6_PF_MASK			(0x1 << 5)
+#define RT5682_GP6_PF_IN			(0x0 << 5)
+#define RT5682_GP6_PF_OUT			(0x1 << 5)
+#define RT5682_GP6_OUT_MASK			(0x1 << 4)
+#define RT5682_GP6_OUT_L			(0x0 << 4)
+#define RT5682_GP6_OUT_H			(0x1 << 4)
+
+
+/* GPIO Status (0x00c2) */
+#define RT5682_GP6_STA				(0x1 << 6)
+#define RT5682_GP5_STA				(0x1 << 5)
+#define RT5682_GP4_STA				(0x1 << 4)
+#define RT5682_GP3_STA				(0x1 << 3)
+#define RT5682_GP2_STA				(0x1 << 2)
+#define RT5682_GP1_STA				(0x1 << 1)
+
+/* Soft volume and zero cross control 1 (0x00d9) */
+#define RT5682_SV_MASK				(0x1 << 15)
+#define RT5682_SV_SFT				15
+#define RT5682_SV_DIS				(0x0 << 15)
+#define RT5682_SV_EN				(0x1 << 15)
+#define RT5682_ZCD_MASK				(0x1 << 10)
+#define RT5682_ZCD_SFT				10
+#define RT5682_ZCD_PD				(0x0 << 10)
+#define RT5682_ZCD_PU				(0x1 << 10)
+#define RT5682_SV_DLY_MASK			(0xf)
+#define RT5682_SV_DLY_SFT			0
+
+/* Soft volume and zero cross control 2 (0x00da) */
+#define RT5682_ZCD_BST1_CBJ_MASK		(0x1 << 7)
+#define RT5682_ZCD_BST1_CBJ_SFT			7
+#define RT5682_ZCD_BST1_CBJ_DIS			(0x0 << 7)
+#define RT5682_ZCD_BST1_CBJ_EN			(0x1 << 7)
+#define RT5682_ZCD_RECMIX_MASK			(0x1)
+#define RT5682_ZCD_RECMIX_SFT			0
+#define RT5682_ZCD_RECMIX_DIS			(0x0)
+#define RT5682_ZCD_RECMIX_EN			(0x1)
+
+/* 4 Button Inline Command Control 2 (0x00e3) */
+#define RT5682_4BTN_IL_MASK			(0x1 << 15)
+#define RT5682_4BTN_IL_EN			(0x1 << 15)
+#define RT5682_4BTN_IL_DIS			(0x0 << 15)
+#define RT5682_4BTN_IL_RST_MASK			(0x1 << 14)
+#define RT5682_4BTN_IL_NOR			(0x1 << 14)
+#define RT5682_4BTN_IL_RST			(0x0 << 14)
+
+/* Analog JD Control (0x00f0) */
+#define RT5682_JDH_RS_MASK			(0x1 << 4)
+#define RT5682_JDH_NO_PLUG			(0x1 << 4)
+#define RT5682_JDH_PLUG				(0x0 << 4)
+
+/* Chopper and Clock control for DAC (0x013a)*/
+#define RT5682_CKXEN_DAC1_MASK			(0x1 << 13)
+#define RT5682_CKXEN_DAC1_SFT			13
+#define RT5682_CKGEN_DAC1_MASK			(0x1 << 12)
+#define RT5682_CKGEN_DAC1_SFT			12
+
+/* Chopper and Clock control for ADC (0x013b)*/
+#define RT5682_CKXEN_ADC1_MASK			(0x1 << 13)
+#define RT5682_CKXEN_ADC1_SFT			13
+#define RT5682_CKGEN_ADC1_MASK			(0x1 << 12)
+#define RT5682_CKGEN_ADC1_SFT			12
+
+/* Volume test (0x013f)*/
+#define RT5682_SEL_CLK_VOL_MASK			(0x1 << 15)
+#define RT5682_SEL_CLK_VOL_EN			(0x1 << 15)
+#define RT5682_SEL_CLK_VOL_DIS			(0x0 << 15)
+
+/* Test Mode Control 1 (0x0145) */
+#define RT5682_AD2DA_LB_MASK			(0x1 << 10)
+#define RT5682_AD2DA_LB_SFT			10
+
+/* Stereo Noise Gate Control 1 (0x0160) */
+#define RT5682_NG2_EN_MASK			(0x1 << 15)
+#define RT5682_NG2_EN				(0x1 << 15)
+#define RT5682_NG2_DIS				(0x0 << 15)
+
+/* Stereo1 DAC Silence Detection Control (0x0190) */
+#define RT5682_DEB_STO_DAC_MASK			(0x7 << 4)
+#define RT5682_DEB_80_MS			(0x0 << 4)
+
+/* SAR ADC Inline Command Control 1 (0x0210) */
+#define RT5682_SAR_BUTT_DET_MASK		(0x1 << 15)
+#define RT5682_SAR_BUTT_DET_EN			(0x1 << 15)
+#define RT5682_SAR_BUTT_DET_DIS			(0x0 << 15)
+#define RT5682_SAR_BUTDET_MODE_MASK		(0x1 << 14)
+#define RT5682_SAR_BUTDET_POW_SAV		(0x1 << 14)
+#define RT5682_SAR_BUTDET_POW_NORM		(0x0 << 14)
+#define RT5682_SAR_BUTDET_RST_MASK		(0x1 << 13)
+#define RT5682_SAR_BUTDET_RST_NORMAL		(0x1 << 13)
+#define RT5682_SAR_BUTDET_RST			(0x0 << 13)
+#define RT5682_SAR_POW_MASK			(0x1 << 12)
+#define RT5682_SAR_POW_EN			(0x1 << 12)
+#define RT5682_SAR_POW_DIS			(0x0 << 12)
+#define RT5682_SAR_RST_MASK			(0x1 << 11)
+#define RT5682_SAR_RST_NORMAL			(0x1 << 11)
+#define RT5682_SAR_RST				(0x0 << 11)
+#define RT5682_SAR_BYPASS_MASK			(0x1 << 10)
+#define RT5682_SAR_BYPASS_EN			(0x1 << 10)
+#define RT5682_SAR_BYPASS_DIS			(0x0 << 10)
+#define RT5682_SAR_SEL_MB1_MASK			(0x1 << 9)
+#define RT5682_SAR_SEL_MB1_SEL			(0x1 << 9)
+#define RT5682_SAR_SEL_MB1_NOSEL		(0x0 << 9)
+#define RT5682_SAR_SEL_MB2_MASK			(0x1 << 8)
+#define RT5682_SAR_SEL_MB2_SEL			(0x1 << 8)
+#define RT5682_SAR_SEL_MB2_NOSEL		(0x0 << 8)
+#define RT5682_SAR_SEL_MODE_MASK		(0x1 << 7)
+#define RT5682_SAR_SEL_MODE_CMP			(0x1 << 7)
+#define RT5682_SAR_SEL_MODE_ADC			(0x0 << 7)
+#define RT5682_SAR_SEL_MB1_MB2_MASK		(0x1 << 5)
+#define RT5682_SAR_SEL_MB1_MB2_AUTO		(0x1 << 5)
+#define RT5682_SAR_SEL_MB1_MB2_MANU		(0x0 << 5)
+#define RT5682_SAR_SEL_SIGNAL_MASK		(0x1 << 4)
+#define RT5682_SAR_SEL_SIGNAL_AUTO		(0x1 << 4)
+#define RT5682_SAR_SEL_SIGNAL_MANU		(0x0 << 4)
+
+/* SAR ADC Inline Command Control 13 (0x021c) */
+#define RT5682_SAR_SOUR_MASK			(0x3f)
+#define RT5682_SAR_SOUR_BTN			(0x3f)
+#define RT5682_SAR_SOUR_TYPE			(0x0)
+
+
+/* System Clock Source */
+enum {
+	RT5682_SCLK_S_MCLK,
+	RT5682_SCLK_S_PLL1,
+	RT5682_SCLK_S_PLL2,
+	RT5682_SCLK_S_RCCLK,
+};
+
+/* PLL Source */
+enum {
+	RT5682_PLL1_S_MCLK,
+	RT5682_PLL1_S_BCLK1,
+	RT5682_PLL1_S_RCCLK,
+};
+
+enum {
+	RT5682_AIF1,
+	RT5682_AIF2,
+	RT5682_AIFS
+};
+
+/* filter mask */
+enum {
+	RT5682_DA_STEREO1_FILTER = 0x1,
+	RT5682_AD_STEREO1_FILTER = (0x1 << 1),
+};
+
+enum {
+	RT5682_CLK_SEL_SYS,
+	RT5682_CLK_SEL_I2S1_ASRC,
+	RT5682_CLK_SEL_I2S2_ASRC,
+};
+
+int rt5682_sel_asrc_clk_src(struct snd_soc_component *component,
+		unsigned int filter_mask, unsigned int clk_src);
+
+#endif /* __RT5682_H__ */
diff --git a/sound/soc/codecs/dio2125.c b/sound/soc/codecs/simple-amplifier.c
index 09451cd44f9b..85524acf3e9c 100644
--- a/sound/soc/codecs/dio2125.c
+++ b/sound/soc/codecs/simple-amplifier.c
@@ -21,9 +21,9 @@
 #include <linux/module.h>
 #include <sound/soc.h>
 
-#define DRV_NAME "dio2125"
+#define DRV_NAME "simple-amplifier"
 
-struct dio2125 {
+struct simple_amp {
 	struct gpio_desc *gpiod_enable;
 };
 
@@ -31,7 +31,7 @@ static int drv_event(struct snd_soc_dapm_widget *w,
 		     struct snd_kcontrol *control, int event)
 {
 	struct snd_soc_component *c = snd_soc_dapm_to_component(w->dapm);
-	struct dio2125 *priv = snd_soc_component_get_drvdata(c);
+	struct simple_amp *priv = snd_soc_component_get_drvdata(c);
 	int val;
 
 	switch (event) {
@@ -51,7 +51,7 @@ static int drv_event(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
-static const struct snd_soc_dapm_widget dio2125_dapm_widgets[] = {
+static const struct snd_soc_dapm_widget simple_amp_dapm_widgets[] = {
 	SND_SOC_DAPM_INPUT("INL"),
 	SND_SOC_DAPM_INPUT("INR"),
 	SND_SOC_DAPM_OUT_DRV_E("DRV", SND_SOC_NOPM, 0, 0, NULL, 0, drv_event,
@@ -60,24 +60,24 @@ static const struct snd_soc_dapm_widget dio2125_dapm_widgets[] = {
 	SND_SOC_DAPM_OUTPUT("OUTR"),
 };
 
-static const struct snd_soc_dapm_route dio2125_dapm_routes[] = {
+static const struct snd_soc_dapm_route simple_amp_dapm_routes[] = {
 	{ "DRV", NULL, "INL" },
 	{ "DRV", NULL, "INR" },
 	{ "OUTL", NULL, "DRV" },
 	{ "OUTR", NULL, "DRV" },
 };
 
-static const struct snd_soc_component_driver dio2125_component_driver = {
-	.dapm_widgets		= dio2125_dapm_widgets,
-	.num_dapm_widgets	= ARRAY_SIZE(dio2125_dapm_widgets),
-	.dapm_routes		= dio2125_dapm_routes,
-	.num_dapm_routes	= ARRAY_SIZE(dio2125_dapm_routes),
+static const struct snd_soc_component_driver simple_amp_component_driver = {
+	.dapm_widgets		= simple_amp_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(simple_amp_dapm_widgets),
+	.dapm_routes		= simple_amp_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(simple_amp_dapm_routes),
 };
 
-static int dio2125_probe(struct platform_device *pdev)
+static int simple_amp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct dio2125 *priv;
+	struct simple_amp *priv;
 	int err;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -93,28 +93,30 @@ static int dio2125_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	return devm_snd_soc_register_component(dev, &dio2125_component_driver,
+	return devm_snd_soc_register_component(dev,
+					       &simple_amp_component_driver,
 					       NULL, 0);
 }
 
 #ifdef CONFIG_OF
-static const struct of_device_id dio2125_ids[] = {
+static const struct of_device_id simple_amp_ids[] = {
 	{ .compatible = "dioo,dio2125", },
+	{ .compatible = "simple-audio-amplifier", },
 	{ }
 };
-MODULE_DEVICE_TABLE(of, dio2125_ids);
+MODULE_DEVICE_TABLE(of, simple_amp_ids);
 #endif
 
-static struct platform_driver dio2125_driver = {
+static struct platform_driver simple_amp_driver = {
 	.driver = {
 		.name = DRV_NAME,
-		.of_match_table = of_match_ptr(dio2125_ids),
+		.of_match_table = of_match_ptr(simple_amp_ids),
 	},
-	.probe = dio2125_probe,
+	.probe = simple_amp_probe,
 };
 
-module_platform_driver(dio2125_driver);
+module_platform_driver(simple_amp_driver);
 
-MODULE_DESCRIPTION("ASoC DIO2125 output driver");
+MODULE_DESCRIPTION("ASoC Simple Audio Amplifier driver");
 MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c
index 52f34c94ec25..ca2dfe12344e 100644
--- a/sound/soc/codecs/tas571x.c
+++ b/sound/soc/codecs/tas571x.c
@@ -7,6 +7,9 @@
  * TAS5721 support:
  * Copyright (C) 2016 Petr Kulhavy, Barix AG <petr@barix.com>
  *
+ * TAS5707 support:
+ * Copyright (C) 2018 Jerome Brunet, Baylibre SAS <jbrunet@baylibre.com>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -444,6 +447,111 @@ static const struct tas571x_chip tas5711_chip = {
 	.vol_reg_size			= 1,
 };
 
+static const struct regmap_range tas5707_volatile_regs_range[] = {
+	regmap_reg_range(TAS571X_CLK_CTRL_REG,  TAS571X_ERR_STATUS_REG),
+	regmap_reg_range(TAS571X_OSC_TRIM_REG,  TAS571X_OSC_TRIM_REG),
+	regmap_reg_range(TAS5707_CH1_BQ0_REG, TAS5707_CH2_BQ6_REG),
+};
+
+static const struct regmap_access_table tas5707_volatile_regs = {
+	.yes_ranges =	tas5707_volatile_regs_range,
+	.n_yes_ranges =	ARRAY_SIZE(tas5707_volatile_regs_range),
+
+};
+
+static const DECLARE_TLV_DB_SCALE(tas5707_volume_tlv, -7900, 50, 1);
+
+static const char * const tas5707_volume_slew_step_txt[] = {
+	"256", "512", "1024", "2048",
+};
+
+static const unsigned int tas5707_volume_slew_step_values[] = {
+	3, 0, 1, 2,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(tas5707_volume_slew_step_enum,
+				  TAS571X_VOL_CFG_REG, 0, 0x3,
+				  tas5707_volume_slew_step_txt,
+				  tas5707_volume_slew_step_values);
+
+static const struct snd_kcontrol_new tas5707_controls[] = {
+	SOC_SINGLE_TLV("Master Volume",
+		       TAS571X_MVOL_REG,
+		       0, 0xff, 1, tas5707_volume_tlv),
+	SOC_DOUBLE_R_TLV("Speaker Volume",
+			 TAS571X_CH1_VOL_REG,
+			 TAS571X_CH2_VOL_REG,
+			 0, 0xff, 1, tas5707_volume_tlv),
+	SOC_DOUBLE("Speaker Switch",
+		   TAS571X_SOFT_MUTE_REG,
+		   TAS571X_SOFT_MUTE_CH1_SHIFT, TAS571X_SOFT_MUTE_CH2_SHIFT,
+		   1, 1),
+
+	SOC_ENUM("Slew Rate Steps", tas5707_volume_slew_step_enum),
+
+	BIQUAD_COEFS("CH1 - Biquad 0", TAS5707_CH1_BQ0_REG),
+	BIQUAD_COEFS("CH1 - Biquad 1", TAS5707_CH1_BQ1_REG),
+	BIQUAD_COEFS("CH1 - Biquad 2", TAS5707_CH1_BQ2_REG),
+	BIQUAD_COEFS("CH1 - Biquad 3", TAS5707_CH1_BQ3_REG),
+	BIQUAD_COEFS("CH1 - Biquad 4", TAS5707_CH1_BQ4_REG),
+	BIQUAD_COEFS("CH1 - Biquad 5", TAS5707_CH1_BQ5_REG),
+	BIQUAD_COEFS("CH1 - Biquad 6", TAS5707_CH1_BQ6_REG),
+
+	BIQUAD_COEFS("CH2 - Biquad 0", TAS5707_CH2_BQ0_REG),
+	BIQUAD_COEFS("CH2 - Biquad 1", TAS5707_CH2_BQ1_REG),
+	BIQUAD_COEFS("CH2 - Biquad 2", TAS5707_CH2_BQ2_REG),
+	BIQUAD_COEFS("CH2 - Biquad 3", TAS5707_CH2_BQ3_REG),
+	BIQUAD_COEFS("CH2 - Biquad 4", TAS5707_CH2_BQ4_REG),
+	BIQUAD_COEFS("CH2 - Biquad 5", TAS5707_CH2_BQ5_REG),
+	BIQUAD_COEFS("CH2 - Biquad 6", TAS5707_CH2_BQ6_REG),
+};
+
+static const struct reg_default tas5707_reg_defaults[] = {
+	{TAS571X_CLK_CTRL_REG,		0x6c},
+	{TAS571X_DEV_ID_REG,		0x70},
+	{TAS571X_ERR_STATUS_REG,	0x00},
+	{TAS571X_SYS_CTRL_1_REG,	0xa0},
+	{TAS571X_SDI_REG,		0x05},
+	{TAS571X_SYS_CTRL_2_REG,	0x40},
+	{TAS571X_SOFT_MUTE_REG,		0x00},
+	{TAS571X_MVOL_REG,		0xff},
+	{TAS571X_CH1_VOL_REG,		0x30},
+	{TAS571X_CH2_VOL_REG,		0x30},
+	{TAS571X_VOL_CFG_REG,		0x91},
+	{TAS571X_MODULATION_LIMIT_REG,	0x02},
+	{TAS571X_IC_DELAY_CH1_REG,	0xac},
+	{TAS571X_IC_DELAY_CH2_REG,	0x54},
+	{TAS571X_IC_DELAY_CH3_REG,	0xac},
+	{TAS571X_IC_DELAY_CH4_REG,	0x54},
+	{TAS571X_START_STOP_PERIOD_REG,	0x0f},
+	{TAS571X_OSC_TRIM_REG,		0x82},
+	{TAS571X_BKND_ERR_REG,		0x02},
+	{TAS571X_INPUT_MUX_REG,		0x17772},
+	{TAS571X_PWM_MUX_REG,		0x1021345},
+};
+
+static const struct regmap_config tas5707_regmap_config = {
+	.reg_bits			= 8,
+	.val_bits			= 32,
+	.max_register			= 0xff,
+	.reg_read			= tas571x_reg_read,
+	.reg_write			= tas571x_reg_write,
+	.reg_defaults			= tas5707_reg_defaults,
+	.num_reg_defaults		= ARRAY_SIZE(tas5707_reg_defaults),
+	.cache_type			= REGCACHE_RBTREE,
+	.wr_table			= &tas571x_write_regs,
+	.volatile_table			= &tas5707_volatile_regs,
+};
+
+static const struct tas571x_chip tas5707_chip = {
+	.supply_names			= tas5711_supply_names,
+	.num_supply_names		= ARRAY_SIZE(tas5711_supply_names),
+	.controls			= tas5707_controls,
+	.num_controls			= ARRAY_SIZE(tas5707_controls),
+	.regmap_config			= &tas5707_regmap_config,
+	.vol_reg_size			= 1,
+};
+
 static const char *const tas5717_supply_names[] = {
 	"AVDD",
 	"DVDD",
@@ -775,6 +883,7 @@ static int tas571x_i2c_remove(struct i2c_client *client)
 }
 
 static const struct of_device_id tas571x_of_match[] = {
+	{ .compatible = "ti,tas5707", .data = &tas5707_chip, },
 	{ .compatible = "ti,tas5711", .data = &tas5711_chip, },
 	{ .compatible = "ti,tas5717", .data = &tas5717_chip, },
 	{ .compatible = "ti,tas5719", .data = &tas5717_chip, },
@@ -784,6 +893,7 @@ static const struct of_device_id tas571x_of_match[] = {
 MODULE_DEVICE_TABLE(of, tas571x_of_match);
 
 static const struct i2c_device_id tas571x_i2c_id[] = {
+	{ "tas5707", (kernel_ulong_t) &tas5707_chip },
 	{ "tas5711", (kernel_ulong_t) &tas5711_chip },
 	{ "tas5717", (kernel_ulong_t) &tas5717_chip },
 	{ "tas5719", (kernel_ulong_t) &tas5717_chip },
diff --git a/sound/soc/codecs/tas571x.h b/sound/soc/codecs/tas571x.h
index c45677bc26ad..bd23e89cfe79 100644
--- a/sound/soc/codecs/tas571x.h
+++ b/sound/soc/codecs/tas571x.h
@@ -53,6 +53,22 @@
 #define TAS571X_PWM_MUX_REG		0x25
 
 /* 20-byte biquad registers */
+#define TAS5707_CH1_BQ0_REG		0x29
+#define TAS5707_CH1_BQ1_REG		0x2a
+#define TAS5707_CH1_BQ2_REG		0x2b
+#define TAS5707_CH1_BQ3_REG		0x2c
+#define TAS5707_CH1_BQ4_REG		0x2d
+#define TAS5707_CH1_BQ5_REG		0x2e
+#define TAS5707_CH1_BQ6_REG		0x2f
+
+#define TAS5707_CH2_BQ0_REG		0x30
+#define TAS5707_CH2_BQ1_REG		0x31
+#define TAS5707_CH2_BQ2_REG		0x32
+#define TAS5707_CH2_BQ3_REG		0x33
+#define TAS5707_CH2_BQ4_REG		0x34
+#define TAS5707_CH2_BQ5_REG		0x35
+#define TAS5707_CH2_BQ6_REG		0x36
+
 #define TAS5717_CH1_BQ0_REG		0x26
 #define TAS5717_CH1_BQ1_REG		0x27
 #define TAS5717_CH1_BQ2_REG		0x28
diff --git a/sound/soc/codecs/tda7419.c b/sound/soc/codecs/tda7419.c
index 225c210ac38f..7f3b79c5a563 100644
--- a/sound/soc/codecs/tda7419.c
+++ b/sound/soc/codecs/tda7419.c
@@ -142,9 +142,9 @@ struct tda7419_vol_control {
 static inline bool tda7419_vol_is_stereo(struct tda7419_vol_control *tvc)
 {
 	if (tvc->reg == tvc->rreg)
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
 
 static int tda7419_vol_info(struct snd_kcontrol *kcontrol,
diff --git a/sound/soc/codecs/tscs42xx.c b/sound/soc/codecs/tscs42xx.c
index d18ff17719cc..7396a6e5277e 100644
--- a/sound/soc/codecs/tscs42xx.c
+++ b/sound/soc/codecs/tscs42xx.c
@@ -625,25 +625,34 @@ static int bytes_info_ext(struct snd_kcontrol *kcontrol,
 
 static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 	/* Volumes */
-	SOC_DOUBLE_R_TLV("Headphone Playback Volume", R_HPVOLL, R_HPVOLR,
+	SOC_DOUBLE_R_TLV("Headphone Volume", R_HPVOLL, R_HPVOLR,
 			FB_HPVOLL, 0x7F, 0, hpvol_scale),
-	SOC_DOUBLE_R_TLV("Speaker Playback Volume", R_SPKVOLL, R_SPKVOLR,
+	SOC_DOUBLE_R_TLV("Speaker Volume", R_SPKVOLL, R_SPKVOLR,
 			FB_SPKVOLL, 0x7F, 0, spkvol_scale),
-	SOC_DOUBLE_R_TLV("Master Playback Volume", R_DACVOLL, R_DACVOLR,
+	SOC_DOUBLE_R_TLV("Master Volume", R_DACVOLL, R_DACVOLR,
 			FB_DACVOLL, 0xFF, 0, dacvol_scale),
-	SOC_DOUBLE_R_TLV("PCM Capture Volume", R_ADCVOLL, R_ADCVOLR,
+	SOC_DOUBLE_R_TLV("PCM Volume", R_ADCVOLL, R_ADCVOLR,
 			FB_ADCVOLL, 0xFF, 0, adcvol_scale),
-	SOC_DOUBLE_R_TLV("Master Capture Volume", R_INVOLL, R_INVOLR,
+	SOC_DOUBLE_R_TLV("Input Volume", R_INVOLL, R_INVOLR,
 			FB_INVOLL, 0x3F, 0, invol_scale),
 
 	/* INSEL */
-	SOC_DOUBLE_R_TLV("Mic Boost Capture Volume", R_INSELL, R_INSELR,
+	SOC_DOUBLE_R_TLV("Mic Boost Volume", R_INSELL, R_INSELR,
 			FB_INSELL_MICBSTL, FV_INSELL_MICBSTL_30DB,
 			0, mic_boost_scale),
 
 	/* Input Channel Map */
 	SOC_ENUM("Input Channel Map", ch_map_select_enum),
 
+	/* Mic Bias */
+	SOC_SINGLE("Mic Bias Boost Switch", 0x71, 0x07, 1, 0),
+
+	/* Headphone Auto Switching */
+	SOC_SINGLE("Headphone Auto Switching Switch",
+			R_CTL, FB_CTL_HPSWEN, 1, 0),
+	SOC_SINGLE("Headphone Detect Polarity Toggle Switch",
+			R_CTL, FB_CTL_HPSWPOL, 1, 0),
+
 	/* Coefficient Ram */
 	COEFF_RAM_CTL("Cascade1L BiQuad1", BIQUAD_SIZE, 0x00),
 	COEFF_RAM_CTL("Cascade1L BiQuad2", BIQUAD_SIZE, 0x05),
@@ -733,9 +742,9 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 		R_CLECTL, FB_CLECTL_LIMIT_EN, 1, 0),
 	SOC_SINGLE("Comp Switch",
 		R_CLECTL, FB_CLECTL_COMP_EN, 1, 0),
-	SOC_SINGLE_TLV("CLE Make-Up Gain Playback Volume",
+	SOC_SINGLE_TLV("CLE Make-Up Gain Volume",
 		R_MUGAIN, FB_MUGAIN_CLEMUG, 0x1f, 0, mugain_scale),
-	SOC_SINGLE_TLV("Comp Thresh Playback Volume",
+	SOC_SINGLE_TLV("Comp Thresh Volume",
 		R_COMPTH, FB_COMPTH, 0xff, 0, compth_scale),
 	SOC_ENUM("Comp Ratio", compressor_ratio_enum),
 	SND_SOC_BYTES("Comp Atk Time", R_CATKTCL, 2),
@@ -766,9 +775,9 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 
 	SOC_SINGLE("MBC1 Phase Invert Switch",
 		R_DACMBCMUG1, FB_DACMBCMUG1_PHASE, 1, 0),
-	SOC_SINGLE_TLV("DAC MBC1 Make-Up Gain Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC1 Make-Up Gain Volume",
 		R_DACMBCMUG1, FB_DACMBCMUG1_MUGAIN, 0x1f, 0, mugain_scale),
-	SOC_SINGLE_TLV("DAC MBC1 Comp Thresh Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC1 Comp Thresh Volume",
 		R_DACMBCTHR1, FB_DACMBCTHR1_THRESH, 0xff, 0, compth_scale),
 	SOC_ENUM("DAC MBC1 Comp Ratio",
 		dac_mbc1_compressor_ratio_enum),
@@ -778,9 +787,9 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 
 	SOC_SINGLE("MBC2 Phase Invert Switch",
 		R_DACMBCMUG2, FB_DACMBCMUG2_PHASE, 1, 0),
-	SOC_SINGLE_TLV("DAC MBC2 Make-Up Gain Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC2 Make-Up Gain Volume",
 		R_DACMBCMUG2, FB_DACMBCMUG2_MUGAIN, 0x1f, 0, mugain_scale),
-	SOC_SINGLE_TLV("DAC MBC2 Comp Thresh Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC2 Comp Thresh Volume",
 		R_DACMBCTHR2, FB_DACMBCTHR2_THRESH, 0xff, 0, compth_scale),
 	SOC_ENUM("DAC MBC2 Comp Ratio",
 		dac_mbc2_compressor_ratio_enum),
@@ -790,9 +799,9 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 
 	SOC_SINGLE("MBC3 Phase Invert Switch",
 		R_DACMBCMUG3, FB_DACMBCMUG3_PHASE, 1, 0),
-	SOC_SINGLE_TLV("DAC MBC3 Make-Up Gain Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC3 Make-Up Gain Volume",
 		R_DACMBCMUG3, FB_DACMBCMUG3_MUGAIN, 0x1f, 0, mugain_scale),
-	SOC_SINGLE_TLV("DAC MBC3 Comp Thresh Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC3 Comp Thresh Volume",
 		R_DACMBCTHR3, FB_DACMBCTHR3_THRESH, 0xff, 0, compth_scale),
 	SOC_ENUM("DAC MBC3 Comp Ratio",
 		dac_mbc3_compressor_ratio_enum),
diff --git a/sound/soc/codecs/tscs42xx.h b/sound/soc/codecs/tscs42xx.h
index 814c8f3c4a68..6b3a21081635 100644
--- a/sound/soc/codecs/tscs42xx.h
+++ b/sound/soc/codecs/tscs42xx.h
@@ -34,6 +34,7 @@ enum {
 #define R_DACSR         0x19
 #define R_PWRM1         0x1A
 #define R_PWRM2         0x1B
+#define R_CTL		0x1C
 #define R_CONFIG0       0x1F
 #define R_CONFIG1       0x20
 #define R_DMICCTL       0x24
@@ -1110,6 +1111,13 @@ enum {
 #define RV_PWRM2_VREF_DISABLE \
 	 RV(FV_PWRM2_VREF_DISABLE, FB_PWRM2_VREF)
 
+/******************************
+ *      R_CTL (0x1C)          *
+ ******************************/
+
+/* Fiel Offsets */
+#define FB_CTL_HPSWEN                        7
+#define FB_CTL_HPSWPOL                       6
 
 /******************************
  *      R_CONFIG0 (0x1F)      *
diff --git a/sound/soc/codecs/twl6040.c b/sound/soc/codecs/twl6040.c
index bfd1abd72253..94675da514c8 100644
--- a/sound/soc/codecs/twl6040.c
+++ b/sound/soc/codecs/twl6040.c
@@ -148,7 +148,7 @@ static bool twl6040_can_write_to_chip(struct snd_soc_component *component,
 	case TWL6040_REG_HFRCTL:
 		return priv->dl2_unmuted;
 	default:
-		return 1;
+		return true;
 	}
 }
 
diff --git a/sound/soc/codecs/wm2200.c b/sound/soc/codecs/wm2200.c
index 3663b9fd4d65..deff65161504 100644
--- a/sound/soc/codecs/wm2200.c
+++ b/sound/soc/codecs/wm2200.c
@@ -1180,6 +1180,9 @@ SOC_DOUBLE_R_TLV("OUT2 Digital Volume", WM2200_DAC_DIGITAL_VOLUME_2L,
 SOC_DOUBLE("OUT2 Switch", WM2200_PDM_1, WM2200_SPK1L_MUTE_SHIFT,
 	   WM2200_SPK1R_MUTE_SHIFT, 1, 1),
 SOC_ENUM("RxANC Src", wm2200_rxanc_input_sel),
+
+WM_ADSP_FW_CONTROL("DSP1", 0),
+WM_ADSP_FW_CONTROL("DSP2", 1),
 };
 
 WM2200_MIXER_ENUMS(OUT1L, WM2200_OUT1LMIX_INPUT_1_SOURCE);
@@ -1553,15 +1556,10 @@ static const struct snd_soc_dapm_route wm2200_dapm_routes[] = {
 static int wm2200_probe(struct snd_soc_component *component)
 {
 	struct wm2200_priv *wm2200 = snd_soc_component_get_drvdata(component);
-	int ret;
 
 	wm2200->component = component;
 
-	ret = snd_soc_add_component_controls(component, wm_adsp_fw_controls, 2);
-	if (ret != 0)
-		return ret;
-
-	return ret;
+	return 0;
 }
 
 static int wm2200_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
diff --git a/sound/soc/codecs/wm5100-tables.c b/sound/soc/codecs/wm5100-tables.c
index e239f4bf2460..9e987cf07450 100644
--- a/sound/soc/codecs/wm5100-tables.c
+++ b/sound/soc/codecs/wm5100-tables.c
@@ -30,7 +30,7 @@ bool wm5100_volatile_register(struct device *dev, unsigned int reg)
 	case WM5100_OUTPUT_STATUS_2:
 	case WM5100_INPUT_ENABLES_STATUS:
 	case WM5100_MIC_DETECT_3:
-		return 1;
+		return true;
 	default:
 		if ((reg >= WM5100_DSP1_PM_0 && reg <= WM5100_DSP1_PM_1535) ||
 		    (reg >= WM5100_DSP1_ZM_0 && reg <= WM5100_DSP1_ZM_2047) ||
@@ -41,9 +41,9 @@ bool wm5100_volatile_register(struct device *dev, unsigned int reg)
 		    (reg >= WM5100_DSP3_PM_0 && reg <= WM5100_DSP3_PM_1535) ||
 		    (reg >= WM5100_DSP3_ZM_0 && reg <= WM5100_DSP3_ZM_2047) ||
 		    (reg >= WM5100_DSP3_DM_0 && reg <= WM5100_DSP3_DM_511))
-			return 1;
+			return true;
 		else
-			return 0;
+			return false;
 	}
 }
 
@@ -798,7 +798,7 @@ bool wm5100_readable_register(struct device *dev, unsigned int reg)
 	case WM5100_DSP3_CONTROL_28:
 	case WM5100_DSP3_CONTROL_29:
 	case WM5100_DSP3_CONTROL_30:
-		return 1;
+		return true;
 	default:
 		if ((reg >= WM5100_DSP1_PM_0 && reg <= WM5100_DSP1_PM_1535) ||
 		    (reg >= WM5100_DSP1_ZM_0 && reg <= WM5100_DSP1_ZM_2047) ||
@@ -809,9 +809,9 @@ bool wm5100_readable_register(struct device *dev, unsigned int reg)
 		    (reg >= WM5100_DSP3_PM_0 && reg <= WM5100_DSP3_PM_1535) ||
 		    (reg >= WM5100_DSP3_ZM_0 && reg <= WM5100_DSP3_ZM_2047) ||
 		    (reg >= WM5100_DSP3_DM_0 && reg <= WM5100_DSP3_DM_511))
-			return 1;
+			return true;
 		else
-			return 0;
+			return false;
 	}
 }
 
diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c
index 1ac83388d1b8..7e817e1877c2 100644
--- a/sound/soc/codecs/wm5102.c
+++ b/sound/soc/codecs/wm5102.c
@@ -985,6 +985,8 @@ ARIZONA_MIXER_CONTROLS("SLIMTX5", ARIZONA_SLIMTX5MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX6", ARIZONA_SLIMTX6MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX7", ARIZONA_SLIMTX7MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX8", ARIZONA_SLIMTX8MIX_INPUT_1_SOURCE),
+
+WM_ADSP_FW_CONTROL("DSP1", 0),
 };
 
 ARIZONA_MIXER_ENUMS(EQ1, ARIZONA_EQ1MIX_INPUT_1_SOURCE);
@@ -2094,6 +2096,12 @@ static int wm5102_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 1);
+	if (ret != 0)
+		dev_warn(&pdev->dev,
+			 "Failed to set compressed IRQ as a wake source: %d\n",
+			 ret);
+
 	arizona_init_common(arizona);
 
 	ret = arizona_init_vol_limit(arizona);
@@ -2117,6 +2125,7 @@ static int wm5102_probe(struct platform_device *pdev)
 err_spk_irqs:
 	arizona_free_spk_irqs(arizona);
 err_dsp_irq:
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5102);
 
 	return ret;
@@ -2133,6 +2142,7 @@ static int wm5102_remove(struct platform_device *pdev)
 
 	arizona_free_spk_irqs(arizona);
 
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5102);
 
 	return 0;
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index fb9835dcd836..b0789a03d699 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -927,6 +927,11 @@ ARIZONA_MIXER_CONTROLS("SLIMTX5", ARIZONA_SLIMTX5MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX6", ARIZONA_SLIMTX6MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX7", ARIZONA_SLIMTX7MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX8", ARIZONA_SLIMTX8MIX_INPUT_1_SOURCE),
+
+WM_ADSP_FW_CONTROL("DSP1", 0),
+WM_ADSP_FW_CONTROL("DSP2", 1),
+WM_ADSP_FW_CONTROL("DSP3", 2),
+WM_ADSP_FW_CONTROL("DSP4", 3),
 };
 
 ARIZONA_MIXER_ENUMS(EQ1, ARIZONA_EQ1MIX_INPUT_1_SOURCE);
@@ -2455,6 +2460,12 @@ static int wm5110_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 1);
+	if (ret != 0)
+		dev_warn(&pdev->dev,
+			 "Failed to set compressed IRQ as a wake source: %d\n",
+			 ret);
+
 	arizona_init_common(arizona);
 
 	ret = arizona_init_vol_limit(arizona);
@@ -2478,6 +2489,7 @@ static int wm5110_probe(struct platform_device *pdev)
 err_spk_irqs:
 	arizona_free_spk_irqs(arizona);
 err_dsp_irq:
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5110);
 
 	return ret;
@@ -2496,6 +2508,7 @@ static int wm5110_remove(struct platform_device *pdev)
 
 	arizona_free_spk_irqs(arizona);
 
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5110);
 
 	return 0;
diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c
index 7b8b6ef2f632..6cb3c153ba19 100644
--- a/sound/soc/codecs/wm8903.c
+++ b/sound/soc/codecs/wm8903.c
@@ -251,10 +251,10 @@ static bool wm8903_volatile_register(struct device *dev, unsigned int reg)
 	case WM8903_DC_SERVO_READBACK_2:
 	case WM8903_DC_SERVO_READBACK_3:
 	case WM8903_DC_SERVO_READBACK_4:
-		return 1;
+		return true;
 
 	default:
-		return 0;
+		return false;
 	}
 }
 
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 9037a35b931d..1965635ec07c 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -1455,6 +1455,7 @@ static int wm8904_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif1 |= 0x3 | WM8904_AIF_LRCLK_INV;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif1 |= 0x3;
 		break;
diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c
index ba44e3d6c1e0..cd204f79647d 100644
--- a/sound/soc/codecs/wm8955.c
+++ b/sound/soc/codecs/wm8955.c
@@ -686,6 +686,7 @@ static int wm8955_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif |= WM8955_LRP;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif |= 0x3;
 		break;
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index c30f5aa392c6..8dc1f3d6a988 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -839,6 +839,7 @@ static int wm8960_hw_params(struct snd_pcm_substream *substream,
 			iface |= 0x000c;
 			break;
 		}
+		/* fall through */
 	default:
 		dev_err(component->dev, "unsupported width %d\n",
 			params_width(params));
diff --git a/sound/soc/codecs/wm8961.c b/sound/soc/codecs/wm8961.c
index f70f563d59f3..68b4cadc308f 100644
--- a/sound/soc/codecs/wm8961.c
+++ b/sound/soc/codecs/wm8961.c
@@ -653,6 +653,7 @@ static int wm8961_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 
 	case SND_SOC_DAIFMT_DSP_B:
 		aif |= WM8961_LRP;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif |= 3;
 		switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index a11e9d6bf950..efd8910b1ff7 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -2649,6 +2649,7 @@ static int wm8962_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif0 |= WM8962_LRCLK_INV | 3;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif0 |= 3;
 
diff --git a/sound/soc/codecs/wm8988.c b/sound/soc/codecs/wm8988.c
index 62200117444b..6e52c6a8bab3 100644
--- a/sound/soc/codecs/wm8988.c
+++ b/sound/soc/codecs/wm8988.c
@@ -522,7 +522,7 @@ static inline int get_coeff(int mclk, int rate)
 /* The set of rates we can generate from the above for each SYSCLK */
 
 static const unsigned int rates_12288[] = {
-	8000, 12000, 16000, 24000, 24000, 32000, 48000, 96000,
+	8000, 12000, 16000, 24000, 32000, 48000, 96000,
 };
 
 static const struct snd_pcm_hw_constraint_list constraints_12288 = {
@@ -540,7 +540,7 @@ static const struct snd_pcm_hw_constraint_list constraints_112896 = {
 };
 
 static const unsigned int rates_12[] = {
-	8000, 11025, 12000, 16000, 22050, 2400, 32000, 41100, 48000,
+	8000, 11025, 12000, 16000, 22050, 24000, 32000, 41100, 48000,
 	48000, 88235, 96000,
 };
 
diff --git a/sound/soc/codecs/wm8990.c b/sound/soc/codecs/wm8990.c
index 411b9eee88c2..457bc437ce54 100644
--- a/sound/soc/codecs/wm8990.c
+++ b/sound/soc/codecs/wm8990.c
@@ -40,9 +40,9 @@ static bool wm8990_volatile_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
 	case WM8990_RESET:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 7fdfdf3f6e67..14f1b0c0d286 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -2432,6 +2432,7 @@ static int wm8994_set_dai_sysclk(struct snd_soc_dai *dai,
 			snd_soc_component_update_bits(component, WM8994_POWER_MANAGEMENT_2,
 					    WM8994_OPCLK_ENA, 0);
 		}
+		break;
 
 	default:
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8995.c b/sound/soc/codecs/wm8995.c
index 60e227832331..68c99fe37097 100644
--- a/sound/soc/codecs/wm8995.c
+++ b/sound/soc/codecs/wm8995.c
@@ -1465,6 +1465,7 @@ static int wm8995_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif |= WM8995_AIF1_LRCLK_INV;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif |= (0x3 << WM8995_AIF1_FMT_SHIFT);
 		break;
diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c
index d9d206046f8c..91711f8958c5 100644
--- a/sound/soc/codecs/wm8996.c
+++ b/sound/soc/codecs/wm8996.c
@@ -1498,9 +1498,9 @@ static bool wm8996_readable_register(struct device *dev, unsigned int reg)
 	case WM8996_RIGHT_PDM_SPEAKER:
 	case WM8996_PDM_SPEAKER_MUTE_SEQUENCE:
 	case WM8996_PDM_SPEAKER_VOLUME:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -1522,9 +1522,9 @@ static bool wm8996_volatile_register(struct device *dev, unsigned int reg)
 	case WM8996_MIC_DETECT_3:
 	case WM8996_HEADPHONE_DETECT_1:
 	case WM8996_HEADPHONE_DETECT_2:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -1858,6 +1858,7 @@ static int wm8996_set_sysclk(struct snd_soc_dai *dai,
 	case 24576000:
 		ratediv = WM8996_SYSCLK_DIV;
 		wm8996->sysclk /= 2;
+		/* fall through */
 	case 11289600:
 	case 12288000:
 		snd_soc_component_update_bits(component, WM8996_AIF_RATE,
diff --git a/sound/soc/codecs/wm9081.c b/sound/soc/codecs/wm9081.c
index 5a0ea7b3c149..399255d1f78a 100644
--- a/sound/soc/codecs/wm9081.c
+++ b/sound/soc/codecs/wm9081.c
@@ -933,6 +933,7 @@ static int wm9081_set_dai_fmt(struct snd_soc_dai *dai,
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif2 |= WM9081_AIF_LRCLK_INV;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif2 |= 0x3;
 		break;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 2fcdd84021a5..f61656070225 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/ctype.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
@@ -35,15 +36,15 @@
 #include "wm_adsp.h"
 
 #define adsp_crit(_dsp, fmt, ...) \
-	dev_crit(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_crit(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 #define adsp_err(_dsp, fmt, ...) \
-	dev_err(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_err(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 #define adsp_warn(_dsp, fmt, ...) \
-	dev_warn(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_warn(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 #define adsp_info(_dsp, fmt, ...) \
-	dev_info(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_info(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 #define adsp_dbg(_dsp, fmt, ...) \
-	dev_dbg(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_dbg(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 
 #define ADSP1_CONTROL_1                   0x00
 #define ADSP1_CONTROL_2                   0x02
@@ -418,7 +419,7 @@ static const struct wm_adsp_fw_caps ctrl_caps[] = {
 	{
 		.id = SND_AUDIOCODEC_BESPOKE,
 		.desc = {
-			.max_ch = 1,
+			.max_ch = 8,
 			.sample_rates = { 16000 },
 			.num_sample_rates = 1,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
@@ -608,7 +609,6 @@ static void wm_adsp2_init_debugfs(struct wm_adsp *dsp,
 				  struct snd_soc_component *component)
 {
 	struct dentry *root = NULL;
-	char *root_name;
 	int i;
 
 	if (!component->debugfs_root) {
@@ -616,13 +616,7 @@ static void wm_adsp2_init_debugfs(struct wm_adsp *dsp,
 		goto err;
 	}
 
-	root_name = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!root_name)
-		goto err;
-
-	snprintf(root_name, PAGE_SIZE, "dsp%d", dsp->num);
-	root = debugfs_create_dir(root_name, component->debugfs_root);
-	kfree(root_name);
+	root = debugfs_create_dir(dsp->name, component->debugfs_root);
 
 	if (!root)
 		goto err;
@@ -684,8 +678,8 @@ static inline void wm_adsp_debugfs_clear(struct wm_adsp *dsp)
 }
 #endif
 
-static int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
-			  struct snd_ctl_elem_value *ucontrol)
+int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
+		   struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
@@ -695,9 +689,10 @@ static int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(wm_adsp_fw_get);
 
-static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
-			  struct snd_ctl_elem_value *ucontrol)
+int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
+		   struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
@@ -721,8 +716,9 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(wm_adsp_fw_put);
 
-static const struct soc_enum wm_adsp_fw_enum[] = {
+const struct soc_enum wm_adsp_fw_enum[] = {
 	SOC_ENUM_SINGLE(0, 0, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
 	SOC_ENUM_SINGLE(0, 1, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
 	SOC_ENUM_SINGLE(0, 2, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
@@ -731,24 +727,7 @@ static const struct soc_enum wm_adsp_fw_enum[] = {
 	SOC_ENUM_SINGLE(0, 5, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
 	SOC_ENUM_SINGLE(0, 6, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
 };
-
-const struct snd_kcontrol_new wm_adsp_fw_controls[] = {
-	SOC_ENUM_EXT("DSP1 Firmware", wm_adsp_fw_enum[0],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP2 Firmware", wm_adsp_fw_enum[1],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP3 Firmware", wm_adsp_fw_enum[2],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP4 Firmware", wm_adsp_fw_enum[3],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP5 Firmware", wm_adsp_fw_enum[4],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP6 Firmware", wm_adsp_fw_enum[5],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP7 Firmware", wm_adsp_fw_enum[6],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-};
-EXPORT_SYMBOL_GPL(wm_adsp_fw_controls);
+EXPORT_SYMBOL_GPL(wm_adsp_fw_enum);
 
 static struct wm_adsp_region const *wm_adsp_find_region(struct wm_adsp *dsp,
 							int type)
@@ -1330,12 +1309,12 @@ static int wm_adsp_create_control(struct wm_adsp *dsp,
 	switch (dsp->fw_ver) {
 	case 0:
 	case 1:
-		snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "DSP%d %s %x",
-			 dsp->num, region_name, alg_region->alg);
+		snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s %x",
+			 dsp->name, region_name, alg_region->alg);
 		break;
 	default:
 		ret = snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN,
-				"DSP%d%c %.12s %x", dsp->num, *region_name,
+				"%s%c %.12s %x", dsp->name, *region_name,
 				wm_adsp_fw_text[dsp->fw], alg_region->alg);
 
 		/* Truncate the subname from the start if it is too long */
@@ -1343,6 +1322,9 @@ static int wm_adsp_create_control(struct wm_adsp *dsp,
 			int avail = SNDRV_CTL_ELEM_ID_NAME_MAXLEN - ret - 2;
 			int skip = 0;
 
+			if (dsp->component->name_prefix)
+				avail -= strlen(dsp->component->name_prefix) + 1;
+
 			if (subname_len > avail)
 				skip = subname_len - avail;
 
@@ -1604,6 +1586,15 @@ static int wm_adsp_parse_coeff(struct wm_adsp *dsp,
 			if (ret)
 				return -EINVAL;
 			break;
+		case WMFW_CTL_TYPE_HOST_BUFFER:
+			ret = wm_adsp_check_coeff_flags(dsp, &coeff_blk,
+						WMFW_CTL_FLAG_SYS |
+						WMFW_CTL_FLAG_VOLATILE |
+						WMFW_CTL_FLAG_READABLE,
+						0);
+			if (ret)
+				return -EINVAL;
+			break;
 		default:
 			adsp_err(dsp, "Unknown control type: %d\n",
 				 coeff_blk.ctl_type);
@@ -1651,7 +1642,7 @@ static int wm_adsp_load(struct wm_adsp *dsp)
 	if (file == NULL)
 		return -ENOMEM;
 
-	snprintf(file, PAGE_SIZE, "%s-dsp%d-%s.wmfw", dsp->part, dsp->num,
+	snprintf(file, PAGE_SIZE, "%s-%s-%s.wmfw", dsp->part, dsp->fwf_name,
 		 wm_adsp_fw[dsp->fw].file);
 	file[PAGE_SIZE - 1] = '\0';
 
@@ -1871,9 +1862,11 @@ static void wm_adsp_ctl_fixup_base(struct wm_adsp *dsp,
 }
 
 static void *wm_adsp_read_algs(struct wm_adsp *dsp, size_t n_algs,
+			       const struct wm_adsp_region *mem,
 			       unsigned int pos, unsigned int len)
 {
 	void *alg;
+	unsigned int reg;
 	int ret;
 	__be32 val;
 
@@ -1888,7 +1881,9 @@ static void *wm_adsp_read_algs(struct wm_adsp *dsp, size_t n_algs,
 	}
 
 	/* Read the terminator first to validate the length */
-	ret = regmap_raw_read(dsp->regmap, pos + len, &val, sizeof(val));
+	reg = wm_adsp_region_to_reg(mem, pos + len);
+
+	ret = regmap_raw_read(dsp->regmap, reg, &val, sizeof(val));
 	if (ret != 0) {
 		adsp_err(dsp, "Failed to read algorithm list end: %d\n",
 			ret);
@@ -1897,13 +1892,18 @@ static void *wm_adsp_read_algs(struct wm_adsp *dsp, size_t n_algs,
 
 	if (be32_to_cpu(val) != 0xbedead)
 		adsp_warn(dsp, "Algorithm list end %x 0x%x != 0xbedead\n",
-			  pos + len, be32_to_cpu(val));
+			  reg, be32_to_cpu(val));
+
+	/* Convert length from DSP words to bytes */
+	len *= sizeof(u32);
 
-	alg = kcalloc(len, 2, GFP_KERNEL | GFP_DMA);
+	alg = kzalloc(len, GFP_KERNEL | GFP_DMA);
 	if (!alg)
 		return ERR_PTR(-ENOMEM);
 
-	ret = regmap_raw_read(dsp->regmap, pos, alg, len * 2);
+	reg = wm_adsp_region_to_reg(mem, pos);
+
+	ret = regmap_raw_read(dsp->regmap, reg, alg, len);
 	if (ret != 0) {
 		adsp_err(dsp, "Failed to read algorithm list: %d\n", ret);
 		kfree(alg);
@@ -2002,10 +2002,11 @@ static int wm_adsp1_setup_algs(struct wm_adsp *dsp)
 	if (IS_ERR(alg_region))
 		return PTR_ERR(alg_region);
 
-	pos = sizeof(adsp1_id) / 2;
-	len = (sizeof(*adsp1_alg) * n_algs) / 2;
+	/* Calculate offset and length in DSP words */
+	pos = sizeof(adsp1_id) / sizeof(u32);
+	len = (sizeof(*adsp1_alg) * n_algs) / sizeof(u32);
 
-	adsp1_alg = wm_adsp_read_algs(dsp, n_algs, mem->base + pos, len);
+	adsp1_alg = wm_adsp_read_algs(dsp, n_algs, mem, pos, len);
 	if (IS_ERR(adsp1_alg))
 		return PTR_ERR(adsp1_alg);
 
@@ -2113,10 +2114,11 @@ static int wm_adsp2_setup_algs(struct wm_adsp *dsp)
 	if (IS_ERR(alg_region))
 		return PTR_ERR(alg_region);
 
-	pos = sizeof(adsp2_id) / 2;
-	len = (sizeof(*adsp2_alg) * n_algs) / 2;
+	/* Calculate offset and length in DSP words */
+	pos = sizeof(adsp2_id) / sizeof(u32);
+	len = (sizeof(*adsp2_alg) * n_algs) / sizeof(u32);
 
-	adsp2_alg = wm_adsp_read_algs(dsp, n_algs, mem->base + pos, len);
+	adsp2_alg = wm_adsp_read_algs(dsp, n_algs, mem, pos, len);
 	if (IS_ERR(adsp2_alg))
 		return PTR_ERR(adsp2_alg);
 
@@ -2218,7 +2220,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
 	if (file == NULL)
 		return -ENOMEM;
 
-	snprintf(file, PAGE_SIZE, "%s-dsp%d-%s.bin", dsp->part, dsp->num,
+	snprintf(file, PAGE_SIZE, "%s-%s-%s.bin", dsp->part, dsp->fwf_name,
 		 wm_adsp_fw[dsp->fw].file);
 	file[PAGE_SIZE - 1] = '\0';
 
@@ -2390,8 +2392,38 @@ out:
 	return ret;
 }
 
+static int wm_adsp_create_name(struct wm_adsp *dsp)
+{
+	char *p;
+
+	if (!dsp->name) {
+		dsp->name = devm_kasprintf(dsp->dev, GFP_KERNEL, "DSP%d",
+					   dsp->num);
+		if (!dsp->name)
+			return -ENOMEM;
+	}
+
+	if (!dsp->fwf_name) {
+		p = devm_kstrdup(dsp->dev, dsp->name, GFP_KERNEL);
+		if (!p)
+			return -ENOMEM;
+
+		dsp->fwf_name = p;
+		for (; *p != 0; ++p)
+			*p = tolower(*p);
+	}
+
+	return 0;
+}
+
 int wm_adsp1_init(struct wm_adsp *dsp)
 {
+	int ret;
+
+	ret = wm_adsp_create_name(dsp);
+	if (ret)
+		return ret;
+
 	INIT_LIST_HEAD(&dsp->alg_regions);
 
 	mutex_init(&dsp->pwr_lock);
@@ -2642,7 +2674,10 @@ int wm_adsp2_preloader_get(struct snd_kcontrol *kcontrol,
 			   struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct wm_adsp *dsp = snd_soc_component_get_drvdata(component);
+	struct wm_adsp *dsps = snd_soc_component_get_drvdata(component);
+	struct soc_mixer_control *mc =
+		(struct soc_mixer_control *)kcontrol->private_value;
+	struct wm_adsp *dsp = &dsps[mc->shift - 1];
 
 	ucontrol->value.integer.value[0] = dsp->preloaded;
 
@@ -2654,13 +2689,14 @@ int wm_adsp2_preloader_put(struct snd_kcontrol *kcontrol,
 			   struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct wm_adsp *dsp = snd_soc_component_get_drvdata(component);
+	struct wm_adsp *dsps = snd_soc_component_get_drvdata(component);
 	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
 	struct soc_mixer_control *mc =
 		(struct soc_mixer_control *)kcontrol->private_value;
+	struct wm_adsp *dsp = &dsps[mc->shift - 1];
 	char preload[32];
 
-	snprintf(preload, ARRAY_SIZE(preload), "DSP%u Preload", mc->shift);
+	snprintf(preload, ARRAY_SIZE(preload), "%s Preload", dsp->name);
 
 	dsp->preloaded = ucontrol->value.integer.value[0];
 
@@ -2671,6 +2707,8 @@ int wm_adsp2_preloader_put(struct snd_kcontrol *kcontrol,
 
 	snd_soc_dapm_sync(dapm);
 
+	flush_work(&dsp->boot_work);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(wm_adsp2_preloader_put);
@@ -2853,17 +2891,14 @@ int wm_adsp2_component_probe(struct wm_adsp *dsp, struct snd_soc_component *comp
 {
 	char preload[32];
 
-	snprintf(preload, ARRAY_SIZE(preload), "DSP%d Preload", dsp->num);
-
+	snprintf(preload, ARRAY_SIZE(preload), "%s Preload", dsp->name);
 	snd_soc_component_disable_pin(component, preload);
 
 	wm_adsp2_init_debugfs(dsp, component);
 
 	dsp->component = component;
 
-	return snd_soc_add_component_controls(component,
-					  &wm_adsp_fw_controls[dsp->num - 1],
-					  1);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(wm_adsp2_component_probe);
 
@@ -2879,6 +2914,10 @@ int wm_adsp2_init(struct wm_adsp *dsp)
 {
 	int ret;
 
+	ret = wm_adsp_create_name(dsp);
+	if (ret)
+		return ret;
+
 	switch (dsp->rev) {
 	case 0:
 		/*
@@ -3186,7 +3225,7 @@ static inline int wm_adsp_buffer_write(struct wm_adsp_compr_buf *buf,
 				       buf->host_buf_ptr + field_offset, data);
 }
 
-static int wm_adsp_buffer_locate(struct wm_adsp_compr_buf *buf)
+static int wm_adsp_legacy_host_buf_addr(struct wm_adsp_compr_buf *buf)
 {
 	struct wm_adsp_alg_region *alg_region;
 	struct wm_adsp *dsp = buf->dsp;
@@ -3225,6 +3264,61 @@ static int wm_adsp_buffer_locate(struct wm_adsp_compr_buf *buf)
 	return 0;
 }
 
+static struct wm_coeff_ctl *
+wm_adsp_find_host_buffer_ctrl(struct wm_adsp_compr_buf *buf)
+{
+	struct wm_adsp *dsp = buf->dsp;
+	struct wm_coeff_ctl *ctl;
+
+	list_for_each_entry(ctl, &dsp->ctl_list, list) {
+		if (ctl->type != WMFW_CTL_TYPE_HOST_BUFFER)
+			continue;
+
+		if (!ctl->enabled)
+			continue;
+
+		return ctl;
+	}
+
+	return NULL;
+}
+
+static int wm_adsp_buffer_locate(struct wm_adsp_compr_buf *buf)
+{
+	struct wm_adsp *dsp = buf->dsp;
+	struct wm_coeff_ctl *ctl;
+	unsigned int reg;
+	u32 val;
+	int i, ret;
+
+	ctl = wm_adsp_find_host_buffer_ctrl(buf);
+	if (!ctl)
+		return wm_adsp_legacy_host_buf_addr(buf);
+
+	ret = wm_coeff_base_reg(ctl, &reg);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 5; ++i) {
+		ret = regmap_raw_read(dsp->regmap, reg, &val, sizeof(val));
+		if (ret < 0)
+			return ret;
+
+		if (val)
+			break;
+
+		usleep_range(1000, 2000);
+	}
+
+	if (!val)
+		return -EIO;
+
+	buf->host_buf_ptr = be32_to_cpu(val);
+	adsp_dbg(dsp, "host_buf_ptr=%x\n", buf->host_buf_ptr);
+
+	return 0;
+}
+
 static int wm_adsp_buffer_populate(struct wm_adsp_compr_buf *buf)
 {
 	const struct wm_adsp_fw_caps *caps = wm_adsp_fw[buf->dsp->fw].caps;
diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h
index bc6d359f0533..4b8778b0b06c 100644
--- a/sound/soc/codecs/wm_adsp.h
+++ b/sound/soc/codecs/wm_adsp.h
@@ -57,6 +57,8 @@ struct wm_adsp_compr_buf;
 
 struct wm_adsp {
 	const char *part;
+	const char *name;
+	const char *fwf_name;
 	int rev;
 	int num;
 	int type;
@@ -121,7 +123,11 @@ struct wm_adsp {
 	.reg = SND_SOC_NOPM, .shift = num, .event = wm_adsp2_event, \
 	.event_flags = SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD }
 
-extern const struct snd_kcontrol_new wm_adsp_fw_controls[];
+#define WM_ADSP_FW_CONTROL(dspname, num) \
+	SOC_ENUM_EXT(dspname " Firmware", wm_adsp_fw_enum[num], \
+		     wm_adsp_fw_get, wm_adsp_fw_put)
+
+extern const struct soc_enum wm_adsp_fw_enum[];
 
 int wm_adsp1_init(struct wm_adsp *dsp);
 int wm_adsp2_init(struct wm_adsp *dsp);
@@ -144,6 +150,10 @@ int wm_adsp2_preloader_get(struct snd_kcontrol *kcontrol,
 			   struct snd_ctl_elem_value *ucontrol);
 int wm_adsp2_preloader_put(struct snd_kcontrol *kcontrol,
 			   struct snd_ctl_elem_value *ucontrol);
+int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
+		   struct snd_ctl_elem_value *ucontrol);
+int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
+		   struct snd_ctl_elem_value *ucontrol);
 
 int wm_adsp_compr_open(struct wm_adsp *dsp, struct snd_compr_stream *stream);
 int wm_adsp_compr_free(struct snd_compr_stream *stream);
diff --git a/sound/soc/codecs/wmfw.h b/sound/soc/codecs/wmfw.h
index ec78b9da020f..0c3f50acb8b1 100644
--- a/sound/soc/codecs/wmfw.h
+++ b/sound/soc/codecs/wmfw.h
@@ -29,6 +29,7 @@
 /* Non-ALSA coefficient types start at 0x1000 */
 #define WMFW_CTL_TYPE_ACKED       0x1000 /* acked control */
 #define WMFW_CTL_TYPE_HOSTEVENT   0x1001 /* event control */
+#define WMFW_CTL_TYPE_HOST_BUFFER 0x1002 /* host buffer pointer */
 
 struct wmfw_header {
 	char magic[4];
diff --git a/sound/soc/davinci/davinci-i2s.c b/sound/soc/davinci/davinci-i2s.c
index 807040bb3921..a3206e65e5e5 100644
--- a/sound/soc/davinci/davinci-i2s.c
+++ b/sound/soc/davinci/davinci-i2s.c
@@ -340,6 +340,7 @@ static int davinci_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 		 * rate is lowered.
 		 */
 		inv_fs = true;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		dev->mode = MOD_DSP_A;
 		break;
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 47c0c821d325..f70db8412c7c 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -320,12 +320,8 @@ static irqreturn_t davinci_mcasp_tx_irq_handler(int irq, void *data)
 		handled_mask |= XUNDRN;
 
 		substream = mcasp->substreams[SNDRV_PCM_STREAM_PLAYBACK];
-		if (substream) {
-			snd_pcm_stream_lock_irq(substream);
-			if (snd_pcm_running(substream))
-				snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
-			snd_pcm_stream_unlock_irq(substream);
-		}
+		if (substream)
+			snd_pcm_stop_xrun(substream);
 	}
 
 	if (!handled_mask)
@@ -355,12 +351,8 @@ static irqreturn_t davinci_mcasp_rx_irq_handler(int irq, void *data)
 		handled_mask |= ROVRN;
 
 		substream = mcasp->substreams[SNDRV_PCM_STREAM_CAPTURE];
-		if (substream) {
-			snd_pcm_stream_lock_irq(substream);
-			if (snd_pcm_running(substream))
-				snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
-			snd_pcm_stream_unlock_irq(substream);
-		}
+		if (substream)
+			snd_pcm_stop_xrun(substream);
 	}
 
 	if (!handled_mask)
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index 4a6750aa3637..44433b20435c 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -1,14 +1,10 @@
-/*
- * Freescale Generic ASoC Sound Card driver with ASRC
- *
- * Copyright (C) 2014 Freescale Semiconductor, Inc.
- *
- * Author: Nicolin Chen <nicoleotsuka@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale Generic ASoC Sound Card driver with ASRC
+//
+// Copyright (C) 2014 Freescale Semiconductor, Inc.
+//
+// Author: Nicolin Chen <nicoleotsuka@gmail.com>
 
 #include <linux/clk.h>
 #include <linux/i2c.h>
@@ -199,7 +195,7 @@ static int be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	mask = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
 	snd_mask_none(mask);
-	snd_mask_set(mask, (__force int)priv->asrc_format);
+	snd_mask_set_format(mask, priv->asrc_format);
 
 	return 0;
 }
diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c
index adfb8135d739..528e8b108422 100644
--- a/sound/soc/fsl/fsl_asrc.c
+++ b/sound/soc/fsl/fsl_asrc.c
@@ -1,14 +1,10 @@
-/*
- * Freescale ASRC ALSA SoC Digital Audio Interface (DAI) driver
- *
- * Copyright (C) 2014 Freescale Semiconductor, Inc.
- *
- * Author: Nicolin Chen <nicoleotsuka@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale ASRC ALSA SoC Digital Audio Interface (DAI) driver
+//
+// Copyright (C) 2014 Freescale Semiconductor, Inc.
+//
+// Author: Nicolin Chen <nicoleotsuka@gmail.com>
 
 #include <linux/clk.h>
 #include <linux/delay.h>
diff --git a/sound/soc/fsl/fsl_asrc.h b/sound/soc/fsl/fsl_asrc.h
index d558dd5499a5..c60075112570 100644
--- a/sound/soc/fsl/fsl_asrc.h
+++ b/sound/soc/fsl/fsl_asrc.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * fsl_asrc.h - Freescale ASRC ALSA SoC header file
  *
  * Copyright (C) 2014 Freescale Semiconductor, Inc.
  *
  * Author: Nicolin Chen <nicoleotsuka@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #ifndef _FSL_ASRC_H
diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c
index 565e16d8fe85..1033ac6631b0 100644
--- a/sound/soc/fsl/fsl_asrc_dma.c
+++ b/sound/soc/fsl/fsl_asrc_dma.c
@@ -1,14 +1,10 @@
-/*
- * Freescale ASRC ALSA SoC Platform (DMA) driver
- *
- * Copyright (C) 2014 Freescale Semiconductor, Inc.
- *
- * Author: Nicolin Chen <nicoleotsuka@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale ASRC ALSA SoC Platform (DMA) driver
+//
+// Copyright (C) 2014 Freescale Semiconductor, Inc.
+//
+// Author: Nicolin Chen <nicoleotsuka@gmail.com>
 
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index 8f43110373b8..c1d1d06783e5 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -249,6 +249,7 @@ static int fsl_esai_set_dai_sysclk(struct snd_soc_dai *dai, int clk_id,
 		break;
 	case ESAI_HCKT_EXTAL:
 		ecr |= ESAI_ECR_ETI;
+		/* fall through */
 	case ESAI_HCKR_EXTAL:
 		ecr |= ESAI_ECR_ERI;
 		break;
diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c
index 9b59d87b61bf..740b90df44bb 100644
--- a/sound/soc/fsl/fsl_spdif.c
+++ b/sound/soc/fsl/fsl_spdif.c
@@ -1118,7 +1118,7 @@ static u32 fsl_spdif_txclk_caldiv(struct fsl_spdif_priv *spdif_priv,
 
 	for (sysclk_df = sysclk_dfmin; sysclk_df <= sysclk_dfmax; sysclk_df++) {
 		for (txclk_df = 1; txclk_df <= 128; txclk_df++) {
-			rate_ideal = rate[index] * txclk_df * 64;
+			rate_ideal = rate[index] * txclk_df * 64ULL;
 			if (round)
 				rate_actual = clk_round_rate(clk, rate_ideal);
 			else
diff --git a/sound/soc/fsl/fsl_utils.c b/sound/soc/fsl/fsl_utils.c
index 7592b0406370..7f0fa4b52223 100644
--- a/sound/soc/fsl/fsl_utils.c
+++ b/sound/soc/fsl/fsl_utils.c
@@ -1,14 +1,10 @@
-/**
- * Freescale ALSA SoC Machine driver utility
- *
- * Author: Timur Tabi <timur@freescale.com>
- *
- * Copyright 2010 Freescale Semiconductor, Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale ALSA SoC Machine driver utility
+//
+// Author: Timur Tabi <timur@freescale.com>
+//
+// Copyright 2010 Freescale Semiconductor, Inc.
 
 #include <linux/module.h>
 #include <linux/of_address.h>
diff --git a/sound/soc/fsl/fsl_utils.h b/sound/soc/fsl/fsl_utils.h
index 1687b66ef18e..c5dc2a14b492 100644
--- a/sound/soc/fsl/fsl_utils.h
+++ b/sound/soc/fsl/fsl_utils.h
@@ -1,13 +1,10 @@
-/**
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Freescale ALSA SoC Machine driver utility
  *
  * Author: Timur Tabi <timur@freescale.com>
  *
  * Copyright 2010 Freescale Semiconductor, Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #ifndef _FSL_UTILS_H
diff --git a/sound/soc/fsl/imx-sgtl5000.c b/sound/soc/fsl/imx-sgtl5000.c
index b99e0b5e00e9..c29200cf755a 100644
--- a/sound/soc/fsl/imx-sgtl5000.c
+++ b/sound/soc/fsl/imx-sgtl5000.c
@@ -1,14 +1,7 @@
-/*
- * Copyright 2012 Freescale Semiconductor, Inc.
- * Copyright 2012 Linaro Ltd.
- *
- * The code contained herein is licensed under the GNU General Public
- * License. You may obtain a copy of the GNU General Public License
- * Version 2 or later at the following locations:
- *
- * http://www.opensource.org/licenses/gpl-license.html
- * http://www.gnu.org/copyleft/gpl.html
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2012 Freescale Semiconductor, Inc.
+// Copyright 2012 Linaro Ltd.
 
 #include <linux/module.h>
 #include <linux/of.h>
diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c
index d93bacacbd5b..2094d2c8919f 100644
--- a/sound/soc/generic/audio-graph-card.c
+++ b/sound/soc/generic/audio-graph-card.c
@@ -1,15 +1,12 @@
-/*
- * ASoC audio graph sound card support
- *
- * Copyright (C) 2016 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * based on ${LINUX}/sound/soc/generic/simple-card.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ASoC audio graph sound card support
+//
+// Copyright (C) 2016 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// based on ${LINUX}/sound/soc/generic/simple-card.c
+
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/gpio.h>
@@ -21,7 +18,6 @@
 #include <linux/of_graph.h>
 #include <linux/platform_device.h>
 #include <linux/string.h>
-#include <sound/jack.h>
 #include <sound/simple_card_utils.h>
 
 struct graph_card_data {
@@ -32,6 +28,8 @@ struct graph_card_data {
 		unsigned int mclk_fs;
 	} *dai_props;
 	unsigned int mclk_fs;
+	struct asoc_simple_jack hp_jack;
+	struct asoc_simple_jack mic_jack;
 	struct snd_soc_dai_link *dai_link;
 	struct gpio_desc *pa_gpio;
 };
@@ -278,6 +276,22 @@ static int asoc_graph_get_dais_count(struct device *dev)
 	return count;
 }
 
+static int asoc_graph_soc_card_probe(struct snd_soc_card *card)
+{
+	struct graph_card_data *priv = snd_soc_card_get_drvdata(card);
+	int ret;
+
+	ret = asoc_simple_card_init_hp(card, &priv->hp_jack, NULL);
+	if (ret < 0)
+		return ret;
+
+	ret = asoc_simple_card_init_mic(card, &priv->mic_jack, NULL);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int asoc_graph_card_probe(struct platform_device *pdev)
 {
 	struct graph_card_data *priv;
@@ -319,6 +333,7 @@ static int asoc_graph_card_probe(struct platform_device *pdev)
 	card->num_links	= num;
 	card->dapm_widgets = asoc_graph_card_dapm_widgets;
 	card->num_dapm_widgets = ARRAY_SIZE(asoc_graph_card_dapm_widgets);
+	card->probe	= asoc_graph_soc_card_probe;
 
 	ret = asoc_graph_card_parse_of(priv);
 	if (ret < 0) {
diff --git a/sound/soc/generic/audio-graph-scu-card.c b/sound/soc/generic/audio-graph-scu-card.c
index 095ef6426d42..92882e392d6c 100644
--- a/sound/soc/generic/audio-graph-scu-card.c
+++ b/sound/soc/generic/audio-graph-scu-card.c
@@ -1,17 +1,14 @@
-/*
- * ASoC audio graph SCU sound card support
- *
- * Copyright (C) 2017 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * based on
- *	${LINUX}/sound/soc/generic/simple-scu-card.c
- *	${LINUX}/sound/soc/generic/audio-graph-card.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ASoC audio graph SCU sound card support
+//
+// Copyright (C) 2017 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// based on
+//	${LINUX}/sound/soc/generic/simple-scu-card.c
+//	${LINUX}/sound/soc/generic/audio-graph-card.c
+
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/gpio.h>
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index 3751a07de6aa..d3f3f0fec74c 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -1,16 +1,17 @@
-/*
- * simple-card-utils.c
- *
- * Copyright (c) 2016 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// simple-card-utils.c
+//
+// Copyright (c) 2016 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include <linux/clk.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_gpio.h>
 #include <linux/of_graph.h>
+#include <sound/jack.h>
 #include <sound/simple_card_utils.h>
 
 void asoc_simple_card_convert_fixup(struct asoc_simple_card_data *data,
@@ -419,6 +420,61 @@ int asoc_simple_card_of_parse_widgets(struct snd_soc_card *card,
 }
 EXPORT_SYMBOL_GPL(asoc_simple_card_of_parse_widgets);
 
+int asoc_simple_card_init_jack(struct snd_soc_card *card,
+			       struct asoc_simple_jack *sjack,
+			       int is_hp, char *prefix)
+{
+	struct device *dev = card->dev;
+	enum of_gpio_flags flags;
+	char prop[128];
+	char *pin_name;
+	char *gpio_name;
+	int mask;
+	int det;
+
+	if (!prefix)
+		prefix = "";
+
+	sjack->gpio.gpio = -ENOENT;
+
+	if (is_hp) {
+		snprintf(prop, sizeof(prop), "%shp-det-gpio", prefix);
+		pin_name	= "Headphones";
+		gpio_name	= "Headphone detection";
+		mask		= SND_JACK_HEADPHONE;
+	} else {
+		snprintf(prop, sizeof(prop), "%smic-det-gpio", prefix);
+		pin_name	= "Mic Jack";
+		gpio_name	= "Mic detection";
+		mask		= SND_JACK_MICROPHONE;
+	}
+
+	det = of_get_named_gpio_flags(dev->of_node, prop, 0, &flags);
+	if (det == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
+	if (gpio_is_valid(det)) {
+		sjack->pin.pin		= pin_name;
+		sjack->pin.mask		= mask;
+
+		sjack->gpio.name	= gpio_name;
+		sjack->gpio.report	= mask;
+		sjack->gpio.gpio	= det;
+		sjack->gpio.invert	= !!(flags & OF_GPIO_ACTIVE_LOW);
+		sjack->gpio.debounce_time = 150;
+
+		snd_soc_card_jack_new(card, pin_name, mask,
+				      &sjack->jack,
+				      &sjack->pin, 1);
+
+		snd_soc_jack_add_gpios(&sjack->jack, 1,
+				       &sjack->gpio);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(asoc_simple_card_init_jack);
+
 /* Module information */
 MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
 MODULE_DESCRIPTION("ALSA SoC Simple Card Utils");
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 8b374af86a6e..64bf3560c1d1 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -1,32 +1,20 @@
-/*
- * ASoC simple sound card support
- *
- * Copyright (C) 2012 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ASoC simple sound card support
+//
+// Copyright (C) 2012 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include <linux/clk.h>
 #include <linux/device.h>
-#include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/platform_device.h>
 #include <linux/string.h>
-#include <sound/jack.h>
 #include <sound/simple_card.h>
 #include <sound/soc-dai.h>
 #include <sound/soc.h>
 
-struct asoc_simple_jack {
-	struct snd_soc_jack jack;
-	struct snd_soc_jack_pin pin;
-	struct snd_soc_jack_gpio gpio;
-};
-
 struct simple_card_data {
 	struct snd_soc_card snd_card;
 	struct simple_dai_props {
@@ -49,61 +37,6 @@ struct simple_card_data {
 #define CELL	"#sound-dai-cells"
 #define PREFIX	"simple-audio-card,"
 
-#define asoc_simple_card_init_hp(card, sjack, prefix)\
-	asoc_simple_card_init_jack(card, sjack, 1, prefix)
-#define asoc_simple_card_init_mic(card, sjack, prefix)\
-	asoc_simple_card_init_jack(card, sjack, 0, prefix)
-static int asoc_simple_card_init_jack(struct snd_soc_card *card,
-				      struct asoc_simple_jack *sjack,
-				      int is_hp, char *prefix)
-{
-	struct device *dev = card->dev;
-	enum of_gpio_flags flags;
-	char prop[128];
-	char *pin_name;
-	char *gpio_name;
-	int mask;
-	int det;
-
-	sjack->gpio.gpio = -ENOENT;
-
-	if (is_hp) {
-		snprintf(prop, sizeof(prop), "%shp-det-gpio", prefix);
-		pin_name	= "Headphones";
-		gpio_name	= "Headphone detection";
-		mask		= SND_JACK_HEADPHONE;
-	} else {
-		snprintf(prop, sizeof(prop), "%smic-det-gpio", prefix);
-		pin_name	= "Mic Jack";
-		gpio_name	= "Mic detection";
-		mask		= SND_JACK_MICROPHONE;
-	}
-
-	det = of_get_named_gpio_flags(dev->of_node, prop, 0, &flags);
-	if (det == -EPROBE_DEFER)
-		return -EPROBE_DEFER;
-
-	if (gpio_is_valid(det)) {
-		sjack->pin.pin		= pin_name;
-		sjack->pin.mask		= mask;
-
-		sjack->gpio.name	= gpio_name;
-		sjack->gpio.report	= mask;
-		sjack->gpio.gpio	= det;
-		sjack->gpio.invert	= !!(flags & OF_GPIO_ACTIVE_LOW);
-		sjack->gpio.debounce_time = 150;
-
-		snd_soc_card_jack_new(card, pin_name, mask,
-				      &sjack->jack,
-				      &sjack->pin, 1);
-
-		snd_soc_jack_add_gpios(&sjack->jack, 1,
-				       &sjack->gpio);
-	}
-
-	return 0;
-}
-
 static int asoc_simple_card_startup(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -213,14 +146,6 @@ static int asoc_simple_card_dai_init(struct snd_soc_pcm_runtime *rtd)
 	if (ret < 0)
 		return ret;
 
-	ret = asoc_simple_card_init_hp(rtd->card, &priv->hp_jack, PREFIX);
-	if (ret < 0)
-		return ret;
-
-	ret = asoc_simple_card_init_mic(rtd->card, &priv->mic_jack, PREFIX);
-	if (ret < 0)
-		return ret;
-
 	return 0;
 }
 
@@ -414,6 +339,22 @@ card_parse_end:
 	return ret;
 }
 
+static int asoc_simple_soc_card_probe(struct snd_soc_card *card)
+{
+	struct simple_card_data *priv = snd_soc_card_get_drvdata(card);
+	int ret;
+
+	ret = asoc_simple_card_init_hp(card, &priv->hp_jack, PREFIX);
+	if (ret < 0)
+		return ret;
+
+	ret = asoc_simple_card_init_mic(card, &priv->mic_jack, PREFIX);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int asoc_simple_card_probe(struct platform_device *pdev)
 {
 	struct simple_card_data *priv;
@@ -449,6 +390,7 @@ static int asoc_simple_card_probe(struct platform_device *pdev)
 	card->dev		= dev;
 	card->dai_link		= priv->dai_link;
 	card->num_links		= num;
+	card->probe		= asoc_simple_soc_card_probe;
 
 	if (np && of_device_is_available(np)) {
 
diff --git a/sound/soc/generic/simple-scu-card.c b/sound/soc/generic/simple-scu-card.c
index 487716559deb..16a83bc51e0e 100644
--- a/sound/soc/generic/simple-scu-card.c
+++ b/sound/soc/generic/simple-scu-card.c
@@ -1,15 +1,12 @@
-/*
- * ASoC simple SCU sound card support
- *
- * Copyright (C) 2015 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * based on ${LINUX}/sound/soc/generic/simple-card.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ASoC simple SCU sound card support
+//
+// Copyright (C) 2015 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// based on ${LINUX}/sound/soc/generic/simple-card.c
+
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/module.h>
diff --git a/sound/soc/intel/atom/sst/sst_drv_interface.c b/sound/soc/intel/atom/sst/sst_drv_interface.c
index 6a8b253c58d2..5455d6e0ab53 100644
--- a/sound/soc/intel/atom/sst/sst_drv_interface.c
+++ b/sound/soc/intel/atom/sst/sst_drv_interface.c
@@ -266,17 +266,15 @@ static int sst_cdev_ack(struct device *dev, unsigned int str_id,
 	stream->cumm_bytes += bytes;
 	dev_dbg(dev, "bytes copied %d inc by %ld\n", stream->cumm_bytes, bytes);
 
-	memcpy_fromio(&fw_tstamp,
-		((void *)(ctx->mailbox + ctx->tstamp)
-		+(str_id * sizeof(fw_tstamp))),
-		sizeof(fw_tstamp));
+	addr =  ((void __iomem *)(ctx->mailbox + ctx->tstamp)) +
+		(str_id * sizeof(fw_tstamp));
+
+	memcpy_fromio(&fw_tstamp, addr, sizeof(fw_tstamp));
 
 	fw_tstamp.bytes_copied = stream->cumm_bytes;
 	dev_dbg(dev, "bytes sent to fw %llu inc by %ld\n",
 			fw_tstamp.bytes_copied, bytes);
 
-	addr =  ((void *)(ctx->mailbox + ctx->tstamp)) +
-			(str_id * sizeof(fw_tstamp));
 	offset =  offsetof(struct snd_sst_tstamp, bytes_copied);
 	sst_shim_write(addr, offset, fw_tstamp.bytes_copied);
 	return 0;
@@ -360,11 +358,12 @@ static int sst_cdev_tstamp(struct device *dev, unsigned int str_id,
 	struct snd_sst_tstamp fw_tstamp = {0,};
 	struct stream_info *stream;
 	struct intel_sst_drv *ctx = dev_get_drvdata(dev);
+	void __iomem *addr;
+
+	addr = (void __iomem *)(ctx->mailbox + ctx->tstamp) +
+		(str_id * sizeof(fw_tstamp));
 
-	memcpy_fromio(&fw_tstamp,
-		((void *)(ctx->mailbox + ctx->tstamp)
-		+(str_id * sizeof(fw_tstamp))),
-		sizeof(fw_tstamp));
+	memcpy_fromio(&fw_tstamp, addr, sizeof(fw_tstamp));
 
 	stream = get_stream_info(ctx, str_id);
 	if (!stream)
@@ -530,6 +529,7 @@ static int sst_read_timestamp(struct device *dev, struct pcm_stream_info *info)
 	struct snd_sst_tstamp fw_tstamp;
 	unsigned int str_id;
 	struct intel_sst_drv *ctx = dev_get_drvdata(dev);
+	void __iomem *addr;
 
 	str_id = info->str_id;
 	stream = get_stream_info(ctx, str_id);
@@ -540,10 +540,11 @@ static int sst_read_timestamp(struct device *dev, struct pcm_stream_info *info)
 		return -EINVAL;
 	substream = stream->pcm_substream;
 
-	memcpy_fromio(&fw_tstamp,
-		((void *)(ctx->mailbox + ctx->tstamp)
-			+ (str_id * sizeof(fw_tstamp))),
-		sizeof(fw_tstamp));
+	addr = (void __iomem *)(ctx->mailbox + ctx->tstamp) +
+		(str_id * sizeof(fw_tstamp));
+
+	memcpy_fromio(&fw_tstamp, addr, sizeof(fw_tstamp));
+
 	return sst_calc_tstamp(ctx, info, substream, &fw_tstamp);
 }
 
diff --git a/sound/soc/intel/atom/sst/sst_loader.c b/sound/soc/intel/atom/sst/sst_loader.c
index a686eef2cf7f..27413ebae956 100644
--- a/sound/soc/intel/atom/sst/sst_loader.c
+++ b/sound/soc/intel/atom/sst/sst_loader.c
@@ -44,15 +44,15 @@ void memcpy32_toio(void __iomem *dst, const void *src, int count)
 	/* __iowrite32_copy uses 32-bit count values so divide by 4 for
 	 * right count in words
 	 */
-	__iowrite32_copy(dst, src, count/4);
+	__iowrite32_copy(dst, src, count / 4);
 }
 
 void memcpy32_fromio(void *dst, const void __iomem *src, int count)
 {
-	/* __iowrite32_copy uses 32-bit count values so divide by 4 for
+	/* __ioread32_copy uses 32-bit count values so divide by 4 for
 	 * right count in words
 	 */
-	__iowrite32_copy(dst, src, count/4);
+	__ioread32_copy(dst, src, count / 4);
 }
 
 /**
diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index 24797482a3d2..cccda87f4b34 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -281,6 +281,20 @@ config SND_SOC_INTEL_KBL_DA7219_MAX98357A_MACH
 	  Say Y if you have such a device.
 	  If unsure select "N".
 
+config SND_SOC_INTEL_GLK_RT5682_MAX98357A_MACH
+	tristate "GLK with RT5682 and MAX98357A in I2S Mode"
+	depends on MFD_INTEL_LPSS && I2C && ACPI
+	select SND_SOC_RT5682
+	select SND_SOC_MAX98357A
+	select SND_SOC_DMIC
+	select SND_SOC_HDAC_HDMI
+	select SND_HDA_DSP_LOADER
+	help
+	   This adds support for ASoC machine driver for Geminilake platforms
+	   with RT5682 + MAX98357A I2S audio codec.
+	   Say Y if you have such a device.
+	   If unsure select "N".
+
 endif ## SND_SOC_INTEL_SKYLAKE
 
 endif ## SND_SOC_INTEL_MACH
diff --git a/sound/soc/intel/boards/Makefile b/sound/soc/intel/boards/Makefile
index 92b5507291af..87ef8b4058e5 100644
--- a/sound/soc/intel/boards/Makefile
+++ b/sound/soc/intel/boards/Makefile
@@ -6,6 +6,7 @@ snd-soc-sst-bdw-rt5677-mach-objs := bdw-rt5677.o
 snd-soc-sst-broadwell-objs := broadwell.o
 snd-soc-sst-bxt-da7219_max98357a-objs := bxt_da7219_max98357a.o
 snd-soc-sst-bxt-rt298-objs := bxt_rt298.o
+snd-soc-sst-glk-rt5682_max98357a-objs := glk_rt5682_max98357a.o
 snd-soc-sst-bytcr-rt5640-objs := bytcr_rt5640.o
 snd-soc-sst-bytcr-rt5651-objs := bytcr_rt5651.o
 snd-soc-sst-cht-bsw-rt5672-objs := cht_bsw_rt5672.o
@@ -27,6 +28,7 @@ obj-$(CONFIG_SND_SOC_INTEL_BYT_RT5640_MACH) += snd-soc-sst-byt-rt5640-mach.o
 obj-$(CONFIG_SND_SOC_INTEL_BYT_MAX98090_MACH) += snd-soc-sst-byt-max98090-mach.o
 obj-$(CONFIG_SND_SOC_INTEL_BXT_DA7219_MAX98357A_MACH) += snd-soc-sst-bxt-da7219_max98357a.o
 obj-$(CONFIG_SND_SOC_INTEL_BXT_RT298_MACH) += snd-soc-sst-bxt-rt298.o
+obj-$(CONFIG_SND_SOC_INTEL_GLK_RT5682_MAX98357A_MACH) += snd-soc-sst-glk-rt5682_max98357a.o
 obj-$(CONFIG_SND_SOC_INTEL_BROADWELL_MACH) += snd-soc-sst-broadwell.o
 obj-$(CONFIG_SND_SOC_INTEL_BDW_RT5677_MACH) += snd-soc-sst-bdw-rt5677-mach.o
 obj-$(CONFIG_SND_SOC_INTEL_BYTCR_RT5640_MACH) += snd-soc-sst-bytcr-rt5640.o
diff --git a/sound/soc/intel/boards/bdw-rt5677.c b/sound/soc/intel/boards/bdw-rt5677.c
index 6ea360f33575..efcfd906c856 100644
--- a/sound/soc/intel/boards/bdw-rt5677.c
+++ b/sound/soc/intel/boards/bdw-rt5677.c
@@ -154,9 +154,7 @@ static int broadwell_ssp0_fixup(struct snd_soc_pcm_runtime *rtd,
 	channels->min = channels->max = 2;
 
 	/* set SSP0 to 16 bit */
-	snd_mask_set(&params->masks[SNDRV_PCM_HW_PARAM_FORMAT -
-				    SNDRV_PCM_HW_PARAM_FIRST_MASK],
-				    SNDRV_PCM_FORMAT_S16_LE);
+	params_set_format(params, SNDRV_PCM_FORMAT_S16_LE);
 	return 0;
 }
 
diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index 40eb979d5ac1..6f052fc8d1e2 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -160,7 +160,7 @@ static int broxton_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 
 	return 0;
 }
@@ -324,8 +324,22 @@ static const struct snd_pcm_hw_constraint_list constraints_16000 = {
 	.list  = rates_16000,
 };
 
+static const unsigned int ch_mono[] = {
+	1,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_refcap = {
+	.count = ARRAY_SIZE(ch_mono),
+	.list  = ch_mono,
+};
+
 static int broxton_refcap_startup(struct snd_pcm_substream *substream)
 {
+	substream->runtime->hw.channels_max = 1;
+	snd_pcm_hw_constraint_list(substream->runtime, 0,
+				   SNDRV_PCM_HW_PARAM_CHANNELS,
+				   &constraints_refcap);
+
 	return snd_pcm_hw_constraint_list(substream->runtime, 0,
 			SNDRV_PCM_HW_PARAM_RATE,
 			&constraints_16000);
@@ -586,7 +600,7 @@ static int broxton_audio_probe(struct platform_device *pdev)
 static struct platform_driver broxton_audio = {
 	.probe = broxton_audio_probe,
 	.driver = {
-		.name = "bxt_da7219_max98357a_i2s",
+		.name = "bxt_da7219_max98357a",
 		.pm = &snd_soc_pm_ops,
 	},
 };
@@ -599,4 +613,4 @@ MODULE_AUTHOR("Rohit Ainapure <rohit.m.ainapure@intel.com>");
 MODULE_AUTHOR("Harsha Priya <harshapriya.n@intel.com>");
 MODULE_AUTHOR("Conrad Cooke <conrad.cooke@intel.com>");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:bxt_da7219_max98357a_i2s");
+MODULE_ALIAS("platform:bxt_da7219_max98357a");
diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
index b68c289558a8..27308337ab12 100644
--- a/sound/soc/intel/boards/bxt_rt298.c
+++ b/sound/soc/intel/boards/bxt_rt298.c
@@ -221,7 +221,7 @@ static int broxton_ssp5_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP5 to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 33065ba294a9..d32844f94d74 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -404,7 +404,7 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 		},
 		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
 					BYT_RT5640_JD_SRC_JD1_IN4P |
-					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_TH_1500UA |
 					BYT_RT5640_OVCD_SF_0P75 |
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
@@ -464,12 +464,38 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_MCLK_EN),
 	},
 	{
+		/* Chuwi Vi10 (CWI505) */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"),
+			DMI_MATCH(DMI_BOARD_NAME, "BYT-PF02"),
+			DMI_MATCH(DMI_SYS_VENDOR, "ilife"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "S165"),
+		},
+		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_DIFF_MIC |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
+	{
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Circuitco"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Max B3 PLATFORM"),
 		},
 		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP),
 	},
+	{	/* Connect Tablet 9 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Connect"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Tablet 9"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -536,6 +562,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{	/* Lenovo Miix 2 8 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "20326"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "Hiking"),
+		},
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_MCLK_EN),
+	},
 	{	/* MSI S100 tablet */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Micro-Star International Co., Ltd."),
@@ -549,6 +588,20 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_DIFF_MIC |
 					BYT_RT5640_MCLK_EN),
 	},
+	{	/* Nuvison/TMax TM800W560 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TMAX"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "TM800W560L"),
+		},
+		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_JD_NOT_INV |
+					BYT_RT5640_DIFF_MIC |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{	/* Pipo W4 */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 987720e203f9..f8a68bdb3885 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -26,8 +26,12 @@
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/dmi.h>
+#include <linux/input.h>
+#include <linux/gpio/consumer.h>
+#include <linux/gpio/machine.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include <asm/platform_sst_audio.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -42,8 +46,6 @@ enum {
 	BYT_RT5651_IN1_MAP,
 	BYT_RT5651_IN2_MAP,
 	BYT_RT5651_IN1_IN2_MAP,
-	BYT_RT5651_IN1_HS_IN3_MAP,
-	BYT_RT5651_IN2_HS_IN3_MAP,
 };
 
 enum {
@@ -76,21 +78,26 @@ enum {
 #define BYT_RT5651_SSP2_AIF2		BIT(19) /* default is using AIF1  */
 #define BYT_RT5651_SSP0_AIF1		BIT(20)
 #define BYT_RT5651_SSP0_AIF2		BIT(21)
+#define BYT_RT5651_HP_LR_SWAPPED	BIT(22)
+#define BYT_RT5651_MONO_SPEAKER		BIT(23)
+
+#define BYT_RT5651_DEFAULT_QUIRKS	(BYT_RT5651_MCLK_EN | \
+					 BYT_RT5651_JD1_1   | \
+					 BYT_RT5651_OVCD_TH_2000UA | \
+					 BYT_RT5651_OVCD_SF_0P75)
 
 /* jack-detect-source + dmic-en + ovcd-th + -sf + terminating empty entry */
 #define MAX_NO_PROPS 5
 
 struct byt_rt5651_private {
 	struct clk *mclk;
+	struct gpio_desc *ext_amp_gpio;
 	struct snd_soc_jack jack;
 };
 
 /* Default: jack-detect on JD1_1, internal mic on in2, headsetmic on in3 */
-static unsigned long byt_rt5651_quirk = BYT_RT5651_MCLK_EN |
-					BYT_RT5651_JD1_1 |
-					BYT_RT5651_OVCD_TH_2000UA |
-					BYT_RT5651_OVCD_SF_0P75 |
-					BYT_RT5651_IN2_HS_IN3_MAP;
+static unsigned long byt_rt5651_quirk = BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN2_MAP;
 
 static void log_quirks(struct device *dev)
 {
@@ -100,10 +107,8 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk IN1_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN2_MAP)
 		dev_info(dev, "quirk IN2_MAP enabled");
-	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_HS_IN3_MAP)
-		dev_info(dev, "quirk IN1_HS_IN3_MAP enabled");
-	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN2_HS_IN3_MAP)
-		dev_info(dev, "quirk IN2_HS_IN3_MAP enabled");
+	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_IN2_MAP)
+		dev_info(dev, "quirk IN1_IN2_MAP enabled");
 	if (BYT_RT5651_JDSRC(byt_rt5651_quirk)) {
 		dev_info(dev, "quirk realtek,jack-detect-source %ld\n",
 			 BYT_RT5651_JDSRC(byt_rt5651_quirk));
@@ -124,6 +129,8 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk SSP0_AIF1 enabled\n");
 	if (byt_rt5651_quirk & BYT_RT5651_SSP0_AIF2)
 		dev_info(dev, "quirk SSP0_AIF2 enabled\n");
+	if (byt_rt5651_quirk & BYT_RT5651_MONO_SPEAKER)
+		dev_info(dev, "quirk MONO_SPEAKER enabled\n");
 }
 
 #define BYT_CODEC_DAI1	"rt5651-aif1"
@@ -211,6 +218,20 @@ static int platform_clock_control(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
+static int rt5651_ext_amp_power_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_card *card = w->dapm->card;
+	struct byt_rt5651_private *priv = snd_soc_card_get_drvdata(card);
+
+	if (SND_SOC_DAPM_EVENT_ON(event))
+		gpiod_set_value_cansleep(priv->ext_amp_gpio, 1);
+	else
+		gpiod_set_value_cansleep(priv->ext_amp_gpio, 0);
+
+	return 0;
+}
+
 static const struct snd_soc_dapm_widget byt_rt5651_widgets[] = {
 	SND_SOC_DAPM_HP("Headphone", NULL),
 	SND_SOC_DAPM_MIC("Headset Mic", NULL),
@@ -220,7 +241,9 @@ static const struct snd_soc_dapm_widget byt_rt5651_widgets[] = {
 	SND_SOC_DAPM_SUPPLY("Platform Clock", SND_SOC_NOPM, 0, 0,
 			    platform_clock_control, SND_SOC_DAPM_PRE_PMU |
 			    SND_SOC_DAPM_POST_PMD),
-
+	SND_SOC_DAPM_SUPPLY("Ext Amp Power", SND_SOC_NOPM, 0, 0,
+			    rt5651_ext_amp_power_event,
+			    SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMU),
 };
 
 static const struct snd_soc_dapm_route byt_rt5651_audio_map[] = {
@@ -228,6 +251,7 @@ static const struct snd_soc_dapm_route byt_rt5651_audio_map[] = {
 	{"Headset Mic", NULL, "Platform Clock"},
 	{"Internal Mic", NULL, "Platform Clock"},
 	{"Speaker", NULL, "Platform Clock"},
+	{"Speaker", NULL, "Ext Amp Power"},
 	{"Line In", NULL, "Platform Clock"},
 
 	{"Headset Mic", NULL, "micbias1"}, /* lowercase for rt5651 */
@@ -241,38 +265,26 @@ static const struct snd_soc_dapm_route byt_rt5651_audio_map[] = {
 };
 
 static const struct snd_soc_dapm_route byt_rt5651_intmic_dmic_map[] = {
-	{"IN2P", NULL, "Headset Mic"},
 	{"DMIC L1", NULL, "Internal Mic"},
 	{"DMIC R1", NULL, "Internal Mic"},
+	{"IN3P", NULL, "Headset Mic"},
 };
 
 static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_map[] = {
 	{"Internal Mic", NULL, "micbias1"},
 	{"IN1P", NULL, "Internal Mic"},
-	{"IN2P", NULL, "Headset Mic"},
+	{"IN3P", NULL, "Headset Mic"},
 };
 
 static const struct snd_soc_dapm_route byt_rt5651_intmic_in2_map[] = {
 	{"Internal Mic", NULL, "micbias1"},
-	{"IN1P", NULL, "Headset Mic"},
-	{"IN2P", NULL, "Internal Mic"},
-};
-
-static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_in2_map[] = {
-	{"Internal Mic", NULL, "micbias1"},
-	{"IN1P", NULL, "Internal Mic"},
 	{"IN2P", NULL, "Internal Mic"},
 	{"IN3P", NULL, "Headset Mic"},
 };
 
-static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_hs_in3_map[] = {
+static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_in2_map[] = {
 	{"Internal Mic", NULL, "micbias1"},
 	{"IN1P", NULL, "Internal Mic"},
-	{"IN3P", NULL, "Headset Mic"},
-};
-
-static const struct snd_soc_dapm_route byt_rt5651_intmic_in2_hs_in3_map[] = {
-	{"Internal Mic", NULL, "micbias1"},
 	{"IN2P", NULL, "Internal Mic"},
 	{"IN3P", NULL, "Headset Mic"},
 };
@@ -357,46 +369,72 @@ static int byt_rt5651_quirk_cb(const struct dmi_system_id *id)
 
 static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 	{
+		/* Chuwi Hi8 Pro (CWI513) */
 		.callback = byt_rt5651_quirk_cb,
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Circuitco"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Max B3 PLATFORM"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Hampoo"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X1D3_C806N"),
 		},
-		.driver_data = (void *)(BYT_RT5651_IN1_HS_IN3_MAP),
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN2_MAP |
+					BYT_RT5651_HP_LR_SWAPPED |
+					BYT_RT5651_MONO_SPEAKER),
 	},
 	{
+		/* Chuwi Vi8 Plus (CWI519) */
 		.callback = byt_rt5651_quirk_cb,
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ADI"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Turbot"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Hampoo"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "D2D3_Vi8A1"),
 		},
-		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
-					BYT_RT5651_IN1_HS_IN3_MAP),
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN2_MAP |
+					BYT_RT5651_HP_LR_SWAPPED |
+					BYT_RT5651_MONO_SPEAKER),
+	},
+	{
+		/* I.T.Works TW701, Ployer Momo7w and Trekstor ST70416-6
+		 * (these all use the same mainboard) */
+		.callback = byt_rt5651_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_BIOS_VENDOR, "INSYDE Corp."),
+			/* Partial match for all of itWORKS.G.WI71C.JGBMRBA,
+			 * TREK.G.WI71C.JGBMRBA0x and MOMO.G.WI71C.MABMRBA02 */
+			DMI_MATCH(DMI_BIOS_VERSION, ".G.WI71C."),
+		},
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN2_MAP |
+					BYT_RT5651_SSP0_AIF1 |
+					BYT_RT5651_MONO_SPEAKER),
 	},
 	{
+		/* KIANO SlimNote 14.2 */
 		.callback = byt_rt5651_quirk_cb,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "KIANO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "KIANO SlimNote 14.2"),
 		},
-		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
-					BYT_RT5651_JD1_1 |
-					BYT_RT5651_OVCD_TH_2000UA |
-					BYT_RT5651_OVCD_SF_0P75 |
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
 					BYT_RT5651_IN1_IN2_MAP),
 	},
 	{
-		/* Chuwi Vi8 Plus (CWI519) */
+		/* Minnowboard Max B3 */
 		.callback = byt_rt5651_quirk_cb,
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Hampoo"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "D2D3_Vi8A1"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Circuitco"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Max B3 PLATFORM"),
+		},
+		.driver_data = (void *)(BYT_RT5651_IN1_MAP),
+	},
+	{
+		/* Minnowboard Turbot */
+		.callback = byt_rt5651_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ADI"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Turbot"),
 		},
 		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
-					BYT_RT5651_JD1_1 |
-					BYT_RT5651_OVCD_TH_2000UA |
-					BYT_RT5651_OVCD_SF_0P75 |
-					BYT_RT5651_IN2_HS_IN3_MAP),
+					BYT_RT5651_IN1_MAP),
 	},
 	{
 		/* VIOS LTH17 */
@@ -405,11 +443,24 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "VIOS"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "LTH17"),
 		},
-		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
+		.driver_data = (void *)(BYT_RT5651_IN1_IN2_MAP |
 					BYT_RT5651_JD1_1 |
 					BYT_RT5651_OVCD_TH_2000UA |
 					BYT_RT5651_OVCD_SF_1P0 |
-					BYT_RT5651_IN1_IN2_MAP),
+					BYT_RT5651_MCLK_EN),
+	},
+	{
+		/* Yours Y8W81 (and others using the same mainboard) */
+		.callback = byt_rt5651_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_BIOS_VENDOR, "INSYDE Corp."),
+			/* Partial match for all devs with a W86C mainboard */
+			DMI_MATCH(DMI_BIOS_VERSION, ".F.W86C."),
+		},
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN2_MAP |
+					BYT_RT5651_SSP0_AIF1 |
+					BYT_RT5651_MONO_SPEAKER),
 	},
 	{}
 };
@@ -418,15 +469,10 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
  * Note this MUST be called before snd_soc_register_card(), so that the props
  * are in place before the codec component driver's probe function parses them.
  */
-static int byt_rt5651_add_codec_device_props(const char *i2c_dev_name)
+static int byt_rt5651_add_codec_device_props(struct device *i2c_dev)
 {
 	struct property_entry props[MAX_NO_PROPS] = {};
-	struct device *i2c_dev;
-	int ret, cnt = 0;
-
-	i2c_dev = bus_find_device_by_name(&i2c_bus_type, NULL, i2c_dev_name);
-	if (!i2c_dev)
-		return -EPROBE_DEFER;
+	int cnt = 0;
 
 	props[cnt++] = PROPERTY_ENTRY_U32("realtek,jack-detect-source",
 				BYT_RT5651_JDSRC(byt_rt5651_quirk));
@@ -440,10 +486,7 @@ static int byt_rt5651_add_codec_device_props(const char *i2c_dev_name)
 	if (byt_rt5651_quirk & BYT_RT5651_DMIC_EN)
 		props[cnt++] = PROPERTY_ENTRY_BOOL("realtek,dmic-en");
 
-	ret = device_add_properties(i2c_dev, props);
-	put_device(i2c_dev);
-
-	return ret;
+	return device_add_properties(i2c_dev, props);
 }
 
 static int byt_rt5651_init(struct snd_soc_pcm_runtime *runtime)
@@ -475,14 +518,6 @@ static int byt_rt5651_init(struct snd_soc_pcm_runtime *runtime)
 		custom_map = byt_rt5651_intmic_in1_in2_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in1_in2_map);
 		break;
-	case BYT_RT5651_IN1_HS_IN3_MAP:
-		custom_map = byt_rt5651_intmic_in1_hs_in3_map;
-		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in1_hs_in3_map);
-		break;
-	case BYT_RT5651_IN2_HS_IN3_MAP:
-		custom_map = byt_rt5651_intmic_in2_hs_in3_map;
-		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in2_hs_in3_map);
-		break;
 	default:
 		custom_map = byt_rt5651_intmic_dmic_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_dmic_map);
@@ -546,13 +581,17 @@ static int byt_rt5651_init(struct snd_soc_pcm_runtime *runtime)
 
 	if (BYT_RT5651_JDSRC(byt_rt5651_quirk)) {
 		ret = snd_soc_card_jack_new(runtime->card, "Headset",
-				    SND_JACK_HEADSET, &priv->jack,
-				    bytcr_jack_pins, ARRAY_SIZE(bytcr_jack_pins));
+				    SND_JACK_HEADSET | SND_JACK_BTN_0,
+				    &priv->jack, bytcr_jack_pins,
+				    ARRAY_SIZE(bytcr_jack_pins));
 		if (ret) {
 			dev_err(runtime->dev, "jack creation failed %d\n", ret);
 			return ret;
 		}
 
+		snd_jack_set_key(priv->jack.jack, SND_JACK_BTN_0,
+				 KEY_PLAYPAUSE);
+
 		ret = snd_soc_component_set_jack(codec, &priv->jack, NULL);
 		if (ret)
 			return ret;
@@ -691,6 +730,48 @@ static struct snd_soc_dai_link byt_rt5651_dais[] = {
 };
 
 /* SoC card */
+static char byt_rt5651_codec_name[SND_ACPI_I2C_ID_LEN];
+static char byt_rt5651_codec_aif_name[12]; /*  = "rt5651-aif[1|2]" */
+static char byt_rt5651_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
+static char byt_rt5651_long_name[50]; /* = "bytcr-rt5651-*-spk-*-mic[-swapped-hp]" */
+
+static int byt_rt5651_suspend(struct snd_soc_card *card)
+{
+	struct snd_soc_component *component;
+
+	if (!BYT_RT5651_JDSRC(byt_rt5651_quirk))
+		return 0;
+
+	list_for_each_entry(component, &card->component_dev_list, card_list) {
+		if (!strcmp(component->name, byt_rt5651_codec_name)) {
+			dev_dbg(component->dev, "disabling jack detect before suspend\n");
+			snd_soc_component_set_jack(component, NULL, NULL);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int byt_rt5651_resume(struct snd_soc_card *card)
+{
+	struct byt_rt5651_private *priv = snd_soc_card_get_drvdata(card);
+	struct snd_soc_component *component;
+
+	if (!BYT_RT5651_JDSRC(byt_rt5651_quirk))
+		return 0;
+
+	list_for_each_entry(component, &card->component_dev_list, card_list) {
+		if (!strcmp(component->name, byt_rt5651_codec_name)) {
+			dev_dbg(component->dev, "re-enabling jack detect after resume\n");
+			snd_soc_component_set_jack(component, &priv->jack, NULL);
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static struct snd_soc_card byt_rt5651_card = {
 	.name = "bytcr-rt5651",
 	.owner = THIS_MODULE,
@@ -701,23 +782,86 @@ static struct snd_soc_card byt_rt5651_card = {
 	.dapm_routes = byt_rt5651_audio_map,
 	.num_dapm_routes = ARRAY_SIZE(byt_rt5651_audio_map),
 	.fully_routed = true,
+	.suspend_pre = byt_rt5651_suspend,
+	.resume_post = byt_rt5651_resume,
 };
 
-static char byt_rt5651_codec_name[SND_ACPI_I2C_ID_LEN];
-static char byt_rt5651_codec_aif_name[12]; /*  = "rt5651-aif[1|2]" */
-static char byt_rt5651_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
-static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-spk-*-mic" */
+static const struct x86_cpu_id baytrail_cpu_ids[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, /* Valleyview */
+	{}
+};
+
+static const struct x86_cpu_id cherrytrail_cpu_ids[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },     /* Braswell */
+	{}
+};
+
+static const struct acpi_gpio_params first_gpio = { 0, 0, false };
+static const struct acpi_gpio_params second_gpio = { 1, 0, false };
+
+static const struct acpi_gpio_mapping byt_rt5651_amp_en_first[] = {
+	{ "ext-amp-enable-gpios", &first_gpio, 1 },
+	{ },
+};
 
-static bool is_valleyview(void)
+static const struct acpi_gpio_mapping byt_rt5651_amp_en_second[] = {
+	{ "ext-amp-enable-gpios", &second_gpio, 1 },
+	{ },
+};
+
+/*
+ * Some boards have I2cSerialBusV2, GpioIo, GpioInt as ACPI resources, other
+ * boards may  have I2cSerialBusV2, GpioInt, GpioIo instead. We want the
+ * GpioIo one for the ext-amp-enable-gpio and both count for the index in
+ * acpi_gpio_params index.  So we have 2 different mappings and the code
+ * below figures out which one to use.
+ */
+struct byt_rt5651_acpi_resource_data {
+	int gpio_count;
+	int gpio_int_idx;
+};
+
+static int snd_byt_rt5651_acpi_resource(struct acpi_resource *ares, void *arg)
 {
-	static const struct x86_cpu_id cpu_ids[] = {
-		{ X86_VENDOR_INTEL, 6, 55 }, /* Valleyview, Bay Trail */
-		{}
-	};
-
-	if (!x86_match_cpu(cpu_ids))
-		return false;
-	return true;
+	struct byt_rt5651_acpi_resource_data *data = arg;
+
+	if (ares->type != ACPI_RESOURCE_TYPE_GPIO)
+		return 0;
+
+	if (ares->data.gpio.connection_type == ACPI_RESOURCE_GPIO_TYPE_INT)
+		data->gpio_int_idx = data->gpio_count;
+
+	data->gpio_count++;
+	return 0;
+}
+
+static void snd_byt_rt5651_mc_add_amp_en_gpio_mapping(struct device *codec)
+{
+	struct byt_rt5651_acpi_resource_data data = { 0, -1 };
+	LIST_HEAD(resources);
+	int ret;
+
+	ret = acpi_dev_get_resources(ACPI_COMPANION(codec), &resources,
+				     snd_byt_rt5651_acpi_resource, &data);
+	if (ret < 0) {
+		dev_warn(codec, "Failed to get ACPI resources, not adding external amplifier GPIO mapping\n");
+		return;
+	}
+
+	/* All info we need is gathered during the walk */
+	acpi_dev_free_resource_list(&resources);
+
+	switch (data.gpio_int_idx) {
+	case 0:
+		devm_acpi_dev_add_driver_gpios(codec, byt_rt5651_amp_en_second);
+		break;
+	case 1:
+		devm_acpi_dev_add_driver_gpios(codec, byt_rt5651_amp_en_first);
+		break;
+	default:
+		dev_warn(codec, "Unknown GpioInt index %d, not adding external amplifier GPIO mapping\n",
+			 data.gpio_int_idx);
+	}
 }
 
 struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
@@ -727,13 +871,12 @@ struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 
 static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 {
-	const char * const intmic_name[] =
-		{ "dmic", "in1", "in2", "in12", "in1", "in2" };
-	const char * const hsmic_name[] =
-		{  "in2", "in2", "in1",  "in3", "in3", "in3" };
+	const char * const mic_name[] = { "dmic", "in1", "in2", "in12" };
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
+	struct device *codec_dev;
 	const char *i2c_name = NULL;
+	const char *hp_swapped;
 	bool is_bytcr = false;
 	int ret_val = 0;
 	int dai_index = 0;
@@ -767,11 +910,16 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 		"%s%s", "i2c-", i2c_name);
 	byt_rt5651_dais[dai_index].codec_name = byt_rt5651_codec_name;
 
+	codec_dev = bus_find_device_by_name(&i2c_bus_type, NULL,
+					    byt_rt5651_codec_name);
+	if (!codec_dev)
+		return -EPROBE_DEFER;
+
 	/*
 	 * swap SSP0 if bytcr is detected
 	 * (will be overridden if DMI quirk is detected)
 	 */
-	if (is_valleyview()) {
+	if (x86_match_cpu(baytrail_cpu_ids)) {
 		struct sst_platform_info *p_info = mach->pdata;
 		const struct sst_res_info *res_info = p_info->res_info;
 
@@ -830,9 +978,37 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	dmi_check_system(byt_rt5651_quirk_table);
 
 	/* Must be called before register_card, also see declaration comment. */
-	ret_val = byt_rt5651_add_codec_device_props(byt_rt5651_codec_name);
-	if (ret_val)
+	ret_val = byt_rt5651_add_codec_device_props(codec_dev);
+	if (ret_val) {
+		put_device(codec_dev);
 		return ret_val;
+	}
+
+	/* Cherry Trail devices use an external amplifier enable gpio */
+	if (x86_match_cpu(cherrytrail_cpu_ids)) {
+		snd_byt_rt5651_mc_add_amp_en_gpio_mapping(codec_dev);
+		priv->ext_amp_gpio = devm_fwnode_get_index_gpiod_from_child(
+						&pdev->dev, "ext-amp-enable", 0,
+						codec_dev->fwnode,
+						GPIOD_OUT_LOW, "speaker-amp");
+		if (IS_ERR(priv->ext_amp_gpio)) {
+			ret_val = PTR_ERR(priv->ext_amp_gpio);
+			switch (ret_val) {
+			case -ENOENT:
+				priv->ext_amp_gpio = NULL;
+				break;
+			default:
+				dev_err(&pdev->dev, "Failed to get ext-amp-enable GPIO: %d\n",
+					ret_val);
+				/* fall through */
+			case -EPROBE_DEFER:
+				put_device(codec_dev);
+				return ret_val;
+			}
+		}
+	}
+
+	put_device(codec_dev);
 
 	log_quirks(&pdev->dev);
 
@@ -876,10 +1052,16 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (byt_rt5651_quirk & BYT_RT5651_HP_LR_SWAPPED)
+		hp_swapped = "-hp-swapped";
+	else
+		hp_swapped = "";
+
 	snprintf(byt_rt5651_long_name, sizeof(byt_rt5651_long_name),
-		 "bytcr-rt5651-%s-intmic-%s-hsmic",
-		 intmic_name[BYT_RT5651_MAP(byt_rt5651_quirk)],
-		 hsmic_name[BYT_RT5651_MAP(byt_rt5651_quirk)]);
+		 "bytcr-rt5651-%s-spk-%s-mic%s",
+		 (byt_rt5651_quirk & BYT_RT5651_MONO_SPEAKER) ?
+			"mono" : "stereo",
+		 mic_name[BYT_RT5651_MAP(byt_rt5651_quirk)], hp_swapped);
 	byt_rt5651_card.long_name = byt_rt5651_long_name;
 
 	ret_val = devm_snd_soc_register_card(&pdev->dev, &byt_rt5651_card);
diff --git a/sound/soc/intel/boards/glk_rt5682_max98357a.c b/sound/soc/intel/boards/glk_rt5682_max98357a.c
new file mode 100644
index 000000000000..c4b94e2617c5
--- /dev/null
+++ b/sound/soc/intel/boards/glk_rt5682_max98357a.c
@@ -0,0 +1,643 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright(c) 2018 Intel Corporation.
+
+/*
+ * Intel Geminilake I2S Machine Driver with MAX98357A & RT5682 Codecs
+ *
+ * Modified from:
+ *   Intel Apollolake I2S Machine driver
+ */
+
+#include <linux/input.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <sound/core.h>
+#include <sound/jack.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include "../skylake/skl.h"
+#include "../../codecs/rt5682.h"
+#include "../../codecs/hdac_hdmi.h"
+
+/* The platform clock outputs 19.2Mhz clock to codec as I2S MCLK */
+#define GLK_PLAT_CLK_FREQ 19200000
+#define RT5682_PLL_FREQ (48000 * 512)
+#define GLK_REALTEK_CODEC_DAI "rt5682-aif1"
+#define GLK_MAXIM_CODEC_DAI "HiFi"
+#define MAXIM_DEV0_NAME "MX98357A:00"
+#define DUAL_CHANNEL 2
+#define QUAD_CHANNEL 4
+#define NAME_SIZE 32
+
+static struct snd_soc_jack geminilake_hdmi[3];
+
+struct glk_hdmi_pcm {
+	struct list_head head;
+	struct snd_soc_dai *codec_dai;
+	int device;
+};
+
+struct glk_card_private {
+	struct snd_soc_jack geminilake_headset;
+	struct list_head hdmi_pcm_list;
+};
+
+enum {
+	GLK_DPCM_AUDIO_PB = 0,
+	GLK_DPCM_AUDIO_CP,
+	GLK_DPCM_AUDIO_HS_PB,
+	GLK_DPCM_AUDIO_ECHO_REF_CP,
+	GLK_DPCM_AUDIO_REF_CP,
+	GLK_DPCM_AUDIO_DMIC_CP,
+	GLK_DPCM_AUDIO_HDMI1_PB,
+	GLK_DPCM_AUDIO_HDMI2_PB,
+	GLK_DPCM_AUDIO_HDMI3_PB,
+};
+
+static int platform_clock_control(struct snd_soc_dapm_widget *w,
+					struct snd_kcontrol *k, int  event)
+{
+	struct snd_soc_dapm_context *dapm = w->dapm;
+	struct snd_soc_card *card = dapm->card;
+	struct snd_soc_dai *codec_dai;
+	int ret = 0;
+
+	codec_dai = snd_soc_card_get_codec_dai(card, GLK_REALTEK_CODEC_DAI);
+	if (!codec_dai) {
+		dev_err(card->dev, "Codec dai not found; Unable to set/unset codec pll\n");
+		return -EIO;
+	}
+
+	if (SND_SOC_DAPM_EVENT_OFF(event)) {
+		ret = snd_soc_dai_set_sysclk(codec_dai, 0, 0, 0);
+		if (ret)
+			dev_err(card->dev, "failed to stop sysclk: %d\n", ret);
+	} else if (SND_SOC_DAPM_EVENT_ON(event)) {
+		ret = snd_soc_dai_set_pll(codec_dai, 0, RT5682_PLL1_S_MCLK,
+					GLK_PLAT_CLK_FREQ, RT5682_PLL_FREQ);
+		if (ret < 0) {
+			dev_err(card->dev, "can't set codec pll: %d\n", ret);
+			return ret;
+		}
+	}
+
+	if (ret)
+		dev_err(card->dev, "failed to start internal clk: %d\n", ret);
+
+	return ret;
+}
+
+static const struct snd_kcontrol_new geminilake_controls[] = {
+	SOC_DAPM_PIN_SWITCH("Headphone Jack"),
+	SOC_DAPM_PIN_SWITCH("Headset Mic"),
+	SOC_DAPM_PIN_SWITCH("Spk"),
+};
+
+static const struct snd_soc_dapm_widget geminilake_widgets[] = {
+	SND_SOC_DAPM_HP("Headphone Jack", NULL),
+	SND_SOC_DAPM_MIC("Headset Mic", NULL),
+	SND_SOC_DAPM_SPK("Spk", NULL),
+	SND_SOC_DAPM_MIC("SoC DMIC", NULL),
+	SND_SOC_DAPM_SPK("HDMI1", NULL),
+	SND_SOC_DAPM_SPK("HDMI2", NULL),
+	SND_SOC_DAPM_SPK("HDMI3", NULL),
+	SND_SOC_DAPM_SUPPLY("Platform Clock", SND_SOC_NOPM, 0, 0,
+			platform_clock_control, SND_SOC_DAPM_PRE_PMU |
+			SND_SOC_DAPM_POST_PMD),
+};
+
+static const struct snd_soc_dapm_route geminilake_map[] = {
+	/* HP jack connectors - unknown if we have jack detection */
+	{ "Headphone Jack", NULL, "Platform Clock" },
+	{ "Headphone Jack", NULL, "HPOL" },
+	{ "Headphone Jack", NULL, "HPOR" },
+
+	/* speaker */
+	{ "Spk", NULL, "Speaker" },
+
+	/* other jacks */
+	{ "Headset Mic", NULL, "Platform Clock" },
+	{ "IN1P", NULL, "Headset Mic" },
+
+	/* digital mics */
+	{ "DMic", NULL, "SoC DMIC" },
+
+	/* CODEC BE connections */
+	{ "HiFi Playback", NULL, "ssp1 Tx" },
+	{ "ssp1 Tx", NULL, "codec0_out" },
+
+	{ "AIF1 Playback", NULL, "ssp2 Tx" },
+	{ "ssp2 Tx", NULL, "codec1_out" },
+
+	{ "codec0_in", NULL, "ssp2 Rx" },
+	{ "ssp2 Rx", NULL, "AIF1 Capture" },
+
+	{ "HDMI1", NULL, "hif5-0 Output" },
+	{ "HDMI2", NULL, "hif6-0 Output" },
+	{ "HDMI2", NULL, "hif7-0 Output" },
+
+	{ "hifi3", NULL, "iDisp3 Tx" },
+	{ "iDisp3 Tx", NULL, "iDisp3_out" },
+	{ "hifi2", NULL, "iDisp2 Tx" },
+	{ "iDisp2 Tx", NULL, "iDisp2_out" },
+	{ "hifi1", NULL, "iDisp1 Tx" },
+	{ "iDisp1 Tx", NULL, "iDisp1_out" },
+
+	/* DMIC */
+	{ "dmic01_hifi", NULL, "DMIC01 Rx" },
+	{ "DMIC01 Rx", NULL, "DMIC AIF" },
+};
+
+static int geminilake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
+			struct snd_pcm_hw_params *params)
+{
+	struct snd_interval *rate = hw_param_interval(params,
+			SNDRV_PCM_HW_PARAM_RATE);
+	struct snd_interval *channels = hw_param_interval(params,
+			SNDRV_PCM_HW_PARAM_CHANNELS);
+	struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
+
+	/* The ADSP will convert the FE rate to 48k, stereo */
+	rate->min = rate->max = 48000;
+	channels->min = channels->max = DUAL_CHANNEL;
+
+	/* set SSP to 24 bit */
+	snd_mask_none(fmt);
+	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+
+	return 0;
+}
+
+static int geminilake_rt5682_codec_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct glk_card_private *ctx = snd_soc_card_get_drvdata(rtd->card);
+	struct snd_soc_component *component = rtd->codec_dai->component;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	struct snd_soc_jack *jack;
+	int ret;
+
+	/* Configure sysclk for codec */
+	ret = snd_soc_dai_set_sysclk(codec_dai, RT5682_SCLK_S_PLL1,
+					RT5682_PLL_FREQ, SND_SOC_CLOCK_IN);
+	if (ret < 0)
+		dev_err(rtd->dev, "snd_soc_dai_set_sysclk err = %d\n", ret);
+
+	/*
+	 * Headset buttons map to the google Reference headset.
+	 * These can be configured by userspace.
+	 */
+	ret = snd_soc_card_jack_new(rtd->card, "Headset Jack",
+			SND_JACK_HEADSET | SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+			SND_JACK_BTN_2 | SND_JACK_BTN_3 | SND_JACK_LINEOUT,
+			&ctx->geminilake_headset, NULL, 0);
+	if (ret) {
+		dev_err(rtd->dev, "Headset Jack creation failed: %d\n", ret);
+		return ret;
+	}
+
+	jack = &ctx->geminilake_headset;
+
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_0, KEY_PLAYPAUSE);
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_1, KEY_VOLUMEUP);
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_2, KEY_VOLUMEDOWN);
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_3, KEY_VOICECOMMAND);
+	ret = snd_soc_component_set_jack(component, jack, NULL);
+
+	if (ret) {
+		dev_err(rtd->dev, "Headset Jack call-back failed: %d\n", ret);
+		return ret;
+	}
+
+	return ret;
+};
+
+static int geminilake_rt5682_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	int ret;
+
+	/* Set valid bitmask & configuration for I2S in 24 bit */
+	ret = snd_soc_dai_set_tdm_slot(codec_dai, 0x0, 0x0, 2, 24);
+	if (ret < 0) {
+		dev_err(rtd->dev, "set TDM slot err:%d\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static struct snd_soc_ops geminilake_rt5682_ops = {
+	.hw_params = geminilake_rt5682_hw_params,
+};
+
+static int geminilake_hdmi_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct glk_card_private *ctx = snd_soc_card_get_drvdata(rtd->card);
+	struct snd_soc_dai *dai = rtd->codec_dai;
+	struct glk_hdmi_pcm *pcm;
+
+	pcm = devm_kzalloc(rtd->card->dev, sizeof(*pcm), GFP_KERNEL);
+	if (!pcm)
+		return -ENOMEM;
+
+	pcm->device = GLK_DPCM_AUDIO_HDMI1_PB + dai->id;
+	pcm->codec_dai = dai;
+
+	list_add_tail(&pcm->head, &ctx->hdmi_pcm_list);
+
+	return 0;
+}
+
+static int geminilake_rt5682_fe_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_soc_component *component = rtd->cpu_dai->component;
+	struct snd_soc_dapm_context *dapm;
+	int ret;
+
+	dapm = snd_soc_component_get_dapm(component);
+	ret = snd_soc_dapm_ignore_suspend(dapm, "Reference Capture");
+	if (ret) {
+		dev_err(rtd->dev, "Ref Cap ignore suspend failed %d\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static const unsigned int rates[] = {
+	48000,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_rates = {
+	.count = ARRAY_SIZE(rates),
+	.list  = rates,
+	.mask = 0,
+};
+
+static const unsigned int channels[] = {
+	DUAL_CHANNEL,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_channels = {
+	.count = ARRAY_SIZE(channels),
+	.list = channels,
+	.mask = 0,
+};
+
+static unsigned int channels_quad[] = {
+	QUAD_CHANNEL,
+};
+
+static struct snd_pcm_hw_constraint_list constraints_channels_quad = {
+	.count = ARRAY_SIZE(channels_quad),
+	.list = channels_quad,
+	.mask = 0,
+};
+
+static int geminilake_dmic_fixup(struct snd_soc_pcm_runtime *rtd,
+		struct snd_pcm_hw_params *params)
+{
+	struct snd_interval *channels = hw_param_interval(params,
+				SNDRV_PCM_HW_PARAM_CHANNELS);
+
+	/*
+	 * set BE channel constraint as user FE channels
+	 */
+	channels->min = channels->max = 4;
+
+	return 0;
+}
+
+static int geminilake_dmic_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+
+	runtime->hw.channels_min = runtime->hw.channels_max = QUAD_CHANNEL;
+	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
+			&constraints_channels_quad);
+
+	return snd_pcm_hw_constraint_list(substream->runtime, 0,
+			SNDRV_PCM_HW_PARAM_RATE, &constraints_rates);
+}
+
+static const struct snd_soc_ops geminilake_dmic_ops = {
+	.startup = geminilake_dmic_startup,
+};
+
+static const unsigned int rates_16000[] = {
+	16000,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_16000 = {
+	.count = ARRAY_SIZE(rates_16000),
+	.list  = rates_16000,
+};
+
+static int geminilake_refcap_startup(struct snd_pcm_substream *substream)
+{
+	return snd_pcm_hw_constraint_list(substream->runtime, 0,
+				SNDRV_PCM_HW_PARAM_RATE,
+				&constraints_16000);
+};
+
+static const struct snd_soc_ops geminilake_refcap_ops = {
+	.startup = geminilake_refcap_startup,
+};
+
+/* geminilake digital audio interface glue - connects codec <--> CPU */
+static struct snd_soc_dai_link geminilake_dais[] = {
+	/* Front End DAI links */
+	[GLK_DPCM_AUDIO_PB] = {
+		.name = "Glk Audio Port",
+		.stream_name = "Audio",
+		.cpu_dai_name = "System Pin",
+		.platform_name = "0000:00:0e.0",
+		.dynamic = 1,
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.nonatomic = 1,
+		.init = geminilake_rt5682_fe_init,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.dpcm_playback = 1,
+	},
+	[GLK_DPCM_AUDIO_CP] = {
+		.name = "Glk Audio Capture Port",
+		.stream_name = "Audio Record",
+		.cpu_dai_name = "System Pin",
+		.platform_name = "0000:00:0e.0",
+		.dynamic = 1,
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.nonatomic = 1,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.dpcm_capture = 1,
+	},
+	[GLK_DPCM_AUDIO_HS_PB] = {
+		.name = "Glk Audio Headset Playback",
+		.stream_name = "Headset Audio",
+		.cpu_dai_name = "System Pin2",
+		.platform_name = "0000:00:0e.0",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.dpcm_playback = 1,
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	[GLK_DPCM_AUDIO_ECHO_REF_CP] = {
+		.name = "Glk Audio Echo Reference cap",
+		.stream_name = "Echoreference Capture",
+		.cpu_dai_name = "Echoref Pin",
+		.platform_name = "0000:00:0e.0",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.init = NULL,
+		.capture_only = 1,
+		.nonatomic = 1,
+	},
+	[GLK_DPCM_AUDIO_REF_CP] = {
+		.name = "Glk Audio Reference cap",
+		.stream_name = "Refcap",
+		.cpu_dai_name = "Reference Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.init = NULL,
+		.dpcm_capture = 1,
+		.nonatomic = 1,
+		.dynamic = 1,
+		.ops = &geminilake_refcap_ops,
+	},
+	[GLK_DPCM_AUDIO_DMIC_CP] = {
+		.name = "Glk Audio DMIC cap",
+		.stream_name = "dmiccap",
+		.cpu_dai_name = "DMIC Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.init = NULL,
+		.dpcm_capture = 1,
+		.nonatomic = 1,
+		.dynamic = 1,
+		.ops = &geminilake_dmic_ops,
+	},
+	[GLK_DPCM_AUDIO_HDMI1_PB] = {
+		.name = "Glk HDMI Port1",
+		.stream_name = "Hdmi1",
+		.cpu_dai_name = "HDMI1 Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.dpcm_playback = 1,
+		.init = NULL,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	[GLK_DPCM_AUDIO_HDMI2_PB] =	{
+		.name = "Glk HDMI Port2",
+		.stream_name = "Hdmi2",
+		.cpu_dai_name = "HDMI2 Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.dpcm_playback = 1,
+		.init = NULL,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	[GLK_DPCM_AUDIO_HDMI3_PB] =	{
+		.name = "Glk HDMI Port3",
+		.stream_name = "Hdmi3",
+		.cpu_dai_name = "HDMI3 Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.dpcm_playback = 1,
+		.init = NULL,
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	/* Back End DAI links */
+	{
+		/* SSP1 - Codec */
+		.name = "SSP1-Codec",
+		.id = 0,
+		.cpu_dai_name = "SSP1 Pin",
+		.platform_name = "0000:00:0e.0",
+		.no_pcm = 1,
+		.codec_name = MAXIM_DEV0_NAME,
+		.codec_dai_name = GLK_MAXIM_CODEC_DAI,
+		.dai_fmt = SND_SOC_DAIFMT_I2S |
+			SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		.ignore_pmdown_time = 1,
+		.be_hw_params_fixup = geminilake_ssp_fixup,
+		.dpcm_playback = 1,
+	},
+	{
+		/* SSP2 - Codec */
+		.name = "SSP2-Codec",
+		.id = 1,
+		.cpu_dai_name = "SSP2 Pin",
+		.platform_name = "0000:00:0e.0",
+		.no_pcm = 1,
+		.codec_name = "i2c-10EC5682:00",
+		.codec_dai_name = GLK_REALTEK_CODEC_DAI,
+		.init = geminilake_rt5682_codec_init,
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		.ignore_pmdown_time = 1,
+		.be_hw_params_fixup = geminilake_ssp_fixup,
+		.ops = &geminilake_rt5682_ops,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+	},
+	{
+		.name = "dmic01",
+		.id = 2,
+		.cpu_dai_name = "DMIC01 Pin",
+		.codec_name = "dmic-codec",
+		.codec_dai_name = "dmic-hifi",
+		.platform_name = "0000:00:0e.0",
+		.ignore_suspend = 1,
+		.be_hw_params_fixup = geminilake_dmic_fixup,
+		.dpcm_capture = 1,
+		.no_pcm = 1,
+	},
+	{
+		.name = "iDisp1",
+		.id = 3,
+		.cpu_dai_name = "iDisp1 Pin",
+		.codec_name = "ehdaudio0D2",
+		.codec_dai_name = "intel-hdmi-hifi1",
+		.platform_name = "0000:00:0e.0",
+		.init = geminilake_hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+	},
+	{
+		.name = "iDisp2",
+		.id = 4,
+		.cpu_dai_name = "iDisp2 Pin",
+		.codec_name = "ehdaudio0D2",
+		.codec_dai_name = "intel-hdmi-hifi2",
+		.platform_name = "0000:00:0e.0",
+		.init = geminilake_hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+	},
+	{
+		.name = "iDisp3",
+		.id = 5,
+		.cpu_dai_name = "iDisp3 Pin",
+		.codec_name = "ehdaudio0D2",
+		.codec_dai_name = "intel-hdmi-hifi3",
+		.platform_name = "0000:00:0e.0",
+		.init = geminilake_hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+	},
+};
+
+static int glk_card_late_probe(struct snd_soc_card *card)
+{
+	struct glk_card_private *ctx = snd_soc_card_get_drvdata(card);
+	struct snd_soc_component *component = NULL;
+	char jack_name[NAME_SIZE];
+	struct glk_hdmi_pcm *pcm;
+	int err = 0;
+	int i = 0;
+
+	list_for_each_entry(pcm, &ctx->hdmi_pcm_list, head) {
+		component = pcm->codec_dai->component;
+		snprintf(jack_name, sizeof(jack_name),
+			"HDMI/DP, pcm=%d Jack", pcm->device);
+		err = snd_soc_card_jack_new(card, jack_name,
+					SND_JACK_AVOUT, &geminilake_hdmi[i],
+					NULL, 0);
+
+		if (err)
+			return err;
+
+		err = hdac_hdmi_jack_init(pcm->codec_dai, pcm->device,
+						&geminilake_hdmi[i]);
+		if (err < 0)
+			return err;
+
+		i++;
+	}
+
+	if (!component)
+		return -EINVAL;
+
+	return hdac_hdmi_jack_port_init(component, &card->dapm);
+}
+
+/* geminilake audio machine driver for SPT + RT5682 */
+static struct snd_soc_card glk_audio_card_rt5682_m98357a = {
+	.name = "glkrt5682max",
+	.owner = THIS_MODULE,
+	.dai_link = geminilake_dais,
+	.num_links = ARRAY_SIZE(geminilake_dais),
+	.controls = geminilake_controls,
+	.num_controls = ARRAY_SIZE(geminilake_controls),
+	.dapm_widgets = geminilake_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(geminilake_widgets),
+	.dapm_routes = geminilake_map,
+	.num_dapm_routes = ARRAY_SIZE(geminilake_map),
+	.fully_routed = true,
+	.late_probe = glk_card_late_probe,
+};
+
+static int geminilake_audio_probe(struct platform_device *pdev)
+{
+	struct glk_card_private *ctx;
+
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	if (!ctx)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&ctx->hdmi_pcm_list);
+
+	glk_audio_card_rt5682_m98357a.dev = &pdev->dev;
+	snd_soc_card_set_drvdata(&glk_audio_card_rt5682_m98357a, ctx);
+
+	return devm_snd_soc_register_card(&pdev->dev,
+					&glk_audio_card_rt5682_m98357a);
+}
+
+static const struct platform_device_id glk_board_ids[] = {
+	{
+		.name = "glk_rt5682_max98357a",
+		.driver_data =
+			(kernel_ulong_t)&glk_audio_card_rt5682_m98357a,
+	},
+	{ }
+};
+
+static struct platform_driver geminilake_audio = {
+	.probe = geminilake_audio_probe,
+	.driver = {
+		.name = "glk_rt5682_max98357a",
+		.pm = &snd_soc_pm_ops,
+	},
+	.id_table = glk_board_ids,
+};
+module_platform_driver(geminilake_audio)
+
+/* Module information */
+MODULE_DESCRIPTION("Geminilake Audio Machine driver-RT5682 & MAX98357A in I2S mode");
+MODULE_AUTHOR("Naveen Manohar <naveen.m@intel.com>");
+MODULE_AUTHOR("Harsha Priya <harshapriya.n@intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:glk_rt5682_max98357a");
diff --git a/sound/soc/intel/boards/kbl_da7219_max98357a.c b/sound/soc/intel/boards/kbl_da7219_max98357a.c
index 94294c27d1db..38f6ab74709d 100644
--- a/sound/soc/intel/boards/kbl_da7219_max98357a.c
+++ b/sound/soc/intel/boards/kbl_da7219_max98357a.c
@@ -152,7 +152,7 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 
 	return 0;
 }
@@ -380,6 +380,7 @@ static struct snd_soc_dai_link kabylake_dais[] = {
 		.trigger = {
 			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
 		.dpcm_capture = 1,
+		.ops = &kabylake_da7219_fe_ops,
 	},
 	[KBL_DPCM_AUDIO_DMIC_CP] = {
 		.name = "Kbl Audio DMIC cap",
diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c
index 3a61252fe450..21a6490746a6 100644
--- a/sound/soc/intel/boards/kbl_rt5663_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c
@@ -434,14 +434,14 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 		rate->min = rate->max = 48000;
 		channels->min = channels->max = 2;
 		snd_mask_none(fmt);
-		snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+		snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 	}
 	/*
 	 * The speaker on the SSP0 supports S16_LE and not S24_LE.
 	 * thus changing the mask here
 	 */
 	if (!strcmp(be_dai_link->name, "SSP0-Codec"))
-		snd_mask_set(fmt, SNDRV_PCM_FORMAT_S16_LE);
+		snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
index 92f5fb2ae0a3..a892b37eab7c 100644
--- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
@@ -307,7 +307,7 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 		rate->min = rate->max = 48000;
 		channels->min = channels->max = 2;
 		snd_mask_none(fmt);
-		snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+		snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 	} else if (!strcmp(fe_dai_link->name, "Kbl Audio DMIC cap")) {
 		if (params_channels(params) == 2 ||
 				DMIC_CH(dmic_constraints) == 2)
@@ -320,7 +320,7 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 	 * thus changing the mask here
 	 */
 	if (!strcmp(be_dai_link->name, "SSP0-Codec"))
-		snd_mask_set(fmt, SNDRV_PCM_FORMAT_S16_LE);
+		snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/skl_nau88l25_max98357a.c b/sound/soc/intel/boards/skl_nau88l25_max98357a.c
index 3ff6646cfa21..d31482b8c9bb 100644
--- a/sound/soc/intel/boards/skl_nau88l25_max98357a.c
+++ b/sound/soc/intel/boards/skl_nau88l25_max98357a.c
@@ -157,7 +157,7 @@ static int skylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP0 to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/skl_nau88l25_ssm4567.c b/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
index b0610bba3cfa..e877bb60beb1 100644
--- a/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
+++ b/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
@@ -346,7 +346,7 @@ static int skylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP0 to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 	return 0;
 }
 
diff --git a/sound/soc/intel/boards/skl_rt286.c b/sound/soc/intel/boards/skl_rt286.c
index 38a1495c29cf..0e1818dd4cc6 100644
--- a/sound/soc/intel/boards/skl_rt286.c
+++ b/sound/soc/intel/boards/skl_rt286.c
@@ -229,7 +229,7 @@ static int skylake_ssp0_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP0 to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 	return 0;
 }
 
diff --git a/sound/soc/intel/common/Makefile b/sound/soc/intel/common/Makefile
index 7379d8830c39..915a34cdc8ac 100644
--- a/sound/soc/intel/common/Makefile
+++ b/sound/soc/intel/common/Makefile
@@ -3,7 +3,11 @@ snd-soc-sst-dsp-objs := sst-dsp.o
 snd-soc-sst-acpi-objs := sst-acpi.o
 snd-soc-sst-ipc-objs := sst-ipc.o
 snd-soc-sst-firmware-objs := sst-firmware.o
-snd-soc-acpi-intel-match-objs := soc-acpi-intel-byt-match.o soc-acpi-intel-cht-match.o soc-acpi-intel-hsw-bdw-match.o
+snd-soc-acpi-intel-match-objs := soc-acpi-intel-byt-match.o soc-acpi-intel-cht-match.o \
+	soc-acpi-intel-hsw-bdw-match.o \
+	soc-acpi-intel-skl-match.o soc-acpi-intel-kbl-match.o \
+	soc-acpi-intel-bxt-match.o soc-acpi-intel-glk-match.o \
+	soc-acpi-intel-cnl-match.o
 
 obj-$(CONFIG_SND_SOC_INTEL_SST) += snd-soc-sst-dsp.o snd-soc-sst-ipc.o
 obj-$(CONFIG_SND_SOC_INTEL_SST_ACPI) += snd-soc-sst-acpi.o
diff --git a/sound/soc/intel/common/soc-acpi-intel-bxt-match.c b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
new file mode 100644
index 000000000000..f39386e540d3
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-bxt-match.c - tables and support for BXT ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+
+static struct snd_soc_acpi_codecs bxt_codecs = {
+	.num_codecs = 1,
+	.codecs = {"MX98357A"}
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_bxt_machines[] = {
+	{
+		.id = "INT343A",
+		.drv_name = "bxt_alc298s_i2s",
+		.fw_filename = "intel/dsp_fw_bxtn.bin",
+	},
+	{
+		.id = "DLGS7219",
+		.drv_name = "bxt_da7219_max98357a",
+		.fw_filename = "intel/dsp_fw_bxtn.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &bxt_codecs,
+		.sof_fw_filename = "intel/sof-apl.ri",
+		.sof_tplg_filename = "intel/sof-apl-da7219.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
+	},
+	{
+		.id = "104C5122",
+		.drv_name = "bxt-pcm512x",
+		.sof_fw_filename = "intel/sof-apl.ri",
+		.sof_tplg_filename = "intel/sof-apl-pcm512x.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
+	},
+	{
+		.id = "1AEC8804",
+		.drv_name = "bxt-wm8804",
+		.sof_fw_filename = "intel/sof-apl.ri",
+		.sof_tplg_filename = "intel/sof-apl-wm8804.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
+	},
+	{
+		.id = "INT34C3",
+		.drv_name = "bxt_tdf8532",
+		.sof_fw_filename = "intel/sof-apl.ri",
+		.sof_tplg_filename = "intel/sof-apl-tdf8532.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_bxt_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-byt-match.c b/sound/soc/intel/common/soc-acpi-intel-byt-match.c
index bfe1ca68a542..4daa8a4f0c0c 100644
--- a/sound/soc/intel/common/soc-acpi-intel-byt-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-byt-match.c
@@ -59,8 +59,8 @@ static struct snd_soc_acpi_mach byt_thinkpad_10 = {
 	.drv_name = "cht-bsw-rt5672",
 	.fw_filename = "intel/fw_sst_0f28.bin",
 	.board = "cht-bsw",
-	.sof_fw_filename = "intel/reef-byt.ri",
-	.sof_tplg_filename = "intel/reef-byt-rt5670.tplg",
+	.sof_fw_filename = "intel/sof-byt.ri",
+	.sof_tplg_filename = "intel/sof-byt-rt5670.tplg",
 	.asoc_plat_name = "sst-mfld-platform",
 };
 
@@ -98,8 +98,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcr_rt5640",
 		.machine_quirk = byt_quirk,
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -107,8 +107,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcr_rt5640",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcr_rt5640",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -116,8 +116,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcr_rt5640",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcr_rt5640",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -125,8 +125,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcr_rt5651",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcr_rt5651",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5651.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5651.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -134,8 +134,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcht_da7213",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcht_da7213",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-da7213.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-da7213.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -143,8 +143,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcht_da7213",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcht_da7213",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-da7213.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-da7213.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	/* some Baytrail platforms rely on RT5645, use CHT machine driver */
@@ -153,8 +153,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -162,8 +162,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	/* use CHT driver to Baytrail Chromebooks */
@@ -172,8 +172,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "cht-bsw-max98090",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-max98090.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-max98090.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 #if IS_ENABLED(CONFIG_SND_SOC_INTEL_BYT_CHT_NOCODEC_MACH)
diff --git a/sound/soc/intel/common/soc-acpi-intel-cht-match.c b/sound/soc/intel/common/soc-acpi-intel-cht-match.c
index ad1eb2d644be..91bb99b69601 100644
--- a/sound/soc/intel/common/soc-acpi-intel-cht-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-cht-match.c
@@ -44,8 +44,8 @@ static struct snd_soc_acpi_mach cht_surface_mach = {
 	.drv_name = "cht-bsw-rt5645",
 	.fw_filename = "intel/fw_sst_22a8.bin",
 	.board = "cht-bsw",
-	.sof_fw_filename = "intel/reef-cht.ri",
-	.sof_tplg_filename = "intel/reef-cht-rt5645.tplg",
+	.sof_fw_filename = "intel/sof-cht.ri",
+	.sof_tplg_filename = "intel/sof-cht-rt5645.tplg",
 	.asoc_plat_name = "sst-mfld-platform",
 };
 
@@ -68,8 +68,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5672",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5670.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5670.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -77,8 +77,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5672",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5670.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5670.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -86,8 +86,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -95,8 +95,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -104,8 +104,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -113,8 +113,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-max98090",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-max98090.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-max98090.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -122,8 +122,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-nau8824",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-nau8824.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-nau8824.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -131,8 +131,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcht_da7213",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcht_da7213",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-da7213.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-da7213.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -140,8 +140,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcht_da7213",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcht_da7213",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-da7213.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-da7213.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -149,8 +149,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcht_es8316",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcht_es8316",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-es8316.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-es8316.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	/* some CHT-T platforms rely on RT5640, use Baytrail machine driver */
@@ -160,8 +160,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcr_rt5640",
 		.machine_quirk = cht_quirk,
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -169,8 +169,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcr_rt5640",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcr_rt5640",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	/* some CHT-T platforms rely on RT5651, use Baytrail machine driver */
@@ -179,8 +179,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcr_rt5651",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcr_rt5651",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5651.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5651.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 #if IS_ENABLED(CONFIG_SND_SOC_INTEL_BYT_CHT_NOCODEC_MACH)
diff --git a/sound/soc/intel/common/soc-acpi-intel-cnl-match.c b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
new file mode 100644
index 000000000000..ec8e28e7b937
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-cnl-match.c - tables and support for CNL ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+#include "../skylake/skl.h"
+
+static struct skl_machine_pdata cnl_pdata = {
+	.use_tplg_pcm = true,
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[] = {
+	{
+		.id = "INT34C2",
+		.drv_name = "cnl_rt274",
+		.fw_filename = "intel/dsp_fw_cnl.bin",
+		.pdata = &cnl_pdata,
+		.sof_fw_filename = "intel/sof-cnl.ri",
+		.sof_tplg_filename = "intel/sof-cnl-rt274.tplg",
+		.asoc_plat_name = "0000:00:1f.3",
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_cnl_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-glk-match.c b/sound/soc/intel/common/soc-acpi-intel-glk-match.c
new file mode 100644
index 000000000000..305875af71ca
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-glk-match.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-glk-match.c - tables and support for GLK ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+
+static struct snd_soc_acpi_codecs glk_codecs = {
+	.num_codecs = 1,
+	.codecs = {"MX98357A"}
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[] = {
+	{
+		.id = "INT343A",
+		.drv_name = "glk_alc298s_i2s",
+		.fw_filename = "intel/dsp_fw_glk.bin",
+		.sof_fw_filename = "intel/sof-glk.ri",
+		.sof_tplg_filename = "intel/sof-glk-alc298.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
+	},
+	{
+		.id = "DLGS7219",
+		.drv_name = "glk_da7219_max98357a",
+		.fw_filename = "intel/dsp_fw_glk.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &glk_codecs,
+		.sof_fw_filename = "intel/sof-glk.ri",
+		.sof_tplg_filename = "intel/sof-glk-da7219.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_glk_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c b/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c
index e0e8c8c27528..494a0ea9b029 100644
--- a/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c
@@ -23,8 +23,8 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_haswell_machines[] = {
 		.id = "INT33CA",
 		.drv_name = "haswell-audio",
 		.fw_filename = "intel/IntcSST1.bin",
-		.sof_fw_filename = "intel/reef-hsw.ri",
-		.sof_tplg_filename = "intel/reef-hsw.tplg",
+		.sof_fw_filename = "intel/sof-hsw.ri",
+		.sof_tplg_filename = "intel/sof-hsw.tplg",
 		.asoc_plat_name = "haswell-pcm-audio",
 	},
 	{}
@@ -36,24 +36,24 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_broadwell_machines[] = {
 		.id = "INT343A",
 		.drv_name = "broadwell-audio",
 		.fw_filename =  "intel/IntcSST2.bin",
-		.sof_fw_filename = "intel/reef-bdw.ri",
-		.sof_tplg_filename = "intel/reef-bdw-rt286.tplg",
+		.sof_fw_filename = "intel/sof-bdw.ri",
+		.sof_tplg_filename = "intel/sof-bdw-rt286.tplg",
 		.asoc_plat_name = "haswell-pcm-audio",
 	},
 	{
 		.id = "RT5677CE",
 		.drv_name = "bdw-rt5677",
 		.fw_filename =  "intel/IntcSST2.bin",
-		.sof_fw_filename = "intel/reef-bdw.ri",
-		.sof_tplg_filename = "intel/reef-bdw-rt286.tplg",
+		.sof_fw_filename = "intel/sof-bdw.ri",
+		.sof_tplg_filename = "intel/sof-bdw-rt5677.tplg",
 		.asoc_plat_name = "haswell-pcm-audio",
 	},
 	{
 		.id = "INT33CA",
 		.drv_name = "haswell-audio",
 		.fw_filename = "intel/IntcSST2.bin",
-		.sof_fw_filename = "intel/reef-bdw.ri",
-		.sof_tplg_filename = "intel/reef-bdw-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-bdw.ri",
+		.sof_tplg_filename = "intel/sof-bdw-rt5640.tplg",
 		.asoc_plat_name = "haswell-pcm-audio",
 	},
 	{}
diff --git a/sound/soc/intel/common/soc-acpi-intel-kbl-match.c b/sound/soc/intel/common/soc-acpi-intel-kbl-match.c
new file mode 100644
index 000000000000..0ee173ca437d
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-kbl-match.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-kbl-match.c - tables and support for KBL ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+#include "../skylake/skl.h"
+
+static struct skl_machine_pdata skl_dmic_data;
+
+static struct snd_soc_acpi_codecs kbl_codecs = {
+	.num_codecs = 1,
+	.codecs = {"10508825"}
+};
+
+static struct snd_soc_acpi_codecs kbl_poppy_codecs = {
+	.num_codecs = 1,
+	.codecs = {"10EC5663"}
+};
+
+static struct snd_soc_acpi_codecs kbl_5663_5514_codecs = {
+	.num_codecs = 2,
+	.codecs = {"10EC5663", "10EC5514"}
+};
+
+static struct snd_soc_acpi_codecs kbl_7219_98357_codecs = {
+	.num_codecs = 1,
+	.codecs = {"MX98357A"}
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_kbl_machines[] = {
+	{
+		.id = "INT343A",
+		.drv_name = "kbl_alc286s_i2s",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+	},
+	{
+		.id = "INT343B",
+		.drv_name = "kbl_n88l25_s4567",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "MX98357A",
+		.drv_name = "kbl_n88l25_m98357a",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "MX98927",
+		.drv_name = "kbl_r5514_5663_max",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_5663_5514_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "MX98927",
+		.drv_name = "kbl_rt5663_m98927",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_poppy_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "10EC5663",
+		.drv_name = "kbl_rt5663",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+	},
+	{
+		.id = "DLGS7219",
+		.drv_name = "kbl_da7219_max98357a",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_7219_98357_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_kbl_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-skl-match.c b/sound/soc/intel/common/soc-acpi-intel-skl-match.c
new file mode 100644
index 000000000000..0c9c0edd35b3
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-skl-match.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-skl-match.c - tables and support for SKL ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+#include "../skylake/skl.h"
+
+static struct skl_machine_pdata skl_dmic_data;
+
+static struct snd_soc_acpi_codecs skl_codecs = {
+	.num_codecs = 1,
+	.codecs = {"10508825"}
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_skl_machines[] = {
+	{
+		.id = "INT343A",
+		.drv_name = "skl_alc286s_i2s",
+		.fw_filename = "intel/dsp_fw_release.bin",
+	},
+	{
+		.id = "INT343B",
+		.drv_name = "skl_n88l25_s4567",
+		.fw_filename = "intel/dsp_fw_release.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &skl_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "MX98357A",
+		.drv_name = "skl_n88l25_m98357a",
+		.fw_filename = "intel/dsp_fw_release.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &skl_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_skl_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/sst-firmware.c b/sound/soc/intel/common/sst-firmware.c
index 657afc02f1c4..11041aedea31 100644
--- a/sound/soc/intel/common/sst-firmware.c
+++ b/sound/soc/intel/common/sst-firmware.c
@@ -270,7 +270,7 @@ void sst_dsp_dma_put_channel(struct sst_dsp *dsp)
 }
 EXPORT_SYMBOL_GPL(sst_dsp_dma_put_channel);
 
-int sst_dma_new(struct sst_dsp *sst)
+static int sst_dma_new(struct sst_dsp *sst)
 {
 	struct sst_pdata *sst_pdata = sst->pdata;
 	struct sst_dma *dma;
@@ -320,9 +320,8 @@ err_dma_dev:
 	devm_kfree(sst->dev, dma);
 	return ret;
 }
-EXPORT_SYMBOL(sst_dma_new);
 
-void sst_dma_free(struct sst_dma *dma)
+static void sst_dma_free(struct sst_dma *dma)
 {
 
 	if (dma == NULL)
@@ -335,7 +334,6 @@ void sst_dma_free(struct sst_dma *dma)
 		dw_remove(dma->chip);
 
 }
-EXPORT_SYMBOL(sst_dma_free);
 
 /* create new generic firmware object */
 struct sst_fw *sst_fw_new(struct sst_dsp *dsp, 
diff --git a/sound/soc/intel/haswell/sst-haswell-dsp.c b/sound/soc/intel/haswell/sst-haswell-dsp.c
index b2bec36d074c..a28220e67cdf 100644
--- a/sound/soc/intel/haswell/sst-haswell-dsp.c
+++ b/sound/soc/intel/haswell/sst-haswell-dsp.c
@@ -93,29 +93,31 @@ static int hsw_parse_module(struct sst_dsp *dsp, struct sst_fw *fw,
 	struct sst_module_template template;
 	int count, ret;
 	void __iomem *ram;
+	int type = le16_to_cpu(module->type);
+	int entry_point = le32_to_cpu(module->entry_point);
 
 	/* TODO: allowed module types need to be configurable */
-	if (module->type != SST_HSW_MODULE_BASE_FW
-		&& module->type != SST_HSW_MODULE_PCM_SYSTEM
-		&& module->type != SST_HSW_MODULE_PCM
-		&& module->type != SST_HSW_MODULE_PCM_REFERENCE
-		&& module->type != SST_HSW_MODULE_PCM_CAPTURE
-		&& module->type != SST_HSW_MODULE_WAVES
-		&& module->type != SST_HSW_MODULE_LPAL)
+	if (type != SST_HSW_MODULE_BASE_FW &&
+	    type != SST_HSW_MODULE_PCM_SYSTEM &&
+	    type != SST_HSW_MODULE_PCM &&
+	    type != SST_HSW_MODULE_PCM_REFERENCE &&
+	    type != SST_HSW_MODULE_PCM_CAPTURE &&
+	    type != SST_HSW_MODULE_WAVES &&
+	    type != SST_HSW_MODULE_LPAL)
 		return 0;
 
 	dev_dbg(dsp->dev, "new module sign 0x%s size 0x%x blocks 0x%x type 0x%x\n",
 		module->signature, module->mod_size,
-		module->blocks, module->type);
-	dev_dbg(dsp->dev, " entrypoint 0x%x\n", module->entry_point);
+		module->blocks, type);
+	dev_dbg(dsp->dev, " entrypoint 0x%x\n", entry_point);
 	dev_dbg(dsp->dev, " persistent 0x%x scratch 0x%x\n",
 		module->info.persistent_size, module->info.scratch_size);
 
 	memset(&template, 0, sizeof(template));
-	template.id = module->type;
-	template.entry = module->entry_point - 4;
-	template.persistent_size = module->info.persistent_size;
-	template.scratch_size = module->info.scratch_size;
+	template.id = type;
+	template.entry = entry_point - 4;
+	template.persistent_size = le32_to_cpu(module->info.persistent_size);
+	template.scratch_size = le32_to_cpu(module->info.scratch_size);
 
 	mod = sst_module_new(fw, &template, NULL);
 	if (mod == NULL)
@@ -123,26 +125,26 @@ static int hsw_parse_module(struct sst_dsp *dsp, struct sst_fw *fw,
 
 	block = (void *)module + sizeof(*module);
 
-	for (count = 0; count < module->blocks; count++) {
+	for (count = 0; count < le32_to_cpu(module->blocks); count++) {
 
-		if (block->size <= 0) {
+		if (le32_to_cpu(block->size) <= 0) {
 			dev_err(dsp->dev,
 				"error: block %d size invalid\n", count);
 			sst_module_free(mod);
 			return -EINVAL;
 		}
 
-		switch (block->type) {
+		switch (le32_to_cpu(block->type)) {
 		case SST_HSW_IRAM:
 			ram = dsp->addr.lpe;
-			mod->offset =
-				block->ram_offset + dsp->addr.iram_offset;
+			mod->offset = le32_to_cpu(block->ram_offset) +
+				dsp->addr.iram_offset;
 			mod->type = SST_MEM_IRAM;
 			break;
 		case SST_HSW_DRAM:
 		case SST_HSW_REGS:
 			ram = dsp->addr.lpe;
-			mod->offset = block->ram_offset;
+			mod->offset = le32_to_cpu(block->ram_offset);
 			mod->type = SST_MEM_DRAM;
 			break;
 		default:
@@ -152,7 +154,7 @@ static int hsw_parse_module(struct sst_dsp *dsp, struct sst_fw *fw,
 			return -EINVAL;
 		}
 
-		mod->size = block->size;
+		mod->size = le32_to_cpu(block->size);
 		mod->data = (void *)block + sizeof(*block);
 		mod->data_offset = mod->data - fw->dma_buf;
 
@@ -169,7 +171,8 @@ static int hsw_parse_module(struct sst_dsp *dsp, struct sst_fw *fw,
 			return ret;
 		}
 
-		block = (void *)block + sizeof(*block) + block->size;
+		block = (void *)block + sizeof(*block) +
+			le32_to_cpu(block->size);
 	}
 	mod->state = SST_MODULE_STATE_LOADED;
 
@@ -188,7 +191,8 @@ static int hsw_parse_fw_image(struct sst_fw *sst_fw)
 
 	/* verify FW */
 	if ((strncmp(header->signature, SST_HSW_FW_SIGN, 4) != 0) ||
-		(sst_fw->size != header->file_size + sizeof(*header))) {
+	    (sst_fw->size !=
+	     le32_to_cpu(header->file_size) + sizeof(*header))) {
 		dev_err(dsp->dev, "error: invalid fw sign/filesize mismatch\n");
 		return -EINVAL;
 	}
@@ -199,7 +203,7 @@ static int hsw_parse_fw_image(struct sst_fw *sst_fw)
 
 	/* parse each module */
 	module = (void *)sst_fw->dma_buf + sizeof(*header);
-	for (count = 0; count < header->modules; count++) {
+	for (count = 0; count < le32_to_cpu(header->modules); count++) {
 
 		/* module */
 		ret = hsw_parse_module(dsp, sst_fw, module);
@@ -207,7 +211,8 @@ static int hsw_parse_fw_image(struct sst_fw *sst_fw)
 			dev_err(dsp->dev, "error: invalid module %d\n", count);
 			return ret;
 		}
-		module = (void *)module + sizeof(*module) + module->mod_size;
+		module = (void *)module + sizeof(*module) +
+			le32_to_cpu(module->mod_size);
 	}
 
 	return 0;
diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c
index d5f9c30eba32..8bfb8b0fa3d5 100644
--- a/sound/soc/intel/skylake/skl-messages.c
+++ b/sound/soc/intel/skylake/skl-messages.c
@@ -33,8 +33,7 @@
 static int skl_alloc_dma_buf(struct device *dev,
 		struct snd_dma_buffer *dmab, size_t size)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 
 	if (!bus)
 		return -ENODEV;
@@ -44,8 +43,7 @@ static int skl_alloc_dma_buf(struct device *dev,
 
 static int skl_free_dma_buf(struct device *dev, struct snd_dma_buffer *dmab)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 
 	if (!bus)
 		return -ENODEV;
@@ -89,8 +87,7 @@ void skl_dsp_enable_notification(struct skl_sst *ctx, bool enable)
 static int skl_dsp_setup_spib(struct device *dev, unsigned int size,
 				int stream_tag, int enable)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	struct hdac_stream *stream = snd_hdac_get_stream(bus,
 			SNDRV_PCM_STREAM_PLAYBACK, stream_tag);
 	struct hdac_ext_stream *estream;
@@ -100,10 +97,10 @@ static int skl_dsp_setup_spib(struct device *dev, unsigned int size,
 
 	estream = stream_to_hdac_ext_stream(stream);
 	/* enable/disable SPIB for this hdac stream */
-	snd_hdac_ext_stream_spbcap_enable(ebus, enable, stream->index);
+	snd_hdac_ext_stream_spbcap_enable(bus, enable, stream->index);
 
 	/* set the spib value */
-	snd_hdac_ext_stream_set_spib(ebus, estream, size);
+	snd_hdac_ext_stream_set_spib(bus, estream, size);
 
 	return 0;
 }
@@ -111,8 +108,7 @@ static int skl_dsp_setup_spib(struct device *dev, unsigned int size,
 static int skl_dsp_prepare(struct device *dev, unsigned int format,
 			unsigned int size, struct snd_dma_buffer *dmab)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	struct hdac_ext_stream *estream;
 	struct hdac_stream *stream;
 	struct snd_pcm_substream substream;
@@ -124,7 +120,7 @@ static int skl_dsp_prepare(struct device *dev, unsigned int format,
 	memset(&substream, 0, sizeof(substream));
 	substream.stream = SNDRV_PCM_STREAM_PLAYBACK;
 
-	estream = snd_hdac_ext_stream_assign(ebus, &substream,
+	estream = snd_hdac_ext_stream_assign(bus, &substream,
 					HDAC_EXT_STREAM_TYPE_HOST);
 	if (!estream)
 		return -ENODEV;
@@ -143,9 +139,8 @@ static int skl_dsp_prepare(struct device *dev, unsigned int format,
 
 static int skl_dsp_trigger(struct device *dev, bool start, int stream_tag)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	struct hdac_stream *stream;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 
 	if (!bus)
 		return -ENODEV;
@@ -163,10 +158,9 @@ static int skl_dsp_trigger(struct device *dev, bool start, int stream_tag)
 static int skl_dsp_cleanup(struct device *dev,
 		struct snd_dma_buffer *dmab, int stream_tag)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	struct hdac_stream *stream;
 	struct hdac_ext_stream *estream;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 
 	if (!bus)
 		return -ENODEV;
@@ -270,8 +264,7 @@ const struct skl_dsp_ops *skl_get_dsp_ops(int pci_id)
 int skl_init_dsp(struct skl *skl)
 {
 	void __iomem *mmio_base;
-	struct hdac_ext_bus *ebus = &skl->ebus;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct skl_dsp_loader_ops loader_ops;
 	int irq = bus->irq;
 	const struct skl_dsp_ops *ops;
@@ -279,8 +272,8 @@ int skl_init_dsp(struct skl *skl)
 	int ret;
 
 	/* enable ppcap interrupt */
-	snd_hdac_ext_bus_ppcap_enable(&skl->ebus, true);
-	snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, true);
+	snd_hdac_ext_bus_ppcap_enable(bus, true);
+	snd_hdac_ext_bus_ppcap_int_enable(bus, true);
 
 	/* read the BAR of the ADSP MMIO */
 	mmio_base = pci_ioremap_bar(skl->pci, 4);
@@ -335,12 +328,11 @@ unmap_mmio:
 
 int skl_free_dsp(struct skl *skl)
 {
-	struct hdac_ext_bus *ebus = &skl->ebus;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct skl_sst *ctx = skl->skl_sst;
 
 	/* disable  ppcap interrupt */
-	snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, false);
+	snd_hdac_ext_bus_ppcap_int_enable(bus, false);
 
 	ctx->dsp_ops->cleanup(bus->dev, ctx);
 
@@ -383,10 +375,11 @@ int skl_suspend_late_dsp(struct skl *skl)
 int skl_suspend_dsp(struct skl *skl)
 {
 	struct skl_sst *ctx = skl->skl_sst;
+	struct hdac_bus *bus = skl_to_bus(skl);
 	int ret;
 
 	/* if ppcap is not supported return 0 */
-	if (!skl->ebus.bus.ppcap)
+	if (!bus->ppcap)
 		return 0;
 
 	ret = skl_dsp_sleep(ctx->dsp);
@@ -394,8 +387,8 @@ int skl_suspend_dsp(struct skl *skl)
 		return ret;
 
 	/* disable ppcap interrupt */
-	snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, false);
-	snd_hdac_ext_bus_ppcap_enable(&skl->ebus, false);
+	snd_hdac_ext_bus_ppcap_int_enable(bus, false);
+	snd_hdac_ext_bus_ppcap_enable(bus, false);
 
 	return 0;
 }
@@ -403,15 +396,16 @@ int skl_suspend_dsp(struct skl *skl)
 int skl_resume_dsp(struct skl *skl)
 {
 	struct skl_sst *ctx = skl->skl_sst;
+	struct hdac_bus *bus = skl_to_bus(skl);
 	int ret;
 
 	/* if ppcap is not supported return 0 */
-	if (!skl->ebus.bus.ppcap)
+	if (!bus->ppcap)
 		return 0;
 
 	/* enable ppcap interrupt */
-	snd_hdac_ext_bus_ppcap_enable(&skl->ebus, true);
-	snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, true);
+	snd_hdac_ext_bus_ppcap_enable(bus, true);
+	snd_hdac_ext_bus_ppcap_int_enable(bus, true);
 
 	/* check if DSP 1st boot is done */
 	if (skl->skl_sst->is_first_boot == true)
diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c
index b9b140275be0..01a050cf8775 100644
--- a/sound/soc/intel/skylake/skl-nhlt.c
+++ b/sound/soc/intel/skylake/skl-nhlt.c
@@ -141,7 +141,7 @@ struct nhlt_specific_cfg
 {
 	struct nhlt_fmt *fmt;
 	struct nhlt_endpoint *epnt;
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct device *dev = bus->dev;
 	struct nhlt_specific_cfg *sp_config;
 	struct nhlt_acpi_table *nhlt = skl->nhlt;
@@ -228,7 +228,7 @@ static void skl_nhlt_trim_space(char *trim)
 int skl_nhlt_update_topology_bin(struct skl *skl)
 {
 	struct nhlt_acpi_table *nhlt = (struct nhlt_acpi_table *)skl->nhlt;
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct device *dev = bus->dev;
 
 	dev_dbg(dev, "oem_id %.6s, oem_table_id %8s oem_revision %d\n",
@@ -248,8 +248,8 @@ static ssize_t skl_nhlt_platform_id_show(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl = bus_to_skl(bus);
 	struct nhlt_acpi_table *nhlt = (struct nhlt_acpi_table *)skl->nhlt;
 	char platform_id[32];
 
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index afa86b9e4dcf..823e39103edd 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -67,16 +67,15 @@ struct hdac_ext_stream *get_hdac_ext_stream(struct snd_pcm_substream *substream)
 	return substream->runtime->private_data;
 }
 
-static struct hdac_ext_bus *get_bus_ctx(struct snd_pcm_substream *substream)
+static struct hdac_bus *get_bus_ctx(struct snd_pcm_substream *substream)
 {
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 	struct hdac_stream *hstream = hdac_stream(stream);
 	struct hdac_bus *bus = hstream->bus;
-
-	return hbus_to_ebus(bus);
+	return bus;
 }
 
-static int skl_substream_alloc_pages(struct hdac_ext_bus *ebus,
+static int skl_substream_alloc_pages(struct hdac_bus *bus,
 				 struct snd_pcm_substream *substream,
 				 size_t size)
 {
@@ -95,7 +94,7 @@ static int skl_substream_free_pages(struct hdac_bus *bus,
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static void skl_set_pcm_constrains(struct hdac_ext_bus *ebus,
+static void skl_set_pcm_constrains(struct hdac_bus *bus,
 				 struct snd_pcm_runtime *runtime)
 {
 	snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS);
@@ -105,9 +104,9 @@ static void skl_set_pcm_constrains(struct hdac_ext_bus *ebus,
 				     20, 178000000);
 }
 
-static enum hdac_ext_stream_type skl_get_host_stream_type(struct hdac_ext_bus *ebus)
+static enum hdac_ext_stream_type skl_get_host_stream_type(struct hdac_bus *bus)
 {
-	if ((ebus_to_hbus(ebus))->ppcap)
+	if (bus->ppcap)
 		return HDAC_EXT_STREAM_TYPE_HOST;
 	else
 		return HDAC_EXT_STREAM_TYPE_COUPLED;
@@ -123,9 +122,9 @@ static enum hdac_ext_stream_type skl_get_host_stream_type(struct hdac_ext_bus *e
 static void skl_set_suspend_active(struct snd_pcm_substream *substream,
 					 struct snd_soc_dai *dai, bool enable)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct snd_soc_dapm_widget *w;
-	struct skl *skl = ebus_to_skl(ebus);
+	struct skl *skl = bus_to_skl(bus);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		w = dai->playback_widget;
@@ -140,8 +139,7 @@ static void skl_set_suspend_active(struct snd_pcm_substream *substream,
 
 int skl_pcm_host_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	unsigned int format_val;
 	struct hdac_stream *hstream;
 	struct hdac_ext_stream *stream;
@@ -153,7 +151,7 @@ int skl_pcm_host_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 		return -EINVAL;
 
 	stream = stream_to_hdac_ext_stream(hstream);
-	snd_hdac_ext_stream_decouple(ebus, stream, true);
+	snd_hdac_ext_stream_decouple(bus, stream, true);
 
 	format_val = snd_hdac_calc_stream_format(params->s_freq,
 			params->ch, params->format, params->host_bps, 0);
@@ -177,8 +175,7 @@ int skl_pcm_host_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 
 int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	unsigned int format_val;
 	struct hdac_stream *hstream;
 	struct hdac_ext_stream *stream;
@@ -190,7 +187,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 		return -EINVAL;
 
 	stream = stream_to_hdac_ext_stream(hstream);
-	snd_hdac_ext_stream_decouple(ebus, stream, true);
+	snd_hdac_ext_stream_decouple(bus, stream, true);
 	format_val = snd_hdac_calc_stream_format(params->s_freq, params->ch,
 					params->format, params->link_bps, 0);
 
@@ -201,7 +198,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 
 	snd_hdac_ext_link_stream_setup(stream, format_val);
 
-	list_for_each_entry(link, &ebus->hlink_list, list) {
+	list_for_each_entry(link, &bus->hlink_list, list) {
 		if (link->index == params->link_index)
 			snd_hdac_ext_link_set_stream_id(link,
 					hstream->stream_tag);
@@ -215,7 +212,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 static int skl_pcm_open(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct hdac_ext_stream *stream;
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct skl_dma_params *dma_params;
@@ -224,12 +221,12 @@ static int skl_pcm_open(struct snd_pcm_substream *substream,
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
 
-	stream = snd_hdac_ext_stream_assign(ebus, substream,
-					skl_get_host_stream_type(ebus));
+	stream = snd_hdac_ext_stream_assign(bus, substream,
+					skl_get_host_stream_type(bus));
 	if (stream == NULL)
 		return -EBUSY;
 
-	skl_set_pcm_constrains(ebus, runtime);
+	skl_set_pcm_constrains(bus, runtime);
 
 	/*
 	 * disable WALLCLOCK timestamps for capture streams
@@ -301,7 +298,7 @@ static int skl_pcm_hw_params(struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *params,
 				struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct skl_pipe_params p_params = {0};
@@ -309,7 +306,7 @@ static int skl_pcm_hw_params(struct snd_pcm_substream *substream,
 	int ret, dma_id;
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
-	ret = skl_substream_alloc_pages(ebus, substream,
+	ret = skl_substream_alloc_pages(bus, substream,
 					  params_buffer_bytes(params));
 	if (ret < 0)
 		return ret;
@@ -343,14 +340,14 @@ static void skl_pcm_close(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct skl_dma_params *dma_params = NULL;
-	struct skl *skl = ebus_to_skl(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	struct skl_module_cfg *mconfig;
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
 
-	snd_hdac_ext_stream_release(stream, skl_get_host_stream_type(ebus));
+	snd_hdac_ext_stream_release(stream, skl_get_host_stream_type(bus));
 
 	dma_params = snd_soc_dai_get_dma_data(dai, substream);
 	/*
@@ -380,7 +377,7 @@ static void skl_pcm_close(struct snd_pcm_substream *substream,
 static int skl_pcm_hw_free(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 	struct skl *skl = get_skl_ctx(dai->dev);
 	struct skl_module_cfg *mconfig;
@@ -400,7 +397,7 @@ static int skl_pcm_hw_free(struct snd_pcm_substream *substream,
 	snd_hdac_stream_cleanup(hdac_stream(stream));
 	hdac_stream(stream)->prepared = 0;
 
-	return skl_substream_free_pages(ebus_to_hbus(ebus), substream);
+	return skl_substream_free_pages(bus, substream);
 }
 
 static int skl_be_hw_params(struct snd_pcm_substream *substream,
@@ -420,8 +417,7 @@ static int skl_be_hw_params(struct snd_pcm_substream *substream,
 static int skl_decoupled_trigger(struct snd_pcm_substream *substream,
 		int cmd)
 {
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	struct hdac_ext_stream *stream;
 	int start;
 	unsigned long cookie;
@@ -470,7 +466,7 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd,
 	struct skl *skl = get_skl_ctx(dai->dev);
 	struct skl_sst *ctx = skl->skl_sst;
 	struct skl_module_cfg *mconfig;
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 	struct snd_soc_dapm_widget *w;
 	int ret;
@@ -492,9 +488,9 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd,
 			 * dpib & lpib position to resume before starting the
 			 * DMA
 			 */
-			snd_hdac_ext_stream_drsm_enable(ebus, true,
+			snd_hdac_ext_stream_drsm_enable(bus, true,
 						hdac_stream(stream)->index);
-			snd_hdac_ext_stream_set_dpibr(ebus, stream,
+			snd_hdac_ext_stream_set_dpibr(bus, stream,
 							stream->lpib);
 			snd_hdac_ext_stream_set_lpib(stream, stream->lpib);
 		}
@@ -528,14 +524,14 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd,
 		ret = skl_decoupled_trigger(substream, cmd);
 		if ((cmd == SNDRV_PCM_TRIGGER_SUSPEND) && !w->ignore_suspend) {
 			/* save the dpib and lpib positions */
-			stream->dpib = readl(ebus->bus.remap_addr +
+			stream->dpib = readl(bus->remap_addr +
 					AZX_REG_VS_SDXDPIB_XBASE +
 					(AZX_REG_VS_SDXDPIB_XINTERVAL *
 					hdac_stream(stream)->index));
 
 			stream->lpib = snd_hdac_stream_get_pos_lpib(
 							hdac_stream(stream));
-			snd_hdac_ext_stream_decouple(ebus, stream, false);
+			snd_hdac_ext_stream_decouple(bus, stream, false);
 		}
 		break;
 
@@ -546,11 +542,12 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd,
 	return 0;
 }
 
+
 static int skl_link_hw_params(struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *params,
 				struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct hdac_ext_stream *link_dev;
 	struct snd_soc_pcm_runtime *rtd = snd_pcm_substream_chip(substream);
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
@@ -558,14 +555,14 @@ static int skl_link_hw_params(struct snd_pcm_substream *substream,
 	struct hdac_ext_link *link;
 	int stream_tag;
 
-	link_dev = snd_hdac_ext_stream_assign(ebus, substream,
+	link_dev = snd_hdac_ext_stream_assign(bus, substream,
 					HDAC_EXT_STREAM_TYPE_LINK);
 	if (!link_dev)
 		return -EBUSY;
 
 	snd_soc_dai_set_dma_data(dai, substream, (void *)link_dev);
 
-	link = snd_hdac_ext_bus_get_link(ebus, codec_dai->component->name);
+	link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name);
 	if (!link)
 		return -EINVAL;
 
@@ -610,7 +607,7 @@ static int skl_link_pcm_trigger(struct snd_pcm_substream *substream,
 {
 	struct hdac_ext_stream *link_dev =
 				snd_soc_dai_get_dma_data(dai, substream);
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 
 	dev_dbg(dai->dev, "In %s cmd=%d\n", __func__, cmd);
@@ -626,7 +623,7 @@ static int skl_link_pcm_trigger(struct snd_pcm_substream *substream,
 	case SNDRV_PCM_TRIGGER_STOP:
 		snd_hdac_ext_link_stream_clear(link_dev);
 		if (cmd == SNDRV_PCM_TRIGGER_SUSPEND)
-			snd_hdac_ext_stream_decouple(ebus, stream, false);
+			snd_hdac_ext_stream_decouple(bus, stream, false);
 		break;
 
 	default:
@@ -638,7 +635,7 @@ static int skl_link_pcm_trigger(struct snd_pcm_substream *substream,
 static int skl_link_hw_free(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct snd_soc_pcm_runtime *rtd = snd_pcm_substream_chip(substream);
 	struct hdac_ext_stream *link_dev =
 				snd_soc_dai_get_dma_data(dai, substream);
@@ -648,7 +645,7 @@ static int skl_link_hw_free(struct snd_pcm_substream *substream,
 
 	link_dev->link_prepared = 0;
 
-	link = snd_hdac_ext_bus_get_link(ebus, rtd->codec_dai->component->name);
+	link = snd_hdac_ext_bus_get_link(bus, rtd->codec_dai->component->name);
 	if (!link)
 		return -EINVAL;
 
@@ -1017,10 +1014,11 @@ static struct snd_soc_dai_driver skl_platform_dai[] = {
 },
 };
 
-int skl_dai_load(struct snd_soc_component *cmp,
-		 struct snd_soc_dai_driver *pcm_dai)
+int skl_dai_load(struct snd_soc_component *cmp, int index,
+			struct snd_soc_dai_driver *dai_drv,
+			struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai)
 {
-	pcm_dai->ops = &skl_pcm_dai_ops;
+	dai_drv->ops = &skl_pcm_dai_ops;
 
 	return 0;
 }
@@ -1041,8 +1039,7 @@ static int skl_platform_open(struct snd_pcm_substream *substream)
 static int skl_coupled_trigger(struct snd_pcm_substream *substream,
 					int cmd)
 {
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	struct hdac_ext_stream *stream;
 	struct snd_pcm_substream *s;
 	bool start;
@@ -1115,9 +1112,9 @@ static int skl_coupled_trigger(struct snd_pcm_substream *substream,
 static int skl_platform_pcm_trigger(struct snd_pcm_substream *substream,
 					int cmd)
 {
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 
-	if (!(ebus_to_hbus(ebus))->ppcap)
+	if (!bus->ppcap)
 		return skl_coupled_trigger(substream, cmd);
 
 	return 0;
@@ -1127,7 +1124,7 @@ static snd_pcm_uframes_t skl_platform_pcm_pointer
 			(struct snd_pcm_substream *substream)
 {
 	struct hdac_ext_stream *hstream = get_hdac_ext_stream(substream);
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	unsigned int pos;
 
 	/*
@@ -1152,12 +1149,12 @@ static snd_pcm_uframes_t skl_platform_pcm_pointer
 	 */
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		pos = readl(ebus->bus.remap_addr + AZX_REG_VS_SDXDPIB_XBASE +
+		pos = readl(bus->remap_addr + AZX_REG_VS_SDXDPIB_XBASE +
 				(AZX_REG_VS_SDXDPIB_XINTERVAL *
 				hdac_stream(hstream)->index));
 	} else {
 		udelay(20);
-		readl(ebus->bus.remap_addr +
+		readl(bus->remap_addr +
 				AZX_REG_VS_SDXDPIB_XBASE +
 				(AZX_REG_VS_SDXDPIB_XINTERVAL *
 				 hdac_stream(hstream)->index));
@@ -1242,11 +1239,11 @@ static void skl_pcm_free(struct snd_pcm *pcm)
 static int skl_pcm_new(struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_dai *dai = rtd->cpu_dai;
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct snd_pcm *pcm = rtd->pcm;
 	unsigned int size;
 	int retval = 0;
-	struct skl *skl = ebus_to_skl(ebus);
+	struct skl *skl = bus_to_skl(bus);
 
 	if (dai->driver->playback.channels_min ||
 		dai->driver->capture.channels_min) {
@@ -1356,19 +1353,19 @@ static int skl_populate_modules(struct skl *skl)
 
 static int skl_platform_soc_probe(struct snd_soc_component *component)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(component->dev);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(component->dev);
+	struct skl *skl = bus_to_skl(bus);
 	const struct skl_dsp_ops *ops;
 	int ret;
 
 	pm_runtime_get_sync(component->dev);
-	if ((ebus_to_hbus(ebus))->ppcap) {
+	if (bus->ppcap) {
 		skl->component = component;
 
 		/* init debugfs */
 		skl->debugfs = skl_debugfs_init(skl);
 
-		ret = skl_tplg_init(component, ebus);
+		ret = skl_tplg_init(component, bus);
 		if (ret < 0) {
 			dev_err(component->dev, "Failed to init topology!\n");
 			return ret;
@@ -1425,10 +1422,10 @@ static const struct snd_soc_component_driver skl_component  = {
 int skl_platform_register(struct device *dev)
 {
 	int ret;
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct skl *skl = ebus_to_skl(ebus);
 	struct snd_soc_dai_driver *dais;
 	int num_dais = ARRAY_SIZE(skl_platform_dai);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
+	struct skl *skl = bus_to_skl(bus);
 
 	INIT_LIST_HEAD(&skl->ppl_list);
 	INIT_LIST_HEAD(&skl->bind_list);
@@ -1464,8 +1461,8 @@ err:
 
 int skl_platform_unregister(struct device *dev)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
+	struct skl *skl = bus_to_skl(bus);
 	struct skl_module_deferred_bind *modules, *tmp;
 
 	if (!list_empty(&skl->bind_list)) {
diff --git a/sound/soc/intel/skylake/skl-sst-cldma.c b/sound/soc/intel/skylake/skl-sst-cldma.c
index d2b1d60fec02..5bc0d38da7e3 100644
--- a/sound/soc/intel/skylake/skl-sst-cldma.c
+++ b/sound/soc/intel/skylake/skl-sst-cldma.c
@@ -83,9 +83,9 @@ static void skl_cldma_stream_clear(struct sst_dsp  *ctx)
 /* Code loader helper APIs */
 static void skl_cldma_setup_bdle(struct sst_dsp *ctx,
 		struct snd_dma_buffer *dmab_data,
-		u32 **bdlp, int size, int with_ioc)
+		__le32 **bdlp, int size, int with_ioc)
 {
-	u32 *bdl = *bdlp;
+	__le32 *bdl = *bdlp;
 
 	ctx->cl_dev.frags = 0;
 	while (size > 0) {
@@ -330,7 +330,7 @@ void skl_cldma_process_intr(struct sst_dsp *ctx)
 int skl_cldma_prepare(struct sst_dsp *ctx)
 {
 	int ret;
-	u32 *bdl;
+	__le32 *bdl;
 
 	ctx->cl_dev.bufsize = SKL_MAX_BUFFER_SIZE;
 
@@ -359,7 +359,7 @@ int skl_cldma_prepare(struct sst_dsp *ctx)
 		ctx->dsp_ops.free_dma_buf(ctx->dev, &ctx->cl_dev.dmab_data);
 		return ret;
 	}
-	bdl = (u32 *)ctx->cl_dev.dmab_bdl.area;
+	bdl = (__le32 *)ctx->cl_dev.dmab_bdl.area;
 
 	/* Allocate BDLs */
 	ctx->cl_dev.ops.cl_setup_bdle(ctx, &ctx->cl_dev.dmab_data,
diff --git a/sound/soc/intel/skylake/skl-sst-cldma.h b/sound/soc/intel/skylake/skl-sst-cldma.h
index 5b730a1a0ae4..ec736921a083 100644
--- a/sound/soc/intel/skylake/skl-sst-cldma.h
+++ b/sound/soc/intel/skylake/skl-sst-cldma.h
@@ -203,7 +203,7 @@ struct sst_dsp;
 struct skl_cl_dev_ops {
 	void (*cl_setup_bdle)(struct sst_dsp *ctx,
 			struct snd_dma_buffer *dmab_data,
-			u32 **bdlp, int size, int with_ioc);
+			__le32 **bdlp, int size, int with_ioc);
 	void (*cl_setup_controller)(struct sst_dsp *ctx,
 			struct snd_dma_buffer *dmab_bdl,
 			unsigned int max_size, u32 page_count);
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index fcdc716754b6..2620d77729c5 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -108,6 +108,9 @@ static int is_skl_dsp_widget_type(struct snd_soc_dapm_widget *w,
 	case snd_soc_dapm_aif_out:
 	case snd_soc_dapm_dai_out:
 	case snd_soc_dapm_switch:
+	case snd_soc_dapm_output:
+	case snd_soc_dapm_mux:
+
 		return false;
 	default:
 		return true;
@@ -934,7 +937,7 @@ static int skl_tplg_find_moduleid_from_uuid(struct skl *skl,
 	struct soc_bytes_ext *sb = (void *) k->private_value;
 	struct skl_algo_data *bc = (struct skl_algo_data *)sb->dobj.private;
 	struct skl_kpb_params *uuid_params, *params;
-	struct hdac_bus *bus = ebus_to_hbus(skl_to_ebus(skl));
+	struct hdac_bus *bus = skl_to_bus(skl);
 	int i, size, module_id;
 
 	if (bc->set_params == SKL_PARAM_BIND && bc->max) {
@@ -3024,14 +3027,13 @@ void skl_cleanup_resources(struct skl *skl)
  * information to the driver about module and pipeline parameters which DSP
  * FW expects like ids, resource values, formats etc
  */
-static int skl_tplg_widget_load(struct snd_soc_component *cmpnt,
+static int skl_tplg_widget_load(struct snd_soc_component *cmpnt, int index,
 				struct snd_soc_dapm_widget *w,
 				struct snd_soc_tplg_dapm_widget *tplg_w)
 {
 	int ret;
-	struct hdac_ext_bus *ebus = snd_soc_component_get_drvdata(cmpnt);
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = snd_soc_component_get_drvdata(cmpnt);
+	struct skl *skl = bus_to_skl(bus);
 	struct skl_module_cfg *mconfig;
 
 	if (!tplg_w->priv.size)
@@ -3131,14 +3133,14 @@ static int skl_init_enum_data(struct device *dev, struct soc_enum *se,
 }
 
 static int skl_tplg_control_load(struct snd_soc_component *cmpnt,
+				int index,
 				struct snd_kcontrol_new *kctl,
 				struct snd_soc_tplg_ctl_hdr *hdr)
 {
 	struct soc_bytes_ext *sb;
 	struct snd_soc_tplg_bytes_control *tplg_bc;
 	struct snd_soc_tplg_enum_control *tplg_ec;
-	struct hdac_ext_bus *ebus  = snd_soc_component_get_drvdata(cmpnt);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus  = snd_soc_component_get_drvdata(cmpnt);
 	struct soc_enum *se;
 
 	switch (hdr->ops.info) {
@@ -3619,12 +3621,11 @@ static int skl_tplg_get_manifest_data(struct snd_soc_tplg_manifest *manifest,
 	return 0;
 }
 
-static int skl_manifest_load(struct snd_soc_component *cmpnt,
+static int skl_manifest_load(struct snd_soc_component *cmpnt, int index,
 				struct snd_soc_tplg_manifest *manifest)
 {
-	struct hdac_ext_bus *ebus = snd_soc_component_get_drvdata(cmpnt);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = snd_soc_component_get_drvdata(cmpnt);
+	struct skl *skl = bus_to_skl(bus);
 
 	/* proceed only if we have private data defined */
 	if (manifest->priv.size == 0)
@@ -3713,12 +3714,11 @@ static void skl_tplg_set_pipe_type(struct skl *skl, struct skl_pipe *pipe)
 /*
  * SKL topology init routine
  */
-int skl_tplg_init(struct snd_soc_component *component, struct hdac_ext_bus *ebus)
+int skl_tplg_init(struct snd_soc_component *component, struct hdac_bus *bus)
 {
 	int ret;
 	const struct firmware *fw;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	struct skl_pipeline *ppl;
 
 	ret = request_firmware(&fw, skl->tplg_name, bus->dev);
diff --git a/sound/soc/intel/skylake/skl-topology.h b/sound/soc/intel/skylake/skl-topology.h
index 6d7e0569695f..82282cac9751 100644
--- a/sound/soc/intel/skylake/skl-topology.h
+++ b/sound/soc/intel/skylake/skl-topology.h
@@ -458,9 +458,9 @@ enum skl_channel {
 
 static inline struct skl *get_skl_ctx(struct device *dev)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 
-	return ebus_to_skl(ebus);
+	return bus_to_skl(bus);
 }
 
 int skl_tplg_be_update_params(struct snd_soc_dai *dai,
@@ -470,7 +470,7 @@ int skl_dsp_set_dma_control(struct skl_sst *ctx, u32 *caps,
 void skl_tplg_set_be_dmic_config(struct snd_soc_dai *dai,
 	struct skl_pipe_params *params, int stream);
 int skl_tplg_init(struct snd_soc_component *component,
-				struct hdac_ext_bus *ebus);
+				struct hdac_bus *ebus);
 struct skl_module_cfg *skl_tplg_fe_get_cpr_module(
 		struct snd_soc_dai *dai, int stream);
 int skl_tplg_update_pipe_params(struct device *dev,
@@ -512,8 +512,9 @@ int skl_pcm_host_dma_prepare(struct device *dev,
 int skl_pcm_link_dma_prepare(struct device *dev,
 			struct skl_pipe_params *params);
 
-int skl_dai_load(struct snd_soc_component *cmp,
-		 struct snd_soc_dai_driver *pcm_dai);
+int skl_dai_load(struct snd_soc_component *cmp, int index,
+		struct snd_soc_dai_driver *dai_drv,
+		struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai);
 void skl_tplg_add_moduleid_in_bind_params(struct skl *skl,
 				struct snd_soc_dapm_widget *w);
 #endif
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index f0d9793f872a..dce649485649 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -29,6 +29,7 @@
 #include <linux/delay.h>
 #include <sound/pcm.h>
 #include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
 #include <sound/hda_register.h>
 #include <sound/hdaudio.h>
 #include <sound/hda_i915.h>
@@ -36,8 +37,6 @@
 #include "skl-sst-dsp.h"
 #include "skl-sst-ipc.h"
 
-static struct skl_machine_pdata skl_dmic_data;
-
 /*
  * initialize the PCI registers
  */
@@ -54,7 +53,7 @@ static void skl_update_pci_byte(struct pci_dev *pci, unsigned int reg,
 
 static void skl_init_pci(struct skl *skl)
 {
-	struct hdac_ext_bus *ebus = &skl->ebus;
+	struct hdac_bus *bus = skl_to_bus(skl);
 
 	/*
 	 * Clear bits 0-2 of PCI register TCSEL (at offset 0x44)
@@ -63,7 +62,7 @@ static void skl_init_pci(struct skl *skl)
 	 * codecs.
 	 * The PCI register TCSEL is defined in the Intel manuals.
 	 */
-	dev_dbg(ebus_to_hbus(ebus)->dev, "Clearing TCSEL\n");
+	dev_dbg(bus->dev, "Clearing TCSEL\n");
 	skl_update_pci_byte(skl->pci, AZX_PCIREG_TCSEL, 0x07, 0);
 }
 
@@ -103,8 +102,7 @@ static void skl_enable_miscbdcge(struct device *dev, bool enable)
 static void skl_clock_power_gating(struct device *dev, bool enable)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 	u32 val;
 
 	/* Update PDCGE bit of CGCTL register */
@@ -127,7 +125,6 @@ static void skl_clock_power_gating(struct device *dev, bool enable)
  */
 static int skl_init_chip(struct hdac_bus *bus, bool full_reset)
 {
-	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 	struct hdac_ext_link *hlink;
 	int ret;
 
@@ -135,7 +132,7 @@ static int skl_init_chip(struct hdac_bus *bus, bool full_reset)
 	ret = snd_hdac_bus_init_chip(bus, full_reset);
 
 	/* Reset stream-to-link mapping */
-	list_for_each_entry(hlink, &ebus->hlink_list, list)
+	list_for_each_entry(hlink, &bus->hlink_list, list)
 		bus->io_ops->reg_writel(0, hlink->ml_addr + AZX_REG_ML_LOSIDV);
 
 	skl_enable_miscbdcge(bus->dev, true);
@@ -146,8 +143,7 @@ static int skl_init_chip(struct hdac_bus *bus, bool full_reset)
 void skl_update_d0i3c(struct device *dev, bool enable)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 	u8 reg;
 	int timeout = 50;
 
@@ -197,8 +193,7 @@ static void skl_stream_update(struct hdac_bus *bus, struct hdac_stream *hstr)
 
 static irqreturn_t skl_interrupt(int irq, void *dev_id)
 {
-	struct hdac_ext_bus *ebus = dev_id;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_id;
 	u32 status;
 
 	if (!pm_runtime_active(bus->dev))
@@ -227,8 +222,7 @@ static irqreturn_t skl_interrupt(int irq, void *dev_id)
 
 static irqreturn_t skl_threaded_handler(int irq, void *dev_id)
 {
-	struct hdac_ext_bus *ebus = dev_id;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_id;
 	u32 status;
 
 	status = snd_hdac_chip_readl(bus, INTSTS);
@@ -238,16 +232,15 @@ static irqreturn_t skl_threaded_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int skl_acquire_irq(struct hdac_ext_bus *ebus, int do_disconnect)
+static int skl_acquire_irq(struct hdac_bus *bus, int do_disconnect)
 {
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	int ret;
 
 	ret = request_threaded_irq(skl->pci->irq, skl_interrupt,
 			skl_threaded_handler,
 			IRQF_SHARED,
-			KBUILD_MODNAME, ebus);
+			KBUILD_MODNAME, bus);
 	if (ret) {
 		dev_err(bus->dev,
 			"unable to grab IRQ %d, disabling device\n",
@@ -264,21 +257,20 @@ static int skl_acquire_irq(struct hdac_ext_bus *ebus, int do_disconnect)
 static int skl_suspend_late(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl = bus_to_skl(bus);
 
 	return skl_suspend_late_dsp(skl);
 }
 
 #ifdef CONFIG_PM
-static int _skl_suspend(struct hdac_ext_bus *ebus)
+static int _skl_suspend(struct hdac_bus *bus)
 {
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	struct pci_dev *pci = to_pci_dev(bus->dev);
 	int ret;
 
-	snd_hdac_ext_bus_link_power_down_all(ebus);
+	snd_hdac_ext_bus_link_power_down_all(bus);
 
 	ret = skl_suspend_dsp(skl);
 	if (ret < 0)
@@ -295,10 +287,9 @@ static int _skl_suspend(struct hdac_ext_bus *ebus)
 	return 0;
 }
 
-static int _skl_resume(struct hdac_ext_bus *ebus)
+static int _skl_resume(struct hdac_bus *bus)
 {
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl = bus_to_skl(bus);
 
 	skl_init_pci(skl);
 	skl_init_chip(bus, true);
@@ -314,9 +305,8 @@ static int _skl_resume(struct hdac_ext_bus *ebus)
 static int skl_suspend(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl  = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl  = bus_to_skl(bus);
 	int ret = 0;
 
 	/*
@@ -325,15 +315,15 @@ static int skl_suspend(struct device *dev)
 	 */
 	if (skl->supend_active) {
 		/* turn off the links and stop the CORB/RIRB DMA if it is On */
-		snd_hdac_ext_bus_link_power_down_all(ebus);
+		snd_hdac_ext_bus_link_power_down_all(bus);
 
-		if (ebus->cmd_dma_state)
-			snd_hdac_bus_stop_cmd_io(&ebus->bus);
+		if (bus->cmd_dma_state)
+			snd_hdac_bus_stop_cmd_io(bus);
 
 		enable_irq_wake(bus->irq);
 		pci_save_state(pci);
 	} else {
-		ret = _skl_suspend(ebus);
+		ret = _skl_suspend(bus);
 		if (ret < 0)
 			return ret;
 		skl->skl_sst->fw_loaded = false;
@@ -352,9 +342,8 @@ static int skl_suspend(struct device *dev)
 static int skl_resume(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl  = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl  = bus_to_skl(bus);
 	struct hdac_ext_link *hlink = NULL;
 	int ret;
 
@@ -374,32 +363,32 @@ static int skl_resume(struct device *dev)
 	 */
 	if (skl->supend_active) {
 		pci_restore_state(pci);
-		snd_hdac_ext_bus_link_power_up_all(ebus);
+		snd_hdac_ext_bus_link_power_up_all(bus);
 		disable_irq_wake(bus->irq);
 		/*
 		 * turn On the links which are On before active suspend
 		 * and start the CORB/RIRB DMA if On before
 		 * active suspend.
 		 */
-		list_for_each_entry(hlink, &ebus->hlink_list, list) {
+		list_for_each_entry(hlink, &bus->hlink_list, list) {
 			if (hlink->ref_count)
 				snd_hdac_ext_bus_link_power_up(hlink);
 		}
 
-		if (ebus->cmd_dma_state)
-			snd_hdac_bus_init_cmd_io(&ebus->bus);
 		ret = 0;
+		if (bus->cmd_dma_state)
+			snd_hdac_bus_init_cmd_io(bus);
 	} else {
-		ret = _skl_resume(ebus);
+		ret = _skl_resume(bus);
 
 		/* turn off the links which are off before suspend */
-		list_for_each_entry(hlink, &ebus->hlink_list, list) {
+		list_for_each_entry(hlink, &bus->hlink_list, list) {
 			if (!hlink->ref_count)
 				snd_hdac_ext_bus_link_power_down(hlink);
 		}
 
-		if (!ebus->cmd_dma_state)
-			snd_hdac_bus_stop_cmd_io(&ebus->bus);
+		if (!bus->cmd_dma_state)
+			snd_hdac_bus_stop_cmd_io(bus);
 	}
 
 	return ret;
@@ -410,23 +399,21 @@ static int skl_resume(struct device *dev)
 static int skl_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 
 	dev_dbg(bus->dev, "in %s\n", __func__);
 
-	return _skl_suspend(ebus);
+	return _skl_suspend(bus);
 }
 
 static int skl_runtime_resume(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 
 	dev_dbg(bus->dev, "in %s\n", __func__);
 
-	return _skl_resume(ebus);
+	return _skl_resume(bus);
 }
 #endif /* CONFIG_PM */
 
@@ -439,20 +426,19 @@ static const struct dev_pm_ops skl_pm = {
 /*
  * destructor
  */
-static int skl_free(struct hdac_ext_bus *ebus)
+static int skl_free(struct hdac_bus *bus)
 {
-	struct skl *skl  = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl  = bus_to_skl(bus);
 
 	skl->init_done = 0; /* to be sure */
 
-	snd_hdac_ext_stop_streams(ebus);
+	snd_hdac_ext_stop_streams(bus);
 
 	if (bus->irq >= 0)
-		free_irq(bus->irq, (void *)ebus);
+		free_irq(bus->irq, (void *)bus);
 	snd_hdac_bus_free_stream_pages(bus);
-	snd_hdac_stream_free_all(ebus);
-	snd_hdac_link_free_all(ebus);
+	snd_hdac_stream_free_all(bus);
+	snd_hdac_link_free_all(bus);
 
 	if (bus->remap_addr)
 		iounmap(bus->remap_addr);
@@ -460,11 +446,11 @@ static int skl_free(struct hdac_ext_bus *ebus)
 	pci_release_regions(skl->pci);
 	pci_disable_device(skl->pci);
 
-	snd_hdac_ext_bus_exit(ebus);
+	snd_hdac_ext_bus_exit(bus);
 
 	cancel_work_sync(&skl->probe_work);
 	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
-		snd_hdac_i915_exit(&ebus->bus);
+		snd_hdac_i915_exit(bus);
 
 	return 0;
 }
@@ -488,8 +474,8 @@ static struct skl_ssp_clk skl_ssp_clks[] = {
 
 static int skl_find_machine(struct skl *skl, void *driver_data)
 {
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct snd_soc_acpi_mach *mach = driver_data;
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
 	struct skl_machine_pdata *pdata;
 
 	mach = snd_soc_acpi_find_machine(mach);
@@ -500,17 +486,19 @@ static int skl_find_machine(struct skl *skl, void *driver_data)
 
 	skl->mach = mach;
 	skl->fw_name = mach->fw_filename;
-	pdata = skl->mach->pdata;
+	pdata = mach->pdata;
 
-	if (mach->pdata)
+	if (pdata) {
 		skl->use_tplg_pcm = pdata->use_tplg_pcm;
+		pdata->dmic_num = skl_get_dmic_geo(skl);
+	}
 
 	return 0;
 }
 
 static int skl_machine_device_register(struct skl *skl)
 {
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct snd_soc_acpi_mach *mach = skl->mach;
 	struct platform_device *pdev;
 	int ret;
@@ -544,7 +532,7 @@ static void skl_machine_device_unregister(struct skl *skl)
 
 static int skl_dmic_device_register(struct skl *skl)
 {
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct platform_device *pdev;
 	int ret;
 
@@ -643,12 +631,13 @@ static void skl_clock_device_unregister(struct skl *skl)
 /*
  * Probe the given codec address
  */
-static int probe_codec(struct hdac_ext_bus *ebus, int addr)
+static int probe_codec(struct hdac_bus *bus, int addr)
 {
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	unsigned int cmd = (addr << 28) | (AC_NODE_ROOT << 20) |
 		(AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID;
 	unsigned int res = -1;
+	struct skl *skl = bus_to_skl(bus);
+	struct hdac_device *hdev;
 
 	mutex_lock(&bus->cmd_mutex);
 	snd_hdac_bus_send_cmd(bus, cmd);
@@ -658,13 +647,16 @@ static int probe_codec(struct hdac_ext_bus *ebus, int addr)
 		return -EIO;
 	dev_dbg(bus->dev, "codec #%d probed OK\n", addr);
 
-	return snd_hdac_ext_bus_device_init(ebus, addr);
+	hdev = devm_kzalloc(&skl->pci->dev, sizeof(*hdev), GFP_KERNEL);
+	if (!hdev)
+		return -ENOMEM;
+
+	return snd_hdac_ext_bus_device_init(bus, addr, hdev);
 }
 
 /* Codec initialization */
-static void skl_codec_create(struct hdac_ext_bus *ebus)
+static void skl_codec_create(struct hdac_bus *bus)
 {
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	int c, max_slots;
 
 	max_slots = HDA_MAX_CODECS;
@@ -672,7 +664,7 @@ static void skl_codec_create(struct hdac_ext_bus *ebus)
 	/* First try to probe all given codec slots */
 	for (c = 0; c < max_slots; c++) {
 		if ((bus->codec_mask & (1 << c))) {
-			if (probe_codec(ebus, c) < 0) {
+			if (probe_codec(bus, c) < 0) {
 				/*
 				 * Some BIOSen give you wrong codec addresses
 				 * that don't exist
@@ -722,8 +714,7 @@ static int skl_i915_init(struct hdac_bus *bus)
 static void skl_probe_work(struct work_struct *work)
 {
 	struct skl *skl = container_of(work, struct skl, probe_work);
-	struct hdac_ext_bus *ebus = &skl->ebus;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct hdac_ext_link *hlink = NULL;
 	int err;
 
@@ -744,7 +735,7 @@ static void skl_probe_work(struct work_struct *work)
 		dev_info(bus->dev, "no hda codecs found!\n");
 
 	/* create codec instances */
-	skl_codec_create(ebus);
+	skl_codec_create(bus);
 
 	/* register platform dai and controls */
 	err = skl_platform_register(bus->dev);
@@ -773,8 +764,8 @@ static void skl_probe_work(struct work_struct *work)
 	/*
 	 * we are done probing so decrement link counts
 	 */
-	list_for_each_entry(hlink, &ebus->hlink_list, list)
-		snd_hdac_ext_bus_link_put(ebus, hlink);
+	list_for_each_entry(hlink, &bus->hlink_list, list)
+		snd_hdac_ext_bus_link_put(bus, hlink);
 
 	/* configure PM */
 	pm_runtime_put_noidle(bus->dev);
@@ -796,7 +787,7 @@ static int skl_create(struct pci_dev *pci,
 		      struct skl **rskl)
 {
 	struct skl *skl;
-	struct hdac_ext_bus *ebus;
+	struct hdac_bus *bus;
 
 	int err;
 
@@ -811,23 +802,22 @@ static int skl_create(struct pci_dev *pci,
 		pci_disable_device(pci);
 		return -ENOMEM;
 	}
-	ebus = &skl->ebus;
-	snd_hdac_ext_bus_init(ebus, &pci->dev, &bus_core_ops, io_ops);
-	ebus->bus.use_posbuf = 1;
+
+	bus = skl_to_bus(skl);
+	snd_hdac_ext_bus_init(bus, &pci->dev, &bus_core_ops, io_ops, NULL);
+	bus->use_posbuf = 1;
 	skl->pci = pci;
 	INIT_WORK(&skl->probe_work, skl_probe_work);
-
-	ebus->bus.bdl_pos_adj = 0;
+	bus->bdl_pos_adj = 0;
 
 	*rskl = skl;
 
 	return 0;
 }
 
-static int skl_first_init(struct hdac_ext_bus *ebus)
+static int skl_first_init(struct hdac_bus *bus)
 {
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	struct pci_dev *pci = skl->pci;
 	int err;
 	unsigned short gcap;
@@ -848,7 +838,7 @@ static int skl_first_init(struct hdac_ext_bus *ebus)
 
 	snd_hdac_bus_parse_capabilities(bus);
 
-	if (skl_acquire_irq(ebus, 0) < 0)
+	if (skl_acquire_irq(bus, 0) < 0)
 		return -EBUSY;
 
 	pci_set_master(pci);
@@ -872,14 +862,14 @@ static int skl_first_init(struct hdac_ext_bus *ebus)
 	if (!pb_streams && !cp_streams)
 		return -EIO;
 
-	ebus->num_streams = cp_streams + pb_streams;
+	bus->num_streams = cp_streams + pb_streams;
 
 	/* initialize streams */
 	snd_hdac_ext_stream_init_all
-		(ebus, 0, cp_streams, SNDRV_PCM_STREAM_CAPTURE);
+		(bus, 0, cp_streams, SNDRV_PCM_STREAM_CAPTURE);
 	start_idx = cp_streams;
 	snd_hdac_ext_stream_init_all
-		(ebus, start_idx, pb_streams, SNDRV_PCM_STREAM_PLAYBACK);
+		(bus, start_idx, pb_streams, SNDRV_PCM_STREAM_PLAYBACK);
 
 	err = snd_hdac_bus_alloc_stream_pages(bus);
 	if (err < 0)
@@ -895,7 +885,6 @@ static int skl_probe(struct pci_dev *pci,
 		     const struct pci_device_id *pci_id)
 {
 	struct skl *skl;
-	struct hdac_ext_bus *ebus = NULL;
 	struct hdac_bus *bus = NULL;
 	int err;
 
@@ -904,10 +893,9 @@ static int skl_probe(struct pci_dev *pci,
 	if (err < 0)
 		return err;
 
-	ebus = &skl->ebus;
-	bus = ebus_to_hbus(ebus);
+	bus = skl_to_bus(skl);
 
-	err = skl_first_init(ebus);
+	err = skl_first_init(bus);
 	if (err < 0)
 		goto out_free;
 
@@ -928,9 +916,7 @@ static int skl_probe(struct pci_dev *pci,
 
 	skl_nhlt_update_topology_bin(skl);
 
-	pci_set_drvdata(skl->pci, ebus);
-
-	skl_dmic_data.dmic_num = skl_get_dmic_geo(skl);
+	pci_set_drvdata(skl->pci, bus);
 
 	/* check if dsp is there */
 	if (bus->ppcap) {
@@ -952,7 +938,7 @@ static int skl_probe(struct pci_dev *pci,
 		skl->skl_sst->clock_power_gating = skl_clock_power_gating;
 	}
 	if (bus->mlcap)
-		snd_hdac_ext_bus_get_ml_capabilities(ebus);
+		snd_hdac_ext_bus_get_ml_capabilities(bus);
 
 	snd_hdac_bus_stop_chip(bus);
 
@@ -972,31 +958,30 @@ out_clk_free:
 out_nhlt_free:
 	skl_nhlt_free(skl->nhlt);
 out_free:
-	skl_free(ebus);
+	skl_free(bus);
 
 	return err;
 }
 
 static void skl_shutdown(struct pci_dev *pci)
 {
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 	struct hdac_stream *s;
 	struct hdac_ext_stream *stream;
 	struct skl *skl;
 
-	if (ebus == NULL)
+	if (!bus)
 		return;
 
-	skl = ebus_to_skl(ebus);
+	skl = bus_to_skl(bus);
 
 	if (!skl->init_done)
 		return;
 
-	snd_hdac_ext_stop_streams(ebus);
+	snd_hdac_ext_stop_streams(bus);
 	list_for_each_entry(s, &bus->stream_list, list) {
 		stream = stream_to_hdac_ext_stream(s);
-		snd_hdac_ext_stream_decouple(ebus, stream, false);
+		snd_hdac_ext_stream_decouple(bus, stream, false);
 	}
 
 	snd_hdac_bus_stop_chip(bus);
@@ -1004,15 +989,15 @@ static void skl_shutdown(struct pci_dev *pci)
 
 static void skl_remove(struct pci_dev *pci)
 {
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl = bus_to_skl(bus);
 
 	release_firmware(skl->tplg);
 
 	pm_runtime_get_noresume(&pci->dev);
 
 	/* codec removal, invoke bus_device_remove */
-	snd_hdac_ext_bus_device_remove(ebus);
+	snd_hdac_ext_bus_device_remove(bus);
 
 	skl->debugfs = NULL;
 	skl_platform_unregister(&pci->dev);
@@ -1022,176 +1007,27 @@ static void skl_remove(struct pci_dev *pci)
 	skl_clock_device_unregister(skl);
 	skl_nhlt_remove_sysfs(skl);
 	skl_nhlt_free(skl->nhlt);
-	skl_free(ebus);
+	skl_free(bus);
 	dev_set_drvdata(&pci->dev, NULL);
 }
 
-static struct snd_soc_acpi_codecs skl_codecs = {
-	.num_codecs = 1,
-	.codecs = {"10508825"}
-};
-
-static struct snd_soc_acpi_codecs kbl_codecs = {
-	.num_codecs = 1,
-	.codecs = {"10508825"}
-};
-
-static struct snd_soc_acpi_codecs bxt_codecs = {
-	.num_codecs = 1,
-	.codecs = {"MX98357A"}
-};
-
-static struct snd_soc_acpi_codecs kbl_poppy_codecs = {
-	.num_codecs = 1,
-	.codecs = {"10EC5663"}
-};
-
-static struct snd_soc_acpi_codecs kbl_5663_5514_codecs = {
-	.num_codecs = 2,
-	.codecs = {"10EC5663", "10EC5514"}
-};
-
-static struct snd_soc_acpi_codecs kbl_7219_98357_codecs = {
-	.num_codecs = 1,
-	.codecs = {"MX98357A"}
-};
-
-static struct skl_machine_pdata cnl_pdata = {
-	.use_tplg_pcm = true,
-};
-
-static struct snd_soc_acpi_mach sst_skl_devdata[] = {
-	{
-		.id = "INT343A",
-		.drv_name = "skl_alc286s_i2s",
-		.fw_filename = "intel/dsp_fw_release.bin",
-	},
-	{
-		.id = "INT343B",
-		.drv_name = "skl_n88l25_s4567",
-		.fw_filename = "intel/dsp_fw_release.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &skl_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "MX98357A",
-		.drv_name = "skl_n88l25_m98357a",
-		.fw_filename = "intel/dsp_fw_release.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &skl_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{}
-};
-
-static struct snd_soc_acpi_mach sst_bxtp_devdata[] = {
-	{
-		.id = "INT343A",
-		.drv_name = "bxt_alc298s_i2s",
-		.fw_filename = "intel/dsp_fw_bxtn.bin",
-	},
-	{
-		.id = "DLGS7219",
-		.drv_name = "bxt_da7219_max98357a_i2s",
-		.fw_filename = "intel/dsp_fw_bxtn.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &bxt_codecs,
-	},
-	{}
-};
-
-static struct snd_soc_acpi_mach sst_kbl_devdata[] = {
-	{
-		.id = "INT343A",
-		.drv_name = "kbl_alc286s_i2s",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-	},
-	{
-		.id = "INT343B",
-		.drv_name = "kbl_n88l25_s4567",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "MX98357A",
-		.drv_name = "kbl_n88l25_m98357a",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "MX98927",
-		.drv_name = "kbl_r5514_5663_max",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_5663_5514_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "MX98927",
-		.drv_name = "kbl_rt5663_m98927",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_poppy_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "10EC5663",
-		.drv_name = "kbl_rt5663",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-	},
-	{
-		.id = "DLGS7219",
-		.drv_name = "kbl_da7219_max98357a",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_7219_98357_codecs,
-		.pdata = &skl_dmic_data
-	},
-
-	{}
-};
-
-static struct snd_soc_acpi_mach sst_glk_devdata[] = {
-	{
-		.id = "INT343A",
-		.drv_name = "glk_alc298s_i2s",
-		.fw_filename = "intel/dsp_fw_glk.bin",
-	},
-	{}
-};
-
-static const struct snd_soc_acpi_mach sst_cnl_devdata[] = {
-	{
-		.id = "INT34C2",
-		.drv_name = "cnl_rt274",
-		.fw_filename = "intel/dsp_fw_cnl.bin",
-		.pdata = &cnl_pdata,
-	},
-	{}
-};
-
 /* PCI IDs */
 static const struct pci_device_id skl_ids[] = {
 	/* Sunrise Point-LP */
 	{ PCI_DEVICE(0x8086, 0x9d70),
-		.driver_data = (unsigned long)&sst_skl_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_skl_machines},
 	/* BXT-P */
 	{ PCI_DEVICE(0x8086, 0x5a98),
-		.driver_data = (unsigned long)&sst_bxtp_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_bxt_machines},
 	/* KBL */
 	{ PCI_DEVICE(0x8086, 0x9D71),
-		.driver_data = (unsigned long)&sst_kbl_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_kbl_machines},
 	/* GLK */
 	{ PCI_DEVICE(0x8086, 0x3198),
-		.driver_data = (unsigned long)&sst_glk_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_glk_machines},
 	/* CNL */
 	{ PCI_DEVICE(0x8086, 0x9dc8),
-		.driver_data = (unsigned long)&sst_cnl_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_cnl_machines},
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, skl_ids);
diff --git a/sound/soc/intel/skylake/skl.h b/sound/soc/intel/skylake/skl.h
index 0d5375cbcf6e..78aa8bdcb619 100644
--- a/sound/soc/intel/skylake/skl.h
+++ b/sound/soc/intel/skylake/skl.h
@@ -71,7 +71,7 @@ struct skl_fw_config {
 };
 
 struct skl {
-	struct hdac_ext_bus ebus;
+	struct hdac_bus hbus;
 	struct pci_dev *pci;
 
 	unsigned int init_done:1; /* delayed init status */
@@ -105,9 +105,8 @@ struct skl {
 	struct snd_soc_acpi_mach *mach;
 };
 
-#define skl_to_ebus(s)	(&(s)->ebus)
-#define ebus_to_skl(sbus) \
-	container_of(sbus, struct skl, sbus)
+#define skl_to_bus(s)  (&(s)->hbus)
+#define bus_to_skl(bus) container_of(bus, struct skl, hbus)
 
 /* to pass dai dma data */
 struct skl_dma_params {
diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
index 51ec4ff6ed95..697aa50aff9a 100644
--- a/sound/soc/mediatek/common/mtk-afe-platform-driver.c
+++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
@@ -15,20 +15,12 @@
 
 int mtk_afe_combine_sub_dai(struct mtk_base_afe *afe)
 {
-	struct snd_soc_dai_driver *sub_dai_drivers;
+	struct mtk_base_afe_dai *dai;
 	size_t num_dai_drivers = 0, dai_idx = 0;
-	int i;
-
-	if (!afe->sub_dais) {
-		dev_err(afe->dev, "%s(), sub_dais == NULL\n", __func__);
-		return -EINVAL;
-	}
 
 	/* calcualte total dai driver size */
-	for (i = 0; i < afe->num_sub_dais; i++) {
-		if (afe->sub_dais[i].dai_drivers &&
-		    afe->sub_dais[i].num_dai_drivers != 0)
-			num_dai_drivers += afe->sub_dais[i].num_dai_drivers;
+	list_for_each_entry(dai, &afe->sub_dais, list) {
+		num_dai_drivers += dai->num_dai_drivers;
 	}
 
 	dev_info(afe->dev, "%s(), num of dai %zd\n", __func__, num_dai_drivers);
@@ -42,19 +34,14 @@ int mtk_afe_combine_sub_dai(struct mtk_base_afe *afe)
 	if (!afe->dai_drivers)
 		return -ENOMEM;
 
-	for (i = 0; i < afe->num_sub_dais; i++) {
-		if (afe->sub_dais[i].dai_drivers &&
-		    afe->sub_dais[i].num_dai_drivers != 0) {
-			sub_dai_drivers = afe->sub_dais[i].dai_drivers;
-			/* dai driver */
-			memcpy(&afe->dai_drivers[dai_idx],
-			       sub_dai_drivers,
-			       afe->sub_dais[i].num_dai_drivers *
-			       sizeof(struct snd_soc_dai_driver));
-			dai_idx += afe->sub_dais[i].num_dai_drivers;
-		}
+	list_for_each_entry(dai, &afe->sub_dais, list) {
+		/* dai driver */
+		memcpy(&afe->dai_drivers[dai_idx],
+		       dai->dai_drivers,
+		       dai->num_dai_drivers *
+		       sizeof(struct snd_soc_dai_driver));
+		dai_idx += dai->num_dai_drivers;
 	}
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mtk_afe_combine_sub_dai);
@@ -62,28 +49,25 @@ EXPORT_SYMBOL_GPL(mtk_afe_combine_sub_dai);
 int mtk_afe_add_sub_dai_control(struct snd_soc_component *component)
 {
 	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
-	int i;
+	struct mtk_base_afe_dai *dai;
 
-	if (!afe->sub_dais) {
-		dev_err(afe->dev, "%s(), sub_dais == NULL\n", __func__);
-		return -EINVAL;
-	}
-
-	for (i = 0; i < afe->num_sub_dais; i++) {
-		if (afe->sub_dais[i].controls)
+	list_for_each_entry(dai, &afe->sub_dais, list) {
+		if (dai->controls)
 			snd_soc_add_component_controls(component,
-				afe->sub_dais[i].controls,
-				afe->sub_dais[i].num_controls);
+						       dai->controls,
+						       dai->num_controls);
 
-		if (afe->sub_dais[i].dapm_widgets)
+		if (dai->dapm_widgets)
 			snd_soc_dapm_new_controls(&component->dapm,
-				afe->sub_dais[i].dapm_widgets,
-				afe->sub_dais[i].num_dapm_widgets);
-
-		if (afe->sub_dais[i].dapm_routes)
+						  dai->dapm_widgets,
+						  dai->num_dapm_widgets);
+	}
+	/* add routes after all widgets are added */
+	list_for_each_entry(dai, &afe->sub_dais, list) {
+		if (dai->dapm_routes)
 			snd_soc_dapm_add_routes(&component->dapm,
-				afe->sub_dais[i].dapm_routes,
-				afe->sub_dais[i].num_dapm_routes);
+						dai->dapm_routes,
+						dai->num_dapm_routes);
 	}
 
 	snd_soc_dapm_new_widgets(component->dapm.card);
diff --git a/sound/soc/mediatek/common/mtk-base-afe.h b/sound/soc/mediatek/common/mtk-base-afe.h
index bcf562f029b6..bd8d5e0c6843 100644
--- a/sound/soc/mediatek/common/mtk-base-afe.h
+++ b/sound/soc/mediatek/common/mtk-base-afe.h
@@ -46,6 +46,7 @@ struct mtk_base_irq_data {
 };
 
 struct device;
+struct list_head;
 struct mtk_base_afe_memif;
 struct mtk_base_afe_irq;
 struct mtk_base_afe_dai;
@@ -72,8 +73,7 @@ struct mtk_base_afe {
 	struct mtk_base_afe_irq *irqs;
 	int irqs_size;
 
-	struct mtk_base_afe_dai *sub_dais;
-	int num_sub_dais;
+	struct list_head sub_dais;
 	struct snd_soc_dai_driver *dai_drivers;
 	unsigned int num_dai_drivers;
 
@@ -110,6 +110,8 @@ struct mtk_base_afe_dai {
 	unsigned int num_dapm_widgets;
 	const struct snd_soc_dapm_route *dapm_routes;
 	unsigned int num_dapm_routes;
+
+	struct list_head list;
 };
 
 #endif
diff --git a/sound/soc/mediatek/mt6797/mt6797-afe-common.h b/sound/soc/mediatek/mt6797/mt6797-afe-common.h
index 22eb7b455cf1..4eac9977b2b0 100644
--- a/sound/soc/mediatek/mt6797/mt6797-afe-common.h
+++ b/sound/soc/mediatek/mt6797/mt6797-afe-common.h
@@ -10,6 +10,7 @@
 #define _MT_6797_AFE_COMMON_H_
 
 #include <sound/soc.h>
+#include <linux/list.h>
 #include <linux/regmap.h>
 #include "../common/mtk-base-afe.h"
 
diff --git a/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c b/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
index 6c5dd9fc9976..192f4d7b37b6 100644
--- a/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
+++ b/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
@@ -733,6 +733,34 @@ static const struct snd_soc_component_driver mt6797_afe_component = {
 	.probe = mt6797_afe_component_probe,
 };
 
+static int mt6797_dai_memif_register(struct mtk_base_afe *afe)
+{
+	struct mtk_base_afe_dai *dai;
+
+	dai = devm_kzalloc(afe->dev, sizeof(*dai), GFP_KERNEL);
+	if (!dai)
+		return -ENOMEM;
+
+	list_add(&dai->list, &afe->sub_dais);
+
+	dai->dai_drivers = mt6797_memif_dai_driver;
+	dai->num_dai_drivers = ARRAY_SIZE(mt6797_memif_dai_driver);
+
+	dai->dapm_widgets = mt6797_memif_widgets;
+	dai->num_dapm_widgets = ARRAY_SIZE(mt6797_memif_widgets);
+	dai->dapm_routes = mt6797_memif_routes;
+	dai->num_dapm_routes = ARRAY_SIZE(mt6797_memif_routes);
+	return 0;
+}
+
+typedef int (*dai_register_cb)(struct mtk_base_afe *);
+static const dai_register_cb dai_register_cbs[] = {
+	mt6797_dai_adda_register,
+	mt6797_dai_pcm_register,
+	mt6797_dai_hostless_register,
+	mt6797_dai_memif_register,
+};
+
 static int mt6797_afe_pcm_dev_probe(struct platform_device *pdev)
 {
 	struct mtk_base_afe *afe;
@@ -811,29 +839,24 @@ static int mt6797_afe_pcm_dev_probe(struct platform_device *pdev)
 	}
 
 	/* init sub_dais */
-	afe->num_sub_dais = MT6797_DAI_NUM;
-	afe->sub_dais = devm_kcalloc(dev, afe->num_sub_dais,
-				     sizeof(*afe->sub_dais),
-				     GFP_KERNEL);
-	if (!afe->sub_dais)
-		return -ENOMEM;
-
-	mt6797_dai_adda_register(afe);
-	mt6797_dai_pcm_register(afe);
-	mt6797_dai_hostless_register(afe);
-
-	afe->sub_dais[MT6797_MEMIF_DL1].dai_drivers = mt6797_memif_dai_driver;
-	afe->sub_dais[MT6797_MEMIF_DL1].num_dai_drivers =
-		ARRAY_SIZE(mt6797_memif_dai_driver);
-	afe->sub_dais[MT6797_MEMIF_DL1].dapm_widgets = mt6797_memif_widgets;
-	afe->sub_dais[MT6797_MEMIF_DL1].num_dapm_widgets =
-		ARRAY_SIZE(mt6797_memif_widgets);
-	afe->sub_dais[MT6797_MEMIF_DL1].dapm_routes = mt6797_memif_routes;
-	afe->sub_dais[MT6797_MEMIF_DL1].num_dapm_routes =
-		ARRAY_SIZE(mt6797_memif_routes);
+	INIT_LIST_HEAD(&afe->sub_dais);
+
+	for (i = 0; i < ARRAY_SIZE(dai_register_cbs); i++) {
+		ret = dai_register_cbs[i](afe);
+		if (ret) {
+			dev_warn(afe->dev, "dai register i %d fail, ret %d\n",
+				 i, ret);
+			return ret;
+		}
+	}
 
 	/* init dai_driver and component_driver */
-	mtk_afe_combine_sub_dai(afe);
+	ret = mtk_afe_combine_sub_dai(afe);
+	if (ret) {
+		dev_warn(afe->dev, "mtk_afe_combine_sub_dai fail, ret %d\n",
+			 ret);
+		return ret;
+	}
 
 	afe->mtk_afe_hardware = &mt6797_afe_hardware;
 	afe->memif_fs = mt6797_memif_fs;
diff --git a/sound/soc/mediatek/mt6797/mt6797-dai-adda.c b/sound/soc/mediatek/mt6797/mt6797-dai-adda.c
index ad083265ce94..0ac6409c6d61 100644
--- a/sound/soc/mediatek/mt6797/mt6797-dai-adda.c
+++ b/sound/soc/mediatek/mt6797/mt6797-dai-adda.c
@@ -383,14 +383,20 @@ static struct snd_soc_dai_driver mtk_dai_adda_driver[] = {
 
 int mt6797_dai_adda_register(struct mtk_base_afe *afe)
 {
-	int id = MT6797_DAI_ADDA;
+	struct mtk_base_afe_dai *dai;
 
-	afe->sub_dais[id].dai_drivers = mtk_dai_adda_driver;
-	afe->sub_dais[id].num_dai_drivers = ARRAY_SIZE(mtk_dai_adda_driver);
+	dai = devm_kzalloc(afe->dev, sizeof(*dai), GFP_KERNEL);
+	if (!dai)
+		return -ENOMEM;
 
-	afe->sub_dais[id].dapm_widgets = mtk_dai_adda_widgets;
-	afe->sub_dais[id].num_dapm_widgets = ARRAY_SIZE(mtk_dai_adda_widgets);
-	afe->sub_dais[id].dapm_routes = mtk_dai_adda_routes;
-	afe->sub_dais[id].num_dapm_routes = ARRAY_SIZE(mtk_dai_adda_routes);
+	list_add(&dai->list, &afe->sub_dais);
+
+	dai->dai_drivers = mtk_dai_adda_driver;
+	dai->num_dai_drivers = ARRAY_SIZE(mtk_dai_adda_driver);
+
+	dai->dapm_widgets = mtk_dai_adda_widgets;
+	dai->num_dapm_widgets = ARRAY_SIZE(mtk_dai_adda_widgets);
+	dai->dapm_routes = mtk_dai_adda_routes;
+	dai->num_dapm_routes = ARRAY_SIZE(mtk_dai_adda_routes);
 	return 0;
 }
diff --git a/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c b/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c
index 4cf985b15a11..ed23e6a53b08 100644
--- a/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c
+++ b/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c
@@ -100,13 +100,19 @@ static struct snd_soc_dai_driver mtk_dai_hostless_driver[] = {
 
 int mt6797_dai_hostless_register(struct mtk_base_afe *afe)
 {
-	int id = MT6797_DAI_HOSTLESS_LPBK;
+	struct mtk_base_afe_dai *dai;
 
-	afe->sub_dais[id].dai_drivers = mtk_dai_hostless_driver;
-	afe->sub_dais[id].num_dai_drivers = ARRAY_SIZE(mtk_dai_hostless_driver);
+	dai = devm_kzalloc(afe->dev, sizeof(*dai), GFP_KERNEL);
+	if (!dai)
+		return -ENOMEM;
 
-	afe->sub_dais[id].dapm_routes = mtk_dai_hostless_routes;
-	afe->sub_dais[id].num_dapm_routes = ARRAY_SIZE(mtk_dai_hostless_routes);
+	list_add(&dai->list, &afe->sub_dais);
+
+	dai->dai_drivers = mtk_dai_hostless_driver;
+	dai->num_dai_drivers = ARRAY_SIZE(mtk_dai_hostless_driver);
+
+	dai->dapm_routes = mtk_dai_hostless_routes;
+	dai->num_dapm_routes = ARRAY_SIZE(mtk_dai_hostless_routes);
 
 	return 0;
 }
diff --git a/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c b/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c
index 16d5b5067204..3136f0bc7827 100644
--- a/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c
+++ b/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c
@@ -298,15 +298,20 @@ static struct snd_soc_dai_driver mtk_dai_pcm_driver[] = {
 
 int mt6797_dai_pcm_register(struct mtk_base_afe *afe)
 {
-	int id = MT6797_DAI_PCM_1;
+	struct mtk_base_afe_dai *dai;
 
-	afe->sub_dais[id].dai_drivers = mtk_dai_pcm_driver;
-	afe->sub_dais[id].num_dai_drivers = ARRAY_SIZE(mtk_dai_pcm_driver);
+	dai = devm_kzalloc(afe->dev, sizeof(*dai), GFP_KERNEL);
+	if (!dai)
+		return -ENOMEM;
 
-	afe->sub_dais[id].dapm_widgets = mtk_dai_pcm_widgets;
-	afe->sub_dais[id].num_dapm_widgets = ARRAY_SIZE(mtk_dai_pcm_widgets);
-	afe->sub_dais[id].dapm_routes = mtk_dai_pcm_routes;
-	afe->sub_dais[id].num_dapm_routes = ARRAY_SIZE(mtk_dai_pcm_routes);
+	list_add(&dai->list, &afe->sub_dais);
 
+	dai->dai_drivers = mtk_dai_pcm_driver;
+	dai->num_dai_drivers = ARRAY_SIZE(mtk_dai_pcm_driver);
+
+	dai->dapm_widgets = mtk_dai_pcm_widgets;
+	dai->num_dapm_widgets = ARRAY_SIZE(mtk_dai_pcm_widgets);
+	dai->dapm_routes = mtk_dai_pcm_routes;
+	dai->num_dapm_routes = ARRAY_SIZE(mtk_dai_pcm_routes);
 	return 0;
 }
diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
new file mode 100644
index 000000000000..8af8bc358a90
--- /dev/null
+++ b/sound/soc/meson/Kconfig
@@ -0,0 +1,65 @@
+menu "ASoC support for Amlogic platforms"
+	depends on ARCH_MESON || COMPILE_TEST
+
+config SND_MESON_AXG_FIFO
+	tristate
+	select REGMAP_MMIO
+
+config SND_MESON_AXG_FRDDR
+	tristate "Amlogic AXG Playback FIFO support"
+	select SND_MESON_AXG_FIFO
+	help
+	  Select Y or M to add support for the frontend playback interfaces
+	  embedded in the Amlogic AXG SoC family
+
+config SND_MESON_AXG_TODDR
+	tristate "Amlogic AXG Capture FIFO support"
+	select SND_MESON_AXG_FIFO
+	help
+	  Select Y or M to add support for the frontend capture interfaces
+	  embedded in the Amlogic AXG SoC family
+
+config SND_MESON_AXG_TDM_FORMATTER
+	tristate
+	select REGMAP_MMIO
+
+config SND_MESON_AXG_TDM_INTERFACE
+	tristate
+	select SND_MESON_AXG_TDM_FORMATTER
+
+config SND_MESON_AXG_TDMIN
+	tristate "Amlogic AXG TDM Input Support"
+	select SND_MESON_AXG_TDM_FORMATTER
+	select SND_MESON_AXG_TDM_INTERFACE
+	help
+	  Select Y or M to add support for TDM input formatter embedded
+	  in the Amlogic AXG SoC family
+
+config SND_MESON_AXG_TDMOUT
+	tristate "Amlogic AXG TDM Output Support"
+	select SND_MESON_AXG_TDM_FORMATTER
+	select SND_MESON_AXG_TDM_INTERFACE
+	help
+	  Select Y or M to add support for TDM output formatter embedded
+	  in the Amlogic AXG SoC family
+
+config SND_MESON_AXG_SOUND_CARD
+	tristate "Amlogic AXG Sound Card Support"
+	select SND_MESON_AXG_TDM_INTERFACE
+	imply SND_MESON_AXG_FRDDR
+	imply SND_MESON_AXG_TODDR
+	imply SND_MESON_AXG_TDMIN
+	imply SND_MESON_AXG_TDMOUT
+	imply SND_MESON_AXG_SPDIFOUT
+	help
+	  Select Y or M to add support for the AXG SoC sound card
+
+config SND_MESON_AXG_SPDIFOUT
+	tristate "Amlogic AXG SPDIF Output Support"
+	select SND_PCM_IEC958
+	imply SND_SOC_SPDIF
+	help
+	  Select Y or M to add support for SPDIF output serializer embedded
+	  in the Amlogic AXG SoC family
+
+endmenu
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
new file mode 100644
index 000000000000..c5e003b093db
--- /dev/null
+++ b/sound/soc/meson/Makefile
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+snd-soc-meson-axg-fifo-objs := axg-fifo.o
+snd-soc-meson-axg-frddr-objs := axg-frddr.o
+snd-soc-meson-axg-toddr-objs := axg-toddr.o
+snd-soc-meson-axg-tdm-formatter-objs := axg-tdm-formatter.o
+snd-soc-meson-axg-tdm-interface-objs := axg-tdm-interface.o
+snd-soc-meson-axg-tdmin-objs := axg-tdmin.o
+snd-soc-meson-axg-tdmout-objs := axg-tdmout.o
+snd-soc-meson-axg-sound-card-objs := axg-card.o
+snd-soc-meson-axg-spdifout-objs := axg-spdifout.o
+
+obj-$(CONFIG_SND_MESON_AXG_FIFO) += snd-soc-meson-axg-fifo.o
+obj-$(CONFIG_SND_MESON_AXG_FRDDR) += snd-soc-meson-axg-frddr.o
+obj-$(CONFIG_SND_MESON_AXG_TODDR) += snd-soc-meson-axg-toddr.o
+obj-$(CONFIG_SND_MESON_AXG_TDM_FORMATTER) += snd-soc-meson-axg-tdm-formatter.o
+obj-$(CONFIG_SND_MESON_AXG_TDM_INTERFACE) += snd-soc-meson-axg-tdm-interface.o
+obj-$(CONFIG_SND_MESON_AXG_TDMIN) += snd-soc-meson-axg-tdmin.o
+obj-$(CONFIG_SND_MESON_AXG_TDMOUT) += snd-soc-meson-axg-tdmout.o
+obj-$(CONFIG_SND_MESON_AXG_SOUND_CARD) += snd-soc-meson-axg-sound-card.o
+obj-$(CONFIG_SND_MESON_AXG_SPDIFOUT) += snd-soc-meson-axg-spdifout.o
diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c
new file mode 100644
index 000000000000..2914ba0d965b
--- /dev/null
+++ b/sound/soc/meson/axg-card.c
@@ -0,0 +1,671 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-tdm.h"
+
+struct axg_card {
+	struct snd_soc_card card;
+	void **link_data;
+};
+
+struct axg_dai_link_tdm_mask {
+	u32 tx;
+	u32 rx;
+};
+
+struct axg_dai_link_tdm_data {
+	unsigned int mclk_fs;
+	unsigned int slots;
+	unsigned int slot_width;
+	u32 *tx_mask;
+	u32 *rx_mask;
+	struct axg_dai_link_tdm_mask *codec_masks;
+};
+
+#define PREFIX "amlogic,"
+
+static int axg_card_reallocate_links(struct axg_card *priv,
+				     unsigned int num_links)
+{
+	struct snd_soc_dai_link *links;
+	void **ldata;
+
+	links = krealloc(priv->card.dai_link,
+			 num_links * sizeof(*priv->card.dai_link),
+			 GFP_KERNEL | __GFP_ZERO);
+	ldata = krealloc(priv->link_data,
+			 num_links * sizeof(*priv->link_data),
+			 GFP_KERNEL | __GFP_ZERO);
+
+	if (!links || !ldata) {
+		dev_err(priv->card.dev, "failed to allocate links\n");
+		return -ENOMEM;
+	}
+
+	priv->card.dai_link = links;
+	priv->link_data = ldata;
+	priv->card.num_links = num_links;
+	return 0;
+}
+
+static int axg_card_parse_dai(struct snd_soc_card *card,
+			      struct device_node *node,
+			      struct device_node **dai_of_node,
+			      const char **dai_name)
+{
+	struct of_phandle_args args;
+	int ret;
+
+	if (!dai_name || !dai_of_node || !node)
+		return -EINVAL;
+
+	ret = of_parse_phandle_with_args(node, "sound-dai",
+					 "#sound-dai-cells", 0, &args);
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(card->dev, "can't parse dai %d\n", ret);
+		return ret;
+	}
+	*dai_of_node = args.np;
+
+	return snd_soc_get_dai_name(&args, dai_name);
+}
+
+static int axg_card_set_link_name(struct snd_soc_card *card,
+				  struct snd_soc_dai_link *link,
+				  const char *prefix)
+{
+	char *name = devm_kasprintf(card->dev, GFP_KERNEL, "%s.%s",
+				    prefix, link->cpu_of_node->full_name);
+	if (!name)
+		return -ENOMEM;
+
+	link->name = name;
+	link->stream_name = name;
+
+	return 0;
+}
+
+static void axg_card_clean_references(struct axg_card *priv)
+{
+	struct snd_soc_card *card = &priv->card;
+	struct snd_soc_dai_link *link;
+	int i, j;
+
+	if (card->dai_link) {
+		for (i = 0; i < card->num_links; i++) {
+			link = &card->dai_link[i];
+			of_node_put(link->cpu_of_node);
+			for (j = 0; j < link->num_codecs; j++)
+				of_node_put(link->codecs[j].of_node);
+		}
+	}
+
+	if (card->aux_dev) {
+		for (i = 0; i < card->num_aux_devs; i++)
+			of_node_put(card->aux_dev[i].codec_of_node);
+	}
+
+	kfree(card->dai_link);
+	kfree(priv->link_data);
+}
+
+static int axg_card_add_aux_devices(struct snd_soc_card *card)
+{
+	struct device_node *node = card->dev->of_node;
+	struct snd_soc_aux_dev *aux;
+	int num, i;
+
+	num = of_count_phandle_with_args(node, "audio-aux-devs", NULL);
+	if (num == -ENOENT) {
+		/*
+		 * It is ok to have no auxiliary devices but for this card it
+		 * is a strange situtation. Let's warn the about it.
+		 */
+		dev_warn(card->dev, "card has no auxiliary devices\n");
+		return 0;
+	} else if (num < 0) {
+		dev_err(card->dev, "error getting auxiliary devices: %d\n",
+			num);
+		return num;
+	}
+
+	aux = devm_kcalloc(card->dev, num, sizeof(*aux), GFP_KERNEL);
+	if (!aux)
+		return -ENOMEM;
+	card->aux_dev = aux;
+	card->num_aux_devs = num;
+
+	for (i = 0; i < card->num_aux_devs; i++, aux++) {
+		aux->codec_of_node =
+			of_parse_phandle(node, "audio-aux-devs", i);
+		if (!aux->codec_of_node)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int axg_card_tdm_be_hw_params(struct snd_pcm_substream *substream,
+				     struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct axg_card *priv = snd_soc_card_get_drvdata(rtd->card);
+	struct axg_dai_link_tdm_data *be =
+		(struct axg_dai_link_tdm_data *)priv->link_data[rtd->num];
+	struct snd_soc_dai *codec_dai;
+	unsigned int mclk;
+	int ret, i;
+
+	if (be->mclk_fs) {
+		mclk = params_rate(params) * be->mclk_fs;
+
+		for (i = 0; i < rtd->num_codecs; i++) {
+			codec_dai = rtd->codec_dais[i];
+			ret = snd_soc_dai_set_sysclk(codec_dai, 0, mclk,
+						     SND_SOC_CLOCK_IN);
+			if (ret && ret != -ENOTSUPP)
+				return ret;
+		}
+
+		ret = snd_soc_dai_set_sysclk(rtd->cpu_dai, 0, mclk,
+					     SND_SOC_CLOCK_OUT);
+		if (ret && ret != -ENOTSUPP)
+			return ret;
+	}
+
+	return 0;
+}
+
+static const struct snd_soc_ops axg_card_tdm_be_ops = {
+	.hw_params = axg_card_tdm_be_hw_params,
+};
+
+static int axg_card_tdm_dai_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(rtd->card);
+	struct axg_dai_link_tdm_data *be =
+		(struct axg_dai_link_tdm_data *)priv->link_data[rtd->num];
+	struct snd_soc_dai *codec_dai;
+	int ret, i;
+
+	for (i = 0; i < rtd->num_codecs; i++) {
+		codec_dai = rtd->codec_dais[i];
+		ret = snd_soc_dai_set_tdm_slot(codec_dai,
+					       be->codec_masks[i].tx,
+					       be->codec_masks[i].rx,
+					       be->slots, be->slot_width);
+		if (ret && ret != -ENOTSUPP) {
+			dev_err(codec_dai->dev,
+				"setting tdm link slots failed\n");
+			return ret;
+		}
+	}
+
+	ret = axg_tdm_set_tdm_slots(rtd->cpu_dai, be->tx_mask, be->rx_mask,
+				    be->slots, be->slot_width);
+	if (ret) {
+		dev_err(rtd->cpu_dai->dev, "setting tdm link slots failed\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int axg_card_tdm_dai_lb_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(rtd->card);
+	struct axg_dai_link_tdm_data *be =
+		(struct axg_dai_link_tdm_data *)priv->link_data[rtd->num];
+	int ret;
+
+	/* The loopback rx_mask is the pad tx_mask */
+	ret = axg_tdm_set_tdm_slots(rtd->cpu_dai, NULL, be->tx_mask,
+				    be->slots, be->slot_width);
+	if (ret) {
+		dev_err(rtd->cpu_dai->dev, "setting tdm link slots failed\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int axg_card_add_tdm_loopback(struct snd_soc_card *card,
+				     int *index)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai_link *pad = &card->dai_link[*index];
+	struct snd_soc_dai_link *lb;
+	int ret;
+
+	/* extend links */
+	ret = axg_card_reallocate_links(priv, card->num_links + 1);
+	if (ret)
+		return ret;
+
+	lb = &card->dai_link[*index + 1];
+
+	lb->name = kasprintf(GFP_KERNEL, "%s-lb", pad->name);
+	if (!lb->name)
+		return -ENOMEM;
+
+	lb->stream_name = lb->name;
+	lb->cpu_of_node = pad->cpu_of_node;
+	lb->cpu_dai_name = "TDM Loopback";
+	lb->codec_name = "snd-soc-dummy";
+	lb->codec_dai_name = "snd-soc-dummy-dai";
+	lb->dpcm_capture = 1;
+	lb->no_pcm = 1;
+	lb->ops = &axg_card_tdm_be_ops;
+	lb->init = axg_card_tdm_dai_lb_init;
+
+	/* Provide the same link data to the loopback */
+	priv->link_data[*index + 1] = priv->link_data[*index];
+
+	/*
+	 * axg_card_clean_references() will iterate over this link,
+	 * make sure the node count is balanced
+	 */
+	of_node_get(lb->cpu_of_node);
+
+	/* Let add_links continue where it should */
+	*index += 1;
+
+	return 0;
+}
+
+static unsigned int axg_card_parse_daifmt(struct device_node *node,
+					  struct device_node *cpu_node)
+{
+	struct device_node *bitclkmaster = NULL;
+	struct device_node *framemaster = NULL;
+	unsigned int daifmt;
+
+	daifmt = snd_soc_of_parse_daifmt(node, PREFIX,
+					 &bitclkmaster, &framemaster);
+	daifmt &= ~SND_SOC_DAIFMT_MASTER_MASK;
+
+	/* If no master is provided, default to cpu master */
+	if (!bitclkmaster || bitclkmaster == cpu_node) {
+		daifmt |= (!framemaster || framemaster == cpu_node) ?
+			SND_SOC_DAIFMT_CBS_CFS : SND_SOC_DAIFMT_CBS_CFM;
+	} else {
+		daifmt |= (!framemaster || framemaster == cpu_node) ?
+			SND_SOC_DAIFMT_CBM_CFS : SND_SOC_DAIFMT_CBM_CFM;
+	}
+
+	of_node_put(bitclkmaster);
+	of_node_put(framemaster);
+
+	return daifmt;
+}
+
+static int axg_card_parse_cpu_tdm_slots(struct snd_soc_card *card,
+					struct snd_soc_dai_link *link,
+					struct device_node *node,
+					struct axg_dai_link_tdm_data *be)
+{
+	char propname[32];
+	u32 tx, rx;
+	int i;
+
+	be->tx_mask = devm_kcalloc(card->dev, AXG_TDM_NUM_LANES,
+				   sizeof(*be->tx_mask), GFP_KERNEL);
+	be->rx_mask = devm_kcalloc(card->dev, AXG_TDM_NUM_LANES,
+				   sizeof(*be->rx_mask), GFP_KERNEL);
+	if (!be->tx_mask || !be->rx_mask)
+		return -ENOMEM;
+
+	for (i = 0, tx = 0; i < AXG_TDM_NUM_LANES; i++) {
+		snprintf(propname, 32, "dai-tdm-slot-tx-mask-%d", i);
+		snd_soc_of_get_slot_mask(node, propname, &be->tx_mask[i]);
+		tx = max(tx, be->tx_mask[i]);
+	}
+
+	/* Disable playback is the interface has no tx slots */
+	if (!tx)
+		link->dpcm_playback = 0;
+
+	for (i = 0, rx = 0; i < AXG_TDM_NUM_LANES; i++) {
+		snprintf(propname, 32, "dai-tdm-slot-rx-mask-%d", i);
+		snd_soc_of_get_slot_mask(node, propname, &be->rx_mask[i]);
+		rx = max(rx, be->rx_mask[i]);
+	}
+
+	/* Disable capture is the interface has no rx slots */
+	if (!rx)
+		link->dpcm_capture = 0;
+
+	/* ... but the interface should at least have one of them */
+	if (!tx && !rx) {
+		dev_err(card->dev, "tdm link has no cpu slots\n");
+		return -EINVAL;
+	}
+
+	of_property_read_u32(node, "dai-tdm-slot-num", &be->slots);
+	if (!be->slots) {
+		/*
+		 * If the slot number is not provided, set it such as it
+		 * accommodates the largest mask
+		 */
+		be->slots = fls(max(tx, rx));
+	} else if (be->slots < fls(max(tx, rx)) || be->slots > 32) {
+		/*
+		 * Error if the slots can't accommodate the largest mask or
+		 * if it is just too big
+		 */
+		dev_err(card->dev, "bad slot number\n");
+		return -EINVAL;
+	}
+
+	of_property_read_u32(node, "dai-tdm-slot-width", &be->slot_width);
+
+	return 0;
+}
+
+static int axg_card_parse_codecs_masks(struct snd_soc_card *card,
+				       struct snd_soc_dai_link *link,
+				       struct device_node *node,
+				       struct axg_dai_link_tdm_data *be)
+{
+	struct axg_dai_link_tdm_mask *codec_mask;
+	struct device_node *np;
+
+	codec_mask = devm_kcalloc(card->dev, link->num_codecs,
+				  sizeof(*codec_mask), GFP_KERNEL);
+	if (!codec_mask)
+		return -ENOMEM;
+
+	be->codec_masks = codec_mask;
+
+	for_each_child_of_node(node, np) {
+		snd_soc_of_get_slot_mask(np, "dai-tdm-slot-rx-mask",
+					 &codec_mask->rx);
+		snd_soc_of_get_slot_mask(np, "dai-tdm-slot-tx-mask",
+					 &codec_mask->tx);
+
+		codec_mask++;
+	}
+
+	return 0;
+}
+
+static int axg_card_parse_tdm(struct snd_soc_card *card,
+			      struct device_node *node,
+			      int *index)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai_link *link = &card->dai_link[*index];
+	struct axg_dai_link_tdm_data *be;
+	int ret;
+
+	/* Allocate tdm link parameters */
+	be = devm_kzalloc(card->dev, sizeof(*be), GFP_KERNEL);
+	if (!be)
+		return -ENOMEM;
+	priv->link_data[*index] = be;
+
+	/* Setup tdm link */
+	link->ops = &axg_card_tdm_be_ops;
+	link->init = axg_card_tdm_dai_init;
+	link->dai_fmt = axg_card_parse_daifmt(node, link->cpu_of_node);
+
+	of_property_read_u32(node, "mclk-fs", &be->mclk_fs);
+
+	ret = axg_card_parse_cpu_tdm_slots(card, link, node, be);
+	if (ret) {
+		dev_err(card->dev, "error parsing tdm link slots\n");
+		return ret;
+	}
+
+	ret = axg_card_parse_codecs_masks(card, link, node, be);
+	if (ret)
+		return ret;
+
+	/* Add loopback if the pad dai has playback */
+	if (link->dpcm_playback) {
+		ret = axg_card_add_tdm_loopback(card, index);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int axg_card_set_be_link(struct snd_soc_card *card,
+				struct snd_soc_dai_link *link,
+				struct device_node *node)
+{
+	struct snd_soc_dai_link_component *codec;
+	struct device_node *np;
+	int ret, num_codecs;
+
+	link->no_pcm = 1;
+	link->dpcm_playback = 1;
+	link->dpcm_capture = 1;
+
+	num_codecs = of_get_child_count(node);
+	if (!num_codecs) {
+		dev_err(card->dev, "be link %s has no codec\n",
+			node->full_name);
+		return -EINVAL;
+	}
+
+	codec = devm_kcalloc(card->dev, num_codecs, sizeof(*codec), GFP_KERNEL);
+	if (!codec)
+		return -ENOMEM;
+
+	link->codecs = codec;
+	link->num_codecs = num_codecs;
+
+	for_each_child_of_node(node, np) {
+		ret = axg_card_parse_dai(card, np, &codec->of_node,
+					 &codec->dai_name);
+		if (ret) {
+			of_node_put(np);
+			return ret;
+		}
+
+		codec++;
+	}
+
+	ret = axg_card_set_link_name(card, link, "be");
+	if (ret)
+		dev_err(card->dev, "error setting %s link name\n", np->name);
+
+	return ret;
+}
+
+static int axg_card_set_fe_link(struct snd_soc_card *card,
+				struct snd_soc_dai_link *link,
+				bool is_playback)
+{
+	link->dynamic = 1;
+	link->dpcm_merged_format = 1;
+	link->dpcm_merged_chan = 1;
+	link->dpcm_merged_rate = 1;
+	link->codec_dai_name = "snd-soc-dummy-dai";
+	link->codec_name = "snd-soc-dummy";
+
+	if (is_playback)
+		link->dpcm_playback = 1;
+	else
+		link->dpcm_capture = 1;
+
+	return axg_card_set_link_name(card, link, "fe");
+}
+
+static int axg_card_cpu_is_capture_fe(struct device_node *np)
+{
+	return of_device_is_compatible(np, PREFIX "axg-toddr");
+}
+
+static int axg_card_cpu_is_playback_fe(struct device_node *np)
+{
+	return of_device_is_compatible(np, PREFIX "axg-frddr");
+}
+
+static int axg_card_cpu_is_tdm_iface(struct device_node *np)
+{
+	return of_device_is_compatible(np, PREFIX "axg-tdm-iface");
+}
+
+static int axg_card_add_link(struct snd_soc_card *card, struct device_node *np,
+			     int *index)
+{
+	struct snd_soc_dai_link *dai_link = &card->dai_link[*index];
+	int ret;
+
+	ret = axg_card_parse_dai(card, np, &dai_link->cpu_of_node,
+				 &dai_link->cpu_dai_name);
+	if (ret)
+		return ret;
+
+	if (axg_card_cpu_is_playback_fe(dai_link->cpu_of_node))
+		ret = axg_card_set_fe_link(card, dai_link, true);
+	else if (axg_card_cpu_is_capture_fe(dai_link->cpu_of_node))
+		ret = axg_card_set_fe_link(card, dai_link, false);
+	else
+		ret = axg_card_set_be_link(card, dai_link, np);
+
+	if (ret)
+		return ret;
+
+	if (axg_card_cpu_is_tdm_iface(dai_link->cpu_of_node))
+		ret = axg_card_parse_tdm(card, np, index);
+
+	return ret;
+}
+
+static int axg_card_add_links(struct snd_soc_card *card)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(card);
+	struct device_node *node = card->dev->of_node;
+	struct device_node *np;
+	int num, i, ret;
+
+	num = of_get_child_count(node);
+	if (!num) {
+		dev_err(card->dev, "card has no links\n");
+		return -EINVAL;
+	}
+
+	ret = axg_card_reallocate_links(priv, num);
+	if (ret)
+		return ret;
+
+	i = 0;
+	for_each_child_of_node(node, np) {
+		ret = axg_card_add_link(card, np, &i);
+		if (ret) {
+			of_node_put(np);
+			return ret;
+		}
+
+		i++;
+	}
+
+	return 0;
+}
+
+static int axg_card_parse_of_optional(struct snd_soc_card *card,
+				      const char *propname,
+				      int (*func)(struct snd_soc_card *c,
+						  const char *p))
+{
+	/* If property is not provided, don't fail ... */
+	if (!of_property_read_bool(card->dev->of_node, propname))
+		return 0;
+
+	/* ... but do fail if it is provided and the parsing fails */
+	return func(card, propname);
+}
+
+static const struct of_device_id axg_card_of_match[] = {
+	{ .compatible = "amlogic,axg-sound-card", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, axg_card_of_match);
+
+static int axg_card_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct axg_card *priv;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, priv);
+	snd_soc_card_set_drvdata(&priv->card, priv);
+
+	priv->card.owner = THIS_MODULE;
+	priv->card.dev = dev;
+
+	ret = snd_soc_of_parse_card_name(&priv->card, "model");
+	if (ret < 0)
+		return ret;
+
+	ret = axg_card_parse_of_optional(&priv->card, "audio-routing",
+					 snd_soc_of_parse_audio_routing);
+	if (ret) {
+		dev_err(dev, "error while parsing routing\n");
+		return ret;
+	}
+
+	ret = axg_card_parse_of_optional(&priv->card, "audio-widgets",
+					 snd_soc_of_parse_audio_simple_widgets);
+	if (ret) {
+		dev_err(dev, "error while parsing widgets\n");
+		return ret;
+	}
+
+	ret = axg_card_add_links(&priv->card);
+	if (ret)
+		goto out_err;
+
+	ret = axg_card_add_aux_devices(&priv->card);
+	if (ret)
+		goto out_err;
+
+	ret = devm_snd_soc_register_card(dev, &priv->card);
+	if (ret)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	axg_card_clean_references(priv);
+	return ret;
+}
+
+static int axg_card_remove(struct platform_device *pdev)
+{
+	struct axg_card *priv = platform_get_drvdata(pdev);
+
+	axg_card_clean_references(priv);
+
+	return 0;
+}
+
+static struct platform_driver axg_card_pdrv = {
+	.probe = axg_card_probe,
+	.remove = axg_card_remove,
+	.driver = {
+		.name = "axg-sound-card",
+		.of_match_table = axg_card_of_match,
+	},
+};
+module_platform_driver(axg_card_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG ALSA machine driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c
new file mode 100644
index 000000000000..30262550e37b
--- /dev/null
+++ b/sound/soc/meson/axg-fifo.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/clk.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-fifo.h"
+
+/*
+ * This file implements the platform operations common to the playback and
+ * capture frontend DAI. The logic behind this two types of fifo is very
+ * similar but some difference exist.
+ * These differences the respective DAI drivers
+ */
+
+static struct snd_pcm_hardware axg_fifo_hw = {
+	.info = (SNDRV_PCM_INFO_INTERLEAVED |
+		 SNDRV_PCM_INFO_MMAP |
+		 SNDRV_PCM_INFO_MMAP_VALID |
+		 SNDRV_PCM_INFO_BLOCK_TRANSFER |
+		 SNDRV_PCM_INFO_PAUSE),
+
+	.formats = AXG_FIFO_FORMATS,
+	.rate_min = 5512,
+	.rate_max = 192000,
+	.channels_min = 1,
+	.channels_max = AXG_FIFO_CH_MAX,
+	.period_bytes_min = AXG_FIFO_MIN_DEPTH,
+	.period_bytes_max = UINT_MAX,
+	.periods_min = 2,
+	.periods_max = UINT_MAX,
+
+	/* No real justification for this */
+	.buffer_bytes_max = 1 * 1024 * 1024,
+};
+
+static struct snd_soc_dai *axg_fifo_dai(struct snd_pcm_substream *ss)
+{
+	struct snd_soc_pcm_runtime *rtd = ss->private_data;
+
+	return rtd->cpu_dai;
+}
+
+static struct axg_fifo *axg_fifo_data(struct snd_pcm_substream *ss)
+{
+	struct snd_soc_dai *dai = axg_fifo_dai(ss);
+
+	return snd_soc_dai_get_drvdata(dai);
+}
+
+static struct device *axg_fifo_dev(struct snd_pcm_substream *ss)
+{
+	struct snd_soc_dai *dai = axg_fifo_dai(ss);
+
+	return dai->dev;
+}
+
+static void __dma_enable(struct axg_fifo *fifo,  bool enable)
+{
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_DMA_EN,
+			   enable ? CTRL0_DMA_EN : 0);
+}
+
+static int axg_fifo_pcm_trigger(struct snd_pcm_substream *ss, int cmd)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		__dma_enable(fifo, true);
+		break;
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+	case SNDRV_PCM_TRIGGER_STOP:
+		__dma_enable(fifo, false);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static snd_pcm_uframes_t axg_fifo_pcm_pointer(struct snd_pcm_substream *ss)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	struct snd_pcm_runtime *runtime = ss->runtime;
+	unsigned int addr;
+
+	regmap_read(fifo->map, FIFO_STATUS2, &addr);
+
+	return bytes_to_frames(runtime, addr - (unsigned int)runtime->dma_addr);
+}
+
+static int axg_fifo_pcm_hw_params(struct snd_pcm_substream *ss,
+				  struct snd_pcm_hw_params *params)
+{
+	struct snd_pcm_runtime *runtime = ss->runtime;
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	dma_addr_t end_ptr;
+	unsigned int burst_num;
+	int ret;
+
+	ret = snd_pcm_lib_malloc_pages(ss, params_buffer_bytes(params));
+	if (ret < 0)
+		return ret;
+
+	/* Setup dma memory pointers */
+	end_ptr = runtime->dma_addr + runtime->dma_bytes - AXG_FIFO_BURST;
+	regmap_write(fifo->map, FIFO_START_ADDR, runtime->dma_addr);
+	regmap_write(fifo->map, FIFO_FINISH_ADDR, end_ptr);
+
+	/* Setup interrupt periodicity */
+	burst_num = params_period_bytes(params) / AXG_FIFO_BURST;
+	regmap_write(fifo->map, FIFO_INT_ADDR, burst_num);
+
+	/* Enable block count irq */
+	regmap_update_bits(fifo->map, FIFO_CTRL0,
+			   CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT),
+			   CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT));
+
+	return 0;
+}
+
+static int axg_fifo_pcm_hw_free(struct snd_pcm_substream *ss)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+
+	/* Disable the block count irq */
+	regmap_update_bits(fifo->map, FIFO_CTRL0,
+			   CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT), 0);
+
+	return snd_pcm_lib_free_pages(ss);
+}
+
+static void axg_fifo_ack_irq(struct axg_fifo *fifo, u8 mask)
+{
+	regmap_update_bits(fifo->map, FIFO_CTRL1,
+			   CTRL1_INT_CLR(FIFO_INT_MASK),
+			   CTRL1_INT_CLR(mask));
+
+	/* Clear must also be cleared */
+	regmap_update_bits(fifo->map, FIFO_CTRL1,
+			   CTRL1_INT_CLR(FIFO_INT_MASK),
+			   0);
+}
+
+static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id)
+{
+	struct snd_pcm_substream *ss = dev_id;
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	unsigned int status;
+
+	regmap_read(fifo->map, FIFO_STATUS1, &status);
+
+	status = STATUS1_INT_STS(status) & FIFO_INT_MASK;
+	if (status & FIFO_INT_COUNT_REPEAT)
+		snd_pcm_period_elapsed(ss);
+	else
+		dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n",
+			status);
+
+	/* Ack irqs */
+	axg_fifo_ack_irq(fifo, status);
+
+	return IRQ_RETVAL(status);
+}
+
+static int axg_fifo_pcm_open(struct snd_pcm_substream *ss)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	struct device *dev = axg_fifo_dev(ss);
+	int ret;
+
+	snd_soc_set_runtime_hwparams(ss, &axg_fifo_hw);
+
+	/*
+	 * Make sure the buffer and period size are multiple of the FIFO
+	 * minimum depth size
+	 */
+	ret = snd_pcm_hw_constraint_step(ss->runtime, 0,
+					 SNDRV_PCM_HW_PARAM_BUFFER_BYTES,
+					 AXG_FIFO_MIN_DEPTH);
+	if (ret)
+		return ret;
+
+	ret = snd_pcm_hw_constraint_step(ss->runtime, 0,
+					 SNDRV_PCM_HW_PARAM_PERIOD_BYTES,
+					 AXG_FIFO_MIN_DEPTH);
+	if (ret)
+		return ret;
+
+	ret = request_irq(fifo->irq, axg_fifo_pcm_irq_block, 0,
+			  dev_name(dev), ss);
+
+	/* Enable pclk to access registers and clock the fifo ip */
+	ret = clk_prepare_enable(fifo->pclk);
+	if (ret)
+		return ret;
+
+	/* Setup status2 so it reports the memory pointer */
+	regmap_update_bits(fifo->map, FIFO_CTRL1,
+			   CTRL1_STATUS2_SEL_MASK,
+			   CTRL1_STATUS2_SEL(STATUS2_SEL_DDR_READ));
+
+	/* Make sure the dma is initially disabled */
+	__dma_enable(fifo, false);
+
+	/* Disable irqs until params are ready */
+	regmap_update_bits(fifo->map, FIFO_CTRL0,
+			   CTRL0_INT_EN(FIFO_INT_MASK), 0);
+
+	/* Clear any pending interrupt */
+	axg_fifo_ack_irq(fifo, FIFO_INT_MASK);
+
+	/* Take memory arbitror out of reset */
+	ret = reset_control_deassert(fifo->arb);
+	if (ret)
+		clk_disable_unprepare(fifo->pclk);
+
+	return ret;
+}
+
+static int axg_fifo_pcm_close(struct snd_pcm_substream *ss)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	int ret;
+
+	/* Put the memory arbitror back in reset */
+	ret = reset_control_assert(fifo->arb);
+
+	/* Disable fifo ip and register access */
+	clk_disable_unprepare(fifo->pclk);
+
+	/* remove IRQ */
+	free_irq(fifo->irq, ss);
+
+	return ret;
+}
+
+const struct snd_pcm_ops axg_fifo_pcm_ops = {
+	.open =		axg_fifo_pcm_open,
+	.close =        axg_fifo_pcm_close,
+	.ioctl =	snd_pcm_lib_ioctl,
+	.hw_params =	axg_fifo_pcm_hw_params,
+	.hw_free =      axg_fifo_pcm_hw_free,
+	.pointer =	axg_fifo_pcm_pointer,
+	.trigger =	axg_fifo_pcm_trigger,
+};
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_ops);
+
+int axg_fifo_pcm_new(struct snd_soc_pcm_runtime *rtd, unsigned int type)
+{
+	struct snd_card *card = rtd->card->snd_card;
+	size_t size = axg_fifo_hw.buffer_bytes_max;
+
+	return snd_pcm_lib_preallocate_pages(rtd->pcm->streams[type].substream,
+					     SNDRV_DMA_TYPE_DEV, card->dev,
+					     size, size);
+}
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_new);
+
+static const struct regmap_config axg_fifo_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= FIFO_STATUS2,
+};
+
+int axg_fifo_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct axg_fifo_match_data *data;
+	struct axg_fifo *fifo;
+	struct resource *res;
+	void __iomem *regs;
+
+	data = of_device_get_match_data(dev);
+	if (!data) {
+		dev_err(dev, "failed to match device\n");
+		return -ENODEV;
+	}
+
+	fifo = devm_kzalloc(dev, sizeof(*fifo), GFP_KERNEL);
+	if (!fifo)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, fifo);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	fifo->map = devm_regmap_init_mmio(dev, regs, &axg_fifo_regmap_cfg);
+	if (IS_ERR(fifo->map)) {
+		dev_err(dev, "failed to init regmap: %ld\n",
+			PTR_ERR(fifo->map));
+		return PTR_ERR(fifo->map);
+	}
+
+	fifo->pclk = devm_clk_get(dev, NULL);
+	if (IS_ERR(fifo->pclk)) {
+		if (PTR_ERR(fifo->pclk) != -EPROBE_DEFER)
+			dev_err(dev, "failed to get pclk: %ld\n",
+				PTR_ERR(fifo->pclk));
+		return PTR_ERR(fifo->pclk);
+	}
+
+	fifo->arb = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(fifo->arb)) {
+		if (PTR_ERR(fifo->arb) != -EPROBE_DEFER)
+			dev_err(dev, "failed to get arb reset: %ld\n",
+				PTR_ERR(fifo->arb));
+		return PTR_ERR(fifo->arb);
+	}
+
+	fifo->irq = of_irq_get(dev->of_node, 0);
+	if (fifo->irq <= 0) {
+		dev_err(dev, "failed to get irq: %d\n", fifo->irq);
+		return fifo->irq;
+	}
+
+	return devm_snd_soc_register_component(dev, data->component_drv,
+					       data->dai_drv, 1);
+}
+EXPORT_SYMBOL_GPL(axg_fifo_probe);
+
+MODULE_DESCRIPTION("Amlogic AXG fifo driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-fifo.h b/sound/soc/meson/axg-fifo.h
new file mode 100644
index 000000000000..cb6c4013ca33
--- /dev/null
+++ b/sound/soc/meson/axg-fifo.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef _MESON_AXG_FIFO_H
+#define _MESON_AXG_FIFO_H
+
+struct clk;
+struct platform_device;
+struct regmap;
+struct reset_control;
+
+struct snd_soc_component_driver;
+struct snd_soc_dai;
+struct snd_soc_dai_driver;
+struct snd_pcm_ops;
+struct snd_soc_pcm_runtime;
+
+#define AXG_FIFO_CH_MAX			128
+#define AXG_FIFO_RATES			(SNDRV_PCM_RATE_5512 |		\
+					 SNDRV_PCM_RATE_8000_192000)
+#define AXG_FIFO_FORMATS		(SNDRV_PCM_FMTBIT_S8 |		\
+					 SNDRV_PCM_FMTBIT_S16_LE |	\
+					 SNDRV_PCM_FMTBIT_S20_LE |	\
+					 SNDRV_PCM_FMTBIT_S24_LE |	\
+					 SNDRV_PCM_FMTBIT_S32_LE)
+
+#define AXG_FIFO_BURST			8
+#define AXG_FIFO_MIN_CNT		64
+#define AXG_FIFO_MIN_DEPTH		(AXG_FIFO_BURST * AXG_FIFO_MIN_CNT)
+
+#define FIFO_INT_ADDR_FINISH		BIT(0)
+#define FIFO_INT_ADDR_INT		BIT(1)
+#define FIFO_INT_COUNT_REPEAT		BIT(2)
+#define FIFO_INT_COUNT_ONCE		BIT(3)
+#define FIFO_INT_FIFO_ZERO		BIT(4)
+#define FIFO_INT_FIFO_DEPTH		BIT(5)
+#define FIFO_INT_MASK			GENMASK(7, 0)
+
+#define FIFO_CTRL0			0x00
+#define  CTRL0_DMA_EN			BIT(31)
+#define  CTRL0_INT_EN(x)		((x) << 16)
+#define  CTRL0_SEL_MASK			GENMASK(2, 0)
+#define  CTRL0_SEL_SHIFT		0
+#define FIFO_CTRL1			0x04
+#define  CTRL1_INT_CLR(x)		((x) << 0)
+#define  CTRL1_STATUS2_SEL_MASK		GENMASK(11, 8)
+#define  CTRL1_STATUS2_SEL(x)		((x) << 8)
+#define   STATUS2_SEL_DDR_READ		0
+#define  CTRL1_THRESHOLD_MASK		GENMASK(23, 16)
+#define  CTRL1_THRESHOLD(x)		((x) << 16)
+#define  CTRL1_FRDDR_DEPTH_MASK		GENMASK(31, 24)
+#define  CTRL1_FRDDR_DEPTH(x)		((x) << 24)
+#define FIFO_START_ADDR			0x08
+#define FIFO_FINISH_ADDR		0x0c
+#define FIFO_INT_ADDR			0x10
+#define FIFO_STATUS1			0x14
+#define  STATUS1_INT_STS(x)		((x) << 0)
+#define FIFO_STATUS2			0x18
+
+struct axg_fifo {
+	struct regmap *map;
+	struct clk *pclk;
+	struct reset_control *arb;
+	int irq;
+};
+
+struct axg_fifo_match_data {
+	const struct snd_soc_component_driver *component_drv;
+	struct snd_soc_dai_driver *dai_drv;
+};
+
+extern const struct snd_pcm_ops axg_fifo_pcm_ops;
+
+int axg_fifo_pcm_new(struct snd_soc_pcm_runtime *rtd, unsigned int type);
+int axg_fifo_probe(struct platform_device *pdev);
+
+#endif /* _MESON_AXG_FIFO_H */
diff --git a/sound/soc/meson/axg-frddr.c b/sound/soc/meson/axg-frddr.c
new file mode 100644
index 000000000000..a6f6f6a2eca8
--- /dev/null
+++ b/sound/soc/meson/axg-frddr.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+/* This driver implements the frontend playback DAI of AXG based SoCs */
+
+#include <linux/clk.h>
+#include <linux/regmap.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-fifo.h"
+
+#define CTRL0_FRDDR_PP_MODE	BIT(30)
+
+static int axg_frddr_dai_startup(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+	unsigned int fifo_depth, fifo_threshold;
+	int ret;
+
+	/* Enable pclk to access registers and clock the fifo ip */
+	ret = clk_prepare_enable(fifo->pclk);
+	if (ret)
+		return ret;
+
+	/* Apply single buffer mode to the interface */
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_FRDDR_PP_MODE, 0);
+
+	/*
+	 * TODO: We could adapt the fifo depth and the fifo threshold
+	 * depending on the expected memory throughput and lantencies
+	 * For now, we'll just use the same values as the vendor kernel
+	 * Depth and threshold are zero based.
+	 */
+	fifo_depth = AXG_FIFO_MIN_CNT - 1;
+	fifo_threshold = (AXG_FIFO_MIN_CNT / 2) - 1;
+	regmap_update_bits(fifo->map, FIFO_CTRL1,
+			   CTRL1_FRDDR_DEPTH_MASK | CTRL1_THRESHOLD_MASK,
+			   CTRL1_FRDDR_DEPTH(fifo_depth) |
+			   CTRL1_THRESHOLD(fifo_threshold));
+
+	return 0;
+}
+
+static void axg_frddr_dai_shutdown(struct snd_pcm_substream *substream,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+
+	clk_disable_unprepare(fifo->pclk);
+}
+
+static int axg_frddr_pcm_new(struct snd_soc_pcm_runtime *rtd,
+			     struct snd_soc_dai *dai)
+{
+	return axg_fifo_pcm_new(rtd, SNDRV_PCM_STREAM_PLAYBACK);
+}
+
+static const struct snd_soc_dai_ops axg_frddr_ops = {
+	.startup	= axg_frddr_dai_startup,
+	.shutdown	= axg_frddr_dai_shutdown,
+};
+
+static struct snd_soc_dai_driver axg_frddr_dai_drv = {
+	.name = "FRDDR",
+	.playback = {
+		.stream_name	= "Playback",
+		.channels_min	= 1,
+		.channels_max	= AXG_FIFO_CH_MAX,
+		.rates		= AXG_FIFO_RATES,
+		.formats	= AXG_FIFO_FORMATS,
+	},
+	.ops		= &axg_frddr_ops,
+	.pcm_new	= axg_frddr_pcm_new,
+};
+
+static const char * const axg_frddr_sel_texts[] = {
+	"OUT 0", "OUT 1", "OUT 2", "OUT 3"
+};
+
+static SOC_ENUM_SINGLE_DECL(axg_frddr_sel_enum, FIFO_CTRL0, CTRL0_SEL_SHIFT,
+			    axg_frddr_sel_texts);
+
+static const struct snd_kcontrol_new axg_frddr_out_demux =
+	SOC_DAPM_ENUM("Output Sink", axg_frddr_sel_enum);
+
+static const struct snd_soc_dapm_widget axg_frddr_dapm_widgets[] = {
+	SND_SOC_DAPM_DEMUX("SINK SEL", SND_SOC_NOPM, 0, 0,
+			   &axg_frddr_out_demux),
+	SND_SOC_DAPM_AIF_OUT("OUT 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("OUT 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("OUT 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("OUT 3", NULL, 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route axg_frddr_dapm_routes[] = {
+	{ "SINK SEL", NULL, "Playback" },
+	{ "OUT 0", "OUT 0",  "SINK SEL" },
+	{ "OUT 1", "OUT 1",  "SINK SEL" },
+	{ "OUT 2", "OUT 2",  "SINK SEL" },
+	{ "OUT 3", "OUT 3",  "SINK SEL" },
+};
+
+static const struct snd_soc_component_driver axg_frddr_component_drv = {
+	.dapm_widgets		= axg_frddr_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_frddr_dapm_widgets),
+	.dapm_routes		= axg_frddr_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_frddr_dapm_routes),
+	.ops			= &axg_fifo_pcm_ops
+};
+
+static const struct axg_fifo_match_data axg_frddr_match_data = {
+	.component_drv	= &axg_frddr_component_drv,
+	.dai_drv	= &axg_frddr_dai_drv
+};
+
+static const struct of_device_id axg_frddr_of_match[] = {
+	{
+		.compatible = "amlogic,axg-frddr",
+		.data = &axg_frddr_match_data,
+	}, {}
+};
+MODULE_DEVICE_TABLE(of, axg_frddr_of_match);
+
+static struct platform_driver axg_frddr_pdrv = {
+	.probe = axg_fifo_probe,
+	.driver = {
+		.name = "axg-frddr",
+		.of_match_table = axg_frddr_of_match,
+	},
+};
+module_platform_driver(axg_frddr_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG playback fifo driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-spdifout.c b/sound/soc/meson/axg-spdifout.c
new file mode 100644
index 000000000000..9dea528053ad
--- /dev/null
+++ b/sound/soc/meson/axg-spdifout.c
@@ -0,0 +1,456 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+#include <sound/pcm_params.h>
+#include <sound/pcm_iec958.h>
+
+/*
+ * NOTE:
+ * The meaning of bits SPDIFOUT_CTRL0_XXX_SEL is actually the opposite
+ * of what the documentation says. Manual control on V, U and C bits is
+ * applied when the related sel bits are cleared
+ */
+
+#define SPDIFOUT_STAT			0x00
+#define SPDIFOUT_GAIN0			0x04
+#define SPDIFOUT_GAIN1			0x08
+#define SPDIFOUT_CTRL0			0x0c
+#define  SPDIFOUT_CTRL0_EN		BIT(31)
+#define  SPDIFOUT_CTRL0_RST_OUT		BIT(29)
+#define  SPDIFOUT_CTRL0_RST_IN		BIT(28)
+#define  SPDIFOUT_CTRL0_USEL		BIT(26)
+#define  SPDIFOUT_CTRL0_USET		BIT(25)
+#define  SPDIFOUT_CTRL0_CHSTS_SEL	BIT(24)
+#define  SPDIFOUT_CTRL0_DATA_SEL	BIT(20)
+#define  SPDIFOUT_CTRL0_MSB_FIRST	BIT(19)
+#define  SPDIFOUT_CTRL0_VSEL		BIT(18)
+#define  SPDIFOUT_CTRL0_VSET		BIT(17)
+#define  SPDIFOUT_CTRL0_MASK_MASK	GENMASK(11, 4)
+#define  SPDIFOUT_CTRL0_MASK(x)		((x) << 4)
+#define SPDIFOUT_CTRL1			0x10
+#define  SPDIFOUT_CTRL1_MSB_POS_MASK	GENMASK(12, 8)
+#define  SPDIFOUT_CTRL1_MSB_POS(x)	((x) << 8)
+#define  SPDIFOUT_CTRL1_TYPE_MASK	GENMASK(6, 4)
+#define  SPDIFOUT_CTRL1_TYPE(x)		((x) << 4)
+#define SPDIFOUT_PREAMB			0x14
+#define SPDIFOUT_SWAP			0x18
+#define SPDIFOUT_CHSTS0			0x1c
+#define SPDIFOUT_CHSTS1			0x20
+#define SPDIFOUT_CHSTS2			0x24
+#define SPDIFOUT_CHSTS3			0x28
+#define SPDIFOUT_CHSTS4			0x2c
+#define SPDIFOUT_CHSTS5			0x30
+#define SPDIFOUT_CHSTS6			0x34
+#define SPDIFOUT_CHSTS7			0x38
+#define SPDIFOUT_CHSTS8			0x3c
+#define SPDIFOUT_CHSTS9			0x40
+#define SPDIFOUT_CHSTSA			0x44
+#define SPDIFOUT_CHSTSB			0x48
+#define SPDIFOUT_MUTE_VAL		0x4c
+
+struct axg_spdifout {
+	struct regmap *map;
+	struct clk *mclk;
+	struct clk *pclk;
+};
+
+static void axg_spdifout_enable(struct regmap *map)
+{
+	/* Apply both reset */
+	regmap_update_bits(map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_RST_OUT | SPDIFOUT_CTRL0_RST_IN,
+			   0);
+
+	/* Clear out reset before in reset */
+	regmap_update_bits(map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_RST_OUT, SPDIFOUT_CTRL0_RST_OUT);
+	regmap_update_bits(map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_RST_IN,  SPDIFOUT_CTRL0_RST_IN);
+
+	/* Enable spdifout */
+	regmap_update_bits(map, SPDIFOUT_CTRL0, SPDIFOUT_CTRL0_EN,
+			   SPDIFOUT_CTRL0_EN);
+}
+
+static void axg_spdifout_disable(struct regmap *map)
+{
+	regmap_update_bits(map, SPDIFOUT_CTRL0, SPDIFOUT_CTRL0_EN, 0);
+}
+
+static int axg_spdifout_trigger(struct snd_pcm_substream *substream, int cmd,
+				struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		axg_spdifout_enable(priv->map);
+		return 0;
+
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		axg_spdifout_disable(priv->map);
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int axg_spdifout_digital_mute(struct snd_soc_dai *dai, int mute)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+
+	/* Use spdif valid bit to perform digital mute */
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0, SPDIFOUT_CTRL0_VSET,
+			   mute ? SPDIFOUT_CTRL0_VSET : 0);
+
+	return 0;
+}
+
+static int axg_spdifout_sample_fmt(struct snd_pcm_hw_params *params,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+	unsigned int val;
+
+	/* Set the samples spdifout will pull from the FIFO */
+	switch (params_channels(params)) {
+	case 1:
+		val = SPDIFOUT_CTRL0_MASK(0x1);
+		break;
+	case 2:
+		val = SPDIFOUT_CTRL0_MASK(0x3);
+		break;
+	default:
+		dev_err(dai->dev, "too many channels for spdif dai: %u\n",
+			params_channels(params));
+		return -EINVAL;
+	}
+
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_MASK_MASK, val);
+
+	/* FIFO data are arranged in chunks of 64bits */
+	switch (params_physical_width(params)) {
+	case 8:
+		/* 8 samples of 8 bits */
+		val = SPDIFOUT_CTRL1_TYPE(0);
+		break;
+	case 16:
+		/* 4 samples of 16 bits - right justified */
+		val = SPDIFOUT_CTRL1_TYPE(2);
+		break;
+	case 32:
+		/* 2 samples of 32 bits - right justified */
+		val = SPDIFOUT_CTRL1_TYPE(4);
+		break;
+	default:
+		dev_err(dai->dev, "Unsupported physical width: %u\n",
+			params_physical_width(params));
+		return -EINVAL;
+	}
+
+	/* Position of the MSB in FIFO samples */
+	val |= SPDIFOUT_CTRL1_MSB_POS(params_width(params) - 1);
+
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL1,
+			   SPDIFOUT_CTRL1_MSB_POS_MASK |
+			   SPDIFOUT_CTRL1_TYPE_MASK, val);
+
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_MSB_FIRST | SPDIFOUT_CTRL0_DATA_SEL,
+			   0);
+
+	return 0;
+}
+
+static int axg_spdifout_set_chsts(struct snd_pcm_hw_params *params,
+				  struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+	unsigned int offset;
+	int ret;
+	u8 cs[4];
+	u32 val;
+
+	ret = snd_pcm_create_iec958_consumer_hw_params(params, cs, 4);
+	if (ret < 0) {
+		dev_err(dai->dev, "Creating IEC958 channel status failed %d\n",
+			ret);
+		return ret;
+	}
+	val = cs[0] | cs[1] << 8 | cs[2] << 16 | cs[3] << 24;
+
+	/* Setup channel status A bits [31 - 0]*/
+	regmap_write(priv->map, SPDIFOUT_CHSTS0, val);
+
+	/* Clear channel status A bits [191 - 32] */
+	for (offset = SPDIFOUT_CHSTS1; offset <= SPDIFOUT_CHSTS5;
+	     offset += regmap_get_reg_stride(priv->map))
+		regmap_write(priv->map, offset, 0);
+
+	/* Setup channel status B bits [31 - 0]*/
+	regmap_write(priv->map, SPDIFOUT_CHSTS6, val);
+
+	/* Clear channel status B bits [191 - 32] */
+	for (offset = SPDIFOUT_CHSTS7; offset <= SPDIFOUT_CHSTSB;
+	     offset += regmap_get_reg_stride(priv->map))
+		regmap_write(priv->map, offset, 0);
+
+	return 0;
+}
+
+static int axg_spdifout_hw_params(struct snd_pcm_substream *substream,
+				  struct snd_pcm_hw_params *params,
+				  struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+	unsigned int rate = params_rate(params);
+	int ret;
+
+	/* 2 * 32bits per subframe * 2 channels = 128 */
+	ret = clk_set_rate(priv->mclk, rate * 128);
+	if (ret) {
+		dev_err(dai->dev, "failed to set spdif clock\n");
+		return ret;
+	}
+
+	ret = axg_spdifout_sample_fmt(params, dai);
+	if (ret) {
+		dev_err(dai->dev, "failed to setup sample format\n");
+		return ret;
+	}
+
+	ret = axg_spdifout_set_chsts(params, dai);
+	if (ret) {
+		dev_err(dai->dev, "failed to setup channel status words\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int axg_spdifout_startup(struct snd_pcm_substream *substream,
+				struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+	int ret;
+
+	/* Clock the spdif output block */
+	ret = clk_prepare_enable(priv->pclk);
+	if (ret) {
+		dev_err(dai->dev, "failed to enable pclk\n");
+		return ret;
+	}
+
+	/* Make sure the block is initially stopped */
+	axg_spdifout_disable(priv->map);
+
+	/* Insert data from bit 27 lsb first */
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_MSB_FIRST | SPDIFOUT_CTRL0_DATA_SEL,
+			   0);
+
+	/* Manual control of V, C and U, U = 0 */
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_CHSTS_SEL | SPDIFOUT_CTRL0_VSEL |
+			   SPDIFOUT_CTRL0_USEL | SPDIFOUT_CTRL0_USET,
+			   0);
+
+	/* Static SWAP configuration ATM */
+	regmap_write(priv->map, SPDIFOUT_SWAP, 0x10);
+
+	return 0;
+}
+
+static void axg_spdifout_shutdown(struct snd_pcm_substream *substream,
+				  struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+
+	clk_disable_unprepare(priv->pclk);
+}
+
+static const struct snd_soc_dai_ops axg_spdifout_ops = {
+	.trigger	= axg_spdifout_trigger,
+	.digital_mute	= axg_spdifout_digital_mute,
+	.hw_params	= axg_spdifout_hw_params,
+	.startup	= axg_spdifout_startup,
+	.shutdown	= axg_spdifout_shutdown,
+};
+
+static struct snd_soc_dai_driver axg_spdifout_dai_drv[] = {
+	{
+		.name = "SPDIF Output",
+		.playback = {
+			.stream_name	= "Playback",
+			.channels_min	= 1,
+			.channels_max	= 2,
+			.rates		= (SNDRV_PCM_RATE_32000  |
+					   SNDRV_PCM_RATE_44100  |
+					   SNDRV_PCM_RATE_48000  |
+					   SNDRV_PCM_RATE_88200  |
+					   SNDRV_PCM_RATE_96000  |
+					   SNDRV_PCM_RATE_176400 |
+					   SNDRV_PCM_RATE_192000),
+			.formats	= (SNDRV_PCM_FMTBIT_S8     |
+					   SNDRV_PCM_FMTBIT_S16_LE |
+					   SNDRV_PCM_FMTBIT_S20_LE |
+					   SNDRV_PCM_FMTBIT_S24_LE),
+		},
+		.ops = &axg_spdifout_ops,
+	},
+};
+
+static const char * const spdifout_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2",
+};
+
+static SOC_ENUM_SINGLE_DECL(axg_spdifout_sel_enum, SPDIFOUT_CTRL1, 24,
+			    spdifout_sel_texts);
+
+static const struct snd_kcontrol_new axg_spdifout_in_mux =
+	SOC_DAPM_ENUM("Input Source", axg_spdifout_sel_enum);
+
+static const struct snd_soc_dapm_widget axg_spdifout_dapm_widgets[] = {
+	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &axg_spdifout_in_mux),
+};
+
+static const struct snd_soc_dapm_route axg_spdifout_dapm_routes[] = {
+	{ "SRC SEL", "IN 0", "IN 0" },
+	{ "SRC SEL", "IN 1", "IN 1" },
+	{ "SRC SEL", "IN 2", "IN 2" },
+	{ "Playback", NULL, "SRC SEL" },
+};
+
+static const struct snd_kcontrol_new axg_spdifout_controls[] = {
+	SOC_DOUBLE("Playback Volume", SPDIFOUT_GAIN0,  0,  8, 255, 0),
+	SOC_DOUBLE("Playback Switch", SPDIFOUT_CTRL0, 22, 21, 1, 1),
+	SOC_SINGLE("Playback Gain Enable Switch",
+		   SPDIFOUT_CTRL1, 26, 1, 0),
+	SOC_SINGLE("Playback Channels Mix Switch",
+		   SPDIFOUT_CTRL0, 23, 1, 0),
+};
+
+static int axg_spdifout_set_bias_level(struct snd_soc_component *component,
+				       enum snd_soc_bias_level level)
+{
+	struct axg_spdifout *priv = snd_soc_component_get_drvdata(component);
+	enum snd_soc_bias_level now =
+		snd_soc_component_get_bias_level(component);
+	int ret = 0;
+
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		if (now == SND_SOC_BIAS_STANDBY)
+			ret = clk_prepare_enable(priv->mclk);
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		if (now == SND_SOC_BIAS_PREPARE)
+			clk_disable_unprepare(priv->mclk);
+		break;
+
+	case SND_SOC_BIAS_OFF:
+	case SND_SOC_BIAS_ON:
+		break;
+	}
+
+	return ret;
+}
+
+static const struct snd_soc_component_driver axg_spdifout_component_drv = {
+	.controls		= axg_spdifout_controls,
+	.num_controls		= ARRAY_SIZE(axg_spdifout_controls),
+	.dapm_widgets		= axg_spdifout_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_spdifout_dapm_widgets),
+	.dapm_routes		= axg_spdifout_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_spdifout_dapm_routes),
+	.set_bias_level		= axg_spdifout_set_bias_level,
+};
+
+static const struct regmap_config axg_spdifout_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= SPDIFOUT_MUTE_VAL,
+};
+
+static const struct of_device_id axg_spdifout_of_match[] = {
+	{ .compatible = "amlogic,axg-spdifout", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, axg_spdifout_of_match);
+
+static int axg_spdifout_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct axg_spdifout *priv;
+	struct resource *res;
+	void __iomem *regs;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, priv);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	priv->map = devm_regmap_init_mmio(dev, regs, &axg_spdifout_regmap_cfg);
+	if (IS_ERR(priv->map)) {
+		dev_err(dev, "failed to init regmap: %ld\n",
+			PTR_ERR(priv->map));
+		return PTR_ERR(priv->map);
+	}
+
+	priv->pclk = devm_clk_get(dev, "pclk");
+	if (IS_ERR(priv->pclk)) {
+		ret = PTR_ERR(priv->pclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get pclk: %d\n", ret);
+		return ret;
+	}
+
+	priv->mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(priv->mclk)) {
+		ret = PTR_ERR(priv->mclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get mclk: %d\n", ret);
+		return ret;
+	}
+
+	return devm_snd_soc_register_component(dev, &axg_spdifout_component_drv,
+			axg_spdifout_dai_drv, ARRAY_SIZE(axg_spdifout_dai_drv));
+}
+
+static struct platform_driver axg_spdifout_pdrv = {
+	.probe = axg_spdifout_probe,
+	.driver = {
+		.name = "axg-spdifout",
+		.of_match_table = axg_spdifout_of_match,
+	},
+};
+module_platform_driver(axg_spdifout_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG SPDIF Output driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-tdm-formatter.c b/sound/soc/meson/axg-tdm-formatter.c
new file mode 100644
index 000000000000..43e390f9358a
--- /dev/null
+++ b/sound/soc/meson/axg-tdm-formatter.c
@@ -0,0 +1,381 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+
+#include "axg-tdm-formatter.h"
+
+struct axg_tdm_formatter {
+	struct list_head list;
+	struct axg_tdm_stream *stream;
+	const struct axg_tdm_formatter_driver *drv;
+	struct clk *pclk;
+	struct clk *sclk;
+	struct clk *lrclk;
+	struct clk *sclk_sel;
+	struct clk *lrclk_sel;
+	bool enabled;
+	struct regmap *map;
+};
+
+int axg_tdm_formatter_set_channel_masks(struct regmap *map,
+					struct axg_tdm_stream *ts,
+					unsigned int offset)
+{
+	unsigned int val, ch = ts->channels;
+	unsigned long mask;
+	int i, j;
+
+	/*
+	 * Distribute the channels of the stream over the available slots
+	 * of each TDM lane
+	 */
+	for (i = 0; i < AXG_TDM_NUM_LANES; i++) {
+		val = 0;
+		mask = ts->mask[i];
+
+		for (j = find_first_bit(&mask, 32);
+		     (j < 32) && ch;
+		     j = find_next_bit(&mask, 32, j + 1)) {
+			val |= 1 << j;
+			ch -= 1;
+		}
+
+		regmap_write(map, offset, val);
+		offset += regmap_get_reg_stride(map);
+	}
+
+	/*
+	 * If we still have channel left at the end of the process, it means
+	 * the stream has more channels than we can accommodate and we should
+	 * have caught this earlier.
+	 */
+	if (WARN_ON(ch != 0)) {
+		pr_err("channel mask error\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_formatter_set_channel_masks);
+
+static int axg_tdm_formatter_enable(struct axg_tdm_formatter *formatter)
+{
+	struct axg_tdm_stream *ts = formatter->stream;
+	bool invert = formatter->drv->invert_sclk;
+	int ret;
+
+	/* Do nothing if the formatter is already enabled */
+	if (formatter->enabled)
+		return 0;
+
+	/*
+	 * If sclk is inverted, invert it back and provide the inversion
+	 * required by the formatter
+	 */
+	invert ^= axg_tdm_sclk_invert(ts->iface->fmt);
+	ret = clk_set_phase(formatter->sclk, invert ? 180 : 0);
+	if (ret)
+		return ret;
+
+	/* Setup the stream parameter in the formatter */
+	ret = formatter->drv->ops->prepare(formatter->map, formatter->stream);
+	if (ret)
+		return ret;
+
+	/* Enable the signal clocks feeding the formatter */
+	ret = clk_prepare_enable(formatter->sclk);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(formatter->lrclk);
+	if (ret) {
+		clk_disable_unprepare(formatter->sclk);
+		return ret;
+	}
+
+	/* Finally, actually enable the formatter */
+	formatter->drv->ops->enable(formatter->map);
+	formatter->enabled = true;
+
+	return 0;
+}
+
+static void axg_tdm_formatter_disable(struct axg_tdm_formatter *formatter)
+{
+	/* Do nothing if the formatter is already disabled */
+	if (!formatter->enabled)
+		return;
+
+	formatter->drv->ops->disable(formatter->map);
+	clk_disable_unprepare(formatter->lrclk);
+	clk_disable_unprepare(formatter->sclk);
+	formatter->enabled = false;
+}
+
+static int axg_tdm_formatter_attach(struct axg_tdm_formatter *formatter)
+{
+	struct axg_tdm_stream *ts = formatter->stream;
+	int ret = 0;
+
+	mutex_lock(&ts->lock);
+
+	/* Catch up if the stream is already running when we attach */
+	if (ts->ready) {
+		ret = axg_tdm_formatter_enable(formatter);
+		if (ret) {
+			pr_err("failed to enable formatter\n");
+			goto out;
+		}
+	}
+
+	list_add_tail(&formatter->list, &ts->formatter_list);
+out:
+	mutex_unlock(&ts->lock);
+	return ret;
+}
+
+static void axg_tdm_formatter_dettach(struct axg_tdm_formatter *formatter)
+{
+	struct axg_tdm_stream *ts = formatter->stream;
+
+	mutex_lock(&ts->lock);
+	list_del(&formatter->list);
+	mutex_unlock(&ts->lock);
+
+	axg_tdm_formatter_disable(formatter);
+}
+
+static int axg_tdm_formatter_power_up(struct axg_tdm_formatter *formatter,
+				      struct snd_soc_dapm_widget *w)
+{
+	struct axg_tdm_stream *ts = formatter->drv->ops->get_stream(w);
+	int ret;
+
+	/*
+	 * If we don't get a stream at this stage, it would mean that the
+	 * widget is powering up but is not attached to any backend DAI.
+	 * It should not happen, ever !
+	 */
+	if (WARN_ON(!ts))
+		return -ENODEV;
+
+	/* Clock our device */
+	ret = clk_prepare_enable(formatter->pclk);
+	if (ret)
+		return ret;
+
+	/* Reparent the bit clock to the TDM interface */
+	ret = clk_set_parent(formatter->sclk_sel, ts->iface->sclk);
+	if (ret)
+		goto disable_pclk;
+
+	/* Reparent the sample clock to the TDM interface */
+	ret = clk_set_parent(formatter->lrclk_sel, ts->iface->lrclk);
+	if (ret)
+		goto disable_pclk;
+
+	formatter->stream = ts;
+	ret = axg_tdm_formatter_attach(formatter);
+	if (ret)
+		goto disable_pclk;
+
+	return 0;
+
+disable_pclk:
+	clk_disable_unprepare(formatter->pclk);
+	return ret;
+}
+
+static void axg_tdm_formatter_power_down(struct axg_tdm_formatter *formatter)
+{
+	axg_tdm_formatter_dettach(formatter);
+	clk_disable_unprepare(formatter->pclk);
+	formatter->stream = NULL;
+}
+
+int axg_tdm_formatter_event(struct snd_soc_dapm_widget *w,
+			    struct snd_kcontrol *control,
+			    int event)
+{
+	struct snd_soc_component *c = snd_soc_dapm_to_component(w->dapm);
+	struct axg_tdm_formatter *formatter = snd_soc_component_get_drvdata(c);
+	int ret = 0;
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		ret = axg_tdm_formatter_power_up(formatter, w);
+		break;
+
+	case SND_SOC_DAPM_PRE_PMD:
+		axg_tdm_formatter_power_down(formatter);
+		break;
+
+	default:
+		dev_err(c->dev, "Unexpected event %d\n", event);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_formatter_event);
+
+int axg_tdm_formatter_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct axg_tdm_formatter_driver *drv;
+	struct axg_tdm_formatter *formatter;
+	struct resource *res;
+	void __iomem *regs;
+	int ret;
+
+	drv = of_device_get_match_data(dev);
+	if (!drv) {
+		dev_err(dev, "failed to match device\n");
+		return -ENODEV;
+	}
+
+	formatter = devm_kzalloc(dev, sizeof(*formatter), GFP_KERNEL);
+	if (!formatter)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, formatter);
+	formatter->drv = drv;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	formatter->map = devm_regmap_init_mmio(dev, regs, drv->regmap_cfg);
+	if (IS_ERR(formatter->map)) {
+		dev_err(dev, "failed to init regmap: %ld\n",
+			PTR_ERR(formatter->map));
+		return PTR_ERR(formatter->map);
+	}
+
+	/* Peripharal clock */
+	formatter->pclk = devm_clk_get(dev, "pclk");
+	if (IS_ERR(formatter->pclk)) {
+		ret = PTR_ERR(formatter->pclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get pclk: %d\n", ret);
+		return ret;
+	}
+
+	/* Formatter bit clock */
+	formatter->sclk = devm_clk_get(dev, "sclk");
+	if (IS_ERR(formatter->sclk)) {
+		ret = PTR_ERR(formatter->sclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get sclk: %d\n", ret);
+		return ret;
+	}
+
+	/* Formatter sample clock */
+	formatter->lrclk = devm_clk_get(dev, "lrclk");
+	if (IS_ERR(formatter->lrclk)) {
+		ret = PTR_ERR(formatter->lrclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get lrclk: %d\n", ret);
+		return ret;
+	}
+
+	/* Formatter bit clock input multiplexer */
+	formatter->sclk_sel = devm_clk_get(dev, "sclk_sel");
+	if (IS_ERR(formatter->sclk_sel)) {
+		ret = PTR_ERR(formatter->sclk_sel);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get sclk_sel: %d\n", ret);
+		return ret;
+	}
+
+	/* Formatter sample clock input multiplexer */
+	formatter->lrclk_sel = devm_clk_get(dev, "lrclk_sel");
+	if (IS_ERR(formatter->lrclk_sel)) {
+		ret = PTR_ERR(formatter->lrclk_sel);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get lrclk_sel: %d\n", ret);
+		return ret;
+	}
+
+	return devm_snd_soc_register_component(dev, drv->component_drv,
+					       NULL, 0);
+}
+EXPORT_SYMBOL_GPL(axg_tdm_formatter_probe);
+
+int axg_tdm_stream_start(struct axg_tdm_stream *ts)
+{
+	struct axg_tdm_formatter *formatter;
+	int ret = 0;
+
+	mutex_lock(&ts->lock);
+	ts->ready = true;
+
+	/* Start all the formatters attached to the stream */
+	list_for_each_entry(formatter, &ts->formatter_list, list) {
+		ret = axg_tdm_formatter_enable(formatter);
+		if (ret) {
+			pr_err("failed to start tdm stream\n");
+			goto out;
+		}
+	}
+
+out:
+	mutex_unlock(&ts->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_stream_start);
+
+void axg_tdm_stream_stop(struct axg_tdm_stream *ts)
+{
+	struct axg_tdm_formatter *formatter;
+
+	mutex_lock(&ts->lock);
+	ts->ready = false;
+
+	/* Stop all the formatters attached to the stream */
+	list_for_each_entry(formatter, &ts->formatter_list, list) {
+		axg_tdm_formatter_disable(formatter);
+	}
+
+	mutex_unlock(&ts->lock);
+}
+EXPORT_SYMBOL_GPL(axg_tdm_stream_stop);
+
+struct axg_tdm_stream *axg_tdm_stream_alloc(struct axg_tdm_iface *iface)
+{
+	struct axg_tdm_stream *ts;
+
+	ts = kzalloc(sizeof(*ts), GFP_KERNEL);
+	if (ts) {
+		INIT_LIST_HEAD(&ts->formatter_list);
+		mutex_init(&ts->lock);
+		ts->iface = iface;
+	}
+
+	return ts;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_stream_alloc);
+
+void axg_tdm_stream_free(struct axg_tdm_stream *ts)
+{
+	/*
+	 * If the list is not empty, it would mean that one of the formatter
+	 * widget is still powered and attached to the interface while we
+	 * we are removing the TDM DAI. It should not be possible
+	 */
+	WARN_ON(!list_empty(&ts->formatter_list));
+	mutex_destroy(&ts->lock);
+	kfree(ts);
+}
+EXPORT_SYMBOL_GPL(axg_tdm_stream_free);
+
+MODULE_DESCRIPTION("Amlogic AXG TDM formatter driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-tdm-formatter.h b/sound/soc/meson/axg-tdm-formatter.h
new file mode 100644
index 000000000000..cf947caf3cb1
--- /dev/null
+++ b/sound/soc/meson/axg-tdm-formatter.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT)
+ *
+ * Copyright (c) 2018 Baylibre SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef _MESON_AXG_TDM_FORMATTER_H
+#define _MESON_AXG_TDM_FORMATTER_H
+
+#include "axg-tdm.h"
+
+struct platform_device;
+struct regmap;
+struct snd_soc_dapm_widget;
+struct snd_kcontrol;
+
+struct axg_tdm_formatter_ops {
+	struct axg_tdm_stream *(*get_stream)(struct snd_soc_dapm_widget *w);
+	void (*enable)(struct regmap *map);
+	void (*disable)(struct regmap *map);
+	int (*prepare)(struct regmap *map, struct axg_tdm_stream *ts);
+};
+
+struct axg_tdm_formatter_driver {
+	const struct snd_soc_component_driver *component_drv;
+	const struct regmap_config *regmap_cfg;
+	const struct axg_tdm_formatter_ops *ops;
+	bool invert_sclk;
+};
+
+int axg_tdm_formatter_set_channel_masks(struct regmap *map,
+					struct axg_tdm_stream *ts,
+					unsigned int offset);
+int axg_tdm_formatter_event(struct snd_soc_dapm_widget *w,
+			    struct snd_kcontrol *control,
+			    int event);
+int axg_tdm_formatter_probe(struct platform_device *pdev);
+
+#endif /* _MESON_AXG_TDM_FORMATTER_H */
diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c
new file mode 100644
index 000000000000..7b8baf46d968
--- /dev/null
+++ b/sound/soc/meson/axg-tdm-interface.c
@@ -0,0 +1,542 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-tdm.h"
+
+enum {
+	TDM_IFACE_PAD,
+	TDM_IFACE_LOOPBACK,
+};
+
+static unsigned int axg_tdm_slots_total(u32 *mask)
+{
+	unsigned int slots = 0;
+	int i;
+
+	if (!mask)
+		return 0;
+
+	/* Count the total number of slots provided by all 4 lanes */
+	for (i = 0; i < AXG_TDM_NUM_LANES; i++)
+		slots += hweight32(mask[i]);
+
+	return slots;
+}
+
+int axg_tdm_set_tdm_slots(struct snd_soc_dai *dai, u32 *tx_mask,
+			  u32 *rx_mask, unsigned int slots,
+			  unsigned int slot_width)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	struct axg_tdm_stream *tx = (struct axg_tdm_stream *)
+		dai->playback_dma_data;
+	struct axg_tdm_stream *rx = (struct axg_tdm_stream *)
+		dai->capture_dma_data;
+	unsigned int tx_slots, rx_slots;
+
+	tx_slots = axg_tdm_slots_total(tx_mask);
+	rx_slots = axg_tdm_slots_total(rx_mask);
+
+	/* We should at least have a slot for a valid interface */
+	if (!tx_slots && !rx_slots) {
+		dev_err(dai->dev, "interface has no slot\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Amend the dai driver channel number and let dpcm channel merge do
+	 * its job
+	 */
+	if (tx) {
+		tx->mask = tx_mask;
+		dai->driver->playback.channels_max = tx_slots;
+	}
+
+	if (rx) {
+		rx->mask = rx_mask;
+		dai->driver->capture.channels_max = rx_slots;
+	}
+
+	iface->slots = slots;
+
+	switch (slot_width) {
+	case 0:
+		/* defaults width to 32 if not provided */
+		iface->slot_width = 32;
+		break;
+	case 8:
+	case 16:
+	case 24:
+	case 32:
+		iface->slot_width = slot_width;
+		break;
+	default:
+		dev_err(dai->dev, "unsupported slot width: %d\n", slot_width);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_set_tdm_slots);
+
+static int axg_tdm_iface_set_sysclk(struct snd_soc_dai *dai, int clk_id,
+				    unsigned int freq, int dir)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	int ret = -ENOTSUPP;
+
+	if (dir == SND_SOC_CLOCK_OUT && clk_id == 0) {
+		if (!iface->mclk) {
+			dev_warn(dai->dev, "master clock not provided\n");
+		} else {
+			ret = clk_set_rate(iface->mclk, freq);
+			if (!ret)
+				iface->mclk_rate = freq;
+		}
+	}
+
+	return ret;
+}
+
+static int axg_tdm_iface_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+
+	/* These modes are not supported */
+	if (fmt & (SND_SOC_DAIFMT_CBS_CFM | SND_SOC_DAIFMT_CBM_CFS)) {
+		dev_err(dai->dev, "only CBS_CFS and CBM_CFM are supported\n");
+		return -EINVAL;
+	}
+
+	/* If the TDM interface is the clock master, it requires mclk */
+	if (!iface->mclk && (fmt & SND_SOC_DAIFMT_CBS_CFS)) {
+		dev_err(dai->dev, "cpu clock master: mclk missing\n");
+		return -ENODEV;
+	}
+
+	iface->fmt = fmt;
+	return 0;
+}
+
+static int axg_tdm_iface_startup(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	struct axg_tdm_stream *ts =
+		snd_soc_dai_get_dma_data(dai, substream);
+	int ret;
+
+	if (!axg_tdm_slots_total(ts->mask)) {
+		dev_err(dai->dev, "interface has not slots\n");
+		return -EINVAL;
+	}
+
+	/* Apply component wide rate symmetry */
+	if (dai->component->active) {
+		ret = snd_pcm_hw_constraint_single(substream->runtime,
+						   SNDRV_PCM_HW_PARAM_RATE,
+						   iface->rate);
+		if (ret < 0) {
+			dev_err(dai->dev,
+				"can't set iface rate constraint\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int axg_tdm_iface_set_stream(struct snd_pcm_substream *substream,
+				    struct snd_pcm_hw_params *params,
+				    struct snd_soc_dai *dai)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream);
+	unsigned int channels = params_channels(params);
+	unsigned int width = params_width(params);
+
+	/* Save rate and sample_bits for component symmetry */
+	iface->rate = params_rate(params);
+
+	/* Make sure this interface can cope with the stream */
+	if (axg_tdm_slots_total(ts->mask) < channels) {
+		dev_err(dai->dev, "not enough slots for channels\n");
+		return -EINVAL;
+	}
+
+	if (iface->slot_width < width) {
+		dev_err(dai->dev, "incompatible slots width for stream\n");
+		return -EINVAL;
+	}
+
+	/* Save the parameter for tdmout/tdmin widgets */
+	ts->physical_width = params_physical_width(params);
+	ts->width = params_width(params);
+	ts->channels = params_channels(params);
+
+	return 0;
+}
+
+static int axg_tdm_iface_set_lrclk(struct snd_soc_dai *dai,
+				   struct snd_pcm_hw_params *params)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	unsigned int ratio_num;
+	int ret;
+
+	ret = clk_set_rate(iface->lrclk, params_rate(params));
+	if (ret) {
+		dev_err(dai->dev, "setting sample clock failed: %d\n", ret);
+		return ret;
+	}
+
+	switch (iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+		/* 50% duty cycle ratio */
+		ratio_num = 1;
+		break;
+
+	case SND_SOC_DAIFMT_DSP_A:
+	case SND_SOC_DAIFMT_DSP_B:
+		/*
+		 * A zero duty cycle ratio will result in setting the mininum
+		 * ratio possible which, for this clock, is 1 cycle of the
+		 * parent bclk clock high and the rest low, This is exactly
+		 * what we want here.
+		 */
+		ratio_num = 0;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	ret = clk_set_duty_cycle(iface->lrclk, ratio_num, 2);
+	if (ret) {
+		dev_err(dai->dev,
+			"setting sample clock duty cycle failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Set sample clock inversion */
+	ret = clk_set_phase(iface->lrclk,
+			    axg_tdm_lrclk_invert(iface->fmt) ? 180 : 0);
+	if (ret) {
+		dev_err(dai->dev,
+			"setting sample clock phase failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int axg_tdm_iface_set_sclk(struct snd_soc_dai *dai,
+				  struct snd_pcm_hw_params *params)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	unsigned long srate;
+	int ret;
+
+	srate = iface->slots * iface->slot_width * params_rate(params);
+
+	if (!iface->mclk_rate) {
+		/* If no specific mclk is requested, default to bit clock * 4 */
+		clk_set_rate(iface->mclk, 4 * srate);
+	} else {
+		/* Check if we can actually get the bit clock from mclk */
+		if (iface->mclk_rate % srate) {
+			dev_err(dai->dev,
+				"can't derive sclk %lu from mclk %lu\n",
+				srate, iface->mclk_rate);
+			return -EINVAL;
+		}
+	}
+
+	ret = clk_set_rate(iface->sclk, srate);
+	if (ret) {
+		dev_err(dai->dev, "setting bit clock failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Set the bit clock inversion */
+	ret = clk_set_phase(iface->sclk,
+			    axg_tdm_sclk_invert(iface->fmt) ? 0 : 180);
+	if (ret) {
+		dev_err(dai->dev, "setting bit clock phase failed: %d\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int axg_tdm_iface_hw_params(struct snd_pcm_substream *substream,
+				   struct snd_pcm_hw_params *params,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	int ret;
+
+	switch (iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+		if (iface->slots > 2) {
+			dev_err(dai->dev, "bad slot number for format: %d\n",
+				iface->slots);
+			return -EINVAL;
+		}
+		break;
+
+	case SND_SOC_DAI_FORMAT_DSP_A:
+	case SND_SOC_DAI_FORMAT_DSP_B:
+		break;
+
+	default:
+		dev_err(dai->dev, "unsupported dai format\n");
+		return -EINVAL;
+	}
+
+	ret = axg_tdm_iface_set_stream(substream, params, dai);
+	if (ret)
+		return ret;
+
+	if (iface->fmt & SND_SOC_DAIFMT_CBS_CFS) {
+		ret = axg_tdm_iface_set_sclk(dai, params);
+		if (ret)
+			return ret;
+
+		ret = axg_tdm_iface_set_lrclk(dai, params);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int axg_tdm_iface_hw_free(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream);
+
+	/* Stop all attached formatters */
+	axg_tdm_stream_stop(ts);
+
+	return 0;
+}
+
+static int axg_tdm_iface_prepare(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream);
+
+	/* Force all attached formatters to update */
+	return axg_tdm_stream_reset(ts);
+}
+
+static int axg_tdm_iface_remove_dai(struct snd_soc_dai *dai)
+{
+	if (dai->capture_dma_data)
+		axg_tdm_stream_free(dai->capture_dma_data);
+
+	if (dai->playback_dma_data)
+		axg_tdm_stream_free(dai->playback_dma_data);
+
+	return 0;
+}
+
+static int axg_tdm_iface_probe_dai(struct snd_soc_dai *dai)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+
+	if (dai->capture_widget) {
+		dai->capture_dma_data = axg_tdm_stream_alloc(iface);
+		if (!dai->capture_dma_data)
+			return -ENOMEM;
+	}
+
+	if (dai->playback_widget) {
+		dai->playback_dma_data = axg_tdm_stream_alloc(iface);
+		if (!dai->playback_dma_data) {
+			axg_tdm_iface_remove_dai(dai);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops axg_tdm_iface_ops = {
+	.set_sysclk	= axg_tdm_iface_set_sysclk,
+	.set_fmt	= axg_tdm_iface_set_fmt,
+	.startup	= axg_tdm_iface_startup,
+	.hw_params	= axg_tdm_iface_hw_params,
+	.prepare	= axg_tdm_iface_prepare,
+	.hw_free	= axg_tdm_iface_hw_free,
+};
+
+/* TDM Backend DAIs */
+static const struct snd_soc_dai_driver axg_tdm_iface_dai_drv[] = {
+	[TDM_IFACE_PAD] = {
+		.name = "TDM Pad",
+		.playback = {
+			.stream_name	= "Playback",
+			.channels_min	= 1,
+			.channels_max	= AXG_TDM_CHANNEL_MAX,
+			.rates		= AXG_TDM_RATES,
+			.formats	= AXG_TDM_FORMATS,
+		},
+		.capture = {
+			.stream_name	= "Capture",
+			.channels_min	= 1,
+			.channels_max	= AXG_TDM_CHANNEL_MAX,
+			.rates		= AXG_TDM_RATES,
+			.formats	= AXG_TDM_FORMATS,
+		},
+		.id = TDM_IFACE_PAD,
+		.ops = &axg_tdm_iface_ops,
+		.probe = axg_tdm_iface_probe_dai,
+		.remove = axg_tdm_iface_remove_dai,
+	},
+	[TDM_IFACE_LOOPBACK] = {
+		.name = "TDM Loopback",
+		.capture = {
+			.stream_name	= "Loopback",
+			.channels_min	= 1,
+			.channels_max	= AXG_TDM_CHANNEL_MAX,
+			.rates		= AXG_TDM_RATES,
+			.formats	= AXG_TDM_FORMATS,
+		},
+		.id = TDM_IFACE_LOOPBACK,
+		.ops = &axg_tdm_iface_ops,
+		.probe = axg_tdm_iface_probe_dai,
+		.remove = axg_tdm_iface_remove_dai,
+	},
+};
+
+static int axg_tdm_iface_set_bias_level(struct snd_soc_component *component,
+					enum snd_soc_bias_level level)
+{
+	struct axg_tdm_iface *iface = snd_soc_component_get_drvdata(component);
+	enum snd_soc_bias_level now =
+		snd_soc_component_get_bias_level(component);
+	int ret = 0;
+
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		if (now == SND_SOC_BIAS_STANDBY)
+			ret = clk_prepare_enable(iface->mclk);
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		if (now == SND_SOC_BIAS_PREPARE)
+			clk_disable_unprepare(iface->mclk);
+		break;
+
+	case SND_SOC_BIAS_OFF:
+	case SND_SOC_BIAS_ON:
+		break;
+	}
+
+	return ret;
+}
+
+static const struct snd_soc_component_driver axg_tdm_iface_component_drv = {
+	.set_bias_level	= axg_tdm_iface_set_bias_level,
+};
+
+static const struct of_device_id axg_tdm_iface_of_match[] = {
+	{ .compatible = "amlogic,axg-tdm-iface", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, axg_tdm_iface_of_match);
+
+static int axg_tdm_iface_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct snd_soc_dai_driver *dai_drv;
+	struct axg_tdm_iface *iface;
+	int ret, i;
+
+	iface = devm_kzalloc(dev, sizeof(*iface), GFP_KERNEL);
+	if (!iface)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, iface);
+
+	/*
+	 * Duplicate dai driver: depending on the slot masks configuration
+	 * We'll change the number of channel provided by DAI stream, so dpcm
+	 * channel merge can be done properly
+	 */
+	dai_drv = devm_kcalloc(dev, ARRAY_SIZE(axg_tdm_iface_dai_drv),
+			       sizeof(*dai_drv), GFP_KERNEL);
+	if (!dai_drv)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(axg_tdm_iface_dai_drv); i++)
+		memcpy(&dai_drv[i], &axg_tdm_iface_dai_drv[i],
+		       sizeof(*dai_drv));
+
+	/* Bit clock provided on the pad */
+	iface->sclk = devm_clk_get(dev, "sclk");
+	if (IS_ERR(iface->sclk)) {
+		ret = PTR_ERR(iface->sclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get sclk: %d\n", ret);
+		return ret;
+	}
+
+	/* Sample clock provided on the pad */
+	iface->lrclk = devm_clk_get(dev, "lrclk");
+	if (IS_ERR(iface->lrclk)) {
+		ret = PTR_ERR(iface->lrclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get lrclk: %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * mclk maybe be missing when the cpu dai is in slave mode and
+	 * the codec does not require it to provide a master clock.
+	 * At this point, ignore the error if mclk is missing. We'll
+	 * throw an error if the cpu dai is master and mclk is missing
+	 */
+	iface->mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(iface->mclk)) {
+		ret = PTR_ERR(iface->mclk);
+		if (ret == -ENOENT) {
+			iface->mclk = NULL;
+		} else {
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "failed to get mclk: %d\n", ret);
+			return ret;
+		}
+	}
+
+	return devm_snd_soc_register_component(dev,
+					&axg_tdm_iface_component_drv, dai_drv,
+					ARRAY_SIZE(axg_tdm_iface_dai_drv));
+}
+
+static struct platform_driver axg_tdm_iface_pdrv = {
+	.probe = axg_tdm_iface_probe,
+	.driver = {
+		.name = "axg-tdm-iface",
+		.of_match_table = axg_tdm_iface_of_match,
+	},
+};
+module_platform_driver(axg_tdm_iface_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG TDM interface driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-tdm.h b/sound/soc/meson/axg-tdm.h
new file mode 100644
index 000000000000..e578b6f40a07
--- /dev/null
+++ b/sound/soc/meson/axg-tdm.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT)
+ *
+ * Copyright (c) 2018 Baylibre SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef _MESON_AXG_TDM_H
+#define _MESON_AXG_TDM_H
+
+#include <linux/clk.h>
+#include <linux/regmap.h>
+#include <sound/pcm.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#define AXG_TDM_NUM_LANES	4
+#define AXG_TDM_CHANNEL_MAX	128
+#define AXG_TDM_RATES		(SNDRV_PCM_RATE_5512 |		\
+				 SNDRV_PCM_RATE_8000_192000)
+#define AXG_TDM_FORMATS		(SNDRV_PCM_FMTBIT_S8 |		\
+				 SNDRV_PCM_FMTBIT_S16_LE |	\
+				 SNDRV_PCM_FMTBIT_S20_LE |	\
+				 SNDRV_PCM_FMTBIT_S24_LE |	\
+				 SNDRV_PCM_FMTBIT_S32_LE)
+
+struct axg_tdm_iface {
+	struct clk *sclk;
+	struct clk *lrclk;
+	struct clk *mclk;
+	unsigned long mclk_rate;
+
+	/* format is common to all the DAIs of the iface */
+	unsigned int fmt;
+	unsigned int slots;
+	unsigned int slot_width;
+
+	/* For component wide symmetry */
+	int rate;
+};
+
+static inline bool axg_tdm_lrclk_invert(unsigned int fmt)
+{
+	return (fmt & SND_SOC_DAIFMT_I2S) ^
+		!!(fmt & (SND_SOC_DAIFMT_IB_IF | SND_SOC_DAIFMT_NB_IF));
+}
+
+static inline bool axg_tdm_sclk_invert(unsigned int fmt)
+{
+	return fmt & (SND_SOC_DAIFMT_IB_IF | SND_SOC_DAIFMT_IB_NF);
+}
+
+struct axg_tdm_stream {
+	struct axg_tdm_iface *iface;
+	struct list_head formatter_list;
+	struct mutex lock;
+	unsigned int channels;
+	unsigned int width;
+	unsigned int physical_width;
+	u32 *mask;
+	bool ready;
+};
+
+struct axg_tdm_stream *axg_tdm_stream_alloc(struct axg_tdm_iface *iface);
+void axg_tdm_stream_free(struct axg_tdm_stream *ts);
+int axg_tdm_stream_start(struct axg_tdm_stream *ts);
+void axg_tdm_stream_stop(struct axg_tdm_stream *ts);
+
+static inline int axg_tdm_stream_reset(struct axg_tdm_stream *ts)
+{
+	axg_tdm_stream_stop(ts);
+	return axg_tdm_stream_start(ts);
+}
+
+int axg_tdm_set_tdm_slots(struct snd_soc_dai *dai, u32 *tx_mask,
+			  u32 *rx_mask, unsigned int slots,
+			  unsigned int slot_width);
+
+#endif /* _MESON_AXG_TDM_H */
diff --git a/sound/soc/meson/axg-tdmin.c b/sound/soc/meson/axg-tdmin.c
new file mode 100644
index 000000000000..bbac44c81688
--- /dev/null
+++ b/sound/soc/meson/axg-tdmin.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-tdm-formatter.h"
+
+#define TDMIN_CTRL			0x00
+#define  TDMIN_CTRL_ENABLE		BIT(31)
+#define  TDMIN_CTRL_I2S_MODE		BIT(30)
+#define  TDMIN_CTRL_RST_OUT		BIT(29)
+#define  TDMIN_CTRL_RST_IN		BIT(28)
+#define  TDMIN_CTRL_WS_INV		BIT(25)
+#define  TDMIN_CTRL_SEL_SHIFT		20
+#define  TDMIN_CTRL_IN_BIT_SKEW_MASK	GENMASK(18, 16)
+#define  TDMIN_CTRL_IN_BIT_SKEW(x)	((x) << 16)
+#define  TDMIN_CTRL_LSB_FIRST		BIT(5)
+#define  TDMIN_CTRL_BITNUM_MASK	GENMASK(4, 0)
+#define  TDMIN_CTRL_BITNUM(x)		((x) << 0)
+#define TDMIN_SWAP			0x04
+#define TDMIN_MASK0			0x08
+#define TDMIN_MASK1			0x0c
+#define TDMIN_MASK2			0x10
+#define TDMIN_MASK3			0x14
+#define TDMIN_STAT			0x18
+#define TDMIN_MUTE_VAL			0x1c
+#define TDMIN_MUTE0			0x20
+#define TDMIN_MUTE1			0x24
+#define TDMIN_MUTE2			0x28
+#define TDMIN_MUTE3			0x2c
+
+static const struct regmap_config axg_tdmin_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= TDMIN_MUTE3,
+};
+
+static const char * const axg_tdmin_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2", "IN 3", "IN 4", "IN 5",
+};
+
+/* Change to special mux control to reset dapm */
+static SOC_ENUM_SINGLE_DECL(axg_tdmin_sel_enum, TDMIN_CTRL,
+			    TDMIN_CTRL_SEL_SHIFT, axg_tdmin_sel_texts);
+
+static const struct snd_kcontrol_new axg_tdmin_in_mux =
+	SOC_DAPM_ENUM("Input Source", axg_tdmin_sel_enum);
+
+static struct snd_soc_dai *
+axg_tdmin_get_be(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dapm_path *p = NULL;
+	struct snd_soc_dai *be;
+
+	snd_soc_dapm_widget_for_each_source_path(w, p) {
+		if (!p->connect)
+			continue;
+
+		if (p->source->id == snd_soc_dapm_dai_out)
+			return (struct snd_soc_dai *)p->source->priv;
+
+		be = axg_tdmin_get_be(p->source);
+		if (be)
+			return be;
+	}
+
+	return NULL;
+}
+
+static struct axg_tdm_stream *
+axg_tdmin_get_tdm_stream(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dai *be = axg_tdmin_get_be(w);
+
+	if (!be)
+		return NULL;
+
+	return be->capture_dma_data;
+}
+
+static void axg_tdmin_enable(struct regmap *map)
+{
+	/* Apply both reset */
+	regmap_update_bits(map, TDMIN_CTRL,
+			   TDMIN_CTRL_RST_OUT | TDMIN_CTRL_RST_IN, 0);
+
+	/* Clear out reset before in reset */
+	regmap_update_bits(map, TDMIN_CTRL,
+			   TDMIN_CTRL_RST_OUT, TDMIN_CTRL_RST_OUT);
+	regmap_update_bits(map, TDMIN_CTRL,
+			   TDMIN_CTRL_RST_IN,  TDMIN_CTRL_RST_IN);
+
+	/* Actually enable tdmin */
+	regmap_update_bits(map, TDMIN_CTRL,
+			   TDMIN_CTRL_ENABLE, TDMIN_CTRL_ENABLE);
+}
+
+static void axg_tdmin_disable(struct regmap *map)
+{
+	regmap_update_bits(map, TDMIN_CTRL, TDMIN_CTRL_ENABLE, 0);
+}
+
+static int axg_tdmin_prepare(struct regmap *map, struct axg_tdm_stream *ts)
+{
+	unsigned int val = 0;
+
+	/* Set stream skew */
+	switch (ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_DSP_A:
+		val |= TDMIN_CTRL_IN_BIT_SKEW(3);
+		break;
+
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+	case SND_SOC_DAIFMT_DSP_B:
+		val = TDMIN_CTRL_IN_BIT_SKEW(2);
+		break;
+
+	default:
+		pr_err("Unsupported format: %u\n",
+		       ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK);
+		return -EINVAL;
+	}
+
+	/* Set stream format mode */
+	switch (ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+		val |= TDMIN_CTRL_I2S_MODE;
+		break;
+	}
+
+	/* If the sample clock is inverted, invert it back for the formatter */
+	if (axg_tdm_lrclk_invert(ts->iface->fmt))
+		val |= TDMIN_CTRL_WS_INV;
+
+	/* Set the slot width */
+	val |= TDMIN_CTRL_BITNUM(ts->iface->slot_width - 1);
+
+	/*
+	 * The following also reset LSB_FIRST which result in the formatter
+	 * placing the first bit received at bit 31
+	 */
+	regmap_update_bits(map, TDMIN_CTRL,
+			   (TDMIN_CTRL_IN_BIT_SKEW_MASK | TDMIN_CTRL_WS_INV |
+			    TDMIN_CTRL_I2S_MODE | TDMIN_CTRL_LSB_FIRST |
+			    TDMIN_CTRL_BITNUM_MASK), val);
+
+	/* Set static swap mask configuration */
+	regmap_write(map, TDMIN_SWAP, 0x76543210);
+
+	return axg_tdm_formatter_set_channel_masks(map, ts, TDMIN_MASK0);
+}
+
+static const struct snd_soc_dapm_widget axg_tdmin_dapm_widgets[] = {
+	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 3", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 4", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 5", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &axg_tdmin_in_mux),
+	SND_SOC_DAPM_PGA_E("DEC", SND_SOC_NOPM, 0, 0, NULL, 0,
+			   axg_tdm_formatter_event,
+			   (SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD)),
+	SND_SOC_DAPM_AIF_OUT("OUT", NULL, 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route axg_tdmin_dapm_routes[] = {
+	{ "SRC SEL", "IN 0", "IN 0" },
+	{ "SRC SEL", "IN 1", "IN 1" },
+	{ "SRC SEL", "IN 2", "IN 2" },
+	{ "SRC SEL", "IN 3", "IN 3" },
+	{ "SRC SEL", "IN 4", "IN 4" },
+	{ "SRC SEL", "IN 5", "IN 5" },
+	{ "DEC", NULL, "SRC SEL" },
+	{ "OUT", NULL, "DEC" },
+};
+
+static const struct snd_soc_component_driver axg_tdmin_component_drv = {
+	.dapm_widgets		= axg_tdmin_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_tdmin_dapm_widgets),
+	.dapm_routes		= axg_tdmin_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_tdmin_dapm_routes),
+};
+
+static const struct axg_tdm_formatter_ops axg_tdmin_ops = {
+	.get_stream	= axg_tdmin_get_tdm_stream,
+	.prepare	= axg_tdmin_prepare,
+	.enable		= axg_tdmin_enable,
+	.disable	= axg_tdmin_disable,
+};
+
+static const struct axg_tdm_formatter_driver axg_tdmin_drv = {
+	.component_drv	= &axg_tdmin_component_drv,
+	.regmap_cfg	= &axg_tdmin_regmap_cfg,
+	.ops		= &axg_tdmin_ops,
+	.invert_sclk	= false,
+};
+
+static const struct of_device_id axg_tdmin_of_match[] = {
+	{
+		.compatible = "amlogic,axg-tdmin",
+		.data = &axg_tdmin_drv,
+	}, {}
+};
+MODULE_DEVICE_TABLE(of, axg_tdmin_of_match);
+
+static struct platform_driver axg_tdmin_pdrv = {
+	.probe = axg_tdm_formatter_probe,
+	.driver = {
+		.name = "axg-tdmin",
+		.of_match_table = axg_tdmin_of_match,
+	},
+};
+module_platform_driver(axg_tdmin_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG TDM input formatter driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-tdmout.c b/sound/soc/meson/axg-tdmout.c
new file mode 100644
index 000000000000..f73368ee1088
--- /dev/null
+++ b/sound/soc/meson/axg-tdmout.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-tdm-formatter.h"
+
+#define TDMOUT_CTRL0			0x00
+#define  TDMOUT_CTRL0_BITNUM_MASK	GENMASK(4, 0)
+#define  TDMOUT_CTRL0_BITNUM(x)		((x) << 0)
+#define  TDMOUT_CTRL0_SLOTNUM_MASK	GENMASK(9, 5)
+#define  TDMOUT_CTRL0_SLOTNUM(x)	((x) << 5)
+#define  TDMOUT_CTRL0_INIT_BITNUM_MASK	GENMASK(19, 15)
+#define  TDMOUT_CTRL0_INIT_BITNUM(x)	((x) << 15)
+#define  TDMOUT_CTRL0_ENABLE		BIT(31)
+#define  TDMOUT_CTRL0_RST_OUT		BIT(29)
+#define  TDMOUT_CTRL0_RST_IN		BIT(28)
+#define TDMOUT_CTRL1			0x04
+#define  TDMOUT_CTRL1_TYPE_MASK		GENMASK(6, 4)
+#define  TDMOUT_CTRL1_TYPE(x)		((x) << 4)
+#define  TDMOUT_CTRL1_MSB_POS_MASK	GENMASK(12, 8)
+#define  TDMOUT_CTRL1_MSB_POS(x)	((x) << 8)
+#define  TDMOUT_CTRL1_SEL_SHIFT		24
+#define  TDMOUT_CTRL1_GAIN_EN		26
+#define  TDMOUT_CTRL1_WS_INV		BIT(28)
+#define TDMOUT_SWAP			0x08
+#define TDMOUT_MASK0			0x0c
+#define TDMOUT_MASK1			0x10
+#define TDMOUT_MASK2			0x14
+#define TDMOUT_MASK3			0x18
+#define TDMOUT_STAT			0x1c
+#define TDMOUT_GAIN0			0x20
+#define TDMOUT_GAIN1			0x24
+#define TDMOUT_MUTE_VAL			0x28
+#define TDMOUT_MUTE0			0x2c
+#define TDMOUT_MUTE1			0x30
+#define TDMOUT_MUTE2			0x34
+#define TDMOUT_MUTE3			0x38
+#define TDMOUT_MASK_VAL			0x3c
+
+static const struct regmap_config axg_tdmout_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= TDMOUT_MASK_VAL,
+};
+
+static const struct snd_kcontrol_new axg_tdmout_controls[] = {
+	SOC_DOUBLE("Lane 0 Volume", TDMOUT_GAIN0,  0,  8, 255, 0),
+	SOC_DOUBLE("Lane 1 Volume", TDMOUT_GAIN0, 16, 24, 255, 0),
+	SOC_DOUBLE("Lane 2 Volume", TDMOUT_GAIN1,  0,  8, 255, 0),
+	SOC_DOUBLE("Lane 3 Volume", TDMOUT_GAIN1, 16, 24, 255, 0),
+	SOC_SINGLE("Gain Enable Switch", TDMOUT_CTRL1,
+		   TDMOUT_CTRL1_GAIN_EN, 1, 0),
+};
+
+static const char * const tdmout_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2",
+};
+
+static SOC_ENUM_SINGLE_DECL(axg_tdmout_sel_enum, TDMOUT_CTRL1,
+			    TDMOUT_CTRL1_SEL_SHIFT, tdmout_sel_texts);
+
+static const struct snd_kcontrol_new axg_tdmout_in_mux =
+	SOC_DAPM_ENUM("Input Source", axg_tdmout_sel_enum);
+
+static struct snd_soc_dai *
+axg_tdmout_get_be(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dapm_path *p = NULL;
+	struct snd_soc_dai *be;
+
+	snd_soc_dapm_widget_for_each_sink_path(w, p) {
+		if (!p->connect)
+			continue;
+
+		if (p->sink->id == snd_soc_dapm_dai_in)
+			return (struct snd_soc_dai *)p->sink->priv;
+
+		be = axg_tdmout_get_be(p->sink);
+		if (be)
+			return be;
+	}
+
+	return NULL;
+}
+
+static struct axg_tdm_stream *
+axg_tdmout_get_tdm_stream(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dai *be = axg_tdmout_get_be(w);
+
+	if (!be)
+		return NULL;
+
+	return be->playback_dma_data;
+}
+
+static void axg_tdmout_enable(struct regmap *map)
+{
+	/* Apply both reset */
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_RST_OUT | TDMOUT_CTRL0_RST_IN, 0);
+
+	/* Clear out reset before in reset */
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_RST_OUT, TDMOUT_CTRL0_RST_OUT);
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_RST_IN,  TDMOUT_CTRL0_RST_IN);
+
+	/* Actually enable tdmout */
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_ENABLE, TDMOUT_CTRL0_ENABLE);
+}
+
+static void axg_tdmout_disable(struct regmap *map)
+{
+	regmap_update_bits(map, TDMOUT_CTRL0, TDMOUT_CTRL0_ENABLE, 0);
+}
+
+static int axg_tdmout_prepare(struct regmap *map, struct axg_tdm_stream *ts)
+{
+	unsigned int val = 0;
+
+	/* Set the stream skew */
+	switch (ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_DSP_A:
+		val |= TDMOUT_CTRL0_INIT_BITNUM(1);
+		break;
+
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+	case SND_SOC_DAIFMT_DSP_B:
+		val |= TDMOUT_CTRL0_INIT_BITNUM(2);
+		break;
+
+	default:
+		pr_err("Unsupported format: %u\n",
+		       ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK);
+		return -EINVAL;
+	}
+
+	/* Set the slot width */
+	val |= TDMOUT_CTRL0_BITNUM(ts->iface->slot_width - 1);
+
+	/* Set the slot number */
+	val |= TDMOUT_CTRL0_SLOTNUM(ts->iface->slots - 1);
+
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_INIT_BITNUM_MASK |
+			   TDMOUT_CTRL0_BITNUM_MASK |
+			   TDMOUT_CTRL0_SLOTNUM_MASK, val);
+
+	/* Set the sample width */
+	val = TDMOUT_CTRL1_MSB_POS(ts->width - 1);
+
+	/* FIFO data are arranged in chunks of 64bits */
+	switch (ts->physical_width) {
+	case 8:
+		/* 8 samples of 8 bits */
+		val |= TDMOUT_CTRL1_TYPE(0);
+		break;
+	case 16:
+		/* 4 samples of 16 bits - right justified */
+		val |= TDMOUT_CTRL1_TYPE(2);
+		break;
+	case 32:
+		/* 2 samples of 32 bits - right justified */
+		val |= TDMOUT_CTRL1_TYPE(4);
+		break;
+	default:
+		pr_err("Unsupported physical width: %u\n",
+		       ts->physical_width);
+		return -EINVAL;
+	}
+
+	/* If the sample clock is inverted, invert it back for the formatter */
+	if (axg_tdm_lrclk_invert(ts->iface->fmt))
+		val |= TDMOUT_CTRL1_WS_INV;
+
+	regmap_update_bits(map, TDMOUT_CTRL1,
+			   (TDMOUT_CTRL1_TYPE_MASK | TDMOUT_CTRL1_MSB_POS_MASK |
+			    TDMOUT_CTRL1_WS_INV), val);
+
+	/* Set static swap mask configuration */
+	regmap_write(map, TDMOUT_SWAP, 0x76543210);
+
+	return axg_tdm_formatter_set_channel_masks(map, ts, TDMOUT_MASK0);
+}
+
+static const struct snd_soc_dapm_widget axg_tdmout_dapm_widgets[] = {
+	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &axg_tdmout_in_mux),
+	SND_SOC_DAPM_PGA_E("ENC", SND_SOC_NOPM, 0, 0, NULL, 0,
+			   axg_tdm_formatter_event,
+			   (SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD)),
+	SND_SOC_DAPM_AIF_OUT("OUT", NULL, 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route axg_tdmout_dapm_routes[] = {
+	{ "SRC SEL", "IN 0", "IN 0" },
+	{ "SRC SEL", "IN 1", "IN 1" },
+	{ "SRC SEL", "IN 2", "IN 2" },
+	{ "ENC", NULL, "SRC SEL" },
+	{ "OUT", NULL, "ENC" },
+};
+
+static const struct snd_soc_component_driver axg_tdmout_component_drv = {
+	.controls		= axg_tdmout_controls,
+	.num_controls		= ARRAY_SIZE(axg_tdmout_controls),
+	.dapm_widgets		= axg_tdmout_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_tdmout_dapm_widgets),
+	.dapm_routes		= axg_tdmout_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_tdmout_dapm_routes),
+};
+
+static const struct axg_tdm_formatter_ops axg_tdmout_ops = {
+	.get_stream	= axg_tdmout_get_tdm_stream,
+	.prepare	= axg_tdmout_prepare,
+	.enable		= axg_tdmout_enable,
+	.disable	= axg_tdmout_disable,
+};
+
+static const struct axg_tdm_formatter_driver axg_tdmout_drv = {
+	.component_drv	= &axg_tdmout_component_drv,
+	.regmap_cfg	= &axg_tdmout_regmap_cfg,
+	.ops		= &axg_tdmout_ops,
+	.invert_sclk	= true,
+};
+
+static const struct of_device_id axg_tdmout_of_match[] = {
+	{
+		.compatible = "amlogic,axg-tdmout",
+		.data = &axg_tdmout_drv,
+	}, {}
+};
+MODULE_DEVICE_TABLE(of, axg_tdmout_of_match);
+
+static struct platform_driver axg_tdmout_pdrv = {
+	.probe = axg_tdm_formatter_probe,
+	.driver = {
+		.name = "axg-tdmout",
+		.of_match_table = axg_tdmout_of_match,
+	},
+};
+module_platform_driver(axg_tdmout_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG TDM output formatter driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-toddr.c b/sound/soc/meson/axg-toddr.c
new file mode 100644
index 000000000000..c2c9bb312586
--- /dev/null
+++ b/sound/soc/meson/axg-toddr.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+/* This driver implements the frontend capture DAI of AXG based SoCs */
+
+#include <linux/clk.h>
+#include <linux/regmap.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-fifo.h"
+
+#define CTRL0_TODDR_SEL_RESAMPLE	BIT(30)
+#define CTRL0_TODDR_EXT_SIGNED		BIT(29)
+#define CTRL0_TODDR_PP_MODE		BIT(28)
+#define CTRL0_TODDR_TYPE_MASK		GENMASK(15, 13)
+#define CTRL0_TODDR_TYPE(x)		((x) << 13)
+#define CTRL0_TODDR_MSB_POS_MASK	GENMASK(12, 8)
+#define CTRL0_TODDR_MSB_POS(x)		((x) << 8)
+#define CTRL0_TODDR_LSB_POS_MASK	GENMASK(7, 3)
+#define CTRL0_TODDR_LSB_POS(x)		((x) << 3)
+
+static int axg_toddr_pcm_new(struct snd_soc_pcm_runtime *rtd,
+			     struct snd_soc_dai *dai)
+{
+	return axg_fifo_pcm_new(rtd, SNDRV_PCM_STREAM_CAPTURE);
+}
+
+static int axg_toddr_dai_hw_params(struct snd_pcm_substream *substream,
+				   struct snd_pcm_hw_params *params,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+	unsigned int type, width, msb = 31;
+
+	/*
+	 * NOTE:
+	 * Almost all backend will place the MSB at bit 31, except SPDIF Input
+	 * which will put it at index 28. When adding support for the SPDIF
+	 * Input, we'll need to find which type of backend we are connected to.
+	 */
+
+	switch (params_physical_width(params)) {
+	case 8:
+		type = 0; /* 8 samples of 8 bits */
+		break;
+	case 16:
+		type = 2; /* 4 samples of 16 bits - right justified */
+		break;
+	case 32:
+		type = 4; /* 2 samples of 32 bits - right justified */
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	width = params_width(params);
+
+	regmap_update_bits(fifo->map, FIFO_CTRL0,
+			   CTRL0_TODDR_TYPE_MASK |
+			   CTRL0_TODDR_MSB_POS_MASK |
+			   CTRL0_TODDR_LSB_POS_MASK,
+			   CTRL0_TODDR_TYPE(type) |
+			   CTRL0_TODDR_MSB_POS(msb) |
+			   CTRL0_TODDR_LSB_POS(msb - (width - 1)));
+
+	return 0;
+}
+
+static int axg_toddr_dai_startup(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+	unsigned int fifo_threshold;
+	int ret;
+
+	/* Enable pclk to access registers and clock the fifo ip */
+	ret = clk_prepare_enable(fifo->pclk);
+	if (ret)
+		return ret;
+
+	/* Select orginal data - resampling not supported ATM */
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_TODDR_SEL_RESAMPLE, 0);
+
+	/* Only signed format are supported ATM */
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_TODDR_EXT_SIGNED,
+			   CTRL0_TODDR_EXT_SIGNED);
+
+	/* Apply single buffer mode to the interface */
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_TODDR_PP_MODE, 0);
+
+	/* TODDR does not have a configurable fifo depth */
+	fifo_threshold = AXG_FIFO_MIN_CNT - 1;
+	regmap_update_bits(fifo->map, FIFO_CTRL1, CTRL1_THRESHOLD_MASK,
+			   CTRL1_THRESHOLD(fifo_threshold));
+
+	return 0;
+}
+
+static void axg_toddr_dai_shutdown(struct snd_pcm_substream *substream,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+
+	clk_disable_unprepare(fifo->pclk);
+}
+
+static const struct snd_soc_dai_ops axg_toddr_ops = {
+	.hw_params	= axg_toddr_dai_hw_params,
+	.startup	= axg_toddr_dai_startup,
+	.shutdown	= axg_toddr_dai_shutdown,
+};
+
+static struct snd_soc_dai_driver axg_toddr_dai_drv = {
+	.name = "TODDR",
+	.capture = {
+		.stream_name	= "Capture",
+		.channels_min	= 1,
+		.channels_max	= AXG_FIFO_CH_MAX,
+		.rates		= AXG_FIFO_RATES,
+		.formats	= AXG_FIFO_FORMATS,
+	},
+	.ops		= &axg_toddr_ops,
+	.pcm_new	= axg_toddr_pcm_new,
+};
+
+static const char * const axg_toddr_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2", "IN 3", "IN 4", "IN 6"
+};
+
+static const unsigned int axg_toddr_sel_values[] = {
+	0, 1, 2, 3, 4, 6
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(axg_toddr_sel_enum, FIFO_CTRL0,
+				  CTRL0_SEL_SHIFT, CTRL0_SEL_MASK,
+				  axg_toddr_sel_texts, axg_toddr_sel_values);
+
+static const struct snd_kcontrol_new axg_toddr_in_mux =
+	SOC_DAPM_ENUM("Input Source", axg_toddr_sel_enum);
+
+static const struct snd_soc_dapm_widget axg_toddr_dapm_widgets[] = {
+	SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &axg_toddr_in_mux),
+	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 3", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 4", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 6", NULL, 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route axg_toddr_dapm_routes[] = {
+	{ "Capture", NULL, "SRC SEL" },
+	{ "SRC SEL", "IN 0", "IN 0" },
+	{ "SRC SEL", "IN 1", "IN 1" },
+	{ "SRC SEL", "IN 2", "IN 2" },
+	{ "SRC SEL", "IN 3", "IN 3" },
+	{ "SRC SEL", "IN 4", "IN 4" },
+	{ "SRC SEL", "IN 6", "IN 6" },
+};
+
+static const struct snd_soc_component_driver axg_toddr_component_drv = {
+	.dapm_widgets		= axg_toddr_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_toddr_dapm_widgets),
+	.dapm_routes		= axg_toddr_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_toddr_dapm_routes),
+	.ops			= &axg_fifo_pcm_ops
+};
+
+static const struct axg_fifo_match_data axg_toddr_match_data = {
+	.component_drv	= &axg_toddr_component_drv,
+	.dai_drv	= &axg_toddr_dai_drv
+};
+
+static const struct of_device_id axg_toddr_of_match[] = {
+	{
+		.compatible = "amlogic,axg-toddr",
+		.data = &axg_toddr_match_data,
+	}, {}
+};
+MODULE_DEVICE_TABLE(of, axg_toddr_of_match);
+
+static struct platform_driver axg_toddr_pdrv = {
+	.probe = axg_fifo_probe,
+	.driver = {
+		.name = "axg-toddr",
+		.of_match_table = axg_toddr_of_match,
+	},
+};
+module_platform_driver(axg_toddr_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG capture fifo driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/omap/omap-abe-twl6040.c b/sound/soc/omap/omap-abe-twl6040.c
index 15ccbf479c96..d5ae9eb8c756 100644
--- a/sound/soc/omap/omap-abe-twl6040.c
+++ b/sound/soc/omap/omap-abe-twl6040.c
@@ -40,7 +40,7 @@ struct abe_twl6040 {
 	int	mclk_freq;	/* MCLK frequency speed for twl6040 */
 };
 
-struct platform_device *dmic_codec_dev;
+static struct platform_device *dmic_codec_dev;
 
 static int omap_abe_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_hw_params *params)
diff --git a/sound/soc/omap/omap-dmic.c b/sound/soc/omap/omap-dmic.c
index 51dd7c65096b..fe966272bd0c 100644
--- a/sound/soc/omap/omap-dmic.c
+++ b/sound/soc/omap/omap-dmic.c
@@ -213,8 +213,10 @@ static int omap_dmic_dai_hw_params(struct snd_pcm_substream *substream,
 	switch (channels) {
 	case 6:
 		dmic->ch_enabled |= OMAP_DMIC_UP3_ENABLE;
+		/* fall through */
 	case 4:
 		dmic->ch_enabled |= OMAP_DMIC_UP2_ENABLE;
+		/* fall through */
 	case 2:
 		dmic->ch_enabled |= OMAP_DMIC_UP1_ENABLE;
 		break;
diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c
index 0e97360f9890..4c1be36c2207 100644
--- a/sound/soc/omap/omap-mcpdm.c
+++ b/sound/soc/omap/omap-mcpdm.c
@@ -310,15 +310,19 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream,
 			/* up to 3 channels for capture */
 			return -EINVAL;
 		link_mask |= 1 << 4;
+		/* fall through */
 	case 4:
 		if (stream == SNDRV_PCM_STREAM_CAPTURE)
 			/* up to 3 channels for capture */
 			return -EINVAL;
 		link_mask |= 1 << 3;
+		/* fall through */
 	case 3:
 		link_mask |= 1 << 2;
+		/* fall through */
 	case 2:
 		link_mask |= 1 << 1;
+		/* fall through */
 	case 1:
 		link_mask |= 1 << 0;
 		break;
diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 960744e46edc..776e148b0aa2 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -24,15 +24,19 @@ config SND_PXA2XX_AC97
 config SND_PXA2XX_SOC_AC97
 	tristate
 	select AC97_BUS
+	select SND_PXA2XX_LIB
 	select SND_PXA2XX_LIB_AC97
 	select SND_SOC_AC97_BUS
 
 config SND_PXA2XX_SOC_I2S
+	select SND_PXA2XX_LIB
 	tristate
 
 config SND_PXA_SOC_SSP
-	tristate
+	tristate "Soc Audio via PXA2xx/PXA3xx SSP ports"
+	depends on PLAT_PXA
 	select PXA_SSP
+	select SND_PXA2XX_LIB
 
 config SND_MMP_SOC_SSPA
 	tristate
diff --git a/sound/soc/pxa/magician.c b/sound/soc/pxa/magician.c
index 2fc012b06c43..935a248e5bf6 100644
--- a/sound/soc/pxa/magician.c
+++ b/sound/soc/pxa/magician.c
@@ -90,95 +90,9 @@ static int magician_playback_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	unsigned int acps, acds, width;
-	unsigned int div4 = PXA_SSP_CLK_SCDB_4;
+	unsigned int width;
 	int ret = 0;
 
-	width = snd_pcm_format_physical_width(params_format(params));
-
-	/*
-	 * rate = SSPSCLK / (2 * width(16 or 32))
-	 * SSPSCLK = (ACPS / ACDS) / SSPSCLKDIV(div4 or div1)
-	 */
-	switch (params_rate(params)) {
-	case 8000:
-		/* off by a factor of 2: bug in the PXA27x audio clock? */
-		acps = 32842000;
-		switch (width) {
-		case 16:
-			/* 513156 Hz ~= _2_ * 8000 Hz * 32 (+0.23%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_16;
-			break;
-		default: /* 32 */
-			/* 1026312 Hz ~= _2_ * 8000 Hz * 64 (+0.23%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_8;
-		}
-		break;
-	case 11025:
-		acps = 5622000;
-		switch (width) {
-		case 16:
-			/* 351375 Hz ~= 11025 Hz * 32 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_4;
-			break;
-		default: /* 32 */
-			/* 702750 Hz ~= 11025 Hz * 64 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-		}
-		break;
-	case 22050:
-		acps = 5622000;
-		switch (width) {
-		case 16:
-			/* 702750 Hz ~= 22050 Hz * 32 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-			break;
-		default: /* 32 */
-			/* 1405500 Hz ~= 22050 Hz * 64 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_1;
-		}
-		break;
-	case 44100:
-		acps = 5622000;
-		switch (width) {
-		case 16:
-			/* 1405500 Hz ~= 44100 Hz * 32 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-			break;
-		default: /* 32 */
-			/* 2811000 Hz ~= 44100 Hz * 64 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_1;
-		}
-		break;
-	case 48000:
-		acps = 12235000;
-		switch (width) {
-		case 16:
-			/* 1529375 Hz ~= 48000 Hz * 32 (-0.44%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-			break;
-		default: /* 32 */
-			/* 3058750 Hz ~= 48000 Hz * 64 (-0.44%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_1;
-		}
-		break;
-	case 96000:
-	default:
-		acps = 12235000;
-		switch (width) {
-		case 16:
-			/* 3058750 Hz ~= 96000 Hz * 32 (-0.44%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_1;
-			break;
-		default: /* 32 */
-			/* 6117500 Hz ~= 96000 Hz * 64 (-0.44%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-			div4 = PXA_SSP_CLK_SCDB_1;
-			break;
-		}
-		break;
-	}
-
 	/* set codec DAI configuration */
 	ret = snd_soc_dai_set_fmt(codec_dai, SND_SOC_DAIFMT_MSB |
 			SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBS_CFS);
@@ -191,6 +105,7 @@ static int magician_playback_hw_params(struct snd_pcm_substream *substream,
 	if (ret < 0)
 		return ret;
 
+	width = snd_pcm_format_physical_width(params_format(params));
 	ret = snd_soc_dai_set_tdm_slot(cpu_dai, 1, 0, 1, width);
 	if (ret < 0)
 		return ret;
@@ -201,23 +116,6 @@ static int magician_playback_hw_params(struct snd_pcm_substream *substream,
 	if (ret < 0)
 		return ret;
 
-	/* set the SSP audio system clock ACDS divider */
-	ret = snd_soc_dai_set_clkdiv(cpu_dai,
-			PXA_SSP_AUDIO_DIV_ACDS, acds);
-	if (ret < 0)
-		return ret;
-
-	/* set the SSP audio system clock SCDB divider4 */
-	ret = snd_soc_dai_set_clkdiv(cpu_dai,
-			PXA_SSP_AUDIO_DIV_SCDB, div4);
-	if (ret < 0)
-		return ret;
-
-	/* set SSP audio pll clock */
-	ret = snd_soc_dai_set_pll(cpu_dai, 0, 0, 0, acps);
-	if (ret < 0)
-		return ret;
-
 	return 0;
 }
 
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index 6fc986080130..69033e1a84e6 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -34,7 +34,6 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-#include "../../arm/pxa2xx-pcm.h"
 #include "pxa-ssp.h"
 
 /*
@@ -42,6 +41,8 @@
  */
 struct ssp_priv {
 	struct ssp_device *ssp;
+	struct clk *extclk;
+	unsigned long ssp_clk;
 	unsigned int sysclk;
 	unsigned int dai_fmt;
 	unsigned int configured_dai_fmt;
@@ -105,9 +106,8 @@ static int pxa_ssp_startup(struct snd_pcm_substream *substream,
 	dma = kzalloc(sizeof(struct snd_dmaengine_dai_dma_data), GFP_KERNEL);
 	if (!dma)
 		return -ENOMEM;
-
-	dma->filter_data = substream->stream == SNDRV_PCM_STREAM_PLAYBACK ?
-				&ssp->drcmr_tx : &ssp->drcmr_rx;
+	dma->chan_name = substream->stream == SNDRV_PCM_STREAM_PLAYBACK ?
+		"tx" : "rx";
 
 	snd_soc_dai_set_dma_data(cpu_dai, substream, dma);
 
@@ -194,21 +194,6 @@ static void pxa_ssp_set_scr(struct ssp_device *ssp, u32 div)
 	pxa_ssp_write_reg(ssp, SSCR0, sscr0);
 }
 
-/**
- * pxa_ssp_get_clkdiv - get SSP clock divider
- */
-static u32 pxa_ssp_get_scr(struct ssp_device *ssp)
-{
-	u32 sscr0 = pxa_ssp_read_reg(ssp, SSCR0);
-	u32 div;
-
-	if (ssp->type == PXA25x_SSP)
-		div = ((sscr0 >> 8) & 0xff) * 2 + 2;
-	else
-		div = ((sscr0 >> 8) & 0xfff) + 1;
-	return div;
-}
-
 /*
  * Set the SSP ports SYSCLK.
  */
@@ -221,6 +206,21 @@ static int pxa_ssp_set_dai_sysclk(struct snd_soc_dai *cpu_dai,
 	u32 sscr0 = pxa_ssp_read_reg(ssp, SSCR0) &
 		~(SSCR0_ECS | SSCR0_NCS | SSCR0_MOD | SSCR0_ACS);
 
+	if (priv->extclk) {
+		int ret;
+
+		/*
+		 * For DT based boards, if an extclk is given, use it
+		 * here and configure PXA_SSP_CLK_EXT.
+		 */
+
+		ret = clk_set_rate(priv->extclk, freq);
+		if (ret < 0)
+			return ret;
+
+		clk_id = PXA_SSP_CLK_EXT;
+	}
+
 	dev_dbg(&ssp->pdev->dev,
 		"pxa_ssp_set_dai_sysclk id: %d, clk_id %d, freq %u\n",
 		cpu_dai->id, clk_id, freq);
@@ -265,66 +265,17 @@ static int pxa_ssp_set_dai_sysclk(struct snd_soc_dai *cpu_dai,
 }
 
 /*
- * Set the SSP clock dividers.
- */
-static int pxa_ssp_set_dai_clkdiv(struct snd_soc_dai *cpu_dai,
-	int div_id, int div)
-{
-	struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai);
-	struct ssp_device *ssp = priv->ssp;
-	int val;
-
-	switch (div_id) {
-	case PXA_SSP_AUDIO_DIV_ACDS:
-		val = (pxa_ssp_read_reg(ssp, SSACD) & ~0x7) | SSACD_ACDS(div);
-		pxa_ssp_write_reg(ssp, SSACD, val);
-		break;
-	case PXA_SSP_AUDIO_DIV_SCDB:
-		val = pxa_ssp_read_reg(ssp, SSACD);
-		val &= ~SSACD_SCDB;
-		if (ssp->type == PXA3xx_SSP)
-			val &= ~SSACD_SCDX8;
-		switch (div) {
-		case PXA_SSP_CLK_SCDB_1:
-			val |= SSACD_SCDB;
-			break;
-		case PXA_SSP_CLK_SCDB_4:
-			break;
-		case PXA_SSP_CLK_SCDB_8:
-			if (ssp->type == PXA3xx_SSP)
-				val |= SSACD_SCDX8;
-			else
-				return -EINVAL;
-			break;
-		default:
-			return -EINVAL;
-		}
-		pxa_ssp_write_reg(ssp, SSACD, val);
-		break;
-	case PXA_SSP_DIV_SCR:
-		pxa_ssp_set_scr(ssp, div);
-		break;
-	default:
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-/*
  * Configure the PLL frequency pxa27x and (afaik - pxa320 only)
  */
-static int pxa_ssp_set_dai_pll(struct snd_soc_dai *cpu_dai, int pll_id,
-	int source, unsigned int freq_in, unsigned int freq_out)
+static int pxa_ssp_set_pll(struct ssp_priv *priv, unsigned int freq)
 {
-	struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai);
 	struct ssp_device *ssp = priv->ssp;
 	u32 ssacd = pxa_ssp_read_reg(ssp, SSACD) & ~0x70;
 
 	if (ssp->type == PXA3xx_SSP)
 		pxa_ssp_write_reg(ssp, SSACDD, 0);
 
-	switch (freq_out) {
+	switch (freq) {
 	case 5622000:
 		break;
 	case 11345000:
@@ -355,7 +306,7 @@ static int pxa_ssp_set_dai_pll(struct snd_soc_dai *cpu_dai, int pll_id,
 			u64 tmp = 19968;
 
 			tmp *= 1000000;
-			do_div(tmp, freq_out);
+			do_div(tmp, freq);
 			val = tmp;
 
 			val = (val << 16) | 64;
@@ -365,7 +316,7 @@ static int pxa_ssp_set_dai_pll(struct snd_soc_dai *cpu_dai, int pll_id,
 
 			dev_dbg(&ssp->pdev->dev,
 				"Using SSACDD %x to supply %uHz\n",
-				val, freq_out);
+				val, freq);
 			break;
 		}
 
@@ -535,6 +486,7 @@ static int pxa_ssp_configure_dai_fmt(struct ssp_priv *priv)
 
 	case SND_SOC_DAIFMT_DSP_A:
 		sspsp |= SSPSP_FSRT;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_B:
 		sscr0 |= SSCR0_MOD | SSCR0_PSP;
 		sscr1 |= SSCR1_TRAIL | SSCR1_RWOT;
@@ -570,6 +522,24 @@ static int pxa_ssp_configure_dai_fmt(struct ssp_priv *priv)
 	return 0;
 }
 
+struct pxa_ssp_clock_mode {
+	int rate;
+	int pll;
+	u8 acds;
+	u8 scdb;
+};
+
+static const struct pxa_ssp_clock_mode pxa_ssp_clock_modes[] = {
+	{ .rate =  8000, .pll = 32842000, .acds = SSACD_ACDS_32, .scdb = SSACD_SCDB_4X },
+	{ .rate = 11025, .pll =  5622000, .acds = SSACD_ACDS_4,  .scdb = SSACD_SCDB_4X },
+	{ .rate = 16000, .pll = 32842000, .acds = SSACD_ACDS_16, .scdb = SSACD_SCDB_4X },
+	{ .rate = 22050, .pll =  5622000, .acds = SSACD_ACDS_2,  .scdb = SSACD_SCDB_4X },
+	{ .rate = 44100, .pll = 11345000, .acds = SSACD_ACDS_2,  .scdb = SSACD_SCDB_4X },
+	{ .rate = 48000, .pll = 12235000, .acds = SSACD_ACDS_2,  .scdb = SSACD_SCDB_4X },
+	{ .rate = 96000, .pll = 12235000, .acds = SSACD_ACDS_4,  .scdb = SSACD_SCDB_1X },
+	{}
+};
+
 /*
  * Set the SSP audio DMA parameters and sample size.
  * Can be called multiple times by oss emulation.
@@ -581,11 +551,12 @@ static int pxa_ssp_hw_params(struct snd_pcm_substream *substream,
 	struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai);
 	struct ssp_device *ssp = priv->ssp;
 	int chn = params_channels(params);
-	u32 sscr0;
-	u32 sspsp;
+	u32 sscr0, sspsp;
 	int width = snd_pcm_format_physical_width(params_format(params));
 	int ttsa = pxa_ssp_read_reg(ssp, SSTSA) & 0xf;
 	struct snd_dmaengine_dai_dma_data *dma_data;
+	int rate = params_rate(params);
+	int bclk = rate * chn * (width / 8);
 	int ret;
 
 	dma_data = snd_soc_dai_get_dma_data(cpu_dai, substream);
@@ -625,11 +596,57 @@ static int pxa_ssp_hw_params(struct snd_pcm_substream *substream,
 	}
 	pxa_ssp_write_reg(ssp, SSCR0, sscr0);
 
+	if (sscr0 & SSCR0_ACS) {
+		ret = pxa_ssp_set_pll(priv, bclk);
+
+		/*
+		 * If we were able to generate the bclk directly,
+		 * all is fine. Otherwise, look up the closest rate
+		 * from the table and also set the dividers.
+		 */
+
+		if (ret < 0) {
+			const struct pxa_ssp_clock_mode *m;
+			int ssacd, acds;
+
+			for (m = pxa_ssp_clock_modes; m->rate; m++) {
+				if (m->rate == rate)
+					break;
+			}
+
+			if (!m->rate)
+				return -EINVAL;
+
+			acds = m->acds;
+
+			/* The values in the table are for 16 bits */
+			if (width == 32)
+				acds--;
+
+			ret = pxa_ssp_set_pll(priv, bclk);
+			if (ret < 0)
+				return ret;
+
+			ssacd = pxa_ssp_read_reg(ssp, SSACD);
+			ssacd &= ~(SSACD_ACDS(7) | SSACD_SCDB_1X);
+			ssacd |= SSACD_ACDS(m->acds);
+			ssacd |= m->scdb;
+			pxa_ssp_write_reg(ssp, SSACD, ssacd);
+		}
+	} else if (sscr0 & SSCR0_ECS) {
+		/*
+		 * For setups with external clocking, the PLL and its diviers
+		 * are not active. Instead, the SCR bits in SSCR0 can be used
+		 * to divide the clock.
+		 */
+		pxa_ssp_set_scr(ssp, bclk / rate);
+	}
+
 	switch (priv->dai_fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 	       sspsp = pxa_ssp_read_reg(ssp, SSPSP);
 
-		if ((pxa_ssp_get_scr(ssp) == 4) && (width == 16)) {
+		if (((priv->sysclk / bclk) == 64) && (width == 16)) {
 			/* This is a special case where the bitclk is 64fs
 			 * and we're not dealing with 2*32 bits of audio
 			 * samples.
@@ -773,6 +790,15 @@ static int pxa_ssp_probe(struct snd_soc_dai *dai)
 			ret = -ENODEV;
 			goto err_priv;
 		}
+
+		priv->extclk = devm_clk_get(dev, "extclk");
+		if (IS_ERR(priv->extclk)) {
+			ret = PTR_ERR(priv->extclk);
+			if (ret == -EPROBE_DEFER)
+				return ret;
+
+			priv->extclk = NULL;
+		}
 	} else {
 		priv->ssp = pxa_ssp_request(dai->id + 1, "SoC audio");
 		if (priv->ssp == NULL) {
@@ -814,8 +840,6 @@ static const struct snd_soc_dai_ops pxa_ssp_dai_ops = {
 	.trigger	= pxa_ssp_trigger,
 	.hw_params	= pxa_ssp_hw_params,
 	.set_sysclk	= pxa_ssp_set_dai_sysclk,
-	.set_clkdiv	= pxa_ssp_set_dai_clkdiv,
-	.set_pll	= pxa_ssp_set_dai_pll,
 	.set_fmt	= pxa_ssp_set_dai_fmt,
 	.set_tdm_slot	= pxa_ssp_set_dai_tdm_slot,
 	.set_tristate	= pxa_ssp_set_dai_tristate,
@@ -843,6 +867,9 @@ static struct snd_soc_dai_driver pxa_ssp_dai = {
 
 static const struct snd_soc_component_driver pxa_ssp_component = {
 	.name		= "pxa-ssp",
+	.ops		= &pxa2xx_pcm_ops,
+	.pcm_new	= pxa2xx_soc_pcm_new,
+	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
 };
 
 #ifdef CONFIG_OF
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index 803818aabee9..9f779657bc86 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -68,61 +68,39 @@ static struct snd_ac97_bus_ops pxa2xx_ac97_ops = {
 	.reset	= pxa2xx_ac97_cold_reset,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_stereo_in_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 11,
-};
-
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_in = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "pcm_pcm_stereo_in",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_ac97_pcm_stereo_in_req,
-};
-
-static struct pxad_param pxa2xx_ac97_pcm_stereo_out_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 12,
 };
 
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_out = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "pcm_pcm_stereo_out",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_ac97_pcm_stereo_out_req,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_aux_mono_out_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 10,
-};
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_aux_mono_out = {
 	.addr		= __PREG(MODR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_2_BYTES,
+	.chan_name	= "pcm_aux_mono_out",
 	.maxburst	= 16,
-	.filter_data	= &pxa2xx_ac97_pcm_aux_mono_out_req,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_aux_mono_in_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 9,
-};
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_aux_mono_in = {
 	.addr		= __PREG(MODR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_2_BYTES,
+	.chan_name	= "pcm_aux_mono_in",
 	.maxburst	= 16,
-	.filter_data	= &pxa2xx_ac97_pcm_aux_mono_in_req,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_aux_mic_mono_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 8,
-};
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_mic_mono_in = {
 	.addr		= __PREG(MCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_2_BYTES,
+	.chan_name	= "pcm_aux_mic_mono",
 	.maxburst	= 16,
-	.filter_data	= &pxa2xx_ac97_pcm_aux_mic_mono_req,
 };
 
 static int pxa2xx_ac97_hifi_startup(struct snd_pcm_substream *substream,
@@ -236,7 +214,21 @@ static struct snd_soc_dai_driver pxa_ac97_dai_driver[] = {
 
 static const struct snd_soc_component_driver pxa_ac97_component = {
 	.name		= "pxa-ac97",
+	.ops		= &pxa2xx_pcm_ops,
+	.pcm_new	= pxa2xx_soc_pcm_new,
+	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id pxa2xx_ac97_dt_ids[] = {
+	{ .compatible = "marvell,pxa250-ac97", },
+	{ .compatible = "marvell,pxa270-ac97", },
+	{ .compatible = "marvell,pxa300-ac97", },
+	{ }
 };
+MODULE_DEVICE_TABLE(of, pxa2xx_ac97_dt_ids);
+
+#endif
 
 static int pxa2xx_ac97_dev_probe(struct platform_device *pdev)
 {
@@ -296,6 +288,7 @@ static struct platform_driver pxa2xx_ac97_driver = {
 #ifdef CONFIG_PM_SLEEP
 		.pm	= &pxa2xx_ac97_pm_ops,
 #endif
+		.of_match_table = of_match_ptr(pxa2xx_ac97_dt_ids),
 	},
 };
 
diff --git a/sound/soc/pxa/pxa2xx-i2s.c b/sound/soc/pxa/pxa2xx-i2s.c
index 3fb60baf6eab..42820121e5b9 100644
--- a/sound/soc/pxa/pxa2xx-i2s.c
+++ b/sound/soc/pxa/pxa2xx-i2s.c
@@ -82,20 +82,18 @@ static struct pxa_i2s_port pxa_i2s;
 static struct clk *clk_i2s;
 static int clk_ena = 0;
 
-static unsigned long pxa2xx_i2s_pcm_stereo_out_req = 3;
 static struct snd_dmaengine_dai_dma_data pxa2xx_i2s_pcm_stereo_out = {
 	.addr		= __PREG(SADR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "tx",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_i2s_pcm_stereo_out_req,
 };
 
-static unsigned long pxa2xx_i2s_pcm_stereo_in_req = 2;
 static struct snd_dmaengine_dai_dma_data pxa2xx_i2s_pcm_stereo_in = {
 	.addr		= __PREG(SADR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "rx",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_i2s_pcm_stereo_in_req,
 };
 
 static int pxa2xx_i2s_startup(struct snd_pcm_substream *substream,
@@ -366,6 +364,9 @@ static struct snd_soc_dai_driver pxa_i2s_dai = {
 
 static const struct snd_soc_component_driver pxa_i2s_component = {
 	.name		= "pxa-i2s",
+	.ops		= &pxa2xx_pcm_ops,
+	.pcm_new	= pxa2xx_soc_pcm_new,
+	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
 };
 
 static int pxa2xx_i2s_drv_probe(struct platform_device *pdev)
diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c
index 8b6a70e94c01..72eaaef1b426 100644
--- a/sound/soc/pxa/pxa2xx-pcm.c
+++ b/sound/soc/pxa/pxa2xx-pcm.c
@@ -20,70 +20,6 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-#include "../../arm/pxa2xx-pcm.h"
-
-static int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
-	struct snd_pcm_hw_params *params)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_dmaengine_dai_dma_data *dma;
-
-	dma = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream);
-
-	/* return if this is a bufferless transfer e.g.
-	 * codec <--> BT codec or GSM modem -- lg FIXME */
-	if (!dma)
-		return 0;
-
-	return __pxa2xx_pcm_hw_params(substream, params);
-}
-
-static int pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream)
-{
-	__pxa2xx_pcm_hw_free(substream);
-
-	return 0;
-}
-
-static const struct snd_pcm_ops pxa2xx_pcm_ops = {
-	.open		= __pxa2xx_pcm_open,
-	.close		= __pxa2xx_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= pxa2xx_pcm_hw_params,
-	.hw_free	= pxa2xx_pcm_hw_free,
-	.prepare	= __pxa2xx_pcm_prepare,
-	.trigger	= pxa2xx_pcm_trigger,
-	.pointer	= pxa2xx_pcm_pointer,
-	.mmap		= pxa2xx_pcm_mmap,
-};
-
-static int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd)
-{
-	struct snd_card *card = rtd->card->snd_card;
-	struct snd_pcm *pcm = rtd->pcm;
-	int ret;
-
-	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
-	if (ret)
-		return ret;
-
-	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
-		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
-			SNDRV_PCM_STREAM_PLAYBACK);
-		if (ret)
-			goto out;
-	}
-
-	if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
-		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
-			SNDRV_PCM_STREAM_CAPTURE);
-		if (ret)
-			goto out;
-	}
- out:
-	return ret;
-}
-
 static const struct snd_soc_component_driver pxa2xx_soc_platform = {
 	.ops		= &pxa2xx_pcm_ops,
 	.pcm_new	= pxa2xx_soc_pcm_new,
@@ -96,18 +32,9 @@ static int pxa2xx_soc_platform_probe(struct platform_device *pdev)
 					       NULL, 0);
 }
 
-#ifdef CONFIG_OF
-static const struct of_device_id snd_soc_pxa_audio_match[] = {
-	{ .compatible   = "mrvl,pxa-pcm-audio" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, snd_soc_pxa_audio_match);
-#endif
-
 static struct platform_driver pxa_pcm_driver = {
 	.driver = {
 		.name = "pxa-pcm-audio",
-		.of_match_table = of_match_ptr(snd_soc_pxa_audio_match),
 	},
 
 	.probe = pxa2xx_soc_platform_probe,
diff --git a/sound/soc/pxa/zylonite.c b/sound/soc/pxa/zylonite.c
index ba468e560dd2..230eee450f45 100644
--- a/sound/soc/pxa/zylonite.c
+++ b/sound/soc/pxa/zylonite.c
@@ -83,11 +83,9 @@ static int zylonite_voice_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	unsigned int pll_out = 0;
 	unsigned int wm9713_div = 0;
 	int ret = 0;
 	int rate = params_rate(params);
-	int width = snd_pcm_format_physical_width(params_format(params));
 
 	/* Only support ratios that we can generate neatly from the AC97
 	 * based master clock - in particular, this excludes 44.1kHz.
@@ -109,17 +107,10 @@ static int zylonite_voice_hw_params(struct snd_pcm_substream *substream,
 		return -EINVAL;
 	}
 
-	/* Add 1 to the width for the leading clock cycle */
-	pll_out = rate * (width + 1) * 8;
-
 	ret = snd_soc_dai_set_sysclk(cpu_dai, PXA_SSP_CLK_AUDIO, 0, 1);
 	if (ret < 0)
 		return ret;
 
-	ret = snd_soc_dai_set_pll(cpu_dai, 0, 0, 0, pll_out);
-	if (ret < 0)
-		return ret;
-
 	if (clk_pout)
 		ret = snd_soc_dai_set_clkdiv(codec_dai, WM9713_PCMCLK_PLL_DIV,
 					     WM9713_PCMDIV(wm9713_div));
diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index 87838fa27997..2a4c912d1e48 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -41,6 +41,9 @@ config SND_SOC_APQ8016_SBC
           APQ8016 SOC-based systems.
           Say Y if you want to use audio devices on MI2S.
 
+config SND_SOC_QCOM_COMMON
+	tristate
+
 config SND_SOC_QDSP6_COMMON
 	tristate
 
@@ -86,7 +89,18 @@ config SND_SOC_MSM8996
 	tristate "SoC Machine driver for MSM8996 and APQ8096 boards"
 	depends on QCOM_APR
 	select SND_SOC_QDSP6
+	select SND_SOC_QCOM_COMMON
 	help
           Support for Qualcomm Technologies LPASS audio block in
           APQ8096 SoC-based systems.
           Say Y if you want to use audio device on this SoCs
+
+config SND_SOC_SDM845
+	tristate "SoC Machine driver for SDM845 boards"
+	depends on QCOM_APR
+	select SND_SOC_QDSP6
+	select SND_SOC_QCOM_COMMON
+	help
+	  To add support for audio on Qualcomm Technologies Inc.
+	  SDM845 SoC-based systems.
+	  Say Y if you want to use audio device on this SoCs.
diff --git a/sound/soc/qcom/Makefile b/sound/soc/qcom/Makefile
index 206945bb9ba1..41b2c7a23a4d 100644
--- a/sound/soc/qcom/Makefile
+++ b/sound/soc/qcom/Makefile
@@ -14,10 +14,14 @@ obj-$(CONFIG_SND_SOC_LPASS_APQ8016) += snd-soc-lpass-apq8016.o
 snd-soc-storm-objs := storm.o
 snd-soc-apq8016-sbc-objs := apq8016_sbc.o
 snd-soc-apq8096-objs := apq8096.o
+snd-soc-sdm845-objs := sdm845.o
+snd-soc-qcom-common-objs := common.o
 
 obj-$(CONFIG_SND_SOC_STORM) += snd-soc-storm.o
 obj-$(CONFIG_SND_SOC_APQ8016_SBC) += snd-soc-apq8016-sbc.o
 obj-$(CONFIG_SND_SOC_MSM8996) += snd-soc-apq8096.o
+obj-$(CONFIG_SND_SOC_SDM845) += snd-soc-sdm845.o
+obj-$(CONFIG_SND_SOC_QCOM_COMMON) += snd-soc-qcom-common.o
 
 #DSP lib
 obj-$(CONFIG_SND_SOC_QDSP6) += qdsp6/
diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
index 561cd429e6f2..1543e85629f8 100644
--- a/sound/soc/qcom/apq8096.c
+++ b/sound/soc/qcom/apq8096.c
@@ -1,14 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2018, Linaro Limited
 
-#include <linux/soc/qcom/apr.h>
 #include <linux/module.h>
-#include <linux/component.h>
 #include <linux/platform_device.h>
 #include <linux/of_device.h>
 #include <sound/soc.h>
 #include <sound/soc-dapm.h>
 #include <sound/pcm.h>
+#include "common.h"
 
 static int apq8096_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 				      struct snd_pcm_hw_params *params)
@@ -24,211 +23,57 @@ static int apq8096_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 	return 0;
 }
 
-static int apq8096_sbc_parse_of(struct snd_soc_card *card)
+static void apq8096_add_be_ops(struct snd_soc_card *card)
 {
-	struct device_node *np;
-	struct device_node *codec = NULL;
-	struct device_node *platform = NULL;
-	struct device_node *cpu = NULL;
-	struct device *dev = card->dev;
-	struct snd_soc_dai_link *link;
-	int ret, num_links;
-
-	ret = snd_soc_of_parse_card_name(card, "qcom,model");
-	if (ret) {
-		dev_err(dev, "Error parsing card name: %d\n", ret);
-		return ret;
-	}
-
-	/* DAPM routes */
-	if (of_property_read_bool(dev->of_node, "qcom,audio-routing")) {
-		ret = snd_soc_of_parse_audio_routing(card,
-					"qcom,audio-routing");
-		if (ret)
-			return ret;
-	}
-
-	/* Populate links */
-	num_links = of_get_child_count(dev->of_node);
+	struct snd_soc_dai_link *link = card->dai_link;
+	int i, num_links = card->num_links;
 
-	/* Allocate the DAI link array */
-	card->dai_link = kcalloc(num_links, sizeof(*link), GFP_KERNEL);
-	if (!card->dai_link)
-		return -ENOMEM;
-
-	card->num_links	= num_links;
-	link = card->dai_link;
-
-	for_each_child_of_node(dev->of_node, np) {
-		cpu = of_get_child_by_name(np, "cpu");
-		if (!cpu) {
-			dev_err(dev, "Can't find cpu DT node\n");
-			ret = -EINVAL;
-			goto err;
-		}
-
-		link->cpu_of_node = of_parse_phandle(cpu, "sound-dai", 0);
-		if (!link->cpu_of_node) {
-			dev_err(card->dev, "error getting cpu phandle\n");
-			ret = -EINVAL;
-			goto err;
-		}
-
-		ret = snd_soc_of_get_dai_name(cpu, &link->cpu_dai_name);
-		if (ret) {
-			dev_err(card->dev, "error getting cpu dai name\n");
-			goto err;
-		}
-
-		platform = of_get_child_by_name(np, "platform");
-		codec = of_get_child_by_name(np, "codec");
-		if (codec && platform) {
-			link->platform_of_node = of_parse_phandle(platform,
-								  "sound-dai",
-								   0);
-			if (!link->platform_of_node) {
-				dev_err(card->dev, "platform dai not found\n");
-				ret = -EINVAL;
-				goto err;
-			}
-
-			ret = snd_soc_of_get_dai_link_codecs(dev, codec, link);
-			if (ret < 0) {
-				dev_err(card->dev, "codec dai not found\n");
-				goto err;
-			}
-			link->no_pcm = 1;
-			link->ignore_pmdown_time = 1;
+	for (i = 0; i < num_links; i++) {
+		if (link->no_pcm == 1)
 			link->be_hw_params_fixup = apq8096_be_hw_params_fixup;
-		} else {
-			link->platform_of_node = link->cpu_of_node;
-			link->codec_dai_name = "snd-soc-dummy-dai";
-			link->codec_name = "snd-soc-dummy";
-			link->dynamic = 1;
-		}
-
-		link->ignore_suspend = 1;
-		ret = of_property_read_string(np, "link-name", &link->name);
-		if (ret) {
-			dev_err(card->dev, "error getting codec dai_link name\n");
-			goto err;
-		}
-
-		link->dpcm_playback = 1;
-		link->dpcm_capture = 1;
-		link->stream_name = link->name;
 		link++;
 	}
-
-	return 0;
-err:
-	of_node_put(cpu);
-	of_node_put(codec);
-	of_node_put(platform);
-	kfree(card->dai_link);
-	return ret;
 }
 
-static int apq8096_bind(struct device *dev)
+static int apq8096_platform_probe(struct platform_device *pdev)
 {
 	struct snd_soc_card *card;
+	struct device *dev = &pdev->dev;
 	int ret;
 
 	card = kzalloc(sizeof(*card), GFP_KERNEL);
 	if (!card)
 		return -ENOMEM;
 
-	component_bind_all(dev, card);
 	card->dev = dev;
-	ret = apq8096_sbc_parse_of(card);
+	dev_set_drvdata(dev, card);
+	ret = qcom_snd_parse_of(card);
 	if (ret) {
 		dev_err(dev, "Error parsing OF data\n");
 		goto err;
 	}
 
+	apq8096_add_be_ops(card);
 	ret = snd_soc_register_card(card);
 	if (ret)
-		goto err;
+		goto err_card_register;
 
 	return 0;
 
+err_card_register:
+	kfree(card->dai_link);
 err:
-	component_unbind_all(dev, card);
 	kfree(card);
 	return ret;
 }
 
-static void apq8096_unbind(struct device *dev)
+static int apq8096_platform_remove(struct platform_device *pdev)
 {
-	struct snd_soc_card *card = dev_get_drvdata(dev);
+	struct snd_soc_card *card = dev_get_drvdata(&pdev->dev);
 
 	snd_soc_unregister_card(card);
-	component_unbind_all(dev, card);
 	kfree(card->dai_link);
 	kfree(card);
-}
-
-static const struct component_master_ops apq8096_ops = {
-	.bind = apq8096_bind,
-	.unbind = apq8096_unbind,
-};
-
-static int apq8016_compare_of(struct device *dev, void *data)
-{
-	return dev->of_node == data;
-}
-
-static void apq8016_release_of(struct device *dev, void *data)
-{
-	of_node_put(data);
-}
-
-static int add_audio_components(struct device *dev,
-				struct component_match **matchptr)
-{
-	struct device_node *np, *platform, *cpu, *node, *dai_node;
-
-	node = dev->of_node;
-
-	for_each_child_of_node(node, np) {
-		cpu = of_get_child_by_name(np, "cpu");
-		if (cpu) {
-			dai_node = of_parse_phandle(cpu, "sound-dai", 0);
-			of_node_get(dai_node);
-			component_match_add_release(dev, matchptr,
-						    apq8016_release_of,
-						    apq8016_compare_of,
-						    dai_node);
-		}
-
-		platform = of_get_child_by_name(np, "platform");
-		if (platform) {
-			dai_node = of_parse_phandle(platform, "sound-dai", 0);
-			component_match_add_release(dev, matchptr,
-						    apq8016_release_of,
-						    apq8016_compare_of,
-						    dai_node);
-		}
-	}
-
-	return 0;
-}
-
-static int apq8096_platform_probe(struct platform_device *pdev)
-{
-	struct component_match *match = NULL;
-	int ret;
-
-	ret = add_audio_components(&pdev->dev, &match);
-	if (ret)
-		return ret;
-
-	return component_master_add_with_match(&pdev->dev, &apq8096_ops, match);
-}
-
-static int apq8096_platform_remove(struct platform_device *pdev)
-{
-	component_master_del(&pdev->dev, &apq8096_ops);
 
 	return 0;
 }
@@ -245,7 +90,6 @@ static struct platform_driver msm_snd_apq8096_driver = {
 	.remove = apq8096_platform_remove,
 	.driver = {
 		.name = "msm-snd-apq8096",
-		.owner = THIS_MODULE,
 		.of_match_table = msm_snd_apq8096_dt_match,
 	},
 };
diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c
new file mode 100644
index 000000000000..eb1b9da05dd4
--- /dev/null
+++ b/sound/soc/qcom/common.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, Linaro Limited.
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#include <linux/module.h>
+#include "common.h"
+
+int qcom_snd_parse_of(struct snd_soc_card *card)
+{
+	struct device_node *np;
+	struct device_node *codec = NULL;
+	struct device_node *platform = NULL;
+	struct device_node *cpu = NULL;
+	struct device *dev = card->dev;
+	struct snd_soc_dai_link *link;
+	int ret, num_links;
+
+	ret = snd_soc_of_parse_card_name(card, "model");
+	if (ret) {
+		dev_err(dev, "Error parsing card name: %d\n", ret);
+		return ret;
+	}
+
+	/* DAPM routes */
+	if (of_property_read_bool(dev->of_node, "audio-routing")) {
+		ret = snd_soc_of_parse_audio_routing(card,
+				"audio-routing");
+		if (ret)
+			return ret;
+	}
+
+	/* Populate links */
+	num_links = of_get_child_count(dev->of_node);
+
+	/* Allocate the DAI link array */
+	card->dai_link = kcalloc(num_links, sizeof(*link), GFP_KERNEL);
+	if (!card->dai_link)
+		return -ENOMEM;
+
+	card->num_links = num_links;
+	link = card->dai_link;
+	for_each_child_of_node(dev->of_node, np) {
+		cpu = of_get_child_by_name(np, "cpu");
+		if (!cpu) {
+			dev_err(dev, "Can't find cpu DT node\n");
+			ret = -EINVAL;
+			goto err;
+		}
+
+		link->cpu_of_node = of_parse_phandle(cpu, "sound-dai", 0);
+		if (!link->cpu_of_node) {
+			dev_err(card->dev, "error getting cpu phandle\n");
+			ret = -EINVAL;
+			goto err;
+		}
+
+		ret = snd_soc_of_get_dai_name(cpu, &link->cpu_dai_name);
+		if (ret) {
+			dev_err(card->dev, "error getting cpu dai name\n");
+			goto err;
+		}
+
+		platform = of_get_child_by_name(np, "platform");
+		codec = of_get_child_by_name(np, "codec");
+		if (codec && platform) {
+			link->platform_of_node = of_parse_phandle(platform,
+					"sound-dai",
+					0);
+			if (!link->platform_of_node) {
+				dev_err(card->dev, "platform dai not found\n");
+				ret = -EINVAL;
+				goto err;
+			}
+
+			ret = snd_soc_of_get_dai_link_codecs(dev, codec, link);
+			if (ret < 0) {
+				dev_err(card->dev, "codec dai not found\n");
+				goto err;
+			}
+			link->no_pcm = 1;
+			link->ignore_pmdown_time = 1;
+		} else {
+			link->platform_of_node = link->cpu_of_node;
+			link->codec_dai_name = "snd-soc-dummy-dai";
+			link->codec_name = "snd-soc-dummy";
+			link->dynamic = 1;
+		}
+
+		link->ignore_suspend = 1;
+		ret = of_property_read_string(np, "link-name", &link->name);
+		if (ret) {
+			dev_err(card->dev, "error getting codec dai_link name\n");
+			goto err;
+		}
+
+		link->dpcm_playback = 1;
+		link->dpcm_capture = 1;
+		link->stream_name = link->name;
+		link++;
+	}
+
+	return 0;
+err:
+	of_node_put(cpu);
+	of_node_put(codec);
+	of_node_put(platform);
+	kfree(card->dai_link);
+	return ret;
+}
+EXPORT_SYMBOL(qcom_snd_parse_of);
+
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/common.h b/sound/soc/qcom/common.h
new file mode 100644
index 000000000000..f05c05b12bd7
--- /dev/null
+++ b/sound/soc/qcom/common.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#ifndef __QCOM_SND_COMMON_H__
+#define __QCOM_SND_COMMON_H__
+
+#include <sound/soc.h>
+
+int qcom_snd_parse_of(struct snd_soc_card *card);
+
+#endif
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index 31fe78aa207f..d07271ea4c45 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -458,7 +458,7 @@ static irqreturn_t lpass_dma_interrupt_handler(
 			return IRQ_NONE;
 		}
 		dev_warn(soc_runtime->dev, "xrun warning\n");
-		snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+		snd_pcm_stop_xrun(substream);
 		ret = IRQ_HANDLED;
 	}
 
diff --git a/sound/soc/qcom/qdsp6/q6adm.c b/sound/soc/qcom/qdsp6/q6adm.c
index 9983c665a941..932c3ebfd252 100644
--- a/sound/soc/qcom/qdsp6/q6adm.c
+++ b/sound/soc/qcom/qdsp6/q6adm.c
@@ -64,7 +64,6 @@ struct q6adm {
 	struct aprv2_ibasic_rsp_result_t result;
 	struct mutex lock;
 	wait_queue_head_t matrix_map_wait;
-	struct platform_device *pdev_routing;
 };
 
 struct q6adm_cmd_device_open_v5 {
@@ -588,7 +587,6 @@ EXPORT_SYMBOL_GPL(q6adm_close);
 static int q6adm_probe(struct apr_device *adev)
 {
 	struct device *dev = &adev->dev;
-	struct device_node *dais_np;
 	struct q6adm *adm;
 
 	adm = devm_kzalloc(&adev->dev, sizeof(*adm), GFP_KERNEL);
@@ -605,22 +603,12 @@ static int q6adm_probe(struct apr_device *adev)
 	INIT_LIST_HEAD(&adm->copps_list);
 	spin_lock_init(&adm->copps_list_lock);
 
-	dais_np = of_get_child_by_name(dev->of_node, "routing");
-	if (dais_np) {
-		adm->pdev_routing = of_platform_device_create(dais_np,
-							   "q6routing", dev);
-		of_node_put(dais_np);
-	}
-
-	return 0;
+	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
 
 static int q6adm_remove(struct apr_device *adev)
 {
-	struct q6adm *adm = dev_get_drvdata(&adev->dev);
-
-	if (adm->pdev_routing)
-		of_platform_device_destroy(&adm->pdev_routing->dev, NULL);
+	of_platform_depopulate(&adev->dev);
 
 	return 0;
 }
diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index 5002dd05bf27..60ff4a2d3577 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -4,7 +4,6 @@
 
 #include <linux/err.h>
 #include <linux/init.h>
-#include <linux/component.h>
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
@@ -81,7 +80,6 @@ static int q6slim_hw_params(struct snd_pcm_substream *substream,
 	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
 	struct q6afe_slim_cfg *slim = &dai_data->port_config[dai->id].slim;
 
-	slim->num_channels = params_channels(params);
 	slim->sample_rate = params_rate(params);
 
 	switch (params_format(params)) {
@@ -315,6 +313,9 @@ static void q6afe_dai_shutdown(struct snd_pcm_substream *substream,
 	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
 	int rc;
 
+	if (!dai_data->is_port_started[dai->id])
+		return;
+
 	rc = q6afe_port_stop(dai_data->port[dai->id]);
 	if (rc < 0)
 		dev_err(dai->dev, "fail to close AFE port (%d)\n", rc);
@@ -382,23 +383,31 @@ static int q6slim_set_channel_map(struct snd_soc_dai *dai,
 	struct q6afe_port_config *pcfg = &dai_data->port_config[dai->id];
 	int i;
 
-	if (!rx_slot) {
-		pr_err("%s: rx slot not found\n", __func__);
-		return -EINVAL;
-	}
+	if (dai->id & 0x1) {
+		/* TX */
+		if (!tx_slot) {
+			pr_err("%s: tx slot not found\n", __func__);
+			return -EINVAL;
+		}
 
-	for (i = 0; i < rx_num; i++) {
-		pcfg->slim.ch_mapping[i] =   rx_slot[i];
-		pr_debug("%s: find number of channels[%d] ch[%d]\n",
-		       __func__, i, rx_slot[i]);
-	}
+		for (i = 0; i < tx_num; i++)
+			pcfg->slim.ch_mapping[i] = tx_slot[i];
+
+		pcfg->slim.num_channels = tx_num;
+
+
+	} else {
+		if (!rx_slot) {
+			pr_err("%s: rx slot not found\n", __func__);
+			return -EINVAL;
+		}
 
-	pcfg->slim.num_channels = rx_num;
+		for (i = 0; i < rx_num; i++)
+			pcfg->slim.ch_mapping[i] =   rx_slot[i];
 
-	pr_debug("%s: SLIMBUS_%d_RX cnt[%d] ch[%d %d]\n", __func__,
-		(dai->id - SLIMBUS_0_RX) / 2, rx_num,
-		pcfg->slim.ch_mapping[0],
-		pcfg->slim.ch_mapping[1]);
+		pcfg->slim.num_channels = rx_num;
+
+	}
 
 	return 0;
 }
@@ -443,6 +452,14 @@ static const struct snd_soc_dapm_route q6afe_dapm_routes[] = {
 	{"Slimbus5 Playback", NULL, "SLIMBUS_5_RX"},
 	{"Slimbus6 Playback", NULL, "SLIMBUS_6_RX"},
 
+	{"SLIMBUS_0_TX", NULL, "Slimbus Capture"},
+	{"SLIMBUS_1_TX", NULL, "Slimbus1 Capture"},
+	{"SLIMBUS_2_TX", NULL, "Slimbus2 Capture"},
+	{"SLIMBUS_3_TX", NULL, "Slimbus3 Capture"},
+	{"SLIMBUS_4_TX", NULL, "Slimbus4 Capture"},
+	{"SLIMBUS_5_TX", NULL, "Slimbus5 Capture"},
+	{"SLIMBUS_6_TX", NULL, "Slimbus6 Capture"},
+
 	{"Primary MI2S Playback", NULL, "PRI_MI2S_RX"},
 	{"Secondary MI2S Playback", NULL, "SEC_MI2S_RX"},
 	{"Tertiary MI2S Playback", NULL, "TERT_MI2S_RX"},
@@ -637,6 +654,24 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 			.rate_max = 192000,
 		},
 	}, {
+		.name = "SLIMBUS_0_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_0_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
+	}, {
 		.playback = {
 			.stream_name = "Slimbus1 Playback",
 			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |
@@ -655,6 +690,24 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
 	}, {
+		.name = "SLIMBUS_1_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_1_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus1 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
+	}, {
 		.playback = {
 			.stream_name = "Slimbus2 Playback",
 			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
@@ -672,6 +725,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_2_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_2_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_2_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus2 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus3 Playback",
@@ -690,6 +762,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_3_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_3_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_3_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus3 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus4 Playback",
@@ -708,6 +799,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_4_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_4_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_4_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus4 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus5 Playback",
@@ -726,6 +836,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_5_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_5_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_5_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus5 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus6 Playback",
@@ -744,6 +873,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_6_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_6_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_6_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus6 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Primary MI2S Playback",
@@ -972,6 +1120,13 @@ static const struct snd_soc_dapm_widget q6afe_dai_widgets[] = {
 	SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_RX", "Slimbus4 Playback", 0, 0, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_RX", "Slimbus5 Playback", 0, 0, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_RX", "Slimbus6 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_0_TX", "Slimbus Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_1_TX", "Slimbus1 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_2_TX", "Slimbus2 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_3_TX", "Slimbus3 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_4_TX", "Slimbus4 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_5_TX", "Slimbus5 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_6_TX", "Slimbus6 Capture", 0, 0, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_MI2S_RX", "Quaternary MI2S Playback",
 						0, 0, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_MI2S_TX", "Quaternary MI2S Capture",
@@ -1180,7 +1335,7 @@ static void of_q6afe_parse_dai_data(struct device *dev,
 		int id, i, num_lines;
 
 		ret = of_property_read_u32(node, "reg", &id);
-		if (ret || id > AFE_PORT_MAX) {
+		if (ret || id < 0 || id >= AFE_PORT_MAX) {
 			dev_err(dev, "valid dai id not found:%d\n", ret);
 			continue;
 		}
@@ -1249,11 +1404,12 @@ static void of_q6afe_parse_dai_data(struct device *dev,
 	}
 }
 
-static int q6afe_dai_bind(struct device *dev, struct device *master, void *data)
+static int q6afe_dai_dev_probe(struct platform_device *pdev)
 {
 	struct q6afe_dai_data *dai_data;
+	struct device *dev = &pdev->dev;
 
-	dai_data = kzalloc(sizeof(*dai_data), GFP_KERNEL);
+	dai_data = devm_kzalloc(dev, sizeof(*dai_data), GFP_KERNEL);
 	if (!dai_data)
 		return -ENOMEM;
 
@@ -1261,41 +1417,22 @@ static int q6afe_dai_bind(struct device *dev, struct device *master, void *data)
 
 	of_q6afe_parse_dai_data(dev, dai_data);
 
-	return snd_soc_register_component(dev, &q6afe_dai_component,
+	return devm_snd_soc_register_component(dev, &q6afe_dai_component,
 					  q6afe_dais, ARRAY_SIZE(q6afe_dais));
 }
 
-static void q6afe_dai_unbind(struct device *dev, struct device *master,
-			     void *data)
-{
-	struct q6afe_dai_data *dai_data = dev_get_drvdata(dev);
-
-	snd_soc_unregister_component(dev);
-	kfree(dai_data);
-}
-
-static const struct component_ops q6afe_dai_comp_ops = {
-	.bind   = q6afe_dai_bind,
-	.unbind = q6afe_dai_unbind,
+static const struct of_device_id q6afe_dai_device_id[] = {
+	{ .compatible = "qcom,q6afe-dais" },
+	{},
 };
-
-static int q6afe_dai_dev_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &q6afe_dai_comp_ops);
-}
-
-static int q6afe_dai_dev_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &q6afe_dai_comp_ops);
-	return 0;
-}
+MODULE_DEVICE_TABLE(of, q6afe_dai_device_id);
 
 static struct platform_driver q6afe_dai_platform_driver = {
 	.driver = {
 		.name = "q6afe-dai",
+		.of_match_table = of_match_ptr(q6afe_dai_device_id),
 	},
 	.probe = q6afe_dai_dev_probe,
-	.remove = q6afe_dai_dev_remove,
 };
 module_platform_driver(q6afe_dai_platform_driver);
 
diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c
index 01f43218984b..000775b4bba8 100644
--- a/sound/soc/qcom/qdsp6/q6afe.c
+++ b/sound/soc/qcom/qdsp6/q6afe.c
@@ -316,7 +316,6 @@ struct q6afe {
 	struct mutex lock;
 	struct list_head port_list;
 	spinlock_t port_list_lock;
-	struct platform_device *pdev_dais;
 };
 
 struct afe_port_cmd_device_start {
@@ -515,6 +514,20 @@ static struct afe_port_map port_maps[AFE_PORT_MAX] = {
 				SLIMBUS_5_RX, 1, 1},
 	[SLIMBUS_6_RX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_RX,
 				SLIMBUS_6_RX, 1, 1},
+	[SLIMBUS_0_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_TX,
+				SLIMBUS_0_TX, 0, 1},
+	[SLIMBUS_1_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_TX,
+				SLIMBUS_1_TX, 0, 1},
+	[SLIMBUS_2_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_TX,
+				SLIMBUS_2_TX, 0, 1},
+	[SLIMBUS_3_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_3_TX,
+				SLIMBUS_3_TX, 0, 1},
+	[SLIMBUS_4_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_4_TX,
+				SLIMBUS_4_TX, 0, 1},
+	[SLIMBUS_5_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_5_TX,
+				SLIMBUS_5_TX, 0, 1},
+	[SLIMBUS_6_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_TX,
+				SLIMBUS_6_TX, 0, 1},
 	[PRIMARY_MI2S_RX] = { AFE_PORT_ID_PRIMARY_MI2S_RX,
 				PRIMARY_MI2S_RX, 1, 1},
 	[PRIMARY_MI2S_TX] = { AFE_PORT_ID_PRIMARY_MI2S_TX,
@@ -777,7 +790,7 @@ static int q6afe_callback(struct apr_device *adev, struct apr_resp_pkt *data)
  */
 int q6afe_get_port_id(int index)
 {
-	if (index < 0 || index > AFE_PORT_MAX)
+	if (index < 0 || index >= AFE_PORT_MAX)
 		return -EINVAL;
 
 	return port_maps[index].port_id;
@@ -1014,7 +1027,7 @@ int q6afe_port_stop(struct q6afe_port *port)
 
 	port_id = port->id;
 	index = port->token;
-	if (index < 0 || index > AFE_PORT_MAX) {
+	if (index < 0 || index >= AFE_PORT_MAX) {
 		dev_err(afe->dev, "AFE port index[%d] invalid!\n", index);
 		return -EINVAL;
 	}
@@ -1355,7 +1368,7 @@ struct q6afe_port *q6afe_port_get_from_id(struct device *dev, int id)
 	unsigned long flags;
 	int cfg_type;
 
-	if (id < 0 || id > AFE_PORT_MAX) {
+	if (id < 0 || id >= AFE_PORT_MAX) {
 		dev_err(dev, "AFE port token[%d] invalid!\n", id);
 		return ERR_PTR(-EINVAL);
 	}
@@ -1373,6 +1386,13 @@ struct q6afe_port *q6afe_port_get_from_id(struct device *dev, int id)
 	case AFE_PORT_ID_MULTICHAN_HDMI_RX:
 		cfg_type = AFE_PARAM_ID_HDMI_CONFIG;
 		break;
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_3_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_4_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_5_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_TX:
 	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_RX:
 	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_RX:
 	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_RX:
@@ -1438,7 +1458,6 @@ static int q6afe_probe(struct apr_device *adev)
 {
 	struct q6afe *afe;
 	struct device *dev = &adev->dev;
-	struct device_node *dais_np;
 
 	afe = devm_kzalloc(dev, sizeof(*afe), GFP_KERNEL);
 	if (!afe)
@@ -1453,22 +1472,12 @@ static int q6afe_probe(struct apr_device *adev)
 
 	dev_set_drvdata(dev, afe);
 
-	dais_np = of_get_child_by_name(dev->of_node, "dais");
-	if (dais_np) {
-		afe->pdev_dais = of_platform_device_create(dais_np,
-							   "q6afe-dai", dev);
-		of_node_put(dais_np);
-	}
-
-	return 0;
+	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
 
 static int q6afe_remove(struct apr_device *adev)
 {
-	struct q6afe *afe = dev_get_drvdata(&adev->dev);
-
-	if (afe->pdev_dais)
-		of_platform_device_destroy(&afe->pdev_dais->dev, NULL);
+	of_platform_depopulate(&adev->dev);
 
 	return 0;
 }
diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c
index 349c6a883c63..9db9a2944ef2 100644
--- a/sound/soc/qcom/qdsp6/q6asm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6asm-dai.c
@@ -7,7 +7,6 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/component.h>
 #include <sound/soc.h>
 #include <sound/soc.h>
 #include <sound/soc-dapm.h>
@@ -390,7 +389,9 @@ static int q6asm_dai_close(struct snd_pcm_substream *substream)
 	struct q6asm_dai_rtd *prtd = runtime->private_data;
 
 	if (prtd->audio_client) {
-		q6asm_cmd(prtd->audio_client, CMD_CLOSE);
+		if (prtd->state)
+			q6asm_cmd(prtd->audio_client, CMD_CLOSE);
+
 		q6asm_unmap_memory_regions(substream->stream,
 					   prtd->audio_client);
 		q6asm_audio_client_free(prtd->audio_client);
@@ -561,14 +562,15 @@ static struct snd_soc_dai_driver q6asm_fe_dais[] = {
 	Q6ASM_FEDAI_DRIVER(8),
 };
 
-static int q6asm_dai_bind(struct device *dev, struct device *master, void *data)
+static int q6asm_dai_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct device_node *node = dev->of_node;
 	struct of_phandle_args args;
 	struct q6asm_dai_data *pdata;
 	int rc;
 
-	pdata = kzalloc(sizeof(struct q6asm_dai_data), GFP_KERNEL);
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return -ENOMEM;
 
@@ -580,43 +582,23 @@ static int q6asm_dai_bind(struct device *dev, struct device *master, void *data)
 
 	dev_set_drvdata(dev, pdata);
 
-	return snd_soc_register_component(dev, &q6asm_fe_dai_component,
+	return devm_snd_soc_register_component(dev, &q6asm_fe_dai_component,
 					q6asm_fe_dais,
 					ARRAY_SIZE(q6asm_fe_dais));
 }
-static void q6asm_dai_unbind(struct device *dev, struct device *master,
-			     void *data)
-{
-	struct q6asm_dai_data *pdata = dev_get_drvdata(dev);
-
-	snd_soc_unregister_component(dev);
-
-	kfree(pdata);
-
-}
 
-static const struct component_ops q6asm_dai_comp_ops = {
-	.bind   = q6asm_dai_bind,
-	.unbind = q6asm_dai_unbind,
+static const struct of_device_id q6asm_dai_device_id[] = {
+	{ .compatible = "qcom,q6asm-dais" },
+	{},
 };
-
-static int q6asm_dai_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &q6asm_dai_comp_ops);
-}
-
-static int q6asm_dai_dev_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &q6asm_dai_comp_ops);
-	return 0;
-}
+MODULE_DEVICE_TABLE(of, q6asm_dai_device_id);
 
 static struct platform_driver q6asm_dai_platform_driver = {
 	.driver = {
 		.name = "q6asm-dai",
+		.of_match_table = of_match_ptr(q6asm_dai_device_id),
 	},
 	.probe = q6asm_dai_probe,
-	.remove = q6asm_dai_dev_remove,
 };
 module_platform_driver(q6asm_dai_platform_driver);
 
diff --git a/sound/soc/qcom/qdsp6/q6asm.c b/sound/soc/qcom/qdsp6/q6asm.c
index 530852385cad..2b2c7233bb5f 100644
--- a/sound/soc/qcom/qdsp6/q6asm.c
+++ b/sound/soc/qcom/qdsp6/q6asm.c
@@ -174,10 +174,8 @@ struct q6asm {
 	struct device *dev;
 	struct q6core_svc_api_info ainfo;
 	wait_queue_head_t mem_wait;
-	struct platform_device *pcmdev;
 	spinlock_t slock;
 	struct audio_client *session[MAX_SESSIONS + 1];
-	struct platform_device *pdev_dais;
 };
 
 struct audio_client {
@@ -1344,7 +1342,6 @@ EXPORT_SYMBOL_GPL(q6asm_cmd_nowait);
 static int q6asm_probe(struct apr_device *adev)
 {
 	struct device *dev = &adev->dev;
-	struct device_node *dais_np;
 	struct q6asm *q6asm;
 
 	q6asm = devm_kzalloc(dev, sizeof(*q6asm), GFP_KERNEL);
@@ -1359,22 +1356,12 @@ static int q6asm_probe(struct apr_device *adev)
 	spin_lock_init(&q6asm->slock);
 	dev_set_drvdata(dev, q6asm);
 
-	dais_np = of_get_child_by_name(dev->of_node, "dais");
-	if (dais_np) {
-		q6asm->pdev_dais = of_platform_device_create(dais_np,
-							   "q6asm-dai", dev);
-		of_node_put(dais_np);
-	}
-
-	return 0;
+	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
 
 static int q6asm_remove(struct apr_device *adev)
 {
-	struct q6asm *q6asm = dev_get_drvdata(&adev->dev);
-
-	if (q6asm->pdev_dais)
-		of_platform_device_destroy(&q6asm->pdev_dais->dev, NULL);
+	of_platform_depopulate(&adev->dev);
 
 	return 0;
 }
diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
index 593f66b8622f..dc94c5c53788 100644
--- a/sound/soc/qcom/qdsp6/q6routing.c
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -8,7 +8,6 @@
 #include <linux/platform_device.h>
 #include <linux/of_platform.h>
 #include <linux/bitops.h>
-#include <linux/component.h>
 #include <linux/mutex.h>
 #include <linux/of_device.h>
 #include <linux/slab.h>
@@ -68,6 +67,13 @@
 	{ mix_name, "SEC_MI2S_TX", "SEC_MI2S_TX" },	\
 	{ mix_name, "QUAT_MI2S_TX", "QUAT_MI2S_TX" },	\
 	{ mix_name, "TERT_MI2S_TX", "TERT_MI2S_TX" },		\
+	{ mix_name, "SLIMBUS_0_TX", "SLIMBUS_0_TX" },		\
+	{ mix_name, "SLIMBUS_1_TX", "SLIMBUS_1_TX" },		\
+	{ mix_name, "SLIMBUS_2_TX", "SLIMBUS_2_TX" },		\
+	{ mix_name, "SLIMBUS_3_TX", "SLIMBUS_3_TX" },		\
+	{ mix_name, "SLIMBUS_4_TX", "SLIMBUS_4_TX" },		\
+	{ mix_name, "SLIMBUS_5_TX", "SLIMBUS_5_TX" },		\
+	{ mix_name, "SLIMBUS_6_TX", "SLIMBUS_6_TX" },		\
 	{ mix_name, "PRIMARY_TDM_TX_0", "PRIMARY_TDM_TX_0"},	\
 	{ mix_name, "PRIMARY_TDM_TX_1", "PRIMARY_TDM_TX_1"},	\
 	{ mix_name, "PRIMARY_TDM_TX_2", "PRIMARY_TDM_TX_2"},	\
@@ -122,6 +128,27 @@
 	SOC_SINGLE_EXT("QUAT_MI2S_TX", QUATERNARY_MI2S_TX,		\
 		id, 1, 0, msm_routing_get_audio_mixer,			\
 		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_0_TX", SLIMBUS_0_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_1_TX", SLIMBUS_1_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_2_TX", SLIMBUS_2_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_3_TX", SLIMBUS_3_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_4_TX", SLIMBUS_4_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_5_TX", SLIMBUS_5_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_6_TX", SLIMBUS_6_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
 	SOC_SINGLE_EXT("PRIMARY_TDM_TX_0", PRIMARY_TDM_TX_0,		\
 		id, 1, 0, msm_routing_get_audio_mixer,			\
 		msm_routing_put_audio_mixer),				\
@@ -310,7 +337,7 @@ int q6routing_stream_open(int fedai_id, int perf_mode,
 			      session->channels, topology, perf_mode,
 			      session->bits_per_sample, 0, 0);
 
-	if (!copp) {
+	if (IS_ERR_OR_NULL(copp)) {
 		mutex_unlock(&routing_data->lock);
 		return -EINVAL;
 	}
@@ -899,7 +926,7 @@ static int routing_hw_params(struct snd_pcm_substream *substream,
 	else
 		path_type = ADM_PATH_LIVE_REC;
 
-	if (be_id > AFE_MAX_PORTS)
+	if (be_id >= AFE_MAX_PORTS)
 		return -EINVAL;
 
 	session = &data->port_data[be_id];
@@ -949,9 +976,10 @@ static const struct snd_soc_component_driver msm_soc_routing_component = {
 	.num_dapm_routes = ARRAY_SIZE(intercon),
 };
 
-static int q6routing_dai_bind(struct device *dev, struct device *master,
-			      void *data)
+static int q6pcm_routing_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
+
 	routing_data = kzalloc(sizeof(*routing_data), GFP_KERNEL);
 	if (!routing_data)
 		return -ENOMEM;
@@ -961,41 +989,28 @@ static int q6routing_dai_bind(struct device *dev, struct device *master,
 	mutex_init(&routing_data->lock);
 	dev_set_drvdata(dev, routing_data);
 
-	return snd_soc_register_component(dev, &msm_soc_routing_component,
+	return devm_snd_soc_register_component(dev, &msm_soc_routing_component,
 					  NULL, 0);
 }
 
-static void q6routing_dai_unbind(struct device *dev, struct device *master,
-				 void *d)
+static int q6pcm_routing_remove(struct platform_device *pdev)
 {
-	struct msm_routing_data *data = dev_get_drvdata(dev);
-
-	snd_soc_unregister_component(dev);
-
-	kfree(data);
-
+	kfree(routing_data);
 	routing_data = NULL;
-}
-
-static const struct component_ops q6routing_dai_comp_ops = {
-	.bind   = q6routing_dai_bind,
-	.unbind = q6routing_dai_unbind,
-};
 
-static int q6pcm_routing_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &q6routing_dai_comp_ops);
-}
-
-static int q6pcm_routing_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &q6routing_dai_comp_ops);
 	return 0;
 }
 
+static const struct of_device_id q6pcm_routing_device_id[] = {
+	{ .compatible = "qcom,q6adm-routing" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, q6pcm_routing_device_id);
+
 static struct platform_driver q6pcm_routing_platform_driver = {
 	.driver = {
 		.name = "q6routing",
+		.of_match_table = of_match_ptr(q6pcm_routing_device_id),
 	},
 	.probe = q6pcm_routing_probe,
 	.remove = q6pcm_routing_remove,
diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
new file mode 100644
index 000000000000..2a781d87ee65
--- /dev/null
+++ b/sound/soc/qcom/sdm845.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include "common.h"
+#include "qdsp6/q6afe.h"
+
+#define DEFAULT_SAMPLE_RATE_48K		48000
+#define DEFAULT_MCLK_RATE		24576000
+#define DEFAULT_BCLK_RATE		12288000
+
+struct sdm845_snd_data {
+	struct snd_soc_card *card;
+	uint32_t pri_mi2s_clk_count;
+	uint32_t quat_tdm_clk_count;
+};
+
+static unsigned int tdm_slot_offset[8] = {0, 4, 8, 12, 16, 20, 24, 28};
+
+static int sdm845_tdm_snd_hw_params(struct snd_pcm_substream *substream,
+					struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+	int ret = 0;
+	int channels, slot_width;
+
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		slot_width = 32;
+		break;
+	default:
+		dev_err(rtd->dev, "%s: invalid param format 0x%x\n",
+				__func__, params_format(params));
+		return -EINVAL;
+	}
+
+	channels = params_channels(params);
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		ret = snd_soc_dai_set_tdm_slot(cpu_dai, 0, 0x3,
+				8, slot_width);
+		if (ret < 0) {
+			dev_err(rtd->dev, "%s: failed to set tdm slot, err:%d\n",
+					__func__, ret);
+			goto end;
+		}
+
+		ret = snd_soc_dai_set_channel_map(cpu_dai, 0, NULL,
+				channels, tdm_slot_offset);
+		if (ret < 0) {
+			dev_err(rtd->dev, "%s: failed to set channel map, err:%d\n",
+					__func__, ret);
+			goto end;
+		}
+	} else {
+		ret = snd_soc_dai_set_tdm_slot(cpu_dai, 0xf, 0,
+				8, slot_width);
+		if (ret < 0) {
+			dev_err(rtd->dev, "%s: failed to set tdm slot, err:%d\n",
+					__func__, ret);
+			goto end;
+		}
+
+		ret = snd_soc_dai_set_channel_map(cpu_dai, channels,
+				tdm_slot_offset, 0, NULL);
+		if (ret < 0) {
+			dev_err(rtd->dev, "%s: failed to set channel map, err:%d\n",
+					__func__, ret);
+			goto end;
+		}
+	}
+end:
+	return ret;
+}
+
+static int sdm845_snd_hw_params(struct snd_pcm_substream *substream,
+					struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+	int ret = 0;
+
+	switch (cpu_dai->id) {
+	case QUATERNARY_TDM_RX_0:
+	case QUATERNARY_TDM_TX_0:
+		ret = sdm845_tdm_snd_hw_params(substream, params);
+		break;
+	default:
+		pr_err("%s: invalid dai id 0x%x\n", __func__, cpu_dai->id);
+		break;
+	}
+	return ret;
+}
+
+static int sdm845_snd_startup(struct snd_pcm_substream *substream)
+{
+	unsigned int fmt = SND_SOC_DAIFMT_CBS_CFS;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct sdm845_snd_data *data = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+
+	switch (cpu_dai->id) {
+	case PRIMARY_MI2S_RX:
+	case PRIMARY_MI2S_TX:
+		if (++(data->pri_mi2s_clk_count) == 1) {
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_MCLK_1,
+				DEFAULT_MCLK_RATE, SNDRV_PCM_STREAM_PLAYBACK);
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_PRI_MI2S_IBIT,
+				DEFAULT_BCLK_RATE, SNDRV_PCM_STREAM_PLAYBACK);
+		}
+		snd_soc_dai_set_fmt(cpu_dai, fmt);
+		break;
+
+	case QUATERNARY_TDM_RX_0:
+	case QUATERNARY_TDM_TX_0:
+		if (++(data->quat_tdm_clk_count) == 1) {
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_QUAD_TDM_IBIT,
+				DEFAULT_BCLK_RATE, SNDRV_PCM_STREAM_PLAYBACK);
+		}
+		break;
+
+	default:
+		pr_err("%s: invalid dai id 0x%x\n", __func__, cpu_dai->id);
+		break;
+	}
+	return 0;
+}
+
+static void  sdm845_snd_shutdown(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct sdm845_snd_data *data = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+
+	switch (cpu_dai->id) {
+	case PRIMARY_MI2S_RX:
+	case PRIMARY_MI2S_TX:
+		if (--(data->pri_mi2s_clk_count) == 0) {
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_MCLK_1,
+				0, SNDRV_PCM_STREAM_PLAYBACK);
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_PRI_MI2S_IBIT,
+				0, SNDRV_PCM_STREAM_PLAYBACK);
+		};
+		break;
+
+	case QUATERNARY_TDM_RX_0:
+	case QUATERNARY_TDM_TX_0:
+		if (--(data->quat_tdm_clk_count) == 0) {
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_QUAD_TDM_IBIT,
+				0, SNDRV_PCM_STREAM_PLAYBACK);
+		}
+		break;
+
+	default:
+		pr_err("%s: invalid dai id 0x%x\n", __func__, cpu_dai->id);
+		break;
+	}
+}
+
+static struct snd_soc_ops sdm845_be_ops = {
+	.hw_params = sdm845_snd_hw_params,
+	.startup = sdm845_snd_startup,
+	.shutdown = sdm845_snd_shutdown,
+};
+
+static int sdm845_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
+				struct snd_pcm_hw_params *params)
+{
+	struct snd_interval *rate = hw_param_interval(params,
+					SNDRV_PCM_HW_PARAM_RATE);
+	struct snd_interval *channels = hw_param_interval(params,
+					SNDRV_PCM_HW_PARAM_CHANNELS);
+	struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
+
+	rate->min = rate->max = DEFAULT_SAMPLE_RATE_48K;
+	channels->min = channels->max = 2;
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE);
+
+	return 0;
+}
+
+static void sdm845_add_be_ops(struct snd_soc_card *card)
+{
+	struct snd_soc_dai_link *link = card->dai_link;
+	int i, num_links = card->num_links;
+
+	for (i = 0; i < num_links; i++) {
+		if (link->no_pcm == 1) {
+			link->ops = &sdm845_be_ops;
+			link->be_hw_params_fixup = sdm845_be_hw_params_fixup;
+		}
+		link++;
+	}
+}
+
+static int sdm845_snd_platform_probe(struct platform_device *pdev)
+{
+	struct snd_soc_card *card;
+	struct sdm845_snd_data *data;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	card = kzalloc(sizeof(*card), GFP_KERNEL);
+	if (!card)
+		return -ENOMEM;
+
+	/* Allocate the private data */
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		ret = -ENOMEM;
+		goto data_alloc_fail;
+	}
+
+	card->dev = dev;
+	dev_set_drvdata(dev, card);
+	ret = qcom_snd_parse_of(card);
+	if (ret) {
+		dev_err(dev, "Error parsing OF data\n");
+		goto parse_dt_fail;
+	}
+
+	data->card = card;
+	snd_soc_card_set_drvdata(card, data);
+
+	sdm845_add_be_ops(card);
+	ret = snd_soc_register_card(card);
+	if (ret) {
+		dev_err(dev, "Sound card registration failed\n");
+		goto register_card_fail;
+	}
+	return ret;
+
+register_card_fail:
+	kfree(card->dai_link);
+parse_dt_fail:
+	kfree(data);
+data_alloc_fail:
+	kfree(card);
+	return ret;
+}
+
+static int sdm845_snd_platform_remove(struct platform_device *pdev)
+{
+	struct snd_soc_card *card = dev_get_drvdata(&pdev->dev);
+	struct sdm845_snd_data *data = snd_soc_card_get_drvdata(card);
+
+	snd_soc_unregister_card(card);
+	kfree(card->dai_link);
+	kfree(data);
+	kfree(card);
+	return 0;
+}
+
+static const struct of_device_id sdm845_snd_device_id[]  = {
+	{ .compatible = "qcom,sdm845-sndcard" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, sdm845_snd_device_id);
+
+static struct platform_driver sdm845_snd_driver = {
+	.probe = sdm845_snd_platform_probe,
+	.remove = sdm845_snd_platform_remove,
+	.driver = {
+		.name = "msm-snd-sdm845",
+		.of_match_table = sdm845_snd_device_id,
+	},
+};
+module_platform_driver(sdm845_snd_driver);
+
+MODULE_DESCRIPTION("sdm845 ASoC Machine Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/rockchip/Makefile b/sound/soc/rockchip/Makefile
index 05b078e7b87f..65e814d46006 100644
--- a/sound/soc/rockchip/Makefile
+++ b/sound/soc/rockchip/Makefile
@@ -1,10 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 # ROCKCHIP Platform Support
 snd-soc-rockchip-i2s-objs := rockchip_i2s.o
+snd-soc-rockchip-pcm-objs := rockchip_pcm.o
 snd-soc-rockchip-pdm-objs := rockchip_pdm.o
 snd-soc-rockchip-spdif-objs := rockchip_spdif.o
 
-obj-$(CONFIG_SND_SOC_ROCKCHIP_I2S) += snd-soc-rockchip-i2s.o
+obj-$(CONFIG_SND_SOC_ROCKCHIP_I2S) += snd-soc-rockchip-i2s.o snd-soc-rockchip-pcm.o
 obj-$(CONFIG_SND_SOC_ROCKCHIP_PDM) += snd-soc-rockchip-pdm.o
 obj-$(CONFIG_SND_SOC_ROCKCHIP_SPDIF) += snd-soc-rockchip-spdif.o
 
diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c
index 950823d69e9c..60d43d53a8f5 100644
--- a/sound/soc/rockchip/rockchip_i2s.c
+++ b/sound/soc/rockchip/rockchip_i2s.c
@@ -22,6 +22,7 @@
 #include <sound/dmaengine_pcm.h>
 
 #include "rockchip_i2s.h"
+#include "rockchip_pcm.h"
 
 #define DRV_NAME "rockchip-i2s"
 
@@ -674,7 +675,7 @@ static int rockchip_i2s_probe(struct platform_device *pdev)
 		goto err_suspend;
 	}
 
-	ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+	ret = rockchip_pcm_platform_register(&pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Could not register PCM\n");
 		return ret;
diff --git a/sound/soc/rockchip/rockchip_pcm.c b/sound/soc/rockchip/rockchip_pcm.c
new file mode 100644
index 000000000000..f77538319221
--- /dev/null
+++ b/sound/soc/rockchip/rockchip_pcm.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright (c) 2018 Rockchip Electronics Co. Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/module.h>
+
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/soc.h>
+#include <sound/dmaengine_pcm.h>
+
+#include "rockchip_pcm.h"
+
+static const struct snd_pcm_hardware snd_rockchip_hardware = {
+	.info			= SNDRV_PCM_INFO_MMAP |
+				  SNDRV_PCM_INFO_MMAP_VALID |
+				  SNDRV_PCM_INFO_PAUSE |
+				  SNDRV_PCM_INFO_RESUME,
+	.period_bytes_min	= 32,
+	.period_bytes_max	= 8192,
+	.periods_min		= 1,
+	.periods_max		= 52,
+	.buffer_bytes_max	= 64 * 1024,
+	.fifo_size		= 32,
+};
+
+static const struct snd_dmaengine_pcm_config rk_dmaengine_pcm_config = {
+	.pcm_hardware = &snd_rockchip_hardware,
+	.prealloc_buffer_size = 32 * 1024,
+};
+
+int rockchip_pcm_platform_register(struct device *dev)
+{
+	return devm_snd_dmaengine_pcm_register(dev, &rk_dmaengine_pcm_config,
+		SND_DMAENGINE_PCM_FLAG_COMPAT);
+}
+EXPORT_SYMBOL_GPL(rockchip_pcm_platform_register);
+
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/rockchip/rockchip_pcm.h b/sound/soc/rockchip/rockchip_pcm.h
new file mode 100644
index 000000000000..d6c36115c60a
--- /dev/null
+++ b/sound/soc/rockchip/rockchip_pcm.h
@@ -0,0 +1,14 @@
+/*
+ * Copyright (c) 2018 Rockchip Electronics Co. Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ROCKCHIP_PCM_H
+#define _ROCKCHIP_PCM_H
+
+int rockchip_pcm_platform_register(struct device *dev);
+
+#endif
diff --git a/sound/soc/rockchip/rockchip_rt5645.c b/sound/soc/rockchip/rockchip_rt5645.c
index 4db4fd56db35..881c32498808 100644
--- a/sound/soc/rockchip/rockchip_rt5645.c
+++ b/sound/soc/rockchip/rockchip_rt5645.c
@@ -181,7 +181,8 @@ static int snd_rk_mc_probe(struct platform_device *pdev)
 	if (!rk_dailink.cpu_of_node) {
 		dev_err(&pdev->dev,
 			"Property 'rockchip,i2s-controller' missing or invalid\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_codec_of_node;
 	}
 
 	rk_dailink.platform_of_node = rk_dailink.cpu_of_node;
@@ -190,17 +191,36 @@ static int snd_rk_mc_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev,
 			"Soc parse card name failed %d\n", ret);
-		return ret;
+		goto put_cpu_of_node;
 	}
 
 	ret = devm_snd_soc_register_card(&pdev->dev, card);
 	if (ret) {
 		dev_err(&pdev->dev,
 			"Soc register card failed %d\n", ret);
-		return ret;
+		goto put_cpu_of_node;
 	}
 
 	return ret;
+
+put_cpu_of_node:
+	of_node_put(rk_dailink.cpu_of_node);
+	rk_dailink.cpu_of_node = NULL;
+put_codec_of_node:
+	of_node_put(rk_dailink.codec_of_node);
+	rk_dailink.codec_of_node = NULL;
+
+	return ret;
+}
+
+static int snd_rk_mc_remove(struct platform_device *pdev)
+{
+	of_node_put(rk_dailink.cpu_of_node);
+	rk_dailink.cpu_of_node = NULL;
+	of_node_put(rk_dailink.codec_of_node);
+	rk_dailink.codec_of_node = NULL;
+
+	return 0;
 }
 
 static const struct of_device_id rockchip_rt5645_of_match[] = {
@@ -212,6 +232,7 @@ MODULE_DEVICE_TABLE(of, rockchip_rt5645_of_match);
 
 static struct platform_driver snd_rk_mc_driver = {
 	.probe = snd_rk_mc_probe,
+	.remove = snd_rk_mc_remove,
 	.driver = {
 		.name = DRV_NAME,
 		.pm = &snd_soc_pm_ops,
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index f914ed45db7d..d6c62aa13041 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -710,6 +710,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream,
 	switch (params_channels(params)) {
 	case 6:
 		val |= MOD_DC2_EN;
+		/* fall through */
 	case 4:
 		val |= MOD_DC1_EN;
 		break;
diff --git a/sound/soc/sh/Kconfig b/sound/soc/sh/Kconfig
index 0ae0800bf3a8..dc20f0f7080a 100644
--- a/sound/soc/sh/Kconfig
+++ b/sound/soc/sh/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 menu "SoC Audio support for Renesas SoCs"
 	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 
diff --git a/sound/soc/sh/dma-sh7760.c b/sound/soc/sh/dma-sh7760.c
index 2dc3b762fdd9..922fb6aa3ed1 100644
--- a/sound/soc/sh/dma-sh7760.c
+++ b/sound/soc/sh/dma-sh7760.c
@@ -1,16 +1,14 @@
-/*
- * SH7760 ("camelot") DMABRG audio DMA unit support
- *
- * Copyright (C) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
- *  licensed under the terms outlined in the file COPYING at the root
- *  of the linux kernel sources.
- *
- * The SH7760 DMABRG provides 4 dma channels (2x rec, 2x play), which
- * trigger an interrupt when one half of the programmed transfer size
- * has been xmitted.
- *
- * FIXME: little-endian only for now
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// SH7760 ("camelot") DMABRG audio DMA unit support
+//
+// Copyright (C) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
+//
+// The SH7760 DMABRG provides 4 dma channels (2x rec, 2x play), which
+// trigger an interrupt when one half of the programmed transfer size
+// has been xmitted.
+//
+// FIXME: little-endian only for now
 
 #include <linux/module.h>
 #include <linux/gfp.h>
@@ -341,6 +339,6 @@ static struct platform_driver sh7760_pcm_driver = {
 
 module_platform_driver(sh7760_pcm_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("SH7760 Audio DMA (DMABRG) driver");
 MODULE_AUTHOR("Manuel Lauss <mano@roarinelk.homelinux.net>");
diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c
index 3bae06dd121f..aa7e902f0c02 100644
--- a/sound/soc/sh/fsi.c
+++ b/sound/soc/sh/fsi.c
@@ -1,16 +1,12 @@
-/*
- * Fifo-attached Serial Interface (FSI) support for SH7724
- *
- * Copyright (C) 2009 Renesas Solutions Corp.
- * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * Based on ssi.c
- * Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Fifo-attached Serial Interface (FSI) support for SH7724
+//
+// Copyright (C) 2009 Renesas Solutions Corp.
+// Kuninori Morimoto <morimoto.kuninori@renesas.com>
+//
+// Based on ssi.c
+// Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
 
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
diff --git a/sound/soc/sh/hac.c b/sound/soc/sh/hac.c
index 624aaf569fef..c2b496398e6b 100644
--- a/sound/soc/sh/hac.c
+++ b/sound/soc/sh/hac.c
@@ -1,13 +1,11 @@
-/*
- * Hitachi Audio Controller (AC97) support for SH7760/SH7780
- *
- * Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
- *  licensed under the terms outlined in the file COPYING at the root
- *  of the linux kernel sources.
- *
- * dont forget to set IPSEL/OMSEL register bits (in your board code) to
- * enable HAC output pins!
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Hitachi Audio Controller (AC97) support for SH7760/SH7780
+//
+// Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
+//
+// dont forget to set IPSEL/OMSEL register bits (in your board code) to
+// enable HAC output pins!
 
 /* BIG FAT FIXME: although the SH7760 has 2 independent AC97 units, only
  * the FIRST can be used since ASoC does not pass any information to the
@@ -343,6 +341,6 @@ static struct platform_driver hac_pcm_driver = {
 
 module_platform_driver(hac_pcm_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("SuperH onchip HAC (AC97) audio driver");
 MODULE_AUTHOR("Manuel Lauss <mano@roarinelk.homelinux.net>");
diff --git a/sound/soc/sh/migor.c b/sound/soc/sh/migor.c
index ecb057ff9fbb..8739c9f60672 100644
--- a/sound/soc/sh/migor.c
+++ b/sound/soc/sh/migor.c
@@ -1,12 +1,8 @@
-/*
- * ALSA SoC driver for Migo-R
- *
- * Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ALSA SoC driver for Migo-R
+//
+// Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
 
 #include <linux/clkdev.h>
 #include <linux/device.h>
diff --git a/sound/soc/sh/rcar/Makefile b/sound/soc/sh/rcar/Makefile
index 9c3d5aed99d1..5d1ff8ef26f9 100644
--- a/sound/soc/sh/rcar/Makefile
+++ b/sound/soc/sh/rcar/Makefile
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
 snd-soc-rcar-objs	:= core.o gen.o dma.o adg.o ssi.o ssiu.o src.o ctu.o mix.o dvc.o cmd.o
 obj-$(CONFIG_SND_SOC_RCAR)	+= snd-soc-rcar.o
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index 4672688cac32..3a3064dda57f 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -1,12 +1,9 @@
-/*
- * Helper routines for R-Car sound ADG.
- *
- *  Copyright (C) 2013  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Helper routines for R-Car sound ADG.
+//
+//  Copyright (C) 2013  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include <linux/clk-provider.h>
 #include "rsnd.h"
 
diff --git a/sound/soc/sh/rcar/cmd.c b/sound/soc/sh/rcar/cmd.c
index 5900fb535a2b..cc191cd5fb82 100644
--- a/sound/soc/sh/rcar/cmd.c
+++ b/sound/soc/sh/rcar/cmd.c
@@ -1,13 +1,10 @@
-/*
- * Renesas R-Car CMD support
- *
- * Copyright (C) 2015 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car CMD support
+//
+// Copyright (C) 2015 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include "rsnd.h"
 
 struct rsnd_cmd {
@@ -89,7 +86,7 @@ static int rsnd_cmd_init(struct rsnd_mod *mod,
 			cmd_case[rsnd_mod_id(src)] << 16;
 	}
 
-	dev_dbg(dev, "ctu/mix path = 0x%08x", data);
+	dev_dbg(dev, "ctu/mix path = 0x%08x\n", data);
 
 	rsnd_mod_write(mod, CMD_ROUTE_SLCT, data);
 	rsnd_mod_write(mod, CMD_BUSIF_MODE, rsnd_get_busif_shift(io, mod) | 1);
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index f237002180c0..f8425d8b44d2 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -1,16 +1,12 @@
-/*
- * Renesas R-Car SRU/SCU/SSIU/SSI support
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * Based on fsi.c
- * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car SRU/SCU/SSIU/SSI support
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// Based on fsi.c
+// Kuninori Morimoto <morimoto.kuninori@renesas.com>
 
 /*
  * Renesas R-Car sound device structure
@@ -552,6 +548,15 @@ struct rsnd_dai *rsnd_rdai_get(struct rsnd_priv *priv, int id)
 	return priv->rdai + id;
 }
 
+static struct snd_soc_dai_driver
+*rsnd_daidrv_get(struct rsnd_priv *priv, int id)
+{
+	if ((id < 0) || (id >= rsnd_rdai_nr(priv)))
+		return NULL;
+
+	return priv->daidrv + id;
+}
+
 #define rsnd_dai_to_priv(dai) snd_soc_dai_get_drvdata(dai)
 static struct rsnd_dai *rsnd_dai_to_rdai(struct snd_soc_dai *dai)
 {
@@ -1037,7 +1042,7 @@ static void __rsnd_dai_probe(struct rsnd_priv *priv,
 	int io_i;
 
 	rdai		= rsnd_rdai_get(priv, dai_i);
-	drv		= priv->daidrv + dai_i;
+	drv		= rsnd_daidrv_get(priv, dai_i);
 	io_playback	= &rdai->playback;
 	io_capture	= &rdai->capture;
 
@@ -1085,6 +1090,12 @@ static void __rsnd_dai_probe(struct rsnd_priv *priv,
 		of_node_put(capture);
 	}
 
+	if (rsnd_ssi_is_pin_sharing(io_capture) ||
+	    rsnd_ssi_is_pin_sharing(io_playback)) {
+		/* should have symmetric_rates if pin sharing */
+		drv->symmetric_rates = 1;
+	}
+
 	dev_dbg(dev, "%s (%s/%s)\n", rdai->name,
 		rsnd_io_to_mod_ssi(io_playback) ? "play"    : " -- ",
 		rsnd_io_to_mod_ssi(io_capture) ? "capture" : "  --   ");
@@ -1606,7 +1617,7 @@ static struct platform_driver rsnd_driver = {
 };
 module_platform_driver(rsnd_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Renesas R-Car audio driver");
 MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
 MODULE_ALIAS("platform:rcar-pcm-audio");
diff --git a/sound/soc/sh/rcar/ctu.c b/sound/soc/sh/rcar/ctu.c
index 83be7d3ae0a8..6a55aa753003 100644
--- a/sound/soc/sh/rcar/ctu.c
+++ b/sound/soc/sh/rcar/ctu.c
@@ -1,12 +1,9 @@
-/*
- * ctu.c
- *
- * Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ctu.c
+//
+// Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include "rsnd.h"
 
 #define CTU_NAME_SIZE	16
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index ef82b94d038b..fe63ef8600d0 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -1,13 +1,10 @@
-/*
- * Renesas R-Car Audio DMAC support
- *
- * Copyright (C) 2015 Renesas Electronics Corp.
- * Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car Audio DMAC support
+//
+// Copyright (C) 2015 Renesas Electronics Corp.
+// Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include <linux/delay.h>
 #include <linux/of_dma.h>
 #include "rsnd.h"
diff --git a/sound/soc/sh/rcar/dvc.c b/sound/soc/sh/rcar/dvc.c
index ca1780e0b830..2b16e0ce6bc5 100644
--- a/sound/soc/sh/rcar/dvc.c
+++ b/sound/soc/sh/rcar/dvc.c
@@ -1,13 +1,9 @@
-/*
- * Renesas R-Car DVC support
- *
- * Copyright (C) 2014 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car DVC support
+//
+// Copyright (C) 2014 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 /*
  * Playback Volume
diff --git a/sound/soc/sh/rcar/gen.c b/sound/soc/sh/rcar/gen.c
index 25642e92dae0..0230301fe078 100644
--- a/sound/soc/sh/rcar/gen.c
+++ b/sound/soc/sh/rcar/gen.c
@@ -1,13 +1,9 @@
-/*
- * Renesas R-Car Gen1 SRU/SSI support
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car Gen1 SRU/SSI support
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 /*
  * #define DEBUG
diff --git a/sound/soc/sh/rcar/mix.c b/sound/soc/sh/rcar/mix.c
index 1881b2de9126..8e3b57eaa708 100644
--- a/sound/soc/sh/rcar/mix.c
+++ b/sound/soc/sh/rcar/mix.c
@@ -1,12 +1,8 @@
-/*
- * mix.c
- *
- * Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// mix.c
+//
+// Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 /*
  *		    CTUn	MIXn
diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h
index 6d7280d2d9be..96d93330b1e1 100644
--- a/sound/soc/sh/rcar/rsnd.h
+++ b/sound/soc/sh/rcar/rsnd.h
@@ -1,13 +1,10 @@
-/*
- * Renesas R-Car
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #ifndef RSND_H
 #define RSND_H
 
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index 6c72d1a81cf5..beccfbac7581 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -1,13 +1,9 @@
-/*
- * Renesas R-Car SRC support
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car SRC support
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 /*
  * you can enable below define if you don't need
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 6e1166ec24a0..8304e4ec9242 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -1,16 +1,12 @@
-/*
- * Renesas R-Car SSIU/SSI support
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * Based on fsi.c
- * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car SSIU/SSI support
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// Based on fsi.c
+// Kuninori Morimoto <morimoto.kuninori@renesas.com>
 
 /*
  * you can enable below define if you don't need
@@ -37,6 +33,7 @@
 #define	CHNL_4		(1 << 22)	/* Channels */
 #define	CHNL_6		(2 << 22)	/* Channels */
 #define	CHNL_8		(3 << 22)	/* Channels */
+#define DWL_MASK	(7 << 19)	/* Data Word Length mask */
 #define	DWL_8		(0 << 19)	/* Data Word Length */
 #define	DWL_16		(1 << 19)	/* Data Word Length */
 #define	DWL_18		(2 << 19)	/* Data Word Length */
@@ -353,21 +350,18 @@ static void rsnd_ssi_config_init(struct rsnd_mod *mod,
 	struct rsnd_dai *rdai = rsnd_io_to_rdai(io);
 	struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
 	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
-	u32 cr_own;
-	u32 cr_mode;
-	u32 wsr;
+	u32 cr_own	= ssi->cr_own;
+	u32 cr_mode	= ssi->cr_mode;
+	u32 wsr		= ssi->wsr;
 	int is_tdm;
 
-	if (rsnd_ssi_is_parent(mod, io))
-		return;
-
 	is_tdm = rsnd_runtime_is_ssi_tdm(io);
 
 	/*
 	 * always use 32bit system word.
 	 * see also rsnd_ssi_master_clk_enable()
 	 */
-	cr_own = FORCE | SWL_32;
+	cr_own |= FORCE | SWL_32;
 
 	if (rdai->bit_clk_inv)
 		cr_own |= SCKP;
@@ -377,9 +371,18 @@ static void rsnd_ssi_config_init(struct rsnd_mod *mod,
 		cr_own |= SDTA;
 	if (rdai->sys_delay)
 		cr_own |= DEL;
+
+	/*
+	 * We shouldn't exchange SWSP after running.
+	 * This means, parent needs to care it.
+	 */
+	if (rsnd_ssi_is_parent(mod, io))
+		goto init_end;
+
 	if (rsnd_io_is_play(io))
 		cr_own |= TRMD;
 
+	cr_own &= ~DWL_MASK;
 	switch (snd_pcm_format_width(runtime->format)) {
 	case 16:
 		cr_own |= DWL_16;
@@ -406,7 +409,7 @@ static void rsnd_ssi_config_init(struct rsnd_mod *mod,
 		wsr	|= WS_MODE;
 		cr_own	|= CHNL_8;
 	}
-
+init_end:
 	ssi->cr_own	= cr_own;
 	ssi->cr_mode	= cr_mode;
 	ssi->wsr	= wsr;
@@ -470,15 +473,18 @@ static int rsnd_ssi_quit(struct rsnd_mod *mod,
 		return -EIO;
 	}
 
-	if (!rsnd_ssi_is_parent(mod, io))
-		ssi->cr_own	= 0;
-
 	rsnd_ssi_master_clk_stop(mod, io);
 
 	rsnd_mod_power_off(mod);
 
 	ssi->usrcnt--;
 
+	if (!ssi->usrcnt) {
+		ssi->cr_own	= 0;
+		ssi->cr_mode	= 0;
+		ssi->wsr	= 0;
+	}
+
 	return 0;
 }
 
@@ -1055,9 +1061,10 @@ struct rsnd_mod *rsnd_ssi_mod_get(struct rsnd_priv *priv, int id)
 
 int __rsnd_ssi_is_pin_sharing(struct rsnd_mod *mod)
 {
-	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
+	if (!mod)
+		return 0;
 
-	return !!(rsnd_flags_has(ssi, RSND_SSI_CLK_PIN_SHARE));
+	return !!(rsnd_flags_has(rsnd_mod_to_ssi(mod), RSND_SSI_CLK_PIN_SHARE));
 }
 
 static u32 *rsnd_ssi_get_status(struct rsnd_dai_stream *io,
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index 47bdba9fc582..016fbf5ac242 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -1,12 +1,9 @@
-/*
- * Renesas R-Car SSIU support
- *
- * Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car SSIU support
+//
+// Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include "rsnd.h"
 
 #define SSIU_NAME "ssiu"
diff --git a/sound/soc/sh/sh7760-ac97.c b/sound/soc/sh/sh7760-ac97.c
index 4a3568a9bf59..4bb4c13cf860 100644
--- a/sound/soc/sh/sh7760-ac97.c
+++ b/sound/soc/sh/sh7760-ac97.c
@@ -1,10 +1,8 @@
-/*
- * Generic AC97 sound support for SH7760
- *
- * (c) 2007 Manuel Lauss
- *
- * Licensed under the GPLv2.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Generic AC97 sound support for SH7760
+//
+// (c) 2007 Manuel Lauss
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -68,6 +66,6 @@ static void __exit sh7760_ac97_exit(void)
 module_init(sh7760_ac97_init);
 module_exit(sh7760_ac97_exit);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Generic SH7760 AC97 sound machine");
 MODULE_AUTHOR("Manuel Lauss <mano@roarinelk.homelinux.net>");
diff --git a/sound/soc/sh/siu.h b/sound/soc/sh/siu.h
index 6088d627c0e4..63a508fdfe78 100644
--- a/sound/soc/sh/siu.h
+++ b/sound/soc/sh/siu.h
@@ -1,23 +1,9 @@
-/*
- * siu.h - ALSA SoC driver for Renesas SH7343, SH7722 SIU peripheral.
- *
- * Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- * Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// siu.h - ALSA SoC driver for Renesas SH7343, SH7722 SIU peripheral.
+//
+// Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+// Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
 
 #ifndef SIU_H
 #define SIU_H
diff --git a/sound/soc/sh/siu_dai.c b/sound/soc/sh/siu_dai.c
index ee2211635e92..f2a386fcd92e 100644
--- a/sound/soc/sh/siu_dai.c
+++ b/sound/soc/sh/siu_dai.c
@@ -1,23 +1,9 @@
-/*
- * siu_dai.c - ALSA SoC driver for Renesas SH7343, SH7722 SIU peripheral.
- *
- * Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- * Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// siu_dai.c - ALSA SoC driver for Renesas SH7343, SH7722 SIU peripheral.
+//
+// Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+// Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
 
 #include <linux/delay.h>
 #include <linux/firmware.h>
diff --git a/sound/soc/sh/siu_pcm.c b/sound/soc/sh/siu_pcm.c
index 172909570ed5..e263757e4a69 100644
--- a/sound/soc/sh/siu_pcm.c
+++ b/sound/soc/sh/siu_pcm.c
@@ -1,23 +1,10 @@
-/*
- * siu_pcm.c - ALSA driver for Renesas SH7343, SH7722 SIU peripheral.
- *
- * Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- * Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// siu_pcm.c - ALSA driver for Renesas SH7343, SH7722 SIU peripheral.
+//
+// Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+// Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
+
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
diff --git a/sound/soc/sh/ssi.c b/sound/soc/sh/ssi.c
index 89ed1b107ac5..8125fa3840b6 100644
--- a/sound/soc/sh/ssi.c
+++ b/sound/soc/sh/ssi.c
@@ -1,14 +1,11 @@
-/*
- * Serial Sound Interface (I2S) support for SH7760/SH7780
- *
- * Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
- *
- *  licensed under the terms outlined in the file COPYING at the root
- *  of the linux kernel sources.
- *
- * dont forget to set IPSEL/OMSEL register bits (in your board code) to
- * enable SSI output pins!
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Serial Sound Interface (I2S) support for SH7760/SH7780
+//
+// Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
+//
+// dont forget to set IPSEL/OMSEL register bits (in your board code) to
+// enable SSI output pins!
 
 /*
  * LIMITATIONS:
@@ -400,6 +397,6 @@ static struct platform_driver sh4_ssi_driver = {
 
 module_platform_driver(sh4_ssi_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("SuperH onchip SSI (I2S) audio driver");
 MODULE_AUTHOR("Manuel Lauss <mano@roarinelk.homelinux.net>");
diff --git a/sound/soc/sirf/sirf-usp.c b/sound/soc/sirf/sirf-usp.c
index 77e7dcf969d0..d70fcd4a1adf 100644
--- a/sound/soc/sirf/sirf-usp.c
+++ b/sound/soc/sirf/sirf-usp.c
@@ -370,10 +370,9 @@ static int sirf_usp_pcm_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, usp);
 
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	base = devm_ioremap(&pdev->dev, mem_res->start,
-		resource_size(mem_res));
-	if (base == NULL)
-		return -ENOMEM;
+	base = devm_ioremap_resource(&pdev->dev, mem_res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 	usp->regmap = devm_regmap_init_mmio(&pdev->dev, base,
 					    &sirf_usp_regmap_config);
 	if (IS_ERR(usp->regmap))
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index 3f424f214bca..c086786e4471 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -1,20 +1,15 @@
-/*
- * soc-ac97.c  --  ALSA SoC Audio Layer AC97 support
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Copyright 2005 Openedhand Ltd.
- * Copyright (C) 2010 Slimlogic Ltd.
- * Copyright (C) 2010 Texas Instruments Inc.
- *
- * Author: Liam Girdwood <lrg@slimlogic.co.uk>
- *         with code, comments and ideas from :-
- *         Richard Purdie <richard@openedhand.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-ac97.c  --  ALSA SoC Audio Layer AC97 support
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Copyright 2005 Openedhand Ltd.
+// Copyright (C) 2010 Slimlogic Ltd.
+// Copyright (C) 2010 Texas Instruments Inc.
+//
+// Author: Liam Girdwood <lrg@slimlogic.co.uk>
+//         with code, comments and ideas from :-
+//         Richard Purdie <richard@openedhand.com>
 
 #include <linux/ctype.h>
 #include <linux/delay.h>
diff --git a/sound/soc/soc-acpi.c b/sound/soc/soc-acpi.c
index 3d7e1ff79139..b8e72b52db30 100644
--- a/sound/soc/soc-acpi.c
+++ b/sound/soc/soc-acpi.c
@@ -1,18 +1,8 @@
-/*
- * soc-apci.c - support for ACPI enumeration.
- *
- * Copyright (c) 2013-15, Intel Corporation.
- *
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// soc-apci.c - support for ACPI enumeration.
+//
+// Copyright (c) 2013-15, Intel Corporation.
 
 #include <sound/soc-acpi.h>
 
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index e095115fa9f9..409d082e80d1 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -1,18 +1,12 @@
-/*
- * soc-compress.c  --  ALSA SoC Compress
- *
- * Copyright (C) 2012 Intel Corp.
- *
- * Authors: Namarta Kohli <namartax.kohli@intel.com>
- *          Ramesh Babu K V <ramesh.babu@linux.intel.com>
- *          Vinod Koul <vinod.koul@linux.intel.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-compress.c  --  ALSA SoC Compress
+//
+// Copyright (C) 2012 Intel Corp.
+//
+// Authors: Namarta Kohli <namartax.kohli@intel.com>
+//          Ramesh Babu K V <ramesh.babu@linux.intel.com>
+//          Vinod Koul <vinod.koul@linux.intel.com>
 
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -146,6 +140,30 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 		stream = SNDRV_PCM_STREAM_CAPTURE;
 
 	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+	fe->dpcm[stream].runtime = fe_substream->runtime;
+
+	ret = dpcm_path_get(fe, stream, &list);
+	if (ret < 0)
+		goto be_err;
+	else if (ret == 0)
+		dev_dbg(fe->dev, "Compress ASoC: %s no valid %s route\n",
+			fe->dai_link->name, stream ? "capture" : "playback");
+	/* calculate valid and active FE <-> BE dpcms */
+	dpcm_process_paths(fe, stream, &list, 1);
+	fe->dpcm[stream].runtime = fe_substream->runtime;
+
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+	ret = dpcm_be_dai_startup(fe, stream);
+	if (ret < 0) {
+		/* clean up all links */
+		list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be)
+			dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
+
+		dpcm_be_disconnect(fe, stream);
+		fe->dpcm[stream].runtime = NULL;
+		goto out;
+	}
 
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->startup) {
 		ret = cpu_dai->driver->cops->startup(cstream, cpu_dai);
@@ -159,7 +177,7 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 
 	ret = soc_compr_components_open(cstream, &component);
 	if (ret < 0)
-		goto machine_err;
+		goto open_err;
 
 	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->startup) {
 		ret = fe->dai_link->compr_ops->startup(cstream);
@@ -170,31 +188,6 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 		}
 	}
 
-	fe->dpcm[stream].runtime = fe_substream->runtime;
-
-	ret = dpcm_path_get(fe, stream, &list);
-	if (ret < 0)
-		goto fe_err;
-	else if (ret == 0)
-		dev_dbg(fe->dev, "Compress ASoC: %s no valid %s route\n",
-			fe->dai_link->name, stream ? "capture" : "playback");
-
-	/* calculate valid and active FE <-> BE dpcms */
-	dpcm_process_paths(fe, stream, &list, 1);
-
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
-
-	ret = dpcm_be_dai_startup(fe, stream);
-	if (ret < 0) {
-		/* clean up all links */
-		list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be)
-			dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
-
-		dpcm_be_disconnect(fe, stream);
-		fe->dpcm[stream].runtime = NULL;
-		goto path_err;
-	}
-
 	dpcm_clear_pending_state(fe, stream);
 	dpcm_path_put(&list);
 
@@ -207,17 +200,14 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 
 	return 0;
 
-path_err:
-	dpcm_path_put(&list);
-fe_err:
-	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
-		fe->dai_link->compr_ops->shutdown(cstream);
 machine_err:
 	soc_compr_components_free(cstream, component);
-
+open_err:
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->shutdown)
 		cpu_dai->driver->cops->shutdown(cstream, cpu_dai);
 out:
+	dpcm_path_put(&list);
+be_err:
 	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
 	mutex_unlock(&fe->card->mutex);
 	return ret;
@@ -557,6 +547,24 @@ static int soc_compr_set_params_fe(struct snd_compr_stream *cstream,
 
 	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
 
+	/*
+	 * Create an empty hw_params for the BE as the machine driver must
+	 * fix this up to match DSP decoder and ASRC configuration.
+	 * I.e. machine driver fixup for compressed BE is mandatory.
+	 */
+	memset(&fe->dpcm[fe_substream->stream].hw_params, 0,
+		sizeof(struct snd_pcm_hw_params));
+
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+	ret = dpcm_be_dai_hw_params(fe, stream);
+	if (ret < 0)
+		goto out;
+
+	ret = dpcm_be_dai_prepare(fe, stream);
+	if (ret < 0)
+		goto out;
+
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->set_params) {
 		ret = cpu_dai->driver->cops->set_params(cstream, params, cpu_dai);
 		if (ret < 0)
@@ -583,24 +591,6 @@ static int soc_compr_set_params_fe(struct snd_compr_stream *cstream,
 			goto out;
 	}
 
-	/*
-	 * Create an empty hw_params for the BE as the machine driver must
-	 * fix this up to match DSP decoder and ASRC configuration.
-	 * I.e. machine driver fixup for compressed BE is mandatory.
-	 */
-	memset(&fe->dpcm[fe_substream->stream].hw_params, 0,
-		sizeof(struct snd_pcm_hw_params));
-
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
-
-	ret = dpcm_be_dai_hw_params(fe, stream);
-	if (ret < 0)
-		goto out;
-
-	ret = dpcm_be_dai_prepare(fe, stream);
-	if (ret < 0)
-		goto out;
-
 	dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_START);
 	fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PREPARE;
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 4663de3cf495..9cfe10d8040c 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1,26 +1,21 @@
-/*
- * soc-core.c  --  ALSA SoC Audio Layer
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Copyright 2005 Openedhand Ltd.
- * Copyright (C) 2010 Slimlogic Ltd.
- * Copyright (C) 2010 Texas Instruments Inc.
- *
- * Author: Liam Girdwood <lrg@slimlogic.co.uk>
- *         with code, comments and ideas from :-
- *         Richard Purdie <richard@openedhand.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- *  TODO:
- *   o Add hw rules to enforce rates, etc.
- *   o More testing with other codecs/machines.
- *   o Add more codecs and platforms to ensure good API coverage.
- *   o Support TDM on PCM and I2S
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-core.c  --  ALSA SoC Audio Layer
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Copyright 2005 Openedhand Ltd.
+// Copyright (C) 2010 Slimlogic Ltd.
+// Copyright (C) 2010 Texas Instruments Inc.
+//
+// Author: Liam Girdwood <lrg@slimlogic.co.uk>
+//         with code, comments and ideas from :-
+//         Richard Purdie <richard@openedhand.com>
+//
+//  TODO:
+//   o Add hw rules to enforce rates, etc.
+//   o More testing with other codecs/machines.
+//   o Add more codecs and platforms to ensure good API coverage.
+//   o Support TDM on PCM and I2S
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -533,6 +528,7 @@ int snd_soc_suspend(struct device *dev)
 						"ASoC: idle_bias_off CODEC on over suspend\n");
 					break;
 				}
+				/* fall through */
 
 			case SND_SOC_BIAS_OFF:
 				if (component->driver->suspend)
@@ -852,6 +848,9 @@ static int soc_bind_dai_link(struct snd_soc_card *card,
 	const char *platform_name;
 	int i;
 
+	if (dai_link->ignore)
+		return 0;
+
 	dev_dbg(card->dev, "ASoC: binding %s\n", dai_link->name);
 
 	if (soc_is_dai_link_bound(card, dai_link)) {
@@ -1195,15 +1194,27 @@ void snd_soc_remove_dai_link(struct snd_soc_card *card,
 }
 EXPORT_SYMBOL_GPL(snd_soc_remove_dai_link);
 
+static void soc_set_of_name_prefix(struct snd_soc_component *component)
+{
+	struct device_node *component_of_node = component->dev->of_node;
+	const char *str;
+	int ret;
+
+	if (!component_of_node && component->dev->parent)
+		component_of_node = component->dev->parent->of_node;
+
+	ret = of_property_read_string(component_of_node, "sound-name-prefix",
+				      &str);
+	if (!ret)
+		component->name_prefix = str;
+}
+
 static void soc_set_name_prefix(struct snd_soc_card *card,
 				struct snd_soc_component *component)
 {
 	int i;
 
-	if (card->codec_conf == NULL)
-		return;
-
-	for (i = 0; i < card->num_configs; i++) {
+	for (i = 0; i < card->num_configs && card->codec_conf; i++) {
 		struct snd_soc_codec_conf *map = &card->codec_conf[i];
 		struct device_node *component_of_node = component->dev->of_node;
 
@@ -1215,8 +1226,14 @@ static void soc_set_name_prefix(struct snd_soc_card *card,
 		if (map->dev_name && strcmp(component->name, map->dev_name))
 			continue;
 		component->name_prefix = map->name_prefix;
-		break;
+		return;
 	}
+
+	/*
+	 * If there is no configuration table or no match in the table,
+	 * check if a prefix is provided in the node
+	 */
+	soc_set_of_name_prefix(component);
 }
 
 static int soc_probe_component(struct snd_soc_card *card,
@@ -1461,7 +1478,9 @@ static int soc_probe_link_dais(struct snd_soc_card *card,
 {
 	struct snd_soc_dai_link *dai_link = rtd->dai_link;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	int i, ret;
+	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_component *component;
+	int i, ret, num;
 
 	dev_dbg(card->dev, "ASoC: probe %s dai link %d late %d\n",
 			card->name, rtd->num, order);
@@ -1507,9 +1526,28 @@ static int soc_probe_link_dais(struct snd_soc_card *card,
 		soc_dpcm_debugfs_add(rtd);
 #endif
 
+	num = rtd->num;
+
+	/*
+	 * most drivers will register their PCMs using DAI link ordering but
+	 * topology based drivers can use the DAI link id field to set PCM
+	 * device number and then use rtd + a base offset of the BEs.
+	 */
+	for_each_rtdcom(rtd, rtdcom) {
+		component = rtdcom->component;
+
+		if (!component->driver->use_dai_pcm_id)
+			continue;
+
+		if (rtd->dai_link->no_pcm)
+			num += component->driver->be_pcm_base;
+		else
+			num = rtd->dai_link->id;
+	}
+
 	if (cpu_dai->driver->compress_new) {
 		/*create compress_device"*/
-		ret = cpu_dai->driver->compress_new(rtd, rtd->num);
+		ret = cpu_dai->driver->compress_new(rtd, num);
 		if (ret < 0) {
 			dev_err(card->dev, "ASoC: can't create compress %s\n",
 					 dai_link->stream_name);
@@ -1519,7 +1557,7 @@ static int soc_probe_link_dais(struct snd_soc_card *card,
 
 		if (!dai_link->params) {
 			/* create the pcm */
-			ret = soc_new_pcm(rtd, rtd->num);
+			ret = soc_new_pcm(rtd, num);
 			if (ret < 0) {
 				dev_err(card->dev, "ASoC: can't create pcm %s :%d\n",
 				       dai_link->stream_name, ret);
@@ -1846,6 +1884,74 @@ int snd_soc_set_dmi_name(struct snd_soc_card *card, const char *flavour)
 EXPORT_SYMBOL_GPL(snd_soc_set_dmi_name);
 #endif /* CONFIG_DMI */
 
+static void soc_check_tplg_fes(struct snd_soc_card *card)
+{
+	struct snd_soc_component *component;
+	const struct snd_soc_component_driver *comp_drv;
+	struct snd_soc_dai_link *dai_link;
+	int i;
+
+	list_for_each_entry(component, &component_list, list) {
+
+		/* does this component override FEs ? */
+		if (!component->driver->ignore_machine)
+			continue;
+
+		/* for this machine ? */
+		if (strcmp(component->driver->ignore_machine,
+			   card->dev->driver->name))
+			continue;
+
+		/* machine matches, so override the rtd data */
+		for (i = 0; i < card->num_links; i++) {
+
+			dai_link = &card->dai_link[i];
+
+			/* ignore this FE */
+			if (dai_link->dynamic) {
+				dai_link->ignore = true;
+				continue;
+			}
+
+			dev_info(card->dev, "info: override FE DAI link %s\n",
+				 card->dai_link[i].name);
+
+			/* override platform component */
+			dai_link->platform_name = component->name;
+
+			/* convert non BE into BE */
+			dai_link->no_pcm = 1;
+
+			/* override any BE fixups */
+			dai_link->be_hw_params_fixup =
+				component->driver->be_hw_params_fixup;
+
+			/* most BE links don't set stream name, so set it to
+			 * dai link name if it's NULL to help bind widgets.
+			 */
+			if (!dai_link->stream_name)
+				dai_link->stream_name = dai_link->name;
+		}
+
+		/* Inform userspace we are using alternate topology */
+		if (component->driver->topology_name_prefix) {
+
+			/* topology shortname created ? */
+			if (!card->topology_shortname_created) {
+				comp_drv = component->driver;
+
+				snprintf(card->topology_shortname, 32, "%s-%s",
+					 comp_drv->topology_name_prefix,
+					 card->name);
+				card->topology_shortname_created = true;
+			}
+
+			/* use topology shortname */
+			card->name = card->topology_shortname;
+		}
+	}
+}
+
 static int snd_soc_instantiate_card(struct snd_soc_card *card)
 {
 	struct snd_soc_pcm_runtime *rtd;
@@ -1855,6 +1961,9 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 	mutex_lock(&client_mutex);
 	mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_INIT);
 
+	/* check whether any platform is ignore machine FE and using topology */
+	soc_check_tplg_fes(card);
+
 	/* bind DAIs */
 	for (i = 0; i < card->num_links; i++) {
 		ret = soc_bind_dai_link(card, &card->dai_link[i]);
@@ -2523,6 +2632,28 @@ int snd_soc_dai_set_channel_map(struct snd_soc_dai *dai,
 EXPORT_SYMBOL_GPL(snd_soc_dai_set_channel_map);
 
 /**
+ * snd_soc_dai_get_channel_map - Get DAI audio channel map
+ * @dai: DAI
+ * @tx_num: how many TX channels
+ * @tx_slot: pointer to an array which imply the TX slot number channel
+ *           0~num-1 uses
+ * @rx_num: how many RX channels
+ * @rx_slot: pointer to an array which imply the RX slot number channel
+ *           0~num-1 uses
+ */
+int snd_soc_dai_get_channel_map(struct snd_soc_dai *dai,
+	unsigned int *tx_num, unsigned int *tx_slot,
+	unsigned int *rx_num, unsigned int *rx_slot)
+{
+	if (dai->driver->ops->get_channel_map)
+		return dai->driver->ops->get_channel_map(dai, tx_num, tx_slot,
+			rx_num, rx_slot);
+	else
+		return -ENOTSUPP;
+}
+EXPORT_SYMBOL_GPL(snd_soc_dai_get_channel_map);
+
+/**
  * snd_soc_dai_set_tristate - configure DAI system or master clock.
  * @dai: DAI
  * @tristate: tristate enable
@@ -3258,9 +3389,9 @@ int snd_soc_of_parse_audio_simple_widgets(struct snd_soc_card *card,
 }
 EXPORT_SYMBOL_GPL(snd_soc_of_parse_audio_simple_widgets);
 
-static int snd_soc_of_get_slot_mask(struct device_node *np,
-				    const char *prop_name,
-				    unsigned int *mask)
+int snd_soc_of_get_slot_mask(struct device_node *np,
+			     const char *prop_name,
+			     unsigned int *mask)
 {
 	u32 val;
 	const __be32 *of_slot_mask = of_get_property(np, prop_name, &val);
@@ -3275,6 +3406,7 @@ static int snd_soc_of_get_slot_mask(struct device_node *np,
 
 	return val;
 }
+EXPORT_SYMBOL_GPL(snd_soc_of_get_slot_mask);
 
 int snd_soc_of_parse_tdm_slot(struct device_node *np,
 			      unsigned int *tx_mask,
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 229c12349803..7e96793050c9 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1,27 +1,21 @@
-/*
- * soc-dapm.c  --  ALSA SoC Dynamic Audio Power Management
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Author: Liam Girdwood <lrg@slimlogic.co.uk>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- *  Features:
- *    o Changes power status of internal codec blocks depending on the
- *      dynamic configuration of codec internal audio paths and active
- *      DACs/ADCs.
- *    o Platform power domain - can support external components i.e. amps and
- *      mic/headphone insertion events.
- *    o Automatic Mic Bias support
- *    o Jack insertion power event initiation - e.g. hp insertion will enable
- *      sinks, dacs, etc
- *    o Delayed power down of audio subsystem to reduce pops between a quick
- *      device reopen.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-dapm.c  --  ALSA SoC Dynamic Audio Power Management
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Author: Liam Girdwood <lrg@slimlogic.co.uk>
+//
+//  Features:
+//    o Changes power status of internal codec blocks depending on the
+//      dynamic configuration of codec internal audio paths and active
+//      DACs/ADCs.
+//    o Platform power domain - can support external components i.e. amps and
+//      mic/headphone insertion events.
+//    o Automatic Mic Bias support
+//    o Jack insertion power event initiation - e.g. hp insertion will enable
+//      sinks, dacs, etc
+//    o Delayed power down of audio subsystem to reduce pops between a quick
+//      device reopen.
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -3662,7 +3656,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w,
 	struct snd_pcm_substream substream;
 	struct snd_pcm_hw_params *params = NULL;
 	struct snd_pcm_runtime *runtime = NULL;
-	u64 fmt;
+	unsigned int fmt;
 	int ret;
 
 	if (WARN_ON(!config) ||
@@ -4073,6 +4067,13 @@ int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card)
 			continue;
 		}
 
+		/* let users know there is no DAI to link */
+		if (!dai_w->priv) {
+			dev_dbg(card->dev, "dai widget %s has no DAI\n",
+				dai_w->name);
+			continue;
+		}
+
 		dai = dai_w->priv;
 
 		/* ...find all widgets with the same stream and link them */
diff --git a/sound/soc/soc-devres.c b/sound/soc/soc-devres.c
index 7ac745df1412..a9ea172a66a7 100644
--- a/sound/soc/soc-devres.c
+++ b/sound/soc/soc-devres.c
@@ -1,13 +1,8 @@
-/*
- * soc-devres.c  --  ALSA SoC Audio Layer devres functions
- *
- * Copyright (C) 2013 Linaro Ltd
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-devres.c  --  ALSA SoC Audio Layer devres functions
+//
+// Copyright (C) 2013 Linaro Ltd
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index 56a541b9ff9e..52fd7af952a5 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -1,17 +1,8 @@
-/*
- *  Copyright (C) 2013, Analog Devices Inc.
- *	Author: Lars-Peter Clausen <lars@metafoo.de>
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under  the terms of the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the License, or (at your
- *  option) any later version.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+//  Copyright (C) 2013, Analog Devices Inc.
+//	Author: Lars-Peter Clausen <lars@metafoo.de>
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/dmaengine.h>
@@ -197,7 +188,7 @@ static int dmaengine_pcm_set_runtime_hwparams(struct snd_pcm_substream *substrea
 			case 32:
 			case 64:
 				if (addr_widths & (1 << (bits / 8)))
-					hw.formats |= (1LL << i);
+					hw.formats |= pcm_format_to_bits(i);
 				break;
 			default:
 				/* Unsupported types */
@@ -343,7 +334,7 @@ static snd_pcm_uframes_t dmaengine_pcm_pointer(
 
 static int dmaengine_copy_user(struct snd_pcm_substream *substream,
 			       int channel, unsigned long hwoff,
-			       void *buf, unsigned long bytes)
+			       void __user *buf, unsigned long bytes)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_component *component =
@@ -359,18 +350,17 @@ static int dmaengine_copy_user(struct snd_pcm_substream *substream,
 	int ret;
 
 	if (is_playback)
-		if (copy_from_user(dma_ptr, (void __user *)buf, bytes))
+		if (copy_from_user(dma_ptr, buf, bytes))
 			return -EFAULT;
 
 	if (process) {
-		ret = process(substream, channel, hwoff,
-			      (void __user *)buf, bytes);
+		ret = process(substream, channel, hwoff, (__force void *)buf, bytes);
 		if (ret < 0)
 			return ret;
 	}
 
 	if (!is_playback)
-		if (copy_to_user((void __user *)buf, dma_ptr, bytes))
+		if (copy_to_user(buf, dma_ptr, bytes))
 			return -EFAULT;
 
 	return 0;
diff --git a/sound/soc/soc-io.c b/sound/soc/soc-io.c
index 026cd5347e53..1ff9175e9d5e 100644
--- a/sound/soc/soc-io.c
+++ b/sound/soc/soc-io.c
@@ -1,15 +1,10 @@
-/*
- * soc-io.c  --  ASoC register I/O helpers
- *
- * Copyright 2009-2011 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-io.c  --  ASoC register I/O helpers
+//
+// Copyright 2009-2011 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/i2c.h>
 #include <linux/spi/spi.h>
diff --git a/sound/soc/soc-jack.c b/sound/soc/soc-jack.c
index b2b16044ae80..c7b990abdbaa 100644
--- a/sound/soc/soc-jack.c
+++ b/sound/soc/soc-jack.c
@@ -1,15 +1,10 @@
-/*
- * soc-jack.c  --  ALSA SoC jack handling
- *
- * Copyright 2008 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-jack.c  --  ALSA SoC jack handling
+//
+// Copyright 2008 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <sound/jack.h>
 #include <sound/soc.h>
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index 7144a51ddfa9..592efb370c44 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -1,20 +1,15 @@
-/*
- * soc-ops.c  --  Generic ASoC operations
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Copyright 2005 Openedhand Ltd.
- * Copyright (C) 2010 Slimlogic Ltd.
- * Copyright (C) 2010 Texas Instruments Inc.
- *
- * Author: Liam Girdwood <lrg@slimlogic.co.uk>
- *         with code, comments and ideas from :-
- *         Richard Purdie <richard@openedhand.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-ops.c  --  Generic ASoC operations
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Copyright 2005 Openedhand Ltd.
+// Copyright (C) 2010 Slimlogic Ltd.
+// Copyright (C) 2010 Texas Instruments Inc.
+//
+// Author: Liam Girdwood <lrg@slimlogic.co.uk>
+//         with code, comments and ideas from :-
+//         Richard Purdie <richard@openedhand.com>
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 5e7ae47a9658..e8b98bfd4cf1 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1,20 +1,14 @@
-/*
- * soc-pcm.c  --  ALSA SoC PCM
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Copyright 2005 Openedhand Ltd.
- * Copyright (C) 2010 Slimlogic Ltd.
- * Copyright (C) 2010 Texas Instruments Inc.
- *
- * Authors: Liam Girdwood <lrg@ti.com>
- *          Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-pcm.c  --  ALSA SoC PCM
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Copyright 2005 Openedhand Ltd.
+// Copyright (C) 2010 Slimlogic Ltd.
+// Copyright (C) 2010 Texas Instruments Inc.
+//
+// Authors: Liam Girdwood <lrg@ti.com>
+//          Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -448,6 +442,29 @@ static void soc_pcm_init_runtime_hw(struct snd_pcm_substream *substream)
 	hw->rate_max = min_not_zero(hw->rate_max, rate_max);
 }
 
+static int soc_pcm_components_close(struct snd_pcm_substream *substream,
+				    struct snd_soc_component *last)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_component *component;
+
+	for_each_rtdcom(rtd, rtdcom) {
+		component = rtdcom->component;
+
+		if (component == last)
+			break;
+
+		if (!component->driver->ops ||
+		    !component->driver->ops->close)
+			continue;
+
+		component->driver->ops->close(substream);
+	}
+
+	return 0;
+}
+
 /*
  * Called by ALSA when a PCM substream is opened, the runtime->hw record is
  * then initialized and any private data can be allocated. This also calls
@@ -462,7 +479,7 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_dai *codec_dai;
 	const char *codec_dai_name = "multicodec";
-	int i, ret = 0, __ret;
+	int i, ret = 0;
 
 	pinctrl_pm_select_default_state(cpu_dai->dev);
 	for (i = 0; i < rtd->num_codecs; i++)
@@ -486,7 +503,6 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 		}
 	}
 
-	ret = 0;
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
@@ -494,16 +510,15 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 		    !component->driver->ops->open)
 			continue;
 
-		__ret = component->driver->ops->open(substream);
-		if (__ret < 0) {
+		ret = component->driver->ops->open(substream);
+		if (ret < 0) {
 			dev_err(component->dev,
 				"ASoC: can't open component %s: %d\n",
-				component->name, __ret);
-			ret = __ret;
+				component->name, ret);
+			goto component_err;
 		}
 	}
-	if (ret < 0)
-		goto component_err;
+	component = NULL;
 
 	for (i = 0; i < rtd->num_codecs; i++) {
 		codec_dai = rtd->codec_dais[i];
@@ -612,15 +627,7 @@ codec_dai_err:
 	}
 
 component_err:
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (!component->driver->ops ||
-		    !component->driver->ops->close)
-			continue;
-
-		component->driver->ops->close(substream);
-	}
+	soc_pcm_components_close(substream, component);
 
 	if (cpu_dai->driver->ops->shutdown)
 		cpu_dai->driver->ops->shutdown(substream, cpu_dai);
@@ -714,15 +721,7 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 	if (rtd->dai_link->ops->shutdown)
 		rtd->dai_link->ops->shutdown(substream);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (!component->driver->ops ||
-		    !component->driver->ops->close)
-			continue;
-
-		component->driver->ops->close(substream);
-	}
+	soc_pcm_components_close(substream, NULL);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		if (snd_soc_runtime_ignore_pmdown_time(rtd)) {
@@ -860,8 +859,20 @@ int soc_dai_hw_params(struct snd_pcm_substream *substream,
 		      struct snd_pcm_hw_params *params,
 		      struct snd_soc_dai *dai)
 {
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	int ret;
 
+	/* perform any topology hw_params fixups before DAI  */
+	if (rtd->dai_link->be_hw_params_fixup) {
+		ret = rtd->dai_link->be_hw_params_fixup(rtd, params);
+		if (ret < 0) {
+			dev_err(rtd->dev,
+				"ASoC: hw_params topology fixup failed %d\n",
+				ret);
+			return ret;
+		}
+	}
+
 	if (dai->driver->ops->hw_params) {
 		ret = dai->driver->ops->hw_params(substream, params, dai);
 		if (ret < 0) {
@@ -874,6 +885,29 @@ int soc_dai_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
+static int soc_pcm_components_hw_free(struct snd_pcm_substream *substream,
+				      struct snd_soc_component *last)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_component *component;
+
+	for_each_rtdcom(rtd, rtdcom) {
+		component = rtdcom->component;
+
+		if (component == last)
+			break;
+
+		if (!component->driver->ops ||
+		    !component->driver->ops->hw_free)
+			continue;
+
+		component->driver->ops->hw_free(substream);
+	}
+
+	return 0;
+}
+
 /*
  * Called by ALSA when the hardware params are set by application. This
  * function can also be called multiple times and can allocate buffers
@@ -886,7 +920,7 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	int i, ret = 0, __ret;
+	int i, ret = 0;
 
 	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
 	if (rtd->dai_link->ops->hw_params) {
@@ -944,7 +978,6 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 	if (ret < 0)
 		goto interface_err;
 
-	ret = 0;
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
@@ -952,16 +985,15 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 		    !component->driver->ops->hw_params)
 			continue;
 
-		__ret = component->driver->ops->hw_params(substream, params);
-		if (__ret < 0) {
+		ret = component->driver->ops->hw_params(substream, params);
+		if (ret < 0) {
 			dev_err(component->dev,
 				"ASoC: %s hw params failed: %d\n",
-				component->name, __ret);
-			ret = __ret;
+				component->name, ret);
+			goto component_err;
 		}
 	}
-	if (ret < 0)
-		goto component_err;
+	component = NULL;
 
 	/* store the parameters for each DAIs */
 	cpu_dai->rate = params_rate(params);
@@ -977,15 +1009,7 @@ out:
 	return ret;
 
 component_err:
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (!component->driver->ops ||
-		    !component->driver->ops->hw_free)
-			continue;
-
-		component->driver->ops->hw_free(substream);
-	}
+	soc_pcm_components_hw_free(substream, component);
 
 	if (cpu_dai->driver->ops->hw_free)
 		cpu_dai->driver->ops->hw_free(substream, cpu_dai);
@@ -1014,8 +1038,6 @@ codec_err:
 static int soc_pcm_hw_free(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component;
-	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_dai *codec_dai;
 	bool playback = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
@@ -1052,15 +1074,7 @@ static int soc_pcm_hw_free(struct snd_pcm_substream *substream)
 		rtd->dai_link->ops->hw_free(substream);
 
 	/* free any component resources */
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (!component->driver->ops ||
-		    !component->driver->ops->hw_free)
-			continue;
-
-		component->driver->ops->hw_free(substream);
-	}
+	soc_pcm_components_hw_free(substream, NULL);
 
 	/* now free hw params for the DAIs  */
 	for (i = 0; i < rtd->num_codecs; i++) {
@@ -1165,6 +1179,9 @@ static snd_pcm_uframes_t soc_pcm_pointer(struct snd_pcm_substream *substream)
 	snd_pcm_sframes_t codec_delay = 0;
 	int i;
 
+	/* clearing the previous total delay */
+	runtime->delay = 0;
+
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
@@ -1176,6 +1193,8 @@ static snd_pcm_uframes_t soc_pcm_pointer(struct snd_pcm_substream *substream)
 		offset = component->driver->ops->pointer(substream);
 		break;
 	}
+	/* base delay if assigned in pointer callback */
+	delay = runtime->delay;
 
 	if (cpu_dai->driver->ops->delay)
 		delay += cpu_dai->driver->ops->delay(substream, cpu_dai);
@@ -1658,29 +1677,28 @@ unwind:
 }
 
 static void dpcm_init_runtime_hw(struct snd_pcm_runtime *runtime,
-				 struct snd_soc_pcm_stream *stream,
-				 u64 formats)
+				 struct snd_soc_pcm_stream *stream)
 {
 	runtime->hw.rate_min = stream->rate_min;
 	runtime->hw.rate_max = stream->rate_max;
 	runtime->hw.channels_min = stream->channels_min;
 	runtime->hw.channels_max = stream->channels_max;
 	if (runtime->hw.formats)
-		runtime->hw.formats &= formats & stream->formats;
+		runtime->hw.formats &= stream->formats;
 	else
-		runtime->hw.formats = formats & stream->formats;
+		runtime->hw.formats = stream->formats;
 	runtime->hw.rates = stream->rates;
 }
 
-static u64 dpcm_runtime_base_format(struct snd_pcm_substream *substream)
+static void dpcm_runtime_merge_format(struct snd_pcm_substream *substream,
+				      u64 *formats)
 {
 	struct snd_soc_pcm_runtime *fe = substream->private_data;
 	struct snd_soc_dpcm *dpcm;
-	u64 formats = ULLONG_MAX;
 	int stream = substream->stream;
 
 	if (!fe->dai_link->dpcm_merged_format)
-		return formats;
+		return;
 
 	/*
 	 * It returns merged BE codec format
@@ -1694,17 +1712,132 @@ static u64 dpcm_runtime_base_format(struct snd_pcm_substream *substream)
 		int i;
 
 		for (i = 0; i < be->num_codecs; i++) {
+			/*
+			 * Skip CODECs which don't support the current stream
+			 * type. See soc_pcm_init_runtime_hw() for more details
+			 */
+			if (!snd_soc_dai_stream_valid(be->codec_dais[i],
+						      stream))
+				continue;
+
 			codec_dai_drv = be->codec_dais[i]->driver;
 			if (stream == SNDRV_PCM_STREAM_PLAYBACK)
 				codec_stream = &codec_dai_drv->playback;
 			else
 				codec_stream = &codec_dai_drv->capture;
 
-			formats &= codec_stream->formats;
+			*formats &= codec_stream->formats;
 		}
 	}
+}
+
+static void dpcm_runtime_merge_chan(struct snd_pcm_substream *substream,
+				    unsigned int *channels_min,
+				    unsigned int *channels_max)
+{
+	struct snd_soc_pcm_runtime *fe = substream->private_data;
+	struct snd_soc_dpcm *dpcm;
+	int stream = substream->stream;
 
-	return formats;
+	if (!fe->dai_link->dpcm_merged_chan)
+		return;
+
+	/*
+	 * It returns merged BE codec channel;
+	 * if FE want to use it (= dpcm_merged_chan)
+	 */
+
+	list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be) {
+		struct snd_soc_pcm_runtime *be = dpcm->be;
+		struct snd_soc_dai_driver *cpu_dai_drv =  be->cpu_dai->driver;
+		struct snd_soc_dai_driver *codec_dai_drv;
+		struct snd_soc_pcm_stream *codec_stream;
+		struct snd_soc_pcm_stream *cpu_stream;
+
+		if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+			cpu_stream = &cpu_dai_drv->playback;
+		else
+			cpu_stream = &cpu_dai_drv->capture;
+
+		*channels_min = max(*channels_min, cpu_stream->channels_min);
+		*channels_max = min(*channels_max, cpu_stream->channels_max);
+
+		/*
+		 * chan min/max cannot be enforced if there are multiple CODEC
+		 * DAIs connected to a single CPU DAI, use CPU DAI's directly
+		 */
+		if (be->num_codecs == 1) {
+			codec_dai_drv = be->codec_dais[0]->driver;
+
+			if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+				codec_stream = &codec_dai_drv->playback;
+			else
+				codec_stream = &codec_dai_drv->capture;
+
+			*channels_min = max(*channels_min,
+					    codec_stream->channels_min);
+			*channels_max = min(*channels_max,
+					    codec_stream->channels_max);
+		}
+	}
+}
+
+static void dpcm_runtime_merge_rate(struct snd_pcm_substream *substream,
+				    unsigned int *rates,
+				    unsigned int *rate_min,
+				    unsigned int *rate_max)
+{
+	struct snd_soc_pcm_runtime *fe = substream->private_data;
+	struct snd_soc_dpcm *dpcm;
+	int stream = substream->stream;
+
+	if (!fe->dai_link->dpcm_merged_rate)
+		return;
+
+	/*
+	 * It returns merged BE codec channel;
+	 * if FE want to use it (= dpcm_merged_chan)
+	 */
+
+	list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be) {
+		struct snd_soc_pcm_runtime *be = dpcm->be;
+		struct snd_soc_dai_driver *cpu_dai_drv =  be->cpu_dai->driver;
+		struct snd_soc_dai_driver *codec_dai_drv;
+		struct snd_soc_pcm_stream *codec_stream;
+		struct snd_soc_pcm_stream *cpu_stream;
+		int i;
+
+		if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+			cpu_stream = &cpu_dai_drv->playback;
+		else
+			cpu_stream = &cpu_dai_drv->capture;
+
+		*rate_min = max(*rate_min, cpu_stream->rate_min);
+		*rate_max = min_not_zero(*rate_max, cpu_stream->rate_max);
+		*rates = snd_pcm_rate_mask_intersect(*rates, cpu_stream->rates);
+
+		for (i = 0; i < be->num_codecs; i++) {
+			/*
+			 * Skip CODECs which don't support the current stream
+			 * type. See soc_pcm_init_runtime_hw() for more details
+			 */
+			if (!snd_soc_dai_stream_valid(be->codec_dais[i],
+						      stream))
+				continue;
+
+			codec_dai_drv = be->codec_dais[i]->driver;
+			if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+				codec_stream = &codec_dai_drv->playback;
+			else
+				codec_stream = &codec_dai_drv->capture;
+
+			*rate_min = max(*rate_min, codec_stream->rate_min);
+			*rate_max = min_not_zero(*rate_max,
+						 codec_stream->rate_max);
+			*rates = snd_pcm_rate_mask_intersect(*rates,
+						codec_stream->rates);
+		}
+	}
 }
 
 static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream)
@@ -1713,12 +1846,17 @@ static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream)
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_dai_driver *cpu_dai_drv = cpu_dai->driver;
-	u64 format = dpcm_runtime_base_format(substream);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->playback, format);
+		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->playback);
 	else
-		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->capture, format);
+		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->capture);
+
+	dpcm_runtime_merge_format(substream, &runtime->hw.formats);
+	dpcm_runtime_merge_chan(substream, &runtime->hw.channels_min,
+				&runtime->hw.channels_max);
+	dpcm_runtime_merge_rate(substream, &runtime->hw.rates,
+				&runtime->hw.rate_min, &runtime->hw.rate_max);
 }
 
 static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd);
@@ -2543,106 +2681,113 @@ static int dpcm_run_old_update(struct snd_soc_pcm_runtime *fe, int stream)
 	return ret;
 }
 
-/* Called by DAPM mixer/mux changes to update audio routing between PCMs and
- * any DAI links.
- */
-int soc_dpcm_runtime_update(struct snd_soc_card *card)
+static int soc_dpcm_fe_runtime_update(struct snd_soc_pcm_runtime *fe, int new)
 {
-	struct snd_soc_pcm_runtime *fe;
-	int old, new, paths;
+	struct snd_soc_dapm_widget_list *list;
+	int count, paths;
 
-	mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
-	list_for_each_entry(fe, &card->rtd_list, list) {
-		struct snd_soc_dapm_widget_list *list;
+	if (!fe->dai_link->dynamic)
+		return 0;
 
-		/* make sure link is FE */
-		if (!fe->dai_link->dynamic)
-			continue;
+	/* only check active links */
+	if (!fe->cpu_dai->active)
+		return 0;
 
-		/* only check active links */
-		if (!fe->cpu_dai->active)
-			continue;
+	/* DAPM sync will call this to update DSP paths */
+	dev_dbg(fe->dev, "ASoC: DPCM %s runtime update for FE %s\n",
+		new ? "new" : "old", fe->dai_link->name);
 
-		/* DAPM sync will call this to update DSP paths */
-		dev_dbg(fe->dev, "ASoC: DPCM runtime update for FE %s\n",
-			fe->dai_link->name);
+	/* skip if FE doesn't have playback capability */
+	if (!fe->cpu_dai->driver->playback.channels_min ||
+	    !fe->codec_dai->driver->playback.channels_min)
+		goto capture;
 
-		/* skip if FE doesn't have playback capability */
-		if (!fe->cpu_dai->driver->playback.channels_min
-		    || !fe->codec_dai->driver->playback.channels_min)
-			goto capture;
-
-		/* skip if FE isn't currently playing */
-		if (!fe->cpu_dai->playback_active
-		    || !fe->codec_dai->playback_active)
-			goto capture;
-
-		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list);
-		if (paths < 0) {
-			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
-					fe->dai_link->name,  "playback");
-			mutex_unlock(&card->mutex);
-			return paths;
-		}
+	/* skip if FE isn't currently playing */
+	if (!fe->cpu_dai->playback_active || !fe->codec_dai->playback_active)
+		goto capture;
 
-		/* update any new playback paths */
-		new = dpcm_process_paths(fe, SNDRV_PCM_STREAM_PLAYBACK, &list, 1);
-		if (new) {
-			dpcm_run_new_update(fe, SNDRV_PCM_STREAM_PLAYBACK);
-			dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_PLAYBACK);
-			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
-		}
+	paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list);
+	if (paths < 0) {
+		dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
+			 fe->dai_link->name,  "playback");
+		return paths;
+	}
 
-		/* update any old playback paths */
-		old = dpcm_process_paths(fe, SNDRV_PCM_STREAM_PLAYBACK, &list, 0);
-		if (old) {
+	/* update any playback paths */
+	count = dpcm_process_paths(fe, SNDRV_PCM_STREAM_PLAYBACK, &list, new);
+	if (count) {
+		if (new)
+			dpcm_run_new_update(fe, SNDRV_PCM_STREAM_PLAYBACK);
+		else
 			dpcm_run_old_update(fe, SNDRV_PCM_STREAM_PLAYBACK);
-			dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_PLAYBACK);
-			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
-		}
 
-		dpcm_path_put(&list);
+		dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_PLAYBACK);
+		dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
+	}
+
+	dpcm_path_put(&list);
+
 capture:
-		/* skip if FE doesn't have capture capability */
-		if (!fe->cpu_dai->driver->capture.channels_min
-		    || !fe->codec_dai->driver->capture.channels_min)
-			continue;
+	/* skip if FE doesn't have capture capability */
+	if (!fe->cpu_dai->driver->capture.channels_min ||
+	    !fe->codec_dai->driver->capture.channels_min)
+		return 0;
 
-		/* skip if FE isn't currently capturing */
-		if (!fe->cpu_dai->capture_active
-		    || !fe->codec_dai->capture_active)
-			continue;
+	/* skip if FE isn't currently capturing */
+	if (!fe->cpu_dai->capture_active || !fe->codec_dai->capture_active)
+		return 0;
 
-		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list);
-		if (paths < 0) {
-			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
-					fe->dai_link->name,  "capture");
-			mutex_unlock(&card->mutex);
-			return paths;
-		}
+	paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list);
+	if (paths < 0) {
+		dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
+			 fe->dai_link->name,  "capture");
+		return paths;
+	}
 
-		/* update any new capture paths */
-		new = dpcm_process_paths(fe, SNDRV_PCM_STREAM_CAPTURE, &list, 1);
-		if (new) {
+	/* update any old capture paths */
+	count = dpcm_process_paths(fe, SNDRV_PCM_STREAM_CAPTURE, &list, new);
+	if (count) {
+		if (new)
 			dpcm_run_new_update(fe, SNDRV_PCM_STREAM_CAPTURE);
-			dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_CAPTURE);
-			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_CAPTURE);
-		}
-
-		/* update any old capture paths */
-		old = dpcm_process_paths(fe, SNDRV_PCM_STREAM_CAPTURE, &list, 0);
-		if (old) {
+		else
 			dpcm_run_old_update(fe, SNDRV_PCM_STREAM_CAPTURE);
-			dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_CAPTURE);
-			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_CAPTURE);
-		}
 
-		dpcm_path_put(&list);
+		dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_CAPTURE);
+		dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_CAPTURE);
 	}
 
-	mutex_unlock(&card->mutex);
+	dpcm_path_put(&list);
+
 	return 0;
 }
+
+/* Called by DAPM mixer/mux changes to update audio routing between PCMs and
+ * any DAI links.
+ */
+int soc_dpcm_runtime_update(struct snd_soc_card *card)
+{
+	struct snd_soc_pcm_runtime *fe;
+	int ret = 0;
+
+	mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+	/* shutdown all old paths first */
+	list_for_each_entry(fe, &card->rtd_list, list) {
+		ret = soc_dpcm_fe_runtime_update(fe, 0);
+		if (ret)
+			goto out;
+	}
+
+	/* bring new paths up */
+	list_for_each_entry(fe, &card->rtd_list, list) {
+		ret = soc_dpcm_fe_runtime_update(fe, 1);
+		if (ret)
+			goto out;
+	}
+
+out:
+	mutex_unlock(&card->mutex);
+	return ret;
+}
 int soc_dpcm_be_digital_mute(struct snd_soc_pcm_runtime *fe, int mute)
 {
 	struct snd_soc_dpcm *dpcm;
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 53f121a50c97..66e77e020745 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -1,29 +1,24 @@
-/*
- * soc-topology.c  --  ALSA SoC Topology
- *
- * Copyright (C) 2012 Texas Instruments Inc.
- * Copyright (C) 2015 Intel Corporation.
- *
- * Authors: Liam Girdwood <liam.r.girdwood@linux.intel.com>
- *		K, Mythri P <mythri.p.k@intel.com>
- *		Prusty, Subhransu S <subhransu.s.prusty@intel.com>
- *		B, Jayachandran <jayachandran.b@intel.com>
- *		Abdullah, Omair M <omair.m.abdullah@intel.com>
- *		Jin, Yao <yao.jin@intel.com>
- *		Lin, Mengdong <mengdong.lin@intel.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- *  Add support to read audio firmware topology alongside firmware text. The
- *  topology data can contain kcontrols, DAPM graphs, widgets, DAIs, DAI links,
- *  equalizers, firmware, coefficients etc.
- *
- *  This file only manages the core ALSA and ASoC components, all other bespoke
- *  firmware topology data is passed to component drivers for bespoke handling.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-topology.c  --  ALSA SoC Topology
+//
+// Copyright (C) 2012 Texas Instruments Inc.
+// Copyright (C) 2015 Intel Corporation.
+//
+// Authors: Liam Girdwood <liam.r.girdwood@linux.intel.com>
+//		K, Mythri P <mythri.p.k@intel.com>
+//		Prusty, Subhransu S <subhransu.s.prusty@intel.com>
+//		B, Jayachandran <jayachandran.b@intel.com>
+//		Abdullah, Omair M <omair.m.abdullah@intel.com>
+//		Jin, Yao <yao.jin@intel.com>
+//		Lin, Mengdong <mengdong.lin@intel.com>
+//
+//  Add support to read audio firmware topology alongside firmware text. The
+//  topology data can contain kcontrols, DAPM graphs, widgets, DAIs, DAI links,
+//  equalizers, firmware, coefficients etc.
+//
+//  This file only manages the core ALSA and ASoC components, all other bespoke
+//  firmware topology data is passed to component drivers for bespoke handling.
 
 #include <linux/kernel.h>
 #include <linux/export.h>
@@ -259,7 +254,7 @@ static int soc_tplg_vendor_load_(struct soc_tplg *tplg,
 	int ret = 0;
 
 	if (tplg->comp && tplg->ops && tplg->ops->vendor_load)
-		ret = tplg->ops->vendor_load(tplg->comp, hdr);
+		ret = tplg->ops->vendor_load(tplg->comp, tplg->index, hdr);
 	else {
 		dev_err(tplg->dev, "ASoC: no vendor load callback for ID %d\n",
 			hdr->vendor_type);
@@ -291,7 +286,8 @@ static int soc_tplg_widget_load(struct soc_tplg *tplg,
 	struct snd_soc_dapm_widget *w, struct snd_soc_tplg_dapm_widget *tplg_w)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->widget_load)
-		return tplg->ops->widget_load(tplg->comp, w, tplg_w);
+		return tplg->ops->widget_load(tplg->comp, tplg->index, w,
+			tplg_w);
 
 	return 0;
 }
@@ -302,27 +298,30 @@ static int soc_tplg_widget_ready(struct soc_tplg *tplg,
 	struct snd_soc_dapm_widget *w, struct snd_soc_tplg_dapm_widget *tplg_w)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->widget_ready)
-		return tplg->ops->widget_ready(tplg->comp, w, tplg_w);
+		return tplg->ops->widget_ready(tplg->comp, tplg->index, w,
+			tplg_w);
 
 	return 0;
 }
 
 /* pass DAI configurations to component driver for extra initialization */
 static int soc_tplg_dai_load(struct soc_tplg *tplg,
-	struct snd_soc_dai_driver *dai_drv)
+	struct snd_soc_dai_driver *dai_drv,
+	struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->dai_load)
-		return tplg->ops->dai_load(tplg->comp, dai_drv);
+		return tplg->ops->dai_load(tplg->comp, tplg->index, dai_drv,
+			pcm, dai);
 
 	return 0;
 }
 
 /* pass link configurations to component driver for extra initialization */
 static int soc_tplg_dai_link_load(struct soc_tplg *tplg,
-	struct snd_soc_dai_link *link)
+	struct snd_soc_dai_link *link, struct snd_soc_tplg_link_config *cfg)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->link_load)
-		return tplg->ops->link_load(tplg->comp, link);
+		return tplg->ops->link_load(tplg->comp, tplg->index, link, cfg);
 
 	return 0;
 }
@@ -643,7 +642,8 @@ static int soc_tplg_init_kcontrol(struct soc_tplg *tplg,
 	struct snd_kcontrol_new *k, struct snd_soc_tplg_ctl_hdr *hdr)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->control_load)
-		return tplg->ops->control_load(tplg->comp, k, hdr);
+		return tplg->ops->control_load(tplg->comp, tplg->index, k,
+			hdr);
 
 	return 0;
 }
@@ -1100,6 +1100,17 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg,
 	return 0;
 }
 
+/* optionally pass new dynamic kcontrol to component driver. */
+static int soc_tplg_add_route(struct soc_tplg *tplg,
+	struct snd_soc_dapm_route *route)
+{
+	if (tplg->comp && tplg->ops && tplg->ops->dapm_route_load)
+		return tplg->ops->dapm_route_load(tplg->comp, tplg->index,
+			route);
+
+	return 0;
+}
+
 static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg,
 	struct snd_soc_tplg_hdr *hdr)
 {
@@ -1148,6 +1159,8 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg,
 		else
 			route.control = elem->control;
 
+		soc_tplg_add_route(tplg, &route);
+
 		/* add route, but keep going if some fail */
 		snd_soc_dapm_add_routes(dapm, &route, 1);
 	}
@@ -1702,7 +1715,7 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg,
 		dai_drv->compress_new = snd_soc_new_compress;
 
 	/* pass control to component driver for optional further init */
-	ret = soc_tplg_dai_load(tplg, dai_drv);
+	ret = soc_tplg_dai_load(tplg, dai_drv, pcm, NULL);
 	if (ret < 0) {
 		dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n");
 		kfree(dai_drv);
@@ -1772,7 +1785,7 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg,
 		set_link_flags(link, pcm->flag_mask, pcm->flags);
 
 	/* pass control to component driver for optional further init */
-	ret = soc_tplg_dai_link_load(tplg, link);
+	ret = soc_tplg_dai_link_load(tplg, link, NULL);
 	if (ret < 0) {
 		dev_err(tplg->comp->dev, "ASoC: FE link loading failed\n");
 		kfree(link);
@@ -2080,7 +2093,7 @@ static int soc_tplg_link_config(struct soc_tplg *tplg,
 		set_link_flags(link, cfg->flag_mask, cfg->flags);
 
 	/* pass control to component driver for optional further init */
-	ret = soc_tplg_dai_link_load(tplg, link);
+	ret = soc_tplg_dai_link_load(tplg, link, cfg);
 	if (ret < 0) {
 		dev_err(tplg->dev, "ASoC: physical link loading failed\n");
 		return ret;
@@ -2202,7 +2215,7 @@ static int soc_tplg_dai_config(struct soc_tplg *tplg,
 		set_dai_flags(dai_drv, d->flag_mask, d->flags);
 
 	/* pass control to component driver for optional further init */
-	ret = soc_tplg_dai_load(tplg, dai_drv);
+	ret = soc_tplg_dai_load(tplg, dai_drv, NULL, dai);
 	if (ret < 0) {
 		dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n");
 		return ret;
@@ -2311,7 +2324,7 @@ static int soc_tplg_manifest_load(struct soc_tplg *tplg,
 
 	/* pass control to component driver for optional further init */
 	if (tplg->comp && tplg->ops && tplg->ops->manifest)
-		return tplg->ops->manifest(tplg->comp, _manifest);
+		return tplg->ops->manifest(tplg->comp, tplg->index, _manifest);
 
 	if (!abi_match)	/* free the duplicated one */
 		kfree(_manifest);
diff --git a/sound/soc/soc-utils.c b/sound/soc/soc-utils.c
index 2d9e98bd1530..e0c93496c0cd 100644
--- a/sound/soc/soc-utils.c
+++ b/sound/soc/soc-utils.c
@@ -1,17 +1,11 @@
-/*
- * soc-util.c  --  ALSA SoC Audio Layer utility functions
- *
- * Copyright 2009 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *         Liam Girdwood <lrg@slimlogic.co.uk>
- *         
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-util.c  --  ALSA SoC Audio Layer utility functions
+//
+// Copyright 2009 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+//         Liam Girdwood <lrg@slimlogic.co.uk>
 
 #include <linux/platform_device.h>
 #include <linux/export.h>
@@ -381,6 +375,6 @@ int __init snd_soc_util_init(void)
 
 void __exit snd_soc_util_exit(void)
 {
-	platform_device_unregister(soc_dummy_dev);
 	platform_driver_unregister(&soc_dummy_driver);
+	platform_device_unregister(soc_dummy_dev);
 }
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index d8b6936e544e..313dab2857ef 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -91,7 +91,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 			SET_UNIPERIF_ITM_BCLR_FIFO_ERROR(player);
 
 			/* Stop the player */
-			snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
+			snd_pcm_stop_xrun(player->substream);
 		}
 
 		ret = IRQ_HANDLED;
@@ -105,7 +105,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 		SET_UNIPERIF_ITM_BCLR_DMA_ERROR(player);
 
 		/* Stop the player */
-		snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
+		snd_pcm_stop_xrun(player->substream);
 
 		ret = IRQ_HANDLED;
 	}
@@ -138,7 +138,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 		dev_err(player->dev, "Underflow recovery failed\n");
 
 		/* Stop the player */
-		snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
+		snd_pcm_stop_xrun(player->substream);
 
 		ret = IRQ_HANDLED;
 	}
diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c
index ee0055e60852..7b63d35ef428 100644
--- a/sound/soc/sti/uniperif_reader.c
+++ b/sound/soc/sti/uniperif_reader.c
@@ -65,7 +65,7 @@ static irqreturn_t uni_reader_irq_handler(int irq, void *dev_id)
 	if (unlikely(status & UNIPERIF_ITS_FIFO_ERROR_MASK(reader))) {
 		dev_err(reader->dev, "FIFO error detected\n");
 
-		snd_pcm_stop(reader->substream, SNDRV_PCM_STATE_XRUN);
+		snd_pcm_stop_xrun(reader->substream);
 
 		ret = IRQ_HANDLED;
 	}
diff --git a/sound/soc/stm/Kconfig b/sound/soc/stm/Kconfig
index 48f9ddd94016..9b2681397dba 100644
--- a/sound/soc/stm/Kconfig
+++ b/sound/soc/stm/Kconfig
@@ -6,6 +6,7 @@ config SND_SOC_STM32_SAI
 	depends on SND_SOC
 	select SND_SOC_GENERIC_DMAENGINE_PCM
 	select REGMAP_MMIO
+	select SND_PCM_IEC958
 	help
 	  Say Y if you want to enable SAI for STM32
 
diff --git a/sound/soc/stm/stm32_adfsdm.c b/sound/soc/stm/stm32_adfsdm.c
index db73fef3e500..706ff005234f 100644
--- a/sound/soc/stm/stm32_adfsdm.c
+++ b/sound/soc/stm/stm32_adfsdm.c
@@ -149,7 +149,7 @@ static int stm32_afsdm_pcm_cb(const void *data, size_t size, void *private)
 	unsigned int old_pos = priv->pos;
 	unsigned int cur_size = size;
 
-	dev_dbg(rtd->dev, "%s: buff_add :%p, pos = %d, size = %zu\n",
+	dev_dbg(rtd->dev, "%s: buff_add :%pK, pos = %d, size = %zu\n",
 		__func__, &pcm_buff[priv->pos], priv->pos, size);
 
 	if ((priv->pos + size) > buff_size) {
@@ -269,16 +269,10 @@ static int stm32_adfsdm_pcm_new(struct snd_soc_pcm_runtime *rtd)
 static void stm32_adfsdm_pcm_free(struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
-	struct snd_soc_pcm_runtime *rtd;
-	struct stm32_adfsdm_priv *priv;
 
 	substream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream;
-	if (substream) {
-		rtd = substream->private_data;
-		priv = snd_soc_dai_get_drvdata(rtd->cpu_dai);
-
+	if (substream)
 		snd_pcm_lib_preallocate_free_for_all(pcm);
-	}
 }
 
 static struct snd_soc_component_driver stm32_adfsdm_soc_platform = {
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index cfeb219e1d78..06fba9650ac4 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -96,7 +96,8 @@
  * @slot_mask: rx or tx active slots mask. set at init or at runtime
  * @data_size: PCM data width. corresponds to PCM substream width.
  * @spdif_frm_cnt: S/PDIF playback frame counter
- * @spdif_status_bits: S/PDIF status bits
+ * @snd_aes_iec958: iec958 data
+ * @ctrl_lock: control lock
  */
 struct stm32_sai_sub_data {
 	struct platform_device *pdev;
@@ -125,7 +126,8 @@ struct stm32_sai_sub_data {
 	int slot_mask;
 	int data_size;
 	unsigned int spdif_frm_cnt;
-	unsigned char spdif_status_bits[SAI_IEC60958_STATUS_BYTES];
+	struct snd_aes_iec958 iec958;
+	struct mutex ctrl_lock; /* protect resources accessed by controls */
 };
 
 enum stm32_sai_fifo_th {
@@ -184,10 +186,6 @@ static bool stm32_sai_sub_writeable_reg(struct device *dev, unsigned int reg)
 	}
 }
 
-static const unsigned char default_status_bits[SAI_IEC60958_STATUS_BYTES] = {
-	0, 0, 0, IEC958_AES3_CON_FS_48000,
-};
-
 static const struct regmap_config stm32_sai_sub_regmap_config_f4 = {
 	.reg_bits = 32,
 	.reg_stride = 4,
@@ -210,6 +208,49 @@ static const struct regmap_config stm32_sai_sub_regmap_config_h7 = {
 	.fast_io = true,
 };
 
+static int snd_pcm_iec958_info(struct snd_kcontrol *kcontrol,
+			       struct snd_ctl_elem_info *uinfo)
+{
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_IEC958;
+	uinfo->count = 1;
+
+	return 0;
+}
+
+static int snd_pcm_iec958_get(struct snd_kcontrol *kcontrol,
+			      struct snd_ctl_elem_value *uctl)
+{
+	struct stm32_sai_sub_data *sai = snd_kcontrol_chip(kcontrol);
+
+	mutex_lock(&sai->ctrl_lock);
+	memcpy(uctl->value.iec958.status, sai->iec958.status, 4);
+	mutex_unlock(&sai->ctrl_lock);
+
+	return 0;
+}
+
+static int snd_pcm_iec958_put(struct snd_kcontrol *kcontrol,
+			      struct snd_ctl_elem_value *uctl)
+{
+	struct stm32_sai_sub_data *sai = snd_kcontrol_chip(kcontrol);
+
+	mutex_lock(&sai->ctrl_lock);
+	memcpy(sai->iec958.status, uctl->value.iec958.status, 4);
+	mutex_unlock(&sai->ctrl_lock);
+
+	return 0;
+}
+
+static const struct snd_kcontrol_new iec958_ctls = {
+	.access = (SNDRV_CTL_ELEM_ACCESS_READWRITE |
+			SNDRV_CTL_ELEM_ACCESS_VOLATILE),
+	.iface = SNDRV_CTL_ELEM_IFACE_PCM,
+	.name = SNDRV_CTL_NAME_IEC958("", PLAYBACK, DEFAULT),
+	.info = snd_pcm_iec958_info,
+	.get = snd_pcm_iec958_get,
+	.put = snd_pcm_iec958_put,
+};
+
 static irqreturn_t stm32_sai_isr(int irq, void *devid)
 {
 	struct stm32_sai_sub_data *sai = (struct stm32_sai_sub_data *)devid;
@@ -259,11 +300,8 @@ static irqreturn_t stm32_sai_isr(int irq, void *devid)
 		status = SNDRV_PCM_STATE_XRUN;
 	}
 
-	if (status != SNDRV_PCM_STATE_RUNNING) {
-		snd_pcm_stream_lock(sai->substream);
-		snd_pcm_stop(sai->substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock(sai->substream);
-	}
+	if (status != SNDRV_PCM_STATE_RUNNING)
+		snd_pcm_stop_xrun(sai->substream);
 
 	return IRQ_HANDLED;
 }
@@ -619,6 +657,59 @@ static void stm32_sai_set_frame(struct snd_soc_dai *cpu_dai)
 	}
 }
 
+static void stm32_sai_init_iec958_status(struct stm32_sai_sub_data *sai)
+{
+	unsigned char *cs = sai->iec958.status;
+
+	cs[0] = IEC958_AES0_CON_NOT_COPYRIGHT | IEC958_AES0_CON_EMPHASIS_NONE;
+	cs[1] = IEC958_AES1_CON_GENERAL;
+	cs[2] = IEC958_AES2_CON_SOURCE_UNSPEC | IEC958_AES2_CON_CHANNEL_UNSPEC;
+	cs[3] = IEC958_AES3_CON_CLOCK_1000PPM | IEC958_AES3_CON_FS_NOTID;
+}
+
+static void stm32_sai_set_iec958_status(struct stm32_sai_sub_data *sai,
+					struct snd_pcm_runtime *runtime)
+{
+	if (!runtime)
+		return;
+
+	/* Force the sample rate according to runtime rate */
+	mutex_lock(&sai->ctrl_lock);
+	switch (runtime->rate) {
+	case 22050:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_22050;
+		break;
+	case 44100:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_44100;
+		break;
+	case 88200:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_88200;
+		break;
+	case 176400:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_176400;
+		break;
+	case 24000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_24000;
+		break;
+	case 48000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_48000;
+		break;
+	case 96000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_96000;
+		break;
+	case 192000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_192000;
+		break;
+	case 32000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_32000;
+		break;
+	default:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_NOTID;
+		break;
+	}
+	mutex_unlock(&sai->ctrl_lock);
+}
+
 static int stm32_sai_configure_clock(struct snd_soc_dai *cpu_dai,
 				     struct snd_pcm_hw_params *params)
 {
@@ -709,7 +800,11 @@ static int stm32_sai_hw_params(struct snd_pcm_substream *substream,
 
 	sai->data_size = params_width(params);
 
-	if (!STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+	if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+		/* Rate not already set in runtime structure */
+		substream->runtime->rate = params_rate(params);
+		stm32_sai_set_iec958_status(sai, substream->runtime);
+	} else {
 		ret = stm32_sai_set_slots(cpu_dai);
 		if (ret < 0)
 			return ret;
@@ -789,6 +884,20 @@ static void stm32_sai_shutdown(struct snd_pcm_substream *substream,
 	sai->substream = NULL;
 }
 
+static int stm32_sai_pcm_new(struct snd_soc_pcm_runtime *rtd,
+			     struct snd_soc_dai *cpu_dai)
+{
+	struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev);
+
+	if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+		dev_dbg(&sai->pdev->dev, "%s: register iec controls", __func__);
+		return snd_ctl_add(rtd->pcm->card,
+				   snd_ctl_new1(&iec958_ctls, sai));
+	}
+
+	return 0;
+}
+
 static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 {
 	struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev);
@@ -809,6 +918,10 @@ static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 	else
 		snd_soc_dai_init_dma_data(cpu_dai, NULL, &sai->dma_params);
 
+	/* Next settings are not relevant for spdif mode */
+	if (STM_SAI_PROTOCOL_IS_SPDIF(sai))
+		return 0;
+
 	cr1_mask = SAI_XCR1_RX_TX;
 	if (STM_SAI_IS_CAPTURE(sai))
 		cr1 |= SAI_XCR1_RX_TX;
@@ -820,10 +933,6 @@ static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 				     sai->synco, sai->synci);
 	}
 
-	if (STM_SAI_PROTOCOL_IS_SPDIF(sai))
-		memcpy(sai->spdif_status_bits, default_status_bits,
-		       sizeof(default_status_bits));
-
 	cr1_mask |= SAI_XCR1_SYNCEN_MASK;
 	cr1 |= SAI_XCR1_SYNCEN_SET(sai->sync);
 
@@ -861,7 +970,7 @@ static int stm32_sai_pcm_process_spdif(struct snd_pcm_substream *substream,
 		/* Set channel status bit */
 		byte = frm_cnt >> 3;
 		mask = 1 << (frm_cnt - (byte << 3));
-		if (sai->spdif_status_bits[byte] & mask)
+		if (sai->iec958.status[byte] & mask)
 			*ptr |= 0x04000000;
 		ptr++;
 
@@ -888,6 +997,7 @@ static const struct snd_pcm_hardware stm32_sai_pcm_hw = {
 static struct snd_soc_dai_driver stm32_sai_playback_dai[] = {
 {
 		.probe = stm32_sai_dai_probe,
+		.pcm_new = stm32_sai_pcm_new,
 		.id = 1, /* avoid call to fmt_single_name() */
 		.playback = {
 			.channels_min = 1,
@@ -998,6 +1108,7 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev,
 			dev_err(&pdev->dev, "S/PDIF IEC60958 not supported\n");
 			return -EINVAL;
 		}
+		stm32_sai_init_iec958_status(sai);
 		sai->spdif = true;
 		sai->master = true;
 	}
@@ -1114,6 +1225,7 @@ static int stm32_sai_sub_probe(struct platform_device *pdev)
 	sai->id = (uintptr_t)of_id->data;
 
 	sai->pdev = pdev;
+	mutex_init(&sai->ctrl_lock);
 	platform_set_drvdata(pdev, sai);
 
 	sai->pdata = dev_get_drvdata(pdev->dev.parent);
diff --git a/sound/soc/tegra/tegra20_ac97.c b/sound/soc/tegra/tegra20_ac97.c
index affad46bf188..682ef33afb5f 100644
--- a/sound/soc/tegra/tegra20_ac97.c
+++ b/sound/soc/tegra/tegra20_ac97.c
@@ -377,7 +377,7 @@ static int tegra20_ac97_platform_probe(struct platform_device *pdev)
 	ret = clk_prepare_enable(ac97->clk_ac97);
 	if (ret) {
 		dev_err(&pdev->dev, "clk_enable failed: %d\n", ret);
-		goto err;
+		goto err_clk_put;
 	}
 
 	ret = snd_soc_set_ac97_ops(&tegra20_ac97_ops);
diff --git a/sound/soc/tegra/tegra30_i2s.h b/sound/soc/tegra/tegra30_i2s.h
index 774fc6ad2026..2e561e946de2 100644
--- a/sound/soc/tegra/tegra30_i2s.h
+++ b/sound/soc/tegra/tegra30_i2s.h
@@ -173,7 +173,7 @@
 /* Number of slots in frame, minus 1 */
 #define TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_SHIFT		16
 #define TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK_US	7
-#define TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK		(TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOT_MASK_US << TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOT_SHIFT)
+#define TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK		(TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK_US << TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_SHIFT)
 
 /* TDM mode slot enable bitmask */
 #define TEGRA30_I2S_SLOT_CTRL_RX_SLOT_ENABLES_SHIFT	8
diff --git a/sound/soc/tegra/tegra_alc5632.c b/sound/soc/tegra/tegra_alc5632.c
index 5197d6b18cb6..98d87801d57a 100644
--- a/sound/soc/tegra/tegra_alc5632.c
+++ b/sound/soc/tegra/tegra_alc5632.c
@@ -190,14 +190,14 @@ static int tegra_alc5632_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev,
 			"Property 'nvidia,i2s-controller' missing or invalid\n");
 		ret = -EINVAL;
-		goto err;
+		goto err_put_codec_of_node;
 	}
 
 	tegra_alc5632_dai.platform_of_node = tegra_alc5632_dai.cpu_of_node;
 
 	ret = tegra_asoc_utils_init(&alc5632->util_data, &pdev->dev);
 	if (ret)
-		goto err;
+		goto err_put_cpu_of_node;
 
 	ret = snd_soc_register_card(card);
 	if (ret) {
@@ -210,6 +210,13 @@ static int tegra_alc5632_probe(struct platform_device *pdev)
 
 err_fini_utils:
 	tegra_asoc_utils_fini(&alc5632->util_data);
+err_put_cpu_of_node:
+	of_node_put(tegra_alc5632_dai.cpu_of_node);
+	tegra_alc5632_dai.cpu_of_node = NULL;
+	tegra_alc5632_dai.platform_of_node = NULL;
+err_put_codec_of_node:
+	of_node_put(tegra_alc5632_dai.codec_of_node);
+	tegra_alc5632_dai.codec_of_node = NULL;
 err:
 	return ret;
 }
@@ -223,6 +230,12 @@ static int tegra_alc5632_remove(struct platform_device *pdev)
 
 	tegra_asoc_utils_fini(&machine->util_data);
 
+	of_node_put(tegra_alc5632_dai.cpu_of_node);
+	tegra_alc5632_dai.cpu_of_node = NULL;
+	tegra_alc5632_dai.platform_of_node = NULL;
+	of_node_put(tegra_alc5632_dai.codec_of_node);
+	tegra_alc5632_dai.codec_of_node = NULL;
+
 	return 0;
 }
 
diff --git a/sound/soc/tegra/tegra_rt5677.c b/sound/soc/tegra/tegra_rt5677.c
index 0e4805c7b4ca..7081f15302cc 100644
--- a/sound/soc/tegra/tegra_rt5677.c
+++ b/sound/soc/tegra/tegra_rt5677.c
@@ -264,13 +264,13 @@ static int tegra_rt5677_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev,
 			"Property 'nvidia,i2s-controller' missing or invalid\n");
 		ret = -EINVAL;
-		goto err;
+		goto err_put_codec_of_node;
 	}
 	tegra_rt5677_dai.platform_of_node = tegra_rt5677_dai.cpu_of_node;
 
 	ret = tegra_asoc_utils_init(&machine->util_data, &pdev->dev);
 	if (ret)
-		goto err;
+		goto err_put_cpu_of_node;
 
 	ret = snd_soc_register_card(card);
 	if (ret) {
@@ -283,6 +283,13 @@ static int tegra_rt5677_probe(struct platform_device *pdev)
 
 err_fini_utils:
 	tegra_asoc_utils_fini(&machine->util_data);
+err_put_cpu_of_node:
+	of_node_put(tegra_rt5677_dai.cpu_of_node);
+	tegra_rt5677_dai.cpu_of_node = NULL;
+	tegra_rt5677_dai.platform_of_node = NULL;
+err_put_codec_of_node:
+	of_node_put(tegra_rt5677_dai.codec_of_node);
+	tegra_rt5677_dai.codec_of_node = NULL;
 err:
 	return ret;
 }
@@ -296,6 +303,12 @@ static int tegra_rt5677_remove(struct platform_device *pdev)
 
 	tegra_asoc_utils_fini(&machine->util_data);
 
+	tegra_rt5677_dai.platform_of_node = NULL;
+	of_node_put(tegra_rt5677_dai.codec_of_node);
+	tegra_rt5677_dai.codec_of_node = NULL;
+	of_node_put(tegra_rt5677_dai.cpu_of_node);
+	tegra_rt5677_dai.cpu_of_node = NULL;
+
 	return 0;
 }
 
diff --git a/sound/soc/uniphier/aio-core.c b/sound/soc/uniphier/aio-core.c
index 638cb3fc5f7b..9bcba06ba52e 100644
--- a/sound/soc/uniphier/aio-core.c
+++ b/sound/soc/uniphier/aio-core.c
@@ -265,6 +265,57 @@ void aio_port_reset(struct uniphier_aio_sub *sub)
 }
 
 /**
+ * aio_port_set_ch - set channels of LPCM
+ * @sub: the AIO substream pointer, PCM substream only
+ * @ch : count of channels
+ *
+ * Set suitable slot selecting to input/output port block of AIO.
+ *
+ * This function may return error if non-PCM substream.
+ *
+ * Return: Zero if successful, otherwise a negative value on error.
+ */
+static int aio_port_set_ch(struct uniphier_aio_sub *sub)
+{
+	struct regmap *r = sub->aio->chip->regmap;
+	u32 slotsel_2ch[] = {
+		0, 0, 0, 0, 0,
+	};
+	u32 slotsel_multi[] = {
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT0,
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT1,
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT2,
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT3,
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT4,
+	};
+	u32 mode, *slotsel;
+	int i;
+
+	switch (params_channels(&sub->params)) {
+	case 8:
+	case 6:
+		mode = OPORTMXTYSLOTCTR_MODE;
+		slotsel = slotsel_multi;
+		break;
+	case 2:
+		mode = 0;
+		slotsel = slotsel_2ch;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (i = 0; i < AUD_MAX_SLOTSEL; i++) {
+		regmap_update_bits(r, OPORTMXTYSLOTCTR(sub->swm->oport.map, i),
+				   OPORTMXTYSLOTCTR_MODE, mode);
+		regmap_update_bits(r, OPORTMXTYSLOTCTR(sub->swm->oport.map, i),
+				   OPORTMXTYSLOTCTR_SLOTSEL_MASK, slotsel[i]);
+	}
+
+	return 0;
+}
+
+/**
  * aio_port_set_rate - set sampling rate of LPCM
  * @sub: the AIO substream pointer, PCM substream only
  * @rate: Sampling rate in Hz.
@@ -276,7 +327,7 @@ void aio_port_reset(struct uniphier_aio_sub *sub)
  *
  * Return: Zero if successful, otherwise a negative value on error.
  */
-int aio_port_set_rate(struct uniphier_aio_sub *sub, int rate)
+static int aio_port_set_rate(struct uniphier_aio_sub *sub, int rate)
 {
 	struct regmap *r = sub->aio->chip->regmap;
 	struct device *dev = &sub->aio->chip->pdev->dev;
@@ -395,7 +446,7 @@ int aio_port_set_rate(struct uniphier_aio_sub *sub, int rate)
  *
  * Return: Zero if successful, otherwise a negative value on error.
  */
-int aio_port_set_fmt(struct uniphier_aio_sub *sub)
+static int aio_port_set_fmt(struct uniphier_aio_sub *sub)
 {
 	struct regmap *r = sub->aio->chip->regmap;
 	struct device *dev = &sub->aio->chip->pdev->dev;
@@ -460,7 +511,7 @@ int aio_port_set_fmt(struct uniphier_aio_sub *sub)
  *
  * Return: Zero if successful, otherwise a negative value on error.
  */
-int aio_port_set_clk(struct uniphier_aio_sub *sub)
+static int aio_port_set_clk(struct uniphier_aio_sub *sub)
 {
 	struct uniphier_aio_chip *chip = sub->aio->chip;
 	struct device *dev = &sub->aio->chip->pdev->dev;
@@ -575,6 +626,10 @@ int aio_port_set_param(struct uniphier_aio_sub *sub, int pass_through,
 			rate = params_rate(params);
 		}
 
+		ret = aio_port_set_ch(sub);
+		if (ret)
+			return ret;
+
 		ret = aio_port_set_rate(sub, rate);
 		if (ret)
 			return ret;
@@ -731,15 +786,28 @@ void aio_port_set_volume(struct uniphier_aio_sub *sub, int vol)
 int aio_if_set_param(struct uniphier_aio_sub *sub, int pass_through)
 {
 	struct regmap *r = sub->aio->chip->regmap;
-	u32 v;
+	u32 memfmt, v;
 
 	if (sub->swm->dir == PORT_DIR_OUTPUT) {
-		if (pass_through)
+		if (pass_through) {
 			v = PBOUTMXCTR0_ENDIAN_0123 |
 				PBOUTMXCTR0_MEMFMT_STREAM;
-		else
-			v = PBOUTMXCTR0_ENDIAN_3210 |
-				PBOUTMXCTR0_MEMFMT_2CH;
+		} else {
+			switch (params_channels(&sub->params)) {
+			case 2:
+				memfmt = PBOUTMXCTR0_MEMFMT_2CH;
+				break;
+			case 6:
+				memfmt = PBOUTMXCTR0_MEMFMT_6CH;
+				break;
+			case 8:
+				memfmt = PBOUTMXCTR0_MEMFMT_8CH;
+				break;
+			default:
+				return -EINVAL;
+			}
+			v = PBOUTMXCTR0_ENDIAN_3210 | memfmt;
+		}
 
 		regmap_write(r, PBOUTMXCTR0(sub->swm->oif.map), v);
 		regmap_write(r, PBOUTMXCTR1(sub->swm->oif.map), 0);
diff --git a/sound/soc/uniphier/aio-cpu.c b/sound/soc/uniphier/aio-cpu.c
index 2d9b7dde2ffa..ee90e6c3937c 100644
--- a/sound/soc/uniphier/aio-cpu.c
+++ b/sound/soc/uniphier/aio-cpu.c
@@ -219,15 +219,10 @@ static int uniphier_aio_set_pll(struct snd_soc_dai *dai, int pll_id,
 				unsigned int freq_out)
 {
 	struct uniphier_aio *aio = uniphier_priv(dai);
-	struct device *dev = &aio->chip->pdev->dev;
 	int ret;
 
 	if (!is_valid_pll(aio->chip, pll_id))
 		return -EINVAL;
-	if (!aio->chip->plls[pll_id].enable) {
-		dev_err(dev, "PLL(%d) is not implemented\n", pll_id);
-		return -ENOTSUPP;
-	}
 
 	ret = aio_chip_set_pll(aio->chip, pll_id, freq_out);
 	if (ret < 0)
diff --git a/sound/soc/uniphier/aio-ld11.c b/sound/soc/uniphier/aio-ld11.c
index ab04d3331be9..de962df245ba 100644
--- a/sound/soc/uniphier/aio-ld11.c
+++ b/sound/soc/uniphier/aio-ld11.c
@@ -286,7 +286,7 @@ static struct snd_soc_dai_driver uniphier_aio_dai_ld11[] = {
 			.formats     = SNDRV_PCM_FMTBIT_S32_LE,
 			.rates       = SNDRV_PCM_RATE_48000,
 			.channels_min = 2,
-			.channels_max = 2,
+			.channels_max = 8,
 		},
 		.ops = &uniphier_aio_i2s_ops,
 	},
diff --git a/sound/soc/uniphier/aio-reg.h b/sound/soc/uniphier/aio-reg.h
index 45fdc6ae358a..734395dbcffb 100644
--- a/sound/soc/uniphier/aio-reg.h
+++ b/sound/soc/uniphier/aio-reg.h
@@ -374,6 +374,7 @@
 #define OPORTMXTYVOLGAINSTATUS(n, m)     (0x42108 + 0x400 * (n) + 0x20 * (m))
 #define   OPORTMXTYVOLGAINSTATUS_CUR_MASK  GENMASK(15, 0)
 #define OPORTMXTYSLOTCTR(n, m)           (0x42114 + 0x400 * (n) + 0x20 * (m))
+#define   OPORTMXTYSLOTCTR_MODE            BIT(15)
 #define   OPORTMXTYSLOTCTR_SLOTSEL_MASK    GENMASK(11, 8)
 #define   OPORTMXTYSLOTCTR_SLOTSEL_SLOT0   (0x8 << 8)
 #define   OPORTMXTYSLOTCTR_SLOTSEL_SLOT1   (0x9 << 8)
diff --git a/sound/soc/uniphier/aio.h b/sound/soc/uniphier/aio.h
index aa89c2f6fa24..ca6ccbae0ee8 100644
--- a/sound/soc/uniphier/aio.h
+++ b/sound/soc/uniphier/aio.h
@@ -141,6 +141,9 @@ enum IEC61937_PC {
 #define AUD_MIN_FRAGMENT_SIZE    (4 * 1024)
 #define AUD_MAX_FRAGMENT_SIZE    (16 * 1024)
 
+/* max 5 slots, 10 channels, 2 channel in 1 slot */
+#define AUD_MAX_SLOTSEL    5
+
 /*
  * This is a selector for virtual register map of AIO.
  *
@@ -322,9 +325,6 @@ int aio_chip_set_pll(struct uniphier_aio_chip *chip, int pll_id,
 void aio_chip_init(struct uniphier_aio_chip *chip);
 int aio_init(struct uniphier_aio_sub *sub);
 void aio_port_reset(struct uniphier_aio_sub *sub);
-int aio_port_set_rate(struct uniphier_aio_sub *sub, int rate);
-int aio_port_set_fmt(struct uniphier_aio_sub *sub);
-int aio_port_set_clk(struct uniphier_aio_sub *sub);
 int aio_port_set_param(struct uniphier_aio_sub *sub, int pass_through,
 		       const struct snd_pcm_hw_params *params);
 void aio_port_set_enable(struct uniphier_aio_sub *sub, int enable);
diff --git a/sound/soc/zte/zx-tdm.c b/sound/soc/zte/zx-tdm.c
index dc955272f58b..389272eeba9a 100644
--- a/sound/soc/zte/zx-tdm.c
+++ b/sound/soc/zte/zx-tdm.c
@@ -144,8 +144,8 @@ static void zx_tdm_rx_dma_en(struct zx_tdm_info *tdm, bool on)
 #define ZX_TDM_RATES	(SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000)
 
 #define ZX_TDM_FMTBIT \
-	(SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FORMAT_MU_LAW | \
-	SNDRV_PCM_FORMAT_A_LAW)
+	(SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_MU_LAW | \
+	SNDRV_PCM_FMTBIT_A_LAW)
 
 static int zx_tdm_dai_probe(struct snd_soc_dai *dai)
 {
diff --git a/sound/synth/emux/emux.c b/sound/synth/emux/emux.c
index b840ff2dcfbb..64f3141a3e1b 100644
--- a/sound/synth/emux/emux.c
+++ b/sound/synth/emux/emux.c
@@ -163,20 +163,3 @@ int snd_emux_free(struct snd_emux *emu)
 }
 
 EXPORT_SYMBOL(snd_emux_free);
-
-
-/*
- *  INIT part
- */
-
-static int __init alsa_emux_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_emux_exit(void)
-{
-}
-
-module_init(alsa_emux_init)
-module_exit(alsa_emux_exit)
diff --git a/sound/synth/util_mem.c b/sound/synth/util_mem.c
index 8e34bc4e07ec..4bd1e98200d2 100644
--- a/sound/synth/util_mem.c
+++ b/sound/synth/util_mem.c
@@ -193,19 +193,3 @@ EXPORT_SYMBOL(snd_util_mem_avail);
 EXPORT_SYMBOL(__snd_util_mem_alloc);
 EXPORT_SYMBOL(__snd_util_mem_free);
 EXPORT_SYMBOL(__snd_util_memblk_new);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_util_mem_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_util_mem_exit(void)
-{
-}
-
-module_init(alsa_util_mem_init)
-module_exit(alsa_util_mem_exit)
diff --git a/sound/usb/6fire/pcm.c b/sound/usb/6fire/pcm.c
index 2dd2518a71d3..f8ef3e2a8ca0 100644
--- a/sound/usb/6fire/pcm.c
+++ b/sound/usb/6fire/pcm.c
@@ -565,7 +565,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.trigger = usb6fire_pcm_trigger,
 	.pointer = usb6fire_pcm_pointer,
 	.page = snd_pcm_lib_get_vmalloc_page,
-	.mmap = snd_pcm_lib_mmap_vmalloc,
 };
 
 static void usb6fire_pcm_init_urb(struct pcm_urb *urb,
diff --git a/sound/usb/Makefile b/sound/usb/Makefile
index 05440e2df8d9..d330f74c90e6 100644
--- a/sound/usb/Makefile
+++ b/sound/usb/Makefile
@@ -13,6 +13,7 @@ snd-usb-audio-objs := 	card.o \
 			mixer_scarlett.o \
 			mixer_us16x08.o \
 			pcm.o \
+			power.o \
 			proc.o \
 			quirks.o \
 			stream.o
diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c
index f35d29f49ffe..c6108a3d7f8f 100644
--- a/sound/usb/caiaq/audio.c
+++ b/sound/usb/caiaq/audio.c
@@ -348,7 +348,6 @@ static const struct snd_pcm_ops snd_usb_caiaq_ops = {
 	.trigger =	snd_usb_caiaq_pcm_trigger,
 	.pointer =	snd_usb_caiaq_pcm_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 static void check_for_elapsed_periods(struct snd_usb_caiaqdev *cdev,
@@ -636,6 +635,7 @@ static void read_completed(struct urb *urb)
 	struct device *dev;
 	struct urb *out = NULL;
 	int i, frame, len, send_it = 0, outframe = 0;
+	unsigned long flags;
 	size_t offset = 0;
 
 	if (urb->status || !info)
@@ -672,10 +672,10 @@ static void read_completed(struct urb *urb)
 		offset += len;
 
 		if (len > 0) {
-			spin_lock(&cdev->spinlock);
+			spin_lock_irqsave(&cdev->spinlock, flags);
 			fill_out_urb(cdev, out, &out->iso_frame_desc[outframe]);
 			read_in_urb(cdev, urb, &urb->iso_frame_desc[frame]);
-			spin_unlock(&cdev->spinlock);
+			spin_unlock_irqrestore(&cdev->spinlock, flags);
 			check_for_elapsed_periods(cdev, cdev->sub_playback);
 			check_for_elapsed_periods(cdev, cdev->sub_capture);
 			send_it = 1;
diff --git a/sound/usb/card.c b/sound/usb/card.c
index a1ed798a1c6b..2bfe4e80a6b9 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -809,6 +809,7 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
 	if (!chip->num_suspended_intf++) {
 		list_for_each_entry(as, &chip->pcm_list, list) {
 			snd_pcm_suspend_all(as->pcm);
+			snd_usb_pcm_suspend(as);
 			as->substream[0].need_setup_ep =
 				as->substream[1].need_setup_ep = true;
 		}
@@ -824,6 +825,7 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
 static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 {
 	struct snd_usb_audio *chip = usb_get_intfdata(intf);
+	struct snd_usb_stream *as;
 	struct usb_mixer_interface *mixer;
 	struct list_head *p;
 	int err = 0;
@@ -834,6 +836,13 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 		return 0;
 
 	atomic_inc(&chip->active); /* avoid autopm */
+
+	list_for_each_entry(as, &chip->pcm_list, list) {
+		err = snd_usb_pcm_resume(as);
+		if (err < 0)
+			goto err_out;
+	}
+
 	/*
 	 * ALSA leaves material resumption to user space
 	 * we just notify and restart the mixers
diff --git a/sound/usb/card.h b/sound/usb/card.h
index 9b41b7dda84f..ac785d15ced4 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -37,6 +37,7 @@ struct audioformat {
 
 struct snd_usb_substream;
 struct snd_usb_endpoint;
+struct snd_usb_power_domain;
 
 struct snd_urb_ctx {
 	struct urb *urb;
@@ -115,6 +116,7 @@ struct snd_usb_substream {
 	int interface;	/* current interface */
 	int endpoint;	/* assigned endpoint */
 	struct audioformat *cur_audiofmt;	/* current audioformat pointer (for hw_params callback) */
+	struct snd_usb_power_domain *str_pd;	/* UAC3 Power Domain for streaming path */
 	snd_pcm_format_t pcm_format;	/* current audio format (for hw_params callback) */
 	unsigned int channels;		/* current number of channels (for hw_params callback) */
 	unsigned int channels_max;	/* max channels in the all audiofmts */
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index c79749613fa6..db5e39d67a90 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -513,14 +513,28 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface,
 	bool writeable;
 	u32 bmControls;
 
+	/* First, try to find a valid clock. This may trigger
+	 * automatic clock selection if the current clock is not
+	 * valid.
+	 */
 	clock = snd_usb_clock_find_source(chip, fmt->protocol,
 					  fmt->clock, true);
-	if (clock < 0)
-		return clock;
+	if (clock < 0) {
+		/* We did not find a valid clock, but that might be
+		 * because the current sample rate does not match an
+		 * external clock source. Try again without validation
+		 * and we will do another validation after setting the
+		 * rate.
+		 */
+		clock = snd_usb_clock_find_source(chip, fmt->protocol,
+						  fmt->clock, false);
+		if (clock < 0)
+			return clock;
+	}
 
 	prev_rate = get_sample_rate_v2v3(chip, iface, fmt->altsetting, clock);
 	if (prev_rate == rate)
-		return 0;
+		goto validation;
 
 	if (fmt->protocol == UAC_VERSION_3) {
 		struct uac3_clock_source_descriptor *cs_desc;
@@ -577,6 +591,10 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface,
 		snd_usb_set_interface_quirk(dev);
 	}
 
+validation:
+	/* validate clock after rate change */
+	if (!uac_clock_source_is_valid(chip, fmt->protocol, clock))
+		return -ENXIO;
 	return 0;
 }
 
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index c90607ebe155..d86be8bfe412 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -325,7 +325,6 @@ static void queue_pending_output_urbs(struct snd_usb_endpoint *ep)
 		unsigned long flags;
 		struct snd_usb_packet_info *uninitialized_var(packet);
 		struct snd_urb_ctx *ctx = NULL;
-		struct urb *urb;
 		int err, i;
 
 		spin_lock_irqsave(&ep->lock, flags);
@@ -345,7 +344,6 @@ static void queue_pending_output_urbs(struct snd_usb_endpoint *ep)
 			return;
 
 		list_del_init(&ctx->ready_list);
-		urb = ctx->urb;
 
 		/* copy over the length information */
 		for (i = 0; i < packet->packets; i++)
diff --git a/sound/usb/hiface/pcm.c b/sound/usb/hiface/pcm.c
index 396c317115b1..e1fbb9cc9ea7 100644
--- a/sound/usb/hiface/pcm.c
+++ b/sound/usb/hiface/pcm.c
@@ -523,7 +523,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.trigger = hiface_pcm_trigger,
 	.pointer = hiface_pcm_pointer,
 	.page = snd_pcm_lib_get_vmalloc_page,
-	.mmap = snd_pcm_lib_mmap_vmalloc,
 };
 
 static int hiface_pcm_init_urb(struct pcm_urb *urb,
diff --git a/sound/usb/line6/toneport.c b/sound/usb/line6/toneport.c
index 750467fb95db..f47ba94e6f4a 100644
--- a/sound/usb/line6/toneport.c
+++ b/sound/usb/line6/toneport.c
@@ -367,12 +367,13 @@ static bool toneport_has_source_select(struct usb_line6_toneport *toneport)
 */
 static void toneport_setup(struct usb_line6_toneport *toneport)
 {
-	int ticks;
+	u32 ticks;
 	struct usb_line6 *line6 = &toneport->line6;
 	struct usb_device *usbdev = line6->usbdev;
 
 	/* sync time on device with host: */
-	ticks = (int)get_seconds();
+	/* note: 32-bit timestamps overflow in year 2106 */
+	ticks = (u32)ktime_get_real_seconds();
 	line6_write_data(line6, 0x80c6, &ticks, 4);
 
 	/* enable device: */
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 2c1aaa3292bf..dcfc546d81b9 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -281,15 +281,16 @@ static void snd_usbmidi_out_urb_complete(struct urb *urb)
 	struct out_urb_context *context = urb->context;
 	struct snd_usb_midi_out_endpoint *ep = context->ep;
 	unsigned int urb_index;
+	unsigned long flags;
 
-	spin_lock(&ep->buffer_lock);
+	spin_lock_irqsave(&ep->buffer_lock, flags);
 	urb_index = context - ep->urbs;
 	ep->active_urbs &= ~(1 << urb_index);
 	if (unlikely(ep->drain_urbs)) {
 		ep->drain_urbs &= ~(1 << urb_index);
 		wake_up(&ep->drain_wait);
 	}
-	spin_unlock(&ep->buffer_lock);
+	spin_unlock_irqrestore(&ep->buffer_lock, flags);
 	if (urb->status < 0) {
 		int err = snd_usbmidi_urb_error(urb);
 		if (err < 0) {
diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c
index 386fbfd5c617..a0b6d039017f 100644
--- a/sound/usb/misc/ua101.c
+++ b/sound/usb/misc/ua101.c
@@ -900,7 +900,6 @@ static const struct snd_pcm_ops capture_pcm_ops = {
 	.trigger = capture_pcm_trigger,
 	.pointer = capture_pcm_pointer,
 	.page = snd_pcm_lib_get_vmalloc_page,
-	.mmap = snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops playback_pcm_ops = {
@@ -913,7 +912,6 @@ static const struct snd_pcm_ops playback_pcm_ops = {
 	.trigger = playback_pcm_trigger,
 	.pointer = playback_pcm_pointer,
 	.page = snd_pcm_lib_get_vmalloc_page,
-	.mmap = snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct uac_format_type_i_discrete_descriptor *
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index ca963e94ec03..c63c84b54969 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -675,16 +675,16 @@ static int get_term_name(struct snd_usb_audio *chip, struct usb_audio_term *iter
 		if (term_only)
 			return 0;
 		switch (iterm->type >> 16) {
-		case UAC_SELECTOR_UNIT:
+		case UAC3_SELECTOR_UNIT:
 			strcpy(name, "Selector");
 			return 8;
-		case UAC1_PROCESSING_UNIT:
+		case UAC3_PROCESSING_UNIT:
 			strcpy(name, "Process Unit");
 			return 12;
-		case UAC1_EXTENSION_UNIT:
+		case UAC3_EXTENSION_UNIT:
 			strcpy(name, "Ext Unit");
 			return 8;
-		case UAC_MIXER_UNIT:
+		case UAC3_MIXER_UNIT:
 			strcpy(name, "Mixer");
 			return 5;
 		default:
@@ -832,7 +832,7 @@ static int check_input_term(struct mixer_build *state, int id,
 			case UAC_MIXER_UNIT: {
 				struct uac_mixer_unit_descriptor *d = p1;
 
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_MIXER_UNIT << 16; /* virtual type */
 				term->channels = uac_mixer_unit_bNrChannels(d);
 				term->chconfig = uac_mixer_unit_wChannelConfig(d, protocol);
 				term->name = uac_mixer_unit_iMixer(d);
@@ -845,15 +845,25 @@ static int check_input_term(struct mixer_build *state, int id,
 				err = check_input_term(state, d->baSourceID[0], term);
 				if (err < 0)
 					return err;
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_SELECTOR_UNIT << 16; /* virtual type */
 				term->id = id;
 				term->name = uac_selector_unit_iSelector(d);
 				return 0;
 			}
 			case UAC1_PROCESSING_UNIT:
+			/* UAC2_EFFECT_UNIT */
+				if (protocol == UAC_VERSION_1)
+					term->type = UAC3_PROCESSING_UNIT << 16; /* virtual type */
+				else /* UAC_VERSION_2 */
+					term->type = UAC3_EFFECT_UNIT << 16; /* virtual type */
+				/* fall through */
 			case UAC1_EXTENSION_UNIT:
 			/* UAC2_PROCESSING_UNIT_V2 */
-			/* UAC2_EFFECT_UNIT */
+				if (protocol == UAC_VERSION_1 && !term->type)
+					term->type = UAC3_EXTENSION_UNIT << 16; /* virtual type */
+				else if (protocol == UAC_VERSION_2 && !term->type)
+					term->type = UAC3_PROCESSING_UNIT << 16; /* virtual type */
+				/* fall through */
 			case UAC2_EXTENSION_UNIT_V2: {
 				struct uac_processing_unit_descriptor *d = p1;
 
@@ -869,7 +879,9 @@ static int check_input_term(struct mixer_build *state, int id,
 					id = d->baSourceID[0];
 					break; /* continue to parse */
 				}
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				if (!term->type)
+					term->type = UAC3_EXTENSION_UNIT << 16; /* virtual type */
+
 				term->channels = uac_processing_unit_bNrChannels(d);
 				term->chconfig = uac_processing_unit_wChannelConfig(d, protocol);
 				term->name = uac_processing_unit_iProcessing(d, protocol);
@@ -878,7 +890,7 @@ static int check_input_term(struct mixer_build *state, int id,
 			case UAC2_CLOCK_SOURCE: {
 				struct uac_clock_source_descriptor *d = p1;
 
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_CLOCK_SOURCE << 16; /* virtual type */
 				term->id = id;
 				term->name = d->iClockSource;
 				return 0;
@@ -923,7 +935,7 @@ static int check_input_term(struct mixer_build *state, int id,
 			case UAC3_CLOCK_SOURCE: {
 				struct uac3_clock_source_descriptor *d = p1;
 
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_CLOCK_SOURCE << 16; /* virtual type */
 				term->id = id;
 				term->name = le16_to_cpu(d->wClockSourceStr);
 				return 0;
@@ -936,7 +948,37 @@ static int check_input_term(struct mixer_build *state, int id,
 					return err;
 
 				term->channels = err;
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_MIXER_UNIT << 16; /* virtual type */
+
+				return 0;
+			}
+			case UAC3_SELECTOR_UNIT:
+			case UAC3_CLOCK_SELECTOR: {
+				struct uac_selector_unit_descriptor *d = p1;
+				/* call recursively to retrieve the channel info */
+				err = check_input_term(state, d->baSourceID[0], term);
+				if (err < 0)
+					return err;
+				term->type = UAC3_SELECTOR_UNIT << 16; /* virtual type */
+				term->id = id;
+				term->name = 0; /* TODO: UAC3 Class-specific strings */
+
+				return 0;
+			}
+			case UAC3_PROCESSING_UNIT: {
+				struct uac_processing_unit_descriptor *d = p1;
+
+				if (!d->bNrInPins)
+					return -EINVAL;
+
+				/* call recursively to retrieve the channel info */
+				err = check_input_term(state, d->baSourceID[0], term);
+				if (err < 0)
+					return err;
+
+				term->type = UAC3_PROCESSING_UNIT << 16; /* virtual type */
+				term->id = id;
+				term->name = 0; /* TODO: UAC3 Class-specific strings */
 
 				return 0;
 			}
@@ -2167,6 +2209,11 @@ struct procunit_info {
 	struct procunit_value_info *values;
 };
 
+static struct procunit_value_info undefined_proc_info[] = {
+	{ 0x00, "Control Undefined", 0 },
+	{ 0 }
+};
+
 static struct procunit_value_info updown_proc_info[] = {
 	{ UAC_UD_ENABLE, "Switch", USB_MIXER_BOOLEAN },
 	{ UAC_UD_MODE_SELECT, "Mode Select", USB_MIXER_U8, 1 },
@@ -2215,6 +2262,23 @@ static struct procunit_info procunits[] = {
 	{ UAC_PROCESS_DYN_RANGE_COMP, "DCR", dcr_proc_info },
 	{ 0 },
 };
+
+static struct procunit_value_info uac3_updown_proc_info[] = {
+	{ UAC3_UD_MODE_SELECT, "Mode Select", USB_MIXER_U8, 1 },
+	{ 0 }
+};
+static struct procunit_value_info uac3_stereo_ext_proc_info[] = {
+	{ UAC3_EXT_WIDTH_CONTROL, "Width Control", USB_MIXER_U8 },
+	{ 0 }
+};
+
+static struct procunit_info uac3_procunits[] = {
+	{ UAC3_PROCESS_UP_DOWNMIX, "Up Down", uac3_updown_proc_info },
+	{ UAC3_PROCESS_STEREO_EXTENDER, "3D Stereo Extender", uac3_stereo_ext_proc_info },
+	{ UAC3_PROCESS_MULTI_FUNCTION, "Multi-Function", undefined_proc_info },
+	{ 0 },
+};
+
 /*
  * predefined data for extension units
  */
@@ -2287,8 +2351,16 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 	for (valinfo = info->values; valinfo->control; valinfo++) {
 		__u8 *controls = uac_processing_unit_bmControls(desc, state->mixer->protocol);
 
-		if (!(controls[valinfo->control / 8] & (1 << ((valinfo->control % 8) - 1))))
-			continue;
+		if (state->mixer->protocol == UAC_VERSION_1) {
+			if (!(controls[valinfo->control / 8] &
+					(1 << ((valinfo->control % 8) - 1))))
+				continue;
+		} else { /* UAC_VERSION_2/3 */
+			if (!uac_v2v3_control_is_readable(controls[valinfo->control / 8],
+							  valinfo->control))
+				continue;
+		}
+
 		map = find_map(state->map, unitid, valinfo->control);
 		if (check_ignored_ctl(map))
 			continue;
@@ -2300,26 +2372,55 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 		cval->val_type = valinfo->val_type;
 		cval->channels = 1;
 
+		if (state->mixer->protocol > UAC_VERSION_1 &&
+		    !uac_v2v3_control_is_writeable(controls[valinfo->control / 8],
+						   valinfo->control))
+			cval->master_readonly = 1;
+
 		/* get min/max values */
-		if (type == UAC_PROCESS_UP_DOWNMIX && cval->control == UAC_UD_MODE_SELECT) {
-			__u8 *control_spec = uac_processing_unit_specific(desc, state->mixer->protocol);
-			/* FIXME: hard-coded */
-			cval->min = 1;
-			cval->max = control_spec[0];
-			cval->res = 1;
-			cval->initialized = 1;
-		} else {
-			if (type == USB_XU_CLOCK_RATE) {
-				/*
-				 * E-Mu USB 0404/0202/TrackerPre/0204
-				 * samplerate control quirk
-				 */
-				cval->min = 0;
-				cval->max = 5;
+		switch (type) {
+		case UAC_PROCESS_UP_DOWNMIX: {
+			bool mode_sel = false;
+
+			switch (state->mixer->protocol) {
+			case UAC_VERSION_1:
+			case UAC_VERSION_2:
+			default:
+				if (cval->control == UAC_UD_MODE_SELECT)
+					mode_sel = true;
+				break;
+			case UAC_VERSION_3:
+				if (cval->control == UAC3_UD_MODE_SELECT)
+					mode_sel = true;
+				break;
+			}
+
+			if (mode_sel) {
+				__u8 *control_spec = uac_processing_unit_specific(desc,
+								state->mixer->protocol);
+				cval->min = 1;
+				cval->max = control_spec[0];
 				cval->res = 1;
 				cval->initialized = 1;
-			} else
-				get_min_max(cval, valinfo->min_value);
+				break;
+			}
+
+			get_min_max(cval, valinfo->min_value);
+			break;
+		}
+		case USB_XU_CLOCK_RATE:
+			/*
+			 * E-Mu USB 0404/0202/TrackerPre/0204
+			 * samplerate control quirk
+			 */
+			cval->min = 0;
+			cval->max = 5;
+			cval->res = 1;
+			cval->initialized = 1;
+			break;
+		default:
+			get_min_max(cval, valinfo->min_value);
+			break;
 		}
 
 		kctl = snd_ctl_new1(&mixer_procunit_ctl, cval);
@@ -2362,8 +2463,16 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 static int parse_audio_processing_unit(struct mixer_build *state, int unitid,
 				       void *raw_desc)
 {
-	return build_audio_procunit(state, unitid, raw_desc,
-				    procunits, "Processing Unit");
+	switch (state->mixer->protocol) {
+	case UAC_VERSION_1:
+	case UAC_VERSION_2:
+	default:
+		return build_audio_procunit(state, unitid, raw_desc,
+				procunits, "Processing Unit");
+	case UAC_VERSION_3:
+		return build_audio_procunit(state, unitid, raw_desc,
+				uac3_procunits, "Processing Unit");
+	}
 }
 
 static int parse_audio_extension_unit(struct mixer_build *state, int unitid,
@@ -2509,11 +2618,20 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
 	cval->res = 1;
 	cval->initialized = 1;
 
-	if (state->mixer->protocol == UAC_VERSION_1)
+	switch (state->mixer->protocol) {
+	case UAC_VERSION_1:
+	default:
 		cval->control = 0;
-	else /* UAC_VERSION_2 */
-		cval->control = (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR) ?
-			UAC2_CX_CLOCK_SELECTOR : UAC2_SU_SELECTOR;
+		break;
+	case UAC_VERSION_2:
+	case UAC_VERSION_3:
+		if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR ||
+		    desc->bDescriptorSubtype == UAC3_CLOCK_SELECTOR)
+			cval->control = UAC2_CX_CLOCK_SELECTOR;
+		else /* UAC2/3_SELECTOR_UNIT */
+			cval->control = UAC2_SU_SELECTOR;
+		break;
+	}
 
 	namelist = kmalloc_array(desc->bNrInPins, sizeof(char *), GFP_KERNEL);
 	if (!namelist) {
@@ -2555,12 +2673,22 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
 	len = check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name));
 	if (!len) {
 		/* no mapping ? */
+		switch (state->mixer->protocol) {
+		case UAC_VERSION_1:
+		case UAC_VERSION_2:
+		default:
 		/* if iSelector is given, use it */
-		nameid = uac_selector_unit_iSelector(desc);
-		if (nameid)
-			len = snd_usb_copy_string_desc(state->chip, nameid,
-						       kctl->id.name,
-						       sizeof(kctl->id.name));
+			nameid = uac_selector_unit_iSelector(desc);
+			if (nameid)
+				len = snd_usb_copy_string_desc(state->chip,
+							nameid, kctl->id.name,
+							sizeof(kctl->id.name));
+			break;
+		case UAC_VERSION_3:
+			/* TODO: Class-Specific strings not yet supported */
+			break;
+		}
+
 		/* ... or pick up the terminal name at next */
 		if (!len)
 			len = get_term_name(state->chip, &state->oterm,
@@ -2570,7 +2698,8 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
 			strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name));
 
 		/* and add the proper suffix */
-		if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR)
+		if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR ||
+		    desc->bDescriptorSubtype == UAC3_CLOCK_SELECTOR)
 			append_ctl_name(kctl, " Clock Source");
 		else if ((state->oterm.type & 0xff00) == 0x0100)
 			append_ctl_name(kctl, " Capture Source");
@@ -2641,6 +2770,7 @@ static int parse_audio_unit(struct mixer_build *state, int unitid)
 			return parse_audio_mixer_unit(state, unitid, p1);
 		case UAC3_CLOCK_SOURCE:
 			return parse_clock_source_unit(state, unitid, p1);
+		case UAC3_SELECTOR_UNIT:
 		case UAC3_CLOCK_SELECTOR:
 			return parse_audio_selector_unit(state, unitid, p1);
 		case UAC3_FEATURE_UNIT:
diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index e02653465e29..3d12af8bf191 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -109,4 +109,6 @@ int snd_usb_get_cur_mix_value(struct usb_mixer_elem_info *cval,
 
 extern void snd_usb_mixer_elem_free(struct snd_kcontrol *kctl);
 
+extern struct snd_kcontrol_new *snd_usb_feature_unit_ctl;
+
 #endif /* __USBMIXER_H */
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index e82a72fea9a1..cbfb48bdea51 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -47,8 +47,6 @@
 #include "mixer_us16x08.h"
 #include "helper.h"
 
-extern struct snd_kcontrol_new *snd_usb_feature_unit_ctl;
-
 struct std_mono_table {
 	unsigned int unitid, control, cmask;
 	int val_type;
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 160f52c4871b..382847154227 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -711,6 +711,54 @@ static int configure_endpoint(struct snd_usb_substream *subs)
 	return ret;
 }
 
+static int snd_usb_pcm_change_state(struct snd_usb_substream *subs, int state)
+{
+	int ret;
+
+	if (!subs->str_pd)
+		return 0;
+
+	ret = snd_usb_power_domain_set(subs->stream->chip, subs->str_pd, state);
+	if (ret < 0) {
+		dev_err(&subs->dev->dev,
+			"Cannot change Power Domain ID: %d to state: %d. Err: %d\n",
+			subs->str_pd->pd_id, state, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int snd_usb_pcm_suspend(struct snd_usb_stream *as)
+{
+	int ret;
+
+	ret = snd_usb_pcm_change_state(&as->substream[0], UAC3_PD_STATE_D2);
+	if (ret < 0)
+		return ret;
+
+	ret = snd_usb_pcm_change_state(&as->substream[1], UAC3_PD_STATE_D2);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+int snd_usb_pcm_resume(struct snd_usb_stream *as)
+{
+	int ret;
+
+	ret = snd_usb_pcm_change_state(&as->substream[0], UAC3_PD_STATE_D1);
+	if (ret < 0)
+		return ret;
+
+	ret = snd_usb_pcm_change_state(&as->substream[1], UAC3_PD_STATE_D1);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 /*
  * hw_params callback
  *
@@ -755,16 +803,22 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream,
 	ret = snd_usb_lock_shutdown(subs->stream->chip);
 	if (ret < 0)
 		return ret;
+
+	ret = snd_usb_pcm_change_state(subs, UAC3_PD_STATE_D0);
+	if (ret < 0)
+		goto unlock;
+
 	ret = set_format(subs, fmt);
-	snd_usb_unlock_shutdown(subs->stream->chip);
 	if (ret < 0)
-		return ret;
+		goto unlock;
 
 	subs->interface = fmt->iface;
 	subs->altset_idx = fmt->altset_idx;
 	subs->need_setup_ep = true;
 
-	return 0;
+ unlock:
+	snd_usb_unlock_shutdown(subs->stream->chip);
+	return ret;
 }
 
 /*
@@ -821,6 +875,10 @@ static int snd_usb_pcm_prepare(struct snd_pcm_substream *substream)
 	snd_usb_endpoint_sync_pending_stop(subs->sync_endpoint);
 	snd_usb_endpoint_sync_pending_stop(subs->data_endpoint);
 
+	ret = snd_usb_pcm_change_state(subs, UAC3_PD_STATE_D0);
+	if (ret < 0)
+		goto unlock;
+
 	ret = set_format(subs, subs->cur_audiofmt);
 	if (ret < 0)
 		goto unlock;
@@ -1265,6 +1323,7 @@ static int snd_usb_pcm_close(struct snd_pcm_substream *substream)
 	int direction = substream->stream;
 	struct snd_usb_stream *as = snd_pcm_substream_chip(substream);
 	struct snd_usb_substream *subs = &as->substream[direction];
+	int ret;
 
 	stop_endpoints(subs, true);
 
@@ -1273,7 +1332,10 @@ static int snd_usb_pcm_close(struct snd_pcm_substream *substream)
 	    !snd_usb_lock_shutdown(subs->stream->chip)) {
 		usb_set_interface(subs->dev, subs->interface, 0);
 		subs->interface = -1;
+		ret = snd_usb_pcm_change_state(subs, UAC3_PD_STATE_D1);
 		snd_usb_unlock_shutdown(subs->stream->chip);
+		if (ret < 0)
+			return ret;
 	}
 
 	subs->pcm_substream = NULL;
@@ -1632,6 +1694,7 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 		subs->trigger_tstamp_pending_update = true;
+		/* fall through */
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 		subs->data_endpoint->prepare_data_urb = prepare_playback_urb;
 		subs->data_endpoint->retire_data_urb = retire_playback_urb;
@@ -1694,7 +1757,6 @@ static const struct snd_pcm_ops snd_usb_playback_ops = {
 	.trigger =	snd_usb_substream_playback_trigger,
 	.pointer =	snd_usb_pcm_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops snd_usb_capture_ops = {
@@ -1707,7 +1769,6 @@ static const struct snd_pcm_ops snd_usb_capture_ops = {
 	.trigger =	snd_usb_substream_capture_trigger,
 	.pointer =	snd_usb_pcm_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops snd_usb_playback_dev_ops = {
diff --git a/sound/usb/pcm.h b/sound/usb/pcm.h
index f77ec58bf1a1..9833627c1eca 100644
--- a/sound/usb/pcm.h
+++ b/sound/usb/pcm.h
@@ -6,6 +6,8 @@ snd_pcm_uframes_t snd_usb_pcm_delay(struct snd_usb_substream *subs,
 				    unsigned int rate);
 
 void snd_usb_set_pcm_ops(struct snd_pcm *pcm, int stream);
+int snd_usb_pcm_suspend(struct snd_usb_stream *as);
+int snd_usb_pcm_resume(struct snd_usb_stream *as);
 
 int snd_usb_init_pitch(struct snd_usb_audio *chip, int iface,
 		       struct usb_host_interface *alts,
diff --git a/sound/usb/power.c b/sound/usb/power.c
new file mode 100644
index 000000000000..bd303a1ba1b7
--- /dev/null
+++ b/sound/usb/power.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *   UAC3 Power Domain state management functions
+ */
+
+#include <linux/slab.h>
+#include <linux/usb.h>
+#include <linux/usb/audio.h>
+#include <linux/usb/audio-v2.h>
+#include <linux/usb/audio-v3.h>
+
+#include "usbaudio.h"
+#include "helper.h"
+#include "power.h"
+
+struct snd_usb_power_domain *
+snd_usb_find_power_domain(struct usb_host_interface *ctrl_iface,
+			  unsigned char id)
+{
+	struct snd_usb_power_domain *pd;
+	void *p;
+
+	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return NULL;
+
+	p = NULL;
+	while ((p = snd_usb_find_csint_desc(ctrl_iface->extra,
+					    ctrl_iface->extralen,
+					    p, UAC3_POWER_DOMAIN)) != NULL) {
+		struct uac3_power_domain_descriptor *pd_desc = p;
+		int i;
+
+		for (i = 0; i < pd_desc->bNrEntities; i++) {
+			if (pd_desc->baEntityID[i] == id) {
+				pd->pd_id = pd_desc->bPowerDomainID;
+				pd->pd_d1d0_rec =
+					le16_to_cpu(pd_desc->waRecoveryTime1);
+				pd->pd_d2d0_rec =
+					le16_to_cpu(pd_desc->waRecoveryTime2);
+				return pd;
+			}
+		}
+	}
+
+	kfree(pd);
+	return NULL;
+}
+
+int snd_usb_power_domain_set(struct snd_usb_audio *chip,
+			     struct snd_usb_power_domain *pd,
+			     unsigned char state)
+{
+	struct usb_device *dev = chip->dev;
+	unsigned char current_state;
+	int err, idx;
+
+	idx = snd_usb_ctrl_intf(chip) | (pd->pd_id << 8);
+
+	err = snd_usb_ctl_msg(chip->dev, usb_rcvctrlpipe(chip->dev, 0),
+			      UAC2_CS_CUR,
+			      USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN,
+			      UAC3_AC_POWER_DOMAIN_CONTROL << 8, idx,
+			      &current_state, sizeof(current_state));
+	if (err < 0) {
+		dev_err(&dev->dev, "Can't get UAC3 power state for id %d\n",
+			pd->pd_id);
+		return err;
+	}
+
+	if (current_state == state) {
+		dev_dbg(&dev->dev, "UAC3 power domain id %d already in state %d\n",
+			pd->pd_id, state);
+		return 0;
+	}
+
+	err = snd_usb_ctl_msg(chip->dev, usb_sndctrlpipe(chip->dev, 0), UAC2_CS_CUR,
+			      USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT,
+			      UAC3_AC_POWER_DOMAIN_CONTROL << 8, idx,
+			      &state, sizeof(state));
+	if (err < 0) {
+		dev_err(&dev->dev, "Can't set UAC3 power state to %d for id %d\n",
+			state, pd->pd_id);
+		return err;
+	}
+
+	if (state == UAC3_PD_STATE_D0) {
+		switch (current_state) {
+		case UAC3_PD_STATE_D2:
+			udelay(pd->pd_d2d0_rec * 50);
+			break;
+		case UAC3_PD_STATE_D1:
+			udelay(pd->pd_d1d0_rec * 50);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	dev_dbg(&dev->dev, "UAC3 power domain id %d change to state %d\n",
+		pd->pd_id, state);
+
+	return 0;
+}
diff --git a/sound/usb/power.h b/sound/usb/power.h
index b2e25f60c5a2..6004231a7c75 100644
--- a/sound/usb/power.h
+++ b/sound/usb/power.h
@@ -2,6 +2,25 @@
 #ifndef __USBAUDIO_POWER_H
 #define __USBAUDIO_POWER_H
 
+struct snd_usb_power_domain {
+	int pd_id;              /* UAC3 Power Domain ID */
+	int pd_d1d0_rec;        /* D1 to D0 recovery time */
+	int pd_d2d0_rec;        /* D2 to D0 recovery time */
+};
+
+enum {
+	UAC3_PD_STATE_D0,
+	UAC3_PD_STATE_D1,
+	UAC3_PD_STATE_D2,
+};
+
+int snd_usb_power_domain_set(struct snd_usb_audio *chip,
+			     struct snd_usb_power_domain *pd,
+			     unsigned char state);
+struct snd_usb_power_domain *
+snd_usb_find_power_domain(struct usb_host_interface *ctrl_iface,
+			  unsigned char id);
+
 #ifdef CONFIG_PM
 int snd_usb_autoresume(struct snd_usb_audio *chip);
 void snd_usb_autosuspend(struct snd_usb_audio *chip);
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 8aac48f9c322..08aa78007020 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2875,7 +2875,8 @@ YAMAHA_DEVICE(0x7010, "UB99"),
  */
 
 #define AU0828_DEVICE(vid, pid, vname, pname) { \
-	USB_DEVICE_VENDOR_SPEC(vid, pid), \
+	.idVendor = vid, \
+	.idProduct = pid, \
 	.match_flags = USB_DEVICE_ID_MATCH_DEVICE | \
 		       USB_DEVICE_ID_MATCH_INT_CLASS | \
 		       USB_DEVICE_ID_MATCH_INT_SUBCLASS, \
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 02b6cc02767f..8a945ece9869 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1213,7 +1213,7 @@ int snd_usb_select_mode_quirk(struct snd_usb_substream *subs,
 		if (err < 0)
 			return err;
 
-		mdelay(20); /* Delay needed after setting the interface */
+		msleep(20); /* Delay needed after setting the interface */
 
 		/* Vendor mode switch cmd is required. */
 		if (fmt->formats & SNDRV_PCM_FMTBIT_DSD_U32_BE) {
@@ -1234,7 +1234,7 @@ int snd_usb_select_mode_quirk(struct snd_usb_substream *subs,
 				return err;
 
 		}
-		mdelay(20);
+		msleep(20);
 	}
 	return 0;
 }
@@ -1281,7 +1281,7 @@ void snd_usb_set_interface_quirk(struct usb_device *dev)
 	switch (USB_ID_VENDOR(chip->usb_id)) {
 	case 0x23ba: /* Playback Design */
 	case 0x0644: /* TEAC Corp. */
-		mdelay(50);
+		msleep(50);
 		break;
 	}
 }
@@ -1301,7 +1301,7 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	 */
 	if (USB_ID_VENDOR(chip->usb_id) == 0x23ba &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
-		mdelay(20);
+		msleep(20);
 
 	/*
 	 * "TEAC Corp." products need a 20ms delay after each
@@ -1309,14 +1309,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	 */
 	if (USB_ID_VENDOR(chip->usb_id) == 0x0644 &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
-		mdelay(20);
+		msleep(20);
 
 	/* ITF-USB DSD based DACs functionality need a delay
 	 * after each class compliant request
 	 */
 	if (is_itf_usb_dsd_dac(chip->usb_id)
 	    && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
-		mdelay(20);
+		msleep(20);
 
 	/* Zoom R16/24, Logitech H650e, Jabra 550a needs a tiny delay here,
 	 * otherwise requests like get/set frequency return as failed despite
@@ -1326,7 +1326,7 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	     chip->usb_id == USB_ID(0x046d, 0x0a46) ||
 	     chip->usb_id == USB_ID(0x0b0e, 0x0349)) &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
-		mdelay(1);
+		usleep_range(1000, 2000);
 }
 
 /*
@@ -1373,6 +1373,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
 		break;
 
+	case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */
 	case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */
 	case USB_ID(0x16b0, 0x06b2): /* NuPrime DAC-10 */
 	case USB_ID(0x16d0, 0x0733): /* Furutech ADL Stratos */
@@ -1443,6 +1444,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 	 */
 	switch (USB_ID_VENDOR(chip->usb_id)) {
 	case 0x20b1:  /* XMOS based devices */
+	case 0x152a:  /* Thesycon devices */
 	case 0x25ce:  /* Mytek devices */
 		if (fp->dsd_raw)
 			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index 729afd808cc4..67cf849aa16b 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -37,6 +37,7 @@
 #include "format.h"
 #include "clock.h"
 #include "stream.h"
+#include "power.h"
 
 /*
  * free a substream
@@ -53,6 +54,7 @@ static void free_substream(struct snd_usb_substream *subs)
 		kfree(fp);
 	}
 	kfree(subs->rate_list.list);
+	kfree(subs->str_pd);
 }
 
 
@@ -82,7 +84,8 @@ static void snd_usb_audio_pcm_free(struct snd_pcm *pcm)
 
 static void snd_usb_init_substream(struct snd_usb_stream *as,
 				   int stream,
-				   struct audioformat *fp)
+				   struct audioformat *fp,
+				   struct snd_usb_power_domain *pd)
 {
 	struct snd_usb_substream *subs = &as->substream[stream];
 
@@ -107,6 +110,13 @@ static void snd_usb_init_substream(struct snd_usb_stream *as,
 	if (fp->channels > subs->channels_max)
 		subs->channels_max = fp->channels;
 
+	if (pd) {
+		subs->str_pd = pd;
+		/* Initialize Power Domain to idle status D1 */
+		snd_usb_power_domain_set(subs->stream->chip, pd,
+					 UAC3_PD_STATE_D1);
+	}
+
 	snd_usb_preallocate_buffer(subs);
 }
 
@@ -468,9 +478,11 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor
  * fmt_list and will be freed on the chip instance release. do not free
  * fp or do remove it from the substream fmt_list to avoid double-free.
  */
-int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
-			     int stream,
-			     struct audioformat *fp)
+static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip,
+				      int stream,
+				      struct audioformat *fp,
+				      struct snd_usb_power_domain *pd)
+
 {
 	struct snd_usb_stream *as;
 	struct snd_usb_substream *subs;
@@ -498,7 +510,7 @@ int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 		err = snd_pcm_new_stream(as->pcm, stream, 1);
 		if (err < 0)
 			return err;
-		snd_usb_init_substream(as, stream, fp);
+		snd_usb_init_substream(as, stream, fp, pd);
 		return add_chmap(as->pcm, stream, subs);
 	}
 
@@ -526,7 +538,7 @@ int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 	else
 		strcpy(pcm->name, "USB Audio");
 
-	snd_usb_init_substream(as, stream, fp);
+	snd_usb_init_substream(as, stream, fp, pd);
 
 	/*
 	 * Keep using head insertion for M-Audio Audiophile USB (tm) which has a
@@ -544,6 +556,21 @@ int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 	return add_chmap(pcm, stream, &as->substream[stream]);
 }
 
+int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
+			     int stream,
+			     struct audioformat *fp)
+{
+	return __snd_usb_add_audio_stream(chip, stream, fp, NULL);
+}
+
+static int snd_usb_add_audio_stream_v3(struct snd_usb_audio *chip,
+				       int stream,
+				       struct audioformat *fp,
+				       struct snd_usb_power_domain *pd)
+{
+	return __snd_usb_add_audio_stream(chip, stream, fp, pd);
+}
+
 static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip,
 					 struct usb_host_interface *alts,
 					 int protocol, int iface_no)
@@ -819,6 +846,7 @@ found_clock:
 static struct audioformat *
 snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip,
 			     struct usb_host_interface *alts,
+			     struct snd_usb_power_domain **pd_out,
 			     int iface_no, int altset_idx,
 			     int altno, int stream)
 {
@@ -829,6 +857,7 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip,
 	struct uac3_as_header_descriptor *as = NULL;
 	struct uac3_hc_descriptor_header hc_header;
 	struct snd_pcm_chmap_elem *chmap;
+	struct snd_usb_power_domain *pd;
 	unsigned char badd_profile;
 	u64 badd_formats = 0;
 	unsigned int num_channels;
@@ -1008,12 +1037,28 @@ found_clock:
 		fp->rate_max = UAC3_BADD_SAMPLING_RATE;
 		fp->rates = SNDRV_PCM_RATE_CONTINUOUS;
 
+		pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+		if (!pd) {
+			kfree(fp->rate_table);
+			kfree(fp);
+			return NULL;
+		}
+		pd->pd_id = (stream == SNDRV_PCM_STREAM_PLAYBACK) ?
+					UAC3_BADD_PD_ID10 : UAC3_BADD_PD_ID11;
+		pd->pd_d1d0_rec = UAC3_BADD_PD_RECOVER_D1D0;
+		pd->pd_d2d0_rec = UAC3_BADD_PD_RECOVER_D2D0;
+
 	} else {
 		fp->attributes = parse_uac_endpoint_attributes(chip, alts,
 							       UAC_VERSION_3,
 							       iface_no);
+
+		pd = snd_usb_find_power_domain(chip->ctrl_intf,
+					       as->bTerminalLink);
+
 		/* ok, let's parse further... */
 		if (snd_usb_parse_audio_format_v3(chip, fp, as, stream) < 0) {
+			kfree(pd);
 			kfree(fp->chmap);
 			kfree(fp->rate_table);
 			kfree(fp);
@@ -1021,6 +1066,9 @@ found_clock:
 		}
 	}
 
+	if (pd)
+		*pd_out = pd;
+
 	return fp;
 }
 
@@ -1032,6 +1080,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 	struct usb_interface_descriptor *altsd;
 	int i, altno, err, stream;
 	struct audioformat *fp = NULL;
+	struct snd_usb_power_domain *pd = NULL;
 	int num, protocol;
 
 	dev = chip->dev;
@@ -1114,7 +1163,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 			break;
 		}
 		case UAC_VERSION_3:
-			fp = snd_usb_get_audioformat_uac3(chip, alts,
+			fp = snd_usb_get_audioformat_uac3(chip, alts, &pd,
 						iface_no, i, altno, stream);
 			break;
 		}
@@ -1125,9 +1174,14 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 			return PTR_ERR(fp);
 
 		dev_dbg(&dev->dev, "%u:%d: add audio endpoint %#x\n", iface_no, altno, fp->endpoint);
-		err = snd_usb_add_audio_stream(chip, stream, fp);
+		if (protocol == UAC_VERSION_3)
+			err = snd_usb_add_audio_stream_v3(chip, stream, fp, pd);
+		else
+			err = snd_usb_add_audio_stream(chip, stream, fp);
+
 		if (err < 0) {
 			list_del(&fp->list); /* unlink for avoiding double-free */
+			kfree(pd);
 			kfree(fp->rate_table);
 			kfree(fp->chmap);
 			kfree(fp);
diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c
index 4ed9d0c41843..fa7dca5a68c8 100644
--- a/sound/x86/intel_hdmi_audio.c
+++ b/sound/x86/intel_hdmi_audio.c
@@ -290,7 +290,6 @@ static void had_reset_audio(struct snd_intelhad *intelhaddata)
 static int had_prog_status_reg(struct snd_pcm_substream *substream,
 			struct snd_intelhad *intelhaddata)
 {
-	union aud_cfg cfg_val = {.regval = 0};
 	union aud_ch_status_0 ch_stat0 = {.regval = 0};
 	union aud_ch_status_1 ch_stat1 = {.regval = 0};
 
@@ -298,7 +297,6 @@ static int had_prog_status_reg(struct snd_pcm_substream *substream,
 					  IEC958_AES0_NONAUDIO) >> 1;
 	ch_stat0.regx.clk_acc = (intelhaddata->aes_bits &
 					  IEC958_AES3_CON_CLOCK) >> 4;
-	cfg_val.regx.val_bit = ch_stat0.regx.lpcm_id;
 
 	switch (substream->runtime->rate) {
 	case AUD_SAMPLE_RATE_32:
@@ -1854,7 +1852,7 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev)
 		/* setup private data which can be retrieved when required */
 		pcm->private_data = ctx;
 		pcm->info_flags = 0;
-		strncpy(pcm->name, card->shortname, strlen(card->shortname));
+		strlcpy(pcm->name, card->shortname, strlen(card->shortname));
 		/* setup the ops for playabck */
 		snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &had_pcm_ops);
 
diff --git a/sound/xen/xen_snd_front_alsa.c b/sound/xen/xen_snd_front_alsa.c
index 5a2bd70a2fa1..129180e17db1 100644
--- a/sound/xen/xen_snd_front_alsa.c
+++ b/sound/xen/xen_snd_front_alsa.c
@@ -188,7 +188,7 @@ static u64 to_sndif_formats_mask(u64 alsa_formats)
 
 	mask = 0;
 	for (i = 0; i < ARRAY_SIZE(ALSA_SNDIF_FORMATS); i++)
-		if (1 << ALSA_SNDIF_FORMATS[i].alsa & alsa_formats)
+		if (pcm_format_to_bits(ALSA_SNDIF_FORMATS[i].alsa) & alsa_formats)
 			mask |= 1 << ALSA_SNDIF_FORMATS[i].sndif;
 
 	return mask;
@@ -202,7 +202,7 @@ static u64 to_alsa_formats_mask(u64 sndif_formats)
 	mask = 0;
 	for (i = 0; i < ARRAY_SIZE(ALSA_SNDIF_FORMATS); i++)
 		if (1 << ALSA_SNDIF_FORMATS[i].sndif & sndif_formats)
-			mask |= 1 << ALSA_SNDIF_FORMATS[i].alsa;
+			mask |= pcm_format_to_bits(ALSA_SNDIF_FORMATS[i].alsa);
 
 	return mask;
 }
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index caae4843cb70..16e006f708ca 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 04b3256f8e6d..4e76630dd655 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5072cbd15c82
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define __ARCH_WANT_RENAMEAT
+
+#include <asm-generic/unistd.h>
diff --git a/tools/arch/parisc/include/uapi/asm/errno.h b/tools/arch/parisc/include/uapi/asm/errno.h
index fc0df353ff0d..87245c584784 100644
--- a/tools/arch/parisc/include/uapi/asm/errno.h
+++ b/tools/arch/parisc/include/uapi/asm/errno.h
@@ -113,7 +113,6 @@
 #define	ELOOP		249	/* Too many symbolic links encountered */
 #define	ENOSYS		251	/* Function not implemented */
 
-#define ENOTSUP		252	/* Function not implemented (POSIX.4 / HPUX) */
 #define ECANCELLED	253	/* aio request was canceled before complete (POSIX.4 / HPUX) */
 #define ECANCELED	ECANCELLED	/* SuSv3 and Solaris wants one 'L' */
 
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 833ed9a16adf..1b32b56a03d3 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -633,6 +633,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_PSSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
index 389c36fd8299..985534d0b448 100644
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ b/tools/arch/powerpc/include/uapi/asm/unistd.h
@@ -398,5 +398,7 @@
 #define __NR_pkey_alloc		384
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
+#define __NR_rseq		387
+#define __NR_io_pgetevents	388
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index fb00a2fca990..64aaa3f5f36c 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -219,6 +219,7 @@
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -282,7 +283,9 @@
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -339,6 +342,7 @@
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
@@ -371,5 +375,6 @@
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/mcsafe_test.h b/tools/arch/x86/include/asm/mcsafe_test.h
new file mode 100644
index 000000000000..2ccd588fbad4
--- /dev/null
+++ b/tools/arch/x86/include/asm/mcsafe_test.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MCSAFE_TEST_H_
+#define _MCSAFE_TEST_H_
+
+.macro MCSAFE_TEST_CTL
+.endm
+
+.macro MCSAFE_TEST_SRC reg count target
+.endm
+
+.macro MCSAFE_TEST_DST reg count target
+.endm
+#endif /* _MCSAFE_TEST_H_ */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 9a53a06e5a3e..298ef1479240 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -3,6 +3,7 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
+#include <asm/mcsafe_test.h>
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
@@ -183,12 +184,15 @@ ENTRY(memcpy_orig)
 ENDPROC(memcpy_orig)
 
 #ifndef CONFIG_UML
+
+MCSAFE_TEST_CTL
+
 /*
- * memcpy_mcsafe_unrolled - memory copy with machine check exception handling
+ * __memcpy_mcsafe - memory copy with machine check exception handling
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(memcpy_mcsafe_unrolled)
+ENTRY(__memcpy_mcsafe)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
@@ -204,58 +208,33 @@ ENTRY(memcpy_mcsafe_unrolled)
 	subl $8, %ecx
 	negl %ecx
 	subl %ecx, %edx
-.L_copy_leading_bytes:
+.L_read_leading_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
+.L_write_leading_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_leading_bytes
+	jnz .L_read_leading_bytes
 
 .L_8byte_aligned:
-	/* Figure out how many whole cache lines (64-bytes) to copy */
-	movl %edx, %ecx
-	andl $63, %edx
-	shrl $6, %ecx
-	jz .L_no_whole_cache_lines
-
-	/* Loop copying whole cache lines */
-.L_cache_w0: movq (%rsi), %r8
-.L_cache_w1: movq 1*8(%rsi), %r9
-.L_cache_w2: movq 2*8(%rsi), %r10
-.L_cache_w3: movq 3*8(%rsi), %r11
-	movq %r8, (%rdi)
-	movq %r9, 1*8(%rdi)
-	movq %r10, 2*8(%rdi)
-	movq %r11, 3*8(%rdi)
-.L_cache_w4: movq 4*8(%rsi), %r8
-.L_cache_w5: movq 5*8(%rsi), %r9
-.L_cache_w6: movq 6*8(%rsi), %r10
-.L_cache_w7: movq 7*8(%rsi), %r11
-	movq %r8, 4*8(%rdi)
-	movq %r9, 5*8(%rdi)
-	movq %r10, 6*8(%rdi)
-	movq %r11, 7*8(%rdi)
-	leaq 64(%rsi), %rsi
-	leaq 64(%rdi), %rdi
-	decl %ecx
-	jnz .L_cache_w0
-
-	/* Are there any trailing 8-byte words? */
-.L_no_whole_cache_lines:
 	movl %edx, %ecx
 	andl $7, %edx
 	shrl $3, %ecx
 	jz .L_no_whole_words
 
-	/* Copy trailing words */
-.L_copy_trailing_words:
+.L_read_words:
 	movq (%rsi), %r8
-	mov %r8, (%rdi)
-	leaq 8(%rsi), %rsi
-	leaq 8(%rdi), %rdi
+	MCSAFE_TEST_SRC %rsi 8 .E_read_words
+	MCSAFE_TEST_DST %rdi 8 .E_write_words
+.L_write_words:
+	movq %r8, (%rdi)
+	addq $8, %rsi
+	addq $8, %rdi
 	decl %ecx
-	jnz .L_copy_trailing_words
+	jnz .L_read_words
 
 	/* Any trailing bytes? */
 .L_no_whole_words:
@@ -264,38 +243,55 @@ ENTRY(memcpy_mcsafe_unrolled)
 
 	/* Copy trailing bytes */
 	movl %edx, %ecx
-.L_copy_trailing_bytes:
+.L_read_trailing_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
+.L_write_trailing_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_trailing_bytes
+	jnz .L_read_trailing_bytes
 
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
 	xorq %rax, %rax
 	ret
-ENDPROC(memcpy_mcsafe_unrolled)
-EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
+ENDPROC(__memcpy_mcsafe)
+EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 
 	.section .fixup, "ax"
-	/* Return -EFAULT for any failure */
-.L_memcpy_mcsafe_fail:
-	mov	$-EFAULT, %rax
+	/*
+	 * Return number of bytes not copied for any failure. Note that
+	 * there is no "tail" handling since the source buffer is 8-byte
+	 * aligned and poison is cacheline aligned.
+	 */
+.E_read_words:
+	shll	$3, %ecx
+.E_leading_bytes:
+	addl	%edx, %ecx
+.E_trailing_bytes:
+	mov	%ecx, %eax
 	ret
 
+	/*
+	 * For write fault handling, given the destination is unaligned,
+	 * we handle faults on multi-byte writes with a byte-by-byte
+	 * copy up to the write-protected page.
+	 */
+.E_write_words:
+	shll	$3, %ecx
+	addl	%edx, %ecx
+	movl	%ecx, %edx
+	jmp mcsafe_handle_tail
+
 	.previous
 
-	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
+	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE(.L_write_words, .E_write_words)
+	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
 #endif
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 32f9e397a6c0..3f140eff039f 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -217,6 +217,14 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 	int err;
 	int fd;
 
+	if (argc < 3) {
+		p_err("too few arguments, id ID and FILE path is required");
+		return -1;
+	} else if (argc > 3) {
+		p_err("too many arguments");
+		return -1;
+	}
+
 	if (!is_prefix(*argv, "id")) {
 		p_err("expected 'id' got %s", *argv);
 		return -1;
@@ -230,9 +238,6 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 	}
 	NEXT_ARG();
 
-	if (argc != 1)
-		usage();
-
 	fd = get_fd_by_id(id);
 	if (fd < 0) {
 		p_err("can't get prog by id (%u): %s", id, strerror(errno));
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 097b1a5e046b..f74a8bcbda87 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -36,6 +36,7 @@
 #include <assert.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <linux/kernel.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -90,7 +91,8 @@ static bool map_is_map_of_progs(__u32 type)
 static void *alloc_value(struct bpf_map_info *info)
 {
 	if (map_is_per_cpu(info->type))
-		return malloc(info->value_size * get_possible_cpus());
+		return malloc(round_up(info->value_size, 8) *
+			      get_possible_cpus());
 	else
 		return malloc(info->value_size);
 }
@@ -161,9 +163,10 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 		jsonw_name(json_wtr, "value");
 		print_hex_data_json(value, info->value_size);
 	} else {
-		unsigned int i, n;
+		unsigned int i, n, step;
 
 		n = get_possible_cpus();
+		step = round_up(info->value_size, 8);
 
 		jsonw_name(json_wtr, "key");
 		print_hex_data_json(key, info->key_size);
@@ -176,7 +179,7 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 			jsonw_int_field(json_wtr, "cpu", i);
 
 			jsonw_name(json_wtr, "value");
-			print_hex_data_json(value + i * info->value_size,
+			print_hex_data_json(value + i * step,
 					    info->value_size);
 
 			jsonw_end_object(json_wtr);
@@ -207,9 +210,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 
 		printf("\n");
 	} else {
-		unsigned int i, n;
+		unsigned int i, n, step;
 
 		n = get_possible_cpus();
+		step = round_up(info->value_size, 8);
 
 		printf("key:\n");
 		fprint_hex(stdout, key, info->key_size, " ");
@@ -217,7 +221,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 		for (i = 0; i < n; i++) {
 			printf("value (CPU %02d):%c",
 			       i, info->value_size > 16 ? '\n' : ' ');
-			fprint_hex(stdout, value + i * info->value_size,
+			fprint_hex(stdout, value + i * step,
 				   info->value_size, " ");
 			printf("\n");
 		}
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 05f42a46d6ed..959aa53ab678 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -694,15 +694,19 @@ static int do_load(int argc, char **argv)
 		return -1;
 	}
 
-	if (do_pin_fd(prog_fd, argv[1])) {
-		p_err("failed to pin program");
-		return -1;
-	}
+	if (do_pin_fd(prog_fd, argv[1]))
+		goto err_close_obj;
 
 	if (json_output)
 		jsonw_null(json_wtr);
 
+	bpf_object__close(obj);
+
 	return 0;
+
+err_close_obj:
+	bpf_object__close(obj);
+	return -1;
 }
 
 static int do_help(int argc, char **argv)
diff --git a/tools/build/Build.include b/tools/build/Build.include
index a4bbb984941d..950c1504ca37 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -63,8 +63,8 @@ dep-cmd = $(if $(wildcard $(fixdep)),
            $(fixdep) $(depfile) $@ '$(make-cmd)' > $(dot-target).tmp;           \
            rm -f $(depfile);                                                    \
            mv -f $(dot-target).tmp $(dot-target).cmd,                           \
-           printf '\# cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \
-           printf '\# using basic dep data\n\n' >> $(dot-target).cmd;           \
+           printf '$(pound) cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \
+           printf '$(pound) using basic dep data\n\n' >> $(dot-target).cmd;           \
            cat $(depfile) >> $(dot-target).cmd;                                 \
            printf '\n%s\n' 'cmd_$@ := $(make-cmd)' >> $(dot-target).cmd)
 
@@ -98,4 +98,4 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX
 ###
 ## HOSTCC C flags
 
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CHOSTFLAGS) -D"BUILD_STR(s)=\#s" $(CHOSTFLAGS_$(basetarget).o) $(CHOSTFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
diff --git a/tools/build/Makefile b/tools/build/Makefile
index 5eb4b5ad79cb..5edf65e684ab 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -43,7 +43,7 @@ $(OUTPUT)fixdep-in.o: FORCE
 	$(Q)$(MAKE) $(build)=fixdep
 
 $(OUTPUT)fixdep: $(OUTPUT)fixdep-in.o
-	$(QUIET_LINK)$(HOSTCC) $(LDFLAGS) -o $@ $<
+	$(QUIET_LINK)$(HOSTCC) $(HOSTLDFLAGS) -o $@ $<
 
 FORCE:
 
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
new file mode 100644
index 000000000000..42990676a55e
--- /dev/null
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -0,0 +1,783 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#include <asm/bitsperlong.h>
+
+/*
+ * This file contains the system call numbers, based on the
+ * layout of the x86-64 architecture, which embeds the
+ * pointer to the syscall in the table.
+ *
+ * As a basic principle, no duplication of functionality
+ * should be added, e.g. we don't use lseek when llseek
+ * is present. New architectures should use this file
+ * and implement the less feature-full calls in user space.
+ */
+
+#ifndef __SYSCALL
+#define __SYSCALL(x, y)
+#endif
+
+#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32)
+#else
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
+#endif
+
+#ifdef __SYSCALL_COMPAT
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp)
+#else
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64)
+#endif
+
+#define __NR_io_setup 0
+__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 1
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_submit 2
+__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 3
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_io_getevents 4
+__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
+
+/* fs/xattr.c */
+#define __NR_setxattr 5
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 6
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 7
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 8
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 9
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 10
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 11
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 12
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 13
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 14
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 15
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 16
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+
+/* fs/dcache.c */
+#define __NR_getcwd 17
+__SYSCALL(__NR_getcwd, sys_getcwd)
+
+/* fs/cookies.c */
+#define __NR_lookup_dcookie 18
+__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
+
+/* fs/eventfd.c */
+#define __NR_eventfd2 19
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+
+/* fs/eventpoll.c */
+#define __NR_epoll_create1 20
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_epoll_ctl 21
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_pwait 22
+__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait)
+
+/* fs/fcntl.c */
+#define __NR_dup 23
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_dup3 24
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR3264_fcntl 25
+__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64)
+
+/* fs/inotify_user.c */
+#define __NR_inotify_init1 26
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_inotify_add_watch 27
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 28
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+
+/* fs/ioctl.c */
+#define __NR_ioctl 29
+__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)
+
+/* fs/ioprio.c */
+#define __NR_ioprio_set 30
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 31
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+
+/* fs/locks.c */
+#define __NR_flock 32
+__SYSCALL(__NR_flock, sys_flock)
+
+/* fs/namei.c */
+#define __NR_mknodat 33
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_mkdirat 34
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_unlinkat 35
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_symlinkat 36
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_linkat 37
+__SYSCALL(__NR_linkat, sys_linkat)
+#ifdef __ARCH_WANT_RENAMEAT
+/* renameat is superseded with flags by renameat2 */
+#define __NR_renameat 38
+__SYSCALL(__NR_renameat, sys_renameat)
+#endif /* __ARCH_WANT_RENAMEAT */
+
+/* fs/namespace.c */
+#define __NR_umount2 39
+__SYSCALL(__NR_umount2, sys_umount)
+#define __NR_mount 40
+__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+#define __NR_pivot_root 41
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+
+/* fs/nfsctl.c */
+#define __NR_nfsservctl 42
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+
+/* fs/open.c */
+#define __NR3264_statfs 43
+__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \
+	       compat_sys_statfs64)
+#define __NR3264_fstatfs 44
+__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \
+	       compat_sys_fstatfs64)
+#define __NR3264_truncate 45
+__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \
+	       compat_sys_truncate64)
+#define __NR3264_ftruncate 46
+__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \
+	       compat_sys_ftruncate64)
+
+#define __NR_fallocate 47
+__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate)
+#define __NR_faccessat 48
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_chdir 49
+__SYSCALL(__NR_chdir, sys_chdir)
+#define __NR_fchdir 50
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_chroot 51
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_fchmod 52
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchmodat 53
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_fchownat 54
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_fchown 55
+__SYSCALL(__NR_fchown, sys_fchown)
+#define __NR_openat 56
+__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
+#define __NR_close 57
+__SYSCALL(__NR_close, sys_close)
+#define __NR_vhangup 58
+__SYSCALL(__NR_vhangup, sys_vhangup)
+
+/* fs/pipe.c */
+#define __NR_pipe2 59
+__SYSCALL(__NR_pipe2, sys_pipe2)
+
+/* fs/quota.c */
+#define __NR_quotactl 60
+__SYSCALL(__NR_quotactl, sys_quotactl)
+
+/* fs/readdir.c */
+#define __NR_getdents64 61
+__SYSCALL(__NR_getdents64, sys_getdents64)
+
+/* fs/read_write.c */
+#define __NR3264_lseek 62
+__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek)
+#define __NR_read 63
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 64
+__SYSCALL(__NR_write, sys_write)
+#define __NR_readv 65
+__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+#define __NR_writev 66
+__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+#define __NR_pread64 67
+__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
+#define __NR_pwrite64 68
+__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
+#define __NR_preadv 69
+__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
+#define __NR_pwritev 70
+__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
+
+/* fs/sendfile.c */
+#define __NR3264_sendfile 71
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
+
+/* fs/select.c */
+#define __NR_pselect6 72
+__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
+#define __NR_ppoll 73
+__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
+
+/* fs/signalfd.c */
+#define __NR_signalfd4 74
+__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
+
+/* fs/splice.c */
+#define __NR_vmsplice 75
+__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+#define __NR_splice 76
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee 77
+__SYSCALL(__NR_tee, sys_tee)
+
+/* fs/stat.c */
+#define __NR_readlinkat 78
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR3264_fstatat 79
+__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
+#define __NR3264_fstat 80
+__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+
+/* fs/sync.c */
+#define __NR_sync 81
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_fsync 82
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_fdatasync 83
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#ifdef __ARCH_WANT_SYNC_FILE_RANGE2
+#define __NR_sync_file_range2 84
+__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \
+	  compat_sys_sync_file_range2)
+#else
+#define __NR_sync_file_range 84
+__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
+	  compat_sys_sync_file_range)
+#endif
+
+/* fs/timerfd.c */
+#define __NR_timerfd_create 85
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_timerfd_settime 86
+__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
+	  compat_sys_timerfd_settime)
+#define __NR_timerfd_gettime 87
+__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
+	  compat_sys_timerfd_gettime)
+
+/* fs/utimes.c */
+#define __NR_utimensat 88
+__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
+
+/* kernel/acct.c */
+#define __NR_acct 89
+__SYSCALL(__NR_acct, sys_acct)
+
+/* kernel/capability.c */
+#define __NR_capget 90
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 91
+__SYSCALL(__NR_capset, sys_capset)
+
+/* kernel/exec_domain.c */
+#define __NR_personality 92
+__SYSCALL(__NR_personality, sys_personality)
+
+/* kernel/exit.c */
+#define __NR_exit 93
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_exit_group 94
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_waitid 95
+__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid)
+
+/* kernel/fork.c */
+#define __NR_set_tid_address 96
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_unshare 97
+__SYSCALL(__NR_unshare, sys_unshare)
+
+/* kernel/futex.c */
+#define __NR_futex 98
+__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
+#define __NR_set_robust_list 99
+__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
+	  compat_sys_set_robust_list)
+#define __NR_get_robust_list 100
+__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
+	  compat_sys_get_robust_list)
+
+/* kernel/hrtimer.c */
+#define __NR_nanosleep 101
+__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
+
+/* kernel/itimer.c */
+#define __NR_getitimer 102
+__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer)
+#define __NR_setitimer 103
+__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer)
+
+/* kernel/kexec.c */
+#define __NR_kexec_load 104
+__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load)
+
+/* kernel/module.c */
+#define __NR_init_module 105
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 106
+__SYSCALL(__NR_delete_module, sys_delete_module)
+
+/* kernel/posix-timers.c */
+#define __NR_timer_create 107
+__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+#define __NR_timer_gettime 108
+__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
+#define __NR_timer_getoverrun 109
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_settime 110
+__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
+#define __NR_timer_delete 111
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime 112
+__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
+#define __NR_clock_gettime 113
+__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
+#define __NR_clock_getres 114
+__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
+#define __NR_clock_nanosleep 115
+__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
+	  compat_sys_clock_nanosleep)
+
+/* kernel/printk.c */
+#define __NR_syslog 116
+__SYSCALL(__NR_syslog, sys_syslog)
+
+/* kernel/ptrace.c */
+#define __NR_ptrace 117
+__SYSCALL(__NR_ptrace, sys_ptrace)
+
+/* kernel/sched/core.c */
+#define __NR_sched_setparam 118
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_setscheduler 119
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 120
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_getparam 121
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setaffinity 122
+__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \
+	  compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 123
+__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \
+	  compat_sys_sched_getaffinity)
+#define __NR_sched_yield 124
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 125
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 126
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval 127
+__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
+	  compat_sys_sched_rr_get_interval)
+
+/* kernel/signal.c */
+#define __NR_restart_syscall 128
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_kill 129
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_tkill 130
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_tgkill 131
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_sigaltstack 132
+__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack)
+#define __NR_rt_sigsuspend 133
+__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_rt_sigaction 134
+__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 135
+__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 136
+__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+#define __NR_rt_sigtimedwait 137
+__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
+	  compat_sys_rt_sigtimedwait)
+#define __NR_rt_sigqueueinfo 138
+__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
+	  compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigreturn 139
+__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn)
+
+/* kernel/sys.c */
+#define __NR_setpriority 140
+__SYSCALL(__NR_setpriority, sys_setpriority)
+#define __NR_getpriority 141
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_reboot 142
+__SYSCALL(__NR_reboot, sys_reboot)
+#define __NR_setregid 143
+__SYSCALL(__NR_setregid, sys_setregid)
+#define __NR_setgid 144
+__SYSCALL(__NR_setgid, sys_setgid)
+#define __NR_setreuid 145
+__SYSCALL(__NR_setreuid, sys_setreuid)
+#define __NR_setuid 146
+__SYSCALL(__NR_setuid, sys_setuid)
+#define __NR_setresuid 147
+__SYSCALL(__NR_setresuid, sys_setresuid)
+#define __NR_getresuid 148
+__SYSCALL(__NR_getresuid, sys_getresuid)
+#define __NR_setresgid 149
+__SYSCALL(__NR_setresgid, sys_setresgid)
+#define __NR_getresgid 150
+__SYSCALL(__NR_getresgid, sys_getresgid)
+#define __NR_setfsuid 151
+__SYSCALL(__NR_setfsuid, sys_setfsuid)
+#define __NR_setfsgid 152
+__SYSCALL(__NR_setfsgid, sys_setfsgid)
+#define __NR_times 153
+__SC_COMP(__NR_times, sys_times, compat_sys_times)
+#define __NR_setpgid 154
+__SYSCALL(__NR_setpgid, sys_setpgid)
+#define __NR_getpgid 155
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_getsid 156
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_setsid 157
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_getgroups 158
+__SYSCALL(__NR_getgroups, sys_getgroups)
+#define __NR_setgroups 159
+__SYSCALL(__NR_setgroups, sys_setgroups)
+#define __NR_uname 160
+__SYSCALL(__NR_uname, sys_newuname)
+#define __NR_sethostname 161
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setdomainname 162
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+#define __NR_getrlimit 163
+__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
+#define __NR_setrlimit 164
+__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#define __NR_getrusage 165
+__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
+#define __NR_umask 166
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_prctl 167
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_getcpu 168
+__SYSCALL(__NR_getcpu, sys_getcpu)
+
+/* kernel/time.c */
+#define __NR_gettimeofday 169
+__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 170
+__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
+#define __NR_adjtimex 171
+__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
+
+/* kernel/timer.c */
+#define __NR_getpid 172
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_getppid 173
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getuid 174
+__SYSCALL(__NR_getuid, sys_getuid)
+#define __NR_geteuid 175
+__SYSCALL(__NR_geteuid, sys_geteuid)
+#define __NR_getgid 176
+__SYSCALL(__NR_getgid, sys_getgid)
+#define __NR_getegid 177
+__SYSCALL(__NR_getegid, sys_getegid)
+#define __NR_gettid 178
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_sysinfo 179
+__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
+
+/* ipc/mqueue.c */
+#define __NR_mq_open 180
+__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 181
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend 182
+__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
+#define __NR_mq_timedreceive 183
+__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
+	  compat_sys_mq_timedreceive)
+#define __NR_mq_notify 184
+__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 185
+__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr)
+
+/* ipc/msg.c */
+#define __NR_msgget 186
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 187
+__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl)
+#define __NR_msgrcv 188
+__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv)
+#define __NR_msgsnd 189
+__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
+
+/* ipc/sem.c */
+#define __NR_semget 190
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 191
+__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+#define __NR_semtimedop 192
+__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
+#define __NR_semop 193
+__SYSCALL(__NR_semop, sys_semop)
+
+/* ipc/shm.c */
+#define __NR_shmget 194
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 195
+__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl)
+#define __NR_shmat 196
+__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat)
+#define __NR_shmdt 197
+__SYSCALL(__NR_shmdt, sys_shmdt)
+
+/* net/socket.c */
+#define __NR_socket 198
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_socketpair 199
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_bind 200
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_listen 201
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 202
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_connect 203
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_getsockname 204
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 205
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_sendto 206
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recvfrom 207
+__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
+#define __NR_setsockopt 208
+__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
+#define __NR_getsockopt 209
+__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
+#define __NR_shutdown 210
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_sendmsg 211
+__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 212
+__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg)
+
+/* mm/filemap.c */
+#define __NR_readahead 213
+__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead)
+
+/* mm/nommu.c, also with MMU */
+#define __NR_brk 214
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_munmap 215
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_mremap 216
+__SYSCALL(__NR_mremap, sys_mremap)
+
+/* security/keys/keyctl.c */
+#define __NR_add_key 217
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 218
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 219
+__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl)
+
+/* arch/example/kernel/sys_example.c */
+#define __NR_clone 220
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_execve 221
+__SC_COMP(__NR_execve, sys_execve, compat_sys_execve)
+
+#define __NR3264_mmap 222
+__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
+/* mm/fadvise.c */
+#define __NR3264_fadvise64 223
+__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64)
+
+/* mm/, CONFIG_MMU only */
+#ifndef __ARCH_NOMMU
+#define __NR_swapon 224
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_swapoff 225
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_mprotect 226
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_msync 227
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_mlock 228
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 229
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 230
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 231
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_mincore 232
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 233
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_remap_file_pages 234
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+#define __NR_mbind 235
+__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind)
+#define __NR_get_mempolicy 236
+__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy)
+#define __NR_set_mempolicy 237
+__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy)
+#define __NR_migrate_pages 238
+__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages)
+#define __NR_move_pages 239
+__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages)
+#endif
+
+#define __NR_rt_tgsigqueueinfo 240
+__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
+	  compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 241
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_accept4 242
+__SYSCALL(__NR_accept4, sys_accept4)
+#define __NR_recvmmsg 243
+__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
+
+/*
+ * Architectures may provide up to 16 syscalls of their own
+ * starting with this value.
+ */
+#define __NR_arch_specific_syscall 244
+
+#define __NR_wait4 260
+__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#define __NR_prlimit64 261
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_fanotify_init 262
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 263
+__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at         264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at         265
+__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
+	  compat_sys_open_by_handle_at)
+#define __NR_clock_adjtime 266
+__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
+#define __NR_syncfs 267
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_setns 268
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
+#define __NR_process_vm_readv 270
+__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
+          compat_sys_process_vm_readv)
+#define __NR_process_vm_writev 271
+__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
+          compat_sys_process_vm_writev)
+#define __NR_kcmp 272
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 273
+__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 276
+__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
+#define __NR_getrandom 278
+__SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 279
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
+#define __NR_bpf 280
+__SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
+__SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 284
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 285
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 286
+__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 287
+__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 288
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 289
+__SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
+#define __NR_pkey_free 290
+__SYSCALL(__NR_pkey_free,     sys_pkey_free)
+#define __NR_statx 291
+__SYSCALL(__NR_statx,     sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+
+#undef __NR_syscalls
+#define __NR_syscalls 293
+
+/*
+ * 32 bit systems traditionally used different
+ * syscalls for off_t and loff_t arguments, while
+ * 64 bit systems only need the off_t version.
+ * For new 32 bit platforms, there is no need to
+ * implement the old 32 bit off_t syscalls, so
+ * they take different names.
+ * Here we map the numbers so that both versions
+ * use the same syscall table layout.
+ */
+#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT)
+#define __NR_fcntl __NR3264_fcntl
+#define __NR_statfs __NR3264_statfs
+#define __NR_fstatfs __NR3264_fstatfs
+#define __NR_truncate __NR3264_truncate
+#define __NR_ftruncate __NR3264_ftruncate
+#define __NR_lseek __NR3264_lseek
+#define __NR_sendfile __NR3264_sendfile
+#define __NR_newfstatat __NR3264_fstatat
+#define __NR_fstat __NR3264_fstat
+#define __NR_mmap __NR3264_mmap
+#define __NR_fadvise64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat __NR3264_stat
+#define __NR_lstat __NR3264_lstat
+#endif
+#else
+#define __NR_fcntl64 __NR3264_fcntl
+#define __NR_statfs64 __NR3264_statfs
+#define __NR_fstatfs64 __NR3264_fstatfs
+#define __NR_truncate64 __NR3264_truncate
+#define __NR_ftruncate64 __NR3264_ftruncate
+#define __NR_llseek __NR3264_lseek
+#define __NR_sendfile64 __NR3264_sendfile
+#define __NR_fstatat64 __NR3264_fstatat
+#define __NR_fstat64 __NR3264_fstat
+#define __NR_mmap2 __NR3264_mmap
+#define __NR_fadvise64_64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat64 __NR3264_stat
+#define __NR_lstat64 __NR3264_lstat
+#endif
+#endif
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 6fdff5945c8a..9c660e1688ab 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -680,6 +680,13 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO    4
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e0b06784f227..b7db3261c62d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1857,7 +1857,8 @@ union bpf_attr {
  *		is resolved), the nexthop address is returned in ipv4_dst
  *		or ipv6_dst based on family, smac is set to mac address of
  *		egress device, dmac is set to nexthop mac address, rt_metric
- *		is set to metric from route (IPv4/IPv6 only).
+ *		is set to metric from route (IPv4/IPv6 only), and ifindex
+ *		is set to the device index of the nexthop from the FIB lookup.
  *
  *             *plen* argument is the size of the passed in struct.
  *             *flags* argument can be a combination of one or more of the
@@ -1873,9 +1874,10 @@ union bpf_attr {
  *             *ctx* is either **struct xdp_md** for XDP programs or
  *             **struct sk_buff** tc cls_act programs.
  *     Return
- *             Egress device index on success, 0 if packet needs to continue
- *             up the stack for further processing or a negative error in case
- *             of failure.
+ *		* < 0 if any input argument is invalid
+ *		*   0 on success (packet is forwarded, nexthop neighbor exists)
+ *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ *		*     packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
@@ -2612,6 +2614,18 @@ struct bpf_raw_tracepoint_args {
 #define BPF_FIB_LOOKUP_DIRECT  BIT(0)
 #define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
 
+enum {
+	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
+	BPF_FIB_LKUP_RET_BLACKHOLE,    /* dest is blackholed; can be dropped */
+	BPF_FIB_LKUP_RET_UNREACHABLE,  /* dest is unreachable; can be dropped */
+	BPF_FIB_LKUP_RET_PROHIBIT,     /* dest not allowed; can be dropped */
+	BPF_FIB_LKUP_RET_NOT_FWDED,    /* packet is not forwarded */
+	BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
+	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
+	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+};
+
 struct bpf_fib_lookup {
 	/* input:  network family for lookup (AF_INET, AF_INET6)
 	 * output: network family of egress nexthop
@@ -2625,12 +2639,16 @@ struct bpf_fib_lookup {
 
 	/* total length of packet from network header - used for MTU check */
 	__u16	tot_len;
-	__u32	ifindex;  /* L3 device index for lookup */
+
+	/* input: L3 device index for lookup
+	 * output: device index from FIB lookup
+	 */
+	__u32	ifindex;
 
 	union {
 		/* inputs to lookup */
 		__u8	tos;		/* AF_INET  */
-		__be32	flowlabel;	/* AF_INET6 */
+		__be32	flowinfo;	/* AF_INET6, flow_label + priority */
 
 		/* output: metric of fib result (IPv4/IPv6 only) */
 		__u32	rt_metric;
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 0b5ddbe135a4..972265f32871 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -76,7 +76,7 @@ struct btf_type {
  */
 #define BTF_INT_ENCODING(VAL)	(((VAL) & 0x0f000000) >> 24)
 #define BTF_INT_OFFSET(VAL)	(((VAL  & 0x00ff0000)) >> 16)
-#define BTF_INT_BITS(VAL)	((VAL)  & 0x0000ffff)
+#define BTF_INT_BITS(VAL)	((VAL)  & 0x000000ff)
 
 /* Attributes stored in the BTF_INT_ENCODING */
 #define BTF_INT_SIGNED	(1 << 0)
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 68699f654118..cf01b6824244 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -333,6 +333,7 @@ enum {
 	IFLA_BRPORT_BCAST_FLOOD,
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
+	IFLA_BRPORT_ISOLATED,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -516,6 +517,7 @@ enum {
 	IFLA_VXLAN_COLLECT_METADATA,
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
+	IFLA_VXLAN_TTL_INHERIT,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
new file mode 100644
index 000000000000..48e8a225b985
--- /dev/null
+++ b/tools/include/uapi/linux/in.h
@@ -0,0 +1,301 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions of the Internet Protocol.
+ *
+ * Version:	@(#)in.h	1.0.1	04/21/93
+ *
+ * Authors:	Original taken from the GNU Project <netinet/in.h> file.
+ *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_LINUX_IN_H
+#define _UAPI_LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols.  */
+enum {
+  IPPROTO_IP = 0,		/* Dummy protocol for TCP		*/
+#define IPPROTO_IP		IPPROTO_IP
+  IPPROTO_ICMP = 1,		/* Internet Control Message Protocol	*/
+#define IPPROTO_ICMP		IPPROTO_ICMP
+  IPPROTO_IGMP = 2,		/* Internet Group Management Protocol	*/
+#define IPPROTO_IGMP		IPPROTO_IGMP
+  IPPROTO_IPIP = 4,		/* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP		IPPROTO_IPIP
+  IPPROTO_TCP = 6,		/* Transmission Control Protocol	*/
+#define IPPROTO_TCP		IPPROTO_TCP
+  IPPROTO_EGP = 8,		/* Exterior Gateway Protocol		*/
+#define IPPROTO_EGP		IPPROTO_EGP
+  IPPROTO_PUP = 12,		/* PUP protocol				*/
+#define IPPROTO_PUP		IPPROTO_PUP
+  IPPROTO_UDP = 17,		/* User Datagram Protocol		*/
+#define IPPROTO_UDP		IPPROTO_UDP
+  IPPROTO_IDP = 22,		/* XNS IDP protocol			*/
+#define IPPROTO_IDP		IPPROTO_IDP
+  IPPROTO_TP = 29,		/* SO Transport Protocol Class 4	*/
+#define IPPROTO_TP		IPPROTO_TP
+  IPPROTO_DCCP = 33,		/* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP		IPPROTO_DCCP
+  IPPROTO_IPV6 = 41,		/* IPv6-in-IPv4 tunnelling		*/
+#define IPPROTO_IPV6		IPPROTO_IPV6
+  IPPROTO_RSVP = 46,		/* RSVP Protocol			*/
+#define IPPROTO_RSVP		IPPROTO_RSVP
+  IPPROTO_GRE = 47,		/* Cisco GRE tunnels (rfc 1701,1702)	*/
+#define IPPROTO_GRE		IPPROTO_GRE
+  IPPROTO_ESP = 50,		/* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP		IPPROTO_ESP
+  IPPROTO_AH = 51,		/* Authentication Header protocol	*/
+#define IPPROTO_AH		IPPROTO_AH
+  IPPROTO_MTP = 92,		/* Multicast Transport Protocol		*/
+#define IPPROTO_MTP		IPPROTO_MTP
+  IPPROTO_BEETPH = 94,		/* IP option pseudo header for BEET	*/
+#define IPPROTO_BEETPH		IPPROTO_BEETPH
+  IPPROTO_ENCAP = 98,		/* Encapsulation Header			*/
+#define IPPROTO_ENCAP		IPPROTO_ENCAP
+  IPPROTO_PIM = 103,		/* Protocol Independent Multicast	*/
+#define IPPROTO_PIM		IPPROTO_PIM
+  IPPROTO_COMP = 108,		/* Compression Header Protocol		*/
+#define IPPROTO_COMP		IPPROTO_COMP
+  IPPROTO_SCTP = 132,		/* Stream Control Transport Protocol	*/
+#define IPPROTO_SCTP		IPPROTO_SCTP
+  IPPROTO_UDPLITE = 136,	/* UDP-Lite (RFC 3828)			*/
+#define IPPROTO_UDPLITE		IPPROTO_UDPLITE
+  IPPROTO_MPLS = 137,		/* MPLS in IP (RFC 4023)		*/
+#define IPPROTO_MPLS		IPPROTO_MPLS
+  IPPROTO_RAW = 255,		/* Raw IP packets			*/
+#define IPPROTO_RAW		IPPROTO_RAW
+  IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+	__be32	s_addr;
+};
+#endif
+
+#define IP_TOS		1
+#define IP_TTL		2
+#define IP_HDRINCL	3
+#define IP_OPTIONS	4
+#define IP_ROUTER_ALERT	5
+#define IP_RECVOPTS	6
+#define IP_RETOPTS	7
+#define IP_PKTINFO	8
+#define IP_PKTOPTIONS	9
+#define IP_MTU_DISCOVER	10
+#define IP_RECVERR	11
+#define IP_RECVTTL	12
+#define	IP_RECVTOS	13
+#define IP_MTU		14
+#define IP_FREEBIND	15
+#define IP_IPSEC_POLICY	16
+#define IP_XFRM_POLICY	17
+#define IP_PASSSEC	18
+#define IP_TRANSPARENT	19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS	IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR       20
+#define IP_RECVORIGDSTADDR   IP_ORIGDSTADDR
+
+#define IP_MINTTL       21
+#define IP_NODEFRAG     22
+#define IP_CHECKSUM	23
+#define IP_BIND_ADDRESS_NO_PORT	24
+#define IP_RECVFRAGSIZE	25
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT		0	/* Never send DF frames */
+#define IP_PMTUDISC_WANT		1	/* Use per route hints	*/
+#define IP_PMTUDISC_DO			2	/* Always DF		*/
+#define IP_PMTUDISC_PROBE		3       /* Ignore dst pmtu      */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE		4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT		5
+
+#define IP_MULTICAST_IF			32
+#define IP_MULTICAST_TTL 		33
+#define IP_MULTICAST_LOOP 		34
+#define IP_ADD_MEMBERSHIP		35
+#define IP_DROP_MEMBERSHIP		36
+#define IP_UNBLOCK_SOURCE		37
+#define IP_BLOCK_SOURCE			38
+#define IP_ADD_SOURCE_MEMBERSHIP	39
+#define IP_DROP_SOURCE_MEMBERSHIP	40
+#define IP_MSFILTER			41
+#define MCAST_JOIN_GROUP		42
+#define MCAST_BLOCK_SOURCE		43
+#define MCAST_UNBLOCK_SOURCE		44
+#define MCAST_LEAVE_GROUP		45
+#define MCAST_JOIN_SOURCE_GROUP		46
+#define MCAST_LEAVE_SOURCE_GROUP	47
+#define MCAST_MSFILTER			48
+#define IP_MULTICAST_ALL		49
+#define IP_UNICAST_IF			50
+
+#define MCAST_EXCLUDE	0
+#define MCAST_INCLUDE	1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL        1
+#define IP_DEFAULT_MULTICAST_LOOP       1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq  {
+	struct in_addr imr_multiaddr;	/* IP multicast address of group */
+	struct in_addr imr_interface;	/* local IP address of interface */
+};
+
+struct ip_mreqn {
+	struct in_addr	imr_multiaddr;		/* IP multicast address of group */
+	struct in_addr	imr_address;		/* local IP address of interface */
+	int		imr_ifindex;		/* Interface index */
+};
+
+struct ip_mreq_source {
+	__be32		imr_multiaddr;
+	__be32		imr_interface;
+	__be32		imr_sourceaddr;
+};
+
+struct ip_msfilter {
+	__be32		imsf_multiaddr;
+	__be32		imsf_interface;
+	__u32		imsf_fmode;
+	__u32		imsf_numsrc;
+	__be32		imsf_slist[1];
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+	(sizeof(struct ip_msfilter) - sizeof(__u32) \
+	+ (numsrc) * sizeof(__u32))
+
+struct group_req {
+	__u32				 gr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gr_group;	/* group address */
+};
+
+struct group_source_req {
+	__u32				 gsr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gsr_group;	/* group address */
+	struct __kernel_sockaddr_storage gsr_source;	/* source address */
+};
+
+struct group_filter {
+	__u32				 gf_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gf_group;	/* multicast address */
+	__u32				 gf_fmode;	/* filter mode */
+	__u32				 gf_numsrc;	/* number of sources */
+	struct __kernel_sockaddr_storage gf_slist[1];	/* interface index */
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+	(sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+	+ (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+	int		ipi_ifindex;
+	struct in_addr	ipi_spec_dst;
+	struct in_addr	ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if  __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__	16		/* sizeof(struct sockaddr)	*/
+struct sockaddr_in {
+  __kernel_sa_family_t	sin_family;	/* Address family		*/
+  __be16		sin_port;	/* Port number			*/
+  struct in_addr	sin_addr;	/* Internet address		*/
+
+  /* Pad to size of `struct sockaddr'. */
+  unsigned char		__pad[__SOCK_SIZE__ - sizeof(short int) -
+			sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero	__pad		/* for BSD UNIX comp. -FvK	*/
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define	IN_CLASSA(a)		((((long int) (a)) & 0x80000000) == 0)
+#define	IN_CLASSA_NET		0xff000000
+#define	IN_CLASSA_NSHIFT	24
+#define	IN_CLASSA_HOST		(0xffffffff & ~IN_CLASSA_NET)
+#define	IN_CLASSA_MAX		128
+
+#define	IN_CLASSB(a)		((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define	IN_CLASSB_NET		0xffff0000
+#define	IN_CLASSB_NSHIFT	16
+#define	IN_CLASSB_HOST		(0xffffffff & ~IN_CLASSB_NET)
+#define	IN_CLASSB_MAX		65536
+
+#define	IN_CLASSC(a)		((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define	IN_CLASSC_NET		0xffffff00
+#define	IN_CLASSC_NSHIFT	8
+#define	IN_CLASSC_HOST		(0xffffffff & ~IN_CLASSC_NET)
+
+#define	IN_CLASSD(a)		((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define	IN_MULTICAST(a)		IN_CLASSD(a)
+#define IN_MULTICAST_NET	0xF0000000
+
+#define	IN_EXPERIMENTAL(a)	((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define	IN_BADCLASS(a)		IN_EXPERIMENTAL((a))
+
+/* Address to accept any incoming messages. */
+#define	INADDR_ANY		((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define	INADDR_BROADCAST	((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define	INADDR_NONE		((unsigned long int) 0xffffffff)
+
+/* Network number for local host loopback. */
+#define	IN_LOOPBACKNET		127
+
+/* Address to loopback in software to local host.  */
+#define	INADDR_LOOPBACK		0x7f000001	/* 127.0.0.1   */
+#define	IN_LOOPBACK(a)		((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP   	0xe0000000U	/* 224.0.0.0   */
+#define INADDR_ALLHOSTS_GROUP 	0xe0000001U	/* 224.0.0.1   */
+#define INADDR_ALLRTRS_GROUP    0xe0000002U	/* 224.0.0.2 */
+#define INADDR_MAX_LOCAL_GROUP  0xe00000ffU	/* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h> 
+
+
+#endif /* _UAPI_LINUX_IN_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 39e364c70caf..b6270a3b38e9 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -948,6 +948,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_BPB 152
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index b8e288a1f740..eeb787b1c53c 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -143,6 +143,8 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
+
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
 };
 
 /*
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 8c54a4b6f187..c36a3a76986a 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,8 +1,7 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: LGPL-2.1
 /* Copyright (c) 2018 Facebook */
 
 #include <stdlib.h>
-#include <stdint.h>
 #include <string.h>
 #include <unistd.h>
 #include <errno.h>
@@ -27,13 +26,13 @@ struct btf {
 	struct btf_type **types;
 	const char *strings;
 	void *nohdr_data;
-	uint32_t nr_types;
-	uint32_t types_size;
-	uint32_t data_size;
+	__u32 nr_types;
+	__u32 types_size;
+	__u32 data_size;
 	int fd;
 };
 
-static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset)
+static const char *btf_name_by_offset(const struct btf *btf, __u32 offset)
 {
 	if (offset < btf->hdr->str_len)
 		return &btf->strings[offset];
@@ -45,7 +44,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t)
 {
 	if (btf->types_size - btf->nr_types < 2) {
 		struct btf_type **new_types;
-		u32 expand_by, new_size;
+		__u32 expand_by, new_size;
 
 		if (btf->types_size == BTF_MAX_NR_TYPES)
 			return -E2BIG;
@@ -72,7 +71,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t)
 static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log)
 {
 	const struct btf_header *hdr = btf->hdr;
-	u32 meta_left;
+	__u32 meta_left;
 
 	if (btf->data_size < sizeof(struct btf_header)) {
 		elog("BTF header not found\n");
@@ -151,7 +150,7 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
 
 	while (next_type < end_type) {
 		struct btf_type *t = next_type;
-		uint16_t vlen = BTF_INFO_VLEN(t->info);
+		__u16 vlen = BTF_INFO_VLEN(t->info);
 		int err;
 
 		next_type += sizeof(*t);
@@ -190,8 +189,7 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
 	return 0;
 }
 
-static const struct btf_type *btf_type_by_id(const struct btf *btf,
-					     uint32_t type_id)
+const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 {
 	if (type_id > btf->nr_types)
 		return NULL;
@@ -209,7 +207,7 @@ static bool btf_type_is_void_or_null(const struct btf_type *t)
 	return !t || btf_type_is_void(t);
 }
 
-static int64_t btf_type_size(const struct btf_type *t)
+static __s64 btf_type_size(const struct btf_type *t)
 {
 	switch (BTF_INFO_KIND(t->info)) {
 	case BTF_KIND_INT:
@@ -226,15 +224,15 @@ static int64_t btf_type_size(const struct btf_type *t)
 
 #define MAX_RESOLVE_DEPTH 32
 
-int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
+__s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 {
 	const struct btf_array *array;
 	const struct btf_type *t;
-	uint32_t nelems = 1;
-	int64_t size = -1;
+	__u32 nelems = 1;
+	__s64 size = -1;
 	int i;
 
-	t = btf_type_by_id(btf, type_id);
+	t = btf__type_by_id(btf, type_id);
 	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
 	     i++) {
 		size = btf_type_size(t);
@@ -259,7 +257,7 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
 			return -EINVAL;
 		}
 
-		t = btf_type_by_id(btf, type_id);
+		t = btf__type_by_id(btf, type_id);
 	}
 
 	if (size < 0)
@@ -271,9 +269,9 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
 	return nelems * size;
 }
 
-int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
+__s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 {
-	uint32_t i;
+	__u32 i;
 
 	if (!strcmp(type_name, "void"))
 		return 0;
@@ -302,10 +300,9 @@ void btf__free(struct btf *btf)
 	free(btf);
 }
 
-struct btf *btf__new(uint8_t *data, uint32_t size,
-		     btf_print_fn_t err_log)
+struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
 {
-	uint32_t log_buf_size = 0;
+	__u32 log_buf_size = 0;
 	char *log_buf = NULL;
 	struct btf *btf;
 	int err;
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 74bb344035bb..caac3a404dc5 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -1,22 +1,24 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: LGPL-2.1 */
 /* Copyright (c) 2018 Facebook */
 
 #ifndef __BPF_BTF_H
 #define __BPF_BTF_H
 
-#include <stdint.h>
+#include <linux/types.h>
 
 #define BTF_ELF_SEC ".BTF"
 
 struct btf;
+struct btf_type;
 
 typedef int (*btf_print_fn_t)(const char *, ...)
 	__attribute__((format(printf, 1, 2)));
 
 void btf__free(struct btf *btf);
-struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log);
-int32_t btf__find_by_name(const struct btf *btf, const char *type_name);
-int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id);
+struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
+__s32 btf__find_by_name(const struct btf *btf, const char *type_name);
+const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id);
+__s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 int btf__fd(const struct btf *btf);
 
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a1e96b5de5ff..1aafdbe827fe 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -36,6 +36,7 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <sys/stat.h>
@@ -216,8 +217,8 @@ struct bpf_map {
 	size_t offset;
 	int map_ifindex;
 	struct bpf_map_def def;
-	uint32_t btf_key_type_id;
-	uint32_t btf_value_type_id;
+	__u32 btf_key_type_id;
+	__u32 btf_value_type_id;
 	void *priv;
 	bpf_map_clear_priv_t clear_priv;
 };
@@ -1014,68 +1015,72 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 
 static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
 {
+	const struct btf_type *container_type;
+	const struct btf_member *key, *value;
 	struct bpf_map_def *def = &map->def;
 	const size_t max_name = 256;
-	int64_t key_size, value_size;
-	int32_t key_id, value_id;
-	char name[max_name];
+	char container_name[max_name];
+	__s64 key_size, value_size;
+	__s32 container_id;
 
-	/* Find key type by name from BTF */
-	if (snprintf(name, max_name, "%s_key", map->name) == max_name) {
-		pr_warning("map:%s length of BTF key_type:%s_key is too long\n",
+	if (snprintf(container_name, max_name, "____btf_map_%s", map->name) ==
+	    max_name) {
+		pr_warning("map:%s length of '____btf_map_%s' is too long\n",
 			   map->name, map->name);
 		return -EINVAL;
 	}
 
-	key_id = btf__find_by_name(btf, name);
-	if (key_id < 0) {
-		pr_debug("map:%s key_type:%s cannot be found in BTF\n",
-			 map->name, name);
-		return key_id;
+	container_id = btf__find_by_name(btf, container_name);
+	if (container_id < 0) {
+		pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
+			 map->name, container_name);
+		return container_id;
 	}
 
-	key_size = btf__resolve_size(btf, key_id);
-	if (key_size < 0) {
-		pr_warning("map:%s key_type:%s cannot get the BTF type_size\n",
-			   map->name, name);
-		return key_size;
+	container_type = btf__type_by_id(btf, container_id);
+	if (!container_type) {
+		pr_warning("map:%s cannot find BTF type for container_id:%u\n",
+			   map->name, container_id);
+		return -EINVAL;
 	}
 
-	if (def->key_size != key_size) {
-		pr_warning("map:%s key_type:%s has BTF type_size:%u != key_size:%u\n",
-			   map->name, name, (unsigned int)key_size, def->key_size);
+	if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
+	    BTF_INFO_VLEN(container_type->info) < 2) {
+		pr_warning("map:%s container_name:%s is an invalid container struct\n",
+			   map->name, container_name);
 		return -EINVAL;
 	}
 
-	/* Find value type from BTF */
-	if (snprintf(name, max_name, "%s_value", map->name) == max_name) {
-		pr_warning("map:%s length of BTF value_type:%s_value is too long\n",
-			  map->name, map->name);
-		return -EINVAL;
+	key = (struct btf_member *)(container_type + 1);
+	value = key + 1;
+
+	key_size = btf__resolve_size(btf, key->type);
+	if (key_size < 0) {
+		pr_warning("map:%s invalid BTF key_type_size\n",
+			   map->name);
+		return key_size;
 	}
 
-	value_id = btf__find_by_name(btf, name);
-	if (value_id < 0) {
-		pr_debug("map:%s value_type:%s cannot be found in BTF\n",
-			 map->name, name);
-		return value_id;
+	if (def->key_size != key_size) {
+		pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
+			   map->name, (__u32)key_size, def->key_size);
+		return -EINVAL;
 	}
 
-	value_size = btf__resolve_size(btf, value_id);
+	value_size = btf__resolve_size(btf, value->type);
 	if (value_size < 0) {
-		pr_warning("map:%s value_type:%s cannot get the BTF type_size\n",
-			   map->name, name);
+		pr_warning("map:%s invalid BTF value_type_size\n", map->name);
 		return value_size;
 	}
 
 	if (def->value_size != value_size) {
-		pr_warning("map:%s value_type:%s has BTF type_size:%u != value_size:%u\n",
-			   map->name, name, (unsigned int)value_size, def->value_size);
+		pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
+			   map->name, (__u32)value_size, def->value_size);
 		return -EINVAL;
 	}
 
-	map->btf_key_type_id = key_id;
-	map->btf_value_type_id = value_id;
+	map->btf_key_type_id = key->type;
+	map->btf_value_type_id = value->type;
 
 	return 0;
 }
@@ -2089,12 +2094,12 @@ const char *bpf_map__name(struct bpf_map *map)
 	return map ? map->name : NULL;
 }
 
-uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map)
+__u32 bpf_map__btf_key_type_id(const struct bpf_map *map)
 {
 	return map ? map->btf_key_type_id : 0;
 }
 
-uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map)
+__u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
 {
 	return map ? map->btf_value_type_id : 0;
 }
@@ -2268,8 +2273,8 @@ bpf_perf_event_read_simple(void *mem, unsigned long size,
 	volatile struct perf_event_mmap_page *header = mem;
 	__u64 data_tail = header->data_tail;
 	__u64 data_head = header->data_head;
+	int ret = LIBBPF_PERF_EVENT_ERROR;
 	void *base, *begin, *end;
-	int ret;
 
 	asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */
 	if (data_head == data_tail)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 09976531aa74..b33ae02f7d0e 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -244,8 +244,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
 int bpf_map__fd(struct bpf_map *map);
 const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
 const char *bpf_map__name(struct bpf_map *map);
-uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map);
-uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map);
+__u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
+__u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 int bpf_map__set_priv(struct bpf_map *map, void *priv,
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 1b09f3175a1f..0cbd1ef8f86d 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -804,7 +804,7 @@ type of fence:
 Second, some types of fence affect the way the memory subsystem
 propagates stores.  When a fence instruction is executed on CPU C:
 
-	For each other CPU C', smb_wmb() forces all po-earlier stores
+	For each other CPU C', smp_wmb() forces all po-earlier stores
 	on C to propagate to C' before any po-later stores do.
 
 	For each other CPU C', any store which propagates to C before
diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt
index ee4309a87fc4..af72700cc20a 100644
--- a/tools/memory-model/Documentation/recipes.txt
+++ b/tools/memory-model/Documentation/recipes.txt
@@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by
 locking will be seen as ordered by CPUs not holding that lock.
 Consider this example:
 
-	/* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */
+	/* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */
 	void CPU0(void)
 	{
 		spin_lock(&mylock);
@@ -292,7 +292,7 @@ and to use smp_load_acquire() instead of smp_rmb().  However, the older
 smp_wmb() and smp_rmb() APIs are still heavily used, so it is important
 to understand their use cases.  The general approach is shown below:
 
-	/* See MP+wmbonceonce+rmbonceonce.litmus. */
+	/* See MP+fencewmbonceonce+fencermbonceonce.litmus. */
 	void CPU0(void)
 	{
 		WRITE_ONCE(x, 1);
@@ -322,9 +322,9 @@ the following write-side code fragment:
 And the xlog_valid_lsn() function in fs/xfs/xfs_log_priv.h contains
 the corresponding read-side code fragment:
 
-	cur_cycle = ACCESS_ONCE(log->l_curr_cycle);
+	cur_cycle = READ_ONCE(log->l_curr_cycle);
 	smp_rmb();
-	cur_block = ACCESS_ONCE(log->l_curr_block);
+	cur_block = READ_ONCE(log->l_curr_block);
 
 Alternatively, consider the following comment in function
 perf_output_put_handle() in kernel/events/ring_buffer.c:
@@ -360,7 +360,7 @@ can be seen in the LB+poonceonces.litmus litmus test.
 One way of avoiding the counter-intuitive outcome is through the use of a
 control dependency paired with a full memory barrier:
 
-	/* See LB+ctrlonceonce+mbonceonce.litmus. */
+	/* See LB+fencembonceonce+ctrlonceonce.litmus. */
 	void CPU0(void)
 	{
 		r0 = READ_ONCE(x);
@@ -476,7 +476,7 @@ that one CPU first stores to one variable and then loads from a second,
 while another CPU stores to the second variable and then loads from the
 first.  Preserving order requires nothing less than full barriers:
 
-	/* See SB+mbonceonces.litmus. */
+	/* See SB+fencembonceonces.litmus. */
 	void CPU0(void)
 	{
 		WRITE_ONCE(x, 1);
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 734f7feaa5dc..ee987ce20aae 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -35,13 +35,13 @@ BASIC USAGE: HERD7
 The memory model is used, in conjunction with "herd7", to exhaustively
 explore the state space of small litmus tests.
 
-For example, to run SB+mbonceonces.litmus against the memory model:
+For example, to run SB+fencembonceonces.litmus against the memory model:
 
-  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+mbonceonces.litmus
+  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+fencembonceonces.litmus
 
 Here is the corresponding output:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   States 3
   0:r0=0; 1:r0=1;
   0:r0=1; 1:r0=0;
@@ -50,8 +50,8 @@ Here is the corresponding output:
   Witnesses
   Positive: 0 Negative: 3
   Condition exists (0:r0=0 /\ 1:r0=0)
-  Observation SB+mbonceonces Never 0 3
-  Time SB+mbonceonces 0.01
+  Observation SB+fencembonceonces Never 0 3
+  Time SB+fencembonceonces 0.01
   Hash=d66d99523e2cac6b06e66f4c995ebb48
 
 The "Positive: 0 Negative: 3" and the "Never 0 3" each indicate that
@@ -67,16 +67,16 @@ BASIC USAGE: KLITMUS7
 The "klitmus7" tool converts a litmus test into a Linux kernel module,
 which may then be loaded and run.
 
-For example, to run SB+mbonceonces.litmus against hardware:
+For example, to run SB+fencembonceonces.litmus against hardware:
 
   $ mkdir mymodules
-  $ klitmus7 -o mymodules litmus-tests/SB+mbonceonces.litmus
+  $ klitmus7 -o mymodules litmus-tests/SB+fencembonceonces.litmus
   $ cd mymodules ; make
   $ sudo sh run.sh
 
 The corresponding output includes:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   Histogram (3 states)
   644580  :>0:r0=1; 1:r0=0;
   644328  :>0:r0=0; 1:r0=1;
@@ -86,8 +86,8 @@ The corresponding output includes:
   Positive: 0, Negative: 2000000
   Condition exists (0:r0=0 /\ 1:r0=0) is NOT validated
   Hash=d66d99523e2cac6b06e66f4c995ebb48
-  Observation SB+mbonceonces Never 0 2000000
-  Time SB+mbonceonces 0.16
+  Observation SB+fencembonceonces Never 0 2000000
+  Time SB+fencembonceonces 0.16
 
 The "Positive: 0 Negative: 2000000" and the "Never 0 2000000" indicate
 that during two million trials, the state specified in this litmus
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 64f5740e0e75..b84fb2f67109 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -13,7 +13,7 @@
 
 "Linux-kernel memory consistency model"
 
-enum Accesses = 'once (*READ_ONCE,WRITE_ONCE,ACCESS_ONCE*) ||
+enum Accesses = 'once (*READ_ONCE,WRITE_ONCE*) ||
 		'release (*smp_store_release*) ||
 		'acquire (*smp_load_acquire*) ||
 		'noreturn (* R of non-return RMW *)
diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
index 98a3716efa37..e729d2776e89 100644
--- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
+++ b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
@@ -1,4 +1,4 @@
-C IRIW+mbonceonces+OnceOnce
+C IRIW+fencembonceonces+OnceOnce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
index 7a39a0aaa976..0f749e419b34 100644
--- a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
+++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
@@ -1,4 +1,4 @@
-C ISA2+pooncelock+pooncelock+pombonce.litmus
+C ISA2+pooncelock+pooncelock+pombonce
 
 (*
  * Result: Sometimes
diff --git a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
index de6708229dd1..4727f5aaf03b 100644
--- a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
@@ -1,4 +1,4 @@
-C LB+ctrlonceonce+mbonceonce
+C LB+fencembonceonce+ctrlonceonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
index c078f38ff27a..a273da9faa6d 100644
--- a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
@@ -1,4 +1,4 @@
-C MP+wmbonceonce+rmbonceonce
+C MP+fencewmbonceonce+fencermbonceonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/R+mbonceonces.litmus b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
index a0e884ad2132..222a0b850b4a 100644
--- a/tools/memory-model/litmus-tests/R+mbonceonces.litmus
+++ b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
@@ -1,4 +1,4 @@
-C R+mbonceonces
+C R+fencembonceonces
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 17eb9a8c222d..4581ec2d3c57 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -18,7 +18,7 @@ CoWW+poonceonce.litmus
 	Test of write-write coherence, that is, whether or not two
 	successive writes to the same variable are ordered.
 
-IRIW+mbonceonces+OnceOnce.litmus
+IRIW+fencembonceonces+OnceOnce.litmus
 	Test of independent reads from independent writes with smp_mb()
 	between each pairs of reads.  In other words, is smp_mb()
 	sufficient to cause two different reading processes to agree on
@@ -47,7 +47,7 @@ ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
 	Can a release-acquire chain order a prior store against
 	a later load?
 
-LB+ctrlonceonce+mbonceonce.litmus
+LB+fencembonceonce+ctrlonceonce.litmus
 	Does a control dependency and an smp_mb() suffice for the
 	load-buffering litmus test, where each process reads from one
 	of two variables then writes to the other?
@@ -88,14 +88,14 @@ MP+porevlocks.litmus
 	As below, but with the first access of the writer process
 	and the second access of reader process protected by a lock.
 
-MP+wmbonceonce+rmbonceonce.litmus
+MP+fencewmbonceonce+fencermbonceonce.litmus
 	Does a smp_wmb() (between the stores) and an smp_rmb() (between
 	the loads) suffice for the message-passing litmus test, where one
 	process writes data and then a flag, and the other process reads
 	the flag and then the data.  (This is similar to the ISA2 tests,
 	but with two processes instead of three.)
 
-R+mbonceonces.litmus
+R+fencembonceonces.litmus
 	This is the fully ordered (via smp_mb()) version of one of
 	the classic counterintuitive litmus tests that illustrates the
 	effects of store propagation delays.
@@ -103,7 +103,7 @@ R+mbonceonces.litmus
 R+poonceonces.litmus
 	As above, but without the smp_mb() invocations.
 
-SB+mbonceonces.litmus
+SB+fencembonceonces.litmus
 	This is the fully ordered (again, via smp_mb() version of store
 	buffering, which forms the core of Dekker's mutual-exclusion
 	algorithm.
@@ -111,15 +111,24 @@ SB+mbonceonces.litmus
 SB+poonceonces.litmus
 	As above, but without the smp_mb() invocations.
 
+SB+rfionceonce-poonceonces.litmus
+	This litmus test demonstrates that LKMM is not fully multicopy
+	atomic.  (Neither is it other multicopy atomic.)  This litmus test
+	also demonstrates the "locations" debugging aid, which designates
+	additional registers and locations to be printed out in the dump
+	of final states in the herd7 output.  Without the "locations"
+	statement, only those registers and locations mentioned in the
+	"exists" clause will be printed.
+
 S+poonceonces.litmus
 	As below, but without the smp_wmb() and acquire load.
 
-S+wmbonceonce+poacquireonce.litmus
+S+fencewmbonceonce+poacquireonce.litmus
 	Can a smp_wmb(), instead of a release, and an acquire order
 	a prior store against a subsequent store?
 
 WRC+poonceonces+Once.litmus
-WRC+pooncerelease+rmbonceonce+Once.litmus
+WRC+pooncerelease+fencermbonceonce+Once.litmus
 	These two are members of an extension of the MP litmus-test
 	class in which the first write is moved to a separate process.
 	The second is forbidden because smp_store_release() is
@@ -134,7 +143,7 @@ Z6.0+pooncelock+poonceLock+pombonce.litmus
 	As above, but with smp_mb__after_spinlock() immediately
 	following the spin_lock().
 
-Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
 	Is the ordering provided by a release-acquire chain sufficient
 	to make ordering apparent to accesses by a process that does
 	not participate in that release-acquire chain?
diff --git a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
index c53350205d28..18479823cd6c 100644
--- a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus
+++ b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
@@ -1,4 +1,4 @@
-C S+wmbonceonce+poacquireonce
+C S+fencewmbonceonce+poacquireonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
index 74b874ffa8da..ed5fff18d223 100644
--- a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus
+++ b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
@@ -1,4 +1,4 @@
-C SB+mbonceonces
+C SB+fencembonceonces
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
new file mode 100644
index 000000000000..04a16603660b
--- /dev/null
+++ b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
@@ -0,0 +1,32 @@
+C SB+rfionceonce-poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test demonstrates that LKMM is not fully multicopy atomic.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	int r1;
+	int r2;
+
+	WRITE_ONCE(*x, 1);
+	r1 = READ_ONCE(*x);
+	r2 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+	int r3;
+	int r4;
+
+	WRITE_ONCE(*y, 1);
+	r3 = READ_ONCE(*y);
+	r4 = READ_ONCE(*x);
+}
+
+locations [0:r1; 1:r3; x; y] (* Debug aid: Print things not in "exists". *)
+exists (0:r2=0 /\ 1:r4=0)
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
index ad3448b941e6..e9947250d7de 100644
--- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
@@ -1,4 +1,4 @@
-C WRC+pooncerelease+rmbonceonce+Once
+C WRC+pooncerelease+fencermbonceonce+Once
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
index a20fc3fafb53..88e70b87a683 100644
--- a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
@@ -1,4 +1,4 @@
-C Z6.0+pooncerelease+poacquirerelease+mbonceonce
+C Z6.0+pooncerelease+poacquirerelease+fencembonceonce
 
 (*
  * Result: Sometimes
diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh
index af0aa15ab84e..ca528f9a24d4 100644..100755
--- a/tools/memory-model/scripts/checkalllitmus.sh
+++ b/tools/memory-model/scripts/checkalllitmus.sh
@@ -9,7 +9,7 @@
 # appended.
 #
 # Usage:
-#	sh checkalllitmus.sh [ directory ]
+#	checkalllitmus.sh [ directory ]
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, whose default is defined by the checklitmus.sh script.
diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh
index e2e477472844..bf12a75c0719 100644..100755
--- a/tools/memory-model/scripts/checklitmus.sh
+++ b/tools/memory-model/scripts/checklitmus.sh
@@ -8,7 +8,7 @@
 # with ".out" appended.
 #
 # Usage:
-#	sh checklitmus.sh file.litmus
+#	checklitmus.sh file.litmus
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, which default to "-conf linux-kernel.cfg".  Thus,
diff --git a/tools/objtool/arch/x86/include/asm/orc_types.h b/tools/objtool/arch/x86/include/asm/orc_types.h
index 9c9dc579bd7d..46f516dd80ce 100644
--- a/tools/objtool/arch/x86/include/asm/orc_types.h
+++ b/tools/objtool/arch/x86/include/asm/orc_types.h
@@ -88,6 +88,7 @@ struct orc_entry {
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
+	unsigned	end:1;
 } __packed;
 
 /*
@@ -101,6 +102,7 @@ struct unwind_hint {
 	s16		sp_offset;
 	u8		sp_reg;
 	u8		type;
+	u8		end;
 };
 #endif /* __ASSEMBLY__ */
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f4a25bd1871f..2928939b98ec 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1157,6 +1157,7 @@ static int read_unwind_hints(struct objtool_file *file)
 
 		cfa->offset = hint->sp_offset;
 		insn->state.type = hint->type;
+		insn->state.end = hint->end;
 	}
 
 	return 0;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index c6b68fcb926f..95700a2bcb7c 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -31,7 +31,7 @@ struct insn_state {
 	int stack_size;
 	unsigned char type;
 	bool bp_scratch;
-	bool drap;
+	bool drap, end;
 	int drap_reg, drap_offset;
 	struct cfi_reg vals[CFI_NUM_REGS];
 };
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 4e60e105583e..7ec85d567598 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -302,19 +302,34 @@ static int read_symbols(struct elf *elf)
 				continue;
 			sym->pfunc = sym->cfunc = sym;
 			coldstr = strstr(sym->name, ".cold.");
-			if (coldstr) {
-				coldstr[0] = '\0';
-				pfunc = find_symbol_by_name(elf, sym->name);
-				coldstr[0] = '.';
-
-				if (!pfunc) {
-					WARN("%s(): can't find parent function",
-					     sym->name);
-					goto err;
-				}
-
-				sym->pfunc = pfunc;
-				pfunc->cfunc = sym;
+			if (!coldstr)
+				continue;
+
+			coldstr[0] = '\0';
+			pfunc = find_symbol_by_name(elf, sym->name);
+			coldstr[0] = '.';
+
+			if (!pfunc) {
+				WARN("%s(): can't find parent function",
+				     sym->name);
+				goto err;
+			}
+
+			sym->pfunc = pfunc;
+			pfunc->cfunc = sym;
+
+			/*
+			 * Unfortunately, -fnoreorder-functions puts the child
+			 * inside the parent.  Remove the overlap so we can
+			 * have sane assumptions.
+			 *
+			 * Note that pfunc->len now no longer matches
+			 * pfunc->sym.st_size.
+			 */
+			if (sym->sec == pfunc->sec &&
+			    sym->offset >= pfunc->offset &&
+			    sym->offset + sym->len == pfunc->offset + pfunc->len) {
+				pfunc->len -= sym->len;
 			}
 		}
 	}
@@ -504,10 +519,12 @@ struct section *elf_create_section(struct elf *elf, const char *name,
 	sec->sh.sh_flags = SHF_ALLOC;
 
 
-	/* Add section name to .shstrtab */
+	/* Add section name to .shstrtab (or .strtab for Clang) */
 	shstrtab = find_section_by_name(elf, ".shstrtab");
+	if (!shstrtab)
+		shstrtab = find_section_by_name(elf, ".strtab");
 	if (!shstrtab) {
-		WARN("can't find .shstrtab section");
+		WARN("can't find .shstrtab or .strtab section");
 		return NULL;
 	}
 
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index c3343820916a..faa444270ee3 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -203,7 +203,8 @@ int orc_dump(const char *_objname)
 
 		print_reg(orc[i].bp_reg, orc[i].bp_offset);
 
-		printf(" type:%s\n", orc_type_name(orc[i].type));
+		printf(" type:%s end:%d\n",
+		       orc_type_name(orc[i].type), orc[i].end);
 	}
 
 	elf_end(elf);
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 18384d9be4e1..3f98dcfbc177 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -31,6 +31,8 @@ int create_orc(struct objtool_file *file)
 		struct cfi_reg *cfa = &insn->state.cfa;
 		struct cfi_reg *bp = &insn->state.regs[CFI_BP];
 
+		orc->end = insn->state.end;
+
 		if (cfa->base == CFI_UNDEFINED) {
 			orc->sp_reg = ORC_REG_UNDEFINED;
 			continue;
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 11300dbe35c5..236b9b97dfdb 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -18,6 +18,10 @@ various perf commands with the -e option.
 
 OPTIONS
 -------
+-d::
+--desc::
+Print extra event descriptions. (default)
+
 --no-desc::
 Don't print descriptions.
 
@@ -25,11 +29,13 @@ Don't print descriptions.
 --long-desc::
 Print longer event descriptions.
 
+--debug::
+Enable debugging output.
+
 --details::
 Print how named events are resolved internally into perf events, and also
 any extra expressions computed by perf stat.
 
-
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
@@ -234,7 +240,7 @@ perf also supports group leader sampling using the :S specifier.
   perf record -e '{cycles,instructions}:S' ...
   perf report --group
 
-Normally all events in a event group sample, but with :S only
+Normally all events in an event group sample, but with :S only
 the first event (the leader) samples, and it only reads the values of the
 other events in the group.
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 04168da4268e..246dee081efd 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -94,7 +94,7 @@ OPTIONS
 	  "perf report" to view group events together.
 
 --filter=<filter>::
-        Event filter. This option should follow a event selector (-e) which
+        Event filter. This option should follow an event selector (-e) which
 	selects either tracepoint event(s) or a hardware trace PMU
 	(e.g. Intel PT or CoreSight).
 
@@ -153,7 +153,7 @@ OPTIONS
 
 --exclude-perf::
 	Don't record events issued by perf itself. This option should follow
-	a event selector (-e) which selects tracepoint event(s). It adds a
+	an event selector (-e) which selects tracepoint event(s). It adds a
 	filter expression 'common_pid != $PERFPID' to filters. If other
 	'--filter' exists, the new filter expression will be combined with
 	them by '&&'.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b5ac356ba323..f6d1a03c7523 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -54,6 +54,8 @@ endif
 
 ifeq ($(SRCARCH),arm64)
   NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -I$(OUTPUT)arch/arm64/include/generated
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
@@ -207,8 +209,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
@@ -906,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
-perf_include_dir = lib/include/perf
-perf_examples_dir = lib/examples/perf
+perf_include_dir = lib/perf/include
+perf_examples_dir = lib/perf/examples
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ecc9fc952655..b3d1b12a5081 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -384,6 +384,8 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
 drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
@@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
 $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
 	$(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
 
+socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c
+socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh
+
+$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
+	$(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
+
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
 vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
 vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(sndrv_ctl_ioctl_array) \
 	$(kcmp_type_array) \
 	$(kvm_ioctl_array) \
+	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
 	$(perf_ioctl_array) \
@@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(sndrv_pcm_ioctl_array) \
 		$(OUTPUT)$(kvm_ioctl_array) \
 		$(OUTPUT)$(kcmp_type_array) \
+		$(OUTPUT)$(socket_ipproto_array) \
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 91de4860faad..f013b115dc86 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -4,3 +4,24 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/arm64/include/generated/asm
+header := $(out)/syscalls.c
+sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, arm64) $(RM) $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000000..52e197317d3e
--- /dev/null
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+# Changed by: Kim Phillips <kim.phillips@arm.com>
+
+gcc=$1
+hostcc=$2
+input=$3
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table_from_c()
+{
+	local sc nr last_sc
+
+	create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+
+	{
+
+	cat <<-_EoHEADER
+		#include <stdio.h>
+		#define __ARCH_WANT_RENAMEAT
+		#include "$input"
+		int main(int argc, char *argv[])
+		{
+	_EoHEADER
+
+	while read sc nr; do
+		printf "%s\n" "	printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);"
+		last_sc=$sc
+	done
+
+	printf "%s\n" "	printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
+	printf "}\n"
+
+	} | $hostcc -o $create_table_exe -x c -
+
+	$create_table_exe
+
+	rm -f $create_table_exe
+}
+
+create_table()
+{
+	echo "static const char *syscalltbl_arm64[] = {"
+	create_table_from_c
+	echo "};"
+}
+
+$gcc -E -dM -x c  $input	       \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -nu	       \
+	|create_table
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3598b8b75d27..7c6eeb4633fe 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
 	}
 
 	/*
-	 * Check if return address is on the stack.
+	 * Check if return address is on the stack. If return address
+	 * is in a register (typically R0), it is yet to be saved on
+	 * the stack.
 	 */
-	if (nops != 0 || ops != NULL)
+	if ((nops != 0 || ops != NULL) &&
+		!(nops == 1 && ops[0].atom == DW_OP_regx &&
+			ops[0].number2 == 0 && ops[0].offset == 0))
 		return 0;
 
 	/*
@@ -243,10 +247,10 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	u64 ip;
 	u64 skip_slot = -1;
 
-	if (chain->nr < 3)
+	if (!chain || chain->nr < 3)
 		return skip_slot;
 
-	ip = chain->ips[2];
+	ip = chain->ips[1];
 
 	thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index d233e2eb9592..aaabab5e2830 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = {
 
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
 {
-	if (strstr(cpuid, "IBM/S390")) {
+	if (strstr(cpuid, "IBM")) {
 		kvm->exit_reasons = sie_exit_reasons;
 		kvm->exit_reasons_isa = "SIE";
 	} else
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 4dfe42666d0c..f0b1709a5ffb 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -341,6 +341,8 @@
 330	common	pkey_alloc		__x64_sys_pkey_alloc
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
+333	common	io_pgetevents		__x64_sys_io_pgetevents
+334	common	rseq			__x64_sys_rseq
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 4b2caf6d48e7..fead6b3b4206 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -226,7 +226,7 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 		else if (rm[2].rm_so != rm[2].rm_eo)
 			prefix[0] = '+';
 		else
-			strncpy(prefix, "+0", 2);
+			scnprintf(prefix, sizeof(prefix), "+0");
 	}
 
 	/* Rename register */
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 63a74c32ddc5..e33ef5bc31c5 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 #include "../../util/intel-pt.h"
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 06bae7023a51..950539f9a4f7 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -2,6 +2,7 @@
 #include <stdbool.h>
 #include <errno.h>
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 #include "../../perf.h"
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 60bf11943047..eafce1a130a1 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 perf-y += futex-lock-pi.o
 
+perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
 
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index b43f8d2a34ec..9ad015a1e202 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -6,6 +6,7 @@
 #define altinstr_replacement text
 #define globl p2align 4; .globl
 #define _ASM_EXTABLE_FAULT(x, y)
+#define _ASM_EXTABLE(x, y)
 
 #include "../../arch/x86/lib/memcpy_64.S"
 /*
diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c
new file mode 100644
index 000000000000..4130734dde84
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c
@@ -0,0 +1,24 @@
+/*
+ * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy
+ * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy'
+ * happy.
+ */
+#include <linux/types.h>
+
+unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len);
+
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len)
+{
+	for (; len; --len, to++, from++) {
+		/*
+		 * Call the assembly routine back directly since
+		 * memcpy_mcsafe() may silently fallback to memcpy.
+		 */
+		unsigned long rem = __memcpy_mcsafe(to, from, 1);
+
+		if (rem)
+			break;
+	}
+	return len;
+}
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 63eb49082774..44195514b19e 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
 	u8 *global_data;
 	u8 *process_data;
 	u8 *thread_data;
-	u64 bytes_done;
+	u64 bytes_done, secs;
 	long work_done;
 	u32 l;
 	struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
 	td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
-	td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+	secs = td->runtime_ns / NSEC_PER_SEC;
+	td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
 
 	getrusage(RUSAGE_THREAD, &rusage);
 	td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5eb22cc56363..8180319285af 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,6 +283,15 @@ out_put:
 	return ret;
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
@@ -471,7 +480,7 @@ int cmd_annotate(int argc, const char **argv)
 			.attr	= perf_event__process_attr,
 			.build_id = perf_event__process_build_id,
 			.tracing_data   = perf_event__process_tracing_data,
-			.feature	= perf_event__process_feature,
+			.feature	= process_feature_event,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 6a8738f7ead3..f3aa9d02a5ab 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2193,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists,
 	fprintf(out, "%s\n", bf);
 	fprintf(out, "  -------------------------------------------------------------\n");
 
-	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true);
+	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false);
 }
 
 static void print_pareto(FILE *out)
@@ -2268,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session)
 	fprintf(out, "=================================================\n");
 	fprintf(out, "#\n");
 
-	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false);
+	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true);
 
 	fprintf(out, "\n");
 	fprintf(out, "=================================================\n");
@@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	" s             Toggle full length of symbol and source line columns \n"
 	" q             Return back to cacheline list \n";
 
+	if (!he)
+		return 0;
+
 	/* Display compact version first. */
 	c2c.symbol_full = false;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index d660cb7b222b..39db2ee32d48 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -696,7 +696,7 @@ static void hists__process(struct hists *hists)
 	hists__output_resort(hists, NULL);
 
 	hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
-		       symbol_conf.use_callchain);
+		       !symbol_conf.use_callchain);
 }
 
 static void data__fprintf(void)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cdb5b6949832..02f7a3c27761 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -217,7 +217,8 @@ static int process_feature_event(struct perf_tool *tool,
 	}
 
 	/*
-	 * All features are received, we can force the
+	 * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+	 * means all features are received, now we can force the
 	 * group if needed.
 	 */
 	setup_forced_leader(rep, session->evlist);
@@ -477,8 +478,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
 		hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
-			       symbol_conf.use_callchain ||
-			       symbol_conf.show_branchflag_count);
+			       !(symbol_conf.use_callchain ||
+			         symbol_conf.show_branchflag_count));
 		fprintf(stdout, "\n\n");
 	}
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index a31d7082188e..568ddfac3213 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1834,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	struct perf_evlist *evlist;
 	struct perf_evsel *evsel, *pos;
 	int err;
+	static struct perf_evsel_script *es;
 
 	err = perf_event__process_attr(tool, event, pevlist);
 	if (err)
@@ -1842,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	evlist = *pevlist;
 	evsel = perf_evlist__last(*pevlist);
 
+	if (!evsel->priv) {
+		if (scr->per_event_dump) {
+			evsel->priv = perf_evsel_script__new(evsel,
+						scr->session->data);
+		} else {
+			es = zalloc(sizeof(*es));
+			if (!es)
+				return -ENOMEM;
+			es->fp = stdout;
+			evsel->priv = es;
+		}
+	}
+
 	if (evsel->attr.type >= PERF_TYPE_MAX &&
 	    evsel->attr.type != PERF_TYPE_SYNTH)
 		return 0;
@@ -3030,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 static int perf_script__process_auxtrace_info(struct perf_tool *tool,
 					      union perf_event *event,
@@ -3074,7 +3097,7 @@ int cmd_script(int argc, const char **argv)
 			.attr		 = process_attr,
 			.event_update   = perf_event__process_event_update,
 			.tracing_data	 = perf_event__process_tracing_data,
-			.feature	 = perf_event__process_feature,
+			.feature	 = process_feature_event,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_script__process_auxtrace_info,
@@ -3125,8 +3148,9 @@ int cmd_script(int argc, const char **argv)
 		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
+		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+		     "callindent,insn,insnlen,synth,phys_addr,metric,misc",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 22547a490e1f..d097b5b47eb8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,18 +296,6 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
-/*
- * Does the counter have nsecs as a unit?
- */
-static inline int nsec_counter(struct perf_evsel *evsel)
-{
-	if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
-	    perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		return 1;
-
-	return 0;
-}
-
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -1058,34 +1046,6 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused,
 		fprintf(os->fh, "%*s ", metric_only_len, unit);
 }
 
-static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
-	FILE *output = stat_config.output;
-	double msecs = avg / NSEC_PER_MSEC;
-	const char *fmt_v, *fmt_n;
-	char name[25];
-
-	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
-	fmt_n = csv_output ? "%s" : "%-25s";
-
-	aggr_printout(evsel, id, nr);
-
-	scnprintf(name, sizeof(name), "%s%s",
-		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-
-	fprintf(output, fmt_v, msecs, csv_sep);
-
-	if (csv_output)
-		fprintf(output, "%s%s", evsel->unit, csv_sep);
-	else
-		fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
-
-	fprintf(output, fmt_n, name);
-
-	if (evsel->cgrp)
-		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-}
-
 static int first_shadow_cpu(struct perf_evsel *evsel, int id)
 {
 	int i;
@@ -1241,11 +1201,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		return;
 	}
 
-	if (metric_only)
-		/* nothing */;
-	else if (nsec_counter(counter))
-		nsec_printout(id, nr, counter, uval);
-	else
+	if (!metric_only)
 		abs_printout(id, nr, counter, uval);
 
 	out.print_metric = pm;
@@ -1331,7 +1287,7 @@ static void collect_all_aliases(struct perf_evsel *counter,
 		    alias->scale != counter->scale ||
 		    alias->cgrp != counter->cgrp ||
 		    strcmp(alias->unit, counter->unit) ||
-		    nsec_counter(alias) != nsec_counter(counter))
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
 			break;
 		alias->merged_stat = true;
 		cb(alias, data, false);
@@ -1742,7 +1698,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 		}
 	}
 
-	if ((num_print_interval == 0 && metric_only) || interval_clear)
+	if ((num_print_interval == 0 || interval_clear) && metric_only)
 		print_metric_headers(" ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
@@ -2449,6 +2405,18 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (transaction_run) {
+		/* Handle -T as -M transaction. Once platform specific metrics
+		 * support has been added to the json files, all archictures
+		 * will use this approach. To determine transaction support
+		 * on an architecture test for such a metric name.
+		 */
+		if (metricgroup__has_metric("transaction")) {
+			struct option opt = { .value = &evsel_list };
+
+			return metricgroup__parse_groups(&opt, "transaction",
+							 &metric_events);
+		}
+
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
 			err = parse_events(evsel_list, transaction_attrs,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ffdc2769ff9f..d21d8751e749 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -307,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
 	hists__fprintf(hists, false, top->print_entries - printed, win_width,
-		       top->min_percent, stdout, symbol_conf.use_callchain);
+		       top->min_percent, stdout, !symbol_conf.use_callchain);
 }
 
 static void prompt_integer(int *target, const char *msg)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6a748eca2edb..88561eed7950 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -291,7 +291,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha
 {
 	int idx = val - sa->offset;
 
-	if (idx < 0 || idx >= sa->nr_entries)
+	if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
 		return scnprintf(bf, size, intfmt, val);
 
 	return scnprintf(bf, size, "%s", sa->entries[idx]);
@@ -761,10 +761,12 @@ static struct syscall_fmt {
 	  .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
 	{ .name	    = "socket",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "socketpair",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "stat", .alias = "newstat", },
 	{ .name	    = "statx",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT,	 /* fdat */ },
@@ -2990,6 +2992,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 
 		if (trace__validate_ev_qualifier(trace))
 			goto out;
+		trace->trace_syscalls = true;
 	}
 
 	err = 0;
@@ -3045,7 +3048,7 @@ int cmd_trace(int argc, const char **argv)
 		},
 		.output = stderr,
 		.show_comm = true,
-		.trace_syscalls = true,
+		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
 	};
@@ -3191,13 +3194,7 @@ int cmd_trace(int argc, const char **argv)
 
 	if (!trace.trace_syscalls && !trace.trace_pgfaults &&
 	    trace.evlist->nr_entries == 0 /* Was --events used? */) {
-		pr_err("Please specify something to trace.\n");
-		return -1;
-	}
-
-	if (!trace.trace_syscalls && trace.ev_qualifier) {
-		pr_err("The -e option can't be used with --no-syscalls.\n");
-		goto out;
+		trace.trace_syscalls = true;
 	}
 
 	if (output_name != NULL) {
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 10f333e2e825..de28466c0186 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
+include/uapi/linux/in.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
@@ -35,6 +36,7 @@ arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
+arch/arm64/include/uapi/asm/unistd.h
 arch/alpha/include/uapi/asm/errno.h
 arch/mips/include/asm/errno.h
 arch/mips/include/uapi/asm/errno.h
@@ -53,6 +55,7 @@ include/uapi/asm-generic/errno.h
 include/uapi/asm-generic/errno-base.h
 include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
+include/uapi/asm-generic/unistd.h
 '
 
 check_2 () {
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index dd764ad5efdf..a63aa6241b7f 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #ifndef _PERF_BPF_H
 #define _PERF_BPF_H
+
+#include <uapi/linux/bpf.h>
+
 #define SEC(NAME) __attribute__((section(NAME),  used))
 
 #define probe(function, vars) \
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index 0c6d1002b524..ac1bcdc17dae 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -35,6 +35,7 @@
 #include <sys/mman.h>
 #include <syscall.h> /* for gettid() */
 #include <err.h>
+#include <linux/kernel.h>
 
 #include "jvmti_agent.h"
 #include "../util/jitdump.h"
@@ -249,7 +250,7 @@ void *jvmti_open(void)
 	/*
 	 * jitdump file name
 	 */
-	snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index a1a97956136f..21bf7f5a3cf5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -5,6 +5,7 @@
 #include <time.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 extern bool test_attr__enabled;
@@ -24,7 +25,9 @@ static inline unsigned long long rdclock(void)
 	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
+#ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS			1024
+#endif
 
 extern const char *input_name;
 extern bool perf_host, perf_guest;
diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 17783913d330..215ba30b8534 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -1,7 +1,7 @@
 hostprogs := jevents
 
 jevents-y	+= json.o jsmn.o jevents.o
-CHOSTFLAGS_jevents.o	= -I$(srctree)/tools/include
+HOSTCFLAGS_jevents.o	= -I$(srctree)/tools/include
 pmu-events-y	+= pmu-events.o
 JDIR		=  pmu-events/arch/$(SRCARCH)
 JSON		=  $(shell [ -d $(JDIR) ] &&				\
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
index bc03c06c3918..752e47eb6977 100644
--- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
@@ -12,6 +12,21 @@
         "ArchStdEvent": "L1D_CACHE_REFILL_WR",
     },
     {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
         "ArchStdEvent": "L1D_TLB_REFILL_RD",
     },
     {
@@ -24,9 +39,75 @@
         "ArchStdEvent": "L1D_TLB_WR",
     },
     {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR",
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_WR",
-   }
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_SMC",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
index 0feedb40f30f..b6b7f29ca831 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
@@ -1,107 +1,125 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1I_L3_LOCAL_WRITES",
 		"BriefDescription": "L1I L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1D_L3_LOCAL_WRITES",
 		"BriefDescription": "L1D L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1I_L3_REMOTE_WRITES",
 		"BriefDescription": "L1I L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L3_REMOTE_WRITES",
 		"BriefDescription": "L1D L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_CACHELINE_INVALIDATES",
 		"BriefDescription": "L1I Cacheline Invalidates",
 		"PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
index 9a002b6967f1..436ce33f1182 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
@@ -1,335 +1,391 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB1_GPAGE_WRITES",
 		"BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
 		"PublicDescription": "Counter:132	Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB1_MISSES",
 		"BriefDescription": "L1C TLB1 Misses",
 		"PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "176",
 		"EventName": "L1I_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "218",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "219",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "220",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
index 8f653c9d899d..17fb5241928b 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
@@ -1,47 +1,55 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index aa4dfb46b65b..e7a3524b748f 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -1,317 +1,370 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "Counter:128	Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB2_WRITES",
 		"BriefDescription": "DTLB2 Writes",
 		"PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB2_MISSES",
 		"BriefDescription": "DTLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB2_HPAGE_WRITES",
 		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB2_GPAGE_WRITES",
 		"BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
 		"PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB2_WRITES",
 		"BriefDescription": "ITLB2 Writes",
 		"PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB2_MISSES",
 		"BriefDescription": "ITLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_ENGINES_BUSY",
 		"BriefDescription": "TLB2 Engines Busy",
 		"PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB2_MISSES",
 		"BriefDescription": "L1C TLB2 Misses",
 		"PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "224",
 		"EventName": "BCD_DFP_EXECUTION_SLOTS",
 		"BriefDescription": "BCD DFP Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "225",
 		"EventName": "VX_BCD_EXECUTION_SLOTS",
 		"BriefDescription": "VX BCD Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "226",
 		"EventName": "DECIMAL_INSTRUCTIONS",
 		"BriefDescription": "Decimal Instructions",
 		"PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "232",
 		"EventName": "LAST_HOST_TRANSLATIONS",
 		"BriefDescription": "Last host translation done",
 		"PublicDescription": "Last Host Translation done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "243",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "244",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "245",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
index b6d7fec7c2e7..b7b42a870bb0 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
@@ -1,143 +1,167 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
 		"PublicDescription": "Incremented by one for every store sent to Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
index 8682126aabb2..162251037219 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
@@ -1,209 +1,244 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1D_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1D L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index db3a594ee1e4..68c92bb599ee 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -233,6 +233,8 @@ static struct map {
 	{ "QPI LL", "uncore_qpi" },
 	{ "SBO", "uncore_sbox" },
 	{ "iMPH-U", "uncore_arb" },
+	{ "CPU-M-CF", "cpum_cf" },
+	{ "CPU-M-SF", "cpum_sf" },
 	{}
 };
 
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index 38dfb720fb6f..54ace2f6bc36 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -31,10 +31,8 @@ def flag_str(event_name, field_name, value):
     string = ""
 
     if flag_fields[event_name][field_name]:
-	print_delim = 0
-        keys = flag_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        print_delim = 0
+        for idx in sorted(flag_fields[event_name][field_name]['values']):
             if not value and not idx:
                 string += flag_fields[event_name][field_name]['values'][idx]
                 break
@@ -51,14 +49,12 @@ def symbol_str(event_name, field_name, value):
     string = ""
 
     if symbolic_fields[event_name][field_name]:
-        keys = symbolic_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        for idx in sorted(symbolic_fields[event_name][field_name]['values']):
             if not value and not idx:
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
-	    if (value == idx):
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+            if (value == idx):
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
 
     return string
@@ -74,19 +70,17 @@ def trace_flag_str(value):
     string = ""
     print_delim = 0
 
-    keys = trace_flags.keys()
-
-    for idx in keys:
-	if not value and not idx:
-	    string += "NONE"
-	    break
-
-	if idx and (value & idx) == idx:
-	    if print_delim:
-		string += " | ";
-	    string += trace_flags[idx]
-	    print_delim = 1
-	    value &= ~idx
+    for idx in trace_flags:
+        if not value and not idx:
+            string += "NONE"
+            break
+
+        if idx and (value & idx) == idx:
+            if print_delim:
+                string += " | ";
+            string += trace_flags[idx]
+            print_delim = 1
+            value &= ~idx
 
     return string
 
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
index 81a56cd2b3c1..21a7a1298094 100755
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
@@ -8,6 +8,7 @@
 # PerfEvent is the base class for all perf event sample, PebsEvent
 # is a HW base Intel x86 PEBS event, and user could add more SW/HW
 # event classes based on requirements.
+from __future__ import print_function
 
 import struct
 
@@ -44,7 +45,8 @@ class PerfEvent(object):
                 PerfEvent.event_num += 1
 
         def show(self):
-                print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso)
+                print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" %
+                      (self.name, self.symbol, self.comm, self.dso))
 
 #
 # Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
index fdd92f699055..cac7b2542ee8 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
@@ -11,7 +11,7 @@
 try:
 	import wx
 except ImportError:
-	raise ImportError, "You need to install the wxpython lib for this script"
+	raise ImportError("You need to install the wxpython lib for this script")
 
 
 class RootFrame(wx.Frame):
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index f6c84966e4f8..7384dcb628c4 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -5,6 +5,7 @@
 # This software may be distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
+from __future__ import print_function
 
 import errno, os
 
@@ -33,7 +34,7 @@ def nsecs_str(nsecs):
     return str
 
 def add_stats(dict, key, value):
-	if not dict.has_key(key):
+	if key not in dict:
 		dict[key] = (value, value, value, 1)
 	else:
 		min, max, avg, count = dict[key]
@@ -72,10 +73,10 @@ try:
 except:
 	if not audit_package_warned:
 		audit_package_warned = True
-		print "Install the audit-libs-python package to get syscall names.\n" \
-                    "For example:\n  # apt-get install python-audit (Ubuntu)" \
-                    "\n  # yum install audit-libs-python (Fedora)" \
-                    "\n  etc.\n"
+		print("Install the audit-libs-python package to get syscall names.\n"
+                    "For example:\n  # apt-get install python-audit (Ubuntu)"
+                    "\n  # yum install audit-libs-python (Fedora)"
+                    "\n  etc.\n")
 
 def syscall_name(id):
 	try:
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index de66cb3b72c9..3473e7f66081 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -9,13 +9,17 @@
 # This software is distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
-
+from __future__ import print_function
 
 import os
 import sys
 
 from collections import defaultdict
-from UserList import UserList
+try:
+    from UserList import UserList
+except ImportError:
+    # Python 3: UserList moved to the collections package
+    from collections import UserList
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
@@ -300,7 +304,7 @@ class TimeSliceList(UserList):
 		if i == -1:
 			return
 
-		for i in xrange(i, len(self.data)):
+		for i in range(i, len(self.data)):
 			timeslice = self.data[i]
 			if timeslice.start > end:
 				return
@@ -336,8 +340,8 @@ class SchedEventProxy:
 		on_cpu_task = self.current_tsk[headers.cpu]
 
 		if on_cpu_task != -1 and on_cpu_task != prev_pid:
-			print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
-				(headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
+			print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
+				headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
 
 		threads[prev_pid] = prev_comm
 		threads[next_pid] = next_comm
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 2bde505e2e7e..d7a5e1b9aa6f 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
 	if (!t->subtest.get_nr)
 		pr_debug("%s:", t->desc);
 	else
-		pr_debug("%s subtest %d:", t->desc, subtest);
+		pr_debug("%s subtest %d:", t->desc, subtest + 1);
 
 	switch (err) {
 	case TEST_OK:
@@ -422,7 +422,7 @@ static const char *shell_test__description(char *description, size_t size,
 
 #define for_each_shell_test(dir, base, ent)	\
 	while ((ent = readdir(dir)) != NULL)	\
-		if (!is_directory(base, ent))
+		if (!is_directory(base, ent) && ent->d_name[0] != '.')
 
 static const char *shell_tests__dir(char *path, size_t size)
 {
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7d4077068454..3b97ac018d5a 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,6 +1309,11 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
 	return 0;
 }
 
+static bool test__intel_pt_valid(void)
+{
+	return !!perf_pmu__find("intel_pt");
+}
+
 static int test__intel_pt(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
@@ -1317,6 +1322,14 @@ static int test__intel_pt(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_complex_name(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
@@ -1375,6 +1388,7 @@ struct evlist_test {
 	const char *name;
 	__u32 type;
 	const int id;
+	bool (*valid)(void);
 	int (*check)(struct perf_evlist *evlist);
 };
 
@@ -1648,9 +1662,15 @@ static struct evlist_test test__events[] = {
 	},
 	{
 		.name  = "intel_pt//u",
+		.valid = test__intel_pt_valid,
 		.check = test__intel_pt,
 		.id    = 52,
 	},
+	{
+		.name  = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk",
+		.check = test__checkevent_complex_name,
+		.id    = 53
+	}
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1669,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = {
 		.check = test__checkevent_pmu_partial_time_callgraph,
 		.id    = 2,
 	},
+	{
+		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",
+		.check = test__checkevent_complex_name,
+		.id    = 3,
+	}
 };
 
 struct terms_test {
@@ -1686,17 +1711,24 @@ static struct terms_test test__terms[] = {
 
 static int test_event(struct evlist_test *e)
 {
+	struct parse_events_error err = { .idx = 0, };
 	struct perf_evlist *evlist;
 	int ret;
 
+	if (e->valid && !e->valid()) {
+		pr_debug("... SKIP");
+		return 0;
+	}
+
 	evlist = perf_evlist__new();
 	if (evlist == NULL)
 		return -ENOMEM;
 
-	ret = parse_events(evlist, e->name, NULL);
+	ret = parse_events(evlist, e->name, &err);
 	if (ret) {
-		pr_debug("failed to parse event '%s', err %d\n",
-			 e->name, ret);
+		pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+			 e->name, ret, err.str);
+		parse_events_print_error(&err, e->name);
 	} else {
 		ret = e->check(evlist);
 	}
@@ -1714,10 +1746,11 @@ static int test_events(struct evlist_test *events, unsigned cnt)
 	for (i = 0; i < cnt; i++) {
 		struct evlist_test *e = &events[i];
 
-		pr_debug("running test %d '%s'\n", e->id, e->name);
+		pr_debug("running test %d '%s'", e->id, e->name);
 		ret1 = test_event(e);
 		if (ret1)
 			ret2 = ret1;
+		pr_debug("\n");
 	}
 
 	return ret2;
@@ -1799,7 +1832,7 @@ static int test_pmu_events(void)
 	}
 
 	while (!ret && (ent = readdir(dir))) {
-		struct evlist_test e;
+		struct evlist_test e = { .id = 0, };
 		char name[2 * NAME_MAX + 1 + 12 + 3];
 
 		/* Names containing . are special and cannot be used directly */
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 263057039693..3013ac8f83d0 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -13,36 +13,60 @@
 libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
+event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?'
+
+add_libc_inet_pton_event() {
+
+	event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \
+			grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))")
+
+	if [ $? -ne 0 -o -z "$event_name" ] ; then
+		printf "FAIL: could not add event\n"
+		return 1
+	fi
+}
+
 trace_libc_inet_pton_backtrace() {
-	idx=0
-	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-	expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+
+	expected=`mktemp -u /tmp/expected.XXX`
+
+	echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected
+	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
-		expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		;;
+	ppc64|ppc64le)
+		eventattr='max-stack=4'
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
-		expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	esac
 
-	file=`mktemp -u /tmp/perf.data.XXX`
+	perf_data=`mktemp -u /tmp/perf.data.XXX`
+	perf_script=`mktemp -u /tmp/perf.script.XXX`
+	perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf script -i $perf_data > $perf_script
 
-	perf record -e probe_libc:inet_pton/$eventattr/ -o $file ping -6 -c 1 ::1 > /dev/null 2>&1
-	perf script -i $file | while read line ; do
+	exec 3<$perf_script
+	exec 4<$expected
+	while read line <&3 && read -r pattern <&4; do
+		[ -z "$pattern" ] && break
 		echo $line
-		echo "$line" | egrep -q "${expected[$idx]}"
+		echo "$line" | egrep -q "$pattern"
 		if [ $? -ne 0 ] ; then
-			printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
-			exit 1
+			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
+			return 1
 		fi
-		let idx+=1
-		[ -z "${expected[$idx]}" ] && break
 	done
 
 	# If any statements are executed from this point onwards,
@@ -51,13 +75,20 @@ trace_libc_inet_pton_backtrace() {
 	# even if the perf script output does not match.
 }
 
+delete_libc_inet_pton_event() {
+
+	if [ -n "$event_name" ] ; then
+		perf probe -q -d $event_name
+	fi
+}
+
 # Check for IPv6 interface existence
 ip a sh lo | fgrep -q inet6 || exit 2
 
 skip_if_no_perf_probe && \
-perf probe -q $libc inet_pton && \
+add_libc_inet_pton_event && \
 trace_libc_inet_pton_backtrace
 err=$?
-rm -f ${file}
-perf probe -q -d probe_libc:inet_pton
+rm -f ${perf_data} ${perf_script} ${expected}
+delete_libc_inet_pton_event
 exit $err
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 55ad9793d544..4ce276efe6b4 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,7 +17,7 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
 	perf trace -e $evts touch $file 2>&1 | \
 	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 40e30a26b23c..9497d02f69e6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -45,6 +45,7 @@ static int session_write_header(char *path)
 
 	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
 	perf_header__set_feat(&session->header, HEADER_NRCPUS);
+	perf_header__set_feat(&session->header, HEADER_ARCH);
 
 	session->header.data_size += DATA_SIZE;
 
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index 66330d4b739b..f528ba35e140 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,4 +7,5 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += socket.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 984a504d335c..9615af5d412b 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
 size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
 
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 2149d3a98e42..9d3816815e60 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,13 +1,14 @@
 #!/bin/sh
 
-drm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
+
 printf "#ifndef DRM_COMMAND_BASE\n"
-grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+grep "#define DRM_COMMAND_BASE" $header_dir/drm.h
 printf "#endif\n"
 
 printf "static const char *drm_ioctl_cmds[] = {\n"
-grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \
 	sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[	 ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/	[\2] = "\1",/g'
-grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $drm_header_dir/i915_drm.h | \
+grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $header_dir/i915_drm.h | \
 	sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[	 ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index 40d063b8c082..a3c304caa336 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kcmp_types[] = {\n"
 regex='^[[:space:]]+(KCMP_(\w+)),'
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index bd28817afced..c4699fd46bb6 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,10 +1,10 @@
 #!/bin/sh
 
-kvm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kvm_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${kvm_header_dir}/kvm.h	| \
+egrep $regex ${header_dir}/kvm.h	| \
 	sed -r "s/$regex/\2 \1/g"	| \
 	egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 60ef8640ee70..431639eb4d29 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *madvise_advices[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index faea4237c793..6492c74df928 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *perf_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index 62e51a02b839..e0a51aeb20b2 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *pkey_alloc_access_rights[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index aad5ab130539..eb511bb5fbd3 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index b7e9ef6b2f55..6818392968b2 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
new file mode 100644
index 000000000000..65227269384b
--- /dev/null
+++ b/tools/perf/trace/beauty/socket.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace/beauty/socket.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <sys/types.h>
+#include <sys/socket.h>
+
+static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size)
+{
+#include "trace/beauty/generated/socket_ipproto_array.c"
+	static DEFINE_STRARRAY(socket_ipproto);
+
+	return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol);
+}
+
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int domain = syscall_arg__val(arg, 0);
+
+	if (domain == AF_INET || domain == AF_INET6)
+		return socket__scnprintf_ipproto(arg->val, bf, size);
+
+	return syscall_arg__scnprintf_int(bf, size, arg);
+}
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
new file mode 100755
index 000000000000..a3cc24633bec
--- /dev/null
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *socket_ipproto[] = {\n"
+regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
+
+egrep $regex ${header_dir}/in.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 76f1de697787..0f6a5197d0be 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,17 +1,17 @@
 #!/bin/sh
 
-vhost_virtio_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 69b7a28f7a1c..74c4ae1f0a05 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -529,7 +529,7 @@ out:
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       char *bf, size_t bfsz, FILE *fp,
-			       bool use_callchain)
+			       bool ignore_callchains)
 {
 	int ret;
 	int callchain_ret = 0;
@@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 
 	ret = fprintf(fp, "%s\n", bf);
 
-	if (hist_entry__has_callchains(he) && use_callchain)
+	if (hist_entry__has_callchains(he) && !ignore_callchains)
 		callchain_ret = hist_entry_callchain__fprintf(he, total_period,
 							      0, fp);
 
@@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp)
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain)
+		      bool ignore_callchains)
 {
 	struct rb_node *nd;
 	size_t ret = 0;
@@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		if (percent < min_pcnt)
 			continue;
 
-		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
+		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains);
 
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index cee658733e2c..3d02ae38ec56 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj)
 
 	err = bpf_object__load(obj);
 	if (err) {
-		pr_debug("bpf: load objects failed\n");
+		char bf[128];
+		libbpf_strerror(err, bf, sizeof(bf));
+		pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
 		return err;
 	}
 	return 0;
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index bf31ceab33bd..89512504551b 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -146,8 +146,15 @@ getBPFObjectFromModule(llvm::Module *Module)
 	raw_svector_ostream ostream(*Buffer);
 
 	legacy::PassManager PM;
-	if (TargetMachine->addPassesToEmitFile(PM, ostream,
-					       TargetMachine::CGFT_ObjectFile)) {
+	bool NotAdded;
+#if CLANG_VERSION_MAJOR < 7
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream,
+						      TargetMachine::CGFT_ObjectFile);
+#else
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr,
+						      TargetMachine::CGFT_ObjectFile);
+#endif
+	if (NotAdded) {
 		llvm::errs() << "TargetMachine can't emit a file of this type\n";
 		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
 	}
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 7798a2cc8a86..31279a7bd919 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,}
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	if (cs)
-		refcount_inc(&cs->refcnt);
-	return cs;
+	if (cs && refcount_inc_not_zero(&cs->refcnt))
+		return cs;
+
+	return NULL;
 }
 
 static void comm_str__put(struct comm_str *cs)
@@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
 		parent = *p;
 		iter = rb_entry(parent, struct comm_str, rb_node);
 
+		/*
+		 * If we race with comm_str__put, iter->refcnt is 0
+		 * and it will be removed within comm_str__put call
+		 * shortly, ignore it in this search.
+		 */
 		cmp = strcmp(str, iter->str);
-		if (!cmp)
-			return comm_str__get(iter);
+		if (!cmp && comm_str__get(iter))
+			return iter;
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 4d5fc374e730..938def6d0bb9 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -31,6 +31,8 @@
 #endif
 #endif
 
+#define CS_ETM_INVAL_ADDR	0xdeadbeefdeadbeefUL
+
 struct cs_etm_decoder {
 	void *data;
 	void (*packet_printer)(const char *msg);
@@ -261,8 +263,8 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 	decoder->tail = 0;
 	decoder->packet_count = 0;
 	for (i = 0; i < MAX_BUFFER; i++) {
-		decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
-		decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
+		decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
+		decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
 		decoder->packet_buffer[i].last_instr_taken_branch = false;
 		decoder->packet_buffer[i].exc = false;
 		decoder->packet_buffer[i].exc_ret = false;
@@ -295,8 +297,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 	decoder->packet_buffer[et].exc = false;
 	decoder->packet_buffer[et].exc_ret = false;
 	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-	decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
-	decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
+	decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
+	decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 743f5f444304..612b5755f742 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -23,6 +23,7 @@ struct cs_etm_buffer {
 };
 
 enum cs_etm_sample_type {
+	CS_ETM_EMPTY = 0,
 	CS_ETM_RANGE = 1 << 0,
 	CS_ETM_TRACE_ON = 1 << 1,
 };
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 822ba915d144..2ae640257fdb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
 
 static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 {
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
 	/*
 	 * The packet records the execution range with an exclusive end address
 	 *
@@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 	return packet->end_addr - A64_INSTR_SIZE;
 }
 
+static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
+{
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
+	return packet->start_addr;
+}
+
 static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
 {
 	/*
@@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
 
 	be       = &bs->entries[etmq->last_branch_pos];
 	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
-	be->to	 = etmq->packet->start_addr;
+	be->to	 = cs_etm__first_executed_instr(etmq->packet);
 	/* No support for mispredict */
 	be->flags.mispred = 0;
 	be->flags.predicted = 1;
@@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
-	sample.addr = etmq->packet->start_addr;
+	sample.addr = cs_etm__first_executed_instr(etmq->packet);
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
@@ -897,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		etmq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches &&
-	    etmq->prev_packet &&
-	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
-	    etmq->prev_packet->last_instr_taken_branch) {
-		ret = cs_etm__synth_branch_sample(etmq);
-		if (ret)
-			return ret;
+	if (etm->sample_branches && etmq->prev_packet) {
+		bool generate_sample = false;
+
+		/* Generate sample for tracing on packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON)
+			generate_sample = true;
+
+		/* Generate sample for branch taken packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+		    etmq->prev_packet->last_instr_taken_branch)
+			generate_sample = true;
+
+		if (generate_sample) {
+			ret = cs_etm__synth_branch_sample(etmq);
+			if (ret)
+				return ret;
+		}
 	}
 
 	if (etm->sample_branches || etm->synth_opts.last_branch) {
@@ -922,10 +945,17 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 static int cs_etm__flush(struct cs_etm_queue *etmq)
 {
 	int err = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
+	if (!etmq->prev_packet)
+		return 0;
+
+	/* Handle start tracing packet */
+	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+		goto swap_packet;
+
 	if (etmq->etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
 		/*
 		 * Generate a last branch event for the branches left in the
@@ -939,8 +969,22 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 		err = cs_etm__synth_instruction_sample(
 			etmq, addr,
 			etmq->period_instructions);
+		if (err)
+			return err;
+
 		etmq->period_instructions = 0;
 
+	}
+
+	if (etm->sample_branches &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+		err = cs_etm__synth_branch_sample(etmq);
+		if (err)
+			return err;
+	}
+
+swap_packet:
+	if (etmq->etm->synth_opts.last_branch) {
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
@@ -1020,6 +1064,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 					 */
 					cs_etm__flush(etmq);
 					break;
+				case CS_ETM_EMPTY:
+					/*
+					 * Should not receive empty packet,
+					 * report error.
+					 */
+					pr_err("CS ETM Trace: empty packet\n");
+					return -EINVAL;
 				default:
 					break;
 				}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 94fce4f537e9..ddf84b941abf 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -260,6 +260,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 		evsel->attr.sample_period = 1;
 	}
 
+	if (perf_evsel__is_clock(evsel)) {
+		/*
+		 * The evsel->unit points to static alias->unit
+		 * so it's ok to use static string in here.
+		 */
+		static const char *unit = "msec";
+
+		evsel->unit = unit;
+		evsel->scale = 1e-6;
+	}
+
 	return evsel;
 }
 
@@ -848,6 +859,12 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	}
 }
 
+static bool is_dummy_event(struct perf_evsel *evsel)
+{
+	return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
+	       (evsel->attr.config == PERF_COUNT_SW_DUMMY);
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1086,6 +1103,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		else
 			perf_evsel__reset_sample_bit(evsel, PERIOD);
 	}
+
+	/*
+	 * For initial_delay, a dummy event is added implicitly.
+	 * The software event will trigger -EOPNOTSUPP error out,
+	 * if BRANCH_STACK bit is set.
+	 */
+	if (opts->initial_delay && is_dummy_event(evsel))
+		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d277930b19a1..973c03167947 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -402,10 +402,13 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel);
 
 static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 {
-	struct perf_event_attr *attr = &evsel->attr;
+	return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
+}
 
-	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
-		(attr->type == PERF_TYPE_SOFTWARE);
+static inline bool perf_evsel__is_clock(struct perf_evsel *evsel)
+{
+	return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+	       perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
 struct perf_attr_details {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 540cd2dcd3e7..5af58aac91ad 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2129,6 +2129,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 	int cpu_nr = ff->ph->env.nr_cpus_avail;
 	u64 size = 0;
 	struct perf_header *ph = ff->ph;
+	bool do_core_id_test = true;
 
 	ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
 	if (!ph->env.cpu)
@@ -2183,6 +2184,13 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		return 0;
 	}
 
+	/* On s390 the socket_id number is not related to the numbers of cpus.
+	 * The socket_id number might be higher than the numbers of cpus.
+	 * This depends on the configuration.
+	 */
+	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+		do_core_id_test = false;
+
 	for (i = 0; i < (u32)cpu_nr; i++) {
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
@@ -2192,7 +2200,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
 
-		if (nr != (u32)-1 && nr > (u32)cpu_nr) {
+		if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) {
 			pr_debug("socket_id number is too big."
 				 "You may need to upgrade the perf tool.\n");
 			goto free_cpu;
@@ -2579,7 +2587,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(NUMA_TOPOLOGY,	numa_topology,	true),
 	FEAT_OPN(BRANCH_STACK,	branch_stack,	false),
 	FEAT_OPR(PMU_MAPPINGS,	pmu_mappings,	false),
-	FEAT_OPN(GROUP_DESC,	group_desc,	false),
+	FEAT_OPR(GROUP_DESC,	group_desc,	false),
 	FEAT_OPN(AUXTRACE,	auxtrace,	false),
 	FEAT_OPN(STAT,		stat,		false),
 	FEAT_OPN(CACHE,		cache,		true),
@@ -3456,7 +3464,7 @@ int perf_event__process_feature(struct perf_tool *tool,
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return 0;
 	}
-	if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+	if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) {
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return -1;
 	}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 90d4577a92dc..6d7fe44aadc0 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -2,6 +2,7 @@
 #ifndef __PERF_HEADER_H
 #define __PERF_HEADER_H
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <sys/types.h>
 #include <stdbool.h>
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 73049f7f0f60..3badd7f1e1b8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -181,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain);
+		      bool ignore_callchains);
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index ba4c9dd18643..d426761a549d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -366,7 +366,7 @@ static int intel_pt_get_cyc(unsigned int byte, const unsigned char *buf,
 		if (len < offs)
 			return INTEL_PT_NEED_MORE_BYTES;
 		byte = buf[offs++];
-		payload |= (byte >> 1) << shift;
+		payload |= ((uint64_t)byte >> 1) << shift;
 	}
 
 	packet->type = INTEL_PT_CYC;
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 976e658e38dc..5e94857dfca2 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -266,16 +266,16 @@ static const char *kinc_fetch_script =
 "#!/usr/bin/env sh\n"
 "if ! test -d \"$KBUILD_DIR\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "TMPDIR=`mktemp -d`\n"
 "if test -z \"$TMPDIR\"\n"
 "then\n"
-"    exit -1\n"
+"    exit 1\n"
 "fi\n"
 "cat << EOF > $TMPDIR/Makefile\n"
 "obj-y := dummy.o\n"
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e7b4a8b513f2..b300a3973448 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -408,23 +408,16 @@ out_err:
 }
 
 /*
- * Caller must eventually drop thread->refcnt returned with a successful
- * lookup/new thread inserted.
+ * Front-end cache - TID lookups come in blocks,
+ * so most of the time we dont have to look up
+ * the full rbtree:
  */
-static struct thread *____machine__findnew_thread(struct machine *machine,
-						  struct threads *threads,
-						  pid_t pid, pid_t tid,
-						  bool create)
+static struct thread*
+__threads__get_last_match(struct threads *threads, struct machine *machine,
+			  int pid, int tid)
 {
-	struct rb_node **p = &threads->entries.rb_node;
-	struct rb_node *parent = NULL;
 	struct thread *th;
 
-	/*
-	 * Front-end cache - TID lookups come in blocks,
-	 * so most of the time we dont have to look up
-	 * the full rbtree:
-	 */
 	th = threads->last_match;
 	if (th != NULL) {
 		if (th->tid == tid) {
@@ -435,12 +428,57 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		threads->last_match = NULL;
 	}
 
+	return NULL;
+}
+
+static struct thread*
+threads__get_last_match(struct threads *threads, struct machine *machine,
+			int pid, int tid)
+{
+	struct thread *th = NULL;
+
+	if (perf_singlethreaded)
+		th = __threads__get_last_match(threads, machine, pid, tid);
+
+	return th;
+}
+
+static void
+__threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	threads->last_match = th;
+}
+
+static void
+threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	if (perf_singlethreaded)
+		__threads__set_last_match(threads, th);
+}
+
+/*
+ * Caller must eventually drop thread->refcnt returned with a successful
+ * lookup/new thread inserted.
+ */
+static struct thread *____machine__findnew_thread(struct machine *machine,
+						  struct threads *threads,
+						  pid_t pid, pid_t tid,
+						  bool create)
+{
+	struct rb_node **p = &threads->entries.rb_node;
+	struct rb_node *parent = NULL;
+	struct thread *th;
+
+	th = threads__get_last_match(threads, machine, pid, tid);
+	if (th)
+		return th;
+
 	while (*p != NULL) {
 		parent = *p;
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			threads->last_match = th;
+			threads__set_last_match(threads, th);
 			machine__update_thread_pid(machine, th, pid);
 			return thread__get(th);
 		}
@@ -477,7 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		threads->last_match = th;
+		threads__set_last_match(threads, th);
 		++threads->nr;
 	}
 
@@ -1635,7 +1673,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	struct threads *threads = machine__threads(machine, th->tid);
 
 	if (threads->last_match == th)
-		threads->last_match = NULL;
+		threads__set_last_match(threads, NULL);
 
 	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
@@ -2272,6 +2310,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
+	u64 addr;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2279,7 +2318,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
 		return 0;
 
-	srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
+	/*
+	 * Convert entry->ip from a virtual address to an offset in
+	 * its corresponding binary.
+	 */
+	addr = map__map_ip(entry->map, entry->ip);
+
+	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym,
 				       false, NULL, 0, 0, 0, srcline);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 1ddc3d1d0147..a28f9b5cc4ff 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 				if (raw)
 					s = (char *)pe->metric_name;
 				else {
-					if (asprintf(&s, "%s\n\t[%s]",
-						     pe->metric_name, pe->desc) < 0)
+					if (asprintf(&s, "%s\n%*s%s]",
+						     pe->metric_name, 8, "[", pe->desc) < 0)
 						return;
 				}
 
@@ -490,3 +490,25 @@ out:
 	metricgroup__free_egroups(&group_list);
 	return ret;
 }
+
+bool metricgroup__has_metric(const char *metric)
+{
+	struct pmu_events_map *map = perf_pmu__find_map(NULL);
+	struct pmu_event *pe;
+	int i;
+
+	if (!map)
+		return false;
+
+	for (i = 0; ; i++) {
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		if (match_metric(pe->metric_name, metric))
+			return true;
+	}
+	return false;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 06854e125ee7..8a155dba0581 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt,
 			struct rblist *metric_events);
 
 void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+bool metricgroup__has_metric(const char *metric);
 #endif
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 760558dcfd18..cae1a9a39722 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -10,6 +10,7 @@
 #define __PERF_NAMESPACES_H
 
 #include <sys/types.h>
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d2fb597c9a8c..afd68524ffa9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -234,6 +234,74 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
+static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
+				char **new_str)
+{
+	if (!*old_str)
+		goto set_new;
+
+	if (*new_str) {	/* Have new string, check with old */
+		if (strcasecmp(*old_str, *new_str))
+			pr_debug("alias %s differs in field '%s'\n",
+				 name, field);
+		zfree(old_str);
+	} else		/* Nothing new --> keep old string */
+		return;
+set_new:
+	*old_str = *new_str;
+	*new_str = NULL;
+}
+
+static void perf_pmu_update_alias(struct perf_pmu_alias *old,
+				  struct perf_pmu_alias *newalias)
+{
+	perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
+	perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
+			    &newalias->long_desc);
+	perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
+	perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr,
+			    &newalias->metric_expr);
+	perf_pmu_assign_str(old->name, "metric_name", &old->metric_name,
+			    &newalias->metric_name);
+	perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
+	old->scale = newalias->scale;
+	old->per_pkg = newalias->per_pkg;
+	old->snapshot = newalias->snapshot;
+	memcpy(old->unit, newalias->unit, sizeof(old->unit));
+}
+
+/* Delete an alias entry. */
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+{
+	zfree(&newalias->name);
+	zfree(&newalias->desc);
+	zfree(&newalias->long_desc);
+	zfree(&newalias->topic);
+	zfree(&newalias->str);
+	zfree(&newalias->metric_expr);
+	zfree(&newalias->metric_name);
+	parse_events_terms__purge(&newalias->terms);
+	free(newalias);
+}
+
+/* Merge an alias, search in alias list. If this name is already
+ * present merge both of them to combine all information.
+ */
+static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
+				 struct list_head *alist)
+{
+	struct perf_pmu_alias *a;
+
+	list_for_each_entry(a, alist, list) {
+		if (!strcasecmp(newalias->name, a->name)) {
+			perf_pmu_update_alias(a, newalias);
+			perf_pmu_free_alias(newalias);
+			return true;
+		}
+	}
+	return false;
+}
+
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *desc, char *val,
 				 char *long_desc, char *topic,
@@ -241,9 +309,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *metric_expr,
 				 char *metric_name)
 {
+	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
 	int ret;
 	int num;
+	char newval[256];
 
 	alias = malloc(sizeof(*alias));
 	if (!alias)
@@ -262,6 +332,27 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		return ret;
 	}
 
+	/* Scan event and remove leading zeroes, spaces, newlines, some
+	 * platforms have terms specified as
+	 * event=0x0091 (read from files ../<PMU>/events/<FILE>
+	 * and terms specified as event=0x91 (read from JSON files).
+	 *
+	 * Rebuild string to make alias->str member comparable.
+	 */
+	memset(newval, 0, sizeof(newval));
+	ret = 0;
+	list_for_each_entry(term, &alias->terms, list) {
+		if (ret)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 ",");
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%#x", term->config, term->val.num);
+		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%s", term->config, term->val.str);
+	}
+
 	alias->name = strdup(name);
 	if (dir) {
 		/*
@@ -285,9 +376,10 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
 	alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
-	alias->str = strdup(val);
+	alias->str = strdup(newval);
 
-	list_add_tail(&alias->list, list);
+	if (!perf_pmu_merge_alias(alias, list))
+		list_add_tail(&alias->list, list);
 
 	return 0;
 }
@@ -303,6 +395,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 
 	buf[ret] = 0;
 
+	/* Remove trailing newline from sysfs file */
+	rtrim(buf);
+
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
 				     NULL, NULL, NULL);
 }
@@ -557,12 +652,6 @@ static int is_arm_pmu_core(const char *name)
 	if (stat(path, &st) == 0)
 		return 1;
 
-	/* Look for cpu sysfs (specific to s390) */
-	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
-		  sysfs, name);
-	if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
-		return 1;
-
 	return 0;
 }
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 46e9e19ab1ac..bc32e57d17be 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -908,14 +908,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	if (!dict) {
+	if (!dict)
 		call_object(handler, t, handler_name);
-	} else {
+	else
 		call_object(handler, t, default_handler_name);
-		Py_DECREF(dict);
-	}
 
-	Py_XDECREF(all_entries_dict);
 	Py_DECREF(t);
 }
 
@@ -1235,7 +1232,6 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	call_object(handler, t, handler_name);
 
-	Py_DECREF(dict);
 	Py_DECREF(t);
 }
 
@@ -1627,6 +1623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "# See the perf-script-python Documentation for the list "
 		"of available functions.\n\n");
 
+	fprintf(ofp, "from __future__ import print_function\n\n");
 	fprintf(ofp, "import os\n");
 	fprintf(ofp, "import sys\n\n");
 
@@ -1636,10 +1633,10 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "from Core import *\n\n\n");
 
 	fprintf(ofp, "def trace_begin():\n");
-	fprintf(ofp, "\tprint \"in trace_begin\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_begin\")\n\n");
 
 	fprintf(ofp, "def trace_end():\n");
-	fprintf(ofp, "\tprint \"in trace_end\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
 	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
@@ -1675,7 +1672,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			"common_secs, common_nsecs,\n\t\t\t"
 			"common_pid, common_comm)\n\n");
 
-		fprintf(ofp, "\t\tprint \"");
+		fprintf(ofp, "\t\tprint(\"");
 
 		not_first = 0;
 		count = 0;
@@ -1736,31 +1733,31 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%s", f->name);
 		}
 
-		fprintf(ofp, ")\n\n");
+		fprintf(ofp, "))\n\n");
 
-		fprintf(ofp, "\t\tprint 'Sample: {'+"
-			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+		fprintf(ofp, "\t\tprint('Sample: {'+"
+			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 		fprintf(ofp, "\t\tfor node in common_callchain:");
 		fprintf(ofp, "\n\t\t\tif 'sym' in node:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))");
 		fprintf(ofp, "\n\t\t\telse:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
-		fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n");
+		fprintf(ofp, "\t\tprint()\n\n");
 
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
 		"event_fields_dict, perf_sample_dict):\n");
 
-	fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n");
-	fprintf(ofp, "\t\tprint 'Sample: {'+"
-		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+	fprintf(ofp, "\t\tprint(get_dict_as_string(event_fields_dict))\n");
+	fprintf(ofp, "\t\tprint('Sample: {'+"
+		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 	fprintf(ofp, "def print_header("
 		"event_name, cpu, secs, nsecs, pid, comm):\n"
-		"\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
-		"(event_name, cpu, secs, nsecs, pid, comm),\n\n");
+		"\tprint(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
+		"(event_name, cpu, secs, nsecs, pid, comm), end=\"\")\n\n");
 
 	fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n"
 		"\treturn delimiter.join"
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 594d14a02b67..99990f5f2512 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -913,11 +913,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
-		   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
+	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
 			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
-				     avg / ratio);
+				     avg / (ratio * evsel->scale));
 		else
 			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 0ee7f568d60c..3393d7ee9401 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_64;
 #include <asm/syscalls_32.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_powerpc_32;
+#elif defined(__aarch64__)
+#include <asm/syscalls.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_arm64;
 #endif
 
 struct syscall {
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 538db4e5d1e6..6f318b15950e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -77,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui)
 	if (__report_module(&al, ip, ui))
 		return -1;
 
-	e->ip  = al.addr;
+	e->ip  = ip;
 	e->map = al.map;
 	e->sym = al.sym;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6a11bc7e6b27..79f521a552cf 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -575,7 +575,7 @@ static int entry(u64 ip, struct thread *thread,
 	struct addr_location al;
 
 	e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
-	e.ip = al.addr;
+	e.ip  = ip;
 	e.map = al.map;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index d39e4ff7d0bf..a6db83a88e85 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -106,7 +106,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics
 \fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3....  The system summary is the average of all CPUs in the system.  Note that these are software, reflecting what was requested.  The hardware counters reflect what was actually achieved.
 \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.  These numbers are from hardware residency counters.
 \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
-\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
+\fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
 \fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
 \fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
 \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states.  These numbers are from hardware residency counters.
@@ -114,7 +114,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics
 \fBCorWatt\fP Watts consumed by the core part of the package.
 \fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors.
 \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
-\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.
+\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.  Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system.  Note that the meaning of this field is model specific.  For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits.  Comparing PkgWatt and PkgTmp to system limits is necessary.
 \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
 .fi
 .SH TOO MUCH INFORMATION EXAMPLE
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 4d14bbbf9b63..980bd9d20646 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1163,9 +1163,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_
 	if (!printed || !summary_only)
 		print_header("\t");
 
-	if (topo.num_cpus > 1)
-		format_counters(&average.threads, &average.cores,
-			&average.packages);
+	format_counters(&average.threads, &average.cores, &average.packages);
 
 	printed = 1;
 
@@ -1692,7 +1690,7 @@ void get_apic_id(struct thread_data *t)
 	t->x2apic_id = edx;
 
 	if (debug && (t->apic_id != t->x2apic_id))
-		fprintf(stderr, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id);
+		fprintf(outf, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id);
 }
 
 /*
@@ -2473,55 +2471,43 @@ int get_core_id(int cpu)
 
 void set_node_data(void)
 {
-	char path[80];
-	FILE *filep;
-	int pkg, node, cpu;
-
-	struct pkg_node_info {
-		int count;
-		int min;
-	} *pni;
-
-	pni = calloc(topo.num_packages, sizeof(struct pkg_node_info));
-	if (!pni)
-		err(1, "calloc pkg_node_count");
-
-	for (pkg = 0; pkg < topo.num_packages; pkg++)
-		pni[pkg].min = topo.num_cpus;
-
-	for (node = 0; node <= topo.max_node_num; node++) {
-		/* find the "first" cpu in the node */
-		sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node);
-		filep = fopen(path, "r");
-		if (!filep)
-			continue;
-		fscanf(filep, "%d", &cpu);
-		fclose(filep);
-
-		pkg = cpus[cpu].physical_package_id;
-		pni[pkg].count++;
-
-		if (node < pni[pkg].min)
-			pni[pkg].min = node;
-	}
-
-	for (pkg = 0; pkg < topo.num_packages; pkg++)
-		if (pni[pkg].count > topo.nodes_per_pkg)
-			topo.nodes_per_pkg = pni[0].count;
-
-	/* Fake 1 node per pkg for machines that don't
-	 * expose nodes and thus avoid -nan results
-	 */
-	if (topo.nodes_per_pkg == 0)
-		topo.nodes_per_pkg = 1;
-
-	for (cpu = 0; cpu < topo.num_cpus; cpu++) {
-		pkg = cpus[cpu].physical_package_id;
-		node = cpus[cpu].physical_node_id;
-		cpus[cpu].logical_node_id = node - pni[pkg].min;
+	int pkg, node, lnode, cpu, cpux;
+	int cpu_count;
+
+	/* initialize logical_node_id */
+	for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu)
+		cpus[cpu].logical_node_id = -1;
+
+	cpu_count = 0;
+	for (pkg = 0; pkg < topo.num_packages; pkg++) {
+		lnode = 0;
+		for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu) {
+			if (cpus[cpu].physical_package_id != pkg)
+				continue;
+			/* find a cpu with an unset logical_node_id */
+			if (cpus[cpu].logical_node_id != -1)
+				continue;
+			cpus[cpu].logical_node_id = lnode;
+			node = cpus[cpu].physical_node_id;
+			cpu_count++;
+			/*
+			 * find all matching cpus on this pkg and set
+			 * the logical_node_id
+			 */
+			for (cpux = cpu; cpux <= topo.max_cpu_num; cpux++) {
+				if ((cpus[cpux].physical_package_id == pkg) &&
+				   (cpus[cpux].physical_node_id == node)) {
+					cpus[cpux].logical_node_id = lnode;
+					cpu_count++;
+				}
+			}
+			lnode++;
+			if (lnode > topo.nodes_per_pkg)
+				topo.nodes_per_pkg = lnode;
+		}
+		if (cpu_count >= topo.max_cpu_num)
+			break;
 	}
-	free(pni);
-
 }
 
 int get_physical_node_id(struct cpu_topology *thiscpu)
@@ -4471,7 +4457,9 @@ void process_cpuid()
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	stepping = fms & 0xf;
-	if (family == 6 || family == 0xf)
+	if (family == 0xf)
+		family += (fms >> 20) & 0xff;
+	if (family >= 6)
 		model += ((fms >> 16) & 0xf) << 4;
 
 	if (!quiet) {
@@ -4840,16 +4828,8 @@ void topology_probe()
 		siblings = get_thread_siblings(&cpus[i]);
 		if (siblings > max_siblings)
 			max_siblings = siblings;
-		if (cpus[i].thread_id != -1)
+		if (cpus[i].thread_id == 0)
 			topo.num_cores++;
-
-		if (debug > 1)
-			fprintf(outf,
-				"cpu %d pkg %d node %d core %d thread %d\n",
-				i, cpus[i].physical_package_id,
-				cpus[i].physical_node_id,
-				cpus[i].physical_core_id,
-				cpus[i].thread_id);
 	}
 
 	topo.cores_per_node = max_core_id + 1;
@@ -4875,6 +4855,20 @@ void topology_probe()
 	topo.threads_per_core = max_siblings;
 	if (debug > 1)
 		fprintf(outf, "max_siblings %d\n", max_siblings);
+
+	if (debug < 1)
+		return;
+
+	for (i = 0; i <= topo.max_cpu_num; ++i) {
+		fprintf(outf,
+			"cpu %d pkg %d node %d lnode %d core %d thread %d\n",
+			i, cpus[i].physical_package_id,
+			cpus[i].physical_node_id,
+			cpus[i].logical_node_id,
+			cpus[i].physical_core_id,
+			cpus[i].thread_id);
+	}
+
 }
 
 void
@@ -5102,7 +5096,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 18.06.20"
+	fprintf(outf, "turbostat version 18.07.27"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index a8fb63edcf89..e2926f72a821 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -1991,8 +1991,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	pcap->header.type = ACPI_NFIT_TYPE_CAPABILITIES;
 	pcap->header.length = sizeof(*pcap);
 	pcap->highest_capability = 1;
-	pcap->capabilities = ACPI_NFIT_CAPABILITY_CACHE_FLUSH |
-		ACPI_NFIT_CAPABILITY_MEM_FLUSH;
+	pcap->capabilities = ACPI_NFIT_CAPABILITY_MEM_FLUSH;
 	offset += pcap->header.length;
 
 	if (t->setup_hotplug) {
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 7a6214e9ae58..a362e3d7abc6 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -105,7 +105,7 @@ $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
 
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
-BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM)
+BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
 
 ifneq ($(BTF_LLC_PROBE),)
 ifneq ($(BTF_PAHOLE_PROBE),)
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index f2f28b6c8915..810de20e8e26 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -158,6 +158,15 @@ struct bpf_map_def {
 	unsigned int numa_node;
 };
 
+#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val)		\
+	struct ____btf_map_##name {				\
+		type_key key;					\
+		type_val value;					\
+	};							\
+	struct ____btf_map_##name				\
+	__attribute__ ((section(".maps." #name), used))		\
+		____btf_map_##name = { }
+
 static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
 	(void *) BPF_FUNC_skb_load_bytes;
 static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 7eb613ffef55..b4994a94968b 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -6,6 +6,7 @@ CONFIG_TEST_BPF=m
 CONFIG_CGROUP_BPF=y
 CONFIG_NETDEVSIM=m
 CONFIG_NET_CLS_ACT=y
+CONFIG_NET_SCHED=y
 CONFIG_NET_SCH_INGRESS=y
 CONFIG_NET_IPIP=y
 CONFIG_IPV6=y
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 3619f3023088..ffdd27737c9e 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -247,6 +247,34 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 4,
 },
 
+{
+	.descr = "struct test #3 Invalid member offset",
+	.raw_types = {
+		/* int */					/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+		/* int64 */					/* [2] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8),
+
+		/* struct A { */				/* [3] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 16),
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),	/* int m;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),		/* int64 n; */
+		/* } */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0",
+	.str_sec_size = sizeof("\0A\0m\0n\0"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_test3_map",
+	.key_size = sizeof(int),
+	.value_size = 16,
+	.key_type_id = 1,
+	.value_type_id = 3,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid member bits_offset",
+},
+
 /* Test member exceeds the size of struct.
  *
  * struct A {
@@ -479,7 +507,7 @@ static struct btf_raw_test raw_tests[] = {
 	.key_size = sizeof(int),
 	.value_size = sizeof(void *) * 4,
 	.key_type_id = 1,
-	.value_type_id = 4,
+	.value_type_id = 5,
 	.max_entries = 4,
 },
 
@@ -1264,6 +1292,88 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "type != 0",
 },
 
+{
+	.descr = "arraymap invalid btf key (a bit field)",
+	.raw_types = {
+		/* int */				/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+		/* 32 bit int with 32 bit offset */	/* [2] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 32, 32, 8),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "array_map_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 2,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.map_create_err = true,
+},
+
+{
+	.descr = "arraymap invalid btf key (!= 32 bits)",
+	.raw_types = {
+		/* int */				/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+		/* 16 bit int with 0 bit offset */	/* [2] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 16, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "array_map_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 2,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.map_create_err = true,
+},
+
+{
+	.descr = "arraymap invalid btf value (too small)",
+	.raw_types = {
+		/* int */				/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "array_map_check_btf",
+	.key_size = sizeof(int),
+	/* btf_value_size < map->value_size */
+	.value_size = sizeof(__u64),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.map_create_err = true,
+},
+
+{
+	.descr = "arraymap invalid btf value (too big)",
+	.raw_types = {
+		/* int */				/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "array_map_check_btf",
+	.key_size = sizeof(int),
+	/* btf_value_size > map->value_size */
+	.value_size = sizeof(__u16),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.map_create_err = true,
+},
+
 }; /* struct btf_raw_test raw_tests[] */
 
 static const char *get_next_str(const char *start, const char *end)
@@ -2023,7 +2133,7 @@ static struct btf_raw_test pprint_test = {
 		BTF_ENUM_ENC(NAME_TBD, 2),
 		BTF_ENUM_ENC(NAME_TBD, 3),
 		/* struct pprint_mapv */		/* [16] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28),
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 32),
 		BTF_MEMBER_ENC(NAME_TBD, 11, 0),	/* uint32_t ui32 */
 		BTF_MEMBER_ENC(NAME_TBD, 10, 32),	/* uint16_t ui16 */
 		BTF_MEMBER_ENC(NAME_TBD, 12, 64),	/* int32_t si32 */
diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c
index 8c7ca096ecf2..b21b876f475d 100644
--- a/tools/testing/selftests/bpf/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/test_btf_haskv.c
@@ -10,11 +10,6 @@ struct ipv_counts {
 	unsigned int v6;
 };
 
-typedef int btf_map_key;
-typedef struct ipv_counts btf_map_value;
-btf_map_key dumm_key;
-btf_map_value dummy_value;
-
 struct bpf_map_def SEC("maps") btf_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(int),
@@ -22,6 +17,8 @@ struct bpf_map_def SEC("maps") btf_map = {
 	.max_entries = 4,
 };
 
+BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts);
+
 struct dummy_tracepoint_args {
 	unsigned long long pad;
 	struct sock *sock;
diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh
index 35669ccd4d23..9df0d2ac45f8 100755
--- a/tools/testing/selftests/bpf/test_kmod.sh
+++ b/tools/testing/selftests/bpf/test_kmod.sh
@@ -1,6 +1,15 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ "$(id -u)" != "0" ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
 SRC_TREE=../../../../
 
 test_run()
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh
index ce2e15e4f976..677686198df3 100755
--- a/tools/testing/selftests/bpf/test_lirc_mode2.sh
+++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh
@@ -1,6 +1,15 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
 GREEN='\033[0;92m'
 RED='\033[0;31m'
 NC='\033[0m' # No Color
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
index 1c77994b5e71..785eabf2a593 100755
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh
+++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
@@ -21,6 +21,15 @@
 # An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
 # datagram can be read on NS6 when binding to fb00::6.
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
 TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
 
 cleanup()
@@ -106,14 +115,14 @@ ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o
 ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link
 
 ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65
-ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4
+ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4
 
-ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6
+ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6
 ip netns exec ns4 ip -6 addr add fc42::1 dev lo
 ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87
 
 ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109
-ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8
+ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8
 
 ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo
 ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 05c8cb71724a..0c7d9e556b47 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -354,7 +354,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		while (s->bytes_recvd < total_bytes) {
 			if (txmsg_cork) {
 				timeout.tv_sec = 0;
-				timeout.tv_usec = 1000;
+				timeout.tv_usec = 300000;
 			} else {
 				timeout.tv_sec = 1;
 				timeout.tv_usec = 0;
@@ -1413,18 +1413,12 @@ out:
 
 int main(int argc, char **argv)
 {
-	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
 	int iov_count = 1, length = 1024, rate = 1;
 	struct sockmap_options options = {0};
 	int opt, longindex, err, cg_fd = 0;
 	char *bpf_file = BPF_SOCKMAP_FILENAME;
 	int test = PING_PONG;
 
-	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
-		perror("setrlimit(RLIMIT_MEMLOCK)");
-		return 1;
-	}
-
 	if (argc < 2)
 		return test_suite();
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 2ecd27b670d7..41106d9d5cc7 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4975,6 +4975,24 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
 	},
 	{
+		"make headroom for LWT_XMIT",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_2, 34),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
+			/* split for s390 to succeed */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_MOV64_IMM(BPF_REG_2, 42),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
+	},
+	{
 		"invalid access of tc_classid for LWT_IN",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
@@ -11987,6 +12005,46 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
 	{
+		"xadd/w check whether src/dst got mangled, 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 3,
+	},
+	{
+		"xadd/w check whether src/dst got mangled, 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 3,
+	},
+	{
 		"bpf_get_stack return R0 within range",
 		.insns = {
 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
@@ -12554,8 +12612,11 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	}
 
 	if (fd_prog >= 0) {
+		__u8 tmp[TEST_DATA_LEN << 2];
+		__u32 size_tmp = sizeof(tmp);
+
 		err = bpf_prog_test_run(fd_prog, 1, test->data,
-					sizeof(test->data), NULL, NULL,
+					sizeof(test->data), tmp, &size_tmp,
 					&retval, NULL);
 		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
 			printf("Unexpected bpf_prog_test_run error\n");
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc
new file mode 100644
index 000000000000..3b1f45e13a2e
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc
@@ -0,0 +1,28 @@
+#!/bin/sh
+# description: Snapshot and tracing setting
+# flags: instance
+
+[ ! -f snapshot ] && exit_unsupported
+
+echo "Set tracing off"
+echo 0 > tracing_on
+
+echo "Allocate and take a snapshot"
+echo 1 > snapshot
+
+# Since trace buffer is empty, snapshot is also empty, but allocated
+grep -q "Snapshot is allocated" snapshot
+
+echo "Ensure keep tracing off"
+test `cat tracing_on` -eq 0
+
+echo "Set tracing on"
+echo 1 > tracing_on
+
+echo "Take a snapshot again"
+echo 1 > snapshot
+
+echo "Ensure keep tracing on"
+test `cat tracing_on` -eq 1
+
+exit 0
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 128e548aa377..1a0ac3a29ec5 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -12,3 +12,4 @@ tcp_mmap
 udpgso
 udpgso_bench_rx
 udpgso_bench_tx
+tcp_inq
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 7ba089b33e8b..cd3a2f1545b5 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -12,3 +12,5 @@ CONFIG_NET_IPVTI=y
 CONFIG_INET6_XFRM_MODE_TUNNEL=y
 CONFIG_IPV6_VTI=y
 CONFIG_DUMMY=y
+CONFIG_BRIDGE=y
+CONFIG_VLAN_8021Q=y
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 78245d60d8bc..0f45633bd634 100644..100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -740,13 +740,6 @@ ipv6_rt_add()
 	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
 	log_test $? 2 "Attempt to add duplicate route - reject route"
 
-	# iproute2 prepend only sets NLM_F_CREATE
-	# - adds a new route; does NOT convert existing route to ECMP
-	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
-	run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2"
-	check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
-	log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)"
-
 	# route append with same prefix adds a new route
 	# - iproute2 sets NLM_F_CREATE | NLM_F_APPEND
 	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
@@ -754,27 +747,6 @@ ipv6_rt_add()
 	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
 	log_test $? 0 "Append nexthop to existing route - gw"
 
-	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
-	run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
-	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1"
-	log_test $? 0 "Append nexthop to existing route - dev only"
-
-	# multipath route can not have a nexthop that is a reject route
-	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
-	run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64"
-	log_test $? 2 "Append nexthop to existing route - reject route"
-
-	# reject route can not be converted to multipath route
-	run_cmd "$IP -6 ro flush 2001:db8:104::/64"
-	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
-	run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2"
-	log_test $? 2 "Append nexthop to existing reject route - gw"
-
-	run_cmd "$IP -6 ro flush 2001:db8:104::/64"
-	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
-	run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
-	log_test $? 2 "Append nexthop to existing reject route - dev only"
-
 	# insert mpath directly
 	add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	check_route6  "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
@@ -819,13 +791,6 @@ ipv6_rt_replace_single()
 	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
 	log_test $? 0 "Single path with multipath"
 
-	# single path with reject
-	#
-	add_initial_route6 "nexthop via 2001:db8:101::2"
-	run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
-	check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
-	log_test $? 0 "Single path with reject route"
-
 	# single path with single path using MULTIPATH attribute
 	#
 	add_initial_route6 "via 2001:db8:101::2"
@@ -873,12 +838,6 @@ ipv6_rt_replace_mpath()
 	check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
 	log_test $? 0 "Multipath with single path via multipath attribute"
 
-	# multipath with reject
-	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
-	run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
-	check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
-	log_test $? 0 "Multipath with reject route"
-
 	# route replace fails - invalid nexthop 1
 	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 77f762780199..e8c5dff448eb 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -402,7 +402,7 @@ int main(int argc, char *argv[])
 		exit(1);
 	}
 
-	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	fd = socket(cfg_family, SOCK_STREAM, 0);
 	if (fd == -1) {
 		perror("socket");
 		exit(1);
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 792fa4d0285e..850767befa47 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -35,9 +35,6 @@ run_udp() {
 
 	echo "udp gso"
 	run_in_netns ${args} -S
-
-	echo "udp gso zerocopy"
-	run_in_netns ${args} -S -z
 }
 
 run_tcp() {
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index c15f270e121d..65541c21a544 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 #
-# Usage: configinit.sh config-spec-file [ build output dir ]
+# Usage: configinit.sh config-spec-file build-output-dir results-dir
 #
 # Create a .config file from the spec file.  Run from the kernel source tree.
 # Exits with 0 if all went well, with 1 if all went well but the config
@@ -40,20 +40,18 @@ mkdir $T
 
 c=$1
 buildloc=$2
+resdir=$3
 builddir=
-if test -n $buildloc
+if echo $buildloc | grep -q '^O='
 then
-	if echo $buildloc | grep -q '^O='
+	builddir=`echo $buildloc | sed -e 's/^O=//'`
+	if test ! -d $builddir
 	then
-		builddir=`echo $buildloc | sed -e 's/^O=//'`
-		if test ! -d $builddir
-		then
-			mkdir $builddir
-		fi
-	else
-		echo Bad build directory: \"$buildloc\"
-		exit 2
+		mkdir $builddir
 	fi
+else
+	echo Bad build directory: \"$buildloc\"
+	exit 2
 fi
 
 sed -e 's/^\(CONFIG[0-9A-Z_]*\)=.*$/grep -v "^# \1" |/' < $c > $T/u.sh
@@ -61,12 +59,12 @@ sed -e 's/^\(CONFIG[0-9A-Z_]*=\).*$/grep -v \1 |/' < $c >> $T/u.sh
 grep '^grep' < $T/u.sh > $T/upd.sh
 echo "cat - $c" >> $T/upd.sh
 make mrproper
-make $buildloc distclean > $builddir/Make.distclean 2>&1
-make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1
+make $buildloc distclean > $resdir/Make.distclean 2>&1
+make $buildloc $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1
 mv $builddir/.config $builddir/.config.sav
 sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
 cp $builddir/.config $builddir/.config.new
-yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err
+yes '' | make $buildloc oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err
 
 # verify new config matches specification.
 configcheck.sh $builddir/.config $c
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 34d126734cde..9115fcdb5617 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -2,7 +2,7 @@
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
-# Usage: kvm-build.sh config-template build-dir
+# Usage: kvm-build.sh config-template build-dir resdir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -29,6 +29,7 @@ then
 	exit 1
 fi
 builddir=${2}
+resdir=${3}
 
 T=${TMPDIR-/tmp}/test-linux.sh.$$
 trap 'rm -rf $T' 0
@@ -41,19 +42,19 @@ CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_CONSOLE=y
 ___EOF___
 
-configinit.sh $T/config O=$builddir
+configinit.sh $T/config O=$builddir $resdir
 retval=$?
 if test $retval -gt 1
 then
 	exit 2
 fi
 ncpus=`cpus2use.sh`
-make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $builddir/Make.out 2>&1
+make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $resdir/Make.out 2>&1
 retval=$?
-if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out
+if test $retval -ne 0 || grep "rcu[^/]*": < $resdir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $resdir/Make.out
 then
 	echo Kernel build error
-	egrep "Stop|Error|error:|warning:" < $builddir/Make.out
+	egrep "Stop|Error|error:|warning:" < $resdir/Make.out
 	echo Run aborted.
 	exit 3
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 477ecb1293ab..0fa8a61ccb7b 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -70,4 +70,5 @@ else
 	else
 		print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
 	fi
+	echo $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i > $i/console.log.rcu.diags
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index c27e97824163..c9bab57a77eb 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -39,6 +39,7 @@ do
 			head -1 $resdir/log
 		fi
 		TORTURE_SUITE="`cat $i/../TORTURE_SUITE`"
+		rm -f $i/console.log.*.diags
 		kvm-recheck-${TORTURE_SUITE}.sh $i
 		if test -f "$i/console.log"
 		then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index c5b0f94341d9..f7247ee00514 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -98,14 +98,15 @@ then
 	ln -s $base_resdir/.config $resdir  # for kvm-recheck.sh
 	# Arch-independent indicator
 	touch $resdir/builtkernel
-elif kvm-build.sh $T/Kc2 $builddir
+elif kvm-build.sh $T/Kc2 $builddir $resdir
 then
 	# Had to build a kernel for this test.
 	QEMU="`identify_qemu $builddir/vmlinux`"
 	BOOT_IMAGE="`identify_boot_image $QEMU`"
-	cp $builddir/Make*.out $resdir
 	cp $builddir/vmlinux $resdir
 	cp $builddir/.config $resdir
+	cp $builddir/Module.symvers $resdir > /dev/null || :
+	cp $builddir/System.map $resdir > /dev/null || :
 	if test -n "$BOOT_IMAGE"
 	then
 		cp $builddir/$BOOT_IMAGE $resdir
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 56610dbbdf73..5a7a62d76a50 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -347,7 +347,7 @@ function dump(first, pastlast, batchnum)
 	print "needqemurun="
 	jn=1
 	for (j = first; j < pastlast; j++) {
-		builddir=KVM "/b" jn
+		builddir=KVM "/b1"
 		cpusr[jn] = cpus[j];
 		if (cfrep[cf[j]] == "") {
 			cfr[jn] = cf[j];
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 17293436f551..84933f6aed77 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -163,6 +163,13 @@ then
 	print_warning Summary: $summary
 	cat $T.diags >> $file.diags
 fi
+for i in $file.*.diags
+do
+	if test -f "$i"
+	then
+		cat $i >> $file.diags
+	fi
+done
 if ! test -s $file.diags
 then
 	rm -f $file.diags
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
index 5d2cc0bd50a0..5c3213cc3ad7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
@@ -1,5 +1,5 @@
-rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
-rcutree.gp_preinit_delay=3
+rcutorture.onoff_interval=200 rcutorture.onoff_holdoff=30
+rcutree.gp_preinit_delay=12
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
 rcutree.kthread_prio=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
deleted file mode 100644
index 883149b5f2d1..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
+++ /dev/null
@@ -1 +0,0 @@
-rcutree.rcu_fanout_exact=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 24ec91041957..7bab8246392b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -39,7 +39,7 @@ rcutorture_param_onoff () {
 	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
 	then
 		echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
-		echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+		echo rcutorture.onoff_interval=1000 rcutorture.onoff_holdoff=30
 	fi
 }
 
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 615252331813..642d4e12abea 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -90,6 +90,30 @@ unsigned int yield_mod_cnt, nr_abort;
 #error "Unsupported architecture"
 #endif
 
+#elif defined(__s390__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1]"m"(loop_cnt[1]) \
+	, [loop_cnt_2]"m"(loop_cnt[2]) \
+	, [loop_cnt_3]"m"(loop_cnt[3]) \
+	, [loop_cnt_4]"m"(loop_cnt[4]) \
+	, [loop_cnt_5]"m"(loop_cnt[5]) \
+	, [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG	"r12"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"l %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"ltr %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG "\n\t" \
+	"je 333f\n\t" \
+	"222:\n\t" \
+	"ahi %%" INJECT_ASM_REG ", -1\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
 #elif defined(__ARMEL__)
 
 #define RSEQ_INJECT_INPUT \
@@ -114,6 +138,26 @@ unsigned int yield_mod_cnt, nr_abort;
 	"bne 222b\n\t" \
 	"333:\n\t"
 
+#elif defined(__AARCH64EL__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1] "Qo" (loop_cnt[1]) \
+	, [loop_cnt_2] "Qo" (loop_cnt[2]) \
+	, [loop_cnt_3] "Qo" (loop_cnt[3]) \
+	, [loop_cnt_4] "Qo" (loop_cnt[4]) \
+	, [loop_cnt_5] "Qo" (loop_cnt[5]) \
+	, [loop_cnt_6] "Qo" (loop_cnt[6])
+
+#define INJECT_ASM_REG	RSEQ_ASM_TMP_REG32
+
+#define RSEQ_INJECT_ASM(n) \
+	"	ldr	" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n"	\
+	"	cbz	" INJECT_ASM_REG ", 333f\n"			\
+	"222:\n"							\
+	"	sub	" INJECT_ASM_REG ", " INJECT_ASM_REG ", #1\n"	\
+	"	cbnz	" INJECT_ASM_REG ", 222b\n"			\
+	"333:\n"
+
 #elif __PPC__
 
 #define RSEQ_INJECT_INPUT \
diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h
new file mode 100644
index 000000000000..954f34671ca6
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-arm64.h
@@ -0,0 +1,594 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-arm64.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2018 - Will Deacon <will.deacon@arm.com>
+ */
+
+#define RSEQ_SIG	0xd428bc00	/* BRK #0x45E0 */
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("dmb ish" ::: "memory")
+#define rseq_smp_rmb()	__asm__ __volatile__ ("dmb ishld" ::: "memory")
+#define rseq_smp_wmb()	__asm__ __volatile__ ("dmb ishst" ::: "memory")
+
+#define rseq_smp_load_acquire(p)						\
+__extension__ ({								\
+	__typeof(*p) ____p1;							\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		asm volatile ("ldarb %w0, %1"					\
+			: "=r" (*(__u8 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	case 2:									\
+		asm volatile ("ldarh %w0, %1"					\
+			: "=r" (*(__u16 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	case 4:									\
+		asm volatile ("ldar %w0, %1"					\
+			: "=r" (*(__u32 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	case 8:									\
+		asm volatile ("ldar %0, %1"					\
+			: "=r" (*(__u64 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	}									\
+	____p1;									\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)						\
+do {										\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		asm volatile ("stlrb %w1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u8)v)					\
+				: "memory");					\
+		break;								\
+	case 2:									\
+		asm volatile ("stlrh %w1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u16)v)				\
+				: "memory");					\
+		break;								\
+	case 4:									\
+		asm volatile ("stlr %w1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u32)v)				\
+				: "memory");					\
+		break;								\
+	case 8:									\
+		asm volatile ("stlr %1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u64)v)				\
+				: "memory");					\
+		break;								\
+	}									\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#define RSEQ_ASM_TMP_REG32	"w15"
+#define RSEQ_ASM_TMP_REG	"x15"
+#define RSEQ_ASM_TMP_REG_2	"x14"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip,		\
+				post_commit_offset, abort_ip)			\
+	"	.pushsection	__rseq_table, \"aw\"\n"				\
+	"	.balign	32\n"							\
+	__rseq_str(label) ":\n"							\
+	"	.long	" __rseq_str(version) ", " __rseq_str(flags) "\n"	\
+	"	.quad	" __rseq_str(start_ip) ", "				\
+			  __rseq_str(post_commit_offset) ", "			\
+			  __rseq_str(abort_ip) "\n"				\
+	"	.popsection\n"
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip)	\
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,			\
+				(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)			\
+	RSEQ_INJECT_ASM(1)							\
+	"	adrp	" RSEQ_ASM_TMP_REG ", " __rseq_str(cs_label) "\n"	\
+	"	add	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", :lo12:" __rseq_str(cs_label) "\n"			\
+	"	str	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(rseq_cs) "]\n"	\
+	__rseq_str(label) ":\n"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, abort_label)				\
+	"	b	222f\n"							\
+	"	.inst 	"	__rseq_str(RSEQ_SIG) "\n"			\
+	__rseq_str(label) ":\n"							\
+	"	b	%l[" __rseq_str(abort_label) "]\n"			\
+	"222:\n"
+
+#define RSEQ_ASM_OP_STORE(value, var)						\
+	"	str	%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_STORE_RELEASE(value, var)					\
+	"	stlr	%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label)			\
+	RSEQ_ASM_OP_STORE(value, var)						\
+	__rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_FINAL_STORE_RELEASE(value, var, post_commit_label)		\
+	RSEQ_ASM_OP_STORE_RELEASE(value, var)					\
+	__rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_CMPEQ(var, expect, label)					\
+	"	ldr	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"		\
+	"	sub	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(expect) "]\n"				\
+	"	cbnz	" RSEQ_ASM_TMP_REG ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_OP_CMPEQ32(var, expect, label)					\
+	"	ldr	" RSEQ_ASM_TMP_REG32 ", %[" __rseq_str(var) "]\n"	\
+	"	sub	" RSEQ_ASM_TMP_REG32 ", " RSEQ_ASM_TMP_REG32		\
+			", %w[" __rseq_str(expect) "]\n"			\
+	"	cbnz	" RSEQ_ASM_TMP_REG32 ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_OP_CMPNE(var, expect, label)					\
+	"	ldr	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"		\
+	"	sub	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(expect) "]\n"				\
+	"	cbz	" RSEQ_ASM_TMP_REG ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)			\
+	RSEQ_INJECT_ASM(2)							\
+	RSEQ_ASM_OP_CMPEQ32(current_cpu_id, cpu_id, label)
+
+#define RSEQ_ASM_OP_R_LOAD(var)							\
+	"	ldr	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_R_STORE(var)						\
+	"	str	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_R_LOAD_OFF(offset)						\
+	"	ldr	" RSEQ_ASM_TMP_REG ", [" RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(offset) "]]\n"
+
+#define RSEQ_ASM_OP_R_ADD(count)						\
+	"	add	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(count) "]\n"
+
+#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label)			\
+	"	str	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"		\
+	__rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)					\
+	"	cbz	%[" __rseq_str(len) "], 333f\n"				\
+	"	mov	" RSEQ_ASM_TMP_REG_2 ", %[" __rseq_str(len) "]\n"	\
+	"222:	sub	" RSEQ_ASM_TMP_REG_2 ", " RSEQ_ASM_TMP_REG_2 ", #1\n"	\
+	"	ldrb	" RSEQ_ASM_TMP_REG32 ", [%[" __rseq_str(src) "]"	\
+			", " RSEQ_ASM_TMP_REG_2 "]\n"				\
+	"	strb	" RSEQ_ASM_TMP_REG32 ", [%[" __rseq_str(dst) "]"	\
+			", " RSEQ_ASM_TMP_REG_2 "]\n"				\
+	"	cbnz	" RSEQ_ASM_TMP_REG_2 ", 222b\n"				\
+	"333:\n"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"Qo" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       off_t voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPNE(v, expectnot, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPNE(v, expectnot, %l[error2])
+#endif
+		RSEQ_ASM_OP_R_LOAD(v)
+		RSEQ_ASM_OP_R_STORE(load)
+		RSEQ_ASM_OP_R_LOAD_OFF(voffp)
+		RSEQ_ASM_OP_R_FINAL_STORE(v, 3)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"Qo" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [load]		"Qo" (*load),
+		  [voffp]		"r" (voffp)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+		RSEQ_ASM_OP_R_LOAD(v)
+		RSEQ_ASM_OP_R_ADD(count)
+		RSEQ_ASM_OP_R_FINAL_STORE(v, 3)
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"Qo" (*v),
+		  [count]		"r" (count)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+				 intptr_t *v2, intptr_t newv2,
+				 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_STORE(newv2, v2)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [v2]			"Qo" (*v2),
+		  [newv2]		"r" (newv2)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+					 intptr_t *v2, intptr_t newv2,
+					 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_STORE(newv2, v2)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [v2]			"Qo" (*v2),
+		  [newv2]		"r" (newv2)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+			      intptr_t *v2, intptr_t expect2,
+			      intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[cmpfail])
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+		RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[error3])
+#endif
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"Qo" (*v),
+		  [expect]		"r" (expect),
+		  [v2]			"Qo" (*v2),
+		  [expect2]		"r" (expect2),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+error3:
+	rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+				 void *dst, void *src, size_t len,
+				 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG, RSEQ_ASM_TMP_REG_2
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+					 void *dst, void *src, size_t len,
+					 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG, RSEQ_ASM_TMP_REG_2
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
new file mode 100644
index 000000000000..1069e85258ce
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -0,0 +1,513 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+
+#define RSEQ_SIG	0x53053053
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("bcr 15,0" ::: "memory")
+#define rseq_smp_rmb()	rseq_smp_mb()
+#define rseq_smp_wmb()	rseq_smp_mb()
+
+#define rseq_smp_load_acquire(p)					\
+__extension__ ({							\
+	__typeof(*p) ____p1 = RSEQ_READ_ONCE(*p);			\
+	rseq_barrier();							\
+	____p1;								\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)					\
+do {									\
+	rseq_barrier();							\
+	RSEQ_WRITE_ONCE(*p, v);						\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#ifdef __s390x__
+
+#define LONG_L			"lg"
+#define LONG_S			"stg"
+#define LONG_LT_R		"ltgr"
+#define LONG_CMP		"cg"
+#define LONG_CMP_R		"cgr"
+#define LONG_ADDI		"aghi"
+#define LONG_ADD_R		"agr"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_table, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"
+
+#elif __s390__
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_table, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"
+
+#define LONG_L			"l"
+#define LONG_S			"st"
+#define LONG_LT_R		"ltr"
+#define LONG_CMP		"c"
+#define LONG_CMP_R		"cr"
+#define LONG_ADDI		"ahi"
+#define LONG_ADD_R		"ar"
+
+#endif
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,		\
+				(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)		\
+		RSEQ_INJECT_ASM(1)					\
+		"larl %%r0, " __rseq_str(cs_label) "\n\t"		\
+		LONG_S " %%r0, %[" __rseq_str(rseq_cs) "]\n\t"		\
+		__rseq_str(label) ":\n\t"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)		\
+		RSEQ_INJECT_ASM(2)					\
+		"c %[" __rseq_str(cpu_id) "], %[" __rseq_str(current_cpu_id) "]\n\t" \
+		"jnz " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		".long " __rseq_str(RSEQ_SIG) "\n\t"			\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"j %l[" __rseq_str(abort_label) "]\n\t"			\
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"j %l[" __rseq_str(cmpfail_label) "]\n\t"		\
+		".popsection\n\t"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/*
+ * Compare @v against @expectnot. When it does _not_ match, load @v
+ * into @load, and store the content of *@v + voffp into @v.
+ */
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       off_t voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " %%r1, %[v]\n\t"
+		LONG_CMP_R " %%r1, %[expectnot]\n\t"
+		"je %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " %%r1, %[v]\n\t"
+		LONG_CMP_R " %%r1, %[expectnot]\n\t"
+		"je %l[error2]\n\t"
+#endif
+		LONG_S " %%r1, %[load]\n\t"
+		LONG_ADD_R " %%r1, %[voffp]\n\t"
+		LONG_L " %%r1, 0(%%r1)\n\t"
+		/* final store */
+		LONG_S " %%r1, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"r" (voffp),
+		  [load]		"m" (*load)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0", "r1"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+		LONG_L " %%r0, %[v]\n\t"
+		LONG_ADD_R " %%r0, %[count]\n\t"
+		/* final store */
+		LONG_S " %%r0, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [count]		"r" (count)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+				 intptr_t *v2, intptr_t newv2,
+				 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* try store */
+		LONG_S " %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+					 intptr_t *v2, intptr_t newv2,
+					 intptr_t newv, int cpu)
+{
+	return rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2, newv, cpu);
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+			      intptr_t *v2, intptr_t expect2,
+			      intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+		LONG_CMP " %[expect2], %[v2]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+		LONG_CMP " %[expect2], %[v2]\n\t"
+		"jnz %l[error3]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+				 void *dst, void *src, size_t len,
+				 intptr_t newv, int cpu)
+{
+	uint64_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		LONG_S " %[src], %[rseq_scratch0]\n\t"
+		LONG_S " %[dst], %[rseq_scratch1]\n\t"
+		LONG_S " %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz 7f\n\t"
+#endif
+		/* try memcpy */
+		LONG_LT_R " %[len], %[len]\n\t"
+		"jz 333f\n\t"
+		"222:\n\t"
+		"ic %%r0,0(%[src])\n\t"
+		"stc %%r0,0(%[dst])\n\t"
+		LONG_ADDI " %[src], 1\n\t"
+		LONG_ADDI " %[dst], 1\n\t"
+		LONG_ADDI " %[len], -1\n\t"
+		"jnz 222b\n\t"
+		"333:\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		LONG_L " %[len], %[rseq_scratch2]\n\t"
+		LONG_L " %[dst], %[rseq_scratch1]\n\t"
+		LONG_L " %[src], %[rseq_scratch0]\n\t"
+		RSEQ_ASM_DEFINE_ABORT(4,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			abort)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			error2)
+#endif
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv),
+		  /* try memcpy input */
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len),
+		  [rseq_scratch0]	"m" (rseq_scratch[0]),
+		  [rseq_scratch1]	"m" (rseq_scratch[1]),
+		  [rseq_scratch2]	"m" (rseq_scratch[2])
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+					 void *dst, void *src, size_t len,
+					 intptr_t newv, int cpu)
+{
+	return rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len,
+					    newv, cpu);
+}
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index a4684112676c..c72eb70f9b52 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -71,10 +71,14 @@ extern __thread volatile struct rseq __rseq_abi;
 #include <rseq-x86.h>
 #elif defined(__ARMEL__)
 #include <rseq-arm.h>
+#elif defined (__AARCH64EL__)
+#include <rseq-arm64.h>
 #elif defined(__PPC__)
 #include <rseq-ppc.h>
 #elif defined(__mips__)
 #include <rseq-mips.h>
+#elif defined(__s390__)
+#include <rseq-s390.h>
 #else
 #error unsupported target
 #endif
@@ -133,17 +137,27 @@ static inline uint32_t rseq_current_cpu(void)
 	return cpu;
 }
 
+static inline void rseq_clear_rseq_cs(void)
+{
+#ifdef __LP64__
+	__rseq_abi.rseq_cs.ptr = 0;
+#else
+	__rseq_abi.rseq_cs.ptr.ptr32 = 0;
+#endif
+}
+
 /*
- * rseq_prepare_unload() should be invoked by each thread using rseq_finish*()
- * at least once between their last rseq_finish*() and library unload of the
- * library defining the rseq critical section (struct rseq_cs). This also
- * applies to use of rseq in code generated by JIT: rseq_prepare_unload()
- * should be invoked at least once by each thread using rseq_finish*() before
- * reclaim of the memory holding the struct rseq_cs.
+ * rseq_prepare_unload() should be invoked by each thread executing a rseq
+ * critical section at least once between their last critical section and
+ * library unload of the library defining the rseq critical section
+ * (struct rseq_cs). This also applies to use of rseq in code generated by
+ * JIT: rseq_prepare_unload() should be invoked at least once by each
+ * thread executing a rseq critical section before reclaim of the memory
+ * holding the struct rseq_cs.
  */
 static inline void rseq_prepare_unload(void)
 {
-	__rseq_abi.rseq_cs = 0;
+	rseq_clear_rseq_cs();
 }
 
 #endif  /* RSEQ_H_ */
diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c
index ca6cd146aafe..dcf73c5dab6e 100644
--- a/tools/testing/selftests/timers/raw_skew.c
+++ b/tools/testing/selftests/timers/raw_skew.c
@@ -134,6 +134,11 @@ int main(int argv, char **argc)
 	printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000)));
 
 	if (llabs(eppm - ppm) > 1000) {
+		if (tx1.offset || tx2.offset ||
+		    tx1.freq != tx2.freq || tx1.tick != tx2.tick) {
+			printf("	[SKIP]\n");
+			return ksft_exit_skip("The clock was adjusted externally. Shutdown NTPd or other time sync daemons\n");
+		}
 		printf("	[FAILED]\n");
 		return ksft_exit_fail();
 	}
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index 246145b84a12..4d9dc3f2fd70 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -610,21 +610,41 @@ static int test_valid_sigreturn(int cs_bits, bool use_16bit_ss, int force_ss)
 	 */
 	for (int i = 0; i < NGREG; i++) {
 		greg_t req = requested_regs[i], res = resulting_regs[i];
+
 		if (i == REG_TRAPNO || i == REG_IP)
 			continue;	/* don't care */
-		if (i == REG_SP) {
-			printf("\tSP: %llx -> %llx\n", (unsigned long long)req,
-			       (unsigned long long)res);
 
+		if (i == REG_SP) {
 			/*
-			 * In many circumstances, the high 32 bits of rsp
-			 * are zeroed.  For example, we could be a real
-			 * 32-bit program, or we could hit any of a number
-			 * of poorly-documented IRET or segmented ESP
-			 * oddities.  If this happens, it's okay.
+			 * If we were using a 16-bit stack segment, then
+			 * the kernel is a bit stuck: IRET only restores
+			 * the low 16 bits of ESP/RSP if SS is 16-bit.
+			 * The kernel uses a hack to restore bits 31:16,
+			 * but that hack doesn't help with bits 63:32.
+			 * On Intel CPUs, bits 63:32 end up zeroed, and, on
+			 * AMD CPUs, they leak the high bits of the kernel
+			 * espfix64 stack pointer.  There's very little that
+			 * the kernel can do about it.
+			 *
+			 * Similarly, if we are returning to a 32-bit context,
+			 * the CPU will often lose the high 32 bits of RSP.
 			 */
-			if (res == (req & 0xFFFFFFFF))
-				continue;  /* OK; not expected to work */
+
+			if (res == req)
+				continue;
+
+			if (cs_bits != 64 && ((res ^ req) & 0xFFFFFFFF) == 0) {
+				printf("[NOTE]\tSP: %llx -> %llx\n",
+				       (unsigned long long)req,
+				       (unsigned long long)res);
+				continue;
+			}
+
+			printf("[FAIL]\tSP mismatch: requested 0x%llx; got 0x%llx\n",
+			       (unsigned long long)requested_regs[i],
+			       (unsigned long long)resulting_regs[i]);
+			nerrs++;
+			continue;
 		}
 
 		bool ignore_reg = false;
@@ -654,25 +674,18 @@ static int test_valid_sigreturn(int cs_bits, bool use_16bit_ss, int force_ss)
 #endif
 
 		/* Sanity check on the kernel */
-		if (i == REG_CX && requested_regs[i] != resulting_regs[i]) {
+		if (i == REG_CX && req != res) {
 			printf("[FAIL]\tCX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n",
-			       (unsigned long long)requested_regs[i],
-			       (unsigned long long)resulting_regs[i]);
+			       (unsigned long long)req,
+			       (unsigned long long)res);
 			nerrs++;
 			continue;
 		}
 
-		if (requested_regs[i] != resulting_regs[i] && !ignore_reg) {
-			/*
-			 * SP is particularly interesting here.  The
-			 * usual cause of failures is that we hit the
-			 * nasty IRET case of returning to a 16-bit SS,
-			 * in which case bits 16:31 of the *kernel*
-			 * stack pointer persist in ESP.
-			 */
+		if (req != res && !ignore_reg) {
 			printf("[FAIL]\tReg %d mismatch: requested 0x%llx; got 0x%llx\n",
-			       i, (unsigned long long)requested_regs[i],
-			       (unsigned long long)resulting_regs[i]);
+			       i, (unsigned long long)req,
+			       (unsigned long long)res);
 			nerrs++;
 		}
 	}
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index 95dd14648ba5..0f395dfb7774 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -44,12 +44,25 @@
 
 /******************** Little Endian Handling ********************************/
 
-#define cpu_to_le16(x)  htole16(x)
-#define cpu_to_le32(x)  htole32(x)
+/*
+ * cpu_to_le16/32 are used when initializing structures, a context where a
+ * function call is not allowed. To solve this, we code cpu_to_le16/32 in a way
+ * that allows them to be used when initializing structures.
+ */
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define cpu_to_le16(x)  (x)
+#define cpu_to_le32(x)  (x)
+#else
+#define cpu_to_le16(x)  ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))
+#define cpu_to_le32(x)  \
+	((((x) & 0xff000000u) >> 24) | (((x) & 0x00ff0000u) >>  8) | \
+	(((x) & 0x0000ff00u) <<  8) | (((x) & 0x000000ffu) << 24))
+#endif
+
 #define le32_to_cpu(x)  le32toh(x)
 #define le16_to_cpu(x)  le16toh(x)
 
-
 /******************** Messages and Errors ***********************************/
 
 static const char argv0[] = "ffs-test";
diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h
index 0ac3caf90877..d0351f83aebe 100644
--- a/tools/virtio/asm/barrier.h
+++ b/tools/virtio/asm/barrier.h
@@ -13,8 +13,8 @@
 } while (0);
 /* Weak barriers should be used. If not - it's a bug */
 # define mb() abort()
-# define rmb() abort()
-# define wmb() abort()
+# define dma_rmb() abort()
+# define dma_wmb() abort()
 #else
 #error Please fill in barrier macros
 #endif
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
index fca8381bbe04..fb22bccfbc8a 100644
--- a/tools/virtio/linux/kernel.h
+++ b/tools/virtio/linux/kernel.h
@@ -52,6 +52,11 @@ static inline void *kmalloc(size_t s, gfp_t gfp)
 		return __kmalloc_fake;
 	return malloc(s);
 }
+static inline void *kmalloc_array(unsigned n, size_t s, gfp_t gfp)
+{
+	return kmalloc(n * s, gfp);
+}
+
 static inline void *kzalloc(size_t s, gfp_t gfp)
 {
 	void *p = kmalloc(s, gfp);
diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h
index 9a45f90e2d08..369ee308b668 100644
--- a/tools/virtio/linux/scatterlist.h
+++ b/tools/virtio/linux/scatterlist.h
@@ -36,7 +36,6 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
 	 */
 	BUG_ON((unsigned long) page & 0x03);
 #ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
 	BUG_ON(sg_is_chain(sg));
 #endif
 	sg->page_link = page_link | (unsigned long) page;
@@ -67,7 +66,6 @@ static inline void sg_set_page(struct scatterlist *sg, struct page *page,
 static inline struct page *sg_page(struct scatterlist *sg)
 {
 #ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
 	BUG_ON(sg_is_chain(sg));
 #endif
 	return (struct page *)((sg)->page_link & ~0x3);
@@ -116,9 +114,6 @@ static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
  **/
 static inline void sg_mark_end(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	/*
 	 * Set termination bit, clear potential chain bit
 	 */
@@ -136,17 +131,11 @@ static inline void sg_mark_end(struct scatterlist *sg)
  **/
 static inline void sg_unmark_end(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	sg->page_link &= ~0x02;
 }
 
 static inline struct scatterlist *sg_next(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	if (sg_is_last(sg))
 		return NULL;
 
@@ -160,13 +149,6 @@ static inline struct scatterlist *sg_next(struct scatterlist *sg)
 static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents)
 {
 	memset(sgl, 0, sizeof(*sgl) * nents);
-#ifdef CONFIG_DEBUG_SG
-	{
-		unsigned int i;
-		for (i = 0; i < nents; i++)
-			sgl[i].sg_magic = SG_MAGIC;
-	}
-#endif
 	sg_mark_end(&sgl[nents - 1]);
 }
 
diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c
index efc84cbe8277..5abbe9b3c652 100644
--- a/virt/kvm/arm/aarch32.c
+++ b/virt/kvm/arm/aarch32.c
@@ -108,9 +108,9 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
 {
 	unsigned long itbits, cond;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	bool is_arm = !(cpsr & COMPAT_PSR_T_BIT);
+	bool is_arm = !(cpsr & PSR_AA32_T_BIT);
 
-	if (is_arm || !(cpsr & COMPAT_PSR_IT_MASK))
+	if (is_arm || !(cpsr & PSR_AA32_IT_MASK))
 		return;
 
 	cond = (cpsr & 0xe000) >> 13;
@@ -123,7 +123,7 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
 	else
 		itbits = (itbits << 1) & 0x1f;
 
-	cpsr &= ~COMPAT_PSR_IT_MASK;
+	cpsr &= ~PSR_AA32_IT_MASK;
 	cpsr |= cond << 13;
 	cpsr |= (itbits & 0x1c) << (10 - 2);
 	cpsr |= (itbits & 0x3) << 25;
@@ -138,7 +138,7 @@ void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
 	bool is_thumb;
 
-	is_thumb = !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_T_BIT);
+	is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT);
 	if (is_thumb && !is_wide_instr)
 		*vcpu_pc(vcpu) += 2;
 	else
@@ -164,16 +164,16 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
 	unsigned long cpsr;
 	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
-	bool is_thumb = (new_spsr_value & COMPAT_PSR_T_BIT);
+	bool is_thumb = (new_spsr_value & PSR_AA32_T_BIT);
 	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
 	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
-	cpsr = mode | COMPAT_PSR_I_BIT;
+	cpsr = mode | PSR_AA32_I_BIT;
 
 	if (sctlr & (1 << 30))
-		cpsr |= COMPAT_PSR_T_BIT;
+		cpsr |= PSR_AA32_T_BIT;
 	if (sctlr & (1 << 25))
-		cpsr |= COMPAT_PSR_E_BIT;
+		cpsr |= PSR_AA32_E_BIT;
 
 	*vcpu_cpsr(vcpu) = cpsr;
 
@@ -192,7 +192,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 
 void kvm_inject_undef32(struct kvm_vcpu *vcpu)
 {
-	prepare_fault32(vcpu, COMPAT_PSR_MODE_UND, 4);
+	prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4);
 }
 
 /*
@@ -216,7 +216,7 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 		fsr = &vcpu_cp15(vcpu, c5_DFSR);
 	}
 
-	prepare_fault32(vcpu, COMPAT_PSR_MODE_ABT | COMPAT_PSR_A_BIT, vect_offset);
+	prepare_fault32(vcpu, PSR_AA32_MODE_ABT | PSR_AA32_A_BIT, vect_offset);
 
 	*far = addr;
 
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 04e554cae3a2..108250e4d376 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -604,7 +604,7 @@ void kvm_arm_resume_guest(struct kvm *kvm)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		vcpu->arch.pause = false;
-		swake_up(kvm_arch_vcpu_wq(vcpu));
+		swake_up_one(kvm_arch_vcpu_wq(vcpu));
 	}
 }
 
@@ -612,7 +612,7 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 {
 	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
-	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+	swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
 				       (!vcpu->arch.pause)));
 
 	if (vcpu->arch.power_off || vcpu->arch.pause) {
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index c95ab4c5a475..9b73d3ad918a 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -155,7 +155,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
-	swake_up(wq);
+	swake_up_one(wq);
 
 	return PSCI_RET_SUCCESS;
 }
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 57bcb27dcf30..23c2519c5b32 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -107,7 +107,7 @@ static void async_pf_execute(struct work_struct *work)
 	trace_kvm_async_pf_completed(addr, gva);
 
 	if (swq_has_sleeper(&vcpu->wq))
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 
 	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 90d30fbe95ae..b20b751286fc 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -119,8 +119,12 @@ irqfd_shutdown(struct work_struct *work)
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(work, struct kvm_kernel_irqfd, shutdown);
+	struct kvm *kvm = irqfd->kvm;
 	u64 cnt;
 
+	/* Make sure irqfd has been initalized in assign path. */
+	synchronize_srcu(&kvm->irq_srcu);
+
 	/*
 	 * Synchronize with the wait-queue and unhook ourselves to prevent
 	 * further events.
@@ -387,7 +391,6 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	irqfd_update(kvm, irqfd);
-	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	list_add_tail(&irqfd->list, &kvm->irqfds.items);
 
@@ -402,11 +405,6 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	if (events & EPOLLIN)
 		schedule_work(&irqfd->inject);
 
-	/*
-	 * do not drop the file until the irqfd is fully initialized, otherwise
-	 * we might race against the EPOLLHUP
-	 */
-	fdput(f);
 #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
 	if (kvm_arch_has_irq_bypass()) {
 		irqfd->consumer.token = (void *)irqfd->eventfd;
@@ -421,6 +419,13 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	}
 #endif
 
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+
+	/*
+	 * do not drop the file until the irqfd is fully initialized, otherwise
+	 * we might race against the EPOLLHUP
+	 */
+	fdput(f);
 	return 0;
 
 fail:
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8b47507faab5..3d233ebfbee9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2172,7 +2172,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	kvm_arch_vcpu_blocking(vcpu);
 
 	for (;;) {
-		prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+		prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
@@ -2214,7 +2214,7 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
 	if (swq_has_sleeper(wqp)) {
-		swake_up(wqp);
+		swake_up_one(wqp);
 		++vcpu->stat.halt_wakeup;
 		return true;
 	}